Principal Component Analysis and Discrete Wavelet Transform Based Feature Extraction for Epileptic Seizure Detection from EEG Signals

Abstract

Epilepsy is a chronic neurological disorder affecting approximately 50 million people worldwide, characterized by recurrent seizures caused by abnormal electrical activity in the brain. Early and accurate detection of epileptic seizures is crucial for effective treatment and management. This paper presents a hybrid feature extraction approach combining Principal Component Analysis (PCA) and Discrete Wavelet Transform (DWT) for automated epileptic seizure detection from electroencephalogram (EEG) signals. The proposed methodology decomposes EEG signals using DWT to extract time-frequency features, followed by dimensionality reduction using PCA to identify the most discriminative features. The extracted features are then classified using support vector machines (SVM) and artificial neural networks (ANN). Experimental results on the benchmark Bonn University EEG database demonstrate that the proposed PCA-DWT approach achieves classification accuracy of 98.67% for seizure detection, outperforming conventional methods. The hybrid approach significantly reduces computational complexity while maintaining high detection accuracy, making it suitable for real-time clinical applications.