A Design of Bat based Optimized Deep Learning Model for EEG Signal Analysis

Abstract

Depression is one of the mental illnesses that negatively affect a person's thinking, action, and feeling. Thus the rate of depression is identified by analyzing Electroencephalogram (EEG) signals, but it has the problem of classifying depression rate because of noise. In this paper, a novel Bat-based UNET Signal Analysis (BUSA) framework is designed to organize the depression rate of patients with an EEG dataset. This technique involves preprocessing, feature selection, feature extraction, and classification. After the data training process preprocessing function was activated to remove the noise in the brain signal. Hereafter, the noiseless signal is used for the further process. Here, the fitness of the bat is upgraded in the UNET classification layer. Moreover, the brain signal's feature selection and depression rate were classified using the bat fitness that has helped to gain the desired output. Finally, performance metrics of the proposed BUSA technique are compared with other existing methods regarding the accuracy, AUC, precision, recall, and power. In that, the developed framework has attained better results to classify depression rates.