Study of Emotion Recognition Based on Electrocardiogram and RBF neural network

Abstract This paper compares the emotional pattern recognition method between standard BP neural network classifier and RBF neural network classifier. The experiment introduces wavelet transform to analyze the Electrocardiogram (ECG) signal, and extracts maximum and standard deviation of the wavelet coefficients in every level. Then we construct the coefficients as eigenvectors and input them into BP and RBF neural network, then take a comparison of their experimental results. The result of experiment also show that the wavelet coefficients as the eigenvector can be effective characterization of ECG. The classification of the samples with BP neural network gets overall recognition rate of 87.5%, but RBF gets overall recognition rate of 91.67%. So compared with BP neural network, RBF has a better recognition rate for emotional pattern recognition.