A Survey on Ambient Sensor-Based Abnormal Behaviour Detection for Elderly People in Healthcare

With advances in machine learning and ambient sensors as well the emergence of assisted living (AAL), modeling humans’ abnormal behaviour patterns has become an important assistive technology for rising elderly population recent decades. Abnormal observed from daily activities can be indicator consequences a disease that resident might suffer or occurrence hazardous incident. Therefore, tracking life detecting are significant managing health conditions smart environment. This paper provides comprehensive in-depth review, focusing on techniques profile (ADL) detect healthcare. In particular, we discuss definitions examples behaviour/activity healthcare people. We also describe public ground-truth datasets along with approaches applied to produce synthetic data when no real-world available. identify key facets detection environment, particular focus sensor types, datasets, representations, conventional deep learning-based methods. Finally, survey discusses challenges open questions, which would beneficial researchers field address.