Enhancing P300 wave of BCI systems via Ngentropy in Adaptive Wavelet denoising

Abstract

Abstract Brian Computer interface (BCI) is a direct communication pathway between the brain and an external device. BCIs are often aimed at assisting, augmenting or repairing human cognitive or sensory-motor functions. In this work a new algorithm is introduced to enhancing EEG signals that have been concerned the P300 problem. Signal to noise ratio of EEG signals is very low and have  much artifacts. We have proposed a new method based on multiresolution  analysis via Independent Component Analysis Fundamentals.  We have suggest combination of negentropy  as a feature of signal and subband information from wavelet transform . The proposed method is finally tested with dataset from BCI Competition 2003 and gives results that compare favorably.