EEG-based Mouse Cursor Control using Motor Imagery-based Brain-Computer Interface

Abstract

A brain-computer interface (BCI) framework uses computer algorithms to detect mental activity patterns and manipulate external devices. Most commonly used in imaging technologies is electroencephalography (EEG) because of its non-invasiveness. The evaluation method used in assessing the output of an EEG-based BCI system is classifying EEG signals for particular applications. In this study, we present a system of EEG-based mouse cursor control using a Motor Imagery-based Brain-Computer Interface (MI-BCI). The growth of technology and artificial intelligence inspired us to develop a system for physically impaired individuals as well as to work with electroencephalogram (EEG) signals. This signal is a noninvasive and low-cost method to extract brain signals from a subject. Our work also includes the EEG signal acquisition as well as advanced signal processing methods to utilize the MI-BCI-based brain activity. This work also includes the machine learning algorithm which carried out the system to do the successful cursor movement using binary classification. Furthermore, the successful mouse cursor movement added up the higher accuracy of 93.83% which is the result of the offline dataset.