Smart Homes offer improved living conditions and levels of independence for the elderly population who require support with both physical and cognitive functions. Within these environments sensing technologies provide a key facility to monitor the behaviour of the person and their interactions with the living environment. In this paper we investigate the effects of sensor failures on the `trust' of activity inference processing. We introduce a sensor evidence reasoning network which has been developed for ADL recognition along with the ability of handling uncertainty that may occur at a sensor level. Details of the initial experiments which have been conducted in the assessment of ADLs in a smart laboratory environment using this model are presented. Finally, we present the findings from the analysis on experimental and simulation data taking into consideration the impact of sensor failure on the overall stage of inference processing.
|Name||LECTURE NOTES IN COMPUTER SCIENCE|
|Conference||6th International Conference on Smart Homes and Health Telematics (ICOST 2008)|
|Period||1/06/08 → …|
- Smart homes
- activities of daily living
- sensing technologies
- evidence fusion