Enhancing Performance and User Engagement in Everyday Stress Monitoring: A Context-Aware Active Reinforcement Learning Approach
This work addresses the challenge of personalized stress monitoring for users by balancing data collection efficiency and user convenience, representing an incremental improvement in active learning methods for health applications.
The paper tackled the problem of efficiently collecting stress labels via Ecological Momentary Assessments (EMAs) by introducing a context-aware active reinforcement learning algorithm that dynamically selects optimal times for EMAs, resulting in an 11% improvement in stress detection efficiency, a 4% increase in model accuracy with contextual data, and a 10% enhancement in AUC-ROC scores for personalization.
In today's fast-paced world, accurately monitoring stress levels is crucial. Sensor-based stress monitoring systems often need large datasets for training effective models. However, individual-specific models are necessary for personalized and interactive scenarios. Traditional methods like Ecological Momentary Assessments (EMAs) assess stress but struggle with efficient data collection without burdening users. The challenge is to timely send EMAs, especially during stress, balancing monitoring efficiency and user convenience. This paper introduces a novel context-aware active reinforcement learning (RL) algorithm for enhanced stress detection using Photoplethysmography (PPG) data from smartwatches and contextual data from smartphones. Our approach dynamically selects optimal times for deploying EMAs, utilizing the user's immediate context to maximize label accuracy and minimize intrusiveness. Initially, the study was executed in an offline environment to refine the label collection process, aiming to increase accuracy while reducing user burden. Later, we integrated a real-time label collection mechanism, transitioning to an online methodology. This shift resulted in an 11% improvement in stress detection efficiency. Incorporating contextual data improved model accuracy by 4%. Personalization studies indicated a 10% enhancement in AUC-ROC scores, demonstrating better stress level differentiation. This research marks a significant move towards personalized, context-driven real-time stress monitoring methods.