基于主元分析的神经网络教学质量评估  

Neural Network for Teaching Quality Evaluation Based on Principal Component Analysis Method

作　　者：吴祎[1] 周强[1] 胡胜[2] 赵进博 WU Yi, ZHOU Qiang, HU Sheng, ZHAO Jin-bo （1. School of Electrical and Information Engineering, Shaanxi University of Science and Technology, Xi＇an Shaanxi 710021, China; 2. School of economics and management, Xi＇ an University of Technology, Xi＇an 710054, china）

机构地区：[1]陕西科技大学电气与信息工程学院,陕西西安710021 [2]西安交通大学机械制造系统国家重点实验室,陕西西安710049 [3]西安理工大学经济与管理学院,陕西西安710054

出　　处：《电脑知识与技术》2015年第12期157-159,共3页Computer Knowledge and Technology

基　　金：陕西省科技统筹创新工程计划项目（2012KTCQ01-19）;陕西省科技攻关项目（2011K06-06）;西安市未央区科技计划项目（201304）

摘　　要：现有的课堂教学评价指标体系间存在高度的非线性，数据冗余等特征。针对此课堂教学评估方法无法消除数据之间的冗余和捕捉非线性规律导致预测精度较低的问题，提出一种基于主元分析的神经网络教学质量评估方法。首先构建影响课堂教学质量评估的因素体系，利用主元分析法消除数据的冗余信息，选择贡献率大的主成分因子作为网络输入，然后构造神经网络模型对教学质量进行评估。通过收集陕西科技大学30名教师的评价数据进行实例验证，结果显示基于主元分析的评估模型在简化BP神经网络结构的同时，也提高了课堂教学质量评估的预测效果。Currently, the classroom teaching evaluation system exist characteristics which integrates highly nonlinear, data redundancy and other features together. Considering the problem that traditional classroom teaching and assessment methods can not eliminate the redundancy between the data and capture nonlinear law, a method of classroom teaching evaluation based on Principal Component Analysis （PCA） and neural network is presented in this paper. Firstly, the principal component analysis （PCA） is used to eliminate redundant information of assessment data, and the principal component factor which contribution rate is large are selected as the input of the network. Secondly, the BP neural network was introduced to evaluate the teaching quality. Finally, thirty teachers＇ evaluation data are collected to verify proposed method. The result demonstrates that the model can simplify BP network model effectively and improve teaching quality assessment prediction accuracy. So this paper proposed a simple and effective approach to evaluate the classroom teaching quality.

关 键 词：教学质量评估 主成分分析BP神经网络 特征提取 

分 类 号：TP18[自动化与计算机技术—控制科学与工程;自动化与计算机技术—控制理论与控制工程]