臺灣博碩士論文加值系統

自動光學檢測是電子產業常用檢測儀器，決定產品最終品質關鍵，檢測中常有漏報或誤檢情形，需再次複檢，此情形為產業所不樂見，改善瑕疵檢測是產業重視一大議題。而瑕疵品即早發現，能節省不必要的成本，故不斷的改善自動光學檢測是解決問題的關鍵。收集數據常發生數據不平衡問題，導致機器學習無法有效分類，採樣方法是解決類別不平衡常用方法，目的於使類別數據能趨於平衡，而資料的不同採樣，所訓練出模型會有不同結果。本研究探討不同比例及不同採樣方法，嘗試解決不平衡情況，數據集為表面貼裝技術產線不平衡資料集。
本研究採用不同資料分布模擬不同的不平衡情況，使用隨機降採樣、隨機過採樣及隨機過採樣結合隨機降採樣，三種不同採樣透過隨機森林得出分類效果比較何種採樣方法適合解決此問題，並用該數據集不同的不平衡問題是否有效。而驗證其數據集前，本研究使用單因子重複量數變異數分析，檢測模型效度，並以Cohen's Kappa判斷模型信度，證明模型的效果和穩定度。
研究成果發現，隨機過採樣結合隨機降採樣優於隨機過採樣優於隨機降採樣，防止漏檢及誤報，而漏檢比誤報更為嚴重，本研究選擇隨機降採樣為模型，原因於隨機降採樣有效地降低漏檢情況發生而誤報的情況也還在可控制的範圍內，該數據集不同不平衡結果本研究模型是有效，不過數據集本身瑕疵樣本極少，造成不平衡比例越高，漏檢率有提升現象，說明不同不平衡問題會因原始樣本數多寡影響分類結果。

Automatic optical inspection (AOI) is a commonly used inspection instrument in the electronics industry. It is the key to determining the final quality of the products. During inspection, there are often omissions or false detections, which require re-inspection. This situation is not welcomed by the industry. Improving defect detection is an important issue that the industry attaches great importance to. Early detection of defective products can save unnecessary costs, so continuous improvement of AOI is the key to solving the problem. Data imbalance often occurs when collecting data, resulting in the inability of machine learning to effectively classify. The sampling method is a common method to solve the category imbalance. The purpose is to make the category data tend to be balanced. Different sampling of the data will produce different results for the trained model. This study explores different proportions and different sampling methods to try to solve the imbalance situation. The data set is the surface-mounted technology production line imbalance data set.
This study uses different data distributions to simulate different imbalance situations, using Random Under-Sampling (RUS), Random Over-Sampling (ROS), and ROS combined with RUS. Three different samplings are used to obtain classification effects through random forests to compare which sampling method is suitable to solve this problem. The question and whether the different imbalance problems are valid with this data set. Before validating its data set, this study used one-way repeated measures ANOVA to test the validity of the model, and used Cohen's Kappa to judge the reliability of the model to prove the effect and stability of the model.
The research results show that ROS combined with RUS is better than ROS than RUS in preventing missed detections and false alarms. Missed detections are more serious than false alarms. This study chose RUS as the model because RUS can effectively reduce the occurrence of missed detections and the number of false positives is still within a controllable range. The different results of the imbalance of this data set are effective. This research model is effective, but the data set itself has very few defective samples, resulting in an imbalanced ratio. The higher the value, the higher the missed detection rate, indicating that different imbalance problems will affect the classification results due to the number of original samples.

摘要..........................i
Abstract..........................ii
誌謝..........................iv
目錄..........................v
表目錄..........................vii
圖目錄..........................ix
第一章 緒論..........................1
1.1 研究背景與動機..........................1
1.2 研究目的..........................2
1.3 研究方法..........................2
1.4 研究流程..........................2
第二章 文獻探討..........................5
2.1表面貼焊技術..........................5
2.2類別不平衡..........................6
2.3資料採樣..........................7
2.4利用機器學習進行類別不平衡相關預測..........................11
2.5品質控制在漏檢和誤報的影響..........................12
第三章 研究方法..........................13
3.1數據集說明..........................13
3.2資料預處理..........................15
3.3特徵建構..........................16
3.4不平衡比例..........................16
3.5採樣方法..........................17
3.5.1隨機降採樣..........................17
3.5.2隨機過採樣..........................18
3.5.3隨機過採樣結合隨機降採樣..........................18
3.6隨機森林..........................19
3.7模型評估..........................21
3.8研究流程..........................22
第四章 研究結果..........................25
4.1不同比例對採樣效度的影響..........................25
4.2不同比例對於採樣的信度影響..........................27
4.3不同採樣對不同比例的精確率和召回率比較..........................28
4.3.1使用隨機降採樣的精確率和召回率驗證第二個不平衡問題..........................29
第五章 結果與討論..........................31
5.1結果與討論..........................31
5.2結論與建議..........................32
參考文獻..........................33
附錄一..........................39
附錄二..........................63
Extended Abstract..........................74

1.Ahmadzadeh, A., & Angryk, R. A. (2022). Measuring Class-Imbalance Sensitivity of Deterministic Performance Evaluation Metrics. 2022 IEEE International Conference on Image Processing (ICIP) (pp. 51–55).
2.Ahmed, A. N., & Saini, R. (2023). Detection of Credit Card Fraudulent Transactions Utilizing Machine Learning Algorithms. 2023 2nd International Conference for Innovation in Technology (INOCON) (pp. 1–5).
3.Alghamdi, T. A., & Javaid, N. (2022). A Survey of Preprocessing Methods Used for Analysis of Big Data Originated From Smart Grids. IEEE Access, 10, 29149–29171.
4.Azuaje, F., Witten, I., & E, F. (2006). Witten IH, Frank E: Data Mining: Practical Machine Learning Tools and Techniques. Biomedical Engineering Online—BIOMED ENG ONLINE, 5, 1–2.
5.Bellinger, C., Sharma, S., & Japkowicz, N. (2012). One-Class versus Binary Classification: Which and When? 2012 11th International Conference on Machine Learning and Applications (Vol. 2, pp. 102–106).
6.Biau, G., & Scornet, E. (2016). A random forest guided tour. TEST, 25(2), 197–227.
7.Breiman, L. (2001). Random Forests. Machine Learning, 45(1), 5–32.
8.Cao, L., & Zhai, Y. (2015). Imbalanced Data Classification Based on a Hybrid Resampling SVM Method. 2015 IEEE 12th Intl Conf on Ubiquitous Intelligence and Computing and 2015 IEEE 12th Intl Conf on Autonomic and Trusted Computing and 2015 IEEE 15th Intl Conf on Scalable Computing and Communications and Its Associated Workshops (UIC-ATC-ScalCom) (pp. 1533–1536).
9.Chang, Y.-M., Chen, J., & Hsieh, P. (2017). Prediction of Solder Joint Quality Using a Data Mining Methodology for Surface Mounted Technology Process. Proceedings of the 1st International Conference on Big Data Research, ICBDR ’17 (pp. 52–56).
10.Chang, Y.-M., Wei, C.-C., Chen, J., & Hsieh, P. (2018). Classification of Solder Joints via Automatic Mistake Reduction System for Improvement of AOI Inspection. 2018 13th International Microsystems, Packaging, Assembly and Circuits Technology Conference (IMPACT) (pp. 150–153).
11.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.
12.Fawcett, T., & Provost, F. (1997). Adaptive Fraud Detection. Data Mining and Knowledge Discovery, 1(3), 291–316.
13.Hand, D., & Christen, P. (2018). A note on using the F-measure for evaluating record linkage algorithms. Statistics and Computing, 28(3), 539–547.
14.Hasan, K. A., & Hasan, Md. A. M. (2020). Prediction of Clinical Risk Factors of Diabetes Using Multiple Machine Learning Techniques Resolving Class Imbalance. 2020 23rd International Conference on Computer and Information Technology (ICCIT) (pp. 1–6).
15.Hastie, T., Tibshirani, R., & Friedman, J. (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Second Edition (Springer Series in Statistics).
16.He, H., & Garcia, E. A. (2009). Learning from Imbalanced Data. IEEE Transactions on Knowledge and Data Engineering, 21(9), 1263–1284.
17.Heaton, J. (2018). Ian Goodfellow, Yoshua Bengio, and Aaron Courville: Deep learning. Genetic Programming and Evolvable Machines, 19(1), 305–307.
18.Johnson, J. M., & Khoshgoftaar, T. M. (2021). Robust Thresholding Strategies for Highly Imbalanced and Noisy Data. 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA) (pp. 1182–1188).
19.Khushi, M., Shaukat, K., Alam, T. M., Hameed, I. A., Uddin, S., Luo, S., Yang, X., et al. (2021). A Comparative Performance Analysis of Data Resampling Methods on Imbalance Medical Data. IEEE Access, 9, 109960–109975.
20.Kusdiyanto, A. Y., & Pristyanto, Y. (2022). Machine Learning Models for Classifying Imbalanced Class Datasets Using Ensemble Learning. 2022 5th International Seminar on Research of Information Technology and Intelligent Systems (ISRITI) (pp. 648–653).
21.Lau, F. K. H., & Yeung, V. W. S. (1997). A hierarchical evaluation of the solder paste printing process. Journal of Materials Processing Technology, 69(1), 79–89.
22.Le, T., Vo, M., Vo, B., Lee, M., & Baik, S. (2019). A Hybrid Approach Using Oversampling Technique and Cost-Sensitive Learning for Bankruptcy Prediction. Complexity, 2019, 1–12.
23.Lemaître, G., Nogueira, F., & Aridas, C. (2016). Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning, 18.
24.Liaw, A., & Wiener, M. (2001). Classification and Regression by RandomForest. Forest, 23.
25.Lin, W.-C., Tsai, C.-F., Hu, Y.-H., & Jhang, J.-S. (2017). Clustering-based undersampling in class-imbalanced data. Information Sciences, 409–410, 17–26.
26.Mohammed, R., Rawashdeh, J., & Abdullah, M. (2020). Machine Learning with Oversampling and Undersampling Techniques: Overview Study and Experimental Results. 2020 11th International Conference on Information and Communication Systems (ICICS) (pp. 243–248).
27.Mohammed, Z., Asghar, M., & Kanwal, N. (2021). Analyzing the impact of COVID-19 on flight cancellation using machine learning and deep learning algorithms for a highly unbalanced dataset. 2021 International Conference on Electrical, Computer and Energy Technologies (ICECET) (pp. 1–6).
28.Mohosheu, Md. S., al Noman, MD. A., Newaz, A., Al-Amin, & Jabid, T. (2024). A Comprehensive Evaluation of Sampling Techniques in Addressing Class Imbalance Across Diverse Datasets. 2024 6th International Conference on Electrical Engineering and Information & Communication Technology (ICEEICT) (pp. 1008–1013).
29.More, A. S., & Rana, D. P. (2017). Review of random forest classification techniques to resolve data imbalance. 2017 1st International Conference on Intelligent Systems and Information Management (ICISIM) (pp. 72–78).
30.Murphy, K. P. (2012). Machine Learning: A Probabilistic Perspective. MIT Press.
31.Nhita, F., Adiwijaya, & Kurniawan, I. (2023a). Performance and Statistical Evaluation of Three Sampling Approaches in Handling Binary Imbalanced Data Sets. 2023 International Conference on Data Science and Its Applications (ICoDSA) (pp. 420–425).
32.Nhita, F., Adiwijaya, & Kurniawan, I. (2023b). Improvement of Imbalanced Data Handling: A Hybrid Sampling Approach by using Adaptive Synthetic Sampling and Tomek links. 2023 Eighth International Conference on Informatics and Computing (ICIC) (pp. 1–5).
33.Palli, A. S., Jaafar, J., Hashmani, M. A., Gomes, H. M., & Gilal, A. R. (2022). A Hybrid Sampling Approach for Imbalanced Binary and Multi-Class Data Using Clustering Analysis. IEEE Access, 10, 118639–118653.
34.Permataning Tyas, S. M., Sarno, R., Haryono, A. T., & Rossa Sungkono, K. (2023). A Robustly Optimized BERT using Random Oversampling for Analyzing Imbalanced Stock News Sentiment Data. 2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE) (pp. 897–902).
35.Pristyanto, Y., & Dahlan, A. (2019). Hybrid Resampling for Imbalanced Class Handling on Web Phishing Classification Dataset. 2019 4th International Conference on Information Technology, Information Systems and Electrical Engineering (ICITISEE) (pp. 401–406).
36.Rahman, M., Palash, M. I. A., Sumi, M. S., Rahman, M., & Al Nahian, M. J. (2023). Using Ensemble Approaches and Different Sampling Techniques to Handle Class Imbalance Challenges in Coronary Heart Disease Prediction. 2023 International Conference on Information and Communication Technology for Sustainable Development (ICICT4SD) (pp. 31–35).
37.Rau, F. C., Wigger, A., Tellhelm, B., Zwick, M., Klumpp, S., Neumann, A., Oltersdorf, B., et al. (2011). Observer variability and sensitivity of radiographic diagnosis of canine medial coronoid disease. Tierarztliche Praxis. Ausgabe K, Kleintiere/Heimtiere, 39(5), 313–322.
38.Reshadat, V., & Kapteijns, R. A. J. W. (2021). Improving the Performance of Automated Optical Inspection (AOI) Using Machine Learning Classifiers. 2021 International Conference on Data and Software Engineering (ICoDSE) (pp. 1–5).
39.Rottmann, M., Hüger, F., Maag, K., Schlicht, P., Chan, R., & Gottschalk, H. (2019). Detection of False Positive and False Negative Samples in Semantic Segmentation.
40.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.
41.Sammut, C., & Webb, G. (2010). Encyclopedia of Machine Learning. Encyclopedia of Machine Learning: , ISBN 978-0-387-30768-8. Springer Science+Business Media, LLC, 2010.
42.Seiffert, C., Khoshgoftaar, T. M., & Van Hulse, J. (2008). Hybrid sampling for imbalanced data. 2008 IEEE International Conference on Information Reuse and Integration (pp. 202–207).
43.Shehada, D., Muammar, S., Amour, M. A., & Bouridane, A. (2023). Investigating The Impact of Sampling Techniques on an Imbalanced Classification Problem. 2023 6th International Conference on Signal Processing and Information Security (ICSPIS) (pp. 39–44).
44.Sridhar, S., & Sanagavarapu, S. (2021). Handling Data Imbalance in Predictive Maintenance for Machines using SMOTE-based Oversampling. 2021 13th International Conference on Computational Intelligence and Communication Networks (CICN) (pp. 44–49).
45.Sun, Y., Kamel, M. S., Wong, A. K. C., & Wang, Y. (2007). Cost-sensitive boosting for classification of imbalanced data. Pattern Recognition, 40(12), 3358–3378.
46.Ugarković, A., & Oreški, D. (2022). Supervised and Unsupervised Machine Learning Approaches on Class Imbalanced Data. 2022 International Conference on Smart Systems and Technologies (SST) (pp. 159–162).
47.Yadav, S., & Bhole, G. P. (2020). Handling Imbalanced Dataset Classification in Machine Learning. 2020 IEEE Pune Section International Conference (PuneCon) (pp. 38–43).
48.Zhang, L., & Wang, W. (2011). A Re-sampling Method for Class Imbalance Learning with Credit Data. 2011 International Conference of Information Technology, Computer Engineering and Management Sciences (Vol. 1, pp. 393–397).