SELF-CROSSOVER - A NEW GENETIC OPERATOR AND ITS APPLICATION TO FEATURE-SELECTION

Crossover is an important genetic operation that helps in random recom bination of structured information to locate new points in the search space, in order to achieve a good solution to an optimization problem. The conventional crossover operation when applied on a pair of binary strings will usually not retain the total number of Is in the offspri ngs to be the same as that of their parents, but there are many optimi zation problems which require such a constraint. In this article, we p ropose a new crossover technique called 'self-crossover', which satisf ies this constraint as well as retaining the stochastic and evolutiona ry characteristics of genetic algorithms. This new operator serves the combined role of crossover and mutation. We have proved that self-cro ssover can generate any permutation of a given string. As an illustrat ion, the effectiveness of this new technique has been demonstrated for the feature selection problem of pattern recognition. Performance of self-crossover for feature selection is also compared with that of ord inary crossover.