Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
158 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

BeliefPPG: Uncertainty-aware Heart Rate Estimation from PPG signals via Belief Propagation (2306.07730v2)

Published 13 Jun 2023 in cs.LG, cs.CV, and eess.SP

Abstract: We present a novel learning-based method that achieves state-of-the-art performance on several heart rate estimation benchmarks extracted from photoplethysmography signals (PPG). We consider the evolution of the heart rate in the context of a discrete-time stochastic process that we represent as a hidden Markov model. We derive a distribution over possible heart rate values for a given PPG signal window through a trained neural network. Using belief propagation, we incorporate the statistical distribution of heart rate changes to refine these estimates in a temporal context. From this, we obtain a quantized probability distribution over the range of possible heart rate values that captures a meaningful and well-calibrated estimate of the inherent predictive uncertainty. We show the robustness of our method on eight public datasets with three different cross-validation experiments.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (48)
  1. Photoplethysmography (ppg):: State-of-the-art methods and applications. Physiological Measurement, 42(10), Nov. 2021. ISSN 0967-3334. 10.1088/1361-6579/ac2d82.
  2. Benchmarking bayesian deep learning on diabetic retinopathy detection tasks. ArXiv, abs/2211.12717, 2022.
  3. Cornet: Deep learning framework for ppg-based heart rate estimation and biometric identification in ambulant environment. IEEE Transactions on Biomedical Circuits and Systems, 13(2):282–291, 2019. 10.1109/TBCAS.2019.2892297.
  4. Q-ppg: Energy-efficient ppg-based heart rate monitoring on wearable devices. IEEE Transactions on Biomedical Circuits and Systems, 15(6):1196–1209, 2021. 10.1109/TBCAS.2021.3122017.
  5. Embedding temporal convolutional networks for energy-efficient ppg-based heart rate monitoring. ACM Trans. Comput. Healthcare, 3(2), mar 2022. ISSN 2691-1957. 10.1145/3487910.
  6. Deepheart: A deep learning approach for accurate heart rate estimation from ppg signals. ACM Trans. Sen. Netw., 17(2), jan 2021. ISSN 1550-4859. 10.1145/3441626.
  7. W. Chen and D. McDuff. Deepphys: Video-based physiological measurement using convolutional attention networks. In Proceedings of the european conference on computer vision (ECCV), pages 349–365, 2018.
  8. Finite state machine framework for instantaneous heart rate validation using wearable photoplethysmography during intensive exercise. IEEE Journal of Biomedical and Health Informatics, 23(4):1595–1606, 2019. 10.1109/JBHI.2018.2871177.
  9. Deep learning for heart rate estimation from reflectance photoplethysmography with acceleration power spectrum and acceleration intensity. IEEE Access, 8:63390–63402, 2020. 10.1109/ACCESS.2020.2981956.
  10. Decomposition of uncertainty in bayesian deep learning for efficient and risk-sensitive learning. In International Conference on Machine Learning, 2017.
  11. Body composition and body weight changes at different altitude levels: a systematic review and meta-analysis. Frontiers in physiology, 10:430, 2019.
  12. G. Forney. The viterbi algorithm. Proceedings of the IEEE, 61(3):268–278, 1973. 10.1109/PROC.1973.9030.
  13. Y. Gal and Z. Ghahramani. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48, ICML’16, page 1050–1059. JMLR.org, 2016.
  14. Self-supervised ppg representation learning shows high inter-subject variability. arXiv preprint arXiv:2212.04902, 2022.
  15. An effective photoplethysmography heart rate estimation framework integrating two-level denoising method and heart rate tracking algorithm guided by finite state machine. IEEE Journal of Biomedical and Health Informatics, 26(8):3731–3742, 2022. 10.1109/JBHI.2022.3165071.
  16. Probabilistic backpropagation for scalable learning of bayesian neural networks. In Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37, ICML’15, page 1861–1869. JMLR.org, 2015.
  17. N. Huang and N. Selvaraj. Robust ppg-based ambulatory heart rate tracking algorithm. In 2020 42nd Annual International Conference of the IEEE Engineering in Medicine Biology Society (EMBC), pages 5929–5934, 2020.
  18. A novel walking detection and step counting algorithm using unconstrained smartphones. Sensors, 18(1):297, 2018.
  19. W. Karlen. Capnobase ieee tbme respiratory rate benchmark, 2021.
  20. D. P. Kingma and J. Ba. Adam: A method for stochastic optimization, 2014. URL https://arxiv.org/abs/1412.6980.
  21. Critical scale invariance in a healthy human heart rate. Physical Review Letters, 93(17):178103, 2004.
  22. Motion artifact cancellation in wearable photoplethysmography using gyroscope. IEEE Sensors Journal, 19(3):1166–1175, 2019. 10.1109/JSEN.2018.2879970.
  23. D. J. MacKay. A practical bayesian framework for backpropagation networks. Neural computation, 4(3):448–472, 1992.
  24. Clas: A database for cognitive load, affect and stress recognition. In 2019 International Conference on Biomedical Innovations and Applications (BIA), pages 1–4, 2019. 10.1109/BIA48344.2019.8967457.
  25. R. M. Neal. Bayesian learning for neural networks, volume 118. Springer Science & Business Media, 2012.
  26. Attention u-net: Learning where to look for the pancreas, 2018. URL https://arxiv.org/abs/1804.03999.
  27. Practical Deep Learning with Bayesian Principles. Curran Associates Inc., Red Hook, NY, USA, 2019.
  28. Can You Trust Your Model’s Uncertainty? Evaluating Predictive Uncertainty under Dataset Shift. Curran Associates Inc., Red Hook, NY, USA, 2019.
  29. Long-range anticorrelations and non-gaussian behavior of a leaky faucet. Physical Review E, 52(3):R2168, 1995.
  30. Toward a robust estimation of respiratory rate from pulse oximeters. IEEE Transactions on Biomedical Engineering, 64(8):1914–1923, 2017. 10.1109/TBME.2016.2613124.
  31. Bcg algorithm for unobtrusive heart rate monitoring. In 2017 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT), pages 180–183. IEEE, 2017.
  32. DeepPulse: An Uncertainty-aware Deep Neural Network for Heart Rate Estimations from Wrist-worn Photoplethysmography. 3 2022. 10.36227/techrxiv.19368140.v2.
  33. Deep ppg: Large-scale heart rate estimation with convolutional neural networks. Sensors, 19(14), 2019. ISSN 1424-8220. URL https://www.mdpi.com/1424-8220/19/14/3079.
  34. Binary cornet: Accelerator for hr estimation from wrist-ppg. IEEE Transactions on Biomedical Circuits and Systems, 14(4):715–726, 2020. 10.1109/TBCAS.2020.3001675.
  35. P. Sarkar and A. Etemad. Cardiogan: Attentive generative adversarial network with dual discriminators for synthesis of ecg from ppg, 2020. URL https://arxiv.org/abs/2010.00104.
  36. Introducing wesad, a multimodal dataset for wearable stress and affect detection. In Proceedings of the 20th ACM International Conference on Multimodal Interaction, ICMI ’18, page 400–408, New York, NY, USA, 2018. Association for Computing Machinery. ISBN 9781450356923. URL https://doi.org/10.1145/3242969.3242985.
  37. Ppgnet: Deep network for device independent heart rate estimation from photoplethysmogram. In 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pages 1899–1902, 2019. 10.1109/EMBC.2019.8856989.
  38. Nas-ppg: Ppg-based heart rate estimation using neural architecture search. IEEE Sensors Journal, 21(13):14941–14949, 2021. 10.1109/JSEN.2021.3073047.
  39. Spectral analysis of signals, volume 452. Pearson Prentice Hall Upper Saddle River, NJ, 2005.
  40. Age-predicted maximal heart rate revisited. Journal of the American College of Cardiology, 37(1):153–156, 2001. 10.1016/S0735-1097(00)01054-8.
  41. A. Temko. Accurate heart rate monitoring during physical exercises using ppg. IEEE Transactions on Biomedical Engineering, 64(9):2016–2024, 2017. 10.1109/TBME.2017.2676243.
  42. D. Ulmer and G. Cinà. Know your limits: Uncertainty estimation with relu classifiers fails at reliable ood detection. In C. de Campos and M. H. Maathuis, editors, Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, volume 161 of Proceedings of Machine Learning Research, pages 1766–1776. PMLR, 27–30 Jul 2021. URL https://proceedings.mlr.press/v161/ulmer21a.html.
  43. Pixel recurrent neural networks. In International conference on machine learning, pages 1747–1756. PMLR, 2016.
  44. M. Wilkosz and A. Szczęsna. Multi-headed conv-lstm network for heart rate estimation during daily living activities. Sensors, 21(15), 2021. ISSN 1424-8220. 10.3390/s21155212.
  45. Simper: Simple self-supervised learning of periodic targets, 2023.
  46. Z. Zhang. Photoplethysmography-based heart rate monitoring in physical activities via joint sparse spectrum reconstruction. IEEE Transactions on Biomedical Engineering, 62:1902 – 1910, 08 2015. 10.1109/TBME.2015.2406332.
  47. TROIKA: A general framework for heart rate monitoring using wrist-type photoplethysmographic signals during intensive physical exercise. IEEE Transactions on Biomedical Engineering, 62(2):522–531, feb 2015. 10.1109/tbme.2014.2359372.
  48. M. Zhou and N. Selvaraj. Heart rate monitoring using sparse spectral curve tracing. volume 2020, pages 5347–5352, 07 2020. 10.1109/EMBC44109.2020.9175349.
Citations (7)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now