Paperdoi:10.1016/j.bspc.2026.111128
Physical PPG signal synthesis via reinforcement learning-based LED control
Biomedical Signal Processing and Control (Nov 2026 issue)
TL;DR
Hardware-in-the-loop testbed: a PPO agent drives LED intensity and change rate so a PPG sensor's output reproduces a target waveform, for repeatable device evaluation rather than physiology modelling. Analyses how LED stimuli and change rates affect amplitude/timing; task-specific states and latency/amplitude-aware rewards. Evaluated on three representative PPG signals (low, moderate, high amplitude); beats baseline controllers under the same set-up.
- Form factor: other
Abstract
We introduce a hardware-in-the-loop framework for physical Photoplethysmography (PPG) signal synthesis and benchmarking, leveraging reinforcement learning (RL) as a control engine for the controllable, LED-based reconstruction of target PPG waveforms. Rather than focusing on physiological modeling or proposing a new RL algorithm, this work provides a repeatable testbed for sensor-output waveform reconstruction to facilitate device evaluation. To address the challenges of physical signal reconstruction, we comprehensively analyze how LED stimuli affect the amplitude and temporal characteristics of generated PPG signals and how LED change rates influence reconstruction performance. A standard Proximal Policy Optimization (PPO) agent is used as the underlying controller in this system to adjust LED intensity and control rate so that the sensor’s output matches the target signal. In particular, we design task-specific state representations and latency- and amplitude- aware reward functions that play a critical role in improving performance across waveforms with varying shapes and amplitudes. Evaluated across three representative PPG signals featuring low, moderate, and high amplitudes, our PPO-based control framework consistently reconstructs the target waveforms, outperforming alternative baseline controllers under the same standardized evaluation setup and the current tested conditions. Overall, our framework positions deep RL as a practical complement to classical control for hard-to-model hardware-coupled dynamics, highlighting the promise of data-driven paradigms for nonlinear system identification and control in bioengineering.
Verbatim from OpenAlex (opens in a new tab) · Abstract via OpenAlex (publisher-deposited); © the authors/publisher
Results on ChatPPG leaderboards
All leaderboardsNo results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.
Tasks & signals
Signals
Keywords
How it works
Cite this paper
Zhou, F., Holsinger, A., Zhao, T., & Yao, Z. (2026). Physical PPG signal synthesis via reinforcement learning-based LED control. Biomedical Signal Processing and Control. https://doi.org/10.1016/j.bspc.2026.111128
Zhou, Fangshi, Adam Holsinger, Tianming Zhao, and Zhongmei Yao. 2026. "Physical PPG signal synthesis via reinforcement learning-based LED control." Biomedical Signal Processing and Control. https://doi.org/10.1016/j.bspc.2026.111128.
Zhou, F., Holsinger, A., Zhao, T. and Yao, Z. (2026) 'Physical PPG signal synthesis via reinforcement learning-based LED control', Biomedical Signal Processing and Control. doi: 10.1016/j.bspc.2026.111128.
Zhou, Fangshi, et al. "Physical PPG signal synthesis via reinforcement learning-based LED control." Biomedical Signal Processing and Control, 2026. https://doi.org/10.1016/j.bspc.2026.111128.
F. Zhou, A. Holsinger, T. Zhao, and Z. Yao, "Physical PPG signal synthesis via reinforcement learning-based LED control," Biomedical Signal Processing and Control, 2026, doi: 10.1016/j.bspc.2026.111128.
@article{zhou2026physical,
title = {{Physical PPG signal synthesis via reinforcement learning-based LED control}},
author = {Zhou, Fangshi and Holsinger, Adam and Zhao, Tianming and Yao, Zhongmei},
year = {2026},
journal = {Biomedical Signal Processing and Control},
doi = {10.1016/j.bspc.2026.111128}
}Added to the ChatPPG research hub
