Multi Objective Optimization used in Genetic Algorithm

Abstract

Genetic algorithms (GA) is an optimization technique for searching very large spaces that newlinemodels the role of the genetic material in living organisms. A small population of individual newlineexemplars can effectively search a large space because they contain schemata, useful newlinesubstructures that can be potentially combined to make fitter individuals. Formal studies of newlinecompeting schemata show that the best policy for replicating them is to increase them newlineexponentially according to their relative fitness. This turns out to be the policy used by genetic newlinealgorithms. Fitness is determined by examining a large number of individual fitness cases. This newlineprocess can be very efficient if the fitness cases also evolve by their own GAs. In First Chapter newlineof Introduction to GA, the different search methods give in details like, Hill Climbing, Simulated newlineannealing, etc. Biological Background of GA s given in broad way, including DNA structure, newlineMethodology, coding, types of parameters with one simple GA s program. newlineChapter 2 deals with Introduction to Optimization techniques. Basically, there are two major newlinetechniques viz. Single objective optimization and Multi objective optimization. There is in detail newlinediscussion for both by using best search techniques for single and multi optimization techniques. newlineIn chapter 3, there is broad view on Binary GA s, like selecting variables and its cost function, newlineVariable incoding and decoding, natural selection from given population, how Binary GA works newlinein Multiobjective Optimization by giving related and suitable examples. newlineBehavior of Hierarchical Genetic Algorithms for Multiobjective optimizations is discuss in newlineChapter 4. With its biological inspiration, Regulatory Sequences and Structural Genes, Active newlineand Inactive Genes, Hierarchical Chromosome Formulation, Genetic Operations for HGA, newlineMultiple Objective Approach contains Iterative Approach, Group Technique, Multiple-Objective newlineRanking. The other search techniques like use of Neural Networks in GA, Simulation Results, newlineapplications of HGA in Neural