集成神经网络的高校教学质量评估系统研究  

Research on university teaching quality evaluation system based on integrated neural network

作　　者：王磊[1] 张慧娟 WANG Lei;ZHANG Huijuan(College of Mechatronical and Electrical Engineering,Hebei Agricultural University,Baoding 071000,China;School of Mathematics and Systems Science,Shenyang Normal University,Shenyang 110034,China)

机构地区：[1]河北农业大学机电工程学院,河北保定071000 [2]沈阳师范大学数学与系统科学学院,辽宁沈阳110034

出　　处：《现代电子技术》2021年第3期69-73,共5页Modern Electronics Technique

基　　金：教育部产学研合作协同育人项目(201901189009);河北农业大学第十批教学研究项目重点课题(2018ZD06);河北省高等学校科学技术研究青年基金项目(QN2018032)。

摘　　要：为了解决当前高校教学质量评估过程中存在的不足,以提高高校教学质量评估准确性,提出了集成神经网络的高校教学质量评估系统。该系统首先收集大量的高校教学质量历史数据,并对数据进行一些预处理,构建高校教学质量评估学习样本;然后分别采用RBF神经网络、BP神经网络、回声状态网络进行高校教学质量评估,得到高校教学质量评估结果;最后对RBF神经网络、BP神经网络、回声状态网络的评估通过加权得到高校教学质量评估的最后结果。在相同平台上,与其他的高校教学质量评估系统进行对比实验,结果表明,所提系统的高校教学质量评估正确率超过95%,而对比系统的高校教学质量评估正确率均低于95%,说明集成神经网络的高校教学质量评估更加可靠,能够满足高校现代教学管理要求。A teaching quality evaluation system integrating several neural networks is proposed to eliminate the shortcomings existing in the process of teaching quality evaluation and improve the evaluation accuracy.In the system,a large number of historical data of university teaching quality are collected and preprocessed to construct the learning samples of teaching quality evaluation.And then,RBF neural network,BP neural network and echo state network are used to evaluate the teaching quality and obtain the evaluation results.In the end,the evaluations of RBF neural network,BP neural network and echo state network are weighted to get the final results.The final result is compared with that of the other systems.The results show that the evaluation accuracy of the proposed system is above 95%,while that of the contrast systems is below 95%,which show that the university teaching quality evaluation system based on integrated neural network is more reliable and can meet the requirements of modern teaching management.

关 键 词：高校教育 教学质量评估 教学管理 集成神经网络 数据预处理 学习样本构建 

分 类 号：TN99-34[电子电信—信号与信息处理] TP311[电子电信—信息与通信工程]