首页 | 官方网站   微博 | 高级检索  
     

近红外光谱技术结合支持向量回归法测定非法对硫磷的含量
引用本文:吴厚斌,于荣,刘苹苹,穆兰,刘丰茂,张延秋,江树人,闵顺耕.近红外光谱技术结合支持向量回归法测定非法对硫磷的含量[J].农药,2012,51(4):270-272.
作者姓名:吴厚斌  于荣  刘苹苹  穆兰  刘丰茂  张延秋  江树人  闵顺耕
作者单位:1. 中国农业大学理学院,北京100193;农业部农药检定所,北京100125
2. 农业部农药检定所,北京,100125
3. 中国农业大学理学院,北京,100193
基金项目:国家自然科学基金资助项目
摘    要:目的]采用近红外光谱(NIR)技术结合支持向量回归法(SVR)建立乳油中非法对硫磷的定量分析方法.方法]通过向1.8%阿维菌素乳油中加入对硫磷原药和二甲苯溶剂来配制不同质量分数的校正集,采用SVR法建立非法对硫磷的定量分析模型.结果]模型的决定系数(R2)、校正集均方根误差(RMSEC)、检验集均方根误差(RMSEV)、预测集均方根误差(RMSEP)分别为0.9994、0.4377、0.5065、0.7482.结论]该法可以定量测定乳油中非法对硫磷的含量.

关 键 词:近红外光谱  支持向量回归  对硫磷  定量  分析

Determination of the Content of Illegal Parathion by Near-infrared Spectroscopy Combined with Support Vector Regression
WU Hou-bin , YU Rong , LIU Ping-ping , MU Lan , LIU Feng-mao , ZHANG Yan-qiu , JIANG Shu-ren , MIN Shun-geng.Determination of the Content of Illegal Parathion by Near-infrared Spectroscopy Combined with Support Vector Regression[J].Pesticides,2012,51(4):270-272.
Authors:WU Hou-bin  YU Rong  LIU Ping-ping  MU Lan  LIU Feng-mao  ZHANG Yan-qiu  JIANG Shu-ren  MIN Shun-geng
Affiliation:1(1.College of Science,China Agriculture University,Beijing 100193,China; 2.Institute for the Control of Agrochemicals,Ministry of Agriculture,Beijing 100125,China)
Abstract:Aims] The method of determination of the content of illegal parathion in EC was established by near-infrared spectroscopy(NIR),combined with support vector regression(SVR).Methods] The calibration set was composed of samples with different content of parathion by adding parathion TC and xylene to abamectin 1.8% EC.the model for the content of the illegal parathion was established by SVR.Results] The determination coefficient(R2),root mean squared error of calibration(RMSEC),root mean squared error of validation(RMSEV),and root mean squared error of prediction(RMSEP) for the model were 0.9994,0.4377,0.5065 and 0.7482 respectively.Conclusions] The results showed the method could be used to analyze the content of illegal parathion in EC quantitatively.
Keywords:NIR  SVR  parathion  quantitative  analysis
本文献已被 CNKI 万方数据 等数据库收录!
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-23

京公网安备 11010802026262号