基于主成分分析和支持向量机的山羊绒原料品种鉴别分析  

Identification of Varieties of Cashmere by Vis/NIR Spectroscopy Technology Based on PCA-SVM

作　　者：吴桂芳[1,2] 何勇[1] 

机构地区：[1]浙江大学生物系统工程与食品科学学院,浙江杭州310029 [2]内蒙古农业大学机电工程学院,内蒙古呼和浩特010018

出　　处：《光谱学与光谱分析》2009年第6期1541-1544,共4页Spectroscopy and Spectral Analysis

基　　金：国家“十一五”科技支撑项目(2006BAD10A04);高等学校优秀青年教师教学科研奖励计划项目(02411)资助

摘　　要：提出了一种用近红外光谱技术快速无损鉴别羊绒原料品种的新方法。山羊绒的外观形态和品质特征随着山羊绒原料的品种不同有很大的区别,快速、有效、正确地鉴别山羊绒纤维,对山羊绒及其制品的生产与交易具有重要的意义。应用可见/近红外光谱漫反射技术测定各种山羊绒原料的光谱曲线,用主成分分析法对不同品种山羊绒原料进行聚类分析并获取山羊绒原料的近红外指纹图谱,再结合支持向量机技术进行品种鉴别。用主成分1,2和3对所有建模样本的得分值做出的得分图,分析聚类效果,将主成分分析得到的10个主成分作为支持向量机的输入,应用数据挖掘新方法—支持向量机对山羊绒原料品种进行鉴别。通过对5个山羊绒原料品种共100个样本的训练,对未知的75个样本进行鉴别,建立了山羊绒原料品种鉴别的支持向量机的分类模型,并对比了四种核函数的支持向量机的分类性能,结果表明,具有高斯核函数的支持向量机对山羊绒原料的鉴别准确率达到100%。说明文章提出主成分分析结合支持向量机的数据挖掘方法具有很好的分类和鉴别作用,为山羊绒原料的品种快速鉴别提供了一种新方法。One mixed algorithm was presented to discriminate cashmere varieties with principal component analysis （PCA） and support vector machine （SVM）. Cashmere fiber has such characteristics as threadlike, softness, glossiness and high tensile strength. The quality characters and economic value of each breed of cashmere are very different. In order to safeguard the consumer＇s rights and guarantee the quality of cashmere product, quickly, efficiently and correctly identifying cashmere has significant meaning to the production and transaction of cashmere material. The present research adopts Vis/NIRS spectroscopy diffuse techniques to collect the spectral data of cashmere. The near infrared fingerprint of cashmere was acquired by principal component analysis （PCA）, and support vector machine （SVM） methods were used to further identify the cashmere material. The result of PCA indicated that the score map made by the scores of PC1, PC2 and PC3 was used, and 10 principal components （PCs） were selected as the input of support vector machine （SVM） based on the reliabilities of PCs of 99. 99%. One hundred cashmere samples were used for calibration and the remaining 75 cashmere samples were used for validation. A one-against-all multi-class SVM model was built, the capabilities of SVM with different kernel function were comparatively analyzed, and the result showed that SVM possessing with the Gaussian kernel function has the best identification capabilities with the accuracy of 100%. This research indicated that the data mining method of PCA-SVM has a good identification effect, and can work as a new method for rapid identification of cashmere material varieties.

关 键 词：可见-近红外光谱 山羊绒原料 主成分分析 支持向量机 

分 类 号：TS101.9[轻工技术与工程—纺织工程]