Mental task onset detection from the continuous electroencephalogram (EEG) in real time is a critical issue in self-paced brain\r\ncomputer interface (BCI) design. The paper shows that self-paced BCI performance can be significantly improved by combining\r\na range of simple techniques including (1) constant-Q filters with varying bandwidth size depending on the center frequency,\r\ninstead of constant bandwidth filters for frequency decomposition of the EEG signal in the 6 to 36Hz band; (2) subjectspecific\r\npostprocessing parameter optimization consisting of dwell time and threshold, and (3) debiasing before postprocessing by\r\nreadjusting the classification output based on the current and previous brain states, to reduce the number of false detections. This\r\ndebiasing block is shown to be optimal when activated only in special cases which are predetermined during the training phase.\r\nAnalysis of the data recorded from seven subjects executing foot movement shows a statistically significant 10% (P < 0.05) average\r\nimprovement in true positive rate (TPR) and a 1% reduction in false positive rate (FPR) detections compared with previous work\r\non the same data.
Loading....