Method for predicting city traffic accidents based on time-space distribution characteristics

Abstract

The invention relates to a method for predicting city traffic accidents based on time-space distribution characteristics. The method comprises: first, in combination of the case information and the space information, creating a case space database and performing pretreatment to the data; then, based on surface area statistics, analyzing the traffic accidents' time-space distribution characteristics; using the global and local self-correlation method to realize the analyzing of the aggregate state; based on the case happening point data, analyzing the traffic accidents' time-space distribution characteristics; through the hierarchical clustering analysis, expressing the distribution rule of the cases hierarchically; through the nuclear density estimation method, expressing the continuous changes and accurate gathering center of the traffic accidents' happening distribution; and finally, utilizing the BP neural network prediction algorithm, using the time-space distribution characteristics of the already happened cases to predict the time-space distribution areas of traffic accidents in the future. According to the invention, in combination with the time-space distribution and through the utilization of big date excavation BP neural network prediction algorithm and the time-space distribution characteristics of the already happened cases to predict the time-space distribution areas of traffic accidents in the future, it is possible to increase the precision, the timeliness and reduce the manual cost.

Description

technical field [0001] The invention relates to the field of traffic accident analysis, in particular to a method for predicting urban traffic accidents based on time-space distribution characteristics. Background technique [0002] At present, foreign scholars have conducted in-depth research on the geography of traffic accident cases, and have achieved fruitful results in the formation mechanism and characteristics of the temporal and spatial distribution of traffic accidents. The current main technology for the temporal and spatial distribution of traffic accident cases is to use the correlation analysis method to study. This method needs to limit several specific factors in advance, by continuously collecting accident data of a specific road section, artificially fitting the correlation between various factors, and then analyzing the obtained data to predict the distribution of each road section in different time and space. [0003] The traditional method has the follow...

AI Technical Summary

Problems solved by technology

[0003] The traditional method has the following deficiencies: first, the factors in the correlation fitting are limited after processing the data, which may lead to limitations in the results; second, the traditional fitting data correlation results cannot independently change factors However, the real-time performance is relatively low; finally, the prediction of traditional technology is artificially obtained, with serious subjectivity and large errors.

Although the heat map method adopts the histogram and the parallel coordinate method to reflect the change of the number of cases over time and highlight the trend of change to a certain extent, this method is more concerned with the two aspects of spatial aggregation and change over time put together

In essence, it is still the result of spatial analysis plus the trend of time changes, which still cannot solve the core problem of the study of the distribution characteristics of traffic accident cases in time and space

Images