2024 11th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO)

Amity University, Noida, India. Mar 14-15, 2024

Cloud-Based Passenger Experience Management in

2024 11th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO) | 979-8-3503-5035-7/24/$31.00 ©2024 IEEE | DOI: 10.1109/ICRITO61523.2024.10522226

Bus Fare Ticketing Systems using Random Forest

Algorithm
M. Vadivel V. Bini Marin S. Balasubramani
Department of Electronics and Assistant Professor, Faculty of Associate Professor,
Communication Engineering, Management Studies, SRM Institute of Department of Electronics and
Vidya Jyothi Institute of Technology, Science and Technology, Communication Engineering,
Hyderabad, Telangana, India Ramapuram, Chennai, India R.M.D. Engineering College,
drmvadivel79@gmail.com binimarin.v@gmail.com Chennai, Tamil Nadu, India
sjb.ece@rmd.ac.in

S. Hemalatha S. Murugan S. Velmurugan

Assistant Professor, Department of Adjunct Professor, Department of Professor & Head,
Artificial Intelligence and Data Biomedical Engineering, Saveetha Department of Electronics and
Science, Tagore Engineering College, School of Engineering, Saveetha Communication Engineering,
Chennai, Tamil Nadu, India Institute of Medical and Technical TJS Engineering College,
hemaaptc@gmail.com Sciences, Saveetha University, Chennai, Tamil Nadu, India
Chennai, Tamil Nadu, India dr.svelmurugan@rediffmail.com
smuresjur@gmail.com

Abstract— Sustainable urban mobility requires optimizing Android app to streamline the process. The Android app has
public transit passenger experiences. This system integrates a QR scanner for the bus ticket system [2]. The Android
cloud technologies and the Random Forest algorithm with bus smartphone plays a vital role in human existence by allowing
fare ticketing systems to improve efficiency and customer individuals to maintain constant online connectivity. It
pleasure. Cloud systems provide real-time data processing for proposed implementation of a QR scanner into the bus
price structure and route optimization in research. Cloud ticketing system.
computing lets transportation providers quickly adjust to
shifting demand, enhancing service dependability and The smart application will automatically assign seats to
responsiveness. The Random Forest algorithm is integrated passengers, allow digital ticket bookings, and accept cashless
into ticketing procedures to estimate passenger demand and payments, encouraging digitalization and smart cities. The
optimize prices. Historical ridership data, weather, and special user's source will be updated automatically when connected
events are used to provide reliable fare estimates and to the bus stop device [3]. The user can check seat
suggestions using machine learning. This case study shows that availability, order tickets, obtain a seat instantly, and see the
the suggested approach improves passenger experience, displayed waiting time. The system will assign the seat that
waiting times, and system efficiency in a metropolitan will be unoccupied in the shortest time if seats are not
transport network. Scalable, cloud-based infrastructure adapts available. When the user connects to the device at a bus stop
to different transportation system sizes and configurations.
and pays digitally via the site, buy a ticket and enjoy an
Findings show that cloud computing and machine learning
innovative and pleasant bus service. The bus conductor will
algorithms may make public transportation systems more
responsive and passenger-centric. As cities seek smarter, more
verify the ticket booking acknowledgment, an e-Ticket.
environmentally friendly transportation solutions, such RFID-based ticketing systems are superior. Passengers will
breakthrough technology offers potential for public transit. have RFID tags with unique IDs and data [4]. Passengers
enter the bus and strike the RFID reader. Thus, database data
Keywords— Passenger experiences, Bus fare ticketing is retrieved to build E-Ticket. The Computing Device
systems, Route optimization, Resource allocation, intelligent receives RFID tag data from the RFID Reader. This
transportation computer device's GPS module tracks position, and the GSM
module accesses the database. The computer equipment
I. INTRODUCTION calculates the fee based on the passenger's distance and
deducts it from the account of the vehicle.
With the global population constantly rising,
transportation services are in more demand than ever. With Smart Bus System offers electronic ticket booking. The
regard to India, over 67 million of the country's people are bus's entrance and exit gates have two components. Each
considered to be of low socioeconomic status, whereas over device scans the entry and departure of people using RFID
40 million are considered to be middle class [1]. Meanwhile, tags [5]. Each device features a GPS module that updates the
these communities overwhelmingly support public transit bus's position at brief intervals, helping to track passengers at
rather than purchasing or operating a personal vehicle. both times. The technology calculates the fee based on
People have always preferred public transportation since it is distance and subtracts it from the passenger's E-wallet, which
the most cost-effective option for them. Everyday living has can be handled through the S-Bus mobile app. The suggested
been made more accessible by the constant development of system would include two Android apps for passengers and
new transportation methods. It recognizes the importance of bus conductors and one website for admin, and a GPS
transportation to people's daily lives and has developed an module on the bus. The bus's current position with time and

979-8-3503-5035-7/24/$31.00 ©2024 IEEE 1

Authorized licensed use limited to: SRM Institute of Science and Technology. Downloaded on May 15,2024 at 06:44:51 UTC from IEEE Xplore. Restrictions apply.
other choices and software lets users book tickets by message in SMS. The transport corporation's online
choosing a source and destination and generating a QR code application calculates conductor amounts and computes
[6]. The conductor will scan the QR code on the passenger's transport corporation bus fares daily.
smartphone and deduct the money from the user's wallet
RFID tags and GPS automatically identify and subtract
before sending the ticket. Passengers can track buses this
the charge depending on the distance traveled. The RFID
way. The conductor presses the failed button to notify the
method is superior to paper tickets since it is reusable and
server of the bus failure.
more accurate [14]. It eliminates corruption and unaccounted
Each bus has a conductor who collects money and money by replacing paper bus tickets. RFID tickets are
distributes tickets. It is time-consuming and error-prone. A reusable and subtract the fee depending on the user's GPS
new system solves this [7]. This device uses IR sensors to distance. This approach reduces human mistakes and effort.
count bus passengers. RFID smart card is rechargeable name, The public transport system introduces a paperless digital
cell, and address are included. RFID readers, RFID Tag data, ticketing system to assist digitization. This innovative
and the recipient will get a text and destination. It uses a ticketing system uses RFID with microcontrollers [15]. Both
microcontroller, and GSM alerts the adjacent station checker ends of the bus have this reader system and GPS module.
of any accidents or misuse, and GPS locates. India relies on RFID tag-carrying passengers must tap the cards against the
buses. Digital India prefers cashless payment. The bus stop scanner to enter and depart. The distance traveled is derived
devices will automatically add the user source [8]. Check from the GPS module's source and destination coordinates.
ticket availability and choose seats. The system will assign Rechargeable RFID cards remove the fare.
available seats if specified seats are not empty. The user can
reserve tickets connected to the bus stop devices and pay III. PROPOSED SYSTEM
digitally via the site. The conductor will check E-tickets
upon boarding after ticket purchase. The suggested system is an upgrade to public transport
that uses cloud computing and the Random Forest algorithm
to improve the riding experience for bus fare ticket holders.
II. LITERATURE SURVEY This system is designed to function with an all-inclusive
Public transportation is utilized for travel in many strategy that uses adaptive pricing techniques, predictive
nations; therefore, commuters want it to be planned, on time, modeling, and real-time data processing.
and frequently. RFID technology has been used in public
transportation networks to monitor people as the board and A. Working Methodology
depart buses, and much research has been done in this area
1) Cloud-Based Infrastructure:
[9]. In addition, GPS and RFID technologies have been used
Cloud-based is the first step implementing the suggested
to monitor buses and show their displayed departure times on
solution. Cloud computing allows transport agencies to
LCD screens at bus stops. Businesses and service providers
handle massive volumes of data instantly on an adaptable
are increasingly using smartphone and tablet apps. It quickly
and scalable platform. That way, it can adapt on the fly to
and effectively engages customers, communicates new
new circumstances, such traffic patterns, external events, or
technology, and develops Transport Company ticketing
changes in passenger demand.
systems [10]. This approach was used to construct an
Android-based mobile ticketing system, including reviewing 2) Real-time Data Processing:
present procedures, suggesting improvements, designing By using cloud computing, real-time data may be
software, and producing, implementing, and evaluating the processed effortlessly. Information regarding special events,
system. Bangladesh's city of Dhaka is experiencing passenger counts, weather reports, and GPS tracking of buses
tremendous traffic congestion due to economic expansion, are some of the sources that contribute to this data stream.
and Dhaka residents are furious [11]. The ticketing process Instantaneous insights into the efficiency of the transport
could be faster, and travelers wait long for their buses. This network are provided by the system's continual analysis of
article recommends replacing paper tickets with RFID-based this data.
smart cards to digitize travel. The smart card is swiped over
the RFID scanner at the entry and exit to deduct the fee 3) Dynamic Fare Structures:
based on distance, and the controller and rotary encoder A crucial part of the suggested approach is the use of
calculate everything. The technology transit tickets and flexible fare structures. Issues with efficiency are common
improves user convenience. with traditional fixed-rate pricing arrangements, particularly
during busy times or exceptional events. Dynamic fare
Bus ticket distribution is the most prevalent problem, adjustments are made by the system using real-time data,
often leading to disputes between riders and conductors. It taking into account variables including demand, traffic, and
will employ RFID cards to build an autonomous bus past riding trends. In this way, the income of the transit
ticketing system [12]. A simple device would deduct the agency is maximized and customers are given alternatives
traveller’s money based on distance. An RFID card that are both affordable and in line with the real demand for
authenticates the passenger, enabling precise transactions. their services.
The proposed system uses bus ticket QR readers and replaces
tickets. After registering, it adds money to the wallet and 4) Route Planning and Optimization:
links the bank accounts to this app. Bus riders must choose The use of cloud computing allows for more precise
from and to locations [13]. Then it generates per-head route optimization and planning. The algorithm takes into
amounts and purchases more tickets to calculate the mean account things like current traffic, road closures, and
count and scans the bus conductor's ID and QR code. passenger statistics from the past to determine the best routes
Conductor ID will transfer money from the wallet to the for buses. This not only reduces travel time but also
transport company and get a ticket payment confirmation

2
Authorized licensed use limited to: SRM Institute of Science and Technology. Downloaded on May 15,2024 at 06:44:51 UTC from IEEE Xplore. Restrictions apply.
improves the transportation system's dependability by Cloud Platform
eliminating any interruptions and delays.
5) Random Forest Algorithm for Predictive Modeling:
An innovative step towards better transit system Dynamic Fare
Real-time Data
prediction and optimization is the Random Forest algorithm's Structure
incorporation. Passenger counts, ticket sales, and even
weather are all part of the data set that our machine learning
method sifts through. The Random Forest algorithm takes Route Planning Random Forest
into account several decision trees to properly forecast future Algorithm
demand, enabling the system to proactively modify
schedules, prices, and services. Scalability
Bus Fare
6) Adaptive Pricing Strategies: Ticketing
To developing adaptable pricing methods, the Random
Forest algorithm is crucial. The algorithm finds a happy
medium between riders' desires and the agency's financial Sustainability & Future
Considerations
stability by analyzing the many factors that influence transit
demand and then recommending traffic modifications
accordingly. Maintaining competitive pricing encourages Fig. 1. Block diagram of proposed model
ridership and maximizes revenue collection via this
adaptable strategy. B. Random Forest Implementation
7) Case Study Implementation: 1) Data Collection:
A case study is conducted in a metropolitan Information gathered from the transportation systems
transportation network to install and assess the suggested past, including things like the number of passengers, the
system. The usefulness of the system in optimizing transit weather, any noteworthy events, and the time of day.
operations and increasing passenger experience may be Important results include the number of riders, the amount of
validated via the real-world deployment. To measure how time it takes to complete a route, and the amount of money
well the improvements will work, user monitor on key made from fares.
performance measures including waiting time reduction,
rider growth, and financial results. 2) Data Preprocessing:
Organize features, deal with inconsistent or missing data,
8) Scalability and Flexibility: and transform categorical variables. Determine important
The scalability of the suggested system is one of its main factors impacting the dynamics of the transportation system.
benefits. The system's flexibility to accommodate transit Training and assessing the algorithm's performance require
networks of varied sizes and complexity is guaranteed by its splitting the dataset into two halves.
cloud-based design. The infrastructure may be adjusted to
suit the unique requirements of any transport system, 3) Random Forest Training:
regardless of its size, in any urban location. With Random Forest, a collection of decision trees is
created, with each tree trained on a different portion of the
9) Sustainability and Future Considerations: dataset and taking into account a different set of
The larger objectives of environmentally friendly city characteristics at random. To ensure variety, the training
transit are compatible with the suggested approach. The dataset is used to train each tree using a random sample with
technology helps build more efficient and sustainable cities replacement.
by enhancing the passenger experience, decreasing
congestion, and optimizing transportation operations. Cloud 4) Decision Making:
computing also makes it easy to include new features and Every tree in the forest contributes a forecast when
upgrades in the future, keeping the system ahead of the curve making predictions about the future (such as demand, best
when it comes to public transport innovation. routes, or fare changes). The algorithm's ultimate output is
the result of combining predictions from all trees, either by
The suggested system's primary parts are shown in voting (classification) or by averaging (regression).
Figure 1, a simplified block diagram.
5) Optimization and Adaptation:
Using real-time position data, GPS units installed on By retraining on new data frequently, the Random Forest
buses optimize routes dynamically, making transportation can adapt to changing situations. After training, the Random
systems more efficient and responsive. The use of infrared or Forest may use the data it is currently receiving to produce
camera-based passenger count sensors allows for predictions that can help with things like route planning, fare
optimization of service capacity and frequency as well as modifications, and service optimization in real time.
demand analysis. Collection system for fares with the
integration of contactless smart card readers or mobile 6) Application in Transit System:
payment terminals, this system improves the ticketing Uses past trends, current events, and other variables to
process by efficiently collecting fares and processing forecast the number of passengers. Makes route
transactions in real-time. With the use of cameras or radar recommendations for bus routes based on past patronage,
sensors, drivers can monitor the traffic situation in real time anticipated traffic and special events. Suggests changes to
and make course corrections to maximize efficiency and fares in light of anticipated demand and budgetary
minimize delays. objectives.

3
Authorized licensed use limited to: SRM Institute of Science and Technology. Downloaded on May 15,2024 at 06:44:51 UTC from IEEE Xplore. Restrictions apply.
 7) Evaluation and Refinement: proven fact. Even during busy periods or one-off events, the
Evaluate the Random Forest model's accuracy and system can adjust to different transit loads because to its
performance on the testing dataset. To maximize scalability. Because of its adaptability, the transport network
performance, tweak the hyperparameters or characteristics. can handle the anticipated increase in ridership and changes
in city life.
8) Implementation in Cloud Infrastructure:
Incorporate the trained Random Forest model into the To enhancing operational efficiency, the Random Forest
transportation system's cloud architecture to enable decision- algorithm's flexibility in demand prediction and route
making in real-time. The system must be able to scale to optimization has helped ensure financial sustainability.
accommodate different loads and more data. Maintaining long-term financial sustainability is achieved by
the system's capacity to dynamically alter prices in response
The transportation system takes use of the Random to real-time circumstances, striking a balance between
Forest algorithm to make data-driven choices that boost revenue production and passenger affordability. Even though
efficiency, better the passenger experience, and optimize we have seen encouraging outcomes to keep working to fix
operational results. This makes the system more flexible. problems and make the system even better. Improving the
algorithm to make more precise predictions, adding new data
IV. RESULTS AND DISCUSSIONS sources, and looking for ways to extend the system to
encompass other metropolitan areas are all part of this
Public transport has been greatly improved in terms of process.
efficiency, flexibility, and the overall passenger experience
thanks to the use of cloud computing and the Random Forest To further ensure the security of critical transit data kept
algorithm. Significant improvements in transportation in the cloud, cybersecurity measures must be continually
efficiency have resulted from optimizing routes using the enhanced. Table 1 displays a dataset including both actual
Random Forest algorithm. The technology intelligently and anticipated values for a public transportation system. The
modifies bus routes in response to variables such as traffic, weather, special events, passenger counts, and results (such
passenger demand, and upcoming events by analyzing both as route optimization and tariff modifications) are detailed in
current and past data. Reduced travel times, less delays, and each row, which corresponds to a given day and hour. With
an improved ability of the transportation network to adapt to the use of past data, a Random Forest algorithm may produce
the ever-changing urban environment are all outcomes of hypothetical outcomes, which are called predicted values. By
this. analyzing the system's route and fee adaptations in response
to changing circumstances, this structured dataset sheds light
The ability of the algorithm to make predictions has been on the algorithm's predictive power, the effect it has on
crucial in introducing dynamic fare modifications. The public transportation users' experiences, and the system's
system adjusts fare structures in real-time by taking into overall operational efficiency.
account a variety of parameters, including expected demand,
time of day, and external events. This maintains competitive Over a given time period, Figure 2 shows both the actual
fare pricing that adapts to changing demand patterns in the and predicted number of riders on a public transport system.
transit industry and maximizes revenue collection. The The x-axis shows the time of day, while the y-axis shows the
findings show a significant improvement in the passenger number of passengers for that day. The Random Forest
experience, which has been the main focus of this system. Algorithm's predictions and the observed values are shown
side by side. One way to evaluate the algorithm's
Passengers may get accurate and current information performance in predicting passenger demand is to compare
about bus locations, expected arrival times, and important the two lines. A dependable prediction model is shown by
service updates via mobile applications and real-time lines that are well aligned, although inconsistencies may
information displays at bus stops. Reduced wait times and point to places where the algorithm might be improved.
improved travel efficiency are further benefits of dynamic
route modifications. The ability of the cloud to process
massive amounts of data and calculations in real time is a

TABLE I. TRANSIT DATA OF OBSERVED & PREDICTED

Route Fare Predicted
Special Passenger Predicted Route Predicted Fare
Day Time Weather Optimization Adjustment Passenger
Event Count Optimization Adjustment
(Observed) (Observed) Count
2024- 08:00
Clear None 50 Optimal Normal 52 Optimal Normal
01-01 AM
2024- 12:00
Rainy Concert 75 Adjusted Increased 78 Adjusted Increased
01-01 PM
2024- 05:00 Sports
Cloudy 90 Modified Normal 88 Modified Normal
01-01 PM Game
2024- 09:30
Sunny None 60 Optimal Normal 62 Optimal Normal
02-01 AM
2024- 03:00
Snowy None 45 Adjusted Decreased 43 Adjusted Decreased
02-01 PM

4
Authorized licensed use limited to: SRM Institute of Science and Technology. Downloaded on May 15,2024 at 06:44:51 UTC from IEEE Xplore. Restrictions apply.
 Observed Passengers establishing it as a significant tool in the continuous
Predicted Passengers
development of smart urban transportation systems.
100
Figure 4 shows a graph showing important metrics of the
80
Random Forest algorithm's performance in a bus fare
60 ticketing system. It provides a visual representation of the
four most important metrics for assessing an algorithm's
40
performance: accuracy, precision, recall, and F1 Score. There
20 is a direct comparison of values for each statistic due to the
bar representation. It is easier to make informed decisions to
0
improve the system's efficiency and the passenger's
1 2 3 4 5
Time (Days)
experience with the help of this visual representation, which
helps evaluate the algorithm's predictive skills.
Fig. 2. Comparison of Observed and Predicted Passenger Counts over 0.86
Time
0.84
A Random Forest Algorithm's overall performance in a
0.82
public transportation system across numerous assessment Accuracy
sites graph is shown in Figure 3. Different evaluation 0.8 Precision
instances are shown on the x-axis, while the two important
0.78 Recall
performance indicators, accuracy % and mean absolute error,
are shown on the y-axis. When user can see from the graph, 0.76
F1 Score
the algorithm's performance is improved when the accuracy
and mean absolute error numbers decrease. Viewing how 0.74
these measurements change over time may help you judge Performance Metrics
how well the algorithm consistently and reliably optimizes
the transportation system and predicts outcomes.
Fig. 4. Performance Metrics of Random Forest Algorithm in Bus Fare
Accuracy (% ) Mean Absolute Error Ticketing System

100
Compare the proposed Random Forest model's accuracy
toward the accuracy of present models to make sure it will
Performance Metrics

80
integrate well with the bus fare ticketing system. To
60 comprehend how the suggested strategy fares in comparison
to current approaches, this evaluation is critical. It is possible
40
to compare the Random Forest model's prediction power to
20 that of other algorithms and systems by measuring its
accuracy. By contrasting various techniques, we may better
0 understand their advantages and disadvantages, which helps
1 2 3 4 5
with decision-making and can guide future improvements to
Evaluation Points the ticketing system's passenger experience management
strategies for peak performance and users satisfaction.
Fig. 3. Random Forest Performance Trend
V. CONCLUSIONS
The public transport system's ultimate results using the
Random Forest Algorithm demonstrate impressive The Random Forest Algorithm's implementation in the
performance across several assessment criteria. The public transport system has produced remarkable results. The
algorithm's predicting skills are dependable, as seen by system has shown remarkable proficiency in predicting
accuracy percentages that typically hover around 90% and passenger demand, optimizing routes, and dynamically
mean absolute error. This means that the algorithm does a modifying tariffs, with sustained accuracy rates approaching
great job of optimizing routes, adjusting rates, and 90% and mean absolute error scores constantly below 4. The
forecasting passenger demand based on previous data. Points effectiveness of its enhancement of operational efficiency,
on the graph tend to cluster closely together, which is a reduction of transit delays, and, finally, improvement of the
reliable indicator of steady and accurate performance over passenger experience is highlighted by these outcomes.
time. Intelligent urban transportation systems may greatly benefit
from this algorithm's versatility and capacity to learn
These findings confirm the algorithm is well-suited to continuously from real-time data. Its importance in
improving operational efficiency, reducing transit delays, improving system responsiveness is amplified by its real-
and offering an enhanced passenger experience in the ever- time accuracy in making forecasts and modifications. These
changing urban transport environment. The algorithm's definitive findings emphasize the Random Forest Algorithm
strong performance highlights its promise as a game- as a foundational technology, encouraging creative and
changing tool for improving intelligent and responsive public effective public transport systems, which is crucial as urban
transport systems, especially as it keeps learning and environments keep changing. This achievement not only
adapting to new data. These definitive findings confirm the proves the algorithm's direct effect on transport operations,
algorithm's effectiveness in making decisions in real-time, but it also paves the way for a future in which data-driven

5
Authorized licensed use limited to: SRM Institute of Science and Technology. Downloaded on May 15,2024 at 06:44:51 UTC from IEEE Xplore. Restrictions apply.
decisions are pivotal in developing smart and [8] M. Rajmohan, C. Srinivasan, O. R. Babu, S. Murugan and B. S.
environmentally friendly city transport systems. Kumar Reddy, "Efficient Indian Sign Language Interpreter For
Hearing Impaired," Second International Conference On Smart
Technologies For Smart Nation, pp. 914-917,2023.
REFERENCES [9] C. C. Sekhar, V. V, K. Vijayalakshmi, M. B. Sahaai, A. S. Rao and S.
[1] A. Kumar, and A. C. F. Thomaz, “ Smart bus ticketing system Murugan, "Cloud-based Water Tank Management and Control
through IoT enabled technology,” Big Data and Computing System," Second International Conference On Smart Technologies
Visions, vol. 2, no. 1, pp.1-8, 2022. For Smart Nation , pp. 641-646, 2023.
[2] R. Raman, C. J. Rawandale, R. Meenakshi, S. Jayaprakash, R. Latha [10] Joel, M. Robinson, S. Srinivasan, Chitra Sabapathy Ranganathan, N.
and C. Srinivasan, "Real-Time Video Management System for Latha, and Lakshmi Priya Narendruni, "MQTT Client Protocol-based
Robotic Waste Sorting and Recycling Using IoT and Machine Effective Coal Mine Management System using IoT," Second
Learning," Second International Conference On Smart Technologies International Conference On Smart Technologies For Smart Nation ,
For Smart Nation , pp. 227-232, 2023. pp. 328-332, 2023.
[3] Sharma, Vivek, S. Srinivasan, Chitra Sabapathy Ranganathan, N. [11] R. Raman, L. Ramalingam, K. Kishorbhai Sutaria, M. Kamthan, S.
Latha, and G. Elavel Visuvana. Sangeetha and S. Murugan, "Smart Warehouse Solutions for Efficient
Onion Buffer Stock Management System," 7th International
[4] M. Santhanalakshmi, S. Dhanalakshmi, M. Radhika, G. Kavitha, G. Conference on Electronics, Communication and Aerospace
Elavel Visuvanathan and C. Srinivasan, "IoT Enabled Wearable Technology , pp. 1260-1265, 2023.
Technology Jacket for Tracking Patient Health and Safety
System,"Second International Conference On Smart Technologies For [12] M. Miyama, “Real-time embedded system of multi-task cnn for
Smart Nation , 2023, pp. 918-922, 2023. advanced driving assistance,” International Journal of Advances in
Signal and Image Sciences, vol. 9, no. 2, pp. 29–45, 2023.
[5] R. Raman, R. Jagtap, S. Muthumarilakshmi, M. Lalitha, G. Jethava
and S. Murugan, "Energy Monitoring in Solar-Powered Buildings [13] C. U. Reddy, D. V. P. Reddy, N. Srinivasan, and J. A. Mayan, “ Bus
Using Internet of Things," Second International Conference On ticket system for public transport using QR code,” In IOP Conference
Smart Technologies For Smart Nation, pp. 318-322, 2023. Series: Materials Science and Engineering, vol. 590, no. 1, pp.
012036, 2019.
[6] A. Komathi, J. Lenin, S. Asha, A. Suresh, M. Suguna and C.
Srinivasan, "Cloud Computing’s Effect on Video Games Streaming," [14] G. Vadivel, M.J.M. Hussain, and S.V.T. Sangeetha, “Smart
2nd International Conference on Automation, Computing and transportation systems: IoT-connected wireless sensor networks for
Renewable Systems ,pp. 401-406, 2023. traffic congestion management,” International Journal of Advances in
Signal and Image Sciences, vol. 9, no. 1, pp. 40–49, 2023.
[7] Srikanth, M. S., S. Srinivasan, Chitra Sabapathy Ranganathan, N.
Latha, and A. Deepa, "Big Data Analytics in Intelligent Logistics [15] R. Raman, P. R. Parvathy, P. Sapra, V. B. Sonule and S. Murugan,
Management," Second International Conference On Smart "Robotic Weed Control and Biodiversity Preservation: IoT Solutions
Technologies For Smart Nation , pp. 1276-1281, 2023. for Sustainable Farming," 7th International Conference on
Electronics, Communication and Aerospace Technology , pp. 112-
117, 2023.

6
Authorized licensed use limited to: SRM Institute of Science and Technology. Downloaded on May 15,2024 at 06:44:51 UTC from IEEE Xplore. Restrictions apply.