| Web日志挖掘中模糊C均值聚类研究 |
| |
| 引用本文： | 贾丙静,王传安,王亚军,吴长勤.Web日志挖掘中模糊C均值聚类研究[J].丹东纺专学报,2011(1):28-30. |
| |
| 作者姓名： | 贾丙静 王传安 王亚军 吴长勤 |
| |
| 作者单位： | 安徽科技学院理学院,安徽风阳233100 |
| |
| 基金项目： | 安徽省教育厅自然科学基金项目（KJ2009B121Z）; 安徽科技学院引进人才基金项目（ZRC2008176） |
| |
| 摘 要： | Web日志挖掘就是通过一定的方法分析Web日志数据,发现用户的访问习惯,帮助管理人员改进Web站点的性能和结构,提高用户获取知识的质量和速度。笔者首先在Web日志挖掘的背景下分析了模糊C均值聚类算法的缺陷,针对其的不足,在粗糙集理论的支持下,介绍属性信息量的概念,并通过计算待聚类对象的属性权值,区分重要性属性和噪音属性对聚类结果的影响,实验证明该方法提高了模糊C均值聚类算法的准确率。
|
| 关 键 词： | Web日志挖掘 模糊C均值聚类算法 信息量 权值 |
Fussy C-means Clustering in Web Log Mining |
| |
| JIA Bing-jing,WANG Chuan-an,WANG Ya-jun,WU Chang-qin.Fussy C-means Clustering in Web Log Mining[J].Journal of Dandong Textile College,2011(1):28-30. |
| |
| Authors: | JIA Bing-jing WANG Chuan-an WANG Ya-jun WU Chang-qin |
| |
| Affiliation: | (College of Science,Anhui Science and Technology University,Fengyang 233100,China) |
| |
| Abstract: | Defects of fuzzy C-means clustering algorithm were analyzed under the background of web log mining.Accordingly,the concept of property information was introduced.Furthermore,the effects of the important properties and noise properties on clustering results were distinguished by calculating the attribute weights of clustering objects.Experiment results show that the accuracy of the fuzzy C-means clustering algorithm is improved by this method. |
| |
| Keywords: | web log mining fuzzy C-means clustering algorithm information weight |
| 本文献已被 维普 等数据库收录！ |
|
