基于特征加权C均值聚类算法的案例索引和检索

CASE INDEXING AND RETRIEVAL BASED ON CLUSTERING ALGORITHM OF WEIGHTED FEATURE C-MEANS

一个成功的案例推理系统高度取决于如何设计出一个精确并且高效的案例检索机制。提出用特征加权C均值聚类算法(WF-C-means)把源案例中的初始案例分成几类。在WF-C-means的分类结果基础上提出了案例索引方案。实验表明,研究的结果对于一个现实的案例推理系统非常有用。

A successful case-based reasoning （CBR） system highly depends on how to design an accurate and efficient case retrieval mechanism. In this article we propose a weighted feature C-means clustering algorithm （WF-C-means） to Classify all primary cases in case base into several clusters. Based on the clustering result of WF-C-means, we present a cluster-based case indexing scheme. Through our experiments, it is shown that the results of this research are very useful for an actual CBR system.