Title: Approach of context-aware computing with uncertainty for ubiquitous active service

Authors: De-gan Zhang, Hua Zhang, Hong-yun Ning

Addresses: Tianjin Key Lab of Intelligent Computing and Novel Software Technology, Tianjin University of Technology, 300191, P.R. China; Key Laboratory of Computer Vision and System, Tianjin University of Technology, Ministry of Education, 300191, Tianjin, P.R. China; Key Lab of Industrial Controlling Technology, Zhejiang University, Hangzhou, 310027, P.R. China. ' Tianjin Key Lab of Intelligent Computing and Novel Software Technology, Tianjin University of Technology, 300191, P.R. China; Key Laboratory of Computer Vision and System, Tianjin University of Technology, Ministry of Education, 300191, Tianjin, P.R. China. ' Tianjin Key Lab of Intelligent Computing and Novel Software Technology, Tianjin University of Technology, 300191, P.R. China; Key Laboratory of Computer Vision and System, Tianjin University of Technology, Ministry of Education, 300191, Tianjin, P.R. China

Abstract: As we know, context-aware computing with uncertainty is an important part of pervasive computing with uncertainty, which includes three aspects: obtaining of context information with uncertainty, modelling and fusing of context information with uncertainty and management of context information with uncertainty. Among these, fusing of context information with uncertainty is the most important. Because multi-source evidence context-aware information with uncertainty is dynamic and changing randomly, in order to ensure the QoS of different application fields based on pervasive computing, we modified the fusion method of evidence information after considering context|s reliability, time-efficiency and relativity, which has improved the classic combination rule of D-S evidence theory when used in the pervasive computing paradigm and overcome its shortcoming. All these suggested technologies have been successfully integrated and demonstrated in our project, including context-aware computing by fusing of dynamic multi-source evidence information with uncertainty. The efficiency of our researches has been tested by application practice and validation of the demo.

Keywords: context-aware computing; D-S evidence theory; uncertainty; reliability; time-efficiency; relativity; context awareness; pervasive computing; ubiquitous computing; information fusion; modelling; QoS; quality of service.

DOI: 10.1504/IJMIC.2009.028869

International Journal of Modelling, Identification and Control, 2009 Vol.8 No.1, pp.10 - 17

Published online: 09 Oct 2009 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article