Monitoring of veterinary drug residues in mutton based on hyperspectral combined with explainable AI: A case study of OFX

Abstract

Veterinary drug residues in meat seriously harm human health. Rapid and accurate detection of veterinary drug residues is necessary to minimize contamination. Taking ofloxacin (OFX) residues in mutton as an example, the near-infrared hyperspectral imaging combined with explainable AI was used to evaluate the importance of feature wavelengths in the convolutional neural network-stacked sparse auto-encoder (CNN-SSAE) model for chemical properties. Based on this, the qualitative (residue identification-residue level identification) and quantitative detection of OFX residues in mutton was realized. The results showed that the accuracy of CNN-SSAE in identifying residue and residue level of OFX was 100% and 93.65%, respectively, and the correlation coefficients for validation (R²_P) in quantitative detection of OFX residue was 0.8980. In addition, SHapley Additive exPlanation (SHAP) values were used to identify feature wavelengths that contribute the most in the CNN-SSAE model, which effectively explained the quality attribute information that spectral and chemical values may improve the predicted results in the model decision process. The reliability of the CNN-SSAE model was evaluated by statistical validation methods (F-test and T-test). Finally, the visualization diagram of OFX content distribution was established. This study provides a method reference for explainability detection of veterinary drug residues.