Fusion of Audio and Temporal Multimodal Data by Spreading Activation for Dweller Localisation in a Smart Home
Pedro Chahuara, François Portet, Michel Vacher · 2011
In this paper, an approach to locate a person using non visual sensors in a smart home is presented. The information extracted from these sensors gives uncertain evidence about the location of a person. To improve robustness of location, audio information (used for voice command) is fused with classical domotic sensor data using a two-level dynamic network and using an adapted spreading activation method that considers the temporal dimension to deal with evidence that expire. The automatic location was tested within two different smart homes using data from experiments involving 25 participants. The preliminary results show that an accuracy of 90 % can be reached using several uncertain sources. 1