id	sid	tid	token	lemma	pos
cana-5634	1	1	communications	communication	NOUN
cana-5634	1	2	on	on	ADP
cana-5634	1	3	applied	apply	VERB
cana-5634	1	4	nonlinear	nonlinear	ADJ
cana-5634	1	5	analysis	analysis	NOUN
cana-5634	1	6	issn	issn	NOUN
cana-5634	1	7	:	:	PUNCT
cana-5634	1	8	1074	1074	NUM
cana-5634	1	9	-	-	PUNCT
cana-5634	1	10	133x	133x	NUM
cana-5634	1	11	vol	vol	VERB
cana-5634	1	12	32	32	NUM
cana-5634	1	13	no.1s	no.1s	PROPN
cana-5634	1	14	(	(	PUNCT
cana-5634	1	15	2025	2025	NUM
cana-5634	1	16	)	)	PUNCT
cana-5634	1	17	670	670	NUM
cana-5634	1	18	https://internationalpubls.com	https://internationalpubls.com	X
cana-5634	1	19	a	a	DET
cana-5634	1	20	comprehensive	comprehensive	ADJ
cana-5634	1	21	evaluation	evaluation	NOUN
cana-5634	1	22	of	of	ADP
cana-5634	1	23	deep	deep	ADJ
cana-5634	1	24	learning	learning	NOUN
cana-5634	1	25	architectures	architecture	NOUN
cana-5634	1	26	and	and	CCONJ
cana-5634	1	27	traditional	traditional	ADJ
cana-5634	1	28	machine	machine	NOUN
cana-5634	1	29	learning	learn	VERB
cana-5634	1	30	algorithms	algorithm	NOUN
cana-5634	1	31	for	for	ADP
cana-5634	1	32	prognostic	prognostic	ADJ
cana-5634	1	33	modeling	modeling	NOUN
cana-5634	1	34	in	in	ADP
cana-5634	1	35	alzheimer	alzheimer	PROPN
cana-5634	1	36	’s	’s	PART
cana-5634	1	37	disease	disease	PROPN
cana-5634	1	38	r.	r.	PROPN
cana-5634	1	39	arumugam1	arumugam1	PROPN
cana-5634	1	40	and	and	CCONJ
cana-5634	1	41	a.	a.	NOUN
cana-5634	1	42	murugan2	murugan2	PROPN
cana-5634	2	1	1research	1research	NUM
cana-5634	2	2	scholar	scholar	NOUN
cana-5634	2	3	,	,	PUNCT
cana-5634	2	4	department	department	NOUN
cana-5634	2	5	of	of	ADP
cana-5634	2	6	computer	computer	NOUN
cana-5634	2	7	and	and	CCONJ
cana-5634	2	8	information	information	NOUN
cana-5634	2	9	science	science	NOUN
cana-5634	2	10	,	,	PUNCT
cana-5634	2	11	annamalai	annamalai	PROPN
cana-5634	2	12	university	university	PROPN
cana-5634	2	13	,	,	PUNCT
cana-5634	2	14	annamalainagar	annamalainagar	NOUN
cana-5634	2	15	–	–	PUNCT
cana-5634	2	16	608	608	NUM
cana-5634	2	17	002	002	NUM
cana-5634	2	18	,	,	PUNCT
cana-5634	2	19	tamil	tamil	PROPN
cana-5634	2	20	nadu	nadu	PROPN
cana-5634	2	21	,	,	PUNCT
cana-5634	2	22	india	india	PROPN
cana-5634	2	23	2assistant	2assistant	PROPN
cana-5634	2	24	professor	professor	NOUN
cana-5634	2	25	,	,	PUNCT
cana-5634	2	26	department	department	NOUN
cana-5634	2	27	of	of	ADP
cana-5634	2	28	computer	computer	NOUN
cana-5634	2	29	science	science	NOUN
cana-5634	2	30	,	,	PUNCT
cana-5634	2	31	periyar	periyar	NOUN
cana-5634	2	32	arts	arts	PROPN
cana-5634	2	33	college	college	PROPN
cana-5634	2	34	,	,	PUNCT
cana-5634	2	35	cuddalore	cuddalore	PROPN
cana-5634	2	36	,	,	PUNCT
cana-5634	2	37	(	(	PUNCT
cana-5634	2	38	deputed	depute	VERB
cana-5634	2	39	from	from	ADP
cana-5634	2	40	annamalai	annamalai	PROPN
cana-5634	2	41	university	university	PROPN
cana-5634	2	42	,	,	PUNCT
cana-5634	2	43	annamalainagar	annamalainagar	NOUN
cana-5634	2	44	)	)	PUNCT
cana-5634	2	45	tamil	tamil	PROPN
cana-5634	2	46	nadu	nadu	PROPN
cana-5634	2	47	,	,	PUNCT
cana-5634	2	48	india	india	PROPN
cana-5634	2	49	email	email	NOUN
cana-5634	2	50	:	:	PUNCT
cana-5634	2	51	1arumugammca848@gmail.com,2drmuruganapcs@gmail.com	1arumugammca848@gmail.com,2drmuruganapcs@gmail.com	NUM
cana-5634	2	52	article	article	NOUN
cana-5634	2	53	history	history	NOUN
cana-5634	2	54	:	:	PUNCT
cana-5634	2	55	received	receive	VERB
cana-5634	2	56	:	:	PUNCT
cana-5634	2	57	10	10	NUM
cana-5634	2	58	-	-	SYM
cana-5634	2	59	11	11	NUM
cana-5634	2	60	-	-	PUNCT
cana-5634	2	61	2024	2024	NUM
cana-5634	2	62	revised	revise	VERB
cana-5634	2	63	:	:	PUNCT
cana-5634	2	64	08	08	NUM
cana-5634	2	65	-	-	SYM
cana-5634	2	66	12	12	NUM
cana-5634	2	67	-	-	PUNCT
cana-5634	2	68	2024	2024	NUM
cana-5634	2	69	accepted	accept	VERB
cana-5634	2	70	:	:	PUNCT
cana-5634	2	71	02	02	NUM
cana-5634	2	72	-	-	PUNCT
cana-5634	2	73	01	01	NUM
cana-5634	2	74	-	-	PUNCT
cana-5634	2	75	2025	2025	NUM
cana-5634	2	76	abstract	abstract	NOUN
cana-5634	2	77	:	:	PUNCT
cana-5634	2	78	alzheimer	alzheimer	PROPN
cana-5634	2	79	’s	’s	PART
cana-5634	2	80	disease	disease	NOUN
cana-5634	2	81	(	(	PUNCT
cana-5634	2	82	ad	ad	NOUN
cana-5634	2	83	)	)	PUNCT
cana-5634	2	84	poses	pose	VERB
cana-5634	2	85	a	a	DET
cana-5634	2	86	growing	grow	VERB
cana-5634	2	87	public	public	ADJ
cana-5634	2	88	health	health	NOUN
cana-5634	2	89	challenge	challenge	NOUN
cana-5634	2	90	,	,	PUNCT
cana-5634	2	91	underscoring	underscore	VERB
cana-5634	2	92	the	the	DET
cana-5634	2	93	need	need	NOUN
cana-5634	2	94	for	for	ADP
cana-5634	2	95	accurate	accurate	ADJ
cana-5634	2	96	and	and	CCONJ
cana-5634	2	97	early	early	ADJ
cana-5634	2	98	prognostic	prognostic	ADJ
cana-5634	2	99	methods	method	NOUN
cana-5634	2	100	.	.	PUNCT
cana-5634	3	1	this	this	DET
cana-5634	3	2	study	study	NOUN
cana-5634	3	3	compares	compare	VERB
cana-5634	3	4	traditional	traditional	ADJ
cana-5634	3	5	machine	machine	NOUN
cana-5634	3	6	learning	learning	NOUN
cana-5634	3	7	(	(	PUNCT
cana-5634	3	8	ml	ml	NOUN
cana-5634	3	9	)	)	PUNCT
cana-5634	3	10	algorithms	algorithm	NOUN
cana-5634	3	11	and	and	CCONJ
cana-5634	3	12	contemporary	contemporary	ADJ
cana-5634	3	13	deep	deep	ADJ
cana-5634	3	14	learning	learning	NOUN
cana-5634	3	15	(	(	PUNCT
cana-5634	3	16	dl	dl	NOUN
cana-5634	3	17	)	)	PUNCT
cana-5634	3	18	models	model	NOUN
cana-5634	3	19	for	for	ADP
cana-5634	3	20	predicting	predict	VERB
cana-5634	3	21	ad	ad	NOUN
cana-5634	3	22	outcomes	outcome	NOUN
cana-5634	3	23	using	use	VERB
cana-5634	3	24	the	the	DET
cana-5634	3	25	cross	cross	ADJ
cana-5634	3	26	-	-	ADJ
cana-5634	3	27	sectional	sectional	ADJ
cana-5634	3	28	dataset	dataset	NOUN
cana-5634	3	29	.	.	PUNCT
cana-5634	4	1	the	the	DET
cana-5634	4	2	dataset	dataset	NOUN
cana-5634	4	3	includes	include	VERB
cana-5634	4	4	demographic	demographic	ADJ
cana-5634	4	5	(	(	PUNCT
cana-5634	4	6	i	i	PROPN
cana-5634	4	7	d	d	PROPN
cana-5634	4	8	,	,	PUNCT
cana-5634	4	9	gender	gender	NOUN
cana-5634	4	10	,	,	PUNCT
cana-5634	4	11	handedness	handedness	NOUN
cana-5634	4	12	,	,	PUNCT
cana-5634	4	13	age	age	NOUN
cana-5634	4	14	,	,	PUNCT
cana-5634	4	15	education	education	NOUN
cana-5634	4	16	,	,	PUNCT
cana-5634	4	17	socioeconomic	socioeconomic	ADJ
cana-5634	4	18	status	status	NOUN
cana-5634	4	19	)	)	PUNCT
cana-5634	4	20	,	,	PUNCT
cana-5634	4	21	cognitive	cognitive	ADJ
cana-5634	4	22	(	(	PUNCT
cana-5634	4	23	mmse	mmse	ADJ
cana-5634	4	24	,	,	PUNCT
cana-5634	4	25	cdr	cdr	NOUN
cana-5634	4	26	)	)	PUNCT
cana-5634	4	27	,	,	PUNCT
cana-5634	4	28	and	and	CCONJ
cana-5634	4	29	structural	structural	ADJ
cana-5634	4	30	(	(	PUNCT
cana-5634	4	31	etiv	etiv	PROPN
cana-5634	4	32	,	,	PUNCT
cana-5634	4	33	nwbv	nwbv	PROPN
cana-5634	4	34	,	,	PUNCT
cana-5634	4	35	asf	asf	NOUN
cana-5634	4	36	)	)	PUNCT
cana-5634	4	37	features	feature	NOUN
cana-5634	4	38	.	.	PUNCT
cana-5634	5	1	standard	standard	ADJ
cana-5634	5	2	ml	ml	NOUN
cana-5634	5	3	techniques	technique	NOUN
cana-5634	5	4	—	—	PUNCT
cana-5634	5	5	support	support	NOUN
cana-5634	5	6	vector	vector	NOUN
cana-5634	5	7	machines	machine	NOUN
cana-5634	5	8	(	(	PUNCT
cana-5634	5	9	svm	svm	PROPN
cana-5634	5	10	)	)	PUNCT
cana-5634	5	11	,	,	PUNCT
cana-5634	5	12	random	random	ADJ
cana-5634	5	13	forest	forest	NOUN
cana-5634	5	14	(	(	PUNCT
cana-5634	5	15	rf	rf	NOUN
cana-5634	5	16	)	)	PUNCT
cana-5634	5	17	,	,	PUNCT
cana-5634	5	18	and	and	CCONJ
cana-5634	5	19	gradient	gradient	ADJ
cana-5634	5	20	boosting	boost	VERB
cana-5634	5	21	machines	machine	NOUN
cana-5634	5	22	(	(	PUNCT
cana-5634	5	23	gbm)—were	gbm)—were	VERB
cana-5634	5	24	implemented	implement	VERB
cana-5634	5	25	with	with	ADP
cana-5634	5	26	hyperparameters	hyperparameter	NOUN
cana-5634	5	27	optimized	optimize	VERB
cana-5634	5	28	via	via	ADP
cana-5634	5	29	grid	grid	NOUN
cana-5634	5	30	search	search	NOUN
cana-5634	5	31	and	and	CCONJ
cana-5634	5	32	cross	cross	NOUN
cana-5634	5	33	-	-	NOUN
cana-5634	5	34	validation	validation	NOUN
cana-5634	5	35	.	.	PUNCT
cana-5634	6	1	concurrently	concurrently	ADV
cana-5634	6	2	,	,	PUNCT
cana-5634	6	3	deep	deep	ADJ
cana-5634	6	4	neural	neural	ADJ
cana-5634	6	5	networks	network	NOUN
cana-5634	6	6	(	(	PUNCT
cana-5634	6	7	dnns	dnn	NOUN
cana-5634	6	8	)	)	PUNCT
cana-5634	6	9	were	be	AUX
cana-5634	6	10	constructed	construct	VERB
cana-5634	6	11	with	with	ADP
cana-5634	6	12	varied	varied	ADJ
cana-5634	6	13	architectures	architecture	NOUN
cana-5634	6	14	and	and	CCONJ
cana-5634	6	15	refined	refined	ADJ
cana-5634	6	16	using	use	VERB
cana-5634	6	17	advanced	advanced	ADJ
cana-5634	6	18	strategies	strategy	NOUN
cana-5634	6	19	such	such	ADJ
cana-5634	6	20	as	as	ADP
cana-5634	6	21	dynamic	dynamic	ADJ
cana-5634	6	22	learning	learning	NOUN
cana-5634	6	23	rate	rate	NOUN
cana-5634	6	24	scheduling	scheduling	NOUN
cana-5634	6	25	,	,	PUNCT
cana-5634	6	26	dropout	dropout	NOUN
cana-5634	6	27	regularization	regularization	NOUN
cana-5634	6	28	,	,	PUNCT
cana-5634	6	29	and	and	CCONJ
cana-5634	6	30	enhanced	enhance	VERB
cana-5634	6	31	adam	adam	PROPN
cana-5634	6	32	optimization	optimization	NOUN
cana-5634	6	33	to	to	PART
cana-5634	6	34	mitigate	mitigate	VERB
cana-5634	6	35	overfitting	overfitte	VERB
cana-5634	6	36	and	and	CCONJ
cana-5634	6	37	improve	improve	VERB
cana-5634	6	38	training	training	NOUN
cana-5634	6	39	efficacy	efficacy	NOUN
cana-5634	6	40	.	.	PUNCT
cana-5634	7	1	model	model	NOUN
cana-5634	7	2	performance	performance	NOUN
cana-5634	7	3	was	be	AUX
cana-5634	7	4	evaluated	evaluate	VERB
cana-5634	7	5	using	use	VERB
cana-5634	7	6	accuracy	accuracy	NOUN
cana-5634	7	7	,	,	PUNCT
cana-5634	7	8	precision	precision	NOUN
cana-5634	7	9	,	,	PUNCT
cana-5634	7	10	recall	recall	NOUN
cana-5634	7	11	,	,	PUNCT
cana-5634	7	12	f1	f1	NOUN
cana-5634	7	13	-	-	PUNCT
cana-5634	7	14	score	score	NOUN
cana-5634	7	15	,	,	PUNCT
cana-5634	7	16	and	and	CCONJ
cana-5634	7	17	the	the	DET
cana-5634	7	18	area	area	NOUN
cana-5634	7	19	under	under	ADP
cana-5634	7	20	the	the	DET
cana-5634	7	21	roc	roc	PROPN
cana-5634	7	22	curve	curve	NOUN
cana-5634	7	23	(	(	PUNCT
cana-5634	7	24	auc	auc	NOUN
cana-5634	7	25	-	-	PUNCT
cana-5634	7	26	roc	roc	NOUN
cana-5634	7	27	)	)	PUNCT
cana-5634	7	28	.	.	PUNCT
cana-5634	8	1	results	result	NOUN
cana-5634	8	2	demonstrate	demonstrate	VERB
cana-5634	8	3	that	that	SCONJ
cana-5634	8	4	while	while	SCONJ
cana-5634	8	5	traditional	traditional	ADJ
cana-5634	8	6	ml	ml	NOUN
cana-5634	8	7	models	model	NOUN
cana-5634	8	8	offer	offer	VERB
cana-5634	8	9	competitive	competitive	ADJ
cana-5634	8	10	performance	performance	NOUN
cana-5634	8	11	with	with	ADP
cana-5634	8	12	lower	low	ADJ
cana-5634	8	13	computational	computational	ADJ
cana-5634	8	14	overhead	overhead	NOUN
cana-5634	8	15	,	,	PUNCT
cana-5634	8	16	well	well	ADV
cana-5634	8	17	-	-	PUNCT
cana-5634	8	18	tuned	tune	VERB
cana-5634	8	19	dl	dl	PROPN
cana-5634	8	20	models	model	NOUN
cana-5634	8	21	deliver	deliver	VERB
cana-5634	8	22	superior	superior	ADJ
cana-5634	8	23	predictive	predictive	ADJ
cana-5634	8	24	accuracy	accuracy	NOUN
cana-5634	8	25	and	and	CCONJ
cana-5634	8	26	generalization	generalization	NOUN
cana-5634	8	27	on	on	ADP
cana-5634	8	28	unseen	unseen	ADJ
cana-5634	8	29	data	datum	NOUN
cana-5634	8	30	.	.	PUNCT
cana-5634	9	1	keywords	keyword	NOUN
cana-5634	9	2	:	:	PUNCT
cana-5634	9	3	alzheimer	alzheimer	PROPN
cana-5634	9	4	’s	’s	PART
cana-5634	9	5	disease	disease	NOUN
cana-5634	9	6	prediction	prediction	NOUN
cana-5634	9	7	,	,	PUNCT
cana-5634	9	8	machine	machine	NOUN
cana-5634	9	9	learning	learning	NOUN
cana-5634	9	10	,	,	PUNCT
cana-5634	9	11	deep	deep	ADJ
cana-5634	9	12	learning	learning	NOUN
cana-5634	9	13	,	,	PUNCT
cana-5634	9	14	hyperparameter	hyperparameter	NOUN
cana-5634	9	15	tuning	tuning	NOUN
cana-5634	9	16	,	,	PUNCT
cana-5634	9	17	deep	deep	ADJ
cana-5634	9	18	learning	learning	NOUN
cana-5634	9	19	,	,	PUNCT
cana-5634	9	20	and	and	CCONJ
cana-5634	9	21	optimization	optimization	NOUN
cana-5634	9	22	techniques	technique	NOUN
cana-5634	9	23	.	.	PUNCT
cana-5634	9	24	.	.	PUNCT
cana-5634	10	1	1	1	X
cana-5634	10	2	.	.	X
cana-5634	10	3	introduction	introduction	PROPN
cana-5634	10	4	alzheimer	alzheimer	PROPN
cana-5634	10	5	’s	’s	PART
cana-5634	10	6	disease	disease	NOUN
cana-5634	10	7	(	(	PUNCT
cana-5634	10	8	ad	ad	NOUN
cana-5634	10	9	)	)	PUNCT
cana-5634	10	10	is	be	AUX
cana-5634	10	11	a	a	DET
cana-5634	10	12	brain	brain	NOUN
cana-5634	10	13	disorder	disorder	NOUN
cana-5634	10	14	that	that	PRON
cana-5634	10	15	gradually	gradually	ADV
cana-5634	10	16	damages	damage	VERB
cana-5634	10	17	memory	memory	NOUN
cana-5634	10	18	,	,	PUNCT
cana-5634	10	19	thinking	thinking	NOUN
cana-5634	10	20	skills	skill	NOUN
cana-5634	10	21	,	,	PUNCT
cana-5634	10	22	and	and	CCONJ
cana-5634	10	23	behavior	behavior	NOUN
cana-5634	10	24	.	.	PUNCT
cana-5634	11	1	it	it	PRON
cana-5634	11	2	is	be	AUX
cana-5634	11	3	the	the	DET
cana-5634	11	4	leading	lead	VERB
cana-5634	11	5	cause	cause	NOUN
cana-5634	11	6	of	of	ADP
cana-5634	11	7	dementia	dementia	NOUN
cana-5634	11	8	and	and	CCONJ
cana-5634	11	9	poses	pose	VERB
cana-5634	11	10	a	a	DET
cana-5634	11	11	major	major	ADJ
cana-5634	11	12	health	health	NOUN
cana-5634	11	13	issue	issue	NOUN
cana-5634	11	14	worldwide	worldwide	ADV
cana-5634	11	15	,	,	PUNCT
cana-5634	11	16	especially	especially	ADV
cana-5634	11	17	as	as	SCONJ
cana-5634	11	18	the	the	DET
cana-5634	11	19	elderly	elderly	ADJ
cana-5634	11	20	population	population	NOUN
cana-5634	11	21	grows	grow	VERB
cana-5634	11	22	.	.	PUNCT
cana-5634	12	1	since	since	SCONJ
cana-5634	12	2	there	there	PRON
cana-5634	12	3	is	be	VERB
cana-5634	12	4	no	no	DET
cana-5634	12	5	known	know	VERB
cana-5634	12	6	cure	cure	NOUN
cana-5634	12	7	and	and	CCONJ
cana-5634	12	8	only	only	ADV
cana-5634	12	9	limited	limited	ADJ
cana-5634	12	10	treatment	treatment	NOUN
cana-5634	12	11	options	option	NOUN
cana-5634	12	12	,	,	PUNCT
cana-5634	12	13	finding	find	VERB
cana-5634	12	14	ways	way	NOUN
cana-5634	12	15	to	to	PART
cana-5634	12	16	predict	predict	VERB
cana-5634	12	17	the	the	DET
cana-5634	12	18	disease	disease	NOUN
cana-5634	12	19	early	early	ADV
cana-5634	12	20	is	be	AUX
cana-5634	12	21	very	very	ADV
cana-5634	12	22	important	important	ADJ
cana-5634	12	23	.	.	PUNCT
cana-5634	13	1	early	early	ADJ
cana-5634	13	2	detection	detection	NOUN
cana-5634	13	3	can	can	AUX
cana-5634	13	4	help	help	VERB
cana-5634	13	5	manage	manage	VERB
cana-5634	13	6	symptoms	symptom	NOUN
cana-5634	13	7	better	well	ADV
cana-5634	13	8	and	and	CCONJ
cana-5634	13	9	slow	slow	VERB
cana-5634	13	10	the	the	DET
cana-5634	13	11	progression	progression	NOUN
cana-5634	13	12	.	.	PUNCT
cana-5634	14	1	in	in	ADP
cana-5634	14	2	recent	recent	ADJ
cana-5634	14	3	years	year	NOUN
cana-5634	14	4	,	,	PUNCT
cana-5634	14	5	artificial	artificial	ADJ
cana-5634	14	6	intelligence	intelligence	NOUN
cana-5634	14	7	(	(	PUNCT
cana-5634	14	8	ai	ai	NOUN
cana-5634	14	9	)	)	PUNCT
cana-5634	14	10	has	have	AUX
cana-5634	14	11	played	play	VERB
cana-5634	14	12	a	a	DET
cana-5634	14	13	growing	grow	VERB
cana-5634	14	14	role	role	NOUN
cana-5634	14	15	in	in	ADP
cana-5634	14	16	healthcare	healthcare	PROPN
cana-5634	14	17	,	,	PUNCT
cana-5634	14	18	especially	especially	ADV
cana-5634	14	19	in	in	ADP
cana-5634	14	20	identifying	identify	VERB
cana-5634	14	21	and	and	CCONJ
cana-5634	14	22	predicting	predict	VERB
cana-5634	14	23	brain	brain	NOUN
cana-5634	14	24	disorders	disorder	NOUN
cana-5634	14	25	like	like	ADP
cana-5634	14	26	alzheimer	alzheimer	PROPN
cana-5634	14	27	’s	’s	PART
cana-5634	14	28	.	.	PUNCT
cana-5634	15	1	machine	machine	NOUN
cana-5634	15	2	learning	learning	NOUN
cana-5634	15	3	(	(	PUNCT
cana-5634	15	4	ml	ml	NOUN
cana-5634	15	5	)	)	PUNCT
cana-5634	15	6	and	and	CCONJ
cana-5634	15	7	deep	deep	ADJ
cana-5634	15	8	learning	learning	NOUN
cana-5634	15	9	(	(	PUNCT
cana-5634	15	10	dl	dl	PROPN
cana-5634	15	11	)	)	PUNCT
cana-5634	15	12	mailto:arumugammca848@gmail.com	mailto:arumugammca848@gmail.com	PROPN
cana-5634	15	13	mailto:drmuruganapcs@gmail.com	mailto:drmuruganapcs@gmail.com	NOUN
cana-5634	15	14	communications	communication	NOUN
cana-5634	15	15	on	on	ADP
cana-5634	15	16	applied	apply	VERB
cana-5634	15	17	nonlinear	nonlinear	ADJ
cana-5634	15	18	analysis	analysis	NOUN
cana-5634	15	19	issn	issn	NOUN
cana-5634	15	20	:	:	PUNCT
cana-5634	15	21	1074	1074	NUM
cana-5634	15	22	-	-	PUNCT
cana-5634	15	23	133x	133x	NUM
cana-5634	15	24	vol	vol	VERB
cana-5634	15	25	32	32	NUM
cana-5634	15	26	no.1s	no.1s	PROPN
cana-5634	15	27	(	(	PUNCT
cana-5634	15	28	2025	2025	NUM
cana-5634	15	29	)	)	PUNCT
cana-5634	15	30	671	671	NUM
cana-5634	15	31	https://internationalpubls.com	https://internationalpubls.com	X
cana-5634	15	32	have	have	AUX
cana-5634	15	33	shown	show	VERB
cana-5634	15	34	great	great	ADJ
cana-5634	15	35	potential	potential	NOUN
cana-5634	15	36	in	in	ADP
cana-5634	15	37	analyzing	analyze	VERB
cana-5634	15	38	medical	medical	ADJ
cana-5634	15	39	data	datum	NOUN
cana-5634	15	40	and	and	CCONJ
cana-5634	15	41	providing	provide	VERB
cana-5634	15	42	more	more	ADV
cana-5634	15	43	accurate	accurate	ADJ
cana-5634	15	44	predictions	prediction	NOUN
cana-5634	15	45	.	.	PUNCT
cana-5634	16	1	these	these	DET
cana-5634	16	2	techniques	technique	NOUN
cana-5634	16	3	are	be	AUX
cana-5634	16	4	able	able	ADJ
cana-5634	16	5	to	to	PART
cana-5634	16	6	uncover	uncover	VERB
cana-5634	16	7	hidden	hidden	ADJ
cana-5634	16	8	patterns	pattern	NOUN
cana-5634	16	9	in	in	ADP
cana-5634	16	10	both	both	CCONJ
cana-5634	16	11	clinical	clinical	ADJ
cana-5634	16	12	and	and	CCONJ
cana-5634	16	13	imaging	imaging	NOUN
cana-5634	16	14	data	datum	NOUN
cana-5634	16	15	,	,	PUNCT
cana-5634	16	16	helping	help	VERB
cana-5634	16	17	doctors	doctor	NOUN
cana-5634	16	18	make	make	VERB
cana-5634	16	19	better	well	ADJ
cana-5634	16	20	decisions	decision	NOUN
cana-5634	16	21	.	.	PUNCT
cana-5634	17	1	traditional	traditional	ADJ
cana-5634	17	2	ml	ml	NOUN
cana-5634	17	3	methods	method	NOUN
cana-5634	17	4	like	like	ADP
cana-5634	17	5	support	support	NOUN
cana-5634	17	6	vector	vector	NOUN
cana-5634	17	7	machines	machine	NOUN
cana-5634	17	8	(	(	PUNCT
cana-5634	17	9	svm	svm	PROPN
cana-5634	17	10	)	)	PUNCT
cana-5634	17	11	,	,	PUNCT
cana-5634	17	12	random	random	ADJ
cana-5634	17	13	forest	forest	NOUN
cana-5634	17	14	(	(	PUNCT
cana-5634	17	15	rf	rf	NOUN
cana-5634	17	16	)	)	PUNCT
cana-5634	17	17	,	,	PUNCT
cana-5634	17	18	and	and	CCONJ
cana-5634	17	19	gradient	gradient	ADJ
cana-5634	17	20	boosting	boost	VERB
cana-5634	17	21	machines	machine	NOUN
cana-5634	17	22	(	(	PUNCT
cana-5634	17	23	gbm	gbm	NOUN
cana-5634	17	24	)	)	PUNCT
cana-5634	17	25	have	have	AUX
cana-5634	17	26	been	be	AUX
cana-5634	17	27	successful	successful	ADJ
cana-5634	17	28	in	in	ADP
cana-5634	17	29	many	many	ADJ
cana-5634	17	30	medical	medical	ADJ
cana-5634	17	31	applications	application	NOUN
cana-5634	17	32	.	.	PUNCT
cana-5634	18	1	however	however	ADV
cana-5634	18	2	,	,	PUNCT
cana-5634	18	3	they	they	PRON
cana-5634	18	4	often	often	ADV
cana-5634	18	5	need	need	VERB
cana-5634	18	6	manual	manual	ADJ
cana-5634	18	7	work	work	NOUN
cana-5634	18	8	to	to	PART
cana-5634	18	9	choose	choose	VERB
cana-5634	18	10	and	and	CCONJ
cana-5634	18	11	fine	fine	ADJ
cana-5634	18	12	-	-	PUNCT
cana-5634	18	13	tune	tune	NOUN
cana-5634	18	14	features	feature	NOUN
cana-5634	18	15	.	.	PUNCT
cana-5634	19	1	on	on	ADP
cana-5634	19	2	the	the	DET
cana-5634	19	3	other	other	ADJ
cana-5634	19	4	hand	hand	NOUN
cana-5634	19	5	,	,	PUNCT
cana-5634	19	6	deep	deep	ADJ
cana-5634	19	7	learning	learning	NOUN
cana-5634	19	8	models	model	NOUN
cana-5634	19	9	such	such	ADJ
cana-5634	19	10	as	as	ADP
cana-5634	19	11	deep	deep	ADJ
cana-5634	19	12	neural	neural	ADJ
cana-5634	19	13	networks	network	NOUN
cana-5634	19	14	(	(	PUNCT
cana-5634	19	15	dnns	dnn	NOUN
cana-5634	19	16	)	)	PUNCT
cana-5634	19	17	can	can	AUX
cana-5634	19	18	automatically	automatically	ADV
cana-5634	19	19	learn	learn	VERB
cana-5634	19	20	useful	useful	ADJ
cana-5634	19	21	patterns	pattern	NOUN
cana-5634	19	22	from	from	ADP
cana-5634	19	23	data	datum	NOUN
cana-5634	19	24	,	,	PUNCT
cana-5634	19	25	and	and	CCONJ
cana-5634	19	26	when	when	SCONJ
cana-5634	19	27	trained	train	VERB
cana-5634	19	28	properly	properly	ADV
cana-5634	19	29	,	,	PUNCT
cana-5634	19	30	they	they	PRON
cana-5634	19	31	often	often	ADV
cana-5634	19	32	give	give	VERB
cana-5634	19	33	better	well	ADJ
cana-5634	19	34	results	result	NOUN
cana-5634	19	35	.	.	PUNCT
cana-5634	20	1	this	this	DET
cana-5634	20	2	study	study	NOUN
cana-5634	20	3	compares	compare	VERB
cana-5634	20	4	traditional	traditional	ADJ
cana-5634	20	5	ml	ml	NOUN
cana-5634	20	6	models	model	NOUN
cana-5634	20	7	and	and	CCONJ
cana-5634	20	8	deep	deep	ADJ
cana-5634	20	9	learning	learning	NOUN
cana-5634	20	10	approaches	approach	NOUN
cana-5634	20	11	for	for	ADP
cana-5634	20	12	predicting	predict	VERB
cana-5634	20	13	alzheimer	alzheimer	PROPN
cana-5634	20	14	’s	’s	PART
cana-5634	20	15	disease	disease	NOUN
cana-5634	20	16	using	use	VERB
cana-5634	20	17	the	the	DET
cana-5634	20	18	oasis	oasis	NOUN
cana-5634	20	19	cross	cross	ADJ
cana-5634	20	20	-	-	ADJ
cana-5634	20	21	sectional	sectional	ADJ
cana-5634	20	22	dataset	dataset	NOUN
cana-5634	20	23	.	.	PUNCT
cana-5634	21	1	we	we	PRON
cana-5634	21	2	applied	apply	VERB
cana-5634	21	3	hyperparameter	hyperparameter	NOUN
cana-5634	21	4	tuning	tune	VERB
cana-5634	21	5	to	to	PART
cana-5634	21	6	improve	improve	VERB
cana-5634	21	7	ml	ml	NOUN
cana-5634	21	8	models	model	NOUN
cana-5634	21	9	and	and	CCONJ
cana-5634	21	10	used	use	VERB
cana-5634	21	11	advanced	advanced	ADJ
cana-5634	21	12	training	training	NOUN
cana-5634	21	13	methods	method	NOUN
cana-5634	21	14	for	for	ADP
cana-5634	21	15	deep	deep	ADJ
cana-5634	21	16	learning	learning	NOUN
cana-5634	21	17	models	model	NOUN
cana-5634	21	18	.	.	PUNCT
cana-5634	22	1	our	our	PRON
cana-5634	22	2	goal	goal	NOUN
cana-5634	22	3	is	be	AUX
cana-5634	22	4	to	to	PART
cana-5634	22	5	find	find	VERB
cana-5634	22	6	which	which	DET
cana-5634	22	7	method	method	NOUN
cana-5634	22	8	works	work	VERB
cana-5634	22	9	best	well	ADV
cana-5634	22	10	for	for	ADP
cana-5634	22	11	accurate	accurate	ADJ
cana-5634	22	12	prediction	prediction	NOUN
cana-5634	22	13	.	.	PUNCT
cana-5634	23	1	the	the	DET
cana-5634	23	2	rest	rest	NOUN
cana-5634	23	3	of	of	ADP
cana-5634	23	4	the	the	DET
cana-5634	23	5	paper	paper	NOUN
cana-5634	23	6	is	be	AUX
cana-5634	23	7	organized	organize	VERB
cana-5634	23	8	as	as	SCONJ
cana-5634	23	9	follows	follow	VERB
cana-5634	23	10	:	:	PUNCT
cana-5634	23	11	section	section	PROPN
cana-5634	23	12	ii	ii	PROPN
cana-5634	23	13	reviews	review	VERB
cana-5634	23	14	related	relate	VERB
cana-5634	23	15	studies	study	NOUN
cana-5634	23	16	using	use	VERB
cana-5634	23	17	ml	ml	X
cana-5634	24	1	and	and	CCONJ
cana-5634	24	2	dl	dl	PROPN
cana-5634	24	3	in	in	ADP
cana-5634	24	4	alzheimer	alzheimer	PROPN
cana-5634	24	5	’s	’s	PART
cana-5634	24	6	diagnosis	diagnosis	NOUN
cana-5634	24	7	.	.	PUNCT
cana-5634	25	1	section	section	NOUN
cana-5634	25	2	iii	iii	PROPN
cana-5634	25	3	explains	explain	VERB
cana-5634	25	4	the	the	DET
cana-5634	25	5	methods	method	NOUN
cana-5634	25	6	used	use	VERB
cana-5634	25	7	,	,	PUNCT
cana-5634	25	8	including	include	VERB
cana-5634	25	9	data	data	NOUN
cana-5634	25	10	preparation	preparation	NOUN
cana-5634	25	11	,	,	PUNCT
cana-5634	25	12	model	model	NOUN
cana-5634	25	13	building	building	NOUN
cana-5634	25	14	,	,	PUNCT
cana-5634	25	15	and	and	CCONJ
cana-5634	25	16	evaluation	evaluation	NOUN
cana-5634	25	17	.	.	PUNCT
cana-5634	26	1	section	section	NOUN
cana-5634	26	2	iv	iv	NUM
cana-5634	26	3	discusses	discuss	VERB
cana-5634	26	4	the	the	DET
cana-5634	26	5	results	result	NOUN
cana-5634	26	6	.	.	PUNCT
cana-5634	27	1	section	section	NOUN
cana-5634	27	2	v	v	PROPN
cana-5634	27	3	concludes	conclude	VERB
cana-5634	27	4	the	the	DET
cana-5634	27	5	study	study	NOUN
cana-5634	27	6	and	and	CCONJ
cana-5634	27	7	outlines	outline	VERB
cana-5634	27	8	future	future	ADJ
cana-5634	27	9	work	work	NOUN
cana-5634	27	10	.	.	PUNCT
cana-5634	28	1	2	2	X
cana-5634	28	2	.	.	X
cana-5634	28	3	literature	literature	NOUN
cana-5634	28	4	review	review	VERB
cana-5634	28	5	many	many	ADJ
cana-5634	28	6	researchers	researcher	NOUN
cana-5634	28	7	have	have	AUX
cana-5634	28	8	studied	study	VERB
cana-5634	28	9	how	how	SCONJ
cana-5634	28	10	machine	machine	NOUN
cana-5634	28	11	learning	learning	NOUN
cana-5634	28	12	(	(	PUNCT
cana-5634	28	13	ml	ml	NOUN
cana-5634	28	14	)	)	PUNCT
cana-5634	28	15	and	and	CCONJ
cana-5634	28	16	deep	deep	ADJ
cana-5634	28	17	learning	learning	NOUN
cana-5634	28	18	(	(	PUNCT
cana-5634	28	19	dl	dl	INTJ
cana-5634	28	20	)	)	PUNCT
cana-5634	28	21	can	can	AUX
cana-5634	28	22	help	help	VERB
cana-5634	28	23	diagnose	diagnose	VERB
cana-5634	28	24	alzheimer	alzheimer	PROPN
cana-5634	28	25	’s	’s	PART
cana-5634	28	26	disease	disease	NOUN
cana-5634	28	27	(	(	PUNCT
cana-5634	28	28	ad	ad	NOUN
cana-5634	28	29	)	)	PUNCT
cana-5634	28	30	,	,	PUNCT
cana-5634	28	31	especially	especially	ADV
cana-5634	28	32	by	by	ADP
cana-5634	28	33	using	use	VERB
cana-5634	28	34	brain	brain	NOUN
cana-5634	28	35	scan	scan	NOUN
cana-5634	28	36	images	image	NOUN
cana-5634	28	37	like	like	ADP
cana-5634	28	38	mri	mri	NOUN
cana-5634	28	39	,	,	PUNCT
cana-5634	28	40	fmri	fmri	NOUN
cana-5634	28	41	,	,	PUNCT
cana-5634	28	42	and	and	CCONJ
cana-5634	28	43	patient	patient	ADJ
cana-5634	28	44	health	health	NOUN
cana-5634	28	45	records	record	NOUN
cana-5634	28	46	.	.	PUNCT
cana-5634	29	1	this	this	DET
cana-5634	29	2	section	section	NOUN
cana-5634	29	3	summarizes	summarize	VERB
cana-5634	29	4	25	25	NUM
cana-5634	29	5	important	important	ADJ
cana-5634	29	6	studies	study	NOUN
cana-5634	29	7	in	in	ADP
cana-5634	29	8	this	this	DET
cana-5634	29	9	field	field	NOUN
cana-5634	29	10	.	.	PUNCT
cana-5634	30	1	sarraf	sarraf	NOUN
cana-5634	30	2	and	and	CCONJ
cana-5634	30	3	tofighi	tofighi	NOUN
cana-5634	30	4	[	[	X
cana-5634	30	5	1	1	X
cana-5634	30	6	]	]	PUNCT
cana-5634	30	7	created	create	VERB
cana-5634	30	8	a	a	DET
cana-5634	30	9	cnn	cnn	PROPN
cana-5634	30	10	-	-	PUNCT
cana-5634	30	11	based	base	VERB
cana-5634	30	12	model	model	NOUN
cana-5634	30	13	called	call	VERB
cana-5634	30	14	deepad	deepad	PROPN
cana-5634	30	15	,	,	PUNCT
cana-5634	30	16	one	one	NUM
cana-5634	30	17	of	of	ADP
cana-5634	30	18	the	the	DET
cana-5634	30	19	earliest	early	ADJ
cana-5634	30	20	to	to	PART
cana-5634	30	21	use	use	VERB
cana-5634	30	22	brain	brain	NOUN
cana-5634	30	23	scans	scan	NOUN
cana-5634	30	24	for	for	ADP
cana-5634	30	25	detecting	detect	VERB
cana-5634	30	26	ad	ad	NOUN
cana-5634	30	27	.	.	PUNCT
cana-5634	31	1	their	their	PRON
cana-5634	31	2	model	model	NOUN
cana-5634	31	3	performed	perform	VERB
cana-5634	31	4	better	well	ADV
cana-5634	31	5	than	than	ADP
cana-5634	31	6	older	old	ADJ
cana-5634	31	7	ml	ml	NOUN
cana-5634	31	8	methods	method	NOUN
cana-5634	31	9	,	,	PUNCT
cana-5634	31	10	showing	show	VERB
cana-5634	31	11	the	the	DET
cana-5634	31	12	power	power	NOUN
cana-5634	31	13	of	of	ADP
cana-5634	31	14	dl	dl	PROPN
cana-5634	31	15	for	for	ADP
cana-5634	31	16	analyzing	analyze	VERB
cana-5634	31	17	medical	medical	ADJ
cana-5634	31	18	images	image	NOUN
cana-5634	31	19	.	.	PUNCT
cana-5634	32	1	other	other	ADJ
cana-5634	32	2	studies	study	NOUN
cana-5634	32	3	focused	focus	VERB
cana-5634	32	4	on	on	ADP
cana-5634	32	5	the	the	DET
cana-5634	32	6	strengths	strength	NOUN
cana-5634	32	7	of	of	ADP
cana-5634	32	8	traditional	traditional	ADJ
cana-5634	32	9	ml	ml	NOUN
cana-5634	32	10	.	.	PUNCT
cana-5634	32	11	ortiz	ortiz	PROPN
cana-5634	32	12	-	-	PUNCT
cana-5634	32	13	sanz	sanz	PROPN
cana-5634	32	14	et	et	PROPN
cana-5634	32	15	al	al	PROPN
cana-5634	32	16	.	.	PUNCT
cana-5634	33	1	[	[	X
cana-5634	33	2	2	2	NUM
cana-5634	33	3	]	]	PUNCT
cana-5634	33	4	used	use	VERB
cana-5634	33	5	support	support	NOUN
cana-5634	33	6	vector	vector	NOUN
cana-5634	33	7	machines	machine	NOUN
cana-5634	33	8	and	and	CCONJ
cana-5634	33	9	random	random	ADJ
cana-5634	33	10	forests	forest	NOUN
cana-5634	33	11	along	along	ADP
cana-5634	33	12	with	with	ADP
cana-5634	33	13	brain	brain	NOUN
cana-5634	33	14	scan	scan	PROPN
cana-5634	33	15	features	feature	NOUN
cana-5634	33	16	and	and	CCONJ
cana-5634	33	17	memory	memory	NOUN
cana-5634	33	18	scores	score	NOUN
cana-5634	33	19	.	.	PUNCT
cana-5634	34	1	these	these	DET
cana-5634	34	2	models	model	NOUN
cana-5634	34	3	performed	perform	VERB
cana-5634	34	4	well	well	ADV
cana-5634	34	5	,	,	PUNCT
cana-5634	34	6	especially	especially	ADV
cana-5634	34	7	after	after	ADP
cana-5634	34	8	being	be	AUX
cana-5634	34	9	tuned	tune	VERB
cana-5634	34	10	with	with	ADP
cana-5634	34	11	cross	cross	NOUN
cana-5634	34	12	-	-	NOUN
cana-5634	34	13	validation	validation	NOUN
cana-5634	34	14	.	.	PUNCT
cana-5634	35	1	likewise	likewise	ADV
cana-5634	35	2	,	,	PUNCT
cana-5634	35	3	basaia	basaia	PROPN
cana-5634	35	4	et	et	PROPN
cana-5634	35	5	al	al	PROPN
cana-5634	35	6	.	.	PUNCT
cana-5634	36	1	[	[	X
cana-5634	36	2	3	3	NUM
cana-5634	36	3	]	]	X
cana-5634	36	4	trained	train	VERB
cana-5634	36	5	deep	deep	ADJ
cana-5634	36	6	neural	neural	ADJ
cana-5634	36	7	networks	network	NOUN
cana-5634	36	8	on	on	ADP
cana-5634	36	9	mri	mri	NOUN
cana-5634	36	10	data	datum	NOUN
cana-5634	36	11	and	and	CCONJ
cana-5634	36	12	successfully	successfully	ADV
cana-5634	36	13	classified	classified	ADJ
cana-5634	36	14	patients	patient	NOUN
cana-5634	36	15	with	with	ADP
cana-5634	36	16	ad	ad	NOUN
cana-5634	36	17	,	,	PUNCT
cana-5634	36	18	mild	mild	ADJ
cana-5634	36	19	cognitive	cognitive	ADJ
cana-5634	36	20	impairment	impairment	NOUN
cana-5634	36	21	(	(	PUNCT
cana-5634	36	22	mci	mci	NOUN
cana-5634	36	23	)	)	PUNCT
cana-5634	36	24	,	,	PUNCT
cana-5634	36	25	and	and	CCONJ
cana-5634	36	26	healthy	healthy	ADJ
cana-5634	36	27	individuals	individual	NOUN
cana-5634	36	28	.	.	PUNCT
cana-5634	37	1	suk	suk	PROPN
cana-5634	37	2	et	et	PROPN
cana-5634	37	3	al	al	PROPN
cana-5634	37	4	.	.	PUNCT
cana-5634	38	1	[	[	X
cana-5634	38	2	4	4	X
cana-5634	38	3	]	]	PUNCT
cana-5634	38	4	and	and	CCONJ
cana-5634	38	5	suk	suk	PROPN
cana-5634	38	6	&	&	CCONJ
cana-5634	38	7	shen	shen	PROPN
cana-5634	39	1	[	[	X
cana-5634	39	2	19	19	NUM
cana-5634	39	3	]	]	PUNCT
cana-5634	39	4	tested	test	VERB
cana-5634	39	5	stacked	stack	VERB
cana-5634	39	6	autoencoders	autoencoder	NOUN
cana-5634	39	7	to	to	PART
cana-5634	39	8	improve	improve	VERB
cana-5634	39	9	feature	feature	NOUN
cana-5634	39	10	extraction	extraction	NOUN
cana-5634	39	11	from	from	ADP
cana-5634	39	12	brain	brain	NOUN
cana-5634	39	13	images	image	NOUN
cana-5634	39	14	.	.	PUNCT
cana-5634	40	1	these	these	DET
cana-5634	40	2	dl	dl	PROPN
cana-5634	40	3	methods	method	NOUN
cana-5634	40	4	worked	work	VERB
cana-5634	40	5	better	well	ADV
cana-5634	40	6	than	than	ADP
cana-5634	40	7	manually	manually	ADV
cana-5634	40	8	selected	select	VERB
cana-5634	40	9	features	feature	NOUN
cana-5634	40	10	,	,	PUNCT
cana-5634	40	11	making	make	VERB
cana-5634	40	12	predictions	prediction	NOUN
cana-5634	40	13	more	more	ADV
cana-5634	40	14	accurate	accurate	ADJ
cana-5634	40	15	.	.	PUNCT
cana-5634	41	1	jie	jie	PROPN
cana-5634	41	2	et	et	PROPN
cana-5634	41	3	al	al	PROPN
cana-5634	41	4	.	.	PUNCT
cana-5634	42	1	[	[	X
cana-5634	42	2	5	5	NUM
cana-5634	42	3	]	]	PUNCT
cana-5634	42	4	used	use	VERB
cana-5634	42	5	3d	3d	NUM
cana-5634	42	6	convolutional	convolutional	ADJ
cana-5634	42	7	networks	network	NOUN
cana-5634	42	8	to	to	PART
cana-5634	42	9	better	well	ADV
cana-5634	42	10	detect	detect	VERB
cana-5634	42	11	changes	change	NOUN
cana-5634	42	12	in	in	ADP
cana-5634	42	13	brain	brain	NOUN
cana-5634	42	14	volume	volume	NOUN
cana-5634	42	15	—	—	PUNCT
cana-5634	42	16	a	a	DET
cana-5634	42	17	key	key	ADJ
cana-5634	42	18	sign	sign	NOUN
cana-5634	42	19	of	of	ADP
cana-5634	42	20	alzheimer	alzheimer	PROPN
cana-5634	42	21	’s	’s	PART
cana-5634	42	22	.	.	PUNCT
cana-5634	43	1	zhang	zhang	PROPN
cana-5634	43	2	et	et	PROPN
cana-5634	43	3	al	al	PROPN
cana-5634	43	4	.	.	PUNCT
cana-5634	44	1	[	[	X
cana-5634	44	2	8	8	NUM
cana-5634	44	3	]	]	PUNCT
cana-5634	44	4	and	and	CCONJ
cana-5634	44	5	liu	liu	PROPN
cana-5634	44	6	et	et	PROPN
cana-5634	44	7	al	al	PROPN
cana-5634	44	8	.	.	PUNCT
cana-5634	45	1	[	[	X
cana-5634	45	2	11	11	NUM
cana-5634	45	3	]	]	PUNCT
cana-5634	45	4	combined	combine	VERB
cana-5634	45	5	different	different	ADJ
cana-5634	45	6	types	type	NOUN
cana-5634	45	7	of	of	ADP
cana-5634	45	8	imaging	imaging	NOUN
cana-5634	45	9	data	datum	NOUN
cana-5634	45	10	,	,	PUNCT
cana-5634	45	11	like	like	ADP
cana-5634	45	12	mri	mri	NOUN
cana-5634	45	13	and	and	CCONJ
cana-5634	45	14	fmri	fmri	NOUN
cana-5634	45	15	,	,	PUNCT
cana-5634	45	16	using	use	VERB
cana-5634	45	17	graph	graph	NOUN
cana-5634	45	18	-	-	PUNCT
cana-5634	45	19	based	base	VERB
cana-5634	45	20	and	and	CCONJ
cana-5634	45	21	stacking	stack	VERB
cana-5634	45	22	techniques	technique	NOUN
cana-5634	45	23	.	.	PUNCT
cana-5634	46	1	their	their	PRON
cana-5634	46	2	results	result	NOUN
cana-5634	46	3	showed	show	VERB
cana-5634	46	4	that	that	SCONJ
cana-5634	46	5	combining	combine	VERB
cana-5634	46	6	data	datum	NOUN
cana-5634	46	7	types	type	NOUN
cana-5634	46	8	improved	improve	VERB
cana-5634	46	9	the	the	DET
cana-5634	46	10	model	model	NOUN
cana-5634	46	11	’s	’s	PART
cana-5634	46	12	prediction	prediction	NOUN
cana-5634	46	13	power	power	NOUN
cana-5634	46	14	.	.	PUNCT
cana-5634	47	1	padilla	padilla	PROPN
cana-5634	47	2	et	et	PROPN
cana-5634	47	3	al	al	PROPN
cana-5634	47	4	.	.	PUNCT
cana-5634	48	1	[	[	X
cana-5634	48	2	9	9	NUM
cana-5634	48	3	]	]	PUNCT
cana-5634	48	4	also	also	ADV
cana-5634	48	5	applied	apply	VERB
cana-5634	48	6	ml	ml	ADP
cana-5634	48	7	on	on	ADP
cana-5634	48	8	the	the	DET
cana-5634	48	9	oasis	oasis	NOUN
cana-5634	48	10	dataset	dataset	NOUN
cana-5634	48	11	and	and	CCONJ
cana-5634	48	12	showed	show	VERB
cana-5634	48	13	that	that	SCONJ
cana-5634	48	14	selecting	select	VERB
cana-5634	48	15	the	the	DET
cana-5634	48	16	right	right	ADJ
cana-5634	48	17	features	feature	NOUN
cana-5634	48	18	improves	improve	VERB
cana-5634	48	19	accuracy	accuracy	NOUN
cana-5634	48	20	.	.	PUNCT
cana-5634	49	1	farooq	farooq	PROPN
cana-5634	49	2	et	et	PROPN
cana-5634	49	3	al	al	PROPN
cana-5634	49	4	.	.	PUNCT
cana-5634	50	1	[	[	X
cana-5634	50	2	6	6	NUM
cana-5634	50	3	]	]	PUNCT
cana-5634	50	4	and	and	CCONJ
cana-5634	50	5	esmaeilzadeh	esmaeilzadeh	VERB
cana-5634	50	6	et	et	PROPN
cana-5634	50	7	al	al	PROPN
cana-5634	50	8	.	.	PUNCT
cana-5634	51	1	[	[	X
cana-5634	51	2	10	10	NUM
cana-5634	51	3	]	]	PUNCT
cana-5634	51	4	worked	work	VERB
cana-5634	51	5	on	on	ADP
cana-5634	51	6	classifying	classify	VERB
cana-5634	51	7	ad	ad	NOUN
cana-5634	51	8	,	,	PUNCT
cana-5634	51	9	mci	mci	NOUN
cana-5634	51	10	,	,	PUNCT
cana-5634	51	11	and	and	CCONJ
cana-5634	51	12	healthy	healthy	ADJ
cana-5634	51	13	cases	case	NOUN
cana-5634	51	14	using	use	VERB
cana-5634	51	15	cnns	cnn	NOUN
cana-5634	51	16	and	and	CCONJ
cana-5634	51	17	mixed	mixed	ADJ
cana-5634	51	18	deep	deep	ADJ
cana-5634	51	19	learning	learning	NOUN
cana-5634	51	20	models	model	NOUN
cana-5634	51	21	.	.	PUNCT
cana-5634	52	1	they	they	PRON
cana-5634	52	2	used	use	VERB
cana-5634	52	3	techniques	technique	NOUN
cana-5634	52	4	like	like	ADP
cana-5634	52	5	dropout	dropout	NOUN
cana-5634	52	6	,	,	PUNCT
cana-5634	52	7	batch	batch	NOUN
cana-5634	52	8	normalization	normalization	NOUN
cana-5634	52	9	,	,	PUNCT
cana-5634	52	10	and	and	CCONJ
cana-5634	52	11	adaptive	adaptive	ADJ
cana-5634	52	12	learning	learning	NOUN
cana-5634	52	13	rates	rate	NOUN
cana-5634	52	14	to	to	PART
cana-5634	52	15	avoid	avoid	VERB
cana-5634	52	16	overfitting	overfitte	VERB
cana-5634	52	17	and	and	CCONJ
cana-5634	52	18	improve	improve	VERB
cana-5634	52	19	training	training	NOUN
cana-5634	52	20	.	.	PUNCT
cana-5634	53	1	zhang	zhang	PROPN
cana-5634	53	2	et	et	PROPN
cana-5634	53	3	al	al	PROPN
cana-5634	53	4	.	.	PUNCT
cana-5634	54	1	[	[	X
cana-5634	54	2	15	15	NUM
cana-5634	54	3	]	]	PUNCT
cana-5634	54	4	also	also	ADV
cana-5634	54	5	used	use	VERB
cana-5634	54	6	transfer	transfer	NOUN
cana-5634	54	7	learning	learn	VERB
cana-5634	54	8	to	to	PART
cana-5634	54	9	improve	improve	VERB
cana-5634	54	10	results	result	NOUN
cana-5634	54	11	while	while	SCONJ
cana-5634	54	12	saving	save	VERB
cana-5634	54	13	training	training	NOUN
cana-5634	54	14	time	time	NOUN
cana-5634	54	15	.	.	PUNCT
cana-5634	55	1	from	from	ADP
cana-5634	55	2	the	the	DET
cana-5634	55	3	ml	ml	NOUN
cana-5634	55	4	side	side	NOUN
cana-5634	55	5	,	,	PUNCT
cana-5634	55	6	decision	decision	NOUN
cana-5634	55	7	trees	tree	NOUN
cana-5634	55	8	and	and	CCONJ
cana-5634	55	9	ensemble	ensemble	ADJ
cana-5634	55	10	methods	method	NOUN
cana-5634	55	11	are	be	AUX
cana-5634	55	12	still	still	ADV
cana-5634	55	13	popular	popular	ADJ
cana-5634	55	14	for	for	ADP
cana-5634	55	15	their	their	PRON
cana-5634	55	16	ease	ease	NOUN
cana-5634	55	17	of	of	ADP
cana-5634	55	18	understanding	understanding	NOUN
cana-5634	55	19	.	.	PUNCT
cana-5634	56	1	liu	liu	PROPN
cana-5634	56	2	et	et	PROPN
cana-5634	56	3	al	al	PROPN
cana-5634	56	4	.	.	PUNCT
cana-5634	57	1	[	[	X
cana-5634	57	2	14	14	NUM
cana-5634	57	3	]	]	PUNCT
cana-5634	57	4	used	use	VERB
cana-5634	57	5	decision	decision	NOUN
cana-5634	57	6	trees	tree	NOUN
cana-5634	57	7	to	to	PART
cana-5634	57	8	find	find	VERB
cana-5634	57	9	early	early	ADJ
cana-5634	57	10	signs	sign	NOUN
cana-5634	57	11	of	of	ADP
cana-5634	57	12	memory	memory	NOUN
cana-5634	57	13	loss	loss	NOUN
cana-5634	57	14	,	,	PUNCT
cana-5634	57	15	while	while	SCONJ
cana-5634	57	16	lin	lin	PROPN
cana-5634	57	17	&	&	CCONJ
cana-5634	57	18	zhang	zhang	PROPN
cana-5634	58	1	[	[	X
cana-5634	58	2	24	24	NUM
cana-5634	58	3	]	]	PUNCT
cana-5634	58	4	applied	apply	VERB
cana-5634	58	5	boosting	boost	VERB
cana-5634	58	6	and	and	CCONJ
cana-5634	58	7	bagging	bagging	NOUN
cana-5634	58	8	methods	method	NOUN
cana-5634	58	9	,	,	PUNCT
cana-5634	58	10	which	which	PRON
cana-5634	58	11	gave	give	VERB
cana-5634	58	12	good	good	ADJ
cana-5634	58	13	results	result	NOUN
cana-5634	58	14	with	with	ADP
cana-5634	58	15	less	less	ADJ
cana-5634	58	16	computing	compute	VERB
cana-5634	58	17	power	power	NOUN
cana-5634	58	18	.	.	PUNCT
cana-5634	59	1	ahmed	ahmed	PROPN
cana-5634	59	2	et	et	PROPN
cana-5634	59	3	al	al	PROPN
cana-5634	59	4	.	.	PUNCT
cana-5634	60	1	[	[	X
cana-5634	60	2	16	16	NUM
cana-5634	60	3	]	]	PUNCT
cana-5634	60	4	and	and	CCONJ
cana-5634	60	5	jain	jain	PROPN
cana-5634	60	6	et	et	PROPN
cana-5634	60	7	al	al	PROPN
cana-5634	60	8	.	.	PUNCT
cana-5634	61	1	[	[	X
cana-5634	61	2	20	20	NUM
cana-5634	61	3	]	]	PUNCT
cana-5634	61	4	built	build	VERB
cana-5634	61	5	full	full	ADJ
cana-5634	61	6	pipelines	pipeline	NOUN
cana-5634	61	7	that	that	PRON
cana-5634	61	8	included	include	VERB
cana-5634	61	9	feature	feature	NOUN
cana-5634	61	10	selection	selection	NOUN
cana-5634	61	11	and	and	CCONJ
cana-5634	61	12	data	datum	NOUN
cana-5634	61	13	augmentation	augmentation	NOUN
cana-5634	61	14	,	,	PUNCT
cana-5634	61	15	which	which	PRON
cana-5634	61	16	helped	help	VERB
cana-5634	61	17	improve	improve	VERB
cana-5634	61	18	early	early	ADJ
cana-5634	61	19	diagnosis	diagnosis	NOUN
cana-5634	61	20	.	.	PUNCT
cana-5634	62	1	ravi	ravi	NOUN
cana-5634	62	2	and	and	CCONJ
cana-5634	62	3	karthik	karthik	PROPN
cana-5634	63	1	[	[	X
cana-5634	63	2	23	23	NUM
cana-5634	63	3	]	]	PUNCT
cana-5634	63	4	compared	compare	VERB
cana-5634	63	5	deep	deep	ADJ
cana-5634	63	6	and	and	CCONJ
cana-5634	63	7	traditional	traditional	ADJ
cana-5634	63	8	models	model	NOUN
cana-5634	63	9	and	and	CCONJ
cana-5634	63	10	found	find	VERB
cana-5634	63	11	that	that	SCONJ
cana-5634	63	12	while	while	SCONJ
cana-5634	63	13	deep	deep	ADJ
cana-5634	63	14	models	model	NOUN
cana-5634	63	15	are	be	AUX
cana-5634	63	16	powerful	powerful	ADJ
cana-5634	63	17	,	,	PUNCT
cana-5634	63	18	classical	classical	ADJ
cana-5634	63	19	methods	method	NOUN
cana-5634	63	20	can	can	AUX
cana-5634	63	21	also	also	ADV
cana-5634	63	22	perform	perform	VERB
cana-5634	63	23	well	well	ADV
cana-5634	63	24	with	with	ADP
cana-5634	63	25	the	the	DET
cana-5634	63	26	right	right	ADJ
cana-5634	63	27	tuning	tuning	NOUN
cana-5634	63	28	.	.	PUNCT
cana-5634	64	1	overviews	overview	NOUN
cana-5634	64	2	by	by	ADP
cana-5634	64	3	razzak	razzak	PROPN
cana-5634	64	4	et	et	PROPN
cana-5634	64	5	al	al	PROPN
cana-5634	64	6	.	.	PUNCT
cana-5634	65	1	[	[	X
cana-5634	65	2	25	25	NUM
cana-5634	65	3	]	]	PUNCT
cana-5634	65	4	and	and	CCONJ
cana-5634	65	5	communications	communication	NOUN
cana-5634	65	6	on	on	ADP
cana-5634	65	7	applied	apply	VERB
cana-5634	65	8	nonlinear	nonlinear	ADJ
cana-5634	65	9	analysis	analysis	NOUN
cana-5634	65	10	issn	issn	NOUN
cana-5634	65	11	:	:	PUNCT
cana-5634	65	12	1074	1074	NUM
cana-5634	65	13	-	-	PUNCT
cana-5634	65	14	133x	133x	NUM
cana-5634	65	15	vol	vol	VERB
cana-5634	65	16	32	32	NUM
cana-5634	65	17	no.1s	no.1s	PROPN
cana-5634	65	18	(	(	PUNCT
cana-5634	65	19	2025	2025	NUM
cana-5634	65	20	)	)	PUNCT
cana-5634	65	21	672	672	NUM
cana-5634	65	22	https://internationalpubls.com	https://internationalpubls.com	X
cana-5634	65	23	salvatore	salvatore	NOUN
cana-5634	65	24	et	et	PROPN
cana-5634	65	25	al	al	PROPN
cana-5634	65	26	.	.	PUNCT
cana-5634	66	1	[	[	X
cana-5634	66	2	7	7	X
cana-5634	66	3	]	]	PUNCT
cana-5634	66	4	discussed	discuss	VERB
cana-5634	66	5	challenges	challenge	NOUN
cana-5634	66	6	like	like	ADP
cana-5634	66	7	limited	limited	ADJ
cana-5634	66	8	data	datum	NOUN
cana-5634	66	9	and	and	CCONJ
cana-5634	66	10	model	model	NOUN
cana-5634	66	11	transparency	transparency	NOUN
cana-5634	66	12	,	,	PUNCT
cana-5634	66	13	and	and	CCONJ
cana-5634	66	14	recommended	recommend	VERB
cana-5634	66	15	using	use	VERB
cana-5634	66	16	explainable	explainable	ADJ
cana-5634	66	17	ai	ai	NOUN
cana-5634	66	18	(	(	PUNCT
cana-5634	66	19	xai	xai	PROPN
cana-5634	66	20	)	)	PUNCT
cana-5634	66	21	for	for	ADP
cana-5634	66	22	better	well	ADJ
cana-5634	66	23	trust	trust	NOUN
cana-5634	66	24	in	in	ADP
cana-5634	66	25	predictions	prediction	NOUN
cana-5634	66	26	.	.	PUNCT
cana-5634	67	1	bron	bron	PROPN
cana-5634	67	2	et	et	PROPN
cana-5634	67	3	al	al	PROPN
cana-5634	67	4	.	.	PUNCT
cana-5634	68	1	[	[	X
cana-5634	68	2	21	21	NUM
cana-5634	68	3	]	]	PUNCT
cana-5634	68	4	created	create	VERB
cana-5634	68	5	a	a	DET
cana-5634	68	6	standard	standard	ADJ
cana-5634	68	7	dataset	dataset	NOUN
cana-5634	68	8	and	and	CCONJ
cana-5634	68	9	benchmarks	benchmark	NOUN
cana-5634	68	10	for	for	ADP
cana-5634	68	11	ad	ad	NOUN
cana-5634	68	12	detection	detection	NOUN
cana-5634	68	13	,	,	PUNCT
cana-5634	68	14	which	which	PRON
cana-5634	68	15	many	many	ADJ
cana-5634	68	16	studies	study	NOUN
cana-5634	68	17	now	now	ADV
cana-5634	68	18	follow	follow	VERB
cana-5634	68	19	for	for	ADP
cana-5634	68	20	consistent	consistent	ADJ
cana-5634	68	21	evaluation	evaluation	NOUN
cana-5634	68	22	.	.	PUNCT
cana-5634	69	1	brosch	brosch	PROPN
cana-5634	69	2	and	and	CCONJ
cana-5634	69	3	tam	tam	X
cana-5634	69	4	[	[	X
cana-5634	69	5	17	17	NUM
cana-5634	69	6	]	]	PUNCT
cana-5634	69	7	tackled	tackle	VERB
cana-5634	69	8	small	small	ADJ
cana-5634	69	9	dataset	dataset	NOUN
cana-5634	69	10	problems	problem	NOUN
cana-5634	69	11	by	by	ADP
cana-5634	69	12	using	use	VERB
cana-5634	69	13	unsupervised	unsupervised	ADJ
cana-5634	69	14	learning	learning	NOUN
cana-5634	69	15	and	and	CCONJ
cana-5634	69	16	dimensionality	dimensionality	NOUN
cana-5634	69	17	reduction	reduction	NOUN
cana-5634	69	18	,	,	PUNCT
cana-5634	69	19	helping	help	VERB
cana-5634	69	20	models	model	NOUN
cana-5634	69	21	avoid	avoid	VERB
cana-5634	69	22	overfitting	overfitte	VERB
cana-5634	69	23	.	.	PUNCT
cana-5634	70	1	lastly	lastly	ADV
cana-5634	70	2	,	,	PUNCT
cana-5634	70	3	wang	wang	PROPN
cana-5634	70	4	et	et	PROPN
cana-5634	70	5	al	al	PROPN
cana-5634	70	6	.	.	PUNCT
cana-5634	71	1	[	[	X
cana-5634	71	2	12	12	NUM
cana-5634	71	3	]	]	PUNCT
cana-5634	71	4	and	and	CCONJ
cana-5634	71	5	vieira	vieira	PROPN
cana-5634	71	6	et	et	PROPN
cana-5634	71	7	al	al	PROPN
cana-5634	71	8	.	.	PUNCT
cana-5634	72	1	[	[	X
cana-5634	72	2	13	13	NUM
cana-5634	72	3	]	]	PUNCT
cana-5634	72	4	looked	look	VERB
cana-5634	72	5	at	at	ADP
cana-5634	72	6	how	how	SCONJ
cana-5634	72	7	well	well	ADV
cana-5634	72	8	dl	dl	PROPN
cana-5634	72	9	models	model	NOUN
cana-5634	72	10	work	work	VERB
cana-5634	72	11	across	across	ADP
cana-5634	72	12	different	different	ADJ
cana-5634	72	13	groups	group	NOUN
cana-5634	72	14	of	of	ADP
cana-5634	72	15	people	people	NOUN
cana-5634	72	16	.	.	PUNCT
cana-5634	73	1	they	they	PRON
cana-5634	73	2	stressed	stress	VERB
cana-5634	73	3	the	the	DET
cana-5634	73	4	need	need	NOUN
cana-5634	73	5	for	for	ADP
cana-5634	73	6	more	more	ADV
cana-5634	73	7	diverse	diverse	ADJ
cana-5634	73	8	training	training	NOUN
cana-5634	73	9	data	datum	NOUN
cana-5634	73	10	to	to	PART
cana-5634	73	11	make	make	VERB
cana-5634	73	12	models	model	NOUN
cana-5634	73	13	useful	useful	ADJ
cana-5634	73	14	in	in	ADP
cana-5634	73	15	real	real	ADJ
cana-5634	73	16	-	-	PUNCT
cana-5634	73	17	world	world	NOUN
cana-5634	73	18	settings	setting	NOUN
cana-5634	73	19	.	.	PUNCT
cana-5634	74	1	in	in	ADP
cana-5634	74	2	summary	summary	NOUN
cana-5634	74	3	,	,	PUNCT
cana-5634	74	4	this	this	DET
cana-5634	74	5	literature	literature	NOUN
cana-5634	74	6	review	review	NOUN
cana-5634	74	7	shows	show	VERB
cana-5634	74	8	the	the	DET
cana-5634	74	9	shift	shift	NOUN
cana-5634	74	10	from	from	ADP
cana-5634	74	11	traditional	traditional	ADJ
cana-5634	74	12	ml	ml	ADP
cana-5634	74	13	approaches	approach	NOUN
cana-5634	74	14	to	to	ADP
cana-5634	74	15	modern	modern	ADJ
cana-5634	74	16	dl	dl	PROPN
cana-5634	74	17	models	model	NOUN
cana-5634	74	18	in	in	ADP
cana-5634	74	19	alzheimer	alzheimer	PROPN
cana-5634	74	20	’s	’s	PART
cana-5634	74	21	prediction	prediction	NOUN
cana-5634	74	22	.	.	PUNCT
cana-5634	75	1	while	while	SCONJ
cana-5634	75	2	deep	deep	ADJ
cana-5634	75	3	learning	learning	NOUN
cana-5634	75	4	often	often	ADV
cana-5634	75	5	performs	perform	VERB
cana-5634	75	6	better	well	ADJ
cana-5634	75	7	,	,	PUNCT
cana-5634	75	8	traditional	traditional	ADJ
cana-5634	75	9	methods	method	NOUN
cana-5634	75	10	are	be	AUX
cana-5634	75	11	still	still	ADV
cana-5634	75	12	useful	useful	ADJ
cana-5634	75	13	—	—	PUNCT
cana-5634	75	14	especially	especially	ADV
cana-5634	75	15	when	when	SCONJ
cana-5634	75	16	using	use	VERB
cana-5634	75	17	structured	structured	ADJ
cana-5634	75	18	data	datum	NOUN
cana-5634	75	19	and	and	CCONJ
cana-5634	75	20	good	good	ADJ
cana-5634	75	21	tuning	tuning	NOUN
cana-5634	75	22	methods	method	NOUN
cana-5634	75	23	.	.	PUNCT
cana-5634	76	1	this	this	PRON
cana-5634	76	2	supports	support	VERB
cana-5634	76	3	our	our	PRON
cana-5634	76	4	study	study	NOUN
cana-5634	76	5	’s	’s	PART
cana-5634	76	6	goal	goal	NOUN
cana-5634	76	7	to	to	PART
cana-5634	76	8	compare	compare	VERB
cana-5634	76	9	both	both	DET
cana-5634	76	10	approaches	approach	NOUN
cana-5634	76	11	using	use	VERB
cana-5634	76	12	the	the	DET
cana-5634	76	13	oasis	oasis	NOUN
cana-5634	76	14	dataset	dataset	NOUN
cana-5634	76	15	.	.	PUNCT
cana-5634	77	1	the	the	DET
cana-5634	77	2	classification	classification	NOUN
cana-5634	77	3	methods	method	NOUN
cana-5634	77	4	used	use	VERB
cana-5634	77	5	include	include	VERB
cana-5634	77	6	j48	j48	PROPN
cana-5634	77	7	,	,	PUNCT
cana-5634	77	8	random	random	ADJ
cana-5634	77	9	tree	tree	NOUN
cana-5634	77	10	(	(	PUNCT
cana-5634	77	11	rt	rt	NOUN
cana-5634	77	12	)	)	PUNCT
cana-5634	77	13	,	,	PUNCT
cana-5634	77	14	decision	decision	NOUN
cana-5634	77	15	stump	stump	NOUN
cana-5634	77	16	(	(	PUNCT
cana-5634	77	17	ds	ds	NOUN
cana-5634	77	18	)	)	PUNCT
cana-5634	77	19	,	,	PUNCT
cana-5634	77	20	logistic	logistic	ADJ
cana-5634	77	21	model	model	NOUN
cana-5634	77	22	tree	tree	NOUN
cana-5634	77	23	(	(	PUNCT
cana-5634	77	24	lmt	lmt	PROPN
cana-5634	77	25	)	)	PUNCT
cana-5634	77	26	,	,	PUNCT
cana-5634	77	27	hoeffding	hoeffde	VERB
cana-5634	77	28	tree	tree	NOUN
cana-5634	77	29	(	(	PUNCT
cana-5634	77	30	ht	ht	PROPN
cana-5634	77	31	)	)	PUNCT
cana-5634	77	32	,	,	PUNCT
cana-5634	77	33	reduced	reduce	VERB
cana-5634	77	34	error	error	NOUN
cana-5634	77	35	pruning	pruning	NOUN
cana-5634	77	36	(	(	PUNCT
cana-5634	77	37	rep	rep	NOUN
cana-5634	77	38	)	)	PUNCT
cana-5634	77	39	,	,	PUNCT
cana-5634	77	40	and	and	CCONJ
cana-5634	77	41	random	random	ADJ
cana-5634	77	42	forest	forest	NOUN
cana-5634	77	43	(	(	PUNCT
cana-5634	77	44	rf	rf	NOUN
cana-5634	77	45	)	)	PUNCT
cana-5634	77	46	,	,	PUNCT
cana-5634	77	47	and	and	CCONJ
cana-5634	77	48	their	their	PRON
cana-5634	77	49	accuracies	accuracy	NOUN
cana-5634	77	50	are	be	AUX
cana-5634	77	51	assessed	assess	VERB
cana-5634	77	52	[	[	X
cana-5634	77	53	26	26	NUM
cana-5634	77	54	]	]	PUNCT
cana-5634	77	55	and	and	CCONJ
cana-5634	77	56	the	the	DET
cana-5634	77	57	similar	similar	ADJ
cana-5634	77	58	paper	paper	NOUN
cana-5634	77	59	analysis	analysis	NOUN
cana-5634	77	60	using	use	VERB
cana-5634	77	61	medical	medical	ADJ
cana-5634	77	62	related	related	ADJ
cana-5634	77	63	research	research	NOUN
cana-5634	77	64	using	use	VERB
cana-5634	77	65	same	same	ADJ
cana-5634	77	66	approaches	approach	NOUN
cana-5634	77	67	using	use	VERB
cana-5634	77	68	data	datum	NOUN
cana-5634	77	69	mining	mining	NOUN
cana-5634	77	70	and	and	CCONJ
cana-5634	77	71	machine	machine	NOUN
cana-5634	77	72	learning	learn	VERB
cana-5634	77	73	algorithms	algorithm	NOUN
cana-5634	77	74	[	[	X
cana-5634	77	75	27	27	NUM
cana-5634	77	76	]	]	PUNCT
cana-5634	77	77	.	.	PUNCT
cana-5634	78	1	ravishankar	ravishankar	NOUN
cana-5634	78	2	and	and	CCONJ
cana-5634	78	3	rajesh	rajesh	PROPN
cana-5634	79	1	[	[	X
cana-5634	79	2	28	28	NUM
cana-5634	79	3	]	]	PUNCT
cana-5634	79	4	studied	study	VERB
cana-5634	79	5	the	the	DET
cana-5634	79	6	impact	impact	NOUN
cana-5634	79	7	of	of	ADP
cana-5634	79	8	selecting	select	VERB
cana-5634	79	9	important	important	ADJ
cana-5634	79	10	variables	variable	NOUN
cana-5634	79	11	from	from	ADP
cana-5634	79	12	climate	climate	NOUN
cana-5634	79	13	change	change	NOUN
cana-5634	79	14	datasets	dataset	NOUN
cana-5634	79	15	and	and	CCONJ
cana-5634	79	16	how	how	SCONJ
cana-5634	79	17	this	this	PRON
cana-5634	79	18	affects	affect	VERB
cana-5634	79	19	prediction	prediction	NOUN
cana-5634	79	20	accuracy	accuracy	NOUN
cana-5634	79	21	.	.	PUNCT
cana-5634	80	1	they	they	PRON
cana-5634	80	2	applied	apply	VERB
cana-5634	80	3	different	different	ADJ
cana-5634	80	4	data	datum	NOUN
cana-5634	80	5	mining	mining	NOUN
cana-5634	80	6	techniques	technique	NOUN
cana-5634	80	7	along	along	ADP
cana-5634	80	8	with	with	ADP
cana-5634	80	9	machine	machine	NOUN
cana-5634	80	10	learning	learning	NOUN
cana-5634	80	11	models	model	NOUN
cana-5634	80	12	to	to	PART
cana-5634	80	13	understand	understand	VERB
cana-5634	80	14	climate	climate	NOUN
cana-5634	80	15	patterns	pattern	NOUN
cana-5634	80	16	.	.	PUNCT
cana-5634	81	1	in	in	ADP
cana-5634	81	2	another	another	DET
cana-5634	81	3	related	relate	VERB
cana-5634	81	4	study	study	NOUN
cana-5634	81	5	,	,	PUNCT
cana-5634	81	6	ravishankar	ravishankar	NOUN
cana-5634	81	7	and	and	CCONJ
cana-5634	81	8	rajesh	rajesh	PROPN
cana-5634	81	9	[	[	X
cana-5634	81	10	29	29	NUM
cana-5634	81	11	]	]	PUNCT
cana-5634	81	12	extended	extend	VERB
cana-5634	81	13	their	their	PRON
cana-5634	81	14	research	research	NOUN
cana-5634	81	15	using	use	VERB
cana-5634	81	16	a	a	DET
cana-5634	81	17	global	global	ADJ
cana-5634	81	18	weather	weather	NOUN
cana-5634	81	19	repository	repository	NOUN
cana-5634	81	20	to	to	PART
cana-5634	81	21	predict	predict	VERB
cana-5634	81	22	climate	climate	NOUN
cana-5634	81	23	change	change	NOUN
cana-5634	81	24	indicators	indicator	NOUN
cana-5634	81	25	more	more	ADV
cana-5634	81	26	effectively	effectively	ADV
cana-5634	81	27	.	.	PUNCT
cana-5634	82	1	they	they	PRON
cana-5634	82	2	used	use	VERB
cana-5634	82	3	data	data	NOUN
cana-5634	82	4	mining	mining	NOUN
cana-5634	82	5	tools	tool	NOUN
cana-5634	82	6	combined	combine	VERB
cana-5634	82	7	with	with	ADP
cana-5634	82	8	advanced	advanced	ADJ
cana-5634	82	9	machine	machine	NOUN
cana-5634	82	10	learning	learning	NOUN
cana-5634	82	11	methods	method	NOUN
cana-5634	82	12	to	to	PART
cana-5634	82	13	process	process	VERB
cana-5634	82	14	large	large	ADJ
cana-5634	82	15	-	-	PUNCT
cana-5634	82	16	scale	scale	NOUN
cana-5634	82	17	environmental	environmental	ADJ
cana-5634	82	18	data	datum	NOUN
cana-5634	82	19	.	.	PUNCT
cana-5634	83	1	ravishankar	ravishankar	NOUN
cana-5634	83	2	and	and	CCONJ
cana-5634	83	3	rajesh	rajesh	PROPN
cana-5634	84	1	[	[	X
cana-5634	84	2	30	30	NUM
cana-5634	84	3	]	]	PUNCT
cana-5634	84	4	carried	carry	VERB
cana-5634	84	5	out	out	ADP
cana-5634	84	6	a	a	DET
cana-5634	84	7	detailed	detailed	ADJ
cana-5634	84	8	study	study	NOUN
cana-5634	84	9	on	on	ADP
cana-5634	84	10	analyzing	analyze	VERB
cana-5634	84	11	climate	climate	NOUN
cana-5634	84	12	change	change	NOUN
cana-5634	84	13	datasets	dataset	NOUN
cana-5634	84	14	in	in	ADP
cana-5634	84	15	relation	relation	NOUN
cana-5634	84	16	to	to	ADP
cana-5634	84	17	the	the	DET
cana-5634	84	18	air	air	NOUN
cana-5634	84	19	quality	quality	PROPN
cana-5634	84	20	index	index	NOUN
cana-5634	84	21	(	(	PUNCT
cana-5634	84	22	aqi	aqi	PROPN
cana-5634	84	23	)	)	PUNCT
cana-5634	84	24	using	use	VERB
cana-5634	84	25	data	datum	NOUN
cana-5634	84	26	mining	mining	NOUN
cana-5634	84	27	and	and	CCONJ
cana-5634	84	28	machine	machine	NOUN
cana-5634	84	29	learning	learn	VERB
cana-5634	84	30	techniques	technique	NOUN
cana-5634	84	31	.	.	PUNCT
cana-5634	85	1	their	their	PRON
cana-5634	85	2	research	research	NOUN
cana-5634	85	3	focused	focus	VERB
cana-5634	85	4	on	on	ADP
cana-5634	85	5	understanding	understand	VERB
cana-5634	85	6	how	how	SCONJ
cana-5634	85	7	different	different	ADJ
cana-5634	85	8	environmental	environmental	ADJ
cana-5634	85	9	parameters	parameter	NOUN
cana-5634	85	10	contribute	contribute	VERB
cana-5634	85	11	to	to	ADP
cana-5634	85	12	aqi	aqi	PROPN
cana-5634	85	13	levels	level	NOUN
cana-5634	85	14	.	.	PUNCT
cana-5634	86	1	by	by	ADP
cana-5634	86	2	applying	apply	VERB
cana-5634	86	3	classification	classification	NOUN
cana-5634	86	4	and	and	CCONJ
cana-5634	86	5	regression	regression	NOUN
cana-5634	86	6	models	model	NOUN
cana-5634	86	7	,	,	PUNCT
cana-5634	86	8	they	they	PRON
cana-5634	86	9	demonstrated	demonstrate	VERB
cana-5634	86	10	how	how	SCONJ
cana-5634	86	11	machine	machine	NOUN
cana-5634	86	12	learning	learning	NOUN
cana-5634	86	13	can	can	AUX
cana-5634	86	14	accurately	accurately	ADV
cana-5634	86	15	predict	predict	VERB
cana-5634	86	16	air	air	NOUN
cana-5634	86	17	quality	quality	NOUN
cana-5634	86	18	trends	trend	NOUN
cana-5634	86	19	.	.	PUNCT
cana-5634	87	1	santhoshkumar	santhoshkumar	NOUN
cana-5634	87	2	and	and	CCONJ
cana-5634	87	3	rajesh	rajesh	PROPN
cana-5634	88	1	[	[	X
cana-5634	88	2	31	31	NUM
cana-5634	88	3	]	]	PUNCT
cana-5634	88	4	explored	explore	VERB
cana-5634	88	5	how	how	SCONJ
cana-5634	88	6	machine	machine	NOUN
cana-5634	88	7	learning	learn	VERB
cana-5634	88	8	techniques	technique	NOUN
cana-5634	88	9	can	can	AUX
cana-5634	88	10	be	be	AUX
cana-5634	88	11	used	use	VERB
cana-5634	88	12	to	to	PART
cana-5634	88	13	analyze	analyze	VERB
cana-5634	88	14	the	the	DET
cana-5634	88	15	connection	connection	NOUN
cana-5634	88	16	between	between	ADP
cana-5634	88	17	various	various	ADJ
cana-5634	88	18	types	type	NOUN
cana-5634	88	19	of	of	ADP
cana-5634	88	20	energy	energy	NOUN
cana-5634	88	21	usage	usage	NOUN
cana-5634	88	22	and	and	CCONJ
cana-5634	88	23	the	the	DET
cana-5634	88	24	sustainable	sustainable	ADJ
cana-5634	88	25	development	development	NOUN
cana-5634	88	26	goals	goal	NOUN
cana-5634	88	27	(	(	PUNCT
cana-5634	88	28	sdgs	sdgs	ADJ
cana-5634	88	29	)	)	PUNCT
cana-5634	88	30	.	.	PUNCT
cana-5634	89	1	their	their	PRON
cana-5634	89	2	study	study	NOUN
cana-5634	89	3	applied	apply	VERB
cana-5634	89	4	predictive	predictive	ADJ
cana-5634	89	5	modeling	modeling	NOUN
cana-5634	89	6	to	to	PART
cana-5634	89	7	identify	identify	VERB
cana-5634	89	8	how	how	SCONJ
cana-5634	89	9	changes	change	NOUN
cana-5634	89	10	in	in	ADP
cana-5634	89	11	energy	energy	NOUN
cana-5634	89	12	consumption	consumption	NOUN
cana-5634	89	13	patterns	pattern	NOUN
cana-5634	89	14	affect	affect	VERB
cana-5634	89	15	progress	progress	NOUN
cana-5634	89	16	toward	toward	ADP
cana-5634	89	17	sdg	sdg	NOUN
cana-5634	89	18	targets	target	NOUN
cana-5634	89	19	.	.	PUNCT
cana-5634	90	1	2.1	2.1	NUM
cana-5634	90	2	.	.	PUNCT
cana-5634	91	1	dataset	dataset	ADJ
cana-5634	91	2	description	description	NOUN
cana-5634	91	3	the	the	DET
cana-5634	91	4	oasis	oasis	NOUN
cana-5634	91	5	(	(	PUNCT
cana-5634	91	6	open	open	ADJ
cana-5634	91	7	access	access	NOUN
cana-5634	91	8	series	series	NOUN
cana-5634	91	9	of	of	ADP
cana-5634	91	10	imaging	imaging	NOUN
cana-5634	91	11	studies	study	NOUN
cana-5634	91	12	)	)	PUNCT
cana-5634	91	13	cross	cross	ADJ
cana-5634	91	14	-	-	ADJ
cana-5634	91	15	sectional	sectional	ADJ
cana-5634	91	16	dataset	dataset	NOUN
cana-5634	91	17	is	be	AUX
cana-5634	91	18	a	a	DET
cana-5634	91	19	publicly	publicly	ADV
cana-5634	91	20	available	available	ADJ
cana-5634	91	21	resource	resource	NOUN
cana-5634	91	22	designed	design	VERB
cana-5634	91	23	for	for	ADP
cana-5634	91	24	alzheimer	alzheimer	PROPN
cana-5634	91	25	’s	’s	PART
cana-5634	91	26	disease	disease	NOUN
cana-5634	91	27	research	research	NOUN
cana-5634	91	28	.	.	PUNCT
cana-5634	92	1	it	it	PRON
cana-5634	92	2	comprises	comprise	VERB
cana-5634	92	3	mri	mri	NOUN
cana-5634	92	4	data	datum	NOUN
cana-5634	92	5	and	and	CCONJ
cana-5634	92	6	associates	associate	NOUN
cana-5634	92	7	clinical	clinical	ADJ
cana-5634	92	8	and	and	CCONJ
cana-5634	92	9	demographic	demographic	ADJ
cana-5634	92	10	information	information	NOUN
cana-5634	92	11	from	from	ADP
cana-5634	92	12	a	a	DET
cana-5634	92	13	cross	cross	ADJ
cana-5634	92	14	-	-	ADJ
cana-5634	92	15	sectional	sectional	ADJ
cana-5634	92	16	cohort	cohort	NOUN
cana-5634	92	17	of	of	ADP
cana-5634	92	18	participants	participant	NOUN
cana-5634	92	19	aged	age	VERB
cana-5634	92	20	18	18	NUM
cana-5634	92	21	to	to	PART
cana-5634	92	22	96	96	NUM
cana-5634	92	23	years	year	NOUN
cana-5634	92	24	.	.	PUNCT
cana-5634	93	1	the	the	DET
cana-5634	93	2	dataset	dataset	NOUN
cana-5634	93	3	includes	include	VERB
cana-5634	93	4	both	both	DET
cana-5634	93	5	cognitively	cognitively	ADV
cana-5634	93	6	normal	normal	ADJ
cana-5634	93	7	individuals	individual	NOUN
cana-5634	93	8	and	and	CCONJ
cana-5634	93	9	those	those	PRON
cana-5634	93	10	diagnosed	diagnose	VERB
cana-5634	93	11	with	with	ADP
cana-5634	93	12	varying	vary	VERB
cana-5634	93	13	stages	stage	NOUN
cana-5634	93	14	of	of	ADP
cana-5634	93	15	alzheimer	alzheimer	PROPN
cana-5634	93	16	’s	’s	PART
cana-5634	93	17	disease	disease	NOUN
cana-5634	93	18	[	[	X
cana-5634	93	19	32	32	NUM
cana-5634	93	20	]	]	PUNCT
cana-5634	93	21	.	.	PUNCT
cana-5634	94	1	2.1.1	2.1.1	NUM
cana-5634	94	2	features	feature	VERB
cana-5634	94	3	in	in	ADP
cana-5634	94	4	the	the	DET
cana-5634	94	5	dataset	dataset	NOUN
cana-5634	94	6	:	:	PUNCT
cana-5634	94	7	feature	feature	NOUN
cana-5634	94	8	description	description	NOUN
cana-5634	94	9	i	i	NOUN
cana-5634	94	10	d	d	PROPN
cana-5634	94	11	unique	unique	VERB
cana-5634	94	12	identifier	identifier	NOUN
cana-5634	94	13	for	for	ADP
cana-5634	94	14	each	each	DET
cana-5634	94	15	participant	participant	ADJ
cana-5634	94	16	age	age	NOUN
cana-5634	94	17	age	age	NOUN
cana-5634	94	18	of	of	ADP
cana-5634	94	19	the	the	DET
cana-5634	94	20	subject	subject	NOUN
cana-5634	94	21	in	in	ADP
cana-5634	94	22	years	year	NOUN
cana-5634	94	23	sex	sex	NOUN
cana-5634	94	24	gender	gender	NOUN
cana-5634	94	25	of	of	ADP
cana-5634	94	26	the	the	DET
cana-5634	94	27	subject	subject	NOUN
cana-5634	94	28	(	(	PUNCT
cana-5634	94	29	m	m	PROPN
cana-5634	94	30	or	or	CCONJ
cana-5634	94	31	f	f	X
cana-5634	94	32	)	)	PUNCT
cana-5634	94	33	educ	educ	VERB
cana-5634	94	34	years	year	NOUN
cana-5634	94	35	of	of	ADP
cana-5634	94	36	education	education	NOUN
cana-5634	94	37	communications	communication	NOUN
cana-5634	94	38	on	on	ADP
cana-5634	94	39	applied	apply	VERB
cana-5634	94	40	nonlinear	nonlinear	ADJ
cana-5634	94	41	analysis	analysis	NOUN
cana-5634	94	42	issn	issn	NOUN
cana-5634	94	43	:	:	PUNCT
cana-5634	94	44	1074	1074	NUM
cana-5634	94	45	-	-	PUNCT
cana-5634	94	46	133x	133x	NUM
cana-5634	94	47	vol	vol	VERB
cana-5634	94	48	32	32	NUM
cana-5634	94	49	no.1s	no.1s	PROPN
cana-5634	94	50	(	(	PUNCT
cana-5634	94	51	2025	2025	NUM
cana-5634	94	52	)	)	PUNCT
cana-5634	94	53	673	673	NUM
cana-5634	94	54	https://internationalpubls.com	https://internationalpubls.com	X
cana-5634	94	55	ses	ses	PROPN
cana-5634	94	56	socioeconomic	socioeconomic	ADJ
cana-5634	94	57	status	status	NOUN
cana-5634	94	58	(	(	PUNCT
cana-5634	94	59	1	1	NUM
cana-5634	94	60	=	=	SYM
cana-5634	94	61	high	high	ADJ
cana-5634	94	62	,	,	PUNCT
cana-5634	94	63	5	5	NUM
cana-5634	94	64	=	=	SYM
cana-5634	94	65	low	low	ADJ
cana-5634	94	66	;	;	PUNCT
cana-5634	94	67	may	may	AUX
cana-5634	94	68	have	have	VERB
cana-5634	94	69	missing	miss	VERB
cana-5634	94	70	values	value	NOUN
cana-5634	94	71	)	)	PUNCT
cana-5634	94	72	mmse	mmse	PROPN
cana-5634	94	73	mini	mini	ADJ
cana-5634	94	74	-	-	ADJ
cana-5634	94	75	mental	mental	ADJ
cana-5634	94	76	state	state	NOUN
cana-5634	94	77	examination	examination	NOUN
cana-5634	94	78	score	score	NOUN
cana-5634	94	79	(	(	PUNCT
cana-5634	94	80	0–30	0–30	PROPN
cana-5634	94	81	)	)	PUNCT
cana-5634	94	82	cdr	cdr	PROPN
cana-5634	94	83	clinical	clinical	ADJ
cana-5634	94	84	dementia	dementia	NOUN
cana-5634	94	85	rating	rating	NOUN
cana-5634	94	86	(	(	PUNCT
cana-5634	94	87	0	0	NUM
cana-5634	94	88	=	=	SYM
cana-5634	94	89	normal	normal	ADJ
cana-5634	94	90	,	,	PUNCT
cana-5634	94	91	0.5	0.5	NUM
cana-5634	94	92	=	=	SYM
cana-5634	94	93	mild	mild	ADJ
cana-5634	94	94	,	,	PUNCT
cana-5634	94	95	1–3	1–3	NOUN
cana-5634	94	96	=	=	SYM
cana-5634	94	97	increasing	increase	VERB
cana-5634	94	98	severity	severity	NOUN
cana-5634	94	99	)	)	PUNCT
cana-5634	94	100	etiv	etiv	NOUN
cana-5634	94	101	estimated	estimate	VERB
cana-5634	94	102	total	total	ADJ
cana-5634	94	103	intracranial	intracranial	ADJ
cana-5634	94	104	volume	volume	NOUN
cana-5634	94	105	nwbv	nwbv	PROPN
cana-5634	94	106	normalized	normalize	VERB
cana-5634	94	107	whole	whole	ADJ
cana-5634	94	108	brain	brain	NOUN
cana-5634	94	109	volume	volume	NOUN
cana-5634	94	110	asf	asf	PROPN
cana-5634	94	111	atlas	atlas	PROPN
cana-5634	94	112	scaling	scaling	NOUN
cana-5634	94	113	factor	factor	NOUN
cana-5634	94	114	group	group	NOUN
cana-5634	94	115	diagnosis	diagnosis	NOUN
cana-5634	94	116	group	group	NOUN
cana-5634	94	117	(	(	PUNCT
cana-5634	94	118	nondemented	nondemente	VERB
cana-5634	94	119	,	,	PUNCT
cana-5634	94	120	demented	demented	ADJ
cana-5634	94	121	,	,	PUNCT
cana-5634	94	122	converted	convert	VERB
cana-5634	94	123	)	)	PUNCT
cana-5634	94	124	2.1.2	2.1.2	NUM
cana-5634	94	125	dataset	dataset	NOUN
cana-5634	94	126	table	table	NOUN
cana-5634	94	127	here	here	ADV
cana-5634	94	128	is	be	AUX
cana-5634	94	129	a	a	DET
cana-5634	94	130	sample	sample	NOUN
cana-5634	94	131	version	version	NOUN
cana-5634	94	132	of	of	ADP
cana-5634	94	133	the	the	DET
cana-5634	94	134	dataset	dataset	NOUN
cana-5634	94	135	showing	show	VERB
cana-5634	94	136	the	the	DET
cana-5634	94	137	first	first	ADJ
cana-5634	94	138	five	five	NUM
cana-5634	94	139	representative	representative	ADJ
cana-5634	94	140	rows	row	NOUN
cana-5634	94	141	:	:	PUNCT
cana-5634	94	142	i	i	PROPN
cana-5634	94	143	d	d	PROPN
cana-5634	94	144	age	age	NOUN
cana-5634	94	145	sex	sex	NOUN
cana-5634	94	146	educ	educ	X
cana-5634	94	147	ses	se	VERB
cana-5634	94	148	mmse	mmse	PROPN
cana-5634	94	149	cdr	cdr	PROPN
cana-5634	94	150	etiv	etiv	PROPN
cana-5634	94	151	nwbv	nwbv	PROPN
cana-5634	94	152	asf	asf	PROPN
cana-5634	94	153	group	group	PROPN
cana-5634	94	154	oas1_0001	oas1_0001	X
cana-5634	94	155	74	74	NUM
cana-5634	94	156	m	m	NOUN
cana-5634	94	157	12	12	NUM
cana-5634	94	158	3.0	3.0	NUM
cana-5634	94	159	28	28	NUM
cana-5634	94	160	0.0	0.0	NUM
cana-5634	94	161	1987	1987	NUM
cana-5634	94	162	0.696	0.696	NUM
cana-5634	94	163	1.20	1.20	NUM
cana-5634	94	164	nondemented	nondemente	VERB
cana-5634	94	165	oas1_0002	oas1_0002	NOUN
cana-5634	94	166	55	55	NUM
cana-5634	94	167	f	f	NOUN
cana-5634	94	168	14	14	NUM
cana-5634	94	169	2.0	2.0	NUM
cana-5634	94	170	30	30	NUM
cana-5634	94	171	0.0	0.0	NUM
cana-5634	94	172	1739	1739	NUM
cana-5634	94	173	0.736	0.736	NUM
cana-5634	94	174	1.00	1.00	NUM
cana-5634	94	175	nondemented	nondemente	VERB
cana-5634	94	176	oas1_0003	oas1_0003	ADJ
cana-5634	94	177	73	73	NUM
cana-5634	94	178	m	m	NUM
cana-5634	94	179	12	12	NUM
cana-5634	94	180	3.0	3.0	NUM
cana-5634	94	181	26	26	NUM
cana-5634	94	182	0.5	0.5	NUM
cana-5634	94	183	1989	1989	NUM
cana-5634	94	184	0.694	0.694	NUM
cana-5634	94	185	1.21	1.21	NUM
cana-5634	94	186	demented	demented	ADJ
cana-5634	94	187	oas1_0004	oas1_0004	NOUN
cana-5634	94	188	76	76	NUM
cana-5634	94	189	f	f	NOUN
cana-5634	94	190	12	12	NUM
cana-5634	94	191	1.0	1.0	NUM
cana-5634	94	192	30	30	NUM
cana-5634	94	193	0.0	0.0	NUM
cana-5634	94	194	1964	1964	NUM
cana-5634	94	195	0.736	0.736	NUM
cana-5634	94	196	1.18	1.18	NUM
cana-5634	94	197	nondemented	nondemente	VERB
cana-5634	94	198	oas1_0005	oas1_0005	ADV
cana-5634	94	199	88	88	NUM
cana-5634	94	200	f	f	NOUN
cana-5634	94	201	12	12	NUM
cana-5634	94	202	nan	nan	NOUN
cana-5634	94	203	25	25	NUM
cana-5634	94	204	1.0	1.0	NUM
cana-5634	94	205	1672	1672	NUM
cana-5634	94	206	0.664	0.664	NUM
cana-5634	94	207	1.12	1.12	NUM
cana-5634	94	208	demented	demented	ADJ
cana-5634	94	209	3	3	NUM
cana-5634	94	210	.	.	PUNCT
cana-5634	95	1	background	background	NOUN
cana-5634	95	2	and	and	CCONJ
cana-5634	95	3	methodologies	methodology	NOUN
cana-5634	95	4	alzheimer	alzheimer	PROPN
cana-5634	95	5	’s	’s	PART
cana-5634	95	6	disease	disease	NOUN
cana-5634	95	7	(	(	PUNCT
cana-5634	95	8	ad	ad	NOUN
cana-5634	95	9	)	)	PUNCT
cana-5634	95	10	is	be	AUX
cana-5634	95	11	a	a	DET
cana-5634	95	12	serious	serious	ADJ
cana-5634	95	13	brain	brain	NOUN
cana-5634	95	14	condition	condition	NOUN
cana-5634	95	15	that	that	PRON
cana-5634	95	16	gradually	gradually	ADV
cana-5634	95	17	leads	lead	VERB
cana-5634	95	18	to	to	ADP
cana-5634	95	19	memory	memory	NOUN
cana-5634	95	20	problems	problem	NOUN
cana-5634	95	21	,	,	PUNCT
cana-5634	95	22	confusion	confusion	NOUN
cana-5634	95	23	,	,	PUNCT
cana-5634	95	24	and	and	CCONJ
cana-5634	95	25	poor	poor	ADJ
cana-5634	95	26	decision	decision	NOUN
cana-5634	95	27	-	-	PUNCT
cana-5634	95	28	making	making	NOUN
cana-5634	95	29	.	.	PUNCT
cana-5634	96	1	as	as	SCONJ
cana-5634	96	2	the	the	DET
cana-5634	96	3	world	world	NOUN
cana-5634	96	4	’s	’s	PART
cana-5634	96	5	population	population	NOUN
cana-5634	96	6	continues	continue	VERB
cana-5634	96	7	to	to	ADP
cana-5634	96	8	age	age	NOUN
cana-5634	96	9	,	,	PUNCT
cana-5634	96	10	the	the	DET
cana-5634	96	11	number	number	NOUN
cana-5634	96	12	of	of	ADP
cana-5634	96	13	people	people	NOUN
cana-5634	96	14	affected	affect	VERB
cana-5634	96	15	by	by	ADP
cana-5634	96	16	ad	ad	NOUN
cana-5634	96	17	is	be	AUX
cana-5634	96	18	expected	expect	VERB
cana-5634	96	19	to	to	PART
cana-5634	96	20	grow	grow	VERB
cana-5634	96	21	rapidly	rapidly	ADV
cana-5634	96	22	.	.	PUNCT
cana-5634	97	1	this	this	PRON
cana-5634	97	2	makes	make	VERB
cana-5634	97	3	it	it	PRON
cana-5634	97	4	more	more	ADV
cana-5634	97	5	important	important	ADJ
cana-5634	97	6	than	than	ADP
cana-5634	97	7	ever	ever	ADV
cana-5634	97	8	to	to	PART
cana-5634	97	9	find	find	VERB
cana-5634	97	10	reliable	reliable	ADJ
cana-5634	97	11	ways	way	NOUN
cana-5634	97	12	to	to	PART
cana-5634	97	13	detect	detect	VERB
cana-5634	97	14	the	the	DET
cana-5634	97	15	disease	disease	NOUN
cana-5634	97	16	early	early	ADV
cana-5634	97	17	.	.	PUNCT
cana-5634	98	1	while	while	SCONJ
cana-5634	98	2	standard	standard	ADJ
cana-5634	98	3	methods	method	NOUN
cana-5634	98	4	like	like	ADP
cana-5634	98	5	brain	brain	NOUN
cana-5634	98	6	scans	scan	NOUN
cana-5634	98	7	and	and	CCONJ
cana-5634	98	8	memory	memory	NOUN
cana-5634	98	9	tests	test	NOUN
cana-5634	98	10	are	be	AUX
cana-5634	98	11	useful	useful	ADJ
cana-5634	98	12	,	,	PUNCT
cana-5634	98	13	they	they	PRON
cana-5634	98	14	can	can	AUX
cana-5634	98	15	be	be	AUX
cana-5634	98	16	expensive	expensive	ADJ
cana-5634	98	17	and	and	CCONJ
cana-5634	98	18	time	time	NOUN
cana-5634	98	19	-	-	PUNCT
cana-5634	98	20	consuming	consume	VERB
cana-5634	98	21	,	,	PUNCT
cana-5634	98	22	making	make	VERB
cana-5634	98	23	them	they	PRON
cana-5634	98	24	hard	hard	ADJ
cana-5634	98	25	to	to	PART
cana-5634	98	26	use	use	VERB
cana-5634	98	27	for	for	ADP
cana-5634	98	28	large	large	ADJ
cana-5634	98	29	groups	group	NOUN
cana-5634	98	30	of	of	ADP
cana-5634	98	31	people	people	NOUN
cana-5634	98	32	.	.	PUNCT
cana-5634	99	1	in	in	ADP
cana-5634	99	2	recent	recent	ADJ
cana-5634	99	3	years	year	NOUN
cana-5634	99	4	,	,	PUNCT
cana-5634	99	5	artificial	artificial	ADJ
cana-5634	99	6	intelligence	intelligence	NOUN
cana-5634	99	7	(	(	PUNCT
cana-5634	99	8	ai	ai	NOUN
cana-5634	99	9	)	)	PUNCT
cana-5634	99	10	has	have	AUX
cana-5634	99	11	provided	provide	VERB
cana-5634	99	12	new	new	ADJ
cana-5634	99	13	ways	way	NOUN
cana-5634	99	14	to	to	PART
cana-5634	99	15	help	help	VERB
cana-5634	99	16	with	with	ADP
cana-5634	99	17	medical	medical	ADJ
cana-5634	99	18	diagnosis	diagnosis	NOUN
cana-5634	99	19	.	.	PUNCT
cana-5634	100	1	machine	machine	NOUN
cana-5634	100	2	learning	learning	NOUN
cana-5634	100	3	(	(	PUNCT
cana-5634	100	4	ml	ml	NOUN
cana-5634	100	5	)	)	PUNCT
cana-5634	100	6	and	and	CCONJ
cana-5634	100	7	deep	deep	ADJ
cana-5634	100	8	learning	learning	NOUN
cana-5634	100	9	(	(	PUNCT
cana-5634	100	10	dl	dl	INTJ
cana-5634	100	11	)	)	PUNCT
cana-5634	100	12	are	be	AUX
cana-5634	100	13	two	two	NUM
cana-5634	100	14	types	type	NOUN
cana-5634	100	15	of	of	ADP
cana-5634	100	16	ai	ai	NOUN
cana-5634	100	17	that	that	PRON
cana-5634	100	18	have	have	AUX
cana-5634	100	19	shown	show	VERB
cana-5634	100	20	promise	promise	NOUN
cana-5634	100	21	in	in	ADP
cana-5634	100	22	predicting	predict	VERB
cana-5634	100	23	diseases	disease	NOUN
cana-5634	100	24	like	like	ADP
cana-5634	100	25	ad	ad	NOUN
cana-5634	100	26	.	.	PUNCT
cana-5634	101	1	traditional	traditional	ADJ
cana-5634	101	2	ml	ml	NOUN
cana-5634	101	3	models	model	NOUN
cana-5634	101	4	such	such	ADJ
cana-5634	101	5	as	as	ADP
cana-5634	101	6	support	support	NOUN
cana-5634	101	7	vector	vector	NOUN
cana-5634	101	8	machines	machine	NOUN
cana-5634	101	9	(	(	PUNCT
cana-5634	101	10	svm	svm	PROPN
cana-5634	101	11	)	)	PUNCT
cana-5634	101	12	,	,	PUNCT
cana-5634	101	13	random	random	ADJ
cana-5634	101	14	forests	forest	NOUN
cana-5634	101	15	(	(	PUNCT
cana-5634	101	16	rf	rf	NOUN
cana-5634	101	17	)	)	PUNCT
cana-5634	101	18	,	,	PUNCT
cana-5634	101	19	and	and	CCONJ
cana-5634	101	20	gradient	gradient	ADJ
cana-5634	101	21	boosting	boost	VERB
cana-5634	101	22	machines	machine	NOUN
cana-5634	101	23	(	(	PUNCT
cana-5634	101	24	gbm	gbm	NOUN
cana-5634	101	25	)	)	PUNCT
cana-5634	101	26	are	be	AUX
cana-5634	101	27	good	good	ADJ
cana-5634	101	28	at	at	ADP
cana-5634	101	29	making	make	VERB
cana-5634	101	30	sense	sense	NOUN
cana-5634	101	31	of	of	ADP
cana-5634	101	32	structured	structured	ADJ
cana-5634	101	33	data	datum	NOUN
cana-5634	101	34	,	,	PUNCT
cana-5634	101	35	especially	especially	ADV
cana-5634	101	36	when	when	SCONJ
cana-5634	101	37	their	their	PRON
cana-5634	101	38	settings	setting	NOUN
cana-5634	101	39	are	be	AUX
cana-5634	101	40	fine	fine	ADV
cana-5634	101	41	-	-	PUNCT
cana-5634	101	42	tuned	tune	VERB
cana-5634	101	43	.	.	PUNCT
cana-5634	102	1	however	however	ADV
cana-5634	102	2	,	,	PUNCT
cana-5634	102	3	they	they	PRON
cana-5634	102	4	often	often	ADV
cana-5634	102	5	require	require	VERB
cana-5634	102	6	experts	expert	NOUN
cana-5634	102	7	to	to	PART
cana-5634	102	8	pick	pick	VERB
cana-5634	102	9	the	the	DET
cana-5634	102	10	right	right	ADJ
cana-5634	102	11	features	feature	NOUN
cana-5634	102	12	from	from	ADP
cana-5634	102	13	the	the	DET
cana-5634	102	14	data	datum	NOUN
cana-5634	102	15	.	.	PUNCT
cana-5634	103	1	deep	deep	ADJ
cana-5634	103	2	learning	learning	NOUN
cana-5634	103	3	models	model	NOUN
cana-5634	103	4	,	,	PUNCT
cana-5634	103	5	such	such	ADJ
cana-5634	103	6	as	as	ADP
cana-5634	103	7	deep	deep	ADJ
cana-5634	103	8	neural	neural	ADJ
cana-5634	103	9	networks	network	NOUN
cana-5634	103	10	(	(	PUNCT
cana-5634	103	11	dnns	dnn	NOUN
cana-5634	103	12	)	)	PUNCT
cana-5634	103	13	,	,	PUNCT
cana-5634	103	14	can	can	AUX
cana-5634	103	15	automatically	automatically	ADV
cana-5634	103	16	learn	learn	VERB
cana-5634	103	17	important	important	ADJ
cana-5634	103	18	features	feature	NOUN
cana-5634	103	19	from	from	ADP
cana-5634	103	20	the	the	DET
cana-5634	103	21	data	datum	NOUN
cana-5634	103	22	without	without	ADP
cana-5634	103	23	much	much	ADJ
cana-5634	103	24	manual	manual	ADJ
cana-5634	103	25	work	work	NOUN
cana-5634	103	26	.	.	PUNCT
cana-5634	104	1	these	these	DET
cana-5634	104	2	models	model	NOUN
cana-5634	104	3	are	be	AUX
cana-5634	104	4	better	well	ADJ
cana-5634	104	5	at	at	ADP
cana-5634	104	6	handling	handle	VERB
cana-5634	104	7	complex	complex	ADJ
cana-5634	104	8	data	datum	NOUN
cana-5634	104	9	but	but	CCONJ
cana-5634	104	10	need	need	VERB
cana-5634	104	11	a	a	DET
cana-5634	104	12	lot	lot	NOUN
cana-5634	104	13	of	of	ADP
cana-5634	104	14	computing	compute	VERB
cana-5634	104	15	power	power	NOUN
cana-5634	104	16	and	and	CCONJ
cana-5634	104	17	can	can	AUX
cana-5634	104	18	sometimes	sometimes	ADV
cana-5634	104	19	overfit	overfit	VERB
cana-5634	104	20	—	—	PUNCT
cana-5634	104	21	especially	especially	ADV
cana-5634	104	22	if	if	SCONJ
cana-5634	104	23	the	the	DET
cana-5634	104	24	dataset	dataset	NOUN
cana-5634	104	25	is	be	AUX
cana-5634	104	26	small	small	ADJ
cana-5634	104	27	.	.	PUNCT
cana-5634	105	1	to	to	PART
cana-5634	105	2	deal	deal	VERB
cana-5634	105	3	with	with	ADP
cana-5634	105	4	these	these	DET
cana-5634	105	5	challenges	challenge	NOUN
cana-5634	105	6	,	,	PUNCT
cana-5634	105	7	techniques	technique	NOUN
cana-5634	105	8	like	like	ADP
cana-5634	105	9	dropout	dropout	NOUN
cana-5634	105	10	,	,	PUNCT
cana-5634	105	11	learning	learn	VERB
cana-5634	105	12	rate	rate	NOUN
cana-5634	105	13	adjustment	adjustment	NOUN
cana-5634	105	14	,	,	PUNCT
cana-5634	105	15	and	and	CCONJ
cana-5634	105	16	using	use	VERB
cana-5634	105	17	advanced	advanced	ADJ
cana-5634	105	18	optimizers	optimizer	NOUN
cana-5634	105	19	like	like	ADP
cana-5634	105	20	adam	adam	PROPN
cana-5634	105	21	are	be	AUX
cana-5634	105	22	used	use	VERB
cana-5634	105	23	.	.	PUNCT
cana-5634	106	1	this	this	DET
cana-5634	106	2	study	study	NOUN
cana-5634	106	3	compares	compare	VERB
cana-5634	106	4	both	both	DET
cana-5634	106	5	traditional	traditional	ADJ
cana-5634	106	6	ml	ml	NOUN
cana-5634	106	7	and	and	CCONJ
cana-5634	106	8	deep	deep	ADJ
cana-5634	106	9	learning	learning	NOUN
cana-5634	106	10	models	model	NOUN
cana-5634	106	11	for	for	ADP
cana-5634	106	12	predicting	predict	VERB
cana-5634	106	13	alzheimer	alzheimer	PROPN
cana-5634	106	14	’s	’s	PART
cana-5634	106	15	disease	disease	NOUN
cana-5634	106	16	using	use	VERB
cana-5634	106	17	the	the	DET
cana-5634	106	18	oasis	oasis	NOUN
cana-5634	106	19	cross	cross	ADJ
cana-5634	106	20	-	-	ADJ
cana-5634	106	21	sectional	sectional	ADJ
cana-5634	106	22	dataset	dataset	NOUN
cana-5634	106	23	.	.	PUNCT
cana-5634	107	1	the	the	DET
cana-5634	107	2	aim	aim	NOUN
cana-5634	107	3	is	be	AUX
cana-5634	107	4	to	to	PART
cana-5634	107	5	find	find	VERB
cana-5634	107	6	out	out	ADP
cana-5634	107	7	which	which	DET
cana-5634	107	8	method	method	NOUN
cana-5634	107	9	gives	give	VERB
cana-5634	107	10	the	the	DET
cana-5634	107	11	most	most	ADV
cana-5634	107	12	accurate	accurate	ADJ
cana-5634	107	13	and	and	CCONJ
cana-5634	107	14	reliable	reliable	ADJ
cana-5634	107	15	results	result	NOUN
cana-5634	107	16	by	by	ADP
cana-5634	107	17	testing	test	VERB
cana-5634	107	18	different	different	ADJ
cana-5634	107	19	models	model	NOUN
cana-5634	107	20	and	and	CCONJ
cana-5634	107	21	comparing	compare	VERB
cana-5634	107	22	their	their	PRON
cana-5634	107	23	performance	performance	NOUN
cana-5634	107	24	.	.	PUNCT
cana-5634	108	1	3.1	3.1	NUM
cana-5634	108	2	machine	machine	NOUN
cana-5634	108	3	learning	learning	NOUN
cana-5634	108	4	models	model	NOUN
cana-5634	108	5	three	three	NUM
cana-5634	108	6	popular	popular	ADJ
cana-5634	108	7	ml	ml	NOUN
cana-5634	108	8	algorithms	algorithm	NOUN
cana-5634	108	9	were	be	AUX
cana-5634	108	10	used	use	VERB
cana-5634	108	11	:	:	PUNCT
cana-5634	108	12	step	step	NOUN
cana-5634	108	13	.	.	PUNCT
cana-5634	109	1	1	1	NUM
cana-5634	109	2	support	support	NOUN
cana-5634	109	3	vector	vector	NOUN
cana-5634	109	4	machine	machine	NOUN
cana-5634	109	5	(	(	PUNCT
cana-5634	109	6	svm	svm	PROPN
cana-5634	109	7	):	):	PUNCT
cana-5634	109	8	o	o	NOUN
cana-5634	109	9	used	use	VERB
cana-5634	109	10	an	an	DET
cana-5634	109	11	rbf	rbf	PROPN
cana-5634	109	12	kernel	kernel	PROPN
cana-5634	109	13	.	.	PUNCT
cana-5634	110	1	communications	communication	NOUN
cana-5634	110	2	on	on	ADP
cana-5634	110	3	applied	apply	VERB
cana-5634	110	4	nonlinear	nonlinear	ADJ
cana-5634	110	5	analysis	analysis	NOUN
cana-5634	110	6	issn	issn	NOUN
cana-5634	110	7	:	:	PUNCT
cana-5634	110	8	1074	1074	NUM
cana-5634	110	9	-	-	PUNCT
cana-5634	110	10	133x	133x	NUM
cana-5634	110	11	vol	vol	VERB
cana-5634	110	12	32	32	NUM
cana-5634	110	13	no.1s	no.1s	PROPN
cana-5634	110	14	(	(	PUNCT
cana-5634	110	15	2025	2025	NUM
cana-5634	110	16	)	)	PUNCT
cana-5634	110	17	674	674	NUM
cana-5634	110	18	https://internationalpubls.com	https://internationalpubls.com	X
cana-5634	110	19	o	o	NOUN
cana-5634	110	20	hyperparameters	hyperparameter	NOUN
cana-5634	110	21	(	(	PUNCT
cana-5634	110	22	c	c	NOUN
cana-5634	110	23	and	and	CCONJ
cana-5634	110	24	gamma	gamma	NOUN
cana-5634	110	25	)	)	PUNCT
cana-5634	110	26	were	be	AUX
cana-5634	110	27	optimized	optimize	VERB
cana-5634	110	28	using	use	VERB
cana-5634	110	29	grid	grid	NOUN
cana-5634	110	30	search	search	NOUN
cana-5634	110	31	and	and	CCONJ
cana-5634	110	32	5	5	NUM
cana-5634	110	33	-	-	ADJ
cana-5634	110	34	fold	fold	ADJ
cana-5634	110	35	crossvalidation	crossvalidation	NOUN
cana-5634	110	36	.	.	PUNCT
cana-5634	111	1	step	step	NOUN
cana-5634	111	2	.	.	PUNCT
cana-5634	112	1	2	2	NUM
cana-5634	112	2	random	random	ADJ
cana-5634	112	3	forest	forest	NOUN
cana-5634	112	4	(	(	PUNCT
cana-5634	112	5	rf	rf	NOUN
cana-5634	112	6	):	):	PUNCT
cana-5634	112	7	o	o	NOUN
cana-5634	112	8	tested	test	VERB
cana-5634	112	9	different	different	ADJ
cana-5634	112	10	numbers	number	NOUN
cana-5634	112	11	of	of	ADP
cana-5634	112	12	trees	tree	NOUN
cana-5634	112	13	and	and	CCONJ
cana-5634	112	14	depth	depth	NOUN
cana-5634	112	15	levels	level	NOUN
cana-5634	112	16	to	to	PART
cana-5634	112	17	improve	improve	VERB
cana-5634	112	18	performance	performance	NOUN
cana-5634	112	19	.	.	PUNCT
cana-5634	113	1	step	step	NOUN
cana-5634	113	2	.	.	PUNCT
cana-5634	114	1	3	3	NUM
cana-5634	114	2	gradient	gradient	NOUN
cana-5634	114	3	boosting	boost	VERB
cana-5634	114	4	machine	machine	NOUN
cana-5634	114	5	(	(	PUNCT
cana-5634	114	6	gbm	gbm	PROPN
cana-5634	114	7	):	):	PUNCT
cana-5634	114	8	o	o	NOUN
cana-5634	114	9	used	use	VERB
cana-5634	114	10	learning	learn	VERB
cana-5634	114	11	rate	rate	NOUN
cana-5634	114	12	tuning	tuning	NOUN
cana-5634	114	13	and	and	CCONJ
cana-5634	114	14	early	early	ADV
cana-5634	114	15	stopping	stop	VERB
cana-5634	114	16	to	to	PART
cana-5634	114	17	avoid	avoid	VERB
cana-5634	114	18	overfitting	overfitte	VERB
cana-5634	114	19	.	.	PUNCT
cana-5634	115	1	3.2	3.2	NUM
cana-5634	115	2	deep	deep	ADJ
cana-5634	115	3	learning	learning	NOUN
cana-5634	115	4	model	model	NOUN
cana-5634	115	5	a	a	DET
cana-5634	115	6	deep	deep	ADJ
cana-5634	115	7	neural	neural	ADJ
cana-5634	115	8	network	network	NOUN
cana-5634	115	9	(	(	PUNCT
cana-5634	115	10	dnn	dnn	PROPN
cana-5634	115	11	)	)	PUNCT
cana-5634	115	12	was	be	AUX
cana-5634	115	13	designed	design	VERB
cana-5634	115	14	with	with	ADP
cana-5634	115	15	the	the	DET
cana-5634	115	16	following	follow	VERB
cana-5634	115	17	setup	setup	NOUN
cana-5634	115	18	:	:	PUNCT
cana-5634	115	19	step	step	NOUN
cana-5634	115	20	.	.	PUNCT
cana-5634	116	1	1	1	NUM
cana-5634	116	2	structure	structure	NOUN
cana-5634	116	3	:	:	PUNCT
cana-5634	116	4	a.	a.	NOUN
cana-5634	116	5	input	input	NOUN
cana-5634	116	6	layer	layer	NOUN
cana-5634	116	7	with	with	ADP
cana-5634	116	8	the	the	DET
cana-5634	116	9	number	number	NOUN
cana-5634	116	10	of	of	ADP
cana-5634	116	11	features	feature	NOUN
cana-5634	116	12	in	in	ADP
cana-5634	116	13	the	the	DET
cana-5634	116	14	dataset	dataset	NOUN
cana-5634	116	15	.	.	PUNCT
cana-5634	117	1	b.two	b.two	NUM
cana-5634	117	2	hidden	hide	VERB
cana-5634	117	3	layers	layer	NOUN
cana-5634	117	4	with	with	ADP
cana-5634	117	5	relu	relu	NOUN
cana-5634	117	6	activation	activation	NOUN
cana-5634	117	7	(	(	PUNCT
cana-5634	117	8	64	64	NUM
cana-5634	117	9	and	and	CCONJ
cana-5634	117	10	32	32	NUM
cana-5634	117	11	neurons	neuron	NOUN
cana-5634	117	12	)	)	PUNCT
cana-5634	117	13	.	.	PUNCT
cana-5634	118	1	c.	c.	PROPN
cana-5634	118	2	dropout	dropout	PROPN
cana-5634	118	3	layers	layer	NOUN
cana-5634	118	4	with	with	ADP
cana-5634	118	5	a	a	DET
cana-5634	118	6	rate	rate	NOUN
cana-5634	118	7	of	of	ADP
cana-5634	118	8	0.3	0.3	NUM
cana-5634	118	9	to	to	PART
cana-5634	118	10	reduce	reduce	VERB
cana-5634	118	11	overfitting	overfitte	VERB
cana-5634	118	12	.	.	PUNCT
cana-5634	119	1	d.output	d.output	ADJ
cana-5634	119	2	layer	layer	NOUN
cana-5634	119	3	with	with	ADP
cana-5634	119	4	softmax	softmax	NOUN
cana-5634	119	5	for	for	ADP
cana-5634	119	6	multi	multi	ADJ
cana-5634	119	7	-	-	ADJ
cana-5634	119	8	class	class	ADJ
cana-5634	119	9	classification	classification	NOUN
cana-5634	119	10	and	and	CCONJ
cana-5634	119	11	sigmoid	sigmoid	NOUN
cana-5634	119	12	for	for	ADP
cana-5634	119	13	binary	binary	ADJ
cana-5634	119	14	classification	classification	NOUN
cana-5634	119	15	.	.	PUNCT
cana-5634	120	1	step	step	NOUN
cana-5634	120	2	.	.	PUNCT
cana-5634	121	1	2	2	NUM
cana-5634	121	2	training	training	NOUN
cana-5634	121	3	settings	setting	NOUN
cana-5634	121	4	:	:	PUNCT
cana-5634	121	5	a.	a.	NOUN
cana-5634	121	6	loss	loss	NOUN
cana-5634	121	7	function	function	NOUN
cana-5634	121	8	:	:	PUNCT
cana-5634	121	9	binary	binary	PROPN
cana-5634	121	10	cross	cross	NOUN
cana-5634	121	11	-	-	NOUN
cana-5634	121	12	entropy	entropy	NOUN
cana-5634	121	13	for	for	ADP
cana-5634	121	14	binary	binary	ADJ
cana-5634	121	15	tasks	task	NOUN
cana-5634	121	16	or	or	CCONJ
cana-5634	121	17	categorical	categorical	ADJ
cana-5634	121	18	cross	cross	NOUN
cana-5634	121	19	-	-	NOUN
cana-5634	121	20	entropy	entropy	NOUN
cana-5634	121	21	for	for	ADP
cana-5634	121	22	multi	multi	ADJ
cana-5634	121	23	-	-	NOUN
cana-5634	121	24	class	class	NOUN
cana-5634	121	25	.	.	PUNCT
cana-5634	122	1	b.optimizer	b.optimizer	NOUN
cana-5634	122	2	:	:	PUNCT
cana-5634	122	3	adam	adam	NOUN
cana-5634	122	4	with	with	ADP
cana-5634	122	5	a	a	DET
cana-5634	122	6	learning	learn	VERB
cana-5634	122	7	rate	rate	NOUN
cana-5634	122	8	scheduler	scheduler	NOUN
cana-5634	122	9	to	to	PART
cana-5634	122	10	adjust	adjust	VERB
cana-5634	122	11	learning	learn	VERB
cana-5634	122	12	automatically	automatically	ADV
cana-5634	122	13	.	.	PUNCT
cana-5634	123	1	c.	c.	NOUN
cana-5634	123	2	regularization	regularization	NOUN
cana-5634	123	3	:	:	PUNCT
cana-5634	123	4	dropout	dropout	NOUN
cana-5634	123	5	layers	layer	NOUN
cana-5634	123	6	and	and	CCONJ
cana-5634	123	7	early	early	ADJ
cana-5634	123	8	stopping	stopping	NOUN
cana-5634	123	9	based	base	VERB
cana-5634	123	10	on	on	ADP
cana-5634	123	11	validation	validation	NOUN
cana-5634	123	12	loss	loss	NOUN
cana-5634	123	13	.	.	PUNCT
cana-5634	124	1	d.training	d.traine	VERB
cana-5634	124	2	:	:	PUNCT
cana-5634	124	3	epochs	epoch	NOUN
cana-5634	124	4	:	:	PUNCT
cana-5634	124	5	100	100	NUM
cana-5634	124	6	(	(	PUNCT
cana-5634	124	7	with	with	ADP
cana-5634	124	8	early	early	ADJ
cana-5634	124	9	stopping	stopping	NOUN
cana-5634	124	10	if	if	SCONJ
cana-5634	124	11	no	no	DET
cana-5634	124	12	improvement	improvement	NOUN
cana-5634	124	13	after	after	ADP
cana-5634	124	14	10	10	NUM
cana-5634	124	15	epochs	epoch	NOUN
cana-5634	124	16	)	)	PUNCT
cana-5634	124	17	.	.	PUNCT
cana-5634	125	1	batch	batch	NOUN
cana-5634	125	2	size	size	NOUN
cana-5634	125	3	:	:	PUNCT
cana-5634	125	4	32	32	NUM
cana-5634	125	5	3.3	3.3	NUM
cana-5634	125	6	evaluation	evaluation	NOUN
cana-5634	125	7	metrics	metric	NOUN
cana-5634	125	8	the	the	DET
cana-5634	125	9	performance	performance	NOUN
cana-5634	125	10	of	of	ADP
cana-5634	125	11	each	each	DET
cana-5634	125	12	model	model	NOUN
cana-5634	125	13	was	be	AUX
cana-5634	125	14	measured	measure	VERB
cana-5634	125	15	using	using	NOUN
cana-5634	125	16	:	:	PUNCT
cana-5634	125	17	step	step	NOUN
cana-5634	125	18	.	.	PUNCT
cana-5634	126	1	1	1	NUM
cana-5634	126	2	accuracy	accuracy	NOUN
cana-5634	126	3	–	–	PUNCT
cana-5634	126	4	how	how	SCONJ
cana-5634	126	5	often	often	ADV
cana-5634	126	6	the	the	DET
cana-5634	126	7	model	model	NOUN
cana-5634	126	8	predicts	predict	VERB
cana-5634	126	9	correctly	correctly	ADV
cana-5634	126	10	.	.	PUNCT
cana-5634	127	1	step	step	NOUN
cana-5634	127	2	.	.	PUNCT
cana-5634	128	1	2	2	NUM
cana-5634	128	2	precision	precision	NOUN
cana-5634	128	3	–	–	PUNCT
cana-5634	128	4	how	how	SCONJ
cana-5634	128	5	well	well	ADV
cana-5634	128	6	the	the	DET
cana-5634	128	7	model	model	NOUN
cana-5634	128	8	avoids	avoid	VERB
cana-5634	128	9	false	false	ADJ
cana-5634	128	10	positives	positive	NOUN
cana-5634	128	11	.	.	PUNCT
cana-5634	129	1	step	step	NOUN
cana-5634	129	2	.	.	PUNCT
cana-5634	130	1	3	3	NUM
cana-5634	130	2	recall	recall	NOUN
cana-5634	130	3	–	–	PUNCT
cana-5634	130	4	how	how	SCONJ
cana-5634	130	5	well	well	ADV
cana-5634	130	6	the	the	DET
cana-5634	130	7	model	model	NOUN
cana-5634	130	8	finds	find	VERB
cana-5634	130	9	all	all	DET
cana-5634	130	10	true	true	ADJ
cana-5634	130	11	positives	positive	NOUN
cana-5634	130	12	.	.	PUNCT
cana-5634	131	1	step	step	NOUN
cana-5634	131	2	.	.	PUNCT
cana-5634	132	1	4	4	NUM
cana-5634	132	2	f1	f1	NOUN
cana-5634	132	3	-	-	PUNCT
cana-5634	132	4	score	score	NOUN
cana-5634	132	5	–	–	PUNCT
cana-5634	132	6	the	the	DET
cana-5634	132	7	balance	balance	NOUN
cana-5634	132	8	between	between	ADP
cana-5634	132	9	precision	precision	NOUN
cana-5634	132	10	and	and	CCONJ
cana-5634	132	11	recall	recall	NOUN
cana-5634	132	12	.	.	PUNCT
cana-5634	133	1	step	step	NOUN
cana-5634	133	2	.	.	PUNCT
cana-5634	134	1	5	5	NUM
cana-5634	134	2	roc	roc	NOUN
cana-5634	134	3	-	-	PUNCT
cana-5634	134	4	auc	auc	NOUN
cana-5634	134	5	–	–	PUNCT
cana-5634	134	6	a	a	DET
cana-5634	134	7	metric	metric	NOUN
cana-5634	134	8	used	use	VERB
cana-5634	134	9	for	for	ADP
cana-5634	134	10	binary	binary	ADJ
cana-5634	134	11	classification	classification	NOUN
cana-5634	134	12	that	that	PRON
cana-5634	134	13	evaluates	evaluate	VERB
cana-5634	134	14	the	the	DET
cana-5634	134	15	model	model	NOUN
cana-5634	134	16	’s	’s	PART
cana-5634	134	17	ability	ability	NOUN
cana-5634	134	18	to	to	PART
cana-5634	134	19	separate	separate	ADJ
cana-5634	134	20	classes	class	NOUN
cana-5634	134	21	.	.	PUNCT
cana-5634	135	1	4	4	X
cana-5634	135	2	.	.	X
cana-5634	135	3	experimental	experimental	ADJ
cana-5634	135	4	results	result	NOUN
cana-5634	135	5	table	table	VERB
cana-5634	135	6	1	1	NUM
cana-5634	135	7	.	.	PUNCT
cana-5634	135	8	machine	machine	NOUN
cana-5634	135	9	learning	learning	NOUN
cana-5634	135	10	and	and	CCONJ
cana-5634	135	11	deep	deep	ADJ
cana-5634	135	12	learning	learning	NOUN
cana-5634	135	13	with	with	ADP
cana-5634	135	14	performance	performance	NOUN
cana-5634	135	15	model	model	NOUN
cana-5634	135	16	accuracy	accuracy	NOUN
cana-5634	135	17	precision	precision	NOUN
cana-5634	135	18	recall	recall	VERB
cana-5634	135	19	f1	f1	NOUN
cana-5634	135	20	-	-	PUNCT
cana-5634	135	21	score	score	NOUN
cana-5634	135	22	auc	auc	NOUN
cana-5634	135	23	-	-	PUNCT
cana-5634	135	24	roc	roc	NOUN
cana-5634	135	25	svm	svm	VERB
cana-5634	135	26	0.8525	0.8525	NUM
cana-5634	135	27	0.8354	0.8354	NUM
cana-5634	135	28	0.8196	0.8196	NUM
cana-5634	135	29	0.8278	0.8278	NUM
cana-5634	135	30	0.8754	0.8754	NUM
cana-5634	135	31	random	random	ADJ
cana-5634	135	32	forest	forest	NOUN
cana-5634	135	33	0.8874	0.8874	NUM
cana-5634	135	34	0.8784	0.8784	NUM
cana-5634	135	35	0.8652	0.8652	NUM
cana-5634	135	36	0.8695	0.8695	NUM
cana-5634	135	37	0.9054	0.9054	NUM
cana-5634	135	38	gradient	gradient	NOUN
cana-5634	135	39	boosting	boost	VERB
cana-5634	135	40	0.8946	0.8946	NUM
cana-5634	135	41	0.8869	0.8869	NUM
cana-5634	135	42	0.8711	0.8711	NOUN
cana-5634	135	43	0.8754	0.8754	NUM
cana-5634	135	44	0.9125	0.9125	NUM
cana-5634	135	45	deep	deep	ADJ
cana-5634	135	46	neural	neural	ADJ
cana-5634	135	47	network	network	NOUN
cana-5634	135	48	0.9254	0.9254	NUM
cana-5634	135	49	0.9174	0.9174	NUM
cana-5634	135	50	0.9322	0.9322	NUM
cana-5634	135	51	0.9214	0.9214	NUM
cana-5634	135	52	0.9523	0.9523	NUM
cana-5634	135	53	table	table	NOUN
cana-5634	135	54	2	2	NUM
cana-5634	135	55	.	.	PUNCT
cana-5634	135	56	machine	machine	NOUN
cana-5634	135	57	learning	learning	NOUN
cana-5634	135	58	and	and	CCONJ
cana-5634	135	59	deep	deep	ADJ
cana-5634	135	60	learning	learning	NOUN
cana-5634	135	61	with	with	ADP
cana-5634	135	62	time	time	NOUN
cana-5634	135	63	to	to	PART
cana-5634	135	64	train	train	VERB
cana-5634	135	65	model	model	NOUN
cana-5634	135	66	accuracy	accuracy	NOUN
cana-5634	135	67	svm	svm	VERB
cana-5634	135	68	9.9122	9.9122	NUM
cana-5634	135	69	random	random	ADJ
cana-5634	135	70	forest	forest	NOUN
cana-5634	135	71	10.3214	10.3214	NUM
cana-5634	135	72	gradient	gradient	NOUN
cana-5634	135	73	boosting	boost	VERB
cana-5634	135	74	11.6741	11.6741	NUM
cana-5634	135	75	deep	deep	ADJ
cana-5634	135	76	neural	neural	ADJ
cana-5634	135	77	network	network	NOUN
cana-5634	135	78	36.2541	36.2541	NUM
cana-5634	135	79	communications	communication	NOUN
cana-5634	135	80	on	on	ADP
cana-5634	135	81	applied	apply	VERB
cana-5634	135	82	nonlinear	nonlinear	ADJ
cana-5634	135	83	analysis	analysis	NOUN
cana-5634	135	84	issn	issn	NOUN
cana-5634	135	85	:	:	PUNCT
cana-5634	135	86	1074	1074	NUM
cana-5634	135	87	-	-	PUNCT
cana-5634	135	88	133x	133x	NUM
cana-5634	135	89	vol	vol	VERB
cana-5634	135	90	32	32	NUM
cana-5634	135	91	no.1s	no.1s	PROPN
cana-5634	135	92	(	(	PUNCT
cana-5634	135	93	2025	2025	NUM
cana-5634	135	94	)	)	PUNCT
cana-5634	135	95	675	675	NUM
cana-5634	135	96	https://internationalpubls.com	https://internationalpubls.com	X
cana-5634	135	97	fig	fig	NOUN
cana-5634	135	98	.	.	PUNCT
cana-5634	136	1	1	1	X
cana-5634	136	2	.	.	PUNCT
cana-5634	136	3	model	model	PROPN
cana-5634	136	4	comparison	comparison	NOUN
cana-5634	136	5	:	:	PUNCT
cana-5634	136	6	accuracy	accuracy	NOUN
cana-5634	136	7	,	,	PUNCT
cana-5634	136	8	precision	precision	NOUN
cana-5634	136	9	,	,	PUNCT
cana-5634	136	10	and	and	CCONJ
cana-5634	136	11	recall	recall	VERB
cana-5634	136	12	fig	fig	NOUN
cana-5634	136	13	.	.	PUNCT
cana-5634	137	1	2	2	X
cana-5634	137	2	.	.	X
cana-5634	137	3	model	model	PROPN
cana-5634	137	4	comparison	comparison	NOUN
cana-5634	137	5	:	:	PUNCT
cana-5634	137	6	f1	f1	ADJ
cana-5634	137	7	-	-	PUNCT
cana-5634	137	8	score	score	NOUN
cana-5634	137	9	and	and	CCONJ
cana-5634	137	10	auc	auc	NOUN
cana-5634	137	11	-	-	PUNCT
cana-5634	137	12	roc	roc	NOUN
cana-5634	137	13	fig	fig	NOUN
cana-5634	137	14	.	.	PUNCT
cana-5634	138	1	3	3	X
cana-5634	138	2	.	.	X
cana-5634	138	3	model	model	NOUN
cana-5634	138	4	training	training	NOUN
cana-5634	138	5	time	time	NOUN
cana-5634	138	6	comparison	comparison	NOUN
cana-5634	138	7	communications	communication	NOUN
cana-5634	138	8	on	on	ADP
cana-5634	138	9	applied	apply	VERB
cana-5634	138	10	nonlinear	nonlinear	ADJ
cana-5634	138	11	analysis	analysis	NOUN
cana-5634	138	12	issn	issn	NOUN
cana-5634	138	13	:	:	PUNCT
cana-5634	138	14	1074	1074	NUM
cana-5634	138	15	-	-	PUNCT
cana-5634	138	16	133x	133x	NUM
cana-5634	138	17	vol	vol	VERB
cana-5634	138	18	32	32	NUM
cana-5634	138	19	no.1s	no.1s	PROPN
cana-5634	138	20	(	(	PUNCT
cana-5634	138	21	2025	2025	NUM
cana-5634	138	22	)	)	PUNCT
cana-5634	138	23	676	676	NUM
cana-5634	138	24	https://internationalpubls.com	https://internationalpubls.com	X
cana-5634	138	25	5	5	NUM
cana-5634	138	26	.	.	NOUN
cana-5634	138	27	results	result	NOUN
cana-5634	138	28	and	and	CCONJ
cana-5634	138	29	discussion	discussion	NOUN
cana-5634	138	30	this	this	DET
cana-5634	138	31	section	section	NOUN
cana-5634	138	32	compares	compare	VERB
cana-5634	139	1	how	how	SCONJ
cana-5634	139	2	well	well	ADV
cana-5634	139	3	different	different	ADJ
cana-5634	139	4	machine	machine	NOUN
cana-5634	139	5	learning	learning	NOUN
cana-5634	139	6	(	(	PUNCT
cana-5634	139	7	ml	ml	NOUN
cana-5634	139	8	)	)	PUNCT
cana-5634	139	9	and	and	CCONJ
cana-5634	139	10	deep	deep	ADJ
cana-5634	139	11	learning	learning	NOUN
cana-5634	139	12	(	(	PUNCT
cana-5634	139	13	dl	dl	NOUN
cana-5634	139	14	)	)	PUNCT
cana-5634	139	15	models	model	NOUN
cana-5634	139	16	predict	predict	VERB
cana-5634	139	17	alzheimer	alzheimer	PROPN
cana-5634	139	18	’s	’s	PART
cana-5634	139	19	disease	disease	NOUN
cana-5634	139	20	using	use	VERB
cana-5634	139	21	the	the	DET
cana-5634	139	22	oasis	oasis	NOUN
cana-5634	139	23	cross	cross	ADJ
cana-5634	139	24	-	-	ADJ
cana-5634	139	25	sectional	sectional	ADJ
cana-5634	139	26	dataset	dataset	NOUN
cana-5634	139	27	.	.	PUNCT
cana-5634	140	1	the	the	DET
cana-5634	140	2	models	model	NOUN
cana-5634	140	3	were	be	AUX
cana-5634	140	4	evaluated	evaluate	VERB
cana-5634	140	5	using	use	VERB
cana-5634	140	6	five	five	NUM
cana-5634	140	7	key	key	ADJ
cana-5634	140	8	metrics	metric	NOUN
cana-5634	140	9	:	:	PUNCT
cana-5634	140	10	accuracy	accuracy	NOUN
cana-5634	140	11	,	,	PUNCT
cana-5634	140	12	precision	precision	NOUN
cana-5634	140	13	,	,	PUNCT
cana-5634	140	14	recall	recall	NOUN
cana-5634	140	15	,	,	PUNCT
cana-5634	140	16	f1	f1	NOUN
cana-5634	140	17	-	-	PUNCT
cana-5634	140	18	score	score	NOUN
cana-5634	140	19	,	,	PUNCT
cana-5634	140	20	and	and	CCONJ
cana-5634	140	21	auc	auc	NOUN
cana-5634	140	22	-	-	PUNCT
cana-5634	140	23	roc	roc	NOUN
cana-5634	140	24	.	.	PUNCT
cana-5634	141	1	in	in	ADP
cana-5634	141	2	addition	addition	NOUN
cana-5634	141	3	,	,	PUNCT
cana-5634	141	4	the	the	DET
cana-5634	141	5	time	time	NOUN
cana-5634	141	6	taken	take	VERB
cana-5634	141	7	to	to	PART
cana-5634	141	8	train	train	VERB
cana-5634	141	9	each	each	DET
cana-5634	141	10	model	model	NOUN
cana-5634	141	11	was	be	AUX
cana-5634	141	12	also	also	ADV
cana-5634	141	13	considered	consider	VERB
cana-5634	141	14	.	.	PUNCT
cana-5634	142	1	the	the	DET
cana-5634	142	2	performance	performance	NOUN
cana-5634	142	3	of	of	ADP
cana-5634	142	4	four	four	NUM
cana-5634	142	5	models	model	NOUN
cana-5634	142	6	—	—	PUNCT
cana-5634	142	7	support	support	NOUN
cana-5634	142	8	vector	vector	NOUN
cana-5634	142	9	machine	machine	NOUN
cana-5634	142	10	(	(	PUNCT
cana-5634	142	11	svm	svm	PROPN
cana-5634	142	12	)	)	PUNCT
cana-5634	142	13	,	,	PUNCT
cana-5634	142	14	random	random	ADJ
cana-5634	142	15	forest	forest	NOUN
cana-5634	142	16	(	(	PUNCT
cana-5634	142	17	rf	rf	NOUN
cana-5634	142	18	)	)	PUNCT
cana-5634	142	19	,	,	PUNCT
cana-5634	142	20	gradient	gradient	NOUN
cana-5634	142	21	boosting	boost	VERB
cana-5634	142	22	machine	machine	NOUN
cana-5634	142	23	(	(	PUNCT
cana-5634	142	24	gbm	gbm	NOUN
cana-5634	142	25	)	)	PUNCT
cana-5634	142	26	,	,	PUNCT
cana-5634	142	27	and	and	CCONJ
cana-5634	142	28	deep	deep	ADJ
cana-5634	142	29	neural	neural	ADJ
cana-5634	142	30	network	network	NOUN
cana-5634	142	31	(	(	PUNCT
cana-5634	142	32	dnn)—is	dnn)—is	ADV
cana-5634	142	33	shown	show	VERB
cana-5634	142	34	in	in	ADP
cana-5634	142	35	table	table	NOUN
cana-5634	142	36	1	1	NUM
cana-5634	142	37	and	and	CCONJ
cana-5634	142	38	illustrated	illustrate	VERB
cana-5634	142	39	in	in	ADP
cana-5634	142	40	figures	figure	NOUN
cana-5634	142	41	1	1	NUM
cana-5634	142	42	and	and	CCONJ
cana-5634	142	43	2	2	NUM
cana-5634	142	44	.	.	X
cana-5634	142	45	from	from	ADP
cana-5634	142	46	figure	figure	NOUN
cana-5634	142	47	1	1	NUM
cana-5634	142	48	,	,	PUNCT
cana-5634	142	49	it	it	PRON
cana-5634	142	50	is	be	AUX
cana-5634	142	51	clear	clear	ADJ
cana-5634	142	52	that	that	SCONJ
cana-5634	142	53	the	the	DET
cana-5634	142	54	dnn	dnn	PROPN
cana-5634	142	55	outperformed	outperform	VERB
cana-5634	142	56	all	all	DET
cana-5634	142	57	other	other	ADJ
cana-5634	142	58	models	model	NOUN
cana-5634	142	59	in	in	ADP
cana-5634	142	60	every	every	DET
cana-5634	142	61	metric	metric	NOUN
cana-5634	142	62	,	,	PUNCT
cana-5634	142	63	especially	especially	ADV
cana-5634	142	64	in	in	ADP
cana-5634	142	65	recall	recall	NOUN
cana-5634	142	66	(	(	PUNCT
cana-5634	142	67	93.22	93.22	NUM
cana-5634	142	68	%	%	NOUN
cana-5634	142	69	)	)	PUNCT
cana-5634	142	70	and	and	CCONJ
cana-5634	142	71	auc	auc	NOUN
cana-5634	142	72	-	-	PUNCT
cana-5634	142	73	roc	roc	NOUN
cana-5634	142	74	(	(	PUNCT
cana-5634	142	75	95.23	95.23	NUM
cana-5634	142	76	%	%	NOUN
cana-5634	142	77	)	)	PUNCT
cana-5634	142	78	,	,	PUNCT
cana-5634	142	79	which	which	PRON
cana-5634	142	80	are	be	AUX
cana-5634	142	81	critical	critical	ADJ
cana-5634	142	82	for	for	ADP
cana-5634	142	83	detecting	detect	VERB
cana-5634	142	84	medical	medical	ADJ
cana-5634	142	85	conditions	condition	NOUN
cana-5634	142	86	accurately	accurately	ADV
cana-5634	142	87	.	.	PUNCT
cana-5634	143	1	gbm	gbm	NOUN
cana-5634	143	2	and	and	CCONJ
cana-5634	143	3	rf	rf	PRON
cana-5634	143	4	also	also	ADV
cana-5634	143	5	gave	give	VERB
cana-5634	143	6	strong	strong	ADJ
cana-5634	143	7	and	and	CCONJ
cana-5634	143	8	balanced	balanced	ADJ
cana-5634	143	9	performance	performance	NOUN
cana-5634	143	10	,	,	PUNCT
cana-5634	143	11	making	make	VERB
cana-5634	143	12	them	they	PRON
cana-5634	143	13	reliable	reliable	ADJ
cana-5634	143	14	alternatives	alternative	NOUN
cana-5634	143	15	.	.	PUNCT
cana-5634	144	1	svm	svm	PROPN
cana-5634	144	2	had	have	VERB
cana-5634	144	3	decent	decent	ADJ
cana-5634	144	4	accuracy	accuracy	NOUN
cana-5634	144	5	but	but	CCONJ
cana-5634	144	6	scored	score	VERB
cana-5634	144	7	lower	lower	ADV
cana-5634	144	8	in	in	ADP
cana-5634	144	9	recall	recall	NOUN
cana-5634	144	10	and	and	CCONJ
cana-5634	144	11	f1score	f1score	NOUN
cana-5634	144	12	,	,	PUNCT
cana-5634	144	13	meaning	mean	VERB
cana-5634	144	14	it	it	PRON
cana-5634	144	15	missed	miss	VERB
cana-5634	144	16	more	more	ADJ
cana-5634	144	17	actual	actual	ADJ
cana-5634	144	18	cases	case	NOUN
cana-5634	144	19	.	.	PUNCT
cana-5634	145	1	figure	figure	NOUN
cana-5634	145	2	1	1	NUM
cana-5634	145	3	shows	show	NOUN
cana-5634	145	4	grouped	group	VERB
cana-5634	145	5	bar	bar	NOUN
cana-5634	145	6	charts	chart	NOUN
cana-5634	145	7	for	for	ADP
cana-5634	145	8	accuracy	accuracy	NOUN
cana-5634	145	9	,	,	PUNCT
cana-5634	145	10	precision	precision	NOUN
cana-5634	145	11	,	,	PUNCT
cana-5634	145	12	and	and	CCONJ
cana-5634	145	13	recall	recall	NOUN
cana-5634	145	14	,	,	PUNCT
cana-5634	145	15	while	while	SCONJ
cana-5634	145	16	figure	figure	NOUN
cana-5634	145	17	2	2	NUM
cana-5634	145	18	shows	show	VERB
cana-5634	145	19	similar	similar	ADJ
cana-5634	145	20	graphs	graph	NOUN
cana-5634	145	21	for	for	ADP
cana-5634	145	22	f1	f1	NOUN
cana-5634	145	23	-	-	PUNCT
cana-5634	145	24	score	score	NOUN
cana-5634	145	25	and	and	CCONJ
cana-5634	145	26	auc	auc	NOUN
cana-5634	145	27	-	-	PUNCT
cana-5634	145	28	roc	roc	NOUN
cana-5634	145	29	.	.	PUNCT
cana-5634	146	1	these	these	DET
cana-5634	146	2	visual	visual	ADJ
cana-5634	146	3	comparisons	comparison	NOUN
cana-5634	146	4	help	help	NOUN
cana-5634	146	5	in	in	ADP
cana-5634	146	6	understanding	understand	VERB
cana-5634	146	7	the	the	DET
cana-5634	146	8	strengths	strength	NOUN
cana-5634	146	9	of	of	ADP
cana-5634	146	10	each	each	DET
cana-5634	146	11	model	model	NOUN
cana-5634	146	12	.	.	PUNCT
cana-5634	147	1	training	training	NOUN
cana-5634	147	2	time	time	NOUN
cana-5634	147	3	is	be	AUX
cana-5634	147	4	another	another	DET
cana-5634	147	5	important	important	ADJ
cana-5634	147	6	factor	factor	NOUN
cana-5634	147	7	,	,	PUNCT
cana-5634	147	8	especially	especially	ADV
cana-5634	147	9	when	when	SCONJ
cana-5634	147	10	the	the	DET
cana-5634	147	11	model	model	NOUN
cana-5634	147	12	needs	need	VERB
cana-5634	147	13	to	to	PART
cana-5634	147	14	be	be	AUX
cana-5634	147	15	used	use	VERB
cana-5634	147	16	in	in	ADP
cana-5634	147	17	real	real	ADJ
cana-5634	147	18	-	-	PUNCT
cana-5634	147	19	time	time	NOUN
cana-5634	147	20	applications	application	NOUN
cana-5634	147	21	or	or	CCONJ
cana-5634	147	22	where	where	SCONJ
cana-5634	147	23	computing	computing	NOUN
cana-5634	147	24	power	power	NOUN
cana-5634	147	25	is	be	AUX
cana-5634	147	26	limited	limit	VERB
cana-5634	147	27	.	.	PUNCT
cana-5634	148	1	table	table	NOUN
cana-5634	148	2	2	2	NUM
cana-5634	148	3	and	and	CCONJ
cana-5634	148	4	figure	figure	VERB
cana-5634	148	5	3	3	NUM
cana-5634	148	6	show	show	VERB
cana-5634	148	7	how	how	SCONJ
cana-5634	148	8	long	long	ADV
cana-5634	148	9	it	it	PRON
cana-5634	148	10	took	take	VERB
cana-5634	148	11	to	to	PART
cana-5634	148	12	train	train	VERB
cana-5634	148	13	each	each	DET
cana-5634	148	14	model	model	NOUN
cana-5634	148	15	.	.	PUNCT
cana-5634	149	1	the	the	DET
cana-5634	149	2	dnn	dnn	PROPN
cana-5634	149	3	took	take	VERB
cana-5634	149	4	the	the	DET
cana-5634	149	5	longest	long	ADJ
cana-5634	149	6	to	to	PART
cana-5634	149	7	train	train	VERB
cana-5634	149	8	over	over	ADP
cana-5634	149	9	36	36	NUM
cana-5634	149	10	seconds	second	NOUN
cana-5634	149	11	,	,	PUNCT
cana-5634	149	12	which	which	PRON
cana-5634	149	13	is	be	AUX
cana-5634	149	14	more	more	ADJ
cana-5634	149	15	than	than	ADP
cana-5634	149	16	three	three	NUM
cana-5634	149	17	times	time	NOUN
cana-5634	149	18	longer	long	ADJ
cana-5634	149	19	than	than	ADP
cana-5634	149	20	the	the	DET
cana-5634	149	21	other	other	ADJ
cana-5634	149	22	models	model	NOUN
cana-5634	149	23	.	.	PUNCT
cana-5634	150	1	this	this	PRON
cana-5634	150	2	shows	show	VERB
cana-5634	150	3	that	that	SCONJ
cana-5634	150	4	while	while	SCONJ
cana-5634	150	5	dnn	dnn	PROPN
cana-5634	150	6	gives	give	VERB
cana-5634	150	7	better	well	ADJ
cana-5634	150	8	results	result	NOUN
cana-5634	150	9	,	,	PUNCT
cana-5634	150	10	it	it	PRON
cana-5634	150	11	requires	require	VERB
cana-5634	150	12	more	more	ADJ
cana-5634	150	13	resources	resource	NOUN
cana-5634	150	14	and	and	CCONJ
cana-5634	150	15	time	time	NOUN
cana-5634	150	16	,	,	PUNCT
cana-5634	150	17	creating	create	VERB
cana-5634	150	18	a	a	DET
cana-5634	150	19	trade	trade	NOUN
cana-5634	150	20	-	-	PUNCT
cana-5634	150	21	off	off	NOUN
cana-5634	150	22	between	between	ADP
cana-5634	150	23	accuracy	accuracy	NOUN
cana-5634	150	24	and	and	CCONJ
cana-5634	150	25	efficiency	efficiency	NOUN
cana-5634	150	26	.	.	PUNCT
cana-5634	151	1	summary	summary	NOUN
cana-5634	151	2	of	of	ADP
cana-5634	151	3	each	each	DET
cana-5634	151	4	model	model	NOUN
cana-5634	151	5	:	:	PUNCT
cana-5634	151	6	deep	deep	ADJ
cana-5634	151	7	neural	neural	ADJ
cana-5634	151	8	network	network	NOUN
cana-5634	151	9	(	(	PUNCT
cana-5634	151	10	dnn	dnn	PROPN
cana-5634	151	11	):	):	PUNCT
cana-5634	151	12	gives	give	VERB
cana-5634	151	13	the	the	DET
cana-5634	151	14	best	good	ADJ
cana-5634	151	15	predictions	prediction	NOUN
cana-5634	151	16	but	but	CCONJ
cana-5634	151	17	takes	take	VERB
cana-5634	151	18	the	the	DET
cana-5634	151	19	longest	long	ADJ
cana-5634	151	20	to	to	PART
cana-5634	151	21	train	train	VERB
cana-5634	151	22	.	.	PUNCT
cana-5634	152	1	gradient	gradient	ADJ
cana-5634	152	2	boosting	boost	VERB
cana-5634	152	3	machine	machine	NOUN
cana-5634	152	4	(	(	PUNCT
cana-5634	152	5	gbm	gbm	NOUN
cana-5634	152	6	):	):	PUNCT
cana-5634	152	7	balances	balance	NOUN
cana-5634	152	8	good	good	ADJ
cana-5634	152	9	performance	performance	NOUN
cana-5634	152	10	and	and	CCONJ
cana-5634	152	11	speed	speed	NOUN
cana-5634	152	12	;	;	PUNCT
cana-5634	152	13	well	well	ADV
cana-5634	152	14	-	-	PUNCT
cana-5634	152	15	suited	suit	VERB
cana-5634	152	16	for	for	ADP
cana-5634	152	17	clinical	clinical	ADJ
cana-5634	152	18	settings	setting	NOUN
cana-5634	152	19	.	.	PUNCT
cana-5634	153	1	random	random	ADJ
cana-5634	153	2	forest	forest	NOUN
cana-5634	153	3	(	(	PUNCT
cana-5634	153	4	rf	rf	ADJ
cana-5634	153	5	):	):	PUNCT
cana-5634	153	6	slightly	slightly	ADV
cana-5634	153	7	faster	fast	ADV
cana-5634	153	8	than	than	ADP
cana-5634	153	9	gbm	gbm	NOUN
cana-5634	153	10	and	and	CCONJ
cana-5634	153	11	still	still	ADV
cana-5634	153	12	accurate	accurate	ADJ
cana-5634	153	13	.	.	PUNCT
cana-5634	154	1	support	support	NOUN
cana-5634	154	2	vector	vector	NOUN
cana-5634	154	3	machine	machine	NOUN
cana-5634	154	4	(	(	PUNCT
cana-5634	154	5	svm	svm	PROPN
cana-5634	154	6	):	):	PUNCT
cana-5634	154	7	fastest	fast	ADJ
cana-5634	154	8	to	to	PART
cana-5634	154	9	train	train	VERB
cana-5634	154	10	but	but	CCONJ
cana-5634	154	11	not	not	PART
cana-5634	154	12	as	as	ADV
cana-5634	154	13	good	good	ADJ
cana-5634	154	14	at	at	ADP
cana-5634	154	15	detecting	detect	VERB
cana-5634	154	16	complex	complex	ADJ
cana-5634	154	17	patterns	pattern	NOUN
cana-5634	154	18	.	.	PUNCT
cana-5634	155	1	6	6	X
cana-5634	155	2	.	.	X
cana-5634	155	3	conclusion	conclusion	NOUN
cana-5634	155	4	this	this	DET
cana-5634	155	5	study	study	NOUN
cana-5634	155	6	compared	compare	VERB
cana-5634	155	7	traditional	traditional	ADJ
cana-5634	155	8	machine	machine	NOUN
cana-5634	155	9	learning	learn	VERB
cana-5634	155	10	techniques	technique	NOUN
cana-5634	155	11	and	and	CCONJ
cana-5634	155	12	deep	deep	ADJ
cana-5634	155	13	learning	learning	NOUN
cana-5634	155	14	models	model	NOUN
cana-5634	155	15	for	for	ADP
cana-5634	155	16	predicting	predict	VERB
cana-5634	155	17	alzheimer	alzheimer	PROPN
cana-5634	155	18	’s	’s	PART
cana-5634	155	19	disease	disease	NOUN
cana-5634	155	20	using	use	VERB
cana-5634	155	21	the	the	DET
cana-5634	155	22	oasis	oasis	NOUN
cana-5634	155	23	dataset	dataset	NOUN
cana-5634	155	24	.	.	PUNCT
cana-5634	156	1	the	the	DET
cana-5634	156	2	results	result	NOUN
cana-5634	156	3	show	show	VERB
cana-5634	156	4	that	that	SCONJ
cana-5634	156	5	deep	deep	ADJ
cana-5634	156	6	learning	learning	NOUN
cana-5634	156	7	models	model	NOUN
cana-5634	156	8	,	,	PUNCT
cana-5634	156	9	especially	especially	ADV
cana-5634	156	10	when	when	SCONJ
cana-5634	156	11	fine	fine	ADV
cana-5634	156	12	-	-	PUNCT
cana-5634	156	13	tuned	tune	VERB
cana-5634	156	14	,	,	PUNCT
cana-5634	156	15	provide	provide	VERB
cana-5634	156	16	the	the	DET
cana-5634	156	17	most	most	ADV
cana-5634	156	18	accurate	accurate	ADJ
cana-5634	156	19	and	and	CCONJ
cana-5634	156	20	reliable	reliable	ADJ
cana-5634	156	21	predictions	prediction	NOUN
cana-5634	156	22	,	,	PUNCT
cana-5634	156	23	particularly	particularly	ADV
cana-5634	156	24	in	in	ADP
cana-5634	156	25	recognizing	recognize	VERB
cana-5634	156	26	true	true	ADJ
cana-5634	156	27	positive	positive	ADJ
cana-5634	156	28	cases	case	NOUN
cana-5634	156	29	and	and	CCONJ
cana-5634	156	30	achieving	achieve	VERB
cana-5634	156	31	high	high	ADJ
cana-5634	156	32	auc	auc	NOUN
cana-5634	156	33	-	-	PUNCT
cana-5634	156	34	roc	roc	NOUN
cana-5634	156	35	scores	score	NOUN
cana-5634	156	36	.	.	PUNCT
cana-5634	157	1	however	however	ADV
cana-5634	157	2	,	,	PUNCT
cana-5634	157	3	traditional	traditional	ADJ
cana-5634	157	4	ml	ml	NOUN
cana-5634	157	5	models	model	NOUN
cana-5634	157	6	like	like	ADP
cana-5634	157	7	gbm	gbm	PROPN
cana-5634	157	8	and	and	CCONJ
cana-5634	157	9	rf	rf	PRON
cana-5634	157	10	also	also	ADV
cana-5634	157	11	performed	perform	VERB
cana-5634	157	12	very	very	ADV
cana-5634	157	13	well	well	ADV
cana-5634	157	14	and	and	CCONJ
cana-5634	157	15	required	require	VERB
cana-5634	157	16	less	less	ADJ
cana-5634	157	17	training	training	NOUN
cana-5634	157	18	time	time	NOUN
cana-5634	157	19	,	,	PUNCT
cana-5634	157	20	making	make	VERB
cana-5634	157	21	them	they	PRON
cana-5634	157	22	practical	practical	ADJ
cana-5634	157	23	for	for	ADP
cana-5634	157	24	use	use	NOUN
cana-5634	157	25	in	in	ADP
cana-5634	157	26	real	real	ADJ
cana-5634	157	27	-	-	PUNCT
cana-5634	157	28	world	world	NOUN
cana-5634	157	29	healthcare	healthcare	NOUN
cana-5634	157	30	applications	application	NOUN
cana-5634	157	31	.	.	PUNCT
cana-5634	158	1	although	although	SCONJ
cana-5634	158	2	svm	svm	PROPN
cana-5634	158	3	is	be	AUX
cana-5634	158	4	the	the	DET
cana-5634	158	5	fastest	fast	ADJ
cana-5634	158	6	,	,	PUNCT
cana-5634	158	7	its	its	PRON
cana-5634	158	8	lower	low	ADJ
cana-5634	158	9	accuracy	accuracy	NOUN
cana-5634	158	10	makes	make	VERB
cana-5634	158	11	it	it	PRON
cana-5634	158	12	more	more	ADV
cana-5634	158	13	suitable	suitable	ADJ
cana-5634	158	14	for	for	ADP
cana-5634	158	15	simpler	simple	ADJ
cana-5634	158	16	tasks	task	NOUN
cana-5634	158	17	.	.	PUNCT
cana-5634	159	1	overall	overall	ADV
cana-5634	159	2	,	,	PUNCT
cana-5634	159	3	the	the	DET
cana-5634	159	4	findings	finding	NOUN
cana-5634	159	5	suggest	suggest	VERB
cana-5634	159	6	that	that	SCONJ
cana-5634	159	7	deep	deep	ADJ
cana-5634	159	8	learning	learning	NOUN
cana-5634	159	9	is	be	AUX
cana-5634	159	10	highly	highly	ADV
cana-5634	159	11	effective	effective	ADJ
cana-5634	159	12	,	,	PUNCT
cana-5634	159	13	but	but	CCONJ
cana-5634	159	14	machine	machine	NOUN
cana-5634	159	15	learning	learning	NOUN
cana-5634	159	16	remains	remain	VERB
cana-5634	159	17	a	a	DET
cana-5634	159	18	strong	strong	ADJ
cana-5634	159	19	choice	choice	NOUN
cana-5634	159	20	when	when	SCONJ
cana-5634	159	21	computing	compute	VERB
cana-5634	159	22	power	power	NOUN
cana-5634	159	23	or	or	CCONJ
cana-5634	159	24	data	datum	NOUN
cana-5634	159	25	is	be	AUX
cana-5634	159	26	limited	limited	ADJ
cana-5634	159	27	.	.	PUNCT
cana-5634	160	1	7	7	X
cana-5634	160	2	.	.	X
cana-5634	160	3	future	future	ADJ
cana-5634	160	4	research	research	NOUN
cana-5634	160	5	there	there	PRON
cana-5634	160	6	are	be	VERB
cana-5634	160	7	several	several	ADJ
cana-5634	160	8	ways	way	NOUN
cana-5634	160	9	to	to	PART
cana-5634	160	10	build	build	VERB
cana-5634	160	11	on	on	ADP
cana-5634	160	12	this	this	DET
cana-5634	160	13	research	research	NOUN
cana-5634	160	14	in	in	ADP
cana-5634	160	15	the	the	DET
cana-5634	160	16	future	future	NOUN
cana-5634	160	17	.	.	PUNCT
cana-5634	161	1	one	one	NUM
cana-5634	161	2	key	key	ADJ
cana-5634	161	3	direction	direction	NOUN
cana-5634	161	4	is	be	AUX
cana-5634	161	5	to	to	PART
cana-5634	161	6	combine	combine	VERB
cana-5634	161	7	different	different	ADJ
cana-5634	161	8	types	type	NOUN
cana-5634	161	9	of	of	ADP
cana-5634	161	10	data	datum	NOUN
cana-5634	161	11	—	—	PUNCT
cana-5634	161	12	such	such	ADJ
cana-5634	161	13	as	as	ADP
cana-5634	161	14	mri	mri	NOUN
cana-5634	161	15	images	image	NOUN
cana-5634	161	16	,	,	PUNCT
cana-5634	161	17	cognitive	cognitive	ADJ
cana-5634	161	18	tests	test	NOUN
cana-5634	161	19	,	,	PUNCT
cana-5634	161	20	and	and	CCONJ
cana-5634	161	21	genetic	genetic	ADJ
cana-5634	161	22	details	detail	NOUN
cana-5634	161	23	—	—	PUNCT
cana-5634	161	24	to	to	PART
cana-5634	161	25	create	create	VERB
cana-5634	161	26	more	more	ADV
cana-5634	161	27	complete	complete	ADJ
cana-5634	161	28	and	and	CCONJ
cana-5634	161	29	accurate	accurate	ADJ
cana-5634	161	30	prediction	prediction	NOUN
cana-5634	161	31	models	model	NOUN
cana-5634	161	32	.	.	PUNCT
cana-5634	162	1	another	another	DET
cana-5634	162	2	important	important	ADJ
cana-5634	162	3	area	area	NOUN
cana-5634	162	4	is	be	AUX
cana-5634	162	5	using	use	VERB
cana-5634	162	6	explainable	explainable	ADJ
cana-5634	162	7	ai	ai	NOUN
cana-5634	162	8	(	(	PUNCT
cana-5634	162	9	xai	xai	PROPN
cana-5634	162	10	)	)	PUNCT
cana-5634	162	11	,	,	PUNCT
cana-5634	162	12	which	which	PRON
cana-5634	162	13	can	can	AUX
cana-5634	162	14	help	help	VERB
cana-5634	162	15	make	make	VERB
cana-5634	162	16	deep	deep	ADJ
cana-5634	162	17	learning	learning	NOUN
cana-5634	162	18	models	model	NOUN
cana-5634	162	19	easier	easy	ADJ
cana-5634	162	20	to	to	PART
cana-5634	162	21	understand	understand	VERB
cana-5634	162	22	and	and	CCONJ
cana-5634	162	23	more	more	ADV
cana-5634	162	24	trustworthy	trustworthy	ADJ
cana-5634	162	25	for	for	ADP
cana-5634	162	26	doctors	doctor	NOUN
cana-5634	162	27	and	and	CCONJ
cana-5634	162	28	medical	medical	ADJ
cana-5634	162	29	staff	staff	NOUN
cana-5634	162	30	.	.	PUNCT
cana-5634	163	1	also	also	ADV
cana-5634	163	2	,	,	PUNCT
cana-5634	163	3	applying	apply	VERB
cana-5634	163	4	transfer	transfer	NOUN
cana-5634	163	5	learning	learning	NOUN
cana-5634	163	6	—	—	PUNCT
cana-5634	163	7	where	where	SCONJ
cana-5634	163	8	models	model	NOUN
cana-5634	163	9	trained	train	VERB
cana-5634	163	10	on	on	ADP
cana-5634	163	11	larger	large	ADJ
cana-5634	163	12	datasets	dataset	NOUN
cana-5634	163	13	are	be	AUX
cana-5634	163	14	reused	reuse	VERB
cana-5634	163	15	—	—	PUNCT
cana-5634	163	16	can	can	AUX
cana-5634	163	17	help	help	VERB
cana-5634	163	18	improve	improve	VERB
cana-5634	163	19	performance	performance	NOUN
cana-5634	163	20	,	,	PUNCT
cana-5634	163	21	especially	especially	ADV
cana-5634	163	22	when	when	SCONJ
cana-5634	163	23	communications	communication	NOUN
cana-5634	163	24	on	on	ADP
cana-5634	163	25	applied	apply	VERB
cana-5634	163	26	nonlinear	nonlinear	ADJ
cana-5634	163	27	analysis	analysis	NOUN
cana-5634	163	28	issn	issn	NOUN
cana-5634	163	29	:	:	PUNCT
cana-5634	163	30	1074	1074	NUM
cana-5634	163	31	-	-	PUNCT
cana-5634	163	32	133x	133x	NUM
cana-5634	163	33	vol	vol	VERB
cana-5634	163	34	32	32	NUM
cana-5634	163	35	no.1s	no.1s	PROPN
cana-5634	163	36	(	(	PUNCT
cana-5634	163	37	2025	2025	NUM
cana-5634	163	38	)	)	PUNCT
cana-5634	163	39	677	677	NUM
cana-5634	163	40	https://internationalpubls.com	https://internationalpubls.com	X
cana-5634	163	41	working	work	VERB
cana-5634	163	42	with	with	ADP
cana-5634	163	43	small	small	ADJ
cana-5634	163	44	datasets	dataset	NOUN
cana-5634	163	45	like	like	ADP
cana-5634	163	46	oasis	oasis	NOUN
cana-5634	163	47	.	.	PUNCT
cana-5634	164	1	additionally	additionally	ADV
cana-5634	164	2	,	,	PUNCT
cana-5634	164	3	future	future	ADJ
cana-5634	164	4	systems	system	NOUN
cana-5634	164	5	should	should	AUX
cana-5634	164	6	aim	aim	VERB
cana-5634	164	7	to	to	PART
cana-5634	164	8	work	work	VERB
cana-5634	164	9	in	in	ADP
cana-5634	164	10	real	real	ADJ
cana-5634	164	11	-	-	PUNCT
cana-5634	164	12	time	time	NOUN
cana-5634	164	13	using	use	VERB
cana-5634	164	14	lightweight	lightweight	ADJ
cana-5634	164	15	models	model	NOUN
cana-5634	164	16	that	that	PRON
cana-5634	164	17	can	can	AUX
cana-5634	164	18	be	be	AUX
cana-5634	164	19	deployed	deploy	VERB
cana-5634	164	20	on	on	ADP
cana-5634	164	21	mobile	mobile	ADJ
cana-5634	164	22	or	or	CCONJ
cana-5634	164	23	portable	portable	ADJ
cana-5634	164	24	devices	device	NOUN
cana-5634	164	25	for	for	ADP
cana-5634	164	26	early	early	ADJ
cana-5634	164	27	screening	screening	NOUN
cana-5634	164	28	.	.	PUNCT
cana-5634	165	1	lastly	lastly	ADV
cana-5634	165	2	,	,	PUNCT
cana-5634	165	3	future	future	ADJ
cana-5634	165	4	studies	study	NOUN
cana-5634	165	5	should	should	AUX
cana-5634	165	6	look	look	VERB
cana-5634	165	7	at	at	ADP
cana-5634	165	8	long	long	ADJ
cana-5634	165	9	-	-	PUNCT
cana-5634	165	10	term	term	NOUN
cana-5634	165	11	data	datum	NOUN
cana-5634	165	12	(	(	PUNCT
cana-5634	165	13	longitudinal	longitudinal	ADJ
cana-5634	165	14	analysis	analysis	NOUN
cana-5634	165	15	)	)	PUNCT
cana-5634	165	16	to	to	PART
cana-5634	165	17	track	track	VERB
cana-5634	165	18	how	how	SCONJ
cana-5634	165	19	the	the	DET
cana-5634	165	20	disease	disease	NOUN
cana-5634	165	21	progresses	progress	VERB
cana-5634	165	22	over	over	ADP
cana-5634	165	23	time	time	NOUN
cana-5634	165	24	,	,	PUNCT
cana-5634	165	25	helping	help	VERB
cana-5634	165	26	to	to	PART
cana-5634	165	27	plan	plan	VERB
cana-5634	165	28	treatment	treatment	NOUN
cana-5634	165	29	more	more	ADV
cana-5634	165	30	effectively	effectively	ADV
cana-5634	165	31	.	.	PUNCT
cana-5634	166	1	these	these	DET
cana-5634	166	2	advancements	advancement	NOUN
cana-5634	166	3	can	can	AUX
cana-5634	166	4	improve	improve	VERB
cana-5634	166	5	the	the	DET
cana-5634	166	6	accuracy	accuracy	NOUN
cana-5634	166	7	,	,	PUNCT
cana-5634	166	8	usability	usability	NOUN
cana-5634	166	9	,	,	PUNCT
cana-5634	166	10	and	and	CCONJ
cana-5634	166	11	practical	practical	ADJ
cana-5634	166	12	impact	impact	NOUN
cana-5634	166	13	of	of	ADP
cana-5634	166	14	alzheimer	alzheimer	PROPN
cana-5634	166	15	’s	’s	PART
cana-5634	166	16	disease	disease	NOUN
cana-5634	166	17	prediction	prediction	NOUN
cana-5634	166	18	systems	system	NOUN
cana-5634	166	19	.	.	PUNCT
cana-5634	167	1	references	reference	NOUN
cana-5634	167	2	[	[	X
cana-5634	167	3	1	1	NUM
cana-5634	167	4	]	]	PUNCT
cana-5634	167	5	m.	m.	NOUN
cana-5634	167	6	sarraf	sarraf	NOUN
cana-5634	167	7	and	and	CCONJ
cana-5634	167	8	g.	g.	PROPN
cana-5634	167	9	tofighi	tofighi	PROPN
cana-5634	167	10	,	,	PUNCT
cana-5634	167	11	"	"	PUNCT
cana-5634	167	12	deepad	deepad	NOUN
cana-5634	167	13	:	:	PUNCT
cana-5634	167	14	alzheimer	alzheimer	PROPN
cana-5634	167	15	’s	’s	PART
cana-5634	167	16	disease	disease	NOUN
cana-5634	167	17	classification	classification	NOUN
cana-5634	167	18	via	via	ADP
cana-5634	167	19	deep	deep	ADJ
cana-5634	167	20	convolutional	convolutional	ADJ
cana-5634	167	21	neural	neural	ADJ
cana-5634	167	22	networks	network	NOUN
cana-5634	167	23	using	use	VERB
cana-5634	167	24	mri	mri	NOUN
cana-5634	167	25	and	and	CCONJ
cana-5634	167	26	fmri	fmri	NOUN
cana-5634	167	27	,	,	PUNCT
cana-5634	167	28	"	"	PUNCT
cana-5634	167	29	arxiv	arxiv	PROPN
cana-5634	167	30	preprint	preprint	NOUN
cana-5634	167	31	arxiv:1602.05691	arxiv:1602.05691	NOUN
cana-5634	167	32	,	,	PUNCT
cana-5634	167	33	2016	2016	NUM
cana-5634	167	34	.	.	PUNCT
cana-5634	168	1	[	[	X
cana-5634	168	2	2	2	NUM
cana-5634	168	3	]	]	PUNCT
cana-5634	168	4	r.	r.	PROPN
cana-5634	168	5	ortiz	ortiz	PROPN
cana-5634	168	6	-	-	PUNCT
cana-5634	168	7	sanz	sanz	PROPN
cana-5634	168	8	et	et	PROPN
cana-5634	168	9	al	al	PROPN
cana-5634	168	10	.	.	PROPN
cana-5634	168	11	,	,	PUNCT
cana-5634	168	12	"	"	PUNCT
cana-5634	168	13	alzheimer	alzheimer	X
cana-5634	168	14	’s	’s	PART
cana-5634	168	15	disease	disease	NOUN
cana-5634	168	16	detection	detection	NOUN
cana-5634	168	17	using	use	VERB
cana-5634	168	18	machine	machine	NOUN
cana-5634	168	19	learning	learning	NOUN
cana-5634	168	20	techniques	technique	NOUN
cana-5634	168	21	,	,	PUNCT
cana-5634	168	22	"	"	PUNCT
cana-5634	168	23	int	int	NOUN
cana-5634	168	24	.	.	PUNCT
cana-5634	169	1	j.	j.	PROPN
cana-5634	169	2	environ	environ	PROPN
cana-5634	169	3	.	.	PUNCT
cana-5634	170	1	res	re	NOUN
cana-5634	170	2	.	.	PUNCT
cana-5634	171	1	public	public	ADJ
cana-5634	171	2	health	health	NOUN
cana-5634	171	3	,	,	PUNCT
cana-5634	171	4	vol	vol	NOUN
cana-5634	171	5	.	.	PROPN
cana-5634	171	6	18	18	NUM
cana-5634	171	7	,	,	PUNCT
cana-5634	171	8	no	no	INTJ
cana-5634	171	9	.	.	NOUN
cana-5634	171	10	21	21	NUM
cana-5634	171	11	,	,	PUNCT
cana-5634	171	12	pp	pp	ADJ
cana-5634	171	13	.	.	PUNCT
cana-5634	172	1	1–17	1–17	NOUN
cana-5634	172	2	,	,	PUNCT
cana-5634	172	3	2021	2021	NUM
cana-5634	172	4	.	.	PUNCT
cana-5634	173	1	[	[	X
cana-5634	173	2	3	3	X
cana-5634	173	3	]	]	PUNCT
cana-5634	173	4	s.	s.	PROPN
cana-5634	173	5	basaia	basaia	PROPN
cana-5634	173	6	et	et	PROPN
cana-5634	173	7	al	al	PROPN
cana-5634	173	8	.	.	PROPN
cana-5634	173	9	,	,	PUNCT
cana-5634	173	10	"	"	PUNCT
cana-5634	173	11	automated	automate	VERB
cana-5634	173	12	classification	classification	NOUN
cana-5634	173	13	of	of	ADP
cana-5634	173	14	alzheimer	alzheimer	PROPN
cana-5634	173	15	’s	’s	PART
cana-5634	173	16	disease	disease	NOUN
cana-5634	173	17	and	and	CCONJ
cana-5634	173	18	mild	mild	ADJ
cana-5634	173	19	cognitive	cognitive	ADJ
cana-5634	173	20	impairment	impairment	NOUN
cana-5634	173	21	using	use	VERB
cana-5634	173	22	a	a	DET
cana-5634	173	23	single	single	ADJ
cana-5634	173	24	mri	mri	NOUN
cana-5634	173	25	and	and	CCONJ
cana-5634	173	26	deep	deep	ADJ
cana-5634	173	27	neural	neural	ADJ
cana-5634	173	28	networks	network	NOUN
cana-5634	173	29	,	,	PUNCT
cana-5634	173	30	"	"	PUNCT
cana-5634	173	31	neuroimage	neuroimage	NOUN
cana-5634	173	32	:	:	PUNCT
cana-5634	173	33	clinical	clinical	ADJ
cana-5634	173	34	,	,	PUNCT
cana-5634	173	35	vol	vol	NOUN
cana-5634	173	36	.	.	PROPN
cana-5634	173	37	21	21	NUM
cana-5634	173	38	,	,	PUNCT
cana-5634	173	39	2019	2019	NUM
cana-5634	173	40	.	.	PUNCT
cana-5634	174	1	[	[	X
cana-5634	174	2	4	4	NUM
cana-5634	174	3	]	]	X
cana-5634	174	4	r.	r.	PROPN
cana-5634	174	5	suk	suk	PROPN
cana-5634	174	6	,	,	PUNCT
cana-5634	174	7	s.	s.	PROPN
cana-5634	174	8	lee	lee	PROPN
cana-5634	174	9	,	,	PUNCT
cana-5634	174	10	and	and	CCONJ
cana-5634	174	11	d.	d.	PROPN
cana-5634	174	12	shen	shen	PROPN
cana-5634	174	13	,	,	PUNCT
cana-5634	174	14	"	"	PUNCT
cana-5634	174	15	latent	latent	ADJ
cana-5634	174	16	feature	feature	NOUN
cana-5634	174	17	representation	representation	NOUN
cana-5634	174	18	with	with	ADP
cana-5634	174	19	stacked	stack	VERB
cana-5634	174	20	auto	auto	NOUN
cana-5634	174	21	-	-	PUNCT
cana-5634	174	22	encoder	encoder	NOUN
cana-5634	174	23	for	for	ADP
cana-5634	174	24	ad	ad	NOUN
cana-5634	174	25	/	/	SYM
cana-5634	174	26	mci	mci	NOUN
cana-5634	174	27	diagnosis	diagnosis	NOUN
cana-5634	174	28	,	,	PUNCT
cana-5634	174	29	"	"	PUNCT
cana-5634	174	30	brain	brain	NOUN
cana-5634	174	31	structure	structure	NOUN
cana-5634	174	32	and	and	CCONJ
cana-5634	174	33	function	function	NOUN
cana-5634	174	34	,	,	PUNCT
cana-5634	174	35	vol	vol	NOUN
cana-5634	174	36	.	.	NOUN
cana-5634	174	37	220	220	NUM
cana-5634	174	38	,	,	PUNCT
cana-5634	174	39	no	no	INTJ
cana-5634	174	40	.	.	NOUN
cana-5634	174	41	2	2	NUM
cana-5634	174	42	,	,	PUNCT
cana-5634	174	43	pp	pp	ADJ
cana-5634	174	44	.	.	PUNCT
cana-5634	175	1	841–859	841–859	NUM
cana-5634	175	2	,	,	PUNCT
cana-5634	175	3	2015	2015	NUM
cana-5634	175	4	.	.	PUNCT
cana-5634	176	1	[	[	X
cana-5634	176	2	5	5	X
cana-5634	176	3	]	]	PUNCT
cana-5634	176	4	k.	k.	PROPN
cana-5634	176	5	jie	jie	PROPN
cana-5634	176	6	et	et	PROPN
cana-5634	176	7	al	al	PROPN
cana-5634	176	8	.	.	PROPN
cana-5634	176	9	,	,	PUNCT
cana-5634	176	10	"	"	PUNCT
cana-5634	176	11	predicting	predict	VERB
cana-5634	176	12	alzheimer	alzheimer	PROPN
cana-5634	176	13	’s	’s	PART
cana-5634	176	14	disease	disease	NOUN
cana-5634	176	15	using	use	VERB
cana-5634	176	16	brain	brain	NOUN
cana-5634	176	17	mri	mri	NOUN
cana-5634	176	18	with	with	ADP
cana-5634	176	19	a	a	DET
cana-5634	176	20	deep	deep	ADJ
cana-5634	176	21	convolutional	convolutional	ADJ
cana-5634	176	22	neural	neural	ADJ
cana-5634	176	23	network	network	NOUN
cana-5634	176	24	,	,	PUNCT
cana-5634	176	25	"	"	PUNCT
cana-5634	176	26	frontiers	frontier	NOUN
cana-5634	176	27	in	in	ADP
cana-5634	176	28	neuroscience	neuroscience	NOUN
cana-5634	176	29	,	,	PUNCT
cana-5634	176	30	vol	vol	NOUN
cana-5634	176	31	.	.	PROPN
cana-5634	176	32	14	14	NUM
cana-5634	176	33	,	,	PUNCT
cana-5634	176	34	2020	2020	NUM
cana-5634	176	35	.	.	PUNCT
cana-5634	177	1	[	[	X
cana-5634	177	2	6	6	NUM
cana-5634	177	3	]	]	PUNCT
cana-5634	177	4	a.	a.	NOUN
cana-5634	177	5	farooq	farooq	PROPN
cana-5634	177	6	,	,	PUNCT
cana-5634	177	7	s.	s.	PROPN
cana-5634	177	8	anwar	anwar	PROPN
cana-5634	177	9	,	,	PUNCT
cana-5634	177	10	and	and	CCONJ
cana-5634	177	11	a.	a.	NOUN
cana-5634	177	12	awais	awais	PROPN
cana-5634	177	13	,	,	PUNCT
cana-5634	177	14	"	"	PUNCT
cana-5634	177	15	a	a	DET
cana-5634	177	16	deep	deep	ADJ
cana-5634	177	17	cnn	cnn	NOUN
cana-5634	177	18	based	base	VERB
cana-5634	177	19	multi	multi	ADJ
cana-5634	177	20	-	-	ADJ
cana-5634	177	21	class	class	ADJ
cana-5634	177	22	classification	classification	NOUN
cana-5634	177	23	of	of	ADP
cana-5634	177	24	alzheimer	alzheimer	PROPN
cana-5634	177	25	’s	’s	PART
cana-5634	177	26	disease	disease	NOUN
cana-5634	177	27	using	use	VERB
cana-5634	177	28	mri	mri	NOUN
cana-5634	177	29	,	,	PUNCT
cana-5634	177	30	"	"	PUNCT
cana-5634	177	31	neural	neural	ADJ
cana-5634	177	32	computing	computing	NOUN
cana-5634	177	33	and	and	CCONJ
cana-5634	177	34	applications	application	NOUN
cana-5634	177	35	,	,	PUNCT
cana-5634	177	36	vol	vol	NOUN
cana-5634	177	37	.	.	PROPN
cana-5634	177	38	32	32	NUM
cana-5634	177	39	,	,	PUNCT
cana-5634	177	40	pp	pp	ADJ
cana-5634	177	41	.	.	PUNCT
cana-5634	177	42	999	999	NUM
cana-5634	177	43	–	–	PUNCT
cana-5634	177	44	1012	1012	NUM
cana-5634	177	45	,	,	PUNCT
cana-5634	177	46	2020	2020	NUM
cana-5634	177	47	.	.	PUNCT
cana-5634	178	1	[	[	X
cana-5634	178	2	7	7	X
cana-5634	178	3	]	]	X
cana-5634	178	4	n.	n.	NOUN
cana-5634	178	5	salvatore	salvatore	PROPN
cana-5634	178	6	et	et	PROPN
cana-5634	178	7	al	al	PROPN
cana-5634	178	8	.	.	PROPN
cana-5634	178	9	,	,	PUNCT
cana-5634	178	10	"	"	PUNCT
cana-5634	178	11	machine	machine	NOUN
cana-5634	178	12	learning	learn	VERB
cana-5634	178	13	on	on	ADP
cana-5634	178	14	brain	brain	NOUN
cana-5634	178	15	mri	mri	NOUN
cana-5634	178	16	data	datum	NOUN
cana-5634	178	17	for	for	ADP
cana-5634	178	18	differential	differential	ADJ
cana-5634	178	19	diagnosis	diagnosis	NOUN
cana-5634	178	20	of	of	ADP
cana-5634	178	21	parkinson	parkinson	NOUN
cana-5634	178	22	’s	’s	PART
cana-5634	178	23	disease	disease	NOUN
cana-5634	178	24	and	and	CCONJ
cana-5634	178	25	progressive	progressive	ADJ
cana-5634	178	26	supranuclear	supranuclear	ADJ
cana-5634	178	27	palsy	palsy	ADJ
cana-5634	178	28	,	,	PUNCT
cana-5634	178	29	"	"	PUNCT
cana-5634	178	30	journal	journal	NOUN
cana-5634	178	31	of	of	ADP
cana-5634	178	32	neuroscience	neuroscience	NOUN
cana-5634	178	33	methods	method	NOUN
cana-5634	178	34	,	,	PUNCT
cana-5634	178	35	vol	vol	NOUN
cana-5634	178	36	.	.	PROPN
cana-5634	178	37	222	222	NUM
cana-5634	178	38	,	,	PUNCT
cana-5634	178	39	pp	pp	ADJ
cana-5634	178	40	.	.	PUNCT
cana-5634	179	1	230–237	230–237	NUM
cana-5634	179	2	,	,	PUNCT
cana-5634	179	3	2014	2014	NUM
cana-5634	179	4	.	.	PUNCT
cana-5634	180	1	[	[	X
cana-5634	180	2	8	8	NUM
cana-5634	180	3	]	]	PUNCT
cana-5634	180	4	f.	f.	PROPN
cana-5634	180	5	zhang	zhang	PROPN
cana-5634	180	6	et	et	PROPN
cana-5634	180	7	al	al	PROPN
cana-5634	180	8	.	.	PROPN
cana-5634	180	9	,	,	PUNCT
cana-5634	180	10	"	"	PUNCT
cana-5634	180	11	multi	multi	ADJ
cana-5634	180	12	-	-	ADJ
cana-5634	180	13	modal	modal	ADJ
cana-5634	180	14	classification	classification	NOUN
cana-5634	180	15	of	of	ADP
cana-5634	180	16	alzheimer	alzheimer	PROPN
cana-5634	180	17	's	's	PART
cana-5634	180	18	disease	disease	NOUN
cana-5634	180	19	using	use	VERB
cana-5634	180	20	nonlinear	nonlinear	ADJ
cana-5634	180	21	graph	graph	NOUN
cana-5634	180	22	fusion	fusion	NOUN
cana-5634	180	23	,	,	PUNCT
cana-5634	180	24	"	"	PUNCT
cana-5634	180	25	pattern	pattern	NOUN
cana-5634	180	26	recognition	recognition	NOUN
cana-5634	180	27	,	,	PUNCT
cana-5634	180	28	vol	vol	NOUN
cana-5634	180	29	.	.	PROPN
cana-5634	180	30	63	63	NUM
cana-5634	180	31	,	,	PUNCT
cana-5634	180	32	pp	pp	ADJ
cana-5634	180	33	.	.	PUNCT
cana-5634	181	1	171–181	171–181	NUM
cana-5634	181	2	,	,	PUNCT
cana-5634	181	3	2017	2017	NUM
cana-5634	181	4	.	.	PUNCT
cana-5634	182	1	[	[	X
cana-5634	182	2	9	9	NUM
cana-5634	182	3	]	]	PUNCT
cana-5634	182	4	p.	p.	NOUN
cana-5634	182	5	padilla	padilla	PROPN
cana-5634	182	6	et	et	PROPN
cana-5634	182	7	al	al	PROPN
cana-5634	182	8	.	.	PROPN
cana-5634	182	9	,	,	PUNCT
cana-5634	182	10	"	"	PUNCT
cana-5634	182	11	machine	machine	NOUN
cana-5634	182	12	learning	learning	NOUN
cana-5634	182	13	approaches	approach	NOUN
cana-5634	182	14	in	in	ADP
cana-5634	182	15	alzheimer	alzheimer	PROPN
cana-5634	182	16	’s	’s	PART
cana-5634	182	17	disease	disease	NOUN
cana-5634	182	18	prediction	prediction	NOUN
cana-5634	182	19	using	use	VERB
cana-5634	182	20	oasis	oasis	NOUN
cana-5634	182	21	dataset	dataset	NOUN
cana-5634	182	22	,	,	PUNCT
cana-5634	182	23	"	"	PUNCT
cana-5634	182	24	procedia	procedia	NOUN
cana-5634	182	25	computer	computer	NOUN
cana-5634	182	26	science	science	NOUN
cana-5634	182	27	,	,	PUNCT
cana-5634	182	28	vol	vol	NOUN
cana-5634	182	29	.	.	PROPN
cana-5634	182	30	100	100	NUM
cana-5634	182	31	,	,	PUNCT
cana-5634	182	32	pp	pp	ADJ
cana-5634	182	33	.	.	PUNCT
cana-5634	183	1	365–371	365–371	NUM
cana-5634	183	2	,	,	PUNCT
cana-5634	183	3	2016	2016	NUM
cana-5634	183	4	.	.	PUNCT
cana-5634	184	1	[	[	X
cana-5634	184	2	10	10	NUM
cana-5634	184	3	]	]	PUNCT
cana-5634	184	4	a.	a.	NOUN
cana-5634	184	5	esmaeilzadeh	esmaeilzadeh	PROPN
cana-5634	184	6	,	,	PUNCT
cana-5634	184	7	d.	d.	PROPN
cana-5634	184	8	belivanis	belivanis	PROPN
cana-5634	184	9	,	,	PUNCT
cana-5634	184	10	a.	a.	NOUN
cana-5634	184	11	p.	p.	NOUN
cana-5634	184	12	jafari	jafari	PROPN
cana-5634	184	13	,	,	PUNCT
cana-5634	184	14	and	and	CCONJ
cana-5634	184	15	d.	d.	PROPN
cana-5634	184	16	p.	p.	PROPN
cana-5634	184	17	papageorgiou	papageorgiou	PROPN
cana-5634	184	18	,	,	PUNCT
cana-5634	184	19	"	"	PUNCT
cana-5634	184	20	end	end	NOUN
cana-5634	184	21	-	-	PUNCT
cana-5634	184	22	to	to	ADP
cana-5634	184	23	-	-	PUNCT
cana-5634	184	24	end	end	NOUN
cana-5634	184	25	alzheimer	alzheimer	PROPN
cana-5634	184	26	’s	’s	PART
cana-5634	184	27	disease	disease	NOUN
cana-5634	184	28	diagnosis	diagnosis	NOUN
cana-5634	184	29	and	and	CCONJ
cana-5634	184	30	biomarker	biomarker	NOUN
cana-5634	184	31	identification	identification	NOUN
cana-5634	184	32	,	,	PUNCT
cana-5634	184	33	"	"	PUNCT
cana-5634	184	34	medical	medical	ADJ
cana-5634	184	35	image	image	NOUN
cana-5634	184	36	analysis	analysis	NOUN
cana-5634	184	37	,	,	PUNCT
cana-5634	184	38	vol	vol	NOUN
cana-5634	184	39	.	.	PROPN
cana-5634	184	40	63	63	NUM
cana-5634	184	41	,	,	PUNCT
cana-5634	184	42	2020	2020	NUM
cana-5634	184	43	.	.	PUNCT
cana-5634	185	1	[	[	X
cana-5634	185	2	11	11	NUM
cana-5634	185	3	]	]	PUNCT
cana-5634	185	4	h.	h.	PROPN
cana-5634	185	5	liu	liu	PROPN
cana-5634	185	6	et	et	PROPN
cana-5634	185	7	al	al	PROPN
cana-5634	185	8	.	.	PROPN
cana-5634	185	9	,	,	PUNCT
cana-5634	185	10	"	"	PUNCT
cana-5634	185	11	combining	combine	VERB
cana-5634	185	12	multiple	multiple	ADJ
cana-5634	185	13	imaging	imaging	NOUN
cana-5634	185	14	modalities	modality	NOUN
cana-5634	185	15	for	for	ADP
cana-5634	185	16	ad	ad	NOUN
cana-5634	185	17	diagnosis	diagnosis	NOUN
cana-5634	185	18	using	use	VERB
cana-5634	185	19	stacked	stack	VERB
cana-5634	185	20	generalization	generalization	NOUN
cana-5634	185	21	,	,	PUNCT
cana-5634	185	22	"	"	PUNCT
cana-5634	185	23	neuroimage	neuroimage	NOUN
cana-5634	185	24	,	,	PUNCT
cana-5634	185	25	vol	vol	NOUN
cana-5634	185	26	.	.	PROPN
cana-5634	185	27	59	59	NUM
cana-5634	185	28	,	,	PUNCT
cana-5634	185	29	no	no	INTJ
cana-5634	185	30	.	.	NOUN
cana-5634	185	31	3	3	NUM
cana-5634	185	32	,	,	PUNCT
cana-5634	185	33	pp	pp	ADJ
cana-5634	185	34	.	.	PUNCT
cana-5634	185	35	2230–2239	2230–2239	NUM
cana-5634	185	36	,	,	PUNCT
cana-5634	185	37	2012	2012	NUM
cana-5634	185	38	.	.	PUNCT
cana-5634	186	1	[	[	X
cana-5634	186	2	12	12	NUM
cana-5634	186	3	]	]	PUNCT
cana-5634	186	4	s.	s.	PROPN
cana-5634	186	5	wang	wang	PROPN
cana-5634	186	6	et	et	PROPN
cana-5634	186	7	al	al	PROPN
cana-5634	186	8	.	.	PROPN
cana-5634	186	9	,	,	PUNCT
cana-5634	186	10	"	"	PUNCT
cana-5634	186	11	alzheimer	alzheimer	PROPN
cana-5634	186	12	’s	’s	PART
cana-5634	186	13	disease	disease	NOUN
cana-5634	186	14	classification	classification	NOUN
cana-5634	186	15	using	use	VERB
cana-5634	186	16	deep	deep	ADJ
cana-5634	186	17	convolutional	convolutional	ADJ
cana-5634	186	18	neural	neural	ADJ
cana-5634	186	19	networks	network	NOUN
cana-5634	186	20	,	,	PUNCT
cana-5634	186	21	"	"	PUNCT
cana-5634	186	22	j.	j.	PROPN
cana-5634	186	23	medical	medical	PROPN
cana-5634	186	24	imaging	imaging	PROPN
cana-5634	186	25	and	and	CCONJ
cana-5634	186	26	health	health	NOUN
cana-5634	186	27	informatics	informatic	NOUN
cana-5634	186	28	,	,	PUNCT
cana-5634	186	29	vol	vol	NOUN
cana-5634	186	30	.	.	PROPN
cana-5634	186	31	6	6	NUM
cana-5634	186	32	,	,	PUNCT
cana-5634	186	33	no	no	INTJ
cana-5634	186	34	.	.	NOUN
cana-5634	186	35	5	5	NUM
cana-5634	186	36	,	,	PUNCT
cana-5634	186	37	pp	pp	ADJ
cana-5634	186	38	.	.	PUNCT
cana-5634	187	1	1416–1424	1416–1424	NUM
cana-5634	187	2	,	,	PUNCT
cana-5634	187	3	2016	2016	NUM
cana-5634	187	4	.	.	PUNCT
cana-5634	188	1	[	[	X
cana-5634	188	2	13	13	NUM
cana-5634	188	3	]	]	X
cana-5634	188	4	c.	c.	PROPN
cana-5634	188	5	vieira	vieira	PROPN
cana-5634	188	6	et	et	PROPN
cana-5634	188	7	al	al	PROPN
cana-5634	188	8	.	.	PROPN
cana-5634	188	9	,	,	PUNCT
cana-5634	188	10	"	"	PUNCT
cana-5634	188	11	using	use	VERB
cana-5634	188	12	machine	machine	NOUN
cana-5634	188	13	learning	learning	NOUN
cana-5634	188	14	and	and	CCONJ
cana-5634	188	15	structural	structural	ADJ
cana-5634	188	16	neuroimaging	neuroimaging	NOUN
cana-5634	188	17	to	to	PART
cana-5634	188	18	detect	detect	VERB
cana-5634	188	19	first	first	ADJ
cana-5634	188	20	episode	episode	NOUN
cana-5634	188	21	psychosis	psychosis	NOUN
cana-5634	188	22	,	,	PUNCT
cana-5634	188	23	"	"	PUNCT
cana-5634	188	24	frontiers	frontier	NOUN
cana-5634	188	25	in	in	ADP
cana-5634	188	26	psychiatry	psychiatry	NOUN
cana-5634	188	27	,	,	PUNCT
cana-5634	188	28	vol	vol	NOUN
cana-5634	188	29	.	.	PROPN
cana-5634	188	30	8	8	NUM
cana-5634	188	31	,	,	PUNCT
cana-5634	188	32	pp	pp	ADJ
cana-5634	188	33	.	.	PUNCT
cana-5634	189	1	1–13	1–13	NOUN
cana-5634	189	2	,	,	PUNCT
cana-5634	189	3	2017	2017	NUM
cana-5634	189	4	.	.	PUNCT
cana-5634	190	1	[	[	X
cana-5634	190	2	14	14	NUM
cana-5634	190	3	]	]	X
cana-5634	190	4	g.	g.	PROPN
cana-5634	190	5	liu	liu	PROPN
cana-5634	190	6	et	et	PROPN
cana-5634	190	7	al	al	PROPN
cana-5634	190	8	.	.	PROPN
cana-5634	190	9	,	,	PUNCT
cana-5634	190	10	"	"	PUNCT
cana-5634	190	11	mild	mild	ADJ
cana-5634	190	12	cognitive	cognitive	ADJ
cana-5634	190	13	impairment	impairment	NOUN
cana-5634	190	14	detection	detection	NOUN
cana-5634	190	15	using	use	VERB
cana-5634	190	16	decision	decision	NOUN
cana-5634	190	17	tree	tree	NOUN
cana-5634	190	18	algorithm	algorithm	NOUN
cana-5634	190	19	,	,	PUNCT
cana-5634	190	20	"	"	PUNCT
cana-5634	190	21	cognitive	cognitive	ADJ
cana-5634	190	22	neurodynamics	neurodynamic	NOUN
cana-5634	190	23	,	,	PUNCT
cana-5634	190	24	vol	vol	NOUN
cana-5634	190	25	.	.	PROPN
cana-5634	190	26	13	13	NUM
cana-5634	190	27	,	,	PUNCT
cana-5634	190	28	pp	pp	ADJ
cana-5634	190	29	.	.	PUNCT
cana-5634	191	1	453–462	453–462	NUM
cana-5634	191	2	,	,	PUNCT
cana-5634	191	3	2019	2019	NUM
cana-5634	191	4	.	.	PUNCT
cana-5634	192	1	[	[	X
cana-5634	192	2	15	15	NUM
cana-5634	192	3	]	]	PUNCT
cana-5634	192	4	k.	k.	PROPN
cana-5634	192	5	zhang	zhang	PROPN
cana-5634	192	6	et	et	PROPN
cana-5634	192	7	al	al	PROPN
cana-5634	192	8	.	.	PROPN
cana-5634	192	9	,	,	PUNCT
cana-5634	192	10	"	"	PUNCT
cana-5634	192	11	automated	automate	VERB
cana-5634	192	12	classification	classification	NOUN
cana-5634	192	13	of	of	ADP
cana-5634	192	14	ad	ad	NOUN
cana-5634	192	15	from	from	ADP
cana-5634	192	16	structural	structural	ADJ
cana-5634	192	17	mri	mri	NOUN
cana-5634	192	18	using	use	VERB
cana-5634	192	19	transfer	transfer	NOUN
cana-5634	192	20	learning	learning	NOUN
cana-5634	192	21	and	and	CCONJ
cana-5634	192	22	region	region	NOUN
cana-5634	192	23	selection	selection	NOUN
cana-5634	192	24	,	,	PUNCT
cana-5634	192	25	"	"	PUNCT
cana-5634	192	26	computerized	computerized	ADJ
cana-5634	192	27	medical	medical	ADJ
cana-5634	192	28	imaging	imaging	NOUN
cana-5634	192	29	and	and	CCONJ
cana-5634	192	30	graphics	graphic	NOUN
cana-5634	192	31	,	,	PUNCT
cana-5634	192	32	vol	vol	NOUN
cana-5634	192	33	.	.	PROPN
cana-5634	192	34	76	76	NUM
cana-5634	192	35	,	,	PUNCT
cana-5634	192	36	2019	2019	NUM
cana-5634	192	37	.	.	PUNCT
cana-5634	193	1	[	[	X
cana-5634	193	2	16	16	NUM
cana-5634	193	3	]	]	X
cana-5634	193	4	m.	m.	NOUN
cana-5634	193	5	ahmed	ahmed	PROPN
cana-5634	193	6	et	et	PROPN
cana-5634	193	7	al	al	PROPN
cana-5634	193	8	.	.	PROPN
cana-5634	193	9	,	,	PUNCT
cana-5634	193	10	"	"	PUNCT
cana-5634	193	11	early	early	ADJ
cana-5634	193	12	diagnosis	diagnosis	NOUN
cana-5634	193	13	of	of	ADP
cana-5634	193	14	alzheimer	alzheimer	PROPN
cana-5634	193	15	's	's	PART
cana-5634	193	16	disease	disease	NOUN
cana-5634	193	17	based	base	VERB
cana-5634	193	18	on	on	ADP
cana-5634	193	19	feature	feature	NOUN
cana-5634	193	20	extraction	extraction	NOUN
cana-5634	193	21	and	and	CCONJ
cana-5634	193	22	classification	classification	NOUN
cana-5634	193	23	using	use	VERB
cana-5634	193	24	deep	deep	ADJ
cana-5634	193	25	learning	learning	NOUN
cana-5634	193	26	,	,	PUNCT
cana-5634	193	27	"	"	PUNCT
cana-5634	193	28	journal	journal	NOUN
cana-5634	193	29	of	of	ADP
cana-5634	193	30	healthcare	healthcare	PROPN
cana-5634	193	31	engineering	engineering	PROPN
cana-5634	193	32	,	,	PUNCT
cana-5634	193	33	vol	vol	NOUN
cana-5634	193	34	.	.	PUNCT
cana-5634	193	35	2020	2020	NUM
cana-5634	193	36	,	,	PUNCT
cana-5634	193	37	2020	2020	NUM
cana-5634	193	38	.	.	PUNCT
cana-5634	194	1	communications	communication	NOUN
cana-5634	194	2	on	on	ADP
cana-5634	194	3	applied	apply	VERB
cana-5634	194	4	nonlinear	nonlinear	ADJ
cana-5634	194	5	analysis	analysis	NOUN
cana-5634	194	6	issn	issn	NOUN
cana-5634	194	7	:	:	PUNCT
cana-5634	194	8	1074	1074	NUM
cana-5634	194	9	-	-	PUNCT
cana-5634	194	10	133x	133x	NUM
cana-5634	194	11	vol	vol	VERB
cana-5634	194	12	32	32	NUM
cana-5634	194	13	no.1s	no.1s	PROPN
cana-5634	194	14	(	(	PUNCT
cana-5634	194	15	2025	2025	NUM
cana-5634	194	16	)	)	PUNCT
cana-5634	194	17	678	678	NUM
cana-5634	194	18	https://internationalpubls.com	https://internationalpubls.com	X
cana-5634	195	1	[	[	X
cana-5634	195	2	17	17	NUM
cana-5634	195	3	]	]	X
cana-5634	195	4	l.	l.	PROPN
cana-5634	195	5	brosch	brosch	PROPN
cana-5634	195	6	and	and	CCONJ
cana-5634	195	7	r.	r.	PROPN
cana-5634	195	8	tam	tam	PROPN
cana-5634	195	9	,	,	PUNCT
cana-5634	195	10	"	"	PUNCT
cana-5634	195	11	manifold	manifold	ADJ
cana-5634	195	12	learning	learning	NOUN
cana-5634	195	13	of	of	ADP
cana-5634	195	14	brain	brain	NOUN
cana-5634	195	15	mris	mris	NOUN
cana-5634	195	16	by	by	ADP
cana-5634	195	17	deep	deep	ADJ
cana-5634	195	18	learning	learning	NOUN
cana-5634	195	19	,	,	PUNCT
cana-5634	195	20	"	"	PUNCT
cana-5634	195	21	medical	medical	ADJ
cana-5634	195	22	image	image	NOUN
cana-5634	195	23	analysis	analysis	NOUN
cana-5634	195	24	,	,	PUNCT
cana-5634	195	25	vol	vol	NOUN
cana-5634	195	26	.	.	PROPN
cana-5634	195	27	24	24	NUM
cana-5634	195	28	,	,	PUNCT
cana-5634	195	29	no	no	INTJ
cana-5634	195	30	.	.	NOUN
cana-5634	195	31	1	1	NUM
cana-5634	195	32	,	,	PUNCT
cana-5634	195	33	pp	pp	ADJ
cana-5634	195	34	.	.	PUNCT
cana-5634	196	1	18–27	18–27	NUM
cana-5634	196	2	,	,	PUNCT
cana-5634	196	3	2015	2015	NUM
cana-5634	196	4	.	.	PUNCT
cana-5634	197	1	[	[	X
cana-5634	197	2	18	18	NUM
cana-5634	197	3	]	]	PUNCT
cana-5634	197	4	a.	a.	NOUN
cana-5634	197	5	basaia	basaia	PROPN
cana-5634	197	6	et	et	PROPN
cana-5634	197	7	al	al	PROPN
cana-5634	197	8	.	.	PROPN
cana-5634	197	9	,	,	PUNCT
cana-5634	197	10	"	"	PUNCT
cana-5634	197	11	automated	automate	VERB
cana-5634	197	12	classification	classification	NOUN
cana-5634	197	13	of	of	ADP
cana-5634	197	14	alzheimer	alzheimer	PROPN
cana-5634	197	15	's	's	PART
cana-5634	197	16	disease	disease	NOUN
cana-5634	197	17	and	and	CCONJ
cana-5634	197	18	mild	mild	ADJ
cana-5634	197	19	cognitive	cognitive	ADJ
cana-5634	197	20	impairment	impairment	NOUN
cana-5634	197	21	using	use	VERB
cana-5634	197	22	a	a	DET
cana-5634	197	23	single	single	ADJ
cana-5634	197	24	mri	mri	NOUN
cana-5634	197	25	and	and	CCONJ
cana-5634	197	26	deep	deep	ADJ
cana-5634	197	27	neural	neural	ADJ
cana-5634	197	28	networks	network	NOUN
cana-5634	197	29	,	,	PUNCT
cana-5634	197	30	"	"	PUNCT
cana-5634	197	31	neuroimage	neuroimage	NOUN
cana-5634	197	32	:	:	PUNCT
cana-5634	197	33	clinical	clinical	ADJ
cana-5634	197	34	,	,	PUNCT
cana-5634	197	35	vol	vol	NOUN
cana-5634	197	36	.	.	PROPN
cana-5634	197	37	21	21	NUM
cana-5634	197	38	,	,	PUNCT
cana-5634	197	39	2019	2019	NUM
cana-5634	197	40	.	.	PUNCT
cana-5634	198	1	[	[	X
cana-5634	198	2	19	19	NUM
cana-5634	198	3	]	]	PUNCT
cana-5634	198	4	a.	a.	NOUN
cana-5634	198	5	suk	suk	PROPN
cana-5634	198	6	and	and	CCONJ
cana-5634	198	7	d.	d.	PROPN
cana-5634	198	8	shen	shen	PROPN
cana-5634	198	9	,	,	PUNCT
cana-5634	198	10	"	"	PUNCT
cana-5634	198	11	deep	deep	ADJ
cana-5634	198	12	learning	learning	NOUN
cana-5634	198	13	-	-	PUNCT
cana-5634	198	14	based	base	VERB
cana-5634	198	15	feature	feature	NOUN
cana-5634	198	16	representation	representation	NOUN
cana-5634	198	17	for	for	ADP
cana-5634	198	18	ad	ad	NOUN
cana-5634	198	19	/	/	SYM
cana-5634	198	20	mci	mci	NOUN
cana-5634	198	21	classification	classification	NOUN
cana-5634	198	22	,	,	PUNCT
cana-5634	198	23	"	"	PUNCT
cana-5634	198	24	medical	medical	ADJ
cana-5634	198	25	image	image	NOUN
cana-5634	198	26	computing	computing	NOUN
cana-5634	198	27	and	and	CCONJ
cana-5634	198	28	computer	computer	NOUN
cana-5634	198	29	-	-	PUNCT
cana-5634	198	30	assisted	assist	VERB
cana-5634	198	31	intervention	intervention	NOUN
cana-5634	198	32	–	–	PUNCT
cana-5634	198	33	miccai	miccai	NOUN
cana-5634	198	34	,	,	PUNCT
cana-5634	198	35	pp	pp	X
cana-5634	198	36	.	.	PUNCT
cana-5634	199	1	583–590	583–590	NUM
cana-5634	199	2	,	,	PUNCT
cana-5634	199	3	2013	2013	NUM
cana-5634	199	4	.	.	PUNCT
cana-5634	200	1	[	[	X
cana-5634	200	2	20	20	NUM
cana-5634	200	3	]	]	PUNCT
cana-5634	200	4	h.	h.	PROPN
cana-5634	200	5	jain	jain	PROPN
cana-5634	200	6	et	et	PROPN
cana-5634	200	7	al	al	PROPN
cana-5634	200	8	.	.	PROPN
cana-5634	200	9	,	,	PUNCT
cana-5634	200	10	"	"	PUNCT
cana-5634	200	11	machine	machine	NOUN
cana-5634	200	12	learning	learn	VERB
cana-5634	200	13	for	for	ADP
cana-5634	200	14	early	early	ADJ
cana-5634	200	15	detection	detection	NOUN
cana-5634	200	16	of	of	ADP
cana-5634	200	17	alzheimer	alzheimer	PROPN
cana-5634	200	18	's	's	PART
cana-5634	200	19	disease	disease	NOUN
cana-5634	200	20	using	use	VERB
cana-5634	200	21	structural	structural	ADJ
cana-5634	200	22	mr	mr	PROPN
cana-5634	200	23	imaging	imaging	PROPN
cana-5634	200	24	,	,	PUNCT
cana-5634	200	25	"	"	PUNCT
cana-5634	200	26	neurocomputing	neurocomputing	NOUN
cana-5634	200	27	,	,	PUNCT
cana-5634	200	28	vol	vol	NOUN
cana-5634	200	29	.	.	PROPN
cana-5634	200	30	328	328	NUM
cana-5634	200	31	,	,	PUNCT
cana-5634	200	32	pp	pp	ADJ
cana-5634	200	33	.	.	PUNCT
cana-5634	201	1	139–147	139–147	NUM
cana-5634	201	2	,	,	PUNCT
cana-5634	201	3	2019	2019	NUM
cana-5634	201	4	.	.	PUNCT
cana-5634	202	1	[	[	X
cana-5634	202	2	21	21	NUM
cana-5634	202	3	]	]	PUNCT
cana-5634	202	4	m.	m.	NOUN
cana-5634	202	5	bron	bron	PROPN
cana-5634	202	6	et	et	PROPN
cana-5634	202	7	al	al	PROPN
cana-5634	202	8	.	.	PROPN
cana-5634	202	9	,	,	PUNCT
cana-5634	202	10	"	"	PUNCT
cana-5634	202	11	standardized	standardized	ADJ
cana-5634	202	12	evaluation	evaluation	NOUN
cana-5634	202	13	of	of	ADP
cana-5634	202	14	algorithms	algorithm	NOUN
cana-5634	202	15	for	for	ADP
cana-5634	202	16	computer	computer	NOUN
cana-5634	202	17	-	-	PUNCT
cana-5634	202	18	aided	aid	VERB
cana-5634	202	19	diagnosis	diagnosis	NOUN
cana-5634	202	20	of	of	ADP
cana-5634	202	21	dementia	dementia	NOUN
cana-5634	202	22	based	base	VERB
cana-5634	202	23	on	on	ADP
cana-5634	202	24	structural	structural	ADJ
cana-5634	202	25	mri	mri	NOUN
cana-5634	202	26	,	,	PUNCT
cana-5634	202	27	"	"	PUNCT
cana-5634	202	28	neuroimage	neuroimage	NOUN
cana-5634	202	29	,	,	PUNCT
cana-5634	202	30	vol	vol	NOUN
cana-5634	202	31	.	.	PROPN
cana-5634	203	1	54	54	NUM
cana-5634	203	2	,	,	PUNCT
cana-5634	203	3	pp	pp	ADJ
cana-5634	203	4	.	.	PUNCT
cana-5634	204	1	113–123	113–123	NUM
cana-5634	204	2	,	,	PUNCT
cana-5634	204	3	2011	2011	NUM
cana-5634	204	4	.	.	PUNCT
cana-5634	205	1	[	[	X
cana-5634	205	2	22	22	NUM
cana-5634	205	3	]	]	X
cana-5634	205	4	r.	r.	PROPN
cana-5634	205	5	m.	m.	PROPN
cana-5634	205	6	harikumar	harikumar	PROPN
cana-5634	205	7	and	and	CCONJ
cana-5634	205	8	p.	p.	PROPN
cana-5634	205	9	r.	r.	PROPN
cana-5634	205	10	bhanu	bhanu	PROPN
cana-5634	205	11	,	,	PUNCT
cana-5634	205	12	"	"	PUNCT
cana-5634	205	13	comparative	comparative	ADJ
cana-5634	205	14	analysis	analysis	NOUN
cana-5634	205	15	of	of	ADP
cana-5634	205	16	traditional	traditional	ADJ
cana-5634	205	17	machine	machine	NOUN
cana-5634	205	18	learning	learning	NOUN
cana-5634	205	19	models	model	NOUN
cana-5634	205	20	and	and	CCONJ
cana-5634	205	21	deep	deep	ADJ
cana-5634	205	22	learning	learning	NOUN
cana-5634	205	23	techniques	technique	NOUN
cana-5634	205	24	for	for	ADP
cana-5634	205	25	alzheimer	alzheimer	PROPN
cana-5634	205	26	’s	’s	PART
cana-5634	205	27	disease	disease	NOUN
cana-5634	205	28	prediction	prediction	NOUN
cana-5634	205	29	,	,	PUNCT
cana-5634	205	30	"	"	PUNCT
cana-5634	205	31	international	international	ADJ
cana-5634	205	32	journal	journal	NOUN
cana-5634	205	33	of	of	ADP
cana-5634	205	34	advanced	advanced	ADJ
cana-5634	205	35	computer	computer	NOUN
cana-5634	205	36	science	science	NOUN
cana-5634	205	37	and	and	CCONJ
cana-5634	205	38	applications	application	NOUN
cana-5634	205	39	,	,	PUNCT
cana-5634	205	40	vol	vol	NOUN
cana-5634	205	41	.	.	PROPN
cana-5634	205	42	12	12	NUM
cana-5634	205	43	,	,	PUNCT
cana-5634	205	44	no	no	INTJ
cana-5634	205	45	.	.	NOUN
cana-5634	205	46	9	9	NUM
cana-5634	205	47	,	,	PUNCT
cana-5634	205	48	pp	pp	ADJ
cana-5634	205	49	.	.	PUNCT
cana-5634	206	1	34–42	34–42	NUM
cana-5634	206	2	,	,	PUNCT
cana-5634	206	3	2021	2021	NUM
cana-5634	206	4	.	.	PUNCT
cana-5634	207	1	[	[	X
cana-5634	207	2	23	23	NUM
cana-5634	207	3	]	]	X
cana-5634	207	4	p.	p.	NOUN
cana-5634	207	5	ravi	ravi	PROPN
cana-5634	207	6	and	and	CCONJ
cana-5634	207	7	m.	m.	PROPN
cana-5634	207	8	karthik	karthik	PROPN
cana-5634	207	9	,	,	PUNCT
cana-5634	207	10	"	"	PUNCT
cana-5634	207	11	neural	neural	ADJ
cana-5634	207	12	networks	network	NOUN
cana-5634	207	13	in	in	ADP
cana-5634	207	14	medical	medical	ADJ
cana-5634	207	15	diagnosis	diagnosis	NOUN
cana-5634	207	16	:	:	PUNCT
cana-5634	207	17	a	a	DET
cana-5634	207	18	survey	survey	NOUN
cana-5634	207	19	on	on	ADP
cana-5634	207	20	alzheimer	alzheimer	PROPN
cana-5634	207	21	’s	’s	PART
cana-5634	207	22	prediction	prediction	NOUN
cana-5634	207	23	using	use	VERB
cana-5634	207	24	mri	mri	NOUN
cana-5634	207	25	and	and	CCONJ
cana-5634	207	26	cognitive	cognitive	ADJ
cana-5634	207	27	scores	score	NOUN
cana-5634	207	28	,	,	PUNCT
cana-5634	207	29	"	"	PUNCT
cana-5634	207	30	procedia	procedia	NOUN
cana-5634	207	31	computer	computer	NOUN
cana-5634	207	32	science	science	NOUN
cana-5634	207	33	,	,	PUNCT
cana-5634	207	34	vol	vol	NOUN
cana-5634	207	35	.	.	PROPN
cana-5634	207	36	172	172	NUM
cana-5634	207	37	,	,	PUNCT
cana-5634	207	38	pp	pp	ADJ
cana-5634	207	39	.	.	PUNCT
cana-5634	208	1	458–464	458–464	NUM
cana-5634	208	2	,	,	PUNCT
cana-5634	208	3	2020	2020	NUM
cana-5634	208	4	.	.	PUNCT
cana-5634	209	1	[	[	X
cana-5634	209	2	24	24	NUM
cana-5634	209	3	]	]	X
cana-5634	209	4	d.	d.	PROPN
cana-5634	209	5	lin	lin	PROPN
cana-5634	209	6	and	and	CCONJ
cana-5634	209	7	y.	y.	PROPN
cana-5634	209	8	zhang	zhang	PROPN
cana-5634	209	9	,	,	PUNCT
cana-5634	209	10	"	"	PUNCT
cana-5634	209	11	structural	structural	ADJ
cana-5634	209	12	mri	mri	NOUN
cana-5634	209	13	-	-	PUNCT
cana-5634	209	14	based	base	VERB
cana-5634	209	15	alzheimer	alzheimer	PROPN
cana-5634	209	16	’s	’s	PART
cana-5634	209	17	disease	disease	NOUN
cana-5634	209	18	classification	classification	NOUN
cana-5634	209	19	using	use	VERB
cana-5634	209	20	boosted	boost	VERB
cana-5634	209	21	trees	tree	NOUN
cana-5634	209	22	and	and	CCONJ
cana-5634	209	23	bagging	bagging	NOUN
cana-5634	209	24	,	,	PUNCT
cana-5634	209	25	"	"	PUNCT
cana-5634	209	26	journal	journal	NOUN
cana-5634	209	27	of	of	ADP
cana-5634	209	28	healthcare	healthcare	PROPN
cana-5634	209	29	informatics	informatics	PROPN
cana-5634	209	30	research	research	PROPN
cana-5634	209	31	,	,	PUNCT
cana-5634	209	32	vol	vol	NOUN
cana-5634	209	33	.	.	PROPN
cana-5634	209	34	4	4	NUM
cana-5634	209	35	,	,	PUNCT
cana-5634	209	36	pp	pp	ADJ
cana-5634	209	37	.	.	PUNCT
cana-5634	209	38	251	251	NUM
cana-5634	209	39	–	–	PUNCT
cana-5634	209	40	265	265	NUM
cana-5634	209	41	,	,	PUNCT
cana-5634	209	42	2020	2020	NUM
cana-5634	209	43	.	.	PUNCT
cana-5634	210	1	[	[	X
cana-5634	210	2	25	25	NUM
cana-5634	210	3	]	]	X
cana-5634	210	4	s.	s.	PROPN
cana-5634	210	5	razzak	razzak	PROPN
cana-5634	210	6	et	et	PROPN
cana-5634	210	7	al	al	PROPN
cana-5634	210	8	.	.	PROPN
cana-5634	210	9	,	,	PUNCT
cana-5634	210	10	"	"	PUNCT
cana-5634	210	11	deep	deep	ADJ
cana-5634	210	12	learning	learning	NOUN
cana-5634	210	13	for	for	ADP
cana-5634	210	14	medical	medical	ADJ
cana-5634	210	15	image	image	NOUN
cana-5634	210	16	processing	processing	NOUN
cana-5634	210	17	:	:	PUNCT
cana-5634	210	18	overview	overview	NOUN
cana-5634	210	19	,	,	PUNCT
cana-5634	210	20	challenges	challenge	NOUN
cana-5634	210	21	and	and	CCONJ
cana-5634	210	22	the	the	DET
cana-5634	210	23	future	future	NOUN
cana-5634	210	24	,	,	PUNCT
cana-5634	210	25	"	"	PUNCT
cana-5634	210	26	classification	classification	NOUN
cana-5634	210	27	in	in	ADP
cana-5634	210	28	bioapps	bioapp	NOUN
cana-5634	210	29	,	,	PUNCT
cana-5634	210	30	pp	pp	ADV
cana-5634	210	31	.	.	PUNCT
cana-5634	211	1	323–350	323–350	NUM
cana-5634	211	2	,	,	PUNCT
cana-5634	211	3	springer	springer	NOUN
cana-5634	211	4	,	,	PUNCT
cana-5634	211	5	2018	2018	NUM
cana-5634	211	6	.	.	PUNCT
cana-5634	212	1	[	[	X
cana-5634	212	2	26	26	NUM
cana-5634	212	3	]	]	PUNCT
cana-5634	212	4	p.	p.	NOUN
cana-5634	212	5	rajesh	rajesh	PROPN
cana-5634	212	6	and	and	CCONJ
cana-5634	212	7	m.	m.	PROPN
cana-5634	212	8	karthikeyan	karthikeyan	PROPN
cana-5634	212	9	,	,	PUNCT
cana-5634	212	10	"	"	PUNCT
cana-5634	212	11	a	a	DET
cana-5634	212	12	comparative	comparative	ADJ
cana-5634	212	13	study	study	NOUN
cana-5634	212	14	of	of	ADP
cana-5634	212	15	data	datum	NOUN
cana-5634	212	16	mining	mining	NOUN
cana-5634	212	17	algorithms	algorithm	NOUN
cana-5634	212	18	for	for	ADP
cana-5634	212	19	decision	decision	NOUN
cana-5634	212	20	tree	tree	NOUN
cana-5634	212	21	approaches	approach	NOUN
cana-5634	212	22	using	use	VERB
cana-5634	212	23	weka	weka	PROPN
cana-5634	212	24	tool	tool	NOUN
cana-5634	212	25	,	,	PUNCT
cana-5634	212	26	"	"	PUNCT
cana-5634	212	27	advances	advance	NOUN
cana-5634	212	28	in	in	ADP
cana-5634	212	29	natural	natural	ADJ
cana-5634	212	30	and	and	CCONJ
cana-5634	212	31	applied	applied	ADJ
cana-5634	212	32	sciences	science	NOUN
cana-5634	212	33	,	,	PUNCT
cana-5634	212	34	vol	vol	NOUN
cana-5634	212	35	.	.	PROPN
cana-5634	213	1	11	11	NUM
cana-5634	213	2	,	,	PUNCT
cana-5634	213	3	no	no	INTJ
cana-5634	213	4	.	.	NOUN
cana-5634	213	5	9	9	NUM
cana-5634	213	6	,	,	PUNCT
cana-5634	213	7	pp	pp	ADJ
cana-5634	213	8	.	.	PUNCT
cana-5634	214	1	230–243	230–243	NUM
cana-5634	214	2	,	,	PUNCT
cana-5634	214	3	2017	2017	NUM
cana-5634	214	4	.	.	PUNCT
cana-5634	215	1	[	[	X
cana-5634	215	2	27	27	NUM
cana-5634	215	3	]	]	X
cana-5634	215	4	p.	p.	PROPN
cana-5634	215	5	rajesh	rajesh	PROPN
cana-5634	215	6	,	,	PUNCT
cana-5634	215	7	m.	m.	NOUN
cana-5634	215	8	karthikeyan	karthikeyan	PROPN
cana-5634	215	9	,	,	PUNCT
cana-5634	215	10	b.	b.	PROPN
cana-5634	215	11	santhosh	santhosh	PROPN
cana-5634	215	12	kumar	kumar	PROPN
cana-5634	215	13	,	,	PUNCT
cana-5634	215	14	and	and	CCONJ
cana-5634	215	15	m.	m.	PROPN
cana-5634	215	16	y.	y.	PROPN
cana-5634	215	17	mohamed	mohamed	PROPN
cana-5634	215	18	parvees	parvees	PROPN
cana-5634	215	19	,	,	PUNCT
cana-5634	215	20	"	"	PUNCT
cana-5634	215	21	comparative	comparative	ADJ
cana-5634	215	22	study	study	NOUN
cana-5634	215	23	of	of	ADP
cana-5634	215	24	decision	decision	NOUN
cana-5634	215	25	tree	tree	NOUN
cana-5634	215	26	approaches	approach	VERB
cana-5634	215	27	in	in	ADP
cana-5634	215	28	data	datum	NOUN
cana-5634	215	29	mining	mining	NOUN
cana-5634	215	30	using	use	VERB
cana-5634	215	31	chronic	chronic	ADJ
cana-5634	215	32	disease	disease	NOUN
cana-5634	215	33	indicators	indicator	NOUN
cana-5634	215	34	(	(	PUNCT
cana-5634	215	35	cdi	cdi	PROPN
cana-5634	215	36	)	)	PUNCT
cana-5634	215	37	data	datum	NOUN
cana-5634	215	38	,	,	PUNCT
cana-5634	215	39	"	"	PUNCT
cana-5634	215	40	journal	journal	NOUN
cana-5634	215	41	of	of	ADP
cana-5634	215	42	computational	computational	ADJ
cana-5634	215	43	and	and	CCONJ
cana-5634	215	44	theoretical	theoretical	ADJ
cana-5634	215	45	nanoscience	nanoscience	NOUN
cana-5634	215	46	,	,	PUNCT
cana-5634	215	47	vol	vol	NOUN
cana-5634	215	48	.	.	PROPN
cana-5634	216	1	16	16	NUM
cana-5634	216	2	,	,	PUNCT
cana-5634	216	3	no	no	INTJ
cana-5634	216	4	.	.	NOUN
cana-5634	216	5	4	4	NUM
cana-5634	216	6	,	,	PUNCT
cana-5634	216	7	pp	pp	ADJ
cana-5634	216	8	.	.	PUNCT
cana-5634	217	1	1472–1477	1472–1477	NUM
cana-5634	217	2	,	,	PUNCT
cana-5634	217	3	2019	2019	NUM
cana-5634	217	4	.	.	PUNCT
cana-5634	218	1	[	[	X
cana-5634	218	2	28	28	NUM
cana-5634	218	3	]	]	X
cana-5634	218	4	s.	s.	PROPN
cana-5634	218	5	ravishankar	ravishankar	PROPN
cana-5634	218	6	and	and	CCONJ
cana-5634	218	7	p.	p.	PROPN
cana-5634	218	8	rajesh	rajesh	PROPN
cana-5634	218	9	,	,	PUNCT
cana-5634	218	10	"	"	PUNCT
cana-5634	218	11	a	a	DET
cana-5634	218	12	study	study	NOUN
cana-5634	218	13	on	on	ADP
cana-5634	218	14	variable	variable	ADJ
cana-5634	218	15	selections	selection	NOUN
cana-5634	218	16	and	and	CCONJ
cana-5634	218	17	prediction	prediction	NOUN
cana-5634	218	18	for	for	ADP
cana-5634	218	19	climate	climate	NOUN
cana-5634	218	20	change	change	NOUN
cana-5634	218	21	dataset	dataset	NOUN
cana-5634	218	22	using	use	VERB
cana-5634	218	23	data	datum	NOUN
cana-5634	218	24	mining	mining	NOUN
cana-5634	218	25	with	with	ADP
cana-5634	218	26	machine	machine	NOUN
cana-5634	218	27	learning	learning	NOUN
cana-5634	218	28	approaches	approach	NOUN
cana-5634	218	29	,	,	PUNCT
cana-5634	218	30	"	"	PUNCT
cana-5634	218	31	european	european	ADJ
cana-5634	218	32	chemical	chemical	PROPN
cana-5634	218	33	bulletin	bulletin	PROPN
cana-5634	218	34	,	,	PUNCT
cana-5634	218	35	vol	vol	NOUN
cana-5634	218	36	.	.	PROPN
cana-5634	218	37	11	11	NUM
cana-5634	218	38	,	,	PUNCT
cana-5634	218	39	no	no	INTJ
cana-5634	218	40	.	.	NOUN
cana-5634	218	41	12	12	NUM
cana-5634	218	42	,	,	PUNCT
cana-5634	218	43	pp	pp	ADJ
cana-5634	218	44	.	.	PUNCT
cana-5634	219	1	1866–1877	1866–1877	NUM
cana-5634	219	2	,	,	PUNCT
cana-5634	219	3	2022	2022	NUM
cana-5634	219	4	.	.	PUNCT
cana-5634	220	1	[	[	X
cana-5634	220	2	29	29	NUM
cana-5634	220	3	]	]	X
cana-5634	220	4	s.	s.	PROPN
cana-5634	220	5	ravishankar	ravishankar	PROPN
cana-5634	220	6	and	and	CCONJ
cana-5634	220	7	p.	p.	PROPN
cana-5634	220	8	rajesh	rajesh	PROPN
cana-5634	220	9	,	,	PUNCT
cana-5634	220	10	"	"	PUNCT
cana-5634	220	11	a	a	DET
cana-5634	220	12	study	study	NOUN
cana-5634	220	13	on	on	ADP
cana-5634	220	14	variable	variable	ADJ
cana-5634	220	15	selections	selection	NOUN
cana-5634	220	16	and	and	CCONJ
cana-5634	220	17	prediction	prediction	NOUN
cana-5634	220	18	for	for	ADP
cana-5634	220	19	climate	climate	NOUN
cana-5634	220	20	change	change	NOUN
cana-5634	220	21	with	with	ADP
cana-5634	220	22	global	global	ADJ
cana-5634	220	23	weather	weather	NOUN
cana-5634	220	24	repository	repository	NOUN
cana-5634	220	25	using	use	VERB
cana-5634	220	26	data	datum	NOUN
cana-5634	220	27	mining	mining	NOUN
cana-5634	220	28	with	with	ADP
cana-5634	220	29	machine	machine	NOUN
cana-5634	220	30	learning	learning	NOUN
cana-5634	220	31	approaches	approach	NOUN
cana-5634	220	32	,	,	PUNCT
cana-5634	220	33	"	"	PUNCT
cana-5634	220	34	journal	journal	NOUN
cana-5634	220	35	of	of	ADP
cana-5634	220	36	propulsion	propulsion	NOUN
cana-5634	220	37	technology	technology	NOUN
cana-5634	220	38	,	,	PUNCT
cana-5634	220	39	vol	vol	NOUN
cana-5634	220	40	.	.	PROPN
cana-5634	220	41	44	44	NUM
cana-5634	220	42	,	,	PUNCT
cana-5634	220	43	no	no	INTJ
cana-5634	220	44	.	.	NOUN
cana-5634	220	45	2	2	NUM
cana-5634	220	46	,	,	PUNCT
cana-5634	220	47	pp	pp	ADJ
cana-5634	220	48	.	.	PUNCT
cana-5634	221	1	976–989	976–989	NUM
cana-5634	221	2	.	.	PUNCT
cana-5634	222	1	[	[	X
cana-5634	222	2	30	30	NUM
cana-5634	222	3	]	]	X
cana-5634	222	4	s.	s.	PROPN
cana-5634	222	5	ravishankar	ravishankar	PROPN
cana-5634	222	6	and	and	CCONJ
cana-5634	222	7	p.	p.	PROPN
cana-5634	222	8	rajesh	rajesh	PROPN
cana-5634	222	9	,	,	PUNCT
cana-5634	222	10	"	"	PUNCT
cana-5634	222	11	analysis	analysis	NOUN
cana-5634	222	12	and	and	CCONJ
cana-5634	222	13	predictions	prediction	NOUN
cana-5634	222	14	for	for	ADP
cana-5634	222	15	climate	climate	NOUN
cana-5634	222	16	change	change	NOUN
cana-5634	222	17	dataset	dataset	VERB
cana-5634	222	18	with	with	ADP
cana-5634	222	19	air	air	NOUN
cana-5634	222	20	quality	quality	NOUN
cana-5634	222	21	index	index	NOUN
cana-5634	222	22	using	use	VERB
cana-5634	222	23	data	datum	NOUN
cana-5634	222	24	mining	mining	NOUN
cana-5634	222	25	and	and	CCONJ
cana-5634	222	26	machine	machine	NOUN
cana-5634	222	27	learning	learning	NOUN
cana-5634	222	28	approaches	approach	NOUN
cana-5634	222	29	,	,	PUNCT
cana-5634	222	30	"	"	PUNCT
cana-5634	222	31	journal	journal	NOUN
cana-5634	222	32	of	of	ADP
cana-5634	222	33	data	datum	NOUN
cana-5634	222	34	acquisition	acquisition	NOUN
cana-5634	222	35	and	and	CCONJ
cana-5634	222	36	processing	processing	NOUN
cana-5634	222	37	,	,	PUNCT
cana-5634	222	38	vol	vol	NOUN
cana-5634	222	39	.	.	PROPN
cana-5634	222	40	38	38	NUM
cana-5634	222	41	,	,	PUNCT
cana-5634	222	42	no	no	INTJ
cana-5634	222	43	.	.	NOUN
cana-5634	222	44	3	3	NUM
cana-5634	222	45	,	,	PUNCT
cana-5634	222	46	pp	pp	ADJ
cana-5634	222	47	.	.	PUNCT
cana-5634	222	48	2023–2038	2023–2038	NUM
cana-5634	222	49	,	,	PUNCT
cana-5634	222	50	2023	2023	NUM
cana-5634	222	51	.	.	PUNCT
cana-5634	223	1	[	[	X
cana-5634	223	2	31	31	NUM
cana-5634	223	3	]	]	PUNCT
cana-5634	223	4	b.	b.	PROPN
cana-5634	223	5	santhoshkumar	santhoshkumar	PROPN
cana-5634	223	6	and	and	CCONJ
cana-5634	223	7	p.	p.	PROPN
cana-5634	223	8	rajesh	rajesh	PROPN
cana-5634	223	9	,	,	PUNCT
cana-5634	223	10	"	"	PUNCT
cana-5634	223	11	a	a	DET
cana-5634	223	12	machine	machine	NOUN
cana-5634	223	13	learning	learn	VERB
cana-5634	223	14	approach	approach	NOUN
cana-5634	223	15	to	to	PART
cana-5634	223	16	analyze	analyze	VERB
cana-5634	223	17	and	and	CCONJ
cana-5634	223	18	predict	predict	VERB
cana-5634	223	19	the	the	DET
cana-5634	223	20	relationship	relationship	NOUN
cana-5634	223	21	between	between	ADP
cana-5634	223	22	sustainable	sustainable	ADJ
cana-5634	223	23	development	development	NOUN
cana-5634	223	24	goals	goal	NOUN
cana-5634	223	25	with	with	ADP
cana-5634	223	26	various	various	ADJ
cana-5634	223	27	energy	energy	NOUN
cana-5634	223	28	,	,	PUNCT
cana-5634	223	29	"	"	PUNCT
cana-5634	223	30	journal	journal	NOUN
cana-5634	223	31	of	of	ADP
cana-5634	223	32	propulsion	propulsion	NOUN
cana-5634	223	33	technology	technology	NOUN
cana-5634	223	34	,	,	PUNCT
cana-5634	223	35	vol	vol	NOUN
cana-5634	223	36	.	.	PROPN
cana-5634	223	37	44	44	NUM
cana-5634	223	38	,	,	PUNCT
cana-5634	223	39	no	no	INTJ
cana-5634	223	40	.	.	NOUN
cana-5634	223	41	2	2	NUM
cana-5634	223	42	,	,	PUNCT
cana-5634	223	43	pp	pp	ADJ
cana-5634	223	44	.	.	PUNCT
cana-5634	224	1	956–968	956–968	NUM
cana-5634	224	2	.	.	PUNCT
cana-5634	225	1	[	[	X
cana-5634	225	2	32	32	NUM
cana-5634	225	3	]	]	PUNCT
cana-5634	225	4	m.	m.	PROPN
cana-5634	225	5	f.	f.	PROPN
cana-5634	225	6	marcus	marcus	PROPN
cana-5634	225	7	,	,	PUNCT
cana-5634	225	8	t.	t.	PROPN
cana-5634	225	9	h.	h.	PROPN
cana-5634	225	10	wang	wang	PROPN
cana-5634	225	11	,	,	PUNCT
cana-5634	225	12	j.	j.	PROPN
cana-5634	225	13	parker	parker	PROPN
cana-5634	225	14	,	,	PUNCT
cana-5634	225	15	m.	m.	NOUN
cana-5634	225	16	g.	g.	PROPN
cana-5634	225	17	csernansky	csernansky	PROPN
cana-5634	225	18	,	,	PUNCT
cana-5634	225	19	j.	j.	PROPN
cana-5634	225	20	c.	c.	PROPN
cana-5634	225	21	morris	morris	PROPN
cana-5634	225	22	,	,	PUNCT
cana-5634	225	23	and	and	CCONJ
cana-5634	225	24	r.	r.	PROPN
cana-5634	225	25	l.	l.	PROPN
cana-5634	225	26	buckner	buckner	PROPN
cana-5634	225	27	,	,	PUNCT
cana-5634	225	28	“	"	PUNCT
cana-5634	225	29	open	open	ADJ
cana-5634	225	30	access	access	NOUN
cana-5634	225	31	series	series	NOUN
cana-5634	225	32	of	of	ADP
cana-5634	225	33	imaging	imaging	NOUN
cana-5634	225	34	studies	study	NOUN
cana-5634	225	35	(	(	PUNCT
cana-5634	225	36	oasis	oasis	NOUN
cana-5634	225	37	):	):	PUNCT
cana-5634	225	38	cross	cross	ADJ
cana-5634	225	39	-	-	ADJ
cana-5634	225	40	sectional	sectional	ADJ
cana-5634	225	41	mri	mri	NOUN
cana-5634	225	42	data	datum	NOUN
cana-5634	225	43	in	in	ADP
cana-5634	225	44	young	young	ADJ
cana-5634	225	45	,	,	PUNCT
cana-5634	225	46	middle	middle	ADJ
cana-5634	225	47	aged	aged	ADJ
cana-5634	225	48	,	,	PUNCT
cana-5634	225	49	nondemented	nondemente	VERB
cana-5634	225	50	,	,	PUNCT
cana-5634	225	51	and	and	CCONJ
cana-5634	225	52	demented	demented	ADJ
cana-5634	225	53	older	old	ADJ
cana-5634	225	54	adults	adult	NOUN
cana-5634	225	55	,	,	PUNCT
cana-5634	225	56	”	"	PUNCT
cana-5634	225	57	journal	journal	NOUN
cana-5634	225	58	of	of	ADP
cana-5634	225	59	cognitive	cognitive	ADJ
cana-5634	225	60	neuroscience	neuroscience	NOUN
cana-5634	225	61	,	,	PUNCT
cana-5634	225	62	vol	vol	NOUN
cana-5634	225	63	.	.	PROPN
cana-5634	226	1	19	19	NUM
cana-5634	226	2	,	,	PUNCT
cana-5634	226	3	no	no	INTJ
cana-5634	226	4	.	.	NOUN
cana-5634	226	5	9	9	NUM
cana-5634	226	6	,	,	PUNCT
cana-5634	226	7	pp	pp	ADJ
cana-5634	226	8	.	.	PUNCT
cana-5634	227	1	1498–1507	1498–1507	NUM
cana-5634	227	2	,	,	PUNCT
cana-5634	227	3	2007	2007	NUM
cana-5634	227	4	.	.	PUNCT