Literature Review on EEG Preprocessing, Feature Extraction, and Classifications Techniques

Classification is one of the main applications of machine learning, which can group and classify the cases based on learning and development using the available data and experience knowledge. Classification is used widely in biological and medical aspects. This paper presents the problem of electroencephalogram (EEG) signal classification. Classification is the step of identifying groups or classes based on similarities between them. This step is essential to differentiate between seizure and normal periods. EEG is a monitoring tool to determine the electrical activity of the brain. The nature of EEG is quite long, so it consumes time and very difficult in processing. Epilepsy is an illness that affects people of all ages, both cases males and females. Epilepsy is a neurological disorder that makes the activities of the brain abnormal and generates seizures. Seizure symptoms vary from one people to another; it depends on the location of epileptic discharge in the cortex. To speed up the classification process and make it efficient, EEG signal needs to be preprocessed. This paper reviews the epilepsy mentality disorder and the types of seizure, preprocessing operations that performed on EEG data, a common extracted feature from the signal, and detailed view on classification techniques that can be used in this problem.