{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T16:57:18Z","timestamp":1782147438496,"version":"3.54.5"},"reference-count":41,"publisher":"MDPI AG","issue":"21","license":[{"start":{"date-parts":[[2022,11,5]],"date-time":"2022-11-05T00:00:00Z","timestamp":1667606400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018YFB2003201"],"award-info":[{"award-number":["2018YFB2003201"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The common spatial pattern (CSP) is a popular method in feature extraction for motor imagery (MI) electroencephalogram (EEG) classification in brain\u2013computer interface (BCI) systems. However, combining temporal and spectral information in the CSP-based spatial features is still a challenging issue, which greatly affects the performance of MI-based BCI systems. Here, we propose a novel circulant singular spectrum analysis embedded CSP (CiSSA-CSP) method for learning the optimal time-frequency-spatial features to improve the MI classification accuracy. Specifically, raw EEG data are first segmented into multiple time segments and spectrum-specific sub-bands are further derived by CiSSA from each time segment in a set of non-overlapping filter bands. CSP features extracted from all time-frequency segments contain more sufficient time-frequency-spatial information. An experimental study was implemented on the publicly available EEG dataset (BCI Competition III dataset IVa) and a self-collected experimental EEG dataset to validate the effectiveness of the CiSSA-CSP method. Experimental results demonstrate that discriminative and robust features are extracted effectively. Compared with several state-of-the-art methods, the proposed method exhibited optimal accuracies of 96.6% and 95.2% on the public and experimental datasets, respectively, which confirms that it is a promising method for improving the performance of MI-based BCIs.<\/jats:p>","DOI":"10.3390\/s22218526","type":"journal-article","created":{"date-parts":[[2022,11,7]],"date-time":"2022-11-07T03:02:22Z","timestamp":1667790142000},"page":"8526","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Learning Optimal Time-Frequency-Spatial Features by the CiSSA-CSP Method for Motor Imagery EEG Classification"],"prefix":"10.3390","volume":"22","author":[{"given":"Hai","family":"Hu","sequence":"first","affiliation":[{"name":"Department of Precision Instrument, Tsinghua University, Beijing 100084, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihang","family":"Pu","sequence":"additional","affiliation":[{"name":"Department of Precision Instrument, Tsinghua University, Beijing 100084, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haohan","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Precision Instrument, Tsinghua University, Beijing 100084, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhexian","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Precision Instrument, Tsinghua University, Beijing 100084, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Precision Instrument, Tsinghua University, Beijing 100084, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,11,5]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1016\/j.asoc.2018.11.031","article-title":"Classification of multiple motor imagery using deep convolutional neural networks and spatial filters","volume":"75","year":"2019","journal-title":"Appl. Soft Comput."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1292","DOI":"10.1109\/TNSRE.2019.2914916","article-title":"An asynchronous hybrid spelling approach based on EEG\u2013EOG signals for Chinese character input","volume":"27","author":"Yu","year":"2019","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1016\/j.compbiomed.2016.08.010","article-title":"Toward brain-actuated car applications: Self-paced control with a motor imagery-based brain-computer interface","volume":"77","author":"Yu","year":"2016","journal-title":"Comput. Biol. Med."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"715","DOI":"10.1109\/JBHI.2016.2532354","article-title":"Driver fatigue classification with independent component by entropy rate bound minimization analysis in an EEG-based system","volume":"21","author":"Chai","year":"2016","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"79826","DOI":"10.1155\/2007\/79826","article-title":"The self-paced graz brain-computer interface: Methods and applications","volume":"2007","author":"Scherer","year":"2007","journal-title":"Comput. Intell. Neurosci."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"699","DOI":"10.1109\/TNSRE.2021.3071140","article-title":"Learning common time-frequency-spatial patterns for motor imagery classification","volume":"29","author":"Miao","year":"2021","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_7","first-page":"1","article-title":"Brain Computer Interfaces, Principles and Practise","volume":"12","author":"Clerc","year":"2013","journal-title":"Biomed. Eng. Online"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"302","DOI":"10.1016\/j.bspc.2017.06.016","article-title":"Subject-specific time-frequency selection for multi-class motor imagery-based BCIs using few Laplacian EEG channels","volume":"38","author":"Yang","year":"2017","journal-title":"Biomed. Signal Process. Control."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1109\/86.895946","article-title":"Optimal spatial filtering of single trial EEG during imagined hand movement","volume":"8","author":"Ramoser","year":"2000","journal-title":"IEEE Trans. Rehabil. Eng."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2137","DOI":"10.1016\/j.patcog.2011.04.018","article-title":"Mutual information-based selection of optimal spatial\u2013temporal patterns for single-trial EEG-based BCIs","volume":"45","author":"Ang","year":"2012","journal-title":"Pattern Recognit."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1650032","DOI":"10.1142\/S0129065716500325","article-title":"Sparse Bayesian learning for obtaining sparsity of EEG frequency bands based feature vectors in motor imagery classification","volume":"27","author":"Zhang","year":"2017","journal-title":"Int. J. Neural Syst."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"3322","DOI":"10.1109\/TCYB.2018.2841847","article-title":"Temporally constrained sparse group spatial patterns for motor imagery BCI","volume":"49","author":"Zhang","year":"2018","journal-title":"IEEE Trans. Cybern."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Novi, Q., Guan, C., Dat, T.H., and Xue, P. (2007, January 2\u20135). Sub-Band Common Spatial Pattern (SBCSP) for Brain-Computer Interface. Proceedings of the 2007 3rd International IEEE\/EMBS Conference on Neural Engineering, Kohala Coast, HI, USA.","DOI":"10.1109\/CNE.2007.369647"},{"key":"ref_14","unstructured":"Ang, K.K., Chin, Z.Y., Zhang, H., and Guan, C. (2008, January 1\u20138). Filter Bank Common Spatial Pattern (FBCSP) in Brain-Computer Interface. Proceedings of the 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), Hong Kong, China."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Thomas, K.P., Guan, C., Tong, L.C., and Vinod, A.P. (2009, January 24\u201327). Discriminative FilterBank Selection and EEG Information Fusion for Brain Computer Interface. Proceedings of the 2009 IEEE International Symposium on Circuits and Systems, Taipei, Taiwan.","DOI":"10.1109\/ISCAS.2009.5118044"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.jneumeth.2015.08.004","article-title":"Optimizing spatial patterns with sparse filter bands for motor-imagery based brain\u2013computer interface","volume":"255","author":"Zhang","year":"2015","journal-title":"J. Neurosci. Methods"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"e3474","DOI":"10.7717\/peerj.3474","article-title":"An adaptive singular spectrum analysis method for extracting brain rhythms of electroencephalography","volume":"5","author":"Hu","year":"2017","journal-title":"PeerJ"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"4814","DOI":"10.1109\/TNNLS.2020.3015505","article-title":"Internal feature selection method of CSP based on L1-norm and Dempster\u2013Shafer theory","volume":"32","author":"Jin","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1016\/j.bspc.2017.11.014","article-title":"A self-adaptive frequency selection common spatial pattern and least squares twin support vector machine for motor imagery electroencephalography recognition","volume":"41","author":"Li","year":"2018","journal-title":"Biomed. Signal Process. Control."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1861","DOI":"10.1007\/s11517-018-1821-4","article-title":"A new parameter tuning approach for enhanced motor imagery EEG signal classification","volume":"56","author":"Kumar","year":"2018","journal-title":"Med. Biol. Eng. Comput."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1016\/j.irbm.2021.01.002","article-title":"Motor imagery EEG spectral-spatial feature optimization using dual-tree complex wavelet and neighbourhood component analysis","volume":"43","author":"Malan","year":"2022","journal-title":"IRBM"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"537218","DOI":"10.1155\/2013\/537218","article-title":"Common spatio-time-frequency patterns for motor imagery-based brain machine interfaces","volume":"2013","author":"Higashi","year":"2013","journal-title":"Comput. Intell. Neurosci."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"102026","DOI":"10.1016\/j.bspc.2020.102026","article-title":"Feature subset and time segment selection for the classification of EEG data based motor imagery","volume":"61","author":"Wang","year":"2020","journal-title":"Biomed. Signal Process. Control."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"109378","DOI":"10.1016\/j.jneumeth.2021.109378","article-title":"Multi-view optimization of time-frequency common spatial patterns for brain-computer interfaces","volume":"365","author":"Huang","year":"2022","journal-title":"J. Neurosci. Methods"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10916-018-0931-8","article-title":"Relevant feature selection from a combination of spectral-temporal and spatial features for classification of motor imagery EEG","volume":"42","author":"Kirar","year":"2018","journal-title":"J. Med. Syst."},{"key":"ref_26","unstructured":"Jin, J., Wang, Z., Xu, R., Liu, C., Wang, X., and Cichocki, A. (2021). Robust similarity measurement based on a novel time filter for SSVEPs detection. IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Pei, Y., Sheng, T., Luo, Z., Xie, L., Li, W., Yan, Y., and Yin, E. (2021). A Tensor-Based Frequency Features Combination Method for Brain\u2013Computer Interfaces. International Conference on Cognitive Systems and Signal Processing, Springer.","DOI":"10.1007\/978-981-16-9247-5_40"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1186\/s12859-017-1964-6","article-title":"An improved discriminative filter bank selection approach for motor imagery EEG signal classification using mutual information","volume":"18","author":"Kumar","year":"2017","journal-title":"BMC Bioinform."},{"key":"ref_29","first-page":"61","article-title":"Dimensionality Reduction for Classification and Clustering","volume":"11","author":"Singh","year":"2019","journal-title":"Int. J. Intell. Syst. Appl."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"107824","DOI":"10.1016\/j.sigpro.2020.107824","article-title":"Circulant Singular Spectrum Analysis: A new automated procedure for signal extraction","volume":"179","author":"Poncela","year":"2021","journal-title":"Signal Process."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1561\/0100000006","article-title":"Toeplitz and Circulant Matrices: A review","volume":"2","author":"Gray","year":"2006","journal-title":"Found. Trends Commun. Inf. Theory"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1016\/0167-2789(92)90103-T","article-title":"Singular-spectrum analysis: A toolkit for short, noisy chaotic signals","volume":"158","author":"Vautard","year":"1992","journal-title":"Physica D"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Xu, S., Hu, H., Ji, L., and Peng, W. (2018). Embedding Dimension Selection for Adaptive Singular Spectrum Analysis of EEG Signal. Sensors, 18.","DOI":"10.3390\/s18030697"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"498","DOI":"10.1109\/TNSRE.2017.2757519","article-title":"Filter bank regularized common spatial pattern ensemble for small sample motor imagery classification","volume":"26","author":"Park","year":"2017","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1016\/j.bspc.2009.03.005","article-title":"Adapting subject specific motor imagery EEG patterns in space\u2013time\u2013frequency for a brain computer interface","volume":"4","author":"Ince","year":"2009","journal-title":"Biomed. Signal Process. Control."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"2977","DOI":"10.1109\/JSEN.2017.2671842","article-title":"Small sample setting and frequency band selection problem solving using subband regularized common spatial pattern","volume":"17","author":"Park","year":"2017","journal-title":"IEEE Sens. J."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"767","DOI":"10.1016\/j.cmpb.2013.12.020","article-title":"Modified CC-LR algorithm with three diverse feature sets for motor imagery tasks classification in EEG based brain\u2013computer interface","volume":"113","author":"Li","year":"2014","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Ke, L., and Shen, J. (2010, January 16\u201318). Classification of EEG signals by ICA and OVR-CSP. Proceedings of the 2010 3rd International Congress on Image and Signal Processing, Yantai, China.","DOI":"10.1109\/CISP.2010.5647534"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.jneumeth.2016.12.010","article-title":"Discriminative spatial-frequency-temporal feature extraction and classification of motor imagery EEG: A sparse regression and Weighted Na\u00efve Bayesian Classifier-based approach","volume":"278","author":"Miao","year":"2017","journal-title":"J. Neurosci. Methods"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1100","DOI":"10.1109\/TBME.2012.2215960","article-title":"Simultaneous design of FIR filter banks and spatial patterns for EEG signal classification","volume":"60","author":"Higashi","year":"2012","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"1733","DOI":"10.1109\/TBME.2008.919125","article-title":"Classifying single-trial EEG during motor imagery by iterative spatio-spectral patterns learning (ISSPL)","volume":"55","author":"Wu","year":"2008","journal-title":"IEEE Trans. Biomed. Eng."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/21\/8526\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:11:10Z","timestamp":1760145070000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/21\/8526"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,5]]},"references-count":41,"journal-issue":{"issue":"21","published-online":{"date-parts":[[2022,11]]}},"alternative-id":["s22218526"],"URL":"https:\/\/doi.org\/10.3390\/s22218526","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,5]]}}}