ESEEG: An Efficient Epileptic Seizure Detection using EEG signals based on Machine Learning Algorithms

Epileptic seizure Disease is a substantial health burden and cause of death worldwide. For epileptic seizure localization and classification,It's critical to be able to detect recorded epileptic seizure activity in EEG segments. Seizure progression is usually a dynamic and non-stationary process involving signals of multiple frequency., therefore visual and traditional frequency-based techniques are restricted in their utility. Researchers are attempting to integrate artificial intelligence (AI) and machine learning (ML) approaches to improve medical practise as a result of advancements in AI and ML methodology. Early disease identification and prediction is a critical goal in healthcare in order to provide timely preventive actions. This is especially true in the case of epilepsy, which is characterised by frequent and unexpected convulsions. We present a comprehensive overview of existing machine learning strategies for early seizure prediction using EEG data. We will highlight the research's shortcomings, difficulties, and pitfalls, as well as make recommendations for future directions. The following findings (accuracy) were obtained: KNN : 94%, Decision Tree : 94%, Random forrest: 96%, and Convolutional Neural Network (CNN) : 96.9%