课堂教学评估的多层次贝叶斯网络分类器方法  

The method of mult-hierarchical Bayesian network classifier for classroom teaching 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）》2012年第1期50-54,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：课堂教学是为实现一定的教学目标而展开的信息传递、过程控制和策略实施过程.依据课堂教学的特点给出了课堂教学评估的指标体系,并在此基础上建立了课堂教学评估的层次贝叶斯网络分类器模型.为提高分类器的分类识别准确率,在连续属性中引入形状参数,实验结果显示,通过形状参数的优化能够显著提高分类器的分类识别可靠性.The classroom teaching is a process of teaching information transfer,classroom control and implementation of teaching strategies for realizing certain educational objectives.A index system of classroom teaching assessment is presented based on the features of classroom teaching.And a model of mult-hierarchical naive Bayesian network classifier is developed for classroom teaching assessment.In order to improve the classification accuracy of classifier,the shape parameter is pulled in continuous attributes.Experimental results show that the reliability of classifier can be significantly improved by shape parameter optimization.

关 键 词：课堂教学 朴素贝叶斯网络 分类器 评估 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]