Mental Health Monitoring Using Deep Learning Technique for Early-Stage Depression Detection

An electroencephalogram, often known as an EEG, can detect neuronal activity by analysing the electrical currents that are generated within the brain by a collection of specific pyramidal cells as a result of the synchronised activity. EEG signal contains essential information about brain activity and is often used to diagnose and treat brain diseases such as depression and other healthcare issues. This study offers a deep learning model that is built on convolutional neural network (CNN) and bi-directional long short-term memory (Bi-LSTM), with the goal of extracting negative emotions from EEG data, such as depression. The depression recognition deep learning model (DRDL) includes segmentation, normalization, data augmentation and ensembling methods to preprocess and enhance the number of samples in EEG signals. The DRDL model employed 1D-CNN and Bi-LSTM to classify human EEG signals as Relaxed, Mild depression, Moderate depression, and Severe depression. The DRDL model achieves 91.31% and 90.12% accuracy, respectively, over binary and quaternary class labeling. Furthermore, the classification result significantly improves the performance of lower-performing subjects 1 and 23 in the DEAP dataset. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.