| Meat quality assessment | Convolutional neural networks (CNNs) | Successfully attained accuracy in the classification of the freshness of meat with improved performance compared to traditional techniques. | Elmasry and Abdullah (2024) |
| Meat freshness detection | Ensemble of shallow CNNs (ConvNet-18 and ConvNet-24) | ConvNet-18 achieved 99.4% accuracy; ConvNet-24 had 96.6% accuracy in classifying degrees of freshness of meat. | Elangovan et al. (2024) |
| Non-destructive meat quality evaluation | Airflow pulse and 3D structured light imaging with AI models | Provided real-time, non-invasive prediction of tenderness in meat with a very high level of accuracy (correlation coefficient may reach 0.975). | Luo et al. (2023) |
| Food safety risk prediction | Machine learning, deep learning, transformers (e.g., BERT, RoBERTa), explainable AI (XAI) | Better prediction of food safety risk by enriched datasets; XAI techniques enhance model transparency. | Food Safety Magazine (2025) |
| Food safety monitoring | AI-driven sensor systems | Optimized cleaning processes in food production because it was able to detect residual microbes and sanitation on equipment. | Smart Food Safe (2025) |
| Early detection of foodborne illness outbreaks | Natural language processing (NLP) on public data | AI analyzed online reviews to provide early warnings of foodborne diseases outbreaks, aiding rapid response. | Smart Food Safe (2025) |
| Food safety risk assessment | Deep learning with categorical embedding | Predicted food safety issues with accuracy ranging from 74.08% to 93.06% using EU data. | Nogales et al. (2020) |