Design and Performance Evaluation of an Ultralow-Power Smart IoT Device with Embedded TinyML for Asset Activity Monitoring
Open accessAbstract
This article proposes a proof-of-concept device to continuously assess the usage of handheld power tools and detect construction working tasks (e.g., different drilling works) along with potential misusages, e.g., drops, with an energy-efficient architecture design. The designed device is based on Bluetooth low energy (BLE) and NFC connectivity. BLE is used to exchange data with a gateway, whereas NFC has been chosen as an energy-efficient wake-up mechanism. A temperature and humidity sensor is embedded to monitor storage conditions and an accelerometer for tool usage monitoring. The ARM Cortex-M4 core embedded in the BLE module is exploited to process the information at the edge. A Tiny Machine Learning (TinyML) algorithm is proposed to process the data directly on board and achieve low latency and high energy efficiency. The TinyML algorithm has been developed embedded in the proposed device to detect four different usage classes (tool transportation, no-load, metal, and wood drilling). A dataset containing more than 280 min of three-axis accelerations during different activities has been acquired with the device attached to a construction rotary hammer drill and used to train and validate the algorithm. A neural architecture search has been performed to optimize the trade-off between accuracy and complexity, achieving an accuracy of 90.6% with a model size of roughly 30 kB. The experimental results showed an ultralow power consumption in sleep mode of 550 nA and a peak power consumption of 8 mA while running TinyML on the edge. This results in a balanced combination of edge processing capabilities and low power consumption, enabling to obtain a smart Internet of Things (IoT) device in the field with a long lifetime of up to four years in operation and 17 years in shelf mode with a standard 250-mAh coin battery. This work enables a long battery lifetime operation of device degradation and utility analysis, further closing the gap between edge processing and fine granularity data evaluation.
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?
Lightweight convolutional neural networks have been proposed to support behavior monitoring under strict power budgets, allowing continuous operation below a few watts.
“Lightweight convolutional neural networks have also been proposed to support behavior monitoring under strict power budgets, allowing continuous operation below a few watts [19].”
From Child Playground Entry/Exit Tracking and Log Visualization System Using BLE Beacons and Smart Devices (2026) · cites this paper as [19]
The Neural Network Architecture section describes a small convolutional model, and the Conclusion says it classifies power-tool activities on an ultralow-power sensor node. But Power Consumption reports more than four years of battery-powered operation with up to ten wake-ups and inferences per day, not continuous CNN inference; it does not establish a continuous-operation power figure in watts. (LLM, conf=0.84)
Experimental — accuracy not yet measured
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
Edge computing: Vision and challenges
Shi, W., Cao, J., Zhang, Q., Li, Y., & Xu, L. (2016) · IEEE Internet of Things Journal · doi:10.1109/jiot.2016.2579198 · Cited by 8,733 · see citing works
Oesterreich, T. D., & Teuteberg, F. (2016) · Computers in Industry · doi:10.1016/j.compind.2016.09.006 · Cited by 1,529 · see citing works
Nižetić, S., Šolić, P., López–de–Ipiña, D., & Patrono, L. (2020) · Journal of Cleaner Production · doi:10.1016/j.jclepro.2020.122877 · Cited by 1,063 · see citing works
Internet of Things (IoT): A review of enabling technologies, challenges, and open research issues
Čolaković, A., & Hadžialić, M. (2018) · Computer Networks · doi:10.1016/j.comnet.2018.07.017 · Cited by 825 · see citing works
A hybrid predictive maintenance approach for CNC machine tool driven by Digital Twin
Luo, W., Hu, T., Ye, Y., Zhang, C., & Wei, Y. (2020) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2020.101974 · Cited by 525 · see citing works
TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systems
David, R., Duke, J., Jain, A., Reddi, V. J., Jeffries, N., Li, J., Kreeger, N., Nappier, I., Natraj, M., Regev, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.08678 · Cited by 470 · see citing works
Chen, J., Liu, Z., Wang, H., Nunez, A., & Han, Z. (2018) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2017.2775345 · Cited by 456 · see citing works
Ahmed, E., Yaqoob, I., Gani, A., Imran, M. A., & Guizani, M. (2016) · IEEE Wireless Communications · doi:10.1109/mwc.2016.7721736 · Cited by 448 · see citing works
CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUsPreprint
Lai, L., Suda, N., & Chandra, V. (2018) · arXiv (Cornell University) · doi:10.4230/oasics.ng-res.2025.4 · Cited by 304 · see citing works
Kuntoğlu, M., Aslan, A., Pimenov, D. Y., et al. (2020) · Sensors · doi:10.3390/s21010108 · Cited by 297 · see citing works
Kanan, R., Elhassan, O., & Bensalem, R. (2018) · Automation in Construction · doi:10.1016/j.autcon.2017.12.033 · Cited by 290 · see citing works
Data acquisition technologies for construction progress tracking
Omar, T., & Nehdi, M. L. (2016) · Automation in Construction · doi:10.1016/j.autcon.2016.06.016 · Cited by 287 · see citing works
Empowered self-development and continuous learning
London, M., & Smither, J. W. (1999) · Human Resource Management · doi:10.1002/(sici)1099-050x(199921)38:1 · Cited by 250 · see citing works
Benchmarking TinyML Systems: Challenges and Direction
Banbury, C. R., Reddi, V. J., Lam, M., Fu, W., Fazel, A., Holleman, J., Huang, X., Hurtado, R., Kanter, D., Lokhmotov, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2003.04821 · Cited by 216 · see citing works
Banbury, C., Zhou, C., Fedorov, I., Navarro, R. M., Thakker, U., Gope, D., Reddi, V. J., Mattina, M., & Whatmough, P. N. (2020) · arXiv · doi:10.48550/arxiv.2010.11267 · Cited by 183 · see citing works
The Art of Designing Remote IoT Devices—Technologies and Strategies for a Long Battery Life
Callebaut, G., Leenders, G., Mulders, J. V., Ottoy, G., Strycker, L. D., & der Perre, L. V. (2021) · Sensors · doi:10.3390/s21030913 · Cited by 140 · see citing works
Banbury, C., Reddi, V. J., Torelli, P., Holleman, J., Jeffries, N., Kiraly, C., Montino, P., Kanter, D., Ahmed, S., Pau, D., et al. (2021) · arXiv · doi:10.48550/arxiv.2106.07597 · Cited by 121 · see citing works
Maruthi, G. S., & Hegde, V. (2015) · IEEE Sensors Journal · doi:10.1109/jsen.2015.2476561 · Cited by 99 · see citing works
Wireless Sensor Network System for Landslide Monitoring and Warning
Giri, P., Ng, K. W., & Phillips, W. (2018) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2018.2861999 · Cited by 96 · see citing works
Worker 4.0: The Future of Sensored Construction Sites
Calvetti, D., Mêda, P., Gonçalves, M. C., et al. (2020) · Buildings · doi:10.3390/buildings10100169 · Cited by 88 · see citing works
Advancing the Competitiveness and Efficiency of the U.S. Construction Industry
National Research Council (2009) · National Academies Press eBooks · doi:10.17226/12717 · Cited by 82 · see citing works
Liu, R., Ramli, A. A., Zhang, H., Henricson, E., & Liu, X. (2022) · Lecture notes in computer science · doi:10.1007/978-3-030-96068-1_1 · Cited by 72 · see citing works
Vibration-based SHM with up-scalable and low-cost Sensor Networks
Zonzini, F., Malatesta, M. M., Bogomolov, D., et al. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.2982814 · Cited by 71 · see citing works
Human Activity Recognition Using Multichannel Convolutional Neural Network
Sikder, N., Chowdhury, M. S., Arif, A. S. M., et al. (2019) · doi:10.1109/icaee48663.2019.8975649 · Cited by 70 · see citing works
Wang, X., Lu, S., Huang, W., Wang, Q., Zhang, S., & Xia, M. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3051668 · Cited by 65 · cited 1× · see citing works
“Previous work demonstrated how accelerometers are a good fit for devices’ health assessment [34]–[36], and the aforehand mentioned signal processing techniques, used isolated, are proven to extract useful information from accelerometer data.”
BackgroundWeb-Based Benchmarking System for the Construction Industry
Lee, S., Thomas, S. R., & Tucker, R. L. (2005) · Journal of Construction Engineering and Management · doi:10.1061/(asce)0733-9364(2005)131:7(790 · Cited by 62 · see citing works
Widening Access to Applied Machine Learning with TinyML
Janapa Reddi, V., Plancher, B., Kennedy, S., Moroney, L., Warden, P., Suzuki, L., Agarwal, A., Banbury, C., Banzi, M., Bennett, M., et al. (2022) · Harvard Data Science Review · doi:10.1162/99608f92.762d171a · Cited by 62 · see citing works
Experimental Analysis of Filtering Algorithms for IMU-Based Applications Under Vibrations
Capriglione, D., Carratù, M., Catelani, M., et al. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.3044339 · Cited by 51 · see citing works
Railroad Track Condition Monitoring Using Inertial Sensors and Digital Signal Processing: A Review
Chia, L., Bhardwaj, B., Lu, P., et al. (2018) · IEEE Sensors Journal · doi:10.1109/jsen.2018.2875600 · Cited by 46 · see citing works
A Vision-Based Monitoring Method for the Looseness of High-Strength Bolt
Pan, Y. D., Ma, Y., Dong, Y., et al. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3101316 · Cited by 44 · see citing works
Murphy, F. E., Magno, M., Whelan, P. M., et al. (2015) · IEEE Sensors Applications Symposium (SAS) · doi:10.1109/sas.2015.7133587 · Cited by 41 · see citing works
Self-citationAqueveque, P., Radrigán, L., Pastene, F., et al. (2021) · IEEE Access · doi:10.1109/access.2021.3051583 · Cited by 41 · see citing works
Human Activity Recognition using Deep Learning Models on Smartphones and Smartwatches Sensor Data
Oluwalade, B., Neela, S., Wawira, J. G., et al. (2021) · International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC) · doi:10.5220/0010325906450650 · Cited by 39 · see citing works
Design and Field Validation of a Low Power Wireless Sensor Node for Structural Health Monitoring
Zanelli, F., Dezza, F. C., Tarsitano, D., et al. (2021) · Sensors · doi:10.3390/s21041050 · Cited by 35 · see citing works
Tool Wear Classification Using Decision Treesin Stone Drilling Applications: A Preliminary Study
Klaić, M., Staroveški, T., & Udiljak, T. (2014) · Procedia Engineering · doi:10.1016/j.proeng.2014.03.125 · Cited by 32 · see citing works
HHAR-net: Hierarchical Human Activity Recognition using Neural Networks
Fazli, M., Kowsari, K., Gharavi, E., Barnes, L., & Doryab, A. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-68449-5_6 · Cited by 32 · see citing works
Induction motor fault detection and diagnosis by vibration analysis using MEMS accelerometer
Raj, V. P., Natarajan, K., & Girikumar, S. T. G. (2013) · doi:10.1109/c2spca.2013.6749391 · Cited by 31 · see citing works
SmarTEG: An Autonomous Wireless Sensor Node for High Accuracy Accelerometer-Based Monitoring
Magno, M., Sigrist, L., Gomez, A., et al. (2019) · Sensors · doi:10.3390/s19122747 · Cited by 27 · see citing works
Self-citationA Bluetooth-Low-Energy Sensor Node for Acoustic Monitoring of Small Birds
Magno, M., Vultier, F., Szebedy, B., Yamahachi, H., Hahnloser, R. H. R., & Luca Benini, C. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2019.2940282 · Cited by 27 · see citing works
Self-citationCondition Monitoring in Industry 4.0-Design Challenges and Possibilities: A Case Study
Shahzad, K., & O’Nils, M. (2018) · doi:10.1109/metroi4.2018.8428306 · Cited by 25 · see citing works
Material Classification By Drilling
LaBelle, D., Bares, J. E., & Nourbakhsh, I. (2000) · Proceedings of the ... ISARC · doi:10.22260/isarc2000/0088 · Cited by 23 · see citing works
Development of universal wireless sensor node for tool condition monitoring in milling
Ostaševičius, V., Karpavicius, P., Jūrėnas, V., et al. (2020) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-020-05812-x · Cited by 20 · see citing works
Giordano, M., Fischer, R., Crabolu, M., Bellusci, G., & Magno, M. (2021) · IEEE Sensors Applications Symposium (SAS) · doi:10.1109/sas51076.2021.9530182 · Cited by 9 · see citing works
Self-citationA Multisensor Induction Motors Diagnostics Method for Bearing Cyclic Fault
Minervini, M., Frosini, L., Hasani, L., et al. (2020) · International Conference on Electrical Machines (ICEM) · doi:10.1109/icem49940.2020.9271000 · Cited by 8 · see citing works
Robust fault detection filter and its application in MEMS-based INS/GPS
Shi, J., Miao, L., & Ni, M. (2011) · Journal of Systems Engineering and Electronics · doi:10.3969/j.issn.1004-4132.2011.01.014 · Cited by 5 · see citing works
Preview: IEEE Technology Report on Wake-Up Radio
McCormick, D. (2017) · doi:10.1109/ieeestd.2017.8053470 · Cited by 5 · see citing works
Livesey, A., & Robinson, A. (2006) · Routledge eBooks · doi:10.4324/9780080459813-11 · Cited by 1 · see citing works
Flagged first, then by citations
Research works printed but not linked: 4
- M. M. Baig, H. Gholamhosseini, S. Afifi, and F. Mirza, "Current chal- lenges and barriers to the wider adoption of wearable sensor applications and Internet-of-Things in health and well-being," in Proc. CONF-IRM, 2019, p. 20.
- Recognizing Product Application Based on Integrated Consumer Grade Sensors: A Case Study With Handheld Power Tools Sci- encedirect. Accessed: Nov. 19, 2021. [Online]. Available: https://www. sciencedirect.com/science/article/pii/S2212827119309655
- How to Make IoT Batteries Last Longer IEEE Innovation at Work. Accessed: Nov. 19, 2021. [Online]. Available: https://innovationatwork. ieee.org/how-to-make-iot-batteries-last-longer/
- Buildings | Free Full-Text | Worker 4.0: The Future of Sensored Con- struction Sites | HTML. Accessed: Nov. 19, 2021. [Online]. Available: https://www.mdpi.com/2075-5309/10/10/169/htm
Cited by
Sorted by citations
Chung, M. (2026) · Signals · doi:10.3390/signals7040067
“Lightweight convolutional neural networks have also been proposed to support behavior monitoring under strict power budgets, allowing continuous operation below a few watts [19].”
- Authors
- Giordano, M., Baumann, N., Crabolu, M., Fischer, R., Bellusci, G., & Magno, M.
- Affiliations
- ETH Zurich (CH)
- Hilti (Liechtenstein) (LI)
- Corresponding author
- Giordano, Marco
- ORCID
- Venue
- IEEE Transactions on Instrumentation and Measurement
- Published
- 2022
- Volume
- 71
- Pages
- 1-11
- ISSN
- 0018-9456 (ISSN-L)
- 1557-9662
- OpenAlex
- W4225705568
- Cited by
- 72
- References
- 47
- Citations by year
- 2026: 18 · 2025: 22 · 2024: 19 · 2023: 13
- FWCI
- 5.99
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Locations
- IEEE Transactions on Instrumentation and Measurement (publishedVersion, cc-by)
- Repository for Publications and Research Data (ETH Zurich) (submittedVersion, cc-by)
- ETH Zürich Research Collection (cc-by)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Computer Science › Computer Networks and Communications › Bluetooth and Wireless Communication Technologies
- Physical Sciences › Engineering › Electrical and Electronic Engineering › IoT Networks and Protocols
- Keywords
- TinyML, edge computing, accelerometer, Bluetooth Low Energy, ARM Cortex-M4, neural architecture search, battery life
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
