Towards the detection of temporal behavioural patterns in intelligent environments

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-network-driven embedded agent able to work with online, real-time data from unobtrusive low-level sensors and actuators. We present experimental results that show that our agent is able to detect temporal patterns along with spatial similarity associations found in human behaviours and activities, in everyday living environments