Eeg Feature Extraction and Recognition with Different Mental States Based on Wavelet Transform and ACCLN Network

The electroencephalogram (EEG) is a record of brain activity. BrainComputer Interface (BCI) technology has become one of the hotspots, especiallyfor the identification of EEG characteristic signals. We here describea novel method which involves the combination of discrete wavelettransformation and neural network to recognize different states of the humanbrain, including fatigue, consciousness and concentration from EEG signal.To eliminate the high frequency noise, raw signal was preprocessed by thewavelet denoising method and was then decomposed into multi-layer highfrequency signal and low frequency signal. Thus,  wave,  wave,  wave, wave were obtained by wavelet transformation. In this experiment, thefrequency band energy of the different waves was regarded as the featuresignal of EEG for further signal processing. The feature signal was thenclassified by both radial basis function (RBF) and annealed chaotic competitivelearning network (ACCLN). The experimental results showed thatthe average accuracy of ACCLN network is 98.4%, which is much higherthan the traditional method. The results together showed the effectivenessand feasibility of the proposed method. The proposed algorithm has a goodpractical value in the analysis of the mental states of a driver or high riskoperation personnel.