Urban traffic flow forecasting using Gauss-SVR with cat mapping, cloud model and PSO hybrid algorithm

Authors:
Ming-Wei Li;Wei-Chiang Hong;Hai-Gui Kang
Affiliations:
Faculty of infrastructure Engineering, Dalian University of Technology, Dalian, Liaoning116024, China;Department of Information Management, Oriental Institute of Technology, 58, Sec. 2 Sichuan Rd., Panchiao, 220, Taipei, Taiwan;Faculty of infrastructure Engineering, Dalian University of Technology, Dalian, Liaoning116024, China
Venue:
Neurocomputing
Year:
2013

Citing 10
Cited 3

New Support Vector Algorithms

Neural Computation
A robust shot transition detection method based on support vector machine in compressed domain

Pattern Recognition Letters
A hybrid genetic algorithm and particle swarm optimization for multimodal functions

Applied Soft Computing
Real-Time Freeway Traffic State Estimation Based on Extended Kalman Filter: A Case Study

Transportation Science
A hybrid-forecasting model based on Gaussian support vector machine and chaotic particle swarm optimization

Expert Systems with Applications: An International Journal
Traffic Flow Forecasting Algorithm Using Simulated Annealing Genetic BP Network

ICMTMA '10 Proceedings of the 2010 International Conference on Measuring Technology and Mechatronics Automation - Volume 03
Short-term traffic flow parameters prediction based on multi-scale analysis and artificial neural network

CAR'10 Proceedings of the 2nd international Asia conference on Informatics in control, automation and robotics - Volume 1
Traffic flow forecasting by seasonal SVR with chaotic simulated annealing algorithm

Neurocomputing
An Approach to Estimating Product Design Time Based on Fuzzy -Support Vector Machine

IEEE Transactions on Neural Networks
An evolutionary algorithm that constructs recurrent neural networks

IEEE Transactions on Neural Networks

Hybrid self-adaptive learning based particle swarm optimization and support vector regression model for grade estimation

Neurocomputing
Sales forecasting of computer products based on variable selection scheme and support vector regression

Neurocomputing
Fuzzy artificial neural network p, d, q model for incomplete financial time series forecasting

Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology

Quantified Score

Hi-index	0.01

Visualization

Abstract

In order to improve forecasting accuracy of urban traffic flow, this paper applies support vector regression (SVR) model with Gauss loss function (namely Gauss-SVR) to forecast urban traffic flow. By using the input historical flow data as the validation data, the Gauss-SVR model is dedicated to reduce the random error of the traffic flow data sequence. The chaotic cloud particle swarm optimization algorithm (CCPSO) is then proposed, based on cat chaotic mapping and cloud model, to optimize the hyper parameters of the Gauss-SVR model. Finally, the Gauss-SVR model with CCPSO is established to conduct the urban traffic flow forecasting. Numerical example results have proved that the proposed model has received better forecasting performance compared to existing alternative models. Thus, the proposed model has the feasibility and the availability in urban traffic flow forecasting fields.