Method for judging traffic congestion reasons based on characteristic significance

Abstract

The invention relates to a method for analyzing traffic congestion reasons and particularly relates to a method for judging traffic congestion reasons based on characteristic significance. The method is characterized by extracting traffic congestion levels and relevant characteristics of congestion point sections, obtaining a reason library of the congestion point sections based on a prediction residual integration characteristic importance assessment method and analyzing specific reasons of one congestion based on a association rule mining method; assessing characteristic importance by using multiple supervised learning methods including an Lasso model method, a random forest model and a linear model method, and weighting the characteristic importance assessed by three methods according to prediction errors. Through the characteristic importance analysis, more accurate and more robust results can be obtained, so that the accuracy of analysis of the traffic congestion reasons is ensured.

Description

[0001] Technical field: [0002] The invention relates to a method for analyzing the causes of traffic jams, in particular to a method for judging the causes of traffic jams based on feature importance. [0003] Background technique: [0004] The rapid development of my country's economy and society has accelerated the process of urbanization and motorization, which has led to a sharp increase in the level of road traffic. As of the end of 2012, my country has become the second largest country in the world in terms of car ownership; Compared with that, the growth of traffic supply capacity in Chinese cities is relatively slow. Traffic congestion has become a common problem, seriously affecting the development of urban economy, causing energy consumption, environmental pollution, and bringing a lot of inconvenience to people's life and work, increasing huge social costs, which is of great significance to the long-term development of society Very unfavorable. In recent years, th...

AI Technical Summary

Problems solved by technology

A lot of work has been carried out on the research and development of road travel time prediction, traffic flow prediction, traffic congestion evaluation, etc. for the data collected by the intelligent transportation system, such as traffic flow and checkpoint crossing, which facilitates the management of urban traffic, but it is difficult to alleviate or even cure There is still a big gap in traffic congestion. Clarifying the cause of congestion is a prerequisite for planning urban traffic and alleviating traffic congestion; most of the existing work analyzes from a macro perspective, or explores the mechanism of traffic congestion and optimization strategies based on simulation models, and lacks the use of large-scale historical data analysis. An automated method for the cause of a congestion point segment or a cause of a certain congestion

Images