系統識別號 U0026-0812200914292881
論文名稱(中文) 基於粒子群優演算法之適性化數位課程組裝流程
論文名稱(英文) Adaptive E-Course Composition Process based on Particle Swarm Optimization
校院名稱 成功大學
系所名稱(中) 資訊工程學系碩博士班
系所名稱(英) Institute of Computer Science and Information Engineering
學年度 96
學期 2
出版年 97
研究生(中文) 蔡承昌
研究生(英文) Cheng-Chang Tsai
電子信箱 p7695128@mail.ncku.edu.tw
學號 p7695128
學位類別 碩士
語文別 中文
論文頁數 69頁
口試委員 口試委員-邱瓊慧
中文關鍵字 粒子群優演算法  數位課程組裝  適性學習 
英文關鍵字 adaptive learning  e-course composition  Particle Swarm Optimization (PSO) 
中文摘要 網際網路(Internet)的發展造就了數位學習(E-learning)的普及化,而數位學習的優勢之一即是適性學習(Adaptive learning)-是為針對學習者之間的個別差異提供每位學習者合適的教材(material)。為強化數位學習中適性學習之優勢,本論文提出了以粒子群優演算法(Particle Swarm Optimization, PSO)為基礎之適性化數位課程組裝流程(Adaptive E-Course Composition Process based on PSO),針對學習者的能力、學習經驗以及學習需求等個別差異,提供適合每位學習者之適性化數位課程;此流程之特點為(1)以學習概念結構為基礎,結合試題反應理論分析出不同學習者的學習目標與能力程度,再依據學習者的個別差異挑選適合學習者的教材,加以組裝成適性化數位課程,以確實達成適性學習之目的。(2)利用粒子群優演算法協助授課者從大量多樣性的教材中,組裝出適合不同學習者能力以及不同學習經驗的適性化數位課程,不但減輕授課者於實行適性教學之負擔,亦可縮短編輯數位課程的時間。(3)適性化數位課程之教學品質不受授課者的教學經驗而影響,具有較穩定的教學品質。實驗顯示,利用本流程所組裝出的數位課程,再經實際學生使用過後調查顯示,約70%反應出數位課程難度適合本身的能力與相關概念切合本身需求的學習目標。
英文摘要 This thesis proposes an Adaptive E-Course Composition Process based on Particle Swarm Optimization (PSO) to compose appropriate e-learning materials into an adaptive e-course for individual learners. The advantages of the proposed process include: 1) the composition process of adaptive e-course combines Learning Concept Structure with Item Response Theory to analyze learners’ learning target and ability level. Hence, the adaptive e-course composed by the proposed process meets the demand of different learners to achieve adaptive learning; 2) the proposed process adopts PSO to facilitate that an instructor selects the appropriate e-learning materials from a mass of candidate materials, and then saves a lot of time and effort for editing an e-course; and 3) since the appropriate e-learning materials are automatically composed according to the demand of individual learners, the teaching quality of e-course composed by the proposed process is independent of an instructor’s teaching experience. That is, the teaching quality of the adaptive e-course is more stable. Experiment results based on proposed process in actual e-learning environments, indicate about 70% of the participants agreed that the adaptive e-course meets their abilities and learning targets.
論文目次 圖目錄 xii
表目錄 xiv
第一章 緒論 1
1.1簡介 1
1.2 研究動機與目的 2
1.3 章節提要 3
第二章 相關研究 4
2.1 學習概念圖與知識結構 4
2.2 試題反應理論(Item Response Theory, IRT) 5
2.3 粒子群優演算法(Particle Swarm Optimization, PSO) 7
2.3.1 連續型粒子群優演算法(CPSO) 8
2.3.2 離散型粒子群優演算法(DPSO) 11
2.3.3 PSO於數位學習之應用 12
第三章 基於粒子群優演算法之適性化數位課程組裝流程(Adaptive E-Course Composition Process Based on PSO) 14
3.1 學習概念結構建構 17
3.2 學習目標分析及能力估測 22
3.2.1 學習目標分析 23
3.2.2 能力階段估測 24
3.3 基於PSO之多目標數位課程組裝(Multi-objective E-Course Composition based on PSO, MECPSO) 26
3.3.1 數位課程組裝模型 26
3.3.2 課程組裝步驟 29
3.3.3範例說明 34
第四章 適性化數位課程組裝工具設計 38
第五章 工具實作與驗證 41
5.1 實作 41
5.2 驗證 48
5.2.1 數據分析 49
5.2.2 與基因演算法之比較 54
5.2.3 使用調查 56
第六章 結論與未來工作 60
6.1 結論 60
6.2 未來工作 62
參考文獻 63
附錄A 66
參考文獻 [1] 余民寧。IRT導論與應用。台北市:心理出版社。2007。
[2] 林進材。教學理論與方法。五南圖書出版。民88。
[3] 林寶山。實用教學原理。台北市:心理出版社。民92。
[4] 林瓊甄。適性化e-Learning教材發展之研究。國立高雄師範大學資訊教育研究所碩士論文。2005。
[5] 張怡君,陳奕錡,朱治平。 Design of a Learning Strategy Authoring Tool. 台灣數位學習發展研討會(TWELF 2005), 台北市,國立台灣師範大學,2005年5月。
[6] 許峰銜。網路學習之適性化教學設計與學習成效評估。國立中山大學資訊管理研究所碩士論文。2005。
[7] 郭伯臣、謝友振、張峻豪、蔡坤穎。以結構理論為基礎之適性測驗與適性補救教學線上系統。台灣數位學習發展研討會(TWELF 2005), 台北市,國立台灣師範大學,2005年5月。
[8] 楊岱霖。動態適性化學習系統之研究。國立高雄師範大學資訊教育研究所碩士論文。2005。
[9] Advanced distributed learning, 2004,Sharable Content Object Reference Model (SCORM), http://www.adlnet.gov/scorm/index.aspx
[10] Baker, F. B. Item response theory: Parameter estimation techniques”. New York: Marcel Dekker. 1992.
[11] Brusilovsky, P. and Pesin, L. Visual annotation of links in adaptive hypermedia. Conference companion on Human factors in computing systems, 222-223, 1996.
[12] Brusilovsky, P., Bra, P. D., Eklund, J., Hall, W. and Kobsa, A. Adaptive hypermedia (panel): purpose, methods, and techniques. Proceedings of the tenth ACM Conference on Hypertext and hypermedia: returning to our diverse roots, 199-200, 1999.
[13] Chang, K. E., Sung, Y. T. and Chen, S. F. Learning through computer-based concept mapping with scaffolding aid. Journal of Computer Assisted Learning, 17, 13-20, 2001.
[14] Cheng, S. C., Lin, Y. T. and Huang, Y. M. Dynamic Question Generation System for Web-Based Testing Using Particle Swarm Optimization. Expert Systems with Applications. 2007.
[15] Davis, L. Handbook of genetic algorithms. Amsterdam: Van Nostrand Reinhold. 1991.
[16] Deb, K. Multi-objective Genetic Algorithms: Problem Difficulties and Construction of Test Problems, in MIT Evolutionary Computation, 7(3), 205-230, 1999.
[17] Hu, X. and Eberhart, R. Multiobjective optimization using dynamic neighborhood particle swarm optimization. Proceedings of congress on Evolutionary Computation, 1677-1681, 2002.
[18] Hu, X., Shi, Y., Eberhart, R. Recent Advances in Particle Swarm. Proceedings of congress on Evolutionary Computation, 90-97, 2004.
[19] Huang, T. C., Huang, Y. M. and Cheng, S. C. Automatic and Interactive e-Learning Auxiliary Material Generation utilizing Particle Swarm Optimization. Expert Systems with Applications. 2007.
[20] Kennedy, J. and Eberhart, R. C. Particle swarm optimization. In Proceedings of the IEEE International Conference on Neural Networks 4, 1942-1948, 1995.
[21] Kennedy, J. and Eberhart, R.C. A discrete binary version of the particle swarm algorithm. Proceedings of IEEE International Conference on Systems, Man, and Cybernetics, Piscataway, NJ. 4104-4108, 1997.
[22] Modular Object-Oriented Dynamic Learning Environment (Moodle), http://moodle.org/
[23] Novak, J. D. and Gowin, D. B. Concept mapping for meaningful learning. In Learning how to learn, 15-54, 1984.
[24] Parsopoulos, K. E. and Vrahatis, M. N. Particle Swarm Optimization Method in Multi-objective Problems, in Proc. 2002 ACM Symp. Applied Computing (SAS’2002), 603-607, 2002.
[25] Salerno, J. Using the particle swarm optimization technique to train a recurrent neural model. In Proceedings of the Ninth IEEE International Conference on Tools with Artificial Intelligence, 45-49, 1997.
[26] Secrest, B. R. Travelling Salesman Problem for Surveillance Mission Planning using Particle Swarm Optimization. Master's thesis, School of Engineering and Management of the Air Force Institute of Technology, Air University, 2001.
[27] Salman, A. I. and Al-Madani, S. Particle Swarm Optimization for Task Assignment Problem. Microprocessors and Microsystems, 26(8), 363-371, 2002.
[28] Tan, S. C. The effects of incorporating concept mapping into computer assisted instruction. Journal of Educational Computing Research, 23, 113-131, 2000.
[29] Tsai, C. C., Lin, S. S. J. and Yuan, S. M. Students' use of web-based concept map testing and strategies for learning. Journal of computer Assisted Learning, 17, 72-84, 2001.
[30] Van der Merwe, D. W. and Engelbrecht, A. P. Data clustering using particle swarm optimization. Proceedings of IEEE Congress on Evolutionary Computation 2003 (CEC 2003), Canbella, Australia. 215-220, 2003.
[31] Yin P. Y., Hwang, G. J., Chang, K. C., Hwang, G.H. and Chan Y. A particle swarm optimization approach to composing serial test sheets for multiple assessment criteria. Educational Technology and Society, 9(3), 3-15, 2006.
  • 同意授權校內瀏覽/列印電子全文服務,於2010-08-19起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2010-08-19起公開。

  • 如您有疑問,請聯絡圖書館