A dynamic holding strategy in public transit systems with real-time information

Abstract Holding strategies are among the most commonly used operation control strategies in transit systems. In this paper, a dynamic holding strategy is developed, which consists of two major steps: (1) judging whether an early bus should be held, and (2) optimizing the holding times of the held bus. A model based on support vector machine (SVM), which contains four input variables (time-of-day, segment, the latest speed on the next segment, and the bus speed on the current segment) for forecasting the early bus departure times from the next stop is also developed. Then, in order to determine the optimal holding times, a model aiming to minimize the user costs is constructed and a genetic algorithm is used to optimize the holding times. Finally, the dynamic holding strategy proposed in this study is illustrated with the microscopic simulation model Paramics and some conclusions are drawn.

[1]  Vladimir Vapnik,et al.  An overview of statistical learning theory , 1999, IEEE Trans. Neural Networks.

[2]  Baozhen Yao,et al.  Bus Arrival Time Prediction Using Support Vector Machines , 2006, J. Intell. Transp. Syst..

[3]  Randolph W. Hall,et al.  Bus dispatching at timed transfer transit stations using bus tracking technology , 1999 .

[4]  Qing Liu,et al.  Real-Time Optimization Model for Dynamic Scheduling of Transit Operations , 2003 .

[5]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[6]  Steven I-Jy Chien,et al.  Dynamic Bus Arrival Time Prediction with Artificial Neural Networks , 2002 .

[7]  Lutgarde M. C. Buydens,et al.  Using support vector machines for time series prediction , 2003 .

[8]  Saeed Zolfaghari,et al.  A Model For Holding Strategy In Public Transit Systems With Real-Time Information , 2004 .

[9]  D. T. Lee,et al.  Travel-time prediction with support vector regression , 2004, IEEE Transactions on Intelligent Transportation Systems.

[10]  A. Barnett.  On Controlling Randomness in Transit Operations , 1974 .

[11]  G. F. Newell,et al.  Control Strategies for an Idealized Public Transportation System , 1972 .

[12]  Lai-Wan Chan,et al.  Support Vector Machine Regression for Volatile Stock Market Prediction , 2002, IDEAL.

[13]  S. Mohan,et al.  TRANSIT ROUTE NETWORK DESIGN USING FREQUENCY CODED GENETIC ALGORITHM , 2003 .

[14]  Francis Eng Hock Tay,et al.  Financial Forecasting Using Support Vector Machines , 2001, Neural Computing & Applications.

[15]  Allen Chen,et al.  Stochastic modeling and real-time prediction of incident effects on surface street traffic congestion , 2004 .

[16]  Francis Eng Hock Tay,et al.  Improved financial time series forecasting by combining Support Vector Machines with self-organizing feature map , 2001, Intell. Data Anal..

[17]  Francis Eng Hock Tay,et al.  Support vector machine with adaptive parameters in financial time series forecasting , 2003, IEEE Trans. Neural Networks.

[18]  David Koffman,et al.  A SIMULATION STUDY OF ALTERNATIVE REAL-TIME BUS HEADWAY CONTROL STRATEGIES , 1977 .

[19]  Mark D. Abkowitz,et al.  OPTIMAL CONTROL OF HEADWAY VARIATION ON TRANSIT ROUTES , 1986 .

[20]  A. Giralt,et al.  Head detection inside vehicles with a modified SVM for safer airbags , 2001, ITSC 2001. 2001 IEEE Intelligent Transportation Systems. Proceedings (Cat. No.01TH8585).

[21]  Xiaobo Liu,et al.  A Dynamic Bus‐Arrival Time Prediction Model Based on APC Data , 2004 .

[22]  Chuntian Cheng,et al.  Optimizing the distribution of shopping centers with parallel genetic algorithm , 2007, Eng. Appl. Artif. Intell..

[23]  Yi Zhang,et al.  Research on network-level traffic pattern recognition , 2002, Proceedings. The IEEE 5th International Conference on Intelligent Transportation Systems.

[24]  Shlomo Zilberstein,et al.  Optimal Composition of Real-Time Systems , 1996, Artif. Intell..

[25]  Donald J Dailey,et al.  Transit Vehicle Arrival Prediction: Algorithm and Large-Scale Implementation , 2001 .

[26]  Nigel H. M. Wilson,et al.  Modeling real-time control strategies in public transit operations , 1999 .

[27]  Y Ding,et al.  THE PREDICTION OF TRANSIT ARRIVAL TIMES USING LINK-BASED AND STOP-BASED ARTIFICIAL NEURAL NETWORKS , 2000 .

[28]  G. F Newell.  THE ROLLING HORIZON SCHEME OF TRAFFIC SIGNAL CONTROL , 1998 .

[29]  Yu Bin,et al.  Bus Arrival Time Prediction Using Support Vector Machines , 2006 .

[30]  M. Dessouky.  REAL-TIME CONTROL OF BUSES FOR SCHEDULE COORDINATION AT A TERMINAL March 7 , 2002 , 2003 .

[31]  B. Dong,et al.  Applying support vector machines to predict building energy consumption in tropical region , 2005 .

[32]  Shlomo Zilberstein,et al.  Monitoring and control of anytime algorithms: A dynamic programming approach , 2001, Artif. Intell..

[33]  Baher Abdulhai,et al.  Simulation of ITS on the Irvine FOT Area Using "Paramics 1.5" Scalable Microscopic Traffic Simulator: Phase I: Model Calibration and Validation , 1999 .

[34]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[35]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[36]  Gunnar Rätsch,et al.  Using support vector machines for time series prediction , 1999 .

[37]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[38]  Jan-Ming Ho,et al.  Travel-Time Prediction With Support , 2004 .

[39]  Gunnar Rätsch,et al.  Predicting Time Series with Support Vector Machines , 1997, ICANN.