Motor imagery EEG classification based on ensemble support vector learning

BACKGROUND AND OBJECTIVE Brain-computer interfaces build a communication pathway from the human brain to a computer. Motor imagery-based electroencephalogram (EEG) classification is a widely applied paradigm in brain-computer interfaces. The common spatial pattern, based on the event-related desynchronization (ERD)/event-related synchronization (ERS) phenomenon, is one of the most popular algorithms for motor imagery-based EEG classification. Moreover, the spatiotemporal discrepancy feature based on the event-related potential phenomenon has been demonstrated to provide complementary information to ERD/ERS-based features. In this paper, aiming to improve the performance of motor imagery-based EEG classification in a few-channel situation, an ensemble support vector learning (ESVL)-based approach is proposed to combine the advantages of the ERD/ERS-based features and the event-related potential-based features in motor imagery-based EEG classification. METHODS ESVL is an ensemble learning algorithm based on support vector machine classifier. Specifically, the decision boundary with the largest interclass margin is obtained using the support vector machine algorithm, and the distances between sample points and the decision boundary are mapped to posterior probabilities. The probabilities obtained from different support vector machine classifiers are combined to make prediction. Thus, ESVL leverages the advantages of multiple trained support vector machine classifiers and makes a better prediction based on the posterior probabilities. The class discrepancy-guided sub-band-based common spatial pattern and the spatiotemporal discrepancy feature are applied to extract discriminative features, and then, the extracted features are used to train the ESVL classifier and make predictions. RESULTS The BCI Competition IV datasets 2a and 2b are employed to evaluate the performance of the proposed ESVL algorithm. Experimental comparisons with the state-of-the-art methods are performed, and the proposed ESVL-based approach achieves an average max kappa value of 0.60 and 0.71 on BCI Competition IV datasets 2a and 2b respectively. The results show that the proposed ESVL-based approach improves the performance of motor imagery-based brain-computer interfaces. CONCLUSION The proposed ESVL classifier could use the posterior probabilities to realize ensemble learning and the ESVL-based motor imagery classification approach takes advantage of the merits of ERD/ERS based feature and event-related potential based feature to improve the experimental performance.

[1]  G. Pfurtscheller,et al.  Brain–Computer Communication: Motivation, Aim, and Impact of Exploring a Virtual Apartment , 2007, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[2]  Wei Wu,et al.  Probabilistic Common Spatial Patterns for Multichannel EEG Analysis , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  S. Luck.  An Introduction to the Event-Related Potential Technique , 2005 .

[4]  Banghua Yang,et al.  Subject-based feature extraction by using fisher WPD-CSP in brain-computer interfaces , 2016, Comput. Methods Programs Biomed..

[5]  T. Martin McGinnity,et al.  Quantum Neural Network-Based EEG Filtering for a Brain–Computer Interface , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[6]  M Congedo,et al.  A review of classification algorithms for EEG-based brain–computer interfaces , 2007, Journal of neural engineering.

[7]  Ingrid Daubechies,et al.  Ten Lectures on Wavelets , 1992 .

[8]  Keiji Iramina,et al.  A Double-Partial Least-Squares Model for the Detection of Steady-State Visual Evoked Potentials , 2017, IEEE Journal of Biomedical and Health Informatics.

[9]  Keiji Iramina,et al.  Sinusoidal Signal Assisted Multivariate Empirical Mode Decomposition for Brain–Computer Interfaces , 2018, IEEE Journal of Biomedical and Health Informatics.

[10]  K. Jellinger.  Toward Brain-Computer Interfacing , 2009 .

[11]  Shuichi Nishio,et al.  Neuromagnetic Decoding of Simultaneous Bilateral Hand Movements for Multidimensional Brain–Machine Interfaces , 2018, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[12]  Na Lu,et al.  Motor imagery classification via combinatory decomposition of ERP and ERSP using sparse nonnegative matrix factorization , 2015, Journal of Neuroscience Methods.

[13]  F. L. D. Silva,et al.  Event-related EEG/MEG synchronization and desynchronization: basic principles , 1999, Clinical Neurophysiology.

[14]  Febo Cincotti,et al.  Human Movement-Related Potentials vs Desynchronization of EEG Alpha Rhythm: A High-Resolution EEG Study , 1999, NeuroImage.

[15]  Zuren Feng,et al.  Structure constrained semi-nonnegative matrix factorization for EEG-based motor imagery classification , 2015, Comput. Biol. Medicine.

[16]  Xingyu Wang,et al.  Optimized Motor Imagery Paradigm Based on Imagining Chinese Characters Writing Movement , 2016, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[17]  Wei Wu,et al.  Bayesian estimation of ERP components from multicondition and multichannel EEG , 2014, NeuroImage.

[18]  T. Ward,et al.  Brain computer interfaces for neurorehabilitation – its current status as a rehabilitation strategy post-stroke. , 2015, Annals of physical and rehabilitation medicine.

[19]  Cuntai Guan,et al.  Filter Bank Common Spatial Pattern (FBCSP) in Brain-Computer Interface , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[20]  Alok Sharma,et al.  An improved discriminative filter bank selection approach for motor imagery EEG signal classification using mutual information , 2017, BMC Bioinformatics.

[21]  Cuntai Guan,et al.  Filter Bank Common Spatial Pattern Algorithm on BCI Competition IV Datasets 2a and 2b , 2012, Front. Neurosci..

[22]  Jing Luo,et al.  Spatio-temporal discrepancy feature for classification of motor imageries , 2019, Biomed. Signal Process. Control..

[23]  Jing Luo,et al.  Class discrepancy-guided sub-band filter-based common spatial pattern for motor imagery classification , 2019, Journal of Neuroscience Methods.

[24]  Girijesh Prasad,et al.  Bispectrum-based feature extraction technique for devising a practical brain–computer interface , 2011, Journal of neural engineering.

[25]  Chao Chen,et al.  Classification of multi-class motor imagery with a novel hierarchical SVM algorithm for brain–computer interfaces , 2017, Medical & Biological Engineering & Computing.

[26]  M Congedo,et al.  A review of classification algorithms for EEG-based brain–computer interfaces: a 10 year update , 2018, Journal of neural engineering.

[27]  G. Pfurtscheller,et al.  Designing optimal spatial filters for single-trial EEG classification in a movement task , 1999, Clinical Neurophysiology.

[28]  L R Quitadamo,et al.  Support vector machines to detect physiological patterns for EEG and EMG-based human–computer interaction: a review , 2017, Journal of neural engineering.

[29]  John Platt,et al.  Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods , 1999 .

[30]  Xingyu Wang,et al.  Sparse Bayesian Learning for Obtaining Sparsity of EEG Frequency Bands Based Feature Vectors in Motor Imagery Classification , 2017, Int. J. Neural Syst..

[31]  G. Pfurtscheller,et al.  Brain-Computer Interfaces for Communication and Control. , 2011, Communications of the ACM.

[32]  Philippa J. Benson.  Decoding brain-computer interfaces , 2018 .

[33]  Haiping Lu,et al.  Regularized Common Spatial Pattern With Aggregation for EEG Classification in Small-Sample Setting , 2010, IEEE Transactions on Biomedical Engineering.

[34]  Jun Zhang,et al.  Dynamic frequency feature selection based approach for classification of motor imageries , 2016, Comput. Biol. Medicine.

[35]  Cuntai Guan,et al.  Regularizing Common Spatial Patterns to Improve BCI Designs: Unified Theory and New Algorithms , 2011, IEEE Transactions on Biomedical Engineering.

[36]  David Lee,et al.  Filter Bank Regularized Common Spatial Pattern Ensemble for Small Sample Motor Imagery Classification , 2018, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[37]  R. Leeb,et al.  BCI Competition 2008 { Graz data set B , 2008 .

[38]  Ad Aertsen,et al.  Review of the BCI Competition IV , 2012, Front. Neurosci..

[39]  Chiew Tong Lau,et al.  A New Discriminative Common Spatial Pattern Method for Motor Imagery Brain–Computer Interfaces , 2009, IEEE Transactions on Biomedical Engineering.

[40]  Ingrid Daubechies,et al.  The wavelet transform, time-frequency localization and signal analysis , 1990, IEEE Trans. Inf. Theory.

[41]  Alok Sharma,et al.  CSP-TSM: Optimizing the performance of Riemannian tangent space mapping using common spatial pattern for MI-BCI , 2017, Comput. Biol. Medicine.