Intersection traffic state identification method based on PSO-ELM algorithm

Abstract

The invention provides an intersection traffic state identification method based on a PSO-ELM algorithm. The method comprises the following steps: acquiring a historical traffic flow data set of a labeled intersection connection road section; learning the historical traffic flow data set by using an extreme learning machine (ELM) algorithm, optimizing parameters of the ELM by using a particle swarm optimization (PSO) algorithm, setting a fitness function of the PSO as a mean square error (MSE) of an ELM predicted value and an actual value, taking a parameter at the optimal fitness value as a final parameter of the ELM, and taking a final ELM model as an intersection traffic state recognition model; and identifying the traffic state of the intersection to be identified by using the intersection traffic state identification model. According to the method, the PSO-ELM algorithm is applied to the field of traffic state recognition, and the traffic state of the intersection is recognized by using the traffic state of the intersection connecting road, so that the formulation of traffic control measures of the intersection connecting road is facilitated.

Description

technical field [0001] The invention relates to the technical field of intersection traffic state identification, in particular to an intersection traffic state identification method based on a PSO-ELM algorithm. Background technique [0002] As a branch of intelligent transportation system, traffic state discrimination is the basic condition for traffic control and guidance, and plays an important role in traffic intelligent management and dynamic control. Many traffic practices show that in urban road traffic, the traffic state can be divided into different types, and these types always appear repeatedly. Different control strategies can be designed for different traffic conditions. If the traffic operation status can be identified, traffic control and guidance can be carried out according to the strategies formulated in advance to avoid or alleviate traffic congestion and improve the operating efficiency of the city. [0003] In the urban road network, due to the role o...

AI Technical Summary

Problems solved by technology

[0004] ELM (Extreme Learning Machine, extreme learning machine) algorithm is widely used in the identification of traffic status, but ELM itself has some defects: (1) the initial weight vector w i and the bias b of the hidden nodes i , the output matrix H in the least squares solution is calculated by these two parameters, and the selection of its value is directly related to the quality of the recognition effect; (2) the traditional ELM algorithm randomly generates the initial weight matrix and bias

Images