北京邮电大学学报

  • EI核心期刊

北京邮电大学学报 ›› 2016, Vol. 39 ›› Issue (3): 70-74.doi: 10.13190/j.jbupt.2016.03.012

• 论文 • 上一篇    下一篇

融合信息瓶颈的模糊三维聚类

刘永利, 万兴   

  1. 河南理工大学 计算机科学与技术学院, 河南 焦作 454000
  • 收稿日期:2015-09-21 出版日期:2016-06-28 发布日期:2016-06-27
  • 作者简介:刘永利(1980-),男,副教授,硕士生导师,E-mail:yongli.buaa@gmail.com.
  • 基金资助:

    国家自然科学基金项目(61202286);河南省高等学校青年骨干教师资助项目(2015GGJS-068)

Fuzzy Tri-Clustering Based on Information Bottleneck

LIU Yong-li, WAN Xing   

  1. School of Computer Science and Technology, Henan Polytechnic University, Henan Jiaozuo 454000, China
  • Received:2015-09-21 Online:2016-06-28 Published:2016-06-27

摘要:

为了有效处理三维列联表数据,采用模糊联合聚类算法的思想,提出一种基于信息瓶颈理论的模糊三维聚类算法(IBFTC).IBFTC算法为每个维度指定隶属度函数,可实现3个维度上的同时聚类,且在目标函数中引入信息瓶颈理论计算对象与簇之间的距离.采用MovieLens数据集对IBFTC算法进行多方面分析,结果表明,IBFTC算法可获得比现有模糊联合聚类算法更高的聚类准确率.

关键词: 模糊聚类, 联合聚类, 三维聚类, 信息瓶颈

Abstract:

In order to group three-dimensional data, the thought of fuzzy co-clustering was adopted, and an information bottleneck based fuzzy tri-clustering algorithm, named IBFTC, was presented. The IBFTC specifies membership function for each dimension, simultaneously generates fuzzy clusters on three dimensions and adds information bottleneck theory into objective function for measuring distances between objects and clusters. Experiments on the MovieLens dataset evaluate the performances of IBFTC from several aspects. Experiment shows that IBFTC could achieve higher accuracy than conventional fuzzy co-clustering algorithms.

Key words: fuzzy clustering, co-clustering, tri-clustering, information bottleneck

中图分类号: