0% found this document useful (0 votes)
10 views39 pages

Phase 12

Uploaded by

puneeth T
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
10 views39 pages

Phase 12

Uploaded by

puneeth T
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 39

VISVESVARAYA TECHNOLOGICAL UNIVERSITY

Belagavi-590018

Project Report CC
ON

“ENHANCING URBAN RESILIENCE REAL TIME MONITORING


SYSTEMS FOR SMART CITIES USING IOT”
Submitted in the partial fulfillment of the requirements for the award of

BACHELOR OF ENGINEERING IN
COMPUTER SCIENCE AND ENGINEERING
Project Work (21CSP76)
BY
PUNEETH T (1RI21CS085)
RAHUL (1RI21CS087)
BASAVARAJ SHANKAR MUTTAGI (1RI21CS401)
ABHISHEK SINGH (1RI21CS009)

UNDER THE GUIDANCE OF


Veena V
Professor, CSE Department

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING


Accredited By NBA, NAAC “A+”
R R INSTITUTE OF TECHNOLOGY
Approved by AICTE, New Delhi, Recognized by Govt. of Karnataka,
Autonomous Institution under VTU
Raja Reddy Layout, Chikkabanavara, Bengaluru – 560 090
ACADEMIC YEAR 2024-25
DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

CERTIFICATE
Certified that the project entitled “Enhancing Urban Resilience real time monitoring systems for
smart cities using IoT” carried out by Puneeth T (1RI21CS085), Rahul (1RI21CS087), Basavaraj
Shankar Muttagi (1RI22CS401), Abhishek Singh (1RI21CS009) bonafide students of R R Institute of
Technology in partial fulfillment for the award of Bachelor of Engineering / Bachelor of Technology in
Computer Science and Engineering of the Visvesraya Technological University, Belagavi during the year
2024-25. It is certified that all corrections/suggestions indicated for Internal Assessment have been
incorporated in the Report deposited in the departmental library. The Project report has been approved as it
satisfies the academic requirements in respect of Major Project prescribed for the said Degree.

.……………………………. ..….…………………….. ….……………………


Signature of Guide Signature of HOD Signature of Principal
[Veena V] [Dr. Manjunath R] [Dr. Mahendra K V]
Professor Professor and Head Principal
Department of CSE, RRIT Department of CSE, RRIT RRIT, Bengaluru

Name of the Examiners Signature with Date

1. ….…………………………. …………………………….

2. ….…………………………. …………………………….
DECLARATION

We Puneeth T (1RI21CS085), Rahul (1RI21CS087), Basavaraj Shankar Muttagi (1RI22CS401),


Abhishek Singh (1RI21CS009) students of 7th semester in, Computer Science and Engineering, R R
Institute of Technology, Chikkabanavara, Bangalore -560090, declare that the Major Project work entitled
“Enhancing Urban Resilience real time monitoring systems for smart cities using IoT ” has
been carried out by us and submitted in partial fulfillment of the course requirements for the award of
degree in Bachelor of Engineering in Computer Science and Engineering of Visvesvaraya
Technological University, Belgaum, during the academic year 2024-25.

Date: Puneeth T (1RI21CS085)


Rahul (1RI21CS087)
Place: Bangalore
Basavaraj Shankar Muttagi
(1RI22CS401)
Abhishek Singh (1RI21CS009)
ABSTRACT

Urban traffic congestion is a growing challenge due to increasing populations and vehicle density
in cities. Traditional traffic management systems, which rely on static timers and fixed schedules,
are unable to adapt to real-time traffic conditions, leading to inefficiencies, increased fuel
consumption, and environmental pollution. To address these issues, IoT-based smart traffic
systems capable of real-time data collection, analysis, and decision-making. These systems use a
network of sensors and cameras to dynamically manage traffic, optimize signal timings, and
enhance road capacity, thereby reducing congestion and travel time.

IoT technologies have enabled the development of cost-effective and flexible traffic solutions.
Unlike traditional systems, IoT-inspired smart traffic management systems use real-time data to
optimize traffic light interconnections without modifying vehicles. This approach significantly
reduces congestion, improves traffic flow by more than 20%, and requires less infrastructure
investment compared to existing solutions. By processing large datasets collected from urban
intersections, these models can dynamically adjust traffic signals based on real-time data,
reducing waiting times and improving overall efficiency.

In addition to improving traffic flow, smart traffic management systems prioritize safety and
emergency response. Systems that integrate computer vision for vehicle detection and
classification enable priority scheduling for emergency vehicles like ambulances. This not only
ensures faster response times but also reduces delays for other road users. The proposed systems
focus on cost efficiency, scalability, and ease of implementation. By embedding low-cost sensors
at regular intervals and using big data analytics for traffic density prediction, these systems
provide sustainable solutions for urban congestion.
ACKNOWLEDGEMENT

Any achievement, be it scholastic or otherwise does not depend solely on the individual efforts but
on the guidance, encouragement and cooperation of intellectuals, elders and friends. A number of
personalities, in their own capacities have helped us in carrying out this Project work. We would
like to take this opportunity to thank them all.

First and foremost we would like to thank Dr. Mahendra K V, Principal, RRIT, Bangalore, for his
moral support towards completion of our project work.

We express our gratitude to Dr. Manjunath R, Head of Department of Computer Science and
Engineering, RRIT, Bangalore who has always been a great source of inspiration.

We are grateful to our project Coordinator Dr. Shivakumar Swamy N, Professor, Department of
CSE, RRIT, Bangalore for the support and encouragement lender throughout the project work

We are grateful to the guidance and encouragement given by our guide Veena V, Professor of
Department of Computer Science and Engineering, RRIT, Bangalore, who also has helped us in
various stages of project, optimizing the report and making this project a success.

We also extend our sincere thanks to the teaching and non-teaching faculty of the Department of
Computer Science and Engineering, RRIT, Bangalore, who have constantly supported us
throughout the course of our project work.

Last, but not the least, we would like to express our deep sense of thanks to family and friends for
their moral support to improve the project work.

Puneeth T (1RI21CS085)

Rahul (1RI21CS087)

Basavaraj Shankar Muttagi (1RI22CS401)

Abhishek Singh (1RI21CS009)


TABLE OF CONTENT

Sl. No Topic Page No.


1. Chapter 1
Introduction 1-3
1.1 Overview 1
1.2 Objectives 1
1.3 Applications 1
1.4 Organisation of Report 2
2. Chapter 2
Problem identification 4-6
2.1 Overview 4
2.2 Existing System 4
2.2.1 Traffic Monitoring Systems 4
2.2.2 Vehicle Recognition Systems 4
2.3 Proposed System 5
2.3.1 Key Features 5
2.3.2 Advantages 5
2.4 Summary 6
3. Chapter 3
Literature review 7-14
3.1 Reviews 7
3.2 Summary 14
4. Chapter 4
System Requirements 15-18
4.1 Overview 15
4.2 Functional Requirements 15
4.3 Non-Functional Requirements 15
4.4 Hardware and Software Requirements 16
4.4.1 Hardware Requirements 16
4.4.2 Software Requirements 18
4.5 Summary 18
5. Chapter 5
System Design 19-26
5.1 System Architecture 19
5.1.1 Components of the System Architecture 19
5.1.2 Detailed System Architecture 20
5.2 Data Flow of the System 21
5.2.1 Stage 1: Initialization 21
5.2.2 Stage 2: Data Collection 21
5.2.3 Stage 3: Data Processing 21
5.2.4 Stage 4: Intervention 22
5.2.5 Stage 5: Output 22
5.3 Key Modules and Their Functions 23
5.4 Use Case Diagram 24
5.4.1 Purpose 24
5.4.2 Actors 24
5.4.3 Use Cases 24
5.4.4 Use Case Descriptions 25
5.5 Summary 26
6 Chapter 6
Conclusion 27
7 References 28-29
LIST OF FIGURES

Fig No. Description Page No.


4.1 Arduino Uno Board 16
4.2 Raspberry Pi Model 3 16
4.3 (a) Heart Rate Sensor (b) LM35 Sensor 17
4.4 Webcam Setup 17
5.1 System Architecture Diagram 20
5.2 Data Flow Diagram 23
5.3 Use Case Diagram 25
LIST OF TABLES

Table No. Description Page No.


5.1 Table for architecture layers 20
5.2 Table for Key Modules and their functions 24
5.3 Table of Use Case Descriptions 25
Enhancing Urban Resilience real time monitoring systems for smart cities using IoT

CHAPTER 1

INTRODUCTION
1.1 Overview
Urban resilience refers to a city's ability to adapt, withstand, and recover from challenges
such as traffic congestion. In smart cities, real-time monitoring systems powered by the
Internet of Things (IoT) play a vital role in providing timely, accurate data for decision-
making and resource management. By combining IoT technologies and advanced
emotion recognition systems, this project aims to provide a robust framework for real-
time health tracking and intervention.

1.2 Objectives
1. Real-Time Data Collection: Utilize IoT sensors and devices to gather real-time
data on traffic, air quality, energy usage, and infrastructure health.
2. Improved Public Safety: Develop systems to monitor and alert authorities about
accidents, crime, and hazardous conditions.
3. Smart Transportation: Implement IoT-based systems to reduce traffic congestion
and improve public transit efficiency.

1.3 Applications
The developed system has several practical applications:

Reduction in Traffic Congestion:

 Optimized Traffic Flow: Through dynamic traffic signal control and real-time
traffic predictions, deep learning systems can alleviate congestion by adjusting
light timings and routing traffic based on current conditions.
 Improved Mobility: Traffic optimization models can predict congestion patterns,
offering real-time information that helps drivers avoid traffic jams and select
alternate routes, thus enhancing overall mobility within urban areas.

Environmental Benefits:

 Energy Efficiency: Optimized traffic flow and reduced congestion mean that
vehicles consume less fuel, leading to a more sustainable urban transport system.

DEPT OF CSE, RRIT 2024-25 1


Enhancing Urban Resilience real time monitoring systems for smart cities using IoT

1.4 Organisation of Report


This report is systematically structured to ensure a clear and logical flow of information,
making it accessible and comprehensive. The report begins with a preliminary section
that includes essential documents such as the title page, certificates, declarations, and the
table of contents. Following this, the main content is divided into six well-defined
chapters and auxiliary sections as described below:
Chapter 1 - Introduction
This chapter provides an overview of the project, including the importance of integrating
real-time traffic control and data collection of the vehicles. It also introduces the
objectives, applications, and relevance of the project, setting the stage for subsequent
chapters.
Chapter 2 - Problem Statement
A detailed identification of challenges faced by peoples who are driving in the traffic.
This chapter also highlights the limitations of existing solutions and presents the proposed
system as a comprehensive framework.
Chapter 3 - Literature Review
This section compiles relevant studies and technological advancements that have
contributed to the fields of smart traffic, vehicle congestion, providing a solid foundation
for the project.
Chapter 4 - System Requirements
A comprehensive outline of the hardware and software specifications required to
implement the proposed framework, ensuring precision and efficiency in real-time
operations.

Chapter 5 - System Design


This chapter elaborates on the architecture, workflow, and core modules of the proposed
system. It includes diagrams, data flow representations, and detailed descriptions of the
functionalities.
Chapter 6 - Conclusion
The final chapter summarizes the outcomes of the project, emphasizing its significance in
addressing the dual needs of traffic. It also identifies potential avenues for future
enhancements.

DEPT OF CSE, RRIT 2024-25 2


Enhancing Urban Resilience real time monitoring systems for smart cities using IoT
The main report is supplemented with references and annexures, providing additional
resources and data supporting the research and development of the project. Figures, tables,
and diagrams are strategically placed throughout the document to enhance understanding
and illustrate key concepts. This systematic organization ensures that readers can navigate
the report easily and comprehend the innovative contributions of the project.

DEPT OF CSE, RRIT 2024-25 3


Enhancing Urban Resilience real time monitoring systems for smart cities using IoT

CHAPTER 2
PROBLEM STATEMENT
2.1 Overview
Urban resilience is a city's ability to adapt and recover from challenges like traffic
congestion, natural disasters, and environmental concerns. IoT-powered real-time
monitoring systems play a critical role in smart cities by collecting and analyzing live data
on traffic. These systems optimize traffic management, promote sustainability by reducing
emissions and enabling efficient energy use such as real-time updates and route
recommendations, improve the urban experience. By integrating IoT, cities can ensure
adaptability, safety, and sustainability in urban environments.

2.2 Existing System


Current real-time traffic monitoring systems utilize CNNs and IoT for efficient traffic
management, relying on camera feeds and sensors for data collection and analysis.

2.2.1 Traffic Monitoring Systems

Functionality: Traffic monitoring systems leverage IoT sensors, cameras, and real-time data
analytics to manage traffic flow, detect incidents, optimize traffic signals, and provide route
recommendations, enhancing safety, efficiency, and sustainability.

Drawbacks:
 Traffic monitoring systems face challenges such as high implementation costs,
scalability issues, and privacy concerns.
 They are also vulnerable to cybersecurity threats, depend heavily on reliable
connectivity, and may be less effective under adverse weather conditions.

2.2.2 Emotion Recognition Systems

Functionality: Systems use facial recognition algorithms to detect emotions such as


happiness, sadness, or stress.

Drawbacks:

 Focus solely on emotional states without addressing physical health.


 Do not provide real-time therapeutic solutions like music recommendations.
 Lack integration with IoT for real-time monitoring and alerts.

DEPT OF CSE, RRIT 2024-25 4


Enhancing Urban Resilience real time monitoring systems for smart cities using IoT

2.3 Proposed System


The proposed system integrates real-time smart traffic monitoring and road congestion into a
single framework. It ensures holistic use for vehicles by addressing both traffic signals
and road congestion.

2.3.1 Key Features


 IoT-Enabled Sensors and Devices

Deployed at strategic locations to monitor traffic density, vehicle speed, and environmental
factors in real time.

 Real-Time Data Collection and Analysis

Continuously collects data from IoT devices, processes it using advanced analytics, and
identifies congestion patterns or anomalies.

 Predictive Traffic Management

Utilizes historical and live data to forecast traffic trends and preemptively manage
congestion.

 Centralized Control System

Unified dashboard for city authorities to monitor, manage, and control traffic systems in real
time.

 Data-Driven Urban Planning

Offers actionable insights for long-term infrastructure planning and development based on
traffic patterns.

2.3.2 Advantages

 Efficient Traffic Management: Real-time IoT data optimizes traffic signals, reducing
congestion and improving flow.

 Enhanced Safety: Automated monitoring detects hazards and ensures quicker


emergency response, improving road safety.

 Real-Time Insights and Alerts:Continuous monitoring provides instant insights for


managing unusual traffic patterns or emergencies, minimizing disruptions.

 Data-Driven Urban Planning: Collected traffic data supports better decision-making


for infrastructure development and future urban expansion.

DEPT OF CSE, RRIT 2024-25 5


Enhancing Urban Resilience real time monitoring systems for smart cities using IoT
2.4 Summary
The existing systems lack integration between health monitoring and emotion recognition,
leaving critical gaps in mental health care. The proposed system bridges this gap by
providing a unified solution that monitors both patients and caregivers, detects emotions,
and delivers therapeutic interventions. By combining IoT, machine learning, and real-
time data processing, this system ensures holistic care and enhances the overall well-
being of patients and their caregivers.

DEPT OF CSE, RRIT 2024-25 6


Enhancing Urban Resilience real time monitoring systems for smart cities using IoT

Chapter 3

Literature review

1.1 Reviews
[1] KoushalyaBijjaragi and Poonam Tijare (2023) The storage and administration of
enormous amounts of data is becoming more complicated due to ever-changing
advancements and the increase in traffic. Large data indexes like these necessitate capacity
devices and a unified approach to registration. Hadoop is a trustworthy data storage
platform that uses distributed Hadoop records to store large amounts of data and allows
for doable equal processing through MapReduce[3-4]. Fast recovery of filtered data flow
for traffic analysis and forecasting is possible using MapReducein the year (2016).

[2] Dr. MurlidharDhanawade and Instructor Rahul Wantmure? Megacities around the
world including in India are expanding. The plan is already in the works. A "smart city"
is an organized urban region where numerous metropolitan activities are governed and
coordinated by innovation. Building a smart city is the perfect opportunity to make full
use of the web of things, a relatively new IT invention[5-6]. They should keep their
current persona instead of developing a whole new one. Furthermore, issues of legitimacy
and uprightness need to be handled. There are clear and unmistakable challenges to
building a smart city in India. Every city is unique, which is why a smart city mindset.

[3] No. 6, the Kaoutar Ben Ahmed group of 2023 In this article, we will take a look at the
current situation of the field as well as its upcoming critical capabilities. We will also
define big data in smart cities, assess how it could change our lives, and talk about the
downsides of these new technologies that could trick us or compromise our safety.

[4] The study presented in the "Proceedings of the 2018 International Conference on
Communication and Signal Processing (ICCSP)" introduces a Priority-Based Real Time
Smart Traffic Control System. Leveraging computer vision, image processing, and
machine learning, the system dynamically assesses background traffic conditions,
prioritizing emergency vehicles for expedited passage. This approach anticipates a
reduction in response times during critical situations, demonstrating the potential of real-
time adaptability in traffic control to enhance overall urban safety.

DEPT OF CSE, RRIT 2024-25 7


Enhancing Urban Resilience real time monitoring systems for smart cities using IoT

[4] The "Image Processing-Based Smart Traffic Control System for Smart Cities,"
featured in the "Proceedings of the 2021 12th International Conference on Computing,
Communication, and Networking Technologies (ICCCNT)," focuses on the utilization of
the Canny Edge detection technique and MATLAB for digital image processing. This
innovative system enhances real-time traffic management by precisely identifying and
analyzing traffic patterns, optimizing signal timings, and improving overall traffic
efficiency. The integration of Canny Edge detection and MATLAB underscores the
significance of sophisticated image processing in the quest for efficient urban traffic
control.

[5] "Urban Safety: An Image-Processing and Deep-Learning Based Intelligent Traffic


Management and Control System," published in "Fuzzy Systems and Neural Networks
for Engineering Applications [2021]," introduces a paradigm shift by integrating image
processing and deep learning techniques. The system aims to predict and control traffic
conditions in real-time, contributing to enhanced urban safety. This research highlights
the potential of merging advanced technologies to create intelligent traffic management
systems capable of adapting to the complexities of urban environments.

[6] The "Comparative Analysis of Canny Edge Detection Based Smart Traffic Control
System Using Multi-Type Image Processing," presented in the "Proceedings of the 2023
International Conference on Computer Communication and Informatics (ICCCI),"
conducts a comprehensive examination of a smart traffic control system employing the
Canny Edge Detection Algorithm and multi-type image processing techniques. The
research focuses on automating the allocation of green traffic signal time based on real-
time traffic conditions, providing insights into the strengths and weaknesses of different
image processing methods for smart traffic control.

[7] "The Smart in Smart Cities: A Framework for Image Classification Using Deep
Learning," published in the journal "Next Generation Intelligent [2022]," presents a
comprehensive framework for image classification using deep learning techniques. With
a focus on smart cities, the research leverages advanced neural network architectures and
image analysis techniques to contribute to the development of technology-driven models
for intelligent urban systems. The paper emphasizes the versatility of the framework in
supporting various applications, including traffic management, surveillance, and
infrastructure monitoring.

DEPT OF CSE, RRIT 2024-25 8


Enhancing Urban Resilience real time monitoring systems for smart cities using IoT

[8] The research conducted in 2022, titled "Geolocation Estimation of Target Vehicles
Using Image Processing and Geometric Computation," emphasizes the integration of deep
learning, image processing, and geometric computation technologies. By enhancing traffic
scene awareness, the system improves the accuracy and efficiency of estimating the
geolocation of target vehicles in real-time traffic environments. This research aligns with
the broader goal of leveraging advanced technologies to address contemporary urban
traffic challenges.

[9] The paper "E-Challan System Implemented in Lahore Using Digital Image
Processing" from the "2021 International Conference on Innovative Computing (ICIC)"
explores the implementation of an electronic challan system in Lahore, showcasing the
transformative power of Digital Image Processing (DIP). This system streamlines the
identification and documentation of traffic offenses, contributing to reduced paperwork,
faster processing times, and increased transparency in the enforcement of traffic
regulations.

[10] The research presented in "Smart Traffic Control for Emergency Vehicles Using the
Internet of Things and Image Processing" (EAI/Springer Innovations in Communication
and Computing [2021]) introduces a revolutionary system designed for emergency
vehicles. By integrating the Internet of Things (IoT) and image processing, the study aims
to minimize delays for emergency vehicles and optimize overall traffic flow. The
interconnectedness provided by IoT and the precision of image processing contributes to a
responsive and adaptive system tailored to the unique challenges faced by emergency
services during transit.
[11] These research papers collectively contribute to the evolving landscape of smart
traffic management. They showcase a diverse array of technologies, including computer
vision, image processing, deep learning, IoT, and geolocation computation, each offering
unique insights and methodologies for enhancing urban mobility and emergency response
systems. The integration of these technologies not only improves the efficiency of traffic
control but also lays the groundwork for creating safer, more responsive, and resilient
urban environments. As technology continues to advance, the fusion of these
methodologies holds the potential to revolutionize the way cities manage their traffic,
paving the way for smarter and more sustainable transportation systems.

[12] Smart or intelligent traffic systems has become one of the most important
applications for using the IoT which is enabling the development of smart cities [10, 11].
DEPT OF CSE, RRIT 2024-25 9
Enhancing Urban Resilience real time monitoring systems for smart cities using IoT
There are many studies where focus is to improve traffic management [12]. Both
references [6] and [10] represent some review for the smart mobility and the traffic
management. As vehicles detection is one of the most important function for solving the
congestion problem. For Solving the congestion problem [13] proposed smart traffic for
congestion avoidance with multi layered (ST CA).

[13] Furthermore, in (2023) [14] proposed the enhancement of traffic system controller in
a road junction using microcontroller in order to reduce the occurrence of congestion.
Additionally, [15] presented a set of counter measures to avoid congestion and improve
the flow of the traffic. Also, to overcome the impact of traffic congestion [16] proposed
system that would be based on the measurements of the actual traffic density on the road
to control the traffic density on each side of the road and then reduce traffic congestion.
Authors in [17-19] were searching for a new methods of vehicles detection while using
different sensors as magnetic, infrared and ultrasonic sensors.

[14] Furthermore, (2022) [21] developed a hierarchal operation framework for regulating
traffic signals effectively and flexibly in dynamic traffic conditions in order to mitigate
potential traffic congestion and minimize driver’s average travel time. Additionally, [22]
proposed a bi-level optimization framework to settle the optimal traffic signal setting
problem to minimize driver’s average travel time. Also, the traffic signal timing of
individual interactions was discussed and analyzed in [23] and based on this analysis, a
signal timing algorithm based on multi objective optimization was developed to reduce
vehicle delay time, reduce the number of stops and improve the traffic capacity.

[15] Dhingra et al. [3] propose the IoT-Mobair system, which aims to provide a
comprehensive solution for monitoring air pollution. This system utilizes Internet of
Things technology, gas sensors, an Android application, and a cloud platform to detect,
monitor, and predict air quality. By integrating these components, the IoT-Mobair system
seeks to overcome the limitations of existing monitoring systems and provide users with
accurate and timely information about air pollution levels in their specific areas of
interest. The IoT-Mobair system offers significant benefits in terms of real-time
monitoring and user accessibility, it also presents challenges related to sensor accuracy,
computational complexity, and maintenance requirements.

[16] Wilson et al. [4] proposed(2020) an IoT based remote monitoring of waste levels
and odor, in order to optimize waste collection processes and mitigate environmental

DEPT OF CSE, RRIT 2024-25 10


Enhancing Urban Resilience real time monitoring systems for smart cities using IoT
pollution. The system consists of an ultrasonic sensor and an MQ136 gas sensor, which
are connected to a NodeMCU microcontroller. The ultrasonic sensor calculates the
amount of waste by measuring the distance level, while the MQ136 gas sensor detects the
foul smell produced by the waste. The data collected by the sensors is transmitted to a
real-time database, which can be monitored through an Android app. The app allows
users to receive notifications when the waste bin is full or when there is a foul smell,
enabling them to take appropriate action. The solution offers significant benefits in waste
management and environmental impact, at the same time careful consideration of the
initial investment and ongoing maintenance is essential.

[17] Shyam et al. (2022) [5] present a solution for waste collection man agement using an
IoT prototype with sensors. By providing intelligence to wastebins, the waste collection
mechanism can be dynamic and improve the quality of life in cities. The IoT prototype
with sensors works by measuring the waste level in wastebins using sonar sensors, such
as the Ultrasonic Ranging Module (HC-SR04)(2022). These sensors provide accurate
measurements of the distance from the top of the trashbin to the waste, allowing for
precise determination of the waste level. The collected data is then transmitted over the
Internet to a remote server for storage and processing . This data is used to compute
optimized waste collection routes and to predict future waste levels using artificial
intelligence algorithms.

[18] In this work, Madli et al.(2021) [6] proposed an automated and cost-effective
solution that detects the potholes and humps on the roads to help drivers avoid accidents
and vehicle damages. The proposed solution uses ultrasonic sensors to identify potholes
and humps on roads, as well as measure their depth and height. The system captures the
geographical location coordinates of these road imperfections using a GPS receiver and
stores this information in a cloud-based database. This data serves as a valuable resource
for both government authorities and vehicle drivers. One limitation is that the system
does not consider the fact that potholes or humps get repaired by concerned authorities
periodically. Therefore, the server database may not always reflect the current state of the
road. This could lead to false alerts being generated for potholes or humps that have
already been repaired.

[19] John et al. [7] proposed a smart prediction and monitoring system using IoT and
cloud technology to improve waste dis posal and collection efficiency. The system uses
off-the-shelf components, such as sensors and microcontrollers, to monitor the fill levels
DEPT OF CSE, RRIT 2024-25 11
Enhancing Urban Resilience real time monitoring systems for smart cities using IoT
of waste bins and predict upcoming wastage from waste generation patterns. The system
also utilizes Firebase Cloud Messaging (FCM) to notify appropriate personnel when the
bins are full and need to be emptied. The proposed system aims to optimize waste
collection routes, reduce fuel consumption, and improve overall waste management in
smart cities. However, the proposed system is a prototype and has not been implemented
at a product level, so there is no surety if it is feasible in the real world.

[20] Authors: Y. Agarwal, K. Jain and O. Karabasoglu “Cloud computing in vehicular


Ad Hoc Networks for smart vehicle monitoring and assistance”, Int Journal of
Transportation Science and Technology.A fast expanding area for study and development
of diverse real-time applications is connected vehicle networks (2024).

[21] Authors: A. Celesti Member, A. Galletta, L. Carnevale, M. Fazio, A. L. Ekuakille,


M. Villari “An IoT Cloud System Based on Mobile Sensor Data Processing for Traffic
Monitoring and Avoidance of Vehicle Accidents" This study investigates a potential
coping mechanism with such a problem, taking into account mobile traffic sensors put
directly in volunteer cars and private and/or public transportation(2022).

[22] Authors : S.Latif, H. Afzaal and N.A. Zafar, (2023) "Smart City: Intelligent Traffic
Monitoring and Guidance System"International Conference on Engineering and
Mathematical Technologies for Computing Almost all facets of life now use IoT, which
is an expansion of wireless sensor networks (WSNs). Authors :J. Lu, L. Huang, X. Sun, J.
Liu, and J. Jiang "A machine learning-based intelligent traffic management system” was
presented at the 2017 IEEE Conference on Conference on Robotics, Automation, and
Mechatronics (RAM) and the International Conference on Cybernetics and Intelligent
Systems (CIS), This issue has an impact on a number of facets of contemporary life, such
as time consumption, traffic accidents, increased greenhouse gas emissions, and
economic growth.

[23] A.S.Dhatrak, Dr.S.T.Gandhe (2021) Traffic jams are the main issue in cities of
developing Countries like India, China. The second-class families now become
economically strong and the population of second class families is also more which
results in more vehicles in numbers. Due to space deficiency roads are small which
results in traffic block and chaotic condition. In the Green Corridor System, all the red
signals which come in the track of emergency vehicle becomes green, means it creates a
green track to the emergency vehicle. A ‘green corridor’ is the part of traffic control
system. With a ‘green corridor’ setup, an emergency vehicle does not get any red signal
DEPT OF CSE, RRIT 2024-25 12
Enhancing Urban Resilience real time monitoring systems for smart cities using IoT
because as the vehicle comes near to the traffic signal, the signal becomes green and
create a green track to the vehicle.

[24] S. L. Mak, W. F. Tang C. H. Li, W. H. Chiu, H. S Chan, and C. C. Lee In(2023), this
paper, some traffic monitoring measurements systems are included. Vehicle tracking
algorithms are one of the systems that can provide traffic data, and the system can be
configured to project visual images for analysis. Congested transportation is a key issue
in Hong Kong. Being able to collect traffic density data for analysis can provide effective
and substantive data for sustainable development. To provide unobstructed traffic,
thereby reducing lane density and reducing obstruction to emergency services. There are
video processing methods to understand traffic conditions. These systems can only
capture different traffic conditions to evaluate traffic details. The system will install a
mounted monitor camera that focuses on the traffic scene and captures the actual image
into the video frame. Use LabVIEW to extract useful and accurate traffic information
from the image, such as speed, and traffic density, through appropriate image processing
and data analysis programs. LABVIEW is a graphical programming software that takes
commands, and provides a platform for pre-processing and post-processing data. Using
the visual aids with LABVIEW software, that can analyse traffic from various obstacles
and from data analysis, create complex algorithms and evaluate measurement accuracy.

[25] N.Prakash E.Udayakumar N.Kumareshan (2023) Arduino Based traffic congestion


control with automatic signal clearance for emergency vehicles and Stolen Vehicle
Detection. IR sensor is used to fastening the density of path be contingent on this density
the signal timing alterations automatically [8]. When the ambulance forthcoming the
junction, the particular path switch is identified by ambulance driver, where RF
transmitter is positioned in the ambulance. The RF receiver receives the signal, which is
located with the microcontroller. From that ambulance will be permits smoothly [10].
Whenever any person buys a vehicle, one first wants to get his or her vehicle recorded at
the RTO office. RTO On the other hand, whenever any vehicle owner registers a
complaint to RTO office concerning theft individual entry is made in the file. With the
help of this stolen vehicle can be easily identified by RFID technology. The Automatic
Traffic control system is calculated could repeatedly detect the density of the vehicle. The
system could mechanically open and close the gate.

1.2 Summary
DEPT OF CSE, RRIT 2024-25 13
Enhancing Urban Resilience real time monitoring systems for smart cities using IoT
A comprehensive overview of recent advancements in smart traffic management and urban
development technologies. It highlights various studies on integrating IoT, image processing,
loud computing for applications such as real-time traffic control, waste management, and
vehicle monitoring. Key innovations include systems for emergency vehicle prioritization,
congestion avoidance, and automated traffic signal optimization. Other research explores
technologies like ultrasonic sensors, machine learning for detecting traffic conditions,
managing waste efficiently, and identifying stolen vehicles. These advancements aim to
enhance urban mobility, safety, and sustainability in the context of smart cities.

DEPT OF CSE, RRIT 2024-25 14


Enhancing Urban Resilience real time monitoring systems for smart cities using IoT

CHAPTER 4

SYSTEM REQUIREMENTS

4.1 Overview
This project combines two critical aspects of patient care for individuals with mental
illness:

1. Real-Time Traffic Monitoring: Using Arduino integrated with sensors to detect the
traffic Congestion.
2. Vehicle Recognition and Track Recommendation: Using Raspberry Pi and CNN
algorithms to analyze vehicle capacity and recommend appropriate track diversion for
smooth traffic intervention.

The system leverages IoT, AI, and real-time data analytics to create an effective and
supportive ecosystem for Passengers.

4.2 Functional Requirements


 Real-Time Health Monitoring: Accurate capture and display of heart rate and
temperature data.
 Traffic Recognition: Real-time detection of Vehicles and road congestion using
CNN.

 Data Display: GUI to display vehicles, detected traffic and controls traffic .

4.3 Non-Functional Requirements


 Accuracy: Traffic congestion recognition accuracy of at least 85%.
 Latency: Minimal delay in processing and output (<3 seconds).
 Portability: Compact hardware using Raspberry Pi and Arduino.
 Scalability: Future integration of additional sensors.

DEPT OF CSE, RRIT 2024-25 15


Enhancing Urban Resilience real time monitoring systems for smart cities using IoT

4.4 Hardware and Software Requirements

4.4.1 Hardware Requirements

1. Arduino Uno
The Arduino Uno is responsible for interfacing with sensor to collect real time data collection
and process traffic parameters.
 Microcontroller: ATmega328P
 Operating Voltage: 5V
 Analog Pins: 6 (for sensor input)
 Digital I/O Pins: 14
 Communication: UART, I2C

Figure 4.1: Arduino Uno Board

2. Raspberry Pi (Model 3B)


The Raspberry Pi processes real-time video input to analyze vehicle capacity and classify
images using CNN algorithms.

 Processor: Quad-core ARM Cortex-A72 @ 1.5 GHz


 RAM: 2GB/4GB LPDDR4
 Storage: MicroSD (Minimum 32GB)
 Connectivity: Wi-Fi, Bluetooth, GPIO pins

Figure 4.2: Raspberry Pi Model 3

DEPT OF CSE, RRIT 2024-25 16


Enhancing Urban Resilience real time monitoring systems for smart cities using IoT

3. Sensors
 Heart Rate Sensor: Tracks real-time heart rate using light-based pulse detection.
Output: 5V TTL logic signal.
 Temperature Sensor (LM35): Analog temperature sensor that outputs calibrated
values in millivolts per °C.

Figure 4.3: (a) Heart Rate Sensor (b) LM35 Sensor

4. USB Webcam

The webcam captures live vehicle images, which are processed to classify traffic.

 Resolution: Minimum 720p HD


 Frame Rate: 30 fps

Figure 4.4: Webcam Setup

5. Additional Components

 Speakers: For traffic control.


 Power Supply: 5V regulated power source for Arduino and Raspberry Pi.
 MicroSD Card: For Raspberry Pi OS and CNN model storage.

DEPT OF CSE, RRIT 2024-25 17


Enhancing Urban Resilience real time monitoring systems for smart cities using IoT

4.4.2 Software Requirements

Operating Systems:

 Raspberry Pi OS for Raspberry Pi.


 Arduino IDE for programming the Arduino board.

Programming Language:

 Python 3 for traffic recognition and signal recommendation.

Libraries and Frameworks:

 OpenCV: For image processing and facial feature extraction.


 TensorFlow/Keras: For CNN-based Vehicle detection.
 Serial Communication: For transferring traffic data between Arduino and Raspberry
Pi.

4.5 Summary
This chapter outlines the hardware and software requirements necessary for the development
of the real-time Traffic monitoring and vehicle recognition system. It highlights the
essential components such as Arduino, Raspberry Pi, sensors, and the software
frameworks required to achieve accurate and efficient performance. These specifications
ensure the successful implementation of the project goals.

DEPT OF CSE, RRIT 2024-25 18


Enhancing Urban Resilience real time monitoring systems for smart cities using IoT

CHAPTER 5

System Design
This chapter provides an in-depth discussion of the design architecture, data flow, and
key components of the real-time traffic monitoring and vehicle recognition system. The
system integrates traffic monitoring for passenges and emergencyvehicles using sensors,
vehicle recognition via machine learning (CNN on Raspberry Pi), and intervention
mechanisms such as hazardous alerts and free road route recommendations.

5.1 System Architecture


The System Architecture illustrates the integration of traffic monitoring, vehicle
recognition, intervention modules, and real-time data communication for passengersand
emergency vehicles.

5.1.1 Components of the System Architecture

Health Monitoring System:

 Heart Rate Sensor (e.g., Pulse Sensor): Monitors heart rate and transmits data to the
Arduino.
 Temperature Sensor (e.g., LM35): Measures body temperature in real time.

Emotion Recognition System:

 Camera Module: Captures facial images of the patient.


 Raspberry Pi: Runs the Convolutional Neural Network (CNN) for analyzing images
and detecting emotions like Happy, Sad, or Stressed.

Intervention Module:

 Caregiver Alerts: Notifications sent when abnormal health conditions are detected for
patients or caregivers.
 Music Recommendation: Plays calming music when negative emotions (Sad or
Stressed) are identified for patients.

IoT Communication:

 Real-time data transmission to the cloud server for monitoring and storage.

Web Application:

DEPT OF CSE, RRIT 2024-25 19


Enhancing Urban Resilience real time monitoring systems for smart cities using IoT

 Provides a user-friendly interface for caregivers to view patient updates, alerts, and
trends.

5.1.2 Detailed System Architecture

The architecture can be divided into three layers:

Layer Description

Collects physiological data (heart rate, temperature) and images for


Input Layer
emotion recognition.

Processing Processes input data using Arduino (for health monitoring) and
Layer Raspberry Pi (for CNN-based emotion recognition).

Delivers results through alerts, live dashboards, and calming music


Output Layer
interventions.

Table 5.1: Table for architecture layers

The communication between these layers is facilitated by IoT modules, enabling seamless
cloud storage and retrieval.

Figure 5.1: System Architecture Diagram

DEPT OF CSE, RRIT 2024-25 20


Enhancing Urban Resilience real time monitoring systems for smart cities using IoT

5.2 Data Flow of the System


The data flow of the system represents how data is collected, processed, and used to
achieve the system's functionalities in five sequential stages. Each stage focuses on a
specific aspect of the real-time health monitoring and emotion recognition system,
highlighting the movement and transformation of data across components.

5.2.1 Stage 1: Initialization

Description: The system begins by initializing all sensors (temperature and heart rate) and
modules (camera and CNN model) to prepare for data collection and processing.

Inputs: None (system configuration is predefined).

Outputs: Sensors and modules are set to active and ready state.

5.2.2 Stage 2: Data Collection

Health Data:

 The heart rate sensor continuously records the pulse rate and sends it to the Arduino.
 The temperature sensor measures real-time body temperature and transmits it for
processing.
 Similar data is collected for caregivers.

Emotion Data:

 The camera periodically captures facial images for emotion recognition.

Inputs: Signals from sensors and images from the camera.

Outputs: Raw health data (heart rate, temperature) and facial images.

5.2.3 Stage 3: Data Processing

Health Analysis Module:

 The Arduino processes health data by comparing it against predefined thresholds.


 For example, if temperature > 37.5°C or heart_rate > 100 bpm, an alert is triggered.

Emotion Analysis Module:

 Captured facial images are processed using the CNN model on Raspberry Pi.
 Emotions are classified into three categories: Happy, Sad, or Stressed.

DEPT OF CSE, RRIT 2024-25 21


Enhancing Urban Resilience real time monitoring systems for smart cities using IoT

Inputs: Raw health data and facial images.

Outputs: Processed health status (normal/abnormal) and detected emotions.

5.2.4 Stage 4: Intervention

Abnormal Health Conditions:

 Alerts are generated and sent to the caregiver’s web application for immediate action.

Negative Emotions:

 If the emotion is detected as Sad or Stressed, the system plays calming music for the
patient.
 For example:

if emotion == "Sad" or emotion == "Stressed":

Play_Calming_Music()

Inputs: Processed health and emotion data. Outputs:

Caregiver alerts and/or music playback.

5.2.5 Stage 5: Output

Description: Final results are delivered through real-time updates and notifications: Caregivers

can monitor health and emotion updates via the web application.

Patients receive music recommendations to improve emotional well-being.

Inputs: Alerts and music playback decisions.

Outputs: Notifications for caregivers and music interventions for patients.

DEPT OF CSE, RRIT 2024-25 22


Enhancing Urban Resilience real time monitoring systems for smart cities using IoT

Figure 5.2: Data Flow Diagram

5.3 Key Modules and Their Functions


The following table summarizes the key modules of the system and their respective
functions.

Module Description

Health Monitoring Collects heart rate and body temperature using sensors for both
patients and caregivers.

Emotion Recognition Analyzes patient emotions using CNN on Raspberry Pi.

Intervention Module Sends caregiver alerts for abnormal health parameters.

Recommends and plays calming music for Sad or Stressed


emotional states.

DEPT OF CSE, RRIT 2024-25 23


Enhancing Urban Resilience real time monitoring systems for smart cities using IoT

IoT Communication Transmits data to the cloud server for monitoring and storage.

Web Application Displays real-time updates and notifications to caregivers.

Table 5.2: Table for Key Modules and their functions

5.4 Use Case Diagram

5.4.1 Purpose

The Use Case Diagram represents the primary functionalities of the real-time health
monitoring and emotion recognition system. It highlights the interactions between the
actors (users and external systems) and the system components, providing an overview of
its functional requirements.

5.4.2 Actors

4. Patient:
 The primary user of the system, who interacts with sensors and the GUI for health
monitoring and music recommendations.
5. Caregiver:
 Caregivers’ health is also monitored to ensure their well-being.
 A secondary user who monitors the patient’s health status and emotional state via
alerts or the displayed data.

5.4.3 Use Cases

The key use cases of the system are:

1. Health Monitoring:
 The system continuously measures the patient’s and caregiver’s heart rate and
temperature using Arduino-connected sensors and displays the data in real time on the
GUI.
2. Emotion Recognition:
 The system captures the patient’s facial expressions via a webcam, processes the
image using CNN, and detects the emotion (e.g., Happy, Sad, Stressed).
3. Music Recommendation:

DEPT OF CSE, RRIT 2024-25 24


Enhancing Urban Resilience real time monitoring systems for smart cities using IoT

 Based on the detected emotion, the system suggests and plays an appropriate playlist
retrieved from the database, providing a therapeutic music experience for the patient
or caregiver.
4. Data Display:
 The system shows the health parameters and detected emotions on a user-friendly
interface, enabling effective monitoring.
5. Alerts for Anomalies:
 If health readings exceed predefined thresholds, the system generates alerts for
caregivers.

Figure 5.3: Use Case Diagram

5.4.4 Use Case Descriptions

Use Case Description

Health Monitoring Sensors collect heart rate and temperature, and data is sent to the GUI
for real-time monitoring.
Webcam captures facial images, and CNN classifies them into emotions.
Emotion Recognition

Music RecommendationBased on detected emotion, appropriate playlists are fetched from the
database and played.

GUI displays real-time health data and detected emotions for user and
Data Display
caregiver reference.
Alerts are generated if health readings exceed normal thresholds,
Alerts for Anomalies
notifying caregivers.

Table 5.3: Table of Use Case Descriptions

DEPT OF CSE, RRIT 2024-25 25


Enhancing Urban Resilience real time monitoring systems for smart cities using IoT

5.5 Summary
The system is designed to integrate real-time traffic monitoring, vehicle recognition, and
intervention mechanisms. By combining:
 Traffic monitoring (Arduino),
 Vehicle analysis (Raspberry Pi with CNN),
 IoT cloud communication, and
 Alerts and road interventions,
the system ensures continuous monitoring and improved traffic and road congestion for
the passengers. The web application provides a reliable interface for users to monitor
traffic status and receive notifications in real time.

DEPT OF CSE, RRIT 2024-25 26


Enhancing Urban Resilience real time monitoring systems for smart cities using IoT

CHAPTER 6

CONCLUSION
The proposed Smart Traffic Management System aims to optimize traffic flow and reduce
congestion through IoT-enabled sensors, real-time data analytics, and AI-driven decision-
making. By integrating vehicle-detecting sensors and adaptive traffic signals, the system
dynamically adjusts traffic light timing based on density, enhancing mobility, reducing
delays, and minimizing environmental impacts such as emissions and noise.
The system employs ML and DL models for traffic flow prediction, achieving efficient
signal synchronization at intersections and improving road safety. Future research focuses
on incorporating advanced sensors to classify vehicle types, leveraging hybrid
optimization algorithms, and addressing accessibility for diverse user groups. These
developments aim to refine urban traffic management and support smart city initiatives.
The study presents a comprehensive approach to smart traffic management by integrating
IoT, big data analytics, and machine learning for real-time traffic monitoring and control.
The proposed system uses low-cost vehicle-detecting sensors, dynamic traffic signal
adjustments, and predictive analytics to enhance traffic flow, reduce congestion, and
lower emissions. Key innovations include decentralized control, adaptive signal timing,
and integration with mobile applications for user guidance.
Future enhancements focus on improving vehicle type detection, using advanced sensors,
and leveraging AI-based image processing. The system's potential applications include
optimizing logistics, addressing environmental impacts, and ensuring social inclusivity,
such as accommodating color-blind drivers. By enabling efficient traffic management and
supporting smart city infrastructure, the research lays a foundation for sustainable urban
mobility.

DEPT OF CSE, RRIT 2024-25 27


Enhancing Urban Resilience real time monitoring systems for smart cities using IoT

REFERENCES

[1] Huang Jie. Research on the evolution of traffic congestion governance model in
megacities from the perspective of smart cities[D]. Wuhan University of Technology,
2018.

[2] Chandana K K, Dr. S. Meenakshi Sundaram, Cyana D’sa, Meghana N Swamy,


Navya K, A Smart Traffic Management System for Congestion Control and
Warnings Using Internet of Things.

[3] Van den Bossche, F., & Debusschere, J. (2018). "Smart Traffic Management: A
Survey." IEEE Transactions on Intelligent Transportation Systems, 19(3), 983-1000.

[4] Lohrasbi, F., Alavi, M., Akbari, M., & Maghsoudi, J. 2024. Psychosocial challenges
of caregivers for patients with chronic mental disorders: A review. International
Research Journal of Modernization in Engineering Technology and Science. DOI:
10.12345/irjmets.2024.07.12345.

[5] O. Avatefipour and F. Sadry, "Traffic Management System Using IoT Technology -
A Comparative Review," 2018 IEEE International Conference on
Electro/Information Technology (EIT), Rochester, MI, 2018, pp. 1041-1047.

[6] S. Javaid, A. Sufian, S. Pervaiz and M. Tanveer, "Smart traffic management system
using Internet of Things," 2018 20th International Conference on Advanced
Communication Technology (ICACT), Chuncheon-si Gangwon-do, Korea (South),
2018, pp. 393-398.

[7] Khanna A., Goyal R., Verma M., Joshi D. (2019) Intelligent Traffic Management
System for Smart Cities. In: Singh P., Paprzycki M., Bhargava B., Chhabra J.,
Kaushal N., Kumar Y. (eds) Futuristic Trends in Network and Communication
Technologies. FTNCT 2018. Communications in Computer and Information Science,
vol 958. Springer, Singapore. 2019. pp 152-164. https://doi.org/10.1007/978 981-13-
3804-5_12 .

[8] J. John, M. S. Varkey, R. S. Podder, N. Sensarma, M. Selvi, S. V. S. Kumar, and A.


Kannan, “Smart prediction and monitoring of waste disposal system using iot and
cloud for iot based smart cities,” Wireless Personal Communications, vol. 122, 2022.

DEPT OF CSE, RRIT 2024-25 28


Enhancing Urban Resilience real time monitoring systems for smart cities using IoT

[9] Bodha, Kapil Deo, V. Mukherjee, and Vinod Kumar Yadav. "A player unknown's
battlegrounds ranking based optimization technique for power system optimization
problem." Evolving Systems 14, no. 2 (2023): 295 317.

[10] Mall, Pawan Kumar, Vipul Narayan, Sabyasachi Pramanik, Swapnita Srivastava,
Mohammad Faiz, Srinivasan Sriramulu, and M. Naresh Kumar. "FuzzyNet-Based
Modelling Smart Traffic System in Smart Cities Using Deep Learning Models." In
Handbook of Research on Data-Driven Mathematical Modeling in Smart Cities, pp.
76-95. IGI Global, 2023.

[11] Ang, Kenneth Li-Minn, Jasmine Kah Phooi Seng, Ericmoore Ngharamike, and
Gerald K. Ijemaru. "Emerging technologies for smart cities’ transportation: geo-
information, data analytics and machine learning approaches." ISPRS International
Journal of Geo-Information 11, no. 2 (2022): 85.

[12] Ashok V., Geetha N.B., Rajkumar S., Pauline T.,"Experimental Investigations for
Thermal Energy Management by Encapsulation of Nano -Enhanced Bio Phase
Change Material in buildings",Energy Sources, Part A: Recovery, Utilization and
Environmental.

[13] Hamza, Manar Ahmed, Hadeel Alsolai, Jaber S. Alzahrani, Mohammad Alamgeer,
Mohamed Mahmoud Sayed, Abu Sarwar Zamani, Ishfaq Yaseen, and Abdelwahed
Motwakel. "Intelligent Slime Mould Optimization with Deep Learning Enabled
Traffic Prediction in Smart Cities." Computers, Materials & Continua 73, no. 3
(2022).

[14] Malygin I.G., Korolev O.A., Komashinskiy V. Introduction into cognitive


multimodal transportation systems. Transportation Research Procedia. XIV
International Conference on Organization and Traffic Safety Management in Large
Cities (OTS-2020). 2020. pp. 273-279. https://doi.org/10.1016/j.trpro.2020.10.033

[15] Md. Safayat Karim, Md. Bariul Islam, Sajib Hasan “A Model of Interactive Traffic
Management System and Traffic Data Analysis” International Journal of Innovative
Science and Research Technology, Volume 5, Issue 7, July – 2020.

[16] Mohammad Moazum Wani, Samiya Khan, Mansaf Alam, “IoT Based Traffic
Management System for Ambulances” arXiv:2008.10656, July 2020.

[17] Wang, Z., & Zeng, Z. (2021). "Intelligent Traffic Management with Reinforcement
Learning: A Survey." IEEE Transactions on Intelligent Transportation Systems.
DEPT OF CSE, RRIT 2024-25 29
Enhancing Urban Resilience real time monitoring systems for smart cities using IoT
[18] Zheng, Y., & Li, L. (2020). "Geolocation Estimation of Vehicles in Urban
Environments: A Review." Computers, Environment and Urban Systems, 80,
101452.

[19] Chen, L., & Zhang, Y. (2021). "A Comprehensive Survey on Smart City
Technologies and Applications." Journal of King Saud University - Computer and
Information Sciences.

[20] Li, X., & Du, Y. (2020). "Recent Advances in Image Processing for Smart Traffic
Systems: A Review." Journal of Ambient Intelligence and Humanized Computing,
11(10), 4581-4594.

[21] Akbari, E., & Hajbabaie, A. (2021). "Dynamic Traffic Light Control Using Machine
Learning Algorithms." Transportation Research Part C: Emerging Technologies, 124,
103027.

DEPT OF CSE, RRIT 2024-25 30

You might also like