Note: Some visual elements in this video were generated using artificial intelligence.

On 17 June 2025, Saksonita Khoeurn, Kyunghee Lee, and Wan-Sup Cho published an original research paper titled ‘Application of Explainable Artificial Intelligence and Voting Ensemble Models in Predicting the Results of Import Inspections of Aquatic Products’ in the Journal of Food Safety and Food Quality-Archiv für Lebensmittelhygiene (JFSFQ).

Author's Interpretation

As South Korea sees a surge in food imports driven by free trade agreements, ensuring food safety has never been more urgent. Yet, traditional inspections are becoming more time-consuming and costly. Could artificial intelligence be the key? One major hurdle remains — the lack of a reliable machine learning model to predict food safety.

This study developed an effective classification model for predicting non-conformance in customs inspection of imported seafood products. To address the severe class imbalance inherent in the inspection data, they applied class weight-based cost-sensitive learning and adopted an ensemble approach combining Decision Trees (DT), Random Forests (RF), Logistic Regression (LR), and Naive Bayes (NB) models.

Watch the video for a concise overview of this research.

Original Article:

Explainable AI and Voting Ensemble Model to Predict the Results of Seafood Product Importation Inspections: https://www.imrpress.com/journal/JFSFQ/76/2/10.31083/JFSFQ39242

Related Articles:

Enhancement of Hygiene and Safety in the Food Industry Through Digitalization With Blockchain Technology: https://www.imrpress.com/journal/JFSFQ/76/4/10.31083/JFSFQ42885

Food Safety Practices and Contributing Factors Among Food Handlers in Food Establishments in Ethiopia: https://www.imrpress.com/journal/JFSFQ/76/1/10.31083/JFSFQ38137