Noise Study on the OH1 Wearable Device: Analysis of 11 Hand Movement Artifacts
DOI:
https://doi.org/10.57152/malcom.v4i4.1408Keywords:
Data Accuracy, Hand Movements, Heart Rate Monitoring, Motion Artifacts, OH1 DeviceAbstract
Wearable devices like the OH1 are increasingly used for real-time health monitoring, particularly for measuring heart rate (BPM). However, their accuracy is often compromised by motion artifacts, introducing significant noise into the measurements. This study specifically addresses the issue of noise generated by the OH1 wearable device during eleven different hand movements. To tackle this problem, we implemented a precise experimental setup involving device calibration, stable testing conditions, and participant training to ensure high consistency in hand movements. Additionally, machine learning algorithms were employed to separate noise from desired hand movement data. Our results indicate that certain hand movements, such as lifting arms and shoulder rotations, produce higher noise levels, while others, like placing hands on the table, generate minimal noise. These findings provide valuable insights for developing effective noise reduction algorithms, ultimately enhancing the accuracy and reliability of BPM measurements from wearable devices.
References
Allen, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 8078-8082.
Allen, J., 2007. Photoplethysmography and its application in clinical physiological measurement.. Physiol. Meas., Volume 28, p. 39.
B A Dolezal, D. M. B. J. C. M. A. D. L. S. C. B. C., 2017. Validation of heart rate derived from a physiological status monitor-embedded compression shirt against criterion ECG. Medicine and Science in Sports and Exercise , 49(8), pp. 1679-1703.
Bishop, C., 2006. Pattern Recognition and Machine Learning. Volume 4, p. 356.
Casson, D. J. a. A. J., 2017. Description of a Database Containing Wrist PPG Signals Recorded during Physical Exercise with Both Accelerometer and Gyroscope Measures of Motion. MDPI Journal Data, 2(1).
Chicco, D. a. J. G. (., 2020. The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation’,. BMC Genomics, 21(1), pp. 1-13.
Fabian Pedregosa, G. V. G., 2011. Scikit-learn: Machine Learning in Python.
Harun Al Azies, D. T. E. M. P., 2019. Comparison of Kernel Support Vector Machine (SVM) in Classification of Human Development Index (HDI). IPTEK Journal of Proceedings, The 1st International Conference on Global Development - ICODEV, Volume 6, pp. 53-57.
Huhn1, S. et al., 2022. The Impact of Wearable Technologies in Health Research: Scoping Review. JMIR Mhealth Uhealth , 10(1), p. 1.
Imali T. HettiarachchiID, S. H. D. N. S. N., 2019. Validation of Polar OH1 optical heart rate sensor for moderate and high intensity physical activities. PLOS ONE.
IoP Science , pp. 27-37.
J. Lui, A. F. K. A. L. C. a. C. M., 2017. “A preliminary investigation into infrared sensors in wearables for upper extremity motion sensing,”. Future Technologies Conference, p. 120–125..
Journal of Machine Learning Research 12, pp. 2825-2830.
Khan, E. et al., 2016 . A Robust Heart Rate Monitoring Scheme Using Photoplethysmographic Signals Corrupted by Intense Motion Artifacts.. IEEE Trans. Biomed. Eng. , Volume 63, p. 550–562.
Krishnan, R., Natarajan, B. & Warren, S., 2010. Two-Stage Approach for Detection and Reduction of Motion Artifacts in Photoplethysmographic Data.. IEEE Trans. Biomed. Eng. , Volume 57, p. 1867–1876.
L. A. Simpson, J. J. E. a. M. C., 2017. “H-GRASP: the feasibility of an upper limb home exercise program monitored by phone for individuals post stroke,” Disabil.. vol. 39(9), p. 874–882.
Lam, K., Sorzano, C., Zhang, Z. & Campisi, P., 2015. Undergraduate students compete in the IEEE Signal Processing Cup: Part 1. IEEE Signal Processing Mag.. Volume 32, p. 123–125. .
Lui, J. D. C. Y., 2019. Design of a Wearable to Improve Single-Device Motion Classification of Arm Motions. Canada: SIMON FRASER UNIVERSITY.
M J Butler, J. A. C. B. R. H.-G. a. P. I. R., 2016. Motion limitations of non-contact photoplethysmography due to the optical and topological properties of skin.
Mullan, P. et al., 2015. Unobtrusive Heart Rate Estimation during Physical Exercise using Photoplethysmographic and Acceleration Data.. In Proceedings of the 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), p. 6114–6117.
Omar J Escalona1, A. V. S. M. G. P. D. J. M., 2020. Wireless Arm Wearable Sensor Band for Long-Term Heart Rhythms Surveillance Using a Bipolar Arm-ECG Lead. Computing in Cardiology, Volume 47, pp. 1-4.
Piskorski J, G. P., 2007. Filtering Poincare plots.. Computational methods in science and technology., Issue 11, p. 39–48.
Schubert M, C. A. B. D. L. R. A., 2018; 02:. Sensor is Valid during Moderate Vigorous Exercise. . Dalam: The Polar® OH1 Optical Heart Rate . s.l.:s.n., p. E67–E70.
T. Imam, K. T. a. J. K., 2006. ,z-SVM: An SVM for Improved Classification of Imbalanced Data BT. Advances in Artificial Intelligence, p. 264–273.
Weinan Li1, 2. H. Z. J. W. a. Y. L., 2018. A wearable exercise heart rate detection device based on single- arm ECG. BIBE.
Zhang, L. L. M. P. X. G. a. Q. F., 2016. “A Fuzzy Kernel Motion Classifier for Autonomous Stroke Rehabilitation,”. IEEE J. Biomed. Heal. Informatics, 20(3), p. 893–901.
Zhang, Z., 2015. Photoplethysmography-Based Heart Rate Monitoring in Physical Activities via Joint Sparse Spectrum Reconstruction.. IEEE Trans. Biomed. Eng. , Volume 62, p. 1902–1910.
Zhang, Z., Pi, Z. & Liu, B., 2015. TROIKA: A General Framework for Heart Rate Monitoring Using Wrist-Type Photoplethysmographic Signals During Intensive Physical Exercise.. IEEE Trans. Biomed. Eng. , Volume 62, p. 522– 531..
Zong, C. & Jafari, R., 2015. Robust Heart Rate Estimation using Wrist-based PPG Signals in the Presence of Intense Physical Activities.. In Proceedings of the