NMIEDA: Estimation of distribution algorithm based on normalized mutual information

Abstract

A new estimation of distribution algorithm based on normalized mutual information (NMIEDA) is proposed for overcoming the premature convergence of bivariate estimation of distribution algorithms. NMIEDA first uses normalized mutual information to measure the interaction between two variables and then generate a dependency forest model. Second, based on the concept of sporadic model building and a reward and punishment scheme in Selfish Gene, NMIEDA provides a new updating mechanism that accelerates the convergence speed. Finally, a new sampling mechanism is adopted in NMIEDA to improve the efficiency of sampling, which combines stochastic sampling, the opposition-based learning scheme and the mutation operator. The simulation results on benchmark problems and real-world problems demonstrate that NMIEDA often outperforms several other bivariate algorithms. K E Y W O R D S estimation of distribution algorithm, new sampling mechanism, new updating mechanism, NMIEDA, normalized mutual information However, there are two major problems in these current bivariate EDAs. First, the size of the population seriously affects the performance of the bivariate EDAs. 24,39 On one hand, bivariate EDA under small population size is unable to represent the general information of the selected individuals