Personalized Anomaly Detection in PPG Data using Representation Learning and Biometric Identification

TL;DR

This paper presents a two-stage framework that uses representation learning and personalization to improve anomaly detection in PPG signals from wearable devices, addressing challenges of variability and limited labeled data.

Contribution

It introduces a novel two-stage approach combining representation learning with personalization for enhanced anomaly detection in PPG data, validated on multiple datasets.

Findings

Representation learning improves detection accuracy.

Personalized models outperform generalized ones.

Biometric identification is more accurate for individual users.

Abstract

Photoplethysmography (PPG) signals, typically acquired from wearable devices, hold significant potential for continuous fitness-health monitoring. In particular, heart conditions that manifest in rare and subtle deviating heart patterns may be interesting. However, robust and reliable anomaly detection within these data remains a challenge due to the scarcity of labeled data and high inter-subject variability. This paper introduces a two-stage framework leveraging representation learning and personalization to improve anomaly detection performance in PPG data. The proposed framework first employs representation learning to transform the original PPG signals into a more discriminative and compact representation. We then apply three different unsupervised anomaly detection methods for movement detection and biometric identification. We validate our approach using two different datasets in both generalized and personalized scenarios. The results show that representation learning significantly improves anomaly detection performance while reducing the high inter-subject variability. Personalized models further enhance anomaly detection performance, underscoring the role of personalization in PPG-based fitness-health monitoring systems. The results from biometric identification show that it's easier to distinguish a new user from one intended authorized user than from a group of users. Overall, this study provides evidence of the effectiveness of representation learning and personalization for anomaly detection in PPG data.