id	sid	tid	token	lemma	pos
cana-2432	1	1	communications	communication	NOUN
cana-2432	1	2	on	on	ADP
cana-2432	1	3	applied	apply	VERB
cana-2432	1	4	nonlinear	nonlinear	ADJ
cana-2432	1	5	analysis	analysis	NOUN
cana-2432	1	6	issn	issn	NOUN
cana-2432	1	7	:	:	PUNCT
cana-2432	1	8	1074	1074	NUM
cana-2432	1	9	-	-	PUNCT
cana-2432	1	10	133x	133x	NUM
cana-2432	1	11	vol	vol	NOUN
cana-2432	1	12	32	32	NUM
cana-2432	1	13	no	no	NOUN
cana-2432	1	14	.	.	PUNCT
cana-2432	2	1	2s	2s	NUM
cana-2432	2	2	(	(	PUNCT
cana-2432	2	3	2025	2025	NUM
cana-2432	2	4	)	)	PUNCT
cana-2432	2	5	423	423	NUM
cana-2432	2	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-2432	2	7	wtban	wtban	NOUN
cana-2432	2	8	-	-	PUNCT
cana-2432	2	9	cnn	cnn	PROPN
cana-2432	2	10	-	-	PUNCT
cana-2432	2	11	tl	tl	PROPN
cana-2432	2	12	:	:	PUNCT
cana-2432	2	13	wavelet	wavelet	NOUN
cana-2432	2	14	transform	transform	NOUN
cana-2432	2	15	-	-	PUNCT
cana-2432	2	16	based	base	VERB
cana-2432	2	17	feature	feature	NOUN
cana-2432	2	18	extraction	extraction	NOUN
cana-2432	2	19	and	and	CCONJ
cana-2432	2	20	bonferroni	bonferroni	NOUN
cana-2432	2	21	adjusted	adjust	VERB
cana-2432	2	22	anova	anova	PROPN
cana-2432	2	23	-	-	PROPN
cana-2432	2	24	cnn	cnn	PROPN
cana-2432	2	25	with	with	ADP
cana-2432	2	26	transfer	transfer	NOUN
cana-2432	2	27	learning	learning	NOUN
cana-2432	2	28	for	for	ADP
cana-2432	2	29	lung	lung	NOUN
cana-2432	2	30	x	x	PROPN
cana-2432	2	31	-	-	NOUN
cana-2432	2	32	ray	ray	NOUN
cana-2432	2	33	image	image	NOUN
cana-2432	2	34	classification	classification	NOUN
cana-2432	2	35	kavitha	kavitha	PROPN
cana-2432	2	36	s1	s1	PROPN
cana-2432	2	37	and	and	CCONJ
cana-2432	2	38	dr.h.hannah	dr.h.hannah	PROPN
cana-2432	2	39	inbarani2	inbarani2	NOUN
cana-2432	2	40	1research	1research	NUM
cana-2432	2	41	scholar	scholar	NOUN
cana-2432	2	42	,	,	PUNCT
cana-2432	2	43	department	department	NOUN
cana-2432	2	44	of	of	ADP
cana-2432	2	45	computer	computer	NOUN
cana-2432	2	46	science	science	NOUN
cana-2432	2	47	,	,	PUNCT
cana-2432	2	48	periyar	periyar	PROPN
cana-2432	2	49	university	university	NOUN
cana-2432	2	50	,	,	PUNCT
cana-2432	2	51	salem	salem	NOUN
cana-2432	2	52	,	,	PUNCT
cana-2432	2	53	tamilnadu	tamilnadu	NOUN
cana-2432	2	54	,	,	PUNCT
cana-2432	2	55	india	india	PROPN
cana-2432	2	56	.	.	PUNCT
cana-2432	3	1	kavitha.chanjhana@gmail.com	kavitha.chanjhana@gmail.com	X
cana-2432	3	2	2associate	2associate	NUM
cana-2432	3	3	professor	professor	NOUN
cana-2432	3	4	,	,	PUNCT
cana-2432	3	5	department	department	NOUN
cana-2432	3	6	of	of	ADP
cana-2432	3	7	computer	computer	NOUN
cana-2432	3	8	science	science	NOUN
cana-2432	3	9	,	,	PUNCT
cana-2432	3	10	periyar	periyar	PROPN
cana-2432	3	11	university	university	NOUN
cana-2432	3	12	,	,	PUNCT
cana-2432	3	13	salem	salem	NOUN
cana-2432	3	14	,	,	PUNCT
cana-2432	3	15	tamilnadu	tamilnadu	NOUN
cana-2432	3	16	,	,	PUNCT
cana-2432	3	17	india	india	PROPN
cana-2432	3	18	.	.	PUNCT
cana-2432	4	1	hhinba@periyaruniversity.ac.in	hhinba@periyaruniversity.ac.in	PROPN
cana-2432	4	2	article	article	NOUN
cana-2432	4	3	history	history	NOUN
cana-2432	4	4	:	:	PUNCT
cana-2432	4	5	received	receive	VERB
cana-2432	4	6	:	:	PUNCT
cana-2432	4	7	20	20	NUM
cana-2432	4	8	-	-	SYM
cana-2432	4	9	09	09	NUM
cana-2432	4	10	-	-	PUNCT
cana-2432	4	11	2024	2024	NUM
cana-2432	4	12	revised	revise	VERB
cana-2432	4	13	:	:	PUNCT
cana-2432	4	14	28	28	NUM
cana-2432	4	15	-	-	SYM
cana-2432	4	16	10	10	NUM
cana-2432	4	17	-	-	PUNCT
cana-2432	4	18	2024	2024	NUM
cana-2432	4	19	accepted	accept	VERB
cana-2432	4	20	:	:	PUNCT
cana-2432	4	21	08	08	NUM
cana-2432	4	22	-	-	SYM
cana-2432	4	23	11	11	NUM
cana-2432	4	24	-	-	PUNCT
cana-2432	4	25	2024	2024	NUM
cana-2432	4	26	abstract	abstract	NOUN
cana-2432	4	27	:	:	PUNCT
cana-2432	4	28	a	a	DET
cana-2432	4	29	comprehensive	comprehensive	ADJ
cana-2432	4	30	approach	approach	NOUN
cana-2432	4	31	for	for	ADP
cana-2432	4	32	lung	lung	NOUN
cana-2432	4	33	x	x	PROPN
cana-2432	4	34	-	-	NOUN
cana-2432	4	35	ray	ray	NOUN
cana-2432	4	36	image	image	NOUN
cana-2432	4	37	classification	classification	NOUN
cana-2432	4	38	is	be	AUX
cana-2432	4	39	proposed	propose	VERB
cana-2432	4	40	,	,	PUNCT
cana-2432	4	41	combining	combine	VERB
cana-2432	4	42	wavelet	wavelet	NOUN
cana-2432	4	43	transform	transform	NOUN
cana-2432	4	44	-	-	PUNCT
cana-2432	4	45	based	base	VERB
cana-2432	4	46	feature	feature	NOUN
cana-2432	4	47	extraction	extraction	NOUN
cana-2432	4	48	with	with	ADP
cana-2432	4	49	bonferroni	bonferroni	PROPN
cana-2432	4	50	anova	anova	PROPN
cana-2432	4	51	feature	feature	NOUN
cana-2432	4	52	selection	selection	NOUN
cana-2432	4	53	and	and	CCONJ
cana-2432	4	54	deep	deep	ADJ
cana-2432	4	55	learning	learning	NOUN
cana-2432	4	56	techniques	technique	NOUN
cana-2432	4	57	.	.	PUNCT
cana-2432	5	1	features	feature	NOUN
cana-2432	5	2	are	be	AUX
cana-2432	5	3	initially	initially	ADV
cana-2432	5	4	extracted	extract	VERB
cana-2432	5	5	from	from	ADP
cana-2432	5	6	lung	lung	NOUN
cana-2432	5	7	x	x	NOUN
cana-2432	5	8	-	-	NOUN
cana-2432	5	9	ray	ray	NOUN
cana-2432	5	10	images	image	NOUN
cana-2432	5	11	using	use	VERB
cana-2432	5	12	wavelet	wavelet	NOUN
cana-2432	5	13	transform	transform	NOUN
cana-2432	5	14	,	,	PUNCT
cana-2432	5	15	capturing	capture	VERB
cana-2432	5	16	crucial	crucial	ADJ
cana-2432	5	17	information	information	NOUN
cana-2432	5	18	across	across	ADP
cana-2432	5	19	multiple	multiple	ADJ
cana-2432	5	20	scales	scale	NOUN
cana-2432	5	21	.	.	PUNCT
cana-2432	6	1	these	these	DET
cana-2432	6	2	features	feature	NOUN
cana-2432	6	3	are	be	AUX
cana-2432	6	4	concatenated	concatenate	VERB
cana-2432	6	5	to	to	PART
cana-2432	6	6	form	form	VERB
cana-2432	6	7	a	a	DET
cana-2432	6	8	comprehensive	comprehensive	ADJ
cana-2432	6	9	feature	feature	NOUN
cana-2432	6	10	set	set	VERB
cana-2432	6	11	.	.	PUNCT
cana-2432	7	1	to	to	PART
cana-2432	7	2	optimize	optimize	VERB
cana-2432	7	3	this	this	DET
cana-2432	7	4	feature	feature	NOUN
cana-2432	7	5	set	set	NOUN
cana-2432	7	6	,	,	PUNCT
cana-2432	7	7	anova	anova	PROPN
cana-2432	7	8	is	be	AUX
cana-2432	7	9	employed	employ	VERB
cana-2432	7	10	with	with	ADP
cana-2432	7	11	bonferroni	bonferroni	NOUN
cana-2432	7	12	adjusted	adjust	VERB
cana-2432	7	13	feature	feature	NOUN
cana-2432	7	14	selection	selection	NOUN
cana-2432	7	15	to	to	PART
cana-2432	7	16	control	control	VERB
cana-2432	7	17	the	the	DET
cana-2432	7	18	false	false	ADJ
cana-2432	7	19	positive	positive	ADJ
cana-2432	7	20	rate	rate	NOUN
cana-2432	7	21	and	and	CCONJ
cana-2432	7	22	to	to	PART
cana-2432	7	23	identify	identify	VERB
cana-2432	7	24	the	the	DET
cana-2432	7	25	most	most	ADV
cana-2432	7	26	relevant	relevant	ADJ
cana-2432	7	27	features	feature	NOUN
cana-2432	7	28	,	,	PUNCT
cana-2432	7	29	thereby	thereby	ADV
cana-2432	7	30	reducing	reduce	VERB
cana-2432	7	31	the	the	DET
cana-2432	7	32	dimensionality	dimensionality	NOUN
cana-2432	7	33	of	of	ADP
cana-2432	7	34	the	the	DET
cana-2432	7	35	input	input	NOUN
cana-2432	7	36	data	datum	NOUN
cana-2432	7	37	.	.	PUNCT
cana-2432	8	1	this	this	DET
cana-2432	8	2	optimization	optimization	NOUN
cana-2432	8	3	can	can	AUX
cana-2432	8	4	result	result	VERB
cana-2432	8	5	in	in	ADP
cana-2432	8	6	expedited	expedite	VERB
cana-2432	8	7	training	training	NOUN
cana-2432	8	8	times	time	NOUN
cana-2432	8	9	and	and	CCONJ
cana-2432	8	10	reduced	reduce	VERB
cana-2432	8	11	computational	computational	ADJ
cana-2432	8	12	resources	resource	NOUN
cana-2432	8	13	required	require	VERB
cana-2432	8	14	by	by	ADP
cana-2432	8	15	the	the	DET
cana-2432	8	16	cnn	cnn	PROPN
cana-2432	8	17	.	.	PUNCT
cana-2432	9	1	the	the	DET
cana-2432	9	2	selected	select	VERB
cana-2432	9	3	features	feature	NOUN
cana-2432	9	4	are	be	AUX
cana-2432	9	5	subsequently	subsequently	ADV
cana-2432	9	6	fed	feed	VERB
cana-2432	9	7	into	into	ADP
cana-2432	9	8	a	a	DET
cana-2432	9	9	convolutional	convolutional	ADJ
cana-2432	9	10	neural	neural	ADJ
cana-2432	9	11	network	network	NOUN
cana-2432	9	12	(	(	PUNCT
cana-2432	9	13	cnn	cnn	PROPN
cana-2432	9	14	)	)	PUNCT
cana-2432	9	15	for	for	ADP
cana-2432	9	16	classification	classification	NOUN
cana-2432	9	17	.	.	PUNCT
cana-2432	10	1	to	to	PART
cana-2432	10	2	further	far	ADV
cana-2432	10	3	boost	boost	VERB
cana-2432	10	4	the	the	DET
cana-2432	10	5	cnn	cnn	PROPN
cana-2432	10	6	's	's	PART
cana-2432	10	7	performance	performance	NOUN
cana-2432	10	8	,	,	PUNCT
cana-2432	10	9	transfer	transfer	NOUN
cana-2432	10	10	learning	learning	NOUN
cana-2432	10	11	is	be	AUX
cana-2432	10	12	utilized	utilize	VERB
cana-2432	10	13	by	by	ADP
cana-2432	10	14	leveraging	leverage	VERB
cana-2432	10	15	pre	pre	ADJ
cana-2432	10	16	-	-	ADJ
cana-2432	10	17	trained	train	VERB
cana-2432	10	18	models	model	NOUN
cana-2432	10	19	.	.	PUNCT
cana-2432	11	1	additionally	additionally	ADV
cana-2432	11	2	,	,	PUNCT
cana-2432	11	3	the	the	DET
cana-2432	11	4	performance	performance	NOUN
cana-2432	11	5	of	of	ADP
cana-2432	11	6	anova	anova	PROPN
cana-2432	11	7	-	-	PUNCT
cana-2432	11	8	based	base	VERB
cana-2432	11	9	feature	feature	NOUN
cana-2432	11	10	selection	selection	NOUN
cana-2432	11	11	is	be	AUX
cana-2432	11	12	also	also	ADV
cana-2432	11	13	compared	compare	VERB
cana-2432	11	14	with	with	ADP
cana-2432	11	15	that	that	PRON
cana-2432	11	16	of	of	ADP
cana-2432	11	17	a	a	DET
cana-2432	11	18	genetic	genetic	ADJ
cana-2432	11	19	algorithm	algorithm	NOUN
cana-2432	11	20	-	-	PUNCT
cana-2432	11	21	based	base	VERB
cana-2432	11	22	method	method	NOUN
cana-2432	11	23	.	.	PUNCT
cana-2432	12	1	this	this	DET
cana-2432	12	2	integrated	integrate	VERB
cana-2432	12	3	method	method	NOUN
cana-2432	12	4	,	,	PUNCT
cana-2432	12	5	referred	refer	VERB
cana-2432	12	6	to	to	ADP
cana-2432	12	7	as	as	ADP
cana-2432	12	8	wtban	wtban	NOUN
cana-2432	12	9	-	-	PUNCT
cana-2432	12	10	cnn	cnn	PROPN
cana-2432	12	11	-	-	PUNCT
cana-2432	12	12	tl	tl	PROPN
cana-2432	12	13	,	,	PUNCT
cana-2432	12	14	aims	aim	VERB
cana-2432	12	15	to	to	PART
cana-2432	12	16	reduce	reduce	VERB
cana-2432	12	17	the	the	DET
cana-2432	12	18	training	training	NOUN
cana-2432	12	19	times	time	NOUN
cana-2432	12	20	and	and	CCONJ
cana-2432	12	21	resource	resource	NOUN
cana-2432	12	22	requirements	requirement	NOUN
cana-2432	12	23	while	while	SCONJ
cana-2432	12	24	improving	improve	VERB
cana-2432	12	25	the	the	DET
cana-2432	12	26	accuracy	accuracy	NOUN
cana-2432	12	27	and	and	CCONJ
cana-2432	12	28	efficiency	efficiency	NOUN
cana-2432	12	29	of	of	ADP
cana-2432	12	30	lung	lung	NOUN
cana-2432	12	31	x	x	PROPN
cana-2432	12	32	-	-	NOUN
cana-2432	12	33	ray	ray	NOUN
cana-2432	12	34	image	image	NOUN
cana-2432	12	35	classification	classification	NOUN
cana-2432	12	36	.	.	PUNCT
cana-2432	13	1	keywords	keyword	NOUN
cana-2432	13	2	:	:	PUNCT
cana-2432	13	3	wavelet	wavelet	NOUN
cana-2432	13	4	transform	transform	NOUN
cana-2432	13	5	,	,	PUNCT
cana-2432	13	6	bonferroni	bonferroni	NOUN
cana-2432	13	7	anova	anova	X
cana-2432	13	8	(	(	PUNCT
cana-2432	13	9	analysis	analysis	NOUN
cana-2432	13	10	of	of	ADP
cana-2432	13	11	variance	variance	NOUN
cana-2432	13	12	)	)	PUNCT
cana-2432	13	13	,	,	PUNCT
cana-2432	13	14	feature	feature	NOUN
cana-2432	13	15	extraction	extraction	NOUN
cana-2432	13	16	,	,	PUNCT
cana-2432	13	17	feature	feature	NOUN
cana-2432	13	18	selection	selection	NOUN
cana-2432	13	19	,	,	PUNCT
cana-2432	13	20	wtban	wtban	NOUN
cana-2432	13	21	-	-	PUNCT
cana-2432	13	22	cnn	cnn	PROPN
cana-2432	13	23	-	-	PUNCT
cana-2432	13	24	tl	tl	PROPN
cana-2432	13	25	(	(	PUNCT
cana-2432	13	26	wavelet	wavelet	NOUN
cana-2432	13	27	transform	transform	NOUN
cana-2432	13	28	bonferroni	bonferroni	NOUN
cana-2432	13	29	anova	anova	PROPN
cana-2432	13	30	enhanced	enhance	VERB
cana-2432	13	31	convolutional	convolutional	ADJ
cana-2432	13	32	neural	neural	ADJ
cana-2432	13	33	network	network	NOUN
cana-2432	13	34	with	with	ADP
cana-2432	13	35	transfer	transfer	NOUN
cana-2432	13	36	learning	learning	NOUN
cana-2432	13	37	)	)	PUNCT
cana-2432	13	38	introduction	introduction	NOUN
cana-2432	13	39	medical	medical	ADJ
cana-2432	13	40	imaging	imaging	NOUN
cana-2432	13	41	,	,	PUNCT
cana-2432	13	42	particularly	particularly	ADV
cana-2432	13	43	the	the	DET
cana-2432	13	44	analysis	analysis	NOUN
cana-2432	13	45	of	of	ADP
cana-2432	13	46	lung	lung	NOUN
cana-2432	13	47	x	x	NOUN
cana-2432	13	48	-	-	NOUN
cana-2432	13	49	ray	ray	NOUN
cana-2432	13	50	images	image	NOUN
cana-2432	13	51	,	,	PUNCT
cana-2432	13	52	holds	hold	VERB
cana-2432	13	53	paramount	paramount	ADJ
cana-2432	13	54	importance	importance	NOUN
cana-2432	13	55	in	in	ADP
cana-2432	13	56	the	the	DET
cana-2432	13	57	diagnosis	diagnosis	NOUN
cana-2432	13	58	and	and	CCONJ
cana-2432	13	59	treatment	treatment	NOUN
cana-2432	13	60	of	of	ADP
cana-2432	13	61	various	various	ADJ
cana-2432	13	62	respiratory	respiratory	ADJ
cana-2432	13	63	ailments	ailment	NOUN
cana-2432	13	64	,	,	PUNCT
cana-2432	13	65	including	include	VERB
cana-2432	13	66	infections	infection	NOUN
cana-2432	13	67	,	,	PUNCT
cana-2432	13	68	tumors	tumor	NOUN
cana-2432	13	69	,	,	PUNCT
cana-2432	13	70	covid-19	covid-19	PROPN
cana-2432	13	71	and	and	CCONJ
cana-2432	13	72	pneumonia	pneumonia	NOUN
cana-2432	13	73	related	relate	VERB
cana-2432	13	74	diseases[1][2	diseases[1][2	PROPN
cana-2432	13	75	]	]	PUNCT
cana-2432	13	76	.	.	PUNCT
cana-2432	14	1	in	in	ADP
cana-2432	14	2	recent	recent	ADJ
cana-2432	14	3	years	year	NOUN
cana-2432	14	4	,	,	PUNCT
cana-2432	14	5	the	the	DET
cana-2432	14	6	fusion	fusion	NOUN
cana-2432	14	7	of	of	ADP
cana-2432	14	8	advanced	advanced	ADJ
cana-2432	14	9	computational	computational	ADJ
cana-2432	14	10	techniques	technique	NOUN
cana-2432	14	11	with	with	ADP
cana-2432	14	12	traditional	traditional	ADJ
cana-2432	14	13	diagnostic	diagnostic	ADJ
cana-2432	14	14	methods	method	NOUN
cana-2432	14	15	has	have	AUX
cana-2432	14	16	led	lead	VERB
cana-2432	14	17	to	to	ADP
cana-2432	14	18	significant	significant	ADJ
cana-2432	14	19	advancements	advancement	NOUN
cana-2432	14	20	in	in	ADP
cana-2432	14	21	the	the	DET
cana-2432	14	22	field	field	NOUN
cana-2432	14	23	of	of	ADP
cana-2432	14	24	medical	medical	ADJ
cana-2432	14	25	image	image	NOUN
cana-2432	14	26	analysis	analysis	NOUN
cana-2432	15	1	[	[	X
cana-2432	15	2	3][4	3][4	NOUN
cana-2432	15	3	]	]	X
cana-2432	15	4	.	.	PUNCT
cana-2432	16	1	this	this	DET
cana-2432	16	2	paper	paper	NOUN
cana-2432	16	3	introduces	introduce	VERB
cana-2432	16	4	a	a	DET
cana-2432	16	5	comprehensive	comprehensive	ADJ
cana-2432	16	6	approach	approach	NOUN
cana-2432	16	7	aimed	aim	VERB
cana-2432	16	8	at	at	ADP
cana-2432	16	9	refining	refine	VERB
cana-2432	16	10	the	the	DET
cana-2432	16	11	classification	classification	NOUN
cana-2432	16	12	accuracy	accuracy	NOUN
cana-2432	16	13	and	and	CCONJ
cana-2432	16	14	efficiency	efficiency	NOUN
cana-2432	16	15	of	of	ADP
cana-2432	16	16	lung	lung	NOUN
cana-2432	16	17	x	x	PROPN
cana-2432	16	18	-	-	NOUN
cana-2432	16	19	ray	ray	NOUN
cana-2432	16	20	images	image	NOUN
cana-2432	16	21	through	through	ADP
cana-2432	16	22	a	a	DET
cana-2432	16	23	synergy	synergy	NOUN
cana-2432	16	24	of	of	ADP
cana-2432	16	25	wavelet	wavelet	NOUN
cana-2432	16	26	transform	transform	NOUN
cana-2432	16	27	-	-	PUNCT
cana-2432	16	28	based	base	VERB
cana-2432	16	29	feature	feature	NOUN
cana-2432	16	30	extraction	extraction	NOUN
cana-2432	16	31	,	,	PUNCT
cana-2432	16	32	bonferroni	bonferroni	NOUN
cana-2432	16	33	adjusted	adjust	VERB
cana-2432	16	34	anova	anova	PROPN
cana-2432	16	35	feature	feature	NOUN
cana-2432	16	36	selection	selection	NOUN
cana-2432	16	37	,	,	PUNCT
cana-2432	16	38	and	and	CCONJ
cana-2432	16	39	state	state	NOUN
cana-2432	16	40	-	-	PUNCT
cana-2432	16	41	of	of	ADP
cana-2432	16	42	-	-	PUNCT
cana-2432	16	43	the	the	DET
cana-2432	16	44	-	-	PUNCT
cana-2432	16	45	art	art	NOUN
cana-2432	16	46	deep	deep	ADJ
cana-2432	16	47	learning	learning	NOUN
cana-2432	16	48	methodologies	methodology	NOUN
cana-2432	16	49	.	.	PUNCT
cana-2432	17	1	the	the	DET
cana-2432	17	2	proposed	propose	VERB
cana-2432	17	3	methodology	methodology	NOUN
cana-2432	17	4	capitalizes	capitalize	VERB
cana-2432	17	5	on	on	ADP
cana-2432	17	6	the	the	DET
cana-2432	17	7	inherent	inherent	ADJ
cana-2432	17	8	advantages	advantage	NOUN
cana-2432	17	9	of	of	ADP
cana-2432	17	10	wavelet	wavelet	NOUN
cana-2432	17	11	transform	transform	NOUN
cana-2432	17	12	,	,	PUNCT
cana-2432	17	13	a	a	DET
cana-2432	17	14	powerful	powerful	ADJ
cana-2432	17	15	signal	signal	NOUN
cana-2432	17	16	processing	processing	NOUN
cana-2432	17	17	technique	technique	NOUN
cana-2432	17	18	renowned	renowne	VERB
cana-2432	17	19	for	for	ADP
cana-2432	17	20	its	its	PRON
cana-2432	17	21	ability	ability	NOUN
cana-2432	17	22	to	to	PART
cana-2432	17	23	decompose	decompose	VERB
cana-2432	17	24	complex	complex	ADJ
cana-2432	17	25	signals	signal	NOUN
cana-2432	17	26	into	into	ADP
cana-2432	17	27	frequency	frequency	NOUN
cana-2432	17	28	sub	sub	NOUN
cana-2432	17	29	-	-	NOUN
cana-2432	17	30	bands	band	NOUN
cana-2432	17	31	at	at	ADP
cana-2432	17	32	different	different	ADJ
cana-2432	17	33	scales	scale	NOUN
cana-2432	17	34	.	.	PUNCT
cana-2432	18	1	by	by	ADP
cana-2432	18	2	applying	apply	VERB
cana-2432	18	3	wavelet	wavelet	NOUN
cana-2432	18	4	transform	transform	NOUN
cana-2432	18	5	[	[	X
cana-2432	18	6	5	5	NUM
cana-2432	18	7	]	]	PUNCT
cana-2432	18	8	to	to	ADP
cana-2432	18	9	lung	lung	NOUN
cana-2432	18	10	x	x	PROPN
cana-2432	18	11	-	-	NOUN
cana-2432	18	12	ray	ray	NOUN
cana-2432	18	13	images	image	NOUN
cana-2432	18	14	,	,	PUNCT
cana-2432	18	15	we	we	PRON
cana-2432	18	16	can	can	AUX
cana-2432	18	17	mailto:hhinba@periyaruniversity.ac.in	mailto:hhinba@periyaruniversity.ac.in	VERB
cana-2432	18	18	communications	communication	NOUN
cana-2432	18	19	on	on	ADP
cana-2432	18	20	applied	apply	VERB
cana-2432	18	21	nonlinear	nonlinear	ADJ
cana-2432	18	22	analysis	analysis	NOUN
cana-2432	18	23	issn	issn	NOUN
cana-2432	18	24	:	:	PUNCT
cana-2432	18	25	1074	1074	NUM
cana-2432	18	26	-	-	PUNCT
cana-2432	18	27	133x	133x	NUM
cana-2432	18	28	vol	vol	NOUN
cana-2432	18	29	32	32	NUM
cana-2432	18	30	no	no	NOUN
cana-2432	18	31	.	.	PUNCT
cana-2432	19	1	2s	2s	NUM
cana-2432	19	2	(	(	PUNCT
cana-2432	19	3	2025	2025	NUM
cana-2432	19	4	)	)	PUNCT
cana-2432	19	5	424	424	NUM
cana-2432	19	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-2432	19	7	capture	capture	VERB
cana-2432	19	8	crucial	crucial	ADJ
cana-2432	19	9	information	information	NOUN
cana-2432	19	10	embedded	embed	VERB
cana-2432	19	11	within	within	ADP
cana-2432	19	12	the	the	DET
cana-2432	19	13	images	image	NOUN
cana-2432	19	14	across	across	ADP
cana-2432	19	15	multiple	multiple	ADJ
cana-2432	19	16	resolutions	resolution	NOUN
cana-2432	19	17	,	,	PUNCT
cana-2432	19	18	thereby	thereby	ADV
cana-2432	19	19	facilitating	facilitate	VERB
cana-2432	19	20	the	the	DET
cana-2432	19	21	extraction	extraction	NOUN
cana-2432	19	22	of	of	ADP
cana-2432	19	23	discriminative	discriminative	NOUN
cana-2432	19	24	features	feature	VERB
cana-2432	19	25	indicative	indicative	ADJ
cana-2432	19	26	of	of	ADP
cana-2432	19	27	various	various	ADJ
cana-2432	19	28	pulmonary	pulmonary	ADJ
cana-2432	19	29	conditions	condition	NOUN
cana-2432	19	30	[	[	X
cana-2432	19	31	6	6	NUM
cana-2432	19	32	]	]	PUNCT
cana-2432	19	33	.	.	PUNCT
cana-2432	20	1	these	these	DET
cana-2432	20	2	features	feature	NOUN
cana-2432	20	3	,	,	PUNCT
cana-2432	20	4	extracted	extract	VERB
cana-2432	20	5	at	at	ADP
cana-2432	20	6	different	different	ADJ
cana-2432	20	7	frequency	frequency	NOUN
cana-2432	20	8	scales	scale	NOUN
cana-2432	20	9	,	,	PUNCT
cana-2432	20	10	are	be	AUX
cana-2432	20	11	subsequently	subsequently	ADV
cana-2432	20	12	concatenated	concatenate	VERB
cana-2432	20	13	to	to	PART
cana-2432	20	14	construct	construct	VERB
cana-2432	20	15	a	a	DET
cana-2432	20	16	comprehensive	comprehensive	ADJ
cana-2432	20	17	feature	feature	NOUN
cana-2432	20	18	set	set	NOUN
cana-2432	20	19	that	that	PRON
cana-2432	20	20	encapsulates	encapsulate	VERB
cana-2432	20	21	the	the	DET
cana-2432	20	22	intricate	intricate	ADJ
cana-2432	20	23	details	detail	NOUN
cana-2432	20	24	essential	essential	ADJ
cana-2432	20	25	for	for	ADP
cana-2432	20	26	accurate	accurate	ADJ
cana-2432	20	27	classification	classification	NOUN
cana-2432	20	28	.	.	PUNCT
cana-2432	21	1	in	in	ADP
cana-2432	21	2	addition	addition	NOUN
cana-2432	21	3	to	to	ADP
cana-2432	21	4	feature	feature	NOUN
cana-2432	21	5	extraction	extraction	NOUN
cana-2432	21	6	,	,	PUNCT
cana-2432	21	7	the	the	DET
cana-2432	21	8	proposed	propose	VERB
cana-2432	21	9	approach	approach	NOUN
cana-2432	21	10	integrates	integrate	NOUN
cana-2432	21	11	anova	anova	PROPN
cana-2432	22	1	[	[	X
cana-2432	22	2	7	7	NUM
cana-2432	22	3	]	]	PUNCT
cana-2432	22	4	feature	feature	NOUN
cana-2432	22	5	selection	selection	NOUN
cana-2432	22	6	algorithm	algorithm	NOUN
cana-2432	22	7	with	with	ADP
cana-2432	22	8	bonferroni	bonferroni	PROPN
cana-2432	22	9	correction	correction	NOUN
cana-2432	22	10	to	to	PART
cana-2432	22	11	refine	refine	VERB
cana-2432	22	12	the	the	DET
cana-2432	22	13	feature	feature	NOUN
cana-2432	22	14	set	set	VERB
cana-2432	22	15	further	far	ADV
cana-2432	22	16	.	.	PUNCT
cana-2432	23	1	to	to	PART
cana-2432	23	2	enhance	enhance	VERB
cana-2432	23	3	the	the	DET
cana-2432	23	4	efficiency	efficiency	NOUN
cana-2432	23	5	and	and	CCONJ
cana-2432	23	6	effectiveness	effectiveness	NOUN
cana-2432	23	7	of	of	ADP
cana-2432	23	8	the	the	DET
cana-2432	23	9	classification	classification	NOUN
cana-2432	23	10	process	process	NOUN
cana-2432	23	11	,	,	PUNCT
cana-2432	23	12	anova	anova	X
cana-2432	23	13	(	(	PUNCT
cana-2432	23	14	analysis	analysis	NOUN
cana-2432	23	15	of	of	ADP
cana-2432	23	16	variance	variance	NOUN
cana-2432	23	17	)	)	PUNCT
cana-2432	23	18	with	with	ADP
cana-2432	23	19	bonferroni	bonferroni	NOUN
cana-2432	23	20	correction	correction	NOUN
cana-2432	23	21	is	be	AUX
cana-2432	23	22	utilized	utilize	VERB
cana-2432	23	23	to	to	PART
cana-2432	23	24	control	control	VERB
cana-2432	23	25	the	the	DET
cana-2432	23	26	false	false	ADJ
cana-2432	23	27	positive	positive	ADJ
cana-2432	23	28	rate	rate	NOUN
cana-2432	23	29	for	for	ADP
cana-2432	23	30	feature	feature	NOUN
cana-2432	23	31	selection	selection	NOUN
cana-2432	23	32	.	.	PUNCT
cana-2432	24	1	this	this	DET
cana-2432	24	2	statistical	statistical	ADJ
cana-2432	24	3	method	method	NOUN
cana-2432	24	4	identifies	identify	VERB
cana-2432	24	5	the	the	DET
cana-2432	24	6	most	most	ADV
cana-2432	24	7	relevant	relevant	ADJ
cana-2432	24	8	features	feature	NOUN
cana-2432	24	9	,	,	PUNCT
cana-2432	24	10	thereby	thereby	ADV
cana-2432	24	11	reducing	reduce	VERB
cana-2432	24	12	the	the	DET
cana-2432	24	13	dimensionality	dimensionality	NOUN
cana-2432	24	14	of	of	ADP
cana-2432	24	15	the	the	DET
cana-2432	24	16	input	input	NOUN
cana-2432	24	17	data	datum	NOUN
cana-2432	24	18	and	and	CCONJ
cana-2432	24	19	optimizing	optimize	VERB
cana-2432	24	20	the	the	DET
cana-2432	24	21	computational	computational	ADJ
cana-2432	24	22	resources	resource	NOUN
cana-2432	24	23	required	require	VERB
cana-2432	24	24	by	by	ADP
cana-2432	24	25	the	the	DET
cana-2432	24	26	cnn	cnn	PROPN
cana-2432	24	27	.	.	PUNCT
cana-2432	25	1	this	this	DET
cana-2432	25	2	reduction	reduction	NOUN
cana-2432	25	3	in	in	ADP
cana-2432	25	4	dimensionality	dimensionality	NOUN
cana-2432	25	5	not	not	PART
cana-2432	25	6	only	only	ADV
cana-2432	25	7	expedites	expedite	VERB
cana-2432	25	8	training	training	NOUN
cana-2432	25	9	times	time	NOUN
cana-2432	25	10	but	but	CCONJ
cana-2432	25	11	also	also	ADV
cana-2432	25	12	mitigates	mitigate	VERB
cana-2432	25	13	the	the	DET
cana-2432	25	14	risk	risk	NOUN
cana-2432	25	15	of	of	ADP
cana-2432	25	16	overfitting	overfitte	VERB
cana-2432	25	17	,	,	PUNCT
cana-2432	25	18	thereby	thereby	ADV
cana-2432	25	19	improving	improve	VERB
cana-2432	25	20	the	the	DET
cana-2432	25	21	overall	overall	ADJ
cana-2432	25	22	performance	performance	NOUN
cana-2432	25	23	of	of	ADP
cana-2432	25	24	the	the	DET
cana-2432	25	25	model	model	NOUN
cana-2432	25	26	.	.	PUNCT
cana-2432	26	1	the	the	DET
cana-2432	26	2	optimized	optimize	VERB
cana-2432	26	3	feature	feature	NOUN
cana-2432	26	4	set	set	NOUN
cana-2432	26	5	,	,	PUNCT
cana-2432	26	6	curated	curate	VERB
cana-2432	26	7	through	through	ADP
cana-2432	26	8	the	the	DET
cana-2432	26	9	joint	joint	ADJ
cana-2432	26	10	efforts	effort	NOUN
cana-2432	26	11	of	of	ADP
cana-2432	26	12	wavelet	wavelet	NOUN
cana-2432	26	13	transform	transform	NOUN
cana-2432	26	14	and	and	CCONJ
cana-2432	26	15	anova	anova	PROPN
cana-2432	26	16	,	,	PUNCT
cana-2432	26	17	serves	serve	VERB
cana-2432	26	18	as	as	ADP
cana-2432	26	19	the	the	DET
cana-2432	26	20	input	input	NOUN
cana-2432	26	21	to	to	ADP
cana-2432	26	22	a	a	DET
cana-2432	26	23	convolutional	convolutional	ADJ
cana-2432	26	24	neural	neural	ADJ
cana-2432	26	25	network	network	NOUN
cana-2432	26	26	(	(	PUNCT
cana-2432	26	27	cnn	cnn	PROPN
cana-2432	26	28	)	)	PUNCT
cana-2432	26	29	,	,	PUNCT
cana-2432	26	30	a	a	DET
cana-2432	26	31	class	class	NOUN
cana-2432	26	32	of	of	ADP
cana-2432	26	33	deep	deep	ADJ
cana-2432	26	34	learning	learning	NOUN
cana-2432	26	35	models	model	NOUN
cana-2432	26	36	renowned	renowned	ADJ
cana-2432	26	37	for	for	ADP
cana-2432	26	38	their	their	PRON
cana-2432	26	39	ability	ability	NOUN
cana-2432	26	40	in	in	ADP
cana-2432	26	41	extracting	extract	VERB
cana-2432	26	42	hierarchical	hierarchical	ADJ
cana-2432	26	43	representations	representation	NOUN
cana-2432	26	44	from	from	ADP
cana-2432	26	45	complex	complex	ADJ
cana-2432	26	46	data	datum	NOUN
cana-2432	26	47	.	.	PUNCT
cana-2432	27	1	the	the	DET
cana-2432	27	2	cnn	cnn	PROPN
cana-2432	27	3	is	be	AUX
cana-2432	27	4	tasked	task	VERB
cana-2432	27	5	with	with	ADP
cana-2432	27	6	learning	learn	VERB
cana-2432	27	7	discriminative	discriminative	NOUN
cana-2432	27	8	patterns	pattern	NOUN
cana-2432	27	9	and	and	CCONJ
cana-2432	27	10	relationships	relationship	NOUN
cana-2432	27	11	inherent	inherent	ADJ
cana-2432	27	12	in	in	ADP
cana-2432	27	13	the	the	DET
cana-2432	27	14	feature	feature	NOUN
cana-2432	27	15	-	-	PUNCT
cana-2432	27	16	rich	rich	ADJ
cana-2432	27	17	lung	lung	NOUN
cana-2432	27	18	x	x	PROPN
cana-2432	27	19	-	-	NOUN
cana-2432	27	20	ray	ray	NOUN
cana-2432	27	21	images	image	NOUN
cana-2432	27	22	,	,	PUNCT
cana-2432	27	23	ultimately	ultimately	ADV
cana-2432	27	24	facilitating	facilitate	VERB
cana-2432	27	25	accurate	accurate	ADJ
cana-2432	27	26	classification	classification	NOUN
cana-2432	27	27	across	across	ADP
cana-2432	27	28	diverse	diverse	ADJ
cana-2432	27	29	pathological	pathological	ADJ
cana-2432	27	30	conditions	condition	NOUN
cana-2432	27	31	.	.	PUNCT
cana-2432	28	1	moreover	moreover	ADV
cana-2432	28	2	,	,	PUNCT
cana-2432	28	3	to	to	PART
cana-2432	28	4	augment	augment	VERB
cana-2432	28	5	the	the	DET
cana-2432	28	6	cnn	cnn	PROPN
cana-2432	28	7	's	's	PART
cana-2432	28	8	learning	learn	VERB
cana-2432	28	9	capabilities	capability	NOUN
cana-2432	28	10	and	and	CCONJ
cana-2432	28	11	foster	foster	ADJ
cana-2432	28	12	generalization	generalization	NOUN
cana-2432	28	13	across	across	ADP
cana-2432	28	14	datasets	dataset	NOUN
cana-2432	28	15	,	,	PUNCT
cana-2432	28	16	transfer	transfer	NOUN
cana-2432	28	17	learning	learning	NOUN
cana-2432	28	18	is	be	AUX
cana-2432	28	19	leveraged	leverage	VERB
cana-2432	28	20	.	.	PUNCT
cana-2432	29	1	this	this	DET
cana-2432	29	2	approach	approach	NOUN
cana-2432	29	3	involves	involve	VERB
cana-2432	29	4	transferring	transfer	VERB
cana-2432	29	5	knowledge	knowledge	NOUN
cana-2432	29	6	from	from	ADP
cana-2432	29	7	pre	pre	ADJ
cana-2432	29	8	-	-	ADJ
cana-2432	29	9	trained	train	VERB
cana-2432	29	10	models	model	NOUN
cana-2432	29	11	trained	train	VERB
cana-2432	29	12	on	on	ADP
cana-2432	29	13	large	large	ADJ
cana-2432	29	14	-	-	PUNCT
cana-2432	29	15	scale	scale	NOUN
cana-2432	29	16	datasets	dataset	NOUN
cana-2432	29	17	to	to	ADP
cana-2432	29	18	our	our	PRON
cana-2432	29	19	specific	specific	ADJ
cana-2432	29	20	task	task	NOUN
cana-2432	29	21	of	of	ADP
cana-2432	29	22	lung	lung	PROPN
cana-2432	29	23	x	x	PROPN
cana-2432	29	24	-	-	NOUN
cana-2432	29	25	ray	ray	NOUN
cana-2432	29	26	image	image	NOUN
cana-2432	29	27	classification	classification	NOUN
cana-2432	29	28	.	.	PUNCT
cana-2432	30	1	by	by	ADP
cana-2432	30	2	initializing	initialize	VERB
cana-2432	30	3	the	the	DET
cana-2432	30	4	cnn	cnn	NOUN
cana-2432	30	5	with	with	ADP
cana-2432	30	6	pre	pre	ADJ
cana-2432	30	7	-	-	ADJ
cana-2432	30	8	learned	learned	ADJ
cana-2432	30	9	parameters	parameter	NOUN
cana-2432	30	10	and	and	CCONJ
cana-2432	30	11	fine	fine	ADV
cana-2432	30	12	-	-	PUNCT
cana-2432	30	13	tuning	tune	VERB
cana-2432	30	14	its	its	PRON
cana-2432	30	15	architecture	architecture	NOUN
cana-2432	30	16	on	on	ADP
cana-2432	30	17	our	our	PRON
cana-2432	30	18	dataset	dataset	NOUN
cana-2432	30	19	,	,	PUNCT
cana-2432	30	20	the	the	DET
cana-2432	30	21	wealth	wealth	NOUN
cana-2432	30	22	of	of	ADP
cana-2432	30	23	information	information	NOUN
cana-2432	30	24	encapsulated	encapsulate	VERB
cana-2432	30	25	within	within	ADP
cana-2432	30	26	the	the	DET
cana-2432	30	27	pre	pre	ADJ
cana-2432	30	28	-	-	ADJ
cana-2432	30	29	trained	train	VERB
cana-2432	30	30	models	model	NOUN
cana-2432	30	31	is	be	AUX
cana-2432	30	32	utilized	utilize	VERB
cana-2432	30	33	,	,	PUNCT
cana-2432	30	34	thereby	thereby	ADV
cana-2432	30	35	enhancing	enhance	VERB
cana-2432	30	36	the	the	DET
cana-2432	30	37	cnn	cnn	PROPN
cana-2432	30	38	's	's	PART
cana-2432	30	39	performance	performance	NOUN
cana-2432	30	40	and	and	CCONJ
cana-2432	30	41	accelerating	accelerate	VERB
cana-2432	30	42	the	the	DET
cana-2432	30	43	convergence	convergence	NOUN
cana-2432	30	44	of	of	ADP
cana-2432	30	45	the	the	DET
cana-2432	30	46	training	training	NOUN
cana-2432	30	47	process	process	NOUN
cana-2432	30	48	.	.	PUNCT
cana-2432	31	1	2	2	X
cana-2432	31	2	.	.	X
cana-2432	31	3	related	relate	VERB
cana-2432	31	4	works	work	NOUN
cana-2432	31	5	numerous	numerous	ADJ
cana-2432	31	6	studies	study	NOUN
cana-2432	31	7	have	have	AUX
cana-2432	31	8	investigated	investigate	VERB
cana-2432	31	9	various	various	ADJ
cana-2432	31	10	techniques	technique	NOUN
cana-2432	31	11	to	to	PART
cana-2432	31	12	enhance	enhance	VERB
cana-2432	31	13	the	the	DET
cana-2432	31	14	accuracy	accuracy	NOUN
cana-2432	31	15	and	and	CCONJ
cana-2432	31	16	efficiency	efficiency	NOUN
cana-2432	31	17	of	of	ADP
cana-2432	31	18	medical	medical	ADJ
cana-2432	31	19	image	image	NOUN
cana-2432	31	20	classification	classification	NOUN
cana-2432	31	21	,	,	PUNCT
cana-2432	31	22	especially	especially	ADV
cana-2432	31	23	for	for	ADP
cana-2432	31	24	lung	lung	NOUN
cana-2432	31	25	x	x	NOUN
cana-2432	31	26	-	-	NOUN
cana-2432	31	27	rays	ray	NOUN
cana-2432	31	28	.	.	PUNCT
cana-2432	32	1	a	a	DET
cana-2432	32	2	significant	significant	ADJ
cana-2432	32	3	emphasis	emphasis	NOUN
cana-2432	32	4	has	have	AUX
cana-2432	32	5	been	be	AUX
cana-2432	32	6	placed	place	VERB
cana-2432	32	7	on	on	ADP
cana-2432	32	8	leveraging	leverage	VERB
cana-2432	32	9	deep	deep	ADJ
cana-2432	32	10	learning	learning	NOUN
cana-2432	32	11	methods	method	NOUN
cana-2432	32	12	and	and	CCONJ
cana-2432	32	13	feature	feature	NOUN
cana-2432	32	14	extraction	extraction	NOUN
cana-2432	32	15	algorithms	algorithm	NOUN
cana-2432	32	16	to	to	PART
cana-2432	32	17	improve	improve	VERB
cana-2432	32	18	diagnostic	diagnostic	ADJ
cana-2432	32	19	capabilities	capability	NOUN
cana-2432	32	20	.	.	PUNCT
cana-2432	33	1	table	table	NOUN
cana-2432	33	2	i	i	PRON
cana-2432	33	3	summarizes	summarize	VERB
cana-2432	33	4	these	these	DET
cana-2432	33	5	related	relate	VERB
cana-2432	33	6	works	work	NOUN
cana-2432	33	7	.	.	PUNCT
cana-2432	34	1	table	table	NOUN
cana-2432	34	2	i	i	PRON
cana-2432	34	3	–	–	PUNCT
cana-2432	34	4	related	relate	VERB
cana-2432	34	5	works	work	NOUN
cana-2432	34	6	authors	author	NOUN
cana-2432	34	7	techniques	technique	NOUN
cana-2432	34	8	result	result	PROPN
cana-2432	34	9	reduwan	reduwan	PROPN
cana-2432	34	10	,	,	PUNCT
cana-2432	34	11	n.h	n.h	PROPN
cana-2432	34	12	.	.	PROPN
cana-2432	34	13	et	et	PROPN
cana-2432	34	14	al	al	PROPN
cana-2432	34	15	(	(	PUNCT
cana-2432	34	16	2024	2024	NUM
cana-2432	34	17	)	)	PUNCT
cana-2432	35	1	[	[	X
cana-2432	35	2	8	8	NUM
cana-2432	35	3	]	]	SYM
cana-2432	35	4	keshta	keshta	NOUN
cana-2432	35	5	,	,	PUNCT
cana-2432	35	6	i	i	PRON
cana-2432	35	7	et	et	VERB
cana-2432	35	8	al	al	PROPN
cana-2432	35	9	.	.	PROPN
cana-2432	36	1	(	(	PUNCT
cana-2432	36	2	2023	2023	NUM
cana-2432	36	3	)	)	PUNCT
cana-2432	37	1	[	[	X
cana-2432	37	2	9	9	NUM
cana-2432	37	3	]	]	PUNCT
cana-2432	37	4	.	.	PUNCT
cana-2432	38	1	feature	feature	NOUN
cana-2432	38	2	selection	selection	NOUN
cana-2432	38	3	techniques	technique	NOUN
cana-2432	38	4	combined	combine	VERB
cana-2432	38	5	with	with	ADP
cana-2432	38	6	deep	deep	ADJ
cana-2432	38	7	learning	learning	NOUN
cana-2432	38	8	models	model	NOUN
cana-2432	38	9	for	for	ADP
cana-2432	38	10	external	external	ADJ
cana-2432	38	11	root	root	NOUN
cana-2432	38	12	resorption	resorption	NOUN
cana-2432	38	13	identification	identification	NOUN
cana-2432	38	14	.	.	PUNCT
cana-2432	39	1	integration	integration	NOUN
cana-2432	39	2	of	of	ADP
cana-2432	39	3	anova	anova	PROPN
cana-2432	39	4	,	,	PUNCT
cana-2432	39	5	rrelieff	rrelieff	NOUN
cana-2432	39	6	and	and	CCONJ
cana-2432	39	7	random	random	ADJ
cana-2432	39	8	forest	forest	NOUN
cana-2432	39	9	feature	feature	NOUN
cana-2432	39	10	selection	selection	NOUN
cana-2432	39	11	algorithm	algorithm	NOUN
cana-2432	39	12	for	for	ADP
cana-2432	39	13	cancer	cancer	NOUN
cana-2432	39	14	detection	detection	NOUN
cana-2432	39	15	in	in	ADP
cana-2432	39	16	microarray	microarray	NOUN
cana-2432	39	17	data	datum	NOUN
cana-2432	39	18	discrete	discrete	VERB
cana-2432	39	19	wavelet	wavelet	NOUN
cana-2432	39	20	transform	transform	NOUN
cana-2432	39	21	and	and	CCONJ
cana-2432	39	22	capsule	capsule	ADJ
cana-2432	39	23	recursive	recursive	ADJ
cana-2432	39	24	feature	feature	NOUN
cana-2432	39	25	selection	selection	NOUN
cana-2432	39	26	with	with	ADP
cana-2432	39	27	vgg	vgg	PROPN
cana-2432	39	28	model	model	NOUN
cana-2432	39	29	achieved	achieve	VERB
cana-2432	39	30	higher	high	ADJ
cana-2432	39	31	accuracy	accuracy	NOUN
cana-2432	39	32	.	.	PUNCT
cana-2432	40	1	the	the	DET
cana-2432	40	2	proposed	propose	VERB
cana-2432	40	3	approach	approach	NOUN
cana-2432	40	4	demonstrates	demonstrate	VERB
cana-2432	40	5	that	that	SCONJ
cana-2432	40	6	feature	feature	NOUN
cana-2432	40	7	selection	selection	NOUN
cana-2432	40	8	improves	improve	VERB
cana-2432	40	9	the	the	DET
cana-2432	40	10	communications	communication	NOUN
cana-2432	40	11	on	on	ADP
cana-2432	40	12	applied	apply	VERB
cana-2432	40	13	nonlinear	nonlinear	ADJ
cana-2432	40	14	analysis	analysis	NOUN
cana-2432	40	15	issn	issn	NOUN
cana-2432	40	16	:	:	PUNCT
cana-2432	40	17	1074	1074	NUM
cana-2432	40	18	-	-	PUNCT
cana-2432	40	19	133x	133x	NUM
cana-2432	40	20	vol	vol	NOUN
cana-2432	40	21	32	32	NUM
cana-2432	40	22	no	no	NOUN
cana-2432	40	23	.	.	PUNCT
cana-2432	41	1	2s	2s	NUM
cana-2432	41	2	(	(	PUNCT
cana-2432	41	3	2025	2025	NUM
cana-2432	41	4	)	)	PUNCT
cana-2432	41	5	425	425	NUM
cana-2432	41	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-2432	41	7	monday	monday	PROPN
cana-2432	41	8	hn	hn	PROPN
cana-2432	41	9	et	et	PROPN
cana-2432	41	10	al	al	PROPN
cana-2432	41	11	(	(	PUNCT
cana-2432	41	12	2022	2022	NUM
cana-2432	41	13	)	)	PUNCT
cana-2432	42	1	[	[	X
cana-2432	42	2	10	10	NUM
cana-2432	42	3	]	]	PUNCT
cana-2432	42	4	nasiri	nasiri	ADV
cana-2432	42	5	,	,	PUNCT
cana-2432	42	6	hamid	hamid	PROPN
cana-2432	42	7	&	&	CCONJ
cana-2432	42	8	alavi	alavi	PROPN
cana-2432	42	9	,	,	PUNCT
cana-2432	42	10	seyed	seyed	PROPN
cana-2432	42	11	ali	ali	PROPN
cana-2432	42	12	.	.	PUNCT
cana-2432	42	13	(	(	PUNCT
cana-2432	42	14	2022	2022	NUM
cana-2432	42	15	)	)	PUNCT
cana-2432	43	1	[	[	X
cana-2432	43	2	11	11	NUM
cana-2432	43	3	]	]	PUNCT
cana-2432	43	4	samee	samee	PROPN
cana-2432	43	5	,	,	PUNCT
cana-2432	43	6	n.a	n.a	PROPN
cana-2432	43	7	.	.	PROPN
cana-2432	43	8	et	et	PROPN
cana-2432	43	9	al	al	PROPN
cana-2432	43	10	.	.	PROPN
cana-2432	43	11	(	(	PUNCT
cana-2432	43	12	2022	2022	NUM
cana-2432	43	13	)	)	PUNCT
cana-2432	44	1	[	[	X
cana-2432	44	2	12	12	NUM
cana-2432	44	3	]	]	X
cana-2432	44	4	zheng	zheng	PROPN
cana-2432	44	5	chen	chen	PROPN
cana-2432	44	6	et	et	PROPN
cana-2432	44	7	al	al	PROPN
cana-2432	44	8	.	.	PROPN
cana-2432	45	1	(	(	PUNCT
cana-2432	45	2	2020	2020	NUM
cana-2432	45	3	)	)	PUNCT
cana-2432	46	1	[	[	X
cana-2432	46	2	13	13	NUM
cana-2432	46	3	]	]	X
cana-2432	46	4	liu	liu	PROPN
cana-2432	46	5	et	et	PROPN
cana-2432	46	6	al	al	PROPN
cana-2432	46	7	.	.	PROPN
cana-2432	46	8	(	(	PUNCT
cana-2432	46	9	2021	2021	NUM
cana-2432	46	10	)	)	PUNCT
cana-2432	47	1	[	[	X
cana-2432	47	2	14	14	NUM
cana-2432	47	3	]	]	PUNCT
cana-2432	47	4	sarhan	sarhan	ADP
cana-2432	47	5	et	et	PROPN
cana-2432	47	6	al	al	PROPN
cana-2432	47	7	.	.	PROPN
cana-2432	47	8	(	(	PUNCT
cana-2432	47	9	2020	2020	NUM
cana-2432	47	10	)	)	PUNCT
cana-2432	48	1	[	[	X
cana-2432	48	2	15	15	NUM
cana-2432	48	3	]	]	X
cana-2432	48	4	rasheed	rasheed	NOUN
cana-2432	48	5	et	et	NOUN
cana-2432	48	6	al.(2021	al.(2021	PROPN
cana-2432	49	1	[	[	X
cana-2432	49	2	16	16	NUM
cana-2432	49	3	]	]	X
cana-2432	49	4	network	network	NOUN
cana-2432	49	5	for	for	ADP
cana-2432	49	6	classifying	classify	VERB
cana-2432	49	7	pneumonia	pneumonia	NOUN
cana-2432	49	8	related	relate	VERB
cana-2432	49	9	diseases	disease	NOUN
cana-2432	49	10	using	use	VERB
cana-2432	49	11	xray	xray	ADJ
cana-2432	49	12	images	image	NOUN
cana-2432	49	13	.	.	PUNCT
cana-2432	50	1	densenet169	densenet169	PROPN
cana-2432	50	2	and	and	CCONJ
cana-2432	50	3	anova	anova	PROPN
cana-2432	50	4	feature	feature	NOUN
cana-2432	50	5	selection	selection	NOUN
cana-2432	50	6	and	and	CCONJ
cana-2432	50	7	xgboost	xgboost	NOUN
cana-2432	50	8	for	for	ADP
cana-2432	50	9	classification	classification	NOUN
cana-2432	50	10	of	of	ADP
cana-2432	50	11	chest	chest	NOUN
cana-2432	50	12	x	x	NOUN
cana-2432	50	13	-	-	NOUN
cana-2432	50	14	ray	ray	NOUN
cana-2432	50	15	images	image	NOUN
cana-2432	50	16	alexnet	alexnet	ADJ
cana-2432	50	17	,	,	PUNCT
cana-2432	50	18	vgg	vgg	NOUN
cana-2432	50	19	,	,	PUNCT
cana-2432	50	20	and	and	CCONJ
cana-2432	50	21	googlenet	googlenet	NOUN
cana-2432	50	22	for	for	ADP
cana-2432	50	23	feature	feature	NOUN
cana-2432	50	24	extraction	extraction	NOUN
cana-2432	50	25	from	from	ADP
cana-2432	50	26	the	the	DET
cana-2432	50	27	inbreast	inbreast	ADJ
cana-2432	50	28	mammograms	mammogram	NOUN
cana-2432	50	29	and	and	CCONJ
cana-2432	50	30	univariate	univariate	ADJ
cana-2432	50	31	approach	approach	NOUN
cana-2432	50	32	for	for	ADP
cana-2432	50	33	feature	feature	NOUN
cana-2432	50	34	selection	selection	NOUN
cana-2432	50	35	feature	feature	NOUN
cana-2432	50	36	selection	selection	NOUN
cana-2432	50	37	integrated	integrate	VERB
cana-2432	50	38	with	with	ADP
cana-2432	50	39	deep	deep	ADJ
cana-2432	50	40	neural	neural	ADJ
cana-2432	50	41	networks	network	NOUN
cana-2432	50	42	.	.	PUNCT
cana-2432	51	1	wavelet	wavelet	NOUN
cana-2432	51	2	based	base	VERB
cana-2432	51	3	convolutional	convolutional	ADJ
cana-2432	51	4	wavelet	wavelet	NOUN
cana-2432	51	5	neural	neural	ADJ
cana-2432	51	6	network	network	NOUN
cana-2432	51	7	by	by	ADP
cana-2432	51	8	replacing	replace	VERB
cana-2432	51	9	the	the	DET
cana-2432	51	10	fully	fully	ADV
cana-2432	51	11	connected	connected	ADJ
cana-2432	51	12	neural	neural	ADJ
cana-2432	51	13	network	network	NOUN
cana-2432	51	14	with	with	ADP
cana-2432	51	15	wavelet	wavelet	NOUN
cana-2432	51	16	neural	neural	ADJ
cana-2432	51	17	network	network	NOUN
cana-2432	51	18	.	.	PUNCT
cana-2432	52	1	wavelet	wavelet	NOUN
cana-2432	52	2	decomposition	decomposition	NOUN
cana-2432	52	3	and	and	CCONJ
cana-2432	52	4	cnn	cnn	PROPN
cana-2432	52	5	for	for	ADP
cana-2432	52	6	lung	lung	NOUN
cana-2432	52	7	cancer	cancer	NOUN
cana-2432	52	8	detection	detection	NOUN
cana-2432	52	9	using	use	VERB
cana-2432	52	10	ct	ct	NUM
cana-2432	52	11	images	image	NOUN
cana-2432	52	12	.	.	PUNCT
cana-2432	53	1	wavelets	wavelet	NOUN
cana-2432	53	2	transform	transform	VERB
cana-2432	53	3	and	and	CCONJ
cana-2432	53	4	transfer	transfer	VERB
cana-2432	53	5	learning	learn	VERB
cana-2432	53	6	to	to	PART
cana-2432	53	7	detect	detect	VERB
cana-2432	53	8	cancer	cancer	NOUN
cana-2432	53	9	in	in	ADP
cana-2432	53	10	mammograms	mammogram	NOUN
cana-2432	53	11	.	.	PUNCT
cana-2432	54	1	classification	classification	NOUN
cana-2432	54	2	accuracy	accuracy	NOUN
cana-2432	54	3	.	.	PUNCT
cana-2432	55	1	accuracy	accuracy	NOUN
cana-2432	55	2	99.6	99.6	NUM
cana-2432	55	3	%	%	NOUN
cana-2432	55	4	two	two	NUM
cana-2432	55	5	class	class	NOUN
cana-2432	55	6	classification	classification	NOUN
cana-2432	55	7	accuracy	accuracy	NOUN
cana-2432	55	8	–	–	PUNCT
cana-2432	55	9	98.72	98.72	NUM
cana-2432	55	10	%	%	NOUN
cana-2432	55	11	and	and	CCONJ
cana-2432	55	12	multiclass	multiclass	ADJ
cana-2432	55	13	classification	classification	NOUN
cana-2432	55	14	accuracy	accuracy	NOUN
cana-2432	55	15	–	–	PUNCT
cana-2432	55	16	92	92	NUM
cana-2432	55	17	%	%	NOUN
cana-2432	55	18	classification	classification	NOUN
cana-2432	55	19	accuracy	accuracy	NOUN
cana-2432	55	20	98.50	98.50	NUM
cana-2432	55	21	%	%	NOUN
cana-2432	55	22	svm	svm	PROPN
cana-2432	55	23	-	-	ADJ
cana-2432	55	24	rfe	rfe	ADJ
cana-2432	55	25	(	(	PUNCT
cana-2432	55	26	recursive	recursive	ADJ
cana-2432	55	27	feature	feature	NOUN
cana-2432	55	28	elimination	elimination	NOUN
cana-2432	55	29	)	)	PUNCT
cana-2432	55	30	feature	feature	NOUN
cana-2432	55	31	selection	selection	NOUN
cana-2432	55	32	achieved	achieve	VERB
cana-2432	55	33	better	well	ADJ
cana-2432	55	34	accuracy	accuracy	NOUN
cana-2432	55	35	.	.	PUNCT
cana-2432	56	1	average	average	ADJ
cana-2432	56	2	accuracy	accuracy	NOUN
cana-2432	56	3	–	–	PUNCT
cana-2432	56	4	96.57	96.57	NUM
cana-2432	56	5	%	%	NOUN
cana-2432	56	6	accuracy	accuracy	NOUN
cana-2432	56	7	99.5	99.5	NUM
cana-2432	56	8	%	%	NOUN
cana-2432	56	9	resnet50	resnet50	NOUN
cana-2432	56	10	achieved	achieve	VERB
cana-2432	56	11	better	well	ADJ
cana-2432	56	12	accuracy	accuracy	NOUN
cana-2432	56	13	than	than	ADP
cana-2432	56	14	vgg16	vgg16	NOUN
cana-2432	56	15	,	,	PUNCT
cana-2432	56	16	googlenet	googlenet	NOUN
cana-2432	56	17	and	and	CCONJ
cana-2432	56	18	alexnet	alexnet	NOUN
cana-2432	56	19	.	.	PUNCT
cana-2432	57	1	3	3	X
cana-2432	57	2	.	.	X
cana-2432	57	3	research	research	NOUN
cana-2432	57	4	motivation	motivation	NOUN
cana-2432	57	5	the	the	DET
cana-2432	57	6	motivation	motivation	NOUN
cana-2432	57	7	for	for	ADP
cana-2432	57	8	this	this	DET
cana-2432	57	9	research	research	NOUN
cana-2432	57	10	is	be	AUX
cana-2432	57	11	driven	drive	VERB
cana-2432	57	12	by	by	ADP
cana-2432	57	13	the	the	DET
cana-2432	57	14	critical	critical	ADJ
cana-2432	57	15	need	need	NOUN
cana-2432	57	16	for	for	ADP
cana-2432	57	17	precise	precise	ADJ
cana-2432	57	18	and	and	CCONJ
cana-2432	57	19	efficient	efficient	ADJ
cana-2432	57	20	diagnostic	diagnostic	ADJ
cana-2432	57	21	tools	tool	NOUN
cana-2432	57	22	in	in	ADP
cana-2432	57	23	medical	medical	ADJ
cana-2432	57	24	imaging	imaging	NOUN
cana-2432	57	25	,	,	PUNCT
cana-2432	57	26	particularly	particularly	ADV
cana-2432	57	27	for	for	ADP
cana-2432	57	28	lung	lung	NOUN
cana-2432	57	29	diseases	disease	NOUN
cana-2432	57	30	such	such	ADJ
cana-2432	57	31	as	as	ADP
cana-2432	57	32	pneumonia	pneumonia	NOUN
cana-2432	57	33	,	,	PUNCT
cana-2432	57	34	covid-19	covid-19	PROPN
cana-2432	57	35	,	,	PUNCT
cana-2432	57	36	communications	communication	NOUN
cana-2432	57	37	on	on	ADP
cana-2432	57	38	applied	apply	VERB
cana-2432	57	39	nonlinear	nonlinear	ADJ
cana-2432	57	40	analysis	analysis	NOUN
cana-2432	57	41	issn	issn	NOUN
cana-2432	57	42	:	:	PUNCT
cana-2432	57	43	1074	1074	NUM
cana-2432	57	44	-	-	PUNCT
cana-2432	57	45	133x	133x	NUM
cana-2432	57	46	vol	vol	NOUN
cana-2432	57	47	32	32	NUM
cana-2432	57	48	no	no	NOUN
cana-2432	57	49	.	.	PUNCT
cana-2432	58	1	2s	2s	NUM
cana-2432	58	2	(	(	PUNCT
cana-2432	58	3	2025	2025	NUM
cana-2432	58	4	)	)	PUNCT
cana-2432	58	5	426	426	NUM
cana-2432	58	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-2432	58	7	and	and	CCONJ
cana-2432	58	8	other	other	ADJ
cana-2432	58	9	lung	lung	NOUN
cana-2432	58	10	opacities	opacity	NOUN
cana-2432	58	11	.	.	PUNCT
cana-2432	59	1	accurate	accurate	ADJ
cana-2432	59	2	diagnosis	diagnosis	NOUN
cana-2432	59	3	is	be	AUX
cana-2432	59	4	crucial	crucial	ADJ
cana-2432	59	5	for	for	ADP
cana-2432	59	6	effective	effective	ADJ
cana-2432	59	7	treatment	treatment	NOUN
cana-2432	59	8	,	,	PUNCT
cana-2432	59	9	yet	yet	CCONJ
cana-2432	59	10	traditional	traditional	ADJ
cana-2432	59	11	methods	method	NOUN
cana-2432	59	12	relying	rely	VERB
cana-2432	59	13	on	on	ADP
cana-2432	59	14	radiologist	radiologist	NOUN
cana-2432	59	15	interpretation	interpretation	NOUN
cana-2432	59	16	can	can	AUX
cana-2432	59	17	be	be	AUX
cana-2432	59	18	slow	slow	ADJ
cana-2432	59	19	and	and	CCONJ
cana-2432	59	20	variable	variable	ADJ
cana-2432	59	21	.	.	PUNCT
cana-2432	60	1	while	while	SCONJ
cana-2432	60	2	deep	deep	ADJ
cana-2432	60	3	learning	learning	NOUN
cana-2432	60	4	,	,	PUNCT
cana-2432	60	5	especially	especially	ADV
cana-2432	60	6	convolutional	convolutional	ADJ
cana-2432	60	7	neural	neural	ADJ
cana-2432	60	8	networks	network	NOUN
cana-2432	60	9	(	(	PUNCT
cana-2432	60	10	cnns	cnns	PROPN
cana-2432	60	11	)	)	PUNCT
cana-2432	60	12	,	,	PUNCT
cana-2432	60	13	shows	show	VERB
cana-2432	60	14	promise	promise	NOUN
cana-2432	60	15	in	in	ADP
cana-2432	60	16	automating	automate	VERB
cana-2432	60	17	diagnosis	diagnosis	NOUN
cana-2432	60	18	,	,	PUNCT
cana-2432	60	19	challenges	challenge	NOUN
cana-2432	60	20	such	such	ADJ
cana-2432	60	21	as	as	ADP
cana-2432	60	22	high	high	ADJ
cana-2432	60	23	computational	computational	ADJ
cana-2432	60	24	demands	demand	NOUN
cana-2432	60	25	and	and	CCONJ
cana-2432	60	26	the	the	DET
cana-2432	60	27	need	need	NOUN
cana-2432	60	28	for	for	SCONJ
cana-2432	60	29	large	large	ADJ
cana-2432	60	30	datasets	dataset	NOUN
cana-2432	60	31	persist	persist	VERB
cana-2432	60	32	.	.	PUNCT
cana-2432	61	1	this	this	DET
cana-2432	61	2	study	study	NOUN
cana-2432	61	3	proposes	propose	VERB
cana-2432	61	4	a	a	DET
cana-2432	61	5	novel	novel	ADJ
cana-2432	61	6	approach	approach	NOUN
cana-2432	61	7	that	that	PRON
cana-2432	61	8	integrates	integrate	VERB
cana-2432	61	9	wavelet	wavelet	NOUN
cana-2432	61	10	transform	transform	NOUN
cana-2432	61	11	-	-	PUNCT
cana-2432	61	12	based	base	VERB
cana-2432	61	13	feature	feature	NOUN
cana-2432	61	14	extraction	extraction	NOUN
cana-2432	61	15	with	with	ADP
cana-2432	61	16	modified	modify	VERB
cana-2432	61	17	anova	anova	PROPN
cana-2432	61	18	feature	feature	NOUN
cana-2432	61	19	selection	selection	NOUN
cana-2432	61	20	,	,	PUNCT
cana-2432	61	21	and	and	CCONJ
cana-2432	61	22	deep	deep	ADJ
cana-2432	61	23	learning	learning	NOUN
cana-2432	61	24	techniques	technique	NOUN
cana-2432	61	25	to	to	PART
cana-2432	61	26	address	address	VERB
cana-2432	61	27	these	these	DET
cana-2432	61	28	issues	issue	NOUN
cana-2432	61	29	.	.	PUNCT
cana-2432	62	1	wavelet	wavelet	NOUN
cana-2432	62	2	transforms	transform	VERB
cana-2432	62	3	effectively	effectively	ADV
cana-2432	62	4	capture	capture	VERB
cana-2432	62	5	multi	multi	ADJ
cana-2432	62	6	-	-	ADJ
cana-2432	62	7	scale	scale	ADJ
cana-2432	62	8	information	information	NOUN
cana-2432	62	9	from	from	ADP
cana-2432	62	10	lung	lung	PROPN
cana-2432	62	11	x	x	NOUN
cana-2432	62	12	-	-	NOUN
cana-2432	62	13	rays	ray	NOUN
cana-2432	62	14	,	,	PUNCT
cana-2432	62	15	and	and	CCONJ
cana-2432	62	16	bonferroni	bonferroni	NOUN
cana-2432	62	17	adjusted	adjust	VERB
cana-2432	62	18	anova	anova	PROPN
cana-2432	62	19	help	help	NOUN
cana-2432	62	20	in	in	ADP
cana-2432	62	21	selecting	select	VERB
cana-2432	62	22	the	the	DET
cana-2432	62	23	most	most	ADV
cana-2432	62	24	relevant	relevant	ADJ
cana-2432	62	25	features	feature	NOUN
cana-2432	62	26	with	with	ADP
cana-2432	62	27	less	less	ADV
cana-2432	62	28	false	false	ADJ
cana-2432	62	29	positive	positive	ADJ
cana-2432	62	30	rate	rate	NOUN
cana-2432	62	31	,	,	PUNCT
cana-2432	62	32	reducing	reduce	VERB
cana-2432	62	33	data	datum	NOUN
cana-2432	62	34	dimensionality	dimensionality	NOUN
cana-2432	62	35	and	and	CCONJ
cana-2432	62	36	computational	computational	ADJ
cana-2432	62	37	load	load	NOUN
cana-2432	62	38	.	.	PUNCT
cana-2432	63	1	furthermore	furthermore	ADV
cana-2432	63	2	,	,	PUNCT
cana-2432	63	3	transfer	transfer	VERB
cana-2432	63	4	learning	learning	NOUN
cana-2432	63	5	leverages	leverage	NOUN
cana-2432	63	6	pre	pre	ADJ
cana-2432	63	7	-	-	ADJ
cana-2432	63	8	trained	train	VERB
cana-2432	63	9	cnn	cnn	PROPN
cana-2432	63	10	models	model	NOUN
cana-2432	63	11	to	to	PART
cana-2432	63	12	enhance	enhance	VERB
cana-2432	63	13	classification	classification	NOUN
cana-2432	63	14	accuracy	accuracy	NOUN
cana-2432	63	15	and	and	CCONJ
cana-2432	63	16	efficiency	efficiency	NOUN
cana-2432	63	17	.	.	PUNCT
cana-2432	64	1	this	this	DET
cana-2432	64	2	integrated	integrate	VERB
cana-2432	64	3	method	method	NOUN
cana-2432	64	4	aims	aim	VERB
cana-2432	64	5	to	to	PART
cana-2432	64	6	provide	provide	VERB
cana-2432	64	7	a	a	DET
cana-2432	64	8	robust	robust	ADJ
cana-2432	64	9	,	,	PUNCT
cana-2432	64	10	scalable	scalable	ADJ
cana-2432	64	11	,	,	PUNCT
cana-2432	64	12	and	and	CCONJ
cana-2432	64	13	accurate	accurate	ADJ
cana-2432	64	14	tool	tool	NOUN
cana-2432	64	15	for	for	ADP
cana-2432	64	16	lung	lung	NOUN
cana-2432	64	17	x	x	PROPN
cana-2432	64	18	-	-	NOUN
cana-2432	64	19	ray	ray	NOUN
cana-2432	64	20	classification	classification	NOUN
cana-2432	64	21	,	,	PUNCT
cana-2432	64	22	improving	improve	VERB
cana-2432	64	23	diagnostic	diagnostic	ADJ
cana-2432	64	24	consistency	consistency	NOUN
cana-2432	64	25	and	and	CCONJ
cana-2432	64	26	patient	patient	ADJ
cana-2432	64	27	outcomes	outcome	NOUN
cana-2432	64	28	.	.	PUNCT
cana-2432	65	1	4	4	X
cana-2432	65	2	.	.	X
cana-2432	65	3	methodology	methodology	NOUN
cana-2432	65	4	the	the	DET
cana-2432	65	5	proposed	propose	VERB
cana-2432	65	6	methodology	methodology	NOUN
cana-2432	65	7	integrates	integrate	VERB
cana-2432	65	8	wavelet	wavelet	NOUN
cana-2432	65	9	transform	transform	NOUN
cana-2432	65	10	-	-	PUNCT
cana-2432	65	11	based	base	VERB
cana-2432	65	12	feature	feature	NOUN
cana-2432	65	13	extraction	extraction	NOUN
cana-2432	65	14	and	and	CCONJ
cana-2432	65	15	concatenation	concatenation	NOUN
cana-2432	65	16	,	,	PUNCT
cana-2432	65	17	bonferroni	bonferroni	PROPN
cana-2432	65	18	adjusted	adjust	VERB
cana-2432	65	19	anova	anova	PROPN
cana-2432	65	20	feature	feature	NOUN
cana-2432	65	21	selection	selection	NOUN
cana-2432	65	22	,	,	PUNCT
cana-2432	65	23	and	and	CCONJ
cana-2432	65	24	deep	deep	ADJ
cana-2432	65	25	learning	learning	NOUN
cana-2432	65	26	techniques	technique	NOUN
cana-2432	65	27	for	for	ADP
cana-2432	65	28	lung	lung	NOUN
cana-2432	65	29	x	x	PROPN
cana-2432	65	30	-	-	NOUN
cana-2432	65	31	ray	ray	NOUN
cana-2432	65	32	image	image	NOUN
cana-2432	65	33	classification	classification	NOUN
cana-2432	65	34	.	.	PUNCT
cana-2432	66	1	the	the	DET
cana-2432	66	2	following	follow	VERB
cana-2432	66	3	steps	step	NOUN
cana-2432	66	4	outline	outline	VERB
cana-2432	66	5	the	the	DET
cana-2432	66	6	comprehensive	comprehensive	ADJ
cana-2432	66	7	approach	approach	NOUN
cana-2432	66	8	:	:	PUNCT
cana-2432	66	9	4.1	4.1	NUM
cana-2432	66	10	data	datum	NOUN
cana-2432	66	11	acquisition	acquisition	NOUN
cana-2432	66	12	and	and	CCONJ
cana-2432	66	13	preprocessing	preprocessing	NOUN
cana-2432	66	14	:	:	PUNCT
cana-2432	66	15	the	the	DET
cana-2432	66	16	experimental	experimental	ADJ
cana-2432	66	17	dataset	dataset	NOUN
cana-2432	66	18	consists	consist	NOUN
cana-2432	66	19	of	of	ADP
cana-2432	66	20	4,000	4,000	NUM
cana-2432	66	21	lung	lung	NOUN
cana-2432	66	22	x	x	NOUN
cana-2432	66	23	-	-	NOUN
cana-2432	66	24	ray	ray	NOUN
cana-2432	66	25	images	image	NOUN
cana-2432	66	26	sourced	source	VERB
cana-2432	66	27	from	from	ADP
cana-2432	66	28	the	the	DET
cana-2432	66	29	covid-19	covid-19	PROPN
cana-2432	66	30	radiography	radiography	NOUN
cana-2432	66	31	database	database	NOUN
cana-2432	66	32	on	on	ADP
cana-2432	66	33	kaggle	kaggle	PROPN
cana-2432	66	34	[	[	X
cana-2432	66	35	17	17	NUM
cana-2432	66	36	]	]	PUNCT
cana-2432	66	37	.	.	PUNCT
cana-2432	67	1	the	the	DET
cana-2432	67	2	images	image	NOUN
cana-2432	67	3	are	be	AUX
cana-2432	67	4	organized	organize	VERB
cana-2432	67	5	into	into	ADP
cana-2432	67	6	four	four	NUM
cana-2432	67	7	categories	category	NOUN
cana-2432	67	8	:	:	PUNCT
cana-2432	67	9	covid-19	covid-19	PROPN
cana-2432	67	10	pneumonia	pneumonia	NOUN
cana-2432	67	11	(	(	PUNCT
cana-2432	67	12	class	class	NOUN
cana-2432	67	13	0	0	NUM
cana-2432	67	14	)	)	PUNCT
cana-2432	67	15	,	,	PUNCT
cana-2432	67	16	normal	normal	ADJ
cana-2432	67	17	(	(	PUNCT
cana-2432	67	18	class	class	NOUN
cana-2432	67	19	1	1	NUM
cana-2432	67	20	)	)	PUNCT
cana-2432	67	21	,	,	PUNCT
cana-2432	67	22	viral	viral	ADJ
cana-2432	67	23	pneumonia	pneumonia	NOUN
cana-2432	67	24	(	(	PUNCT
cana-2432	67	25	class	class	NOUN
cana-2432	67	26	2	2	NUM
cana-2432	67	27	)	)	PUNCT
cana-2432	67	28	,	,	PUNCT
cana-2432	67	29	and	and	CCONJ
cana-2432	67	30	lung	lung	NOUN
cana-2432	67	31	opacity	opacity	NOUN
cana-2432	67	32	(	(	PUNCT
cana-2432	67	33	class	class	NOUN
cana-2432	67	34	3	3	NUM
cana-2432	67	35	)	)	PUNCT
cana-2432	67	36	,	,	PUNCT
cana-2432	67	37	with	with	ADP
cana-2432	67	38	each	each	DET
cana-2432	67	39	category	category	NOUN
cana-2432	67	40	containing	contain	VERB
cana-2432	67	41	1,000	1,000	NUM
cana-2432	67	42	images	image	NOUN
cana-2432	67	43	,	,	PUNCT
cana-2432	67	44	ensuring	ensure	VERB
cana-2432	67	45	a	a	DET
cana-2432	67	46	balanced	balanced	ADJ
cana-2432	67	47	dataset	dataset	NOUN
cana-2432	67	48	for	for	ADP
cana-2432	67	49	comprehensive	comprehensive	ADJ
cana-2432	67	50	analysis	analysis	NOUN
cana-2432	67	51	and	and	CCONJ
cana-2432	67	52	model	model	NOUN
cana-2432	67	53	training	training	NOUN
cana-2432	67	54	.	.	PUNCT
cana-2432	68	1	all	all	DET
cana-2432	68	2	images	image	NOUN
cana-2432	68	3	are	be	AUX
cana-2432	68	4	standardized	standardize	VERB
cana-2432	68	5	to	to	ADP
cana-2432	68	6	a	a	DET
cana-2432	68	7	resolution	resolution	NOUN
cana-2432	68	8	of	of	ADP
cana-2432	68	9	299x299	299x299	NUM
cana-2432	68	10	pixels	pixel	NOUN
cana-2432	68	11	.	.	PUNCT
cana-2432	69	1	for	for	ADP
cana-2432	69	2	the	the	DET
cana-2432	69	3	purposes	purpose	NOUN
cana-2432	69	4	of	of	ADP
cana-2432	69	5	model	model	NOUN
cana-2432	69	6	training	training	NOUN
cana-2432	69	7	and	and	CCONJ
cana-2432	69	8	evaluation	evaluation	NOUN
cana-2432	69	9	,	,	PUNCT
cana-2432	69	10	the	the	DET
cana-2432	69	11	dataset	dataset	NOUN
cana-2432	69	12	has	have	AUX
cana-2432	69	13	been	be	AUX
cana-2432	69	14	divided	divide	VERB
cana-2432	69	15	into	into	ADP
cana-2432	69	16	training	training	NOUN
cana-2432	69	17	and	and	CCONJ
cana-2432	69	18	testing	testing	NOUN
cana-2432	69	19	sets	set	NOUN
cana-2432	69	20	with	with	ADP
cana-2432	69	21	a	a	DET
cana-2432	69	22	90	90	NUM
cana-2432	69	23	-	-	SYM
cana-2432	69	24	10	10	NUM
cana-2432	69	25	split	split	NOUN
cana-2432	69	26	,	,	PUNCT
cana-2432	69	27	respectively	respectively	ADV
cana-2432	69	28	.	.	PUNCT
cana-2432	70	1	figure	figure	NOUN
cana-2432	70	2	1	1	NUM
cana-2432	70	3	illustrates	illustrate	VERB
cana-2432	70	4	representative	representative	ADJ
cana-2432	70	5	samples	sample	NOUN
cana-2432	70	6	from	from	ADP
cana-2432	70	7	each	each	DET
cana-2432	70	8	category	category	NOUN
cana-2432	70	9	used	use	VERB
cana-2432	70	10	in	in	ADP
cana-2432	70	11	the	the	DET
cana-2432	70	12	analysis	analysis	NOUN
cana-2432	70	13	.	.	PUNCT
cana-2432	71	1	fig.1	fig.1	ADJ
cana-2432	71	2	sample	sample	NOUN
cana-2432	71	3	images	image	NOUN
cana-2432	71	4	from	from	ADP
cana-2432	71	5	lung	lung	NOUN
cana-2432	71	6	x	x	NOUN
cana-2432	71	7	-	-	NOUN
cana-2432	71	8	ray	ray	NOUN
cana-2432	71	9	data	datum	NOUN
cana-2432	71	10	set	set	NOUN
cana-2432	71	11	(	(	PUNCT
cana-2432	71	12	a	a	DET
cana-2432	71	13	)	)	PUNCT
cana-2432	71	14	covid	covid	PROPN
cana-2432	71	15	(	(	PUNCT
cana-2432	71	16	b	b	NOUN
cana-2432	71	17	)	)	PUNCT
cana-2432	71	18	normal	normal	ADJ
cana-2432	71	19	(	(	PUNCT
cana-2432	71	20	c	c	NOUN
cana-2432	71	21	)	)	PUNCT
cana-2432	71	22	viral	viral	ADJ
cana-2432	71	23	pneumonia	pneumonia	NOUN
cana-2432	71	24	(	(	PUNCT
cana-2432	71	25	d	d	NOUN
cana-2432	71	26	)	)	PUNCT
cana-2432	71	27	lung	lung	NOUN
cana-2432	71	28	opacity	opacity	NOUN
cana-2432	71	29	the	the	DET
cana-2432	71	30	preprocessing	preprocessing	NOUN
cana-2432	71	31	of	of	ADP
cana-2432	71	32	the	the	DET
cana-2432	71	33	dataset	dataset	NOUN
cana-2432	71	34	involved	involve	VERB
cana-2432	71	35	two	two	NUM
cana-2432	71	36	main	main	ADJ
cana-2432	71	37	steps	step	NOUN
cana-2432	71	38	:	:	PUNCT
cana-2432	71	39	normalization	normalization	NOUN
cana-2432	71	40	and	and	CCONJ
cana-2432	71	41	resizing	resizing	NOUN
cana-2432	71	42	.	.	PUNCT
cana-2432	72	1	first	first	ADV
cana-2432	72	2	,	,	PUNCT
cana-2432	72	3	the	the	DET
cana-2432	72	4	input	input	NOUN
cana-2432	72	5	images	image	NOUN
cana-2432	72	6	were	be	AUX
cana-2432	72	7	normalized	normalize	VERB
cana-2432	72	8	to	to	PART
cana-2432	72	9	scale	scale	VERB
cana-2432	72	10	the	the	DET
cana-2432	72	11	pixel	pixel	PROPN
cana-2432	72	12	values	value	NOUN
cana-2432	72	13	between	between	ADP
cana-2432	72	14	0	0	NUM
cana-2432	72	15	and	and	CCONJ
cana-2432	72	16	1	1	NUM
cana-2432	72	17	.	.	PUNCT
cana-2432	73	1	this	this	DET
cana-2432	73	2	normalization	normalization	NOUN
cana-2432	73	3	enhances	enhance	VERB
cana-2432	73	4	the	the	DET
cana-2432	73	5	performance	performance	NOUN
cana-2432	73	6	of	of	ADP
cana-2432	73	7	pre	pre	ADJ
cana-2432	73	8	-	-	ADJ
cana-2432	73	9	trained	train	VERB
cana-2432	73	10	models	model	NOUN
cana-2432	73	11	by	by	ADP
cana-2432	73	12	standardizing	standardize	VERB
cana-2432	73	13	the	the	DET
cana-2432	73	14	input	input	NOUN
cana-2432	73	15	data	datum	NOUN
cana-2432	73	16	.	.	PUNCT
cana-2432	74	1	the	the	DET
cana-2432	74	2	normalization	normalization	NOUN
cana-2432	74	3	is	be	AUX
cana-2432	74	4	performed	perform	VERB
cana-2432	74	5	using	use	VERB
cana-2432	74	6	the	the	DET
cana-2432	74	7	formula	formula	NOUN
cana-2432	74	8	:	:	PUNCT
cana-2432	75	1	𝑋𝑖	𝑋𝑖	NOUN
cana-2432	75	2	=	=	PUNCT
cana-2432	75	3	𝑋𝑖	𝑋𝑖	PROPN
cana-2432	75	4	max	max	PROPN
cana-2432	75	5	(	(	PUNCT
cana-2432	75	6	𝑋	𝑋	PROPN
cana-2432	75	7	)	)	PUNCT
cana-2432	75	8	(	(	PUNCT
cana-2432	75	9	1	1	X
cana-2432	75	10	)	)	PUNCT
cana-2432	75	11	communications	communication	NOUN
cana-2432	75	12	on	on	ADP
cana-2432	75	13	applied	apply	VERB
cana-2432	75	14	nonlinear	nonlinear	ADJ
cana-2432	75	15	analysis	analysis	NOUN
cana-2432	75	16	issn	issn	NOUN
cana-2432	75	17	:	:	PUNCT
cana-2432	75	18	1074	1074	NUM
cana-2432	75	19	-	-	PUNCT
cana-2432	75	20	133x	133x	NUM
cana-2432	75	21	vol	vol	NOUN
cana-2432	75	22	32	32	NUM
cana-2432	75	23	no	no	NOUN
cana-2432	75	24	.	.	PUNCT
cana-2432	76	1	2s	2s	NUM
cana-2432	76	2	(	(	PUNCT
cana-2432	76	3	2025	2025	NUM
cana-2432	76	4	)	)	PUNCT
cana-2432	76	5	427	427	NUM
cana-2432	76	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-2432	76	7	where	where	SCONJ
cana-2432	76	8	𝑋𝑖	𝑋𝑖	PROPN
cana-2432	76	9	represents	represent	VERB
cana-2432	76	10	an	an	DET
cana-2432	76	11	individual	individual	ADJ
cana-2432	76	12	pixel	pixel	NOUN
cana-2432	76	13	value	value	NOUN
cana-2432	76	14	and	and	CCONJ
cana-2432	76	15	max(x	max(x	PROPN
cana-2432	76	16	)	)	PUNCT
cana-2432	76	17	is	be	AUX
cana-2432	76	18	the	the	DET
cana-2432	76	19	maximum	maximum	ADJ
cana-2432	76	20	pixel	pixel	NOUN
cana-2432	76	21	value	value	NOUN
cana-2432	76	22	in	in	ADP
cana-2432	76	23	the	the	DET
cana-2432	76	24	image	image	NOUN
cana-2432	76	25	.	.	PUNCT
cana-2432	77	1	following	follow	VERB
cana-2432	77	2	normalization	normalization	NOUN
cana-2432	77	3	,	,	PUNCT
cana-2432	77	4	the	the	DET
cana-2432	77	5	images	image	NOUN
cana-2432	77	6	were	be	AUX
cana-2432	77	7	resized	resize	VERB
cana-2432	77	8	to	to	ADP
cana-2432	77	9	224x224	224x224	NUM
cana-2432	77	10	pixels	pixel	NOUN
cana-2432	77	11	to	to	PART
cana-2432	77	12	match	match	VERB
cana-2432	77	13	the	the	DET
cana-2432	77	14	input	input	NOUN
cana-2432	77	15	dimensions	dimension	NOUN
cana-2432	77	16	required	require	VERB
cana-2432	77	17	by	by	ADP
cana-2432	77	18	the	the	DET
cana-2432	77	19	pre	pre	ADJ
cana-2432	77	20	-	-	ADJ
cana-2432	77	21	trained	train	VERB
cana-2432	77	22	models	model	NOUN
cana-2432	77	23	.	.	PUNCT
cana-2432	78	1	4.2	4.2	NUM
cana-2432	78	2	wavelet	wavelet	NOUN
cana-2432	78	3	transform	transform	NOUN
cana-2432	78	4	-	-	PUNCT
cana-2432	78	5	based	base	VERB
cana-2432	78	6	feature	feature	NOUN
cana-2432	78	7	extraction	extraction	NOUN
cana-2432	78	8	and	and	CCONJ
cana-2432	78	9	concatenation	concatenation	NOUN
cana-2432	78	10	:	:	PUNCT
cana-2432	78	11	the	the	DET
cana-2432	78	12	haar	haar	PROPN
cana-2432	78	13	wavelet	wavelet	PROPN
cana-2432	78	14	transform	transform	NOUN
cana-2432	78	15	[	[	X
cana-2432	78	16	18	18	NUM
cana-2432	78	17	]	]	PUNCT
cana-2432	78	18	is	be	AUX
cana-2432	78	19	a	a	DET
cana-2432	78	20	type	type	NOUN
cana-2432	78	21	of	of	ADP
cana-2432	78	22	discrete	discrete	ADJ
cana-2432	78	23	wavelet	wavelet	NOUN
cana-2432	78	24	transform	transform	NOUN
cana-2432	78	25	(	(	PUNCT
cana-2432	78	26	dwt	dwt	NOUN
cana-2432	78	27	)	)	PUNCT
cana-2432	78	28	that	that	PRON
cana-2432	78	29	is	be	AUX
cana-2432	78	30	particularly	particularly	ADV
cana-2432	78	31	effective	effective	ADJ
cana-2432	78	32	for	for	ADP
cana-2432	78	33	image	image	NOUN
cana-2432	78	34	processing	processing	NOUN
cana-2432	78	35	tasks	task	NOUN
cana-2432	78	36	due	due	ADP
cana-2432	78	37	to	to	ADP
cana-2432	78	38	its	its	PRON
cana-2432	78	39	simplicity	simplicity	NOUN
cana-2432	78	40	and	and	CCONJ
cana-2432	78	41	efficiency	efficiency	NOUN
cana-2432	78	42	.	.	PUNCT
cana-2432	79	1	the	the	DET
cana-2432	79	2	haar	haar	PROPN
cana-2432	79	3	wavelet	wavelet	NOUN
cana-2432	79	4	decomposes	decompose	VERB
cana-2432	79	5	an	an	DET
cana-2432	79	6	image	image	NOUN
cana-2432	79	7	into	into	ADP
cana-2432	79	8	different	different	ADJ
cana-2432	79	9	frequency	frequency	NOUN
cana-2432	79	10	components	component	NOUN
cana-2432	79	11	,	,	PUNCT
cana-2432	79	12	allowing	allow	VERB
cana-2432	79	13	the	the	DET
cana-2432	79	14	capture	capture	NOUN
cana-2432	79	15	of	of	ADP
cana-2432	79	16	both	both	CCONJ
cana-2432	79	17	spatial	spatial	ADJ
cana-2432	79	18	and	and	CCONJ
cana-2432	79	19	frequency	frequency	NOUN
cana-2432	79	20	information	information	NOUN
cana-2432	79	21	.	.	PUNCT
cana-2432	80	1	this	this	DET
cana-2432	80	2	decomposition	decomposition	NOUN
cana-2432	80	3	helps	help	VERB
cana-2432	80	4	in	in	ADP
cana-2432	80	5	identifying	identify	VERB
cana-2432	80	6	various	various	ADJ
cana-2432	80	7	levels	level	NOUN
cana-2432	80	8	of	of	ADP
cana-2432	80	9	detail	detail	NOUN
cana-2432	80	10	within	within	ADP
cana-2432	80	11	the	the	DET
cana-2432	80	12	image	image	NOUN
cana-2432	80	13	,	,	PUNCT
cana-2432	80	14	which	which	PRON
cana-2432	80	15	are	be	AUX
cana-2432	80	16	essential	essential	ADJ
cana-2432	80	17	for	for	ADP
cana-2432	80	18	distinguishing	distinguish	VERB
cana-2432	80	19	between	between	ADP
cana-2432	80	20	different	different	ADJ
cana-2432	80	21	classes	class	NOUN
cana-2432	80	22	of	of	ADP
cana-2432	80	23	lung	lung	NOUN
cana-2432	80	24	conditions	condition	NOUN
cana-2432	80	25	.	.	PUNCT
cana-2432	81	1	each	each	DET
cana-2432	81	2	x	x	ADJ
cana-2432	81	3	-	-	NOUN
cana-2432	81	4	ray	ray	NOUN
cana-2432	81	5	image	image	NOUN
cana-2432	81	6	from	from	ADP
cana-2432	81	7	the	the	DET
cana-2432	81	8	dataset	dataset	NOUN
cana-2432	81	9	is	be	AUX
cana-2432	81	10	initially	initially	ADV
cana-2432	81	11	decomposed	decompose	VERB
cana-2432	81	12	into	into	ADP
cana-2432	81	13	four	four	NUM
cana-2432	81	14	sub	sub	NOUN
cana-2432	81	15	-	-	NOUN
cana-2432	81	16	bands	band	NOUN
cana-2432	81	17	using	use	VERB
cana-2432	81	18	two	two	NUM
cana-2432	81	19	level	level	NOUN
cana-2432	81	20	‘	'	PUNCT
cana-2432	81	21	haar	haar	NOUN
cana-2432	81	22	’	'	PUNCT
cana-2432	81	23	wavelet	wavelet	NOUN
cana-2432	81	24	decomposition	decomposition	NOUN
cana-2432	81	25	.	.	PUNCT
cana-2432	82	1	the	the	DET
cana-2432	82	2	first	first	ADJ
cana-2432	82	3	level	level	NOUN
cana-2432	82	4	haar	haar	X
cana-2432	82	5	wavelet	wavelet	NOUN
cana-2432	82	6	transform	transform	NOUN
cana-2432	82	7	decomposes	decompose	NOUN
cana-2432	82	8	x	x	PUNCT
cana-2432	82	9	into	into	ADP
cana-2432	82	10	four	four	NUM
cana-2432	82	11	subbands	subband	NOUN
cana-2432	82	12	:	:	PUNCT
cana-2432	82	13	approximation	approximation	NOUN
cana-2432	82	14	(	(	PUNCT
cana-2432	82	15	𝐴(1	𝐴(1	NOUN
cana-2432	82	16	)	)	PUNCT
cana-2432	82	17	)	)	PUNCT
cana-2432	82	18	,	,	PUNCT
cana-2432	82	19	horizontal	horizontal	ADJ
cana-2432	82	20	detail(𝐻(1	detail(𝐻(1	NOUN
cana-2432	82	21	)	)	PUNCT
cana-2432	82	22	)	)	PUNCT
cana-2432	82	23	,	,	PUNCT
cana-2432	82	24	vertical	vertical	ADJ
cana-2432	82	25	detail(𝑉(1	detail(𝑉(1	NOUN
cana-2432	82	26	)	)	PUNCT
cana-2432	82	27	)	)	PUNCT
cana-2432	82	28	,	,	PUNCT
cana-2432	82	29	and	and	CCONJ
cana-2432	82	30	diagonal	diagonal	ADJ
cana-2432	82	31	detail(𝐷(1	detail(𝐷(1	NOUN
cana-2432	82	32	)	)	PUNCT
cana-2432	82	33	)	)	PUNCT
cana-2432	82	34	.	.	PUNCT
cana-2432	83	1	the	the	PRON
cana-2432	83	2	(	(	PUNCT
cana-2432	83	3	𝐴(1	𝐴(1	NOUN
cana-2432	83	4	)	)	PUNCT
cana-2432	83	5	)	)	PUNCT
cana-2432	83	6	sub	sub	ADJ
cana-2432	83	7	-	-	ADJ
cana-2432	83	8	band	band	NOUN
cana-2432	83	9	captures	capture	VERB
cana-2432	83	10	the	the	DET
cana-2432	83	11	low	low	ADJ
cana-2432	83	12	-	-	PUNCT
cana-2432	83	13	frequency	frequency	NOUN
cana-2432	83	14	information	information	NOUN
cana-2432	83	15	,	,	PUNCT
cana-2432	83	16	representing	represent	VERB
cana-2432	83	17	the	the	DET
cana-2432	83	18	coarse	coarse	ADJ
cana-2432	83	19	approximation	approximation	NOUN
cana-2432	83	20	of	of	ADP
cana-2432	83	21	the	the	DET
cana-2432	83	22	image	image	NOUN
cana-2432	83	23	.	.	PUNCT
cana-2432	84	1	in	in	ADP
cana-2432	84	2	contrast	contrast	NOUN
cana-2432	84	3	,	,	PUNCT
cana-2432	84	4	the(𝐻(1	the(𝐻(1	NUM
cana-2432	84	5	)	)	PUNCT
cana-2432	84	6	)	)	PUNCT
cana-2432	84	7	,	,	PUNCT
cana-2432	84	8	(	(	PUNCT
cana-2432	84	9	𝑉(1	𝑉(1	X
cana-2432	84	10	)	)	PUNCT
cana-2432	84	11	)	)	PUNCT
cana-2432	84	12	,	,	PUNCT
cana-2432	84	13	and	and	CCONJ
cana-2432	84	14	(	(	PUNCT
cana-2432	84	15	𝐷(1	𝐷(1	NUM
cana-2432	84	16	)	)	PUNCT
cana-2432	84	17	)	)	PUNCT
cana-2432	84	18	sub	sub	NOUN
cana-2432	84	19	-	-	ADJ
cana-2432	84	20	bands	band	NOUN
cana-2432	84	21	contain	contain	VERB
cana-2432	84	22	highfrequency	highfrequency	NOUN
cana-2432	84	23	information	information	NOUN
cana-2432	84	24	,	,	PUNCT
cana-2432	84	25	detailing	detail	VERB
cana-2432	84	26	the	the	DET
cana-2432	84	27	edges	edge	NOUN
cana-2432	84	28	and	and	CCONJ
cana-2432	84	29	textures	texture	NOUN
cana-2432	84	30	of	of	ADP
cana-2432	84	31	the	the	DET
cana-2432	84	32	image	image	NOUN
cana-2432	84	33	.	.	PUNCT
cana-2432	85	1	the	the	DET
cana-2432	85	2	extracted	extract	VERB
cana-2432	85	3	coefficients	coefficient	NOUN
cana-2432	85	4	from	from	ADP
cana-2432	85	5	these	these	DET
cana-2432	85	6	sub	sub	NOUN
cana-2432	85	7	-	-	ADJ
cana-2432	85	8	bands	band	NOUN
cana-2432	85	9	encapsulate	encapsulate	VERB
cana-2432	85	10	the	the	DET
cana-2432	85	11	image	image	NOUN
cana-2432	85	12	's	's	PART
cana-2432	85	13	structure	structure	NOUN
cana-2432	85	14	and	and	CCONJ
cana-2432	85	15	texture	texture	NOUN
cana-2432	85	16	across	across	ADP
cana-2432	85	17	different	different	ADJ
cana-2432	85	18	scales	scale	NOUN
cana-2432	85	19	and	and	CCONJ
cana-2432	85	20	orientations	orientation	NOUN
cana-2432	85	21	.	.	PUNCT
cana-2432	86	1	it	it	PRON
cana-2432	86	2	is	be	AUX
cana-2432	86	3	calculated	calculate	VERB
cana-2432	86	4	as	as	ADP
cana-2432	86	5	:	:	PUNCT
cana-2432	86	6	𝐴(1	𝐴(1	NUM
cana-2432	86	7	)	)	PUNCT
cana-2432	86	8	=	=	VERB
cana-2432	87	1	𝑋2𝑖−1,2𝑗−1+𝑋2𝑖−1,2𝑗+𝑋2𝑖,2𝑗−1+𝑋2𝑖,2𝑗	𝑋2𝑖−1,2𝑗−1+𝑋2𝑖−1,2𝑗+𝑋2𝑖,2𝑗−1+𝑋2𝑖,2𝑗	ADJ
cana-2432	87	2	4	4	NUM
cana-2432	87	3	(	(	PUNCT
cana-2432	87	4	2	2	NUM
cana-2432	87	5	)	)	PUNCT
cana-2432	87	6	𝐻(1	𝐻(1	PROPN
cana-2432	87	7	)	)	PUNCT
cana-2432	87	8	=	=	SYM
cana-2432	87	9	𝑋2𝑖−1,2𝑗−1−𝑋2𝑖−1,2𝑗+𝑋2𝑖,2𝑗−1−𝑋2𝑖,2𝑗	𝑋2𝑖−1,2𝑗−1−𝑋2𝑖−1,2𝑗+𝑋2𝑖,2𝑗−1−𝑋2𝑖,2𝑗	X
cana-2432	87	10	4	4	NUM
cana-2432	87	11	(	(	PUNCT
cana-2432	87	12	3	3	NUM
cana-2432	87	13	)	)	PUNCT
cana-2432	87	14	𝑉(1	𝑉(1	NOUN
cana-2432	87	15	)	)	PUNCT
cana-2432	87	16	=	=	SYM
cana-2432	87	17	𝑋2𝑖−1,2𝑗−1+𝑋2𝑖−1,2𝑗−𝑋2𝑖,2𝑗−1−𝑋2𝑖,2𝑗	𝑋2𝑖−1,2𝑗−1+𝑋2𝑖−1,2𝑗−𝑋2𝑖,2𝑗−1−𝑋2𝑖,2𝑗	X
cana-2432	87	18	4	4	NUM
cana-2432	87	19	(	(	PUNCT
cana-2432	87	20	4	4	NUM
cana-2432	87	21	)	)	PUNCT
cana-2432	87	22	𝐷(1	𝐷(1	NUM
cana-2432	87	23	)	)	PUNCT
cana-2432	87	24	=	=	VERB
cana-2432	87	25	𝑋2𝑖−1,2𝑗−1−𝑋2𝑖−1,2𝑗−𝑋2𝑖,2𝑗−1+𝑋2𝑖,2𝑗	𝑋2𝑖−1,2𝑗−1−𝑋2𝑖−1,2𝑗−𝑋2𝑖,2𝑗−1+𝑋2𝑖,2𝑗	NOUN
cana-2432	87	26	4	4	NUM
cana-2432	87	27	(	(	PUNCT
cana-2432	87	28	5	5	NUM
cana-2432	87	29	)	)	PUNCT
cana-2432	87	30	here	here	ADV
cana-2432	87	31	,	,	PUNCT
cana-2432	87	32	the	the	DET
cana-2432	87	33	indices	index	NOUN
cana-2432	87	34	i	i	PRON
cana-2432	87	35	and	and	CCONJ
cana-2432	87	36	j	j	PROPN
cana-2432	87	37	run	run	VERB
cana-2432	87	38	from	from	ADP
cana-2432	87	39	1	1	NUM
cana-2432	87	40	to	to	ADP
cana-2432	87	41	m/2	m/2	NUM
cana-2432	87	42	and	and	CCONJ
cana-2432	87	43	n/2	n/2	PROPN
cana-2432	87	44	respectively	respectively	ADV
cana-2432	87	45	.	.	PUNCT
cana-2432	88	1	the	the	DET
cana-2432	88	2	second	second	ADJ
cana-2432	88	3	level	level	NOUN
cana-2432	88	4	transform	transform	NOUN
cana-2432	88	5	is	be	AUX
cana-2432	88	6	calculated	calculate	VERB
cana-2432	88	7	as	as	ADP
cana-2432	88	8	:	:	PUNCT
cana-2432	88	9	𝐴(2	𝐴(2	PUNCT
cana-2432	88	10	)	)	PUNCT
cana-2432	88	11	=	=	SYM
cana-2432	88	12	𝐴	𝐴	PROPN
cana-2432	88	13	2𝑖−1,2𝑗−1	2𝑖−1,2𝑗−1	PROPN
cana-2432	88	14	(	(	PUNCT
cana-2432	88	15	1	1	NUM
cana-2432	88	16	)	)	PUNCT
cana-2432	88	17	+	+	NOUN
cana-2432	89	1	𝐴	𝐴	NOUN
cana-2432	89	2	2𝑖−1,2𝑗	2𝑖−1,2𝑗	NUM
cana-2432	89	3	(	(	PUNCT
cana-2432	89	4	1	1	NUM
cana-2432	89	5	)	)	PUNCT
cana-2432	89	6	+	+	NOUN
cana-2432	89	7	𝐴	𝐴	NOUN
cana-2432	89	8	2𝑖,2𝑗−1	2𝑖,2𝑗−1	NUM
cana-2432	89	9	(	(	PUNCT
cana-2432	89	10	1	1	NUM
cana-2432	89	11	)	)	PUNCT
cana-2432	89	12	+	+	NOUN
cana-2432	89	13	𝐴	𝐴	NOUN
cana-2432	89	14	2𝑖,2𝑗	2𝑖,2𝑗	NUM
cana-2432	89	15	(	(	PUNCT
cana-2432	89	16	1	1	NUM
cana-2432	89	17	)	)	PUNCT
cana-2432	89	18	4	4	NUM
cana-2432	89	19	(	(	PUNCT
cana-2432	89	20	6	6	NUM
cana-2432	89	21	)	)	PUNCT
cana-2432	89	22	𝐻(2	𝐻(2	NUM
cana-2432	89	23	)	)	PUNCT
cana-2432	89	24	=	=	SYM
cana-2432	89	25	𝐴	𝐴	PROPN
cana-2432	89	26	2𝑖−1,2𝑗−1	2𝑖−1,2𝑗−1	PROPN
cana-2432	89	27	(	(	PUNCT
cana-2432	89	28	1	1	NUM
cana-2432	89	29	)	)	PUNCT
cana-2432	89	30	−𝐴2𝑖−1,2𝑗	−𝐴2𝑖−1,2𝑗	PROPN
cana-2432	89	31	(	(	PUNCT
cana-2432	89	32	1	1	X
cana-2432	89	33	)	)	PUNCT
cana-2432	90	1	+	+	PROPN
cana-2432	90	2	𝐴2𝑖,2𝑗−1	𝐴2𝑖,2𝑗−1	X
cana-2432	90	3	(	(	PUNCT
cana-2432	90	4	1	1	X
cana-2432	90	5	)	)	PUNCT
cana-2432	90	6	−𝐴	−𝐴	NOUN
cana-2432	90	7	2𝑖,2𝑗	2𝑖,2𝑗	NUM
cana-2432	90	8	(	(	PUNCT
cana-2432	90	9	1	1	NUM
cana-2432	90	10	)	)	PUNCT
cana-2432	90	11	4	4	NUM
cana-2432	90	12	(	(	PUNCT
cana-2432	90	13	7	7	NUM
cana-2432	90	14	)	)	PUNCT
cana-2432	90	15	𝑉(2	𝑉(2	NUM
cana-2432	90	16	)	)	PUNCT
cana-2432	90	17	=	=	SYM
cana-2432	90	18	𝐴	𝐴	PROPN
cana-2432	90	19	2𝑖−1,2𝑗−1	2𝑖−1,2𝑗−1	PROPN
cana-2432	90	20	(	(	PUNCT
cana-2432	90	21	1	1	NUM
cana-2432	90	22	)	)	PUNCT
cana-2432	90	23	+	+	NOUN
cana-2432	90	24	𝐴	𝐴	NOUN
cana-2432	90	25	2𝑖−1,2𝑗	2𝑖−1,2𝑗	NUM
cana-2432	90	26	(	(	PUNCT
cana-2432	90	27	1	1	NUM
cana-2432	90	28	)	)	PUNCT
cana-2432	90	29	−𝐴2𝑖,2𝑗−1	−𝐴2𝑖,2𝑗−1	NOUN
cana-2432	90	30	(	(	PUNCT
cana-2432	90	31	1	1	X
cana-2432	90	32	)	)	PUNCT
cana-2432	90	33	−𝐴	−𝐴	NOUN
cana-2432	90	34	2𝑖,2𝑗	2𝑖,2𝑗	NUM
cana-2432	90	35	(	(	PUNCT
cana-2432	90	36	1	1	NUM
cana-2432	90	37	)	)	PUNCT
cana-2432	90	38	4	4	NUM
cana-2432	90	39	(	(	PUNCT
cana-2432	90	40	8)	8)	NUM
cana-2432	90	41	𝐷(2	𝐷(2	NOUN
cana-2432	90	42	)	)	PUNCT
cana-2432	90	43	=	=	SYM
cana-2432	90	44	𝐴	𝐴	PROPN
cana-2432	90	45	2𝑖−1,2𝑗−1	2𝑖−1,2𝑗−1	PROPN
cana-2432	90	46	(	(	PUNCT
cana-2432	90	47	1	1	NUM
cana-2432	90	48	)	)	PUNCT
cana-2432	90	49	−𝐴2𝑖−1,2𝑗	−𝐴2𝑖−1,2𝑗	PROPN
cana-2432	90	50	(	(	PUNCT
cana-2432	90	51	1	1	X
cana-2432	90	52	)	)	PUNCT
cana-2432	90	53	−𝐴	−𝐴	PROPN
cana-2432	90	54	2𝑖,2𝑗−1	2𝑖,2𝑗−1	NUM
cana-2432	90	55	(	(	PUNCT
cana-2432	90	56	1	1	NUM
cana-2432	90	57	)	)	PUNCT
cana-2432	90	58	+	+	NOUN
cana-2432	90	59	𝐴	𝐴	NOUN
cana-2432	90	60	2𝑖,2𝑗	2𝑖,2𝑗	NUM
cana-2432	90	61	(	(	PUNCT
cana-2432	90	62	1	1	NUM
cana-2432	90	63	)	)	PUNCT
cana-2432	90	64	4	4	NUM
cana-2432	90	65	(	(	PUNCT
cana-2432	90	66	9	9	NUM
cana-2432	90	67	)	)	PUNCT
cana-2432	90	68	to	to	PART
cana-2432	90	69	form	form	VERB
cana-2432	90	70	a	a	DET
cana-2432	90	71	comprehensive	comprehensive	ADJ
cana-2432	90	72	feature	feature	NOUN
cana-2432	90	73	set	set	NOUN
cana-2432	90	74	,	,	PUNCT
cana-2432	90	75	the	the	DET
cana-2432	90	76	coefficients	coefficient	NOUN
cana-2432	90	77	from	from	ADP
cana-2432	90	78	the	the	DET
cana-2432	90	79	ll	ll	NOUN
cana-2432	90	80	,	,	PUNCT
cana-2432	90	81	lh	lh	PROPN
cana-2432	90	82	,	,	PUNCT
cana-2432	90	83	hl	hl	NOUN
cana-2432	90	84	,	,	PUNCT
cana-2432	90	85	and	and	CCONJ
cana-2432	90	86	hh	hh	VERB
cana-2432	90	87	sub	sub	NOUN
cana-2432	90	88	-	-	ADJ
cana-2432	90	89	bands	band	NOUN
cana-2432	90	90	are	be	AUX
cana-2432	90	91	concatenated	concatenate	VERB
cana-2432	90	92	.	.	PUNCT
cana-2432	91	1	this	this	PRON
cana-2432	91	2	,	,	PUNCT
cana-2432	91	3	results	result	VERB
cana-2432	91	4	in	in	ADP
cana-2432	91	5	a	a	DET
cana-2432	91	6	unified	unified	ADJ
cana-2432	91	7	feature	feature	NOUN
cana-2432	91	8	vector	vector	NOUN
cana-2432	91	9	comprising	comprise	VERB
cana-2432	91	10	32768	32768	NUM
cana-2432	91	11	features	feature	NOUN
cana-2432	91	12	.	.	PUNCT
cana-2432	92	1	this	this	DET
cana-2432	92	2	extensive	extensive	ADJ
cana-2432	92	3	feature	feature	NOUN
cana-2432	92	4	set	set	NOUN
cana-2432	92	5	provides	provide	VERB
cana-2432	92	6	a	a	DET
cana-2432	92	7	holistic	holistic	ADJ
cana-2432	92	8	representation	representation	NOUN
cana-2432	92	9	of	of	ADP
cana-2432	92	10	the	the	DET
cana-2432	92	11	image	image	NOUN
cana-2432	92	12	,	,	PUNCT
cana-2432	92	13	encompassing	encompass	VERB
cana-2432	92	14	both	both	CCONJ
cana-2432	92	15	the	the	DET
cana-2432	92	16	overall	overall	ADJ
cana-2432	92	17	shape	shape	NOUN
cana-2432	92	18	and	and	CCONJ
cana-2432	92	19	structure	structure	NOUN
cana-2432	92	20	of	of	ADP
cana-2432	92	21	the	the	DET
cana-2432	92	22	lungs	lung	NOUN
cana-2432	92	23	(	(	PUNCT
cana-2432	92	24	from	from	ADP
cana-2432	92	25	the	the	DET
cana-2432	92	26	ll	ll	NOUN
cana-2432	92	27	coefficients	coefficient	NOUN
cana-2432	92	28	)	)	PUNCT
cana-2432	92	29	and	and	CCONJ
cana-2432	92	30	the	the	DET
cana-2432	92	31	detailed	detailed	ADJ
cana-2432	92	32	edges	edge	NOUN
cana-2432	92	33	and	and	CCONJ
cana-2432	92	34	textures	texture	NOUN
cana-2432	92	35	(	(	PUNCT
cana-2432	92	36	from	from	ADP
cana-2432	92	37	the	the	DET
cana-2432	92	38	lh	lh	PROPN
cana-2432	92	39	,	,	PUNCT
cana-2432	92	40	communications	communication	NOUN
cana-2432	92	41	on	on	ADP
cana-2432	92	42	applied	apply	VERB
cana-2432	92	43	nonlinear	nonlinear	ADJ
cana-2432	92	44	analysis	analysis	NOUN
cana-2432	92	45	issn	issn	NOUN
cana-2432	92	46	:	:	PUNCT
cana-2432	92	47	1074	1074	NUM
cana-2432	92	48	-	-	PUNCT
cana-2432	92	49	133x	133x	NUM
cana-2432	92	50	vol	vol	NOUN
cana-2432	92	51	32	32	NUM
cana-2432	92	52	no	no	NOUN
cana-2432	92	53	.	.	PUNCT
cana-2432	93	1	2s	2s	NUM
cana-2432	93	2	(	(	PUNCT
cana-2432	93	3	2025	2025	NUM
cana-2432	93	4	)	)	PUNCT
cana-2432	93	5	428	428	NUM
cana-2432	93	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-2432	93	7	hl	hl	NOUN
cana-2432	93	8	,	,	PUNCT
cana-2432	93	9	and	and	CCONJ
cana-2432	93	10	hh	hh	PROPN
cana-2432	93	11	coefficients	coefficient	NOUN
cana-2432	93	12	)	)	PUNCT
cana-2432	93	13	.	.	PUNCT
cana-2432	94	1	this	this	DET
cana-2432	94	2	comprehensive	comprehensive	ADJ
cana-2432	94	3	approach	approach	NOUN
cana-2432	94	4	ensures	ensure	VERB
cana-2432	94	5	that	that	SCONJ
cana-2432	94	6	the	the	DET
cana-2432	94	7	feature	feature	NOUN
cana-2432	94	8	set	set	NOUN
cana-2432	94	9	includes	include	VERB
cana-2432	94	10	a	a	DET
cana-2432	94	11	wide	wide	ADJ
cana-2432	94	12	range	range	NOUN
cana-2432	94	13	of	of	ADP
cana-2432	94	14	information	information	NOUN
cana-2432	94	15	,	,	PUNCT
cana-2432	94	16	making	make	VERB
cana-2432	94	17	it	it	PRON
cana-2432	94	18	robust	robust	ADJ
cana-2432	94	19	for	for	ADP
cana-2432	94	20	further	further	ADJ
cana-2432	94	21	analysis	analysis	NOUN
cana-2432	94	22	or	or	CCONJ
cana-2432	94	23	machine	machine	NOUN
cana-2432	94	24	learning	learning	NOUN
cana-2432	94	25	tasks	task	NOUN
cana-2432	94	26	.	.	PUNCT
cana-2432	95	1	the	the	DET
cana-2432	95	2	concatenation	concatenation	NOUN
cana-2432	95	3	of	of	ADP
cana-2432	95	4	wavelet	wavelet	NOUN
cana-2432	95	5	coefficients	coefficient	NOUN
cana-2432	95	6	involves	involve	VERB
cana-2432	95	7	combining	combine	VERB
cana-2432	95	8	all	all	DET
cana-2432	95	9	the	the	DET
cana-2432	95	10	coefficients	coefficient	NOUN
cana-2432	95	11	obtained	obtain	VERB
cana-2432	95	12	from	from	ADP
cana-2432	95	13	the	the	DET
cana-2432	95	14	decomposition	decomposition	NOUN
cana-2432	95	15	into	into	ADP
cana-2432	95	16	a	a	DET
cana-2432	95	17	single	single	ADJ
cana-2432	95	18	feature	feature	NOUN
cana-2432	95	19	vector	vector	NOUN
cana-2432	95	20	.	.	PUNCT
cana-2432	96	1	discrete	discrete	ADJ
cana-2432	96	2	wavelet	wavelet	NOUN
cana-2432	96	3	transform	transform	NOUN
cana-2432	96	4	is	be	AUX
cana-2432	96	5	applied	apply	VERB
cana-2432	96	6	on	on	ADP
cana-2432	96	7	each	each	DET
cana-2432	96	8	feature	feature	NOUN
cana-2432	96	9	to	to	PART
cana-2432	96	10	obtain	obtain	VERB
cana-2432	96	11	a	a	DET
cana-2432	96	12	set	set	NOUN
cana-2432	96	13	of	of	ADP
cana-2432	96	14	coefficients	coefficient	NOUN
cana-2432	96	15	for	for	ADP
cana-2432	96	16	each	each	DET
cana-2432	96	17	feature	feature	NOUN
cana-2432	96	18	.	.	PUNCT
cana-2432	97	1	mathematically	mathematically	ADV
cana-2432	97	2	,	,	PUNCT
cana-2432	97	3	for	for	ADP
cana-2432	97	4	feature	feature	NOUN
cana-2432	97	5	i	i	PRON
cana-2432	97	6	and	and	CCONJ
cana-2432	97	7	level	level	ADJ
cana-2432	97	8	j	j	PROPN
cana-2432	97	9	:	:	PUNCT
cana-2432	97	10	𝑐𝑜𝑒𝑓𝑓𝑠𝑖	𝑐𝑜𝑒𝑓𝑓𝑠𝑖	NOUN
cana-2432	97	11	=	=	PUNCT
cana-2432	98	1	[	[	X
cana-2432	98	2	𝐴𝑖,1	𝐴𝑖,1	X
cana-2432	98	3	,	,	PUNCT
cana-2432	98	4	𝐷𝑖,1	𝐷𝑖,1	NOUN
cana-2432	98	5	,	,	PUNCT
cana-2432	98	6	𝐴𝑖,2	𝐴𝑖,2	PROPN
cana-2432	98	7	,	,	PUNCT
cana-2432	98	8	𝐷𝑖,2	𝐷𝑖,2	PROPN
cana-2432	98	9	,	,	PUNCT
cana-2432	98	10	…	…	PUNCT
cana-2432	98	11	.	.	PUNCT
cana-2432	98	12	.	.	PUNCT
cana-2432	99	1	𝐴𝑖,𝑗	𝐴𝑖,𝑗	PROPN
cana-2432	99	2	,	,	PUNCT
cana-2432	99	3	𝐷𝑖,𝑗	𝐷𝑖,𝑗	PROPN
cana-2432	99	4	]	]	PUNCT
cana-2432	99	5	(	(	PUNCT
cana-2432	99	6	10	10	NUM
cana-2432	99	7	)	)	PUNCT
cana-2432	99	8	for	for	ADP
cana-2432	99	9	all	all	DET
cana-2432	99	10	features	feature	NOUN
cana-2432	99	11	,	,	PUNCT
cana-2432	99	12	the	the	DET
cana-2432	99	13	transformed	transform	VERB
cana-2432	99	14	dataset	dataset	NOUN
cana-2432	99	15	𝑋𝑡𝑟𝑎𝑛𝑠𝑓𝑜𝑟𝑚𝑒𝑑	𝑋𝑡𝑟𝑎𝑛𝑠𝑓𝑜𝑟𝑚𝑒𝑑	PROPN
cana-2432	99	16	is	be	AUX
cana-2432	99	17	:	:	PUNCT
cana-2432	99	18	𝑋𝑡𝑟𝑎𝑛𝑠𝑓𝑜𝑟𝑚𝑒𝑑	𝑋𝑡𝑟𝑎𝑛𝑠𝑓𝑜𝑟𝑚𝑒𝑑	PROPN
cana-2432	99	19	=	=	PUNCT
cana-2432	100	1	[	[	X
cana-2432	100	2	𝑐𝑜𝑒𝑓𝑓𝑠1	𝑐𝑜𝑒𝑓𝑓𝑠1	X
cana-2432	100	3	||	||	NOUN
cana-2432	101	1	𝑐𝑜𝑒𝑓𝑓𝑠2	𝑐𝑜𝑒𝑓𝑓𝑠2	ADJ
cana-2432	101	2	||	||	PROPN
cana-2432	101	3	…	…	PUNCT
cana-2432	101	4	…	…	PUNCT
cana-2432	101	5	||	||	NUM
cana-2432	102	1	𝑐𝑜𝑒𝑓𝑓𝑠𝑚	𝑐𝑜𝑒𝑓𝑓𝑠𝑚	ADJ
cana-2432	102	2	]	]	PUNCT
cana-2432	102	3	(	(	PUNCT
cana-2432	102	4	11	11	NUM
cana-2432	102	5	)	)	PUNCT
cana-2432	102	6	here	here	ADV
cana-2432	102	7	,	,	PUNCT
cana-2432	102	8	||	||	PROPN
cana-2432	102	9	denotes	denote	NOUN
cana-2432	102	10	concatenation	concatenation	PROPN
cana-2432	102	11	.	.	PUNCT
cana-2432	103	1	4.3	4.3	NUM
cana-2432	103	2	bonferroni	bonferroni	NOUN
cana-2432	103	3	-	-	PUNCT
cana-2432	103	4	adjusted	adjust	VERB
cana-2432	103	5	anova	anova	PROPN
cana-2432	103	6	feature	feature	NOUN
cana-2432	103	7	selection	selection	NOUN
cana-2432	103	8	:	:	PUNCT
cana-2432	103	9	after	after	ADP
cana-2432	103	10	the	the	DET
cana-2432	103	11	wavelet	wavelet	NOUN
cana-2432	103	12	transform	transform	NOUN
cana-2432	103	13	-	-	PUNCT
cana-2432	103	14	based	base	VERB
cana-2432	103	15	feature	feature	NOUN
cana-2432	103	16	extraction	extraction	NOUN
cana-2432	103	17	and	and	CCONJ
cana-2432	103	18	concatenation	concatenation	NOUN
cana-2432	103	19	process	process	NOUN
cana-2432	103	20	,	,	PUNCT
cana-2432	103	21	a	a	DET
cana-2432	103	22	substantial	substantial	ADJ
cana-2432	103	23	number	number	NOUN
cana-2432	103	24	of	of	ADP
cana-2432	103	25	features	feature	NOUN
cana-2432	103	26	are	be	AUX
cana-2432	103	27	generated	generate	VERB
cana-2432	103	28	.	.	PUNCT
cana-2432	104	1	the	the	DET
cana-2432	104	2	concatenated	concatenate	VERB
cana-2432	104	3	feature	feature	NOUN
cana-2432	104	4	set	set	NOUN
cana-2432	104	5	,	,	PUNCT
cana-2432	104	6	comprising	comprise	VERB
cana-2432	104	7	32,768	32,768	NUM
cana-2432	104	8	features	feature	NOUN
cana-2432	104	9	,	,	PUNCT
cana-2432	104	10	exhibits	exhibit	VERB
cana-2432	104	11	high	high	ADJ
cana-2432	104	12	dimensionality	dimensionality	NOUN
cana-2432	104	13	,	,	PUNCT
cana-2432	104	14	potentially	potentially	ADV
cana-2432	104	15	impeding	impede	VERB
cana-2432	104	16	subsequent	subsequent	ADJ
cana-2432	104	17	processing	processing	NOUN
cana-2432	104	18	steps	step	NOUN
cana-2432	104	19	.	.	PUNCT
cana-2432	105	1	to	to	PART
cana-2432	105	2	address	address	VERB
cana-2432	105	3	this	this	DET
cana-2432	105	4	challenge	challenge	NOUN
cana-2432	105	5	,	,	PUNCT
cana-2432	105	6	it	it	PRON
cana-2432	105	7	becomes	become	VERB
cana-2432	105	8	imperative	imperative	ADJ
cana-2432	105	9	to	to	PART
cana-2432	105	10	manage	manage	VERB
cana-2432	105	11	the	the	DET
cana-2432	105	12	dimensionality	dimensionality	NOUN
cana-2432	105	13	effectively	effectively	ADV
cana-2432	105	14	to	to	PART
cana-2432	105	15	ensure	ensure	VERB
cana-2432	105	16	efficient	efficient	ADJ
cana-2432	105	17	analysis	analysis	NOUN
cana-2432	105	18	.	.	PUNCT
cana-2432	106	1	employing	employ	VERB
cana-2432	106	2	anova	anova	PROPN
cana-2432	106	3	(	(	PUNCT
cana-2432	106	4	analysis	analysis	NOUN
cana-2432	106	5	of	of	ADP
cana-2432	106	6	variance	variance	NOUN
cana-2432	106	7	)	)	PUNCT
cana-2432	106	8	becomes	become	VERB
cana-2432	106	9	crucial	crucial	ADJ
cana-2432	106	10	in	in	ADP
cana-2432	106	11	this	this	DET
cana-2432	106	12	context	context	NOUN
cana-2432	106	13	to	to	PART
cana-2432	106	14	select	select	VERB
cana-2432	106	15	the	the	DET
cana-2432	106	16	most	most	ADV
cana-2432	106	17	pertinent	pertinent	ADJ
cana-2432	106	18	features	feature	NOUN
cana-2432	106	19	from	from	ADP
cana-2432	106	20	the	the	DET
cana-2432	106	21	extracted	extract	VERB
cana-2432	106	22	feature	feature	NOUN
cana-2432	106	23	set	set	NOUN
cana-2432	106	24	.	.	PUNCT
cana-2432	107	1	anova	anova	PROPN
cana-2432	107	2	meticulously	meticulously	ADV
cana-2432	107	3	evaluates	evaluate	VERB
cana-2432	107	4	the	the	DET
cana-2432	107	5	statistical	statistical	ADJ
cana-2432	107	6	significance	significance	NOUN
cana-2432	107	7	of	of	ADP
cana-2432	107	8	each	each	DET
cana-2432	107	9	feature	feature	NOUN
cana-2432	107	10	concerning	concern	VERB
cana-2432	107	11	the	the	DET
cana-2432	107	12	target	target	NOUN
cana-2432	107	13	variable	variable	NOUN
cana-2432	107	14	,	,	PUNCT
cana-2432	107	15	discerning	discern	VERB
cana-2432	107	16	those	those	DET
cana-2432	107	17	features	feature	NOUN
cana-2432	107	18	that	that	PRON
cana-2432	107	19	contribute	contribute	VERB
cana-2432	107	20	significantly	significantly	ADV
cana-2432	107	21	to	to	ADP
cana-2432	107	22	the	the	DET
cana-2432	107	23	classification	classification	NOUN
cana-2432	107	24	task	task	NOUN
cana-2432	107	25	.	.	PUNCT
cana-2432	108	1	for	for	ADP
cana-2432	108	2	a	a	DET
cana-2432	108	3	single	single	ADJ
cana-2432	108	4	feature	feature	NOUN
cana-2432	108	5	𝑋𝑖	𝑋𝑖	PROPN
cana-2432	108	6	,	,	PUNCT
cana-2432	108	7	the	the	DET
cana-2432	108	8	anova	anova	PROPN
cana-2432	108	9	f	f	X
cana-2432	108	10	-	-	PUNCT
cana-2432	108	11	value	value	NOUN
cana-2432	108	12	is	be	AUX
cana-2432	108	13	calculated	calculate	VERB
cana-2432	108	14	as	as	SCONJ
cana-2432	108	15	follows	follow	VERB
cana-2432	108	16	:	:	PUNCT
cana-2432	108	17	𝐹𝑖	𝐹𝑖	PROPN
cana-2432	108	18	=	=	SYM
cana-2432	108	19	𝐵𝑒𝑡𝑤𝑒𝑒𝑛	𝐵𝑒𝑡𝑤𝑒𝑒𝑛	PROPN
cana-2432	108	20	𝑔𝑟𝑜𝑢𝑝	𝑔𝑟𝑜𝑢𝑝	NOUN
cana-2432	108	21	𝑣𝑎𝑟𝑖𝑎𝑛𝑐𝑒	𝑣𝑎𝑟𝑖𝑎𝑛𝑐𝑒	VERB
cana-2432	108	22	𝑓𝑜𝑟	𝑓𝑜𝑟	ADV
cana-2432	108	23	𝑒𝑎𝑐ℎ	𝑒𝑎𝑐ℎ	NOUN
cana-2432	108	24	𝑓𝑒𝑎𝑡𝑢𝑟𝑒	𝑓𝑒𝑎𝑡𝑢𝑟𝑒	VERB
cana-2432	108	25	𝑋𝑖	𝑋𝑖	PROPN
cana-2432	108	26	𝑊𝑖𝑡ℎ𝑖𝑛	𝑊𝑖𝑡ℎ𝑖𝑛	PROPN
cana-2432	108	27	𝑔𝑟𝑜𝑢𝑝	𝑔𝑟𝑜𝑢𝑝	NOUN
cana-2432	108	28	𝑣𝑎𝑟𝑖𝑎𝑛𝑐𝑒	𝑣𝑎𝑟𝑖𝑎𝑛𝑐𝑒	VERB
cana-2432	108	29	𝑓𝑜𝑟	𝑓𝑜𝑟	ADV
cana-2432	108	30	𝑓𝑒𝑎𝑡𝑢𝑟𝑒	𝑓𝑒𝑎𝑡𝑢𝑟𝑒	VERB
cana-2432	108	31	𝑋𝑖	𝑋𝑖	PROPN
cana-2432	108	32	(	(	PUNCT
cana-2432	108	33	12	12	NUM
cana-2432	108	34	)	)	PUNCT
cana-2432	108	35	where	where	SCONJ
cana-2432	108	36	𝐹𝑖	𝐹𝑖	PROPN
cana-2432	108	37	is	be	AUX
cana-2432	108	38	the	the	DET
cana-2432	108	39	anova	anova	PROPN
cana-2432	108	40	f	f	X
cana-2432	108	41	-	-	PUNCT
cana-2432	108	42	value	value	NOUN
cana-2432	108	43	for	for	ADP
cana-2432	108	44	feature	feature	NOUN
cana-2432	108	45	𝑋𝑖	𝑋𝑖	NOUN
cana-2432	108	46	,	,	PUNCT
cana-2432	108	47	between	between	ADP
cana-2432	108	48	-	-	PUNCT
cana-2432	108	49	group	group	NOUN
cana-2432	108	50	variance	variance	NOUN
cana-2432	108	51	for	for	ADP
cana-2432	108	52	feature	feature	NOUN
cana-2432	108	53	𝑋𝑖	𝑋𝑖	PROPN
cana-2432	108	54	measures	measure	NOUN
cana-2432	108	55	the	the	DET
cana-2432	108	56	variance	variance	NOUN
cana-2432	108	57	of	of	ADP
cana-2432	108	58	feature	feature	NOUN
cana-2432	108	59	𝑋𝑖	𝑋𝑖	PROPN
cana-2432	108	60	across	across	ADP
cana-2432	108	61	different	different	ADJ
cana-2432	108	62	classes	class	NOUN
cana-2432	108	63	of	of	ADP
cana-2432	108	64	the	the	DET
cana-2432	108	65	target	target	NOUN
cana-2432	108	66	variable	variable	NOUN
cana-2432	108	67	.	.	PUNCT
cana-2432	109	1	within	within	ADP
cana-2432	109	2	-	-	PUNCT
cana-2432	109	3	group	group	NOUN
cana-2432	109	4	variance	variance	NOUN
cana-2432	109	5	for	for	ADP
cana-2432	109	6	feature	feature	NOUN
cana-2432	109	7	𝑋𝑖	𝑋𝑖	PROPN
cana-2432	109	8	measures	measure	NOUN
cana-2432	109	9	the	the	DET
cana-2432	109	10	variance	variance	NOUN
cana-2432	109	11	of	of	ADP
cana-2432	109	12	feature	feature	NOUN
cana-2432	109	13	𝑋𝑖	𝑋𝑖	PROPN
cana-2432	109	14	within	within	ADP
cana-2432	109	15	each	each	DET
cana-2432	109	16	class	class	NOUN
cana-2432	109	17	of	of	ADP
cana-2432	109	18	the	the	DET
cana-2432	109	19	target	target	NOUN
cana-2432	109	20	variable	variable	NOUN
cana-2432	109	21	.	.	PUNCT
cana-2432	110	1	the	the	DET
cana-2432	110	2	anova	anova	PROPN
cana-2432	110	3	f	f	X
cana-2432	110	4	-	-	PUNCT
cana-2432	110	5	value	value	NOUN
cana-2432	110	6	is	be	AUX
cana-2432	110	7	computed	compute	VERB
cana-2432	110	8	for	for	ADP
cana-2432	110	9	each	each	DET
cana-2432	110	10	feature	feature	NOUN
cana-2432	110	11	,	,	PUNCT
cana-2432	110	12	and	and	CCONJ
cana-2432	110	13	the	the	DET
cana-2432	110	14	corresponding	correspond	VERB
cana-2432	110	15	p	p	NOUN
cana-2432	110	16	-	-	PUNCT
cana-2432	110	17	value	value	NOUN
cana-2432	110	18	(	(	PUNCT
cana-2432	110	19	probability	probability	NOUN
cana-2432	110	20	value	value	NOUN
cana-2432	110	21	)	)	PUNCT
cana-2432	110	22	for	for	ADP
cana-2432	110	23	each	each	DET
cana-2432	110	24	feature	feature	NOUN
cana-2432	110	25	is	be	AUX
cana-2432	110	26	returned	return	VERB
cana-2432	110	27	.	.	PUNCT
cana-2432	111	1	the	the	DET
cana-2432	111	2	bonferroni	bonferroni	NOUN
cana-2432	111	3	correction	correction	NOUN
cana-2432	111	4	is	be	AUX
cana-2432	111	5	applied	apply	VERB
cana-2432	111	6	to	to	PART
cana-2432	111	7	adjust	adjust	VERB
cana-2432	111	8	the	the	DET
cana-2432	111	9	p	p	NOUN
cana-2432	111	10	-	-	PUNCT
cana-2432	111	11	values	value	NOUN
cana-2432	111	12	for	for	ADP
cana-2432	111	13	multiple	multiple	ADJ
cana-2432	111	14	comparisons	comparison	NOUN
cana-2432	111	15	to	to	PART
cana-2432	111	16	control	control	VERB
cana-2432	111	17	the	the	DET
cana-2432	111	18	error	error	NOUN
cana-2432	111	19	rate	rate	NOUN
cana-2432	111	20	.	.	PUNCT
cana-2432	112	1	it	it	PRON
cana-2432	112	2	is	be	AUX
cana-2432	112	3	modified	modify	VERB
cana-2432	112	4	as	as	ADP
cana-2432	112	5	:	:	PUNCT
cana-2432	112	6	𝑝𝑎𝑑𝑗𝑢𝑠𝑡𝑒𝑑	𝑝𝑎𝑑𝑗𝑢𝑠𝑡𝑒𝑑	PROPN
cana-2432	112	7	=	=	SYM
cana-2432	112	8	min	min	PROPN
cana-2432	112	9	(	(	PUNCT
cana-2432	112	10	𝑝.	𝑝.	PROPN
cana-2432	112	11	𝑚	𝑚	PROPN
cana-2432	112	12	,	,	PUNCT
cana-2432	112	13	1	1	NUM
cana-2432	112	14	)	)	PUNCT
cana-2432	112	15	(	(	PUNCT
cana-2432	112	16	13	13	NUM
cana-2432	112	17	)	)	PUNCT
cana-2432	112	18	where	where	SCONJ
cana-2432	112	19	m	m	NOUN
cana-2432	112	20	is	be	AUX
cana-2432	112	21	the	the	DET
cana-2432	112	22	number	number	NOUN
cana-2432	112	23	of	of	ADP
cana-2432	112	24	features	feature	NOUN
cana-2432	112	25	.	.	PUNCT
cana-2432	113	1	by	by	ADP
cana-2432	113	2	exclusively	exclusively	ADV
cana-2432	113	3	retaining	retain	VERB
cana-2432	113	4	the	the	DET
cana-2432	113	5	most	most	ADV
cana-2432	113	6	informative	informative	ADJ
cana-2432	113	7	features	feature	NOUN
cana-2432	113	8	,	,	PUNCT
cana-2432	113	9	bonferroni	bonferroni	NOUN
cana-2432	113	10	-	-	PUNCT
cana-2432	113	11	adjusted	adjust	VERB
cana-2432	113	12	anova	anova	PROPN
cana-2432	113	13	effectively	effectively	ADV
cana-2432	113	14	control	control	VERB
cana-2432	113	15	the	the	DET
cana-2432	113	16	false	false	ADJ
cana-2432	113	17	positive	positive	ADJ
cana-2432	113	18	rate	rate	NOUN
cana-2432	113	19	and	and	CCONJ
cana-2432	113	20	curtails	curtail	VERB
cana-2432	113	21	the	the	DET
cana-2432	113	22	dimensionality	dimensionality	NOUN
cana-2432	113	23	of	of	ADP
cana-2432	113	24	the	the	DET
cana-2432	113	25	input	input	NOUN
cana-2432	113	26	data	datum	NOUN
cana-2432	113	27	to	to	ADP
cana-2432	113	28	16384	16384	NUM
cana-2432	113	29	features	feature	NOUN
cana-2432	113	30	.	.	PUNCT
cana-2432	114	1	this	this	DET
cana-2432	114	2	reduction	reduction	NOUN
cana-2432	114	3	in	in	ADP
cana-2432	114	4	dimensionality	dimensionality	NOUN
cana-2432	114	5	not	not	PART
cana-2432	114	6	only	only	ADV
cana-2432	114	7	expedites	expedite	VERB
cana-2432	114	8	the	the	DET
cana-2432	114	9	training	training	NOUN
cana-2432	114	10	process	process	NOUN
cana-2432	114	11	but	but	CCONJ
cana-2432	114	12	also	also	ADV
cana-2432	114	13	minimizing	minimize	VERB
cana-2432	114	14	computational	computational	ADJ
cana-2432	114	15	resources	resource	NOUN
cana-2432	114	16	while	while	SCONJ
cana-2432	114	17	retaining	retain	VERB
cana-2432	114	18	the	the	DET
cana-2432	114	19	most	most	ADV
cana-2432	114	20	informative	informative	ADJ
cana-2432	114	21	features	feature	NOUN
cana-2432	114	22	.	.	PUNCT
cana-2432	115	1	in	in	ADP
cana-2432	115	2	addition	addition	NOUN
cana-2432	115	3	to	to	ADP
cana-2432	115	4	anova	anova	PROPN
cana-2432	115	5	,	,	PUNCT
cana-2432	115	6	a	a	DET
cana-2432	115	7	genetic	genetic	ADJ
cana-2432	115	8	algorithm	algorithm	NOUN
cana-2432	115	9	(	(	PUNCT
cana-2432	115	10	ga	ga	NOUN
cana-2432	115	11	)	)	PUNCT
cana-2432	115	12	based	base	VERB
cana-2432	115	13	feature	feature	NOUN
cana-2432	115	14	selection	selection	NOUN
cana-2432	115	15	method	method	NOUN
cana-2432	115	16	is	be	AUX
cana-2432	115	17	employed	employ	VERB
cana-2432	115	18	for	for	ADP
cana-2432	115	19	comparison	comparison	NOUN
cana-2432	115	20	.	.	PUNCT
cana-2432	116	1	ga	ga	PROPN
cana-2432	116	2	iteratively	iteratively	ADV
cana-2432	116	3	evolves	evolve	VERB
cana-2432	116	4	a	a	DET
cana-2432	116	5	population	population	NOUN
cana-2432	116	6	of	of	ADP
cana-2432	116	7	candidate	candidate	NOUN
cana-2432	116	8	feature	feature	NOUN
cana-2432	116	9	subsets	subset	NOUN
cana-2432	116	10	using	use	VERB
cana-2432	116	11	principles	principle	NOUN
cana-2432	116	12	inspired	inspire	VERB
cana-2432	116	13	by	by	ADP
cana-2432	116	14	natural	natural	ADJ
cana-2432	116	15	selection	selection	NOUN
cana-2432	116	16	.	.	PUNCT
cana-2432	117	1	the	the	DET
cana-2432	117	2	fitness	fitness	NOUN
cana-2432	117	3	of	of	ADP
cana-2432	117	4	each	each	DET
cana-2432	117	5	candidate	candidate	NOUN
cana-2432	117	6	subset	subset	NOUN
cana-2432	117	7	is	be	AUX
cana-2432	117	8	evaluated	evaluate	VERB
cana-2432	117	9	based	base	VERB
cana-2432	117	10	on	on	ADP
cana-2432	117	11	its	its	PRON
cana-2432	117	12	performance	performance	NOUN
cana-2432	117	13	in	in	ADP
cana-2432	117	14	a	a	DET
cana-2432	117	15	deep	deep	ADJ
cana-2432	117	16	learning	learning	NOUN
cana-2432	117	17	models	model	NOUN
cana-2432	117	18	trained	train	VERB
cana-2432	117	19	on	on	ADP
cana-2432	117	20	the	the	DET
cana-2432	117	21	selected	select	VERB
cana-2432	117	22	features	feature	NOUN
cana-2432	117	23	.	.	PUNCT
cana-2432	118	1	communications	communication	NOUN
cana-2432	118	2	on	on	ADP
cana-2432	118	3	applied	apply	VERB
cana-2432	118	4	nonlinear	nonlinear	ADJ
cana-2432	118	5	analysis	analysis	NOUN
cana-2432	118	6	issn	issn	NOUN
cana-2432	118	7	:	:	PUNCT
cana-2432	118	8	1074	1074	NUM
cana-2432	118	9	-	-	PUNCT
cana-2432	118	10	133x	133x	NUM
cana-2432	118	11	vol	vol	NOUN
cana-2432	118	12	32	32	NUM
cana-2432	118	13	no	no	NOUN
cana-2432	118	14	.	.	PUNCT
cana-2432	119	1	2s	2s	NUM
cana-2432	119	2	(	(	PUNCT
cana-2432	119	3	2025	2025	NUM
cana-2432	119	4	)	)	PUNCT
cana-2432	119	5	429	429	NUM
cana-2432	119	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-2432	119	7	4.4	4.4	NUM
cana-2432	119	8	proposed	propose	VERB
cana-2432	119	9	wtan	wtan	PROPN
cana-2432	119	10	-	-	PUNCT
cana-2432	119	11	cnn	cnn	PROPN
cana-2432	119	12	with	with	ADP
cana-2432	119	13	transfer	transfer	NOUN
cana-2432	119	14	learning	learning	NOUN
cana-2432	119	15	in	in	ADP
cana-2432	119	16	this	this	DET
cana-2432	119	17	study	study	NOUN
cana-2432	119	18	,	,	PUNCT
cana-2432	119	19	transfer	transfer	NOUN
cana-2432	119	20	learning	learning	NOUN
cana-2432	119	21	model	model	NOUN
cana-2432	119	22	vgg19	vgg19	PROPN
cana-2432	120	1	[	[	X
cana-2432	120	2	19	19	NUM
cana-2432	120	3	]	]	PUNCT
cana-2432	120	4	is	be	AUX
cana-2432	120	5	employed	employ	VERB
cana-2432	120	6	to	to	PART
cana-2432	120	7	train	train	VERB
cana-2432	120	8	on	on	ADP
cana-2432	120	9	features	feature	NOUN
cana-2432	120	10	selected	select	VERB
cana-2432	120	11	using	use	VERB
cana-2432	120	12	the	the	DET
cana-2432	120	13	bonferroni	bonferroni	NOUN
cana-2432	120	14	-	-	PUNCT
cana-2432	120	15	adjusted	adjust	VERB
cana-2432	120	16	anova	anova	PROPN
cana-2432	120	17	feature	feature	NOUN
cana-2432	120	18	selection	selection	NOUN
cana-2432	120	19	method	method	NOUN
cana-2432	120	20	.	.	PUNCT
cana-2432	121	1	these	these	DET
cana-2432	121	2	features	feature	NOUN
cana-2432	121	3	are	be	AUX
cana-2432	121	4	derived	derive	VERB
cana-2432	121	5	from	from	ADP
cana-2432	121	6	the	the	DET
cana-2432	121	7	concatenation	concatenation	NOUN
cana-2432	121	8	of	of	ADP
cana-2432	121	9	features	feature	NOUN
cana-2432	121	10	extracted	extract	VERB
cana-2432	121	11	using	use	VERB
cana-2432	121	12	the	the	DET
cana-2432	121	13	haar	haar	PROPN
cana-2432	121	14	wavelet	wavelet	NOUN
cana-2432	121	15	transform	transform	NOUN
cana-2432	121	16	.	.	PUNCT
cana-2432	122	1	utilizing	utilize	VERB
cana-2432	122	2	the	the	DET
cana-2432	122	3	pre	pre	ADJ
cana-2432	122	4	-	-	ADJ
cana-2432	122	5	trained	train	VERB
cana-2432	122	6	weights	weight	NOUN
cana-2432	122	7	of	of	ADP
cana-2432	122	8	the	the	DET
cana-2432	122	9	model	model	NOUN
cana-2432	122	10	has	have	AUX
cana-2432	122	11	proven	prove	VERB
cana-2432	122	12	to	to	PART
cana-2432	122	13	be	be	AUX
cana-2432	122	14	a	a	DET
cana-2432	122	15	more	more	ADV
cana-2432	122	16	effective	effective	ADJ
cana-2432	122	17	strategy	strategy	NOUN
cana-2432	122	18	,	,	PUNCT
cana-2432	122	19	significantly	significantly	ADV
cana-2432	122	20	accelerating	accelerate	VERB
cana-2432	122	21	the	the	DET
cana-2432	122	22	training	training	NOUN
cana-2432	122	23	process	process	NOUN
cana-2432	122	24	.	.	PUNCT
cana-2432	123	1	vgg19	vgg19	PROPN
cana-2432	123	2	,	,	PUNCT
cana-2432	123	3	a	a	DET
cana-2432	123	4	cnn	cnn	PROPN
cana-2432	123	5	model	model	NOUN
cana-2432	123	6	proposed	propose	VERB
cana-2432	123	7	by	by	ADP
cana-2432	123	8	zisserman	zisserman	NOUN
cana-2432	123	9	and	and	CCONJ
cana-2432	123	10	his	his	PRON
cana-2432	123	11	team	team	NOUN
cana-2432	123	12	,	,	PUNCT
cana-2432	123	13	is	be	AUX
cana-2432	123	14	19	19	NUM
cana-2432	123	15	layers	layer	NOUN
cana-2432	123	16	deep	deep	ADJ
cana-2432	123	17	.	.	PUNCT
cana-2432	124	1	it	it	PRON
cana-2432	124	2	excels	excel	VERB
cana-2432	124	3	at	at	ADP
cana-2432	124	4	capturing	capture	VERB
cana-2432	124	5	detailed	detailed	ADJ
cana-2432	124	6	features	feature	NOUN
cana-2432	124	7	by	by	ADP
cana-2432	124	8	utilizing	utilize	VERB
cana-2432	124	9	5x5	5x5	NUM
cana-2432	124	10	and	and	CCONJ
cana-2432	124	11	3x3	3x3	NUM
cana-2432	124	12	receptive	receptive	ADJ
cana-2432	124	13	fields	field	NOUN
cana-2432	124	14	,	,	PUNCT
cana-2432	124	15	thereby	thereby	ADV
cana-2432	124	16	enhancing	enhance	VERB
cana-2432	124	17	prediction	prediction	NOUN
cana-2432	124	18	accuracy	accuracy	NOUN
cana-2432	124	19	.	.	PUNCT
cana-2432	125	1	in	in	ADP
cana-2432	125	2	the	the	DET
cana-2432	125	3	proposed	propose	VERB
cana-2432	125	4	work	work	NOUN
cana-2432	125	5	,	,	PUNCT
cana-2432	125	6	a	a	DET
cana-2432	125	7	common	common	ADJ
cana-2432	125	8	approach	approach	NOUN
cana-2432	125	9	is	be	AUX
cana-2432	125	10	adopted	adopt	VERB
cana-2432	125	11	where	where	SCONJ
cana-2432	125	12	the	the	DET
cana-2432	125	13	top	top	ADJ
cana-2432	125	14	layers	layer	NOUN
cana-2432	125	15	of	of	ADP
cana-2432	125	16	these	these	DET
cana-2432	125	17	models	model	NOUN
cana-2432	125	18	are	be	AUX
cana-2432	125	19	frozen	frozen	ADJ
cana-2432	125	20	and	and	CCONJ
cana-2432	125	21	then	then	ADV
cana-2432	125	22	modified	modify	VERB
cana-2432	125	23	by	by	ADP
cana-2432	125	24	adding	add	VERB
cana-2432	125	25	three	three	NUM
cana-2432	125	26	dense	dense	ADJ
cana-2432	125	27	layers	layer	NOUN
cana-2432	125	28	and	and	CCONJ
cana-2432	125	29	one	one	NUM
cana-2432	125	30	dropout	dropout	NOUN
cana-2432	125	31	layer	layer	NOUN
cana-2432	125	32	.	.	PUNCT
cana-2432	126	1	the	the	DET
cana-2432	126	2	final	final	ADJ
cana-2432	126	3	dense	dense	ADJ
cana-2432	126	4	layer	layer	NOUN
cana-2432	126	5	consists	consist	VERB
cana-2432	126	6	of	of	ADP
cana-2432	126	7	four	four	NUM
cana-2432	126	8	neurons	neuron	NOUN
cana-2432	126	9	,	,	PUNCT
cana-2432	126	10	corresponding	correspond	VERB
cana-2432	126	11	to	to	ADP
cana-2432	126	12	our	our	PRON
cana-2432	126	13	four	four	NUM
cana-2432	126	14	target	target	NOUN
cana-2432	126	15	output	output	NOUN
cana-2432	126	16	classes	class	NOUN
cana-2432	126	17	:	:	PUNCT
cana-2432	126	18	class	class	NOUN
cana-2432	126	19	0	0	NUM
cana-2432	126	20	(	(	PUNCT
cana-2432	126	21	covid	covid	PROPN
cana-2432	126	22	)	)	PUNCT
cana-2432	126	23	,	,	PUNCT
cana-2432	126	24	class	class	NOUN
cana-2432	126	25	1	1	NUM
cana-2432	126	26	(	(	PUNCT
cana-2432	126	27	normal	normal	ADJ
cana-2432	126	28	)	)	PUNCT
cana-2432	126	29	,	,	PUNCT
cana-2432	126	30	class	class	NOUN
cana-2432	126	31	2	2	NUM
cana-2432	126	32	(	(	PUNCT
cana-2432	126	33	viral	viral	ADJ
cana-2432	126	34	pneumonia	pneumonia	NOUN
cana-2432	126	35	)	)	PUNCT
cana-2432	126	36	,	,	PUNCT
cana-2432	126	37	and	and	CCONJ
cana-2432	126	38	class	class	NOUN
cana-2432	126	39	3	3	NUM
cana-2432	126	40	(	(	PUNCT
cana-2432	126	41	lung	lung	NOUN
cana-2432	126	42	opacity	opacity	NOUN
cana-2432	126	43	)	)	PUNCT
cana-2432	126	44	.	.	PUNCT
cana-2432	127	1	additionally	additionally	ADV
cana-2432	127	2	,	,	PUNCT
cana-2432	127	3	a	a	DET
cana-2432	127	4	deep	deep	ADJ
cana-2432	127	5	learning	learning	NOUN
cana-2432	127	6	model	model	NOUN
cana-2432	127	7	,	,	PUNCT
cana-2432	127	8	specifically	specifically	ADV
cana-2432	127	9	a	a	DET
cana-2432	127	10	cnn	cnn	PROPN
cana-2432	127	11	,	,	PUNCT
cana-2432	127	12	has	have	AUX
cana-2432	127	13	been	be	AUX
cana-2432	127	14	trained	train	VERB
cana-2432	127	15	on	on	ADP
cana-2432	127	16	the	the	DET
cana-2432	127	17	same	same	ADJ
cana-2432	127	18	features	feature	NOUN
cana-2432	127	19	to	to	PART
cana-2432	127	20	compare	compare	VERB
cana-2432	127	21	its	its	PRON
cana-2432	127	22	performance	performance	NOUN
cana-2432	127	23	with	with	ADP
cana-2432	127	24	the	the	DET
cana-2432	127	25	transfer	transfer	NOUN
cana-2432	127	26	learning	learning	NOUN
cana-2432	127	27	models	model	NOUN
cana-2432	127	28	.	.	PUNCT
cana-2432	128	1	both	both	CCONJ
cana-2432	128	2	the	the	DET
cana-2432	128	3	transfer	transfer	NOUN
cana-2432	128	4	learning	learning	NOUN
cana-2432	128	5	models	model	NOUN
cana-2432	128	6	and	and	CCONJ
cana-2432	128	7	the	the	DET
cana-2432	128	8	cnn	cnn	PROPN
cana-2432	128	9	have	have	AUX
cana-2432	128	10	been	be	AUX
cana-2432	128	11	fine	fine	ADV
cana-2432	128	12	-	-	PUNCT
cana-2432	128	13	tuned	tune	VERB
cana-2432	128	14	on	on	ADP
cana-2432	128	15	the	the	DET
cana-2432	128	16	dataset	dataset	NOUN
cana-2432	128	17	to	to	PART
cana-2432	128	18	optimize	optimize	VERB
cana-2432	128	19	their	their	PRON
cana-2432	128	20	performance	performance	NOUN
cana-2432	128	21	in	in	ADP
cana-2432	128	22	classifying	classify	VERB
cana-2432	128	23	the	the	DET
cana-2432	128	24	lung	lung	NOUN
cana-2432	128	25	x	x	NOUN
cana-2432	128	26	-	-	NOUN
cana-2432	128	27	ray	ray	NOUN
cana-2432	128	28	images	image	NOUN
cana-2432	128	29	into	into	ADP
cana-2432	128	30	their	their	PRON
cana-2432	128	31	respective	respective	ADJ
cana-2432	128	32	categories	category	NOUN
cana-2432	128	33	.	.	PUNCT
cana-2432	129	1	fig.2	fig.2	PROPN
cana-2432	129	2	.	.	PROPN
cana-2432	129	3	illustrates	illustrate	VERB
cana-2432	129	4	the	the	DET
cana-2432	129	5	comprehensive	comprehensive	ADJ
cana-2432	129	6	structure	structure	NOUN
cana-2432	129	7	of	of	ADP
cana-2432	129	8	the	the	DET
cana-2432	129	9	proposed	propose	VERB
cana-2432	129	10	model	model	NOUN
cana-2432	129	11	,	,	PUNCT
cana-2432	129	12	showcasing	showcase	VERB
cana-2432	129	13	the	the	DET
cana-2432	129	14	integration	integration	NOUN
cana-2432	129	15	of	of	ADP
cana-2432	129	16	wavelet	wavelet	NOUN
cana-2432	129	17	-	-	PUNCT
cana-2432	129	18	based	base	VERB
cana-2432	129	19	feature	feature	NOUN
cana-2432	129	20	extraction	extraction	NOUN
cana-2432	129	21	,	,	PUNCT
cana-2432	129	22	bonferroni	bonferroni	NOUN
cana-2432	129	23	-	-	PUNCT
cana-2432	129	24	adjusted	adjust	VERB
cana-2432	129	25	anova	anova	PROPN
cana-2432	129	26	feature	feature	NOUN
cana-2432	129	27	selection	selection	NOUN
cana-2432	129	28	,	,	PUNCT
cana-2432	129	29	and	and	CCONJ
cana-2432	129	30	the	the	DET
cana-2432	129	31	architecture	architecture	NOUN
cana-2432	129	32	modifications	modification	NOUN
cana-2432	129	33	of	of	ADP
cana-2432	129	34	the	the	DET
cana-2432	129	35	transfer	transfer	NOUN
cana-2432	129	36	learning	learning	NOUN
cana-2432	129	37	models	model	NOUN
cana-2432	129	38	.	.	PUNCT
cana-2432	130	1	this	this	DET
cana-2432	130	2	integrated	integrate	VERB
cana-2432	130	3	approach	approach	NOUN
cana-2432	130	4	aims	aim	VERB
cana-2432	130	5	to	to	PART
cana-2432	130	6	improve	improve	VERB
cana-2432	130	7	the	the	DET
cana-2432	130	8	accuracy	accuracy	NOUN
cana-2432	130	9	and	and	CCONJ
cana-2432	130	10	efficiency	efficiency	NOUN
cana-2432	130	11	of	of	ADP
cana-2432	130	12	lung	lung	NOUN
cana-2432	130	13	x	x	PROPN
cana-2432	130	14	-	-	NOUN
cana-2432	130	15	ray	ray	NOUN
cana-2432	130	16	image	image	NOUN
cana-2432	130	17	classification	classification	NOUN
cana-2432	130	18	,	,	PUNCT
cana-2432	130	19	providing	provide	VERB
cana-2432	130	20	a	a	DET
cana-2432	130	21	robust	robust	ADJ
cana-2432	130	22	tool	tool	NOUN
cana-2432	130	23	for	for	ADP
cana-2432	130	24	medical	medical	ADJ
cana-2432	130	25	diagnostics	diagnostic	NOUN
cana-2432	130	26	.	.	PUNCT
cana-2432	131	1	fig.2	fig.2	PROPN
cana-2432	131	2	.	.	PUNCT
cana-2432	131	3	structure	structure	NOUN
cana-2432	131	4	of	of	ADP
cana-2432	131	5	proposed	propose	VERB
cana-2432	131	6	wtban	wtban	NOUN
cana-2432	131	7	-	-	PUNCT
cana-2432	131	8	cnn	cnn	PROPN
cana-2432	131	9	-	-	PUNCT
cana-2432	131	10	tl	tl	PROPN
cana-2432	131	11	communications	communication	NOUN
cana-2432	131	12	on	on	ADP
cana-2432	131	13	applied	apply	VERB
cana-2432	131	14	nonlinear	nonlinear	ADJ
cana-2432	131	15	analysis	analysis	NOUN
cana-2432	131	16	issn	issn	NOUN
cana-2432	131	17	:	:	PUNCT
cana-2432	131	18	1074	1074	NUM
cana-2432	131	19	-	-	PUNCT
cana-2432	131	20	133x	133x	NUM
cana-2432	131	21	vol	vol	NOUN
cana-2432	131	22	32	32	NUM
cana-2432	131	23	no	no	NOUN
cana-2432	131	24	.	.	PUNCT
cana-2432	132	1	2s	2s	NUM
cana-2432	132	2	(	(	PUNCT
cana-2432	132	3	2025	2025	NUM
cana-2432	132	4	)	)	PUNCT
cana-2432	132	5	430	430	NUM
cana-2432	132	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-2432	132	7	algorithm	algorithm	NOUN
cana-2432	132	8	:	:	PUNCT
cana-2432	132	9	wavelet	wavelet	NOUN
cana-2432	132	10	-	-	PUNCT
cana-2432	132	11	bonferroni	bonferroni	NOUN
cana-2432	132	12	anova	anova	PROPN
cana-2432	132	13	-	-	PROPN
cana-2432	132	14	cnn	cnn	PROPN
cana-2432	132	15	with	with	ADP
cana-2432	132	16	transfer	transfer	NOUN
cana-2432	132	17	learning	learning	NOUN
cana-2432	132	18	for	for	ADP
cana-2432	132	19	lung	lung	NOUN
cana-2432	132	20	x	x	PROPN
cana-2432	132	21	-	-	NOUN
cana-2432	132	22	ray	ray	NOUN
cana-2432	132	23	image	image	NOUN
cana-2432	132	24	classification	classification	NOUN
cana-2432	132	25	input	input	NOUN
cana-2432	132	26	:	:	PUNCT
cana-2432	132	27	set	set	NOUN
cana-2432	132	28	of	of	ADP
cana-2432	132	29	lung	lung	NOUN
cana-2432	132	30	x	x	PROPN
cana-2432	132	31	-	-	NOUN
cana-2432	132	32	ray	ray	NOUN
cana-2432	132	33	images	image	NOUN
cana-2432	132	34	output	output	NOUN
cana-2432	132	35	:	:	PUNCT
cana-2432	132	36	wtbanen	wtbanen	PROPN
cana-2432	132	37	-	-	PUNCT
cana-2432	132	38	cnn	cnn	PROPN
cana-2432	132	39	:	:	PUNCT
cana-2432	132	40	wavelet	wavelet	PROPN
cana-2432	132	41	anova	anova	PROPN
cana-2432	132	42	enhanced	enhance	VERB
cana-2432	132	43	cnn	cnn	PROPN
cana-2432	132	44	model	model	NOUN
cana-2432	132	45	steps	step	NOUN
cana-2432	132	46	:	:	PUNCT
cana-2432	132	47	1	1	X
cana-2432	132	48	.	.	X
cana-2432	132	49	feature	feature	NOUN
cana-2432	132	50	extraction	extraction	NOUN
cana-2432	132	51	using	use	VERB
cana-2432	132	52	wavelet	wavelet	NOUN
cana-2432	132	53	transform	transform	NOUN
cana-2432	132	54	:	:	PUNCT
cana-2432	132	55	for	for	ADP
cana-2432	132	56	each	each	DET
cana-2432	132	57	x	x	ADJ
cana-2432	132	58	-	-	NOUN
cana-2432	132	59	ray	ray	NOUN
cana-2432	132	60	image	image	NOUN
cana-2432	132	61	in	in	ADP
cana-2432	132	62	data	datum	NOUN
cana-2432	132	63	set	set	VERB
cana-2432	132	64	:	:	PUNCT
cana-2432	132	65	a.	a.	NOUN
cana-2432	132	66	apply	apply	VERB
cana-2432	132	67	two	two	NUM
cana-2432	132	68	level	level	NOUN
cana-2432	132	69	haar	haar	X
cana-2432	132	70	wavelet	wavelet	NOUN
cana-2432	132	71	transform	transform	NOUN
cana-2432	132	72	to	to	ADP
cana-2432	132	73	the	the	DET
cana-2432	132	74	image	image	NOUN
cana-2432	132	75	to	to	PART
cana-2432	132	76	extract	extract	VERB
cana-2432	132	77	features	feature	NOUN
cana-2432	132	78	across	across	ADP
cana-2432	132	79	multiple	multiple	ADJ
cana-2432	132	80	scales	scale	NOUN
cana-2432	132	81	.	.	PUNCT
cana-2432	133	1	b.	b.	PROPN
cana-2432	133	2	concatenate	concatenate	PROPN
cana-2432	133	3	the	the	DET
cana-2432	133	4	wavelet	wavelet	NOUN
cana-2432	133	5	features	feature	VERB
cana-2432	133	6	to	to	PART
cana-2432	133	7	form	form	VERB
cana-2432	133	8	a	a	DET
cana-2432	133	9	comprehensive	comprehensive	ADJ
cana-2432	133	10	feature	feature	NOUN
cana-2432	133	11	set	set	NOUN
cana-2432	133	12	.	.	PUNCT
cana-2432	134	1	2	2	X
cana-2432	134	2	.	.	X
cana-2432	134	3	feature	feature	NOUN
cana-2432	134	4	selection	selection	NOUN
cana-2432	134	5	using	use	VERB
cana-2432	134	6	bonferroni	bonferroni	NOUN
cana-2432	134	7	-	-	PUNCT
cana-2432	134	8	adjusted	adjust	VERB
cana-2432	134	9	anova	anova	PROPN
cana-2432	134	10	:	:	PUNCT
cana-2432	134	11	a.	a.	NOUN
cana-2432	134	12	perform	perform	PROPN
cana-2432	134	13	bonferroni	bonferroni	NOUN
cana-2432	134	14	-	-	PUNCT
cana-2432	134	15	adjusted	adjust	VERB
cana-2432	134	16	anova	anova	PROPN
cana-2432	134	17	feature	feature	NOUN
cana-2432	134	18	selection	selection	NOUN
cana-2432	134	19	on	on	ADP
cana-2432	134	20	the	the	DET
cana-2432	134	21	concatenated	concatenate	VERB
cana-2432	134	22	feature	feature	NOUN
cana-2432	134	23	set	set	VERB
cana-2432	134	24	to	to	PART
cana-2432	134	25	identify	identify	VERB
cana-2432	134	26	the	the	DET
cana-2432	134	27	most	most	ADV
cana-2432	134	28	relevant	relevant	ADJ
cana-2432	134	29	features	feature	NOUN
cana-2432	134	30	and	and	CCONJ
cana-2432	134	31	reduce	reduce	VERB
cana-2432	134	32	the	the	DET
cana-2432	134	33	dimensionality	dimensionality	NOUN
cana-2432	134	34	of	of	ADP
cana-2432	134	35	the	the	DET
cana-2432	134	36	feature	feature	NOUN
cana-2432	134	37	set	set	NOUN
cana-2432	134	38	.	.	PUNCT
cana-2432	135	1	3	3	X
cana-2432	135	2	.	.	X
cana-2432	135	3	convolutional	convolutional	ADJ
cana-2432	135	4	neural	neural	ADJ
cana-2432	135	5	network	network	NOUN
cana-2432	135	6	(	(	PUNCT
cana-2432	135	7	cnn	cnn	PROPN
cana-2432	135	8	)	)	PUNCT
cana-2432	135	9	initialization	initialization	NOUN
cana-2432	135	10	and	and	CCONJ
cana-2432	135	11	transfer	transfer	NOUN
cana-2432	135	12	learning	learning	NOUN
cana-2432	135	13	:	:	PUNCT
cana-2432	135	14	a.	a.	NOUN
cana-2432	135	15	initialize	initialize	NOUN
cana-2432	135	16	cnn	cnn	PROPN
cana-2432	135	17	model	model	NOUN
cana-2432	135	18	architecture	architecture	NOUN
cana-2432	135	19	suitable	suitable	ADJ
cana-2432	135	20	for	for	ADP
cana-2432	135	21	image	image	NOUN
cana-2432	135	22	classification	classification	NOUN
cana-2432	135	23	.	.	PUNCT
cana-2432	136	1	b.	b.	NOUN
cana-2432	136	2	incorporate	incorporate	NOUN
cana-2432	136	3	transfer	transfer	NOUN
cana-2432	136	4	learning	learning	NOUN
cana-2432	136	5	by	by	ADP
cana-2432	136	6	adding	add	VERB
cana-2432	136	7	pre	pre	ADJ
cana-2432	136	8	-	-	ADJ
cana-2432	136	9	trained	train	VERB
cana-2432	136	10	layers	layer	NOUN
cana-2432	136	11	from	from	ADP
cana-2432	136	12	vgg19	vgg19	PROPN
cana-2432	136	13	.	.	PUNCT
cana-2432	137	1	4	4	X
cana-2432	137	2	.	.	X
cana-2432	137	3	model	model	NOUN
cana-2432	137	4	training	training	NOUN
cana-2432	137	5	:	:	PUNCT
cana-2432	137	6	a.train	a.train	VERB
cana-2432	137	7	the	the	DET
cana-2432	137	8	cnn	cnn	PROPN
cana-2432	137	9	model	model	NOUN
cana-2432	137	10	using	use	VERB
cana-2432	137	11	the	the	DET
cana-2432	137	12	selected	select	VERB
cana-2432	137	13	features	feature	NOUN
cana-2432	137	14	and	and	CCONJ
cana-2432	137	15	corresponding	corresponding	ADJ
cana-2432	137	16	labels	label	NOUN
cana-2432	137	17	:	:	PUNCT
cana-2432	137	18	b.split	b.split	ADP
cana-2432	137	19	the	the	DET
cana-2432	137	20	dataset	dataset	NOUN
cana-2432	137	21	into	into	ADP
cana-2432	137	22	training	training	NOUN
cana-2432	137	23	and	and	CCONJ
cana-2432	137	24	validation	validation	NOUN
cana-2432	137	25	sets	set	NOUN
cana-2432	137	26	.	.	PUNCT
cana-2432	138	1	5	5	X
cana-2432	138	2	.	.	X
cana-2432	138	3	evaluation	evaluation	NOUN
cana-2432	138	4	:	:	PUNCT
cana-2432	138	5	a.	a.	NOUN
cana-2432	138	6	evaluate	evaluate	VERB
cana-2432	138	7	the	the	DET
cana-2432	138	8	trained	train	VERB
cana-2432	138	9	model	model	NOUN
cana-2432	138	10	on	on	ADP
cana-2432	138	11	the	the	DET
cana-2432	138	12	test	test	NOUN
cana-2432	138	13	data	data	PROPN
cana-2432	138	14	:	:	PUNCT
cana-2432	138	15	b.	b.	PROPN
cana-2432	138	16	compute	compute	PROPN
cana-2432	138	17	evaluation	evaluation	NOUN
cana-2432	138	18	metrics	metric	NOUN
cana-2432	138	19	such	such	ADJ
cana-2432	138	20	as	as	ADP
cana-2432	138	21	accuracy	accuracy	NOUN
cana-2432	138	22	,	,	PUNCT
cana-2432	138	23	precision	precision	NOUN
cana-2432	138	24	,	,	PUNCT
cana-2432	138	25	recall	recall	NOUN
cana-2432	138	26	,	,	PUNCT
cana-2432	138	27	and	and	CCONJ
cana-2432	138	28	f1	f1	NOUN
cana-2432	138	29	-	-	PUNCT
cana-2432	138	30	score	score	NOUN
cana-2432	138	31	.	.	PUNCT
cana-2432	139	1	5	5	X
cana-2432	139	2	.	.	X
cana-2432	139	3	result	result	VERB
cana-2432	139	4	analysis	analysis	NOUN
cana-2432	139	5	in	in	ADP
cana-2432	139	6	this	this	DET
cana-2432	139	7	study	study	NOUN
cana-2432	139	8	,	,	PUNCT
cana-2432	139	9	lung	lung	NOUN
cana-2432	139	10	x	x	PROPN
cana-2432	139	11	-	-	NOUN
cana-2432	139	12	ray	ray	NOUN
cana-2432	139	13	images	image	NOUN
cana-2432	139	14	were	be	AUX
cana-2432	139	15	utilized	utilize	VERB
cana-2432	139	16	to	to	PART
cana-2432	139	17	extract	extract	VERB
cana-2432	139	18	a	a	DET
cana-2432	139	19	comprehensive	comprehensive	ADJ
cana-2432	139	20	set	set	NOUN
cana-2432	139	21	of	of	ADP
cana-2432	139	22	features	feature	NOUN
cana-2432	139	23	,	,	PUNCT
cana-2432	139	24	which	which	PRON
cana-2432	139	25	were	be	AUX
cana-2432	139	26	subsequently	subsequently	ADV
cana-2432	139	27	processed	process	VERB
cana-2432	139	28	to	to	PART
cana-2432	139	29	form	form	VERB
cana-2432	139	30	a	a	DET
cana-2432	139	31	robust	robust	ADJ
cana-2432	139	32	feature	feature	NOUN
cana-2432	139	33	set	set	NOUN
cana-2432	139	34	.	.	PUNCT
cana-2432	140	1	anova	anova	PROPN
cana-2432	140	2	feature	feature	NOUN
cana-2432	140	3	selection	selection	NOUN
cana-2432	140	4	algorithm	algorithm	NOUN
cana-2432	140	5	was	be	AUX
cana-2432	140	6	employed	employ	VERB
cana-2432	140	7	to	to	PART
cana-2432	140	8	perform	perform	VERB
cana-2432	140	9	feature	feature	NOUN
cana-2432	140	10	selection	selection	NOUN
cana-2432	140	11	,	,	PUNCT
cana-2432	140	12	aiming	aim	VERB
cana-2432	140	13	to	to	PART
cana-2432	140	14	enhance	enhance	VERB
cana-2432	140	15	the	the	DET
cana-2432	140	16	performance	performance	NOUN
cana-2432	140	17	of	of	ADP
cana-2432	140	18	the	the	DET
cana-2432	140	19	classification	classification	NOUN
cana-2432	140	20	model	model	NOUN
cana-2432	140	21	by	by	ADP
cana-2432	140	22	identifying	identify	VERB
cana-2432	140	23	the	the	DET
cana-2432	140	24	most	most	ADV
cana-2432	140	25	significant	significant	ADJ
cana-2432	140	26	features	feature	NOUN
cana-2432	140	27	.	.	PUNCT
cana-2432	141	1	the	the	DET
cana-2432	141	2	selected	select	VERB
cana-2432	141	3	features	feature	NOUN
cana-2432	141	4	were	be	AUX
cana-2432	141	5	then	then	ADV
cana-2432	141	6	used	use	VERB
cana-2432	141	7	to	to	PART
cana-2432	141	8	classify	classify	VERB
cana-2432	141	9	the	the	DET
cana-2432	141	10	lung	lung	NOUN
cana-2432	141	11	x	x	PROPN
cana-2432	141	12	-	-	NOUN
cana-2432	141	13	ray	ray	NOUN
cana-2432	141	14	images	image	NOUN
cana-2432	141	15	.	.	PUNCT
cana-2432	142	1	the	the	DET
cana-2432	142	2	following	follow	VERB
cana-2432	142	3	analysis	analysis	NOUN
cana-2432	142	4	discusses	discuss	VERB
cana-2432	142	5	the	the	DET
cana-2432	142	6	results	result	NOUN
cana-2432	142	7	obtained	obtain	VERB
cana-2432	142	8	from	from	ADP
cana-2432	142	9	this	this	DET
cana-2432	142	10	process	process	NOUN
cana-2432	142	11	.	.	PUNCT
cana-2432	143	1	communications	communication	NOUN
cana-2432	143	2	on	on	ADP
cana-2432	143	3	applied	apply	VERB
cana-2432	143	4	nonlinear	nonlinear	ADJ
cana-2432	143	5	analysis	analysis	NOUN
cana-2432	143	6	issn	issn	NOUN
cana-2432	143	7	:	:	PUNCT
cana-2432	143	8	1074	1074	NUM
cana-2432	143	9	-	-	PUNCT
cana-2432	143	10	133x	133x	NUM
cana-2432	143	11	vol	vol	NOUN
cana-2432	143	12	32	32	NUM
cana-2432	143	13	no	no	NOUN
cana-2432	143	14	.	.	PUNCT
cana-2432	144	1	2s	2s	NUM
cana-2432	144	2	(	(	PUNCT
cana-2432	144	3	2025	2025	NUM
cana-2432	144	4	)	)	PUNCT
cana-2432	144	5	431	431	NUM
cana-2432	144	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-2432	144	7	5.1	5.1	NUM
cana-2432	144	8	results	result	NOUN
cana-2432	144	9	from	from	ADP
cana-2432	144	10	feature	feature	NOUN
cana-2432	144	11	extraction	extraction	NOUN
cana-2432	144	12	and	and	CCONJ
cana-2432	144	13	concatenation	concatenation	VERB
cana-2432	144	14	the	the	DET
cana-2432	144	15	application	application	NOUN
cana-2432	144	16	of	of	ADP
cana-2432	144	17	wavelet	wavelet	NOUN
cana-2432	144	18	transform	transform	NOUN
cana-2432	144	19	on	on	ADP
cana-2432	144	20	lung	lung	NOUN
cana-2432	144	21	x	x	PROPN
cana-2432	144	22	-	-	NOUN
cana-2432	144	23	ray	ray	NOUN
cana-2432	144	24	images	image	NOUN
cana-2432	144	25	effectively	effectively	ADV
cana-2432	144	26	captures	capture	VERB
cana-2432	144	27	essential	essential	ADJ
cana-2432	144	28	features	feature	NOUN
cana-2432	144	29	across	across	ADP
cana-2432	144	30	multiple	multiple	ADJ
cana-2432	144	31	scales	scale	NOUN
cana-2432	144	32	.	.	PUNCT
cana-2432	145	1	a	a	DET
cana-2432	145	2	total	total	NOUN
cana-2432	145	3	of	of	ADP
cana-2432	145	4	8,000	8,000	NUM
cana-2432	145	5	images	image	NOUN
cana-2432	145	6	are	be	AUX
cana-2432	145	7	used	use	VERB
cana-2432	145	8	for	for	ADP
cana-2432	145	9	four	four	NUM
cana-2432	145	10	-	-	PUNCT
cana-2432	145	11	class	class	NOUN
cana-2432	145	12	classification	classification	NOUN
cana-2432	145	13	,	,	PUNCT
cana-2432	145	14	with	with	ADP
cana-2432	145	15	2,000	2,000	NUM
cana-2432	145	16	images	image	NOUN
cana-2432	145	17	per	per	ADP
cana-2432	145	18	class	class	NOUN
cana-2432	145	19	.	.	PUNCT
cana-2432	146	1	for	for	ADP
cana-2432	146	2	two	two	NUM
cana-2432	146	3	-	-	PUNCT
cana-2432	146	4	class	class	NOUN
cana-2432	146	5	classification	classification	NOUN
cana-2432	146	6	,	,	PUNCT
cana-2432	146	7	5,000	5,000	NUM
cana-2432	146	8	images	image	NOUN
cana-2432	146	9	are	be	AUX
cana-2432	146	10	used	use	VERB
cana-2432	146	11	,	,	PUNCT
cana-2432	146	12	with	with	ADP
cana-2432	146	13	2,500	2,500	NUM
cana-2432	146	14	images	image	NOUN
cana-2432	146	15	from	from	ADP
cana-2432	146	16	each	each	DET
cana-2432	146	17	class	class	NOUN
cana-2432	146	18	being	be	AUX
cana-2432	146	19	used	use	VERB
cana-2432	146	20	for	for	ADP
cana-2432	146	21	analysis	analysis	NOUN
cana-2432	146	22	.	.	PUNCT
cana-2432	147	1	this	this	DET
cana-2432	147	2	multi	multi	ADJ
cana-2432	147	3	-	-	ADJ
cana-2432	147	4	resolution	resolution	NOUN
cana-2432	147	5	analysis	analysis	NOUN
cana-2432	147	6	helps	help	VERB
cana-2432	147	7	in	in	ADP
cana-2432	147	8	extracting	extract	VERB
cana-2432	147	9	features	feature	NOUN
cana-2432	147	10	that	that	PRON
cana-2432	147	11	are	be	AUX
cana-2432	147	12	both	both	PRON
cana-2432	147	13	spatially	spatially	ADV
cana-2432	147	14	and	and	CCONJ
cana-2432	147	15	frequency	frequency	NOUN
cana-2432	147	16	localized	localize	VERB
cana-2432	147	17	,	,	PUNCT
cana-2432	147	18	offering	offer	VERB
cana-2432	147	19	a	a	DET
cana-2432	147	20	rich	rich	ADJ
cana-2432	147	21	set	set	NOUN
cana-2432	147	22	of	of	ADP
cana-2432	147	23	information	information	NOUN
cana-2432	147	24	from	from	ADP
cana-2432	147	25	the	the	DET
cana-2432	147	26	x	x	NOUN
cana-2432	147	27	-	-	NOUN
cana-2432	147	28	ray	ray	NOUN
cana-2432	147	29	images	image	NOUN
cana-2432	147	30	.	.	PUNCT
cana-2432	148	1	these	these	DET
cana-2432	148	2	features	feature	NOUN
cana-2432	148	3	were	be	AUX
cana-2432	148	4	concatenated	concatenate	VERB
cana-2432	148	5	into	into	ADP
cana-2432	148	6	a	a	DET
cana-2432	148	7	single	single	ADJ
cana-2432	148	8	feature	feature	NOUN
cana-2432	148	9	set	set	NOUN
cana-2432	148	10	,	,	PUNCT
cana-2432	148	11	providing	provide	VERB
cana-2432	148	12	a	a	DET
cana-2432	148	13	rich	rich	ADJ
cana-2432	148	14	representation	representation	NOUN
cana-2432	148	15	of	of	ADP
cana-2432	148	16	the	the	DET
cana-2432	148	17	image	image	NOUN
cana-2432	148	18	data	datum	NOUN
cana-2432	148	19	with	with	ADP
cana-2432	148	20	32768	32768	NUM
cana-2432	148	21	features	feature	NOUN
cana-2432	148	22	extracted	extract	VERB
cana-2432	148	23	from	from	ADP
cana-2432	148	24	a	a	DET
cana-2432	148	25	two	two	NUM
cana-2432	148	26	-	-	PUNCT
cana-2432	148	27	level	level	NOUN
cana-2432	148	28	haar	haar	NOUN
cana-2432	148	29	wavelet	wavelet	NOUN
cana-2432	148	30	transform	transform	NOUN
cana-2432	148	31	,	,	PUNCT
cana-2432	148	32	as	as	SCONJ
cana-2432	148	33	shown	show	VERB
cana-2432	148	34	in	in	ADP
cana-2432	148	35	fig	fig	NOUN
cana-2432	148	36	.	.	PUNCT
cana-2432	149	1	3	3	X
cana-2432	149	2	.	.	X
cana-2432	149	3	the	the	DET
cana-2432	149	4	high	high	ADV
cana-2432	149	5	-	-	PUNCT
cana-2432	149	6	dimensional	dimensional	ADJ
cana-2432	149	7	feature	feature	NOUN
cana-2432	149	8	set	set	NOUN
cana-2432	149	9	,	,	PUNCT
cana-2432	149	10	while	while	SCONJ
cana-2432	149	11	comprehensive	comprehensive	ADJ
cana-2432	149	12	,	,	PUNCT
cana-2432	149	13	posed	pose	VERB
cana-2432	149	14	a	a	DET
cana-2432	149	15	challenge	challenge	NOUN
cana-2432	149	16	due	due	ADP
cana-2432	149	17	to	to	ADP
cana-2432	149	18	the	the	DET
cana-2432	149	19	potential	potential	ADJ
cana-2432	149	20	presence	presence	NOUN
cana-2432	149	21	of	of	ADP
cana-2432	149	22	irrelevant	irrelevant	ADJ
cana-2432	149	23	or	or	CCONJ
cana-2432	149	24	redundant	redundant	ADJ
cana-2432	149	25	features	feature	NOUN
cana-2432	149	26	.	.	PUNCT
cana-2432	150	1	fig.3	fig.3	PROPN
cana-2432	150	2	.	.	PROPN
cana-2432	150	3	concatenated	concatenate	VERB
cana-2432	150	4	features	feature	NOUN
cana-2432	150	5	(	(	PUNCT
cana-2432	150	6	32768	32768	NUM
cana-2432	150	7	)	)	PUNCT
cana-2432	150	8	extracted	extract	VERB
cana-2432	150	9	using	use	VERB
cana-2432	150	10	haar	haar	PROPN
cana-2432	150	11	wavelet	wavelet	NOUN
cana-2432	150	12	transform	transform	VERB
cana-2432	150	13	5.2	5.2	NUM
cana-2432	150	14	.	.	PUNCT
cana-2432	151	1	analysis	analysis	NOUN
cana-2432	151	2	of	of	ADP
cana-2432	151	3	bonferroni	bonferroni	NOUN
cana-2432	151	4	-	-	PUNCT
cana-2432	151	5	adjusted	adjust	VERB
cana-2432	151	6	anova	anova	PROPN
cana-2432	151	7	for	for	ADP
cana-2432	151	8	feature	feature	NOUN
cana-2432	151	9	selection	selection	NOUN
cana-2432	151	10	employing	employ	VERB
cana-2432	151	11	bonferroni	bonferroni	NOUN
cana-2432	151	12	-	-	PUNCT
cana-2432	151	13	adjusted	adjust	VERB
cana-2432	151	14	anova	anova	PROPN
cana-2432	151	15	for	for	ADP
cana-2432	151	16	feature	feature	NOUN
cana-2432	151	17	selection	selection	NOUN
cana-2432	151	18	proves	prove	VERB
cana-2432	151	19	beneficial	beneficial	ADJ
cana-2432	151	20	in	in	ADP
cana-2432	151	21	identifying	identify	VERB
cana-2432	151	22	the	the	DET
cana-2432	151	23	most	most	ADV
cana-2432	151	24	relevant	relevant	ADJ
cana-2432	151	25	16,384	16,384	NUM
cana-2432	151	26	features	feature	NOUN
cana-2432	151	27	from	from	ADP
cana-2432	151	28	the	the	DET
cana-2432	151	29	concatenated	concatenate	VERB
cana-2432	151	30	set	set	NOUN
cana-2432	151	31	of	of	ADP
cana-2432	151	32	32,768	32,768	NUM
cana-2432	151	33	features	feature	NOUN
cana-2432	151	34	shown	show	VERB
cana-2432	151	35	in	in	ADP
cana-2432	151	36	fig.4	fig.4	PROPN
cana-2432	151	37	.	.	PROPN
cana-2432	151	38	also	also	ADV
cana-2432	151	39	includes	include	VERB
cana-2432	151	40	bonferroni	bonferroni	NOUN
cana-2432	151	41	correction	correction	NOUN
cana-2432	151	42	to	to	PART
cana-2432	151	43	adjust	adjust	VERB
cana-2432	151	44	for	for	ADP
cana-2432	151	45	multiple	multiple	ADJ
cana-2432	151	46	tests	test	NOUN
cana-2432	151	47	,	,	PUNCT
cana-2432	151	48	ensuring	ensure	VERB
cana-2432	151	49	a	a	DET
cana-2432	151	50	stricter	strict	ADJ
cana-2432	151	51	control	control	NOUN
cana-2432	151	52	of	of	ADP
cana-2432	151	53	the	the	DET
cana-2432	151	54	false	false	ADJ
cana-2432	151	55	positive	positive	ADJ
cana-2432	151	56	rate	rate	NOUN
cana-2432	151	57	.	.	PUNCT
cana-2432	152	1	this	this	DET
cana-2432	152	2	step	step	NOUN
cana-2432	152	3	not	not	PART
cana-2432	152	4	only	only	ADV
cana-2432	152	5	reduces	reduce	VERB
cana-2432	152	6	dimensionality	dimensionality	NOUN
cana-2432	152	7	but	but	CCONJ
cana-2432	152	8	also	also	ADV
cana-2432	152	9	helps	help	VERB
cana-2432	152	10	eliminate	eliminate	VERB
cana-2432	152	11	redundant	redundant	ADJ
cana-2432	152	12	and	and	CCONJ
cana-2432	152	13	less	less	ADV
cana-2432	152	14	informative	informative	ADJ
cana-2432	152	15	features	feature	NOUN
cana-2432	152	16	.	.	PUNCT
cana-2432	153	1	the	the	DET
cana-2432	153	2	reduction	reduction	NOUN
cana-2432	153	3	in	in	ADP
cana-2432	153	4	dimensionality	dimensionality	NOUN
cana-2432	153	5	leads	lead	VERB
cana-2432	153	6	to	to	ADP
cana-2432	153	7	faster	fast	ADJ
cana-2432	153	8	training	training	NOUN
cana-2432	153	9	times	time	NOUN
cana-2432	153	10	and	and	CCONJ
cana-2432	153	11	less	less	ADV
cana-2432	153	12	computational	computational	ADJ
cana-2432	153	13	load	load	NOUN
cana-2432	153	14	on	on	ADP
cana-2432	153	15	the	the	DET
cana-2432	153	16	subsequent	subsequent	ADJ
cana-2432	153	17	cnn	cnn	PROPN
cana-2432	153	18	model	model	NOUN
cana-2432	153	19	.	.	PUNCT
cana-2432	154	1	fig.4	fig.4	PROPN
cana-2432	154	2	.	.	PROPN
cana-2432	155	1	features	feature	NOUN
cana-2432	155	2	(	(	PUNCT
cana-2432	155	3	16384	16384	NUM
cana-2432	155	4	)	)	PUNCT
cana-2432	155	5	selected	select	VERB
cana-2432	155	6	through	through	ADP
cana-2432	155	7	bonferroni	bonferroni	NOUN
cana-2432	155	8	-	-	PUNCT
cana-2432	155	9	adjusted	adjust	VERB
cana-2432	155	10	anova	anova	PROPN
cana-2432	155	11	feature	feature	NOUN
cana-2432	155	12	selection	selection	NOUN
cana-2432	155	13	5.3	5.3	NUM
cana-2432	155	14	.	.	PUNCT
cana-2432	156	1	results	result	NOUN
cana-2432	156	2	of	of	ADP
cana-2432	156	3	proposed	propose	VERB
cana-2432	156	4	wtan	wtan	PROPN
cana-2432	156	5	-	-	PUNCT
cana-2432	156	6	cnn	cnn	PROPN
cana-2432	156	7	with	with	ADP
cana-2432	156	8	transfer	transfer	NOUN
cana-2432	156	9	learning	learn	VERB
cana-2432	156	10	the	the	DET
cana-2432	156	11	selected	select	VERB
cana-2432	156	12	features	feature	NOUN
cana-2432	156	13	are	be	AUX
cana-2432	156	14	fed	feed	VERB
cana-2432	156	15	into	into	ADP
cana-2432	156	16	a	a	DET
cana-2432	156	17	cnn	cnn	NOUN
cana-2432	156	18	for	for	ADP
cana-2432	156	19	classification	classification	NOUN
cana-2432	156	20	.	.	PUNCT
cana-2432	157	1	the	the	DET
cana-2432	157	2	cnn	cnn	PROPN
cana-2432	157	3	,	,	PUNCT
cana-2432	157	4	trained	train	VERB
cana-2432	157	5	with	with	ADP
cana-2432	157	6	these	these	DET
cana-2432	157	7	optimized	optimize	VERB
cana-2432	157	8	features	feature	NOUN
cana-2432	157	9	,	,	PUNCT
cana-2432	157	10	shows	show	VERB
cana-2432	157	11	significant	significant	ADJ
cana-2432	157	12	improvement	improvement	NOUN
cana-2432	157	13	in	in	ADP
cana-2432	157	14	accuracy	accuracy	NOUN
cana-2432	157	15	and	and	CCONJ
cana-2432	157	16	robustness	robustness	NOUN
cana-2432	157	17	.	.	PUNCT
cana-2432	158	1	the	the	DET
cana-2432	158	2	reduction	reduction	NOUN
cana-2432	158	3	in	in	ADP
cana-2432	158	4	input	input	NOUN
cana-2432	158	5	feature	feature	NOUN
cana-2432	158	6	dimensionality	dimensionality	NOUN
cana-2432	158	7	ensures	ensure	VERB
cana-2432	158	8	that	that	SCONJ
cana-2432	158	9	the	the	DET
cana-2432	158	10	network	network	NOUN
cana-2432	158	11	focuses	focus	VERB
cana-2432	158	12	on	on	ADP
cana-2432	158	13	the	the	DET
cana-2432	158	14	most	most	ADV
cana-2432	158	15	informative	informative	ADJ
cana-2432	158	16	aspects	aspect	NOUN
cana-2432	158	17	,	,	PUNCT
cana-2432	158	18	enhancing	enhance	VERB
cana-2432	158	19	learning	learning	NOUN
cana-2432	158	20	efficiency	efficiency	NOUN
cana-2432	158	21	.	.	PUNCT
cana-2432	159	1	leveraging	leverage	VERB
cana-2432	159	2	transfer	transfer	NOUN
cana-2432	159	3	learning	learning	NOUN
cana-2432	159	4	by	by	ADP
cana-2432	159	5	using	use	VERB
cana-2432	159	6	pre	pre	ADJ
cana-2432	159	7	-	-	ADJ
cana-2432	159	8	trained	train	VERB
cana-2432	159	9	model	model	NOUN
cana-2432	159	10	such	such	ADJ
cana-2432	159	11	as	as	ADP
cana-2432	159	12	vgg19	vgg19	NOUN
cana-2432	159	13	further	far	ADV
cana-2432	159	14	boosts	boost	VERB
cana-2432	159	15	the	the	DET
cana-2432	159	16	cnn	cnn	PROPN
cana-2432	159	17	's	's	PART
cana-2432	159	18	performance	performance	NOUN
cana-2432	159	19	.	.	PUNCT
cana-2432	160	1	the	the	DET
cana-2432	160	2	results	result	NOUN
cana-2432	160	3	,	,	PUNCT
cana-2432	160	4	demonstrated	demonstrate	VERB
cana-2432	160	5	in	in	ADP
cana-2432	160	6	figures	figure	NOUN
cana-2432	160	7	5	5	NUM
cana-2432	160	8	and	and	CCONJ
cana-2432	160	9	6	6	NUM
cana-2432	160	10	,	,	PUNCT
cana-2432	160	11	include	include	VERB
cana-2432	160	12	an	an	DET
cana-2432	160	13	accuracy	accuracy	NOUN
cana-2432	160	14	graph	graph	NOUN
cana-2432	160	15	and	and	CCONJ
cana-2432	160	16	a	a	DET
cana-2432	160	17	classification	classification	NOUN
cana-2432	160	18	report	report	NOUN
cana-2432	160	19	.	.	PUNCT
cana-2432	161	1	communications	communication	NOUN
cana-2432	161	2	on	on	ADP
cana-2432	161	3	applied	apply	VERB
cana-2432	161	4	nonlinear	nonlinear	ADJ
cana-2432	161	5	analysis	analysis	NOUN
cana-2432	161	6	issn	issn	NOUN
cana-2432	161	7	:	:	PUNCT
cana-2432	161	8	1074	1074	NUM
cana-2432	161	9	-	-	PUNCT
cana-2432	161	10	133x	133x	NUM
cana-2432	161	11	vol	vol	NOUN
cana-2432	161	12	32	32	NUM
cana-2432	161	13	no	no	NOUN
cana-2432	161	14	.	.	PUNCT
cana-2432	162	1	2s	2s	NUM
cana-2432	162	2	(	(	PUNCT
cana-2432	162	3	2025	2025	NUM
cana-2432	162	4	)	)	PUNCT
cana-2432	162	5	432	432	NUM
cana-2432	162	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-2432	162	7	fig.5.accuracy	fig.5.accuracy	NUM
cana-2432	162	8	graph	graph	NOUN
cana-2432	162	9	of	of	ADP
cana-2432	162	10	a	a	DET
cana-2432	162	11	)	)	PUNCT
cana-2432	162	12	wtban	wtban	NOUN
cana-2432	162	13	-	-	PUNCT
cana-2432	162	14	cnn	cnn	PROPN
cana-2432	162	15	(	(	PUNCT
cana-2432	162	16	4	4	NUM
cana-2432	162	17	class	class	NOUN
cana-2432	162	18	)	)	PUNCT
cana-2432	162	19	b	b	NOUN
cana-2432	162	20	)	)	PUNCT
cana-2432	162	21	wtban	wtban	NOUN
cana-2432	162	22	-	-	PUNCT
cana-2432	162	23	cnn	cnn	PROPN
cana-2432	162	24	(	(	PUNCT
cana-2432	162	25	2	2	NUM
cana-2432	162	26	class	class	NOUN
cana-2432	162	27	)	)	PUNCT
cana-2432	162	28	fig.6.accuracy	fig.6.accuracy	NOUN
cana-2432	162	29	graph	graph	NOUN
cana-2432	162	30	of	of	ADP
cana-2432	162	31	c	c	NOUN
cana-2432	162	32	)	)	PUNCT
cana-2432	162	33	wtban	wtban	NOUN
cana-2432	162	34	-	-	PUNCT
cana-2432	162	35	cnn	cnn	PROPN
cana-2432	162	36	-	-	PUNCT
cana-2432	162	37	tl	tl	PROPN
cana-2432	162	38	(	(	PUNCT
cana-2432	162	39	4	4	NUM
cana-2432	162	40	class	class	NOUN
cana-2432	162	41	)	)	PUNCT
cana-2432	162	42	d	d	NOUN
cana-2432	162	43	)	)	PUNCT
cana-2432	162	44	wtban	wtban	NOUN
cana-2432	162	45	-	-	PUNCT
cana-2432	162	46	cnn	cnn	PROPN
cana-2432	162	47	-	-	PUNCT
cana-2432	162	48	tl	tl	PROPN
cana-2432	162	49	(	(	PUNCT
cana-2432	162	50	2	2	NUM
cana-2432	162	51	class	class	NOUN
cana-2432	162	52	)	)	PUNCT
cana-2432	162	53	fig.5	fig.5	NOUN
cana-2432	162	54	and	and	CCONJ
cana-2432	162	55	fig.6	fig.6	PROPN
cana-2432	162	56	illustrates	illustrate	VERB
cana-2432	162	57	that	that	SCONJ
cana-2432	162	58	the	the	DET
cana-2432	162	59	proposed	propose	VERB
cana-2432	162	60	wtban	wtban	NOUN
cana-2432	162	61	-	-	PUNCT
cana-2432	162	62	cnn	cnn	PROPN
cana-2432	162	63	-	-	PUNCT
cana-2432	162	64	tl	tl	PROPN
cana-2432	162	65	with	with	ADP
cana-2432	162	66	vgg19	vgg19	PROPN
cana-2432	162	67	achieves	achieve	VERB
cana-2432	162	68	an	an	DET
cana-2432	162	69	accuracy	accuracy	NOUN
cana-2432	162	70	of	of	ADP
cana-2432	162	71	88	88	NUM
cana-2432	162	72	%	%	NOUN
cana-2432	162	73	for	for	ADP
cana-2432	162	74	two	two	NUM
cana-2432	162	75	class	class	NOUN
cana-2432	162	76	classification	classification	NOUN
cana-2432	162	77	and	and	CCONJ
cana-2432	162	78	86	86	NUM
cana-2432	162	79	%	%	NOUN
cana-2432	162	80	for	for	ADP
cana-2432	162	81	four	four	NUM
cana-2432	162	82	-	-	PUNCT
cana-2432	162	83	class	class	NOUN
cana-2432	162	84	classification	classification	NOUN
cana-2432	162	85	.	.	PUNCT
cana-2432	163	1	the	the	DET
cana-2432	163	2	wtban	wtban	NOUN
cana-2432	163	3	-	-	PUNCT
cana-2432	163	4	cnn	cnn	PROPN
cana-2432	163	5	approach	approach	NOUN
cana-2432	163	6	without	without	ADP
cana-2432	163	7	transfer	transfer	NOUN
cana-2432	163	8	learning	learning	NOUN
cana-2432	163	9	achieves	achieve	VERB
cana-2432	163	10	an	an	DET
cana-2432	163	11	accuracy	accuracy	NOUN
cana-2432	163	12	of	of	ADP
cana-2432	163	13	82	82	NUM
cana-2432	163	14	%	%	NOUN
cana-2432	163	15	for	for	ADP
cana-2432	163	16	four	four	NUM
cana-2432	163	17	-	-	PUNCT
cana-2432	163	18	class	class	NOUN
cana-2432	163	19	classification	classification	NOUN
cana-2432	163	20	and	and	CCONJ
cana-2432	163	21	86	86	NUM
cana-2432	163	22	%	%	NOUN
cana-2432	163	23	for	for	ADP
cana-2432	163	24	binary	binary	ADJ
cana-2432	163	25	classification	classification	NOUN
cana-2432	163	26	of	of	ADP
cana-2432	163	27	lung	lung	NOUN
cana-2432	163	28	x	x	PROPN
cana-2432	163	29	-	-	NOUN
cana-2432	163	30	ray	ray	NOUN
cana-2432	163	31	data	datum	NOUN
cana-2432	163	32	set	set	VERB
cana-2432	163	33	.	.	PUNCT
cana-2432	164	1	for	for	ADP
cana-2432	164	2	the	the	DET
cana-2432	164	3	four	four	NUM
cana-2432	164	4	-	-	PUNCT
cana-2432	164	5	class	class	NOUN
cana-2432	164	6	classification	classification	NOUN
cana-2432	164	7	using	use	VERB
cana-2432	164	8	wtban	wtban	NOUN
cana-2432	164	9	-	-	PUNCT
cana-2432	164	10	cnn	cnn	PROPN
cana-2432	164	11	,	,	PUNCT
cana-2432	164	12	out	out	ADP
cana-2432	164	13	of	of	ADP
cana-2432	164	14	8,000	8,000	NUM
cana-2432	164	15	images	image	NOUN
cana-2432	164	16	,	,	PUNCT
cana-2432	164	17	6,400	6,400	NUM
cana-2432	164	18	are	be	AUX
cana-2432	164	19	used	use	VERB
cana-2432	164	20	for	for	ADP
cana-2432	164	21	training	training	NOUN
cana-2432	164	22	and	and	CCONJ
cana-2432	164	23	1,600	1,600	NUM
cana-2432	164	24	for	for	ADP
cana-2432	164	25	testing	testing	NOUN
cana-2432	164	26	.	.	PUNCT
cana-2432	165	1	in	in	ADP
cana-2432	165	2	the	the	DET
cana-2432	165	3	transfer	transfer	NOUN
cana-2432	165	4	learning	learning	NOUN
cana-2432	165	5	approach	approach	NOUN
cana-2432	165	6	,	,	PUNCT
cana-2432	165	7	10,000	10,000	NUM
cana-2432	165	8	images	image	NOUN
cana-2432	165	9	are	be	AUX
cana-2432	165	10	utilized	utilize	VERB
cana-2432	165	11	,	,	PUNCT
cana-2432	165	12	with	with	ADP
cana-2432	165	13	8,000	8,000	NUM
cana-2432	165	14	for	for	ADP
cana-2432	165	15	training	training	NOUN
cana-2432	165	16	and	and	CCONJ
cana-2432	165	17	2,000	2,000	NUM
cana-2432	165	18	for	for	ADP
cana-2432	165	19	testing	testing	NOUN
cana-2432	165	20	.	.	PUNCT
cana-2432	166	1	for	for	ADP
cana-2432	166	2	the	the	DET
cana-2432	166	3	two	two	NUM
cana-2432	166	4	-	-	PUNCT
cana-2432	166	5	class	class	NOUN
cana-2432	166	6	classification	classification	NOUN
cana-2432	166	7	,	,	PUNCT
cana-2432	166	8	from	from	ADP
cana-2432	166	9	a	a	DET
cana-2432	166	10	total	total	NOUN
cana-2432	166	11	of	of	ADP
cana-2432	166	12	5,000	5,000	NUM
cana-2432	166	13	images	image	NOUN
cana-2432	166	14	,	,	PUNCT
cana-2432	166	15	4,000	4,000	NUM
cana-2432	166	16	are	be	AUX
cana-2432	166	17	allocated	allocate	VERB
cana-2432	166	18	for	for	ADP
cana-2432	166	19	training	training	NOUN
cana-2432	166	20	and	and	CCONJ
cana-2432	166	21	1,000	1,000	NUM
cana-2432	166	22	for	for	ADP
cana-2432	166	23	testing	testing	NOUN
cana-2432	166	24	in	in	ADP
cana-2432	166	25	both	both	DET
cana-2432	166	26	approaches	approach	NOUN
cana-2432	166	27	,	,	PUNCT
cana-2432	166	28	as	as	SCONJ
cana-2432	166	29	shown	show	VERB
cana-2432	166	30	in	in	ADP
cana-2432	166	31	fig.7	fig.7	ADJ
cana-2432	166	32	.	.	PUNCT
cana-2432	167	1	fig.7.classification	fig.7.classification	PROPN
cana-2432	167	2	report	report	NOUN
cana-2432	167	3	of	of	ADP
cana-2432	167	4	a	a	DET
cana-2432	167	5	)	)	PUNCT
cana-2432	167	6	wtban	wtban	NOUN
cana-2432	167	7	-	-	PUNCT
cana-2432	167	8	cnn	cnn	PROPN
cana-2432	167	9	(	(	PUNCT
cana-2432	167	10	4	4	NUM
cana-2432	167	11	class	class	NOUN
cana-2432	167	12	)	)	PUNCT
cana-2432	167	13	b	b	NOUN
cana-2432	167	14	)	)	PUNCT
cana-2432	167	15	wtban	wtban	NOUN
cana-2432	167	16	-	-	PUNCT
cana-2432	167	17	cnn	cnn	PROPN
cana-2432	167	18	(	(	PUNCT
cana-2432	167	19	2	2	NUM
cana-2432	167	20	class	class	NOUN
cana-2432	167	21	)	)	PUNCT
cana-2432	167	22	c	c	NOUN
cana-2432	167	23	)	)	PUNCT
cana-2432	167	24	proposed	propose	VERB
cana-2432	167	25	wtban	wtban	NOUN
cana-2432	167	26	-	-	PUNCT
cana-2432	167	27	cnn	cnn	PROPN
cana-2432	167	28	-	-	PUNCT
cana-2432	167	29	tl	tl	PROPN
cana-2432	167	30	(	(	PUNCT
cana-2432	167	31	4	4	NUM
cana-2432	167	32	class	class	NOUN
cana-2432	167	33	)	)	PUNCT
cana-2432	168	1	d	d	NOUN
cana-2432	168	2	)	)	PUNCT
cana-2432	168	3	proposed	propose	VERB
cana-2432	168	4	wtban	wtban	NOUN
cana-2432	168	5	-	-	PUNCT
cana-2432	168	6	cnn	cnn	PROPN
cana-2432	168	7	-	-	PUNCT
cana-2432	168	8	tl	tl	PROPN
cana-2432	168	9	(	(	PUNCT
cana-2432	168	10	2	2	NUM
cana-2432	168	11	class	class	NOUN
cana-2432	168	12	)	)	PUNCT
cana-2432	168	13	communications	communication	NOUN
cana-2432	168	14	on	on	ADP
cana-2432	168	15	applied	apply	VERB
cana-2432	168	16	nonlinear	nonlinear	ADJ
cana-2432	168	17	analysis	analysis	NOUN
cana-2432	168	18	issn	issn	NOUN
cana-2432	168	19	:	:	PUNCT
cana-2432	168	20	1074	1074	NUM
cana-2432	168	21	-	-	PUNCT
cana-2432	168	22	133x	133x	NUM
cana-2432	168	23	vol	vol	NOUN
cana-2432	168	24	32	32	NUM
cana-2432	168	25	no	no	NOUN
cana-2432	168	26	.	.	PUNCT
cana-2432	169	1	2s	2s	NUM
cana-2432	169	2	(	(	PUNCT
cana-2432	169	3	2025	2025	NUM
cana-2432	169	4	)	)	PUNCT
cana-2432	169	5	433	433	NUM
cana-2432	169	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-2432	169	7	5.4	5.4	NUM
cana-2432	169	8	.	.	PUNCT
cana-2432	169	9	comparison	comparison	NOUN
cana-2432	169	10	with	with	ADP
cana-2432	169	11	genetic	genetic	ADJ
cana-2432	169	12	algorithm	algorithm	NOUN
cana-2432	169	13	-	-	PUNCT
cana-2432	169	14	based	base	VERB
cana-2432	169	15	feature	feature	NOUN
cana-2432	169	16	selection	selection	NOUN
cana-2432	169	17	in	in	ADP
cana-2432	169	18	the	the	DET
cana-2432	169	19	comparative	comparative	ADJ
cana-2432	169	20	analysis	analysis	NOUN
cana-2432	169	21	,	,	PUNCT
cana-2432	169	22	anova	anova	PROPN
cana-2432	169	23	demonstrates	demonstrate	VERB
cana-2432	169	24	a	a	DET
cana-2432	169	25	more	more	ADV
cana-2432	169	26	straightforward	straightforward	ADJ
cana-2432	169	27	and	and	CCONJ
cana-2432	169	28	computationally	computationally	ADV
cana-2432	169	29	efficient	efficient	ADJ
cana-2432	169	30	approach	approach	NOUN
cana-2432	169	31	for	for	ADP
cana-2432	169	32	feature	feature	NOUN
cana-2432	169	33	selection	selection	NOUN
cana-2432	169	34	.	.	PUNCT
cana-2432	170	1	while	while	SCONJ
cana-2432	170	2	the	the	DET
cana-2432	170	3	genetic	genetic	ADJ
cana-2432	170	4	algorithm	algorithm	NOUN
cana-2432	170	5	(	(	PUNCT
cana-2432	170	6	ga	ga	NOUN
cana-2432	170	7	)	)	PUNCT
cana-2432	170	8	offers	offer	VERB
cana-2432	170	9	a	a	DET
cana-2432	170	10	robust	robust	ADJ
cana-2432	170	11	search	search	NOUN
cana-2432	170	12	mechanism	mechanism	NOUN
cana-2432	170	13	,	,	PUNCT
cana-2432	170	14	it	it	PRON
cana-2432	170	15	is	be	AUX
cana-2432	170	16	generally	generally	ADV
cana-2432	170	17	more	more	ADJ
cana-2432	170	18	resource	resource	NOUN
cana-2432	170	19	-	-	PUNCT
cana-2432	170	20	intensive	intensive	ADJ
cana-2432	170	21	and	and	CCONJ
cana-2432	170	22	time	time	NOUN
cana-2432	170	23	-	-	PUNCT
cana-2432	170	24	consuming	consume	VERB
cana-2432	170	25	compared	compare	VERB
cana-2432	170	26	to	to	ADP
cana-2432	170	27	anova	anova	PROPN
cana-2432	170	28	.	.	PUNCT
cana-2432	171	1	the	the	DET
cana-2432	171	2	experiments	experiment	NOUN
cana-2432	171	3	indicate	indicate	VERB
cana-2432	171	4	that	that	SCONJ
cana-2432	171	5	anova	anova	PROPN
cana-2432	171	6	selected	select	VERB
cana-2432	171	7	features	feature	NOUN
cana-2432	171	8	achieve	achieve	VERB
cana-2432	171	9	comparable	comparable	ADJ
cana-2432	171	10	results	result	NOUN
cana-2432	171	11	in	in	ADP
cana-2432	171	12	terms	term	NOUN
cana-2432	171	13	of	of	ADP
cana-2432	171	14	classification	classification	NOUN
cana-2432	171	15	accuracy	accuracy	NOUN
cana-2432	171	16	and	and	CCONJ
cana-2432	171	17	computational	computational	ADJ
cana-2432	171	18	efficiency	efficiency	NOUN
cana-2432	171	19	.	.	PUNCT
cana-2432	172	1	table	table	NOUN
cana-2432	172	2	ii	ii	PROPN
cana-2432	172	3	shows	show	VERB
cana-2432	172	4	the	the	DET
cana-2432	172	5	comparison	comparison	NOUN
cana-2432	172	6	results	result	VERB
cana-2432	172	7	.	.	PUNCT
cana-2432	173	1	table	table	NOUN
cana-2432	173	2	ii	ii	PROPN
cana-2432	173	3	accuracy	accuracy	NOUN
cana-2432	173	4	results	result	NOUN
cana-2432	173	5	of	of	ADP
cana-2432	173	6	proposed	propose	VERB
cana-2432	173	7	wtan	wtan	PROPN
cana-2432	173	8	-	-	PUNCT
cana-2432	173	9	cnn	cnn	PROPN
cana-2432	173	10	-	-	PUNCT
cana-2432	173	11	tl	tl	PROPN
cana-2432	173	12	,	,	PUNCT
cana-2432	173	13	wtan	wtan	PROPN
cana-2432	173	14	-	-	PUNCT
cana-2432	173	15	cnn	cnn	PROPN
cana-2432	173	16	and	and	CCONJ
cana-2432	173	17	ga	ga	PROPN
cana-2432	173	18	selected	select	VERB
cana-2432	173	19	features	feature	VERB
cana-2432	173	20	6	6	NUM
cana-2432	173	21	.	.	PUNCT
cana-2432	173	22	conclusion	conclusion	NOUN
cana-2432	173	23	the	the	DET
cana-2432	173	24	proposed	propose	VERB
cana-2432	173	25	(	(	PUNCT
cana-2432	173	26	wtban	wtban	NOUN
cana-2432	173	27	-	-	PUNCT
cana-2432	173	28	cnn	cnn	PROPN
cana-2432	173	29	-	-	PUNCT
cana-2432	173	30	tl	tl	PROPN
cana-2432	173	31	)	)	PUNCT
cana-2432	173	32	comprehensive	comprehensive	ADJ
cana-2432	173	33	approach	approach	NOUN
cana-2432	173	34	for	for	ADP
cana-2432	173	35	lung	lung	NOUN
cana-2432	173	36	x	x	PROPN
cana-2432	173	37	-	-	NOUN
cana-2432	173	38	ray	ray	NOUN
cana-2432	173	39	image	image	NOUN
cana-2432	173	40	classification	classification	NOUN
cana-2432	173	41	effectively	effectively	ADV
cana-2432	173	42	combines	combine	VERB
cana-2432	173	43	wavelet	wavelet	NOUN
cana-2432	173	44	transform	transform	NOUN
cana-2432	173	45	-	-	PUNCT
cana-2432	173	46	based	base	VERB
cana-2432	173	47	feature	feature	NOUN
cana-2432	173	48	extraction	extraction	NOUN
cana-2432	173	49	,	,	PUNCT
cana-2432	173	50	bonferroni	bonferroni	NOUN
cana-2432	173	51	anova	anova	PROPN
cana-2432	173	52	feature	feature	NOUN
cana-2432	173	53	selection	selection	NOUN
cana-2432	173	54	,	,	PUNCT
cana-2432	173	55	and	and	CCONJ
cana-2432	173	56	deep	deep	ADJ
cana-2432	173	57	learning	learning	NOUN
cana-2432	173	58	techniques	technique	NOUN
cana-2432	173	59	.	.	PUNCT
cana-2432	174	1	by	by	ADP
cana-2432	174	2	using	use	VERB
cana-2432	174	3	wavelet	wavelet	NOUN
cana-2432	174	4	transform	transform	NOUN
cana-2432	174	5	,	,	PUNCT
cana-2432	174	6	essential	essential	ADJ
cana-2432	174	7	features	feature	NOUN
cana-2432	174	8	are	be	AUX
cana-2432	174	9	captured	capture	VERB
cana-2432	174	10	across	across	ADP
cana-2432	174	11	multiple	multiple	ADJ
cana-2432	174	12	scales	scale	NOUN
cana-2432	174	13	and	and	CCONJ
cana-2432	174	14	concatenated	concatenate	VERB
cana-2432	174	15	to	to	PART
cana-2432	174	16	form	form	VERB
cana-2432	174	17	a	a	DET
cana-2432	174	18	rich	rich	ADJ
cana-2432	174	19	feature	feature	NOUN
cana-2432	174	20	set	set	NOUN
cana-2432	174	21	.	.	PUNCT
cana-2432	175	1	bonferroni	bonferroni	PROPN
cana-2432	175	2	anova	anova	PROPN
cana-2432	175	3	is	be	AUX
cana-2432	175	4	then	then	ADV
cana-2432	175	5	employed	employ	VERB
cana-2432	175	6	to	to	PART
cana-2432	175	7	select	select	VERB
cana-2432	175	8	the	the	DET
cana-2432	175	9	most	most	ADV
cana-2432	175	10	relevant	relevant	ADJ
cana-2432	175	11	features	feature	NOUN
cana-2432	175	12	with	with	ADP
cana-2432	175	13	less	less	ADV
cana-2432	175	14	false	false	ADJ
cana-2432	175	15	positive	positive	ADJ
cana-2432	175	16	rate	rate	NOUN
cana-2432	175	17	,	,	PUNCT
cana-2432	175	18	reducing	reduce	VERB
cana-2432	175	19	the	the	DET
cana-2432	175	20	feature	feature	NOUN
cana-2432	175	21	set	set	VERB
cana-2432	175	22	from	from	ADP
cana-2432	175	23	32,768	32,768	NUM
cana-2432	175	24	to	to	ADP
cana-2432	175	25	16,384	16,384	NUM
cana-2432	175	26	features	feature	NOUN
cana-2432	175	27	.	.	PUNCT
cana-2432	176	1	this	this	DET
cana-2432	176	2	dimensionality	dimensionality	NOUN
cana-2432	176	3	reduction	reduction	NOUN
cana-2432	176	4	not	not	PART
cana-2432	176	5	only	only	ADV
cana-2432	176	6	streamlines	streamline	VERB
cana-2432	176	7	the	the	DET
cana-2432	176	8	dataset	dataset	NOUN
cana-2432	176	9	but	but	CCONJ
cana-2432	176	10	also	also	ADV
cana-2432	176	11	enhances	enhance	VERB
cana-2432	176	12	the	the	DET
cana-2432	176	13	efficiency	efficiency	NOUN
cana-2432	176	14	of	of	ADP
cana-2432	176	15	the	the	DET
cana-2432	176	16	subsequent	subsequent	ADJ
cana-2432	176	17	cnn	cnn	PROPN
cana-2432	176	18	model	model	NOUN
cana-2432	176	19	,	,	PUNCT
cana-2432	176	20	leading	lead	VERB
cana-2432	176	21	to	to	ADP
cana-2432	176	22	faster	fast	ADJ
cana-2432	176	23	training	training	NOUN
cana-2432	176	24	times	time	NOUN
cana-2432	176	25	and	and	CCONJ
cana-2432	176	26	lower	low	ADJ
cana-2432	176	27	computational	computational	ADJ
cana-2432	176	28	resource	resource	NOUN
cana-2432	176	29	requirements	requirement	NOUN
cana-2432	176	30	.	.	PUNCT
cana-2432	177	1	the	the	DET
cana-2432	177	2	comparative	comparative	ADJ
cana-2432	177	3	analysis	analysis	NOUN
cana-2432	177	4	with	with	ADP
cana-2432	177	5	genetic	genetic	ADJ
cana-2432	177	6	algorithm	algorithm	NOUN
cana-2432	177	7	-	-	PUNCT
cana-2432	177	8	based	base	VERB
cana-2432	177	9	feature	feature	NOUN
cana-2432	177	10	selection	selection	NOUN
cana-2432	177	11	highlights	highlight	VERB
cana-2432	177	12	the	the	DET
cana-2432	177	13	efficiency	efficiency	NOUN
cana-2432	177	14	and	and	CCONJ
cana-2432	177	15	simplicity	simplicity	NOUN
cana-2432	177	16	of	of	ADP
cana-2432	177	17	bonferroni	bonferroni	NOUN
cana-2432	177	18	adjusted	adjust	VERB
cana-2432	177	19	anova	anova	PROPN
cana-2432	177	20	,	,	PUNCT
cana-2432	177	21	which	which	PRON
cana-2432	177	22	achieves	achieve	VERB
cana-2432	177	23	comparable	comparable	ADJ
cana-2432	177	24	results	result	NOUN
cana-2432	177	25	with	with	ADP
cana-2432	177	26	less	less	ADV
cana-2432	177	27	computational	computational	ADJ
cana-2432	177	28	overhead	overhead	NOUN
cana-2432	177	29	.	.	PUNCT
cana-2432	178	1	feeding	feed	VERB
cana-2432	178	2	the	the	DET
cana-2432	178	3	selected	select	VERB
cana-2432	178	4	features	feature	NOUN
cana-2432	178	5	into	into	ADP
cana-2432	178	6	a	a	DET
cana-2432	178	7	cnn	cnn	NOUN
cana-2432	178	8	demonstrates	demonstrate	VERB
cana-2432	178	9	significant	significant	ADJ
cana-2432	178	10	improvements	improvement	NOUN
cana-2432	178	11	in	in	ADP
cana-2432	178	12	classification	classification	NOUN
cana-2432	178	13	accuracy	accuracy	NOUN
cana-2432	178	14	,	,	PUNCT
cana-2432	178	15	and	and	CCONJ
cana-2432	178	16	the	the	DET
cana-2432	178	17	use	use	NOUN
cana-2432	178	18	of	of	ADP
cana-2432	178	19	transfer	transfer	NOUN
cana-2432	178	20	learning	learning	NOUN
cana-2432	178	21	with	with	ADP
cana-2432	178	22	pre	pre	ADJ
cana-2432	178	23	-	-	ADJ
cana-2432	178	24	trained	train	VERB
cana-2432	178	25	models	model	NOUN
cana-2432	178	26	further	far	ADV
cana-2432	178	27	boosts	boost	VERB
cana-2432	178	28	performance	performance	NOUN
cana-2432	178	29	.	.	PUNCT
cana-2432	179	1	references	reference	NOUN
cana-2432	179	2	[	[	X
cana-2432	179	3	1	1	NUM
cana-2432	179	4	]	]	PUNCT
cana-2432	179	5	farhan	farhan	PROPN
cana-2432	179	6	amq	amq	PROPN
cana-2432	179	7	,	,	PUNCT
cana-2432	179	8	yang	yang	PROPN
cana-2432	179	9	s.	s.	PROPN
cana-2432	179	10	automatic	automatic	ADJ
cana-2432	179	11	lung	lung	NOUN
cana-2432	179	12	disease	disease	NOUN
cana-2432	179	13	classification	classification	NOUN
cana-2432	179	14	from	from	ADP
cana-2432	179	15	the	the	DET
cana-2432	179	16	chest	chest	NOUN
cana-2432	179	17	x	x	NOUN
cana-2432	179	18	-	-	NOUN
cana-2432	179	19	ray	ray	NOUN
cana-2432	179	20	images	image	NOUN
cana-2432	179	21	using	use	VERB
cana-2432	179	22	hybrid	hybrid	ADJ
cana-2432	179	23	deep	deep	ADJ
cana-2432	179	24	learning	learning	NOUN
cana-2432	179	25	algorithm	algorithm	NOUN
cana-2432	179	26	.	.	PUNCT
cana-2432	180	1	multimed	multime	VERB
cana-2432	180	2	tools	tool	NOUN
cana-2432	180	3	appl	appl	NOUN
cana-2432	180	4	.	.	PUNCT
cana-2432	181	1	2023	2023	NUM
cana-2432	181	2	mar	mar	PROPN
cana-2432	181	3	22:1	22:1	NUM
cana-2432	181	4	-	-	SYM
cana-2432	181	5	27	27	NUM
cana-2432	181	6	.	.	PUNCT
cana-2432	182	1	[	[	X
cana-2432	182	2	2	2	NUM
cana-2432	182	3	]	]	X
cana-2432	182	4	goyal	goyal	PROPN
cana-2432	182	5	s	s	PROPN
cana-2432	182	6	,	,	PUNCT
cana-2432	182	7	singh	singh	PROPN
cana-2432	182	8	r.	r.	PROPN
cana-2432	182	9	detection	detection	PROPN
cana-2432	182	10	and	and	CCONJ
cana-2432	182	11	classification	classification	NOUN
cana-2432	182	12	of	of	ADP
cana-2432	182	13	lung	lung	NOUN
cana-2432	182	14	diseases	disease	NOUN
cana-2432	182	15	for	for	ADP
cana-2432	182	16	pneumonia	pneumonia	NOUN
cana-2432	182	17	and	and	CCONJ
cana-2432	182	18	covid-19	covid-19	PROPN
cana-2432	182	19	using	use	VERB
cana-2432	182	20	machine	machine	NOUN
cana-2432	182	21	and	and	CCONJ
cana-2432	182	22	deep	deep	ADJ
cana-2432	182	23	learning	learning	NOUN
cana-2432	182	24	techniques	technique	NOUN
cana-2432	182	25	.	.	PUNCT
cana-2432	183	1	j	j	PROPN
cana-2432	183	2	ambient	ambient	PROPN
cana-2432	183	3	intell	intell	PROPN
cana-2432	183	4	humaniz	humaniz	VERB
cana-2432	183	5	comput	comput	NOUN
cana-2432	183	6	.	.	PUNCT
cana-2432	184	1	2023;14(4):3239	2023;14(4):3239	NUM
cana-2432	184	2	-	-	PUNCT
cana-2432	184	3	3259	3259	NUM
cana-2432	184	4	.	.	PUNCT
cana-2432	185	1	method	method	NOUN
cana-2432	185	2	train	train	NOUN
cana-2432	185	3	accuracy	accuracy	NOUN
cana-2432	185	4	(	(	PUNCT
cana-2432	185	5	%	%	INTJ
cana-2432	185	6	)	)	PUNCT
cana-2432	185	7	test	test	NOUN
cana-2432	185	8	accuracy	accuracy	NOUN
cana-2432	185	9	(	(	PUNCT
cana-2432	185	10	%	%	INTJ
cana-2432	185	11	)	)	PUNCT
cana-2432	185	12	epochs	epoch	VERB
cana-2432	185	13	wtban	wtban	NOUN
cana-2432	185	14	-	-	PUNCT
cana-2432	185	15	cnn	cnn	PROPN
cana-2432	185	16	(	(	PUNCT
cana-2432	185	17	2	2	NUM
cana-2432	185	18	class	class	NOUN
cana-2432	185	19	)	)	PUNCT
cana-2432	185	20	88	88	NUM
cana-2432	185	21	86	86	NUM
cana-2432	185	22	20	20	NUM
cana-2432	185	23	wtban	wtban	NOUN
cana-2432	185	24	-	-	PUNCT
cana-2432	185	25	cnn	cnn	PROPN
cana-2432	185	26	(	(	PUNCT
cana-2432	185	27	4	4	NUM
cana-2432	185	28	class	class	NOUN
cana-2432	185	29	)	)	PUNCT
cana-2432	185	30	83	83	NUM
cana-2432	185	31	82	82	NUM
cana-2432	185	32	20	20	NUM
cana-2432	185	33	proposed	propose	VERB
cana-2432	185	34	wtban	wtban	NOUN
cana-2432	185	35	-	-	PUNCT
cana-2432	185	36	cnntl	cnntl	NOUN
cana-2432	185	37	(	(	PUNCT
cana-2432	185	38	vgg19)(2	vgg19)(2	NOUN
cana-2432	185	39	class	class	NOUN
cana-2432	185	40	)	)	PUNCT
cana-2432	185	41	98	98	NUM
cana-2432	185	42	88	88	NUM
cana-2432	185	43	10	10	NUM
cana-2432	185	44	proposed	propose	VERB
cana-2432	185	45	wtban	wtban	NOUN
cana-2432	185	46	-	-	PUNCT
cana-2432	185	47	cnntl	cnntl	NOUN
cana-2432	185	48	(	(	PUNCT
cana-2432	185	49	vgg19)(4	vgg19)(4	NOUN
cana-2432	185	50	class	class	NOUN
cana-2432	185	51	)	)	PUNCT
cana-2432	185	52	95	95	NUM
cana-2432	185	53	86	86	NUM
cana-2432	185	54	10	10	NUM
cana-2432	185	55	wt	wt	NOUN
cana-2432	185	56	with	with	ADP
cana-2432	185	57	genetic	genetic	ADJ
cana-2432	185	58	algorithm	algorithm	NOUN
cana-2432	185	59	based	base	VERB
cana-2432	185	60	cnn(2	cnn(2	ADJ
cana-2432	185	61	class	class	NOUN
cana-2432	185	62	)	)	PUNCT
cana-2432	185	63	49	49	NUM
cana-2432	185	64	50	50	NUM
cana-2432	185	65	10	10	NUM
cana-2432	185	66	wt	wt	NOUN
cana-2432	185	67	with	with	ADP
cana-2432	185	68	genetic	genetic	ADJ
cana-2432	185	69	algorithm	algorithm	NOUN
cana-2432	185	70	based	base	VERB
cana-2432	185	71	cnn	cnn	PROPN
cana-2432	185	72	(	(	PUNCT
cana-2432	185	73	4	4	NUM
cana-2432	185	74	class	class	NOUN
cana-2432	185	75	)	)	PUNCT
cana-2432	185	76	81	81	NUM
cana-2432	185	77	76	76	NUM
cana-2432	185	78	10	10	NUM
cana-2432	185	79	communications	communication	NOUN
cana-2432	185	80	on	on	ADP
cana-2432	185	81	applied	apply	VERB
cana-2432	185	82	nonlinear	nonlinear	ADJ
cana-2432	185	83	analysis	analysis	NOUN
cana-2432	185	84	issn	issn	NOUN
cana-2432	185	85	:	:	PUNCT
cana-2432	185	86	1074	1074	NUM
cana-2432	185	87	-	-	PUNCT
cana-2432	185	88	133x	133x	NUM
cana-2432	185	89	vol	vol	NOUN
cana-2432	185	90	32	32	NUM
cana-2432	185	91	no	no	NOUN
cana-2432	185	92	.	.	PUNCT
cana-2432	186	1	2s	2s	NUM
cana-2432	186	2	(	(	PUNCT
cana-2432	186	3	2025	2025	NUM
cana-2432	186	4	)	)	PUNCT
cana-2432	186	5	434	434	NUM
cana-2432	186	6	https://internationalpubls.com	https://internationalpubls.com	X
cana-2432	187	1	[	[	X
cana-2432	187	2	3	3	X
cana-2432	187	3	]	]	X
cana-2432	187	4	el	el	PROPN
cana-2432	187	5	-	-	PUNCT
cana-2432	187	6	shafai	shafai	PROPN
cana-2432	187	7	,	,	PUNCT
cana-2432	187	8	w.	w.	PROPN
cana-2432	187	9	,	,	PUNCT
cana-2432	187	10	ghandour	ghandour	PROPN
cana-2432	187	11	,	,	PUNCT
cana-2432	187	12	c.	c.	PROPN
cana-2432	187	13	&	&	CCONJ
cana-2432	187	14	el	el	PROPN
cana-2432	187	15	-	-	PROPN
cana-2432	187	16	rabaie	rabaie	PROPN
cana-2432	187	17	,	,	PUNCT
cana-2432	187	18	s.	s.	PROPN
cana-2432	187	19	improving	improve	VERB
cana-2432	187	20	traditional	traditional	ADJ
cana-2432	187	21	method	method	NOUN
cana-2432	187	22	used	use	VERB
cana-2432	187	23	for	for	ADP
cana-2432	187	24	medical	medical	ADJ
cana-2432	187	25	image	image	NOUN
cana-2432	187	26	fusion	fusion	NOUN
cana-2432	187	27	by	by	ADP
cana-2432	187	28	deep	deep	ADJ
cana-2432	187	29	learning	learning	NOUN
cana-2432	187	30	approach	approach	NOUN
cana-2432	187	31	-	-	PUNCT
cana-2432	187	32	based	base	VERB
cana-2432	187	33	convolution	convolution	NOUN
cana-2432	187	34	neural	neural	ADJ
cana-2432	187	35	network	network	NOUN
cana-2432	187	36	.	.	PUNCT
cana-2432	188	1	j	j	PROPN
cana-2432	188	2	opt	opt	VERB
cana-2432	188	3	52	52	NUM
cana-2432	188	4	,	,	PUNCT
cana-2432	188	5	2253–2263	2253–2263	NUM
cana-2432	188	6	(	(	PUNCT
cana-2432	188	7	2023	2023	NUM
cana-2432	188	8	)	)	PUNCT
cana-2432	188	9	.	.	PUNCT
cana-2432	189	1	https://doi.org/10.1007/s12596023-01123-y	https://doi.org/10.1007/s12596023-01123-y	NOUN
cana-2432	189	2	.	.	PUNCT
cana-2432	190	1	[	[	X
cana-2432	190	2	4	4	NUM
cana-2432	190	3	]	]	X
cana-2432	190	4	shreyesh	shreyesh	NOUN
cana-2432	190	5	doppalapudi	doppalapudi	PROPN
cana-2432	190	6	,	,	PUNCT
cana-2432	190	7	robin	robin	PROPN
cana-2432	190	8	g.	g.	PROPN
cana-2432	190	9	qiu	qiu	PROPN
cana-2432	190	10	,	,	PUNCT
cana-2432	190	11	youakim	youakim	NOUN
cana-2432	190	12	badr	badr	PROPN
cana-2432	190	13	,	,	PUNCT
cana-2432	190	14	lung	lung	NOUN
cana-2432	190	15	cancer	cancer	NOUN
cana-2432	190	16	survival	survival	PROPN
cana-2432	190	17	period	period	NOUN
cana-2432	190	18	prediction	prediction	NOUN
cana-2432	190	19	and	and	CCONJ
cana-2432	190	20	understanding	understanding	NOUN
cana-2432	190	21	:	:	PUNCT
cana-2432	190	22	deep	deep	ADJ
cana-2432	190	23	learning	learning	NOUN
cana-2432	190	24	approaches	approach	NOUN
cana-2432	190	25	,	,	PUNCT
cana-2432	190	26	international	international	ADJ
cana-2432	190	27	journal	journal	NOUN
cana-2432	190	28	of	of	ADP
cana-2432	190	29	medical	medical	ADJ
cana-2432	190	30	informatics	informatic	NOUN
cana-2432	190	31	,	,	PUNCT
cana-2432	190	32	volume	volume	NOUN
cana-2432	190	33	148	148	NUM
cana-2432	190	34	,	,	PUNCT
cana-2432	190	35	2021	2021	NUM
cana-2432	190	36	,	,	PUNCT
cana-2432	190	37	104371	104371	NUM
cana-2432	190	38	,	,	PUNCT
cana-2432	190	39	issn	issn	PROPN
cana-2432	190	40	13865056	13865056	NUM
cana-2432	190	41	.	.	PUNCT
cana-2432	191	1	[	[	X
cana-2432	191	2	5	5	NUM
cana-2432	191	3	]	]	PUNCT
cana-2432	191	4	qiao	qiao	NOUN
cana-2432	191	5	,	,	PUNCT
cana-2432	191	6	yu‐long	yu‐long	NOUN
cana-2432	191	7	&	&	CCONJ
cana-2432	191	8	zhao	zhao	PROPN
cana-2432	191	9	,	,	PUNCT
cana-2432	191	10	yue	yue	PROPN
cana-2432	191	11	&	&	CCONJ
cana-2432	191	12	song	song	PROPN
cana-2432	191	13	,	,	PUNCT
cana-2432	191	14	chun‐yan	chun‐yan	PROPN
cana-2432	191	15	&	&	CCONJ
cana-2432	191	16	zhang	zhang	PROPN
cana-2432	191	17	,	,	PUNCT
cana-2432	191	18	kai‐ge	kai‐ge	PROPN
cana-2432	191	19	&	&	CCONJ
cana-2432	191	20	xiang	xiang	PROPN
cana-2432	191	21	,	,	PUNCT
cana-2432	191	22	xue‐zhi	xue‐zhi	PROPN
cana-2432	191	23	.	.	PUNCT
cana-2432	191	24	(	(	PUNCT
cana-2432	191	25	2021	2021	NUM
cana-2432	191	26	)	)	PUNCT
cana-2432	191	27	.	.	PUNCT
cana-2432	192	1	graph	graph	NOUN
cana-2432	192	2	wavelet	wavelet	NOUN
cana-2432	192	3	transform	transform	NOUN
cana-2432	192	4	for	for	ADP
cana-2432	192	5	image	image	NOUN
cana-2432	192	6	texture	texture	NOUN
cana-2432	192	7	classification	classification	NOUN
cana-2432	192	8	.	.	PUNCT
cana-2432	193	1	iet	iet	PROPN
cana-2432	193	2	image	image	NOUN
cana-2432	193	3	processing	processing	NOUN
cana-2432	193	4	.	.	PUNCT
cana-2432	194	1	15	15	NUM
cana-2432	194	2	.	.	X
cana-2432	194	3	10.1049	10.1049	NUM
cana-2432	194	4	/	/	SYM
cana-2432	194	5	ipr2.12220	ipr2.12220	ADJ
cana-2432	194	6	.	.	PUNCT
cana-2432	195	1	[	[	X
cana-2432	195	2	6	6	NUM
cana-2432	195	3	]	]	PUNCT
cana-2432	195	4	wulandari	wulandari	X
cana-2432	195	5	m	m	PROPN
cana-2432	195	6	,	,	PUNCT
cana-2432	195	7	chai	chai	NOUN
cana-2432	195	8	r	r	NOUN
cana-2432	195	9	,	,	PUNCT
cana-2432	195	10	basari	basari	PROPN
cana-2432	195	11	b	b	NOUN
cana-2432	195	12	,	,	PUNCT
cana-2432	195	13	gunawan	gunawan	PROPN
cana-2432	195	14	d.	d.	PROPN
cana-2432	195	15	hybrid	hybrid	PROPN
cana-2432	195	16	feature	feature	NOUN
cana-2432	195	17	extractor	extractor	NOUN
cana-2432	195	18	using	use	VERB
cana-2432	195	19	discrete	discrete	ADJ
cana-2432	195	20	wavelet	wavelet	NOUN
cana-2432	195	21	transform	transform	NOUN
cana-2432	195	22	and	and	CCONJ
cana-2432	195	23	histogram	histogram	NOUN
cana-2432	195	24	of	of	ADP
cana-2432	195	25	oriented	orient	VERB
cana-2432	195	26	gradient	gradient	NOUN
cana-2432	195	27	on	on	ADP
cana-2432	195	28	convolutional	convolutional	ADJ
cana-2432	195	29	-	-	PUNCT
cana-2432	195	30	neural	neural	ADJ
cana-2432	195	31	-	-	PUNCT
cana-2432	195	32	network	network	NOUN
cana-2432	195	33	-	-	PUNCT
cana-2432	195	34	based	base	VERB
cana-2432	195	35	palm	palm	NOUN
cana-2432	195	36	vein	vein	NOUN
cana-2432	195	37	recognition	recognition	NOUN
cana-2432	195	38	.	.	PUNCT
cana-2432	196	1	sensors	sensor	NOUN
cana-2432	196	2	(	(	PUNCT
cana-2432	196	3	basel	basel	PROPN
cana-2432	196	4	)	)	PUNCT
cana-2432	196	5	.	.	PUNCT
cana-2432	197	1	2024	2024	NUM
cana-2432	197	2	jan	jan	PROPN
cana-2432	197	3	6;24(2):341	6;24(2):341	NUM
cana-2432	197	4	.	.	PUNCT
cana-2432	198	1	doi	doi	NOUN
cana-2432	198	2	:	:	PUNCT
cana-2432	198	3	10.3390	10.3390	NUM
cana-2432	198	4	/	/	SYM
cana-2432	198	5	s24020341	s24020341	X
cana-2432	198	6	.	.	PUNCT
cana-2432	199	1	pmid	pmid	NOUN
cana-2432	199	2	:	:	PUNCT
cana-2432	199	3	38257434	38257434	NUM
cana-2432	199	4	;	;	PUNCT
cana-2432	199	5	pmcid	pmcid	NOUN
cana-2432	199	6	:	:	PUNCT
cana-2432	199	7	pmc10820403	pmc10820403	NOUN
cana-2432	199	8	.	.	PUNCT
cana-2432	200	1	[	[	X
cana-2432	200	2	7	7	NUM
cana-2432	200	3	]	]	PUNCT
cana-2432	200	4	balamurugan	balamurugan	NOUN
cana-2432	200	5	,	,	PUNCT
cana-2432	200	6	d.	d.	PROPN
cana-2432	200	7	&	&	CCONJ
cana-2432	200	8	seshadri	seshadri	PROPN
cana-2432	200	9	,	,	PUNCT
cana-2432	200	10	s.aravinth	s.aravinth	ADJ
cana-2432	200	11	&	&	CCONJ
cana-2432	200	12	reddy	reddy	PROPN
cana-2432	200	13	,	,	PUNCT
cana-2432	200	14	p.	p.	NOUN
cana-2432	200	15	&	&	CCONJ
cana-2432	200	16	rupani	rupani	PROPN
cana-2432	200	17	,	,	PUNCT
cana-2432	200	18	ajay	ajay	PROPN
cana-2432	200	19	&	&	CCONJ
cana-2432	200	20	manikandan	manikandan	PROPN
cana-2432	200	21	,	,	PUNCT
cana-2432	200	22	a	a	PRON
cana-2432	200	23	..	..	PUNCT
cana-2432	200	24	(	(	PUNCT
cana-2432	200	25	2022	2022	NUM
cana-2432	200	26	)	)	PUNCT
cana-2432	200	27	.	.	PUNCT
cana-2432	201	1	multiview	multiview	NOUN
cana-2432	201	2	objects	object	VERB
cana-2432	201	3	recognition	recognition	NOUN
cana-2432	201	4	using	use	VERB
cana-2432	201	5	deep	deep	ADJ
cana-2432	201	6	learning	learning	NOUN
cana-2432	201	7	-	-	PUNCT
cana-2432	201	8	based	base	VERB
cana-2432	201	9	wrap	wrap	NOUN
cana-2432	201	10	-	-	PUNCT
cana-2432	201	11	cnn	cnn	PROPN
cana-2432	201	12	with	with	ADP
cana-2432	201	13	voting	voting	NOUN
cana-2432	201	14	scheme	scheme	NOUN
cana-2432	201	15	.	.	PUNCT
cana-2432	202	1	neural	neural	ADJ
cana-2432	202	2	processing	processing	NOUN
cana-2432	202	3	letters	letter	NOUN
cana-2432	202	4	.	.	PUNCT
cana-2432	203	1	54	54	NUM
cana-2432	203	2	.	.	X
cana-2432	204	1	1	1	NUM
cana-2432	204	2	-	-	SYM
cana-2432	204	3	27	27	NUM
cana-2432	204	4	.	.	PUNCT
cana-2432	205	1	10.1007	10.1007	NUM
cana-2432	205	2	/	/	SYM
cana-2432	205	3	s11063	s11063	NOUN
cana-2432	205	4	-	-	PUNCT
cana-2432	205	5	021	021	NUM
cana-2432	205	6	-	-	PUNCT
cana-2432	205	7	10679	10679	NUM
cana-2432	205	8	-	-	PUNCT
cana-2432	205	9	4	4	NUM
cana-2432	205	10	.	.	PUNCT
cana-2432	206	1	[	[	X
cana-2432	206	2	8	8	NUM
cana-2432	206	3	]	]	X
cana-2432	206	4	reduwan	reduwan	PROPN
cana-2432	206	5	,	,	PUNCT
cana-2432	206	6	n.h	n.h	PROPN
cana-2432	206	7	.	.	PROPN
cana-2432	206	8	,	,	PUNCT
cana-2432	206	9	abdul	abdul	PROPN
cana-2432	206	10	aziz	aziz	PROPN
cana-2432	206	11	,	,	PUNCT
cana-2432	206	12	a.a	a.a	PROPN
cana-2432	206	13	.	.	PROPN
cana-2432	206	14	,	,	PUNCT
cana-2432	206	15	mohd	mohd	PROPN
cana-2432	206	16	razi	razi	PROPN
cana-2432	206	17	,	,	PUNCT
cana-2432	206	18	r.	r.	PROPN
cana-2432	206	19	et	et	PROPN
cana-2432	207	1	al	al	PROPN
cana-2432	207	2	.	.	PROPN
cana-2432	207	3	application	application	NOUN
cana-2432	207	4	of	of	ADP
cana-2432	207	5	deep	deep	ADJ
cana-2432	207	6	learning	learning	NOUN
cana-2432	207	7	and	and	CCONJ
cana-2432	207	8	feature	feature	NOUN
cana-2432	207	9	selection	selection	NOUN
cana-2432	207	10	technique	technique	NOUN
cana-2432	207	11	on	on	ADP
cana-2432	207	12	external	external	ADJ
cana-2432	207	13	root	root	NOUN
cana-2432	207	14	resorption	resorption	NOUN
cana-2432	207	15	identification	identification	NOUN
cana-2432	207	16	on	on	ADP
cana-2432	207	17	cbct	cbct	NOUN
cana-2432	207	18	images	image	NOUN
cana-2432	207	19	.	.	PUNCT
cana-2432	208	1	bmc	bmc	PROPN
cana-2432	208	2	oral	oral	ADJ
cana-2432	208	3	health	health	NOUN
cana-2432	208	4	24	24	NUM
cana-2432	208	5	,	,	PUNCT
cana-2432	208	6	252	252	NUM
cana-2432	208	7	(	(	PUNCT
cana-2432	208	8	2024	2024	NUM
cana-2432	208	9	)	)	PUNCT
cana-2432	208	10	.	.	PUNCT
cana-2432	209	1	https://doi.org/10.1186/s12903-024-03910-w	https://doi.org/10.1186/s12903-024-03910-w	NOUN
cana-2432	209	2	.	.	PUNCT
cana-2432	210	1	[	[	X
cana-2432	210	2	9	9	NUM
cana-2432	210	3	]	]	SYM
cana-2432	210	4	annamalai	annamalai	PROPN
cana-2432	210	5	,	,	PUNCT
cana-2432	210	6	manikandan	manikandan	PROPN
cana-2432	210	7	&	&	CCONJ
cana-2432	210	8	muthiah	muthiah	PROPN
cana-2432	210	9	,	,	PUNCT
cana-2432	210	10	ponni	ponni	PROPN
cana-2432	210	11	.	.	PUNCT
cana-2432	210	12	(	(	PUNCT
cana-2432	210	13	2022	2022	NUM
cana-2432	210	14	)	)	PUNCT
cana-2432	210	15	.	.	PUNCT
cana-2432	211	1	an	an	DET
cana-2432	211	2	early	early	ADJ
cana-2432	211	3	prediction	prediction	NOUN
cana-2432	211	4	of	of	ADP
cana-2432	211	5	tumor	tumor	NOUN
cana-2432	211	6	in	in	ADP
cana-2432	211	7	heart	heart	NOUN
cana-2432	211	8	by	by	ADP
cana-2432	211	9	cardiac	cardiac	ADJ
cana-2432	211	10	masses	masse	NOUN
cana-2432	211	11	classification	classification	NOUN
cana-2432	211	12	in	in	ADP
cana-2432	211	13	echocardiogram	echocardiogram	NOUN
cana-2432	211	14	images	image	NOUN
cana-2432	211	15	using	use	VERB
cana-2432	211	16	robust	robust	ADJ
cana-2432	211	17	back	back	NOUN
cana-2432	211	18	propagation	propagation	NOUN
cana-2432	211	19	neural	neural	ADJ
cana-2432	211	20	network	network	NOUN
cana-2432	211	21	classifier	classifier	NOUN
cana-2432	211	22	.	.	PUNCT
cana-2432	212	1	brazilian	brazilian	ADJ
cana-2432	212	2	archives	archive	NOUN
cana-2432	212	3	of	of	ADP
cana-2432	212	4	biology	biology	NOUN
cana-2432	212	5	and	and	CCONJ
cana-2432	212	6	technology	technology	NOUN
cana-2432	212	7	.	.	PUNCT
cana-2432	213	1	65	65	NUM
cana-2432	213	2	.	.	PUNCT
cana-2432	214	1	10.1590/1678	10.1590/1678	NUM
cana-2432	214	2	-	-	SYM
cana-2432	214	3	4324	4324	NUM
cana-2432	214	4	-	-	SYM
cana-2432	214	5	2022210316	2022210316	NUM
cana-2432	214	6	.	.	PUNCT
cana-2432	215	1	[	[	X
cana-2432	215	2	10	10	NUM
cana-2432	215	3	]	]	PUNCT
cana-2432	215	4	monday	monday	PROPN
cana-2432	215	5	hn	hn	PROPN
cana-2432	215	6	,	,	PUNCT
cana-2432	215	7	li	li	PROPN
cana-2432	215	8	j	j	PROPN
cana-2432	215	9	,	,	PUNCT
cana-2432	215	10	nneji	nneji	PROPN
cana-2432	215	11	gu	gu	PROPN
cana-2432	215	12	,	,	PUNCT
cana-2432	215	13	nahar	nahar	PROPN
cana-2432	215	14	s	s	PART
cana-2432	215	15	,	,	PUNCT
cana-2432	215	16	hossin	hossin	PROPN
cana-2432	215	17	ma	ma	PROPN
cana-2432	215	18	,	,	PUNCT
cana-2432	215	19	jackson	jackson	PROPN
cana-2432	215	20	j.	j.	PROPN
cana-2432	215	21	covid-19	covid-19	PROPN
cana-2432	215	22	pneumonia	pneumonia	NOUN
cana-2432	215	23	classification	classification	NOUN
cana-2432	215	24	based	base	VERB
cana-2432	215	25	on	on	ADP
cana-2432	215	26	neurowavelet	neurowavelet	PROPN
cana-2432	215	27	capsule	capsule	PROPN
cana-2432	215	28	network	network	PROPN
cana-2432	215	29	.	.	PUNCT
cana-2432	216	1	healthcare	healthcare	PROPN
cana-2432	216	2	.	.	PUNCT
cana-2432	217	1	2022	2022	NUM
cana-2432	217	2	;	;	PUNCT
cana-2432	218	1	10(3):422	10(3):422	X
cana-2432	218	2	.	.	PUNCT
cana-2432	219	1	[	[	X
cana-2432	219	2	11	11	NUM
cana-2432	219	3	]	]	X
cana-2432	219	4	manikandan	manikandan	PROPN
cana-2432	219	5	,	,	PUNCT
cana-2432	219	6	annamalai	annamalai	PROPN
cana-2432	219	7	,	,	PUNCT
cana-2432	219	8	m	m	PROPN
cana-2432	219	9	,	,	PUNCT
cana-2432	219	10	ponni	ponni	PROPN
cana-2432	219	11	bala	bala	PROPN
cana-2432	219	12	.	.	PUNCT
cana-2432	220	1	(	(	PUNCT
cana-2432	220	2	2023	2023	NUM
cana-2432	220	3	)	)	PUNCT
cana-2432	220	4	.	.	PUNCT
cana-2432	221	1	intracardiac	intracardiac	PROPN
cana-2432	221	2	mass	mass	NOUN
cana-2432	221	3	detection	detection	NOUN
cana-2432	221	4	and	and	CCONJ
cana-2432	221	5	classification	classification	NOUN
cana-2432	221	6	using	use	VERB
cana-2432	221	7	double	double	ADJ
cana-2432	221	8	convolutional	convolutional	ADJ
cana-2432	221	9	neural	neural	ADJ
cana-2432	221	10	network	network	NOUN
cana-2432	221	11	classifier	classifier	NOUN
cana-2432	221	12	.	.	PUNCT
cana-2432	222	1	journal	journal	PROPN
cana-2432	222	2	of	of	ADP
cana-2432	222	3	engineering	engineering	NOUN
cana-2432	222	4	research	research	NOUN
cana-2432	222	5	.	.	PUNCT
cana-2432	223	1	11(2a	11(2a	NUM
cana-2432	223	2	)	)	PUNCT
cana-2432	223	3	.	.	PUNCT
cana-2432	224	1	272	272	NUM
cana-2432	224	2	-	-	SYM
cana-2432	224	3	280	280	NUM
cana-2432	224	4	.	.	NOUN
cana-2432	224	5	10	10	NUM
cana-2432	224	6	.	.	X
cana-2432	225	1	36909	36909	NUM
cana-2432	225	2	/	/	SYM
cana-2432	225	3	jer.12237	jer.12237	NUM
cana-2432	225	4	.	.	PUNCT
cana-2432	226	1	[	[	X
cana-2432	226	2	12	12	NUM
cana-2432	226	3	]	]	X
cana-2432	226	4	ali	ali	PROPN
cana-2432	226	5	,	,	PUNCT
cana-2432	226	6	r.	r.	PROPN
cana-2432	226	7	,	,	PUNCT
cana-2432	226	8	manikandan	manikandan	PROPN
cana-2432	226	9	,	,	PUNCT
cana-2432	226	10	a.	a.	PROPN
cana-2432	226	11	&	&	CCONJ
cana-2432	226	12	xu	xu	PROPN
cana-2432	226	13	,	,	PUNCT
cana-2432	226	14	j.	j.	PROPN
cana-2432	226	15	a	a	DET
cana-2432	226	16	novel	novel	ADJ
cana-2432	226	17	framework	framework	NOUN
cana-2432	226	18	of	of	ADP
cana-2432	226	19	adaptive	adaptive	ADJ
cana-2432	226	20	fuzzy	fuzzy	ADJ
cana-2432	226	21	-	-	PUNCT
cana-2432	226	22	glcm	glcm	NOUN
cana-2432	226	23	segmentation	segmentation	NOUN
cana-2432	226	24	and	and	CCONJ
cana-2432	226	25	fuzzy	fuzzy	ADJ
cana-2432	226	26	with	with	ADP
cana-2432	226	27	capsules	capsule	NOUN
cana-2432	226	28	network	network	NOUN
cana-2432	226	29	(	(	PUNCT
cana-2432	226	30	f	f	NOUN
cana-2432	226	31	-	-	PUNCT
cana-2432	226	32	capsnet	capsnet	ADJ
cana-2432	226	33	)	)	PUNCT
cana-2432	226	34	classification	classification	NOUN
cana-2432	226	35	.	.	PUNCT
cana-2432	227	1	neural	neural	ADJ
cana-2432	227	2	comput	comput	PROPN
cana-2432	227	3	&	&	CCONJ
cana-2432	227	4	applic	applic	PROPN
cana-2432	227	5	(	(	PUNCT
cana-2432	227	6	2023	2023	NUM
cana-2432	227	7	)	)	PUNCT
cana-2432	227	8	.	.	PUNCT
cana-2432	228	1	https://doi.org/10.1007/s00521023-08666-y	https://doi.org/10.1007/s00521023-08666-y	PUNCT
cana-2432	229	1	[	[	X
cana-2432	229	2	13	13	NUM
cana-2432	229	3	]	]	SYM
cana-2432	229	4	ali	ali	PROPN
cana-2432	229	5	,	,	PUNCT
cana-2432	229	6	r.	r.	PROPN
cana-2432	229	7	,	,	PUNCT
cana-2432	229	8	manikandan	manikandan	PROPN
cana-2432	229	9	,	,	PUNCT
cana-2432	229	10	a.	a.	PROPN
cana-2432	229	11	,	,	PUNCT
cana-2432	229	12	lei	lei	PROPN
cana-2432	229	13	,	,	PUNCT
cana-2432	229	14	r.	r.	PROPN
cana-2432	229	15	et	et	PROPN
cana-2432	229	16	al	al	PROPN
cana-2432	229	17	.	.	PUNCT
cana-2432	230	1	a	a	DET
cana-2432	230	2	novel	novel	ADJ
cana-2432	230	3	spasa	spasa	PROPN
cana-2432	230	4	based	base	VERB
cana-2432	230	5	hyper	hyper	ADJ
cana-2432	230	6	-	-	ADJ
cana-2432	230	7	parameter	parameter	NOUN
cana-2432	230	8	optimized	optimize	VERB
cana-2432	230	9	fcedn	fcedn	NOUN
cana-2432	230	10	with	with	ADP
cana-2432	230	11	adaptive	adaptive	ADJ
cana-2432	230	12	cnn	cnn	PROPN
cana-2432	230	13	classification	classification	NOUN
cana-2432	230	14	for	for	ADP
cana-2432	230	15	skin	skin	NOUN
cana-2432	230	16	cancer	cancer	NOUN
cana-2432	230	17	detection	detection	NOUN
cana-2432	230	18	.	.	PUNCT
cana-2432	231	1	sci	sci	PROPN
cana-2432	231	2	rep	rep	PROPN
cana-2432	231	3	14	14	NUM
cana-2432	231	4	,	,	PUNCT
cana-2432	231	5	9336	9336	NUM
cana-2432	231	6	(	(	PUNCT
cana-2432	231	7	2024	2024	NUM
cana-2432	231	8	)	)	PUNCT
cana-2432	231	9	.	.	PUNCT
cana-2432	232	1	https://doi.org/10.1038/s41598-024-573934	https://doi.org/10.1038/s41598-024-573934	X
cana-2432	232	2	.	.	PUNCT
cana-2432	233	1	[	[	X
cana-2432	233	2	14	14	NUM
cana-2432	233	3	]	]	SYM
cana-2432	233	4	li	li	PROPN
cana-2432	233	5	,	,	PUNCT
cana-2432	233	6	qiufu	qiufu	PROPN
cana-2432	233	7	&	&	CCONJ
cana-2432	233	8	shen	shen	PROPN
cana-2432	233	9	,	,	PUNCT
cana-2432	233	10	linlin	linlin	PROPN
cana-2432	233	11	&	&	CCONJ
cana-2432	233	12	guo	guo	PROPN
cana-2432	233	13	,	,	PUNCT
cana-2432	233	14	sheng	sheng	PROPN
cana-2432	233	15	&	&	CCONJ
cana-2432	233	16	lai	lai	PROPN
cana-2432	233	17	,	,	PUNCT
cana-2432	233	18	zhihui	zhihui	PROPN
cana-2432	233	19	.	.	PUNCT
cana-2432	233	20	(	(	PUNCT
cana-2432	233	21	2020	2020	NUM
cana-2432	233	22	)	)	PUNCT
cana-2432	233	23	.	.	PUNCT
cana-2432	233	24	wavelet	wavelet	PROPN
cana-2432	233	25	integrated	integrate	VERB
cana-2432	233	26	cnns	cnn	NOUN
cana-2432	233	27	for	for	ADP
cana-2432	233	28	noise	noise	NOUN
cana-2432	233	29	-	-	PUNCT
cana-2432	233	30	robust	robust	ADJ
cana-2432	233	31	image	image	NOUN
cana-2432	233	32	classification	classification	NOUN
cana-2432	233	33	.	.	PUNCT
cana-2432	234	1	7243	7243	NUM
cana-2432	234	2	-	-	SYM
cana-2432	234	3	7252	7252	NUM
cana-2432	234	4	.	.	PUNCT
cana-2432	235	1	[	[	X
cana-2432	235	2	15	15	NUM
cana-2432	235	3	]	]	X
cana-2432	235	4	sarhan	sarhan	NOUN
cana-2432	235	5	,	,	PUNCT
cana-2432	235	6	ahmad	ahmad	PROPN
cana-2432	235	7	.	.	PUNCT
cana-2432	236	1	(	(	PUNCT
cana-2432	236	2	2020	2020	NUM
cana-2432	236	3	)	)	PUNCT
cana-2432	236	4	.	.	PUNCT
cana-2432	237	1	a	a	DET
cana-2432	237	2	novel	novel	ADJ
cana-2432	237	3	lung	lung	NOUN
cana-2432	237	4	cancer	cancer	NOUN
cana-2432	237	5	detection	detection	NOUN
cana-2432	237	6	method	method	NOUN
cana-2432	237	7	using	use	VERB
cana-2432	237	8	wavelet	wavelet	NOUN
cana-2432	237	9	decomposition	decomposition	NOUN
cana-2432	237	10	and	and	CCONJ
cana-2432	237	11	convolutional	convolutional	ADJ
cana-2432	237	12	neural	neural	ADJ
cana-2432	237	13	network	network	NOUN
cana-2432	237	14	.	.	PUNCT
cana-2432	238	1	journal	journal	PROPN
cana-2432	238	2	of	of	ADP
cana-2432	238	3	biomedical	biomedical	ADJ
cana-2432	238	4	science	science	NOUN
cana-2432	238	5	and	and	CCONJ
cana-2432	238	6	engineering	engineering	NOUN
cana-2432	238	7	.	.	PUNCT
cana-2432	239	1	13	13	NUM
cana-2432	239	2	.	.	X
cana-2432	239	3	81	81	NUM
cana-2432	239	4	-	-	SYM
cana-2432	239	5	92	92	NUM
cana-2432	239	6	.	.	PUNCT
cana-2432	240	1	[	[	X
cana-2432	240	2	16	16	NUM
cana-2432	240	3	]	]	PUNCT
cana-2432	240	4	rasheed	rasheed	NOUN
cana-2432	240	5	,	,	PUNCT
cana-2432	240	6	a.	a.	NOUN
cana-2432	240	7	,	,	PUNCT
cana-2432	240	8	younis	younis	PROPN
cana-2432	240	9	,	,	PUNCT
cana-2432	240	10	m.s	m.s	PROPN
cana-2432	240	11	.	.	PROPN
cana-2432	240	12	,	,	PUNCT
cana-2432	240	13	qadir	qadir	PROPN
cana-2432	240	14	,	,	PUNCT
cana-2432	240	15	j.	j.	PROPN
cana-2432	240	16	,	,	PUNCT
cana-2432	240	17	&	&	CCONJ
cana-2432	240	18	bilal	bilal	PROPN
cana-2432	240	19	,	,	PUNCT
cana-2432	240	20	m.	m.	NOUN
cana-2432	240	21	(	(	PUNCT
cana-2432	240	22	2021	2021	NUM
cana-2432	240	23	)	)	PUNCT
cana-2432	240	24	.	.	PUNCT
cana-2432	241	1	use	use	NOUN
cana-2432	241	2	of	of	ADP
cana-2432	241	3	transfer	transfer	NOUN
cana-2432	241	4	learning	learning	NOUN
cana-2432	241	5	and	and	CCONJ
cana-2432	241	6	wavelet	wavelet	NOUN
cana-2432	241	7	transform	transform	NOUN
cana-2432	241	8	for	for	ADP
cana-2432	241	9	breast	breast	NOUN
cana-2432	241	10	cancer	cancer	NOUN
cana-2432	241	11	detection	detection	NOUN
cana-2432	241	12	.	.	PUNCT
cana-2432	242	1	arxiv	arxiv	PROPN
cana-2432	242	2	,	,	PUNCT
cana-2432	242	3	abs/2103.03602	abs/2103.03602	X
cana-2432	242	4	.	.	PUNCT
cana-2432	243	1	[	[	X
cana-2432	243	2	17	17	NUM
cana-2432	243	3	]	]	X
cana-2432	243	4	https://www.kaggle.com/datasets/tawsifurrahman/covid19-radiography-database	https://www.kaggle.com/datasets/tawsifurrahman/covid19-radiography-database	PROPN
cana-2432	243	5	[	[	X
cana-2432	243	6	18	18	NUM
cana-2432	243	7	]	]	X
cana-2432	243	8	b.	b.	PROPN
cana-2432	243	9	cui	cui	PROPN
cana-2432	243	10	and	and	CCONJ
cana-2432	243	11	h.	h.	PROPN
cana-2432	243	12	jiang	jiang	PROPN
cana-2432	243	13	,	,	PUNCT
cana-2432	243	14	"	"	PUNCT
cana-2432	243	15	an	an	DET
cana-2432	243	16	image	image	NOUN
cana-2432	243	17	edge	edge	NOUN
cana-2432	243	18	detection	detection	NOUN
cana-2432	243	19	method	method	NOUN
cana-2432	243	20	based	base	VERB
cana-2432	243	21	on	on	ADP
cana-2432	243	22	haar	haar	PROPN
cana-2432	243	23	wavelet	wavelet	NOUN
cana-2432	243	24	transform	transform	NOUN
cana-2432	243	25	,	,	PUNCT
cana-2432	243	26	"	"	PUNCT
cana-2432	243	27	2020	2020	NUM
cana-2432	243	28	international	international	ADJ
cana-2432	243	29	conference	conference	NOUN
cana-2432	243	30	on	on	ADP
cana-2432	243	31	artificial	artificial	ADJ
cana-2432	243	32	intelligence	intelligence	NOUN
cana-2432	243	33	and	and	CCONJ
cana-2432	243	34	computer	computer	NOUN
cana-2432	243	35	engineering	engineering	NOUN
cana-2432	243	36	(	(	PUNCT
cana-2432	243	37	icaice	icaice	NOUN
cana-2432	243	38	)	)	PUNCT
cana-2432	243	39	,	,	PUNCT
cana-2432	243	40	beijing	beijing	PROPN
cana-2432	243	41	,	,	PUNCT
cana-2432	243	42	china	china	PROPN
cana-2432	243	43	,	,	PUNCT
cana-2432	243	44	2020	2020	NUM
cana-2432	243	45	,	,	PUNCT
cana-2432	243	46	pp	pp	ADV
cana-2432	243	47	.	.	PUNCT
cana-2432	244	1	250	250	NUM
cana-2432	244	2	-	-	SYM
cana-2432	244	3	254	254	NUM
cana-2432	244	4	,	,	PUNCT
cana-2432	244	5	doi	doi	NOUN
cana-2432	244	6	:	:	PUNCT
cana-2432	244	7	10.1109	10.1109	NUM
cana-2432	244	8	/	/	SYM
cana-2432	244	9	icaice51518.2020.00054	icaice51518.2020.00054	PROPN
cana-2432	244	10	.	.	PUNCT
cana-2432	245	1	[	[	X
cana-2432	245	2	19	19	NUM
cana-2432	245	3	]	]	SYM
cana-2432	245	4	simonyan	simonyan	ADJ
cana-2432	245	5	and	and	CCONJ
cana-2432	245	6	a.	a.	NOUN
cana-2432	245	7	zisserman	zisserman	PROPN
cana-2432	245	8	,	,	PUNCT
cana-2432	245	9	“	"	PUNCT
cana-2432	245	10	very	very	ADV
cana-2432	245	11	deep	deep	ADJ
cana-2432	245	12	convolutional	convolutional	ADJ
cana-2432	245	13	networks	network	NOUN
cana-2432	245	14	for	for	ADP
cana-2432	245	15	large	large	ADJ
cana-2432	245	16	-	-	PUNCT
cana-2432	245	17	scale	scale	NOUN
cana-2432	245	18	image	image	NOUN
cana-2432	245	19	recognition	recognition	NOUN
cana-2432	245	20	,	,	PUNCT
cana-2432	245	21	”	"	PUNCT
cana-2432	245	22	arxiv	arxiv	PROPN
cana-2432	245	23	preprint	preprint	NOUN
cana-2432	245	24	arxiv:1409.1556	arxiv:1409.1556	NOUN
cana-2432	245	25	,	,	PUNCT
cana-2432	245	26	2014	2014	NUM
cana-2432	245	27	.	.	PUNCT
cana-2432	246	1	https://doi.org/10.1007/s12596-023-01123-y	https://doi.org/10.1007/s12596-023-01123-y	PROPN
cana-2432	246	2	https://doi.org/10.1007/s12596-023-01123-y	https://doi.org/10.1007/s12596-023-01123-y	PROPN
cana-2432	246	3	https://doi.org/10.1186/s12903-024-03910-w	https://doi.org/10.1186/s12903-024-03910-w	PROPN
cana-2432	246	4	https://doi.org/10.1038/s41598-024-57393-4	https://doi.org/10.1038/s41598-024-57393-4	NUM
cana-2432	246	5	https://doi.org/10.1038/s41598-024-57393-4	https://doi.org/10.1038/s41598-024-57393-4	NUM
cana-2432	247	1	https://www.kaggle.com/datasets/tawsifurrahman/covid19-radiography-database	https://www.kaggle.com/datasets/tawsifurrahman/covid19-radiography-database	PROPN