Near-infrared spectroscopy identification method of cashmere and wool fibers based on an optimized wavelength selection algorithm

被引:1
作者
Zhu, Yaolin [1 ]
Chen, Long [1 ]
Chen, Xin [1 ]
Chen, Jinni [1 ]
Zhang, Hongsong [2 ]
机构
[1] Xian Polytech Univ, Sch Elect & Informat, Xian 710000, Peoples R China
[2] Shanghai Ranzi Ind Co Ltd, Shanghai 201800, Peoples R China
基金
中国国家自然科学基金;
关键词
Cashmere and wool; Near-infrared spectroscopy; Wavelengths selection; Grouping genetic algorithm; PLS-DA; BLENDS;
D O I
10.1016/j.heliyon.2024.e34537
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Cashmere and wool fibers have similar chemical compositions, making them difficult to distinguish based on their absorption peaks and band positions in near-infrared spectroscopy. Existing studies commonly use wavelength selection or feature extraction algorithms to obtain significant spectral features, but traditional algorithms often overlook the correlations between wavelengths, resulting in weak adaptability and local optimum issues. To address this problem, this paper proposes a recognition algorithm based on optimal wavelength selection, which can remove redundant information and make the model effective in capturing patterns and key features of the data. The wavelengths are rearranged by computing the information gain ratio for each wavelength. Then, the sorted wavelengths are grouped based on equal density, which ensures that all wavelengths within each group have equal information and avoids over-focusing on individual groups. Meanwhile, the group genetic algorithm is used to find the wavelengths with highly informative and search optimal grouped combinations, in order to explore the entire spectrum wavelength. Finally, combined with a partial least squares discriminant analysis(PLS-DA) model, the recognition accuracy reached 97.3 %. The results indicate that, compared to traditional methods such as CARS, SPA, and GA, our method effectively reduces redundant information, selects fewer but more informative wavelengths, and improves classification accuracy and model adaptability.
引用
收藏
页数:14
相关论文
共 37 条
[1]  
Andre J, 2000, ADV ENG SOFTW, V32, P49
[2]   Predicting Soil Organic Carbon Content Using Hyperspectral Remote Sensing in a Degraded Mountain Landscape in Lesotho [J].
Bangelesa, Freddy ;
Adam, Elhadi ;
Knight, Jasper ;
Dhau, Inos ;
Ramudzuli, Marubini ;
Mokotjomela, Thabiso M. .
APPLIED AND ENVIRONMENTAL SOIL SCIENCE, 2020, 2020
[3]   STANDARD NORMAL VARIATE TRANSFORMATION AND DE-TRENDING OF NEAR-INFRARED DIFFUSE REFLECTANCE SPECTRA [J].
BARNES, RJ ;
DHANOA, MS ;
LISTER, SJ .
APPLIED SPECTROSCOPY, 1989, 43 (05) :772-777
[4]  
Chen H., 2013, Int. Sch. Res. Notices, V2013
[5]   Classification of different animal fibers by near infrared spectroscopy and chemometric models [J].
Chen, Hui ;
Lin, Zan ;
Tan, Chao .
MICROCHEMICAL JOURNAL, 2019, 144 :489-494
[6]   Hyperspectral characteristics and quantitative analysis of leaf chlorophyll by reflectance spectroscopy based on a genetic algorithm in combination with partial least squares regression [J].
Chen, Xiaowan ;
Dong, Zhenyu ;
Liu, Jinbao ;
Wang, Huanyuan ;
Zhang, Yang ;
Chen, Tianqing ;
Du, Yichun ;
Shao, Li ;
Xie, Jiancang .
SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY, 2020, 243
[7]  
Chu X. L., 2022, Chemometric methods in modern spectral analysis., V1st
[8]  
Droz JM, 2018, Arxiv, DOI arXiv:1807.10046
[9]  
Franck R.R., 2001, Silk, mohair, cashmere and other luxury fibres
[10]  
Guo F, 2011, LECT NOTES ARTIF INT, V7004, P362, DOI 10.1007/978-3-642-23896-3_44