Data Clustering using Two-Stage Eagle Strategy Based on Slime Mould Algorithm

Dataclustering is considered an important component of data mining which aims tosplit a given dataset into disjoint groups having the same similarities. Thedeveloped techniques for clustering have some challenges to cluster entities incomplex search space and most them aim maximize sum inter-clusterdistances minimize intra-cluster distances. This objectivefunction nonlinear hard optimize especially complex space.Metaheuristics are becoming trend solving this task thanks theirpromising results. In study, eagle strategy used take advantageof exploration provided by Levy Flight (LF) exploitation strengthof Slime Mould Algorithm (SMA) solve problem. The SMAalgorithm efficient technique optimization problemswhich has high competence. On other hand, LF tends havegood exploratory behavior. Our exploits these advantages in balancedway through well-designed rounds ensure optimality clusteringsolutions. proposed method computationally inexpensive. Italso achieves accuracy terms average, worst, best, ofintra-cluster distance. also evaluated according speed ofconvergence using statistical tests, namely Wilcoxon. obtained resultsare compared with seven benchmarked metaheuristics, Grey Wolf Optimizer(GWO), (SMA), Whale Optimization (WOA), HarrisHawks (HHO), Sine Cosine (SCA), Multi-Verse Optimizer (MVO)and Genetic (GA) eighteen datasets shapes UCIrepositories.