Grain processing products constitute an essential component of the human diet and are among the main sources of heavy metal intake. Therefore, a systematic assessment of risk factors and early-warning systems are vital to control heavy metal hazards in grain processing products. In this study, we established a risk assessment model to systematically analyze heavy metal hazards and combined the model with the K-means++ algorithm to perform risk level classification. We then employed deep learning models to conduct a multi-step prediction of risk levels, providing an early warning of food safety risks. By introducing a voting-ensemble technique, the accuracy of the prediction model was improved. The results indicated that the proposed model was superior to other models, exhibiting the overall accuracy of 90.47% in the 7-day prediction and thus satisfying the basic requirement of the food supervision department. This study provides a novel early-warning model for the systematic assessment of the risk level and further allows the development of targeted regulatory strategies to improve supervision efficiency.
This study aims to evaluate the risk of lead pollution in 9 kinds of vegetables consumed by residents in 20 provinces/cities of China. Sampling data and vegetable consumption data from 20 provinces/cities in 2019 were used. Combined with dietary exposure assessment, the vegetable categories and provinces were paired, and a risk classification model based on spectral clustering algorithms was proposed. The results of the spectral clustering algorithm showed that the risk level of lead pollution in vegetables can be divided into five levels. The combination of vegetable‐province/cities at the risk level of 1 and 2 accounted for 92.78%, and that at the risk level of 4 and 5 accounted for 2.22%. The high‐risk combinations were fresh edible fungus–Shaanxi, fresh edible fungus–Sichuan, and fresh edible fungus–Shanghai and bean sprouts–Guangdong. In the proposed model, objective data were used as the classification index, and the spectral clustering algorithm was employed to select the optimal risk classification in a data‐driven way. As a result, the influence of subjective factors was effectively reduced, the risk of lead pollution in vegetables was classified, and the results were scientific and accurate. This study provides a scientific basis of supervision priorities for regulatory departments.
Risk classification assessment and early warning systems are indispensable tools and technologies in the realm of regulatory control. Evaluating and issuing early warnings regarding heavy metal contaminants in meat products play a pivotal role in ensuring public safety and maintaining societal stability. In this study, we focused on heavy metal pollutants such as lead, cadmium, chromium, and arsenic. We collected national inspection data for meat products from 20 provinces in 2020. Combining dietary structure data, toxicology information, and dietary exposure assessment methods, we constructed a risk assessment model for heavy metal contaminants in food. Furthermore, we employed an entropy weight-based analytic hierarchy process (AHP-EW) to classify the results of the risk assessment for heavy metal contaminants in food. This involved determining risk rating levels and thresholds. Finally, we constructed a multi-step food contaminant risk prediction model based on the Transformer framework. To validate the model’s performance, comparative assessments were conducted across 20 datasets using various models. The results clearly indicate that the Transformer model outperformed the others in 14 datasets, excelling in its ability to provide advanced warnings for heavy metal risks in meat products. This empowers relevant authorities to strengthen their regulatory oversight of meat products based on the procedures and models proposed in this study, ultimately enhancing the efficiency of food safety risk management.
As a staple food for people worldwide, processed grain products, including rice, wheat flour, etc., have been the major source of the toxic element cadmium for human exposure. Indeed, cadmium contamination in processed grain products directly affects food security and human health, especially in countries with a grain-based diet like China. By analyzing the cadmium levels in processed grain products across 20 provinces and cities in China during the period 2023–2024, we have developed an improved k-means++ algorithm that determines the optimal clustering number through a voting scheme. This algorithm has enabled us to establish a risk classification model, which provides an objective and rapid assessment of risk levels based on data-driven analysis. The results of the risk classification reveal that the risk levels of cadmium contamination in processed grain products can be classified into five levels, with high-risk products accounting for only 2.81% of the total. As for different types of processed grain products, the risk levels of rice and other processed grain products are higher than that of wheat. In addition, the risk levels of southern provinces/cities in China are higher than those of northern provinces/cities.