当前位置: 首页 > 文章 > 纯牛奶中还原奶的近红外检测判别分析 农机化研究 2008 (8) 145-147
Position: Home > Articles > Identification of Reconstructed Milk in Raw Milk Using Near Infrared Spectroscopy Journal of Agricultural Mechanization Research 2008 (8) 145-147

纯牛奶中还原奶的近红外检测判别分析

作  者:
李凯歌;韩东海;孙明
单  位:
中国农业大学信息与电气工程学院;中国农业大学食品科学与营养工程学院
关键词:
近红外光谱;纯牛奶;还原奶;马氏距离;仿生模式识别
摘  要:
探讨了近红外光谱技术结合化学计量学算法对纯牛奶中是否掺入还原奶鉴别的可行性。考察了马氏距离判别分析和仿生模式识别方法在还原奶检测中的适用性。结果表明:利用马氏距离判别分析方法鉴别,正确判别率为87.5%;利用仿生模式识别方法鉴别,正确判别率为98.3%。由此方法说明:近红外技术可以实现对纯牛奶中是否含有还原奶进行快速鉴别;采用仿生模式识别比马氏距离判别分析法鉴别效果更好。
译  名:
Identification of Reconstructed Milk in Raw Milk Using Near Infrared Spectroscopy
作  者:
LI Kai-ge1, HAN Dong-hai2, SUN Ming1 (China Agricultural University, a. College of Information and Electrical Engineering; b.College of Food Science and Nutritional Engineering, Beijing 100083, China)
关键词:
nirs infrared spectroscopy; raw milk; reconstructed milk; mahalanobis distance; biomimetic pattern recognition
摘  要:
Feasibility of reconstructed milk identification in raw milk was investigated using near infrared spectroscopy combining with chemometrics algorithms. And the applicability of Mahalanobis distance discrimination analysis and biomimetic pattern recognition for reconstructed milk identification was discussed. The result indicated that the accuracy of detection is 87.5% using Mahalanobis distance discrimination analysis, while 98.3% using biomimetic pattern recognition. All of these suggested that NIRS has good potential to detect adulteration of raw milk with reconstructed milk. And biomimetic pattern recognition is better than Mahalanobis distance discrimination analysis in the identification.

相似文章

计量
文章访问数: 9
HTML全文浏览量: 0
PDF下载量: 0

所属期刊

推荐期刊