Textile is an area where products are tested at almost every step from raw material to the final product. With the increasing world population, continuous research and analyses are conducted in the textile sector to produce new products. These analyses create a large data source. For this purpose, a dataset has been created using data from a towel company located in the Demirtaş Organized Industrial Zone. Test results such as tensile strength, hydrophilicity, and air permeability applied to towel fabrics were used in the dataset. Machine learning regression models, suitable for the created dataset have been presented. According to the estimation results, the SVM model performed best R2 score in tensile strength and air permeability results, while Random Forest performed best in hydrophilicity results. The findings suggest that tensile strength, hydrophilicity, and air permeability values can be predicted by machine learning models.
Tekstil, hammaddeden başlayıp son ürün elde edilene kadar hemen hemen her adımda çıkan ürüne test yapılan bir alandır. Artan dünya nüfusu ile birlikte tekstil sektöründe yeni ürünler üretmek için sürekli araştırma ve analiler yapılmaktadır. Yapılan bu analizlerde büyük bir veri kaynağı oluşturmaktadır. Bu amaç doğrultusunda da Demirtaş Organize Sanayi Bölgesi’nde yer alan bir havlu firmasından alınan veriler kullanılarak bir veri seti oluşturulmuştur. Veri setinde havlu kumaşlara uygulanan testlerden olan kopma mukavemeti, hidrofilite ve hava geçirgenliği test sonuçları kullanılmıştır. Oluşturulan veri setine uygun makine öğrenmesi regresyon modelleri sunulmuştur. Elde edilen tahmin analiz sonuçlarına göre kopma mukavemeti ve hava geçirgenliği sonuçlarında SVM modeli, hidrofilite sonuçlarında Random Forest en iyi R2 skor performansı göstermiştir. Bulgular kopma mukavemeti, hidrofilite ve hava geçirgenliği değerlerinin makine öğrenmesi modelleri ile tahmin edilebileceğini sunmaktadır.
| Primary Language | Turkish |
|---|---|
| Subjects | Wearable Materials, Textile Sciences and Engineering (Other) |
| Journal Section | Research Article |
| Authors | |
| Submission Date | April 26, 2024 |
| Acceptance Date | October 15, 2024 |
| Early Pub Date | December 18, 2024 |
| Publication Date | December 24, 2024 |
| DOI | https://doi.org/10.17482/uumfd.1473975 |
| IZ | https://izlik.org/JA56FM23AG |
| Published in Issue | Year 2024 Volume: 29 Issue: 3 |
Announcements:
30.03.2021-Beginning with our April 2021 (26/1) issue, in accordance with the new criteria of TR-Dizin, the Declaration of Conflict of Interest and the Declaration of Author Contribution forms fulfilled and signed by all authors are required as well as the Copyright form during the initial submission of the manuscript. Furthermore two new sections, i.e. ‘Conflict of Interest’ and ‘Author Contribution’, should be added to the manuscript. Links of those forms that should be submitted with the initial manuscript can be found in our 'Author Guidelines' and 'Submission Procedure' pages. The manuscript template is also updated. For articles reviewed and accepted for publication in our 2021 and ongoing issues and for articles currently under review process, those forms should also be fulfilled, signed and uploaded to the system by authors.