RANGE OF THRESHOLDS FOR FUZZY INPUTS IN THE TRAFFIC FLOW BY BELLO SULEIMAN
- 1. RANGE OF THRESHOLDS FOR FUZZY INPUTS IN A TRAFFIC FLOW CIV 8331 (ADVANCED TRAFFIC ENGINEERING) DEPARTMENT OF CIVIL ENGINEERING, B.U.K KANO. BY BELLO SULEIMAN SPS/21/MCE/00034
- 2. INTRODUCTION WHAT DO WE UNDERSTAND BY THE WORD FUZZY IN GENERAL? The word fuzzy refers to something that is not clear or precise. HOW DOES FUZZY RELATE TO THE TRAFFIC FLOW? The term fuzzy in relation to the traffic flow refers to the application of fuzzy logic to analyze and manage traffic flow.
- 3. INTRODUCTION Continues FUZZY LOGIC IN TRAFFIC FLOW Fuzzy logic can be considered to be a generalization of a logic system that includes the class of all logic systems with truth values in the interval (0,1). Fuzzy inputs in traffic flow refer to the use of fuzzy sets and fuzzy logic rules to represent and process variables that are inherently uncertain or imprecise. For instance, traffic density can be represented as a fuzzy set with membership functions that define the degree to which a particular traffic density level belongs to categories such as low, medium, or high. Fuzzy logic rules can then be constructed to relate these fuzzy inputs to output variables, such as traffic signal timings or congestion levels.
- 4. INTRODUCTION Continues… RANGE OF THRESHOLDS FOR FUZZY TRAFFIC FLOW INPUTS Thresholds play a crucial role in fuzzy traffic flow modeling. They define the boundaries between different fuzzy sets, such as "low" and "high" traffic density or "slow" and "fast" vehicle speed. Thresholds are typically determined based on expert knowledge, empirical data, or a combination of both. The range of thresholds for fuzzy traffic flow inputs can vary depending on the specific application and the nature of the input data. For instance, thresholds for vehicle speed may range from 0 km/h to 200 km/h, while thresholds for traffic density may range from 0 vehicles/km to 100 vehicles/km. Determining the exact range of thresholds for fuzzy inputs in traffic flow can vary based on different research studies and the specific parameters they consider.
- 5. STATEMENT OF PROBLEM The selection of appropriate thresholds for fuzzy inputs in Fuzzy Inference Systems (FIS) remains a challenging task. The range of thresholds for fuzzy inputs significantly impacts the behavior of the FIS and its ability to accurately represent the underlying traffic conditions. Therefore, determining the optimal range of thresholds for fuzzy inputs in traffic flow is crucial for developing effective FIS-based traffic management systems. AIM AND OBJECTIVES The research aims to investigate the range of thresholds for fuzzy inputs in traffic flow modeling in a way to improve the accuracy of traffic flow models by capturing the uncertainty in traffic data.
- 6. The specific objectives includes: 1) To review the literature on fuzzy traffic flow modeling and identify the range of thresholds used for various traffic flow inputs. 2) To analyze the impact of different threshold values on the performance of fuzzy traffic flow models. 3) To develop guidelines for selecting appropriate thresholds for fuzzy traffic flow modeling.
- 7. LITERATURE REVIEW Traffic flow is a complex and dynamic system that is influenced by a number of factors, including the number of vehicles on the road, the speed of the vehicles, the road conditions, and the behavior of the drivers. Traditional traffic control systems have often been based on mathematical models that are not able to capture the full complexity of traffic flow. This has led to the development of fuzzy logic control systems, which are able to handle the uncertainty and imprecision that is inherent in traffic data. Traffic data often demonstrate obvious periodic patterns. Over a 24- hour period in a day, there is generally one or two peak hours with congested traffic condition. By considering periodic features in traffic data, we can not only gain better insights into the data but also improve prediction accuracy.
- 8. FUZZY LOGIC MODELLING AND CONTOL SYSTEMS Fuzzy logic is a mathematical framework that is designed to deal with uncertainty and imprecision. It is based on the idea that variables can have multiple values that are not necessarily crisp or exact. Fuzzy logic systems are typically composed of three main components. 1) A fuzzification module that converts crisp inputs into fuzzy sets. 2) A rule base that contains a set of fuzzy rules that map fuzzy inputs to fuzzy outputs. 3) A defuzzification module that converts fuzzy outputs into crisp outputs.
- 9. Taking a case study of the traffic light in the traffic flow; • At the fuzzification stage, the domain based on the data obtained from observation is created. Here is the table that shows the determination of the domain. Number of vehicle Number of vehicle is classified into 3 categories: quite (ranged until 25), normal (ranged from 20 to 45 vehicles) and crowded (ranged from 40).
- 10. Length of queue The length of queue is grouped into 4 categories: short, normal, long, and very long. Short is 150 meters and less, normal is ranged between 100 and 300 meters, long is between 230 to 450 meters and very long is from 400 and above. Width of road The width of road consists of 2 groups, i.e narrow (up to 9 meters) and wide (more than 9 meters). As some of the rules are as follows: a) IF number of vehicles is quite (small) and the queue length is short and the road width is narrow then we can say that the duration of green traffic light is short. b) IF number of vehicles is crowded and the queue length is very long and the road width is wide then duration of green light is long. c) IF number of vehicles is small and the queue length is normal and the road width is narrow then duration of green light is short. d) IF number of vehicles is small and the queue length is normal and the road width is wide then duration of green light is short. e) IF number of vehicles is small and the queue length is long and the road width is narrow then duration of green light is short.
- 11. CONCLUSION AND RECOMENDATIONS In summary, the fuzzy model describe the traffic operations using the linguistic terms and associated rules instead of deterministic mathematical functions. Conclusions Fuzzy logic has been shown to be an effective tool for modeling and controlling traffic flow. The range of thresholds for fuzzy inputs in traffic flow depends on the specific application. In general, the thresholds should be chosen to capture the range of possible values for the input variables. Recommendations 1) Use fuzzy logic to model and control traffic flow. 2) Choose the range of thresholds for fuzzy inputs carefully. 3) Test the fuzzy logic system to ensure that it behaves as expected.
- 12. REFERENCES Wang, J., & Qi, Y. (2010). Fuzzy logic based traffic signal control system. Transportation Research Part C: Emerging Technologies, 18(4), 647-659. Zhang, P., & Sun, C. (2011). Fuzzy logic based congestion detection and prediction for urban traffic management. Expert Systems with Applications, 38(10), 12539-12544. Yang, L., & Tang, S. (2012). Fuzzy logic based route planning algorithm for intelligent transportation systems. Mathematical Problems in Engineering, 2012. Kian, M., & Mirbaha, M. (2017). A fuzzy approach to traffic signal control in urban areas. Journal of Transportation Engineering, 143(10), 04017028. Zhang, S., Wang, Y., & Li, X. (2019). A fuzzy logic approach for adaptive traffic signal control based on real-time traffic data. IEEE Transactions on Intelligent Transportation Systems, 20(3), 1131-1142. Sun, Y., Zhang, C., & Wang, P. (2020). A novel fuzzy logic based approach for adaptive traffic signal control. Transportation Research Part C: Emerging Technologies, 120, 102808.