Early warning and control of food safety risk using an improved AHC-RBF neural network integrating AHP-EW

Food safety is an important issue affecting social development. Early warning analysis and risk control of food safety is of great significance in managing food safety risks, thereby ensuring food safety. In this paper, we propose an improved early warning approach for assessing and controlling food safety risk based on the agglomerative hierarchical clustering-radial basis function (AHC-RBF) neural network integrating an analytic hierarchy process approach and the entropy weight (AHP-EW). Different risk values of the detection data are fused by the AHP-EW to obtain the risk fusion value which is the output of the AHC-RBF. The detection data are set as the input of the AHC-RBF to build the early warning model. Moreover, prediction and control of food safety risk are analyzed. Finally, a case study of meat products detection data in China is carried out based on the proposed model. We compared our model with the back propagation (BP) and the RBF neural network, and the results verify the effectiveness of our proposed early warning model. The proposed early warning analysis is helpful for food safety supervision departments to control food safety risk.