Non Invasive Continuous Detection of Mental Stress via Readily Available Mobile-Based Help Parameters

Abstract

Mental stress is a universal condition experienced by all humans alike at least once in their lifespan. Stress can vary from person to person depending on their age, gender, socioeconomic background and lifestyle. Although some amount of stress act as a beneficial factor, accumulated stress levels over a long period could lead to many other health problems. Hence, early detection and diagnosis is the pre-eminent method in which this damaging phenomenon can be managed. Vocal indices and facial expressions of an individual disclose surfeit amounts of information including emotions, and in turn stress. In this research two noninvasive and dynamic mechanisms, in the form of speech emotion analysis and facial expression analysis, are used in detecting stress, through emotion analysis, of an individual in a mobile and real-life environment as opposed to utilizing only one mechanism to detect stress in a controlled environment. This study proposes a holistic approach in detecting mental stress, through the categorization and identification of fear/anxiety, sadness, anger and disgust as stress emotions via extracted vocal and facial features. A finalized product is proposed to recognize stress, averaged biased on the prediction probabilities of the two detection mechanisms which then can be used to individually and independently monitor stress in order to maintain it without relying on physical medical checkups.