Hybrid SSVEP/P300 BCI Keyboard - Controlled by Visual Evoked Potential

This paper presents a two stage Brain Computer Interface (BCI) keyboard system that consumes Electroencephalography (EEG) signals based on two evoked potential detection methods: P300 and Steady-State Visual Evoked Potential (SSVEP). In order to develop a practical daily use EEG system, signals were captured with a standard low cost Emotiv-EPOC system and processed using OpenViBE platform. Fast Fourier Transform (FFT) and sample average were used as feature extraction methods while Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM) were used as classifiers.