VLSI design of multiclass classification using sparse extreme learning machine for epilepsy and seizure detection

Abstract

An automatic detection system for distinguishing healthy, ictal, and inter-ictal EEG signals is of importance in clinical practice. This paper presents a low-complexity three-class classification VLSI system for epilepsy and seizure detection. The designed system consists of a discrete wavelet transform (DWT)-based feature extraction module, a sparse extreme learning machine (SELM) training module, and a multiclass classifier module. A lifting structure of Daubechies order 4 wavelet is introduced in three-level DWT to save circuit area and speed up the computational time. The SELM which is a novel machine learning algorithm with low hardware complexity and high-performance is used for on-chip training. One-against-one multiclass non-linear SELM is designed for the first time due to its high classification accuracy. The designed system is implemented on an FPGA platform and evaluated using the publicly available epilepsy dataset. The experimental results demonstrate that the designed system achieves high accuracy with low-dimensional feature vectors.