Intelligent Urban Rail Transit Based on Big Data Analysis and Application

Abstract

Abstract It is an intelligent information system developed in recent years to manage and control the traffic system with modern and intelligent technology. It plays an important role in alleviating traffic congestion, reducing traffic accidents and reducing energy consumption. This paper mainly studies the smart urban rail transit based on big data analysis and application. According to the characteristics of complex spatial correlation and time dependence of passenger flow, a deep learning model-temporal attention network is proposed, and multi-input multi-output multi-step forecasting strategy is used to solve the problem of error accumulation in long-term forecasting of passenger flow. Experimental results show that the prediction performance of our method in each time step is better than the traditional linear model, machine learning model and deep learning model, and the error is reduced by 7%-9% compared with the benchmark model. Moreover, the multi-input multi-output multi-step prediction strategy can effectively reduce the error accumulation of the traditional iteration strategy.