RESEARCH ARTICLE | JUNE 21 2019

Application of fuzzy logic to control traffic signals 8

S. Mohanaselvi H; B. Shanpriya
AIP Conf. Proc. 2112, 020045 (2019)
https://doi.org/10.1063/1.5112230

View Export
Online Citation

Articles You May Be Interested In

Application of fuzzy logic to earthquake damage predictions

AIP Conf. Proc. (June 2019)

Intelligent crossroad control system on the base of fuzzy logic and genetic algorithms symbiosis
AIP Conf. Proc. (December 2023)

Vehicle routing problem on dynamic programming using fuzzy logic approach for tourist destination route in
Semarang
AIP Conf. Proc. (June 2023)

19 April 2025 09:28:48

S
 Application of Fuzzy Logic to Control Traffic Signals
Abstract. In this paper, using fuzzy logic technique an intelligent traffic signal control is introduced. The existing traffic light
controllers would not give a best solution to this problem as it changes traffic lights based on constant cycle time. Fuzzy logic
controllers can be used to deal with linguistic and unpredictable traffic data to control the signal timings. This paper aims at
developing an intelligent traffic light controller using fuzzy logic technique and illustrated a control procedure using if – then
rules.
Keywords: Fuzzy logic, Traffic control, Triangular membership function, Fuzzy rule base system.

INTRODUCTION
Traffic congestion is one of the critical problems to be resolved to improve the economy of any country. The proper
way of controlling traffic congestion is done by using traffic signals. Due to increase of vehicles in roads, public
behavior and fixed time controlled traffic signal systems have not provided a solution to high traffic congestion. The
aim of the traffic congestion problem is to minimize the delays in roads by effectively using the existing traffic
signal systems without constructing new roads. Traffic system is more dependent on parameters such as time, day,
season, weather and unpredictable situations. The difficulty and uncertainties present in the existing traffic system
can be rectified by using an intelligent traffic control system which continuously sense and adjust the timings of
traffic lights depending on the traffic jam. If these parameters are not taken into consideration, the traffic control
system will create delays. The difficulty and uncertainty of traffic clogging made an ultimate representation of such
research. Traffic congestion patterns expand over time period as an effect of communications between target and

19 April 2025 09:28:48

congestion over space. At its most basic congestion is caused when the level of traffic exceeds road capacity. L.A
Zadeh proposed a fuzzy set theory to deal with uncertainties present in real world situations. The fuzzy logic
controlled traffic light utilizes sensors that tally cars and permits an improved estimation of modifying traffic
patterns .To proposed the average weight of vehicles at a intersection lane an adaptive controlled design strategy
was proposed by Asthuosh Choudhary [1]. A comparison between different fuzzy logic control algorithms was
made by I N Askerzade [2]. Babangida Zachariah [3] introduced a fuzzy logic inference system to optimize state
phase scheduling of traffic light system (SPSTLS). Using states machine B Dilip [4] proposed an efficient design.
Using sugeno method Erwan Eko Prasetiy [5] proposed an adaptive traffic light controller. A traffic signal control
method for a 6-phase intersection was proposed by Fuyang chan [6]. Ms .Girija H Kulkarni [7] using VB6
environment in MATLAB proposed a fuzzy traffic controller for an isolated intersection. This simulation result
verify the performance of our proposed integrated traffic light control system using RFID technology and fuzzy
logic was projected by Javed Alam [8]. Jarko niittymaki [9] make suggestion fuzzy control principles are very
competitive isolated multi-phase movements. Kamlesh Kumar Pandey [10] proposed a fuzzy decision support
system and component of fuzzy controller with fuzzy rule base. Navneett Kaushal [11] proposed two algorithms of
fuzzy rule base system for an isolated traffic intersection in VB6 environment. O. M Olanrewaju [12] had proved
that the pedestrian delay has significant contribution to traffic control to enhance the safety of the pedestrian.
Constructed the effectiveness and actual situation of the traffic control process are investigated by Sandeep Mehan
[13]. In this paper controlling traffic flow for an isolated four lane traffic junction using fuzzy logic technique are
discussed. This paper has been organized as follows. In the following section II a outline about fuzzy traffic signal
controller is described briefly . Then assumptions and constraints of isolated four lane traffic controller is introduced
in section III are explained. Then in the next section IV and V about fuzzy inputs, output, linguistic variables and
their membership functions. Then different fuzzy rule bases have been set for traffic signal processing and a
simulation of fuzzy rules using mat lab is implemented and the results are presented

020045-1
 FUZZY TRAFFIC SIGNAL CONTROLLER
Now a days predetermined traffic lights are used under time of the day scheme to control traffic congestion. But it
does not offer an optimum solution for the fluctuations of the traffic condition. A fuzzy logic control system
provides a better optimal solution for the fluctuating traffic system. Controlling the traffic flow system using fuzzy
technology has the ability to convert human thinking process into an algorithm using some mathematical models.
Implementation of real rules which are similar to the way that traffic policemen would think to manage traffic signal
lights can be done by fuzzy if-then rules. The traffic signal controllers are supposed to adjust the cycle time of green
light signal depending upon the amount of vehicles arrival which would maximize the traffic flow and control the
regular waiting time. The inputs of fuzzy signal control system are generated by the help of an experience. Fuzzy
rule based system derives actions from given inputs by constructing if-then rules which represent the relation among
the linguistic variables. In general, a fuzzy traffic signal controller will improve the traffic protection in the junction,
usage of junction at its maximum level and minimize the delays. In a traffic light system red light indicates the
arriving vehicles to be stopped, green light indicates the arriving vehicles to be allowed and the yellow light
indicates the switch over of red light or green light.

Traffic Fuzzy Signal

situation Fuzzification inference control
Defuzzification
model system actions

Detection Traffic situation Signal status

19 April 2025 09:28:48

Figure 1: Fuzzy Traffic Signal Controller

An layout of isolated four lane traffic junction is given

Figure 2: Layout of isolated four lane traffic junction

020045-2
 ASSUMPTIONS AND CONSTRAINTS
The following criterions are made to design the proposed fuzzy traffic signal control system:
• The traffic is allowed from north south west and east direction in an isolated four lane traffic junction.
• Initially the traffic from the north direction will be allowed to move and then the traffic from the east,
south and west direction will be allowed to movie in progress.
• When the traffic from north and south are allowed to move then the traffic from east and west are
terminated and also vice versa.
• No left and right turns are considered.
• The main duty of the fuzzy logic controller is to observe the traffic from north and south direction on one
side and also the direction from east and west on another side.
• The main lane is assumed as north south direction.
• Maximum and Minimum time of green light signal is 60 seconds and 2 seconds respectively.

FUZZY INPUTS, OUTPUT AND THEIR LINGUISTIC VARIABLES

In the proposed fuzzy logic signal controller three fuzzy input variables are chosen namely
1. Number of vehicles arriving at the junction or the number of vehicles passing during green light(AV-
Arrival Vehicle)
2. Number of vehicles waiting on the queue on the junction or the number of vehicles waiting during the red
light (QV-Queuing Vehicle)
3. Weather variation (F-Humidity or Fog).
The green light duration (GD) is the output variable which will provide the extension time required for green light
on the arrival side.
The following table 1 provides the range of values for fixing the input and output variables

19 April 2025 09:28:48

TABLE 1
Arriving vehicle Queuing vehicle Fog Green light duration

Range Linguistic Range Linguistic Visual range Linguistic Time Linguistic

variables variables variables variables
(in meters) (in sec)

00 – 10 Less 00 - 10 Less 1000 – 1500 Low 00 - 10 Short

07 - 25 Medium 07 - 25 Medium 400 - 1200 Medium 08 - 30 Medium

20 - 50 High 20 - 50 High 50 - 500 High 25 - 60 Long

FUZZY INPUTS, OUTPUT AND THEIR MEMBERSHIP FUNCTIONS

Triangular fuzzy numbers are often used in many applications due to its computational efficiency. The
graphical representation of the membership functions of the input and output variables are given below. The
amounts of the traffic on the arriving, queuing side have (Less, Medium, High) numbers of vehicles and also the
weather variant fog have (Less, Medium, High) and the Green time duration have (Short, Medium and Long).

The following table 2 provides the membership function of each input and output variables,

020045-3
 TABLE 2

MEMBERSHIP DIAGRAM
FUNCTIONS

Y
L M H
Less μ 1
Arriving vehicle Medium
High No of vehicles
X
0 7 10 20 25 50

y
Less L M H
INPUTS Queuing vehicle Medium μ 1
High
No of vehicles
X
0 7 10 20 25 50

19 April 2025 09:28:48

Less y
Medium L M H
Fog High μ 1

Weather variant
X
0 7 10 20 25 50

y
Short S M L
μ 1
OUTPUT Gduration Medium
Long Signal time
X
0 7 10 20 25 50

For the input fuzzy variables for arriving vehicle and queuing vehicle the universe of discourse (x-axis) is number
of vehicles, fog the universe of discourse is the visibility range in meters and y-axis for all input variables
membership degree varies from 0 to 1. Output fuzzy variable’s universe of discourse is the length of time in signal
to be extended in seconds.

020045-4
 FUZZY IF-THEN RULES
For executing any activities human beings frame rules for implementing it. This human intelligent process is similar
to the fuzzy inference mechanism. On the basis of 3 input variables nearly 27 fuzzy rules are framed to obtain the
following output and given in table 3.
TABLE 3

Rules Inputs Output

No Arrivingvehicle Queuingvehicle Fog G duration
1 H L L S
2 H L M M
3 H L H H
4 H M L M
5 H M M M
6 H M H H
7 H H L H
8 H H M H
9 H H H H
10 M L L S
11 M L M M
12 M L H M
13 M M L M
14 M M M M
15 M M H M
16 M H L H
17 M H M H
18 M H H M

19 April 2025 09:28:48

19 L L L S
20 L L M M
21 L L H M
22 L M L M
23 L M M H
24 L M H M
25 L H L S
26 L H M M
27 L H H H

In this paper fuzzy logic tool box in Mat lab is used to implement the proposed fuzzy logic control system for an
isolated four lane traffic junction and fuzzy rule set. Using the graphical user interface (GUI) the membership
function of input and output variables (Fig 3) are designed as follows

FIGURE: 3 FIS editor

020045-5
The figure 4 shows the membership function for the input variable arriving vehicle (AV). The membership function
for the arriving vehicle are less = 0 to 10, medium = 7 to 25 and high = 20 to 50

FIGURE 4 : Membership function (Arriving vehicle)

The figure 5 shows the membership function for the input variable queuing vehicle (QV). The membership function
for the queuing vehicle are less = 0 to 10, medium = 7 to 25 and high = 20 to 50.

19 April 2025 09:28:48

FIGURE 5 : Membership function (Queuing vehicle)
The figure 6 shows the membership function for the input variable fog (F). The membership function for the fog (in
meters) are low = 1000 to 1500, medium = 400 to 1200 and high = 50 to 500.

FIGURE 6: Membership function (Fog)

The figure 7 shows the membership function for the output variable green light duration (GD). The membership
function for the green light duration (in seconds) are short = 0 to 10, medium = 08 to 30 and high = 25 to 60.

020045-6
 FIGURE 7: Membership function (Gduration)
Using FIS editor in MATLAB the proposed fuzzy if-then rules are inserted.

19 April 2025 09:28:48

FIGURE 8: Rule Editor
FIS can view graphically using rule viewer and surface viewer.

FIGURE 9: Rule viewer

Figure 10 shows the surface viewer of the proposed control system. The surface viewer is a 3-Dimensional output
surface, here drawn for arriving vehicle and queuing vehicle. For varying output we can generate different surface
viewer.

020045-7
 FIGURE 10: Surface viewer
To provide suitability performance, this paper aims at proposing a fuzzy logic control system to control the traffic
congestion at a junction. By considering the fuzzy inputs AV, QV and F, the fuzzy rules have been framed by using
fuzzy logic tool box in mat lab, the traffic congestion at a junction have been estimated. It is observed that by using
fuzzy logic techniques, a better estimation of the traffic congestion at an intersection during traffic flow is obtained.
CONCLUSION
In this paper an effort has been made to develop a fuzzy logic controller to improve the performance of the traffic
signal controller. The number of arriving vehicles, queuing vehicles during different weather conditions have been
taken into account for estimating the green light extension time is made by using the proposed fuzzy logic controller.

19 April 2025 09:28:48

REFERENCES

1. Ash tosh choudhary, Avinash G Keshkar, Pratik Kothari, Ashwin Gajghate, Atul Pandey, “Adaptive control of
traffic Grid using Fuzzy Logic,” International journal of Electrical, Electronics and Data Communication,
ISSN : 2320 - 2084 volume 2, Issue - 8, Aug 2014.
2. I. N. Askerzade (Askerbeyli), Mustafa Mahmood. Control the Extension Time of Traffic Light in Single
Junction by Using Fuzzy Logic,” International Journal of Electrical and Computer Sciences IJECS - IJENS
volume 10 (No 02).
3. Babangida Zacharials, Peter Ayuba and Luhutyid Peter Damuut “ Optimization of Traffic Light Control
System of An Intersection using Fuzzy Inference System,” Science World Journal volume 12 (No 4) 2017.
ISSN: 1597 - 6343.
4. B. Dilip, Y.Alekhya, P.Divya Bharathi “FPGA Implementation of An Advanced Traffic Controller using
Verilog HDL,” International Journal of Advanced Research in Computer Engineering and Technology
(IJARCET) volume 1, Issue 7, September 2012.
5. Erwan Eko Prasetiy O, Oyas Wahyuggoro, Selosulistyo “ Design and Simulation of Adaptive Traffic Light
Controller Using Fuzzy Logic Control Sugeno Method,” International Journal Of Scientific and Research
publications, volume 5 - Issue 4, April 2015 ISSN : 2250 - 3153.
6. Fuyang chan, Zhichaochen, Feng Jiang “Study on Traffic Signal Control for Single Intersection via Fuzzy
Logic,” Applied Mechanics and Materials volume : 263 - 266 (2013) pp 624 - 628.
7. Ms .Girija H Kulkarni, Ms Poorva G Wainankar “ Fuzzy Logic Based Traffic Light Controller,”
8. Javed Alam and Prof. (Dr). M K. Pandey “ An Integrated System Using RFID Technology and Fuzzy Logic,”
9. Jarko niittymaki “ Using Fuzzy Logic to Control Traffic Signals at Multi – Phase Intersections,”
10. Kamlesh Kumar Pandey, Rajat Kumar Yadu, Pradeep Kumar Shukla, Narendra Pradhan “ A Case Study For
Traffic Signal Control at Four-Way Intersection Road,” International Journal of Computer Techniques volume
- 2 Issue 4, July-Aug 2015 ISSN : 2394 - 2231 page: 54 - 59.
11. Navneet Kaushal, Vithika Joshi “Fuzzy logic Controller Based Traffic Light System ,” volume 6 issue
12,December 2016 ISSN : 2277128X.

020045-8
12. O. M Olanrewaju, A.A. Obiniyi, S. B.Junaidy “Fuzzy Logic Concept For Safety Driven Vehicle Pedestrian
Traffic Interaction,” International Journal of Computer Application (0995-8887) volume 167 (No.1), June
2017.
13. Sandeep Mehan “Introduction of Traffic Light Controller with Fuzzy Control System,” IJECT Vol 2, Issue 3,
Sept 2011. ISSN: 2230 – 7109 (ONLINE) | ISSN: 2230 – 9543 (PRINT).
14. Tan kok khiang, Marzuki Khalid and Rubiyah yusof “Intelligent traffic light control by fuzzy logic”.
15. Zadeh L.A, ( 1965), Fuzzy sets information control 8,338 – 353

19 April 2025 09:28:48

020045-9