VLSI implementation for Epileptic Seizure Prediction System based on Wavelet and Chaos Theory

Abstract

This paper presents a very large scale integration (VLSI) circuit implementation for Epileptic Seizure Prediction System based combination of wavelet and chaos theory. The system consists with operation units of discrete wavelet transform (DWT), correlation dimension ( CD), and correlation coefficient. This work discovered by certain bandwidth of signal extraction with DWT, and the combination with Chaotic features analysis, it can achieve a higher accuracy of epileptic prediction. Furthermore, the correlation coefficient between two correlation dimensions with different embedding dimensions was proposed as a novel feature for epileptic seizure prediction in this study. The proposed system was evaluated with intracranial Electrocorticography (ECoG) recordings from a set of eleven patients with refractory temporal lobe epilepsy (TLE). The accuracy of experiment result for all subjects can achieve 87%, and a false prediction rate is 0.24/h. In average warning time occur about 27 min ahead the ictal.