UCT CS Research Document Archive

On the Relevance of Using Bayesian Belief Networks in Wireless Sensor Networks Situation Recognition

Bagula, A., I. Osunmakinde and M. Zennaro (2010) On the Relevance of Using Bayesian Belief Networks in Wireless Sensor Networks Situation Recognition. Sensors 10(12).

Full text available as:
PDF - Requires Adobe Acrobat Reader or other PDF viewer.

Abstract

Achieving situation recognition in ubiquitous sensor networks (USNs) is an important issue that has been poorly addressed by both the research and practitioner communities. This paper describes some steps taken to address this issue by effecting USN middleware intelligence using an emerging situation awareness (ESA) technology. We propose a situation recognition framework where temporal probabilistic reasoning is used to derive and emerge situation awareness in ubiquitous sensor networks. Using data collected from an outdoor environment monitoring in the city of Cape Town, we illustrate the use of the ESA technology in terms of sensor system operating conditions and environmental situation recognition.

EPrint Type:Journal (On-line/Unpaginated)
Keywords:wireless sensor networks; energy efficiency; situation awareness; situation recognition; probabilistic model
Subjects:C Computer Systems Organization: C.2 COMPUTER-COMMUNICATION NETWORKS
ID Code:660
Deposited By:Bagula, Antoine
Deposited On:22 Febuary 2011