Classification for EEG Signals Using Machine Learning Algorithm

Electroencephalography (EEG) is a non-invasive technique that is used to record the electrical activity of the brain. EEG signals are widely used in the diagnosis of various neurological and psychiatric disorders. EEG signals are complex and noisy, and thus, it is difficult to classify them accurately. In this paper, we have evaluated the performance of two popular machine learning algorithms, namely, Random Forest (RF) and Support Vector Machine (SVM), for classifying EEG signals. The performance of the algorithms was evaluated on a publicly available dataset of EEG signals. The analysis has been done on Bonn University EEG database; the analysis of methodologies signifies that the proposed improved random forest method performs superior to that of conventional random forest as well as support vector machine-based approach.