A crossover strategy integrated dung beetle optimization for global optimization problems and feature selection problems

Abstract

Abstract Dung Beetle Optimization (DBO) is a recent swarm intelligence optimizer inspired by the rolling, dancing, foraging, breeding, and stealing behaviors of dung beetles. Although DBO has shown promising search capability, it may suffer from diversity loss, ineffective inferior-solution utilization, and boundary-induced stagnation when solving complex optimization problems. To address these issues, this paper proposes a Crossover Strategy Integrated Dung Beetle Optimization algorithm, named CSIDBO. The proposed method incorporates three mechanisms: a horizontal crossover strategy for dimension-level information exchange, a precise elimination mechanism for replacing low-quality individuals, and a global-best-guided boundary handling strategy for correcting infeasible solutions. Moreover, a transfer-function-based binary version of CSIDBO is developed for wrapper feature selection. The performance of CSIDBO is evaluated on CEC2017, CEC2020, and CEC2022 benchmark functions and sixteen feature selection datasets. Comparative experiments, ablation studies, convergence curves, exploration–exploitation analysis, runtime comparison, and statistical tests are conducted to provide a comprehensive evaluation. Experimental results show that CSIDBO achieves competitive optimization accuracy and feature selection performance compared with classical algorithms and recent DBO variants. Nevertheless, the results also indicate that CSIDBO is not universally optimal on all functions, and its additional operators introduce extra function evaluations and runtime overhead. These limitations are discussed to provide a balanced assessment of the proposed method.