Hardware Architecture of Lifting-based Discrete Wavelet Transform and Sample Entropy for Epileptic Seizure Detection

An automated seizure detection scheme is developed by combining lifting-based discrete wavelet transform (DWT) and fast computation of sample entropy (SampEn). EEG signals are decomposed into approximation and detail coefficients using three-level DWT, and then SampEn values of the detail coefficients are computed for seizure detection using majority vote. A lifting structure of Daubechies order 4 wavelet is introduced in three-level DWT to save circuit area and speed up the computational time. Half elements of the symmetric distance matrix are stored and module reusing strategy is used to reduce the hardware resources in the proposed fast computation of SampEn architecture. The seizure detection scheme is implemented in FPGA and its classification accuracy is tested with publicly available epilepsy dataset.