近红外木质素模型转移：基于 SWCSS-CARS 耦合算法的研究

IF 1.3 4区农林科学 Q2 MATERIALS SCIENCE, PAPER & WOOD

Bioresources Pub Date : 2023-11-14 DOI:10.15376/biores.19.1.245-256

Zhijian Liu, Honghong Wang, Zhi-xin Xiong, Yunchao Hu, Haoran Huang, Ying Wang, Xianzhi Wu, Long Liang

{"title":"近红外木质素模型转移：基于 SWCSS-CARS 耦合算法的研究","authors":"Zhijian Liu, Honghong Wang, Zhi-xin Xiong, Yunchao Hu, Haoran Huang, Ying Wang, Xianzhi Wu, Long Liang","doi":"10.15376/biores.19.1.245-256","DOIUrl":null,"url":null,"abstract":"In NIR spectral modeling, the method of screening wavelengths with consistent stable signals (SWCSS) is based on a standard-free algorithm. However, the wavelengths selected by SWCSS may contain invalid information. In this paper, the Competitive Adaptive Reweighted Sampling (CARS) wavelength optimization algorithm was used in conjunction with SWCSS to eliminate the uninformative variables in the wavelengths selected by SWCSS. The SWCSS-CARS method was based on three near-infrared spectrometers (Lengguang 1, Lengguang 2, and Lengguang 3), with Lengguang 1 as the master and the other two instruments as the targets, using a total of 84 sample spectra of five types of pulpwood and their lignin contents as the research objects. Compared with the full spectrum, the number of wavelengths was reduced from 1601 to 24 in the model built using the coupling algorithm. For target 1, the value of RPD was improved from 1.9247 to 3.1880; for target 2, t the value of RPD was improved from 1.7415 to 3.2508. The wavelengths selected by the SWCSS-CARS coupling algorithm were able to build stable, robust models.","PeriodicalId":9172,"journal":{"name":"Bioresources","volume":"2 1","pages":""},"PeriodicalIF":1.3000,"publicationDate":"2023-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Near-infrared lignin model transfer: A study based on SWCSS-CARS coupling algorithm\",\"authors\":\"Zhijian Liu, Honghong Wang, Zhi-xin Xiong, Yunchao Hu, Haoran Huang, Ying Wang, Xianzhi Wu, Long Liang\",\"doi\":\"10.15376/biores.19.1.245-256\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In NIR spectral modeling, the method of screening wavelengths with consistent stable signals (SWCSS) is based on a standard-free algorithm. However, the wavelengths selected by SWCSS may contain invalid information. In this paper, the Competitive Adaptive Reweighted Sampling (CARS) wavelength optimization algorithm was used in conjunction with SWCSS to eliminate the uninformative variables in the wavelengths selected by SWCSS. The SWCSS-CARS method was based on three near-infrared spectrometers (Lengguang 1, Lengguang 2, and Lengguang 3), with Lengguang 1 as the master and the other two instruments as the targets, using a total of 84 sample spectra of five types of pulpwood and their lignin contents as the research objects. Compared with the full spectrum, the number of wavelengths was reduced from 1601 to 24 in the model built using the coupling algorithm. For target 1, the value of RPD was improved from 1.9247 to 3.1880; for target 2, t the value of RPD was improved from 1.7415 to 3.2508. The wavelengths selected by the SWCSS-CARS coupling algorithm were able to build stable, robust models.\",\"PeriodicalId\":9172,\"journal\":{\"name\":\"Bioresources\",\"volume\":\"2 1\",\"pages\":\"\"},\"PeriodicalIF\":1.3000,\"publicationDate\":\"2023-11-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Bioresources\",\"FirstCategoryId\":\"88\",\"ListUrlMain\":\"https://doi.org/10.15376/biores.19.1.245-256\",\"RegionNum\":4,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"MATERIALS SCIENCE, PAPER & WOOD\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Bioresources","FirstCategoryId":"88","ListUrlMain":"https://doi.org/10.15376/biores.19.1.245-256","RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MATERIALS SCIENCE, PAPER & WOOD","Score":null,"Total":0}

引用次数: 0

摘要

在近红外光谱建模中，筛选具有一致稳定信号的波长（SWCSS）的方法是基于一种无标准算法。然而，SWCSS 筛选出的波长可能包含无效信息。本文将竞争性自适应重加权采样（CARS）波长优化算法与 SWCSS 结合使用，以消除 SWCSS 所选波长中的无效变量。SWCSS-CARS 方法基于三台近红外光谱仪（冷光 1 号、冷光 2 号和冷光 3 号），以冷光 1 号为主，其他两台为辅，以五种纸浆木材及其木质素含量的共 84 个样品光谱为研究对象。与全光谱相比，在使用耦合算法建立的模型中，波长数从 1601 个减少到 24 个。目标 1 的 RPD 值从 1.9247 提高到 3.1880；目标 2 的 RPD 值从 1.7415 提高到 3.2508。SWCSS-CARS 耦合算法所选择的波长能够建立稳定、稳健的模型。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Near-infrared lignin model transfer: A study based on SWCSS-CARS coupling algorithm

In NIR spectral modeling, the method of screening wavelengths with consistent stable signals (SWCSS) is based on a standard-free algorithm. However, the wavelengths selected by SWCSS may contain invalid information. In this paper, the Competitive Adaptive Reweighted Sampling (CARS) wavelength optimization algorithm was used in conjunction with SWCSS to eliminate the uninformative variables in the wavelengths selected by SWCSS. The SWCSS-CARS method was based on three near-infrared spectrometers (Lengguang 1, Lengguang 2, and Lengguang 3), with Lengguang 1 as the master and the other two instruments as the targets, using a total of 84 sample spectra of five types of pulpwood and their lignin contents as the research objects. Compared with the full spectrum, the number of wavelengths was reduced from 1601 to 24 in the model built using the coupling algorithm. For target 1, the value of RPD was improved from 1.9247 to 3.1880; for target 2, t the value of RPD was improved from 1.7415 to 3.2508. The wavelengths selected by the SWCSS-CARS coupling algorithm were able to build stable, robust models.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Bioresources 工程技术-材料科学：纸与木材

CiteScore

2.90

自引率

13.30%

发文量

397

审稿时长

2.3 months

期刊介绍： The purpose of BioResources is to promote scientific discourse and to foster scientific developments related to sustainable manufacture involving lignocellulosic or woody biomass resources, including wood and agricultural residues. BioResources will focus on advances in science and technology. Emphasis will be placed on bioproducts, bioenergy, papermaking technology, wood products, new manufacturing materials, composite structures, and chemicals derived from lignocellulosic biomass.