Adaptive semi-supervised classification to reduce intersession non-stationarity in multiclass motor imagery-based brain-computer interfaces

The intersession non-stationarity in electroencephalogram (EEG) data is a major issue to robust operation of brain-computer interfaces (BCIs). The aim of this paper is to propose a semi-supervised classification algorithm whereby the model is gradually enhanced with unlabeled data collected online. Additionally, a processing stage is introduced before classification to adaptively reduce the small fluctuations between the features from training and evaluation sessions. The key element of the classification algorithm is an optimized version of kernel discriminant analysis called spectral regression kernel discriminant analysis (SRKDA) in order to meet the low computational cost requirement for online BCI applications. Four different approaches, SRKDA and sequential updating semi-supervised SRKDA (SUSS-SRKDA) with or without adaptive processing stage are considered to quantify the advantages of semi-supervised learning and adaptive stage. The session-to-session performance for each of them is evaluated on the multiclass problem (four motor imagery tasks: the imagination of movement of the left hand, right hand, both feet, and tongue) posed in the BCI Competition IV dataset 2a. The results agree with previous studies reporting semi-supervised learning enhances the adaptability of BCIs to non-stationary EEG data. Moreover, we show that reducing the inter-session non-stationarity before classification further boosts its performance. The classification method combining adaptive processing and semi-supervised learning is found to yield the highest session-to session transfer results presented so far for this multiclass dataset: accuracy (77%) and Cohen?s kappa coefficient (0.70). Thus, the proposed methodology could be of great interest for real-life BCIs.

[1]  Anil K. Jain,et al.  Small Sample Size Effects in Statistical Pattern Recognition: Recommendations for Practitioners , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  James M. Lucas,et al.  Exponentially weighted moving average control schemes: Properties and enhancements , 1990 .

[3]  Gunnar Blohm,et al.  Multi-Class Motor Imagery EEG Decoding for Brain-Computer Interfaces , 2012, Front. Neurosci..

[4]  Janez Demsar,et al.  Statistical Comparisons of Classifiers over Multiple Data Sets , 2006, J. Mach. Learn. Res..

[5]  Klaus-Robert Müller,et al.  Boosting bit rates in noninvasive EEG single-trial classifications by feature combination and multiclass paradigms , 2004, IEEE Transactions on Biomedical Engineering.

[6]  Stephen J. Roberts,et al.  Adaptive BCI based on variational Bayesian Kalman filtering: an empirical evaluation , 2004, IEEE Transactions on Biomedical Engineering.

[7]  P ? ? ? ? ? ? ? % ? ? ? ? , 1991 .

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

[9]  Cuntai Guan,et al.  EEG Data Space Adaptation to Reduce Intersession Nonstationarity in Brain-Computer Interface , 2013, Neural Computation.

[10]  Clemens Brunner,et al.  Nonstationary Brain Source Separation for Multiclass Motor Imagery , 2010, IEEE Transactions on Biomedical Engineering.

[11]  G. Baudat,et al.  Generalized Discriminant Analysis Using a Kernel Approach , 2000, Neural Computation.

[12]  Wei Sun,et al.  A Semisupervised Support Vector Machines Algorithm for BCI Systems , 2007, Comput. Intell. Neurosci..

[13]  S. Coyle,et al.  Brain–computer interfaces: a review , 2003 .

[14]  Ronald Rosenfeld,et al.  Semi-supervised learning with graphs , 2005 .

[15]  Keng Peng Tee,et al.  Multi-class EEG classification of voluntary hand movement directions , 2013, Journal of neural engineering.

[16]  J. Q. Gan,et al.  Multiresolution analysis over simple graphs for brain computer interfaces , 2013, Journal of neural engineering.

[17]  Jiawei Han,et al.  Speed up kernel discriminant analysis , 2011, The VLDB Journal.

[18]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[19]  Elif Derya Übeyli,et al.  Multiclass Support Vector Machines for EEG-Signals Classification , 2007, IEEE Transactions on Information Technology in Biomedicine.

[20]  D. Yao,et al.  An Enhanced Probabilistic LDA for Multi-Class Brain Computer Interface , 2011, PloS one.

[21]  Yuanqing Li,et al.  A self-training semi-supervised SVM algorithm and its application in an EEG-based brain computer interface speller system , 2008, Pattern Recognit. Lett..

[22]  Yuanqing Li,et al.  An Online Semi-supervised Brain–Computer Interface , 2013, IEEE Transactions on Biomedical Engineering.

[23]  Stephen J. Roberts,et al.  Adaptive classification for Brain Computer Interface systems using Sequential Monte Carlo sampling , 2009, Neural Networks.

[24]  Bernhard Graimann,et al.  A comparison of common spatial patterns with complex band power features in a four-class BCI experiment , 2006, IEEE Transactions on Biomedical Engineering.

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

[26]  A. S. Rodionov,et al.  Comparison of linear, nonlinear and feature selection methods for EEG signal classification , 2004, International Conference on Actual Problems of Electron Devices Engineering, 2004. APEDE 2004..

[27]  R. Ward,et al.  EMG and EOG artifacts in brain computer interface systems: A survey , 2007, Clinical Neurophysiology.

[28]  C.W. Anderson,et al.  Comparison of linear, nonlinear, and feature selection methods for EEG signal classification , 2003, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[29]  Stefan Geyer,et al.  Imagery of voluntary movement of fingers, toes, and tongue activates corresponding body-part-specific motor representations. , 2003, Journal of neurophysiology.

[30]  José del R. Millán,et al.  Brain-Computer Interfaces , 2020, Handbook of Clinical Neurology.

[31]  Klaus-Robert Müller,et al.  Combined Optimization of Spatial and Temporal Filters for Improving Brain-Computer Interfacing , 2006, IEEE Transactions on Biomedical Engineering.

[32]  K.-R. Muller,et al.  Linear and nonlinear methods for brain-computer interfaces , 2003, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[33]  Xiaojin Zhu,et al.  --1 CONTENTS , 2006 .

[34]  Dezhong Yao,et al.  Transductive SVM for reducing the training effort in BCI , 2007, Journal of neural engineering.

[35]  Klaus-Robert Müller,et al.  Covariate Shift Adaptation by Importance Weighted Cross Validation , 2007, J. Mach. Learn. Res..

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

[37]  Heung-Il Suk,et al.  Subject and class specific frequency bands selection for multiclass motor imagery classification , 2011, Int. J. Imaging Syst. Technol..

[38]  Haixian Wang Multiclass Filters by a Weighted Pairwise Criterion for EEG Single-Trial Classification , 2011, IEEE Transactions on Biomedical Engineering.

[39]  B. Scholkopf,et al.  Fisher discriminant analysis with kernels , 1999, Neural Networks for Signal Processing IX: Proceedings of the 1999 IEEE Signal Processing Society Workshop (Cat. No.98TH8468).

[40]  J. Blumberg,et al.  Adaptive Classification for Brain Computer Interfaces , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[41]  Klaus-Robert Müller,et al.  The Berlin Brain-Computer Interface: Accurate performance from first-session in BCI-naive subjects , 2008, IEEE Transactions on Biomedical Engineering.

[42]  Jaime Gómez Gil,et al.  Brain Computer Interfaces, a Review , 2012, Sensors.

[43]  G. W. Stewart,et al.  Matrix Algorithms: Volume 1, Basic Decompositions , 1998 .

[44]  Yuanqing Li,et al.  An Extended EM Algorithm for Joint Feature Extraction and Classification in Brain-Computer Interfaces , 2006, Neural Computation.

[45]  Heung-Il Suk,et al.  Non-homogeneous spatial filter optimization for ElectroEncephaloGram (EEG)-based motor imagery classification , 2013, Neurocomputing.

[46]  Sanjoy Dasgupta,et al.  PAC Generalization Bounds for Co-training , 2001, NIPS.

[47]  Dingguo Zhang,et al.  Improved GMM with parameter initialization for unsupervised adaptation of Brain–Computer interface , 2010 .

[48]  Ramaswamy Palaniappan,et al.  Extracting optimal tempo-spatial features using local discriminant bases and common spatial patterns for brain computer interfacing , 2013, Biomed. Signal Process. Control..

[49]  Yasuharu Koike,et al.  Application of Covariate Shift Adaptation Techniques in Brain–Computer Interfaces , 2010, IEEE Transactions on Biomedical Engineering.

[50]  Maria-Florina Balcan,et al.  A PAC-Style Model for Learning from Labeled and Unlabeled Data , 2005, COLT.

[51]  Mei Han An,et al.  accuracy and stability of numerical algorithms , 1991 .

[52]  D J McFarland,et al.  Brain-computer interface research at the Wadsworth Center. , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[53]  G. Pfurtscheller,et al.  Graz-BCI: state of the art and clinical applications , 2003, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[54]  Thomas M. Cover,et al.  Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern Recognition , 1965, IEEE Trans. Electron. Comput..

[55]  K.-R. Muller,et al.  Optimizing Spatial filters for Robust EEG Single-Trial Analysis , 2008, IEEE Signal Processing Magazine.

[56]  Stephen J. Roberts,et al.  Bayesian inference for an adaptive Ordered Probit model: An application to Brain Computer Interfacing , 2011, Neural Networks.

[57]  Rajesh P. N. Rao,et al.  Towards adaptive classification for BCI , 2006, Journal of neural engineering.

[58]  Motoaki Kawanabe,et al.  Toward Unsupervised Adaptation of LDA for Brain–Computer Interfaces , 2011, IEEE Transactions on Biomedical Engineering.

[59]  J. Friedman Regularized Discriminant Analysis , 1989 .

[60]  Christian Jutten,et al.  Multiclass Brain–Computer Interface Classification by Riemannian Geometry , 2012, IEEE Transactions on Biomedical Engineering.