Research on improved zebra optimization algorithm based on Cat mapping and crossover strategy

Abstract

In order to improve the convergence speed and optimization accuracy of the zebra optimization algorithm (ZOA), this paper proposes an improved zebra optimization algorithm (DCZOA) based on Cat mapping and cross-cutting strategies. Firstly, the Cat mapping method is used to process the initial population to improve the diversity and distribution uniformity of the population; secondly, the cross-cutting strategy is introduced to enhance the global search ability of the algorithm and ensure the optimization update of the zebra position. The simulation experiments on 16 standard test functions show that the improved algorithm has significant improvements in convergence speed and optimization accuracy. The improved algorithm is further applied to the hyperparameter optimization of the random forest regression model, and a combined experiment is carried out using the used car price dataset. The results verify the effectiveness of the algorithm in practical applications. Finally, the advantages of the algorithm are further clarified by combining SHAP analysis.