学生综合素质评估的层次贝叶斯网络聚类方法  

The clustering method of hierarchical naive Bayesian network for student comprehensive quality assessment

作　　者：李兰春[1] 王双成[2] 王辉[3] 

机构地区：[1]上海立信会计学院外语学院,上海201620 [2]上海立信会计学院数学与信息学院,上海201620 [3]中央民族大学信息工程学院,北京100081

出　　处：《东北师大学报（自然科学版）》2011年第3期49-53,共5页Journal of Northeast Normal University(Natural Science Edition)

基　　金：国家自然科学基金资助项目(60675036);教育部人文社科基金资助项目(10YJA630154);上海市教委重点学科建设项目(J51702);上海市教委科研创新重点项目(09zz202)

摘　　要：针对学生综合素质评估特点和现有评估方法存在的问题,建立了学生综合素质评估的层次朴素贝叶斯网络聚类方法,这种方法不需要许多例子,甚至在没有例子的情况下也能够进行规则提炼和预测.实验结果显示,层次朴素贝叶斯网络聚类方法具有良好的预测准确性,这将使基于层次朴素贝叶斯网络聚类的学生综合素质评估更加可靠.The student comprehensive quality assessment is one effective way for testing student overall level of development.A hierarchical naive Bayesian network clustering method is developed for student comprehensive quality assessment based on the features of student comprehensive quality assessment and the problems in existing assessment methods.This method not need many examples.Even if no example,it can also extracte rules and do prediction.The experimental results show that the method has very good prediction accuracy so that it will be more reliable to assess student comprehensive quality.

关 键 词：学生综合素质评估 指标体系 层次朴素贝叶斯网络 聚类 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]