An Efficient Epileptic Seizure Detection Technique using Discrete Wavelet Transform and Machine Learning Classifiers

TL;DR

This paper introduces an efficient epilepsy detection method using discrete wavelet transform for feature extraction, PCA for feature reduction, and machine learning classifiers, achieving up to 100% accuracy on Bonn EEG datasets.

Contribution

It combines DWT, PCA, and multiple classifiers in a novel way for accurate seizure detection from EEG signals.

Findings

Achieved 100% accuracy with KNN, SVM, and Naive Bayes classifiers.

Effective feature extraction and fusion improve classification performance.

Validated on Bonn EEG database with promising results.

Abstract

This paper presents an epilepsy detection method based on discrete wavelet transform (DWT) and Machine learning classifiers. Here DWT has been used for feature extraction as it provides a better decomposition of the signals in different frequency bands. At first, DWT has been applied to the EEG signal to extract the detail and approximate coefficients or different sub-bands. After the extraction of the coefficients, principal component analysis (PCA) has been applied on different sub-bands and then a feature level fusion technique is used to extract the important features in low dimensional feature space. Three classifiers namely: Support Vector Machine (SVM) classifier, K-Nearest-Neighbor (KNN) classifier, and Naive Bayes (NB) Classifiers have been used in the proposed work for classifying the EEG signals. The proposed method is tested on Bonn databases and provides a maximum of 100% recognition accuracy for KNN, SVM, NB classifiers.