EEG Signal Classification using Unsupervised and Supervised Machine Learning Algorithm

This work aims to develop a robust classification system for EEG signals to differentiate between ictal, inter-ictal, and pre-ictal stages, essential for accurate epilepsy diagnosis and management. Leveraging advanced machine learning techniques and signal processing methodologies, the work focuses on preprocessing and analyzing EEG data to extract pertinent features that capture the unique patterns associated with each stage. Utilizing classification algorithms such as Random Forest and K-means clustering, EEG segments are categorized into the corresponding stages based on the extracted features. The proposed classification system is subjected to comprehensive evaluation using performance metrics, including accuracy, precision, and recall, to assess its effectiveness and reliability in stage detection. The outcomes of this project hold substantial potential for enhancing the accuracy and efficiency of epilepsy diagnosis. Identifying the pre-ictal stage will make it easy for predicting the on-set of a seizure, contributing to improved patient care and quality of life.