A Bayesian Framework to Optimize Double Band Spectra Spatial Filters for Motor Imagery Classification

Abstract

The ability to discriminate and classify different tasks is a crucial requirement for any Electroencephalogram (EEG) based Brain computer Interface (BCI). However, the intra and inter subject variability in the brain signal patterns is a bottleneck for developing general BCI systems and needs to be tackled. To address this issue, recently filter banks are deployed to extract frequency specific features, which are then fused at the classification step. On the other hand, some works deploy optimization techniques to design (extract) subject-specific filters (features). While both approaches have reached compromising results, there is still a huge gap between the performance of the techniques and that of humans. In this regard, we propose a Bayesian framework to simultaneously optimize a number of filter banks and spatial filters according to the patterns of brain activity for each subject. Referred to as the Bayesian double band spectro-spatial filter optimization (B2B-SSFO), the proposed method aims at combining the advantages of the two aforementioned approaches, and consists of two bandpass filters providing frequency specific features for each subject. The proposed framework is evaluated on dataset 2b from BCI Competition IV. The proposed B2B-SSFO approach outperforms its counterparts and introduces a robust framework for motor imagery studies.