Dispersed foraging slime mould algorithm: Continuous and binary variants for global optimization and wrapper-based feature selection

The slime mould algorithm (SMA) is a logical swarm-based stochastic optimizer that is easy to understand and has a strong optimization capability. However, the SMA is not suitable for solving multimodal and hybrid functions. Therefore, in the present study, to enhance the SMA and maintain population diversity, a dispersed foraging SMA (DFSMA) with a dispersed foraging strategy is proposed. We conducted extensive experiments based on several functions in IEEE CEC2017. The DFSMA were compared with 11 other meta-heuristic algorithms (MAs), 10 advanced algorithms, and 3 recently proposed algorithms. Moreover, to conduct more systematic data analyses, the experimental results were further evaluated using the Wilcoxon signed-rank test. The DFSMA was shown to outperform other optimizers in terms of convergence speed and accuracy. In addition, the binary DFSMA (BDFSMA) was obtained using the transform function. The performance of the BDFSMA was evaluated on 12 datasets in the UCI repository. The experimental results reveal that the BDFSMA performs better than the original SMA, and that, compared with other optimization algorithms, it improves classification accuracy and reduces the number of selected features, demonstrating its practical engineering value in spatial search and feature selection. (c) 2021 Published by Elsevier B.V.

Automated summary

The dispersed foraging slime mould algorithm (DFSMA) is proposed as an enhanced version of the slime mould algorithm (SMA) to address the limitations of SMA in solving multimodal and hybrid functions. Experimental results demonstrate that DFSMA outperforms other algorithms in terms of convergence speed and accuracy. Furthermore, the binary DFSMA (BDFSMA) is evaluated and found to have improved performance in classification accuracy and feature selection compared to other optimization algorithms.