Brain-computer interface design using relative wavelet energy

A brain-computer interface (BCI) is a communication system that translates brain-activity into commands for a computer or other devices. In this paper, we used a new method: relative wavelet energy (RWE) for feature selection in BCI design. Linear discriminant analysis (LDA) and support vector machine (SVM) were utilized to classify the pattern of left and right hand movement imagery. Its performance was evaluated by mutual information (MI) using the data set III of BCI competition 2003. From the results of the experiment, we can get that RWE is a very good method for feature selection in BCI research and there is not much difference between LDA and SVM.