Incorporating duration information in activity recognition

Authors:
Priyanka Chaurasia;Bryan Scotney;Sally McClean;Shuai Zhang;Chris Nugent
Affiliations:
School of Computing and Information Engineering, University of Ulster, Coleraine, Northern Ireland;School of Computing and Information Engineering, University of Ulster, Coleraine, Northern Ireland;School of Computing and Information Engineering, University of Ulster, Coleraine, Northern Ireland;School of Computing and Information Engineering, University of Ulster, Coleraine, Northern Ireland;School of Computing and Mathematics, University of Ulster, Newtownabbey, Northern Ireland
Venue:
KSEM'10 Proceedings of the 4th international conference on Knowledge science, engineering and management
Year:
2010

Citing 8
Cited 1

Dining Activity Analysis Using a Hidden Markov Model

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 2 - Volume 02
Inferring Activities from Interactions with Objects

IEEE Pervasive Computing
Multi-modal emotive computing in a smart house environment

Pervasive and Mobile Computing
Location estimation in a smart home: system implementation and evaluation using experimental data

International Journal of Telemedicine and Applications - Pervasive Health Care Services and Technologies
Pervasive behavior tracking for cognitive assistance

Proceedings of the 1st international conference on PErvasive Technologies Related to Assistive Environments
Decision Support for Alzheimer's Patients in Smart Homes

CBMS '08 Proceedings of the 2008 21st IEEE International Symposium on Computer-Based Medical Systems
Evidential fusion of sensor data for activity recognition in smart homes

Pervasive and Mobile Computing
On using temporal features to create more accurate human-activity classifiers

AICS'09 Proceedings of the 20th Irish conference on Artificial intelligence and cognitive science

Duration discretisation for activity recognition

Technology and Health Care

Quantified Score

Hi-index	0.00

Visualization

Abstract

Activity recognition has become a key issue in smart home environments. The problem involves learning high level activities from low level sensor data. Activity recognition can depend on several variables; one such variable is duration of engagement with sensorised items or duration of intervals between sensor activations that can provide useful information about personal behaviour. In this paper a probabilistic learning algorithm is proposed that incorporates episode, time and duration information to determine inhabitant identity and the activity being undertaken from low level sensor data. Our results verify that incorporating duration information consistently improves the accuracy.