Modeling color fading ozonation of reactive-dyed cotton using the Extreme Learning Machine, Support Vector Regression and Random Forest

Abstract

Textile products with faded effect achieved via ozonation are increasingly popular recently. In this study, the effect of ozonation in terms of pH, temperature, water pickup , time and applied colors on the color fading performance of reactive-dyed cotton are modeled using Extreme Learning Machine (ELM), Support Vector Regression (SVR) and Random Forest Regression (RF) respectively. It is found that RF and SVR perform better than ELM in this issue, but SVR is more recommended to be sued in the real application due to its balance predicting performance and less training time.