A context-aware approach for long-term behavioural change detection and abnormality prediction in ambient assisted living

This research aims to describe pattern recognition models for detecting behavioural and health-related changes in a patient who is monitored continuously in an assisted living environment. The early anticipation of anomalies can improve the rate of disease prevention. Here we present different learning techniques for predicting abnormalities and behavioural trends in various user contexts. In this paper we described a Hidden Markov Model based approach for detecting abnormalities in daily activities, a process of identifying irregularity in routine behaviours from statistical histories and an exponential smoothing technique to predict future changes in various vital signs. The outcomes of these different models are then fused using a fuzzy rule-based model for making the final guess and sending an accurate context-aware alert to the health-care service providers. We demonstrated the proposed techniques by evaluating some case studies for different patient scenarios in ambient assisted living. •We developed a novel change detection framework for context-aware monitoring.•We described a Hidden Markov Model for detecting abnormalities in daily activities.•We developed a statistical process to identify irregularity in routine behaviours.•We presented a disease forecasting technique using Holt׳s liner trend method.•We built a rule-based fuzzy fusion model for making context-aware decision.