Brain-Computer Interface System of Steady-State Visual Evoked Potentials Based on Fractional Domain Features

In this paper, a Brain-Computer Interface (BCI) based on Steady-State Visual Evoked Potential (SSVEP) is designed. In order to improve the accuracy of model classification with small sample size fractional Fourier transform is used to replace the Fourier transform in the Mel-Frequency Cepstral Coefficients. The improved features are used to train the Hidden Markov Models. Improved accuracy by 3% in offline tests. In the actual experiment, the recognition accuracy of the volunteers reached 90%. The information transform rate (ITR) reaches 42bits/min.