Traffic Flow Analytics and Prediction using Nonlinear Autoregressive Network with Exogenous Inputs Technique

Main Article Content

พีรพล พุทธเวชมงคล
วิมล แสนอุ้ม
ชฎาพร เกตุมณี


This paper proposes the traffic flow analytics and prediction using nonlinear autoregressive network with exogenous inputs technique (NARX). The learning of neural network is divided into 2 configuration parts. The configuration delays are 2 and 4 to compare the results and find optimal configuration value for create NARX model using the simulate data. The chaotic simulate data set are generate by Mackey glass equation. Then analyze data set using NARX model. This able to developed to application or web application used in Bangkok.


Download data is not yet available.

Article Details

Research Article


[1] “INRIX 2016 Global Traffic Scorecard,” INRIX. [Online]. Available: traffic-score card/. [Accessed: 23-Mar-2017]
[2] J. D. Farmer and J. J. Sidorowich, “Predicting chaotic time series,” Physical review letters, vol. 59, no. 8, pp. 845–848, Aug. 1987.
[3] E. Diaconescu, “The Use of NARX Neural Networks to Predict Chaotic Time Series,” WSEAS Transactions on computer research, vol. 3, no. 3, pp. 182–191, Mar. 2008.
[4] L. Banjanović-Mehmedović, I. Butigan, M. Kantardžić, and S. Kasapović, “Prediction of cooperative platooning maneuvers using NARX neural network,” in 2016 International Conference on Smart Systems and Technologies (SST), 2016, pp. 287–292.
[5] A. Thakur, A. Tiwari, S. Kumar, A. Jain, and J. Singh, “NARX based forecasting of petrol prices,” in 2016 5th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO), 2016, pp. 610–614.
[6] L. Zhang et al., “NARX models for predicting power consumption of a horizontal axis wind turbine,” in 2016 UKACC 11th International Conference on Control (CONTROL), 2016, pp. 1–5.
[7] A. G. R. Vaz, B. Elsinga, W. G. J. H. M. van Sark, and M. C. Brito, “An artificial neural network to assess the impact of neighbouring photovoltaic systems in power forecasting in Utrecht, the Netherlands,” Renewable Energy, vol. 85, pp. 631–641, Jan. 2016.
[8] Y. Chunshan and L. Xiaofeng, “Study and application of data mining and NARX neural networks in load forecasting,” in 2015 4th International Conference on Computer Science and Network Technology (ICCSNT), 2015, vol. 01, pp. 360–364.
[9] S.-Y. Yun, S. Namkoong, J.-H. Rho, S.-W. Shin, and J.-U. Choi, “A Performance evaluation of neural network models in traffic volume forecasting,” Mathematical and Computer Modelling, vol. 27, no. 9-11, pp. 293–310, May 1998.