PDF下载 分享
[1]吴 强,方 睿,韩 斌,等.基于决策树-LMBP神经网络的学生成绩分析及预测模型的研究[J].成都信息工程大学学报,2018,(03):274-280.[doi:10.16836/j.cnki.jcuit.2018.03.009]
　WU Qiang,FANG Rui,HAN Bin,et al.Research and Analysison Students’ Achievement and PredictionModel based on Decision Tree and LMBP Neural Network[J].Journal of Chengdu University of Information Technology,2018,(03):274-280.[doi:10.16836/j.cnki.jcuit.2018.03.009]
点击复制

基于决策树-LMBP神经网络的学生成绩分析及预测模型的研究

成都信息工程大学学报[ISSN:1006-6977/CN:61-1281/TN] 卷: 期数: 2018年03期 页码: 274-280 栏目: 电子信息科学与技术 出版日期: 2018-02-28
Title:
Research and Analysison Students’ Achievement and PredictionModel based on Decision Tree and LMBP Neural Network
文章编号:
2096-1618(2018)03-0274-07
作者:
吴 强;  方 睿;  韩 斌;  贾 川;  浦 东
(成都信息工程大学网络空间安全学院,四川 成都 610225)
Author(s):
WU Qiang;  FANG Rui;  HAN Bin;  JIA Chuan;  PU Dong
(College of Cybersecurity,Chengdu University of Information Technology, Chengdu 610225, China)Abstract:Education data mining has become a new trend in the new stage of large data technology background and the construction of intelligent campus. Based on the advantages of decision tree and LMBP neural network, the analysis and prediction models were constructed and theywere applied in educational data mining for the first time to achieve application innovation. The experiment results show that the main factors which affectstudents’achievement are analyzed through decision tree, and the LMBP neural network model used forclassifying and predicating has smaller mean square error and higher classification accuracy than single model.
关键词:
教育数据挖掘;  LMBP神经网络;  决策树C4.5
Keywords:
decision tree C4.5;  LMBP;  EDM
分类号:
TP301.6
DOI:
10.16836/j.cnki.jcuit.2018.03.009
文献标志码:
A
摘要:
在大数据技术背景和建设智慧校园新阶段下,教育数据挖掘已成为一个新的潮流趋势。结合决策树和LMBP神经网路算法的优点,构建基于这两种算法的分析预测模型,并应用于教育数据挖掘中,实现了应用创新。实验证明通过决策树分析影响学生成绩的主要因子,并在LMBP神经网络模型进行分类预测拥有较单个模型更小的均方误差和更高的分类准确率。
Abstract:
Education data mining has become a new trend in the new stage of large data technology background and the construction of intelligent campus. Based on the advantages of decision tree and LMBP neural network, the analysis and prediction models were constructed and theywere applied in educational data mining for the first time to achieve application innovation. The experiment results show that the main factors which affectstudents’achievement are analyzed through decision tree, and the LMBP neural network model used forclassifying and predicating has smaller mean square error and higher classification accuracy than single model.

参考文献/References:

[1] 连迅.中外教育数据挖掘专家齐汇聚武汉分享研究成果[EB/OL].http://www.hb.xinhuanet.com/2017-06/26/c_1121206912.htm,2017.
[2] 国家基础教育课程改革“促进教师发展与学生成长的评级研究”项目组.教育性评价[M].北京:中国轻工业出版社,2005.
[3] 胡中锋.教育评价学[M].北京:中国人民大学出版社,2009.
[4] 胡帅,顾艳,姜华.基于PCA-RBF网络的学生写作成绩预测模型[J].计算机与现代化,2016(1):69-72.
[5] 王黎黎,刘学军.决策树C4.5算法在成绩分析中的应用[J].河南工程学院学报(自然科学版),2014(4):69-73.
[6] 王华,刘萍.改进的关联算法在学生成绩预警中的应用[J].计算机工程与设计,2015(3):679-682.
[7] 何楚,宋健,卓桐.基于频繁模式谱聚类的课程关联分析模型和学生成绩预测算法研究[J].计算机应用研究,2015(10):2930-2933.
[8] 陈子健,朱晓亮.基于数据挖掘的在线学习者学业成绩预测建模研究[J].中国电化教育,2017(12):75-81.
[9] 陈安,陈宁,周龙骧,等.数据挖掘技术及应用[M].北京:科学出版社,2006.
[10] 史忠值.神经网络[M].北京:高等教育出版社,2009.
[11] MehmedKantardzic.数据挖掘:概念、模型、方法和算法(第二版)[M].王晓海,吴志刚,译.北京:清华大学出版社,2013.
[12] P Cortez,A Silva.Using Data Mining to Predict Secondary School Student Performance[C].In A.Brito and J.Teixeira Eds.,Proceedings of 5th FUture BUsiness TEChnology Conference(FUBUTEC 2008),2008:5-12.
[13] JiaweiHan MicelineKamber.数据挖掘概念与技术(第三版)[M].范明,孟小峰,译.北京:机械工业出版社,2012.
[14] 梁循.数据挖掘算法与应用[M].北京:北京大学出版,2006.
[15] Pang-Ning Tan,MichaelSteinbach,Vipin Kumar.数据挖掘导论[M].北京:人民邮电出版社,2006.

备注/Memo

收稿日期:2017-12-06基金项目:四川省科技计划资助项目(2017GZ0331)

更新日期/Last Update: 2018-02-28