When a person has epilepsy, they will experience seizures, which are abnormal electrical discharges in the brain. Electroencephalogram (EEG) signs allow for the medical diagnosis of these seizures. People with epilepsy, a serious neurological disorder, must receive a diagnosis quickly if they are to make a full recovery. Finding out how well various classifiers predict and assist early recovery in individuals with epilepsy is the main purpose of this study. It is necessary to demodulate EEG signals before analysis due to their tiny amplitude and low frequency. Several features are extracted from the disintegrated signals that are then fed into the classifier. The dataset is split into two parts: a portion for training and another for testing. The training dataset comprises 70% of the data, while the testing dataset contains 30% less data. Epilepsy can be detected earlier with the use of this analysis. There is a 100% maximum accuracy achieved by the AdaBoosting, decision tree, and random forest classifiers in this study.