Feature extraction using wavelet entropy and band powers in brain-computer interface

Brain-computer interface (BCI) uses brain activity for communication and control of objects in their environment without the participation of peripheral nerves and muscles. BCI technology can help improve the quality of life and restore functions for people with severe motor disabilities. We used combinations of wavelet entropy (WE) and band powers (BP) for feature extraction in BCI system which was based on imaginary left and right hand movements. Linear discriminant analysis (LDA) was used for classification and mutual information (MI) was used for evaluation because it take into account the magnitude of the outputs. This algorithm was applied on the data set III of BCI competition 2003 and got good results. The results of the experiment showed that this algorithm was a very good method for feature extraction in BCI system.