MURFormer: Attention-Based Lightweight Multi-Scale Uncertainty-Guided Refinement Framework for PPG Denoising

Noisy-to-clean PPG denoiser built from a Multi-Scale Attention-Conv Fusion (MACF) block with an uncertainty-guided two-pass refinement that revisits unreliable regions. Evaluated on the public CIME dataset and a new Daily Activities set of paired noisy/clean PPG from 24 subjects. Reported gains over raw input: 129% and 105% relative SNR improvement and 66% and 81% relative reductions in HR MAE (Daily Activities and CIME respectively); beats an existing denoising baseline with a small parameter count while preserving beat timing and morphology, and stays robust across input window lengths.

• Form factor: unknown (not stated in abstract)

Photoplethysmography (PPG) is a widely used physiological signal for its convenience but is highly susceptible to motion artifacts that degrade waveform quality and limit downstream analysis. This paper proposes MURFormer, a lightweight multi-scale uncertainty-guided refinement framework for PPG denoising through noisy-to-clean PPG mapping. MURFormer employs a newly proposed Multi-Scale Attention-Conv Fusion (MACF) block, which is designed to efficiently capture multi-scale temporal dynamics of PPG, as the fundamental building block and performs uncertainty-guided two-pass refinement prioritizing unreliable regions. The method was evaluated on the publicly available CIME dataset and on a Daily Activities dataset collected in this work, comprising paired noisy-clean PPG recordings from 24 subjects. Experimental results show that MURFormer improves both signal quality and physiological fidelity over the raw noisy input, yielding 129% and 105% relative signal-to-noise ratio (SNR) improvements, and 66% and 81% relative reductions in heart-rate mean absolute error (MAE), on the Daily Activities and CIME datasets, respectively. MURFormer also outperforms an existing denoising baseline on both datasets with a relatively small parameter count while preserving beat-level timing and waveform morphology. In addition, the model maintains strong denoising performance across varying input window lengths, suggesting that MURFormer is an effective and robust framework for practical PPG denoising. The implementation of MURFormer is publicly available at https://github.com/k-hram/MURFormer.git

Verbatim from arXiv (opens in a new tab) · arXiv metadata (abstracts are released under CC0)

No results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.