Enhanced Accuracy for Six Commands BCI System Using Hybrid ERPs/SSVEP Based Paradigm

Abstract

This study presents a hybrid brain computer interface (BCI) system that achieves better accuracy based on event related potential signals. Following system based on the P300-SSVEP hybrid sequential BCI system to decode six reactive brain commands using ensemble classifier. The device which we are using for the record of EEG data only displays the signal on the computer screen and does not decode the signal into some readable file. So in order to get EEG readable signal, we convert signal images into digital form using image processing techniques. Based on the proposed algorithm of signal conversion, we have evaluated on previous EEG dataset and results are encouraging. P300 signal is evoked by oddball paradigm using stimuli of images flicker in random order. For P300 we have used already recorded six images stimulus dataset. The feature vector is extracted from the denoised waves after filtered through least mean square (LMS) filters. Extracted feature samples are fed into ensemble classifier model for classification. To achieve high accuracy, output from ensemble classifier trigger respective SSVEP frequency stimulus. On computer screen, triggered SSVEP stimulus begin to flash. A person is asked to focus on the stimulus for several seconds. EEG signal on occipital region is recorded. After classification of SSVEP signal command is sent to drive quadcopter. For BCI application, a virtual quadcopter environment is created and controlled by proposed hybrid BCI system.