Realising transfer learning through convolutional neural network and support vector machine for mental task classification

Electroencephalogram (EEG) measures brainwaves that have been the widely used modality for brain–computer interface (BCI) applications. EEG signal with machine learning has gained substantial success in the BCI. However, the availability of limited training data, appropriate model selection and high...

Full description

Saved in:

Bibliographic Details
Published in:	Electronics letters Vol. 56; no. 25; pp. 1375 - 1378
Main Authors:	Singh, D, Singh, S
Format:	Journal Article
Language:	English
Published:	The Institution of Engineering and Technology 10.12.2020
Subjects:	BCI brainwaves brain‐computer interface applications brain‐computer interfaces classification accuracy conventional machine learning approaches convolutional neural nets convolutional neural network‐based approach data availability data scarcity diverse feature extraction EEG signal EEG‐based classification electroencephalogram electroencephalography false‐positive rates feature extraction learning (artificial intelligence) medical signal processing mental task classification model misclassification ratio model selection optimal network pre‐trained network Resnet18 Resnet50 signal classification Special Issue: Current Trends in Cognitive Science and Brain Computing Research and Applications support vector machine support vector machines training data transfer learning model Vgg16 Vgg19 brain-computer interfaces misclassification ratio Resnet50 classification accuracy diverse feature extraction brain-computer interface applications mental task classification model data scarcity optimal network feature extraction pre-trained network data availability training data conventional machine learning approaches learning (artificial intelligence) EEG-based classification electroencephalography brainwaves support vector machines model selection BCI false-positive rates EEG signal transfer learning model electroencephalogram signal classification medical signal processing Vgg19 support vector machine Resnet18 Vgg16 convolutional neural nets convolutional neural network-based approach
ISSN:	0013-5194, 1350-911X, 1350-911X
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Electroencephalogram (EEG) measures brainwaves that have been the widely used modality for brain–computer interface (BCI) applications. EEG signal with machine learning has gained substantial success in the BCI. However, the availability of limited training data, appropriate model selection and high false-positive rates are the challenges that need immediate attention. Therefore, in this Letter, the authors present a mental task classification model based on the notion of transfer learning that addresses the issue of data scarcity, model selection and misclassification ratio. In the framework, the proposed model uses pre-trained network for the extraction of diverse feature and classify using support vector machine. The authors employed four pre-trained networks to identify the optimal network for the proposed framework: Vgg16, Vgg19, Resnet18 and Resnet50. The highest classification accuracy of 86.85% (using Resnet50) was achieved using transfer learning. Comparison results showed that convolutional neural network-based approach outperformed conventional machine learning approaches and hence it can be concluded that the EEG-based classification of the mental task using transfer learning model could be used in developing a superior model despite the limited data availability.
AbstractList	Electroencephalogram (EEG) measures brainwaves that have been the widely used modality for brain–computer interface (BCI) applications. EEG signal with machine learning has gained substantial success in the BCI. However, the availability of limited training data, appropriate model selection and high false‐positive rates are the challenges that need immediate attention. Therefore, in this Letter, the authors present a mental task classification model based on the notion of transfer learning that addresses the issue of data scarcity, model selection and misclassification ratio. In the framework, the proposed model uses pre‐trained network for the extraction of diverse feature and classify using support vector machine. The authors employed four pre‐trained networks to identify the optimal network for the proposed framework: Vgg16, Vgg19, Resnet18 and Resnet50. The highest classification accuracy of 86.85% (using Resnet50) was achieved using transfer learning. Comparison results showed that convolutional neural network‐based approach outperformed conventional machine learning approaches and hence it can be concluded that the EEG‐based classification of the mental task using transfer learning model could be used in developing a superior model despite the limited data availability.
Author	Singh, S Singh, D
Author_xml	– sequence: 1 givenname: D surname: Singh fullname: Singh, D email: Deepak.singh1@bennett.edu.in organization: Department of Computer Science and Engineering, Bennett University, Greater Noida 201310, India – sequence: 2 givenname: S surname: Singh fullname: Singh, S organization: Department of Computer Science and Engineering, MATS University, Raipur 492004, India
BookMark	eNp9kE9LAzEQxYMoWKs3P0AOHjy4Nf922z2qtCoUBFHwtsTspI1Nk5Jklfrp3W09iFRPMwy_N_PmHaF95x0gdErJgBJRXoIdMMLIgBWc7aEe5TnJSkpf9lGPEMqznJbiEJ3EaF4JFVQURNAe-nwEaU00boZTkC5qCNiCDG4zmQffzOZYeffubZOMd9JiB03YlPThwwJLV-PYrFY-JPwOKvmAl1LNjQOsux5caukk4wIrK9vz2ijZrTpGB1raCCfftY-eJ-Onm7ts-nB7f3M1zRQfUZEJSaWmZS2JqGsuQI2AFLUYSaBiyLguVQmMCQ1aaFJrTgkpcqaHQyYBVF7yPmLbvSr4GAPoSpm0cdB-bGxFSdUFWIGtugCrLsBWdPFLtApmKcP6Lzzf4h_GwvpfthpPp-x6Qoa8EK3ubKszkKo334Q24NgSP_BV-1Mfne_Adjr5AjQmoFk
CitedBy_id	crossref_primary_10_1109_JIOT_2022_3232481 crossref_primary_10_4018_IJBCE_301215 crossref_primary_10_1111_coin_70112 crossref_primary_10_1155_2022_6889564 crossref_primary_10_1109_ACCESS_2022_3158940 crossref_primary_10_1109_ACCESS_2021_3086807 crossref_primary_10_1109_ACCESS_2025_3571437
Cites_doi	10.1109/ICASSP.2018.8462115 10.1109/ICOSP.2004.1442216 10.1109/EMBC44109.2020.9175344 10.1109/10.64464 10.1007/s10916‐008‐9215‐z 10.1007/s00500‐014‐1443‐1 10.1109/EMBC.2019.8857359 10.1109/TSMC.2019.2917599 10.1007/978-3-030-01424-7_27 10.1109/TCDS.2020.3007453 10.1016/j.neucom.2020.07.050 10.1109/TNSRE.2003.814441
ContentType	Journal Article
Copyright	The Institution of Engineering and Technology 2020 The Institution of Engineering and Technology
Copyright_xml	– notice: The Institution of Engineering and Technology – notice: 2020 The Institution of Engineering and Technology
DBID	AAYXX CITATION
DOI	10.1049/el.2020.2632
DatabaseName	CrossRef
DatabaseTitle	CrossRef
DatabaseTitleList	CrossRef
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1350-911X
EndPage	1378
ExternalDocumentID	10_1049_el_2020_2632 ELL2BF07364
Genre	rapidPublication
GroupedDBID	0R 24P 29G 4IJ 5GY 6IK 8VB AAJGR ABPTK ABZEH ACGFS ACIWK AENEX ALMA_UNASSIGNED_HOLDINGS BFFAM CS3 DU5 ESX F5P HZ IFIPE IPLJI JAVBF KBT LAI LOTEE LXI LXO LXU M43 MS NADUK NXXTH O9- OCL P2P QWB RIE RNS RUI TN5 U5U UNMZH UNR WH7 X ZL0 ZZ -4A -~X .DC 0R~ 0ZK 1OC 2QL 3EH 4.4 8FE 8FG 96U AAHHS AAHJG ABJCF ABQXS ACCFJ ACCMX ACESK ACGFO ACXQS ADEYR ADIYS ADZOD AEEZP AEGXH AEQDE AFAZI AFKRA AI. AIAGR AIWBW AJBDE ALUQN ARAPS AVUZU BBWZM BENPR BGLVJ CCPQU EBS EJD ELQJU F8P GOZPB GROUPED_DOAJ GRPMH HCIFZ HZ~ IAO IFBGX ITC K1G K7- L6V M7S MCNEO MS~ OK1 P0- P62 PTHSS R4Z RIG VH1 ~ZZ AAMMB AAYXX AEFGJ AFFHD AGXDD AIDQK AIDYY CITATION IDLOA PHGZM PHGZT PQGLB WIN
ID	FETCH-LOGICAL-c3814-4a1af19da04dd34ec8e06d48ae14723f9c9e224fef4f0df3100652f772aeec593
IEDL.DBID	24P
ISICitedReferencesCount	9
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000604957700008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0013-5194 1350-911X
IngestDate	Wed Oct 29 21:14:12 EDT 2025 Tue Nov 18 22:27:20 EST 2025 Wed Jan 22 16:31:52 EST 2025 Wed Jan 06 06:33:42 EST 2021 Wed Jan 06 04:41:12 EST 2021
IsDoiOpenAccess	false
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	25
Keywords	brain-computer interfaces misclassification ratio Resnet50 classification accuracy diverse feature extraction brain-computer interface applications mental task classification model data scarcity optimal network feature extraction pre-trained network data availability training data conventional machine learning approaches learning (artificial intelligence) EEG-based classification electroencephalography brainwaves support vector machines model selection BCI false-positive rates EEG signal transfer learning model electroencephalogram signal classification medical signal processing Vgg19 support vector machine Resnet18 Vgg16 convolutional neural nets convolutional neural network-based approach
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c3814-4a1af19da04dd34ec8e06d48ae14723f9c9e224fef4f0df3100652f772aeec593
OpenAccessLink	https://onlinelibrary.wiley.com/doi/pdfdirect/10.1049/el.2020.2632
PageCount	4
ParticipantIDs	crossref_citationtrail_10_1049_el_2020_2632 iet_journals_10_1049_el_2020_2632 wiley_primary_10_1049_el_2020_2632_ELL2BF07364 crossref_primary_10_1049_el_2020_2632
ProviderPackageCode	RUI
PublicationCentury	2000
PublicationDate	2020-12-10
PublicationDateYYYYMMDD	2020-12-10
PublicationDate_xml	– month: 12 year: 2020 text: 2020-12-10 day: 10
PublicationDecade	2020
PublicationTitle	Electronics letters
PublicationYear	2020
Publisher	The Institution of Engineering and Technology
Publisher_xml	– name: The Institution of Engineering and Technology
References	Garrett, D.; Peterson, D.A.; Anderson, C.W. (C4) 2003; 11 Keirn, Z.A.; Aunon, J.I. (C12) 1990; 37 Zhang, L.; He, W.; He, C. (C14) 2010; 34 Gupta, A.; Khan, R.U.; Singh, V.K. (C2) 2020 Gupta, A.; Agrawal, R.K.; Kirar, J.S. (C13) 2019 Gupta, A.; Agrawal, R.K.; Kaur, B. (C5) 2015; 19 Nandish, M.; Stafford, M.; Kumar, P.H. (C3) 2012; 2 2010; 34 2019 2018 2012; 2 2004 2015; 19 1990; 37 2020 2018; 11141 2003; 11 e_1_2_5_14_2 e_1_2_5_13_2 e_1_2_5_9_2 e_1_2_5_8_2 e_1_2_5_15_2 e_1_2_5_7_2 e_1_2_5_10_2 e_1_2_5_6_2 e_1_2_5_5_2 e_1_2_5_12_2 e_1_2_5_11_2 e_1_2_5_3_2 e_1_2_5_2_2 Nandish M. (e_1_2_5_4_2) 2012; 2
References_xml	– volume: 37 start-page: 1209 issue: 12 year: 1990 end-page: 1214 ident: C12 article-title: A new mode of communication between man and his surroundings publication-title: IEEE Trans. Biomed. Eng. – volume: 11 start-page: 141 issue: 2 year: 2003 end-page: 144 ident: C4 article-title: Comparison of linear, nonlinear, and feature selection methods for EEG signal classification’ publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. – start-page: 1 year: 2019 end-page: 13 ident: C13 article-title: On the utility of power spectral techniques with feature selection techniques for effective mental task classification in noninvasive BCI publication-title: IEEE Trans. Syst. Man, Cybern. Syst. – volume: 34 start-page: 51 issue: 1 year: 2010 end-page: 60 ident: C14 article-title: Improving mental task classification by adding high frequency band information publication-title: J. Med. Syst. – volume: 2 start-page: 1 issue: 4 year: 2012 end-page: 5 ident: C3 article-title: Feature extraction and classification of EEG signal using neural network based techniques publication-title: Int. J. Eng. Innov. Technol. – start-page: 558 year: 2020 end-page: 584 ident: C2 article-title: A novel approach for classification of mental tasks using multiview ensemble learning (MEL)’ publication-title: Neurocomputing – volume: 19 start-page: 2799 issue: 10 year: 2015 end-page: 2812 ident: C5 article-title: Performance enhancement of mental task classification using EEG signal: a study of multivariate feature selection methods publication-title: Soft Comput.. – volume: 2 start-page: 1 issue: 4 year: 2012 end-page: 5 article-title: Feature extraction and classification of EEG signal using neural network based techniques publication-title: Int. J. Eng. Innov. Technol. – start-page: 2206 year: 2004 end-page: 2209 article-title: Classification of mental tasks using de‐noised EEG signals – volume: 34 start-page: 51 issue: 1 year: 2010 end-page: 60 article-title: Improving mental task classification by adding high frequency band information publication-title: J. Med. Syst. – start-page: 1 year: 2019 end-page: 13 article-title: On the utility of power spectral techniques with feature selection techniques for effective mental task classification in noninvasive BCI publication-title: IEEE Trans. Syst. Man, Cybern. Syst. – volume: 37 start-page: 1209 issue: 12 year: 1990 end-page: 1214 article-title: A new mode of communication between man and his surroundings publication-title: IEEE Trans. Biomed. Eng. – start-page: 3040 year: 2020 end-page: 3045 – start-page: 2547 year: 2019 end-page: 2550 article-title: A convolutional neural network based framework for classification of seizure types – volume: 19 start-page: 2799 issue: 10 year: 2015 end-page: 2812 article-title: Performance enhancement of mental task classification using EEG signal: a study of multivariate feature selection methods publication-title: Soft Comput.. – start-page: 558 year: 2020 end-page: 584 article-title: A novel approach for classification of mental tasks using multiview ensemble learning (MEL)’ publication-title: Neurocomputing – start-page: 1 year: 2020 end-page: 16 – start-page: 1 year: 2020 end-page: 9 – volume: 11141 start-page: 270 year: 2018 end-page: 279 article-title: A survey on deep transfer learning – volume: 11 start-page: 141 issue: 2 year: 2003 end-page: 144 article-title: Comparison of linear, nonlinear, and feature selection methods for EEG signal classification’ publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. – start-page: 916 year: 2018 end-page: 920 – ident: e_1_2_5_12_2 doi: 10.1109/ICASSP.2018.8462115 – ident: e_1_2_5_7_2 doi: 10.1109/ICOSP.2004.1442216 – ident: e_1_2_5_2_2 – ident: e_1_2_5_8_2 doi: 10.1109/EMBC44109.2020.9175344 – ident: e_1_2_5_13_2 doi: 10.1109/10.64464 – ident: e_1_2_5_15_2 doi: 10.1007/s10916‐008‐9215‐z – ident: e_1_2_5_6_2 doi: 10.1007/s00500‐014‐1443‐1 – ident: e_1_2_5_11_2 doi: 10.1109/EMBC.2019.8857359 – ident: e_1_2_5_14_2 doi: 10.1109/TSMC.2019.2917599 – ident: e_1_2_5_10_2 doi: 10.1007/978-3-030-01424-7_27 – volume: 2 start-page: 1 issue: 4 year: 2012 ident: e_1_2_5_4_2 article-title: Feature extraction and classification of EEG signal using neural network based techniques publication-title: Int. J. Eng. Innov. Technol. – ident: e_1_2_5_9_2 doi: 10.1109/TCDS.2020.3007453 – ident: e_1_2_5_3_2 doi: 10.1016/j.neucom.2020.07.050 – ident: e_1_2_5_5_2 doi: 10.1109/TNSRE.2003.814441
SSID	ssib014146041 ssj0012997
Score	2.4079998
Snippet	Electroencephalogram (EEG) measures brainwaves that have been the widely used modality for brain–computer interface (BCI) applications. EEG signal with machine...
SourceID	crossref wiley iet
SourceType	Enrichment Source Index Database Publisher
StartPage	1375
SubjectTerms	BCI brainwaves brain‐computer interface applications brain‐computer interfaces classification accuracy conventional machine learning approaches convolutional neural nets convolutional neural network‐based approach data availability data scarcity diverse feature extraction EEG signal EEG‐based classification electroencephalogram electroencephalography false‐positive rates feature extraction learning (artificial intelligence) medical signal processing mental task classification model misclassification ratio model selection optimal network pre‐trained network Resnet18 Resnet50 signal classification Special Issue: Current Trends in Cognitive Science and Brain Computing Research and Applications support vector machine support vector machines training data transfer learning model Vgg16 Vgg19
Title	Realising transfer learning through convolutional neural network and support vector machine for mental task classification
URI	http://digital-library.theiet.org/content/journals/10.1049/el.2020.2632 https://onlinelibrary.wiley.com/doi/abs/10.1049%2Fel.2020.2632
Volume	56
WOSCitedRecordID	wos000604957700008&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVWIB databaseName: Wiley Online Library Free Content customDbUrl: eissn: 1350-911X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0012997 issn: 0013-5194 databaseCode: WIN dateStart: 20130101 isFulltext: true titleUrlDefault: https://onlinelibrary.wiley.com providerName: Wiley-Blackwell – providerCode: PRVWIB databaseName: Wiley Online Library Open Access customDbUrl: eissn: 1350-911X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0012997 issn: 0013-5194 databaseCode: 24P dateStart: 20130101 isFulltext: true titleUrlDefault: https://authorservices.wiley.com/open-science/open-access/browse-journals.html providerName: Wiley-Blackwell
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3NS8MwFA9uetCD3-LUSQQ9STVt048cVTYUxhDxY7eSJi8w1Dm2uoN_vXlpne4wQby0JXlpS95HHnkvv0fIcW4MjyGNPMMMeBwY80ScKk9yLnypEpAOZ_uxk3S7aa8nbqsNNzwLU-JDTDfcUDOcvUYFl3lZhcQ6tchEDBwE7AwBx2tk0ffDFEs3BPx2GkWwptYVVwkjhkrdqxLf7fjzn6NnlqRaH4pZR9WtNO21__7jOlmtfEx6UQrFBlmAwSZZ-YE8uEU-7gCRD-0zLZzrCiNaFZCwLWXtHooZ6ZVk2tch8qW7ubxxKgeajt-H6L7Tidv6p68uMROowWd3zJIWcvxMFXromJLkpGCbPLRb91fXXlWGwVN2Oecel740vtCSca1DDioFFmueSvB5EoRGKAHWETBguGHaYMQgjgJj3XYJoCIR7pD64G0Au4RKles8SqxNMJqzVEnbr1WucpHISASqQU6_OJGpCqMcS2W8ZC5WzkUGLxnOaIYz2iAnU-phic0xh-7IMjWrlHM8h6Y5Q9PqfPdlQ20apGT0rx-yozrBZdtazZjv_XXAPlnGdkyV8dkBqRejd2iSJTUp-uPRoRNse3266X4C_Wf7uw
linkProvider	Wiley-Blackwell
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3dT9swED8NhgR7YHxq3cYwEjyhgJM6H35kExWIUCHER98ixz5LFVCqNu3D_vr5nFDoA5OmPcWK75LIvjtffOffAeyX1ooEsziw3GIgkPNAJpkOlBAyVDpF5XG27_K02816PXnV1DmlszA1PsRsw400w9trUnDakK5_OAWBZCJFDiJ-RIjjC_BROF-Dajfcn3dnYQRna311lXbMSat7Tea74z9-yz23Ji30sZr3VP1S0_n83x-5BquNl8lOarFYhw842IBPb7AHN-H3NRL2oWuzyjuvOGJNCQl3p67ewygnvZFN9zjCvvQXnznO1MCw8WRIDjyb-s1_9uRTM5FZavuDlqxS4wemyUenpCQvB1tw2zm9-XUWNIUYAu0WdBEIFSobSqO4MKYtUGfIEyMyhaFIo7aVWqJzBSxaYbmxFDNI4sg6x10h6li2t2Fx8DzAL8CULk0Zp84qWCN4ppXrN7rUpUxVLCPdgsOXqSh0g1JOxTIeCx8tF7LAx4JGtKARbcHBjHpYo3O8Q7fnZrVo1HP8Ds3OHM1p_tpXDI1tQT3Tf32R48qjnx1nNxPx9V8ZdmH57OYyL_Lz7sU3WCEaSpwJ-XdYrEYT3IElPa3649EPL-V_AK7Y_wQ
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3db9MwED9t3YTYA-NTFOgwEjyhDCe9fPgRtlVDVFU1DdS3yLHPUkUpVZvtgb9-Pid060OR0J5ixXdJ5LuzL77z7wDeV85hRkUaOekoQpIyUllhIo2oYm1y0gFn-8cwH42KyUSN2zqnfBamwYdYb7ixZYT5mg2cFtY1P5zIIJnEkYNEHjPi-C7sYZrHrNYJjtdhBD_Xhuoq_VSyVU_azHfP_-ku98aatDuletNTDUvN4PDeH_kYHrVepvjcqMUT2KH5Uzi4gz34DP5cEGMf-raog_NKS9GWkPB3muo9gnPSW930j2Psy3AJmeNCz61YXS3YgRfXYfNf_AqpmSQct8NBS1Hr1U9h2EfnpKSgB8_h--Ds8uQ8agsxRMYv6BihjrWLldUSre0jmYJkZrHQFGOe9J0yirwr4Mihk9ZxzCBLE-cdd01kUtV_AZ357zm9BKFNZas097OCsygLo32_NZWpVK5TlZgufPwritK0KOVcLGNWhmg5qpJmJY9oySPahQ9r6kWDzrGF7p2Xatma52oLTW-D5mx421d6oXahkfQ_X-S5hsmXgZ83M3z1vwxv4cH4dFAOv46-vYaHTMJ5M7F8A516eUU92DfX9XS1PApKfgO6Zv4b
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=Realising+transfer+learning+through+convolutional+neural+network+and+support+vector+machine+for+mental+task+classification&rft.jtitle=Electronics+letters&rft.au=Singh%2C+D&rft.au=Singh%2C+S&rft.date=2020-12-10&rft.pub=The+Institution+of+Engineering+and+Technology&rft.issn=0013-5194&rft.eissn=1350-911X&rft.volume=56&rft.issue=25&rft.spage=1375&rft.epage=1378&rft_id=info:doi/10.1049%2Fel.2020.2632&rft.externalDocID=10_1049_el_2020_2632
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0013-5194&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0013-5194&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0013-5194&client=summon