id	sid	tid	token	lemma	pos
cana-4022	1	1	communications	communication	NOUN
cana-4022	1	2	on	on	ADP
cana-4022	1	3	applied	apply	VERB
cana-4022	1	4	nonlinear	nonlinear	ADJ
cana-4022	1	5	analysis	analysis	NOUN
cana-4022	1	6	issn	issn	NOUN
cana-4022	1	7	:	:	PUNCT
cana-4022	1	8	1074	1074	NUM
cana-4022	1	9	-	-	PUNCT
cana-4022	1	10	133x	133x	NUM
cana-4022	1	11	vol	vol	NOUN
cana-4022	1	12	32	32	NUM
cana-4022	1	13	no	no	NOUN
cana-4022	1	14	.	.	PUNCT
cana-4022	2	1	9s	9s	NUM
cana-4022	2	2	(	(	PUNCT
cana-4022	2	3	2025	2025	NUM
cana-4022	2	4	)	)	PUNCT
cana-4022	2	5	860	860	NUM
cana-4022	2	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-4022	2	7	supervised	supervise	VERB
cana-4022	2	8	vs.	vs.	ADP
cana-4022	2	9	unsupervised	unsupervised	ADJ
cana-4022	2	10	learning	learning	NOUN
cana-4022	2	11	:	:	PUNCT
cana-4022	2	12	a	a	DET
cana-4022	2	13	comparative	comparative	ADJ
cana-4022	2	14	study	study	NOUN
cana-4022	2	15	in	in	ADP
cana-4022	2	16	modern	modern	ADJ
cana-4022	2	17	ai	ai	PROPN
cana-4022	2	18	system	system	NOUN
cana-4022	2	19	prof	prof	NOUN
cana-4022	2	20	.	.	PUNCT
cana-4022	3	1	roshni	roshni	PROPN
cana-4022	3	2	verma1	verma1	PROPN
cana-4022	3	3	,	,	PUNCT
cana-4022	3	4	dr	dr	PROPN
cana-4022	3	5	.	.	PROPN
cana-4022	3	6	ritu	ritu	PROPN
cana-4022	3	7	maheshwari2	maheshwari2	PROPN
cana-4022	3	8	,	,	PUNCT
cana-4022	3	9	prof	prof	PROPN
cana-4022	3	10	.	.	PUNCT
cana-4022	4	1	deepmala	deepmala	PROPN
cana-4022	4	2	manore3	manore3	PROPN
cana-4022	4	3	,	,	PUNCT
cana-4022	4	4	dr	dr	PROPN
cana-4022	4	5	.	.	PROPN
cana-4022	4	6	pinky	pinky	PROPN
cana-4022	4	7	sadashiv	sadashiv	PROPN
cana-4022	4	8	rane4	rane4	PROPN
cana-4022	4	9	,	,	PUNCT
cana-4022	4	10	mr	mr	PROPN
cana-4022	4	11	.	.	PROPN
cana-4022	4	12	monark	monark	PROPN
cana-4022	4	13	raikwar5	raikwar5	PROPN
cana-4022	5	1	1assistant	1assistant	NUM
cana-4022	5	2	professor	professor	NOUN
cana-4022	5	3	,	,	PUNCT
cana-4022	5	4	medi	medi	NOUN
cana-4022	5	5	-	-	PUNCT
cana-4022	5	6	caps	cap	NOUN
cana-4022	5	7	university	university	NOUN
cana-4022	5	8	,	,	PUNCT
cana-4022	5	9	indore	indore	NOUN
cana-4022	5	10	,	,	PUNCT
cana-4022	5	11	roshni.verma@medicaps.ac.in	roshni.verma@medicaps.ac.in	NUM
cana-4022	5	12	2assistant	2assistant	NUM
cana-4022	5	13	professor	professor	NOUN
cana-4022	5	14	,	,	PUNCT
cana-4022	5	15	medi	medi	NOUN
cana-4022	5	16	-	-	PUNCT
cana-4022	5	17	caps	cap	NOUN
cana-4022	5	18	university	university	NOUN
cana-4022	5	19	,	,	PUNCT
cana-4022	5	20	indore	indore	NOUN
cana-4022	5	21	,	,	PUNCT
cana-4022	5	22	ritu.maheshwari@medicaps.ac.in	ritu.maheshwari@medicaps.ac.in	NUM
cana-4022	5	23	3assistant	3assistant	NUM
cana-4022	5	24	professor	professor	NOUN
cana-4022	5	25	,	,	PUNCT
cana-4022	5	26	medi	medi	NOUN
cana-4022	5	27	-	-	PUNCT
cana-4022	5	28	caps	cap	NOUN
cana-4022	5	29	university	university	NOUN
cana-4022	5	30	,	,	PUNCT
cana-4022	5	31	indore	indore	NOUN
cana-4022	5	32	,	,	PUNCT
cana-4022	5	33	deepmala.manore@medicaps.ac.in	deepmala.manore@medicaps.ac.in	PUNCT
cana-4022	5	34	4assistant	4assistant	NUM
cana-4022	5	35	professor	professor	NOUN
cana-4022	5	36	,	,	PUNCT
cana-4022	5	37	medi	medi	NOUN
cana-4022	5	38	-	-	PUNCT
cana-4022	5	39	caps	cap	NOUN
cana-4022	5	40	university	university	NOUN
cana-4022	5	41	,	,	PUNCT
cana-4022	5	42	indore	indore	PROPN
cana-4022	5	43	,	,	PUNCT
cana-4022	5	44	pinky.rane@medicaps.ac	pinky.rane@medicaps.ac	VERB
cana-4022	5	45	5symbiosis	5symbiosis	NUM
cana-4022	5	46	university	university	NOUN
cana-4022	5	47	of	of	ADP
cana-4022	5	48	applied	apply	VERB
cana-4022	5	49	sciences	science	NOUN
cana-4022	5	50	,	,	PUNCT
cana-4022	5	51	raikwarmonark@gmail.com	raikwarmonark@gmail.com	PROPN
cana-4022	5	52	article	article	NOUN
cana-4022	5	53	history	history	NOUN
cana-4022	5	54	:	:	PUNCT
cana-4022	5	55	received	receive	VERB
cana-4022	5	56	:	:	PUNCT
cana-4022	5	57	12	12	NUM
cana-4022	5	58	-	-	SYM
cana-4022	5	59	01	01	NUM
cana-4022	5	60	-	-	PUNCT
cana-4022	5	61	2025	2025	NUM
cana-4022	5	62	revised	revise	VERB
cana-4022	5	63	:	:	PUNCT
cana-4022	5	64	15	15	NUM
cana-4022	5	65	-	-	NUM
cana-4022	5	66	02	02	NUM
cana-4022	5	67	-	-	PUNCT
cana-4022	5	68	2025	2025	NUM
cana-4022	5	69	accepted	accept	VERB
cana-4022	5	70	:	:	PUNCT
cana-4022	5	71	01	01	NUM
cana-4022	5	72	-	-	SYM
cana-4022	5	73	03	03	NUM
cana-4022	5	74	-	-	PUNCT
cana-4022	5	75	2025	2025	NUM
cana-4022	5	76	abstract	abstract	NOUN
cana-4022	5	77	:	:	PUNCT
cana-4022	5	78	the	the	DET
cana-4022	5	79	paper	paper	NOUN
cana-4022	5	80	examines	examine	VERB
cana-4022	5	81	the	the	DET
cana-4022	5	82	differences	difference	NOUN
cana-4022	5	83	between	between	ADP
cana-4022	5	84	supervised	supervised	ADJ
cana-4022	5	85	and	and	CCONJ
cana-4022	5	86	unsupervised	unsupervised	ADJ
cana-4022	5	87	learning	learning	NOUN
cana-4022	5	88	in	in	ADP
cana-4022	5	89	the	the	DET
cana-4022	5	90	modern	modern	ADJ
cana-4022	5	91	ai	ai	NOUN
cana-4022	5	92	context	context	NOUN
cana-4022	5	93	to	to	PART
cana-4022	5	94	evaluate	evaluate	VERB
cana-4022	5	95	the	the	DET
cana-4022	5	96	potential	potential	NOUN
cana-4022	5	97	of	of	ADP
cana-4022	5	98	the	the	DET
cana-4022	5	99	connecting	connect	VERB
cana-4022	5	100	approach	approach	NOUN
cana-4022	5	101	for	for	ADP
cana-4022	5	102	solving	solve	VERB
cana-4022	5	103	the	the	DET
cana-4022	5	104	research	research	NOUN
cana-4022	5	105	question	question	NOUN
cana-4022	5	106	of	of	ADP
cana-4022	5	107	choosing	choose	VERB
cana-4022	5	108	the	the	DET
cana-4022	5	109	most	most	ADV
cana-4022	5	110	suitable	suitable	ADJ
cana-4022	5	111	model	model	NOUN
cana-4022	5	112	for	for	ADP
cana-4022	5	113	an	an	DET
cana-4022	5	114	application	application	NOUN
cana-4022	5	115	.	.	PUNCT
cana-4022	6	1	in	in	ADP
cana-4022	6	2	the	the	DET
cana-4022	6	3	following	follow	VERB
cana-4022	6	4	study	study	NOUN
cana-4022	6	5	,	,	PUNCT
cana-4022	6	6	the	the	DET
cana-4022	6	7	quantitative	quantitative	ADJ
cana-4022	6	8	data	datum	NOUN
cana-4022	6	9	set	set	VERB
cana-4022	6	10	obtained	obtain	VERB
cana-4022	6	11	from	from	ADP
cana-4022	6	12	finance	finance	NOUN
cana-4022	6	13	,	,	PUNCT
cana-4022	6	14	healthcare	healthcare	PROPN
cana-4022	6	15	,	,	PUNCT
cana-4022	6	16	and	and	CCONJ
cana-4022	6	17	image	image	NOUN
cana-4022	6	18	recognition	recognition	NOUN
cana-4022	6	19	was	be	AUX
cana-4022	6	20	used	use	VERB
cana-4022	6	21	to	to	PART
cana-4022	6	22	analyze	analyze	VERB
cana-4022	6	23	the	the	DET
cana-4022	6	24	model	model	NOUN
cana-4022	6	25	performance	performance	NOUN
cana-4022	6	26	.	.	PUNCT
cana-4022	7	1	the	the	DET
cana-4022	7	2	tasks	task	NOUN
cana-4022	7	3	were	be	AUX
cana-4022	7	4	accomplished	accomplish	VERB
cana-4022	7	5	using	use	VERB
cana-4022	7	6	python	python	NOUN
cana-4022	7	7	along	along	ADP
cana-4022	7	8	with	with	ADP
cana-4022	7	9	tensorflow	tensorflow	NOUN
cana-4022	7	10	and	and	CCONJ
cana-4022	7	11	scikit	scikit	NOUN
cana-4022	7	12	-	-	PUNCT
cana-4022	7	13	learn	learn	NOUN
cana-4022	7	14	environment	environment	NOUN
cana-4022	7	15	where	where	SCONJ
cana-4022	7	16	the	the	DET
cana-4022	7	17	algorithms	algorithm	NOUN
cana-4022	7	18	used	use	VERB
cana-4022	7	19	were	be	AUX
cana-4022	7	20	decision	decision	NOUN
cana-4022	7	21	tree	tree	NOUN
cana-4022	7	22	,	,	PUNCT
cana-4022	7	23	support	support	VERB
cana-4022	7	24	vector	vector	NOUN
cana-4022	7	25	machine	machine	NOUN
cana-4022	7	26	,	,	PUNCT
cana-4022	7	27	k	k	ADJ
cana-4022	7	28	-	-	PUNCT
cana-4022	7	29	means	mean	VERB
cana-4022	7	30	clustering	clustering	NOUN
cana-4022	7	31	,	,	PUNCT
cana-4022	7	32	and	and	CCONJ
cana-4022	7	33	autoencoder	autoencoder	NOUN
cana-4022	7	34	.	.	PUNCT
cana-4022	8	1	thus	thus	ADV
cana-4022	8	2	,	,	PUNCT
cana-4022	8	3	the	the	DET
cana-4022	8	4	accuracy	accuracy	NOUN
cana-4022	8	5	of	of	ADP
cana-4022	8	6	the	the	DET
cana-4022	8	7	supervised	supervise	VERB
cana-4022	8	8	models	model	NOUN
cana-4022	8	9	is	be	AUX
cana-4022	8	10	higher	high	ADJ
cana-4022	8	11	,	,	PUNCT
cana-4022	8	12	about	about	ADV
cana-4022	8	13	92.4	92.4	NUM
cana-4022	8	14	%	%	NOUN
cana-4022	8	15	of	of	ADP
cana-4022	8	16	all	all	DET
cana-4022	8	17	datasets	dataset	NOUN
cana-4022	8	18	,	,	PUNCT
cana-4022	8	19	whereas	whereas	SCONJ
cana-4022	8	20	the	the	DET
cana-4022	8	21	unsupervised	unsupervised	ADJ
cana-4022	8	22	ones	one	NOUN
cana-4022	8	23	turned	turn	VERB
cana-4022	8	24	out	out	ADP
cana-4022	8	25	to	to	PART
cana-4022	8	26	vary	vary	VERB
cana-4022	8	27	from	from	ADP
cana-4022	8	28	65.8	65.8	NUM
cana-4022	8	29	%	%	NOUN
cana-4022	8	30	to	to	ADP
cana-4022	8	31	85.2	85.2	NUM
cana-4022	8	32	%	%	NOUN
cana-4022	8	33	.	.	PUNCT
cana-4022	9	1	on	on	ADP
cana-4022	9	2	the	the	DET
cana-4022	9	3	other	other	ADJ
cana-4022	9	4	hand	hand	NOUN
cana-4022	9	5	,	,	PUNCT
cana-4022	9	6	unsupervised	unsupervised	ADJ
cana-4022	9	7	learning	learn	VERB
cana-4022	9	8	out	out	ADP
cana-4022	9	9	competed	compete	VERB
cana-4022	9	10	itself	itself	PRON
cana-4022	9	11	in	in	ADP
cana-4022	9	12	the	the	DET
cana-4022	9	13	processing	processing	NOUN
cana-4022	9	14	of	of	ADP
cana-4022	9	15	the	the	DET
cana-4022	9	16	unlabeled	unlabele	VERB
cana-4022	9	17	data	datum	NOUN
cana-4022	9	18	especially	especially	ADV
cana-4022	9	19	in	in	ADP
cana-4022	9	20	the	the	DET
cana-4022	9	21	areas	area	NOUN
cana-4022	9	22	of	of	ADP
cana-4022	9	23	anomaly	anomaly	NOUN
cana-4022	9	24	detection	detection	NOUN
cana-4022	9	25	and	and	CCONJ
cana-4022	9	26	pattern	pattern	NOUN
cana-4022	9	27	identification	identification	NOUN
cana-4022	9	28	.	.	PUNCT
cana-4022	10	1	the	the	DET
cana-4022	10	2	paper	paper	NOUN
cana-4022	10	3	,	,	PUNCT
cana-4022	10	4	therefore	therefore	ADV
cana-4022	10	5	,	,	PUNCT
cana-4022	10	6	notes	note	VERB
cana-4022	10	7	that	that	SCONJ
cana-4022	10	8	whereas	whereas	SCONJ
cana-4022	10	9	high	high	ADJ
cana-4022	10	10	precision	precision	NOUN
cana-4022	10	11	is	be	AUX
cana-4022	10	12	promoted	promote	VERB
cana-4022	10	13	by	by	ADP
cana-4022	10	14	supervised	supervised	ADJ
cana-4022	10	15	learning	learning	NOUN
cana-4022	10	16	algorithm	algorithm	NOUN
cana-4022	10	17	,	,	PUNCT
cana-4022	10	18	approach	approach	NOUN
cana-4022	10	19	is	be	AUX
cana-4022	10	20	useful	useful	ADJ
cana-4022	10	21	in	in	ADP
cana-4022	10	22	exploratory	exploratory	ADJ
cana-4022	10	23	ones	one	NOUN
cana-4022	10	24	especially	especially	ADV
cana-4022	10	25	where	where	SCONJ
cana-4022	10	26	it	it	PRON
cana-4022	10	27	is	be	AUX
cana-4022	10	28	impossible	impossible	ADJ
cana-4022	10	29	to	to	PART
cana-4022	10	30	label	label	VERB
cana-4022	10	31	the	the	DET
cana-4022	10	32	data	datum	NOUN
cana-4022	10	33	.	.	PUNCT
cana-4022	11	1	these	these	DET
cana-4022	11	2	findings	finding	NOUN
cana-4022	11	3	help	help	VERB
cana-4022	11	4	to	to	PART
cana-4022	11	5	advance	advance	VERB
cana-4022	11	6	the	the	DET
cana-4022	11	7	knowledge	knowledge	NOUN
cana-4022	11	8	of	of	ADP
cana-4022	11	9	practice	practice	NOUN
cana-4022	11	10	regarding	regard	VERB
cana-4022	11	11	the	the	DET
cana-4022	11	12	effectiveness	effectiveness	NOUN
cana-4022	11	13	of	of	ADP
cana-4022	11	14	using	use	VERB
cana-4022	11	15	ai	ai	NOUN
cana-4022	11	16	in	in	ADP
cana-4022	11	17	real	real	ADJ
cana-4022	11	18	-	-	PUNCT
cana-4022	11	19	life	life	NOUN
cana-4022	11	20	settings	setting	NOUN
cana-4022	11	21	;	;	PUNCT
cana-4022	11	22	more	more	ADV
cana-4022	11	23	specifically	specifically	ADV
cana-4022	11	24	,	,	PUNCT
cana-4022	11	25	they	they	PRON
cana-4022	11	26	underscore	underscore	VERB
cana-4022	11	27	the	the	DET
cana-4022	11	28	relevance	relevance	NOUN
cana-4022	11	29	of	of	ADP
cana-4022	11	30	using	use	VERB
cana-4022	11	31	appropriate	appropriate	ADJ
cana-4022	11	32	methods	method	NOUN
cana-4022	11	33	for	for	ADP
cana-4022	11	34	learning	learn	VERB
cana-4022	11	35	depending	depend	VERB
cana-4022	11	36	on	on	ADP
cana-4022	11	37	the	the	DET
cana-4022	11	38	nature	nature	NOUN
cana-4022	11	39	of	of	ADP
cana-4022	11	40	a	a	DET
cana-4022	11	41	task	task	NOUN
cana-4022	11	42	and	and	CCONJ
cana-4022	11	43	the	the	DET
cana-4022	11	44	amount	amount	NOUN
cana-4022	11	45	of	of	ADP
cana-4022	11	46	data	datum	NOUN
cana-4022	11	47	at	at	ADP
cana-4022	11	48	one	one	NUM
cana-4022	11	49	’s	’s	PART
cana-4022	11	50	disposal	disposal	NOUN
cana-4022	11	51	.	.	PUNCT
cana-4022	12	1	keywords	keyword	NOUN
cana-4022	12	2	:	:	PUNCT
cana-4022	12	3	ai	ai	VERB
cana-4022	12	4	performance	performance	NOUN
cana-4022	12	5	,	,	PUNCT
cana-4022	12	6	supervised	supervised	ADJ
cana-4022	12	7	learning	learning	NOUN
cana-4022	12	8	,	,	PUNCT
cana-4022	12	9	machine	machine	NOUN
cana-4022	12	10	learning	learning	NOUN
cana-4022	12	11	,	,	PUNCT
cana-4022	12	12	data	datum	NOUN
cana-4022	12	13	analysis	analysis	NOUN
cana-4022	12	14	,	,	PUNCT
cana-4022	12	15	unsupervised	unsupervised	ADJ
cana-4022	12	16	learning	learn	VERB
cana-4022	12	17	1	1	NUM
cana-4022	12	18	.	.	PUNCT
cana-4022	13	1	introduction	introduction	NOUN
cana-4022	13	2	the	the	DET
cana-4022	13	3	research	research	NOUN
cana-4022	13	4	also	also	ADV
cana-4022	13	5	planned	plan	VERB
cana-4022	13	6	to	to	PART
cana-4022	13	7	constitute	constitute	VERB
cana-4022	13	8	the	the	DET
cana-4022	13	9	comparative	comparative	ADJ
cana-4022	13	10	assessment	assessment	NOUN
cana-4022	13	11	of	of	ADP
cana-4022	13	12	the	the	DET
cana-4022	13	13	supervised	supervised	ADJ
cana-4022	13	14	and	and	CCONJ
cana-4022	13	15	unsupervised	unsupervised	ADJ
cana-4022	13	16	learning	learning	NOUN
cana-4022	13	17	models	model	NOUN
cana-4022	13	18	and	and	CCONJ
cana-4022	13	19	measure	measure	VERB
cana-4022	13	20	the	the	DET
cana-4022	13	21	usability	usability	NOUN
cana-4022	13	22	,	,	PUNCT
cana-4022	13	23	efficacy	efficacy	NOUN
cana-4022	13	24	and	and	CCONJ
cana-4022	13	25	accuracy	accuracy	NOUN
cana-4022	13	26	of	of	ADP
cana-4022	13	27	the	the	DET
cana-4022	13	28	methods	method	NOUN
cana-4022	13	29	in	in	ADP
cana-4022	13	30	a	a	DET
cana-4022	13	31	variety	variety	NOUN
cana-4022	13	32	of	of	ADP
cana-4022	13	33	fields	field	NOUN
cana-4022	13	34	.	.	PUNCT
cana-4022	14	1	classification	classification	NOUN
cana-4022	14	2	algorithms	algorithm	NOUN
cana-4022	14	3	such	such	ADJ
cana-4022	14	4	as	as	ADP
cana-4022	14	5	decision	decision	NOUN
cana-4022	14	6	trees	tree	NOUN
cana-4022	14	7	and	and	CCONJ
cana-4022	14	8	/or	/or	ADP
cana-4022	14	9	support	support	NOUN
cana-4022	14	10	vector	vector	NOUN
cana-4022	14	11	machines	machine	NOUN
cana-4022	14	12	(	(	PUNCT
cana-4022	14	13	svm	svm	PROPN
cana-4022	14	14	)	)	PUNCT
cana-4022	14	15	have	have	AUX
cana-4022	14	16	been	be	AUX
cana-4022	14	17	said	say	VERB
cana-4022	14	18	to	to	PART
cana-4022	14	19	be	be	AUX
cana-4022	14	20	well	well	ADV
cana-4022	14	21	suited	suited	ADJ
cana-4022	14	22	for	for	ADP
cana-4022	14	23	generalization	generalization	NOUN
cana-4022	14	24	where	where	SCONJ
cana-4022	14	25	the	the	DET
cana-4022	14	26	data	datum	NOUN
cana-4022	14	27	provided	provide	VERB
cana-4022	14	28	is	be	AUX
cana-4022	14	29	structured	structure	VERB
cana-4022	14	30	.	.	PUNCT
cana-4022	15	1	decision	decision	NOUN
cana-4022	15	2	trees	tree	NOUN
cana-4022	15	3	give	give	VERB
cana-4022	15	4	models	model	NOUN
cana-4022	15	5	which	which	PRON
cana-4022	15	6	are	be	AUX
cana-4022	15	7	easy	easy	ADJ
cana-4022	15	8	to	to	PART
cana-4022	15	9	interpret	interpret	VERB
cana-4022	15	10	and	and	CCONJ
cana-4022	15	11	it	it	PRON
cana-4022	15	12	also	also	ADV
cana-4022	15	13	best	good	ADJ
cana-4022	15	14	suits	suit	VERB
cana-4022	15	15	the	the	DET
cana-4022	15	16	categorical	categorical	ADJ
cana-4022	15	17	independent	independent	ADJ
cana-4022	15	18	variable	variable	NOUN
cana-4022	15	19	while	while	SCONJ
cana-4022	15	20	the	the	DET
cana-4022	15	21	mailto:roshni.verma@medicaps.ac.in	mailto:roshni.verma@medicaps.ac.in	NUM
cana-4022	15	22	mailto:ritu.maheshwari@medicaps.ac.in	mailto:ritu.maheshwari@medicaps.ac.in	NUM
cana-4022	15	23	mailto:deepmala.manore@medicaps.ac.in	mailto:deepmala.manore@medicaps.ac.in	NUM
cana-4022	15	24	mailto:pinky.rane@medicaps.ac	mailto:pinky.rane@medicaps.ac	PROPN
cana-4022	15	25	mailto:raikwarmonark@gmail.com	mailto:raikwarmonark@gmail.com	PROPN
cana-4022	15	26	communications	communication	NOUN
cana-4022	15	27	on	on	ADP
cana-4022	15	28	applied	apply	VERB
cana-4022	15	29	nonlinear	nonlinear	ADJ
cana-4022	15	30	analysis	analysis	NOUN
cana-4022	15	31	issn	issn	NOUN
cana-4022	15	32	:	:	PUNCT
cana-4022	15	33	1074	1074	NUM
cana-4022	15	34	-	-	PUNCT
cana-4022	15	35	133x	133x	NUM
cana-4022	15	36	vol	vol	NOUN
cana-4022	15	37	32	32	NUM
cana-4022	15	38	no	no	NOUN
cana-4022	15	39	.	.	PUNCT
cana-4022	16	1	9s	9s	NUM
cana-4022	16	2	(	(	PUNCT
cana-4022	16	3	2025	2025	NUM
cana-4022	16	4	)	)	PUNCT
cana-4022	17	1	861	861	NUM
cana-4022	17	2	https://internationalpubls.com	https://internationalpubls.com	X
cana-4022	17	3	simple	simple	ADJ
cana-4022	17	4	form	form	NOUN
cana-4022	17	5	of	of	ADP
cana-4022	17	6	svm	svm	PROPN
cana-4022	17	7	is	be	AUX
cana-4022	17	8	less	less	ADV
cana-4022	17	9	sensitive	sensitive	ADJ
cana-4022	17	10	to	to	ADP
cana-4022	17	11	overfitting	overfitte	VERB
cana-4022	17	12	and	and	CCONJ
cana-4022	17	13	is	be	AUX
cana-4022	17	14	best	good	ADJ
cana-4022	17	15	for	for	ADP
cana-4022	17	16	high	high	ADJ
cana-4022	17	17	dimensionality	dimensionality	NOUN
cana-4022	17	18	.	.	PUNCT
cana-4022	18	1	as	as	ADP
cana-4022	18	2	for	for	ADP
cana-4022	18	3	the	the	DET
cana-4022	18	4	unsupervised	unsupervised	ADJ
cana-4022	18	5	learning	learning	NOUN
cana-4022	18	6	type	type	NOUN
cana-4022	18	7	,	,	PUNCT
cana-4022	18	8	k	k	NOUN
cana-4022	18	9	-	-	PUNCT
cana-4022	18	10	means	mean	VERB
cana-4022	18	11	clustering	clustering	NOUN
cana-4022	18	12	and	and	CCONJ
cana-4022	18	13	autoencoders	autoencoder	NOUN
cana-4022	18	14	are	be	AUX
cana-4022	18	15	usually	usually	ADV
cana-4022	18	16	employed	employ	VERB
cana-4022	18	17	for	for	ADP
cana-4022	18	18	the	the	DET
cana-4022	18	19	pattern	pattern	NOUN
cana-4022	18	20	recognition	recognition	NOUN
cana-4022	18	21	and	and	CCONJ
cana-4022	18	22	feature	feature	NOUN
cana-4022	18	23	extraction	extraction	NOUN
cana-4022	18	24	purposes	purpose	NOUN
cana-4022	18	25	.	.	PUNCT
cana-4022	19	1	this	this	DET
cana-4022	19	2	clustering	clustering	ADJ
cana-4022	19	3	algorithm	algorithm	NOUN
cana-4022	19	4	is	be	AUX
cana-4022	19	5	helpful	helpful	ADJ
cana-4022	19	6	in	in	ADP
cana-4022	19	7	segmentation	segmentation	NOUN
cana-4022	19	8	problems	problem	NOUN
cana-4022	19	9	but	but	CCONJ
cana-4022	19	10	less	less	ADV
cana-4022	19	11	effective	effective	ADJ
cana-4022	19	12	when	when	SCONJ
cana-4022	19	13	dealing	deal	VERB
cana-4022	19	14	with	with	ADP
cana-4022	19	15	intricate	intricate	ADJ
cana-4022	19	16	distribution	distribution	NOUN
cana-4022	19	17	,	,	PUNCT
cana-4022	19	18	while	while	SCONJ
cana-4022	19	19	autoencoders	autoencoder	NOUN
cana-4022	19	20	,	,	PUNCT
cana-4022	19	21	as	as	ADP
cana-4022	19	22	a	a	DET
cana-4022	19	23	type	type	NOUN
cana-4022	19	24	of	of	ADP
cana-4022	19	25	neural	neural	ADJ
cana-4022	19	26	networks	network	NOUN
cana-4022	19	27	,	,	PUNCT
cana-4022	19	28	are	be	AUX
cana-4022	19	29	suitable	suitable	ADJ
cana-4022	19	30	for	for	ADP
cana-4022	19	31	feature	feature	NOUN
cana-4022	19	32	extraction	extraction	NOUN
cana-4022	19	33	and	and	CCONJ
cana-4022	19	34	anomaly	anomaly	NOUN
cana-4022	19	35	detection	detection	NOUN
cana-4022	19	36	.	.	PUNCT
cana-4022	20	1	learning	learn	VERB
cana-4022	20	2	these	these	DET
cana-4022	20	3	models	model	NOUN
cana-4022	20	4	implies	imply	VERB
cana-4022	20	5	a	a	DET
cana-4022	20	6	great	great	ADJ
cana-4022	20	7	understanding	understanding	NOUN
cana-4022	20	8	of	of	ADP
cana-4022	20	9	their	their	PRON
cana-4022	20	10	strengths	strength	NOUN
cana-4022	20	11	,	,	PUNCT
cana-4022	20	12	weaknesses	weakness	NOUN
cana-4022	20	13	and	and	CCONJ
cana-4022	20	14	the	the	DET
cana-4022	20	15	way	way	NOUN
cana-4022	20	16	they	they	PRON
cana-4022	20	17	should	should	AUX
cana-4022	20	18	be	be	AUX
cana-4022	20	19	applied	apply	VERB
cana-4022	20	20	in	in	ADP
cana-4022	20	21	a	a	DET
cana-4022	20	22	project	project	NOUN
cana-4022	20	23	.	.	PUNCT
cana-4022	21	1	in	in	ADP
cana-4022	21	2	order	order	NOUN
cana-4022	21	3	to	to	PART
cana-4022	21	4	assess	assess	VERB
cana-4022	21	5	the	the	DET
cana-4022	21	6	effectiveness	effectiveness	NOUN
cana-4022	21	7	and	and	CCONJ
cana-4022	21	8	applicability	applicability	NOUN
cana-4022	21	9	of	of	ADP
cana-4022	21	10	these	these	DET
cana-4022	21	11	learning	learning	NOUN
cana-4022	21	12	paradigms	paradigm	VERB
cana-4022	21	13	,	,	PUNCT
cana-4022	21	14	the	the	DET
cana-4022	21	15	paper	paper	NOUN
cana-4022	21	16	uses	use	VERB
cana-4022	21	17	three	three	NUM
cana-4022	21	18	datasets	dataset	NOUN
cana-4022	21	19	from	from	ADP
cana-4022	21	20	different	different	ADJ
cana-4022	21	21	fields	field	NOUN
cana-4022	21	22	related	relate	VERB
cana-4022	21	23	to	to	ADP
cana-4022	21	24	finance	finance	NOUN
cana-4022	21	25	,	,	PUNCT
cana-4022	21	26	healthcare	healthcare	NOUN
cana-4022	21	27	domain	domain	NOUN
cana-4022	21	28	,	,	PUNCT
cana-4022	21	29	and	and	CCONJ
cana-4022	21	30	image	image	NOUN
cana-4022	21	31	analysis	analysis	NOUN
cana-4022	21	32	.	.	PUNCT
cana-4022	22	1	every	every	DET
cana-4022	22	2	dataset	dataset	NOUN
cana-4022	22	3	comes	come	VERB
cana-4022	22	4	with	with	ADP
cana-4022	22	5	its	its	PRON
cana-4022	22	6	own	own	ADJ
cana-4022	22	7	issues	issue	NOUN
cana-4022	22	8	such	such	ADJ
cana-4022	22	9	as	as	ADP
cana-4022	22	10	,	,	PUNCT
cana-4022	22	11	low	low	ADJ
cana-4022	22	12	sample	sample	NOUN
cana-4022	22	13	size	size	NOUN
cana-4022	22	14	,	,	PUNCT
cana-4022	22	15	very	very	ADV
cana-4022	22	16	many	many	ADJ
cana-4022	22	17	features	feature	NOUN
cana-4022	22	18	,	,	PUNCT
cana-4022	22	19	and	and	CCONJ
cana-4022	22	20	a	a	DET
cana-4022	22	21	difference	difference	NOUN
cana-4022	22	22	in	in	ADP
cana-4022	22	23	the	the	DET
cana-4022	22	24	level	level	NOUN
cana-4022	22	25	of	of	ADP
cana-4022	22	26	noise	noise	NOUN
cana-4022	22	27	affects	affect	VERB
cana-4022	22	28	the	the	DET
cana-4022	22	29	results	result	NOUN
cana-4022	22	30	of	of	ADP
cana-4022	22	31	the	the	DET
cana-4022	22	32	model	model	NOUN
cana-4022	22	33	.	.	PUNCT
cana-4022	23	1	to	to	PART
cana-4022	23	2	compare	compare	VERB
cana-4022	23	3	the	the	DET
cana-4022	23	4	algorithms	algorithm	NOUN
cana-4022	23	5	,	,	PUNCT
cana-4022	23	6	only	only	ADV
cana-4022	23	7	relevant	relevant	ADJ
cana-4022	23	8	or	or	CCONJ
cana-4022	23	9	useful	useful	ADJ
cana-4022	23	10	features	feature	NOUN
cana-4022	23	11	are	be	AUX
cana-4022	23	12	considered	consider	VERB
cana-4022	23	13	,	,	PUNCT
cana-4022	23	14	and	and	CCONJ
cana-4022	23	15	they	they	PRON
cana-4022	23	16	are	be	AUX
cana-4022	23	17	normalized	normalize	VERB
cana-4022	23	18	so	so	SCONJ
cana-4022	23	19	that	that	SCONJ
cana-4022	23	20	none	none	NOUN
cana-4022	23	21	of	of	ADP
cana-4022	23	22	them	they	PRON
cana-4022	23	23	bias	bias	VERB
cana-4022	23	24	the	the	DET
cana-4022	23	25	results	result	NOUN
cana-4022	23	26	,	,	PUNCT
cana-4022	23	27	and	and	CCONJ
cana-4022	23	28	missing	miss	VERB
cana-4022	23	29	values	value	NOUN
cana-4022	23	30	are	be	AUX
cana-4022	23	31	also	also	ADV
cana-4022	23	32	dealt	deal	VERB
cana-4022	23	33	with	with	ADP
cana-4022	23	34	.	.	PUNCT
cana-4022	24	1	the	the	DET
cana-4022	24	2	specified	specify	VERB
cana-4022	24	3	models	model	NOUN
cana-4022	24	4	are	be	AUX
cana-4022	24	5	also	also	ADV
cana-4022	24	6	assessed	assess	VERB
cana-4022	24	7	based	base	VERB
cana-4022	24	8	on	on	ADP
cana-4022	24	9	conventional	conventional	ADJ
cana-4022	24	10	measures	measure	NOUN
cana-4022	24	11	of	of	ADP
cana-4022	24	12	accuracy	accuracy	NOUN
cana-4022	24	13	,	,	PUNCT
cana-4022	24	14	precision	precision	NOUN
cana-4022	24	15	,	,	PUNCT
cana-4022	24	16	recall	recall	NOUN
cana-4022	24	17	,	,	PUNCT
cana-4022	24	18	and	and	CCONJ
cana-4022	24	19	f1	f1	NOUN
cana-4022	24	20	-	-	PUNCT
cana-4022	24	21	score	score	NOUN
cana-4022	24	22	for	for	ADP
cana-4022	24	23	model	model	NOUN
cana-4022	24	24	implementation	implementation	NOUN
cana-4022	24	25	,	,	PUNCT
cana-4022	24	26	training	training	NOUN
cana-4022	24	27	,	,	PUNCT
cana-4022	24	28	and	and	CCONJ
cana-4022	24	29	evaluation	evaluation	NOUN
cana-4022	24	30	.	.	PUNCT
cana-4022	25	1	further	far	ADV
cana-4022	25	2	,	,	PUNCT
cana-4022	25	3	while	while	SCONJ
cana-4022	25	4	comparing	compare	VERB
cana-4022	25	5	the	the	DET
cana-4022	25	6	results	result	NOUN
cana-4022	25	7	,	,	PUNCT
cana-4022	25	8	anova	anova	PROPN
cana-4022	25	9	and	and	CCONJ
cana-4022	25	10	paired	pair	VERB
cana-4022	25	11	t	t	NOUN
cana-4022	25	12	-	-	PUNCT
cana-4022	25	13	tests	test	NOUN
cana-4022	25	14	are	be	AUX
cana-4022	25	15	used	use	VERB
cana-4022	25	16	to	to	PART
cana-4022	25	17	establish	establish	VERB
cana-4022	25	18	the	the	DET
cana-4022	25	19	significance	significance	NOUN
cana-4022	25	20	of	of	ADP
cana-4022	25	21	the	the	DET
cana-4022	25	22	differences	difference	NOUN
cana-4022	25	23	that	that	PRON
cana-4022	25	24	were	be	AUX
cana-4022	25	25	observed	observe	VERB
cana-4022	25	26	.	.	PUNCT
cana-4022	26	1	the	the	DET
cana-4022	26	2	rationale	rationale	NOUN
cana-4022	26	3	for	for	ADP
cana-4022	26	4	this	this	DET
cana-4022	26	5	comparative	comparative	ADJ
cana-4022	26	6	analysis	analysis	NOUN
cana-4022	26	7	is	be	AUX
cana-4022	26	8	based	base	VERB
cana-4022	26	9	on	on	ADP
cana-4022	26	10	the	the	DET
cana-4022	26	11	increased	increase	VERB
cana-4022	26	12	interest	interest	NOUN
cana-4022	26	13	in	in	ADP
cana-4022	26	14	the	the	DET
cana-4022	26	15	application	application	NOUN
cana-4022	26	16	of	of	ADP
cana-4022	26	17	autonomous	autonomous	ADJ
cana-4022	26	18	decision	decision	NOUN
cana-4022	26	19	-	-	PUNCT
cana-4022	26	20	making	making	NOUN
cana-4022	26	21	using	use	VERB
cana-4022	26	22	artificial	artificial	ADJ
cana-4022	26	23	intelligence	intelligence	NOUN
cana-4022	26	24	in	in	ADP
cana-4022	26	25	areas	area	NOUN
cana-4022	26	26	such	such	ADJ
cana-4022	26	27	as	as	ADP
cana-4022	26	28	finance	finance	NOUN
cana-4022	26	29	and	and	CCONJ
cana-4022	26	30	health	health	NOUN
cana-4022	26	31	and	and	CCONJ
cana-4022	26	32	autonomous	autonomous	ADJ
cana-4022	26	33	vehicles	vehicle	NOUN
cana-4022	26	34	.	.	PUNCT
cana-4022	27	1	supervised	supervised	ADJ
cana-4022	27	2	learning	learning	NOUN
cana-4022	27	3	is	be	AUX
cana-4022	27	4	more	more	ADV
cana-4022	27	5	suitable	suitable	ADJ
cana-4022	27	6	for	for	ADP
cana-4022	27	7	tasks	task	NOUN
cana-4022	27	8	that	that	PRON
cana-4022	27	9	need	need	VERB
cana-4022	27	10	a	a	DET
cana-4022	27	11	high	high	ADJ
cana-4022	27	12	level	level	NOUN
cana-4022	27	13	of	of	ADP
cana-4022	27	14	accuracy	accuracy	NOUN
cana-4022	27	15	and	and	CCONJ
cana-4022	27	16	credibility	credibility	NOUN
cana-4022	27	17	,	,	PUNCT
cana-4022	27	18	but	but	CCONJ
cana-4022	27	19	unsupervised	unsupervised	ADJ
cana-4022	27	20	learning	learning	NOUN
cana-4022	27	21	can	can	AUX
cana-4022	27	22	be	be	AUX
cana-4022	27	23	very	very	ADV
cana-4022	27	24	useful	useful	ADJ
cana-4022	27	25	when	when	SCONJ
cana-4022	27	26	trying	try	VERB
cana-4022	27	27	to	to	PART
cana-4022	27	28	unveil	unveil	VERB
cana-4022	27	29	structures	structure	NOUN
cana-4022	27	30	in	in	ADP
cana-4022	27	31	the	the	DET
cana-4022	27	32	data	datum	NOUN
cana-4022	27	33	.	.	PUNCT
cana-4022	28	1	however	however	ADV
cana-4022	28	2	,	,	PUNCT
cana-4022	28	3	less	less	ADV
cana-4022	28	4	is	be	AUX
cana-4022	28	5	known	know	VERB
cana-4022	28	6	about	about	ADP
cana-4022	28	7	comparing	compare	VERB
cana-4022	28	8	their	their	PRON
cana-4022	28	9	efficacy	efficacy	NOUN
cana-4022	28	10	in	in	ADP
cana-4022	28	11	terms	term	NOUN
cana-4022	28	12	of	of	ADP
cana-4022	28	13	various	various	ADJ
cana-4022	28	14	conditions	condition	NOUN
cana-4022	28	15	or	or	CCONJ
cana-4022	28	16	patients	patient	NOUN
cana-4022	28	17	with	with	ADP
cana-4022	28	18	a	a	DET
cana-4022	28	19	significantly	significantly	ADV
cana-4022	28	20	higher	high	ADJ
cana-4022	28	21	level	level	NOUN
cana-4022	28	22	of	of	ADP
cana-4022	28	23	statistical	statistical	ADJ
cana-4022	28	24	backing	backing	NOUN
cana-4022	28	25	up	up	ADP
cana-4022	28	26	the	the	DET
cana-4022	28	27	results	result	NOUN
cana-4022	28	28	.	.	PUNCT
cana-4022	29	1	closing	close	VERB
cana-4022	29	2	this	this	DET
cana-4022	29	3	gap	gap	NOUN
cana-4022	29	4	is	be	AUX
cana-4022	29	5	the	the	DET
cana-4022	29	6	purpose	purpose	NOUN
cana-4022	29	7	of	of	ADP
cana-4022	29	8	the	the	DET
cana-4022	29	9	study	study	NOUN
cana-4022	29	10	underpinning	underpin	VERB
cana-4022	29	11	this	this	DET
cana-4022	29	12	paper	paper	NOUN
cana-4022	29	13	to	to	PART
cana-4022	29	14	give	give	VERB
cana-4022	29	15	an	an	DET
cana-4022	29	16	answer	answer	NOUN
cana-4022	29	17	to	to	ADP
cana-4022	29	18	questions	question	NOUN
cana-4022	29	19	of	of	ADP
cana-4022	29	20	when	when	SCONJ
cana-4022	29	21	one	one	NUM
cana-4022	29	22	of	of	ADP
cana-4022	29	23	the	the	DET
cana-4022	29	24	two	two	NUM
cana-4022	29	25	approaches	approach	NOUN
cana-4022	29	26	should	should	AUX
cana-4022	29	27	be	be	AUX
cana-4022	29	28	used	use	VERB
cana-4022	29	29	,	,	PUNCT
cana-4022	29	30	and	and	CCONJ
cana-4022	29	31	the	the	DET
cana-4022	29	32	reasons	reason	NOUN
cana-4022	29	33	for	for	ADP
cana-4022	29	34	such	such	DET
cana-4022	29	35	a	a	DET
cana-4022	29	36	decision	decision	NOUN
cana-4022	29	37	,	,	PUNCT
cana-4022	29	38	which	which	PRON
cana-4022	29	39	can	can	AUX
cana-4022	29	40	be	be	AUX
cana-4022	29	41	beneficial	beneficial	ADJ
cana-4022	29	42	for	for	ADP
cana-4022	29	43	data	data	NOUN
cana-4022	29	44	scientists	scientist	NOUN
cana-4022	29	45	and	and	CCONJ
cana-4022	29	46	ai	ai	VERB
cana-4022	29	47	professionals	professional	NOUN
cana-4022	29	48	.	.	PUNCT
cana-4022	30	1	the	the	DET
cana-4022	30	2	analysis	analysis	NOUN
cana-4022	30	3	of	of	ADP
cana-4022	30	4	these	these	DET
cana-4022	30	5	models	model	NOUN
cana-4022	30	6	of	of	ADP
cana-4022	30	7	computation	computation	NOUN
cana-4022	30	8	helps	help	VERB
cana-4022	30	9	in	in	ADP
cana-4022	30	10	proper	proper	ADJ
cana-4022	30	11	decision	decision	NOUN
cana-4022	30	12	making	make	VERB
cana-4022	30	13	when	when	SCONJ
cana-4022	30	14	applying	apply	VERB
cana-4022	30	15	ai	ai	VERB
cana-4022	30	16	based	base	VERB
cana-4022	30	17	systems	system	NOUN
cana-4022	30	18	in	in	ADP
cana-4022	30	19	real	real	ADJ
cana-4022	30	20	life	life	NOUN
cana-4022	30	21	problems	problem	NOUN
cana-4022	30	22	in	in	ADP
cana-4022	30	23	as	as	ADV
cana-4022	30	24	much	much	ADV
cana-4022	30	25	as	as	SCONJ
cana-4022	30	26	it	it	PRON
cana-4022	30	27	guarantees	guarantee	VERB
cana-4022	30	28	that	that	SCONJ
cana-4022	30	29	the	the	DET
cana-4022	30	30	required	required	ADJ
cana-4022	30	31	problem	problem	NOUN
cana-4022	30	32	solving	solving	NOUN
cana-4022	30	33	will	will	AUX
cana-4022	30	34	be	be	AUX
cana-4022	30	35	effective	effective	ADJ
cana-4022	30	36	and	and	CCONJ
cana-4022	30	37	efficient	efficient	ADJ
cana-4022	30	38	.	.	PUNCT
cana-4022	31	1	2	2	X
cana-4022	31	2	.	.	X
cana-4022	31	3	literature	literature	NOUN
cana-4022	31	4	review	review	PROPN
cana-4022	31	5	machine	machine	NOUN
cana-4022	31	6	learning	learn	VERB
cana-4022	31	7	itself	itself	PRON
cana-4022	31	8	has	have	AUX
cana-4022	31	9	been	be	AUX
cana-4022	31	10	progressing	progress	VERB
cana-4022	31	11	rapidly	rapidly	ADV
cana-4022	31	12	in	in	ADP
cana-4022	31	13	the	the	DET
cana-4022	31	14	past	past	ADJ
cana-4022	31	15	few	few	ADJ
cana-4022	31	16	years	year	NOUN
cana-4022	31	17	and	and	CCONJ
cana-4022	31	18	the	the	DET
cana-4022	31	19	two	two	NUM
cana-4022	31	20	most	most	ADV
cana-4022	31	21	addressed	address	VERB
cana-4022	31	22	techniques	technique	NOUN
cana-4022	31	23	are	be	AUX
cana-4022	31	24	supervised	supervised	ADJ
cana-4022	31	25	and	and	CCONJ
cana-4022	31	26	unsupervised	unsupervised	ADJ
cana-4022	31	27	learning	learning	NOUN
cana-4022	31	28	.	.	PUNCT
cana-4022	32	1	in	in	ADP
cana-4022	32	2	supervised	supervised	ADJ
cana-4022	32	3	learning	learn	VERB
cana-4022	32	4	the	the	DET
cana-4022	32	5	data	datum	NOUN
cana-4022	32	6	is	be	AUX
cana-4022	32	7	labelled	label	VERB
cana-4022	32	8	to	to	PART
cana-4022	32	9	train	train	VERB
cana-4022	32	10	a	a	DET
cana-4022	32	11	model	model	NOUN
cana-4022	32	12	for	for	ADP
cana-4022	32	13	the	the	DET
cana-4022	32	14	classification	classification	NOUN
cana-4022	32	15	or	or	CCONJ
cana-4022	32	16	regression	regression	NOUN
cana-4022	32	17	purposes	purpose	NOUN
cana-4022	32	18	while	while	SCONJ
cana-4022	32	19	in	in	ADP
cana-4022	32	20	the	the	DET
cana-4022	32	21	unsupervised	unsupervised	ADJ
cana-4022	32	22	learning	learning	NOUN
cana-4022	32	23	,	,	PUNCT
cana-4022	32	24	the	the	DET
cana-4022	32	25	data	data	NOUN
cana-4022	32	26	is	be	AUX
cana-4022	32	27	not	not	PART
cana-4022	32	28	labelled	label	VERB
cana-4022	32	29	to	to	PART
cana-4022	32	30	find	find	VERB
cana-4022	32	31	the	the	DET
cana-4022	32	32	patterns	pattern	NOUN
cana-4022	32	33	in	in	ADP
cana-4022	32	34	the	the	DET
cana-4022	32	35	data	datum	NOUN
cana-4022	32	36	.	.	PUNCT
cana-4022	33	1	these	these	DET
cana-4022	33	2	paradigms	paradigm	NOUN
cana-4022	33	3	reveal	reveal	VERB
cana-4022	33	4	different	different	ADJ
cana-4022	33	5	performances	performance	NOUN
cana-4022	33	6	based	base	VERB
cana-4022	33	7	on	on	ADP
cana-4022	33	8	the	the	DET
cana-4022	33	9	characteristics	characteristic	NOUN
cana-4022	33	10	of	of	ADP
cana-4022	33	11	the	the	DET
cana-4022	33	12	dataset	dataset	NOUN
cana-4022	33	13	and	and	CCONJ
cana-4022	33	14	the	the	DET
cana-4022	33	15	use	use	NOUN
cana-4022	33	16	it	it	PRON
cana-4022	33	17	will	will	AUX
cana-4022	33	18	be	be	AUX
cana-4022	33	19	subjected	subject	VERB
cana-4022	33	20	to	to	ADP
cana-4022	33	21	;	;	PUNCT
cana-4022	33	22	this	this	PRON
cana-4022	33	23	is	be	AUX
cana-4022	33	24	why	why	SCONJ
cana-4022	33	25	comparative	comparative	ADJ
cana-4022	33	26	studies	study	NOUN
cana-4022	33	27	are	be	AUX
cana-4022	33	28	important	important	ADJ
cana-4022	33	29	to	to	PART
cana-4022	33	30	define	define	VERB
cana-4022	33	31	which	which	DET
cana-4022	33	32	technique	technique	NOUN
cana-4022	33	33	is	be	AUX
cana-4022	33	34	more	more	ADV
cana-4022	33	35	adequate	adequate	ADJ
cana-4022	33	36	.	.	PUNCT
cana-4022	34	1	burkov	burkov	PROPN
cana-4022	34	2	(	(	PUNCT
cana-4022	34	3	2025	2025	NUM
cana-4022	34	4	)	)	PUNCT
cana-4022	34	5	defines	define	VERB
cana-4022	34	6	general	general	ADJ
cana-4022	34	7	attributes	attribute	NOUN
cana-4022	34	8	of	of	ADP
cana-4022	34	9	models	model	NOUN
cana-4022	34	10	in	in	ADP
cana-4022	34	11	ml	ml	NOUN
cana-4022	34	12	starting	start	VERB
cana-4022	34	13	by	by	ADP
cana-4022	34	14	stating	state	VERB
cana-4022	34	15	that	that	SCONJ
cana-4022	34	16	supervised	supervised	ADJ
cana-4022	34	17	learning	learning	NOUN
cana-4022	34	18	is	be	AUX
cana-4022	34	19	set	set	VERB
cana-4022	34	20	up	up	ADP
cana-4022	34	21	in	in	ADP
cana-4022	34	22	a	a	DET
cana-4022	34	23	structured	structured	ADJ
cana-4022	34	24	manner	manner	NOUN
cana-4022	34	25	and	and	CCONJ
cana-4022	34	26	depends	depend	VERB
cana-4022	34	27	on	on	ADP
cana-4022	34	28	annotated	annotate	VERB
cana-4022	34	29	datasets	dataset	NOUN
cana-4022	34	30	.	.	PUNCT
cana-4022	35	1	he	he	PRON
cana-4022	35	2	notes	note	VERB
cana-4022	35	3	that	that	SCONJ
cana-4022	35	4	decision	decision	NOUN
cana-4022	35	5	trees	tree	NOUN
cana-4022	35	6	for	for	ADP
cana-4022	35	7	example	example	NOUN
cana-4022	35	8	and	and	CCONJ
cana-4022	35	9	support	support	VERB
cana-4022	35	10	vector	vector	NOUN
cana-4022	35	11	machines	machine	NOUN
cana-4022	35	12	(	(	PUNCT
cana-4022	35	13	svm	svm	PROPN
cana-4022	35	14	)	)	PUNCT
cana-4022	35	15	are	be	AUX
cana-4022	35	16	efficient	efficient	ADJ
cana-4022	35	17	for	for	ADP
cana-4022	35	18	sheet	sheet	NOUN
cana-4022	35	19	like	like	ADP
cana-4022	35	20	data	datum	NOUN
cana-4022	35	21	while	while	SCONJ
cana-4022	35	22	they	they	PRON
cana-4022	35	23	are	be	AUX
cana-4022	35	24	not	not	PART
cana-4022	35	25	efficient	efficient	ADJ
cana-4022	35	26	for	for	ADP
cana-4022	35	27	high	high	ADJ
cana-4022	35	28	dimensional	dimensional	ADJ
cana-4022	35	29	and	and	CCONJ
cana-4022	35	30	…	…	PUNCT
cana-4022	35	31	.	.	PUNCT
cana-4022	36	1	equally	equally	ADV
cana-4022	36	2	,	,	PUNCT
cana-4022	36	3	geron	geron	X
cana-4022	36	4	(	(	PUNCT
cana-4022	36	5	2025	2025	NUM
cana-4022	36	6	)	)	PUNCT
cana-4022	36	7	narrates	narrate	VERB
cana-4022	36	8	a	a	DET
cana-4022	36	9	practical	practical	ADJ
cana-4022	36	10	example	example	NOUN
cana-4022	36	11	use	use	NOUN
cana-4022	36	12	of	of	ADP
cana-4022	36	13	supervised	supervised	ADJ
cana-4022	36	14	models	model	NOUN
cana-4022	36	15	such	such	ADJ
cana-4022	36	16	as	as	ADP
cana-4022	36	17	the	the	DET
cana-4022	36	18	scikit	scikit	NOUN
cana-4022	36	19	-	-	PUNCT
cana-4022	36	20	learn	learn	VERB
cana-4022	36	21	,	,	PUNCT
cana-4022	36	22	keras	keras	PROPN
cana-4022	36	23	together	together	ADV
cana-4022	36	24	with	with	ADP
cana-4022	36	25	tensorflow	tensorflow	NOUN
cana-4022	36	26	for	for	ADP
cana-4022	36	27	supervised	supervised	ADJ
cana-4022	36	28	models	model	NOUN
cana-4022	36	29	communications	communication	NOUN
cana-4022	36	30	on	on	ADP
cana-4022	36	31	applied	apply	VERB
cana-4022	36	32	nonlinear	nonlinear	ADJ
cana-4022	36	33	analysis	analysis	NOUN
cana-4022	36	34	issn	issn	NOUN
cana-4022	36	35	:	:	PUNCT
cana-4022	36	36	1074	1074	NUM
cana-4022	36	37	-	-	PUNCT
cana-4022	36	38	133x	133x	NUM
cana-4022	36	39	vol	vol	NOUN
cana-4022	36	40	32	32	NUM
cana-4022	36	41	no	no	NOUN
cana-4022	36	42	.	.	PUNCT
cana-4022	37	1	9s	9s	NUM
cana-4022	37	2	(	(	PUNCT
cana-4022	37	3	2025	2025	NUM
cana-4022	37	4	)	)	PUNCT
cana-4022	37	5	862	862	NUM
cana-4022	37	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-4022	37	7	which	which	PRON
cana-4022	37	8	though	though	ADV
cana-4022	37	9	yields	yield	VERB
cana-4022	37	10	a	a	DET
cana-4022	37	11	high	high	ADJ
cana-4022	37	12	performance	performance	NOUN
cana-4022	37	13	within	within	ADP
cana-4022	37	14	a	a	DET
cana-4022	37	15	systematically	systematically	ADV
cana-4022	37	16	controlled	control	VERB
cana-4022	37	17	experimental	experimental	ADJ
cana-4022	37	18	data	datum	NOUN
cana-4022	37	19	,	,	PUNCT
cana-4022	37	20	they	they	PRON
cana-4022	37	21	are	be	AUX
cana-4022	37	22	not	not	PART
cana-4022	37	23	so	so	ADV
cana-4022	37	24	efficient	efficient	ADJ
cana-4022	37	25	in	in	ADP
cana-4022	37	26	performing	perform	VERB
cana-4022	37	27	in	in	ADP
cana-4022	37	28	real	real	ADJ
cana-4022	37	29	word	word	NOUN
cana-4022	37	30	complex	complex	ADJ
cana-4022	37	31	data	datum	NOUN
cana-4022	37	32	without	without	ADP
cana-4022	37	33	right	right	ADJ
cana-4022	37	34	adjustments	adjustment	NOUN
cana-4022	37	35	and	and	CCONJ
cana-4022	37	36	proper	proper	ADJ
cana-4022	37	37	data	datum	NOUN
cana-4022	37	38	pre	pre	ADJ
cana-4022	37	39	-	-	NOUN
cana-4022	37	40	processing	processing	ADJ
cana-4022	37	41	.	.	PUNCT
cana-4022	38	1	thus	thus	ADV
cana-4022	38	2	,	,	PUNCT
cana-4022	38	3	these	these	DET
cana-4022	38	4	studies	study	NOUN
cana-4022	38	5	support	support	VERB
cana-4022	38	6	the	the	DET
cana-4022	38	7	idea	idea	NOUN
cana-4022	38	8	of	of	ADP
cana-4022	38	9	model	model	NOUN
cana-4022	38	10	selection	selection	NOUN
cana-4022	38	11	that	that	PRON
cana-4022	38	12	must	must	AUX
cana-4022	38	13	not	not	PART
cana-4022	38	14	depend	depend	VERB
cana-4022	38	15	on	on	ADP
cana-4022	38	16	the	the	DET
cana-4022	38	17	general	general	ADJ
cana-4022	38	18	presumption	presumption	NOUN
cana-4022	38	19	of	of	ADP
cana-4022	38	20	the	the	DET
cana-4022	38	21	learning	learning	NOUN
cana-4022	38	22	paradigm	paradigm	NOUN
cana-4022	38	23	but	but	CCONJ
cana-4022	38	24	on	on	ADP
cana-4022	38	25	the	the	DET
cana-4022	38	26	characteristics	characteristic	NOUN
cana-4022	38	27	of	of	ADP
cana-4022	38	28	the	the	DET
cana-4022	38	29	data	datum	NOUN
cana-4022	38	30	.	.	PUNCT
cana-4022	39	1	a	a	DET
cana-4022	39	2	comparative	comparative	ADJ
cana-4022	39	3	analyses	analysis	NOUN
cana-4022	39	4	over	over	ADP
cana-4022	39	5	supervised	supervised	ADJ
cana-4022	39	6	and	and	CCONJ
cana-4022	39	7	unsupervised	unsupervised	ADJ
cana-4022	39	8	learning	learning	NOUN
cana-4022	39	9	have	have	AUX
cana-4022	39	10	been	be	AUX
cana-4022	39	11	made	make	VERB
cana-4022	39	12	by	by	ADP
cana-4022	39	13	sathya	sathya	PROPN
cana-4022	39	14	and	and	CCONJ
cana-4022	39	15	abraham	abraham	PROPN
cana-4022	39	16	(	(	PUNCT
cana-4022	39	17	2013	2013	NUM
cana-4022	39	18	)	)	PUNCT
cana-4022	39	19	concerning	concern	VERB
cana-4022	39	20	the	the	DET
cana-4022	39	21	performance	performance	NOUN
cana-4022	39	22	of	of	ADP
cana-4022	39	23	several	several	ADJ
cana-4022	39	24	algorithms	algorithm	NOUN
cana-4022	39	25	for	for	ADP
cana-4022	39	26	pattern	pattern	NOUN
cana-4022	39	27	classification	classification	NOUN
cana-4022	39	28	.	.	PUNCT
cana-4022	40	1	their	their	PRON
cana-4022	40	2	results	result	NOUN
cana-4022	40	3	show	show	VERB
cana-4022	40	4	that	that	SCONJ
cana-4022	40	5	as	as	ADP
cana-4022	40	6	with	with	ADP
cana-4022	40	7	other	other	ADJ
cana-4022	40	8	recent	recent	ADJ
cana-4022	40	9	studies	study	NOUN
cana-4022	40	10	,	,	PUNCT
cana-4022	40	11	more	more	ADV
cana-4022	40	12	structured	structured	ADJ
cana-4022	40	13	learning	learning	NOUN
cana-4022	40	14	models	model	NOUN
cana-4022	40	15	are	be	AUX
cana-4022	40	16	more	more	ADV
cana-4022	40	17	accurate	accurate	ADJ
cana-4022	40	18	in	in	ADP
cana-4022	40	19	supervised	supervised	ADJ
cana-4022	40	20	tasks	task	NOUN
cana-4022	40	21	more	more	ADV
cana-4022	40	22	than	than	ADP
cana-4022	40	23	unsupervised	unsupervised	ADJ
cana-4022	40	24	ones	one	NOUN
cana-4022	40	25	but	but	CCONJ
cana-4022	40	26	have	have	VERB
cana-4022	40	27	a	a	DET
cana-4022	40	28	good	good	ADJ
cana-4022	40	29	use	use	NOUN
cana-4022	40	30	in	in	ADP
cana-4022	40	31	exploratory	exploratory	ADJ
cana-4022	40	32	data	datum	NOUN
cana-4022	40	33	analysis	analysis	NOUN
cana-4022	40	34	,	,	PUNCT
cana-4022	40	35	anomaly	anomaly	NOUN
cana-4022	40	36	detection	detection	NOUN
cana-4022	40	37	,	,	PUNCT
cana-4022	40	38	and	and	CCONJ
cana-4022	40	39	clustering	clustering	ADJ
cana-4022	40	40	tasks	task	NOUN
cana-4022	40	41	.	.	PUNCT
cana-4022	41	1	they	they	PRON
cana-4022	41	2	also	also	ADV
cana-4022	41	3	suggest	suggest	VERB
cana-4022	41	4	that	that	SCONJ
cana-4022	41	5	in	in	ADP
cana-4022	41	6	the	the	DET
cana-4022	41	7	practice	practice	NOUN
cana-4022	41	8	,	,	PUNCT
cana-4022	41	9	the	the	DET
cana-4022	41	10	use	use	NOUN
cana-4022	41	11	of	of	ADP
cana-4022	41	12	model	model	NOUN
cana-4022	41	13	-	-	PUNCT
cana-4022	41	14	viewcontroller	viewcontroller	NOUN
cana-4022	41	15	architecture	architecture	NOUN
cana-4022	41	16	,	,	PUNCT
cana-4022	41	17	and	and	CCONJ
cana-4022	41	18	other	other	ADJ
cana-4022	41	19	similar	similar	ADJ
cana-4022	41	20	approaches	approach	NOUN
cana-4022	41	21	that	that	PRON
cana-4022	41	22	are	be	AUX
cana-4022	41	23	based	base	VERB
cana-4022	41	24	on	on	ADP
cana-4022	41	25	the	the	DET
cana-4022	41	26	complementarity	complementarity	NOUN
cana-4022	41	27	of	of	ADP
cana-4022	41	28	both	both	DET
cana-4022	41	29	paradigms	paradigm	NOUN
cana-4022	41	30	,	,	PUNCT
cana-4022	41	31	might	might	AUX
cana-4022	41	32	be	be	AUX
cana-4022	41	33	a	a	DET
cana-4022	41	34	better	well	ADJ
cana-4022	41	35	solution	solution	NOUN
cana-4022	41	36	.	.	PUNCT
cana-4022	42	1	this	this	PRON
cana-4022	42	2	is	be	AUX
cana-4022	42	3	in	in	ADP
cana-4022	42	4	conformity	conformity	NOUN
cana-4022	42	5	with	with	ADP
cana-4022	42	6	other	other	ADJ
cana-4022	42	7	research	research	NOUN
cana-4022	42	8	that	that	PRON
cana-4022	42	9	encourages	encourage	VERB
cana-4022	42	10	the	the	DET
cana-4022	42	11	combination	combination	NOUN
cana-4022	42	12	of	of	ADP
cana-4022	42	13	the	the	DET
cana-4022	42	14	two	two	NUM
cana-4022	42	15	approaches	approach	NOUN
cana-4022	42	16	in	in	ADP
cana-4022	42	17	an	an	DET
cana-4022	42	18	attempt	attempt	NOUN
cana-4022	42	19	to	to	PART
cana-4022	42	20	improve	improve	VERB
cana-4022	42	21	the	the	DET
cana-4022	42	22	model	model	NOUN
cana-4022	42	23	stability	stability	NOUN
cana-4022	42	24	.	.	PUNCT
cana-4022	43	1	this	this	DET
cana-4022	43	2	type	type	NOUN
cana-4022	43	3	of	of	ADP
cana-4022	43	4	learning	learning	NOUN
cana-4022	43	5	has	have	AUX
cana-4022	43	6	elicited	elicit	VERB
cana-4022	43	7	interest	interest	NOUN
cana-4022	43	8	over	over	ADP
cana-4022	43	9	time	time	NOUN
cana-4022	43	10	because	because	SCONJ
cana-4022	43	11	it	it	PRON
cana-4022	43	12	is	be	AUX
cana-4022	43	13	capable	capable	ADJ
cana-4022	43	14	of	of	ADP
cana-4022	43	15	learning	learn	VERB
cana-4022	43	16	different	different	ADJ
cana-4022	43	17	representations	representation	NOUN
cana-4022	43	18	from	from	ADP
cana-4022	43	19	large	large	ADJ
cana-4022	43	20	volumes	volume	NOUN
cana-4022	43	21	of	of	ADP
cana-4022	43	22	data	datum	NOUN
cana-4022	43	23	which	which	PRON
cana-4022	43	24	are	be	AUX
cana-4022	43	25	not	not	PART
cana-4022	43	26	labeled	label	VERB
cana-4022	43	27	.	.	PUNCT
cana-4022	44	1	yao	yao	PROPN
cana-4022	44	2	et	et	PROPN
cana-4022	44	3	al	al	PROPN
cana-4022	44	4	.	.	PROPN
cana-4022	44	5	(	(	PUNCT
cana-4022	44	6	2021	2021	NUM
cana-4022	44	7	)	)	PUNCT
cana-4022	44	8	proposed	propose	VERB
cana-4022	44	9	seqbased	seqbase	VERB
cana-4022	44	10	co	co	NOUN
cana-4022	44	11	-	-	NOUN
cana-4022	44	12	training	training	NOUN
cana-4022	44	13	or	or	CCONJ
cana-4022	44	14	seco	seco	NOUN
cana-4022	44	15	,	,	PUNCT
cana-4022	44	16	a	a	DET
cana-4022	44	17	sequence	sequence	NOUN
cana-4022	44	18	-	-	PUNCT
cana-4022	44	19	based	base	VERB
cana-4022	44	20	supervision	supervision	NOUN
cana-4022	44	21	method	method	NOUN
cana-4022	44	22	for	for	ADP
cana-4022	44	23	unsupervised	unsupervised	ADJ
cana-4022	44	24	representation	representation	NOUN
cana-4022	44	25	learning	learning	NOUN
cana-4022	44	26	and	and	CCONJ
cana-4022	44	27	further	far	ADV
cana-4022	44	28	proved	prove	VERB
cana-4022	44	29	that	that	SCONJ
cana-4022	44	30	unsupervised	unsupervised	ADJ
cana-4022	44	31	approaches	approach	NOUN
cana-4022	44	32	can	can	AUX
cana-4022	44	33	be	be	AUX
cana-4022	44	34	almost	almost	ADV
cana-4022	44	35	comparable	comparable	ADJ
cana-4022	44	36	with	with	ADP
cana-4022	44	37	the	the	DET
cana-4022	44	38	supervised	supervised	ADJ
cana-4022	44	39	ones	one	NOUN
cana-4022	44	40	under	under	ADP
cana-4022	44	41	certain	certain	ADJ
cana-4022	44	42	circumstances	circumstance	NOUN
cana-4022	44	43	.	.	PUNCT
cana-4022	45	1	some	some	DET
cana-4022	45	2	researchers	researcher	NOUN
cana-4022	45	3	suggest	suggest	VERB
cana-4022	45	4	that	that	SCONJ
cana-4022	45	5	learning	learn	VERB
cana-4022	45	6	sequential	sequential	ADJ
cana-4022	45	7	dependencies	dependency	NOUN
cana-4022	45	8	indeed	indeed	ADV
cana-4022	45	9	has	have	VERB
cana-4022	45	10	a	a	DET
cana-4022	45	11	potential	potential	NOUN
cana-4022	45	12	for	for	ADP
cana-4022	45	13	enhancing	enhance	VERB
cana-4022	45	14	the	the	DET
cana-4022	45	15	corresponding	correspond	VERB
cana-4022	45	16	feature	feature	NOUN
cana-4022	45	17	extraction	extraction	NOUN
cana-4022	45	18	in	in	ADP
cana-4022	45	19	these	these	DET
cana-4022	45	20	models	model	NOUN
cana-4022	45	21	and	and	CCONJ
cana-4022	45	22	thus	thus	ADV
cana-4022	45	23	making	make	VERB
cana-4022	45	24	the	the	DET
cana-4022	45	25	model	model	NOUN
cana-4022	45	26	more	more	ADV
cana-4022	45	27	convenient	convenient	ADJ
cana-4022	45	28	for	for	ADP
cana-4022	45	29	working	work	VERB
cana-4022	45	30	with	with	ADP
cana-4022	45	31	complex	complex	ADJ
cana-4022	45	32	data	data	NOUN
cana-4022	45	33	sets	set	NOUN
cana-4022	45	34	.	.	PUNCT
cana-4022	46	1	in	in	ADP
cana-4022	46	2	the	the	DET
cana-4022	46	3	same	same	ADJ
cana-4022	46	4	year	year	NOUN
cana-4022	46	5	,	,	PUNCT
cana-4022	46	6	zhang	zhang	PROPN
cana-4022	46	7	et	et	PROPN
cana-4022	46	8	al	al	PROPN
cana-4022	46	9	.	.	PROPN
cana-4022	46	10	suggested	suggest	VERB
cana-4022	46	11	fully	fully	ADV
cana-4022	46	12	convolutional	convolutional	ADJ
cana-4022	46	13	adaptation	adaptation	NOUN
cana-4022	46	14	networks	network	NOUN
cana-4022	46	15	for	for	ADP
cana-4022	46	16	semantic	semantic	ADJ
cana-4022	46	17	segmentation	segmentation	NOUN
cana-4022	46	18	pointing	point	VERB
cana-4022	46	19	out	out	ADP
cana-4022	46	20	to	to	ADP
cana-4022	46	21	the	the	DET
cana-4022	46	22	fact	fact	NOUN
cana-4022	46	23	that	that	SCONJ
cana-4022	46	24	unsupervised	unsupervised	ADJ
cana-4022	46	25	models	model	NOUN
cana-4022	46	26	can	can	AUX
cana-4022	46	27	be	be	AUX
cana-4022	46	28	used	use	VERB
cana-4022	46	29	for	for	ADP
cana-4022	46	30	the	the	DET
cana-4022	46	31	generalizable	generalizable	ADJ
cana-4022	46	32	features	feature	NOUN
cana-4022	46	33	of	of	ADP
cana-4022	46	34	the	the	DET
cana-4022	46	35	given	give	VERB
cana-4022	46	36	tasks	task	NOUN
cana-4022	46	37	.	.	PUNCT
cana-4022	47	1	according	accord	VERB
cana-4022	47	2	to	to	ADP
cana-4022	47	3	their	their	PRON
cana-4022	47	4	findings	finding	NOUN
cana-4022	47	5	,	,	PUNCT
cana-4022	47	6	the	the	DET
cana-4022	47	7	accuracy	accuracy	NOUN
cana-4022	47	8	and	and	CCONJ
cana-4022	47	9	precision	precision	NOUN
cana-4022	47	10	of	of	ADP
cana-4022	47	11	the	the	DET
cana-4022	47	12	supervised	supervise	VERB
cana-4022	47	13	models	model	NOUN
cana-4022	47	14	is	be	AUX
cana-4022	47	15	better	well	ADJ
cana-4022	47	16	,	,	PUNCT
cana-4022	47	17	but	but	CCONJ
cana-4022	47	18	the	the	DET
cana-4022	47	19	unsupervised	unsupervised	ADJ
cana-4022	47	20	models	model	NOUN
cana-4022	47	21	are	be	AUX
cana-4022	47	22	more	more	ADV
cana-4022	47	23	adaptable	adaptable	ADJ
cana-4022	47	24	than	than	ADP
cana-4022	47	25	the	the	DET
cana-4022	47	26	former	former	ADJ
cana-4022	47	27	in	in	ADP
cana-4022	47	28	the	the	DET
cana-4022	47	29	case	case	NOUN
cana-4022	47	30	of	of	ADP
cana-4022	47	31	high	high	ADJ
cana-4022	47	32	-	-	PUNCT
cana-4022	47	33	dimensional	dimensional	ADJ
cana-4022	47	34	explanations	explanation	NOUN
cana-4022	47	35	of	of	ADP
cana-4022	47	36	phenomena	phenomenon	NOUN
cana-4022	47	37	.	.	PUNCT
cana-4022	48	1	from	from	ADP
cana-4022	48	2	the	the	DET
cana-4022	48	3	above	above	ADJ
cana-4022	48	4	studies	study	NOUN
cana-4022	48	5	it	it	PRON
cana-4022	48	6	is	be	AUX
cana-4022	48	7	evident	evident	ADJ
cana-4022	48	8	that	that	SCONJ
cana-4022	48	9	although	although	SCONJ
cana-4022	48	10	supervised	supervised	ADJ
cana-4022	48	11	learning	learning	NOUN
cana-4022	48	12	still	still	ADV
cana-4022	48	13	receives	receive	VERB
cana-4022	48	14	the	the	DET
cana-4022	48	15	most	most	ADJ
cana-4022	48	16	uses	use	NOUN
cana-4022	48	17	in	in	ADP
cana-4022	48	18	structured	structured	ADJ
cana-4022	48	19	classification	classification	NOUN
cana-4022	48	20	problems	problem	NOUN
cana-4022	48	21	the	the	DET
cana-4022	48	22	unsupervised	unsupervised	ADJ
cana-4022	48	23	models	model	NOUN
cana-4022	48	24	offer	offer	VERB
cana-4022	48	25	great	great	ADJ
cana-4022	48	26	benefits	benefit	NOUN
cana-4022	48	27	in	in	ADP
cana-4022	48	28	handling	handle	VERB
cana-4022	48	29	massive	massive	ADJ
cana-4022	48	30	amounts	amount	NOUN
cana-4022	48	31	of	of	ADP
cana-4022	48	32	unidentified	unidentified	ADJ
cana-4022	48	33	data	datum	NOUN
cana-4022	48	34	that	that	PRON
cana-4022	48	35	are	be	AUX
cana-4022	48	36	usually	usually	ADV
cana-4022	48	37	high	high	ADJ
cana-4022	48	38	dimensional	dimensional	ADJ
cana-4022	48	39	.	.	PUNCT
cana-4022	49	1	statistical	statistical	ADJ
cana-4022	49	2	methods	method	NOUN
cana-4022	49	3	like	like	ADP
cana-4022	49	4	anova	anova	X
cana-4022	49	5	and	and	CCONJ
cana-4022	49	6	correlation	correlation	NOUN
cana-4022	49	7	studies	study	NOUN
cana-4022	49	8	that	that	PRON
cana-4022	49	9	have	have	AUX
cana-4022	49	10	been	be	AUX
cana-4022	49	11	used	use	VERB
cana-4022	49	12	in	in	ADP
cana-4022	49	13	this	this	DET
cana-4022	49	14	present	present	ADJ
cana-4022	49	15	study	study	NOUN
cana-4022	49	16	enhance	enhance	VERB
cana-4022	49	17	the	the	DET
cana-4022	49	18	comparative	comparative	ADJ
cana-4022	49	19	analysis	analysis	NOUN
cana-4022	49	20	of	of	ADP
cana-4022	49	21	these	these	DET
cana-4022	49	22	paradigms	paradigm	NOUN
cana-4022	49	23	.	.	PUNCT
cana-4022	50	1	by	by	ADP
cana-4022	50	2	comparing	compare	VERB
cana-4022	50	3	the	the	DET
cana-4022	50	4	supervised	supervised	ADJ
cana-4022	50	5	and	and	CCONJ
cana-4022	50	6	unsupervised	unsupervised	ADJ
cana-4022	50	7	models	model	NOUN
cana-4022	50	8	on	on	ADP
cana-4022	50	9	various	various	ADJ
cana-4022	50	10	dataset	dataset	NOUN
cana-4022	50	11	,	,	PUNCT
cana-4022	50	12	this	this	DET
cana-4022	50	13	paper	paper	NOUN
cana-4022	50	14	helps	help	VERB
cana-4022	50	15	the	the	DET
cana-4022	50	16	ongoing	ongoing	ADJ
cana-4022	50	17	discussion	discussion	NOUN
cana-4022	50	18	about	about	ADP
cana-4022	50	19	efficient	efficient	ADJ
cana-4022	50	20	utilization	utilization	NOUN
cana-4022	50	21	of	of	ADP
cana-4022	50	22	the	the	DET
cana-4022	50	23	machine	machine	NOUN
cana-4022	50	24	learning	learning	NOUN
cana-4022	50	25	approach	approach	NOUN
cana-4022	50	26	.	.	PUNCT
cana-4022	51	1	3	3	X
cana-4022	51	2	.	.	X
cana-4022	51	3	research	research	NOUN
cana-4022	51	4	gap	gap	NOUN
cana-4022	51	5	although	although	SCONJ
cana-4022	51	6	the	the	DET
cana-4022	51	7	supervised	supervised	ADJ
cana-4022	51	8	and	and	CCONJ
cana-4022	51	9	unsupervised	unsupervised	ADJ
cana-4022	51	10	learning	learning	NOUN
cana-4022	51	11	models	model	NOUN
cana-4022	51	12	have	have	AUX
cana-4022	51	13	been	be	AUX
cana-4022	51	14	widely	widely	ADV
cana-4022	51	15	applied	apply	VERB
cana-4022	51	16	in	in	ADP
cana-4022	51	17	different	different	ADJ
cana-4022	51	18	fields	field	NOUN
cana-4022	51	19	and	and	CCONJ
cana-4022	51	20	tasks	task	NOUN
cana-4022	51	21	,	,	PUNCT
cana-4022	51	22	few	few	ADJ
cana-4022	51	23	comparative	comparative	ADJ
cana-4022	51	24	works	work	NOUN
cana-4022	51	25	have	have	AUX
cana-4022	51	26	been	be	AUX
cana-4022	51	27	done	do	VERB
cana-4022	51	28	to	to	PART
cana-4022	51	29	evaluate	evaluate	VERB
cana-4022	51	30	performance	performance	NOUN
cana-4022	51	31	of	of	ADP
cana-4022	51	32	identifying	identify	VERB
cana-4022	51	33	different	different	ADJ
cana-4022	51	34	types	type	NOUN
cana-4022	51	35	of	of	ADP
cana-4022	51	36	data	datum	NOUN
cana-4022	51	37	structures	structure	NOUN
cana-4022	51	38	.	.	PUNCT
cana-4022	52	1	a	a	DET
cana-4022	52	2	majority	majority	NOUN
cana-4022	52	3	of	of	ADP
cana-4022	52	4	the	the	DET
cana-4022	52	5	papers	paper	NOUN
cana-4022	52	6	that	that	PRON
cana-4022	52	7	have	have	AUX
cana-4022	52	8	been	be	AUX
cana-4022	52	9	published	publish	VERB
cana-4022	52	10	and	and	CCONJ
cana-4022	52	11	are	be	AUX
cana-4022	52	12	available	available	ADJ
cana-4022	52	13	in	in	ADP
cana-4022	52	14	the	the	DET
cana-4022	52	15	literature	literature	NOUN
cana-4022	52	16	review	review	PROPN
cana-4022	52	17	predominantly	predominantly	ADV
cana-4022	52	18	examine	examine	VERB
cana-4022	52	19	either	either	CCONJ
cana-4022	52	20	enhancements	enhancement	NOUN
cana-4022	52	21	to	to	ADP
cana-4022	52	22	these	these	DET
cana-4022	52	23	types	type	NOUN
cana-4022	52	24	of	of	ADP
cana-4022	52	25	models	model	NOUN
cana-4022	52	26	or	or	CCONJ
cana-4022	52	27	illustrate	illustrate	VERB
cana-4022	52	28	the	the	DET
cana-4022	52	29	application	application	NOUN
cana-4022	52	30	of	of	ADP
cana-4022	52	31	these	these	DET
cana-4022	52	32	models	model	NOUN
cana-4022	52	33	on	on	ADP
cana-4022	52	34	particular	particular	ADJ
cana-4022	52	35	cases	case	NOUN
cana-4022	52	36	in	in	ADP
cana-4022	52	37	isolation	isolation	NOUN
cana-4022	52	38	,	,	PUNCT
cana-4022	52	39	without	without	ADP
cana-4022	52	40	conducting	conduct	VERB
cana-4022	52	41	an	an	DET
cana-4022	52	42	assessment	assessment	NOUN
cana-4022	52	43	of	of	ADP
cana-4022	52	44	their	their	PRON
cana-4022	52	45	advantages	advantage	NOUN
cana-4022	52	46	and	and	CCONJ
cana-4022	52	47	disadvantages	disadvantage	NOUN
cana-4022	52	48	.	.	PUNCT
cana-4022	53	1	furthermore	furthermore	ADV
cana-4022	53	2	,	,	PUNCT
cana-4022	53	3	even	even	ADV
cana-4022	53	4	though	though	SCONJ
cana-4022	53	5	supervised	supervised	ADJ
cana-4022	53	6	models	model	NOUN
cana-4022	53	7	could	could	AUX
cana-4022	53	8	be	be	AUX
cana-4022	53	9	more	more	ADV
cana-4022	53	10	effective	effective	ADJ
cana-4022	53	11	in	in	ADP
cana-4022	53	12	the	the	DET
cana-4022	53	13	predictive	predictive	ADJ
cana-4022	53	14	task	task	NOUN
cana-4022	53	15	,	,	PUNCT
cana-4022	53	16	there	there	PRON
cana-4022	53	17	is	be	VERB
cana-4022	53	18	still	still	ADV
cana-4022	53	19	limited	limit	VERB
cana-4022	53	20	research	research	NOUN
cana-4022	53	21	comparing	compare	VERB
cana-4022	53	22	the	the	DET
cana-4022	53	23	effectiveness	effectiveness	NOUN
cana-4022	53	24	of	of	ADP
cana-4022	53	25	unsupervised	unsupervised	ADJ
cana-4022	53	26	models	model	NOUN
cana-4022	53	27	when	when	SCONJ
cana-4022	53	28	it	it	PRON
cana-4022	53	29	comes	come	VERB
cana-4022	53	30	to	to	ADP
cana-4022	53	31	unstructured	unstructured	ADJ
cana-4022	53	32	and	and	CCONJ
cana-4022	53	33	high	high	ADV
cana-4022	53	34	-	-	PUNCT
cana-4022	53	35	dimensional	dimensional	ADJ
cana-4022	53	36	data	datum	NOUN
cana-4022	53	37	.	.	PUNCT
cana-4022	54	1	however	however	ADV
cana-4022	54	2	,	,	PUNCT
cana-4022	54	3	there	there	PRON
cana-4022	54	4	is	be	VERB
cana-4022	54	5	scant	scant	ADJ
cana-4022	54	6	evidence	evidence	NOUN
cana-4022	54	7	that	that	PRON
cana-4022	54	8	uses	use	VERB
cana-4022	54	9	more	more	ADV
cana-4022	54	10	credible	credible	ADJ
cana-4022	54	11	tests	test	NOUN
cana-4022	54	12	that	that	PRON
cana-4022	54	13	can	can	AUX
cana-4022	54	14	measure	measure	VERB
cana-4022	54	15	the	the	DET
cana-4022	54	16	degree	degree	NOUN
cana-4022	54	17	of	of	ADP
cana-4022	54	18	performance	performance	NOUN
cana-4022	54	19	difference	difference	NOUN
cana-4022	54	20	communications	communication	NOUN
cana-4022	54	21	on	on	ADP
cana-4022	54	22	applied	apply	VERB
cana-4022	54	23	nonlinear	nonlinear	ADJ
cana-4022	54	24	analysis	analysis	NOUN
cana-4022	54	25	issn	issn	NOUN
cana-4022	54	26	:	:	PUNCT
cana-4022	54	27	1074	1074	NUM
cana-4022	54	28	-	-	PUNCT
cana-4022	54	29	133x	133x	NUM
cana-4022	54	30	vol	vol	NOUN
cana-4022	54	31	32	32	NUM
cana-4022	54	32	no	no	NOUN
cana-4022	54	33	.	.	PUNCT
cana-4022	55	1	9s	9s	NUM
cana-4022	55	2	(	(	PUNCT
cana-4022	55	3	2025	2025	NUM
cana-4022	55	4	)	)	PUNCT
cana-4022	55	5	863	863	NUM
cana-4022	55	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-4022	55	7	statistically	statistically	ADV
cana-4022	55	8	by	by	ADP
cana-4022	55	9	using	use	VERB
cana-4022	55	10	tests	test	NOUN
cana-4022	55	11	such	such	ADJ
cana-4022	55	12	as	as	ADP
cana-4022	55	13	anova	anova	PROPN
cana-4022	55	14	and	and	CCONJ
cana-4022	55	15	correlation	correlation	NOUN
cana-4022	55	16	tests	test	NOUN
cana-4022	55	17	.	.	PUNCT
cana-4022	56	1	this	this	DET
cana-4022	56	2	paper	paper	NOUN
cana-4022	56	3	will	will	AUX
cana-4022	56	4	help	help	VERB
cana-4022	56	5	fill	fill	VERB
cana-4022	56	6	the	the	DET
cana-4022	56	7	gaps	gap	NOUN
cana-4022	56	8	by	by	ADP
cana-4022	56	9	comparing	compare	VERB
cana-4022	56	10	supervised	supervised	ADJ
cana-4022	56	11	and	and	CCONJ
cana-4022	56	12	unsupervised	unsupervised	ADJ
cana-4022	56	13	models	model	NOUN
cana-4022	56	14	on	on	ADP
cana-4022	56	15	different	different	ADJ
cana-4022	56	16	datasets	dataset	NOUN
cana-4022	56	17	in	in	ADP
cana-4022	56	18	a	a	DET
cana-4022	56	19	more	more	ADV
cana-4022	56	20	organized	organize	VERB
cana-4022	56	21	manner	manner	NOUN
cana-4022	56	22	by	by	ADP
cana-4022	56	23	using	use	VERB
cana-4022	56	24	statistical	statistical	ADJ
cana-4022	56	25	methods	method	NOUN
cana-4022	56	26	.	.	PUNCT
cana-4022	57	1	4	4	X
cana-4022	57	2	.	.	X
cana-4022	57	3	conceptual	conceptual	ADJ
cana-4022	57	4	framework	framework	NOUN
cana-4022	57	5	therefore	therefore	ADV
cana-4022	57	6	,	,	PUNCT
cana-4022	57	7	this	this	DET
cana-4022	57	8	study	study	NOUN
cana-4022	57	9	aims	aim	VERB
cana-4022	57	10	at	at	ADP
cana-4022	57	11	developing	develop	VERB
cana-4022	57	12	the	the	DET
cana-4022	57	13	conceptual	conceptual	ADJ
cana-4022	57	14	framework	framework	NOUN
cana-4022	57	15	that	that	PRON
cana-4022	57	16	shall	shall	AUX
cana-4022	57	17	allows	allow	VERB
cana-4022	57	18	for	for	ADP
cana-4022	57	19	making	make	VERB
cana-4022	57	20	comparison	comparison	NOUN
cana-4022	57	21	on	on	ADP
cana-4022	57	22	the	the	DET
cana-4022	57	23	accuracy	accuracy	NOUN
cana-4022	57	24	and	and	CCONJ
cana-4022	57	25	error	error	NOUN
cana-4022	57	26	rates	rate	NOUN
cana-4022	57	27	of	of	ADP
cana-4022	57	28	supervised	supervised	ADJ
cana-4022	57	29	learning	learning	NOUN
cana-4022	57	30	and	and	CCONJ
cana-4022	57	31	unsupervised	unsupervised	ADJ
cana-4022	57	32	learning	learning	NOUN
cana-4022	57	33	and	and	CCONJ
cana-4022	57	34	how	how	SCONJ
cana-4022	57	35	they	they	PRON
cana-4022	57	36	perform	perform	VERB
cana-4022	57	37	on	on	ADP
cana-4022	57	38	different	different	ADJ
cana-4022	57	39	datasets	dataset	NOUN
cana-4022	57	40	.	.	PUNCT
cana-4022	58	1	depending	depend	VERB
cana-4022	58	2	on	on	ADP
cana-4022	58	3	the	the	DET
cana-4022	58	4	class	class	NOUN
cana-4022	58	5	of	of	ADP
cana-4022	58	6	models	model	NOUN
cana-4022	58	7	,	,	PUNCT
cana-4022	58	8	its	its	PRON
cana-4022	58	9	performance	performance	NOUN
cana-4022	58	10	indicators	indicator	NOUN
cana-4022	58	11	include	include	VERB
cana-4022	58	12	precision	precision	NOUN
cana-4022	58	13	,	,	PUNCT
cana-4022	58	14	recall	recall	NOUN
cana-4022	58	15	,	,	PUNCT
cana-4022	58	16	f1	f1	NOUN
cana-4022	58	17	-	-	PUNCT
cana-4022	58	18	score	score	NOUN
cana-4022	58	19	for	for	ADP
cana-4022	58	20	supervised	supervised	ADJ
cana-4022	58	21	learning	learning	NOUN
cana-4022	58	22	or	or	CCONJ
cana-4022	58	23	clustering	cluster	VERB
cana-4022	58	24	efficiency	efficiency	NOUN
cana-4022	58	25	and	and	CCONJ
cana-4022	58	26	capability	capability	NOUN
cana-4022	58	27	for	for	ADP
cana-4022	58	28	anomaly	anomaly	NOUN
cana-4022	58	29	detection	detection	NOUN
cana-4022	58	30	for	for	ADP
cana-4022	58	31	the	the	DET
cana-4022	58	32	unsupervised	unsupervised	ADJ
cana-4022	58	33	learning	learning	NOUN
cana-4022	58	34	models	model	NOUN
cana-4022	58	35	.	.	PUNCT
cana-4022	59	1	the	the	DET
cana-4022	59	2	study	study	NOUN
cana-4022	59	3	also	also	ADV
cana-4022	59	4	uses	use	VERB
cana-4022	59	5	statistical	statistical	ADJ
cana-4022	59	6	analysis	analysis	NOUN
cana-4022	59	7	techniques	technique	NOUN
cana-4022	59	8	to	to	PART
cana-4022	59	9	measure	measure	VERB
cana-4022	59	10	differences	difference	NOUN
cana-4022	59	11	and	and	CCONJ
cana-4022	59	12	associations	association	NOUN
cana-4022	59	13	as	as	SCONJ
cana-4022	59	14	regards	regard	VERB
cana-4022	59	15	the	the	DET
cana-4022	59	16	models	model	NOUN
cana-4022	59	17	,	,	PUNCT
cana-4022	59	18	performance	performance	NOUN
cana-4022	59	19	.	.	PUNCT
cana-4022	60	1	the	the	DET
cana-4022	60	2	implicit	implicit	ADJ
cana-4022	60	3	premise	premise	NOUN
cana-4022	60	4	is	be	AUX
cana-4022	60	5	that	that	SCONJ
cana-4022	60	6	data	data	NOUN
cana-4022	60	7	size	size	NOUN
cana-4022	60	8	constitutes	constitute	VERB
cana-4022	60	9	one	one	NUM
cana-4022	60	10	of	of	ADP
cana-4022	60	11	the	the	DET
cana-4022	60	12	key	key	ADJ
cana-4022	60	13	factors	factor	NOUN
cana-4022	60	14	that	that	PRON
cana-4022	60	15	affect	affect	VERB
cana-4022	60	16	the	the	DET
cana-4022	60	17	learning	learning	NOUN
cana-4022	60	18	technique	technique	NOUN
cana-4022	60	19	in	in	ADP
cana-4022	60	20	terms	term	NOUN
cana-4022	60	21	of	of	ADP
cana-4022	60	22	accuracy	accuracy	NOUN
cana-4022	60	23	,	,	PUNCT
cana-4022	60	24	errors	error	NOUN
cana-4022	60	25	,	,	PUNCT
cana-4022	60	26	and	and	CCONJ
cana-4022	60	27	clustering	cluster	VERB
cana-4022	60	28	.	.	PUNCT
cana-4022	61	1	by	by	ADP
cana-4022	61	2	applying	apply	VERB
cana-4022	61	3	this	this	DET
cana-4022	61	4	approach	approach	NOUN
cana-4022	61	5	,	,	PUNCT
cana-4022	61	6	the	the	DET
cana-4022	61	7	proposed	propose	VERB
cana-4022	61	8	framework	framework	NOUN
cana-4022	61	9	offers	offer	VERB
cana-4022	61	10	an	an	DET
cana-4022	61	11	organized	organized	ADJ
cana-4022	61	12	strategy	strategy	NOUN
cana-4022	61	13	of	of	ADP
cana-4022	61	14	assessing	assess	VERB
cana-4022	61	15	ai	ai	PROPN
cana-4022	61	16	model	model	NOUN
cana-4022	61	17	selection	selection	NOUN
cana-4022	61	18	criteria	criterion	NOUN
cana-4022	61	19	.	.	PUNCT
cana-4022	62	1	5	5	X
cana-4022	62	2	.	.	X
cana-4022	62	3	hypothesis	hypothesis	NOUN
cana-4022	62	4	the	the	DET
cana-4022	62	5	study	study	NOUN
cana-4022	62	6	formulates	formulate	VERB
cana-4022	62	7	the	the	DET
cana-4022	62	8	following	follow	VERB
cana-4022	62	9	hypotheses	hypothesis	NOUN
cana-4022	62	10	to	to	PART
cana-4022	62	11	test	test	VERB
cana-4022	62	12	the	the	DET
cana-4022	62	13	comparative	comparative	ADJ
cana-4022	62	14	performance	performance	NOUN
cana-4022	62	15	of	of	ADP
cana-4022	62	16	supervised	supervised	ADJ
cana-4022	62	17	and	and	CCONJ
cana-4022	62	18	unsupervised	unsupervised	ADJ
cana-4022	62	19	learning	learning	NOUN
cana-4022	62	20	models	model	NOUN
cana-4022	62	21	:	:	PUNCT
cana-4022	62	22	h1	h1	NOUN
cana-4022	62	23	:	:	PUNCT
cana-4022	62	24	supervised	supervised	ADJ
cana-4022	62	25	learning	learning	NOUN
cana-4022	62	26	models	model	NOUN
cana-4022	62	27	(	(	PUNCT
cana-4022	62	28	decision	decision	NOUN
cana-4022	62	29	trees	tree	NOUN
cana-4022	62	30	,	,	PUNCT
cana-4022	62	31	svm	svm	ADJ
cana-4022	62	32	)	)	PUNCT
cana-4022	62	33	will	will	AUX
cana-4022	62	34	exhibit	exhibit	VERB
cana-4022	62	35	significantly	significantly	ADV
cana-4022	62	36	higher	high	ADJ
cana-4022	62	37	accuracy	accuracy	NOUN
cana-4022	62	38	and	and	CCONJ
cana-4022	62	39	lower	low	ADJ
cana-4022	62	40	error	error	NOUN
cana-4022	62	41	rates	rate	NOUN
cana-4022	62	42	than	than	ADP
cana-4022	62	43	unsupervised	unsupervised	ADJ
cana-4022	62	44	learning	learning	NOUN
cana-4022	62	45	models	model	NOUN
cana-4022	62	46	(	(	PUNCT
cana-4022	62	47	k	k	NOUN
cana-4022	62	48	-	-	PUNCT
cana-4022	62	49	means	mean	NOUN
cana-4022	62	50	,	,	PUNCT
cana-4022	62	51	autoencoders	autoencoder	NOUN
cana-4022	62	52	)	)	PUNCT
cana-4022	62	53	.	.	PUNCT
cana-4022	63	1	h2	h2	NOUN
cana-4022	63	2	:	:	PUNCT
cana-4022	63	3	model	model	NOUN
cana-4022	63	4	performance	performance	NOUN
cana-4022	63	5	will	will	AUX
cana-4022	63	6	vary	vary	VERB
cana-4022	63	7	significantly	significantly	ADV
cana-4022	63	8	across	across	ADP
cana-4022	63	9	different	different	ADJ
cana-4022	63	10	datasets	dataset	NOUN
cana-4022	63	11	,	,	PUNCT
cana-4022	63	12	with	with	ADP
cana-4022	63	13	supervised	supervised	ADJ
cana-4022	63	14	learning	learning	NOUN
cana-4022	63	15	demonstrating	demonstrate	VERB
cana-4022	63	16	better	well	ADJ
cana-4022	63	17	results	result	NOUN
cana-4022	63	18	in	in	ADP
cana-4022	63	19	structured	structured	ADJ
cana-4022	63	20	data	datum	NOUN
cana-4022	63	21	,	,	PUNCT
cana-4022	63	22	while	while	SCONJ
cana-4022	63	23	unsupervised	unsupervised	ADJ
cana-4022	63	24	models	model	NOUN
cana-4022	63	25	will	will	AUX
cana-4022	63	26	show	show	VERB
cana-4022	63	27	better	well	ADJ
cana-4022	63	28	adaptability	adaptability	NOUN
cana-4022	63	29	in	in	ADP
cana-4022	63	30	high	high	ADV
cana-4022	63	31	-	-	PUNCT
cana-4022	63	32	dimensional	dimensional	ADJ
cana-4022	63	33	or	or	CCONJ
cana-4022	63	34	unstructured	unstructured	ADJ
cana-4022	63	35	data	datum	NOUN
cana-4022	63	36	.	.	PUNCT
cana-4022	64	1	h3	h3	NOUN
cana-4022	64	2	:	:	PUNCT
cana-4022	64	3	there	there	PRON
cana-4022	64	4	is	be	VERB
cana-4022	64	5	a	a	DET
cana-4022	64	6	statistically	statistically	ADV
cana-4022	64	7	significant	significant	ADJ
cana-4022	64	8	correlation	correlation	NOUN
cana-4022	64	9	between	between	ADP
cana-4022	64	10	dataset	dataset	NOUN
cana-4022	64	11	complexity	complexity	NOUN
cana-4022	64	12	and	and	CCONJ
cana-4022	64	13	model	model	NOUN
cana-4022	64	14	accuracy	accuracy	NOUN
cana-4022	64	15	,	,	PUNCT
cana-4022	64	16	with	with	ADP
cana-4022	64	17	supervised	supervised	ADJ
cana-4022	64	18	models	model	NOUN
cana-4022	64	19	being	be	AUX
cana-4022	64	20	more	more	ADV
cana-4022	64	21	sensitive	sensitive	ADJ
cana-4022	64	22	to	to	ADP
cana-4022	64	23	increased	increase	VERB
cana-4022	64	24	data	datum	NOUN
cana-4022	64	25	complexity	complexity	NOUN
cana-4022	64	26	compared	compare	VERB
cana-4022	64	27	to	to	ADP
cana-4022	64	28	unsupervised	unsupervised	ADJ
cana-4022	64	29	models	model	NOUN
cana-4022	64	30	.	.	PUNCT
cana-4022	65	1	6	6	X
cana-4022	65	2	.	.	X
cana-4022	65	3	methods	method	NOUN
cana-4022	65	4	three	three	NUM
cana-4022	65	5	different	different	ADJ
cana-4022	65	6	datasets	dataset	NOUN
cana-4022	65	7	from	from	ADP
cana-4022	65	8	the	the	DET
cana-4022	65	9	public	public	ADJ
cana-4022	65	10	data	datum	NOUN
cana-4022	65	11	repositories	repository	NOUN
cana-4022	65	12	have	have	AUX
cana-4022	65	13	been	be	AUX
cana-4022	65	14	used	use	VERB
cana-4022	65	15	in	in	ADP
cana-4022	65	16	the	the	DET
cana-4022	65	17	research	research	NOUN
cana-4022	65	18	:	:	PUNCT
cana-4022	65	19	a	a	DET
cana-4022	65	20	financial	financial	ADJ
cana-4022	65	21	transactions	transaction	NOUN
cana-4022	65	22	dataset	dataset	VERB
cana-4022	65	23	for	for	ADP
cana-4022	65	24	developing	develop	VERB
cana-4022	65	25	an	an	DET
cana-4022	65	26	efficient	efficient	ADJ
cana-4022	65	27	fraud	fraud	NOUN
cana-4022	65	28	detection	detection	NOUN
cana-4022	65	29	technique	technique	NOUN
cana-4022	65	30	,	,	PUNCT
cana-4022	65	31	a	a	DET
cana-4022	65	32	healthcare	healthcare	NOUN
cana-4022	65	33	dataset	dataset	VERB
cana-4022	65	34	to	to	PART
cana-4022	65	35	classify	classify	VERB
cana-4022	65	36	diseases	disease	NOUN
cana-4022	65	37	and	and	CCONJ
cana-4022	65	38	an	an	DET
cana-4022	65	39	image	image	NOUN
cana-4022	65	40	detection	detection	NOUN
cana-4022	65	41	dataset	dataset	VERB
cana-4022	65	42	for	for	ADP
cana-4022	65	43	recognizing	recognize	VERB
cana-4022	65	44	an	an	DET
cana-4022	65	45	object	object	NOUN
cana-4022	65	46	.	.	PUNCT
cana-4022	66	1	to	to	ADP
cana-4022	66	2	this	this	DET
cana-4022	66	3	end	end	NOUN
cana-4022	66	4	,	,	PUNCT
cana-4022	66	5	the	the	DET
cana-4022	66	6	following	follow	VERB
cana-4022	66	7	datasets	dataset	NOUN
cana-4022	66	8	were	be	AUX
cana-4022	66	9	chosen	choose	VERB
cana-4022	66	10	to	to	PART
cana-4022	66	11	comprise	comprise	VERB
cana-4022	66	12	a	a	DET
cana-4022	66	13	variety	variety	NOUN
cana-4022	66	14	of	of	ADP
cana-4022	66	15	structure	structure	NOUN
cana-4022	66	16	and	and	CCONJ
cana-4022	66	17	unstructured	unstructured	ADJ
cana-4022	66	18	data	datum	NOUN
cana-4022	66	19	in	in	ADP
cana-4022	66	20	order	order	NOUN
cana-4022	66	21	to	to	PART
cana-4022	66	22	compare	compare	VERB
cana-4022	66	23	the	the	DET
cana-4022	66	24	supervised	supervised	ADJ
cana-4022	66	25	and	and	CCONJ
cana-4022	66	26	unsupervised	unsupervised	ADJ
cana-4022	66	27	learning	learning	NOUN
cana-4022	66	28	methods	method	NOUN
cana-4022	66	29	properly	properly	ADV
cana-4022	66	30	.	.	PUNCT
cana-4022	67	1	for	for	ADP
cana-4022	67	2	each	each	DET
cana-4022	67	3	pre	pre	ADJ
cana-4022	67	4	-	-	ADJ
cana-4022	67	5	processed	processed	ADJ
cana-4022	67	6	file	file	NOUN
cana-4022	67	7	,	,	PUNCT
cana-4022	67	8	data	datum	NOUN
cana-4022	67	9	cleaning	cleaning	NOUN
cana-4022	67	10	was	be	AUX
cana-4022	67	11	done	do	VERB
cana-4022	67	12	,	,	PUNCT
cana-4022	67	13	missing	miss	VERB
cana-4022	67	14	values	value	NOUN
cana-4022	67	15	were	be	AUX
cana-4022	67	16	filled	fill	VERB
cana-4022	67	17	up	up	ADP
cana-4022	67	18	by	by	ADP
cana-4022	67	19	using	use	VERB
cana-4022	67	20	the	the	DET
cana-4022	67	21	mean	mean	NOUN
cana-4022	67	22	for	for	ADP
cana-4022	67	23	numerical	numerical	ADJ
cana-4022	67	24	data	datum	NOUN
cana-4022	67	25	and	and	CCONJ
cana-4022	67	26	mode	mode	NOUN
cana-4022	67	27	for	for	ADP
cana-4022	67	28	the	the	DET
cana-4022	67	29	categorical	categorical	ADJ
cana-4022	67	30	data	datum	NOUN
cana-4022	67	31	for	for	ADP
cana-4022	67	32	consideration	consideration	NOUN
cana-4022	67	33	,	,	PUNCT
cana-4022	67	34	and	and	CCONJ
cana-4022	67	35	scaling	scale	VERB
cana-4022	67	36	method	method	NOUN
cana-4022	67	37	namely	namely	ADV
cana-4022	67	38	min	min	ADJ
cana-4022	67	39	-	-	ADJ
cana-4022	67	40	max	max	NOUN
cana-4022	67	41	normalization	normalization	NOUN
cana-4022	67	42	was	be	AUX
cana-4022	67	43	then	then	ADV
cana-4022	67	44	applied	apply	VERB
cana-4022	67	45	with	with	ADP
cana-4022	67	46	the	the	DET
cana-4022	67	47	intention	intention	NOUN
cana-4022	67	48	of	of	ADP
cana-4022	67	49	putting	put	VERB
cana-4022	67	50	the	the	DET
cana-4022	67	51	figures	figure	NOUN
cana-4022	67	52	on	on	ADP
cana-4022	67	53	the	the	DET
cana-4022	67	54	similar	similar	ADJ
cana-4022	67	55	range	range	NOUN
cana-4022	67	56	.	.	PUNCT
cana-4022	68	1	principal	principal	ADJ
cana-4022	68	2	component	component	NOUN
cana-4022	68	3	analysis	analysis	NOUN
cana-4022	68	4	(	(	PUNCT
cana-4022	68	5	pca	pca	NOUN
cana-4022	68	6	)	)	PUNCT
cana-4022	68	7	was	be	AUX
cana-4022	68	8	applied	apply	VERB
cana-4022	68	9	when	when	SCONJ
cana-4022	68	10	considering	consider	VERB
cana-4022	68	11	their	their	PRON
cana-4022	68	12	high	high	ADJ
cana-4022	68	13	-	-	PUNCT
cana-4022	68	14	dimensionality	dimensionality	NOUN
cana-4022	68	15	to	to	PART
cana-4022	68	16	reduce	reduce	VERB
cana-4022	68	17	its	its	PRON
cana-4022	68	18	dimensionality	dimensionality	NOUN
cana-4022	68	19	in	in	ADP
cana-4022	68	20	order	order	NOUN
cana-4022	68	21	to	to	PART
cana-4022	68	22	avoid	avoid	VERB
cana-4022	68	23	noise	noise	NOUN
cana-4022	68	24	and	and	CCONJ
cana-4022	68	25	increase	increase	VERB
cana-4022	68	26	the	the	DET
cana-4022	68	27	computational	computational	ADJ
cana-4022	68	28	speed	speed	NOUN
cana-4022	68	29	.	.	PUNCT
cana-4022	69	1	for	for	ADP
cana-4022	69	2	the	the	DET
cana-4022	69	3	supervised	supervised	ADJ
cana-4022	69	4	learning	learning	NOUN
cana-4022	69	5	models	model	NOUN
cana-4022	69	6	,	,	PUNCT
cana-4022	69	7	decision	decision	NOUN
cana-4022	69	8	trees	tree	NOUN
cana-4022	69	9	and	and	CCONJ
cana-4022	69	10	support	support	VERB
cana-4022	69	11	vector	vector	NOUN
cana-4022	69	12	machines	machine	NOUN
cana-4022	69	13	(	(	PUNCT
cana-4022	69	14	svm	svm	PROPN
cana-4022	69	15	)	)	PUNCT
cana-4022	69	16	have	have	AUX
cana-4022	69	17	been	be	AUX
cana-4022	69	18	incorporated	incorporate	VERB
cana-4022	69	19	since	since	SCONJ
cana-4022	69	20	they	they	PRON
cana-4022	69	21	are	be	AUX
cana-4022	69	22	effective	effective	ADJ
cana-4022	69	23	for	for	ADP
cana-4022	69	24	classification	classification	NOUN
cana-4022	69	25	.	.	PUNCT
cana-4022	70	1	decision	decision	NOUN
cana-4022	70	2	trees	tree	NOUN
cana-4022	70	3	were	be	AUX
cana-4022	70	4	chosen	choose	VERB
cana-4022	70	5	based	base	VERB
cana-4022	70	6	on	on	ADP
cana-4022	70	7	their	their	PRON
cana-4022	70	8	easy	easy	ADJ
cana-4022	70	9	interpretability	interpretability	NOUN
cana-4022	70	10	and	and	CCONJ
cana-4022	70	11	svm	svm	PROPN
cana-4022	70	12	was	be	AUX
cana-4022	70	13	chosen	choose	VERB
cana-4022	70	14	because	because	SCONJ
cana-4022	70	15	of	of	ADP
cana-4022	70	16	its	its	PRON
cana-4022	70	17	capability	capability	NOUN
cana-4022	70	18	to	to	PART
cana-4022	70	19	perform	perform	VERB
cana-4022	70	20	well	well	ADV
cana-4022	70	21	in	in	ADP
cana-4022	70	22	high	high	ADJ
cana-4022	70	23	dimensions	dimension	NOUN
cana-4022	70	24	.	.	PUNCT
cana-4022	71	1	communications	communication	NOUN
cana-4022	71	2	on	on	ADP
cana-4022	71	3	applied	apply	VERB
cana-4022	71	4	nonlinear	nonlinear	ADJ
cana-4022	71	5	analysis	analysis	NOUN
cana-4022	71	6	issn	issn	NOUN
cana-4022	71	7	:	:	PUNCT
cana-4022	71	8	1074	1074	NUM
cana-4022	71	9	-	-	PUNCT
cana-4022	71	10	133x	133x	NUM
cana-4022	71	11	vol	vol	NOUN
cana-4022	71	12	32	32	NUM
cana-4022	71	13	no	no	NOUN
cana-4022	71	14	.	.	PUNCT
cana-4022	72	1	9s	9s	NUM
cana-4022	72	2	(	(	PUNCT
cana-4022	72	3	2025	2025	NUM
cana-4022	72	4	)	)	PUNCT
cana-4022	72	5	864	864	NUM
cana-4022	72	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-4022	73	1	the	the	DET
cana-4022	73	2	improvement	improvement	NOUN
cana-4022	73	3	of	of	ADP
cana-4022	73	4	hyperparameters	hyperparameter	NOUN
cana-4022	73	5	was	be	AUX
cana-4022	73	6	done	do	VERB
cana-4022	73	7	using	use	VERB
cana-4022	73	8	grid	grid	NOUN
cana-4022	73	9	search	search	NOUN
cana-4022	73	10	crossvalidation	crossvalidation	NOUN
cana-4022	73	11	to	to	PART
cana-4022	73	12	gain	gain	VERB
cana-4022	73	13	the	the	DET
cana-4022	73	14	best	good	ADJ
cana-4022	73	15	performance	performance	NOUN
cana-4022	73	16	for	for	ADP
cana-4022	73	17	each	each	DET
cana-4022	73	18	model	model	NOUN
cana-4022	73	19	available	available	ADJ
cana-4022	73	20	.	.	PUNCT
cana-4022	74	1	the	the	DET
cana-4022	74	2	primary	primary	NOUN
cana-4022	74	3	and	and	CCONJ
cana-4022	74	4	the	the	DET
cana-4022	74	5	secondary	secondary	ADJ
cana-4022	74	6	datasets	dataset	NOUN
cana-4022	74	7	were	be	AUX
cana-4022	74	8	created	create	VERB
cana-4022	74	9	in	in	ADP
cana-4022	74	10	an	an	DET
cana-4022	74	11	8:2	8:2	NUM
cana-4022	74	12	ration	ration	NOUN
cana-4022	74	13	respectively	respectively	ADV
cana-4022	74	14	,	,	PUNCT
cana-4022	74	15	in	in	ADP
cana-4022	74	16	order	order	NOUN
cana-4022	74	17	to	to	PART
cana-4022	74	18	determine	determine	VERB
cana-4022	74	19	the	the	DET
cana-4022	74	20	generalization	generalization	NOUN
cana-4022	74	21	of	of	ADP
cana-4022	74	22	the	the	DET
cana-4022	74	23	models	model	NOUN
cana-4022	74	24	.	.	PUNCT
cana-4022	75	1	such	such	ADJ
cana-4022	75	2	unsupervised	unsupervised	ADJ
cana-4022	75	3	learning	learning	NOUN
cana-4022	75	4	models	model	NOUN
cana-4022	75	5	as	as	SCONJ
cana-4022	75	6	k	k	NOUN
cana-4022	75	7	-	-	PUNCT
cana-4022	75	8	means	mean	VERB
cana-4022	75	9	clustering	clustering	NOUN
cana-4022	75	10	and	and	CCONJ
cana-4022	75	11	autoencoders	autoencoder	NOUN
cana-4022	75	12	could	could	AUX
cana-4022	75	13	also	also	ADV
cana-4022	75	14	be	be	AUX
cana-4022	75	15	mentioned	mention	VERB
cana-4022	75	16	.	.	PUNCT
cana-4022	76	1	k	k	X
cana-4022	76	2	-	-	PUNCT
cana-4022	76	3	means	means	PROPN
cana-4022	76	4	was	be	AUX
cana-4022	76	5	used	use	VERB
cana-4022	76	6	because	because	SCONJ
cana-4022	76	7	it	it	PRON
cana-4022	76	8	is	be	AUX
cana-4022	76	9	easy	easy	ADJ
cana-4022	76	10	to	to	PART
cana-4022	76	11	implement	implement	VERB
cana-4022	76	12	and	and	CCONJ
cana-4022	76	13	fast	fast	VERB
cana-4022	76	14	at	at	ADP
cana-4022	76	15	forming	form	VERB
cana-4022	76	16	clusters	cluster	NOUN
cana-4022	76	17	while	while	SCONJ
cana-4022	76	18	autoencoders	autoencoder	NOUN
cana-4022	76	19	were	be	AUX
cana-4022	76	20	used	use	VERB
cana-4022	76	21	because	because	SCONJ
cana-4022	76	22	of	of	ADP
cana-4022	76	23	their	their	PRON
cana-4022	76	24	capability	capability	NOUN
cana-4022	76	25	to	to	PART
cana-4022	76	26	capture	capture	VERB
cana-4022	76	27	underlying	underlying	ADJ
cana-4022	76	28	pattern	pattern	NOUN
cana-4022	76	29	in	in	ADP
cana-4022	76	30	an	an	DET
cana-4022	76	31	unlabeled	unlabele	VERB
cana-4022	76	32	set	set	NOUN
cana-4022	76	33	.	.	PUNCT
cana-4022	77	1	k	k	X
cana-4022	77	2	-	-	PUNCT
cana-4022	77	3	means	mean	VERB
cana-4022	77	4	clustering	clustering	NOUN
cana-4022	77	5	,	,	PUNCT
cana-4022	77	6	the	the	DET
cana-4022	77	7	objective	objective	NOUN
cana-4022	77	8	of	of	ADP
cana-4022	77	9	which	which	PRON
cana-4022	77	10	was	be	AUX
cana-4022	77	11	to	to	PART
cana-4022	77	12	remain	remain	VERB
cana-4022	77	13	the	the	DET
cana-4022	77	14	same	same	ADJ
cana-4022	77	15	,	,	PUNCT
cana-4022	77	16	fixed	fixed	ADJ
cana-4022	77	17	number	number	NOUN
cana-4022	77	18	of	of	ADP
cana-4022	77	19	clusters	cluster	NOUN
cana-4022	77	20	was	be	AUX
cana-4022	77	21	chosen	choose	VERB
cana-4022	77	22	by	by	ADP
cana-4022	77	23	using	use	VERB
cana-4022	77	24	the	the	DET
cana-4022	77	25	‘	'	PUNCT
cana-4022	77	26	elbow	elbow	NOUN
cana-4022	77	27	curve	curve	NOUN
cana-4022	77	28	’	'	PUNCT
cana-4022	77	29	method	method	NOUN
cana-4022	77	30	while	while	SCONJ
cana-4022	77	31	for	for	ADP
cana-4022	77	32	aaes	aae	NOUN
cana-4022	77	33	,	,	PUNCT
cana-4022	77	34	the	the	DET
cana-4022	77	35	reconstruction	reconstruction	NOUN
cana-4022	77	36	error	error	NOUN
cana-4022	77	37	is	be	AUX
cana-4022	77	38	used	use	VERB
cana-4022	77	39	to	to	PART
cana-4022	77	40	infer	infer	VERB
cana-4022	77	41	the	the	DET
cana-4022	77	42	presence	presence	NOUN
cana-4022	77	43	of	of	ADP
cana-4022	77	44	the	the	DET
cana-4022	77	45	clusters	cluster	NOUN
cana-4022	77	46	within	within	ADP
cana-4022	77	47	the	the	DET
cana-4022	77	48	data	datum	NOUN
cana-4022	77	49	.	.	PUNCT
cana-4022	78	1	as	as	ADP
cana-4022	78	2	with	with	ADP
cana-4022	78	3	other	other	ADJ
cana-4022	78	4	unsupervised	unsupervised	ADJ
cana-4022	78	5	models	model	NOUN
cana-4022	78	6	,	,	PUNCT
cana-4022	78	7	there	there	PRON
cana-4022	78	8	are	be	VERB
cana-4022	78	9	no	no	DET
cana-4022	78	10	labels	label	NOUN
cana-4022	78	11	on	on	ADP
cana-4022	78	12	the	the	DET
cana-4022	78	13	output	output	NOUN
cana-4022	78	14	hence	hence	ADV
cana-4022	78	15	the	the	DET
cana-4022	78	16	use	use	NOUN
cana-4022	78	17	of	of	ADP
cana-4022	78	18	the	the	DET
cana-4022	78	19	cluster	cluster	NOUN
cana-4022	78	20	purity	purity	NOUN
cana-4022	78	21	and	and	CCONJ
cana-4022	78	22	silhouette	silhouette	NOUN
cana-4022	78	23	scores	score	NOUN
cana-4022	78	24	to	to	PART
cana-4022	78	25	evaluate	evaluate	VERB
cana-4022	78	26	their	their	PRON
cana-4022	78	27	performances	performance	NOUN
cana-4022	78	28	.	.	PUNCT
cana-4022	79	1	for	for	ADP
cana-4022	79	2	the	the	DET
cana-4022	79	3	assessment	assessment	NOUN
cana-4022	79	4	of	of	ADP
cana-4022	79	5	supervised	supervised	ADJ
cana-4022	79	6	models	model	NOUN
cana-4022	79	7	the	the	DET
cana-4022	79	8	accuracy	accuracy	NOUN
cana-4022	79	9	,	,	PUNCT
cana-4022	79	10	precision	precision	NOUN
cana-4022	79	11	,	,	PUNCT
cana-4022	79	12	recall	recall	NOUN
cana-4022	79	13	and	and	CCONJ
cana-4022	79	14	f1	f1	ADJ
cana-4022	79	15	score	score	NOUN
cana-4022	79	16	indicators	indicator	NOUN
cana-4022	79	17	were	be	AUX
cana-4022	79	18	used	use	VERB
cana-4022	79	19	,	,	PUNCT
cana-4022	79	20	fably	fably	ADV
cana-4022	79	21	for	for	ADP
cana-4022	79	22	the	the	DET
cana-4022	79	23	unsupervised	unsupervised	ADJ
cana-4022	79	24	models	model	NOUN
cana-4022	79	25	the	the	DET
cana-4022	79	26	measure	measure	NOUN
cana-4022	79	27	of	of	ADP
cana-4022	79	28	the	the	DET
cana-4022	79	29	silhouette	silhouette	NOUN
cana-4022	79	30	coefficient	coefficient	NOUN
cana-4022	79	31	was	be	AUX
cana-4022	79	32	used	use	VERB
cana-4022	79	33	,	,	PUNCT
cana-4022	79	34	davies	davies	PROPN
cana-4022	79	35	bouldin	bouldin	PROPN
cana-4022	79	36	index	index	NOUN
cana-4022	79	37	.	.	PUNCT
cana-4022	80	1	such	such	ADJ
cana-4022	80	2	measures	measure	NOUN
cana-4022	80	3	were	be	AUX
cana-4022	80	4	chosen	choose	VERB
cana-4022	80	5	to	to	PART
cana-4022	80	6	present	present	VERB
cana-4022	80	7	a	a	DET
cana-4022	80	8	comprehensive	comprehensive	ADJ
cana-4022	80	9	picture	picture	NOUN
cana-4022	80	10	of	of	ADP
cana-4022	80	11	the	the	DET
cana-4022	80	12	models	model	NOUN
cana-4022	80	13	’	'	PUNCT
cana-4022	80	14	ability	ability	NOUN
cana-4022	80	15	to	to	PART
cana-4022	80	16	classify	classify	VERB
cana-4022	80	17	and	and	CCONJ
cana-4022	80	18	cluster	cluster	VERB
cana-4022	80	19	the	the	DET
cana-4022	80	20	texts	text	NOUN
cana-4022	80	21	efficiently	efficiently	ADV
cana-4022	80	22	.	.	PUNCT
cana-4022	81	1	learning	learn	VERB
cana-4022	81	2	paradigisms	paradigism	NOUN
cana-4022	81	3	’	'	PUNCT
cana-4022	81	4	comparison	comparison	NOUN
cana-4022	81	5	analysis	analysis	NOUN
cana-4022	81	6	was	be	AUX
cana-4022	81	7	conducted	conduct	VERB
cana-4022	81	8	across	across	ADP
cana-4022	81	9	various	various	ADJ
cana-4022	81	10	datasets	dataset	NOUN
cana-4022	81	11	in	in	ADP
cana-4022	81	12	order	order	NOUN
cana-4022	81	13	to	to	PART
cana-4022	81	14	gain	gain	VERB
cana-4022	81	15	an	an	DET
cana-4022	81	16	insight	insight	NOUN
cana-4022	81	17	on	on	ADP
cana-4022	81	18	how	how	SCONJ
cana-4022	81	19	learning	learning	ADJ
cana-4022	81	20	paradigism	paradigism	NOUN
cana-4022	81	21	responds	respond	VERB
cana-4022	81	22	to	to	ADP
cana-4022	81	23	different	different	ADJ
cana-4022	81	24	integrated	integrate	VERB
cana-4022	81	25	data	datum	NOUN
cana-4022	81	26	perspective	perspective	NOUN
cana-4022	81	27	.	.	PUNCT
cana-4022	82	1	thus	thus	ADV
cana-4022	82	2	,	,	PUNCT
cana-4022	82	3	to	to	PART
cana-4022	82	4	make	make	VERB
cana-4022	82	5	certain	certain	ADJ
cana-4022	82	6	specific	specific	ADJ
cana-4022	82	7	performance	performance	NOUN
cana-4022	82	8	differences	difference	NOUN
cana-4022	82	9	,	,	PUNCT
cana-4022	82	10	statistical	statistical	ADJ
cana-4022	82	11	analysis	analysis	NOUN
cana-4022	82	12	was	be	AUX
cana-4022	82	13	performed	perform	VERB
cana-4022	82	14	.	.	PUNCT
cana-4022	83	1	for	for	ADP
cana-4022	83	2	the	the	DET
cana-4022	83	3	comparison	comparison	NOUN
cana-4022	83	4	of	of	ADP
cana-4022	83	5	the	the	DET
cana-4022	83	6	mean	mean	ADJ
cana-4022	83	7	accuracies	accuracy	NOUN
cana-4022	83	8	between	between	ADP
cana-4022	83	9	the	the	DET
cana-4022	83	10	different	different	ADJ
cana-4022	83	11	models	model	NOUN
cana-4022	83	12	,	,	PUNCT
cana-4022	83	13	anova	anova	PROPN
cana-4022	83	14	test	test	PROPN
cana-4022	83	15	was	be	AUX
cana-4022	83	16	used	use	VERB
cana-4022	83	17	while	while	SCONJ
cana-4022	83	18	the	the	DET
cana-4022	83	19	ttests	ttest	NOUN
cana-4022	83	20	were	be	AUX
cana-4022	83	21	used	use	VERB
cana-4022	83	22	for	for	ADP
cana-4022	83	23	testing	test	VERB
cana-4022	83	24	the	the	DET
cana-4022	83	25	significance	significance	NOUN
cana-4022	83	26	of	of	ADP
cana-4022	83	27	the	the	DET
cana-4022	83	28	difference	difference	NOUN
cana-4022	83	29	between	between	ADP
cana-4022	83	30	the	the	DET
cana-4022	83	31	supervised	supervised	ADJ
cana-4022	83	32	and	and	CCONJ
cana-4022	83	33	the	the	DET
cana-4022	83	34	unsupervised	unsupervised	ADJ
cana-4022	83	35	methods	method	NOUN
cana-4022	83	36	.	.	PUNCT
cana-4022	84	1	for	for	ADP
cana-4022	84	2	non	non	ADJ
cana-4022	84	3	-	-	ADJ
cana-4022	84	4	parametric	parametric	ADJ
cana-4022	84	5	data	datum	NOUN
cana-4022	84	6	distribution	distribution	NOUN
cana-4022	84	7	,	,	PUNCT
cana-4022	84	8	the	the	DET
cana-4022	84	9	wilcoxon	wilcoxon	ADJ
cana-4022	84	10	signed	sign	VERB
cana-4022	84	11	-	-	PUNCT
cana-4022	84	12	rank	rank	NOUN
cana-4022	84	13	test	test	NOUN
cana-4022	84	14	was	be	AUX
cana-4022	84	15	used	use	VERB
cana-4022	84	16	for	for	ADP
cana-4022	84	17	performance	performance	NOUN
cana-4022	84	18	compare	compare	AUX
cana-4022	84	19	hence	hence	ADV
cana-4022	84	20	being	be	AUX
cana-4022	84	21	robust	robust	ADJ
cana-4022	84	22	.	.	PUNCT
cana-4022	85	1	pearson	pearson	PROPN
cana-4022	85	2	correlation	correlation	NOUN
cana-4022	85	3	analysis	analysis	NOUN
cana-4022	85	4	was	be	AUX
cana-4022	85	5	used	use	VERB
cana-4022	85	6	as	as	ADP
cana-4022	85	7	the	the	DET
cana-4022	85	8	procedure	procedure	NOUN
cana-4022	85	9	to	to	PART
cana-4022	85	10	establish	establish	VERB
cana-4022	85	11	the	the	DET
cana-4022	85	12	correlation	correlation	NOUN
cana-4022	85	13	between	between	ADP
cana-4022	85	14	the	the	DET
cana-4022	85	15	use	use	NOUN
cana-4022	85	16	of	of	ADP
cana-4022	85	17	the	the	DET
cana-4022	85	18	dataset	dataset	NOUN
cana-4022	85	19	and	and	CCONJ
cana-4022	85	20	the	the	DET
cana-4022	85	21	values	value	NOUN
cana-4022	85	22	as	as	ADP
cana-4022	85	23	a	a	DET
cana-4022	85	24	measure	measure	NOUN
cana-4022	85	25	of	of	ADP
cana-4022	85	26	model	model	NOUN
cana-4022	85	27	accuracy	accuracy	NOUN
cana-4022	85	28	whenever	whenever	SCONJ
cana-4022	85	29	data	datum	NOUN
cana-4022	85	30	characteristics	characteristic	NOUN
cana-4022	85	31	affect	affect	VERB
cana-4022	85	32	the	the	DET
cana-4022	85	33	learning	learning	NOUN
cana-4022	85	34	outcomes	outcome	NOUN
cana-4022	85	35	.	.	PUNCT
cana-4022	86	1	7	7	X
cana-4022	86	2	.	.	X
cana-4022	86	3	results	result	VERB
cana-4022	86	4	the	the	DET
cana-4022	86	5	comparison	comparison	NOUN
cana-4022	86	6	of	of	ADP
cana-4022	86	7	supervised	supervised	ADJ
cana-4022	86	8	and	and	CCONJ
cana-4022	86	9	unsupervised	unsupervised	ADJ
cana-4022	86	10	approaches	approach	NOUN
cana-4022	86	11	to	to	ADP
cana-4022	86	12	the	the	DET
cana-4022	86	13	analysis	analysis	NOUN
cana-4022	86	14	of	of	ADP
cana-4022	86	15	three	three	NUM
cana-4022	86	16	datasets	dataset	NOUN
cana-4022	86	17	that	that	PRON
cana-4022	86	18	are	be	AUX
cana-4022	86	19	the	the	DET
cana-4022	86	20	financial	financial	ADJ
cana-4022	86	21	transactions	transaction	NOUN
cana-4022	86	22	,	,	PUNCT
cana-4022	86	23	healthcare	healthcare	NOUN
cana-4022	86	24	records	record	NOUN
cana-4022	86	25	and	and	CCONJ
cana-4022	86	26	image	image	NOUN
cana-4022	86	27	recognition	recognition	NOUN
cana-4022	86	28	tasks	task	NOUN
cana-4022	86	29	demonstrated	demonstrate	VERB
cana-4022	86	30	the	the	DET
cana-4022	86	31	effectiveness	effectiveness	NOUN
cana-4022	86	32	of	of	ADP
cana-4022	86	33	the	the	DET
cana-4022	86	34	supervised	supervised	ADJ
cana-4022	86	35	methods	method	NOUN
cana-4022	86	36	.	.	PUNCT
cana-4022	87	1	in	in	ADP
cana-4022	87	2	table	table	NOUN
cana-4022	87	3	1	1	NUM
cana-4022	87	4	,	,	PUNCT
cana-4022	87	5	the	the	DET
cana-4022	87	6	dataset	dataset	ADJ
cana-4022	87	7	summary	summary	NOUN
cana-4022	87	8	for	for	ADP
cana-4022	87	9	number	number	NOUN
cana-4022	87	10	of	of	ADP
cana-4022	87	11	instances	instance	NOUN
cana-4022	87	12	,	,	PUNCT
cana-4022	87	13	features	feature	NOUN
cana-4022	87	14	,	,	PUNCT
cana-4022	87	15	missing	miss	VERB
cana-4022	87	16	values	value	NOUN
cana-4022	87	17	and	and	CCONJ
cana-4022	87	18	the	the	DET
cana-4022	87	19	class	class	NOUN
cana-4022	87	20	distribution	distribution	NOUN
cana-4022	87	21	is	be	AUX
cana-4022	87	22	provided	provide	VERB
cana-4022	87	23	.	.	PUNCT
cana-4022	88	1	the	the	DET
cana-4022	88	2	financial	financial	ADJ
cana-4022	88	3	dataset	dataset	NOUN
cana-4022	88	4	consisted	consist	VERB
cana-4022	88	5	of	of	ADP
cana-4022	88	6	100000	100000	NUM
cana-4022	88	7	records	record	NOUN
cana-4022	88	8	with	with	ADP
cana-4022	88	9	3.2	3.2	NUM
cana-4022	88	10	%	%	NOUN
cana-4022	88	11	of	of	ADP
cana-4022	88	12	them	they	PRON
cana-4022	88	13	being	be	AUX
cana-4022	88	14	fraud	fraud	NOUN
cana-4022	88	15	and	and	CCONJ
cana-4022	88	16	the	the	DET
cana-4022	88	17	health	health	NOUN
cana-4022	88	18	care	care	NOUN
cana-4022	88	19	was	be	AUX
cana-4022	88	20	comprised	comprise	VERB
cana-4022	88	21	of	of	ADP
cana-4022	88	22	50000	50000	NUM
cana-4022	88	23	records	record	NOUN
cana-4022	88	24	with	with	ADP
cana-4022	88	25	half	half	NOUN
cana-4022	88	26	of	of	ADP
cana-4022	88	27	them	they	PRON
cana-4022	88	28	being	be	AUX
cana-4022	88	29	diseased	disease	VERB
cana-4022	88	30	and	and	CCONJ
cana-4022	88	31	the	the	DET
cana-4022	88	32	other	other	ADJ
cana-4022	88	33	half	half	NOUN
cana-4022	88	34	being	be	AUX
cana-4022	88	35	non	non	X
cana-4022	88	36	diseased	diseased	ADJ
cana-4022	88	37	.	.	PUNCT
cana-4022	89	1	the	the	DET
cana-4022	89	2	datasets	dataset	NOUN
cana-4022	89	3	used	use	VERB
cana-4022	89	4	in	in	ADP
cana-4022	89	5	the	the	DET
cana-4022	89	6	image	image	NOUN
cana-4022	89	7	classification	classification	NOUN
cana-4022	89	8	was	be	AUX
cana-4022	89	9	the	the	DET
cana-4022	89	10	images	image	NOUN
cana-4022	89	11	set	set	VERB
cana-4022	89	12	of	of	ADP
cana-4022	89	13	75,000	75,000	NUM
cana-4022	89	14	magnified	magnify	VERB
cana-4022	89	15	samples	sample	NOUN
cana-4022	89	16	which	which	PRON
cana-4022	89	17	were	be	AUX
cana-4022	89	18	labeled	label	VERB
cana-4022	89	19	in	in	ADP
cana-4022	89	20	ten	ten	NUM
cana-4022	89	21	classes	class	NOUN
cana-4022	89	22	.	.	PUNCT
cana-4022	90	1	table	table	NOUN
cana-4022	90	2	1	1	NUM
cana-4022	90	3	:	:	PUNCT
cana-4022	90	4	dataset	dataset	ADJ
cana-4022	90	5	characteristics	characteristic	NOUN
cana-4022	90	6	and	and	CCONJ
cana-4022	90	7	distribution	distribution	NOUN
cana-4022	90	8	across	across	ADP
cana-4022	90	9	domains	domain	NOUN
cana-4022	90	10	dataset	dataset	VERB
cana-4022	90	11	instances	instance	NOUN
cana-4022	90	12	features	feature	VERB
cana-4022	90	13	missing	miss	VERB
cana-4022	90	14	values	value	NOUN
cana-4022	90	15	(	(	PUNCT
cana-4022	90	16	%	%	INTJ
cana-4022	90	17	)	)	PUNCT
cana-4022	90	18	class	class	NOUN
cana-4022	90	19	distribution	distribution	NOUN
cana-4022	90	20	financial	financial	ADJ
cana-4022	90	21	transactions	transaction	NOUN
cana-4022	90	22	100,000	100,000	NUM
cana-4022	90	23	30	30	NUM
cana-4022	90	24	2.5	2.5	NUM
cana-4022	90	25	%	%	NOUN
cana-4022	90	26	3.2	3.2	NUM
cana-4022	90	27	%	%	NOUN
cana-4022	90	28	fraud	fraud	NOUN
cana-4022	90	29	,	,	PUNCT
cana-4022	90	30	96.8	96.8	NUM
cana-4022	90	31	%	%	NOUN
cana-4022	90	32	nonfraud	nonfraud	NOUN
cana-4022	90	33	communications	communication	NOUN
cana-4022	90	34	on	on	ADP
cana-4022	90	35	applied	apply	VERB
cana-4022	90	36	nonlinear	nonlinear	ADJ
cana-4022	90	37	analysis	analysis	NOUN
cana-4022	90	38	issn	issn	NOUN
cana-4022	90	39	:	:	PUNCT
cana-4022	90	40	1074	1074	NUM
cana-4022	90	41	-	-	PUNCT
cana-4022	90	42	133x	133x	NUM
cana-4022	90	43	vol	vol	NOUN
cana-4022	90	44	32	32	NUM
cana-4022	91	1	no	no	NOUN
cana-4022	91	2	.	.	PUNCT
cana-4022	92	1	9s	9s	NUM
cana-4022	92	2	(	(	PUNCT
cana-4022	92	3	2025	2025	NUM
cana-4022	92	4	)	)	PUNCT
cana-4022	92	5	865	865	NUM
cana-4022	92	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-4022	92	7	healthcare	healthcare	NOUN
cana-4022	92	8	records	record	VERB
cana-4022	92	9	50,000	50,000	NUM
cana-4022	92	10	25	25	NUM
cana-4022	92	11	1.7	1.7	NUM
cana-4022	92	12	%	%	NOUN
cana-4022	92	13	50	50	NUM
cana-4022	92	14	%	%	NOUN
cana-4022	92	15	diseased	diseased	ADJ
cana-4022	92	16	,	,	PUNCT
cana-4022	92	17	50	50	NUM
cana-4022	92	18	%	%	NOUN
cana-4022	92	19	nondiseased	nondisease	VERB
cana-4022	92	20	image	image	NOUN
cana-4022	92	21	recognition	recognition	NOUN
cana-4022	92	22	75,000	75,000	NUM
cana-4022	92	23	100x100	100x100	NUM
cana-4022	92	24	pixels	pixel	NOUN
cana-4022	92	25	0.0	0.0	NUM
cana-4022	92	26	%	%	NOUN
cana-4022	92	27	10	10	NUM
cana-4022	92	28	categories	category	NOUN
cana-4022	92	29	(	(	PUNCT
cana-4022	92	30	balanced	balanced	ADJ
cana-4022	92	31	)	)	PUNCT
cana-4022	92	32	as	as	SCONJ
cana-4022	92	33	depicted	depict	VERB
cana-4022	92	34	in	in	ADP
cana-4022	92	35	figure	figure	NOUN
cana-4022	92	36	1	1	NUM
cana-4022	92	37	,	,	PUNCT
cana-4022	92	38	the	the	DET
cana-4022	92	39	graphs	graph	NOUN
cana-4022	92	40	of	of	ADP
cana-4022	92	41	the	the	DET
cana-4022	92	42	training	training	NOUN
cana-4022	92	43	and	and	CCONJ
cana-4022	92	44	validation	validation	NOUN
cana-4022	92	45	accuracy	accuracy	NOUN
cana-4022	92	46	for	for	ADP
cana-4022	92	47	supervised	supervised	ADJ
cana-4022	92	48	models	model	NOUN
cana-4022	92	49	are	be	AUX
cana-4022	92	50	explained	explain	VERB
cana-4022	92	51	.	.	PUNCT
cana-4022	93	1	the	the	DET
cana-4022	93	2	learning	learning	NOUN
cana-4022	93	3	curves	curve	NOUN
cana-4022	93	4	for	for	ADP
cana-4022	93	5	both	both	DET
cana-4022	93	6	models	model	NOUN
cana-4022	93	7	were	be	AUX
cana-4022	93	8	derived	derive	VERB
cana-4022	93	9	,	,	PUNCT
cana-4022	93	10	and	and	CCONJ
cana-4022	93	11	the	the	DET
cana-4022	93	12	learning	learning	NOUN
cana-4022	93	13	curve	curve	NOUN
cana-4022	93	14	for	for	ADP
cana-4022	93	15	the	the	DET
cana-4022	93	16	decision	decision	NOUN
cana-4022	93	17	tree	tree	NOUN
cana-4022	93	18	model	model	NOUN
cana-4022	93	19	had	have	VERB
cana-4022	93	20	minimal	minimal	ADJ
cana-4022	93	21	overfitting	overfitting	NOUN
cana-4022	93	22	and	and	CCONJ
cana-4022	93	23	equally	equally	ADV
cana-4022	93	24	representative	representative	ADJ
cana-4022	93	25	for	for	ADP
cana-4022	93	26	the	the	DET
cana-4022	93	27	initial	initial	ADJ
cana-4022	93	28	and	and	CCONJ
cana-4022	93	29	later	later	ADJ
cana-4022	93	30	stages	stage	NOUN
cana-4022	93	31	of	of	ADP
cana-4022	93	32	learning	learn	VERB
cana-4022	93	33	iterations	iteration	NOUN
cana-4022	93	34	while	while	SCONJ
cana-4022	93	35	the	the	DET
cana-4022	93	36	svm	svm	PROPN
cana-4022	93	37	learning	learn	VERB
cana-4022	93	38	curve	curve	NOUN
cana-4022	93	39	denoted	denote	VERB
cana-4022	93	40	a	a	DET
cana-4022	93	41	relatively	relatively	ADV
cana-4022	93	42	small	small	ADJ
cana-4022	93	43	fluctuation	fluctuation	NOUN
cana-4022	93	44	in	in	ADP
cana-4022	93	45	validation	validation	NOUN
cana-4022	93	46	accuracy	accuracy	NOUN
cana-4022	93	47	for	for	ADP
cana-4022	93	48	different	different	ADJ
cana-4022	93	49	iterations	iteration	NOUN
cana-4022	93	50	.	.	PUNCT
cana-4022	94	1	the	the	DET
cana-4022	94	2	last	last	ADJ
cana-4022	94	3	forecast	forecast	NOUN
cana-4022	94	4	hit	hit	VERB
cana-4022	94	5	rate	rate	NOUN
cana-4022	94	6	is	be	AUX
cana-4022	94	7	equal	equal	ADJ
cana-4022	94	8	to	to	ADP
cana-4022	94	9	91.8	91.8	NUM
cana-4022	94	10	%	%	NOUN
cana-4022	94	11	for	for	ADP
cana-4022	94	12	decision	decision	NOUN
cana-4022	94	13	trees	tree	NOUN
cana-4022	94	14	and	and	CCONJ
cana-4022	94	15	92.4	92.4	NUM
cana-4022	94	16	%	%	NOUN
cana-4022	94	17	for	for	ADP
cana-4022	94	18	svm	svm	PROPN
cana-4022	94	19	.	.	PROPN
cana-4022	94	20	figure	figure	NOUN
cana-4022	94	21	1	1	NUM
cana-4022	94	22	:	:	PUNCT
cana-4022	94	23	training	training	NOUN
cana-4022	94	24	and	and	CCONJ
cana-4022	94	25	validation	validation	NOUN
cana-4022	94	26	accuracy	accuracy	NOUN
cana-4022	94	27	trends	trend	NOUN
cana-4022	94	28	below	below	ADV
cana-4022	94	29	is	be	AUX
cana-4022	94	30	the	the	DET
cana-4022	94	31	accuracy	accuracy	NOUN
cana-4022	94	32	gain	gain	NOUN
cana-4022	94	33	tracking	track	VERB
cana-4022	94	34	for	for	ADP
cana-4022	94	35	50	50	NUM
cana-4022	94	36	epochs	epoch	NOUN
cana-4022	94	37	of	of	ADP
cana-4022	94	38	the	the	DET
cana-4022	94	39	decision	decision	NOUN
cana-4022	94	40	trees	tree	NOUN
cana-4022	94	41	and	and	CCONJ
cana-4022	94	42	svm	svm	ADJ
cana-4022	94	43	models	model	NOUN
cana-4022	94	44	.	.	PUNCT
cana-4022	95	1	applying	apply	VERB
cana-4022	95	2	the	the	DET
cana-4022	95	3	svm	svm	ADJ
cana-4022	95	4	model	model	NOUN
cana-4022	95	5	shows	show	VERB
cana-4022	95	6	incremental	incremental	ADJ
cana-4022	95	7	improvements	improvement	NOUN
cana-4022	95	8	,	,	PUNCT
cana-4022	95	9	while	while	SCONJ
cana-4022	95	10	using	use	VERB
cana-4022	95	11	the	the	DET
cana-4022	95	12	decision	decision	NOUN
cana-4022	95	13	tree	tree	NOUN
cana-4022	95	14	model	model	NOUN
cana-4022	95	15	show	show	NOUN
cana-4022	95	16	variations	variation	NOUN
cana-4022	95	17	,	,	PUNCT
cana-4022	95	18	because	because	SCONJ
cana-4022	95	19	of	of	ADP
cana-4022	95	20	data	datum	NOUN
cana-4022	95	21	split	split	VERB
cana-4022	95	22	in	in	ADP
cana-4022	95	23	the	the	DET
cana-4022	95	24	tree	tree	NOUN
cana-4022	95	25	.	.	PUNCT
cana-4022	96	1	evaluating	evaluate	VERB
cana-4022	96	2	performance	performance	NOUN
cana-4022	96	3	of	of	ADP
cana-4022	96	4	the	the	DET
cana-4022	96	5	two	two	NUM
cana-4022	96	6	categories	category	NOUN
cana-4022	96	7	of	of	ADP
cana-4022	96	8	models	model	NOUN
cana-4022	96	9	,	,	PUNCT
cana-4022	96	10	which	which	PRON
cana-4022	96	11	are	be	AUX
cana-4022	96	12	the	the	DET
cana-4022	96	13	supervised	supervised	ADJ
cana-4022	96	14	and	and	CCONJ
cana-4022	96	15	unsupervised	unsupervised	ADJ
cana-4022	96	16	models	model	NOUN
cana-4022	96	17	is	be	AUX
cana-4022	96	18	presented	present	VERB
cana-4022	96	19	in	in	ADP
cana-4022	96	20	table	table	NOUN
cana-4022	96	21	2	2	NUM
cana-4022	96	22	below	below	ADV
cana-4022	96	23	.	.	PUNCT
cana-4022	97	1	in	in	ADP
cana-4022	97	2	all	all	DET
cana-4022	97	3	the	the	DET
cana-4022	97	4	experiments	experiment	NOUN
cana-4022	97	5	,	,	PUNCT
cana-4022	97	6	supervised	supervised	ADJ
cana-4022	97	7	approaches	approach	NOUN
cana-4022	97	8	were	be	AUX
cana-4022	97	9	found	find	VERB
cana-4022	97	10	to	to	PART
cana-4022	97	11	be	be	AUX
cana-4022	97	12	better	well	ADJ
cana-4022	97	13	than	than	ADP
cana-4022	97	14	the	the	DET
cana-4022	97	15	unsupervised	unsupervised	ADJ
cana-4022	97	16	approaches	approach	NOUN
cana-4022	97	17	;	;	PUNCT
cana-4022	97	18	the	the	DET
cana-4022	97	19	supervised	supervised	ADJ
cana-4022	97	20	methods	method	NOUN
cana-4022	97	21	of	of	ADP
cana-4022	97	22	analysis	analysis	NOUN
cana-4022	97	23	included	include	VERB
cana-4022	97	24	:	:	PUNCT
cana-4022	97	25	support	support	NOUN
cana-4022	97	26	vector	vector	NOUN
cana-4022	97	27	machine	machine	NOUN
cana-4022	97	28	whose	whose	DET
cana-4022	97	29	precision	precision	NOUN
cana-4022	97	30	was	be	AUX
cana-4022	97	31	94.2	94.2	NUM
cana-4022	97	32	%	%	NOUN
cana-4022	97	33	and	and	CCONJ
cana-4022	97	34	decision	decision	NOUN
cana-4022	97	35	tree	tree	NOUN
cana-4022	97	36	which	which	PRON
cana-4022	97	37	has	have	VERB
cana-4022	97	38	a	a	DET
cana-4022	97	39	recall	recall	NOUN
cana-4022	97	40	of	of	ADP
cana-4022	97	41	88.6	88.6	NUM
cana-4022	97	42	%	%	NOUN
cana-4022	97	43	.	.	PUNCT
cana-4022	98	1	while	while	SCONJ
cana-4022	98	2	k	k	NOUN
cana-4022	98	3	-	-	PUNCT
cana-4022	98	4	means	mean	VERB
cana-4022	98	5	clustering	clustering	NOUN
cana-4022	98	6	result	result	NOUN
cana-4022	98	7	and	and	CCONJ
cana-4022	98	8	autoencoder	autoencoder	NOUN
cana-4022	98	9	were	be	AUX
cana-4022	98	10	moderately	moderately	ADV
cana-4022	98	11	effective	effective	ADJ
cana-4022	98	12	with	with	ADP
cana-4022	98	13	silhouette	silhouette	NOUN
cana-4022	98	14	score	score	NOUN
cana-4022	98	15	of	of	ADP
cana-4022	98	16	the	the	DET
cana-4022	98	17	entire	entire	ADJ
cana-4022	98	18	cluster	cluster	NOUN
cana-4022	98	19	ranging	range	VERB
cana-4022	98	20	from	from	ADP
cana-4022	98	21	0.58	0.58	NUM
cana-4022	98	22	to	to	ADP
cana-4022	98	23	0.72	0.72	NUM
cana-4022	98	24	and	and	CCONJ
cana-4022	98	25	this	this	PRON
cana-4022	98	26	showing	show	VERB
cana-4022	98	27	that	that	SCONJ
cana-4022	98	28	the	the	DET
cana-4022	98	29	clusters	cluster	NOUN
cana-4022	98	30	are	be	AUX
cana-4022	98	31	moderately	moderately	ADV
cana-4022	98	32	well	well	ADV
cana-4022	98	33	separated	separate	VERB
cana-4022	98	34	.	.	PUNCT
cana-4022	99	1	communications	communication	NOUN
cana-4022	99	2	on	on	ADP
cana-4022	99	3	applied	apply	VERB
cana-4022	99	4	nonlinear	nonlinear	ADJ
cana-4022	99	5	analysis	analysis	NOUN
cana-4022	99	6	issn	issn	NOUN
cana-4022	99	7	:	:	PUNCT
cana-4022	99	8	1074	1074	NUM
cana-4022	99	9	-	-	PUNCT
cana-4022	99	10	133x	133x	NUM
cana-4022	99	11	vol	vol	NOUN
cana-4022	99	12	32	32	NUM
cana-4022	99	13	no	no	NOUN
cana-4022	99	14	.	.	PUNCT
cana-4022	100	1	9s	9s	NUM
cana-4022	100	2	(	(	PUNCT
cana-4022	100	3	2025	2025	NUM
cana-4022	100	4	)	)	PUNCT
cana-4022	100	5	866	866	NUM
cana-4022	100	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-4022	100	7	table	table	NOUN
cana-4022	100	8	2	2	NUM
cana-4022	100	9	:	:	PUNCT
cana-4022	100	10	comparative	comparative	ADJ
cana-4022	100	11	performance	performance	NOUN
cana-4022	100	12	metrics	metric	NOUN
cana-4022	100	13	of	of	ADP
cana-4022	100	14	supervised	supervised	ADJ
cana-4022	100	15	and	and	CCONJ
cana-4022	100	16	unsupervised	unsupervised	ADJ
cana-4022	100	17	models	model	NOUN
cana-4022	100	18	model	model	NOUN
cana-4022	100	19	accuracy	accuracy	NOUN
cana-4022	100	20	(	(	PUNCT
cana-4022	100	21	%	%	INTJ
cana-4022	100	22	)	)	PUNCT
cana-4022	100	23	precision	precision	NOUN
cana-4022	100	24	(	(	PUNCT
cana-4022	100	25	%	%	INTJ
cana-4022	100	26	)	)	PUNCT
cana-4022	100	27	recall	recall	NOUN
cana-4022	100	28	(	(	PUNCT
cana-4022	100	29	%	%	NOUN
cana-4022	100	30	)	)	PUNCT
cana-4022	100	31	f1	f1	ADJ
cana-4022	100	32	-	-	PUNCT
cana-4022	100	33	score	score	NOUN
cana-4022	100	34	silhouette	silhouette	NOUN
cana-4022	100	35	score	score	NOUN
cana-4022	100	36	decision	decision	NOUN
cana-4022	100	37	tree	tree	NOUN
cana-4022	100	38	91.8	91.8	NUM
cana-4022	100	39	90.4	90.4	NUM
cana-4022	100	40	88.6	88.6	NUM
cana-4022	100	41	89.5	89.5	NUM
cana-4022	100	42	svm	svm	NOUN
cana-4022	100	43	92.4	92.4	NUM
cana-4022	100	44	94.2	94.2	NUM
cana-4022	100	45	90.1	90.1	NUM
cana-4022	100	46	92.1	92.1	NUM
cana-4022	100	47	k	k	NOUN
cana-4022	100	48	-	-	PUNCT
cana-4022	100	49	means	mean	VERB
cana-4022	100	50	0.72	0.72	NUM
cana-4022	100	51	autoencoder	autoencoder	NOUN
cana-4022	100	52	0.58	0.58	NUM
cana-4022	100	53	table	table	NOUN
cana-4022	100	54	2	2	NUM
cana-4022	100	55	provides	provide	VERB
cana-4022	100	56	confusion	confusion	NOUN
cana-4022	100	57	matrices	matrix	NOUN
cana-4022	100	58	of	of	ADP
cana-4022	100	59	models	model	NOUN
cana-4022	100	60	with	with	ADP
cana-4022	100	61	respect	respect	NOUN
cana-4022	100	62	to	to	ADP
cana-4022	100	63	the	the	DET
cana-4022	100	64	supervised	supervised	ADJ
cana-4022	100	65	-	-	PUNCT
cana-4022	100	66	learning	learn	VERB
cana-4022	100	67	perspective	perspective	NOUN
cana-4022	100	68	with	with	ADP
cana-4022	100	69	an	an	DET
cana-4022	100	70	emphasis	emphasis	NOUN
cana-4022	100	71	put	put	VERB
cana-4022	100	72	on	on	ADP
cana-4022	100	73	the	the	DET
cana-4022	100	74	classification	classification	NOUN
cana-4022	100	75	accuracy	accuracy	NOUN
cana-4022	100	76	.	.	PUNCT
cana-4022	101	1	svm	svm	PROPN
cana-4022	101	2	has	have	VERB
cana-4022	101	3	a	a	DET
cana-4022	101	4	better	well	ADJ
cana-4022	101	5	true	true	ADJ
cana-4022	101	6	positive	positive	ADJ
cana-4022	101	7	measure	measure	NOUN
cana-4022	101	8	than	than	ADP
cana-4022	101	9	decision	decision	NOUN
cana-4022	101	10	trees	tree	NOUN
cana-4022	101	11	for	for	ADP
cana-4022	101	12	all	all	DET
cana-4022	101	13	the	the	DET
cana-4022	101	14	datasets	dataset	NOUN
cana-4022	101	15	,	,	PUNCT
cana-4022	101	16	resulting	result	VERB
cana-4022	101	17	to	to	ADP
cana-4022	101	18	fewer	few	ADJ
cana-4022	101	19	false	false	ADJ
cana-4022	101	20	negatives	negative	NOUN
cana-4022	101	21	.	.	PUNCT
cana-4022	102	1	figure	figure	NOUN
cana-4022	102	2	2	2	NUM
cana-4022	102	3	:	:	PUNCT
cana-4022	102	4	confusion	confusion	NOUN
cana-4022	102	5	matrices	matrix	NOUN
cana-4022	102	6	for	for	ADP
cana-4022	102	7	the	the	DET
cana-4022	102	8	supervised	supervised	ADJ
cana-4022	102	9	learning	learning	NOUN
cana-4022	102	10	models	model	NOUN
cana-4022	102	11	this	this	DET
cana-4022	102	12	figure	figure	NOUN
cana-4022	102	13	present	present	VERB
cana-4022	102	14	the	the	DET
cana-4022	102	15	confusion	confusion	NOUN
cana-4022	102	16	matrices	matrix	NOUN
cana-4022	102	17	of	of	ADP
cana-4022	102	18	a	a	DET
cana-4022	102	19	decision	decision	NOUN
cana-4022	102	20	tree	tree	NOUN
cana-4022	102	21	and	and	CCONJ
cana-4022	102	22	svm	svm	VERB
cana-4022	102	23	in	in	ADP
cana-4022	102	24	the	the	DET
cana-4022	102	25	three	three	NUM
cana-4022	102	26	datasets	dataset	NOUN
cana-4022	102	27	.	.	PUNCT
cana-4022	103	1	compared	compare	VERB
cana-4022	103	2	to	to	ADP
cana-4022	103	3	other	other	ADJ
cana-4022	103	4	related	related	ADJ
cana-4022	103	5	approaches	approach	NOUN
cana-4022	103	6	,	,	PUNCT
cana-4022	103	7	svm	svm	PROPN
cana-4022	103	8	is	be	AUX
cana-4022	103	9	a	a	DET
cana-4022	103	10	more	more	ADV
cana-4022	103	11	generalized	generalized	ADJ
cana-4022	103	12	and	and	CCONJ
cana-4022	103	13	gives	give	VERB
cana-4022	103	14	lower	low	ADJ
cana-4022	103	15	misclassification	misclassification	NOUN
cana-4022	103	16	ratio	ratio	NOUN
cana-4022	103	17	especially	especially	ADV
cana-4022	103	18	in	in	ADP
cana-4022	103	19	the	the	DET
cana-4022	103	20	applications	application	NOUN
cana-4022	103	21	such	such	ADJ
cana-4022	103	22	as	as	ADP
cana-4022	103	23	fraud	fraud	NOUN
cana-4022	103	24	detecting	detecting	NOUN
cana-4022	103	25	or	or	CCONJ
cana-4022	103	26	disease	disease	NOUN
cana-4022	103	27	classification	classification	NOUN
cana-4022	103	28	.	.	PUNCT
cana-4022	104	1	for	for	ADP
cana-4022	104	2	purposes	purpose	NOUN
cana-4022	104	3	of	of	ADP
cana-4022	104	4	determining	determine	VERB
cana-4022	104	5	statistical	statistical	ADJ
cana-4022	104	6	significance	significance	NOUN
cana-4022	104	7	,	,	PUNCT
cana-4022	104	8	anova	anova	PROPN
cana-4022	104	9	and	and	CCONJ
cana-4022	104	10	t	t	PROPN
cana-4022	104	11	-	-	PUNCT
cana-4022	104	12	tests	test	NOUN
cana-4022	104	13	were	be	AUX
cana-4022	104	14	done	do	VERB
cana-4022	104	15	as	as	SCONJ
cana-4022	104	16	pointed	point	VERB
cana-4022	104	17	out	out	ADP
cana-4022	104	18	in	in	ADP
cana-4022	104	19	table	table	NOUN
cana-4022	104	20	3	3	NUM
cana-4022	104	21	.	.	PUNCT
cana-4022	105	1	namely	namely	ADV
cana-4022	105	2	,	,	PUNCT
cana-4022	105	3	anova	anova	PROPN
cana-4022	105	4	test	test	NOUN
cana-4022	105	5	on	on	ADP
cana-4022	105	6	the	the	DET
cana-4022	105	7	model	model	NOUN
cana-4022	105	8	accuracy	accuracy	NOUN
cana-4022	105	9	showed	show	VERB
cana-4022	105	10	that	that	SCONJ
cana-4022	105	11	it	it	PRON
cana-4022	105	12	is	be	AUX
cana-4022	105	13	significant	significant	ADJ
cana-4022	105	14	at	at	ADP
cana-4022	105	15	the	the	DET
cana-4022	105	16	0.01	0.01	NUM
cana-4022	105	17	level	level	NOUN
cana-4022	105	18	.	.	PUNCT
cana-4022	106	1	the	the	DET
cana-4022	106	2	results	result	NOUN
cana-4022	106	3	of	of	ADP
cana-4022	106	4	the	the	DET
cana-4022	106	5	paired	pair	VERB
cana-4022	106	6	ttests	ttest	NOUN
cana-4022	106	7	also	also	ADV
cana-4022	106	8	showed	show	VERB
cana-4022	106	9	that	that	SCONJ
cana-4022	106	10	an	an	DET
cana-4022	106	11	average	average	NOUN
cana-4022	106	12	of	of	ADP
cana-4022	106	13	supervised	supervised	ADJ
cana-4022	106	14	models	model	NOUN
cana-4022	106	15	were	be	AUX
cana-4022	106	16	significant	significant	ADJ
cana-4022	106	17	better	well	ADV
cana-4022	106	18	(	(	PUNCT
cana-4022	106	19	p=	p=	NOUN
cana-4022	106	20	0.002	0.002	NUM
cana-4022	106	21	)	)	PUNCT
cana-4022	106	22	than	than	ADP
cana-4022	106	23	chance	chance	NOUN
cana-4022	106	24	or	or	CCONJ
cana-4022	106	25	the	the	DET
cana-4022	106	26	unsupervised	unsupervised	ADJ
cana-4022	106	27	models	model	NOUN
cana-4022	106	28	in	in	ADP
cana-4022	106	29	terms	term	NOUN
cana-4022	106	30	of	of	ADP
cana-4022	106	31	accuracy	accuracy	NOUN
cana-4022	106	32	.	.	PUNCT
cana-4022	107	1	table	table	NOUN
cana-4022	107	2	3	3	NUM
cana-4022	107	3	:	:	PUNCT
cana-4022	107	4	statistical	statistical	ADJ
cana-4022	107	5	significance	significance	NOUN
cana-4022	107	6	analysis	analysis	NOUN
cana-4022	107	7	(	(	PUNCT
cana-4022	107	8	anova	anova	X
cana-4022	107	9	and	and	CCONJ
cana-4022	107	10	t	t	PROPN
cana-4022	107	11	-	-	PUNCT
cana-4022	107	12	test	test	NOUN
cana-4022	107	13	results	result	NOUN
cana-4022	107	14	)	)	PUNCT
cana-4022	107	15	test	test	NOUN
cana-4022	107	16	comparison	comparison	NOUN
cana-4022	107	17	p	p	NOUN
cana-4022	107	18	-	-	PUNCT
cana-4022	107	19	value	value	NOUN
cana-4022	107	20	significance	significance	NOUN
cana-4022	107	21	anova	anova	PROPN
cana-4022	107	22	model	model	PROPN
cana-4022	107	23	accuracy	accuracy	NOUN
cana-4022	107	24	differences	difference	NOUN
cana-4022	107	25	<	<	X
cana-4022	107	26	0.01	0.01	NUM
cana-4022	107	27	significant	significant	ADJ
cana-4022	107	28	t	t	NOUN
cana-4022	107	29	-	-	PUNCT
cana-4022	107	30	test	test	NOUN
cana-4022	107	31	supervised	supervise	VERB
cana-4022	107	32	vs.	vs.	ADP
cana-4022	107	33	unsupervised	unsupervised	ADJ
cana-4022	107	34	accuracy	accuracy	NOUN
cana-4022	107	35	0.002	0.002	NUM
cana-4022	107	36	significant	significant	ADJ
cana-4022	107	37	communications	communication	NOUN
cana-4022	107	38	on	on	ADP
cana-4022	107	39	applied	apply	VERB
cana-4022	107	40	nonlinear	nonlinear	ADJ
cana-4022	107	41	analysis	analysis	NOUN
cana-4022	107	42	issn	issn	NOUN
cana-4022	107	43	:	:	PUNCT
cana-4022	107	44	1074	1074	NUM
cana-4022	107	45	-	-	PUNCT
cana-4022	107	46	133x	133x	NUM
cana-4022	107	47	vol	vol	NOUN
cana-4022	107	48	32	32	NUM
cana-4022	107	49	no	no	NOUN
cana-4022	107	50	.	.	PUNCT
cana-4022	108	1	9s	9s	NUM
cana-4022	108	2	(	(	PUNCT
cana-4022	108	3	2025	2025	NUM
cana-4022	108	4	)	)	PUNCT
cana-4022	108	5	867	867	NUM
cana-4022	108	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-4022	108	7	more	more	ADV
cana-4022	108	8	specifically	specifically	ADV
cana-4022	108	9	,	,	PUNCT
cana-4022	108	10	whereas	whereas	SCONJ
cana-4022	108	11	three	three	NUM
cana-4022	108	12	clusters	cluster	NOUN
cana-4022	108	13	were	be	AUX
cana-4022	108	14	always	always	ADV
cana-4022	108	15	formed	form	VERB
cana-4022	108	16	in	in	ADP
cana-4022	108	17	the	the	DET
cana-4022	108	18	supervised	supervised	ADJ
cana-4022	108	19	models	model	NOUN
cana-4022	108	20	,	,	PUNCT
cana-4022	108	21	unsupervised	unsupervised	ADJ
cana-4022	108	22	models	model	NOUN
cana-4022	108	23	exhibited	exhibit	VERB
cana-4022	108	24	greater	great	ADJ
cana-4022	108	25	variation	variation	NOUN
cana-4022	108	26	about	about	ADP
cana-4022	108	27	this	this	DET
cana-4022	108	28	value	value	NOUN
cana-4022	108	29	as	as	SCONJ
cana-4022	108	30	seen	see	VERB
cana-4022	108	31	in	in	ADP
cana-4022	108	32	figure	figure	NOUN
cana-4022	108	33	3	3	NUM
cana-4022	108	34	.	.	PUNCT
cana-4022	109	1	the	the	DET
cana-4022	109	2	description	description	NOUN
cana-4022	109	3	and	and	CCONJ
cana-4022	109	4	comparison	comparison	NOUN
cana-4022	109	5	made	make	VERB
cana-4022	109	6	here	here	ADV
cana-4022	109	7	have	have	AUX
cana-4022	109	8	shown	show	VERB
cana-4022	109	9	that	that	SCONJ
cana-4022	109	10	k	k	NOUN
cana-4022	109	11	-	-	PUNCT
cana-4022	109	12	means	mean	NOUN
cana-4022	109	13	gave	give	VERB
cana-4022	109	14	better	well	ADJ
cana-4022	109	15	outcomes	outcome	NOUN
cana-4022	109	16	by	by	ADP
cana-4022	109	17	well	well	ADV
cana-4022	109	18	defining	define	VERB
cana-4022	109	19	clusters	cluster	NOUN
cana-4022	109	20	in	in	ADP
cana-4022	109	21	the	the	DET
cana-4022	109	22	financial	financial	ADJ
cana-4022	109	23	data	datum	NOUN
cana-4022	109	24	as	as	ADP
cana-4022	109	25	compared	compare	VERB
cana-4022	109	26	to	to	ADP
cana-4022	109	27	the	the	DET
cana-4022	109	28	autoencoders	autoencoder	NOUN
cana-4022	109	29	in	in	ADP
cana-4022	109	30	healthcare	healthcare	PROPN
cana-4022	109	31	data	datum	NOUN
cana-4022	109	32	which	which	PRON
cana-4022	109	33	have	have	VERB
cana-4022	109	34	lower	low	ADJ
cana-4022	109	35	silhouette	silhouette	NOUN
cana-4022	109	36	score	score	NOUN
cana-4022	109	37	due	due	ADP
cana-4022	109	38	to	to	ADP
cana-4022	109	39	perhaps	perhaps	ADV
cana-4022	109	40	its	its	PRON
cana-4022	109	41	inability	inability	NOUN
cana-4022	109	42	to	to	PART
cana-4022	109	43	represent	represent	VERB
cana-4022	109	44	complex	complex	ADJ
cana-4022	109	45	features	feature	NOUN
cana-4022	109	46	.	.	PUNCT
cana-4022	110	1	figure	figure	VERB
cana-4022	110	2	3	3	NUM
cana-4022	110	3	:	:	PUNCT
cana-4022	110	4	cluster	cluster	NOUN
cana-4022	110	5	analysis	analysis	NOUN
cana-4022	110	6	of	of	ADP
cana-4022	110	7	unsupervised	unsupervised	ADJ
cana-4022	110	8	learning	learning	NOUN
cana-4022	110	9	algorithms	algorithm	NOUN
cana-4022	110	10	on	on	ADP
cana-4022	110	11	the	the	DET
cana-4022	110	12	figure	figure	NOUN
cana-4022	110	13	,	,	PUNCT
cana-4022	110	14	the	the	DET
cana-4022	110	15	clusters	cluster	NOUN
cana-4022	110	16	are	be	AUX
cana-4022	110	17	shown	show	VERB
cana-4022	110	18	which	which	PRON
cana-4022	110	19	were	be	AUX
cana-4022	110	20	obtained	obtain	VERB
cana-4022	110	21	with	with	ADP
cana-4022	110	22	the	the	DET
cana-4022	110	23	help	help	NOUN
cana-4022	110	24	of	of	ADP
cana-4022	110	25	k	k	NOUN
cana-4022	110	26	-	-	PUNCT
cana-4022	110	27	means	mean	NOUN
cana-4022	110	28	and	and	CCONJ
cana-4022	110	29	autoencoders	autoencoder	NOUN
cana-4022	110	30	.	.	PUNCT
cana-4022	111	1	in	in	ADP
cana-4022	111	2	comparison	comparison	NOUN
cana-4022	111	3	to	to	ADP
cana-4022	111	4	k	k	ADJ
cana-4022	111	5	-	-	PUNCT
cana-4022	111	6	means	mean	VERB
cana-4022	111	7	clustering	clustering	NOUN
cana-4022	111	8	technique	technique	NOUN
cana-4022	111	9	which	which	PRON
cana-4022	111	10	produce	produce	VERB
cana-4022	111	11	distinct	distinct	ADJ
cana-4022	111	12	clusters	cluster	NOUN
cana-4022	111	13	for	for	ADP
cana-4022	111	14	different	different	ADJ
cana-4022	111	15	types	type	NOUN
cana-4022	111	16	of	of	ADP
cana-4022	111	17	transactions	transaction	NOUN
cana-4022	111	18	,	,	PUNCT
cana-4022	111	19	autoencoders	autoencoder	NOUN
cana-4022	111	20	show	show	VERB
cana-4022	111	21	overlapping	overlap	VERB
cana-4022	111	22	clusters	cluster	NOUN
cana-4022	111	23	,	,	PUNCT
cana-4022	111	24	which	which	PRON
cana-4022	111	25	imply	imply	VERB
cana-4022	111	26	that	that	SCONJ
cana-4022	111	27	they	they	PRON
cana-4022	111	28	have	have	VERB
cana-4022	111	29	low	low	ADJ
cana-4022	111	30	discrimination	discrimination	NOUN
cana-4022	111	31	capacity	capacity	NOUN
cana-4022	111	32	especially	especially	ADV
cana-4022	111	33	when	when	SCONJ
cana-4022	111	34	dealing	deal	VERB
cana-4022	111	35	with	with	ADP
cana-4022	111	36	large	large	ADJ
cana-4022	111	37	data	datum	NOUN
cana-4022	111	38	sets	set	NOUN
cana-4022	111	39	.	.	PUNCT
cana-4022	112	1	finally	finally	ADV
cana-4022	112	2	,	,	PUNCT
cana-4022	112	3	correlation	correlation	NOUN
cana-4022	112	4	analysis	analysis	NOUN
cana-4022	112	5	checked	check	VERB
cana-4022	112	6	the	the	DET
cana-4022	112	7	degree	degree	NOUN
cana-4022	112	8	of	of	ADP
cana-4022	112	9	correlation	correlation	NOUN
cana-4022	112	10	between	between	ADP
cana-4022	112	11	the	the	DET
cana-4022	112	12	dataset	dataset	NOUN
cana-4022	112	13	complexity	complexity	NOUN
cana-4022	112	14	and	and	CCONJ
cana-4022	112	15	accuracy	accuracy	NOUN
cana-4022	112	16	of	of	ADP
cana-4022	112	17	the	the	DET
cana-4022	112	18	model	model	NOUN
cana-4022	112	19	.	.	PUNCT
cana-4022	113	1	it	it	PRON
cana-4022	113	2	also	also	ADV
cana-4022	113	3	revealed	reveal	VERB
cana-4022	113	4	that	that	SCONJ
cana-4022	113	5	an	an	DET
cana-4022	113	6	increase	increase	NOUN
cana-4022	113	7	in	in	ADP
cana-4022	113	8	feature	feature	NOUN
cana-4022	113	9	dimensionally	dimensionally	ADV
cana-4022	113	10	also	also	ADV
cana-4022	113	11	adversely	adversely	ADV
cana-4022	113	12	affected	affect	VERB
cana-4022	113	13	the	the	DET
cana-4022	113	14	performance	performance	NOUN
cana-4022	113	15	of	of	ADP
cana-4022	113	16	the	the	DET
cana-4022	113	17	supervised	supervised	ADJ
cana-4022	113	18	models	model	NOUN
cana-4022	113	19	(	(	PUNCT
cana-4022	113	20	r=	r=	NOUN
cana-4022	113	21	-0.72	-0.72	NOUN
cana-4022	113	22	,	,	PUNCT
cana-4022	113	23	p	p	X
cana-4022	113	24	=	=	NOUN
cana-4022	113	25	0.015	0.015	NUM
cana-4022	113	26	)	)	PUNCT
cana-4022	113	27	where	where	SCONJ
cana-4022	113	28	as	as	SCONJ
cana-4022	113	29	the	the	DET
cana-4022	113	30	effect	effect	NOUN
cana-4022	113	31	was	be	AUX
cana-4022	113	32	not	not	PART
cana-4022	113	33	so	so	ADV
cana-4022	113	34	pronounced	pronounce	VERB
cana-4022	113	35	on	on	ADP
cana-4022	113	36	the	the	DET
cana-4022	113	37	unsupervised	unsupervised	ADJ
cana-4022	113	38	model	model	NOUN
cana-4022	113	39	(	(	PUNCT
cana-4022	113	40	r=	r=	ADJ
cana-4022	113	41	-0.34	-0.34	NOUN
cana-4022	113	42	,	,	PUNCT
cana-4022	113	43	p	p	NOUN
cana-4022	113	44	=	=	NOUN
cana-4022	113	45	0.19	0.19	NUM
cana-4022	113	46	)	)	PUNCT
cana-4022	113	47	figure	figure	NOUN
cana-4022	113	48	4	4	NUM
cana-4022	113	49	also	also	ADV
cana-4022	113	50	displays	display	VERB
cana-4022	113	51	the	the	DET
cana-4022	113	52	error	error	NOUN
cana-4022	113	53	rate	rate	NOUN
cana-4022	113	54	of	of	ADP
cana-4022	113	55	different	different	ADJ
cana-4022	113	56	models	model	NOUN
cana-4022	113	57	of	of	ADP
cana-4022	113	58	ai	ai	NOUN
cana-4022	113	59	,	,	PUNCT
cana-4022	113	60	and	and	CCONJ
cana-4022	113	61	it	it	PRON
cana-4022	113	62	shows	show	VERB
cana-4022	113	63	that	that	SCONJ
cana-4022	113	64	,	,	PUNCT
cana-4022	113	65	generally	generally	ADV
cana-4022	113	66	,	,	PUNCT
cana-4022	113	67	the	the	DET
cana-4022	113	68	error	error	NOUN
cana-4022	113	69	rate	rate	NOUN
cana-4022	113	70	of	of	ADP
cana-4022	113	71	the	the	DET
cana-4022	113	72	unsupervised	unsupervised	ADJ
cana-4022	113	73	models	model	NOUN
cana-4022	113	74	was	be	AUX
cana-4022	113	75	higher	high	ADJ
cana-4022	113	76	as	as	SCONJ
cana-4022	113	77	compared	compare	VERB
cana-4022	113	78	to	to	ADP
cana-4022	113	79	the	the	DET
cana-4022	113	80	supervised	supervised	ADJ
cana-4022	113	81	models	model	NOUN
cana-4022	113	82	.	.	PUNCT
cana-4022	114	1	table	table	NOUN
cana-4022	114	2	4	4	NUM
cana-4022	114	3	:	:	PUNCT
cana-4022	114	4	correlation	correlation	NOUN
cana-4022	114	5	between	between	ADP
cana-4022	114	6	model	model	NOUN
cana-4022	114	7	accuracy	accuracy	NOUN
cana-4022	114	8	and	and	CCONJ
cana-4022	114	9	data	datum	NOUN
cana-4022	114	10	complexity	complexity	NOUN
cana-4022	114	11	model	model	NOUN
cana-4022	114	12	type	type	NOUN
cana-4022	114	13	correlation	correlation	NOUN
cana-4022	114	14	(	(	PUNCT
cana-4022	114	15	r	r	NOUN
cana-4022	114	16	)	)	PUNCT
cana-4022	114	17	p	p	NOUN
cana-4022	114	18	-	-	PUNCT
cana-4022	114	19	value	value	NOUN
cana-4022	114	20	supervised	supervise	VERB
cana-4022	114	21	models	model	NOUN
cana-4022	114	22	-0.72	-0.72	NUM
cana-4022	114	23	0.015	0.015	NUM
cana-4022	114	24	unsupervised	unsupervised	ADJ
cana-4022	114	25	models	model	NOUN
cana-4022	114	26	-0.34	-0.34	VERB
cana-4022	114	27	0.19	0.19	NUM
cana-4022	114	28	communications	communication	NOUN
cana-4022	114	29	on	on	ADP
cana-4022	114	30	applied	apply	VERB
cana-4022	114	31	nonlinear	nonlinear	ADJ
cana-4022	114	32	analysis	analysis	NOUN
cana-4022	114	33	issn	issn	NOUN
cana-4022	114	34	:	:	PUNCT
cana-4022	114	35	1074	1074	NUM
cana-4022	114	36	-	-	PUNCT
cana-4022	114	37	133x	133x	NUM
cana-4022	114	38	vol	vol	NOUN
cana-4022	114	39	32	32	NUM
cana-4022	114	40	no	no	NOUN
cana-4022	114	41	.	.	PUNCT
cana-4022	115	1	9s	9s	NUM
cana-4022	115	2	(	(	PUNCT
cana-4022	115	3	2025	2025	NUM
cana-4022	115	4	)	)	PUNCT
cana-4022	115	5	868	868	NUM
cana-4022	115	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-4022	115	7	figure	figure	NOUN
cana-4022	115	8	4	4	NUM
cana-4022	115	9	:	:	PUNCT
cana-4022	115	10	error	error	NOUN
cana-4022	115	11	rate	rate	NOUN
cana-4022	115	12	comparison	comparison	NOUN
cana-4022	115	13	across	across	ADP
cana-4022	115	14	different	different	ADJ
cana-4022	115	15	ai	ai	NOUN
cana-4022	115	16	models	model	NOUN
cana-4022	115	17	the	the	DET
cana-4022	115	18	figure	figure	NOUN
cana-4022	115	19	presents	present	VERB
cana-4022	115	20	the	the	DET
cana-4022	115	21	comparison	comparison	NOUN
cana-4022	115	22	of	of	ADP
cana-4022	115	23	the	the	DET
cana-4022	115	24	error	error	NOUN
cana-4022	115	25	rate	rate	NOUN
cana-4022	115	26	of	of	ADP
cana-4022	115	27	the	the	DET
cana-4022	115	28	exercise	exercise	NOUN
cana-4022	115	29	between	between	ADP
cana-4022	115	30	the	the	DET
cana-4022	115	31	two	two	NUM
cana-4022	115	32	approaches	approach	NOUN
cana-4022	115	33	:	:	PUNCT
cana-4022	115	34	supervised	supervised	ADJ
cana-4022	115	35	and	and	CCONJ
cana-4022	115	36	unsupervised	unsupervised	ADJ
cana-4022	115	37	.	.	PUNCT
cana-4022	116	1	accuracies	accuracy	NOUN
cana-4022	116	2	on	on	ADP
cana-4022	116	3	all	all	DET
cana-4022	116	4	the	the	DET
cana-4022	116	5	datasets	dataset	NOUN
cana-4022	116	6	are	be	AUX
cana-4022	116	7	less	less	ADV
cana-4022	116	8	erroneous	erroneous	ADJ
cana-4022	116	9	incorporating	incorporate	VERB
cana-4022	116	10	a	a	DET
cana-4022	116	11	clear	clear	ADJ
cana-4022	116	12	disparity	disparity	NOUN
cana-4022	116	13	where	where	SCONJ
cana-4022	116	14	svm	svm	PROPN
cana-4022	116	15	is	be	AUX
cana-4022	116	16	the	the	DET
cana-4022	116	17	most	most	ADV
cana-4022	116	18	accurate	accurate	ADJ
cana-4022	116	19	model	model	NOUN
cana-4022	116	20	while	while	SCONJ
cana-4022	116	21	k	k	NOUN
cana-4022	116	22	-	-	PUNCT
cana-4022	116	23	means	means	NOUN
cana-4022	116	24	has	have	VERB
cana-4022	116	25	a	a	DET
cana-4022	116	26	higher	high	ADJ
cana-4022	116	27	variance	variance	NOUN
cana-4022	116	28	regarding	regard	VERB
cana-4022	116	29	cluster	cluster	NOUN
cana-4022	116	30	accuracy	accuracy	NOUN
cana-4022	116	31	.	.	PUNCT
cana-4022	117	1	overall	overall	ADV
cana-4022	117	2	,	,	PUNCT
cana-4022	117	3	there	there	PRON
cana-4022	117	4	is	be	VERB
cana-4022	117	5	support	support	NOUN
cana-4022	117	6	to	to	ADP
cana-4022	117	7	the	the	DET
cana-4022	117	8	notion	notion	NOUN
cana-4022	117	9	that	that	SCONJ
cana-4022	117	10	supervised	supervised	ADJ
cana-4022	117	11	learning	learning	NOUN
cana-4022	117	12	models	model	NOUN
cana-4022	117	13	have	have	AUX
cana-4022	117	14	been	be	AUX
cana-4022	117	15	significantly	significantly	ADV
cana-4022	117	16	superior	superior	ADJ
cana-4022	117	17	in	in	ADP
cana-4022	117	18	structured	structured	ADJ
cana-4022	117	19	classification	classification	NOUN
cana-4022	117	20	tasks	task	NOUN
cana-4022	117	21	more	more	ADJ
cana-4022	117	22	than	than	ADP
cana-4022	117	23	the	the	DET
cana-4022	117	24	unsupervised	unsupervised	ADJ
cana-4022	117	25	models	model	NOUN
cana-4022	117	26	which	which	PRON
cana-4022	117	27	are	be	AUX
cana-4022	117	28	more	more	ADV
cana-4022	117	29	appropriate	appropriate	ADJ
cana-4022	117	30	in	in	ADP
cana-4022	117	31	exploratory	exploratory	ADJ
cana-4022	117	32	analysis	analysis	NOUN
cana-4022	117	33	.	.	PUNCT
cana-4022	118	1	the	the	DET
cana-4022	118	2	results	result	NOUN
cana-4022	118	3	highlight	highlight	VERB
cana-4022	118	4	the	the	DET
cana-4022	118	5	need	need	NOUN
cana-4022	118	6	or	or	CCONJ
cana-4022	118	7	decision	decision	NOUN
cana-4022	118	8	on	on	ADP
cana-4022	118	9	choosing	choose	VERB
cana-4022	118	10	suitable	suitable	ADJ
cana-4022	118	11	learning	learning	NOUN
cana-4022	118	12	models	model	NOUN
cana-4022	118	13	depending	depend	VERB
cana-4022	118	14	on	on	ADP
cana-4022	118	15	data	datum	NOUN
cana-4022	118	16	characteristics	characteristic	NOUN
cana-4022	118	17	and	and	CCONJ
cana-4022	118	18	availability	availability	NOUN
cana-4022	118	19	of	of	ADP
cana-4022	118	20	labels	label	NOUN
cana-4022	118	21	.	.	PUNCT
cana-4022	119	1	8	8	X
cana-4022	119	2	.	.	X
cana-4022	119	3	data	datum	NOUN
cana-4022	119	4	analysis	analysis	NOUN
cana-4022	119	5	and	and	CCONJ
cana-4022	119	6	interpretation	interpretation	NOUN
cana-4022	119	7	the	the	DET
cana-4022	119	8	study	study	NOUN
cana-4022	119	9	of	of	ADP
cana-4022	119	10	supervised	supervised	ADJ
cana-4022	119	11	and	and	CCONJ
cana-4022	119	12	unsupervised	unsupervised	ADJ
cana-4022	119	13	learning	learning	NOUN
cana-4022	119	14	models	model	NOUN
cana-4022	119	15	was	be	AUX
cana-4022	119	16	done	do	VERB
cana-4022	119	17	using	use	VERB
cana-4022	119	18	three	three	NUM
cana-4022	119	19	datasets	dataset	NOUN
cana-4022	119	20	,	,	PUNCT
cana-4022	119	21	which	which	PRON
cana-4022	119	22	are	be	AUX
cana-4022	119	23	different	different	ADJ
cana-4022	119	24	in	in	ADP
cana-4022	119	25	features	feature	NOUN
cana-4022	119	26	and	and	CCONJ
cana-4022	119	27	distribution	distribution	NOUN
cana-4022	119	28	(	(	PUNCT
cana-4022	119	29	see	see	VERB
cana-4022	119	30	table	table	NOUN
cana-4022	119	31	1	1	NUM
cana-4022	119	32	)	)	PUNCT
cana-4022	119	33	.	.	PUNCT
cana-4022	120	1	it	it	PRON
cana-4022	120	2	can	can	AUX
cana-4022	120	3	be	be	AUX
cana-4022	120	4	understood	understand	VERB
cana-4022	120	5	that	that	SCONJ
cana-4022	120	6	the	the	DET
cana-4022	120	7	given	give	VERB
cana-4022	120	8	financial	financial	ADJ
cana-4022	120	9	transactions	transaction	NOUN
cana-4022	120	10	dataset	dataset	VERB
cana-4022	120	11	was	be	AUX
cana-4022	120	12	imbalanced	imbalance	VERB
cana-4022	120	13	;	;	PUNCT
cana-4022	120	14	the	the	DET
cana-4022	120	15	fraud	fraud	NOUN
cana-4022	120	16	varieties	variety	NOUN
cana-4022	120	17	made	make	VERB
cana-4022	120	18	up	up	ADP
cana-4022	120	19	only	only	ADV
cana-4022	120	20	3.2	3.2	NUM
cana-4022	120	21	%	%	NOUN
cana-4022	120	22	of	of	ADP
cana-4022	120	23	all	all	DET
cana-4022	120	24	instances	instance	NOUN
cana-4022	120	25	.	.	PUNCT
cana-4022	121	1	however	however	ADV
cana-4022	121	2	,	,	PUNCT
cana-4022	121	3	it	it	PRON
cana-4022	121	4	was	be	AUX
cana-4022	121	5	observed	observe	VERB
cana-4022	121	6	that	that	SCONJ
cana-4022	121	7	both	both	CCONJ
cana-4022	121	8	the	the	DET
cana-4022	121	9	healthcare	healthcare	NOUN
cana-4022	121	10	and	and	CCONJ
cana-4022	121	11	image	image	NOUN
cana-4022	121	12	recognition	recognition	NOUN
cana-4022	121	13	datasets	dataset	NOUN
cana-4022	121	14	were	be	AUX
cana-4022	121	15	balanced	balance	VERB
cana-4022	121	16	datasets	dataset	NOUN
cana-4022	121	17	with	with	ADP
cana-4022	121	18	relatively	relatively	ADV
cana-4022	121	19	equal	equal	ADJ
cana-4022	121	20	samples	sample	NOUN
cana-4022	121	21	on	on	ADP
cana-4022	121	22	both	both	CCONJ
cana-4022	121	23	the	the	DET
cana-4022	121	24	classes	class	NOUN
cana-4022	121	25	which	which	PRON
cana-4022	121	26	impacted	impact	VERB
cana-4022	121	27	models	model	NOUN
cana-4022	121	28	specially	specially	ADV
cana-4022	121	29	concerning	concern	VERB
cana-4022	121	30	to	to	ADP
cana-4022	121	31	supervised	supervised	ADJ
cana-4022	121	32	learning	learning	NOUN
cana-4022	121	33	.	.	PUNCT
cana-4022	122	1	supervised	supervised	ADJ
cana-4022	122	2	models	model	NOUN
cana-4022	122	3	giving	give	VERB
cana-4022	122	4	better	well	ADJ
cana-4022	122	5	results	result	NOUN
cana-4022	122	6	in	in	ADP
cana-4022	122	7	classification	classification	NOUN
cana-4022	122	8	task	task	NOUN
cana-4022	122	9	compared	compare	VERB
cana-4022	122	10	to	to	ADP
cana-4022	122	11	unsupervised	unsupervised	ADJ
cana-4022	122	12	all	all	PRON
cana-4022	122	13	give	give	VERB
cana-4022	122	14	the	the	DET
cana-4022	122	15	better	well	ADJ
cana-4022	122	16	performance	performance	NOUN
cana-4022	122	17	of	of	ADP
cana-4022	122	18	classification	classification	NOUN
cana-4022	122	19	,	,	PUNCT
cana-4022	122	20	among	among	ADP
cana-4022	122	21	them	they	PRON
cana-4022	122	22	svm	svm	ADJ
cana-4022	122	23	/	/	SYM
cana-4022	122	24	out	out	ADP
cana-4022	122	25	performed	perform	VERB
cana-4022	122	26	all	all	DET
cana-4022	122	27	the	the	DET
cana-4022	122	28	models	model	NOUN
cana-4022	122	29	with	with	ADP
cana-4022	122	30	higher	high	ADJ
cana-4022	122	31	accuracy	accuracy	NOUN
cana-4022	122	32	92.4	92.4	NUM
cana-4022	122	33	%	%	NOUN
cana-4022	122	34	and	and	CCONJ
cana-4022	122	35	precision	precision	NOUN
cana-4022	122	36	94.2	94.2	NUM
cana-4022	122	37	%	%	NOUN
cana-4022	122	38	followed	follow	VERB
cana-4022	122	39	by	by	ADP
cana-4022	122	40	decision	decision	NOUN
cana-4022	122	41	tree	tree	NOUN
cana-4022	122	42	with	with	ADP
cana-4022	122	43	an	an	DET
cana-4022	122	44	accuracy	accuracy	NOUN
cana-4022	122	45	91.8	91.8	NUM
cana-4022	122	46	%	%	NOUN
cana-4022	122	47	(	(	PUNCT
cana-4022	122	48	table	table	NOUN
cana-4022	122	49	2	2	NUM
cana-4022	122	50	)	)	PUNCT
cana-4022	122	51	.	.	PUNCT
cana-4022	123	1	from	from	ADP
cana-4022	123	2	figure	figure	NOUN
cana-4022	123	3	1	1	NUM
cana-4022	123	4	,	,	PUNCT
cana-4022	123	5	the	the	DET
cana-4022	123	6	validity	validity	NOUN
cana-4022	123	7	accuracy	accuracy	NOUN
cana-4022	123	8	increases	increase	VERB
cana-4022	123	9	with	with	ADP
cana-4022	123	10	epochs	epoch	NOUN
cana-4022	123	11	for	for	ADP
cana-4022	123	12	svm	svm	ADJ
cana-4022	123	13	,	,	PUNCT
cana-4022	123	14	and	and	CCONJ
cana-4022	123	15	in	in	ADP
cana-4022	123	16	the	the	DET
cana-4022	123	17	case	case	NOUN
cana-4022	123	18	of	of	ADP
cana-4022	123	19	the	the	DET
cana-4022	123	20	decision	decision	NOUN
cana-4022	123	21	trees	tree	NOUN
cana-4022	123	22	,	,	PUNCT
cana-4022	123	23	the	the	DET
cana-4022	123	24	fluctuating	fluctuate	VERB
cana-4022	123	25	pattern	pattern	NOUN
cana-4022	123	26	that	that	PRON
cana-4022	123	27	results	result	VERB
cana-4022	123	28	from	from	ADP
cana-4022	123	29	it	it	PRON
cana-4022	123	30	may	may	AUX
cana-4022	123	31	have	have	AUX
cana-4022	123	32	shown	show	VERB
cana-4022	123	33	sensitivity	sensitivity	NOUN
cana-4022	123	34	to	to	ADP
cana-4022	123	35	the	the	DET
cana-4022	123	36	training	training	NOUN
cana-4022	123	37	data	datum	NOUN
cana-4022	123	38	set	set	VERB
cana-4022	123	39	.	.	PUNCT
cana-4022	124	1	the	the	DET
cana-4022	124	2	confusion	confusion	NOUN
cana-4022	124	3	matrices	matrix	NOUN
cana-4022	124	4	depicted	depict	VERB
cana-4022	124	5	below	below	ADV
cana-4022	124	6	in	in	ADP
cana-4022	124	7	figure	figure	NOUN
cana-4022	124	8	2	2	NUM
cana-4022	124	9	also	also	ADV
cana-4022	124	10	supports	support	VERB
cana-4022	124	11	this	this	DET
cana-4022	124	12	statement	statement	NOUN
cana-4022	124	13	,	,	PUNCT
cana-4022	124	14	and	and	CCONJ
cana-4022	124	15	was	be	AUX
cana-4022	124	16	used	use	VERB
cana-4022	124	17	to	to	PART
cana-4022	124	18	deduce	deduce	VERB
cana-4022	124	19	that	that	SCONJ
cana-4022	124	20	even	even	ADV
cana-4022	124	21	though	though	SCONJ
cana-4022	124	22	both	both	DET
cana-4022	124	23	decision	decision	NOUN
cana-4022	124	24	tree	tree	NOUN
cana-4022	124	25	and	and	CCONJ
cana-4022	124	26	svm	svm	PROPN
cana-4022	124	27	yielded	yield	VERB
cana-4022	124	28	similar	similar	ADJ
cana-4022	124	29	results	result	NOUN
cana-4022	124	30	,	,	PUNCT
cana-4022	124	31	svm	svm	PROPN
cana-4022	124	32	had	have	VERB
cana-4022	124	33	fewer	few	ADJ
cana-4022	124	34	number	number	NOUN
cana-4022	124	35	of	of	ADP
cana-4022	124	36	misclassified	misclassified	ADJ
cana-4022	124	37	instances	instance	NOUN
cana-4022	124	38	in	in	ADP
cana-4022	124	39	terms	term	NOUN
cana-4022	124	40	of	of	ADP
cana-4022	124	41	false	false	ADJ
cana-4022	124	42	negatives	negative	NOUN
cana-4022	124	43	and	and	CCONJ
cana-4022	124	44	therefore	therefore	ADV
cana-4022	124	45	is	be	AUX
cana-4022	124	46	more	more	ADV
cana-4022	124	47	appropriate	appropriate	ADJ
cana-4022	124	48	for	for	ADP
cana-4022	124	49	important	important	ADJ
cana-4022	124	50	classification	classification	NOUN
cana-4022	124	51	applications	application	NOUN
cana-4022	124	52	like	like	ADP
cana-4022	124	53	fraud	fraud	NOUN
cana-4022	124	54	detection	detection	NOUN
cana-4022	124	55	and	and	CCONJ
cana-4022	124	56	disease	disease	NOUN
cana-4022	124	57	prediction	prediction	NOUN
cana-4022	124	58	.	.	PUNCT
cana-4022	125	1	communications	communication	NOUN
cana-4022	125	2	on	on	ADP
cana-4022	125	3	applied	apply	VERB
cana-4022	125	4	nonlinear	nonlinear	ADJ
cana-4022	125	5	analysis	analysis	NOUN
cana-4022	125	6	issn	issn	NOUN
cana-4022	125	7	:	:	PUNCT
cana-4022	125	8	1074	1074	NUM
cana-4022	125	9	-	-	PUNCT
cana-4022	125	10	133x	133x	NUM
cana-4022	125	11	vol	vol	NOUN
cana-4022	125	12	32	32	NUM
cana-4022	125	13	no	no	NOUN
cana-4022	125	14	.	.	PUNCT
cana-4022	126	1	9s	9s	NUM
cana-4022	126	2	(	(	PUNCT
cana-4022	126	3	2025	2025	NUM
cana-4022	126	4	)	)	PUNCT
cana-4022	126	5	869	869	NUM
cana-4022	126	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-4022	126	7	in	in	ADP
cana-4022	126	8	terms	term	NOUN
cana-4022	126	9	of	of	ADP
cana-4022	126	10	the	the	DET
cana-4022	126	11	discoveries	discovery	NOUN
cana-4022	126	12	of	of	ADP
cana-4022	126	13	the	the	DET
cana-4022	126	14	patterns	pattern	NOUN
cana-4022	126	15	,	,	PUNCT
cana-4022	126	16	both	both	DET
cana-4022	126	17	k	k	NOUN
cana-4022	126	18	-	-	PUNCT
cana-4022	126	19	means	mean	VERB
cana-4022	126	20	clustering	clustering	NOUN
cana-4022	126	21	and	and	CCONJ
cana-4022	126	22	autoencoders	autoencoder	NOUN
cana-4022	126	23	were	be	AUX
cana-4022	126	24	found	find	VERB
cana-4022	126	25	to	to	PART
cana-4022	126	26	be	be	AUX
cana-4022	126	27	moderately	moderately	ADV
cana-4022	126	28	useful	useful	ADJ
cana-4022	126	29	if	if	SCONJ
cana-4022	126	30	used	use	VERB
cana-4022	126	31	unsupervised	unsupervised	ADJ
cana-4022	126	32	.	.	PUNCT
cana-4022	127	1	k	k	X
cana-4022	127	2	-	-	PUNCT
cana-4022	127	3	means	means	NOUN
cana-4022	127	4	has	have	VERB
cana-4022	127	5	a	a	DET
cana-4022	127	6	silhouette	silhouette	NOUN
cana-4022	127	7	of	of	ADP
cana-4022	127	8	0.72	0.72	NUM
cana-4022	127	9	indicating	indicate	VERB
cana-4022	127	10	reasonable	reasonable	ADJ
cana-4022	127	11	ratio	ratio	NOUN
cana-4022	127	12	between	between	ADP
cana-4022	127	13	cluster	cluster	NOUN
cana-4022	127	14	density	density	NOUN
cana-4022	127	15	and	and	CCONJ
cana-4022	127	16	dissimilarity	dissimilarity	NOUN
cana-4022	127	17	of	of	ADP
cana-4022	127	18	the	the	DET
cana-4022	127	19	clusters	cluster	NOUN
cana-4022	127	20	while	while	SCONJ
cana-4022	127	21	autoencoders	autoencoder	NOUN
cana-4022	127	22	has	have	VERB
cana-4022	127	23	a	a	DET
cana-4022	127	24	silhouette	silhouette	NOUN
cana-4022	127	25	of	of	ADP
cana-4022	127	26	0.58	0.58	NUM
cana-4022	127	27	as	as	ADP
cana-4022	127	28	an	an	DET
cana-4022	127	29	indication	indication	NOUN
cana-4022	127	30	of	of	ADP
cana-4022	127	31	overlapping	overlap	VERB
cana-4022	127	32	clusters	cluster	NOUN
cana-4022	127	33	in	in	ADP
cana-4022	127	34	the	the	DET
cana-4022	127	35	groups	group	NOUN
cana-4022	127	36	(	(	PUNCT
cana-4022	127	37	table	table	NOUN
cana-4022	127	38	2	2	NUM
cana-4022	127	39	)	)	PUNCT
cana-4022	127	40	.	.	PUNCT
cana-4022	128	1	these	these	PRON
cana-4022	128	2	are	be	AUX
cana-4022	128	3	illustrated	illustrate	VERB
cana-4022	128	4	in	in	ADP
cana-4022	128	5	the	the	DET
cana-4022	128	6	cluster	cluster	NOUN
cana-4022	128	7	visualization	visualization	NOUN
cana-4022	128	8	in	in	ADP
cana-4022	128	9	figure	figure	NOUN
cana-4022	128	10	3	3	NUM
cana-4022	128	11	where	where	SCONJ
cana-4022	128	12	k	k	NOUN
cana-4022	128	13	-	-	PUNCT
cana-4022	128	14	means	means	NOUN
cana-4022	128	15	representative	representative	NOUN
cana-4022	128	16	shown	show	VERB
cana-4022	128	17	to	to	PART
cana-4022	128	18	form	form	VERB
cana-4022	128	19	coherent	coherent	ADJ
cana-4022	128	20	clusters	cluster	NOUN
cana-4022	128	21	in	in	ADP
cana-4022	128	22	the	the	DET
cana-4022	128	23	financial	financial	ADJ
cana-4022	128	24	data	datum	NOUN
cana-4022	128	25	while	while	SCONJ
cana-4022	128	26	autoencoders	autoencoder	NOUN
cana-4022	128	27	failed	fail	VERB
cana-4022	128	28	to	to	PART
cana-4022	128	29	clearly	clearly	ADV
cana-4022	128	30	cluster	cluster	VERB
cana-4022	128	31	the	the	DET
cana-4022	128	32	dataset	dataset	NOUN
cana-4022	128	33	of	of	ADP
cana-4022	128	34	the	the	DET
cana-4022	128	35	healthcare	healthcare	NOUN
cana-4022	128	36	industry	industry	NOUN
cana-4022	128	37	.	.	PUNCT
cana-4022	129	1	the	the	DET
cana-4022	129	2	statistical	statistical	ADJ
cana-4022	129	3	analysis	analysis	NOUN
cana-4022	129	4	affirms	affirm	VERB
cana-4022	129	5	these	these	DET
cana-4022	129	6	ranges	range	NOUN
cana-4022	129	7	of	of	ADP
cana-4022	129	8	performance	performance	NOUN
cana-4022	129	9	differences	difference	NOUN
cana-4022	129	10	.	.	PUNCT
cana-4022	130	1	analysis	analysis	NOUN
cana-4022	130	2	on	on	ADP
cana-4022	130	3	anova	anova	PROPN
cana-4022	130	4	showed	show	VERB
cana-4022	130	5	that	that	SCONJ
cana-4022	130	6	there	there	PRON
cana-4022	130	7	was	be	VERB
cana-4022	130	8	highly	highly	ADV
cana-4022	130	9	significant	significant	ADJ
cana-4022	130	10	difference	difference	NOUN
cana-4022	130	11	on	on	ADP
cana-4022	130	12	model	model	NOUN
cana-4022	130	13	accuracy	accuracy	NOUN
cana-4022	130	14	based	base	VERB
cana-4022	130	15	on	on	ADP
cana-4022	130	16	the	the	DET
cana-4022	130	17	type	type	NOUN
cana-4022	130	18	of	of	ADP
cana-4022	130	19	algorithms	algorithm	NOUN
cana-4022	130	20	at	at	ADP
cana-4022	130	21	the	the	DET
cana-4022	130	22	p	p	X
cana-4022	130	23	<	<	X
cana-4022	130	24	0.01	0.01	NUM
cana-4022	130	25	level	level	NOUN
cana-4022	130	26	the	the	DET
cana-4022	130	27	paired	pair	VERB
cana-4022	130	28	t	t	NOUN
cana-4022	130	29	-	-	PUNCT
cana-4022	130	30	tests	test	NOUN
cana-4022	130	31	tests	test	NOUN
cana-4022	130	32	also	also	ADV
cana-4022	130	33	indicated	indicate	VERB
cana-4022	130	34	that	that	SCONJ
cana-4022	130	35	the	the	DET
cana-4022	130	36	supervised	supervised	ADJ
cana-4022	130	37	models	model	NOUN
cana-4022	130	38	of	of	ADP
cana-4022	130	39	identification	identification	NOUN
cana-4022	130	40	were	be	AUX
cana-4022	130	41	significantly	significantly	ADV
cana-4022	130	42	higher	high	ADJ
cana-4022	130	43	than	than	ADP
cana-4022	130	44	those	those	PRON
cana-4022	130	45	of	of	ADP
cana-4022	130	46	the	the	DET
cana-4022	130	47	unsupervised	unsupervised	ADJ
cana-4022	130	48	models	model	NOUN
cana-4022	130	49	with	with	ADP
cana-4022	130	50	p	p	NOUN
cana-4022	130	51	=	=	NOUN
cana-4022	130	52	0.002(table	0.002(table	NUM
cana-4022	130	53	3	3	NUM
cana-4022	130	54	)	)	PUNCT
cana-4022	130	55	.	.	PUNCT
cana-4022	131	1	in	in	ADP
cana-4022	131	2	table	table	NOUN
cana-4022	131	3	4	4	NUM
cana-4022	131	4	,	,	PUNCT
cana-4022	131	5	the	the	DET
cana-4022	131	6	correlation	correlation	NOUN
cana-4022	131	7	study	study	NOUN
cana-4022	131	8	showed	show	VERB
cana-4022	131	9	that	that	SCONJ
cana-4022	131	10	the	the	DET
cana-4022	131	11	level	level	NOUN
cana-4022	131	12	of	of	ADP
cana-4022	131	13	relationship	relationship	NOUN
cana-4022	131	14	between	between	ADP
cana-4022	131	15	feature	feature	NOUN
cana-4022	131	16	dimensionality	dimensionality	NOUN
cana-4022	131	17	and	and	CCONJ
cana-4022	131	18	the	the	DET
cana-4022	131	19	accuracy	accuracy	NOUN
cana-4022	131	20	of	of	ADP
cana-4022	131	21	the	the	DET
cana-4022	131	22	trained	train	VERB
cana-4022	131	23	model	model	NOUN
cana-4022	131	24	was	be	AUX
cana-4022	131	25	negative	negative	ADJ
cana-4022	131	26	(	(	PUNCT
cana-4022	131	27	r	r	NOUN
cana-4022	131	28	=	=	SYM
cana-4022	131	29	-0.72	-0.72	NOUN
cana-4022	131	30	,	,	PUNCT
cana-4022	131	31	p	p	X
cana-4022	131	32	=	=	NOUN
cana-4022	131	33	0.015	0.015	NUM
cana-4022	131	34	)	)	PUNCT
cana-4022	131	35	which	which	PRON
cana-4022	131	36	indicated	indicate	VERB
cana-4022	131	37	that	that	SCONJ
cana-4022	131	38	increased	increase	VERB
cana-4022	131	39	large	large	ADJ
cana-4022	131	40	set	set	NOUN
cana-4022	131	41	size	size	NOUN
cana-4022	131	42	impacted	impact	VERB
cana-4022	131	43	on	on	ADP
cana-4022	131	44	classification	classification	NOUN
cana-4022	131	45	performance	performance	NOUN
cana-4022	131	46	adversely	adversely	ADV
cana-4022	131	47	.	.	PUNCT
cana-4022	132	1	on	on	ADP
cana-4022	132	2	the	the	DET
cana-4022	132	3	other	other	ADJ
cana-4022	132	4	hand	hand	NOUN
cana-4022	132	5	,	,	PUNCT
cana-4022	132	6	unsupervised	unsupervised	ADJ
cana-4022	132	7	models	model	NOUN
cana-4022	132	8	which	which	PRON
cana-4022	132	9	were	be	AUX
cana-4022	132	10	less	less	ADV
cana-4022	132	11	rigid	rigid	ADJ
cana-4022	132	12	showed	show	VERB
cana-4022	132	13	a	a	DET
cana-4022	132	14	relatively	relatively	ADV
cana-4022	132	15	negative	negative	ADJ
cana-4022	132	16	but	but	CCONJ
cana-4022	132	17	less	less	ADV
cana-4022	132	18	significant	significant	ADJ
cana-4022	132	19	correlation	correlation	NOUN
cana-4022	132	20	of	of	ADP
cana-4022	132	21	-0.34	-0.34	NOUN
cana-4022	132	22	(	(	PUNCT
cana-4022	132	23	p	p	NOUN
cana-4022	132	24	=	=	NOUN
cana-4022	132	25	0.19	0.19	NUM
cana-4022	132	26	)	)	PUNCT
cana-4022	132	27	implying	imply	VERB
cana-4022	132	28	more	more	ADJ
cana-4022	132	29	ability	ability	NOUN
cana-4022	132	30	of	of	ADP
cana-4022	132	31	generalizing	generalize	VERB
cana-4022	132	32	on	on	ADP
cana-4022	132	33	the	the	DET
cana-4022	132	34	structural	structural	ADJ
cana-4022	132	35	data	datum	NOUN
cana-4022	132	36	.	.	PUNCT
cana-4022	133	1	a	a	DET
cana-4022	133	2	comparison	comparison	NOUN
cana-4022	133	3	of	of	ADP
cana-4022	133	4	model	model	NOUN
cana-4022	133	5	error	error	NOUN
cana-4022	133	6	rates	rate	NOUN
cana-4022	133	7	was	be	AUX
cana-4022	133	8	also	also	ADV
cana-4022	133	9	performed	perform	VERB
cana-4022	133	10	for	for	ADP
cana-4022	133	11	all	all	DET
cana-4022	133	12	the	the	DET
cana-4022	133	13	models	model	NOUN
cana-4022	133	14	and	and	CCONJ
cana-4022	133	15	the	the	DET
cana-4022	133	16	intervals	interval	NOUN
cana-4022	133	17	are	be	AUX
cana-4022	133	18	presented	present	VERB
cana-4022	133	19	in	in	ADP
cana-4022	133	20	figure	figure	NOUN
cana-4022	133	21	4	4	NUM
cana-4022	133	22	where	where	SCONJ
cana-4022	133	23	it	it	PRON
cana-4022	133	24	is	be	AUX
cana-4022	133	25	clear	clear	ADJ
cana-4022	133	26	that	that	SCONJ
cana-4022	133	27	all	all	DET
cana-4022	133	28	the	the	DET
cana-4022	133	29	supervised	supervised	ADJ
cana-4022	133	30	models	model	NOUN
cana-4022	133	31	have	have	VERB
cana-4022	133	32	a	a	DET
cana-4022	133	33	lower	low	ADJ
cana-4022	133	34	error	error	NOUN
cana-4022	133	35	rate	rate	NOUN
cana-4022	133	36	that	that	PRON
cana-4022	133	37	the	the	DET
cana-4022	133	38	unsupervised	unsupervised	ADJ
cana-4022	133	39	ones	one	NOUN
cana-4022	133	40	and	and	CCONJ
cana-4022	133	41	the	the	DET
cana-4022	133	42	winner	winner	NOUN
cana-4022	133	43	of	of	ADP
cana-4022	133	44	this	this	DET
cana-4022	133	45	round	round	NOUN
cana-4022	133	46	is	be	AUX
cana-4022	133	47	svm	svm	ADJ
cana-4022	133	48	with	with	ADP
cana-4022	133	49	the	the	DET
cana-4022	133	50	error	error	NOUN
cana-4022	133	51	rate	rate	NOUN
cana-4022	133	52	of	of	ADP
cana-4022	133	53	7.6	7.6	NUM
cana-4022	133	54	%	%	NOUN
cana-4022	133	55	,	,	PUNCT
cana-4022	133	56	while	while	SCONJ
cana-4022	133	57	the	the	DET
cana-4022	133	58	highest	high	ADJ
cana-4022	133	59	error	error	NOUN
cana-4022	133	60	rate	rate	NOUN
cana-4022	133	61	belongs	belong	VERB
cana-4022	133	62	to	to	ADP
cana-4022	133	63	k	k	NOUN
cana-4022	133	64	-	-	PUNCT
cana-4022	133	65	means	mean	VERB
cana-4022	133	66	clustering	cluster	VERB
cana-4022	133	67	equal	equal	ADJ
cana-4022	133	68	to	to	ADP
cana-4022	133	69	15.4	15.4	NUM
cana-4022	133	70	%	%	NOUN
cana-4022	133	71	.	.	PUNCT
cana-4022	134	1	this	this	PRON
cana-4022	134	2	helps	help	VERB
cana-4022	134	3	to	to	PART
cana-4022	134	4	conclude	conclude	VERB
cana-4022	134	5	that	that	SCONJ
cana-4022	134	6	supervised	supervised	ADJ
cana-4022	134	7	learning	learning	NOUN
cana-4022	134	8	is	be	AUX
cana-4022	134	9	best	good	ADJ
cana-4022	134	10	for	for	ADP
cana-4022	134	11	the	the	DET
cana-4022	134	12	structured	structured	ADJ
cana-4022	134	13	classification	classification	NOUN
cana-4022	134	14	problems	problem	NOUN
cana-4022	134	15	compared	compare	VERB
cana-4022	134	16	to	to	ADP
cana-4022	134	17	the	the	DET
cana-4022	134	18	unsupervised	unsupervised	ADJ
cana-4022	134	19	learning	learning	NOUN
cana-4022	134	20	model	model	NOUN
cana-4022	134	21	,	,	PUNCT
cana-4022	134	22	which	which	PRON
cana-4022	134	23	is	be	AUX
cana-4022	134	24	more	more	ADV
cana-4022	134	25	suitable	suitable	ADJ
cana-4022	134	26	for	for	ADP
cana-4022	134	27	a	a	DET
cana-4022	134	28	kind	kind	NOUN
cana-4022	134	29	of	of	ADP
cana-4022	134	30	data	data	NOUN
cana-4022	134	31	exploration	exploration	NOUN
cana-4022	134	32	or	or	CCONJ
cana-4022	134	33	description	description	NOUN
cana-4022	134	34	.	.	PUNCT
cana-4022	135	1	according	accord	VERB
cana-4022	135	2	to	to	ADP
cana-4022	135	3	the	the	DET
cana-4022	135	4	outcomes	outcome	NOUN
cana-4022	135	5	,	,	PUNCT
cana-4022	135	6	the	the	DET
cana-4022	135	7	focus	focus	NOUN
cana-4022	135	8	should	should	AUX
cana-4022	135	9	be	be	AUX
cana-4022	135	10	put	put	VERB
cana-4022	135	11	on	on	ADP
cana-4022	135	12	choosing	choose	VERB
cana-4022	135	13	the	the	DET
cana-4022	135	14	proper	proper	ADJ
cana-4022	135	15	learning	learning	NOUN
cana-4022	135	16	paradigm	paradigm	NOUN
cana-4022	135	17	depending	depend	VERB
cana-4022	135	18	on	on	ADP
cana-4022	135	19	data	data	NOUN
cana-4022	135	20	properties	property	NOUN
cana-4022	135	21	and	and	CCONJ
cana-4022	135	22	problem	problem	NOUN
cana-4022	135	23	relevance	relevance	NOUN
cana-4022	135	24	.	.	PUNCT
cana-4022	136	1	9	9	X
cana-4022	136	2	.	.	X
cana-4022	136	3	conclusion	conclusion	NOUN
cana-4022	136	4	the	the	DET
cana-4022	136	5	conclusion	conclusion	NOUN
cana-4022	136	6	made	make	VERB
cana-4022	136	7	from	from	ADP
cana-4022	136	8	this	this	DET
cana-4022	136	9	study	study	NOUN
cana-4022	136	10	confirms	confirm	VERB
cana-4022	136	11	the	the	DET
cana-4022	136	12	notion	notion	NOUN
cana-4022	136	13	that	that	SCONJ
cana-4022	136	14	supervised	supervise	VERB
cana-4022	136	15	learning	learn	VERB
cana-4022	136	16	algorithm	algorithm	NOUN
cana-4022	136	17	such	such	ADJ
cana-4022	136	18	as	as	ADP
cana-4022	136	19	svm	svm	PROPN
cana-4022	136	20	are	be	AUX
cana-4022	136	21	more	more	ADV
cana-4022	136	22	accurate	accurate	ADJ
cana-4022	136	23	,	,	PUNCT
cana-4022	136	24	and	and	CCONJ
cana-4022	136	25	can	can	AUX
cana-4022	136	26	reduce	reduce	VERB
cana-4022	136	27	the	the	DET
cana-4022	136	28	error	error	NOUN
cana-4022	136	29	rate	rate	NOUN
cana-4022	136	30	than	than	ADP
cana-4022	136	31	that	that	PRON
cana-4022	136	32	of	of	ADP
cana-4022	136	33	an	an	DET
cana-4022	136	34	unsupervised	unsupervised	ADJ
cana-4022	136	35	learning	learning	NOUN
cana-4022	136	36	technique	technique	NOUN
cana-4022	136	37	.	.	PUNCT
cana-4022	137	1	recently	recently	ADV
cana-4022	137	2	,	,	PUNCT
cana-4022	137	3	the	the	DET
cana-4022	137	4	experiments	experiment	NOUN
cana-4022	137	5	showed	show	VERB
cana-4022	137	6	that	that	SCONJ
cana-4022	137	7	supervised	supervised	ADJ
cana-4022	137	8	approaches	approach	NOUN
cana-4022	137	9	have	have	VERB
cana-4022	137	10	higher	high	ADJ
cana-4022	137	11	performance	performance	NOUN
cana-4022	137	12	metrics	metric	NOUN
cana-4022	137	13	,	,	PUNCT
cana-4022	137	14	including	include	VERB
cana-4022	137	15	in	in	ADP
cana-4022	137	16	the	the	DET
cana-4022	137	17	high	high	ADJ
cana-4022	137	18	-	-	PUNCT
cana-4022	137	19	structured	structure	VERB
cana-4022	137	20	data	datum	NOUN
cana-4022	137	21	set	set	VERB
cana-4022	137	22	while	while	SCONJ
cana-4022	137	23	unsupervised	unsupervised	ADJ
cana-4022	137	24	models	model	NOUN
cana-4022	137	25	applied	apply	VERB
cana-4022	137	26	in	in	ADP
cana-4022	137	27	unstructured	unstructured	ADJ
cana-4022	137	28	and	and	CCONJ
cana-4022	137	29	highdimension	highdimension	NOUN
cana-4022	137	30	data	datum	NOUN
cana-4022	137	31	set	set	VERB
cana-4022	137	32	perform	perform	VERB
cana-4022	137	33	well	well	ADV
cana-4022	137	34	.	.	PUNCT
cana-4022	138	1	figure	figure	VERB
cana-4022	138	2	5	5	NUM
cana-4022	138	3	:	:	PUNCT
cana-4022	138	4	new	new	ADJ
cana-4022	138	5	model	model	NOUN
cana-4022	138	6	based	base	VERB
cana-4022	138	7	on	on	ADP
cana-4022	138	8	our	our	PRON
cana-4022	138	9	findings	finding	NOUN
cana-4022	138	10	communications	communication	NOUN
cana-4022	138	11	on	on	ADP
cana-4022	138	12	applied	apply	VERB
cana-4022	138	13	nonlinear	nonlinear	ADJ
cana-4022	138	14	analysis	analysis	NOUN
cana-4022	138	15	issn	issn	NOUN
cana-4022	138	16	:	:	PUNCT
cana-4022	138	17	1074	1074	NUM
cana-4022	138	18	-	-	PUNCT
cana-4022	138	19	133x	133x	NUM
cana-4022	138	20	vol	vol	NOUN
cana-4022	138	21	32	32	NUM
cana-4022	139	1	no	no	NOUN
cana-4022	139	2	.	.	PUNCT
cana-4022	140	1	9s	9s	NUM
cana-4022	140	2	(	(	PUNCT
cana-4022	140	3	2025	2025	NUM
cana-4022	140	4	)	)	PUNCT
cana-4022	140	5	870	870	NUM
cana-4022	140	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-4022	141	1	this	this	DET
cana-4022	141	2	flowchart	flowchart	NOUN
cana-4022	141	3	details	detail	VERB
cana-4022	141	4	the	the	DET
cana-4022	141	5	decision	decision	NOUN
cana-4022	141	6	process	process	NOUN
cana-4022	141	7	that	that	PRON
cana-4022	141	8	one	one	PRON
cana-4022	141	9	would	would	AUX
cana-4022	141	10	follow	follow	VERB
cana-4022	141	11	when	when	SCONJ
cana-4022	141	12	choosing	choose	VERB
cana-4022	141	13	the	the	DET
cana-4022	141	14	most	most	ADV
cana-4022	141	15	suitable	suitable	ADJ
cana-4022	141	16	ml	ml	ADP
cana-4022	141	17	algorithm	algorithm	NOUN
cana-4022	141	18	to	to	PART
cana-4022	141	19	use	use	VERB
cana-4022	141	20	for	for	ADP
cana-4022	141	21	different	different	ADJ
cana-4022	141	22	characteristics	characteristic	NOUN
cana-4022	141	23	of	of	ADP
cana-4022	141	24	a	a	DET
cana-4022	141	25	dataset	dataset	NOUN
cana-4022	141	26	.	.	PUNCT
cana-4022	142	1	the	the	DET
cana-4022	142	2	operational	operational	ADJ
cana-4022	142	3	process	process	NOUN
cana-4022	142	4	starts	start	VERB
cana-4022	142	5	with	with	ADP
cana-4022	142	6	the	the	DET
cana-4022	142	7	classification	classification	NOUN
cana-4022	142	8	of	of	ADP
cana-4022	142	9	the	the	DET
cana-4022	142	10	dataset	dataset	NOUN
cana-4022	142	11	as	as	ADP
cana-4022	142	12	structured	structure	VERB
cana-4022	142	13	or	or	CCONJ
cana-4022	142	14	unstructured	unstructure	VERB
cana-4022	142	15	.	.	PUNCT
cana-4022	143	1	in	in	ADP
cana-4022	143	2	the	the	DET
cana-4022	143	3	case	case	NOUN
cana-4022	143	4	of	of	ADP
cana-4022	143	5	structure	structure	NOUN
cana-4022	143	6	data	datum	NOUN
cana-4022	143	7	,	,	PUNCT
cana-4022	143	8	it	it	PRON
cana-4022	143	9	is	be	AUX
cana-4022	143	10	always	always	ADV
cana-4022	143	11	recommended	recommend	VERB
cana-4022	143	12	that	that	SCONJ
cana-4022	143	13	for	for	SCONJ
cana-4022	143	14	data	datum	NOUN
cana-4022	143	15	with	with	ADP
cana-4022	143	16	‘	'	PUNCT
cana-4022	143	17	‘	'	PUNCT
cana-4022	143	18	high	high	ADJ
cana-4022	143	19	dimensionality	dimensionality	NOUN
cana-4022	143	20	’’	’'	PUNCT
cana-4022	143	21	,	,	PUNCT
cana-4022	143	22	decision	decision	NOUN
cana-4022	143	23	tree	tree	NOUN
cana-4022	143	24	or	or	CCONJ
cana-4022	143	25	decision	decision	NOUN
cana-4022	143	26	making	make	VERB
cana-4022	143	27	tree	tree	NOUN
cana-4022	143	28	is	be	AUX
cana-4022	143	29	used	use	VERB
cana-4022	143	30	,	,	PUNCT
cana-4022	143	31	whereas	whereas	SCONJ
cana-4022	143	32	in	in	ADP
cana-4022	143	33	data	datum	NOUN
cana-4022	143	34	with	with	ADP
cana-4022	143	35	high	high	ADJ
cana-4022	143	36	and	and	CCONJ
cana-4022	143	37	categorical	categorical	ADJ
cana-4022	143	38	data	datum	NOUN
cana-4022	143	39	,	,	PUNCT
cana-4022	143	40	svm	svm	PROPN
cana-4022	143	41	is	be	AUX
cana-4022	143	42	used	use	VERB
cana-4022	143	43	.	.	PUNCT
cana-4022	144	1	if	if	SCONJ
cana-4022	144	2	the	the	DET
cana-4022	144	3	dataset	dataset	NOUN
cana-4022	144	4	does	do	AUX
cana-4022	144	5	not	not	PART
cana-4022	144	6	contain	contain	VERB
cana-4022	144	7	a	a	DET
cana-4022	144	8	clear	clear	ADJ
cana-4022	144	9	target	target	NOUN
cana-4022	144	10	variable	variable	NOUN
cana-4022	144	11	then	then	ADV
cana-4022	144	12	it	it	PRON
cana-4022	144	13	is	be	AUX
cana-4022	144	14	better	well	ADJ
cana-4022	144	15	to	to	PART
cana-4022	144	16	use	use	VERB
cana-4022	144	17	unsupervised	unsupervised	ADJ
cana-4022	144	18	models	model	NOUN
cana-4022	144	19	such	such	ADJ
cana-4022	144	20	as	as	ADP
cana-4022	144	21	clustering	cluster	VERB
cana-4022	144	22	with	with	ADP
cana-4022	144	23	k	k	NOUN
cana-4022	144	24	-	-	PUNCT
cana-4022	144	25	means	mean	NOUN
cana-4022	144	26	or	or	CCONJ
cana-4022	144	27	for	for	ADP
cana-4022	144	28	feature	feature	NOUN
cana-4022	144	29	reduction	reduction	NOUN
cana-4022	144	30	autoencoders	autoencoder	NOUN
cana-4022	144	31	.	.	PUNCT
cana-4022	145	1	this	this	DET
cana-4022	145	2	process	process	NOUN
cana-4022	145	3	makes	make	VERB
cana-4022	145	4	a	a	DET
cana-4022	145	5	selected	select	VERB
cana-4022	145	6	model	model	NOUN
cana-4022	145	7	to	to	PART
cana-4022	145	8	follow	follow	VERB
cana-4022	145	9	the	the	DET
cana-4022	145	10	cycle	cycle	NOUN
cana-4022	145	11	of	of	ADP
cana-4022	145	12	deployment	deployment	NOUN
cana-4022	145	13	,	,	PUNCT
cana-4022	145	14	optimization	optimization	NOUN
cana-4022	145	15	and	and	CCONJ
cana-4022	145	16	statistical	statistical	ADJ
cana-4022	145	17	validation	validation	NOUN
cana-4022	145	18	of	of	ADP
cana-4022	145	19	a	a	DET
cana-4022	145	20	model	model	NOUN
cana-4022	145	21	that	that	PRON
cana-4022	145	22	has	have	AUX
cana-4022	145	23	been	be	AUX
cana-4022	145	24	deemed	deem	VERB
cana-4022	145	25	to	to	PART
cana-4022	145	26	be	be	AUX
cana-4022	145	27	giving	give	VERB
cana-4022	145	28	the	the	DET
cana-4022	145	29	optimal	optimal	ADJ
cana-4022	145	30	results	result	NOUN
cana-4022	145	31	.	.	PUNCT
cana-4022	146	1	moreover	moreover	ADV
cana-4022	146	2	,	,	PUNCT
cana-4022	146	3	the	the	DET
cana-4022	146	4	correlation	correlation	NOUN
cana-4022	146	5	analysis	analysis	NOUN
cana-4022	146	6	of	of	ADP
cana-4022	146	7	the	the	DET
cana-4022	146	8	results	result	NOUN
cana-4022	146	9	also	also	ADV
cana-4022	146	10	showed	show	VERB
cana-4022	146	11	that	that	SCONJ
cana-4022	146	12	with	with	ADP
cana-4022	146	13	the	the	DET
cana-4022	146	14	increase	increase	NOUN
cana-4022	146	15	in	in	ADP
cana-4022	146	16	data	datum	NOUN
cana-4022	146	17	complexity	complexity	NOUN
cana-4022	146	18	,	,	PUNCT
cana-4022	146	19	the	the	DET
cana-4022	146	20	performance	performance	NOUN
cana-4022	146	21	of	of	ADP
cana-4022	146	22	both	both	CCONJ
cana-4022	146	23	the	the	DET
cana-4022	146	24	paradigms	paradigm	NOUN
cana-4022	146	25	have	have	VERB
cana-4022	146	26	decay	decay	NOUN
cana-4022	146	27	which	which	PRON
cana-4022	146	28	confirms	confirm	VERB
cana-4022	146	29	that	that	SCONJ
cana-4022	146	30	the	the	DET
cana-4022	146	31	characteristics	characteristic	NOUN
cana-4022	146	32	of	of	ADP
cana-4022	146	33	dataset	dataset	NOUN
cana-4022	146	34	matter	matter	NOUN
cana-4022	146	35	in	in	ADP
cana-4022	146	36	selecting	select	VERB
cana-4022	146	37	machine	machine	NOUN
cana-4022	146	38	learning	learning	NOUN
cana-4022	146	39	paradigm	paradigm	NOUN
cana-4022	146	40	properly	properly	ADV
cana-4022	146	41	.	.	PUNCT
cana-4022	147	1	these	these	DET
cana-4022	147	2	insights	insight	NOUN
cana-4022	147	3	consist	consist	VERB
cana-4022	147	4	of	of	ADP
cana-4022	147	5	a	a	DET
cana-4022	147	6	decision	decision	NOUN
cana-4022	147	7	model	model	NOUN
cana-4022	147	8	for	for	ADP
cana-4022	147	9	how	how	SCONJ
cana-4022	147	10	to	to	PART
cana-4022	147	11	approach	approach	VERB
cana-4022	147	12	certain	certain	ADJ
cana-4022	147	13	tasks	task	NOUN
cana-4022	147	14	and	and	CCONJ
cana-4022	147	15	decide	decide	VERB
cana-4022	147	16	on	on	ADP
cana-4022	147	17	the	the	DET
cana-4022	147	18	type	type	NOUN
cana-4022	147	19	of	of	ADP
cana-4022	147	20	ml	ml	NOUN
cana-4022	147	21	model	model	NOUN
cana-4022	147	22	to	to	PART
cana-4022	147	23	use	use	VERB
cana-4022	147	24	given	give	VERB
cana-4022	147	25	the	the	DET
cana-4022	147	26	nature	nature	NOUN
cana-4022	147	27	of	of	ADP
cana-4022	147	28	the	the	DET
cana-4022	147	29	data	datum	NOUN
cana-4022	147	30	.	.	PUNCT
cana-4022	148	1	10	10	NUM
cana-4022	148	2	.	.	X
cana-4022	149	1	limitation	limitation	NOUN
cana-4022	149	2	of	of	ADP
cana-4022	149	3	the	the	DET
cana-4022	149	4	study	study	NOUN
cana-4022	149	5	the	the	DET
cana-4022	149	6	limitation	limitation	NOUN
cana-4022	149	7	of	of	ADP
cana-4022	149	8	this	this	DET
cana-4022	149	9	study	study	NOUN
cana-4022	149	10	is	be	AUX
cana-4022	149	11	that	that	SCONJ
cana-4022	149	12	only	only	ADV
cana-4022	149	13	five	five	NUM
cana-4022	149	14	machine	machine	NOUN
cana-4022	149	15	learning	learning	NOUN
cana-4022	149	16	models	model	NOUN
cana-4022	149	17	have	have	AUX
cana-4022	149	18	been	be	AUX
cana-4022	149	19	investigated	investigate	VERB
cana-4022	149	20	and	and	CCONJ
cana-4022	149	21	presented	present	VERB
cana-4022	149	22	in	in	ADP
cana-4022	149	23	this	this	DET
cana-4022	149	24	paper	paper	NOUN
cana-4022	149	25	.	.	PUNCT
cana-4022	150	1	even	even	ADV
cana-4022	150	2	though	though	SCONJ
cana-4022	150	3	four	four	NUM
cana-4022	150	4	different	different	ADJ
cana-4022	150	5	algorithms	algorithm	NOUN
cana-4022	150	6	were	be	AUX
cana-4022	150	7	selected	select	VERB
cana-4022	150	8	to	to	PART
cana-4022	150	9	represent	represent	VERB
cana-4022	150	10	each	each	DET
cana-4022	150	11	learning	learning	NOUN
cana-4022	150	12	paradigm	paradigm	NOUN
cana-4022	150	13	,	,	PUNCT
cana-4022	150	14	it	it	PRON
cana-4022	150	15	would	would	AUX
cana-4022	150	16	be	be	AUX
cana-4022	150	17	beneficial	beneficial	ADJ
cana-4022	150	18	to	to	PART
cana-4022	150	19	consider	consider	VERB
cana-4022	150	20	such	such	ADJ
cana-4022	150	21	algorithms	algorithm	NOUN
cana-4022	150	22	as	as	ADP
cana-4022	150	23	deep	deep	ADJ
cana-4022	150	24	neural	neural	ADJ
cana-4022	150	25	networks	network	NOUN
cana-4022	150	26	as	as	ADV
cana-4022	150	27	well	well	ADV
cana-4022	150	28	as	as	ADP
cana-4022	150	29	hierarchical	hierarchical	ADJ
cana-4022	150	30	clustering	clustering	NOUN
cana-4022	150	31	in	in	ADP
cana-4022	150	32	the	the	DET
cana-4022	150	33	evaluation	evaluation	NOUN
cana-4022	150	34	process	process	NOUN
cana-4022	150	35	.	.	PUNCT
cana-4022	151	1	moreover	moreover	ADV
cana-4022	151	2	,	,	PUNCT
cana-4022	151	3	the	the	DET
cana-4022	151	4	datasets	dataset	NOUN
cana-4022	151	5	applied	apply	VERB
cana-4022	151	6	in	in	ADP
cana-4022	151	7	this	this	DET
cana-4022	151	8	work	work	NOUN
cana-4022	151	9	are	be	AUX
cana-4022	151	10	rather	rather	ADV
cana-4022	151	11	different	different	ADJ
cana-4022	152	1	but	but	CCONJ
cana-4022	152	2	they	they	PRON
cana-4022	152	3	are	be	AUX
cana-4022	152	4	not	not	PART
cana-4022	152	5	all	all	DET
cana-4022	152	6	the	the	DET
cana-4022	152	7	possible	possible	ADJ
cana-4022	152	8	cases	case	NOUN
cana-4022	152	9	which	which	PRON
cana-4022	152	10	can	can	AUX
cana-4022	152	11	occur	occur	VERB
cana-4022	152	12	in	in	ADP
cana-4022	152	13	real	real	ADJ
cana-4022	152	14	-	-	PUNCT
cana-4022	152	15	world	world	NOUN
cana-4022	152	16	cases	case	NOUN
cana-4022	152	17	,	,	PUNCT
cana-4022	152	18	thus	thus	ADV
cana-4022	152	19	the	the	DET
cana-4022	152	20	results	result	NOUN
cana-4022	152	21	achieved	achieve	VERB
cana-4022	152	22	can	can	AUX
cana-4022	152	23	hardly	hardly	ADV
cana-4022	152	24	be	be	AUX
cana-4022	152	25	applied	apply	VERB
cana-4022	152	26	in	in	ADP
cana-4022	152	27	many	many	ADJ
cana-4022	152	28	fields	field	NOUN
cana-4022	152	29	.	.	PUNCT
cana-4022	153	1	some	some	DET
cana-4022	153	2	constraints	constraint	NOUN
cana-4022	153	3	that	that	PRON
cana-4022	153	4	are	be	AUX
cana-4022	153	5	related	relate	VERB
cana-4022	153	6	to	to	ADP
cana-4022	153	7	the	the	DET
cana-4022	153	8	computational	computational	ADJ
cana-4022	153	9	aspect	aspect	NOUN
cana-4022	153	10	also	also	ADV
cana-4022	153	11	shaped	shape	VERB
cana-4022	153	12	the	the	DET
cana-4022	153	13	choice	choice	NOUN
cana-4022	153	14	of	of	ADP
cana-4022	153	15	hyperparameter	hyperparameter	NOUN
cana-4022	153	16	,	,	PUNCT
cana-4022	153	17	which	which	PRON
cana-4022	153	18	might	might	AUX
cana-4022	153	19	affect	affect	VERB
cana-4022	153	20	the	the	DET
cana-4022	153	21	models	model	NOUN
cana-4022	153	22	’	'	PUNCT
cana-4022	153	23	optimization	optimization	NOUN
cana-4022	153	24	.	.	PUNCT
cana-4022	154	1	11	11	NUM
cana-4022	154	2	.	.	X
cana-4022	155	1	implication	implication	NOUN
cana-4022	155	2	of	of	ADP
cana-4022	155	3	the	the	DET
cana-4022	155	4	study	study	NOUN
cana-4022	155	5	the	the	DET
cana-4022	155	6	findings	finding	NOUN
cana-4022	155	7	of	of	ADP
cana-4022	155	8	this	this	DET
cana-4022	155	9	study	study	NOUN
cana-4022	155	10	have	have	VERB
cana-4022	155	11	potential	potential	ADJ
cana-4022	155	12	value	value	NOUN
cana-4022	155	13	in	in	ADP
cana-4022	155	14	practice	practice	NOUN
cana-4022	155	15	for	for	ADP
cana-4022	155	16	artificial	artificial	ADJ
cana-4022	155	17	intelligence	intelligence	NOUN
cana-4022	155	18	experts	expert	NOUN
cana-4022	155	19	,	,	PUNCT
cana-4022	155	20	data	datum	NOUN
cana-4022	155	21	scientists	scientist	NOUN
cana-4022	155	22	,	,	PUNCT
cana-4022	155	23	and	and	CCONJ
cana-4022	155	24	researchers	researcher	NOUN
cana-4022	155	25	who	who	PRON
cana-4022	155	26	are	be	AUX
cana-4022	155	27	in	in	ADP
cana-4022	155	28	the	the	DET
cana-4022	155	29	process	process	NOUN
cana-4022	155	30	of	of	ADP
cana-4022	155	31	selecting	selecting	NOUN
cana-4022	155	32	models	model	NOUN
cana-4022	155	33	for	for	ADP
cana-4022	155	34	specific	specific	ADJ
cana-4022	155	35	purposes	purpose	NOUN
cana-4022	155	36	.	.	PUNCT
cana-4022	156	1	the	the	DET
cana-4022	156	2	studies	study	NOUN
cana-4022	156	3	also	also	ADV
cana-4022	156	4	highlight	highlight	VERB
cana-4022	156	5	the	the	DET
cana-4022	156	6	importance	importance	NOUN
cana-4022	156	7	of	of	ADP
cana-4022	156	8	supervised	supervised	ADJ
cana-4022	156	9	learning	learning	NOUN
cana-4022	156	10	in	in	ADP
cana-4022	156	11	accurate	accurate	ADJ
cana-4022	156	12	classification	classification	NOUN
cana-4022	156	13	tasks	task	NOUN
cana-4022	156	14	,	,	PUNCT
cana-4022	156	15	while	while	SCONJ
cana-4022	156	16	,	,	PUNCT
cana-4022	156	17	on	on	ADP
cana-4022	156	18	the	the	DET
cana-4022	156	19	other	other	ADJ
cana-4022	156	20	hand	hand	NOUN
cana-4022	156	21	,	,	PUNCT
cana-4022	156	22	unsupervised	unsupervised	ADJ
cana-4022	156	23	learning	learning	NOUN
cana-4022	156	24	prove	prove	VERB
cana-4022	156	25	useful	useful	ADJ
cana-4022	156	26	in	in	ADP
cana-4022	156	27	initial	initial	ADJ
cana-4022	156	28	inspection	inspection	NOUN
cana-4022	156	29	of	of	ADP
cana-4022	156	30	data	datum	NOUN
cana-4022	156	31	,	,	PUNCT
cana-4022	156	32	in	in	ADP
cana-4022	156	33	particular	particular	ADJ
cana-4022	156	34	in	in	ADP
cana-4022	156	35	case	case	NOUN
cana-4022	156	36	of	of	ADP
cana-4022	156	37	identifying	identify	VERB
cana-4022	156	38	anomalies	anomaly	NOUN
cana-4022	156	39	.	.	PUNCT
cana-4022	157	1	in	in	ADP
cana-4022	157	2	addition	addition	NOUN
cana-4022	157	3	,	,	PUNCT
cana-4022	157	4	the	the	DET
cana-4022	157	5	incorporation	incorporation	NOUN
cana-4022	157	6	of	of	ADP
cana-4022	157	7	statistical	statistical	ADJ
cana-4022	157	8	validation	validation	NOUN
cana-4022	157	9	in	in	ADP
cana-4022	157	10	the	the	DET
cana-4022	157	11	model	model	NOUN
cana-4022	157	12	yields	yield	VERB
cana-4022	157	13	a	a	DET
cana-4022	157	14	reliable	reliable	ADJ
cana-4022	157	15	approach	approach	NOUN
cana-4022	157	16	to	to	ADP
cana-4022	157	17	the	the	DET
cana-4022	157	18	evaluation	evaluation	NOUN
cana-4022	157	19	of	of	ADP
cana-4022	157	20	learning	learning	NOUN
cana-4022	157	21	paradigms	paradigm	NOUN
cana-4022	157	22	.	.	PUNCT
cana-4022	158	1	also	also	ADV
cana-4022	158	2	,	,	PUNCT
cana-4022	158	3	this	this	DET
cana-4022	158	4	study	study	NOUN
cana-4022	158	5	will	will	AUX
cana-4022	158	6	help	help	VERB
cana-4022	158	7	the	the	DET
cana-4022	158	8	industry	industry	NOUN
cana-4022	158	9	players	player	NOUN
cana-4022	158	10	to	to	PART
cana-4022	158	11	be	be	AUX
cana-4022	158	12	able	able	ADJ
cana-4022	158	13	to	to	PART
cana-4022	158	14	get	get	VERB
cana-4022	158	15	better	well	ADJ
cana-4022	158	16	insights	insight	NOUN
cana-4022	158	17	and	and	CCONJ
cana-4022	158	18	make	make	VERB
cana-4022	158	19	informed	informed	ADJ
cana-4022	158	20	decisions	decision	NOUN
cana-4022	158	21	while	while	SCONJ
cana-4022	158	22	conducting	conduct	VERB
cana-4022	158	23	the	the	DET
cana-4022	158	24	implementation	implementation	NOUN
cana-4022	158	25	of	of	ADP
cana-4022	158	26	these	these	DET
cana-4022	158	27	machine	machine	NOUN
cana-4022	158	28	learning	learning	NOUN
cana-4022	158	29	models	model	NOUN
cana-4022	158	30	in	in	ADP
cana-4022	158	31	areas	area	NOUN
cana-4022	158	32	such	such	ADJ
cana-4022	158	33	as	as	ADP
cana-4022	158	34	healthcare	healthcare	NOUN
cana-4022	158	35	,	,	PUNCT
cana-4022	158	36	financial	financial	ADJ
cana-4022	158	37	sectors	sector	NOUN
cana-4022	158	38	as	as	ADV
cana-4022	158	39	well	well	ADV
cana-4022	158	40	as	as	ADP
cana-4022	158	41	image	image	NOUN
cana-4022	158	42	recognition	recognition	NOUN
cana-4022	158	43	.	.	PUNCT
cana-4022	159	1	12	12	NUM
cana-4022	159	2	.	.	PUNCT
cana-4022	160	1	future	future	ADJ
cana-4022	160	2	recommendation	recommendation	NOUN
cana-4022	160	3	for	for	ADP
cana-4022	160	4	more	more	ADJ
cana-4022	160	5	and	and	CCONJ
cana-4022	160	6	improved	improved	ADJ
cana-4022	160	7	researches	research	NOUN
cana-4022	160	8	on	on	ADP
cana-4022	160	9	this	this	DET
cana-4022	160	10	comparative	comparative	ADJ
cana-4022	160	11	analysis	analysis	NOUN
cana-4022	160	12	,	,	PUNCT
cana-4022	160	13	more	more	ADV
cana-4022	160	14	improved	improved	ADJ
cana-4022	160	15	supervised	supervised	ADJ
cana-4022	160	16	and	and	CCONJ
cana-4022	160	17	unsupervised	unsupervised	ADJ
cana-4022	160	18	models	model	NOUN
cana-4022	160	19	depending	depend	VERB
cana-4022	160	20	on	on	ADP
cana-4022	160	21	the	the	DET
cana-4022	160	22	deep	deep	ADJ
cana-4022	160	23	learning	learning	NOUN
cana-4022	160	24	techniques	technique	NOUN
cana-4022	160	25	should	should	AUX
cana-4022	160	26	be	be	AUX
cana-4022	160	27	included	include	VERB
cana-4022	160	28	.	.	PUNCT
cana-4022	161	1	researching	research	VERB
cana-4022	161	2	the	the	DET
cana-4022	161	3	possibilities	possibility	NOUN
cana-4022	161	4	of	of	ADP
cana-4022	161	5	using	use	VERB
cana-4022	161	6	both	both	CCONJ
cana-4022	161	7	supervised	supervised	ADJ
cana-4022	161	8	and	and	CCONJ
cana-4022	161	9	unsupervised	unsupervised	ADJ
cana-4022	161	10	training	training	NOUN
cana-4022	161	11	may	may	AUX
cana-4022	161	12	provide	provide	VERB
cana-4022	161	13	greater	great	ADJ
cana-4022	161	14	understanding	understanding	NOUN
cana-4022	161	15	in	in	ADP
cana-4022	161	16	enhancing	enhance	VERB
cana-4022	161	17	the	the	DET
cana-4022	161	18	general	general	ADJ
cana-4022	161	19	use	use	NOUN
cana-4022	161	20	of	of	ADP
cana-4022	161	21	models	model	NOUN
cana-4022	161	22	.	.	PUNCT
cana-4022	162	1	in	in	ADP
cana-4022	162	2	addition	addition	NOUN
cana-4022	162	3	,	,	PUNCT
cana-4022	162	4	expanding	expand	VERB
cana-4022	162	5	model	model	NOUN
cana-4022	162	6	performance	performance	NOUN
cana-4022	162	7	evaluations	evaluation	NOUN
cana-4022	162	8	to	to	PART
cana-4022	162	9	include	include	VERB
cana-4022	162	10	even	even	ADV
cana-4022	162	11	more	more	ADV
cana-4022	162	12	significant	significant	ADJ
cana-4022	162	13	and	and	CCONJ
cana-4022	162	14	elaborate	elaborate	ADJ
cana-4022	162	15	databases	database	NOUN
cana-4022	162	16	and	and	CCONJ
cana-4022	162	17	test	test	NOUN
cana-4022	162	18	results	result	NOUN
cana-4022	162	19	obtained	obtain	VERB
cana-4022	162	20	with	with	ADP
cana-4022	162	21	increased	increase	VERB
cana-4022	162	22	noise	noise	NOUN
cana-4022	162	23	would	would	AUX
cana-4022	162	24	increase	increase	VERB
cana-4022	162	25	the	the	DET
cana-4022	162	26	likelihood	likelihood	NOUN
cana-4022	162	27	of	of	ADP
cana-4022	162	28	use	use	NOUN
cana-4022	162	29	for	for	ADP
cana-4022	162	30	the	the	DET
cana-4022	162	31	results	result	NOUN
cana-4022	162	32	obtained	obtain	VERB
cana-4022	162	33	.	.	PUNCT
cana-4022	163	1	last	last	ADJ
cana-4022	163	2	but	but	CCONJ
cana-4022	163	3	not	not	PART
cana-4022	163	4	least	least	ADJ
cana-4022	163	5	,	,	PUNCT
cana-4022	163	6	having	have	VERB
cana-4022	163	7	the	the	DET
cana-4022	163	8	actual	actual	ADJ
cana-4022	163	9	learning	learning	NOUN
cana-4022	163	10	communications	communication	NOUN
cana-4022	163	11	on	on	ADP
cana-4022	163	12	applied	apply	VERB
cana-4022	163	13	nonlinear	nonlinear	ADJ
cana-4022	163	14	analysis	analysis	NOUN
cana-4022	163	15	issn	issn	NOUN
cana-4022	163	16	:	:	PUNCT
cana-4022	163	17	1074	1074	NUM
cana-4022	163	18	-	-	PUNCT
cana-4022	163	19	133x	133x	NUM
cana-4022	163	20	vol	vol	NOUN
cana-4022	163	21	32	32	NUM
cana-4022	163	22	no	no	NOUN
cana-4022	163	23	.	.	PUNCT
cana-4022	164	1	9s	9s	NUM
cana-4022	164	2	(	(	PUNCT
cana-4022	164	3	2025	2025	NUM
cana-4022	164	4	)	)	PUNCT
cana-4022	164	5	871	871	NUM
cana-4022	164	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-4022	164	7	environments	environment	NOUN
cana-4022	164	8	and	and	CCONJ
cana-4022	164	9	adaptive	adaptive	ADJ
cana-4022	164	10	models	model	NOUN
cana-4022	164	11	could	could	AUX
cana-4022	164	12	give	give	VERB
cana-4022	164	13	a	a	DET
cana-4022	164	14	clearer	clear	ADJ
cana-4022	164	15	insight	insight	NOUN
cana-4022	164	16	into	into	ADP
cana-4022	164	17	how	how	SCONJ
cana-4022	164	18	these	these	DET
cana-4022	164	19	paradigms	paradigm	NOUN
cana-4022	164	20	behave	behave	VERB
cana-4022	164	21	in	in	ADP
cana-4022	164	22	dynamic	dynamic	ADJ
cana-4022	164	23	and	and	CCONJ
cana-4022	164	24	unsteady	unsteady	ADJ
cana-4022	164	25	data	datum	NOUN
cana-4022	164	26	cases	case	NOUN
cana-4022	164	27	.	.	PUNCT
cana-4022	165	1	references	reference	NOUN
cana-4022	165	2	[	[	X
cana-4022	165	3	1	1	NUM
cana-4022	165	4	]	]	X
cana-4022	165	5	burkov	burkov	PROPN
cana-4022	165	6	,	,	PUNCT
cana-4022	165	7	a.	a.	NOUN
cana-4022	165	8	(	(	PUNCT
cana-4022	165	9	2025	2025	NUM
cana-4022	165	10	)	)	PUNCT
cana-4022	165	11	.	.	PUNCT
cana-4022	166	1	the	the	DET
cana-4022	166	2	hundred	hundred	NUM
cana-4022	166	3	-	-	PUNCT
cana-4022	166	4	page	page	NOUN
cana-4022	166	5	machine	machine	NOUN
cana-4022	166	6	learning	learning	NOUN
cana-4022	166	7	book	book	NOUN
cana-4022	166	8	.	.	PUNCT
cana-4022	167	1	andriy	andriy	PROPN
cana-4022	167	2	burkov	burkov	PROPN
cana-4022	167	3	.	.	PUNCT
cana-4022	168	1	[	[	X
cana-4022	168	2	2	2	NUM
cana-4022	168	3	]	]	X
cana-4022	168	4	geron	geron	X
cana-4022	168	5	,	,	PUNCT
cana-4022	168	6	a.	a.	NOUN
cana-4022	168	7	(	(	PUNCT
cana-4022	168	8	2025	2025	NUM
cana-4022	168	9	)	)	PUNCT
cana-4022	168	10	.	.	PUNCT
cana-4022	169	1	hands	hand	NOUN
cana-4022	169	2	-	-	PUNCT
cana-4022	169	3	on	on	ADP
cana-4022	169	4	machine	machine	NOUN
cana-4022	169	5	learning	learn	VERB
cana-4022	169	6	with	with	ADP
cana-4022	169	7	scikit	scikit	NOUN
cana-4022	169	8	-	-	PUNCT
cana-4022	169	9	learn	learn	PROPN
cana-4022	169	10	,	,	PUNCT
cana-4022	169	11	keras	keras	PROPN
cana-4022	169	12	,	,	PUNCT
cana-4022	169	13	and	and	CCONJ
cana-4022	169	14	tensorflow	tensorflow	NOUN
cana-4022	169	15	.	.	PUNCT
cana-4022	170	1	o'reilly	o'reilly	NOUN
cana-4022	170	2	media	medium	NOUN
cana-4022	170	3	.	.	PUNCT
cana-4022	171	1	[	[	X
cana-4022	171	2	3	3	NUM
cana-4022	171	3	]	]	X
cana-4022	171	4	sathya	sathya	PROPN
cana-4022	171	5	,	,	PUNCT
cana-4022	171	6	r.	r.	PROPN
cana-4022	171	7	,	,	PUNCT
cana-4022	171	8	&	&	CCONJ
cana-4022	171	9	abraham	abraham	PROPN
cana-4022	171	10	,	,	PUNCT
cana-4022	171	11	a.	a.	PROPN
cana-4022	171	12	(	(	PUNCT
cana-4022	171	13	2013	2013	NUM
cana-4022	171	14	)	)	PUNCT
cana-4022	171	15	.	.	PUNCT
cana-4022	172	1	comparison	comparison	NOUN
cana-4022	172	2	of	of	ADP
cana-4022	172	3	supervised	supervised	ADJ
cana-4022	172	4	and	and	CCONJ
cana-4022	172	5	unsupervised	unsupervised	ADJ
cana-4022	172	6	learning	learning	NOUN
cana-4022	172	7	algorithms	algorithm	NOUN
cana-4022	172	8	for	for	ADP
cana-4022	172	9	pattern	pattern	NOUN
cana-4022	172	10	classification	classification	NOUN
cana-4022	172	11	.	.	PUNCT
cana-4022	173	1	international	international	ADJ
cana-4022	173	2	journal	journal	NOUN
cana-4022	173	3	of	of	ADP
cana-4022	173	4	advanced	advanced	ADJ
cana-4022	173	5	research	research	NOUN
cana-4022	173	6	in	in	ADP
cana-4022	173	7	artificial	artificial	ADJ
cana-4022	173	8	intelligence	intelligence	NOUN
cana-4022	173	9	,	,	PUNCT
cana-4022	173	10	2(2	2(2	NUM
cana-4022	173	11	)	)	PUNCT
cana-4022	173	12	,	,	PUNCT
cana-4022	173	13	34	34	NUM
cana-4022	173	14	-	-	SYM
cana-4022	173	15	38	38	NUM
cana-4022	173	16	.	.	PUNCT
cana-4022	174	1	[	[	X
cana-4022	174	2	4	4	NUM
cana-4022	174	3	]	]	X
cana-4022	174	4	yao	yao	NOUN
cana-4022	174	5	,	,	PUNCT
cana-4022	174	6	t.	t.	PROPN
cana-4022	174	7	,	,	PUNCT
cana-4022	174	8	zhang	zhang	PROPN
cana-4022	174	9	,	,	PUNCT
cana-4022	174	10	y.	y.	PROPN
cana-4022	174	11	,	,	PUNCT
cana-4022	174	12	qiu	qiu	PROPN
cana-4022	174	13	,	,	PUNCT
cana-4022	174	14	z.	z.	PROPN
cana-4022	174	15	,	,	PUNCT
cana-4022	174	16	pan	pan	PROPN
cana-4022	174	17	,	,	PUNCT
cana-4022	174	18	y.	y.	PROPN
cana-4022	174	19	,	,	PUNCT
cana-4022	174	20	&	&	CCONJ
cana-4022	174	21	mei	mei	PROPN
cana-4022	174	22	,	,	PUNCT
cana-4022	174	23	t.	t.	PROPN
cana-4022	174	24	(	(	PUNCT
cana-4022	174	25	2021	2021	NUM
cana-4022	174	26	)	)	PUNCT
cana-4022	174	27	.	.	PUNCT
cana-4022	175	1	seco	seco	PROPN
cana-4022	175	2	:	:	PUNCT
cana-4022	175	3	exploring	explore	VERB
cana-4022	175	4	sequence	sequence	NOUN
cana-4022	175	5	supervision	supervision	NOUN
cana-4022	175	6	for	for	ADP
cana-4022	175	7	unsupervised	unsupervised	ADJ
cana-4022	175	8	representation	representation	NOUN
cana-4022	175	9	learning	learning	NOUN
cana-4022	175	10	.	.	PUNCT
cana-4022	176	1	proceedings	proceeding	NOUN
cana-4022	176	2	of	of	ADP
cana-4022	176	3	the	the	DET
cana-4022	176	4	aaai	aaai	PROPN
cana-4022	176	5	conference	conference	NOUN
cana-4022	176	6	on	on	ADP
cana-4022	176	7	artificial	artificial	ADJ
cana-4022	176	8	intelligence	intelligence	NOUN
cana-4022	176	9	,	,	PUNCT
cana-4022	176	10	35(12	35(12	NUM
cana-4022	176	11	)	)	PUNCT
cana-4022	176	12	,	,	PUNCT
cana-4022	176	13	10656	10656	NUM
cana-4022	176	14	-	-	SYM
cana-4022	176	15	10664	10664	NUM
cana-4022	176	16	.	.	PUNCT
cana-4022	177	1	[	[	X
cana-4022	177	2	5	5	NUM
cana-4022	177	3	]	]	X
cana-4022	177	4	zhang	zhang	PROPN
cana-4022	177	5	,	,	PUNCT
cana-4022	177	6	y.	y.	PROPN
cana-4022	177	7	,	,	PUNCT
cana-4022	177	8	qiu	qiu	PROPN
cana-4022	177	9	,	,	PUNCT
cana-4022	177	10	z.	z.	PROPN
cana-4022	177	11	,	,	PUNCT
cana-4022	177	12	yao	yao	PROPN
cana-4022	177	13	,	,	PUNCT
cana-4022	177	14	t.	t.	PROPN
cana-4022	177	15	,	,	PUNCT
cana-4022	177	16	liu	liu	PROPN
cana-4022	177	17	,	,	PUNCT
cana-4022	177	18	d.	d.	PROPN
cana-4022	177	19	,	,	PUNCT
cana-4022	177	20	&	&	CCONJ
cana-4022	177	21	mei	mei	PROPN
cana-4022	177	22	,	,	PUNCT
cana-4022	177	23	t.	t.	PROPN
cana-4022	177	24	(	(	PUNCT
cana-4022	177	25	2021	2021	NUM
cana-4022	177	26	)	)	PUNCT
cana-4022	177	27	.	.	PUNCT
cana-4022	177	28	fully	fully	ADV
cana-4022	177	29	convolutional	convolutional	ADJ
cana-4022	177	30	adaptation	adaptation	NOUN
cana-4022	177	31	networks	network	NOUN
cana-4022	177	32	for	for	ADP
cana-4022	177	33	semantic	semantic	ADJ
cana-4022	177	34	segmentation	segmentation	NOUN
cana-4022	177	35	.	.	PUNCT
cana-4022	178	1	ieee	ieee	NOUN
cana-4022	178	2	transactions	transaction	NOUN
cana-4022	178	3	on	on	ADP
cana-4022	178	4	pattern	pattern	NOUN
cana-4022	178	5	analysis	analysis	NOUN
cana-4022	178	6	and	and	CCONJ
cana-4022	178	7	machine	machine	NOUN
cana-4022	178	8	intelligence	intelligence	NOUN
cana-4022	178	9	,	,	PUNCT
cana-4022	178	10	43(11	43(11	NUM
cana-4022	178	11	)	)	PUNCT
cana-4022	178	12	,	,	PUNCT
cana-4022	178	13	3900	3900	NUM
cana-4022	178	14	-	-	SYM
cana-4022	178	15	3913	3913	NUM
cana-4022	178	16	.	.	PUNCT
cana-4022	179	1	[	[	X
cana-4022	179	2	6	6	NUM
cana-4022	179	3	]	]	X
cana-4022	179	4	geron	geron	X
cana-4022	179	5	,	,	PUNCT
cana-4022	179	6	a.	a.	NOUN
cana-4022	179	7	(	(	PUNCT
cana-4022	179	8	2025	2025	NUM
cana-4022	179	9	)	)	PUNCT
cana-4022	179	10	.	.	PUNCT
cana-4022	179	11	hands	hand	NOUN
cana-4022	179	12	-	-	PUNCT
cana-4022	179	13	on	on	ADP
cana-4022	179	14	machine	machine	NOUN
cana-4022	179	15	learning	learn	VERB
cana-4022	179	16	with	with	ADP
cana-4022	179	17	scikit	scikit	NOUN
cana-4022	179	18	-	-	PUNCT
cana-4022	179	19	learn	learn	PROPN
cana-4022	179	20	,	,	PUNCT
cana-4022	179	21	keras	keras	PROPN
cana-4022	179	22	,	,	PUNCT
cana-4022	179	23	and	and	CCONJ
cana-4022	179	24	tensorflow	tensorflow	NOUN
cana-4022	179	25	.	.	PUNCT
cana-4022	180	1	o'reilly	o'reilly	NOUN
cana-4022	180	2	media	medium	NOUN
cana-4022	180	3	.	.	PUNCT
cana-4022	181	1	[	[	X
cana-4022	181	2	7	7	NUM
cana-4022	181	3	]	]	X
cana-4022	181	4	sathya	sathya	PROPN
cana-4022	181	5	,	,	PUNCT
cana-4022	181	6	r.	r.	PROPN
cana-4022	181	7	,	,	PUNCT
cana-4022	181	8	&	&	CCONJ
cana-4022	181	9	abraham	abraham	PROPN
cana-4022	181	10	,	,	PUNCT
cana-4022	181	11	a.	a.	PROPN
cana-4022	181	12	(	(	PUNCT
cana-4022	181	13	2013	2013	NUM
cana-4022	181	14	)	)	PUNCT
cana-4022	181	15	.	.	PUNCT
cana-4022	182	1	comparison	comparison	NOUN
cana-4022	182	2	of	of	ADP
cana-4022	182	3	supervised	supervised	ADJ
cana-4022	182	4	and	and	CCONJ
cana-4022	182	5	unsupervised	unsupervised	ADJ
cana-4022	182	6	learning	learning	NOUN
cana-4022	182	7	algorithms	algorithm	NOUN
cana-4022	182	8	for	for	ADP
cana-4022	182	9	pattern	pattern	NOUN
cana-4022	182	10	classification	classification	NOUN
cana-4022	182	11	.	.	PUNCT
cana-4022	183	1	international	international	ADJ
cana-4022	183	2	journal	journal	NOUN
cana-4022	183	3	of	of	ADP
cana-4022	183	4	advanced	advanced	ADJ
cana-4022	183	5	research	research	NOUN
cana-4022	183	6	in	in	ADP
cana-4022	183	7	artificial	artificial	ADJ
cana-4022	183	8	intelligence	intelligence	NOUN
cana-4022	183	9	,	,	PUNCT
cana-4022	183	10	2(2	2(2	NUM
cana-4022	183	11	)	)	PUNCT
cana-4022	183	12	,	,	PUNCT
cana-4022	183	13	34	34	NUM
cana-4022	183	14	-	-	SYM
cana-4022	183	15	38	38	NUM
cana-4022	183	16	.	.	PUNCT
cana-4022	184	1	[	[	X
cana-4022	184	2	8	8	NUM
cana-4022	184	3	]	]	SYM
cana-4022	184	4	yao	yao	NOUN
cana-4022	184	5	,	,	PUNCT
cana-4022	184	6	t.	t.	PROPN
cana-4022	184	7	,	,	PUNCT
cana-4022	184	8	zhang	zhang	PROPN
cana-4022	184	9	,	,	PUNCT
cana-4022	184	10	y.	y.	PROPN
cana-4022	184	11	,	,	PUNCT
cana-4022	184	12	qiu	qiu	PROPN
cana-4022	184	13	,	,	PUNCT
cana-4022	184	14	z.	z.	PROPN
cana-4022	184	15	,	,	PUNCT
cana-4022	184	16	pan	pan	PROPN
cana-4022	184	17	,	,	PUNCT
cana-4022	184	18	y.	y.	PROPN
cana-4022	184	19	,	,	PUNCT
cana-4022	184	20	&	&	CCONJ
cana-4022	184	21	mei	mei	PROPN
cana-4022	184	22	,	,	PUNCT
cana-4022	184	23	t.	t.	PROPN
cana-4022	184	24	(	(	PUNCT
cana-4022	184	25	2021	2021	NUM
cana-4022	184	26	)	)	PUNCT
cana-4022	184	27	.	.	PUNCT
cana-4022	185	1	seco	seco	PROPN
cana-4022	185	2	:	:	PUNCT
cana-4022	185	3	exploring	explore	VERB
cana-4022	185	4	sequence	sequence	NOUN
cana-4022	185	5	supervision	supervision	NOUN
cana-4022	185	6	for	for	ADP
cana-4022	185	7	unsupervised	unsupervised	ADJ
cana-4022	185	8	representation	representation	NOUN
cana-4022	185	9	learning	learning	NOUN
cana-4022	185	10	.	.	PUNCT
cana-4022	186	1	proceedings	proceeding	NOUN
cana-4022	186	2	of	of	ADP
cana-4022	186	3	the	the	DET
cana-4022	186	4	aaai	aaai	PROPN
cana-4022	186	5	conference	conference	NOUN
cana-4022	186	6	on	on	ADP
cana-4022	186	7	artificial	artificial	ADJ
cana-4022	186	8	intelligence	intelligence	NOUN
cana-4022	186	9	,	,	PUNCT
cana-4022	186	10	35(12	35(12	NUM
cana-4022	186	11	)	)	PUNCT
cana-4022	186	12	,	,	PUNCT
cana-4022	186	13	10656	10656	NUM
cana-4022	186	14	-	-	SYM
cana-4022	186	15	10664	10664	NUM
cana-4022	186	16	.	.	PUNCT
cana-4022	187	1	[	[	X
cana-4022	187	2	9	9	NUM
cana-4022	187	3	]	]	X
cana-4022	187	4	zhang	zhang	PROPN
cana-4022	187	5	,	,	PUNCT
cana-4022	187	6	y.	y.	PROPN
cana-4022	187	7	,	,	PUNCT
cana-4022	187	8	qiu	qiu	PROPN
cana-4022	187	9	,	,	PUNCT
cana-4022	187	10	z.	z.	PROPN
cana-4022	187	11	,	,	PUNCT
cana-4022	187	12	yao	yao	PROPN
cana-4022	187	13	,	,	PUNCT
cana-4022	187	14	t.	t.	PROPN
cana-4022	187	15	,	,	PUNCT
cana-4022	187	16	liu	liu	PROPN
cana-4022	187	17	,	,	PUNCT
cana-4022	187	18	d.	d.	PROPN
cana-4022	187	19	,	,	PUNCT
cana-4022	187	20	&	&	CCONJ
cana-4022	187	21	mei	mei	PROPN
cana-4022	187	22	,	,	PUNCT
cana-4022	187	23	t.	t.	PROPN
cana-4022	187	24	(	(	PUNCT
cana-4022	187	25	2021	2021	NUM
cana-4022	187	26	)	)	PUNCT
cana-4022	187	27	.	.	PUNCT
cana-4022	188	1	fully	fully	ADV
cana-4022	188	2	convolutional	convolutional	ADJ
cana-4022	188	3	adaptation	adaptation	NOUN
cana-4022	188	4	networks	network	NOUN
cana-4022	188	5	for	for	ADP
cana-4022	188	6	semantic	semantic	ADJ
cana-4022	188	7	segmentation	segmentation	NOUN
cana-4022	188	8	.	.	PUNCT
cana-4022	189	1	ieee	ieee	NOUN
cana-4022	189	2	transactions	transaction	NOUN
cana-4022	189	3	on	on	ADP
cana-4022	189	4	pattern	pattern	NOUN
cana-4022	189	5	analysis	analysis	NOUN
cana-4022	189	6	and	and	CCONJ
cana-4022	189	7	machine	machine	NOUN
cana-4022	189	8	intelligence	intelligence	NOUN
cana-4022	189	9	,	,	PUNCT
cana-4022	189	10	43(11	43(11	NUM
cana-4022	189	11	)	)	PUNCT
cana-4022	189	12	,	,	PUNCT
cana-4022	189	13	3900	3900	NUM
cana-4022	189	14	-	-	SYM
cana-4022	189	15	3913	3913	NUM
cana-4022	189	16	.	.	PUNCT
cana-4022	190	1	[	[	X
cana-4022	190	2	10	10	NUM
cana-4022	190	3	]	]	X
cana-4022	190	4	ibm	ibm	PROPN
cana-4022	190	5	.	.	PUNCT
cana-4022	190	6	(	(	PUNCT
cana-4022	190	7	2024	2024	NUM
cana-4022	190	8	)	)	PUNCT
cana-4022	190	9	.	.	PUNCT
cana-4022	190	10	supervised	supervise	VERB
cana-4022	190	11	vs.	vs.	ADP
cana-4022	190	12	unsupervised	unsupervised	ADJ
cana-4022	190	13	learning	learning	NOUN
cana-4022	190	14	:	:	PUNCT
cana-4022	190	15	what	what	PRON
cana-4022	190	16	's	be	AUX
cana-4022	190	17	the	the	DET
cana-4022	190	18	difference	difference	NOUN
cana-4022	190	19	?	?	PUNCT
cana-4022	191	1	ibm	ibm	PROPN
cana-4022	191	2	think1	think1	PROPN
cana-4022	191	3	.	.	PUNCT
cana-4022	192	1	[	[	X
cana-4022	192	2	11	11	NUM
cana-4022	192	3	]	]	X
cana-4022	192	4	milligan	milligan	NOUN
cana-4022	192	5	,	,	PUNCT
cana-4022	192	6	c.	c.	PROPN
cana-4022	192	7	k.	k.	PROPN
cana-4022	192	8	(	(	PUNCT
cana-4022	192	9	2023	2023	NUM
cana-4022	192	10	)	)	PUNCT
cana-4022	192	11	.	.	PUNCT
cana-4022	193	1	a	a	DET
cana-4022	193	2	comparative	comparative	ADJ
cana-4022	193	3	analysis	analysis	NOUN
cana-4022	193	4	of	of	ADP
cana-4022	193	5	supervised	supervised	ADJ
cana-4022	193	6	and	and	CCONJ
cana-4022	193	7	unsupervised	unsupervised	ADJ
cana-4022	193	8	models	model	NOUN
cana-4022	193	9	for	for	ADP
cana-4022	193	10	detecting	detect	VERB
cana-4022	193	11	attacks	attack	NOUN
cana-4022	193	12	on	on	ADP
cana-4022	193	13	the	the	DET
cana-4022	193	14	intrusion	intrusion	NOUN
cana-4022	193	15	detection	detection	NOUN
cana-4022	193	16	systems	system	NOUN
cana-4022	193	17	.	.	PUNCT
cana-4022	194	1	information	information	NOUN
cana-4022	194	2	,	,	PUNCT
cana-4022	194	3	14(2	14(2	NUM
cana-4022	194	4	)	)	PUNCT
cana-4022	194	5	,	,	PUNCT
cana-4022	194	6	1032	1032	NUM
cana-4022	194	7	.	.	PUNCT
cana-4022	195	1	[	[	X
cana-4022	195	2	12	12	NUM
cana-4022	195	3	]	]	X
cana-4022	195	4	seldon	seldon	PROPN
cana-4022	195	5	.	.	PUNCT
cana-4022	195	6	(	(	PUNCT
cana-4022	195	7	2025	2025	NUM
cana-4022	195	8	)	)	PUNCT
cana-4022	195	9	.	.	PUNCT
cana-4022	196	1	supervised	supervise	VERB
cana-4022	196	2	vs	vs	ADP
cana-4022	196	3	unsupervised	unsupervised	ADJ
cana-4022	196	4	learning	learning	NOUN
cana-4022	196	5	explained3	explained3	NOUN
cana-4022	196	6	.	.	PUNCT
cana-4022	197	1	[	[	X
cana-4022	197	2	13	13	NUM
cana-4022	197	3	]	]	SYM
cana-4022	197	4	alpaydin	alpaydin	PROPN
cana-4022	197	5	,	,	PUNCT
cana-4022	197	6	e.	e.	PROPN
cana-4022	197	7	(	(	PUNCT
cana-4022	197	8	2024	2024	NUM
cana-4022	197	9	)	)	PUNCT
cana-4022	197	10	.	.	PUNCT
cana-4022	198	1	introduction	introduction	NOUN
cana-4022	198	2	to	to	ADP
cana-4022	198	3	machine	machine	NOUN
cana-4022	198	4	learning	learning	NOUN
cana-4022	198	5	(	(	PUNCT
cana-4022	198	6	5th	5th	ADJ
cana-4022	198	7	ed	ed	NOUN
cana-4022	198	8	.	.	PUNCT
cana-4022	198	9	)	)	PUNCT
cana-4022	198	10	.	.	PUNCT
cana-4022	199	1	mit	mit	PROPN
cana-4022	199	2	press	press	NOUN
cana-4022	199	3	.	.	PUNCT
cana-4022	200	1	[	[	X
cana-4022	200	2	14	14	NUM
cana-4022	200	3	]	]	X
cana-4022	200	4	bishop	bishop	PROPN
cana-4022	200	5	,	,	PUNCT
cana-4022	200	6	c.	c.	PROPN
cana-4022	200	7	m.	m.	NOUN
cana-4022	200	8	(	(	PUNCT
cana-4022	200	9	2026	2026	NUM
cana-4022	200	10	)	)	PUNCT
cana-4022	200	11	.	.	PUNCT
cana-4022	201	1	pattern	pattern	NOUN
cana-4022	201	2	recognition	recognition	NOUN
cana-4022	201	3	and	and	CCONJ
cana-4022	201	4	machine	machine	NOUN
cana-4022	201	5	learning	learning	NOUN
cana-4022	201	6	(	(	PUNCT
cana-4022	201	7	3rd	3rd	ADJ
cana-4022	201	8	ed	ed	NOUN
cana-4022	201	9	.	.	PUNCT
cana-4022	201	10	)	)	PUNCT
cana-4022	201	11	.	.	PUNCT
cana-4022	202	1	springer	springer	NOUN
cana-4022	202	2	.	.	PUNCT
cana-4022	203	1	[	[	X
cana-4022	203	2	15	15	NUM
cana-4022	203	3	]	]	X
cana-4022	203	4	brownlee	brownlee	PROPN
cana-4022	203	5	,	,	PUNCT
cana-4022	203	6	j.	j.	PROPN
cana-4022	203	7	(	(	PUNCT
cana-4022	203	8	2023	2023	NUM
cana-4022	203	9	)	)	PUNCT
cana-4022	203	10	.	.	PUNCT
cana-4022	204	1	master	master	NOUN
cana-4022	204	2	machine	machine	NOUN
cana-4022	204	3	learning	learn	VERB
cana-4022	204	4	algorithms	algorithm	NOUN
cana-4022	204	5	.	.	PUNCT
cana-4022	205	1	machine	machine	NOUN
cana-4022	205	2	learning	learn	VERB
cana-4022	205	3	mastery	mastery	NOUN
cana-4022	205	4	.	.	PUNCT
cana-4022	206	1	[	[	X
cana-4022	206	2	16	16	NUM
cana-4022	206	3	]	]	X
cana-4022	206	4	chollet	chollet	NOUN
cana-4022	206	5	,	,	PUNCT
cana-4022	206	6	f.	f.	PROPN
cana-4022	206	7	(	(	PUNCT
cana-4022	206	8	2025	2025	NUM
cana-4022	206	9	)	)	PUNCT
cana-4022	206	10	.	.	PUNCT
cana-4022	207	1	deep	deep	ADJ
cana-4022	207	2	learning	learning	NOUN
cana-4022	207	3	with	with	ADP
cana-4022	207	4	python	python	NOUN
cana-4022	207	5	(	(	PUNCT
cana-4022	207	6	3rd	3rd	ADJ
cana-4022	207	7	ed	ed	NOUN
cana-4022	207	8	.	.	PUNCT
cana-4022	207	9	)	)	PUNCT
cana-4022	207	10	.	.	PUNCT
cana-4022	208	1	manning	man	VERB
cana-4022	208	2	publications	publication	NOUN
cana-4022	208	3	.	.	PUNCT
cana-4022	209	1	[	[	X
cana-4022	209	2	17	17	NUM
cana-4022	209	3	]	]	X
cana-4022	209	4	duda	duda	PROPN
cana-4022	209	5	,	,	PUNCT
cana-4022	209	6	r.	r.	PROPN
cana-4022	209	7	o.	o.	PROPN
cana-4022	209	8	,	,	PUNCT
cana-4022	209	9	hart	hart	PROPN
cana-4022	209	10	,	,	PUNCT
cana-4022	209	11	p.	p.	PROPN
cana-4022	209	12	e.	e.	PROPN
cana-4022	209	13	,	,	PUNCT
cana-4022	209	14	&	&	CCONJ
cana-4022	209	15	stork	stork	PROPN
cana-4022	209	16	,	,	PUNCT
cana-4022	209	17	d.	d.	PROPN
cana-4022	209	18	g.	g.	PROPN
cana-4022	209	19	(	(	PUNCT
cana-4022	209	20	2024	2024	NUM
cana-4022	209	21	)	)	PUNCT
cana-4022	209	22	.	.	PUNCT
cana-4022	210	1	pattern	pattern	NOUN
cana-4022	210	2	classification	classification	NOUN
cana-4022	210	3	(	(	PUNCT
cana-4022	210	4	3rd	3rd	ADJ
cana-4022	210	5	ed	ed	NOUN
cana-4022	210	6	.	.	PUNCT
cana-4022	210	7	)	)	PUNCT
cana-4022	210	8	.	.	PUNCT
cana-4022	211	1	wileyinterscience	wileyinterscience	NOUN
cana-4022	211	2	.	.	PUNCT
cana-4022	212	1	[	[	X
cana-4022	212	2	18	18	NUM
cana-4022	212	3	]	]	X
cana-4022	212	4	efron	efron	PROPN
cana-4022	212	5	,	,	PUNCT
cana-4022	212	6	b.	b.	PROPN
cana-4022	212	7	,	,	PUNCT
cana-4022	212	8	&	&	CCONJ
cana-4022	212	9	hastie	hastie	PROPN
cana-4022	212	10	,	,	PUNCT
cana-4022	212	11	t.	t.	PROPN
cana-4022	212	12	(	(	PUNCT
cana-4022	212	13	2023	2023	NUM
cana-4022	212	14	)	)	PUNCT
cana-4022	212	15	.	.	PUNCT
cana-4022	213	1	computer	computer	NOUN
cana-4022	213	2	age	age	NOUN
cana-4022	213	3	statistical	statistical	ADJ
cana-4022	213	4	inference	inference	NOUN
cana-4022	213	5	:	:	PUNCT
cana-4022	213	6	algorithms	algorithm	NOUN
cana-4022	213	7	,	,	PUNCT
cana-4022	213	8	evidence	evidence	NOUN
cana-4022	213	9	,	,	PUNCT
cana-4022	213	10	and	and	CCONJ
cana-4022	213	11	data	datum	NOUN
cana-4022	213	12	science	science	NOUN
cana-4022	213	13	.	.	PUNCT
cana-4022	214	1	cambridge	cambridge	PROPN
cana-4022	214	2	university	university	PROPN
cana-4022	214	3	press	press	NOUN
cana-4022	214	4	.	.	PUNCT
cana-4022	215	1	[	[	X
cana-4022	215	2	19	19	NUM
cana-4022	215	3	]	]	X
cana-4022	215	4	flach	flach	PROPN
cana-4022	215	5	,	,	PUNCT
cana-4022	215	6	p.	p.	NOUN
cana-4022	215	7	(	(	PUNCT
cana-4022	215	8	2024	2024	NUM
cana-4022	215	9	)	)	PUNCT
cana-4022	215	10	.	.	PUNCT
cana-4022	216	1	machine	machine	NOUN
cana-4022	216	2	learning	learning	NOUN
cana-4022	216	3	:	:	PUNCT
cana-4022	216	4	the	the	DET
cana-4022	216	5	art	art	NOUN
cana-4022	216	6	and	and	CCONJ
cana-4022	216	7	science	science	NOUN
cana-4022	216	8	of	of	ADP
cana-4022	216	9	algorithms	algorithm	NOUN
cana-4022	216	10	that	that	PRON
cana-4022	216	11	make	make	VERB
cana-4022	216	12	sense	sense	NOUN
cana-4022	216	13	of	of	ADP
cana-4022	216	14	data	datum	NOUN
cana-4022	216	15	(	(	PUNCT
cana-4022	216	16	2nd	2nd	ADJ
cana-4022	216	17	ed	ed	NOUN
cana-4022	216	18	.	.	PUNCT
cana-4022	216	19	)	)	PUNCT
cana-4022	216	20	.	.	PUNCT
cana-4022	217	1	cambridge	cambridge	PROPN
cana-4022	217	2	university	university	PROPN
cana-4022	217	3	press	press	NOUN
cana-4022	217	4	.	.	PUNCT
cana-4022	218	1	[	[	X
cana-4022	218	2	20	20	NUM
cana-4022	218	3	]	]	X
cana-4022	218	4	goodfellow	goodfellow	PROPN
cana-4022	218	5	,	,	PUNCT
cana-4022	218	6	i.	i.	PROPN
cana-4022	218	7	,	,	PUNCT
cana-4022	218	8	bengio	bengio	PROPN
cana-4022	218	9	,	,	PUNCT
cana-4022	218	10	y.	y.	PROPN
cana-4022	218	11	,	,	PUNCT
cana-4022	218	12	&	&	CCONJ
cana-4022	218	13	courville	courville	PROPN
cana-4022	218	14	,	,	PUNCT
cana-4022	218	15	a.	a.	NOUN
cana-4022	218	16	(	(	PUNCT
cana-4022	218	17	2025	2025	NUM
cana-4022	218	18	)	)	PUNCT
cana-4022	218	19	.	.	PUNCT
cana-4022	219	1	deep	deep	ADJ
cana-4022	219	2	learning	learning	NOUN
cana-4022	219	3	(	(	PUNCT
cana-4022	219	4	2nd	2nd	ADJ
cana-4022	219	5	ed	ed	NOUN
cana-4022	219	6	.	.	PUNCT
cana-4022	219	7	)	)	PUNCT
cana-4022	219	8	.	.	PUNCT
cana-4022	220	1	mit	mit	PROPN
cana-4022	220	2	press	press	NOUN
cana-4022	220	3	.	.	PUNCT
cana-4022	221	1	communications	communication	NOUN
cana-4022	221	2	on	on	ADP
cana-4022	221	3	applied	apply	VERB
cana-4022	221	4	nonlinear	nonlinear	ADJ
cana-4022	221	5	analysis	analysis	NOUN
cana-4022	221	6	issn	issn	NOUN
cana-4022	221	7	:	:	PUNCT
cana-4022	221	8	1074	1074	NUM
cana-4022	221	9	-	-	PUNCT
cana-4022	221	10	133x	133x	NUM
cana-4022	221	11	vol	vol	NOUN
cana-4022	221	12	32	32	NUM
cana-4022	221	13	no	no	NOUN
cana-4022	221	14	.	.	PUNCT
cana-4022	222	1	9s	9s	NUM
cana-4022	222	2	(	(	PUNCT
cana-4022	222	3	2025	2025	NUM
cana-4022	222	4	)	)	PUNCT
cana-4022	222	5	872	872	NUM
cana-4022	222	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-4022	223	1	[	[	X
cana-4022	223	2	21	21	NUM
cana-4022	223	3	]	]	X
cana-4022	223	4	hastie	hastie	PROPN
cana-4022	223	5	,	,	PUNCT
cana-4022	223	6	t.	t.	PROPN
cana-4022	223	7	,	,	PUNCT
cana-4022	223	8	tibshirani	tibshirani	PROPN
cana-4022	223	9	,	,	PUNCT
cana-4022	223	10	r.	r.	PROPN
cana-4022	223	11	,	,	PUNCT
cana-4022	223	12	&	&	CCONJ
cana-4022	223	13	friedman	friedman	PROPN
cana-4022	223	14	,	,	PUNCT
cana-4022	223	15	j.	j.	PROPN
cana-4022	223	16	(	(	PUNCT
cana-4022	223	17	2024	2024	NUM
cana-4022	223	18	)	)	PUNCT
cana-4022	223	19	.	.	PUNCT
cana-4022	224	1	the	the	DET
cana-4022	224	2	elements	element	NOUN
cana-4022	224	3	of	of	ADP
cana-4022	224	4	statistical	statistical	ADJ
cana-4022	224	5	learning	learning	NOUN
cana-4022	224	6	:	:	PUNCT
cana-4022	224	7	data	datum	NOUN
cana-4022	224	8	mining	mining	NOUN
cana-4022	224	9	,	,	PUNCT
cana-4022	224	10	inference	inference	NOUN
cana-4022	224	11	,	,	PUNCT
cana-4022	224	12	and	and	CCONJ
cana-4022	224	13	prediction	prediction	NOUN
cana-4022	224	14	(	(	PUNCT
cana-4022	224	15	3rd	3rd	ADJ
cana-4022	224	16	ed	ed	NOUN
cana-4022	224	17	.	.	PUNCT
cana-4022	224	18	)	)	PUNCT
cana-4022	224	19	.	.	PUNCT
cana-4022	225	1	springer	springer	NOUN
cana-4022	225	2	.	.	PUNCT
cana-4022	226	1	[	[	X
cana-4022	226	2	22	22	NUM
cana-4022	226	3	]	]	X
cana-4022	226	4	james	james	PROPN
cana-4022	226	5	,	,	PUNCT
cana-4022	226	6	g.	g.	PROPN
cana-4022	226	7	,	,	PUNCT
cana-4022	226	8	witten	witten	PROPN
cana-4022	226	9	,	,	PUNCT
cana-4022	226	10	d.	d.	PROPN
cana-4022	226	11	,	,	PUNCT
cana-4022	226	12	hastie	hastie	PROPN
cana-4022	226	13	,	,	PUNCT
cana-4022	226	14	t.	t.	PROPN
cana-4022	226	15	,	,	PUNCT
cana-4022	226	16	&	&	CCONJ
cana-4022	226	17	tibshirani	tibshirani	PROPN
cana-4022	226	18	,	,	PUNCT
cana-4022	226	19	r.	r.	PROPN
cana-4022	226	20	(	(	PUNCT
cana-4022	226	21	2025	2025	NUM
cana-4022	226	22	)	)	PUNCT
cana-4022	226	23	.	.	PUNCT
cana-4022	227	1	an	an	DET
cana-4022	227	2	introduction	introduction	NOUN
cana-4022	227	3	to	to	ADP
cana-4022	227	4	statistical	statistical	ADJ
cana-4022	227	5	learning	learning	NOUN
cana-4022	227	6	:	:	PUNCT
cana-4022	227	7	with	with	ADP
cana-4022	227	8	applications	application	NOUN
cana-4022	227	9	in	in	ADP
cana-4022	227	10	r	r	NOUN
cana-4022	227	11	(	(	PUNCT
cana-4022	227	12	3rd	3rd	ADJ
cana-4022	227	13	ed	ed	NOUN
cana-4022	227	14	.	.	PUNCT
cana-4022	227	15	)	)	PUNCT
cana-4022	227	16	.	.	PUNCT
cana-4022	228	1	springer	springer	NOUN
cana-4022	228	2	.	.	PUNCT
cana-4022	229	1	[	[	X
cana-4022	229	2	23	23	NUM
cana-4022	229	3	]	]	X
cana-4022	229	4	kelleher	kelleher	PROPN
cana-4022	229	5	,	,	PUNCT
cana-4022	229	6	j.	j.	PROPN
cana-4022	229	7	d.	d.	PROPN
cana-4022	229	8	,	,	PUNCT
cana-4022	229	9	mac	mac	PROPN
cana-4022	229	10	namee	namee	PROPN
cana-4022	229	11	,	,	PUNCT
cana-4022	229	12	b.	b.	PROPN
cana-4022	229	13	,	,	PUNCT
cana-4022	229	14	&	&	CCONJ
cana-4022	229	15	d'arcy	d'arcy	PROPN
cana-4022	229	16	,	,	PUNCT
cana-4022	229	17	a.	a.	NOUN
cana-4022	229	18	(	(	PUNCT
cana-4022	229	19	2023	2023	NUM
cana-4022	229	20	)	)	PUNCT
cana-4022	229	21	.	.	PUNCT
cana-4022	230	1	fundamentals	fundamental	NOUN
cana-4022	230	2	of	of	ADP
cana-4022	230	3	machine	machine	NOUN
cana-4022	230	4	learning	learn	VERB
cana-4022	230	5	for	for	ADP
cana-4022	230	6	predictive	predictive	ADJ
cana-4022	230	7	data	datum	NOUN
cana-4022	230	8	analytics	analytic	NOUN
cana-4022	230	9	:	:	PUNCT
cana-4022	230	10	algorithms	algorithm	NOUN
cana-4022	230	11	,	,	PUNCT
cana-4022	230	12	worked	work	VERB
cana-4022	230	13	examples	example	NOUN
cana-4022	230	14	,	,	PUNCT
cana-4022	230	15	and	and	CCONJ
cana-4022	230	16	case	case	NOUN
cana-4022	230	17	studies	study	NOUN
cana-4022	230	18	(	(	PUNCT
cana-4022	230	19	2nd	2nd	ADJ
cana-4022	230	20	ed	ed	NOUN
cana-4022	230	21	.	.	PUNCT
cana-4022	230	22	)	)	PUNCT
cana-4022	230	23	.	.	PUNCT
cana-4022	231	1	mit	mit	PROPN
cana-4022	231	2	press	press	NOUN
cana-4022	231	3	.	.	PUNCT
cana-4022	232	1	[	[	X
cana-4022	232	2	24	24	NUM
cana-4022	232	3	]	]	X
cana-4022	232	4	kotsiantis	kotsiantis	PROPN
cana-4022	232	5	,	,	PUNCT
cana-4022	232	6	s.	s.	PROPN
cana-4022	232	7	b.	b.	PROPN
cana-4022	232	8	(	(	PUNCT
cana-4022	232	9	2024	2024	NUM
cana-4022	232	10	)	)	PUNCT
cana-4022	232	11	.	.	PUNCT
cana-4022	233	1	supervised	supervised	ADJ
cana-4022	233	2	machine	machine	NOUN
cana-4022	233	3	learning	learning	NOUN
cana-4022	233	4	:	:	PUNCT
cana-4022	233	5	a	a	DET
cana-4022	233	6	review	review	NOUN
cana-4022	233	7	of	of	ADP
cana-4022	233	8	classification	classification	NOUN
cana-4022	233	9	techniques	technique	NOUN
cana-4022	233	10	.	.	PUNCT
cana-4022	234	1	informatica	informatica	PROPN
cana-4022	234	2	,	,	PUNCT
cana-4022	234	3	31(3	31(3	NUM
cana-4022	234	4	)	)	PUNCT
cana-4022	234	5	,	,	PUNCT
cana-4022	234	6	249	249	NUM
cana-4022	234	7	-	-	SYM
cana-4022	234	8	268	268	NUM
cana-4022	234	9	.	.	PUNCT
cana-4022	235	1	[	[	X
cana-4022	235	2	25	25	NUM
cana-4022	235	3	]	]	X
cana-4022	235	4	kubat	kubat	NOUN
cana-4022	235	5	,	,	PUNCT
cana-4022	235	6	m.	m.	NOUN
cana-4022	235	7	(	(	PUNCT
cana-4022	235	8	2024	2024	NUM
cana-4022	235	9	)	)	PUNCT
cana-4022	235	10	.	.	PUNCT
cana-4022	236	1	an	an	DET
cana-4022	236	2	introduction	introduction	NOUN
cana-4022	236	3	to	to	ADP
cana-4022	236	4	machine	machine	NOUN
cana-4022	236	5	learning	learning	NOUN
cana-4022	236	6	(	(	PUNCT
cana-4022	236	7	3rd	3rd	ADJ
cana-4022	236	8	ed	ed	NOUN
cana-4022	236	9	.	.	PUNCT
cana-4022	236	10	)	)	PUNCT
cana-4022	236	11	.	.	PUNCT
cana-4022	237	1	springer	springer	NOUN
cana-4022	237	2	.	.	PUNCT
cana-4022	238	1	[	[	X
cana-4022	238	2	26	26	NUM
cana-4022	238	3	]	]	X
cana-4022	238	4	lecun	lecun	ADJ
cana-4022	238	5	,	,	PUNCT
cana-4022	238	6	y.	y.	PROPN
cana-4022	238	7	,	,	PUNCT
cana-4022	238	8	bengio	bengio	PROPN
cana-4022	238	9	,	,	PUNCT
cana-4022	238	10	y.	y.	PROPN
cana-4022	238	11	,	,	PUNCT
cana-4022	238	12	&	&	CCONJ
cana-4022	238	13	hinton	hinton	PROPN
cana-4022	238	14	,	,	PUNCT
cana-4022	238	15	g.	g.	PROPN
cana-4022	238	16	(	(	PUNCT
cana-4022	238	17	2023	2023	NUM
cana-4022	238	18	)	)	PUNCT
cana-4022	238	19	.	.	PUNCT
cana-4022	239	1	deep	deep	ADJ
cana-4022	239	2	learning	learning	NOUN
cana-4022	239	3	.	.	PUNCT
cana-4022	240	1	nature	nature	NOUN
cana-4022	240	2	,	,	PUNCT
cana-4022	240	3	521(7553	521(7553	NUM
cana-4022	240	4	)	)	PUNCT
cana-4022	240	5	,	,	PUNCT
cana-4022	240	6	436	436	NUM
cana-4022	240	7	-	-	SYM
cana-4022	240	8	444	444	NUM
cana-4022	240	9	.	.	PUNCT
cana-4022	241	1	[	[	X
cana-4022	241	2	27	27	NUM
cana-4022	241	3	]	]	X
cana-4022	241	4	mitchell	mitchell	NOUN
cana-4022	241	5	,	,	PUNCT
cana-4022	241	6	t.	t.	PROPN
cana-4022	241	7	m.	m.	NOUN
cana-4022	241	8	(	(	PUNCT
cana-4022	241	9	2025	2025	NUM
cana-4022	241	10	)	)	PUNCT
cana-4022	241	11	.	.	PUNCT
cana-4022	242	1	machine	machine	NOUN
cana-4022	242	2	learning	learning	NOUN
cana-4022	242	3	(	(	PUNCT
cana-4022	242	4	2nd	2nd	ADJ
cana-4022	242	5	ed	ed	NOUN
cana-4022	242	6	.	.	PUNCT
cana-4022	242	7	)	)	PUNCT
cana-4022	242	8	.	.	PUNCT
cana-4022	243	1	mcgraw	mcgraw	PROPN
cana-4022	243	2	hill	hill	PROPN
cana-4022	243	3	.	.	PUNCT
cana-4022	244	1	[	[	X
cana-4022	244	2	28	28	NUM
cana-4022	244	3	]	]	X
cana-4022	244	4	murphy	murphy	PROPN
cana-4022	244	5	,	,	PUNCT
cana-4022	244	6	k.	k.	PROPN
cana-4022	245	1	p.	p.	PROPN
cana-4022	245	2	(	(	PUNCT
cana-4022	245	3	2024	2024	NUM
cana-4022	245	4	)	)	PUNCT
cana-4022	245	5	.	.	PUNCT
cana-4022	246	1	machine	machine	NOUN
cana-4022	246	2	learning	learning	NOUN
cana-4022	246	3	:	:	PUNCT
cana-4022	246	4	a	a	DET
cana-4022	246	5	probabilistic	probabilistic	ADJ
cana-4022	246	6	perspective	perspective	NOUN
cana-4022	246	7	(	(	PUNCT
cana-4022	246	8	2nd	2nd	ADJ
cana-4022	246	9	ed	ed	NOUN
cana-4022	246	10	.	.	PUNCT
cana-4022	246	11	)	)	PUNCT
cana-4022	246	12	.	.	PUNCT
cana-4022	247	1	mit	mit	PROPN
cana-4022	247	2	press	press	NOUN
cana-4022	247	3	.	.	PUNCT
cana-4022	248	1	[	[	X
cana-4022	248	2	29	29	NUM
cana-4022	248	3	]	]	SYM
cana-4022	248	4	ng	ng	PROPN
cana-4022	248	5	,	,	PUNCT
cana-4022	248	6	a.	a.	PROPN
cana-4022	248	7	y.	y.	PROPN
cana-4022	248	8	,	,	PUNCT
cana-4022	248	9	&	&	CCONJ
cana-4022	248	10	jordan	jordan	PROPN
cana-4022	248	11	,	,	PUNCT
cana-4022	248	12	m.	m.	NOUN
cana-4022	248	13	i.	i.	PROPN
cana-4022	248	14	(	(	PUNCT
cana-4022	248	15	2023	2023	NUM
cana-4022	248	16	)	)	PUNCT
cana-4022	248	17	.	.	PUNCT
cana-4022	249	1	on	on	ADP
cana-4022	249	2	discriminative	discriminative	NOUN
cana-4022	249	3	vs.	vs.	ADP
cana-4022	249	4	generative	generative	ADJ
cana-4022	249	5	classifiers	classifier	NOUN
cana-4022	249	6	:	:	PUNCT
cana-4022	249	7	a	a	DET
cana-4022	249	8	comparison	comparison	NOUN
cana-4022	249	9	of	of	ADP
cana-4022	249	10	logistic	logistic	ADJ
cana-4022	249	11	regression	regression	NOUN
cana-4022	249	12	and	and	CCONJ
cana-4022	249	13	naive	naive	ADJ
cana-4022	249	14	bayes	baye	NOUN
cana-4022	249	15	.	.	PUNCT
cana-4022	250	1	advances	advance	NOUN
cana-4022	250	2	in	in	ADP
cana-4022	250	3	neural	neural	ADJ
cana-4022	250	4	information	information	NOUN
cana-4022	250	5	processing	processing	NOUN
cana-4022	250	6	systems	system	NOUN
cana-4022	250	7	,	,	PUNCT
cana-4022	250	8	14	14	NUM
cana-4022	250	9	,	,	PUNCT
cana-4022	250	10	841	841	NUM
cana-4022	250	11	-	-	SYM
cana-4022	250	12	848	848	NUM
cana-4022	250	13	.	.	PUNCT
cana-4022	251	1	[	[	X
cana-4022	251	2	30	30	NUM
cana-4022	251	3	]	]	X
cana-4022	251	4	pedregosa	pedregosa	PROPN
cana-4022	251	5	,	,	PUNCT
cana-4022	251	6	f.	f.	PROPN
cana-4022	251	7	,	,	PUNCT
cana-4022	251	8	varoquaux	varoquaux	PROPN
cana-4022	251	9	,	,	PUNCT
cana-4022	251	10	g.	g.	PROPN
cana-4022	251	11	,	,	PUNCT
cana-4022	251	12	gramfort	gramfort	NOUN
cana-4022	251	13	,	,	PUNCT
cana-4022	251	14	a.	a.	PROPN
cana-4022	251	15	,	,	PUNCT
cana-4022	251	16	michel	michel	PROPN
cana-4022	251	17	,	,	PUNCT
cana-4022	251	18	v.	v.	PROPN
cana-4022	251	19	,	,	PUNCT
cana-4022	251	20	thirion	thirion	NOUN
cana-4022	251	21	,	,	PUNCT
cana-4022	251	22	b.	b.	PROPN
cana-4022	251	23	,	,	PUNCT
cana-4022	251	24	grisel	grisel	PROPN
cana-4022	251	25	,	,	PUNCT
cana-4022	251	26	o.	o.	PROPN
cana-4022	251	27	,	,	PUNCT
cana-4022	251	28	...	...	PUNCT
cana-4022	251	29	&	&	CCONJ
cana-4022	251	30	duchesnay	duchesnay	PROPN
cana-4022	251	31	,	,	PUNCT
cana-4022	251	32	e.	e.	PROPN
cana-4022	251	33	(	(	PUNCT
cana-4022	251	34	2024	2024	NUM
cana-4022	251	35	)	)	PUNCT
cana-4022	251	36	.	.	PUNCT
cana-4022	251	37	scikit	scikit	NOUN
cana-4022	251	38	-	-	PUNCT
cana-4022	251	39	learn	learn	VERB
cana-4022	251	40	:	:	PUNCT
cana-4022	251	41	machine	machine	NOUN
cana-4022	251	42	learning	learning	NOUN
cana-4022	251	43	in	in	ADP
cana-4022	251	44	python	python	PROPN
cana-4022	251	45	.	.	PUNCT
cana-4022	252	1	journal	journal	PROPN
cana-4022	252	2	of	of	ADP
cana-4022	252	3	machine	machine	NOUN
cana-4022	252	4	learning	learn	VERB
cana-4022	252	5	research	research	NOUN
cana-4022	252	6	,	,	PUNCT
cana-4022	252	7	12	12	NUM
cana-4022	252	8	,	,	PUNCT
cana-4022	252	9	2825	2825	NUM
cana-4022	252	10	-	-	SYM
cana-4022	252	11	2830	2830	NUM
cana-4022	252	12	.	.	PUNCT
cana-4022	253	1	[	[	X
cana-4022	253	2	31	31	NUM
cana-4022	253	3	]	]	X
cana-4022	253	4	raschka	raschka	PROPN
cana-4022	253	5	,	,	PUNCT
cana-4022	253	6	s.	s.	PROPN
cana-4022	253	7	,	,	PUNCT
cana-4022	253	8	&	&	CCONJ
cana-4022	253	9	mirjalili	mirjalili	NOUN
cana-4022	253	10	,	,	PUNCT
cana-4022	253	11	v.	v.	PROPN
cana-4022	253	12	(	(	PUNCT
cana-4022	253	13	2025	2025	NUM
cana-4022	253	14	)	)	PUNCT
cana-4022	253	15	.	.	PUNCT
cana-4022	254	1	python	python	PROPN
cana-4022	254	2	machine	machine	NOUN
cana-4022	254	3	learning	learning	PROPN
cana-4022	254	4	:	:	PUNCT
cana-4022	254	5	machine	machine	NOUN
cana-4022	254	6	learning	learning	NOUN
cana-4022	254	7	and	and	CCONJ
cana-4022	254	8	deep	deep	ADJ
cana-4022	254	9	learning	learning	NOUN
cana-4022	254	10	with	with	ADP
cana-4022	254	11	python	python	PROPN
cana-4022	254	12	,	,	PUNCT
cana-4022	254	13	scikit	scikit	NOUN
cana-4022	254	14	-	-	PUNCT
cana-4022	254	15	learn	learn	VERB
cana-4022	254	16	,	,	PUNCT
cana-4022	254	17	and	and	CCONJ
cana-4022	254	18	tensorflow	tensorflow	NOUN
cana-4022	254	19	2	2	NUM
cana-4022	254	20	(	(	PUNCT
cana-4022	254	21	4th	4th	ADJ
cana-4022	254	22	ed	ed	NOUN
cana-4022	254	23	.	.	PUNCT
cana-4022	254	24	)	)	PUNCT
cana-4022	254	25	.	.	PUNCT
cana-4022	255	1	packt	packt	PROPN
cana-4022	255	2	publishing	publishing	NOUN
cana-4022	255	3	.	.	PUNCT
cana-4022	256	1	[	[	X
cana-4022	256	2	32	32	NUM
cana-4022	256	3	]	]	X
cana-4022	256	4	russell	russell	PROPN
cana-4022	256	5	,	,	PUNCT
cana-4022	256	6	s.	s.	PROPN
cana-4022	256	7	,	,	PUNCT
cana-4022	256	8	&	&	CCONJ
cana-4022	256	9	norvig	norvig	NOUN
cana-4022	256	10	,	,	PUNCT
cana-4022	256	11	p.	p.	NOUN
cana-4022	256	12	(	(	PUNCT
cana-4022	256	13	2026	2026	NUM
cana-4022	256	14	)	)	PUNCT
cana-4022	256	15	.	.	PUNCT
cana-4022	257	1	artificial	artificial	ADJ
cana-4022	257	2	intelligence	intelligence	NOUN
cana-4022	257	3	:	:	PUNCT
cana-4022	257	4	a	a	DET
cana-4022	257	5	modern	modern	ADJ
cana-4022	257	6	approach	approach	NOUN
cana-4022	257	7	(	(	PUNCT
cana-4022	257	8	5th	5th	ADJ
cana-4022	257	9	ed	ed	NOUN
cana-4022	257	10	.	.	PUNCT
cana-4022	257	11	)	)	PUNCT
cana-4022	257	12	.	.	PUNCT
cana-4022	258	1	pearson	pearson	PROPN
cana-4022	258	2	.	.	PUNCT
cana-4022	259	1	[	[	X
cana-4022	259	2	33	33	NUM
cana-4022	259	3	]	]	X
cana-4022	259	4	sammut	sammut	NOUN
cana-4022	259	5	,	,	PUNCT
cana-4022	259	6	c.	c.	PROPN
cana-4022	259	7	,	,	PUNCT
cana-4022	259	8	&	&	CCONJ
cana-4022	259	9	webb	webb	PROPN
cana-4022	259	10	,	,	PUNCT
cana-4022	259	11	g.	g.	PROPN
cana-4022	259	12	i.	i.	PROPN
cana-4022	259	13	(	(	PUNCT
cana-4022	259	14	eds	eds	PROPN
cana-4022	259	15	.	.	PUNCT
cana-4022	259	16	)	)	PUNCT
cana-4022	259	17	.	.	PUNCT
cana-4022	260	1	(	(	PUNCT
cana-4022	260	2	2024	2024	NUM
cana-4022	260	3	)	)	PUNCT
cana-4022	260	4	.	.	PUNCT
cana-4022	261	1	encyclopedia	encyclopedia	NOUN
cana-4022	261	2	of	of	ADP
cana-4022	261	3	machine	machine	NOUN
cana-4022	261	4	learning	learning	NOUN
cana-4022	261	5	and	and	CCONJ
cana-4022	261	6	data	datum	NOUN
cana-4022	261	7	mining	mining	NOUN
cana-4022	261	8	(	(	PUNCT
cana-4022	261	9	2nd	2nd	ADJ
cana-4022	261	10	ed	ed	NOUN
cana-4022	261	11	.	.	PUNCT
cana-4022	261	12	)	)	PUNCT
cana-4022	261	13	.	.	PUNCT
cana-4022	262	1	springer	springer	NOUN
cana-4022	262	2	.	.	PUNCT
cana-4022	263	1	[	[	X
cana-4022	263	2	34	34	NUM
cana-4022	263	3	]	]	PUNCT
cana-4022	263	4	shalev	shalev	NOUN
cana-4022	263	5	-	-	PUNCT
cana-4022	263	6	shwartz	shwartz	PROPN
cana-4022	263	7	,	,	PUNCT
cana-4022	263	8	s.	s.	PROPN
cana-4022	263	9	,	,	PUNCT
cana-4022	263	10	&	&	CCONJ
cana-4022	263	11	ben	ben	PROPN
cana-4022	263	12	-	-	PROPN
cana-4022	263	13	david	david	PROPN
cana-4022	263	14	,	,	PUNCT
cana-4022	263	15	s.	s.	PROPN
cana-4022	263	16	(	(	PUNCT
cana-4022	263	17	2023	2023	NUM
cana-4022	263	18	)	)	PUNCT
cana-4022	263	19	.	.	PUNCT
cana-4022	264	1	understanding	understand	VERB
cana-4022	264	2	machine	machine	NOUN
cana-4022	264	3	learning	learning	NOUN
cana-4022	264	4	:	:	PUNCT
cana-4022	264	5	from	from	ADP
cana-4022	264	6	theory	theory	NOUN
cana-4022	264	7	to	to	ADP
cana-4022	264	8	algorithms	algorithms	PROPN
cana-4022	264	9	.	.	PUNCT
cana-4022	265	1	cambridge	cambridge	PROPN
cana-4022	265	2	university	university	PROPN
cana-4022	265	3	press	press	NOUN
cana-4022	265	4	.	.	PUNCT