Research on the Nonlinear Traffic Flow Time Sequence Prediction Model

Zhu Hai Feng

Abstract


This paper proposes a non-linear traffic flow time sequence prediction model aiming at the periodic and stochastic characteristics of the traffic flow. First, one-dimension traffic flow time sequence data are transformed to multi-dimension time sequence. Then the RBF neural network which has strong nonlinear prediction capability is applied to model. Finally the simulation experiment is used to testify to the model. The results of the simulation prove the prediction accuracy of the model with RBF neural traffic flow time sequence prediction model is much higher than the traditional one and the prediction results can be utilized in the practical traffic management. The results show that the nonlinear traffic flow time series forecasting model with nonlinear, non-stationary characteristics of different period randomness, chaos and uncertainty. The results of this study to forecast short-term traffic flow have certain theoretical and practical significance.


Full Text:

PDF


DOI: http://doi.org/10.11591/ijeecs.v12.i9.pp7014-7020

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Indonesian Journal of Electrical Engineering and Computer Science (IJEECS)
p-ISSN: 2502-4752, e-ISSN: 2502-4760
This journal is published by the Institute of Advanced Engineering and Science (IAES) in collaboration with Intelektual Pustaka Media Utama (IPMU).

shopify stats IJEECS visitor statistics