Abnormal human behavioral pattern detection in assisted living environments

Abstract

In recent years, there is a growing interest about assisted living environments especially for the elderly who live alone, due to the increasing number of aged people. In order for them to live safe and healthy, we need to detect abnormal behavior that may cause severe and emergent situations for the elderly. In this work, we suggest a method that detects abnormal behavior using wireless sensor networks. We model an episode that is a series of events, which includes spatial and temporal information about the subject being monitored. We define a similarity scoring function that compares two episodes taking into consideration temporal aspects. We propose a way to determine a threshold to divide episodes into two groups that reduces wrong classification. Weights on individual functions that consist the similarity function are determined experimentally so that they can produce the good results in terms of area under curve in receiver operating characteristic (ROC) curve.

Behavior Rule Specification-Based Intrusion Detection for Safety Critical Medical Cyber Physical Systems

“…We exemplified the utility with VSMs and demonstrated that the detection probability of the medical device approaches one (that is, we can always catch the attacker without false negatives) while bounding the false alarm probability to below 5% for reckless attackers and below 25% for random and opportunistic attackers over a wide range of environment noise levels. Through a comparative analysis, we demonstrated that our behavior-rule specification-based IDS technique outperforms existing techniques [28], [32] based on anomaly intrusion detection.…”

“…We perform a comparative study using the IDS design by Park et al [28] and Tsang and Kwong [32] as baseline schemes. We only included these two studies in the comparative performance analysis because other studies did not provide adequate data.…”

“…Park et al [28] propose a semi-supervised anomaly-based IDS targeted for assisted living environments. Their design is behavior-based and audits series of events which they call episodes.…”

“…We will use Park et al [28] and Tsang and Kwong [32] as base schemes against which BSID will be compared because no others provide meaningful p fp /p fn data for a comparative analysis.…”

A review on vision techniques applied to Human Behaviour Analysis for Ambient-Assisted Living

“…Although, many of the reviewed works in the field of behaviour analysis and AAL [18,36,37,44,61,73,85,120,127] are based on other sensor devices (lights and use of appliances [18,44,73]; pressure mats [18]; basic motion detectors -such as door sensors or similar- [37,85,127]; infrared sensors -SMDs- [18,36,44]; health monitoring [127]; etcetera).…”