A Review on IoT-Cloud based EEG Depression Detection System: A Case Study

Abstract

A debilitating mental disease, major depressive disorder (MDD), may develop functional impairments and become a social problem. An accurate and early diagnosis of depression may be difficult. Automated systems to help human lives thrive with the development of machine learning technology, especially deep learning. In this paper, we suggest a method based on deeper learning to identify automated electroencephalograms (EEGs). Firstly, as a time/space representation, the raw EEG data is processed. The EEG signal’s spatial-temporal structure is the input into a convolutional neural network (CNN). Using transfer learning are three different CNN models; a shallow model, an Alexnet and a ResNet model. Through the order to proceed with the diagnosis of moderate depression for depressed people, the proposed system plays a vital role by informing family members and doctors in emergency situations so that we can safeguard the patients’ lives. Major Depressive Disorder in adolescents is associated with decreased functioning in adulthood, recurrence and an increased risk of death due to suicide. A study of typically developing preschool-aged children found that while irritability and sadness were the most sensitive predictors of depression (identified in 98% of preschoolers), anhedonia was the most specific, apparent only in the depressed group.50 Younger children may present with somatic complaints and behavior problems and may demonstrate a persistent engagement in activities or play with themes of death or suicide.This approach may enable physicians to remotely monitor major depression patients in distant and disadvantaged regions. In this paper, however, we provide a comprehensive review of many current methods for detecting and preventing depression as soon as possible and highlight their strengths, constraints, and difficulties to guarantee the safety of patients and to save precious lives.