A Systematic Review of EEG Signals Classification Using Machine Learning and Deep Learning Approach

AI ML Based industrial scenario is called 21 Era for medical science, here, Human brain consists of millions of neurons can cause normal and abnormal activities. So, these abnormal activities can be cause of multiple disorders such as insomnia, paralysis etc. the human been are suffering due to abnormal activities which can be recorded using EEG signals (reports). These signals are non-stationary in nature and depend on the environment, life cycle, mental status, and other various causes of human life. EEG signals are helpful for decision-making in various applications, especially in the health sector. Seizures, a critical issue of the brain such as series arise from Epilepsy. Epilepsy is one of the most common diseases affecting the largest area of the population. By the application of EEG signal it is easy to diagnose this disease. But the Manual detection of disease is still a time-consuming process. This paper provides a comprehensive study on the performance based on various Deep learning methods and also provides an overview on machine learning methods like Support Vector Machine (SVM), K-Nearest Neighbor (KNN), linear discriminant analysis (LDA), decision tree (DT).