Value of Time for Users of King Fahd Causeway Using Conventional and Artificial Intelligence Methodologies

Value-of-time (VOT) measures are valuable in a wide range of transport planning and policy implementation. Within the transport literature, econometric approach has widely been used to obtain this measure. Mostly, it is derived by estimating models from the logit family for mode choice and route choice behavior, where travel time and travel cost variables are part of the utility function, and the ratio of their estimated parameter is termed as VOT. This paper presents a detailed account on VOT estimation for different user classes. Furthermore, it introduces artificial intelligence (AI) and provides a framework through which VOT can be measured through this technique. The dataset used for the estimation of VOT is cross-sectional data collected from more than 500 individuals, who were users of the causeway and used different modes of transport for their journeys. VOT obtained from the logit approach is only based on the pooled dataset; however, AI technique in the form of artificial neural networks provides results for the different user classes in plausible terms and the values estimated are in line with the value obtained from the logit approach.

[1]  David A. Hensher,et al.  Measurement of Travel Time Values and Opportunity Cost from a Discrete-Choice Model , 1985 .

[2]  Wen-Hsien Ho,et al.  Comparison of Artificial Neural Network and Logistic Regression Models for Predicting In-Hospital Mortality after Primary Liver Cancer Surgery , 2012, PloS one.

[3]  Uneb Gazder,et al.  Effects of potential modes on mode choice behaviour for travel between Saudi Arabia and Bahrain , 2014 .

[4]  J. Bates.  Measuring Travel Time Values with a Discrete Choice Model: A Note , 1987 .

[5]  Staffan Algers,et al.  Mixed Logit Estimation of the Value of Travel Time , 1998 .

[6]  Georgios P. Kouretas,et al.  Modelling the choice of mode and estimation of the value of travel time savings for the case of the Rion-Antirion suspension bridge in Greece , 1997 .

[7]  Andrew Daly,et al.  Calculating Errors for Measures Derived from Choice Modeling Estimates , 2012 .

[8]  Hilmi Berk Celikoglu,et al.  Application of radial basis function and generalized regression neural networks in non-linear utility function specification for travel mode choice modelling , 2006, Math. Comput. Model..

[9]  Mark Wardman,et al.  Meta-analysis of UK values of travel time: An update , 2011 .

[10]  Hasan M. Al-Ahmadi.  Development of Intercity Mode Choice Models for Saudi Arabia , 2006 .

[11]  Kenneth A. Small,et al.  Valuation of Travel Time , 2012 .

[12]  D. McFadden,et al.  MIXED MNL MODELS FOR DISCRETE RESPONSE , 2000 .

[13]  G.E. Cantarella,et al.  Modeling transportation mode choice through artificial neural networks , 2003, Fourth International Symposium on Uncertainty Modeling and Analysis, 2003. ISUMA 2003..

[14]  Anil K. Jain,et al.  Artificial Neural Networks: A Tutorial , 1996, Computer.

[15]  K M Gwilliam,et al.  THE VALUE OF TIME IN ECONOMIC EVALUATION OF TRANSPORT PROJECTS: LESSONS FROM RECENT RESEARCH , 1996 .

[16]  Constantinos Antoniou,et al.  A Methodology for the Estimation of Value-of-Time Using State-of-the-Art Econometric Models , 2007 .

[17]  Giulio Erberto Cantarella,et al.  Multilayer Feedforward Networks for Transportation Mode Choice Analysis: An Analysis and a Comparison with Random Utility Models , 2005 .

[18]  Uneb Gazder,et al.  A new logit‐artificial neural network ensemble for mode choice modeling: a case study for border transport , 2015 .

[19]  Amalia Polydoropoulou,et al.  A National Passenger Mode Choice Model for the Greek Observatory , 2004 .

[20]  Andries P. Engelbrecht,et al.  Computational Intelligence: An Introduction , 2002 .

[21]  Haris N. Koutsopoulos,et al.  Modeling discrete choice behavior using concepts from fuzzy set theory, approximate reasoning and neural networks , 2003 .

[22]  A S Fowkes,et al.  Values of travel time savings in the UK: report to Department for Transport , 2003 .

[23]  J. Shires,et al.  An international meta-analysis of values of travel time savings. , 2009, Evaluation and program planning.

[24]  Mogens Fosgerau,et al.  The value of travel time variance , 2010 .

[25]  Eleni I. Vlahogianni,et al.  Statistical methods versus neural networks in transportation research: Differences, similarities and some insights , 2011 .

[26]  Saad N Aljarad,et al.  Modeling Saudi Arabia-Bahrain corridor mode choice , 1995 .

[27]  David A. Hensher,et al.  Hypothetical bias, choice experiments and willingness to pay , 2010 .

[28]  D. Agrawal,et al.  Market share forecasting: An empirical comparison of artificial neural networks and multinomial logit model , 1996 .

[29]  David A. Hensher,et al.  A comparison of the predictive potential of artificial neural networks and nested logit models for commuter mode choice , 1997 .