Motion Artifact Removal in Functional Near‐Infrared Spectroscopy Based on Long Short‐Term Memory‐Autoencoder Model

ABSTRACT Motion artifact removal is a critical issue in functional near‐infrared spectroscopy (fNIRS) analysis tasks, with traditional methods relying heavily on expert‐based knowledge and optimal selection of model parameters within brain regions. In this paper, we propose a deep learning denoising...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:The European journal of neuroscience Jg. 61; H. 2
Hauptverfasser: Yang, Pan, Wang, Junhong, Wang, Ting, Li, Lihua, Xu, Dongjuan, Xi, Xugang
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Chichester Wiley Subscription Services, Inc 01.01.2025
Schlagworte:
ISSN:0953-816X, 1460-9568
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract ABSTRACT Motion artifact removal is a critical issue in functional near‐infrared spectroscopy (fNIRS) analysis tasks, with traditional methods relying heavily on expert‐based knowledge and optimal selection of model parameters within brain regions. In this paper, we propose a deep learning denoising model based on long short‐term memory (LSTM)‐autoencoder (viz., LSTM‐AE) to reduce motion artifacts. By training a neural network to reconstruct hemodynamic response coupled with neuronal activity, LSTM‐AE achieves positive denoising results on both our synthesized noisy simulated dataset and the real dataset. The LSTM‐AE processes the raw fNIRS in three phases: (1) Morphological feature extraction of the raw fNIRS is conducted through the encoder module. (2) The LSTM module captures temporal correlations between individual samples to enhance features. (3) The decoder module recovers and reconstructs the morphological feature information of fNIRS from the latent space. Finally, clean reconstructed fNIRS is generated at the output layer. We compare our proposed method with existing calibration algorithms for hemodynamic response estimation using the following metrics: mean square error (MSE), Pearson's correlation (R2), signal‐to‐noise ratio (SNR), and percent deviation ratio (PDR). The proposed LSTM‐AE method outperforms conventional methods, demonstrating an improvement in all these metrics. Additionally, the proposed LSTM‐AE method shows statistically significant differences from other motion artifact algorithms in terms of effectiveness (p < 0.01, significance level α = 0.05). This study demonstrates the potential of deep network architectures to remove motion artifacts in fNIRS data. We propose a deep learning denoising model based on long short‐term memory (LSTM)‐autoencoder (viz., LSTM‐AE) to reduce motion artifacts. By training a neural network to reconstruct hemodynamic response coupled with neuronal activity, LSTM‐AE achieves positive denoising results on both our synthesized noisy simulated dataset and the real dataset. This study demonstrates the potential of deep network architectures to remove motion artifacts in fNIRS data.
AbstractList Motion artifact removal is a critical issue in functional near‐infrared spectroscopy (fNIRS) analysis tasks, with traditional methods relying heavily on expert‐based knowledge and optimal selection of model parameters within brain regions. In this paper, we propose a deep learning denoising model based on long short‐term memory (LSTM)‐autoencoder (viz., LSTM‐AE) to reduce motion artifacts. By training a neural network to reconstruct hemodynamic response coupled with neuronal activity, LSTM‐AE achieves positive denoising results on both our synthesized noisy simulated dataset and the real dataset. The LSTM‐AE processes the raw fNIRS in three phases: (1) Morphological feature extraction of the raw fNIRS is conducted through the encoder module. (2) The LSTM module captures temporal correlations between individual samples to enhance features. (3) The decoder module recovers and reconstructs the morphological feature information of fNIRS from the latent space. Finally, clean reconstructed fNIRS is generated at the output layer. We compare our proposed method with existing calibration algorithms for hemodynamic response estimation using the following metrics: mean square error (MSE), Pearson's correlation (R2), signal‐to‐noise ratio (SNR), and percent deviation ratio (PDR). The proposed LSTM‐AE method outperforms conventional methods, demonstrating an improvement in all these metrics. Additionally, the proposed LSTM‐AE method shows statistically significant differences from other motion artifact algorithms in terms of effectiveness (p < 0.01, significance level α = 0.05). This study demonstrates the potential of deep network architectures to remove motion artifacts in fNIRS data.
ABSTRACT Motion artifact removal is a critical issue in functional near‐infrared spectroscopy (fNIRS) analysis tasks, with traditional methods relying heavily on expert‐based knowledge and optimal selection of model parameters within brain regions. In this paper, we propose a deep learning denoising model based on long short‐term memory (LSTM)‐autoencoder (viz., LSTM‐AE) to reduce motion artifacts. By training a neural network to reconstruct hemodynamic response coupled with neuronal activity, LSTM‐AE achieves positive denoising results on both our synthesized noisy simulated dataset and the real dataset. The LSTM‐AE processes the raw fNIRS in three phases: (1) Morphological feature extraction of the raw fNIRS is conducted through the encoder module. (2) The LSTM module captures temporal correlations between individual samples to enhance features. (3) The decoder module recovers and reconstructs the morphological feature information of fNIRS from the latent space. Finally, clean reconstructed fNIRS is generated at the output layer. We compare our proposed method with existing calibration algorithms for hemodynamic response estimation using the following metrics: mean square error (MSE), Pearson's correlation (R2), signal‐to‐noise ratio (SNR), and percent deviation ratio (PDR). The proposed LSTM‐AE method outperforms conventional methods, demonstrating an improvement in all these metrics. Additionally, the proposed LSTM‐AE method shows statistically significant differences from other motion artifact algorithms in terms of effectiveness (p < 0.01, significance level α = 0.05). This study demonstrates the potential of deep network architectures to remove motion artifacts in fNIRS data. We propose a deep learning denoising model based on long short‐term memory (LSTM)‐autoencoder (viz., LSTM‐AE) to reduce motion artifacts. By training a neural network to reconstruct hemodynamic response coupled with neuronal activity, LSTM‐AE achieves positive denoising results on both our synthesized noisy simulated dataset and the real dataset. This study demonstrates the potential of deep network architectures to remove motion artifacts in fNIRS data.
Motion artifact removal is a critical issue in functional near‐infrared spectroscopy (fNIRS) analysis tasks, with traditional methods relying heavily on expert‐based knowledge and optimal selection of model parameters within brain regions. In this paper, we propose a deep learning denoising model based on long short‐term memory (LSTM)‐autoencoder (viz., LSTM‐AE) to reduce motion artifacts. By training a neural network to reconstruct hemodynamic response coupled with neuronal activity, LSTM‐AE achieves positive denoising results on both our synthesized noisy simulated dataset and the real dataset. The LSTM‐AE processes the raw fNIRS in three phases: (1) Morphological feature extraction of the raw fNIRS is conducted through the encoder module. (2) The LSTM module captures temporal correlations between individual samples to enhance features. (3) The decoder module recovers and reconstructs the morphological feature information of fNIRS from the latent space. Finally, clean reconstructed fNIRS is generated at the output layer. We compare our proposed method with existing calibration algorithms for hemodynamic response estimation using the following metrics: mean square error (MSE), Pearson's correlation ( R 2 ), signal‐to‐noise ratio (SNR), and percent deviation ratio (PDR). The proposed LSTM‐AE method outperforms conventional methods, demonstrating an improvement in all these metrics. Additionally, the proposed LSTM‐AE method shows statistically significant differences from other motion artifact algorithms in terms of effectiveness ( p < 0.01, significance level α = 0.05). This study demonstrates the potential of deep network architectures to remove motion artifacts in fNIRS data.
Author Wang, Junhong
Yang, Pan
Xi, Xugang
Wang, Ting
Xu, Dongjuan
Li, Lihua
Author_xml – sequence: 1
  givenname: Pan
  surname: Yang
  fullname: Yang, Pan
  organization: Hangzhou Dianzi University
– sequence: 2
  givenname: Junhong
  surname: Wang
  fullname: Wang, Junhong
  organization: Hangzhou Dianzi University
– sequence: 3
  givenname: Ting
  orcidid: 0000-0003-3000-5315
  surname: Wang
  fullname: Wang, Ting
  organization: Hangzhou Dianzi University
– sequence: 4
  givenname: Lihua
  surname: Li
  fullname: Li, Lihua
  organization: Hangzhou Dianzi University
– sequence: 5
  givenname: Dongjuan
  surname: Xu
  fullname: Xu, Dongjuan
  email: xdj0108@wmu.edu.cn
  organization: Affiliated Dongyang Hospital of Wenzhou Medical University
– sequence: 6
  givenname: Xugang
  surname: Xi
  fullname: Xi, Xugang
  email: xixi@hdu.edu.cn
  organization: Hangzhou Dianzi University
BookMark eNp1kMFOwzAMhiM0JMbgwBtE4sShW9KsaXMc0wZD25DYkLhVaeZApy4paQvsxiPwjDwJGeWKD7Zsf_4l_6eoY6wBhC4o6VMfA9iaPuU8FkeoS4ecBCLiSQd1iYhYkFD-dIJOq2pLCEn4MOqij4Wtc2vwyNW5lqrGD7Czb7LAucHTxqjD0ndLkO7782tmtJMONnhVgqqdrZQt9_haVn7kRebWPOPVi3W1Z9fgdnjh1dzed6OmtmCU3YDDC5-LM3SsZVHB-V_tocfpZD2-Deb3N7PxaB6oMIpFIEK24UIxkiU6DkmWJbABrRTnhMgMuNQqiqXwOQPNdAgxEyohlERDzWgoWA9dtrqls68NVHW6tY3zP1Upo5wwxkIee-qqpZR_qnKg09LlO-n2KSXpwdjUG5v-GuvZQcu-5wXs_wfTyd2yvfgBH6uAoA
Cites_doi 10.1016/j.neuroimage.2013.11.033
10.1142/S1793545813500661
10.1117/1.NPh.9.4.041406
10.1016/S0166-2236(97)01132-6
10.1109/JBHI.2022.3227320
10.3390/s18092957
10.1021/ac60319a045
10.1109/TNSRE.2022.3201197
10.1088/1741-2552/aaaf82
10.1109/TNNLS.2023.3293328
10.1088/0031-9155/33/12/008
10.1161/01.CIR.101.23.e215
10.1088/0967-3334/31/5/004
10.1117/1.NPh.3.3.031410
10.1016/j.neuroimage.2015.02.057
10.1016/j.media.2019.101622
10.1117/1.1852552
10.3390/s23083979
10.3389/fnhum.2020.00030
10.1007/s11571-023-09986-4
10.1109/BIBM.2018.8621080
10.1016/j.neuroimage.2009.11.050
10.1088/0967-3334/33/2/259
10.3389/fnins.2012.00147
10.1364/AO.48.00D280
10.1109/TITB.2012.2207400
10.1371/journal.pone.0244186
10.1016/j.neuroimage.2013.06.054
10.1201/9781420038491.ch8
10.1002/hbm.20767
10.1007/BF02447083
10.1016/j.neuroimage.2018.09.025
10.1080/01621459.1979.10481038
10.1117/1.NPh.5.1.015003
10.1038/s41598-023-47812-3
10.1364/BOE.4.001366
10.1016/j.patcog.2023.109603
10.1109/EMBC46164.2021.9631014
10.1109/TFUZZ.2021.3062723
ContentType Journal Article
Copyright 2025 Federation of European Neuroscience Societies and John Wiley & Sons Ltd.
2025 Federation of European Neuroscience Societies and John Wiley & Sons Ltd
Copyright_xml – notice: 2025 Federation of European Neuroscience Societies and John Wiley & Sons Ltd.
– notice: 2025 Federation of European Neuroscience Societies and John Wiley & Sons Ltd
DBID AAYXX
CITATION
7QP
7QR
7TK
8FD
FR3
P64
DOI 10.1111/ejn.16679
DatabaseName CrossRef
Calcium & Calcified Tissue Abstracts
Chemoreception Abstracts
Neurosciences Abstracts
Technology Research Database
Engineering Research Database
Biotechnology and BioEngineering Abstracts
DatabaseTitle CrossRef
Chemoreception Abstracts
Engineering Research Database
Technology Research Database
Calcium & Calcified Tissue Abstracts
Neurosciences Abstracts
Biotechnology and BioEngineering Abstracts
DatabaseTitleList Chemoreception Abstracts

CrossRef
DeliveryMethod fulltext_linktorsrc
Discipline Anatomy & Physiology
Chemistry
EISSN 1460-9568
EndPage n/a
ExternalDocumentID 10_1111_ejn_16679
EJN16679
Genre article
GrantInformation_xml – fundername: Zhejiang Provincial Natural Science Foundation of China
  funderid: LTGY23H180020
– fundername: Zhejiang Provincial Key Research and Development Program of China
  funderid: 2024C03041
– fundername: National Natural Science Foundation of China
  funderid: 62371178; 62301197
GroupedDBID ---
-~X
.3N
.GA
.GJ
.Y3
05W
0R~
10A
1OB
1OC
29G
31~
33P
36B
3SF
4.4
50Y
50Z
51W
51X
52M
52N
52O
52P
52R
52S
52T
52U
52V
52W
52X
53G
5GY
5HH
5LA
5RE
5VS
66C
702
7PT
8-0
8-1
8-3
8-4
8-5
8UM
930
A01
A03
AAESR
AAEVG
AAHHS
AAHQN
AAIPD
AAMNL
AANHP
AANLZ
AAONW
AASGY
AAXRX
AAYCA
AAZKR
ABCQN
ABCUV
ABDBF
ABEML
ABIVO
ABJNI
ABPVW
ABQWH
ABXGK
ACAHQ
ACBWZ
ACCFJ
ACCZN
ACFBH
ACGFS
ACGOF
ACIWK
ACMXC
ACPOU
ACPRK
ACRPL
ACSCC
ACUHS
ACXBN
ACXQS
ACYXJ
ADBBV
ADBTR
ADEOM
ADIZJ
ADKYN
ADMGS
ADNMO
ADOZA
ADXAS
ADZMN
ADZOD
AEEZP
AEIGN
AEIMD
AENEX
AEQDE
AEUQT
AEUYR
AFBPY
AFEBI
AFFPM
AFGKR
AFPWT
AFWVQ
AFZJQ
AHBTC
AHEFC
AIACR
AITYG
AIURR
AIWBW
AJBDE
ALAGY
ALMA_UNASSIGNED_HOLDINGS
ALUQN
ALVPJ
AMBMR
AMYDB
ASPBG
ATUGU
AVWKF
AZBYB
AZFZN
AZVAB
BAFTC
BDRZF
BFHJK
BHBCM
BMXJE
BROTX
BRXPI
BY8
C45
CAG
COF
CS3
D-6
D-7
D-E
D-F
DC6
DCZOG
DPXWK
DR2
DRFUL
DRMAN
DRSTM
EAD
EAP
EAS
EBC
EBD
EBS
EBX
EJD
EMB
EMK
EMOBN
EPS
ESX
EX3
F00
F01
F04
F5P
FEDTE
FUBAC
FZ0
G-S
G.N
GAKWD
GODZA
H.X
HF~
HGLYW
HVGLF
HZI
HZ~
IHE
IX1
J0M
K48
KBYEO
LATKE
LC2
LC3
LEEKS
LH4
LITHE
LOXES
LP6
LP7
LUTES
LW6
LYRES
MEWTI
MK4
MRFUL
MRMAN
MRSTM
MSFUL
MSMAN
MSSTM
MXFUL
MXMAN
MXSTM
N04
N05
N9A
NF~
O66
O9-
OIG
OVD
P2P
P2W
P2X
P2Z
P4B
P4D
PALCI
PQQKQ
Q.N
Q11
QB0
Q~Q
R.K
RIG
RIWAO
RJQFR
ROL
RX1
SAMSI
SUPJJ
SV3
TEORI
TUS
UB1
W8V
W99
WBKPD
WHG
WIH
WIJ
WIK
WNSPC
WOHZO
WOW
WQJ
WRC
WUP
WXI
WXSBR
WYISQ
XG1
YFH
ZGI
ZZTAW
~IA
~WT
AAMMB
AAYXX
AEFGJ
AEYWJ
AGHNM
AGQPQ
AGXDD
AGYGG
AIDQK
AIDYY
AIQQE
CITATION
O8X
7QP
7QR
7TK
8FD
FR3
P64
ID FETCH-LOGICAL-c2579-923d69c30b8f720bb8edefcc6600abe6afc57a9fc5bef3f2e739c801054f31293
IEDL.DBID DRFUL
ISICitedReferencesCount 1
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001407187500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0953-816X
IngestDate Sat Aug 23 12:40:40 EDT 2025
Sat Nov 29 07:49:15 EST 2025
Wed Jan 29 10:50:40 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 2
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c2579-923d69c30b8f720bb8edefcc6600abe6afc57a9fc5bef3f2e739c801054f31293
Notes Edited by
Funding
This work was supported by the National Natural Science Foundation of China (Nos. 62371178 and 62301197), Zhejiang Provincial Key Research and Development Program of China (No. 2024C03041), and Zhejiang Provincial Natural Science Foundation of China (No. LTGY23H180020).
John Foxe
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0003-3000-5315
PQID 3160333267
PQPubID 34057
PageCount 12
ParticipantIDs proquest_journals_3160333267
crossref_primary_10_1111_ejn_16679
wiley_primary_10_1111_ejn_16679_EJN16679
PublicationCentury 2000
PublicationDate January 2025
2025-01-00
20250101
PublicationDateYYYYMMDD 2025-01-01
PublicationDate_xml – month: 01
  year: 2025
  text: January 2025
PublicationDecade 2020
PublicationPlace Chichester
PublicationPlace_xml – name: Chichester
PublicationTitle The European journal of neuroscience
PublicationYear 2025
Publisher Wiley Subscription Services, Inc
Publisher_xml – name: Wiley Subscription Services, Inc
References 2014b; 85
2010; 31
2023; 13
2013; 4
2023; 141
1997; 20
2020; 60
1988; 33
2020; 15
2020; 14
2022b; 9
2012; 16
2002
2024
2024; 35
2014; 85
2019; 184
1979; 74
2021; 30
2012; 33
1972; 44
2024; 18
2009; 48
2018; 18
2010; 49
2009; 30
2018; 5
2023; 23
2016; 3
2021
2015; 112
1988; 26
2018
2005; 10
2022; 30
2000; 101
2012; 6
2018; 15
2022a; 27
2014a; 7
e_1_2_12_4_1
e_1_2_12_3_1
e_1_2_12_6_1
e_1_2_12_5_1
e_1_2_12_19_1
e_1_2_12_18_1
e_1_2_12_2_1
e_1_2_12_17_1
e_1_2_12_16_1
e_1_2_12_38_1
e_1_2_12_39_1
e_1_2_12_20_1
e_1_2_12_41_1
e_1_2_12_21_1
e_1_2_12_22_1
e_1_2_12_23_1
e_1_2_12_24_1
e_1_2_12_25_1
e_1_2_12_26_1
e_1_2_12_40_1
e_1_2_12_27_1
e_1_2_12_28_1
e_1_2_12_29_1
e_1_2_12_30_1
e_1_2_12_31_1
e_1_2_12_32_1
e_1_2_12_33_1
e_1_2_12_34_1
e_1_2_12_35_1
e_1_2_12_36_1
e_1_2_12_37_1
e_1_2_12_15_1
e_1_2_12_14_1
e_1_2_12_13_1
e_1_2_12_12_1
e_1_2_12_8_1
e_1_2_12_11_1
e_1_2_12_7_1
e_1_2_12_10_1
e_1_2_12_9_1
References_xml – volume: 10
  issue: 1
  year: 2005
  article-title: Eigenvector‐Based Spatial Filtering for Reduction of Physiological Interference in Diffuse Optical Imaging
  publication-title: Journal of Biomedical Optics
– volume: 101
  start-page: e215
  issue: 23
  year: 2000
  end-page: e220
  article-title: PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals
  publication-title: Circulation
– start-page: 2605
  year: 2018
  end-page: 2612
– volume: 33
  start-page: 259
  issue: 2
  year: 2012
  end-page: 270
  article-title: Wavelet‐Based Motion Artifact Removal for Functional Near‐Infrared Spectroscopy
  publication-title: Physiological Measurement
– volume: 4
  start-page: 1366
  issue: 8
  year: 2013
  end-page: 1379
  article-title: Autoregressive Model Based Algorithm for Correcting Motion and Serially Correlated Errors in fNIRS
  publication-title: Biomedical Optics Express
– volume: 184
  start-page: 171
  year: 2019
  end-page: 179
  article-title: Temporal Derivative Distribution Repair (TDDR): A Motion Correction Method for fNIRS
  publication-title: NeuroImage
– volume: 74
  start-page: 829
  issue: 368
  year: 1979
  end-page: 836
  article-title: Robust Locally Weighted Regression and Smoothing Scatterplots
  publication-title: Journal of the American Statistical Association
– volume: 30
  start-page: 3426
  issue: 10
  year: 2009
  end-page: 3435
  article-title: The fMRI Success Rate of Children and Adolescents: Typical Development, Epilepsy, Attention Deficit/Hyperactivity Disorder, and Autism Spectrum Disorders
  publication-title: Human Brain Mapping
– volume: 5
  issue: 1
  year: 2018
  article-title: Motion Artifact Detection and Correction in Functional Near‐Infrared Spectroscopy: A New Hybrid Method Based on Spline Interpolation Method and Savitzky‐Golay Filtering
  publication-title: Neurophotonics
– start-page: 828
  year: 2021
  end-page: 831
– year: 2024
– start-page: 193
  year: 2002
  end-page: 221
– volume: 15
  issue: 12
  year: 2020
  article-title: Comparing fNIRS Signal Qualities Between Approaches With and Without Short Channels
  publication-title: PLoS ONE
– volume: 16
  start-page: 918
  issue: 5
  year: 2012
  end-page: 926
  article-title: A Methodology for Validating Artifact Removal Techniques for Physiological Signals
  publication-title: IEEE Transactions on Information Technology in Biomedicine
– volume: 141
  year: 2023
  article-title: Multi Scale Pixel Attention and Feature Extraction Based Neural Network for Image Denoising
  publication-title: Pattern Recognition
– volume: 15
  issue: 3
  year: 2018
  article-title: Deep Learning for Hybrid EEG‐fNIRS Brain–Computer Interface: Application to Motor Imagery Classification
  publication-title: Journal of Neural Engineering
– volume: 31
  start-page: 649
  issue: 5
  year: 2010
  end-page: 662
  article-title: How to Detect and Reduce Movement Artifacts in Near‐Infrared Imaging Using Moving Standard Deviation and Spline Interpolation
  publication-title: Physiological Measurement
– volume: 49
  start-page: 3039
  issue: 4
  year: 2010
  end-page: 3046
  article-title: Functional Near Infrared Spectroscopy (NIRS) Signal Improvement Based on Negative Correlation Between Oxygenated and Deoxygenated Hemoglobin Dynamics
  publication-title: NeuroImage
– volume: 48
  start-page: D280
  issue: 10
  year: 2009
  end-page: D298
  article-title: HomER: A Review of Time‐Series Analysis Methods for Near‐Infrared Spectroscopy of the Brain
  publication-title: Applied Optics
– volume: 18
  issue: 9
  year: 2018
  article-title: Motion Artifact Correction of Multi‐Measured Functional Near‐Infrared Spectroscopy Signals Based on Signal Reconstruction Using an Artificial Neural Network
  publication-title: Sensors
– volume: 33
  start-page: 1433
  issue: 12
  year: 1988
  end-page: 1442
  article-title: Estimation of Optical Pathlength Through Tissue From Direct Time of Flight Measurement
  publication-title: Physics in Medicine & Biology
– volume: 20
  start-page: 435
  issue: 10
  year: 1997
  end-page: 442
  article-title: Non‐invasive Optical Spectroscopy and Imaging of Human Brain Function
  publication-title: Trends in Neurosciences
– volume: 27
  start-page: 1283
  issue: 3
  year: 2022a
  end-page: 1294
  article-title: EEG Reconstruction With a Dual‐Scale CNN‐LSTM Model for Deep Artifact Removal
  publication-title: IEEE Journal of Biomedical and Health Informatics
– volume: 35
  start-page: 16262
  issue: 11
  year: 2024
  end-page: 16276
  article-title: Eigenimage2Eigenimage (E2E): A Self‐Supervised Deep Learning Network for Hyperspectral Image Denoising
  publication-title: IEEE Transactions on Neural Networks and Learning Systems
– volume: 30
  start-page: 2474
  year: 2022
  end-page: 2485
  article-title: Orthogonal Features Based EEG Signals Denoising Using Fractional and Compressed One‐Dimensional CNN AutoEncoder
  publication-title: IEEE Transactions on Neural Systems and Rehabilitation Engineering
– volume: 7
  issue: 02
  year: 2014a
  article-title: Targeted Principle Component Analysis: A new Motion Artifact Correction Approach for Near‐Infrared Spectroscopy
  publication-title: Journal of Innovative Optical Health Sciences
– volume: 23
  issue: 8
  year: 2023
  article-title: Improved Motion Artifact Correction in fNIRS Data by Combining Wavelet and Correlation‐Based Signal Improvement
  publication-title: Sensors
– volume: 26
  start-page: 289
  year: 1988
  end-page: 294
  article-title: System for Long‐Term Measurement of Cerebral Blood and Tissue Oxygenation on Newborn Infants by Near Infra‐Red Transillumination
  publication-title: Medical and Biological Engineering and Computing
– volume: 44
  start-page: 1906
  issue: 11
  year: 1972
  end-page: 1909
  article-title: Smoothing and Differentiation of Data by Simplified Least Square Procedure
  publication-title: Analytical Chemistry
– volume: 14
  start-page: 30
  year: 2020
  article-title: Using the General Linear Model to Improve Performance in fNIRS Single Trial Analysis and Classification: A Perspective
  publication-title: Frontiers in Human Neuroscience
– volume: 13
  issue: 1
  year: 2023
  article-title: Fuzzy Inference‐Based LSTM for Long‐Term Time Series Prediction
  publication-title: Scientific Reports
– volume: 60
  year: 2020
  article-title: A Robust Deep Neural Network for Denoising Task‐Based fMRI Data: An Application to Working Memory and Episodic Memory
  publication-title: Medical Image Analysis
– volume: 85
  start-page: 1
  year: 2014
  end-page: 5
  article-title: Twenty Years of Functional Near‐Infrared Spectroscopy: Introduction for the Special Issue
  publication-title: NeuroImage
– volume: 6
  year: 2012
  article-title: A Systematic Comparison of Motion Artifact Correction Techniques for Functional Near‐Infrared Spectroscopy
  publication-title: Frontiers in Neuroscience
– volume: 30
  start-page: 1599
  issue: 6
  year: 2021
  end-page: 1613
  article-title: Building Trend Fuzzy Granulation‐Based LSTM Recurrent Neural Network for Long‐Term Time‐Series Forecasting
  publication-title: IEEE Transactions on Fuzzy Systems
– volume: 85
  start-page: 192
  year: 2014b
  end-page: 201
  article-title: Reducing Motion Artifacts for Long‐Term Clinical NIRS Monitoring Using Collodion‐Fixed Prism‐Based Optical Fibers
  publication-title: NeuroImage
– volume: 112
  start-page: 128
  year: 2015
  end-page: 137
  article-title: A Kurtosis‐Based Wavelet Algorithm for Motion Artifact Correction of fNIRS Data
  publication-title: NeuroImage
– volume: 18
  start-page: 1489
  issue: 4
  year: 2024
  end-page: 1506
  article-title: Deep Learning Networks Based Decision Fusion Model of EEG and fNIRS for Classification of Cognitive Tasks
  publication-title: Cognitive Neurodynamics
– volume: 3
  issue: 3
  year: 2016
  article-title: Correction of Motion Artifacts and Serial Correlations for Real‐Time Functional Near‐Infrared Spectroscopy
  publication-title: Neurophotonics
– volume: 9
  issue: 4
  year: 2022b
  article-title: Deep Learning‐Based Motion Artifact Removal in Functional Near‐Infrared Spectroscopy
  publication-title: Neurophotonics
– ident: e_1_2_12_5_1
  doi: 10.1016/j.neuroimage.2013.11.033
– ident: e_1_2_12_38_1
  doi: 10.1142/S1793545813500661
– ident: e_1_2_12_16_1
  doi: 10.1117/1.NPh.9.4.041406
– ident: e_1_2_12_32_1
  doi: 10.1016/S0166-2236(97)01132-6
– ident: e_1_2_12_15_1
  doi: 10.1109/JBHI.2022.3227320
– ident: e_1_2_12_22_1
  doi: 10.3390/s18092957
– ident: e_1_2_12_28_1
  doi: 10.1021/ac60319a045
– ident: e_1_2_12_21_1
– ident: e_1_2_12_25_1
  doi: 10.1109/TNSRE.2022.3201197
– ident: e_1_2_12_7_1
  doi: 10.1088/1741-2552/aaaf82
– ident: e_1_2_12_41_1
  doi: 10.1109/TNNLS.2023.3293328
– ident: e_1_2_12_13_1
  doi: 10.1088/0031-9155/33/12/008
– ident: e_1_2_12_18_1
  doi: 10.1161/01.CIR.101.23.e215
– ident: e_1_2_12_27_1
  doi: 10.1088/0967-3334/31/5/004
– ident: e_1_2_12_4_1
  doi: 10.1117/1.NPh.3.3.031410
– ident: e_1_2_12_8_1
  doi: 10.1016/j.neuroimage.2015.02.057
– ident: e_1_2_12_35_1
  doi: 10.1016/j.media.2019.101622
– ident: e_1_2_12_39_1
  doi: 10.1117/1.1852552
– ident: e_1_2_12_2_1
  doi: 10.3390/s23083979
– ident: e_1_2_12_33_1
  doi: 10.3389/fnhum.2020.00030
– ident: e_1_2_12_26_1
  doi: 10.1007/s11571-023-09986-4
– ident: e_1_2_12_23_1
  doi: 10.1109/BIBM.2018.8621080
– ident: e_1_2_12_12_1
  doi: 10.1016/j.neuroimage.2009.11.050
– ident: e_1_2_12_24_1
  doi: 10.1088/0967-3334/33/2/259
– ident: e_1_2_12_10_1
  doi: 10.3389/fnins.2012.00147
– ident: e_1_2_12_19_1
  doi: 10.1364/AO.48.00D280
– ident: e_1_2_12_29_1
  doi: 10.1109/TITB.2012.2207400
– ident: e_1_2_12_40_1
  doi: 10.1371/journal.pone.0244186
– ident: e_1_2_12_37_1
  doi: 10.1016/j.neuroimage.2013.06.054
– ident: e_1_2_12_6_1
  doi: 10.1201/9781420038491.ch8
– ident: e_1_2_12_36_1
  doi: 10.1002/hbm.20767
– ident: e_1_2_12_11_1
  doi: 10.1007/BF02447083
– ident: e_1_2_12_14_1
  doi: 10.1016/j.neuroimage.2018.09.025
– ident: e_1_2_12_9_1
  doi: 10.1080/01621459.1979.10481038
– ident: e_1_2_12_20_1
  doi: 10.1117/1.NPh.5.1.015003
– ident: e_1_2_12_34_1
  doi: 10.1038/s41598-023-47812-3
– ident: e_1_2_12_3_1
  doi: 10.1364/BOE.4.001366
– ident: e_1_2_12_31_1
  doi: 10.1016/j.patcog.2023.109603
– ident: e_1_2_12_17_1
  doi: 10.1109/EMBC46164.2021.9631014
– ident: e_1_2_12_30_1
  doi: 10.1109/TFUZZ.2021.3062723
SSID ssj0008645
Score 2.4699576
Snippet ABSTRACT Motion artifact removal is a critical issue in functional near‐infrared spectroscopy (fNIRS) analysis tasks, with traditional methods relying heavily...
Motion artifact removal is a critical issue in functional near‐infrared spectroscopy (fNIRS) analysis tasks, with traditional methods relying heavily on...
SourceID proquest
crossref
wiley
SourceType Aggregation Database
Index Database
Publisher
SubjectTerms Algorithms
Deep learning
functional near‐infrared spectroscopy
Hemodynamics
Infrared spectroscopy
LSTM‐AE
Morphology
motion
Neural networks
reconstruct hemodynamic response
Spectrum analysis
Statistical analysis
Title Motion Artifact Removal in Functional Near‐Infrared Spectroscopy Based on Long Short‐Term Memory‐Autoencoder Model
URI https://onlinelibrary.wiley.com/doi/abs/10.1111%2Fejn.16679
https://www.proquest.com/docview/3160333267
Volume 61
WOSCitedRecordID wos001407187500001&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: PRVWIB
  databaseName: Wiley Online Library Full Collection 2020
  customDbUrl:
  eissn: 1460-9568
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0008645
  issn: 0953-816X
  databaseCode: DRFUL
  dateStart: 19970101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1NT9wwEB3RpVK5FAqt2PIhq0JVL6nYZB074rR8rGi1rBCFam9R7IwLqCRod6nYGz-B38gvYcabLPRQCamXKJFsK7JnPM-j8XsAWzIPUbe1DfwVn7aRMsjQZYFpKSZ_Ucp6Lr2fPdXv68EgOZ6DnfouzJQfYpZwY8_w-zU7eGZGz5wcL4uvrThWySuYD8lu2w2Y3z_pnvVmG7GOvUYxM6oFuhUPKmIhLuSZdf47HD1hzOdI1Yea7uJ__eQSvK0QpuhMTeIdzGGxDCudgk7XVxPxWfiaT59MX4Y3e7Xe2wrcHnlBH9-RrzuIE7wqyQ7FRSG6FP2mSUPRJ9d4uLv_Vrgh164LFrAfMyVmeT0RuxQTc0GD9Mril_hxTtie2p7S7i-OuKR3Ql-dm3HJ7Jk5DgUrsf1-D2fdg9O9w6DSZQgsOXgSECbM48RG20Y7FW4bozFHZ21M4CkzGGfOSpUl9DToIheiihKrWYqz7SLGFx-gUZQFroIwBDgzZ6JQ84VaaY1pScxQ5rGVEkNswqd6edLrKf1GWh9baG5TP7dNWK8XLq08cJRGrJ8dEThVTfjil-jfA6QH3_v-5ePLm67BQshSwD4bsw6N8fAGN-C1_TO-GA03K1N8BCvk5uU
linkProvider Wiley-Blackwell
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Nb9QwEB2VLVJ74aOl6tICFkKIS1A3WceOxGUpXbWQjVDZor1FsTOGVm1SbbcVe-Mn8Bv5Jcx4k6UckJC4RIlkW5E943kejd8DeCHLEHVf28Bf8ekbKYMCXRGYnmLyF6Ws59L7nKos05NJ8nEF3rR3YRb8EMuEG3uG36_ZwTkhfcvL8ax63YtjldyB1T6ZkezA6rvj4Um63Il17EWKmVIt0L140jALcSXPsvOf8eg3yLwNVX2sGd7_v798APcajCkGC6N4CCtYbcDmoKLz9cVcvBS-6tOn0zdgbb9VfNuEbyMv6eM78oUHcYwXNVmiOK3EkOLfIm0oMnKOn99_HFVuytXrgiXsZ0yKWV_OxVuKiqWgQdK6-iI-fSV0T23HtP-LERf1zulrcD2rmT-zxKlgLbbzR3AyPBjvHwaNMkNgycWTgFBhGSc22jPaqXDPGI0lOmtjgk-FwbhwVqoioadBF7kQVZRYzWKcfRcxwtiCTlVXuA3CEOQsnIlCzVdqpTWmJ7FAWcZWSgyxC8_b9ckvFwQceXtwobnN_dx2Ybddubzxwas8YgXtiOCp6sIrv0Z_HyA_eJ_5l8f_3vQZrB2OR2meHmUfdmA9ZGFgn5vZhc5seo1P4K69mZ1eTZ82dvkL83nq1Q
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Nb9QwEB2VFlEufLQgFgpYCCEuQd1k_RGJy9I2orCNqtKivUWxM6ZFNFltt4i98RP4jfwSZrzJUg5ISFyiRLKtyPZ4nkcz7wE8l1WMZmBcFEp8BlbKqERfRravmfxFaxe49D6OdJ6b8Tg9XIHXXS3Mgh9iGXBjywjnNRs4Tip_xcrxc_2qr5ROr8HaQKaKzHJt9yg7GS1PYqOCSDFTqkWmr8YtsxBn8iw7_-mPfoPMq1A1-Jrs9v_95R241WJMMVxsiruwgvUGbA5rul-fz8ULEbI-Qzh9A9Z3OsW3Tfh2ECR9QkcueBBHeN7QThRntcjI_y3ChiIn4_j5_cd-7aecvS5Ywn7GpJjNZC7ekFesBA0yaupP4sMpoXtqe0znvzjgpN45fQ0vZw3zZ1Y4FazF9uUenGR7xztvo1aZIXJk4mlEqLBSqUu2rfE63rbWYIXeOUXwqbSoSu-kLlN6WvSJj1EnqTMsxjnwCSOM-7BaNzU-AGEJcpbeJrHhklrprO1LLFFWykmJMfbgWbc-xWRBwFF0Fxea2yLMbQ-2upUrWhu8KBJW0E4InuoevAxr9PcBir13eXh5-O9Nn8KNw92sGO3n7x_BzZh1gUNoZgtWZ9NLfAzX3dfZ2cX0SbstfwGgFOpQ
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=Motion+Artifact+Removal+in+Functional+Near%E2%80%90Infrared+Spectroscopy+Based+on+Long+Short%E2%80%90Term+Memory%E2%80%90Autoencoder+Model&rft.jtitle=The+European+journal+of+neuroscience&rft.au=Yang%2C+Pan&rft.au=Wang%2C+Junhong&rft.au=Wang%2C+Ting&rft.au=Li%2C+Lihua&rft.date=2025-01-01&rft.issn=0953-816X&rft.eissn=1460-9568&rft.volume=61&rft.issue=2&rft.epage=n%2Fa&rft_id=info:doi/10.1111%2Fejn.16679&rft.externalDBID=10.1111%252Fejn.16679&rft.externalDocID=EJN16679
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0953-816X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0953-816X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0953-816X&client=summon