跳到主要內容

臺灣博碩士論文加值系統

(44.192.94.177) 您好!臺灣時間:2024/07/17 00:01
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

: 
twitterline
研究生:朱倩儀
研究生(外文):CHU, CHIEN-YI
論文名稱:應用類神經網路與株落選擇演算法於 IRT 平行組卷問題之研究
論文名稱(外文):The Study of Constructing IRT-based Parallel Tests based on Nerual Network and CLONAL Algorithm
指導教授:張庭毅
指導教授(外文):CHANG, TING-YI
口試委員:張庭毅蔡政容李建緯
口試委員(外文):CHANG, TING-YITSAI, CHENG-JUNGLI, JIAN-WEI
口試日期:2022-07-02
學位類別:碩士
校院名稱:國立彰化師範大學
系所名稱:工業教育與技術學系數位學習碩士班
學門:教育學門
學類:教育科技學類
論文種類:學術論文
論文出版年:2022
畢業學年度:110
語文別:中文
論文頁數:45
中文關鍵詞:平行試卷組裝試題反應理論株落選擇演算法啟發式演算法類神經網路
外文關鍵詞:Parallel tests constructionItem response theoryClonal selection principleHeuristic algorithmneural network
相關次數:
  • 被引用被引用:0
  • 點閱點閱:89
  • 評分評分:
  • 下載下載:7
  • 收藏至我的研究室書目清單書目收藏:0
在大量變數與限制式情況下,組裝多份平行IRT試卷是需要大量運算複雜度。若採用暴力法,則無法在多項式時間內找到最佳解。在試卷試題設定為嚴格的需求下,Hu等人提出改良式株落選擇演算法來同時組裝多份擁有相同試卷訊息量和試卷特性的平行試卷。然而其親和力計算函數之權重採主觀設定,容易造成誤差不穩定的狀況。本研究採用全連接三層前饋類神經網路架構,取代Hu等人所提出的株落選擇演算法組裝試卷測驗中的親和力計算函數,能提供更高品質組裝方式。
In order to simultaneously construct IRT-based parallel tests under large numbers of variables and constraints, which is a very high computational complexities. As we all known, there is no polynomial time algorithm that exists to effectively find the optimal solution. Based on the advantages of CLONALG algorithm, Hu et al. proposed an improved CLONALG algorithm to simultaneously construct IRT-based parallel tests. However, the weights of affinity function in the CLONALG algorithm are set subjectivity. It results in a unstable deviation. In this study, a fully-interconnected 3-layer feed-forward neural network is applied to produce the new affinity function. It has a lower deviation than that in Hu et al.’s scheme and the proposed scheme is also able to construct parallel tests with identical test specifications from the large item bank.
目錄
摘要 Ⅰ
Abstract Ⅱ
目錄 Ⅲ
圖目錄 Ⅳ
表目錄 V
第一章 緒論 1
第二章 文獻探討 5
第三章 Hu等人的平行組卷方式 16
第四章 提出的平行組卷方式 29
第五章 實驗設計與成果 35
第六章 結論 41
參考文獻 42

圖目錄
圖一、兩群受試者的目標測驗訊息量 3
圖二、Hwang等人編碼方式 10
圖三、Chang與Shiu的智慧型電腦輔助測驗管理系統 11
圖四、搜尋方法-單一解 12
圖五、區域最佳解-單一解 12
圖六、搜尋方法-多個解 14
圖七、區域最佳解-多個解 14
圖八、株落選擇演算法 17
圖九、二進制編碼抗體 18
圖十、整數型態編碼抗體 19
圖十一、目標寬鬆範圍設定的試卷規格 20
圖十二、目標嚴格範圍設定的試卷規格 21
圖十三、株落選擇中的單點突變 27
圖十四、本研究應類神經網路於株落演算法 29
圖十五、類神經網路訓練最佳化參數設計親和力計算函數 31
圖十六、單峰型TIF 36
圖十七、雙峰型TIF 36
圖十八、內容標準試題數 37
圖十九、技巧標準試題數 37
圖二十、題型標準試題數 38
圖二十一、一千次隨機測驗規格 38

表目錄
表一、Boekkooi的模型變數 6
表二、Adema的模型變數 8
表三、Hu等人的模型變數 22
表四、類神經網路的模型變數 32
表五、模擬題庫的屬性 35
表六、RGA、CLONAL及N-CLONAL的演算法參數設定 39
表七、GA、CLONAL及N-CLONAL的絕對訊息量均方差 40
參考文獻
[1] T. A. Ackerman, “An alternative methodology for creating parallel test forms using the IRT information function,” in The Annual Meeting of the National Council for Measurement in Education, 1989.
[2] J. J. Adema, “Methods and Models for the Construction of Weakly Parallel Tests,” Applied Psychological Measurement, vol. 16, pp. 53-63, 1992.
[3] R. D. Armstrong and D. H. Jones, “Polynomial Algorithms for Item Matching,” Applied Psychological Measurement, vol. 16, pp. 365-371, 1992.
[4] R. D. Armstrong, D. H. Jones, X. Li, and I. L. Wu, “A Study of a Network-Flow Algorithm and a Noncorrecting Algorithm for Test Assembly,” Applied Psychological Measurement, vol. 20, pp. 89-98, 1996.
[5] D. I. Belov and R. D. Armstrong, “Monte Carlo Test Assembly for Item Pool Analysis and Extension,” Applied Psychological Measurement, vol. 29, pp. 239-261, 2005.
[6] T. Y. Chang and Y. Fu. Shiu, ''Simultaneously Construct IRT-Based Parallel Tests based on an Adapted CLONALG Algorithm,'' Applied Intelligence, vol. 36, no. 4, pp. 979-994, 2012.
[7] A. S. Cohen, P. Montague, L. S. Nathanson, and M. E. Swerdlik, Psychological testing: An introduction to tests and measurement. Mountain View, CA: Mayfield, 1988.
[8] M. Finkelman, W. Kim, and L. A. Roussos, “Automated Test Assembly for Cognitive Diagnosis Models Using a Genetic Algorithm,” Journal of Educational Measurement, vol. 46, pp. 273-292, 2009.
[9] W. J. Hafsa van der Linden, “Optimal Assembly of Psychological and Educational Tests,” Applied Psychological Measurement, vol. 22, pp. 195-211, 1998.
[10] R. K. Hambleton and H. Swaminathan., Item Response Theory: Principles and Applications. Netherlands: Kluwer Academic Publishers Group, 1985.
[11] Y. J. Hu, T. Y. Chang, Y. M. Lu, and P. C. Zheng ''改良式準隨機亂數株落演算法之組裝平行測驗,'' TANET 2013, Taiwan, pp. 219, Oct. 23-25, 2013.
[12] J. Hu, J. Thompson, D. P. Mudaranthakam, L. C. Hinton, D. Streeter, M. Park, B. Terluin, and B. Gajewski, “Estimating power for clinical trials with Patient Reported Outcomes - using Item Response Theory,” Journal of Clinical Epidemiology, vol. 141, pp. 141-148, 2022.
[13] G. J. Hwang, B. M. Lin, H. H. Tseng, and T. L. Lin, “On the development of a computer-assisted testing system with genetic test sheet-generating approach,” IEEE Transactions on Systems, Man, and Cybernetics-Part C: Applications and Reviews, vol. 35, pp. 590-594, 2005.
[14] G. J. Hwang, P. Y. Yin, and S. H. Yeh, “A tabu search approach to generating test sheets for multiple assessment criteria,” IEEE Transactions on Education, vol. 49, pp. 88-97, 2006.
[15] G. J. Hwang, H. C. Chu, P. Y. Yin, and J. Y. Lin, “An innovative parallel test sheet composition approach to meet multiple assessment criteria for national tests,” Computers & Education, vol. 51, pp. 1058-1072, 2008.
[16] S. C. Kong and M. Lai, “Validating a computational thinking concepts test for primary education using item response theory: An analysis of students’responses,” Computers & Education, vol. 187, pp. 104562, 2022.
[17] C. L. Lee, C. H. Huang, and C. J. Lin, “Test-Sheet Composition Using Immune Algorithm for E-Learning Application,” in New Trends in Applied Artificial Intelligence, ed, 2007, pp. 823-833.
[18] van der Linden, W. J. and Adema, J. J., “Simultaneous Assembly of Multiple Test Forms,” Journal of Educational Measurement, vol. 35, pp. 185-198, 1998.
[19] van der Linden, W. J., Linear Models for Optimal Test Design. Berlin: Springer, 2005.
[20] C. S. Oliveira, V. C. Moraes, T. S. Filho, B.C. Prudêncio, “A two-level Item Response Theory model to evaluate speech synthesis and recognition,” Speech Communication, vol. 137, pp. 19-34, 2022.
[21] K. T. Sun and S. F. Chen, “A study of applying the artificial intelligent technique to select test items,” Psychological Testing, vol. 46, pp. 75-88, 1999.
[22] K. T. Sun, Y. J. Chen, S. Y. Tsai, and C. F. Cheng, “Creating IRT-Based Parallel Test Forms Using the Genetic Algorithm Method,” Applied Measurement in Education, vol. 21, pp. 141 - 161, 2008.
[23] P. Y. Yin, K. C. Chang, G. J. Hwang, G. H. Hwang, and Y. Chan, “A Particle Swarm Optimization Method to Composing Serial Test-sheets for Multiple Assessment Criteria,” Educational Technology and Society, vol. 9, pp. 3-15, 2006.
[24] E. Boekkooi-Timminga, “The Construction of Parallel Tests From IRT-Based Item Banks,” Journal of Educational and Behavioral Statistics, vol. 15, pp. 129-145, 1990.
[25] E. Boekkooi-Timminga, “Simultaneous test construction by zero-one programming,” Methodika, vol. 1, pp. 101-112, 1987.
[26] A. J. Verschoor, “Genetic algorithms for automated test assembly,” Enschede, 2007.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top