化学计量学
偏最小二乘回归
高光谱成像
近红外光谱
线性判别分析
光谱学
模式识别(心理学)
人工智能
数学
生物系统
计算机科学
材料科学
分析化学(期刊)
化学
统计
光学
色谱法
机器学习
物理
量子力学
生物
作者
Jingjing Zhang,Guishan Liu,Yan Li,Mei Guo,Fangning Pu,Han Wang
标识
DOI:10.1016/j.jfca.2022.104590
摘要
In the meat industry, it is essential to monitor and identify meat freshness grades due to its impact on the safety of human diets. This study aimed to identify premium, sub-fresh, and spoiled lamb samples using visible and near-infrared (Vis-NIR) hyperspectral imaging (HSI) in the range of 400–1000 nm coupled with chemometrics methods. The two-dimensional correlation spectroscopy (2D-CS) was utilized to select effective wavelengths for simplifying the model and increasing the calculation speed. The capabilities of the four models including partial least squares discriminant analysis (PLS-DA), soft independent modelling of class analogy (SIMCA), back propagation neuron network (BP), decision tree (DT) and random forest (RF) were compared to select the best identification model. The results showed that the RF model generated excellent performance, the accuracies of the training and test sets were 93% and 91%, respectively. In summary, this study showed that it was feasible to rapidly and non-destructively identify and evaluate the freshness grades of lamb using Vis-NIR.
科研通智能强力驱动
Strongly Powered by AbleSci AI