{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T22:16:08Z","timestamp":1767651368509,"version":"3.38.0"},"reference-count":48,"publisher":"SAGE Publications","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AIS"],"published-print":{"date-parts":[[2021,11,23]]},"abstract":"<jats:p>One of the major challenges in Human Activity Recognition (HAR) based on machine learning is the scarcity of labeled data. Indeed, collecting a sufficient amount of training data to build a reliable recognition problem is often prohibitive. Among the many solutions in the literature to mitigate this issue, collaborative learning is emerging as a promising direction to distribute the annotation burden over multiple users that cooperate to build a shared recognition model. One of the major issues of existing methods is that they assume a static activity model with a fixed set of target activities. In this paper, we propose a novel approach that is based on Growing When Required (GWR) neural networks. A GWR network continuously adapts itself according to the input training data, and hence it is particularly suited when the users share heterogeneous sets of activities. Like in federated learning, for the sake of privacy preservation, each user contributes to the global activity classifier by sharing personal model parameters, and not by directly sharing data. In order to further mitigate privacy threats, we implement a strategy to avoid releasing model parameters that may indirectly reveal information about activities that the user specifically marked as private. Our results on two well-known publicly available datasets show the effectiveness and the flexibility of our approach.<\/jats:p>","DOI":"10.3233\/ais-210018","type":"journal-article","created":{"date-parts":[[2021,11,5]],"date-time":"2021-11-05T18:45:59Z","timestamp":1636137959000},"page":"433-452","source":"Crossref","is-referenced-by-count":1,"title":["Collaborative activity recognition with heterogeneous activity sets and privacy preferences"],"prefix":"10.1177","volume":"13","author":[{"given":"Gabriele","family":"Civitarese","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Milan, Italy. E-mails:\u00a0gabriele.civitarese@unimi.it,\u00a0matteo.zampatti@studenti.unimi.it,\u00a0claudio.bettini@unimi.it"}]},{"given":"Juan","family":"Ye","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of St. Andrews, UK. E-mail:\u00a0juan.ye@st-andrews.ac.uk"}]},{"given":"Matteo","family":"Zampatti","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Milan, Italy. E-mails:\u00a0gabriele.civitarese@unimi.it,\u00a0matteo.zampatti@studenti.unimi.it,\u00a0claudio.bettini@unimi.it"}]},{"given":"Claudio","family":"Bettini","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Milan, Italy. E-mails:\u00a0gabriele.civitarese@unimi.it,\u00a0matteo.zampatti@studenti.unimi.it,\u00a0claudio.bettini@unimi.it"}]}],"member":"179","reference":[{"key":"10.3233\/AIS-210018_ref1","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1016\/j.neucom.2014.09.074","article-title":"Adaptive mobile activity recognition system with evolving data streams","volume":"150","author":"Abdallah","year":"2015","journal-title":"Neurocomputing"},{"key":"10.3233\/AIS-210018_ref2","doi-asserted-by":"crossref","unstructured":"Z.S.\u00a0Abdallah, M.M.\u00a0Gaber, B.\u00a0Srinivasan and S.\u00a0Krishnaswamy, Activity recognition with evolving data streams: A review, ACM Computing Surveys (CSUR) 51(4) (2018), 71.","DOI":"10.1145\/3158645"},{"key":"10.3233\/AIS-210018_ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-02397-2_2"},{"key":"10.3233\/AIS-210018_ref4","unstructured":"A.\u00a0Avci, S.\u00a0Bosch, M.\u00a0Marin-Perianu, R.\u00a0Marin-Perianu and P.\u00a0Havinga, Activity recognition using inertial sensing for healthcare, wellbeing and sports applications: A survey, in: 23th International Conference on Architecture of Computing Systems 2010, 2010, pp.\u00a01\u201310, VDE."},{"issue":"11","key":"10.3233\/AIS-210018_ref5","doi-asserted-by":"publisher","first-page":"1649","DOI":"10.1093\/comjnl\/bxt075","article-title":"Recognizing daily and sports activities in two open source machine learning environments using body-worn sensor units","volume":"57","author":"Barshan","year":"2014","journal-title":"The Computer Journal"},{"key":"10.3233\/AIS-210018_ref6","doi-asserted-by":"crossref","unstructured":"C.\u00a0Bettini, G.\u00a0Civitarese and R.\u00a0Presotto, CAVIAR: Context-driven active and incremental activity recognition, Knowledge-Based Systems (2020), 105816.","DOI":"10.1016\/j.knosys.2020.105816"},{"key":"10.3233\/AIS-210018_ref7","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1016\/j.pmcj.2014.09.010","article-title":"Privacy protection in pervasive systems: State of the art and technical challenges","volume":"17","author":"Bettini","year":"2015","journal-title":"Pervasive and Mobile Computing"},{"key":"10.3233\/AIS-210018_ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3380985"},{"issue":"6","key":"10.3233\/AIS-210018_ref9","doi-asserted-by":"publisher","first-page":"790","DOI":"10.1109\/TSMCC.2012.2198883","article-title":"Sensor-based activity recognition","volume":"42","author":"Chen","year":"2012","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews)"},{"key":"10.3233\/AIS-210018_ref12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.pmcj.2019.04.004","article-title":"Cross-position activity recognition with stratified transfer learning","volume":"57","author":"Chen","year":"2019","journal-title":"Pervasive and Mobile Computing"},{"issue":"8","key":"10.3233\/AIS-210018_ref14","doi-asserted-by":"publisher","first-page":"1667","DOI":"10.1162\/neco.1997.9.8.1667","article-title":"Convergence and ordering of kohonen\u2019s batch map","volume":"9","author":"Cheng","year":"1997","journal-title":"Neural Comput."},{"key":"10.3233\/AIS-210018_ref15","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.pmcj.2019.04.006","article-title":"newNECTAR: Collaborative active learning for knowledge-based probabilistic activity recognition","volume":"56","author":"Civitarese","year":"2019","journal-title":"Pervasive and Mobile Computing"},{"issue":"3","key":"10.3233\/AIS-210018_ref17","doi-asserted-by":"publisher","first-page":"537","DOI":"10.1007\/s10115-013-0665-3","article-title":"Transfer learning for activity recognition: A survey","volume":"36","author":"Cook","year":"2013","journal-title":"Knowledge and information systems"},{"key":"10.3233\/AIS-210018_ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3384419.3430735"},{"issue":"10","key":"10.3233\/AIS-210018_ref19","doi-asserted-by":"publisher","first-page":"1568","DOI":"10.1016\/j.neunet.2006.02.009","article-title":"Growing hierarchical tree SOM: An unsupervised neural network with dynamic topology","volume":"19","author":"Forti","year":"2006","journal-title":"Neural networks"},{"issue":"1","key":"10.3233\/AIS-210018_ref20","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.neunet.2005.04.006","article-title":"An incremental network for on-line unsupervised classification and topology learning","volume":"19","author":"Furao","year":"2006","journal-title":"Neural networks"},{"key":"10.3233\/AIS-210018_ref21","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1016\/j.knosys.2017.01.025","article-title":"Probabilistic ontology based activity recognition in smart homes using Markov logic network","volume":"121","author":"Gayathri","year":"2017","journal-title":"Knowledge-Based Systems"},{"key":"10.3233\/AIS-210018_ref22","doi-asserted-by":"crossref","unstructured":"D.\u00a0Guan, W.\u00a0Yuan, Y.-K.\u00a0Lee, A.\u00a0Gavrilov and S.\u00a0Lee, Activity recognition based on semi-supervised learning, in: Embedded and Real-Time Computing Systems and Applications, 2007. RTCSA 2007. 13th IEEE International Conference on, 2007, pp.\u00a0469\u2013475, IEEE.","DOI":"10.1109\/RTCSA.2007.17"},{"key":"10.3233\/AIS-210018_ref23","doi-asserted-by":"crossref","unstructured":"E.\u00a0Hoque and J.\u00a0Stankovic, AALO: Activity recognition in smart homes using active learning in the presence of overlapped activities, in: Pervasive Computing Technologies for Healthcare (PervasiveHealth), 2012 6th International Conference on, 2012, pp.\u00a0139\u2013146, IEEE.","DOI":"10.4108\/icst.pervasivehealth.2012.248600"},{"key":"10.3233\/AIS-210018_ref24","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1016\/j.pmcj.2016.08.017","article-title":"Active learning enabled activity recognition","volume":"38","author":"Hossain","year":"2017","journal-title":"Pervasive and Mobile Computing"},{"key":"10.3233\/AIS-210018_ref25","doi-asserted-by":"publisher","first-page":"193655","DOI":"10.1109\/ACCESS.2020.3033589","article-title":"Graph-based semi-supervised learning for activity labeling in health smart home","volume":"8","author":"Hu","year":"2020","journal-title":"IEEE Access"},{"issue":"9","key":"10.3233\/AIS-210018_ref26","doi-asserted-by":"publisher","first-page":"1464","DOI":"10.1109\/5.58325","article-title":"The self-organizing map","volume":"78","author":"Kohonen","year":"1990","journal-title":"Proceedings of the IEEE"},{"issue":"14","key":"10.3233\/AIS-210018_ref27","doi-asserted-by":"publisher","first-page":"6067","DOI":"10.1016\/j.eswa.2014.04.037","article-title":"Unsupervised learning for human activity recognition using smartphone sensors","volume":"41","author":"Kwon","year":"2014","journal-title":"Expert Systems with Applications"},{"issue":"3","key":"10.3233\/AIS-210018_ref28","doi-asserted-by":"publisher","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":"2012","journal-title":"IEEE communications surveys & tutorials"},{"key":"10.3233\/AIS-210018_ref29","first-page":"134","article-title":"Unsupervised clustering for abnormality detection based on the tri-axial accelerometer","volume":"2009","author":"Lee","year":"2009","journal-title":"ICCAS-SICE"},{"key":"10.3233\/AIS-210018_ref30","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1016\/j.neucom.2013.05.044","article-title":"Activity recognition with Android phone using mixture-of-experts co-trained with labeled and unlabeled data","volume":"126","author":"Lee","year":"2014","journal-title":"Neurocomputing"},{"key":"10.3233\/AIS-210018_ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2426656.2426663"},{"key":"10.3233\/AIS-210018_ref32","doi-asserted-by":"crossref","unstructured":"B.\u00a0Longstaff, S.\u00a0Reddy and D.\u00a0Estrin, Improving activity classification for health applications on mobile devices using active and semi-supervised learning, in: Pervasive Computing Technologies for Healthcare (PervasiveHealth), 2010 4th International Conference on Pervasive Computing Technologies for Healthcare, 2010, pp.\u00a01\u20137, IEEE.","DOI":"10.4108\/ICST.PERVASIVEHEALTH2010.8851"},{"issue":"8\u20139","key":"10.3233\/AIS-210018_ref33","doi-asserted-by":"publisher","first-page":"1041","DOI":"10.1016\/S0893-6080(02)00078-3","article-title":"A self-organising network that grows when required","volume":"15","author":"Marsland","year":"2002","journal-title":"Neural networks"},{"key":"10.3233\/AIS-210018_ref34","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.pmcj.2017.05.003","article-title":"iKnow: Ontology-driven situational awareness for the recognition of activities of daily living","volume":"40","author":"Meditskos","year":"2017","journal-title":"Pervasive and Mobile Computing"},{"key":"10.3233\/AIS-210018_ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CIT\/IUCC\/DASC\/PICOM.2015.170"},{"key":"10.3233\/AIS-210018_ref36","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1016\/j.pmcj.2012.11.004","article-title":"Dynamic sensor data segmentation for real-time knowledge-driven activity recognition","volume":"10","author":"Okeyo","year":"2014","journal-title":"Pervasive and Mobile Computing"},{"issue":"1","key":"10.3233\/AIS-210018_ref37","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1109\/TKDE.2018.2878698","article-title":"Deep private-feature extraction","volume":"32","author":"Osia","year":"2018","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"issue":"9","key":"10.3233\/AIS-210018_ref38","first-page":"2000","article-title":"The growing hierarchical neural gas self-organizing neural network","volume":"28","author":"Palomo","year":"2016","journal-title":"IEEE transactions on neural networks and learning systems"},{"key":"10.3233\/AIS-210018_ref39","doi-asserted-by":"crossref","unstructured":"E.J.\u00a0Palomo, M.A.\u00a0Molina-Cabello, E.\u00a0L\u00f3pez-Rubio and R.M.\u00a0Luque-Baena, A new self-organizing neural gas model based on Bregman divergences, in: 2018 International Joint Conference on Neural Networks (IJCNN), 2018, pp.\u00a01\u20138, IEEE.","DOI":"10.1109\/IJCNN.2018.8489545"},{"key":"10.3233\/AIS-210018_ref40","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/j.neunet.2017.09.001","article-title":"Lifelong learning of human actions with deep neural network self-organization","volume":"96","author":"Parisi","year":"2017","journal-title":"Neural Networks"},{"key":"10.3233\/AIS-210018_ref41","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2018.00078"},{"key":"10.3233\/AIS-210018_ref43","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"10.3233\/AIS-210018_ref44","unstructured":"A.\u00a0Reiss and D.\u00a0Stricker, Pamap2 physical activity monitoring data set, Retrieved April 30 (2012), 2019."},{"issue":"7","key":"10.3233\/AIS-210018_ref45","doi-asserted-by":"publisher","first-page":"1061","DOI":"10.1007\/s00521-010-0428-y","article-title":"An incremental online semi-supervised active learning algorithm based on self-organizing incremental neural network","volume":"20","author":"Shen","year":"2011","journal-title":"Neural Computing and Applications"},{"key":"10.3233\/AIS-210018_ref46","doi-asserted-by":"publisher","DOI":"10.1145\/2810103.2813687"},{"key":"10.3233\/AIS-210018_ref47","doi-asserted-by":"crossref","unstructured":"K.\u00a0Sozinov, V.\u00a0Vlassov and S.\u00a0Girdzijauskas, Human activity recognition using federated learning, in: 2018 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Ubiquitous Computing & Communications, Big Data & Cloud Computing, Social Computing & Networking, Sustainable Computing & Communications (ISPA\/IUCC\/BDCloud\/SocialCom\/SustainCom), 2018, pp.\u00a01103\u20131111, IEEE.","DOI":"10.1109\/BDCloud.2018.00164"},{"issue":"3","key":"10.3233\/AIS-210018_ref48","doi-asserted-by":"publisher","first-page":"829","DOI":"10.1109\/TASE.2013.2256349","article-title":"An unsupervised approach for automatic activity recognition based on hidden Markov model regression","volume":"10","author":"Trabelsi","year":"2013","journal-title":"IEEE Transactions on Automation Science and Engineering"},{"key":"10.3233\/AIS-210018_ref49","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.patrec.2018.02.010","article-title":"Deep learning for sensor-based activity recognition: A survey","volume":"119","author":"Wang","year":"2019","journal-title":"Pattern Recognition Letters"},{"key":"10.3233\/AIS-210018_ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.113069"},{"issue":"2","key":"10.3233\/AIS-210018_ref52","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3298981","article-title":"Federated machine learning: Concept and applications","volume":"10","author":"Yang","year":"2019","journal-title":"ACM Transactions on Intelligent Systems and Technology (TIST)"},{"key":"10.3233\/AIS-210018_ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3368272"},{"issue":"4","key":"10.3233\/AIS-210018_ref54","first-page":"1","article-title":"USMART: An unsupervised semantic mining activity recognition technique","volume":"4","author":"Ye","year":"2014","journal-title":"ACM Transactions on Interactive Intelligent Systems (TiiS)"}],"container-title":["Journal of Ambient Intelligence and Smart Environments"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/AIS-210018","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T10:21:47Z","timestamp":1741688507000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/AIS-210018"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,23]]},"references-count":48,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.3233\/ais-210018","relation":{},"ISSN":["1876-1372","1876-1364"],"issn-type":[{"type":"electronic","value":"1876-1372"},{"type":"print","value":"1876-1364"}],"subject":[],"published":{"date-parts":[[2021,11,23]]}}}