Developing precise travel behavior models is important for estimating traffic demand and, consequently, for planning transportation systems. A study is presented that suggests a hybrid model that combines a stochastic model with a neuro-fuzzy inference system. The model is applied for estimating traveler behavior in the context of the problem of transport mode choice. Particularly, the multinomial logit model with neuro-fuzzy utility functions is developed to investigate shopping traveler preferences regarding the modes of bus, subway, and automobile. The model is evaluated by comparing its results with the results of a multinomial logit model. Moreover, the probabilities of selecting a transport mode obtained by applying the two models are compared with the actual transport mode choices, which show better performance of the proposed model. In addition, the model demonstrates good performance by estimating a large number of right choices during the validation process. A sensitivity analysis demonstrates the influence of time variations of mode subway on the probabilities of selecting a transport mode. The analysis highlights different behaviors of the models caused by the different utility functions. The results confirm that the proposed model can describe uncertainties regarding traveler decisions on the time of transport mode choice.
Get full access to this article
View all access options for this article.
References
1.
ZadehL. A.Semantic Inference from Fuzzy Premises. Presented at 6th International Symposium on Multiple-Value Logic, Logan, Utah, 1976.
2.
ZadehL. A.Commonsense Reasoning Based on Fuzzy Logic. Presented at 18th Conference on Winter Simulation, Washington, D.C., 1986.
3.
LiD. H., and CellierF. E.. Fuzzy Measures in Inductive Reasoning. Presented at 22nd Conference on Winter Simulation, New Orleans, La., 1990.
4.
TeodorovicD.Fuzzy Logic Systems for Transportation Engineering: The State of the Art.Transportation Research A: Policy and Practice, Vol. 33, 1999, pp. 337–364.
5.
LeeB., FujiwaraA., SugieY., and NamgungM.. A Sequential Method for Combining Random Utility Model and Fuzzy Inference Model.Journal of Advanced Computational Intelligence and Intelligent Informatics, Vol. 3, 2003, pp. 117–121.
6.
AkiyamaT., TakabaT., and MizutaniK.. Soft Computing Approaches in Activity Based Analysis. Presented at International Conference of Modeling and Management in Transportation, Nagoya, Japan, 1999.
7.
KagayaS., UchidaK., AbreuV. C., YamashitaY., and WiegangL.. A Method for Trip Distribution Estimation Using Fuzzy Logic. Presented at 1st International Conference on Soft Computing and 3rd International Symposium on Advanced Intelligent Systems, Tsukuba, Japan, 2002.
8.
HennV.Fuzzy Route Choice Model for Traffic Assignment.Fuzzy Sets and Systems, Vol. 116, 2000, pp. 77–101.
9.
InokuchiH., and KawakamiS.. Development of the Fuzzy Traffic Assignment Model. Presented at First International Conference on Soft Computing, Nagoya, Japan, 2002.
10.
MizutaniK., and AkiyamaT.. Construction of Modal Choice Model with Descriptive Utility Function Using Fuzzy Reasoning. Presented at Joint 9th IFSA Congress and 20th NAFIPS International Congress, Vancouver, Canada, 2001.
11.
ParkB.Hybrid Neuro-Fuzzy Application in Short-Term Freeway Traffic Volume Forecasting. In Transportation Research Record: Journal of the Transportation Research Board, No. 1802, TRB, National Research Council, Washington, D.C., 2002, pp. 190–196.
12.
PursulaM., and PikkarainenP.. A Neural Network Approach to Vehicle Classification with Double Induction Loops.Proc., 17th ARRB Conference, Part 4: New Technologies, Local Government, Bridges, Queensland, Australia, 1994, pp. 29–44.
13.
AkiyamaT., and TsuboiH.. Description of Route Choice Behavior by Fuzzy Neural Network. Presented at Mini EURO Conference: Fuzzy Sets in Traffic and Transport Systems, Bruges, Belgium, 1997.
14.
JangJ. S. R.ANFIS: Adaptive Neuro-Fuzzy Inference Systems. In Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence (JangJ. S. R., SunC. T., and MizutaniE., eds.), Prentice-Hall, Englewood Cliffs, N.J., 1997.
15.
JangJ. S. R., and MizutaniE.. Unsupervised Learning and Other Neural Networks. In Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence (JangJ. S. R., SunC. T., and MizutaniE., eds.), Prentice-Hall, Englewood Cliffs, N.J., 1997.
16.
SunC. T., and ChiuH. J.. Evolutionary Neuro-Fuzzy Modeling. In Fuzzy Theory Systems: Techniques and Applications (LeondesC. T., ed.), Academic Press, New York, 1999.
17.
Ben-AkivaM. E., and LermanS. R.. Discrete Choice Analysis: Theory and Application to Travel Demand.MIT Press, Cambridge, Mass., 1985.
18.
YagerR. R., and FilevD. P.. Essentials of Fuzzy Modeling and Control.John Wiley & Sons, New York, 1994.
19.
StopherP. R.Survey and Sampling Techniques. In Handbook of Transport Modelling (HensherD. A., and ButtonK. J., eds.), Pergamon, Oxford, United Kingdom,2000.
20.
Theory and Practice of Disaggregate Behavioral Models.Japan Society for Civil Engineers, Tokyo, 1995 (in Japanese).
21.
WardmanM.Stated Preference Methods and Travel Demand Forecasting: An Examination of the Scale Factor Problem.Transportation Research A: Policy and Practice, Vol. 25, 1991, pp. 79–89.
22.
ArndK., and AxhausenK. W.. The Reliability of the Transportation System and Its Influence on the Choice Behavior. Presented at Second Swiss Transport Research Conference, Monte Verita/Ascona, Switzerland, 2002.
23.
TaylorD., and HaniM.. Analysis of Stated Preferences for Intermodal Bicycle-Transit Interfaces.Transportation Research C: Emerging Technologies, Vol. 5, 1996, pp. 86–95.
24.
BradleyM. A., and DalyA. J.. Estimation of Logit Choice Models Using Mixed Stated-Preference and Revealed-Preference Information. In Understanding Travel Behavior in an Era of Change, Pergamon, Oxford, United Kingdom, 1991, pp. 209–231.
25.
Abdel'atyM. A., KitamuraR., and JovanisP. P.. Using Stated Preference Data for Studying the Effect of Advanced Traffic Information on Drivers’ Route Choice.Transportation Research C: Emerging Technologies, Vol. 5, 1997, pp. 39–50.
JangJ. S. R.Fuzzy Inference Systems. In Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence (JangJ. S. R., SunC. T., and MizutaniE., eds.), Prentice Hall, Englewood Cliffs, N.J.,1997.
28.
ChiuS.Fuzzy Model Identification Based on Cluster Estimation.Journal of Intelligent and Fuzzy Systems, Vol. 2, No. 3, 1994, pp. 267–278.
29.
SunC. T.Rulebase Structure Identification.Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence (JangJ. S. R., SunC. T., and MizutaniE., eds.). Prentice Hall, Englewood Cliffs, N.J., 1997.
30.
PedryczW., and OliveiraJ. V. D.. Optimization Techniques in the Design of Fuzzy Models. In Fuzzy Theory Systems: Techniques and Applications (LeondesC. T., ed.), Academic Press, New York, 1999.
