Anna Brondin
ABSTRACT
Commercial wearable devices and fitness trackers are commonly sold as black boxes of which little is known about their accuracy. This poses serious issues especially in health-related contexts such as clinical research, where transparency about accuracy and reliability are paramount.
We present a validated algorithm for computing step counting that is optimised for use in constrained computing environments. Released as open source, the algorithm is based on the windowed peak detection approach, which has previously shown high accuracy on smartphones. The algorithm is optimised to run on a programmable smartwatch (Pine Time) and tested on 10 subjects in 8 scenarios, with varying varying positions of the wearable and walking paces.
Our approach achieves a 89% average accuracy, with the highest average accuracy when walking outdoor (98%) and the lowest in a slow-walk scenario (77%). This result can be compared with the built-in step counter of the smartwatch (Bosch BMA421), which yielded a 94% average accuracy for the same use cases. Our work thus shows that an open-source approach for extracting physical activity data from wearable devices is possible and achieves an accuracy comparable to the one produced by proprietary embedded algorithms.
- Parastoo Alinia, Chris Cain, Ramin Fallahzadeh, Armin Shahrokni, Diane Cook, and Hassan Ghasemzadeh. 2017. How Accurate Is Your Activity Tracker? A Comparative Study of Step Counts in Low-Intensity Physical Activities. JMIR mHealth and uHealth 5, 8 (Aug. 2017), e106. https://doi.org/10.2196/mhealth.6321Google Scholar
- David R Bassett, Lindsay P Toth, Samuel R LaMunion, and Scott E Crouter. 2017. Step counting: a review of measurement considerations and health-related applications. Sports Medicine 47, 7 (2017), 1303–1315.Google ScholarCross Ref
- Ganapati Bhat, Ranadeep Deb, and Umit Y Ogras. 2019. OpenHealth: Open-source platform for wearable health monitoring. IEEE Design & Test 36, 5 (2019), 27–34.Google ScholarCross Ref
- Agata Brajdic and Robert Harle. 2013. Walk detection and step counting on unconstrained smartphones. In Proceedings of the 2013 ACM international joint conference on Pervasive and ubiquitous computing. 225–234.Google ScholarDigital Library
- Meredith A Case, Holland A Burwick, Kevin G Volpp, and Mitesh S Patel. 2015. Accuracy of smartphone applications and wearable devices for tracking physical activity data. Jama 313, 6 (2015), 625–626.Google ScholarCross Ref
- Yunhoon Cho, Hyuntae Cho, and Chong-Min Kyung. 2016. Design and implementation of practical step detection algorithm for wrist-worn devices. IEEE Sensors Journal 16, 21 (2016), 7720–7730.Google Scholar
- Yuanyuan Feng, Christopher K Wong, Vandana Janeja, Ravi Kuber, and Helena M Mentis. 2017. Comparison of tri-axial accelerometers step-count accuracy in slow walking conditions. Gait & posture 53(2017), 11–16.Google Scholar
- Rahel Gilgen-Ammann, Theresa Schweizer, and Thomas Wyss. 2020. Accuracy of Distance Recordings in Eight Positioning-Enabled Sport Watches: Instrument Validation Study. JMIR mHealth and uHealth 8, 6 (2020), e17118.Google Scholar
- Anders Kalør. 2014. Ring-Buffer. https://github.com/AndersKaloer/Ring-BufferGoogle Scholar
- Aida Kamišalić, Iztok Fister, Muhamed Turkanović, and Sašo Karakatič. 2018. Sensors and functionalities of non-invasive wrist-wearable devices: A review. Sensors 18, 6 (2018), 1714.Google ScholarCross Ref
- Justin McCarthy. 2019. One in Five U.S. Adults Use Health Apps, Wearable Trackers. https://news.gallup.com/poll/269096/one-five-adults-health-apps-wearable-trackers.aspxGoogle Scholar
- Matthew B Rhudy and Joseph M Mahoney. 2018. A comprehensive comparison of simple step counting techniques using wrist-and ankle-mounted accelerometer and gyroscope signals. Journal of Medical Engineering & Technology 42, 3(2018), 236–243.Google ScholarCross Ref
- Dario Salvi, Carmelo Velardo, Jamieson Brynes, and Lionel Tarassenko. 2018. An optimised algorithm for accurate steps counting from smart-phone accelerometry. In 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE, 4423–4427.Google ScholarCross Ref
- The Linux foundation projects. 2020. Zephyr Project. https://www.zephyrproject.org/Google Scholar
- Jack Volder. [n.d.]. The CORDIC computing technique. In Papers presented at the the March 3-5, 1959, western joint computer conference on XX - IRE-AIEE-ACM ’59 (Western) (San Francisco, California, 1959). ACM Press, 257–261. https://doi.org/10.1145/1457838.1457886Google ScholarDigital Library
- Christopher K Wong, Helena M Mentis, and Ravi Kuber. 2018. The bit doesn’t fit: Evaluation of a commercial activity-tracker at slower walking speeds. Gait & posture 59(2018), 177–181.Google Scholar
- Convict Épiscopal Luxembourg. 2002. Square-root based on CORDIC. https://www.convict.lu/Jeunes/Math/square_root_CORDIC.htmGoogle Scholar
Recommendations
Step Detection for Rollator Users with Smartwatches
SUI '18: Proceedings of the 2018 ACM Symposium on Spatial User InteractionSmartwatches enable spatial user input, namely for the continuous tracking of physical activity and relevant health parameters. Additionally, smartwatches are experiencing greater social acceptability, even among the elderly. While step counting is an ...
Open source software licenses: Strong-copyleft, non-copyleft, or somewhere in between?
Studies on open source software (OSS) have shown that the license under which an OSS is released has an impact on the success or failure of the software. In this paper, we model the relationship between an OSS developer's utility, the effort that goes ...
From proprietary to open source-Growing an open source ecosystem
In today's business and software arena, Free/Libre/Open Source Software has emerged as a promising platform for software ecosystems. Following this trend, more and more companies are releasing their proprietary software as open source, forming a ...
Comments