FCM algorithm and index CS for the signal sorting of radiant points

FCM algorithm is a well-known unsupervised clustering algorithm, which needs to know the number of clusters in advance. This paper proposes a method that uses GA according to the optimal value of an evaluation index CS to determine the best cluster result and its corresponding clustering number of FCM. This method prevents from the subjective and large computation by traditional method. The simulation results show that when the number of clusters is reasonable, FCM gets a better performance in signal sorting of radiant points.