基于模糊支持向量机的高校教学质量评价研究  

Research on University Teaching Quality Evaluation Based on Fuzzy Support Vector Machine

作　　者：石磊[1] 苏锡亮[2] 侯丽萍[3] 

机构地区：[1]信阳职业技术学院网络中心,河南信阳464000 [2]信阳职业技术学院经济管理学院,河南信阳464000 [3]信阳农林学院计算机科学系,河南信阳464000

出　　处：《电脑开发与应用》2014年第5期7-10,共4页Computer Development & Applications

摘　　要：高校如何能够客观准确地进行教学质量评价,一直是一个主要的研究课题。由于教学质量评价是一个多指标、多目标的评价系统,传统的计算方法存在繁琐、客观性差的情况,提出一种改进的模糊支持向量机的评价模型对教学质量进行评价。建立的模糊隶属度函数,在减小了训练集中异常样本点对建立分类超平面的干扰同时,并没有减小对训练集中每类样本中边缘样本点对分类超平面的影响。实验表明,改进模糊支持向量机提高了教学质量评价的准确率,同时模糊支持向量机的泛化能力也得到了提高。How to evaluate the quality of teaching in Colleges and universities objectively and accurately,has been a major research topic.Due to the evaluation system of teaching quality evaluati on is a multi index, multi object and the traditional calculation methods are cumbersome,objectivity poor situation,an evaluation of improved fuzzy support vector machine model is presanted in this paper to evaluate the teaching quality.A fuzzy m-embership function,reduction in the small training set of sample points on the establishment of abnormal classification hyper plane interference at the same time,does not reduce the training set of sample each sample impact on the classification hyperplane. Experiments show that this paper improves the accuracy of the evaluation of teaching quality at the same time, fuzzy support vector machine＇s generalization ability has been improved.

关 键 词：高校教学质量评价 模糊支持向量机 隶属度函数 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]