首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于连续投影算法的小麦湿面筋近红外校正模型优化
引用本文:钱海波,孙来军,王乐凯,徐璐璐,戴常军.基于连续投影算法的小麦湿面筋近红外校正模型优化[J].中国农学通报,2011,27(18):51-56.
作者姓名:钱海波  孙来军  王乐凯  徐璐璐  戴常军
作者单位:1. 黑龙江省电子工程省高校重点实验室/黑龙江大学,哈尔滨,150080
2. 农业部谷物及制品质量监督检验测试中心,哈尔滨,150086
基金项目:小麦现代农业产业技术体系建设专项基金资助项目(nycytx-03)
摘    要:为减少建模过程中的计算量、提高模型的稳健性及预测精度,将连续投影算法用于小麦湿面筋近红外校正模型的建立。首先采用SPXY算法选择具有代表性的校正集样本,然后对光谱数据作不同预处理,增强光谱特征;运用连续投影算法对原始光谱和预处理后的光谱进行敏感波点提取,进而分别建立多元线性回归校正模型。测试结果表明,对光谱标准正态变量变换后利用连续投影算法提取敏感波点所建多元线性回归模型预测效果最好,预测均方根误差和预测相关系数分别为1.3332和0.94319,优于同等条件下建立的偏最小二乘回归模型。

关 键 词:土壤  土壤  pH  石灰  有效养分  甘蔗  
收稿时间:2011/2/21 0:00:00
修稿时间:2011/3/18 0:00:00

Near Infrared Spectroscopy Calibration Model Optimizing of Wet Gluten Based on Successive Projections Algorithm
Qian Haibo,Sun Laijun,Wang Lekai,Xu Lulu,Dai Changjun.Near Infrared Spectroscopy Calibration Model Optimizing of Wet Gluten Based on Successive Projections Algorithm[J].Chinese Agricultural Science Bulletin,2011,27(18):51-56.
Authors:Qian Haibo  Sun Laijun  Wang Lekai  Xu Lulu  Dai Changjun
Institution:Qian Haibo 1,Sun Laijun 1,Wang Lekai 2,Xu Lulu 1,Dai Changjun 2 (1 Key Laboratory of Electronics Engineering,College of Heilongjiang Province/Heilongjiang University,Harbin 150080,2 Inspection and Testing Center for Quality of Cereals and Their Products,Ministry of Agriculture,Harbin 150086)
Abstract:In order to reduce computational complexity of modeling and improve the model's robustness and prediction accuracy,successive projections algorithm (SPA) was used in the near infrared spectrum calibration modeling of wheat gluten.Firstly,a representative set of correction samples were selected by SPXY algorithm.Secondly,the spectral data was pretreated with several different methods to enhance spectral features.Thirdly,making use of SPA to extract sensitive wave points of the original spectrum and the spect...
Keywords:wheat  wet gluten  near infrared spectroscopy  successive projections algorithm  wavelength selection  
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《中国农学通报》浏览原始摘要信息
点击此处可从《中国农学通报》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号