Sparse Bayesian Learning for Obtaining Sparsity of EEG Frequency Bands Based Feature Vectors in Motor Imagery Classification

• Published in: International journal of neural systems Vol. 27; no. 2; p. 1650032
• Main Authors: Zhang, Yu, Wang, Yu, Jin, Jing, Wang, Xingyu
• Format: Journal Article
• Language: English
• Published: Singapore 01.03.2017
• Subjects: Algorithms; Bayes Theorem; Brain - physiology; Brain-Computer Interfaces; Datasets as Topic; Discriminant Analysis; Electroencephalography - methods; Humans; Imagination - physiology; Linear Models; Machine Learning; Motor Activity - physiology; Time Factors; Brain-computer interface; motor imagery; common spatial pattern; electroencephalogram; sparse Bayesian learning; frequency band
• ISSN: 0129-0657
• DOI: 10.1142/S0129065716500325

Effective common spatial pattern (CSP) feature extraction for motor imagery (MI) electroencephalogram (EEG) recordings usually depends on the filter band selection to a large extent. Subband optimization has been suggested to enhance classification accuracy of MI. Accordingly, this study introduces a new method that implements sparse Bayesian learning of frequency bands (named SBLFB) from EEG for MI classification. CSP features are extracted on a set of signals that are generated by a filter bank with multiple overlapping subbands from raw EEG data. Sparse Bayesian learning is then exploited to implement selection of significant features with a linear discriminant criterion for classification. The effectiveness of SBLFB is demonstrated on the BCI Competition IV IIb dataset, in comparison with several other competing methods. Experimental results indicate that the SBLFB method is promising for development of an effective classifier to improve MI classification.