Detection of epileptic spike wave in EEG signals based on wavelet transform;

Based on the delay time phase reconstruction of the chaotic dynamical system and the nonlinear characterization of the neural networks, the prediction of factual EEG signals were investigated by using the radial basis function neural networks with the adaptive projective learning algorithm.

Base on the Takens delay-coordinate phase reconstruct and the characteristic of most nonlinear-system expressed by the Volterra progression,the third-order Volterra filter which is approximately implemented by the product-coupling of FIR filter was studied,and it is used to predictions of factual high-dimensional chaotic EEG signal.

The EEG signal has the characteristic of strong randomness, nonstationarity and it is also real-time signal.

Firstly, the comparative studies of phase graph, bifurcation graph, power spectra, correlation dimension and Lyapunov exponent of EEG show that chaotic pattern.

EEG are bioelectrical activity generated by the central nervous system ,it contains a lot of the information about status and changes in the nervous system.