I am a "Smart" watch, Smart Enough to Know the Accuracy of My Own Heart Rate Sensor
Abstract
With the wide-distribution of smart wearables, it seems as though ubiquitous healthcare can finally permeate into our everyday lives, opening the possibility to realize clinical-grade applications. However, given that clinical applications require reliable sensing, there is a need to understand how accurate healthcare sensors on wearable devices (e.g., heart rate sensors) are. To answer this question, this work starts with a thorough investigation on the accuracy of widely used wearable devices' heart rate sensors. Specifically, we show that when actively moving, heart rate readings can diverge far from the ground truth, and also show that such inaccuracies cannot be easily correlated, nor predicted, using accelerometer and gyroscope measurements. Rather, we point out that the light intensity readings at the photoplethysmography (PPG) sensor can be an effective indicator of heart rate accuracy. Using a Viterbi algorithm-based Hidden Markov Model, we show that it is possible to design a filter that allows smartwatches to self-classify measurement quality with ~ 98% accuracy. Given that such capabilities allow the smartwatch to internally filter misleading values from being application input, we foresee this as an essential step in catalyzing novel clinical-grade wearable applications.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Random user gestures will often confuse the predefined sensor calibration model, causing it to misread the user's heart rate.
“Random user gestures will often confuse the predefined sensor calibration model, causing it to misread the user’s heart rate [113].”
From Review of Wearable Devices and Data Collection Considerations for Connected Health (2021) · cites this paper as [113]
Cites
Photoplethysmography and its application in clinical physiological measurement
Allen, J. (2007) · Physiological Measurement · doi:10.1088/0967-3334/28/3/r01 · Cited by 3,967 · see citing works
Zhang, Z., Pi, Z., & Liu, B. (2014) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2014.2359372 · Cited by 759 · see citing works
International Journal of Clinical Practice
(2022) · International Journal of Clinical Practice · doi:10.1111/(issn)1742-1241 · Cited by 596 · see citing works
Motion Artifact Reduction in Photoplethysmography Using Independent Component Analysis
Kim, B., & Yoo, S. K. (2006) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2005.869784 · Cited by 400 · see citing works
Wearable sensors/systems and their impact on biomedical engineering
Bonato, P. (2003) · IEEE Engineering in Medicine and Biology Magazine · doi:10.1109/memb.2003.1213622 · Cited by 382 · cited 1× · see citing works
“3032977 ries of studies show that ubiquitous heart rate sensing can offer possibilities for enabling clinical-grade services [3].”
BackgroundEl-Amrawy, F., & Nounou, M. I. (2015) · Healthcare Informatics Research · doi:10.4258/hir.2015.21.4.315 · Cited by 287 · see citing works
Estimating heart rate using wrist-type Photoplethysmography and acceleration sensor while running
Fukushima, H., Kawanaka, H., Bhuiyan, M. S., & OGURI, K. (2012) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc.2012.6346570 · Cited by 129 · see citing works
Smart-watches: a potential challenger to the implantable loop recorder?
Carpenter, A., & Frontera, A. (2016) · Europace · doi:10.1093/europace/euv427 · Cited by 86 · see citing works
Wrist-located pulse detection using IR signals, activity and nonlinear artifact cancellation
Renevey, P., Vetter, R., Krauss, J., Celka, P., & Depeursinge, Y. (2005) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/iembs.2001.1017437 · Cited by 63 · see citing works
HIPAA compliant wireless sensing smartwatch application for the self-management of pediatric asthma
Hosseini, A., Buonocore, C. M., Hashemzadeh, S., Hojaiji, H., Kalantarian, H., Sideris, C., Bui, A. A. T., King, C., & Sarrafzadeh, M. (2016) · Wearable and Implantable Body Sensor Networks · doi:10.1109/bsn.2016.7516231 · Cited by 29 · see citing works
Towards a natural walking monitor for pulmonary patients using simple smart phones
Juen, J. P., Cheng, Q., & Schatz, B. R. (2014) · doi:10.1145/2649387.2649401 · Cited by 13 · see citing works
Novel Approach for Noise Removal of Brain Tumor MRI Images
Dhanuskodi, A., & Perumal, K. (2015) · Journal of Biomedical Engineering and Medical Imaging · doi:10.14738/jbemi.23.1142 · Cited by 11 · see citing works
Clinical perspective: the importance of heart rate reduction in heart failure
Cowie, M., & Davidson, L. L. (2012) · International Journal of Clinical Practice · doi:10.1111/j.1742-1241.2012.02968.x · Cited by 10 · see citing works
Kokonozi, A., Astaras, A., Semertzidis, P., Michail, E., Filos, D., Chouvarda, I., Grossenbacher, O., Koller, J.-M., Leopoldo, R., Porchet, J.-A., et al. (2010) · Computing in cardiology · Cited by 7 · see citing works
Runtti, H., Honka, A. M., Chouvarda, I., Michail, E., Kokonozi, A., Merilahti, J., Pärkkä, J., & van Gils, M. (2013) · Cited by 7 · see citing works
Liaqat, D., Thukral, I., Sin, P., Alshaer, H., Rudzicz, F., de Lara, E., Wu, R. C., & Gershon, A. S. (2016) · Annual International Conference on Mobile Systems, Applications, and Services Companion (MobiSys Companion) · doi:10.1145/2938559.2938606 · Cited by 4 · see citing works
Adaptive motion artifact reducing algorithm for wrist photoplethysmography application
Zhao, J., Wang, G., & Shi, C. (2016) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2228935 · Cited by 2 · see citing works
Review on Evaluation Methods to Pre-detect the Stroke Using Wearable Devices
Min, S. N., Lee, K., Kim, D., Park, S. J., Seo, Y., Subramaniyam, M., & Kim, S. E. (2016) · Advances in intelligent systems and computing · doi:10.1007/978-3-319-41694-6_75 · Cited by 2 · see citing works
A SOS Heart Smart Wrist Watch App for Heart Attack Patients
Memon, I., Bai, S., Rajper, S., & Gopang, S. (2015) · Journal of Biomedical Engineering and Medical Imaging · doi:10.14738/jbemi.21.981 · Cited by 1 · see citing works
Ferrari, A., Puccinelli, D., & Giordano, S. (2015) · Proceedings of the 28th Annual International Conference on Mobile Computing And Networking · doi:10.1145/2789168.2795160 · Cited by 1 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Review of Wearable Devices and Data Collection Considerations for Connected Health
Vijayan, V., Connolly, J. P., Condell, J., McKelvey, N., & Gardiner, P. (2021) · Sensors · doi:10.3390/s21165589 · Cited by 435 · see citing works
“Random user gestures will often confuse the predefined sensor calibration model, causing it to misread the user’s heart rate [113].”
BackgroundRöddiger, T., Clarke, C., Breitling, P., Schneegans, T., Zhao, H., Gellersen, H. W., & Beigl, M. (2022) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3550314 · Cited by 104 · see citing works
Materials and Structural Designs toward Motion Artifact-Free Bioelectronics
Park, B., Jeong, C., Ok, J., & Kim, T. (2024) · Chemical Reviews · doi:10.1021/acs.chemrev.3c00374 · Cited by 78 · see citing works
Smart watches: A review of evolution in bio-medical sector
Chandel, R. S., Sharma, S., Kaur, S., Singh, S., & Kumar, R. (2021) · Materials Today Proceedings · doi:10.1016/j.matpr.2021.07.460 · Cited by 71 · see citing works
Park, J.-Y., Cho, H. K., Balan, R. K., & Ko, J. (2020) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3411843 · Cited by 36 · see citing works
“There are numerous smartwatches and other wearable devices that can measure the heart rate (in beats per minute) of an individual in fairly unobtrusive ways [11, 13, 24, 28, 66, 77, 91].”
BackgroundSelf-citationWristO2: Reliable Peripheral Oxygen Saturation Readings from Wrist-Worn Pulse Oximeters
Phillips, C., Liaqat, D., Gabel, M., & de Lara, E. (2021) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomworkshops51409.2021.9430986 · Cited by 31 · see citing works
Energy efficient heart rate sensing using a painted electrode ECG wearable
Krachunov, S., Beach, C., Casson, A. J., Pope, J., Fafoutis, X., Piechocki, R. J., & Craddock, I. J. (2017) · Global Internet of Things Summit (GIoTS) · doi:10.1109/giots.2017.8016260 · Cited by 26 · see citing works
“They necessitate complex signal processing to extract a reliable heart rate, for example [3], with debate present on the accuracy of current methods [4], [5].”
MethodG-Sparks: Glanceable Sparklines on Smartwatches
Neshati, A., Sakamoto, Y., Leboe-McGowan, L. C., Leboe-McGowan, J. P., Serrano, M., & Irani, P. (2019) · Open Archive Toulouse Archive Ouverte (University of Toulouse) · doi:10.20380/gi2019.23 · Cited by 25 · see citing works
“Their varied sensors can monitor sleep and heart rate [2,32,42] and assist with fitness tracking [38] or recognizing stress [9].”
Polak, A. G., Klich, B., Saganowski, S., Prucnal, M. A., & Kazienko, P. (2022) · Sensors · doi:10.3390/s22187047 · Cited by 21 · see citing works
“The exception is [40], where changes in the light entering the detector were examined with the 3D-printed rings for the smartwatches with and without holes to change the amount of light falling on the sensor, and this caused a deterioration in the quality of the reading.”
MethodUnderstanding Emotion Changes in Mobile Experience Sampling
Kang, S., Park, C. Y., Kim, A., Cha, N., & Lee, U. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3501944 · Cited by 18 · see citing works
“Also, we only considered signals collected in low-mobility situations such as standing and sitting for the analysis since the quality of wristband data is known to be poor under high mobility circumstances [57, 61], using the automatic motion type detection of MS Band 2.”
MethodSOSW: Stress Sensing With Off-the-Shelf Smartwatches in the Wild
Toshnazarov, K. E., Lee, U., Kim, B. H., Mishra, V., Najarro, L. A. C., & Noh, Y. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3375299 · Cited by 18 · see citing works
“However, PPG is known to be error-prone under motion (or physical activity) [19], [20] due to sensor displacement relative to skin and loose wearing conditions [18], [21].”
BackgroundMethodInfluentialAhn, J., Ra, H.-K., Yoon, H. J., Son, S. H., & Ko, J. (2020) · IEEE Access · doi:10.1109/access.2020.3025776 · Cited by 16 · see citing works
Self-citationChen, Z., Zhang, F., Qian, X., Zhao, G., & Yan, Z. (2025) · Materials Horizons · doi:10.1039/d5mh00700c · Cited by 14 · see citing works
“18,19 This overlap makes it difficult to filter out noise while preserving the integrity of the desired physiological signals.”
PPG Earring: Wireless Smart Earring for Heart Health Monitoring
Xue, Q. S., Nissanka, D., Yan, J. T., Wang, R., Patel, S., & Iyer, V. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713856 · Cited by 10 · see citing works
“Current wearables like smartwatches and smart rings often address this issue by either discarding noisy data or applying advanced processing methods to estimate or interpolate the heart rate [5, 15, 58, 61].”
Hypoglycemia Detection Using Hand Tremors: Home Study of Patients With Type 1 Diabetes
Jahromi, R. K., Zahed, K., Sasangohar, F., Erraguntla, M., Mehta, R. K., & Qaraqe, K. A. (2023) · JMIR Diabetes · doi:10.2196/40990 · Cited by 7 · see citing works
“Sensor measurements are usually contaminated by motion artifacts due to hand movement, wearable tightness level [85], physiological tremors [86], and so on.”
BackgroundA Fine-Grained User-Divided Privacy-Preserving Access Control Protocol in Smart Watch
Fang, L., Li, M., Zhou, L., Zhang, H., & Ge, C. (2019) · Sensors · doi:10.3390/s19092109 · Cited by 5 · see citing works
“A smart watch can realize functions including calling, social entertainment, human health monitoring, etc [2].”
BackgroundFDTLS: Supporting DTLS-Based Combined Storage and Communication Security for IoT Devices
Boo, E., Raza, S., Höglund, J., & Ko, J. (2019) · IEEE International Conference on Mobile Ad-Hoc and Sensor Systems (MASS) · doi:10.1109/mass.2019.00024 · Cited by 5 · see citing works
Self-citationBaker, D. J. (2018) · Elsevier eBooks · doi:10.1016/b978-0-12-809414-3.00011-5 · Cited by 4 · see citing works
Trkulja, A. S. A., Muharemović, A., Pokvić, L. G., Begić, E., & Badnjević, A. (2022) · Mediterranean Conference on Embedded Computing (MECO) · doi:10.1109/meco55406.2022.9797202 · Cited by 3 · see citing works
Low-Power Discreetly-Wearable Smart ECG Patch with On-Board Analytics
Mittal, S. S., Zabran, M., Ghose, K., & Turner, J. N. (2020) · IEEE International Symposium on Medical Measurements and Applications (MeMeA) · doi:10.1109/memea49120.2020.9137284 · Cited by 3 · see citing works
The Effect of Motion on PPG Heart Rate Sensors
Hu, D. J., Henry, C., & Bagchi, S. (2020) · IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume (DSN-S) · doi:10.1109/dsn-s50200.2020.00032 · Cited by 3 · see citing works
“Ra et al. [7] uses the PPG’s light intensity to classify whether or not a smart watch measurements are accurate or not.”
BackgroundTowards Context-Aware Assistance for Smart Self-Management of Knowledge Workers.
Lambusch, F., & Michael Fellmann, M. A. (2018) · Cited by 1 · see citing works
Evaluation of heart rate monitoring accuracy of smart wearable technology devices
Adilović, N., Cogo, E., Cogo, E., & Bešić, I. (2024) · Telecommunications Forum (TELFOR) · doi:10.1109/telfor63250.2024.10819189 · Cited by 1 · see citing works
“…because of the simplicity of the HW-827 sensor that returns only the beats-per-minute (BPM) value [13], to allow for a fair comparison. modes were introduced in order to check for the existence of sensor inaccuracies that might arise due to movement of test subjects, as indicated by Ra et al. [14].”
Wrist02 -- Reliable Peripheral Oxygen Saturation Readings from Wrist-Worn Pulse OximetersPreprint
Phillips, C., Liaqat, D., Gabel, M., & de Lara, E. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.07545 · Cited by 1 · see citing works
Smart Self-Management for Better Working.
Lambusch, F. (2018) · EMISA FORUM
Choudhury, A. D., Banerjee, R., Kimbahune, S., & Pal, A. (2022) · Elsevier eBooks · doi:10.1016/b978-0-12-824499-9.00004-0
Fan, D., & Bao, Z. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-93236-6_12
Application of Machine Learning Approach to Classify Human Activity Level Based on Lifelog Data
Jeong, S.-H., Nam, W., & Park, K. C. (2026) · Sensors · doi:10.3390/s26051612
“To define the heart rate, the optical heart rate sensor of the device flashes a green LED repeatedly per second and uses a light sensitive photodiode to detect volume changes in capillaries above the wrist [27,28].”
- Authors
- Ra, H.-K., Ahn, J., Yoon, H. J., Yoon, D., Son, S. H., & Ko, J.
- Affiliations
- Daegu Gyeongbuk Institute of Science and Technology (KR)
- Ajou University (KR)
- Venue
- Proceedings of the 18th International Workshop on Mobile Computing Systems and Applications
- Publisher
- ACM
- Published
- 2017-02-21
- Pages
- 49-54
- ISSN
- 1550-6193 (ISSN-L)
- OpenAlex
- W2592377534
- Cited by
- 29
- References
- 20
- Citations by year
- 2026: 1 · 2025: 3 · 2024: 4 · 2023: 1 · 2022: 5 · 2021: 3 · 2020: 4 · 2019: 4 · 2018: 3 · 2017: 1
- FWCI
- 6.51
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE Workshop on Mobile Computing Systems and Applications (WMCSA) (publishedVersion)
- Funders
- Ministry of Trade, Industry and Energy (International Cooperative R&D Program (#N0002099))
- Ministry of Health and Welfare, Korea (Korea Health Technology R&D Project (HI16C0982))
- Ministry of Science, ICT and Future Planning (DGIST R&D program (CPS Global Center), Resilient CPS Research (14-824-09-013))
- Topics
- Physical Sciences › Engineering › Biomedical Engineering › Non-Invasive Vital Sign Monitoring
- Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › Heart Rate Variability and Autonomic Control
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Keywords
- smartwatches, heart rate sensor, sensor accuracy, photoplethysmography, hidden Markov models, Viterbi algorithm, accelerometer and gyroscope, ubiquitous healthcare
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
