Skip to main content
SpringerLink
Log in

A review of feedforward neural networks in transportation research

Übersicht über vorausführende neurale Netzwerke in der Fortbewegungsforschung

  • Reviewed Original Papers
  • Published:
e&i Elektrotechnik und Informationstechnik Aims and scope Submit manuscript

Abstract

The paper reports applications of neural networks in transportation research and shows the author’s specific experience and applications of neural networks for many fields concerning transport and traffic theory. By using the interpolation capability of neural networks it is possible to extract relationships present in data according to particular conditions and to the features of used variables. A comparison between applications and a discussion about problems and difficulties arising with the use of feedforward neural networks are carried out. The aim is to underline that some results are obtainable exactly by using neural network capabilities and can be translated to other fields without great difficulties.

Zusammenfassung

Dieser Bericht bezieht sich auf Wendungen neuraler Netzwerke auf dem Gebiet der Verkehrsforschung und zeigt die spezifische Erfahrung des Autors und Anwendungen neuraler Netzwerke auf vielen Gebieten, die sich mit transport- und Verkehrstheorie beschäftigen. Durch Verwendung der Interpolationskapazität neuraler Netzwerke ist es möglich, bestimmten Bedingungen und den Kennzeichen verwendeter Variabler entsprechende Datenbeziehungen zu extrahieren. Es wird ein Vergleich zwischen Anwendungen angestellt, und es findet eine Diskussion über Probleme und Schwierigkeiten statt, die mit der Verwendung vorwärtsgerichteter neuraler Netzwerke verbunden sind. Ziel dabei ist die Unterstreichung der Tatsache, dass einige Ergebnisse genau durch die Verwendung neuraler Netzwerkskapazitäten gezeitigt werden und ohne große Schwierigkeiten auf andere Gebiete übertragen werden können.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Arganese, S., Florio, L., Mussone, L.: An user behaviour model for the choice of public transport mode (in italian). Paesaggio Urbano (1998), 3–4, pp. 67–71.

    Google Scholar 

  2. Belgaroui, B., Blosseville, J. M.: Techniques neuronales appliques au trafic routier. Recherche Transports Securitè, RTS 36 (1992), pp. 35–46.

    Google Scholar 

  3. Burattini, E., De Gregorio, M.: A neural network to evaluate congestion levels. In: Mussone, L., Marescotti, L. (eds.): Urban traffic: control possibility, tools and their effectiveness. CNR, PFT2, II Rostro, Milano. 1998.

  4. Burke, L., Ignizio, J. P.: Neural networks and operational research: an overview. Computer & Operational Research 19 (1992), 3/4, pp. 179–189.

    Article  MATH  Google Scholar 

  5. Chen, H., Mussone, L., Montgomery, F., Grant-Muller, S.: Effects of missing data on neural network performance in forecasting flow. ICTTS 98. Beijing, China. 1998.

  6. Cybenko, G.: Approximation by superpositions of sigmoidal functions. Mathematics Control, Signals and Systems 2 (1989), pp. 303–314.

    Article  MATH  MathSciNet  Google Scholar 

  7. Dochy, T., Danech-Pajouh, M.: Prévision à court terme du trafic routier par réseau de neurons. Recherche Transports Sécurité, RTS. 42 (1994), pp. 35–44.

    Google Scholar 

  8. Dougherty, M., Kirby, H., Boyle, R.: The use of neural networks to recognize and predict traffic congestion. Int. Congress on Transport Research. Lyon. 1992.

  9. Dougherty, M., Joint, M.: A behavioural model of driver route choice using neural networks. International Conference on Artificial Intelligence Applications in Transportation Engineering. San Buenaventura, California. 1992, pp. 99–110.

  10. Dougherty, M., Kirby, H., Boyle, R.: The use of neural networks to recognize and predict traffic congestion. Traffic Engineering and Control (1993), pp. 311–314.

  11. Dougherty, M.: A review of neural networks applied to transport. Transpn. Res.-C 3. 4 (1995), pp. 247–260.

    Article  Google Scholar 

  12. Dougherty, M.: Guest applications of neural networks in transportation. Transpn. Res.-C 5. 5 (1997), pp. 225–257.

    Article  Google Scholar 

  13. Efron, B.: The Jacknife, the Bootstrap and other resampling plans. Society for Industrial and Applied Mathematics. 1982.

  14. Fischer, M. M., Gopal, S.: Artificial neural networks: a new approach to modelling interregional telecommunication flows. Journal of Regional Science 4 (1994), 34, pp. 503–527.

    Article  Google Scholar 

  15. Florio, L., Mussone, L.: Neural network models for classification and forecasting of highway traffic flow stability. Control Engineering Practice 4 (1996), No. 2, pp. 153–164.

    Article  Google Scholar 

  16. Florio, L., Mussone, L.: Freeway section capacity for different meteorological conditions using neural networks. 7th WCTR, World Conference on Transport Research, Vol. 2., pp. 3–18. Amsterdam: Elsevier Science. 1996.

    Google Scholar 

  17. Florio, L., Mussone, L.: Lane occupation models in motorway sections before a toll-gate station. 8th IFAC 97. Creta. 1997, pp. 1472–1477.

  18. Florio, L., Mussone, L.: A model to analyse VMS effects on flow in motorway. 8th WCTR. Antwerp. 1998.

  19. Girosi, F., Poggio, T.: Networks for learning. In Antognetti P., Milutinovič, V. (eds.): Neural networks: concepts, applications and implementation. New York: Prentice Hall, Inc., pp. 110–154.

  20. Hornik, K., Stinchombe, M., White, H.: Universal approximation of an unknown mapping and its derivative using multilayer feedforward networks. Neural Networks 3 (1990), pp. 551–560.

    Article  Google Scholar 

  21. Hornik, K.: Approximation capabilities of multilayer feedforward networks. Neural Networks 4 (1991), pp. 251–257.

    Article  Google Scholar 

  22. Leshno, M., Lin, V. Ya., Pinkus, A., Schocken, S.: Multilayer feedforward networks with a non polynomial activation function can approximate any function. Neural Networks 6 (1993), pp. 861–867.

    Article  Google Scholar 

  23. Marescotti, L., Mussone, L.: A flow saturation model for signalized intersections. Urban Transport and the environment. Lisbon, Portugal: WIT Press. 1998, pp. 63–72.

    Google Scholar 

  24. Masters, T.: Practical neural network recipes in C++. New York: Academic Press, Inc. 1993.

    Google Scholar 

  25. Moseholme, L., Silva, J., Larson, T.: Forecasting carbon monoxide concentrations near a sheltered intersection using video traffic surveillance and neural networks. Transpn. Res.-D. Vol. 1. 1 (1996), pp. 15–28.

    Article  Google Scholar 

  26. Mussone, L.: Artificial neural networks in transport (in italian). Trasporti & Trazione 2 (1994), pp. 56–72.

    Google Scholar 

  27. Mussone, L.: Artificial intelligence techniques to predict urban traffic indicators. AIENG 97. Capri. 1997.

  28. Mussone, L., Reitani, G.: A road safety analysis in urban environments. ISATA 98. Düsseldorf. 1998, pp. 389–396.

  29. Mussone, L., Rinelli, S.: An accident analysis for urban vehicular flow, URBAN 96. Barcelona. 1996.

  30. Mussone, L., Rinelli, S.: An analysis of urban accidents in Milan by AI techniques, 8th WCTR. Antwerp, Belgium. 1998.

  31. Mussone, L., Reitani, G., Rinelli, S.: Estimating the accident probability of a vehicular flow by means of an artificial neural network. Environment and Planning B: Planning and Design. Pion Limited. London. 23 (1996), pp. 667–675.

    Google Scholar 

  32. Mussone, L., Reitani, G., Rinelli, S.: Definition and building of a database for studying driver behaviour in urban vehicular flows. 7th WCTR, World Conference on Transport Research. Vol. 2., pp. 241–256. Amsterdam: Elsevier Science. 1996.

  33. Mussone, L., Reitani, G., Rinelli, S.: A cross-sectional analysis of vehicular accidents to work out a risk exposure model. ISATA 96. Florence. 1996, pp. 213–220.

  34. Mussone, L., Reitani, G., Rinelli, S.: Effect of road peculiarities and length on accident risk exposure. ISATA 97. Firenze. 1997, pp. 201–208.

  35. Mussone, L., Chen, H., Montgomery, F.: Calculating PCU values in motorway environments — a method using the MLP. EIS International ICSC Symposium on Engineering of Intelligent Systems. Tenerife, Spain. 1998.

  36. Mussone, L., Reitani, G., Rinelli, S.: A methodology to modelling driver behaviour in signalised urban intersections using artificial neural networks. In: Himanen, V., Nijkamp, P., Reggiani, A., Raitio, J., (eds.): Neural networks in transport applications, Ashgate. 1998. pp. 171–189.

  37. Nanda, R., Kikuchi, S.: Fuzzy regression based trip generation model by using of neural networks. Int. Congress on Transport Research. Abs. No. 563. Lyon. 1992.

  38. Pant, P. D.: Neural network for gap acceptance at stop-controlled intersection. Journal of Transportation Engineering 120 (1994), No. 3.

    Google Scholar 

  39. Ritchie, S. G., Cheu, R. L., Recker, W. W.: Freeway incident detection using artificial neural networks. Int. Conference on Artificial Intelligence Applications in Transportation Engineering. San Buenaventura, California. 1992, pp. 215–231.

  40. Ritchie, S. G., Cheu, R. L.: Simulation of freeway incident detection using artificial neural networks. Transpn. Res.-C 1, 3 (1993) pp. 203–217.

    Google Scholar 

  41. Rodrigue, J.: Parallel modelling and neural networks: an overview for transportation/land use systems. Transpn. Res.-C5, 5 (1997), pp. 259–271.

    Article  Google Scholar 

  42. Sartori, M. A., Antsaklis, P. J.: Implementation of learning control systems using neural networks. IEEE Control Systems 1992, pp. 49–57.

  43. Sjöberg, J., Hjalmarsson, H., Ljung, L.: Neural networks in system identification. In: From identification to learning Course. Milan, Italy. NATO ASI and CNR. 1994.

  44. Weiss, S. M., Kulikowski, C. A.: Computer Systems that learn. San Mateo, California: Morgan Kaufmann Pub. 1991.

    Google Scholar 

  45. Yang, H., Kitamura, R., Jovanis, P. P., Vaughn, K. M., Abdel-Aty, M. A.: Exploration of route choice behavior with advanced traveler information using neural network concepts. Transportation 20 (1993), No. 2, pp. 199–223.

    Article  Google Scholar 

  46. Yang, B., Qiao, F.: Neural network approach to classification of traffic flow states. Journal of Transportation Eng. 124 (1998), No. 6, pp. 521–525.

    Article  Google Scholar 

  47. Zhang, H. M., Ritchie, S. G.: Freeway ramp metering using artificial neural networks. Transpn. Res.-C 5. 5 (1997) pp. 273–286.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. DSTM, Politecnico di Milano, Pza L. Da Vinci 32, I-20133, Italy

    L. Mussone

Authors
  1. L. Mussone
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Mussone, L. A review of feedforward neural networks in transportation research. Elektrotech. Inftech. 116, 360–365 (1999). https://doi.org/10.1007/BF03159196

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF03159196

Keywords

Schlüsselwörter

Search

Navigation