Objective reduction in many-objective optimization with social spider algorithm for cloud detection in satellite images

An important difficulty with multi-objective algorithms to analyze many-objective optimization problems (MaOPs) is the visualization of large dimensional Pareto front. This article has alleviated this issue by utilizing objective reduction approach in order remove non-conflicting objectives from original set. The present work proposed formulation technique social spider (MOSSO) algorithm provide decision regarding conflict and generate approximate front non-dominated solutions. A comprehensive analysis carried out existing methods on DTLZ WFG test suite which highlight superiority technique. Further, performance evaluated satellite images detect cloudy region against various types earth’s surfaces. compared benchmark algorithm, NSGA-III evaluate potential method clustering application. It observed that obtained results using reduced set MOSSO provides almost equivalent accuracy