Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Risk Classification Assessment and Early Warning of Heavy Metal Contamination in Meat Products
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.
Risk Classification Assessment and Early Warning of Heavy Metal Contamination in Meat Products
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.
Risk Classification Assessment and Early Warning of Heavy Metal Contamination in Meat Products
Zheng Wang (Autor:in) / Yanping Gao (Autor:in) / Xuemei Xu (Autor:in) / Wei Dong (Autor:in) / Tongqiang Jiang (Autor:in)
2023
Aufsatz (Zeitschrift)
Elektronische Ressource
Unbekannt
Metadata by DOAJ is licensed under CC BY-SA 1.0
Heavy Metal Contamination of Soil, Its Risk Assessment and Bioremediation
| Taylor & Francis Verlag | 2011
Heavy Metal Contamination and Risk Assessment around Some Abandoned Metal Mine Sites in Korea
| British Library Online Contents | 2004
Risk-Benefit Assessment of Dam Early Warning Systems
| British Library Conference Proceedings | 2003
| DOAJ | 2023
| DOAJ | 2023