针对直觉模糊集合数据的聚类有效性问题,提出了一种基于直觉模糊包含度的聚类有效性分析方法。该方法采用直觉模糊包含度和直觉模糊划分熵来评价直觉模糊聚类的有效性。其中,直觉模糊包含度通过增加非隶属度参数对模糊包含度进行直觉化扩展,用于评价类与类间包含的程度;而直觉模糊划分熵用于检验分类结果的可靠性。最后通过典型实例验证了该方法的有效性。
To measure the clustering validity for the data of intuitionistic fuzzy sets,a technique of clustering validity was proposed based on intuitionistic fuzzy inclusion degree.The technique includes two important evaluation factors:intuitionistic fuzzy inclusion degree and intuitionistic fuzzy division entropy.Then by adding the non-membership degree parameter to broaden intuitively fuzzy inclusion degree,the first factor can evaluate inclusion degree values during classes.Moreover,the second factor was used to verify the reliability of the clustering results.At last,the validity of the proposed technique was checked with a classical instance.