A new review paper categorizes explainable AI (XAI) techniques for use in Food Engineering, aiming to increase transparency and reliability in AI models. The paper highlights the underutilization of XAI in this field, despite its potential to improve food quality control by identifying key data features, such as spectral wavelengths or image regions, that influence predictions. Techniques like SHAP and Grad-CAM are discussed as methods to pinpoint influential factors, thereby aiding inspectors and encouraging broader adoption of AI in food safety and assessment. AI
Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →
IMPACT Enhances transparency in AI models for food quality control, potentially improving safety and reliability.
RANK_REASON This is a review paper published on arXiv, focusing on the application of XAI techniques in a specific domain.