Assessment of the Impact of Sensor Failure in the Recognition of Activities of Daily Living

Authors:
Xin Hong;Chris Nugent;Maurice Mulvenna;Sally Mcclean;Bryan Scotney;Steven Devlin
Affiliations:
School of Computing and Mathematics and Computer Science Research Institute, University of Ulster, Northern Ireland;School of Computing and Mathematics and Computer Science Research Institute, University of Ulster, Northern Ireland;School of Computing and Mathematics and Computer Science Research Institute, University of Ulster, Northern Ireland;School of Computing and Information Engineering and Computer Science Research Institute, University of Ulster, Northern Ireland;School of Computing and Information Engineering and Computer Science Research Institute, University of Ulster, Northern Ireland;School of Computing and Mathematics and Computer Science Research Institute, University of Ulster, Northern Ireland
Venue:
ICOST '08 Proceedings of the 6th international conference on Smart Homes and Health Telematics
Year:
2008

Citing 7
Cited 1

Reasoning about Uncertain Contexts in Pervasive Computing Environments

IEEE Pervasive Computing
Inferring Activities from Interactions with Objects

IEEE Pervasive Computing
A probabilistic model with parsinomious representation for sensor fusion in recognizing activity in pervasive environment

ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 03
Context-Aware Pervasive Systems

Context-Aware Pervasive Systems
Evidential fusion of sensor data for activity recognition in smart homes

Pervasive and Mobile Computing
homeML: an open standard for the exchange of data within smart environments

ICOST'07 Proceedings of the 5th international conference on Smart homes and health telematics
Simultaneous tracking and activity recognition (STAR) using many anonymous, binary sensors

PERVASIVE'05 Proceedings of the Third international conference on Pervasive Computing

Implementing evidential activity recognition in sensorised homes

Technology and Health Care

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.