[1]罗 奇,谈宏华.自适应过滤算法在社区Elearning的个性化服务系统中的研究[J].智能系统学报,2008,3(01):91-94.
 LUO Qi,TAN Hong-hua.Research on a personalized knowledge service system for community E-learning using an adaptive filtering algorithm[J].CAAI Transactions on Intelligent Systems,2008,3(01):91-94.
点击复制

自适应过滤算法在社区Elearning的个性化服务系统中的研究(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第3卷
期数:
2008年01期
页码:
91-94
栏目:
出版日期:
2008-02-25

文章信息/Info

Title:
Research on a personalized knowledge service system for community  E-learning using an adaptive filtering algorithm
文章编号:
1673-4785(2007)05-0091-04
作者:
罗  奇12谈宏华1
1.武汉工程大学电气信息学院,湖北武汉430073;
2.武汉科技大学中南分校信息工程学院,湖北武汉430223
Author(s):
LUO Qi12 TAN Hong-hua1
1.School of Electrical Information, Wuhan Institute of Technology, Wuhan 430073 , China;
 2.Department of Information Engineering, Wuhan University of Science an d Technology Zhongnan Branch, Wuhan 430223, China
关键词:
自适应过滤个性化知识服务 相似度终身化学习
Keywords:
adaptive filtering personalized knowledge service similarity lifelong educati on
分类号:
TP302
文献标志码:
A
摘要:
针对学习型社区中的教育需求,在传统算法上加以改进,提出了一种基于向量空间模型的教育资源自适应过滤算法.通过训练算法,提取特征向量和伪反馈建立初始模板,设置初始阈值.然后通过过滤算法根据用户的反馈信息自适应地调整模板和阈值.该算法在执行过程中,不需要大量的初始文本,同时在过滤的过程中可不断地进行自主学习来提高过滤精度.该算法已在个性化知识服务系统中进行验证,结果表明是有效的.
Abstract:
To effectively provide personalized Elearning in a community, an adaptive filt ering algorithm for identifying appropriate teaching resources was developed. It is based on a vector space model, an improvement on traditional algorithms used for this purpose. Firstly, feature selection and pseudo feedback were used to e st ablish the initial templates and thresholds through a training algorithm. Then t he user’s feedback was utilized to modify the templates and thresholds adaptivel y for the filtering algorithm. The algorithm did not need massive quantities of initial texts to begin the process of filtering. Furthermore, filtering precisio n improved during the process through self learning. The algorithm proved effect ive as a personalized knowledge service system for community Elearning.

参考文献/References:

[1] LUO Qi,XUE Qiang. Research on application of association rule mining a l gorithm in learning community [C]// Proceedings of CAAI11 .Wuhan, 200 5.
[2]WU Yanwen,WU Zhonghong. Knowledge adaptive presentation strategy in E lea rning [C]// Proceedings of Second International Conference on Knowledge Econ omy and Development of Science and Technology. Beijing, 2004.
[3]HU Tian, XIA Yingju ,HUANG Xuanjing.A webbased Chinese information fil tering system base on VSM [J]. Computer Engineering, 2003, 29(3):2527.
[4]LI Dun,CAO Yuanda. A new weighted text filtering method [C]// Proce edin gs of International Conference on Natural Language Processing and Knowledge Engi neering.Wuhan, 2005.
[5]ROBERTSON S, HULL D A. The TREC9 filtering track final report[C]// Proc eedings of the 9th Text Retrieval Conference. Gaithersburg, Maryland, USA, 20 01.
[6] HUANG X J, WU L D, ISHIZAKI H,et al. Language independent text categoriza tion [J]. Journal of Chinese Information Processing, 2000,14(2):17.
[7]LAWRENCE R D,ALMASI G S. Personalization of supermarket product recomm en dations [J]. Special Issue of the International Journal of Data Mining and Kno wle dge Discovery, 2001, 15(5):1132.

备注/Memo

备注/Memo:
收稿日期:2007-01-25.
基金项目:
国家自然科学基金资助项目(60533080);
“973”基金资助项目(2002CB312100);
“863”基金资助项目(2006AA01Z3 03).
作者简介:
罗 奇,男,1982生,讲师,主要研究方向为情感计算、智能计算|体育工程等,发表论文多篇.
谈宏华,男,1963生,博士,教授,武汉工程大学电气信息学院院长,主要研究方向为机电一体化、智能控制等,曾主持项目40余项,发表文章30余篇.
通讯作者:罗 奇.E-mail:ccnu_luo2008@yahoo.com.cn.
更新日期/Last Update: 2009-05-10