MICAR: multi-inhabitant context-aware activity recognition in home environments

• Published in: Distributed and parallel databases : an international journal Vol. 41; no. 4; pp. 571 - 602
• Main Authors: Arrotta, Luca, Bettini, Claudio, Civitarese, Gabriele
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.12.2023; Springer Nature B.V
• Subjects: Active learning; Activity recognition; Classifiers; Computer Science; Context; Data Structures; Database Management; Information Systems Applications (incl.Internet); Machine learning; Memory Structures; Operating Systems; Reasoning; Semantics; Semi-supervised learning; Sensors; Smart buildings; Special Issue on Best of MDM 2020; Activity recognition; Multi-inhabitant; Smart-home; Semi-supervised learning
• ISSN: 0926-8782; 1573-7578; 1573-7578
• DOI: 10.1007/s10619-022-07403-z

The sensor-based recognition of Activities of Daily Living (ADLs) in smart-home environments enables several important applications, including the continuous monitoring of fragile subjects in their homes for healthcare systems. The majority of the approaches in the literature assume that only one resident is living in the home. Multi-inhabitant ADLs recognition is significantly more challenging, and only a limited effort has been devoted to address this setting by the research community. One of the major open problems is called data association , which is correctly associating each environmental sensor event (e.g., the opening of a fridge door) with the inhabitant that actually triggered it. Moreover, existing multi-inhabitant approaches rely on supervised learning, assuming a high availability of labeled data. However, collecting a comprehensive training set of ADLs (especially in multiple-residents settings) is prohibitive. In this work, we propose MICAR: a novel multi-inhabitant ADLs recognition approach that combines semi-supervised learning and knowledge-based reasoning. Data association is performed by semantic reasoning, combining high-level context information (e.g., residents’ postures and semantic locations) with triggered sensor events. The personalized stream of sensor events is processed by an incremental classifier, that is initialized with a limited amount of labeled ADLs. A novel cache-based active learning strategy is adopted to continuously improve the classifier. Our results on a dataset where up to 4 subjects perform ADLs at the same time show that MICAR reliably recognizes individual and joint activities while triggering a significantly low number of active learning queries.