计算机应用研究2018，Vol.35Issue(2)：367-371,5.DOI:10.3969/j.issn.1001-3695.2018.02.011
混合属性对象的类别关系修正的模糊聚类方法
Category relations modification fuzzy clustering of mixed data
摘要
Abstract
In order to solve the weakness of fuzzy clustering analysis for mixed data set,this paper proposed a method of ensemble based on category relation correction.Firstly,the classification attribution of characteristic parameter used entropy to express.The similarity of numerical characteristic parameter used Euclidean distance and entropy to express.Secondly,this paper defined the mixed category fuzzy and the single category fuzzy confidence,and they made the category relations modification for linear,exponential and logarithmic changes.Lastly,this paper used category relations modification to measure the category fuzzy.Experimental results show that the method proposed is better than the current methods for clustering ensemble.关键词
混合条件属性/模糊聚类/类别关系修正/类别模糊度/模糊可信度Key words
mixed condition attributes/fuzzy clustering/category relations modification/category fuzzy/category fuzzy confidence分类
信息技术与安全科学引用本文复制引用
刘晋胜,周靖..混合属性对象的类别关系修正的模糊聚类方法[J].计算机应用研究,2018,35(2):367-371,5.基金项目
国家自然科学基金资助项目(61473094) （61473094）
