傅里叶变换红外光谱
偏最小二乘回归
均方误差
傅里叶变换
支持向量机
多光谱图像
模式识别(心理学)
数学
人工智能
分析化学(期刊)
计算机科学
化学
统计
色谱法
光学
物理
数学分析
作者
Lemonia-Christina Fengou,Anastasia E. Lytou,George T. Tsekos,Panagiοtis Tsakanikas,George‐John E. Nychas
出处
期刊:Food Chemistry
[Elsevier BV]
日期:2023-12-14
卷期号:440: 138184-138184
被引量:23
标识
DOI:10.1016/j.foodchem.2023.138184
摘要
Rapid assessment of microbiological quality (i.e., Total Aerobic Counts, TAC) and authentication (i.e., fresh vs frozen/thawed) of meat was investigated using spectroscopic-based methods. Data were collected throughout storage experiments from different conditions. In total 526 spectra (Fourier transform infrared, FTIR) and 534 multispectral images (MSI) were acquired. Partial Least Squares (PLS) was applied to select/transform the variables. In the case of FTIR data 30 % of the initial features were used, while for MSI-based models all features were employed. Subsequently, Support Vector Machines (SVM) regression/classification models were developed and evaluated. The performance of the models was evaluated based on the external validation set. In both cases MSI-based models (Root Mean Square Error, RMSE: 0.48–1.08, Accuracy: 91–97 %) were slightly better compared to FTIR (RMSE: 0.83–1.31, Accuracy: 88–94 %). The most informative features of FTIR for the case of quality were mainly in 900–1700 cm−1, while for fraud the features were more dispersed.
科研通智能强力驱动
Strongly Powered by AbleSci AI