{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T16:01:19Z","timestamp":1776096079896,"version":"3.50.1"},"reference-count":49,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2020,12,17]],"date-time":"2020-12-17T00:00:00Z","timestamp":1608163200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. ACM Interact. Mob. Wearable Ubiquitous Technol."],"published-print":{"date-parts":[[2020,12,17]]},"abstract":"<jats:p>Human Activity Recognition (HAR) from devices like smartphone accelerometers is a fundamental problem in ubiquitous computing. Machine learning based recognition models often perform poorly when applied to new users that were not part of the training data. Previous work has addressed this challenge by personalizing general recognition models to the unique motion pattern of a new user in a static batch setting. They require target user data to be available upfront. The more challenging online setting has received less attention. No samples from the target user are available in advance, but they arrive sequentially. Additionally, the motion pattern of users may change over time. Thus, adapting to new and forgetting old information must be traded off. Finally, the target user should not have to do any work to use the recognition system by, say, labeling any activities. Our work addresses all of these challenges by proposing an unsupervised online domain adaptation algorithm. Both classification and personalization happen continuously and incrementally in real time. Our solution works by aligning the feature distributions of all subjects, be they sources or the target, in hidden neural network layers. To this end, we normalize the input of a layer with user-specific mean and variance statistics. During training, these statistics are computed over user-specific batches. In the online phase, they are estimated incrementally for any new target user.<\/jats:p>","DOI":"10.1145\/3432230","type":"journal-article","created":{"date-parts":[[2020,12,18]],"date-time":"2020-12-18T15:39:14Z","timestamp":1608305954000},"page":"1-20","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":32,"title":["Incremental Real-Time Personalization in Human Activity Recognition Using Domain Adaptive Batch Normalization"],"prefix":"10.1145","volume":"4","author":[{"given":"Alan","family":"Mazankiewicz","sequence":"first","affiliation":[{"name":"Karlsruhe Institute of Technology"}]},{"given":"Klemens","family":"B\u00f6hm","sequence":"additional","affiliation":[{"name":"Karlsruhe Institute of Technology"}]},{"given":"Mario","family":"Berges","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}]}],"member":"320","published-online":{"date-parts":[[2020,12,18]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.09.074"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.3390\/s140406474"},{"key":"e_1_2_1_3_1","volume-title":"Unsupervised Domain Adaptation for Human Activity Recognition. In International Conference on Intelligent Data Engineering and Automated Learning. Springer, 623--630","author":"Barbosa Paulo","year":"2018"},{"key":"e_1_2_1_4_1","volume-title":"A theory of learning from different domains. Machine learning 79, 1-2","author":"Ben-David Shai","year":"2010"},{"key":"e_1_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Shai Ben-David John Blitzer Koby Crammer and Fernando Pereira. 2007. Analysis of representations for domain adaptation. In Advances in neural information processing systems. 137--144. Shai Ben-David John Blitzer Koby Crammer and Fernando Pereira. 2007. Analysis of representations for domain adaptation. In Advances in neural information processing systems. 137--144.","DOI":"10.7551\/mitpress\/7503.003.0022"},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6630784"},{"key":"e_1_2_1_7_1","volume-title":"Personalized Activity Recognition with Deep Triplet Embeddings. arXiv preprint arXiv:2001.05517","author":"Burns David M","year":"2020"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.542"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68560-1_32"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3380985"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/2756713.2756718"},{"key":"e_1_2_1_12_1","volume-title":"Proc. of Workshop on Space, Time and Ambient Intelligence, IJCAI. Citeseer, 24--29","author":"Cvetkovic Bozidara","year":"2011"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.01.008"},{"key":"e_1_2_1_14_1","first-page":"11","article-title":"Incremental calculation of weighted mean and variance","volume":"4","author":"Finch Tony","year":"2009","journal-title":"University of Cambridge"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-26401-1_25"},{"key":"e_1_2_1_16_1","unstructured":"Alexander Gepperth and Barbara Hammer. 2016. Incremental learning algorithms and applications. Alexander Gepperth and Barbara Hammer. 2016. Incremental learning algorithms and applications."},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123021.3123044"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/2770421.2770437"},{"key":"e_1_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2015.2489688"},{"key":"e_1_2_1_20_1","volume-title":"Proceedings of the 32nd International Conference on International Conference on Machine Learning -","volume":"37","author":"Ioffe Sergey","year":"2015"},{"key":"e_1_2_1_21_1","volume-title":"Jessica Sena, and William Robson Schwartz.","author":"Jordao Artur","year":"2018"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2030112.2030160"},{"key":"e_1_2_1_23_1","volume-title":"Revisiting batch normalization for practical domain adaptation. arXiv preprint arXiv:1603.04779","author":"Li Yanghao","year":"2016"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2370216.2370441"},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISWC.2011.24"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2809700"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593862"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00397"},{"key":"e_1_2_1_29_1","volume-title":"Classifier personalization for activity recognition using wrist accelerometers","author":"Mannini Andrea","year":"2018"},{"key":"e_1_2_1_30_1","volume-title":"Proceedings of the 2015 XSEDE Conference: Scientific Advancements Enabled by Enhanced Cyberinfrastructure (St","author":"Nystrom Nicholas A."},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITB.2010.2055060"},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3369818"},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1254"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2493988.2494349"},{"key":"e_1_2_1_36_1","volume-title":"Thirty-Second AAAI Conference on Artificial Intelligence.","author":"Rokni Seyed Ali","year":"2018"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2018.8512533"},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-61030-6_23"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01081-2_23"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-3758(00)00115-4"},{"key":"e_1_2_1_42_1","first-page":"5151","article-title":"Incremental Learning to Personalize Human Activity Recognition Models","volume":"19","author":"Siirtola Pekka","year":"2019","journal-title":"The Importance of Human AI Collaboration. Sensors"},{"key":"e_1_2_1_43_1","volume-title":"Cross-subject transfer learning in human activity recognition systems using generative adversarial networks. arXiv preprint arXiv:1903.12489","author":"Soleimani Elnaz","year":"2019"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/PERCOM.2017.7917864"},{"key":"e_1_2_1_45_1","volume-title":"Self-labeled techniques for semi-supervised learning: taxonomy, software and empirical study. Knowledge and Information systems 42, 2","author":"Triguero Isaac","year":"2015"},{"key":"e_1_2_1_46_1","volume-title":"Informatics","author":"Twomey Niall"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3265689.3265705"},{"key":"e_1_2_1_48_1","volume-title":"Workshops at the Twenty-Sixth AAAI Conference on Artificial Intelligence.","author":"Weiss Gary Mitchell","year":"2012"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2940729"},{"key":"e_1_2_1_50_1","unstructured":"Zhongtang Zhao Yiqiang Chen Junfa Liu Zhiqi Shen and Mingjie Liu. 2011. Cross-people mobile-phone based activity recognition. In Twenty-second international joint conference on artificial intelligence. Zhongtang Zhao Yiqiang Chen Junfa Liu Zhiqi Shen and Mingjie Liu. 2011. Cross-people mobile-phone based activity recognition. In Twenty-second international joint conference on artificial intelligence."}],"container-title":["Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3432230","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3432230","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:47:09Z","timestamp":1750193229000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3432230"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,17]]},"references-count":49,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2020,12,17]]}},"alternative-id":["10.1145\/3432230"],"URL":"https:\/\/doi.org\/10.1145\/3432230","relation":{},"ISSN":["2474-9567"],"issn-type":[{"value":"2474-9567","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,12,17]]},"assertion":[{"value":"2020-12-18","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}