Traffic accident prediction method based on hybrid geographically weighted regression

Abstract

The invention belongs to the technical field of traffic safety, and particularly relates to a traffic accident prediction method based on hybrid geographically weighted regression, which comprises thefollowing steps: step 1, dividing a spatial research area of a traffic accident, and collecting influence factor data; 2, explaining variables through multiple colinearity verification, and deletingunreasonable explaining variables; step 3, constructing a space weight function as a Gaussian function and a double square function; 4, determining that the bandwidth selection type is a fixed bandwidth and an adaptive bandwidth, and determining that a bandwidth optimization criterion is a corrected red pool information criterion; step 5, constructing and determining an optimal geographically weighted Poisson regression model; step 6, respectively bringing in explanatory variables as global variables to construct a hybrid geographically weighted Poisson regression model to perform a comparisontest; and step 7, constructing and determining an optimal hybrid geographically weighted Poisson regression model. The invention provides a traffic accident prediction method based on hybrid geographically weighted regression, which is sufficient in spatial heterogeneity consideration and high in prediction model precision.

Description

technical field [0001] The invention belongs to the technical field of traffic safety, in particular to a traffic accident prediction method based on mixed geographic weighted regression. Background technique [0002] For a long time, traffic accidents have brought great harm to people's life and property safety. According to the World Health Organization, 1.35 million people died in traffic accidents worldwide in 2016. Research on the prediction of traffic accidents has always been the focus and difficulty of traffic safety researchers in various countries. Most of the traditional traffic accident prediction methods use accident history data and influencing factor data, based on multiple linear regression, neural network and other theoretical models to predict, but this method ignores the spatial heterogeneity of traffic accident influencing factors, that is, in different urban spaces There are differences in the attribute values ​​of a variable within a region. The prio...

AI Technical Summary

Problems solved by technology

[0004] 2. The Chinese invention patent application with the publication number CN201810352052.3 discloses "a traffic accident prediction method based on the unbiased non-homogeneous gray model and the Markov model", and the Chinese invention patent application with the publication number CN201810320886.6 discloses "a A Traffic Accident Prediction Method Based on PCA and BP Neural Network", these methods mainly propose a traffic accident prediction method that does not consider the spatial effect of traffic accident influencing factors, and does not involve the spatial heterogeneity of traffic accident influencing factors

Images