Road network evaluation method based on Bayesian model and triple standard deviation criterion

Abstract

The invention provides a road network evaluation method based on a Bayesian model and a triple standard deviation criterion. The method comprises the following steps: the traffic indexes in the same period of time of a certain area are counted, and the probability distribution obeyed by the traffic indexes is determined according to the statistical result; calculating parameters of the probabilitydistribution by using a Bayesian model; according to the Bayesian model and the criterion of triple standard deviation, the range threshold of traffic index is calculated, and whether the road network is abnormal or not is judged by comparing the traffic index data with the range threshold of traffic index. If you determine that that road network is abnormal, according to the criterion of triplestandard deviation to calculate the change value and the change rate of network traffic flow, and the change value and the change rate of the traffic congestion index. As an index for evaluating the influence degree of the abnormal event on the road network, the invention can effectively identify the abnormal event of various road networks and the influence degree of the abnormal event on the traffic flow and the traffic congestion of the road network.

Description

technical field [0001] The invention relates to the technical field of network evaluation, in particular to a road network evaluation method based on Bayesian model and triple standard deviation criterion. Background technique [0002] The road network is an important part of the national comprehensive transportation system. Various statutory holidays, major events and emergencies will have an impact on the road network. Effectively assessing the impact of various events on the road network can provide a scientific and reasonable decision-making basis for the traffic management department to formulate and optimize traffic control measures, and also provide a reference for travelers to arrange travel reasonably, thereby improving travel efficiency. [0003] In the existing technology, in terms of the impact of various events on the road network, the estimation of the spatial diffusion range of traffic events is mainly established by using decision tree theory, fuzzy thought ...

AI Technical Summary

Problems solved by technology

The disadvantages of these evaluation methods are: these evaluation methods mainly focus on the model estimation methods of the duration and diffusion range of traffic accidents and traffic congestion, the existing models require a large number of input variables, and in practical applications, it is difficult to obtain a more comprehensive The input data cannot meet the needs of real-time, rapid and comprehensive evaluation in emergencies

[0004] In addition, in the prior art, the real-time data is compared with the data under normal conditions to obtain the impact of the event on the road network. Although this evaluation method can discover and estimate the impact of the event on the road network, the normal data of the road network The determination method is to randomly select a normal data, or select the average value of historical normal data. This evaluation method does not consider the impact of data volatility, and the reliability of the analysis results is low.

Images