A Novel Small-data based Approach for Decoding Yes/No-Decisions of Locked-in Patients Using Generative Adversarial Networks
We demonstrate how to use generative adversarial networks to improve the small data problem when training brain-computer-interfaces. The new approach is based on finely graded frequency bands, which are extracted from motor imagery electroencephalography data by using power spectral density method t...
Saved in:
Published in | IEEE access Vol. 11; p. 1 |
---|---|
Main Authors | , |
Format | Journal Article |
Language | English |
Published |
Piscataway
IEEE
01.01.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | We demonstrate how to use generative adversarial networks to improve the small data problem when training brain-computer-interfaces. The new approach is based on finely graded frequency bands, which are extracted from motor imagery electroencephalography data by using power spectral density method to synthetically generate electroencephalography data using generative adversarial networks. We evaluate our approach using one of the currently largest publicly available electroencephalography datasets, by first checking the synthetic and real data for statistical and visual similarity, and secondly, by training a random forest classifier, once using only the real data and then using the real data augmented with the synthetic data. With similarity scores of 95.72 % in the subject-dependent case and 83.51 % in the subject-independent case, and a predictive gain of 17.53 % in the subject-dependent case, and 7.51 % in the subject-independent case, we were able to achieve promising results. The results show that our approach can make it possible to research rare diseases for which there is too little patient data. Also, synthetic data can be a way for many electroencephalography-based brain-computer interface applications to obtain the required data more cost- and time-efficiently. |
---|---|
AbstractList | We demonstrate how to use generative adversarial networks to improve the small data problem when training brain-computer-interfaces. The new approach is based on finely graded frequency bands, which are extracted from motor imagery electroencephalography data by using power spectral density method to synthetically generate electroencephalography data using generative adversarial networks. We evaluate our approach using one of the currently largest publicly available electroencephalography datasets, by first checking the synthetic and real data for statistical and visual similarity, and secondly, by training a random forest classifier, once using only the real data and then using the real data augmented with the synthetic data. With similarity scores of 95.72 % in the subject-dependent case and 83.51 % in the subject-independent case, and a predictive gain of 17.53 % in the subject-dependent case, and 7.51 % in the subject-independent case, we were able to achieve promising results. The results show that our approach can make it possible to research rare diseases for which there is too little patient data. Also, synthetic data can be a way for many electroencephalography-based brain-computer interface applications to obtain the required data more cost- and time-efficiently. |
Author | Buettner, Ricardo Penava, Pascal |
Author_xml | – sequence: 1 givenname: Pascal orcidid: 0009-0004-9870-8193 surname: Penava fullname: Penava, Pascal organization: Chair of Information Systems and Data Science, University of Bayreuth, Bayreuth, Germany – sequence: 2 givenname: Ricardo orcidid: 0000-0003-2263-6408 surname: Buettner fullname: Buettner, Ricardo organization: Chair of Information Systems and Data Science, University of Bayreuth, Bayreuth, Germany |
BookMark | eNpNUctuGyEUHVWp1DTNF7QLpK7HYYAZYDly85Ist5KbRVfoGi4pzmRwYeKqys8Xd6IqbOAenccV5311MsYRq-pjQxdNQ_VFv1xebjYLRhlfcM46yeib6pQ1na55y7uTV-931XnOO1qOKlArT6vnnqzjAQeyeYRhqB1MQLaQ0ZF-v08R7E_iYyJf0EYXxnvyA_PFOtZlDjnEMZPoySraB3R1GMk3mAKOUyZ3-Ui-xhFTgQ5IenfAlCEFGMgap98xPeQP1VsPQ8bzl_usuru6_L68qVdfr2-X_aq2guqpBsV8I9iWdlRzELTdKm2da-RWKiU989bTIypd66G1XWOZR6477p2wSgl-Vt3Ovi7CzuxTeIT0x0QI5h8Q072BNAU7oGnbToCV4JR0QqAHpiWVlAlpvfbeF6_Ps1f5nF9PmCezi09pLOsbVrKU5rxpC4vPLJtizgn9_9SGmmNpZi7NHEszL6UV1adZFRDxlYJpqmTL_wIhoJTt |
CODEN | IAECCG |
CitedBy_id | crossref_primary_10_1109_ACCESS_2024_3394696 |
Cites_doi | 10.1007/978-3-030-18305-9_9 10.1113/jphysiol.2006.125948 10.1016/S0003-9993(95)80031-X 10.1145/3453892.3461338 10.1530/acta.0.0910629 10.1109/IEMBS.2011.6091432 10.1016/j.neuroimage.2007.01.051 10.1145/3490354.3494393 10.1109/MSP.2008.4408441 10.1016/j.compbiomed.2014.10.021 10.24251/HICSS.2021.460 10.1109/WACV.2018.00028 10.1109/IJCNN.2018.8489727 10.1016/j.jss.2004.02.008 10.1109/ICCV.2019.01040 10.1145/1296843.1296845 10.1109/TPAMI.2009.187 10.1515/bmt-2014-0117 10.1609/aaai.v33i01.33018901 10.1155/ASP.2005.3128 10.1016/j.eij.2015.06.002 10.2307/25148625 10.1088/1741-2552/abca18 10.1007/s11831-021-09684-6 10.1111/ene.14393 10.1109/TNSRE.2004.827220 10.1109/HORA52670.2021.9461383 10.1007/978-3-030-22796-8_16 10.1109/EMBC.2018.8512865 10.1109/ICCV.2017.405 10.1007/s00221-013-3764-1 10.1088/1741-2560/5/2/012 10.1016/j.inffus.2021.06.007 10.1007/s10339-012-0472-x 10.14778/3231751.3231757 10.1016/S1388-2457(99)00141-8 10.1007/s00521-021-06352-5 10.1109/ACCT.2015.72 10.1023/A:1010933404324 10.1080/10400435.2012.723298 10.1109/ICoBE.2012.6178961 10.1007/BF00058655 10.1007/s10479-006-0076-x 10.1016/S1567-424X(09)70400-3 10.1142/S0129065722500137 10.1155/2017/8327980 10.1109/MSP.2017.2765202 10.1109/IEMBS.2010.5626782 10.1007/s40747-021-00336-7 10.1109/TIM.2019.2914712 10.1016/0166-4328(95)00225-1 10.1109/RBME.2009.2035356 10.1109/TAU.1967.1161901 10.1038/nbt.3787 10.1109/TNSRE.2012.2190299 10.1109/ICDM.2017.93 10.1109/TNSRE.2019.2915801 10.1109/TBME.1971.4502880 10.1109/CVPR.2017.19 10.1109/10.293240 10.3389/frobt.2018.00066 10.3390/s120201211 10.1109/TNSRE.2019.2956488 10.17705/1CAIS.03746 10.24251/HICSS.2021.411 10.1109/IEMBS.2011.6091508 10.1023/A:1023437823106 10.1007/978-3-030-60073-0_30 10.1073/pnas.0403504101 10.1016/S0079-6123(09)17723-3 10.1214/06-BA104 10.1093/gigascience/giz002 10.1088/1741-2552/aaf12e 10.1109/TBME.2010.2055564 10.1007/s11222-009-9153-8 10.1016/B978-012373873-8.00017-7 10.1109/JAS.2017.7510583 10.1109/IJCNN48605.2020.9206683 10.1007/978-3-030-30490-4_56 10.1088/1741-2552/aab2f2 10.1016/S1388-2457(02)00057-3 10.1016/j.jval.2018.03.002 10.1007/978-1-4614-5227-0_2 10.1186/s12984-023-01169-w 10.1016/j.neucom.2019.05.108 10.1186/1471-2105-10-213 10.1145/3422622 10.1109/CCMB.2013.6609180 10.3390/s20185083 10.1145/1941487.1941506 10.1093/gigascience/gix034 10.1109/THMS.2020.3047597 10.24251/HICSS.2020.393 10.1038/s41591-018-0316-z 10.1109/TNNLS.2018.2789927 10.3390/info12090375 10.1016/j.neunet.2020.09.001 10.1088/1741-2552/aaf3f6 10.1109/STA50679.2020.9329330 10.1038/s41598-021-89690-7 10.1109/BigData52589.2021.9671448 10.1162/neco.1995.7.6.1129 10.3389/fnhum.2017.00450 10.1109/TNSRE.2006.875557 10.1016/S0304-3940(97)00889-6 |
ContentType | Journal Article |
Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023 |
Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023 |
DBID | 97E ESBDL RIA RIE AAYXX CITATION 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D DOA |
DOI | 10.1109/ACCESS.2023.3326720 |
DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005-present IEEE Xplore Open Access Journals IEEE All-Society Periodicals Package (ASPP) 1998-Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts METADEX Technology Research Database Materials Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional DOAJ Directory of Open Access Journals |
DatabaseTitle | CrossRef Materials Research Database Engineered Materials Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace METADEX Computer and Information Systems Abstracts Professional |
DatabaseTitleList | Materials Research Database |
Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Engineering |
EISSN | 2169-3536 |
EndPage | 1 |
ExternalDocumentID | oai_doaj_org_article_5564ac7ad87d44efa297070247cf9fff 10_1109_ACCESS_2023_3326720 10290875 |
Genre | orig-research |
GroupedDBID | 0R~ 5VS 6IK 97E AAJGR ABVLG ACGFS ADBBV ALMA_UNASSIGNED_HOLDINGS BCNDV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS ESBDL GROUPED_DOAJ IFIPE IPLJI JAVBF KQ8 M43 M~E O9- OCL OK1 RIA RIE RIG RNS 4.4 AAYXX CITATION EJD 7SC 7SP 7SR 8BQ 8FD JG9 JQ2 L7M L~C L~D |
ID | FETCH-LOGICAL-c409t-a82f142b06093a405b89cdd17b7887f2fcf0405b7d5fa5c61c2fe3963fd4c8843 |
IEDL.DBID | RIE |
ISSN | 2169-3536 |
IngestDate | Thu Sep 05 15:43:35 EDT 2024 Fri Sep 13 01:58:34 EDT 2024 Fri Aug 23 01:01:43 EDT 2024 Wed Jun 26 19:24:25 EDT 2024 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c409t-a82f142b06093a405b89cdd17b7887f2fcf0405b7d5fa5c61c2fe3963fd4c8843 |
ORCID | 0000-0003-2263-6408 0009-0004-9870-8193 |
OpenAccessLink | https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/document/10290875 |
PQID | 2884893315 |
PQPubID | 4845423 |
PageCount | 1 |
ParticipantIDs | doaj_primary_oai_doaj_org_article_5564ac7ad87d44efa297070247cf9fff crossref_primary_10_1109_ACCESS_2023_3326720 proquest_journals_2884893315 ieee_primary_10290875 |
PublicationCentury | 2000 |
PublicationDate | 2023-01-01 |
PublicationDateYYYYMMDD | 2023-01-01 |
PublicationDate_xml | – month: 01 year: 2023 text: 2023-01-01 day: 01 |
PublicationDecade | 2020 |
PublicationPlace | Piscataway |
PublicationPlace_xml | – name: Piscataway |
PublicationTitle | IEEE access |
PublicationTitleAbbrev | Access |
PublicationYear | 2023 |
Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
References | ref57 ref56 ref58 ref53 penava (ref106) 2023 ref55 yoon (ref50) 2019; 32 rahutomo (ref120) 2012; 4 ref51 di (ref75) 2010; 5 von alan (ref99) 2004; 28 xu (ref95) 2019; 32 ref46 ref45 ref47 ref42 ref41 ref44 hartmann (ref119) 2018 ref49 ref8 ref7 ref9 ref4 ref3 ref6 ref5 pedregosa (ref109) 2011; 12 ref100 ref101 lee (ref91) 2021; 99 ref40 brenninkmeijer (ref113) 2019 ref35 ref34 ref37 ref36 ref31 ref30 ref33 ref32 ref39 ref38 baumgartl (ref59) 2021 ref24 ref23 ref26 ref25 ref20 ref22 ref21 ref28 ref27 ref29 fahimi (ref48) 2018 scriba (ref1) 1979; 91 ref13 ref12 ref15 ref128 ref14 ref97 ref126 ref96 ref127 ref11 ref124 breitenbach (ref54) 2021 ref10 ref125 song (ref118) 2021 ref17 ref16 ref19 ref18 ref93 ref94 ref90 ref89 baumgartl (ref64) 2020; 48 ref86 ref85 ref88 ref87 nie (ref43) 2018 bishop (ref111) 2006; 4 stieger (ref112) 2021; 8 ref82 ref81 ref84 ref83 ref80 ref79 ref108 breitenbach (ref72) 2020 ref78 ref107 ref74 ref105 ref77 ref102 ref76 ref103 ref2 ref71 ref70 ref73 ref110 arjovsky (ref98) 2017 ref68 ref67 kohavi (ref117) 1995; 2 ref69 ref115 ref63 ref116 ref66 ref65 ref114 buettner (ref52) 2019 makeig (ref104) 1996; 8 choi (ref92) 2017 ref60 ref122 ref123 ref62 ref61 ref121 |
References_xml | – ident: ref42 doi: 10.1007/978-3-030-18305-9_9 – ident: ref10 doi: 10.1113/jphysiol.2006.125948 – ident: ref4 doi: 10.1016/S0003-9993(95)80031-X – ident: ref89 doi: 10.1145/3453892.3461338 – start-page: 1 year: 2021 ident: ref59 article-title: Detection of schizophrenia using machine learning on the five most predictive EEG-channels publication-title: Proc PACIS contributor: fullname: baumgartl – volume: 91 start-page: 629 year: 1979 ident: ref1 article-title: Effects of obesity, total fasting and realimentation on L-thyroxine (T4), 3, 5, 3'-l-triiodothyronine (T3),-3, 3', 5'-L-triiodorhyronine (rT3),-thyroxine binding globulin (TBG), cortisol, thyrotophin, cortisol-binding globulin (CBG), transferrin, ?2-haptoglobin and complement C'3 in serum publication-title: Eur J Endocrinol doi: 10.1530/acta.0.0910629 contributor: fullname: scriba – ident: ref80 doi: 10.1109/IEMBS.2011.6091432 – ident: ref124 doi: 10.1016/j.neuroimage.2007.01.051 – ident: ref46 doi: 10.1145/3490354.3494393 – ident: ref125 doi: 10.1109/MSP.2008.4408441 – ident: ref67 doi: 10.1016/j.compbiomed.2014.10.021 – ident: ref60 doi: 10.24251/HICSS.2021.460 – ident: ref37 doi: 10.1109/WACV.2018.00028 – ident: ref126 doi: 10.1109/IJCNN.2018.8489727 – ident: ref128 doi: 10.1016/j.jss.2004.02.008 – ident: ref41 doi: 10.1109/ICCV.2019.01040 – ident: ref81 doi: 10.1145/1296843.1296845 – volume: 8 start-page: 145 year: 1996 ident: ref104 article-title: Independent component analysis of electroencephalographic data publication-title: Proc Adv Neural Inf Process Syst contributor: fullname: makeig – ident: ref116 doi: 10.1109/TPAMI.2009.187 – ident: ref101 doi: 10.1515/bmt-2014-0117 – ident: ref39 doi: 10.1609/aaai.v33i01.33018901 – ident: ref24 doi: 10.1155/ASP.2005.3128 – ident: ref74 doi: 10.1016/j.eij.2015.06.002 – start-page: 1 year: 2018 ident: ref119 article-title: EEG-GAN: Generative adversarial networks for electroencephalograhic (EEG) brain signals publication-title: arXiv 1806 01875 contributor: fullname: hartmann – volume: 28 start-page: 75 year: 2004 ident: ref99 article-title: Design science in information systems research publication-title: MIS Quart doi: 10.2307/25148625 contributor: fullname: von alan – ident: ref8 doi: 10.1088/1741-2552/abca18 – ident: ref31 doi: 10.1007/s11831-021-09684-6 – ident: ref5 doi: 10.1111/ene.14393 – ident: ref22 doi: 10.1109/TNSRE.2004.827220 – ident: ref83 doi: 10.1109/HORA52670.2021.9461383 – volume: 48 start-page: 1 year: 2020 ident: ref64 article-title: Detecting antisocial personality disorder using a novel machine learning algorithm based on electroencephalographic data publication-title: Proc 24th Pacific Asia Conf Inf Syst (PACIS) contributor: fullname: baumgartl – ident: ref87 doi: 10.1007/978-3-030-22796-8_16 – ident: ref85 doi: 10.1109/EMBC.2018.8512865 – ident: ref36 doi: 10.1109/ICCV.2017.405 – ident: ref23 doi: 10.1007/s00221-013-3764-1 – ident: ref84 doi: 10.1088/1741-2560/5/2/012 – start-page: 286 year: 2017 ident: ref92 article-title: Generating multi-label discrete patient records using generative adversarial networks publication-title: Proc Mach Learn Healthcare Conf contributor: fullname: choi – ident: ref7 doi: 10.1016/j.inffus.2021.06.007 – ident: ref107 doi: 10.1007/s10339-012-0472-x – ident: ref94 doi: 10.14778/3231751.3231757 – ident: ref71 doi: 10.1016/S1388-2457(99)00141-8 – volume: 12 start-page: 2825 year: 2011 ident: ref109 article-title: Scikit-learn: Machine learning in python publication-title: J Mach Learn Res contributor: fullname: pedregosa – ident: ref21 doi: 10.1007/s00521-021-06352-5 – start-page: 1 year: 2018 ident: ref43 article-title: RelGAN: Relational generative adversarial networks for text generation publication-title: Proc Int Conf Learn Represent contributor: fullname: nie – ident: ref12 doi: 10.1109/ACCT.2015.72 – ident: ref68 doi: 10.1023/A:1010933404324 – ident: ref30 doi: 10.1080/10400435.2012.723298 – ident: ref76 doi: 10.1109/ICoBE.2012.6178961 – ident: ref114 doi: 10.1007/BF00058655 – ident: ref44 doi: 10.1007/s10479-006-0076-x – ident: ref69 doi: 10.1016/S1567-424X(09)70400-3 – start-page: 1 year: 2021 ident: ref54 article-title: A novel machine learning approach to working memory evaluation using resting-state EEG data publication-title: Proc 25th Pacific Asia Conf Inf Syst (PACIS) contributor: fullname: breitenbach – start-page: 4057 year: 2023 ident: ref106 article-title: Subject-independent detection of yes/no decisions using EEG recordings during motor imagery tasks: A novel machine-learning approach with fine-graded EEG spectrum publication-title: Proc 56th Hawaii Int Conf Syst Sci contributor: fullname: penava – volume: 8 start-page: 1 year: 2021 ident: ref112 article-title: Continuous sensorimotor rhythm based brain computer interface learning in a large population publication-title: Data Science Journal contributor: fullname: stieger – ident: ref62 doi: 10.1142/S0129065722500137 – ident: ref56 doi: 10.1155/2017/8327980 – ident: ref34 doi: 10.1109/MSP.2017.2765202 – ident: ref79 doi: 10.1109/IEMBS.2010.5626782 – ident: ref86 doi: 10.1007/s40747-021-00336-7 – ident: ref82 doi: 10.1109/TIM.2019.2914712 – ident: ref14 doi: 10.1016/0166-4328(95)00225-1 – ident: ref17 doi: 10.1109/RBME.2009.2035356 – volume: 32 start-page: 5509 year: 2019 ident: ref50 article-title: Time-series generative adversarial networks publication-title: Proc Adv Neural Inf Process Systems contributor: fullname: yoon – ident: ref51 doi: 10.1109/TAU.1967.1161901 – ident: ref57 doi: 10.1038/nbt.3787 – ident: ref28 doi: 10.1109/TNSRE.2012.2190299 – volume: 99 start-page: 2359 year: 2021 ident: ref91 article-title: CTGAN vs TGAN? Which one is more suitable for generating synthetic EEG data publication-title: J Theor Appl Inf Technol contributor: fullname: lee – ident: ref93 doi: 10.1109/ICDM.2017.93 – ident: ref100 doi: 10.1109/TNSRE.2019.2915801 – ident: ref11 doi: 10.1109/TBME.1971.4502880 – ident: ref40 doi: 10.1109/CVPR.2017.19 – ident: ref102 doi: 10.1109/10.293240 – ident: ref38 doi: 10.3389/frobt.2018.00066 – ident: ref13 doi: 10.3390/s120201211 – ident: ref105 doi: 10.1109/TNSRE.2019.2956488 – volume: 4 start-page: 1 year: 2012 ident: ref120 article-title: Semantic cosine similarity publication-title: Proc 7th Int Student Conf Adv Sci Technol ICAST contributor: fullname: rahutomo – ident: ref53 doi: 10.17705/1CAIS.03746 – start-page: 1 year: 2019 ident: ref52 article-title: High-performance detection of epilepsy in seizure-free EEG recordings: A novel machine learning approach using very specific epileptic EEG sub-bands publication-title: Proc ICIS contributor: fullname: buettner – ident: ref6 doi: 10.24251/HICSS.2021.411 – ident: ref78 doi: 10.1109/IEMBS.2011.6091508 – ident: ref70 doi: 10.1023/A:1023437823106 – ident: ref65 doi: 10.1007/978-3-030-60073-0_30 – ident: ref27 doi: 10.1073/pnas.0403504101 – ident: ref2 doi: 10.1016/S0079-6123(09)17723-3 – ident: ref97 doi: 10.1214/06-BA104 – volume: 5 start-page: 406 year: 2010 ident: ref75 article-title: Notice of retraction: Study on human brain after consuming alcohol based on EEG signal publication-title: Proc 3rd Int Conf Comput Sci Inf Technol contributor: fullname: di – ident: ref123 doi: 10.1093/gigascience/giz002 – start-page: 1 year: 2020 ident: ref72 article-title: Detection of excessive daytime sleepiness in resting-state EEG recordings: A novel machine learning approach using specific EEG sub-bands and channels publication-title: AMCIS Healthcare Informat Health Inf Tech (SIGHealth) contributor: fullname: breitenbach – ident: ref29 doi: 10.1088/1741-2552/aaf12e – ident: ref25 doi: 10.1109/TBME.2010.2055564 – volume: 4 year: 2006 ident: ref111 publication-title: Pattern Recognition and Machine Learning contributor: fullname: bishop – ident: ref115 doi: 10.1007/s11222-009-9153-8 – start-page: 1 year: 2018 ident: ref48 article-title: Deep convolutional neural network for the detection of attentive mental state in elderly publication-title: Proc 7th Int BCI Meeting contributor: fullname: fahimi – ident: ref3 doi: 10.1016/B978-012373873-8.00017-7 – ident: ref35 doi: 10.1109/JAS.2017.7510583 – volume: 32 start-page: 1 year: 2019 ident: ref95 article-title: Modeling tabular data using conditional GAN publication-title: Proc Adv Neural Inf Process Syst contributor: fullname: xu – ident: ref127 doi: 10.1109/IJCNN48605.2020.9206683 – ident: ref45 doi: 10.1007/978-3-030-30490-4_56 – ident: ref66 doi: 10.1088/1741-2552/aab2f2 – ident: ref16 doi: 10.1016/S1388-2457(02)00057-3 – ident: ref58 doi: 10.1016/j.jval.2018.03.002 – ident: ref32 doi: 10.1007/978-1-4614-5227-0_2 – ident: ref96 doi: 10.1186/s12984-023-01169-w – ident: ref90 doi: 10.1016/j.neucom.2019.05.108 – ident: ref108 doi: 10.1186/1471-2105-10-213 – ident: ref33 doi: 10.1145/3422622 – ident: ref77 doi: 10.1109/CCMB.2013.6609180 – ident: ref19 doi: 10.3390/s20185083 – ident: ref26 doi: 10.1145/1941487.1941506 – year: 2019 ident: ref113 article-title: On the generation and evaluation of tabular data using GANs contributor: fullname: brenninkmeijer – ident: ref122 doi: 10.1093/gigascience/gix034 – ident: ref18 doi: 10.1109/THMS.2020.3047597 – ident: ref55 doi: 10.24251/HICSS.2020.393 – ident: ref9 doi: 10.1038/s41591-018-0316-z – ident: ref49 doi: 10.1109/TNNLS.2018.2789927 – start-page: 214 year: 2017 ident: ref98 article-title: Wasserstein generative adversarial networks publication-title: Proc Int Conf Mach Learn contributor: fullname: arjovsky – ident: ref110 doi: 10.3390/info12090375 – ident: ref121 doi: 10.1016/j.neunet.2020.09.001 – ident: ref47 doi: 10.1088/1741-2552/aaf3f6 – start-page: 1 year: 2021 ident: ref118 article-title: Common spatial generative adversarial networks based EEG data augmentation for cross-subject brain-computer interface publication-title: arXiv 2102 04456 contributor: fullname: song – ident: ref88 doi: 10.1109/STA50679.2020.9329330 – volume: 2 start-page: 1137 year: 1995 ident: ref117 article-title: A study of cross-validation and bootstrap for accuracy estimation and model selection publication-title: Proc 14th Int Joint Conf Artif Intell (IJCAI) contributor: fullname: kohavi – ident: ref63 doi: 10.1038/s41598-021-89690-7 – ident: ref73 doi: 10.1109/BigData52589.2021.9671448 – ident: ref103 doi: 10.1162/neco.1995.7.6.1129 – ident: ref61 doi: 10.3389/fnhum.2017.00450 – ident: ref20 doi: 10.1109/TNSRE.2006.875557 – ident: ref15 doi: 10.1016/S0304-3940(97)00889-6 |
SSID | ssj0000816957 |
Score | 2.3163548 |
Snippet | We demonstrate how to use generative adversarial networks to improve the small data problem when training brain-computer-interfaces. The new approach is based... |
SourceID | doaj proquest crossref ieee |
SourceType | Open Website Aggregation Database Publisher |
StartPage | 1 |
SubjectTerms | Brain-computer interfaces Brain-computer-interface Classification tree analysis decision prediction Decision trees Decoding Diseases Electroencephalography Frequencies Generative adversarial networks Human-computer interface Machine learning motor imagery tasks Power spectral density Prediction methods Similarity Synthetic data Training |
SummonAdditionalLinks | – databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3Nb9MwFLfQTnBAG2yiYyAfOOI1cew4PnYtU0FQIW2TtpPl2H6n0k5L2WX__J4_iiJx4IKUkxXLeR9-H9HT70fIJ-WUkB6ARSw1JhoumVWqYUG7vhbW9Rnx5seqXd6Ib7fydkT1FWfCMjxwVtxUyha3KOs75YUIYLlW6KZcKAcaAFL0reWomUoxuKtbLVWBGaorPZ3N5yjReWQLP2-wZlGR4XuUihJif6FY-Ssup2RzeUhelyqRzvLXHZEXYfOGvBphB74lTzO62j6GNb36ZddrtrA7Sy8wJXk6KzDhFOtRusD2MqYneheG6WrLFoVTZ6BboN8xGAbPvm7ozwyvOtA0QkAzGHWMhDQxNg82-ild5Znx4ZjcXH65ni9ZYVJgDvu3HbMdh1rwvmor3Vis0fpOO-9r1cdhQuDgoIqrykuw0rW14xAavJvghes60ZyQg812E94Rih2Qcxofob2w2LyBb4OsuMXtVgqYkM97pZr7DJhhUqNRaZNtYKINTLHBhFxExf95NaJdpwX0AVN8wPzLBybkOJptdB7XEal_Qs72djTlag6GozxYpDW1PP0fZ78nL6M8-a_MGTnYPfwOH7BO2fUfk0s-A0E5404 priority: 102 providerName: Directory of Open Access Journals |
Title | A Novel Small-data based Approach for Decoding Yes/No-Decisions of Locked-in Patients Using Generative Adversarial Networks |
URI | https://ieeexplore.ieee.org/document/10290875 https://www.proquest.com/docview/2884893315/abstract/ https://doaj.org/article/5564ac7ad87d44efa297070247cf9fff |
Volume | 11 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Lb9QwELZoT3CgPIpY-pAPHHGaOHYcH5dtqwpBhASVyily_JAQywaR3R7gz3fG9lYrEBJSDpEVy7a-mfGMM_6GkNfKKiFdCAy51JiouWRGqZp5bYdKGDskxpsPXXN1Ld7dyJt8WT3ehfHex-QzX-Br_JfvRrvBozLQcK6RgX2P7LUlT5e17g9UsIKEliozC1WlPpsvFrCIAguEFzW4KQqLeu_sPpGkP1dV-csUx_3l8oB025mltJJvxWY9FPbXH6SN_z31J-Rx9jTpPInGU_LAr56RRzv8g8_J7zntxlu_pJ--m-WSYbYoxW3N0XmmGqfg09JzCFFxi6Nf_HTWjew81-WZ6BjoezCo3rGvK_oxUbRONKYh0ERojdaUxqrPk0FZp13KO58OyfXlxefFFcvVGJiFGHDNTMtDJfhQNqWuDfh5Q6utc5UaMCEx8GBDia3KyWCkbSrLg69Bv4MTtm1F_YLsr8aVf0koRFHWaniEdsJAABhc42XJDXQ3UoQZebNFqf-RSDf6GKyUuk-g9ghqn0GdkbeI5P2nyJgdGwCBPitgL2UDoqeMa5UTwgfDtQJzx4WyQYcAYx4iajvjJcBm5HgrGH1W76nnsB5w9OpKvvpHtyPyEKeYDmuOyf7658afgPuyHk5j2H8ahfcOWXbuDQ |
link.rule.ids | 315,786,790,802,870,2115,27957,27958,55109 |
linkProvider | IEEE |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Lb9QwELagHIADzyIWCvjAEaeJY8fxcdlSLbCNkGilcrIcPyTU7QaRXQ70z3f82GoFQkLKIUpi2dY345lxxt8g9FYYwbj1ngQuNcJqyokWoiZOmr5i2vSJ8eaka-Zn7NM5P8-H1eNZGOdcTD5zRbiN__LtYDZhqww0nMrAwH4b3QFDX8p0XOtmSyXUkJBcZG4heH84nc1gGkUoEV7U4KiIUNZ7x_5Emv5cV-WvxThamOOHqNuOLSWWXBSbdV-Y33_QNv734B-hB9nXxNMkHI_RLbd6gu7vMBA-RVdT3A2_3BJ_vdTLJQn5ojgYNounmWwcg1eLjyBIDUYOf3PjYTeQo1yZZ8SDxwtYUp0l31f4SyJpHXFMRMCJ0jqspzjWfR51kHbcpczzcR-dHX84nc1JrsdADESBa6Jb6itG-7IpZa3B0-tbaaytRB9SEj31xpfhqbDca26aylDvatBwb5lpW1Y_Q3urYeWeIwxxlDESLiYt0xACets4XlINzTVnfoLebVFSPxLthorhSilVAlUFUFUGdYLeByRvPg2c2fEBIKCyCirOGxA-oW0rLGPOayoFLHiUCeOl99DnfkBtp78E2AQdbAVDZQUfFYX5gKtXV_zFP5q9QXfnpycLtfjYfX6J7oXhpq2bA7S3_rlxr8CZWfevowhfA24f8G4 |
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=A+Novel+Small-data+based+Approach+for+Decoding+Yes%2FNo-Decisions+of+Locked-in+Patients+Using+Generative+Adversarial+Networks&rft.jtitle=IEEE+access&rft.au=Penava%2C+Pascal&rft.au=Buettner%2C+Ricardo&rft.date=2023-01-01&rft.pub=IEEE&rft.eissn=2169-3536&rft.spage=1&rft.epage=1&rft_id=info:doi/10.1109%2FACCESS.2023.3326720&rft.externalDocID=10290875 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2169-3536&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2169-3536&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2169-3536&client=summon |