Data Augmentation for Motor Imagery Signal Classification Based on a Hybrid Neural Network

As an important paradigm of spontaneous brain-computer interfaces (BCIs), motor imagery (MI) has been widely used in the fields of neurological rehabilitation and robot control. Recently, researchers have proposed various methods for feature extraction and classification based on MI signals. The dec...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Sensors (Basel, Switzerland) Jg. 20; H. 16; S. 4485
Hauptverfasser: Zhang, Kai, Xu, Guanghua, Han, Zezhen, Ma, Kaiquan, Zheng, Xiaowei, Chen, Longting, Duan, Nan, Zhang, Sicong
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Switzerland MDPI AG 11.08.2020
MDPI
Schlagworte:
ISSN:1424-8220, 1424-8220
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract As an important paradigm of spontaneous brain-computer interfaces (BCIs), motor imagery (MI) has been widely used in the fields of neurological rehabilitation and robot control. Recently, researchers have proposed various methods for feature extraction and classification based on MI signals. The decoding model based on deep neural networks (DNNs) has attracted significant attention in the field of MI signal processing. Due to the strict requirements for subjects and experimental environments, it is difficult to collect large-scale and high-quality electroencephalogram (EEG) data. However, the performance of a deep learning model depends directly on the size of the datasets. Therefore, the decoding of MI-EEG signals based on a DNN has proven highly challenging in practice. Based on this, we investigated the performance of different data augmentation (DA) methods for the classification of MI data using a DNN. First, we transformed the time series signals into spectrogram images using a short-time Fourier transform (STFT). Then, we evaluated and compared the performance of different DA methods for this spectrogram data. Next, we developed a convolutional neural network (CNN) to classify the MI signals and compared the classification performance of after DA. The Fréchet inception distance (FID) was used to evaluate the quality of the generated data (GD) and the classification accuracy, and mean kappa values were used to explore the best CNN-DA method. In addition, analysis of variance (ANOVA) and paired t-tests were used to assess the significance of the results. The results showed that the deep convolutional generative adversarial network (DCGAN) provided better augmentation performance than traditional DA methods: geometric transformation (GT), autoencoder (AE), and variational autoencoder (VAE) (p < 0.01). Public datasets of the BCI competition IV (datasets 1 and 2b) were used to verify the classification performance. Improvements in the classification accuracies of 17% and 21% (p < 0.01) were observed after DA for the two datasets. In addition, the hybrid network CNN-DCGAN outperformed the other classification methods, with average kappa values of 0.564 and 0.677 for the two datasets.
AbstractList As an important paradigm of spontaneous brain-computer interfaces (BCIs), motor imagery (MI) has been widely used in the fields of neurological rehabilitation and robot control. Recently, researchers have proposed various methods for feature extraction and classification based on MI signals. The decoding model based on deep neural networks (DNNs) has attracted significant attention in the field of MI signal processing. Due to the strict requirements for subjects and experimental environments, it is difficult to collect large-scale and high-quality electroencephalogram (EEG) data. However, the performance of a deep learning model depends directly on the size of the datasets. Therefore, the decoding of MI-EEG signals based on a DNN has proven highly challenging in practice. Based on this, we investigated the performance of different data augmentation (DA) methods for the classification of MI data using a DNN. First, we transformed the time series signals into spectrogram images using a short-time Fourier transform (STFT). Then, we evaluated and compared the performance of different DA methods for this spectrogram data. Next, we developed a convolutional neural network (CNN) to classify the MI signals and compared the classification performance of after DA. The Fréchet inception distance (FID) was used to evaluate the quality of the generated data (GD) and the classification accuracy, and mean kappa values were used to explore the best CNN-DA method. In addition, analysis of variance (ANOVA) and paired t-tests were used to assess the significance of the results. The results showed that the deep convolutional generative adversarial network (DCGAN) provided better augmentation performance than traditional DA methods: geometric transformation (GT), autoencoder (AE), and variational autoencoder (VAE) (p < 0.01). Public datasets of the BCI competition IV (datasets 1 and 2b) were used to verify the classification performance. Improvements in the classification accuracies of 17% and 21% (p < 0.01) were observed after DA for the two datasets. In addition, the hybrid network CNN-DCGAN outperformed the other classification methods, with average kappa values of 0.564 and 0.677 for the two datasets.As an important paradigm of spontaneous brain-computer interfaces (BCIs), motor imagery (MI) has been widely used in the fields of neurological rehabilitation and robot control. Recently, researchers have proposed various methods for feature extraction and classification based on MI signals. The decoding model based on deep neural networks (DNNs) has attracted significant attention in the field of MI signal processing. Due to the strict requirements for subjects and experimental environments, it is difficult to collect large-scale and high-quality electroencephalogram (EEG) data. However, the performance of a deep learning model depends directly on the size of the datasets. Therefore, the decoding of MI-EEG signals based on a DNN has proven highly challenging in practice. Based on this, we investigated the performance of different data augmentation (DA) methods for the classification of MI data using a DNN. First, we transformed the time series signals into spectrogram images using a short-time Fourier transform (STFT). Then, we evaluated and compared the performance of different DA methods for this spectrogram data. Next, we developed a convolutional neural network (CNN) to classify the MI signals and compared the classification performance of after DA. The Fréchet inception distance (FID) was used to evaluate the quality of the generated data (GD) and the classification accuracy, and mean kappa values were used to explore the best CNN-DA method. In addition, analysis of variance (ANOVA) and paired t-tests were used to assess the significance of the results. The results showed that the deep convolutional generative adversarial network (DCGAN) provided better augmentation performance than traditional DA methods: geometric transformation (GT), autoencoder (AE), and variational autoencoder (VAE) (p < 0.01). Public datasets of the BCI competition IV (datasets 1 and 2b) were used to verify the classification performance. Improvements in the classification accuracies of 17% and 21% (p < 0.01) were observed after DA for the two datasets. In addition, the hybrid network CNN-DCGAN outperformed the other classification methods, with average kappa values of 0.564 and 0.677 for the two datasets.
As an important paradigm of spontaneous brain-computer interfaces (BCIs), motor imagery (MI) has been widely used in the fields of neurological rehabilitation and robot control. Recently, researchers have proposed various methods for feature extraction and classification based on MI signals. The decoding model based on deep neural networks (DNNs) has attracted significant attention in the field of MI signal processing. Due to the strict requirements for subjects and experimental environments, it is difficult to collect large-scale and high-quality electroencephalogram (EEG) data. However, the performance of a deep learning model depends directly on the size of the datasets. Therefore, the decoding of MI-EEG signals based on a DNN has proven highly challenging in practice. Based on this, we investigated the performance of different data augmentation (DA) methods for the classification of MI data using a DNN. First, we transformed the time series signals into spectrogram images using a short-time Fourier transform (STFT). Then, we evaluated and compared the performance of different DA methods for this spectrogram data. Next, we developed a convolutional neural network (CNN) to classify the MI signals and compared the classification performance of after DA. The Fréchet inception distance (FID) was used to evaluate the quality of the generated data (GD) and the classification accuracy, and mean kappa values were used to explore the best CNN-DA method. In addition, analysis of variance (ANOVA) and paired -tests were used to assess the significance of the results. The results showed that the deep convolutional generative adversarial network (DCGAN) provided better augmentation performance than traditional DA methods: geometric transformation (GT), autoencoder (AE), and variational autoencoder (VAE) ( < 0.01). Public datasets of the BCI competition IV (datasets 1 and 2b) were used to verify the classification performance. Improvements in the classification accuracies of 17% and 21% ( < 0.01) were observed after DA for the two datasets. In addition, the hybrid network CNN-DCGAN outperformed the other classification methods, with average kappa values of 0.564 and 0.677 for the two datasets.
As an important paradigm of spontaneous brain-computer interfaces (BCIs), motor imagery (MI) has been widely used in the fields of neurological rehabilitation and robot control. Recently, researchers have proposed various methods for feature extraction and classification based on MI signals. The decoding model based on deep neural networks (DNNs) has attracted significant attention in the field of MI signal processing. Due to the strict requirements for subjects and experimental environments, it is difficult to collect large-scale and high-quality electroencephalogram (EEG) data. However, the performance of a deep learning model depends directly on the size of the datasets. Therefore, the decoding of MI-EEG signals based on a DNN has proven highly challenging in practice. Based on this, we investigated the performance of different data augmentation (DA) methods for the classification of MI data using a DNN. First, we transformed the time series signals into spectrogram images using a short-time Fourier transform (STFT). Then, we evaluated and compared the performance of different DA methods for this spectrogram data. Next, we developed a convolutional neural network (CNN) to classify the MI signals and compared the classification performance of after DA. The Fréchet inception distance (FID) was used to evaluate the quality of the generated data (GD) and the classification accuracy, and mean kappa values were used to explore the best CNN-DA method. In addition, analysis of variance (ANOVA) and paired t-tests were used to assess the significance of the results. The results showed that the deep convolutional generative adversarial network (DCGAN) provided better augmentation performance than traditional DA methods: geometric transformation (GT), autoencoder (AE), and variational autoencoder (VAE) (p < 0.01). Public datasets of the BCI competition IV (datasets 1 and 2b) were used to verify the classification performance. Improvements in the classification accuracies of 17% and 21% (p < 0.01) were observed after DA for the two datasets. In addition, the hybrid network CNN-DCGAN outperformed the other classification methods, with average kappa values of 0.564 and 0.677 for the two datasets.
Author Ma, Kaiquan
Zhang, Sicong
Zheng, Xiaowei
Xu, Guanghua
Duan, Nan
Zhang, Kai
Han, Zezhen
Chen, Longting
AuthorAffiliation 1 School of Mechanical Engineering, Xi’an Jiaotong University, Xi’an 710049, China; zhangkai0912@stu.xjtu.edu.cn (K.Z.); hanzehen@stu.xjtu.edu.cn (Z.H.); mkq1994@stu.xjtu.edu.cn (K.M.); hlydx1314@stu.xjtu.edu.cn (X.Z.); cltdevelop@stu.xjtu.edu.cn (L.C.); shenkong@stu.xjtu.edu.cn (N.D.); zhsicong@mail.xjtu.edu.cn (S.Z.)
2 State Key Laboratory for Manufacturing Systems Engineering, Xi’an Jiaotong University, Xi’an 710049, China
AuthorAffiliation_xml – name: 1 School of Mechanical Engineering, Xi’an Jiaotong University, Xi’an 710049, China; zhangkai0912@stu.xjtu.edu.cn (K.Z.); hanzehen@stu.xjtu.edu.cn (Z.H.); mkq1994@stu.xjtu.edu.cn (K.M.); hlydx1314@stu.xjtu.edu.cn (X.Z.); cltdevelop@stu.xjtu.edu.cn (L.C.); shenkong@stu.xjtu.edu.cn (N.D.); zhsicong@mail.xjtu.edu.cn (S.Z.)
– name: 2 State Key Laboratory for Manufacturing Systems Engineering, Xi’an Jiaotong University, Xi’an 710049, China
Author_xml – sequence: 1
  givenname: Kai
  surname: Zhang
  fullname: Zhang, Kai
– sequence: 2
  givenname: Guanghua
  surname: Xu
  fullname: Xu, Guanghua
– sequence: 3
  givenname: Zezhen
  surname: Han
  fullname: Han, Zezhen
– sequence: 4
  givenname: Kaiquan
  surname: Ma
  fullname: Ma, Kaiquan
– sequence: 5
  givenname: Xiaowei
  orcidid: 0000-0002-8653-7129
  surname: Zheng
  fullname: Zheng, Xiaowei
– sequence: 6
  givenname: Longting
  surname: Chen
  fullname: Chen, Longting
– sequence: 7
  givenname: Nan
  surname: Duan
  fullname: Duan, Nan
– sequence: 8
  givenname: Sicong
  surname: Zhang
  fullname: Zhang, Sicong
BackLink https://www.ncbi.nlm.nih.gov/pubmed/32796607$$D View this record in MEDLINE/PubMed
BookMark eNptkk1v1DAQhiNURD_gwB9AkbjAYalje-34glSWQlcq5QBcuFgTexy8JHGxE6r995hmWbUVF3s0fub1fB0XB0MYsCieV-QNY4qcJkoqwXm9fFQcVZzyRU0pObhjHxbHKW0IoYyx-klxyKhUQhB5VHx_DyOUZ1Pb4zDC6MNQuhDLT2HM57qHFuO2_OLbAbpy1UFK3nkzc-8goS2zAeXFtonellc4xcxd4XgT4s-nxWMHXcJnu_uk-Pbh_OvqYnH5-eN6dXa5MFyocVHbpRKMEFU1gEBRWOmcFOiy0zluDZBGGQkNt6RpFEqwppGWKeUIVYqxk2I969oAG30dfQ9xqwN4fesIsdUQR2861E6CVCiUpYJyJpY5WgKtcakUdwwga72dta6npkdrclNyRfdE778M_oduw28tueScyizwaicQw68J06h7nwx2HQwYpqTzt5xLQW_Rlw_QTZhibvSOooRWVaZe3M1on8q_EWbg9QyYGFKK6PZIRfTf9dD79cjs6QPW-HnquRjf_SfiD_iQu08
CitedBy_id crossref_primary_10_3390_s23041932
crossref_primary_10_1186_s42490_024_00080_2
crossref_primary_10_3390_info13090406
crossref_primary_10_3390_s20205736
crossref_primary_10_1088_1741_2552_ad6598
crossref_primary_10_3390_brainsci11010075
crossref_primary_10_1016_j_asoc_2024_111771
crossref_primary_10_1007_s00521_023_08927_w
crossref_primary_10_1016_j_bspc_2022_104349
crossref_primary_10_1177_09287329241291367
crossref_primary_10_1007_s00521_021_06352_5
crossref_primary_10_1016_j_aei_2024_102434
crossref_primary_10_3390_ai6090230
crossref_primary_10_3390_app12052598
crossref_primary_10_1007_s00521_025_11346_8
crossref_primary_10_1007_s00521_024_09731_w
crossref_primary_10_1007_s11042_024_20510_6
crossref_primary_10_1016_j_bspc_2022_103614
crossref_primary_10_3390_s21196503
crossref_primary_10_1186_s13634_024_01188_2
crossref_primary_10_3390_s23187694
crossref_primary_10_3390_machines13010071
crossref_primary_10_1002_asjc_3000
crossref_primary_10_1049_2024_5596468
crossref_primary_10_1109_ACCESS_2025_3563623
crossref_primary_10_1016_j_bspc_2021_103052
crossref_primary_10_3389_fninf_2025_1521805
crossref_primary_10_3389_frobt_2024_1362735
crossref_primary_10_1109_MSP_2023_3278074
crossref_primary_10_1155_2022_2047576
crossref_primary_10_3390_app10207208
crossref_primary_10_1007_s11042_023_15900_1
crossref_primary_10_1016_j_compscitech_2021_108713
crossref_primary_10_1080_03091902_2025_2463577
crossref_primary_10_1038_s41598_022_08490_9
crossref_primary_10_1371_journal_pone_0311942
crossref_primary_10_1016_j_jneumeth_2022_109736
crossref_primary_10_1109_ACCESS_2021_3126345
crossref_primary_10_1109_TIM_2024_3522618
crossref_primary_10_1093_cercor_bhad511
crossref_primary_10_1007_s11760_023_02808_4
crossref_primary_10_3389_fnhum_2024_1430086
crossref_primary_10_1109_ACCESS_2025_3604528
crossref_primary_10_3389_fnhum_2021_765525
crossref_primary_10_3390_app10248934
crossref_primary_10_3389_fnhum_2024_1421922
crossref_primary_10_1038_s41598_022_26882_9
crossref_primary_10_1109_ACCESS_2020_3023970
crossref_primary_10_1002_ima_22913
crossref_primary_10_1109_TII_2020_3044310
crossref_primary_10_1088_2632_2153_ad200c
crossref_primary_10_1007_s11517_023_02857_4
crossref_primary_10_1016_j_bspc_2022_103718
crossref_primary_10_3390_electronics12244944
crossref_primary_10_1016_j_ymssp_2025_112561
crossref_primary_10_1088_2057_1976_ac4c28
crossref_primary_10_1007_s00521_025_11403_2
crossref_primary_10_3390_s20216321
crossref_primary_10_1007_s00170_024_14098_2
crossref_primary_10_1016_j_measurement_2024_114795
crossref_primary_10_3390_brainsci14040375
crossref_primary_10_3389_fnhum_2023_1292428
crossref_primary_10_3389_fnins_2023_1219133
crossref_primary_10_1109_TNSRE_2023_3243992
crossref_primary_10_1109_ACCESS_2024_3421569
crossref_primary_10_1109_ACCESS_2023_3299497
crossref_primary_10_30773_pi_2025_0133
crossref_primary_10_3390_s25103178
crossref_primary_10_3389_fnins_2022_988535
crossref_primary_10_3390_life12030374
crossref_primary_10_3389_fnhum_2021_643386
crossref_primary_10_1088_1741_2552_ac4430
Cites_doi 10.1109/TBME.2014.2312397
10.1016/j.apmr.2014.08.024
10.1109/SMC.2019.8914246
10.1038/nature14539
10.1088/1741-2552/ab260c
10.1007/978-3-319-73600-6_8
10.3389/fnbot.2019.00023
10.1109/CVPR.2019.00020
10.1109/TPAMI.2015.2496141
10.1088/1741-2552/ab0ab5
10.1093/ietisy/e91-d.1.44
10.1016/S1388-2457(99)00141-8
10.1016/j.neucom.2018.09.013
10.3390/s19061423
10.1109/CVPR.2016.90
10.1109/LSP.2017.2657381
10.1007/978-3-642-02091-9_18
10.1088/1741-2552/ab405f
10.1088/1741-2552/ab57c0
10.3390/s19030551
10.1109/CVPR.2015.7298594
10.1002/ima.22405
10.1186/s40537-019-0197-0
10.1109/TMI.2016.2538465
10.1109/ACCESS.2017.2696121
10.1109/IJCNN.2017.7966388
10.3390/s19071736
10.1016/j.brainresrev.2008.12.024
10.1109/ICAEE48663.2019.8975578
10.1109/TBME.2006.888836
10.1109/IWW-BCI.2019.8737345
10.3390/s120201211
10.1038/s41598-017-09597-0
10.1111/mice.12458
10.1109/BigData.2018.8622525
10.1109/TASSP.1984.1164317
10.1109/JSEN.2019.2899645
10.1109/NER.2013.6695959
10.1109/5.939829
10.1109/CONIELECOMP.2018.8327170
10.1016/j.compbiomed.2019.02.009
10.1016/j.compind.2019.01.001
10.1088/1741-2560/14/1/016003
10.1002/hbm.23730
10.1097/WNR.0b013e32834ca58d
10.1109/TBME.2015.2402252
10.1109/ACCESS.2019.2895133
10.1109/TMI.2016.2536809
10.1109/TNSRE.2019.2915621
10.3390/s18041136
10.1088/1741-2552/aace8c
10.1109/SSCI.2018.8628917
10.1109/IJCNN.2018.8489727
10.1145/3057280
10.1109/ICDAR.2015.7333881
10.1016/j.compbiomed.2004.05.001
10.1016/j.cell.2019.04.005
ContentType Journal Article
Copyright 2020. This work is licensed under http://creativecommons.org/licenses/by/3.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
2020 by the authors. 2020
Copyright_xml – notice: 2020. This work is licensed under http://creativecommons.org/licenses/by/3.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
– notice: 2020 by the authors. 2020
DBID AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
3V.
7X7
7XB
88E
8FI
8FJ
8FK
ABUWG
AFKRA
AZQEC
BENPR
CCPQU
DWQXO
FYUFA
GHDGH
K9.
M0S
M1P
PHGZM
PHGZT
PIMPY
PJZUB
PKEHL
PPXIY
PQEST
PQQKQ
PQUKI
PRINS
7X8
5PM
DOA
DOI 10.3390/s20164485
DatabaseName CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
ProQuest Central (Corporate)
ProQuest Health & Medical
ProQuest Central (purchase pre-March 2016)
Medical Database (Alumni Edition)
ProQuest Hospital Collection
Hospital Premium Collection (Alumni Edition)
ProQuest Central (Alumni) (purchase pre-March 2016)
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
ProQuest Central Essentials
ProQuest Central
ProQuest One
ProQuest Central
Proquest Health Research Premium Collection
Health Research Premium Collection (Alumni)
ProQuest Health & Medical Complete (Alumni)
ProQuest Health & Medical Collection
Medical Database
Proquest Central Premium
ProQuest One Academic (New)
Publicly Available Content Database
ProQuest Health & Medical Research Collection
ProQuest One Academic Middle East (New)
ProQuest One Health & Nursing
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
MEDLINE - Academic
PubMed Central (Full Participant titles)
DOAJ Directory of Open Access Journals
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
Publicly Available Content Database
ProQuest One Academic Middle East (New)
ProQuest Central Essentials
ProQuest Health & Medical Complete (Alumni)
ProQuest Central (Alumni Edition)
ProQuest One Community College
ProQuest One Health & Nursing
ProQuest Central China
ProQuest Central
ProQuest Health & Medical Research Collection
Health Research Premium Collection
Health and Medicine Complete (Alumni Edition)
ProQuest Central Korea
Health & Medical Research Collection
ProQuest Central (New)
ProQuest Medical Library (Alumni)
ProQuest One Academic Eastern Edition
ProQuest Hospital Collection
Health Research Premium Collection (Alumni)
ProQuest Hospital Collection (Alumni)
ProQuest Health & Medical Complete
ProQuest Medical Library
ProQuest One Academic UKI Edition
ProQuest One Academic
ProQuest One Academic (New)
ProQuest Central (Alumni)
MEDLINE - Academic
DatabaseTitleList MEDLINE - Academic
MEDLINE
Publicly Available Content Database

CrossRef

Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 3
  dbid: PIMPY
  name: ProQuest Publicly Available Content Database
  url: http://search.proquest.com/publiccontent
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1424-8220
ExternalDocumentID oai_doaj_org_article_f7a79e69d26243659337a28e5994f3aa
PMC7474427
32796607
10_3390_s20164485
Genre Journal Article
GrantInformation_xml – fundername: National Natural Science Foundation of China
  grantid: 51775415
– fundername: National Key Research & Development Plan of China
  grantid: 2017YFC1308500
– fundername: Key Research & Development Plan of Shaanxi Province
  grantid: 2018ZDCXL-GY-06-01
GroupedDBID ---
123
2WC
53G
5VS
7X7
88E
8FE
8FG
8FI
8FJ
AADQD
AAHBH
AAYXX
ABDBF
ABUWG
ACUHS
ADBBV
ADMLS
AENEX
AFFHD
AFKRA
AFZYC
ALMA_UNASSIGNED_HOLDINGS
BENPR
BPHCQ
BVXVI
CCPQU
CITATION
CS3
D1I
DU5
E3Z
EBD
ESX
F5P
FYUFA
GROUPED_DOAJ
GX1
HH5
HMCUK
HYE
KQ8
L6V
M1P
M48
MODMG
M~E
OK1
OVT
P2P
P62
PHGZM
PHGZT
PIMPY
PJZUB
PPXIY
PQQKQ
PROAC
PSQYO
RNS
RPM
TUS
UKHRP
XSB
~8M
3V.
ABJCF
ALIPV
ARAPS
CGR
CUY
CVF
ECM
EIF
HCIFZ
KB.
M7S
NPM
PDBOC
7XB
8FK
AZQEC
DWQXO
K9.
PKEHL
PQEST
PQUKI
PRINS
7X8
PUEGO
5PM
ID FETCH-LOGICAL-c469t-8d59630091baea2e6d7ff76ef630ff4dca0b9c7ab4d0bb9e7adcb7d399f029933
IEDL.DBID BENPR
ISICitedReferencesCount 84
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000564803800001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1424-8220
IngestDate Fri Oct 03 12:52:59 EDT 2025
Tue Nov 04 01:49:32 EST 2025
Thu Sep 04 20:06:35 EDT 2025
Tue Oct 07 07:18:13 EDT 2025
Wed Feb 19 02:01:58 EST 2025
Tue Nov 18 21:26:38 EST 2025
Sat Nov 29 07:13:13 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 16
Keywords DCGAN
motor imagery
CNN
data augmentation
classification
Language English
License Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c469t-8d59630091baea2e6d7ff76ef630ff4dca0b9c7ab4d0bb9e7adcb7d399f029933
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0002-8653-7129
OpenAccessLink https://www.proquest.com/docview/2434420211?pq-origsite=%requestingapplication%
PMID 32796607
PQID 2434420211
PQPubID 2032333
ParticipantIDs doaj_primary_oai_doaj_org_article_f7a79e69d26243659337a28e5994f3aa
pubmedcentral_primary_oai_pubmedcentral_nih_gov_7474427
proquest_miscellaneous_2434476227
proquest_journals_2434420211
pubmed_primary_32796607
crossref_primary_10_3390_s20164485
crossref_citationtrail_10_3390_s20164485
PublicationCentury 2000
PublicationDate 20200811
PublicationDateYYYYMMDD 2020-08-11
PublicationDate_xml – month: 8
  year: 2020
  text: 20200811
  day: 11
PublicationDecade 2020
PublicationPlace Switzerland
PublicationPlace_xml – name: Switzerland
– name: Basel
PublicationTitle Sensors (Basel, Switzerland)
PublicationTitleAlternate Sensors (Basel)
PublicationYear 2020
Publisher MDPI AG
MDPI
Publisher_xml – name: MDPI AG
– name: MDPI
References ref_50
Li (ref_27) 2019; 27
Roy (ref_19) 2019; 16
Shorten (ref_34) 2019; 6
Salamon (ref_18) 2017; 24
Ponce (ref_70) 2019; 177
ref_14
ref_57
ref_56
ref_54
ref_53
ref_52
ref_51
ref_16
ref_15
Pereira (ref_22) 2016; 35
ref_25
ref_67
ref_66
Zhang (ref_28) 2019; 7
ref_20
ref_64
ref_63
Setio (ref_21) 2016; 35
ref_29
(ref_45) 2005; 35
Woehrle (ref_11) 2015; 62
Dai (ref_26) 2020; 17
Pfurtscheller (ref_46) 2001; 89
Gao (ref_40) 2019; 34
Yuan (ref_1) 2014; 61
ref_72
ref_71
Lemley (ref_47) 2017; 5
Lozano (ref_61) 2009; 32
(ref_2) 2012; 12
ref_36
ref_35
Ang (ref_62) 2012; 6
Vernon (ref_68) 2018; 15
ref_33
ref_32
Shao (ref_23) 2019; 106
ref_31
Freer (ref_30) 2019; 17
ref_73
ref_39
ref_38
ref_37
Bonassi (ref_3) 2017; 7
Diamant (ref_24) 2018; 321
Phothisonothai (ref_7) 2008; 91
Vidaurre (ref_10) 2007; 54
Anderson (ref_6) 2011; 22
Chaudhary (ref_69) 2019; 19
Craik (ref_60) 2019; 16
Coyle (ref_5) 2015; 96
LeCun (ref_17) 2015; 521
Duan (ref_12) 2019; 13
Dosovitskiy (ref_55) 2015; 38
Munzert (ref_4) 2009; 60
Tabar (ref_58) 2016; 14
ref_42
ref_41
Schirrmeister (ref_59) 2017; 38
ref_49
ref_48
ref_9
ref_8
Song (ref_13) 2017; 35
Pfurtscheller (ref_43) 1999; 110
Malan (ref_65) 2019; 107
Griffin (ref_44) 1984; 32
References_xml – volume: 61
  start-page: 1425
  year: 2014
  ident: ref_1
  article-title: Brain-computer interfaces using sensorimotor rhythms: Current state and future perspectives
  publication-title: IEEE Trans. Biomed. Eng.
  doi: 10.1109/TBME.2014.2312397
– volume: 96
  start-page: S62
  year: 2015
  ident: ref_5
  article-title: Sensorimotor Modulation Assessment and Brain-Computer Interface Training in Disorders of Consciousness
  publication-title: Arch. Phys. Med. Rehabil.
  doi: 10.1016/j.apmr.2014.08.024
– ident: ref_16
  doi: 10.1109/SMC.2019.8914246
– volume: 521
  start-page: 436
  year: 2015
  ident: ref_17
  article-title: Deep learning
  publication-title: Nature
  doi: 10.1038/nature14539
– volume: 16
  start-page: 051001
  year: 2019
  ident: ref_19
  article-title: Deep learning-based electroencephalography analysis: A systematic review
  publication-title: J. Neural Eng.
  doi: 10.1088/1741-2552/ab260c
– ident: ref_37
  doi: 10.1007/978-3-319-73600-6_8
– volume: 32
  start-page: 569
  year: 2009
  ident: ref_61
  article-title: Sensitivity Analysis of k-Fold Cross Validation in Prediction Error Estimation
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 13
  start-page: 23
  year: 2019
  ident: ref_12
  article-title: Quadcopter Flight Control Using a Non-invasive Multi-Modal Brain Computer Interface. Frontiers
  publication-title: Neurorobotics
  doi: 10.3389/fnbot.2019.00023
– ident: ref_48
  doi: 10.1109/CVPR.2019.00020
– ident: ref_51
– volume: 38
  start-page: 1734
  year: 2015
  ident: ref_55
  article-title: Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/TPAMI.2015.2496141
– volume: 16
  start-page: 031001
  year: 2019
  ident: ref_60
  article-title: Deep learning for electroencephalogram (EEG) classification tasks: A review
  publication-title: J. Neural Eng.
  doi: 10.1088/1741-2552/ab0ab5
– ident: ref_39
– volume: 91
  start-page: 44
  year: 2008
  ident: ref_7
  article-title: EEG-based classification of motor imagery tasks using fractal dimension and neural network for brain-computer interface
  publication-title: IEICE Trans. Inf. Syst.
  doi: 10.1093/ietisy/e91-d.1.44
– ident: ref_42
– ident: ref_35
– volume: 110
  start-page: 1842
  year: 1999
  ident: ref_43
  article-title: Event-related EEG/MEG synchronization and desynchronization: Basic principles
  publication-title: Clin. Neurophysiol.
  doi: 10.1016/S1388-2457(99)00141-8
– volume: 321
  start-page: 321
  year: 2018
  ident: ref_24
  article-title: GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2018.09.013
– ident: ref_71
  doi: 10.3390/s19061423
– ident: ref_52
– ident: ref_38
  doi: 10.1109/CVPR.2016.90
– volume: 24
  start-page: 279
  year: 2017
  ident: ref_18
  article-title: Deep convolutional neural networks and data augmentation for environmental sound classification
  publication-title: IEEE Signal. Process. Lett.
  doi: 10.1109/LSP.2017.2657381
– ident: ref_41
– ident: ref_8
  doi: 10.1007/978-3-642-02091-9_18
– volume: 17
  start-page: 016025
  year: 2020
  ident: ref_26
  article-title: HS-CNN: A CNN with hybrid convolution scale for EEG motor imagery classification
  publication-title: J. Neural Eng.
  doi: 10.1088/1741-2552/ab405f
– volume: 17
  start-page: 016041
  year: 2019
  ident: ref_30
  article-title: Data augmentation for self-paced motor imagery classification with C-LSTM
  publication-title: J. Neural Eng.
  doi: 10.1088/1741-2552/ab57c0
– ident: ref_64
  doi: 10.3390/s19030551
– ident: ref_57
  doi: 10.1109/CVPR.2015.7298594
– ident: ref_63
  doi: 10.1002/ima.22405
– volume: 6
  start-page: 1
  year: 2019
  ident: ref_34
  article-title: A survey on Image Data Augmentation for Deep Learning
  publication-title: J. Big Data
  doi: 10.1186/s40537-019-0197-0
– volume: 35
  start-page: 1240
  year: 2016
  ident: ref_22
  article-title: Brain tumor segmentation using convolutional neural networks in MRI images
  publication-title: IEEE Trans. Med. Imaging
  doi: 10.1109/TMI.2016.2538465
– volume: 5
  start-page: 5858
  year: 2017
  ident: ref_47
  article-title: Smart augmentation learning an optimal data augmentation strategy
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2017.2696121
– ident: ref_66
  doi: 10.1109/IJCNN.2017.7966388
– ident: ref_31
  doi: 10.3390/s19071736
– ident: ref_53
– volume: 6
  start-page: 39
  year: 2012
  ident: ref_62
  article-title: Filter Bank Common Spatial Pattern Algorithm on BCI Competition IV Datasets 2a and 2b
  publication-title: Front. Behav. Neurosci.
– volume: 60
  start-page: 306
  year: 2009
  ident: ref_4
  article-title: Cognitive motor processes: The role of motor imagery in the study of motor representations
  publication-title: Brain Res. Rev.
  doi: 10.1016/j.brainresrev.2008.12.024
– ident: ref_32
  doi: 10.1109/ICAEE48663.2019.8975578
– volume: 54
  start-page: 550
  year: 2007
  ident: ref_10
  article-title: Study of on-line adaptive discriminant analysis for EEG-based brain computer interface
  publication-title: IEEE Trans. Biomed. Eng.
  doi: 10.1109/TBME.2006.888836
– ident: ref_29
  doi: 10.1109/IWW-BCI.2019.8737345
– volume: 12
  start-page: 1211
  year: 2012
  ident: ref_2
  article-title: Brain computer interfaces, a review
  publication-title: Sensors
  doi: 10.3390/s120201211
– volume: 7
  start-page: 1
  year: 2017
  ident: ref_3
  article-title: Provision of somatosensory inputs during motor imagery enhances learning-induced plasticity in human motor cortex
  publication-title: Sci. Rep.
  doi: 10.1038/s41598-017-09597-0
– volume: 34
  start-page: 755
  year: 2019
  ident: ref_40
  article-title: Deep leaf-bootstrapping generative adversarial network for structural image data augmentation
  publication-title: Comput. Civ. Infrastruct. Eng.
  doi: 10.1111/mice.12458
– ident: ref_56
  doi: 10.1109/BigData.2018.8622525
– volume: 32
  start-page: 236
  year: 1984
  ident: ref_44
  article-title: Signal estimation from modified short-time Fourier transform
  publication-title: IEEE Trans. Acoust. SpeechSignal Process.
  doi: 10.1109/TASSP.1984.1164317
– ident: ref_67
– volume: 19
  start-page: 4494
  year: 2019
  ident: ref_69
  article-title: Convolutional Neural Network Based Approach Towards Motor Imagery Tasks EEG Signals Classification
  publication-title: IEEE Sens. J.
  doi: 10.1109/JSEN.2019.2899645
– ident: ref_14
– ident: ref_9
  doi: 10.1109/NER.2013.6695959
– volume: 89
  start-page: 1123
  year: 2001
  ident: ref_46
  article-title: Motor imagery and direct brain-computer communication
  publication-title: Proc. IEEE
  doi: 10.1109/5.939829
– ident: ref_73
– ident: ref_20
  doi: 10.1109/CONIELECOMP.2018.8327170
– volume: 107
  start-page: 118
  year: 2019
  ident: ref_65
  article-title: Feature selection using regularized neighbourhood component analysis to enhance the classification performance of motor imagery signals
  publication-title: Comput. Boil. Med.
  doi: 10.1016/j.compbiomed.2019.02.009
– volume: 106
  start-page: 85
  year: 2019
  ident: ref_23
  article-title: Generative adversarial networks for data augmentation in machine fault diagnosis
  publication-title: Comput. Ind.
  doi: 10.1016/j.compind.2019.01.001
– volume: 14
  start-page: 16003
  year: 2016
  ident: ref_58
  article-title: A novel deep learning approach for classification of EEG motor imagery signals
  publication-title: J. Neural Eng.
  doi: 10.1088/1741-2560/14/1/016003
– volume: 38
  start-page: 5391
  year: 2017
  ident: ref_59
  article-title: Deep learning with convolutional neural networks for EEG decoding and visualization
  publication-title: Hum. Brain Mapp.
  doi: 10.1002/hbm.23730
– ident: ref_50
– ident: ref_33
– ident: ref_54
– volume: 22
  start-page: 939
  year: 2011
  ident: ref_6
  article-title: Review of motor and phantom-related imagery
  publication-title: Neuroreport
  doi: 10.1097/WNR.0b013e32834ca58d
– volume: 62
  start-page: 1696
  year: 2015
  ident: ref_11
  article-title: An adaptive spatial flter for user-independent single trial detection of event-related potentials
  publication-title: IEEE Trans. Biomed. Eng.
  doi: 10.1109/TBME.2015.2402252
– volume: 7
  start-page: 15945
  year: 2019
  ident: ref_28
  article-title: A novel deep learning approach with data augmsentation to classify motor imagery signals
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2019.2895133
– volume: 35
  start-page: 1160
  year: 2016
  ident: ref_21
  article-title: Pulmonary Nodule Detection in CT Images: False Positive Reduction Using Multi-View Convolutional Networks
  publication-title: IEEE Trans. Med. Imaging
  doi: 10.1109/TMI.2016.2536809
– volume: 27
  start-page: 1170
  year: 2019
  ident: ref_27
  article-title: A Channel-Projection Mixed-Scale Convolutional Neural Network for Motor Imagery EEG Decoding
  publication-title: IEEE Trans. Neural Syst. Rehabil. Eng.
  doi: 10.1109/TNSRE.2019.2915621
– ident: ref_72
  doi: 10.3390/s18041136
– volume: 15
  start-page: 056013
  year: 2018
  ident: ref_68
  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
– ident: ref_49
  doi: 10.1109/SSCI.2018.8628917
– ident: ref_25
  doi: 10.1109/IJCNN.2018.8489727
– volume: 35
  start-page: 1
  year: 2017
  ident: ref_13
  article-title: DeepMob: Learning deep knowledge of human emergency behavior and mobility from big and heterogeneous data
  publication-title: ACM Trans. Inf. Syst. (TOIS)
  doi: 10.1145/3057280
– ident: ref_15
  doi: 10.1109/ICDAR.2015.7333881
– ident: ref_36
– volume: 35
  start-page: 603
  year: 2005
  ident: ref_45
  article-title: Comparison of STFT and wavelet transform methods in determining epileptic seizure activity in EEG signals for real-time application
  publication-title: Comput. Boil. Med.
  doi: 10.1016/j.compbiomed.2004.05.001
– volume: 177
  start-page: 999
  year: 2019
  ident: ref_70
  article-title: Evolving Images for Visual Neurons Using a Deep Generative Network Reveals Coding Principles and Neuronal Preferences
  publication-title: Cell
  doi: 10.1016/j.cell.2019.04.005
SSID ssj0023338
Score 2.5636027
Snippet As an important paradigm of spontaneous brain-computer interfaces (BCIs), motor imagery (MI) has been widely used in the fields of neurological rehabilitation...
SourceID doaj
pubmedcentral
proquest
pubmed
crossref
SourceType Open Website
Open Access Repository
Aggregation Database
Index Database
Enrichment Source
StartPage 4485
SubjectTerms Algorithms
Brain-Computer Interfaces
Classification
CNN
data augmentation
Datasets
DCGAN
Electroencephalography
Humans
Imagination
Methods
motor imagery
Neural networks
Neural Networks, Computer
Noise
Signal processing
SummonAdditionalLinks – databaseName: DOAJ Directory of Open Access Journals
  dbid: DOA
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1NT9wwEB1ViEM5oEL5SKHIrThwidi1HXt9hAKih64qARLiEvkTVoJsxe5W4t8zk2SjXYTUS2-RPUqc8UTznjJ-A3DYpy5vNhT5IBQylzzE3KXIcyFNEqmnfFSpbjahh8PB7a35vdDqi2rCGnngxnHHSVttojKBKy6FKpCAa8sHsTBGJmFraISoZ06mWqolkHk1OkICSf3xhJOSlKSGyQvZpxbpfw9Zvi2QXMg4F59gvYWK7KRZ4gZ8iNUmrC0ICH6GuzM7texkdv_UHiGqGIJQ9muMTJr9fCJ9ihd2Nbqn-9TtL6kwqLE7xfQVGF5YdvlCx7YY6XSg3bApDN-Cm4vz6x-XedstIfdIcafkbEP6WabvbLQ8qqBT0iomHExJBm97znhtnQw950zUNninAwKU1MOcJMQ2rFTjKu4CK5JPUQYRrcPsryxiRJdsQOZUKF_omMHR3Iulb6XEqaPFY4mUghxedg7P4Htn-qfRz3jP6JS2ojMgyet6AAOhbAOh_FcgZLA_38iy_Q4nJVpKyRHH9DP41k3jF0S_RWwVx7PWBnMC1xnsNPverURwTfKlOKOXImJpqcsz1eihVulGnoaP1l_-x7vtwUdOPJ-kePv7sDJ9nsWvsOr_TkeT54M69F8BZJwKWg
  priority: 102
  providerName: Directory of Open Access Journals
Title Data Augmentation for Motor Imagery Signal Classification Based on a Hybrid Neural Network
URI https://www.ncbi.nlm.nih.gov/pubmed/32796607
https://www.proquest.com/docview/2434420211
https://www.proquest.com/docview/2434476227
https://pubmed.ncbi.nlm.nih.gov/PMC7474427
https://doaj.org/article/f7a79e69d26243659337a28e5994f3aa
Volume 20
WOSCitedRecordID wos000564803800001&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: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 1424-8220
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0023338
  issn: 1424-8220
  databaseCode: DOA
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 1424-8220
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0023338
  issn: 1424-8220
  databaseCode: M~E
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
– providerCode: PRVPQU
  databaseName: Health & Medical Collection (ProQuest)
  customDbUrl:
  eissn: 1424-8220
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0023338
  issn: 1424-8220
  databaseCode: 7X7
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/healthcomplete
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 1424-8220
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0023338
  issn: 1424-8220
  databaseCode: BENPR
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Publicly Available Content Database
  customDbUrl:
  eissn: 1424-8220
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0023338
  issn: 1424-8220
  databaseCode: PIMPY
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/publiccontent
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lj9MwEB6xXQ5w4P0oLFVAHLhE29hOXJ_QFrraPbSqeEiFS-T4USqxydIH0l747cwkbmjRiguXKLJHyUhje-Yb298AvE6oypu2aTywqYgFsy4uvGMxF8pz38-My3xdbEJOJoPZTE1Dwm0VjlVu18R6obaVoRz5MRNcCETqSfL28kdMVaNodzWU0DiAQ2IqEx04HI4m0w8t5OKIwBo-IY7g_njFiFFKUOHkHS9Uk_VfF2H-fVByx_Oc3v1fne_BnRBzRifNILkPN1z5AG7vMBE-hK_v9VpHJ5v5RbiLVEYYzUbjCiF5dH5BRBdX0cfFnL5T19GkE0aN3BD9oI3wRUdnV3T_KyLCD5SbNCfMH8Hn09Gnd2dxKLsQG8TKa7KaIiIulRTaaeYyK72XmfPY6L2wRvcLZaQuhO0XhXJSW1NIi5GO76Nz4_wxdMqqdE8hSr3xTljudIFhRKYx2Cy8tgjB0syk0nXhzdYMuQmc5FQa43uO2IQslrcW68KrVvSyIeK4TmhItmwFiDu7bqiW8zxMxdxLLZXLlGUZGihLUWOp2cClSgnPte7C0daaeZjQq_yPKbvwsu3GqUj7K7p01SbIoHNhsgtPmoHTasKZJB5U7JF7Q2pP1f2ecvGtpvtGwIe_ls_-rdZzuMUoFUBsvckRdNbLjXsBN83P9WK17MGBnMn6OeiFOdKr0w_4HP8aYdv0fDz98ht9ZCAA
linkProvider ProQuest
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9NAEB5VKRJw4P0wFDAIJC5W7fXamz0g1FKqRG2iSBSpcDFr726IRO2SOKD8KX4jM36RoIpbD1wiyztyJvHneax3vw_gZUAqb0pHXl9H3ONMGy-1hnkhlza0fpyZ2FZiE2I87p-eyskW_Gr3wtCyyjYmVoFaFxnNke8yHnKOnXoQvD3_7pFqFL1dbSU0algcmdVPbNkWb4YHeH9fMXb4_uTdwGtUBbwMW8GSnJLEMyWDVBnFTKyFtSI2Fk9ay3Wm_FRmQqVc-2kqjVA6S4XGRG59jN00AYohfxudifo92J4MR5NPXYsXYsdX8xeFofR3F4wYrDgJNa9lvUoc4KKK9u-FmWuZ7vDm__Yf3YIbTU3t7tUPwW3YMvkduL7GtHgXPh-oUrl7y-lZs9cqd7Fad0dFiZ_DMyLyWLkfZlO6TqUTSiuoart9zPPaxQPlDla0v80lQhO0G9cr6O_Bx0v5cfehlxe5eQhuZDNruA6NSrFMihUW06lVGlvMKM4iYRx43d72JGs410n641uCvRchJOkQ4sCLzvS8Jhq5yGifsNMZEDd4daKYT5Mm1CRWKCFNLDWLERBxhB4LxfomkpLbUCkHdlr0JE3AWiR_oOPA824YQw29P1K5KZaNDSZPJhx4UAO18yRkgnhecURsQHjD1c2RfPa1ojPHhha_Wjz6t1vP4OrgZHScHA_HR4_hGqNpD2ImDnagV86X5glcyX6Us8X8afNMuvDlsiH-GxlBesc
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9NAEF5VLUJw4A01FFgQSFys2Ou1N3tAqCVEjUqjSIBUuJj1PkKk1i6JA8pf49cx4xcJqrj1wMWyvCNrbH87j_XsN4S8CLHLmzKx3zcx9zkz1s-cZX7EpYtckGibuKrZhBiP-ycncrJFfrV7YbCssrWJlaE2hcY18h7jEeeQqYdhzzVlEZPB8M35dx87SOGf1radRg2RI7v6Cenb4vVoAN_6JWPDdx_fHvpNhwFfQ1pYooISOadkmCmrmE2McE4k1sFF57jRKsikFirjJsgyaYUyOhMGnLoLwI7jYiiY_x0IyTnMsZ3J6HjyuUv3Isj-ai6jKJJBb8GQzYpj0-Y1D1g1Crgouv27SHPN6w1v_s_v6xa50cTadL-eHLfJls3vkOtrDIx3yZeBKhXdX07Pmj1YOYUonh4XJRxHZ0jwsaIfZlO8T9U_FCurarkD8P-Gwomihyvc90aR6ATkxnVl_T3y6VIe7j7Zzovc7hIaO-0sN5FVGYRPiYIgO3PKQOoZJzoW1iOvWgikuuFix5YgpynkZIiWtEOLR553ouc1AclFQgeIo04AOcOrC8V8mjYmKHVCCWkTaVgC4Ehi0Fgo1rexlNxFSnlkr0VS2hiyRfoHRh551g2DCcL_Siq3xbKRAafKhEce1KDtNImYQP5XGBEbcN5QdXMkn32raM5xVnEmHv5brafkKuA6fT8aHz0i1xiuhiBhcbhHtsv50j4mV_SPcraYP2mmJyVfLxvhvwGktIOH
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=Data+Augmentation+for+Motor+Imagery+Signal+Classification+Based+on+a+Hybrid+Neural+Network&rft.jtitle=Sensors+%28Basel%2C+Switzerland%29&rft.au=Zhang%2C+Kai&rft.au=Xu%2C+Guanghua&rft.au=Han%2C+Zezhen&rft.au=Ma%2C+Kaiquan&rft.date=2020-08-11&rft.eissn=1424-8220&rft.volume=20&rft.issue=16&rft_id=info:doi/10.3390%2Fs20164485&rft_id=info%3Apmid%2F32796607&rft.externalDocID=32796607
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1424-8220&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1424-8220&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1424-8220&client=summon