AHW-BGOA-DNN: a novel deep learning model for epileptic seizure detection

Abstract

“Brain–Computer Interface” (BCI)—a real-life support system provides a way for epileptic patients to improve their quality of life. In general, epileptic seizure detection using Electroencephalogram (EEG) signals provide a significant solution in preventing seizures through medication. Thus, the design of efficient machine learning-based seizure detection model is highly acclaimed by various academic and health professionals. In a motive to address the challenges posed by the state-of-the-art techniques in terms of noise, non-stationarity, and transient nature of EEG signals, this paper presents a novel Deep Learning model for epileptic seizure detection which hybridizes Adaptive Haar Wavelet-based Binary Grasshopper Optimization Algorithm and Deep Neural Network (AHW-BGOA-DNN). The experimental analysis was carried out using three benchmark EEG datasets obtained from the University of Bonn, the University of Bern and CHB-MIT EEG database which confirm the proposed technique to be reliable and accurate over the existing state-of-the-art techniques in terms of stability analysis, classification accuracy, AUC–ROC Curve (Area Under Curve–Receiver Operating Characteristics), sensitivity, and specificity.