LITERATURE SURVEY ON CLASSIFICATION OF BODY PARTS USING EEG SIGNAL

The brain plays a central role in linking biological processes with psychological functions, making the study of human activity crucial for health and well-being. Various neuroimaging approaches have been developed to monitor brain activity, aiming to reduce processing time, enhance accuracy, and increase control capabilities. Motor Imagery (MI)-based Brain-Computer Interface (BCI) systems allow the brain to communicate with external devices by analyzing Electroencephalogram (EEG) signals. Human Activity Recognition (HAR) focuses on identifying human physiological activities using sensor-based data. This survey provides an overview of HAR approaches that utilize MI-EEG signals, reviewing 50 research articles in the field. It examines the challenges faced by different methods and evaluates studies based on criteria such as techniques employed, publication year, performance metrics, tools, and datasets. The reviewed approaches are broadly categorized into Machine Learning (ML) and Deep Learning (DL) models. Finally, research gaps and limitations are discussed to guide the development of more robust and efficient HAR systems.