Study On The Fuzzy Cluster Based On Genetic Algorithm And Information Entropy And Application

Clustering is an emerging area which involves various areas. Fuzzy cluster putsfuzzy theory into data clustering and is widely used in various areas. FCM algorithmis one of important methods in fuzzy clustering. It has advantages of simpleness,easy-to-computer implementation, fast convergence, etc. However, FCM is sensitiveto initialization and tends to result in local minimum in iterations.Genetic Algorithm is a random searching global optimization algorithm. Thecombination of FCM algorithm and genetic algorithm benefits global optimizationand makes tremendous improvement in algorithm performance.Firstly, we use transitive closure to cluster carbon dioxide emissions from thirtyprovinces in China.Secondly, we combine transitive closure and FCM algorithm and cluster thecarbon dioxide emissions in China with the improved algorithm.In the end，Contrary to problems that FCM algorithm tends to result in localminimum in iterations and can not determine the optimal number of clustering, weimproves the FCM algorithm with considering the characteristics of genetic algorithmand information entropy. The improved algorithm is applied to carbon dioxideemissions in China.