Big Data Clustering using Ghost Opposition Learning based Crayfish Optimization Algorithm

Traditional clustering methods often struggle with the sheer scale and complexity of big data. Clustering algorithm of big data models by efficiently handling large datasets, making them more scalable and capable of processing diverse data types. In this big data Clustering technique-based Swarm intelligence optimization various of model are created but still the optimization algorithms are trapping in local optima and its takes huge time for finding the global solution. Addressing these issues and overcome in this paper, proposed the Crayfish Optimization Algorithm by using Ghost Opposition-based Learning (GOL-COA) Strategy and environment update technique for enhancing exploitation phase and increasing Exploration convergence speed of optimization, and avoiding local optima problem. The model is evaluated with the accuracy and F1-score metrices and experiment did on various types of datasets. The numerical validation results showing accuracy of 97.56% in LD dataset, and F1 score of 98.10% in LD dataset. This model compares to the other recent year optimization algorithms such as Particle Swarm Optimization (PSO), Whale Optimization (WOA), Ant Colony Optimization (ACO), Sand Cat Swam Optimization (SCSO), and Werewolf Optimization Algorithms (WOA).