SOSW: Stress Sensing With Off-the-Shelf Smartwatches in the Wild

Abstract

Recent advances in wearable technology have led to the development of various methods for stress sensing in both controlled laboratory and real-life environments. However, existing methods often rely on specialized or expensive sensors that may not be easily accessible to the general population. In this study, we investigate the feasibility of using off-the-shelf smartwatches for stress detection in real-life scenarios. To achieve this, we propose SOSW, a comprehensive methodology for robust sensor data processing by considering both physiological and contextual data. SOSW employs a two-layer machine learning (ML) architecture. The first-layer ML model is trained and validated using carefully collected data under controlled laboratory conditions. The second-layer ML model is trained and validated using data collected in real-life settings. We conducted evaluations with 26 and 18 participants in controlled laboratory and real-life conditions, respectively. The results indicate that our methodology can successfully detect stressful events with an F-1 score of up to 0.84 in laboratory conditions and 0.71 in real-life scenarios using off-the-shelf smartwatches. The results are comparable to those achieved by the state-of-the-art methods that rely on dedicated wearables.