An approach to EEG based BCI for motor imagery using time-frequency representation and CNN

In this contribution, we use electroencephalography for brain-computer interface and focus on two-class recognition of motor imagery data. We present a method with various modifications based on convolutional neural networks, we focus on time-frequency re8presentation of data. We use Short-Time Fourier Transform and Continuous Wavelet Transform. The method and its variation are tested on selected dataset and evaluated using cross-validation setup. The results show competitiveness of this method.