माधव प्रौद्योगिकी एवं विज्ञान संस्थान, ग्वालियर (म.प्र.

), भारत​
MADHAV INSTITUTE OF TECHNOLOGY & SCIENCE, GWALIOR (M.P.), INDIA
Deemed to be University
(Declared under Distinct Category by Ministry of Education, Government of India)
NAAC ACCREDITED WITH A++ GRADE

A Skill Based Mini Project Report

on

Fuzzy Logic Based Student Academic

Performance Analyzing System
Submitted by
Yashika Gangil (0901EO221073)

Submitted to
Prof. Poonam Singh
Assistant Professor

Centre for Internet of Things

Madhav Institute of Technology & Science, Gwalior
Gole ka Mandir, Gwalior - 474005, M.P., India

Jan-Apr 2025
 Madhav Institute of Technology & Science, Gwalior
(Deemed to be University)
NAAC Accredited with A++ Grade
(Declared under Distinct Category by Ministry of Education, Government of India)
Centre for Internet of Things

DECLARATION

I/We hereby declare that the work being presented in this skill based mini project
report, for the partial fulfilment of requirement for the award of the degree of Bachelor of
Technology in Internet of Things at Madhav Institute of Technology & Science, Gwalior
is an authenticated and original record of my work under the mentorship of Prof.
Poonam Singh , Assistant Professor, Centre for Internet of Things.
I/We declare that I/We have not submitted the matter embodied in this report for
the award of any degree or diploma anywhere else.

Yashika Gangil
(0901EO221073)
Centre for Internet of Things
 Madhav Institute of Technology & Science, Gwalior
(Deemed to be University)
NAAC Accredited with A++ Grade
(Declared under Distinct Category by Ministry of Education, Government of India)
Centre for Internet of Things

CERTIFICATE

This is certified that Yashika Gangil (0901EO221073) has submitted the skill
based mini project report titled “Fuzzy Logic Based Student Academic Performance
Analyzing System” under the mentorship of Prof. Poonam Singh, in partial fulfilment of
the requirement for the award of degree of Bachelor of Technology in Internet of Things
from Madhav Institute of Technology and Science, Gwalior.

Prof. Poonam Singh

Assistant Professor
Centre for Internet of Things
 Madhav Institute of Technology & Science, Gwalior
(Deemed to be University)
NAAC Accredited with A++ Grade
(Declared under Distinct Category by Ministry of Education, Government of India)
Centre for Internet of Things

ACKNOWLEDGEMENT

The full semester project has proved to be pivotal to my career. I am thankful to

my institute, Madhav Institute of Technology & Science to allow me to continue my
disciplinary/interdisciplinary project as a curriculum requirement, under the provisions of
the Flexible Curriculum Scheme approved by the Academic Council of the institute. I
extend my gratitude to the Director of the institute, Dr. R. K. Pandit and Dean
Academics, Dr. Manjaree Pandit for this.
I would sincerely like to thank my department, Centre for Internet of Things, for
allowing me to explore this project. I humbly thank Dr. Praveen Bansal, Assistant
Professor and Coordinator, Centre for Internet of Things, for his continued support
during the course of this engagement, which eased the process and formalities
involved.
I am sincerely thankful to my faculty mentors. I am grateful to the guidance of
Prof. Poonam Singh, Assistant Professor, and Centre for Internet of Things, for his
continued support and guidance throughout the project. I am also very thankful to the
faculty and staff of the department.

Yashika Gangil
(0901EO221073)
Centre for Internet of Things
 TABLE OF CONTENTS

Title​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ Page No.

Abstract ​ ​ ​ ​ ​ ​ ​ ​
List of Figures
List of Symbols
Chapter 1: Introduction​ ​ ​ ​ ​ ​ ​ ​ ​ 1-5​
​ 1.1 About recommendation system
​ 1.2 Parameters considered for recommendations
​ 1.3 Objective of project
Chapter 2: Chapter Title​ ​
6-10​
​ 2.1 Sub title 1
​ 2.2 Sub title 2
​ 2.3 Sub title 3
Chapter 3: Chapter Title​ ​
11-15​
3.1 Sub title 1
​ 3.2 Sub title 2
​ 3.3 Sub title 3
Chapter 4: Conclusion​ ​ ​ ​​ ​ ​
16​ ​ 4.1 Sub title 1
​ 4.2 Subtitle 2
​ 4.3 Future Scope

References​ ​ ​
17​ ​ ​ ​ ​ ​ ​
Appendix​ ​ ​ ​ ​ ​ ​ 18​
​
​
 ABSTRACT

Provide abstract of your skill based mini project report here, within 1or 2 pages.
 LIST OF FIGURES

Figure No.​ Figure caption ​ ​ ​ ​ ​ ​ ​ Page No.

1.​ ​ Content Based Filtering ​ ​ ​ ​ ​ ​ 11

2. ​ ​ After cleaning the data, Head ​ ​ ​ ​ ​ ​ 11
3. ​ ​ Cosine similarity ​ ​ ​ ​ ​ ​ ​ 12
4. ​ ​ get_recommendations_new() function ​ ​ ​ ​ 13
5. ​ ​ Home page ​ ​ ​ ​ ​ ​ ​ ​ 14
Chapter 1:
Introduction

1.1 About Recommendation System

Netflix is a company that handles a big collection of television programs and movies, by
streaming it at any time via online (computers or TV). This firm is profitable because the
users do a monthly payment to get access to the platform. However, the clients can
cancel their subscriptions at any time . Therefore, it is vital for the business to keep the
users hooked to the platform and not to lose their interest. This is where
recommendation systems start to play an important role, it is pivotal to provide valuable
suggestions to users. The recommendation systems are increasing their popularity
among the service providers, because they help to increase the number of items sold,
offer a diverse selection of items, the user satisfaction increases, as well as the user
fidelity to the company, and they are quite helpful to have a better understanding of
what the user wants. Then, it is easier to lead the user to make better decisions from a
wide variety of cinematographic products.

Fig 1.1 Building Blocks of IoT

1.2 Parameters Considered For Recommendations

The recommender systems take into account not only information about the users but
also about the items they consume; and so on and so forth. Nevertheless, there are
many algorithms available to perform a recommendation system. For instance,

I.​ Titles, where only the similar titles are recommended

II.​ Cast, which recommends the next show or movie having similar cast
III.​ Directors, sometimes users like same direction or obsessed with directors
so it recommends on the basis of similar direction styles;
 IV.​ Description, the recommendation of items with similar information the user
has liked or used in the past.

Selecting the algorithm that fits better the analysis is not an easy task, and neither
expands the user’s taste into neighboring areas by improving the obvious.

This study is conducted on real data from the Netflix users and they have given to the
movies they have seen. Furthermore, the movies file includes the year of release and
the title of the movie as well.

Fig 1.2 LORAWAN Technologies

Chapter 2:
Chapter Title

2.1 About Recommendation System

Netflix is a company that handles a big collection of television programs and movies, by
streaming it at any time via online (computers or TV). This firm is profitable because the
users do a monthly payment to get access to the platform. However, the clients can
cancel their subscriptions at any time . Therefore, it is vital for the business to keep the
users hooked to the platform and not to lose their interest. This is where
recommendation systems start to play an important role, it is pivotal to provide valuable
suggestions to users. The recommendation systems are increasing their popularity
among the service providers, because they help to increase the number of items sold,
offer a diverse selection of items, the user satisfaction increases, as well as the user
fidelity to the company, and they are quite helpful to have a better understanding of
what the user wants. Then, it is easier to lead the user to make better decisions from a
wide variety of cinematographic products.

Fig .2.1 AWS IoT Core Network

2.2 Parameters Considered For Recommendations

The recommender systems take into account not only information about the users but
also about the items they consume; and so on and so forth. Nevertheless, there are
many algorithms available to perform a recommendation system. For instance,

V.​ Titles, where only the similar titles are recommended

VI.​ Cast, which recommends the next show or movie having similar cast
 VII.​ Directors, sometimes users like same direction or obsessed with directors
so it recommends on the basis of similar direction styles;
VIII.​ Description, the recommendation of items with similar information the user
has liked or used in the past.

Selecting the algorithm that fits better the analysis is not an easy task, and neither
expands the user’s taste into neighbouring areas by improving the obvious.

This study is conducted on real data from the Netflix users and they have given to the
movies they have seen. Furthermore, the movies file includes the year of release and
the title of the movie as well.

Conclusion
References

[1]. https://www.kaggle.com/

[2]. Ali Abur, “Industrial IoT: A Practical Approach”, ABC Publisher, September 2022.

[3].