基于SWIR-HSI的羊肉中食物传播病原体污染的现场检测模型的建立和比较
Zongxiu Bai1, Dongdong Du2, Rongguang Zhu1,3,4
1College of Mechanical and Electrical Engineering, Shihezi University, Shihezi, China.
Frontiers in nutrition
|February 26, 2024
概括
短波红外高光谱成像 (SWIR-HSI) 与人工智能相结合,可以准确地检测食物传播的病原体,如羊肉上的大肠杆菌,金黄色杆菌和型杆菌. 深度学习模型在可靠的肉类安全分析方面表现优于机器学习.
科学领域:
- 食品科学 食品科学 食品科学
- 分析化学 分析化学
- 机器学习 机器学习
背景情况:
- 确保羊肉安全需要快速检测食物传播病原体.
- 受到诸如大肠杆菌 (EC),黄金葡萄球菌 (SA) 和沙门氏菌 (ST) 等病原体的污染会给健康带来重大风险.
研究的目的:
- 探索短波红外高光谱成像 (SWIR-HSI) 的可行性,以检测羊肉上的EC,SA和ST的污染状况和物种.
- 用SWIR-HSI数据评估各种机器学习和深度学习模型的病原体检测性能.
主要方法:
- 采集了羊肉样本的超光谱图像,其中EC,SA和ST的度各不相同.
- 构建和优化的一维卷积神经网络 (1D-CNN) 模型.
- 用不同的光谱预处理技术比较了1D-CNN,部分最小平方差异分析 (PLS-DA) 和支持矢量机 (SVM) 模型的性能.
- 研究了用于简化模型开发的特征波长的使用.
主要成果:
- 最优的全频段模型是具有特定超参数的1D-CNN,在训练组中达到100.00%的准确性,在测试组中达到92.86%,在外部验证组中达到97.62%.
- 支持矢量机 (SVM) 模型,特别是基因算法优化SVM (GA-SVM),在物种歧视方面显示出高精度 (100.00%).
- 使用原始光谱的1D-CNN模型被认为是检测污染状况和物种的最佳模型,因为它们的复杂性和准确性的平衡.
结论:
- 与机器学习和深度学习相结合的SWIR-HSI提供了一种可靠的方法,可以准确地检测羊肉上的食物传播病原体.
- 在这种应用中,深度学习模型的表现通常优于传统的机器学习模型.
- 这项研究支持HSI技术的更广泛应用,以提高肉制品的食品安全.
更多相关视频
12:50Colorimetric Paper-based Detection of Escherichia coli, Salmonella spp., and Listeria monocytogenes from Large Volumes of Agricultural Water
Published on: June 9, 2014
14.5K
05:34Author Spotlight: Development of an Enhanced Protocol for Rapid and Accurate Isolation of Campylobacter from Food Products
Published on: February 23, 2024
1.9K
相关概念视频
Sources of Food Contamination
Contamination of food by microbial agents and natural toxins poses significant risks to public health. These hazards can be introduced at various points across the food supply chain, ranging from environmental sources to processing and storage stages. Understanding these contamination pathways is critical for developing strategies to ensure food safety.Seafood is particularly vulnerable to contamination through both environmental exposure and microbial colonization. Toxins from harmful algal...
Investigation of Disease Outbreaks
Multistate foodborne outbreaks pose significant public health risks and require meticulous investigation to identify sources and implement control measures. The Centers for Disease Control and Prevention (CDC) utilizes a dynamic seven-step process for these investigations, integrating data from laboratories, interviews, and environmental assessments to protect public health.Outbreak Detection: The detection of multistate outbreaks typically begins with PulseNet, the CDC's national laboratory...
