A discriminative subject-specific spatio-spectral filter selection approach for EEG based motor-imagery task classification

作者：

Highlights：

• A subject-specific spatio-spectral filter selection approach is presented.

• CFIS handles non-stationary EEG signals.

• Subject-wise results show superior performance over existing algorithms.

• S-CFIS and SS-CFIS achieve improvement of 15–18% over CSP and 2% over BSSFO.

摘要

•A subject-specific spatio-spectral filter selection approach is presented.•CFIS handles non-stationary EEG signals.•Subject-wise results show superior performance over existing algorithms.•S-CFIS and SS-CFIS achieve improvement of 15–18% over CSP and 2% over BSSFO.

论文关键词：Spectral filters,Band elimination,Spatiospectral filters,Non-stationarity,Interval type-2 neuro-Fuzzy inference system

论文评审过程：Received 1 November 2015, Revised 27 April 2016, Accepted 1 August 2016, Available online 3 August 2016, Version of Record 8 August 2016.

论文官网地址：https://doi.org/10.1016/j.eswa.2016.08.007