INTRODUCTION TO INTERNET OF THINGS

&
DATA ANALYTICS WITH PYTHON

Report Submitted On
SWAYAM Courses
[SWCS- 807]

By

ARGHADEEP SAHA
TU ROLL NO: 216704041
REG NO: 020698 OF 2021-22

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

TECHNO COLLEGE OF ENGINEERING AGARTALA

(A Degree & Diploma Engineering College Affiliated to Tripura University,

Approved by AICTE, MHRD, Govt. of India)
Maheshkhola, PO: Anandanagar, West Tripura PIN-799004

Date of Submission: 13/06/2025

 DECLARATION

I, Arghadeep Saha (TU Roll No: 216704041), hereby declare that the
SWAYAM Courses (SWCS 807) titled “Introduction to Internet of Things &
Data Analytics with Python” submitted during the academic session 2024-2025
in partial fulfilment of the requirements for the award of the degree of Bachelor
of Technology in the discipline of Computer Science and Engineering, is my
original work.
The content presented in this report has been prepared by me under the
supervision and guidance of my mentor, and it has not been submitted, in part or
in full, to any other university or institute for the award of any degree, diploma,
or certificate.

Arghadeep Saha
TU Roll: 216704041
8th Sem CSE, B.Tech
 CERTIFICATE

This is to certify that the work contained in the report titled “Introduction to
Internet of Things & Data Analytics with Python” by Arghadeep Saha (TU
Roll No: 216704041) has success fully completed the SWAYAM- NPTEL online
course. This work has been submitted for the partial fulfillment for the award of
the degree of Bachelor of Technology in the discipline of Computer Science
and Engineering.
The content presented in this report is original and has not been submitted,
in part or in full, to any other university or institute for the award of any degree,
diploma, or certificate.

Mrs. Purbani Kar

Assistant Professor and Head Of the Department
Department of Computer Science & Engineering
Techno College of Engineering Agartala

1
 COURSE 1
INTRODUCTION TO INTERNET OF THINGS
 (1)
INTRODUCTION

1.1 Brief overview of the SWAYAM platform and its objectives:

SWAYAM (Study Webs of Active Learning for Young Aspiring Minds) is a flagship
initiative by the Ministry of Education, Government of India, aimed at democratizing access to
high-quality education. Launched to bridge the digital divide and ensure equitable learning
opportunities, SWAYAM offers interactive courses across various disciplines at both school
and higher education levels, completely free of cost.

Courses are developed by experts from prestigious institutions such as the IITs, IIMs, and
central universities, and are designed to be accessible, flexible, and aligned with modern
academic and professional standards. The platform integrates video lectures, reading materials,
self-assessment tests, and discussion forums to create a holistic and engaging learning
experience.

SWAYAM allows learners to study at their own pace and convenience, making it especially
beneficial for students in remote areas or those with limited access to traditional educational
resources.

1.2 Purpose of enrolling in the specific course:

I enrolled in the "Introduction to Internet of Things (IoT)" course on the SWAYAM

platform, offered by Prof. Sudip Misra of IIT Kharagpur, to build a solid foundation in one
of the most rapidly growing and impactful areas of modern technology. As a final-year
Computer Science and Engineering student, I recognized the increasing relevance of IoT
across diverse domains such as healthcare, agriculture, smart cities, and industrial automation.

The course offered a structured exploration of IoT fundamentals, including network

architecture, sensor technologies, communication protocols, cloud integration, and security
challenges. I was particularly drawn to the practical orientation of the course, which
emphasized real-world applications and emerging trends in IoT deployments.

My purpose for choosing this course was to broaden my technical skill set beyond traditional
software development by understanding how hardware, connectivity, and software interact to
create intelligent systems. I aimed to align my learning with current industry needs and prepare
myself for future roles in embedded systems, smart infrastructure, or IoT-based product
development.

This course has significantly contributed to my understanding of how interconnected devices

can solve complex problems across sectors, and has enhanced my ability to think innovatively
about integrating IoT into real-world solutions.
 (2)
COURSE DETAILS

Course Name: Introduction to Internet of Things

Course Instructor: Prof. Sudip Misra

Offered By: IIT Kharagpur

Duration: 12 weeks (22 July 2024 to 11 October 2024)

Credit Point: 3
 (3)
LEARNING OBJECTIVES

3.1 Primary objectives or goals the course aimed to achieve:

The "Introduction to Internet of Things (IoT)" course aimed to provide learners with a
foundational and application-oriented understanding of IoT systems. The key objectives of the
course were:

A. To introduce the fundamental concepts of IoT

Familiarize students with the basic components and architecture of IoT systems, including
sensing, actuation, connectivity, and data processing.
B. To build a strong foundation in networking and communication protocols
Explain essential networking concepts and IoT-specific protocols (e.g., MQTT, CoAP) that
facilitate reliable data transmission in resource-constrained environments.
C. To teach sensor integration and hardware interfacing
Provide practical exposure to integrating sensors and actuators with popular IoT platforms
such as Arduino and Raspberry Pi for real-world applications.
D. To enable programming skills for IoT development
Introduce learners to Arduino programming, Python programming, and Raspberry Pi-based
implementations, bridging hardware with software logic.
E. To explore Software Defined Networking (SDN) and its relevance to IoT
Introduce SDN principles and how they enable flexible, scalable, and programmable
networking for complex IoT infrastructures.
F. To present modern computing paradigms in IoT
Discuss the roles of Cloud Computing, Fog Computing, and Sensor-Cloud Integration in
enhancing data storage, processing, and analytics capabilities for IoT systems.
G. To highlight real-world applications and emerging trends
Expose students to a range of IoT applications in domains such as Smart Cities, Smart
Homes, Healthcare, Agriculture, Connected Vehicles, and Industrial IoT through case
studies.
H. To integrate theoretical knowledge with practical implementation
Encourage hands-on learning through lab sessions, simulations, and mini-projects that help
apply theoretical concepts to develop IoT solutions.
I. To prepare students for interdisciplinary IoT innovation
Cultivate a mindset that combines computing, electronics, and domain-specific knowledge
to design and implement innovative IoT-based systems.
 (4)
COURSE CONTENT SUMMARY

4.1 Week 1: Introduction to IoT.

This section introduces the foundational concepts of the Internet of Things (IoT), emphasizing
its core components and how they function together. IoT enables the connection of physical
devices through the internet to collect, share, and process data. These systems typically involve
sensors, which capture real-world data like temperature, light, or motion, and convert it into
digital signals for further analysis. Actuators then use this data to perform actions such as
switching on a motor or adjusting a setting. Effective communication between devices is
facilitated by networking technologies and protocols such as MQTT, Wi-Fi, ZigBee, and LoRa,
which ensure smooth data exchange and system responsiveness.

4.2 Week 2: IoT Networking & Connectivity.

The basics of IoT networking revolve around how devices communicate within a structured,
layered network architecture. This includes various communication models such as Device-to-
Device (D2D), Device-to-Gateway, and Device-to-Cloud, each serving different roles in data
transmission and system integration. Key IoT communication protocols are also introduced:
MQTT, known for its lightweight nature and suitability for constrained devices; CoAP, a web-
based protocol optimized for low-power applications; and HTTP, a widely adopted but heavier
option. Additionally, the discussion highlights critical networking challenges such as achieving
low power consumption, ensuring scalability and reliability, and maintaining data security.

In terms of connectivity technologies, both short- and long-range options are explored. Short-
range technologies include Wi-Fi, which offers high data rates but consumes significant power;
Bluetooth, ideal for low power and short-distance needs; and ZigBee, known for its mesh
networking capabilities and low power usage. For long-range connectivity, technologies such
as LoRa (long range, low power, and low data rate), NB-IoT (a cellular-based and energy-
efficient option), and 4G/5G (providing wide coverage and high speed) are considered. The
choice of connectivity method depends on multiple factors, including required range, power
constraints, cost, bandwidth, and the specific application.

4.3 Week 3: Advanced Connectivity and Sensor Networks in IoT.

This section explores advanced connectivity solutions and sensor network architectures critical
to the development and deployment of robust IoT systems. A range of wireless communication
technologies is examined, including cellular standards such as NB-IoT, LTE-M, and 5G, as
well as satellite-based communication for remote or hard-to-reach environments. These
technologies are evaluated based on key parameters such as range, data rate, power efficiency,
scalability, and cost, providing a framework for selecting the most appropriate solution for
specific IoT applications.

In addition, the concept of wireless sensor networks (WSNs) is introduced, focusing on how
distributed sensor nodes operate collaboratively to collect, transmit, and process environmental
data. Important design aspects such as network topology (e.g., star, mesh, and clustered
configurations), data aggregation, and energy-efficient routing protocols are discussed. These
networks are essential for enabling real-time monitoring and control in areas such as smart
cities, agriculture, environmental sensing, and healthcare. The integration of connectivity
technologies with intelligent sensor networks forms the backbone of scalable and energy-aware
IoT infrastructures.

4.4 Week 4: Sensor Networks, UAV Integration, and Machine-to-Machine

Communication in IoT.

This section continues the exploration of wireless sensor networks (WSNs), emphasizing
advanced aspects such as sensor deployment strategies, data fusion techniques, fault tolerance,
and scalability. Special attention is given to optimizing energy efficiency and improving
communication reliability in large-scale and dynamic environments. These considerations are
critical for long-term, autonomous operation of IoT systems in sectors like environmental
monitoring, industrial automation, and smart infrastructure.

In addition, the role of Unmanned Aerial Vehicle (UAV) networks in IoT is introduced. UAVs
serve as mobile nodes or relays within sensor networks, enhancing data collection capabilities
in remote or rapidly changing environments.

4.5 Week 5: Arduino Integration Concepts.

This content provides a comprehensive introduction to essential topics in the Internet of Things
(IoT) and Arduino-based systems. It starts by explaining interoperability, which is the ability
of various IoT devices and platforms to communicate and work together seamlessly, despite
differences in hardware or communication protocols.

Following this, it introduces the Arduino platform, covering both the hardware components
(such as microcontrollers and input/output pins) and the software required to program and
operate these devices. The basics of coding with Arduino are also introduced, laying the
groundwork for further hands-on learning.

4.6 Week 6: Building IoT Systems with Python and Raspberry Pi.

This section introduces the fundamentals of Python programming, which is widely used in IoT
development due to its simplicity and versatility. It then explores the Raspberry Pi, a powerful
single-board computer, explaining its features, setup, and usage for IoT projects. The content
progresses to hands-on implementation, showing how Python and Raspberry Pi can be
combined to build functional IoT systems, enabling data processing, device control, and
network communication. It explains different types of sensors and actuators, common
interfacing protocols (GPIO, I2C, SPI, UART), and provides hands-on examples of sensor data
collection.
4.7 Week 7: Practical IoT Implementation and Advanced Networking.

This section focuses on hands-on IoT implementation using Raspberry Pi, demonstrating how
to build complete systems that collect, process, and transmit data. It then transitions into
Software Defined Networking (SDN), highlighting how network control can be centralized and
made more flexible. The final part introduces Software Defined IoT Networking, which
combines SDN with IoT to improve scalability, manageability, and efficiency in connected
device environments.

4.8 Week 8: Advancing IoT with SDN and Cloud Computing.

This segment begins with Software Defined IoT Networking, emphasizing improved control,
scalability, and automation in managing IoT networks. It then shifts focus to Cloud Computing,
starting with fundamental concepts and progressing through various service models (IaaS,
PaaS, SaaS). Further discussions include cloud service management, security practices, and
real-world case studies, highlighting how cloud infrastructure supports scalable, secure, and
efficient IoT deployments.

4.9 Week 9: Practical Cloud Integration and Edge Computing in IoT.

This section delivers practical insights into cloud computing for IoT, showcasing real-world
applications and deployments. It explores the Sensor-Cloud architecture, where sensor data is
collected, processed, and stored in the cloud for intelligent services. Finally, it introduces Fog
Computing, a model that extends cloud capabilities closer to the network edge, enabling faster
processing, reduced latency, and improved efficiency for time-sensitive IoT applications.

4.10 Week 10: IoT Applications in Smart Environments and Mobility.

This section explores real-world IoT applications, beginning with smart cities and smart homes,
where connected technologies enhance urban infrastructure, energy efficiency, and home
automation. It then covers connected vehicles, focusing on how IoT enables intelligent
transportation systems, vehicle-to-vehicle (V2V) communication, and improved road safety
and traffic management.

4.11 Week 11: Smart Infrastructure, Industrial IoT, and Data Analytics.

This section covers advanced IoT applications in critical infrastructure and industry. It begins
with the smart grid, focusing on how IoT optimizes energy distribution, monitoring, and
reliability. It then explores the Industrial Internet of Things (IIoT), highlighting connected
machinery, predictive maintenance, and automation in manufacturing. The segment concludes
with an introduction to data handling and analytics, emphasizing how collected data is
processed and analyzed to drive intelligent decision-making in IoT systems.
4.12 Week 12: Data Analytics and Real-World IoT Case Studies.

This final section deepens understanding of IoT data handling and analytics, emphasizing
techniques for processing, analyzing, and extracting insights from large-scale sensor data. It
then applies these concepts to practical case studies in domains like agriculture, healthcare, and
activity monitoring, showcasing how IoT solutions are tailored to meet real-world needs,
enhance efficiency, and support decision-making across diverse sectors.
 (5)
ASSIGNMENTS AND ASSESSMENTS

5.1 Types of assignments and assessments undertaken:

• Weekly MCQ-based assignments related to lecture content.

• There were 10-15 questions in the assignments.
• Final exam was conducted online with multiple-choice questions.

5.2 Performance during the course:

Assessment Scores:

Week Lesson Progress Assignment Score

Week 1 100 100
Week 2 100 100
Week 3 100 93
Week 4 100 93
Week 5 100 100
Week 6 100 87
Week 7 100 100
Week 8 100 100
Week 9 100 100
Week 10 100 100
Week 11 100 93
Week 12 100 87

• Online Assignments Score: 24.78/25

• Proctored Exam Score: 42/75

 (6)
SKILLS ACQUIRED

6.1 New Skills and Knowledge Areas Developed:

• Understanding of IoT architecture, components, and ecosystem

• Familiarity with networking basics and IoT communication protocols
• Hands-on skills in Arduino and Raspberry Pi programming
• Integration of sensors and actuators with IoT devices
• Knowledge of Software Defined Networking (SDN) for IoT
• Insights into Cloud, Fog, and Sensor-Cloud computing models
• Ability to analyze and handle IoT data effectively
• Exposure to real-world IoT applications across various domains
• Enhanced problem-solving skills for designing IoT solutions

6.2 Relevance to Academic and Professional Pursuits:

This course has significantly enhanced my conceptual and practical understanding of Internet
of Things technology and its diverse applications. As a final-year Computer Science
Engineering student, this knowledge directly supports my academic projects involving
embedded systems, sensor networks, and data-driven IoT solutions. The course improved my
skills in programming IoT devices, integrating sensors, understanding communication
protocols, and leveraging cloud and fog computing for data processing. Professionally, the
expertise gained aligns well with industry demands in smart systems development, automation,
and IoT infrastructure management. It has prepared me for roles in IoT development, embedded
software engineering, and system integration, making me more competent and confident for
future career opportunities or advanced research in this rapidly growing field.
 (7)
CHALLENGES FACED

7.1 Difficulties encountered during the course:

During the course, I encountered several challenges that tested my understanding and problem-
solving abilities. Initially, grasping the wide range of networking protocols and their specific
use cases in IoT was complex due to the technical depth and variety involved. Additionally,
programming microcontrollers like Arduino and working with Raspberry Pi required a steep
learning curve, especially for someone with limited prior hardware experience. Integrating
sensors and actuators and troubleshooting hardware-software communication issues also
proved to be demanding. Furthermore, concepts like Software Defined Networking (SDN) and
fog computing were new and abstract, making it difficult to fully comprehend their practical
implications without extensive hands-on practice. Despite these difficulties, persistence and
additional self-study helped me overcome these hurdles and strengthened my overall learning
experience.

7.2 Strategies employed to overcome these challenges:

To overcome the challenges encountered during the course, I adopted a multi-pronged

approach. I dedicated extra time to revisiting lecture videos and reading supplementary
materials to deepen my understanding of complex topics like networking protocols and SDN.
For programming and hardware integration tasks, I practiced hands-on exercises repeatedly
and experimented with different sensor and actuator setups to gain practical familiarity. I also
participated in online forums and study groups to discuss difficulties and learn from peers’
experiences. Whenever possible, I applied theoretical concepts through mini-projects, which
helped solidify my knowledge. Additionally, I sought guidance from instructors and utilized
online resources such as tutorials and documentation to resolve specific technical issues. This
proactive and persistent approach enabled me to effectively overcome obstacles and enhance
my learning outcomes.
 APPROVAL LETTER

To
The Head of the Department
Department of Computer Science and Engineering
Techno College of Engineering Agartala
Maheskhola, Agartala, West Tripura

Subject: Approval for 12-week SWAYAM course on Introduction to Internet of Things in

B.Tech Computer Science and Engineering Program

Respected Madam,

I am writing to seek your kind approval to pursue a SWAYAM course as part of my B.Tech
program in Computer Science and Engineering.

Course Details:

• Course Name: Introduction to Internet of Things

• Institution: IIT Kharagpur
• Duration: 12 Weeks
• Course Instructor: Prof. Sudip Misra
• Credit Point: 3

This course is highly relevant to my branch of study and aligns with the evolving curriculum
of Computer Science and Engineering. It covers critical concepts such as IoT architecture,
embedded systems, networking protocols, cloud integration, and real-world applications,
which are vital for today’s technology-driven landscape.

I kindly request you to review and approve this course as part of the elective/self-learning
component of the B.Tech program. Your approval will support my academic growth and help
me gain valuable knowledge aligned with current industry trends.

Thanking you,

Yours sincerely,
Arghadeep Saha
TU Roll No: 216704041
Student ID: 2130401064
Registration No: 020698 of 2021-22

B.Tech, Computer Science and Engineering

Techno College of Engineering Agartala
CERTIFICATE
 COURSE 2
DATA ANALYTICS WITH PYTHON
 (1)
INTRODUCTION

1.3 Brief overview of the SWAYAM platform and its objectives:

SWAYAM (Study Webs of Active Learning for Young Aspiring Minds) is a flagship
initiative by the Ministry of Education, Government of India, aimed at democratizing access to
high-quality education. Launched to bridge the digital divide and ensure equitable learning
opportunities, SWAYAM offers interactive courses across various disciplines at both school
and higher education levels, completely free of cost.

Courses are developed by experts from prestigious institutions such as the IITs, IIMs, and
central universities, and are designed to be accessible, flexible, and aligned with modern
academic and professional standards. The platform integrates video lectures, reading materials,
self-assessment tests, and discussion forums to create a holistic and engaging learning
experience.

SWAYAM allows learners to study at their own pace and convenience, making it especially
beneficial for students in remote areas or those with limited access to traditional educational
resources.

1.4 Purpose of enrolling in the specific course:

I enrolled in the " Data Analytics with Python " course on the SWAYAM platform, offered
by Prof. A Ramesh of IIT Roorkee, to build a solid foundation in one of the most rapidly
growing and impactful areas of modern technology. As a final-year Computer Science and
Engineering student, I recognized the increasing relevance of IoT across diverse domains such
as healthcare, agriculture, smart cities, and industrial automation.

The course offered a structured exploration of IoT fundamentals, including network

architecture, sensor technologies, communication protocols, cloud integration, and security
challenges. I was particularly drawn to the practical orientation of the course, which
emphasized real-world applications and emerging trends in IoT deployments.

My purpose for choosing this course was to broaden my technical skill set beyond traditional
software development by understanding how hardware, connectivity, and software interact to
create intelligent systems. I aimed to align my learning with current industry needs and prepare
myself for future roles in embedded systems, smart infrastructure, or IoT-based product
development.

This course has significantly contributed to my understanding of how interconnected devices

can solve complex problems across sectors, and has enhanced my ability to think innovatively
about integrating IoT into real-world solutions.
 (2)
COURSE DETAILS

Course Name: Data Analytics with Python

Course Instructor: Prof. A Ramesh

Offered By: IIT Roorkee

Duration: 12 weeks (22 Jan 2024 to 12 Apr 2024)

Credit Point: 3
 (3)
LEARNING OBJECTIVES

3.1 Primary objectives or goals the course aimed to achieve:

The "Data Analytics with Python" course aimed to provide learners with a foundational and
application-oriented understanding of data analytics using Python. The key objectives of the
course were:

A. To introduce the fundamental concepts of Data Analytics

Familiarize students with the basic concepts and architecture of data analytics systems,
including data collection, preprocessing, exploration, visualization, and interpretation.

B. To build a strong foundation in data handling and processing techniques

Explain essential data manipulation concepts and Python-specific libraries (e.g., Pandas,
NumPy) that facilitate efficient data cleaning, transformation, and preparation.

C. To teach data visualization and exploratory data analysis

Provide practical exposure to exploring datasets and uncovering insights using popular
Python libraries such as Matplotlib and Seaborn for real-world applications.

D. To enable programming skills for data analytics development

Introduce learners to Python programming, data structures, and data-driven logic
development, bridging theoretical knowledge with practical programming.

E. To explore Machine Learning basics and their relevance to Data Analytics

Introduce fundamental machine learning principles and how they enable predictive and
descriptive analytics for various data domains.

F. To present modern tools and platforms for data analytics

Discuss the roles of Jupyter Notebooks, cloud-based platforms, and big data tools in
enhancing the analysis, visualization, and scalability of data analytics tasks.

G. To highlight real-world applications and emerging trends

Expose students to a range of data analytics applications in domains such as Business
Intelligence, Healthcare, Finance, Retail, and Social Media Analytics through case
studies.

H. To integrate theoretical knowledge with practical implementation

Encourage hands-on learning through lab sessions, simulations, and mini-projects that
help apply theoretical concepts to develop data-driven solutions.

I. To prepare students for interdisciplinary innovation in analytics

Cultivate a mindset that combines computing, statistics, and domain-specific knowledge
to design and implement innovative analytics-based systems.
 (4)
COURSE CONTENT SUMMARY

4.1 Week 1: Building the Foundations of Data Analytics.

This course journey began with an insightful introduction to the world of data analytics,
highlighting its significance in uncovering trends and supporting informed decision-making.
Learners were then guided through the essentials of Python programming, gaining hands-on
experience with variables, data types, loops, functions, and key libraries used in data analysis.
The course further explored statistical fundamentals, focusing on measures of central tendency
and dispersion, which are critical for understanding data distribution and variability. By
integrating programming skills with statistical concepts, the course laid a strong foundation for
learners to transform raw data into meaningful insights.

4.2 Week 2: Mastering Probability and Distributions.

This section of the course offered a comprehensive understanding of probability theory,

beginning with the foundational concepts such as outcomes, events, and rules of probability,
which are essential for reasoning under uncertainty. It then progressed to more complex ideas,
including conditional probability and Bayes’ theorem, equipping learners to assess
relationships between events. The course continued with an in-depth exploration of probability
distributions, covering both discrete and continuous types. Key distributions like Binomial,
Poisson, and Normal were discussed, along with their real-world applications in data analysis.

4.3 Week 3: Exploring Distributions and Confidence Intervals.

This segment of the course deepened learners' understanding of statistical inference through
practical and theoretical approaches. It began with a Python demonstration on probability
distributions, allowing learners to visualize and simulate different types of data behaviors. The
focus then shifted to sampling techniques and the concept of sampling distributions, laying the
groundwork for understanding variability in data. Learners explored the distribution of sample
means, population characteristics, and variance, which are crucial for accurate statistical
estimation. The module concluded with a two-part exploration of confidence interval
estimation for a single population, equipping learners with tools to make reliable predictions
and quantify uncertainty in real-world data analysis.

4.4 Week 4: A Deep Dive into Hypothesis Testing.

This module introduced the critical concept of hypothesis testing, empowering learners to make
data-driven decisions with statistical backing. It began by explaining the formulation of null
and alternative hypotheses, followed by the step-by-step process of conducting hypothesis
tests. As the lessons progressed, more advanced topics such as p-values, test statistics, and
significance levels were covered to help interpret results effectively. Learners also explored
common pitfalls, including errors in hypothesis testing—Type I and Type II errors—
highlighting the importance of careful statistical judgment. Finally, the course introduced two-
sample tests, enabling comparison between population groups. Together, these lessons built a
robust foundation for validating assumptions and drawing meaningful conclusions from data.

4.5 Week 5: Beyond Comparison: Mastering Two-Sample Tests and ANOVA.

This portion of the course extended hypothesis testing into deeper statistical comparisons
across multiple samples. Beginning with two-sample tests, learners explored how to assess
differences between independent groups using various statistical techniques. The focus then
transitioned to ANOVA (Analysis of Variance), a powerful method for comparing means
across three or more groups, highlighting when and why to use it over simpler tests. The lessons
on ANOVA were followed by Post Hoc analysis using Tukey’s test, which provided a deeper
understanding of where the actual differences lie after finding significant variance. This module
equipped learners with the analytical tools necessary for evaluating complex datasets and
drawing nuanced conclusions in data-driven projects.

4.6 Week 6: Designs, Decisions, and Predictions: A Deeper Dive into Statistical
Modeling.

This segment of the course delved into experimental design and predictive analytics. It began
with the Randomized Block Design (RBD), emphasizing how to control variability in
experiments for more accurate results. Building on that, Two-Way ANOVA was introduced to
analyze the influence of two independent factors on a response variable, offering insights into
interactions between variables. The course then transitioned into Linear Regression, spread
over three detailed sessions. These covered the basics of fitting a line to data, interpreting
coefficients, evaluating model performance, and understanding assumptions. Together, these
topics provided a strong foundation in both experimental analysis and predictive modeling,
essential tools in data analytics.

4.7 Week 7: From Prediction to Precision: Mastering Regression Techniques.

This section of the course expanded on the practical and theoretical dimensions of regression
analysis. It started with estimation and prediction using regression models, with a focus on
residual analysis to validate model accuracy and assumptions. These insights paved the way
for understanding model robustness. The course then moved into Multiple Regression Models,
exploring how to incorporate several independent variables to improve predictive performance
and understand complex relationships. Lastly, the concept of Categorical Variable Regression
was introduced, teaching how to handle qualitative data within regression frameworks. This
comprehensive coverage equips learners with the tools needed for accurate forecasting and
analytical modeling in real-world datasets.

4.8 Week 8: Cracking the Code of Classification: Logistic Regression and Maximum
Likelihood.

This segment delved into essential statistical techniques for modeling and prediction. It began
with Maximum Likelihood Estimation (MLE), a foundational method for estimating model
parameters by maximizing the probability of observed data. The course then introduced
Logistic Regression, a powerful tool for binary classification problems, emphasizing model
formulation, interpretation of coefficients, and evaluation metrics. Finally, the comparison
between Linear and Logistic Regression highlighted the appropriate contexts for each model,
focusing on the differences in assumptions, output types, and real-world applications. This
section equipped learners with the skills to handle classification challenges with mathematical
rigor and practical insight.

4.9 Week 9: Decoding Model Performance: From Classification to Regression.

This module dives into the evaluation and fine-tuning of both classification and regression
models. It begins by unraveling the confusion matrix and ROC curve, essential tools for
assessing the performance of classification models. It then explores the effectiveness of logistic
regression models by examining predictive accuracy and interpretation of results. Transitioning
into regression analysis, the focus shifts to building linear regression models, incorporating
both main effects and interaction terms. Emphasis is placed on model selection, interpretation,
and diagnostics to ensure robust and insightful predictions.

4.10 Week 10: Exploring Associations and Uncovering Patterns in Data.

This section begins with the Chi-Square tests, guiding learners through the test of independence
and goodness-of-fit, which are crucial for evaluating relationships between categorical
variables. These tests form the backbone of understanding dependencies and distributions in
qualitative data. The journey then transitions into the realm of unsupervised learning with an
introduction to cluster analysis. Here, learners are introduced to the basic principles of grouping
data points based on similarity, laying the foundation for more advanced clustering techniques
and insights into natural patterns within datasets.

4.11 Week 11: Diving Deeper into Clustering: Finding Structure in Chaos.

This segment takes a deeper dive into clustering, expanding from the foundational concepts to
more specialized and practical approaches. It explores multiple parts of clustering analysis,
emphasizing methods to evaluate and refine clusters for meaningful insights. The K-Means
clustering algorithm is introduced, demonstrating how to partition data into distinct groups
based on centroid proximity. The journey continues with hierarchical clustering, offering a
tree-like structure that helps visualize nested groupings and understand data from multiple
granular perspectives.

4.12 Week 12: From Branches to Decisions: Mastering CART and Clustering.

This section begins with a continuation of hierarchical clustering, building upon the earlier
techniques to further analyze complex data groupings. The focus then shifts to Classification
and Regression Trees (CART), a powerful method for predictive modeling. Learners explore
the construction of decision trees, understanding how data is split based on attribute selection
measures like Gini index and entropy. The series also explains how to evaluate and refine these
trees, ensuring they generalize well to new data. Overall, this module bridges unsupervised
clustering techniques with supervised learning, offering a robust toolkit for classification and
prediction.
 (5)
ASSIGNMENTS AND ASSESSMENTS

5.1 Types of assignments and assessments undertaken:

• Weekly MCQ-based assignments related to lecture content.

• There were 10-15 questions in the assignments.
• Final exam was conducted online with multiple-choice questions.

5.2 Performance during the course:

Assessment Scores:

Week Lesson Progress Assignment Score

Week 1 100 100
Week 2 100 100
Week 3 100 100
Week 4 100 100
Week 5 100 -
Week 6 100 70
Week 7 100 78
Week 8 100 90
Week 9 100 75
Week 10 100 50
Week 11 100 78
Week 12 100 100

• Online Assignments Score: 23.31/25

• Proctored Exam Score: 39.89/75

 (6)
SKILLS ACQUIRED

6.1 New Skills and Knowledge Areas Developed:

• Understanding of data analytics architecture, components, and ecosystem

• Familiarity with data handling, cleaning, and preprocessing using Python
• Hands-on skills in Python programming with libraries like Pandas, NumPy, and
Matplotlib
• Integration of various data sources and formats for analysis
• Knowledge of machine learning basics and model-building using Python
• Insights into cloud platforms and tools for scalable data analytics
• Ability to analyze, visualize, and interpret data effectively
• Exposure to real-world data analytics applications across various domains
• Enhanced problem-solving skills for designing data-driven solutions

6.2 Relevance to Academic and Professional Pursuits:

This course has significantly enhanced my conceptual and practical understanding of Data
Analytics using Python and its wide-ranging applications. As a final-year Computer Science
Engineering student, this knowledge directly supports my academic projects involving data-
driven decision-making, predictive modeling, and real-world data analysis. The course
improved my skills in programming with Python, handling structured and unstructured data,
understanding analytical workflows, and applying statistical and machine learning techniques.

Professionally, the expertise gained aligns well with industry demands in areas such as business
analytics, healthcare informatics, finance, and smart technologies. It has prepared me for roles
in data analytics, data science, and software development, making me more competent and
confident for future career opportunities or advanced research in this rapidly growing field.
 (7)
CHALLENGES FACED

7.1 Difficulties encountered during the course:

During the course, I encountered several challenges that tested my understanding and problem-
solving abilities. Initially, grasping the wide range of data analytics tools and techniques was
complex due to the technical depth and variety involved. Additionally, learning Python
programming for data manipulation and analysis required a steep learning curve, especially for
someone with limited prior coding experience. Understanding data preprocessing, visualization
techniques, and implementing machine learning algorithms also proved to be demanding.
Furthermore, concepts like feature engineering, model evaluation, and interpreting analytical
outcomes were new and abstract, making it difficult to fully comprehend their practical
implications without extensive hands-on practice. Despite these difficulties, persistence and
additional self-study helped me overcome these hurdles and strengthened my overall learning
experience.

7.2 Strategies employed to overcome these challenges:

To overcome the challenges encountered during the course, I adopted a multi-pronged

approach. I dedicated extra time to revisiting lecture videos and reading supplementary
materials to deepen my understanding of complex topics like data cleaning, exploratory data
analysis, and model training. For programming and analytical tasks, I practiced hands-on
exercises repeatedly and experimented with different datasets to gain practical familiarity. I
also participated in online forums and study groups to discuss difficulties and learn from peers’
experiences. Whenever possible, I applied theoretical concepts through mini-projects, which
helped solidify my knowledge. Additionally, I sought guidance from instructors and utilized
online resources such as tutorials and documentation to resolve specific technical issues. This
proactive and persistent approach enabled me to effectively overcome obstacles and enhance
my learning outcomes.
 APPROVAL LETTER

To
The Head of the Department
Department of Computer Science and Engineering
Techno College of Engineering Agartala
Maheskhola, Agartala, West Tripura

Subject: Approval for 12-week SWAYAM course on Introduction to Internet of Things in

B.Tech Computer Science and Engineering Program

Respected Madam,

I am writing to seek your kind approval to pursue a SWAYAM course as part of my B.Tech
program in Computer Science and Engineering.

Course Details:

• Course Name: Data Analytics with Python

• Institution: IIT Roorkee
• Duration: 12 Weeks
• Course Instructor: Prof. A Ramesh
• Credit Point: 3

This course is highly relevant to my branch of study and aligns with the evolving curriculum
of Computer Science and Engineering. It covers critical concepts such as IoT architecture,
embedded systems, networking protocols, cloud integration, and real-world applications,
which are vital for today’s technology-driven landscape.

I kindly request you to review and approve this course as part of the elective/self-learning
component of the B.Tech program. Your approval will support my academic growth and help
me gain valuable knowledge aligned with current industry trends.

Thanking you,

Yours sincerely,
Arghadeep Saha
TU Roll No: 216704041
Student ID: 2130401064
Registration No: 020698 of 2021-22

B.Tech, Computer Science and Engineering

Techno College of Engineering Agartala
CERTIFICATE