基于PLS-模式识别近红外光谱技术快速检测鲜乳和掺假乳

食品科学 ›› 2008, Vol. 29 ›› Issue (8): 492-495.

基于PLS-模式识别近红外光谱技术快速检测鲜乳和掺假乳

荣菡,刘波平, 邓泽元,罗香

南昌大学食品科学与技术国家重点实验室；江西省分析测试中心

出版日期:2008-08-15 发布日期:2011-08-26

Study on Rapid Determination of Raw Milk and Adulterated Milk Using Near Infrared Reflectance Spectroscopy Based on Partial Least Squares-Pattern Recognition Technique

RONG Han, LIU Bo-Ping, DENG Ze-Yuan, LUO Xiang

1.State Key Laboratory of Food Science and Technology,Nanchang University,Nanchang 330047,China;2. Analytical and Testing Center of Jiangxi Province,Nanchang 330029,China

Online:2008-08-15 Published:2011-08-26

摘要/Abstract

摘要： 本实验采用PLS-马氏距离法建立了鲜乳和掺假植物奶油牛乳的判别分析模型,用PLS法将原始数据压缩成3个主成分,在原始光谱的全波数段范围内,无需任何预处理方式,判别准确率达100%。同时对10个未知样品进行预测,预测准确率均为100%。其次建立了植物奶油掺假量的定量检测PLS模型,并采用交互校验和外部检验考察模型的可靠性,模型的校正相关系数为0.9963,均方估计残差(RMSEC)为0.110;交互校验均方残差(RMSECV)为0.142;应用所建PLS模型对样品中植物奶油添加量进行预测,并对预测值与真值进行配对t-检验,结果表明两者差异均不显著。

关键词: 近红外光谱技术, 模式识别, 偏最小二乘, 鲜乳和掺假乳

Abstract: The model of discrimination analysis was established by PLS-Mahalanobis distance for differentiating raw milk and adulterated milk which was added with vegetable cream. Three principal components were compressed from original data by PLS. The whole wave numbers regions were selected without any pretreatment methods,and all the accuracy rates of this model are 100%. Meanwhile,10 unknown samples were used to predict the results by the model,and all the prediction accuracy rates are 100%. PLS model for detecting the content of vegetable cream added with raw milk was set up with good veracity. Reliability of the model was verified by cross-validation and external-validation. Predictive correlation coefficient of the content of vegetable cream by PLS model is 0.9963. Root mean square error of calibration(RMSEC) is 0.11,while root mean square error of cross validation(RMSECV) is 0.142. By paired samples test,the results of prediction are compared with real values with no significantd ifference.

Key words: near infrared spectroscopy, pattern recognition, partial least squares, raw milk, adulterated milk

荣菡, 刘波平, 邓泽元, 罗香. 基于PLS-模式识别近红外光谱技术快速检测鲜乳和掺假乳[J]. 食品科学, 2008, 29(8): 492-495.

RONG Han, LIU Bo-Ping, DENG Ze-Yuan, LUO Xiang. Study on Rapid Determination of Raw Milk and Adulterated Milk Using Near Infrared Reflectance Spectroscopy Based on Partial Least Squares-Pattern Recognition Technique[J]. FOOD SCIENCE, 2008, 29(8): 492-495.

[1]	程超，夏兰欣，杜芬妮，李伟，田成. 基于9 种风味物质的利川红SPME优化及PLS-DA风味识别[J]. 食品科学, 2021, 42(6): 215-222.
[2]	李利利，马宇，黄永光，尤小龙，程平言，胡峰. 酱香白酒机械化酿造不同基酒风味化合物解析[J]. 食品科学, 2021, 42(18): 199-206.
[3]	庄齐斌，郑晓春，杨德勇，彭彦昆. 基于高光谱反射特性的猪肉新鲜度和腐败程度的对比分析[J]. 食品科学, 2021, 42(16): 254-260.
[4]	邱爽，唐飞，刘畅，谢美林，魏阳吉，李景明. 气相色谱-质谱联机结合感官分析共建樱桃香气关联网络[J]. 食品科学, 2021, 42(16): 209-217.
[5]	李睿雯，孙晓荣，刘翠玲，郭泽翰，田密. 拉曼光谱技术快速检测专用煎炸油极性组分[J]. 食品科学, 2021, 42(16): 328-332.
[6]	王珂雯，徐雷，徐贞贞，王雪，杨曙明. 基于液相色谱-四极杆飞行时间质谱方法分析冰鲜鸡肉代谢标志物[J]. 食品科学, 2021, 42(16): 293-303.
[7]	王世成，李国琛，王莹，李波，高凝轩，孙辞，宋阳，王颜红. 基于氮稳定同位素比例质谱和液相色谱-高分辨质谱的有机番茄鉴别[J]. 食品科学, 2021, 42(14): 159-164.
[8]	王华杰，滑金杰，余勤艳，江用文，王近近，杨艳芹，邓余良，袁海波. 基于IRAE-HS-SPME/GC-MS分析杀青方式对绿茶栗香形成的影响[J]. 食品科学, 2021, 42(14): 209-217.
[9]	卢洁，田婧，梁振华，王金梅，康文艺，马常阳，李昌勤. 近红外光谱法快速测定香菇总糖含量[J]. 食品科学, 2021, 42(12): 189-194.
[10]	申晨曦，杜晨晖，李震宇，李爱平，秦雪梅，闫艳. 基于氢核磁共振与偏最小二乘法对酸枣仁及其掺伪品的鉴别[J]. 食品科学, 2020, 41(8): 275-281.
[11]	马雪平，詹萍，田洪磊，未志胜，李凯旋. 基于GC-MS、DSA结合PLSR研究羊脂处理方式对热反应体系风味形成的影响[J]. 食品科学, 2020, 41(8): 194-201.
[12]	张英昊，薛照阳，赵廷彬，殷海松，乔长晟,. 出芽短梗霉发酵液中聚苹果酸定量近红外模型的建立与应用[J]. 食品科学, 2020, 41(8): 152-158.
[13]	苏佳佳，杨天，佟恩杰，赵雪莹，何程豪，杨哪，徐学明，吴凤凤. 糙米酒酿工艺优化与挥发性成分分析[J]. 食品科学, 2020, 41(8): 177-185.
[14]	方冠宇，蒋予箭，穆晓静，施思. 浙江玫瑰醋不同发酵阶段特征性香气成分的确定[J]. 食品科学, 2020, 41(8): 234-242.
[15]	郭俊先，马永杰，田海清，黄华，史勇，周军. 基于高光谱反透射图像的新疆冰糖心红富士水心鉴别[J]. 食品科学, 2020, 41(6): 278-284.