Classification Algorithm for fNIRS-based Brain Signals Using Convolutional Neural Network with Spatiotemporal Feature Extraction Mechanism

This graphic shows the structure of our network. In the preprocessing section, we used the Beer-Lambert law to convert the optical signals into hemodynamic HbR and HbO. We used an end-to-end structure without much preprocessing of the raw fNIRS signal. We input the signal with the number of channels...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Neuroscience Jg. 542; S. 59 - 68
Hauptverfasser: Qin, Yuxin, Li, Baojiang, Wang, Wenlong, Shi, Xingbin, Peng, Cheng, Lu, Yifan
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States Elsevier Inc 26.03.2024
Schlagworte:
ISSN:0306-4522, 1873-7544, 1873-7544
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract This graphic shows the structure of our network. In the preprocessing section, we used the Beer-Lambert law to convert the optical signals into hemodynamic HbR and HbO. We used an end-to-end structure without much preprocessing of the raw fNIRS signal. We input the signal with the number of channels C = 24 and the number of samples T = 351. the original MI and MA signals are first passed through a convolution block. The convolution block consists of a 2D time convolution, a depth convolution, and a separable convolution, each followed by a Batch Normalization layer, an ELU activation function, an average pooling layer, and a dropout layer. Afterwards, spatio-temporal feature extraction is performed by spatial attention and temporal convolutional networks, capable of reducing overfitting. Finally, the fNIRS signal is classified as MI or MA. The results show that the method using only 3.23 K training parameters has an accuracy of 85.63% (HbO) and 86.21% (HbR) in the MI task and 96.84% (HbO) and 94.83% (HbR) in the MA task. [Display omitted] •fNIRS decoding performance improvement.•Using Convolutional Neural Networks for fNIRS Classification.•Spatial attention mechanisms can capture remote contextual information.•Temporal convolutional network outperforms most RNN in time-series tasks. Brain Computer Interface (BCI) is a highly promising human–computer interaction method that can utilize brain signals to control external devices. BCI based on functional near-infrared spectroscopy (fNIRS) is considered a relatively new and promising paradigm. fNIRS is a technique of measuring functional changes in cerebral hemodynamics. It detects changes in the hemodynamic activity of the cerebral cortex by measuring oxyhemoglobin and deoxyhemoglobin (HbR) concentrations and inversely predicts the neural activity of the brain. At the present time, Deep learning (DL) methods have not been widely used in fNIRS decoding, and there are fewer studies considering both spatial and temporal dimensions for fNIRS classification. To solve these problems, we proposed an end-to-end hybrid neural network for feature extraction of fNIRS. The method utilizes a spatial–temporal convolutional layer for automatic extraction of temporally valid information and uses a spatial attention mechanism to extract spatially localized information. A temporal convolutional network (TCN) is used to further utilize the temporal information of fNIRS before the fully connected layer. We validated our approach on a publicly available dataset including 29 subjects, including left-hand and right-hand motor imagery (MI), mental arithmetic (MA), and a baseline task. The results show that the method has few training parameters and high accuracy, providing a meaningful reference for BCI development.
AbstractList This graphic shows the structure of our network. In the preprocessing section, we used the Beer-Lambert law to convert the optical signals into hemodynamic HbR and HbO. We used an end-to-end structure without much preprocessing of the raw fNIRS signal. We input the signal with the number of channels C = 24 and the number of samples T = 351. the original MI and MA signals are first passed through a convolution block. The convolution block consists of a 2D time convolution, a depth convolution, and a separable convolution, each followed by a Batch Normalization layer, an ELU activation function, an average pooling layer, and a dropout layer. Afterwards, spatio-temporal feature extraction is performed by spatial attention and temporal convolutional networks, capable of reducing overfitting. Finally, the fNIRS signal is classified as MI or MA. The results show that the method using only 3.23 K training parameters has an accuracy of 85.63% (HbO) and 86.21% (HbR) in the MI task and 96.84% (HbO) and 94.83% (HbR) in the MA task. [Display omitted] •fNIRS decoding performance improvement.•Using Convolutional Neural Networks for fNIRS Classification.•Spatial attention mechanisms can capture remote contextual information.•Temporal convolutional network outperforms most RNN in time-series tasks. Brain Computer Interface (BCI) is a highly promising human–computer interaction method that can utilize brain signals to control external devices. BCI based on functional near-infrared spectroscopy (fNIRS) is considered a relatively new and promising paradigm. fNIRS is a technique of measuring functional changes in cerebral hemodynamics. It detects changes in the hemodynamic activity of the cerebral cortex by measuring oxyhemoglobin and deoxyhemoglobin (HbR) concentrations and inversely predicts the neural activity of the brain. At the present time, Deep learning (DL) methods have not been widely used in fNIRS decoding, and there are fewer studies considering both spatial and temporal dimensions for fNIRS classification. To solve these problems, we proposed an end-to-end hybrid neural network for feature extraction of fNIRS. The method utilizes a spatial–temporal convolutional layer for automatic extraction of temporally valid information and uses a spatial attention mechanism to extract spatially localized information. A temporal convolutional network (TCN) is used to further utilize the temporal information of fNIRS before the fully connected layer. We validated our approach on a publicly available dataset including 29 subjects, including left-hand and right-hand motor imagery (MI), mental arithmetic (MA), and a baseline task. The results show that the method has few training parameters and high accuracy, providing a meaningful reference for BCI development.
Brain Computer Interface (BCI) is a highly promising human-computer interaction method that can utilize brain signals to control external devices. BCI based on functional near-infrared spectroscopy (fNIRS) is considered a relatively new and promising paradigm. fNIRS is a technique of measuring functional changes in cerebral hemodynamics. It detects changes in the hemodynamic activity of the cerebral cortex by measuring oxyhemoglobin and deoxyhemoglobin (HbR) concentrations and inversely predicts the neural activity of the brain. At the present time, Deep learning (DL) methods have not been widely used in fNIRS decoding, and there are fewer studies considering both spatial and temporal dimensions for fNIRS classification. To solve these problems, we proposed an end-to-end hybrid neural network for feature extraction of fNIRS. The method utilizes a spatial-temporal convolutional layer for automatic extraction of temporally valid information and uses a spatial attention mechanism to extract spatially localized information. A temporal convolutional network (TCN) is used to further utilize the temporal information of fNIRS before the fully connected layer. We validated our approach on a publicly available dataset including 29 subjects, including left-hand and right-hand motor imagery (MI), mental arithmetic (MA), and a baseline task. The results show that the method has few training parameters and high accuracy, providing a meaningful reference for BCI development.
Brain Computer Interface (BCI) is a highly promising human-computer interaction method that can utilize brain signals to control external devices. BCI based on functional near-infrared spectroscopy (fNIRS) is considered a relatively new and promising paradigm. fNIRS is a technique of measuring functional changes in cerebral hemodynamics. It detects changes in the hemodynamic activity of the cerebral cortex by measuring oxyhemoglobin and deoxyhemoglobin (HbR) concentrations and inversely predicts the neural activity of the brain. At the present time, Deep learning (DL) methods have not been widely used in fNIRS decoding, and there are fewer studies considering both spatial and temporal dimensions for fNIRS classification. To solve these problems, we proposed an end-to-end hybrid neural network for feature extraction of fNIRS. The method utilizes a spatial-temporal convolutional layer for automatic extraction of temporally valid information and uses a spatial attention mechanism to extract spatially localized information. A temporal convolutional network (TCN) is used to further utilize the temporal information of fNIRS before the fully connected layer. We validated our approach on a publicly available dataset including 29 subjects, including left-hand and right-hand motor imagery (MI), mental arithmetic (MA), and a baseline task. The results show that the method has few training parameters and high accuracy, providing a meaningful reference for BCI development.Brain Computer Interface (BCI) is a highly promising human-computer interaction method that can utilize brain signals to control external devices. BCI based on functional near-infrared spectroscopy (fNIRS) is considered a relatively new and promising paradigm. fNIRS is a technique of measuring functional changes in cerebral hemodynamics. It detects changes in the hemodynamic activity of the cerebral cortex by measuring oxyhemoglobin and deoxyhemoglobin (HbR) concentrations and inversely predicts the neural activity of the brain. At the present time, Deep learning (DL) methods have not been widely used in fNIRS decoding, and there are fewer studies considering both spatial and temporal dimensions for fNIRS classification. To solve these problems, we proposed an end-to-end hybrid neural network for feature extraction of fNIRS. The method utilizes a spatial-temporal convolutional layer for automatic extraction of temporally valid information and uses a spatial attention mechanism to extract spatially localized information. A temporal convolutional network (TCN) is used to further utilize the temporal information of fNIRS before the fully connected layer. We validated our approach on a publicly available dataset including 29 subjects, including left-hand and right-hand motor imagery (MI), mental arithmetic (MA), and a baseline task. The results show that the method has few training parameters and high accuracy, providing a meaningful reference for BCI development.
Author Lu, Yifan
Wang, Wenlong
Qin, Yuxin
Shi, Xingbin
Li, Baojiang
Peng, Cheng
Author_xml – sequence: 1
  givenname: Yuxin
  orcidid: 0009-0004-2158-8779
  surname: Qin
  fullname: Qin, Yuxin
– sequence: 2
  givenname: Baojiang
  orcidid: 0000-0002-7952-6691
  surname: Li
  fullname: Li, Baojiang
– sequence: 3
  givenname: Wenlong
  surname: Wang
  fullname: Wang, Wenlong
– sequence: 4
  givenname: Xingbin
  surname: Shi
  fullname: Shi, Xingbin
– sequence: 5
  givenname: Cheng
  surname: Peng
  fullname: Peng, Cheng
– sequence: 6
  givenname: Yifan
  surname: Lu
  fullname: Lu, Yifan
BackLink https://www.ncbi.nlm.nih.gov/pubmed/38369007$$D View this record in MEDLINE/PubMed
BookMark eNqNks1u1DAUhS1URKeFV0AWKzYJ_onzw4p2aKFSKRJD15bj3Ew9TeypnbT0FXhqnJkpqroab64ln_PZOsdH6MA6Cwh9oCSlhOafVqmF0bugDVgNKSMsSwlLCaWv0IyWBU8KkWUHaEY4yZNMMHaIjkJYkbhExt-gQ17yvCKkmKG_806FYFqj1WCcxSfd0nkz3PS4dR63Vxe_FkmtAjT41Ctj8cIsreoCvg7GLvHc2XvXjZNTdfgqvmozhgfnb_FDxODFeuIO0K_ddHYOahg94LM_g1d6c-MP0DfKmtC_Ra_biIZ3u3mMrs_Pfs-_J5c_v13MTy4TnfFqSFStykaIUpdFS1gNba7LrOaZolUFtMpB64ZXTHFBWZYJLSoudF6X05ZSkvNj9HHLXXt3N0IYZG-Chq5TFtwYJKtYKcqcFyJK3--kY91DI9fe9Mo_yqf8ouDzVqBjH8FD-19CiZzKkiv5vCw5lSUJk7GsaP7ywqzNsKkhhmO6_RBftwiIgd0b8HKnaowHPcjGmf0wpy8wujM2_onuFh73hfwDiT3TRQ
CitedBy_id crossref_primary_10_1016_j_apacoust_2024_110307
crossref_primary_10_1109_TTS_2025_3556355
crossref_primary_10_3390_s24103040
crossref_primary_10_1111_coin_70044
crossref_primary_10_3390_electronics14051025
crossref_primary_10_3390_e27010014
crossref_primary_10_1016_j_bspc_2025_107503
crossref_primary_10_1371_journal_pone_0325850
Cites_doi 10.1109/TNSRE.2016.2628057
10.1007/s10015-020-00592-9
10.1155/2016/5480760
10.1109/TIP.2019.2921876
10.1109/TBME.2021.3132861
10.1016/j.neuroimage.2013.03.045
10.1016/j.neuroimage.2013.05.004
10.1117/1.NPh.9.4.041411
10.3389/fnhum.2016.00237
10.3390/app10051681
10.1109/TNSRE.2019.2956488
10.48084/etasr.5703
10.1016/j.compbiomed.2019.103355
10.1109/JSEN.2022.3205956
10.1002/jdn.10166
10.1109/ACCESS.2022.3218374
10.1111/nyas.13948
10.1088/1741-2552/aace8c
10.1016/B978-0-323-48067-3.00006-8
10.1016/j.cmpb.2020.105535
10.1007/s00221-013-3764-1
10.1093/brain/awr039
10.1117/1.JBO.21.9.091303
10.34133/cbsystems.0045
10.1007/s00500-020-04954-0
10.1016/j.neuroimage.2013.06.062
ContentType Journal Article
Copyright 2024 IBRO
Copyright © 2024 IBRO. Published by Elsevier Inc. All rights reserved.
Copyright_xml – notice: 2024 IBRO
– notice: Copyright © 2024 IBRO. Published by Elsevier Inc. All rights reserved.
DBID AAYXX
CITATION
NPM
7X8
DOI 10.1016/j.neuroscience.2024.02.011
DatabaseName CrossRef
PubMed
MEDLINE - Academic
DatabaseTitle CrossRef
PubMed
MEDLINE - Academic
DatabaseTitleList

PubMed
MEDLINE - Academic
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Anatomy & Physiology
EISSN 1873-7544
EndPage 68
ExternalDocumentID 38369007
10_1016_j_neuroscience_2024_02_011
S0306452224000617
Genre Journal Article
GroupedDBID ---
--K
--M
-DZ
-~X
.1-
.FO
.~1
0R~
123
1B1
1P~
1RT
1~.
1~5
4.4
457
4G.
5RE
7-5
71M
8P~
9JM
AABNK
AAEDT
AAEDW
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AATTM
AAXKI
AAXLA
AAXUO
AAYWO
ABCQJ
ABFNM
ABFRF
ABJNI
ABLJU
ABMAC
ABTEW
ACDAQ
ACGFO
ACGFS
ACIUM
ACLOT
ACRLP
ACVFH
ADBBV
ADCNI
ADEZE
AEBSH
AEFWE
AEIPS
AEKER
AENEX
AEUPX
AEVXI
AFJKZ
AFPUW
AFRHN
AFTJW
AFXIZ
AGUBO
AGWIK
AGYEJ
AIEXJ
AIGII
AIIUN
AIKHN
AITUG
AJUYK
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
APXCP
AXJTR
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFKBS
EFLBG
EO8
EO9
EP2
EP3
F5P
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
HMQ
IHE
J1W
KOM
L7B
M2V
M41
MO0
MOBAO
N9A
O-L
O9-
OAUVE
OP~
OZT
P-8
P-9
P2P
PC.
Q38
ROL
RPZ
SCC
SDF
SDG
SDP
SES
SPCBC
SSN
SSZ
T5K
UNMZH
Z5R
~G-
~HD
AACTN
AADPK
AAIAV
ABMYL
ABYKQ
AFCTW
AFKWA
AJOXV
AMFUW
RIG
SEW
.55
.GJ
29N
53G
5VS
9DU
AAQXK
AAYXX
ABWVN
ABXDB
ACRPL
ADMUD
ADNMO
AGHFR
AGQPQ
AHHHB
ASPBG
AVWKF
AZFZN
CITATION
EJD
FEDTE
FGOYB
G-2
HVGLF
HZ~
R2-
SNS
WUQ
X7M
YYP
ZGI
ZXP
AGCQF
AGRNS
BNPGV
NPM
SSH
7X8
ID FETCH-LOGICAL-c439t-aba8d558c87f02bef6c84b34a199e196eccd392a3512445c5935c6b845c511063
ISICitedReferencesCount 9
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001236898600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0306-4522
1873-7544
IngestDate Wed Oct 01 07:41:45 EDT 2025
Mon Jul 21 06:04:11 EDT 2025
Sat Nov 29 07:20:52 EST 2025
Tue Nov 18 22:11:16 EST 2025
Sat Mar 23 16:29:10 EDT 2024
Tue Oct 14 19:26:01 EDT 2025
IsPeerReviewed true
IsScholarly true
Keywords spatial attention
fNIRS
EEG
temporal convolutional network
DL
LDA
motor imagery
BCI
SVM
deep learning
fMRI
MA
brain computer interface
MI
TCN
ML
Language English
License Copyright © 2024 IBRO. Published by Elsevier Inc. All rights reserved.
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c439t-aba8d558c87f02bef6c84b34a199e196eccd392a3512445c5935c6b845c511063
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ORCID 0009-0004-2158-8779
0000-0002-7952-6691
PMID 38369007
PQID 2928586375
PQPubID 23479
PageCount 10
ParticipantIDs proquest_miscellaneous_2928586375
pubmed_primary_38369007
crossref_primary_10_1016_j_neuroscience_2024_02_011
crossref_citationtrail_10_1016_j_neuroscience_2024_02_011
elsevier_sciencedirect_doi_10_1016_j_neuroscience_2024_02_011
elsevier_clinicalkey_doi_10_1016_j_neuroscience_2024_02_011
PublicationCentury 2000
PublicationDate 2024-03-26
PublicationDateYYYYMMDD 2024-03-26
PublicationDate_xml – month: 03
  year: 2024
  text: 2024-03-26
  day: 26
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Neuroscience
PublicationTitleAlternate Neuroscience
PublicationYear 2024
Publisher Elsevier Inc
Publisher_xml – name: Elsevier Inc
References Aydin (b0005) 2020; 195
Janani, Sasikala, Chhabra, Shajil, Venkatasubramanian (b0075) 2020; 62
Milu, Rahman, Rashid, Kobayashi (b0100) 2023; 13
Xin, Chen, Li (b0175) 2020; 10
Obrig (b0125) 2014; 85
Wang, Girshick, Gupta, He (b0170) 2018
Si, He, Yu, Ming (b0160) 2023; 4
Naseer, Noori, Qureshi, Hong (b0115) 2016; 10
He, Zhong, PanHe (b0050) 2022
Naseer, Hong, Hong (b0110) 2014; 232
Lawhern, Solon, Waytowich, Gordon, Hung, Lance (b0090) 2018; 15
Hong, Ghafoor, Khan (b0060) 2020; 25
Liu, Qin, Cao, Deng (b0095) 2022; 10
Naseer, Qureshi, Noori, Hong (b0120) 2016
Sanghyun, Jongchan, Joon-Young, In (b0145) 2018
Wang, Wu, Tao, Lee, Cao, Yan, Wang (b0165) 2023
Guo, Wang, Yang, Kang (b0040) 2021
Zheng, Fu, Luo, Mei (b0195) 2020; 29
Pinti, Tachtsidis, Hamilton, Hirsch, Aichelburg, Gilbert, Burgess (b0130) 2020; 1464
Zabcikova, Koudelkova, Jasek, Navarro (b0190) 2022; 82
Hewage, Behera, Trovati, Pereira, Ghahremani, Palmieri, Liu (b0055) 2020; 24
Dashtestani, Zaragoza, Kermanian, Condy, Anderson, Chowdhry, Karamzadeh, Miguel (b0025) 2019
Ghafoor, Zafar, Yaqub, Hong (b0035) 2019
Chen, Lin, Dong Liang, Zhang, Iwamoto, Han, Chen (b0010) 2019
Mughal, Khalil, Khan (b0105) 2021
Shin, Lühmann, Blankertz, Kim, Jeong, Hwang, Müller (b0155) 2016; 25
Xu, Chang, Xie, Ma (b0180) 2021
Cooney, Folli, Coyle (b0015) 2021; 69
Eastmond, Subedi, De, Intes (b0030) 2022; 9
Jin, Li, Daly, Miao, Liu, Wang, Cichocki (b0080) 2019; 28
Yoo, Woo, Amad (b0185) 2018
Jin, Wang, Xu, Liu, Wang, Cichocki (b0085) 2021
Hwang, Choi, Kim, Chang, Kim, Kim, Jo, Im (b0070) 2016; 21
Piper, Krueger, Koch, Mehnert, Habermehl, Steinbrink, Obrig, Schmitz (b0135) 2014; 85
Cramer, Sur, Dobkin, O'Brien, Sanger, Trojanowski, Rumsey, Hicks (b0020) 2011; 134
Hu, Shen, Sun (b0065) 2018
He, Feng, Jiang, Xie (b0045) 2022; 22
Scholkmann, KleiserS, Zimmermann, Pavia, Wolf, Wolf (b0150) 2014; 85
Rosas-Romero, Guevara, Peng, Nguyen, Lesage, Pouliot (b0140) 2019; 111
Rosas-Romero (10.1016/j.neuroscience.2024.02.011_b0140) 2019; 111
Aydin (10.1016/j.neuroscience.2024.02.011_b0005) 2020; 195
He (10.1016/j.neuroscience.2024.02.011_b0050) 2022
Cramer (10.1016/j.neuroscience.2024.02.011_b0020) 2011; 134
Hwang (10.1016/j.neuroscience.2024.02.011_b0070) 2016; 21
Wang (10.1016/j.neuroscience.2024.02.011_b0165) 2023
Sanghyun (10.1016/j.neuroscience.2024.02.011_b0145) 2018
Guo (10.1016/j.neuroscience.2024.02.011_b0040) 2021
Pinti (10.1016/j.neuroscience.2024.02.011_b0130) 2020; 1464
Janani (10.1016/j.neuroscience.2024.02.011_b0075) 2020; 62
Mughal (10.1016/j.neuroscience.2024.02.011_b0105) 2021
Yoo (10.1016/j.neuroscience.2024.02.011_b0185) 2018
Liu (10.1016/j.neuroscience.2024.02.011_b0095) 2022; 10
Obrig (10.1016/j.neuroscience.2024.02.011_b0125) 2014; 85
Si (10.1016/j.neuroscience.2024.02.011_b0160) 2023; 4
Hu (10.1016/j.neuroscience.2024.02.011_b0065) 2018
Eastmond (10.1016/j.neuroscience.2024.02.011_b0030) 2022; 9
Milu (10.1016/j.neuroscience.2024.02.011_b0100) 2023; 13
Zabcikova (10.1016/j.neuroscience.2024.02.011_b0190) 2022; 82
Hong (10.1016/j.neuroscience.2024.02.011_b0060) 2020; 25
Scholkmann (10.1016/j.neuroscience.2024.02.011_b0150) 2014; 85
Zheng (10.1016/j.neuroscience.2024.02.011_b0195) 2020; 29
Xin (10.1016/j.neuroscience.2024.02.011_b0175) 2020; 10
Cooney (10.1016/j.neuroscience.2024.02.011_b0015) 2021; 69
Piper (10.1016/j.neuroscience.2024.02.011_b0135) 2014; 85
Naseer (10.1016/j.neuroscience.2024.02.011_b0120) 2016
He (10.1016/j.neuroscience.2024.02.011_b0045) 2022; 22
Lawhern (10.1016/j.neuroscience.2024.02.011_b0090) 2018; 15
Naseer (10.1016/j.neuroscience.2024.02.011_b0115) 2016; 10
Wang (10.1016/j.neuroscience.2024.02.011_b0170) 2018
Jin (10.1016/j.neuroscience.2024.02.011_b0080) 2019; 28
Naseer (10.1016/j.neuroscience.2024.02.011_b0110) 2014; 232
Jin (10.1016/j.neuroscience.2024.02.011_b0085) 2021
Hewage (10.1016/j.neuroscience.2024.02.011_b0055) 2020; 24
Shin (10.1016/j.neuroscience.2024.02.011_b0155) 2016; 25
Ghafoor (10.1016/j.neuroscience.2024.02.011_b0035) 2019
Chen (10.1016/j.neuroscience.2024.02.011_b0010) 2019
Dashtestani (10.1016/j.neuroscience.2024.02.011_b0025) 2019
Xu (10.1016/j.neuroscience.2024.02.011_b0180) 2021
References_xml – volume: 111
  year: 2019
  ident: b0140
  article-title: Prediction of epileptic seizures with convolutional neural networks and functional near-infrared spectroscopy signals
  publication-title: Comput Biol Med
– volume: 21
  year: 2016
  ident: b0070
  article-title: Toward more intuitive brain-computer interfacing: classification of binary covert intentions using functional near-infrared spectroscopy
  publication-title: J Biomed Opt
– volume: 22
  start-page: 20695
  year: 2022
  end-page: 20706
  ident: b0045
  article-title: Multimodal multitask neural network for motor imagery classification with EEG and fNIRS signals
  publication-title: IEEE Sens J
– volume: 10
  start-page: 237
  year: 2016
  ident: b0115
  article-title: Determining optimal feature-combination for LDA classification of functional near-infrared spectroscopy signals in brain-computer interface application
  publication-title: Front Hum Neurosci
– volume: 85
  start-page: 6
  year: 2014
  end-page: 27
  ident: b0150
  article-title: A review on continuous wave functional near-infrared spectroscopy and imaging instrumentation and methodology
  publication-title: Neuroimage
– year: 2016
  ident: b0120
  article-title: Analysis of different classification techniques for two-class functional near-infrared spectroscopy-based brain-computer interface
  publication-title: Computat Intell Neurosci
– start-page: 3
  year: 2018
  end-page: 19
  ident: b0145
  article-title: Cbam: Convolutional block attention module
  publication-title: Proceedings of the European conference on computer vision (ECCV)
– volume: 69
  start-page: 1983
  year: 2021
  end-page: 1994
  ident: b0015
  article-title: A bimodal deep learning architecture for EEG-fNIRS decoding of overt and imagined speech
  publication-title: IEEE Trans Biomed Eng
– volume: 25
  start-page: 204
  year: 2020
  end-page: 218
  ident: b0060
  article-title: Brain-machine interfaces using functional near-infrared spectroscopy: a review
  publication-title: Artif Life Robot
– volume: 85
  start-page: 64
  year: 2014
  end-page: 71
  ident: b0135
  article-title: A wearable multi-channel fNIRS system for brain imaging in freely moving subjects
  publication-title: Neuroimage
– year: 2021
  ident: b0040
  article-title: IEEG-TCN: A Concise and Robust Temporal Convolutional Network for Intracranial Electroencephalogram Signal Identification
  publication-title: 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
– volume: 1464
  start-page: 5
  year: 2020
  end-page: 29
  ident: b0130
  article-title: The present and future use of functional near-infrared spectroscopy (fNIRS) for cognitive neuroscience
  publication-title: Ann N Y Acad Sci
– volume: 82
  start-page: 107
  year: 2022
  end-page: 123
  ident: b0190
  article-title: Recent advances and current trends in brain-computer interface research and their applications
  publication-title: Int J Dev Neurosci
– year: 2021
  ident: b0180
  article-title: Grad-CAM guided channel-spatial attention module for fine-grained visual classification
  publication-title: 2021 IEEE 31st international workshop on machine learning for signal Processing (MLSP)
– volume: 62
  year: 2020
  ident: b0075
  article-title: Investigation of deep convolutional neural network for classification of motor imagery fNIRS signals for BCI applications
  publication-title: Biomed Signal Process Control
– year: 2023
  ident: b0165
  article-title: The diagnosis of major depressive disorder through wearable fNIRS by using wavelet transform and parallel-CNN feature fusion
  publication-title: IEEE Trans Instrum Meas
– year: 2018
  ident: b0185
  article-title: Classification of three categories from prefrontal cortex using LSTM networks: fNIRS study
  publication-title: 2018 18th International Conference on Control, Automation and Systems (ICCAS)
– volume: 195
  year: 2020
  ident: b0005
  article-title: Subject-Specific feature selection for near infrared spectroscopy based brain-computer interfaces
  publication-title: Comput Methods Programs Biomed
– start-page: 123
  year: 2019
  end-page: 136
  ident: b0025
  article-title: The quest for functional biomarkers in the prefrontal cortex using functional near-infrared spectroscopy (fNIRS)
  publication-title: Neurophoton Biomed Spectrosc
– year: 2021
  ident: b0085
  article-title: Robust similarity measurement based on a novel time filter for SSVEPs detection
  publication-title: IEEE Transactions on Neural Networks and Learning Systems
– year: 2022
  ident: b0050
  article-title: Joint temporal convolutional networks and adversarial discriminative domain adaptation for EEG-based cross-subject emotion recognition
  publication-title: ICASSP 2022–2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
– volume: 13
  start-page: 10425
  year: 2023
  end-page: 10431
  ident: b0100
  article-title: Improvement of classification accuracy of four-class voluntary-imagery fNIRS signals using convolutional neural networks
  publication-title: Eng Technol Appl Sci Res
– year: 2021
  ident: b0105
  article-title: fNIRS based multi-class mental workload classification using recurrence plots and CNN-LSTM
  publication-title: 2021 International Conference on Artificial Intelligence and Mechatronics Systems (AIMS)
– start-page: 7794
  year: 2018
  end-page: 7803
  ident: b0170
  article-title: Non-local neural networks
  publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)
– volume: 29
  start-page: 476
  year: 2020
  end-page: 488
  ident: b0195
  article-title: Learning rich part hierarchies with progressive attention networks for fine-grained image recognition
  publication-title: IEEE Trans Image Process
– volume: 10
  start-page: 115945
  year: 2022
  end-page: 115957
  ident: b0095
  article-title: Short-term load forecasting based on improved TCN and DenseNet
  publication-title: IEEE Access
– year: 2019
  ident: b0035
  article-title: Enhancement in classification accuracy of motor imagery signals with visual aid: An fNIRS-BCI Study
  publication-title: 2019 19th International Conference on Control, Automation and Systems (ICCAS)
– volume: 25
  start-page: 1735
  year: 2016
  end-page: 1745
  ident: b0155
  article-title: Open access dataset for EEG+NIRS single-trial classification
  publication-title: IEEE Trans Neural Syst Rehabil Eng
– volume: 28
  start-page: 3
  year: 2019
  end-page: 12
  ident: b0080
  article-title: The study of generic model set for reducing calibration time in P300-based brain–computer interface
  publication-title: IEEE Trans Neural Syst Rehabil Eng
– year: 2018
  ident: b0065
  article-title: Squeeze-and-excitation networks
  publication-title: Proceedings of the IEEE conference on computer vision and pattern recognition
– volume: 9
  year: 2022
  ident: b0030
  article-title: Deep learning in fNIRS: a review
  publication-title: Neurophotonics
– volume: 232
  start-page: 555
  year: 2014
  end-page: 564
  ident: b0110
  article-title: Online binary decision decoding using functional near-infrared spectroscopy for the development of brain–computer interface
  publication-title: Exp Brain Res
– volume: 134
  start-page: 1591
  year: 2011
  end-page: 1609
  ident: b0020
  article-title: Harnessing neuroplasticity for clinical applications
  publication-title: Brain
– volume: 15
  year: 2018
  ident: b0090
  article-title: EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces
  publication-title: J Neural Eng
– year: 2019
  ident: b0010
  article-title: A dual-attention dilated residual network for liver lesion classification and localization on CT images
  publication-title: 2019 IEEE International Conference on Image Processing (ICIP)
– volume: 85
  start-page: 535
  year: 2014
  end-page: 546
  ident: b0125
  article-title: NIRS in clinical neurology-a ‘promising’ tool?
  publication-title: Neuroimage
– volume: 4
  start-page: 0045
  year: 2023
  ident: b0160
  article-title: Cross-subject emotion recognition brain-computer interface based on fNIRS and DBJNet
  publication-title: Cyborg Bionic Syst
– volume: 24
  start-page: 16453
  year: 2020
  end-page: 16482
  ident: b0055
  article-title: Temporal convolutional neural (TCN) network for an effective weather forecasting using time-series data from the local weather station
  publication-title: Soft Comput
– volume: 10
  start-page: 1681
  year: 2020
  ident: b0175
  article-title: Fine-grained butterfly classification in ecological images using squeeze-and-excitation and spatial attention modules
  publication-title: Appl Sci
– volume: 25
  start-page: 1735
  issue: 10
  year: 2016
  ident: 10.1016/j.neuroscience.2024.02.011_b0155
  article-title: Open access dataset for EEG+NIRS single-trial classification
  publication-title: IEEE Trans Neural Syst Rehabil Eng
  doi: 10.1109/TNSRE.2016.2628057
– year: 2021
  ident: 10.1016/j.neuroscience.2024.02.011_b0180
  article-title: Grad-CAM guided channel-spatial attention module for fine-grained visual classification
– year: 2019
  ident: 10.1016/j.neuroscience.2024.02.011_b0010
  article-title: A dual-attention dilated residual network for liver lesion classification and localization on CT images
– volume: 25
  start-page: 204
  year: 2020
  ident: 10.1016/j.neuroscience.2024.02.011_b0060
  article-title: Brain-machine interfaces using functional near-infrared spectroscopy: a review
  publication-title: Artif Life Robot
  doi: 10.1007/s10015-020-00592-9
– year: 2016
  ident: 10.1016/j.neuroscience.2024.02.011_b0120
  article-title: Analysis of different classification techniques for two-class functional near-infrared spectroscopy-based brain-computer interface
  publication-title: Computat Intell Neurosci
  doi: 10.1155/2016/5480760
– volume: 29
  start-page: 476
  year: 2020
  ident: 10.1016/j.neuroscience.2024.02.011_b0195
  article-title: Learning rich part hierarchies with progressive attention networks for fine-grained image recognition
  publication-title: IEEE Trans Image Process
  doi: 10.1109/TIP.2019.2921876
– volume: 69
  start-page: 1983
  issue: 6
  year: 2021
  ident: 10.1016/j.neuroscience.2024.02.011_b0015
  article-title: A bimodal deep learning architecture for EEG-fNIRS decoding of overt and imagined speech
  publication-title: IEEE Trans Biomed Eng
  doi: 10.1109/TBME.2021.3132861
– volume: 85
  start-page: 535
  year: 2014
  ident: 10.1016/j.neuroscience.2024.02.011_b0125
  article-title: NIRS in clinical neurology-a ‘promising’ tool?
  publication-title: Neuroimage
  doi: 10.1016/j.neuroimage.2013.03.045
– volume: 85
  start-page: 6
  year: 2014
  ident: 10.1016/j.neuroscience.2024.02.011_b0150
  article-title: A review on continuous wave functional near-infrared spectroscopy and imaging instrumentation and methodology
  publication-title: Neuroimage
  doi: 10.1016/j.neuroimage.2013.05.004
– volume: 9
  issue: 4
  year: 2022
  ident: 10.1016/j.neuroscience.2024.02.011_b0030
  article-title: Deep learning in fNIRS: a review
  publication-title: Neurophotonics
  doi: 10.1117/1.NPh.9.4.041411
– volume: 10
  start-page: 237
  year: 2016
  ident: 10.1016/j.neuroscience.2024.02.011_b0115
  article-title: Determining optimal feature-combination for LDA classification of functional near-infrared spectroscopy signals in brain-computer interface application
  publication-title: Front Hum Neurosci
  doi: 10.3389/fnhum.2016.00237
– volume: 10
  start-page: 1681
  issue: 5
  year: 2020
  ident: 10.1016/j.neuroscience.2024.02.011_b0175
  article-title: Fine-grained butterfly classification in ecological images using squeeze-and-excitation and spatial attention modules
  publication-title: Appl Sci
  doi: 10.3390/app10051681
– volume: 28
  start-page: 3
  issue: 1
  year: 2019
  ident: 10.1016/j.neuroscience.2024.02.011_b0080
  article-title: The study of generic model set for reducing calibration time in P300-based brain–computer interface
  publication-title: IEEE Trans Neural Syst Rehabil Eng
  doi: 10.1109/TNSRE.2019.2956488
– volume: 13
  start-page: 10425
  issue: 2
  year: 2023
  ident: 10.1016/j.neuroscience.2024.02.011_b0100
  article-title: Improvement of classification accuracy of four-class voluntary-imagery fNIRS signals using convolutional neural networks
  publication-title: Eng Technol Appl Sci Res
  doi: 10.48084/etasr.5703
– start-page: 3
  year: 2018
  ident: 10.1016/j.neuroscience.2024.02.011_b0145
  article-title: Cbam: Convolutional block attention module
– volume: 62
  year: 2020
  ident: 10.1016/j.neuroscience.2024.02.011_b0075
  article-title: Investigation of deep convolutional neural network for classification of motor imagery fNIRS signals for BCI applications
  publication-title: Biomed Signal Process Control
– volume: 111
  year: 2019
  ident: 10.1016/j.neuroscience.2024.02.011_b0140
  article-title: Prediction of epileptic seizures with convolutional neural networks and functional near-infrared spectroscopy signals
  publication-title: Comput Biol Med
  doi: 10.1016/j.compbiomed.2019.103355
– volume: 22
  start-page: 20695
  issue: 21
  year: 2022
  ident: 10.1016/j.neuroscience.2024.02.011_b0045
  article-title: Multimodal multitask neural network for motor imagery classification with EEG and fNIRS signals
  publication-title: IEEE Sens J
  doi: 10.1109/JSEN.2022.3205956
– volume: 82
  start-page: 107
  issue: 2
  year: 2022
  ident: 10.1016/j.neuroscience.2024.02.011_b0190
  article-title: Recent advances and current trends in brain-computer interface research and their applications
  publication-title: Int J Dev Neurosci
  doi: 10.1002/jdn.10166
– volume: 10
  start-page: 115945
  year: 2022
  ident: 10.1016/j.neuroscience.2024.02.011_b0095
  article-title: Short-term load forecasting based on improved TCN and DenseNet
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2022.3218374
– volume: 1464
  start-page: 5
  issue: 1
  year: 2020
  ident: 10.1016/j.neuroscience.2024.02.011_b0130
  article-title: The present and future use of functional near-infrared spectroscopy (fNIRS) for cognitive neuroscience
  publication-title: Ann N Y Acad Sci
  doi: 10.1111/nyas.13948
– year: 2018
  ident: 10.1016/j.neuroscience.2024.02.011_b0185
  article-title: Classification of three categories from prefrontal cortex using LSTM networks: fNIRS study
– year: 2021
  ident: 10.1016/j.neuroscience.2024.02.011_b0085
  article-title: Robust similarity measurement based on a novel time filter for SSVEPs detection
– year: 2023
  ident: 10.1016/j.neuroscience.2024.02.011_b0165
  article-title: The diagnosis of major depressive disorder through wearable fNIRS by using wavelet transform and parallel-CNN feature fusion
  publication-title: IEEE Trans Instrum Meas
– volume: 15
  issue: 5
  year: 2018
  ident: 10.1016/j.neuroscience.2024.02.011_b0090
  article-title: EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces
  publication-title: J Neural Eng
  doi: 10.1088/1741-2552/aace8c
– start-page: 123
  year: 2019
  ident: 10.1016/j.neuroscience.2024.02.011_b0025
  article-title: The quest for functional biomarkers in the prefrontal cortex using functional near-infrared spectroscopy (fNIRS)
  publication-title: Neurophoton Biomed Spectrosc
  doi: 10.1016/B978-0-323-48067-3.00006-8
– start-page: 7794
  year: 2018
  ident: 10.1016/j.neuroscience.2024.02.011_b0170
  article-title: Non-local neural networks
– volume: 195
  year: 2020
  ident: 10.1016/j.neuroscience.2024.02.011_b0005
  article-title: Subject-Specific feature selection for near infrared spectroscopy based brain-computer interfaces
  publication-title: Comput Methods Programs Biomed
  doi: 10.1016/j.cmpb.2020.105535
– year: 2022
  ident: 10.1016/j.neuroscience.2024.02.011_b0050
  article-title: Joint temporal convolutional networks and adversarial discriminative domain adaptation for EEG-based cross-subject emotion recognition
– volume: 232
  start-page: 555
  year: 2014
  ident: 10.1016/j.neuroscience.2024.02.011_b0110
  article-title: Online binary decision decoding using functional near-infrared spectroscopy for the development of brain–computer interface
  publication-title: Exp Brain Res
  doi: 10.1007/s00221-013-3764-1
– volume: 134
  start-page: 1591
  issue: 6
  year: 2011
  ident: 10.1016/j.neuroscience.2024.02.011_b0020
  article-title: Harnessing neuroplasticity for clinical applications
  publication-title: Brain
  doi: 10.1093/brain/awr039
– year: 2021
  ident: 10.1016/j.neuroscience.2024.02.011_b0105
  article-title: fNIRS based multi-class mental workload classification using recurrence plots and CNN-LSTM
– year: 2021
  ident: 10.1016/j.neuroscience.2024.02.011_b0040
  article-title: IEEG-TCN: A Concise and Robust Temporal Convolutional Network for Intracranial Electroencephalogram Signal Identification
– volume: 21
  issue: 9
  year: 2016
  ident: 10.1016/j.neuroscience.2024.02.011_b0070
  article-title: Toward more intuitive brain-computer interfacing: classification of binary covert intentions using functional near-infrared spectroscopy
  publication-title: J Biomed Opt
  doi: 10.1117/1.JBO.21.9.091303
– year: 2019
  ident: 10.1016/j.neuroscience.2024.02.011_b0035
  article-title: Enhancement in classification accuracy of motor imagery signals with visual aid: An fNIRS-BCI Study
– year: 2018
  ident: 10.1016/j.neuroscience.2024.02.011_b0065
  article-title: Squeeze-and-excitation networks
– volume: 4
  start-page: 0045
  year: 2023
  ident: 10.1016/j.neuroscience.2024.02.011_b0160
  article-title: Cross-subject emotion recognition brain-computer interface based on fNIRS and DBJNet
  publication-title: Cyborg Bionic Syst
  doi: 10.34133/cbsystems.0045
– volume: 24
  start-page: 16453
  year: 2020
  ident: 10.1016/j.neuroscience.2024.02.011_b0055
  article-title: Temporal convolutional neural (TCN) network for an effective weather forecasting using time-series data from the local weather station
  publication-title: Soft Comput
  doi: 10.1007/s00500-020-04954-0
– volume: 85
  start-page: 64
  year: 2014
  ident: 10.1016/j.neuroscience.2024.02.011_b0135
  article-title: A wearable multi-channel fNIRS system for brain imaging in freely moving subjects
  publication-title: Neuroimage
  doi: 10.1016/j.neuroimage.2013.06.062
SSID ssj0000543
Score 2.490284
Snippet This graphic shows the structure of our network. In the preprocessing section, we used the Beer-Lambert law to convert the optical signals into hemodynamic HbR...
Brain Computer Interface (BCI) is a highly promising human-computer interaction method that can utilize brain signals to control external devices. BCI based on...
SourceID proquest
pubmed
crossref
elsevier
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 59
SubjectTerms brain computer interface
deep learning
motor imagery
spatial attention
temporal convolutional network
Title Classification Algorithm for fNIRS-based Brain Signals Using Convolutional Neural Network with Spatiotemporal Feature Extraction Mechanism
URI https://www.clinicalkey.com/#!/content/1-s2.0-S0306452224000617
https://dx.doi.org/10.1016/j.neuroscience.2024.02.011
https://www.ncbi.nlm.nih.gov/pubmed/38369007
https://www.proquest.com/docview/2928586375
Volume 542
WOSCitedRecordID wos001236898600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1873-7544
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000543
  issn: 0306-4522
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lj9MwELbKLgcuCFge5bEyEuKyCsrGcWILcahQEYugAroL5RTZeZRU2WTVTavyF_gx_EbGjyQtqKIgcUkjR7bszmfP2J75BqEnMvOzWATSoZLEji-F67AgS5wsFeQYRE64juP-9DYcjdhkwt_3ej-aWJhlEZYlW634xX8VNZSBsFXo7F-Iu20UCuAdhA5PEDs8dxK8TnOpHICMaAfFtJrn9ddz7VCYjU4-jh2luhIQq8hhcudTTaF8Zj0AyqXtHchOMXfoH-0qbs5sx9oF2zJaFUfKhFR3EMNVPbdpx9-lKpq4oSacNfRQLW9mC6UPhr_gy2KVd45BubkFqWaA22l33G-WpM9pWVRd8VhnJD6aQM-lbcIeYHi-8uAyUfJN4JYbOIrYfX1RpoZzyy6rljTcKGiThue3pd-cQsyerfGAKhpUz9ecrHZF3-Db_kUPtt6JjePbLFpvK1JtRa4XuSqUfN8LKQdFsD84GU7edLqfGj_NZkgNza32KNzWs20m0bYtjzZ9Tm-g63bPggcGazdRLy1voYNBKerq_Bt-irUXsb6eOUDfN-GHW_hhgB9egx_W8MMWfljDD2_ADxv4YQs_rOCHN-GHLfxwBz_cwu82Ons1PH352rH5PpwYzOLaEVKwhFIWszBzPZlmQcx8SXxxzHkKmgJWmwTMeUGoMkppTDmhcSCZegUrNiB30F5Zlek9hBPPJYmIhZvAZ0mpTKibhG7KU5-7Qrp9xJu_PIotGb7KyVJEfxZ-H5G27oWhhNmp1vNGslET9AxqOgL47lT7RVvbfjYm7871HzdgikB_qEtBUabV4jLyuMcoC0hI--iuQVk7KsJIwGETcf-fRvwAXeum-0O0V88X6SN0NV7W-eX8EF0JJ-zQzp-fT9UAKQ
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Classification+Algorithm+for+fNIRS-based+Brain+Signals+Using+Convolutional+Neural+Network+with+Spatiotemporal+Feature+Extraction+Mechanism&rft.jtitle=Neuroscience&rft.au=Qin%2C+Yuxin&rft.au=Li%2C+Baojiang&rft.au=Wang%2C+Wenlong&rft.au=Shi%2C+Xingbin&rft.date=2024-03-26&rft.issn=0306-4522&rft.volume=542&rft.spage=59&rft.epage=68&rft_id=info:doi/10.1016%2Fj.neuroscience.2024.02.011&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_neuroscience_2024_02_011
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0306-4522&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0306-4522&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0306-4522&client=summon