Affiliation:
1. Guangzhou Fibre Product Testing and Research Institute
2. Central South University
Abstract
The analytical method was established for identification of 100% cotton fabric by Raman spectroscopy. 100 samples were analyzed directly by Raman spectrometer with a 1064nm laser source. 1120-1180 cm-1,1320-1400cm-1 and 1560-1600cm-1 were selected as important spectral regions by Random forest method. A Random forest model was established with 65 trees and 80 training samples. The result showed that different kind of textile can be identified by Raman spectroscopy coupled with random forest method.
Publisher
Trans Tech Publications, Ltd.
Reference7 articles.
1. E Cleve, E Bach, E Schollmeyer. Using chemometric methods and NIR spectrophotometry in the textile industry. Analytica Chimica Acta, 2000, 420(2): 163-167.
2. JM Cardamone, JM Gould, SH Gordon. Characterizing aged textile fibers by fourier transform infrared photoacoustic spectroscopy part 1: comparison of artificial and natural ageing in cotton. Textile Research Journal, 1987, 57(4): 235-239.
3. T. Næs, T. Isaksson, T. Fearn, and T. Davies, A user-friendly guide to multivatiate calibration and classification[M]. NIR Publications, Chichester, U.K., (2002).
4. Jian-Hua Huang, Rui-Hua He, Lun-Zhao Yi, etc. Exploring the relationship between 5'AMP-activated protein kinase and markers related to type 2 diabetes mellitus[J]. Talanta, 2013, 110: 1-7.
5. Fang-fang Ai, Jun Bin, Zhi-min Zhang, etc. Application of random forests to select premium quality vegetable oils by their fatty acid composition[J]. Food Chemistry, 2014, 143: 472-478.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献