摘要
对聚类系数无显著性差异的灰色聚类问题进行了研究.运用分类标准矩阵、单指标白化权函数和置信度原则,提出了基于属性识别的灰色聚类方法.该方法充分利用了已有信息和置信度准则,避免了在聚类系数向量中分量取最大时出现聚类系数无显著性差异的问题,使聚类结果更加客观、准确.并经实例验证了该方法的有效性和合理性.
The problem of grey clustering with grey cluster coefficients being not distinguished differences is discussed. Based on classify criterion matrix, single-valued whitenization weight function and reliability code, grey attribute recognition clustering method is put forward. This method can adequately use the known information and reliability code, and avoide the problem of cluster coefficients being not distinguished differences when the maximal heft in the clustering vector is researched, the clustering conclusion is more objective and accurate. The final example is used to demonstrate the rationality and validity of this method.
出处
《华北水利水电学院学报》
2007年第5期90-92,共3页
North China Institute of Water Conservancy and Hydroelectric Power
基金
河南省科技攻关项目(0524490021)
关键词
灰色聚类分析
白化权函数
置信度准则
grey clustering analysis
whitenization weight function
reliability code
