{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T10:48:32Z","timestamp":1761648512139,"version":"build-2065373602"},"reference-count":21,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2017,12,11]],"date-time":"2017-12-11T00:00:00Z","timestamp":1512950400000},"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>Recently, recognizing a user\u2019s daily activity using a smartphone and wearable sensors has become a popular issue. However, in contrast with the ideal definition of an experiment, there could be numerous complex activities in real life with respect to its various background and contexts: time, space, age, culture, and so on. Recognizing these complex activities with limited low-power sensors, considering the power and memory constraints of the wearable environment and the user\u2019s obtrusiveness at once is not an easy problem, although it is very crucial for the activity recognizer to be practically useful. In this paper, we recognize activity of eating, which is one of the most typical examples of a complex activity, using only daily low-power mobile and wearable sensors. To organize the related contexts systemically, we have constructed the context model based on activity theory and the \u201cFive W\u2019s\u201d, and propose a Bayesian network with 88 nodes to predict uncertain contexts probabilistically. The structure of the proposed Bayesian network is designed by a modular and tree-structured approach to reduce the time complexity and increase the scalability. To evaluate the proposed method, we collected the data with 10 different activities from 25 volunteers of various ages, occupations, and jobs, and have obtained 79.71% accuracy, which outperforms other conventional classifiers by 7.54\u201314.4%. Analyses of the results showed that our probabilistic approach could also give approximate results even when one of contexts or sensor values has a very heterogeneous pattern or is missing.<\/jats:p>","DOI":"10.3390\/s17122877","type":"journal-article","created":{"date-parts":[[2017,12,11]],"date-time":"2017-12-11T12:26:37Z","timestamp":1512995197000},"page":"2877","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Modular Bayesian Networks with Low-Power Wearable Sensors for Recognizing Eating Activities"],"prefix":"10.3390","volume":"17","author":[{"given":"Kee-Hoon","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Computer Science, Yonsei University, 50 Yonsei-ro, Seodaemun-gu, Seoul 03722, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0185-1769","authenticated-orcid":false,"given":"Sung-Bae","family":"Cho","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Yonsei University, 50 Yonsei-ro, Seodaemun-gu, Seoul 03722, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2017,12,11]]},"reference":[{"key":"ref_1","first-page":"58","article-title":"Guest editorial: Special issue on vision-based human activity recognition","volume":"30","author":"Testoni","year":"2015","journal-title":"J. Commun. Inf. Syst."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Tian, L., Sigal, L., and Mori, G. (2012, January 16\u201321). Social roles in hierarchical models for human activity recognition. Proceedings of the Computer Vision and Pattern Recognition, Providence, RI, USA.","DOI":"10.1109\/CVPR.2012.6247821"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Casale, P., Pujol, O., and Radeva, P. (2011, January 8\u201310). Human activity recognition from accelerometer data using a wearable device. Proceedings of the Pattern Recognition and Image Analysis, Las Palmas de Gran Canaria, Spain.","DOI":"10.1007\/978-3-642-21257-4_36"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.ins.2016.01.020","article-title":"Complex activity recognition using time series pattern dictionary learned from ubiquitous sensors","volume":"340","author":"Liu","year":"2016","journal-title":"Inf. Sci."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Jatoba, L.C., Grossmann, U., Kunze, C., Ottenbacher, J., and Stork, W. (2008, January 20\u201325). Context-aware mobile health monitoring: Evaluation of different pattern recognition methods for classification of physical activity. Proceedings of the IEEE Annual Conference of Engineering in Medicine and Biology Society, Vancouver, BC, Canada.","DOI":"10.1109\/IEMBS.2008.4650398"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Bao, L., and Intille, S.A. (2004, January 18\u201323). Activity recognition from user-annotated acceleration data. Proceedings of the Pervasive Computing, Vienna, Austria.","DOI":"10.1007\/978-3-540-24646-6_1"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Cheng, J., Amft, O., and Lukowicz, P. (2010, January 17\u201320). Active capacitive sensing: Exploring a new wearable sensing modality for activity recognition. Proceedings of the Pervasice Computing, Helsinki, Finland.","DOI":"10.1007\/978-3-642-12654-3_19"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1192","DOI":"10.1109\/SURV.2012.110112.00192","article-title":"A survey on human activity recognition using wearable sensors","volume":"15","author":"Lara","year":"2013","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Tapia, E.M., Intille, S.S., Haskell, W., Larson, K., Wright, J., King, A., and Friedman, R. (2007, January 11\u201313). Real-time recognition of physical activities and their intensities using wireless accelerometers and a heart rate monitor. Proceedings of the IEEE International Symposium on Wearable Computers, Boston, MA, USA.","DOI":"10.1109\/ISWC.2007.4373774"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1007\/s10489-010-0216-5","article-title":"Semi-Markov conditional random fields for accelerometer-based activity recognition","volume":"35","author":"Lee","year":"2011","journal-title":"Appl. Intell."},{"key":"ref_11","unstructured":"Marchiori, M. (April, January 29). W5: The Five Ws of the World Wide Web. Proceedings of the International Conference on Trust Management, Oxford, UK."},{"key":"ref_12","unstructured":"Jang, S., and Woo, W. (2003, January 23\u201325). Ubi-ucam: A unified context-aware application model. Proceedings of the Modeling and using context, Stanford, CA, USA."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Nardi, B.A. (1995). Context and Consciousness: Activity Theory and Human-Computer Interaction, Massachusetts Institute of Technology.","DOI":"10.7551\/mitpress\/2137.001.0001"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"4","DOI":"10.2753\/RPO1061-040513024","article-title":"The problem of activity in psychology","volume":"13","year":"1974","journal-title":"Sov. Psychol."},{"key":"ref_15","unstructured":"Suchman, L.A. (1987). Plans and Situated Actions: The Problem of Humanmachine Communication, Cambridge University Press."},{"key":"ref_16","unstructured":"Giles, C.L., and Gori, M. (1992). Learning dynamic Bayesian networks. Adaptive Processing of Sequences and Data Structures, Springer."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Korb, K.B., and Nicholson, A.E. (2010). Bayesian Artificial Intelligence, CRC Press. [2nd ed.].","DOI":"10.1201\/b10391"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/j.ins.2015.10.017","article-title":"A modular approach to landmark detection based on a bayesian network and categorized context logs","volume":"330","author":"Lim","year":"2016","journal-title":"Inf. Sci."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"446","DOI":"10.1016\/j.simpat.2009.09.002","article-title":"Mobile health monitoring system based on activity recognition using accelerometer","volume":"18","author":"Hong","year":"2010","journal-title":"Simul. Model. Parct. Theory"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Roggen, D., Calatroni, A., Rossi, M., Holleczek, T., F\u00f6rster, K., Tr\u00f6ster, G., Lukowicz, P., Bannach, D., Pirkl, G., and Ferscha, A. (2010, January 15\u201318). Collecting complex activity data sets in highly rich networked sensor environments. Proceedings of the 7th IEEE International Conference on Networked Sensing Systems (INSS), Kassel, Germany.","DOI":"10.1109\/INSS.2010.5573462"},{"key":"ref_21","unstructured":"Zappi, P., Lombriser, C., Farella, E., Roggen, D., Benini, L., and Tr\u00f6ster, G. (February, January 30). Activity recognition from on-body sensors: Accuracy-power trade-off by dynamic sensor selection. Proceedings of the 5th European Conference on Wireless Sensor Networks (EWSN), Bologna, Italy."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/17\/12\/2877\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T18:53:34Z","timestamp":1760208814000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/17\/12\/2877"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12,11]]},"references-count":21,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2017,12]]}},"alternative-id":["s17122877"],"URL":"https:\/\/doi.org\/10.3390\/s17122877","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2017,12,11]]}}}