运用MAS技术实现的自适应远程教学系统
|
摘要
当前,计算机网络得到前所未有的迅速发展,这为传统的远程教育提供了新的思路和解决方法。出现了大量的基于网络的远程教育系统,这些系统基本上没有自适应性和智能性,给教学效果带来一定的影响。要解决这个问题,需要采用突破传统的新技术。从软件技术和AI领域而言,AGENT具有自适应性、智能性、交互性等一系列的特点,使得它成为较为合适的一种解决问题的技术。
本文分析了基于传统理念构建的远程教学系统的不足,提出了一种新型的远程教育系统模型。该模型将远程教学理念和人工智能技术相结合,综合使用了模糊推理、概念图、及改进的SHERLOCK II方法,设计了包括教师AGENT、学生AGENT、管理AGENT及个性分析AGENT等的MAS系统。该系统能够解决远程教学中的智能化和个性化问题,可以做到因材施教。
本文所做的主要工作有以下几点:(1)分析了现有的基于WEB的远程教学系统的不足和缺点,提出了将人工智能中的AGENT技术和远程教育相结合的理念。(2)提出了一个用MAS技术实现的基于WEB的远程教育系统模型,模型中涉及了多个AGENT(教师AGENT、学生AGENT等),对每个AGENT的功能和作用做详细分析。(3)提出了一种个性化的可见编著方法和相应的知识点表示方法,该方法使得学生学习过程变得更加简单。(4)用考试学理论实现了一个个性化的远程测试系统,通过不同的学生在测试,其试题难度和数目并不相同,从而说明该系统的个性化。从而说明该学生自测模型中所提出的算法是可行的,具有很强的理论研究价值和实践应用价值。
Nowdays,computer networks are developed unprecedently fast,which provides new solutions for traditional remote-education. There have been a large quantity of web-based remote-education systems , which largely do not bear good self-adaption and intelligence and bring some negative impact on education. In order to solve this problem,it is necessary to adopt some new technologies.Regarding software techniques and AI field,Agent is of a variety of advantages, such as good self-adaption, intelligence and interaction,making it be a good techniche for this purpose.
This paper focuses on the disadvantage of the remote-education systems that are based on tradtional concepts and then a new remote-education model is proposed. This model incorporates the ideas of remote-education and AI, involves fuzzy reasoning, concept scheme and improved Sherlock II method, and involves the designing of an MAS system inclucing teacher Agent, student Agent, administration Agent and personality analysis Agent. The system will solve the problems of intelligetizing and individualizing in remote-ducation and help further the relevant research and development.
The contributions of this paper mainly lie in the following aspects:(1)analyzing the limitations of the availabe web-based remote-education systems and proposing a methodology to incorporating the Agent technique in the AI field and concepts used in the remote-education。(2)providing a web-based remote-education model that is established using the MAS technique,which involves multiple Agents(teacher Agent、student Agent and so on). Furthermore, the fuction of each Agent is analyzed in depth.(3)proposing a individualized visually-programming method and the relevant manner of knowledge expression,which will simplify the process of students learning.(4)crystalizing an individualized remote-test system using examination theory, for which when different students are tested the difficulty and number of the questions will vary, which illustrates the individuality of the system。It will further demonstrates that the algorithms proposed in the self-test model is feasible and have significant value of theretical researcdh and practical application。
本文分析了基于传统理念构建的远程教学系统的不足,提出了一种新型的远程教育系统模型。该模型将远程教学理念和人工智能技术相结合,综合使用了模糊推理、概念图、及改进的SHERLOCK II方法,设计了包括教师AGENT、学生AGENT、管理AGENT及个性分析AGENT等的MAS系统。该系统能够解决远程教学中的智能化和个性化问题,可以做到因材施教。
本文所做的主要工作有以下几点:(1)分析了现有的基于WEB的远程教学系统的不足和缺点,提出了将人工智能中的AGENT技术和远程教育相结合的理念。(2)提出了一个用MAS技术实现的基于WEB的远程教育系统模型,模型中涉及了多个AGENT(教师AGENT、学生AGENT等),对每个AGENT的功能和作用做详细分析。(3)提出了一种个性化的可见编著方法和相应的知识点表示方法,该方法使得学生学习过程变得更加简单。(4)用考试学理论实现了一个个性化的远程测试系统,通过不同的学生在测试,其试题难度和数目并不相同,从而说明该系统的个性化。从而说明该学生自测模型中所提出的算法是可行的,具有很强的理论研究价值和实践应用价值。
Nowdays,computer networks are developed unprecedently fast,which provides new solutions for traditional remote-education. There have been a large quantity of web-based remote-education systems , which largely do not bear good self-adaption and intelligence and bring some negative impact on education. In order to solve this problem,it is necessary to adopt some new technologies.Regarding software techniques and AI field,Agent is of a variety of advantages, such as good self-adaption, intelligence and interaction,making it be a good techniche for this purpose.
This paper focuses on the disadvantage of the remote-education systems that are based on tradtional concepts and then a new remote-education model is proposed. This model incorporates the ideas of remote-education and AI, involves fuzzy reasoning, concept scheme and improved Sherlock II method, and involves the designing of an MAS system inclucing teacher Agent, student Agent, administration Agent and personality analysis Agent. The system will solve the problems of intelligetizing and individualizing in remote-ducation and help further the relevant research and development.
The contributions of this paper mainly lie in the following aspects:(1)analyzing the limitations of the availabe web-based remote-education systems and proposing a methodology to incorporating the Agent technique in the AI field and concepts used in the remote-education。(2)providing a web-based remote-education model that is established using the MAS technique,which involves multiple Agents(teacher Agent、student Agent and so on). Furthermore, the fuction of each Agent is analyzed in depth.(3)proposing a individualized visually-programming method and the relevant manner of knowledge expression,which will simplify the process of students learning.(4)crystalizing an individualized remote-test system using examination theory, for which when different students are tested the difficulty and number of the questions will vary, which illustrates the individuality of the system。It will further demonstrates that the algorithms proposed in the self-test model is feasible and have significant value of theretical researcdh and practical application。
引文
[1]刘大有.杨鲲.陈建中.Agent研究现状与发展趋势.软件学报.2000.Vol.11.No.3.p315-321
[2]毛新军.王怀民.Agent技术及其标准化.计算机科学.2001.Vol.28.No.4.p1-4
[3]赵文坛.个性化的远程教学模型[硕士学位论文].太原.太原理工大学.2003
[4]陈玲.基于贝叶斯网络的学生模型的设计与实现[硕士学位论文].太原.太原理工大学.2003
[5]董少春.金莹.徐巧慧.陆现彩.徐士进.E-Learning中的教学设计.全国高等学校教育技术协作委员会第二届年会学术交流会.重庆.2001.12
[6]许彦青.申瑞民.张同珍.申丽萍.加强学习算法的智能多代理在远程教学中的应用.计算机工程.2002.Vol.27,No.8.p125-127
[7]武法提.基于代理的远程教学系统.全国现代远程教育资源建设第一期研讨班讲义.p1-2
[8]符云清.适合远程教育交互协作环境的网络通信协议研究[博士学位论文].重庆.重庆大学.2001.p3-9
[9] M Tokoro. Computational Field Model: Toward a New Computing Model/Methodology for Open Distributed Environment. Proceeding of 2nd IEEE Workshop on Future Trends in Distributed Computing System. Sept 1990
[10] L Gasser anf M Huhns. Distributed Artificial Intelligence. Pittman London,1989 (2)
[11]何炎祥.陈莘萌.Agent和多Agent系统的设计与应用.第一版.武汉大学出版社.2001.6.
[12]Konstantinos Solomos. Nikolaos Avouris. Learning from Collaborating Intelligent Tutors:An Agent-Based Approach. Journal of Interactive Learning Research.1999.Vol.10.No.3.4.p243-262
[13]Ashraf Saad, PhD. A Multi-Agent Spreading Activation Network Model forOnline Learning Objects.
[14]Fuhua Lin. Pete Holt. Larry Korba. Timothy K.Shih. A Framework for Developing Online Learning Systems
[15]申瑞民.汤轶阳.基于概念图的个性化自主学习分析模型及实现.计算机科学.2001.Vol.28.No.10.p39-42
[16]Mark Urban-Lurain. Intelligent Tutoring Systems: An Historic Review in the Context of the Development of Artificial Intelligence and Educational Psychology.
[17]蔡自兴.徐光佑.人工智能及其应用.第二版.清华大学出版社.
[18]Adriana Soares Pereira. Claudio Fernando Resin Geyer. A Pedagogical Agent for Educational Environments in the Internet
[19]Dongming Xu. Huaiqing Wang. Kaile Su. Intelligent Student Profiling with Fuzzy Models. Proceedings of the 35th Hawaii Conference on System Sciences-2002
[20]R.Stathacopoulou.G.D.Magoulas. M.Grigoriadou. Neural Network-based Fuzzy Modeling of the Student in Intelligent Tutoring Systems
[21]Joseph E.Beck. Beverly Park Woolf. Using a Learning Agent with a Student Model
[22]Hugo Gamboa. Ana Fred. Designing Intelligent Tutoring Systems: A Bayesian Approach
[23]Cristina Conati. Kurt VanLehn. POLA: a student modeling framework for Probabilistic On-Line Assessment of problem solving performance
[24]Brent Martin. Constraint-Based Modeling: Representing Student Knowledge
[25]Paul T.Baffes. Raymond J.Mooney. A Novel Application of Theory Refinement to Student Modeling. Proceedings of the Thirteenth National Conference on Artificial Intelligence 1996.p403-408
[26]John Self. Formal Approaches to Student Modeling. AAI/AI-ED Technical Report No.92
[27] Slavomir Stankov . Student Model Developing for Intelligent Tutoring Systems.
[28]周学海.周立.龚育昌.赵振西.自适应超媒体技术及其在智能化CAI中的应用.计算机工程与应用.2001.2.p102-114
[29]Nicola Capuano. Marco Marsella. Saverio Salerno. ABITS: An Agent Based Intelligent Tutoring System for Distance Learning
[30]Barry Kort. External Representation of Learning Process and Domain Knowledge: Affective State as a Determinate of its Structure and Function. AI-ED 2001
[31]Katz. S.,Lesgold.A.. Eggan. Gordin,M.. Modeling the student in Sherlock II. Journal of Artificial Intelligence in Education 3(4).p495-518
[32]Gurer,D.. desJardins,M.. Schlager. M.. Representing a student抯 learning states and transitions. the 1995 American Association of Artificial Intelligence Spring Symposium on Representing Mental States and Mechanisms
[33]Anthony Jameson. Numerical Uncertainty Management in User and Student Modeling: An Overview of Systems and Issues
[2]毛新军.王怀民.Agent技术及其标准化.计算机科学.2001.Vol.28.No.4.p1-4
[3]赵文坛.个性化的远程教学模型[硕士学位论文].太原.太原理工大学.2003
[4]陈玲.基于贝叶斯网络的学生模型的设计与实现[硕士学位论文].太原.太原理工大学.2003
[5]董少春.金莹.徐巧慧.陆现彩.徐士进.E-Learning中的教学设计.全国高等学校教育技术协作委员会第二届年会学术交流会.重庆.2001.12
[6]许彦青.申瑞民.张同珍.申丽萍.加强学习算法的智能多代理在远程教学中的应用.计算机工程.2002.Vol.27,No.8.p125-127
[7]武法提.基于代理的远程教学系统.全国现代远程教育资源建设第一期研讨班讲义.p1-2
[8]符云清.适合远程教育交互协作环境的网络通信协议研究[博士学位论文].重庆.重庆大学.2001.p3-9
[9] M Tokoro. Computational Field Model: Toward a New Computing Model/Methodology for Open Distributed Environment. Proceeding of 2nd IEEE Workshop on Future Trends in Distributed Computing System. Sept 1990
[10] L Gasser anf M Huhns. Distributed Artificial Intelligence. Pittman London,1989 (2)
[11]何炎祥.陈莘萌.Agent和多Agent系统的设计与应用.第一版.武汉大学出版社.2001.6.
[12]Konstantinos Solomos. Nikolaos Avouris. Learning from Collaborating Intelligent Tutors:An Agent-Based Approach. Journal of Interactive Learning Research.1999.Vol.10.No.3.4.p243-262
[13]Ashraf Saad, PhD. A Multi-Agent Spreading Activation Network Model forOnline Learning Objects.
[14]Fuhua Lin. Pete Holt. Larry Korba. Timothy K.Shih. A Framework for Developing Online Learning Systems
[15]申瑞民.汤轶阳.基于概念图的个性化自主学习分析模型及实现.计算机科学.2001.Vol.28.No.10.p39-42
[16]Mark Urban-Lurain. Intelligent Tutoring Systems: An Historic Review in the Context of the Development of Artificial Intelligence and Educational Psychology.
[17]蔡自兴.徐光佑.人工智能及其应用.第二版.清华大学出版社.
[18]Adriana Soares Pereira. Claudio Fernando Resin Geyer. A Pedagogical Agent for Educational Environments in the Internet
[19]Dongming Xu. Huaiqing Wang. Kaile Su. Intelligent Student Profiling with Fuzzy Models. Proceedings of the 35th Hawaii Conference on System Sciences-2002
[20]R.Stathacopoulou.G.D.Magoulas. M.Grigoriadou. Neural Network-based Fuzzy Modeling of the Student in Intelligent Tutoring Systems
[21]Joseph E.Beck. Beverly Park Woolf. Using a Learning Agent with a Student Model
[22]Hugo Gamboa. Ana Fred. Designing Intelligent Tutoring Systems: A Bayesian Approach
[23]Cristina Conati. Kurt VanLehn. POLA: a student modeling framework for Probabilistic On-Line Assessment of problem solving performance
[24]Brent Martin. Constraint-Based Modeling: Representing Student Knowledge
[25]Paul T.Baffes. Raymond J.Mooney. A Novel Application of Theory Refinement to Student Modeling. Proceedings of the Thirteenth National Conference on Artificial Intelligence 1996.p403-408
[26]John Self. Formal Approaches to Student Modeling. AAI/AI-ED Technical Report No.92
[27] Slavomir Stankov . Student Model Developing for Intelligent Tutoring Systems.
[28]周学海.周立.龚育昌.赵振西.自适应超媒体技术及其在智能化CAI中的应用.计算机工程与应用.2001.2.p102-114
[29]Nicola Capuano. Marco Marsella. Saverio Salerno. ABITS: An Agent Based Intelligent Tutoring System for Distance Learning
[30]Barry Kort. External Representation of Learning Process and Domain Knowledge: Affective State as a Determinate of its Structure and Function. AI-ED 2001
[31]Katz. S.,Lesgold.A.. Eggan. Gordin,M.. Modeling the student in Sherlock II. Journal of Artificial Intelligence in Education 3(4).p495-518
[32]Gurer,D.. desJardins,M.. Schlager. M.. Representing a student抯 learning states and transitions. the 1995 American Association of Artificial Intelligence Spring Symposium on Representing Mental States and Mechanisms
[33]Anthony Jameson. Numerical Uncertainty Management in User and Student Modeling: An Overview of Systems and Issues