A cascaded genetic algorithm for efficient optimization and pattern matching

Abstract

A modified genetic algorithm (GA) based search strategy is presented here that is computationally more efficient than the conventional GA. Here the idea is to start a GA with the chromosomes of small length. Such chromosomes represent possible solutions with coarse resolution. A finite space around the position of solution in the first stage is subject to the GA at the second stage. Since this space is smaller than the original search space, chromosomes of same length now represent finer resolution. In this way, the search progresses from coarse to fine solution in a cascaded manner. Since chromosomes of small length are used at each stage, the overall approach becomes computationally more efficient than a single stage algorithm with the same degree of final resolution. The effectiveness of the proposed GA has been demonstrated for the optimization of some synthetic functions and on pattern recognition problem namely dot pattern matching and object matching with edge map.