Developing a Modal Split Model Using Fuzzy Inference System in Ramadi City


Several different deterministic and probabilistic mathematical approaches have been used to develop modal split models. The data collected by a questionnaire survey approach is frequently associated with subjectivity, imprecision, and ambiguity. additionally, several linguistic terms are used to express some of the transportation planning variables. This can be solved by modeling mode choosing behavior with artificial intelligence techniques such as fuzzy logic. In this research, Ramadi city in Iraq has been selected as a study area. For the purpose of obtaining data, the study area was divided into traffic analysis zones (TAZ). The total number of traffic zones was set as 28 traffic zones, 22 were internal traffic zones and 6 external traffic zones. Field surveys and questionnaires are used to collect data on traffic, land use, and socioeconomic characteristics factors (age, gender, vehicle ownership, family income, trip purpose, trip origin and destination, trip time, waiting duration, duration inside mode, trip origin and destination, trip cost, and type of mode used for transport). The results showed that the modal split models based on the fuzzy inference system can deal with linguistic variables as well as address uncertainty and subjectivity and they gave very good prediction accuracy for future prediction. Fuzzy inference system proved that all factors affected the mode choice with a very strong correlation coefficient (R) equal to 93.1 for general trips but when the results were compared with multiple linear regression model found that the correlation coefficient (R) equal to 28.9 for general trips and the most influential factors on the mode choice are car ownership, age and trip cost. Thus, it can be concluded that fuzzy logic models were more capable of capturing and integrating human knowledge in mode selection behavior. In addition, this study will help decision-makers to plan transportation policies for Ramadi city.