Chaos modeling using HMM-NRBF hybrid model approach and its application in EEG

There exists evidence that EEG signal is typical chaotic signal produced by the chaotic dynamics brain system. In this research, we propose a new method to model and predict the EEG signal based on the spatio-temporal chaotic dynamics, which is called HMM and normalized radial basis function network (NRBFNN) hybrid model. At the same time, this three-layer normalized RBF network is trained by Genetic Algorithm (GA) and Hidden Markov Model (HMM) trained by Baum-Welch Algorithm. Compared to conventional single neural network model, the new model can approximate and reveal the essential piecewise chaotic dynamics characteristics of EEG more effectively. The simulations with real EEG signal all evaluated the effectiveness of the proposed model.