Development of a prioritized traffic light control system for emergency vehicles

IAES International Journal of Artificial Intelligence (IJ-AI)
Vol. 13, No. 4, December 2024, pp. 4019~4028
ISSN: 2252-8938, DOI: 10.11591/ijai.v13.i4.pp4019-4028  4019
Journal homepage: http://ijai.iaescore.com
Development of a prioritized traffic light control system for
emergency vehicles
Halleluyah Oluwatobi Aworinde1
, Abidemi Emmanuel Adeniyi1
, Segun Adebayo2
, Faith Adeniji1
,
Oluwasegun Julius Aroba3,4
1
Department of Computer Science, College of Computing and Communication Studies, Bowen University, Iwo, Nigeria
2
College of Agriculture, Engineering and Science, Bowen University, Iwo, Nigeria
3
Department of Operations and Quality Management, Durban University of Technology, Durban, South Africa
4
Centre for Ecological Intelligence, Department of Electrical and Electronic Engineering Science, Faculty of Engineering and the Build
Environment, University of Johannesburg, Johannesburg, South Africa
Article Info ABSTRACT
Article history:
Received Jan 21, 2024
Revised Apr 18, 2024
Accepted Jun 14, 2024
This research presents a model for an adaptive traffic signal control system
aimed at improving urban traffic regulation. It dynamically adjusts signal
timing based on vehicle volume at intersections, prioritizing emergency
vehicles by allowing them immediate passage. Utilizing Arduino coding, the
system controls traffic light intensity according to the traffic flow, enhancing
road safety and efficiency. This innovative approach not only facilitates faster
clearance for emergency services without human intervention but also reduces
congestion and accident rates. This research creates a model for a prioritized
traffic signal control system. When the vehicular volume at the intersection
varies, the signal time alters autonomously. It identifies the
ambulance/emergency vehicles and allows the green light for emergency
vehicles like ambulances, and fire engines. This approach may be used to
detect traffic accidents and infractions of automobile spiral motions. When
erected on the road, the entire system allows for quick traffic clearing for
rescue vehicles without requiring a policeman. The system's design eliminates
the need for sensors or radio frequency identification (RFID) tags, simplifying
traffic management. Simulations validate that emergency vehicle travel time
is significantly reduced, proving the system's effectiveness in streamlining
urban traffic flows.
Keywords:
Emergency
Simulation
Traffic light
Transportation
Vehicles
This is an open-access article under the CC BY-SA license.
Corresponding Author:
Oluwasegun Julius Aroba
Centre for Ecological Intelligence, Department of Electrical and Electronic Engineering Science
Faculty of Engineering and the Build Environment, University of Johannesburg
Auckland Park Campus, Johannesburg, South Africa
Email: aroseglinks@yahoo.co.uk
1. INTRODUCTION
The urban environment hums with the pulse of mobility. Vehicles swirl across a patchwork of streets,
their flow governed by the traffic signal, the quiet conductor. However, in today's modern city, when time is
valuable and fuel is short, a one-size-fits-all strategy for traffic regulation is no longer adequate. Enter the
prioritized traffic light control system model (PTLCSM), a game-changing idea that has the potential to rethink
the urban symphony of movement. Traffic signal systems are used to govern more than two vehicle passing
channels or when pedestrians cross a road [1]–[3]. In the case of a four-way lane, it is also utilized when two
pathways intersect. Traffic congestion is regarded as one of the most serious issues in metropolitan areas [4].

 ISSN: 2252-8938
Int J Artif Intell, Vol. 13, No. 4, December 2024: 4019-4028
4020
Traffic congestion is predicted to worsen as a result of the rising number of modes of transportation
and the existing poor condition of road infrastructure. Furthermore, numerous studies and statistics have been
created in developing nations proving that the majority of road fatalities are caused by limited roads and the
harmful expansion in transportation methods. A system with flexibility capable of managing traffic density is
necessary for big traffic systems. The fundamental disadvantage of a generalized traffic control system is the
difficulty in detecting high-priority events and emergency scenarios [5]. This emphasizes the necessity for a
smart traffic management system that can handle all scenarios and make judgments autonomously.
A traffic management system's goal is to manage vehicle movement within an intersection and to
avoid collisions or road blockages. The signal lights used for the current traffic systems are notably, red, yellow,
and green for stop, get ready, and go accordingly, with each light operating one after another for a specified
length of time in most developing nations. The delay characteristics that affect traffic load include time, day,
season, weather, and unforeseeable events like as accidents or construction operations. Congestion can be
alleviated by constructing new roadways [6]. The only disadvantage is that the environs get more crowded.
Instead of building additional facilities twice, it is necessary to modify the traffic system. These issues can be
remedied by continually monitoring and modifying traffic signal timings based on real traffic demand, which
image detection systems can do.
The major goal of this study is to examine traffic lights and more congested areas and to provide
precedence to emergency vehicles and ambulances at traffic intersections. This requires just minor physical
alterations to the crossing and delivers the quickest clearing to vehicle/pedestrian traffic in all directions. This,
in turn, offers a variable traffic light system that ensures variations in traffic density while also reducing traffic
warden stress and accidents. Traffic congestion causes no problems in the event of an emergency and reduces
fatalities [7]. As a result, traffic may be controlled without the need for a sergeant, and the suggested solution
saves people's lives and valuable time.
Previous studies and practical applications have established the potential of real-time, traffic-responsive
signal optimization strategies to minimize driver pauses and delays at particular signalized junctions [8]. As a
result, it is realistically critical to build, check, and validate simple yet powerful models that aid in the design
and improvement of public transit security and effectiveness, while rescue vehicles are ignored. Ambulances,
police cars, fire engines, and other emergency vehicles that become caught in traffic and are delayed in reaching
their destination can result in the loss of property and valued lives [9], [10]. Rising car number not only enhances
the time taken for rescue vehicles but also improves their chances of being involved in fatalities [11]–[13]. The
emergency car going into a junction at high speed on a red light endangers traffic on other roads and can cause
accidents. Based on the present issue in this section, it is clear that a sophisticated traffic management system is
required for efficient control of both typical and emergency automobiles [14]–[16].
This paper proposes a method for scheduling emergency vehicles in gridlock. The technology
integrates visual detecting techniques for measuring the distance that exists between the rescue car and an
intersection, automobile counting, and time-sensitive warning transmission within the sensor networks. To
recognize emergency vehicles, the sensors capture siren signals and transfer them to the measuring controller
(Arduino UNO). And passes them over to the frequency measurement controller. The emergency vehicle's
siren wavelengths are detected by the control device. The control unit estimates the average of observed
wavelengths after measuring the frequencies of siren sounds. If the frequency is between yelp and wail, the
frequency measurement controller sends an alert signal to the traffic signal controller (Arduino Mega). On
receipt of approaching emergency vehicle information, the traffic signal controller stops the preset sequence
and light length algorithm and conducts the emergency vehicle dispatching algorithm. The suggested algorithm
is executed by the controller, and its judgment is sent to traffic lights. The system resumes regular functioning
following the passing of an emergency vehicle, and we describe distance measuring techniques, vehicle
counting approaches, a distance-based emergency vehicle dispatching mechanism, and the simulation
environment.
The PTLCSM goes beyond the constraints of typical red, yellow, and green. It analyzes real-time data
from a variety of sources, including cameras, sensors embedded in the pavement, and GPS-equipped
automobiles. This data includes information such as traffic density, vehicle type, proximity to emergency
vehicles, and even environmental parameters such as weather conditions. With this real-time knowledge, the
PTLCSM improves traffic signal timing and sequencing on an intersection-by-intersection basis.
The study's benefit is that it gives a novel method for calculating the distance between the emergency
vehicle and the junction. The method will allow for the examination of an aimed at creating a create a
framework for a frequency measuring controller to identify emergency cars. A self-organized traffic control
method that aids in the functioning of emergency response vehicles; allows emergency vehicles to travel
through traffic. A technique for resolving junction-ensuring disputes and implementing a priority plan for
prioritizing emergency vehicles at intersections.

Int J Artif Intell ISSN: 2252-8938 
Development of a prioritized traffic light control system for emergency … (Halleluyah Oluwatobi Aworinde)
4021
The advantages of the PTLCSM go much beyond mere convenience. The technology minimizes fuel
consumption and emissions by minimizing congestion and improving traffic flow, resulting in cleaner air and
a healthier environment. It shortens emergency response times, potentially saving lives in life-threatening
circumstances. Furthermore, it improves the efficiency of public transportation, making buses and trams a more
competitive option and contributing to a more sustainable urban ecology. The remainder of this study is
structured into five sections; section two discusses the literature review of the related work, section three
discusses the methodology used for the prioritized traffic control model, section four describes the results
obtained from the simulation, and section five concludes the study.
Essien and Uloko [17] entailed developing a method to reduce the likelihood of accidents prevalent
at traffic signal junctions, where vehicles frequently need to swerve to make space for emergency vehicles
following a predetermined path. The study was successful in analyzing, simulating, and implementing wireless
communication systems for traffic light management. The realized model uses radio frequency identification
(RFID) communication, operates in concert with the sequential mode of signals to change the traffic light
series, and restores the traffic signals to their original sequence after the emergency vehicle has passed through
the intersections. The system made use of a RFID sensor and a reduced instruction set computing (RISC)
architecture microcontroller to simplify the operation of a 3-way intersection traffic light and to give rescue
vehicles priority.
Mohamed and Radwan [18] provide a unique traffic light control (TLC) technology for different
traffic scenarios that is responsive to current traffic conditions at a crossroads and prioritizes essential cars
above normal traffic. The suggested method allows for several degrees of priority among priority vehicles and
efficiently arranges traffic signals at a junction so that other ordinary traffic is not disrupted. The study does
not service priority vehicles such as buses or emergency vehicles (ambulances and fire engines). This work
investigates the traffic patterns in less-disciplined, diverse traffic (two-three-four-wheeler cars), which is
common in most developing nations. According to the simulation findings, the suggested method can tolerate
a 20% mistake in the passenger car unit count without affecting performance. Furthermore, this study indicates
that the requisite precision in traffic information can be handled in real-time utilizing the available
microcontrollers.
Bisht et al. [19], the investigation strategy has placed a high focus on planning, analyzing, and
reporting outcomes. According to the study's findings, a specialized design that monitors traffic on roads and
gives intelligent alternatives has yet to be established. The standard design method lacks intelligent
performance, adjustable time frames, learning capabilities, emergency prioritization administration, and
dynamic duration sequences. While the adaptive self-organization strategy disregarded learning skills.
However, the vast majority of cleverly planned experiments lacked cognitive stress responses and feedback
capabilities.
Ariffin et al. [20] offer an intelligent system that dynamically modifies the cycle length for each lane
at a junction based on traffic density and gives different types of emergency vehicles access to the crossroads
by assigning varying priority. The system is divided into three modules: automation of traffic lights, emergency
RFID, and the internet. Using ultrasonic sensors, the traffic light regulation modules detect motorist density
and provide an evolving set of cycle lengths according to the specific lane density situation. Emergency RFIDs
are fitted on several sorts of emergency vehicles based on predetermined priority weights. The internet module
enables authorized staff to manage the dynamic traffic signal system in real time.
Kumar et al. [21] use a dynamic and intelligent traffic light control system (DITLCS) that operates in
three forms: Fair mode (FM), priority mode (PM), and emergency mode (EM), in which all vehicles have equal
priority, motorcycles of various categorizations have different degrees of importance, and medical vehicles
have the highest priority. A complex reinforcement learning approach is also demonstrated to toggle traffic
lights in distinct phases (red, green, and yellow), and a fuzzy inference system is demonstrated to pick one
mode between the three options (FM, PM, and EM) based on traffic data. The simulation results demonstrate
DITLCS's efficiency in comparison to other state-of-the-art algorithms on a variety of performance metrics.
According to Peter et al. [22], an attempt is made in study to enhance the Kaduna Refinery Junction's
(KRJ) current programmed stationary road traffic signal management system. The KRJ is the main road
connecting the southern region of the state to Kaduna's major town. During the workday, vehicles from other
parts of the country, public and private servants, students, merchants, and others traveling to other areas of the
country via the state's southern half converge at the KRJ. An economical model of the fuzzy logic (FL) method
is created for the most effective planning of TLC systems using TraCI4MATLAB and simulation of urban
mobility (SUMO). The average improvement over the previous result was 2.74%. When emergency vehicles
were prioritized, there was a 66.79% improvement over static phase scheduling. This demonstrates that FL can
be useful in traffic control systems.
Li et al. [23] planned effort, which is based on automobile priority, intends to provide a smart traffic
signal system to which the high priority vehicles (HPV) may request being loaded at a crossroads. Depending
on the greatest priority, the system would change the traffic signal green to clear the road segment (RS) and

 ISSN: 2252-8938
4022
save HPV travel time. The system is evaluated using the Python traffic control interface (TraCI) and SUMO.
The findings demonstrate the efficiency of the intelligent traffic signal system. In the future, it may have
important theoretical as well as practical utility for intelligent transportation systems (ITS).
Traffic lights are intended to keep cities moving smoothly [24]. The existing traffic system has been
in place for some years [25]-[29]. As the number of cars on the road increases, this method is failing to address
traffic congestion issues, particularly at junctions. HPV becomes caught in traffic as a result of traffic
congestion, causing delays in their services. HPVs, such the ambulances and fire trucks, must respond to a
variety of incidents. HPV must arrive on time. There is a need for a system that provides a conduit for HPV to
travel as soon as feasible. The suggested work takes a prioritized approach. It seeks to provide a user-interactive
HPV system in which an HPV driver may submit requests to the system and the system reacts intelligently. At
a junction, the priority of RS is determined, and the traffic signal turns green for the RS with the highest priority.
The method was evaluated on SUMO and yielded positive results, saving more than 50% of the time across all
traffic concentrations (low, moderate, and high).
2. METHOD
The process employed in this research includes managing traffic center performance, distance
measuring techniques, and a distance-based rescue vehicle, determining the position of the emergency car, and
methods for emergency vehicle identification based on siren sounds. The amount of time it takes to get to the
next set of intersections. The traffic signal will revert to its usual sequence after the emergency vehicle has
passed. For the setting up of this system, an ARDINUO UNO was employed.
2.1. Traffic detection
The support model, like other traffic-responsive flag management systems, determines
signal-switching choices based mainly on expected vehicle coming data. The data is acquired via traffic
detectors strategically placed along the road leading to the controlled junction. The concept allows for the
deployment of one or more traffic detectors along junction approaches at any point. Support records the
detecting time and kind of car whenever the car travels over a sensor. The simulator is entity-oriented and takes
into account three object types: cars, segments, and vehicle actions. The total amount of segments and vehicle
operations are set by the user. Vehicles are created automatically during simulation based on user-defined flow
parameters (for example, statistical distributions of inter-arrival durations, platoon features, and arrival lists).
The simulator can simulate the effects that transit vehicles have on other cars when they stop on the correct
amount of road to board and release people.
2.2. Rule-based signal-switching decision process
The support paradigm decides on signal flipping via a heuristic rule-based signal optimization
approach. The technique is based on the knowledge that signal changes often occur after the realization of
specified discrete occurrences, such as when a line of cars reaches a given size when a queue dissipates, or
when an arriving transit vehicle is detected. The approach allows the support model to greatly minimize the
number of alternative switching permutations that must be investigated to identify a near-optimum solution by
discarding those events that have no significance for signal functioning. The model particularly analyzes the
following reactions to significant traffic events that occur on a particular junction strategy:
− Step 1: If there is an n-vehicle stop line queue that is not being offered, begin servicing the queue as soon
as feasible. If the stop line queue reaches a user-defined length, turn the signal display green.
− Step 2: Keep the present green signal indicator in a direction where the upstream queue's reach exceeds a
user-defined position.
− Step 3: If a backlog on one of the method's user-defined main exit connections impends to leak back over
the junction, turn the light red.
− Step 4: When a group of n or more cars approach the junction, turn the signal show to green at a moment
that allows the platoon to pass the junction without being influenced by vehicles halted at the stop line.
− Step 5: If a vehicle line is being served, continue to serve the queue.
− Step 6: If you are serving a platoon of vehicles, keep doing so.
− Step 7: As a transit vehicle approaches its transit stop, turn the signal show to green at a moment that allows
the vehicle to continue up to its putting position undisturbed.
− Step 8: As a transit vehicle approaches the stop line, turn the signal display to green at a moment when the
vehicle can cross the roadway without stopping.
− Step 9: To account for the reality that not all traffic occurrences are equal in importance, each event is given
a priority or weighting.

4023
− Step 10: By the detection of any priority occurrence during the period during which traffic arrives, the
signal optimization method provides requests for either a green or a red signal indication on certain
approaches at specified times.
2.3. Multi-objective optimization process
While the support approach can identify the relative significance of multiple traffic events by using
prioritized listings of incidents, it is frequently impossible to know which event ought to receive the greatest
priority ahead of time. The user can choose the relative weights for pauses, delays, and travel time (kd, ks,
kTT). Travel time is not taken into account in any of the assessments in this article (i.e. kTT=0). The operation
additionally incorporates a terminal cost component that projections the delays incurred by every car left in the
queue outside the end of the choice horizon under the presumption that no additional cars join the queue beyond
the end of the choice horizon and that queue expelled happens at the greatest rate. The terminal cost is used to
overcome a bias that might cause the signal optimization procedure to pick signal-switching options that
produce a low cost in the short term but a high cost later on.
2.4. Architectural design of the system
The system architecture of the proposed system shows how the system behaves with the aid of a
simple design. As shown in Figure 1, the traffic system must prioritize emergency circumstances. The
administrator logins to the laptop and connects to the Arduino board in which all the wiring of all four lanes is
connected to the Arduino board and also to the ground on the Arduino board, then the traffic light for the
four-lane works. On the preemption of the ambulance, it triggers the light and changes to green for the passage
of the ambulance and returns to the normal traffic flow.
Figure 1. Architectural diagram of a prioritized traffic flow
The algorithm determines which route should be granted a green light based on queue length, vehicle
speed, vehicle acceleration, and car distances from the junction. It defines the sequence in which the various

 ISSN: 2252-8938
4024
green stages ought to be completed and how long they should last. The procedure is then repeated when these
steps have been completed. The sequence of phases is determined by the length of each queue approaching the
intersection, with a bigger queue receiving more priority than a smaller one, and the ambulances which
approach the road first. Furthermore, the algorithm utilizes the journey duration of each lane active in the stage
is determined by the vehicle velocity and distance to the junction. The longest traversing time is then picked
as the stage time frame, as long as it is less than a preset optimum green time of 60 seconds. Three seconds is
the yellow time and red is set to 90 seconds.
3. RESULTS AND DISCUSSION
The model for the prioritized TLC system is designed using a microcontroller and an integrated circuit
i.e. Arduino, a breadboard, jumper wires, a motorcar, LED lights, and Wi-Fi module (T). This system is
employed because of its efficacy, speed, and efficiency. Its functionality and method are simple and easy to
use.
3.1. Testing and evaluation of the system
This system was linked using jumper cables, and each element of the connection functioned well. The
functioning of the system was shown on a tiny carved traffic light board, and its outcomes were carefully tested
against established circumstances, and at any positive of a set conditions something is triggered. Figure 2 shows
the connection of LED lights to the breadboard and jumper wires connected to the breadboard all connected to
the Arduino. The jumper wires are connected respectively to the numbers each on the Arduino, each lane is
connected to 3 spaces each on the Arduino board. The connection of the Arduino board with jumper wires to
the respective 4 lanes of the traffic order and connecting the Arduino to the laptop where the code is written,
the wires are connected to the numbers on the Arduino respectively, and a wire is connected to the ground on
the Arduino board as shown in Figure 3.
Figure 2. Traffic control implementation board Figure 3. Traffic control implementation board
The wires are already connected; the Arduino board is already connected to the system also; it further
shows the light for the four lanes; the first lane is on light, the second lane is on red light, the third lane is on
yellow light about to change to greenlight, then the last lane is on red light as shown in Figure 4. The wires are
already connected; the Arduino board is already connected to the system also; It further shows the light for the
four lanes; The first lane is on a yellow light about to change to a red light, and the second lane is on a red light,
the third lane is on red light about to change to greenlight, then the last lane is on yellow light about to change
to greenlight as shown in Figure 5. Figure 6 shows the lights; The wires already connected; Arduino board
already connected to the system also. It further shows when the ambulance is approaching a particular lane
which is on red; when it receives the signal that the ambulance is approaching from the code it changes to green
light for the passage of the ambulance and goes back to the normal position.

4025
Figure 4. Traffic control board simulation with
prioritized model
Figure 5. The traffic light board shows a yellow
light on the first lane
Figure 6. Traffic light signaling to the ambulance approaching
3.2. Statistical analysis
One sample t-test was conducted to determine the average distance at which the ambulance is detected.
Results show that t=-1, df=14, p-value=0.3343 with a 95% confidence interval (298.9517, 300.3816) for the
mean. Since the p-value=0.3343 is greater than the significance level, 0.05, it was observed that the average
distance at which an ambulance is detected is 300 meters. For the accuracy of the normal traffic flow, a
one-sample t-test was conducted. Accuracy of red traffic lights, there was no need to conduct the t-test since
all the times recorded were 90 seconds. This implies that the red traffic light is accurate in its time delay.
For accuracy of the yellow light for the normal traffic flow: results show that t=-1.8708, df=14,
p-value=0.08242 with a 95% confidence interval (2.570713, 3.029287) for the mean. Since p-value=0.08242
is greater than the significance level, 0.05, we conclude that the yellow light delay is 3 seconds. As such the
yellow light delay time is accurate.
For accuracy of the green light for the normal traffic flow: results show that t=1, df=14,
p-value=0.3343 with a 95% confidence interval (29.92368, 30.20965) for the mean. Since p-value=0.3343 is
greater than the significance level, 0.05, we conclude that the green light delay is 30 seconds. For the green
light passage for the ambulance, a one-sample t-test was also conducted. Results show that t=-1.4446, df=14,
p-value=0.1706 with a 95% confidence interval (28.01227, 30.38773) for the mean. Since p-value=0.1706 is
greater than the significance level, 0.05, we conclude that the green light passage time for the ambulance is 30
seconds.
3.3. Discussion
The creation of a PTLCSM has enormous promise for improving traffic flow, decreasing congestion,
and shortening emergency response times. This statistical study sheds light on the model's performance in

 ISSN: 2252-8938
4026
terms of both regular traffic and ambulance prioritizing. The PTLCSM could be used to create sophisticated
systems that utilize advanced technology and algorithms for dynamic traffic signal control prioritizing
emergency vehicles like ambulances but also allowing normal vehicular movement. The key components of
the PTLCSM are; i) real-time data using sensors: employs a network of traffic sensors and cameras to gather
up-to-the-minute records of traffic density, vehicle types, and on-road status; ii) technologies of
communication: utilizes vehicle-infrastructure communication (V2I) to detect and prioritize emergency
vehicles approaching intersections; and iii) traffic management based on algorithms: incorporates algorithms
capable of rapidly changing signal phases depending on actual road conditions and requiring priorities for
ambulances and other emergency vehicles to allow them to cross junctions quickly without any problems. The
organization PTLCSM guarantees these gains for movements across cities. Including but not limited to; better
traffic modulating efficiency and multi-sectoral influencing factors; such as increased safety where quicker
clearances are provided for ambulances thus providing good patient results in case of medical emergencies;
lowered CO2 emissions that are attributed to less time spent idling and more fluid driving conditions; less time
spent in traffic can lead to lower fuel usage and thus increased productivity at an economical level.
3.4. Key findings
The major findings of this research are as follows:
a. Ambulance detection: the average distance at which ambulances are identified is 300 meters, giving the
system enough time to prioritize traffic signals.
b. Normal traffic flow
− The red-light delay is consistently 90 seconds.
− The yellow light delay is 3 seconds.
− The green light delay is precise at 30 seconds.
c. Prioritization of ambulances: the green light passage duration for ambulances is also correct at 30 seconds,
guaranteeing a smooth and quick transit.
According to the statistical analysis, the PTLCSM meets its objectives for both regular traffic flow and
ambulance prioritizing. The technology recognizes ambulances at a safe distance, prioritizes their passage
through green lights, and keeps all traffic lights on time.
3.5. Further considerations
While the study yields encouraging results, it should be noted that it is based on a small sample size.
Larger dataset testing might reinforce the conclusions and give more generalizable results. The investigation
concentrated on the precision of timing and detection. Future research might look at how the PTLCSM affects
other variables including traffic congestion, travel time, and pollutants. The PTLCSM's efficacy may differ
based on factors such as traffic density, road layout, and emergency vehicle type. More study is required to
understand how the system functions in various settings.
4. CONCLUSION
The PTLCSM has enormous potential to revolutionize traffic management. This statistical study gives
positive evidence of its precision and efficacy. However, further study is required to properly comprehend the
system's strengths and limits. We can get closer to developing smarter, safer, and more efficient cities for
everyone if we continue to enhance and improve the PTLCSM. According to the statistical analysis, the timings
of the traffic light system are compatible with the criteria specified for the red, yellow, and green lights, as well
as the ambulance detection distance. The fact that the p-values for all tests were larger than 0.05, except for the
red light (where the test was not relevant), indicates that there is no substantial evidence that the timings deviate
from their respective hypothesized values. In terms of timing accuracy, the research appears to be rigorous and
shows a well-functioning traffic signal system.
REFERENCES
[1] G. Pau, T. Campisi, A. Canale, A. Severino, M. Collotta, and G. Tesoriere, “Smart pedestrian crossing management at traffic light
junctions through a fuzzy-based approach,” Future Internet, vol. 10, no. 2, 2018, doi: 10.3390/fi10020015.
[2] A. A. Emmanuel et al., “Vehicle-caused road accidents of four major cities in the north-central region of Nigeria. (2010 – 2015),”
International Journal of Civil Engineering and Technology, vol. 10, no. 2, pp. 124–134, 2019.
[3] A. Kathuria and P. Vedagiri, “Evaluating pedestrian-vehicle interaction dynamics at un-signalized intersections: A proactive
approach for safety analysis,” Accident Analysis and Prevention, vol. 134, 2020, doi: 10.1016/j.aap.2019.105316.
[4] D. L. Guidoni, G. Maia, F. S. H. Souza, L. A. Villas, and A. A. F. Loureiro, “Vehicular traffic management based on traffic
engineering for vehicular ad hoc networks,” IEEE Access, vol. 8, pp. 45167–45183, 2020, doi: 10.1109/ACCESS.2020.2978700.
[5] K. Nellore and G. P. Hancke, “A survey on urban traffic management system using wireless sensor networks,” Sensors, vol. 16, no.
2, 2016, doi: 10.3390/s16020157.

4027
[6] R. Vani, N. Thendral, J. C. Kavitha, and N. P. G. Bhavani, “Intelligent traffic control system with priority to emergency vehicles,”
IOP Conference Series: Materials Science and Engineering, vol. 455, no. 1, 2018, doi: 10.1088/1757-899X/455/1/012023.
[7] A. E. Retallack and B. Ostendorf, “Current understanding of the effects of congestion on traffic accidents,” International Journal
of Environmental Research and Public Health, vol. 16, no. 18, 2019, doi: 10.3390/ijerph16183400.
[8] A. Almutairi, P. Yi, and M. Owais, “New approach for estimating intersection control delay from passive traffic sensors at the
network level,” IEEE Access, vol. 12, pp. 2882–2900, 2024, doi: 10.1109/ACCESS.2024.3349499.
[9] G. P. Nithya and A. C. Miniyadan, “Priority-based intelligent traffic control for emergency vehicles at intersections using IoT,”
International Research Journal of Engineering and Technology, vol. 8, no. 3, pp. 1415–1417, 2021.
[10] O. Ajayi, A. Bagula, I. Chukwubueze, and H. Maluleke, “Priority-based traffic pre-emption system for medical emergency vehicles
in smart cities,” 2020 IEEE Symposium on Computers and Communications (ISCC), Rennes, France, 2020, pp. 1-7, doi:
10.1109/ISCC50000.2020.9219628.
[11] H. Hsiao, J. Chang, and P. Simeonov, “Preventing emergency vehicle crashes: status and challenges of human factors issues,”
Human Factors, vol. 60, no. 7, pp. 1048–1072, 2018, doi: 10.1177/0018720818786132.
[12] V. V. Dixit, S. Chand, and D. J. Nair, “Autonomous vehicles: Disengagements, accidents and reaction times,” PLoS ONE, vol. 11,
no. 12, 2016, doi: 10.1371/journal.pone.0168054.
[13] J. A. -Mora, S. Samaranayake, A. Waller, E. Frazzoli, and D. Rus, “On-demand high-capacity ride-sharing via dynamic trip-vehicle
assignment,” Proceedings of the National Academy of Sciences of the United States of America, vol. 114, no. 3, pp. 462–467, 2017,
doi: 10.1073/pnas.1611675114.
[14] S. Djahel, R. Doolan, G. M. Muntean, and J. Murphy, “A communications-oriented perspective on traffic management systems for
smart cities: challenges and innovative approaches,” IEEE Communications Surveys and Tutorials, vol. 17, no. 1, pp. 125–151,
2015, doi: 10.1109/COMST.2014.2339817.
[15] J. Guanetti, Y. Kim, and F. Borrelli, “Control of connected and automated vehicles: State of the art and future challenges,” Annual
Reviews in Control, vol. 45, pp. 18–40, 2018, doi: 10.1016/j.arcontrol.2018.04.011.
[16] R. Hult, G. R. Campos, E. Steinmetz, L. Hammarstrand, P. Falcone, and H. Wymeersch, “Coordination of cooperative autonomous
vehicles: toward safer and more efficient road transportation,” IEEE Signal Processing Magazine, vol. 33, no. 6, pp. 74–84, 2016,
doi: 10.1109/MSP.2016.2602005.
[17] J. Essien and F. Uloko, “Intelligent 3-way priority-driven traffic light control system for emergency vehicles,” Open Journal of
Applied Sciences, vol. 13, no. 8, pp. 1207–1223, 2023, doi: 10.4236/ojapps.2023.138095.
[18] N. E. Mohamed and I. I. Radwan, “Traffic light control design approaches: a systematic literature review,” International Journal
of Electrical and Computer Engineering (IJECE), vol. 12, no. 5, pp. 5355-5363, Oct. 2022, doi: 10.11591/ijece.v12i5.pp5355-5363.
[19] A. Bisht, K. Ravani, M. Chaturvedi, N. Kumar, and S. Tiwari, “Indigenous design of a Traffic Light Control system responsive to
the local traffic dynamics and priority vehicles,” Computers and Industrial Engineering, vol. 171, 2022, doi:
10.1016/j.cie.2022.108503.
[20] W. N. S. F. W. Ariffin et al., “Real-time dynamic traffic light control system with emergency vehicle priority,” Journal of Physics:
Conference Series, vol. 1878, no. 1, 2021, doi: 10.1088/1742-6596/1878/1/012063.
[21] N. Kumar, S. S. Rahman, and N. Dhakad, “Fuzzy inference enabled deep reinforcement learning-based traffic light control for
intelligent transportation system,” IEEE Transactions on Intelligent Transportation Systems, vol. 22, no. 8, pp. 4919–4928, 2021,
doi: 10.1109/TITS.2020.2984033.
[22] A. Peter, B. Zachariah, L. P. Damuut, and S. Abdulkadir, “Efficient traffic control system using fuzzy logic with priority,”
Communications in Computer and Information Science, vol. 1350, pp. 660–674, 2021, doi: 10.1007/978-3-030-69143-1_50.
[23] G. Li, G. Song, and W. Li, “Intelligent traffic light system for high priority vehicles,” Communications in Computer and Information
Science, vol. 1101, pp. 212–223, 2019, doi: 10.1007/978-981-15-1785-3_16.
[24] A. Dodia, S. Kumar, R. Rani, S. K. Pippal, and P. Meduri, “EVATL: A novel framework for emergency vehicle communication
with adaptive traffic lights for smart cities,” IET Smart Cities, vol. 5, no. 4, pp. 254–268, 2023, doi: 10.1049/smc2.12068.
[25] M. Emanuel, “Challenging the system: Pedestrian sovereignty in the early systemisation of city traffic in Stockholm, ca. 1945–
1955,” Journal of Transport History, vol. 42, no. 2, pp. 247–276, 2021, doi: 10.1177/0022526620987795.
[26] O. J. Aroba, T. Xulu, N. N. Msani, T. T. Mohlakoana, E. E. Ndlovu, and S. M. Mthethwa, “The adoption of an intelligent waste
collection system in a smart city,” in 2023 Conference on Information Communications Technology and Society (ICTAS), pp. 1-6.
IEEE, 2023, doi: 10.1109/ICTAS56421.2023.10082750.
[27] O. J. Aroba, “Improving node localization and energy efficiency for wireless sensor networks using hyper-heuristic optimization
algorithms,” Ph.D. Thesis, Durban University of Technology, Durban, South Africa, 2022.
[28] O. J. Aroba, P. Mabuza, A. Mabaso, and P. Sibisi, “Adoption of smart traffic system to reduce traffic congestion in a smart city,”
in International Conference on Digital Technologies and Applications, pp. 822-832, Cham: Springer Nature Switzerland, 2023, doi:
10.1007/978-3-031-29857-8_82.
[29] T. T. Adeliyi, D. Oluwadele, K. Igwe, and O. J. Aroba, “Analysis of road traffic accidents severity using a pruned tree-based model,”
International Journal of Transport Development and Integration, vol. 7, no. 2, 2023, doi: 10.18280/ijtdi.070208.
BIOGRAPHIES OF AUTHORS
Halleluyah Oluwatobi Aworinde lectures at the Computer Science Programme
College of Computing and Communication Studies, Bowen University, Iwo. He has a B.Tech.,
M.Sc., and Ph.D. in Computer Science. His research interests include AI, machine learning,
intelligent systems, information security, pattern recognition, image processing, and
biometrics. He has more than 10 years of experience in teaching and research. He can be
contacted at email: aworinde.halleluyah@bowen.edu.ng.

 ISSN: 2252-8938
4028
Abidemi Emmanuel Adeniyi received the B.Sc. and M.Sc. degrees in computer
science from Ladoke Akintola University of Technology, Ogbomoso, and Landmark
University, Omu-Aran, Nigeria, in 2019 and 2021, respectively, and he is currently a research
student at the Department of Computer Science, University of Ilorin and a lecturer in the
Department of Computer Science, Bowen University, Iwo, Nigeria. He has authored or
co-authored more than 50 journal and conference papers, and 50 book chapters with Elsevier
and Springer. His research interests include internet of things security, information security,
applications of artificial intelligence, application of machine learning for intrusion detection,
internet of medical things, and cryptographic algorithms. He can be contacted at email:
abidemi.adeniyi@bowen.edu.ng.
Segun Adebayo holds a Ph.D. in Electrical and Electronics Engineering. He is a
passionate scholar and researcher in the Department of Mechatronics Engineering, at Bowen
University, Iwo. He is an Assistant Professor with research interests in energy, communication
and signal processing, machine learning, robotics, and the internet of things. He is a member
of the Nigeria Society of Engineers (NSE), the Council for the Regulation of Engineering in
Nigeria (COREN), and the International Association of Engineers (IAENG). He can be
contacted at email: segun.adebayo@bowen.edu.ng or shegdabayo@yahoo.com.
Faith Adeniji is a computer science professional with a B.Sc. from Bowen
University and an M.Sc. from the University of Ibadan. Her research interests include artificial
intelligence, machine learning, and data science, with a passion for leveraging technology to
drive growth, improve efficiency, and enhance lives. She can be contacted at email:
faithadeniji91@gmail.com.
Oluwasegun Julius Aroba is an Artificial Intelligence and Data Science Expert
at the University of Johannesburg, was recently selected as one of the top 10 South African AI
specialists in 2024, a senior lecturer, and an Honorary Research Associate at Durban University
of Technology. He has a Ph.D. in Information Technology. A graduate of Information
Technology University from the prestigious Coventry University United Kingdom, B.Sc.
Computer Science and Technology (upper-class division) Crawford University whose research
inclination focus area are into wireless sensor networks, project management, data science,
machine learning, SAP specialist, robotics, and artificial intelligence with over a decade year
of experience in the higher education sector, healthcare industries, government parastatals, a
consultant across the globe, a graduate member of IEEE, IITPSA South Africa, Member of
IET UK. He has authored or coauthored more than 30 journals, conference papers, and book
chapters with Elsevier, IEEE, and Springer. He has chaired and co-chaired international and
national conferences. He is a board member of SAIMC, Lifestyle Asset Hub, Founder of
Aroseglinks Services Limited and Julius Aroba Ltd, Zillionaire’s Group, He is a Supervisor of
Ph.D. and Masters/MBA students, and he has graduated over 1000 students under his direct
and indirect supervision from honours, bachelor, masters and MBA & PhD’s. He is a global
mentor to SMEs and European African, Sisonke NdabaX, Guest Editor to Q2 Journal outlet
(Journal of Electrical and Computer Engineering) Scopus index. Seasoned three (3) time
speaker at IndabaX South Africa, Indaba, and a seasoned guest speaker at Global Summit on
Artificial Intelligence USA, and AI master class organizers and speakers. He has a vast
collaboration network across Spain, France, Morocco, Canada, Dubai, Nigeria, Ghana,
Rwanda, Germany, India, USA, The UK, South Africa, India, and Sweden. He can be contacted
at email: jaroba@uj.ac.za or oluwaseguna@dut.ac.za.

Development of a prioritized traffic light control system for emergency vehicles

More Related Content

Similar to Development of a prioritized traffic light control system for emergency vehicles (20)

More from IAESIJAI (20)

Recently uploaded (20)

Development of a prioritized traffic light control system for emergency vehicles