Application of Neural Network Based on the Unscented Kalman Filter

Neural network has been widely used for nonlinear mapping, time-series estimation and classification. The unscented Kalman filter is a nonlinear parameter estimation algorithm. By means of it, weights update can be realized. In this paper a three layers neural network is used as a classification of the acupuncture EEG signals. The classifier directly classed the EEG instead of the feature values of the EEG. For almost all the subjects the classification accuracies of 100% are obtained. The numerical simulation results show the effectiveness of the algorithm.