A Smart Cyber-Human System to Support Mental Well-Being through Social Engagement

The widespread adoption of wearable devices and social media is generating population-scale data about people's behavior as situated in their everyday lives. In this paper, an embedded Cyber-Human System (CHS) is used to monitor a person's mental health via physiological, behavioral, and social data. These three data streams will then be relayed to an application used by a professional within the medical industry, to allow remote monitoring of the user's mental health without the uncertainty that face-to-face interviews can introduce. Experimentation and verification have been conducted on a group of test subjects with different test scenarios including a happy, sad, angry, and neutral state of being. We propose to use physiological data to predict a person's emotional state using a machine learning classification algorithm. The proposed system can distinguish between the different emotional states with an accuracy of 92.9%.