AGRICULTURAL CROPS MANAGEMNET

SYSTEM

A Project Report Submitted

In Partial Fulfillment of the Requirements
For the Degree of

BACHELOR OF TECHNOLOGY
In
Computer Science & Engineering
by

SURAJ YADAV
Roll No. 2101870109011
AMITA JAISWAL
Roll No. 2101870109001
RAJEEV PRAJAPTI
Roll No. 2001870100090

Under the Supervision of

Prof. Dr. Shruti Tripathi
(Assistant Professor of C.S.E Department)

To the
DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING

FEROZE GANDHI INSTITUTE OF ENGINEERING

&TECHNOLOGY, RAEBARELI
(Affiliated to Dr. A.P.J. Abdul Kalam Technical University, Lucknow)

MAY, 2024
 CERTIFICATE
This is to certify that the project report entitles

AGRICULTURAL CROPS MANAGEMNET SYSTEM

Submitted by

Suraj Yadav (2101870109011)

Amita Jaiswal (2101870109001)
Rajeev Prajapati (2001870100090)

is a bonafide student of this institute and the work has been carried out by him/her under
the supervision of Mrs. Preeti Singh and it is approved for the partial fulfillment of the
requirement of Dr. Abdul Kalam Technical University for the award of the degree of
Bachelor of Engineering (Computer Engineering).

Mrs. Preeti Singh Dr. Shruti Tripathi

Guide Head
Department of CSE Department of CSE

(Dr. Digvijay Singh Chauhan)

Director,
Feroze Gandhi Institute of Engineering & Technology, Raebareli – 229301

Place: Raebareli
Date:
 DECLARATION

I Suraj Yadav (2101870109011), Amita (2101870109001) and Rajeev Prajapati

(2001870100090) hereby declare that the Project Report entitled “AGRICULTURAL
CROPS MANAGEMNET SYSTEM” done by me under the guidance of Mrs. Priti Singh
(Internal Guide) at Feroze Gandhi Institute of Engineering and Technology, Raebareli is
submitted in partial fulfilment of the requirements for the award of Bachelor of
Technology degree in Computer Science and Engineering.

Signature:
Name:

Signature:
Name:

Signature:
Name:

FGIET Raebareli , Department of Computer Science and Engineering 2023-24 3

 ABSTRACT

Agriculture is a major source of income and employment in India. The most prevalent
problem faced by Indian farmers is that they do not select the appropriate crop for their
land and do not use the appropriate fertilizer. They will experience a significant drop in
production as a result of this. Precision agriculture has been used to solve the farmers'
difficulty. Precision agriculture is a modern farming strategy that employs research data on
soil properties, soil types, and crop yield statistics to recommend the best crop to farmers
as well as fertilizer recommendations based on site-specific features. This decreases the
number of times a crop is chosen incorrectly and increases productivity. In this paper, this
problem is solved by proposing a recommendation system through ML models with
majority voting technique using Random Forest, Naive Bayes, Support Vector Machine
(SVM), Logistic Regression and Random Forest, as learners to recommend a crop for the
site-specific parameters with high accuracy and efficiency. In Addition to that we are
performing real time testing using IOT system. The fertilizer recommendation system is
purely python logic based. In this we compare the data (optimum nutrients for growing the
crop) with the user’s entered data. Then nutrient having maximum difference is made as
HIGH or LOW and according to that suggestions will be fetched.

Keywords: Precision agriculture, Recommendation system, Random Forest, Support

Vector Machine (SVM), Logistic Regression
 ACKNOWLEDGEMENT

It gives us a great sense of pleasure to present the report of the B.Tech Project undertaken
during B.Tech. Final Year. We owe special debt of gratitude to our project guide
Dr./Mr./Mrs./Ms. Preeti Singh, Department of Computer Science & Engineering, Feroze
Gandhi Institute of Engineering & Technology, Raebareli for his/her constant support and
guidance throughout the course of our work. His/her sincerity, thoroughness and
perseverance have been a constant source of inspiration for us. It is only his cognizant
efforts that our endeavors have seen light of the day.

We also take the opportunity to acknowledge the contribution of Dr. Shruti Tripathi,
Head, Department Computer Science & Engineering, Feroze Gandhi Institute of
Engineering & Technology, Raebareli for her full support and assistance during the
development of the project.

We also do not like to miss the opportunity to acknowledge the contribution of all faculty
members of the department for their kind assistance and cooperation during the
development of our project. Last but not the least, we acknowledge our friends for their
contribution in the completion of the project.

Date:
Place:
(Signature of Student)

FGIET Raebareli , Department of Computer Science and Engineering 2023-24 5

 Table of Contents

Declaration
Abstract
Acknowledgment 1
Table of Contents 2
List of Figures 4
1. Introduction 5
1.1Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . ………. 5
1.2 Existing System . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
1.3 Proposed System . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
1.4 Plan of Implementation . . . . . . . . . . . . . . . . . . . . . . . . . . 7
1.5 Problem Definitions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
1.6 Objective of the Project . . . . . . . . . . . . . . . . . . . . . . . . . . 8

2. Literature Survey 9

3. Theoretical Background 11
3.1 Overview on Machine Learning . . . . . . . . . . . . . . . . . . . . . 11
3.2 Machine Learning Tools . . . . . . . . . . . . . . . . . . . . . . . . . . 13
3.3 Scikit-learn . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
3.4 Dataset . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
3.5 Data Preprocessing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15

4. System Requirements Specification 16

4.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . 16
4.2 Functional Requirements . . . . . . . . . . . . . . . . . . . . . …… 17
4.3 External Interface Requirements………………………… 18
4.4 Non-Functional Requirements …………………………… 18
4.5 System Requirements ……………………………………. 20

5. System Analysis 21
5.1 Feasibility Study . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
5.2 Analysis . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22

6. System Design 23
6.1 Analysis Model/Model Phases . . . . . . . . . . . . . . . . . . 23
6.2 Advantages of Waterfall Model . . . . . . . . . . . . . . . . . . . . 24
6.3 System Architecture . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25
6.4 Sequence diagram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26
6.5 Data flow diagrams ……………………………………… 26
6.6 UML diagrams…………………………………………… 28

7. Implementation 29
7.1 Data Analysis . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29
7.2 Data Preprocessing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31
7.3 Machine Learning Models . . . . . . . . . . . . . . . . . . . . . . . . . 32
8. Testing 36
8.1 Testing Methodologies . . . . . . . . . . . . . . . . . . . . . . . . . . . 36
8.2 Unit Testing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 36
8.3 System Testing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 36
8.4 Quality Assurance . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37
8.5 Functional Test . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37

9. Results 38
9.1 Algorithms and accuracies . . . . . . . . . . . . . . . . . . . . . . . 38
9.2 Result Screenshots ………………………………… 40
9.3 Advantages ………………………………………… 44
9.4 Limitations………………………………………… 44

10. Conclusion 45
11. References 46

FGIET Raebareli , Department of Computer Science and Engineering 2023-24 7

 List of Figures

1. Water Fall Model

2. System Architecture
3. Sequence Diagram
4. DFD Level 0
5. DFD Level 1
6. UML Diagram
7. Yield Dataset
i. Yield dataset
ii. Temperature rainfall and nutrient dataset
iii. Soil Nutrients distribution as per crop (Nitrogen, Phosphorous, Potassium).
8. Support Vector Machine
9. Accuracy Comparison
10. Output crop recommender and prediction
CHAPTER 1

1. INTRODUCTION

A farmer’s decision about which crop to grow is generally clouded by his intuition and
other irrelevant factors like making instant profits, lack of awareness about market
demand, overestimating a soil’s potential to support a particular crop, and so on. A very
misguided decision on the part of the farmer could place a significant strain on his family’s
financial condition. Perhaps this could be one of the many reasons contributing to the
countless suicide cases of farmers that we hear from media daily. In a country like India,
where agriculture and related sector contribute to approximately 20.4 per cent of its Gross
Value Added (GVA), such an erroneous judgment would have negative implications on not
just the farmer’s family, but the entire economy of a region. For this reason, we have
identified a farmer’s dilemma about which crop to grow during a particular season, as a
very grave one.

The need of the hour is to design a system that could provide predictive insights to the
Indian farmers, thereby helping them make an informed decision about which crop to
grow. With this in mind, we propose a system, an intelligent system that would consider
environmental parameters (temperature, rainfall, geographical location in terms of state)
and soil characteristics (N, P, K, pH value, soil type and nutrients concentration) before
recommending the most suitable crop to the user. In addition to that a fertilizer suggestion
is also made which is based on the optimum nutrients of the crops grown.

1.1 Motivation

Agriculture is that the backbone for developing countries like India as quite 70% of
population depends on agriculture. Agriculture in India plays a predominant role in
economy and employment. The common problem existing among the Indian farmers are
they do not choose the proper crop supported their soil requirements and which fertilizer to
be used for his or her crop. thanks to this they face a heavy setback in productivity. This
problem of the farmers has been addressed through precision agriculture.

1.2 Existing System

More and more researchers have begun to spot this problem in Indian agriculture and are
increasingly dedicating their time and efforts to assist alleviate the difficulty. Different
works include the employment of Regularized Greedy Forest to see an appropriate crop
sequence at a given time stamp. Another approach proposes a model that creates use of
historical records of meteorological data as training set. Model is trained to spot climate
that are deterrent for the assembly of apples. It then efficiently predicts the yield of apples
on the idea of monthly weather patterns. The use of several algorithms like Artificial
Neural Network, K Nearest Neighbours, and Regularized Greedy Forest is demonstrated in
[5] to pick out a crop supported the pre-diction yield rate, which, in turn, is influenced by
multiple parameters. Additional features included within the system are pesticide
prediction and online trading supported agricultural commodities.

FGIET Raebareli , Department of Computer Science and Engineering 2023-24 9

1.3 Drawbacks

One shortcoming that we identified all told these notable published works was that the
authors of every paper focused on one parameter (either weather or soil) for predicting the
suitability of crop growth. However, in our opinion, both these factors should be taken
together into consideration concomitantly for the most effective and most accurate
prediction.
This is often because, a specific soil type could also be it for supporting one variety of
crop, but if the climatic conditions of the region don't seem to be suitable for that crop
type, then the yield will suffer.

1.4 Proposed System

We to eliminate the aforementioned drawbacks, we propose an efficient Crop

Recommendation system- which takes into consideration all the appropriate parameters
including temperature, rainfall, location and soil condition, to predict crop suitability. This
system is fundamentally concerned with performing the primary function of Agro
Consultant, which is providing crop recommendations to farmers. We also provide the
fertilizers to be used for crops grown in different states which gives the user an easy and
reliable insight to decide and plan the crops

1.5 Plan of Implementation

The steps involved in this system implementation are :-

a) Acquisition of Training Dataset: The accuracy of any machine learning algorithm
depends on the number of parameters and the correctness of the trainingdataset. For the
system, we are using various datasets all downloaded for government website and kaggle.

Datasets include:-

Yield dataset, Fertilizer dataset, Soil nutrient content dataset, Rainfall, Temperature dataset

b). Data Preprocessing:

This step includes replacing the null and 0 values for yield
by -1 so that it does not effect the overall prediction. Further we had to encode the
dataset so that it could be fed into our ML models.

c). Training ML model:

After the preprocessing step we used the dataset to train different
machine learning models like Random forest, Decision Tree, Support Vector
Machine(SVM) and Logistic regression to attain accuracy as high as possible.

d). Model Evaluation and Saving Model: All the ML models which are trained would be
evaluated by comparing their performance (Evaluations Metrics) and Final efficient model
is saved using pickle library.

e). Model Exportation and Integration with Webapp:

The saved efficient ML model would be integrated with Flask Web Application which
would further meant for prediction in user friendly web interface.
1.6 Problem Definition

In India, agriculture is one of the most important professions. Many of the people do
agriculture but are unable to determine which types of crops are more suitable to their soil.
Means there are variety of crops which are only suitable for wet soil, some requires
medium humidity in the soil to grow but this knowledge is less known to farmers as well
as newbies who develop some interest in farming. As of now there are very less resources
as well as software’s which will help them to improve quality. Such type of software is
Precision agriculture using machine learning and IoT.

1.7 Objective of the Project

[1] To build a robust model to provide correct and accurate prediction of crop sustainability
in a given state for the particular soil type and climatic conditions.
[2] Provide recommendation of the most effective suitable crops within the area in order
that the farmer doesn't incur any losses
[3] Provide fertilizer suggestion for crops supported chemical features.

FGIET Raebareli , Department of Computer Science and Engineering 2023-24 11

CHAPTER 2

2. LITERATURE SURVEY

Low-cost IOT + ML design for smart farming with multiple application paper authors Fahad
Kamraan Syed, Agniswar Paul, Ajay Kumar, Jaideep Cherukuri in paper [1] proposed system for
water management systems and improve current irrigation methods. An IoT and MLbased farming
system always keeps farmers aware of the upcoming weather possibilities and gives them the best
suggestions about irrigation methods and crops thereby helping in better
yield.

In paper [2] author’s proposed a smart system that can assist farmers in crop management by
considering sensed parameters (temperature, humidity) and other parameters (soil type,
location of farm, rainfall) that predicts the most suitable crop to grow in that environment.

Reference Paper [3] determines real time sampling of soil properties using MODIFIED
SUPPORT VECTOR REGRESSION, a popular machine learning algorithm and four
modules. The Modules include Sensor interfaced to IoT device, Agri cloud, Analyzing the
real time sensor data and Agri user interface (AUI). The first module is portable IoT device
(NodeMCU) with soil moisture sensor and pH sensor, environmental sensors. Agri cloud
module consists of storage. Analysing the real time data module is processing of types of
crops and small plants suggested using modified support vector machine algorithm. Agri-user
interface is a basic web interface. Thus, with the help of soil properties farmer will be able to get
types of crops and small plants is grown in farmland with help of Modified support vector machine
algorithm.

In paper [4] author’s proposed new technologies include the use of Internet of Things (IOT) and
Machine Learning. The real time data from the field area can be collected using IOT system. The
collected data from the field area is fed to the trained model. The trained model then makes the
predictions using the data. The result produced by the model greatly helps is sowing the suitable
crops in the particular field area.

In Reference paper [5] determines a model is proposed for predicting the soil type and
suggest a suitable crop that can be cultivated in that soil. The model has been tested using
various machine learning algorithms such as KNN, SVM and logistic regression. The
accuracy of the present model is maximum than the existing models.
Aruul Mozhi Varman S proposed an IOT and deep learning based smart agriculture systems. This
system monitors and collects the soil parameters from the field with the help of a wireless sensor
network. The collected data is then uploaded in the cloud. Finally, the
systems suggest best irrigation practices to the farmers by predicting the crop to be sown for next
crop rotation. This information will be sent as an SMS to the farmers. The parameters include soil
temperature, atmospheric temperature, and humidity [6]. This system suggests further improving
the effectiveness by predicting the suitable time for applying pesticides, fertilizer, and manures.

In paper [7] proposed a system would assist the farmers in making an informed decision
about which crop to grow depending on a variety of environmental and geographical factors. The
ML and IoT based suggestions will significantly educate the farmer and help them minimize costs
and make strategic decisions by replacing intuition and passed-down
knowledge with far more reliable data-driven ML models. This allows for a scalable, reliable
solution to an important problem affecting hundreds of millions of people
CHAPTER 3

Theoretical Background

3.1 Overview on Machine Learning

Machine learning is an application of artificial intelligence (AI) that gives systems the ability
to automatically learn and evolve from experience without being specially programmed by
the programmer. The process of learning begins with observations or data, such as examples,
direct experience, or instruction, in order to look for patterns in data and make better
decisions in the future based on the examples that we provide. The main aim of machine
learning is to allow computers to learn automatically and adjust their actions to improve the
accuracy and usefulness of the program, without any human intervention or assistance.
Traditional writing of programs for a computer can be defined as automating the procedures
to be performed on input data in order to create output artifacts. Almost always, they are
linear, procedural and logical. A traditional program is written in a programming language to
some specification, and
it has properties like:
 We know or can control the inputs to the program.
 We can specify how the program will achieve its goal.
 We can map out what decisions the program will make and under what conditions it
makes them.
 Since we know the inputs as well as the expected outputs, we can be confident that the
program will achieve its goal.

Traditional programming works on the premise that, as long as we can define what a
program needs to do, we are confident we can define how a program can achieve that
goal. This is not always the case as sometimes, however, there are problems that you can
represent in a computer that you cannot write a traditional program to solve.
Such problems resist a procedural and logical solution. They have properties such as:

 The scope of all possible inputs is not known beforehand.

 You cannot specify how to achieve the goal of the program, only what that goal is.
 You cannot map out all the decisions the program will need to make to achieve its goal.
 You can collect only sample input data but not all possible input data for the program.

3.1.1 Supervised and Unsupervised Learning

Machine learning techniques can be broadly categorized into the following types: Supervised
learning takes a set of feature/label pairs, called the training set. From this training set the
system creates a generalized model of the relationship between the set of descriptive features
and the target features in the form of a program that contains a set of rules. The objective is to
use the output program produced to predict the label for a previously unseen, unlabelled input
set of features, i.e. to predict the outcome for some new data. Data with known labels, which
have not been included in the training set, are classified by the generated model and the
results are compared to the known labels. This dataset is called the test set. The accuracy of
the predictive model can then be calculated as the proportion of the correct predictions the
model labelled out of the total number of instances in the test set.
Unsupervised learning takes a dataset of descriptive features without labels as a training set.
In unsupervised learning, the algorithms are left to themselves to discover interesting
structures in the data. The goal now is to create a model that finds some hidden structure in
the dataset, such as natural clusters or associations. Unsupervised learning studies how
systems can infer a function to describe a hidden structure from unlabelled data. The system

FGIET Raebareli , Department of Computer Science and Engineering 2023-24 13

does not figure out the right output, but it explores the data and can draw inferences from
datasets to describe hidden structures from unlabelled data. Unsupervised learning can be used
for clustering, which is used to discover any inherent grouping that are already present in the
data. It can also be used for association problems, by creating rules based on the data and
finding relationships or associations between them.
Semi-supervised machine learning falls somewhere in between supervised and unsupervised
learning, since they use both labeled and unlabeled data for training typically a small amount
of labeled data and a large amount of unlabeled data. The systems that use this method are
able to considerably improve learning accuracy. Usually, semi-supervised learning is chosen
when the acquired labeled data requires skilled and relevant resources in order to train it /
learn from it. Otherwise, acquiring labeled data generally does not require additional
resources.
Reinforcement machine learning algorithms is a learning method that interacts with its
environment by producing actions and discovers errors or rewards. Machine learning
algorithms are tools to automatically make decisions from data in order to achieve some over-
arching goal or requirement. The promise of machine learning is that it can solve complex

problems automatically, faster and more accurately than a manually specified solution, and at
a larger scale. Over the past few decades, many machine learning algorithms have been
developed by researchers, and new ones continue to emerge and old ones modified.

3.2 Machine Learning Tools

There are many different software tools available to build machine learning models and to
apply these models to new, unseen data. There are also a large number of well defined
machine learning algorithms available. These tools typically contain libraries implementing
some of the most popular machine learning algorithms. They can be categorized as follows:
 Pre-built application-based solutions.
 Programming languages which have specialized libraries for machine learning.

Using programming languages to develop and implement models is more flexible and
gave us better control of the parameters to the algorithms. It also allows us to have a
better understanding of the output models produced. Some of the popular programming
languages used in the field of machine learning are:
 Python: Python is an extremely popular choice in the field of machine learning and AI
development. Its short and simple syntax make it extremely easy to learn

 Tensorflow: TensorFlow is an end-to-end open source platform for machine learning.

It has a comprehensive, flexible ecosystem of tools, libraries, and community
resources that lets researchers push the state-of-the-art in ML and developers easily
build and deploy ML-powered applications. TensorFlow was originally developed by
researchers and engineers working on the Google Brain team within Google's Machine
Intelligence Research organization to conduct machine learning and deep neural
networks research. The system is general enough to be applicable in a wide variety of
other domains, as well. TensorFlow provides stable Python and C++ APIs, as well as
non-guaranteed backward compatible API for other languages.

3.3 SciKit-learn
SciKit learn is an open source machine learning library built for python. Since its release in
2007, Scikit-learn has become one of the most popular open source machine learning
libraries. Scikit-learn (also called sklearn) provides algorithms for many machine learning
tasks including classification, regression, dimensionality reduction and clustering. The
documentation for scikit-learn is comprehensive, popular and well maintained. Sklearn is
built on mature Python Libraries such as NumPy, SciPy, and matplotlib. While languages
such as R and MATLAB are extremely popular and useful for machine learning, we decided
to choose Python along with its SciKit-learn libraries as our programming language of
choice.
The reasons for this are:
 We already have some familiarity and exposure to Python, and thus have a smaller
learning curve.
 Both Python and Scikit-learn have excellent documentation and tutorials available
online
 The number of classic machine learning algorithms that come with Scikit-learn, and
the consistent patterns for using the different models i.e., each model can be used with
the same basic commands for setting up the data, training the model and using the
model for prediction. This makes it easier to try a range of machine learning
algorithms on the same data.

 The machine learning algorithms included with sklearn have modifiable parameters
known as hyper parameters that effect the performance of the model. These usually
have sensible default values, so that we can run them without needing a detailed
knowledge or understanding of their semantics.

 The IPython notebook, which is an interactive computational environment for Python,

in which a user can combine code execution, rich text, mathematics and plots in a web
page. This functionality allows us to provide the notebooks we used to run our
experiments almost as an audit and in a presentable.

3.4 Dataset
For the system, we are using various datasets all downloaded for government website and
kaggle.

Datasets include:-
 Yield dataset
 Fertilizer dataset
 Soil nutrient content dataset
 Rainfall Temperature dataset

A brief description of the datasets:

 Yield Dataset: This dataset contains yield for 16 major crops grown across all the states
in kg per hectare. Yield of 0 indicates that the crop is not cultivated in the respective
state.
 Soil nutrient content dataset : This dataset has columns with the attributes in the order-
State, Nitrogen content, Phosphorous content, Potassium content and average ph
 Rainfall Temperature dataset: This dataset contains crops, max and min rainfall, max
and min temperature, max and min rainfall and ph values.

3.5 Data Preprocessing

This step includes replacing the null and 0 values for yield by -1 so that it does not effect the
overall prediction. Further we had to encode the data-set so that it could be fed into the ML
models.

FGIET Raebareli , Department of Computer Science and Engineering 2023-24 15

Chapter 4

SOFTWARE REQUIREMENT SPECIFICATION

4.1 Introduction
This Software Requirements Specification provides a complete description of all the
Functions and constraints of the “Precision agriculture using machine learning & IOT”. The
document, describes the issue related to the agriculture system and what actions are needed to
perform to grow which type of crop should be grown in your soil and your environment to
get better crop production.
The basic idea of this project comes from the farmers who don’t know which type of
crop will be better for their soil according to nutrition and other environment conditions. In
India, agriculture is one of the most important professions. Many of the people do agriculture
but are unable to determine which types of crops are more suitable to their soil. Means there
are variety of crops which are only suitable for wet soil, some requires medium humidity in
the soil to grow but this knowledge is less known to farmers as well as newbies who develop
some interest in farming.

4.1.1 Project Scope

 Improve farm management efficiency by adjusting field/crop treatments
 Getting a better result for which type of crop will be growing on your agriculture field.
 Getting more productivity from less efforts by using our application
 Improve farm management efficiency by adjusting field/crop treatments
 Optimise efforts and resources, reduce consumption and waste, and boost land
productivity.
 Which type of fertilizers should be used if any crop having any disease we can
minimize using our app This are some project scope of our project.

4.1.2 User Classes and Characteristics

This protocol is implemented in python language .We also use flask, bootstrap frameworks. The
system design has done using python flask web application.
This project is for end user who has to know about which type of crop should be better
yield in their agriculture field just like farmer and newbies who don’t know how to do
agriculture in their filed so our project provide all necessary thing to get better crop
productivity in your field. Also we can minimize the effect of disease of your crop by
identifying which type of disease it is.

4.1.3 Assumptions and Dependencies

 Data is an asset. It is valuable resource, as it has real and measurable value. Accurate
and timely data is critical to quality and efficiency of service. Data input and its
accuracy will depend on the user. Accountability of data will be defined
 Content generation and updation will be done timely by the user
 Portal Management Framework will be devised and user will play active role in it
 User will provide content in local languages

4.2 Functional Requirements

 System must be fast and efficient
 User friendly GUI
 Performance
 System Validation input
 Proper output
4.2.1 System Feature 1(Functional Requirement)
Functional Requirement defines a function of a software system and how the system
must behave when presented with specific inputs or conditions. These may include
calculations, data manipulation and processing and other specific functionality. Following are
the functional requirements on the system:

1. All the data must be in the same format as a structured data.

2. The data collected will be vectorized and sent across to the classifier.

4.3 External Interface Requirements

4.3.1 User Interfaces

 Front End Software: Flask Framework integrated with HTML, CSS, JS,
BOOTSTRAP
 Back End Software: Machine Learning (Python)

4.3.2 Hardware Interfaces

 RAM - Minimum 512 MB.
 Processor - i3 or above and above with 2.5 GHz

4.3.3 Software Interfaces

 OS: Ubuntu, Windows, Mac

 Tools: VScode or Python IDE and Jupyter Notebook.
 Programming Language: Python flask, HTML, CSS, JS, BOOTSTRAP.
 Dataset: A Dataset which is openly available in kaggle.
 Libraries/Tools : Seaborn, Pandas, NumPy, SciKit-Learn, Pytorch, ResNet-9,
SQLAlchemy, Pickle

4.3.4 Communication Interfaces

The communication protocol started from http from UI interface in which person can see
some details of the soil nutrition section by filling up details user can see which type of
crop
should be grown in your region and your agriculture field. And another one is person can
just
upload the picture of crop then user will get information about the diseases of crop.

4.4 Nonfunctional Requirements

Nonfunctional requirements are the requirements which are not directly concerned with
the specific function delivered by the system. They specify the criteria that can be used to
judge the operation of a system rather than specific behaviours. They may relate to emergent
system properties such as reliability, response time and store occupancy.
Nonfunctional requirements arise through the user needs, because of budget constraints,
organizational policies and the need for interoperability with other software and hardware systems.

4.4.1 Performance Requirements

The System should be interactive and performance should be efficient. The delays of the system
should be less. Also a stable internet connection is required.

4.4.2 Safety Requirements

This Specification shall be sufficient detailed to allow the design and implement to achieve the
required safety integrity and allow an assessment of functional safety

FGIET Raebareli , Department of Computer Science and Engineering 2023-24 17

4.4.3 Security Requirements
We provide login system by passwords for each level of access

4.4.4 Software Quality Attributes

Availability:
The information regarding the nutrition’s must be available.

Usability:
System should be interactive and easy to understand.

Maintainability:
System should be easy to maintain.

Robustness:
Single application failure will not affect the system. System should be fault tolerant.
System should reliable enough to sustain in any condition. It should give Perfect results.

4.5 System Requirements

4.5.1 Database Requirements

 MYSQL

4.5.2 Software Requirements

 Operating System: Windows, Linux and Mac
 Coding Language: Python Flask, HTML,CSS,JS,BOOSTRAP
 Tools: Seaborn, Pandas, NumPy, SciKit-Learn, Pytorch, ResNet-9, SQLAlchemy,
Pickle

4.5.3 Hardware Requirements

 Processor: i3 and above with 2.5 GHz.
 RAM: 512 MB.
 Hard disk space: = 8GB
CHAPTER 5

System Analysis

5.1 Feasibility Study

Analysis is the process of finding the best solution to the problem. System analysis is the process
by which we learn about the existing problems, define objects and requirements and evaluates the
solutions. It is the way of thinking about the organization and the problem it involves, a set of
technologies that helps in solving these problems. Feasibility study plays an important role in
system analysis which gives the target for design and development.

5.1.1 Economical Feasibility

This study is carried out to check the economic impact that the system will have on the
organization. Since the project is Machine learning based, the cost spent in exectuating this
project would not demand cost for softwares and related products, as most of the products
are
open source and free to use. Hence the project would consumed minimal cost and is
economically feasible.

5.1.2 Technical Feasibility

This study is carried out to check the technical feasibility, that is, the technical
requirements
of the system. Since machine learning algorithms is based on pure math there is very less
requirement for any professional software. And also most of the tools are open source. The
best part is that we can run this software in any system without any software requirements
which makes them highly portable. Also most of the documentation and tutorials make
easy
to learn the technology

5.1.3 Social Feasibility

The aspect of study is to check the level of acceptance of the system by the user. This
includes the process of training the user to use the system efficiently. The user must not
feel threatened by the system, instead must accept it as a necessity. The main purpose of
this project which is based on crop prediction is to prevent the farmer from incurring losses
and improve productivity. This also ensures that there is no scarcity of food as lack of
production may lead to severe consequences. Thus, this is a noble cause for the sake of the
society, a small step taken to achieve a secure future.

5.2 Analysis
5.2.1 Performance Analysis
Most of the software we use is open source and free. The models whichwe use in this
software, learn only once ,i.e once they are trained theyneed not be again fed in for the
training phase. One can directly predictfor values, hence time-complexity is very less.
Therefore, this model istemporally sound.

5.2.2 Technical Analysis

As mentioned earlier, the tools used in building this software is opensource. Each tool
contains simple methods and the required methodsare overridden to tackle the problem.

5.2.3 Economical Analysis

The completion of this project can be considered free of cost in itsentirety. As the software

FGIET Raebareli , Department of Computer Science and Engineering 2023-24 19

 used in building the model is free of cost andall the data sets used are being downloaded
from kaggle and Govt. ofIndia website.

CHAPTER 6

System Design

6.1 Analysis Models: SDLC Model to be applied

The waterfall model is a sequential software development process, in which progress is seen
as owing steadily downwards (like a waterfall) through the phases of Requirement initiation,
Analysis, Design, Implementation, Testing and maintenance.

Requirement Analysis:
This phase is concerned about collection of requirement of the system. This process
involves generating document and requirement review.

System Design:
Keeping the requirements in mind the system specifications are translated in to a
software representation. In this phase the designer emphasizes on:- algorithm, data structure,
software architecture etc.

Coding:
In this phase programmer starts his coding in order to give a full sketch of product. In
other words system specifications are only converted in to machine.

Implementation:
The implementation phase involves the actual coding or programming of the software.
The output of this phase is typically the library, executable, user manuals and additional
software documentation.

Testing:
In this phase all programs (models) are integrated and tested to ensure that the
complete system meets the software requirements. The testing is concerned with verification
and validation

Maintenance:
The maintenance phase is the longest phase in which the software is updated to fulfill
the changing customer needs, adapt to accommodate changes in the external environment,
correct errors and oversights previously undetected in the testing phase, enhance the
efficiency of the software .
Fig-1 Waterfall Model
6.2. Advantages of Waterfall model
 _ Clear project objective
 _ Stable project requirements
 _ Progress of system is measurable.
 _ Logic of software development is clearly understood.
 _ Better resource allocation.

6.3 System Architecture

Fig-2 System Architecture

A system architecture is a conceptual model using which we can define the structure and
behaviour of that system. It is a formal representation of a system. Depending on the context,
system architecture can be used to refer to either a model to describe the system or a method
used to build the system. Building a proper system architecture helps in analysis of the
project, especially in the early stages. Figure 6.3 depicts the system architecture and is
explained in the following section.

6.4 Sequence Diagram

FGIET Raebareli , Department of Computer Science and Engineering 2023-24 21

Fig-3 Sequence Diagram
6.5 Data Flow Diagrams

6.5.1 DFD Level-0

Fig-4 DFD Level-0

6.5.2 DFD Level-1

 Data
Identification Data processing
of data source collections

Training Researching
Models models

Predicted
output
Fig-5 DFD Level-1

6.6 UML Diagrams

FGIET Raebareli , Department of Computer Science and Engineering 2023-24 23

Fig-6 UML diagram

CHAPTER 7
Implementation

7.1 Data Analysis

One of the first steps we perform during implementation is an analysis of the data. This was
done by us in an attempt to find the presence of any relationships between the various
attributes present in the dataset.

Acquisition of Training Dataset: The accuracy of any machine learning algorithm depends on the
number of parameters and the correctness of the training dataset.

We In this project analyzed multiple datasets collected from Government website

-https://data.gov.in/ and Kaggle and carefully selected the parameters that would give
the best results.

Many work done in this field have considered environmental parameters to

predict crop sustainability some have used yield as major factor where as in some works only
economic factors are taken into consideration. We have tried to combine both environmental
parameters like rainfall, temperature, ph, nutrients in soil, soil type, location and economic
parameters like production, and yield to provide accurate and reliable recommendation to the
farmer on which crop will be most suitable for his land.

Fig-7.1 Yield Dataset

FGIET Raebareli , Department of Computer Science and Engineering 2023-24 25

Fig-7.2 Temperature Rainfall and Nutrients dataset

Fig-7.3 Soil Nutrients distribution as per crop(Nitrogen,Phosphorous,Potassium).

7.2 Data Preprocessing
After analyzing and visualizing the data, the next step is preprocessing.
Data preprocessing is an important step as it helps in cleaning the data and making it suitable
for use in machine learning algorithms. Most of the focus in preprocessing is to remove any
outliers or erroneous data, as well as handling any missing values.
Missing data can be dealt with in two ways. The first method is to simply remove the entire
row which contains the missing or error value. While this an easy to execute method, it is
better to use only on large datasets. Using this method on small datasets can reduce the
dataset size too much, especially if there are a lot of missing values.

This can severely affect the accuracy of the result. Since ours is a relatively small dataset, we
will not be using this method. The dataset that we used had values that were in string format
so we had to transform and encode the into integer valued so as to pass as an input to the
neural network. First we converted the data into pandas categorical data and then generated
codes for crops and states respectively we than appended these and created separated
datasets.

import pandas as pd
# Reading the data
crop_data_path = '../Data-raw/cpdata.csv'
fertilizer_data_path = '../Data-raw/Fertilizer.csv'
crop = pd.read_csv(crop_data_path)
fert = pd.read_csv(fertilizer_data_path)
# Function for lowering the cases
defchange_case(i):
i = i.replace(" ", "")
i = i.lower()
return i
fert['Crop'] = fert['Crop'].apply(change_case)
crop['label'] = crop['label'].apply(change_case)
crop_names = crop['label'].unique()
print(crop_names)
crop_names_from_fert = fert['Crop'].unique()
print(crop_names_from_fert)
for i in crop_names_from_fert:
print(crop[crop['label'] == i])
extract_labels = []
for i in crop_names_from_fert:
if i in crop_names:
import pandas as pd
# Reading the data
crop_data_path = '../Data-raw/cpdata.csv'
fertilizer_data_path = '../Data-raw/Fertilizer.csv'
crop = pd.read_csv(crop_data_path)
fert = pd.read_csv(fertilizer_data_path)
# Function for lowering the cases
defchange_case(i):
i = i.replace(" ", "")
i = i.lower()
return i
fert['Crop'] = fert['Crop'].apply(change_case)
crop['label'] = crop['label'].apply(change_case)
crop_names = crop['label'].unique()
print(crop_names)
crop_names_from_fert = fert['Crop'].unique()
print(crop_names_from_fert)
for i in crop_names_from_fert:
print(crop[crop['label'] == i])
extract_labels = []
for i in crop_names_from_fert:
if i in crop_names:
extract_labels.append(i)
# using extract labesl on crop to get all the data related to those labels
new_crop = pd.DataFrame(columns = crop.columns)
new_fert = pd.DataFrame(columns = fert.columns)
for label in extract_labels:
new_crop = new_crop.append(crop[crop['label'] == label])
for label in extract_labels:
new_fert = new_fert.append(fert[fert['Crop'] == label].iloc[0])
print(new_crop)
print(new_fert)
new_crop.to_csv('../Data-raw/MergeFileCrop.csv')
new_fert.to_csv('../Data-raw/FertilizerData.csv')

FGIET Raebareli , Department of Computer Science and Engineering 2023-24 27

7.3 Machine Learning Models
7.3.1 Decision Tree :
Decision Trees (DTs) are a non-parametric supervised learning method used
for classification and regression. The goal is to create a model that predicts the value of a
target variable by learning simple decision rules inferred from the data features. A tree can be
seen as a piecewise constant approximation.
For instance, in the example below, decision trees learn from data to approximate a sine
curve with a set of if-then-else decision rules. The deeper the tree, the more complex the
decision rules and the fitter the model.
features = df[['N', 'P','K','temperature', 'humidity', 'ph', 'rainfall']]
target = df['label']
#features = df[['temperature', 'humidity', 'ph', 'rainfall']]
labels = df['label']
# Initialzing empty lists to append all model's name and corresponding name
acc = []
model = []
# Splitting into train and test data
from sklearn.model_selection import train_test_split
Xtrain, Xtest, Ytrain, Ytest = train_test_split(features,target,test_size = 0.2,random_state =2)
from sklearn.tree import DecisionTreeClassifier
DecisionTree = DecisionTreeClassifier(criterion="entropy",random_state=2,max_depth=5)
DecisionTree.fit(Xtrain,Ytrain)
predicted_values = DecisionTree.predict(Xtest)
x = metrics.accuracy_score(Ytest, predicted_values)
acc.append(x)
model.append('Decision Tree')
print("DecisionTrees's Accuracy is: ", x*100)
print(classification_report(Ytest,predicted_values))
from sklearn.model_selection import cross_val_score
# Cross validation score (Decision Tree)
extract_labels.append(i)
# using extract labesl on crop to get all the data related to those labels
new_crop = pd.DataFrame(columns = crop.columns)
new_fert = pd.DataFrame(columns = fert.columns)
for label in extract_labels:
new_crop = new_crop.append(crop[crop['label'] == label])
for label in extract_labels:
new_fert = new_fert.append(fert[fert['Crop'] == label].iloc[0])
print(new_crop)
print(new_fert)
new_crop.to_csv('../Data-raw/MergeFileCrop.csv')
new_fert.to_csv('../Data-raw/FertilizerData.csv')
decision rules and the fitter the model.
features = df[['N', 'P','K','temperature', 'humidity', 'ph', 'rainfall']]
target = df['label']
#features = df[['temperature', 'humidity', 'ph', 'rainfall']]
labels = df['label']
# Initialzing empty lists to append all model's name and corresponding name
acc = []
model = []
# Splitting into train and test data
from sklearn.model_selection import train_test_split
Xtrain, Xtest, Ytrain, Ytest = train_test_split(features,target,test_size = 0.2,random_state =2)
from sklearn.tree import DecisionTreeClassifier
DecisionTree = DecisionTreeClassifier(criterion="entropy",random_state=2,max_depth=5)
DecisionTree.fit(Xtrain,Ytrain)
predicted_values = DecisionTree.predict(Xtest)
x = metrics.accuracy_score(Ytest, predicted_values)
acc.append(x)
model.append('Decision Tree')
print("DecisionTrees's Accuracy is: ", x*100)
print(classification_report(Ytest,predicted_values))
from sklearn.model_selection import cross_val_score
# Cross validation score (Decision Tree)
GHRIET, Department of Computer Engineering 2020-21
33
score = cross_val_score(DecisionTree, features, target,cv=5)
print(score)
#Saving trained Decision Tree model
import pickle
# Dump the trained Naive Bayes classifier with Pickle
DT_pkl_filename = '../models/DecisionTree.pkl'
# Open the file to save as pkl file
DT_Model_pkl = open(DT_pkl_filename, 'wb')
pickle.dump(DecisionTree, DT_Model_pkl)
# Close the pickle instances
DT_Model_pkl.close()
7.3.2 Support Vector Machine
The objective of the support vector machine algorithm is to find a hyperplane in an Ndimensional
space(N — the number of features) that distinctly classifies the data points.

Fig-8 support vector machine

To separate the two classes of data points, there are many possible hyperplanes that could be
chosen. Our objective is to find a plane that has the maximum margin, i.e the maximum
distance between data points of both classes. Maximizing the margin distance provides some
reinforcement so that future data points can be classified with more confidence.

from sklearn.svm import SVC

SVM = SVC(gamma='auto')
SVM.fit(Xtrain,Ytrain)
predicted_values = SVM.predict(Xtest)
x = metrics.accuracy_score(Ytest, predicted_values)
acc.append(x)
model.append('SVM')
print("SVM's Accuracy is: ", x)
print(classification_report(Ytest,predicted_values))
score = cross_val_score(SVM,features,target,cv=5)
print(score)
score = cross_val_score(DecisionTree, features, target,cv=5)
print(score)
#Saving trained Decision Tree model
import pickle
# Dump the trained Naive Bayes classifier with Pickle
DT_pkl_filename = '../models/DecisionTree.pkl'
# Open the file to save as pkl file
DT_Model_pkl = open(DT_pkl_filename, 'wb')
pickle.dump(DecisionTree, DT_Model_pkl)
# Close the pickle instances
DT_Model_pkl.close()
from sklearn.svm import SVC
SVM = SVC(gamma='auto')
SVM.fit(Xtrain,Ytrain)
predicted_values = SVM.predict(Xtest)
x = metrics.accuracy_score(Ytest, predicted_values)
acc.append(x)
model.append('SVM')
print("SVM's Accuracy is: ", x)
print(classification_report(Ytest,predicted_values))
score = cross_val_score(SVM,features,target,cv=5)
print(score)

FGIET Raebareli , Department of Computer Science and Engineering 2023-24 29

7.3.3 Logistic Regression
Logistic regression is a classification algorithm used to assign observations to a discrete set of
classes. Some of the examples of classification problems are Email spam or not spam, Online
transactions Fraud or not Fraud, Tumor Malignant or Benign. Logistic regression transforms
its output using the logistic sigmoid function to return a probability value.
What are the types of logistic regression
1. Binary (eg. Tumor Malignant or Benign)
2. Multi-linear functions failsClass (eg. Cats, dogs or Sheep's)

Logistic Regression is a Machine Learning algorithm which is used for the classification
problems, it is a predictive analysis algorithm and based on the concept of probability.

from sklearn.linear_model import LogisticRegression

LogReg = LogisticRegression(random_state=2)
LogReg.fit(Xtrain,Ytrain)
predicted_values = LogReg.predict(Xtest)
x = metrics.accuracy_score(Ytest, predicted_values)
acc.append(x)
model.append('Logistic Regression')
print("Logistic Regression's Accuracy is: ", x)
print(classification_report(Ytest,predicted_values))
score = cross_val_score(LogReg,features,target,cv=5)
print(score)
import pickle
# Dump the trained Naive Bayes classifier with Pickle
LR_pkl_filename = '../models/LogisticRegression.pkl'
# Open the file to save as pkl file
LR_Model_pkl = open(DT_pkl_filename, 'wb')
pickle.dump(LogReg, LR_Model_pkl)
# Close the pickle instances
LR_Model_pkl.close()

7.3.4 Random Forest

Random forest is a Supervised Machine Learning Algorithm that is used widely in
Classification and Regression problems. It builds decision trees on different samples and
takes their majority vote for classification and average in case of regression.
One of the most important features of the Random Forest Algorithm is that it can handle the
data set containing continuous variables as in the case of regression and categorical
variables as in the case of classification. It performs better results for classification problems.
Random Forests was developed specifically to address the problem of high-variance in
Decision Trees. Like the name suggests, you’re not training a single Decision Tree, you’re
training an entire forest! In this case, a forest of Bagged Decision Trees.
Random Forests algorithm follows these steps:
1. Take the original dataset and create N bagged samples of size n, with n smaller than the
original dataset.
2. Train a Decision Tree with each of the N bagged datasets as input. But, when doing a
node split, don’t explore all features in the dataset. Randomly select a smaller
number, M features, from all the features in training set. Then pick the best split using
impurity measures, like Gini Impurity or Entropy.
3. Aggregate the results of the individual decision trees into a single output.
4. Average the values for each observation, produced by each tree, if you’re working on a
Regression task.
5. Do a majority vote across all trees, for each observation, if you’re working on a
Regression task.

from sklearn.linear_model import LogisticRegression

LogReg = LogisticRegression(random_state=2)
LogReg.fit(Xtrain,Ytrain)
predicted_values = LogReg.predict(Xtest)
x = metrics.accuracy_score(Ytest, predicted_values)
acc.append(x)
model.append('Logistic Regression')
print("Logistic Regression's Accuracy is: ", x)
print(classification_report(Ytest,predicted_values))
score = cross_val_score(LogReg,features,target,cv=5)
print(score)
import pickle
# Dump the trained Naive Bayes classifier with Pickle
LR_pkl_filename = '../models/LogisticRegression.pkl'
# Open the file to save as pkl file
LR_Model_pkl = open(DT_pkl_filename, 'wb')
pickle.dump(LogReg, LR_Model_pkl)
# Close the pickle instances
LR_Model_pkl.close()

from sklearn.ensemble import RandomForestClassifier

RF = RandomForestClassifier(n_estimators=20, random_state=0)
RF.fit(Xtrain,Ytrain)
predicted_values = RF.predict(Xtest)
x = metrics.accuracy_score(Ytest, predicted_values)
acc.append(x)
model.append('RF')
print("RF's Accuracy is: ", x)
print(classification_report(Ytest,predicted_values))
# Cross validation score (Random Forest)
score = cross_val_score(RF,features,target,cv=5)
print(score)
import pickle
# Dump the trained Naive Bayes classifier with Pickle
RF_pkl_filename = '../models/RandomForest.pkl'
# Open the file to save as pkl file
RF_Model_pkl = open(RF_pkl_filename, 'wb')
pickle.dump(RF, RF_Model_pkl)
# Close the pickle instances
RF_Model_pkl.close()
from sklearn.ensemble import RandomForestClassifier
RF = RandomForestClassifier(n_estimators=20, random_state=0)
RF.fit(Xtrain,Ytrain)
predicted_values = RF.predict(Xtest)
x = metrics.accuracy_score(Ytest, predicted_values)
acc.append(x)
model.append('RF')
print("RF's Accuracy is: ", x)
print(classification_report(Ytest,predicted_values))
# Cross validation score (Random Forest)
score = cross_val_score(RF,features,target,cv=5)
print(score)
import pickle
# Dump the trained Naive Bayes classifier with Pickle
RF_pkl_filename = '../models/RandomForest.pkl'
# Open the file to save as pkl file
RF_Model_pkl = open(RF_pkl_filename, 'wb')
pickle.dump(RF, RF_Model_pkl)
# Close the pickle instances
RF_Model_pkl.close()

FGIET Raebareli , Department of Computer Science and Engineering 2023-24 31

CHAPTER 8

Testing
8.1 Testing Methodologies
The program comprises of several algorithms which are tested individually for the accuracy.
we check for the correctness of the program as a whole and how it performs.

8.2 Unit Testing

Unit tests focus on ensuring that the correct changes to the world state take place when a
transaction is processed. The business login transaction processor functions should have unit
tests, ideally with 100 percent code coverage. This will ensure that you do not have typos or
logic errors in the business logic. The various modules can be individually run from a
command line and tested for correctness. The tester can pass various values, to check the
answer returned and verify it with the values given to him/her. The other work around is to
write a script, and run all the tests using it and write the output to a log _le and using that to
verify the results. We tested each of the algorithms individually and made changes in
preprocessing accordingly to increase the accuracy.

8.3 System Testing

System Testing is a level of software testing where a complete and integrated software is
tested. The purpose of this test is to evaluate the systems compliance with the specified
requirements. System Testing is the testing of a complete and fully integrated software
product and White Box Testing. System test falls under the black box testing category of
software testing. Different Types of System Testing:

 Usability Testing - Usability Testing mainly focuses on the users ease to use the
application, exibility in handling controls and ability of the system to meet its
objectives.
 Load Testing - Load Testing is necessary to know that a software solution will perform
under real-life loads.
 Regression Testing- - Regression Testing involves testing done to make sure none of
the changes made over the course of the development process have caused new bugs.
 Recovery Testing - Recovery testing is done to demonstrate a software solution is
reliable, trustworthy and can successfully recoup from possible crashes.
 Migration Testing - Migration testing is done to ensure that the software can be moved
from older system infrastructures to current system infrastructures without any issues.

8.4 Quality Assurance

Quality Assurance is popularly known as QA Testing, is defined as an activity to ensure that
an organization is providing the best possible product or service to customers. QA focuses on
improving the processes to deliver Quality Products to the customer. An organization
has to ensure, that processes are efficient and effective as per the quality standards defined for
software products.

8.5 Functional Test

Functional Testing is also known as functional completeness testing, Functional Testing
involves trying to think of any possible missing functions. As chat-bot evolves into new
application areas, functional testing of essential chatbot components. Functional testing
evaluates use-case scenarios and related business processes, such as the behavior
of smart contracts.
CHAPTER 9

Results

9.1 Algorithms and Their Accuracy

For the purposes of this project we have used four popular algorithms:
Decision Trees, Logistic regression, Support Vector Machine and Random Forest. All the
algorithms are based on supervised learning. Our overall system is divided
into two modules:
 Crop recommender
 Fertilizer Recommender/Suggestion

Algorithm Accuracy (%)

Decision Tree 90%
SVM 97%
Logistic Regression 95%
Random Forest 99%

Accuracy Comparison of ML Models:

plt.figure(figsize=[10,5],dpi ==
plt.figure(figsize=[10,5],dpi 100)
100)
plt.title('Accuracy Comparison')
plt.title('Accuracy Comparison')
plt.xlabel('Accuracy')
plt.xlabel('Accuracy')
plt.ylabel('Algorithm')
plt.ylabel('Algorithm')
sns.barplot(x ==
sns.barplot(x acc,y ==
acc,y model,palette='dark')
model,palette='dark')

Fig-9 Accuracy Comparison

Hence, Random Forest is our Final efficient model.

FGIET Raebareli , Department of Computer Science and Engineering 2023-24 33

Output for Crop recommender:

Fig-10 Output crop recommender

Fertilizer Recommender/Suggestion
The fertilizer recommendation system is purely python logic based. In this we compare the
data (optimum nutrients for growing the crop) with the user’s entered data. Then nutrient
having maximum difference is made as HIGH or LOW and according to that suggestions will
be fetched.
9.2 Results with Screenshots

Home Page

FGIET Raebareli , Department of Computer Science and Engineering 2023-24 35

Prediction & Result Page
1. Crop Prediction

2. Yield Prediction

3. Rainfall Prediction
Crop Recommendation & Result Page

1. Crop Recommendation

2. Fertilizer Recommendation

FGIET Raebareli , Department of Computer Science and Engineering 2023-24 37

Crop Disease Prediction & Result
1. Plant Disease

9.3 Advantages
 Improve farm management efficiency by adjusting field/crop treatments
 Ensure profitability, sustainability and protection of the environment
 To use new technologies to increase crop yields and profitability while lowering the
levels of traditional inputs needed to grow crops
 Optimize efforts and resources, reduce consumption and waste, and boost land
productivity
 It will reduce excessive chemical usage in crop production.

9.4 Limitations
 Extremely demanding work particularly collecting and then analyzing the data.
 Accuracy depends upon input dataset
 Most of the farmer not aware of such program like precision agriculture using machine
learning farmer don’t know the technology
 Complexity grows with data.
CHAPTER 10

Conclusion
All This system helps the farmer to choose the right crop by providing insights that ordinary
farmers don't keep track of thereby decreasing the chances of crop failure and increasing
productivity.

It also prevents them from incurring losses. The system can be extended to the web and can be
accessed by millions of farmers across the country. We could achieve an accuracy of 90 percent
from the Decision Trees, an accuracy of 70.6 percent from the Support Vector Machine, an
accuracy of 94.30 percent from the Logistic Regression and an accuracy of 99.09 percent from the
Random Forest model.

Further development is to integrate the crop recommendation system with another subsystem, yield
predictor that would also provide the farmer an estimate of production if he plants the
recommended crop.
.

FGIET Raebareli , Department of Computer Science and Engineering 2023-24 39

CHAPTER 11

References
[1] 2019, 10th International Conference on Computing, Communication and Networking
Technologies, “Low-cost IOT+ML design for smart farming with multiple applications”,
Fahad Kamraan Syed, Agniswar Paul, Ajay Kumar, Jaideep Cherukuri.

[2] 2019 IEEE “ Smart Management of Crop Cultivation using IoT and Machine Learning”
Archana Gupta, Dharmil Nagda, Pratiksha Nikhare, Atharva Sandbhor

[3] Radhika, Narendiran, “Kind of Crops and Small Plants Prediction using IoT with
Machine Learning,” International Journal of Computer & Mathematical Sciences, 2018.

[4] “Crop Recommendation on Analyzing Soil Using Machine Learning” Anguraj.Ka,

Thiyaneswaran.Bb, Megashree.Gc, Preetha Shri.J.Gd, Navya.Se, Jayanthi. Jf, 2020.

[5] “Classification of Soil and Crop Suggestion using Machine Learning Techniques”, A.
Mythili , IEEE 2019.

[6] Mehta, P., Shah, H., Kori, V., Vikani, V., Shukla, S., & Shenoy, M.,2018. “Survey of
unsupervised machine learning algorithms on precision agricultural data”, IEEE

[7] “IOT based Crop Recommendation, Crop Disease Prediction and Its Solution” Rani
Holambe, Pooja Patil, Padmaja Pawar, Saurabh Salunkhe , Mr. Hrushikesh Joshi, 2019
IRJET

[8] Tom M. Mitchell, Machine Learning, India Edition 2013, McGrawHill Education.

[9] https://data.gov.in/

[10] Kaggle: https://www.kaggle.com/datasets