LIGHT RAIL PASSENGER DEMAND FORECASTING BY ARTIFICIAL NEURAL NETWORKS

被引：9
作者：
Celebi, Dilay [1 ]
Bolat, Bersam [1 ]
Bayraktar, Demet [1 ]
机构：
[1] Istanbul Tech Univ, TR-34367 Istanbul, Turkey
来源：
CIE: 2009 INTERNATIONAL CONFERENCE ON COMPUTERS AND INDUSTRIAL ENGINEERING, VOLS 1-3 | 2009年
关键词：
Forecasting; Light Railway Passenger; Artificial Neural Networks; TIME-SERIES;
D O I：
10.1109/ICCIE.2009.5223851
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
The success of strategic and detailed planning of public transportation highly depends on accurate demand information data. Short-term forecasting is the key to the success of transportation operations planning such as time-tabling and seat allocation. This study adopts neural networks to develop short-term passenger demand forecasting models to be used in operational management of light rail services. A multi-layer perceptron (MLP) model is preferred due to not only its simple architecture but also proven success of solving approximation problems. For eliminating the significant seasonality in time slots, each time slot is handled independent of the others, and an artificial neural network based on daily data is developed for each. Regarding to the 74 different time slots, 74 different neural networks are trained by history data. Three illustrative examples are demonstrated on one of the time slots and performance of the forecast models are evaluated based on mean square errors (MSE) and mean absolute percentage errors (MAPE).
引用
收藏
页码：239 / 243
页数：5
相关论文
共 11 条
[1]   A Lagrangian heuristic algorithm for a real-world train timetabling problem [J].
Caprara, A ;
Monaci, M ;
Toth, P ;
Guida, PL .
DISCRETE APPLIED MATHEMATICS, 2006, 154 (05) :738-753
[2]  
CHOW TWS, 1996, IEEE T POWER SYSTEMS, V11
[3]   Comparison of direct and iterative artificial neural network forecast approaches in multi-periodic time series forecasting [J].
Hamzacebi, Coskun ;
Akay, Diyar ;
Kutay, Fevzi .
EXPERT SYSTEMS WITH APPLICATIONS, 2009, 36 (02) :3839-3844
[4]   Improving artificial neural networks' performance in seasonal time series forecasting [J].
Hamzacebi, Coskun .
INFORMATION SCIENCES, 2008, 178 (23) :4550-4559
[5]   Analysis and modeling of multivariate chaotic time series based on neural network [J].
Han, M. ;
Wang, Y. .
EXPERT SYSTEMS WITH APPLICATIONS, 2009, 36 (02) :1280-1290
[6]   MULTILAYER FEEDFORWARD NETWORKS ARE UNIVERSAL APPROXIMATORS [J].
HORNIK, K ;
STINCHCOMBE, M ;
WHITE, H .
NEURAL NETWORKS, 1989, 2 (05) :359-366
[7]  
Schalkoff R J., 1997, Artificial Neural Networks
[8]   Neural network based temporal feature models for short-term railway passenger demand forecasting [J].
Tsai, Tsung-Hsien ;
Lee, Chi-Kang ;
Wei, Chien-Hung .
EXPERT SYSTEMS WITH APPLICATIONS, 2009, 36 (02) :3728-3736
[9]  
Wilson JH., 2007, Business forecasting, V5
[10]   Neural network forecasting for seasonal and trend time series [J].
Zhang, GP ;
Qi, M .
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2005, 160 (02) :501-514
12