Xiaoyan Shen
School of Automobile, Chang�an University, Xi�an, Shaanxi, 710061, China
Lihua Wang
School of Automobile, Chang�an University, Xi�an, Shaanxi, 710061, China
Haoxue Liu
School of Automobile, Chang�an University, Xi�an, Shaanxi, 710061, China
Jingshuai Yang
School of Automobile, Chang�an University, Xi�an, Shaanxi, 710061, China
ABSTRACT
The percentage of mainline traffic entering is a critical factor for the estimation of the economical benefit and the operation assessment of an existing rest area. This study presents a BP neural network model to predict the percent of mainline traffic entering the rest area for solving the limitations existing in other related methods, including the single factor considered and poor precision. First, seven factors that are considered to affect rest area usage are used as input variables of network and the predicted percent of mainline traffic entering is defined as the output variable. Second, we set up different network structures with different number of neurons in the hidden layer and MSE of results as stopping criteria for getting the best fitting model. Then a network with 7 neurons in input layer, 12 neurons in hidden layer and 1 neuron in output layer, is constructed for the prediction of the percentage entering. The testing result show that the average predicted values of the testing samples have only 1.14% error and the case study also indicates that the predicted value of the model has high reliability.
PDF References Citation
How to cite this article
Xiaoyan Shen, Lihua Wang, Haoxue Liu and Jingshuai Yang, 2013. Estimation of the Percentage of Mainline Traffic Entering Rest Area Based on Bp Neural Network. Journal of Applied Sciences, 13: 2632-2638.
DOI: 10.3923/jas.2013.2632.2638
URL: https://scialert.net/abstract/?doi=jas.2013.2632.2638
DOI: 10.3923/jas.2013.2632.2638
URL: https://scialert.net/abstract/?doi=jas.2013.2632.2638
REFERENCES
- Cui, H.J. and K.J. Liu, 2008. A new determine method on pause rate in expressway service area based on vehicle continuous travel time. J. Hebei Univ. Technol., 37: 100-104.
Direct Link - James, M., S. Arockiasamy and P.R.J. Thangaiah, 2013. Face recognition in compressed domain by applying wavelet transform and feature vector optimization. J. Applied Sci., 13: 451-457.
CrossRefDirect Link - Valipour, M., M.E. Banihabib and S.M.R. Behbahani, 2012. Monthly inflow forecasting using autoregressive artificial neural network. J. Applied Sci., 12: 2139-2147.
CrossRef