Recent Research Topic Detection and Analysis using IFCM

Abstract

Computational geometry has become one of the most important technologies in computer science domain. To assist decision makers establish action plans based on computational geometry, it is an emergency task to analyze recent topic in computational geometry technology. Moreover, existing methods not concentrate to identify the recent topic in computational geometry topic. Hence, in this paper, improved fuzzy c means clustering is developed to identify the recent topic from the computational geometry. The fuzzy c means clustering is utilized to identify the topics from the collated resources. The fuzzy c means clustering process can be improved with the help of mayfly algorithm to find optimal membership index value. The proposed approach is a combination of word to vector and clustering approach. This proposed approach is to perform an annual trend analysis in computational geometry. The proposed method is implemented in MATLAB and performances are analyzed with statistical measurements such as accuracy, precision, recall, specificity and F_Measure respectively. The proposed method is compared with the existing methods such as K nearest neighbor (KNN), Fuzzy c means clustering with Particle Swarm Optimization (FCM-PSO) and Fuzzy c means clustering with Firefly Algorithm (FA) respectively.