A Self-Adaptive Hybrid Genetic Algorithm for Data Mining Applications

Data mining involves nontrivial process of extracting knowledge or patterns from large databases. Many searching and optimization methods are used in data mining. In this paper we propose a self-adaptive hybrid GA (SAHGA), where parameters of population size, crossover rate and mutation rate for each individual in each generation are adaptively fixed. Further, the crossover operator and mutation operator are decided dynamically. Finally, the tabu strategy is involved in the process of evolution. The three measures mentioned above help to maintain the diversity of the population and smooth over premature convergence. The effective performance of the algorithm is then shown using standard testbed functions and a set of classification data mining problems with UCI datasets based on Weka platform.