Check out RSS, or use RSS reader to subscribe this item
Confirmation
Authentication email has already been sent, please check your email box: and activate it as soon as possible.
You can login to My Profile and manage your email alerts.
Sponsored by the Center for Science and Technology Development of the Ministry of Education
Supervised by Ministry of Education of the People's Republic of China
Quantification of Nitrogen Status in Oilseed Rape by Least-Squares Support Vector Machines and Reflectance Spectroscopy
He Yong * #,Cen Haiyan ,Bao Yidan ,Huang Min
Zhejiang University
*Correspondence author
#Submitted by
Subject:
Funding:
教育部博士点基金(No.20040335034 )
Opened online:14 December 2007
Accepted by:
none
Citation: He Yong,Cen Haiyan ,Bao Yidan .Quantification of Nitrogen Status in Oilseed Rape by Least-Squares Support Vector Machines and Reflectance Spectroscopy[OL]. [14 December 2007] http://en.paper.edu.cn/en_releasepaper/content/16936
The estimation of nitrogen status non-destructively in oilseed rape in a crop-growing period was performed using reflectance spectroscopy with least-squares support vector (LS-SVM). This study was conducted at the experiment farm of Zhejiang University, Hangzhou, China. The SPAD value was used as a reference data that reflects nitrogen status in oilseed rape. A total of 159 oilseed rape leaf samples were used for visible and near infrared reflectance spectroscopy at 325-1075 nm using a field spectroradiometer. The reflectance data processed by median filter was applied for LS-SVM regression model to predict SPAD values. The performance of LS-SVM with RBF kernel function and five input variables derived from scores of partial least squares (PLS) latent variables (LVs) was investigated. To serve this purpose, the grid-search technique using 5-fold cross-validation was used to find out the optimal values of two important parameters in LS-SVM regression model. At the same time, LS-SVM model was compared with PLS and back propagation neural network (BPNN) methods. The results showed that LS-SVM was superior to the conventional linear and non-linear methods in predicting SPAD values of oilseed rape leaves. It is concluded that LS-SVM regression method is a promising technique for chemometrics in the field of quantitative prediction.
Keywords:oilseed rape; nitrogen; least-squares support vector; partial least squares