{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T03:44:02Z","timestamp":1782272642105,"version":"3.54.5"},"reference-count":26,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2022,3,25]],"date-time":"2022-03-25T00:00:00Z","timestamp":1648166400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>A lightweight on-device liquid consumption estimation system involving an energy-aware machine learning algorithm is developed in this work. This system consists of two separate on-device neural network models that carry out liquid consumption estimation with the result of two tasks: the detection of sip from gestures with which the bottle is handled by its user and the detection of first sips after a bottle refill. This predictive volume estimation framework incorporates a self-correction mechanism that can minimize the error after each bottle fill-up cycle, which makes the system robust to errors from the sip classification module. In this paper, a detailed characterization of sip detection is performed to understand the accuracy-complexity tradeoffs by developing and implementing a variety of different ML models with varying complexities. The maximum energy consumed by the entire framework is around 119 mJ during a maximum computation time of 300 \u03bcs. The energy consumption and computation times of the proposed framework is suitable for implementation in low-power embedded hardware that can be incorporated in consumer grade water bottles.<\/jats:p>","DOI":"10.3390\/s22072514","type":"journal-article","created":{"date-parts":[[2022,3,27]],"date-time":"2022-03-27T21:31:25Z","timestamp":1648416685000},"page":"2514","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["An On-Device Learning System for Estimating Liquid Consumption from Consumer-Grade Water Bottles and Its Evaluation"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7424-3070","authenticated-orcid":false,"given":"Avirup","family":"Roy","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI 48824, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4436-1054","authenticated-orcid":false,"given":"Hrishikesh","family":"Dutta","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI 48824, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Henry","family":"Griffith","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, The University of Texas at San Antonio, San Antonio, TX 78249, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Subir","family":"Biswas","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI 48824, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,3,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"8","DOI":"10.3928\/00989134-20150814-02","article-title":"Dehydration in the older adult","volume":"41","author":"Miller","year":"2015","journal-title":"J. Gerontol. Nurs."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Amft, O., Bannach, D., Pirkl, G., Kreil, M., and Lukowicz, P. (April, January 29). Towards wearable sensing-based assessment of fluid intake. Proceedings of the 2010 8th IEEE International Conference on Pervasive Computing and Communications Workshops (PERCOM Workshops), Mannheim, Germany.","DOI":"10.1109\/PERCOMW.2010.5470653"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1038\/s41746-020-0246-2","article-title":"Automatic, wearable-based, in-field eating detection approaches for public health research: A scoping review","volume":"3","author":"Bell","year":"2020","journal-title":"NPJ Digit. Med."},{"key":"ref_4","unstructured":"Chiu, M.C., Chang, S.P., Chang, Y.C., Chu, H.H., Chen, C.C.H., Hsiao, F.H., and Ko, J.C. (October, January 30). Playful bottle: A mobile social persuasion system to motivate healthy water intake. Proceedings of the 11th International Conference on Ubiquitous Computing, Orlando, FL, USA."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Cohen, R., Fernie, G., and Roshan Fekr, A. (2021). Fluid Intake Monitoring Systems for the Elderly: A Review of the Literature. Nutrients, 13.","DOI":"10.3390\/nu13062092"},{"key":"ref_6","first-page":"1","article-title":"A dynamic partitioning algorithm for sip detection using a bottle attachable IMU sensor","volume":"10","author":"Griffith","year":"2019","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Venkataramani, S., Roy, K., and Raghunathan, A. (2016, January 25\u201328). Efficient embedded learning for IoT devices. Proceedings of the 2016 21st Asia and South Pacific Design Automation Conference (ASP-DAC), Macao, China.","DOI":"10.1109\/ASPDAC.2016.7428029"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Ibrahim, A., Osta, M., Alameh, M., Saleh, M., Chible, H., and Valle, M. (2018, January 9\u201312). Approximate computing methods for embedded machine learning. Proceedings of the 2018 25th IEEE International Conference on Electronics, Circuits and Systems (ICECS), Bordeaux, France.","DOI":"10.1109\/ICECS.2018.8617877"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1007\/s00240-017-1006-x","article-title":"Accuracy of daily fluid intake measurements using a \u201csmart\u201d water bottle","volume":"46","author":"Borofsky","year":"2018","journal-title":"Urolithiasis"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"559.e1","DOI":"10.1016\/j.ajog.2008.01.049","article-title":"Development and testing of a new instrument to measure fluid intake, output, and urinary symptoms: The questionnaire-based voiding diary","volume":"198","author":"Arya","year":"2008","journal-title":"Am. J. Obstet. Gynecol."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Dong, B., Gallant, R., and Biswas, S. (2014, January 8\u201310). A self-monitoring water bottle for tracking liquid intake. Proceedings of the 2014 IEEE Healthcare Innovation Conference (HIC), Seattle, WA, USA.","DOI":"10.1109\/HIC.2014.7038937"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Griffith, H., and Biswas, S. (2019, January 10\u201312). Improving water consumption estimates from a bottle-attachable sensor using heuristic fusion. Proceedings of the 2019 IEEE 20th International Symposium on \u201cA World of Wireless, Mobile and Multimedia Networks\u201d (WoWMoM), Washington, DC, USA.","DOI":"10.1109\/WoWMoM.2019.8792985"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Kurniawan, A. (2021). Arduino Nano 33 BLE Sense Board Development. IoT Projects with Arduino Nano 33 BLE Sense, Apress.","DOI":"10.1007\/978-1-4842-6458-4"},{"key":"ref_14","unstructured":"Nordic Semiconductor (2021, May 18). nRF52840. Available online: https:\/\/www.nordicsemi.com\/eng\/Products\/nRF52840."},{"key":"ref_15","unstructured":"Yiu, J. (2013). The Definitive Guide to ARM\u00ae Cortex\u00ae-M3 and Cortex\u00ae-M4 Processors, Newnes."},{"key":"ref_16","unstructured":"Pedley, M. (2013). Tilt Sensing Using a Three-Axis Accelerometer, Freescale Semiconductor, Inc.. Freescale semiconductor application note."},{"key":"ref_17","unstructured":"Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., and Isard, M. (2016, January 2\u20134). TensorFlow: A System for Large-Scale Machine Learning. Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16), Savannah, GA, USA."},{"key":"ref_18","first-page":"1839","article-title":"Tensorflow lite: On-device machine learning framework","volume":"57","author":"Li","year":"2020","journal-title":"J. Comput. Res. Dev."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Pan, T., and Zhu, Y. (2018). Getting started with Arduino. Designing Embedded Systems with Arduino, Springer.","DOI":"10.1007\/978-981-10-4418-2"},{"key":"ref_20","first-page":"701","article-title":"The periodic moving average filter for removing motion artifacts from PPG signals","volume":"5","author":"Lee","year":"2007","journal-title":"Int. J. Control. Autom. Syst."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Zou, J., Han, Y., and So, S.-S. (2008). Overview of artificial neural networks. Artificial Neural Networks, Humana Press.","DOI":"10.1007\/978-1-60327-101-1_2"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Shanmuganathan, S. (2016). Artificial neural network modelling: An introduction. Artificial Neural Network Modelling, Springer.","DOI":"10.1007\/978-3-319-28495-8"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Salmon, B.P., Kleynhans, W., Schwegmann, C.P., and Olivier, J.C. (2015, January 26\u201331). Proper comparison among methods using a confusion matrix. Proceedings of the 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Milan, Italy.","DOI":"10.1109\/IGARSS.2015.7326461"},{"key":"ref_24","first-page":"39","article-title":"Evaluation of classification models in machine learning","volume":"7","author":"Milica","year":"2017","journal-title":"Theory Appl. Math. Comput. Sci."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Kumari, R., and Srivastava, S.K. (2017). Machine learning: A review on binary classification. Int. J. Comput. Appl., 160.","DOI":"10.5120\/ijca2017913083"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Loukatos, D., Dimitriou, N., Manolopoulos, I., Kontovasilis, K., and Arvanitis, K.G. (2021, January 25\u201326). Revealing Characteristic IoT Behaviors by Performing Simple Energy Measurements via Open Hardware\/Software Components. Proceedings of the Sixth International Congress on Information and Communication Technology, London, UK.","DOI":"10.1007\/978-981-16-1781-2_90"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/7\/2514\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:43:05Z","timestamp":1760136185000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/7\/2514"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,25]]},"references-count":26,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2022,4]]}},"alternative-id":["s22072514"],"URL":"https:\/\/doi.org\/10.3390\/s22072514","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,25]]}}}