FABRIC AND PRODUCTION DEFECT DETECTION IN THE APPAREL INDUSTRY USING DATA MINING ALGORITHMS

Year 2021, , 742 - 757, 30.12.2021

Taner Ersöz , Hamza Zahoor Filiz Ersöz

https://doi.org/10.46519/ij3dptdi.1030676

Cited By: 1

Abstract

Data mining has proven itself in various fields such as business, health, finance and education when it comes to extracting meaningful insights from data and knowledge discovery. In this study, it was aimed to determine the main causes of the error with faulty production data of a company that produces clothing by using data mining methods. Decision Tree, Naive Bayes, Random Forest and Gradient Boosted Trees Algorithms were used in the research. Accuracy level and Cohen’s kappa value were taken for comparison algorithms in the study. While determining the main reasons for faulty production, the factors of which type of products the company produces for its customers, the sizes of the defective products, types of defects and explanations were taken into consideration. The most common mistakes in sewing production and the main source of the error were evaluated. According to the results, suggestions were made for the company to take various measures.

Keywords

Textile, defect detection, machine learning, data mining, classification algorithms, decision tree.

FABRIC AND PRODUCTION DEFECT DETECTION IN THE APPAREL INDUSTRY USING DATA MINING ALGORITHMS

Abstract

Nowadays, technology plays a crucial role in fabric production in the textile industry. The demand for high-quality products and rapidly changing economic conditions increase the significance of ready-made clothing manufacturers to produce the right quality product. In addition, in order to minimize production errors, to improve and maintain process performance, it is important to identify the sources of variability during manufacturing. The defective fabric is the main reason which is causing harm to the textile business. Therefore, the proper identification of manufacturing defects leads to a successful business. When it comes to extracting meaningful insights from data and knowledge discovery, data mining has proven its significance in various fields such as business, health, finance, and education. As in all other sectors, data mining is widely used in the textile sector too. In this study, it was aimed to determine the main causes of the error with defective production data of a company that produces clothing by using data mining methods. Decision Tree, Naive Bayes, Random Forest, and Gradient Boosted Trees Algorithms were used in the research. Accuracy rate and Cohen’s kappa statistics were taken for comparison algorithms in the study. While determining the main reasons for defective products, the factors of which type of products the company produces for its customers, the sizes of the defective products, types of defects, and explanations were taken into consideration. The most common mistakes in sewing production and the main source of the error were evaluated. According to the results, suggestions were made for the company to take various measures.

Keywords

Textile, defect detection, machine learning, data mining, classification algorithms, decision tree.

References

• 1. Cheng, S.Y, Yuen C.W.M., Kan C.W., Cheuk K.K.L., “Development of cosmetic textiles using microencapsulation technology”, Research Journal of Textile and Apparel, Vol. 12 Issue 4, Pages 41-51, 2008.
• 2. Ersoz, T., Tenbeli, R., Ersoz, F., “Visual analysis of textile sector of Turkey using gephi complex network”, 11th International Symposium on Intelligent Manufacturing and Service Systems, May 2021.
• 3. Devlet Planlama Teşkilatı, “Tekstil ve hazır giyim sanayi özel ihtisas komisyonu raporu”, DPT, Ankara, 1982.
• 4. Aydın, E., “İnternet tüketicilerinin hazır giyim satın alma davranışları üzerine bir araştırma”, Yüksek Lisans Tezi Kastamonu Üniversitesi Sosyal Bilimler Enstitüsü, Kastamonu, 2019.
• 5. Atan, M. A., “Hazır giyim üretim planlamasında karşılaşılan sorunlar ve bir model önerisi”, Yüksek Lisans Tezi, Gazi Üniversitesi Eğitim Bilimleri Ensitüsü, Ankara, 2011.
• 6. Akyol, A., “Tekstil ve hazır giyim sektörüne pazar oryantasyonu açısından genel bir bakış”. Pazarlama Dünya Dergisi, Vol. 45, 2001.
• 7. Fibre2fashion website, Quality and productivity improvement in apparel industry, Pub. 2013, Retrived from https://www.fibre2fashion.com/industry-article/7220/quality-and-productivity-improvement-in-apparel-industry
• 8. Smith, M.L., Stamp, R.J., “Inspection of textured ceramic tiles using automation”, Computers in Industry, Vol. 43 Issue 1, Pages 73-82, 2000.
• 9. Chin, R. T., Harlow, C. A., “Automated visual inspection, IEEE Trans, Pattern Anal. Machine Intell., Vol. 4 Issue 6, Pages 557-573, 1982.
• 10. Sengottuvelan, P., Wahi A., Shanmugam A., “Use of imaging systems for automatic defect analysis”, Research Journal of Applied Sciences, Vol. 3 Issue 1, Pages 26-31, 2008.
• 11. Srinivasan, K., Dastoor, P.H., Radhakrishnaiah & Sundaresan Jayaraman., “FDAS: A knowledge-based frame detection work for analysis of defects in woven textile structures”, Textile Institute’s journal, Vol. 83, Issue 3, Pages 431-448, 1992.
• 12. Smartex website, 04 September 2021, “Retracing production cost”, Retrieved from https://www.smartex.ai/
• 13. Uyanık, S., Çelikel, C.D., “Türk tekstil endüstrisi genel durumu”, Teknik Bilimleri Dergisi, Vol. 9, Pages 32-41, 2019.
• 14. Hazır giyim ve konfeksiyon sektörü 2021 şubat aylık ihracat bilgi notu. https://www.itkib.org.tr Accessed April 2021.
• 15. Küheylan, Z., “İhracatın parlayan yıldızı hazır giyim sektörü”, İzmir Ticaret Odası, İzmir, 2020.
• 16. İstanbul Tekstil Konfeksiyon İşletmeler Birliği, “Hazır giyim ve konfeksiyon sektörü 2020 raporu”, İstanbul. 2020.
• 17. Mozafary, V., Payvandy, P., “Application of data mining technique in predicting worsted spun yarn quality”, The Journal of The Textile Institute, Vol. 105 Issue 1, 2014.
• 18. Ersöz, F., “Veri Madenciliği Teknikleri ve Uygulamaları”, Seçkin Yayınevi, Ankara, 2019.
• 19. Piatetsky-Shapiro, G., Fayyad, U., Smyth, P., “Knowledge discovery and data mining: towards a unifying framework”, AAAI Press / The MIT Press, Menlo Park, CA. Pages 82-88, 1996.
• 20. Seçkin, M., Seçkin, A.Ç., Coşkun, A., “Simulation of production fault and forecasting from time series data with machine learning in glove textile industry”, Journal of Engineered Fibers and Fabrics, Vol. 14, 2019.
• 21. Tyagi, S.K., Sharma B.K., “Data mining tools and techniques to manage the textile quality control data for strategic decision making, International Journal of Computer Applications (0975 – 8887), Vol. 13 Issue 4, January 2011.
• 22. Vajihe, M., Pedram, P., “Application of data mining technique in estimating worsted yarn quality”, The Journal of The Textile Institute, Vol. 105 Issue 1, Pages 100-108, 2014.
• 23. Javed, A., Mirza, A.U., “Comparative analysis of different fabric defects detection techniques”, International journal of image, Graphics and Signal Processing. Vol. 5, Issue 10, 2013. 24. Yıldırım, P., Birant, D., Alpyıldız, T., “Data mining and machine learning in the textile industry”, WIREs data mining knowledge Discovery, DOI: 10.1002/widm.1228, 2018.
• 25. Colson, E., Coffey, B., Rached, T., Cruz, L. (n.d.), “Algorithm’s tour: How data science is woven into the fabric of Stitch Fix”, Retrieved from https://algorithms-tour.stitchfix.com/ 03 September 2021.
• 26. Guo, Z. X., Wong, W. K., Leung S. Y. S., Li M., “Applications of artificial intelligence in the apparel industry: A review”, Textile Research Journal, Vol. 81 Issue 18, Pages 1871- 1892, 2011.
• 27. Jelil, R. A., “Review of artificial intelligence applications in garment manufacturing”, In artificial Intelligence for Fashion Industry in the Big Data Era. Springer, Singapore, Pages 97-123, 2018.
• 28. Sirovich, R., Craparotta G., Marocco, E., “An intelligent fashion replenishment system based on data analytics and expert judgment”, In artificial Intelligence for Fashion Industry in the Big Data Era, Springer, Singapore, Pages 173-195, 2018.
• 29. Tağman, A.B., “Sistem Simülasyonu ile süreç iyileştirme: bir tekstil işletme uygulaması”, Yüksek Lisans Tezi, Karabük Üniversitesi Lisansüstü Eğitim Enstitüsü, Karabük, 2021.
• 30. Tozak, E., “Veri madenciliği programları kullanılarak bir tekstil firmasının satış verilerinin değerlendirilmesi”, Yüksek Lisans Tezi, Karabük Üniversitesi Lisansüstü Eğitim Enstitüsü, Karabük, 2021.
• 31. Odabaş, S., “Tekstil sektöründe ihracat yapan bir firmada talep tahmini uygulaması”, Yüksek Lisans Tezi, Karabük Üniversitesi Lisansüstü Eğitim Enstitüsü, Karabük, 2021.
• 32. Murino, V., Bicego, M., Rossi, I.A., “Statistical classification of raw textile defects”, Proceedings of the 17th International Conference on Pattern Recognition (ICPR’04) 1051-4651/04, 2004.
• 33. Habib, T. Md., Shuvo, S.B., Uddin, M.S., Ahmet, F., “Automated textile defect classification by bayesian classifier based on statistical features”, Conference: International Workshop on Computational Intelligence (IWCI), 2016.
• 34. Mohanty, A.K., Bag, A., “Detection and classification of fabric defects in textile using image mining and association rule miner”, International Journal of Electrical, Electronics and Computers (EEC Journal), Vol-2, Issue 3, 2017.
• 35. Ersoz, F., Ersoz, T., Guler, E., “Knowledge discovery and data mining techniques in textile industry”, International Journal of Computer and Information Engineering, Vol. 11, Issue 7, 2017.
• 36. Tagluk, M., “Dokuma tezgahlarında hatalı kumaş dokusunun tespiti için başarılı bir yöntem”, Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi, Vol. 8, Pages 575-586, 2017.
• 37. Cevik, K.K., Koçer, E., “Computer aided control of cutting error in textile products”, Textile and Apparel, Vol. 27 Issue 3, Pages 300-308, 2017.
• 38. Silvestre-Blanes J., Albero-Albero, T., Miralles I., Pérez-Llorens, R., Moreno, J., “A public fabric database for defect detection methods and results”, Autex Research Journal Vol. 19, No.4, Pages 363-374, 2019.
• 39. Tosun, D., “Hazır giyim sektöründe benzetim tekniği kullanılarak üretim hattının dengelenmesi”, Yüksek Lisans Tezi, Pamukkale Üniversitesi Fen Bilimleri Enstitüsü, Denizli, 2020.
• 40. Amor, N., Noman M. T., Petru, M., “Classification of textile polymer composites: recent trends and challenges”, Polymers, Vol. 13 Issue 16, Pages 2592, 2021.
• 41. Liu, L., Su, J., Zhao, B., Wang, Q., Chen, J., Luo, Y., “Towards an efficient privacy-preserving decision tree evaluation service on the internet of things”, Symmetry, Vol. 12, Issue 103. 2020.
• 42. Song, Y.Y., Lu, Y., “Decision tree methods: Applications for classification and prediction”, Shanghai Arch. Psychiatry, Pages 130–135, 2015.
• 43. Mccallum, A., Nigam, K. A., “Comparison of event models for naive bayes text classification”, In AAAI-98 Workshop on Learning for Text Categorization, Madison, Wisconsin, Pages 41–48., 1998.
• 44. Siddiqui, M.F., Mujtaba, G., Reza, A.W., Shuib, L., “Multi-class disease classification in brain MRIs using computer-aided diagnostic system”, Symmetry, Vol. 9, Issue 37, 2017.
• 45. Aggarwal, C., “Data Classification: Algorithms and Applications”, CRC Press: Boca Raton, FL, USA, 2014.
• 46. Son, J., Jung, I., Park, K., Han, B., “Tracking-by segmentation with online gradient boosting decision tree”, In Proceedings of the IEEE International Conference on Computer Vision, Washington, DC, WA, 2015.
• 47. Merdin. D., Ersöz, F., “Evaluation of the applicability of industry 4.0 processes in businesses and supply chain applications”, 3rd International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT), Pages 1-10, 2019.
• 48. Aksoy, B., Uğuz, S., Oral, O., “Comparison of the data matching performances of string similarity algorithms in big data”, Mühendislik Bilimleri ve Tasarım Dergisi, Vol. 7, Sep. No. 3, 608–618, 2019.
• 49. Ersoz, F., Merdin, D., Ersoz, T., “Research of industry 4.0 awareness: A case study of Turkey”, Economics and Business, ISSN: 1407-7337, Vol: 32, Issue: 1, 247-263, 2018.
• 50. Yalçınkaya, S., Kılıçarslan, Y., Ersöz, F. ve diğerleri, “Sanayi 4.0 Teknolojik Alanları ve Uygulamaları”, Pegem Yayınevi, 2019.
• 51. Ersoz, F., Ersoz, T., Artuc, B., “A general overview on industry 4.0 and society 5.0: A case study of awareness of industry 4.0”, Journal of Turkish Operations Management, JTOM, Special issue, Pages 120-130, 2018.