Online human activity recognition using low-power wearable devices
Open accessAbstract
Human activity recognition (HAR) has attracted significant research interest due to its applications in health monitoring and patient rehabilitation. Recent research on HAR focuses on using smartphones due to their widespread use. However, this leads to inconvenient use, limited choice of sensors and inefficient use of resources, since smartphones are not designed for HAR. This paper presents the first HAR framework that can perform both online training and inference. The proposed framework starts with a novel technique that generates features using the fast Fourier and discrete wavelet transforms of a textile-based stretch sensor and accelerometer data. Using these features, we design a neural network classifier which is trained online using the policy gradient algorithm. Experiments on a low power IoT device (T1-CC2650 MCU) with nine users show 97.7% accuracy in identifying six activities and their transitions with less than 12.5 mW power consumption.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
Bhat et al. propose a HAR online learning framework using reinforcement learning with a policy gradient algorithm for faster convergence, achieving 97.7% in recognizing six activities.
“In [232], Bhat et al. propose a HAR online learning framework that takes advantage of reinforcement learning utilizing a policy gradient algorithm for faster convergence achieving 97.7% in recognizing six activities.”
From Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances (2022) · cites this paper as [232]
In DL-based HAR, the reward of the reinforcement learning agent has to be given by a human.
“Additionally, in the realm of DL-based HAR, the reward of the agent has to be given by a human, as in the case of [230,232].”
From Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances (2022) · cites this paper as [232]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
The Elements of Statistical Learning
Hastie, T., Friedman, J., & Tibshirani, R. (2001) · Springer Series in Statistics · doi:10.1007/978-0-387-21606-5 · Cited by 24,162 · see citing works
Introduction to Reinforcement Learning
Sutton, R. S., & Barto, A. G. (1998) · The MIT Press eBooks · Cited by 6,855 · see citing works
Activity Recognition from User-Annotated Acceleration Data
Bao, L., & Intille, S. S. (2004) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-24646-6_1 · Cited by 3,147 · see citing works
Activity recognition using cell phone accelerometers
Kwapisz, J. R., Weiss, G. M., & Moore, S. A. (2011) · ACM SIGKDD Explorations Newsletter · doi:10.1145/1964897.1964918 · Cited by 2,912 · cited 5× · see citing works
“Most existing studies employ statistical features such as mean, median, minimum, maximum, and kurtosis to perform HAR [4, 20, 28].”
BackgroundMethodResultInfluentialA Fast and Accurate Online Sequential Learning Algorithm for Feedforward Networks
Liang, N., Huang, G.-B., Saratchandran, P., & Sundararajan, N. (2006) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2006.880583 · Cited by 1,967 · see citing works
Accuracy of Smartphone Applications and Wearable Devices for Tracking Physical Activity Data
Case, M. A., Burwick, H. A., Volpp, K. G., & Patel, M. S. (2015) · JAMA · doi:10.1001/jama.2014.17841 · Cited by 694 · see citing works
Technology in Parkinson’s disease: challenges and opportunities
Espay, A. J., Bonato, P., Nahab, F. B., Maetzler, W., Dean, J. M., Klucken, J., Eskofier, B. M., Merola, A., Horak, F., Lang, A. E., et al. (2016) · Movement Disorders · doi:10.1002/mds.26642 · Cited by 654 · see citing works
Activity identification using body-mounted sensors—a review of classification techniques
Preece, S. J., Goulermas, J. Y., Kenney, L. P. J., Howard, D., Meijer, K., & Crompton, R. H. (2009) · Physiological Measurement · doi:10.1088/0967-3334/30/4/r01 · Cited by 606 · see citing works
Measuring and Influencing Physical Activity with Smartphone Technology: A Systematic Review
Roig, J. B., Gilson, N. D., Puig-Ribera, A. M., Contreras-Espinosa, R. S., & Trost, S. G. (2014) · Sports Medicine · doi:10.1007/s40279-014-0142-5 · Cited by 554 · see citing works
A Survey of Online Activity Recognition Using Mobile Phones
Shoaib, M., Bosch, S., Incel, O., Scholten, H., & Havinga, P. (2015) · Sensors · doi:10.3390/s150102059 · Cited by 489 · see citing works
A Comparative Study on Human Activity Recognition Using Inertial Sensors in a Smartphone
Wang, A., Chen, G., Yang, J., Zhao, S., & Chang, C.-Y. (2016) · IEEE Sensors Journal · doi:10.1109/jsen.2016.2545708 · Cited by 324 · see citing works
Performance Analysis of Smartphone-Sensor Behavior for Human Activity Recognition
Chen, Y., & Shen, C. Q. (2017) · IEEE Access · doi:10.1109/access.2017.2676168 · Cited by 297 · see citing works
Detection of Type, Duration, and Intensity of Physical Activity Using an Accelerometer
BONOMI, A. G., Goris, A. H. C., Yin, B., & Westerterp, K. R. (2009) · Medicine & Science in Sports & Exercise · doi:10.1249/mss.0b013e3181a24536 · Cited by 247 · see citing works
An Activity Recognition System For Mobile Phones
Győrbíró, N., Fábián, Á., & Hományi, G. (2008) · Mobile Networks and Applications · doi:10.1007/s11036-008-0112-y · Cited by 237 · see citing works
Feature Selection and Activity Recognition from Wearable Sensors
Pirttikangas, S., Fujinami, K., & Nakajima, T. (2006) · Lecture Notes in Computer Science · doi:10.1007/11890348_39 · Cited by 229 · see citing works
Kirwan, M., Duncan, M. J., Vandelanotte, C., & Mummery, W. K. (2012) · Journal of Medical Internet Research · doi:10.2196/jmir.1950 · Cited by 189 · see citing works
JUCS - Journal of Universal Computer Science
:none (2020) · CINECA IRIS Institutial research information system (University of Pisa) · doi:10.3217/jucs-019-09 · Cited by 188 · see citing works
Wearable Medical Sensor-Based System Design: A Survey
Mosenia, A., Sur‐Kolay, S., Raghunathan, A., & Jha, N. K. (2017) · IEEE Transactions on Multi-Scale Computing Systems · doi:10.1109/tmscs.2017.2675888 · Cited by 143 · see citing works
Reinforcement learning as classification: leveraging modern classifiers
Lagoudakis, M. G., & Parr, R. (2003) · Cited by 128 · see citing works
Physical Activity Recognition Utilizing the Built-In Kinematic Sensors of a Smartphone
He, Y., & Li, Y. (2013) · International Journal of Distributed Sensor Networks · doi:10.1155/2013/481580 · Cited by 104 · see citing works
Better Physical Activity Classification using Smartphone Acceleration Sensor
Arif, M., Bilal, M., Kattan, A. J., & Ahamed, S. I. (2014) · Journal of Medical Systems · doi:10.1007/s10916-014-0095-0 · Cited by 97 · see citing works
Stretch sensors for human body motion
O'Brien, B. M., Gisby, T. A., & Anderson, I. A. (2014) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2046143 · Cited by 83 · see citing works
Physical Activity Monitoring for Assisted Living at Home
Jafari, R., Li, W., Bajcsy, R., et al. (2007) · Springer eBooks · doi:10.1007/978-3-540-70994-7_37 · Cited by 68 · see citing works
Dopaminergic-induced dyskinesia assessment based on a single belt-worn accelerometer
Pérez‐López, C., Samà, A., Rodríguez-Martín, D., Aróstegui, J. M. M., Cabestany, J., Bayés, À., Mestre, B., Alcaine, S., Quispe, P., OLaighin, G. M., et al. (2016) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2016.01.001 · Cited by 66 · see citing works
Flexible PV-cell Modeling for Energy Harvesting in Wearable IoT Applications
Park, J., Joshi, H., Lee, H. G., et al. (2017) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3126568 · Cited by 47 · see citing works
Cheepsync: a time synchronization service for resource constrained bluetooth le advertisers
Sridhar, S., Misra, P., Gill, G. S., et al. (2016) · IEEE Communications Magazine · doi:10.1109/mcom.2016.7378439 · Cited by 46 · see citing works
Dinesh, K., Xiong, M., Adams, J., Dorsey, R. E., & Gaurav Sharma, A. (2016) · IEEE Western New York Image and Signal Processing Workshop (WNYISPW) · doi:10.1109/wnyipw.2016.7904834 · Cited by 22 · see citing works
Near-optimal energy allocation for self-powered wearable systems
Bhat, G., Park, J., & Ogras, U. Y. (2017) · International Conference on Computer Aided Design · doi:10.5555/3199700.3199749 · Cited by 22 · see citing works
Self-citationFlexibility-Aware System-on-Polymer (SoP): Concept to Prototype
Gupta, U., Park, J., Joshi, H., & Ogras, U. Y. (2016) · IEEE Transactions on Multi-Scale Computing Systems · doi:10.1109/tmscs.2016.2637345 · Cited by 15 · see citing works
Self-citationPaul, A., & Mukherjee, D. P. (2016) · Indian Conference on Computer Vision, Graphics and Image Processing · doi:10.1145/3009977.3010003 · Cited by 14 · see citing works
Casellas, R., Gonzalez, O., Paolucci, F., et al. (2016) · IEEE Communications Magazine · doi:10.1109/mcom.2016.7537188 · Cited by 8 · see citing works
Flagged first, then by citations
Research works printed but not linked: 3
- [3][3] D. Anguita et al. Energy Efficient Smartphone-Based Activity Recognition Using Fixed-Point Arithmetic. J. of Universal Comput. Sci. , 19(9):1295-1314. -
- [6][6] G. Bhat, J. Park, and U. Y. Ogras. Near-Optimal Energy Allocation for SelfPowered Wearable Systems. In Proc. Int. Conf. on Comput.-Aided Design , pages 368-375, 2017. -
- [30][30] J. R. Quinlan. C4. 5: Programs for Machine Learning . Elsevier, 2014. -
Cited by
Sorted by citations
Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances
Zhang, S., Li, Y., Zhang, S., Shahabi, F., Xia, S., Deng, Y., & Alshurafa, N. (2022) · Sensors · doi:10.3390/s22041476 · Cited by 625 · see citing works
“Additionally, in the realm of DL-based HAR, the reward of the agent has to be given by a human, as in the case of [40, 246].”
BackgroundDemrozi, F., Pravadelli, G., Bihorac, A., & Rashidi, P. (2020) · IEEE Access · doi:10.1109/access.2020.3037715 · Cited by 368 · see citing works
FedHAR: Semi-Supervised Online Learning for Personalized Federated Human Activity Recognition
Yu, H., Chen, Z., Zhang, X., Chen, X., Zhuang, F., Xiong, H., & Cheng, X. (2023) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2021.3136853 · Cited by 113 · see citing works
Personalized Human Activity Recognition Based on Integrated Wearable Sensor and Transfer Learning
Fu, Z., He, X., Wang, E., Huo, J., Huang, J., & Wu, D. (2021) · Sensors · doi:10.3390/s21030885 · Cited by 79 · see citing works
OpenHealth: Open-Source Platform for Wearable Health Monitoring
Bhat, G., Deb, R., & Ogras, U. Y. (2019) · IEEE Design & Test · doi:10.1109/mdat.2019.2906110 · Cited by 36 · see citing works
Self-citationNakamura, Y., Matsuda, Y., Arakawa, Y., & Yasumoto, K. (2019) · Sensors · doi:10.3390/s19204600 · Cited by 24 · see citing works
- Authors
- Bhat, G., Deb, R., Chaurasia, V. V., Shill, H., & Ogras, U. Y.
- Affiliations
- Arizona State University (US)
- Lonnie and Muhammad Ali Movement Disorder Center
- Venue
- Proceedings of the International Conference on Computer-Aided Design
- Publisher
- ACM
- Published
- 2018-11-05
- Pages
- 1-8
- OpenAlex
- W2888635150
- Cited by
- 82
- References
- 31
- Citations by year
- 2026: 2 · 2025: 5 · 2024: 13 · 2023: 11 · 2022: 12 · 2021: 14 · 2020: 14 · 2019: 11
- FWCI
- 2.94
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Physical Sciences › Engineering › Biomedical Engineering › Advanced Sensor and Energy Harvesting Materials
- Physical Sciences › Engineering › Biomedical Engineering › Non-Invasive Vital Sign Monitoring
- Keywords
- human activity recognition, wearable devices, low-power IoT, online training, online inference, stretch sensors, textile sensors, accelerometer, fast Fourier transform, discrete wavelet transform, policy gradient, neural network classifier, health monitoring, patient rehabilitation, energy consumption
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
