分類為資料探勘領域中重要的研究課題，而真實世界中的資料常具有類別分布不平衡之特性，使傳統分類模型容易受到多數類別影響，進而降低對少數類別樣本之辨識能力。因此，如何提升不平衡資料之分類效能，已成為近年來的重要研究議題。
集成學習可透過整合多個基本模型之預測結果提升分類效能，但在處理不平衡資料時，往往會受到多數類別樣本的影響造成偏誤，使少數類別的辨識能力無法充分展現。此外，若所有基本模型皆納入集成，不會僅增加冗餘資訊，也會提升模型計算成本。因此集成挑選成為重要研究方向。本研究將延伸既有以分類正確率為目標之最佳化式集成挑選方法，重新設計專屬於不平衡資料的處理流程，利用袋裝法與隨機生成法建立候選基本模型，並從中挑選出最佳組合。首先，本研究提出一套負類樣本過濾機制，移除不會影響評估指標計算結果的樣本，以降低最佳化模型中的限制式數量並提升運算效率，接著，針對不平衡資料設計線性化最佳化目標式並加入不平衡比例權重，以提升模型對少數類別樣本的辨識能力。
實驗結果顯示，在資料過濾方面，袋裝法因基本模型間預測結果較為一致，因此具有最高的負類樣本過濾比例，可有效降低最佳化模型規模並提升求解效率。在分類效能方面，袋裝混合隨機生成法於整體表現上最佳，顯示透過混合不同基本模型生成方式建立候選基本模型集合，可維持一定預測穩定性的同時並保有適當的預測結果差異，提升分類效能。而在求解效率方面，由於本研究方法需透過混合整數線性規劃進行求解，計算時間相對長，但能透過資料過濾機制降低計算成本，使整體計算成本得以控制。此外，本研究提出之最佳化目標式於多數資料集上皆具有良好且穩定的表現，證實其能有效提升模型對少數類別樣本的辨識能力。整體而言，本研究所提出之方法能兼顧分類效能與計算效率，對於不平衡資料之集成挑選問題提供一具體且可行的解決方案。

Classification of imbalanced data has become an important issuebecause traditional algorithms tend to favor the majority class and thus perform poorly on minority-class instances. Ensemble learning improves classification performance by integrating multiple base models; however, selecting an appropriate subset of base models for imbalanced data remains a challenging problem. A previous study proposed an optimization-based ensemble selection method to improve prediction accuracy, and this study redesigns its optimization modelfor imbalanced data. Candidate base models are generated using bagging and random generation methods, and a mechanism is designed to remove negative instances that have no impact on ensemble selection. A linear objective function that integrating true positives and false negatives is proposed for the optimization model to enhance the recognition ability of minority-class instances. The experimental results on 30 imbalanced data sets showed that bagging approach achieves the highest filtering rate because its base models have more consistent predictions. When classification performance is evaluated by G-mean, the hybrid of bagging and random generation achieves the best overall performance. The ensemble selection method proposed in this study has a higher G-mean than another method proposed by a previous study regardless of the ways for generating base models. However, our methods need more computation effort in solving the optimization model for ensemble selection.

王敏，(2024)，隨機生成基本模型之集成方法應用於不平衡資料分類。國立成功大學資訊管理研究所碩士班碩士論文。
何政賢，(2024)，以粒子群最佳化方法優化應用於二類別資料之隨機集成演算法。國立成功大學資訊管理研究所碩士班碩士論文。
徐心縈，(2023)，用羅吉斯迴歸建構隨機分類模型之集成方法。國立成功大學資訊管理研究所碩士班碩士論文。
陳毓潔，(2025)，適用於二類別資料之基於正確率最佳化的集成挑選法。國立成功大學資訊管理研究所碩士班碩士論文。
黃愉兒，(2025)，抽樣方法結合隨機生成法應用於分類不平衡資料。國立成功大學資訊管理研究所碩士班碩士論文。
黃中立，(2023)，以簡易貝氏分類器隨機生成基本模型之集成方法。國立成功大學資訊管理研究所碩士班碩士論文。
Afolabi, D., Sennaike, O., Ogunseye, S., & Philips, A. (2023). RAMEN: A ratio-weighted majority entropy-based decision tree algorithm for classifying imbalanced datasets. In 2023 3rd International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME). IEEE.
Bakker, B., & Heskes, T. (2003). Task clustering and gating for Bayesian multitask learning. Journal of Machine Learning Research, 4, 83–99.
Batista, G. E. A. P. A., Prati, R. C., & Monard, M. C. (2004). A study of the behavior of several methods for balancing machine learning training data. SIGKDD Explorations, 6(1), 20–29.
Bian, Y., Wang, Y., Yao, Y., & Chen, H. (2019). Ensemble pruning based on objection maximization with a general distributed framework. IEEE Transactions on Neural Networks and Learning Systems, 31(9), 3766-3774.
Breiman, L. (1996). Bagging predictors. Machine Learning, 24(2), 123–140.
Breiman, L. (2001). Random forests. Machine learning, 45, 5-32.
Buckland, M. & Gey, F. (1994). The relationship between recall and precision. Journal of the American Society for Information Science, 45(1), 12–19.
Caruana, R., Niculescu-Mizil, A., Crew, G., & Ksikes, A. (2004). Ensemble selection from libraries of models. Proceedings of the 21st International Conference on Machine Learning (ICML ’04), 18.
Castro, P. A. D. de, Coelho, G. P., Caetano, M. F., & Von Zuben, F. J. (2005). Designing ensembles of fuzzy classification systems: An immune-inspired approach. In Artificial Immune Systems (ICARIS 2005) (LNCS 3627, pp. 469–482). Springer.
Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: Synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 16, 321–357.
Chen, W., Yang, K., Yu, Z., Shi, Y., & Chen, C. L. P. (2024). A survey on imbalanced learning: Latest research, applications and future directions. Artificial Intelligence Review, 57, 137–189.
Chicco, D. & Jurman, G. (2020). The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics, 21(6), 1–13.
Cieslak, D. A., & Chawla, N. V. (2008). Learning decision trees for unbalanced data. In W. Daelemans, B. Goethals, & K. Morik (Eds.), Machine learning and knowledge discovery in databases (ECML PKDD 2008) (pp. 241–256). Springer.
Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273–297.
Coyle, M., & Smyth, B. (2006). On the use of selective ensembles for relevance classification in case-based web search. Advances in Case-Based Reasoning (ECCBR 2006) (LNCS 4106, pp. 106–120). Springer.
Dietterich, T. G. (2000). Ensemble methods in machine learning. In J. Kittler & F. Roli (Eds.), Multiple classifier systems(pp. 1–15). Springer.
Durgesh, K. S., & Lekha, B. (2010). Data classification using support vector machine. Journal of Theoretical and Applied Information Technology, 12(1), 1–7.
Eom, G., & Byeon, H. (2023). Searching for optimal oversampling to process imbalanced data: Generative adversarial networks and synthetic minority over-sampling technique. Mathematics, 11(16), 3605.
Fawcett, T. (2006). An introduction to ROC analysis. Pattern Recognition Letters, 27(8), 861–874.
Freund, Y. & Schapire, R. E. (1997). A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences, 55(1), 119- 139.
Friedman, J. H. (2001). Greedy function approximation: a gradient boosting machine. Annals of Statistics, 1189-1232.
Galar, M., Fernández, A., Barrenechea, E., Bustince, H., & Herrera, F. (2012). A review on ensembles for the class imbalance problem: Bagging-, boosting-, and hybrid-based approaches. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 42(4), 463–484.
Gao, X., Xie, D., Zhang, Y., Wang, Z., Chen, C., He, C., Yin, H., & Zhang, W. (2023). A comprehensive survey on imbalanced data learning. Artificial Intelligence Review, 56(12), 1125–1154.
Gao, X., Xie, D., Zhang, Y., Wang, Z., Chen, C., He, C., Yin, H., & Zhang, W. (2025). A comprehensive survey on imbalanced data learning. Artificial Intelligence Review, 58(2), 112–145.
Giacinto, G., & Roli, F. (2001). Dynamic classifier selection based on multiple classifier behaviour. Pattern Recognition, 34(9), 1879–1881.
Guo, H., Li, Y., Shang, J., Gu, M., Huang, Y., & Gong, B. (2017). Learning from class-imbalanced data: Review of methods and applications. Expert Systems with Applications, 73, 220–239.
Hanley, J. A., & McNeil, B. J. (1982). The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology, 143(1), 29–36.
Hasib, K. M., Iqbal, M. S., Shah, F. M., Mahmud, J. A., Popel, M. H., Showrov, M. I. H., Ahmed, S., & Rahman, O. (2020). A survey of methods for managing the classification and solution of data imbalance problem. Journal of Computer Science, 16(11), 1546–1557.
He, H., Bai, Y., Garcia, E. A., & Li, S. (2008). ADASYN: Adaptive synthetic sampling approach for imbalanced learning. In 2008 IEEE International Joint Conference on Neural Networks (IJCNN) (pp. 1322–1328). IEEE.
Iranmehr, A., Masnadi-Shirazi, H., & Vasconcelos, N. (2019). Cost-sensitive support vector machines. Neurocomputing, 343, 50–64.
Japkowicz, N., & Stephen, S. (2002). The class imbalance problem: A systematic study. Intelligent Data Analysis, 6(5), 429–449.
Johnson, J. M. & Khoshgoftaar, T. M. (2019). Survey on deep learning with class imbalance. Journal of Big Data, 6(27), 1–54.
Kaisar, S., & Chowdhury, A. (2022). Integrating oversampling and ensemble-based machine learning techniques for an imbalanced dataset in dyslexia screening tests. ICT Express, 8(4), 563–568.
Krawczyk, B., Galar, M., Jeleń, Ł., & Woźniak, M. (2014). Cost-sensitive decision tree ensembles for effective imbalanced classification. Applied Soft Computing, 14, 554–562.
Krawczyk, B. (2016). Learning from imbalanced data: Open challenges and future directions. Progress in Artificial Intelligence, 5(4), 221–232.
Kubat, M., & Matwin, S. (1997). Addressing the curse of imbalanced training sets: One-sided selection. In Proceedings of the 14th International Conference on Machine Learning (ICML ’97) (pp. 179–186).
Laskov, P., Düssel, P., Schäfer, C., & Rieck, K. (2005). Learning intrusion detection: Supervised or unsupervised? In Proceedings of ICIAP 2005: International Conference on Image Analysis and Processing (pp. 1–8).
Leevy, J. L., Khoshgoftaar, T. M., Bauder, R. A., & Seliya, N. (2018). A survey on addressing high-class imbalance in big data. Journal of Big Data, 5(42), 1–30.
Ling, C. X., & Sheng, V. S. (2008). Cost-sensitive learning and the class imbalance problem. In C. Sammut (Ed.), Encyclopedia of machine learning (pp. 231–235). Springer.
López, V., Fernández, A., García, S., Palade, V., & Herrera, F. (2013). An insight into classification with imbalanced data. Information Sciences, 250, 113–141.
Margineantu, D. D., & Dietterich, T. G. (1997). Pruning adaptive boosting. Proceedings of the 14th International Conference on Machine Learning (ICML ’97) (pp. 211–218).
Onan, A., Korukoğlu, S., & Bulut, H. (2017). A hybrid ensemble pruning approach based on consensus clustering and multi-objective evolutionary algorithm for sentiment classification. Information Processing & Management, 53(4), 814–833.
Phua, C., Lee, V., Smith, K., & Gayler, R. (2010). A comprehensive survey of data-mining-based fraud detection research. arXiv preprint arXiv:1009.6119.
Powers, D. M. W. (2011). Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation. Journal of Machine Learning Technologies, 2(1), 37–63.
Prati, R. C., Batista, G. E. A. P. A., & Monard, M. C. (2004). Class imbalances versus class overlapping: An analysis of a learning system behavior. In MICAI 2004: Advances in Artificial Intelligence (pp. 312–321). Springer.
Rainio, O., Teuho, J., & Klén, R. (2024). Evaluation metrics and statistical tests for machine learning. Scientific Reports, 14(6086), 1–12.
Rawat, S. S. & Mishra, A. K. (2022). Review of methods for handling class-imbalanced in classification problems. Amity Journal of Computational Sciences, 6(1), 1–12.
Rout, N., Mishra, D., & Mallick, M. K. (2018). Handling imbalanced data: A survey. In M. S. Reddy, et al. (Eds.), Advances in intelligent systems and computing (Vol. 628, pp. 431–443).
Saito, T. & Rehmsmeier, M. (2015). The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PLoS ONE, 10(3), e0118432.
Saleh, H., Mostafa, S., Alharbi, A., El-Sappagh, S., & Alkhalifah, T. (2022). Heterogeneous ensemble deep learning model for enhanced Arabic sentiment analysis. Sensors, 22(10), 3707.
Sanabila, H. N., & Jatmiko, W. (2018). Ensemble learning on large scale financial imbalanced data. In 2018 International Workshop on Big Data and Information Security (IWBIS) (pp. 79–84). IEEE.
Srivastava, A. N., & Sahami, M. (2010). Text Mining: Classification, Clustering, and Applications. Boca Raton, FL: Chapman & Hall/CRC Press.
Sun, Y., Wong, A. K. C., & Kamel, M. S. (2009). Classification of imbalanced data: A review. International Journal of Pattern Recognition and Artificial Intelligence, 23(4), 687–719.
Tahir, M. A., Kittler, J., & Yan, F. (2009). A multiple expert approach to the class imbalance problem using inverse random under sampling. In Multiple Classifier Systems (MCS 2009) (pp. 82–91).
Wood, D., Mu, T., Webb, A., Reeve, H. W. J., Luján, M., & Brown, G. (2023). A unified theory of diversity in ensemble learning. Journal of Machine Learning Research, 24(359), 1–49.
Woźniak, M., Zyblewski, P., & Ksieniewicz, P. (2023). Active Weighted Aging Ensemble for drifted data stream classification. Information Sciences, 640, 119017.
Yap, B. W., Rani, K. A., Rahman, H. A. A., Fong, S., Khairudin, Z., & Abdullah, N. N. (2014). An application of oversampling, undersampling, bagging and boosting in handling imbalanced datasets. Proceedings of the First International Conference on Advanced Data and Information Engineering (DaEng-2013) (pp. 13–22). Springer.
Zhang, C., Zhang, S., & Yang, Q. (2006). Ensembles of classifiers for handling class imbalance. Proceedings of the 2006 International Conference on Data Mining Workshops (pp. 1–8). IEEE.
Zhang, H., & Cao, L. (2014). A spectral clustering based ensemble pruning approach. Neurocomputing, 139, 289–297.
Zhou, Z.-H., Wu, J., & Tang, W. (2002). Ensembling neural networks: Many could be better than all. Artificial Intelligence, 137(1–2), 239–263.
Zhou, Z.-H., & Liu, X.-Y. (2006). Training cost-sensitive neural networks with methods addressing the class imbalance problem. IEEE Transactions on Knowledge and Data Engineering, 18(1), 63–77.
Zhou, Z.-H. (2012). Ensemble methods: Foundations and algorithms. Boca Raton, FL: CRC Press.