可见/近红外光谱结合变量选择方法检测牛肉挥发性盐基氮  

Detection of beef TVB-N by visible and near-infrared spectroscopy combined with variable selection method

作　　者：马世榜[1,2] 彭彦昆[1] 徐杨[1] 汤修映[1] 田潇瑜[1] 

机构地区：[1]中国农业大学工学院,北京100083 [2]南阳理工学院,河南南阳473004

出　　处：《江苏大学学报（自然科学版）》2013年第1期44-48,共5页Journal of Jiangsu University：Natural Science Edition

基　　金：公益性行业(农业)科研专项经费资助项目(201003008)

摘　　要：为实现生鲜牛肉整个储存期内(4℃环境)挥发性盐基氮(TVB-N)的快速无损检测,提高检测精度,搭建了可见/近红外光谱(VIS/NIR)检测系统,采集储藏在4℃下1～17 d生鲜牛肉400～1 700 nm波段范围的反射光谱.对比多元散射校正(MSC)、Savitzky-Golay(SG)平滑、一阶导数(FD)预处理方法,结合无信息变量消除(UVE)和连续投影算法(SPA)提取有效光谱变量,建立TVB-N的最佳LS-SVM预测模型.结果表明:SG为最佳预处理方法,UVE和SPA方法使LS-SVM建模变量减少了99.5%,预测相关系数和标准差分别为0.925,4.615 mg.(100 g)-1.To realize rapid and non-destructive detection of total volatile basic nitrogen（TVB-N） content of flesh beef with improved detection accuracy throughout the storage period at 4 ℃ , a laboratory visible and near-infrared spectroscopy system was established to collect beef samples reflectance spectra between 400 and 1 700 nm. The beef samples were stored at 4 ℃ for 1 to 17 days. Multiplication scatter correction （MSC）, first derivative （FD）, Szvitzky-Golay （SG） smoothing method were used as pretreatment method for raw sample spectra. Combined with the effective wavelength variables extracted by uninformative variable elimination （UVE） and successive projections algorithm （SPA）, the least square-support vector machine（LS-SVM） was proposed to predict beef TVB-N content. The results show that the SG is the best pretreatment method with reduced input variables by 99.5% for UVE and SPA, and the proposed LS-SVM has good performance with Rv of 0. 925 and S of 4. 615 mg ~ （100 g） ^-1 ,respectively.

关 键 词：牛肉 可见 近红外光谱 变量选择 挥发性盐基氮 最小二乘支持向量机 

分 类 号：S123[农业科学—农业基础科学] O433.5[机械工程—光学工程]