Solving clustering problems via new swarm intelligent algorithms

In this work, improved swarm intelligent algorithms, namely, Salp Swarm Optimization algorithm, whale optimization, and Grasshopper Optimization Algorithm are proposed for data clustering. Our proposed algorithms utilize the crossover operator to obtain an improvised version of the existing algorithms. The performance of our suggested algorithms is tested by comparing the proposed algorithms with standard swarm intelligent algorithms and other existing algorithms in the literature. Non-parametric statistical test, the Friedman test, is applied to show the superiority of our proposed algorithms over other existing algorithms in the literature. The performance of our algorithms outperforms the performance of other algorithms for the data clustering problem in terms of computational time and accuracy.