Day-to-day travel time perception modeling using an adaptive-network-based fuzzy inference system (ANFIS)

• Published in: EURO Journal on Transportation and Logistics Vol. 5; no. 1; pp. 25 - 52
• Main Authors: Khademi, Navid, Rajabi, Mojtaba, Mohaymany, Afshin S., Samadzad, Mahdi
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Elsevier B.V 01.03.2016; Springer Berlin Heidelberg; Elsevier Limited
• Subjects: 03E72 fuzzy set theory; 68T37 reasoning under uncertainty; 90B06 transportation, logistics; 91A26 rationality, learning; Adaptive systems; Artificial neural networks; Business and Management; Computer simulation; Day-to-day dynamics; Driver behavior; Drivers’ learning; Drivers’ perception updating; Fuzzy inference; Fuzzy logic; Fuzzy sets; Fuzzy systems; Inference; Intelligent transportation systems; Learning; Logistics; Management Science; Mathematics Subject Classification codes; Modelling; Operations Research; Operations Research/Decision Theory; Optimization; Perception; Qualitative reasoning; Research Paper; Travel; Travel demand; Travel time; Drivers’ perception updating; 91A26 rationality, learning; 03E72 fuzzy set theory; 68T37 reasoning under uncertainty; Day-to-day dynamics; 90B06 transportation, logistics; Artificial neural networks; Mathematics Subject Classification codes; Fuzzy inference; Drivers’ learning; Driver behavior
• ISSN: 2192-4376; 2192-4384
• DOI: 10.1007/s13676-014-0047-3

Travel time perception and learning play a central role in the modeling of day-to-day travel choice dynamics in traffic networks and have attracted the attention of many researchers, specifically for the analysis and operation of intelligent transportation systems and travel demand management scenarios. In this paper, a fuzzy learning model is proposed to capture the mechanism by which travelers update their travel time perceptions from one day to the next, taking into account their experienced travel times. To capture travelers’ mental representations of uncertain travel time involving imprecision and uncertainty, a combined artificial neural network and fuzzy logic (neuro-fuzzy) architecture called adaptive-network-based fuzzy inference system is employed. This framework, which utilizes a set of fuzzy if–then rules, can serve as a basis for modeling the qualitative sides of travelers’ knowledge and reasoning processes. From the output of this study, the results of our laboratory-like experiment provide a good fit to the stated data of travelers’ behavior, and may reflect the fact that the neuro-fuzzy approach can be considered a promising method in learning and perception updating models. Finally, the proposed learning model is embedded in a microscopic event-based simulation framework to evaluate its credibility within a day-to-day behavior of the traffic network. The results of the simulation, which converge to the equilibrium state of the test network, are finally presented, implying that the proposed perception updating model operates properly.