An Efficient Differential Evolution Via Both Top Collective and p-Best Information

Abstract

This study proposes a novel DE variant for global optimizations based on both top collective information and p-best information (called CIpBDE). A combined mutation strategy (CIpBM) takes advantage of the mutation strategies “target-to-ci_pbest/1” and “target-to-pbest/1” is introduced trying to escape from stuck of local optima. A modified crossover operation (CIpBX) is proposed to handle the stagnation of DE. CIpBX adopts a collective vector or top p-best individual based on probability to execute crossover operation when stagnation occurs. An improved parameter adaptation strategy is figured out to adaptability to adjust the parameters crossover probability and scale factor value in each generation. To evaluate the performance of CIpBDE, comprehensive experiments are conducted on the CEC2013 benchmark test suit with 28 functions. Experimental results show that CIpBDE outperforms the seven state-of-the-art DE variants. What’s more, we also apply CIpBDE to the feature selection problem. Compared results on several standard data sets indicate that CIpBDE outperforms the four comparing algorithms in terms of classification accuracy.