Daily ETC Traffic Flow Time Series Prediction Based on k-NN and BP Neural Network
Daily Electronic Toll Collection (ETC) traffic flow prediction is one of the fundamental processes in ETC management. The precise prediction of traffic flow provides instructions for transportation hub management solution planning and ETC lane constructio
- PDF / 649,958 Bytes
- 12 Pages / 439.37 x 666.142 pts Page_size
- 47 Downloads / 257 Views
School of Engineering Science, University of Chinese Academy of Sciences, Beijing, China [email protected], [email protected] 2 Beijing Sutong Technology Co., Ltd., Beijing, China [email protected]
Abstract. Daily Electronic Toll Collection (ETC) traffic flow prediction is one of the fundamental processes in ETC management. The precise prediction of traffic flow provides instructions for transportation hub management solution planning and ETC lane construction. At present, some of studies are proposed in forecasting traffic flow. However, most studies of model presentation are in the form of mathematical expressions, and it is difficult to describe the trend accurately. Therefore, an ETC traffic flow prediction model based on k nearest neighbor searching (k-NN) and Back Propagation (BP) neural network is proposed, which takes the effect of external factors like holiday, the free of highway and weather etc. into consideration. The traffic flow data of highway ETC lane somewhere is used for prediction. The prediction results indicate that the total average absolute relative error is 5.01 %. The accuracy suggests its advantage in traffic flow prediction and on site application. Keywords: ETC network
Traffic flow prediction Time series k-NN BP neural
1 Introduction With the rapid development of highway, ETC system, as one of the important subsystems of intelligent transportation system, through ETC technology applied in highway toll modular, effectively improves the traffic capacity of highway, alleviates queuing congestion of artificial charge phenomenon, and what’s more, reduces the energy consumption and environmental pollution problems too much. In order to further improve the quality of ETC service and provide instructions for transportation hub management solution planning and ETC lane construction, the research of ETC traffic flow prediction model has important theoretical significance and practical value. About traffic flow prediction, there have been many researches at home and abroad, and among them, time series model is one of the most mature prediction methods. The most important characteristics of time series model is that it acknowledges the dependency and the correlation between observed values, and it is a kind of dynamic model, so it can be applied to the dynamic prediction [1]. The traditional time series © Springer Science+Business Media Singapore 2016 W. Che et al. (Eds.): ICYCSEE 2016, Part II, CCIS 624, pp. 135–146, 2016. DOI: 10.1007/978-981-10-2098-8_17
136
Y. Chen et al.
analysis method is mainly statistical method, like Auto Regression Moving Average (ARMA) and Auto Regressive Integrated Moving Average Model (ARIMA). ARMA model is mainly suitable for linear stationary time series and ARIMA is for difference stationary time series. These are linear approaches. In 1984, Okutani and Stephanedes apply ARIMA to Urban Traffic Control System (UTCS). A lot of improvement models based on the traditional statistics time series prediction models have been proposed. In 2003, Williams and Hoel
Data Loading...
