A new near-infrared spectroscopy informative interval selection method

XU Long; LU Jiangang; YANG Qinmin; CHEN Jinshui; SHI Yingzi

doi:10.3969/j.issn.0438-1157.2013.12.021

您当前的位置：

首页 >

文章列表页 >

A new near-infrared spectroscopy informative interval selection method

更新时间：2025-12-10

- A new near-infrared spectroscopy informative interval selection method
- CIESC Journal Issue 12, Pages: 4410-4415(2013)
- 作者机构：
  
  1. 浙江大学控制科学与工程学系, 工业控制技术国家重点实验室,浙江,杭州,310027
  2. 杭州师范大学教育学院,浙江,杭州,311121
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.0438-1157.2013.12.021
  CLC： 657.33
- Online First：05 December 2013，
  
  Published：05 December 2013
- 稿件说明：
移动端阅览
XU Long, LU Jiangang, YANG Qinmin, et al. A new near-infrared spectroscopy informative interval selection method[J]. CIESC Journal, 2013, (12): 4410-4415.
DOI：

XU Long, LU Jiangang, YANG Qinmin, et al. A new near-infrared spectroscopy informative interval selection method[J]. CIESC Journal, 2013, (12): 4410-4415. DOI： 10.3969/j.issn.0438-1157.2013.12.021.

摘要

基于间隔策略的信息波长选择是近红外光谱分析中广泛应用的一种方法。针对传统算法忽略非线性因素的缺点，首次考虑将最小二乘支持向量机（least-squares support vector machine，LSSVM）方法应用于间隔选择策略，进而提出了一种新的波长选择方法iLSSVM（interval LSSVM）。该算法克服了传统间隔选择算法依赖于线性模型的缺陷，对存在较强非线性的光谱数据能够准确地选择最优信息区间，极大地减少建模变量并显著改善模型预测精度。应用两组业界标准的光谱数据来验证该算法的性能，并和传统方法进行了比较。实验结果表明，在两组数据集上该算法取得的标准预测偏差（root mean square error of prediction，RMSEP）分别比全谱PLS建模降低了20%和4%，比传统的间隔偏最小二乘算法（interval partial least-squares，iPLS）降低了28%和2%。

Abstract

Strategy based on interval selection is widely used in the near-infrared spectroscopy analysis. Inspired by interval partial least-squares method (iPLS)

the present paper proposed a new wavelength method combining interval selection strategy with least-squares support vector machine (LSSVM).By overcoming the shortcomings of traditional interval selection methods whose predictive ability totally depend on the linear model

this new algorithm

named as iLSSVM (interval LSSVM)

can select the optimal informative interval more reasonably to significantly improve the model prediction accuracy with less modeling variables.Two real near-infrared datasets were applied to this new approach and the prediction performance was compared to the other interval selection methods.The experimental results demonstrated that the root mean square error of prediction (RMSEP) of this new method is 20% and 4% smaller than that of full-spectrum PLS modeling method respectively

and is 28% and 2% smaller than that of the traditional iPLS (interval partial least-squares) method respectively.

关键词

Keywords

references

Views

715

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Near-infrared spectroscopy online detecting for 2,6-dimethylphenol purity based on transfer learning

Research on the measurement subset selection for global self-optimizing control strategy

Adaptive soft sensor method and application in determination of dynamic fluid levels

LSSVM modeling for fermentation process based on dividing stages

Melt index prediction of propylene polymerization based on LSSVM using swarm intelligence optimization

Related Author

WU Yunfei

LUAN Xiaoli

LIU Fei

LI Xiaochen

SU Hongye

XIE Lei

WANG Yiqin

WANG Tong

Related Institution

Key Laboratory of Advanced Process Control for Light Industry of the Ministry of Education, Institute of Automation, Jiangnan University

Institute of Cyber-Systems and Control, Zhejiang University

School of Information Science & Engineering, Northeastern University

School of Electrical Engineering, Shenyang University of Technology

School of Electronic Information and Electrical Engineering, Dalian University of Technology

⁰