The growth of population has led to an increase in the number of motor vehicles. This increase has caused traffic congestions in metropolitan cities and higher fuel consumption besides other problems. A solution for dealing with the increase in the number of vehicles is creating more capacity for roads, parking lots, etc. thus aiming at controlling the traffi c problem. Providing proper approaches is on the condition that growth rate of vehicles in future years could be estimated by logical methods and so a relation between supply and demand at any time can be made. Considering this problem, in this paper one of the artifi cial intelligence parameters that is “Bayesian model” is introduced and by providing a model using this parameter, transportation situation (the ratio of capacity to demand) in future years can be forecasted. According to the results of this study, a model for supply and demand is suggested that can be used for traffi c design of different regions and sections. Additionally the necessary capacity for roads and other important parameters in transportation is estimated according to the estimated capacity.
The authors contributed to this work equally.
Albalate, D., Bel, G., (2009). Factors explaining urban transport
supply and demand in large European cities. Working papers of the Research Institute on Applied
Economics, Universitat de Barcelona. JEL codes: L91; L98; R41.
Allahverdizadeh, P., (2003). Methods of travel demand management and transportation system management, Secretariat of the Higher Council for Traffic Coordination in cities, Iran.
Allahverdizadeh, P., (2003). The regulations for travel demand reduction and transportation system management, Secretariat of the Higher Council for Traffi c Coordination in cities, Iran.
Al-Saba, T., El-Amin, I., (1999). Artifi cial neural networks as applied to long-term demand forecasting. Artifi cial Intelligence in engineering, Volume 13, Issue 2, Pages 189-197.
Khadaroo, J., Seetenah, B., (2008). The role of transport infrastructure in international tourism development: a gravity model approach. Tourism Management, Volume 29, Issue 5, Pages 831-84.
Matas, A., (2007). Demand and revenue implications of an integrated public transport policy: the case of Madrid. Journal of Transport Reviews, Pages 195-217.
Heckerman, D., (1997), Bayesian Networks for Data Mining. Data Mining and Knowledge Discovery, Volume 1, Issue 1, pp 79–119, Kluwer Academic Publishers.
C-SHRP594 Canadian Strategic Highway Research Program, (1995). Bayesian Modeling: Joint C-SHRP/Agency Application. Technical Brief No. 8, Ottawa. ISBN: 1-55187-024-X.
B. Korb, K., E. Nicholson, A., (2004), Bayesian Artifi cial Intelligence. Chapman & Hall/CRC, A CRC Press Company. ISBN: 1-58488-387-1.
Grossman, D., Domingos, P., (2004). Learning Bayesian Network Classifi ers by Maximizing Conditional Likelihood. Proceedings of the Twenty-First International Conference on Machine Learning, ICML, Page 46. Doi:10.1145/1015330.1015339.
Neufville, R., Clark J., and Field F., (2013). Introduction to Linear Programming, Engineering Systems Analysis for Design. Massachusetts Institute of Technology.