Abstract
As the passenger flow distribution center cooperating with various modes of transportation, the comprehensive passenger transport hub brings convenience to passengers. With the diversification of passenger travel modes, the passenger flow scale gradually increases, which brings significant challenges to the integrated passenger hub. Therefore, it is urgent to solve the problem of early warning and response to the future passenger flow to avoid congestion accidents. In this paper, the passenger flow GRNN prediction model is proposed, based on the K-means cluster algorithm, and an improved index named BWPs (Between-Within Proportion-Similarity) is proposed to improve the clustering effect of K-means so that the clustering effect of the new index is verified. In addition, the passenger flow data are studied and trained by combining with the GRNN neural network model based on parameter optimization (GA); the passenger flow prediction model is obtained. Finally, the passenger flow of Chengdu East Railway Station has been taken as an example, which is divided into 16 models, and each type of passenger flow is predicted, respectively. Compared with the traditional method, the results show that the model can predict the passenger flow with high accuracy.
Highlights
As an important form of the urban intelligent transportation system [1], the comprehensive passenger transport hub carries the passenger flow of various transportation modes and connects to an urban transportation network that carries out integration and conversion [2]
Graph convolutional neural network [18], which is popular in recent years, uses graph structure data to describe the spatiotemporal relationship of traffic flow to forecast the flow [19,20,21]
The passenger flow is classified by the K-means clustering model. en an improved BWPs index is used to improve the clustering effect. This GRNN neural network model is selected as the primary method of passenger flow prediction in the integrated passenger terminal, and SPREAD parameters will be adjusted by GA. e method used in our paper carried out the passenger flow prediction of different types, providing new theoretical support for the passenger flow prediction in the integrated passenger terminal
Summary
As an important form of the urban intelligent transportation system [1], the comprehensive passenger transport hub carries the passenger flow of various transportation modes and connects to an urban transportation network that carries out integration and conversion [2]. It is urgent to forecast the large passenger flow in the comprehensive passenger transport hub in advance, which can effectively increase the proportion of public transportation and promote the coordinated development of urban culture, economy, and environment. It is important to classify the passenger flow of the comprehensive passenger terminal and identify complex passenger flow types to construct the prediction model for different passenger flow types, which makes real-time prediction analysis. It provides a new idea and new method for predicting the passenger flow state of the comprehensive passenger terminal in the future. (1) To classify complex passenger flows, BWPs index is proposed to enhance the clustering effect of the Kmeans algorithm.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
