Many countries are facing the problem of caring economically for their ageing population. One approach to this is the development of environments which possess ambient intelligence that will provide care for older people while assisting them with their everyday life activities. One function that is required in care provision is spotting abnormal behaviours as this might be an indicator of a problem requiring attention from a carer. Agent technology can be employed to detect abnormalities by first learning a normal set of personal behaviours and then detecting deviations from these. This paper presents a novel connectionist embedded agent architecture that combines the use of unobtrusive and relatively simple sensors and employs a constructive algorithm with temporal capabilities which is able to recognize different high level activities (such as "sleeping", "working at computer", "eating"), and identify abnormal behaviours. The network is trained in an online mode, and is able to adapt and expand itself as new data are made available over time or it can add new output nodes to represent new classes or accommodate the abnormal instances. The developed connectionist approach is not computationally demanding and hence it can be integrated into the limited processor-power embedded computing platforms used in intelligent domestic environments.

The importance of ubiquitous environments has increased in recent years as it has been recognized as a paradigm that can improve the quality of life of many sectors of the population especially care of elderly people by providing automated environments that adapt and respond to its inhabitants' needs. The aim of the work presented here is to provide a solution to the problem of recognition and detection of human behaviours inside ubiquitous environments by using a neural-network driven embedded agent working with online, real-time data from a network of unobtrusive low-level sensors. The final objective of this system was to classify a 'normal' pattern of activities, and sense deviations from it, which could be employed for home care applications.

No abstract

Ubiquitous computing applications propose new and creative solutions to every day needs. This paper addresses the issue of recognition of every day activities inside pervasive domestic environments in order to identify patterns of behaviour that can be later used to support care systems by detecting changes to those patterns. Our system uses a temporal neural-networkdriven embedded agent able to work with online, realtime data from unobtrusive low-level sensors and actuators. We present experimental results that show our agent is able to detect temporal patterns along with spatial similarity associations found in human behaviours and activities, in everyday living environments.

No abstract