Activity monitoring: noticing interesting changes in behavior
KDD '99 Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data mining
Pattern Classification (2nd Edition)
Pattern Classification (2nd Edition)
Detecting Rare Events in Video Using Semantic Primitives with HMM
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 4 - Volume 04
Semi-Supervised Adapted HMMs for Unusual Event Detection
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Human activity recognition in pervasive health-care: Supporting efficient remote collaboration
Journal of Network and Computer Applications
Unsupervised activity recognition using automatically mined common sense
AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 1
Behavioral Patterns of Older Adults in Assisted Living
IEEE Transactions on Information Technology in Biomedicine
Health-status monitoring through analysis of behavioral patterns
IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans
Abnormal behaviours identification for an elder's life activities using dissimilarity measurements
Proceedings of the 4th International Conference on PErvasive Technologies Related to Assistive Environments
A review on vision techniques applied to Human Behaviour Analysis for Ambient-Assisted Living
Expert Systems with Applications: An International Journal
Behavioural pattern identification and prediction in intelligent environments
Applied Soft Computing
A home daily activity simulation model for the evaluation of lifestyle monitoring systems
Computers in Biology and Medicine
Hi-index | 0.00 |
As a consequence of the growing number of older and vulnerable people, health and care providers are increasingly considering new approaches to support people in their own homes. In this context, lifestyle reassurance analyses data collected from a range of sensors to determine a person's `routine' and highlights any important changes. This paper proposes a new approach for detection of individual deviation from normal behaviour focusing on building probabilistic models of behaviour based on a set of activity attributes. Models are trained using only normal behaviour. Variations from the models are considered as abnormal behaviours and these can be highlighted for subsequent review or intervention. Case study experiments with real life data suggest that some users' activities follow regular patterns and that these patterns can be learned with probabilistic models.