Adaptive R-Peak Detection on Wearable ECG Sensors for High-Intensity Exercise

Objective: Continuous monitoring of biosignals via wearable sensors has quickly expanded in the medical and wellness fields. At rest, automatic detection of vital parameters is generally accurate. However, in conditions such as high-intensity exercise, sudden physiological changes occur to the signals, compromising the robustness of standard algorithms. Methods: Our method, called BayeSlope, is based on unsupervised learning, Bayesian filtering, and non-linear normalization to enhance and correctly detect the R peaks according to their expected positions in the ECG. Furthermore, as BayeSlope is computationally heavy and can drain the device battery quickly, we propose an online design that adapts its robustness to sudden physiological changes, and its complexity to the heterogeneous resources of modern embedded platforms. This method combines BayeSlope with a lightweight algorithm, executed in cores with different capabilities, to reduce the energy consumption while preserving the accuracy. Results: BayeSlope achieves an F1 score of 99.3% in experiments during intense cycling exercise with 20 subjects. Additionally, the online adaptive process achieves an F1 score of 99% across five different exercise intensities, with a total energy consumption of 1.55±0.54 mJ. Conclusion: We propose a highly accurate and robust method, and a complete energy-efficient implementation in a modern ultra-low-power embedded platform to improve R peak detection in challenging conditions, such as during highintensity exercise. Significance: The experiments show that BayeSlope outperforms a state-of-the-art algorithm up to 8.4% in F1 score, while our online adaptive method can reach energy savings up to 38.7% on modern heterogeneous wearable platforms.

[1]  P. Kirchhof,et al.  2016 ESC Guidelines for the management of atrial fibrillation developed in collaboration with EACTS. , 2016, Europace : European pacing, arrhythmias, and cardiac electrophysiology : journal of the working groups on cardiac pacing, arrhythmias, and cardiac cellular electrophysiology of the European Society of Cardiology.

[2]  Luca Benini,et al.  Slow and steady wins the race? A comparison of ultra-low-power RISC-V cores for Internet-of-Things applications , 2017, 2017 27th International Symposium on Power and Timing Modeling, Optimization and Simulation (PATMOS).

[3]  A. Soucat,et al.  Public spending on health: a closer look at global trends , 2019 .

[4]  D. Bentley,et al.  The isocapnic buffering phase and mechanical efficiency: relationship to cycle time trial performance of short and long duration. , 2005, Canadian journal of applied physiology = Revue canadienne de physiologie appliquee.

[5]  R. Orglmeister,et al.  The principles of software QRS detection , 2002, IEEE Engineering in Medicine and Biology Magazine.

[6]  Martin Buchheit,et al.  Heart-rate deflection point and the second heart-rate variability threshold during running exercise in trained boys. , 2007, Pediatric exercise science.

[7]  F. J. Richards A Flexible Growth Function for Empirical Use , 1959 .

[8]  Luca Benini,et al.  Mr.Wolf: An Energy-Precision Scalable Parallel Ultra Low Power SoC for IoT Edge Processing , 2019, IEEE Journal of Solid-State Circuits.

[9]  Malcolm s thaler,et al.  The Only EKG Book You'll Ever Need , 1988 .

[10]  M. Murphy,et al.  Untapping the Health Enhancing Potential of Vigorous Intermittent Lifestyle Physical Activity (VILPA): Rationale, Scoping Review, and a 4-Pillar Research Framework , 2020, Sports Medicine.

[11]  Ulrich Schotten,et al.  2016 ESC Guidelines for the Management of Atrial Fibrillation Developed in Collaboration With EACTS. , 2017, Revista espanola de cardiologia.

[12]  Luca Benini,et al.  Online Learning and Classification of EMG-Based Gestures on a Parallel Ultra-Low Power Platform Using Hyperdimensional Computing , 2019, IEEE Transactions on Biomedical Circuits and Systems.

[13]  William Fornaciari,et al.  An FPU design template to optimize the accuracy-efficiency-area trade-off , 2020, Sustain. Comput. Informatics Syst..

[14]  Luca Benini,et al.  GAP-8: A RISC-V SoC for AI at the Edge of the IoT , 2018, 2018 IEEE 29th International Conference on Application-specific Systems, Architectures and Processors (ASAP).

[15]  Luca Benini,et al.  Modular Design and Optimization of Biomedical Applications for Ultralow Power Heterogeneous Platforms , 2020, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[16]  R G Mark,et al.  Robust heart rate estimation from multiple asynchronous noisy sources using signal quality indices and a Kalman filter , 2008, Physiological measurement.

[17]  David Atienza,et al.  Real-Time Event-Driven Classification Technique for Early Detection and Prevention of Myocardial Infarction on Wearable Systems , 2018, IEEE Transactions on Biomedical Circuits and Systems.

[18]  David Atienza,et al.  Real-Time Personalized Atrial Fibrillation Prediction on Multi-Core Wearable Sensors , 2020 .

[19]  Philippe Ryvlin,et al.  A Self-Aware Epilepsy Monitoring System for Real-Time Epileptic Seizure Detection , 2019, Mobile Networks and Applications.

[20]  M. Decramer,et al.  Exercise testing: why, which and how to interpret , 2004, Breathe.

[21]  Thar Baker,et al.  Remote health monitoring of elderly through wearable sensors , 2019, Multimedia Tools and Applications.

[22]  Pablo Laguna,et al.  A wavelet-based ECG delineator: evaluation on standard databases , 2004, IEEE Transactions on Biomedical Engineering.

[23]  F Cottin,et al.  Assessment of ventilatory thresholds from heart rate variability in well-trained subjects during cycling. , 2006, International journal of sports medicine.

[24]  Naveen Verma,et al.  Ultralow-power electronics for biomedical applications. , 2008, Annual review of biomedical engineering.

[25]  David Atienza,et al.  Embedded real-time ECG delineation methods: A comparative evaluation , 2012, 2012 IEEE 12th International Conference on Bioinformatics & Bioengineering (BIBE).

[26]  Jean-Marc Vesin,et al.  REWARD: Design, Optimization, and Evaluation of a Real-Time Relative-Energy Wearable R-Peak Detection Algorithm * , 2019, 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[27]  Rama Komaragiri,et al.  From Pacemaker to Wearable: Techniques for ECG Detection Systems , 2018, Journal of Medical Systems.