Integration of Deep Learning for Improved Diagnosis of Depression using EEG and Facial Features

Abstract

Now-a-days, due to mental stress a major section of society is affected by depression. There may be several reasons for depression especially in adults. As different person has different symptoms and its identification is a major challenge. Most of the people feel shy to accept that they are suffering from depression while some people are unaware of their depressed mental health. The objective of this paper is to design and develop an effective tool or model to diagnose depression. In this work, a hybrid system is designed and simulated for detecting depression using EEG features as well as facial features as biological feature gives accurate diagnosis. In this paper a deep learning approach termed as bidirectional long short-term memory (BiLSTM) is proposed with feature fusion from EEG data as well as facial data. The result analysis shows comparative analysis with other existing model and shows effectiveness of the proposed model.