{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T09:12:18Z","timestamp":1773393138778,"version":"3.50.1"},"reference-count":37,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2019,6,4]],"date-time":"2019-06-04T00:00:00Z","timestamp":1559606400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61603091"],"award-info":[{"award-number":["61603091"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>This paper presents a multi-sensor model combination system with class-specific voting for physical activity monitoring, which combines multiple classifiers obtained by splicing sensor data from different nodes into new data frames to improve the diversity of model inputs. Data obtained from a wearable multi-sensor wireless integrated measurement system (WIMS) consisting of two accelerometers and one ventilation sensor have been analysed to identify 10 different activity types of varying intensities performed by 110 voluntary participants. It is noted that each classifier shows better performance on some specific activity classes. Through class-specific weighted majority voting, the recognition accuracy of 10 PA types has been improved from 86% to 92% compared with the non-combination approach. Furthermore, the combination method has shown to be effective in reducing the subject-to-subject variability (standard deviation of recognition accuracies across subjects) in activity recognition and has better performance in monitoring physical activities of varying intensities than traditional homogeneous classifiers.<\/jats:p>","DOI":"10.3390\/info10060197","type":"journal-article","created":{"date-parts":[[2019,6,4]],"date-time":"2019-06-04T04:26:40Z","timestamp":1559622400000},"page":"197","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Multi-Sensor Activity Monitoring: Combination of Models with Class-Specific Voting"],"prefix":"10.3390","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8561-9122","authenticated-orcid":false,"given":"Lingfei","family":"Mo","sequence":"first","affiliation":[{"name":"School of Instrument Science and Engineer, Southeast University, Nanjing 210096, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lujie","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Instrument Science and Engineer, Southeast University, Nanjing 210096, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaopeng","family":"Liu","sequence":"additional","affiliation":[{"name":"GE Global Research, Niskayuna, NY 12309, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert X.","family":"Gao","sequence":"additional","affiliation":[{"name":"Department of Mechanical and Aerospace Engineering, Case Western Reserve University, Cleveland, OH 44106, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2019,6,4]]},"reference":[{"key":"ref_1","first-page":"126","article-title":"Physical activity, exercise, and physical fitness: Definitions and distinctions for health-related research","volume":"100","author":"Caspersen","year":"1985","journal-title":"Public Health Rep."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"442","DOI":"10.1097\/00005768-200009001-00002","article-title":"Validity of accelerometry for the assessment of moderate intensity physical activity in the field","volume":"32","author":"Hendelman","year":"2000","journal-title":"Med. Sci. Sports Exerc."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1007\/s10439-005-9068-2","article-title":"A review of approaches to mobility telemonitoring of the elderly in their living environment","volume":"34","author":"Scanaill","year":"2006","journal-title":"Ann. Biomed. Eng."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1300","DOI":"10.1152\/japplphysiol.00465.2009","article-title":"An artificial neural network to estimate physical activity energy expenditure and identify physical activity type from an accelerometer","volume":"107","author":"Staudenmayer","year":"2009","journal-title":"J. Appl. Physiol."},{"key":"ref_5","unstructured":"Cao, J., Li, W., Ma, C., Muhammad, S., Stephan, B., Ozlem, I., Hans, S., and Paul, H. (2016). Complex human activity recognition using smartphone and wrist-worn motion sensors. Sensors, 16."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1109\/TITB.2007.899496","article-title":"Detection of daily activities and sports with wearable sensors in controlled and uncontrolled conditions","volume":"12","author":"Ermes","year":"2008","journal-title":"IEEE Trans. Inf. Technol. Biomed."},{"key":"ref_7","unstructured":"Feng, Z., Mo, L., and Li, M. (2015, January 25\u201329). A Random Forest-based ensemble method for activity recognition. Proceedings of the 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Milan, Italy."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1109\/JBHI.2014.2313039","article-title":"Estimating energy expenditure using body-worn accelerometers: A comparison of methods, sensors number and positioning","volume":"19","author":"Altini","year":"2014","journal-title":"Biomed. Health Inform."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Liu, S., Gao, R., and Freedson, P. (2010, January 6\u20139). Design of a wearable multi-sensor system for physical activity assessment. Proceedings of the 2010 IEEE\/ASME International Conference on Advanced Intelligent Mechatronics 2010, Montreal, ON, Canada.","DOI":"10.1109\/AIM.2010.5695932"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1145\/1056743.1056744","article-title":"Machine learning research","volume":"18","author":"Carbonell","year":"1981","journal-title":"ACM Sigart Bull."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1626","DOI":"10.1249\/01.mss.0000227542.43669.45","article-title":"Development of novel techniques to classify physical activity mode using accelerometers","volume":"38","author":"Pober","year":"2006","journal-title":"Med. Sci. Sports Exerc."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1186\/s13640-017-0235-9","article-title":"Gated spatio and temporal convolutional neural network for activity recognition: Towards gated multimodal deep learning","volume":"2017","author":"Yudistira","year":"2017","journal-title":"EURASIP J. Image Video Process."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1109\/TITB.2009.2037752","article-title":"Twin SVM for gesture classification using the surface electromyogram","volume":"14","author":"Naik","year":"2010","journal-title":"IEEE Trans. Inf. Technol. Biomed."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1109\/TBME.2008.2005969","article-title":"Automatic EEG artifact removal: A weighted support vector machine approach with error correction","volume":"56","author":"Shao","year":"2009","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_15","unstructured":"Umakanthan, S., Denman, S., and Fookes, C. (July, January 29). Activity recognition using binary tree SVM. Proceedings of the IEEE Workshop on Statistical Signal Processing Proceeding, Gold Coast, VIC, Australia."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"687","DOI":"10.1109\/TBME.2011.2178070","article-title":"Multi-sensor data fusion for physical activity assessment","volume":"59","author":"Liu","year":"2012","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Wang, C., and Zhang, J. (2014, January 19\u201321). An Ensemble Approach for Activity Recognition with Accelerometer in Mobile-Phone. Proceedings of the IEEE International Conference on Computational Science and Engineering IEEE Computer Society, Chengdu, China.","DOI":"10.1109\/CSE.2014.274"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1023\/A:1022859003006","article-title":"Measures of diversity in classifier ensembles and their relationship with the ensemble accuracy","volume":"51","author":"Kuncheva","year":"2003","journal-title":"Mach. Learn."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Wong, W.K., Guan, X., and Trost, S.G. (2013, January 14\u201318). Physical activity recognition from accelerometer data using a multi-scale ensemble method. Proceedings of the Twenty-Seventh AAAI Conference on Artificial Intelligence, Bellevue, WA, USA.","DOI":"10.1609\/aaai.v27i2.18997"},{"key":"ref_20","unstructured":"Ravi, N., Dandekar, N., Mysore, P., and Littman, M. (2005, January 9\u201313). Activity recognition from accelerometer data. Proceedings of the Seventeenth Conference on Innovative Applications of Artificial Intelligence, Pittsburgh, PA, USA."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Kaur, A., and Sharma, S. (2016). Human Activity Recognition Using Ensemble Modelling. International Conference on Smart Trends for Information Technology & Computer Communications, Springer.","DOI":"10.1007\/978-981-10-3433-6_35"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"113","DOI":"10.4236\/jsea.2012.512B022","article-title":"Multi-Sensor Ensemble Classifier for Activity Recognition","volume":"5","author":"Mo","year":"2012","journal-title":"J. Softw. Eng. Appl."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2141","DOI":"10.1109\/TSP.2018.2807402","article-title":"ToPs: Ensemble learning with trees of predictors","volume":"66","author":"Yoon","year":"2018","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1613\/jair.614","article-title":"Popular ensemble methods: An empirical study","volume":"11","author":"Opitz","year":"1999","journal-title":"J. Artif. Intell. Res."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1016\/j.inffus.2008.11.003","article-title":"Overfitting cautious selection of classifier ensembles with genetic algorithms","volume":"10","author":"Sabourin","year":"2009","journal-title":"Inf. Fusion"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1007\/BF00058655","article-title":"Bagging predictors","volume":"24","author":"Breiman","year":"1996","journal-title":"Mach. Learn."},{"key":"ref_27","unstructured":"Shawkat, A.B.M., and Dobele, T. (2007, January 11\u201313). A novel classifier selection approach for adaptive algorithms. Proceedings of the IEEE\/ACIS International Workshop on e-Activity, Melbourne, QLD, Australia."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Freund, Y., and Schapire, R. (1995). A decision-theoretic generalization of on-line learning and an application to boosting. Lecture Notes in Computer Science, Springer.","DOI":"10.1007\/3-540-59119-2_166"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Gashler, M., Giraud-Carrier, C., and Martinez, T. (2008, January 11\u201313). Decision tree ensemble: Small heterogeneous is better than large homogeneous. Proceedings of the IEEE Seventh International Conference on Machine Learning and Application, San Diego, CA, USA.","DOI":"10.1109\/ICMLA.2008.154"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Kuncheva, L. (2004). Combining Pattern Classifiers: Methods and Algorithms, Wiley-Interscience.","DOI":"10.1002\/0471660264"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Remya, K.R., and Ramya, J.S. (2014, January 10\u201311). Using weighted majority voting classifier combination for relation classification in biomedical texts. Proceedings of the 2014 International Conference on Control, Instrumentation, Communication and Computational Technologies (ICCICCT), Kanyakumari, India.","DOI":"10.1109\/ICCICCT.2014.6993144"},{"key":"ref_32","unstructured":"Markov, Z., and Russell, I. (2006). Introduction to data mining. An Introduction to the WEKA Data Mining System, China Machine Press."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"3230","DOI":"10.1109\/TBME.2012.2208458","article-title":"Wireless Design of a Multi-Sensor System for Physical Activity Monitoring","volume":"59","author":"Mo","year":"2012","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Gao, L., Bourke, A.K., and Nelson, J. (2014, March 11). Evaluation of Accelerometer Based Multi-Sensor versus Single Activity Recognition System. Available online: http:\/\/dx.doi.org\/10.1016\/j.medengphy.2014.02.012.","DOI":"10.1016\/j.medengphy.2014.02.012"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Gravina, R., Alinia, P., and Ghasemzadeh, H. (2016, September 13). Multi-Sensor Fusion in Body Sensor Networks: State-of-the-Art and Research Challenges. Available online: http:\/\/dx.doi.org\/10.1016\/j.inffus.2016.09.005.","DOI":"10.1016\/j.inffus.2016.09.005"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1145\/1961189.1961199","article-title":"LIBSVM: A library for support vector machines","volume":"2","author":"Chang","year":"2011","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Lapin, M., Hein, M., and Schiele, B. (2014, February 14). Learning Using Privileged Information: SVM+ and Weighted SVM. Available online: http:\/\/dx.doi.org\/10.1016\/j.neunet.2014.02.002.","DOI":"10.1016\/j.neunet.2014.02.002"}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/10\/6\/197\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T12:56:00Z","timestamp":1760187360000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/10\/6\/197"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6,4]]},"references-count":37,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2019,6]]}},"alternative-id":["info10060197"],"URL":"https:\/\/doi.org\/10.3390\/info10060197","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,6,4]]}}}