Performance evaluation model of cross border e-commerce supply chain based on LMBP feedback neural network

In recent years,with the support of national policies,Cross Border E-Commerce(CBEC)has developed rapidly.This business model not only brings significant benefits to the national economy,but also has many unique challenges,especially at the level of supply chain management.Therefore,to enable CBEC enterprises to develop sustainable supply chain,this study discusses the performance evaluation model of supply chain and proposes a CBEC Supply Chain Performance Evaluation Model(CBECSC-EM)based on the Levenberg–Marquardt Backpropagation(LMBP)algorithm.This experiment constructs performance evaluation indicators for the supply chain of CBEC enterprises.On this basis,the LMBP algorithm is introduced,and improved in the experiment to make the overall performance of the evaluation model more scientific and reasonable.In the verification set,the maximum F1 values of LMBP,DEA,SBM,and BP are 98.46%,93.78%,87.29%,and 78.95%,respectively.The MAPE value of LMBP model is 0.102%,which is lower than the other three methods(0.282%,0.343%,and 0.385%)selected in the experiment.The maximum standard deviation rates of importance and operability of the evaluation indexes are 0.1346 and 0.1405,respectively,and there is a significant consistency between the expert scores.Therefore,the LMBP algorithm has broad application prospects in supply chain performance evaluation of CBEC enterprises.

Design of similarity measure for discrete data and application to multi-dimension

Similarity measure design for discrete data group was proposed. Similarity measure design for continuous membership function was also carried out. Proposed similarity measures were designed based on fuzzy number and distance measure, and were proved. To calculate the degree of similarity of discrete data, relative degree between data and total distribution was obtained. Discrete data similarity measure was completed with combination of mentioned relative degrees. Power interconnected system with multi characteristics was considered to apply discrete similarity measure. Naturally, similarity measure was extended to multi-dimensional similarity measure case, and applied to bus clustering problem.

Intelligent Approach for Traffic Orchestration in SDVN Based on CMPR

The vehicle ad hoc network that has emerged in recent years was originally a branch of the mobile ad hoc network.With the drafting and gradual establishment of standards such as IEEE802.11p and IEEE1609,the vehicle ad hoc network has gradually become independent of the mobile ad hoc network.The Internet of Vehicles(Vehicular Ad Hoc Network,VANET)is a vehicle-mounted network that comprises vehicles and roadside basic units.This multi-hop hybrid wireless network is based on a vehicle-mounted self-organizing network.As compared to other wireless networks,such as mobile ad hoc networks,wireless sensor networks,wireless mesh networks,etc.,the Internet of Vehicles offers benefits such as a large network scale,limited network topology,and predictability of node movement.The paper elaborates on the Traffic Orchestration(TO)problems in the Software-Defined Vehicular Networks(SDVN).A succinct examination of the Software-defined networks(SDN)is provided along with the growing relevance of TO in SDVN.Considering the technology features of SDN,a modified TO method is proposed,which makes it possible to reduce time complexity in terms of a group of path creation while simultaneously reducing the time needed for path reconfiguration.A criterion for path choosing is proposed and justified,which makes it possible to optimize the load of transport network channels.Summing up,this paper justifies using multipath routing for TO.