Submitted Successfully!
To reward your contribution, here is a gift for you: A free trial for our video production service.
Thank you for your contribution! You can also upload a video entry or images related to this topic.
Version Summary Created by Modification Content Size Created at Operation
1 -- 1717 2023-07-14 16:59:29 |
2 update references and layout -3 word(s) 1714 2023-07-17 04:13:14 |

Video Upload Options

Do you have a full video?


Are you sure to Delete?
If you have any further questions, please contact Encyclopedia Editorial Office.
Erdinç, G.; Colombaroni, C.; Fusco, G. Two-Stage Fuzzy Traffic Congestion Detector. Encyclopedia. Available online: (accessed on 18 April 2024).
Erdinç G, Colombaroni C, Fusco G. Two-Stage Fuzzy Traffic Congestion Detector. Encyclopedia. Available at: Accessed April 18, 2024.
Erdinç, Gizem, Chiara Colombaroni, Gaetano Fusco. "Two-Stage Fuzzy Traffic Congestion Detector" Encyclopedia, (accessed April 18, 2024).
Erdinç, G., Colombaroni, C., & Fusco, G. (2023, July 14). Two-Stage Fuzzy Traffic Congestion Detector. In Encyclopedia.
Erdinç, Gizem, et al. "Two-Stage Fuzzy Traffic Congestion Detector." Encyclopedia. Web. 14 July, 2023.
Two-Stage Fuzzy Traffic Congestion Detector

This research presents a two-stage fuzzy-logic application based on the Mamdani inference method to classify the observed road traffic conditions. It was tested using real data extracted from the Padua–Venice motorway in Italy, which contains a dense monitoring network that provides continuous measurements of flow, occupancy, and speed. The data collected indicate that the traffic flow characteristics of the road network are highly perturbed in oversaturated conditions, suggesting that a fuzzy approach might be more convenient than a deterministic one.

traffic state identification fuzzy logic congestion level

1. Introduction

Estimating traffic conditions has become one of the major problems in transportation engineering. If reliable information on traffic congestion is available, adequate and effective traffic control can be implemented to make traffic flow smoothly and improve the efficiency of surface transportation systems. Furthermore, drivers can be informed of states of congestion downstream, enabling them to change their route or simply drive more cautiously. Nevertheless, traffic congestion is a vague concept and there is still no universally accepted definition. It has either been defined as a state of traffic flow characterized by a high level of density and a low level of speed, as in [1], or it is defined on the basis of time, for example, as a function of delay [2], or, as in [3], as the additional time spent in the network when a vehicle is unable to drive at the free-flow speed level. On the other hand, congestion has been associated with insufficient road space, as an example of a situation occurring when the demand exceeds the supply on a road [4], or when vehicles obstruct each other because of an unbalanced speed–flow relation [5]. Finally, congestion has been defined in more than 10 different ways that are related to the demand-to-capacity ratio, delay and cost [6].
In addition to the definition of the concept of congestion, the thresholds of congestion states also vary between countries and societies. For example, according to the European DATEX II standards [7], congestion is defined at certain percentages of the road’s free-flow speed level. In Asia, if the average level of speed drops to 19 mph for more than 2 h in a day and 10 days in a month, the Korea Highway Corporation accepts that congestion is occurring. This level is 25 mph in Japan [8]. Additionally, in Japan, speed thresholds are also used to define the level of congestion [8]. According to the work of Skabardonis et al. [9] and Kwon et al. [10], congestion occurs when the speed is at a level of 60 mph on urban freeways, while the threshold is 45 mph in Minnesota [11]. In addition to these studies, Polus [12] determined congested conditions based on an occupancy value of more than 30%. Despite the existence of a huge literature on traffic congestion and great efforts to evaluate it with the use of artificial intelligence methods [13], there is still no unified approach that is universally accepted [6]. This motivated researchers to continue studying this area and to propose their own approach.
The previous paragraphs show the amount of effort that has been devoted to the concept of congestion and its definition. Although there are technical specifications defining different congestion states for transport planning [14] and traffic information systems [7], several studies have demonstrated that drivers do not perceive congestion as a clear and precise notion [15]. Thus, qualitative or lexical information on traffic congestion, such as ‘slow traffic’ or ‘queuing traffic’, is rather vague for motorists, despite being able to be defined on the basis of a quantitative definition using precise intervals of a given traffic variable. Concerning the above-mentioned examples, the Datex II European standard defines ‘slow traffic’ and ‘queuing traffic’ as conditions having an average speed between 25% and 75% and 10% and 25% of the free-flow level, respectively. This is a simple and rational method, but it is difficult for it to correspond to drivers’ comprehension because drivers do not perceive traffic conditions as being static and deterministic and do not have a unique and precise—quantitively defined—idea of them. Thus, the fuzzy approach, based on a non-univocal range definition of traffic conditions, seems to be a more appropriate approach to traffic congestion classification.
Furthermore, each traffic state has similar conditions at some level, resulting in there being some degree of similarity with each other traffic state, and each associated property has a level of uncertainty in real-world circumstances. On the other hand, to obtain reliable state information, a highly accurate prediction of short-term traffic parameters (i.e., occupancy, flow, speed) is a necessary step. In particular, the speed parameter is the most beneficial, since it is measured directly and is directly related to drivers’ experiences. Current studies on short-term traffic speed prediction generally provide a prediction level, which is the average value of the parameter based on historical data [16]. However, there are many unpredictable factors that can influence the performance and accuracy of traffic speed level prediction. More importantly, the traffic stream corresponds to the multi-dimensional status of all parameters that are formed by driver behaviors. Therefore, an estimate is needed that can reflect the uncertainty and the noise effect on traffic parameters. Presently, the fuzzy approach makes it possible to consider the value ranges of the data series and to cultivate the integrity of the original data without the loss of any data information [17]. Thus, it has been argued that fuzzy qualitative definitions may better match drivers’ perceptions [18].

2. Two-Stage Fuzzy Traffic Congestion Detector

Fuzzy Logic (FL) is a qualitative approach based on approximation reasoning that is close to human thinking. A fuzzy system (FS) is a structure that represents inputs into the output universe of interest through fuzzy logic principles. In FSs, both subjective and objective inputs, which can be both numerical and linguistic data, are in consideration. It has been very popular for more than forty years in transport engineering applications such as speed control on expressways [19], signalization for traffic control [20][21], seaport [22] and transit [23] operations, lane-changing simulation models [24] and congestion-related applications [25][26][27][28]. In [25], the authors measured the level of congestion by using the same fuzzy approach with inputs such as speed reduction rate, the proportion of delay time within total travel time, and traffic volume to road capacity. Patel and Mukherjee [26] classified the traffic according to a fuzzified index of congestion and the average speed level on the urban road network. Here, the congestion index was calculated as an output of the relationship between actual and free-flow travel time. The authors showed that the fuzzy approach was better at showing the real congested situation than other traditional congestion index values. Another fuzzy congestion evaluation study considering average speed as the input variable was presented by Hamad and Kikuchi [27]. They used travel speed, free-flow speed, and the proportion of very low speed in the total travel time as input variables to determine the congestion situation.
Additionally, in [28], Kikuchi and Chakroborty studied a fuzzy approach for handling the uncertainty embedded in the definition of the level of service (LOS). They criticized the current HCM procedure, arguing that it does not accurately represent the notion of LOS as a user-perceived measure, and questioned whether a single measure (e.g., density) could capture all of the factors that affect LOS. Thus, they provided a framework that handles uncertainty under the different paradigms: deterministic, probabilistic, or possibilistic. Further studies in this field include [16][29][30][31]. On the basis of the described analyses, it is indicated that fuzzy-based applications have a preferable performance. However, recent experiments have generally been focused on detecting and testing abnormal events of traffic, and have rarely addressed the real-time estimation of the traffic state of the network.
The idea of detecting traffic congestion using the Mamdani-based fuzzy approach has already been studied and proven to be effective [32][33][34]. In [32], the authors used three inputs—the length of the lanes, the number of lanes, and flow data—to obtain the congestion level output. However, the experiment was only based on a one-week period of data; Kalinic and Keler [33] worked on a fuzzy method that compares two input sets: flow–density, and occupancy–mean speed parameters for detecting traffic congestion; Kalinic and Krisp [34] presented a model containing only two inputs (flow and density), as in most classical traffic studies, which relate pairs of fundamental variables, with a few noticeable exceptions, like the application of Catastrophe theory to a 3D traffic state space, introduced in the 1980s [34], and which is still being studied and applied for the identification of traffic congestion [35][36].
With respect to the contributions of those reference works, researchers believe that traffic congestion should be evaluated in terms of speed since it is a function of speed reduction in time. There are many studies considering speed as a parameter with or without others to determine the level of congestion on expressways and urban roads [8][25][26][27][29][31]. Specifically, in [8], the authors stated that a speed-based threshold has a greater impact on congestion than a threshold based on capacity does. From this point of view, researchers focused on the speed values. Researchers relate the classification of traffic states to the average speed variable instead of the density in order to obtain a perspective more compliant with the DATEX II European standard, which focuses on providing information to drivers, rather than being directed towards planning purposes. However, researchers also acknowledge that the extent of congestion is multi-dimensional, and the use of a single variable cannot give a decent assessment [37]. It is difficult to assume that there is a single value determining the entire traffic situation [38]. Furthermore, congestion is a state of traffic flow characterized by the fundamental variables together, which must be considered as a whole in the classification operation. Therefore, researchers developed a two-stage traffic congestion detector that is able to predict speed values by considering flow and density values, and which then provides a qualitative estimate of congestion that drivers will find more trustworthy, according to this reasoning.
With the aim of suggesting that a fuzzy approach might be more convenient than a deterministic one for catching the inherent uncertainty in the drivers’ perception of traffic congestion when the flow characteristics are highly perturbed in oversaturated conditions, researchers tested the approach using data collected from the network on a motorway in Italy over a period of more than 8 months. The two-stage detector was able to predict the short-term speed values according to fuzzy rules and then classify the corresponding traffic states based on the EU DATEX II standard ranges.


  1. Toan, T.D. A Fuzzy-Based Methodology for Anticipating Trend of Incident Traffic Congestion on Expressways. Transp. Commun. Sci. J. 2022, 73, 381–396.
  2. Raza, A.; Ali, M.U.; Ullah, U.; Fayaz, M.; Alvi, M.J.; Kallu, K.D.; Zafar, A.; Nengroo, S.H. Evaluation of a Sustainable Urban Transportation System in Terms of Traffic Congestion—A Case Study in Taxila, Pakistan. Sustainability 2022, 14, 12325.
  3. Taylor, M.A.P. Exploring the nature of urban traffic congestion: Concepts, parameters, theories, and models. Austr. Road Res. Board 2002, 16, 83–106.
  4. Weng, J.; Chen, Q. Probabilistic speed–flow models in highway construction work zones. In Proceedings of the Institution of Civil Engineers-Transport; Thomas Telford Ltd.: London, UK, 2023; Volume 176, pp. 110–116.
  5. Pedram, I.; Salek, S.; Omrani, R. Defining and Measuring Urban Congestion—Guidelines for Defining and Measuring Urban Congestion; Transportation Association of Canada: Ottawa, ON, Canada, 2017; Available online: (accessed on 29 March 2023).
  6. Aftabuzzaman, M. Measuring Traffic Congestion—A Critical Review. In Proceedings of the 30th Australasian Transport Research Forum, London, UK, 25–27 September 2007; p. 16. Available online: (accessed on 29 March 2023).
  7. DATEX II. Version 3.2. Available online: (accessed on 29 March 2023).
  8. Rao, A.M.; Rao, K.R. Measuring urban traffic congestion—A review. Int. J. Traff. Transp. Eng. 2012, 2, 286–305.
  9. Skabardonis, A.; Varaiya, P.; Petty, K.F. Measuring recurrent and non-recurrent traffic congestion. Transport. Res. Rec. J. Transp. Res. Board 2003, 1856, 118–124.
  10. Kwon, J.; Mauch, M.; Varaiya, P. Components of congestion: Delay from incidents, special events, lane closures, weather, potential ramp metering gain, and excess demand. Transp. Res. Rec. J. Transp. Res. Board 2006, 1959, 84–91.
  11. Bertini, R.L. You are the traffic jam: An examination of congestion measures. In Proceedings of the 85th Annual Meeting of the Transportation Research Board, Vancouver, BC, Canada, 22–26 January 2006; pp. 16–22.
  12. Polus, A. Evaluation of congestion trends on Chicago expressways. J. Adv. Transp. 1996, 30, 79–100.
  13. Fusco, G.; Gori, S. The use of artificial neural networks in advanced traveler information and traffic management systems. In Applications of Advanced Technologies in Transportation Engineering; ASCE: Reston, VA, USA, 1995; pp. 341–345.
  14. National Academies of Sciences, Engineering, and Medicine. Highway Capacity Manual 7th Edition: A Guide for Multimodal Mobility Analysis; The National Academies Press: Washington, DC, USA, 2022.
  15. Choocharukul, K.; Sinha, K.C.; Mannering, F.L. User perceptions and engineering definitions of highway level of service: An exploratory statistical comparison. Transp. Res. Part A Policy Pract. 2004, 38, 677–689.
  16. Song, Z.; Feng, W.; Liu, W. Interval prediction of short-term traffic speed with limited data input: Application of fuzzy-grey combined prediction model. Expert Syst. Appl. 2022, 187, 115878.
  17. Lu, W.; Chen, X.; Pedrycz, W.; Liu, X.; Yang, J. Using interval information granules to improve forecasting in fuzzy time series. Int. J. Approx. Reason. 2015, 57, 1–18.
  18. Garrigós, D.T.; Zapater, J.J.S.; Durá, J.J.M. Dealing with traffic information and user profiles a semantic approach based on Datex II. In Intelligent Transportation Vehicles; Bentham Science: Amsterdam, The Netherlands, 2011; p. 51.
  19. Ngo, C.Y.; Victor, O.K.L. Freeway traffic control using fuzzy logic controllers. Inform. Sci. 1994, 1, 59–76.
  20. Zhao, D.; Dai, Y.; Zhang, Z. Computational intelligence in urban traffic signal control: A survey. IEEE Trans. Syst. Man Cybern. Part C Appl. Rev. 2011, 42, 485–494.
  21. Eze, U.F.; Emmanuel, I.; Stephen, E. Fuzzy logic model for traffic congestion. IOSR J. Mob. Comput. Appl. 2014, 1, 15–20.
  22. John, A.; Yang, Z.; Riahi, R. Application of a collaborative modeling and strategic fuzzy decision support system for selecting appropriate resilience strategies for seaport operations. J. Traff. Transp. Eng. 2014, 1, 159–179.
  23. Li, X.; Liu, Y.; Wang, Y. Evaluating transit operator efficiency: An enhanced deal model with constrained fuzzy-AHP cones. J. Traff. Transp. Eng. 2016, 3, 215–225.
  24. Li, Q.; Qiao, F.; Yu, L. Socio-demographic impacts on lane-changing response time and distance in work zone with drivers’ smart advisory system. J. Traff. Transp. Eng. 2015, 2, 313–326.
  25. Kukadapwar, S.R.; Parbat, D.K. Modeling of traffic congestion on urban road network using fuzzy inference system. Am. J. Eng. Res. 2015, 4, 143–148.
  26. Patel, N.; Mukherjeem, A.B. Categorization of urban traffic congestion based on the fuzzification of congestion index value and influencing parameters. Theor. Empir. Res. Urban Manag. 2014, 9, 36–51.
  27. Hamad, K.; Kikuchi, S. Developing a measure of traffic congestion—Fuzzy inference approach. Transp. Res. Rec. J. Transp. Res. Board 2002, 1802, 77–85.
  28. Kikuchi, S.; Chakroborty, P. Frameworks to Represent Uncertainty when Level of Service is Determined. Transp. Res. Rec. 2006, 1968, 53–62.
  29. Narayanan, R.; Udayakumar, R.; Kumar, K.; Subbaraj, L. Quantification of Congestion Using Fuzzy Logic and Network Analysis Using GIS. In Proceedings of the Map India Conference, Noida, India, 28–31 January 2003; Available online: (accessed on 29 March 2023).
  30. Dong, C.; Sun, H. An improved non-linear fuzzy comprehensive method for assessing urban freeway network traffic congestion level. Open J. Transp. Technol. 2020, 9, 68–78.
  31. Munajat, E.; Widyantoro, D.H.; Munir, R. A new method for analyzing congestion levels based on road density and vehicle speed. J. Theoret. Appl. Inform. Technol. 2017, 95, 6454–6471.
  32. Amini, M.; Hatwagner, M.; Mikulai, G.; Koczy, L. An intelligent traffic congestion detection approach based on fuzzy inference system. In Proceedings of the IEEE 15th International Symposium on Applied Computational Intelligence and Informatics, Timişoara, Romania, 19–21 May 2021.
  33. Kalinic, M.; Keler, A. Defining input parameters of fuzzy inference model for detecting traffic congestions. In Proceedings of the Conference on Geographical Information Science Research, Newcastle, UK, 23–26 April 2019.
  34. Kalinic, M.; Krisp, J.M. Fuzzy inference approach in traffic congestion detection. Ann. GIS 2019, 25, 329–336.
  35. Persaud, B.N.; Hall, F.L. Catastrophe theory and patterns in 30-second freeway traffic data—Implications for incident detection. Transp. Res. Part A Gen. 1989, 23, 103–113.
  36. Qu, D.; Liu, H.; Song, H.; Meng, Y. Extraction of Catastrophe Boundary and Evolution of Expressway Traffic Flow State. Appl. Sci. 2022, 12, 6291.
  37. Toan, T.D.; Wong, Y.D. Fuzzy logic-based methodology for quantification of traffic congestion. Phys. A 2021, 570, 125784.
  38. Afrin, T.; Yodo, N. A survey of road traffic congestion measures towards a sustainable and resilient transportation system. Sustainability 2020, 12, 4660.
Subjects: Transportation
Contributors MDPI registered users' name will be linked to their SciProfiles pages. To register with us, please refer to : , ,
View Times: 247
Revisions: 2 times (View History)
Update Date: 17 Jul 2023