摘要
利用波长范围400～1 000 nm高光谱对香肠的菌落总数进行预测研究。选取450个香肠样本的光谱数据作为训练集,50个作为测试集。采用多元散射校正方法对光谱预处理并采用主成分分析法对光谱降维处理。对训练集和测试集数据分别采用支持向量回归和迭代决策树(gradient boosting decision tree,GBDT)方法建立定量分析模型,优选最佳建模方法。结果表明:GBDT的建模效果较好,其训练集和测试集的均方根误差分别为0.001和0.003,决定系数R2分别为0.998和0.996。研究表明,基于高光谱成像技术利用GBDT方法预测香肠菌落总数可行并可有效实现。
This experiment used a hyperspectral image system in the wavelength range of 400–1 000 nm to predict the total viable count in sausage. Spectral data of 450 sausage samples were selected as the training set, and another 50 samples as the test set. The spectra was preprocessed by multiplicative scatter correction(MSC) method and principal component analysis(PCA) was used to reduce the dimensionality of the spectral data. Support vector regression(SVR) and gradient boosting decision tree(GBDT) were separately used to establish quantitative analysis models for the training and test sets,and the optimal model was selected. The results showed that the GBDT models were better than the SVR models. The root mean square error(RMSE) of the GBDT models were 0.001 and 0.003 for the training and test sets, respectively, and the coefficients of determination(R2) were 0.998 and 0.996, respectively. This study proved that the GBDT method based on hyperspectral imaging technology was feasible and effective to predict the total viable count in sausage.
作者
郭培源
徐盼
董小栋
许晶晶
GUO Peiyuan;XU Pan;DONG Xiaodong;XU Jingjing(Beijing Key Laboratory of Big Data Technology for Food Safety,School of Computer and Information Engineering,Beijing Technology and Business University,Beijing 100048,China)
出处
《食品科学》
EI
CAS
CSCD
北大核心
2019年第6期312-317,共6页
Food Science
基金
国家自然科学基金面上项目(61473009)
北京市自然科学基金项目(4122020)
关键词
高光谱成像技术
香肠
菌落总数
支持向量回归(SVR)
迭代决策树(GBDT)
hyperspectral imaging technology
sausage
total viable count(TVC)
support vector regression(SVR)
gradient boosting decision tree(GBDT)
