Prediction intervals to account for uncertainties in neural network predictions: Methodology and application in bus travel time prediction

Neural networks have been employed in a multitude of transportation engineering applications because of their powerful capabilities to replicate patterns in field data. Predictions are always subject to uncertainty arising from two sources: model structure and training data. For each prediction point, the former can be quantified by a confidence interval, whereas total prediction uncertainty can be represented by constructing a prediction interval. While confidence intervals are well known in the transportation engineering context, very little attention has been paid to construction of prediction intervals for neural networks. The proposed methodology in this paper provides a foundation for constructing prediction intervals for neural networks and quantifying the extent that each source of uncertainty contributes to total prediction uncertainty. The application of the proposed methodology to predict bus travel time over four bus route sections in Melbourne, Australia, leads to quantitative decomposition of total prediction uncertainty into the component sources. Overall, the results demonstrate the capability of the proposed method to provide robust prediction intervals.

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

[2]  Hojjat Adeli,et al.  Neural network model for rapid forecasting of freeway link travel time , 2003 .

[3]  A. Weigend,et al.  Estimating the mean and variance of the target probability distribution , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

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

[5]  Abbas Khosravi,et al.  Integrating a Feature Selection Algorithm for Classification of Voltage Sags Originated in Transmission and Distribution Networks , 2007, CCIA.

[6]  Hans van Lint,et al.  Reliable travel time prediction for freeways , 2004 .

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

[8]  I. Jolliffe Principal Component Analysis , 2002 .

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

[10]  Taehyung Park,et al.  A Bayesian Approach for Estimating Link Travel Time on Urban Arterial Road Network , 2004, ICCSA.

[11]  Jidong Yang,et al.  Modeling crack deterioration of flexible pavements : Comparison of recurrent Markov chains and artificial neural networks , 2006 .

[12]  Mukesh Khare,et al.  ARTIFICIAL NEURAL NETWORK BASED LINE SOURCE MODELS FOR VEHICULAR EXHAUST EMISSION PREDICTIONS OF AN URBAN ROADWAY , 2004 .

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

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

[15]  Yuanchang Xie,et al.  Predicting motor vehicle collisions using Bayesian neural network models: an empirical analysis. , 2007, Accident; analysis and prevention.

[16]  Geoffrey E. Hinton Learning Translation Invariant Recognition in Massively Parallel Networks , 1987, PARLE.

[17]  Xiaobo Liu,et al.  Using automatic passenger counter data in bus arrival time prediction , 2007 .

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

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

[20]  Bharat A. Jain,et al.  Performance Evaluation of Neural Network Decision Models , 1997, J. Manag. Inf. Syst..

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

[22]  Yafeng Yin,et al.  Prediction of hourly air pollutant concentrations near urban arterials using artificial neural network approach , 2009 .

[23]  Hussein Dia,et al.  Modelling drivers' compliance and route choice behaviour in response to travel information , 2007 .

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

[25]  B. Efron The jackknife, the bootstrap, and other resampling plans , 1987 .

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

[27]  H. J. Van Zuylen,et al.  Bayesian committee of neural networks to predict travel times with confidence intervals , 2009 .

[28]  R. Jeong,et al.  Bus arrival time prediction using artificial neural network model , 2004, Proceedings. The 7th International IEEE Conference on Intelligent Transportation Systems (IEEE Cat. No.04TH8749).

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

[30]  Frans Tillema,et al.  Comparison of Neural Networks and Gravity Models in Trip Distribution , 2006, Comput. Aided Civ. Infrastructure Eng..

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

[32]  Peter J. Angeline,et al.  An evolutionary algorithm that constructs recurrent neural networks , 1994, IEEE Trans. Neural Networks.

[33]  Hussein Dia,et al.  Development and evaluation of neural network freeway incident detection models using field data , 1997 .

[34]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[36]  Shih-Miao Chin,et al.  USING NEURAL NETWORKS TO SYNTHESIZE ORIGIN-DESTINATION FLOWS IN A TRAFFIC CIRCLE , 1994 .

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

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

[39]  Seung-Hwan Lee,et al.  Development of degree of saturation estimation models for adaptive signal systems , 2002 .

[40]  Richard Bellman,et al.  Adaptive Control Processes: A Guided Tour , 1961, The Mathematical Gazette.

[41]  Alan F. Murray,et al.  Confidence estimation methods for neural networks : a practical comparison , 2001, ESANN.

[42]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[43]  Andrew H. Sung,et al.  Feature Selection for Intrusion Detection with Neural Networks and Support Vector Machines , 2003 .

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

[45]  César Hervás-Martínez,et al.  COVNET: a cooperative coevolutionary model for evolving artificial neural networks , 2003, IEEE Trans. Neural Networks.

[46]  Jaydev Sharma,et al.  Comparison of feature selection techniques for ANN-based voltage estimation , 2000 .