Epilepsy Detection using Ensemble Machine Learning

This paper presents an Epilepsy Detection System that utilizes ensemble machine learning models, specifically integrating Support Vector Machine (SVM) and Decision Tree algorithms. The ensemble model aims to detect epileptic seizures by classifying EEG signals, utilizing key features such as Detrended Fluctuation Analysis (DFA), Higuchi Fractal Dimension (HFD), Singular Value Decomposition (SVD) entropy, Fisher Information, and Petrosian Fractal Dimension(PFD). The integration of SVM and Decision Tree models in an ensemble framework aims to improve detection accuracy and reduce false positives. Our experimental results demonstrate that the ensemble approach outperforms individual classifiers,providing a robust solution for real-time seizure detection.