Short-Term Traffic Flow Prediction Based on Parallel Quasi-Newton Neural Network

Identifying and predicting the situation of traffic flow play an important role in traveler information broadcast and real-time traffic control. In this paper, a short-term traffic flow prediction model based on the parallel self-scaling quasi-Newton (SSPQN) neural network is presented. In this method, a set of parallel search directions are generated at the beginning of each iteration. Each of these directions is selectively chosen from a representative class of quasi-Newton (QN) methods. Inexact line searches are then carried out to estimate the minimum point along each search direction. Experimental and analytical results demonstrate the feasibility of applying SSPQN to traffic flow prediction and prove that it can better satisfy real-time demand of traffic flow prediction.

[1]  Ji-xiang Yang,et al.  A Dish Parallel BP for Traffic Flow Forecasting , 2007 .

[2]  Billy M. Williams,et al.  MODELING AND FORECASTING VEHICULAR TRAFFIC FLOW AS A SEASONAL STOCHASTIC TIME SERIES PROCESS , 1999 .

[3]  Fei-Yue Wang,et al.  Short-term fuzzy traffic flow prediction using self-organizing TSK-type fuzzy neural network , 2007, 2007 IEEE International Conference on Vehicular Electronics and Safety.

[4]  Weili Li,et al.  Calculation and Analysis of Double-Fed VSCF Induction Generator Operating Performance , 2007 .

[5]  Paul Kang-Hoh Phua,et al.  Parallel nonlinear optimization techniques for training neural networks , 2003, IEEE Trans. Neural Networks.

[6]  Hao Ding,et al.  Traffic flow prediction based on generalized neural network , 2004, Proceedings. The 7th International IEEE Conference on Intelligent Transportation Systems (IEEE Cat. No.04TH8749).

[7]  Tan Guo.  Shortest Path Algorithm in Time-Dependent Networks , 2002 .

[8]  Brian Lee Smith,et al.  Forecasting freeway traffic flow for intelligent transportation systems application. , 1995 .

[9]  Tommy W. S. Chow,et al.  Self-Organizing and Self-Evolving Neurons: A New Neural Network for Optimization , 2007, IEEE Transactions on Neural Networks.

[10]  Steven Guan,et al.  Parallel growing and training of neural networks using output parallelism , 2002, IEEE Trans. Neural Networks.

[11]  Byung Ro Moon,et al.  A Hybrid Neurogenetic Approach for Stock Forecasting , 2007, IEEE Transactions on Neural Networks.