Natural Dyeing of Bio-Mordanted Cellulosic Okra Fiber and Machine Learning–Based Prediction of Dyeing Characteristics
Journal of Natural Fibers, cilt.23, sa.1, 2026 (SCI-Expanded, Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 23 Sayı: 1
- Basım Tarihi: 2026
- Doi Numarası: 10.1080/15440478.2026.2687604
- Dergi Adı: Journal of Natural Fibers
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, CAB Abstracts, Compendex, Environment Index, INSPEC, Directory of Open Access Journals, Academic Search Ultimate (EBSCO), Engineering Source (EBSCO)
- Anahtar Kelimeler: bio-mordant, Cellulosic fiber, machine learning, natural dye, okra
- Açık Arşiv Koleksiyonu: AVESİS Açık Erişim Koleksiyonu
- İstanbul Ticaret Üniversitesi Adresli: Evet
Özet
In this research, okra fiber was extracted from okra plants by the biological degradation method. Cellulosic okra fibers were treated with sodium carbonate, and then the samples were dyed with natural dye obtained from madder with different concentrations via simultaneous mordanted method using different bio-mordants extracted from eucalyptus seeds, laurel seeds, bitter melon, Agave Americana, and spurge with different concentrations. Consequently, spectrophotometric characteristics, washing, and rubbing fastness of dyed samples were investigated in terms of using bio-mordant, bio-mordant type, and dye concentration. The results indicated that color strength, washing, and rubbing fastness of dyed samples increase with the bio-mordanting process. Color strength of samples improves with an increase in bio-mordant and dye concentration. Furthermore, color coordinates differ from the bio-mordant type, bio-mordant concentration, and dye concentration. In this paper, a new model based on different machine learning techniques was proposed for the prediction of L*, a*, b*, K/S, color change, dry rubbing fastness, and wet rubbing fastness dyeing characteristics of okra fiber. Root mean squared error (RMSE), mean absolute error (MAE), and multiple correlation coefficient (R) metrics were used to evaluate the success of the proposed model. The experimental results show that the model is successful and can be used to predict the dyeing characteristics of okra fibers.