A Statistical Summary Analysis of Window-Based Extracted Features for EEG Signal Classification

Abstract

Epilepsy is a common chronic neurological disorder affecting approximately 50 million people worldwide. The electroencephalogram (EEG) signal, which contains valuable information of electrical activity in the brain, is a standard neuroimaging tool used by clinicians to monitor and diagnose epilepsy. Visually inspecting the EEG signal is an expensive, tedious, and error-prone practice. Moreover, the result can be varied with different neurophysiologists for an identical reading. Thus, automatically classify different epileptic states with a high accuracy rate is an urgent requirement and has long been investigated. In this paper, we propose a novel framework to effectively classify epilepsy leveraging summary statistics analysis of window-based features of EEG signals. The framework first denoised the signals using power spectrum density analysis, replaced outliers with k-NN imputer, and then window level features extracted from statistical, temporal, and spectral domains. Basic summary statistics are then computed from the extracted features to feed into different Machine Learning (ML) classifiers. An optimal set of features are selected leveraging variance thresholding and dropping correlated features before feeding the features for classification. Finally, different ML classifiers such as Support Vector Machine, Decision Tree, Random Forest, and k-Nearest Neighbors classifiers are applied to the extracted features. The proposed framework applying the Random Forest classifier can significantly enhance the EEG signal classification performance compared to other existing state-of-the-art epilepsy classification methods in terms of accuracy, precision, recall, and F-beta score.