Hybrid Sampling and Ensemble Learning for Food Safety Sampling Inspection Classification
Journal of Food Protection · 2025-12 · 88 (12) · 100650
DOI: 10.1016/j.jfp.2025.100650 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Food Protection, 2025-12. Verfasst von Ke Qin und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Business, Jiangnan University, No. 1800, Lihu Avenue, Wuxi 214122, PR China. Electronic address: qinke0905@163.com. Hauptthemen laut MEDLINE: Food Safety, Machine Learning, Food Inspection. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Social Science Fund of China, Major Program of National Fund of Philosophy and Social Science of China.
Abstract (Originalsprache)
Food safety sampling inspection is critical for risk prevention in complex supply chains. However, extreme class imbalance, where unqualified samples are significantly outnumbered by qualified ones, biases machine learning (ML) models to prioritize majority classes, compromising unqualified sample detection. Conventional oversampling methods fail to handle food inspection data's nonlinear features, complex distributions, and multiclass scenarios, often generating low-quality synthetic samples and noisy decision boundaries. To address these challenges, we proposed LOF-KNN-CSENN (Local Outlier Factor-K-Nearest Neighbors-Combined Synthetic Minority Over-sampling Technique and Edited Nearest Neighbors), a hybrid sampling algorithm of Synthetic Minority Over-sampling Technique (SMOTE) and Edited Nearest Neighbors (ENN) integrating Local Outlier Factor (LOF) for noise filtering and K-Nearest Neighbors (KNN) for boundary sample preservation. LOF-KNN-CSENN synergizes minority oversampling and majority undersampling to optimize data distribution. A stacking ensemble learning framework is further introduced, combining six tree-based models with Logistic Regression (LR) as a meta model to enhance classification robustness. Experiments on a real-world food safety sampling inspection dataset demonstrated that LOF-KNN-CSENN suppresses noisy sample synthesis and balances data distribution. When integrated with stacking, the model achieves 0.4-5.6% higher precision and 0.8-30.7% higher F1-score compared to single models. Shapley Additive Explanations (SHAP) analysis identified production address, sampling stage, and location as key risk factors, supporting targeted supervision. This study provides a novel framework for intelligent food safety regulation, leveraging hybrid sampling and ensemble learning to mitigate class imbalance and enhance unqualified sample detection in multicategory food inspection.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Business, Jiangnan University, No. 1800, Lihu Avenue, Wuxi 214122, PR China. Electronic address: qinke0905@163.com.
- School of Business, Jiangnan University, No. 1800, Lihu Avenue, Wuxi 214122, PR China; Jiangsu Provincial Laboratory of Food Safety and National Strategic Governance, Jiangnan University, No. 1800, Lihu Avenue, Wuxi 214…
Förderung
- National Social Science Fund of China
- Major Program of National Fund of Philosophy and Social Science of China
Zitieren
APA
Qin, K., Dai, X., & Wu, L. (2025). Hybrid Sampling and Ensemble Learning for Food Safety Sampling Inspection Classification. Journal of Food Protection, 88(12), 100650. https://doi.org/10.1016/j.jfp.2025.100650
Vancouver
Qin K, Dai X, Wu L. Hybrid Sampling and Ensemble Learning for Food Safety Sampling Inspection Classification. Journal of Food Protection. 2025;88(12):100650. doi:10.1016/j.jfp.2025.100650
BibTeX
@article{Qin2025,
author = {Qin, Ke and Dai, Xiaoting and Wu, Linhai},
title = {Hybrid Sampling and Ensemble Learning for Food Safety Sampling Inspection Classification},
journal = {Journal of Food Protection},
year = {2025},
volume = {88},
number = {12},
pages = {100650},
doi = {10.1016/j.jfp.2025.100650}
}
EUVIMED