A Fitness-Based Adaptive Differential Evolution Approach to Data Clustering

Fuzzy clustering helps to find natural vague boundaries in data. The fuzzy c-means (FCM) is one of the most popular clustering methods based on minimization of a criterion function as it works fast in most scenarios. However, it is sensitive to initialization and is easily trapped in local optima. In this work, a fuzzy clustering (FC) algorithm based on Differential Evolution (DE) is proposed. Here we use a DE with Fitness Based Adaptive Technique (FBADE) for the adaptation of DE parameters. 3 well-known data sets viz. Iris, Wine, Motorcycle and 2 synthetic datasets are used to demonstrate the effectiveness of the algorithm. The resulting algorithm is compared with conventional Fuzzy C-Means (FCM) algorithm, FCM with DE (FCM-DE), FCM with Self Adaptive DE (FCM-SADE).