DEVELOPMENT OF AN INTELLIGENCE TRAFFIC LIGHT SYSTEM

BY

AJIMAJASAN, JAMIU OLUWAFEMI EES/19/20/0113

FOLARANMI ,AYOMIDE OPEYEMI EES/19/20/0247
ONIFADE, JOSHUA ADEBARE EES/19/20/0473
ADEWUNMI ,HASSAN OLUWATOBILOBA EES/20/21/006
ODUKOYA ,BABATUNDE FAROUK EES/17/18/0272

A PROJECT REPORT SUBMITTED TO THE DEPARTMENT OF COMPUTER

ENGINEERING

COLLEGE OF ENGINEERING AND ENIVIROMENTAL STUDIES, OLABISI

ONABANJO UNIVERSITY, IBOGUN CAMPUS, OGUN STATE

IN PARTIAL FULFILLMENTOF THE REQUIREMENT FOR THE AWARD OF

BACHELOR DEGREE (B.Engr.) IN COMPUTER ENGINEERING

SUPERVISED BY

DR. OYEDEJI
APRIL 2024
 DECLARATION
Except as stated herein, this report contains no material whichhas been accepted for the award of any other higher degree
orgraduate diploma in any tertiary institution and to the best of my knowledge and belief, this report contains no
materialpreviously published or written by another person, except when due reference is made in the text of the report.

………………………………………….
AJIMAJASAN,JAMIU OLUWAFEMI
EES/11/12/0412
Title Page i
Declaration ii
Certification iii
Dedication iv
Acknowledgement v
Abstract vi
Table of Contents vii
List of Figures viii
List of Tables

CHAPTER ONE 1
1.0 INTRODUCTION 1
1.1 Background of study
1.2 Statement of the problem
1.3 Aims and objectives
1.4 Signficance of the study
1.5 Scope of the study
1.6 Limitation of the study
CHAPTER TWO
2.0 Literature Review
2.1 information sharing among agents and management centers
2.2 Transportation Management systems (TSM) Relationship
2.3 Control Systems Options
2.4 implications of intelligent traffic light
2.5 Benefits of intelligent traffic light system in urban public transportation systems
2.6 Rules of intelligent traffic lights system
2.7 Vehicle control
2.8 Expert systems
CHAPTER 3
3.1 Methodology
3.2 Hardware components
3.2.1 An Arduino
3.2.2 ESP32CAM
3.3.2 Connecting Wires
3.4.2 LED lights
3.4 Hardware design
3.5 Software design
CHAPTER 4

CHAPTER ONE
INTRODUCTION
1.1 BACKGROUND OF STUDY
This project is about integration of intelligent traffic control system, for the
types of collisions, congestions and traffics rules. The examples and perceptive
in this project deal primarily with World computerized traffic control system
and some civilized countries. Traffic light, also known as traffic signal, stop light,
traffic lamp, stop and go light, robots or semaphore, are signalling devices
positioned at road inspections, pedestrian crossing, and other locations to
control competing flows of traffic.
The rapid development of smart cities is a major focus for scientists and
engineers due to the need to improve the safety of human lives and create
conveniences for the large rural to urban human flow. Highly concerning are
the hazards posed to on-road commuters owing to road traffic jam. This traffic
congestion generates more problems that impact negatively on humans such
as time wastage, fuel burn, exhaust fume, etc. which contributes to an
increased cost of living for inhabitants of the town (Schrank, Lomax, and Eisele,
2011). More so, human productivity is reduced because of the less mobility of
vehicle users. Based on global traffic parameters, it is evident that traffic jam
hinders vehicle users’ mobility, particularly in developing communities,
regardless of traffic lights being used to control the motion of these vehicles.
Over time, various road traffic management systems have either been
proposed or implemented especially dating back to 1868 (Day and McNeil,
1998). Ever since technologies have made improvements in finding ways of
utilizing applications that will aid road management in cities that there is no
need for road traffic wardens and officers; with numerous innovations, there
are now changes to the style of signs and indicators but the operational
principle of the road traffic control has not changed.
The traffic signals have so far not impacted positively on our Nigerian roads
because traffic jams are still obvious on our major junctions. This is specifically
due to existing fixed-time traffic signals that do not align with the ever-
changing traffic patterns.

Adaptive traffic control represents a clear edge over the conventional one and
looks to be the next promising solution to the road congestion problem (Cai et
al, 2009). Due to its importance, various researchers all over the world have
been coming up with different findings that can help improve the traffic light
control technology. Ghazal et al (2016), integrates a Bee wireless system for a
secured communication between controllers that can activate a lengthy ON
mode for the green light until all the queued vehicles have passed. The
superiority of Dynamic Phase Scheduling of a road traffic system was
considered by Zachariah et al (2017) over Static Phase Scheduling of road traffic
system as a means of assigning lengthy phase durations to traffic-congested
lanes and shorter phase durations to traffic-congested lanes in other to attain
an automatic traffic light system. By utilizing network mode learning software
Mei et al (2017) developed a program that can simulate various traffic
conditions and performs its control.
Road traffic load has key dependence on time, day, season, weather
parameters and some situations that can’t be deciphered (Kumari, 2017).
Bottlenecks and delays are very likely if the parameters are not effectively
considered. To achieve this, an intelligent road traffic control system is
developed to consistently sense and monitor the road traffic situation and
effect the controls embedded in it. This prediction ability of the smart system
will create an optimal control so that vehicle users can as well become aware of
roads with gridlocks well ahead of time and the system can be able to perform
logical calculations to allow passage of vehicles on roads with the highest
densities while stopping vehicular mobility on the roads with very fewer
densities
This work considers the application of an effective and adaptable road traffic
control system at roundabouts with dual lanes. Considering the high rate of
road accidents at crossroads, this option of road traffic control will be suitable
and more convenient. In this work, the Programmable Logic Controller (PLC)
will perform the function of secondary control and play a pivotal role in
automatically controlling the traffic light. And so, the ultrasonic infrared sensor
will send a signal to the PLC and relative to the embedded software program it
will energize the LEDs being the output devices. The main devices that will be
utilized to execute this project are Allen Bradley MicroLogix 1000 PLC as
controller, decade counter 4017 and 555 timers as timing interface and LEDs to
display the output.
The 21st century is the period of active development of technologies.
Enterprises are built in megacities, road infrastructure is improved, new
highways and road forks are created, etc. Almost every family has own vehicle
– personal car. According to data for 2019 in Nigeria, there are about 305
motor vehicles per 1000 people living in the country. This indicator is level of
motorization; it is ratio of number of personal cars to population in selected
area. Often there is problem of increased traffic congestion. When cars are
moving on roads, congestion can form, which is large accumulation of cars –
traffic jam. The reasons for this may be accidents, repairs, incorrectly
configured traffic lights, weather conditions, and other factors. Main tool for
regulating road traffic is traffic light. However, the common problem is
inadequate operation and incorrect setting of traffic lights that regulate traffic
flow. In the case of traffic light devices failure, the adjustment function is taken
over by specially trained human traffic controllers, who is subject to human
errors and cannot work for a long time by nature. In Nigeria, the common
method is to set switching of traffic lights on timer, that is, after the fixed
period. Such system is the simplest and its main disadvantage is the inability to
adapt to the current road situation, including various incidents. Despite on
enough large amount of research in the field of automation of traffic systems,
the issues of intelligent adaptive regulation using artificial neural networks are
currently insufficiently studied. Thus, further investigation of the problem of
increased traffic congestion is actual question and urgent issue, so there is
need to develop the system of automatic adaptive traffic light control, the
implementation of which will significantly improve the existing situation.
Scientific novelty of this work is that automated intelligent system has been
developed that can produce corrective effect on the group of traffic lights in
the section to regulate the traffic intensity. Method of model simulation was
used to provide configuration and debugging of neural network, which uses the
multi–layer perceptron with sigmoidal activation function. Object of research:
processes of preparation and decision– making on traffic congestion regulation
on the roads. Subject of research: traffic congestion control on the roads using
artificial neural networks
The increase in urbanization and traffic congestion create an urgent need to
operate our transportation systems with maximum efficiency. Real-time traffic
signal control is an integral part of modern Urban Traffic Control Systems aimed
at achieving optimal Utilization of the road network. Providing effective real
time traffic signal control for a large complex traffic network is an extremely
challenging distributed control problem. Signal system operation is further
complicated by the recent trend that views traffic signal system as a small
component of an integrated multimodal transportation System. Optimization
of traffic signals and other control devices for the efficient movement of traffic
on streets and highways constitutes a challenging part of the advanced traffic
management system of intelligent transportation system.
Simply defined, Intelligent Transport Systems and Services is the integration of
information and communications technology with transport infrastructure,
vehicles and users.
For a large-scale traffic management system, it may be difficult or impossible to
tell whether the traffic network is flowing smoothly and assess its current state.
Over the past few years, multi-agent systems have become a crucial technology
for effectively exploiting the increasing availability of diverse, heterogeneous
and distributed information sources. Researchers over the Years have adopted
numerous techniques and used various tools to implement multi-agent systems
for their problem domains. As researchers gain a better understanding of these
autonomous multi-agent systems, more features are incorporated into them to
enhance their performance and the enhanced systems can then be used for
more complex application domains.
Intelligent software agent is an autonomous computer program, which
interacts with and assists an end user in certain computer related tasks. In any
agent, there is always a certain level of intelligence. The level of the Intelligence
could vary from pre-determined roles and responsibilities to a learning entity.
Multi-Agent System is the aggregate of agents, whose object is to decompose
the large system to several small systems which communicate and coordinate
with each other and can be extended easily. Agent-based simulations are
models where multiple entities sense and stochastically respond to conditions
in their local environments, mimicking complex large-scale system behaviour.
The urban traffic system is a much complex system, which involved many
entities and the relationship among them are Complicated.
Therefore, the most important issues for a learner agent is the assessment of
the behaviour and the intelligence level of the other agents. By sharing vital
information, Intelligent Traffic System allows people to get more from transport
networks, with greater safety and with less impact on the environment.
Intelligent Traffic System helps the whole transport system to work most
effectively and efficiently. Intelligent Traffic System integrates users, transport
systems, and vehicles through state-of-the-art information and
communications technologies. Intelligent Traffic System can dramatically
improve travellers’ safety, efficiency and comfort. Intelligent Traffic System
helps shippers and carriers move freight to its destination reliably and
efficiently. Intelligent Traffic System helps the people who run transport
systems provide better service to their customers. Intelligent Traffic System
helps get the best value from the road and rail systems we already have.
Intelligent Traffic System helps traffic flow more smoothly, reducing delays, fuel
consumption, and air and noise pollution. Intelligent Traffic System helps make
public transport more convenient and affordable.
Intelligent Traffic System often works behind the scenes. When emergency
vehicles get to a crash site more rapidly than before, Intelligent Traffic System is
detecting the crash, notifying emergency services, and getting the nearest
response unit rapidly to the site. Technology in a vehicle prevents skidding and
helps the vehicle to stop safely; the driver may not even realize that assistance
was provided, but Intelligent Traffic System is at work.
1.2 STATEMENT OF THE PROBLEM
Traffic congestion is an increasing problem in cities and sub urban spend more
of their time commuting to work, school, shopping, and social event as well as
dealing with traffic light jambs and accidents. Traffic became heavy in all
directions, more to and from cities as well as between sub urban locations. Sub
urban business locations required huge parking lots because employees have
to drive; there were few buses trains, or trolleys to carry scatter workers to
their work place. The hope of reduced congestion in the sub urban had not
been realized; long commutes and traffic jams could be found everywhere.
1.3 AIMS AND OBJECTIVES
Intelligent Traffic System provides travel opportunities and additional travel
choices for more people in more ways, wherever they live, work and play,
regardless of age or disability.
The aims of this research work are:
- To design and implement an intelligent traffic control system.
- To develop a suitable algorithm to implement the design.
- To simulate the intelligent traffic control using Visual Basic programming.
The first objective is to make each of the traffic lights or semaphores smart.
That is, aware of the time of day, basic turn red, green or yellow rules, and
perhaps what traffic looks like in all directions based upon locally mounted
signals. In achieving these aims, the following objectives will also be followed:
- To design a simple system that is easily adaptable to the existing traffic
conditions at the junction, involving a minimum of physical changes in the
intersection.
- To provide the quickest possible clearance to vehicular and pedestrian
traffic in all directions at a junction.
- To a design flexible artificial intelligence traffic light system that will take
care of changes in the traffic density and character.
- To reduce the stress of the traffic warder.
- To reduce the occurrence of possible accident.
- To verify the efficacy of the program.
1.4 SIGNIFICANCE OF THE STUDY
The important of this research work are:
- It will help in reducing the occurrence of possible collision or accident
and thereby improve the confidence of the driver and the pedestrian plighting
through the highways.
- The project to allay the fear of time wastage at the junctions because of
unevenly directions of traffic system.
- Since the system is capable of working for 24hours uninterrupted
thereby assured constant availability of traffic control service hence reduce
human effort and energy.
1.5 SCOPE OF THE STUDY
The scope is the design of an intelligent traffic control system. The modern
method of traffic control system is indicating each light at a particular time
interval to pass a vehicle at one lane and stop vehicle on the other lane. The
light is broken into three (3) categories (Red, Yellow, and Green) to signal to
lane on what to do at a particular time where the red signify STOP, yellow
signify READY, and green signify MOVE.
Each light is designed to turn itself on whenever it is necessary and turn off the
time elapse.
1.6 LIMITATION OF THE STUDY
Traffic congestion is a serious problem despite costly effort to create an
integrated method of traffic control system. The number of private
automobiles used mainly by people with middle and income, has increased
faster than any form of transportation in Lagos (Nigeria) and this has increased
a demand of expansion of roads, parking space and improved computerized
traffic control system.
1.7 METHODOLOGY
The use of the Millis @ function enables the inclusion of delays in Arduino
programs without inhibiting other program functions from running. That is,
instead of using the traditional delay O routine which wastes processing power
and locks the entire processor in a spot for the entire delay period, the use of
the Millis ( function can add delays in Arduino programs while at the same time
allowing the processing of other functions. This is so important as room is left
for future improvement of the design for instance by the inclusion of sensors

CHAPTER TWO
2.0 LITERATURE REVIEW
Transportation research has the goal to optimize transportation flow of people
and Goods. As the number of road users constantly increases, and resources
provided by current infrastructures are limited, intelligent control of traffic will
become a very important issue in the future. However, some limitations to the
usage of intelligent traffic control exist. Avoiding traffic jams for example is
thought to be beneficial to both environment and economy, but improved
traffic-flow may also lead to an increase in demand [Levinson, 2003].
There are several models for traffic simulation. In our research we focus on
microscopic models that model the behaviour of individual vehicles, and
thereby can simulate dynamics of groups of vehicles. Research has shown that
such models yield realistic behaviour [Nagel and Schreckenberg, 1992, Wahle
and Schreckenberg, 2001].
Cars in urban traffic can experience long travel times due to inefficient traffic
light control. Optimal control of traffic lights using sophisticated sensors and
intelligent optimization algorithms might therefore be very beneficial.
Optimization of traffic light switching increases road capacity and traffic flow,
and can prevent traffic congestions. Traffic light control is a complex
optimization problem and several intelligent algorithms, such as fuzzy logic,
evolutionary algorithms, and reinforcement learning (RL) have already been
used in attempts to solve it. In this paper we describe a model-based, multi-
agent reinforcement learning algorithm for controlling traffic lights.
2.1 INFORMATION SHARING AMONG AGENCIES AND MANAGEMENT
CENTERS
Information is commonly shared among agencies by means of voice
communications and data communications. The Regional Intelligent Traffic
System Architecture establishes the general data flow requirements between
agencies and from each agency’s management centre to the field equipment or
other equipment that it communicates with or controls. To perform data
communication between management centres, a common language and frame
of reference is required. Protocols for the sharing of transportation related
information are being established at the time of this writing by the National
Transportation Communications for Intelligent Traffic System Protocol (NTCIP)
and are available on its website (http://www.ntcip.org).
In essence, the information may be put into the proper high-level language by
the use of the Traffic Management Data Dictionary (TMDD). The TMDD
provides the definition and format for the data and the Message Sets for
External Traffic Management Communications (MS / ETMCC) which organizes
the TMDD elements into relevant messages. Different protocols are included in
the NTCIP standards for transmitting these messages between management
centres.

2.2 TRANSPORTATION SYSTEMS MANAGEMENT (TSM) RELATIONSHIP

Since first introduced in the mid-1970s, transportation systems management
(TSM) has evolved from a list of about 150 low-cost actions to the productive
use of existing transportation resources through their coordinated operations
and improved management. TSM implies "a philosophy about planning,
programming, implementation, and operations that calls for improving the
efficiency and effectiveness of the transportation system by improving the
operations and / or services provided". TSM, then, provides an umbrella
philosophy that aims to:
 Analyse the total system, and
  Improve operation and safety before capital-intensive projects add
significant capacity. Roark classifies TSM actions within 9 different
urban operating environments, including:
 Freeway corridor,
 Arterial corridor,
 Central business district (CBD),
 Regional operating environment,
 Neighbourhood,
 Major employment site (non-CBD),
 Outlying commercial center,
 Major activity center, and
 Modal transfer point.
In contrast, Wagner uses two primary strategies - supply and demand (6).
Supply strategies focus on changing the quality of vehicular flow, whereas
demand-oriented strategies target decreasing the quantity of vehicular travel.
Supply actions include:
 Arterial signal coordination,
 Signal removal or flashing operation,
 Freeway monitoring and control,
 Incident management,
 Parking prohibition,
 Turn controls, and
 Bottleneck-removal programs.

Demand actions include:

 Carpools,
 Vanpools,
 High occupancy vehicle (HOV) priority treatments, and
 Variable work hours.
In both classification schemes, traffic control systems and their effective
operation predominantly affect TSM and prove vital to the full realization of
several other TSM actions. For example, it does little good to entice drivers
to ride the bus or join a vanpool if inefficiently operating traffic signals stop
or delay all vehicles (including buses and vans).
 Figure 1: General traffic management and control structure.
2.3 CONTROL SYSTEM OPTIONS
Operational objectives of traffic control systems include making the best use of
existing roadway and freeway network capacity and reducing trip times,
without creating adverse environmental impacts.
Controlling the movement of vehicles through signalized intersections provides
the major effect on traffic flow in urban areas. The control strategies shown in
Table 2-2 can achieve signalized intersection control. Table 2-2 provides a
summary of the features of different categories of traffic control systems.

2.4 IMPLICATIONS OF INTELLIGENT TRAFFIC SYSTEM

 Intelligent Traffic System for safety More than 40,000 people die
on Europe’s roads each year. Road accidents cost the European
economy around €200 billion each year. While in-car safety
systems have greatly improved the chances of surviving an
accident, more attention now needs to be given to systems that
can actually prevent accidents from happening. Intelligent Traffic
System can help reduce injuries and save lives, time and money by
making transport safer:
 Intelligent Traffic System will help the drivers of cars, trucks and
buses avoid getting into crashes and help keep them from running
 off the road. Intelligent Traffic System will help maintain safe
distances between vehicles and safe speeds approaching danger
spots. Intelligent Traffic System will help improve visibility for
drivers, especially at night and in bad weather.
 Intelligent Traffic System will provide information about work
zones, traffic congestion, road conditions, pedestrian crossings
and other potential hazards.
 Intelligent Traffic System will help detect the crashes that do occur,
determine the severity of the crash and likely injuries, and help
emergency management services provide assistance. Intelligent
Traffic System will help select the closest and most appropriate
rescue unit to respond. Intelligent Traffic System will adjust traffic
signals to clear the way for emergency vehicles.
 Intelligent Traffic System will connect responding units to medical
care facilities to help provide initial care for the injured and help
medical care facilities prepare to deliver more complete treatment
when injured people arrive.
 Intelligent Traffic System for efficiency and economy Congestion
costs the EU 1% of its GDP – around €100 billion – each year3.
There are around 300 million drivers in the EU today, while in the
past 30 years the distance travelled by road has tripled4 and is set
to increase further. With funding and space for large-scale road
building becoming increasingly scarce, governments,
infrastructure operators and pubic authorities are turning to
Intelligent Traffic System solutions to ease congestion. Ramp
metering, traffic and incident detection and variable message sign
systems are already being used across Europe. Intelligent Traffic
System can save time and money for travellers and the freight
industry:
 Intelligent Traffic System will deliver fast, accurate and complete
travel information to help travellers decide whether to make a
trip, when to start, and what travel modes to use. Intelligent
Traffic System will provide his information both prior to a trip and
as the trip proceeds.
 Intelligent Traffic System will help drivers select and follow safe,
efficient routes to their destination. Intelligent Traffic System will
let drivers pay tolls without having to stop.
  Intelligent Traffic System will help freight move swiftly and reliably
using the right combination of ship, truck, train and plane.
 Intelligent Traffic System will help track freight, enabling its owners
to know where it is at all times and when it is due to arrive at its
destination, and allowing for better planning and scheduling of
critical processes.
 Intelligent Traffic System will enable more reliable and timely
commercial vehicle management. Intelligent Traffic System will
automatically keep track of safety-related information about the
vehicle, its driver and its cargo. Intelligent Traffic System will help
communicate this information to the authorities so that, as
appropriate, vehicles can be cleared through checkpoints without
stopping.
 Intelligent Traffic System will help the people who build, manage
and maintain the transport system. Intelligent Traffic System will
help the transport system carry more traffic safely and efficiently
by keeping traffic flowing, clearing incidents quickly, and managing
construction and maintenance to minimize disruptions. Intelligent
Traffic System will help schedule road management vehicles and
help them work more precisely and efficiently.
The next generation of Intelligent Traffic System solutions will:
 Give public transport users real-time service information, as well as
smart and seamless ticketing solutions.
 Enable freight operators and customs authorities to share information
about consignments and keep track of their position and status, as well
as provide information on the most efficient, economical and secure
routes for freight.
 Allow vehicles to communicate directly with the infrastructure around
them and with one another – enabling drivers to make better decisions
about their route and respond to warnings of congestion and accidents.
 Intelligent Traffic System for environment Despite increasing air travel,
the vast majority of this energy is still consumed by road transport. Since
Intelligent Traffic System systems can improve the efficiency of passenger
and goods transport and reduce the time caught in traffic congestion,
they will obviously have secondary benefits for the environment and in
terms of use of space:
 Intelligent Traffic System will keep traffic flowing on urban freeways, on
 toll roads, at commercial vehicle checkpoints and elsewhere. Reducing
delays due to congestion and incidents means that energy waste, wear–
and–tear, and the pollution caused by stop–and–go driving are also
reduced.
 Intelligent Traffic System will help vehicles operate more efficiently.
Intelligent Traffic System will provide location–specific information about
weather and road conditions.
 Intelligent Traffic System will help to plan efficient routes and guide
drivers along these routes.
 Intelligent Traffic System will help make public transport more reliable,
effective and attractive, thereby accelerating its use. Intelligent Traffic
System will provide better information on schedules and connections.
Intelligent Traffic System will help public transport users stay in touch
with their employers and their families while in transit.
 Intelligent Traffic System for security Recent events have shown that the
transport system is under threat from terrorism, whether as a target in
itself or a means of attacking other targets. The need to protect
travellers, transport facilities and transport workers against security risks
has never been greater. However, this must be balanced with the need to
make sure transport continues to operate effectively and efficiently.
Intelligent Traffic System systems are key to striking this balance. In fact,
Intelligent Traffic System will help prepare for, prevent and respond to
disaster situations, whether from natural causes, human error, or
attacks:
 Intelligent Traffic System will help keep watch over transport facilities.
 Intelligent Traffic System will help provide personal security for people
using the public transport system.
 Intelligent Traffic System will monitor freight, especially hazardous
materials, through the entire supply chain.
 Intelligent Traffic System will help transport and safety/security agencies
coordinate their activities and their information so they can respond
more effectively to incidents of all kinds.
 Intelligent Traffic System will help identify the best routes for evacuating
people at risk and for directing emergency services to incidents and
disaster sites.
 Intelligent Traffic System will help the transport system, and all the other
parts of the economy that depend on transport, to return to normal as
 rapidly as possible following a crisis, through better management of the
transport system, more efficient interagency communications, and better
and more timely information to the public.
 Intelligent Vision Systems can automatically spot suspicious behavior at
transport hubs, while automatic tracking and alarm systems can speed
the response to threats.
 Intelligent Traffic System in urban public transport system
Intelligent transport systems in urban public transport might be described as a
combination of information and communication technologies integrated into
urban public transport system. These technologies might be integrated into the
infrastructure of transportation system and/or in urban public transport
vehicles themselves.
At present, public sector infrastructure, including electronic toll collection and
road use charging, still represents the largest Intelligent Traffic System market
segment.
In the future, private sector purchases of Intelligent Traffic System products and
services (either from commercial and consumers) are expected rapidly to
overtake the public sector market, with emphasis on communications- enabled
in-vehicle products and services, reflecting rapid growth in the wireless
internet. Japan is furthest advanced in this market, followed by Europe, and
then North America, but this effect is accelerating in all world regions.

2.5 BENEFITS OF INTELLIGENT TRAFFIC SYSTEM IN URBAN PUBLIC

TRANSPORT SYSTEMS
Application of Intelligent Traffic System in urban transport can lead to an
improvement of urban transport performance through:
 Reductions in transport time, cost, and congestion
 Reductions in pollution
 More effective monitoring and management of traffic flows
 Greater safety and security in stations, streets, roads and vehicles
 Facilitation of multimodal journey planning
 Provision of real time traffic information, alternate routes, etc.
 Creation of appropriate travel conditions for disabled people.
2.6 RULES OF INTELLIGENT TRAFFIC CONTROL
Here are a few samples of the types of rules that might be employed at a
couple levels of an intelligent system.
Individual traffic light:
1. If the time of day is between A and B then red on time is X, yellow on
time is Y and green on time is Z.
2. If direction A is green and direction A number of cars visible is very low
and direction B is red and direction B number of cars visible is very high then
trigger direction A to red and trigger direction B to green.
3. If direction A weighted average wait time is greater than direction B
weighted average wait time then incrementally increase within limits the
direction A green on time and decrease, within limits, direction B green on
time.

2.7 VEHICLE CONTROL

It is a well-known fact that traffic flow would increase drastically if all drivers
would drive at the same (maximum) speed. Another fact is that this will never
happen if you let drivers decide. In this section we first show how vehicles
could learn to cooperate. We then describe an ambitious research program
that aims to control all vehicles by on-board computers.
Moriarty and Langley (1998) have used reinforcement learning for distributed
traffic control.
Their approach enabled cars to learn lane selection strategies from experience
with a traffic simulator. Experimental studies showed that learned strategies let
drivers more closely match their desired speeds than hand-crafted controllers
and reduce the number of lane changes. Their approach, like ours, focuses on
distributed car-based controllers, which makes it easy to take specific
desires/goals of drivers into account such as desired speed or destination.
In the California Partners for Advanced Transit and Highways (PATH) program,
the Automated Highway System (PATH-AHS) project aims to completely
automate traffic [Horowitz and Varaiya, 2000]. Cars on special roads would
travel in so-called platoons. A platoon is a number of cars that travel at high
speed, with little distance in between. Each car controls its own speed and
lateral movement, and makes sure it follows the leader. The leader navigates
the platoon, and makes sure that there is enough space between platoons. In
order to optimize flow, a platoon leader receives information about the optimal
speed from a roadside coordinating system. Because of this, and the fact that
there is little distance in between cars in a platoon, an AHS is said to be able to
increase road capacity by a factor of about four.
Another aspect of traffic control is controlling traffic lights in a way that
minimizes the time drivers have to wait. We will describe previous research in
this area and our car-based, multi-agent reinforcement learning algorithm in
section 4. First, we will discuss reinforcement learning.

Fig 2.7 Traffic control light

2.8 EXPERT SYSTEMS

An expert system uses a set of given rules to decide upon the next action. In
traffic light control, such an action can change some of the control parameters.
Findler and Stapp (1992) describe a network of roads connected by traffic light-
based expert systems. The expert systems can communicate to allow for
synchronization. Performance on the network depends on the rules that are
used. For each traffic light controller, the set of rules can be optimized by
analysing how often each rule fires, and the success it has. The system could
even learn new rules. Findler and Stapp showed that their system could
improve performance, but they had to make some simplifying assumptions to
avoid too much computation.

2.9 PREDICTION-BASED OPTIMIZATION.

Tavladakis and Voulgaris (1999) describe a traffic light controller using a simple
predictor.
Measurements taken during the current cycle are used to test several possible
settings for the next cycle, and the setting resulting in the least amount of
queued vehicles is executed. The system seems highly adaptive, and maybe
even too much so. Since it only uses data of one cycle, it could not handle
strong fluctuations in traffic flow well. In this case, the system would adapt too
quickly, resulting in poor performance.
Liu et al. (2002) introduce a way to overcome problems with fluctuations.
Traffic detectors at both sides of a junction and vehicle identification are used
to measure delay of vehicles at a junction. This is projected to an estimated
average delay time using a filter function to smooth out random fluctuations.
The control system tries to minimize not only the total delay, but the summed
deviations from the average delay as well. Since it is no longer beneficial to let
a vehicle wait for a long time, even if letting it pass would increase the total
waiting time, this introduces a kind of fairness. Data of about 15 minutes is
used to determine the optimal settings for the next cycle, and even using a
simple optimization algorithm, the system performs well compared to preset
and actuated controllers.

CHAPTER THREE
3.1 Methodology
Design and Implementation of the Proposed Algorithm
In this section, focus is on the steps taken to produce the result expected. This
includes the algorithm design, Hardware and Software design, then simulation
with results generated and recorded. The implementation was carried out with
the Arduino Uno prototyping platform.
Arduino is an open-source electronics platform based on easy-to-use hardware
and software. Open Source, meaning the user has the right to modify the
software as he/she pleases. The Arduino is actually a microcontroller based
prototyping platform and is able to:
a, read inputs, such as reading a sensor, a key press on a keypad,
b, turn on an output such as activating a motor, or turning on an LED as in this
case.
The Arduino comes in many variant flavors categorized in either 8bit or 32bit
processing power.
It is a very popular platform with a very active support community, a large
Library repository, and lots of easy add-ons called shields to provide extra
capabilities. Microcontroller based designs are easily implemented on the
Arduino platform as the programs are written in C and a host of very good
library functions are available reducing project development time.The design of
the traffic light sequence implemented in this solution is time-based and was
simulated in software using the Proteus VSM environment and in Hardware
using LEDs. A special function of the Arduino programming language was used
in the development of the time-based sequence of the traffic light design. This
function is called Millis 0.
The use of the Millis @ function enables the inclusion of delays in Arduino
programs without inhibiting other program functions from running. That is,
instead of using the traditional delay O routine which wastes processing power
and locks the entire processor in a spot for the entire delay period, the use of
the Millis ( function can add delays in Arduino programs while at the same time
allowing the processing of other functions. This is so important as room is left
for future improvement of the design for instance by the inclusion of sensors
etc.
3.2 Hardware components
The hardware components used in this project include the ESP32CAM
module, an Arduino Nano, voltage regulator, Strawboard, Play 3d filament,
Model cars, dignity case, model trees, cardboard, flexible iron, connecting
wires, LED lights and a power source.
3.2.1 An Arduino is an open-source electronics platform designed for creating
interactive projects and prototypes. It consists of both hardware and software
components that make it easy to develop and program a wide range of
electronic devices and systems. Here’s a detailed breakdown of what an
Arduino is:

1. Hardware: Arduino boards are physical computing platforms based on

microcontrollers from various manufacturers, such as Atmel (now
Microchip) AVR, ARM-based processors, and others. These boards
typically include:
 Microcontroller: The central processing unit that runs the Arduino
program (sketch).
 Input/output Pins (GPIO): Digital and analog pins that can be used
to interface with sensors, actuators, and other electronic
components.
 Power Supply: USB ports for power and programming, as well as
external power options.
 Communication Interfaces: UART, SPI, I2C, and other
communication protocols for connecting with peripherals and
other devices.

2. Software: The Arduino platform includes the Arduino IDE (Integrated

Development Environment), a software application used to write,
compile, and upload code (referred to as sketches) to Arduino boards.
The Arduino IDE simplifies programming by providing a straightforward
development environment based on the C and C++ programming
languages.

3. Programming: Users write sketches in the Arduino IDE, which are

programs that define the behavior of the Arduino board. These sketches
control how the Arduino interacts with sensors, controls actuators,
processes data, and communicates with other devices or systems.
 4. Applications: Arduino boards are used in a wide range of applications,
including:
 Electronics Prototyping: Rapid prototyping of electronic circuits
and projects.
 Automation and Control: Building systems for home automation,
robotics, and industrial control.
 Education: Teaching electronics, programming, and physical
computing concepts in classrooms and workshops.
 IoT (Internet of Things): Creating IoT devices for monitoring, data
collection, and remote control

FIG 3.1.1 ARDUINO

3.2.2 ESP32CAM
The ESP32-CAM development board has a variety of potential applications,
including security systems, remote monitoring, and video streaming. For
instance, it can be utilized to establish a home security system that transmits
images or video to a cloud-based storage service or to a mobile device via Wi-Fi
or Bluetooth. It can also be employed in robotics projects, such as a remotely
controlled robot that sends a live video feed to a user's smartphone or
computer.
In addition to its camera and wireless capabilities, the ESP32-CAM can be
programmed to perform various tasks using its input/output pins. These tasks
include controlling motors, sensors, and other components, as well as
interfacing with other systems via I2C, SPI, and UART communication protocols.
Programming the ESP32-CAM is relatively simple, owing to its compatibility
with the Arduino IDE. The IDE allows developers and hobbyists to write code in
C++ and upload it to the board via a USB cable. The IDE also provides numerous
libraries and examples, simplifying the process of getting started with the
board.
The ESP32-CAM is a compact, well-designed development board with a range
of features and capabilities. It measures just 40 x 27 mm and comes with a
power supply, reset button, and boot button. It also includes a micro-USB port
for power and data transfer, as well as a JST connector for connecting an
external battery.
Here are the specifications of the ESP32-CAM development board:
Microcontroller: ESP32-WROOM-32 module with dual-core Tensilica LX6
processor clocked at up to 240MHz and 520KB SRAM
Wireless connectivity: Wi-Fi 802.11 b/g/n, Bluetooth v4.2 BR/EDR & BLE
Camera: OV2640 2 megapixel sensor with up to 1600x1200 resolution and
support for JPEG and BMP images
Video recording: Up to 60 frames per second at resolutions up to 640x480
Storage: MicroSD card slot supporting up to 4GB of storage
Input voltage: 5V DC via micro-USB port or external battery connector
Output voltage: 3.3V DC regulated
Operating temperature: -40°C to +85°C
Dimensions: 40 x 27 mm
Input/output pins: 9 GPIOs, 1 I2C, 1 SPI, 1 UART, 1 ADC
Programming: Compatible with the Arduino IDE and Micro Python, with
support for OTA updates.
 FIG 3.1.2 ESP32CAM
3.2.3 Connecting Wires
Connecting wires refers to the process of joining electrical conductors to
establish electrical connections between components, devices, or circuits. Use
wires made of appropriate materials for the intended application, such as
copper or aluminium conductors with insulation suitable for the environment
(e.g., PVC, silicone, or heat-resistant materials for high-temperature
applications).

FIG 3.1.3 Connecting wires

3.2.4 LED LIGHTs
LED lights, or Light Emitting Diode lights, are a type of lighting technology that
has become increasingly popular due to its energy efficiency, longevity, and
versatility. LEDs are semiconductor devices that emit light when an electric
current passes through them. Unlike traditional incandescent bulbs, which use
a filament, LEDs produce light through the movement of electrons in a
semiconductor material.

FIG 3.1.4 LED LIGHTs

3.4Hardware Design
Hardware prototyping of the Traffic lights switching sequence was carried out
with the Arduino Uno platform. Other components employed are:
• LEDs (red, yellow, green - 4pcs each)
• 1k resistors
• Jumper wires
The LEDs were grouped in three's as Red, Yellow, and Green with each group
representing the traffic light at the installation points.
For the Advertising Screen implementation, LED full color displays were
considered. An LED display is made of up three basic components:
• the LED matrix
• the controller computer system and lighting circuitry
• high current DC power supply
TABLE 1.Traffic light Switching and timing Pattern Algorithm
 .
3.5 Software design
The software algorithm is based on the truth table as described in section 4.1.
The LEDs representing the traffic lights are switched on and off based on the
truth table. Also, a delay is inserted in between each lighting sequence as
described in the truth table. These delays provide the timing required between
each light sequence. Delays used in software are achieved using the hunting of
the ordin rites ming language. The wis provides selay functions
facilitate field adjustments during actual implementation. The C programming
language was employed for the coding of the Arduino program.

CHAPTER 4
4.0 RESULT
This research needs to be considered is how to design a highway traffic
regulator, using a microcontroller from Arduino, but in designing, we must use
the help of Arduino , which functions to process the input data entered. If you
do not use the help of , Arduino cannot process data, Arduino only functions as
a microcontroller. Input data will be entered in the worksheet that has been
created as in Figure . below:
4.1 Design Lay Out and Data Input

Based on picture 1 there is a picture of a four-way intersection consisting of

road 1, road 2, road 3 and road 4, each space has different vehicle volumes, so
in reality on the field when the green light is on each section different. In
general, the way to determine how long it lasts for each lamp is determined by
the stakeholders. But there is also in a study all the lights that will light must be
determined or counted. On this occasion specifically for red lights except for
All-Red not specified just waiting for all of the lights will light including All-Red
then each red light will light based on the total number of lights that have been
lit including All-Red. As in the text formula (Red). Thus the way the values in
the input in table 1 green as an assumption are entered 30 seconds, yellow 4.5
seconds and All- Red 0.89 seconds. For line 2 the green assumption is entered
40 seconds, yellow 4.5 seconds and All-Red 0.89 seconds, line 3 green as the
assumption is entered 35 seconds, yellow 4.5 seconds and All-Red 0.89 seconds
and line 4 green as the assumption is entered 35 seconds, yellow 4.5 seconds
and All-Red 0.89 seconds. For red lights will be determined by the formula text
(Red).
4.2 TRAFFIC LIGHT PROGRAM AJD DIAGRAM BLOCK ANALYSIS DESIGN
Based on Table 1, the writing delay will automatically adjust itself because
Microsoft Excel uses the string function to overcome it. In the table above
phase 1 group 1 there is a text formula written ="delay("&J67*1000&")" and in
the table written 30000 ms, this means to delay or time for 30000 milliseconds
and thus this command applies to sketches above it, in real terms the lights are
red, red, red and yellow. In phase 1 group 2 in the table written 4500 ms, this
means the delay or time for 4500 milliseconds and thus this command applies
to the sketches above, in real terms the lights are green, red, red and red. In
phase 1 group 3 in the table written 890 ms, this means the delay or time for
890 milliseconds and thus this command applies to the sketcher above, in real
terms the lights are red, red, red and red (All-Red 1)
In phase 2 group 1 there is a text formula written = "delay("& J68*1000&")"
and in the table it says 40000 ms, this means to delay or time for 40000
milliseconds and thus this command applies to the sketcher above, in real
terms the lights are red, red, red and yellow. In phase 2 group 2 in the table
written 4500 ms, this means delay or time for 4500 milliseconds and thus this
command applies to the sketcher above, in real terms the lights are green, red,
red and red. In phase 2 group 3 in the table written 890 ms, this means the
delay or time for 890 milliseconds and thus this command applies to the
sketcher above, in real terms the lights are red, red, red and red (All-Red 2).In
phase 3 group 1 there is a text formula written = "delay("&J69*1000&")" and in
the table it says 35000 ms, this means to delay or time for 35000 milliseconds
and thus this command applies to the sketcher above, in real terms the lights
are red, red, red and yellow. In phase 3 group 2 in the table written 4500 ms,
this means delay or time for 4500 milliseconds and thus this command applies
to the sketcher above, in real terms the lights are green, red, red and red. In
phase 3 group 3 in the table written 890 ms, this means the delay or time for
890 milliseconds and thus this command applies to the sketcher above, in real
terms the lights are red, red, red and red (All-Red 3).
In phase 4 group 1 there is a text formula written = "delay("&J50*1000&")" and
in the table it says 25000 ms, this means to delay or time for 25000
milliseconds and thus this command applies to the sketcher above, in real
terms the lights are red, red, red and yellow. In phase 4 group 2 in the table
written 4500 ms, this means delay or time for 4500 milliseconds and thus this
command applies to the sketcher above, in real terms the lights are green, red,
red and red. In phase 4 group 3 in the table written 890 ms, this means the
delay or time for 890 milliseconds and thus this command applies to the
sketcher above, in real terms the lights are red, red, red and red (l.Red 4).

Based on Figure 9 it is very clearly printed on the bar, that in phase 1 the green
light is lit based on a data input of 30000 ms, the yellow light is on with data
input of 4500 ms, the All-Red light is on with the data input of 890 ms and the
red light is not on using data input. In phase 2 the red light turns on based on
not based on input, the green light turns on based on data input of 40000 ms,
the yellow light is on with data input of 4500 ms, the All-Red light is on with
data input of 890 ms and the red light is on does not use input data. In phase 3
the red light turns on based on not based on input, the green light turns on
based on data input of 35000 ms, the yellow light lights up with data input of
4500 ms, the All-Red light turns on with data input of 890 ms and the red light
turns on using no input data. In phase 4 the red light turns on based on not
based on input, the green light turns on based on data input of 35000 ms, the
yellow light turns on with data input of 4500 ms,the All-Red light turns on with
data input of 890 ms and the red light turns on using no input data.Thus that
the red light will turn on does not require data input commands and will turn
on due to the accumulation of hilau, yellow and All-Red lights.Based on the
description above about the length of the light is based on each position, then
the question arises? Why at each phase of the hilarious lamp lights up with
different durations. The answer is that the length of the red light in each phase
is due to the different queues of vehicles on each road, that is the
answer.However, on this occasion I introduce a method, to help overcome the
above problem, it needs to be applied to be combined using the Full-start-
speed method with the description as shown in figure
4.3Full-start-speed (FSS) Chart

Based on Figure 10, it can be seen that in normal conditions the vehicle's speed is according
to survey data, the vehicle runs when the green light is on at normal speed, with an average
speed value of 13.25 km/h with a long performance of approximately 132.50 meters in 36
seconds. This speed must be increased by the drivers to be faster, but the reality on the
ground there is still a slower speed than the usual speed with an average value of 11.55 km/h
with a long performance of about 115.55 meters with a time of 36 seconds, and worse again
there are still drivers driving their vehicles at very slower speeds with an average value of
7.65 km/h with long achievements of about 76.50 meters in 36 seconds. On this occasion to
help overcome the queue at the highway crossing traffic. It is expected that the driver can
improve more skillfully and increase speed at the initial start at the time of the green light at
the crossroads. It is expected that the minimum speed improvement can reach the faster
category with an average fast speed value of 15.25 km/h with a long performance of
approximately 152.50 meters with a time of 36 seconds, and a faster speed category of an
average of 16.60 km/h with a length of approximately 160 meters with a time of 36 seconds.
And even more extreme with the category is very faster speed with an average speed of 18
km/h with a long performance of about 180 meters with 36 seconds.This method is very
suitable to be combined with the previous method, only it must require socialization and
regulation by related parties, and make the main conditions in thet driver side
4.4 Traffic light simulation wiring diagram circuit

FIGURE
 Figure

Based on Figure , is a circuit diagram of a simple simulator project with a simple traffic light
using an Arduino microcontroller, each LED is given an R or resistor with a value of 330
ohms, can be mounted on the ground or on the positive part. For deadlines that enter the VCC
using a 9 volt DC deadline, you can use a battery or power supply.
Based on Figure , a traffic light simulation project that is tried by using PCB Breadboard is
more easy and versatile. This simulator is very useful to test the software that we made on
Arduino can work properly, without a simulator, we don't know what happened to the
software.Based on the method used to determine the duration of the green light, it is
determined by the number of vehicle queues at each of the four intersections. So in this study,
the method must be combined with a new method, namely the full-speed method at the
beginning of the start Full-start-speed (FSS). This method is to change the driver's behavior
from slow motion to fast motion, with this method will produce a very long distance using a
relatively short duration. Of course, you have to go through preparation, practice, and testing,
so that the driver will be reliable and professional and not become a driver who is just
learning to drive a vehicle all his life.

CHAPTER 5
5.0 CONCLUSION
Although several studies have covered the areas of traffic controllers and road congestion.
This study has uniquely tried to highlight the need for duplicity of purpose for the traffic light
system. An enhanced and engaging traffic light solution has been developed for the case
study junction. The basic cross-road traffic light algorithm was employed for the traffic
lighting sequence.This solution not only provide traffic control but also provides an avenue
for revenue generation to quickly replenish the money used for the traffic light installation,
cater for future maintenance costs and also revenue generation for other use.
5.2 REFERENCES
1. [ Alam, J. dan Pandey (2016) "Design and Analysis of a Two Stage Traffic Light System Using
Fuzzy Logic," Information Technology & Software Engineering, (November 2015). doi:

2. 10.4172/2165-7866.1000162.

3. Yusupbekov, N. R. et al. (2016) "Application of soft-computing technologies to the traffic control

system design problems," Procedia - Procedia Computer Science. Elsevier Masson SAS,
102(August), hal. 540-546. doi:

4. 10.1016/j.procs.2016.09.440.

5. Winardi, S. et al. (2019) "Determination Of Traffic Lights Duration By Identification Of Vehicle

Numbers Using loT," International Journal of Computer, Network Security and

6. Information System (ICONSIST), (September), hal. 6-12.

7. Otasowie, O. dan Sunday, O. O. (2018) "Simulation Of An Intelligent Traffic Light System

Embedded Technique," Anale. Seria Informatica., XVI.

8. Faruk, E. et al. (2019) "Density Based Traffic Control,"International Journal of Advanced

Engineering, Management and Science (IAEMS), (August 2016). Tersedia pada:www.ijaems.com.

9. Yeasmin, N., Zaman, R. dan Mouri, I. J. (2016) "Traffic Control Management And Road Safety
Using Vehicle To Vehicle Data Transmission Based On Li-Fi Technology," International Journal of
Computer Science, Engineering and Information Technology (ICSEIT), 6(3), hal. 1-7. Tersedia
pada: www.ijaems.com.

10. Marzukia, M. Z. A. et al. (2015) "Fault Monitoring System forTraffic Light," Jurnal Teknologi
(Sciences & Engineering, (April). doi: 10.11113/jt.v73.4407.

11. Darshan, J. et al. (2017) "Real Time Traffic Light Control System Using Image Processing,"
International Journal of Engineering Technology Science and Research IJETSR, 4(4), hal. 142-146.
Tersedia pada: www.ijetsr.com.

12. Gafoor, S., Ki, K. dan Indore, B. (2016) "Optimizing City Traffic Light Management for Improving
Traffic System in Smart Cities," International Journal of Computer Applications, 133(14), hal. 23-
28. Tersedia pada: www.ijcaonline.org.

13. Krause, M., Knott, V. dan Benger, K. (2015) "Implementing the Tactile Detection Task in a Real
Road Experiment to Assess a Traffic Light Assistant," The Eighth International Conference on
Advances in Computer-Human Interactions Implementing, 5 (Figure 1), hal. 43-48.

14. Oskarbski, J. et al. (2016) "Analysis of signalized intersections in the context of pedestrian
traffic,"

15. Transportation Research Procedia. Elsevier B.V., 14, hal.2138-2147. doi:

10.1016/j.trpro.2016.05.229.

16. Singh, S. K. dan Khubani, P. (2018) "Traffic Analysis of Grade Intersections and Measures of
Congestion Mitigation at Indore," Journal of Engineering and Manufacturing Technology, 3(2),
hal. 10-Tersedia pada: http://www.pyrexjournals.org/pjemt.

17. Warren, J. (2011) Arduino Robotics - Arduino Robotics By Jhon-David Warren, Josh Adams and
Harald Molle.pdf. New York: Apress. doi: 10.1007/978-1-4302-3184-4.