Development of a RBFNN prediction model for carrot quality based on meteorological temperatures at vegetable stations  

作　　者：Yu-Tong Yan Zeng-Tao Ji Ce Shi 

机构地区：[1]Research Center of Information Technology,Beijing Academy of Agriculture and Forestry Sciences,Beijing 100097,China [2]National Engineering Research Center for Information Technology in Agriculture,Beijing Academy of Agricultural and Forestry Sciences,Beijing 100097,China [3]National Engineering Laboratory for Agri-product Quality Traceability,Beijing Academy of Agricultural and Forestry Sciences,Beijing 100097,China [4]Key Laboratory of Cold Chain Logistics Technology for Agro-product,Ministry of Agriculture and Rural Affairs,Beijing 100097,China

出　　处：《Food and Health》2024年第2期49-57,共9页食品和健康（英文）

基　　金：This study was supported by the National Natural Science Foundation of China(grant numbers:3207150985)。

摘　　要：To evaluate and predict the quality of carrots during logistics process in North China under extreme temperature conditions,quality indicator changes of carrots were investigated,and temperature-coupled quality prediction models were developed.Seven temperatures were selected from meteorological temperature data by cluster analysis to simulate the changes in extreme temperatures during the short-term transportation of carrots.No carrots rotted during the 48h storage period.Under both isothermal and nonisothermal conditions,weight loss andΔE increased while the firmness and sensory evaluation(SE)decreased.The RBFNN performed better than the Arrhenius model in predicting weight loss andΔE,with R^(2)>0.97,MSE<0.009 and relative errors within±18%.The results of the predictive confidence level and standardized residual indicated the good performance of the RBFNN model.The temperature-coupled prediction models of RBFNN were promising candidates for predicting the quality of vegetable products and therefore reducing economic loss of vegetable industry.

关 键 词：CARROT Extreme temperatures Temperature coupled ARRHENIUS Radial basis function neural network 

分 类 号：TP1[自动化与计算机技术—控制理论与控制工程]