基于改进的K-means聚类算法的分类评价方法  

Classification and Evaluation on Reviewers Based on Improved K-means Clustering Algorithm

作　　者：陈德军[1] 罗金成[1] 张兵[1] 

机构地区：[1]武汉理工大学信息工程学院,湖北武汉430070

出　　处：《武汉理工大学学报（信息与管理工程版）》2011年第1期32-35,共4页Journal of Wuhan University of Technology：Information & Management Engineering

基　　金：武汉理工大学2010年研究生自主创新基金资助项目

摘　　要：针对学术期刊运行与管理中对审稿专家缺乏准确评价依据的问题,结合评价分析的需求和K-means聚类算法特点,提出了一种基于改进的K-means聚类算法的审稿专家分类评价方法,该方法通过研究初始聚类中心的选择和评价标准的量化、聚类维度的选择和分类值大小的合理选择等问题,较为准确地解决了审稿专家的分类问题。经实例分析验证,该方法得到的结果是合理的,并具有很强的可操作性,为建立科学的审稿专家库和准确高质量地送审提供了科学的依据。Aiming at the lack of a comprehensive evaluation system for reviewers in the academic journals,combining with evaluation needs and characteristics of K-means clustering algorithm,a method of classifying reviewers was proposed base on an improved K-means clustering algorithm.The method accurately solved the problem of classifying reviewers by selecting initial cluster centers,quantizing evaluation criteria,choosing cluster dimension and reasonably choosing the classification value in K-means clustering algorithm.The case study verified that the results obtained were reasonable,and the method was strongly operable.It provided a scientific basis to establish a scientific high-quality database of reviewers for the editorial board.

关 键 词：改进的K-means算法 聚类分析 审稿专家分类 

分 类 号：TP393.07[自动化与计算机技术—计算机应用技术]