Risto Uzunov, Aleksandra Angeleska
The adoption of artificial intelligence (AI) within the framework of fourth industrial revolution (Industry 4.0) is reshaping contemporary food safety management by enabling a transition from predominantly reactive practices to proactive and predictive approaches. This study explores how AI-based technologies, including machine learning, computer vision, and Internet of Things (IoT) technologies, contribute to improved food safety control, quality monitoring, and supply chain traceability. The analysis indicates that AI-driven solutions outperform traditional manual methods by delivering faster and more accurate detection of contaminants, improved identification of foodborne pathogens, and more reliable shelf-life prediction. The integration of AI with blockchain further strengthens traceability mechanisms, allowing rapid identification and containment of contamination events. Nevertheless, several limitations remain, notably the limited interpretability of complex deep-learning models, substantial implementation costs, and persistent challenges related to data quality and standardization. In addition, ethical issues, such as data protection and potential algorithmic bias, highlight the importance of transparent governance frameworks. The findings suggest that optimal outcomes are achieved when AI systems operate within a human-in-the-loop model, supported by interdisciplinary expertise and harmonized global datasets. Collectively, these advancements indicate that AI has strong potential to enhance the resilience, efficiency, and transparency of the global food supply chain, supporting progress toward a zero-contamination objective.