BANGALORE INSTITUTE OF TECHNOLOGY

(Affiliated to Visvesvaraya Technological University, Belagavi, Accredited by NBA & NAAC)

K R Road, V V Pura, Bengaluru – 560 004
Department of Electronics and Instrumentation Engineering
Internship Presentation
on

ANALYZING THE COVID-19 PANDEMIC USING MACHINE LEARNING

TECHNIQUES
Internship Carried out
at
Prinston Smart
Engineers
Presented by
1BI21EI027 R VISHWAJIT

Internship Guide Internship Coordinator Head of the

Prof. Dr. Sudha L K Anjan Kumar B S Department
Assistant Professor,
Associate Professor,
Department of EIE, BIT. Department of EIE, BIT.
Dr. Aswathappa P
Associate Professor and HoD
Department of Electronics & Instrumentation Engineering, Department of EIE, BIT.
 TABLE OF CONTENTS
Sl. No Particular Slide No
1 Certificate of Completion 3
2 About the Institute & Department 4
3 Department Vision & Mission 5
4 Acknowledgement 6
5 Abstract 7
6 Company Profile 8-10
7 Weekly Timeline 11-15
8 Project Title And Detail 16
9 Block Diagram 17
10 Flowchart 18
11 Methodology 19-20
12 Result 21-22
13 Visual Representation 23
14 Future Scope 24
15 Reflections and Outcomes 25
16 Conclusion 26
17 References 27-28

Department of Electronics & Instrumentation Engineering, BIT 05/27/2025 2

 CERTIFICATE

Not received yet

Department of Electronics & Instrumentation Engineering, BIT 05/27/2025 3

 ABOUT THE INSTITUTE & DEPARTMENT

Bangalore Institute of Technology (BIT), established in 1979 and affiliated with

Visvesvaraya Technological University (VTU), is a premier institution known for academic
excellence, innovation, and a strong culture of experiential learning. The Department of
Electronics and Instrumentation Engineering (EIE), founded in 1982, is accredited by
the NBA and NAAC with an A++ grade, and houses a state-of-the-art R&D center
established in 2012. The department has produced 82 academic ranks - 63 under VTU
(including 10 gold medals) and 25 under Bangalore University, along with 2 UPSC
ranks, reflecting the high quality of education imparted. With 14 Ph.D. scholars, strong
industry collaborations, and an excellent placement record, EIE continues to nurture skilled,
responsible, and future-ready engineers who thrive in both industry and academia.

Department of Electronics & Instrumentation Engineering, BIT 05/27/2025 4

 DEPARTMENT VISION & MISSION

Vision
Graduates of Electronics and Instrumentation Engineering will have clarity of purpose and the
solid decision-making abilities to be confident, selective and competitive in managing their
careers and further Academic pursuits and to extend their hands for social service.

Mission
• To evolve continually as a Centre of Excellence in offering quality in Electronics and
Instrumentation Engineering education.
• To nurture the students to meet the Global Competency in Industry and Academia.
• To provide Reliable, Modern and Integrated Technology to support and facilitate Teaching,
Learning, Research and Service.
• To promote collaboration with industry and Institute for constructive interaction for better
Integration of Theory and Real-Time Applications.

Department of Electronics & Instrumentation Engineering, BIT 05/27/2025 5

 ACKNOWLEDGEMENT
I would like to extend my heartfelt thanks to Ms. Farheen, my mentor at Prinston Smart
Engineers, for her consistent support and invaluable guidance throughout this project.
My sincere thanks to Dr. Sudha L K , Internship Guide, Associate Professor, Department of
Electronics and Instrumentation Engineering, BIT, for her invaluable assistance.
I am also thankful to Prof. Anjan Kumar B. S., Internships Coordinator and Assistant
Professor, Department of Electronics and Instrumentation Engineering, BIT, for his constant
encouragement.
A special thank you goes to Dr. Aswathappa P., and Head of the Department of Electronics
and Instrumentation Engineering, BIT, for his invaluable assistance and mentorship.
I am equally grateful to Dr. J. Prakash, Vice-Principal, BIT, and Dr. M. U. Aswath, Principal,
BIT, for their ongoing support.
Finally, I would like to extend my heartfelt thanks to my parents, the teaching and non-teaching
staff of the Department of Electronics and Instrumentation Engineering, BIT, and everyone who
played a role
Department in the success
of Electronics of this
& Instrumentation project.
Engineering, BIT 05/27/2025 6
 ABSTRACT
This project focuses on analyzing the COVID-19 pandemic using machine learning
techniques to identify patterns, classify outbreak severity, and predict trends. The
dataset includes global records of confirmed cases, recoveries, active cases, and
deaths, along with country-wise impact data.
Machine learning models are applied to perform classification and trend analysis,
helping to understand the spread and impact of the virus. Visualization and data
preprocessing techniques are used to enhance insight extraction and model accuracy.
The study highlights how data-driven approaches and machine learning can support
effective pandemic monitoring and response, aiding in timely decision-making and
future preparedness.

Department of Electronics & Instrumentation Engineering, BIT 05/27/2025 7

 COMPANY PROFILE
Prinston Smart Engineers
Founded: 2004
Headquarters: Bengaluru, India
Industry: Maintenance and Training Services Fig 1- Company Logo

Enterprise Type: Service-Based Company

Products & Services: Electrical Design and Infrastructure
Design, Full Stack Web Development, Cybersecurity Solutions
and Machine Learning Applications
Notable Clients: Cisco, ThingQbator, Hexaware, Innova
Foodpark, Biovet, Ella Foods
Website: [Link]

Department of Electronics & Instrumentation Engineering, BIT 05/27/2025 8

 COMPANY PROFILE
Domains Expertise at Prinston Smart Engineers:
1. Electrical Design & Infrastructure: Specialized in the planning and implementation of
electrical systems and infrastructure design for commercial, industrial, and residential
projects, ensuring safety, compliance, and energy efficiency.
2. Web Development & Software Solutions: Expertise in full stack web development,
offering end-to-end solutions including UI/UX design, front-end and back-end development,
and deployment of scalable web applications.
3. Cybersecurity: Providing cybersecurity services such as network security, vulnerability
assessment, and threat mitigation strategies to safeguard digital infrastructure and
sensitive data.
4. Machine Learning & AI: Development and integration of machine learning models for
data-driven applications, including predictive analytics, automation, and intelligent system
design.
5. Engineering Internships & Training: Comprehensive internship and training programs
Department of Electronics & Instrumentation Engineering, BIT 05/27/2025 9
in mechanical and civil engineering domains, offering hands-on project experience and
 COMPANY PROFILE
Services Provided by Prinston Smart Engineers:
1. Electrical and Infrastructure Design: Comprehensive electrical and infrastructure planning
services for commercial, industrial, and residential projects, ensuring compliance with safety
standards and optimized energy use.
2. Web Development Solutions: End-to-end full stack web development services, including
custom website design, application development, and deployment using modern frameworks
and technologies.
3. Cybersecurity Services: Security solutions for digital systems including threat assessment,
penetration testing, and implementation of protective measures to secure networks and
applications.
4. Machine Learning Solutions: Design and deployment of machine learning models for
predictive analysis, automation, and intelligent decision-making across various industry
domains.
5. Internship & Industrial Training Programs: Hands-on internship opportunities and industrial
Department of Electronics & Instrumentation Engineering, BIT 05/27/2025 10
training in Mechanical and Civil Engineering, providing practical experience and skill
 WEEKLY TIMELINE
Week Task
Orientation and introduction to company services and project
Week 1
domains. Familiarization with internal tools, platforms, and
(7 February 2025 –
th

13th February 2025) documentation processes. Basic training in electrical design and
IoT fundamentals.
Assisted in preparing electrical layout diagrams for a client
Week 2
project. Gained hands-on experience with AutoCAD Electrical
(14 February 2025
th

– 20th February 2025) tools. Started basic HTML, CSS tutorials for front-end
development tasks.
Contributed to a full-stack project setup using HTML, CSS, and
Week 3
JavaScript. Reviewed cybersecurity case studies under the
(21 February 2025 –
st

27th February 2025) guidance of a senior engineer. Documented learning in daily logs
and shared weekly update with mentor.
Department of Electronics & Instrumentation Engineering, BIT 05/27/2025 11
 WEEKLY TIMELINE
Week Task
Built a basic static website as part of internal web development
Week 4\
training. Introduction to network security fundamentals and threat
(28 March 2025 –
th

6th March 2025) modeling. Assisted in organizing training content for mechanical
internship batches.

Learned basic backend integration using [Link] and [Link].

Week 5
Drafted an electrical wiring plan for a model commercial layout.
(7 March 2025 –
th

13th March 2025) Started working on a capstone project under the machine learning
team.

Week 6 Explored classification algorithms using Python and Scikit-learn.

(14th March 2025 – Collected training data for ML model on predictive maintenance.
20th March 2025)
Supported internship team with civil domain lab session setup.

Department of Electronics & Instrumentation Engineering, BIT 05/27/2025 12

 WEEKLY TIMELINE
Week Task

Completed model training and evaluation for the ML capstone

Week 7\
(21st March 2025 –
project. Presented a short demo on project idea to the internal
27th March 2025) team. Continued development of front-end dashboard for
internal tool.

Week 8 Security analysis of internal project using basic penetration

(28th March 2025 – tools. Created documentation for internship feedback system.
3rd April 2025)
Developed Python script for data preprocessing in ML workflow.

Week 9 Integrated electrical design content into training portal.

(4th April 2025 – Collaborated with the cybersecurity team on a network
10th April 2025)
simulation. Added authentication module to web dashboard.
Department of Electronics & Instrumentation Engineering, BIT 05/27/2025 13
 WEEKLY TIMELINE
Week Task

Week 10\ Worked on improving the UI for internal tools using Bootstrap.
(11th April 2025 – Assisted in preparing a cybersecurity awareness presentation.
17th April 2025)
Tested ML model performance and logged results.

Week 11 Finalized and documented the ML project. Completed full-stack

(18th April 2025 – web application with basic CRUD operations. Helped review
24th April 2025)
civil/mechanical training reports for accuracy.

Week 12 Participated in review and feedback sessions with mentors.

(25th April 2025 – Deployment of web application to internal server. Preparation for
1st May 2025)
final project presentation.

Department of Electronics & Instrumentation Engineering, BIT 05/27/2025 14

 WEEKLY TIMELINE
Week Task

Week 13\ Delivered project presentation and received feedback. Supported

(2nd May 2025 – live training sessions on Electrical Safety and Design. Made final
8th May 2025)
edits to project documentation.

Week 14 Wrap-up meetings and submission of internship report. Knowledge

(9th May 2025 – transfer and code handover to the development team. Assisted
15th May 2025)
juniors in onboarding for upcoming summer training.

Week 15 Final documentation review and mentor feedback collection.

(16th May 2025 – Completion of exit formalities and internship experience sharing
24th May 2025)
session. Received Internship Completion Certificate.

Department of Electronics & Instrumentation Engineering, BIT 05/27/2025 15

 PROJECT TITLE AND DETAIL
 Company: Prinston Smart Engineers, Bengaluru
 Duration: 15 Weeks
 Project Title: Analyzing the COVID-19 Pandemic Using Machine Learning Techniques
 Objective: To apply machine learning techniques for analyzing the COVID-19 pandemic
by identifying patterns, performing classification tasks, and predicting trends based on
global datasets, thereby supporting data-driven decision-making and public health
insights.
Key Features:
1. Comprehensive analysis of COVID-19 cases, recoveries, deaths, and active cases
worldwide.
2. Country-wise classification and visualization of pandemic impact.
3. Implementation of machine learning models to identify patterns and make trend
predictions.
Department of Electronics & Instrumentation Engineering, BIT 05/27/2025 16
4. Data preprocessing and cleaning to improve model accuracy.
 BLOCK DIAGRAM

Feature Machine
COVID-19 Data Pre-
Extraction Learning
Dataset processing
(Relevant Fields: Models (e.g.
(Cases, Deaths, (Cleaning,
Country, SVM, Decision
etc.) Normalizing)
Date, etc.) Tree, KNN)

Model Evaluation
Results &
& Performance
Visualization
Metrics (Accuracy,
(Graphs, Trends,
Confusion Matrix,
Heatmaps)
etc.)

Department of Electronics & Instrumentation Engineering, BIT 05/27/2025 17

 FLOW CHART
Start

COVID-19 patients data

Data cleaning

Cleaned data
Data
transformation
Transformed data

Applying machine learning

algorithms

Output Classifying COVID-19 cases

into positive or negative

Stop

Department of Electronics & Instrumentation Engineering, BIT 05/27/2025 18

 METHODOLOGY

Data Pre- Exploratory Data Feature

Data Collection
processing Analysis (EDA) Selection

Visualization and Prediction and Model Selection

Model Evaluation
Reporting Analysis and Training

The project follows a systematic approach for analysing the COVID-19 pandemic using various
machine learning techniques. The methodology comprises the following stages:
Step 1 Data Collection: The dataset containing global COVID-19 statistics was collected from
reliable open data sources such as WHO, Kaggle, or government health portals. It includes
features such as the number of confirmed cases, deaths, recoveries, and active cases
categorized by country and date.
Department of Electronics & Instrumentation Engineering, BIT 05/27/2025 19
 METHODOLOGY

Step 2 Data Preprocessing: The collected raw data is preprocessed to ensure consistency
and accuracy. This involves handling missing values, removing duplicates, encoding categorical
variables, and normalizing numerical data. Cleaning and structuring the data is essential for
efficient model training.
Step 3 Data Preprocessing: The collected raw data is preprocessed to ensure consistency and
accuracy. This involves handling missing values, removing duplicates, encoding categorical
variables, and normalizing numerical data. Cleaning and structuring the data is essential for
efficient model training.
Step 4 Feature Selection: Relevant features are selected based on correlation analysis and
domain knowledge. Irrelevant or redundant attributes are removed to improve model performance
and reduce overfitting.
Step 5 Model Selection and Training: Supervised machine learning models such as Support
Vector Machine (SVM), Decision Tree, K-Nearest Neighbors (KNN), and Random Forest are selected
for classification and prediction tasks. The dataset is split into training and testing sets, and
models are trained using the training data.
Department of Electronics & Instrumentation Engineering, BIT 05/27/2025 20
 METHODOLOGY

Step 6 Model Evaluation: The performance of each model is evaluated using metrics such as
accuracy, precision, recall, F1-score, and confusion matrix. Cross-validation is also performed to
ensure robustness and generalizability of the models.
Step 7 Prediction and Analysis: Trained models are used to predict future trends or classify
countries based on case severity. Insights from the analysis are interpreted to understand the
effectiveness of control measures and the trajectory of the pandemic.
Step 8 Visualization and Reporting: The results are visualized using graphs and charts to
enhance interpretability. Trends over time, regional comparisons, and classification outputs are
presented in a user-friendly format to support data-driven decisions.

Department of Electronics & Instrumentation Engineering, BIT 05/27/2025 21

 RESULT

The implemented machine learning models provided

insightful results on the classification and analysis of COVID-
19 data. After training and testing the models on the
processed dataset, their performance was evaluated using
standard metrics.
The Support Vector Machine (SVM) model achieved an
accuracy of 87%, showing high effectiveness in classifying
countries based on the severity of COVID-19 cases. The
Decision Tree model provided an accuracy of 84% and
offered better interpretability through its tree structure. The
K-Nearest Neighbors (KNN) model achieved 82%
accuracy, though its performance varied based on the value
of ‘k’.

Department of Electronics & Instrumentation Engineering, BIT 05/27/2025 22

 RESULT

Confusion matrices indicated that the models could reliably distinguish between high-risk
and low-risk countries based on daily case numbers, death counts, and recovery rates.
The Random Forest model outperformed the rest slightly, achieving an accuracy of
89%, along with high precision and recall scores, making it suitable for prediction tasks.
Furthermore, data visualization tools were used to generate line graphs showing daily
trends, heatmaps indicating country-wise severity, and bar charts comparing
confirmed, recovered, and death cases across different regions.

Department of Electronics & Instrumentation Engineering, BIT 05/27/2025 23

 VISUAL REPRESENTATION

Department of Electronics & Instrumentation Engineering, BIT 05/27/2025 24

 FUTURE SCOPE
The current machine learning-based analysis of the COVID-19 pandemic lays a strong foundation for more
advanced data-driven health monitoring and forecasting systems. The project can be further improved
through the following enhancements:
1. Real-Time Data Integration: Instead of relying solely on static datasets, real-time data feeds from
global health organizations and APIs can be integrated to provide up-to-date analysis and live prediction
dashboards.
2. Time-Series Forecasting Models: Advanced models such as LSTM (Long Short-Term Memory) and
ARIMA can be employed to forecast future case numbers and trends with greater temporal accuracy,
helping in early warning systems.
3. Geospatial Analysis: Integration of GIS data would allow spatial tracking of virus spread and clustering,
enabling detailed hotspot identification and regional response planning.
4. Vaccination Impact Modeling: By incorporating vaccination data, machine learning models can be
extended to study the effectiveness of different vaccination strategies and their impact on transmission
and mortality rates.
5. Web-Based Dashboard: A dynamic, interactive web dashboard can be developed to allow users to
Department
visualize of Electronics
trends, & Instrumentation
compare regions,Engineering,
and explore BIT 05/27/2025through charts, maps, and filters.
predictions 25
 REFLECTION AND OUTCOMES
Reflection
• Gained practical experience in handling real-world health datasets and applying various machine
learning algorithms for predictive analysis.
• Learned the importance of data preprocessing, feature selection, and model evaluation in building
accurate classification systems.
• Enhanced analytical and programming skills through the implementation of SVM, Decision Tree,
and Random Forest models using Python.
Outcomes
• Successfully implemented a machine learning pipeline for analyzing COVID-19 data and predicting
case severity across different regions.
• Achieved reliable classification results using multiple ML models, with Random Forest yielding the
highest accuracy.
• Created meaningful visualizations to support data interpretation and help identify patterns and
trends in the spread and control of the virus.

Department of Electronics & Instrumentation Engineering, BIT 05/27/2025 26

 CONCLUSION
The project successfully demonstrated the application of machine learning techniques for
analyzing and interpreting COVID-19 pandemic data. Through systematic data preprocessing,
feature selection, and model implementation, various supervised learning algorithms such as
Support Vector Machines, Decision Trees, and Random Forests were employed to classify and
predict the severity and spread of COVID-19 cases across countries.
The results highlighted the potential of machine learning in generating accurate, data-driven
insights that support better decision-making in public health management. Visualizations and
statistical analysis further enhanced the understanding of global trends, recovery rates, and
risk patterns. This project not only validates the effectiveness of predictive modeling in
epidemiological analysis but also lays the groundwork for building more comprehensive, real-
time, and scalable health analytics systems in the future.

Department of Electronics & Instrumentation Engineering, BIT 05/27/2025 27

 REFERENCES
[1] World Health Organization, “WHO Coronavirus (COVID-19) Dashboard,” [Link]
[2] Kaggle, “COVID-19 Dataset,” [Link]
[3] Scikit-learn Developers, “Scikit-learn: Machine Learning in Python,” [Link]
[4] Pedregosa, F., et al., “Scikit-learn: Machine Learning in Python,” Journal of Machine Learning
Research, 12, pp. 2825–2830, 2011.
[5] Python Software Foundation, “Python Language Reference,” [Link]
[6] Matplotlib Developers, “Matplotlib: Visualization with Python,” [Link]
[7] Brownlee, J., “Machine Learning Mastery: Data Preparation for Machine Learning,”
[Link]
[8] WHO, “Advice for the public: Coronavirus disease (COVID-19),”
[Link]
[9] IBM Cloud Education, “What is Machine Learning?” [Link]
learning
[10] Towards Data Science, “COVID-19 Prediction Using Machine Learning,”
[Link]
Department of Electronics & Instrumentation Engineering, BIT 05/27/2025 28
 THANK YOU

Department of Electronics & Instrumentation Engineering, BIT 05/27/2025 29