跳到主要內容

臺灣博碩士論文加值系統

(44.210.149.218) 您好!臺灣時間:2024/11/07 21:23
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:鐘皓廷
研究生(外文):Hao-Ting Chung
論文名稱:基於深度學習建構學生課程成績預測模型
論文名稱(外文):Building Student Course Performance Prediction Model Based on Deep Learning
指導教授:郭忠義郭忠義引用關係
指導教授(外文):Jong-Yih Kuo
口試委員:范姜永益鄭有進李允中郭忠義
口試日期:2018-07-04
學位類別:碩士
校院名稱:國立臺北科技大學
系所名稱:資訊工程系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2018
畢業學年度:106
語文別:中文
論文頁數:51
中文關鍵詞:整體學習降噪自動編碼器K平均演算法類神經網路深度學習
外文關鍵詞:Ensemble LearningDe-noising AutoencoderK-MeansNeural NetworkDeep Learning
相關次數:
  • 被引用被引用:0
  • 點閱點閱:643
  • 評分評分:
  • 下載下載:64
  • 收藏至我的研究室書目清單書目收藏:0
台灣的大學延畢比例約為16%,延畢生增多之後,會影響學校資源的調度,因此若能預期審視學生的課業表現,對無法如預期通過門檻的學生進行輔導,能夠有效的減少學校資源的浪費。本研究使用近幾年的學生資料屬性及課程成績做為訓練資料來建構學生成績預測模型,一開始先使用K-Means演算法將大一到大四所有課程分類,將具有相關性的課程分在同一群集,訓練時模型能較容易找到相似的特徵、提高分析的準確度,接著將所有課程依照不同學年各自建立一個獨立的神經網路模型,每個模型先使用降噪自動編碼器進行預訓練,完成預訓練後,將相應的結構和權重作為神經網路模型的初始值,每個神經網路可以視為一個基本預測器(Base predictor),基本預測器會依照不同年份權重整合成一個整體預測器(Ensemble predictor),來預測目前在學學生的課程分數,隨著學生在每學期結束修完課程後,預測模型會透過在線學習的方式持續追蹤和更新以強化模型精確度。
The deferral of graduation rate in Taiwan’s universities is estimated 16%, which will affect the scheduling of school resources. Therefore, if we can expect to take notice of students’ academic performance and provide guidance to students who cannot pass the threshold as expected, we can effectively reduce the waste of school resources. In this research, we use recent years’ student data attributes and course results as training data to construct student performance prediction model. The K-Means algorithm was used to classify all courses from the freshman to the senior. The related courses will be grouped in the same cluster, which will more likely to find similar features and improve the accuracy of the prediction. Then, this research constructs independent neural networks for each course according to the different academic year. Each model will be pre-trained by using De-noising Autoencoder. After pre-training, the corresponding structure and weights are taken as the initial value of the neural network model. Each neural network is treated as a base predictor. All predictors will be integrated into an Ensemble predictor according to different years’ weights to predict the current student’s course performance. As the students finish the course at the end of each semester, the prediction model will continue track and update to enhance model accuracy through online learning.
摘 要 i
ABSTRACT ii
誌 謝 iv
目 錄 v
表目錄 viii
圖目錄 ix
第一章 緒論 1
1.1 研究動機與目的 1
1.2 研究貢獻 1
1.3 章節編排 2
第二章 文獻探討 3
2.1 深度學習(Deep Learning) 3
2.1.1 深度神經網路 3
2.1.2 降噪自動編碼器(De-noising Autoencoder) 4
2.1.3 激勵函式(Activation Function) 6
2.1.4 最佳化方法(Optimization Method) 7
2.2 整體學習(Ensemble Learning) 8
2.2.1 自適應增強(AdaBoost) 9
2.2.2 Bagging 11
2.3 K-平均演算法(K-Means) 12
2.4 避免過擬合的方法 13
2.4.1 交叉驗證(Cross Validation) 13
2.4.2 丟棄法(Dropout) 14
2.5 相關成績預測案例 15
第三章 成績預測模型設計 17
3.1 資料準備 18
3.1.1 學生課程資料及相關屬性欄位組成 18
3.1.2 資料的前置處理與清理 19
3.1.3 資料切割 20
3.2 課程分群 20
3.3 建構深度神經網路 21
3.3.1 預訓練神經網路 21
3.3.2 基本預測器(Base Predictor) 22
3.3.3 整體預測器(Ensemble Predictor) 23
3.4 預測在學學生成績表現 23
第四章 模型實作 26
4.1 系統資訊 26
4.2 深度神經網路模型 26
4.2.1 損失函數(Loss function) 26
4.2.2 深度神經網路訓練 27
4.2.3 集合多個神經網路 30
第五章 實驗 32
5.1 使用不同參數 32
5.1.1 不同隱藏層層數與神經元個數 32
5.1.2 不同最佳化方法及學習率比較 34
5.2 使用不同演算法架構 35
5.2.1 降噪自動編碼器作為預訓練的效能 35
5.2.2 將課程分群進行訓練的效能 37
5.2.3 使用整體預測器的效能 38
5.3 比較不同機器學習演算法 40
5.3.1 效能比較 41
5.4 其他相關實驗 44
5.4.1 學生相關屬性的影響程度 44
5.4.2 不同時段修課對學生的影響程度 46
第六章 結論與未來研究方向 48
6.1 結論 48
6.2 未來研究方向 48
參考文獻 49
[1] 教育部統計處「高級中等以上學校學生就學貸款統計」, Available: http://stats.moe.gov.tw/files/important/OVERVIEW_F03.pdf
[2] 行政院主計總處「105 學年大專校院延修生人數」, Available: https://www.dgbas.gov.tw/public/Data/7417174752W75YTOV0.pdf
[3] 財團法人國家政策基金會「別讓延畢當了競爭力」, Available: https://www.npf.org.tw/1/15957
[4] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning representations by back-propagating errors,” Nature, vol. 323, no. 6088, pp. 533–536, Oct. 1986.
[5] G. E. Hinton and R. R. Salakhutdinov, “Reducing the dimensionality of data with neural networks.” Science, vol. 313, issue 5786, pp. 504-507, 2006.
[6] P. Vincent, H. Larochelle, Y. Bengio, and P.-A. Manzagol, “Extracting and Composing Robust Features with Denoising Autoencoders,” in Proceedings of the 25th International Conference on Machine Learning, pp. 1096–1103, 2008.
[7] J. Han and C. Moraga, “The influence of the sigmoid function parameters on the speed of backpropagation learning,” in From Natural to Artificial Neural Computation, Springer, Berlin, Heidelberg, pp. 195–201, 1995.
[8] V. Nair and G. E. Hinton, “Rectified linear units improve restricted boltzmann machines.” Proceedings of 27th International Conference on Machine Learning, pp. 807-814, 2010
[9] J. Duchi, E. Hazan, and Y. Singer, “Adaptive Subgradient Methods for Online Learning and Stochastic Optimization,” Journal of Machine Learning Research, vol. 12, no. Jul, pp. 2121–2159, 2011.
[10] D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” arXiv:1412.6980 [cs], Dec. 2014.
[11] T. G. Dietterich, “Ensemble Methods in Machine Learning,” in Multiple Classifier Systems, pp. 1–15, 2000.
[12] Y. Freund and R. E. Schapire, “Experiments with a New Boosting Algorithm,” in Proceedings of the Thirteenth International Conference on International Conference on Machine Learning, pp. 148–1561, 1996.
[13] L. Breiman, “Bagging Predictors,” Machine Learning, vol. 24, no. 2, pp. 123–140, 1996.
[14] J. A. Hartigan and M. A. Wong, “Algorithm AS 136: A K-Means Clustering Algorithm,” J. R. Stat. Soc. Ser. C Appl. Stat., vol. 28, no. 1, pp. 100–108, 1979.
[15] R. Kohavi, “A Study of Cross-validation and Bootstrap for Accuracy Estimation and Model Selection,” in Proceedings of the 14th International Joint Conference on Artificial Intelligence . vol. 2, pp. 1137–1143, 1995.
[16] A. Y. Ng, “Preventing ‘Overfitting’ of Cross-Validation Data,” in Proceedings of the Fourteenth International Conference on Machine Learning, pp. 245–253, 1997.
[17] N. Srivastava, G. E. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: a simple way to prevent neural networks from overfitting.” The Journal of Machine Learning Research, vol. 15, pp. 1929-1958, 2014.
[18] 潘家偉, “Using Stacked Denoising Autoencoder for the Student Dropout Prediction ”, 2017.
[19] J. Xu, K. H. Moon, and M. van der Schaar, “A Machine Learning Approach for Tracking and Predicting Student Performance in Degree Programs,” IEEE J. Sel. Top. Signal Process., vol. 11, no. 5, pp. 742–753, Aug. 2017.
[20] J. Han, M. Kamber, and J. Pei, “Data Mining: Concepts and Techniques.” Morgan Kaufmann, 2000
[21] Encoding skill, Available: http://scikit-learn.org/stable/modules/classes.html#module- sklearn.preprocessing
[22] M. Abadi et al., “TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems,” Mar. 2016.
[23] Giuseppe Bonaccorso, “Machine Learning Algorithms: A reference guide to popular algorithms for data science and machine learning”, 2017.
[24] L. Breiman, “Random Forests,” Mach. Learn., vol. 45, no. 1, pp. 5–32, Oct. 2001.
[25] C. Cortes and V. Vapnik, “Support-vector networks.” Machine Learning, vol. 20, pp. 273-297, 1995.
[26] 蕭文龍, 統計分析入門與應用, 2018
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊