武汉工程大学学报2017，Vol.39Issue(5)：496-502,7.DOI:10.3969/j.issn.1674-2869.2017.05.001
近红外光谱无损检测技术中数据的分析方法概述
Overview of Data Analysis Methods in Near-Infrared Spectroscopy Nondestructive Testing
摘要
Abstract
Near-infrared spectroscopy nondestructive testing technology can be used for variety identification and the qualitative or quantitative analysis of agricultural products. The basic principle of near-infrared spectroscopy and the methods of near-infrared spectrum analysis were introduced. The data analysis methods in near-infrared nondestructive testing technology aim at finding the relationship between the spectrum and the corresponding concentration through the quantitative analysis of the spectrum, and establishing the corresponding mathematical model,which mainly include partial least squares regression,principal component analysis,back propagation artificial neural network,support vector machine(SVM),K-Nearest neighbor classification algorithm and linear discriminant analysis. The comparison result of these analytical models show that SVM method may be a future research direction in near infrared spectrum data analysis.关键词
近红外光谱/无损检测/数据分析方法Key words
near-infrared spectroscopy/nondestructive testing/data analysis methods分类
医药卫生引用本文复制引用
刘军,吴梦婷,谭正林,李威..近红外光谱无损检测技术中数据的分析方法概述[J].武汉工程大学学报,2017,39(5):496-502,7.基金项目
湖北省食品药品监督管理局项目(201610+13) （201610+13）
湖北省智能机器人重点实验室开放基金( HBIR 201608) （ HBIR 201608）
武汉工程大学研究生创新基金(CX2016063) （CX2016063）
