(54.226.58.177) 您好!臺灣時間:2019/01/18 16:20
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
本論文永久網址: 
line
研究生:陳麒麟
研究生(外文):Chi-LinChen
論文名稱:運用類神經網路分析磨課師學習歷程之研究
論文名稱(外文):Research of Analyzing MOOCs’ Learning Records with Neural Network
指導教授:楊竹星楊竹星引用關係
指導教授(外文):Chu-Sing Yang
學位類別:碩士
校院名稱:國立成功大學
系所名稱:電腦與通信工程研究所
學門:工程學門
學類:電資工程學類
論文出版年:2018
畢業學年度:106
語文別:中文
論文頁數:56
中文關鍵詞:學習分析磨課師長短期記憶類神經網絡xAPI
外文關鍵詞:Learning AnalyticsMOOCsLSTMxAPI
相關次數:
  • 被引用被引用:0
  • 點閱點閱:41
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:1
數位學習環境持續改善,磨課師平台也蓬勃發展,平台上產生大量的學習紀錄。為了藉由這些紀錄改善老師的教學品質,讓學生了解自我的學習情況,學習分析這個研究領域因此而生。
學習分析的趨勢包含辨識、診斷、預測、評估、決策等面向,可以使用的方法包含社群網絡分析、機率模型、深度學習等等方式。學習分析的其中一項挑戰就是資料格式不一致,在各個學習平台上,學習歷程的格式不盡相同,因此資料不方便互相轉移,分析的結果也無法適用於其他平台。ADL (Advanced Distributed Learning )因此發展了xAPI(Experience API),這是一種新的學習歷程規範,不僅可以用來記錄學習平台上的學習行為,甚至在行動載具上的學習行為,也可依照這個規範,紀錄於LRS中,學習歷程因此可以跨平台整合。
本研究實作了一個學習分析系統,系統中包含一個長短期記憶類神經網路,簡稱LSTM(Long Short Term Memory Neural Network),用來分析高雄市教育局Dr.Go這個中小學磨課師平台上的學習歷程,預測學生答題狀況與學習成效表現,再藉由預測模型去了解學習資源彼此之間的關係。將預測結果用圖表呈現,顯示各個學習資源節點的關聯,幫助老師做出教學上的決策。
With the development of technology, the learning methods are different from the past. MOOCs(Massive Open Online Courses) platform like Khan Academy, Cousera and edX are more and more popular from 2012. These platforms contain amount of user’s data and researchers want to know what kind of knowledge we could know from these data. However, it is difficult to analyze data from different learning system together. Moreover, current learning analytic service on platform is not smart enough.
Therefore, we develop a system architecture to collect learning records from different systems and implement a LSTM neural network to predict students’ performance. And the accuracy of prediction is higher than 75% normally and the error rate is lower than 10%. Also, the system could transform the relation between learning material to relation graph. It will be helpful for teacher to adjust their teaching strategy.
摘要 I
Abstract II
誌謝 VII
目錄 VIII
表目錄 XI
圖目錄 XII
1. 緒論 1
1.1 研究背景 1
1.2 研究動機 2
1.3 研究目標 3
1.4 名詞釋義 3
1.5 論文架構 4
2. 相關研究 5
2.1 磨課師 5
2.1.1 磨課師平台介紹 6
2.2 學習分析(Learning Analytics) 8
2.2.1 學習分析的益處 9
2.2.2 學習分析的架構 10
2.2.3 發展與應用案例 11
2.2.4 現有問題 12
2.2.5 發展方向 13
2.3 學習管理系統與歷程資料庫 14
2.4 學習歷程規範 - xAPI (Experience API) 16
2.5 知識追蹤Knowledge Tracing 21
2.5.1 貝氏知識追蹤Bayesian Knowledge Tracing 21
2.5.2 深度知識追蹤 Deep Knowledge Tracing 24
2.6 類神經網路 25
2.6.1 類神經網路(Neural Network) 25
2.6.2 遞歸神經網絡(Recurrent Neural Network, RNN) 26
2.6.3 長短期記憶神經網路(Long Short Term Memory Neural Network) 27
3. 系統分析與設計 28
3.1 系統目標 28
3.2 系統架構 29
3.2.1 系統運作流程 29
3.3 模組介紹 30
3.3.1 資料前處理模組 30
3.3.2 學習分析模組 33
3.3.3 結果分析模組 34
3.3.4 Reporting模組 35
3.4 LSTM架構 36
3.5 實作方式 37
3.6 資料來源 37
4. 實作成果 39
4.1 答題狀況之預測結果 39
4.2 學習成效之預測結果 40
4.3 學習資源相關性 45
4.4 結果分析 46
4.5 改進方式 47
4.5.1 過濾學習平台上之學習歷程 47
4.5.2 加入多元種類的學習歷程 48
4.5.3 發展適性化的預測模型 48
5. 結論與未來工作 49
5.1 結論 49
5.2 未來工作 50
6. 參考文獻 51
英文文獻 51
中文文獻 54
附件 56
附件一 LSTM公式 56
[1]David George Glance, Martin Forsey, Myles Riley, The pedagogical foundations of massive open online courses, First Monday, Vol. 18, No. 5, 2013.
[2]Jenny Mackness, Sui Fai John Mak, Roy Williams, The Ideals and Reality of Participating in a MOOC, 2010 Proceedings of the 7th International Conference on Networked Learning, pp. 266-275, 2010.
[3]Maha Bali, MOOC Pedagogy: Gleaning Good Practice from Existing MOOCs, MERLOT Journal of Online Learning and Teaching, Vol. 10, No. 1, pp. 44-56, 2014
[4]Philip J. Guo, Juho Kim, Rob Rubin, How Video Production Affects Student Engagement: An Empirical Study of MOOC Videos, ACM Conference on Learning @ Scale, pp. 41-50, 2014.
[5]U.S. Department of Education Office of Planning, Evaluation, and Policy Development Policy and Program Studies Service, Evaluation of Evidence-Based Practices in Online Learning: A Meta-Analysis and Review of Online Learning Studies, 2010.
[6]“What is Learning Record Store (LRS)? How can I get one?, Reterived July 2, 2017, from https://scorm.com/tincanoverview/what-is-an-lrs-learning-record-store/
[7]Rustici Software LLC., History of Tin Can, Retrieved July 2, 2017, from https://tincanapi.com/history/ Classroom Aid Inc. , EXPERIENCE API (XAPI) 追蹤
[8]Advanced Distributed Learning (ADL) Initiative, U.S. Department of Defense, xAPI-Spec, Retrieved July 2, 2017, from https://github.com/adlnet/xAPI-Spec/blob/1.0.3/xAPI-About.md
[9]Khan Academy, Retrieved July 6, 2017, from https://www.khanacademy.org/
[10]Dr.Go, Retrieved July 6, 2017, from http://drgo.kh.edu.tw/drgo/
[11]Stanford University, “Artificial Intelligence and Life in 2030, p. 52, 2016.
[12]K.Sukhija, M.Jindal, and N.Aggarwal, “The recent state of educational data mining: A survey and future visions, Proc. 2015 IEEE 3rd Int. Conf. MOOCs, Innov. Technol. Educ. MITE 2015, pp. 354–359, 2016.
[13]N.Sclater, A.Peasgood, and J.Mullan, “Learning analytics in higher education : A review of UK and international practice Full report, no. April, p. 40, 2016.
[14]R.Ferguson, “Learning analytics: drivers, developments and challenges, Int. J. Technol. Enhanc. Learn., vol. 4, no. 5–6, pp. 304–317, 2012.
[15]A.Bakharia et al., “A Conceptual Framework linking Learning Design with Learning Analytics, Proc. LAK16 6th Int. Conf. Anal. Knowl. 2016, no. April, pp. 329–338, 2016.
[16]K.Kitto, S.Cross, Z.Waters, andM.Lupton, “Learning Analytics Beyond the LMS: The Connected Learning Analytics Toolkit, Proc. Fifth Int. Conf. Learn. Anal. Knowl. - LAK ’15, pp. 11–15, 2015.
[17]A.Taamallah andM.Khemaja, “Designing and eXperiencing smart objects based learning scenarios, Proc. Second Int. Conf. Technol. Ecosyst. Enhancing Multicult. - TEEM ’14, pp. 373–379, 2014.
[18]A.Bakharia, K.Kitto, A.Pardo, D.Gašević, and S.Dawson, “Recipe for Success - Lessons Learnt from Using xAPI within the Connected Learning Analytics Toolkit, Proc. Sixth Int. Conf. Learn. Anal. Knowl. - LAK ’16, no. October, pp. 378–382, 2016.
[19]Corbett, A. T.; Anderson, J. R. (1995). Knowledge tracing: Modeling the acquisition of procedural knowledge. User Modeling and User-Adapted Interaction. 4 (4): 253–278.
[20]Z. A.Pardos and N. T.Heffernan, “KT-IDEM: Introducing item difficulty to the knowledge tracing model, Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 6787 LNCS, pp. 243–254, 2011.
[21]M.V.Yudelson, K. R.Koedinger, and G. J.Gordon, “Individualized bayesian knowledge tracing models, Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 7926 LNAI, pp. 171–180, 2013.
[22]W. J.Hawkins, N. T.Heffernan, and R. S. J. D.Baker, “Learning bayesian knowledge tracing parameters with a knowledge heuristic and empirical probabilities, Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 8474 LNCS, pp. 150–155, 2014.
[23]Z. A.Pardos, Y.Bergner, D. T.Seaton, and D. E.Pritchard, “Adapting Bayesian Knowledge Tracing to a Massive Open Online Course in edX, Proc. 6th Int. Conf. Educ. Data Min., pp. 137–144, 2013.
[24]Ryan Baker, “Big Data and Education, Retrieved July 3, 2017 from , https://www.edx.org/course/big-data-education-pennx-bde1x
[25]C.Piech et al., “Deep Knowledge Tracing , Proceedings of the 29th Conference on Neural Information Processing Systems, Montreal, Canada, 2015
[26]X.Xiong, S.Zhao, G.Eric, V.Inwegen, and J. E.Beck, “Going Deeper with Deep Knowledge Tracing, Jonathan Rowe Erica Snow Proc. EDM 2016 Work. Tutorials
[27]M.Khajah, R.V.Lindsey, and M. C.Mozer, “How deep is knowledge tracing?, arXiv:1604.02416v2 [cs.AI] 21 Jun, 2016
[28]“Understanding LSTM Networks, Retrieved July 3, 2017, from http://colah.github.io/posts/2015-08-Understanding-LSTMs/
[29]S.Hochreiter, “LONG SHORT-TERM MEMORY, Neural Computation 9(8), 1997
[30]“Neural Networks Part 1: Setting up the Architecture, http://cs231n.github.io/neural-networks-1/
[31]N. T. Heffernan, “ASSISTmentsData, Retrieved July 4, 2017, from https://sites.google.com/site/assistmentsdata/
[32]Highsoft, Highcharts, Retrieved July 5, 2016, from http://www.highcharts.com/
[33]Rustici Software LLC., TinCanPHP, Retrieved July 4, 2017, from http://rusticisoftware.github.io/TinCanPHP/
[34]Vladimir Kostyukov, “Linear Algebra for Java, Retrieved July 4, 2017 from http://la4j.org/
[35]“Confusion matrix , Retrieved July 4, 2017 from https://en.wikipedia.org/wiki/Confusion_matrix
[36]“Fusion Table , Retrieved July 4, 2017 from https://support.google.com/fusiontables/answer/2571232
[37]“什麼是MOOCS?, Retrieved July 02, 2017, from http://ncux.ncu.edu.tw/?page_id=21
[38]“xMOOC的教學設計與理念, Retrieved July 02, 2017, from http://note-on-open-education.blog.ntu.edu.tw/ntumoocs-basics/xmooc/
[39]“cMOOC的教學設計與原理, Retrieved July 02, 2017, from http://note-on-open-education.blog.ntu.edu.tw/ntumoocs-basics/cmooc/
[40]“所有學習經驗, Retrieved July 02, 2017, from http://chinese.classroom-aid.com/2014/05/experience-api-xapi.html/
[41]“SCORM 簡介–Overview, Retrieved July 2, 2017, from http://chinese.classroom-aid.com/2014/01/scorm-overview-i.html/
[42]“高雄市國民教育輔導團 Dr.Go自主學習網, Retrieved July 6, 2017, from https://sites.google.com/site/ceagmath/wang-lu-zi-yuan-wang-zhan/dr-go
[43]臺北酷課雲, Retrieved July 6, 2017, from http://cooc.tp.edu.tw/
[44]均一教育平,台Retrieved July 6, 2017, from https://www.junyiacademy.org/
[45]1Know, Retrieved July 6, 2017, from http://1know.net
[46]“人工神經網路, Retrieved July 4, 2017, from https://zh.wikipedia.org/wiki/人工神经网络
[47]陳鏗任, “大學院校應用學習分析之概況, 教育資料與圖書館學 51, vol. 4, pp. 597–636, 2014.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔