P300-based Brain–Computer Interface with Latency Estimation Using ABC-based Interval Type-2 Fuzzy Logic System

摘要: P300 is a brain–computer interface (BCI) modality which reflects brains’ processes in stimulus events. Visual stimuli are usually used to elicit event-related components. However, depending on different subjects’ conditions and their current cerebral loads, components occur at posterior from 250 600 ms roughly. These dependent variations affect the performance of BCI. Thus, an estimation model that estimated appropriate interval for feature extraction discussed this paper. An type-2 fuzzy logic system trained by artificial bee-colony algorithm was find latency elicited with certain range means steady-state visually evoked potential. A support vector machine classifier adopted classify extracted epochs into target non-target stimuli. Seven subjects were involved experiments. Results showed information transfer rate improved 1.28 % average if proposed latency-estimation approach introduced.