You are on page 1of 20

CHAPTER 1

INTRODUCTION

Transportation is one of the basic human activities for the development of societies. Ground
transportation is done by all types of vehicles such as cars, motorcycles, bicycles, or public
transportation. With the increase in the number of vehicles, traffic accidents have become a
worldwide threat. Rear-end collision is one of the most important causes of traffic accidents .
In recent years, the rear-end collision has received extensive attention, and many studies have
been conducted with the development of autonomous driving technology. The main reason
for rear-end collisions is that drivers do not have enough time to react to dangers and
incorrectly grasp the timing of braking. If the driver is warned 0.5s ahead, 60% of the
collisions will not occur, according to a study from Daimler-Benz. Moreover, if the driver is
warned 1.5s in advance, then 90% of the collisions can be blocked. Therefore, how to warn
the drivers rear-end collisions in real time is a hot topic for researchers in the field of Internet-
of-Vehicles [1]. Different road traffic problems have appeared around the world as a result of
population growth and increasing the number of cars in traffic lights, especially in large
urbanized areas. Road safety mainly depends on drivers’ decisions, and these depend only on
what drivers see and hear. This collective feedback-driven interactive method is opportunistic
for the development of the future transportation system. In this study, a survey is conducted
considering crowd-intelligence techniques for the transportation system. From this survey,
various challenges of the intelligent transportation system have been outlined and crowd-
intelligent solutions have been discussed [2]. People also face other problems like traffic jam
which is becoming riskier every day and led to traffic accidents. Traffic jam is a very serious
problem, for that many researchers have paid attention to intelligent transportation system, for
example, predicting traffic flow according to monitoring the traffic light. This mission stays
as a challenge for computer vision, several methods have been implemented in previous years
with some drawbacks such as difficulties in implementation due to using large number of
hardware and high cost [3].

There are many ways of detecting vehicles and emergencies cars on road such as motion
detection, installing lasers sensors. On both sides of the road, etc. Smart traffic light system is
an essential part in smart cities to decrease traffic congestion [4]. There are some simple
traffic management systems that have uses Global Positioning System and infrared (IR) for

1
detecting the ambulance and can also count cars and detect the real-time density of traffic
light, and some other technologies have been used radiofrequency identification tags to
identify emergency vehicles and loop inductive methods to determine the number of vehicles
[5].

1.1 Problem Statement


Traffic congestion is a pervasive issue in urban areas, leading to wasted time, increased fuel
consumption, and environmental pollution. Traditional traffic signal control systems often
rely on fixed timing patterns, which may not adapt to varying traffic conditions throughout
the day. The goal is to implement an intelligent traffic signal control system that leverages
machine .learning to optimize traffic flow in real- time. Over several decades, traffic
congestion has become a serious problem in the major cities. Congestion is particularly
associated with motorization and the diffusion of the automobile, which has increased the
demand for transportation infrastructure. However, the supply of the transportation
infrastructure has often not been able to keep up with the growth of mobility. Traffic
congestion problems consist of incremental delay, vehicle operating costs such as fuel
consumption, pollution emissions and stress that result from interference among vehicles in
the traffic stream, particularly as traffic volumes approach a road’s capacity. Across cities
more people are spending more time sitting in traffic jams than ever before Traffic congestion
occurs when the demand is greater than the available road capacity. There are many reasons
that cause congestion; most of them reduce the capacity of the road at a given point or over a
certain length, for example people parking on the roads or increase in the number of vehicles.
Traffic congestion also occurs due to traffic signal. At traffic signal when road traffic density
is low signal still shows the same traffic time due to which other lane traffic increases which
result in traffic congestion. Sometimes due this problem the ambulance, police vans, fire-
fighting vehicle are not reaching at their destination on time.

1.2 Objective
The Main Objective of Developing this project is:
For the big and crowded cities like Bangalore , Mumbai etc traffic congestion is an major
issue of daily life.
One of the main reason of traffic congestion in Delhi cities is lack of planning for traffic
signal.

2
The traffic signal of Delhi city is traditional and its signal time is fixed for every routes. So,
traffic police can’t use these traffic signal nowadays.
Therefore we are proposing a new Traffic Light Control System using ML by frequently
changing the time of the signal on the basis of Traffic Density.
We are using Haar Cascade algorithm. It’s used for detecting the object, which superimposes
positive image over a set of negative images.
 The HERE maps API enables us to extract the traffic density of a particular road.
 API provides us with jam factor of particular road. The extraction of API from maps leads
us to the lane where we want to check congestion.
 Also, we check the surrounding roads as well to distribute the congestion from one crowded
road to less crowded ones. According to the best factor which can be chosen at that time, the
system selects it.
 The priority list will be set in it. The system will execute the algorithm and dynamically
handle the traffic density.

1.1.1 Scope
The current work focuses on how to bring an effective solution to this problem: Reduce the
traffic congestion. Avoid road blocks and prevent accidents from happening by effectively
analyzing vehicles every now and then. Reduce waiting period for the vehicles and people
and also save fuel.
1.3 Introduction to Machine Learning
Following are the components of ML –
Machine Learning is the field of study that gives computers the capability to learn without
being explicitly programmed. ML is one of the most exciting technologies that one would
have ever come across. As it is evident from the name, it gives the computer that makes it
more similar to humans: The ability to learn. Machine learning is actively being used today,
perhaps in many more places than one would expect.
As it is evident from the name, it gives the computer that makes it more similar to humans:
The ability to learn. Machine learning is actively being used today, perhaps in many more
places than one would expect.
Machine learning models are trained with a certain amount of labeled data and will use it to
make predictions on unseen data. Based on this data, machines define a set of rules that they
apply to all datasets, helping them provide consistent and accurate results. No need to worry
about human error or innate bias.

3
Figure 1.1. ML Model

Supervised Learning

Supervised learning is a type of machine learning algorithm that learns from labeled data.
Labeled data is data that has been tagged with a correct answer or classification.
Supervised learning, as the name indicates, has the presence of a supervisor as a teacher.
Supervised learning is when we teach or train the machine using data that is well-labelled.
Which means some data is already tagged with the correct answer. After that, the machine is
provided with a new set of examples(data) so that the supervised learning algorithm analyses
the training data(set of training examples) and produces a correct outcome from labeled data.
For example, a labeled dataset of images of Elephant, Camel and Cow would have each
image tagged with either “Elephant” , “Camel”or “Cow.”

1.4 Existing Software’s


System software consists of different parts which are combined together, below a brief
description of required software is defined one by oneYolov3 “You Only Look Once” is an
algorithm that uses CNN for object detection. YOLO is one of the fastest object detection
algorithms. This algorithm applies a single neural network to the full image, it is accurate as

4
SSD but 3 times faster it can be installed on Windows and Linux [13]. YOLOv3 as an
algorithm that is a single convolutional neural network that predicts the bounding boxes with
the class probabilities from the single check. This sort of algorithm is used mainly within the
real-time application, this algorithm has been used because of it is faster algorithm for
detecting objects in real time and the accuracy is high YOLO is made up of 24 convolutional
layers, with two fully connected layer. Moreover, the input image is separated into M×M grid
cells. Grid cell that includes the midpoint of the object is responsible for predicting the object.
The output tensors of YOLO model will be a vector of N*N*(M*5 + C) in which M indicates
the predicted bounding boxes with the confidence score by each grid cell.

5
CHAPTER 2

BACKGROUND AND RELATED WORK

TABLE 2.1. Comparison of various methodology suggested by authors


SNo. Paper Name Author Year Methodology
1 A real-time collision Wang X. Liu, 2020 The preprocessed
prediction mechanism with J. Qiu T., dataset is divided into
deep learning for intelligent Mu C. Chen, training and testing sets
transportation system. as the input to train our
convolutional neural
network model.
2 Crowd intelligence for Chandra Shit 2020 The vehicles process
sustainable futuristic R. huge computing and
intelligent transportation communication tasks
system to use physical
resources efficiently.
3 Applications of deep Haghighat A.K., 2020 These improvements
learning in intelligent Ravichandra- have facilitated traffic
transportation systems Mouli V. management and traffic
Chakraborty P. planning, increased
Esfandiari Y. safety and security in
transit roads
4 Applications of machine Gangwani D. 2021 Artificial intelligence
learning and artificial Gangwani P (AI) and Machine
intelligence in intelligent Learning (ML) can be
transportation system applied to develop an
Intelligent
Transportation system
that can address the
issues of traffic
congestion and road
safety to prevent
accidents.
5 Machine learning‐based Nama M. 2021 Intelligent
traffic scheduling techniques Nath A., Transportation System
for intelligent transportation Bechra N. provides several
system Bhatia J. services in significant
Tanwar S. smart cities like traffic
management and safety.
6 Big data algorithms and Kaffash S. 2021 Web of Science (WoS)
applications in intelligent Nguyen A. T. as the source for
transportation system Zhu J material collection.
WoS is a research
platform from Thomson
Reuters containing
several databases
7 Smart traffic management Liu, J., Yu, Y., 2021 The accurate and

6
using YOLOv3 and K- & Wang, Y effective analysis of
means algorithm traffic flow made
possible by the use of
the YOLO algorithm
for vehicle recognition
and tracking in
conjunction with Alex
Net for feature
extraction resulted in
improved traffic signal
control.
8 A comprehensive review on Modi Y. 2022 An AI-enabled traffic
intelligent traffic Teli R. management system
management using machine Mehta A. can provide greater
learning algorithms Shah K. leeway to vehicles as
they can then be directed
and controlled more by
the external environment.

Wang X. Liu, J. Qiu T., Mu C. Chen[1]. With the increase in the number of vehicles, traffic
accidents have become a worldwide threat. Rear-end collision is one of the most important
causes of traffic accidents . In recent years, the rear-end collision has received extensive
attention, and many studies have been conducted with the development of autonomous
driving technology. The main reason for rear-end collisions is that drivers do not have enough
time to react to dangers and incorrectly grasp the timing of braking. If the driver is warned 0.5
s ahead, 60% of the collisions will not occur, according to a study from Daimler-Benz.
Moreover, if the driver is warned 1.5 s in advance, then 90% of the collisions can be blocked.
Therefore, how to warn the drivers rear-end collisions in real time is a hot topic for
researchers in the field of Internet-of-Vehicles (IoV).

Chandra Shit R..[2]. A crowd intelligence system plays a key role in interactive system
development. Crowd intelligence is a combined method of data collection, integration and
analysis from devices such as the smartphones, wearables, vehicles and a wide range of
Internet of Things applications to use them as sensors. This collective feedback-driven
interactive method is opportunistic for the development of the future transportation system. In
this study, a survey is conducted considering crowd-intelligence techniques for the
transportation system. From this survey, various challenges of the intelligent transportation
system have been outlined and crowd-intelligent solutions have been discussed. A layered
structure of transportation system architecture is suggested considering various problems in

7
each layer and its crowd-intelligent solutions. The crowd-intelligence-based mobility, traffic
control, traffic prediction, parking solutions have been discussed in this survey. Moreover, the
importance of crowd-intelligent techniques and its applicability is discussed for sustainable
development of futuristic transport infrastructure.

Haghighat, A. K., Ravichandra-Mouli, V., Chakraborty P., Esfandiari Y., Arabi S., & Sharma
A.[3]. Intelligent Transportation Systems (ITS) have seen efficient and faster development by
implementing deep learning techniques in problem domains which were previously addressed
using analytical or statistical solutions and also in some areas that were untouched. These
improvements have facilitated traffic management and traffic planning, increased safety and
security in transit roads, decreased costs of maintenance, optimized public transportation and
ride-sharing company's performance, and advanced driver-less vehicle development to a new
stage.The applications are furthermore categorized based on the gap they are trying to
address. Finally, different embedded systems for deployment of these techniques are
investigated and their advantages and weaknesses over each other are discussed. Based on
this systematic review, credible benefits of deep learning models on ITS are demonstrated and
directions for future research are discussed

Divya Gangwani & Pranav Gangwani[4]. This paper focuses on providing an overview and
applications of how Artificialintelligence (AI) and Machine Learning (ML) can be applied to
develop an Intel-ligent Transportation system that can address the issues of traffic congestion
androad safety to prevent accidents. We will then re-view various ML approaches todetect
road anomalies for avoiding obstacles, predict real-time traffic flow to achievesmart and
efficient transportation, detect and prevent road accidents to ensure safety,using smart city
lights to save energy, and smart infrastructure to achieve efficienttransportation. Next, we
review various AI approaches such as safety and emergencymanagement system to provide
safety to the public, autonomous vehicles to provideeconomical and reliable transportation.
We then propose smart parking managementand how it can be used to find parking spaces or
spots conveniently, incident detec-tion which detects the traffic incidents or accidents in real-
time provides a report.Finally, we conclude with predictive models and how the algorithms
utilize sensordata to develop an Intelligent Transportation System.

Chomtip Pornpanomchai, Thitinut Liamsanguan, Vissakorn Vannakosit . The research


intends to develop the vehicle detection and counting system using image processing. Overall

8
works are software development of a system that requires a video stream and capture to a
video frame. They consist of the following components: background road without any moving
vehicle and the frame with moving vehicles. The system is designed to find the differentiation
which is the moving vehicles and find the number of moving vehicles from the video frame.
The vehicle detection and counting system consists of four major components: 1) image
acquisition, 2) image analysis, 3) object detection and counting, and 4) Display Result The
experiment has been conducted in order to access the following qualities: 1) Usability, to
prove that the system can determine vehicle detection and counting under the specific
condition lay out. 2) Efficiency, to show that the system can work with high accuracy.

Kaffash, S., Nguyen A. T. & Zhu J [6]. The Intelligent Transportation System (ITS) result in
the need for data-driven approaches. Big Data algorithms are applied to further enhance the
intelligence of the applications in the transportation field. Applying Big Data algorithms has
increasingly received attention in both the academic and industrial fields of ITS. Big Data
algorithms in ITS have a wide range of applications including but not limited to signal
recognition, object detection, traffic flow prediction, travel time planning, travel route
planning and safety of vehicle and road. This survey aims to provide a bibliography, a
comprehensive review of the application of ITS and a review of most recognized models with
Big Data used in the context of ITS. 586 papers are reviewed over the period 1997–2019.
This study provides a deep insight into applications of Big Data algorithms in ITS, revealing
different areas of those applications and integrates models and applications. The result of the
study identifies research gaps and direction for the future.

Liu, J., Yu, Y., & Wang, Y. [7]. The suggested system uses machine learning algorithms to
identify and monitor moving objects, analyses and optimize traffic flow in real-time, and then
operate traffic lights appropriately.A collection of traffic recordings was used to test the
system, and the findings showed that high-traffic locations had better traffic flow and less
congestion. The accurate and effective analysis of traffic flow made possible by the use of the
YOLO algorithm for vehicle recognition and tracking in conjunction with Alex Net for
feature extraction resulted in improved traffic signal control.Moreover, the system has an
emergency vehicle recognition and prioritizing capability that can identify emergency cars in
real-time and change traffic signals to priorities them. With this capability, emergency
services may respond more faster, which will eventually increase public safety. Overall, the
ML-powered smart light control system has shown to be excellent in resolving traffic-related

9
issues and enhancing traffic management. Further research and development may increase the
system's precision and effectiveness, making it an even more useful tool for traffic control.

Modi Y., Teli R., Mehta A., Shah K., & Shah M [8]. Due to the rise in the use of more private
vehicles and low road network capacity managing traffic with the traditional approach is
cumbersome. Pollution and productivity of individuals are highly affected due to traffic. The
use of mundane methods may not be an efficient and significant solution for varying traffic
congestion. Nowadays, artificial intelligence (AI) and machine learning (ML) are playing an
important role in solving many real-world problems. So, to tackle this problem, use of
artificial intelligence and machine learning can give optimal solutions. An AI-enabled traffic
management system can provide greater leeway to vehicles as they can then be directed and
controlled more by the external environment. The main aim of using AI is to decrease manual
interfacing. Various algorithms have been designed to curb this problem.This article presents
the detailed methodology, review, challenges, and future scope of the use of various
algorithms for optimizing different aspects of Traffic Management System, i.e., Smart Traffic
Signal Management, Traffic Flow Prediction, Traffic Congestion Detection, and its
Management, and Automatic Detection of Traffic Signal.

10
CHAPTER 3
HARDWARE AND SOFTWARE REQUIREMENTS

3.1. Hardware Requirements


● CPU: Intel Core 2 Quad CPU Q6600 @ 2.40GHz (4 CPUs) / AMD Phenom 9850 Quad-
Core Processor (4 CPUs) @ 2.5GHz
● RAM – 2 GB or higher
● Disk – 30 GB or higher
● Operating System – Windows /Darwin
● Ardeino
● OpenCV
● Powerful server
● ControlUnit

3.2. Software Requirements


● Pycharm
● Python IDE
● Jupyter Notebook
● Redhat Interprise Linux(Rehl)

3.3. Testing Technology


● Cypress
● TestNg
● Appium
● Tensorflow & IBM caffe

11
CHAPTER 4
SDLC METHODOLOGIES
The agile methodology was used. This is because the agile methodology is more adaptable
and can accommodate changes more easily. It is also more user-centric, which is important in
this case because the system is being developed for the users. Agile is an iterative approach to
project management and software development that enables teams to deliver value to
customers faster and with fewer headaches. An agile team delivers work in small but
consumable increments rather than betting everything on a "big bang" launch. Continuous
evaluation of requirements, plans, and results provides teams with a natural mechanism for
responding to change quickly. The following SDLC models are proposed:

4.1. SDLC Models


4.1.1. Waterfall Model

The waterfall is a widely used SDLC model. The waterfall model is a continuous software
development model in which development is seen as flowing steadily downwards (like a
waterfall) through the steps of requirements analysis, design, implementation, testing
(validation), integration, and maintenance. To begin, some certification techniques must be
used at the end of each step to identify the end of one phase and the start of the next. Some
verification and validation usually do this by ensuring that the stage's output is consistent
with its input (which is the output of the previous step) and that the stage's output is
consistent with the overall requirements of the system.

Figure 4.1. Waterfall Model

12
4.1.2. RAD Model

The Rapid Application Development (RAD) process is an adaptation of the waterfall model
that aims to develop software in a short period of time. The RAD model is based on the idea
that by using focus groups to gather system requirements, a better system can be developed in
less time.

o Business Modeling
o Data Modeling
o Process Modeling
o Application Generation
o Testing and Turnover

Figure 4.2. RAD Model

4.1.3. Spiral Model

The spiral model is a process model that is risk-driven. This SDLC model assists the group in
implementing elements of one or more process models such as waterfall, incremental,
waterfall, and so on. The spiral technique is a hybrid of rapid prototyping and concurrent
design and development. Each spiral cycle begins with the identification of the cycle's
objectives, the various alternatives for achieving the goals, and the constraints that exist. This
is the cycle's first quadrant (upper-left quadrant).
The cycle then proceeds to evaluate these various alternatives in light of the objectives and
constraints. The focus of evaluation in this step is on the project's risk perception.
This step may involve activities such as benchmarking, simulation, and prototyping.

13
Figure 4.3. Spiral Model

4.1.4. Incremental Model

The incremental model does not stand alone. It must be a series of waterfall cycles. At the
start of the project, the requirements are divided into groups. The SDLC model is used to
develop software for each group. The SDLC process is repeated, with each release
introducing new features until all requirements are met. Each cycle in this method serves as
the maintenance phase for the previous software release.

Figure 4.5. Incremental Model

The incremental model has been modified to allow development cycles to overlap. The
following cycle may begin before the previous cycle is completed.

14
CHAPTER 5

APPLICATION ARCHITECTURE

OpenCV, or Open Source Computer Vision Library, is an open-source computer vision and
machine learning software library. It provides a wide range of tools and functions for image
and video processing, including various algorithms for tasks such as object detection, image
recognition, feature extraction, image stitching, and more.
OpenCV (Open Source Computer Vision Library) is a free, open-source, and cross-platform
library that includes hundreds of computer vision algorithms. It has C++, Python, Java, and
MATLAB interfaces and supports Windows, Linux, Mac OS X, Android, and iOS.
OpenCV was originally developed by Intel in 1999 and later maintained by Willow Garage. It
has since become a widely used and supported open-source library, with contributions from
researchers, developers, and organizations around the world. OpenCV is written in C++ and
has interfaces for C, Python, and Java, making it accessible to a broad audience of developers.
Some key features of OpenCV include:

5.1.1 Image Processing:


OpenCV provides a variety of functions for basic and advanced image processing tasks, such
as filtering, morphological operations, and color space transformations.
5.1.2 Computer Vision:
The library includes algorithms for computer vision tasks like feature detection, object
tracking, camera calibration, and 3D reconstruction.
5.1.3 Machine Learning:
OpenCV integrates machine learning functionalities, including support for popular machine
learning frameworks like TensorFlow and PyTorch. It includes tools for training and
deploying machine learning models for tasks such as object recognition.
5.1.4 Camera Calibration:
OpenCV supports camera calibration, which is essential for correcting lens distortions and
obtaining accurate measurements from images.
5.1.5 Robotics:
OpenCV is commonly used in robotics for tasks such as navigation, object manipulation, and
visual perception.

15
The library is free to use, modify, and distribute under an open-source license. It has a large
and active community that contributes to its development and maintenance. OpenCV is
widely employed in various fields, including computer vision research, robotics, augmented
reality, and more.

Figure 5.1. Application Architecture

OpenCV provides a variety of functions for basic and advanced image processing tasks, such
as filtering, morphological operations, and color space transformations.The library is free to
use, modify, and distribute under an open-source license. It has a large and active community
that contributes to its development and maintenance.

5.1 Phases of project

There are four main features of this project. So the project is currently being developed in
four phases.
Phase 1: Planning Phase: Clearly define the goals and objectives of the traffic control system
using image processing and AI. Identify the scope of the project, including geographical
coverage, types of traffic scenarios, and expected outcomes.Allocate human resources,
hardware, and software resources needed for the project.Develop a detailed project timeline
with key milestones.

16
Phase 2: Development Phase:
Data Collection and Preparation: Prepare the dataset for training and testing the image
processing and AI models. Develop or select image processing algorithms for vehicle
detection.
Implement AI algorithms for traffic control decision-making.
Phase 3: The third phase will be platform stability, Integrate the image processing and AI
components into a cohesive system. Establish communication channels between different
system components. System Testing: Conduct comprehensive testing of the entire system.
Identify and resolve any bugs or issues.
Phase 4:The deep learning model will assist in matching users with diseases and offering
disease solutions in accordance with it throughout this, the fourth and final phase.

5.2 Use case diagram: Traffic Signal

A use case diagram mainly consists of actors, use cases and relationships. More complex
larger diagrams can include systems and boundaries. We’ll discuss the guidelines based on
objects. This enables you to quickly highlight the important roles in the system. If your use
case is send email and if it interacts with the email management software, then the software is
an actor to that particular use case. For example, if you’re analyzing a bank customer, typical
use cases include open account, deposit and withdraw. Showing them in the logical order
makes more sense. This is done to improve readability and add clarity.
Again this is done to improve the readability of the diagram. Use cases look at a system at its
edges – where “actors” (individuals or other systems) interact with it for some benefit. They
describe what each actor “should be able to do” in the simple language of positive, active-
voice verbs – making them equally understandable by non-technical customers and
sophisticated engineers. That alone is a powerful thing. They provide a quick and simple
mechanism for reaching shared understanding between customers and suppliers about what’s
important to address. This enables you to quickly highlight the important roles in the system.
If your use case is send email and if it interacts with the email management software, then the
software is an actor to that particular use case.

17
Figure 5.3. Use Case Diagram

 Arrow points to the base use case when using <<extend>>

 <<extend>> can have optional extension conditions

 Arrow points to the included use case when using <<include>>

 Both <<extend>> and <<include>> are shown as dashed arrows.

 Actor and use case relationship don’t show arrows.

5.3 Class diagram: Traffic Signal

One of the key benefits of using UML class diagrams is that they provide a clear and concise
way to represent the structure of a system. By using standardized symbols and notation, class
diagrams make it easy for developers to understand the relationships between different classes
and objects, and to communicate these relationships to other team members. This can be
especially useful in large-scale projects, where it can be difficult to keep track of the
thousands of classes and objects that make up a system.

18
Figure 5.4. Class Diagram of Traffic Signalling System

Another important benefit of UML class diagrams is that they allow developers to identify
potential problems early in the development process. For example, if a class diagram shows
that one class has too many dependencies, it may indicate that the class is too complex and
should be refactored. Similarly, if a class diagram shows circular dependencies between
classes, it may indicate a design problem that needs to be resolved.
In terms of software development methodologies, UML class diagrams are a key component
of many methodologies such as Agile and Waterfall, they are widely used in the software
development industry. They allow developers to design and develop a system in an iterative
and incremental way, which is the core of Agile methodology.

19
REFERENCES

[1] Wang, X., Liu, J., Qiu, T., Mu, C., Chen, C., & Zhou, P. (2020). “A real-time collision
prediction mechanism with deep learning for intelligent transportation system.” IEEE
transactions on vehicular technology, volume 69 issue 9, Page no. 9497-9508.
[2] Chandra Shit, R. (2020). Crowd intelligence for sustainable futuristic intelligent
transportation system: a review. Iet intelligent transport systems, volume 14 issue 6, Page no.
480-494.
[3] Haghighat, A. K., Ravichandra-Mouli, V., Chakraborty, P., Esfandiari, Y., Arabi, S., &
Sharma, A. (2020). Applications of deep learning in intelligent transportation systems.
Journal of Big Data Analytics in Transportation, volume 2, Page no. 115-145.
[4] Gangwani, D., & Gangwani, P. (2021). Applications of machine learning and artificial
intelligence in intelligent transportation system: Applications of Artificial Intelligence and
Machine Learning: Select Proceedings of ICAAAIML 2020 , Page no. 203-216.
[5] Nama, M., Nath, A., Bechra, N., Bhatia, J., Tanwar, S., Chaturvedi, M., & Sadoun, B.
(2021). Machine learning‐based traffic scheduling techniques for intelligent transportation
system: Opportunities and challenges. International Journal of Communication Systems,
volume 34 issue 9, Page no. 414 - 425.
[6] Kaffash, S., Nguyen, A. T., & Zhu, J. (2021). Big data algorithms and applications in
intelligent transportation system. International Journal of Production Economics, volume 231,
107868.
[7] Xiaokai Yao, Yucheng Zhang, Yongkang Yao, Jiamin Tian, Chen Yang, Zhengyuelang
Xu,Yongjian Guan. Smart traffic management using YOLOv3 and K-means algorithm
proceedings in IEEE 14th International Conference on Intelligent Computation Technology
and Automation (ICICTA) year 2021 , (Page no. 312-317).
[8] Modi, Y., Teli, R., Mehta, A., Shah, K., & Shah, M. (2022). A comprehensive review on
intelligent traffic management using machine learning algorithms. Innovative infrastructure
solutions, volume 7 issue 1, Page no. 128.

20

You might also like