A genetic algorithm-based method for improving quality of travel time prediction intervals

Abstract The transportation literature is rich in the application of neural networks for travel time prediction. The uncertainty prevailing in operation of transportation systems, however, highly degrades prediction performance of neural networks. Prediction intervals for neural network outcomes can properly represent the uncertainty associated with the predictions. This paper studies an application of the delta technique for the construction of prediction intervals for bus and freeway travel times. The quality of these intervals strongly depends on the neural network structure and a training hyperparameter. A genetic algorithm–based method is developed that automates the neural network model selection and adjustment of the hyperparameter. Model selection and parameter adjustment is carried out through minimization of a prediction interval-based cost function, which depends on the width and coverage probability of constructed prediction intervals. Experiments conducted using the bus and freeway travel time datasets demonstrate the suitability of the proposed method for improving the quality of constructed prediction intervals in terms of their length and coverage probability.

[1]  Stefan Bornholdt,et al.  General asymmetric neural networks and structure design by genetic algorithms: a learning rule for temporal patterns , 1992, Proceedings of IEEE Systems Man and Cybernetics Conference - SMC.

[2]  Saeid Nahavandi,et al.  Constructing prediction intervals for neural network metamodels of complex systems , 2009, 2009 International Joint Conference on Neural Networks.

[3]  Guoqiang Peter Zhang,et al.  An investigation of model selection criteria for neural network time series forecasting , 2001, Eur. J. Oper. Res..

[4]  J. T. Hwang,et al.  Prediction Intervals for Artificial Neural Networks , 1997 .

[5]  Ruimin Li,et al.  Using Automatic Vehicle Identification Data to Gain Insight into Travel Time Variability and Its Causes , 2006 .

[6]  Lakhmi C. Jain,et al.  Automatic generation of a neural network architecture using evolutionary computation , 1995, Proceedings Electronic Technology Directions to the Year 2000.

[7]  Fred L. Mannering.  Poisson analysis of commuter flexibility in changing routes and departure times , 1989 .

[8]  Nirwan Ansari,et al.  Mini-Max Initialization for Function Approximation , 2004, Neurocomputing.

[9]  Xiaoyan Zhang,et al.  Short-term travel time prediction , 2003 .

[10]  Tom Heskes,et al.  Practical Confidence and Prediction Intervals , 1996, NIPS.

[11]  Xin Yao,et al.  Evolving artificial neural networks , 1999, Proc. IEEE.

[12]  Laurent Denant-Boèmont,et al.  Information value and sequential decision-making in a transport setting: an experimental study , 2003 .

[13]  van Lint,et al.  Reliable Real-Time Framework for Short-Term Freeway Travel Time Prediction , 2006 .

[14]  Dongjoo Park,et al.  Dynamic and stochastic shortest path in transportation networks with two components of travel time uncertainty , 2003 .

[15]  Saeid Nahavandi,et al.  Prediction Interval Construction and Optimization for Adaptive Neurofuzzy Inference Systems , 2011, IEEE Transactions on Fuzzy Systems.

[16]  Majid Sarvi,et al.  Journal of Intelligent Transportation Systems: Technology, Planning, and Operations , 2011 .

[17]  S. Roberts,et al.  Confidence Intervals and Prediction Intervals for Feed-Forward Neural Networks , 2001 .

[18]  J. W. C. van Lint,et al.  Online Learning Solutions for Freeway Travel Time Prediction , 2008, IEEE Transactions on Intelligent Transportation Systems.

[19]  Magne Jørgensen,et al.  An effort prediction interval approach based on the empirical distribution of previous estimation accuracy , 2003, Inf. Softw. Technol..

[20]  Hao Liu,et al.  Prediction of urban travel times with intersection delays , 2005, Proceedings. 2005 IEEE Intelligent Transportation Systems, 2005..

[21]  Kenneth A. Small,et al.  The Value of Time and Reliability: Measurement from a Value Pricing Experiment , 2001 .

[22]  Laurence R. Rilett,et al.  Improved Transit Signal Priority System for Networks with Nearside Bus Stops , 2005 .

[23]  S. C. Wirasinghe,et al.  Determination of the number and locations of time points in transit schedule design — Case of a single run , 1995, Ann. Oper. Res..

[24]  Graham Currie,et al.  Prediction intervals to account for uncertainties in neural network predictions: Methodology and application in bus travel time prediction , 2011, Eng. Appl. Artif. Intell..

[25]  David J. C. MacKay,et al.  The Evidence Framework Applied to Classification Networks , 1992, Neural Computation.

[26]  Haris N. Koutsopoulos,et al.  Nonlinear Kalman Filtering Algorithms for On-Line Calibration of Dynamic Traffic Assignment Models , 2006, IEEE Transactions on Intelligent Transportation Systems.

[27]  R. D. Veaux,et al.  Prediction intervals for neural networks via nonlinear regression , 1998 .

[28]  Tommy W. S. Chow,et al.  Feedforward networks training speed enhancement by optimal initialization of the synaptic coefficients , 2001, IEEE Trans. Neural Networks.

[29]  Richard Dybowski,et al.  Clinical applications of artificial neural networks: Theory , 2001 .

[30]  Léon Personnaz,et al.  Construction of confidence intervals for neural networks based on least squares estimation , 2000, Neural Networks.

[31]  L. B. Fu,et al.  Expected Shortest Paths in Dynamic and Stochastic Traf c Networks , 1998 .

[32]  Lance D. Chambers.  Practical handbook of genetic algorithms , 1995 .

[33]  D. E. Goldberg,et al.  Genetic Algorithm in Search , 1989 .

[34]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[35]  J. Bates,et al.  The valuation of reliability for personal travel , 2001 .

[36]  Abbas Khosravi.  Construction and optimisation of prediction intervals for neural network models , 2010 .

[37]  Goldberg,et al.  Genetic algorithms , 1993, Robust Control Systems with Genetic Algorithms.

[38]  Graham Currie,et al.  Using GPS Data to Gain Insight into Public Transport Travel Time Variability , 2010 .

[39]  Thong Ngee Goh,et al.  Neural network modeling with confidence bounds: a case study on the solder paste deposition process , 2001 .

[40]  David M Levinson,et al.  The Value of Advanced Traveler Information Systems for Route Choice , 2003 .

[41]  Steven I-Jy Chien,et al.  DYNAMIC TRAVEL TIME PREDICTION WITH REAL-TIME AND HISTORICAL DATA , 2003 .

[42]  Petros A. Ioannou,et al.  Real-Time Estimation of Travel Times Along the Arcs and Arrival Times at the Nodes of Dynamic Stochastic Networks , 2008, IEEE Transactions on Intelligent Transportation Systems.

[43]  Amir F. Atiya,et al.  Lower Upper Bound Estimation Method for Construction of Neural Network-Based Prediction Intervals , 2011, IEEE Transactions on Neural Networks.

[44]  Chandra R. Bhat,et al.  The Impact of Stop-Making and Travel Time Reliability on Commute Mode Choice , 2006 .

[45]  Graham Currie,et al.  Using SCATS data to predict bus travel time , 2009 .

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

[47]  E. Fernández,et al.  Finding Optimal Neural Network Architecture Using Genetic Algorithms , 2007 .

[48]  Laurence R. Rilett,et al.  Prediction Model of Bus Arrival Time for Real-Time Applications , 2005 .

[49]  Jay Lee,et al.  Feature signature prediction of a boring process using neural network modeling with confidence bounds , 2006 .

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

[51]  H. J. Van Zuylen,et al.  Accurate freeway travel time prediction with state-space neural networks under missing data , 2005 .

[52]  Saeid Nahavandi,et al.  A prediction interval-based approach to determine optimal structures of neural network metamodels , 2010, Expert Syst. Appl..

[53]  Saeid Nahavandi,et al.  Prediction Intervals to Account for Uncertainties in Travel Time Prediction , 2011, IEEE Transactions on Intelligent Transportation Systems.

[54]  Dongjoo Park,et al.  Direct Forecasting of Freeway Corridor Travel Times Using Spectral Basis Neural Networks , 2001 .

[55]  B. Efron.  Bootstrap Methods: Another Look at the Jackknife , 1979 .

[56]  Saeid Nahavandi,et al.  Construction of Optimal Prediction Intervals for Load Forecasting Problems , 2010, IEEE Transactions on Power Systems.

[57]  H. Liu,et al.  Travel time prediction for urban networks , 2008 .

[58]  Michael J Demetsky,et al.  MODELING SCHEDULE DEVIATIONS OF BUSES USING AUTOMATIC VEHICLE-LOCATION DATA AND ARTIFICIAL NEURAL NETWORKS , 1995 .

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

[60]  Tao Lu,et al.  Prediction of indoor temperature and relative humidity using neural network models: model comparison , 2009, Neural Computing and Applications.

[61]  Aidong Adam Ding,et al.  Backpropagation of pseudo-errors: neural networks that are adaptive to heterogeneous noise , 2003, IEEE Trans. Neural Networks.

[62]  Xin Yao,et al.  A new evolutionary system for evolving artificial neural networks , 1997, IEEE Trans. Neural Networks.