Emotion Recognition System Based on EEG Signals Using Relative Wavelet Energy Features and a Modified Radial Basis Function Neural Networks

Emotion recognition is very important, especially on its application for patient monitoring and in the treatment management system of that patient. In this paper, an EEG-based emotion recognition system is developed that consists of a feature extraction subsystem and a classifier subsystem. In this research, we have studied the utilization of a relative wavelet energy as the feature extraction, and a modified radial basis function neural networks is then implemented as the classifier. Experimental result shows that the relative wavelet energy and the modified radial basis function neural networks achieved an average recognition rate of 76% when using a 50% of the data in the training stage.