臺灣紡織品是世界機能性紡織品消費市場主要原料供應來源之一，在紡織產業中，瑕疵品的出現是不可避免且持續存在的一個問題，尤其是在生產線的過程中有許多機器參數的設定干預到了最終產品的良率，降低了產品的價值和製造商的利潤。
如何有效同時降低多種紡織瑕疵是本研究之重點，目的在於找出對多種瑕疵種類與資料集特徵，本研究對生成型資料集進行數據分析以及規則探勘，選擇並找出對相對應的瑕疵種類有重大影響之特徵集，辨識出每個關鍵特徵的最佳範圍，並且將各關鍵特徵之範圍合成為規則。
此規則能提供給製造工程師當作調整參數的建議，並結合製造工程師之經驗，使最終紡織產品的良率得到改善。本研究的實驗結果闡明，在不同種類的資料集中需要使用不同的方法來進行規則探勘，以求得最佳的規則來改善紡織產品的良率，因此，本研究將會使用兩種不同的方法來對同一資料集進行分析與比較。

The textiles of Taiwan serve as one of the primary raw material sources for the global functional textile consumption market. Within this manufacturing, the occurrence of defects is an unavoidable and persistent issue. Particularly, myriad machine parameters during the production line process exert an influence on the final product's yield rate, subsequently depreciating the product's value and eroding the profit margins for manufacturers.
A central tenet of this study is the effective mitigation of various textile defects. Our objective is to discern patterns among multiple defect types and key parameters or features in the dataset. In this pursuit, we undertook data analysis and do the rule mining on synthetic datasets. After key features that significantly impact corresponding defect types were identified. Each key feature's optimal range was delineated, and a merged set of rules encapsulating the ranges of these key features was constructed.
These rules proffer suggestions for manufacturing engineers to refine parameter adjustments, and when integrated with the engineers' experiential knowledge, can enhance the yield rate of the final textile products. Experimental results of this study show that different dataset types necessitate distinct rule-mining methodologies to optimize textile product yield rates. Consequently, this research employed two disparate methods to analyze and compare a singular dataset.

[1] 王建敏：紡織業製程數位化—品質與交期的改善策略。2020年3月18日，取自https://reurl.cc/x62Zn4
[2] 中華民國紡織業拓展會：2022年台灣紡織工業概況。2023年7月12日，取自https://www.textiles.org.tw/ttf/main/content/ContentDesc.aspx?menu_id=95
[3] Lewis, Roger J. "An introduction to classification and regression tree (CART) analysis." Annual meeting of the society for academic emergency medicine in San Francisco, California. Vol. 14. San Francisco, CA, USA: Department of Emergency Medicine Harbor-UCLA Medical Center Torrance, 2000.
[4] Pedregosa, Fabian, et al. "Scikit-learn: Machine learning in Python." the Journal of machine Learning research 12 (2011): 2825-2830.
[5] Lee, D. H., Kim, S. H., Kim, E. S., Kim, K. J., & He, Z. "MR-CART: Multiresponse optimization using a classification and regression tree method." Quality Engineering 33.3 (2021): 457-473.
[6] Wahyuni, I., Chang, C. C., Yang, H. S., Wang, W. J., & Liang, D. "Multistage Parameter Optimization for Rule Generation for Multistage Manufacturing Processes." IEEE Transactions on Industrial Informatics (2023).
[7] Montgomery, Douglas C., Elizabeth A. Peck, and G. Geoffrey Vining. Introduction to linear regression analysis. John Wiley & Sons, 2021.
[8] Lee, Myeong-Soo, and Kwang-Jae Kim. "MR-PRIM: patient rule induction method for multiresponse optimization." Quality Engineering 20.2 (2008): 232-242.
[9] NASSIH, Rym, and Abdelaziz BERRADO. "Towards a patient rule induction method based classifier." 2019 1st International Conference on Smart Systems and Data Science (ICSSD) (pp. 1-5). Rabat, Morocco. IEEE, 2019.
[10] 倢愷：Scikit Learn 0.24 更新 SequentialFeatureSelector 介紹。2021年2月10日，取自https://reurl.cc/y6G53D
[11] Raschka, Sebastian. "MLxtend: Providing machine learning and data science utilities and extensions to Python’s scientific computing stack." Journal of open source software 3.24 (2018): 638.
[12] Lee, Dong-Hee, So-Hee Kim, and Kwang-Jae Kim. "Multistage MR-CART: Multiresponse optimization in a multistage process using a classification and regression tree method." Computers & Industrial Engineering 159 (2021): 107513.
[13] Wang, Bo, and Tao Chen. "Gaussian process regression with multiple response variables." Chemometrics and Intelligent Laboratory Systems 142 (2015): 159-165.
[14] Mukhopadhyay, Arunangshu, Vinay Kumar Midha, and Nemai Chandra Ray. "Multi-objective optimization of parametric combination of injected slub yarn for producing knitted and woven fabrics with least abrasive damage." Research Journal of Textile and Apparel 21.2 (2017): 111-133.
[15] Kwakkel, Jan H., and Marc Jaxa-Rozen. "Improving scenario discovery for handling heterogeneous uncertainties and multinomial classified outcomes." Environmental Modelling & Software 79 (2016): 311-321.
[16] Liang, Hua, and Hulin Wu. "Parameter estimation for differential equation models using a framework of measurement error in regression models." Journal of the American Statistical Association 103.484 (2008): 1570-1583.
[17] Arulsudar, N., N. Subramanian, and R. S. R. Murthy. "Comparison of artificial neural network and multiple linear regression in the optimization of formulation parameters of leuprolide acetate loaded liposomes." J Pharm Pharm Sci 8.2 (2005): 243-258.
[18] Dao-de, Sun. "Selection of the linear regression model according to the parameter estimation." Wuhan University Journal of Natural Sciences 5.4 (2000): 400-405.
[19] YANG,HUA-SHENG, “Adopting regression tree for rules mining to effectively reduce various fabric defects simultaneously”, National Central University, Master thesis, 2022.
[20] Chakraborty, Samit, Marguerite Moore, and Lisa Parrillo-Chapman. "Automatic Printed Fabric Defect Detection Based on Image Classification Using Modified VGG Network." International Conference on Applied Human Factors and Ergonomics (pp. 384-393). San Diego, CA, USA. Cham: Springer International Publishing, 2021.
[21] Arora, Parul, and Madasu Hanmandlu. "Detection of defects in fabrics using information set features in comparison with deep learning approaches." The Journal of The Textile Institute 113.2 (2022): 266-272.
[22] Kim, Seong-Jun, and Kang Bae Lee. "Constructing decision trees with multiple response variables." International Journal of Management and Decision Making 4.4 (2003): 337-353.
[23] Tsymbal, A., Cunningham, P., Pechenizkiy, M., & Puuronen, S. "Search strategies for ensemble feature selection in medical diagnostics." 16th IEEE Symposium Computer-Based Medical Systems, 2003. Proceedings.. IEEE, 2003.
[24] Uyanık, Gülden Kaya, and Neşe Güler. "A study on multiple linear regression analysis." Procedia-Social and Behavioral Sciences 106 (2013): 234-240.
[25] Nasrin, T., Pourali, M., Pourkamali-Anaraki, F., & Peterson, A. M. "Active learning for prediction of tensile properties for material extrusion additive manufacturing." Scientific Reports 13.1 (2023): 11460.
[26] Kim, Sungshin, and George J. Vachtsevanos. "An intelligent approach to integration and control of textile processes." Information Sciences 123.3-4 (2000): 181-199.
[27] Dema, M., Turner, C., Sari-Sarraf, H., & Hequet, E. "Machine vision system for characterizing horizontal wicking and drying using an infrared camera." IEEE Transactions on Industrial Informatics 12.2 (2016): 493-502.
[28] Bouatmane, S., Roula, M. A., Bouridane, A., & Al-Maadeed, S. "Round-Robin sequential forward selection algorithm for prostate cancer classification and diagnosis using multispectral imagery." Machine Vision and Applications 22 (2011): 865-878.
[29] Naheed, N., Shaheen, M., Khan, S. A., Alawairdhi, M., & Khan, M. A. "Importance of Features Selection, Attributes Selection, Challenges and Future Directions for Medical Imaging Data: A Review." CMES-Computer Modeling in Engineering & Sciences 125.1 (2020).
[30] Jović, Alan, Karla Brkić, and Nikola Bogunović. "A review of feature selection methods with applications." 2015 38th international convention on information and communication technology, electronics and microelectronics (MIPRO). Ieee, 2015.
[31] Dunne, Kevin, Padraig Cunningham, and Francisco Azuaje. "Solutions to instability problems with sequential wrapper-based approaches to feature selection." Journal of Machine Learning Research 1 (2002): 22.
[32] Almetwally, Alsaid Ahemd. "Multi-objective optimization of woven fabric parameters using Taguchi–Grey relational analysis." Journal of Natural fibers 17.10 (2020): 1468-1478.
[33] Vachtsevanos, G. J., Dorrity, J. L., Kumar, A., & Kim, S. "Advanced application of statistical and fuzzy control to textile processes." IEEE transactions on industry applications 30.3 (1994): 510-516.
[34] Hussain, Tanveer, Abdul Jabbar, and Shakeel Ahmed. "Comparison of regression and adaptive neuro-fuzzy models for predicting the compressed air consumption in air-jet weaving." Fibers and Polymers 15 (2014): 390-395.
[35] Bose, Indranil, and Radha K. Mahapatra. "Business data mining—a machine learning perspective." Information & management 39.3 (2001): 211-225.
[36] Langley, Pat, and Herbert A. Simon. "Applications of machine learning and rule induction." Communications of the ACM 38.11 (1995): 54-64.
[37] Stark, K. D., and Dirk U. Pfeiffer. "The application of non-parametric techniques to solve classification problems in complex data sets in veterinary epidemiology-an example." Intelligent Data Analysis 3.1 (1999): 23-35.
[38] Long, X., Fang, B., Zhang, Y., Luo, G., & Sun, F. "Fabric defect detection using tactile information." 2021 IEEE International Conference on Robotics and Automation (ICRA) (pp. 11169-11174). Xi'an, China. IEEE, 2021.