English  |  正體中文  |  简体中文  |  Post-Print筆數 : 27 |  全文筆數/總筆數 : 118209/149242 (79%)
造訪人次 : 74463349      線上人數 : 122
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜尋範圍 查詢小技巧：
  • 您可在西文檢索詞彙前後加上"雙引號"，以獲取較精準的檢索結果
  • 若欲以作者姓名搜尋，建議至進階搜尋限定作者欄位，可獲得較完整資料
    •  進階搜尋
    政大機構典藏 > 商學院 > 統計學系 > 學位論文 >  Item 140.119/159039


    請使用永久網址來引用或連結此文件: https://nccur.lib.nccu.edu.tw/handle/140.119/159039


    題名: 穩健自適應加權二元分類
    Robust Adaptive Weights for Binary Classification
    作者: 葉佐晨
    Ye, Zuo-Chen
    貢獻者: 張志浩
    Cheng, Chih-Hao
    葉佐晨
    Ye, Zuo-Chen
    關鍵詞: 邏輯斯迴歸
    支持向量機
    混合整數規劃
    二元分類
    加權方法
    Logistic regression
    SVM
    MIP
    Classification
    Weighting
    日期: 2025
    上傳時間: 2025-09-01 14:49:33 (UTC+8)
    摘要: 在常見的分類問題中，分類模型的穩健度與預測正確率經常受到數據集中的不尋常觀測值 (如離群值或槓桿點) 而產生分析上的偏誤。文獻常見的方法是使用最小共變異行列式 (Minimum Covariance Determinant，MCD) 計算樣本點在建模時的距離權重，用以減輕不尋常觀測值對建模的影響。本研究結合 MCD 方法提出一個穩健自適應加權方法 (Robust Adaptive Weight，RAW) 調整距離權重。我們建構一些模擬研究呈現 RAW 在持續迭代更新自適應分類權重後，可以有效降低不尋常觀測值與盲信錯誤分類點 (blindly-confident misclassification) 對分類模型的影響。在這些模擬研究中，我們將 RAW 方法應用至常見二元分類方法如邏輯斯迴歸 (logistic regression，LR)、支持向量機 (Support Vector Machine，SVM) 以及混合整數規劃 (Mixed-Integer Programming，MIP)，並藉以得到相應的穩健自適應加權分類模型，包括穩健自適應加權邏輯斯迴歸(RAWLR)、穩健自適應加權支持向量機 (RAWSVM) 與穩健自適應加權混合整數規劃 (RAWMIP)。大量的實證分析結果顯示，本文所提出的 RAW 方法在處理不同程度的不尋常點和標註誤差時均能保持良好的預測表現與模型穩健性，優於傳統分類模型與其他穩健分類方法。
    Modern classification tasks often include anomalous observations such as data noises and high-leverage points. These irregularities bias conventional classifiers and weaken both robustness and predictive accuracy. This study proposes a Robust Adaptive Weighting (RAW) strategy that fuses two components: a Distributional Weight derived from Minimum Covariance Determinant (MCD) distances, which attenuates the influence of leverage outliers, and an iteratively updated Adaptive Classification Weight, which suppresses the effect of samples that are confidently misclassified. RAW is embedded in three binary classification frameworks, like logistic regression (LR), Support Vector Machines (SVM), and Mixed-Integer Programming (MIP), to create Robust Adaptively Weighted Logistic Regression (RAWLR), Robust Adaptively Weighted SVM (RAWSVM), and Robust Adaptively Weighted MIP (RAWMIP). Comprehensive simulation studies and evaluations on real datasets show that these models maintain strong predictive performance and stability across varying levels of data contamination, consistently surpassing traditional classifiers and other robust methods.
    參考文獻: Afonso, A. M., Ebell, M. H., Gonzales, R., Stein, J., Genton, B., & Senn, N. (2012, 12). The use of classification and regression trees to predict the likelihood of seasonal influenza. Family Practice, 29, 671-677. doi:10.1093/fampra/cms020
    Agresti, A. (2015). Foundations of linear and generalized linear models (1st ed.). Wiley.
    Ahmed, I. A. I., & Cheng, W. (2020). The performance of robust methods in logistic regression model. Open Journal of Statistics. Retrieved from https://api.semanticscholar.org/CorpusID:213840976
    Anand, A., Pugalenthi, G., Fogel, G. B., & Suganthan, P. N. (2010). An approach for classification of highly imbalanced data using weighting and undersampling. Amino
    Acids, 39, 1385-1391. Retrieved from https://doi.org/10.1007/s00726-010-0595-2 doi: 10.1007/s00726-010-0595-2
    Ben-David, S., Loker, D., Srebro, N., & Sridharan, K. (2012, 6). Minimizing the misclassification error rate using a surrogate convex loss.
    Bertsimas, D., & Dunn, J. (2017, 7). Optimal classification trees. Machine Learning, 106. doi:10.1007/s10994-017-5633-9
    Bertsimas, D., & Gurnee, W. (2022, 5). Learning sparse nonlinear dynamics via mixed-integer optimization.
    Bertsimas, D., & Stellato, B. (2019, 7). Online mixed-integer optimization in milliseconds.
    Bifarin, O. O. (2023, 5). Interpretable machine learning with tree-based shapley additive explanations: Application to metabolomics datasets for binary classification. PLOS ONE, 18, e0284315. Retrieved from https://dx.plos.org/10.1371/journal.pone.0284315 doi: 10.1371/journal.pone.0284315
    Bishop, C. (2006, 1). Pattern recognition and machine learning. In Journal of electronic imaging (Vol. 16, p. 140-155). doi: 10.1117/1.281911948
    Bishop, C. (2007). Pattern recognition and machine learning (information science and statistics).
    Boser, B. E., Guyon, I. M., & Vapnik, V. N. (1992, 7). A training algorithm for optimal margin classifiers. In Proceedings of the fifth annual workshop on computational learning theory (p. 144-152). ACM. doi:10.1145/130385.130401
    Burges, C. J. (1998). A tutorial on support vector machine for pattern recognition. Data Mining and Knowledge Discovery, 2, 121-167. doi: 10.1023/A:1009715923555
    Carrizosa, E., & Morales, D. R. (2013). Supervised classification and mathematical optimization. Computers & Operations Research, 40, 150-165. Retrieved from https://www.sciencedirect.com/science/article/pii/S0305054812001190 doi: https://doi.org/10.1016/j.cor.2012.05.015
    Carroll, R. J., & Pederson, S. (1993). On robustness in the logistic regression model. Journal of the Royal Statistical Society. Series B (Methodological), 55, 693-706. Retrieved from http://www.jstor.org/stable/2345881 doi: https://doi.org/10.1111/j.2517-6161.1993.tb01934.x
    Chang, C.-C., & Lin, C.-J. (2011, 5). Libsvm: A library for support vector machines. ACM Trans. Intell. Syst. Technol., 2. Retrieved from https://doi.org/10.1145/1961189.1961199 doi: 10.1145/1961189.1961199
    Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20, 273-297. Retrieved from https://doi.org/10.1007/BF00994018 doi: 10.1007/BF00994018
    Cox, D. R. (1958, 7). The regression analysis of binary sequences. Journal of the Royal Statistical Society: Series B (Methodological), 20, 215-232. Retrieved from https://doi.org/10.1111/j.2517-6161.1958.tb00292.x doi:https://doi.org/10.1111/j.2517-6161.1958.tb00292.x
    Cristianini, N., & Shawe-Taylor, J. (2000). An introduction to support vector machines and other kernel-based learning methods. Cambridge University Press. doi: 10.1017/CBO9780511801389
    FINNEY, D. J. (1947, 12). The estimation from individual records of the relationship between dose and quantal response. Biometrika, 34, 320-334. Retrieved from https://doi.org/10.1093/biomet/34.3-4.320 doi:10.1093/biomet/34.3-4.32049
    Flury, B., & Riedwyl, H. (1988). Multivariate statistics: A practical approach. Chapman & Hall.
    Friedman, J. (2000, 11). Greedy function approximation: A gradient boosting machine. The Annals of Statistics, 29. doi: 10.1214/aos/1013203451
    Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press. Retrieved from https://books.google.com.tw/books?id=Np9SDQAAQBAJ
    Green, P. J. (1984, 1). Iteratively reweighted least squares for maximum likelihood estimation, and some robust and resistant alternatives. Journal of the Royal Statistical Society Series B: Statistical Methodology, 46, 149-170. doi: 10.1111/j.2517-6161.1984.tb01288.x
    Gurobi. (2025). Gurobi optimizer reference manual. Retrieved from https://www.gurobi.com
    Guzelsoy, M., & Ralphs, T. (2007, 5). Duality for mixed-integer linear programs. Internat. J. Oper. Res., 4.
    Hastie, T., Tibshirani, R., & Friedman, J. (2009a). The elements of statistical learning: Data mining, inference, and prediction, second edition (springer series in statistics).
    Hastie, T., Tibshirani, R., & Friedman, J. (2009b). Linear methods for classification. In T. Hastie, R. Tibshirani, & J. Friedman (Eds.), The elements of statistical learning: Data mining, inference, and prediction (p.101-137). Springer New York. Retrieved from https://doi.org/10.1007/978-0-387-84858-7_4 doi:10.1007/978-0-387-84858-74
    Hubert, M., & Debruyne, M. (2010, 1). Minimum covariance determinant. WIREs Computational Statistics, 2, 36-43. Retrieved from https://doi.org/10.1002/wics.61 doi: https://doi.org/10.1002/wics.61
    Jr, D. W. H., Lemeshow, S., & Sturdivant, R. X. (2013). Applied logistic regression. John Wiley
    & Sons.
    Ketha, A., & Goldsztein, G. (2021, 11). Applications of feature engineering and logistic regression to analyze microchip performance: Using key features of machine learning to calculate, generate, and enhance a nonlinear decision boundary. Journal of Student Research, 10. Retrieved from https://www.jsr.org/hs/index.php/path/article/view/2331 doi: 10.47611/jsrhs.v10i4.2331
    Koch, T., Berthold, T., Pedersen, J., & Vanaret, C. (2022). Progress in mathematical 50 programming solvers from 2001 to 2020. EURO Journal on Computational Optimization, 10, 100031. Retrieved from https://www.sciencedirect.com/science/article/pii/S2192440622000077 doi: https://doi.org/10.1016/j.ejco.2022.100031
    Krawczyk, B., Woźniak, M., & Herrera, F. (2014). Weighted one-class classification for different types of minority class examples in imbalanced data. In 2014 ieee symposium on computational intelligence and data mining (cidm) (p. 337-344). doi: 10.1109/CIDM.2014.7008687
    Künsch, H. R., Stefanski, L. A., & Carroll, R. J. (1989). Conditionally unbiased bounded-influence estimation in general regression models, with applications to generalized linear models. Journal of the American Statistical Association, 84, 460-466. Retrieved from http://www.jstor.org/stable/2289930 doi: 10.2307/2289930
    Manikandaprabhu, P., Prasanna, S., Sivaranjan, K., & Senthilkumar, R. (2023, 5). Fraudulent banking transaction classification using deep learning algorithm. International Journal of Advanced Research in Science, Communication and Technology, 3, 68-74. Retrieved from http://dx.doi.org/10.48175/ijarsct-9660 doi: 10.48175/ijarsct-9660
    Maroco, J., Silva, D., Rodrigues, A., Guerreiro, M., Santana, I., & de Mendonça, A. (2011,8). Data mining methods in the prediction of dementia: A real-data comparison of the accuracy, sensitivity and specificity of linear discriminant analysis, logistic regression, neural networks, support vector machines, classification trees and random forests. BMC research notes, 4, 299. doi: 10.1186/1756-0500-4-299
    McCullagh, P., & Nelder, J. (2019). Generalized linear models. Routledge. doi: 10.1201/9780203753736
    Meyer, D. (2024, 10). Weightsvm: Subject weighted support vector machines. Retrieved from https://www.csie.ntu.edu.tw/~cjlin/libsvmtools/#weights_for_data_instances
    Murphy, K. P. (2012). Machine learning: a probabilistic perspective. MIT press.
    Nemhauser, G., & Wolsey, L. (1988). Integer and combinatorial optimization. Wiley. doi: 10.1002/9781118627372
    Nguyen, T., & Sanner, S. (2013, 5). Algorithms for direct 0–1 loss optimization in binary classification. In S. Dasgupta & D. McAllester (Eds.), Proceedings of the 30th 51 international conference on machine learning (Vol. 28, p. 1085-1093). PMLR. Retrieved from https://proceedings.mlr.press/v28/nguyen13a.html
    Nocedal, J., & Wright, S. J. (2006). Quasi-newton methods. Numerical optimization, 135-163.
    Olive, D. J., & Hawkins, D. M. (2010). Robust multivariate location and dispersion. Preprint.
    Pearson, R. (2002). Outliers in process modeling and identification. IEEE Transactions on Control Systems Technology, 10, 55-63. doi: 10.1109/87.974338
    Phogat, M., & Kumar, D. (2020, 9). Classification of complex diseases using an improved binary cuckoo search and conditional mutual information maximization. Computación y Sistemas, 24. Retrieved from https://doi.org/10.13053/cys-24-3-3354 doi: 10.13053/cys-24-3-3354
    Rousseeuw, P. J. (1984). Least median of squares regression. Journal of the American Statistical Association, 79, 871-880. Retrieved from http://www.jstor.org/stable/2288718 doi: 10.2307/2288718
    Rousseeuw, P. J., & Christmann, A. (2003, 7). Robustness against separation and outliers in logistic regression. Computational Statistics and Data Analysis, 43, 315-332. doi: 10.1016/S0167-9473(02)00304-3
    Rousseeuw, P. J., & Driessen, K. V. (1999, 8). A fast algorithm for the minimum covariance determinant estimator. Technometrics, 41, 212-223. Retrieved from https://www.tandfonline.com/doi/abs/10.1080/00401706.1999.10485670 (doi: 10.1080/00401706.1999.10485670) doi: 10.1080/00401706.1999.10485670
    Schumacher, D. (2023). ompr: Model and solve mixed integer linear programs. Retrieved fromhttps://github.com/dirkschumacher/ompr
    Schölkopf, B., & Smola, A. J. (2001). Learning with kernels. The MIT Press. doi: 10.7551/mitpress/4175.001.0001
    Su, S. (2025, 1). Research on spam filters based on nb algorithm. ITM Web of Conferences, 70, 01016. Retrieved from https://www.itm-conferences.org/10.1051/itmconf/20257001016 doi: 10.1051/itmconf/20257001016
    Venter, J. H., & la Rey, T. (2007). Detecting outliers using weights. South African Statistical Journal, 41, 127-160.
    Wang, H., Liu, J., Chen, X., Wang, X., Li, P., & Yin, W. (2023, 10). Dig-milp: a deep instance generator for mixed-integer linear programming with feasibility guarantee. 52
    Williamson, R. C., & Cranko, Z. (2023). The geometry and calculus of losses. Journal of Machine Learning Research, 24, 1-72. Retrieved from http://jmlr.org/papers/v24/22-0987.html
    Xu, L., Crammer, K., & Schuurmans, D. (2006). Robust support vector machine training via convex outlier ablation. In Proceedings of the 21st national conference on artificial intelligence - volume 1 (p. 536-542). AAAI Press.
    Yadav, J. (2023, 1). Sentiment analysis on social media. Qeios. Retrieved from https://www.qeios.com/read/YF9X04 doi: 10.32388/YF9X04
    Zhang, W., Yang, D., & Zhang, S. (2021, 7). A new hybrid ensemble model with voting-based outlier detection and balanced sampling for credit scoring. Expert Systems with Applications, 174. doi: 10.1016/j.eswa.2021.114744
    描述: 碩士
    國立政治大學
    統計學系
    112354016
    資料來源: http://thesis.lib.nccu.edu.tw/record/#G0112354016
    資料類型: thesis
    顯示於類別:[統計學系] 學位論文

    文件中的檔案:

    檔案 描述 大小格式瀏覽次數
    401601.pdf1738KbAdobe PDF0檢視/開啟


    在政大典藏中所有的資料項目都受到原著作權保護.


    社群 sharing

    著作權政策宣告 Copyright Announcement
    1.本網站之數位內容為國立政治大學所收錄之機構典藏，無償提供學術研究與公眾教育等公益性使用，惟仍請適度，合理使用本網站之內容，以尊重著作權人之權益。商業上之利用，則請先取得著作權人之授權。
    The digital content of this website is part of National Chengchi University Institutional Repository. It provides free access to academic research and public education for non-commercial use. Please utilize it in a proper and reasonable manner and respect the rights of copyright owners. For commercial use, please obtain authorization from the copyright owner in advance.

    2.本網站之製作，已盡力防止侵害著作權人之權益，如仍發現本網站之數位內容有侵害著作權人權益情事者，請權利人通知本網站維護人員(nccur@nccu.edu.tw)，維護人員將立即採取移除該數位著作等補救措施。
    NCCU Institutional Repository is made to protect the interests of copyright owners. If you believe that any material on the website infringes copyright, please contact our staff(nccur@nccu.edu.tw). We will remove the work from the repository and investigate your claim.
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 回饋