Feature Selection Using Grey Wolf Optimization with Random Differential Grouping

Big data are regarded as a tremendous technology for processing huge variety of in short time and with large storage capacity. The user’s access over the internet creates massive internet. require an intelligent feature selection model by addressing varieties data. Traditional techniques only applicable to simple mining. Intelligent needed big machine learning efficient classification. Major algorithms read input features they are. Then, preprocessed classified. Here, algorithm does not consider relatedness. During selection, all misread outputs. Accordingly, less optimal solution is achieved. In our proposed research, we focus on using supervised called grey wolf optimization (GWO) decomposed random differential grouping (DrnDG-GWO). First, decomposition into subsets based relatedness variables performed. Random performed fitness value two variables. Now, every subset population GWO techniques. combination swarm intelligence produces best results this research. Once optimized, classify advanced kNN process accurate result DrnDG-GWO compared those standard PSO compare efficiency algorithm. accuracy complexity 98% 5 s, which better than existing