q-increment direct annealing fuzzy c-means clustering using Tsallis entropy

摘要：

　　Tsallis entropy is a q-parameter extension of Shannon entropy.By extremizing Tsallis entropy within the framework of fuzzy c-means(FCM)clustering,a membership function similar to the statistical mechanical distribution function is obtained.The extent of the membership function is determined by a system temperature and q.In this study,a q-increment annealing method of Tsallis entropy based FCM is proposed and investigated.In this method,in order to determine an appropriate q value automatically,q is increased while lowering the temperature.This method is combined with the deterministic annealing(DA)method,and Tsallis entropy based q-increment DA FCM clustering algorithm is developed.Experiment is performed on the Iris dataset,and it is confirmed that the proposed method determines an appropriate q value in many cases and improves the accuracy of clustering,and is superior to the standard Tsallis entropy based DA FCM.

作者: Makoto Yasuda

作者单位: Dept. of Electrical and Computer Engineering,Gifu National College of Technology Motosu 2236-2,Gifu 501-0495,Japan

会议类型: 国际会议

会议名称: The 2014 10th International Conference on Natural Computation (ICNC 2014) and the 2014 11th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD 2014)(第十届自然计算和第十一届模糊系统与知识发现国际会议)

会议地点: 厦门

会议语种:英文

页码: 31-35

在线出版日期: 2014-08-19（万方平台首次上网日期，不代表论文的发表时间）