基於互補度與社群網路分析於基因演算法之分組機制

以作者查詢圖書館館藏

、以作者查詢臺灣博碩士

、以作者查詢全國書目

、勘誤回報

、線上人數：37

、訪客IP：18.117.106.206

姓名

蘇皇名(Huang-Ming Su) 查詢紙本館藏

畢業系所

資訊工程學系

論文名稱

基於互補度與社群網路分析於基因演算法之分組機制
(Grouping based on Complementary Degree and Social Network Analysis in Genetic Algorithm)

相關論文

★ 基於edX線上討論板社交關係之分組機制	★ 利用Kinect建置3D視覺化之Facebook互動系統
★ 利用 Kinect建置智慧型教室之評量系統	★ 基於行動裝置應用之智慧型都會區路徑規劃機制
★ 基於分析關鍵動量相關性之動態紋理轉換	★ 基於保護影像中直線結構的細縫裁減系統
★ 建基於開放式網路社群學習環境之社群推薦機制	★ 英語作為外語的互動式情境學習環境之系統設計
★ 基於膚色保存之情感色彩轉換機制	★ 一個用於虛擬鍵盤之手勢識別框架
★ 分數冪次型灰色生成預測模型誤差分析暨電腦工具箱之研發	★ 使用慣性傳感器構建即時人體骨架動作
★ 基於多台攝影機即時三維建模	★ 即時手部追蹤之虛擬樂器演奏系統
★ 基於類神經網路之即時虛擬樂器演奏系統	★ 即時手部追蹤系統以虛擬大提琴為例

檔案

[Endnote RIS 格式]

[Bibtex 格式]

[相關文章]

[文章引用]

[完整記錄]

[館藏目錄]

[檢視]

[下載]

本電子論文使用權限為同意立即開放。
已達開放權限電子全文僅授權使用者為學術研究之目的，進行個人非營利性質之檢索、閱讀、列印。
請遵守中華民國著作權法之相關規定，切勿任意重製、散佈、改作、轉貼、播送，以免觸法。

摘要(中)

在過去幾年中，合作式學習已成為最重要的教學策略之一。在合作學習裡，如何將學習者們適當地分組成為了一個重要的議題。為了解決這個問題，許多學者提出了各式各樣的方法。
在本研究中，我們採用一種不同的方法，利用學習者們的知識結構互補程度以及社群網路結構來提高學習者之間的互動以及團隊合作。另外，本研究利用基因演算法(GA)來演化出更好的分組結果。另一方面，本研究開發出一套系統，學習者以及教師可以利用數位學習系統來快速查詢分組結果以及取得課堂上的訊息。而分組系統可以記錄每一位學習者的學習狀態以及與組員之間的互動程度。分組系統利用這些資訊來動態調整每一次的分組結果。
在研究結果中，我們可以發現本研究的方法確實可以優化分組。本研究可以在維持高異質分組的狀況下，同時兼顧分組結果的接受程度。另外，學生利用系統分組進行合作學習在學習效果上有明顯提升。經過實驗結果分析後，我們發現實驗組的後測平均分數高於對照組，而且實驗組的知識結構比對照組要來的一致。在最後的問卷中，學生說他們喜歡系統上的分組功能以及分組結果。本研究所採用的分組方法確實能夠幫助他們學習。

摘要(英)

In the past years, Cooperative Learning has become one of the most important teaching strategies. Helping learners grouping appropriately is now becoming more and more important. To solve the problem, a lot of methods have been proposed.
In this study, we employ a novel grouping approach that considers the complementary degree of learner’s learning state and social networks to enhance interaction and teamwork between learners. This study also used genetic algorithm (GA) to generate better grouping results. Moreover, a set of systems have been developed. The e-learning system was developed for learners and tutors that they can view the grouping result and academic information conveniently. In grouping system, it will record learners’ learning statuses and interaction between team members to adjust grouping result from each assignment dynamically.
In the end, the results show that the proposed approach can optimize the grouping well. The proposed method of grouping can generate high heterogeneous grouping results and the learners are satisfied with the grouping results at the same time. Meanwhile, the learners’ learning effects are improved by using the proposed method of grouping in cooperative learning. The mean score of post-test in the experimental group was higher than the control group. Moreover, the experimental group learners’ academic level reaching more consistent than the learners of the control groups. Finally, the learners said that they liked the grouping function of the system in their feedback. The grouping method of the system really helped them to learn efficiently.

關鍵字(中)

★ 合作式學習
★ 分組
★ 基因演算法
★ 社群關係

關鍵字(英)

★ Cooperative Learning
★ Grouping
★ Genetic Algorithm
★ Social Network

論文目次

摘要 i
Abstract ii
Acknowledgements iii
Contents iv
List of Figures vii
List of Tables ix
Chapter 1 Introduction 1
1.1 Motivation 1
1.2 Background 2
1.3 Thesis Organization 6
Chapter 2 Related Works 7
2.1 Cooperative Learning 7
2.2 Concept Map and Complementary Degree 10
2.2.1 Concept Map 10
2.2.2 Concept Weight 13
2.2.3 Knowledge Structure Score 17
2.2.4 Complementary Degree 20
2.2.5 Group Complementary Degree Calculation 22
2.3 Genetic Algorithm 23
2.3.1 Genetic Operator of Roulette Wheel Selection 25
2.3.2 Genetic Operator of Mutation 27
2.3.3 Genetic Operator of Reproduction 27
2.3.4 Genetic Operator of Crossover 27
Chapter 3 Proposed Method 29
3.1 Social Network Generation 32
3.2 Grouping Method 33
3.2.1 Genetic Algorithm of Complementary Degree 33
3.2.2 Genetic Algorithm of Social Network 37
Chapter 4 System Architecture 42
4.1 System Implementation Environment 43
4.1.1 E-Learning System Environment 43
4.1.2 Grouping System Environment 45
4.2 System Functionality Demonstration 46
Chapter 5 Results and Analysis 56
5.1 Experimental Subjects 56
5.2 Measuring Tools 59
5.3 Experimental Design 60
5.4 Data Analysis 64
5.4.1 The Changes in Complementary Degree and Friendship Value in Different Generations 64
5.4.2 Post-test Analysis of Experimental Group and Control Group 66
5.4.3 Analysis of Each Assignment 67
5.4.4 The Evaluation of Each Grouping Result 70
5.5 Analysis of Questionnaire 71
Chapter 6 Conclusions and Future Works 74
6.1 Conclusions 74
6.2 Future Works 75
References 76
Appendix I 78
Appendix II 79

參考文獻

[1] Spencer Kagan, “Cooperative learning: Resources for teachers,” 1985.
[2] Robert E. Slavin, “Cooperative learning,” Review of educational research, vol. 50, no. 2, 1980, pp. 315-342.
[3] Chan, Paul Kam Wing, “Enhancing cooperative learning: human factors,” New Horizons in Education, vol. 58, no. 2, 2010.
[4] M.B. Tinzmann, B.F. Jones, T.F. Fennimore, J. Bakker, C. Fine, and J. Pierce NCREL, “What Is the Collaborative Classroom?” North Central Regional Educational Library, Oak Brook, 1990.
[5] Johnson D., Johnson R., and Holubec E., “Cooperative learning in the classroom,” Alexandria. VA: Association for Supervision and Curriculum Development, 1994.
[6] 黃政傑、林佩璇，合作學習，五南圖書出版公司，台北，1996。
[7] Yan-Jou Chen, “A Study on Applying Genetic Algorithm to Dynamic Grouping Strategy Based On a Conceptual Graph,” M.Comp.S. thesis, Chung Yuan Christian University, 2004.
[8] Rong-Chang Chen, Shih-Ying Chen, Jyun-You Fan, and Yen-Ting Chen, “Grouping partners for cooperative learning using genetic algorithm and social network analysis,” Procedia Engineering, vol. 29, 2012, pp. 3888-3893.
[9] Grimmett, Geoffrey R., and Colin JH McDiarmid, “On colouring random graphs. In: Mathematical Proceedings of the Cambridge Philosophical Society,” Cambridge University Press, 1975, pp. 313-324.
[10] Culberson, Joseph C., and Feng Luo, “Exploring the k-colorable landscape with iterated greedy,” Cliques, coloring, and satisfiability: second DIMACS implementation challenge, vol. 26, 1996, pp. 245-284.
[11] Holland, and John H., “Adaptation in natural and artificial systems: An introductory analysis with applications to biology, control, and artificial intelligence.” U Michigan Press, 1975.
[12] D.R. Jones, and M.A. Beltramo, “Solving partitioning problems with genetic algorithms.” Belew, Booker (Eds.), 1991.
[13] E. Falkenauer, “The grouping genetic algorithms-widening the scope of the GAs,” JORBEL-Belgian Journal of Operations Research, Statistics and Computer Science, vol. 33, 1992, pp. 79-102.
[14] David S. Johnson, Cecilia R. Aragon, Lyle A. McGeoch, and Catherine Schevon, “Optimization by simulated annealing: an experimental evaluation; part II, graph coloring and number partitioning,” Operations research, vol. 39, no. 3, 1991, pp. 378-406.
[15] Eiben, Ágoston E., Jan K. Van Der Hauw, and Jano I. van Hemert, “Graph coloring with adaptive evolutionary algorithms,” Journal of Heuristics, vol. 4, no. 1, 1998, pp. 25-46.
[16] Thomas R. Guskey, Implementing Mastery Learning., Wadsworth Pub. Co., 1985.
[17] Mitchell, Melanie, “An introduction to genetic algorithms,” MIT press, 1998.
[18] Likert, Rensis, “A technique for the measurement of attitudes,” Archives of psychology, 1932.
[19] Cronbach, Lee J, “Coefficient alpha and the internal structure of tests,” Psychometrika, vol. 16, no. 3, 1951, pp. 297-334.

指導教授

施國琛(Timothy K. Shih)

審核日期

2014-7-10

推文