By Topic

Optimizing Sensor Placement for Intruder Detection with Genetic Algorithms

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

1 Author(s)
Samuel R. Barrett ; Stevens Institute of Technology, Hoboken, NJ 07030, USA, email:

Sensor networks are effective tools for detecting intruders. However, the standard technique of placing sensors in a perimeter is not optimal. Using optimization techniques to determine sensor placement can improve the effectiveness of the sensor network. The optimization should take into account the environmental conditions and place sensors to take advantage of these conditions. Additionally, there are multiple objectives to consider in sensor placement, specifically the probability of detection and the time to detect. Genetic algorithms are capable of optimizing both objectives simultaneously, achieving the Pareto-optimal curve. This allows the designer of the network to specify a necessary value for one objective and get sensor placements that optimize the other objective. Compared to the standard perimeter configurations, the genetic algorithm networks perform significantly better with respect to both probability of detection and time to detect.

Published in:

Intelligence and Security Informatics, 2007 IEEE

Date of Conference:

23-24 May 2007