2018/09/21 by Syed Yusha Kareem, Kareem, Syed Yusha, Luca Buoncompagni +3
Computer Science · Social Sciences · #Artificial Intelligence (cs.AI) #Context-Aware Activity Recognition Systems #FOS: Computer and information sciences #Human Pose and Action Recognition #Technology Use by Older Adults
paper · pdf · doi:10.48550/arxiv.1809.08208
openalex publication_date 2018/09/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Aging population ratios are rising significantly. Meanwhile, smart home based\nhealth monitoring services are evolving rapidly to become a viable alternative\nto traditional healthcare solutions. Such services can augment qualitative\nanalyses done by gerontologists with quantitative data. Hence, the recognition\nof Activities of Daily Living (ADL) has become an active domain of research in\nrecent times. For a system to perform human activity recognition in a\nreal-world environment, multiple requirements exist, such as scalability,\nrobustness, ability to deal with uncertainty (e.g., missing sensor data), to\noperate with multi-occupants and to take into account their privacy and\nsecurity. This paper attempts to address the requirements of scalability and\nrobustness, by describing a reasoning mechanism based on modular spatial and/or\ntemporal context models as a network of ontologies. The reasoning mechanism has\nbeen implemented in a smart home system referred to as Arianna+. The paper\npresents and discusses a use case, and experiments are performed on a simulated\ndataset, to showcase Arianna+'s modularity feature, internal working, and\ncomputational performance. Results indicate scalability and robustness for\nhuman activity recognition processes.\n