Show simple item record

dc.contributor.author陈孝敬
dc.contributor.author吴迪
dc.contributor.author虞佳佳
dc.contributor.author何勇
dc.contributor.author刘守
dc.date.accessioned2017-11-14T03:09:15Z
dc.date.available2017-11-14T03:09:15Z
dc.date.issued2008-11-15
dc.identifier.citation光学学报,2008,(11):119-124
dc.identifier.issn0253-2239
dc.identifier.otherGXXB200811022
dc.identifier.urihttps://dspace.xmu.edu.cn/handle/2288/155910
dc.description.abstract提出了一种基于模拟退火(SA)算法和最小二乘法支持向量机(LS-SVM)选择可见-近红外光谱特征波长的新方法(SA-LS-SVM)。该方法用LS-SVM作为识别器,用识别率作为SA的目标函数,提取合适的特征波长数以及对应的特征波长。3种不同品牌的润滑油可见-近红外光谱的特征波长分别用SA-LS-SVM,主成分回归分析(PCA)和偏最小二乘法(PLS)进行处理,提取特征波长或主成分,然后结合反向传播人工神经网络(BP-ANN)对各种处理方法进行识别预测。结果发现,SA-LS-SVM只需从751个数据光谱中提取4个特征波长,就可以使三种品牌润滑油的识别率达到了100%,而其他所有的方法发现预测率都达不到100%,由此验证了SA-LS-SVM的优越性。实验结果表明,SA-LS-SVM不仅能有效地减少建模的变量数,而且可以提高预测精度。
dc.description.abstractA new method based on simulated annealing algorithm(SA) and least-squares support vector machine(LS-SVM)(SA-LS-SVM) was proposed to select the characteristic wavelength for visible-near infrared(Vis/NIR) spectroscopy discrimination.In order to find suitable numbers of characteristic wavelength and corresponding characteristic wavelength,discriminating rate was used as object function for SA,and LS-SVM was adopted as discrimination model.The Vis/NIR spectroscopy characteristic wavelengths of three categories of lubricant were processed by SA-LS-SVM,principal component analysis(PCA) and partial least squares(PLS) respectively,and then predicted by back-propagation artificial neural network(BP-ANN).The results of experiment showed that discriminating rate by using combination of SA-LS-SVM with BP-ANN reaches 100% only using 4 characteristic wavelengths from total of 751 wavelengths,while discriminating rate did not reach 100% by other methods.The proposed algorithm not only reduced the number of spectral variables,but also improved the discriminating rate.
dc.description.sponsorship国家自然科学基金项目(30671213);; 教育部高等学校优秀青年教师教学科研奖励计划(02411)资助课题
dc.language.isozh_CN
dc.subject可见-近红外光谱分析
dc.subject识别模型
dc.subject模拟退火算法
dc.subject最小二乘法支持向量机
dc.subjectvisible/near infrared spectroscopy
dc.subjectdiscrimination model
dc.subjectsimulated annealing algorithm(SA)
dc.subjectleast squares-support vector machine(LS-SVM)
dc.title一种用于可见-近红外光谱特征波长选择的新方法
dc.title.alternativeA New Choice Method of Characteristic Wavelength of Visible/Near Infrared Spectroscopy
dc.typeArticle


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record