Prediction of humans' activity for learning the behaviors of electrical appliances in an intelligent ambiant environment

Javier Gil-Quijano (1) , Nicolas Sabouret (1) , Cédric Herpson (1)

1 SMA - Systèmes Multi-Agents

In this paper we propose a mechanism of prediction of domestic human activity in a smart home context. We use those predictions to adapt the behavior of home appliances whose impact on the environment is delayed (for example the heating). The behaviors of appliances are built by a reinforcement learning mechanism. We compare the behavior built by the learning approach with both a merely reactive behavior and a state-remanent behavior.

Domaines: Informatique [cs]

Javier Gil-Quijano, Nicolas Sabouret, Cédric Herpson. Prediction of humans' activity for learning the behaviors of electrical appliances in an intelligent ambiant environment. 2010 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, Aug 2010, Toronto, ON, Canada. pp.283-286, ⟨10.1109/WI-IAT.2010.283⟩. ⟨hal-01292235⟩