A Rough Neural Network-Based Approach to the Traffic Matching Identification for Logistics Hub

This paper aims to establish a traffic matching identification model combining the rough set theory and neural network theory. Through using the algorithm for attribute reduction of rough set theory, this paper investigates the key factors for input of BP neural network in those factors impacted on traffic demand and freight transport capacity outward and inward logistics hub, and sets up a relationship model for evaluating the matching level between traffic supply and demand based on the artificial neural network. Taking one logistics hub as an example, this paper explores the matching level between traffic supply and demand outside the logistics hub at different period of time and predicts the future traffic conditions outside logistics hub.