Food safety risk prediction is crucial for timely hazard detection and effective control. This study proposes a novel risk prediction method for food safety called TabNet-GRA, which combines a specialized deep learning architecture for tabular data (TabNet) with a grey relational analysis (GRA) to predict food safety risk. Initially, this study employed a GRA to derive comprehensive risk values from fused detection data. Subsequently, a food safety risk prediction model was constructed based on TabNet, and training was performed using the detection data as inputs and the comprehensive risk values calculated via the GRA as the expected outputs. Comparative experiments with six typical models demonstrated the superior fitting ability of the TabNet-based prediction model. Moreover, a food safety risk prediction and visualization system (FSRvis system) was designed and implemented based on TabNet-GRA to facilitate risk prediction and visual analysis. A case study in which our method was applied to a dataset of cooked meat products from a Chinese province further validated the effectiveness of the TabNet-GRA method and the FSRvis system. The method can be applied to targeted risk assessment, hazard identification, and early warning systems to strengthen decision making and safeguard public health by proactively addressing food safety risks.

Pesticide residue is a prominent factor that leads to food safety problems. For this reason, many countries sample and detect pesticide residues in food every year, which generates a large amount of pesticide residue data. However, the way to deeply analyze and mine these data to quickly identify food safety risks is still an unresolved issue. In this study, we present an intelligent analysis system that supports the collection, processing, and analysis of detection data of pesticide residues. The system is first based on a number of databases such as maximum residue limit standards for the fusion of pesticide residue detection results; then, it applies a series of statistical methods to analyze pesticide residue data from multiple dimensions for quickly identifying potential risks; it uses the Apriori algorithm to mine the implicit association in the data to form pre-warning rules; finally, it applies Word document automatic generation technology to automatically generate pesticide residue analysis and pre-warning reports. The system was applied to analyze the pesticide residue detection results of 42 cities in mainland China from 2012 to 2015. Application results show that the system proposed in this study can greatly improve the depth, accuracy and efficiency of pesticide residue detection data analysis, and it can provide better decision support for food safety supervision.