Research Article

A probabilistic zonal approach for swarm-inspired wildfire detection using sensor networks

  1. Chandrasekar Ramachandran1,*,
  2. Sudip Misra2 and
  3. Mohammad S. Obaidat3

Article first published online: 9 JUN 2008

DOI: 10.1002/dac.937

Issue

International Journal of Communication Systems

International Journal of Communication Systems

Volume 21, Issue 10, pages 1047–1073, October 2008


Additional Information

How to Cite

Ramachandran, C., Misra, S. and Obaidat, M. S. (2008), A probabilistic zonal approach for swarm-inspired wildfire detection using sensor networks. Int. J. Commun. Syst., 21: 1047–1073. doi: 10.1002/dac.937

Author Information

  1. 1

    Department of Computer Science, University of Illinois at Urbana-Champaign, Champaign, IL, U.S.A.

  2. 2

    School of Information Technology, Indian Institute of Technology, Kharagpur, WB, India

  3. 3

    Department of Computer Science, Monmouth University, West Long Branch, NJ, U.S.A.

*Department of Computer Science, University of Illinois at Urbana-Champaign, Champaign, IL, U.S.A.

Publication History

  1. Issue published online: 5 SEP 2008
  2. Article first published online: 9 JUN 2008
  3. Manuscript Revised: 4 MAR 2008
  4. Manuscript Accepted: 4 MAR 2008
  5. Manuscript Received: 3 FEB 2008

SEARCH

SEARCH BY CITATION

ARTICLE TOOLS

Get PDF (611K)Get PDF (611K)

Keywords:

  • wireless sensor networks;
  • swarm intelligence;
  • ant colony optimization;
  • data aggregation

Abstract

In this paper, we propose a novel swarm-inspired system for detecting wildfires using sensor networks. There are three-fold concerns of this paper. The first is the speed of information propagation, the second is the accuracy of the information being propagated and the third is the reliability of the system over a long period of time. With these in mind, we develop a probabilistic model for focusing on responses for query requests in an accurate manner, similar to the assignment of probabilities of occurrence in a distributed database. We follow a data-centric approach where the system executes a swarm-inspired routing and aggregation algorithm. For effective management of the system, zones of reachability are formed which denote areas, which help the sensor nodes in local maintenance, and through an interaction of these zones, a globally robust system is obtained. The system generates various kinds of reports and is connected to disaster response stations. We simulate our proposed system in NS-2 for certain parameters, and more importantly in the presence of failures, to conclude that the system performs well for different scenarios and very well when an optimal zone radius is chosen. Copyright © 2008 John Wiley & Sons, Ltd.

Get PDF (611K)Get PDF (611K)