Mental Task Classification Based on HMM and BPNN

Effective feature extraction and accurate classification of EEG signals have important role in performance of Brain-Computer Interface (BCI) systems. In this paper, a mental task classification approach based on HMM and BPNN is proposed. In this approach, spectral and spatial features are extracted from the L-second epochs. Then transition matrix is calculated based on Hidden Markov Model (HMM) to reduce the feature vector dimension for each the extracted features sequence. Finally, a multi layer perceptron (MLP) neural network is used to classify and recognize the different mental task. The proposed approach is applied to classify three mental tasks (left hand movement imagination, right hand movement imagination and word generation) and it´s performance has been evaluated for some influence parameters and other existing methods.