Active Reinforcement Learning for Personalized Stress Monitoring in Everyday Settings
This work addresses the challenge of minimizing user burden while improving personalization for stress monitoring, representing an incremental advancement in active learning for wearable sensor applications.
The paper tackles the problem of personalizing stress detection models in everyday settings by proposing a context-aware active learning strategy that reduces the number of queries needed from users, achieving 88% and 32% fewer queries compared to randomized and traditional active learning strategies, respectively.
Most existing sensor-based monitoring frameworks presume that a large available labeled dataset is processed to train accurate detection models. However, in settings where personalization is necessary at deployment time to fine-tune the model, a person-specific dataset needs to be collected online by interacting with the users. Optimizing the collection of labels in such phase is instrumental to impose a tolerable burden on the users while maximizing personal improvement. In this paper, we consider a fine-grain stress detection problem based on wearable sensors targeting everyday settings, and propose a novel context-aware active learning strategy capable of jointly maximizing the meaningfulness of the signal samples we request the user to label and the response rate. We develop a multilayered sensor-edge-cloud platform to periodically capture physiological signals and process them in real-time, as well as to collect labels and retrain the detection model. We collect a large dataset and show that the context-aware active learning technique we propose achieves a desirable detection performance using 88\% and 32\% fewer queries from users compared to a randomized strategy and a traditional active learning strategy, respectively.