Fuzzy Clustering by Differential Evolution
Yu‐Cheng Kao, Jin-Cherng Lin, Shin-Chia Huang · 2008
A fuzzy clustering algorithm based on differential evolution (FCDE) is presented in this paper in order to overcome the disadvantages of traditional fuzzy c-means algorithm (FCM). FCM is sensitive to initialization so that its search is easy to fall into a local optimum. The algorithm we proposed in this paper will avoid this problem and lead to global optimum. The experiments show that FCDE has better performance than FCM and is more efficient particularly when the number of dimension of data becomes large.