id	sid	tid	token	lemma	pos
cana-5401	1	1	communications	communication	NOUN
cana-5401	1	2	on	on	ADP
cana-5401	1	3	applied	apply	VERB
cana-5401	1	4	nonlinear	nonlinear	ADJ
cana-5401	1	5	analysis	analysis	NOUN
cana-5401	1	6	issn	issn	NOUN
cana-5401	1	7	:	:	PUNCT
cana-5401	1	8	1074	1074	NUM
cana-5401	1	9	-	-	PUNCT
cana-5401	1	10	133x	133x	NUM
cana-5401	1	11	vol	vol	NOUN
cana-5401	1	12	32	32	NUM
cana-5401	1	13	no	no	NOUN
cana-5401	1	14	.	.	PUNCT
cana-5401	2	1	icmasd	icmasd	NOUN
cana-5401	2	2	(	(	PUNCT
cana-5401	2	3	2025	2025	NUM
cana-5401	2	4	)	)	PUNCT
cana-5401	2	5	1854	1854	NUM
cana-5401	3	1	https://internationalpubls.com	https://internationalpubls.com	X
cana-5401	3	2	evaluation	evaluation	NOUN
cana-5401	3	3	of	of	ADP
cana-5401	3	4	various	various	ADJ
cana-5401	3	5	machine	machine	NOUN
cana-5401	3	6	learning	learn	VERB
cana-5401	3	7	algorithms	algorithm	NOUN
cana-5401	3	8	for	for	ADP
cana-5401	3	9	crime	crime	NOUN
cana-5401	3	10	prediction	prediction	NOUN
cana-5401	3	11	mankaranjit	mankaranjit	NOUN
cana-5401	3	12	singh1	singh1	PROPN
cana-5401	3	13	,	,	PUNCT
cana-5401	3	14	kamal	kamal	PROPN
cana-5401	3	15	malik1	malik1	PROPN
cana-5401	3	16	1	1	NUM
cana-5401	3	17	department	department	NOUN
cana-5401	3	18	of	of	ADP
cana-5401	3	19	computer	computer	NOUN
cana-5401	3	20	science	science	PROPN
cana-5401	3	21	&	&	CCONJ
cana-5401	3	22	engineering	engineering	PROPN
cana-5401	3	23	,	,	PUNCT
cana-5401	3	24	ct	ct	PROPN
cana-5401	3	25	university	university	NOUN
cana-5401	3	26	,	,	PUNCT
cana-5401	3	27	ludhiana	ludhiana	PROPN
cana-5401	3	28	article	article	NOUN
cana-5401	3	29	history	history	NOUN
cana-5401	3	30	:	:	PUNCT
cana-5401	3	31	received	receive	VERB
cana-5401	3	32	:	:	PUNCT
cana-5401	3	33	12	12	NUM
cana-5401	3	34	-	-	SYM
cana-5401	3	35	12	12	NUM
cana-5401	3	36	-	-	PUNCT
cana-5401	3	37	2024	2024	NUM
cana-5401	3	38	revised	revise	VERB
cana-5401	3	39	:	:	PUNCT
cana-5401	3	40	25	25	NUM
cana-5401	3	41	-	-	PUNCT
cana-5401	3	42	01	01	NUM
cana-5401	3	43	-	-	PUNCT
cana-5401	3	44	2025	2025	NUM
cana-5401	3	45	accepted	accept	VERB
cana-5401	3	46	:	:	PUNCT
cana-5401	3	47	05	05	NUM
cana-5401	3	48	-	-	PUNCT
cana-5401	3	49	02	02	NUM
cana-5401	3	50	-	-	PUNCT
cana-5401	3	51	2025	2025	NUM
cana-5401	3	52	abstract	abstract	NOUN
cana-5401	3	53	:	:	PUNCT
cana-5401	3	54	crime	crime	NOUN
cana-5401	3	55	poses	pose	VERB
cana-5401	3	56	a	a	DET
cana-5401	3	57	challenge	challenge	NOUN
cana-5401	3	58	to	to	ADP
cana-5401	3	59	every	every	DET
cana-5401	3	60	nation	nation	NOUN
cana-5401	3	61	's	's	PART
cana-5401	3	62	jurisdiction	jurisdiction	NOUN
cana-5401	3	63	and	and	CCONJ
cana-5401	3	64	administration	administration	NOUN
cana-5401	3	65	.	.	PUNCT
cana-5401	4	1	thus	thus	ADV
cana-5401	4	2	,	,	PUNCT
cana-5401	4	3	computerized	computerized	ADJ
cana-5401	4	4	crime	crime	NOUN
cana-5401	4	5	forecasting	forecasting	NOUN
cana-5401	4	6	and	and	CCONJ
cana-5401	4	7	prediction	prediction	NOUN
cana-5401	4	8	may	may	AUX
cana-5401	4	9	contribute	contribute	VERB
cana-5401	4	10	toward	toward	ADP
cana-5401	4	11	making	make	VERB
cana-5401	4	12	cities	city	NOUN
cana-5401	4	13	more	more	ADV
cana-5401	4	14	secure	secure	ADJ
cana-5401	4	15	.	.	PUNCT
cana-5401	5	1	however	however	ADV
cana-5401	5	2	,	,	PUNCT
cana-5401	5	3	creating	create	VERB
cana-5401	5	4	accurate	accurate	ADJ
cana-5401	5	5	and	and	CCONJ
cana-5401	5	6	fast	fast	ADJ
cana-5401	5	7	predictions	prediction	NOUN
cana-5401	5	8	about	about	ADP
cana-5401	5	9	criminal	criminal	ADJ
cana-5401	5	10	activity	activity	NOUN
cana-5401	5	11	is	be	AUX
cana-5401	5	12	challenging	challenging	ADJ
cana-5401	5	13	.	.	PUNCT
cana-5401	6	1	this	this	PRON
cana-5401	6	2	is	be	AUX
cana-5401	6	3	due	due	ADJ
cana-5401	6	4	to	to	ADP
cana-5401	6	5	the	the	DET
cana-5401	6	6	incapability	incapability	NOUN
cana-5401	6	7	of	of	ADP
cana-5401	6	8	humans	human	NOUN
cana-5401	6	9	that	that	SCONJ
cana-5401	6	10	they	they	PRON
cana-5401	6	11	ca	can	AUX
cana-5401	6	12	n’t	not	PART
cana-5401	6	13	process	process	VERB
cana-5401	6	14	large	large	ADJ
cana-5401	6	15	amounts	amount	NOUN
cana-5401	6	16	of	of	ADP
cana-5401	6	17	data	datum	NOUN
cana-5401	6	18	and	and	CCONJ
cana-5401	6	19	information	information	NOUN
cana-5401	6	20	.	.	PUNCT
cana-5401	7	1	thus	thus	ADV
cana-5401	7	2	,	,	PUNCT
cana-5401	7	3	in	in	ADP
cana-5401	7	4	the	the	DET
cana-5401	7	5	present	present	ADJ
cana-5401	7	6	scenario	scenario	NOUN
cana-5401	7	7	,	,	PUNCT
cana-5401	7	8	machine	machine	NOUN
cana-5401	7	9	learning	learn	VERB
cana-5401	7	10	algorithms	algorithm	NOUN
cana-5401	7	11	are	be	AUX
cana-5401	7	12	utilized	utilize	VERB
cana-5401	7	13	in	in	ADP
cana-5401	7	14	crime	crime	NOUN
cana-5401	7	15	prediction	prediction	NOUN
cana-5401	7	16	models	model	NOUN
cana-5401	7	17	to	to	PART
cana-5401	7	18	analyse	analyse	VERB
cana-5401	7	19	big	big	ADJ
cana-5401	7	20	data	datum	NOUN
cana-5401	7	21	and	and	CCONJ
cana-5401	7	22	find	find	VERB
cana-5401	7	23	crime	crime	NOUN
cana-5401	7	24	patterns	pattern	NOUN
cana-5401	7	25	based	base	VERB
cana-5401	7	26	on	on	ADP
cana-5401	7	27	various	various	ADJ
cana-5401	7	28	factors	factor	NOUN
cana-5401	7	29	.	.	PUNCT
cana-5401	8	1	in	in	ADP
cana-5401	8	2	this	this	DET
cana-5401	8	3	paper	paper	NOUN
cana-5401	8	4	,	,	PUNCT
cana-5401	8	5	we	we	PRON
cana-5401	8	6	have	have	AUX
cana-5401	8	7	evaluated	evaluate	VERB
cana-5401	8	8	the	the	DET
cana-5401	8	9	various	various	ADJ
cana-5401	8	10	machine	machine	NOUN
cana-5401	8	11	learning	learn	VERB
cana-5401	8	12	algorithms	algorithm	NOUN
cana-5401	8	13	,	,	PUNCT
cana-5401	8	14	namely	namely	ADV
cana-5401	8	15	,	,	PUNCT
cana-5401	8	16	knn	knn	PROPN
cana-5401	8	17	,	,	PUNCT
cana-5401	8	18	nn	nn	PROPN
cana-5401	8	19	,	,	PUNCT
cana-5401	8	20	rf	rf	NOUN
cana-5401	8	21	,	,	PUNCT
cana-5401	8	22	and	and	CCONJ
cana-5401	8	23	nb	nb	INTJ
cana-5401	8	24	for	for	ADP
cana-5401	8	25	crime	crime	NOUN
cana-5401	8	26	prediction	prediction	NOUN
cana-5401	8	27	.	.	PUNCT
cana-5401	9	1	in	in	ADP
cana-5401	9	2	the	the	DET
cana-5401	9	3	proposed	propose	VERB
cana-5401	9	4	model	model	NOUN
cana-5401	9	5	,	,	PUNCT
cana-5401	9	6	the	the	DET
cana-5401	9	7	same	same	ADJ
cana-5401	9	8	dataset	dataset	NOUN
cana-5401	9	9	is	be	AUX
cana-5401	9	10	trained	train	VERB
cana-5401	9	11	and	and	CCONJ
cana-5401	9	12	tested	test	VERB
cana-5401	9	13	for	for	ADP
cana-5401	9	14	different	different	ADJ
cana-5401	9	15	machine	machine	NOUN
cana-5401	9	16	learning	learn	VERB
cana-5401	9	17	algorithms	algorithm	NOUN
cana-5401	9	18	and	and	CCONJ
cana-5401	9	19	find	find	VERB
cana-5401	9	20	out	out	ADP
cana-5401	9	21	which	which	DET
cana-5401	9	22	algorithm	algorithm	NOUN
cana-5401	9	23	is	be	AUX
cana-5401	9	24	effectively	effectively	ADV
cana-5401	9	25	predicting	predict	VERB
cana-5401	9	26	the	the	DET
cana-5401	9	27	crime	crime	NOUN
cana-5401	9	28	.	.	PUNCT
cana-5401	10	1	in	in	ADP
cana-5401	10	2	addition	addition	NOUN
cana-5401	10	3	,	,	PUNCT
cana-5401	10	4	preprocessing	preprocessing	NOUN
cana-5401	10	5	of	of	ADP
cana-5401	10	6	the	the	DET
cana-5401	10	7	dataset	dataset	NOUN
cana-5401	10	8	is	be	AUX
cana-5401	10	9	done	do	VERB
cana-5401	10	10	to	to	PART
cana-5401	10	11	remove	remove	VERB
cana-5401	10	12	inconsistencies	inconsistency	NOUN
cana-5401	10	13	in	in	ADP
cana-5401	10	14	the	the	DET
cana-5401	10	15	dataset	dataset	NOUN
cana-5401	10	16	and	and	CCONJ
cana-5401	10	17	select	select	VERB
cana-5401	10	18	the	the	DET
cana-5401	10	19	appropriate	appropriate	ADJ
cana-5401	10	20	features	feature	NOUN
cana-5401	10	21	using	use	VERB
cana-5401	10	22	the	the	DET
cana-5401	10	23	correlation	correlation	NOUN
cana-5401	10	24	matrix	matrix	NOUN
cana-5401	10	25	.	.	PUNCT
cana-5401	11	1	further	far	ADV
cana-5401	11	2	,	,	PUNCT
cana-5401	11	3	the	the	DET
cana-5401	11	4	chicago	chicago	PROPN
cana-5401	11	5	dataset	dataset	NOUN
cana-5401	11	6	is	be	AUX
cana-5401	11	7	used	use	VERB
cana-5401	11	8	for	for	ADP
cana-5401	11	9	evaluation	evaluation	NOUN
cana-5401	11	10	purposes	purpose	NOUN
cana-5401	11	11	and	and	CCONJ
cana-5401	11	12	the	the	DET
cana-5401	11	13	code	code	NOUN
cana-5401	11	14	is	be	AUX
cana-5401	11	15	designed	design	VERB
cana-5401	11	16	and	and	CCONJ
cana-5401	11	17	simulated	simulate	VERB
cana-5401	11	18	with	with	ADP
cana-5401	11	19	the	the	DET
cana-5401	11	20	help	help	NOUN
cana-5401	11	21	of	of	ADP
cana-5401	11	22	python	python	NOUN
cana-5401	11	23	and	and	CCONJ
cana-5401	11	24	google	google	PROPN
cana-5401	11	25	colab	colab	PROPN
cana-5401	11	26	software	software	PROPN
cana-5401	11	27	.	.	PUNCT
cana-5401	12	1	finally	finally	ADV
cana-5401	12	2	,	,	PUNCT
cana-5401	12	3	the	the	DET
cana-5401	12	4	various	various	ADJ
cana-5401	12	5	performance	performance	NOUN
cana-5401	12	6	metrics	metric	NOUN
cana-5401	12	7	are	be	AUX
cana-5401	12	8	determined	determine	VERB
cana-5401	12	9	for	for	ADP
cana-5401	12	10	the	the	DET
cana-5401	12	11	crime	crime	NOUN
cana-5401	12	12	prediction	prediction	NOUN
cana-5401	12	13	model	model	NOUN
cana-5401	12	14	and	and	CCONJ
cana-5401	12	15	find	find	VERB
cana-5401	12	16	out	out	ADP
cana-5401	12	17	that	that	SCONJ
cana-5401	12	18	nn	nn	PROPN
cana-5401	12	19	outperforms	outperform	NOUN
cana-5401	12	20	over	over	ADP
cana-5401	12	21	other	other	ADJ
cana-5401	12	22	machine	machine	NOUN
cana-5401	12	23	learning	learn	VERB
cana-5401	12	24	algorithms	algorithm	NOUN
cana-5401	12	25	.	.	PUNCT
cana-5401	13	1	keywords	keyword	NOUN
cana-5401	13	2	:	:	PUNCT
cana-5401	13	3	chicago	chicago	PROPN
cana-5401	13	4	,	,	PUNCT
cana-5401	13	5	crime	crime	NOUN
cana-5401	13	6	,	,	PUNCT
cana-5401	13	7	knn	knn	PROPN
cana-5401	13	8	,	,	PUNCT
cana-5401	13	9	machine	machine	NOUN
cana-5401	13	10	learning	learning	NOUN
cana-5401	13	11	,	,	PUNCT
cana-5401	13	12	neural	neural	ADJ
cana-5401	13	13	network	network	NOUN
cana-5401	13	14	,	,	PUNCT
cana-5401	13	15	prediction	prediction	NOUN
cana-5401	13	16	,	,	PUNCT
cana-5401	13	17	random	random	ADJ
cana-5401	13	18	forest	forest	NOUN
cana-5401	13	19	.	.	PUNCT
cana-5401	14	1	abbreviations	abbreviation	NOUN
cana-5401	14	2	:	:	PUNCT
cana-5401	14	3	ml	ml	X
cana-5401	14	4	:	:	PUNCT
cana-5401	14	5	machine	machine	NOUN
cana-5401	14	6	learning	learning	NOUN
cana-5401	14	7	nb	nb	PROPN
cana-5401	14	8	:	:	PUNCT
cana-5401	14	9	naïve	naïve	PROPN
cana-5401	14	10	bayes	bayes	PROPN
cana-5401	14	11	knn	knn	PROPN
cana-5401	14	12	:	:	PUNCT
cana-5401	14	13	k	k	ADJ
cana-5401	14	14	-	-	PUNCT
cana-5401	14	15	nearest	near	ADJ
cana-5401	14	16	neighbour	neighbour	NOUN
cana-5401	14	17	rf	rf	NOUN
cana-5401	14	18	:	:	PUNCT
cana-5401	14	19	random	random	ADJ
cana-5401	14	20	forest	forest	NOUN
cana-5401	14	21	nn	nn	PROPN
cana-5401	14	22	:	:	PUNCT
cana-5401	14	23	neural	neural	ADJ
cana-5401	14	24	network	network	NOUN
cana-5401	14	25	a	a	PRON
cana-5401	14	26	:	:	PUNCT
cana-5401	14	27	accuracy	accuracy	NOUN
cana-5401	14	28	p	p	X
cana-5401	14	29	:	:	PUNCT
cana-5401	14	30	precision	precision	NOUN
cana-5401	14	31	r	r	NOUN
cana-5401	14	32	:	:	PUNCT
cana-5401	14	33	recall	recall	NOUN
cana-5401	14	34	1	1	NUM
cana-5401	14	35	.	.	PUNCT
cana-5401	15	1	introduction	introduction	NOUN
cana-5401	15	2	criminal	criminal	ADJ
cana-5401	15	3	activity	activity	NOUN
cana-5401	15	4	has	have	AUX
cana-5401	15	5	become	become	VERB
cana-5401	15	6	a	a	DET
cana-5401	15	7	serious	serious	ADJ
cana-5401	15	8	societal	societal	ADJ
cana-5401	15	9	issue	issue	NOUN
cana-5401	15	10	due	due	ADP
cana-5401	15	11	to	to	ADP
cana-5401	15	12	its	its	PRON
cana-5401	15	13	negative	negative	ADJ
cana-5401	15	14	impact	impact	NOUN
cana-5401	15	15	on	on	ADP
cana-5401	15	16	human	human	ADJ
cana-5401	15	17	lives	life	NOUN
cana-5401	15	18	,	,	PUNCT
cana-5401	15	19	safety	safety	NOUN
cana-5401	15	20	,	,	PUNCT
cana-5401	15	21	and	and	CCONJ
cana-5401	15	22	economy	economy	NOUN
cana-5401	15	23	.	.	PUNCT
cana-5401	16	1	in	in	ADP
cana-5401	16	2	the	the	DET
cana-5401	16	3	past	past	ADJ
cana-5401	16	4	few	few	ADJ
cana-5401	16	5	years	year	NOUN
cana-5401	16	6	,	,	PUNCT
cana-5401	16	7	crime	crime	NOUN
cana-5401	16	8	data	datum	NOUN
cana-5401	16	9	has	have	AUX
cana-5401	16	10	become	become	VERB
cana-5401	16	11	more	more	ADV
cana-5401	16	12	accessible	accessible	ADJ
cana-5401	16	13	,	,	PUNCT
cana-5401	16	14	which	which	PRON
cana-5401	16	15	has	have	AUX
cana-5401	16	16	allowed	allow	VERB
cana-5401	16	17	experts	expert	NOUN
cana-5401	16	18	communications	communication	NOUN
cana-5401	16	19	on	on	ADP
cana-5401	16	20	applied	apply	VERB
cana-5401	16	21	nonlinear	nonlinear	ADJ
cana-5401	16	22	analysis	analysis	NOUN
cana-5401	16	23	issn	issn	NOUN
cana-5401	16	24	:	:	PUNCT
cana-5401	16	25	1074	1074	NUM
cana-5401	16	26	-	-	PUNCT
cana-5401	16	27	133x	133x	NUM
cana-5401	16	28	vol	vol	NOUN
cana-5401	16	29	32	32	NUM
cana-5401	16	30	no	no	NOUN
cana-5401	16	31	.	.	PUNCT
cana-5401	17	1	icmasd	icmasd	NOUN
cana-5401	17	2	(	(	PUNCT
cana-5401	17	3	2025	2025	NUM
cana-5401	17	4	)	)	PUNCT
cana-5401	17	5	1855	1855	NUM
cana-5401	17	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-5401	18	1	to	to	PART
cana-5401	18	2	create	create	VERB
cana-5401	18	3	models	model	NOUN
cana-5401	18	4	that	that	PRON
cana-5401	18	5	can	can	AUX
cana-5401	18	6	predict	predict	VERB
cana-5401	18	7	crime	crime	NOUN
cana-5401	19	1	[	[	X
cana-5401	19	2	1	1	NUM
cana-5401	19	3	]	]	PUNCT
cana-5401	19	4	.	.	PUNCT
cana-5401	20	1	based	base	VERB
cana-5401	20	2	on	on	ADP
cana-5401	20	3	past	past	ADJ
cana-5401	20	4	crimes	crime	NOUN
cana-5401	20	5	,	,	PUNCT
cana-5401	20	6	the	the	DET
cana-5401	20	7	government	government	NOUN
cana-5401	20	8	and	and	CCONJ
cana-5401	20	9	other	other	ADJ
cana-5401	20	10	responsible	responsible	ADJ
cana-5401	20	11	officials	official	NOUN
cana-5401	20	12	can	can	AUX
cana-5401	20	13	take	take	VERB
cana-5401	20	14	steps	step	NOUN
cana-5401	20	15	to	to	PART
cana-5401	20	16	stop	stop	VERB
cana-5401	20	17	crimes	crime	NOUN
cana-5401	20	18	before	before	SCONJ
cana-5401	20	19	they	they	PRON
cana-5401	20	20	happen	happen	VERB
cana-5401	20	21	.	.	PUNCT
cana-5401	21	1	to	to	PART
cana-5401	21	2	keep	keep	VERB
cana-5401	21	3	society	society	NOUN
cana-5401	21	4	safe	safe	ADJ
cana-5401	21	5	from	from	ADP
cana-5401	21	6	crimes	crime	NOUN
cana-5401	21	7	,	,	PUNCT
cana-5401	21	8	it	it	PRON
cana-5401	21	9	would	would	AUX
cana-5401	21	10	be	be	AUX
cana-5401	21	11	helpful	helpful	ADJ
cana-5401	21	12	to	to	PART
cana-5401	21	13	understand	understand	VERB
cana-5401	21	14	the	the	DET
cana-5401	21	15	reasons	reason	NOUN
cana-5401	21	16	behind	behind	ADP
cana-5401	21	17	crime	crime	NOUN
cana-5401	21	18	predictions	prediction	NOUN
cana-5401	21	19	so	so	SCONJ
cana-5401	21	20	that	that	SCONJ
cana-5401	21	21	suitable	suitable	ADJ
cana-5401	21	22	preventative	preventative	ADJ
cana-5401	21	23	measures	measure	NOUN
cana-5401	21	24	may	may	AUX
cana-5401	21	25	be	be	AUX
cana-5401	21	26	planned	plan	VERB
cana-5401	21	27	.	.	PUNCT
cana-5401	22	1	it	it	PRON
cana-5401	22	2	is	be	AUX
cana-5401	22	3	difficult	difficult	ADJ
cana-5401	22	4	to	to	PART
cana-5401	22	5	reach	reach	VERB
cana-5401	22	6	conclusions	conclusion	NOUN
cana-5401	22	7	from	from	ADP
cana-5401	22	8	the	the	DET
cana-5401	22	9	crime	crime	NOUN
cana-5401	22	10	data	datum	NOUN
cana-5401	22	11	since	since	SCONJ
cana-5401	22	12	it	it	PRON
cana-5401	22	13	is	be	AUX
cana-5401	22	14	both	both	CCONJ
cana-5401	22	15	large	large	ADJ
cana-5401	22	16	and	and	CCONJ
cana-5401	22	17	unorganized	unorganized	ADJ
cana-5401	22	18	.	.	PUNCT
cana-5401	23	1	because	because	SCONJ
cana-5401	23	2	of	of	ADP
cana-5401	23	3	this	this	PRON
cana-5401	23	4	,	,	PUNCT
cana-5401	23	5	machine	machine	NOUN
cana-5401	23	6	learning	learning	NOUN
cana-5401	23	7	(	(	PUNCT
cana-5401	23	8	ml	ml	NOUN
cana-5401	23	9	)	)	PUNCT
cana-5401	23	10	methods	method	NOUN
cana-5401	23	11	have	have	VERB
cana-5401	23	12	the	the	DET
cana-5401	23	13	potential	potential	NOUN
cana-5401	23	14	to	to	PART
cana-5401	23	15	minimize	minimize	VERB
cana-5401	23	16	effort	effort	NOUN
cana-5401	23	17	in	in	ADP
cana-5401	23	18	the	the	DET
cana-5401	23	19	current	current	ADJ
cana-5401	23	20	context	context	NOUN
cana-5401	23	21	by	by	ADP
cana-5401	23	22	rapidly	rapidly	ADV
cana-5401	23	23	evaluating	evaluate	VERB
cana-5401	23	24	vast	vast	ADJ
cana-5401	23	25	volumes	volume	NOUN
cana-5401	23	26	of	of	ADP
cana-5401	23	27	data	datum	NOUN
cana-5401	23	28	to	to	PART
cana-5401	23	29	uncover	uncover	VERB
cana-5401	23	30	criminal	criminal	ADJ
cana-5401	23	31	patterns	pattern	NOUN
cana-5401	23	32	.	.	PUNCT
cana-5401	24	1	this	this	PRON
cana-5401	24	2	is	be	AUX
cana-5401	24	3	made	make	VERB
cana-5401	24	4	possible	possible	ADJ
cana-5401	24	5	by	by	ADP
cana-5401	24	6	the	the	DET
cana-5401	24	7	rising	rise	VERB
cana-5401	24	8	movement	movement	NOUN
cana-5401	24	9	toward	toward	ADP
cana-5401	24	10	technology	technology	NOUN
cana-5401	24	11	and	and	CCONJ
cana-5401	24	12	developments	development	NOUN
cana-5401	24	13	in	in	ADP
cana-5401	24	14	artificial	artificial	ADJ
cana-5401	24	15	intelligence	intelligence	NOUN
cana-5401	24	16	(	(	PUNCT
cana-5401	24	17	ai	ai	NOUN
cana-5401	24	18	)	)	PUNCT
cana-5401	25	1	[	[	X
cana-5401	25	2	2	2	NUM
cana-5401	25	3	]	]	PUNCT
cana-5401	25	4	.	.	PUNCT
cana-5401	26	1	the	the	DET
cana-5401	26	2	next	next	ADJ
cana-5401	26	3	section	section	NOUN
cana-5401	26	4	provides	provide	VERB
cana-5401	26	5	an	an	DET
cana-5401	26	6	overview	overview	NOUN
cana-5401	26	7	of	of	ADP
cana-5401	26	8	machine	machine	NOUN
cana-5401	26	9	learning	learning	NOUN
cana-5401	26	10	and	and	CCONJ
cana-5401	26	11	its	its	PRON
cana-5401	26	12	many	many	ADJ
cana-5401	26	13	categories	category	NOUN
cana-5401	26	14	.	.	PUNCT
cana-5401	27	1	machine	machine	NOUN
cana-5401	27	2	learning	learning	NOUN
cana-5401	27	3	(	(	PUNCT
cana-5401	27	4	ml	ml	NOUN
cana-5401	27	5	)	)	PUNCT
cana-5401	27	6	is	be	AUX
cana-5401	27	7	widely	widely	ADV
cana-5401	27	8	recognized	recognize	VERB
cana-5401	27	9	as	as	ADP
cana-5401	27	10	the	the	DET
cana-5401	27	11	newest	new	ADJ
cana-5401	27	12	and	and	CCONJ
cana-5401	27	13	most	most	ADV
cana-5401	27	14	popular	popular	ADJ
cana-5401	27	15	technology	technology	NOUN
cana-5401	27	16	because	because	SCONJ
cana-5401	27	17	it	it	PRON
cana-5401	27	18	enables	enable	VERB
cana-5401	27	19	systems	system	NOUN
cana-5401	27	20	to	to	PART
cana-5401	27	21	automatically	automatically	ADV
cana-5401	27	22	learn	learn	VERB
cana-5401	27	23	from	from	ADP
cana-5401	27	24	experience	experience	NOUN
cana-5401	27	25	and	and	CCONJ
cana-5401	27	26	improve	improve	VERB
cana-5401	27	27	without	without	ADP
cana-5401	27	28	special	special	ADJ
cana-5401	27	29	programming	programming	NOUN
cana-5401	27	30	.	.	PUNCT
cana-5401	28	1	figure	figure	NOUN
cana-5401	28	2	1	1	NUM
cana-5401	29	1	[	[	X
cana-5401	29	2	3	3	NUM
cana-5401	29	3	]	]	PUNCT
cana-5401	29	4	illustrates	illustrate	VERB
cana-5401	29	5	how	how	SCONJ
cana-5401	29	6	machine	machine	NOUN
cana-5401	29	7	learning	learn	VERB
cana-5401	29	8	algorithms	algorithm	NOUN
cana-5401	29	9	are	be	AUX
cana-5401	29	10	primarily	primarily	ADV
cana-5401	29	11	categorized	categorize	VERB
cana-5401	29	12	into	into	ADP
cana-5401	29	13	four	four	NUM
cana-5401	29	14	types	type	NOUN
cana-5401	29	15	.	.	PUNCT
cana-5401	30	1	these	these	PRON
cana-5401	30	2	are	be	AUX
cana-5401	30	3	semi	semi	ADJ
cana-5401	30	4	-	-	ADJ
cana-5401	30	5	supervised	supervised	ADJ
cana-5401	30	6	learning	learning	NOUN
cana-5401	30	7	,	,	PUNCT
cana-5401	30	8	reinforcement	reinforcement	NOUN
cana-5401	30	9	learning	learning	NOUN
cana-5401	30	10	,	,	PUNCT
cana-5401	30	11	unsupervised	unsupervised	ADJ
cana-5401	30	12	learning	learning	NOUN
cana-5401	30	13	,	,	PUNCT
cana-5401	30	14	and	and	CCONJ
cana-5401	30	15	supervised	supervised	ADJ
cana-5401	30	16	learning	learning	NOUN
cana-5401	30	17	.	.	PUNCT
cana-5401	31	1	figure	figure	VERB
cana-5401	31	2	1	1	NUM
cana-5401	31	3	:	:	PUNCT
cana-5401	31	4	categories	category	NOUN
cana-5401	31	5	of	of	ADP
cana-5401	31	6	the	the	DET
cana-5401	31	7	ml	ml	X
cana-5401	31	8	the	the	DET
cana-5401	31	9	following	following	NOUN
cana-5401	31	10	provides	provide	VERB
cana-5401	31	11	a	a	DET
cana-5401	31	12	brief	brief	ADJ
cana-5401	31	13	summary	summary	NOUN
cana-5401	31	14	of	of	ADP
cana-5401	31	15	every	every	DET
cana-5401	31	16	type	type	NOUN
cana-5401	31	17	of	of	ADP
cana-5401	31	18	learning	learn	VERB
cana-5401	31	19	strategy	strategy	NOUN
cana-5401	31	20	and	and	CCONJ
cana-5401	31	21	how	how	SCONJ
cana-5401	31	22	it	it	PRON
cana-5401	31	23	might	might	AUX
cana-5401	31	24	be	be	AUX
cana-5401	31	25	used	use	VERB
cana-5401	31	26	to	to	PART
cana-5401	31	27	address	address	VERB
cana-5401	31	28	real	real	ADJ
cana-5401	31	29	-	-	PUNCT
cana-5401	31	30	world	world	NOUN
cana-5401	31	31	issues	issue	NOUN
cana-5401	31	32	[	[	X
cana-5401	31	33	3	3	NUM
cana-5401	31	34	]	]	PUNCT
cana-5401	31	35	.	.	PUNCT
cana-5401	32	1	•	•	NUM
cana-5401	32	2	supervised	supervised	ADJ
cana-5401	32	3	:	:	PUNCT
cana-5401	32	4	supervised	supervised	ADJ
cana-5401	32	5	learning	learning	NOUN
cana-5401	32	6	is	be	AUX
cana-5401	32	7	a	a	DET
cana-5401	32	8	machine	machine	NOUN
cana-5401	32	9	learning	learning	NOUN
cana-5401	32	10	technique	technique	NOUN
cana-5401	32	11	that	that	PRON
cana-5401	32	12	involves	involve	VERB
cana-5401	32	13	using	use	VERB
cana-5401	32	14	example	example	NOUN
cana-5401	32	15	input	input	NOUN
cana-5401	32	16	-	-	PUNCT
cana-5401	32	17	output	output	NOUN
cana-5401	32	18	pairs	pair	NOUN
cana-5401	32	19	to	to	PART
cana-5401	32	20	develop	develop	VERB
cana-5401	32	21	a	a	DET
cana-5401	32	22	function	function	NOUN
cana-5401	32	23	that	that	PRON
cana-5401	32	24	links	link	VERB
cana-5401	32	25	an	an	DET
cana-5401	32	26	input	input	NOUN
cana-5401	32	27	to	to	ADP
cana-5401	32	28	an	an	DET
cana-5401	32	29	output	output	NOUN
cana-5401	32	30	.	.	PUNCT
cana-5401	33	1	the	the	DET
cana-5401	33	2	method	method	NOUN
cana-5401	33	3	generates	generate	VERB
cana-5401	33	4	a	a	DET
cana-5401	33	5	function	function	NOUN
cana-5401	33	6	from	from	ADP
cana-5401	33	7	a	a	DET
cana-5401	33	8	set	set	NOUN
cana-5401	33	9	of	of	ADP
cana-5401	33	10	labelled	label	VERB
cana-5401	33	11	training	training	NOUN
cana-5401	33	12	examples	example	NOUN
cana-5401	33	13	and	and	CCONJ
cana-5401	33	14	training	training	NOUN
cana-5401	33	15	data	datum	NOUN
cana-5401	33	16	.	.	PUNCT
cana-5401	34	1	this	this	DET
cana-5401	34	2	type	type	NOUN
cana-5401	34	3	of	of	ADP
cana-5401	34	4	learning	learning	NOUN
cana-5401	34	5	is	be	AUX
cana-5401	34	6	called	call	VERB
cana-5401	34	7	taskdriven	taskdriven	ADJ
cana-5401	34	8	learning	learning	NOUN
cana-5401	34	9	,	,	PUNCT
cana-5401	34	10	and	and	CCONJ
cana-5401	34	11	it	it	PRON
cana-5401	34	12	happens	happen	VERB
cana-5401	34	13	when	when	SCONJ
cana-5401	34	14	clear	clear	ADJ
cana-5401	34	15	goals	goal	NOUN
cana-5401	34	16	need	need	VERB
cana-5401	34	17	to	to	PART
cana-5401	34	18	be	be	AUX
cana-5401	34	19	met	meet	VERB
cana-5401	34	20	from	from	ADP
cana-5401	34	21	a	a	DET
cana-5401	34	22	set	set	NOUN
cana-5401	34	23	of	of	ADP
cana-5401	34	24	sources	source	NOUN
cana-5401	34	25	[	[	X
cana-5401	34	26	105	105	NUM
cana-5401	34	27	]	]	PUNCT
cana-5401	34	28	.	.	PUNCT
cana-5401	35	1	the	the	DET
cana-5401	35	2	two	two	NUM
cana-5401	35	3	most	most	ADV
cana-5401	35	4	popular	popular	ADJ
cana-5401	35	5	supervised	supervised	ADJ
cana-5401	35	6	tasks	task	NOUN
cana-5401	35	7	are	be	AUX
cana-5401	35	8	“	"	PUNCT
cana-5401	35	9	regression	regression	NOUN
cana-5401	35	10	,	,	PUNCT
cana-5401	35	11	”	"	PUNCT
cana-5401	35	12	which	which	PRON
cana-5401	35	13	fits	fit	VERB
cana-5401	35	14	the	the	DET
cana-5401	35	15	data	datum	NOUN
cana-5401	35	16	,	,	PUNCT
cana-5401	35	17	and	and	CCONJ
cana-5401	35	18	“	"	PUNCT
cana-5401	35	19	classification	classification	NOUN
cana-5401	35	20	,	,	PUNCT
cana-5401	35	21	”	"	PUNCT
cana-5401	35	22	which	which	PRON
cana-5401	35	23	divides	divide	VERB
cana-5401	35	24	the	the	DET
cana-5401	35	25	data	datum	NOUN
cana-5401	35	26	.	.	PUNCT
cana-5401	36	1	•	•	NUM
cana-5401	36	2	unsupervised	unsupervised	ADJ
cana-5401	36	3	:	:	PUNCT
cana-5401	37	1	unsupervised	unsupervised	ADJ
cana-5401	37	2	learning	learning	NOUN
cana-5401	37	3	,	,	PUNCT
cana-5401	37	4	also	also	ADV
cana-5401	37	5	known	know	VERB
cana-5401	37	6	as	as	ADP
cana-5401	37	7	data	data	NOUN
cana-5401	37	8	-	-	PUNCT
cana-5401	37	9	driven	drive	VERB
cana-5401	37	10	processing	processing	NOUN
cana-5401	37	11	,	,	PUNCT
cana-5401	37	12	analyses	analyse	VERB
cana-5401	37	13	unlabelled	unlabelled	ADJ
cana-5401	37	14	information	information	NOUN
cana-5401	37	15	without	without	ADP
cana-5401	37	16	the	the	DET
cana-5401	37	17	need	need	NOUN
cana-5401	37	18	for	for	ADP
cana-5401	37	19	human	human	ADJ
cana-5401	37	20	supervision	supervision	NOUN
cana-5401	37	21	.	.	PUNCT
cana-5401	38	1	this	this	PRON
cana-5401	38	2	is	be	AUX
cana-5401	38	3	often	often	ADV
cana-5401	38	4	used	use	VERB
cana-5401	38	5	for	for	ADP
cana-5401	38	6	exploratory	exploratory	ADJ
cana-5401	38	7	reasons	reason	NOUN
cana-5401	38	8	,	,	PUNCT
cana-5401	38	9	groupings	grouping	NOUN
cana-5401	38	10	in	in	ADP
cana-5401	38	11	findings	finding	NOUN
cana-5401	38	12	,	,	PUNCT
cana-5401	38	13	generative	generative	ADJ
cana-5401	38	14	feature	feature	NOUN
cana-5401	38	15	extraction	extraction	NOUN
cana-5401	38	16	,	,	PUNCT
cana-5401	38	17	and	and	CCONJ
cana-5401	38	18	significant	significant	ADJ
cana-5401	38	19	trend	trend	NOUN
cana-5401	38	20	and	and	CCONJ
cana-5401	38	21	structure	structure	NOUN
cana-5401	38	22	identification	identification	NOUN
cana-5401	38	23	.	.	PUNCT
cana-5401	39	1	in	in	ADP
cana-5401	39	2	unsupervised	unsupervised	ADJ
cana-5401	39	3	learning	learning	NOUN
cana-5401	39	4	,	,	PUNCT
cana-5401	39	5	the	the	DET
cana-5401	39	6	most	most	ADV
cana-5401	39	7	common	common	ADJ
cana-5401	39	8	duties	duty	NOUN
cana-5401	39	9	are	be	AUX
cana-5401	39	10	finding	find	VERB
cana-5401	39	11	association	association	NOUN
cana-5401	39	12	rules	rule	NOUN
cana-5401	39	13	,	,	PUNCT
cana-5401	39	14	estimating	estimate	VERB
cana-5401	39	15	density	density	NOUN
cana-5401	39	16	,	,	PUNCT
cana-5401	39	17	learning	learn	VERB
cana-5401	39	18	features	feature	NOUN
cana-5401	39	19	,	,	PUNCT
cana-5401	39	20	reducing	reduce	VERB
cana-5401	39	21	the	the	DET
cana-5401	39	22	number	number	NOUN
cana-5401	39	23	of	of	ADP
cana-5401	39	24	dimensions	dimension	NOUN
cana-5401	39	25	,	,	PUNCT
cana-5401	39	26	finding	find	VERB
cana-5401	39	27	outliers	outlier	NOUN
cana-5401	39	28	,	,	PUNCT
cana-5401	39	29	and	and	CCONJ
cana-5401	39	30	so	so	ADV
cana-5401	39	31	on	on	ADV
cana-5401	39	32	.	.	PUNCT
cana-5401	40	1	•	•	NUM
cana-5401	40	2	semi	semi	ADV
cana-5401	40	3	-	-	ADJ
cana-5401	40	4	supervised	supervised	ADJ
cana-5401	40	5	:	:	PUNCT
cana-5401	40	6	semi	semi	ADJ
cana-5401	40	7	-	-	ADJ
cana-5401	40	8	supervised	supervised	ADJ
cana-5401	40	9	learning	learning	NOUN
cana-5401	40	10	is	be	AUX
cana-5401	40	11	a	a	DET
cana-5401	40	12	combination	combination	NOUN
cana-5401	40	13	of	of	ADP
cana-5401	40	14	the	the	DET
cana-5401	40	15	previous	previous	ADJ
cana-5401	40	16	supervised	supervised	ADJ
cana-5401	40	17	and	and	CCONJ
cana-5401	40	18	unsupervised	unsupervised	ADJ
cana-5401	40	19	approaches	approach	NOUN
cana-5401	40	20	which	which	PRON
cana-5401	40	21	operates	operate	VERB
cana-5401	40	22	on	on	ADP
cana-5401	40	23	both	both	PRON
cana-5401	40	24	labelled	label	VERB
cana-5401	40	25	and	and	CCONJ
cana-5401	40	26	unlabelled	unlabelled	ADJ
cana-5401	40	27	data	datum	NOUN
cana-5401	40	28	[	[	X
cana-5401	40	29	41	41	NUM
cana-5401	40	30	,	,	PUNCT
cana-5401	40	31	105	105	NUM
cana-5401	40	32	]	]	PUNCT
cana-5401	40	33	.	.	PUNCT
cana-5401	41	1	therefore	therefore	ADV
cana-5401	41	2	,	,	PUNCT
cana-5401	41	3	it	it	PRON
cana-5401	41	4	communications	communication	VERB
cana-5401	41	5	on	on	ADP
cana-5401	41	6	applied	apply	VERB
cana-5401	41	7	nonlinear	nonlinear	ADJ
cana-5401	41	8	analysis	analysis	NOUN
cana-5401	41	9	issn	issn	NOUN
cana-5401	41	10	:	:	PUNCT
cana-5401	41	11	1074	1074	NUM
cana-5401	41	12	-	-	PUNCT
cana-5401	41	13	133x	133x	NUM
cana-5401	41	14	vol	vol	NOUN
cana-5401	41	15	32	32	NUM
cana-5401	41	16	no	no	NOUN
cana-5401	41	17	.	.	PUNCT
cana-5401	42	1	icmasd	icmasd	NOUN
cana-5401	42	2	(	(	PUNCT
cana-5401	42	3	2025	2025	NUM
cana-5401	42	4	)	)	PUNCT
cana-5401	42	5	1856	1856	NUM
cana-5401	43	1	https://internationalpubls.com	https://internationalpubls.com	X
cana-5401	43	2	is	be	AUX
cana-5401	43	3	situated	situate	VERB
cana-5401	43	4	the	the	DET
cana-5401	43	5	middle	middle	NOUN
cana-5401	43	6	of	of	ADP
cana-5401	43	7	"	"	PUNCT
cana-5401	43	8	supervised	supervised	ADJ
cana-5401	43	9	"	"	PUNCT
cana-5401	43	10	and	and	CCONJ
cana-5401	43	11	"	"	PUNCT
cana-5401	43	12	unsupervised	unsupervised	ADJ
cana-5401	43	13	"	"	PUNCT
cana-5401	43	14	learning	learning	NOUN
cana-5401	43	15	.	.	PUNCT
cana-5401	44	1	in	in	ADP
cana-5401	44	2	real	real	ADJ
cana-5401	44	3	life	life	NOUN
cana-5401	44	4	,	,	PUNCT
cana-5401	44	5	semi	semi	ADJ
cana-5401	44	6	-	-	ADJ
cana-5401	44	7	supervised	supervised	ADJ
cana-5401	44	8	learning	learning	NOUN
cana-5401	44	9	is	be	AUX
cana-5401	44	10	helpful	helpful	ADJ
cana-5401	44	11	since	since	SCONJ
cana-5401	44	12	labelled	label	VERB
cana-5401	44	13	data	datum	NOUN
cana-5401	44	14	may	may	AUX
cana-5401	44	15	be	be	AUX
cana-5401	44	16	limited	limit	VERB
cana-5401	44	17	in	in	ADP
cana-5401	44	18	some	some	DET
cana-5401	44	19	situations	situation	NOUN
cana-5401	44	20	while	while	SCONJ
cana-5401	44	21	unlabelled	unlabelled	ADJ
cana-5401	44	22	data	datum	NOUN
cana-5401	44	23	are	be	AUX
cana-5401	44	24	common	common	ADJ
cana-5401	44	25	.	.	PUNCT
cana-5401	45	1	a	a	DET
cana-5401	45	2	semi	semi	ADJ
cana-5401	45	3	-	-	ADJ
cana-5401	45	4	supervised	supervised	ADJ
cana-5401	45	5	learning	learning	NOUN
cana-5401	45	6	model	model	NOUN
cana-5401	45	7	's	's	PART
cana-5401	45	8	main	main	ADJ
cana-5401	45	9	goal	goal	NOUN
cana-5401	45	10	is	be	AUX
cana-5401	45	11	to	to	PART
cana-5401	45	12	make	make	VERB
cana-5401	45	13	predictions	prediction	NOUN
cana-5401	45	14	that	that	PRON
cana-5401	45	15	are	be	AUX
cana-5401	45	16	more	more	ADV
cana-5401	45	17	accurate	accurate	ADJ
cana-5401	45	18	than	than	ADP
cana-5401	45	19	those	those	PRON
cana-5401	45	20	made	make	VERB
cana-5401	45	21	with	with	ADP
cana-5401	45	22	just	just	ADV
cana-5401	45	23	the	the	DET
cana-5401	45	24	labelled	label	VERB
cana-5401	45	25	data	datum	NOUN
cana-5401	45	26	from	from	ADP
cana-5401	45	27	the	the	DET
cana-5401	45	28	model	model	NOUN
cana-5401	45	29	.	.	PUNCT
cana-5401	46	1	•	•	NUM
cana-5401	46	2	reinforcement	reinforcement	NOUN
cana-5401	46	3	:	:	PUNCT
cana-5401	46	4	reinforcement	reinforcement	NOUN
cana-5401	46	5	learning	learning	NOUN
cana-5401	46	6	is	be	AUX
cana-5401	46	7	a	a	DET
cana-5401	46	8	form	form	NOUN
cana-5401	46	9	of	of	ADP
cana-5401	46	10	machine	machine	NOUN
cana-5401	46	11	learning	learning	NOUN
cana-5401	46	12	technique	technique	NOUN
cana-5401	46	13	that	that	PRON
cana-5401	46	14	allows	allow	VERB
cana-5401	46	15	software	software	NOUN
cana-5401	46	16	agents	agent	NOUN
cana-5401	46	17	and	and	CCONJ
cana-5401	46	18	computers	computer	NOUN
cana-5401	46	19	to	to	PART
cana-5401	46	20	automatically	automatically	ADV
cana-5401	46	21	analyse	analyse	VERB
cana-5401	46	22	the	the	DET
cana-5401	46	23	best	good	ADJ
cana-5401	46	24	behaviour	behaviour	NOUN
cana-5401	46	25	in	in	ADP
cana-5401	46	26	a	a	DET
cana-5401	46	27	certain	certain	ADJ
cana-5401	46	28	context	context	NOUN
cana-5401	46	29	or	or	CCONJ
cana-5401	46	30	environment	environment	NOUN
cana-5401	46	31	in	in	ADP
cana-5401	46	32	order	order	NOUN
cana-5401	46	33	to	to	PART
cana-5401	46	34	enhance	enhance	VERB
cana-5401	46	35	its	its	PRON
cana-5401	46	36	efficiency	efficiency	NOUN
cana-5401	46	37	.	.	PUNCT
cana-5401	47	1	this	this	DET
cana-5401	47	2	method	method	NOUN
cana-5401	47	3	is	be	AUX
cana-5401	47	4	known	know	VERB
cana-5401	47	5	as	as	ADP
cana-5401	47	6	an	an	DET
cana-5401	47	7	environment	environment	NOUN
cana-5401	47	8	-	-	PUNCT
cana-5401	47	9	driven	drive	VERB
cana-5401	47	10	approach	approach	NOUN
cana-5401	47	11	.	.	PUNCT
cana-5401	48	1	with	with	ADP
cana-5401	48	2	the	the	DET
cana-5401	48	3	help	help	NOUN
cana-5401	48	4	of	of	ADP
cana-5401	48	5	environmental	environmental	ADJ
cana-5401	48	6	activists	activist	NOUN
cana-5401	48	7	,	,	PUNCT
cana-5401	48	8	this	this	DET
cana-5401	48	9	kind	kind	NOUN
cana-5401	48	10	of	of	ADP
cana-5401	48	11	reinforcement	reinforcement	NOUN
cana-5401	48	12	learning	learning	NOUN
cana-5401	48	13	aims	aim	VERB
cana-5401	48	14	to	to	PART
cana-5401	48	15	take	take	VERB
cana-5401	48	16	action	action	NOUN
cana-5401	48	17	that	that	PRON
cana-5401	48	18	will	will	AUX
cana-5401	48	19	maximize	maximize	VERB
cana-5401	48	20	reward	reward	NOUN
cana-5401	48	21	and	and	CCONJ
cana-5401	48	22	reduce	reduce	VERB
cana-5401	48	23	risk	risk	NOUN
cana-5401	48	24	.	.	PUNCT
cana-5401	49	1	the	the	DET
cana-5401	49	2	main	main	ADJ
cana-5401	49	3	motive	motive	NOUN
cana-5401	49	4	of	of	ADP
cana-5401	49	5	this	this	DET
cana-5401	49	6	research	research	NOUN
cana-5401	49	7	is	be	AUX
cana-5401	49	8	to	to	PART
cana-5401	49	9	evaluate	evaluate	VERB
cana-5401	49	10	the	the	DET
cana-5401	49	11	various	various	ADJ
cana-5401	49	12	machine	machine	NOUN
cana-5401	49	13	learning	learn	VERB
cana-5401	49	14	algorithms	algorithm	NOUN
cana-5401	49	15	for	for	ADP
cana-5401	49	16	crime	crime	NOUN
cana-5401	49	17	prediction	prediction	NOUN
cana-5401	49	18	.	.	PUNCT
cana-5401	50	1	in	in	ADP
cana-5401	50	2	this	this	DET
cana-5401	50	3	research	research	NOUN
cana-5401	50	4	,	,	PUNCT
cana-5401	50	5	nb	nb	PROPN
cana-5401	50	6	,	,	PUNCT
cana-5401	50	7	knn	knn	PROPN
cana-5401	50	8	,	,	PUNCT
cana-5401	50	9	rf	rf	PROPN
cana-5401	50	10	,	,	PUNCT
cana-5401	50	11	and	and	CCONJ
cana-5401	50	12	nn	nn	NUM
cana-5401	50	13	algorithms	algorithm	NOUN
cana-5401	50	14	are	be	AUX
cana-5401	50	15	taken	take	VERB
cana-5401	50	16	into	into	ADP
cana-5401	50	17	consideration	consideration	NOUN
cana-5401	50	18	.	.	PUNCT
cana-5401	51	1	besides	besides	SCONJ
cana-5401	51	2	that	that	PRON
cana-5401	51	3	,	,	PUNCT
cana-5401	51	4	the	the	DET
cana-5401	51	5	crime	crime	NOUN
cana-5401	51	6	prediction	prediction	NOUN
cana-5401	51	7	dataset	dataset	NOUN
cana-5401	51	8	is	be	AUX
cana-5401	51	9	inconsistent	inconsistent	ADJ
cana-5401	51	10	so	so	ADV
cana-5401	51	11	pre	pre	ADJ
cana-5401	51	12	-	-	ADJ
cana-5401	51	13	processing	processing	NOUN
cana-5401	51	14	is	be	AUX
cana-5401	51	15	done	do	VERB
cana-5401	51	16	on	on	ADP
cana-5401	51	17	it	it	PRON
cana-5401	51	18	for	for	ADP
cana-5401	51	19	removing	remove	VERB
cana-5401	51	20	the	the	DET
cana-5401	51	21	unwanted	unwanted	ADJ
cana-5401	51	22	attributes	attribute	NOUN
cana-5401	51	23	,	,	PUNCT
cana-5401	51	24	missing	miss	VERB
cana-5401	51	25	values	value	NOUN
cana-5401	51	26	,	,	PUNCT
cana-5401	51	27	finding	find	VERB
cana-5401	51	28	the	the	DET
cana-5401	51	29	appropriate	appropriate	ADJ
cana-5401	51	30	features	feature	NOUN
cana-5401	51	31	,	,	PUNCT
cana-5401	51	32	and	and	CCONJ
cana-5401	51	33	splitting	splitting	NOUN
cana-5401	51	34	in	in	ADP
cana-5401	51	35	the	the	DET
cana-5401	51	36	training	training	NOUN
cana-5401	51	37	and	and	CCONJ
cana-5401	51	38	testing	testing	NOUN
cana-5401	51	39	dataset	dataset	NOUN
cana-5401	51	40	.	.	PUNCT
cana-5401	52	1	the	the	DET
cana-5401	52	2	simulation	simulation	NOUN
cana-5401	52	3	evaluation	evaluation	NOUN
cana-5401	52	4	of	of	ADP
cana-5401	52	5	the	the	DET
cana-5401	52	6	proposed	propose	VERB
cana-5401	52	7	model	model	NOUN
cana-5401	52	8	is	be	AUX
cana-5401	52	9	done	do	VERB
cana-5401	52	10	for	for	ADP
cana-5401	52	11	chicago	chicago	PROPN
cana-5401	52	12	dataset	dataset	NOUN
cana-5401	52	13	and	and	CCONJ
cana-5401	52	14	various	various	ADJ
cana-5401	52	15	performance	performance	NOUN
cana-5401	52	16	metrics	metric	NOUN
cana-5401	52	17	are	be	AUX
cana-5401	52	18	determined	determine	VERB
cana-5401	52	19	.	.	PUNCT
cana-5401	53	1	the	the	DET
cana-5401	53	2	result	result	NOUN
cana-5401	53	3	shows	show	VERB
cana-5401	53	4	that	that	SCONJ
cana-5401	53	5	the	the	DET
cana-5401	53	6	nn	nn	PROPN
cana-5401	53	7	algorithm	algorithm	NOUN
cana-5401	53	8	is	be	AUX
cana-5401	53	9	outperformed	outperform	VERB
cana-5401	53	10	over	over	ADP
cana-5401	53	11	the	the	DET
cana-5401	53	12	other	other	ADJ
cana-5401	53	13	algorithms	algorithm	NOUN
cana-5401	53	14	.	.	PUNCT
cana-5401	54	1	the	the	DET
cana-5401	54	2	paper	paper	NOUN
cana-5401	54	3	is	be	AUX
cana-5401	54	4	outlines	outline	NOUN
cana-5401	54	5	into	into	ADP
cana-5401	54	6	six	six	NUM
cana-5401	54	7	sections	section	NOUN
cana-5401	54	8	.	.	PUNCT
cana-5401	55	1	section	section	NOUN
cana-5401	55	2	1	1	NUM
cana-5401	55	3	gives	give	VERB
cana-5401	55	4	a	a	DET
cana-5401	55	5	background	background	NOUN
cana-5401	55	6	information	information	NOUN
cana-5401	55	7	,	,	PUNCT
cana-5401	55	8	followed	follow	VERB
cana-5401	55	9	by	by	ADP
cana-5401	55	10	why	why	SCONJ
cana-5401	55	11	machine	machine	NOUN
cana-5401	55	12	learning	learn	VERB
cana-5401	55	13	algorithms	algorithm	NOUN
cana-5401	55	14	are	be	AUX
cana-5401	55	15	gained	gain	VERB
cana-5401	55	16	popularity	popularity	NOUN
cana-5401	55	17	in	in	ADP
cana-5401	55	18	the	the	DET
cana-5401	55	19	crime	crime	NOUN
cana-5401	55	20	prediction	prediction	NOUN
cana-5401	55	21	models	model	NOUN
cana-5401	55	22	.	.	PUNCT
cana-5401	56	1	section	section	NOUN
cana-5401	56	2	2	2	NUM
cana-5401	56	3	shows	show	VERB
cana-5401	56	4	the	the	DET
cana-5401	56	5	related	relate	VERB
cana-5401	56	6	work	work	NOUN
cana-5401	56	7	is	be	AUX
cana-5401	56	8	done	do	VERB
cana-5401	56	9	in	in	ADP
cana-5401	56	10	the	the	DET
cana-5401	56	11	crime	crime	NOUN
cana-5401	56	12	prediction	prediction	NOUN
cana-5401	56	13	models	model	NOUN
cana-5401	56	14	.	.	PUNCT
cana-5401	57	1	section	section	NOUN
cana-5401	57	2	3	3	NUM
cana-5401	57	3	explains	explain	VERB
cana-5401	57	4	the	the	DET
cana-5401	57	5	proposed	propose	VERB
cana-5401	57	6	methodology	methodology	NOUN
cana-5401	57	7	in	in	ADP
cana-5401	57	8	this	this	DET
cana-5401	57	9	section	section	NOUN
cana-5401	57	10	the	the	DET
cana-5401	57	11	relevant	relevant	ADJ
cana-5401	57	12	dataset	dataset	NOUN
cana-5401	57	13	,	,	PUNCT
cana-5401	57	14	machine	machine	NOUN
cana-5401	57	15	learning	learning	NOUN
cana-5401	57	16	algorithms	algorithm	NOUN
cana-5401	57	17	,	,	PUNCT
cana-5401	57	18	and	and	CCONJ
cana-5401	57	19	performance	performance	NOUN
cana-5401	57	20	metrics	metric	NOUN
cana-5401	57	21	.	.	PUNCT
cana-5401	58	1	section	section	NOUN
cana-5401	58	2	4	4	NUM
cana-5401	58	3	explains	explain	VERB
cana-5401	58	4	the	the	DET
cana-5401	58	5	proposed	propose	VERB
cana-5401	58	6	crime	crime	NOUN
cana-5401	58	7	prediction	prediction	NOUN
cana-5401	58	8	model	model	NOUN
cana-5401	58	9	.	.	PUNCT
cana-5401	59	1	section	section	NOUN
cana-5401	59	2	5	5	NUM
cana-5401	59	3	shows	show	VERB
cana-5401	59	4	the	the	DET
cana-5401	59	5	simulation	simulation	NOUN
cana-5401	59	6	results	result	NOUN
cana-5401	59	7	are	be	AUX
cana-5401	59	8	performed	perform	VERB
cana-5401	59	9	for	for	ADP
cana-5401	59	10	chicago	chicago	PROPN
cana-5401	59	11	dataset	dataset	NOUN
cana-5401	59	12	using	use	VERB
cana-5401	59	13	the	the	DET
cana-5401	59	14	various	various	ADJ
cana-5401	59	15	performance	performance	NOUN
cana-5401	59	16	metrics	metric	NOUN
cana-5401	59	17	.	.	PUNCT
cana-5401	60	1	finally	finally	ADV
cana-5401	60	2	,	,	PUNCT
cana-5401	60	3	the	the	DET
cana-5401	60	4	paper	paper	NOUN
cana-5401	60	5	is	be	AUX
cana-5401	60	6	concluded	conclude	VERB
cana-5401	60	7	and	and	CCONJ
cana-5401	60	8	future	future	ADJ
cana-5401	60	9	aspects	aspect	NOUN
cana-5401	60	10	are	be	AUX
cana-5401	60	11	defined	define	VERB
cana-5401	60	12	to	to	PART
cana-5401	60	13	enhance	enhance	VERB
cana-5401	60	14	the	the	DET
cana-5401	60	15	proposed	propose	VERB
cana-5401	60	16	model	model	NOUN
cana-5401	60	17	in	in	ADP
cana-5401	60	18	section	section	NOUN
cana-5401	60	19	6	6	NUM
cana-5401	60	20	.	.	NOUN
cana-5401	61	1	2	2	NUM
cana-5401	61	2	.	.	NUM
cana-5401	61	3	related	relate	VERB
cana-5401	61	4	work	work	NOUN
cana-5401	61	5	in	in	ADP
cana-5401	61	6	this	this	DET
cana-5401	61	7	section	section	NOUN
cana-5401	61	8	,	,	PUNCT
cana-5401	61	9	related	related	ADJ
cana-5401	61	10	work	work	NOUN
cana-5401	61	11	is	be	AUX
cana-5401	61	12	shown	show	VERB
cana-5401	61	13	to	to	PART
cana-5401	61	14	understand	understand	VERB
cana-5401	61	15	how	how	SCONJ
cana-5401	61	16	the	the	DET
cana-5401	61	17	researchers	researcher	NOUN
cana-5401	61	18	utilized	utilize	VERB
cana-5401	61	19	the	the	DET
cana-5401	61	20	various	various	ADJ
cana-5401	61	21	machine	machine	NOUN
cana-5401	61	22	learning	learn	VERB
cana-5401	61	23	algorithms	algorithm	NOUN
cana-5401	61	24	to	to	PART
cana-5401	61	25	design	design	VERB
cana-5401	61	26	crime	crime	NOUN
cana-5401	61	27	prediction	prediction	NOUN
cana-5401	61	28	model	model	NOUN
cana-5401	61	29	in	in	ADP
cana-5401	61	30	the	the	DET
cana-5401	61	31	literature	literature	NOUN
cana-5401	61	32	.	.	PUNCT
cana-5401	62	1	the	the	DET
cana-5401	62	2	authors	author	NOUN
cana-5401	62	3	,	,	PUNCT
cana-5401	62	4	safat	safat	PROPN
cana-5401	62	5	et	et	PROPN
cana-5401	62	6	al	al	PROPN
cana-5401	62	7	.	.	PROPN
cana-5401	62	8	,	,	PUNCT
cana-5401	62	9	(	(	PUNCT
cana-5401	62	10	2021	2021	NUM
cana-5401	62	11	)	)	PUNCT
cana-5401	62	12	,	,	PUNCT
cana-5401	62	13	designed	design	VERB
cana-5401	62	14	two	two	NUM
cana-5401	62	15	models	model	NOUN
cana-5401	62	16	,	,	PUNCT
cana-5401	62	17	the	the	DET
cana-5401	62	18	first	first	ADJ
cana-5401	62	19	model	model	NOUN
cana-5401	62	20	is	be	AUX
cana-5401	62	21	employed	employ	VERB
cana-5401	62	22	for	for	ADP
cana-5401	62	23	crime	crime	NOUN
cana-5401	62	24	predicted	predict	VERB
cana-5401	62	25	whereas	whereas	SCONJ
cana-5401	62	26	second	second	ADJ
cana-5401	62	27	model	model	NOUN
cana-5401	62	28	is	be	AUX
cana-5401	62	29	employed	employ	VERB
cana-5401	62	30	for	for	ADP
cana-5401	62	31	crime	crime	NOUN
cana-5401	62	32	forecasting	forecasting	NOUN
cana-5401	62	33	.	.	PUNCT
cana-5401	63	1	in	in	ADP
cana-5401	63	2	their	their	PRON
cana-5401	63	3	research	research	NOUN
cana-5401	63	4	,	,	PUNCT
cana-5401	63	5	a	a	DET
cana-5401	63	6	number	number	NOUN
cana-5401	63	7	of	of	ADP
cana-5401	63	8	machine	machine	NOUN
cana-5401	63	9	learning	learn	VERB
cana-5401	63	10	algorithms	algorithm	NOUN
cana-5401	63	11	are	be	AUX
cana-5401	63	12	utilized	utilize	VERB
cana-5401	63	13	and	and	CCONJ
cana-5401	63	14	evaluated	evaluate	VERB
cana-5401	63	15	using	use	VERB
cana-5401	63	16	the	the	DET
cana-5401	63	17	various	various	ADJ
cana-5401	63	18	performance	performance	NOUN
cana-5401	63	19	metrics	metric	NOUN
cana-5401	63	20	.	.	PUNCT
cana-5401	64	1	the	the	DET
cana-5401	64	2	simulation	simulation	NOUN
cana-5401	64	3	evaluation	evaluation	NOUN
cana-5401	64	4	of	of	ADP
cana-5401	64	5	the	the	DET
cana-5401	64	6	crime	crime	NOUN
cana-5401	64	7	prediction	prediction	NOUN
cana-5401	64	8	model	model	NOUN
cana-5401	64	9	is	be	AUX
cana-5401	64	10	done	do	VERB
cana-5401	64	11	using	use	VERB
cana-5401	64	12	various	various	ADJ
cana-5401	64	13	performance	performance	NOUN
cana-5401	64	14	metrics	metric	NOUN
cana-5401	64	15	such	such	ADJ
cana-5401	64	16	as	as	ADP
cana-5401	64	17	accuracy	accuracy	NOUN
cana-5401	64	18	,	,	PUNCT
cana-5401	64	19	precision	precision	NOUN
cana-5401	64	20	,	,	PUNCT
cana-5401	64	21	recall	recall	NOUN
cana-5401	64	22	,	,	PUNCT
cana-5401	64	23	and	and	CCONJ
cana-5401	64	24	f1	f1	NOUN
cana-5401	64	25	-	-	PUNCT
cana-5401	64	26	score	score	NOUN
cana-5401	64	27	.	.	PUNCT
cana-5401	65	1	on	on	ADP
cana-5401	65	2	the	the	DET
cana-5401	65	3	other	other	ADJ
cana-5401	65	4	side	side	NOUN
cana-5401	65	5	,	,	PUNCT
cana-5401	65	6	the	the	DET
cana-5401	65	7	crime	crime	NOUN
cana-5401	65	8	forecasting	forecasting	NOUN
cana-5401	65	9	model	model	NOUN
cana-5401	65	10	is	be	AUX
cana-5401	65	11	evaluated	evaluate	VERB
cana-5401	65	12	using	use	VERB
cana-5401	65	13	rmse	rmse	PROPN
cana-5401	65	14	and	and	CCONJ
cana-5401	65	15	mae	mae	PROPN
cana-5401	65	16	parameter	parameter	NOUN
cana-5401	65	17	.	.	PUNCT
cana-5401	66	1	the	the	DET
cana-5401	66	2	result	result	NOUN
cana-5401	66	3	shows	show	VERB
cana-5401	66	4	the	the	DET
cana-5401	66	5	lr	lr	NOUN
cana-5401	66	6	outperforms	outperform	NOUN
cana-5401	66	7	over	over	ADP
cana-5401	66	8	other	other	ADJ
cana-5401	66	9	algorithms	algorithm	NOUN
cana-5401	66	10	in	in	ADP
cana-5401	66	11	the	the	DET
cana-5401	66	12	crime	crime	NOUN
cana-5401	66	13	prediction	prediction	NOUN
cana-5401	66	14	model	model	NOUN
cana-5401	66	15	and	and	CCONJ
cana-5401	66	16	forecasting	forecasting	NOUN
cana-5401	66	17	model	model	NOUN
cana-5401	66	18	shows	show	VERB
cana-5401	66	19	that	that	SCONJ
cana-5401	66	20	the	the	DET
cana-5401	66	21	crime	crime	NOUN
cana-5401	66	22	rate	rate	NOUN
cana-5401	66	23	in	in	ADP
cana-5401	66	24	the	the	DET
cana-5401	66	25	los	los	PROPN
cana-5401	66	26	angeles	angeles	PROPN
cana-5401	66	27	increases	increase	VERB
cana-5401	66	28	in	in	ADP
cana-5401	66	29	the	the	DET
cana-5401	66	30	future	future	NOUN
cana-5401	66	31	over	over	ADP
cana-5401	66	32	the	the	DET
cana-5401	66	33	chicago	chicago	PROPN
cana-5401	66	34	.	.	PUNCT
cana-5401	67	1	3	3	X
cana-5401	67	2	.	.	NUM
cana-5401	67	3	proposed	propose	VERB
cana-5401	67	4	methodology	methodology	NOUN
cana-5401	67	5	in	in	ADP
cana-5401	67	6	order	order	NOUN
cana-5401	67	7	to	to	PART
cana-5401	67	8	understand	understand	VERB
cana-5401	67	9	the	the	DET
cana-5401	67	10	proposed	propose	VERB
cana-5401	67	11	crime	crime	NOUN
cana-5401	67	12	prediction	prediction	NOUN
cana-5401	67	13	model	model	NOUN
cana-5401	67	14	,	,	PUNCT
cana-5401	67	15	in	in	ADP
cana-5401	67	16	this	this	DET
cana-5401	67	17	section	section	NOUN
cana-5401	67	18	,	,	PUNCT
cana-5401	67	19	dataset	dataset	NOUN
cana-5401	67	20	,	,	PUNCT
cana-5401	67	21	machine	machine	NOUN
cana-5401	67	22	learning	learning	NOUN
cana-5401	67	23	algorithms	algorithm	NOUN
cana-5401	67	24	,	,	PUNCT
cana-5401	67	25	and	and	CCONJ
cana-5401	67	26	performance	performance	NOUN
cana-5401	67	27	evaluation	evaluation	NOUN
cana-5401	67	28	metrics	metric	NOUN
cana-5401	67	29	are	be	AUX
cana-5401	67	30	explained	explain	VERB
cana-5401	67	31	.	.	PUNCT
cana-5401	68	1	3.1	3.1	NUM
cana-5401	68	2	dataset	dataset	NOUN
cana-5401	68	3	:	:	PUNCT
cana-5401	68	4	in	in	ADP
cana-5401	68	5	this	this	DET
cana-5401	68	6	study	study	NOUN
cana-5401	68	7	,	,	PUNCT
cana-5401	68	8	the	the	DET
cana-5401	68	9	criminal	criminal	ADJ
cana-5401	68	10	record	record	NOUN
cana-5401	68	11	of	of	ADP
cana-5401	68	12	chicago	chicago	PROPN
cana-5401	68	13	city	city	NOUN
cana-5401	68	14	dataset	dataset	NOUN
cana-5401	68	15	is	be	AUX
cana-5401	68	16	taken	take	VERB
cana-5401	68	17	because	because	SCONJ
cana-5401	68	18	of	of	ADP
cana-5401	68	19	data	datum	NOUN
cana-5401	68	20	availability	availability	NOUN
cana-5401	68	21	and	and	CCONJ
cana-5401	68	22	higher	high	ADJ
cana-5401	68	23	crime	crime	NOUN
cana-5401	68	24	rate	rate	NOUN
cana-5401	68	25	over	over	ADP
cana-5401	68	26	the	the	DET
cana-5401	68	27	us	us	PROPN
cana-5401	68	28	.	.	PUNCT
cana-5401	69	1	this	this	DET
cana-5401	69	2	dataset	dataset	NOUN
cana-5401	69	3	contains	contain	VERB
cana-5401	69	4	the	the	DET
cana-5401	69	5	crime	crime	NOUN
cana-5401	69	6	information	information	NOUN
cana-5401	69	7	from	from	ADP
cana-5401	69	8	the	the	DET
cana-5401	69	9	communications	communication	NOUN
cana-5401	69	10	on	on	ADP
cana-5401	69	11	applied	apply	VERB
cana-5401	69	12	nonlinear	nonlinear	ADJ
cana-5401	69	13	analysis	analysis	NOUN
cana-5401	69	14	issn	issn	NOUN
cana-5401	69	15	:	:	PUNCT
cana-5401	69	16	1074	1074	NUM
cana-5401	69	17	-	-	PUNCT
cana-5401	69	18	133x	133x	NUM
cana-5401	69	19	vol	vol	NOUN
cana-5401	69	20	32	32	NUM
cana-5401	69	21	no	no	NOUN
cana-5401	69	22	.	.	PUNCT
cana-5401	70	1	icmasd	icmasd	NOUN
cana-5401	70	2	(	(	PUNCT
cana-5401	70	3	2025	2025	NUM
cana-5401	70	4	)	)	PUNCT
cana-5401	70	5	1857	1857	NUM
cana-5401	70	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-5401	70	7	year	year	NOUN
cana-5401	70	8	2001	2001	NUM
cana-5401	70	9	to	to	ADP
cana-5401	70	10	2019	2019	NUM
cana-5401	70	11	.	.	PUNCT
cana-5401	71	1	in	in	ADP
cana-5401	71	2	this	this	DET
cana-5401	71	3	research	research	NOUN
cana-5401	71	4	,	,	PUNCT
cana-5401	71	5	7002821	7002821	NUM
cana-5401	71	6	instance	instance	NOUN
cana-5401	71	7	are	be	AUX
cana-5401	71	8	taken	take	VERB
cana-5401	71	9	into	into	ADP
cana-5401	71	10	consideration	consideration	NOUN
cana-5401	71	11	out	out	ADP
cana-5401	71	12	of	of	ADP
cana-5401	71	13	7019734	7019734	NUM
cana-5401	71	14	because	because	SCONJ
cana-5401	71	15	some	some	PRON
cana-5401	71	16	of	of	ADP
cana-5401	71	17	the	the	DET
cana-5401	71	18	dataset	dataset	NOUN
cana-5401	71	19	instance	instance	NOUN
cana-5401	71	20	is	be	AUX
cana-5401	71	21	inappropriate	inappropriate	ADJ
cana-5401	71	22	.	.	PUNCT
cana-5401	72	1	3.2	3.2	NUM
cana-5401	72	2	machine	machine	NOUN
cana-5401	72	3	learning	learn	VERB
cana-5401	72	4	algorithms	algorithm	NOUN
cana-5401	72	5	:	:	PUNCT
cana-5401	72	6	in	in	ADP
cana-5401	72	7	this	this	DET
cana-5401	72	8	section	section	NOUN
cana-5401	72	9	,	,	PUNCT
cana-5401	72	10	a	a	DET
cana-5401	72	11	detailed	detailed	ADJ
cana-5401	72	12	description	description	NOUN
cana-5401	72	13	of	of	ADP
cana-5401	72	14	the	the	DET
cana-5401	72	15	machine	machine	NOUN
cana-5401	72	16	learning	learn	VERB
cana-5401	72	17	algorithms	algorithm	NOUN
cana-5401	72	18	is	be	AUX
cana-5401	72	19	given	give	VERB
cana-5401	72	20	which	which	PRON
cana-5401	72	21	are	be	AUX
cana-5401	72	22	employed	employ	VERB
cana-5401	72	23	in	in	ADP
cana-5401	72	24	the	the	DET
cana-5401	72	25	crime	crime	NOUN
cana-5401	72	26	prediction	prediction	NOUN
cana-5401	72	27	model	model	NOUN
cana-5401	72	28	.	.	PUNCT
cana-5401	73	1	•	•	NUM
cana-5401	73	2	nb	nb	INTJ
cana-5401	73	3	:	:	PUNCT
cana-5401	73	4	the	the	DET
cana-5401	73	5	naive	naive	ADJ
cana-5401	73	6	bayes	bayes	NOUN
cana-5401	73	7	technique	technique	NOUN
cana-5401	73	8	of	of	ADP
cana-5401	73	9	conditional	conditional	ADJ
cana-5401	73	10	probabilities	probability	NOUN
cana-5401	73	11	relies	rely	VERB
cana-5401	73	12	on	on	ADP
cana-5401	73	13	the	the	DET
cana-5401	73	14	bayesian	bayesian	NOUN
cana-5401	73	15	theorem	theorem	VERB
cana-5401	73	16	.	.	PUNCT
cana-5401	74	1	it	it	PRON
cana-5401	74	2	determines	determine	VERB
cana-5401	74	3	probability	probability	NOUN
cana-5401	74	4	by	by	ADP
cana-5401	74	5	the	the	DET
cana-5401	74	6	counting	counting	NOUN
cana-5401	74	7	of	of	ADP
cana-5401	74	8	frequently	frequently	ADV
cana-5401	74	9	occurring	occur	VERB
cana-5401	74	10	values	value	NOUN
cana-5401	74	11	[	[	X
cana-5401	74	12	1	1	NUM
cana-5401	74	13	]	]	PUNCT
cana-5401	74	14	.	.	PUNCT
cana-5401	75	1	the	the	DET
cana-5401	75	2	following	follow	VERB
cana-5401	75	3	is	be	AUX
cana-5401	75	4	an	an	DET
cana-5401	75	5	overview	overview	NOUN
cana-5401	75	6	of	of	ADP
cana-5401	75	7	naive	naive	ADJ
cana-5401	75	8	bayes	baye	NOUN
cana-5401	75	9	:	:	PUNCT
cana-5401	76	1	1	1	X
cana-5401	76	2	.	.	X
cana-5401	76	3	a	a	DET
cana-5401	76	4	basic	basic	ADJ
cana-5401	76	5	classifier	classifier	NOUN
cana-5401	76	6	for	for	ADP
cana-5401	76	7	a	a	DET
cana-5401	76	8	classification	classification	NOUN
cana-5401	76	9	method	method	NOUN
cana-5401	76	10	2	2	NUM
cana-5401	76	11	.	.	PUNCT
cana-5401	76	12	most	most	ADV
cana-5401	76	13	appropriate	appropriate	ADJ
cana-5401	76	14	for	for	ADP
cana-5401	76	15	past	past	ADJ
cana-5401	76	16	data	datum	NOUN
cana-5401	76	17	and	and	CCONJ
cana-5401	76	18	forecasting	forecasting	NOUN
cana-5401	76	19	3	3	NUM
cana-5401	76	20	.	.	PUNCT
cana-5401	77	1	analyse	analyse	VERB
cana-5401	77	2	the	the	DET
cana-5401	77	3	link	link	NOUN
cana-5401	77	4	between	between	ADP
cana-5401	77	5	attributes	attribute	NOUN
cana-5401	77	6	and	and	CCONJ
cana-5401	77	7	class	class	NOUN
cana-5401	77	8	instances	instance	NOUN
cana-5401	77	9	using	use	VERB
cana-5401	77	10	the	the	DET
cana-5401	77	11	classification	classification	NOUN
cana-5401	77	12	approach	approach	NOUN
cana-5401	77	13	.	.	PUNCT
cana-5401	78	1	4	4	X
cana-5401	78	2	.	.	X
cana-5401	78	3	a	a	DET
cana-5401	78	4	technique	technique	NOUN
cana-5401	78	5	for	for	ADP
cana-5401	78	6	supervised	supervised	ADJ
cana-5401	78	7	learning	learning	NOUN
cana-5401	78	8	that	that	PRON
cana-5401	78	9	can	can	AUX
cana-5401	78	10	resolve	resolve	VERB
cana-5401	78	11	probabilistic	probabilistic	ADJ
cana-5401	78	12	and	and	CCONJ
cana-5401	78	13	categorical	categorical	ADJ
cana-5401	78	14	issues	issue	NOUN
cana-5401	78	15	5	5	NUM
cana-5401	78	16	.	.	PUNCT
cana-5401	79	1	a	a	DET
cana-5401	79	2	well	well	ADV
cana-5401	79	3	-	-	PUNCT
cana-5401	79	4	liked	like	VERB
cana-5401	79	5	method	method	NOUN
cana-5401	79	6	of	of	ADP
cana-5401	79	7	classification	classification	NOUN
cana-5401	79	8	for	for	ADP
cana-5401	79	9	text	text	NOUN
cana-5401	79	10	classification	classification	NOUN
cana-5401	79	11	.	.	PUNCT
cana-5401	80	1	in	in	ADP
cana-5401	80	2	1995	1995	NUM
cana-5401	80	3	,	,	PUNCT
cana-5401	80	4	naive	naive	ADJ
cana-5401	80	5	bayes	bayes	NOUN
cana-5401	80	6	algorithm	algorithm	PROPN
cana-5401	80	7	was	be	AUX
cana-5401	80	8	first	first	ADV
cana-5401	80	9	used	use	VERB
cana-5401	80	10	.	.	PUNCT
cana-5401	81	1	it	it	PRON
cana-5401	81	2	is	be	AUX
cana-5401	81	3	referred	refer	VERB
cana-5401	81	4	to	to	ADP
cana-5401	81	5	by	by	ADP
cana-5401	81	6	several	several	ADJ
cana-5401	81	7	names	name	NOUN
cana-5401	81	8	in	in	ADP
cana-5401	81	9	the	the	DET
cana-5401	81	10	machine	machine	NOUN
cana-5401	81	11	learning	learning	NOUN
cana-5401	81	12	and	and	CCONJ
cana-5401	81	13	data	datum	NOUN
cana-5401	81	14	mining	mining	NOUN
cana-5401	81	15	communities	community	NOUN
cana-5401	81	16	,	,	PUNCT
cana-5401	81	17	including	include	VERB
cana-5401	81	18	independence	independence	NOUN
cana-5401	81	19	bayes	baye	NOUN
cana-5401	81	20	and	and	CCONJ
cana-5401	81	21	simple	simple	ADJ
cana-5401	81	22	bases	basis	NOUN
cana-5401	81	23	.	.	PUNCT
cana-5401	82	1	this	this	DET
cana-5401	82	2	classifier	classifier	NOUN
cana-5401	82	3	is	be	AUX
cana-5401	82	4	widely	widely	ADV
cana-5401	82	5	utilized	utilize	VERB
cana-5401	82	6	in	in	ADP
cana-5401	82	7	many	many	ADJ
cana-5401	82	8	applications	application	NOUN
cana-5401	82	9	,	,	PUNCT
cana-5401	82	10	including	include	VERB
cana-5401	82	11	ensemble	ensemble	ADJ
cana-5401	82	12	prediction	prediction	NOUN
cana-5401	82	13	and	and	CCONJ
cana-5401	82	14	sentiment	sentiment	NOUN
cana-5401	82	15	classification	classification	NOUN
cana-5401	82	16	models	model	NOUN
cana-5401	82	17	.	.	PUNCT
cana-5401	83	1	the	the	DET
cana-5401	83	2	naive	naive	ADJ
cana-5401	83	3	bayes	bayes	NOUN
cana-5401	83	4	classifier	classifier	NOUN
cana-5401	83	5	must	must	AUX
cana-5401	83	6	compute	compute	VERB
cana-5401	83	7	two	two	NUM
cana-5401	83	8	sorts	sort	NOUN
cana-5401	83	9	of	of	ADP
cana-5401	83	10	values	value	NOUN
cana-5401	83	11	from	from	ADP
cana-5401	83	12	the	the	DET
cana-5401	83	13	dataset	dataset	NOUN
cana-5401	83	14	.	.	PUNCT
cana-5401	84	1	these	these	PRON
cana-5401	84	2	are	be	AUX
cana-5401	84	3	conditional	conditional	ADJ
cana-5401	84	4	probabilities	probability	NOUN
cana-5401	84	5	and	and	CCONJ
cana-5401	84	6	class	class	NOUN
cana-5401	84	7	probabilities	probability	NOUN
cana-5401	84	8	.	.	PUNCT
cana-5401	85	1	the	the	DET
cana-5401	85	2	following	follow	VERB
cana-5401	85	3	equation	equation	NOUN
cana-5401	85	4	describes	describe	VERB
cana-5401	85	5	the	the	DET
cana-5401	85	6	bayesian	bayesian	NOUN
cana-5401	85	7	classifier	classifier	NOUN
cana-5401	85	8	's	's	PART
cana-5401	85	9	approach	approach	NOUN
cana-5401	85	10	:	:	PUNCT
cana-5401	85	11	(	(	PUNCT
cana-5401	85	12	1	1	X
cana-5401	85	13	)	)	PUNCT
cana-5401	85	14	in	in	ADP
cana-5401	85	15	this	this	DET
cana-5401	85	16	case	case	NOUN
cana-5401	85	17	,	,	PUNCT
cana-5401	85	18	p(c	p(c	NOUN
cana-5401	85	19	-	-	PUNCT
cana-5401	85	20	x	x	NOUN
cana-5401	85	21	)	)	PUNCT
cana-5401	85	22	represents	represent	VERB
cana-5401	85	23	the	the	DET
cana-5401	85	24	maximum	maximum	ADJ
cana-5401	85	25	posterior	posterior	ADJ
cana-5401	85	26	hypothesis	hypothesis	NOUN
cana-5401	85	27	,	,	PUNCT
cana-5401	85	28	p(x	p(x	PROPN
cana-5401	85	29	)	)	PUNCT
cana-5401	85	30	is	be	AUX
cana-5401	85	31	evidence	evidence	NOUN
cana-5401	85	32	,	,	PUNCT
cana-5401	85	33	p(c	p(c	NOUN
cana-5401	85	34	)	)	PUNCT
cana-5401	85	35	is	be	AUX
cana-5401	85	36	the	the	DET
cana-5401	85	37	prior	prior	ADJ
cana-5401	85	38	,	,	PUNCT
cana-5401	85	39	and	and	CCONJ
cana-5401	85	40	p(x	p(x	NOUN
cana-5401	85	41	-	-	PUNCT
cana-5401	85	42	c	c	NOUN
cana-5401	85	43	)	)	PUNCT
cana-5401	85	44	is	be	AUX
cana-5401	85	45	the	the	DET
cana-5401	85	46	probability	probability	NOUN
cana-5401	85	47	of	of	ADP
cana-5401	85	48	the	the	DET
cana-5401	85	49	hypothesis	hypothesis	NOUN
cana-5401	85	50	.	.	PUNCT
cana-5401	86	1	•	•	NUM
cana-5401	86	2	knn	knn	PROPN
cana-5401	86	3	:	:	PUNCT
cana-5401	86	4	this	this	PRON
cana-5401	86	5	is	be	AUX
cana-5401	86	6	a	a	DET
cana-5401	86	7	well	well	ADV
cana-5401	86	8	-	-	PUNCT
cana-5401	86	9	known	know	VERB
cana-5401	86	10	machine	machine	NOUN
cana-5401	86	11	learning	learning	NOUN
cana-5401	86	12	method	method	NOUN
cana-5401	86	13	that	that	PRON
cana-5401	86	14	works	work	VERB
cana-5401	86	15	well	well	ADV
cana-5401	86	16	even	even	ADV
cana-5401	86	17	with	with	ADP
cana-5401	86	18	simple	simple	ADJ
cana-5401	86	19	,	,	PUNCT
cana-5401	86	20	old	old	ADJ
cana-5401	86	21	,	,	PUNCT
cana-5401	86	22	or	or	CCONJ
cana-5401	86	23	noisy	noisy	ADJ
cana-5401	86	24	training	training	NOUN
cana-5401	86	25	data	datum	NOUN
cana-5401	86	26	.	.	PUNCT
cana-5401	87	1	however	however	ADV
cana-5401	87	2	,	,	PUNCT
cana-5401	87	3	there	there	PRON
cana-5401	87	4	is	be	VERB
cana-5401	87	5	a	a	DET
cana-5401	87	6	drawback	drawback	NOUN
cana-5401	87	7	as	as	ADV
cana-5401	87	8	well	well	ADV
cana-5401	87	9	.	.	PUNCT
cana-5401	88	1	for	for	ADP
cana-5401	88	2	example	example	NOUN
cana-5401	88	3	,	,	PUNCT
cana-5401	88	4	since	since	SCONJ
cana-5401	88	5	it	it	PRON
cana-5401	88	6	saves	save	VERB
cana-5401	88	7	all	all	DET
cana-5401	88	8	states	state	NOUN
cana-5401	88	9	while	while	SCONJ
cana-5401	88	10	computing	compute	VERB
cana-5401	88	11	distances	distance	NOUN
cana-5401	88	12	,	,	PUNCT
cana-5401	88	13	it	it	PRON
cana-5401	88	14	requires	require	VERB
cana-5401	88	15	a	a	DET
cana-5401	88	16	significant	significant	ADJ
cana-5401	88	17	quantity	quantity	NOUN
cana-5401	88	18	of	of	ADP
cana-5401	88	19	memory	memory	NOUN
cana-5401	88	20	space	space	NOUN
cana-5401	88	21	.	.	PUNCT
cana-5401	89	1	the	the	DET
cana-5401	89	2	knn	knn	PROPN
cana-5401	89	3	algorithm	algorithm	PROPN
cana-5401	89	4	's	's	PART
cana-5401	89	5	stages	stage	NOUN
cana-5401	89	6	are	be	AUX
cana-5401	89	7	as	as	SCONJ
cana-5401	89	8	follows	follow	VERB
cana-5401	89	9	[	[	X
cana-5401	89	10	1	1	NUM
cana-5401	89	11	]	]	X
cana-5401	89	12	:	:	PUNCT
cana-5401	90	1	1	1	X
cana-5401	90	2	.	.	PUNCT
cana-5401	90	3	the	the	DET
cana-5401	90	4	first	first	ADJ
cana-5401	90	5	step	step	NOUN
cana-5401	90	6	is	be	AUX
cana-5401	90	7	to	to	PART
cana-5401	90	8	identify	identify	VERB
cana-5401	90	9	the	the	DET
cana-5401	90	10	parameter	parameter	NOUN
cana-5401	90	11	k.	k.	PROPN
cana-5401	91	1	the	the	DET
cana-5401	91	2	number	number	NOUN
cana-5401	91	3	of	of	ADP
cana-5401	91	4	nearby	nearby	ADJ
cana-5401	91	5	neighbors	neighbor	NOUN
cana-5401	91	6	to	to	ADP
cana-5401	91	7	a	a	DET
cana-5401	91	8	particular	particular	ADJ
cana-5401	91	9	place	place	NOUN
cana-5401	91	10	is	be	AUX
cana-5401	91	11	represented	represent	VERB
cana-5401	91	12	by	by	ADP
cana-5401	91	13	this	this	DET
cana-5401	91	14	parameter	parameter	NOUN
cana-5401	91	15	.	.	PUNCT
cana-5401	92	1	for	for	ADP
cana-5401	92	2	example	example	NOUN
cana-5401	92	3	,	,	PUNCT
cana-5401	92	4	suppose	suppose	VERB
cana-5401	92	5	k=2	k=2	PROPN
cana-5401	92	6	.	.	PUNCT
cana-5401	93	1	in	in	ADP
cana-5401	93	2	this	this	DET
cana-5401	93	3	instance	instance	NOUN
cana-5401	93	4	,	,	PUNCT
cana-5401	93	5	the	the	DET
cana-5401	93	6	two	two	NUM
cana-5401	93	7	nearest	near	ADJ
cana-5401	93	8	neighbors	neighbor	NOUN
cana-5401	93	9	will	will	AUX
cana-5401	93	10	be	be	AUX
cana-5401	93	11	used	use	VERB
cana-5401	93	12	to	to	PART
cana-5401	93	13	determine	determine	VERB
cana-5401	93	14	classification	classification	NOUN
cana-5401	93	15	.	.	PUNCT
cana-5401	94	1	2	2	X
cana-5401	94	2	.	.	X
cana-5401	94	3	using	use	VERB
cana-5401	94	4	distance	distance	NOUN
cana-5401	94	5	functions	function	NOUN
cana-5401	94	6	,	,	PUNCT
cana-5401	94	7	new	new	ADJ
cana-5401	94	8	data	datum	NOUN
cana-5401	94	9	is	be	AUX
cana-5401	94	10	added	add	VERB
cana-5401	94	11	to	to	ADP
cana-5401	94	12	the	the	DET
cana-5401	94	13	sample	sample	NOUN
cana-5401	94	14	data	datum	NOUN
cana-5401	94	15	set	set	VERB
cana-5401	94	16	by	by	ADP
cana-5401	94	17	calculating	calculate	VERB
cana-5401	94	18	its	its	PRON
cana-5401	94	19	distance	distance	NOUN
cana-5401	94	20	from	from	ADP
cana-5401	94	21	existing	exist	VERB
cana-5401	94	22	data	datum	NOUN
cana-5401	94	23	.	.	PUNCT
cana-5401	95	1	3	3	X
cana-5401	95	2	.	.	X
cana-5401	95	3	the	the	DET
cana-5401	95	4	k	k	PROPN
cana-5401	95	5	closest	close	ADJ
cana-5401	95	6	neighbors	neighbor	NOUN
cana-5401	95	7	of	of	ADP
cana-5401	95	8	the	the	DET
cana-5401	95	9	associated	associated	ADJ
cana-5401	95	10	distances	distance	NOUN
cana-5401	95	11	are	be	AUX
cana-5401	95	12	evaluated	evaluate	VERB
cana-5401	95	13	.	.	PUNCT
cana-5401	96	1	based	base	VERB
cana-5401	96	2	on	on	ADP
cana-5401	96	3	the	the	DET
cana-5401	96	4	attribute	attribute	NOUN
cana-5401	96	5	values	value	NOUN
cana-5401	96	6	,	,	PUNCT
cana-5401	96	7	it	it	PRON
cana-5401	96	8	is	be	AUX
cana-5401	96	9	allocated	allocate	VERB
cana-5401	96	10	to	to	ADP
cana-5401	96	11	the	the	DET
cana-5401	96	12	class	class	NOUN
cana-5401	96	13	of	of	ADP
cana-5401	96	14	k	k	PROPN
cana-5401	96	15	neighbors	neighbor	NOUN
cana-5401	96	16	or	or	CCONJ
cana-5401	96	17	neighbors	neighbor	NOUN
cana-5401	96	18	.	.	PUNCT
cana-5401	97	1	4	4	X
cana-5401	97	2	.	.	X
cana-5401	97	3	the	the	DET
cana-5401	97	4	chosen	choose	VERB
cana-5401	97	5	class	class	NOUN
cana-5401	97	6	corresponds	correspond	VERB
cana-5401	97	7	to	to	ADP
cana-5401	97	8	the	the	DET
cana-5401	97	9	predicted	predict	VERB
cana-5401	97	10	observation	observation	NOUN
cana-5401	97	11	value	value	NOUN
cana-5401	97	12	for	for	ADP
cana-5401	97	13	estimation	estimation	NOUN
cana-5401	97	14	.	.	PUNCT
cana-5401	98	1	as	as	ADP
cana-5401	98	2	a	a	DET
cana-5401	98	3	result	result	NOUN
cana-5401	98	4	,	,	PUNCT
cana-5401	98	5	the	the	DET
cana-5401	98	6	new	new	ADJ
cana-5401	98	7	information	information	NOUN
cana-5401	98	8	has	have	VERB
cana-5401	98	9	labels	label	NOUN
cana-5401	98	10	.	.	PUNCT
cana-5401	99	1	•	•	X
cana-5401	99	2	rf	rf	NOUN
cana-5401	99	3	:	:	PUNCT
cana-5401	99	4	the	the	DET
cana-5401	99	5	random	random	ADJ
cana-5401	99	6	forest	forest	NOUN
cana-5401	99	7	method	method	NOUN
cana-5401	99	8	is	be	AUX
cana-5401	99	9	a	a	DET
cana-5401	99	10	supervised	supervised	ADJ
cana-5401	99	11	classification	classification	NOUN
cana-5401	99	12	system	system	NOUN
cana-5401	99	13	.	.	PUNCT
cana-5401	100	1	it	it	PRON
cana-5401	100	2	is	be	AUX
cana-5401	100	3	applicable	applicable	ADJ
cana-5401	100	4	to	to	ADP
cana-5401	100	5	both	both	CCONJ
cana-5401	100	6	classification	classification	NOUN
cana-5401	100	7	and	and	CCONJ
cana-5401	100	8	regression	regression	NOUN
cana-5401	100	9	issues	issue	NOUN
cana-5401	100	10	[	[	X
cana-5401	100	11	1	1	NUM
cana-5401	100	12	]	]	PUNCT
cana-5401	100	13	.	.	PUNCT
cana-5401	101	1	the	the	DET
cana-5401	101	2	algorithm	algorithm	NOUN
cana-5401	101	3	's	's	PART
cana-5401	101	4	goal	goal	NOUN
cana-5401	101	5	is	be	AUX
cana-5401	101	6	to	to	PART
cana-5401	101	7	enhance	enhance	VERB
cana-5401	101	8	classification	classification	NOUN
cana-5401	101	9	value	value	NOUN
cana-5401	101	10	by	by	ADP
cana-5401	101	11	creating	create	VERB
cana-5401	101	12	several	several	ADJ
cana-5401	101	13	decision	decision	NOUN
cana-5401	101	14	trees	tree	NOUN
cana-5401	101	15	throughout	throughout	ADP
cana-5401	101	16	the	the	DET
cana-5401	101	17	classification	classification	NOUN
cana-5401	101	18	phase	phase	NOUN
cana-5401	101	19	.	.	PUNCT
cana-5401	102	1	the	the	DET
cana-5401	102	2	random	random	ADJ
cana-5401	102	3	forest	forest	NOUN
cana-5401	102	4	method	method	NOUN
cana-5401	102	5	selects	select	VERB
cana-5401	102	6	the	the	DET
cana-5401	102	7	highest	high	ADJ
cana-5401	102	8	score	score	NOUN
cana-5401	102	9	from	from	ADP
cana-5401	102	10	a	a	DET
cana-5401	102	11	group	group	NOUN
cana-5401	102	12	of	of	ADP
cana-5401	102	13	independent	independent	ADJ
cana-5401	102	14	decision	decision	NOUN
cana-5401	102	15	trees	tree	NOUN
cana-5401	102	16	.	.	PUNCT
cana-5401	103	1	our	our	PRON
cana-5401	103	2	ability	ability	NOUN
cana-5401	103	3	to	to	PART
cana-5401	103	4	generate	generate	VERB
cana-5401	103	5	exact	exact	ADJ
cana-5401	103	6	results	result	NOUN
cana-5401	103	7	grows	grow	VERB
cana-5401	103	8	communications	communication	NOUN
cana-5401	103	9	on	on	ADP
cana-5401	103	10	applied	apply	VERB
cana-5401	103	11	nonlinear	nonlinear	ADJ
cana-5401	103	12	analysis	analysis	NOUN
cana-5401	103	13	issn	issn	NOUN
cana-5401	103	14	:	:	PUNCT
cana-5401	103	15	1074	1074	NUM
cana-5401	103	16	-	-	PUNCT
cana-5401	103	17	133x	133x	NUM
cana-5401	103	18	vol	vol	NOUN
cana-5401	103	19	32	32	NUM
cana-5401	103	20	no	no	NOUN
cana-5401	103	21	.	.	PUNCT
cana-5401	104	1	icmasd	icmasd	NOUN
cana-5401	104	2	(	(	PUNCT
cana-5401	104	3	2025	2025	NUM
cana-5401	104	4	)	)	PUNCT
cana-5401	104	5	1858	1858	NUM
cana-5401	104	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-5401	104	7	as	as	ADP
cana-5401	104	8	the	the	DET
cana-5401	104	9	number	number	NOUN
cana-5401	104	10	of	of	ADP
cana-5401	104	11	trees	tree	NOUN
cana-5401	104	12	increases	increase	NOUN
cana-5401	104	13	.	.	PUNCT
cana-5401	105	1	the	the	DET
cana-5401	105	2	primary	primary	ADJ
cana-5401	105	3	distinction	distinction	NOUN
cana-5401	105	4	between	between	ADP
cana-5401	105	5	the	the	DET
cana-5401	105	6	random	random	ADJ
cana-5401	105	7	forest	forest	NOUN
cana-5401	105	8	algorithm	algorithm	NOUN
cana-5401	105	9	and	and	CCONJ
cana-5401	105	10	the	the	DET
cana-5401	105	11	decision	decision	NOUN
cana-5401	105	12	tree	tree	NOUN
cana-5401	105	13	method	method	NOUN
cana-5401	105	14	is	be	AUX
cana-5401	105	15	that	that	SCONJ
cana-5401	105	16	the	the	DET
cana-5401	105	17	process	process	NOUN
cana-5401	105	18	of	of	ADP
cana-5401	105	19	locating	locate	VERB
cana-5401	105	20	the	the	DET
cana-5401	105	21	root	root	NOUN
cana-5401	105	22	node	node	NOUN
cana-5401	105	23	and	and	CCONJ
cana-5401	105	24	dividing	divide	VERB
cana-5401	105	25	the	the	DET
cana-5401	105	26	nodes	node	NOUN
cana-5401	105	27	is	be	AUX
cana-5401	105	28	random	random	ADJ
cana-5401	105	29	.	.	PUNCT
cana-5401	106	1	•	•	NUM
cana-5401	106	2	nn	nn	NOUN
cana-5401	106	3	:	:	PUNCT
cana-5401	106	4	for	for	ADP
cana-5401	106	5	classification	classification	NOUN
cana-5401	106	6	and	and	CCONJ
cana-5401	106	7	prediction	prediction	NOUN
cana-5401	106	8	purposes	purpose	NOUN
cana-5401	106	9	,	,	PUNCT
cana-5401	106	10	neural	neural	ADJ
cana-5401	106	11	networks	network	NOUN
cana-5401	106	12	(	(	PUNCT
cana-5401	106	13	nns	nn	NOUN
cana-5401	106	14	)	)	PUNCT
cana-5401	106	15	are	be	AUX
cana-5401	106	16	an	an	DET
cana-5401	106	17	excellent	excellent	ADJ
cana-5401	106	18	machine	machine	NOUN
cana-5401	106	19	learning	learn	VERB
cana-5401	106	20	approach	approach	NOUN
cana-5401	106	21	[	[	X
cana-5401	106	22	1	1	NUM
cana-5401	106	23	]	]	PUNCT
cana-5401	106	24	.	.	PUNCT
cana-5401	107	1	because	because	SCONJ
cana-5401	107	2	neural	neural	ADJ
cana-5401	107	3	networks	network	NOUN
cana-5401	107	4	learn	learn	VERB
cana-5401	107	5	,	,	PUNCT
cana-5401	107	6	they	they	PRON
cana-5401	107	7	can	can	AUX
cana-5401	107	8	solve	solve	VERB
cana-5401	107	9	arbitrarily	arbitrarily	ADV
cana-5401	107	10	complicated	complicate	VERB
cana-5401	107	11	problems	problem	NOUN
cana-5401	107	12	.	.	PUNCT
cana-5401	108	1	nns	nns	PROPN
cana-5401	108	2	may	may	AUX
cana-5401	108	3	learn	learn	VERB
cana-5401	108	4	via	via	ADP
cana-5401	108	5	two	two	NUM
cana-5401	108	6	different	different	ADJ
cana-5401	108	7	mechanisms	mechanism	NOUN
cana-5401	108	8	:	:	PUNCT
cana-5401	108	9	unsupervised	unsupervised	ADJ
cana-5401	108	10	learning	learning	NOUN
cana-5401	108	11	,	,	PUNCT
cana-5401	108	12	which	which	PRON
cana-5401	108	13	extracts	extract	VERB
cana-5401	108	14	patterns	pattern	NOUN
cana-5401	108	15	directly	directly	ADV
cana-5401	108	16	from	from	ADP
cana-5401	108	17	the	the	DET
cana-5401	108	18	data	datum	NOUN
cana-5401	108	19	,	,	PUNCT
cana-5401	108	20	and	and	CCONJ
cana-5401	108	21	supervised	supervised	ADJ
cana-5401	108	22	learning	learning	NOUN
cana-5401	108	23	,	,	PUNCT
cana-5401	108	24	which	which	PRON
cana-5401	108	25	needs	need	VERB
cana-5401	108	26	historical	historical	ADJ
cana-5401	108	27	data	datum	NOUN
cana-5401	108	28	with	with	ADP
cana-5401	108	29	known	known	ADJ
cana-5401	108	30	outcomes	outcome	NOUN
cana-5401	108	31	.	.	PUNCT
cana-5401	109	1	the	the	DET
cana-5401	109	2	nn	nn	PROPN
cana-5401	109	3	needs	need	VERB
cana-5401	109	4	to	to	PART
cana-5401	109	5	be	be	AUX
cana-5401	109	6	taught	teach	VERB
cana-5401	109	7	to	to	PART
cana-5401	109	8	learn	learn	VERB
cana-5401	109	9	,	,	PUNCT
cana-5401	109	10	and	and	CCONJ
cana-5401	109	11	there	there	PRON
cana-5401	109	12	are	be	VERB
cana-5401	109	13	different	different	ADJ
cana-5401	109	14	training	training	NOUN
cana-5401	109	15	methods	method	NOUN
cana-5401	109	16	for	for	ADP
cana-5401	109	17	each	each	DET
cana-5401	109	18	type	type	NOUN
cana-5401	109	19	of	of	ADP
cana-5401	109	20	nn	nn	NOUN
cana-5401	109	21	learning	learning	NOUN
cana-5401	109	22	.	.	PUNCT
cana-5401	110	1	for	for	ADP
cana-5401	110	2	controlled	control	VERB
cana-5401	110	3	learning	learning	NOUN
cana-5401	110	4	,	,	PUNCT
cana-5401	110	5	backpropagation	backpropagation	NOUN
cana-5401	110	6	is	be	AUX
cana-5401	110	7	the	the	DET
cana-5401	110	8	most	most	ADV
cana-5401	110	9	common	common	ADJ
cana-5401	110	10	,	,	PUNCT
cana-5401	110	11	and	and	CCONJ
cana-5401	110	12	for	for	ADP
cana-5401	110	13	unsupervised	unsupervised	ADJ
cana-5401	110	14	learning	learning	NOUN
cana-5401	110	15	,	,	PUNCT
cana-5401	110	16	self	self	NOUN
cana-5401	110	17	-	-	PUNCT
cana-5401	110	18	organizing	organize	VERB
cana-5401	110	19	maps	map	NOUN
cana-5401	110	20	(	(	PUNCT
cana-5401	110	21	som	som	NOUN
cana-5401	110	22	)	)	PUNCT
cana-5401	110	23	are	be	AUX
cana-5401	110	24	the	the	DET
cana-5401	110	25	most	most	ADV
cana-5401	110	26	common	common	ADJ
cana-5401	110	27	.	.	PUNCT
cana-5401	111	1	every	every	DET
cana-5401	111	2	nn	nn	PROPN
cana-5401	111	3	has	have	VERB
cana-5401	111	4	two	two	NUM
cana-5401	111	5	layers	layer	NOUN
cana-5401	111	6	:	:	PUNCT
cana-5401	111	7	an	an	DET
cana-5401	111	8	output	output	NOUN
cana-5401	111	9	layer	layer	NOUN
cana-5401	111	10	that	that	PRON
cana-5401	111	11	specifies	specify	VERB
cana-5401	111	12	the	the	DET
cana-5401	111	13	intended	intend	VERB
cana-5401	111	14	classification	classification	NOUN
cana-5401	111	15	or	or	CCONJ
cana-5401	111	16	prediction	prediction	NOUN
cana-5401	111	17	result	result	NOUN
cana-5401	111	18	,	,	PUNCT
cana-5401	111	19	and	and	CCONJ
cana-5401	111	20	an	an	DET
cana-5401	111	21	input	input	NOUN
cana-5401	111	22	layer	layer	NOUN
cana-5401	111	23	that	that	PRON
cana-5401	111	24	specifies	specify	VERB
cana-5401	111	25	the	the	DET
cana-5401	111	26	variables	variable	NOUN
cana-5401	111	27	supplied	supply	VERB
cana-5401	111	28	to	to	ADP
cana-5401	111	29	the	the	DET
cana-5401	111	30	nn	nn	PROPN
cana-5401	111	31	for	for	ADP
cana-5401	111	32	learning	learn	VERB
cana-5401	111	33	.	.	PUNCT
cana-5401	112	1	one	one	NUM
cana-5401	112	2	or	or	CCONJ
cana-5401	112	3	more	more	ADV
cana-5401	112	4	hidden	hidden	ADJ
cana-5401	112	5	layers	layer	NOUN
cana-5401	112	6	are	be	AUX
cana-5401	112	7	included	include	VERB
cana-5401	112	8	in	in	ADP
cana-5401	112	9	both	both	PRON
cana-5401	112	10	supervised	supervised	ADJ
cana-5401	112	11	learning	learning	NOUN
cana-5401	112	12	and	and	CCONJ
cana-5401	112	13	hybrid	hybrid	NOUN
cana-5401	112	14	models	model	NOUN
cana-5401	112	15	,	,	PUNCT
cana-5401	112	16	and	and	CCONJ
cana-5401	112	17	each	each	DET
cana-5401	112	18	layer	layer	NOUN
cana-5401	112	19	has	have	VERB
cana-5401	112	20	a	a	DET
cana-5401	112	21	weighted	weighted	ADJ
cana-5401	112	22	link	link	NOUN
cana-5401	112	23	that	that	PRON
cana-5401	112	24	connects	connect	VERB
cana-5401	112	25	it	it	PRON
cana-5401	112	26	entirely	entirely	ADV
cana-5401	112	27	to	to	ADP
cana-5401	112	28	the	the	DET
cana-5401	112	29	previous	previous	ADJ
cana-5401	112	30	layer	layer	NOUN
cana-5401	112	31	.	.	PUNCT
cana-5401	113	1	this	this	DET
cana-5401	113	2	form	form	NOUN
cana-5401	113	3	of	of	ADP
cana-5401	113	4	neural	neural	ADJ
cana-5401	113	5	network	network	NOUN
cana-5401	113	6	learns	learn	VERB
cana-5401	113	7	by	by	ADP
cana-5401	113	8	detecting	detect	VERB
cana-5401	113	9	the	the	DET
cana-5401	113	10	error	error	NOUN
cana-5401	113	11	of	of	ADP
cana-5401	113	12	a	a	DET
cana-5401	113	13	training	training	NOUN
cana-5401	113	14	forecast	forecast	NOUN
cana-5401	113	15	from	from	ADP
cana-5401	113	16	the	the	DET
cana-5401	113	17	actual	actual	ADJ
cana-5401	113	18	value	value	NOUN
cana-5401	113	19	.	.	PUNCT
cana-5401	114	1	and	and	CCONJ
cana-5401	114	2	then	then	ADV
cana-5401	114	3	sending	send	VERB
cana-5401	114	4	out	out	ADP
cana-5401	114	5	this	this	DET
cana-5401	114	6	error	error	NOUN
cana-5401	114	7	backward	backward	ADV
cana-5401	114	8	across	across	ADP
cana-5401	114	9	the	the	DET
cana-5401	114	10	network	network	NOUN
cana-5401	114	11	to	to	PART
cana-5401	114	12	alter	alter	VERB
cana-5401	114	13	the	the	DET
cana-5401	114	14	weights	weight	NOUN
cana-5401	114	15	of	of	ADP
cana-5401	114	16	the	the	DET
cana-5401	114	17	links	link	NOUN
cana-5401	114	18	to	to	PART
cana-5401	114	19	better	well	ADV
cana-5401	114	20	align	align	VERB
cana-5401	114	21	the	the	DET
cana-5401	114	22	forecast	forecast	NOUN
cana-5401	114	23	with	with	ADP
cana-5401	114	24	the	the	DET
cana-5401	114	25	true	true	ADJ
cana-5401	114	26	output	output	NOUN
cana-5401	114	27	value	value	NOUN
cana-5401	114	28	.	.	PUNCT
cana-5401	115	1	3.3	3.3	NUM
cana-5401	115	2	performance	performance	NOUN
cana-5401	115	3	metrics	metric	NOUN
cana-5401	115	4	:	:	PUNCT
cana-5401	115	5	next	next	ADJ
cana-5401	115	6	,	,	PUNCT
cana-5401	115	7	table	table	NOUN
cana-5401	115	8	2	2	NUM
cana-5401	115	9	gives	give	VERB
cana-5401	115	10	a	a	DET
cana-5401	115	11	detailed	detailed	ADJ
cana-5401	115	12	description	description	NOUN
cana-5401	115	13	of	of	ADP
cana-5401	115	14	the	the	DET
cana-5401	115	15	performance	performance	NOUN
cana-5401	115	16	metrics	metric	NOUN
cana-5401	115	17	are	be	AUX
cana-5401	115	18	evaluated	evaluate	VERB
cana-5401	115	19	for	for	ADP
cana-5401	115	20	the	the	DET
cana-5401	115	21	proposed	propose	VERB
cana-5401	115	22	model	model	NOUN
cana-5401	115	23	.	.	PUNCT
cana-5401	116	1	table	table	NOUN
cana-5401	116	2	2	2	NUM
cana-5401	116	3	performance	performance	NOUN
cana-5401	116	4	metrics	metric	NOUN
cana-5401	116	5	4	4	NUM
cana-5401	116	6	.	.	PUNCT
cana-5401	116	7	proposed	propose	VERB
cana-5401	116	8	crime	crime	NOUN
cana-5401	116	9	prediction	prediction	NOUN
cana-5401	116	10	model	model	NOUN
cana-5401	116	11	in	in	ADP
cana-5401	116	12	this	this	DET
cana-5401	116	13	research	research	NOUN
cana-5401	116	14	,	,	PUNCT
cana-5401	116	15	crime	crime	NOUN
cana-5401	116	16	prediction	prediction	NOUN
cana-5401	116	17	model	model	NOUN
cana-5401	116	18	is	be	AUX
cana-5401	116	19	designed	design	VERB
cana-5401	116	20	using	use	VERB
cana-5401	116	21	the	the	DET
cana-5401	116	22	various	various	ADJ
cana-5401	116	23	machine	machine	NOUN
cana-5401	116	24	learning	learn	VERB
cana-5401	116	25	algorithms	algorithm	NOUN
cana-5401	116	26	to	to	PART
cana-5401	116	27	find	find	VERB
cana-5401	116	28	out	out	ADP
cana-5401	116	29	which	which	DET
cana-5401	116	30	algorithm	algorithm	NOUN
cana-5401	116	31	outperforms	outperform	VERB
cana-5401	116	32	over	over	ADP
cana-5401	116	33	others	other	NOUN
cana-5401	116	34	.	.	PUNCT
cana-5401	117	1	the	the	DET
cana-5401	117	2	flowchart	flowchart	NOUN
cana-5401	117	3	of	of	ADP
cana-5401	117	4	the	the	DET
cana-5401	117	5	proposed	propose	VERB
cana-5401	117	6	crime	crime	NOUN
cana-5401	117	7	prediction	prediction	NOUN
cana-5401	117	8	model	model	NOUN
cana-5401	117	9	is	be	AUX
cana-5401	117	10	shown	show	VERB
cana-5401	117	11	in	in	ADP
cana-5401	117	12	figure	figure	NOUN
cana-5401	117	13	1	1	NUM
cana-5401	117	14	.	.	PUNCT
cana-5401	117	15	communications	communication	NOUN
cana-5401	117	16	on	on	ADP
cana-5401	117	17	applied	apply	VERB
cana-5401	117	18	nonlinear	nonlinear	ADJ
cana-5401	117	19	analysis	analysis	NOUN
cana-5401	117	20	issn	issn	NOUN
cana-5401	117	21	:	:	PUNCT
cana-5401	117	22	1074	1074	NUM
cana-5401	117	23	-	-	PUNCT
cana-5401	117	24	133x	133x	NUM
cana-5401	117	25	vol	vol	NOUN
cana-5401	117	26	32	32	NUM
cana-5401	117	27	no	no	NOUN
cana-5401	117	28	.	.	PUNCT
cana-5401	118	1	icmasd	icmasd	NOUN
cana-5401	118	2	(	(	PUNCT
cana-5401	118	3	2025	2025	NUM
cana-5401	118	4	)	)	PUNCT
cana-5401	118	5	1859	1859	NUM
cana-5401	119	1	https://internationalpubls.com	https://internationalpubls.com	X
cana-5401	119	2	figure	figure	NOUN
cana-5401	119	3	1	1	NUM
cana-5401	119	4	flowchart	flowchart	NOUN
cana-5401	119	5	of	of	ADP
cana-5401	119	6	the	the	DET
cana-5401	119	7	proposed	propose	VERB
cana-5401	119	8	crime	crime	NOUN
cana-5401	119	9	prediction	prediction	NOUN
cana-5401	119	10	model	model	NOUN
cana-5401	119	11	initially	initially	ADV
cana-5401	119	12	,	,	PUNCT
cana-5401	119	13	in	in	ADP
cana-5401	119	14	the	the	DET
cana-5401	119	15	proposed	propose	VERB
cana-5401	119	16	model	model	NOUN
cana-5401	119	17	,	,	PUNCT
cana-5401	119	18	the	the	DET
cana-5401	119	19	standard	standard	ADJ
cana-5401	119	20	dataset	dataset	NOUN
cana-5401	119	21	is	be	AUX
cana-5401	119	22	read	read	VERB
cana-5401	119	23	and	and	CCONJ
cana-5401	119	24	pre	pre	ADJ
cana-5401	119	25	-	-	ADJ
cana-5401	119	26	processing	processing	NOUN
cana-5401	119	27	is	be	AUX
cana-5401	119	28	done	do	VERB
cana-5401	119	29	to	to	PART
cana-5401	119	30	fill	fill	VERB
cana-5401	119	31	the	the	DET
cana-5401	119	32	missing	missing	ADJ
cana-5401	119	33	and	and	CCONJ
cana-5401	119	34	undefined	undefined	ADJ
cana-5401	119	35	values	value	NOUN
cana-5401	119	36	of	of	ADP
cana-5401	119	37	the	the	DET
cana-5401	119	38	attributes	attribute	NOUN
cana-5401	119	39	are	be	AUX
cana-5401	119	40	presented	present	VERB
cana-5401	119	41	in	in	ADP
cana-5401	119	42	the	the	DET
cana-5401	119	43	dataset	dataset	NOUN
cana-5401	119	44	.	.	PUNCT
cana-5401	120	1	further	far	ADV
cana-5401	120	2	,	,	PUNCT
cana-5401	120	3	feature	feature	NOUN
cana-5401	120	4	selection	selection	NOUN
cana-5401	120	5	is	be	AUX
cana-5401	120	6	performed	perform	VERB
cana-5401	120	7	to	to	PART
cana-5401	120	8	select	select	VERB
cana-5401	120	9	the	the	DET
cana-5401	120	10	most	most	ADV
cana-5401	120	11	appropriate	appropriate	ADJ
cana-5401	120	12	data	datum	NOUN
cana-5401	120	13	by	by	ADP
cana-5401	120	14	decreasing	decrease	VERB
cana-5401	120	15	the	the	DET
cana-5401	120	16	inputs	input	NOUN
cana-5401	120	17	for	for	ADP
cana-5401	120	18	analysis	analysis	NOUN
cana-5401	120	19	and	and	CCONJ
cana-5401	120	20	processing	processing	NOUN
cana-5401	120	21	purposes	purpose	NOUN
cana-5401	120	22	.	.	PUNCT
cana-5401	121	1	in	in	ADP
cana-5401	121	2	other	other	ADJ
cana-5401	121	3	terms	term	NOUN
cana-5401	121	4	,	,	PUNCT
cana-5401	121	5	it	it	PRON
cana-5401	121	6	is	be	AUX
cana-5401	121	7	referred	refer	VERB
cana-5401	121	8	as	as	ADP
cana-5401	121	9	the	the	DET
cana-5401	121	10	procedure	procedure	NOUN
cana-5401	121	11	to	to	PART
cana-5401	121	12	select	select	VERB
cana-5401	121	13	the	the	DET
cana-5401	121	14	attributes	attribute	NOUN
cana-5401	121	15	,	,	PUNCT
cana-5401	121	16	subset	subset	NOUN
cana-5401	121	17	of	of	ADP
cana-5401	121	18	the	the	DET
cana-5401	121	19	dataset	dataset	NOUN
cana-5401	121	20	to	to	PART
cana-5401	121	21	construct	construct	VERB
cana-5401	121	22	the	the	DET
cana-5401	121	23	model	model	NOUN
cana-5401	121	24	.	.	PUNCT
cana-5401	122	1	in	in	ADP
cana-5401	122	2	this	this	DET
cana-5401	122	3	research	research	NOUN
cana-5401	122	4	,	,	PUNCT
cana-5401	122	5	correlation	correlation	NOUN
cana-5401	122	6	matrix	matrix	NOUN
cana-5401	122	7	is	be	AUX
cana-5401	122	8	used	use	VERB
cana-5401	122	9	for	for	ADP
cana-5401	122	10	feature	feature	NOUN
cana-5401	122	11	selection	selection	NOUN
cana-5401	122	12	.	.	PUNCT
cana-5401	123	1	next	next	ADV
cana-5401	123	2	,	,	PUNCT
cana-5401	123	3	the	the	DET
cana-5401	123	4	dataset	dataset	NOUN
cana-5401	123	5	is	be	AUX
cana-5401	123	6	split	split	VERB
cana-5401	123	7	into	into	ADP
cana-5401	123	8	70:30	70:30	NUM
cana-5401	123	9	ratio	ratio	NOUN
cana-5401	123	10	.	.	PUNCT
cana-5401	124	1	the	the	DET
cana-5401	124	2	70	70	NUM
cana-5401	124	3	%	%	NOUN
cana-5401	124	4	dataset	dataset	NOUN
cana-5401	124	5	is	be	AUX
cana-5401	124	6	used	use	VERB
cana-5401	124	7	for	for	ADP
cana-5401	124	8	train	train	VERB
cana-5401	124	9	the	the	DET
cana-5401	124	10	model	model	NOUN
cana-5401	124	11	whereas	whereas	SCONJ
cana-5401	124	12	30	30	NUM
cana-5401	124	13	%	%	NOUN
cana-5401	124	14	dataset	dataset	NOUN
cana-5401	124	15	is	be	AUX
cana-5401	124	16	used	use	VERB
cana-5401	124	17	for	for	ADP
cana-5401	124	18	validate	validate	VERB
cana-5401	124	19	the	the	DET
cana-5401	124	20	model	model	NOUN
cana-5401	124	21	.	.	PUNCT
cana-5401	125	1	moreover	moreover	ADV
cana-5401	125	2	,	,	PUNCT
cana-5401	125	3	the	the	DET
cana-5401	125	4	machine	machine	NOUN
cana-5401	125	5	learning	learn	VERB
cana-5401	125	6	model	model	NOUN
cana-5401	125	7	predict	predict	VERB
cana-5401	125	8	the	the	DET
cana-5401	125	9	crime	crime	NOUN
cana-5401	125	10	based	base	VERB
cana-5401	125	11	on	on	ADP
cana-5401	125	12	the	the	DET
cana-5401	125	13	various	various	ADJ
cana-5401	125	14	attributes	attribute	NOUN
cana-5401	125	15	are	be	AUX
cana-5401	125	16	chosen	choose	VERB
cana-5401	125	17	in	in	ADP
cana-5401	125	18	the	the	DET
cana-5401	125	19	feature	feature	NOUN
cana-5401	125	20	selection	selection	NOUN
cana-5401	125	21	.	.	PUNCT
cana-5401	126	1	finally	finally	ADV
cana-5401	126	2	,	,	PUNCT
cana-5401	126	3	the	the	DET
cana-5401	126	4	performance	performance	NOUN
cana-5401	126	5	metrics	metric	NOUN
cana-5401	126	6	are	be	AUX
cana-5401	126	7	evaluated	evaluate	VERB
cana-5401	126	8	for	for	ADP
cana-5401	126	9	evaluation	evaluation	NOUN
cana-5401	126	10	purposes	purpose	NOUN
cana-5401	126	11	.	.	PUNCT
cana-5401	127	1	5	5	X
cana-5401	127	2	.	.	X
cana-5401	127	3	simulation	simulation	NOUN
cana-5401	127	4	results	result	VERB
cana-5401	127	5	in	in	ADP
cana-5401	127	6	this	this	DET
cana-5401	127	7	section	section	NOUN
cana-5401	127	8	,	,	PUNCT
cana-5401	127	9	the	the	DET
cana-5401	127	10	simulation	simulation	NOUN
cana-5401	127	11	evaluation	evaluation	NOUN
cana-5401	127	12	of	of	ADP
cana-5401	127	13	various	various	ADJ
cana-5401	127	14	machine	machine	NOUN
cana-5401	127	15	learning	learn	VERB
cana-5401	127	16	algorithms	algorithm	NOUN
cana-5401	127	17	for	for	ADP
cana-5401	127	18	crime	crime	NOUN
cana-5401	127	19	prediction	prediction	NOUN
cana-5401	127	20	is	be	AUX
cana-5401	127	21	shown	show	VERB
cana-5401	127	22	.	.	PUNCT
cana-5401	128	1	the	the	DET
cana-5401	128	2	crime	crime	NOUN
cana-5401	128	3	prediction	prediction	NOUN
cana-5401	128	4	model	model	NOUN
cana-5401	128	5	is	be	AUX
cana-5401	128	6	designed	design	VERB
cana-5401	128	7	and	and	CCONJ
cana-5401	128	8	simulated	simulate	VERB
cana-5401	128	9	in	in	ADP
cana-5401	128	10	the	the	DET
cana-5401	128	11	google	google	PROPN
cana-5401	128	12	colab	colab	PROPN
cana-5401	128	13	software	software	PROPN
cana-5401	128	14	.	.	PUNCT
cana-5401	129	1	further	far	ADV
cana-5401	129	2	,	,	PUNCT
cana-5401	129	3	table	table	NOUN
cana-5401	129	4	2	2	NUM
cana-5401	129	5	shows	show	VERB
cana-5401	129	6	the	the	DET
cana-5401	129	7	simulation	simulation	NOUN
cana-5401	129	8	setup	setup	NOUN
cana-5401	129	9	configuration	configuration	NOUN
cana-5401	129	10	is	be	AUX
cana-5401	129	11	defined	define	VERB
cana-5401	129	12	for	for	ADP
cana-5401	129	13	machine	machine	NOUN
cana-5401	129	14	learning	learn	VERB
cana-5401	129	15	algorithms	algorithm	NOUN
cana-5401	129	16	during	during	ADP
cana-5401	129	17	simulations	simulation	NOUN
cana-5401	129	18	.	.	PUNCT
cana-5401	130	1	table	table	NOUN
cana-5401	130	2	2	2	NUM
cana-5401	130	3	simulation	simulation	NOUN
cana-5401	130	4	setup	setup	NOUN
cana-5401	130	5	configuration	configuration	NOUN
cana-5401	130	6	for	for	ADP
cana-5401	130	7	the	the	DET
cana-5401	130	8	machine	machine	NOUN
cana-5401	130	9	learning	learn	VERB
cana-5401	130	10	algorithms	algorithm	NOUN
cana-5401	130	11	algorithms	algorithm	NOUN
cana-5401	130	12	parameter	parameter	PROPN
cana-5401	130	13	value	value	PROPN
cana-5401	130	14	nb	nb	PROPN
cana-5401	130	15	alpha:0.1	alpha:0.1	PROPN
cana-5401	130	16	knn	knn	PROPN
cana-5401	130	17	n	n	PROPN
cana-5401	130	18	-	-	PUNCT
cana-5401	130	19	neighbour:5	neighbour:5	NOUN
cana-5401	130	20	weight	weight	NOUN
cana-5401	130	21	:	:	PUNCT
cana-5401	130	22	distance	distance	NOUN
cana-5401	130	23	rf	rf	ADJ
cana-5401	130	24	n	n	CCONJ
cana-5401	130	25	-	-	PUNCT
cana-5401	130	26	estimator:50	estimator:50	NOUN
cana-5401	130	27	communications	communication	NOUN
cana-5401	130	28	on	on	ADP
cana-5401	130	29	applied	apply	VERB
cana-5401	130	30	nonlinear	nonlinear	ADJ
cana-5401	130	31	analysis	analysis	NOUN
cana-5401	130	32	issn	issn	NOUN
cana-5401	130	33	:	:	PUNCT
cana-5401	130	34	1074	1074	NUM
cana-5401	130	35	-	-	PUNCT
cana-5401	130	36	133x	133x	NUM
cana-5401	130	37	vol	vol	NOUN
cana-5401	130	38	32	32	NUM
cana-5401	130	39	no	no	NOUN
cana-5401	130	40	.	.	PUNCT
cana-5401	131	1	icmasd	icmasd	NOUN
cana-5401	131	2	(	(	PUNCT
cana-5401	131	3	2025	2025	NUM
cana-5401	131	4	)	)	PUNCT
cana-5401	131	5	1860	1860	NUM
cana-5401	131	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-5401	131	7	max	max	PROPN
cana-5401	131	8	depth:15	depth:15	PROPN
cana-5401	131	9	min	min	PROPN
cana-5401	131	10	sample	sample	NOUN
cana-5401	131	11	leaf:1	leaf:1	VERB
cana-5401	131	12	nn	nn	NUM
cana-5401	131	13	hidden	hide	VERB
cana-5401	131	14	layer	layer	NOUN
cana-5401	131	15	size	size	NOUN
cana-5401	131	16	:	:	PUNCT
cana-5401	131	17	50	50	NUM
cana-5401	131	18	alpha	alpha	NOUN
cana-5401	131	19	:	:	PUNCT
cana-5401	131	20	0.1	0.1	NUM
cana-5401	131	21	maximum	maximum	ADJ
cana-5401	131	22	iteration	iteration	NOUN
cana-5401	131	23	:	:	PUNCT
cana-5401	131	24	1000	1000	NUM
cana-5401	131	25	finally	finally	ADV
cana-5401	131	26	,	,	PUNCT
cana-5401	131	27	table	table	NOUN
cana-5401	131	28	3	3	NUM
cana-5401	131	29	shows	show	VERB
cana-5401	131	30	the	the	DET
cana-5401	131	31	various	various	ADJ
cana-5401	131	32	performance	performance	NOUN
cana-5401	131	33	metrics	metric	NOUN
cana-5401	131	34	are	be	AUX
cana-5401	131	35	determined	determine	VERB
cana-5401	131	36	for	for	ADP
cana-5401	131	37	the	the	DET
cana-5401	131	38	various	various	ADJ
cana-5401	131	39	machine	machine	NOUN
cana-5401	131	40	learning	learn	VERB
cana-5401	131	41	algorithms	algorithm	NOUN
cana-5401	131	42	.	.	PUNCT
cana-5401	132	1	the	the	DET
cana-5401	132	2	results	result	NOUN
cana-5401	132	3	show	show	VERB
cana-5401	132	4	that	that	SCONJ
cana-5401	132	5	the	the	DET
cana-5401	132	6	neural	neural	ADJ
cana-5401	132	7	network	network	NOUN
cana-5401	132	8	algorithm	algorithm	NOUN
cana-5401	132	9	achieves	achieve	VERB
cana-5401	132	10	the	the	DET
cana-5401	132	11	highest	high	ADJ
cana-5401	132	12	accuracy	accuracy	NOUN
cana-5401	132	13	,	,	PUNCT
cana-5401	132	14	precision	precision	NOUN
cana-5401	132	15	,	,	PUNCT
cana-5401	132	16	recall	recall	NOUN
cana-5401	132	17	,	,	PUNCT
cana-5401	132	18	and	and	CCONJ
cana-5401	132	19	f1	f1	NOUN
cana-5401	132	20	-	-	PUNCT
cana-5401	132	21	score	score	NOUN
cana-5401	132	22	over	over	ADP
cana-5401	132	23	the	the	DET
cana-5401	132	24	nb	nb	PROPN
cana-5401	132	25	,	,	PUNCT
cana-5401	132	26	knn	knn	PROPN
cana-5401	132	27	,	,	PUNCT
cana-5401	132	28	and	and	CCONJ
cana-5401	132	29	rf	rf	NOUN
cana-5401	132	30	algorithm	algorithm	NOUN
cana-5401	132	31	.	.	PUNCT
cana-5401	133	1	table	table	NOUN
cana-5401	133	2	3	3	NUM
cana-5401	133	3	performance	performance	NOUN
cana-5401	133	4	metrics	metric	NOUN
cana-5401	133	5	for	for	ADP
cana-5401	133	6	different	different	ADJ
cana-5401	133	7	machine	machine	NOUN
cana-5401	133	8	learning	learn	VERB
cana-5401	133	9	algorithms	algorithm	NOUN
cana-5401	133	10	parameter	parameter	PROPN
cana-5401	133	11	naïve	naïve	PROPN
cana-5401	133	12	bayes	bayes	PROPN
cana-5401	133	13	knn	knn	PROPN
cana-5401	133	14	rf	rf	PROPN
cana-5401	133	15	nn	nn	PROPN
cana-5401	133	16	proposed	propose	VERB
cana-5401	133	17	model	model	NOUN
cana-5401	133	18	accuracy	accuracy	NOUN
cana-5401	133	19	0.91	0.91	NUM
cana-5401	133	20	0.92	0.92	NUM
cana-5401	133	21	0.88	0.88	NUM
cana-5401	133	22	0.94	0.94	NUM
cana-5401	133	23	0.94	0.94	NUM
cana-5401	133	24	precision	precision	NOUN
cana-5401	133	25	0.91	0.91	NUM
cana-5401	133	26	0.92	0.92	NUM
cana-5401	133	27	0.89	0.89	NUM
cana-5401	133	28	0.94	0.94	NUM
cana-5401	133	29	0.94	0.94	NUM
cana-5401	133	30	recall	recall	NOUN
cana-5401	133	31	0.91	0.91	NUM
cana-5401	133	32	0.92	0.92	NUM
cana-5401	133	33	0.88	0.88	NUM
cana-5401	133	34	0.94	0.94	NUM
cana-5401	133	35	0.94	0.94	NUM
cana-5401	133	36	f1	f1	NOUN
cana-5401	133	37	-	-	PUNCT
cana-5401	133	38	score	score	NOUN
cana-5401	133	39	0.90	0.90	NUM
cana-5401	133	40	0.92	0.92	NUM
cana-5401	133	41	0.87	0.87	NUM
cana-5401	133	42	0.94	0.94	NUM
cana-5401	133	43	0.94	0.94	NUM
cana-5401	133	44	6	6	NUM
cana-5401	133	45	.	.	PUNCT
cana-5401	133	46	conclusion	conclusion	NOUN
cana-5401	133	47	and	and	CCONJ
cana-5401	133	48	future	future	ADJ
cana-5401	133	49	scope	scope	NOUN
cana-5401	133	50	in	in	ADP
cana-5401	133	51	this	this	DET
cana-5401	133	52	paper	paper	NOUN
cana-5401	133	53	,	,	PUNCT
cana-5401	133	54	we	we	PRON
cana-5401	133	55	have	have	AUX
cana-5401	133	56	designed	design	VERB
cana-5401	133	57	crime	crime	NOUN
cana-5401	133	58	prediction	prediction	NOUN
cana-5401	133	59	model	model	NOUN
cana-5401	133	60	using	use	VERB
cana-5401	133	61	the	the	DET
cana-5401	133	62	various	various	ADJ
cana-5401	133	63	machine	machine	NOUN
cana-5401	133	64	learning	learn	VERB
cana-5401	133	65	algorithms	algorithm	NOUN
cana-5401	133	66	such	such	ADJ
cana-5401	133	67	as	as	ADP
cana-5401	133	68	nb	nb	PROPN
cana-5401	133	69	,	,	PUNCT
cana-5401	133	70	knn	knn	PROPN
cana-5401	133	71	,	,	PUNCT
cana-5401	133	72	rf	rf	PROPN
cana-5401	133	73	,	,	PUNCT
cana-5401	133	74	and	and	CCONJ
cana-5401	133	75	nn	nn	INTJ
cana-5401	133	76	.	.	PROPN
cana-5401	134	1	besides	besides	SCONJ
cana-5401	134	2	that	that	PRON
cana-5401	134	3	,	,	PUNCT
cana-5401	134	4	pre	pre	ADJ
cana-5401	134	5	-	-	ADJ
cana-5401	134	6	processing	processing	NOUN
cana-5401	134	7	of	of	ADP
cana-5401	134	8	the	the	DET
cana-5401	134	9	dataset	dataset	NOUN
cana-5401	134	10	is	be	AUX
cana-5401	134	11	done	do	VERB
cana-5401	134	12	using	use	VERB
cana-5401	134	13	the	the	DET
cana-5401	134	14	correlation	correlation	NOUN
cana-5401	134	15	matrix	matrix	NOUN
cana-5401	134	16	to	to	PART
cana-5401	134	17	find	find	VERB
cana-5401	134	18	the	the	DET
cana-5401	134	19	appropriate	appropriate	ADJ
cana-5401	134	20	features	feature	NOUN
cana-5401	134	21	from	from	ADP
cana-5401	134	22	it	it	PRON
cana-5401	134	23	.	.	PUNCT
cana-5401	135	1	further	far	ADV
cana-5401	135	2	,	,	PUNCT
cana-5401	135	3	the	the	DET
cana-5401	135	4	dataset	dataset	NOUN
cana-5401	135	5	is	be	AUX
cana-5401	135	6	split	split	VERB
cana-5401	135	7	into	into	ADP
cana-5401	135	8	70:30	70:30	NUM
cana-5401	135	9	ratio	ratio	NOUN
cana-5401	135	10	.	.	PUNCT
cana-5401	136	1	the	the	DET
cana-5401	136	2	70	70	NUM
cana-5401	136	3	%	%	NOUN
cana-5401	136	4	dataset	dataset	NOUN
cana-5401	136	5	is	be	AUX
cana-5401	136	6	utilized	utilize	VERB
cana-5401	136	7	for	for	ADP
cana-5401	136	8	train	train	NOUN
cana-5401	136	9	the	the	DET
cana-5401	136	10	machine	machine	NOUN
cana-5401	136	11	learning	learn	VERB
cana-5401	136	12	algorithm	algorithm	NOUN
cana-5401	136	13	and	and	CCONJ
cana-5401	136	14	30	30	NUM
cana-5401	136	15	%	%	NOUN
cana-5401	136	16	dataset	dataset	NOUN
cana-5401	136	17	is	be	AUX
cana-5401	136	18	utilized	utilize	VERB
cana-5401	136	19	for	for	ADP
cana-5401	136	20	validate	validate	VERB
cana-5401	136	21	the	the	DET
cana-5401	136	22	model	model	NOUN
cana-5401	136	23	in	in	ADP
cana-5401	136	24	the	the	DET
cana-5401	136	25	testing	testing	NOUN
cana-5401	136	26	phase	phase	NOUN
cana-5401	136	27	.	.	PUNCT
cana-5401	137	1	the	the	DET
cana-5401	137	2	simulation	simulation	NOUN
cana-5401	137	3	evaluation	evaluation	NOUN
cana-5401	137	4	shows	show	VERB
cana-5401	137	5	that	that	SCONJ
cana-5401	137	6	the	the	DET
cana-5401	137	7	neural	neural	ADJ
cana-5401	137	8	network	network	NOUN
cana-5401	137	9	algorithm	algorithm	NOUN
cana-5401	137	10	achieves	achieve	VERB
cana-5401	137	11	the	the	DET
cana-5401	137	12	highest	high	ADJ
cana-5401	137	13	accuracy	accuracy	NOUN
cana-5401	137	14	over	over	ADP
cana-5401	137	15	the	the	DET
cana-5401	137	16	other	other	ADJ
cana-5401	137	17	ml	ml	NOUN
cana-5401	137	18	algorithms	algorithm	NOUN
cana-5401	137	19	.	.	PUNCT
cana-5401	138	1	in	in	ADP
cana-5401	138	2	the	the	DET
cana-5401	138	3	future	future	NOUN
cana-5401	138	4	,	,	PUNCT
cana-5401	138	5	we	we	PRON
cana-5401	138	6	will	will	AUX
cana-5401	138	7	enhance	enhance	VERB
cana-5401	138	8	the	the	DET
cana-5401	138	9	performance	performance	NOUN
cana-5401	138	10	of	of	ADP
cana-5401	138	11	the	the	DET
cana-5401	138	12	neural	neural	ADJ
cana-5401	138	13	network	network	NOUN
cana-5401	138	14	by	by	ADP
cana-5401	138	15	finding	find	VERB
cana-5401	138	16	the	the	DET
cana-5401	138	17	optimal	optimal	ADJ
cana-5401	138	18	weight	weight	NOUN
cana-5401	138	19	values	value	NOUN
cana-5401	138	20	of	of	ADP
cana-5401	138	21	it	it	PRON
cana-5401	138	22	using	use	VERB
cana-5401	138	23	the	the	DET
cana-5401	138	24	metaheuristic	metaheuristic	ADJ
cana-5401	138	25	algorithms	algorithm	NOUN
cana-5401	138	26	.	.	PUNCT
cana-5401	139	1	further	far	ADV
cana-5401	139	2	,	,	PUNCT
cana-5401	139	3	we	we	PRON
cana-5401	139	4	will	will	AUX
cana-5401	139	5	validate	validate	VERB
cana-5401	139	6	the	the	DET
cana-5401	139	7	robustness	robustness	NOUN
cana-5401	139	8	of	of	ADP
cana-5401	139	9	the	the	DET
cana-5401	139	10	proposed	propose	VERB
cana-5401	139	11	model	model	NOUN
cana-5401	139	12	by	by	ADP
cana-5401	139	13	evaluating	evaluate	VERB
cana-5401	139	14	on	on	ADP
cana-5401	139	15	the	the	DET
cana-5401	139	16	different	different	ADJ
cana-5401	139	17	datasets	dataset	NOUN
cana-5401	139	18	.	.	PUNCT
cana-5401	140	1	references	reference	NOUN
cana-5401	140	2	introduction	introduction	NOUN
cana-5401	140	3	[	[	X
cana-5401	140	4	1	1	X
cana-5401	140	5	]	]	X
cana-5401	140	6	y.	y.	PROPN
cana-5401	140	7	rayhan	rayhan	PROPN
cana-5401	140	8	and	and	CCONJ
cana-5401	140	9	t.	t.	PROPN
cana-5401	140	10	hashem	hashem	PROPN
cana-5401	140	11	,	,	PUNCT
cana-5401	140	12	“	"	PUNCT
cana-5401	140	13	aist	aist	NOUN
cana-5401	140	14	:	:	PUNCT
cana-5401	140	15	an	an	DET
cana-5401	140	16	interpretable	interpretable	ADJ
cana-5401	140	17	attention	attention	NOUN
cana-5401	140	18	-	-	PUNCT
cana-5401	140	19	based	base	VERB
cana-5401	140	20	deep	deep	ADJ
cana-5401	140	21	learning	learning	NOUN
cana-5401	140	22	model	model	NOUN
cana-5401	140	23	for	for	ADP
cana-5401	140	24	crime	crime	NOUN
cana-5401	140	25	prediction	prediction	NOUN
cana-5401	140	26	,	,	PUNCT
cana-5401	140	27	”	"	PUNCT
cana-5401	140	28	acm	acm	NOUN
cana-5401	140	29	transactions	transaction	NOUN
cana-5401	140	30	on	on	ADP
cana-5401	140	31	spatial	spatial	ADJ
cana-5401	140	32	algorithms	algorithm	NOUN
cana-5401	140	33	and	and	CCONJ
cana-5401	140	34	systems	system	NOUN
cana-5401	140	35	,	,	PUNCT
cana-5401	140	36	vol	vol	NOUN
cana-5401	140	37	.	.	PROPN
cana-5401	141	1	9	9	NUM
cana-5401	141	2	,	,	PUNCT
cana-5401	141	3	no	no	INTJ
cana-5401	141	4	.	.	NOUN
cana-5401	141	5	2	2	NUM
cana-5401	141	6	,	,	PUNCT
cana-5401	141	7	pp	pp	PROPN
cana-5401	141	8	.	.	PUNCT
cana-5401	142	1	1–31	1–31	PROPN
cana-5401	142	2	,	,	PUNCT
cana-5401	142	3	apr	apr	PROPN
cana-5401	142	4	.	.	PROPN
cana-5401	142	5	2023	2023	NUM
cana-5401	142	6	,	,	PUNCT
cana-5401	142	7	doi	doi	NOUN
cana-5401	142	8	:	:	PUNCT
cana-5401	142	9	10.1145/3582274	10.1145/3582274	NUM
cana-5401	142	10	.	.	PUNCT
cana-5401	143	1	[	[	X
cana-5401	143	2	2	2	NUM
cana-5401	143	3	]	]	X
cana-5401	143	4	f.	f.	PROPN
cana-5401	143	5	dakalbab	dakalbab	PROPN
cana-5401	143	6	,	,	PUNCT
cana-5401	143	7	m.	m.	NOUN
cana-5401	143	8	a.	a.	PROPN
cana-5401	143	9	talib	talib	PROPN
cana-5401	143	10	,	,	PUNCT
cana-5401	143	11	o.	o.	PROPN
cana-5401	143	12	a.	a.	PROPN
cana-5401	143	13	waraga	waraga	PROPN
cana-5401	143	14	,	,	PUNCT
cana-5401	143	15	a.	a.	PROPN
cana-5401	143	16	b.	b.	PROPN
cana-5401	143	17	nassif	nassif	PROPN
cana-5401	143	18	,	,	PUNCT
cana-5401	143	19	s.	s.	PROPN
cana-5401	143	20	abbas	abbas	PROPN
cana-5401	143	21	,	,	PUNCT
cana-5401	143	22	and	and	CCONJ
cana-5401	143	23	q.	q.	PROPN
cana-5401	143	24	nasir	nasir	PROPN
cana-5401	143	25	,	,	PUNCT
cana-5401	143	26	“	"	PUNCT
cana-5401	143	27	artificial	artificial	ADJ
cana-5401	143	28	intelligence	intelligence	NOUN
cana-5401	143	29	&	&	CCONJ
cana-5401	143	30	crime	crime	PROPN
cana-5401	143	31	prediction	prediction	PROPN
cana-5401	143	32	:	:	PUNCT
cana-5401	143	33	a	a	DET
cana-5401	143	34	systematic	systematic	ADJ
cana-5401	143	35	literature	literature	NOUN
cana-5401	143	36	review	review	NOUN
cana-5401	143	37	,	,	PUNCT
cana-5401	143	38	”	"	PUNCT
cana-5401	143	39	social	social	PROPN
cana-5401	143	40	sciences	sciences	PROPN
cana-5401	143	41	&	&	CCONJ
cana-5401	143	42	humanities	humanity	NOUN
cana-5401	143	43	open	open	VERB
cana-5401	143	44	,	,	PUNCT
cana-5401	143	45	vol	vol	NOUN
cana-5401	143	46	.	.	PROPN
cana-5401	143	47	6	6	NUM
cana-5401	143	48	,	,	PUNCT
cana-5401	143	49	no	no	INTJ
cana-5401	143	50	.	.	NOUN
cana-5401	143	51	1	1	NUM
cana-5401	143	52	,	,	PUNCT
cana-5401	143	53	p.	p.	NOUN
cana-5401	143	54	100342	100342	NUM
cana-5401	143	55	,	,	PUNCT
cana-5401	143	56	jan	jan	PROPN
cana-5401	143	57	.	.	PROPN
cana-5401	143	58	2022	2022	NUM
cana-5401	143	59	,	,	PUNCT
cana-5401	143	60	doi	doi	NOUN
cana-5401	143	61	:	:	PUNCT
cana-5401	143	62	10.1016	10.1016	NUM
cana-5401	143	63	/	/	SYM
cana-5401	143	64	j.ssaho.2022.100342	j.ssaho.2022.100342	NOUN
cana-5401	143	65	.	.	PUNCT
cana-5401	144	1	communications	communication	NOUN
cana-5401	144	2	on	on	ADP
cana-5401	144	3	applied	apply	VERB
cana-5401	144	4	nonlinear	nonlinear	ADJ
cana-5401	144	5	analysis	analysis	NOUN
cana-5401	144	6	issn	issn	NOUN
cana-5401	144	7	:	:	PUNCT
cana-5401	144	8	1074	1074	NUM
cana-5401	144	9	-	-	PUNCT
cana-5401	144	10	133x	133x	NUM
cana-5401	144	11	vol	vol	NOUN
cana-5401	144	12	32	32	NUM
cana-5401	144	13	no	no	NOUN
cana-5401	144	14	.	.	PUNCT
cana-5401	145	1	icmasd	icmasd	NOUN
cana-5401	145	2	(	(	PUNCT
cana-5401	145	3	2025	2025	NUM
cana-5401	145	4	)	)	PUNCT
cana-5401	145	5	1861	1861	NUM
cana-5401	145	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-5401	146	1	ml	ml	ADP
cana-5401	146	2	[	[	X
cana-5401	146	3	3	3	NUM
cana-5401	146	4	]	]	X
cana-5401	146	5	i.	i.	PROPN
cana-5401	146	6	h.	h.	PROPN
cana-5401	146	7	sarker	sarker	PROPN
cana-5401	146	8	,	,	PUNCT
cana-5401	146	9	“	"	PUNCT
cana-5401	146	10	machine	machine	NOUN
cana-5401	146	11	learning	learning	NOUN
cana-5401	146	12	:	:	PUNCT
cana-5401	146	13	algorithms	algorithm	NOUN
cana-5401	146	14	,	,	PUNCT
cana-5401	146	15	real	real	ADJ
cana-5401	146	16	-	-	PUNCT
cana-5401	146	17	world	world	NOUN
cana-5401	146	18	applications	application	NOUN
cana-5401	146	19	and	and	CCONJ
cana-5401	146	20	research	research	NOUN
cana-5401	146	21	directions	direction	NOUN
cana-5401	146	22	,	,	PUNCT
cana-5401	146	23	”	"	PUNCT
cana-5401	146	24	sn	sn	PROPN
cana-5401	146	25	computer	computer	NOUN
cana-5401	146	26	science	science	NOUN
cana-5401	146	27	,	,	PUNCT
cana-5401	146	28	vol	vol	NOUN
cana-5401	146	29	.	.	PROPN
cana-5401	147	1	2	2	NUM
cana-5401	147	2	,	,	PUNCT
cana-5401	147	3	no	no	INTJ
cana-5401	147	4	.	.	NOUN
cana-5401	147	5	3	3	NUM
cana-5401	147	6	,	,	PUNCT
cana-5401	147	7	mar	mar	PROPN
cana-5401	147	8	.	.	PROPN
cana-5401	147	9	2021	2021	NUM
cana-5401	147	10	,	,	PUNCT
cana-5401	147	11	doi	doi	NOUN
cana-5401	147	12	:	:	PUNCT
cana-5401	147	13	10.1007	10.1007	NUM
cana-5401	147	14	/	/	SYM
cana-5401	147	15	s42979	s42979	NOUN
cana-5401	147	16	-	-	PUNCT
cana-5401	147	17	021	021	NUM
cana-5401	147	18	-	-	PUNCT
cana-5401	147	19	00592	00592	NUM
cana-5401	147	20	-	-	PUNCT
cana-5401	147	21	x.	x.	NOUN
cana-5401	147	22	knn	knn	PROPN
cana-5401	148	1	and	and	CCONJ
cana-5401	148	2	rf	rf	PRON
cana-5401	149	1	[	[	X
cana-5401	149	2	4	4	NUM
cana-5401	149	3	]	]	PUNCT
cana-5401	149	4	a.	a.	NOUN
cana-5401	149	5	sayli	sayli	NOUN
cana-5401	149	6	and	and	CCONJ
cana-5401	149	7	s.	s.	PROPN
cana-5401	149	8	başarir	başarir	PROPN
cana-5401	149	9	,	,	PUNCT
cana-5401	149	10	“	"	PUNCT
cana-5401	149	11	s	s	AUX
cana-5401	149	12	sampling	sample	VERB
cana-5401	149	13	techniques	technique	NOUN
cana-5401	149	14	and	and	CCONJ
cana-5401	149	15	application	application	NOUN
cana-5401	149	16	in	in	ADP
cana-5401	149	17	machine	machine	NOUN
cana-5401	149	18	learning	learn	VERB
cana-5401	149	19	in	in	ADP
cana-5401	149	20	order	order	NOUN
cana-5401	149	21	to	to	PART
cana-5401	149	22	analyse	analyse	VERB
cana-5401	149	23	crime	crime	NOUN
cana-5401	149	24	dataset	dataset	NOUN
cana-5401	149	25	,	,	PUNCT
cana-5401	149	26	”	"	PUNCT
cana-5401	149	27	european	european	PROPN
cana-5401	149	28	journal	journal	PROPN
cana-5401	149	29	of	of	ADP
cana-5401	149	30	science	science	NOUN
cana-5401	149	31	and	and	CCONJ
cana-5401	149	32	technology	technology	NOUN
cana-5401	149	33	,	,	PUNCT
cana-5401	149	34	no	no	INTJ
cana-5401	149	35	.	.	PROPN
cana-5401	149	36	38	38	NUM
cana-5401	149	37	,	,	PUNCT
cana-5401	149	38	pp	pp	ADJ
cana-5401	149	39	.	.	PUNCT
cana-5401	149	40	296	296	NUM
cana-5401	149	41	-	-	SYM
cana-5401	149	42	310	310	NUM
cana-5401	149	43	,	,	PUNCT
cana-5401	149	44	jun	jun	PROPN
cana-5401	149	45	.	.	PROPN
cana-5401	149	46	2022	2022	NUM
cana-5401	149	47	,	,	PUNCT
cana-5401	149	48	doi	doi	NOUN
cana-5401	149	49	:	:	PUNCT
cana-5401	149	50	10.31590	10.31590	NUM
cana-5401	149	51	/	/	SYM
cana-5401	149	52	ejosat.1115323	ejosat.1115323	PROPN
cana-5401	149	53	.	.	PUNCT
cana-5401	149	54	nb	nb	X
cana-5401	150	1	[	[	X
cana-5401	150	2	5	5	NUM
cana-5401	150	3	]	]	PUNCT
cana-5401	150	4	m.	m.	NOUN
cana-5401	150	5	khan	khan	PROPN
cana-5401	150	6	,	,	PUNCT
cana-5401	150	7	a.	a.	PROPN
cana-5401	150	8	ali	ali	PROPN
cana-5401	150	9	,	,	PUNCT
cana-5401	150	10	and	and	CCONJ
cana-5401	150	11	y.	y.	PROPN
cana-5401	150	12	alharbi	alharbi	PROPN
cana-5401	150	13	,	,	PUNCT
cana-5401	150	14	“	"	PUNCT
cana-5401	150	15	predicting	predict	VERB
cana-5401	150	16	and	and	CCONJ
cana-5401	150	17	preventing	prevent	VERB
cana-5401	150	18	crime	crime	NOUN
cana-5401	150	19	:	:	PUNCT
cana-5401	150	20	a	a	DET
cana-5401	150	21	crime	crime	NOUN
cana-5401	150	22	prediction	prediction	NOUN
cana-5401	150	23	model	model	NOUN
cana-5401	150	24	using	use	VERB
cana-5401	150	25	san	san	PROPN
cana-5401	150	26	francisco	francisco	PROPN
cana-5401	150	27	crime	crime	NOUN
cana-5401	150	28	data	datum	NOUN
cana-5401	150	29	by	by	ADP
cana-5401	150	30	classification	classification	NOUN
cana-5401	150	31	techniques	technique	NOUN
cana-5401	150	32	,	,	PUNCT
cana-5401	150	33	”	"	PUNCT
cana-5401	150	34	complexity	complexity	NOUN
cana-5401	150	35	,	,	PUNCT
cana-5401	150	36	vol	vol	NOUN
cana-5401	150	37	.	.	NOUN
cana-5401	150	38	2022	2022	NUM
cana-5401	150	39	,	,	PUNCT
cana-5401	150	40	pp	pp	ADJ
cana-5401	150	41	.	.	PUNCT
cana-5401	151	1	1–13	1–13	PROPN
cana-5401	151	2	,	,	PUNCT
cana-5401	151	3	feb	feb	PROPN
cana-5401	151	4	.	.	PROPN
cana-5401	151	5	2022	2022	NUM
cana-5401	151	6	,	,	PUNCT
cana-5401	151	7	doi	doi	NOUN
cana-5401	151	8	:	:	PUNCT
cana-5401	151	9	10.1155/2022/4830411	10.1155/2022/4830411	NUM
cana-5401	151	10	.	.	PUNCT
cana-5401	151	11	nn	nn	PROPN
cana-5401	152	1	[	[	X
cana-5401	152	2	6]s	6]s	NUM
cana-5401	152	3	.	.	PUNCT
cana-5401	152	4	walczak	walczak	ADJ
cana-5401	152	5	,	,	PUNCT
cana-5401	152	6	“	"	PUNCT
cana-5401	152	7	predicting	predict	VERB
cana-5401	152	8	crime	crime	NOUN
cana-5401	152	9	and	and	CCONJ
cana-5401	152	10	other	other	ADJ
cana-5401	152	11	uses	use	NOUN
cana-5401	152	12	of	of	ADP
cana-5401	152	13	neural	neural	ADJ
cana-5401	152	14	networks	network	NOUN
cana-5401	152	15	in	in	ADP
cana-5401	152	16	police	police	NOUN
cana-5401	152	17	decision	decision	NOUN
cana-5401	152	18	making	making	NOUN
cana-5401	152	19	,	,	PUNCT
cana-5401	152	20	”	"	PUNCT
cana-5401	152	21	frontiers	frontier	NOUN
cana-5401	152	22	in	in	ADP
cana-5401	152	23	psychology	psychology	NOUN
cana-5401	152	24	,	,	PUNCT
cana-5401	152	25	vol	vol	NOUN
cana-5401	152	26	.	.	PROPN
cana-5401	152	27	12	12	NUM
cana-5401	152	28	,	,	PUNCT
cana-5401	152	29	oct	oct	PROPN
cana-5401	152	30	.	.	PROPN
cana-5401	152	31	2021	2021	NUM
cana-5401	152	32	,	,	PUNCT
cana-5401	152	33	doi	doi	NOUN
cana-5401	152	34	:	:	PUNCT
cana-5401	152	35	10.3389	10.3389	NUM
cana-5401	152	36	/	/	SYM
cana-5401	152	37	fpsyg.2021.587943	fpsyg.2021.587943	NOUN
cana-5401	152	38	.	.	PUNCT
cana-5401	153	1	crime	crime	NOUN
cana-5401	153	2	dataset	dataset	VERB
cana-5401	154	1	[	[	X
cana-5401	154	2	7	7	NUM
cana-5401	154	3	]	]	SYM
cana-5401	154	4	crimes	crime	NOUN
cana-5401	154	5	2001	2001	NUM
cana-5401	154	6	to	to	PART
cana-5401	154	7	present	present	VERB
cana-5401	154	8	dashboard	dashboard	NOUN
cana-5401	154	9	.	.	PUNCT
cana-5401	155	1	(	(	PUNCT
cana-5401	155	2	n.d	n.d	PROPN
cana-5401	155	3	.	.	PROPN
cana-5401	155	4	)	)	PUNCT
cana-5401	155	5	.	.	PUNCT
cana-5401	156	1	city	city	NOUN
cana-5401	156	2	of	of	ADP
cana-5401	156	3	chicago	chicago	PROPN
cana-5401	156	4	|	|	PROPN
cana-5401	156	5	data	datum	NOUN
cana-5401	156	6	portal	portal	NOUN
cana-5401	156	7	.	.	PUNCT
cana-5401	157	1	https://data.cityofchicago.org/stories/s/crimes-2001-to-present-dashboard/5cd6-ry5	https://data.cityofchicago.org/stories/s/crimes-2001-to-present-dashboard/5cd6-ry5	PROPN
cana-5401	157	2	g	g	NOUN
cana-5401	157	3	about	about	ADP
cana-5401	157	4	:	:	PUNCT
cana-5401	157	5	blank	blank	ADJ