Traffic flow prediction method based on firefly algorithm and RBF neural network

A firefly algorithm and neural network technology, applied in the field of traffic flow prediction based on firefly algorithm and RBF neural network, can solve problems such as imperfect method, slow convergence speed of particle swarm algorithm, and premature genetic algorithm, so as to avoid premature convergence. , improve the global search ability, improve the effect of diversity

Inactive Publication Date: 2017-06-30
CHANGAN UNIV
View PDF2 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Although the above models have made some progress in traffic flow prediction and neural network training, the methods themselves still have imperfections, which are manifested in: for example, the premature phenomenon of genetic algorithm, and the slower convergence speed of particle swarm algorithm in the later stage of iteration. Wait a minute

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Traffic flow prediction method based on firefly algorithm and RBF neural network
  • Traffic flow prediction method based on firefly algorithm and RBF neural network
  • Traffic flow prediction method based on firefly algorithm and RBF neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] In this embodiment, in the training data, the division rule of the input data and the expected output data is: the obtained training data is [a1, a2, a3, a4, a5, a6...a(n-1), an], and the The first four data in the training data are used as input data, and the fifth data is used as the expected output. These four input data and one expected output are divided into a set of input data and expected output; that is, a1, a2, a3, a4 are input data , take a5 as the expected output data, a2, a3, a4, a5 as the input data, then a6 as the expected output data, a(n-4), a(n-3), a(n-2), a (n-1) is used as input data, an is output data, a(n-4), a(n-3), a(n-2), a(n-1) and an are divided into a set of input data and expected output;

Embodiment 2

[0062] On the basis of Example 1, the formula for calculating the relative brightness of firefly i relative to firefly j is:

[0063]

[0064] where r ij is the Euclidean distance between firefly i and firefly j in matrix F, I 0 is the brightness of firefly individual j, γ is the light intensity absorption coefficient; 1≤i≤s, 1≤j≤s; s represents the individual number of fireflies in the matrix F;

[0065] The formula for calculating relative attraction between two fireflies is:

[0066]

[0067] Among them, β(r ij ) represents the relative attraction between two fireflies, where r ij is the Euclidean distance between two fireflies, β 0 is the maximum attraction between two fireflies, β 0 =1, m takes 2; γ is the light intensity absorption coefficient.

Embodiment 3

[0069] The data in this embodiment comes from the traffic flow on an expressway in Stockton, San Joaquin County, California, USA. The expressway has three observation points, which are the traffic flow every five minutes.

[0070] The first column is the specific data collection time, which is counted every five minutes. The second column is the traffic flow of the first observation point, the third column is the traffic flow of the second observation point, the fourth column is the traffic flow of the third observation point, and the last column is the sum of the traffic flow of the three observation points .

[0071] Since the prediction method needs to use things with similar development status to predict the prediction object, this paper separates the traffic flow of weekdays and rest days for training and prediction. The data of April 2011 in the sample is selected as the experimental data. Select the data of the first three weeks as the training data, and the data of t...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention proposes a traffic flow prediction method based on firefly algorithm and RBF neural network. The method comprises: performing normalization to the sample data so that the input data and output data are on the same order of magnitude; initializing the firefly algorithm parameters; utilizing the random method to initialize the firefly populations and encoding each individual in the populations; using the firefly algorithm to train the RBF neural network to obtain the best individual in the populations; decoding the best individual in the populations to obtain the trained RBF neural network; and utilizing the trained RBF neural network to predict the traffic flow data sample. Compared with the traditional traffic flow prediction method, the method of the invention makes full use of the advantages of the firefly algorithm in the RBF neural network training so that the RBF network possesses a more accurate prediction capability, achieves even faster training efficiency and better generalization capability. The invention belongs to the traffic transportation information engineering technology field and can be used for the predictions of road traffic flows in an intelligent traffic system.

Description

technical field [0001] The invention relates to a traffic flow prediction method, in particular to a traffic flow prediction method based on firefly algorithm and RBF neural network. Background technique [0002] In order to alleviate urban traffic congestion and reduce the occurrence of traffic accidents, modern road traffic needs to be scientifically planned, managed, induced and controlled. In this case, Intelligent Transport System (Intelligent Transport System, ITS) came into being. In the intelligent transportation system, the prediction of traffic information plays a key role in traffic planning and traffic guidance, among which traffic flow prediction is an important part of traffic information prediction. [0003] Earlier traffic flow forecasting methods include: autoregressive method (AR), moving average model (MA), autoregressive moving average model (ARMA) and historical average model (HA). Relatively speaking, these methods have simple models, but they are only...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G08G1/01G06N3/06
CPCG06N3/061G08G1/0125
Inventor 段宗涛陈柘康军葛建东江华刘研吴晓声
Owner CHANGAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap