Building a better air defence system using genetic algorithms

  • Authors:
  • Millie Pant;Kusum Deep

  • Affiliations:
  • Lecturer, BITS-Pilani, India;IIT-Roorkee, India

  • Venue:
  • KES'06 Proceedings of the 10th international conference on Knowledge-Based Intelligent Information and Engineering Systems - Volume Part I
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

It is the aim of every country to have a good and strong defence system for the protection of its people and its assets. In this paper we have shown the application of Genetic Algorithms (GA'S) for optimizing the expected survival value of an asset subjected to air attacks. We have developed a mathematical model of the problem subjected to relevant constraints. We have solved this problem with the help of Binary Coded Genetic Algorithm or Simple Genetic Algorithm (SGA) and Real Coded Genetic Algorithm (RCGA). For RCGA we have developed a new crossover operator called the Quadratic Crossover Operator (QCX), which is multi parental in nature. This operator makes use of three parents to produce an offspring, which lies at the point of extrema of the quadratic curve passing through the three selected parents. The working of the operator is shown with help of a simple, steady state Genetic Algorithm having conditional elitism. After testing the validity of this algorithm on several test problems we applied it to the mathematical model of the air defence problem. The comparison of results show that although both the techniques are well suited for solving the above said problem, RCGA with QCX operator gives slightly better results then the SGA.