A

PROJECT REPORT
ON

“Crop Recommendation System using ML Algorithm”

SUBMITTED TO THE SAVITRIBAI PHULE PUNE UNIVERSITY, PUNE
IN THE PARTIAL FULFILLMENT OF THE REQUIREMENTS
FOR THE AWARD OF THE DEGREE
OF
BACHELOR OF ENGINEERING (COMPUTER ENGINEERING)
SUBMITTED BY

Mr. Shaikh Moin Ansar Exam No : B190504259

Mr. Dange Aniket Machhindra Exam No : B190504215
Miss. Salve Dnyaneshwari Anil Exam No : B190504257
Miss. Kaklij Rutuja Devidas Exam No : B190504232

GUIDED BY
PROF.SONAWANE M.J.

DEPARTMENT OF COMPUTER ENGINEERING

SND COLLEGE OF ENGINEERING AND RESEARCH CENTER
YEOLA, NASHIK 423401
SAVITRIBAI PHULE PUNE UNIVERSITY
2023-24
 CERTIFICATE
This is to certify that the project report entitles
’CROP RECOMMENDATION SYSTEM USING ML ALGORITHMS’
Submitted by
Mr. Shaikh Moin Ansar Exam No : B190504259
Mr. Dange Aniket Machhindra Exam No : B190504215
Miss. Salve Dnyaneshwari Anil Exam No : B190504257
Miss. Kaklij Rutuja Devidas Exam No : B190504232

are bonafide student of this institute and the work has been carried out by them under the su-
pervision of Prof.Sonawane M.J. and it is approved for the partial fulfillment of the requirement of
Savitribai Phule Pune University, for the award of the degree of Bachelor of Engineering (Computer
Engineering).

(Prof.Sonawane M.J.) (Prof. Daund R.P.)

Project Guide Head of Department

(Dr.Yadav D.M.)
Principle

Internal Examiner External Examiner

Place:
Date:
 ACKNOWLEDGEMENT

It gives us great pleasure in presenting the project report on ”CROP RECOMMENDATION

SYSTEM USING ML ALGORITHMS”

We would like to take this opportunity to thank our internal guide Prof. Sonawane M.J. for giving
us all the help and guidance we needed. So really grateful to him for their kind support. Their valuable
suggestions were very helpful.

We are thankful to our Head of Department Prof. Daund R.P. for providing various resources
such as laboratory with all needed software platforms, continuous internet connection, for our project.
Beside we are thankful to Dr. Yadav D.M. Principal of our college and management.

We would like to extend our sincere thanks to our family members. It is privilege to acknowledge
their cooperation during the course of this dissertation. We express our heartiest thanks to our known
and unknown well-wishers for their unreserved cooperation, encouragement and suggestions during
the course of this dissertation report.

We would like to thanks to our all teachers, and all our friends who helped with the ever daunting
task of gathering information for the dissertation.

MR.SHAIKH MOIN ANSAR

MR. DANGE ANIKET MACHHINDRA
MISS. SALVE DNYANESHWARI ANIL
MISS. KAKLIJ RUTUJA DEVIDAS

I
 ABSTRACT

In the world of developing technologies, the success of sharing information will help the agriculturists
in realizing and developing their eventuality. The information sharing is that the precious and timely
information is being shared between agriculturists, either formally or informally. The amenability of
information sharing refers to the open station among agriculturists. This open station determines the
degree and compass of information sharing. Using web- technologies like html and CSS we make the
web operation; we produce dataset by gathering data from multiple resources and place them in place
which is used to predict the price of the crop and results are vanquished tenon-direct test subsequently
priorities are set, and rankings are given to the list of crops. Place information in our operation and
share that information to agriculturists whose data is collected and stored in the MySQL. we use
software to automatically shoot the streamlined information to the agriculturists in the form of text
communication. So that agronomists no need to go to near- by cosmopolises and cosmopolises to
know the streamlined information.

We will be machine knowledge algorithms to predict the price of the crop for the coming two
months. For prophecy purpose we will be using Support vector machine (SVM), Naı̈ve Baye’s (NB)
and K- Nearest Neighbour (KNN) algorithms to predict the cost of the crop product. further, a
ranking process is applied for decision making in order to handpick the classifiers results. Crop
recommendation systems have gained significant attention in recent times due to their capability to help
farmers in making informed opinions regarding crop selection and optimization. This report reviews
the pivotal generalities, ways, challenges, and advancements related to ML algorithms employed in crop
recommendation systems. Similarly, it explores different datasets, evaluation metrics, and practical
examples found in the literature to showcase the strengths and weaknesses of intelligent systems.

Keywords: Crop recommendation, humidity, Rainfall, pH, Machine Learning (ML), Random Forest
(RF), Decision Tree (DT), Support Vector Machine (SVM), Logistic Regression (LR), and Naı̈ve Bayes
(NB).

II
 Contents

Acknowledgement I

Abstract II

contents III

List of Figures V

List of Tables VI

1 INTRODUCTION 1
1.1 Significance of Technology in Modern Agriculture . . . . . . . . . . . . . . . . . . 3
1.2 The Need for Integrated Systems and Crop Recommendation in Sustainable Farming 3
1.3 Scope and Objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4

2 LITERATURE SURVEY 5
2.1 Existing System . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7

3 PROPOSED SYSTEM AND REQUIREMENT SPECIFICATION 8

3.1 PROPOSED SYSTEM: . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
3.1.1 Flow of the Proposed System . . . . . . . . . . . . . . . . . . . . . . . . . . 9
3.2 Requirement Specification . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
3.2.1 Functional Requirements: . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
3.2.2 Non-Functional Requirements: . . . . . . . . . . . . . . . . . . . . . . . . . 12

4 SYSTEM DESIGN 14
4.1 System Architecture . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
4.2 Flow Chart: . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
4.3 Data Flow Diagram (DFD): . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
4.4 Class Diagram: . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
4.5 Use Case Diagram: . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17

III
 4.6 Activity Diagram: . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18

5 IMPLEMENTATION 20
5.1 Overview of Project: . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20
5.2 Tools and Techniques Used: . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20
5.3 Algorithms: . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21

6 SOFTWARE TESTING 22
6.1 Types of testing: . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22
6.2 Test cases: . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23
6.3 Test results: . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23

7 RESULTS 25

8 APPLICATION 29

9 CONCLUSION 31

A 32
A.1 Paper published details . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 32
A.2 Certificates . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33
A.2.1 Certificates of group members: . . . . . . . . . . . . . . . . . . . . . . . . . 33

B 37
B.1 National Level Project Competition Certificates: . . . . . . . . . . . . . . . . . . . . 37
B.1.1 SND College Of Engineering Research Center, Yeola: IDEA HACKATHON 37
B.1.2 SND College Of Engineering Research Center, Yeola: TECHFUSION . . . 40

C 43
C.1 Plagiarism report of published paper . . . . . . . . . . . . . . . . . . . . . . . . . . 43

D 44
D.1 Information of group members: . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 44
D.1.1 Member 1: . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 44
D.1.2 Member 2: . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 45
D.1.3 Member 3: . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 46
D.1.4 Member 4: . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 47

References 47

IV
 List of Figures

2.1 Existing System . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7

3.1 Block Diagram of Overall Methodology of Proposed System . . . . . . . . . . . . . 8

3.2 Proposed System Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10

4.1 System Architecture . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14

4.2 Flow-Chart . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
4.3 Data Flow Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
4.4 Class Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18
4.5 Use Case Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
4.6 Activity Diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19

7.1 UI of Websites . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25
7.2 Adding farm details for crop . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26
7.3 Recommended crop . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26
7.4 Adding farm details for fertilizers . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27
7.5 Recommended fertilizers . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27
7.6 Upload disease plant image . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28
7.7 Predicted disease . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28

V
 List of Tables

3.1 Hardware Requirements . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13

3.2 Software Requirements . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13

A.1 Paper published details . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 32

C.1 Plagiarism report . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 43

VI
 Chapter 1

INTRODUCTION

Agriculture is a significant area for the Indian frugality and mortal survival. It’s one of the primary
occupations which is essential for mortal life. It likewise contributes a huge part to our day- to- day life.
In utmost cases, growers commit self-murder due to product loss because they aren’t suitable to pay
the bank loans taking for tilling purposes. We’ve noticed in present times that the climate is changing
persistently which is dangerous to the crops and leading growers towards debts and self-murder. These
pitfalls can be minimized when colorful fine or statistical styles are applied to data and by using these
styles, we can recommend the stylish crop to the planter for his agrarian land so that it helps him to get
maximum profit.

In India moment, husbandry has made significant advancements. Precision husbandry’s secret
armament is” area-specific” civilization. Although advancements have been made, there are still some
problems with perfection civilization. Crop recommendations are significantly told by perfection
husbandry. Crop recommendations are determined by a variety of factors. Precision agriculture
focuses on relating these parameters in an area-specific way to identify issues. Not all the results given
by perfection Farming are correct to affect but in Farming, it’s significant to have accurate and precise
recommendations because in case of crimes it may lead to heavy material and capital loss. numerous
exploration workshop are being carried out, to attain an accurate and more effective model for crop
vaccination.

Machine learning focuses on the algorithm like supervised, unsupervised, and underpinning literacy
and each of them has its advantages and disadvantages. Supervised learning the algorithm assembles
a fine model from a set of data that contains both the inputs and the asked labors. An unsupervised
literacy the algorithm constructs a fine model from a set of data that contains only inputs and no wanted
affair markers. Semi-supervised literacy- algorithms expand fine models from deficient training data,
where a portion of the sample input does not have markers.

SND COE RC, Department of Computer Engineering, 2023-24 1

 This paper aims to recommend the most suitable crop grounded on input parameters like Nitrogen(
N), Phosphorous( P), Potassium( K), PH value of soil, moisture, Temperature, and downfall. This
paper predicts the delicacy of the unborn product of twenty- two different crops similar as rice, sludge,
chickpea, order sap, chump peas, moth sap, mung bean, black gram, lentil, pomegranate, banana,
mango, grapes, watermelon, muskmelon, apple, orange, papaya, coconut, cotton, jute, and coffee
crops using colorful supervised machine literacy approaches in of India and recommends the most
suitable crop. The dataset contains colorful parameters like Nitrogen( N), Phosphorous( P), Potassium(
K), PH value of soil, moisture, Temperature, and Rainfall. This proposed system applied different kinds
of Machine Learning algorithms like Decision Tree( DT), Support Vector Machine( SVM), Logistic
Retrogression ( LR), and Gaussian Naı̈ve Bayes( GNB).

Husbandry is the backbone of the country. It’s continuing to be one of the major sources of income
for a significant portion of the population in India, sustaining livelihoods and contributing to profitable
growth. further than 50 of the people depend on husbandry. further than 60 of the land in the country
is used for husbandry to serve the requirements of1.3 billion people( 15). A many decades ago, people
used to do husbandry by using ancient tools. But now, after the Green Revolution, and globalization,
advanced technology has come. High yielding kinds of food grains and vegetables have also been
constructed which has led to lesser growth of husbandry in India. Our country, India is the world’s
largest patron of fresh fruits, vegetables, and food grains. For all these correct nutrients of soils, rainfall
cast, and enough water is essential for the civilization of crops. For husbandry we bear water which
does not contain high quantities of swab. Water is a ubiquitous resource that covers an astonishing
71 of the Earth’s face. But only0.3 of the earth’s face has fresh water. So, numerous people follow
numerous ways to conserve the rainwater. We’ve colorful kinds of land water coffers similar as gutters,
lakes, ponds, and groundwater coffers similar as wells, bore wells etc. Grounded on records from the
former times of 2018 and 2019, it can be estimated that there were approx. 145 million landholdings
in India( 9). It results into negative impacts like planter self-murders, diversion of agrarian land for
non-agricultural purpose. On the other hand, 48 of growers do not want their coming generation to take
care of their husbandry and its land, rather want to settle down in civic areas( 3). The reasons behind
doing this dreadful act are wrong opinions about the crop selection like selection of a crop that will
not give important yield for the soil, planting in the wrong season, and so on. growers can be in a great
loss if they don’t know the former status of the land. If the family primarily depends on husbandry
for the major source of income, also it’s veritably delicate to survive. So, to address these problems,
a Crop Recommendation System has been proposed for growers which provides prophetic perceptive
on crop sustainability and recommendations grounded on Machine literacy models trained. It’s done
by considering essential environmental parameters similar as downfall, temperature, and geographical
position, soil parameters similar as Nitrogen( N), Phosphorus( P) and Potassium( K).

SND COE RC, Department of Computer Engineering, 2023-24 2

 By considering all the below parameters, a suitable crop will be prognosticated to the planter for
their land. colorful experimenters have proposed their own Crop Recommendation System by using
different Machine literacy and Deep literacy algorithms. Some of the algorithms used for erecting Crop
Recommendation Systems are Random Forest algorithm, Decision Tree algorithms, K- NN, Neural
Network, Linear and Logistic Regression algorithms, SVR, Lasso and Ridge Regression algorithms.

1.1 Significance of Technology in Modern Agriculture

The agricultural sector is no stranger to the waves of innovation that have swept across various
industries over the past few decades. However, the importance of technology in agriculture has taken
on new dimensions in recent years. The adoption of cutting-edge technologies has redefined farming
practices, ushering in an era of precision and sustainability. Advanced technologies are not merely
a choice for modern farmers but a necessity in addressing the formidable challenges they confront.
The ever-increasing global population, coupled with unpredictable climate patterns and the need to
preserve natural resources, has created an urgency for the integration of technology in agriculture.
This is where integrated crop management systems and disease detection come into play, as they offer
solutions that bridge the gap between agricultural demands and sustainable practices.

1.2 The Need for Integrated Systems and Crop Recommendation in Sustainable
Farming

One of the central challenges facing agriculture is the need to balance increased food production
with sustainability. As the world struggle with climate change and dwindling natural resources, the
agricultural sector is compelled to adapt and adopt innovative approaches which not only increase crop
yields but also protect the environment. Integrated crop management systems stand at the forefront of
this transformation. These systems combine a variety of technologies and data-driven approaches to
optimize farming practices. By managing resources efficiently and minimizing waste, they hold the
potential to enhance productivity while reducing the environmental impact of agriculture.

Additionally, the survey examines the critical aspect of disease detection in the context of sustainable
farming. Plant’s diseases pose a significant threat to global food security, leading to substantial yield
losses. Timely detection and management of crop diseases are crucial for maintaining sustainable
agricultural practices. Advanced technologies, particularly in the field of disease detection, are paving
the way for early identification and targeted interventions to mitigate the impact of plant diseases on
crops

SND COE RC, Department of Computer Engineering, 2023-24 3

1.3 Scope and Objectives

The main objective of the survey is to provide a comprehensive overview of advancements in

integrated crop management systems and disease detection technologies, exploring their significance
and applications in the context of sustainable agriculture.
To achieve this, the survey will:

• Review and analyse recent research and developments in integrated crop management systems,
emphasizing their impact on sustainable agriculture.

• Examine the latest breakthroughs in technology-based disease detection methods, with a focus
on their role in crop protection and yield optimization.

• Identify common themes, challenges, and trends in the integration of technology into agriculture.

• Offer insights into the implications and future prospects of technology-driven agricultural prac-
tices.

• In the following sections, we will explore in detail the various facets of integrated crop man-
agement systems, cutting-edge disease detection techniques, and their combined impact on
sustainable farming

SND COE RC, Department of Computer Engineering, 2023-24 4

 Chapter 2

LITERATURE SURVEY

In the literature review of this project, team sought out and studied various patents, research
papers, documents, and newspapers and magazine articles from various scenes. The paper states
requirements and why they tend to move into precision agriculture which is due to globalization are
discussed. Precision agriculture is site-specific farming. Though Precision agriculture has shown an
improvement with the time, there exists some issues. As mentioned above site specific methods of
such systems are needed to be supervised to get an improved result. Only a some of the outcomes are
provided a particular result. Nevertheless, the situation is farming is indispensable since if any default
or a mistake occurs, it might lead to serious damage to resources and as well as the plants. In this
research, it is proposing a system where the major factors are taken into consideration at same time
and come up with a solution so that a system will not be complicated for the user. As mentioned above
in the sentence, the major factors taken into consideration at once is unlike other models proposed in
last researchers, this system considers all the major factors which are essential for plant growth, are
processed together using various algorithms whereas the other models consider only parameters at
once keeping the other factors constant.

As an example, some tests are carried out to find the rate evaporation and how the plant growth is
affected when there’s no sufficient water present. And a derived equation is presented as a result:
ETo = K pan × E pan
Where,
ETo: reference crop transportation.
Kpan: pan coefficient
E pan: pan evaporation.

Even though an equation is proposed, there are few limitations. Mainly this could be done only for
a land with a minimum area. This is not suitable for commercialization as the profit will be low when
you use less area for cultivation. The next limitation is the average rainfall of SriLanka mostly suitable

SND COE RC, Department of Computer Engineering, 2023-24 5

for multiple crop types to grow without any lack of elements. Therefore, water level alone itself is not
a large issue whereas other factors are. If there’s enough water for plants but no temperature that would
be a problem because the mostly environmental factors have a equal relationship with each other in
plant growth.

The ultimate thing of the former inquiries is also to prognosticate the stylish crop type. But once
the planter or stoner has cultivated the prognosticated crop type, the system’s job is done. But in the
system that proposed from this paper, has a feedback system as well. Indeed after suggesting the stylish
crop type, the system can track the factory growth and it provides feedback if the ranch is glutted. So
that the stoner can take necessary preventives previous.

Rakesh Shirsath and other co-author in paper(1) proposed a system which helps the druggies to make
opinions regarding the crop to be planted. The system used is a subscription- grounded system which
would have substantiated information of every planter registered. The system includes a module which
maintains the information of the former crops planted collected from colorful sources and shows a
matching crop that can be planted. The whole process is done with the help of artificial neutral
networks. At the end a feedback system is handed so that the inventor can make changes needed if the
planter finds some difficulty while using the system.

The system in paper(4) suggested by authorsS. Pudumalar and associated co-authors uses an ensem-
ble fashion called Majority Voting fashion which combines the power of multiple models to achieve
lesser vaccination delicacy. The styles used are Random Trees, KNN, and Naı̈ve Bayes for ensemble so
that indeed if one system predicts inaptly, the other models are likely to make correct prognostications
and since the maturity voting fashion is used, the final vaccination is correct one. If- also rules are the
main factors which are used in the vaccination process. The delicacy attained is 88 using the ensemble
model.

In Reference(1), This paper proposed a system named Crop Selection Method( CSM) to break crop
selection problem, and maximize net yield rate of crop over season and latterly achieves maximum
profitable growth of the country. The proposed system may ameliorate net yield rate of crops.

In Reference(2), This paper, proposed and enforced an intelligent crop recommendation system,
which can be fluently used by growers each over India. This system would help the growers in
making an informed decision about which crop to grow depending on a variety of environmental
and geographical factors. We’ve also enforced a secondary system, called Rainfall Predictor, which
predicts the downfall of the coming 12 months.

SND COE RC, Department of Computer Engineering, 2023-24 6

 In Reference(3), This paper contains about the exploration and the structure of an effective agrarian
yield soothsaying system grounded on real-time yearly rainfall. It’s delicate to prognosticate the
agrarian crop product because of the abnormal rainfall that happens every time and rapid-fire indigenous
climate change due to global warming. The development of agrarian yield soothsaying system that
leverages real- time rainfall in conformation is urgently needed. In this exploration, we cover how to
reuse the number of rainfall data( monthly, daily) and how to configure the vaticination system. We
establish a non- parametric statistical model on the base of 33 times of agrarian rainfall information.
According to the enforced model, we prognosticate final product using the yearly rainfall information.
This paper contains the results of the imitation.

In Reference( 4), This paper, proposes a recommendation system through an ensemble model with
maturity voting fashion using Random tree, CHAID, K- Nearest Neighbor and Naive Bayes as learners
to recommend a crop for the point specific with high delicacy and effectiveness parameters.

2.1 Existing System

Figure 2.1: Existing System

The system shown in figure uses an ensemble model which gathers the vaticination from every
model mentioned Random Tree, KNN and Naive Bayes and uses a maturity voting fashion which will
help to make accurate prognostications indeed if one algorithm fails to make the correct vaticination.
Advanced the competition, advanced is the chance of getting a correct affair(4). Hence, choosing the
models to be used for ensemble has to be done considering the delicacy and results attained from the
models. If- also rules are generated by the Random Forest models. They’re fed to the recommendation
machine and the stylish set of rules are given as recommendation.

SND COE RC, Department of Computer Engineering, 2023-24 7

 Chapter 3

PROPOSED SYSTEM AND REQUIREMENT SPECIFICATION

3.1 PROPOSED SYSTEM:

Figure 3.1: Block Diagram of Overall Methodology of Proposed System

In our frame, we’ve proposed a procedure that’s separated into colorful stages as appeared in
Figure3.1.
The six phases are as per the following

1. Collection of Datasets

2. Pre-processing(Noise Junking)

3. Feature Extraction

4. Applied Machine Learning Algorithm

5. Recommendation System

6. Recommended Crop

SND COE RC, Department of Computer Engineering, 2023-24 8

3.1.1 Flow of the Proposed System

As demonstrated in the figure, the methodology to prize the sentiment contains the several way that
are described below:

1. Data Collection:
The dataset consists of parameters like Nitrogen( N), Phosphorous( P), Potassium( K), PH value
of soil, moisture, Temperature and downfall. The datasets have been attained from the Kaggle
website. The data set has 2200 case or data that have taken from the once major data. The dataset
includes 22 different crops similar as rice, sludge, chickpea, order sap, chump peas, moth sap,
mung bean, Black gram, lentil, pomegranate, banana, mango, grapes, watermelon, muskmelon,
apple, orange, papaya, coconut, cotton, jute, beetroot and coffee. The dataset is separated in
Train and Test sets in which 80 of the whole dataset is taken as Train and 20 as Test dataset.

2. Pre-Processing( Noise Junking):

For the successful operational-processing is needed. The data which is acquired from different
coffers are eventually in raw form. It may contain some deficient, spare, inconsistent data. thus,
in this step similar spare data should be filtered. Data should be regularized. We also use turbo
and Power BI to remove peak/ downfall, original min- maximum, outliers, and junk values.

3. Feature Extraction:
This step is focus on relating and using most applicable trait from the dataset. Through this
process inapplicable and spare information is removed for the operation of classifiers.

4. Applied Machine Learning Algorithm:

Our crop recommendation system utilizes applied machine learning algorithms to assist farmers
in making informed decisions. By gathering data on factors such as humidity, rainfall, and pH,
we employ algorithms like Support Vector Machine (SVM), Naı̈ve Bayes (NB), and K-Nearest
Neighbour (KNN) to predict crop prices for the upcoming two months. Further, we employ
techniques such as Random Forest (RF), Decision Tree (DT), and Logistic Regression (LR) for
prioritizing crop recommendations. This system automates the delivery of insights to farmers,
enhancing their decision-making process and optimizing crop selection.

5. Recommendation System:
Our project focuses on developing a recommendation system for crop selection using machine
learning (ML) algorithms. Leveraging data on factors like humidity, rainfall, and pH, we employ
ML algorithms such as Support Vector Machine (SVM), Naı̈ve Bayes (NB), and K-Nearest
Neighbour (KNN) to predict crop prices for the upcoming two months. Additionally, techniques

SND COE RC, Department of Computer Engineering, 2023-24 9

 like Random Forest (RF), Decision Tree (DT), and Logistic Regression (LR) are utilized for
prioritizing crop recommendations based on the gathered data. The system automates the
delivery of tailored recommendations to farmers, aiding them in making informed decisions and
optimizing their crop selections for better yields.

6. Recommended Crop
Our project aims to develop a crop recommendation system using machine learning (ML)
algorithms. By analyzing data on various factors like soil type, climate conditions, and historical
crop yields, we employ ML algorithms such as Support Vector Machine (SVM), Naı̈ve Bayes
(NB), and K-Nearest Neighbour (KNN) to recommend the most suitable crops for a given area.
Additionally, techniques like Random Forest (RF), Decision Tree (DT), and Logistic Regression
(LR) are used to refine the recommendations based on factors such as market demand and
profitability. The system aims to provide farmers with tailored recommendations to optimize
crop selection and maximize yields, ultimately contributing to sustainable agriculture practices
and improved livelihoods.

Figure 3.2: Proposed System Diagram

Crop recommendation system using ML algorithms is a complex task that can involve numerous
interactions and steps. However, I can provide a simplified sequence diagram that outlines the general
flow of interactions between system components and users. The actual system interactions may vary
depending on the specific implementation.

SND COE RC, Department of Computer Engineering, 2023-24 10

 Here’s a brief explanation of the interactions in the diagram:

• The user enters data into the system, which includes information about their location, soil quality,
historical data, and preferences.

• The user requests crop recommendations based on the entered data.

• The system pre-processes the data, which may involve data cleaning and transformation.

• The system applies various algorithms like KNN, Random-forest, Decision tree etc. to extract
relevant features from the data.

• The system provides the user with crop recommendations based on the pre-processed data and
ML algorithms.

This is a simplified representation, and a real-world system may involve more complex interactions,
multiple iterations, and feedback loops to improve recommendations over time.

In this project, we have proposed a model that addresses the existing issues. The novelty of the
proposed system is to guide the farmers to maximize the crop yield as well as suggest the most
profitable crop for the specific region. The proposed model provides crop selection based on economic
and environmental conditions, and benefit to maximize the crop yield that will subsequently help to
meet the increasing demand for the country’s food supplies. The proposed system predicts the crop
yield by studying factors such as State, District, area, season. The system also helps to determine the
best time to use fertilizers. The user provides a State, District, Season, Crop and Area as inputs for
Production. The user provides a State, District, Season and Area as inputs for Crop Recommendation.
According to the requirement, the model predicts the crop yield for a specific crop. The model also
recommends the most profitable crop and suggests the right time to use the fertilizers. The main
objective is to obtain a better variety of crops that can be grown over the season. The proposed system
would help to minimize the difficulties faced by farmers in choosing a crop and maximize the yield.

In regions with fluctuating climatic conditions, traditional farming methods struggle to optimize
crop growth. Leveraging technology is crucial to gather and analyze data on weather patterns, guiding
farmers for better crop management. Fertilizer usage is pivotal; excessive application can deplete
soil fertility, impacting yields. Temperature data is especially vital for India, driving its economy
through crop predictions. Our proposed AI model, utilizing data mining techniques, aids farmers
in decision-making, surpassing outdated methods. It suggests crop selection based on economic and
environmental factors, optimizing yield and meeting food demand. Additionally, it advises on fertilizer
timing, ensuring efficient usage.

SND COE RC, Department of Computer Engineering, 2023-24 11

3.2 Requirement Specification

3.2.1 Functional Requirements:

Functional requirements are those that give examples of how the system works inside and describe
how each subsystem works. It covers the job the system is supposed to execute, the steps necessary,
the information the system is supposed to keep, and the user interfaces. Data analysis and cleansing
technique is applied to make the raw data into processing data. The data collected is subject to machine
learning system along with run time analysis it makes an efficient crop value updating system. The
Usage of Ensemble of classifiers makes the model more robust and efficient.

3.2.2 Non-Functional Requirements:

Availability: A crop recommendation system leveraging ML algorithms is available, utilizing predic-

tive models trained on historical agricultural data. It considers factors such as soil quality, climate,
and crop yield patterns to provide personalized suggestions for optimal crop selection, enhancing
agricultural productivity.
Reliability: The reliability of a crop recommendation system using ML algorithms depends on the
quality and quantity of input data, the appropriateness of the chosen machine learning models, and the
system’s ability to adapt to dynamic environmental factors. Regular updates, validation against real-
world conditions, and user feedback contribute to enhancing the system’s accuracy and dependability
in providing optimal crop recommendations.
Scalability: For a crop recommendation system using ML algorithms refers to the system’s ability to
efficiently handle increasing amounts of data and user requests as the size of the system grows.
Accessibility: Implementing accessibility for a crop recommendation system involves designing a
user-friendly interface compatible with screen readers and ensuring keyboard navigation. Utilize
text-to-speech functionality for auditory feedback, adhere to high contrast colour schemes for visual
impairment, and provide adjustable font sizes. Implement a seamless integration with popular plat-
forms and devices for broader accessibility. Regularly test the system with diverse user groups to
address specific needs and continually improve accessibility features.
Maintainability: The system should be built and coded in a way which is easily readable and main-
tainable. The database is automatically updated when a reservation is made or a new user is created.
Every time a new reservation or registration is made, the system need to be able to immediately update
the database without any further administrative work. This web application will allow the user to do
various things such as:

• Farmers can see the crop information from their area.

• Farmers can post their own cultivating crop information.

SND COE RC, Department of Computer Engineering, 2023-24 12

• This web application will ease the process of selecting good crop for cultivation.

Requirements Specification
Smartphone Android
Android i5 Processor based or higher
Hard Drive 40 GB

Table 3.1: Hardware Requirements

Requirements Specification
Operating System Windows 10
Anaconda/Git software Version: 2.3.2/2.42.0
Python Version: 3.10.0
MySQL Version: 8.0.35

Table 3.2: Software Requirements

SND COE RC, Department of Computer Engineering, 2023-24 13

 Chapter 4

SYSTEM DESIGN

4.1 System Architecture

Figure 4.1: System Architecture

The armature illustration represents the overall design of the design. After taking the position as
input from the stoner, the data get reused using soil attributes and rainfall attributes that includes crop
details and all other trained data and eventually the affair that has maximum yield will be given to
the stoner. This armature ensures a flawless inflow from data ingestion to stoner commerce, easing
effective crop recommendations and iterative model enhancement. The data inflow of the system
armature is as follow:

• User: The user interface in the system armature serves as the entry point for growers to input
applicable data similar as soil characteristics and geographical position. This stoner- handed

SND COE RC, Department of Computer Engineering, 2023-24 14

 information is also reused through machine literacy algorithms, generating substantiated crop
recommendations. The intuitive design of the stoner interface ensures availability and ease of
commerce for growers seeking optimized agrarian opinions.

• User Interface: The user interface element in the crop recommendation system facilitates
flawless commerce between growers and the machine literacy model. It provides an intuitive
platform for growers to input their specific soil and climate conditions, displays substantiated
crop recommendations generated by the ML algorithms, and ensures a user-friendly experience
through clear visualization of results. Integration of stoner feedback mechanisms enhances the
system’s rigidity and usability for agrarian interpreters.

• Dataset: The dataset for the crop recommendation system includes comprehensive information
on soil attributes, climate conditions, and literal crop performance. It encompasses variables
similar as soil pH, temperature, rush, and crop yield, furnishing a rich source for training machine
literacy algorithms to make accurate crop recommendations.

• Data Pre-processing: In the data pre-processing stage of the crop recommendation system,
raw datasets suffer drawing to handle missing values and outliers. point scaling is applied to
homogenize variables, icing harmonious influence during model training. Categorical variables
are decoded, and the dataset is resolve into training and testing sets for algorithm training and
evaluation, independently. also, dimensionality reduction ways may be employed to enhance
computational effectiveness. • Algorithms: The system armature incorporates machine literacy
algorithms similar as Decision Trees, Random Forest, SVM, Gaussian NB, LR and K- NN
to assay the dataset and prognosticate suitable crops. Ensemble ways andcross-validation are
employed to enhance the robustness and delicacy of the recommendations, icing rigidity to
different agrarian scripts.

• Recommended System: The recommendation system within the armature employs machine
literacy algorithms like Decision Trees or Random Forest to assay the input dataset and prognosti-
cate suitable crops grounded on soil and climate conditions. The system integrates stoner-friendly
interfaces for growers to input their specific parameters, easing substantiated and optimized crop
recommendations.

• Result Prediction: Result Prediction in the crop recommendation system involves planting
trained machine literacy models to assay stoner- input data, including soil composition and cli-
matic conditions. The system utilizes these inputs to induce substantiated crop recommendations
with associated confidence scores, abetting growers in making informed planting opinions. The
results are presented through a stoner-friendly interface, enhancing availability and usability for
agrarian stakeholders

SND COE RC, Department of Computer Engineering, 2023-24 15

4.2 Flow Chart:

he below flowchart represents the overall inflow of the design. The stoner has to register to the operation
and he’s suitable to login if he’s a registered stoner and if the stoner fails to log- in also it’ll don’t
allow the stoner to use the operation, stoner got abandoned. Once he logins stoner should give crop
information and after getting stoner details the operation checks fordataset.However, also the stoner
gets crop vaticination if not also stoner is suitable to check for other locales and he gets result for the
same, If data is available. At last stoner logs out and the operation stops.

Figure 4.2: Flow-Chart

4.3 Data Flow Diagram (DFD):

The data flow diagram for the crop recommendation system involves data collection, preprocessing,
and flow through the model training and validation stages, leading to the integration of the trained
model into the recommendation system, culminating in system testing and optimization.

SND COE RC, Department of Computer Engineering, 2023-24 16

 Figure 4.3: Data Flow Diagram

4.4 Class Diagram:

The class diagram for the crop recommendation system illustrates the key classes and their attributes
and relationships, capturing entities like given in diagram. These classes collaborate to facilitate data
flow and decision-making processes within the system

4.5 Use Case Diagram:

A use case diagram visually represents the interactions between actors (users or external systems) and
a system, showcasing the various ways users can interact with the system to achieve specific goals. A
use case diagram for the crop recommendation system illustrates actors, such as farmers and the ML
model, interacting with the system to achieve goals like receiving personalized crop recommendations.
The diagram visually represents the relationships and interactions between these actors and the core
functionalities of the recommendation system.

SND COE RC, Department of Computer Engineering, 2023-24 17

 Figure 4.4: Class Diagram

4.6 Activity Diagram:

An activity diagram visually represents the flow of activities within a system or process, illustrating
the sequence of actions and decision points. Activity Diagram for Crop Recommendation System
Using ML Algorithms: Illustrates the flow of activities in the system, including data collection, feature
extraction, model training, validation, integration, and system testing.

SND COE RC, Department of Computer Engineering, 2023-24 18

 Figure 4.5: Use Case Diagram

Figure 4.6: Activity Diagram

SND COE RC, Department of Computer Engineering, 2023-24 19

 Chapter 5

IMPLEMENTATION

5.1 Overview of Project:

The Crop Recommendation System is a project that utilizes machine learning algorithms to suggest
suitable crops to farmers based on various factors such as soil type, climate conditions, and historical
crop yield data. By analyzing these factors, the system aims to optimize crop selection and increase
agricultural productivity. Key components include data collection, preprocessing, algorithm selec-
tion, model training, and deployment. The ultimate goal is to provide farmers with personalized
recommendations to improve their crop yield and profitability.

5.2 Tools and Techniques Used:

• Jupyter Notebooks: It is use for documenting the analysis process and Markdown for creating
documentation.

• Python: Python is commonly used for machine learning projects due to its extensive libraries
like scikit-learn, pandas, and NumPy.

• scikit-learn: Provides a wide range of machine learning algorithms and tools for data prepro-
cessing, model selection, and evaluation.

• TensorFlow or PyTorch: For implementing deep learning models if needed.

• Pandas: For data manipulation and preprocessing tasks like handling missing values, encoding
categorical variables, and scaling numerical features.

• NumPy: For numerical operations and array manipulation.

• OpenCV: If dealing with image data for analysis (e.g., satellite imagery for crop monitoring).

• Matplotlib and Seaborn: For data visualization to understand the distributions, correlations,
and patterns in the data.

SND COE RC, Department of Computer Engineering, 2023-24 20

 • MySQL: For storing and managing the data if required.

5.3 Algorithms:

In this system we applied different Machine Learning algorithms like Random Forest, Decision Tree,
Support Vector Machine (SVM), Logistic Regression (LR), and Gaussian NB, K- NN algorithm.

• Random Forest: Random Forest is an ensemble literacy algorithm that builds multiple decision
trees during training and merges their prognostications. It operates by constructing a multitude
of decision trees at training time and labours the mode of the classes (bracket) or the average
vaticination (retrogression) of the individual trees.

• Decision Tree: Decision tree classifiers use greedy methodology. It’s a supervised literacy
algorithm where attributes and class markers are represented using a tree. The main purpose of
using Decision Tree is to form a training prototype which we can use to prevision class or value
of target variables by learning decision rules derived from former data (training data).

• Support Vector Machine (SVM): Support Vector Machine (SVM) is a supervised machine
learning algorithm or model which can be employed for bracket and as well as for retrogression
challenges. still, we substantially use it in bracket challenges. SVM is generally represented as
training data points in space which is divided into groups by comprehensible gap which is as far
as possible.

• Logistic Regression (LR): The Logistic Regression model is a astronomically used statistical
model that, in its introductory form, uses a logistic function to model a double dependent
variable; numerous further complex extensions live. In Retrogression Examination, Logistic
retrogression is prognosticating the parameters of a logistic model; it’s a form of Binomial
retrogression. Logistic Retrogression is a double bracket algorithm used for prognosticating the
probability of a case belonging to a particular class.

• K-Nearest Neighbors (KNN): is a simple and understandable supervised machine learning

algorithm used for classification and regression tasks. In classification, it assigns a data point to
the majority class among its k nearest neighbors in the feature space. For regression, it predicts
average of the target values of it KNN. The choice of ’k’ is a crucial parameter, impacting
the algorithm’s sensitivity to local variations. KNN is non-parametric, means it doesn’t makes
predictions about the underlying data distribution. It is computationally inexpensive but may
suffer from high dimensionality and requires a meaningful distance metric for accurate results.

SND COE RC, Department of Computer Engineering, 2023-24 21

 Chapter 6

SOFTWARE TESTING

Software testing is a critical process in software development which involves evaluating the quality,
functionality, and performance of a software system. It aims to identify defects, errors, or gaps in the
system to ensure that it meets the desired requirements and delivers a reliable and satisfactory user
experience. Here’s an overview of software testing, including types, test cases, and test results:

6.1 Types of testing:

There are several types of software testing techniques, each serving a specific purpose. Here are some
commonly used types:

• Unit Testing: It focuses on testing individual components or modules of the software to ensure
they function correctly in isolation.

• Integration Testing: It verifies the proper integration and interaction between different modules
or components of the software.

• System Testing: It tests the entire system as a whole to confirm its compliance with specified
requirements and evaluate its behavior in different scenarios.

• Acceptance Testing: It involves testing the software from an end-user’s perspective to ensure it
meets the specified acceptance criteria.

• Regression Testing: It verifies that previously implemented functionalities continue to work as

intended after making changes or adding new features.

• Performance Testing: It evaluates the system’s performance under different workload condi-
tions to determine its responsiveness, scalability, and stability.

• Security Testing: It checks for vulnerabilities and weaknesses in the software system to ensure
its resistance against unauthorized access, data breaches, and attacks.

SND COE RC, Department of Computer Engineering, 2023-24 22

 • Usability Testing: It assesses the software’s user-friendliness, ease of use, and overall user
experience.

6.2 Test cases:

Test cases are specific scenarios or conditions that need to be executed during testing to verify the
software’s behavior. Test cases typically consist of the following elements:

• Test Case ID: A unique identifier for each test case.

• Test Case Description: A detailed description of the test case, including the inputs, actions,
and expected outcomes.

• Test Steps: Step-by-step instructions on how to execute the test case.

• Test Data: The specific data values or inputs required for executing the test case.

• Expected Results: The expected outcomes or behaviors after executing the test case.

• Actual Results: The observed results or behaviors during test execution.

• Pass/Fail Status: The indication of whether the test case passed or failed based on the comparison
between the actual and expected results.

Test cases should cover a wide range of scenarios, including normal and boundary cases, error
conditions, and negative scenarios, to ensure comprehensive testing

6.3 Test results:

Test results provide an overview of the testing process, including the status of each test case and any
defects or issues encountered. The test results typically include the following information:

• Test Case ID: The unique identifier of the test case.

• Test Case Description: A brief description of the test case.

• Test Status: The pass/fail status of the test case.

• Defects: Any defects or issues discovered during the test case execution.

• Severity: The level of impact or criticality associated with each defect.

• Priority: The order in which defects should be resolved based on their importance.

SND COE RC, Department of Computer Engineering, 2023-24 23

 • Comments/Notes: Additional comments or observations related to the test case.

Test results provide valuable insights into the software’s quality, helping developers and stakeholders
identify areas for improvement, prioritize bug fixes, and make informed decisions regarding the
software’s readiness for release.

SND COE RC, Department of Computer Engineering, 2023-24 24

 Chapter 7

RESULTS

After using different machine algorithms for predicting crops, we have come with the following results:

Figure 7.1: UI of Websites

SND COE RC, Department of Computer Engineering, 2023-24 25

 Figure 7.2: Adding farm details for crop

Figure 7.3: Recommended crop

SND COE RC, Department of Computer Engineering, 2023-24 26

 Figure 7.4: Adding farm details for fertilizers

Figure 7.5: Recommended fertilizers

SND COE RC, Department of Computer Engineering, 2023-24 27

 Figure 7.6: Upload disease plant image

Figure 7.7: Predicted disease

SND COE RC, Department of Computer Engineering, 2023-24 28

 Chapter 8

APPLICATION

Crop recommendation systems using ML algorithms find applications in precision agriculture, aiding
farmers in optimal crop selection based on environmental and soil conditions. Here are specific
applications of crop recommendation systems using ML algorithms:

• Availability: A crop recommendation system leveraging ML algorithms is available, utilizing

predictive models trained on historical agricultural data. It considers factors such as soil quality,
climate, and crop yield patterns to provide personalized suggestions for optimal crop selection,
enhancing agricultural productivity.

• Reliability: The reliability of a crop recommendation system using ML algorithms depends

on the quality and quantity of input data, the appropriateness of the chosen machine learning
models, and the system’s ability to adapt to dynamic environmental factors. Regular updates,
validation against real-world conditions, and user feedback contribute to enhancing the system’s
accuracy and dependability in providing optimal crop recommendations.

• Scalability: For a crop recommendation system using ML algorithms refers to the system’s
ability to efficiently handle increasing amounts of data and user requests as the size of the system
grows.

• Accessibility: Implementing accessibility for a crop recommendation system involves designing

a user-friendly interface compatible with screen readers and ensuring keyboard navigation.
Utilize text-to-speech functionality for auditory feedback, adhere to high contrast colour schemes
for visual impairment, and provide adjustable font sizes. Implement a seamless integration with
popular platforms and devices for broader accessibility. Regularly test the system with diverse
user groups to address specific needs and continually improve accessibility features.

• Maintainability: The system should be built and coded in a way which is easily readable and
maintainable. The database is automatically updated when a reservation is made or a new user
is created. Every time a new reservation or registration is made, the system need to be able to

SND COE RC, Department of Computer Engineering, 2023-24 29

 immediately update the database without any further administrative work. This web application
will allow the user to do various things such as:
• Farmers can see the crop information from their area.
• Farmers can post their own cultivating crop information.
• This web application will ease the process of selecting good crop for cultivation.

• Usability: The crop recommendation system using ML algorithms enhances agricultural pro-
ductivity by providing data-driven, personalized crop suggestions based on soil and climate
conditions. It streamlines decision-making for farmers, optimizing resource utilization and
fostering sustainable agricultural practices.

• Precision Agriculture: ML-based crop recommendation systems enhance precision farming

by providing tailored advice on crop selection, optimizing resource allocation, and improving
overall yield.

• Resource Optimization: Efficient use of resources such as water, fertilizers, and pesticides are
achieved through ML algorithms, minimizing waste and environmental impact.

• Sustainable Farming: ML-driven recommendations contribute to sustainable agricultural prac-

tices by promoting crop diversity, minimizing environmental impact, and optimizing land usage.

• Climate Resilience: ML algorithms help farmers adapt to changing climate conditions by

recommending crops that are better suited to prevailing environmental factors.

• Cost Efficiency: The cost efficiency of a crop recommendation system using ML algorithms
lies in optimized resource allocation, reduced input wastage, and improved yield prediction. By
leveraging machine learning, it minimizes the cost of trial-and-error in crop selection, enhances
resource utilization, and ultimately maximizes returns for farmers.

• Time Efficiency: The time efficiency of the crop recommendation system using ML algorithms
is notable, as it swiftly processes input data to deliver timely and accurate crop suggestions,
optimizing decision-making for farmers.

SND COE RC, Department of Computer Engineering, 2023-24 30

 Chapter 9

CONCLUSION

The implementation of a Crop Recommendation System (CRS) using Machine Learning (ML)
algorithms holds immense promise for modern agriculture. By leveraging data from various sources,
ML algorithms can provide farmers with tailored crop recommendations, enhancing productivity,
sustainability, and economic outcomes. These recommendations empower farmers to optimize resource
allocation and mitigate risks, contributing to efficient land and resource use. The adaptability of ML
algorithms allows CRS to continuously improve, incorporating real-time data and user feedback. Future
innovations such as IoT integration and advanced AI techniques can further enhance the accuracy and
applicability of CRS, addressing the challenges of sustainable agriculture and climate change. In
essence, the synergy between ML algorithms and agriculture offers a transformative opportunity for a
resilient, sustainable, and productive agricultural future.

SND COE RC, Department of Computer Engineering, 2023-24 31

 Appendix A

A.1 Paper published details

Sr.No Name of Conference / National or International ISSN No. Month-Year

Journal
1. Crop Recommendation International 2320-2882 April 2024
System Using ML Al-
gorithms

Table A.1: Paper published details

SND COE RC, Department of Computer Engineering, 2023-24 32

A.2 Certificates

A.2.1 Certificates of group members:

SND COE RC, Department of Computer Engineering, 2023-24 33

SND COE RC, Department of Computer Engineering, 2023-24 34
SND COE RC, Department of Computer Engineering, 2023-24 35
SND COE RC, Department of Computer Engineering, 2023-24 36
 Appendix B

B.1 National Level Project Competition Certificates:

B.1.1 SND College Of Engineering Research Center, Yeola: IDEA HACKATHON

SND COE RC, Department of Computer Engineering, 2023-24 37

SND COE RC, Department of Computer Engineering, 2023-24 38
SND COE RC, Department of Computer Engineering, 2023-24 39
B.1.2 SND College Of Engineering Research Center, Yeola: TECHFUSION

SND COE RC, Department of Computer Engineering, 2023-24 40

SND COE RC, Department of Computer Engineering, 2023-24 41
SND COE RC, Department of Computer Engineering, 2023-24 42
 Appendix C

C.1 Plagiarism report of published paper

Sr.No Chapter Name Unique Plagiarism

1. Abstract 3% 97%
2. Introduction 11% 89%
3. Proposed system 9% 91%
4. Design and architecture 9% 91%
5. Implementation 4% 96%

Table C.1: Plagiarism report

SND COE RC, Department of Computer Engineering, 2023-24 43

 Appendix D

D.1 Information of group members:

D.1.1 Member 1:

• Name: Mr. Shaikh Moin Ansar

• DOB: 28-Feb-2002
• E-mail: shaikhmoin7968@gmail.com
• Paper Published: IJCRT(Crop Recommendation System Using ML Algorithms)

SND COE RC, Department of Computer Engineering, 2023-24 44

D.1.2 Member 2:

• Name: Mr. Dange Aniket Machhindra

• DOB: 4-Dec-2002
• E-mail: aniketmdange100@gmail.com
• Paper Published: IJCRT(Crop Recommendation System Using ML Algorithms)

SND COE RC, Department of Computer Engineering, 2023-24 45

D.1.3 Member 3:

• Name: Miss. Salve Dnyaneshwari Anil

• DOB: 15-June-2001
• E-mail: dnyaneshwarisalve1506@gmail.com
• Paper Published: IJCRT(Crop Recommendation System Using ML Algorithms)

SND COE RC, Department of Computer Engineering, 2023-24 46

D.1.4 Member 4:

• Name: Miss. Kaklij Rutuja Devidas

• DOB: 25-Sep-2001
• E-mail: kaklijr25@gmail.com
• Paper Published: IJCRT(Crop Recommendation System Using ML Algorithms)

SND COE RC, Department of Computer Engineering, 2023-24 47

 References

[1] Crop Recommendation Using Machine Learning Algorithms 2023 by Prashant Kumar, Keshav
bhagat, Kusum Lata, Sushant Jhingran.

[2] 2023 International Conférence on Disruptive Technologies (ICDT) — ©2023 IEEE — DOI:
10.1109/ICDT57929.2023.10151325.

[3] Crop Recommendation using Machine Learning and Plant Disease Identification using CNN and
TransferLearning Approach 2022 by Shivesh Tiwari, Somesh Kumar, Sunil Tyagi, Minakshi Ponia.

[4] Crop Recommender System Using Machine Learning Approach 2021 by Shilpa Mangesh Pande,
Prem Kumar Ramesh, B. R. Aishwarya, Kumar Shourya.

[5] Crop Recommendation System for Precision agriculture by S. Pudumalar, E. Ramanujam, R.

Harine Rajashreen, C. Kavyan, T. Kiruthikan, J. Nishan.

[6] International Journal for Research in Applied Science Engineering Technology (IJRASET) ISSN:
2321- 9653; IC Value: 45.98; SJ Impact Factor: 7.538 Volume 11 Issue II Feb 2023- Available at
www.ijraset.com.

[7] https://www.kaggle.com/datasets

[8] https://jupyter.org/

[9] https://www.javatpoint.com/machine-learning-algorithms

[10] https://www.geeksforgeeks.org/machine-learning-algorithms/

SND COE RC, Department of Computer Engineering, 2023-24 48