id	sid	tid	token	lemma	pos
ajst-30190	1	1	academic	academic	ADJ
ajst-30190	1	2	journal	journal	NOUN
ajst-30190	1	3	of	of	ADP
ajst-30190	1	4	science	science	NOUN
ajst-30190	1	5	and	and	CCONJ
ajst-30190	1	6	technology	technology	NOUN
ajst-30190	1	7	issn	issn	NOUN
ajst-30190	1	8	:	:	PUNCT
ajst-30190	1	9	2771	2771	NUM
ajst-30190	1	10	-	-	SYM
ajst-30190	1	11	3032	3032	NUM
ajst-30190	1	12	|	|	NOUN
ajst-30190	1	13	vol	vol	NOUN
ajst-30190	1	14	.	.	PUNCT
ajst-30190	2	1	14	14	NUM
ajst-30190	2	2	,	,	PUNCT
ajst-30190	2	3	no	no	INTJ
ajst-30190	2	4	.	.	NOUN
ajst-30190	2	5	3	3	NUM
ajst-30190	2	6	,	,	PUNCT
ajst-30190	2	7	2025	2025	NUM
ajst-30190	2	8	141	141	NUM
ajst-30190	2	9	fatigue	fatigue	NOUN
ajst-30190	2	10	eeg	eeg	NOUN
ajst-30190	2	11	classification	classification	NOUN
ajst-30190	2	12	study	study	NOUN
ajst-30190	2	13	based	base	VERB
ajst-30190	2	14	on	on	ADP
ajst-30190	2	15	convolutionally	convolutionally	ADV
ajst-30190	2	16	constrained	constrain	VERB
ajst-30190	2	17	boltzmann	boltzmann	PROPN
ajst-30190	2	18	machine	machine	NOUN
ajst-30190	2	19	xiaoran	xiaoran	PROPN
ajst-30190	2	20	dong1	dong1	PROPN
ajst-30190	2	21	,	,	PUNCT
ajst-30190	2	22	*	*	PROPN
ajst-30190	2	23	,	,	PUNCT
ajst-30190	2	24	yahan	yahan	PROPN
ajst-30190	2	25	gao2	gao2	PROPN
ajst-30190	2	26	1university	1university	NUM
ajst-30190	2	27	of	of	ADP
ajst-30190	2	28	shanghai	shanghai	PROPN
ajst-30190	2	29	for	for	ADP
ajst-30190	2	30	science	science	NOUN
ajst-30190	2	31	and	and	CCONJ
ajst-30190	2	32	technology	technology	NOUN
ajst-30190	2	33	,	,	PUNCT
ajst-30190	2	34	shanghai	shanghai	PROPN
ajst-30190	2	35	10252	10252	NUM
ajst-30190	3	1	,	,	PUNCT
ajst-30190	3	2	china	china	PROPN
ajst-30190	3	3	2shanghai	2shanghai	PROPN
ajst-30190	3	4	university	university	PROPN
ajst-30190	3	5	of	of	ADP
ajst-30190	3	6	medicine	medicine	PROPN
ajst-30190	3	7	&	&	CCONJ
ajst-30190	3	8	health	health	PROPN
ajst-30190	3	9	sciences	sciences	PROPN
ajst-30190	3	10	,	,	PUNCT
ajst-30190	3	11	shanghai	shanghai	PROPN
ajst-30190	3	12	10262	10262	NUM
ajst-30190	3	13	,	,	PUNCT
ajst-30190	3	14	china	china	PROPN
ajst-30190	3	15	*	*	PUNCT
ajst-30190	3	16	corresponding	correspond	VERB
ajst-30190	3	17	author	author	NOUN
ajst-30190	3	18	abstract	abstract	NOUN
ajst-30190	3	19	:	:	PUNCT
ajst-30190	3	20	as	as	SCONJ
ajst-30190	3	21	the	the	DET
ajst-30190	3	22	demand	demand	NOUN
ajst-30190	3	23	for	for	ADP
ajst-30190	3	24	the	the	DET
ajst-30190	3	25	detection	detection	NOUN
ajst-30190	3	26	of	of	ADP
ajst-30190	3	27	brain	brain	NOUN
ajst-30190	3	28	fatigue	fatigue	NOUN
ajst-30190	3	29	state	state	NOUN
ajst-30190	3	30	grows	grow	VERB
ajst-30190	3	31	,	,	PUNCT
ajst-30190	3	32	portable	portable	ADJ
ajst-30190	3	33	eeg	eeg	NOUN
ajst-30190	3	34	instruments	instrument	NOUN
ajst-30190	3	35	are	be	AUX
ajst-30190	3	36	becoming	become	VERB
ajst-30190	3	37	more	more	ADV
ajst-30190	3	38	and	and	CCONJ
ajst-30190	3	39	more	more	ADV
ajst-30190	3	40	critical	critical	ADJ
ajst-30190	3	41	in	in	ADP
ajst-30190	3	42	related	related	ADJ
ajst-30190	3	43	research	research	NOUN
ajst-30190	3	44	.	.	PUNCT
ajst-30190	4	1	in	in	ADP
ajst-30190	4	2	this	this	DET
ajst-30190	4	3	study	study	NOUN
ajst-30190	4	4	,	,	PUNCT
ajst-30190	4	5	we	we	PRON
ajst-30190	4	6	designed	design	VERB
ajst-30190	4	7	a	a	DET
ajst-30190	4	8	1	1	NUM
ajst-30190	4	9	-	-	PUNCT
ajst-30190	4	10	back	back	NOUN
ajst-30190	4	11	task	task	NOUN
ajst-30190	4	12	paradigm	paradigm	NOUN
ajst-30190	4	13	to	to	PART
ajst-30190	4	14	induce	induce	VERB
ajst-30190	4	15	fatigue	fatigue	NOUN
ajst-30190	4	16	eeg	eeg	NOUN
ajst-30190	4	17	signals	signal	NOUN
ajst-30190	4	18	using	use	VERB
ajst-30190	4	19	the	the	DET
ajst-30190	4	20	emotivepoc+14	emotivepoc+14	ADJ
ajst-30190	4	21	eeg	eeg	NOUN
ajst-30190	4	22	instrument	instrument	NOUN
ajst-30190	4	23	.	.	PUNCT
ajst-30190	5	1	the	the	DET
ajst-30190	5	2	eeg	eeg	PROPN
ajst-30190	5	3	dataset	dataset	NOUN
ajst-30190	5	4	was	be	AUX
ajst-30190	5	5	built	build	VERB
ajst-30190	5	6	based	base	VERB
ajst-30190	5	7	on	on	ADP
ajst-30190	5	8	the	the	DET
ajst-30190	5	9	subjective	subjective	ADJ
ajst-30190	5	10	rating	rating	NOUN
ajst-30190	5	11	scale	scale	NOUN
ajst-30190	5	12	rating	rating	NOUN
ajst-30190	5	13	scores	score	NOUN
ajst-30190	5	14	of	of	ADP
ajst-30190	5	15	the	the	DET
ajst-30190	5	16	kss	kss	PROPN
ajst-30190	5	17	scale	scale	NOUN
ajst-30190	5	18	and	and	CCONJ
ajst-30190	5	19	the	the	DET
ajst-30190	5	20	behavioral	behavioral	ADJ
ajst-30190	5	21	analysis	analysis	NOUN
ajst-30190	5	22	results	result	NOUN
ajst-30190	5	23	.	.	PUNCT
ajst-30190	6	1	construct	construct	VERB
ajst-30190	6	2	an	an	DET
ajst-30190	6	3	improved	improve	VERB
ajst-30190	6	4	convolutionally	convolutionally	ADV
ajst-30190	6	5	constrained	constrain	VERB
ajst-30190	6	6	boltzmann	boltzmann	PROPN
ajst-30190	6	7	machine	machine	NOUN
ajst-30190	6	8	model	model	NOUN
ajst-30190	6	9	,	,	PUNCT
ajst-30190	6	10	introducing	introduce	VERB
ajst-30190	6	11	convolutional	convolutional	ADJ
ajst-30190	6	12	operations	operation	NOUN
ajst-30190	6	13	to	to	ADP
ajst-30190	6	14	the	the	DET
ajst-30190	6	15	visible	visible	ADJ
ajst-30190	6	16	and	and	CCONJ
ajst-30190	6	17	hidden	hidden	ADJ
ajst-30190	6	18	layers	layer	NOUN
ajst-30190	6	19	to	to	PART
ajst-30190	6	20	achieve	achieve	VERB
ajst-30190	6	21	weight	weight	NOUN
ajst-30190	6	22	sharing	sharing	NOUN
ajst-30190	6	23	.	.	PUNCT
ajst-30190	7	1	feature	feature	NOUN
ajst-30190	7	2	selection	selection	NOUN
ajst-30190	7	3	using	use	VERB
ajst-30190	7	4	principal	principal	ADJ
ajst-30190	7	5	component	component	NOUN
ajst-30190	7	6	analysis	analysis	NOUN
ajst-30190	7	7	method	method	NOUN
ajst-30190	7	8	combined	combine	VERB
ajst-30190	7	9	with	with	ADP
ajst-30190	7	10	pearson	pearson	PROPN
ajst-30190	7	11	's	's	PART
ajst-30190	7	12	coefficient	coefficient	NOUN
ajst-30190	7	13	to	to	PART
ajst-30190	7	14	retain	retain	VERB
ajst-30190	7	15	highly	highly	ADV
ajst-30190	7	16	correlated	correlate	VERB
ajst-30190	7	17	features	feature	NOUN
ajst-30190	7	18	.	.	PUNCT
ajst-30190	8	1	self	self	NOUN
ajst-30190	8	2	-	-	PUNCT
ajst-30190	8	3	training	training	NOUN
ajst-30190	8	4	-	-	PUNCT
ajst-30190	8	5	semi	semi	ADV
ajst-30190	8	6	-	-	ADJ
ajst-30190	8	7	supervised	supervised	ADJ
ajst-30190	8	8	learning	learning	NOUN
ajst-30190	8	9	method	method	NOUN
ajst-30190	8	10	is	be	AUX
ajst-30190	8	11	used	use	VERB
ajst-30190	8	12	to	to	PART
ajst-30190	8	13	train	train	VERB
ajst-30190	8	14	the	the	DET
ajst-30190	8	15	model	model	NOUN
ajst-30190	8	16	,	,	PUNCT
ajst-30190	8	17	and	and	CCONJ
ajst-30190	8	18	the	the	DET
ajst-30190	8	19	results	result	NOUN
ajst-30190	8	20	show	show	VERB
ajst-30190	8	21	that	that	SCONJ
ajst-30190	8	22	the	the	DET
ajst-30190	8	23	features	feature	NOUN
ajst-30190	8	24	extracted	extract	VERB
ajst-30190	8	25	from	from	ADP
ajst-30190	8	26	the	the	DET
ajst-30190	8	27	c	c	PROPN
ajst-30190	8	28	-	-	PUNCT
ajst-30190	8	29	rbm	rbm	PROPN
ajst-30190	8	30	model	model	NOUN
ajst-30190	8	31	achieve	achieve	VERB
ajst-30190	8	32	89	89	NUM
ajst-30190	8	33	%	%	NOUN
ajst-30190	8	34	and	and	CCONJ
ajst-30190	8	35	91	91	NUM
ajst-30190	8	36	%	%	NOUN
ajst-30190	8	37	classification	classification	NOUN
ajst-30190	8	38	accuracy	accuracy	NOUN
ajst-30190	8	39	in	in	ADP
ajst-30190	8	40	the	the	DET
ajst-30190	8	41	frontal	frontal	ADJ
ajst-30190	8	42	and	and	CCONJ
ajst-30190	8	43	occipital	occipital	ADJ
ajst-30190	8	44	lobes	lobe	NOUN
ajst-30190	8	45	.	.	PUNCT
ajst-30190	9	1	after	after	ADP
ajst-30190	9	2	reducing	reduce	VERB
ajst-30190	9	3	the	the	DET
ajst-30190	9	4	channels	channel	NOUN
ajst-30190	9	5	it	it	PRON
ajst-30190	9	6	is	be	AUX
ajst-30190	9	7	used	use	VERB
ajst-30190	9	8	for	for	ADP
ajst-30190	9	9	svm	svm	ADJ
ajst-30190	9	10	and	and	CCONJ
ajst-30190	9	11	rf	rf	NOUN
ajst-30190	9	12	classifiers	classifier	NOUN
ajst-30190	9	13	with	with	ADP
ajst-30190	9	14	the	the	DET
ajst-30190	9	15	best	good	ADJ
ajst-30190	9	16	results	result	NOUN
ajst-30190	9	17	,	,	PUNCT
ajst-30190	9	18	svm	svm	PROPN
ajst-30190	9	19	achieves	achieve	VERB
ajst-30190	9	20	93	93	NUM
ajst-30190	9	21	%	%	NOUN
ajst-30190	9	22	classification	classification	NOUN
ajst-30190	9	23	accuracy	accuracy	NOUN
ajst-30190	9	24	of	of	ADP
ajst-30190	9	25	hm	hm	INTJ
ajst-30190	9	26	+	+	CCONJ
ajst-30190	9	27	psd	psd	PROPN
ajst-30190	9	28	+	+	CCONJ
ajst-30190	9	29	pe	pe	X
ajst-30190	9	30	for	for	ADP
ajst-30190	9	31	occipital	occipital	NOUN
ajst-30190	9	32	lobe	lobe	NOUN
ajst-30190	9	33	and	and	CCONJ
ajst-30190	9	34	rf	rf	PRON
ajst-30190	9	35	achieves	achieve	VERB
ajst-30190	9	36	92	92	NUM
ajst-30190	9	37	%	%	NOUN
ajst-30190	9	38	classification	classification	NOUN
ajst-30190	9	39	accuracy	accuracy	NOUN
ajst-30190	9	40	of	of	ADP
ajst-30190	9	41	hm	hm	INTJ
ajst-30190	9	42	+	+	CCONJ
ajst-30190	9	43	psd	psd	PROPN
ajst-30190	10	1	+	+	CCONJ
ajst-30190	10	2	we	we	PRON
ajst-30190	10	3	for	for	ADP
ajst-30190	10	4	occipital	occipital	ADJ
ajst-30190	10	5	lobe	lobe	NOUN
ajst-30190	10	6	.	.	PUNCT
ajst-30190	11	1	this	this	PRON
ajst-30190	11	2	shows	show	VERB
ajst-30190	11	3	that	that	SCONJ
ajst-30190	11	4	the	the	DET
ajst-30190	11	5	combination	combination	NOUN
ajst-30190	11	6	of	of	ADP
ajst-30190	11	7	the	the	DET
ajst-30190	11	8	c	c	PROPN
ajst-30190	11	9	-	-	PUNCT
ajst-30190	11	10	rbm	rbm	PROPN
ajst-30190	11	11	model	model	NOUN
ajst-30190	11	12	proposed	propose	VERB
ajst-30190	11	13	in	in	ADP
ajst-30190	11	14	this	this	DET
ajst-30190	11	15	paper	paper	NOUN
ajst-30190	11	16	with	with	ADP
ajst-30190	11	17	svm	svm	PROPN
ajst-30190	11	18	and	and	CCONJ
ajst-30190	11	19	rf	rf	NOUN
ajst-30190	11	20	classifiers	classifier	NOUN
ajst-30190	11	21	can	can	AUX
ajst-30190	11	22	effectively	effectively	ADV
ajst-30190	11	23	use	use	VERB
ajst-30190	11	24	the	the	DET
ajst-30190	11	25	reduced	reduce	VERB
ajst-30190	11	26	dimensionality	dimensionality	NOUN
ajst-30190	11	27	channel	channel	NOUN
ajst-30190	11	28	features	feature	VERB
ajst-30190	11	29	for	for	ADP
ajst-30190	11	30	fatigue	fatigue	NOUN
ajst-30190	11	31	detection	detection	NOUN
ajst-30190	11	32	,	,	PUNCT
ajst-30190	11	33	which	which	PRON
ajst-30190	11	34	provides	provide	VERB
ajst-30190	11	35	a	a	DET
ajst-30190	11	36	reference	reference	NOUN
ajst-30190	11	37	for	for	ADP
ajst-30190	11	38	fatigue	fatigue	NOUN
ajst-30190	11	39	detection	detection	NOUN
ajst-30190	11	40	of	of	ADP
ajst-30190	11	41	feature	feature	NOUN
ajst-30190	11	42	combinations	combination	NOUN
ajst-30190	11	43	for	for	ADP
ajst-30190	11	44	sparse	sparse	ADJ
ajst-30190	11	45	channels	channel	NOUN
ajst-30190	11	46	.	.	PUNCT
ajst-30190	12	1	keywords	keyword	NOUN
ajst-30190	12	2	:	:	PUNCT
ajst-30190	12	3	n	n	NUM
ajst-30190	12	4	-	-	PUNCT
ajst-30190	12	5	back	back	NOUN
ajst-30190	12	6	,	,	PUNCT
ajst-30190	12	7	c	c	X
ajst-30190	12	8	-	-	PUNCT
ajst-30190	12	9	rbm	rbm	NOUN
ajst-30190	12	10	,	,	PUNCT
ajst-30190	12	11	semi	semi	ADJ
ajst-30190	12	12	-	-	ADJ
ajst-30190	12	13	supervised	supervised	ADJ
ajst-30190	12	14	learning	learning	NOUN
ajst-30190	12	15	,	,	PUNCT
ajst-30190	12	16	eeg	eeg	NOUN
ajst-30190	12	17	classification	classification	NOUN
ajst-30190	12	18	.	.	PUNCT
ajst-30190	13	1	1	1	X
ajst-30190	13	2	.	.	X
ajst-30190	13	3	introduction	introduction	NOUN
ajst-30190	13	4	with	with	ADP
ajst-30190	13	5	the	the	DET
ajst-30190	13	6	development	development	NOUN
ajst-30190	13	7	of	of	ADP
ajst-30190	13	8	the	the	DET
ajst-30190	13	9	times	time	NOUN
ajst-30190	13	10	and	and	CCONJ
ajst-30190	13	11	social	social	ADJ
ajst-30190	13	12	progress	progress	NOUN
ajst-30190	13	13	,	,	PUNCT
ajst-30190	13	14	fatigue	fatigue	NOUN
ajst-30190	13	15	has	have	AUX
ajst-30190	13	16	become	become	VERB
ajst-30190	13	17	a	a	DET
ajst-30190	13	18	common	common	ADJ
ajst-30190	13	19	physiological	physiological	ADJ
ajst-30190	13	20	and	and	CCONJ
ajst-30190	13	21	psychological	psychological	ADJ
ajst-30190	13	22	state	state	NOUN
ajst-30190	13	23	of	of	ADP
ajst-30190	13	24	people	people	NOUN
ajst-30190	13	25	,	,	PUNCT
ajst-30190	13	26	which	which	PRON
ajst-30190	13	27	is	be	AUX
ajst-30190	13	28	widely	widely	ADV
ajst-30190	13	29	existed	exist	VERB
ajst-30190	13	30	in	in	ADP
ajst-30190	13	31	daily	daily	ADJ
ajst-30190	13	32	life	life	NOUN
ajst-30190	13	33	and	and	CCONJ
ajst-30190	13	34	has	have	VERB
ajst-30190	13	35	a	a	DET
ajst-30190	13	36	significant	significant	ADJ
ajst-30190	13	37	impact	impact	NOUN
ajst-30190	13	38	,	,	PUNCT
ajst-30190	13	39	so	so	SCONJ
ajst-30190	13	40	the	the	DET
ajst-30190	13	41	research	research	NOUN
ajst-30190	13	42	on	on	ADP
ajst-30190	13	43	fatigue	fatigue	NOUN
ajst-30190	13	44	has	have	VERB
ajst-30190	13	45	a	a	DET
ajst-30190	13	46	better	well	ADJ
ajst-30190	13	47	prospect	prospect	NOUN
ajst-30190	13	48	and	and	CCONJ
ajst-30190	13	49	important	important	ADJ
ajst-30190	13	50	significance	significance	NOUN
ajst-30190	13	51	.	.	PUNCT
ajst-30190	14	1	in	in	ADP
ajst-30190	14	2	the	the	DET
ajst-30190	14	3	field	field	NOUN
ajst-30190	14	4	of	of	ADP
ajst-30190	14	5	transport	transport	NOUN
ajst-30190	14	6	,	,	PUNCT
ajst-30190	14	7	driver	driver	NOUN
ajst-30190	14	8	fatigue	fatigue	NOUN
ajst-30190	14	9	is	be	AUX
ajst-30190	14	10	one	one	NUM
ajst-30190	14	11	of	of	ADP
ajst-30190	14	12	the	the	DET
ajst-30190	14	13	major	major	ADJ
ajst-30190	14	14	causes	cause	NOUN
ajst-30190	14	15	of	of	ADP
ajst-30190	14	16	traffic	traffic	NOUN
ajst-30190	14	17	accidents	accident	NOUN
ajst-30190	14	18	.	.	PUNCT
ajst-30190	15	1	according	accord	VERB
ajst-30190	15	2	to	to	ADP
ajst-30190	15	3	statistics	statistic	NOUN
ajst-30190	15	4	,	,	PUNCT
ajst-30190	15	5	a	a	DET
ajst-30190	15	6	large	large	ADJ
ajst-30190	15	7	number	number	NOUN
ajst-30190	15	8	of	of	ADP
ajst-30190	15	9	traffic	traffic	NOUN
ajst-30190	15	10	tragedies	tragedy	NOUN
ajst-30190	15	11	are	be	AUX
ajst-30190	15	12	related	relate	VERB
ajst-30190	15	13	to	to	ADP
ajst-30190	15	14	fatigue	fatigue	NOUN
ajst-30190	15	15	driving	driving	NOUN
ajst-30190	15	16	,	,	PUNCT
ajst-30190	15	17	and	and	CCONJ
ajst-30190	15	18	improving	improve	VERB
ajst-30190	15	19	the	the	DET
ajst-30190	15	20	accuracy	accuracy	NOUN
ajst-30190	15	21	of	of	ADP
ajst-30190	15	22	detecting	detect	VERB
ajst-30190	15	23	driver	driver	NOUN
ajst-30190	15	24	fatigue	fatigue	NOUN
ajst-30190	15	25	can	can	AUX
ajst-30190	15	26	effectively	effectively	ADV
ajst-30190	15	27	reduce	reduce	VERB
ajst-30190	15	28	the	the	DET
ajst-30190	15	29	occurrence	occurrence	NOUN
ajst-30190	15	30	of	of	ADP
ajst-30190	15	31	such	such	ADJ
ajst-30190	15	32	accidents	accident	NOUN
ajst-30190	15	33	.	.	PUNCT
ajst-30190	16	1	in	in	ADP
ajst-30190	16	2	industrial	industrial	ADJ
ajst-30190	16	3	production	production	NOUN
ajst-30190	16	4	,	,	PUNCT
ajst-30190	16	5	worker	worker	NOUN
ajst-30190	16	6	fatigue	fatigue	NOUN
ajst-30190	16	7	can	can	AUX
ajst-30190	16	8	lead	lead	VERB
ajst-30190	16	9	to	to	ADP
ajst-30190	16	10	operational	operational	ADJ
ajst-30190	16	11	errors	error	NOUN
ajst-30190	16	12	,	,	PUNCT
ajst-30190	16	13	reduce	reduce	VERB
ajst-30190	16	14	productivity	productivity	NOUN
ajst-30190	16	15	,	,	PUNCT
ajst-30190	16	16	and	and	CCONJ
ajst-30190	16	17	even	even	ADV
ajst-30190	16	18	cause	cause	VERB
ajst-30190	16	19	serious	serious	ADJ
ajst-30190	16	20	safety	safety	NOUN
ajst-30190	16	21	accidents	accident	NOUN
ajst-30190	16	22	,	,	PUNCT
ajst-30190	16	23	so	so	SCONJ
ajst-30190	16	24	it	it	PRON
ajst-30190	16	25	is	be	AUX
ajst-30190	16	26	crucial	crucial	ADJ
ajst-30190	16	27	for	for	ADP
ajst-30190	16	28	enterprises	enterprise	NOUN
ajst-30190	16	29	and	and	CCONJ
ajst-30190	16	30	factories	factory	NOUN
ajst-30190	16	31	to	to	PART
ajst-30190	16	32	ensure	ensure	VERB
ajst-30190	16	33	that	that	SCONJ
ajst-30190	16	34	workers	worker	NOUN
ajst-30190	16	35	work	work	VERB
ajst-30190	16	36	in	in	ADP
ajst-30190	16	37	a	a	DET
ajst-30190	16	38	sober	sober	ADJ
ajst-30190	16	39	state	state	NOUN
ajst-30190	16	40	for	for	ADP
ajst-30190	16	41	safe	safe	ADJ
ajst-30190	16	42	and	and	CCONJ
ajst-30190	16	43	effective	effective	ADJ
ajst-30190	16	44	production	production	NOUN
ajst-30190	16	45	.	.	PUNCT
ajst-30190	17	1	eeg	eeg	NOUN
ajst-30190	17	2	signals	signal	NOUN
ajst-30190	17	3	,	,	PUNCT
ajst-30190	17	4	as	as	ADP
ajst-30190	17	5	a	a	DET
ajst-30190	17	6	kind	kind	NOUN
ajst-30190	17	7	of	of	ADP
ajst-30190	17	8	physiological	physiological	ADJ
ajst-30190	17	9	signals	signal	NOUN
ajst-30190	17	10	,	,	PUNCT
ajst-30190	17	11	can	can	AUX
ajst-30190	17	12	directly	directly	ADV
ajst-30190	17	13	reflect	reflect	VERB
ajst-30190	17	14	the	the	DET
ajst-30190	17	15	changes	change	NOUN
ajst-30190	17	16	of	of	ADP
ajst-30190	17	17	brain	brain	NOUN
ajst-30190	17	18	nerve	nerve	NOUN
ajst-30190	17	19	activity	activity	NOUN
ajst-30190	17	20	and	and	CCONJ
ajst-30190	17	21	contain	contain	VERB
ajst-30190	17	22	key	key	ADJ
ajst-30190	17	23	characteristic	characteristic	ADJ
ajst-30190	17	24	information	information	NOUN
ajst-30190	17	25	related	relate	VERB
ajst-30190	17	26	to	to	ADP
ajst-30190	17	27	fatigue	fatigue	NOUN
ajst-30190	17	28	state	state	NOUN
ajst-30190	17	29	.	.	PUNCT
ajst-30190	18	1	research	research	NOUN
ajst-30190	18	2	on	on	ADP
ajst-30190	18	3	fatigue	fatigue	NOUN
ajst-30190	18	4	eeg	eeg	NOUN
ajst-30190	18	5	can	can	AUX
ajst-30190	18	6	provide	provide	VERB
ajst-30190	18	7	insight	insight	NOUN
ajst-30190	18	8	into	into	ADP
ajst-30190	18	9	the	the	DET
ajst-30190	18	10	physiological	physiological	ADJ
ajst-30190	18	11	mechanisms	mechanism	NOUN
ajst-30190	18	12	of	of	ADP
ajst-30190	18	13	the	the	DET
ajst-30190	18	14	brain	brain	NOUN
ajst-30190	18	15	during	during	ADP
ajst-30190	18	16	fatigue	fatigue	NOUN
ajst-30190	18	17	,	,	PUNCT
ajst-30190	18	18	provide	provide	VERB
ajst-30190	18	19	scientific	scientific	ADJ
ajst-30190	18	20	and	and	CCONJ
ajst-30190	18	21	reliable	reliable	ADJ
ajst-30190	18	22	fatigue	fatigue	NOUN
ajst-30190	18	23	assessment	assessment	NOUN
ajst-30190	18	24	methods	method	NOUN
ajst-30190	18	25	for	for	ADP
ajst-30190	18	26	related	related	ADJ
ajst-30190	18	27	fields	field	NOUN
ajst-30190	18	28	,	,	PUNCT
ajst-30190	18	29	and	and	CCONJ
ajst-30190	18	30	thus	thus	ADV
ajst-30190	18	31	safeguard	safeguard	VERB
ajst-30190	18	32	people	people	NOUN
ajst-30190	18	33	's	's	PART
ajst-30190	18	34	lives	life	NOUN
ajst-30190	18	35	and	and	CCONJ
ajst-30190	18	36	improve	improve	VERB
ajst-30190	18	37	productivity	productivity	NOUN
ajst-30190	18	38	and	and	CCONJ
ajst-30190	18	39	quality	quality	NOUN
ajst-30190	18	40	of	of	ADP
ajst-30190	18	41	life	life	NOUN
ajst-30190	18	42	.	.	PUNCT
ajst-30190	19	1	currently	currently	ADV
ajst-30190	19	2	,	,	PUNCT
ajst-30190	19	3	the	the	DET
ajst-30190	19	4	methods	method	NOUN
ajst-30190	19	5	of	of	ADP
ajst-30190	19	6	fatigue	fatigue	NOUN
ajst-30190	19	7	eeg	eeg	NOUN
ajst-30190	19	8	assessment	assessment	NOUN
ajst-30190	19	9	are	be	AUX
ajst-30190	19	10	divided	divide	VERB
ajst-30190	19	11	into	into	ADP
ajst-30190	19	12	subjective	subjective	ADJ
ajst-30190	19	13	and	and	CCONJ
ajst-30190	19	14	objective	objective	ADJ
ajst-30190	19	15	assessment	assessment	NOUN
ajst-30190	19	16	.	.	PUNCT
ajst-30190	20	1	subjective	subjective	ADJ
ajst-30190	20	2	assessment	assessment	NOUN
ajst-30190	20	3	methods	method	NOUN
ajst-30190	20	4	are	be	AUX
ajst-30190	20	5	usually	usually	ADV
ajst-30190	20	6	used	use	VERB
ajst-30190	20	7	:	:	PUNCT
ajst-30190	20	8	piper	piper	NOUN
ajst-30190	20	9	fatigue	fatigue	NOUN
ajst-30190	20	10	scale	scale	NOUN
ajst-30190	20	11	,	,	PUNCT
ajst-30190	20	12	karolinska	karolinska	ADJ
ajst-30190	20	13	sleepiness	sleepiness	ADJ
ajst-30190	20	14	scale	scale	NOUN
ajst-30190	21	1	[	[	X
ajst-30190	21	2	1	1	NUM
ajst-30190	21	3	]	]	PUNCT
ajst-30190	21	4	,	,	PUNCT
ajst-30190	21	5	epworth	epworth	ADJ
ajst-30190	21	6	sleepiness	sleepiness	NOUN
ajst-30190	21	7	scale	scale	NOUN
ajst-30190	21	8	[	[	X
ajst-30190	21	9	2	2	NUM
ajst-30190	21	10	,	,	PUNCT
ajst-30190	21	11	3	3	NUM
ajst-30190	21	12	]	]	PUNCT
ajst-30190	21	13	,	,	PUNCT
ajst-30190	21	14	stanford	stanford	PROPN
ajst-30190	21	15	sleepiness	sleepiness	PROPN
ajst-30190	21	16	scale	scale	NOUN
ajst-30190	22	1	[	[	X
ajst-30190	22	2	4	4	NUM
ajst-30190	22	3	]	]	PUNCT
ajst-30190	22	4	.	.	PUNCT
ajst-30190	23	1	this	this	DET
ajst-30190	23	2	approach	approach	NOUN
ajst-30190	23	3	relies	rely	VERB
ajst-30190	23	4	on	on	ADP
ajst-30190	23	5	the	the	DET
ajst-30190	23	6	subjective	subjective	ADJ
ajst-30190	23	7	feelings	feeling	NOUN
ajst-30190	23	8	of	of	ADP
ajst-30190	23	9	the	the	DET
ajst-30190	23	10	subjects	subject	NOUN
ajst-30190	23	11	to	to	PART
ajst-30190	23	12	judge	judge	VERB
ajst-30190	23	13	the	the	DET
ajst-30190	23	14	degree	degree	NOUN
ajst-30190	23	15	of	of	ADP
ajst-30190	23	16	fatigue	fatigue	NOUN
ajst-30190	23	17	,	,	PUNCT
ajst-30190	23	18	which	which	PRON
ajst-30190	23	19	is	be	AUX
ajst-30190	23	20	susceptible	susceptible	ADJ
ajst-30190	23	21	to	to	ADP
ajst-30190	23	22	the	the	DET
ajst-30190	23	23	interference	interference	NOUN
ajst-30190	23	24	of	of	ADP
ajst-30190	23	25	a	a	DET
ajst-30190	23	26	variety	variety	NOUN
ajst-30190	23	27	of	of	ADP
ajst-30190	23	28	factors	factor	NOUN
ajst-30190	23	29	,	,	PUNCT
ajst-30190	23	30	so	so	SCONJ
ajst-30190	23	31	the	the	DET
ajst-30190	23	32	combination	combination	NOUN
ajst-30190	23	33	of	of	ADP
ajst-30190	23	34	objective	objective	ADJ
ajst-30190	23	35	assessment	assessment	NOUN
ajst-30190	23	36	methods	method	NOUN
ajst-30190	23	37	can	can	AUX
ajst-30190	23	38	more	more	ADV
ajst-30190	23	39	comprehensively	comprehensively	ADV
ajst-30190	23	40	and	and	CCONJ
ajst-30190	23	41	objectively	objectively	ADV
ajst-30190	23	42	reflect	reflect	VERB
ajst-30190	23	43	the	the	DET
ajst-30190	23	44	actual	actual	ADJ
ajst-30190	23	45	fatigue	fatigue	NOUN
ajst-30190	23	46	status	status	NOUN
ajst-30190	23	47	of	of	ADP
ajst-30190	23	48	the	the	DET
ajst-30190	23	49	subjects	subject	NOUN
ajst-30190	23	50	.	.	PUNCT
ajst-30190	24	1	objective	objective	ADJ
ajst-30190	24	2	assessment	assessment	NOUN
ajst-30190	24	3	methods	method	NOUN
ajst-30190	24	4	mainly	mainly	ADV
ajst-30190	24	5	include	include	VERB
ajst-30190	24	6	psychological	psychological	ADJ
ajst-30190	24	7	indicators	indicator	NOUN
ajst-30190	24	8	,	,	PUNCT
ajst-30190	24	9	behavioral	behavioral	ADJ
ajst-30190	24	10	characteristics	characteristic	NOUN
ajst-30190	24	11	and	and	CCONJ
ajst-30190	24	12	physiological	physiological	ADJ
ajst-30190	24	13	signals	signal	NOUN
ajst-30190	24	14	.	.	PUNCT
ajst-30190	25	1	eeg	eeg	PROPN
ajst-30190	25	2	,	,	PUNCT
ajst-30190	25	3	as	as	ADP
ajst-30190	25	4	a	a	DET
ajst-30190	25	5	physiological	physiological	ADJ
ajst-30190	25	6	signal	signal	NOUN
ajst-30190	25	7	,	,	PUNCT
ajst-30190	25	8	can	can	AUX
ajst-30190	25	9	directly	directly	ADV
ajst-30190	25	10	reflect	reflect	VERB
ajst-30190	25	11	brain	brain	NOUN
ajst-30190	25	12	activity	activity	NOUN
ajst-30190	25	13	with	with	ADP
ajst-30190	25	14	high	high	ADJ
ajst-30190	25	15	sensitivity	sensitivity	NOUN
ajst-30190	25	16	and	and	CCONJ
ajst-30190	25	17	objectivity	objectivity	NOUN
ajst-30190	25	18	,	,	PUNCT
ajst-30190	25	19	and	and	CCONJ
ajst-30190	25	20	is	be	AUX
ajst-30190	25	21	regarded	regard	VERB
ajst-30190	25	22	as	as	ADP
ajst-30190	25	23	the	the	DET
ajst-30190	25	24	‘	'	PUNCT
ajst-30190	25	25	gold	gold	ADJ
ajst-30190	25	26	standard	standard	NOUN
ajst-30190	25	27	’	'	PUNCT
ajst-30190	25	28	for	for	ADP
ajst-30190	25	29	fatigue	fatigue	NOUN
ajst-30190	25	30	detection	detection	NOUN
ajst-30190	26	1	[	[	X
ajst-30190	26	2	5	5	NUM
ajst-30190	26	3	]	]	PUNCT
ajst-30190	26	4	,	,	PUNCT
ajst-30190	26	5	and	and	CCONJ
ajst-30190	26	6	is	be	AUX
ajst-30190	26	7	usually	usually	ADV
ajst-30190	26	8	used	use	VERB
ajst-30190	26	9	in	in	ADP
ajst-30190	26	10	studies	study	NOUN
ajst-30190	26	11	to	to	PART
ajst-30190	26	12	detect	detect	VERB
ajst-30190	26	13	human	human	ADJ
ajst-30190	26	14	brain	brain	NOUN
ajst-30190	26	15	load	load	NOUN
ajst-30190	26	16	and	and	CCONJ
ajst-30190	26	17	fatigue	fatigue	NOUN
ajst-30190	26	18	status	status	NOUN
ajst-30190	26	19	.	.	PUNCT
ajst-30190	27	1	at	at	ADP
ajst-30190	27	2	present	present	ADJ
ajst-30190	27	3	,	,	PUNCT
ajst-30190	27	4	the	the	DET
ajst-30190	27	5	research	research	NOUN
ajst-30190	27	6	on	on	ADP
ajst-30190	27	7	fatigue	fatigue	NOUN
ajst-30190	27	8	eeg	eeg	PROPN
ajst-30190	27	9	is	be	AUX
ajst-30190	27	10	getting	get	VERB
ajst-30190	27	11	more	more	ADJ
ajst-30190	27	12	and	and	CCONJ
ajst-30190	27	13	more	more	ADJ
ajst-30190	27	14	attention	attention	NOUN
ajst-30190	27	15	and	and	CCONJ
ajst-30190	27	16	importance	importance	NOUN
ajst-30190	27	17	at	at	ADP
ajst-30190	27	18	home	home	NOUN
ajst-30190	27	19	and	and	CCONJ
ajst-30190	27	20	abroad	abroad	ADV
ajst-30190	27	21	,	,	PUNCT
ajst-30190	27	22	and	and	CCONJ
ajst-30190	27	23	some	some	DET
ajst-30190	27	24	better	well	ADJ
ajst-30190	27	25	results	result	NOUN
ajst-30190	27	26	have	have	AUX
ajst-30190	27	27	been	be	AUX
ajst-30190	27	28	achieved	achieve	VERB
ajst-30190	27	29	.	.	PUNCT
ajst-30190	28	1	peng	peng	PROPN
ajst-30190	29	1	[	[	X
ajst-30190	29	2	6	6	NUM
ajst-30190	29	3	]	]	PUNCT
ajst-30190	29	4	et	et	PROPN
ajst-30190	29	5	al	al	PROPN
ajst-30190	29	6	.	.	PROPN
ajst-30190	29	7	achieved	achieve	VERB
ajst-30190	29	8	the	the	DET
ajst-30190	29	9	approximation	approximation	NOUN
ajst-30190	29	10	of	of	ADP
ajst-30190	29	11	eeg	eeg	NOUN
ajst-30190	29	12	by	by	ADP
ajst-30190	29	13	wavelet	wavelet	NOUN
ajst-30190	29	14	analysis	analysis	NOUN
ajst-30190	29	15	,	,	PUNCT
ajst-30190	29	16	and	and	CCONJ
ajst-30190	29	17	the	the	DET
ajst-30190	29	18	sample	sample	NOUN
ajst-30190	29	19	entropy	entropy	NOUN
ajst-30190	29	20	value	value	NOUN
ajst-30190	29	21	was	be	AUX
ajst-30190	29	22	used	use	VERB
ajst-30190	29	23	as	as	ADP
ajst-30190	29	24	the	the	DET
ajst-30190	29	25	key	key	ADJ
ajst-30190	29	26	feature	feature	NOUN
ajst-30190	29	27	,	,	PUNCT
ajst-30190	29	28	and	and	CCONJ
ajst-30190	29	29	the	the	DET
ajst-30190	29	30	accuracy	accuracy	NOUN
ajst-30190	29	31	of	of	ADP
ajst-30190	29	32	fatigue	fatigue	NOUN
ajst-30190	29	33	recognition	recognition	NOUN
ajst-30190	29	34	was	be	AUX
ajst-30190	29	35	increased	increase	VERB
ajst-30190	29	36	from	from	ADP
ajst-30190	29	37	65.1	65.1	NUM
ajst-30190	29	38	%	%	NOUN
ajst-30190	29	39	to	to	ADP
ajst-30190	29	40	87.7	87.7	NUM
ajst-30190	29	41	%	%	NOUN
ajst-30190	29	42	compared	compare	VERB
ajst-30190	29	43	with	with	ADP
ajst-30190	29	44	the	the	DET
ajst-30190	29	45	traditional	traditional	ADJ
ajst-30190	29	46	entropy	entropy	NOUN
ajst-30190	29	47	method	method	NOUN
ajst-30190	29	48	.	.	PUNCT
ajst-30190	30	1	luo	luo	PROPN
ajst-30190	31	1	[	[	X
ajst-30190	31	2	7	7	X
ajst-30190	31	3	]	]	PUNCT
ajst-30190	31	4	et	et	PROPN
ajst-30190	31	5	al	al	PROPN
ajst-30190	31	6	.	.	PROPN
ajst-30190	31	7	collected	collect	VERB
ajst-30190	31	8	the	the	DET
ajst-30190	31	9	prefrontal	prefrontal	ADJ
ajst-30190	31	10	fatigue	fatigue	NOUN
ajst-30190	31	11	eeg	eeg	NOUN
ajst-30190	31	12	signals	signal	NOUN
ajst-30190	31	13	with	with	ADP
ajst-30190	31	14	adaptive	adaptive	ADJ
ajst-30190	31	15	multi	multi	ADJ
ajst-30190	31	16	-	-	ADJ
ajst-30190	31	17	scale	scale	ADJ
ajst-30190	31	18	entropy	entropy	NOUN
ajst-30190	31	19	feature	feature	NOUN
ajst-30190	31	20	extraction	extraction	NOUN
ajst-30190	31	21	algorithm	algorithm	NOUN
ajst-30190	31	22	,	,	PUNCT
ajst-30190	31	23	and	and	CCONJ
ajst-30190	31	24	the	the	DET
ajst-30190	31	25	fatigue	fatigue	NOUN
ajst-30190	31	26	driving	drive	VERB
ajst-30190	31	27	detection	detection	NOUN
ajst-30190	31	28	accuracy	accuracy	NOUN
ajst-30190	31	29	reached	reach	VERB
ajst-30190	31	30	95.37%.hu	95.37%.hu	PROPN
ajst-30190	32	1	[	[	X
ajst-30190	32	2	8	8	NUM
ajst-30190	32	3	]	]	PUNCT
ajst-30190	32	4	et	et	PROPN
ajst-30190	32	5	al	al	PROPN
ajst-30190	32	6	.	.	PROPN
ajst-30190	32	7	used	use	VERB
ajst-30190	32	8	adaboost	adaboost	ADJ
ajst-30190	32	9	classifier	classifier	NOUN
ajst-30190	32	10	for	for	ADP
ajst-30190	32	11	fatigue	fatigue	NOUN
ajst-30190	32	12	prediction	prediction	NOUN
ajst-30190	32	13	with	with	ADP
ajst-30190	32	14	fuzzy	fuzzy	ADJ
ajst-30190	32	15	entropy	entropy	NOUN
ajst-30190	32	16	,	,	PUNCT
ajst-30190	32	17	sample	sample	NOUN
ajst-30190	32	18	entropy	entropy	PROPN
ajst-30190	32	19	,	,	PUNCT
ajst-30190	32	20	approximate	approximate	ADJ
ajst-30190	32	21	entropy	entropy	PROPN
ajst-30190	32	22	,	,	PUNCT
ajst-30190	32	23	spectral	spectral	ADJ
ajst-30190	32	24	entropy	entropy	NOUN
ajst-30190	32	25	,	,	PUNCT
ajst-30190	32	26	and	and	CCONJ
ajst-30190	32	27	combinatorial	combinatorial	ADJ
ajst-30190	32	28	entropy	entropy	NOUN
ajst-30190	32	29	,	,	PUNCT
ajst-30190	32	30	and	and	CCONJ
ajst-30190	32	31	proved	prove	VERB
ajst-30190	32	32	the	the	DET
ajst-30190	32	33	best	good	ADJ
ajst-30190	32	34	performance	performance	NOUN
ajst-30190	32	35	as	as	ADP
ajst-30190	32	36	fuzzy	fuzzy	ADJ
ajst-30190	32	37	entropy	entropy	NOUN
ajst-30190	32	38	and	and	CCONJ
ajst-30190	32	39	combinatorial	combinatorial	ADJ
ajst-30190	32	40	entropy	entropy	NOUN
ajst-30190	32	41	.	.	PUNCT
ajst-30190	33	1	liu	liu	PROPN
ajst-30190	34	1	[	[	X
ajst-30190	34	2	9	9	NUM
ajst-30190	34	3	]	]	PUNCT
ajst-30190	34	4	et	et	PROPN
ajst-30190	34	5	al	al	PROPN
ajst-30190	34	6	.	.	PROPN
ajst-30190	34	7	induced	induce	VERB
ajst-30190	34	8	fatigue	fatigue	NOUN
ajst-30190	34	9	through	through	ADP
ajst-30190	34	10	a	a	DET
ajst-30190	34	11	2	2	NUM
ajst-30190	34	12	-	-	PUNCT
ajst-30190	34	13	back	back	NOUN
ajst-30190	34	14	task	task	NOUN
ajst-30190	34	15	and	and	CCONJ
ajst-30190	34	16	used	use	VERB
ajst-30190	34	17	the	the	DET
ajst-30190	34	18	relief	relief	NOUN
ajst-30190	34	19	f	f	PROPN
ajst-30190	34	20	algorithm	algorithm	NOUN
ajst-30190	34	21	to	to	PART
ajst-30190	34	22	calculate	calculate	VERB
ajst-30190	34	23	the	the	DET
ajst-30190	34	24	weights	weight	NOUN
ajst-30190	34	25	of	of	ADP
ajst-30190	34	26	the	the	DET
ajst-30190	34	27	features	feature	NOUN
ajst-30190	34	28	of	of	ADP
ajst-30190	34	29	each	each	DET
ajst-30190	34	30	channel	channel	NOUN
ajst-30190	34	31	,	,	PUNCT
ajst-30190	34	32	selected	select	VERB
ajst-30190	34	33	the	the	DET
ajst-30190	34	34	upper	upper	ADJ
ajst-30190	34	35	half	half	NOUN
ajst-30190	34	36	of	of	ADP
ajst-30190	34	37	the	the	DET
ajst-30190	34	38	weight	weight	NOUN
ajst-30190	34	39	order	order	NOUN
ajst-30190	34	40	as	as	ADP
ajst-30190	34	41	the	the	DET
ajst-30190	34	42	common	common	ADJ
ajst-30190	34	43	channel	channel	NOUN
ajst-30190	34	44	and	and	CCONJ
ajst-30190	34	45	combined	combine	VERB
ajst-30190	34	46	it	it	PRON
ajst-30190	34	47	with	with	ADP
ajst-30190	34	48	the	the	DET
ajst-30190	34	49	srda	srda	NOUN
ajst-30190	34	50	classifier	classifier	NOUN
ajst-30190	34	51	to	to	PART
ajst-30190	34	52	classify	classify	VERB
ajst-30190	34	53	the	the	DET
ajst-30190	34	54	time	time	NOUN
ajst-30190	34	55	-	-	PUNCT
ajst-30190	34	56	frequency	frequency	NOUN
ajst-30190	34	57	fusion	fusion	NOUN
ajst-30190	34	58	features	feature	NOUN
ajst-30190	34	59	,	,	PUNCT
ajst-30190	34	60	which	which	PRON
ajst-30190	34	61	reduced	reduce	VERB
ajst-30190	34	62	the	the	DET
ajst-30190	34	63	number	number	NOUN
ajst-30190	34	64	of	of	ADP
ajst-30190	34	65	computational	computational	ADJ
ajst-30190	34	66	channels	channel	NOUN
ajst-30190	34	67	and	and	CCONJ
ajst-30190	34	68	improved	improve	VERB
ajst-30190	34	69	the	the	DET
ajst-30190	34	70	accuracy	accuracy	NOUN
ajst-30190	34	71	of	of	ADP
ajst-30190	34	72	the	the	DET
ajst-30190	34	73	mental	mental	ADJ
ajst-30190	34	74	fatigue	fatigue	NOUN
ajst-30190	34	75	detection	detection	NOUN
ajst-30190	34	76	.	.	PUNCT
ajst-30190	35	1	the	the	DET
ajst-30190	35	2	degfrjmcmc	degfrjmcmc	PROPN
ajst-30190	35	3	model	model	NOUN
ajst-30190	35	4	proposed	propose	VERB
ajst-30190	35	5	by	by	ADP
ajst-30190	35	6	guo	guo	PROPN
ajst-30190	35	7	[	[	X
ajst-30190	35	8	10	10	NUM
ajst-30190	35	9	]	]	PUNCT
ajst-30190	35	10	et	et	PROPN
ajst-30190	35	11	al	al	PROPN
ajst-30190	35	12	utilizes	utilize	VERB
ajst-30190	35	13	the	the	DET
ajst-30190	35	14	empirical	empirical	ADJ
ajst-30190	35	15	mode	mode	NOUN
ajst-30190	35	16	decomposition	decomposition	NOUN
ajst-30190	35	17	(	(	PUNCT
ajst-30190	35	18	emd	emd	PROPN
ajst-30190	35	19	)	)	PUNCT
ajst-30190	35	20	and	and	CCONJ
ajst-30190	35	21	the	the	DET
ajst-30190	35	22	improved	improve	VERB
ajst-30190	35	23	reversible	reversible	ADJ
ajst-30190	35	24	jump	jump	NOUN
ajst-30190	35	25	markov	markov	NOUN
ajst-30190	35	26	chain	chain	NOUN
ajst-30190	35	27	monte	monte	PROPN
ajst-30190	35	28	carlo	carlo	PROPN
ajst-30190	35	29	(	(	PUNCT
ajst-30190	35	30	rjmcmc	rjmcmc	NOUN
ajst-30190	35	31	)	)	PUNCT
ajst-30190	35	32	algorithms	algorithm	NOUN
ajst-30190	35	33	to	to	PART
ajst-30190	35	34	filter	filter	VERB
ajst-30190	35	35	out	out	ADP
ajst-30190	35	36	the	the	DET
ajst-30190	35	37	optimal	optimal	ADJ
ajst-30190	35	38	subset	subset	NOUN
ajst-30190	35	39	of	of	ADP
ajst-30190	35	40	features	feature	NOUN
ajst-30190	35	41	and	and	CCONJ
ajst-30190	35	42	combines	combine	VERB
ajst-30190	35	43	them	they	PRON
ajst-30190	35	44	with	with	ADP
ajst-30190	35	45	the	the	DET
ajst-30190	35	46	k	k	PROPN
ajst-30190	35	47	nearest	near	ADJ
ajst-30190	35	48	neighbors	neighbor	NOUN
ajst-30190	35	49	(	(	PUNCT
ajst-30190	35	50	knn	knn	PROPN
ajst-30190	35	51	)	)	PUNCT
ajst-30190	35	52	classifier	classifier	NOUN
ajst-30190	35	53	to	to	PART
ajst-30190	35	54	achieve	achieve	VERB
ajst-30190	35	55	the	the	DET
ajst-30190	35	56	highest	high	ADJ
ajst-30190	35	57	recognition	recognition	NOUN
ajst-30190	35	58	accuracy	accuracy	NOUN
ajst-30190	35	59	of	of	ADP
ajst-30190	35	60	96.11	96.11	NUM
ajst-30190	35	61	%	%	NOUN
ajst-30190	35	62	±	±	NUM
ajst-30190	35	63	0.43	0.43	NUM
ajst-30190	35	64	%	%	NOUN
ajst-30190	35	65	.	.	PUNCT
ajst-30190	36	1	hu	hu	PROPN
ajst-30190	37	1	[	[	X
ajst-30190	37	2	11	11	NUM
ajst-30190	37	3	]	]	PUNCT
ajst-30190	37	4	et	et	PROPN
ajst-30190	37	5	al	al	PROPN
ajst-30190	37	6	.	.	PROPN
ajst-30190	38	1	on	on	ADP
ajst-30190	38	2	the	the	DET
ajst-30190	38	3	other	other	ADJ
ajst-30190	38	4	hand	hand	NOUN
ajst-30190	38	5	,	,	PUNCT
ajst-30190	38	6	used	use	VERB
ajst-30190	38	7	multiple	multiple	ADJ
ajst-30190	38	8	entropy	entropy	NOUN
ajst-30190	38	9	features	feature	NOUN
ajst-30190	38	10	of	of	ADP
ajst-30190	38	11	a	a	DET
ajst-30190	38	12	single	single	ADJ
ajst-30190	38	13	eeg	eeg	NOUN
ajst-30190	38	14	channel	channel	NOUN
ajst-30190	38	15	as	as	ADP
ajst-30190	38	16	inputs	input	NOUN
ajst-30190	38	17	to	to	ADP
ajst-30190	38	18	a	a	DET
ajst-30190	38	19	gradient	gradient	ADJ
ajst-30190	38	20	boosting	boost	VERB
ajst-30190	38	21	decision	decision	NOUN
ajst-30190	38	22	tree	tree	NOUN
ajst-30190	38	23	(	(	PUNCT
ajst-30190	38	24	gbdt	gbdt	PROPN
ajst-30190	38	25	)	)	PUNCT
ajst-30190	38	26	,	,	PUNCT
ajst-30190	38	27	achieving	achieve	VERB
ajst-30190	38	28	the	the	DET
ajst-30190	38	29	highest	high	ADJ
ajst-30190	38	30	average	average	ADJ
ajst-30190	38	31	recognition	recognition	NOUN
ajst-30190	38	32	rate	rate	NOUN
ajst-30190	38	33	of	of	ADP
ajst-30190	38	34	94.0	94.0	NUM
ajst-30190	38	35	%	%	NOUN
ajst-30190	38	36	for	for	ADP
ajst-30190	38	37	the	the	DET
ajst-30190	38	38	three	three	NUM
ajst-30190	38	39	142	142	NUM
ajst-30190	38	40	classifiers	classifier	NOUN
ajst-30190	38	41	of	of	ADP
ajst-30190	38	42	k	k	NOUN
ajst-30190	38	43	-	-	PUNCT
ajst-30190	38	44	nearest	near	ADJ
ajst-30190	38	45	neighbors	neighbor	NOUN
ajst-30190	38	46	,	,	PUNCT
ajst-30190	38	47	support	support	NOUN
ajst-30190	38	48	vector	vector	NOUN
ajst-30190	38	49	machines	machine	NOUN
ajst-30190	38	50	and	and	CCONJ
ajst-30190	38	51	neural	neural	ADJ
ajst-30190	38	52	networks	network	NOUN
ajst-30190	38	53	.	.	PUNCT
ajst-30190	39	1	in	in	ADP
ajst-30190	39	2	summary	summary	NOUN
ajst-30190	39	3	,	,	PUNCT
ajst-30190	39	4	there	there	PRON
ajst-30190	39	5	are	be	VERB
ajst-30190	39	6	relatively	relatively	ADV
ajst-30190	39	7	few	few	ADJ
ajst-30190	39	8	studies	study	NOUN
ajst-30190	39	9	on	on	ADP
ajst-30190	39	10	the	the	DET
ajst-30190	39	11	feature	feature	NOUN
ajst-30190	39	12	combination	combination	NOUN
ajst-30190	39	13	of	of	ADP
ajst-30190	39	14	fatigue	fatigue	NOUN
ajst-30190	39	15	eeg	eeg	NOUN
ajst-30190	39	16	signals	signal	NOUN
ajst-30190	39	17	for	for	ADP
ajst-30190	39	18	sparse	sparse	ADJ
ajst-30190	39	19	channels	channel	NOUN
ajst-30190	39	20	,	,	PUNCT
ajst-30190	39	21	so	so	SCONJ
ajst-30190	39	22	this	this	DET
ajst-30190	39	23	paper	paper	NOUN
ajst-30190	39	24	proposes	propose	VERB
ajst-30190	39	25	a	a	DET
ajst-30190	39	26	model	model	NOUN
ajst-30190	39	27	construction	construction	NOUN
ajst-30190	39	28	method	method	NOUN
ajst-30190	39	29	,	,	PUNCT
ajst-30190	39	30	which	which	PRON
ajst-30190	39	31	introduces	introduce	VERB
ajst-30190	39	32	the	the	DET
ajst-30190	39	33	convolution	convolution	NOUN
ajst-30190	39	34	structure	structure	NOUN
ajst-30190	39	35	into	into	ADP
ajst-30190	39	36	the	the	DET
ajst-30190	39	37	restricted	restricted	ADJ
ajst-30190	39	38	boltzmann	boltzmann	PROPN
ajst-30190	39	39	machine	machine	NOUN
ajst-30190	39	40	model	model	NOUN
ajst-30190	39	41	,	,	PUNCT
ajst-30190	39	42	and	and	CCONJ
ajst-30190	39	43	after	after	ADP
ajst-30190	39	44	dimensionality	dimensionality	NOUN
ajst-30190	39	45	reduction	reduction	NOUN
ajst-30190	39	46	by	by	ADP
ajst-30190	39	47	using	use	VERB
ajst-30190	39	48	principal	principal	ADJ
ajst-30190	39	49	component	component	NOUN
ajst-30190	39	50	analysis	analysis	NOUN
ajst-30190	39	51	,	,	PUNCT
ajst-30190	39	52	combined	combine	VERB
ajst-30190	39	53	with	with	ADP
ajst-30190	39	54	pearson	pearson	PROPN
ajst-30190	39	55	coefficients	coefficient	NOUN
ajst-30190	39	56	,	,	PUNCT
ajst-30190	39	57	retains	retain	VERB
ajst-30190	39	58	the	the	DET
ajst-30190	39	59	features	feature	NOUN
ajst-30190	39	60	with	with	ADP
ajst-30190	39	61	strong	strong	ADJ
ajst-30190	39	62	correlation	correlation	NOUN
ajst-30190	39	63	as	as	ADP
ajst-30190	39	64	the	the	DET
ajst-30190	39	65	input	input	NOUN
ajst-30190	39	66	of	of	ADP
ajst-30190	39	67	the	the	DET
ajst-30190	39	68	classifier	classifier	NOUN
ajst-30190	39	69	.	.	PUNCT
ajst-30190	40	1	a	a	DET
ajst-30190	40	2	self	self	NOUN
ajst-30190	40	3	-	-	PUNCT
ajst-30190	40	4	training	training	NOUN
ajst-30190	40	5	semisupervised	semisupervise	VERB
ajst-30190	40	6	learning	learning	NOUN
ajst-30190	40	7	algorithm	algorithm	NOUN
ajst-30190	40	8	is	be	AUX
ajst-30190	40	9	used	use	VERB
ajst-30190	40	10	to	to	PART
ajst-30190	40	11	train	train	VERB
ajst-30190	40	12	the	the	DET
ajst-30190	40	13	cnn	cnn	PROPN
ajst-30190	40	14	classifier	classifier	NOUN
ajst-30190	40	15	,	,	PUNCT
ajst-30190	40	16	and	and	CCONJ
ajst-30190	40	17	several	several	ADJ
ajst-30190	40	18	iterations	iteration	NOUN
ajst-30190	40	19	are	be	AUX
ajst-30190	40	20	finally	finally	ADV
ajst-30190	40	21	used	use	VERB
ajst-30190	40	22	in	in	ADP
ajst-30190	40	23	svm	svm	PROPN
ajst-30190	40	24	and	and	CCONJ
ajst-30190	40	25	knn	knn	PROPN
ajst-30190	40	26	machine	machine	PROPN
ajst-30190	40	27	learning	learn	VERB
ajst-30190	40	28	classifiers	classifier	NOUN
ajst-30190	40	29	with	with	ADP
ajst-30190	40	30	fatigue	fatigue	NOUN
ajst-30190	40	31	detection	detection	NOUN
ajst-30190	40	32	and	and	CCONJ
ajst-30190	40	33	classification	classification	NOUN
ajst-30190	40	34	,	,	PUNCT
ajst-30190	40	35	aiming	aim	VERB
ajst-30190	40	36	to	to	PART
ajst-30190	40	37	find	find	VERB
ajst-30190	40	38	the	the	DET
ajst-30190	40	39	optimal	optimal	ADJ
ajst-30190	40	40	combination	combination	NOUN
ajst-30190	40	41	of	of	ADP
ajst-30190	40	42	features	feature	NOUN
ajst-30190	40	43	for	for	ADP
ajst-30190	40	44	the	the	DET
ajst-30190	40	45	sparse	sparse	ADJ
ajst-30190	40	46	channel	channel	NOUN
ajst-30190	40	47	and	and	CCONJ
ajst-30190	40	48	the	the	DET
ajst-30190	40	49	classifier	classifier	NOUN
ajst-30190	40	50	with	with	ADP
ajst-30190	40	51	the	the	DET
ajst-30190	40	52	best	good	ADJ
ajst-30190	40	53	performance	performance	NOUN
ajst-30190	40	54	.	.	PUNCT
ajst-30190	41	1	2	2	X
ajst-30190	41	2	.	.	X
ajst-30190	41	3	fatigue	fatigue	NOUN
ajst-30190	41	4	eeg	eeg	PROPN
ajst-30190	41	5	acquisition	acquisition	NOUN
ajst-30190	41	6	process	process	NOUN
ajst-30190	41	7	and	and	CCONJ
ajst-30190	41	8	pre	pre	ADJ
ajst-30190	41	9	-	-	ADJ
ajst-30190	41	10	processing	processing	ADJ
ajst-30190	41	11	(	(	PUNCT
ajst-30190	41	12	1	1	NUM
ajst-30190	41	13	)	)	PUNCT
ajst-30190	41	14	self	self	NOUN
ajst-30190	41	15	-	-	PUNCT
ajst-30190	41	16	assessment	assessment	NOUN
ajst-30190	41	17	of	of	ADP
ajst-30190	41	18	fatigue	fatigue	NOUN
ajst-30190	41	19	status	status	NOUN
ajst-30190	41	20	the	the	DET
ajst-30190	41	21	karolinska	karolinska	PROPN
ajst-30190	41	22	sleepiness	sleepiness	NOUN
ajst-30190	41	23	scale	scale	NOUN
ajst-30190	41	24	(	(	PUNCT
ajst-30190	41	25	kss	kss	PROPN
ajst-30190	41	26	)	)	PUNCT
ajst-30190	41	27	,	,	PUNCT
ajst-30190	41	28	a	a	DET
ajst-30190	41	29	scale	scale	NOUN
ajst-30190	41	30	that	that	PRON
ajst-30190	41	31	enables	enable	VERB
ajst-30190	41	32	subjects	subject	NOUN
ajst-30190	41	33	to	to	PART
ajst-30190	41	34	autonomously	autonomously	ADV
ajst-30190	41	35	assess	assess	VERB
ajst-30190	41	36	their	their	PRON
ajst-30190	41	37	level	level	NOUN
ajst-30190	41	38	of	of	ADP
ajst-30190	41	39	fatigue	fatigue	NOUN
ajst-30190	41	40	,	,	PUNCT
ajst-30190	41	41	has	have	AUX
ajst-30190	41	42	been	be	AUX
ajst-30190	41	43	widely	widely	ADV
ajst-30190	41	44	validated	validate	VERB
ajst-30190	41	45	and	and	CCONJ
ajst-30190	41	46	successfully	successfully	ADV
ajst-30190	41	47	applied	apply	VERB
ajst-30190	41	48	to	to	ADP
ajst-30190	41	49	the	the	DET
ajst-30190	41	50	field	field	NOUN
ajst-30190	41	51	of	of	ADP
ajst-30190	41	52	eeg	eeg	PROPN
ajst-30190	41	53	signal	signal	NOUN
ajst-30190	41	54	research[1	research[1	VERB
ajst-30190	41	55	]	]	PUNCT
ajst-30190	41	56	.	.	PUNCT
ajst-30190	42	1	in	in	ADP
ajst-30190	42	2	this	this	DET
ajst-30190	42	3	study	study	NOUN
ajst-30190	42	4	,	,	PUNCT
ajst-30190	42	5	a	a	DET
ajst-30190	42	6	sample	sample	NOUN
ajst-30190	42	7	of	of	ADP
ajst-30190	42	8	16	16	NUM
ajst-30190	42	9	subjects	subject	NOUN
ajst-30190	42	10	was	be	AUX
ajst-30190	42	11	used	use	VERB
ajst-30190	42	12	to	to	PART
ajst-30190	42	13	calculate	calculate	VERB
ajst-30190	42	14	their	their	PRON
ajst-30190	42	15	kss	kss	PROPN
ajst-30190	42	16	scores	score	NOUN
ajst-30190	42	17	,	,	PUNCT
ajst-30190	42	18	which	which	PRON
ajst-30190	42	19	are	be	AUX
ajst-30190	42	20	rated	rate	VERB
ajst-30190	42	21	as	as	ADP
ajst-30190	42	22	fatigue	fatigue	NOUN
ajst-30190	42	23	with	with	ADP
ajst-30190	42	24	a	a	DET
ajst-30190	42	25	kss	kss	PROPN
ajst-30190	42	26	score	score	NOUN
ajst-30190	42	27	greater	great	ADJ
ajst-30190	42	28	than	than	ADP
ajst-30190	42	29	or	or	CCONJ
ajst-30190	42	30	equal	equal	ADJ
ajst-30190	42	31	to	to	ADP
ajst-30190	42	32	5	5	NUM
ajst-30190	42	33	.	.	PUNCT
ajst-30190	42	34	as	as	SCONJ
ajst-30190	42	35	shown	show	VERB
ajst-30190	42	36	in	in	ADP
ajst-30190	42	37	table	table	NOUN
ajst-30190	42	38	2.1	2.1	NUM
ajst-30190	42	39	below	below	ADV
ajst-30190	42	40	,	,	PUNCT
ajst-30190	42	41	87.5	87.5	NUM
ajst-30190	42	42	%	%	NOUN
ajst-30190	42	43	of	of	ADP
ajst-30190	42	44	subjects	subject	NOUN
ajst-30190	42	45	experienced	experience	VERB
ajst-30190	42	46	fatigue	fatigue	NOUN
ajst-30190	42	47	after	after	ADP
ajst-30190	42	48	completing	complete	VERB
ajst-30190	42	49	the	the	DET
ajst-30190	42	50	1	1	NUM
ajst-30190	42	51	-	-	PUNCT
ajst-30190	42	52	back	back	NOUN
ajst-30190	42	53	experiment	experiment	NOUN
ajst-30190	42	54	.	.	PUNCT
ajst-30190	43	1	the	the	DET
ajst-30190	43	2	results	result	NOUN
ajst-30190	43	3	showed	show	VERB
ajst-30190	43	4	that	that	SCONJ
ajst-30190	43	5	the	the	DET
ajst-30190	43	6	experiment	experiment	NOUN
ajst-30190	43	7	successfully	successfully	ADV
ajst-30190	43	8	induced	induce	VERB
ajst-30190	43	9	fatigue	fatigue	NOUN
ajst-30190	43	10	eeg	eeg	NOUN
ajst-30190	43	11	,	,	PUNCT
ajst-30190	43	12	which	which	PRON
ajst-30190	43	13	could	could	AUX
ajst-30190	43	14	be	be	AUX
ajst-30190	43	15	used	use	VERB
ajst-30190	43	16	as	as	ADP
ajst-30190	43	17	a	a	DET
ajst-30190	43	18	sample	sample	NOUN
ajst-30190	43	19	of	of	ADP
ajst-30190	43	20	fatigue	fatigue	NOUN
ajst-30190	43	21	state	state	NOUN
ajst-30190	43	22	.	.	PUNCT
ajst-30190	44	1	table	table	NOUN
ajst-30190	44	2	2.1	2.1	NUM
ajst-30190	44	3	comparison	comparison	NOUN
ajst-30190	44	4	of	of	ADP
ajst-30190	44	5	kss	kss	PROPN
ajst-30190	44	6	scores	score	NOUN
ajst-30190	44	7	before	before	ADV
ajst-30190	44	8	and	and	CCONJ
ajst-30190	44	9	after	after	ADP
ajst-30190	44	10	the	the	DET
ajst-30190	44	11	1back	1back	NUM
ajst-30190	44	12	task	task	NOUN
ajst-30190	44	13	(	(	PUNCT
ajst-30190	44	14	2	2	NUM
ajst-30190	44	15	)	)	PUNCT
ajst-30190	44	16	n	n	CCONJ
ajst-30190	44	17	-	-	PUNCT
ajst-30190	44	18	back	back	NOUN
ajst-30190	44	19	experimental	experimental	ADJ
ajst-30190	44	20	design	design	NOUN
ajst-30190	44	21	in	in	ADP
ajst-30190	44	22	this	this	DET
ajst-30190	44	23	paper	paper	NOUN
ajst-30190	44	24	,	,	PUNCT
ajst-30190	44	25	in	in	ADP
ajst-30190	44	26	the	the	DET
ajst-30190	44	27	laboratory	laboratory	NOUN
ajst-30190	44	28	,	,	PUNCT
ajst-30190	44	29	the	the	DET
ajst-30190	44	30	eeg	eeg	NOUN
ajst-30190	44	31	signals	signal	NOUN
ajst-30190	44	32	before	before	ADV
ajst-30190	44	33	and	and	CCONJ
ajst-30190	44	34	after	after	ADP
ajst-30190	44	35	the	the	DET
ajst-30190	44	36	n	n	CCONJ
ajst-30190	44	37	-	-	PUNCT
ajst-30190	44	38	back	back	NOUN
ajst-30190	44	39	experiment	experiment	NOUN
ajst-30190	44	40	were	be	AUX
ajst-30190	44	41	collected	collect	VERB
ajst-30190	44	42	from	from	ADP
ajst-30190	44	43	16	16	NUM
ajst-30190	44	44	participants	participant	NOUN
ajst-30190	44	45	using	use	VERB
ajst-30190	44	46	the	the	DET
ajst-30190	44	47	eeg	eeg	NOUN
ajst-30190	44	48	emotivepoc+14	emotivepoc+14	PROPN
ajst-30190	44	49	.	.	PUNCT
ajst-30190	45	1	the	the	DET
ajst-30190	45	2	n	n	CCONJ
ajst-30190	45	3	-	-	PUNCT
ajst-30190	45	4	back	back	NOUN
ajst-30190	45	5	task	task	NOUN
ajst-30190	45	6	paradigm	paradigm	NOUN
ajst-30190	45	7	can	can	AUX
ajst-30190	45	8	be	be	AUX
ajst-30190	45	9	used	use	VERB
ajst-30190	45	10	to	to	PART
ajst-30190	45	11	assess	assess	VERB
ajst-30190	45	12	the	the	DET
ajst-30190	45	13	effects	effect	NOUN
ajst-30190	45	14	of	of	ADP
ajst-30190	45	15	cognitive	cognitive	ADJ
ajst-30190	45	16	aging	aging	NOUN
ajst-30190	45	17	,	,	PUNCT
ajst-30190	45	18	fatigue	fatigue	NOUN
ajst-30190	45	19	,	,	PUNCT
ajst-30190	45	20	and	and	CCONJ
ajst-30190	45	21	stress	stress	NOUN
ajst-30190	45	22	on	on	ADP
ajst-30190	45	23	individuals[12	individuals[12	NOUN
ajst-30190	45	24	]	]	PUNCT
ajst-30190	45	25	.	.	PUNCT
ajst-30190	46	1	in	in	ADP
ajst-30190	46	2	this	this	DET
ajst-30190	46	3	paper	paper	NOUN
ajst-30190	46	4	,	,	PUNCT
ajst-30190	46	5	a	a	DET
ajst-30190	46	6	1	1	NUM
ajst-30190	46	7	-	-	PUNCT
ajst-30190	46	8	back	back	NOUN
ajst-30190	46	9	experimental	experimental	ADJ
ajst-30190	46	10	paradigm	paradigm	NOUN
ajst-30190	46	11	is	be	AUX
ajst-30190	46	12	chosen	choose	VERB
ajst-30190	46	13	,	,	PUNCT
ajst-30190	46	14	using	use	VERB
ajst-30190	46	15	shapes	shape	NOUN
ajst-30190	46	16	of	of	ADP
ajst-30190	46	17	different	different	ADJ
ajst-30190	46	18	colors	color	NOUN
ajst-30190	46	19	as	as	ADP
ajst-30190	46	20	stimulus	stimulus	ADJ
ajst-30190	46	21	elements	element	NOUN
ajst-30190	46	22	at	at	ADP
ajst-30190	46	23	different	different	ADJ
ajst-30190	46	24	locations	location	NOUN
ajst-30190	46	25	.	.	PUNCT
ajst-30190	47	1	a	a	DET
ajst-30190	47	2	sequence	sequence	NOUN
ajst-30190	47	3	of	of	ADP
ajst-30190	47	4	30	30	NUM
ajst-30190	47	5	images	image	NOUN
ajst-30190	47	6	is	be	AUX
ajst-30190	47	7	presented	present	VERB
ajst-30190	47	8	,	,	PUNCT
ajst-30190	47	9	each	each	PRON
ajst-30190	47	10	for	for	ADP
ajst-30190	47	11	3	3	NUM
ajst-30190	47	12	seconds	second	NOUN
ajst-30190	47	13	,	,	PUNCT
ajst-30190	47	14	with	with	ADP
ajst-30190	47	15	an	an	DET
ajst-30190	47	16	empty	empty	ADJ
ajst-30190	47	17	screen	screen	NOUN
ajst-30190	47	18	for	for	ADP
ajst-30190	47	19	2	2	NUM
ajst-30190	47	20	seconds	second	NOUN
ajst-30190	47	21	,	,	PUNCT
ajst-30190	47	22	before	before	SCONJ
ajst-30190	47	23	the	the	DET
ajst-30190	47	24	next	next	ADJ
ajst-30190	47	25	image	image	NOUN
ajst-30190	47	26	appears	appear	VERB
ajst-30190	47	27	.	.	PUNCT
ajst-30190	48	1	subjects	subject	NOUN
ajst-30190	48	2	are	be	AUX
ajst-30190	48	3	asked	ask	VERB
ajst-30190	48	4	to	to	PART
ajst-30190	48	5	judge	judge	VERB
ajst-30190	48	6	whether	whether	SCONJ
ajst-30190	48	7	the	the	DET
ajst-30190	48	8	current	current	ADJ
ajst-30190	48	9	stimulus	stimulus	NOUN
ajst-30190	48	10	is	be	AUX
ajst-30190	48	11	consistent	consistent	ADJ
ajst-30190	48	12	with	with	ADP
ajst-30190	48	13	the	the	DET
ajst-30190	48	14	previous	previous	ADJ
ajst-30190	48	15	stimulus	stimulus	NOUN
ajst-30190	48	16	.	.	PUNCT
ajst-30190	49	1	the	the	DET
ajst-30190	49	2	sequence	sequence	NOUN
ajst-30190	49	3	of	of	ADP
ajst-30190	49	4	stimuli	stimulus	NOUN
ajst-30190	49	5	is	be	AUX
ajst-30190	49	6	shown	show	VERB
ajst-30190	49	7	in	in	ADP
ajst-30190	49	8	figure	figure	NOUN
ajst-30190	49	9	2.1	2.1	NUM
ajst-30190	49	10	.	.	PUNCT
ajst-30190	50	1	the	the	DET
ajst-30190	50	2	final	final	ADJ
ajst-30190	50	3	result	result	NOUN
ajst-30190	50	4	of	of	ADP
ajst-30190	50	5	the	the	DET
ajst-30190	50	6	mean	mean	ADJ
ajst-30190	50	7	response	response	NOUN
ajst-30190	50	8	time	time	NOUN
ajst-30190	50	9	and	and	CCONJ
ajst-30190	50	10	average	average	ADJ
ajst-30190	50	11	correct	correct	ADJ
ajst-30190	50	12	response	response	NOUN
ajst-30190	50	13	rate	rate	NOUN
ajst-30190	50	14	for	for	ADP
ajst-30190	50	15	16	16	NUM
ajst-30190	50	16	participants	participant	NOUN
ajst-30190	50	17	was	be	AUX
ajst-30190	50	18	combined	combine	VERB
ajst-30190	50	19	with	with	ADP
ajst-30190	50	20	subjective	subjective	ADJ
ajst-30190	50	21	rating	rating	NOUN
ajst-30190	50	22	to	to	PART
ajst-30190	50	23	determine	determine	VERB
ajst-30190	50	24	subject	subject	ADJ
ajst-30190	50	25	status	status	NOUN
ajst-30190	50	26	.	.	PUNCT
ajst-30190	51	1	figure	figure	VERB
ajst-30190	51	2	2.1	2.1	NUM
ajst-30190	51	3	design	design	NOUN
ajst-30190	51	4	diagram	diagram	NOUN
ajst-30190	51	5	of	of	ADP
ajst-30190	51	6	the	the	DET
ajst-30190	51	7	stimulation	stimulation	NOUN
ajst-30190	51	8	sequence	sequence	NOUN
ajst-30190	51	9	the	the	DET
ajst-30190	51	10	results	result	NOUN
ajst-30190	51	11	showed	show	VERB
ajst-30190	51	12	that	that	SCONJ
ajst-30190	51	13	the	the	DET
ajst-30190	51	14	average	average	ADJ
ajst-30190	51	15	reaction	reaction	NOUN
ajst-30190	51	16	time	time	NOUN
ajst-30190	51	17	of	of	ADP
ajst-30190	51	18	the	the	DET
ajst-30190	51	19	16	16	NUM
ajst-30190	51	20	participants	participant	NOUN
ajst-30190	51	21	gradually	gradually	ADV
ajst-30190	51	22	increased	increase	VERB
ajst-30190	51	23	with	with	ADP
ajst-30190	51	24	the	the	DET
ajst-30190	51	25	increase	increase	NOUN
ajst-30190	51	26	of	of	ADP
ajst-30190	51	27	duration	duration	NOUN
ajst-30190	51	28	,	,	PUNCT
ajst-30190	51	29	and	and	CCONJ
ajst-30190	51	30	the	the	DET
ajst-30190	51	31	response	response	NOUN
ajst-30190	51	32	accuracy	accuracy	NOUN
ajst-30190	51	33	also	also	ADV
ajst-30190	51	34	gradually	gradually	ADV
ajst-30190	51	35	decreased	decrease	VERB
ajst-30190	51	36	.	.	PUNCT
ajst-30190	52	1	therefore	therefore	ADV
ajst-30190	52	2	,	,	PUNCT
ajst-30190	52	3	it	it	PRON
ajst-30190	52	4	was	be	AUX
ajst-30190	52	5	proved	prove	VERB
ajst-30190	52	6	that	that	SCONJ
ajst-30190	52	7	the	the	DET
ajst-30190	52	8	brain	brain	NOUN
ajst-30190	52	9	fatigue	fatigue	NOUN
ajst-30190	52	10	of	of	ADP
ajst-30190	52	11	the	the	DET
ajst-30190	52	12	subjects	subject	NOUN
ajst-30190	52	13	was	be	AUX
ajst-30190	52	14	successfully	successfully	ADV
ajst-30190	52	15	induced	induce	VERB
ajst-30190	52	16	,	,	PUNCT
ajst-30190	52	17	and	and	CCONJ
ajst-30190	52	18	their	their	PRON
ajst-30190	52	19	eeg	eeg	NOUN
ajst-30190	52	20	signals	signal	NOUN
ajst-30190	52	21	could	could	AUX
ajst-30190	52	22	be	be	AUX
ajst-30190	52	23	used	use	VERB
ajst-30190	52	24	for	for	ADP
ajst-30190	52	25	subsequent	subsequent	ADJ
ajst-30190	52	26	classification	classification	NOUN
ajst-30190	52	27	studies	study	NOUN
ajst-30190	52	28	.	.	PUNCT
ajst-30190	53	1	figure	figure	VERB
ajst-30190	53	2	2.2	2.2	NUM
ajst-30190	53	3	shows	show	VERB
ajst-30190	53	4	the	the	DET
ajst-30190	53	5	overall	overall	ADJ
ajst-30190	53	6	process	process	NOUN
ajst-30190	53	7	framework	framework	NOUN
ajst-30190	53	8	figure	figure	VERB
ajst-30190	53	9	2.2	2.2	NUM
ajst-30190	53	10	framework	framework	NOUN
ajst-30190	53	11	diagram	diagram	NOUN
ajst-30190	53	12	of	of	ADP
ajst-30190	53	13	the	the	DET
ajst-30190	53	14	overall	overall	ADJ
ajst-30190	53	15	flow	flow	NOUN
ajst-30190	53	16	of	of	ADP
ajst-30190	53	17	the	the	DET
ajst-30190	53	18	experiment	experiment	NOUN
ajst-30190	53	19	(	(	PUNCT
ajst-30190	53	20	3	3	X
ajst-30190	53	21	)	)	PUNCT
ajst-30190	53	22	eeg	eeg	PROPN
ajst-30190	53	23	signal	signal	NOUN
ajst-30190	53	24	pre	pre	ADJ
ajst-30190	53	25	-	-	ADJ
ajst-30190	53	26	processing	process	VERB
ajst-30190	53	27	the	the	DET
ajst-30190	53	28	acquired	acquire	VERB
ajst-30190	53	29	raw	raw	ADJ
ajst-30190	53	30	signals	signal	NOUN
ajst-30190	53	31	are	be	AUX
ajst-30190	53	32	interfered	interfere	VERB
ajst-30190	53	33	by	by	ADP
ajst-30190	53	34	noise	noise	NOUN
ajst-30190	53	35	,	,	PUNCT
ajst-30190	53	36	artefacts	artefact	NOUN
ajst-30190	53	37	or	or	CCONJ
ajst-30190	53	38	other	other	ADJ
ajst-30190	53	39	electrophysiological	electrophysiological	ADJ
ajst-30190	53	40	signals	signal	NOUN
ajst-30190	53	41	,	,	PUNCT
ajst-30190	53	42	which	which	PRON
ajst-30190	53	43	to	to	ADP
ajst-30190	53	44	a	a	DET
ajst-30190	53	45	large	large	ADJ
ajst-30190	53	46	extent	extent	NOUN
ajst-30190	53	47	will	will	AUX
ajst-30190	53	48	directly	directly	ADV
ajst-30190	53	49	affect	affect	VERB
ajst-30190	53	50	the	the	DET
ajst-30190	53	51	data	datum	NOUN
ajst-30190	53	52	quality	quality	NOUN
ajst-30190	53	53	and	and	CCONJ
ajst-30190	53	54	analysis	analysis	NOUN
ajst-30190	53	55	results	result	NOUN
ajst-30190	53	56	.	.	PUNCT
ajst-30190	54	1	therefore	therefore	ADV
ajst-30190	54	2	,	,	PUNCT
ajst-30190	54	3	pre	pre	ADJ
ajst-30190	54	4	-	-	ADJ
ajst-30190	54	5	processing	processing	NOUN
ajst-30190	54	6	of	of	ADP
ajst-30190	54	7	eeg	eeg	NOUN
ajst-30190	54	8	signals	signal	NOUN
ajst-30190	54	9	is	be	AUX
ajst-30190	54	10	a	a	DET
ajst-30190	54	11	very	very	ADV
ajst-30190	54	12	necessary	necessary	ADJ
ajst-30190	54	13	process	process	NOUN
ajst-30190	54	14	before	before	ADP
ajst-30190	54	15	eeg	eeg	NOUN
ajst-30190	54	16	characterization	characterization	NOUN
ajst-30190	54	17	.	.	PUNCT
ajst-30190	55	1	the	the	DET
ajst-30190	55	2	acquired	acquire	VERB
ajst-30190	55	3	raw	raw	ADJ
ajst-30190	55	4	signal	signal	NOUN
ajst-30190	55	5	can	can	AUX
ajst-30190	55	6	be	be	AUX
ajst-30190	55	7	interfered	interfere	VERB
ajst-30190	55	8	with	with	ADP
ajst-30190	55	9	by	by	ADP
ajst-30190	55	10	noise	noise	NOUN
ajst-30190	55	11	or	or	CCONJ
ajst-30190	55	12	artifacts	artifact	NOUN
ajst-30190	55	13	,	,	PUNCT
ajst-30190	55	14	which	which	PRON
ajst-30190	55	15	can	can	AUX
ajst-30190	55	16	directly	directly	ADV
ajst-30190	55	17	affect	affect	VERB
ajst-30190	55	18	data	datum	NOUN
ajst-30190	55	19	quality	quality	NOUN
ajst-30190	55	20	and	and	CCONJ
ajst-30190	55	21	analysis	analysis	NOUN
ajst-30190	55	22	results	result	NOUN
ajst-30190	55	23	.	.	PUNCT
ajst-30190	56	1	therefore	therefore	ADV
ajst-30190	56	2	,	,	PUNCT
ajst-30190	56	3	the	the	DET
ajst-30190	56	4	preprocessing	preprocessing	NOUN
ajst-30190	56	5	of	of	ADP
ajst-30190	56	6	eeg	eeg	NOUN
ajst-30190	56	7	signals	signal	NOUN
ajst-30190	56	8	is	be	AUX
ajst-30190	56	9	a	a	DET
ajst-30190	56	10	very	very	ADV
ajst-30190	56	11	necessary	necessary	ADJ
ajst-30190	56	12	process	process	NOUN
ajst-30190	56	13	prior	prior	ADV
ajst-30190	56	14	to	to	ADP
ajst-30190	56	15	eeg	eeg	NOUN
ajst-30190	56	16	signs	sign	NOUN
ajst-30190	56	17	.	.	PUNCT
ajst-30190	57	1	in	in	ADP
ajst-30190	57	2	order	order	NOUN
ajst-30190	57	3	to	to	PART
ajst-30190	57	4	effectively	effectively	ADV
ajst-30190	57	5	eliminate	eliminate	VERB
ajst-30190	57	6	the	the	DET
ajst-30190	57	7	interference	interference	NOUN
ajst-30190	57	8	,	,	PUNCT
ajst-30190	57	9	the	the	DET
ajst-30190	57	10	empirical	empirical	ADJ
ajst-30190	57	11	mode	mode	NOUN
ajst-30190	57	12	decomposition	decomposition	NOUN
ajst-30190	57	13	algorithm	algorithm	NOUN
ajst-30190	57	14	and	and	CCONJ
ajst-30190	57	15	the	the	DET
ajst-30190	57	16	adaptive	adaptive	ADJ
ajst-30190	57	17	filtering	filtering	NOUN
ajst-30190	57	18	of	of	ADP
ajst-30190	57	19	the	the	DET
ajst-30190	57	20	digital	digital	ADJ
ajst-30190	57	21	filter	filter	NOUN
ajst-30190	57	22	are	be	AUX
ajst-30190	57	23	selected	select	VERB
ajst-30190	57	24	to	to	PART
ajst-30190	57	25	denoise	denoise	VERB
ajst-30190	57	26	the	the	DET
ajst-30190	57	27	original	original	ADJ
ajst-30190	57	28	signal	signal	NOUN
ajst-30190	57	29	.	.	PUNCT
ajst-30190	58	1	the	the	DET
ajst-30190	58	2	purpose	purpose	NOUN
ajst-30190	58	3	of	of	ADP
ajst-30190	58	4	emd	emd	PROPN
ajst-30190	58	5	decomposition	decomposition	NOUN
ajst-30190	58	6	is	be	AUX
ajst-30190	58	7	to	to	PART
ajst-30190	58	8	decompose	decompose	VERB
ajst-30190	58	9	a	a	DET
ajst-30190	58	10	signal	signal	NOUN
ajst-30190	58	11	x(n	x(n	NOUN
ajst-30190	58	12	)	)	PUNCT
ajst-30190	58	13	into	into	ADP
ajst-30190	58	14	m	m	PROPN
ajst-30190	58	15	intrinsic	intrinsic	ADJ
ajst-30190	58	16	mode	mode	NOUN
ajst-30190	58	17	functions	function	NOUN
ajst-30190	58	18	(	(	PUNCT
ajst-30190	58	19	imf	imf	PROPN
ajst-30190	58	20	)	)	PUNCT
ajst-30190	58	21	and	and	CCONJ
ajst-30190	58	22	a	a	DET
ajst-30190	58	23	residual	residual	ADJ
ajst-30190	58	24	.	.	PUNCT
ajst-30190	59	1	the	the	DET
ajst-30190	59	2	expression	expression	NOUN
ajst-30190	59	3	of	of	ADP
ajst-30190	59	4	the	the	DET
ajst-30190	59	5	original	original	ADJ
ajst-30190	59	6	signal	signal	NOUN
ajst-30190	59	7	x(n	x(n	NOUN
ajst-30190	59	8	)	)	PUNCT
ajst-30190	59	9	after	after	SCONJ
ajst-30190	59	10	emd	emd	PROPN
ajst-30190	59	11	decomposition	decomposition	NOUN
ajst-30190	59	12	is	be	AUX
ajst-30190	59	13	:	:	PUNCT
ajst-30190	59	14	[	[	X
ajst-30190	59	15	13	13	NUM
ajst-30190	59	16	,	,	PUNCT
ajst-30190	59	17	14	14	NUM
ajst-30190	59	18	]	]	PUNCT
ajst-30190	59	19	.	.	PUNCT
ajst-30190	60	1	143	143	NUM
ajst-30190	60	2	𝑋	𝑋	PROPN
ajst-30190	60	3	𝑛	𝑛	VERB
ajst-30190	60	4	𝑐	𝑐	PROPN
ajst-30190	60	5	𝑛	𝑛	ADJ
ajst-30190	60	6	𝑟	𝑟	X
ajst-30190	60	7	𝑛	𝑛	PROPN
ajst-30190	60	8	𝑐	𝑐	NOUN
ajst-30190	60	9	𝑛	𝑛	PROPN
ajst-30190	60	10	:	:	PUNCT
ajst-30190	60	11	represents	represent	VERB
ajst-30190	60	12	the	the	DET
ajst-30190	60	13	order	order	NOUN
ajst-30190	60	14	m	m	VERB
ajst-30190	60	15	modal	modal	ADJ
ajst-30190	60	16	function	function	NOUN
ajst-30190	60	17	.	.	PUNCT
ajst-30190	61	1	𝑟	𝑟	X
ajst-30190	61	2	𝑛	𝑛	X
ajst-30190	61	3	:	:	PUNCT
ajst-30190	61	4	represents	represent	VERB
ajst-30190	61	5	the	the	DET
ajst-30190	61	6	residuals	residual	NOUN
ajst-30190	61	7	that	that	PRON
ajst-30190	61	8	ultimately	ultimately	ADV
ajst-30190	61	9	meet	meet	VERB
ajst-30190	61	10	the	the	DET
ajst-30190	61	11	criterion	criterion	NOUN
ajst-30190	61	12	.	.	PUNCT
ajst-30190	62	1	in	in	ADP
ajst-30190	62	2	this	this	DET
ajst-30190	62	3	paper	paper	NOUN
ajst-30190	62	4	,	,	PUNCT
ajst-30190	62	5	we	we	PRON
ajst-30190	62	6	chose	choose	VERB
ajst-30190	62	7	to	to	PART
ajst-30190	62	8	continue	continue	VERB
ajst-30190	62	9	to	to	PART
ajst-30190	62	10	remove	remove	VERB
ajst-30190	62	11	artifacts	artifact	NOUN
ajst-30190	62	12	such	such	ADJ
ajst-30190	62	13	as	as	ADP
ajst-30190	62	14	ocular	ocular	ADJ
ajst-30190	62	15	and	and	CCONJ
ajst-30190	62	16	electromyography	electromyography	NOUN
ajst-30190	62	17	with	with	ADP
ajst-30190	62	18	fastica	fastica	PROPN
ajst-30190	62	19	.	.	PUNCT
ajst-30190	63	1	fastica	fastica	PROPN
ajst-30190	63	2	expects	expect	VERB
ajst-30190	63	3	to	to	PART
ajst-30190	63	4	find	find	VERB
ajst-30190	63	5	a	a	DET
ajst-30190	63	6	separation	separation	NOUN
ajst-30190	63	7	vector	vector	NOUN
ajst-30190	63	8	that	that	PRON
ajst-30190	63	9	maximizes	maximize	VERB
ajst-30190	63	10	the	the	DET
ajst-30190	63	11	latent	latent	ADJ
ajst-30190	63	12	non	non	ADJ
ajst-30190	63	13	-	-	ADJ
ajst-30190	63	14	gaussian	gaussian	ADJ
ajst-30190	63	15	features	feature	NOUN
ajst-30190	63	16	of	of	ADP
ajst-30190	63	17	multidimensional	multidimensional	ADJ
ajst-30190	63	18	data	datum	NOUN
ajst-30190	63	19	in	in	ADP
ajst-30190	63	20	an	an	DET
ajst-30190	63	21	efficient	efficient	ADJ
ajst-30190	63	22	way	way	NOUN
ajst-30190	63	23	,	,	PUNCT
ajst-30190	63	24	so	so	SCONJ
ajst-30190	63	25	as	as	SCONJ
ajst-30190	63	26	to	to	PART
ajst-30190	63	27	achieve	achieve	VERB
ajst-30190	63	28	blind	blind	ADJ
ajst-30190	63	29	source	source	NOUN
ajst-30190	63	30	separation	separation	NOUN
ajst-30190	63	31	[	[	X
ajst-30190	63	32	15	15	NUM
ajst-30190	63	33	]	]	PUNCT
ajst-30190	63	34	.	.	PUNCT
ajst-30190	64	1	the	the	DET
ajst-30190	64	2	iteration	iteration	NOUN
ajst-30190	64	3	formula	formula	NOUN
ajst-30190	64	4	is	be	AUX
ajst-30190	64	5	as	as	SCONJ
ajst-30190	64	6	follows	follow	VERB
ajst-30190	64	7	:	:	PUNCT
ajst-30190	64	8	𝑊	𝑊	VERB
ajst-30190	64	9	𝐸	𝐸	PROPN
ajst-30190	64	10	𝑥𝑔	𝑥𝑔	NOUN
ajst-30190	64	11	𝑊	𝑊	PROPN
ajst-30190	64	12	𝐸	𝐸	PROPN
ajst-30190	64	13	𝑔	𝑔	PROPN
ajst-30190	64	14	𝑊	𝑊	VERB
ajst-30190	64	15	𝑥	𝑥	NOUN
ajst-30190	64	16	𝑊	𝑊	PROPN
ajst-30190	64	17	𝑔	𝑔	PROPN
ajst-30190	64	18	𝑢	𝑢	X
ajst-30190	64	19	𝑢𝑒	𝑢𝑒	PROPN
ajst-30190	64	20	⁄	⁄	ADJ
ajst-30190	64	21	figure	figure	NOUN
ajst-30190	64	22	2.3	2.3	NUM
ajst-30190	64	23	comparison	comparison	NOUN
ajst-30190	64	24	of	of	ADP
ajst-30190	64	25	eeg	eeg	NOUN
ajst-30190	64	26	signals	signal	NOUN
ajst-30190	64	27	before	before	ADV
ajst-30190	64	28	and	and	CCONJ
ajst-30190	64	29	after	after	ADP
ajst-30190	64	30	filtering	filter	VERB
ajst-30190	64	31	and	and	CCONJ
ajst-30190	64	32	artifact	artifact	ADJ
ajst-30190	64	33	removal	removal	NOUN
ajst-30190	64	34	3	3	NUM
ajst-30190	64	35	.	.	PUNCT
ajst-30190	64	36	characteristic	characteristic	ADJ
ajst-30190	64	37	extraction	extraction	NOUN
ajst-30190	64	38	(	(	PUNCT
ajst-30190	64	39	1	1	NUM
ajst-30190	64	40	)	)	PUNCT
ajst-30190	64	41	time	time	NOUN
ajst-30190	64	42	-	-	PUNCT
ajst-30190	64	43	domain	domain	NOUN
ajst-30190	64	44	characterization	characterization	NOUN
ajst-30190	64	45	hjorth	hjorth	NOUN
ajst-30190	64	46	parameters	parameter	NOUN
ajst-30190	64	47	are	be	AUX
ajst-30190	64	48	a	a	DET
ajst-30190	64	49	set	set	NOUN
ajst-30190	64	50	of	of	ADP
ajst-30190	64	51	time	time	NOUN
ajst-30190	64	52	-	-	PUNCT
ajst-30190	64	53	domain	domain	NOUN
ajst-30190	64	54	parameters	parameter	NOUN
ajst-30190	64	55	used	use	VERB
ajst-30190	64	56	to	to	PART
ajst-30190	64	57	characterize	characterize	VERB
ajst-30190	64	58	signals	signal	NOUN
ajst-30190	64	59	and	and	CCONJ
ajst-30190	64	60	have	have	VERB
ajst-30190	64	61	important	important	ADJ
ajst-30190	64	62	applications	application	NOUN
ajst-30190	64	63	in	in	ADP
ajst-30190	64	64	analyzing	analyze	VERB
ajst-30190	64	65	the	the	DET
ajst-30190	64	66	correlation	correlation	NOUN
ajst-30190	64	67	between	between	ADP
ajst-30190	64	68	eeg	eeg	NOUN
ajst-30190	64	69	signals	signal	NOUN
ajst-30190	64	70	and	and	CCONJ
ajst-30190	64	71	states	state	NOUN
ajst-30190	64	72	such	such	ADJ
ajst-30190	64	73	as	as	ADP
ajst-30190	64	74	fatigue	fatigue	NOUN
ajst-30190	64	75	.	.	PUNCT
ajst-30190	65	1	it	it	PRON
ajst-30190	65	2	mainly	mainly	ADV
ajst-30190	65	3	consists	consist	VERB
ajst-30190	65	4	of	of	ADP
ajst-30190	65	5	three	three	NUM
ajst-30190	65	6	parameters	parameter	NOUN
ajst-30190	65	7	:	:	PUNCT
ajst-30190	65	8	hjorth	hjorth	NOUN
ajst-30190	65	9	activity	activity	NOUN
ajst-30190	65	10	(	(	PUNCT
ajst-30190	65	11	ha	ha	INTJ
ajst-30190	65	12	)	)	PUNCT
ajst-30190	65	13	,	,	PUNCT
ajst-30190	65	14	hjorth	hjorth	NOUN
ajst-30190	65	15	mobility	mobility	NOUN
ajst-30190	65	16	(	(	PUNCT
ajst-30190	65	17	hm	hm	INTJ
ajst-30190	65	18	)	)	PUNCT
ajst-30190	65	19	and	and	CCONJ
ajst-30190	65	20	hjorth	hjorth	NOUN
ajst-30190	65	21	complexity	complexity	NOUN
ajst-30190	65	22	(	(	PUNCT
ajst-30190	65	23	hc	hc	NOUN
ajst-30190	65	24	)	)	PUNCT
ajst-30190	66	1	[	[	X
ajst-30190	66	2	16	16	NUM
ajst-30190	66	3	]	]	PUNCT
ajst-30190	66	4	.	.	PUNCT
ajst-30190	67	1	hjorth	hjorth	NOUN
ajst-30190	67	2	activity	activity	NOUN
ajst-30190	67	3	is	be	AUX
ajst-30190	67	4	used	use	VERB
ajst-30190	67	5	to	to	PART
ajst-30190	67	6	measure	measure	VERB
ajst-30190	67	7	the	the	DET
ajst-30190	67	8	intensity	intensity	NOUN
ajst-30190	67	9	or	or	CCONJ
ajst-30190	67	10	energy	energy	NOUN
ajst-30190	67	11	level	level	NOUN
ajst-30190	67	12	of	of	ADP
ajst-30190	67	13	a	a	DET
ajst-30190	67	14	signal	signal	NOUN
ajst-30190	67	15	.	.	PUNCT
ajst-30190	68	1	the	the	DET
ajst-30190	68	2	hjorth	hjorth	NOUN
ajst-30190	68	3	mobility	mobility	NOUN
ajst-30190	68	4	characterizes	characterize	VERB
ajst-30190	68	5	the	the	DET
ajst-30190	68	6	major	major	ADJ
ajst-30190	68	7	frequency	frequency	NOUN
ajst-30190	68	8	components	component	NOUN
ajst-30190	68	9	of	of	ADP
ajst-30190	68	10	the	the	DET
ajst-30190	68	11	signal	signal	NOUN
ajst-30190	68	12	.	.	PUNCT
ajst-30190	69	1	the	the	DET
ajst-30190	69	2	hjorth	hjorth	NOUN
ajst-30190	69	3	complexity	complexity	NOUN
ajst-30190	69	4	reflects	reflect	VERB
ajst-30190	69	5	the	the	DET
ajst-30190	69	6	rate	rate	NOUN
ajst-30190	69	7	of	of	ADP
ajst-30190	69	8	change	change	NOUN
ajst-30190	69	9	in	in	ADP
ajst-30190	69	10	the	the	DET
ajst-30190	69	11	frequency	frequency	NOUN
ajst-30190	69	12	of	of	ADP
ajst-30190	69	13	the	the	DET
ajst-30190	69	14	signal	signal	NOUN
ajst-30190	69	15	.	.	PUNCT
ajst-30190	70	1	therefore	therefore	ADV
ajst-30190	70	2	,	,	PUNCT
ajst-30190	70	3	the	the	DET
ajst-30190	70	4	hjorth	hjorth	NOUN
ajst-30190	70	5	parameter	parameter	NOUN
ajst-30190	70	6	can	can	AUX
ajst-30190	70	7	be	be	AUX
ajst-30190	70	8	well	well	ADV
ajst-30190	70	9	used	use	VERB
ajst-30190	70	10	to	to	PART
ajst-30190	70	11	analyze	analyze	VERB
ajst-30190	70	12	the	the	DET
ajst-30190	70	13	time	time	NOUN
ajst-30190	70	14	-	-	PUNCT
ajst-30190	70	15	domain	domain	NOUN
ajst-30190	70	16	characteristics	characteristic	NOUN
ajst-30190	70	17	of	of	ADP
ajst-30190	70	18	eeg	eeg	PROPN
ajst-30190	70	19	signals[17	signals[17	X
ajst-30190	70	20	]	]	PUNCT
ajst-30190	70	21	.	.	PUNCT
ajst-30190	71	1	(	(	PUNCT
ajst-30190	71	2	2	2	NUM
ajst-30190	71	3	)	)	PUNCT
ajst-30190	71	4	frequency	frequency	NOUN
ajst-30190	71	5	-	-	PUNCT
ajst-30190	71	6	domain	domain	NOUN
ajst-30190	71	7	characterization	characterization	NOUN
ajst-30190	71	8	frequency	frequency	NOUN
ajst-30190	71	9	domain	domain	NOUN
ajst-30190	71	10	characteristics	characteristic	NOUN
ajst-30190	71	11	mainly	mainly	ADV
ajst-30190	71	12	analyze	analyze	VERB
ajst-30190	71	13	the	the	DET
ajst-30190	71	14	information	information	NOUN
ajst-30190	71	15	of	of	ADP
ajst-30190	71	16	frequency	frequency	NOUN
ajst-30190	71	17	characteristics	characteristic	NOUN
ajst-30190	71	18	from	from	ADP
ajst-30190	71	19	the	the	DET
ajst-30190	71	20	perspective	perspective	NOUN
ajst-30190	71	21	of	of	ADP
ajst-30190	71	22	frequency	frequency	NOUN
ajst-30190	71	23	domain	domain	NOUN
ajst-30190	71	24	.	.	PUNCT
ajst-30190	72	1	power	power	NOUN
ajst-30190	72	2	spectral	spectral	ADJ
ajst-30190	72	3	density	density	NOUN
ajst-30190	72	4	is	be	AUX
ajst-30190	72	5	used	use	VERB
ajst-30190	72	6	to	to	PART
ajst-30190	72	7	characterize	characterize	VERB
ajst-30190	72	8	the	the	DET
ajst-30190	72	9	distribution	distribution	NOUN
ajst-30190	72	10	characteristics	characteristic	NOUN
ajst-30190	72	11	of	of	ADP
ajst-30190	72	12	signal	signal	ADJ
ajst-30190	72	13	power	power	NOUN
ajst-30190	72	14	,	,	PUNCT
ajst-30190	72	15	which	which	PRON
ajst-30190	72	16	can	can	AUX
ajst-30190	72	17	visualize	visualize	VERB
ajst-30190	72	18	the	the	DET
ajst-30190	72	19	change	change	NOUN
ajst-30190	72	20	in	in	ADP
ajst-30190	72	21	signal	signal	ADJ
ajst-30190	72	22	power	power	NOUN
ajst-30190	72	23	with	with	ADP
ajst-30190	72	24	frequency	frequency	NOUN
ajst-30190	72	25	.	.	PUNCT
ajst-30190	73	1	therefore	therefore	ADV
ajst-30190	73	2	,	,	PUNCT
ajst-30190	73	3	in	in	ADP
ajst-30190	73	4	this	this	DET
ajst-30190	73	5	paper	paper	NOUN
ajst-30190	73	6	,	,	PUNCT
ajst-30190	73	7	the	the	DET
ajst-30190	73	8	welch	welch	NOUN
ajst-30190	73	9	method	method	NOUN
ajst-30190	73	10	is	be	AUX
ajst-30190	73	11	used	use	VERB
ajst-30190	73	12	to	to	PART
ajst-30190	73	13	obtain	obtain	VERB
ajst-30190	73	14	the	the	DET
ajst-30190	73	15	power	power	NOUN
ajst-30190	73	16	spectral	spectral	ADJ
ajst-30190	73	17	density	density	NOUN
ajst-30190	73	18	,	,	PUNCT
ajst-30190	73	19	and	and	CCONJ
ajst-30190	73	20	the	the	DET
ajst-30190	73	21	power	power	NOUN
ajst-30190	73	22	spectral	spectral	ADJ
ajst-30190	73	23	density	density	NOUN
ajst-30190	73	24	of	of	ADP
ajst-30190	73	25	the	the	DET
ajst-30190	73	26	original	original	ADJ
ajst-30190	73	27	eeg	eeg	NOUN
ajst-30190	73	28	signal	signal	NOUN
ajst-30190	73	29	and	and	CCONJ
ajst-30190	73	30	each	each	DET
ajst-30190	73	31	rhythm	rhythm	PROPN
ajst-30190	73	32	wave	wave	NOUN
ajst-30190	73	33	is	be	AUX
ajst-30190	73	34	calculated	calculate	VERB
ajst-30190	73	35	separately	separately	ADV
ajst-30190	73	36	,	,	PUNCT
ajst-30190	73	37	and	and	CCONJ
ajst-30190	73	38	then	then	ADV
ajst-30190	73	39	the	the	DET
ajst-30190	73	40	power	power	NOUN
ajst-30190	73	41	spectral	spectral	ADJ
ajst-30190	73	42	density	density	NOUN
ajst-30190	73	43	of	of	ADP
ajst-30190	73	44	different	different	ADJ
ajst-30190	73	45	frequency	frequency	NOUN
ajst-30190	73	46	bands	band	NOUN
ajst-30190	73	47	is	be	AUX
ajst-30190	73	48	superimposed	superimpose	VERB
ajst-30190	73	49	and	and	CCONJ
ajst-30190	73	50	integrated	integrate	VERB
ajst-30190	73	51	as	as	ADP
ajst-30190	73	52	the	the	DET
ajst-30190	73	53	final	final	ADJ
ajst-30190	73	54	extracted	extract	VERB
ajst-30190	73	55	feature	feature	NOUN
ajst-30190	73	56	.	.	PUNCT
ajst-30190	74	1	[	[	X
ajst-30190	74	2	18	18	NUM
ajst-30190	74	3	]	]	PUNCT
ajst-30190	74	4	.	.	PUNCT
ajst-30190	75	1	based	base	VERB
ajst-30190	75	2	on	on	ADP
ajst-30190	75	3	the	the	DET
ajst-30190	75	4	acquired	acquire	VERB
ajst-30190	75	5	eeg	eeg	NOUN
ajst-30190	75	6	,	,	PUNCT
ajst-30190	75	7	the	the	DET
ajst-30190	75	8	frequency	frequency	NOUN
ajst-30190	75	9	domain	domain	NOUN
ajst-30190	75	10	power	power	NOUN
ajst-30190	75	11	spectral	spectral	ADJ
ajst-30190	75	12	density	density	NOUN
ajst-30190	75	13	waveforms	waveform	NOUN
ajst-30190	75	14	of	of	ADP
ajst-30190	75	15	some	some	DET
ajst-30190	75	16	brain	brain	NOUN
ajst-30190	75	17	regions	region	NOUN
ajst-30190	75	18	were	be	AUX
ajst-30190	75	19	intercepted	intercept	VERB
ajst-30190	75	20	as	as	SCONJ
ajst-30190	75	21	shown	show	VERB
ajst-30190	75	22	in	in	ADP
ajst-30190	75	23	figure	figure	NOUN
ajst-30190	75	24	3.1	3.1	NUM
ajst-30190	75	25	below	below	ADV
ajst-30190	75	26	.	.	PUNCT
ajst-30190	76	1	figure	figure	VERB
ajst-30190	76	2	3.1	3.1	NUM
ajst-30190	76	3	waveforms	waveform	NOUN
ajst-30190	76	4	for	for	ADP
ajst-30190	76	5	extracting	extract	VERB
ajst-30190	76	6	the	the	DET
ajst-30190	76	7	power	power	NOUN
ajst-30190	76	8	spectral	spectral	ADJ
ajst-30190	76	9	density	density	NOUN
ajst-30190	76	10	of	of	ADP
ajst-30190	76	11	the	the	DET
ajst-30190	76	12	eeg	eeg	PROPN
ajst-30190	76	13	signal	signal	NOUN
ajst-30190	76	14	the	the	DET
ajst-30190	76	15	energy	energy	NOUN
ajst-30190	76	16	spectrum	spectrum	NOUN
ajst-30190	76	17	is	be	AUX
ajst-30190	76	18	a	a	DET
ajst-30190	76	19	function	function	NOUN
ajst-30190	76	20	used	use	VERB
ajst-30190	76	21	to	to	PART
ajst-30190	76	22	describe	describe	VERB
ajst-30190	76	23	the	the	DET
ajst-30190	76	24	distribution	distribution	NOUN
ajst-30190	76	25	of	of	ADP
ajst-30190	76	26	signal	signal	ADJ
ajst-30190	76	27	energy	energy	NOUN
ajst-30190	76	28	in	in	ADP
ajst-30190	76	29	the	the	DET
ajst-30190	76	30	frequency	frequency	NOUN
ajst-30190	76	31	domain	domain	NOUN
ajst-30190	76	32	.	.	PUNCT
ajst-30190	77	1	it	it	PRON
ajst-30190	77	2	represents	represent	VERB
ajst-30190	77	3	the	the	DET
ajst-30190	77	4	variation	variation	NOUN
ajst-30190	77	5	of	of	ADP
ajst-30190	77	6	the	the	DET
ajst-30190	77	7	signal	signal	ADJ
ajst-30190	77	8	energy	energy	NOUN
ajst-30190	77	9	with	with	ADP
ajst-30190	77	10	frequency	frequency	NOUN
ajst-30190	77	11	and	and	CCONJ
ajst-30190	77	12	visualizes	visualize	VERB
ajst-30190	77	13	the	the	DET
ajst-30190	77	14	amount	amount	NOUN
ajst-30190	77	15	of	of	ADP
ajst-30190	77	16	energy	energy	NOUN
ajst-30190	77	17	contained	contain	VERB
ajst-30190	77	18	in	in	ADP
ajst-30190	77	19	different	different	ADJ
ajst-30190	77	20	frequency	frequency	NOUN
ajst-30190	77	21	components	component	NOUN
ajst-30190	77	22	of	of	ADP
ajst-30190	77	23	the	the	DET
ajst-30190	77	24	signal	signal	NOUN
ajst-30190	77	25	.	.	PUNCT
ajst-30190	78	1	the	the	DET
ajst-30190	78	2	energy	energy	NOUN
ajst-30190	78	3	spectrum	spectrum	NOUN
ajst-30190	78	4	provides	provide	VERB
ajst-30190	78	5	a	a	DET
ajst-30190	78	6	clear	clear	ADJ
ajst-30190	78	7	picture	picture	NOUN
ajst-30190	78	8	of	of	ADP
ajst-30190	78	9	how	how	SCONJ
ajst-30190	78	10	much	much	ADJ
ajst-30190	78	11	each	each	DET
ajst-30190	78	12	frequency	frequency	NOUN
ajst-30190	78	13	component	component	NOUN
ajst-30190	78	14	of	of	ADP
ajst-30190	78	15	the	the	DET
ajst-30190	78	16	signal	signal	NOUN
ajst-30190	78	17	contributes	contribute	VERB
ajst-30190	78	18	to	to	ADP
ajst-30190	78	19	the	the	DET
ajst-30190	78	20	total	total	ADJ
ajst-30190	78	21	energy	energy	NOUN
ajst-30190	78	22	.	.	PUNCT
ajst-30190	79	1	figure	figure	NOUN
ajst-30190	79	2	3.2	3.2	NUM
ajst-30190	79	3	shows	show	VERB
ajst-30190	79	4	the	the	DET
ajst-30190	79	5	distribution	distribution	NOUN
ajst-30190	79	6	of	of	ADP
ajst-30190	79	7	the	the	DET
ajst-30190	79	8	eeg	eeg	PROPN
ajst-30190	79	9	energy	energy	NOUN
ajst-30190	79	10	spectrum	spectrum	NOUN
ajst-30190	79	11	.	.	PUNCT
ajst-30190	80	1	144	144	NUM
ajst-30190	80	2	figure	figure	NOUN
ajst-30190	80	3	3.2	3.2	NUM
ajst-30190	80	4	schematic	schematic	ADJ
ajst-30190	80	5	of	of	ADP
ajst-30190	80	6	the	the	DET
ajst-30190	80	7	energy	energy	NOUN
ajst-30190	80	8	spectrum	spectrum	NOUN
ajst-30190	80	9	distribution	distribution	NOUN
ajst-30190	80	10	of	of	ADP
ajst-30190	80	11	the	the	DET
ajst-30190	80	12	eeg	eeg	NOUN
ajst-30190	80	13	signal	signal	NOUN
ajst-30190	80	14	.	.	PUNCT
ajst-30190	81	1	(	(	PUNCT
ajst-30190	81	2	3	3	X
ajst-30190	81	3	)	)	PUNCT
ajst-30190	81	4	time	time	NOUN
ajst-30190	81	5	-	-	PUNCT
ajst-30190	81	6	frequency	frequency	NOUN
ajst-30190	81	7	domain	domain	NOUN
ajst-30190	81	8	characterization	characterization	NOUN
ajst-30190	81	9	time	time	NOUN
ajst-30190	81	10	-	-	PUNCT
ajst-30190	81	11	frequency	frequency	NOUN
ajst-30190	81	12	analysis	analysis	NOUN
ajst-30190	81	13	can	can	AUX
ajst-30190	81	14	effectively	effectively	ADV
ajst-30190	81	15	integrate	integrate	VERB
ajst-30190	81	16	the	the	DET
ajst-30190	81	17	feature	feature	NOUN
ajst-30190	81	18	information	information	NOUN
ajst-30190	81	19	in	in	ADP
ajst-30190	81	20	the	the	DET
ajst-30190	81	21	time	time	NOUN
ajst-30190	81	22	and	and	CCONJ
ajst-30190	81	23	frequency	frequency	NOUN
ajst-30190	81	24	domains	domain	NOUN
ajst-30190	81	25	to	to	PART
ajst-30190	81	26	more	more	ADV
ajst-30190	81	27	comprehensively	comprehensively	ADV
ajst-30190	81	28	analyze	analyze	VERB
ajst-30190	81	29	the	the	DET
ajst-30190	81	30	characteristics	characteristic	NOUN
ajst-30190	81	31	of	of	ADP
ajst-30190	81	32	the	the	DET
ajst-30190	81	33	signal	signal	NOUN
ajst-30190	81	34	.	.	PUNCT
ajst-30190	82	1	wavelet	wavelet	NOUN
ajst-30190	82	2	packet	packet	NOUN
ajst-30190	82	3	transform	transform	NOUN
ajst-30190	82	4	is	be	AUX
ajst-30190	82	5	a	a	DET
ajst-30190	82	6	commonly	commonly	ADV
ajst-30190	82	7	used	use	VERB
ajst-30190	82	8	method	method	NOUN
ajst-30190	82	9	for	for	ADP
ajst-30190	82	10	eeg	eeg	PROPN
ajst-30190	82	11	time	time	NOUN
ajst-30190	82	12	-	-	PUNCT
ajst-30190	82	13	frequency	frequency	NOUN
ajst-30190	82	14	analysis	analysis	NOUN
ajst-30190	82	15	,	,	PUNCT
ajst-30190	82	16	and	and	CCONJ
ajst-30190	82	17	its	its	PRON
ajst-30190	82	18	advantage	advantage	NOUN
ajst-30190	82	19	is	be	AUX
ajst-30190	82	20	the	the	DET
ajst-30190	82	21	deep	deep	ADJ
ajst-30190	82	22	decomposition	decomposition	NOUN
ajst-30190	82	23	of	of	ADP
ajst-30190	82	24	low	low	ADJ
ajst-30190	82	25	-	-	PUNCT
ajst-30190	82	26	frequency	frequency	NOUN
ajst-30190	82	27	sub	sub	NOUN
ajst-30190	82	28	-	-	NOUN
ajst-30190	82	29	band	band	NOUN
ajst-30190	82	30	,	,	PUNCT
ajst-30190	82	31	which	which	PRON
ajst-30190	82	32	makes	make	VERB
ajst-30190	82	33	up	up	ADP
ajst-30190	82	34	for	for	ADP
ajst-30190	82	35	the	the	DET
ajst-30190	82	36	lack	lack	NOUN
ajst-30190	82	37	of	of	ADP
ajst-30190	82	38	high	high	ADJ
ajst-30190	82	39	-	-	PUNCT
ajst-30190	82	40	frequency	frequency	NOUN
ajst-30190	82	41	sub	sub	ADJ
ajst-30190	82	42	-	-	ADJ
ajst-30190	82	43	band	band	ADJ
ajst-30190	82	44	decomposition	decomposition	NOUN
ajst-30190	82	45	.	.	PUNCT
ajst-30190	83	1	when	when	SCONJ
ajst-30190	83	2	using	use	VERB
ajst-30190	83	3	wavelet	wavelet	NOUN
ajst-30190	83	4	packet	packet	NOUN
ajst-30190	83	5	transform	transform	NOUN
ajst-30190	83	6	to	to	PART
ajst-30190	83	7	process	process	VERB
ajst-30190	83	8	the	the	DET
ajst-30190	83	9	signal	signal	NOUN
ajst-30190	83	10	,	,	PUNCT
ajst-30190	83	11	the	the	DET
ajst-30190	83	12	signal	signal	NOUN
ajst-30190	83	13	will	will	AUX
ajst-30190	83	14	generate	generate	VERB
ajst-30190	83	15	a	a	DET
ajst-30190	83	16	series	series	NOUN
ajst-30190	83	17	of	of	ADP
ajst-30190	83	18	wavelet	wavelet	NOUN
ajst-30190	83	19	packet	packet	NOUN
ajst-30190	83	20	coefficients	coefficient	NOUN
ajst-30190	83	21	according	accord	VERB
ajst-30190	83	22	to	to	ADP
ajst-30190	83	23	different	different	ADJ
ajst-30190	83	24	scales	scale	NOUN
ajst-30190	83	25	and	and	CCONJ
ajst-30190	83	26	frequencies	frequency	NOUN
ajst-30190	83	27	,	,	PUNCT
ajst-30190	83	28	which	which	PRON
ajst-30190	83	29	can	can	AUX
ajst-30190	83	30	accurately	accurately	ADV
ajst-30190	83	31	reflect	reflect	VERB
ajst-30190	83	32	the	the	DET
ajst-30190	83	33	composition	composition	NOUN
ajst-30190	83	34	of	of	ADP
ajst-30190	83	35	the	the	DET
ajst-30190	83	36	signal	signal	NOUN
ajst-30190	83	37	in	in	ADP
ajst-30190	83	38	different	different	ADJ
ajst-30190	83	39	frequency	frequency	NOUN
ajst-30190	83	40	bands[19	bands[19	NOUN
ajst-30190	83	41	]	]	PUNCT
ajst-30190	83	42	.	.	PUNCT
ajst-30190	84	1	figure	figure	VERB
ajst-30190	84	2	3.3	3.3	NUM
ajst-30190	84	3	below	below	ADV
ajst-30190	84	4	shows	show	VERB
ajst-30190	84	5	the	the	DET
ajst-30190	84	6	wavelet	wavelet	NOUN
ajst-30190	84	7	packet	packet	NOUN
ajst-30190	84	8	reconstructed	reconstruct	VERB
ajst-30190	84	9	eeg	eeg	NOUN
ajst-30190	84	10	signal	signal	NOUN
ajst-30190	84	11	in	in	ADP
ajst-30190	84	12	the	the	DET
ajst-30190	84	13	corresponding	corresponding	ADJ
ajst-30190	84	14	frequency	frequency	NOUN
ajst-30190	84	15	band	band	NOUN
ajst-30190	84	16	.	.	PUNCT
ajst-30190	85	1	figure	figure	VERB
ajst-30190	85	2	3.3	3.3	NUM
ajst-30190	85	3	schematic	schematic	ADJ
ajst-30190	85	4	of	of	ADP
ajst-30190	85	5	wavelet	wavelet	NOUN
ajst-30190	85	6	packet	packet	NOUN
ajst-30190	85	7	reconstruction	reconstruction	NOUN
ajst-30190	85	8	of	of	ADP
ajst-30190	85	9	δ	δ	PROPN
ajst-30190	85	10	,	,	PUNCT
ajst-30190	85	11	θ	θ	PROPN
ajst-30190	85	12	,	,	PUNCT
ajst-30190	85	13	α	α	PROPN
ajst-30190	85	14	and	and	CCONJ
ajst-30190	85	15	β	β	X
ajst-30190	85	16	waves	wave	NOUN
ajst-30190	85	17	145	145	NUM
ajst-30190	85	18	(	(	PUNCT
ajst-30190	85	19	4	4	NUM
ajst-30190	85	20	)	)	PUNCT
ajst-30190	85	21	nonlinear	nonlinear	ADJ
ajst-30190	85	22	characterization	characterization	NOUN
ajst-30190	85	23	eeg	eeg	NOUN
ajst-30190	85	24	signals	signal	NOUN
ajst-30190	85	25	are	be	AUX
ajst-30190	85	26	chaotic	chaotic	ADJ
ajst-30190	85	27	and	and	CCONJ
ajst-30190	85	28	nonlinear	nonlinear	ADJ
ajst-30190	85	29	,	,	PUNCT
ajst-30190	85	30	and	and	CCONJ
ajst-30190	85	31	nonlinear	nonlinear	ADJ
ajst-30190	85	32	dynamics	dynamic	NOUN
ajst-30190	85	33	analysis	analysis	NOUN
ajst-30190	85	34	has	have	AUX
ajst-30190	85	35	become	become	VERB
ajst-30190	85	36	a	a	DET
ajst-30190	85	37	common	common	ADJ
ajst-30190	85	38	and	and	CCONJ
ajst-30190	85	39	popular	popular	ADJ
ajst-30190	85	40	method	method	NOUN
ajst-30190	85	41	to	to	PART
ajst-30190	85	42	study	study	VERB
ajst-30190	85	43	eeg	eeg	NOUN
ajst-30190	85	44	signals	signal	NOUN
ajst-30190	85	45	.	.	PUNCT
ajst-30190	86	1	commonly	commonly	ADV
ajst-30190	86	2	used	use	VERB
ajst-30190	86	3	nonlinear	nonlinear	ADJ
ajst-30190	86	4	dynamics	dynamic	NOUN
ajst-30190	86	5	methods	method	NOUN
ajst-30190	86	6	include	include	VERB
ajst-30190	86	7	correlation	correlation	NOUN
ajst-30190	86	8	dimension	dimension	NOUN
ajst-30190	86	9	,	,	PUNCT
ajst-30190	86	10	lyapunov	lyapunov	NOUN
ajst-30190	86	11	exponent	exponent	NOUN
ajst-30190	86	12	,	,	PUNCT
ajst-30190	86	13	entropy	entropy	VERB
ajst-30190	86	14	analysis	analysis	NOUN
ajst-30190	86	15	and	and	CCONJ
ajst-30190	86	16	complexity	complexity	NOUN
ajst-30190	86	17	analysis	analysis	NOUN
ajst-30190	86	18	.	.	PUNCT
ajst-30190	87	1	in	in	ADP
ajst-30190	87	2	this	this	DET
ajst-30190	87	3	paper	paper	NOUN
ajst-30190	87	4	,	,	PUNCT
ajst-30190	87	5	approximate	approximate	ADJ
ajst-30190	87	6	entropy	entropy	PROPN
ajst-30190	87	7	,	,	PUNCT
ajst-30190	87	8	sample	sample	NOUN
ajst-30190	87	9	entropy	entropy	NOUN
ajst-30190	88	1	[	[	X
ajst-30190	88	2	20	20	NUM
ajst-30190	88	3	,	,	PUNCT
ajst-30190	88	4	21	21	NUM
ajst-30190	88	5	]	]	PUNCT
ajst-30190	88	6	,	,	PUNCT
ajst-30190	88	7	fuzzy	fuzzy	ADJ
ajst-30190	88	8	entropy	entropy	NOUN
ajst-30190	89	1	[	[	X
ajst-30190	89	2	22	22	NUM
ajst-30190	89	3	,	,	PUNCT
ajst-30190	89	4	23	23	NUM
ajst-30190	89	5	]	]	PUNCT
ajst-30190	89	6	and	and	CCONJ
ajst-30190	89	7	wavelet	wavelet	NOUN
ajst-30190	89	8	entropy	entropy	PROPN
ajst-30190	89	9	[	[	X
ajst-30190	89	10	24	24	NUM
ajst-30190	89	11	]	]	PUNCT
ajst-30190	89	12	are	be	AUX
ajst-30190	89	13	chosen	choose	VERB
ajst-30190	89	14	for	for	ADP
ajst-30190	89	15	characterization	characterization	NOUN
ajst-30190	89	16	.	.	PUNCT
ajst-30190	90	1	4	4	X
ajst-30190	90	2	.	.	X
ajst-30190	90	3	c	c	X
ajst-30190	90	4	-	-	PUNCT
ajst-30190	90	5	rbm	rbm	NOUN
ajst-30190	90	6	modeling	modeling	NOUN
ajst-30190	90	7	and	and	CCONJ
ajst-30190	90	8	general	general	ADJ
ajst-30190	90	9	framework	framework	NOUN
ajst-30190	90	10	for	for	ADP
ajst-30190	90	11	fatigue	fatigue	NOUN
ajst-30190	90	12	detection	detection	NOUN
ajst-30190	90	13	(	(	PUNCT
ajst-30190	90	14	1	1	X
ajst-30190	90	15	)	)	PUNCT
ajst-30190	90	16	general	general	ADJ
ajst-30190	90	17	framework	framework	NOUN
ajst-30190	90	18	of	of	ADP
ajst-30190	90	19	c	c	PROPN
ajst-30190	90	20	-	-	PUNCT
ajst-30190	90	21	rbm	rbm	NOUN
ajst-30190	90	22	modeling	modeling	NOUN
ajst-30190	90	23	the	the	DET
ajst-30190	90	24	constrained	constrained	ADJ
ajst-30190	90	25	boltzmann	boltzmann	PROPN
ajst-30190	90	26	machine	machine	NOUN
ajst-30190	90	27	is	be	AUX
ajst-30190	90	28	a	a	DET
ajst-30190	90	29	generative	generative	ADJ
ajst-30190	90	30	stochastic	stochastic	ADJ
ajst-30190	90	31	neural	neural	ADJ
ajst-30190	90	32	network	network	NOUN
ajst-30190	90	33	based	base	VERB
ajst-30190	90	34	on	on	ADP
ajst-30190	90	35	energy	energy	NOUN
ajst-30190	90	36	functions	function	NOUN
ajst-30190	90	37	,	,	PUNCT
ajst-30190	90	38	consisting	consist	VERB
ajst-30190	90	39	of	of	ADP
ajst-30190	90	40	visible	visible	ADJ
ajst-30190	90	41	and	and	CCONJ
ajst-30190	90	42	hidden	hidden	ADJ
ajst-30190	90	43	layers	layer	NOUN
ajst-30190	90	44	with	with	ADP
ajst-30190	90	45	unconnected	unconnected	ADJ
ajst-30190	90	46	nodes	node	NOUN
ajst-30190	90	47	within	within	ADP
ajst-30190	90	48	the	the	DET
ajst-30190	90	49	layers	layer	NOUN
ajst-30190	90	50	and	and	CCONJ
ajst-30190	90	51	fully	fully	ADV
ajst-30190	90	52	connected	connect	VERB
ajst-30190	90	53	nodes	node	NOUN
ajst-30190	90	54	between	between	ADP
ajst-30190	90	55	the	the	DET
ajst-30190	90	56	layers[25	layers[25	NOUN
ajst-30190	90	57	]	]	PUNCT
ajst-30190	90	58	.	.	PUNCT
ajst-30190	91	1	however	however	ADV
ajst-30190	91	2	,	,	PUNCT
ajst-30190	91	3	in	in	ADP
ajst-30190	91	4	the	the	DET
ajst-30190	91	5	face	face	NOUN
ajst-30190	91	6	of	of	ADP
ajst-30190	91	7	diverse	diverse	ADJ
ajst-30190	91	8	application	application	NOUN
ajst-30190	91	9	scenarios	scenario	NOUN
ajst-30190	91	10	,	,	PUNCT
ajst-30190	91	11	it	it	PRON
ajst-30190	91	12	is	be	AUX
ajst-30190	91	13	necessary	necessary	ADJ
ajst-30190	91	14	to	to	PART
ajst-30190	91	15	improve	improve	VERB
ajst-30190	91	16	and	and	CCONJ
ajst-30190	91	17	extend	extend	VERB
ajst-30190	91	18	it	it	PRON
ajst-30190	91	19	to	to	PART
ajst-30190	91	20	adapt	adapt	VERB
ajst-30190	91	21	to	to	ADP
ajst-30190	91	22	different	different	ADJ
ajst-30190	91	23	task	task	NOUN
ajst-30190	91	24	requirements	requirement	NOUN
ajst-30190	91	25	thus	thus	ADV
ajst-30190	91	26	optimizing	optimize	VERB
ajst-30190	91	27	the	the	DET
ajst-30190	91	28	model	model	NOUN
ajst-30190	91	29	performance	performance	NOUN
ajst-30190	91	30	.	.	PUNCT
ajst-30190	92	1	therefore	therefore	ADV
ajst-30190	92	2	,	,	PUNCT
ajst-30190	92	3	in	in	ADP
ajst-30190	92	4	this	this	DET
ajst-30190	92	5	paper	paper	NOUN
ajst-30190	92	6	,	,	PUNCT
ajst-30190	92	7	the	the	DET
ajst-30190	92	8	convolution	convolution	NOUN
ajst-30190	92	9	operation	operation	NOUN
ajst-30190	92	10	is	be	AUX
ajst-30190	92	11	innovatively	innovatively	ADV
ajst-30190	92	12	introduced	introduce	VERB
ajst-30190	92	13	into	into	ADP
ajst-30190	92	14	the	the	DET
ajst-30190	92	15	hidden	hide	VERB
ajst-30190	92	16	layer	layer	NOUN
ajst-30190	92	17	of	of	ADP
ajst-30190	92	18	the	the	DET
ajst-30190	92	19	restricted	restricted	ADJ
ajst-30190	92	20	boltzmann	boltzmann	PROPN
ajst-30190	92	21	machine	machine	NOUN
ajst-30190	92	22	,	,	PUNCT
ajst-30190	92	23	where	where	SCONJ
ajst-30190	92	24	each	each	DET
ajst-30190	92	25	hidden	hide	VERB
ajst-30190	92	26	unit	unit	NOUN
ajst-30190	92	27	is	be	AUX
ajst-30190	92	28	connected	connect	VERB
ajst-30190	92	29	to	to	ADP
ajst-30190	92	30	only	only	ADV
ajst-30190	92	31	one	one	NUM
ajst-30190	92	32	local	local	ADJ
ajst-30190	92	33	region	region	NOUN
ajst-30190	92	34	of	of	ADP
ajst-30190	92	35	the	the	DET
ajst-30190	92	36	visible	visible	ADJ
ajst-30190	92	37	layer	layer	NOUN
ajst-30190	92	38	to	to	PART
ajst-30190	92	39	realize	realize	VERB
ajst-30190	92	40	spatial	spatial	ADJ
ajst-30190	92	41	weight	weight	NOUN
ajst-30190	92	42	sharing	sharing	NOUN
ajst-30190	92	43	.	.	PUNCT
ajst-30190	93	1	this	this	PRON
ajst-30190	93	2	greatly	greatly	ADV
ajst-30190	93	3	reduces	reduce	VERB
ajst-30190	93	4	the	the	DET
ajst-30190	93	5	number	number	NOUN
ajst-30190	93	6	of	of	ADP
ajst-30190	93	7	parameters	parameter	NOUN
ajst-30190	93	8	in	in	ADP
ajst-30190	93	9	the	the	DET
ajst-30190	93	10	model	model	NOUN
ajst-30190	93	11	and	and	CCONJ
ajst-30190	93	12	the	the	DET
ajst-30190	93	13	computation	computation	NOUN
ajst-30190	93	14	becomes	become	VERB
ajst-30190	93	15	faster	fast	ADJ
ajst-30190	93	16	,	,	PUNCT
ajst-30190	93	17	thus	thus	ADV
ajst-30190	93	18	mining	mine	VERB
ajst-30190	93	19	potential	potential	ADJ
ajst-30190	93	20	local	local	ADJ
ajst-30190	93	21	features	feature	NOUN
ajst-30190	93	22	more	more	ADV
ajst-30190	93	23	accurately	accurately	ADV
ajst-30190	93	24	.	.	PUNCT
ajst-30190	94	1	figure	figure	VERB
ajst-30190	94	2	4.1	4.1	NUM
ajst-30190	94	3	shows	show	VERB
ajst-30190	94	4	a	a	DET
ajst-30190	94	5	flowchart	flowchart	NOUN
ajst-30190	94	6	of	of	ADP
ajst-30190	94	7	the	the	DET
ajst-30190	94	8	general	general	ADJ
ajst-30190	94	9	framework	framework	NOUN
ajst-30190	94	10	of	of	ADP
ajst-30190	94	11	the	the	DET
ajst-30190	94	12	convolutionally	convolutionally	ADV
ajst-30190	94	13	constrained	constrain	VERB
ajst-30190	94	14	boltzmann	boltzmann	PROPN
ajst-30190	94	15	machine	machine	NOUN
ajst-30190	94	16	model	model	NOUN
ajst-30190	94	17	and	and	CCONJ
ajst-30190	94	18	classifier	classifier	NOUN
ajst-30190	94	19	to	to	PART
ajst-30190	94	20	implement	implement	VERB
ajst-30190	94	21	fatigue	fatigue	NOUN
ajst-30190	94	22	prediction	prediction	NOUN
ajst-30190	94	23	.	.	PUNCT
ajst-30190	95	1	figure	figure	VERB
ajst-30190	95	2	4.1	4.1	NUM
ajst-30190	95	3	convolutionally	convolutionally	ADV
ajst-30190	95	4	constrained	constrain	VERB
ajst-30190	95	5	boltzmann	boltzmann	PROPN
ajst-30190	95	6	machine	machine	NOUN
ajst-30190	95	7	and	and	CCONJ
ajst-30190	95	8	classifier	classifier	PROPN
ajst-30190	95	9	model	model	PROPN
ajst-30190	95	10	flowchart	flowchart	PROPN
ajst-30190	95	11	(	(	PUNCT
ajst-30190	95	12	2	2	NUM
ajst-30190	95	13	)	)	PUNCT
ajst-30190	95	14	feature	feature	NOUN
ajst-30190	95	15	selection	selection	NOUN
ajst-30190	95	16	the	the	DET
ajst-30190	95	17	focus	focus	NOUN
ajst-30190	95	18	of	of	ADP
ajst-30190	95	19	this	this	DET
ajst-30190	95	20	chapter	chapter	NOUN
ajst-30190	95	21	is	be	AUX
ajst-30190	95	22	to	to	PART
ajst-30190	95	23	categorize	categorize	VERB
ajst-30190	95	24	the	the	DET
ajst-30190	95	25	fatigue	fatigue	NOUN
ajst-30190	95	26	eeg	eeg	NOUN
ajst-30190	95	27	signals	signal	NOUN
ajst-30190	95	28	from	from	ADP
ajst-30190	95	29	different	different	ADJ
ajst-30190	95	30	channels	channel	NOUN
ajst-30190	95	31	.	.	PUNCT
ajst-30190	96	1	in	in	ADP
ajst-30190	96	2	order	order	NOUN
ajst-30190	96	3	to	to	PART
ajst-30190	96	4	investigate	investigate	VERB
ajst-30190	96	5	whether	whether	SCONJ
ajst-30190	96	6	there	there	PRON
ajst-30190	96	7	is	be	VERB
ajst-30190	96	8	an	an	DET
ajst-30190	96	9	intrinsic	intrinsic	ADJ
ajst-30190	96	10	correlation	correlation	NOUN
ajst-30190	96	11	between	between	ADP
ajst-30190	96	12	individual	individual	ADJ
ajst-30190	96	13	channels	channel	NOUN
ajst-30190	96	14	and	and	CCONJ
ajst-30190	96	15	these	these	DET
ajst-30190	96	16	extracted	extract	VERB
ajst-30190	96	17	features	feature	NOUN
ajst-30190	96	18	,	,	PUNCT
ajst-30190	96	19	the	the	DET
ajst-30190	96	20	brain	brain	NOUN
ajst-30190	96	21	areas	area	NOUN
ajst-30190	96	22	where	where	SCONJ
ajst-30190	96	23	the	the	DET
ajst-30190	96	24	electrodes	electrode	NOUN
ajst-30190	96	25	are	be	AUX
ajst-30190	96	26	located	locate	VERB
ajst-30190	96	27	are	be	AUX
ajst-30190	96	28	divided	divide	VERB
ajst-30190	96	29	into	into	ADP
ajst-30190	96	30	several	several	ADJ
ajst-30190	96	31	regions	region	NOUN
ajst-30190	96	32	:	:	PUNCT
ajst-30190	96	33	the	the	DET
ajst-30190	96	34	brain	brain	NOUN
ajst-30190	96	35	areas	area	NOUN
ajst-30190	96	36	corresponding	correspond	VERB
ajst-30190	96	37	to	to	PART
ajst-30190	96	38	electrodes	electrode	VERB
ajst-30190	96	39	af3	af3	NOUN
ajst-30190	96	40	,	,	PUNCT
ajst-30190	96	41	af4	af4	PROPN
ajst-30190	96	42	,	,	PUNCT
ajst-30190	96	43	f7	f7	PROPN
ajst-30190	96	44	,	,	PUNCT
ajst-30190	96	45	f8	f8	PROPN
ajst-30190	96	46	,	,	PUNCT
ajst-30190	96	47	f3	f3	ADJ
ajst-30190	96	48	,	,	PUNCT
ajst-30190	96	49	and	and	CCONJ
ajst-30190	96	50	f4	f4	NOUN
ajst-30190	96	51	are	be	AUX
ajst-30190	96	52	categorized	categorize	VERB
ajst-30190	96	53	as	as	ADP
ajst-30190	96	54	frontal	frontal	ADJ
ajst-30190	96	55	lobes	lobe	NOUN
ajst-30190	96	56	;	;	PUNCT
ajst-30190	96	57	the	the	DET
ajst-30190	96	58	brain	brain	NOUN
ajst-30190	96	59	areas	area	NOUN
ajst-30190	96	60	where	where	SCONJ
ajst-30190	96	61	electrodes	electrode	VERB
ajst-30190	96	62	fc5	fc5	PROPN
ajst-30190	96	63	and	and	CCONJ
ajst-30190	96	64	fc6	fc6	NOUN
ajst-30190	96	65	are	be	AUX
ajst-30190	96	66	located	locate	VERB
ajst-30190	96	67	are	be	AUX
ajst-30190	96	68	defined	define	VERB
ajst-30190	96	69	as	as	ADP
ajst-30190	96	70	the	the	DET
ajst-30190	96	71	central	central	ADJ
ajst-30190	96	72	brain	brain	NOUN
ajst-30190	96	73	areas	area	NOUN
ajst-30190	96	74	;	;	PUNCT
ajst-30190	96	75	the	the	DET
ajst-30190	96	76	brain	brain	NOUN
ajst-30190	96	77	regions	region	NOUN
ajst-30190	96	78	corresponding	correspond	VERB
ajst-30190	96	79	to	to	PART
ajst-30190	96	80	electrodes	electrode	VERB
ajst-30190	96	81	t7	t7	PROPN
ajst-30190	96	82	and	and	CCONJ
ajst-30190	96	83	t8	t8	NOUN
ajst-30190	96	84	were	be	AUX
ajst-30190	96	85	categorized	categorize	VERB
ajst-30190	96	86	as	as	ADP
ajst-30190	96	87	temporal	temporal	ADJ
ajst-30190	96	88	lobes	lobe	NOUN
ajst-30190	96	89	;	;	PUNCT
ajst-30190	96	90	the	the	DET
ajst-30190	96	91	brain	brain	NOUN
ajst-30190	96	92	regions	region	NOUN
ajst-30190	96	93	corresponding	correspond	VERB
ajst-30190	96	94	to	to	PART
ajst-30190	96	95	electrodes	electrode	VERB
ajst-30190	96	96	p7	p7	ADJ
ajst-30190	96	97	and	and	CCONJ
ajst-30190	96	98	p8	p8	PROPN
ajst-30190	96	99	were	be	AUX
ajst-30190	96	100	categorized	categorize	VERB
ajst-30190	96	101	as	as	ADP
ajst-30190	96	102	parietal	parietal	ADJ
ajst-30190	96	103	lobes	lobe	NOUN
ajst-30190	96	104	;	;	PUNCT
ajst-30190	96	105	and	and	CCONJ
ajst-30190	96	106	the	the	DET
ajst-30190	96	107	brain	brain	NOUN
ajst-30190	96	108	regions	region	NOUN
ajst-30190	96	109	corresponding	correspond	VERB
ajst-30190	96	110	to	to	PART
ajst-30190	96	111	electrodes	electrode	VERB
ajst-30190	96	112	o1	o1	NOUN
ajst-30190	96	113	and	and	CCONJ
ajst-30190	96	114	o2	o2	PROPN
ajst-30190	96	115	were	be	AUX
ajst-30190	96	116	designated	designate	VERB
ajst-30190	96	117	as	as	ADP
ajst-30190	96	118	occipital	occipital	ADJ
ajst-30190	96	119	lobes	lobe	NOUN
ajst-30190	96	120	.	.	PUNCT
ajst-30190	97	1	as	as	SCONJ
ajst-30190	97	2	the	the	DET
ajst-30190	97	3	extracted	extract	VERB
ajst-30190	97	4	multidimensional	multidimensional	ADJ
ajst-30190	97	5	features	feature	NOUN
ajst-30190	97	6	may	may	AUX
ajst-30190	97	7	have	have	VERB
ajst-30190	97	8	redundancy	redundancy	NOUN
ajst-30190	97	9	and	and	CCONJ
ajst-30190	97	10	thus	thus	ADV
ajst-30190	97	11	affect	affect	VERB
ajst-30190	97	12	the	the	DET
ajst-30190	97	13	accuracy	accuracy	NOUN
ajst-30190	97	14	of	of	ADP
ajst-30190	97	15	classification	classification	NOUN
ajst-30190	97	16	,	,	PUNCT
ajst-30190	97	17	we	we	PRON
ajst-30190	97	18	chose	choose	VERB
ajst-30190	97	19	to	to	PART
ajst-30190	97	20	downscale	downscale	VERB
ajst-30190	97	21	the	the	DET
ajst-30190	97	22	features	feature	NOUN
ajst-30190	97	23	by	by	ADP
ajst-30190	97	24	principal	principal	ADJ
ajst-30190	97	25	component	component	NOUN
ajst-30190	97	26	analysis	analysis	NOUN
ajst-30190	97	27	before	before	ADP
ajst-30190	97	28	detecting	detect	VERB
ajst-30190	97	29	fatigue	fatigue	NOUN
ajst-30190	97	30	,	,	PUNCT
ajst-30190	97	31	and	and	CCONJ
ajst-30190	97	32	remove	remove	VERB
ajst-30190	97	33	the	the	DET
ajst-30190	97	34	complicated	complicate	VERB
ajst-30190	97	35	irrelevant	irrelevant	ADJ
ajst-30190	97	36	features	feature	NOUN
ajst-30190	97	37	as	as	ADP
ajst-30190	97	38	input	input	NOUN
ajst-30190	97	39	features	feature	NOUN
ajst-30190	97	40	for	for	ADP
ajst-30190	97	41	classification	classification	NOUN
ajst-30190	97	42	.	.	PUNCT
ajst-30190	98	1	principal	principal	ADJ
ajst-30190	98	2	component	component	NOUN
ajst-30190	98	3	analysis	analysis	NOUN
ajst-30190	98	4	(	(	PUNCT
ajst-30190	98	5	pca	pca	NOUN
ajst-30190	98	6	)	)	PUNCT
ajst-30190	98	7	is	be	AUX
ajst-30190	98	8	the	the	DET
ajst-30190	98	9	process	process	NOUN
ajst-30190	98	10	of	of	ADP
ajst-30190	98	11	reusing	reuse	VERB
ajst-30190	98	12	highly	highly	ADV
ajst-30190	98	13	correlated	correlate	VERB
ajst-30190	98	14	variables	variable	NOUN
ajst-30190	98	15	and	and	CCONJ
ajst-30190	98	16	transforming	transform	VERB
ajst-30190	98	17	them	they	PRON
ajst-30190	98	18	into	into	ADP
ajst-30190	98	19	several	several	ADJ
ajst-30190	98	20	highly	highly	ADV
ajst-30190	98	21	representative	representative	ADJ
ajst-30190	98	22	composite	composite	ADJ
ajst-30190	98	23	variables	variable	NOUN
ajst-30190	98	24	,	,	PUNCT
ajst-30190	98	25	i.e.	i.e.	X
ajst-30190	98	26	,	,	PUNCT
ajst-30190	98	27	principal	principal	ADJ
ajst-30190	98	28	components	component	NOUN
ajst-30190	98	29	.	.	PUNCT
ajst-30190	99	1	they	they	PRON
ajst-30190	99	2	are	be	AUX
ajst-30190	99	3	independent	independent	ADJ
ajst-30190	99	4	and	and	CCONJ
ajst-30190	99	5	unrelated	unrelated	ADJ
ajst-30190	99	6	to	to	ADP
ajst-30190	99	7	each	each	DET
ajst-30190	99	8	other	other	ADJ
ajst-30190	99	9	,	,	PUNCT
ajst-30190	99	10	so	so	SCONJ
ajst-30190	99	11	they	they	PRON
ajst-30190	99	12	can	can	AUX
ajst-30190	99	13	reflect	reflect	VERB
ajst-30190	99	14	most	most	ADJ
ajst-30190	99	15	of	of	ADP
ajst-30190	99	16	the	the	DET
ajst-30190	99	17	information	information	NOUN
ajst-30190	99	18	of	of	ADP
ajst-30190	99	19	the	the	DET
ajst-30190	99	20	variables	variable	NOUN
ajst-30190	99	21	and	and	CCONJ
ajst-30190	99	22	the	the	DET
ajst-30190	99	23	feature	feature	NOUN
ajst-30190	99	24	information	information	NOUN
ajst-30190	99	25	does	do	AUX
ajst-30190	99	26	not	not	PART
ajst-30190	99	27	overlap	overlap	VERB
ajst-30190	99	28	with	with	ADP
ajst-30190	99	29	each	each	DET
ajst-30190	99	30	other	other	ADJ
ajst-30190	99	31	,	,	PUNCT
ajst-30190	99	32	which	which	PRON
ajst-30190	99	33	is	be	AUX
ajst-30190	99	34	a	a	DET
ajst-30190	99	35	good	good	ADJ
ajst-30190	99	36	solution	solution	NOUN
ajst-30190	99	37	to	to	ADP
ajst-30190	99	38	the	the	DET
ajst-30190	99	39	problem	problem	NOUN
ajst-30190	99	40	of	of	ADP
ajst-30190	99	41	feature	feature	NOUN
ajst-30190	99	42	redundancy	redundancy	NOUN
ajst-30190	99	43	[	[	X
ajst-30190	99	44	26	26	NUM
ajst-30190	99	45	]	]	PUNCT
ajst-30190	99	46	.	.	PUNCT
ajst-30190	100	1	in	in	ADP
ajst-30190	100	2	this	this	DET
ajst-30190	100	3	paper	paper	NOUN
ajst-30190	100	4	,	,	PUNCT
ajst-30190	100	5	we	we	PRON
ajst-30190	100	6	choose	choose	VERB
ajst-30190	100	7	to	to	PART
ajst-30190	100	8	extract	extract	VERB
ajst-30190	100	9	the	the	DET
ajst-30190	100	10	first	first	ADJ
ajst-30190	100	11	,	,	PUNCT
ajst-30190	100	12	second	second	ADJ
ajst-30190	100	13	and	and	CCONJ
ajst-30190	100	14	third	third	ADJ
ajst-30190	100	15	features	feature	NOUN
ajst-30190	100	16	as	as	ADP
ajst-30190	100	17	the	the	DET
ajst-30190	100	18	principal	principal	ADJ
ajst-30190	100	19	components	component	NOUN
ajst-30190	100	20	,	,	PUNCT
ajst-30190	100	21	combined	combine	VERB
ajst-30190	100	22	with	with	ADP
ajst-30190	100	23	the	the	DET
ajst-30190	100	24	pearson	pearson	PROPN
ajst-30190	100	25	coefficient	coefficient	NOUN
ajst-30190	100	26	to	to	PART
ajst-30190	100	27	retain	retain	VERB
ajst-30190	100	28	the	the	DET
ajst-30190	100	29	highly	highly	ADV
ajst-30190	100	30	correlated	correlate	VERB
ajst-30190	100	31	features	feature	NOUN
ajst-30190	100	32	for	for	ADP
ajst-30190	100	33	the	the	DET
ajst-30190	100	34	next	next	ADJ
ajst-30190	100	35	study	study	NOUN
ajst-30190	100	36	.	.	PUNCT
ajst-30190	101	1	pearson	pearson	PROPN
ajst-30190	101	2	correlation	correlation	PROPN
ajst-30190	101	3	coefficient	coefficient	NOUN
ajst-30190	101	4	(	(	PUNCT
ajst-30190	101	5	pearson	pearson	PROPN
ajst-30190	101	6	correlation	correlation	NOUN
ajst-30190	101	7	coefficient	coefficient	NOUN
ajst-30190	101	8	)	)	PUNCT
ajst-30190	101	9	can	can	AUX
ajst-30190	101	10	well	well	ADV
ajst-30190	101	11	reflect	reflect	VERB
ajst-30190	101	12	the	the	DET
ajst-30190	101	13	correlation	correlation	NOUN
ajst-30190	101	14	between	between	ADP
ajst-30190	101	15	variables	variable	NOUN
ajst-30190	101	16	[	[	X
ajst-30190	101	17	28	28	NUM
ajst-30190	101	18	]	]	PUNCT
ajst-30190	101	19	.	.	PUNCT
ajst-30190	102	1	in	in	ADP
ajst-30190	102	2	this	this	DET
ajst-30190	102	3	paper	paper	NOUN
ajst-30190	102	4	,	,	PUNCT
ajst-30190	102	5	13	13	NUM
ajst-30190	102	6	-	-	PUNCT
ajst-30190	102	7	dimensional	dimensional	ADJ
ajst-30190	102	8	features	feature	NOUN
ajst-30190	102	9	such	such	ADJ
ajst-30190	102	10	as	as	ADP
ajst-30190	102	11	timefrequency	timefrequency	NOUN
ajst-30190	102	12	entropy	entropy	NOUN
ajst-30190	102	13	are	be	AUX
ajst-30190	102	14	combined	combine	VERB
ajst-30190	102	15	two	two	NUM
ajst-30190	102	16	by	by	ADP
ajst-30190	102	17	two	two	NUM
ajst-30190	102	18	for	for	ADP
ajst-30190	102	19	pearson	pearson	NOUN
ajst-30190	102	20	correlation	correlation	NOUN
ajst-30190	102	21	coefficient	coefficient	NOUN
ajst-30190	102	22	analysis	analysis	NOUN
ajst-30190	102	23	.	.	PUNCT
ajst-30190	103	1	figure	figure	VERB
ajst-30190	103	2	4.2	4.2	NUM
ajst-30190	103	3	heat	heat	NOUN
ajst-30190	103	4	map	map	NOUN
ajst-30190	103	5	of	of	ADP
ajst-30190	103	6	feature	feature	NOUN
ajst-30190	103	7	correlation	correlation	NOUN
ajst-30190	103	8	coefficient	coefficient	NOUN
ajst-30190	103	9	matrix	matrix	NOUN
ajst-30190	103	10	corresponding	correspond	VERB
ajst-30190	103	11	to	to	ADP
ajst-30190	103	12	eeg	eeg	NOUN
ajst-30190	103	13	data	datum	NOUN
ajst-30190	103	14	of	of	ADP
ajst-30190	103	15	selected	select	VERB
ajst-30190	103	16	subjects	subject	NOUN
ajst-30190	103	17	,	,	PUNCT
ajst-30190	103	18	where	where	SCONJ
ajst-30190	103	19	red	red	NOUN
ajst-30190	103	20	represents	represent	VERB
ajst-30190	103	21	positive	positive	ADJ
ajst-30190	103	22	correlation	correlation	NOUN
ajst-30190	103	23	,	,	PUNCT
ajst-30190	103	24	blue	blue	NOUN
ajst-30190	103	25	represents	represent	VERB
ajst-30190	103	26	negative	negative	ADJ
ajst-30190	103	27	correlation	correlation	NOUN
ajst-30190	103	28	,	,	PUNCT
ajst-30190	103	29	and	and	CCONJ
ajst-30190	103	30	the	the	DET
ajst-30190	103	31	depth	depth	NOUN
ajst-30190	103	32	of	of	ADP
ajst-30190	103	33	color	color	NOUN
ajst-30190	103	34	represents	represent	VERB
ajst-30190	103	35	the	the	DET
ajst-30190	103	36	strength	strength	NOUN
ajst-30190	103	37	of	of	ADP
ajst-30190	103	38	correlation	correlation	NOUN
ajst-30190	103	39	.	.	PUNCT
ajst-30190	104	1	from	from	ADP
ajst-30190	104	2	the	the	DET
ajst-30190	104	3	figure	figure	NOUN
ajst-30190	104	4	,	,	PUNCT
ajst-30190	104	5	it	it	PRON
ajst-30190	104	6	can	can	AUX
ajst-30190	104	7	be	be	AUX
ajst-30190	104	8	seen	see	VERB
ajst-30190	104	9	that	that	SCONJ
ajst-30190	104	10	:	:	PUNCT
ajst-30190	104	11	hjorth	hjorth	NOUN
ajst-30190	104	12	mobility	mobility	NOUN
ajst-30190	104	13	is	be	AUX
ajst-30190	104	14	negatively	negatively	ADV
ajst-30190	104	15	correlated	correlate	VERB
ajst-30190	104	16	with	with	ADP
ajst-30190	104	17	hjorth	hjorth	NOUN
ajst-30190	104	18	complexity	complexity	NOUN
ajst-30190	104	19	,	,	PUNCT
ajst-30190	104	20	power	power	NOUN
ajst-30190	104	21	spectral	spectral	ADJ
ajst-30190	104	22	density	density	NOUN
ajst-30190	104	23	,	,	PUNCT
ajst-30190	104	24	energy	energy	NOUN
ajst-30190	104	25	spectrum	spectrum	NOUN
ajst-30190	104	26	and	and	CCONJ
ajst-30190	104	27	sample	sample	NOUN
ajst-30190	104	28	entropy	entropy	NOUN
ajst-30190	104	29	,	,	PUNCT
ajst-30190	104	30	and	and	CCONJ
ajst-30190	104	31	hjorth	hjorth	NOUN
ajst-30190	104	32	complexity	complexity	NOUN
ajst-30190	104	33	and	and	CCONJ
ajst-30190	104	34	sample	sample	NOUN
ajst-30190	104	35	entropy	entropy	NOUN
ajst-30190	104	36	;	;	PUNCT
ajst-30190	104	37	hjorth	hjorth	NOUN
ajst-30190	104	38	mobility	mobility	NOUN
ajst-30190	104	39	is	be	AUX
ajst-30190	104	40	positively	positively	ADV
ajst-30190	104	41	correlated	correlate	VERB
ajst-30190	104	42	with	with	ADP
ajst-30190	104	43	sample	sample	NOUN
ajst-30190	104	44	entropy	entropy	NOUN
ajst-30190	104	45	,	,	PUNCT
ajst-30190	104	46	power	power	NOUN
ajst-30190	104	47	spectral	spectral	ADJ
ajst-30190	104	48	density	density	NOUN
ajst-30190	104	49	,	,	PUNCT
ajst-30190	104	50	energy	energy	NOUN
ajst-30190	104	51	spectrum	spectrum	NOUN
ajst-30190	104	52	and	and	CCONJ
ajst-30190	104	53	wavelet	wavelet	NOUN
ajst-30190	104	54	entropy	entropy	PROPN
ajst-30190	104	55	.	.	PUNCT
ajst-30190	105	1	therefore	therefore	ADV
ajst-30190	105	2	,	,	PUNCT
ajst-30190	105	3	hjorth	hjorth	NOUN
ajst-30190	105	4	complexity	complexity	NOUN
ajst-30190	105	5	and	and	CCONJ
ajst-30190	105	6	energy	energy	NOUN
ajst-30190	105	7	spectrum	spectrum	NOUN
ajst-30190	105	8	features	feature	NOUN
ajst-30190	105	9	are	be	AUX
ajst-30190	105	10	excluded	exclude	VERB
ajst-30190	105	11	and	and	CCONJ
ajst-30190	105	12	the	the	DET
ajst-30190	105	13	remaining	remain	VERB
ajst-30190	105	14	features	feature	NOUN
ajst-30190	105	15	with	with	ADP
ajst-30190	105	16	no	no	DET
ajst-30190	105	17	significant	significant	ADJ
ajst-30190	105	18	correlation	correlation	NOUN
ajst-30190	105	19	are	be	AUX
ajst-30190	105	20	analyzed	analyze	VERB
ajst-30190	105	21	in	in	ADP
ajst-30190	105	22	the	the	DET
ajst-30190	105	23	next	next	ADJ
ajst-30190	105	24	step	step	NOUN
ajst-30190	105	25	.	.	PUNCT
ajst-30190	106	1	146	146	NUM
ajst-30190	106	2	figure	figure	NOUN
ajst-30190	106	3	4.2	4.2	NUM
ajst-30190	106	4	heat	heat	NOUN
ajst-30190	106	5	map	map	NOUN
ajst-30190	106	6	of	of	ADP
ajst-30190	106	7	correlation	correlation	NOUN
ajst-30190	106	8	coefficients	coefficient	NOUN
ajst-30190	106	9	between	between	ADP
ajst-30190	106	10	different	different	ADJ
ajst-30190	106	11	combinations	combination	NOUN
ajst-30190	106	12	of	of	ADP
ajst-30190	106	13	features	feature	NOUN
ajst-30190	106	14	(	(	PUNCT
ajst-30190	106	15	3	3	NUM
ajst-30190	106	16	)	)	PUNCT
ajst-30190	106	17	c	c	NOUN
ajst-30190	106	18	-	-	PUNCT
ajst-30190	106	19	rbm	rbm	PROPN
ajst-30190	106	20	fatigue	fatigue	NOUN
ajst-30190	106	21	detection	detection	NOUN
ajst-30190	106	22	study	study	NOUN
ajst-30190	106	23	in	in	ADP
ajst-30190	106	24	this	this	DET
ajst-30190	106	25	paper	paper	NOUN
ajst-30190	106	26	,	,	PUNCT
ajst-30190	106	27	a	a	DET
ajst-30190	106	28	classification	classification	NOUN
ajst-30190	106	29	model	model	NOUN
ajst-30190	106	30	based	base	VERB
ajst-30190	106	31	on	on	ADP
ajst-30190	106	32	self	self	NOUN
ajst-30190	106	33	-	-	PUNCT
ajst-30190	106	34	trainingsemi	trainingsemi	NOUN
ajst-30190	106	35	-	-	PUNCT
ajst-30190	106	36	supervised	supervised	ADJ
ajst-30190	106	37	learning	learning	NOUN
ajst-30190	106	38	is	be	AUX
ajst-30190	106	39	proposed	propose	VERB
ajst-30190	106	40	.	.	PUNCT
ajst-30190	107	1	the	the	DET
ajst-30190	107	2	cnn	cnn	PROPN
ajst-30190	107	3	is	be	AUX
ajst-30190	107	4	used	use	VERB
ajst-30190	107	5	as	as	ADP
ajst-30190	107	6	the	the	DET
ajst-30190	107	7	initial	initial	ADJ
ajst-30190	107	8	classifier	classifier	NOUN
ajst-30190	107	9	,	,	PUNCT
ajst-30190	107	10	32	32	NUM
ajst-30190	107	11	5×5	5×5	NUM
ajst-30190	107	12	convolutional	convolutional	ADJ
ajst-30190	107	13	kernels	kernel	NOUN
ajst-30190	107	14	are	be	AUX
ajst-30190	107	15	selected	select	VERB
ajst-30190	107	16	for	for	ADP
ajst-30190	107	17	the	the	DET
ajst-30190	107	18	convolutional	convolutional	ADJ
ajst-30190	107	19	layer	layer	NOUN
ajst-30190	107	20	and	and	CCONJ
ajst-30190	107	21	moved	move	VERB
ajst-30190	107	22	step	step	NOUN
ajst-30190	107	23	by	by	ADP
ajst-30190	107	24	step	step	NOUN
ajst-30190	107	25	,	,	PUNCT
ajst-30190	107	26	the	the	DET
ajst-30190	107	27	relu	relu	NOUN
ajst-30190	107	28	function	function	NOUN
ajst-30190	107	29	is	be	AUX
ajst-30190	107	30	selected	select	VERB
ajst-30190	107	31	for	for	ADP
ajst-30190	107	32	the	the	DET
ajst-30190	107	33	activation	activation	NOUN
ajst-30190	107	34	layer	layer	NOUN
ajst-30190	107	35	,	,	PUNCT
ajst-30190	107	36	the	the	DET
ajst-30190	107	37	window	window	NOUN
ajst-30190	107	38	of	of	ADP
ajst-30190	107	39	the	the	DET
ajst-30190	107	40	pooling	pooling	NOUN
ajst-30190	107	41	layer	layer	NOUN
ajst-30190	107	42	is	be	AUX
ajst-30190	107	43	set	set	VERB
ajst-30190	107	44	to	to	ADP
ajst-30190	107	45	2×2	2×2	NUM
ajst-30190	107	46	,	,	PUNCT
ajst-30190	107	47	the	the	DET
ajst-30190	107	48	step	step	NOUN
ajst-30190	107	49	size	size	NOUN
ajst-30190	107	50	is	be	AUX
ajst-30190	107	51	set	set	VERB
ajst-30190	107	52	to	to	ADP
ajst-30190	107	53	2	2	NUM
ajst-30190	107	54	,	,	PUNCT
ajst-30190	107	55	and	and	CCONJ
ajst-30190	107	56	the	the	DET
ajst-30190	107	57	learning	learning	NOUN
ajst-30190	107	58	rate	rate	NOUN
ajst-30190	107	59	is	be	AUX
ajst-30190	107	60	set	set	VERB
ajst-30190	107	61	to	to	ADP
ajst-30190	107	62	0.001	0.001	NUM
ajst-30190	107	63	.	.	PUNCT
ajst-30190	108	1	after	after	ADP
ajst-30190	108	2	that	that	PRON
ajst-30190	108	3	,	,	PUNCT
ajst-30190	108	4	the	the	DET
ajst-30190	108	5	dataset	dataset	NOUN
ajst-30190	108	6	is	be	AUX
ajst-30190	108	7	divided	divide	VERB
ajst-30190	108	8	into	into	ADP
ajst-30190	108	9	the	the	DET
ajst-30190	108	10	training	training	NOUN
ajst-30190	108	11	set	set	NOUN
ajst-30190	108	12	and	and	CCONJ
ajst-30190	108	13	the	the	DET
ajst-30190	108	14	test	test	NOUN
ajst-30190	108	15	set	set	VERB
ajst-30190	108	16	according	accord	VERB
ajst-30190	108	17	to	to	ADP
ajst-30190	108	18	the	the	DET
ajst-30190	108	19	ratio	ratio	NOUN
ajst-30190	108	20	of	of	ADP
ajst-30190	108	21	3:7	3:7	NUM
ajst-30190	108	22	,	,	PUNCT
ajst-30190	108	23	and	and	CCONJ
ajst-30190	108	24	the	the	DET
ajst-30190	108	25	confidence	confidence	NOUN
ajst-30190	108	26	threshold	threshold	NOUN
ajst-30190	108	27	is	be	AUX
ajst-30190	108	28	set	set	VERB
ajst-30190	108	29	to	to	ADP
ajst-30190	108	30	0.8	0.8	NUM
ajst-30190	108	31	,	,	PUNCT
ajst-30190	108	32	and	and	CCONJ
ajst-30190	108	33	the	the	DET
ajst-30190	108	34	data	datum	NOUN
ajst-30190	108	35	with	with	ADP
ajst-30190	108	36	a	a	DET
ajst-30190	108	37	higher	high	ADJ
ajst-30190	108	38	value	value	NOUN
ajst-30190	108	39	than	than	ADP
ajst-30190	108	40	0.8	0.8	NUM
ajst-30190	108	41	are	be	AUX
ajst-30190	108	42	added	add	VERB
ajst-30190	108	43	into	into	ADP
ajst-30190	108	44	the	the	DET
ajst-30190	108	45	test	test	NOUN
ajst-30190	108	46	set	set	VERB
ajst-30190	108	47	as	as	ADP
ajst-30190	108	48	pseudo	pseudo	NOUN
ajst-30190	108	49	-	-	PUNCT
ajst-30190	108	50	labeled	label	VERB
ajst-30190	108	51	data	datum	NOUN
ajst-30190	108	52	.	.	PUNCT
ajst-30190	109	1	the	the	DET
ajst-30190	109	2	confidence	confidence	NOUN
ajst-30190	109	3	threshold	threshold	NOUN
ajst-30190	109	4	is	be	AUX
ajst-30190	109	5	set	set	VERB
ajst-30190	109	6	to	to	ADP
ajst-30190	109	7	0.8	0.8	NUM
ajst-30190	109	8	,	,	PUNCT
ajst-30190	109	9	and	and	CCONJ
ajst-30190	109	10	data	datum	NOUN
ajst-30190	109	11	higher	high	ADJ
ajst-30190	109	12	than	than	ADP
ajst-30190	109	13	0.8	0.8	NUM
ajst-30190	109	14	are	be	AUX
ajst-30190	109	15	added	add	VERB
ajst-30190	109	16	to	to	ADP
ajst-30190	109	17	the	the	DET
ajst-30190	109	18	test	test	NOUN
ajst-30190	109	19	set	set	VERB
ajst-30190	109	20	as	as	ADP
ajst-30190	109	21	pseudomarked	pseudomarked	ADJ
ajst-30190	109	22	data	datum	NOUN
ajst-30190	109	23	.	.	PUNCT
ajst-30190	110	1	data	datum	NOUN
ajst-30190	110	2	less	less	ADJ
ajst-30190	110	3	than	than	ADP
ajst-30190	110	4	0.8	0.8	NUM
ajst-30190	110	5	will	will	AUX
ajst-30190	110	6	continue	continue	VERB
ajst-30190	110	7	to	to	PART
ajst-30190	110	8	participate	participate	VERB
ajst-30190	110	9	in	in	ADP
ajst-30190	110	10	the	the	DET
ajst-30190	110	11	training	training	NOUN
ajst-30190	110	12	until	until	SCONJ
ajst-30190	110	13	the	the	DET
ajst-30190	110	14	preset	preset	ADJ
ajst-30190	110	15	number	number	NOUN
ajst-30190	110	16	of	of	ADP
ajst-30190	110	17	iterations	iteration	NOUN
ajst-30190	110	18	is	be	AUX
ajst-30190	110	19	reached	reach	VERB
ajst-30190	110	20	.	.	PUNCT
ajst-30190	111	1	finally	finally	ADV
ajst-30190	111	2	,	,	PUNCT
ajst-30190	111	3	a	a	DET
ajst-30190	111	4	new	new	ADJ
ajst-30190	111	5	test	test	NOUN
ajst-30190	111	6	set	set	NOUN
ajst-30190	111	7	is	be	AUX
ajst-30190	111	8	formed	form	VERB
ajst-30190	111	9	,	,	PUNCT
ajst-30190	111	10	which	which	PRON
ajst-30190	111	11	serves	serve	VERB
ajst-30190	111	12	as	as	ADP
ajst-30190	111	13	the	the	DET
ajst-30190	111	14	target	target	NOUN
ajst-30190	111	15	input	input	NOUN
ajst-30190	111	16	for	for	ADP
ajst-30190	111	17	svm	svm	PROPN
ajst-30190	111	18	and	and	CCONJ
ajst-30190	111	19	knn	knn	PROPN
ajst-30190	111	20	classifiers	classifier	NOUN
ajst-30190	111	21	to	to	PART
ajst-30190	111	22	predict	predict	VERB
ajst-30190	111	23	fatigue	fatigue	NOUN
ajst-30190	111	24	eeg	eeg	PROPN
ajst-30190	111	25	.	.	PUNCT
ajst-30190	111	26	figure	figure	VERB
ajst-30190	111	27	4.3	4.3	NUM
ajst-30190	111	28	below	below	ADV
ajst-30190	111	29	shows	show	VERB
ajst-30190	111	30	the	the	DET
ajst-30190	111	31	general	general	ADJ
ajst-30190	111	32	framework	framework	NOUN
ajst-30190	111	33	diagram	diagram	PROPN
ajst-30190	111	34	.	.	PUNCT
ajst-30190	112	1	table	table	NOUN
ajst-30190	112	2	4.1	4.1	NUM
ajst-30190	112	3	compares	compare	VERB
ajst-30190	112	4	the	the	DET
ajst-30190	112	5	fatigue	fatigue	NOUN
ajst-30190	112	6	eeg	eeg	NOUN
ajst-30190	112	7	classification	classification	NOUN
ajst-30190	112	8	accuracy	accuracy	NOUN
ajst-30190	112	9	results	result	NOUN
ajst-30190	112	10	for	for	ADP
ajst-30190	112	11	different	different	ADJ
ajst-30190	112	12	channels	channel	NOUN
ajst-30190	112	13	after	after	ADP
ajst-30190	112	14	feature	feature	NOUN
ajst-30190	112	15	selection	selection	NOUN
ajst-30190	112	16	.	.	PUNCT
ajst-30190	113	1	figure	figure	VERB
ajst-30190	113	2	4.3	4.3	NUM
ajst-30190	113	3	general	general	ADJ
ajst-30190	113	4	framework	framework	NOUN
ajst-30190	113	5	diagram	diagram	NOUN
ajst-30190	113	6	of	of	ADP
ajst-30190	113	7	self	self	NOUN
ajst-30190	113	8	-	-	PUNCT
ajst-30190	113	9	training	training	NOUN
ajst-30190	113	10	-	-	PUNCT
ajst-30190	113	11	semi	semi	ADV
ajst-30190	113	12	-	-	ADJ
ajst-30190	113	13	supervised	supervised	ADJ
ajst-30190	113	14	learning	learn	VERB
ajst-30190	113	15	classification	classification	NOUN
ajst-30190	113	16	model	model	NOUN
ajst-30190	113	17	147	147	NUM
ajst-30190	113	18	table	table	NOUN
ajst-30190	113	19	4.1	4.1	NUM
ajst-30190	113	20	fatigue	fatigue	NOUN
ajst-30190	113	21	eeg	eeg	NOUN
ajst-30190	113	22	classification	classification	NOUN
ajst-30190	113	23	accuracy	accuracy	NOUN
ajst-30190	113	24	for	for	ADP
ajst-30190	113	25	different	different	ADJ
ajst-30190	113	26	channels	channel	NOUN
ajst-30190	113	27	in	in	ADP
ajst-30190	113	28	16	16	NUM
ajst-30190	113	29	subjects	subject	NOUN
ajst-30190	113	30	from	from	ADP
ajst-30190	113	31	the	the	DET
ajst-30190	113	32	above	above	ADJ
ajst-30190	113	33	table	table	NOUN
ajst-30190	113	34	,	,	PUNCT
ajst-30190	113	35	it	it	PRON
ajst-30190	113	36	can	can	AUX
ajst-30190	113	37	be	be	AUX
ajst-30190	113	38	seen	see	VERB
ajst-30190	113	39	that	that	SCONJ
ajst-30190	113	40	the	the	DET
ajst-30190	113	41	average	average	ADJ
ajst-30190	113	42	classification	classification	NOUN
ajst-30190	113	43	accuracy	accuracy	NOUN
ajst-30190	113	44	of	of	ADP
ajst-30190	113	45	frontal	frontal	ADJ
ajst-30190	113	46	,	,	PUNCT
ajst-30190	113	47	parietal	parietal	ADJ
ajst-30190	113	48	and	and	CCONJ
ajst-30190	113	49	occipital	occipital	NOUN
ajst-30190	113	50	lobes	lobe	NOUN
ajst-30190	113	51	is	be	AUX
ajst-30190	113	52	higher	high	ADJ
ajst-30190	113	53	,	,	PUNCT
ajst-30190	113	54	reaching	reach	VERB
ajst-30190	113	55	89	89	NUM
ajst-30190	113	56	%	%	NOUN
ajst-30190	113	57	,	,	PUNCT
ajst-30190	113	58	87	87	NUM
ajst-30190	113	59	%	%	NOUN
ajst-30190	113	60	and	and	CCONJ
ajst-30190	113	61	91	91	NUM
ajst-30190	113	62	%	%	NOUN
ajst-30190	113	63	,	,	PUNCT
ajst-30190	113	64	respectively	respectively	ADV
ajst-30190	113	65	,	,	PUNCT
ajst-30190	113	66	which	which	PRON
ajst-30190	113	67	determines	determine	VERB
ajst-30190	113	68	that	that	SCONJ
ajst-30190	113	69	the	the	DET
ajst-30190	113	70	number	number	NOUN
ajst-30190	113	71	of	of	ADP
ajst-30190	113	72	channels	channel	NOUN
ajst-30190	113	73	can	can	AUX
ajst-30190	113	74	be	be	AUX
ajst-30190	113	75	appropriately	appropriately	ADV
ajst-30190	113	76	reduced	reduce	VERB
ajst-30190	113	77	to	to	PART
ajst-30190	113	78	analyze	analyze	VERB
ajst-30190	113	79	and	and	CCONJ
ajst-30190	113	80	classify	classify	VERB
ajst-30190	113	81	fatigue	fatigue	NOUN
ajst-30190	113	82	eeg	eeg	NOUN
ajst-30190	113	83	features	feature	NOUN
ajst-30190	113	84	,	,	PUNCT
ajst-30190	113	85	and	and	CCONJ
ajst-30190	113	86	the	the	DET
ajst-30190	113	87	following	follow	VERB
ajst-30190	113	88	use	use	NOUN
ajst-30190	113	89	of	of	ADP
ajst-30190	113	90	different	different	ADJ
ajst-30190	113	91	classifiers	classifier	NOUN
ajst-30190	113	92	focuses	focus	VERB
ajst-30190	113	93	on	on	ADP
ajst-30190	113	94	the	the	DET
ajst-30190	113	95	fatigue	fatigue	NOUN
ajst-30190	113	96	detection	detection	NOUN
ajst-30190	113	97	of	of	ADP
ajst-30190	113	98	the	the	DET
ajst-30190	113	99	sparse	sparse	ADJ
ajst-30190	113	100	channels	channel	NOUN
ajst-30190	113	101	and	and	CCONJ
ajst-30190	113	102	the	the	DET
ajst-30190	113	103	features	feature	NOUN
ajst-30190	113	104	after	after	ADP
ajst-30190	113	105	dimensionality	dimensionality	NOUN
ajst-30190	113	106	reduction	reduction	NOUN
ajst-30190	113	107	.	.	PUNCT
ajst-30190	114	1	in	in	ADP
ajst-30190	114	2	this	this	DET
ajst-30190	114	3	paper	paper	NOUN
ajst-30190	114	4	,	,	PUNCT
ajst-30190	114	5	welch	welch	PROPN
ajst-30190	114	6	's	's	PART
ajst-30190	114	7	method	method	NOUN
ajst-30190	114	8	,	,	PUNCT
ajst-30190	114	9	wavelet	wavelet	NOUN
ajst-30190	114	10	packet	packet	NOUN
ajst-30190	114	11	transform	transform	NOUN
ajst-30190	114	12	and	and	CCONJ
ajst-30190	114	13	fuzzy	fuzzy	ADJ
ajst-30190	114	14	entropy	entropy	NOUN
ajst-30190	114	15	method	method	NOUN
ajst-30190	114	16	are	be	AUX
ajst-30190	114	17	used	use	VERB
ajst-30190	114	18	to	to	PART
ajst-30190	114	19	extract	extract	VERB
ajst-30190	114	20	the	the	DET
ajst-30190	114	21	power	power	NOUN
ajst-30190	114	22	spectrum	spectrum	NOUN
ajst-30190	114	23	and	and	CCONJ
ajst-30190	114	24	sub	sub	ADJ
ajst-30190	114	25	-	-	ADJ
ajst-30190	114	26	band	band	ADJ
ajst-30190	114	27	feature	feature	NOUN
ajst-30190	114	28	information	information	NOUN
ajst-30190	114	29	of	of	ADP
ajst-30190	114	30	δ	δ	PROPN
ajst-30190	114	31	,	,	PUNCT
ajst-30190	114	32	θ	θ	PROPN
ajst-30190	114	33	,	,	PUNCT
ajst-30190	114	34	α	α	PROPN
ajst-30190	114	35	and	and	CCONJ
ajst-30190	114	36	β	β	X
ajst-30190	114	37	of	of	ADP
ajst-30190	114	38	the	the	DET
ajst-30190	114	39	eeg	eeg	NOUN
ajst-30190	114	40	signals	signal	NOUN
ajst-30190	114	41	,	,	PUNCT
ajst-30190	114	42	respectively	respectively	ADV
ajst-30190	114	43	,	,	PUNCT
ajst-30190	114	44	and	and	CCONJ
ajst-30190	114	45	compare	compare	VERB
ajst-30190	114	46	the	the	DET
ajst-30190	114	47	fatigue	fatigue	NOUN
ajst-30190	114	48	detection	detection	NOUN
ajst-30190	114	49	of	of	ADP
ajst-30190	114	50	the	the	DET
ajst-30190	114	51	frontal	frontal	ADJ
ajst-30190	114	52	lobe	lobe	NOUN
ajst-30190	114	53	,	,	PUNCT
ajst-30190	114	54	parietal	parietal	ADJ
ajst-30190	114	55	lobe	lobe	NOUN
ajst-30190	114	56	and	and	CCONJ
ajst-30190	114	57	occipital	occipital	NOUN
ajst-30190	114	58	lobe	lobe	VERB
ajst-30190	114	59	with	with	ADP
ajst-30190	114	60	the	the	DET
ajst-30190	114	61	classical	classical	ADJ
ajst-30190	114	62	binary	binary	ADJ
ajst-30190	114	63	classification	classification	NOUN
ajst-30190	114	64	svm	svm	PROPN
ajst-30190	114	65	classifiers	classifier	NOUN
ajst-30190	114	66	and	and	CCONJ
ajst-30190	114	67	the	the	DET
ajst-30190	114	68	trained	train	VERB
ajst-30190	114	69	cnn	cnn	PROPN
ajst-30190	114	70	classifier	classifier	PROPN
ajst-30190	114	71	model	model	PROPN
ajst-30190	114	72	,	,	PUNCT
ajst-30190	114	73	respectively	respectively	ADV
ajst-30190	114	74	,	,	PUNCT
ajst-30190	114	75	and	and	CCONJ
ajst-30190	114	76	the	the	DET
ajst-30190	114	77	comparison	comparison	NOUN
ajst-30190	114	78	of	of	ADP
ajst-30190	114	79	the	the	DET
ajst-30190	114	80	classification	classification	NOUN
ajst-30190	114	81	results	result	NOUN
ajst-30190	114	82	is	be	AUX
ajst-30190	114	83	shown	show	VERB
ajst-30190	114	84	in	in	ADP
ajst-30190	114	85	the	the	DET
ajst-30190	114	86	table	table	NOUN
ajst-30190	114	87	below	below	ADV
ajst-30190	114	88	:	:	PUNCT
ajst-30190	114	89	table	table	NOUN
ajst-30190	114	90	4.2	4.2	NUM
ajst-30190	114	91	mean	mean	NOUN
ajst-30190	114	92	classification	classification	NOUN
ajst-30190	114	93	accuracy	accuracy	NOUN
ajst-30190	114	94	in	in	ADP
ajst-30190	114	95	different	different	ADJ
ajst-30190	114	96	brain	brain	NOUN
ajst-30190	114	97	regions	region	NOUN
ajst-30190	114	98	as	as	SCONJ
ajst-30190	114	99	can	can	AUX
ajst-30190	114	100	be	be	AUX
ajst-30190	114	101	seen	see	VERB
ajst-30190	114	102	from	from	ADP
ajst-30190	114	103	table	table	NOUN
ajst-30190	114	104	4.2	4.2	NUM
ajst-30190	114	105	,	,	PUNCT
ajst-30190	114	106	the	the	DET
ajst-30190	114	107	traditional	traditional	ADJ
ajst-30190	114	108	method	method	NOUN
ajst-30190	114	109	using	use	VERB
ajst-30190	114	110	svm	svm	PROPN
ajst-30190	114	111	classifier	classifier	NOUN
ajst-30190	114	112	achieves	achieve	VERB
ajst-30190	114	113	good	good	ADJ
ajst-30190	114	114	results	result	NOUN
ajst-30190	114	115	with	with	ADP
ajst-30190	114	116	an	an	DET
ajst-30190	114	117	average	average	ADJ
ajst-30190	114	118	accuracy	accuracy	NOUN
ajst-30190	114	119	close	close	ADJ
ajst-30190	114	120	to	to	ADP
ajst-30190	114	121	78	78	NUM
ajst-30190	114	122	%	%	NOUN
ajst-30190	114	123	for	for	ADP
ajst-30190	114	124	all	all	DET
ajst-30190	114	125	three	three	NUM
ajst-30190	114	126	brain	brain	NOUN
ajst-30190	114	127	regions	region	NOUN
ajst-30190	114	128	.	.	PUNCT
ajst-30190	115	1	this	this	PRON
ajst-30190	115	2	indicates	indicate	VERB
ajst-30190	115	3	that	that	SCONJ
ajst-30190	115	4	with	with	ADP
ajst-30190	115	5	the	the	DET
ajst-30190	115	6	a	a	DET
ajst-30190	115	7	priori	priori	ADJ
ajst-30190	115	8	experience	experience	NOUN
ajst-30190	115	9	of	of	ADP
ajst-30190	115	10	manually	manually	ADV
ajst-30190	115	11	selecting	select	VERB
ajst-30190	115	12	features	feature	NOUN
ajst-30190	115	13	,	,	PUNCT
ajst-30190	115	14	the	the	DET
ajst-30190	115	15	svm	svm	PROPN
ajst-30190	115	16	classification	classification	NOUN
ajst-30190	115	17	model	model	NOUN
ajst-30190	115	18	is	be	AUX
ajst-30190	115	19	able	able	ADJ
ajst-30190	115	20	to	to	PART
ajst-30190	115	21	obtain	obtain	VERB
ajst-30190	115	22	a	a	DET
ajst-30190	115	23	high	high	ADJ
ajst-30190	115	24	classification	classification	NOUN
ajst-30190	115	25	accuracy	accuracy	NOUN
ajst-30190	115	26	.	.	PUNCT
ajst-30190	116	1	and	and	CCONJ
ajst-30190	116	2	the	the	DET
ajst-30190	116	3	classification	classification	NOUN
ajst-30190	116	4	accuracy	accuracy	NOUN
ajst-30190	116	5	of	of	ADP
ajst-30190	116	6	c	c	PROPN
ajst-30190	116	7	-	-	PUNCT
ajst-30190	116	8	rbm	rbm	PROPN
ajst-30190	116	9	+	+	PROPN
ajst-30190	116	10	cnn	cnn	PROPN
ajst-30190	116	11	for	for	ADP
ajst-30190	116	12	all	all	DET
ajst-30190	116	13	three	three	NUM
ajst-30190	116	14	channels	channel	NOUN
ajst-30190	116	15	reaches	reach	VERB
ajst-30190	116	16	about	about	ADP
ajst-30190	116	17	85	85	NUM
ajst-30190	116	18	%	%	NOUN
ajst-30190	116	19	,	,	PUNCT
ajst-30190	116	20	which	which	PRON
ajst-30190	116	21	is	be	AUX
ajst-30190	116	22	about	about	ADV
ajst-30190	116	23	7	7	NUM
ajst-30190	116	24	%	%	NOUN
ajst-30190	116	25	higher	high	ADJ
ajst-30190	116	26	than	than	ADP
ajst-30190	116	27	the	the	DET
ajst-30190	116	28	c	c	PROPN
ajst-30190	116	29	-	-	PUNCT
ajst-30190	116	30	rbm	rbm	PROPN
ajst-30190	116	31	+	+	CCONJ
ajst-30190	116	32	svm	svm	ADJ
ajst-30190	116	33	model	model	NOUN
ajst-30190	116	34	.	.	PUNCT
ajst-30190	117	1	it	it	PRON
ajst-30190	117	2	is	be	AUX
ajst-30190	117	3	proved	prove	VERB
ajst-30190	117	4	that	that	SCONJ
ajst-30190	117	5	the	the	DET
ajst-30190	117	6	trained	train	VERB
ajst-30190	117	7	initial	initial	ADJ
ajst-30190	117	8	classifier	classifier	NOUN
ajst-30190	117	9	achieves	achieve	VERB
ajst-30190	117	10	higher	high	ADJ
ajst-30190	117	11	accuracy	accuracy	NOUN
ajst-30190	117	12	on	on	ADP
ajst-30190	117	13	sparse	sparse	ADJ
ajst-30190	117	14	channels	channel	NOUN
ajst-30190	117	15	,	,	PUNCT
ajst-30190	117	16	based	base	VERB
ajst-30190	117	17	on	on	ADP
ajst-30190	117	18	which	which	DET
ajst-30190	117	19	fatigue	fatigue	NOUN
ajst-30190	117	20	is	be	AUX
ajst-30190	117	21	detected	detect	VERB
ajst-30190	117	22	and	and	CCONJ
ajst-30190	117	23	evaluated	evaluate	VERB
ajst-30190	117	24	using	use	VERB
ajst-30190	117	25	svm	svm	PROPN
ajst-30190	117	26	and	and	CCONJ
ajst-30190	117	27	rf	rf	NOUN
ajst-30190	117	28	classifiers	classifier	NOUN
ajst-30190	117	29	for	for	ADP
ajst-30190	117	30	this	this	DET
ajst-30190	117	31	test	test	NOUN
ajst-30190	117	32	set	set	VERB
ajst-30190	117	33	.	.	PUNCT
ajst-30190	118	1	148	148	NUM
ajst-30190	118	2	(	(	PUNCT
ajst-30190	118	3	4	4	NUM
ajst-30190	118	4	)	)	PUNCT
ajst-30190	118	5	analysis	analysis	NOUN
ajst-30190	118	6	of	of	ADP
ajst-30190	118	7	feature	feature	NOUN
ajst-30190	118	8	classification	classification	NOUN
ajst-30190	118	9	results	result	NOUN
ajst-30190	118	10	of	of	ADP
ajst-30190	118	11	different	different	ADJ
ajst-30190	118	12	classifiers	classifier	NOUN
ajst-30190	118	13	for	for	ADP
ajst-30190	118	14	sparse	sparse	ADJ
ajst-30190	118	15	channels	channel	NOUN
ajst-30190	118	16	the	the	DET
ajst-30190	118	17	classification	classification	NOUN
ajst-30190	118	18	results	result	NOUN
ajst-30190	118	19	of	of	ADP
ajst-30190	118	20	the	the	DET
ajst-30190	118	21	overall	overall	ADJ
ajst-30190	118	22	fatigue	fatigue	NOUN
ajst-30190	118	23	eeg	eeg	NOUN
ajst-30190	118	24	features	feature	NOUN
ajst-30190	118	25	of	of	ADP
ajst-30190	118	26	different	different	ADJ
ajst-30190	118	27	channels	channel	NOUN
ajst-30190	118	28	were	be	AUX
ajst-30190	118	29	analyzed	analyze	VERB
ajst-30190	118	30	above	above	ADV
ajst-30190	118	31	,	,	PUNCT
ajst-30190	118	32	and	and	CCONJ
ajst-30190	118	33	after	after	ADP
ajst-30190	118	34	dimensionality	dimensionality	NOUN
ajst-30190	118	35	reduction	reduction	NOUN
ajst-30190	118	36	,	,	PUNCT
ajst-30190	118	37	it	it	PRON
ajst-30190	118	38	was	be	AUX
ajst-30190	118	39	found	find	VERB
ajst-30190	118	40	that	that	SCONJ
ajst-30190	118	41	the	the	DET
ajst-30190	118	42	frontal	frontal	ADJ
ajst-30190	118	43	,	,	PUNCT
ajst-30190	118	44	parietal	parietal	ADJ
ajst-30190	118	45	and	and	CCONJ
ajst-30190	118	46	occipital	occipital	NOUN
ajst-30190	118	47	lobes	lobe	NOUN
ajst-30190	118	48	had	have	VERB
ajst-30190	118	49	higher	high	ADJ
ajst-30190	118	50	classification	classification	NOUN
ajst-30190	118	51	accuracy	accuracy	NOUN
ajst-30190	118	52	.	.	PUNCT
ajst-30190	119	1	therefore	therefore	ADV
ajst-30190	119	2	,	,	PUNCT
ajst-30190	119	3	the	the	DET
ajst-30190	119	4	subsequent	subsequent	ADJ
ajst-30190	119	5	fatigue	fatigue	NOUN
ajst-30190	119	6	detection	detection	NOUN
ajst-30190	119	7	is	be	AUX
ajst-30190	119	8	mainly	mainly	ADV
ajst-30190	119	9	performed	perform	VERB
ajst-30190	119	10	on	on	ADP
ajst-30190	119	11	the	the	DET
ajst-30190	119	12	channels	channel	NOUN
ajst-30190	119	13	of	of	ADP
ajst-30190	119	14	these	these	DET
ajst-30190	119	15	three	three	NUM
ajst-30190	119	16	brain	brain	NOUN
ajst-30190	119	17	regions	region	NOUN
ajst-30190	119	18	to	to	PART
ajst-30190	119	19	find	find	VERB
ajst-30190	119	20	the	the	DET
ajst-30190	119	21	model	model	NOUN
ajst-30190	119	22	that	that	PRON
ajst-30190	119	23	can	can	AUX
ajst-30190	119	24	have	have	VERB
ajst-30190	119	25	better	well	ADJ
ajst-30190	119	26	fatigue	fatigue	NOUN
ajst-30190	119	27	detection	detection	NOUN
ajst-30190	119	28	performance	performance	NOUN
ajst-30190	119	29	for	for	ADP
ajst-30190	119	30	different	different	ADJ
ajst-30190	119	31	combinations	combination	NOUN
ajst-30190	119	32	of	of	ADP
ajst-30190	119	33	temporal	temporal	ADJ
ajst-30190	119	34	entropy	entropy	NOUN
ajst-30190	119	35	features	feature	NOUN
ajst-30190	119	36	in	in	ADP
ajst-30190	119	37	the	the	DET
ajst-30190	119	38	case	case	NOUN
ajst-30190	119	39	of	of	ADP
ajst-30190	119	40	sparse	sparse	ADJ
ajst-30190	119	41	channels	channel	NOUN
ajst-30190	119	42	.	.	PUNCT
ajst-30190	120	1	the	the	DET
ajst-30190	120	2	classifier	classifier	NOUN
ajst-30190	120	3	is	be	AUX
ajst-30190	120	4	accomplished	accomplish	VERB
ajst-30190	120	5	using	use	VERB
ajst-30190	120	6	support	support	NOUN
ajst-30190	120	7	vector	vector	NOUN
ajst-30190	120	8	machines	machine	NOUN
ajst-30190	120	9	and	and	CCONJ
ajst-30190	120	10	random	random	ADJ
ajst-30190	120	11	forests	forest	NOUN
ajst-30190	120	12	,	,	PUNCT
ajst-30190	120	13	and	and	CCONJ
ajst-30190	120	14	the	the	DET
ajst-30190	120	15	core	core	ADJ
ajst-30190	120	16	ideas	idea	NOUN
ajst-30190	120	17	of	of	ADP
ajst-30190	120	18	the	the	DET
ajst-30190	120	19	two	two	NUM
ajst-30190	120	20	classifiers	classifier	NOUN
ajst-30190	120	21	are	be	AUX
ajst-30190	120	22	briefly	briefly	ADV
ajst-30190	120	23	described	describe	VERB
ajst-30190	120	24	below	below	ADV
ajst-30190	120	25	.	.	PUNCT
ajst-30190	121	1	the	the	DET
ajst-30190	121	2	core	core	ADJ
ajst-30190	121	3	idea	idea	NOUN
ajst-30190	121	4	of	of	ADP
ajst-30190	121	5	support	support	NOUN
ajst-30190	121	6	vector	vector	NOUN
ajst-30190	121	7	machine	machine	NOUN
ajst-30190	121	8	is	be	AUX
ajst-30190	121	9	to	to	PART
ajst-30190	121	10	explore	explore	VERB
ajst-30190	121	11	an	an	DET
ajst-30190	121	12	ideal	ideal	ADJ
ajst-30190	121	13	hyperplane	hyperplane	NOUN
ajst-30190	121	14	in	in	ADP
ajst-30190	121	15	the	the	DET
ajst-30190	121	16	high	high	ADV
ajst-30190	121	17	-	-	PUNCT
ajst-30190	121	18	dimensional	dimensional	ADJ
ajst-30190	121	19	data	datum	NOUN
ajst-30190	121	20	space	space	NOUN
ajst-30190	121	21	,	,	PUNCT
ajst-30190	121	22	which	which	PRON
ajst-30190	121	23	can	can	AUX
ajst-30190	121	24	clearly	clearly	ADV
ajst-30190	121	25	delineate	delineate	VERB
ajst-30190	121	26	the	the	DET
ajst-30190	121	27	data	datum	NOUN
ajst-30190	121	28	belonging	belong	VERB
ajst-30190	121	29	to	to	ADP
ajst-30190	121	30	different	different	ADJ
ajst-30190	121	31	categories	category	NOUN
ajst-30190	121	32	.	.	PUNCT
ajst-30190	122	1	the	the	DET
ajst-30190	122	2	decision	decision	NOUN
ajst-30190	122	3	function	function	NOUN
ajst-30190	122	4	of	of	ADP
ajst-30190	122	5	the	the	DET
ajst-30190	122	6	optimal	optimal	ADJ
ajst-30190	122	7	hyperplane	hyperplane	NOUN
ajst-30190	122	8	is	be	AUX
ajst-30190	122	9	formulated	formulate	VERB
ajst-30190	122	10	as	as	SCONJ
ajst-30190	122	11	follows	follow	VERB
ajst-30190	122	12	:	:	PUNCT
ajst-30190	122	13	𝑓	𝑓	PRON
ajst-30190	122	14	𝑥	𝑥	PRON
ajst-30190	122	15	𝑠𝑔𝑛	𝑠𝑔𝑛	VERB
ajst-30190	122	16	𝑎	𝑎	X
ajst-30190	122	17	𝑦	𝑦	NOUN
ajst-30190	122	18	𝑥	𝑥	NOUN
ajst-30190	122	19	,	,	PUNCT
ajst-30190	122	20	𝑥	𝑥	PROPN
ajst-30190	122	21	𝑏	𝑏	PROPN
ajst-30190	122	22	the	the	DET
ajst-30190	122	23	core	core	ADJ
ajst-30190	122	24	idea	idea	NOUN
ajst-30190	122	25	of	of	ADP
ajst-30190	122	26	random	random	ADJ
ajst-30190	122	27	forest	forest	NOUN
ajst-30190	122	28	is	be	AUX
ajst-30190	122	29	to	to	PART
ajst-30190	122	30	draw	draw	VERB
ajst-30190	122	31	random	random	ADJ
ajst-30190	122	32	samples	sample	NOUN
ajst-30190	122	33	from	from	ADP
ajst-30190	122	34	the	the	DET
ajst-30190	122	35	training	training	NOUN
ajst-30190	122	36	set	set	NOUN
ajst-30190	122	37	and	and	CCONJ
ajst-30190	122	38	each	each	DET
ajst-30190	122	39	subset	subset	NOUN
ajst-30190	122	40	is	be	AUX
ajst-30190	122	41	used	use	VERB
ajst-30190	122	42	to	to	PART
ajst-30190	122	43	train	train	VERB
ajst-30190	122	44	a	a	DET
ajst-30190	122	45	decision	decision	NOUN
ajst-30190	122	46	tree	tree	NOUN
ajst-30190	122	47	.	.	PUNCT
ajst-30190	123	1	at	at	ADP
ajst-30190	123	2	each	each	DET
ajst-30190	123	3	node	node	NOUN
ajst-30190	123	4	of	of	ADP
ajst-30190	123	5	each	each	DET
ajst-30190	123	6	decision	decision	NOUN
ajst-30190	123	7	tree	tree	NOUN
ajst-30190	123	8	the	the	DET
ajst-30190	123	9	features	feature	NOUN
ajst-30190	123	10	to	to	PART
ajst-30190	123	11	build	build	VERB
ajst-30190	123	12	the	the	DET
ajst-30190	123	13	tree	tree	NOUN
ajst-30190	123	14	are	be	AUX
ajst-30190	123	15	randomly	randomly	ADV
ajst-30190	123	16	selected	select	VERB
ajst-30190	123	17	.	.	PUNCT
ajst-30190	124	1	for	for	ADP
ajst-30190	124	2	the	the	DET
ajst-30190	124	3	classification	classification	NOUN
ajst-30190	124	4	task	task	NOUN
ajst-30190	124	5	,	,	PUNCT
ajst-30190	124	6	assume	assume	VERB
ajst-30190	124	7	that	that	SCONJ
ajst-30190	124	8	the	the	DET
ajst-30190	124	9	random	random	ADJ
ajst-30190	124	10	forest	forest	NOUN
ajst-30190	124	11	has	have	VERB
ajst-30190	124	12	n	n	DET
ajst-30190	124	13	trees	tree	NOUN
ajst-30190	124	14	,	,	PUNCT
ajst-30190	124	15	and	and	CCONJ
ajst-30190	124	16	the	the	DET
ajst-30190	124	17	nth	nth	NOUN
ajst-30190	124	18	tree	tree	NOUN
ajst-30190	124	19	is	be	AUX
ajst-30190	124	20	predicted	predict	VERB
ajst-30190	124	21	by	by	ADP
ajst-30190	124	22	𝑦	𝑦	PRON
ajst-30190	124	23	,	,	PUNCT
ajst-30190	124	24	and	and	CCONJ
ajst-30190	124	25	the	the	DET
ajst-30190	124	26	final	final	ADJ
ajst-30190	124	27	prediction	prediction	NOUN
ajst-30190	124	28	is	be	AUX
ajst-30190	124	29	:	:	PUNCT
ajst-30190	124	30	𝑦	𝑦	NOUN
ajst-30190	124	31	𝑎𝑟𝑔𝑚𝑎𝑥	𝑎𝑟𝑔𝑚𝑎𝑥	NOUN
ajst-30190	124	32	𝐼	𝐼	ADP
ajst-30190	124	33	𝑦	𝑦	PRON
ajst-30190	124	34	𝑐	𝑐	NOUN
ajst-30190	124	35	based	base	VERB
ajst-30190	124	36	on	on	ADP
ajst-30190	124	37	the	the	DET
ajst-30190	124	38	features	feature	NOUN
ajst-30190	124	39	after	after	ADP
ajst-30190	124	40	the	the	DET
ajst-30190	124	41	screening	screening	NOUN
ajst-30190	124	42	of	of	ADP
ajst-30190	124	43	the	the	DET
ajst-30190	124	44	original	original	ADJ
ajst-30190	124	45	signal	signal	NOUN
ajst-30190	124	46	,	,	PUNCT
ajst-30190	124	47	this	this	DET
ajst-30190	124	48	paper	paper	NOUN
ajst-30190	124	49	retains	retain	VERB
ajst-30190	124	50	the	the	DET
ajst-30190	124	51	feature	feature	NOUN
ajst-30190	124	52	information	information	NOUN
ajst-30190	124	53	with	with	ADP
ajst-30190	124	54	a	a	DET
ajst-30190	124	55	total	total	NOUN
ajst-30190	124	56	of	of	ADP
ajst-30190	124	57	11	11	NUM
ajst-30190	124	58	dimensions	dimension	NOUN
ajst-30190	124	59	of	of	ADP
ajst-30190	124	60	time	time	NOUN
ajst-30190	124	61	-	-	PUNCT
ajst-30190	124	62	frequency	frequency	NOUN
ajst-30190	124	63	entropy	entropy	NOUN
ajst-30190	124	64	,	,	PUNCT
ajst-30190	124	65	and	and	CCONJ
ajst-30190	124	66	uses	use	VERB
ajst-30190	124	67	2	2	NUM
ajst-30190	124	68	classifiers	classifier	NOUN
ajst-30190	124	69	for	for	ADP
ajst-30190	124	70	fatigue	fatigue	NOUN
ajst-30190	124	71	detection	detection	NOUN
ajst-30190	124	72	of	of	ADP
ajst-30190	124	73	the	the	DET
ajst-30190	124	74	remaining	remain	VERB
ajst-30190	124	75	features	feature	NOUN
ajst-30190	124	76	.	.	PUNCT
ajst-30190	125	1	the	the	DET
ajst-30190	125	2	penalty	penalty	NOUN
ajst-30190	125	3	parameter	parameter	NOUN
ajst-30190	125	4	c	c	PROPN
ajst-30190	125	5	of	of	ADP
ajst-30190	125	6	svm	svm	PROPN
ajst-30190	125	7	is	be	AUX
ajst-30190	125	8	set	set	VERB
ajst-30190	125	9	to	to	ADP
ajst-30190	125	10	10	10	NUM
ajst-30190	125	11	,	,	PUNCT
ajst-30190	125	12	the	the	DET
ajst-30190	125	13	kernel	kernel	PROPN
ajst-30190	125	14	function	function	PROPN
ajst-30190	125	15	selects	select	VERB
ajst-30190	125	16	radial	radial	ADJ
ajst-30190	125	17	basis	basis	NOUN
ajst-30190	125	18	kernel	kernel	NOUN
ajst-30190	125	19	function	function	NOUN
ajst-30190	125	20	,	,	PUNCT
ajst-30190	125	21	and	and	CCONJ
ajst-30190	125	22	the	the	DET
ajst-30190	125	23	gamma	gamma	PROPN
ajst-30190	125	24	parameter	parameter	NOUN
ajst-30190	125	25	is	be	AUX
ajst-30190	125	26	set	set	VERB
ajst-30190	125	27	to	to	ADP
ajst-30190	125	28	0.02	0.02	NUM
ajst-30190	125	29	.	.	PUNCT
ajst-30190	126	1	the	the	DET
ajst-30190	126	2	number	number	NOUN
ajst-30190	126	3	of	of	ADP
ajst-30190	126	4	n_estimators	n_estimator	NOUN
ajst-30190	126	5	decision	decision	VERB
ajst-30190	126	6	tree	tree	NOUN
ajst-30190	126	7	of	of	ADP
ajst-30190	126	8	rf	rf	PRON
ajst-30190	126	9	is	be	AUX
ajst-30190	126	10	selected	select	VERB
ajst-30190	126	11	to	to	PART
ajst-30190	126	12	be	be	AUX
ajst-30190	126	13	30	30	NUM
ajst-30190	126	14	,	,	PUNCT
ajst-30190	126	15	the	the	DET
ajst-30190	126	16	maximum	maximum	ADJ
ajst-30190	126	17	depth	depth	NOUN
ajst-30190	126	18	of	of	ADP
ajst-30190	126	19	max_depth	max_depth	NOUN
ajst-30190	126	20	decision	decision	NOUN
ajst-30190	126	21	tree	tree	NOUN
ajst-30190	126	22	is	be	AUX
ajst-30190	126	23	set	set	VERB
ajst-30190	126	24	to	to	PART
ajst-30190	126	25	be	be	AUX
ajst-30190	126	26	10	10	NUM
ajst-30190	126	27	,	,	PUNCT
ajst-30190	126	28	the	the	DET
ajst-30190	126	29	minimum	minimum	ADJ
ajst-30190	126	30	number	number	NOUN
ajst-30190	126	31	of	of	ADP
ajst-30190	126	32	samples	sample	NOUN
ajst-30190	126	33	inside	inside	ADP
ajst-30190	126	34	min_samples_split	min_samples_split	NOUN
ajst-30190	126	35	is	be	AUX
ajst-30190	126	36	set	set	VERB
ajst-30190	126	37	to	to	PART
ajst-30190	126	38	be	be	AUX
ajst-30190	126	39	5	5	NUM
ajst-30190	126	40	,	,	PUNCT
ajst-30190	126	41	and	and	CCONJ
ajst-30190	126	42	the	the	DET
ajst-30190	126	43	learning	learning	NOUN
ajst-30190	126	44	rate	rate	NOUN
ajst-30190	126	45	is	be	AUX
ajst-30190	126	46	set	set	VERB
ajst-30190	126	47	to	to	PART
ajst-30190	126	48	be	be	AUX
ajst-30190	126	49	0.02	0.02	NUM
ajst-30190	126	50	.	.	PUNCT
ajst-30190	127	1	the	the	DET
ajst-30190	127	2	time	time	NOUN
ajst-30190	127	3	-	-	PUNCT
ajst-30190	127	4	frequency	frequency	NOUN
ajst-30190	127	5	entropy	entropy	NOUN
ajst-30190	127	6	features	feature	NOUN
ajst-30190	127	7	are	be	AUX
ajst-30190	127	8	categorized	categorize	VERB
ajst-30190	127	9	into	into	ADP
ajst-30190	127	10	ha	ha	INTJ
ajst-30190	127	11	and	and	CCONJ
ajst-30190	127	12	hm	hm	INTJ
ajst-30190	127	13	,	,	PUNCT
ajst-30190	127	14	psd	psd	PROPN
ajst-30190	127	15	,	,	PUNCT
ajst-30190	127	16	ae	ae	PROPN
ajst-30190	127	17	,	,	PUNCT
ajst-30190	127	18	se	se	ADV
ajst-30190	127	19	,	,	PUNCT
ajst-30190	127	20	pe	pe	INTJ
ajst-30190	128	1	and	and	CCONJ
ajst-30190	128	2	we	we	PRON
ajst-30190	128	3	are	be	AUX
ajst-30190	128	4	combined	combine	VERB
ajst-30190	128	5	into	into	ADP
ajst-30190	128	6	8	8	NUM
ajst-30190	128	7	feature	feature	NOUN
ajst-30190	128	8	combinations	combination	NOUN
ajst-30190	128	9	,	,	PUNCT
ajst-30190	128	10	which	which	PRON
ajst-30190	128	11	are	be	AUX
ajst-30190	128	12	classified	classify	VERB
ajst-30190	128	13	and	and	CCONJ
ajst-30190	128	14	compared	compare	VERB
ajst-30190	128	15	with	with	ADP
ajst-30190	128	16	svm	svm	ADJ
ajst-30190	128	17	and	and	CCONJ
ajst-30190	128	18	rf	rf	NOUN
ajst-30190	128	19	classifiers	classifier	NOUN
ajst-30190	128	20	respectively	respectively	ADV
ajst-30190	128	21	,	,	PUNCT
ajst-30190	128	22	as	as	SCONJ
ajst-30190	128	23	shown	show	VERB
ajst-30190	128	24	in	in	ADP
ajst-30190	128	25	figure	figure	NOUN
ajst-30190	128	26	4.3	4.3	NUM
ajst-30190	128	27	below	below	ADV
ajst-30190	128	28	.	.	PUNCT
ajst-30190	129	1	figure	figure	VERB
ajst-30190	129	2	4.3	4.3	NUM
ajst-30190	129	3	comparison	comparison	NOUN
ajst-30190	129	4	of	of	ADP
ajst-30190	129	5	classification	classification	NOUN
ajst-30190	129	6	accuracy	accuracy	NOUN
ajst-30190	129	7	of	of	ADP
ajst-30190	129	8	svm	svm	PROPN
ajst-30190	129	9	and	and	CCONJ
ajst-30190	129	10	rf	rf	VERB
ajst-30190	129	11	for	for	ADP
ajst-30190	129	12	different	different	ADJ
ajst-30190	129	13	channels	channel	NOUN
ajst-30190	129	14	and	and	CCONJ
ajst-30190	129	15	combinations	combination	NOUN
ajst-30190	129	16	of	of	ADP
ajst-30190	129	17	features	feature	NOUN
ajst-30190	129	18	as	as	SCONJ
ajst-30190	129	19	can	can	AUX
ajst-30190	129	20	be	be	AUX
ajst-30190	129	21	seen	see	VERB
ajst-30190	129	22	in	in	ADP
ajst-30190	129	23	figure	figure	NOUN
ajst-30190	129	24	4.3	4.3	NUM
ajst-30190	129	25	,	,	PUNCT
ajst-30190	129	26	it	it	PRON
ajst-30190	129	27	can	can	AUX
ajst-30190	129	28	be	be	AUX
ajst-30190	129	29	seen	see	VERB
ajst-30190	129	30	that	that	SCONJ
ajst-30190	129	31	the	the	DET
ajst-30190	129	32	accuracy	accuracy	NOUN
ajst-30190	129	33	of	of	ADP
ajst-30190	129	34	the	the	DET
ajst-30190	129	35	frontal	frontal	ADJ
ajst-30190	129	36	and	and	CCONJ
ajst-30190	129	37	occipital	occipital	NOUN
ajst-30190	129	38	lobes	lobe	NOUN
ajst-30190	129	39	is	be	AUX
ajst-30190	129	40	slightly	slightly	ADV
ajst-30190	129	41	higher	high	ADJ
ajst-30190	129	42	than	than	ADP
ajst-30190	129	43	that	that	PRON
ajst-30190	129	44	of	of	ADP
ajst-30190	129	45	the	the	DET
ajst-30190	129	46	parietal	parietal	ADJ
ajst-30190	129	47	lobe	lobe	NOUN
ajst-30190	129	48	,	,	PUNCT
ajst-30190	129	49	and	and	CCONJ
ajst-30190	129	50	the	the	DET
ajst-30190	129	51	best	good	ADJ
ajst-30190	129	52	feature	feature	NOUN
ajst-30190	129	53	combinations	combination	NOUN
ajst-30190	129	54	for	for	ADP
ajst-30190	129	55	classification	classification	NOUN
ajst-30190	129	56	are	be	AUX
ajst-30190	129	57	hm	hm	INTJ
ajst-30190	129	58	+	+	NUM
ajst-30190	129	59	psd	psd	PROPN
ajst-30190	130	1	+	+	CCONJ
ajst-30190	130	2	pe	pe	PROPN
ajst-30190	131	1	and	and	CCONJ
ajst-30190	131	2	hm	hm	INTJ
ajst-30190	132	1	+	+	CCONJ
ajst-30190	132	2	psd	psd	NOUN
ajst-30190	132	3	+	+	CCONJ
ajst-30190	132	4	we	we	PRON
ajst-30190	132	5	,	,	PUNCT
ajst-30190	132	6	followed	follow	VERB
ajst-30190	132	7	by	by	ADP
ajst-30190	132	8	ha	ha	INTJ
ajst-30190	132	9	+	+	X
ajst-30190	132	10	psd	psd	PROPN
ajst-30190	132	11	+	+	CCONJ
ajst-30190	132	12	pe	pe	PROPN
ajst-30190	132	13	and	and	CCONJ
ajst-30190	132	14	ha	ha	INTJ
ajst-30190	133	1	+	+	NUM
ajst-30190	133	2	psd	psd	NOUN
ajst-30190	134	1	+	+	CCONJ
ajst-30190	134	2	we	we	PRON
ajst-30190	134	3	.	.	PUNCT
ajst-30190	135	1	this	this	PRON
ajst-30190	135	2	indicates	indicate	VERB
ajst-30190	135	3	that	that	SCONJ
ajst-30190	135	4	the	the	DET
ajst-30190	135	5	feature	feature	NOUN
ajst-30190	135	6	combinations	combination	NOUN
ajst-30190	135	7	of	of	ADP
ajst-30190	135	8	hjorth	hjorth	NOUN
ajst-30190	135	9	parameter	parameter	NOUN
ajst-30190	135	10	,	,	PUNCT
ajst-30190	135	11	power	power	NOUN
ajst-30190	135	12	spectral	spectral	ADJ
ajst-30190	135	13	density	density	NOUN
ajst-30190	135	14	with	with	ADP
ajst-30190	135	15	fuzzy	fuzzy	ADJ
ajst-30190	135	16	entropy	entropy	NOUN
ajst-30190	135	17	and	and	CCONJ
ajst-30190	135	18	wavelet	wavelet	NOUN
ajst-30190	135	19	entropy	entropy	NOUN
ajst-30190	135	20	for	for	ADP
ajst-30190	135	21	frontal	frontal	ADJ
ajst-30190	135	22	and	and	CCONJ
ajst-30190	135	23	occipital	occipital	NOUN
ajst-30190	135	24	lobes	lobe	NOUN
ajst-30190	135	25	have	have	VERB
ajst-30190	135	26	obvious	obvious	ADJ
ajst-30190	135	27	advantages	advantage	NOUN
ajst-30190	135	28	in	in	ADP
ajst-30190	135	29	fatigue	fatigue	NOUN
ajst-30190	135	30	detection	detection	NOUN
ajst-30190	135	31	in	in	ADP
ajst-30190	135	32	this	this	DET
ajst-30190	135	33	paper	paper	NOUN
ajst-30190	135	34	.	.	PUNCT
ajst-30190	136	1	5	5	X
ajst-30190	136	2	.	.	X
ajst-30190	136	3	conclusion	conclusion	NOUN
ajst-30190	136	4	in	in	ADP
ajst-30190	136	5	today	today	NOUN
ajst-30190	136	6	's	's	PART
ajst-30190	136	7	neuroscience	neuroscience	NOUN
ajst-30190	136	8	and	and	CCONJ
ajst-30190	136	9	brain	brain	NOUN
ajst-30190	136	10	-	-	PUNCT
ajst-30190	136	11	computer	computer	NOUN
ajst-30190	136	12	interface	interface	NOUN
ajst-30190	136	13	research	research	NOUN
ajst-30190	136	14	field	field	NOUN
ajst-30190	136	15	,	,	PUNCT
ajst-30190	136	16	the	the	DET
ajst-30190	136	17	characterization	characterization	NOUN
ajst-30190	136	18	of	of	ADP
ajst-30190	136	19	fatigue	fatigue	NOUN
ajst-30190	136	20	eeg	eeg	NOUN
ajst-30190	136	21	is	be	AUX
ajst-30190	136	22	becoming	become	VERB
ajst-30190	136	23	more	more	ADV
ajst-30190	136	24	and	and	CCONJ
ajst-30190	136	25	more	more	ADV
ajst-30190	136	26	important	important	ADJ
ajst-30190	136	27	.	.	PUNCT
ajst-30190	137	1	fatigue	fatigue	NOUN
ajst-30190	137	2	state	state	NOUN
ajst-30190	137	3	in	in	ADP
ajst-30190	137	4	special	special	ADJ
ajst-30190	137	5	scenarios	scenario	NOUN
ajst-30190	137	6	such	such	ADJ
ajst-30190	137	7	as	as	ADP
ajst-30190	137	8	driving	drive	VERB
ajst-30190	137	9	and	and	CCONJ
ajst-30190	137	10	working	work	VERB
ajst-30190	137	11	at	at	ADP
ajst-30190	137	12	heights	height	NOUN
ajst-30190	137	13	not	not	PART
ajst-30190	137	14	only	only	ADV
ajst-30190	137	15	affects	affect	VERB
ajst-30190	137	16	the	the	DET
ajst-30190	137	17	daily	daily	ADJ
ajst-30190	137	18	life	life	NOUN
ajst-30190	137	19	of	of	ADP
ajst-30190	137	20	an	an	DET
ajst-30190	137	21	individual	individual	NOUN
ajst-30190	137	22	,	,	PUNCT
ajst-30190	137	23	but	but	CCONJ
ajst-30190	137	24	also	also	ADV
ajst-30190	137	25	may	may	AUX
ajst-30190	137	26	lead	lead	VERB
ajst-30190	137	27	to	to	ADP
ajst-30190	137	28	149	149	NUM
ajst-30190	137	29	safety	safety	NOUN
ajst-30190	137	30	hazards	hazard	NOUN
ajst-30190	137	31	in	in	ADP
ajst-30190	137	32	serious	serious	ADJ
ajst-30190	137	33	cases	case	NOUN
ajst-30190	137	34	,	,	PUNCT
ajst-30190	137	35	so	so	SCONJ
ajst-30190	137	36	it	it	PRON
ajst-30190	137	37	is	be	AUX
ajst-30190	137	38	of	of	ADP
ajst-30190	137	39	crucial	crucial	ADJ
ajst-30190	137	40	importance	importance	NOUN
ajst-30190	137	41	to	to	PART
ajst-30190	137	42	accurately	accurately	ADV
ajst-30190	137	43	recognize	recognize	VERB
ajst-30190	137	44	fatigue	fatigue	NOUN
ajst-30190	137	45	eeg	eeg	NOUN
ajst-30190	137	46	signals	signal	NOUN
ajst-30190	137	47	.	.	PUNCT
ajst-30190	138	1	in	in	ADP
ajst-30190	138	2	this	this	DET
ajst-30190	138	3	paper	paper	NOUN
ajst-30190	138	4	,	,	PUNCT
ajst-30190	138	5	16	16	NUM
ajst-30190	138	6	subjects	subject	NOUN
ajst-30190	138	7	were	be	AUX
ajst-30190	138	8	selected	select	VERB
ajst-30190	138	9	to	to	PART
ajst-30190	138	10	participate	participate	VERB
ajst-30190	138	11	in	in	ADP
ajst-30190	138	12	a	a	DET
ajst-30190	138	13	1	1	NUM
ajst-30190	138	14	back	back	NOUN
ajst-30190	138	15	task	task	NOUN
ajst-30190	138	16	paradigm	paradigm	NOUN
ajst-30190	138	17	to	to	PART
ajst-30190	138	18	induce	induce	VERB
ajst-30190	138	19	their	their	PRON
ajst-30190	138	20	fatigue	fatigue	NOUN
ajst-30190	138	21	eeg	eeg	NOUN
ajst-30190	138	22	state	state	NOUN
ajst-30190	138	23	,	,	PUNCT
ajst-30190	138	24	in	in	ADP
ajst-30190	138	25	which	which	PRON
ajst-30190	138	26	subjects	subject	NOUN
ajst-30190	138	27	were	be	AUX
ajst-30190	138	28	asked	ask	VERB
ajst-30190	138	29	to	to	PART
ajst-30190	138	30	judge	judge	VERB
ajst-30190	138	31	whether	whether	SCONJ
ajst-30190	138	32	the	the	DET
ajst-30190	138	33	previous	previous	ADJ
ajst-30190	138	34	stimulus	stimulus	NOUN
ajst-30190	138	35	was	be	AUX
ajst-30190	138	36	the	the	DET
ajst-30190	138	37	same	same	ADJ
ajst-30190	138	38	as	as	ADP
ajst-30190	138	39	the	the	DET
ajst-30190	138	40	current	current	ADJ
ajst-30190	138	41	stimulus	stimulus	NOUN
ajst-30190	138	42	and	and	CCONJ
ajst-30190	138	43	give	give	VERB
ajst-30190	138	44	a	a	DET
ajst-30190	138	45	response	response	NOUN
ajst-30190	138	46	.	.	PUNCT
ajst-30190	139	1	as	as	SCONJ
ajst-30190	139	2	the	the	DET
ajst-30190	139	3	task	task	NOUN
ajst-30190	139	4	progressed	progress	VERB
ajst-30190	139	5	,	,	PUNCT
ajst-30190	139	6	the	the	DET
ajst-30190	139	7	subjects	subject	NOUN
ajst-30190	139	8	'	'	PART
ajst-30190	139	9	visual	visual	ADJ
ajst-30190	139	10	and	and	CCONJ
ajst-30190	139	11	central	central	ADJ
ajst-30190	139	12	nervous	nervous	ADJ
ajst-30190	139	13	system	system	NOUN
ajst-30190	139	14	were	be	AUX
ajst-30190	139	15	highly	highly	ADV
ajst-30190	139	16	focused	focused	ADJ
ajst-30190	139	17	,	,	PUNCT
ajst-30190	139	18	which	which	PRON
ajst-30190	139	19	led	lead	VERB
ajst-30190	139	20	to	to	ADP
ajst-30190	139	21	the	the	DET
ajst-30190	139	22	presentation	presentation	NOUN
ajst-30190	139	23	of	of	ADP
ajst-30190	139	24	eeg	eeg	NOUN
ajst-30190	139	25	signals	signal	NOUN
ajst-30190	139	26	specific	specific	ADJ
ajst-30190	139	27	to	to	ADP
ajst-30190	139	28	the	the	DET
ajst-30190	139	29	fatigued	fatigued	ADJ
ajst-30190	139	30	state	state	NOUN
ajst-30190	139	31	.	.	PUNCT
ajst-30190	140	1	based	base	VERB
ajst-30190	140	2	on	on	ADP
ajst-30190	140	3	the	the	DET
ajst-30190	140	4	average	average	ADJ
ajst-30190	140	5	reaction	reaction	NOUN
ajst-30190	140	6	time	time	NOUN
ajst-30190	140	7	and	and	CCONJ
ajst-30190	140	8	average	average	ADJ
ajst-30190	140	9	correct	correct	ADJ
ajst-30190	140	10	response	response	NOUN
ajst-30190	140	11	rate	rate	NOUN
ajst-30190	140	12	combined	combine	VERB
ajst-30190	140	13	with	with	ADP
ajst-30190	140	14	the	the	DET
ajst-30190	140	15	fatigue	fatigue	NOUN
ajst-30190	140	16	index	index	NOUN
ajst-30190	140	17	value	value	NOUN
ajst-30190	140	18	f	f	PROPN
ajst-30190	140	19	as	as	SCONJ
ajst-30190	140	20	the	the	DET
ajst-30190	140	21	objective	objective	ADJ
ajst-30190	140	22	assessment	assessment	NOUN
ajst-30190	140	23	results	result	VERB
ajst-30190	140	24	,	,	PUNCT
ajst-30190	140	25	the	the	DET
ajst-30190	140	26	trend	trend	NOUN
ajst-30190	140	27	of	of	ADP
ajst-30190	140	28	change	change	NOUN
ajst-30190	140	29	is	be	AUX
ajst-30190	140	30	consistent	consistent	ADJ
ajst-30190	140	31	with	with	ADP
ajst-30190	140	32	the	the	DET
ajst-30190	140	33	subjective	subjective	ADJ
ajst-30190	140	34	assessment	assessment	NOUN
ajst-30190	140	35	of	of	ADP
ajst-30190	140	36	the	the	DET
ajst-30190	140	37	kss	kss	PROPN
ajst-30190	140	38	scale	scale	NOUN
ajst-30190	140	39	,	,	PUNCT
ajst-30190	140	40	which	which	PRON
ajst-30190	140	41	proves	prove	VERB
ajst-30190	140	42	that	that	SCONJ
ajst-30190	140	43	brain	brain	NOUN
ajst-30190	140	44	fatigue	fatigue	NOUN
ajst-30190	140	45	has	have	AUX
ajst-30190	140	46	been	be	AUX
ajst-30190	140	47	successfully	successfully	ADV
ajst-30190	140	48	induced	induce	VERB
ajst-30190	140	49	.	.	PUNCT
ajst-30190	141	1	in	in	ADP
ajst-30190	141	2	order	order	NOUN
ajst-30190	141	3	to	to	PART
ajst-30190	141	4	extract	extract	VERB
ajst-30190	141	5	effective	effective	ADJ
ajst-30190	141	6	features	feature	NOUN
ajst-30190	141	7	from	from	ADP
ajst-30190	141	8	complex	complex	ADJ
ajst-30190	141	9	eeg	eeg	PROPN
ajst-30190	141	10	data	datum	NOUN
ajst-30190	141	11	,	,	PUNCT
ajst-30190	141	12	this	this	DET
ajst-30190	141	13	paper	paper	NOUN
ajst-30190	141	14	adds	add	VERB
ajst-30190	141	15	a	a	DET
ajst-30190	141	16	convolution	convolution	NOUN
ajst-30190	141	17	operation	operation	NOUN
ajst-30190	141	18	to	to	ADP
ajst-30190	141	19	the	the	DET
ajst-30190	141	20	restricted	restricted	ADJ
ajst-30190	141	21	boltzmann	boltzmann	PROPN
ajst-30190	141	22	machine	machine	NOUN
ajst-30190	141	23	,	,	PUNCT
ajst-30190	141	24	aiming	aim	VERB
ajst-30190	141	25	to	to	PART
ajst-30190	141	26	use	use	VERB
ajst-30190	141	27	convolution	convolution	NOUN
ajst-30190	141	28	operations	operation	NOUN
ajst-30190	141	29	to	to	PART
ajst-30190	141	30	better	well	ADV
ajst-30190	141	31	identify	identify	VERB
ajst-30190	141	32	features	feature	NOUN
ajst-30190	141	33	in	in	ADP
ajst-30190	141	34	localized	localized	ADJ
ajst-30190	141	35	regions	region	NOUN
ajst-30190	141	36	.	.	PUNCT
ajst-30190	142	1	pca	pca	PROPN
ajst-30190	142	2	and	and	CCONJ
ajst-30190	142	3	pearson	pearson	PROPN
ajst-30190	142	4	's	's	PART
ajst-30190	142	5	coefficient	coefficient	NOUN
ajst-30190	142	6	are	be	AUX
ajst-30190	142	7	applied	apply	VERB
ajst-30190	142	8	to	to	PART
ajst-30190	142	9	correlate	correlate	VERB
ajst-30190	142	10	the	the	DET
ajst-30190	142	11	features	feature	NOUN
ajst-30190	142	12	,	,	PUNCT
ajst-30190	142	13	remove	remove	VERB
ajst-30190	142	14	redundant	redundant	ADJ
ajst-30190	142	15	features	feature	NOUN
ajst-30190	142	16	,	,	PUNCT
ajst-30190	142	17	filter	filter	VERB
ajst-30190	142	18	out	out	ADP
ajst-30190	142	19	the	the	DET
ajst-30190	142	20	features	feature	NOUN
ajst-30190	142	21	that	that	PRON
ajst-30190	142	22	are	be	AUX
ajst-30190	142	23	highly	highly	ADV
ajst-30190	142	24	correlated	correlate	VERB
ajst-30190	142	25	with	with	ADP
ajst-30190	142	26	fatigue	fatigue	NOUN
ajst-30190	142	27	eeg	eeg	NOUN
ajst-30190	142	28	,	,	PUNCT
ajst-30190	142	29	and	and	CCONJ
ajst-30190	142	30	select	select	VERB
ajst-30190	142	31	the	the	DET
ajst-30190	142	32	timefrequency	timefrequency	NOUN
ajst-30190	142	33	entropy	entropy	NOUN
ajst-30190	142	34	features	feature	NOUN
ajst-30190	142	35	of	of	ADP
ajst-30190	142	36	frontal	frontal	ADJ
ajst-30190	142	37	,	,	PUNCT
ajst-30190	142	38	parietal	parietal	ADJ
ajst-30190	142	39	,	,	PUNCT
ajst-30190	142	40	and	and	CCONJ
ajst-30190	142	41	occipital	occipital	NOUN
ajst-30190	142	42	lobes	lobe	NOUN
ajst-30190	142	43	as	as	SCONJ
ajst-30190	142	44	the	the	DET
ajst-30190	142	45	input	input	NOUN
ajst-30190	142	46	features	feature	VERB
ajst-30190	142	47	for	for	ADP
ajst-30190	142	48	classification	classification	NOUN
ajst-30190	142	49	and	and	CCONJ
ajst-30190	142	50	recognition	recognition	NOUN
ajst-30190	142	51	.	.	PUNCT
ajst-30190	143	1	afterwards	afterwards	ADV
ajst-30190	143	2	,	,	PUNCT
ajst-30190	143	3	the	the	DET
ajst-30190	143	4	convolutional	convolutional	ADJ
ajst-30190	143	5	neural	neural	ADJ
ajst-30190	143	6	network	network	NOUN
ajst-30190	143	7	(	(	PUNCT
ajst-30190	143	8	cnn	cnn	PROPN
ajst-30190	143	9	)	)	PUNCT
ajst-30190	143	10	classifier	classifier	NOUN
ajst-30190	143	11	was	be	AUX
ajst-30190	143	12	trained	train	VERB
ajst-30190	143	13	based	base	VERB
ajst-30190	143	14	on	on	ADP
ajst-30190	143	15	self	self	NOUN
ajst-30190	143	16	-	-	PUNCT
ajst-30190	143	17	training	training	NOUN
ajst-30190	143	18	and	and	CCONJ
ajst-30190	143	19	semisupervised	semisupervised	ADJ
ajst-30190	143	20	learning	learning	NOUN
ajst-30190	143	21	,	,	PUNCT
ajst-30190	143	22	making	make	VERB
ajst-30190	143	23	full	full	ADJ
ajst-30190	143	24	use	use	NOUN
ajst-30190	143	25	of	of	ADP
ajst-30190	143	26	a	a	DET
ajst-30190	143	27	small	small	ADJ
ajst-30190	143	28	number	number	NOUN
ajst-30190	143	29	of	of	ADP
ajst-30190	143	30	labeled	label	VERB
ajst-30190	143	31	samples	sample	NOUN
ajst-30190	143	32	and	and	CCONJ
ajst-30190	143	33	a	a	DET
ajst-30190	143	34	large	large	ADJ
ajst-30190	143	35	number	number	NOUN
ajst-30190	143	36	of	of	ADP
ajst-30190	143	37	unlabeled	unlabeled	ADJ
ajst-30190	143	38	samples	sample	NOUN
ajst-30190	143	39	,	,	PUNCT
ajst-30190	143	40	and	and	CCONJ
ajst-30190	143	41	repeatedly	repeatedly	ADV
ajst-30190	143	42	iterating	iterate	VERB
ajst-30190	143	43	to	to	PART
ajst-30190	143	44	optimize	optimize	VERB
ajst-30190	143	45	its	its	PRON
ajst-30190	143	46	own	own	ADJ
ajst-30190	143	47	weight	weight	NOUN
ajst-30190	143	48	parameters	parameter	NOUN
ajst-30190	143	49	,	,	PUNCT
ajst-30190	143	50	so	so	SCONJ
ajst-30190	143	51	that	that	SCONJ
ajst-30190	143	52	the	the	DET
ajst-30190	143	53	average	average	ADJ
ajst-30190	143	54	classification	classification	NOUN
ajst-30190	143	55	accuracies	accuracy	NOUN
ajst-30190	143	56	of	of	ADP
ajst-30190	143	57	frontal	frontal	ADJ
ajst-30190	143	58	,	,	PUNCT
ajst-30190	143	59	parietal	parietal	ADJ
ajst-30190	143	60	,	,	PUNCT
ajst-30190	143	61	and	and	CCONJ
ajst-30190	143	62	occipital	occipital	NOUN
ajst-30190	143	63	eeg	eeg	NOUN
ajst-30190	143	64	signals	signal	NOUN
ajst-30190	143	65	finally	finally	ADV
ajst-30190	143	66	reached	reach	VERB
ajst-30190	143	67	89	89	NUM
ajst-30190	143	68	%	%	NOUN
ajst-30190	143	69	,	,	PUNCT
ajst-30190	143	70	87	87	NUM
ajst-30190	143	71	%	%	NOUN
ajst-30190	143	72	,	,	PUNCT
ajst-30190	143	73	and	and	CCONJ
ajst-30190	143	74	91	91	NUM
ajst-30190	143	75	%	%	NOUN
ajst-30190	143	76	,	,	PUNCT
ajst-30190	143	77	respectively	respectively	ADV
ajst-30190	143	78	.	.	PUNCT
ajst-30190	144	1	on	on	ADP
ajst-30190	144	2	this	this	DET
ajst-30190	144	3	basis	basis	NOUN
ajst-30190	144	4	,	,	PUNCT
ajst-30190	144	5	support	support	VERB
ajst-30190	144	6	vector	vector	NOUN
ajst-30190	144	7	machine	machine	NOUN
ajst-30190	144	8	(	(	PUNCT
ajst-30190	144	9	svm	svm	PROPN
ajst-30190	144	10	)	)	PUNCT
ajst-30190	144	11	and	and	CCONJ
ajst-30190	144	12	random	random	ADJ
ajst-30190	144	13	forest	forest	NOUN
ajst-30190	144	14	(	(	PUNCT
ajst-30190	144	15	rf	rf	NOUN
ajst-30190	144	16	)	)	PUNCT
ajst-30190	144	17	classifiers	classifier	NOUN
ajst-30190	144	18	were	be	AUX
ajst-30190	144	19	further	far	ADV
ajst-30190	144	20	used	use	VERB
ajst-30190	144	21	to	to	PART
ajst-30190	144	22	reclassify	reclassify	VERB
ajst-30190	144	23	the	the	DET
ajst-30190	144	24	time	time	NOUN
ajst-30190	144	25	-	-	PUNCT
ajst-30190	144	26	frequency	frequency	NOUN
ajst-30190	144	27	entropy	entropy	NOUN
ajst-30190	144	28	feature	feature	NOUN
ajst-30190	144	29	combinations	combination	NOUN
ajst-30190	144	30	after	after	ADP
ajst-30190	144	31	feature	feature	NOUN
ajst-30190	144	32	selection	selection	NOUN
ajst-30190	144	33	,	,	PUNCT
ajst-30190	144	34	aiming	aim	VERB
ajst-30190	144	35	to	to	PART
ajst-30190	144	36	find	find	VERB
ajst-30190	144	37	more	more	ADV
ajst-30190	144	38	explicit	explicit	ADJ
ajst-30190	144	39	feature	feature	NOUN
ajst-30190	144	40	combinations	combination	NOUN
ajst-30190	144	41	with	with	ADP
ajst-30190	144	42	higher	high	ADJ
ajst-30190	144	43	classification	classification	NOUN
ajst-30190	144	44	accuracy	accuracy	NOUN
ajst-30190	144	45	.	.	PUNCT
ajst-30190	145	1	the	the	DET
ajst-30190	145	2	experimental	experimental	ADJ
ajst-30190	145	3	results	result	NOUN
ajst-30190	145	4	show	show	VERB
ajst-30190	145	5	that	that	SCONJ
ajst-30190	145	6	the	the	DET
ajst-30190	145	7	frontal	frontal	ADJ
ajst-30190	145	8	and	and	CCONJ
ajst-30190	145	9	occipital	occipital	ADJ
ajst-30190	145	10	regions	region	NOUN
ajst-30190	145	11	perform	perform	VERB
ajst-30190	145	12	slightly	slightly	ADV
ajst-30190	145	13	better	well	ADJ
ajst-30190	145	14	than	than	ADP
ajst-30190	145	15	the	the	DET
ajst-30190	145	16	parietal	parietal	ADJ
ajst-30190	145	17	lobe	lobe	NOUN
ajst-30190	145	18	in	in	ADP
ajst-30190	145	19	terms	term	NOUN
ajst-30190	145	20	of	of	ADP
ajst-30190	145	21	classification	classification	NOUN
ajst-30190	145	22	accuracy	accuracy	NOUN
ajst-30190	145	23	,	,	PUNCT
ajst-30190	145	24	especially	especially	ADV
ajst-30190	145	25	for	for	ADP
ajst-30190	145	26	the	the	DET
ajst-30190	145	27	two	two	NUM
ajst-30190	145	28	feature	feature	NOUN
ajst-30190	145	29	combinations	combination	NOUN
ajst-30190	145	30	of	of	ADP
ajst-30190	145	31	hm	hm	INTJ
ajst-30190	145	32	+	+	CCONJ
ajst-30190	145	33	psd	psd	PROPN
ajst-30190	145	34	+	+	CCONJ
ajst-30190	145	35	pe	pe	PROPN
ajst-30190	146	1	and	and	CCONJ
ajst-30190	146	2	hm	hm	INTJ
ajst-30190	147	1	+	+	CCONJ
ajst-30190	147	2	psd	psd	NOUN
ajst-30190	148	1	+	+	CCONJ
ajst-30190	148	2	we	we	PRON
ajst-30190	148	3	.	.	PUNCT
ajst-30190	149	1	svm	svm	PROPN
ajst-30190	149	2	achieves	achieve	VERB
ajst-30190	149	3	a	a	DET
ajst-30190	149	4	classification	classification	NOUN
ajst-30190	149	5	accuracy	accuracy	NOUN
ajst-30190	149	6	of	of	ADP
ajst-30190	149	7	93	93	NUM
ajst-30190	149	8	%	%	NOUN
ajst-30190	149	9	for	for	ADP
ajst-30190	149	10	the	the	DET
ajst-30190	149	11	occipital	occipital	NOUN
ajst-30190	149	12	lobe	lobe	VERB
ajst-30190	149	13	with	with	ADP
ajst-30190	149	14	hm	hm	INTJ
ajst-30190	150	1	+	+	CCONJ
ajst-30190	150	2	psd	psd	PROPN
ajst-30190	150	3	+	+	CCONJ
ajst-30190	150	4	pe	pe	PROPN
ajst-30190	150	5	,	,	PUNCT
ajst-30190	150	6	and	and	CCONJ
ajst-30190	150	7	rf	rf	PRON
ajst-30190	150	8	achieves	achieve	VERB
ajst-30190	150	9	a	a	DET
ajst-30190	150	10	classification	classification	NOUN
ajst-30190	150	11	accuracy	accuracy	NOUN
ajst-30190	150	12	of	of	ADP
ajst-30190	150	13	92	92	NUM
ajst-30190	150	14	%	%	NOUN
ajst-30190	150	15	for	for	ADP
ajst-30190	150	16	the	the	DET
ajst-30190	150	17	occipital	occipital	NOUN
ajst-30190	150	18	lobe	lobe	VERB
ajst-30190	150	19	with	with	ADP
ajst-30190	150	20	hm	hm	INTJ
ajst-30190	151	1	+	+	CCONJ
ajst-30190	151	2	psd	psd	NOUN
ajst-30190	152	1	+	+	CCONJ
ajst-30190	152	2	we	we	PRON
ajst-30190	152	3	.	.	PUNCT
ajst-30190	153	1	this	this	PRON
ajst-30190	153	2	fully	fully	ADV
ajst-30190	153	3	demonstrates	demonstrate	VERB
ajst-30190	153	4	that	that	SCONJ
ajst-30190	153	5	the	the	DET
ajst-30190	153	6	model	model	NOUN
ajst-30190	153	7	of	of	ADP
ajst-30190	153	8	c	c	PROPN
ajst-30190	153	9	-	-	PUNCT
ajst-30190	153	10	rbm	rbm	ADJ
ajst-30190	153	11	extracting	extract	VERB
ajst-30190	153	12	features	feature	NOUN
ajst-30190	153	13	constructed	construct	VERB
ajst-30190	153	14	in	in	ADP
ajst-30190	153	15	this	this	DET
ajst-30190	153	16	paper	paper	NOUN
ajst-30190	153	17	and	and	CCONJ
ajst-30190	153	18	the	the	DET
ajst-30190	153	19	combination	combination	NOUN
ajst-30190	153	20	of	of	ADP
ajst-30190	153	21	svm	svm	PROPN
ajst-30190	153	22	and	and	CCONJ
ajst-30190	153	23	rf	rf	NOUN
ajst-30190	153	24	classifiers	classifier	NOUN
ajst-30190	153	25	have	have	VERB
ajst-30190	153	26	better	well	ADJ
ajst-30190	153	27	fatigue	fatigue	NOUN
ajst-30190	153	28	detection	detection	NOUN
ajst-30190	153	29	effect	effect	NOUN
ajst-30190	153	30	on	on	ADP
ajst-30190	153	31	the	the	DET
ajst-30190	153	32	two	two	NUM
ajst-30190	153	33	combinations	combination	NOUN
ajst-30190	153	34	of	of	ADP
ajst-30190	153	35	features	feature	NOUN
ajst-30190	153	36	after	after	ADP
ajst-30190	153	37	channel	channel	NOUN
ajst-30190	153	38	reduction	reduction	NOUN
ajst-30190	153	39	,	,	PUNCT
ajst-30190	153	40	which	which	PRON
ajst-30190	153	41	provides	provide	VERB
ajst-30190	153	42	an	an	DET
ajst-30190	153	43	effective	effective	ADJ
ajst-30190	153	44	reference	reference	NOUN
ajst-30190	153	45	and	and	CCONJ
ajst-30190	153	46	feasibility	feasibility	NOUN
ajst-30190	153	47	for	for	ADP
ajst-30190	153	48	the	the	DET
ajst-30190	153	49	subsequent	subsequent	ADJ
ajst-30190	153	50	sparse	sparse	ADJ
ajst-30190	153	51	channel	channel	NOUN
ajst-30190	153	52	detection	detection	NOUN
ajst-30190	153	53	of	of	ADP
ajst-30190	153	54	fatigue	fatigue	NOUN
ajst-30190	153	55	eeg	eeg	PROPN
ajst-30190	153	56	.	.	PUNCT
ajst-30190	153	57	discussions	discussion	NOUN
ajst-30190	153	58	:	:	PUNCT
ajst-30190	153	59	(	(	PUNCT
ajst-30190	153	60	1	1	X
ajst-30190	153	61	)	)	PUNCT
ajst-30190	153	62	most	most	ADJ
ajst-30190	153	63	of	of	ADP
ajst-30190	153	64	the	the	DET
ajst-30190	153	65	methods	method	NOUN
ajst-30190	153	66	used	use	VERB
ajst-30190	153	67	in	in	ADP
ajst-30190	153	68	this	this	DET
ajst-30190	153	69	study	study	NOUN
ajst-30190	153	70	to	to	PART
ajst-30190	153	71	induce	induce	VERB
ajst-30190	153	72	fatigue	fatigue	NOUN
ajst-30190	153	73	eeg	eeg	NOUN
ajst-30190	153	74	are	be	AUX
ajst-30190	153	75	based	base	VERB
ajst-30190	153	76	on	on	ADP
ajst-30190	153	77	small	small	ADJ
ajst-30190	153	78	-	-	PUNCT
ajst-30190	153	79	scale	scale	NOUN
ajst-30190	153	80	data	data	NOUN
ajst-30190	153	81	sets	set	NOUN
ajst-30190	153	82	,	,	PUNCT
ajst-30190	153	83	which	which	PRON
ajst-30190	153	84	inevitably	inevitably	ADV
ajst-30190	153	85	lack	lack	VERB
ajst-30190	153	86	diversity	diversity	NOUN
ajst-30190	153	87	and	and	CCONJ
ajst-30190	153	88	representativeness	representativeness	NOUN
ajst-30190	153	89	.	.	PUNCT
ajst-30190	154	1	due	due	ADP
ajst-30190	154	2	to	to	ADP
ajst-30190	154	3	the	the	DET
ajst-30190	154	4	differences	difference	NOUN
ajst-30190	154	5	in	in	ADP
ajst-30190	154	6	experimental	experimental	ADJ
ajst-30190	154	7	environments	environment	NOUN
ajst-30190	154	8	,	,	PUNCT
ajst-30190	154	9	types	type	NOUN
ajst-30190	154	10	of	of	ADP
ajst-30190	154	11	tasks	task	NOUN
ajst-30190	154	12	,	,	PUNCT
ajst-30190	154	13	and	and	CCONJ
ajst-30190	154	14	groups	group	NOUN
ajst-30190	154	15	of	of	ADP
ajst-30190	154	16	subjects	subject	NOUN
ajst-30190	154	17	,	,	PUNCT
ajst-30190	154	18	the	the	DET
ajst-30190	154	19	eeg	eeg	NOUN
ajst-30190	154	20	data	datum	NOUN
ajst-30190	154	21	may	may	AUX
ajst-30190	154	22	vary	vary	VERB
ajst-30190	154	23	,	,	PUNCT
ajst-30190	154	24	and	and	CCONJ
ajst-30190	154	25	the	the	DET
ajst-30190	154	26	individual	individual	NOUN
ajst-30190	154	27	's	's	PART
ajst-30190	154	28	own	own	ADJ
ajst-30190	154	29	habits	habit	NOUN
ajst-30190	154	30	and	and	CCONJ
ajst-30190	154	31	genetic	genetic	ADJ
ajst-30190	154	32	factors	factor	NOUN
ajst-30190	154	33	may	may	AUX
ajst-30190	154	34	also	also	ADV
ajst-30190	154	35	have	have	VERB
ajst-30190	154	36	an	an	DET
ajst-30190	154	37	impact	impact	NOUN
ajst-30190	154	38	on	on	ADP
ajst-30190	154	39	the	the	DET
ajst-30190	154	40	eeg	eeg	NOUN
ajst-30190	154	41	signals	signal	NOUN
ajst-30190	154	42	.	.	PUNCT
ajst-30190	155	1	in	in	ADP
ajst-30190	155	2	the	the	DET
ajst-30190	155	3	future	future	NOUN
ajst-30190	155	4	,	,	PUNCT
ajst-30190	155	5	we	we	PRON
ajst-30190	155	6	can	can	AUX
ajst-30190	155	7	try	try	VERB
ajst-30190	155	8	to	to	PART
ajst-30190	155	9	collect	collect	VERB
ajst-30190	155	10	detailed	detailed	ADJ
ajst-30190	155	11	information	information	NOUN
ajst-30190	155	12	of	of	ADP
ajst-30190	155	13	individuals	individual	NOUN
ajst-30190	155	14	,	,	PUNCT
ajst-30190	155	15	construct	construct	VERB
ajst-30190	155	16	a	a	DET
ajst-30190	155	17	model	model	NOUN
ajst-30190	155	18	based	base	VERB
ajst-30190	155	19	on	on	ADP
ajst-30190	155	20	the	the	DET
ajst-30190	155	21	eeg	eeg	NOUN
ajst-30190	155	22	data	datum	NOUN
ajst-30190	155	23	of	of	ADP
ajst-30190	155	24	some	some	DET
ajst-30190	155	25	individuals	individual	NOUN
ajst-30190	155	26	,	,	PUNCT
ajst-30190	155	27	and	and	CCONJ
ajst-30190	155	28	then	then	ADV
ajst-30190	155	29	test	test	VERB
ajst-30190	155	30	it	it	PRON
ajst-30190	155	31	with	with	ADP
ajst-30190	155	32	the	the	DET
ajst-30190	155	33	eeg	eeg	NOUN
ajst-30190	155	34	data	datum	NOUN
ajst-30190	155	35	of	of	ADP
ajst-30190	155	36	the	the	DET
ajst-30190	155	37	rest	rest	NOUN
ajst-30190	155	38	of	of	ADP
ajst-30190	155	39	the	the	DET
ajst-30190	155	40	subjects	subject	NOUN
ajst-30190	155	41	to	to	PART
ajst-30190	155	42	check	check	VERB
ajst-30190	155	43	the	the	DET
ajst-30190	155	44	validity	validity	NOUN
ajst-30190	155	45	of	of	ADP
ajst-30190	155	46	the	the	DET
ajst-30190	155	47	model	model	NOUN
ajst-30190	155	48	,	,	PUNCT
ajst-30190	155	49	and	and	CCONJ
ajst-30190	155	50	then	then	ADV
ajst-30190	155	51	explore	explore	VERB
ajst-30190	155	52	the	the	DET
ajst-30190	155	53	unique	unique	ADJ
ajst-30190	155	54	fatigue	fatigue	NOUN
ajst-30190	155	55	characteristics	characteristic	NOUN
ajst-30190	155	56	model	model	NOUN
ajst-30190	155	57	.	.	PUNCT
ajst-30190	156	1	(	(	PUNCT
ajst-30190	156	2	2	2	X
ajst-30190	156	3	)	)	PUNCT
ajst-30190	156	4	in	in	ADP
ajst-30190	156	5	this	this	DET
ajst-30190	156	6	study	study	NOUN
ajst-30190	156	7	,	,	PUNCT
ajst-30190	156	8	only	only	ADV
ajst-30190	156	9	the	the	DET
ajst-30190	156	10	states	state	NOUN
ajst-30190	156	11	of	of	ADP
ajst-30190	156	12	the	the	DET
ajst-30190	156	13	first	first	ADJ
ajst-30190	156	14	and	and	CCONJ
ajst-30190	156	15	last	last	ADJ
ajst-30190	156	16	stages	stage	NOUN
ajst-30190	156	17	of	of	ADP
ajst-30190	156	18	the	the	DET
ajst-30190	156	19	subjects	subject	NOUN
ajst-30190	156	20	were	be	AUX
ajst-30190	156	21	selected	select	VERB
ajst-30190	156	22	as	as	ADP
ajst-30190	156	23	the	the	DET
ajst-30190	156	24	research	research	NOUN
ajst-30190	156	25	data	datum	NOUN
ajst-30190	156	26	,	,	PUNCT
ajst-30190	156	27	and	and	CCONJ
ajst-30190	156	28	although	although	SCONJ
ajst-30190	156	29	the	the	DET
ajst-30190	156	30	accuracy	accuracy	NOUN
ajst-30190	156	31	of	of	ADP
ajst-30190	156	32	the	the	DET
ajst-30190	156	33	dichotomous	dichotomous	ADJ
ajst-30190	156	34	classification	classification	NOUN
ajst-30190	156	35	task	task	NOUN
ajst-30190	156	36	is	be	AUX
ajst-30190	156	37	quite	quite	ADV
ajst-30190	156	38	impressive	impressive	ADJ
ajst-30190	156	39	,	,	PUNCT
ajst-30190	156	40	it	it	PRON
ajst-30190	156	41	is	be	AUX
ajst-30190	156	42	possible	possible	ADJ
ajst-30190	156	43	to	to	PART
ajst-30190	156	44	find	find	VERB
ajst-30190	156	45	an	an	DET
ajst-30190	156	46	intermediate	intermediate	ADJ
ajst-30190	156	47	state	state	NOUN
ajst-30190	156	48	between	between	ADP
ajst-30190	156	49	these	these	DET
ajst-30190	156	50	two	two	NUM
ajst-30190	156	51	states	state	NOUN
ajst-30190	156	52	,	,	PUNCT
ajst-30190	156	53	and	and	CCONJ
ajst-30190	156	54	multiple	multiple	ADJ
ajst-30190	156	55	fatigue	fatigue	NOUN
ajst-30190	156	56	level	level	NOUN
ajst-30190	156	57	classifications	classification	NOUN
ajst-30190	156	58	can	can	AUX
ajst-30190	156	59	be	be	AUX
ajst-30190	156	60	attempted	attempt	VERB
ajst-30190	156	61	in	in	ADP
ajst-30190	156	62	the	the	DET
ajst-30190	156	63	future	future	NOUN
ajst-30190	156	64	.	.	PUNCT
ajst-30190	157	1	references	reference	NOUN
ajst-30190	157	2	[	[	X
ajst-30190	157	3	1	1	NUM
ajst-30190	157	4	]	]	X
ajst-30190	157	5	martin	martin	PROPN
ajst-30190	157	6	v	v	ADP
ajst-30190	157	7	p	p	PROPN
ajst-30190	157	8	,	,	PUNCT
ajst-30190	157	9	lopez	lopez	PROPN
ajst-30190	157	10	r	r	PROPN
ajst-30190	157	11	,	,	PUNCT
ajst-30190	157	12	dauvilliers	dauvillier	NOUN
ajst-30190	157	13	y	y	PROPN
ajst-30190	157	14	,	,	PUNCT
ajst-30190	157	15	et	et	PROPN
ajst-30190	157	16	al	al	PROPN
ajst-30190	157	17	.	.	PROPN
ajst-30190	157	18	sleepiness	sleepiness	PROPN
ajst-30190	157	19	in	in	ADP
ajst-30190	157	20	adults	adult	NOUN
ajst-30190	157	21	:	:	PUNCT
ajst-30190	157	22	an	an	DET
ajst-30190	157	23	umbrella	umbrella	NOUN
ajst-30190	157	24	review	review	NOUN
ajst-30190	157	25	of	of	ADP
ajst-30190	157	26	a	a	DET
ajst-30190	157	27	complex	complex	ADJ
ajst-30190	157	28	construct[j	construct[j	NOUN
ajst-30190	157	29	]	]	PUNCT
ajst-30190	157	30	.	.	PUNCT
ajst-30190	158	1	sleep	sleep	PROPN
ajst-30190	158	2	med	med	PROPN
ajst-30190	158	3	rev	rev	PROPN
ajst-30190	158	4	,	,	PUNCT
ajst-30190	158	5	2023,67	2023,67	NUM
ajst-30190	158	6	:	:	PUNCT
ajst-30190	158	7	101718	101718	NUM
ajst-30190	158	8	.	.	PUNCT
ajst-30190	159	1	[	[	X
ajst-30190	159	2	2	2	X
ajst-30190	159	3	]	]	PUNCT
ajst-30190	159	4	goncalves	goncalves	PROPN
ajst-30190	159	5	m	m	PROPN
ajst-30190	159	6	t	t	PROPN
ajst-30190	159	7	,	,	PUNCT
ajst-30190	159	8	malafaia	malafaia	PROPN
ajst-30190	159	9	s	s	PROPN
ajst-30190	159	10	,	,	PUNCT
ajst-30190	159	11	santos	santos	PROPN
ajst-30190	159	12	j	j	PROPN
ajst-30190	159	13	m	m	PROPN
ajst-30190	159	14	d	d	PROPN
ajst-30190	159	15	,	,	PUNCT
ajst-30190	159	16	et	et	PROPN
ajst-30190	159	17	al	al	PROPN
ajst-30190	159	18	.	.	PUNCT
ajst-30190	160	1	epworth	epworth	ADJ
ajst-30190	160	2	sleepiness	sleepiness	PROPN
ajst-30190	160	3	scale	scale	NOUN
ajst-30190	160	4	:	:	PUNCT
ajst-30190	160	5	a	a	DET
ajst-30190	160	6	meta	meta	ADJ
ajst-30190	160	7	-	-	PUNCT
ajst-30190	160	8	analytic	analytic	ADJ
ajst-30190	160	9	study	study	NOUN
ajst-30190	160	10	on	on	ADP
ajst-30190	160	11	the	the	DET
ajst-30190	160	12	internal	internal	ADJ
ajst-30190	160	13	consistency[j	consistency[j	NOUN
ajst-30190	160	14	]	]	PUNCT
ajst-30190	160	15	.	.	PUNCT
ajst-30190	161	1	sleep	sleep	NOUN
ajst-30190	161	2	medicine	medicine	NOUN
ajst-30190	161	3	,	,	PUNCT
ajst-30190	161	4	2023,109	2023,109	NUM
ajst-30190	161	5	:	:	PUNCT
ajst-30190	161	6	261269	261269	NUM
ajst-30190	161	7	.	.	PUNCT
ajst-30190	162	1	[	[	X
ajst-30190	162	2	3	3	X
ajst-30190	162	3	]	]	X
ajst-30190	162	4	popp	popp	NOUN
ajst-30190	162	5	r	r	PROPN
ajst-30190	162	6	f	f	PROPN
ajst-30190	162	7	,	,	PUNCT
ajst-30190	162	8	fierlbeck	fierlbeck	NOUN
ajst-30190	162	9	a	a	DET
ajst-30190	162	10	k	k	NOUN
ajst-30190	162	11	,	,	PUNCT
ajst-30190	162	12	knuttel	knuttel	NOUN
ajst-30190	162	13	h	h	PROPN
ajst-30190	162	14	,	,	PUNCT
ajst-30190	162	15	et	et	PROPN
ajst-30190	162	16	al	al	PROPN
ajst-30190	162	17	.	.	PUNCT
ajst-30190	162	18	daytime	daytime	ADJ
ajst-30190	162	19	sleepiness	sleepiness	NOUN
ajst-30190	162	20	versus	versus	ADP
ajst-30190	162	21	fatigue	fatigue	NOUN
ajst-30190	162	22	in	in	ADP
ajst-30190	162	23	patients	patient	NOUN
ajst-30190	162	24	with	with	ADP
ajst-30190	162	25	multiple	multiple	ADJ
ajst-30190	162	26	sclerosis	sclerosis	NOUN
ajst-30190	162	27	:	:	PUNCT
ajst-30190	162	28	a	a	DET
ajst-30190	162	29	systematic	systematic	ADJ
ajst-30190	162	30	review	review	NOUN
ajst-30190	162	31	on	on	ADP
ajst-30190	162	32	the	the	DET
ajst-30190	162	33	epworth	epworth	ADJ
ajst-30190	162	34	sleepiness	sleepiness	NOUN
ajst-30190	162	35	scale	scale	NOUN
ajst-30190	162	36	as	as	ADP
ajst-30190	162	37	an	an	DET
ajst-30190	162	38	assessment	assessment	NOUN
ajst-30190	162	39	tool[j	tool[j	NUM
ajst-30190	162	40	]	]	PUNCT
ajst-30190	162	41	.	.	PUNCT
ajst-30190	163	1	sleep	sleep	PROPN
ajst-30190	163	2	med	med	PROPN
ajst-30190	163	3	rev	rev	PROPN
ajst-30190	163	4	,	,	PUNCT
ajst-30190	163	5	2017,32	2017,32	NUM
ajst-30190	163	6	:	:	PUNCT
ajst-30190	163	7	95	95	NUM
ajst-30190	163	8	-	-	SYM
ajst-30190	163	9	108	108	NUM
ajst-30190	163	10	.	.	PUNCT
ajst-30190	164	1	[	[	X
ajst-30190	164	2	4	4	X
ajst-30190	164	3	]	]	PUNCT
ajst-30190	164	4	xiang	xiang	PROPN
ajst-30190	164	5	c	c	PROPN
ajst-30190	164	6	,	,	PUNCT
ajst-30190	164	7	fan	fan	NOUN
ajst-30190	164	8	x	x	NOUN
ajst-30190	164	9	,	,	PUNCT
ajst-30190	164	10	bai	bai	PROPN
ajst-30190	164	11	d	d	PROPN
ajst-30190	164	12	,	,	PUNCT
ajst-30190	164	13	et	et	PROPN
ajst-30190	164	14	al	al	PROPN
ajst-30190	164	15	.	.	PUNCT
ajst-30190	165	1	a	a	DET
ajst-30190	165	2	resting	rest	VERB
ajst-30190	165	3	-	-	PUNCT
ajst-30190	165	4	state	state	NOUN
ajst-30190	165	5	eeg	eeg	NOUN
ajst-30190	165	6	dataset	dataset	VERB
ajst-30190	165	7	for	for	ADP
ajst-30190	165	8	sleep	sleep	NOUN
ajst-30190	165	9	deprivation[j	deprivation[j	PROPN
ajst-30190	165	10	]	]	PUNCT
ajst-30190	165	11	.	.	PUNCT
ajst-30190	166	1	sci	sci	PROPN
ajst-30190	166	2	data	data	PROPN
ajst-30190	166	3	,	,	PUNCT
ajst-30190	166	4	2024,11(1	2024,11(1	NUM
ajst-30190	166	5	):	):	PUNCT
ajst-30190	166	6	427	427	NUM
ajst-30190	166	7	.	.	PUNCT
ajst-30190	167	1	[	[	X
ajst-30190	167	2	5	5	X
ajst-30190	167	3	]	]	X
ajst-30190	167	4	zhang	zhang	PROPN
ajst-30190	167	5	h	h	PROPN
ajst-30190	167	6	,	,	PUNCT
ajst-30190	167	7	zhou	zhou	PROPN
ajst-30190	167	8	q	q	PROPN
ajst-30190	167	9	,	,	PUNCT
ajst-30190	167	10	chen	chen	PROPN
ajst-30190	167	11	h	h	PROPN
ajst-30190	167	12	,	,	PUNCT
ajst-30190	167	13	et	et	PROPN
ajst-30190	167	14	al	al	PROPN
ajst-30190	167	15	.	.	PUNCT
ajst-30190	168	1	the	the	DET
ajst-30190	168	2	applied	apply	VERB
ajst-30190	168	3	principles	principle	NOUN
ajst-30190	168	4	of	of	ADP
ajst-30190	168	5	eeg	eeg	NOUN
ajst-30190	168	6	analysis	analysis	NOUN
ajst-30190	168	7	methods	method	NOUN
ajst-30190	168	8	in	in	ADP
ajst-30190	168	9	neuroscience	neuroscience	NOUN
ajst-30190	168	10	and	and	CCONJ
ajst-30190	168	11	clinical	clinical	ADJ
ajst-30190	168	12	neurology[j	neurology[j	NOUN
ajst-30190	168	13	]	]	PUNCT
ajst-30190	168	14	.	.	PUNCT
ajst-30190	169	1	mil	mil	PROPN
ajst-30190	169	2	med	med	PROPN
ajst-30190	169	3	res	re	NOUN
ajst-30190	169	4	,	,	PUNCT
ajst-30190	169	5	2023,10(1	2023,10(1	NUM
ajst-30190	169	6	):	):	PUNCT
ajst-30190	169	7	67	67	NUM
ajst-30190	169	8	.	.	PUNCT
ajst-30190	170	1	[	[	X
ajst-30190	170	2	6	6	NUM
ajst-30190	170	3	]	]	X
ajst-30190	170	4	y.	y.	NOUN
ajst-30190	170	5	p	p	PROPN
ajst-30190	170	6	,	,	PUNCT
ajst-30190	170	7	c.	c.	PROPN
ajst-30190	170	8	m	m	PROPN
ajst-30190	170	9	w	w	PROPN
ajst-30190	170	10	,	,	PUNCT
ajst-30190	170	11	z.	z.	PROPN
ajst-30190	170	12	w	w	PROPN
ajst-30190	170	13	,	,	PUNCT
ajst-30190	170	14	et	et	PROPN
ajst-30190	170	15	al	al	PROPN
ajst-30190	170	16	.	.	PROPN
ajst-30190	170	17	fatigue	fatigue	NOUN
ajst-30190	170	18	detection	detection	NOUN
ajst-30190	170	19	in	in	ADP
ajst-30190	170	20	ssvep	ssvep	NOUN
ajst-30190	170	21	-	-	PUNCT
ajst-30190	170	22	bcis	bcis	NOUN
ajst-30190	170	23	based	base	VERB
ajst-30190	170	24	on	on	ADP
ajst-30190	170	25	wavelet	wavelet	NOUN
ajst-30190	170	26	entropy	entropy	NOUN
ajst-30190	170	27	of	of	ADP
ajst-30190	170	28	eeg[j	eeg[j	NOUN
ajst-30190	170	29	]	]	PUNCT
ajst-30190	170	30	.	.	PUNCT
ajst-30190	171	1	ieee	ieee	NOUN
ajst-30190	171	2	access	access	NOUN
ajst-30190	171	3	,	,	PUNCT
ajst-30190	171	4	2021,9	2021,9	NUM
ajst-30190	171	5	:	:	PUNCT
ajst-30190	171	6	114905	114905	NUM
ajst-30190	171	7	-	-	SYM
ajst-30190	171	8	114913	114913	NUM
ajst-30190	171	9	.	.	PUNCT
ajst-30190	172	1	[	[	X
ajst-30190	172	2	7	7	X
ajst-30190	172	3	]	]	X
ajst-30190	172	4	luo	luo	PROPN
ajst-30190	172	5	h	h	PROPN
ajst-30190	172	6	,	,	PUNCT
ajst-30190	172	7	qiu	qiu	PROPN
ajst-30190	172	8	t	t	PROPN
ajst-30190	172	9	,	,	PUNCT
ajst-30190	172	10	liu	liu	PROPN
ajst-30190	172	11	c	c	PROPN
ajst-30190	172	12	,	,	PUNCT
ajst-30190	172	13	et	et	PROPN
ajst-30190	172	14	al	al	PROPN
ajst-30190	172	15	.	.	PROPN
ajst-30190	172	16	research	research	NOUN
ajst-30190	172	17	on	on	ADP
ajst-30190	172	18	fatigue	fatigue	NOUN
ajst-30190	172	19	driving	drive	VERB
ajst-30190	172	20	detection	detection	NOUN
ajst-30190	172	21	using	use	VERB
ajst-30190	172	22	forehead	forehead	NOUN
ajst-30190	172	23	eeg	eeg	NOUN
ajst-30190	172	24	based	base	VERB
ajst-30190	172	25	on	on	ADP
ajst-30190	172	26	adaptive	adaptive	ADJ
ajst-30190	172	27	multi	multi	ADJ
ajst-30190	172	28	-	-	ADJ
ajst-30190	172	29	scale	scale	ADJ
ajst-30190	172	30	entropy[j	entropy[j	PROPN
ajst-30190	172	31	]	]	PUNCT
ajst-30190	172	32	.	.	PUNCT
ajst-30190	172	33	biomedical	biomedical	ADJ
ajst-30190	172	34	signal	signal	NOUN
ajst-30190	172	35	processing	processing	NOUN
ajst-30190	172	36	and	and	CCONJ
ajst-30190	172	37	control	control	NOUN
ajst-30190	172	38	,	,	PUNCT
ajst-30190	172	39	2019,51	2019,51	PROPN
ajst-30190	172	40	:	:	PUNCT
ajst-30190	172	41	50	50	NUM
ajst-30190	172	42	-	-	SYM
ajst-30190	172	43	58	58	NUM
ajst-30190	172	44	.	.	PUNCT
ajst-30190	173	1	[	[	X
ajst-30190	173	2	8	8	NUM
ajst-30190	173	3	]	]	SYM
ajst-30190	173	4	hu	hu	PROPN
ajst-30190	173	5	j.	j.	PROPN
ajst-30190	173	6	automated	automate	VERB
ajst-30190	173	7	detection	detection	NOUN
ajst-30190	173	8	of	of	ADP
ajst-30190	173	9	driver	driver	NOUN
ajst-30190	173	10	fatigue	fatigue	NOUN
ajst-30190	173	11	based	base	VERB
ajst-30190	173	12	on	on	ADP
ajst-30190	173	13	adaboost	adaboost	ADJ
ajst-30190	173	14	classifier	classifier	NOUN
ajst-30190	173	15	with	with	ADP
ajst-30190	173	16	eeg	eeg	PROPN
ajst-30190	173	17	signals[j	signals[j	PROPN
ajst-30190	173	18	]	]	PUNCT
ajst-30190	173	19	.	.	PUNCT
ajst-30190	174	1	front	front	ADJ
ajst-30190	174	2	comput	comput	PROPN
ajst-30190	174	3	neurosci	neurosci	NOUN
ajst-30190	174	4	,	,	PUNCT
ajst-30190	174	5	2017,11	2017,11	NOUN
ajst-30190	174	6	:	:	PUNCT
ajst-30190	174	7	72	72	NUM
ajst-30190	174	8	.	.	PUNCT
ajst-30190	175	1	[	[	X
ajst-30190	175	2	9	9	NUM
ajst-30190	175	3	]	]	X
ajst-30190	175	4	liu	liu	PROPN
ajst-30190	175	5	q	q	PROPN
ajst-30190	175	6	,	,	PUNCT
ajst-30190	175	7	liu	liu	PROPN
ajst-30190	175	8	y	y	PROPN
ajst-30190	175	9	,	,	PUNCT
ajst-30190	175	10	chen	chen	PROPN
ajst-30190	175	11	k	k	PROPN
ajst-30190	175	12	,	,	PUNCT
ajst-30190	175	13	et	et	PROPN
ajst-30190	175	14	al	al	PROPN
ajst-30190	175	15	.	.	PROPN
ajst-30190	175	16	research	research	PROPN
ajst-30190	175	17	on	on	ADP
ajst-30190	175	18	channel	channel	NOUN
ajst-30190	175	19	selection	selection	NOUN
ajst-30190	175	20	and	and	CCONJ
ajst-30190	175	21	multi	multi	ADJ
ajst-30190	175	22	-	-	ADJ
ajst-30190	175	23	feature	feature	ADJ
ajst-30190	175	24	fusion	fusion	NOUN
ajst-30190	175	25	of	of	ADP
ajst-30190	175	26	eeg	eeg	NOUN
ajst-30190	175	27	signals	signal	NOUN
ajst-30190	175	28	for	for	ADP
ajst-30190	175	29	mental	mental	ADJ
ajst-30190	175	30	fatigue	fatigue	NOUN
ajst-30190	175	31	detection[j	detection[j	PROPN
ajst-30190	175	32	]	]	PUNCT
ajst-30190	175	33	.	.	PUNCT
ajst-30190	175	34	entropy	entropy	PROPN
ajst-30190	175	35	(	(	PUNCT
ajst-30190	175	36	basel	basel	PROPN
ajst-30190	175	37	)	)	PUNCT
ajst-30190	175	38	,	,	PUNCT
ajst-30190	175	39	2021,23(4	2021,23(4	NOUN
ajst-30190	175	40	)	)	PUNCT
ajst-30190	175	41	.	.	PUNCT
ajst-30190	176	1	[	[	X
ajst-30190	176	2	10	10	NUM
ajst-30190	176	3	]	]	X
ajst-30190	176	4	guo	guo	PROPN
ajst-30190	176	5	h	h	PROPN
ajst-30190	176	6	,	,	PUNCT
ajst-30190	176	7	chen	chen	PROPN
ajst-30190	176	8	s	s	PROPN
ajst-30190	176	9	,	,	PUNCT
ajst-30190	176	10	zhou	zhou	PROPN
ajst-30190	176	11	y	y	PROPN
ajst-30190	176	12	,	,	PUNCT
ajst-30190	176	13	et	et	PROPN
ajst-30190	176	14	al	al	PROPN
ajst-30190	176	15	.	.	PUNCT
ajst-30190	177	1	a	a	DET
ajst-30190	177	2	hybrid	hybrid	ADJ
ajst-30190	177	3	critical	critical	ADJ
ajst-30190	177	4	channels	channel	NOUN
ajst-30190	177	5	and	and	CCONJ
ajst-30190	177	6	optimal	optimal	ADJ
ajst-30190	177	7	feature	feature	NOUN
ajst-30190	177	8	subset	subset	NOUN
ajst-30190	177	9	selection	selection	NOUN
ajst-30190	177	10	framework	framework	NOUN
ajst-30190	177	11	for	for	ADP
ajst-30190	177	12	eeg	eeg	NOUN
ajst-30190	177	13	fatigue	fatigue	NOUN
ajst-30190	177	14	recognition[j	recognition[j	PROPN
ajst-30190	177	15	]	]	PUNCT
ajst-30190	177	16	.	.	PUNCT
ajst-30190	178	1	sci	sci	PROPN
ajst-30190	178	2	rep	rep	PROPN
ajst-30190	178	3	,	,	PUNCT
ajst-30190	178	4	2025,15(1	2025,15(1	NOUN
ajst-30190	178	5	):	):	PUNCT
ajst-30190	178	6	2139	2139	NUM
ajst-30190	178	7	.	.	PUNCT
ajst-30190	179	1	[	[	X
ajst-30190	179	2	11	11	NUM
ajst-30190	179	3	]	]	SYM
ajst-30190	179	4	hu	hu	PROPN
ajst-30190	179	5	j	j	PROPN
ajst-30190	179	6	,	,	PUNCT
ajst-30190	179	7	min	min	PROPN
ajst-30190	179	8	j.	j.	PROPN
ajst-30190	179	9	automated	automate	VERB
ajst-30190	179	10	detection	detection	NOUN
ajst-30190	179	11	of	of	ADP
ajst-30190	179	12	driver	driver	NOUN
ajst-30190	179	13	fatigue	fatigue	NOUN
ajst-30190	179	14	based	base	VERB
ajst-30190	179	15	on	on	ADP
ajst-30190	179	16	eeg	eeg	NOUN
ajst-30190	179	17	signals	signal	NOUN
ajst-30190	179	18	using	use	VERB
ajst-30190	179	19	gradient	gradient	NOUN
ajst-30190	179	20	boosting	boost	VERB
ajst-30190	179	21	decision	decision	NOUN
ajst-30190	179	22	tree	tree	NOUN
ajst-30190	179	23	model[j	model[j	PROPN
ajst-30190	179	24	]	]	PUNCT
ajst-30190	179	25	.	.	PUNCT
ajst-30190	180	1	cognitive	cognitive	ADJ
ajst-30190	180	2	neurodynamics	neurodynamic	NOUN
ajst-30190	180	3	,	,	PUNCT
ajst-30190	180	4	2018,12(4	2018,12(4	PROPN
ajst-30190	180	5	):	):	PUNCT
ajst-30190	180	6	431	431	NUM
ajst-30190	180	7	-	-	SYM
ajst-30190	180	8	440	440	NUM
ajst-30190	180	9	.	.	PUNCT
ajst-30190	181	1	[	[	X
ajst-30190	181	2	12	12	NUM
ajst-30190	181	3	]	]	X
ajst-30190	181	4	lamichhane	lamichhane	PROPN
ajst-30190	181	5	b	b	PROPN
ajst-30190	181	6	,	,	PUNCT
ajst-30190	181	7	westbrook	westbrook	PROPN
ajst-30190	181	8	a	a	PROPN
ajst-30190	181	9	,	,	PUNCT
ajst-30190	181	10	cole	cole	PROPN
ajst-30190	181	11	m	m	PROPN
ajst-30190	181	12	w	w	PROPN
ajst-30190	181	13	,	,	PUNCT
ajst-30190	181	14	et	et	PROPN
ajst-30190	181	15	al	al	PROPN
ajst-30190	181	16	.	.	PUNCT
ajst-30190	181	17	exploring	explore	VERB
ajst-30190	181	18	brain	brain	NOUN
ajst-30190	181	19	-	-	PUNCT
ajst-30190	181	20	behavior	behavior	NOUN
ajst-30190	181	21	relationships	relationship	NOUN
ajst-30190	181	22	in	in	ADP
ajst-30190	181	23	the	the	DET
ajst-30190	181	24	n	n	CCONJ
ajst-30190	181	25	-	-	PUNCT
ajst-30190	181	26	back	back	NOUN
ajst-30190	181	27	task[j	task[j	NOUN
ajst-30190	181	28	]	]	PUNCT
ajst-30190	181	29	.	.	PUNCT
ajst-30190	182	1	neuroimage	neuroimage	NOUN
ajst-30190	182	2	,	,	PUNCT
ajst-30190	182	3	2020,212	2020,212	NUM
ajst-30190	182	4	:	:	PUNCT
ajst-30190	182	5	116683	116683	NUM
ajst-30190	182	6	.	.	PUNCT
ajst-30190	183	1	[	[	X
ajst-30190	183	2	13	13	NUM
ajst-30190	183	3	]	]	PUNCT
ajst-30190	183	4	eltrass	eltrass	VERB
ajst-30190	183	5	a	a	DET
ajst-30190	183	6	s	s	PROPN
ajst-30190	183	7	,	,	PUNCT
ajst-30190	183	8	ghanem	ghanem	PROPN
ajst-30190	183	9	n	n	PROPN
ajst-30190	183	10	h.	h.	NOUN
ajst-30190	183	11	a	a	DET
ajst-30190	183	12	new	new	ADJ
ajst-30190	183	13	automated	automate	VERB
ajst-30190	183	14	multi	multi	ADJ
ajst-30190	183	15	-	-	ADJ
ajst-30190	183	16	stage	stage	ADJ
ajst-30190	183	17	system	system	NOUN
ajst-30190	183	18	of	of	ADP
ajst-30190	183	19	non	non	ADJ
ajst-30190	183	20	-	-	ADJ
ajst-30190	183	21	local	local	ADJ
ajst-30190	183	22	means	mean	NOUN
ajst-30190	183	23	and	and	CCONJ
ajst-30190	183	24	multi	multi	ADJ
ajst-30190	183	25	-	-	ADJ
ajst-30190	183	26	kernel	kernel	ADJ
ajst-30190	183	27	adaptive	adaptive	ADJ
ajst-30190	183	28	filtering	filtering	NOUN
ajst-30190	183	29	techniques	technique	NOUN
ajst-30190	183	30	for	for	ADP
ajst-30190	183	31	eeg	eeg	NOUN
ajst-30190	183	32	noise	noise	NOUN
ajst-30190	183	33	and	and	CCONJ
ajst-30190	183	34	artifacts	artifact	NOUN
ajst-30190	183	35	suppression[j	suppression[j	NOUN
ajst-30190	183	36	]	]	PUNCT
ajst-30190	183	37	.	.	PUNCT
ajst-30190	184	1	j	j	PROPN
ajst-30190	184	2	neural	neural	PROPN
ajst-30190	184	3	eng	eng	PROPN
ajst-30190	184	4	,	,	PUNCT
ajst-30190	184	5	2021,18(3	2021,18(3	PROPN
ajst-30190	184	6	)	)	PUNCT
ajst-30190	184	7	.	.	PUNCT
ajst-30190	185	1	[	[	X
ajst-30190	185	2	14	14	NUM
ajst-30190	185	3	]	]	X
ajst-30190	185	4	riaz	riaz	PROPN
ajst-30190	186	1	f	f	PROPN
ajst-30190	186	2	,	,	PUNCT
ajst-30190	186	3	hassan	hassan	PROPN
ajst-30190	186	4	a	a	PRON
ajst-30190	186	5	,	,	PUNCT
ajst-30190	186	6	rehman	rehman	PROPN
ajst-30190	186	7	s	s	PROPN
ajst-30190	186	8	,	,	PUNCT
ajst-30190	186	9	et	et	PROPN
ajst-30190	186	10	al	al	PROPN
ajst-30190	186	11	.	.	PROPN
ajst-30190	186	12	emd	emd	PROPN
ajst-30190	186	13	-	-	PUNCT
ajst-30190	186	14	based	base	VERB
ajst-30190	186	15	temporal	temporal	ADJ
ajst-30190	186	16	and	and	CCONJ
ajst-30190	186	17	spectral	spectral	ADJ
ajst-30190	186	18	features	feature	NOUN
ajst-30190	186	19	for	for	ADP
ajst-30190	186	20	the	the	DET
ajst-30190	186	21	classification	classification	NOUN
ajst-30190	186	22	of	of	ADP
ajst-30190	186	23	eeg	eeg	NOUN
ajst-30190	186	24	signals	signal	NOUN
ajst-30190	186	25	using	use	VERB
ajst-30190	186	26	supervised	supervised	ADJ
ajst-30190	186	27	learning[j	learning[j	NOUN
ajst-30190	186	28	]	]	PUNCT
ajst-30190	186	29	.	.	PUNCT
ajst-30190	187	1	ieee	ieee	PROPN
ajst-30190	187	2	trans	trans	PROPN
ajst-30190	187	3	neural	neural	PROPN
ajst-30190	187	4	syst	syst	PROPN
ajst-30190	187	5	rehabil	rehabil	PROPN
ajst-30190	187	6	eng	eng	PROPN
ajst-30190	187	7	,	,	PUNCT
ajst-30190	187	8	2016,24(1	2016,24(1	NOUN
ajst-30190	187	9	):	):	PUNCT
ajst-30190	187	10	28	28	NUM
ajst-30190	187	11	-	-	SYM
ajst-30190	187	12	35	35	NUM
ajst-30190	187	13	.	.	PUNCT
ajst-30190	188	1	[	[	X
ajst-30190	188	2	15	15	NUM
ajst-30190	188	3	]	]	PUNCT
ajst-30190	188	4	xu	xu	PROPN
ajst-30190	188	5	x	x	PROPN
ajst-30190	188	6	,	,	PUNCT
ajst-30190	188	7	tang	tang	PROPN
ajst-30190	188	8	j	j	PROPN
ajst-30190	188	9	,	,	PUNCT
ajst-30190	188	10	xu	xu	PROPN
ajst-30190	188	11	t	t	PROPN
ajst-30190	188	12	,	,	PUNCT
ajst-30190	188	13	et	et	PROPN
ajst-30190	188	14	al	al	PROPN
ajst-30190	188	15	.	.	PROPN
ajst-30190	189	1	mental	mental	ADJ
ajst-30190	189	2	fatigue	fatigue	NOUN
ajst-30190	189	3	degree	degree	NOUN
ajst-30190	189	4	recognition	recognition	NOUN
ajst-30190	189	5	based	base	VERB
ajst-30190	189	6	on	on	ADP
ajst-30190	189	7	relative	relative	ADJ
ajst-30190	189	8	band	band	NOUN
ajst-30190	189	9	power	power	NOUN
ajst-30190	189	10	and	and	CCONJ
ajst-30190	189	11	fuzzy	fuzzy	ADJ
ajst-30190	189	12	entropy	entropy	NOUN
ajst-30190	189	13	of	of	ADP
ajst-30190	189	14	eeg[j	eeg[j	NOUN
ajst-30190	189	15	]	]	PUNCT
ajst-30190	189	16	.	.	PUNCT
ajst-30190	190	1	int	int	PROPN
ajst-30190	191	1	j	j	PROPN
ajst-30190	191	2	environ	environ	PROPN
ajst-30190	191	3	res	re	VERB
ajst-30190	191	4	public	public	ADJ
ajst-30190	191	5	health	health	NOUN
ajst-30190	191	6	,	,	PUNCT
ajst-30190	191	7	2023,20(2	2023,20(2	PROPN
ajst-30190	191	8	)	)	PUNCT
ajst-30190	191	9	.	.	PUNCT
ajst-30190	192	1	[	[	X
ajst-30190	192	2	16	16	NUM
ajst-30190	192	3	]	]	PUNCT
ajst-30190	192	4	chaddad	chaddad	PROPN
ajst-30190	192	5	a	a	PROPN
ajst-30190	192	6	,	,	PUNCT
ajst-30190	192	7	wu	wu	PROPN
ajst-30190	192	8	y	y	PROPN
ajst-30190	192	9	,	,	PUNCT
ajst-30190	192	10	kateb	kateb	NOUN
ajst-30190	192	11	r	r	NOUN
ajst-30190	192	12	,	,	PUNCT
ajst-30190	192	13	et	et	PROPN
ajst-30190	192	14	al	al	PROPN
ajst-30190	192	15	.	.	PROPN
ajst-30190	192	16	electroencephalography	electroencephalography	PROPN
ajst-30190	192	17	signal	signal	NOUN
ajst-30190	192	18	processing	processing	NOUN
ajst-30190	192	19	:	:	PUNCT
ajst-30190	192	20	a	a	DET
ajst-30190	192	21	comprehensive	comprehensive	ADJ
ajst-30190	192	22	review	review	NOUN
ajst-30190	192	23	and	and	CCONJ
ajst-30190	192	24	analysis	analysis	NOUN
ajst-30190	192	25	of	of	ADP
ajst-30190	192	26	methods	method	NOUN
ajst-30190	192	27	and	and	CCONJ
ajst-30190	192	28	techniques[j	techniques[j	NOUN
ajst-30190	192	29	]	]	PUNCT
ajst-30190	192	30	.	.	PUNCT
ajst-30190	193	1	sensors	sensor	NOUN
ajst-30190	193	2	(	(	PUNCT
ajst-30190	193	3	basel	basel	PROPN
ajst-30190	193	4	)	)	PUNCT
ajst-30190	193	5	,	,	PUNCT
ajst-30190	193	6	2023,23(14	2023,23(14	NUM
ajst-30190	193	7	)	)	PUNCT
ajst-30190	193	8	.	.	PUNCT
ajst-30190	194	1	[	[	X
ajst-30190	194	2	17	17	NUM
ajst-30190	194	3	]	]	X
ajst-30190	194	4	yan	yan	PROPN
ajst-30190	194	5	t	t	PROPN
ajst-30190	194	6	,	,	PUNCT
ajst-30190	194	7	wang	wang	PROPN
ajst-30190	194	8	d	d	PROPN
ajst-30190	194	9	,	,	PUNCT
ajst-30190	194	10	xia	xia	PROPN
ajst-30190	194	11	t	t	PROPN
ajst-30190	194	12	,	,	PUNCT
ajst-30190	194	13	et	et	PROPN
ajst-30190	194	14	al	al	PROPN
ajst-30190	194	15	.	.	PUNCT
ajst-30190	195	1	investigations	investigation	NOUN
ajst-30190	195	2	on	on	ADP
ajst-30190	195	3	generalized	generalized	ADJ
ajst-30190	195	4	hjorth	hjorth	NOUN
ajst-30190	195	5	's	's	PART
ajst-30190	195	6	parameters	parameter	NOUN
ajst-30190	195	7	for	for	ADP
ajst-30190	195	8	machine	machine	NOUN
ajst-30190	195	9	performance	performance	NOUN
ajst-30190	195	10	degradation	degradation	NOUN
ajst-30190	195	11	assessment[j	assessment[j	X
ajst-30190	195	12	]	]	PUNCT
ajst-30190	195	13	.	.	PUNCT
ajst-30190	196	1	mechanical	mechanical	ADJ
ajst-30190	196	2	systems	system	NOUN
ajst-30190	196	3	and	and	CCONJ
ajst-30190	196	4	signal	signal	NOUN
ajst-30190	196	5	processing	processing	NOUN
ajst-30190	196	6	,	,	PUNCT
ajst-30190	196	7	2022,168	2022,168	NUM
ajst-30190	196	8	.	.	PUNCT
ajst-30190	197	1	150	150	NUM
ajst-30190	198	1	[	[	SYM
ajst-30190	198	2	18	18	NUM
ajst-30190	198	3	]	]	X
ajst-30190	198	4	hag	hag	X
ajst-30190	198	5	a	a	PRON
ajst-30190	198	6	,	,	PUNCT
ajst-30190	198	7	al	al	PROPN
ajst-30190	198	8	-	-	PUNCT
ajst-30190	198	9	shargie	shargie	PROPN
ajst-30190	198	10	f	f	PROPN
ajst-30190	198	11	,	,	PUNCT
ajst-30190	198	12	handayani	handayani	PROPN
ajst-30190	198	13	d	d	PROPN
ajst-30190	198	14	,	,	PUNCT
ajst-30190	198	15	et	et	PROPN
ajst-30190	198	16	al	al	PROPN
ajst-30190	198	17	.	.	PROPN
ajst-30190	198	18	mental	mental	ADJ
ajst-30190	198	19	stress	stress	NOUN
ajst-30190	198	20	classification	classification	NOUN
ajst-30190	198	21	based	base	VERB
ajst-30190	198	22	on	on	ADP
ajst-30190	198	23	selected	select	VERB
ajst-30190	198	24	electroencephalography	electroencephalography	NOUN
ajst-30190	198	25	channels	channel	NOUN
ajst-30190	198	26	using	use	VERB
ajst-30190	198	27	correlation	correlation	NOUN
ajst-30190	198	28	coefficient	coefficient	NOUN
ajst-30190	198	29	of	of	ADP
ajst-30190	198	30	hjorth	hjorth	NOUN
ajst-30190	198	31	parameters	parameter	NOUN
ajst-30190	199	1	[	[	X
ajst-30190	199	2	j	j	X
ajst-30190	199	3	]	]	X
ajst-30190	199	4	.	.	PUNCT
ajst-30190	200	1	brain	brain	PROPN
ajst-30190	200	2	sci	sci	PROPN
ajst-30190	200	3	,	,	PUNCT
ajst-30190	200	4	2023,13(9	2023,13(9	PROPN
ajst-30190	200	5	)	)	PUNCT
ajst-30190	200	6	.	.	PUNCT
ajst-30190	201	1	[	[	X
ajst-30190	201	2	19	19	NUM
ajst-30190	201	3	]	]	PUNCT
ajst-30190	201	4	cizmeci	cizmeci	PROPN
ajst-30190	201	5	h	h	PROPN
ajst-30190	201	6	,	,	PUNCT
ajst-30190	201	7	ozcan	ozcan	ADJ
ajst-30190	201	8	c	c	X
ajst-30190	201	9	,	,	PUNCT
ajst-30190	201	10	durgut	durgut	PROPN
ajst-30190	201	11	r.	r.	PROPN
ajst-30190	201	12	channel	channel	PROPN
ajst-30190	201	13	selection	selection	NOUN
ajst-30190	201	14	and	and	CCONJ
ajst-30190	201	15	feature	feature	NOUN
ajst-30190	201	16	extraction	extraction	NOUN
ajst-30190	201	17	on	on	ADP
ajst-30190	201	18	deep	deep	ADJ
ajst-30190	201	19	eeg	eeg	NOUN
ajst-30190	201	20	classification	classification	NOUN
ajst-30190	201	21	using	use	VERB
ajst-30190	201	22	metaheuristic	metaheuristic	ADJ
ajst-30190	201	23	and	and	CCONJ
ajst-30190	201	24	welch	welch	PROPN
ajst-30190	201	25	psd[j	psd[j	PROPN
ajst-30190	201	26	]	]	PUNCT
ajst-30190	201	27	.	.	PUNCT
ajst-30190	202	1	soft	soft	ADJ
ajst-30190	202	2	computing	computing	NOUN
ajst-30190	202	3	,	,	PUNCT
ajst-30190	202	4	2022,26(19	2022,26(19	NUM
ajst-30190	202	5	):	):	PUNCT
ajst-30190	202	6	10115	10115	NUM
ajst-30190	202	7	-	-	SYM
ajst-30190	202	8	10125	10125	NUM
ajst-30190	202	9	.	.	PUNCT
ajst-30190	203	1	[	[	X
ajst-30190	203	2	20	20	NUM
ajst-30190	203	3	]	]	X
ajst-30190	203	4	zhang	zhang	PROPN
ajst-30190	203	5	y	y	PROPN
ajst-30190	203	6	,	,	PUNCT
ajst-30190	203	7	liu	liu	PROPN
ajst-30190	203	8	b	b	PROPN
ajst-30190	203	9	,	,	PUNCT
ajst-30190	203	10	ji	ji	PROPN
ajst-30190	203	11	x	x	PROPN
ajst-30190	203	12	,	,	PUNCT
ajst-30190	203	13	et	et	PROPN
ajst-30190	203	14	al	al	PROPN
ajst-30190	203	15	.	.	PUNCT
ajst-30190	204	1	classification	classification	NOUN
ajst-30190	204	2	of	of	ADP
ajst-30190	204	3	eeg	eeg	NOUN
ajst-30190	204	4	signals	signal	NOUN
ajst-30190	204	5	based	base	VERB
ajst-30190	204	6	on	on	ADP
ajst-30190	204	7	autoregressive	autoregressive	ADJ
ajst-30190	204	8	model	model	NOUN
ajst-30190	204	9	and	and	CCONJ
ajst-30190	204	10	wavelet	wavelet	NOUN
ajst-30190	204	11	packet	packet	NOUN
ajst-30190	204	12	decomposition[j	decomposition[j	PROPN
ajst-30190	204	13	]	]	PUNCT
ajst-30190	204	14	.	.	PUNCT
ajst-30190	205	1	neural	neural	ADJ
ajst-30190	205	2	processing	processing	NOUN
ajst-30190	205	3	letters	letter	NOUN
ajst-30190	205	4	,	,	PUNCT
ajst-30190	205	5	2017,45(2	2017,45(2	NUM
ajst-30190	205	6	):	):	PUNCT
ajst-30190	205	7	365378	365378	NUM
ajst-30190	205	8	.	.	PUNCT
ajst-30190	206	1	[	[	X
ajst-30190	206	2	21	21	NUM
ajst-30190	206	3	]	]	PUNCT
ajst-30190	206	4	ye	ye	PROPN
ajst-30190	206	5	b	b	PROPN
ajst-30190	206	6	,	,	PUNCT
ajst-30190	206	7	qiu	qiu	PROPN
ajst-30190	206	8	t	t	PROPN
ajst-30190	206	9	,	,	PUNCT
ajst-30190	206	10	bai	bai	PROPN
ajst-30190	206	11	x	x	SYM
ajst-30190	206	12	,	,	PUNCT
ajst-30190	206	13	et	et	PROPN
ajst-30190	206	14	al	al	PROPN
ajst-30190	206	15	.	.	PROPN
ajst-30190	206	16	research	research	NOUN
ajst-30190	206	17	on	on	ADP
ajst-30190	206	18	recognition	recognition	NOUN
ajst-30190	206	19	method	method	NOUN
ajst-30190	206	20	of	of	ADP
ajst-30190	206	21	driving	drive	VERB
ajst-30190	206	22	fatigue	fatigue	NOUN
ajst-30190	206	23	state	state	NOUN
ajst-30190	206	24	based	base	VERB
ajst-30190	206	25	on	on	ADP
ajst-30190	206	26	sample	sample	NOUN
ajst-30190	206	27	entropy	entropy	NOUN
ajst-30190	206	28	and	and	CCONJ
ajst-30190	206	29	kernel	kernel	PROPN
ajst-30190	206	30	principal	principal	PROPN
ajst-30190	206	31	component	component	PROPN
ajst-30190	206	32	analysis[j	analysis[j	PROPN
ajst-30190	206	33	]	]	PUNCT
ajst-30190	206	34	.	.	PUNCT
ajst-30190	207	1	entropy	entropy	PROPN
ajst-30190	207	2	(	(	PUNCT
ajst-30190	207	3	basel	basel	PROPN
ajst-30190	207	4	)	)	PUNCT
ajst-30190	207	5	,	,	PUNCT
ajst-30190	207	6	2018,20(9	2018,20(9	NUM
ajst-30190	207	7	)	)	PUNCT
ajst-30190	207	8	.	.	PUNCT
ajst-30190	208	1	[	[	X
ajst-30190	208	2	22	22	NUM
ajst-30190	208	3	]	]	X
ajst-30190	208	4	chen	chen	PROPN
ajst-30190	208	5	s	s	PROPN
ajst-30190	208	6	,	,	PUNCT
ajst-30190	208	7	luo	luo	PROPN
ajst-30190	208	8	z	z	PROPN
ajst-30190	208	9	,	,	PUNCT
ajst-30190	208	10	gan	gan	PROPN
ajst-30190	208	11	h.	h.	PROPN
ajst-30190	208	12	an	an	DET
ajst-30190	208	13	entropy	entropy	NOUN
ajst-30190	208	14	fusion	fusion	NOUN
ajst-30190	208	15	method	method	NOUN
ajst-30190	208	16	for	for	ADP
ajst-30190	208	17	feature	feature	NOUN
ajst-30190	208	18	extraction	extraction	NOUN
ajst-30190	208	19	of	of	ADP
ajst-30190	208	20	eeg[j	eeg[j	NOUN
ajst-30190	208	21	]	]	PUNCT
ajst-30190	208	22	.	.	PUNCT
ajst-30190	209	1	neural	neural	ADJ
ajst-30190	209	2	computing	computing	NOUN
ajst-30190	209	3	and	and	CCONJ
ajst-30190	209	4	applications	application	NOUN
ajst-30190	209	5	,	,	PUNCT
ajst-30190	209	6	2018,29(10	2018,29(10	NUM
ajst-30190	209	7	):	):	PUNCT
ajst-30190	209	8	857	857	NUM
ajst-30190	209	9	-	-	SYM
ajst-30190	209	10	863	863	NUM
ajst-30190	209	11	.	.	PUNCT
ajst-30190	210	1	[	[	X
ajst-30190	210	2	23	23	NUM
ajst-30190	210	3	]	]	X
ajst-30190	210	4	liu	liu	PROPN
ajst-30190	210	5	y	y	PROPN
ajst-30190	210	6	,	,	PUNCT
ajst-30190	210	7	xiang	xiang	PROPN
ajst-30190	211	1	z	z	PROPN
ajst-30190	211	2	,	,	PUNCT
ajst-30190	211	3	yan	yan	PROPN
ajst-30190	212	1	z	z	X
ajst-30190	212	2	,	,	PUNCT
ajst-30190	212	3	et	et	PROPN
ajst-30190	212	4	al	al	PROPN
ajst-30190	212	5	.	.	PROPN
ajst-30190	212	6	ceemdan	ceemdan	PROPN
ajst-30190	212	7	fuzzy	fuzzy	PROPN
ajst-30190	212	8	entropy	entropy	PROPN
ajst-30190	212	9	based	base	VERB
ajst-30190	212	10	fatigue	fatigue	NOUN
ajst-30190	212	11	driving	drive	VERB
ajst-30190	212	12	detection	detection	NOUN
ajst-30190	212	13	using	use	VERB
ajst-30190	212	14	single	single	ADJ
ajst-30190	212	15	-	-	PUNCT
ajst-30190	212	16	channel	channel	NOUN
ajst-30190	212	17	eeg[j	eeg[j	NOUN
ajst-30190	212	18	]	]	PUNCT
ajst-30190	212	19	.	.	PUNCT
ajst-30190	213	1	biomedical	biomedical	ADJ
ajst-30190	213	2	signal	signal	NOUN
ajst-30190	213	3	processing	processing	NOUN
ajst-30190	213	4	and	and	CCONJ
ajst-30190	213	5	control	control	NOUN
ajst-30190	213	6	,	,	PUNCT
ajst-30190	213	7	2024,95	2024,95	NUM
ajst-30190	213	8	.	.	PUNCT
ajst-30190	214	1	[	[	X
ajst-30190	214	2	24	24	NUM
ajst-30190	214	3	]	]	PUNCT
ajst-30190	214	4	ye	ye	PROPN
ajst-30190	214	5	b	b	PROPN
ajst-30190	214	6	,	,	PUNCT
ajst-30190	214	7	qiu	qiu	PROPN
ajst-30190	214	8	t	t	PROPN
ajst-30190	214	9	,	,	PUNCT
ajst-30190	214	10	bai	bai	PROPN
ajst-30190	214	11	x	x	SYM
ajst-30190	214	12	,	,	PUNCT
ajst-30190	214	13	et	et	PROPN
ajst-30190	214	14	al	al	PROPN
ajst-30190	214	15	.	.	PROPN
ajst-30190	214	16	research	research	NOUN
ajst-30190	214	17	on	on	ADP
ajst-30190	214	18	recognition	recognition	NOUN
ajst-30190	214	19	method	method	NOUN
ajst-30190	214	20	of	of	ADP
ajst-30190	214	21	driving	drive	VERB
ajst-30190	214	22	fatigue	fatigue	NOUN
ajst-30190	214	23	state	state	NOUN
ajst-30190	214	24	based	base	VERB
ajst-30190	214	25	on	on	ADP
ajst-30190	214	26	sample	sample	NOUN
ajst-30190	214	27	entropy	entropy	NOUN
ajst-30190	214	28	and	and	CCONJ
ajst-30190	214	29	kernel	kernel	PROPN
ajst-30190	214	30	principal	principal	PROPN
ajst-30190	214	31	component	component	PROPN
ajst-30190	214	32	analysis[j	analysis[j	PROPN
ajst-30190	214	33	]	]	PUNCT
ajst-30190	214	34	.	.	PUNCT
ajst-30190	215	1	entropy	entropy	PROPN
ajst-30190	215	2	(	(	PUNCT
ajst-30190	215	3	basel	basel	PROPN
ajst-30190	215	4	)	)	PUNCT
ajst-30190	215	5	,	,	PUNCT
ajst-30190	215	6	2018,20(9	2018,20(9	NUM
ajst-30190	215	7	)	)	PUNCT
ajst-30190	215	8	.	.	PUNCT
ajst-30190	216	1	[	[	X
ajst-30190	216	2	25	25	NUM
ajst-30190	216	3	]	]	X
ajst-30190	216	4	peng	peng	PROPN
ajst-30190	216	5	y	y	PROPN
ajst-30190	216	6	,	,	PUNCT
ajst-30190	216	7	wong	wong	PROPN
ajst-30190	216	8	c	c	PROPN
ajst-30190	216	9	m	m	PROPN
ajst-30190	216	10	,	,	PUNCT
ajst-30190	216	11	wang	wang	PROPN
ajst-30190	216	12	z	z	PROPN
ajst-30190	216	13	,	,	PUNCT
ajst-30190	216	14	et	et	PROPN
ajst-30190	216	15	al	al	PROPN
ajst-30190	216	16	.	.	PROPN
ajst-30190	216	17	fatigue	fatigue	NOUN
ajst-30190	216	18	detection	detection	NOUN
ajst-30190	216	19	in	in	ADP
ajst-30190	216	20	ssvep	ssvep	NOUN
ajst-30190	216	21	-	-	PUNCT
ajst-30190	216	22	bcis	bcis	NOUN
ajst-30190	216	23	based	base	VERB
ajst-30190	216	24	on	on	ADP
ajst-30190	216	25	wavelet	wavelet	NOUN
ajst-30190	216	26	entropy	entropy	NOUN
ajst-30190	216	27	of	of	ADP
ajst-30190	216	28	eeg[j	eeg[j	NOUN
ajst-30190	216	29	]	]	PUNCT
ajst-30190	216	30	.	.	PUNCT
ajst-30190	217	1	ieee	ieee	NOUN
ajst-30190	217	2	access	access	NOUN
ajst-30190	217	3	,	,	PUNCT
ajst-30190	217	4	2021,9	2021,9	NUM
ajst-30190	217	5	:	:	PUNCT
ajst-30190	217	6	114905	114905	NUM
ajst-30190	217	7	-	-	SYM
ajst-30190	217	8	114913	114913	NUM
ajst-30190	217	9	.	.	PUNCT
ajst-30190	218	1	[	[	X
ajst-30190	218	2	26	26	NUM
ajst-30190	218	3	]	]	X
ajst-30190	218	4	zhang	zhang	PROPN
ajst-30190	218	5	n	n	CCONJ
ajst-30190	218	6	,	,	PUNCT
ajst-30190	218	7	ding	ding	NOUN
ajst-30190	218	8	s	s	PROPN
ajst-30190	218	9	,	,	PUNCT
ajst-30190	218	10	zhang	zhang	PROPN
ajst-30190	218	11	j	j	PROPN
ajst-30190	218	12	,	,	PUNCT
ajst-30190	218	13	et	et	PROPN
ajst-30190	218	14	al	al	PROPN
ajst-30190	218	15	.	.	PUNCT
ajst-30190	219	1	an	an	DET
ajst-30190	219	2	overview	overview	NOUN
ajst-30190	219	3	on	on	ADP
ajst-30190	219	4	restricted	restrict	VERB
ajst-30190	219	5	boltzmann	boltzmann	PROPN
ajst-30190	219	6	machines[j	machines[j	PROPN
ajst-30190	219	7	]	]	PUNCT
ajst-30190	219	8	.	.	PUNCT
ajst-30190	220	1	neurocomputing	neurocomputing	NOUN
ajst-30190	220	2	,	,	PUNCT
ajst-30190	220	3	2018	2018	NUM
ajst-30190	220	4	,	,	PUNCT
ajst-30190	220	5	275	275	NUM
ajst-30190	220	6	:	:	SYM
ajst-30190	220	7	1186	1186	NUM
ajst-30190	220	8	-	-	SYM
ajst-30190	220	9	1199	1199	NUM
ajst-30190	220	10	.	.	PUNCT
ajst-30190	221	1	[	[	X
ajst-30190	221	2	27	27	NUM
ajst-30190	221	3	]	]	X
ajst-30190	221	4	f.	f.	PROPN
ajst-30190	221	5	y	y	PROPN
ajst-30190	221	6	,	,	PUNCT
ajst-30190	221	7	s.	s.	PROPN
ajst-30190	221	8	l	l	PROPN
ajst-30190	221	9	,	,	PUNCT
ajst-30190	221	10	e.	e.	PROPN
ajst-30190	221	11	d	d	PROPN
ajst-30190	221	12	,	,	PUNCT
ajst-30190	221	13	et	et	PROPN
ajst-30190	221	14	al	al	PROPN
ajst-30190	221	15	.	.	PUNCT
ajst-30190	222	1	how	how	SCONJ
ajst-30190	222	2	to	to	PART
ajst-30190	222	3	reduce	reduce	VERB
ajst-30190	222	4	dimension	dimension	NOUN
ajst-30190	222	5	with	with	ADP
ajst-30190	222	6	pca	pca	NOUN
ajst-30190	222	7	and	and	CCONJ
ajst-30190	222	8	random	random	ADJ
ajst-30190	222	9	projections?[j	projections?[j	NOUN
ajst-30190	222	10	]	]	PUNCT
ajst-30190	222	11	.	.	PUNCT
ajst-30190	223	1	ieee	ieee	NOUN
ajst-30190	223	2	transactions	transaction	NOUN
ajst-30190	223	3	on	on	ADP
ajst-30190	223	4	information	information	NOUN
ajst-30190	223	5	theory	theory	NOUN
ajst-30190	223	6	,	,	PUNCT
ajst-30190	223	7	2021,67(12	2021,67(12	NUM
ajst-30190	223	8	):	):	PUNCT
ajst-30190	223	9	8154	8154	NUM
ajst-30190	223	10	-	-	SYM
ajst-30190	223	11	8189	8189	NUM
ajst-30190	223	12	.	.	PUNCT
ajst-30190	224	1	[	[	X
ajst-30190	224	2	28	28	NUM
ajst-30190	224	3	]	]	X
ajst-30190	224	4	lan	lan	PROPN
ajst-30190	224	5	z	z	PROPN
ajst-30190	224	6	,	,	PUNCT
ajst-30190	224	7	zhao	zhao	PROPN
ajst-30190	224	8	j	j	PROPN
ajst-30190	224	9	,	,	PUNCT
ajst-30190	224	10	liu	liu	PROPN
ajst-30190	224	11	p	p	PROPN
ajst-30190	224	12	,	,	PUNCT
ajst-30190	224	13	et	et	PROPN
ajst-30190	224	14	al	al	PROPN
ajst-30190	224	15	.	.	PROPN
ajst-30190	224	16	driving	drive	VERB
ajst-30190	224	17	fatigue	fatigue	NOUN
ajst-30190	224	18	detection	detection	NOUN
ajst-30190	224	19	based	base	VERB
ajst-30190	224	20	on	on	ADP
ajst-30190	224	21	fusion	fusion	NOUN
ajst-30190	224	22	of	of	ADP
ajst-30190	224	23	eeg	eeg	NOUN
ajst-30190	224	24	and	and	CCONJ
ajst-30190	224	25	vehicle	vehicle	NOUN
ajst-30190	224	26	motion	motion	NOUN
ajst-30190	224	27	information[j	information[j	PROPN
ajst-30190	224	28	]	]	PUNCT
ajst-30190	224	29	.	.	PUNCT
ajst-30190	225	1	biomedical	biomedical	ADJ
ajst-30190	225	2	signal	signal	NOUN
ajst-30190	225	3	processing	processing	NOUN
ajst-30190	225	4	and	and	CCONJ
ajst-30190	225	5	control	control	NOUN
ajst-30190	225	6	,	,	PUNCT
ajst-30190	225	7	2024,92	2024,92	NUM
ajst-30190	225	8	.	.	PUNCT