Hindawi

Journal of Advanced Transportation

Volume 2022, Article ID 4687319, 13 pages
https://doi.org/10.1155/2022/4687319

Research Article
Smart Traffic Management System for Metropolitan Cities of
Kingdom Using Cutting Edge Technologies

Mamoona Humayun ,1 Sadia Afsar,2 Maram Fahaad Almufareh,1 N. Z. Jhanjhi,3

and Mashayel AlSuwailem4
1
Department of Information Systems, College of Computer and Information Sciences, Jouf University, Saudi Arabia
2
Department of Software Engineering, International Islamic University, Islamabad, Pakistan
3
School of Computer Science (SCS), Taylor's University, Malaysia
4
Department of Computer Science, College of Computer and Information Sciences, Jouf University, Saudi Arabia

Correspondence should be addressed to Mamoona Humayun; mahumayun@ju.edu.sa

Received 15 June 2022; Revised 6 September 2022; Accepted 14 September 2022; Published 2 September 2022

Academic Editor: Jose E. Naranjo

Copyright © 2022 Mamoona Humayun et al. This is an open access article distributed under the Creative Commons Attribution
License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is
properly cited.

The expansion of technology in metropolitan centers draws people to cities, which causes excessive traffic on the roadways
during peak hours. This exacerbated the traffic situation, resulting in a delay, a loss of resources, and a waste of time. Like
any other metropolitan metropolis, Riyadh, Saudi Arabia, has everyday traffic congestion during business hours. The
current traffic management has made many attempts to ease traffic congestion in cities; despite these measures, the
problem has not been solved adequately. To handle this road congestion, there is a need to appropriately store the big
data collected by traffic sensors and utilize it for efficient traffic management employing cutting-edge technology. This
study provides an architecture for a smart traffic management system that uses modern technologies such as the Internet
of Things (IoT), cloud computing, 5G, and big data to aid conventional traffic management systems and efficiently handle
the stated problem. The proposed technique has the potential to reduce traffic congestion significantly. Our proposed
solution encourages mobility by using roadside messaging agents to offer real-time traffic information on traffic congestion
and unexpected traffic incidents. Citizens will save time by getting these early warning messages, particularly during peak
hours. As part of the suggested method, each signal dashboard gets traffic information. A case study is used in the
research to evaluate alternative solutions to traffic congestion. The case study results show that the proposed strategy
outperforms the present options.

1. Introduction ing time delay. In Riyadh, congestion costs have been proved
to result in a significant economic loss for the city.
In today’s fast-paced world, the rapid increase in automo- The increasing number of vehicles on the road has
biles on the road continues to be a severe concern in big cit- necessitated the development of effective traffic management
ies [1]. In Riyadh [2], traffic congestion is becoming more of systems. The academic research suggested different technol-
a worry as the number of cars on the road continues to grow ogies for monitoring vehicles and recognizing traffic conges-
exponentially, surpassing the capacity of existing infrastruc- tion to improve traffic management [4–6]. Identifying traffic
ture. Furthermore, since the city of Riyadh is growing at a congestion may be accomplished using loop coils and intel-
fast pace, the extent of the issue is expanding in parallel with ligent video cameras (also known as security cameras sys-
the city’s population. It contributes to road traffic congestion tems). A massive amount of data, namely, big data or
[3], becoming more typical with each passing day. Traffic traffic data, is gathered from various sources, including cam-
congestion is one of the key causes of rising transportation eras that serve as sensors, police officers responsible for
expenses, primarily due to excessive gasoline and the result- maintenance, service providers, and drivers on the highways
2 Journal of Advanced Transportation

themselves. However, cameras have several downsides, 1.1.1. Internet of Things. The Internet of Things (IoT) is a
such as being affected by weather conditions and having networked system of interconnected computing devices,
a high installation cost [7]. Therefore, the Kingdom must mechanical and digital machinery, items, animals, or people
use the internet and cutting-edge technologies [8, 9], espe- with unique identities (UIDs), and the capacity to transmit
cially in metropolitan areas, to provide residents with data without needing human-to-human or human-to-
more certainty and dependable services than they now computer contact. It comprises web-enabled smart devices
have. that gather, transmit, and act on environmental data using
Numerous technical advancements in various disci- embedded systems, including CPUs, sensors, and communi-
plines, such as hardware size reduction, wireless technology, cation hardware.
environmental sensors, and integrated computers, have con-
tributed significantly to the physical world. Example 1.1.2. 5G. Fifth-generation wireless (5G) is the most recent
includes, the Internet of Things (IoT) is one of these prom- evolution of cellular technology, developed to boost wireless
ising technologies that has significantly contributed to network speeds and responsiveness significantly. Some esti-
society’s advancement. IoT refers to connecting smart things mates put the maximum speed of 5G at 20 Gbps, allowing
to the internet [10–12], enabling people and machines to for the transmission of multigigabit data through wireless
interact in real-time. The IoT is gradually becoming one of internet connections. Latency is less than 5 ms, making these
ICT’s most notable development and research topics [13]. speeds ideal for applications that need instantaneous
The IoT links various devices, systems, and applications to responses. Because of more bandwidth and improved
provide consumers with more sophisticated services than antenna technology, 5G will allow for a dramatic rise in
traditional machine-to-machine communication [14, 15]. the volume of data sent across wireless networks.
The big data generated through IoT sensors is stored in
Cloud for further usage, and 5G technology helps to trans- 1.1.3. Cloud Computing. Computing resources, such as data
mit this big data among multiple entities involved. storage (cloud storage) and processing power, may be made
The preceding explanation demonstrates how cutting- available on demand in a cloud computing environment
edge technologies contribute significantly to intelligent traf- without requiring the user to take on any administrative
fic management. This study leverages the benefits of responsibilities. Functions in large clouds are generally
advanced technologies, namely, IoT, big data, Cloud com- decentralized over numerous data centers. To accomplish
puting, and 5G, and presents a smart traffic management consistency, cloud computing uses pooled resources and a
architecture for Kingdom metro cities. The proposed “pay as you go” pricing model, both of which may assist
approach is a layered approach based on cutting-edge tech- cut down on upfront costs but can potentially leave con-
nologies. These layers include (1) the physical layer, which sumers unprepared for ongoing service fees.
contains the IoT sensors and agent, as depicted in Figure 1 The remainder of the study is arranged as follows: the
at the roadside. This layer is responsible for sensing, count- second section will discuss relevant traffic management
ing, and uploading the available vehicle data to the Cloud studies; Section 3 will discuss the research methodology; Sec-
using the Wi-Fi controller/5G through the second layer; tion 4 will focus on a case study; Section 5 will include the
(2) the network layer is mainly responsible for uploading results and a discussion of them. The last presents the con-
the data to the Cloud and then syncing that data to the dash- clusion and future work.
board and an updated Google Map for traffic route aware-
ness; (3) the application layer helps with the specifically 2. Related Work
designed dashboards in the cars, equipped with the Google
Map routes, and smart mobile app-based smartphone appli- This section covers recent advances in smart transportation
cation, to assist the drivers with the current traffic situation. research, such as models for traffic analysis, traffic conges-
The explicit contribution of the study is mentioned as tion estimates, and the use of roadside units to send mes-
follows: sages. The following sections cover some recent
developments in the field of traffic management.
(i) Using cutting-edge technologies to provide an The authors of [16] developed a traffic information
appropriate solution for reducing traffic congestion system based on historical traffic data. This research
in metropolitan areas intends to let drivers choose a different route or change
their existing route in the case of a traffic incident. Traffic
(ii) Monitoring real-time traffic on junctions using
speed data was collected via video analysis of varying seg-
magnetic sensors and providing error-free vehicle
ment routes. Each road length is captured using cameras,
detection, particularly during peak hours
which are then processed to get speed information. Using
(iii) Keeping the city residents updated on traffic status the data, an interface is created to show traffic conditions
and significant traffic incidents using Google Maps on an open map with speed restrictions displayed in vari-
ous colors, which may be used as a reference for develop-
1.1. Background. Before moving toward the existing knowl- ing countries where navigation is unavailable. On the
edge in the area under study, this subsection discusses other hand, this technique has some disadvantages, and
cutting-edge technologies used in the study for a better the most significant is that collecting many videos is diffi-
understanding of the readers. cult and time-consuming. Furthermore, only historical
Journal of Advanced Transportation 3

Google map
Cloud
Application
layer

Message agent
Network
layer

Smart traffic management Dashboard

WiFi controller

Open signal
Perception

Smart traffic signal Congestion

layer

Mobile user

Figure 1: IoT-based architecture of Smart Traffic Management System for metropolitan cities.

data is available, rather than real-time traffic statistics, and depending on the traffic density, and a daily report is pro-
it is also restricted to highways. vided via a web application.
According to research [17], the first step in traffic man- In addition to sensors, video monitoring is used to
agement is to identify and assess congestion. Flow, occu- predict traffic congestion intensity and real-time update
pancy, and density are the most regularly used road traffic lights in the study [20]. The proposed paper is
congestion measures, which are often derived from photo- based on a case study of a public route. According to
graphs or videos taken by vision-based cameras. The proto- study findings, surveillance cameras are both costly and
type was developed in this study to assess traffic data from challenging. Another scientific advancement proposed by
public roadways. Web-based applications were used to man- a study [21] is the internet of linked automobiles, which
age traffic data packets. For dynamic signalized intersection collects real-time traffic data from local traffic. Based on
handling based on the traffic density, an IoT-based existing this data, vehicle monitoring is possible with connected
traffic surveillance system has been proposed by [18]. The automobiles. Integrating the road units (such as traffic sig-
suggested approach involves a prototype. It includes two nals) with the vehicular platform ensures that traffic events
components: one for traffic monitoring and another for pri- are reliable. This system was created with highways in
ority scheduling, along with a set of sensors. IoT devices mind as this study predicts drivers using smart devices,
send the density concentrations of a public roadway to the traffic updates via roadside message units are not included.
next signal, and the data is transferred to the server for later The development of the Beijing Olympic region [22] is
use. Ultrasonic sensors were used to identify cars, and the a great example of how to deal with city traffic. In-vehicle
density rates of a public roadway were communicated to monitors are used to keep track of and deliver traffic
another signal by IoT devices. On district roads, the planned information. However, because of new programs and gad-
prototype is put to the test. gets, system development became much more expensive.
The researchers of the paper [19] presented an ultrasonic Following that, a lot of research was done in this field to
controller system model for traffic intersections on signifi- figure out how to improve traffic flow. In paper [23], a
cant highways. Aside from traffic signal lights, the system structure is put in place at decision points to show traffic
also detects illegal vehicle activity, such as crossing red lights. congestion using three different light colors on electronic
Another study [11] proposes an IoT-based intelligent traffic boards. The number of cars on this major highway is esti-
framework to control real-time traffic via a centralized and mated based on the average speed of the vehicles detected
decentralized server. To validate the system, an experiment by automotive detection sensors. The authors used image
is carried out on a national highway. Sensors, camera sys- processing techniques to look at real-time traffic footage,
tems, and RFIDs are used at the data gathering layer. The and optical flow was used to determine the congestion
application layer automatically controls the control signal rate.
4 Journal of Advanced Transportation

One of the key features of “smart cities” is the mobile app-based smartphone application to assist the
connected-vehicle infrastructure. All automobiles and drivers with the current traffic situation.
other road users’ real-time data is necessary to fully realize
the advantages of connected-vehicle technology. Existing 3.1. Working of the Proposed Methodology. In the proposed
connected-vehicle deployments, however, only learn about system, sensors detect the presence of cars on the road,
the connected cars’ current condition in real time, while and actuators determine their quantity. This count is com-
still being in the dark about the unconnected traffic that pared to the predetermined threshold number to determine
shares the roads with them. Finding a method to gather the road’s condition. The information collected by sensors
the disconnected road users’ high-resolution real-time sta- and actuators is saved in the Cloud for decision-making pur-
tus is essential. Because it will be impossible for all auto- poses. If the number of vehicles on the road is fewer than the
mobiles, pedestrians, and bicycles to actively broadcast threshold figure, the dashboard will display a green signal,
their real-time status in the near future, improving traffic indicating that the road is not crowded. If the number of
infrastructures to actively recognize and broadcast each vehicles on the road exceeds the threshold amount, a red
road user’s status is a natural way to bridge the data indicator will show on the driver’s dashboard to indicate
gap. With the help of roadside LiDAR sensors and DSRC traffic congestion.
roadside units, the next generation of linked infrastruc- Below, we provide the detailed working of the compo-
tures introduced in paper [24] may actively detect the nents used in the proposed architecture.
high-resolution state of surrounding traffic participants.
However, LiDAR has numerous drawbacks, including a 3.2. Magnetic Sensors. Magnetic sensors are a kind of mul-
hefty price tag and the inability to gauge distances in con- tisensor system that is used to recognize many types of
ditions of severe rain, snow, or fog. vehicles [27]. As vehicle movement influences the Earth’s
The above discussions show that current studies address magnetic field in the monitored location, this magnetic
the problem of traffic congestion management on different disturbance may be detected with the help of appropriate
city roads such as district roads, urban areas, and a section magnetic sensor equipment. The HMC-5883L magnetic
of the highway, as well as real-time monitoring and traffic sensor is extensively employed in traffic monitoring due
control. However, some of the most cutting-edge technolo- to its high sensitivity and low cost [28, 29]. Its vehicle
gies, such as IoT and cloud computing, may help to improve identification rate is 99 percent correct. As a result, in
traffic monitoring systems in major cities. To leverage the our suggested architecture for gathering vehicle data, we
potential benefits of modern cutting-edge technologies in employed the HMC-5883L magnetic sensor. The magneto-
getting context awareness and providing real-time traffic resistive sensor used by HMC5883L is constructed of
updates [25, 26], this paper proposes an IoT-based architec- nickel-iron (Ni-Fe magnetic film) and is set up in a bridge
ture to provide mobile users with real-time traffic updates circuit. Its electrical resistance changes as the magnetic
via roadside message agents and Google Maps. This smart field being applied changes. The earth’s magnetic field
traffic management is required in metropolitan areas to interacts with the nickel-iron substance in space in a way
avoid congestion, control delays, and comfort end-users that affects its resistance, which in turn causes voltage
daily, especially during peak hours. fluctuations across the bridge. The direction of the mag-
netic field in space may be determined using this voltage
change. Among the characteristics of HMC5883L are: it
3. Proposed Methodology may be used for inexpensive magnetometry and compass-
ing. Compass heading accuracy is up to 1 to 2 degrees and
This section covers in detail our proposed three-tier archi- it contains a 12-bit ADC. Anisotropic Magneto Resistive
tecture, which includes different components such as vehi- (AMR) technology from Honeywell is used in it, and it
cle sensors, roadside message agents, Cloud-based server, offers accuracy in axis sensitivity and linearity. To inter-
Google Map, and user dashboard, as seen in Figure 1. face with microcontrollers, it employs the I2C communi-
The suggested architecture’s detailed operation is also cation protocol. When an automobile or any other metal
illustrated using an algorithm and a flow chart in object passes over the HMC5883L AMR sensor, which
Figure 2. The first layer of the proposed architecture is measures the earth’s magnetic field in three directions (x,
the physical layer; this layer contains the sensors and actu- y, and z), the earth magnetic field is disturbed, and the
ator/software agents working at the roadside. Sensors are values of x, y, and z are significantly altered from their ini-
responsible for capturing vehicle images while the actua- tial values. The sensor offers a resolution of up to 5 milli-
tors count the vehicles and upload the vehicle data to Gauss and a full-scale range of 8 Gauss.
the Cloud using Wi-Fi controller/5G through the second
layer. The second layer of the proposed architecture is 3.3. Actuators. Actuators are autonomous software agents
the network layer which is mainly responsible for upload- that have been created as a low-cost option for tackling com-
ing the data to the Cloud and then syncing that data to plicated issues across a wide range of application fields [30,
the dashboard and an updated Google Map for traffic 31]. Actuators in the proposed architecture operate as mes-
route awareness. The third layer is the application layer, sage agents to improve traffic flow by learning a traffic man-
which helps with the specifically designed dashboards in agement policy that determines when to show signal status,
the cars, equipped with the Google Map routes and smart which measures the number of cars at a specific signal
Journal of Advanced Transportation 5

Start Sensing V1, V2, V3 Count vehicles Set threshold = 10

User request Store in cloud

Yes
If user request = Store cloud = Sum of
Dasboard vehicle

No

No
User request = Google map If store cloud < Sets signal color = Red
threshold

Yes
Store cloud = Sum of vehicle Dashboard = Some of
vehicles, Red
Sets signal color = Green

Store in cloud
If store cloud >
Dashboard = Some of vehicles,
threshold
Green
No Yes

Sets signal color = Green Sets signal color = Red Store in cloud

Google map = Green Google map = Red

Output “low traffic flow” Output “traffic congestion”

Store in cloud Store in cloud

End

Figure 2: Real-time traffic updates on signal dashboard and Google Map.

[32]. Actuators collect vehicles’ information and upload this 3.4. Mongo DB Atlas as Cloud Storage. MongoDB Atlas is a
data to the Cloud using Wi-Fi controller/5G through the multicloud database service that allows you to construct
network layer. durable and performant global applications on your
6 Journal of Advanced Transportation

preferred cloud providers [33]. MongoDB Atlas is used in where gradient of ℂℊ packages all its partial derivatives into
the proposed architecture to store vehicle information and a vector as shown in Equation (8)
then sync this information to the dashboard and an updated
2 3
Google Map for traffic route awareness. We picked Mon- ∂ℂℊ
goDB Atlas due to its robust access control and broad query 6 ∂sv 7
6 7
language. 6 7
6 ∂ℂℊ 7
6 7
3.5. LCD Unit. Dashboards are character-type LCD devices 6 ∂cv 7
6 7
that are Wi-Fi enabled [34, 35] and are used to display mes- 6 ∂ℂℊ 7
sages in the proposed design. Vehicles dashboard is ∇ℂℊ = 6
6
7:
7 ð8Þ
6 ∂uvc 7
equipped with Google Map routes and a smart mobile 6 7
6 ∂ℂℊ 7
app-based application to assist the drivers with the current 6 7
6 ∂sd 7
traffic situation. 6 7
6 7
4 ∂ℂℊ 5
4. Mathematical Modeling and Evaluation ∂uℊm
The proposed approach aims to minimize traffic congestion
by providing timely intimation to the drivers on their dash- 4.1. Case Study. In this section, we will evaluate the proposed
boards using cutting-edge technologies. The objective func- methodology using a real-life case study and will discuss the
tion in our case is to reduce traffic congestion by results in detail
optimizing traffic information updates. Table 1 lists down A case study of the Smart Traffic Management System is
the notations used for mathematical modeling conducted in a metropolitan city of the Kingdom. The steps
involved in conducting a case study are:
ℴϜ = minimizeðℂℊ Þunder I, ð1Þ
(1) Capturing images
where (2) Counting Vehicles
[
n (3) Updating Traffic dashboard with real-time traffic
ℂℊ = f ðsv, cv, uvc, sd, uℊmÞ, ð2Þ data
v=1
(4) Sending data on user devices through Google Maps
where ν = 1 to n represents the number of vehicles presented
on the road. Consider a traffic scenario with heavy traffic during
The ℂℊ will be minimized ⇔sv⋒cv⋒uvc⋒sd⋒uℊm crowding hours and having four entry and exit points, as
=1 shown in Figure 3
All the factors affecting congestion optimization will be
true in the normal situation; however, during I, there is a (a) Empty roads and interconnection on road A
chance that the absence or lack of any of these factors will (b) Vehicles are approaching near to intersection on
affect the ℂℊ control. To evaluate the effect of individual fac- road B
tors on ℂℊ, we need to consider the partial derivative of
Equation (2) w.r.t. mentioned factors as shown in Equations (c) Vehicles are approaching near to intersection on
(3)–(7), where h ⟶ 0 implies that we are interested in road C
extremely tiny values of h those close to 0. (d) Vehicles are approaching near to intersection on
∂ℂℊ f ðsv + h, cv, uvc, sd, uℊmÞ − f ðsv, cv, uvc, sd, uℊmÞ
road D
= lim ,
∂sv h⟶0 h
4.2. Case A: Road A with Zero Traffic towards the
ð3Þ Junction. Using the suggested architecture, traffic manage-
ment in the instance (a) of the case study is controlled in
∂ℂℊ f ðsv, cv + h, uvc, sd, uℊmÞ − f ðsv, cv, uvc, sd, uℊmÞ
= lim , ð4Þ such a manner that IoT sensors capture vehicle images.
∂cv h⟶0 h
Actuators/message agents count the number of cars
∂ℂℊ f ðsv + h, cv, uvc + h, sd, uℊmÞ − f ðsv, cv, uvc, sd, uℊmÞ approaching the intersection. Actuators are also in charge
= lim ,
∂uvc h⟶0 h
of storing big data in the Cloud through a Wi-Fi control-
ð5Þ ler/5G. The Actuator/message agent provides the most
∂ℂℊ f ðsv + h, cv, uvc, sd + h, uℊmÞ − f ðsv, cv, uvc, sd, uℊmÞ current vehicle status to the user’s dashboard through
= lim ,
∂sd h⟶0 h Cloud and Google Maps. The dashboard provides all vehi-
ð6Þ cle data concerning the concerned intersection, which
helps drivers stay informed about traffic conditions. There
∂ℂℊ f ðsv + h, cv, uvc, sd, uℊm + hÞ − f ðsv, cv, uvc, sd, uℊmÞ
= lim , are specifically designed dashboards in the cars, equipped
∂uℊm h⟶0 h
with the Google Map routes and smart mobile app-based
ð7Þ smartphone applications to assist the drivers with the
Journal of Advanced Transportation 7

Let V1 ⋯ ::Vn are vehicles on the Road.

1: Begin.
2: Read V1 ⋯ ::Vn:
3: Compute CountVehicle ΣV ⟵ V1 + V2 + V3 ⋯ ::Vn
4: Set Threshold ←10
5: Initialize User Request ←Dashboard or GoogleMap
////////////////////Traffic Updates on Signal Dashboard/////////////
6: While User Request==Dashboard
7: Store.Cloud ←Count Vehicle
8: If (Store.Cloud <Threshold) then
9: Active Message.Agent
10: Set Signal.Colour←Green
11: Dashboard ←ΣV,Signal.Colour
12: Updat Store.Cloud
else
13: Store.Cloud←Heavy traffic
14: Set Signal Color ←Red
15: Dashboard ←ΣV,Signal.Color
16: Goto step userRequest
////////////////////Message Popup on Users Smartphones////////////
17: While User Request==GoogleMap
18: Store.Cloud ←Count Vehicle
19: If (Store.Cloud >Threshold) then
20: Active Message.Agent
21: Set Signal.Colour←Red
22: GoogleMap ←Signal.Color
23: Output←Traffic Congestion
24: Update Store.Cloud
else
25: Store.Cloud←Empty Road
26: Set Signal Color ←Green
27: GoogleMap ←Signal.Color
28: Output←Smooth Passage
29: Update Store Cloud
30: End.

Algorithm 1: Proposed algorithm.

Table 1: Symbols used for mathematical modeling.

in case study instance (b) is regulated in such a way that
Symbols Used for IoT sensors identify vehicles. Message agents count the
ℴϜ Objective function total number of vehicles, which is 10 in this case, as indi-
cated in Figure 3, and save this data to the Cloud through
ℂℊ Traffic congestion
Wi-Fi controller/5G. The messaging agent is constantly
I Peak hours timings updating the cloud storage. The Dashboard in the car
sv Sensing vehicle/capturing vehicle images receives traffic data from Google Maps through Cloud.
cv Counting vehicles The updated data comprises traffic statistics on the
affected route since the number of vehicles on the road
uvc Uploading vehicle data to Cloud
exceeds the threshold value. In this situation, a red signal
sd Syncing dashboards will display on the user’s dashboard, indicating traffic con-
uℊm Update Google Map gestion. This early warning message benefits drivers in
lowering the driving time and arriving on time.
current traffic situation. These dashboards display a red or
green indicator indicating traffic congestion or a smooth 4.4. Case C: Vehicles Are Oncoming near to Intersection on
journey. Users get a green light on Google Maps in this Road C. Using the proposed architecture, traffic manage-
situation since there is no traffic on the road and the user ment in case study instance (c) is regulated in such a
has a clear path to go. way that IoT sensors identify cars. Message agents counted
four cars and this data is transmitted to the Cloud. Fol-
4.3. Case B: Vehicles Are Oncoming near to Intersection on lowing processing, vehicle data is received on the users’
Road B. Using the proposed architecture, traffic management dashboard. In this situation, a green signal will display
8 Journal of Advanced Transportation

Table 2: Vehicle detection and counting using IoT sensors and

Road C
actuators.

Road Real vehicle Detected

RSU3
RSU2 Road D A 00 00
B 10 10
C 04 04
D 08 08
Road B
In this case study, we set the sync timing of communica-
Road A

RSU1 RSU4 tion messages between sensors, message agents, and the
Cloud to 3 seconds. This value demonstrates the efficacy
of our recommended approach. Figure 5 shows the time
Figure 3: Case study description of road junctions. consumption of communication messages between sensors,
message agents, and the Cloud.
on the user’s dashboard, indicating that there is little traf-
fic, and the driver will get a delay-free signal. 5.2.1. Road A. Sensors detect no vehicles. It takes 0.5 seconds
to sense the vehicle, and the message agent takes 1.5 seconds
4.5. Case D: Vehicles Are Approaching near to Intersection for all processing and sends it to the Cloud. In contrast, all
on Road D. Using the proposed architecture, traffic man- the data is stored and updated in only 02 sec. At the same
agement in case study instance (d) is regulated in such a time, our threshold value is 3 sec.
way that IoT sensors identify cars. Message agents counted
5.2.2. Road B. Sensors detect ten vehicles. It takes 1.0 sec-
eight vehicles. In this situation, a red signal will display on
onds to sense the vehicles, and message agent takes 2.0 sec-
the user’s dashboard, indicating traffic congestion. This
onds for all processing and sending to the Cloud. In
enables drivers to save time and arrive at their destination
comparison, all the data is stored and updated in only
on time.
03 sec, matching our threshold value.
5. Results and Discussion 5.2.3. Road C. Sensors detect 04 vehicles. It takes 0.5 seconds
to sense the vehicles, and the message agent takes 1.75 sec-
As mentioned in the previous section, a case study was per- onds for all processing and sends to the Cloud. At the same
formed to demonstrate the proposed architecture’s applica- time, all the data is stored and updated in only 2.25 sec. Sync
bility. This section provides the results of the case study; message timing is less than our threshold value.
our results will focus on the following two main functions:
5.2.4. Road D. Sensors detect 08 vehicles. It takes 0.75 sec-
(i) Collection and counting of vehicles onds to sense the vehicles, and the message agent takes
1.75 seconds for all processing and sends to the Cloud. At
(ii) Broadcast message on dashboard and Google Map
the same time, all the data is stored and updated in only
To assess the resulting values for correctness, we estab- 2.75 sec.
lished a threshold value against which the obtained values This reveals that our proposed system takes less time to
may be compared. Below, we discuss our findings in detail. transport messages from the sensor to the cloud repository,
demonstrating its efficacy.
5.1. Collection and Counting of Vehicles. Table 2 presents the The proposed architecture is compared with an existing
evaluation of IoT sensors and actuators used to collect and solution by real-time data collection to a cloud repository.
count vehicles in the given case study scenario. Figure 6 represents the calculated timing of messages to
As seen from the data in Table 2 and Figure 4, the reach collected data to the citizens of the Kingdom by broad-
total number of vehicles on all four roads at a junction casting on the signal dashboard or showing on Google Map
identified by sensors and tallied via the actuator is the by the end user’s request from their smartphones.
same as the total number of cars on all four lanes. This
5.2.5. Road A. Signal dashboard takes 3.5 secs to update the
demonstrates that the proposed architecture’s vehicle
traffic status. In comparison, Google Map takes 4 secs to
detection and counting approach using IoT sensors and
update the traffic signal status.
actuators is sufficient in all situations.
5.2.6. Road B. Signal dashboard takes 4.0 secs to update the
5.2. Sync Message on Dashboard and G-Map. In real-time traffic status. In comparison, Google Map takes 4.5 secs to
traffic data, Smart Traffic Management System uses update the traffic signal status.
cutting-edge technologies to collaborate with road junc-
tions and agents to build signal dashboards, store real- 5.2.7. Road C. Signal dashboard takes 3.65 secs to update the
time traffic data, and continuously update data in Cloud traffic status. In comparison, Google Map takes 4.25 secs to
storage to save time and provide convenience to users. update the traffic signal status.
Journal of Advanced Transportation 9

Vehicle detection accuracy on the road

10

4
Accuracy
2

0 Detected
Road-A
Road-B
Road-C Real vehicle
Road-D
0-2 6-8
2-4 8-10
4-6

Figure 4: Vehicle detection accuracy on the road.

Sync timing of message between sensor, message agent & cloud

3
2.75

2.25
2

3 2
1.75
1.75
2.5 1.5

1.5 1
0.75 Sensor to cloud time
1 0.5
0.5
Message agent
0.5
Sensor
0
Road A Road B Road C Road D

Sensor
Message agent
Sensor to cloud time

Figure 5: Sync timing of communication messages between sensors, message agents, and Cloud.

5.2.8. Road D. Signal dashboard takes 3.75 secs to update the tional to the number of vehicles detected on every road
traffic status. In comparison, Google Map takes 4.0 secs to junction.
update the traffic signal status. The case study results demonstrated accuracy in vehi-
Figure 7 represents the sync time between components cle detection with zero error, and timings of various mes-
of the proposed solution, which is further elaborated in Fig- sages sent to the dashboard and Google Map were
ures. 8 and 9. Real-time traffic information is broadcasted on elaborated. As a result, the proposed architecture can help
the signal dashboard and Google Map. Figure 7 shows that citizens of the Kingdom save time and fuel by receiving
message timing between components is directly propor- early messages on smartphones, particularly during
10 Journal of Advanced Transportation

Sync timing of messages between cloud, signal dashboard & google map
4.5
4.25
4 4

4
3.65 3.75
3.5
4.5
4 3
3.5 2.75
3 2.25
2.5
2 1 Google map
1.5
1 Signal dashboard
0.5 Cloud
0
Road A Road B Road C Road D

Cloud
Signal dashboard
Google map

Figure 6: Sync timing communication messages between Cloud, signal dashboard, and Google Map.

Vehicle vs time (sensor to cloud sync time (s))

10

6
4
2
Vehicle
0
Road-A
Road-B
Road-C Sensor to cloud time
Road-D
0-2 6-8
2-4 8-10
4-6

Figure 7: Road vise total sync time (sensor—Google Map) and (sensor—signal dashboard).

crowning hours. These messages will assist with traffic Successfully Addressed = ♦♦
congestion and unusual incidents, and citizens can arrive Partially addressed = ♦◊
at their destinations on time. Not Addressed = ◊◊
The above discussion shows that the proposed solution Three parameters are selected to have a broader look at
can be implemented in metropolitan cities of the Kingdom efficiency and accuracy. These parameters are real-time traf-
to improve citizens’ lifestyles. They get updated information fic collection and counting. Real-time traffic updates on the
on their mobile phones or previous signal dashboard. These signal dashboard and Google Map, as shown in Table 3.
alert messages help citizens consume valuable time and Because IoT devices are more accurate than traditional
reach their targeted area on time. cameras, real-time vehicle collection in existing ETM is less
To evaluate the main objective of the research, Table 3 accurate than smart traffic management (STM). No dash-
compares Existing Traffic Management (ETM) with our board data is built-in to ETM because our proposed solution
proposed solution in which we define different parameters is provided on each signal. Google Map provides traffic
such as successfully addressed, partially addressed, and not updates, resulting in a more efficient Smart Traffic Manage-
addressed by assigning symbols as shown below. ment System than ETM. The results show that based on
Journal of Advanced Transportation 11

Vehicle vs sync time (s) (sensor to google map)

10

2
Vehicle
0
Road-A
Road-B
Road-C
Sensor to google map
Road-D
0-2 6-8
2-4 8-10
4-6

Figure 8: Vehicle vs sync time(s) (sensor to Google Map).

Vehicle vs sync time(s) (sensor to signal dashboard)

10

2
Vehicle
0
Road-A
Road-B
Road-C Signal dashboard
Road-D
0-2 6-8
2-4 8-10
4-6

Figure 9: Vehicle vs. sync time(s) (sensor to signal dashboard).

real-time data, our solution can be practically implemented gle Map. This graph summarizes the proposed system is dis-
in Kingdom metropolitan cities to ensure congestion control tinct from existing traffic management systems.
and time consumption.
Table 3 represents the efficiency comparison of our pro- 6. Conclusion and Future Work
posed solution. In 2019 and 2020, researchers took a step
towards real-time traffic monitoring. It was either partial This study proposed an IoT-based architecture with agents
or ultimately achieved, but real-time traffic updates are miss- collecting and counting vehicles via IoT devices and storing
ing, a need of today’s lifestyle. As the technology grows and real-time data on clouds via message agents. The messaging
citizens’ demands are enhanced, there is a need for a Smart agent acts as an actuator in the proposed solution and col-
Traffic System that provides early alerts for the delay and laborating in real-time with the environment and cloud stor-
congestion control. Our Smart Traffic System helps the citi- age. Meanwhile, these messages are being broadcasted on the
zen with time consumption, delay control, and efficiency by dashboard and Google Map to assist Kingdom citizens in
providing traffic updates on the signal dashboard and Goo- making decisions and saving time on the roads. Wi-Fi-
12 Journal of Advanced Transportation

Table 3: Comparison of the proposed approach with existing holders' perspective,” Urban, Planning and Transport
studies. Research, vol. 6, no. 1, pp. 35–53, 2018.
[4] M. Humayun, N. Jhanjhi, B. Hamid, and G. Ahmed, “Emerg-
Real-time ing smart logistics and transportation using IoT and block-
Real-time traffic
Real-time traffic updates chain,” IEEE Internet of Things Magazine, vol. 3, no. 2,
Ref Year updates on the
monitoring on Google pp. 58–62, 2020.
signal dashboard
Map
[5] A. Khan, N. Jhanjhi, M. Humayun, and M. Ahmad, “The role
Proposed of IoT in digital governance,” in Employing Recent Technolo-
2022 ♦♦ ♦♦ ♦♦
system gies for Improved Digital Governance, vol. 1pp. 128–150, IGI
[17] 2020 ♦♦ ◊◊ ◊◊ Global, USA, 1st edition, 2020.
[18] 2019 ♦◊ ◊◊ ◊◊ [6] M. Humayun, “Industrial revolution 5.0 and the role of cutting
[19] 2020 ♦♦ ◊◊ ◊◊ edge technologies,” International Journal of Advanced Com-
puter Science and Applications (IJACSA), vol. 12, no. 12, 2021.
[20] 2020 ♦♦ ◊◊ ◊◊
[7] N. A. Khan, N. Jhanjhi, S. N. Brohi, R. S. A. Usmani, and
[21] 2019 ♦◊ ◊◊ ◊◊
A. Nayyar, “Smart traffic monitoring system using unmanned
[22] 2020 ♦♦ ◊◊ ◊◊ aerial vehicles (UAVs),” Computer Communications, vol. 157,
no. 1, pp. 434–443, 2020.
[8] M. Humayun, N. Jhanjhi, M. Z. Alamri, and A. Khan, “Smart
enabled controllers carry out this process to send a message
cities and digital governance,” in Employing Recent Technolo-
on time. The case study is carried out to validate the accu- gies for Improved Digital Governance, vol. 1pp. 87–106, IGI
racy of the proposed architecture. Global, USA, 1st edition, 2020.
In terms of future directions, the proposed system could [9] M. Shafiq, H. Ashraf, A. Ullah et al., “Robust cluster-based
be enhanced further by taking various features into the ver- routing protocol for IoT-assisted smart devices in WSN,”
sion. The first dimension requires recommending an opti- Computers, Materials & Continua, vol. 67, no. 3, pp. 3505–
mum route based on real-time data to drivers. Future 3521, 2021.
research will focus on dynamic traffic signal control func- [10] M. Humayun, “Role of emerging IoT big data and cloud com-
tionality and performance in low-light environments or dur- puting for real time application,” International Journal of
ing extreme weather. Communication between roadside Advanced Computer Science and Applications, vol. 11, no. 4,
display units and traffic lights must be recognized in this pp. 1–13, 2020.
case. Another factor to consider is the system’s real-time [11] J. H. Park, M. Salim, J. H. Jo, J. C. S. Sicato, S. Rathore, and J. H.
implementation, which includes IoT security features in Park, “CIoT-Net: a scalable cognitive IoT based smart city net-
the communication layer; the architecture must be expanded work architecture,” Human-centric Computing and Informa-
to a whole end-to-end system with central server tion Sciences, vol. 9, no. 1, pp. 1–20, 2019.
communication. [12] A. Ullah, M. Azeem, H. Ashraf, A. A. Alaboudi, M. Humayun,
and N. Z. Jhanjhi, “Secure healthcare data aggregation and
transmission in IoT—a survey,” IEEE Access, vol. 9, no. 1,
Data Availability pp. 16849–16865, 2021.
The numerical data used to support the findings of this [13] D. Mahmood, S. Latif, A. Anwar et al., “Utilization of ICT and
study are included within the article. AI techniques in harnessing residential energy consumption
for an energy-aware smart city: a review,” International Jour-
nal of Advanced and Applied Sciences, vol. 8, no. 7, pp. 50–
Conflicts of Interest 66, 2021.
[14] M. Humayun, N. Jhanjhi, and M. Alamri, “Smart secure and
The authors declare no conflict of interest. energy efficient scheme for e-health applications using IoT: a
review,” International Journal of Computer Science and Net-
Acknowledgments work Security, vol. 20, no. 1, pp. 55–74, 2020.
[15] V. Ponnusamy, A. Yichiet, N. Jhanjhi, M. Humayun, and
This work was funded by the Deanship of Scientific Research M. Almufareh, “IoT wireless intrusion detection and network
at Jouf University under grant No (DSR-2021-02-0325). traffic analysis,” Computer Systems Science & Engineering,
vol. 40, no. 3, pp. 865–879, 2022.
References [16] V. F. Arguedas, G. Pallotta, and M. Vespe, “Maritime traffic
networks: from historical positioning data to unsupervised
[1] T. Afrin and N. Yodo, “A survey of road traffic congestion maritime traffic monitoring,” IEEE Transactions on Intelli-
measures towards a sustainable and resilient transportation gent Transportation Systems, vol. 19, no. 3, pp. 722–732,
system,” Sustainability, vol. 12, no. 11, pp. 4660–4683, 2020. 2018.
[2] Z. Youssef, H. Alshuwaikhat, and I. Reza, “Modeling the [17] Z. Liu, Y. Wu, S. Cao, L. Zhu, and G. Shen, “A ramp metering
modal shift towards a more sustainable transport by stated method based on congestion status in the urban freeway,”
preference in Riyadh, Saudi Arabia,” Sustainability, vol. 13, IEEE Access, vol. 8, no. 1, pp. 76823–76831, 2020.
no. 1, pp. 337–352, 2021. [18] P. Kuppusamy, R. Kalpana, and P. V. Rao, “Optimized traffic
[3] O. Alotaibi and D. Potoglou, “Introducing public transport control and data processing using IoT,” Cluster Computing,
and relevant strategies in Riyadh city, Saudi Arabia: a stake- vol. 22, no. S1, pp. 2169–2178, 2019.
Journal of Advanced Transportation 13

[19] D. Kavitha and S. Ravikumar, “Retracted article: designing an road transportation,” Annual Reviews in Control, vol. 48,
IoT based autonomous vehicle meant for detecting speed no. 1, pp. 292–311, 2019.
bumps and lanes on roads,” Journal of Ambient Intelligence [33] C. Akasiadis, V. Pitsilis, and C. D. Spyropoulos, “A multi-
and Humanized Computing, vol. 12, no. 7, pp. 7417–7426, protocol IoT platform based on open-source frameworks,”
2021. Sensors, vol. 19, no. 19, p. 4217, 2019.
[20] W. Lee and C. Chiu, “Design and implementation of a smart [34] T. Parekh, B. V. Kumar, R. Maheswar, P. Sivakumar,
traffic signal control system for smart city applications,” Sen- B. Surendiran, and R. M. Aileni, “Intelligent transportation
sors, vol. 20, no. 2, pp. 508–520, 2020. system in smart city: a SWOT analysis,” in Challenges and
[21] D. Biswas, H. Su, C. Wang, A. Stevanovic, and W. Wang, “An Solutions for Sustainable Smart City Development, pp. 17–47,
automatic traffic density estimation using single shot detection Springer, Cham, 1st edition, 2021.
(SSD) and MobileNet-SSD,” Physics and Chemistry of the [35] S. Uzairue, J. Ighalo, V. O. Matthews, F. Nwukor, and S. I.
Earth, Parts A/B/C, vol. 110, no. 1, pp. 176–184, 2019. Popoola, “IoT-Enabled Alcohol Detection System for Road
[22] L. Mingwei and L. Lin, “Intelligent transportation system in Transportation Safety in Smart City,” in International Confer-
China: the optimal evaluation period of transportation's appli- ence on Computational Science and Its Applications, pp. 695–
cation performance,” Journal of Intelligent & Fuzzy Systems, 704, Melbourne, VIC, Australia, 2018.
vol. 38, no. 6, pp. 6979–6990, 2020.
[23] H. Hamidi and A. Kamankesh, “An approach to intelligent
traffic management system using a multi-agent system,” Inter-
national Journal of Intelligent Transportation Systems
Research, vol. 16, no. 2, pp. 112–124, 2018.
[24] B. Lv, H. Xu, J. Wu et al., “LiDAR-enhanced connected infra-
structures sensing and broadcasting high-resolution traffic
information serving smart cities,” IEEE Access, vol. 7,
pp. 79895–79907, 2019.
[25] F. Colace, M. Lombardi, F. Pascale, D. Santaniello, A. Tucker,
and P. Villani, “MuG: a multilevel graph representation for big
data interpretation,” in In 2018 IEEE 20th International Con-
ference on High Performance Computing and Communica-
tions; IEEE 16th International Conference on Smart City;
IEEE 4th International Conference on Data Science and Sys-
tems (HPCC/SmartCity/DSS), pp. 1408–1413, IEEE, Exeter,
UK, 2018.
[26] M. Aqib, R. Mehmood, A. Alzahrani, I. Katib, A. Albeshri, and
S. M. Altowaijri, “Smarter traffic prediction using big data, in-
memory computing, deep learning and GPUs,” Sensors,
vol. 19, no. 9, p. 2206, 2019.
[27] X. Cheng, C. Chen, and P. Weng, “Vehicle Detection System
with Statistical Functions Based on 3-Axis AMR Using Wire-
less Communication Technology,” in Advances in Intelligent
Automation and Soft Computing. IASC 2021, X. Li, Ed.,
vol. 80 of Lecture Notes on Data Engineering and Communi-
cations Technologies, Springer, Cham, 2022.
[28] Y. Feng, G. Mao, B. Cheng et al., “MagMonitor: vehicle speed
estimation and vehicle classification through a magnetic sen-
sor,” IEEE Transactions on Intelligent Transportation Systems,
vol. 23, no. 2, 2020.
[29] Q. Wang, J. Zheng, H. Xu, B. Xu, and R. Chen, “Roadside mag-
netic sensor system for vehicle detection in urban environ-
ments,” IEEE Transactions on Intelligent Transportation
Systems, vol. 19, no. 5, pp. 1365–1374, 2017.
[30] B. Jan, H. Farman, M. Khan, M. Talha, and I. U. Din, “Design-
ing a smart transportation system: an internet of things and big
data approach,” IEEE Wireless Communications, vol. 26, no. 4,
pp. 73–79, 2019.
[31] W. U. K. Fernando, R. M. Samarakkody, and M. N. Halga-
muge, “Smart transportation tracking systems based on the
internet of things vision,” in Connected Vehicles in the Internet
of Things, pp. 143–166, Springer, 2020.
[32] B. Othman, G. De Nunzio, D. D. Domenico, and C. Wit, “Eco-
logical traffic management: a review of the modeling and con-
trol strategies for improving environmental sustainability of