Golden subject is everyone: A subject transfer neural network for motor imagery-based brain computer interfaces
Electroencephalographic measurement of cortical activity subserving motor behavior varies among different individuals, restricting the potential of brain computer interfaces (BCIs) based on motor imagery (MI). How to deal with this variability and thereby improve the accuracy of BCI classification r...
Saved in:
| Published in | Neural networks Vol. 151; pp. 111 - 120 |
|---|---|
| Main Authors | , , , |
| Format | Journal Article |
| Language | English |
| Published |
United States
Elsevier Ltd
01.07.2022
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | Electroencephalographic measurement of cortical activity subserving motor behavior varies among different individuals, restricting the potential of brain computer interfaces (BCIs) based on motor imagery (MI). How to deal with this variability and thereby improve the accuracy of BCI classification remains a key issue. This paper proposes a deep learning-based approach to transfer the data distribution from BCI-friendly — “golden subjects” to the data from more typical BCI-illiterate users. In this work, we use the perceptual loss to align the dimensionality-reduced BCI-illiterate data with the data of golden subjects in low dimensions, by which a subject transfer neural network (STNN) is proposed. The network consists of two parts: 1) a generator, which generates the transferred BCI-illiterate features, and 2) a CNN classifier, which is used for the classification of the transferred features, thus outperforming traditional classification methods both in terms of accuracy and robustness. Electroencephalography (EEG) signals from 25 healthy subjects performing MI of the right hand and foot were classified with an average accuracy of 88.2%±5.1%. The proposed model was further validated on the BCI Competition IV dataset 2b, and was demonstrated to be robust to inter-subject variations. The advantages of STNN allow it to bridge the gap between the golden subjects and the BCI-illiterate ones, paving the way to real-time BCI applications. |
|---|---|
| AbstractList | Electroencephalographic measurement of cortical activity subserving motor behavior varies among different individuals, restricting the potential of brain computer interfaces (BCIs) based on motor imagery (MI). How to deal with this variability and thereby improve the accuracy of BCI classification remains a key issue. This paper proposes a deep learning-based approach to transfer the data distribution from BCI-friendly — “golden subjects” to the data from more typical BCI-illiterate users. In this work, we use the perceptual loss to align the dimensionality-reduced BCI-illiterate data with the data of golden subjects in low dimensions, by which a subject transfer neural network (STNN) is proposed. The network consists of two parts: 1) a generator, which generates the transferred BCI-illiterate features, and 2) a CNN classifier, which is used for the classification of the transferred features, thus outperforming traditional classification methods both in terms of accuracy and robustness. Electroencephalography (EEG) signals from 25 healthy subjects performing MI of the right hand and foot were classified with an average accuracy of 88.2%±5.1%. The proposed model was further validated on the BCI Competition IV dataset 2b, and was demonstrated to be robust to inter-subject variations. The advantages of STNN allow it to bridge the gap between the golden subjects and the BCI-illiterate ones, paving the way to real-time BCI applications. Electroencephalographic measurement of cortical activity subserving motor behavior varies among different individuals, restricting the potential of brain computer interfaces (BCIs) based on motor imagery (MI). How to deal with this variability and thereby improve the accuracy of BCI classification remains a key issue. This paper proposes a deep learning-based approach to transfer the data distribution from BCI-friendly - "golden subjects" to the data from more typical BCI-illiterate users. In this work, we use the perceptual loss to align the dimensionality-reduced BCI-illiterate data with the data of golden subjects in low dimensions, by which a subject transfer neural network (STNN) is proposed. The network consists of two parts: 1) a generator, which generates the transferred BCI-illiterate features, and 2) a CNN classifier, which is used for the classification of the transferred features, thus outperforming traditional classification methods both in terms of accuracy and robustness. Electroencephalography (EEG) signals from 25 healthy subjects performing MI of the right hand and foot were classified with an average accuracy of 88.2%±5.1%. The proposed model was further validated on the BCI Competition IV dataset 2b, and was demonstrated to be robust to inter-subject variations. The advantages of STNN allow it to bridge the gap between the golden subjects and the BCI-illiterate ones, paving the way to real-time BCI applications.Electroencephalographic measurement of cortical activity subserving motor behavior varies among different individuals, restricting the potential of brain computer interfaces (BCIs) based on motor imagery (MI). How to deal with this variability and thereby improve the accuracy of BCI classification remains a key issue. This paper proposes a deep learning-based approach to transfer the data distribution from BCI-friendly - "golden subjects" to the data from more typical BCI-illiterate users. In this work, we use the perceptual loss to align the dimensionality-reduced BCI-illiterate data with the data of golden subjects in low dimensions, by which a subject transfer neural network (STNN) is proposed. The network consists of two parts: 1) a generator, which generates the transferred BCI-illiterate features, and 2) a CNN classifier, which is used for the classification of the transferred features, thus outperforming traditional classification methods both in terms of accuracy and robustness. Electroencephalography (EEG) signals from 25 healthy subjects performing MI of the right hand and foot were classified with an average accuracy of 88.2%±5.1%. The proposed model was further validated on the BCI Competition IV dataset 2b, and was demonstrated to be robust to inter-subject variations. The advantages of STNN allow it to bridge the gap between the golden subjects and the BCI-illiterate ones, paving the way to real-time BCI applications. |
| Author | Hu, Yong Li, Ting Sun, Biao Wu, Zexu |
| Author_xml | – sequence: 1 givenname: Biao orcidid: 0000-0002-4124-9350 surname: Sun fullname: Sun, Biao organization: School of Electrical and Information Engineering, Tianjin University, Tianjin, 300072, China – sequence: 2 givenname: Zexu orcidid: 0000-0001-7609-9762 surname: Wu fullname: Wu, Zexu organization: School of Electrical and Information Engineering, Tianjin University, Tianjin, 300072, China – sequence: 3 givenname: Yong surname: Hu fullname: Hu, Yong organization: Department of Orthopaedics and Traumatology, The University of Hong Kong, 999077, Hong Kong Special Administrative Region of China – sequence: 4 givenname: Ting surname: Li fullname: Li, Ting email: t.li619@foxmail.com organization: Institute of Biomedical Engineering, Chinese Academy of Medical Sciences & Peking Union Medical College, Tianjin, 300192, China |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/35405471$$D View this record in MEDLINE/PubMed |
| BookMark | eNqFkU9rFTEUxYNU7Gv1G4hk6Wam-TfJTBdCKVqFQje6DpnkRvKcSZ5JptJvb8prXbhQCPdCOL97ueecoZOYIiD0lpKeEiov9n2ELULtGWGsJ7wnbHiBdnRUU8fUyE7QjowT7yQZySk6K2VPCJGj4K_QKR8EGYSiO5Ru0uIg4rLNe7AVh4LhHvJD23WJr_5812xi8ZBx25nN0lr9lfIP7FPGa6qthtV8b1w3mwIOz9mEiG1aD1ttVIitemOhvEYvvVkKvHnq5-jbp49frz93t3c3X66vbjvLJasdeAKzZ9YowrkdvBITFVwCtVIZBkzOniqn2huVm7jyoxPMKe8HLodJGn6O3h_nHnL6uUGpeg3FwrKYCGkrmkkxDRMXQjXpuyfpNq_g9CG3W_KDfjapCS6PAptTKRm8tqGaGlJstoRFU6IfE9F7fUxEPyaiCdctkQaLv-Dn-f_BPhwxaCbdB8i62ADRggu5BaJdCv8e8BtZYqkY |
| CitedBy_id | crossref_primary_10_1016_j_engappai_2023_106863 crossref_primary_10_1016_j_bspc_2023_105621 crossref_primary_10_3389_fnins_2023_1303648 crossref_primary_10_1016_j_bspc_2023_104693 crossref_primary_10_3390_electronics12030604 crossref_primary_10_1364_BOE_487456 crossref_primary_10_3389_fnins_2023_1274320 crossref_primary_10_1111_ina_13062 crossref_primary_10_1088_1741_2552_ad0c61 crossref_primary_10_1080_27706710_2023_2285052 crossref_primary_10_1016_j_engappai_2022_105347 crossref_primary_10_3390_s24010077 crossref_primary_10_1364_BOE_504669 crossref_primary_10_1016_j_irbm_2024_100836 crossref_primary_10_3389_fbioe_2023_917328 crossref_primary_10_1109_ACCESS_2023_3346674 crossref_primary_10_3389_fnhum_2023_1194751 crossref_primary_10_1016_j_bspc_2023_105154 crossref_primary_10_3390_s24051678 crossref_primary_10_3390_s23136210 crossref_primary_10_1109_ACCESS_2023_3299497 crossref_primary_10_1016_j_neucom_2024_128577 crossref_primary_10_1016_j_bbe_2024_11_003 crossref_primary_10_1016_j_compbiomed_2022_106220 crossref_primary_10_1371_journal_pone_0313261 crossref_primary_10_1109_TNSRE_2023_3243257 crossref_primary_10_1007_s13246_023_01316_6 crossref_primary_10_1038_s41598_024_79202_8 |
| Cites_doi | 10.1109/TNSRE.2016.2601240 10.1126/scirobotics.aaw6844 10.1049/htl.2016.0073 10.1137/0515056 10.1371/journal.pone.0207351 10.1016/0028-3932(95)00073-C 10.1016/S0013-4694(97)88021-6 10.1007/s10548-009-0121-6 10.1037/0735-7028.24.2.190 10.4236/jbbs.2019.93006 10.1109/MCI.2015.2501545 10.1016/j.jphysparis.2006.03.012 10.1088/1741-2552/aace8c 10.1109/CVPR.2017.195 10.1016/j.neuron.2018.01.040 10.1088/1741-2552/aaf3f6 10.1088/1741-2560/12/6/066024 10.1016/j.neunet.2009.06.003 10.1007/s10916-019-1270-0 10.1016/j.neuropsychologia.2017.02.005 10.1109/CVPR.2016.265 10.1109/5.488704 10.1016/j.neunet.2020.01.017 10.1155/2017/4653256 10.1016/j.biopsycho.2011.09.006 10.1109/86.847819 10.1109/LSP.2021.3049683 10.1016/j.jneumeth.2015.01.033 10.1109/CVPR.2015.7298965 10.3389/fnsys.2013.00031 10.1073/pnas.1817207116 10.1111/cts.12086 10.1523/JNEUROSCI.2912-18.2019 10.1016/j.compbiomed.2019.02.023 10.1016/j.neuroimage.2015.04.020 10.1038/18581 10.1109/TASE.2020.3021456 10.1113/jphysiol.2006.123067 10.1109/TBME.2004.827062 10.1016/j.neuroimage.2019.07.003 10.1016/j.neuroimage.2010.03.022 10.1109/JBHI.2018.2832538 10.1016/j.jneumeth.2009.04.006 10.1109/TBME.2010.2082539 10.3389/fncom.2019.00087 10.1109/JPROC.2020.2976475 10.1016/j.eswa.2018.08.031 10.1088/1741-2560/14/1/016003 10.1088/1741-2560/13/2/026024 |
| ContentType | Journal Article |
| Copyright | 2022 Elsevier Ltd Copyright © 2022 Elsevier Ltd. All rights reserved. |
| Copyright_xml | – notice: 2022 Elsevier Ltd – notice: Copyright © 2022 Elsevier Ltd. All rights reserved. |
| DBID | AAYXX CITATION NPM 7X8 |
| DOI | 10.1016/j.neunet.2022.03.025 |
| DatabaseName | CrossRef PubMed MEDLINE - Academic |
| DatabaseTitle | CrossRef PubMed MEDLINE - Academic |
| DatabaseTitleList | PubMed MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1879-2782 |
| EndPage | 120 |
| ExternalDocumentID | 35405471 10_1016_j_neunet_2022_03_025 S0893608022001034 |
| Genre | Journal Article |
| GroupedDBID | --- --K --M -~X .DC .~1 0R~ 123 186 1B1 1RT 1~. 1~5 29N 4.4 457 4G. 53G 5RE 5VS 6TJ 7-5 71M 8P~ 9JM 9JN AABNK AACTN AADPK AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXLA AAXUO AAYFN ABAOU ABBOA ABCQJ ABEFU ABFNM ABFRF ABHFT ABIVO ABJNI ABLJU ABMAC ABXDB ABYKQ ACAZW ACDAQ ACGFO ACGFS ACIUM ACNNM ACRLP ACZNC ADBBV ADEZE ADGUI ADJOM ADMUD ADRHT AEBSH AECPX AEFWE AEKER AENEX AFKWA AFTJW AFXIZ AGHFR AGUBO AGWIK AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ARUGR ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F0J F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q G8K GBLVA GBOLZ HLZ HMQ HVGLF HZ~ IHE J1W JJJVA K-O KOM KZ1 LG9 LMP M2V M41 MHUIS MO0 MOBAO MVM N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SBC SCC SDF SDG SDP SES SEW SNS SPC SPCBC SSN SST SSV SSW SSZ T5K TAE UAP UNMZH VOH WUQ XPP ZMT ~G- AATTM AAXKI AAYWO AAYXX ABDPE ABWVN ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGCQF AGQPQ AGRNS AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP BNPGV CITATION SSH EFKBS NPM 7X8 |
| ID | FETCH-LOGICAL-c362t-ef0ebf2ca7033c5f7491436e1c67a2e26bf17d77d787d937f8d42d7ff536596a3 |
| IEDL.DBID | .~1 |
| ISSN | 0893-6080 1879-2782 |
| IngestDate | Fri Jul 11 01:12:04 EDT 2025 Mon Jul 21 06:00:19 EDT 2025 Tue Jul 01 01:24:40 EDT 2025 Thu Apr 24 22:56:07 EDT 2025 Fri Feb 23 02:39:50 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | BCI-illiterate Motor imagery (MI) Brain computer interfaces (BCIs) Convolutional neural network (CNN) Golden subject |
| Language | English |
| License | Copyright © 2022 Elsevier Ltd. All rights reserved. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c362t-ef0ebf2ca7033c5f7491436e1c67a2e26bf17d77d787d937f8d42d7ff536596a3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0002-4124-9350 0000-0001-7609-9762 |
| PMID | 35405471 |
| PQID | 2649593447 |
| PQPubID | 23479 |
| PageCount | 10 |
| ParticipantIDs | proquest_miscellaneous_2649593447 pubmed_primary_35405471 crossref_citationtrail_10_1016_j_neunet_2022_03_025 crossref_primary_10_1016_j_neunet_2022_03_025 elsevier_sciencedirect_doi_10_1016_j_neunet_2022_03_025 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | July 2022 2022-07-00 2022-Jul 20220701 |
| PublicationDateYYYYMMDD | 2022-07-01 |
| PublicationDate_xml | – month: 07 year: 2022 text: July 2022 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | Neural networks |
| PublicationTitleAlternate | Neural Netw |
| PublicationYear | 2022 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Šťastný, Sovka, Kostilek (b52) 2014; 23 Betzel, Bertolero, Gordon, Gratton, Dosenbach, Bassett (b3) 2019; 202 Wierzbicki, Pekarik (b64) 1993; 24 Ahn, Jun (b1) 2015; 243 Faller, Cummings, Saproo, Sajda (b15) 2019; 116 Fu, Tian, Bao, Meng, Shi (b18) 2019; 43 Blankertz, Sannelli, Halder, Hammer, Kübler, Müller (b6) 2010; 51 Gatys, L. A., Ecker, A. S., & Bethge, M. (2016). Image style transfer using convolutional neural networks. In Han, Gu, Lo (b23) 2021 Collinger, Kryger, Barbara, Betler, Bowsher, Brown (b9) 2014; 7 Hammer, Halder, Blankertz, Sannelli, Dickhaus, Kleih (b22) 2012; 89 Lotte, Guan (b35) 2010; 58 Dose, Møller, Iversen, Puthusserypady (b12) 2018; 114 Birbaumer, Ghanayim, Hinterberger, Iversen, Kotchoubey, Kübler (b4) 1999; 398 Deng, Li, Han, Shi, Xie (b10) 2020; 108 Lotze, Halsband (b36) 2006; 99 Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In Jayaram, Alamgir, Altun, Scholkopf, Grosse-Wentrup (b26) 2016; 11 Ketkar (b30) 2017 Sitnikova, Hramov, Koronovsky, van Luijtelaar (b50) 2009; 180 Edelman, Meng, Suma, Zurn, Nagarajan, Baxter (b13) 2019; 4 Grossmann, Morlet (b21) 1984; 15 Vasilyev, Liburkina, Yakovlev, Perepelkina, Kaplan (b60) 2017; 97 Schlögl (b49) 2003 Vidaurre, Blankertz (b61) 2010; 23 (pp. 3431–3440). Hramov, Koronovskii, Makarov, Pavlov, Sitnikova (b24) 2015 Oikonomou, Nikolopoulos, Petrantonakis, Kompatsiaris (b40) 2018 Saha, Baumert (b46) 2019; 13 Scherer, Muller, Neuper, Graimann, Pfurtscheller (b48) 2004; 51 Fahimi, Zhang, Goh, Lee, Ang, Guan (b14) 2019; 16 Kingma, Ba (b31) 2014 (pp. 1251–1258). Smith, Duff, Groves, Nichols, Jbabdi, Westlye (b51) 2019; 39 Sun, Mu, Wu, Zhu (b53) 2021 Radford, Metz, Chintala (b42) 2015 Johnson, Alahi, Fei-Fei (b29) 2016 Sannelli, Vidaurre, Müller, Blankertz (b47) 2019; 14 Yumatov, Hramov, Grubov, Glazachev, Dudnik, Karatygin (b65) 2019; 9 Unser, Aldroubi (b59) 1996; 84 Dobkin (b11) 2007; 579 Zhang, Yao, Valdés-Sosa, Li, Li, Zhang (b67) 2015; 12 Wang, Collinger, Perez, Tyler-Kabara, Cohen, Birbaumer (b63) 2010; 21 Tabar, Halici (b56) 2016; 14 Zhang, Goodfellow, Metaxas, Odena (b66) 2019 Fazli, Grozea, Danóczy, Blankertz, Popescu, Müller (b16) 2009 Pfurtscheller (b41) 1997; 1 Zhang, Zhao, Wu, Sun, Li (b69) 2021; 18 Zhang, Zhang, Sun, Fan, Zhong (b68) 2019; 107 Lawhern, Solon, Waytowich, Gordon, Hung, Lance (b32) 2018; 15 Lu, Li, Ren, Miao (b37) 2016; 25 Middendorf, McMillan, Calhoun, Jones (b38) 2000; 8 Tan, Sun, Zhang (b57) 2018 Blankertz, Sanelli, Halder, Hammer, Kübler, Müller (b5) 2009; 10 Sun, Zhao, Zhang, Bai, Li (b55) 2020; 18 Goswami, Chan (b20) 2011 Liu, Breuel, Kautz (b33) 2017 Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In Raghu, Sriraam, Temel, Rao, Kubben (b43) 2020; 124 (pp. 2414–2423). Vyas, Even-Chen, Stavisky, Ryu, Nuyujukian, Shenoy (b62) 2018; 97 Braun, Kranczioch, Liepert, Dettmers, Zich, Büsching (b7) 2017; 2017 Fazli, Popescu, Danóczy, Blankertz, Müller, Grozea (b17) 2009; 22 Jiao, Zhang, Chen, Yin, Jin, Wang (b28) 2018; 23 Ang, Chin, Zhang, Guan (b2) 2008 Zich, Debener, Kranczioch, Bleichner, Gutberlet, De Vos (b70) 2015; 114 Nijboer, Birbaumer, Kubler (b39) 2010; 4 Townsend, Platsko (b58) 2016; 13 Rönnberg, Lunner, Zekveld, Sörqvist, Danielsson, Lyxell (b44) 2013; 7 Jeannerod (b27) 1995; 33 Saha, Ahmed, Mostafa, Khandoker, Hadjileontiadis (b45) 2017; 4 Sun, Zhang, Wu, Zhang, Li (b54) 2021; 28 Ioffe, Szegedy (b25) 2015 Lotte (10.1016/j.neunet.2022.03.025_b35) 2010; 58 Tabar (10.1016/j.neunet.2022.03.025_b56) 2016; 14 Sitnikova (10.1016/j.neunet.2022.03.025_b50) 2009; 180 Dose (10.1016/j.neunet.2022.03.025_b12) 2018; 114 Jiao (10.1016/j.neunet.2022.03.025_b28) 2018; 23 Ang (10.1016/j.neunet.2022.03.025_b2) 2008 Pfurtscheller (10.1016/j.neunet.2022.03.025_b41) 1997; 1 Fazli (10.1016/j.neunet.2022.03.025_b16) 2009 Lotze (10.1016/j.neunet.2022.03.025_b36) 2006; 99 Grossmann (10.1016/j.neunet.2022.03.025_b21) 1984; 15 Zhang (10.1016/j.neunet.2022.03.025_b69) 2021; 18 Oikonomou (10.1016/j.neunet.2022.03.025_b40) 2018 Fahimi (10.1016/j.neunet.2022.03.025_b14) 2019; 16 10.1016/j.neunet.2022.03.025_b19 Kingma (10.1016/j.neunet.2022.03.025_b31) 2014 Sannelli (10.1016/j.neunet.2022.03.025_b47) 2019; 14 Townsend (10.1016/j.neunet.2022.03.025_b58) 2016; 13 Blankertz (10.1016/j.neunet.2022.03.025_b6) 2010; 51 Sun (10.1016/j.neunet.2022.03.025_b54) 2021; 28 Blankertz (10.1016/j.neunet.2022.03.025_b5) 2009; 10 Wang (10.1016/j.neunet.2022.03.025_b63) 2010; 21 Ahn (10.1016/j.neunet.2022.03.025_b1) 2015; 243 Johnson (10.1016/j.neunet.2022.03.025_b29) 2016 Betzel (10.1016/j.neunet.2022.03.025_b3) 2019; 202 Sun (10.1016/j.neunet.2022.03.025_b55) 2020; 18 Vasilyev (10.1016/j.neunet.2022.03.025_b60) 2017; 97 Birbaumer (10.1016/j.neunet.2022.03.025_b4) 1999; 398 Zhang (10.1016/j.neunet.2022.03.025_b66) 2019 Vyas (10.1016/j.neunet.2022.03.025_b62) 2018; 97 Lawhern (10.1016/j.neunet.2022.03.025_b32) 2018; 15 Tan (10.1016/j.neunet.2022.03.025_b57) 2018 10.1016/j.neunet.2022.03.025_b8 Deng (10.1016/j.neunet.2022.03.025_b10) 2020; 108 Lu (10.1016/j.neunet.2022.03.025_b37) 2016; 25 Ioffe (10.1016/j.neunet.2022.03.025_b25) 2015 Scherer (10.1016/j.neunet.2022.03.025_b48) 2004; 51 10.1016/j.neunet.2022.03.025_b34 Rönnberg (10.1016/j.neunet.2022.03.025_b44) 2013; 7 Dobkin (10.1016/j.neunet.2022.03.025_b11) 2007; 579 Radford (10.1016/j.neunet.2022.03.025_b42) 2015 Šťastný (10.1016/j.neunet.2022.03.025_b52) 2014; 23 Unser (10.1016/j.neunet.2022.03.025_b59) 1996; 84 Fu (10.1016/j.neunet.2022.03.025_b18) 2019; 43 Braun (10.1016/j.neunet.2022.03.025_b7) 2017; 2017 Jayaram (10.1016/j.neunet.2022.03.025_b26) 2016; 11 Saha (10.1016/j.neunet.2022.03.025_b45) 2017; 4 Liu (10.1016/j.neunet.2022.03.025_b33) 2017 Raghu (10.1016/j.neunet.2022.03.025_b43) 2020; 124 Vidaurre (10.1016/j.neunet.2022.03.025_b61) 2010; 23 Collinger (10.1016/j.neunet.2022.03.025_b9) 2014; 7 Han (10.1016/j.neunet.2022.03.025_b23) 2021 Hammer (10.1016/j.neunet.2022.03.025_b22) 2012; 89 Jeannerod (10.1016/j.neunet.2022.03.025_b27) 1995; 33 Zich (10.1016/j.neunet.2022.03.025_b70) 2015; 114 Wierzbicki (10.1016/j.neunet.2022.03.025_b64) 1993; 24 Smith (10.1016/j.neunet.2022.03.025_b51) 2019; 39 Yumatov (10.1016/j.neunet.2022.03.025_b65) 2019; 9 Fazli (10.1016/j.neunet.2022.03.025_b17) 2009; 22 Nijboer (10.1016/j.neunet.2022.03.025_b39) 2010; 4 Sun (10.1016/j.neunet.2022.03.025_b53) 2021 Edelman (10.1016/j.neunet.2022.03.025_b13) 2019; 4 Zhang (10.1016/j.neunet.2022.03.025_b67) 2015; 12 Middendorf (10.1016/j.neunet.2022.03.025_b38) 2000; 8 Saha (10.1016/j.neunet.2022.03.025_b46) 2019; 13 Ketkar (10.1016/j.neunet.2022.03.025_b30) 2017 Zhang (10.1016/j.neunet.2022.03.025_b68) 2019; 107 Schlögl (10.1016/j.neunet.2022.03.025_b49) 2003 Goswami (10.1016/j.neunet.2022.03.025_b20) 2011 Hramov (10.1016/j.neunet.2022.03.025_b24) 2015 Faller (10.1016/j.neunet.2022.03.025_b15) 2019; 116 |
| References_xml | – volume: 7 start-page: 52 year: 2014 end-page: 59 ident: b9 article-title: Collaborative approach in the development of High-Performance Brain–Computer interfaces for a neuroprosthetic arm: Translation from animal models to human control publication-title: Clinical and Translational Science – volume: 14 year: 2016 ident: b56 article-title: A novel deep learning approach for classification of EEG motor imagery signals publication-title: Journal of Neural Engineering – volume: 84 start-page: 626 year: 1996 end-page: 638 ident: b59 article-title: A review of wavelets in biomedical applications publication-title: Proceedings of the IEEE – reference: Gatys, L. A., Ecker, A. S., & Bethge, M. (2016). Image style transfer using convolutional neural networks. In – start-page: 700 year: 2017 end-page: 708 ident: b33 article-title: Unsupervised image-to-image translation networks publication-title: Advances in neural information processing systems – volume: 25 start-page: 566 year: 2016 end-page: 576 ident: b37 article-title: A deep learning scheme for motor imagery classification based on restricted Boltzmann machines publication-title: IEEE Transactions on Neural Systems and Rehabilitation Engineering – volume: 14 year: 2019 ident: b47 article-title: A large scale screening study with a SMR-based BCI: Categorization of BCI users and differences in their SMR activity publication-title: PLoS One – volume: 51 start-page: 1303 year: 2010 end-page: 1309 ident: b6 article-title: Neurophysiological predictor of SMR-based BCI performance publication-title: Neuroimage – start-page: 513 year: 2009 end-page: 521 ident: b16 article-title: Subject independent EEG-based BCI decoding publication-title: Advances in neural information processing systems – year: 2015 ident: b42 article-title: Unsupervised representation learning with deep convolutional generative adversarial networks – start-page: 1 year: 2021 end-page: 4 ident: b23 article-title: Semi-supervised contrastive learning for generalizable motor imagery EEG classification publication-title: 2021 IEEE 17th international conference on wearable and implantable body sensor networks (BSN) – volume: 21 start-page: 157 year: 2010 end-page: 178 ident: b63 article-title: Neural interface technology for rehabilitation: exploiting and promoting neuroplasticity publication-title: Physical Medicine and Rehabilitation Clinics – reference: Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In – year: 2014 ident: b31 article-title: Adam: A method for stochastic optimization – start-page: 207 year: 2018 end-page: 210 ident: b40 article-title: Sparse kernel machines for motor imagery eeg classification publication-title: 2018 40th annual international conference of the IEEE engineering in medicine and biology society (EMBC) – volume: 10 start-page: P84 year: 2009 ident: b5 article-title: Predicting BCI performance to study BCI illiteracy publication-title: BMC Neuroscience – volume: 15 year: 2018 ident: b32 article-title: EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces publication-title: Journal of Neural Engineering – volume: 23 start-page: 194 year: 2010 end-page: 198 ident: b61 article-title: Towards a cure for BCI illiteracy publication-title: Brain Topography – volume: 97 start-page: 56 year: 2017 end-page: 65 ident: b60 article-title: Assessing motor imagery in brain-computer interface training: psychological and neurophysiological correlates publication-title: Neuropsychologia – volume: 108 start-page: 485 year: 2020 end-page: 532 ident: b10 article-title: Model compression and hardware acceleration for neural networks: A comprehensive survey publication-title: Proceedings of the IEEE – volume: 22 start-page: 1305 year: 2009 end-page: 1312 ident: b17 article-title: Subject-independent mental state classification in single trials publication-title: Neural Networks – volume: 4 start-page: 55 year: 2010 ident: b39 article-title: The influence of psychological state and motivation on brain–computer interface performance in patients with amyotrophic lateral sclerosis–a longitudinal study publication-title: Frontiers in Neuroscience – volume: 243 start-page: 103 year: 2015 end-page: 110 ident: b1 article-title: Performance variation in motor imagery brain–computer interface: a brief review publication-title: Journal of Neuroscience Methods – volume: 114 start-page: 532 year: 2018 end-page: 542 ident: b12 article-title: An end-to-end deep learning approach to MI-EEG signal classification for BCIs publication-title: Expert Systems with Applications – volume: 116 start-page: 6482 year: 2019 end-page: 6490 ident: b15 article-title: Regulation of arousal via online neurofeedback improves human performance in a demanding sensory-motor task publication-title: Proceedings of the National Academy of Sciences – volume: 97 start-page: 1177 year: 2018 end-page: 1186 ident: b62 article-title: Neural population dynamics underlying motor learning transfer publication-title: Neuron – volume: 2017 year: 2017 ident: b7 article-title: Motor imagery impairment in postacute stroke patients publication-title: Neural Plasticity – volume: 4 start-page: 39 year: 2017 end-page: 43 ident: b45 article-title: Enhanced inter-subject brain computer interface with associative sensorimotor oscillations publication-title: Healthcare Technology Letters – volume: 28 start-page: 219 year: 2021 end-page: 223 ident: b54 article-title: Adaptive spatiotemporal graph convolutional networks for motor imagery classification publication-title: IEEE Signal Processing Letters – volume: 18 start-page: 541 year: 2020 end-page: 551 ident: b55 article-title: Eeg motor imagery classification with sparse spectrotemporal decomposition and deep learning publication-title: IEEE Transactions on Automation Science and Engineering – start-page: 7354 year: 2019 end-page: 7363 ident: b66 article-title: Self-attention generative adversarial networks publication-title: International conference on machine learning – start-page: 195 year: 2017 end-page: 208 ident: b30 article-title: Introduction to pytorch publication-title: Deep learning with Python – year: 2015 ident: b25 article-title: Batch normalization: Accelerating deep network training by reducing internal covariate shift – volume: 107 start-page: 248 year: 2019 end-page: 256 ident: b68 article-title: Portable brain-computer interface based on novel convolutional neural network publication-title: Computers in Biology and Medicine – start-page: 916 year: 2018 end-page: 920 ident: b57 article-title: Deep transfer learning for EEG-based brain computer interface publication-title: 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP) – volume: 39 start-page: 6136 year: 2019 end-page: 6149 ident: b51 article-title: Structural variability in the human brain reflects fine-grained functional architecture at the population level publication-title: Journal of Neuroscience – volume: 4 year: 2019 ident: b13 article-title: Noninvasive neuroimaging enhances continuous neural tracking for robotic device control publication-title: Science Robotics – volume: 23 start-page: 631 year: 2018 end-page: 641 ident: b28 article-title: Sparse group representation model for motor imagery EEG classification publication-title: IEEE Journal of Biomedical and Health Informatics – volume: 51 start-page: 979 year: 2004 end-page: 984 ident: b48 article-title: An asynchronously controlled EEG-based virtual keyboard: improvement of the spelling rate publication-title: IEEE Transactions on Biomedical Engineering – volume: 13 year: 2016 ident: b58 article-title: Pushing the P300-based brain–computer interface beyond 100 bpm: Extending performance guided constraints into the temporal domain publication-title: Journal of Neural Engineering – volume: 114 start-page: 438 year: 2015 end-page: 447 ident: b70 article-title: Real-time EEG feedback during simultaneous EEG–fMRI identifies the cortical signature of motor imagery publication-title: Neuroimage – year: 2015 ident: b24 article-title: Wavelets in neuroscience – start-page: 694 year: 2016 end-page: 711 ident: b29 article-title: Perceptual losses for real-time style transfer and super-resolution publication-title: European conference on computer vision – volume: 1 start-page: 26 year: 1997 ident: b41 article-title: EEG event-related desynchronization (ERD) and synchronization (ERS) publication-title: Electroencephalography and Clinical Neurophysiology – volume: 24 start-page: 190 year: 1993 ident: b64 article-title: A meta-analysis of psychotherapy dropout. publication-title: Professional Psychology: Research and Practice – volume: 18 year: 2021 ident: b69 article-title: Motor imagery recognition with automatic EEG channel selection and deep learning publication-title: Journal of Neural Engineering – volume: 579 start-page: 637 year: 2007 end-page: 642 ident: b11 article-title: Brain–computer interface technology as a tool to augment plasticity and outcomes for neurological rehabilitation publication-title: The Journal of Physiology – start-page: 2390 year: 2008 end-page: 2397 ident: b2 article-title: Filter bank common spatial pattern (FBCSP) in brain-computer interface publication-title: 2008 IEEE international joint conference on neural networks (IEEE world congress on computational intelligence) – volume: 33 start-page: 1419 year: 1995 end-page: 1432 ident: b27 article-title: Mental imagery in the motor context publication-title: Neuropsychologia – volume: 58 start-page: 355 year: 2010 end-page: 362 ident: b35 article-title: Regularizing common spatial patterns to improve BCI designs: unified theory and new algorithms publication-title: IEEE Transactions on Biomedical Engineering – volume: 7 start-page: 31 year: 2013 ident: b44 article-title: The Ease of Language Understanding (ELU) model: theoretical, empirical, and clinical advances publication-title: Frontiers in Systems Neuroscience – volume: 15 start-page: 723 year: 1984 end-page: 736 ident: b21 article-title: Decomposition of Hardy functions into square integrable wavelets of constant shape publication-title: SIAM Journal on Mathematical Analysis – volume: 11 start-page: 20 year: 2016 end-page: 31 ident: b26 article-title: Transfer learning in brain-computer interfaces publication-title: IEEE Computational Intelligence Magazine – volume: 16 year: 2019 ident: b14 article-title: Inter-subject transfer learning with an end-to-end deep convolutional neural network for EEG-based BCI publication-title: Journal of Neural Engineering – volume: 89 start-page: 80 year: 2012 end-page: 86 ident: b22 article-title: Psychological predictors of SMR-BCI performance publication-title: Biological Psychology – year: 2011 ident: b20 article-title: Fundamentals of wavelets: Theory, algorithms, and applications, Vol. 233 – volume: 124 start-page: 202 year: 2020 end-page: 212 ident: b43 article-title: EEG based multi-class seizure type classification using convolutional neural network and transfer learning publication-title: Neural Networks – volume: 9 start-page: 67 year: 2019 end-page: 77 ident: b65 article-title: Possibility for recognition of psychic brain activity with continuous wavelet analysis of EEG publication-title: Journal of Behavioral and Brain Science – volume: 12 year: 2015 ident: b67 article-title: Efficient resting-state EEG network facilitates motor imagery performance publication-title: Journal of Neural Engineering – volume: 180 start-page: 304 year: 2009 end-page: 316 ident: b50 article-title: Sleep spindles and spike–wave discharges in EEG: their generic features, similarities and distinctions disclosed with Fourier transform and continuous wavelet analysis publication-title: Journal of Neuroscience Methods – volume: 23 year: 2014 ident: b52 article-title: Overcoming inter-subject variability in BCI using EEG-based identification publication-title: Radioengineering – volume: 202 year: 2019 ident: b3 article-title: The community structure of functional brain networks exhibits scale-specific patterns of inter-and intra-subject variability publication-title: Neuroimage – volume: 43 start-page: 169 year: 2019 ident: b18 article-title: Improvement motor imagery EEG classification based on regularized linear discriminant analysis publication-title: Journal of Medical Systems – volume: 8 start-page: 211 year: 2000 end-page: 214 ident: b38 article-title: Brain-computer interfaces based on the steady-state visual-evoked response publication-title: IEEE Transactions on Rehabilitation Engineering – reference: (pp. 3431–3440). – volume: 99 start-page: 386 year: 2006 end-page: 395 ident: b36 article-title: Motor imagery publication-title: Journal de Physiologie (Paris) – reference: (pp. 1251–1258). – volume: 13 start-page: 87 year: 2019 ident: b46 article-title: Intra-and inter-subject variability in EEG-based sensorimotor brain computer interface: a review publication-title: Frontiers in Computational Neuroscience – year: 2003 ident: b49 article-title: Outcome of the BCI-competition 2003 on the Graz data set – year: 2021 ident: b53 article-title: Training-free deep generative networks for compressed sensing of neural action potentials publication-title: IEEE Transactions on Neural Networks and Learning Systems – volume: 398 start-page: 297 year: 1999 end-page: 298 ident: b4 article-title: A spelling device for the paralysed publication-title: Nature – reference: Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In – reference: (pp. 2414–2423). – year: 2011 ident: 10.1016/j.neunet.2022.03.025_b20 – volume: 25 start-page: 566 issue: 6 year: 2016 ident: 10.1016/j.neunet.2022.03.025_b37 article-title: A deep learning scheme for motor imagery classification based on restricted Boltzmann machines publication-title: IEEE Transactions on Neural Systems and Rehabilitation Engineering doi: 10.1109/TNSRE.2016.2601240 – year: 2015 ident: 10.1016/j.neunet.2022.03.025_b25 – volume: 18 issue: 1 year: 2021 ident: 10.1016/j.neunet.2022.03.025_b69 article-title: Motor imagery recognition with automatic EEG channel selection and deep learning publication-title: Journal of Neural Engineering – start-page: 2390 year: 2008 ident: 10.1016/j.neunet.2022.03.025_b2 article-title: Filter bank common spatial pattern (FBCSP) in brain-computer interface – volume: 4 issue: 31 year: 2019 ident: 10.1016/j.neunet.2022.03.025_b13 article-title: Noninvasive neuroimaging enhances continuous neural tracking for robotic device control publication-title: Science Robotics doi: 10.1126/scirobotics.aaw6844 – volume: 4 start-page: 39 issue: 1 year: 2017 ident: 10.1016/j.neunet.2022.03.025_b45 article-title: Enhanced inter-subject brain computer interface with associative sensorimotor oscillations publication-title: Healthcare Technology Letters doi: 10.1049/htl.2016.0073 – year: 2003 ident: 10.1016/j.neunet.2022.03.025_b49 – start-page: 700 year: 2017 ident: 10.1016/j.neunet.2022.03.025_b33 article-title: Unsupervised image-to-image translation networks – volume: 15 start-page: 723 issue: 4 year: 1984 ident: 10.1016/j.neunet.2022.03.025_b21 article-title: Decomposition of Hardy functions into square integrable wavelets of constant shape publication-title: SIAM Journal on Mathematical Analysis doi: 10.1137/0515056 – volume: 14 issue: 1 year: 2019 ident: 10.1016/j.neunet.2022.03.025_b47 article-title: A large scale screening study with a SMR-based BCI: Categorization of BCI users and differences in their SMR activity publication-title: PLoS One doi: 10.1371/journal.pone.0207351 – volume: 33 start-page: 1419 issue: 11 year: 1995 ident: 10.1016/j.neunet.2022.03.025_b27 article-title: Mental imagery in the motor context publication-title: Neuropsychologia doi: 10.1016/0028-3932(95)00073-C – volume: 1 start-page: 26 issue: 103 year: 1997 ident: 10.1016/j.neunet.2022.03.025_b41 article-title: EEG event-related desynchronization (ERD) and synchronization (ERS) publication-title: Electroencephalography and Clinical Neurophysiology doi: 10.1016/S0013-4694(97)88021-6 – volume: 23 start-page: 194 issue: 2 year: 2010 ident: 10.1016/j.neunet.2022.03.025_b61 article-title: Towards a cure for BCI illiteracy publication-title: Brain Topography doi: 10.1007/s10548-009-0121-6 – volume: 24 start-page: 190 issue: 2 year: 1993 ident: 10.1016/j.neunet.2022.03.025_b64 article-title: A meta-analysis of psychotherapy dropout. publication-title: Professional Psychology: Research and Practice doi: 10.1037/0735-7028.24.2.190 – volume: 9 start-page: 67 issue: 3 year: 2019 ident: 10.1016/j.neunet.2022.03.025_b65 article-title: Possibility for recognition of psychic brain activity with continuous wavelet analysis of EEG publication-title: Journal of Behavioral and Brain Science doi: 10.4236/jbbs.2019.93006 – volume: 11 start-page: 20 issue: 1 year: 2016 ident: 10.1016/j.neunet.2022.03.025_b26 article-title: Transfer learning in brain-computer interfaces publication-title: IEEE Computational Intelligence Magazine doi: 10.1109/MCI.2015.2501545 – volume: 99 start-page: 386 issue: 4–6 year: 2006 ident: 10.1016/j.neunet.2022.03.025_b36 article-title: Motor imagery publication-title: Journal de Physiologie (Paris) doi: 10.1016/j.jphysparis.2006.03.012 – volume: 15 issue: 5 year: 2018 ident: 10.1016/j.neunet.2022.03.025_b32 article-title: EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces publication-title: Journal of Neural Engineering doi: 10.1088/1741-2552/aace8c – ident: 10.1016/j.neunet.2022.03.025_b8 doi: 10.1109/CVPR.2017.195 – volume: 97 start-page: 1177 issue: 5 year: 2018 ident: 10.1016/j.neunet.2022.03.025_b62 article-title: Neural population dynamics underlying motor learning transfer publication-title: Neuron doi: 10.1016/j.neuron.2018.01.040 – volume: 16 issue: 2 year: 2019 ident: 10.1016/j.neunet.2022.03.025_b14 article-title: Inter-subject transfer learning with an end-to-end deep convolutional neural network for EEG-based BCI publication-title: Journal of Neural Engineering doi: 10.1088/1741-2552/aaf3f6 – volume: 12 issue: 6 year: 2015 ident: 10.1016/j.neunet.2022.03.025_b67 article-title: Efficient resting-state EEG network facilitates motor imagery performance publication-title: Journal of Neural Engineering doi: 10.1088/1741-2560/12/6/066024 – volume: 22 start-page: 1305 issue: 9 year: 2009 ident: 10.1016/j.neunet.2022.03.025_b17 article-title: Subject-independent mental state classification in single trials publication-title: Neural Networks doi: 10.1016/j.neunet.2009.06.003 – volume: 43 start-page: 169 issue: 6 year: 2019 ident: 10.1016/j.neunet.2022.03.025_b18 article-title: Improvement motor imagery EEG classification based on regularized linear discriminant analysis publication-title: Journal of Medical Systems doi: 10.1007/s10916-019-1270-0 – volume: 97 start-page: 56 year: 2017 ident: 10.1016/j.neunet.2022.03.025_b60 article-title: Assessing motor imagery in brain-computer interface training: psychological and neurophysiological correlates publication-title: Neuropsychologia doi: 10.1016/j.neuropsychologia.2017.02.005 – ident: 10.1016/j.neunet.2022.03.025_b19 doi: 10.1109/CVPR.2016.265 – start-page: 207 year: 2018 ident: 10.1016/j.neunet.2022.03.025_b40 article-title: Sparse kernel machines for motor imagery eeg classification – volume: 84 start-page: 626 issue: 4 year: 1996 ident: 10.1016/j.neunet.2022.03.025_b59 article-title: A review of wavelets in biomedical applications publication-title: Proceedings of the IEEE doi: 10.1109/5.488704 – volume: 124 start-page: 202 year: 2020 ident: 10.1016/j.neunet.2022.03.025_b43 article-title: EEG based multi-class seizure type classification using convolutional neural network and transfer learning publication-title: Neural Networks doi: 10.1016/j.neunet.2020.01.017 – start-page: 916 year: 2018 ident: 10.1016/j.neunet.2022.03.025_b57 article-title: Deep transfer learning for EEG-based brain computer interface – year: 2015 ident: 10.1016/j.neunet.2022.03.025_b42 – volume: 2017 year: 2017 ident: 10.1016/j.neunet.2022.03.025_b7 article-title: Motor imagery impairment in postacute stroke patients publication-title: Neural Plasticity doi: 10.1155/2017/4653256 – volume: 89 start-page: 80 issue: 1 year: 2012 ident: 10.1016/j.neunet.2022.03.025_b22 article-title: Psychological predictors of SMR-BCI performance publication-title: Biological Psychology doi: 10.1016/j.biopsycho.2011.09.006 – volume: 4 start-page: 55 year: 2010 ident: 10.1016/j.neunet.2022.03.025_b39 article-title: The influence of psychological state and motivation on brain–computer interface performance in patients with amyotrophic lateral sclerosis–a longitudinal study publication-title: Frontiers in Neuroscience – volume: 8 start-page: 211 issue: 2 year: 2000 ident: 10.1016/j.neunet.2022.03.025_b38 article-title: Brain-computer interfaces based on the steady-state visual-evoked response publication-title: IEEE Transactions on Rehabilitation Engineering doi: 10.1109/86.847819 – volume: 28 start-page: 219 year: 2021 ident: 10.1016/j.neunet.2022.03.025_b54 article-title: Adaptive spatiotemporal graph convolutional networks for motor imagery classification publication-title: IEEE Signal Processing Letters doi: 10.1109/LSP.2021.3049683 – volume: 243 start-page: 103 year: 2015 ident: 10.1016/j.neunet.2022.03.025_b1 article-title: Performance variation in motor imagery brain–computer interface: a brief review publication-title: Journal of Neuroscience Methods doi: 10.1016/j.jneumeth.2015.01.033 – volume: 10 start-page: P84 issue: Suppl 1 year: 2009 ident: 10.1016/j.neunet.2022.03.025_b5 article-title: Predicting BCI performance to study BCI illiteracy publication-title: BMC Neuroscience – start-page: 1 year: 2021 ident: 10.1016/j.neunet.2022.03.025_b23 article-title: Semi-supervised contrastive learning for generalizable motor imagery EEG classification – start-page: 513 year: 2009 ident: 10.1016/j.neunet.2022.03.025_b16 article-title: Subject independent EEG-based BCI decoding – ident: 10.1016/j.neunet.2022.03.025_b34 doi: 10.1109/CVPR.2015.7298965 – volume: 7 start-page: 31 year: 2013 ident: 10.1016/j.neunet.2022.03.025_b44 article-title: The Ease of Language Understanding (ELU) model: theoretical, empirical, and clinical advances publication-title: Frontiers in Systems Neuroscience doi: 10.3389/fnsys.2013.00031 – volume: 116 start-page: 6482 issue: 13 year: 2019 ident: 10.1016/j.neunet.2022.03.025_b15 article-title: Regulation of arousal via online neurofeedback improves human performance in a demanding sensory-motor task publication-title: Proceedings of the National Academy of Sciences doi: 10.1073/pnas.1817207116 – start-page: 195 year: 2017 ident: 10.1016/j.neunet.2022.03.025_b30 article-title: Introduction to pytorch – volume: 7 start-page: 52 issue: 1 year: 2014 ident: 10.1016/j.neunet.2022.03.025_b9 article-title: Collaborative approach in the development of High-Performance Brain–Computer interfaces for a neuroprosthetic arm: Translation from animal models to human control publication-title: Clinical and Translational Science doi: 10.1111/cts.12086 – start-page: 694 year: 2016 ident: 10.1016/j.neunet.2022.03.025_b29 article-title: Perceptual losses for real-time style transfer and super-resolution – volume: 39 start-page: 6136 issue: 31 year: 2019 ident: 10.1016/j.neunet.2022.03.025_b51 article-title: Structural variability in the human brain reflects fine-grained functional architecture at the population level publication-title: Journal of Neuroscience doi: 10.1523/JNEUROSCI.2912-18.2019 – volume: 107 start-page: 248 year: 2019 ident: 10.1016/j.neunet.2022.03.025_b68 article-title: Portable brain-computer interface based on novel convolutional neural network publication-title: Computers in Biology and Medicine doi: 10.1016/j.compbiomed.2019.02.023 – start-page: 7354 year: 2019 ident: 10.1016/j.neunet.2022.03.025_b66 article-title: Self-attention generative adversarial networks – volume: 114 start-page: 438 year: 2015 ident: 10.1016/j.neunet.2022.03.025_b70 article-title: Real-time EEG feedback during simultaneous EEG–fMRI identifies the cortical signature of motor imagery publication-title: Neuroimage doi: 10.1016/j.neuroimage.2015.04.020 – volume: 398 start-page: 297 issue: 6725 year: 1999 ident: 10.1016/j.neunet.2022.03.025_b4 article-title: A spelling device for the paralysed publication-title: Nature doi: 10.1038/18581 – volume: 18 start-page: 541 issue: 2 year: 2020 ident: 10.1016/j.neunet.2022.03.025_b55 article-title: Eeg motor imagery classification with sparse spectrotemporal decomposition and deep learning publication-title: IEEE Transactions on Automation Science and Engineering doi: 10.1109/TASE.2020.3021456 – volume: 579 start-page: 637 issue: 3 year: 2007 ident: 10.1016/j.neunet.2022.03.025_b11 article-title: Brain–computer interface technology as a tool to augment plasticity and outcomes for neurological rehabilitation publication-title: The Journal of Physiology doi: 10.1113/jphysiol.2006.123067 – volume: 51 start-page: 979 issue: 6 year: 2004 ident: 10.1016/j.neunet.2022.03.025_b48 article-title: An asynchronously controlled EEG-based virtual keyboard: improvement of the spelling rate publication-title: IEEE Transactions on Biomedical Engineering doi: 10.1109/TBME.2004.827062 – volume: 202 year: 2019 ident: 10.1016/j.neunet.2022.03.025_b3 article-title: The community structure of functional brain networks exhibits scale-specific patterns of inter-and intra-subject variability publication-title: Neuroimage doi: 10.1016/j.neuroimage.2019.07.003 – volume: 51 start-page: 1303 issue: 4 year: 2010 ident: 10.1016/j.neunet.2022.03.025_b6 article-title: Neurophysiological predictor of SMR-based BCI performance publication-title: Neuroimage doi: 10.1016/j.neuroimage.2010.03.022 – year: 2015 ident: 10.1016/j.neunet.2022.03.025_b24 – volume: 23 start-page: 631 issue: 2 year: 2018 ident: 10.1016/j.neunet.2022.03.025_b28 article-title: Sparse group representation model for motor imagery EEG classification publication-title: IEEE Journal of Biomedical and Health Informatics doi: 10.1109/JBHI.2018.2832538 – volume: 180 start-page: 304 issue: 2 year: 2009 ident: 10.1016/j.neunet.2022.03.025_b50 article-title: Sleep spindles and spike–wave discharges in EEG: their generic features, similarities and distinctions disclosed with Fourier transform and continuous wavelet analysis publication-title: Journal of Neuroscience Methods doi: 10.1016/j.jneumeth.2009.04.006 – volume: 58 start-page: 355 issue: 2 year: 2010 ident: 10.1016/j.neunet.2022.03.025_b35 article-title: Regularizing common spatial patterns to improve BCI designs: unified theory and new algorithms publication-title: IEEE Transactions on Biomedical Engineering doi: 10.1109/TBME.2010.2082539 – volume: 13 start-page: 87 year: 2019 ident: 10.1016/j.neunet.2022.03.025_b46 article-title: Intra-and inter-subject variability in EEG-based sensorimotor brain computer interface: a review publication-title: Frontiers in Computational Neuroscience doi: 10.3389/fncom.2019.00087 – volume: 108 start-page: 485 issue: 4 year: 2020 ident: 10.1016/j.neunet.2022.03.025_b10 article-title: Model compression and hardware acceleration for neural networks: A comprehensive survey publication-title: Proceedings of the IEEE doi: 10.1109/JPROC.2020.2976475 – year: 2014 ident: 10.1016/j.neunet.2022.03.025_b31 – volume: 21 start-page: 157 issue: 1 year: 2010 ident: 10.1016/j.neunet.2022.03.025_b63 article-title: Neural interface technology for rehabilitation: exploiting and promoting neuroplasticity publication-title: Physical Medicine and Rehabilitation Clinics – year: 2021 ident: 10.1016/j.neunet.2022.03.025_b53 article-title: Training-free deep generative networks for compressed sensing of neural action potentials publication-title: IEEE Transactions on Neural Networks and Learning Systems – volume: 114 start-page: 532 year: 2018 ident: 10.1016/j.neunet.2022.03.025_b12 article-title: An end-to-end deep learning approach to MI-EEG signal classification for BCIs publication-title: Expert Systems with Applications doi: 10.1016/j.eswa.2018.08.031 – volume: 23 issue: 1 year: 2014 ident: 10.1016/j.neunet.2022.03.025_b52 article-title: Overcoming inter-subject variability in BCI using EEG-based identification publication-title: Radioengineering – volume: 14 issue: 1 year: 2016 ident: 10.1016/j.neunet.2022.03.025_b56 article-title: A novel deep learning approach for classification of EEG motor imagery signals publication-title: Journal of Neural Engineering doi: 10.1088/1741-2560/14/1/016003 – volume: 13 issue: 2 year: 2016 ident: 10.1016/j.neunet.2022.03.025_b58 article-title: Pushing the P300-based brain–computer interface beyond 100 bpm: Extending performance guided constraints into the temporal domain publication-title: Journal of Neural Engineering doi: 10.1088/1741-2560/13/2/026024 |
| SSID | ssj0006843 |
| Score | 2.5107048 |
| Snippet | Electroencephalographic measurement of cortical activity subserving motor behavior varies among different individuals, restricting the potential of brain... |
| SourceID | proquest pubmed crossref elsevier |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 111 |
| SubjectTerms | BCI-illiterate Brain computer interfaces (BCIs) Convolutional neural network (CNN) Golden subject Motor imagery (MI) |
| Title | Golden subject is everyone: A subject transfer neural network for motor imagery-based brain computer interfaces |
| URI | https://dx.doi.org/10.1016/j.neunet.2022.03.025 https://www.ncbi.nlm.nih.gov/pubmed/35405471 https://www.proquest.com/docview/2649593447 |
| Volume | 151 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3NS8MwFA-iFy9-f8yPEcFrXJe0SettiHMq7qKD3UKbJjCZ3XDbwYt_u-817URQBkIpNCRtyO8l77X95fcIuYyMypVzjsVGKAbvG5wlea4Y584EFgwgTnBz8lNf9gbhwzAarpGbei8M0iqrtd-v6eVqXZW0qtFsTUej1nMArlb6raKYrAA1QcNQoZVffX7TPGTsmXNQmWHtevtcyfEq7KKwyKjkvJQ6xYTZv7unv8LP0g11d8hWFT_Sju_iLlmzxR7ZrnMz0Gqq7pPJ3WQMSwqdLTL80kJHM2rBaj8mhb2mnWXxvIxboSHqWsJ9C88KpxDKUgARzqM3VLn4YOjucpphRglq6seh2MS7Q1bXARl0b19ueqxKrsAM-Kw5sy6wmeMmhSkvTORUmEDoJG3bSJVyy2Xm2gAjHLHKIYZxcR5yhDUSMkpkKg7JegF9PiY0lUEmRGLyVMnQcJQ-ThwK06UiijOeNYiox1SbSnkcE2CMdU0xe9UeCY1I6EBoQKJB2LLV1CtvrKivarj0DwvS4BxWtLyo0dUwufCPSVrYyWKmIVpE4WYwqwY58rAv-4IfzCJw7Sf_fu4p2cQrT_49I-vz94U9hxBnnjVLG26Sjc79Y6__BcQg_Jk |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1LT9wwEB5RONBLW6CPLQWMBEd3g53YSaUeEK_leQEkbm7i2NJWNIvYXVV76Z_qH2QmThYhgZCQkKIckvg545lJ8vkbgI3E6lJ773lqpeb4viF4VpaaC-Ft5FAB0ow2J5-eqd5lfHSVXM3A_3YvDMEqG9sfbHptrZsr3WY2uzf9fvc8QlerwlZRSlYQN8jKYzf5i-9tw5-HuyjkTSH29y52erxJLcAtWuwRdz5yhRc2R4WXNvE6zjBwUG7LKp0LJ1Tht3AQeKS6RA_u0zIWNKhEqiRTucR638BcjOaC0iZ8_3ePK1FpgOph7zh1r92vV4PKKjeuHEE4hai5VSlD9-P-8Kl4t_Z7-x_gXROwsu0wJwsw46pFeN8mg2CNbViCwcHgGm0YG44L-rTD-kPmcJlMBpX7wbanl0d1oIwFiUgT660CDJ1h7MxQa_Dc_0O0GhNO_rVkBaWwYLZtjtgtbj3ByD7C5atM-SeYrbDPX4DlKiqkzGyZaxVbQVzLmScmvFwmaSGKDsh2To1tqM4p48a1aTFtv02QhCFJmEgalEQH-LTUTaD6eOZ53YrLPFBZg97omZLrrXQNrmb6RZNXbjAeGgxPiSk6jnUHPgexT_tCX-gSjCW-vrjdNZjvXZyemJPDs-NleEt3AvL4G8yObsduBeOrUbFa6zODX6-9gO4AnKk4Tg |
| 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=Golden+subject+is+everyone%3A+A+subject+transfer+neural+network+for+motor+imagery-based+brain+computer+interfaces&rft.jtitle=Neural+networks&rft.au=Sun%2C+Biao&rft.au=Wu%2C+Zexu&rft.au=Hu%2C+Yong&rft.au=Li%2C+Ting&rft.date=2022-07-01&rft.issn=1879-2782&rft.eissn=1879-2782&rft.volume=151&rft.spage=111&rft_id=info:doi/10.1016%2Fj.neunet.2022.03.025&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0893-6080&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0893-6080&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0893-6080&client=summon |