计算机与现代化 ›› 2011, Vol. 1 ›› Issue (6): 132-4.doi: 10.3969/j.issn.1006-2475.2011.06.036

• 应用与开发 • 上一篇    下一篇

可视化数据挖掘工具的设计与实现

孟海东1,蔺志举1,徐贯东2   

  1. 1.内蒙古科技大学信息工程学院,内蒙古 包头014010; 2.维多利亚大学工程与科学学院应用信息技术研究所,澳大利亚 墨尔本 3029
  • 收稿日期:2010-12-29 修回日期:1900-01-01 出版日期:2011-06-29 发布日期:2011-06-29

esign and Implementation of Visual Data Mining Tool

MENG Hai-dong1, LIN Zhi-ju1, XU Guan-dong2   

  1. 1.School of Information Engineering, Inner Mongolia University of Science and Technology, Baotou 014010, China;2.School of Engineering and Science, Victoria University, Melbourne 3029, Australia
  • Received:2010-12-29 Revised:1900-01-01 Online:2011-06-29 Published:2011-06-29

摘要: 为了在海量数据中把有用的数据提取给用户进行分析,通过对数据可视化和聚类分析的深入研究,将可视化技术与数据挖掘技术两者结合起来,在Java平台下开发一个可视化的数据挖掘系统,把数据挖掘的结果以3D散点图、平行坐标图的方式显示给用户, 使用户能够直观地看到数据集的全貌及分析各对象同一属性值的分布和各属性之间的关系,有效地表达数据挖掘结果。

关键词: 数据挖掘, 聚类分析, 可视化, 平行坐标技术

Abstract: In order to extract useful data from the mass data for users to analyse, this paper combines visualization technique with data mining technology by the thorough research of data visualization and clustering analyses, develops a visual data mining system in Java platform, and the result of data mining is displayed to users in the way of scatter 3D plot and parallel coordinates figure, so users can see the whole data set, and analyse the distribution of the same attribute value of each object and relationship between each attribute, thus, it can effectively express the results of data mining.

Key words: data mining, clustering analysis, visualization, parallel coordinates