Akademska digitalna zbirka SLovenije - logo
ALL libraries (COBIB.SI union bibliographic/catalogue database)
  • Engineered cotton fibre selection - machine learning vs. neural networks [Elektronski vir]
    Golob, Darko, 1956- ; Stjepanović, Zoran
    We can influence the mechanical properties and regularity of yarn, as well as significantly reduce the number of yarn faults by using the appropriate raw material and suitable fibre blend proportion. ... The article presents a study of the influence of quality characteristics of cotton fibres and structural parameters of a yarn on its important properties such as yarn tenacity. Two different methods have been used: machine learning of regression trees and neural networks. The results achieved have been used for the determination of optimized cotton fibre blends regarding the quality and cost of a cotton yarn.
    Type of material - conference contribution ; adult, serious
    Publish date - 2009
    Language - english
    COBISS.SI-ID - 13236502