Classification of multi-class motor imagery EEG using four band common spatial pattern

Brain Computer Interfaces (BCIs) serve as an integration tool between acquired brain signals and external devices. Precise classification of the acquired brain signals with the least misclassification error is an arduous task. Existing techniques for classification of multi-class motor imagery electroencephalogram (EEG) have low accuracy and are computationally inefficient. This paper introduces a classification algorithm, which uses two frequency ranges, mu and beta rythms, for feature extraction using common spatial pattern (CSP) along with support vector machine (SVM) for classification. The technique uses only four frequency bands with no feature reduction and consequently less computational cost. The implementation of this algorithm on BCI competition III dataset IIIa, resulted in the highest classification accuracy in comparison to existing algorithms. A mean accuracy of 85.5 for offline classification has been achieved using this technique.

[1]  Ashwani Kumar Jha,et al.  SVM-Q Based Classification Method In EEG-Based Brain-Computer Interfaces , 2013 .

[2]  G. Pfurtscheller,et al.  Classification of movement-related EEG in a memorized delay task experiment , 2000, Clinical Neurophysiology.

[3]  T. Mulder.  Motor imagery and action observation: cognitive tools for rehabilitation , 2007, Journal of Neural Transmission.

[4]  B. Xiaoping,et al.  The offline feature extraction of four-class motor imagery EEG based on ICA and Wavelet-CSP , 2014, Proceedings of the 33rd Chinese Control Conference.

[5]  G. Pfurtscheller,et al.  The BCI competition III: validating alternative approaches to actual BCI problems , 2006, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[6]  Lu Wang,et al.  Classification of Four-Class Motor Imagery EEG Data Using Spatial Filtering , 2008, 2008 2nd International Conference on Bioinformatics and Biomedical Engineering.

[7]  Ruimin Wang,et al.  Classification of Four-Class Motor Imagery Employing Single-Channel Electroencephalography , 2014, PloS one.

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

[9]  Reza Ebrahimpour,et al.  EEG-based motor imagery classification using wavelet coefficients and ensemble classifiers , 2012, The 16th CSI International Symposium on Artificial Intelligence and Signal Processing (AISP 2012).

[10]  Saeid Sanei,et al.  EEG signal processing , 2000, Clinical Neurophysiology.

[11]  Yang Li,et al.  A Sparse Common Spatial Pattern Algorithm for Brain-Computer Interface , 2011, ICONIP.

[12]  G. Pfurtscheller,et al.  Motor imagery activates primary sensorimotor area in humans , 1997, Neuroscience Letters.

[13]  Songmin Jia,et al.  Multi-class imagery EEG recognition based on adaptive subject-based feature extraction and SVM-BP classifier , 2011, 2011 IEEE International Conference on Mechatronics and Automation.

[14]  Yijun Wang,et al.  Amplitude and phase coupling measures for feature extraction in an EEG-based brain–computer interface , 2007, Journal of neural engineering.

[15]  Gert Pfurtscheller,et al.  Characterization of four-class motor imagery EEG data for the BCI-competition 2005 , 2005, Journal of neural engineering.

[16]  T. Martin McGinnity,et al.  A multi-class brain-computer interface with SOFNN-based prediction preprocessing , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).