中国食品学报2012，Vol.12Issue(6)：166-173,8.
基于fisher线性判别和BP神经网络的电子鼻羊奶贮藏时间预测
Classification of Fresh Goat Milk at Different Storage Temperature Based on Electronic Nose by Fisher
摘要
Abstract
The classification of different storage time of fresh goat milk at ambient temperature and refrigerated temperature was detected by an electronic nose. The volatile composition emanating from the goat milk was sampled by PEN3 systems, and the response values of PEN3 was obtained. The data was analyzed using PC A (principal component analysis) and FDA(fisher linear discrimination analysis). The results showed that the classification of fresh goat milk during dayl~day5 storing at ambient temperature and refrigerated temperature by FDA were better than PCA, moreover LDA showed variation trend of volatile composition clearly which has a great agreement with acidity of the samples. Prediction rate of samples at ambient and refrigerate temperatures were 100% and 98.9% respectively, which was better than BP neural network.关键词
电子鼻/羊奶/贮藏时间/fisher/BPKey words
Electronic Nose/ goat milk/ storing time/ fisher/ BP引用本文复制引用
张虹艳,丁武..基于fisher线性判别和BP神经网络的电子鼻羊奶贮藏时间预测[J].中国食品学报,2012,12(6):166-173,8.基金项目
公益性行业科研专项经费项目(3-45) （3-45）
