Monitoring and Shelf Life Extension of Food Products Based on Machine Learning and Deep Learning: Progress and Potential Applications
Adjoba Grace Marie-Désirée Ablegue, Min Zhang, Qing Guo, Luming Rui
Abstract
Recent advances in Artificial Intelligence (AI), particularly machine learning (ML) and deep learning (DL), offer promising approaches for the rapid, precise, and dynamic assessment of food quality and shelf life. The aim of this review is to critically evaluate the progress of ML and DL algorithms in monitoring and predicting the shelf life of diverse food products, including meat, dairy, fruits, vegetables, and beverages. It highlights their capacity to process complex datasets and integrate key intrinsic and extrinsic degradation factors, thereby improving prediction accuracy. The review also discusses AI model validation frameworks essential for ensuring reliability and robustness of predictions in real-world food industry applications. The integration of AI technologies with blockchain systems is further explored as a pathway to ensuring transparency and traceability within the food supply chain. Additionally, the review addresses critical challenges such as limited data availability, high implementation costs, regulatory compliance, and ethical concerns that may hinder large-scale adoption. The findings indicate that AI-based approaches outperform traditional techniques in predictive modeling by leveraging high-dimensional data, enabling real-time monitoring, and adapting to dynamic food systems. Moreover, the integration of AI with the Internet of Things (IoT) and big data holds transformative potential to revolutionize food industry practices and ensure enhanced food safety and sustainability.