Risk Evaluation of Cold Chain Marine Logistics based on the Dempster-Shafer (D-S) Evidence Theory and Radial Basis Function (RBF) Neural Network

Abstract

Wang, L.; Zhang, G., and Hao, Q., 2019. Risk evaluation of cold chain marine logistics based on the Dempster-Shafer (DS) evidence theory and radial basis function (RBF) neural network. In: Li, L.; Wan, X.; and Huang, X. (eds.), Recent Developments in Practices and Research on Coastal Regions: Transportation, Environment and Economy. Journal of Coastal Research, Special Issue No. 98, pp. 376–380. Coconut Creek (Florida), ISSN 0749-0208.Cold chain marine logistics on fresh agriculture products takes a long time and has a degree of high risk because it is necessary to evaluate the logistics risk with scientific methods in a complex marine environment. This article analyzes the risk factors of cold chain marine logistics. The risk evaluation index system of cold chain marine logistics is established and a new method for logistics risk evaluation based on the Dempster-Shafer (D-S) evidence theory and the radial basis function (RBF) neural network is introduced. The evaluation data of experts is fused effectively by the D-S evidence theory. The risk level of logistics projects is identified by the RBF neural network. Then, 24 cold chain marine logistics projects were selected as samples to verify the effectiveness of this method and to prove that RBF is more superior to the back-propagation (BP) neural network for logistical risk evaluation. This method can overcome the shortcomings of expert evaluation data dispersion and the dependence on experts.