要点：

MSI和FTIR光谱法用于快速检测冷冻再解冻切馅牛肉

FTIR检测以及外在验证试验的PLS-DA正确率分别为93.3和96.7%。

MSI检测以及外在验证试验表明PLS-DA 和SVM 鉴别正确率可达100%。

使用MSI和FTIR的快速方法可应用于快速、性价比高的造假检测。

近年来，造假检测已成为食品检测机构监测重点，造假行为会产生多种经济和有效隐患。本研究工作旨在探索标签为新鲜牛肉的冷冻再解冻牛肉馅的快速、大规模和性价比高的鉴别方法。

摘要

基于此目的，不同时间于7个不同商店购买了新鲜牛肉，分成了15份，放置在培养皿中。很快获得了前5个样本的多光谱图像和FTIR光谱，其余样品冷冻在−20°C，储存7天和32天（每个时间间隔有5个样品）。

解冻样品，之后按同样方法获取相同数据。总共生成105张多光谱图像和FTIR光谱，并用偏较小二乘法和支持向量机发进行分析。

保存2个肉批次（30个样本）用做独立验证，其余5批分为培训集和检测集（75个样品）。结果显示，MSI检测集和外部验证集的准确率达100%，而FTIR检测集和外部验证集的总正确检出率为93.3%和96.7%。

Rapid detection of frozen-then-thawed minced beef using multispectral imaging and Fourier transform infrared spectroscopy

Author links open overlay panelAthina I.RopodiEfstathios Z.PanagouGeorge-John E.Nychas

Show more

https://doi.org/10.1016/j.meatsci.2017.09.016

Highlights

•MSI and FTIR spectroscopy used for rapid detection of frozen-thawed minced beef

•PLS-DA and SVM yielded 100% correct classification for MSI test and external validation sets.

•PLS-DA yielded 93.3 and 96.7% classification accuracy for FTIR test and external validation set.

•Rapid methods using MSI and FTIR sensors can be applied for rapid, cost-effective fraud detection.

Abstract

In recent years, fraud detection has become a major priority for food authorities, as fraudulent practices can have various economic and safety consequences. This work explores ways of identifying frozen-then-thawed minced beef labeled as fresh in a rapid, large-scale and cost-effective way. For this reason, freshly-ground beef was purchased from seven separate shops at different times, divided in fifteen portions and placed in Petri dishes. Multi-spectral images and FTIR spectra of the first five were immediately acquired while the remaining were frozen (− 20 °C) and stored for 7 and 32 days (5 samples for each time interval). Samples were thawed and subsequently subjected to similar data acquisition. In total, 105 multispectral images and FTIR spectra were collected which were further analyzed using partial least-squares discriminant analysis and support vector machines. Two meat batches (30 samples) were reserved for independent validation and the remaining five batches were divided in training and test set (75 samples). Results showed 100% overall correct classification for test and external validation MSI data, while FTIR data yielded 93.3 and 96.7% overall correct classification for FTIR test set and external validation set respectively.

Keywords

Minced beef，Frozen-thawed，Multispectral imaging，FTIR spectroscopy，Fraud detection，Data analysis