Abstract:
This study aims to understand the feasibility of a stress detection model through a smartwatch, in the Indian adult population using the physiological data collected for lab and real-life settings. Wearable devices such as smartwatches have the potential to revolutionize mental health care by providing continuous, unobtrusive monitoring of physiological signals that can be used to detect mental states such as stress. When a person experiences stress, there are notable shifts in various bio-signals. by using such biosignals stress levels can be identified. The study will also explore current state-of-the-art machine learning (ML) models for stress and anxiety detection. The study also aims to compare the results of stress detection algorithms in two contexts, real-life data, and lab-induced data. Additionally, an in-depth examination of the Electrodermal activity-based dataset’s quality for emotion recognition research across diverse compiled datasets is done initially as they are less explored. This facilitates in building a more generalized stress detection model. The project is a middle ground between effective machine learning models on small scale wearable devices, and a humanistic approach to the design process of arriving at the final model. Through the project we explore the opportunities for the Indian population and incorporate the insights in an edge-based solution, through wearables and companion applications.
