Chua S-LFoo LKGuesgen HWMarsland SMobilio MMicucci D2023-11-132023-11-202022-11-032023-11-132023-11-202022-11-03Chua S-L, Foo LK, Guesgen HW, Marsland S. (2022). Incremental Learning of Human Activities in Smart Homes.. Sensors (Basel). 22. 21. (pp. 8458-).1424-8220https://mro.massey.ac.nz/handle/10179/69130Sensor-based human activity recognition has been extensively studied. Systems learn from a set of training samples to classify actions into a pre-defined set of ground truth activities. However, human behaviours vary over time, and so a recognition system should ideally be able to continuously learn and adapt, while retaining the knowledge of previously learned activities, and without failing to highlight novel, and therefore potentially risky, behaviours. In this paper, we propose a method based on compression that can incrementally learn new behaviours, while retaining prior knowledge. Evaluation was conducted on three publicly available smart home datasets.(c) 2022 The Author/sCC BYhttps://creativecommons.org/licenses/by/4.0/activity recognitionincremental learningnovelty detectionprediction by partial matchingsmart homesHumansHuman ActivitiesMachine LearningJournal article10.3390/s222184581424-8220journal-article8458-https://www.ncbi.nlm.nih.gov/pubmed/363661548458s22218458