Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Traffic flow forecasting method optimizing support vector regression by mixed artificial fish swarm algorithm

An artificial fish swarm algorithm and support vector regression technology, applied in traffic flow detection, calculation, special data processing applications, etc., can solve problems such as the inability to select optimal regression parameters, and the inability to obtain high prediction accuracy for traffic flow prediction applications.

Inactive Publication Date: 2015-05-06
DALIAN UNIV OF TECH
View PDF0 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0011] The technical problem to be solved by the present invention is the shortcoming of the influence of the setting of the step size factor in the initial parameters on the optimization performance when using the artificial fish swarm algorithm to optimize the support vector regression, and the optimal regression parameters cannot be selected, resulting in traffic flow forecasting applications can not get higher prediction accuracy

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 forecasting method optimizing support vector regression by mixed artificial fish swarm algorithm
  • Traffic flow forecasting method optimizing support vector regression by mixed artificial fish swarm algorithm
  • Traffic flow forecasting method optimizing support vector regression by mixed artificial fish swarm algorithm

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0047] The prediction accuracy of the method proposed in the present invention and the established traffic flow model is illustrated by examples. The example uses the actual traffic flow data collected by the California Highway Performance Evaluation System (PeMS) as the source of experimental data, and the data sample time interval is 5 minutes. The experiment selects the traffic flow from 6:00 am to 10:00 am in a day as the experimental data set. The experimental data uses the data of five sites in the context of working days. The training set of each site has 576 data, and the 48 data of the 25th day are predicted. The example uses historical time series traffic flow data to predict future traffic flow. let x i (t) is the traffic flow at time t on road section i, and the experiment uses the traffic flow x of the first five time periods i (t-5),x i (t-4),x i (t-3),x i (t-2) and x i (t-1) as input, x i (t) as the predicted output of the model.

[0048] The initial pa...

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 belongs to the field of artificial intelligence of a computer application technology, relates to an application of a swarm intelligence optimization method of an intelligence optimization algorithm, and particularly relates to a traffic flow forecasting method for an intelligent traffic system. A mixed artificial fish swarm optimization support vector regression method is applied to traffic flow forecasting. The construction process of the mixed optimization method is characterized in that a particle swarm algorithm is applied to improve the behavior selection of the artificial fish swarm algorithm aiming at the problem that the effect of a step-length factor in the artificial fish swarm algorithm on the algorithm is insufficient to reduce the step-length effect, then the support vector regression is optimized to conduct parameter selection to further build a mixed artificial fish swarm optimization traffic flow forecasting model. The method has the advantages of being capable of overcoming the shortcomings of the artificial fish swarm algorithm, acquires better combination regression parameters compared with the single swarm intelligence optimization algorithm application, and improves the traffic flow forecasting accuracy accordingly. The mixed optimization method is applicable to actual traffic flow predication and other engineering optimization.

Description

technical field [0001] The invention belongs to the artificial intelligence field of computer application technology, relates to the application of a group intelligence optimization method of an intelligent optimization algorithm, and particularly relates to a traffic flow prediction method in an intelligent transportation system. Aiming at the shortcomings of the artificial fish swarm algorithm in the swarm intelligence algorithm, which has many initial parameter settings and the influence of the step size factor setting on the optimization performance, it is proposed to use the particle swarm optimization algorithm to improve the artificial fish swarm algorithm to optimize the support vector regression for parameter selection, and establish The traffic flow forecasting model based on mixed artificial fish swarm optimization support vector regression improves the forecasting accuracy. Background technique [0002] Intelligent transportation system is an effective method to ...

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
IPC IPC(8): G08G1/01G06F19/00
Inventor 姚卫红方仁孝张旭东
Owner DALIAN UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com