ChatPPG.
Join free
First page or project page of “ARTA: Graph Combinatorial Optimization for Robust Interbeat Interval Estimation from Wearable Electrocardiogram Signals” (opens in a new tab)

PaperarXiv:2611.00011

ARTA: Graph Combinatorial Optimization for Robust Interbeat Interval Estimation from Wearable Electrocardiogram Signals

Under review2026Added Nov 3, 2026

  • SS
  • AA
  • HG

Authors: Shovito Barua Soumma, Asiful Arefeen, Hassan Ghasemzadeh

arXiv 2611.00011 (dated 2026-09-15); under review

PDF (opens in a new tab) arXiv2611.00011 (opens in a new tab) Cite
First page or project page of “ARTA: Graph Combinatorial Optimization for Robust Interbeat Interval Estimation from Wearable Electrocardiogram Signals” (opens in a new tab)

Soumma, Shovito Barua et al., "ARTA: Graph Combinatorial Optimization for Robust Interbeat Interval Estimation from Wearable Electrocardiogram Signals", arXiv:2611.00011, CC BY 4.0

TL;DR

ARTA (Artifact-Robust Temporal Alignment) pools beat candidates from several ECG QRS detectors into a directed acyclic graph, links them by physiologically plausible RR intervals, scores nodes by detector agreement and local ECG quality, and adds history-dependent transition costs plus a soft HR prior. Beam-search dynamic programming picks one coherent beat path, suppressing false peaks and recovering missed beats. On the IEEE Signal Processing Cup exercise data with electrode-motion noise (-2 to 12 dB): HR MAE 1.79 bpm (54% below the best single detector), 92.38% of windows within ±5 bpm, R-peak F1 0.95, IBI MAE 6.52 ms.

  • Form factor: wearable-ecg

Abstract

Accurate heart rate (HR) and interbeat interval (IBI) estimation from wearable electrocardiogram (ECG) is essential for continuous physiological monitoring, but motion artifacts can create false QRS-like peaks and obscure true R-peaks. Conventional detectors and local interval-repair rules process detections independently and may become unreliable when several consecutive beats are corrupted. We present ARTA (Artifact-Robust Temporal Alignment), a graph-based combinatorial framework that estimates the heartbeat sequence through constrained temporal optimization. ARTA combines candidates from multiple ECG detectors, represents them as nodes in a directed acyclic graph and connects candidates through physiologically plausible RR intervals. Candidate confidence uses detector agreement and local ECG quality, while history-dependent transition costs capture recent IBI consistency and a soft heart-rate prior. Beam-search dynamic programming selects a coherent low-cost path across the recording, suppressing false detections and recovering missed beats when plausible auxiliary candidates are available. On the IEEE Signal Processing Cup exercise dataset with electrode-motion artifacts from -2 to 12 dB, ARTA achieved an HR mean absolute error of 1.79 beats per minute, 54% lower than the strongest single-detector baseline, with 92.38% of windows within +/-5 beats per minute, an R-peak F1 score of 0.95, and an IBI mean absolute error of 6.52 ms. Cross-dataset evaluation on the European ST-T Database further assessed transfer to long clinical ambulatory recordings and a label-free reliability analysis examined conditional performance without using reference annotations for segment selection. ARTA is single-channel, training-free, interpretable and computationally lightweight, operating approximately 27 times faster than real time with peak memory below 2.1 MB in a single-thread CPU simulation.

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

Results on ChatPPG leaderboards

All leaderboards

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

Tasks & signals

Tasks

Heart rateSignal denoising

Signals

ECG

Keywords

IBIHRHRVR PeakMotion ArtifactTraining FreeGraphDynamic Programming

Datasets used

How it works

How Method works: Setup → Method → TargetSetup: Signals (ecg); Form factor (wearable-ecg). Method: Method. Target: Heart rate; Signal denoising.SetupSignals: ecgSignalsecgForm factor: wearable-ecgForm factorwearable-ecgMethodMethodTargetHeart rateHeart rateSignal denoisingSignal denoising

Cite this paper

Cite this paper with the fields recorded here. Check it against the publisher before submitting.

Soumma, S. B., Arefeen, A., & Ghasemzadeh, H. (2026). ARTA: Graph Combinatorial Optimization for Robust Interbeat Interval Estimation from Wearable Electrocardiogram Signals. arXiv 2611.00011. https://arxiv.org/abs/2611.00011
Soumma, Shovito Barua, Asiful Arefeen, and Hassan Ghasemzadeh. 2026. "ARTA: Graph Combinatorial Optimization for Robust Interbeat Interval Estimation from Wearable Electrocardiogram Signals." arXiv 2611.00011. https://arxiv.org/abs/2611.00011.
Soumma, S. B., Arefeen, A. and Ghasemzadeh, H. (2026) 'ARTA: Graph Combinatorial Optimization for Robust Interbeat Interval Estimation from Wearable Electrocardiogram Signals', arXiv 2611.00011. Available at: https://arxiv.org/abs/2611.00011
Soumma, Shovito Barua, et al. "ARTA: Graph Combinatorial Optimization for Robust Interbeat Interval Estimation from Wearable Electrocardiogram Signals." arXiv 2611.00011, 2026. https://arxiv.org/abs/2611.00011.
S. B. Soumma, A. Arefeen, and H. Ghasemzadeh, "ARTA: Graph Combinatorial Optimization for Robust Interbeat Interval Estimation from Wearable Electrocardiogram Signals," arXiv 2611.00011, 2026, [Online]. Available: https://arxiv.org/abs/2611.00011.
@misc{soumma2026arta,
  title         = {{ARTA: Graph Combinatorial Optimization for Robust Interbeat Interval Estimation from Wearable Electrocardiogram Signals}},
  author        = {Soumma, Shovito Barua and Arefeen, Asiful and Ghasemzadeh, Hassan},
  year          = {2026},
  howpublished  = {arXiv 2611.00011},
  eprint        = {2611.00011},
  archivePrefix = {arXiv}
}

Source metadata: 2026

Record updated Nov 3, 2026

Added to the ChatPPG research hub

Same tasks, data and authors

Papers

Models

Datasets