A novel modified differential evolution algorithm for clustering

Zhao Hongwei and Xia Honggang

Abstract

Differential evolution (DE) is easy to trap into local optima. In this paper, a modified differential evolution algorithm (MDE) proposed to speed the convergence rate of DE and enhance the global search of DE. The MDE employed a new mutation operation and modified crossover operation. The former can rapidly enhance the convergence of the MDE, and the latter can prevent the MDE from being trapped into the local optimum effectively. In this work, firstly, we employed a new strategy to dynamic adjust mutation rate (MR) and crossover rate (CR), which is aimed at further improving algorithm performance. Secondly, the MDE algorithms are used for data clustering on several benchmark data sets. The performance of the algorithm based on MDE is compared with DE algorithms on clustering problem. The simulation results show that the proposed MDE outperforms the other two algorithms in terms of accuracy, robustness and convergence speed.