Author(s)

Tongjuan Liu, Anqi Hu

Information School, Beijing Wuzi University, Beijing, China.

There is still no effective means to analyze in depth and utilize domestic mass data about agricultural product quality safety tests in china now. The neural network algorithm, the classification regression tree algorithm, the Bayesian network algorithm were selected according to the principle of selecting combination model and were used to build models respectively and then combined, innovatively establishing a combination model which has relatively high precision, strong robustness and better explanatory to predict the results of perishable food transportation meta-morphism monitoring. The relative optimal prediction model of the perishable food transportation metamorphism monitoring system could be got. The relative perfect prediction model can guide the actual sampling work about food quality and safety by prognosticating the occurrence of unqualified food to select the typical and effective samples for test, thus improving the efficiency and effectiveness of sampling work effectively, so as to avoid deteriorated perishable food’s approaching the market to ensure the quality and safety of perishable food transportation. A solid protective wall was built in the protection of general perishable food consumers’ health.

Perishable Foodstuffs, Transport Monitoring, Dada Mining, Sample Detection, Neural Network, the Classification and Regression Tree Algorithm (CART), Bayesian Network

Liu, T. and Hu, A. (2017) Model of Combined Transport of Perishable Foodstuffs and Safety Inspection Based on Data Mining. Food and Nutrition Sciences, 8, 760-777. doi: 10.4236/fns.2017.87054.