Neural network based temporal feature models for short-term railway passenger demand forecasting

Accurate forecasts are the base for correct decisions in revenue management. This paper addresses two novel neural network structures for short-term railway passenger demand forecasting. An idea to render information at suitable places rather than mixing all available information at the beginning in neural network operations is proposed. The first proposed network structure is multiple temporal units neural network (MTUNN), which deals with distinctive input information via designated connections in the network. The second proposed network structure is parallel ensemble neural network (PENN), which deals with different input information in several individual models. The outputs of the individual models are then integrated to obtain final forecasts. Conventional multi-layer perceptron (MLP) is also constructed for comparison purposes. The results show that both MTUNN and PENN outperform conventional MLP in the study. On average, MTUNN can obtain 8.1% improvement of MSE and 4.4% improvement of MAPE in comparison with MLP. PENN can achieve 10.5% improvement of MSE and 3.3% improvement of MAPE in comparison with MLP.

[1]  Michael J Demetsky,et al.  SHORT-TERM TRAFFIC FLOW PREDICTION: NEURAL NETWORK APPROACH , 1994 .

[2]  Jeffrey Sohl,et al.  An intelligent model selection and forecasting system , 1999 .

[3]  Billy M. Williams,et al.  Modeling and Forecasting Vehicular Traffic Flow as a Seasonal ARIMA Process: Theoretical Basis and Empirical Results , 2003, Journal of Transportation Engineering.

[4]  Thomas Whalen,et al.  A Weighted Window Approach to Neural Network Time Series Forecasting , 2004 .

[5]  Eleni I. Vlahogianni,et al.  Short‐term traffic forecasting: Overview of objectives and methods , 2004 .

[6]  Anthony Owen Lee,et al.  Airline reservations forecasting--probabilistic and statistical models of the booking process , 1990 .

[7]  S. Y. Yun,et al.  A Performance evaluation of neural network models in traffic volume forecasting , 1998 .

[8]  David West,et al.  Predicting WastewaterBOD Levels with Neural Network Time Series Models , 2004 .

[9]  Carlos E. Pedreira,et al.  Neural networks for short-term load forecasting: a review and evaluation , 2001 .

[10]  O. Nelles.  Nonlinear System Identification , 2001 .

[11]  J. Faraway,et al.  Time series forecasting with neural networks: a comparative study using the air line data , 2008 .

[12]  Duc Truong Pham,et al.  Identification of linear and nonlinear dynamic systems using recurrent neural networks , 1993, Artif. Intell. Eng..

[13]  J. Scott Armstrong,et al.  Principles of forecasting , 2001 .

[14]  Spyros Makridakis,et al.  The M3-Competition: results, conclusions and implications , 2000 .

[15]  Ramin Yasdi.  Prediction of Road Traffic using a Neural Network Approach , 1999, Neural Computing & Applications.

[16]  Kyungdoo “Ted” Nam,et al.  FORECASTING INTERNATIONAL AIRLINE PASSENGER TRAFFIC USING NEURAL NETWORKS , 1995 .

[17]  Francisco de A. T. de Carvalho,et al.  A Modal Symbolic Classifier for selecting time series models , 2004, Pattern Recognit. Lett..

[18]  Sung-Suk Kim.  Time-delay recurrent neural network for temporal correlations and prediction , 1998, Neurocomputing.

[19]  Hani S. Mahmassani,et al.  Estimation and Application of Dynamic Speed-Density Relations by Using Transfer Function Models , 2000 .

[20]  G. Peter Zhang.  Neural Networks in Business Forecasting , 2003 .

[21]  Ah Chung Tsoi,et al.  FIR and IIR Synapses, a New Neural Network Architecture for Time Series Modeling , 1991, Neural Computation.

[22]  Giovanni Soda,et al.  Local Feedback Multilayered Networks , 1992, Neural Computation.

[23]  Eleni I. Vlahogianni,et al.  Optimized and meta-optimized neural networks for short-term traffic flow prediction: A genetic approach , 2005 .

[24]  John W. Polak,et al.  Modeling Urban Link Travel Time with Inductive Loop Detector Data by Using the k-NN Method , 2005 .

[25]  A. D. Patton,et al.  Long-term electric load forecasting using a dynamic neural network architecture , 1993, Proceedings. Joint International Power Conference Athens Power Tech,.

[26]  Geoffrey E. Hinton,et al.  Phoneme recognition using time-delay neural networks , 1989, IEEE Trans. Acoust. Speech Signal Process..

[27]  Sherif Ishak,et al.  OPTIMIZATION OF DYNAMIC NEURAL NETWORKS PERFORMANCE FOR SHORT-TERM TRAFFIC PREDICTION , 2003 .

[28]  Sheryl E. Kimes,et al.  Restaurant revenue management: Could it work? , 2005 .

[29]  Chris Chatfield,et al.  Time series forecasting with neural networks: a comparative study using the air line data , 2008 .

[30]  John McFadden,et al.  Application of Artificial Neural Networks to Predict Speeds on Two-Lane Rural Highways , 2001 .

[31]  Mark Dougherty,et al.  A REVIEW OF NEURAL NETWORKS APPLIED TO TRANSPORT , 1995 .

[32]  Stephen D. Clark,et al.  Traffic Prediction Using Multivariate Nonparametric Regression , 2003 .