Performance Analysis of Random Forest Classifier in Extracting Features from the EEG signal

Abstract

Epilepsy is a disorder and is identified by baseless seizures that have been associated with unexpected improper neural discharges which result in various health issues and also result in death. One of the most common methods in monitoring and detecting contraction seizures is an electroencephalogram. But it is highly affordable and requires increased temporal resolution. EEG (electroencephalogram) is a commonly used method for monitoring and detecting seizures. The prevalence of EEG seizure detection has increased due to the increasing number of researchers who are focused on developing automated methods to detect the abnormalities in the EEG signals. But, it requires higher temporal resolution and is typically only available for a limited amount of time. Through machine learning, it is possible to extract the details of EEG signals that can help detect seizures. In this paper, the performance analysis is performed under various classifiers such as Random Forest, Gaussian Boosting, and AdaBoost. The results show that Random Forest is the most accurate classifier for achieving high degree of accuracy.