{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T19:58:24Z","timestamp":1780775904755,"version":"3.54.1"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"16","license":[{"start":{"date-parts":[[2023,2,19]],"date-time":"2023-02-19T00:00:00Z","timestamp":1676764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,2,19]],"date-time":"2023-02-19T00:00:00Z","timestamp":1676764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001775","name":"University of Technology Sydney","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001775","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2023,6]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>In recent years, there has been a renewal of interest in brain\u2013computer interface (BCI). One of the BCI tasks is to classify the EEG motor imagery (MI). A great deal of effort has been made on MI classification. What seems to be lacking, however, is multiple MI classification. This paper develops a single-channel-based convolutional neural network to tackle multi-classification motor imagery tasks. For multi-classification, a single-channel learning strategy can extract effective information from each independent channel, making the information between adjacent channels not affect each other. A data evaluation method and a mutual information-based regularization parameters auto-selection algorithm are also proposed to generate effective spatial filters. The proposed method can be used to tackle the problem of an inaccurate mixed covariance matrix caused by fixed regularization parameters and invalid training data. To illustrate the merits of the proposed methods, we used the tenfold cross-validation accuracy and kappa as the evaluation measures to test two data sets. BCI4-2a and BCI3a data sets have four mental classes. For the BCI4-2a data set, the average accuracy is 79.01%, and the kappa is 0.7202 using data evaluation-based auto-selected filter bank regularized common spatial pattern voting (D-ACSP-V) and single-channel series convolutional neural network (SCS-CNN). Compared to traditional FBRCSP, the proposed method improved accuracy by 7.14% for the BCI4-2a data set. By using the BCI3a data set, the proposed method improved accuracy by 9.54% compared with traditional FBRCSP, the average accuracy of the proposed method is 83.70%, and the kappa is 0.7827.<\/jats:p>","DOI":"10.1007\/s00521-023-08336-z","type":"journal-article","created":{"date-parts":[[2023,2,23]],"date-time":"2023-02-23T17:15:11Z","timestamp":1677172511000},"page":"12001-12027","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":41,"title":["Multi-classification for EEG motor imagery signals using data evaluation-based auto-selected regularized FBCSP and convolutional neural network"],"prefix":"10.1007","volume":"35","author":[{"given":"Yang","family":"An","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hak Keung","family":"Lam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0849-5098","authenticated-orcid":false,"given":"Sai Ho","family":"Ling","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,2,19]]},"reference":[{"key":"8336_CR1","doi-asserted-by":"crossref","unstructured":"Trad D, Al-ani T, Jemni M (2015) A feature extraction technique of EEG based on EMD-BP for motor imagery classification in BCI. In: 2015 5th international conference on information & communication technology and accessibility (ICTA), pp 1\u20136","DOI":"10.1109\/ICTA.2015.7426931"},{"key":"8336_CR2","doi-asserted-by":"crossref","unstructured":"Wu Y, Huang TH, Lin CY, Tsai SJ, Wang P (2018) Classification of EEG motor imagery using support vector machine and convolutional neural network. In: 2018 international automatic control conference (CACS), pp 1\u20134","DOI":"10.1109\/CACS.2018.8606765"},{"key":"8336_CR3","doi-asserted-by":"crossref","unstructured":"Li S, Feng H (2019) EEG signal classification method based on feature priority analysis and CNN. In: 2019 international conference on communications, information system and computer engineering (CISCE), pp 403\u2013406","DOI":"10.1109\/CISCE.2019.00095"},{"key":"8336_CR4","doi-asserted-by":"publisher","first-page":"132720","DOI":"10.1109\/ACCESS.2019.2941867","volume":"7","author":"D Li","year":"2019","unstructured":"Li D, Wang J, Xu J, Fang X (2019) Densely feature fusion based on convolutional neural networks for motor imagery EEG classification. IEEE Access 7:132720\u2013132730","journal-title":"IEEE Access"},{"key":"8336_CR5","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2012.00039","author":"KK Ang","year":"2012","unstructured":"Ang KK, Chin ZY, Wang C, Guan C, Zhang H (2012) Filter bank common spatial pattern algorithm on BCI competition IV datasets 2a and 2b. Front Neurosci. https:\/\/doi.org\/10.3389\/fnins.2012.00039","journal-title":"Front Neurosci"},{"key":"8336_CR6","doi-asserted-by":"publisher","first-page":"101749","DOI":"10.1016\/j.bspc.2019.101749","volume":"57","author":"A Jafarifarmand","year":"2020","unstructured":"Jafarifarmand A, Badamchizadeh MA (2020) Real-time multiclass motor imagery brain-computer interface by modified common spatial patterns and adaptive neuro-fuzzy classifier. Biomed Signal Process Control 57:101749","journal-title":"Biomed Signal Process Control"},{"key":"8336_CR7","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1007\/s11063-012-9228-y","volume":"36","author":"H Wang","year":"2012","unstructured":"Wang H (2012) Harmonic mean of Kullback\u2013Leibler divergences for optimizing multi-class eeg spatio-temporal filters. Neural Process Lett 36:161\u2013171. https:\/\/doi.org\/10.1007\/s11063-012-9228-y","journal-title":"Neural Process Lett"},{"key":"8336_CR8","doi-asserted-by":"crossref","unstructured":"Li M, Lin L, Yang J-F (2011) Adaptive feature extraction of four-class motor imagery EEG based on best basis of wavelet packet and CSP. In: 2011 international conference on electric information and control engineering, pp 3918\u20133921","DOI":"10.1109\/ICEICE.2011.5777773"},{"key":"8336_CR9","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1016\/j.jneumeth.2016.12.010","volume":"278","author":"M Miao","year":"2017","unstructured":"Miao M, Zeng H, Wang A, Zhao C, Liu F (2017) Discriminative spatial-frequency-temporal feature extraction and classification of motor imagery EEG: an sparse regression and Weighted Na\u00efve Bayesian Classifier-based approach. J Neurosci Methods 278:13\u201324","journal-title":"J Neurosci Methods"},{"key":"8336_CR10","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1016\/j.eswa.2017.11.007","volume":"95","author":"P Gaur","year":"2018","unstructured":"Gaur P, Pachori RB, Wang H, Prasad G (2018) A multi-class EEG-based BCI classification using multivariate empirical mode decomposition based filtering and Riemannian geometry. Expert Syst Appl 95:201\u2013211","journal-title":"Expert Syst Appl"},{"key":"8336_CR11","unstructured":"Lu H, Plataniotis KN, Venetsanopoulos AN (2009) Regularized common spatial patterns with generic learning for EEG signal classification. In: 2009 annual international conference of the IEEE engineering in medicine and biology society, pp 6599\u20136602"},{"key":"8336_CR12","doi-asserted-by":"publisher","first-page":"2936","DOI":"10.1109\/TBME.2010.2082540","volume":"57","author":"H Lu","year":"2010","unstructured":"Lu H, Eng H, Guan C, Plataniotis KN, Venetsanopoulos AN (2010) Regularized common spatial pattern with aggregation for EEG classification in small-sample setting. IEEE Trans Biomed Eng 57:2936\u20132946","journal-title":"IEEE Trans Biomed Eng"},{"key":"8336_CR13","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1109\/TNSRE.2017.2757519","volume":"26","author":"SH Park","year":"2018","unstructured":"Park SH, Lee D, Lee SG (2018) Filter bank regularized common spatial pattern ensemble for small sample motor imagery classification. IEEE Trans Neural Syst Rehabil Eng 26:498\u2013505","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"key":"8336_CR14","doi-asserted-by":"publisher","first-page":"2977","DOI":"10.1109\/JSEN.2017.2671842","volume":"17","author":"S Park","year":"2017","unstructured":"Park S, Lee S (2017) Small sample setting and frequency band selection problem solving using subband regularized common spatial pattern. IEEE Sens J 17:2977\u20132983","journal-title":"IEEE Sens J"},{"key":"8336_CR15","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1109\/TNSRE.2006.875642","volume":"14","author":"B Blankertz","year":"2006","unstructured":"Blankertz B, Muller KR, Krusienski DJ, Schalk G, Wolpaw JR, Schlogl A, Pfurtscheller G, Millan JR, Schroder M, Birbaumer N (2006) The BCI competition III: validating alternative approaches to actual BCI problems. IEEE Trans Neural Syst Rehabil Eng 14:153\u2013159","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"key":"8336_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/JTEHM.2015.2485261","volume":"3","author":"H Baali","year":"2015","unstructured":"Baali H, Khorshidtalab A, Mesbah M, Salami MJE (2015) A transform-based feature extraction approach for motor imagery tasks classification. IEEE J Transl Eng Health Med 3:1\u20138","journal-title":"IEEE J Transl Eng Health Med"},{"key":"8336_CR17","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1016\/j.bspc.2016.12.006","volume":"33","author":"A Khorshidtalab","year":"2017","unstructured":"Khorshidtalab A, Salami MJE, Akmeliawati R (2017) Motor imagery task classification using transformation based features. Biomed Signal Process Control 33:213\u2013219","journal-title":"Biomed Signal Process Control"},{"key":"8336_CR18","doi-asserted-by":"publisher","first-page":"036019","DOI":"10.1088\/1741-2552\/aa61bb","volume":"14","author":"A Davoudi","year":"2017","unstructured":"Davoudi A, Ghidary SS, Sadatnejad K (2017) Dimensionality reduction based on distance preservation to local mean for symmetric positive definite matrices and its application in brain\u2013computer interfaces. J Neural Eng IOP Publishing 14:036019. https:\/\/doi.org\/10.1088\/1741-2552\/aa61bb","journal-title":"J Neural Eng IOP Publishing"},{"key":"8336_CR19","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1109\/TNSRE.2016.2587939","volume":"25","author":"X Xie","year":"2017","unstructured":"Xie X, Yu ZL, Lu H, Gu Z, Li Y (2017) Motor imagery classification based on bilinear sub-manifold learning of symmetric positive-definite matrices. IEEE Trans Neural Syst Rehabil Eng 25:504\u2013516","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"key":"8336_CR20","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1016\/j.asoc.2018.11.031","volume":"75","author":"BE Olivas-Padilla","year":"2019","unstructured":"Olivas-Padilla BE, Chacon-Murguia MI (2019) Classification of multiple motor imagery using deep convolutional neural networks and spatial filters. Appl Soft Comput 75:461\u2013472","journal-title":"Appl Soft Comput"},{"key":"8336_CR21","doi-asserted-by":"publisher","first-page":"2854","DOI":"10.3390\/s19132854","volume":"19","author":"K-W Ha","year":"2019","unstructured":"Ha K-W, Jeong J-W (2019) Motor imagery EEG classification using capsule networks. Sensors 19:2854","journal-title":"Sensors"},{"key":"8336_CR22","doi-asserted-by":"publisher","first-page":"5391","DOI":"10.1002\/hbm.23730","volume":"38","author":"RT Schirrmeister","year":"2017","unstructured":"Schirrmeister RT, Springenberg JT, Fiederer LDJ, Glasstetter M, Eggensperger K, Tangermann M, Hutter F, Burgard W, Ball T (2017) Deep learning with convolutional neural networks for EEG decoding and visualization. Hum Brain Mapp 38:5391\u20135420. https:\/\/doi.org\/10.1002\/hbm.23730","journal-title":"Hum Brain Mapp"},{"key":"8336_CR23","doi-asserted-by":"publisher","first-page":"2164","DOI":"10.1109\/TNSRE.2019.2938295","volume":"27","author":"X Zhao","year":"2019","unstructured":"Zhao X, Zhang H, Zhu G, You F, Kuang S, Sun L (2019) A multi-branch 3D convolutional neural network for EEG-based motor imagery classification. IEEE Trans Neural Syst Rehabil Eng 27:2164\u20132177","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"key":"8336_CR24","doi-asserted-by":"publisher","first-page":"5619","DOI":"10.1109\/TNNLS.2018.2789927","volume":"29","author":"S Sakhavi","year":"2018","unstructured":"Sakhavi S, Guan C, Yan S (2018) Learning temporal information for brain-computer interface using convolutional neural networks. IEEE Trans Neural Netw Learn Syst 29:5619\u20135629","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"8336_CR25","doi-asserted-by":"publisher","first-page":"715","DOI":"10.1109\/LSP.2019.2906824","volume":"26","author":"D Zhang","year":"2019","unstructured":"Zhang D, Yao L, Chen K, Monaghan J (2019) A convolutional recurrent attention model for subject-independent EEG signal analysis. IEEE Signal Process Lett 26:715\u2013719","journal-title":"IEEE Signal Process Lett"},{"key":"8336_CR26","doi-asserted-by":"publisher","first-page":"49192","DOI":"10.1109\/ACCESS.2018.2868178","volume":"6","author":"S Selim","year":"2018","unstructured":"Selim S, Tantawi MM, Shedeed HA, Badr A (2018) A CSP\\AM-BA-SVM approach for motor imagery BCI system. IEEE Access 6:49192\u201349208","journal-title":"IEEE Access"},{"key":"8336_CR27","doi-asserted-by":"publisher","first-page":"2461","DOI":"10.1109\/TNSRE.2017.2726779","volume":"25","author":"D Rathee","year":"2017","unstructured":"Rathee D, Raza H, Prasad G, Cecotti H (2017) Current source density estimation enhances the performance of motor-imagery-related brain\u2013computer interface. IEEE Trans Neural Syst Rehabil Eng 25:2461\u20132471","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"key":"8336_CR28","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1016\/j.bspc.2017.06.016","volume":"38","author":"Y Yang","year":"2017","unstructured":"Yang Y, Chevallier S, Wiart J, Bloch I (2017) Subject-specific time-frequency selection for multi-class motor imagery-based BCIs using few Laplacian EEG channels. Biomed Signal Process Control 38:302\u2013311","journal-title":"Biomed Signal Process Control"},{"key":"8336_CR29","doi-asserted-by":"crossref","unstructured":"An Y, Hu T, Wang J, Lyu J, Banerjee S, Ling SH (2019) Lung nodule classification using a novel two-stage convolutional neural networks structure. In: 2019 41st annual international conference of the IEEE engineering in medicine and biology society (EMBC), pp 6259\u20136262","DOI":"10.1109\/EMBC.2019.8857744"},{"key":"8336_CR30","unstructured":"Brunner C, Leeb R, M\u00fcller-Putz G, Schl\u00f6gl A, Pfurtscheller G (2008) BCI competition 2008\u2013Graz data set A. In: Institute for knowledge discovery (laboratory of brain-computer interfaces), Graz University of Technology, pp 1\u20136"},{"key":"8336_CR31","unstructured":"Blankertz B, M\u00fcller K-R, Krusienski D, Schalk G, Wolpaw JR, Schl\u00f6gl A, Pfurtscheller G, Mill\u00e1n JdR, Schr\u00f6der M, Birbaumer N (2005) Bci competition iii. Fraunhofer FIRST. IDA, http:\/\/ida.first.fraunhofer.de\/projects\/bci\/competition_iii"},{"key":"8336_CR32","doi-asserted-by":"publisher","first-page":"276","DOI":"10.11613\/BM.2012.031","volume":"22","author":"ML McHugh","year":"2012","unstructured":"McHugh ML (2012) Interrater reliability: the kappa statistic. Biochem Med 22:276\u2013282","journal-title":"Biochem Med"},{"key":"8336_CR33","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1016\/j.ejor.2017.11.054","volume":"270","author":"T Fischer","year":"2018","unstructured":"Fischer T, Krauss C (2018) Deep learning with long short-term memory networks for financial market predictions. Eur J Oper Res 270:654\u2013669","journal-title":"Eur J Oper Res"},{"key":"8336_CR34","doi-asserted-by":"publisher","first-page":"883","DOI":"10.1007\/s11869-018-0585-1","volume":"11","author":"U Pak","year":"2018","unstructured":"Pak U, Kim C, Ryu U, Sok K, Pak S (2018) A hybrid model based on convolutional neural networks and long short-term memory for ozone concentration prediction. Air Qual Atmos Health 11:883\u2013895. https:\/\/doi.org\/10.1007\/s11869-018-0585-1","journal-title":"Air Qual Atmos Health"},{"key":"8336_CR35","doi-asserted-by":"crossref","unstructured":"Auria L, Moro RA (2008) Support vector machines (SVM) as a technique for solvency analysis","DOI":"10.2139\/ssrn.1424949"},{"key":"8336_CR36","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1080\/01431160412331269698","volume":"26","author":"M Pal","year":"2005","unstructured":"Pal M (2005) Random forest classifier for remote sensing classification. Int J Remote Sens 26:217\u2013222","journal-title":"Int J Remote Sens"},{"key":"8336_CR37","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Identity mappings in deep residual networks. In: Computer vision\u2014ECCV 2016, Springer International Publishing, pp 630\u2013645","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"8336_CR38","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"8336_CR39","doi-asserted-by":"crossref","unstructured":"Mesbah M, Khorshidtalab A, Baali H, Al-Ani A (2015) Motor imagery task classification using a signal-dependent orthogonal transform based feature extraction. In: Neural Information Processing. Springer, Cham, pp 1\u20139","DOI":"10.1007\/978-3-319-26535-3_1"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08336-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-023-08336-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-023-08336-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,11]],"date-time":"2023-05-11T17:20:32Z","timestamp":1683825632000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-023-08336-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,19]]},"references-count":39,"journal-issue":{"issue":"16","published-print":{"date-parts":[[2023,6]]}},"alternative-id":["8336"],"URL":"https:\/\/doi.org\/10.1007\/s00521-023-08336-z","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,19]]},"assertion":[{"value":"3 June 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 January 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 February 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors declare that they have no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}