Modifying the Classic Peak Picking Technique Using a Fuzzy Multi Agent to Have an Accurate P300-based BCI

摘要

EEG-based brain computer interface (BCI) provides a new communication channel between the human brain and a computer. The classification of EEG data is an important task in EEG-based BCI. In this paper we present a new modification on classic "Peak Picking" to make a better detection for a specific pattern in EEG. The new method shows a significant improvement in P300 detection which is a common approach in BCI systems. The proposed model uses more than one scalp electrode and combines the outputs with a fuzzy technique, to detect P300 cognitive component.