Active Reinforcement Learning for Personalized Stress Monitoring in Everyday Settings

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 b...

Full description

Saved in:
Bibliographic Details
Published in:IEEE/ACM Conference on Connected Health: Applications, Systems and Engineering Technologies (Online) pp. 44 - 55
Main Authors: Tazarv, Ali, Labbaf, Sina, Rahmani, Amir, Dutt, Nikil, Levorato, Marco
Format: Conference Proceeding
Language:English
Published: ACM 01.06.2023
Subjects:
Active learning
Biomedical monitoring
Data collection
E-healt
Human factors
Instruments
lIoT Systems
Personalization
Predictive models
Q-learning
Real-time systems
ISSN:2832-2975
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2832-2975
DOI:10.1145/3580252.3586979