
第21卷第10期 2013年10月
1004-924X(2013)10-2513-07
文章编号
光学精密工程
Optics and Precision Engineering
同步荧光光谱结合CARS变量优选
预测猪肉中四环素残留含量肖海斌,赵进辉,袁海超,洪茜,刘木华*
(江西农业大学工学院/生物光电及应用重点实验室,江西南昌330045)
Vol. 21No.10
Oct.2013
摘要:为快速检测猪肉中的四环索残留含量,采用同步荧光法结合竞争适应重加权采样(CARS)变量优选法建立了预测猪肉中四环素残留含量的支持向量回归(SVR)模型。从样本的三维同步荧光光谱申确定了最佳波长差为65nm.采用 CARS方法从中挑选出与四环索相关的待征波长变量,并与连续投影算法(SPA)及遗传算法(GA)进行比较。最后,应用SVR算法对优选出的16个波长变量建立猪肉中四环素含量的预测模型。分析发现,多元散射校正(MSC)光谱预处理后的CARS方法优于SPA及GA变量选择方法,可以有效地筛选出全光谱中的特征波长变量。CARS-SVR建立的四环素预测模型优于原始光谱的SVR模型,其预测集的决定系数(R*)和预测均方根误差(RMSEP)分别为0.9612和 10.94mg/kg。研究结果表明,采用同步荧光法结合CARS-SVR模型可以预测猪肉中的四环索残留含量,且CARS-SVR 能有效地简化模型并提高预测精度。
关键词调:同步荧光光谱;竞争适应重加权采样(CARS);支持向量回归;四环素;猪肉
中图分类号:(0657.31
文献标识码:A
doi;10.3788/OPE.20132110.2513
Determination of tetracycline content inpork by synchronous
fluorescencespectroscopywithCARSmethod
XIAOHai-bin,ZHAO Jin-hui,YUAN Hai-chao,HONGQian,LIU Mu-hua(Optics-electricsApplicationofBiomaterialLaboratory,CollegeofEngineering
Jiang.riAgriculturalUniversity,Nanchang330045,China
*Correspondingauthor,E-mail:suikelmh@sohu.com
Abstract: The Support Vector Regression (SVR) prediction model was established for the rapid detec tion of tetracycline contents in pork by the synchronous fluorescence spectroscopy combined with Competitive Adaptive Reweighted Sampling (CARS) method. The CARS was used to select tetracy cline correlative variables of pork samples from spectral data and the optimum wavelength difference was set to be 65 nm. Then, the performance of three variable selection methods including CARS, Successive Project Algorithm (SPA) and Genetic Algorithm (GA) were compared. Finally, the SVR was used to establish the prediction model for tetracycline contents of the pork by using 16 selected variables, The results show that CARS after Multi Scattering Correction(MSC) processing is superior
收稿日期:2013-03-13;修订日期:2013-04-25.
基金项目:国家科技支撑计划资助项目(No.2012BAK17B02);国家自然科学基金资助项目(No.31101295);江西容
科技厅对外科技合作计划资助项目(No.20132BDH80005);国家863高技术研究发展计划资助项目(No 2008AA10Z209);江西省科技厅科技支撑计划资助项目(No.2012BBG70058);江西省教育厅科技计划资助项目(NoGJ12244)