Traffic condition information prediction method based on improved decision tree algorithm

Abstract

The invention discloses a traffic condition information prediction method based on an improved decision tree algorithm. The method comprises: determining an attribute of analyzing road connectivity based on an influence factor of road connectivity; acquiring road data, preprocessing data, calculating information entropy, and calculating the attribute entropy of each attribute, calculating the correlation function value of each attribute based on a correlation function, and calculating the weight value of each attribute based on the correlation function value of each attribute; calculating theinformation gain of each attribute based on the information entropy, the attribute entropy of each attribute, and the weight value of each attribute, arranging the information gain of each attribute in an ascending order to construct a decision tree, and predicting the traffic condition according to the decision tree. The method constructs the decision tree by calculating the correlation functionvalue of the attributes and the attribute weight value obtained by the information entropy expansion operation, can overcome a problem that a traditional ID3 algorithm tends to select an element withmore possible values as a high weight attribute, and uses the constructed decision tree to predict the degree of road congestion improvement in the next time period.

Description

technical field [0001] The invention relates to the technical field of decision tree algorithms and road traffic flow models, in particular to a method for predicting road condition information based on improved decision tree algorithms. Background technique [0002] With the advancement of global urbanization, the number of motor vehicles in cities is increasing year by year. As of the end of June 2016, the number of motor vehicles in Beijing has reached 5.44 million, ranking first in the country. For mega-cities like Beijing, Tokyo, and New York, this figure will continue to rise over time. A huge number of motor vehicles will not only cause traffic congestion, but also air pollution, energy waste and other problems, hindering urban development and reducing people's living standards. Among the world's 200 large cities (population greater than 800,000), Beijing's traffic congestion ranks 15th. Congested traffic conditions not only bring extra time consumption to people's...

AI Technical Summary

Problems solved by technology

In these two algorithms, the sensitivity calculation will derive the corresponding neural network according to the input attribute value and train it, which will greatly increase the complexity of the algorithm, and the algorithm efficiency is not high; the analysis using the joint density function is only applicable to discrete The data is not necessarily compatible with the data of the present invention

Images