BUSA Deep Learning Model for EEG Signal Analysis

Depression, a debilitating mental illness, profoundly impacts an individual’s cognition, behaviour, and emotions. Despite efforts to quantify depression rates through electro-encephalo-gram (EEG) signal analysis, classification remains challenging due to inherent noise. This paper introduces a Bat based UNET signal analysis, aimed at accurately classifying depression rates using a normal EEG dataset. It comprises of pre-processing, feature extraction, feature selection, and classification stages. The framework excels at noise reduction during pre-processing, enhancing dataset integrity. Feature extraction leverages band power and correlation dimension to extract crucial features. Furthermore, feature selection optimizes classification accuracy by refining the fitness function of bats in the classification layer. Utilizing a standardized EEG dataset implemented in Matrix Laboratory (MATLAB), the proposed technique demonstrates superior performance compared to existing methods, as evidenced by metrics such as accuracy, area under the curve, precision, and recall (or sensitivity). This innovative framework represents a significant advancement in the classification of depression rates.