Hybrid Depression Detection Framework Using BILSTM

Nowadays, due to mental stress, a significant section of society is affected by depression. There may be several reasons for depression, especially in adults. As a different person has different symptoms, and its identification is a significant challenge. Most people feel shy to accept that they are suffering from depression, while others are unaware of their depressed mental health. The objective of this work is to design and develop a practical tool or model to diagnose depression. In this work, a hybrid system is designed and simulated for detecting depression using EEG features, and facial features as a biological feature give an accurate diagnosis. EEG (Electroencephalogram) is the most adaptive way that can reflect the actual mental state among all biological signals.