Anomaly Score-Based Risk Early Warning System for Rapidly Controlling Food Safety Risk

An explainable unsupervised risk early warning framework based on the empirical cumulative distribution function: Application to dairy safety

Efficient food safety risk assessment significantly affects food safety supervision. However, food detection data of different types and batches show different feature distributions, resulting in unstable detection results of most risk assessment models, lack of interpretability of risk classification, and insufficient risk traceability. This study aims to explore an efficient food safety risk assessment model that takes into account robustness, interpretability and traceability. Therefore, the Explainable unsupervised risk Warning Framework based on the Empirical cumulative Distribution function (EWFED) was proposed. Firstly, the detection data's underlying distribution is estimated as non-parametric by calculating each testing indicator's empirical cumulative distribution. Next, the tail probabilities of each testing indicator are estimated based on these distributions and summarized to obtain the sample risk value. Finally, the "3σ Rule" is used to achieve explainable risk classification of qualified samples, and the reasons for unqualified samples are tracked according to the risk score of each testing indicator. The experiments of the EWFED model on two types of dairy product detection data in actual application scenarios have verified its effectiveness, achieving interpretable risk division and risk tracing of unqualified samples. Therefore, this study provides a more robust and systematic food safety risk assessment method to promote precise management and control of food safety risks effectively.

CSGNN: Contamination Warning and Control of Food Quality via Contrastive Self-Supervised Learning-Based Graph Neural Network

Effective contamination warning and control of food quality can significantly reduce the likelihood of food quality safety incidents. Existing food contamination warning models for food quality rely on supervised learning, do not model the complex feature associations between detection samples, and do not consider the unevenness of detection data categories. In this paper, To overcome these limitations, we propose a Contrastive Self-supervised learning-based Graph Neural Network framework (CSGNN) for contamination warning of food quality. Specifically, we structure the graph for detecting correlations between samples and then define the positive and negative instance pairs for contrastive learning based on attribute networks. Further, we use a self-supervised approach to capture the complex relationships between detection samples. Finally, we assessed each sample's contamination level based on the absolute value of the subtraction of the prediction scores from multiple rounds of positive and negative instances obtained by the CSGNN. Moreover, we conducted a sample study on a batch of dairy product detection data in a Chinese province. The experimental results show that CSGNN outperforms other baseline models in contamination assessment of food quality, with AUC and recall of unqualified samples reaching 0.9188 and 1.0000, respectively. Meanwhile, our framework provides interpretable contamination classification for food detection. This study provides an efficient early warning method with precise and hierarchical contamination classification for contamination warning of food quality work.