Joint Attention Mechanism Learning to Facilitate Opto-physiological Monitoring during Physical Activity

2025-02-13

AI Summary

Motion artifacts (MAs) severely degrade photoplethysmography (PPG) signal quality during physical activity, compromising the accuracy of heart rate (HR) and respiratory rate (RR) estimation. To address this, we propose an attention-guided generative adversarial network (AM-GAN), the first method to dynamically leverage tri-axial accelerometer signals via an attention module for adaptive MA modeling and suppression—enabling motion-intensity-aware, end-to-end MA removal. Extensive evaluation on IEEE-SPC, PPG-DaLiA, and our proprietary LU dataset demonstrates state-of-the-art performance: mean absolute HR estimation errors of 1.81, 3.86, and <1.37 bpm, respectively, and RR estimation errors <2.49 breaths/min—significantly outperforming existing approaches. This work establishes a novel, highly robust, and generalizable paradigm for MA suppression in contactless physiological monitoring during motion.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: Motion and Path Planning
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search

Abstract

Opto-physiological monitoring is a non-contact technique for measuring cardiac signals, i.e., photoplethysmography (PPG). Quality PPG signals directly lead to reliable physiological readings. However, PPG signal acquisition procedures are often accompanied by spurious motion artefacts (MAs), especially during low-to-high-intensity physical activity. This study proposes a practical adversarial learning approach for opto-physiological monitoring by using a generative adversarial network with an attention mechanism (AM-GAN) to model motion noise and to allow MA removal. The AM-GAN learns an MA-resistant mapping from raw and noisy signals to clear PPG signals in an adversarial manner, guided by an attention mechanism to directly translate the motion reference of triaxial acceleration to the MAs appearing in the raw signal. The AM-GAN was experimented with three various protocols engaged with 39 subjects in various physical activities. The average absolute error for heart rate (HR) derived from the MA-free PPG signal via the AM-GAN, is 1.81 beats/min for the IEEE-SPC dataset and 3.86 beats/min for the PPGDalia dataset. The same procedure applied to an in-house LU dataset resulted in average absolute errors for HR and respiratory rate (RR) of less than 1.37 beats/min and 2.49 breaths/min, respectively. The study demonstrates the robustness and resilience of AM-GAN, particularly during low-to-high-intensity physical activities.

Problem

• Remove motion artefacts from PPG signals
• Enhance opto-physiological monitoring accuracy
• Apply AM-GAN during physical activities

Innovation

• Generative Adversarial Network with Attention Mechanism
• Motion Artefact Removal via Adversarial Learning
• Triaxial Acceleration to Signal Translation