IEEE Signal Processing Cup 2015 (TROIKA)

Name: IEEE Signal Processing Cup 2015 (TROIKA)
License: Original: copyright, academic research only (prior INDEX reject note); Zenodo IEEEPPG repackaging labelled CC BY 4.0

wrist PPG during intensive exercise

PPGIMUECGWrist-wornDOI

Dataset

Key facts

Signals: ppg, accel, ecg
Reference Labels: hr
Sampling Rates: 125 Hz (PPG ×2, 3-axis accel, ECG)
Subjects: 12
License: Original: copyright, academic research only (prior INDEX reject note); Zenodo IEEEPPG repackaging labelled CC BY 4.0

Summary

Zhang et al. (TROIKA; arXiv 1409.5181). Used for the IEEE SPC 2015 heart-rate challenge.

Used by

Models

ecg-ppg-jepa gpt-ppg

Papers

gpt-ppg-gpt-foundation-model-ppg-physiolmeas-2025 ecg-ppg-jepa-latent-space-prediction-kdd-2026

Leaderboards

Heart rate estimation

Mean absolute HR error (BPM) ↓

Updated: Oct 11, 2026

Related Research

ECG-PPG JEPA (Bridging ECG and PPG; unnamed in paper)
Foundation model
GPT-PPG
Foundation model
GPT-PPG: a GPT-based foundation model for photoplethysmography signals
Zhaoliang Chen, Cheng Ding, Saurabh Kataria, Runze Yan, Minxiao Wang, Randall Lee, Xiao Hu. Physiol.
Bridging ECG and PPG: Latent-Space Prediction for Robust Physiological Analysis
Zhaoliang Chen, Saurabh Kataria, Minxiao Wang, Xiao Hu. Nell Hodgson Woodruff School of Nursing, Emo
Heart rate estimation leaderboard
Benchmark results on IEEE Signal Processing Cup 2015 (TROIKA)
A Longitudinal and Multimodal physiological signals dataset of Para handcycling training and race for SCI Rehabilitation
Research dataset