簡易檢索 / 詳目顯示

回結果列表
研究生： 陳怡蓁
Chen, Yi-Jen
論文名稱： 基於基因演算法與隨機基本模型之集成挑選方法
A Genetic Algorithm-Based Ensemble Selection Method for Random Base Models
指導教授： 翁慈宗
Wong, Tzu-Tsung
學位類別： 碩士
Master
系所名稱： 管理學院 - 資訊管理研究所
Institute of Information Management
論文出版年： 2026
畢業學年度： 114
語文別： 英文
論文頁數： 91
中文關鍵詞： 集成學習 、集成選擇 、基因演算法 、簡易貝氏 、隨機生成模型
外文關鍵詞： ensemble learning, ensemble selection, genetic algorithm, naïve Bayes, randomized model generation
相關次數： 點閱：44  下載：0 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 傳統的集成模型生成與選擇方法雖然能夠提升預測準確率，但在應用於大型候選模型池時，往往面臨計算效率不佳與收斂不穩定等問題。為了解決上述挑戰，本研究提出一種基於基因演算法之集成選擇框架（GeneticAlgorithm-based Ensemble Selection, GAES），用以提升二元分類任務中以簡易貝氏模型為基礎之集成模型的計算效率與分類效能。
    本研究所提出之框架結合了基於粒子群最佳化之隨機生成模型方法與基於基因演算法之集成選擇方法。候選模型首先透過隨機生成機制建立，接著再透過演化式選擇程序進行最佳化，以選取較具代表性且具預測能力的模型子集。
    實驗結果顯示，相較於結合二元整數規劃法的集成挑選方法（BinaryInteger Programming Ensemble Selection, BIPES），GAES 能夠大幅降低計算成本。尤其在較複雜的資料集上，BIPES經常無法在實務可接受的時間限制內完成收斂。另一方面，GAES 在執行時間方面也持續優於基於資訊熵值之集成選擇方法COMEP。就分類準確率而言，各方法都能達到相近的分類表現，而GAES在不同模型生成策略下皆維持具有競爭力的準確率。
    綜合而言，實驗結果顯示 GAES能夠在計算效率與預測效能之間取得良好的平衡。更重要的是，隨機生成模型與基於基因演算法之集成選擇的結合，為集成選擇問題提供了一種具可擴展性且實務可行的替代方案，可用以取代計算成本較高的精確最佳化方法，並應用於實際情境中的集成模型建構。

    Ensemble learning can improve classification performance, but selecting an effective subset from a large pool of base models may be computationally expensive. This study proposes a genetic algorithm-based ensemble selection method (GAES) for Naïve Bayes ensembles in binary classification.
    Base models are generated using Bagging, particle swarm optimization (PSO) based randomized generation, and a hybrid strategy. GAES selects a fixed-size subset from each base model pool. The method is evaluated on 20 datasets using five-fold cross-validation and compared with Binary Integer Programming Ensemble Selection (BIPES) and COMEP in terms of accuracy and runtime.
    The results show that GAES achieves accuracy comparable to the benchmark methods while maintaining low and stable runtimes. BIPES frequently reaches the predefined 500-second time limit, whereas GAES completes all evaluated cases within the limit. Ensemble selection also reduces ensemble size while generally preserving accuracy.
    These findings indicate that GAES provides an effective balance between predictive performance and computational efficiency.

    中文摘要 i Abstract ii 誌謝 Acknowledgement iii Contents v List of Tables viii List of Figures ix 1 Introduction 1 1.1 Motivation 1 1.2 Objective 2 2 Literature Review 5 2.1 Ensemble Learning 5 2.1.1 Bagging 6 2.1.2 Boosting 7 2.1.3 Randomly Generated Model 9 2.2 Ensemble Selection 10 2.2.1 Ordering-based Ensemble Selection 11 2.2.2 Search-based Ensemble Selection 11 2.2.3 Optimization-based Ensemble Selection 12 2.3 Heuristic Algorithm 13 2.4 Summary 16 3 Methodology 18 3.1 Research Flow 18 3.2 Data Preprocessing and Partitioning 23 3.3 The Generation of Base Models 24 3.3.1 Bagging 24 3.3.2 Random Model Generation 25 3.3.3 Particle Swarm Optimization Algorithm 26 3.4 Data Filtering 29 3.5 Optimization Model 30 3.6 Ensemble Selection 31 3.6.1 Population Initialization 32 3.6.2 Selection 34 3.6.3 Crossover 36 3.6.4 Mutation 37 3.6.5 Stopping Criteria 39 3.7 Experimental Result Evaluation 39 4 Experiments and Results 42 4.1 Datasets 42 4.2 Experimental Setup 43 4.3 Parameter Settings 45 4.4 Analysis of Base Model Probability Distributions 49 4.5 Data Filtering Analysis 52 4.6 Experimental Results and Comparison 55 4.6.1 Computational Efficiency 55 4.6.2 Classification Accuracy 59 4.7 Analysis of Hybrid Ensemble Composition 67 4.8 Discussion 67 5 Conclusions and Future Work 72 5.1 Conclusions 72 5.2 Future Work 74 References 77

    Bian, Y., Wang, Y., Yao, Y., and Chen, H. (2020). Ensemble pruning based on objection maximization with a general distributed framework. IEEE Transactions on Neural Networks and Learning Systems, 31(9):3766-3774.

    Boukir, S., Guo, L., and Chehata, N. (2021). Improving remote sensing multiple classification by data and ensemble selection. Photogrammetric Engineering & Remote Sensing, 87(11):841-852.

    Chen, Y.-C. (2025). An ensemble selection method based on accuracy optimization for bi-class data. Master’s thesis, National Cheng Kung University.

    Deb, K., Pratap, A., Agarwal, S., and Meyarivan, T. (2002). A fast and elitist multi-objective genetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation, 6(2):182-197.

    Eberhart, R. C. and Shi, Y. (2000). Comparing inertia weights and constriction factors in particle swarm optimization. In Proceedings of the 2000 Congress on Evolutionary Computation, volume 1, pages 84-88.

    Ezugwu, A. E. and Adewumi, A. O. (2022). Metaheuristic ensemble pruning via greedy-based optimization selection. International Journal of Applied Metaheuristic Computing, 13(1):1-26.

    Goldberg, D. E. (1989). Genetic Algorithms in Search, Optimization, and Machine Learning. Addison-Wesley.

    Gupta, N., Smith, J., Adlam, B., and Mariet, Z. (2022). Ensembles of classifiers: A bias-variance perspective. Transactions on Machine Learning Research, 2022.

    Ho, C.-H. (2024). Optimizing random ensemble algorithms for binary classification using particle swarm optimization. Master’s thesis, National Cheng Kung University.

    Holland, J. H. (1975). Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence. University of Michigan Press.

    Hsu, H.-Y. (2023). An ensemble approach for constructing random classification models using logistic regression. Master’s thesis, National Cheng Kung University.

    Huang, C.-L. (2023). Ensemble algorithms with randomly generated base models induced by naïve bayesian classifier. Master’s thesis, National Cheng Kung University.

    Jiang, Y., Ma, C., Wang, S., and Li, Y. (2024). A novel evolutionary algorithm for structural model updating with a hybrid initialization and multi-stage update strategy. Ocean Engineering, 305:117836.

    Karlos, S., Kostopoulos, G., and Kotsiantis, S. (2020). A soft-voting ensemble based co-training scheme using static selection for binary classification problems. Algorithms, 13(1):26.

    Katoch, S., Chauhan, S. S., and Kumar, V. (2021). A review on genetic algorithm: past, present, and future. Multimedia Tools and Applications, 80(5):8091-8126.

    Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.-Y. (2017). LightGBM: A highly efficient gradient boosting decision tree. In Advances in Neural Information Processing Systems, volume 30.

    Khan, A. A., Chaudhari, O., and Chandra, R. (2024). A review of ensemble learning and data augmentation models for class imbalanced problems: Combination, implementation and evaluation. Expert Systems with Applications, 244:122778.

    Lai, S.-Y. (2025). Ensemble algorithms with random base models based on a hybrid of adaptive particle swarm optimization and grey wolf optimization. Master’s thesis, National Cheng Kung University.

    Mienye, I. D. and Sun, Y. (2022). A survey of ensemble learning: Concepts, algorithms, applications, and prospects. IEEE Access, 10:99129-99153.

    Moslemi, A. (2023). A tutorial-based survey on feature selection: Recent advancements on feature selection. Engineering Applications of Artificial Intelligence, 126:107136.

    Ngo, G., Beard, R., and Chandra, R. (2022). Evolutionary bagging for ensemble learning. Neurocomputing, 510:1-14.

    Nguyen, K. A., Chen, W., Lin, B.-S., and Seeboonruang, U. (2021). Comparison of ensemble machine learning methods for soil erosion pin measurements. ISPRS International Journal of Geo-Information, 10(1):42.

    Ni, Z., Xia, P., Zhu, X., Ding, Y., and Ni, L. (2020). A novel ensemble pruning approach based on information exchange glowworm swarm optimization and complementarity measure. Journal of Intelligent & Fuzzy Systems, 39(6):8299-8313.

    Raut, S. A. and Harale, S. D. (2022). An in-depth and contrasting survey of meta-heuristic approaches with classical feature selection techniques specific to cervical cancer. Biomedical Signal Processing and Control, 77:103811.

    Sagi, O. and Rokach, L. (2018). Ensemble learning: A survey. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 8(4):e1249.

    Shen, X., Dai, Q., Zhu, G., and Zhang, J. (2023). Dynamic ensemble pruning algorithms fusing meta-learning with heuristic parameter optimization for time series prediction. Expert Systems with Applications, 225:120148.

    Soloff, J. A., Barber, R. F., and Willett, R. (2024). Bagging provides assumption-free stability. Journal of Machine Learning Research, 25(131):1-35.

    Tan, P.-N., Steinbach, M., and Kumar, V. (2006). Introduction to Data Mining. Pearson Addison-Wesley.

    Tsoumakas, G., Partalas, I., and Vlahavas, I. (2009). An ensemble pruning primer. In Applications of Supervised and Unsupervised Ensemble Methods, pages 1-13. Springer.

    Xie, X.-F., Zhang, W.-J., and Yang, Z.-L. (2003). Overview of particle swarm optimization. Control and Decision, 18(2):129-134.

    Zhou, Z.-H., Wu, J., and Tang, W. (2002). Ensembling neural networks: Many could be better than all. Artificial Intelligence, 137(1-2):239-263.

    QR CODE