Anomaly Detection in the Elderly Daily Behavior

The increasing availability of sensors and intelligent objects enables new functionalities and services. In the Ambient Assisted Living (AAL) domain, such technologies can be used for monitoring and reasoning about the older people behavior to detect possible anomalous situations, which could be a sign of the next onset of chronic illness or initial physical and cognitive decline. We propose an approach to detecting abnormal behavior by developing a profiling strategy (in which task models specify the normal behavior), which can also work in case of rare anomaly data. Events corresponding to the user behavior is detecting by a middleware software(Context Manager). Afterward, our algorithm compares the planned and actual behavior to identify if any deviation occurred and also defines to which category the anomaly belongs. The resulting environment should be able to generate multi-modal actions (i.e alarms, reminders) based on detected anomalous behavior, aiming to provide useful support to improve older people well-being.