ECOFARM: INTELLIGENT ANALYTICS FOR

SUSTAINABLE AGRICULTURE
A Project Report

submitted in partial fulfillment of the requirements

for the award of the degree of

Bachelor of Engineering

in

Computer Science & Engineering

by

Pawar Dhananjay Shekhar Roll No.66

Sawant Sayali Kishor Roll No.67
Chaudhari Abhijit Bharat Roll No.68
Dange Mayuri Arjun Roll No.69
Gaikwad Vaishnav Sanjay Roll No.70

under the guidance of

Mr. Sagar. B. Patil

Department of Computer Science & Engineering

BHARATI VIDYAPEETH’S COLLEGE OF ENGINEERING, KOLHAPUR
YEAR: 2023-24
 CERTIFICATE

This is to certify that the project report entitled “Eco-farm: Intelligent

analytics for sustainable agriculture” submitted by Mr. Pawar Dhananjay
Shekhar, Ms. Sawant Sayali Kishor, Mr. Chaudhari Abhijit Bharat, Ms.
Dange Mayuri Arjun, Mr. Gaikwad Vaishnav Sanjay for the partial fulfilment
of the requirement for the award of degree of Bachelor of Technology in
Computer Science & Engineering to the Shivaji University.

This report is record of students’ teamwork carried out by them under my

supervision and guidance.

Date:
Place:

Guide HOD

Mr. Sagar B. Patil Dr. R. P. Mirajkar

Ext. Examiner Principal

Dr. V. R. Ghorpade
 ACKNOWLEDGEMENT

It is our privilege to acknowledge with deep sense of gratitude to our

project guide Mr. Sagar B. Patil for his valuable suggestions and guidance
throughout our course of study and project.
We express our gratitude to Dr. R. P. Mirajakar (HOD) for their kind
help and co-operation and special thanks to our Principal Dr. V. R. Ghorpade for
giving us an opportunity to work on this topic.
We are highly obliged to the entire staff of the Computer Science
&Engineering Department for their kind co-operation and help. We also take this
opportunity to thank all our colleagues, who backed our interest by giving useful
suggestions and all possible help.

• Mr. Pawar Dhananjay Shekhar

• Mr. Sawant Sayali Kishor

• Mr. Chaudhari Abhijit Bharat

• Ms. Dange Mayuri Arjun

• Mr. Gaikwad Vaishnav Sanjay

MoU LETTER
SPONSERSHIP LETTER
 ABSTRACT
Internet of Things (IoT) technology has brought revolution to each and every field in human life
by making everything smart and intelligent. IoT refers to a network of things which make a self
configuring network. The development of Intelligent Smart Farming IoT based devices is day by
day turning the face of agriculture production by not only enhancing it but also making it cost
effective save wastage of water. The aim / objective of this project is to proposed IoT based
Smart Farming System assisting farmers in getting Live Data (Temperature, Soil Moisture) for
efficient environment monitoring which will enable them to increase their overall crop yield and
quality of products. The IoT based Smart Farming System being proposed via this project is
integrated with Arduino Technology mixed with different Sensors and a WiFi module producing
live data feed that can be obtained online with the help of firebase database.
 INDEX
SR. NO. CONTENT PAGE NO.

1 INTRODUCTION 01

1.1 NEED OF THE WORK 01

1.2 THESIS OVERVIEW 02

2 LITERATURE SURVEY 03

3 OUTLINE OF THE PROPOSED WORK 06

3.1 FORMALIZATION OF THE PROBLEM 06

3.2 SYSTEM ARCHITECTURE 07

3.3 LIST OF MODULES 08

3.4 METHODOLOGIES 10

4 SOFTWARE DESIGN 11

4.1 REQUIREMENT ANALYSIS 11

4.2 DESIGNED MODULES 12

5 IMPLEMENTATION DETAILS 17

5.1 TECHONOLOGIES USED 17

5.2 SNAPSHOTS 21
6 EXPERIMENTAL RESULT AND 30
TESTING

7 CONCLUSION WITH FUTURE SCOPE 31

8 REFERENCE 33

9 PUBLICATIONS 35

10 OVERALL COMPLETION CHART 36

11 FUNDING LETTER 38

12 COMPLIETION LETTER 39
 FIGURES TABLE
Figure Number Figure Description
Fig1 System Architecture Diagram

Fig2 Design Module

Fig3 DFD 0

Fig4 DFD 1

Fig5 Control Flow

Fig6 Block Diagram

Fig7 Main Page Module

Fig8 Login Page Module

Fig9 Dashboard Module

Fig10 Disease Detection

Fig11 Sensor Data

Fig12 Agri Robot

Fig13 Manual Mode

Fig14 Automatic Mode

Fig15 Irrigation System

Eco-farm: Intelligent analytics for sustainable agriculture

1. INTRODUNCTION
“Ecofarm: Intelligent analytics for sustainable agriculture” is a concept of farming
management using modern technology to increase the quantity and quality of agricultural
products, which is a new trend in Agriculture Technology. Due to population growth and demand
for resources, agriculture plays a major vital role. Building a “Ecofarm: Intelligent analytics for
sustainable agriculture” will be able to act as a major role in the agriculture economy. A Ecofarm:
Intelligent analytics for sustainable agriculture that builds an automated and transparent
agricultural process through the internet using various sensors and application software. Project
proposes an innovative smart solution using “Automated TechAgri App”.

The app contains the soil moisture, weather forecast, Agri Robot, pH level of soil and
plant disease detection. In soil moisture, it connects to the soil moisture sensor to measure the
amount of water in the soil. In traditional method seeding take lot of time and the Laborer’s had
to put more energy either using some animals or equipped tools or Tractors or some other
vehicles which used to give a lot of sound and fuel. To overcome this problem, we create Agri
robot seeder.

Plant disease detection using machine learning is a identify and detect diseases in plants.
Machine learning algorithms analyze images of plants to identify disease symptoms and classify
the type of diseases. Machine learning algorithms like KNN or neural networks are used to
classify plants. This technology can help farmers and gardeners detect diseases early and take
care of their plants and prevent diseases from spreading.

Creating a robot that navigates using GPS waypoints involves integrating hardware and
software components to enable the robot work automatically.

1.1 Need of the work

The choice of “Ecofarm; Intelligent analytics for sustainable agriculture” For the project
is driven by the aim to enhance modern agriculture. Modules like cutter, sprayer, seeder, soil
moisture, plowing and plant disease detection are integrated into an android app for ease of use.

Department of Computer Science & Engineering 1

Eco-farm: Intelligent analytics for sustainable agriculture

This smart farming approach improves efficiency, conserves resources, and ultimately benefiting
both farmers and the environment.

1.2 Thesis overview

Smart farming is a modern approach to agriculture that leverages advanced technologies
such as the Internet of Things (IoT) and deep learning to optimize various farming processes. In
this thesis, we will explore the implementation of smart farming techniques in the context of
cutter, seeder, spray, and plug operations. Specifically, we will investigate how IoT devices can
be integrated into farming equipment to gather data on crop conditions, soil moisture levels, and
other relevant metrics. By using deep learning algorithms, we can analyze this data to make more
informed decisions about when and where to plant, water, fertilize, and harvest crops.

Furthermore, we will explore how smart farming techniques can be applied to cutter,
seeder, spray, and plug operations to improve efficiency, reduce waste, and increase overall crop
yields. By automating these processes and optimizing them based on real-time data, farmers can
save time and resources while maximizing their profits. Overall, this thesis will provide a
comprehensive overview of how smart farming using IoT and deep learning can revolutionize the
agriculture industry, with a focus on cutter, seeder, spray, and plug operations.

Department of Computer Science & Engineering 2

Eco-farm: Intelligent analytics for sustainable agriculture

2. LITERATURE SURVEY
Today’s world, we have advanced technologies that can produce enough food to meet
society's demands. However, ensuring the safety and security of our food supply remains a
challenge due to factors such as climate change, declining pollinators, and plant diseases.
During pandemics like COVID-19, we rely on technology to address issues and reduce disease
transmission. Plant diseases pose a significant threat, potentially leading to droughts and
famines, causing substantial losses in commercial farming. Technologies like IoT and Machine
Learning play a crucial role in fighting these diseases.

This paper presents a Machine Learning-based solution to detect plant diseases. The
process involves three stages: Identity, Analysis, and Verification using an available database.
Researchers and scientists face various challenges when analyzing leaf diseases, including the
need for high-quality leaf images, publicly available datasets and the complexity of disease
detection due to variations in leaf colour and different plant diseases [1].

In this research paper, the focus is on the importance of plants as a vital source of energy
for humans and the significant impact of plant diseases on crop production and the economy.
Plant diseases can come to at any stage between sowing and harvesting, leading to losses.
Traditional methods of disease identification using larger fields due to their manpower,
inaccuracy, and high costs. To address this, machine learning techniques are applied to detect
diseases in plant leaves by analyzing various data aspects and classifying them into predefined
categories. [2]. The research explores different types of plant diseases and classification
techniques in machine learning used to identify diseases in various plant leaves. Key terms
include Artificial Neural Network, Classification, Disease Detection, Support Vector Machine,
and Machine Learning .

The research identifies the challenges in the agricultural field in India, emphasizing the
role of agriculture in the country's development. Plant leaf diseases are recognized as a major
factor contributing to crop production losses. The traditional method of visual identification is
found to be insufficient due to its manpower and high cost. To overcome these challenges,
machine learning is proposed as a reliable method for detecting plant leaf diseases caused by
fungi, bacteria, and viruses.

Department of Computer Science & Engineering 3

Eco-farm: Intelligent analytics for sustainable agriculture

Plant diseases compose a great threat to global food security. It requires experts to
accurately identify if the plant is healthy or not and identify the type of infection. Deep learning
techniques have recently been used to identify and diagnose diseased plants from digital images
to help automate plant disease diagnosis and help non-experts identify diseased plants. In this
paper, an end-to-end deep learning model is developed to identify healthy and unhealthy corn
plant leaves the proposed model utilizes two pre-trained convolutional neural networks (CNNs),
EfficientNetB0, and DenseNet121, to extract deep features from the corn plant images. The
proposed model is able to achieve a classification accuracy of 98.56% which shows the
superiority of the proposed model over ResNet152 and InceptionV3 that achieved a classification
accuracy of 98.37% and 96.26% respectively.

Food security is threatened by many factors, including the decline in pollinators, climate
change, plant diseases, and others. Plant diseases compose a threat to global food security and
smallholder farmers. Hence, rapid and accurate methods of identifying plant diseases are needed
to do the appropriate measures [3].

Plant disease detection is an important area of deep learning which has been addressed by
many recent methods. The system is trained and evaluated on two plant disease datasets i.e.,
PlantVillage (a publicly available dataset) and pepper disease dataset [4].

The pepper dataset is contains images from different parts of the plant such as the leaf,
pulp, and stem. The proposed system has dominated the previous works on the Plant Village
dataset and achieved 99% and 99.69% accuracy on the Pepper dataset and Plant Village datasets,
respectively.

The app contains the soil moisture, weather forecast, Agri Robot and plant disease
detection. In soil moisture, it connects to the soil moisture sensor to measure the amount of water
in the soil [13]. In traditional method seeding take lot of time and the Labourer’s had to put more
energy either using some animals or equipped tools or Tractors or some other vehicles which
used to give a lot of sound and fuel. To overcome this problem, we create Agri robot seeder. We
chose the topic of “Ecofarm: Intelligent analytics for sustainable agriculture” for our project for
several reasons. Ecofarm involves using advanced technologies to make agriculture more

Department of Computer Science & Engineering 4

Eco-farm: Intelligent analytics for sustainable agriculture

efficient and productive. In our project, we focused on integrating different module such as a
cutter, sprayer, seeder, and soil moisture and plant disease detection using machine learning. All
of this module information is displayed in a user-friendly Android app.

The cutter helps harvest crops more efficiently and saving time. The sprayer makes sure
that fertilizers and pesticides are applied accurately. The seeder helps plant seeds accurately for
suitable growth of the plant. The soil moisture sensor provides real- time data on moisture level
in the soil [14]. By integrating all of these modules into our project, we aim to make farming
easier and more accessible for farmers. Our Android app provides a simple interface that allows
farmers to control and monitor these modules remotely through their smartphones. They can
receive real-time data and analysis for managing their crops effectively. This integration
optimizes resource usage, increases productivity, and helps farmers make informed decisions.

Department of Computer Science & Engineering 5

Eco-farm: Intelligent analytics for sustainable agriculture

3. PROPOSED WORK
There are no users who don’t want to add more features over the existing system which
gives more elasticity and runs with few general applications like a smart-phone. Our system is
designed in such a way that abstains from the drawbacks of the existing system. The developed
method gives more security, comfort, and flexibility. The aim of our proposed method is to
design and to implement a low cost and open-source Smart farming that’s able to lead most of
the farms and sustain the Smart Farming. To use wireless reliable technology to interconnecting
many modules to the server of the Smart Farming, as a result, the proposed system gives more
flexibility. This system will reduce the expansion cost; will add to the elasticity of advancement.
Figure shows the block diagram of our proposed method.

3.1 Formalization of the problem

Smart farming using IoT and ML is to address the challenges faced by traditional
agriculture practices, such as inefficient resource management, limited visibility into crop health
and environmental conditions, and the need for manual intervention in various farming
processes. These challenges often result in reduced yields, wasted resources, increased costs,
and potential crop losses. The goal is to leverage IoT technologies and machine learning
algorithms to collect real-time data from sensors and devices placed in the field, analyze this
data, and gain insights to optimize farming operations. This includes monitoring soil moisture
levels, temperature, humidity, and other environmental factors, as well as detecting and
identifying diseases, pests, and nutrient deficiencies. By combining IoT and machine learning,
the aim is to improve decision-making, optimize resource usage for irrigation and fertilization,
predict and prevent crop diseases and pests, enhance overall crop health, and ultimately increase
agricultural productivity and sustainability.

Department of Computer Science & Engineering 6

Eco-farm: Intelligent analytics for sustainable agriculture

3.2 System Architecture

Fig1: System Architecture

Department of Computer Science & Engineering 7

Eco-farm: Intelligent analytics for sustainable agriculture

The overall system architecture is depending on the Node MCU, Android app, and cloud
connection system. The first block is Android App. It receives input, user input. The UI includes
a control, and monitoring system page that allow users to remotely control and monitor, sensor
and Agri Robot that includes the seeder, sprayer, plowing and cutter. Once the user gives the
input via the android application process is complete, then the output is uploaded to Firebase
and processed by Node MCU to operate. The next block is the Smart Farming architectures, the
Node MCU as the main board. Each data read by the sensor is progressed by the board and
uploaded to Firebase via the board’s built-in Wi-Fi. The remote-control system and home
automation architecture are applied two-way wireless communication with the Firebase Real-
time Database to update and retrieve the status of the irrigation system and Agri robot.

3.3 List of modules

• Main Screen Module

• User Login and Registration Module

• Dashboard Module

• Plant Disease Detection Module

• Sensor Data

• Agri Robot

• Irrigation System

To access our Agri robot we have to develop android application let us see various
modules of android application.

Main Screen Module

In first image we can see our main of our Android Application.

User Login and Registration Module

In User Login and Registration Module User have to login in the app through the
Email and Password, if user is new then user can create an account and register in app. On

Department of Computer Science & Engineering 8

Eco-farm: Intelligent analytics for sustainable agriculture

this page another option is also available that is change app language user can change
language in Marathi and Hindi also. This the benefit of our application.

Dashboard Module

On the Dashboard Module there are four modules are present that is Plant Disease
Detection Module, Sensor Data, Agri Robot, Irrigation System.

Plant Disease Detection Module

In Plant Disease Detection Module first our Agri robot capture the live image of the
crop or plant then it displays on our application then Disease Detection Module Detect the
Disease of crop and also detect the symptoms of the disease and its display on our
application.

Sensor Data

In Sensor Data Soil Moisture Sensor and DHT11 Sensor are Present. Soil Moisture
Sensor gives Data about soil moisture of the field and its also display the content present in
the soil. DHT11(Temperature and Humidity Sensor) gives the information of Realtime
weather forecast.

Agri Robot

In Agri Robot Module there are four operations are present that is Seeder, Spray,
Cutter, ploug. User can operate Seeder, Spray, and Cutter using on and off button and ploug
using up and down button.

Our Agri Robot Work also Automatically and Manually. In Manual Mode there is
live status of the field is display on our application and we can operate our Agri Robot using
Forword, backward, up and down button.

Irrigation System

When Soil Moisture of the field is low then we can irrigate now.

Department of Computer Science & Engineering 9

Eco-farm: Intelligent analytics for sustainable agriculture

3.4 Methodologies

The basic functionalities of the Smart Farming Robot using IoT and ML. The overall
system architecture for Smart Farming Robot using IoT and ML depends on the Node MCU,
Android app, and cloud connection system. Plant disease detection is a valuable application
of AI and computer vision, and deep learning models can be effective in identifying diseases
from images of plants.

NodeMCU

In this Smart Farming, we will control irrigation system and Agri using “Automated
TechAgri” android Application. The WIFI Module NodeMCU ESP8266 will receive
commands from the smartphone wirelessly through the internet.

Android app

With the help of “Automated TechAgri” android application, we can control all
devices and Sensor through the database. In Smart Farming we use firebase database.
Firebase database helps to build bridge between android application and micro-controller i.e.,
Node MCU.

Firebase

Google Firebase is a Google-backed application development software that enables

developers to develop iOS, Android and Web apps. Firebase provides tools for tracking
analytics, reporting and fixing app crashes, creating marketing and product experiment.

Google Colab

Google Colab is a cloud-based development platform that allows users to write and
execute Python code in a browser, with powerful support for machine learning and data
analysis.

Department of Computer Science & Engineering 10

Eco-farm: Intelligent analytics for sustainable agriculture

4. SOFTWARE DESIGN
4.1 Requirement Analysis

Software Requirements

• Operating System - Windows 10 home and above version, Raspbian OS.

• Language - Java, XML, Embedded C, Python.

• Source Code Editor - Android Studio, Arduino IDE, Google Colab.

• Database - Firebase.

Hardware Requirements

• Processor - i5 11th gen

• Ram - 8 GB

• HDD - 256 GB

Components

• Micro-Controller - Node-MCU

• Microprocessor - Raspberry Pi

• Sensors - DHT11, Soil Moisture.

• Other Components - Motor, Pi Camera, Servo Motors.

Department of Computer Science & Engineering 11

Eco-farm: Intelligent analytics for sustainable agriculture

4.2 Designed Modules

Fig 2: Design Module

Department of Computer Science & Engineering 12

Eco-farm: Intelligent analytics for sustainable agriculture

DFD’s

Fig 3: Level 0

Department of Computer Science & Engineering 13

Eco-farm: Intelligent analytics for sustainable agriculture

Fig 4: Level 1

Department of Computer Science & Engineering 14

Eco-farm: Intelligent analytics for sustainable agriculture

4.3 Control Flow Diagram

Fig 5: Control Flow diagram

Department of Computer Science & Engineering 15

Eco-farm: Intelligent analytics for sustainable agriculture

Block Diagram

Department of Computer Science & Engineering 16

Eco-farm: Intelligent analytics for sustainable agriculture

5. IMPLEMENTATION DEATAIL
5.1 Technologies used for the implementation

Google Colab

Google Colab is a free cloud service offered by Google that lets you run Python code
in a Jupyter notebook environment without having to set up and manage an environment on
your local machine. It provides access to GPUs and TPUs for free, which can be very useful
for running deep learning models and other computationally intensive tasks. It also allows for
easy collaboration with others by sharing notebooks and code.

Cloud

A cloud platform is used to store and retrieve live information from the sensors. It
facilitates remote monitoring and access to system data The cloud" refers to servers that are
accessed over the Internet, and the software and databases that run on those servers. Cloud
servers are located in data center’s all over the world. By using cloud computing. users and
companies do not have to manage physical servers themselves or run software applications
on their own machines.

The cloud enables users to access the same files and applications from almost any
device. because the computing and storage takes place on servers in a data center, instead of
locally on the user device. Thing Speak Cloud is a popular platform in the field of lot
(Internet of Things) that provides data storage, visualization, and analysis capabilities It
offers a cloud-based infrastructure to collect, store, and analysis data from various IoT
devices and sensors. Thing Speak is specifically designed to handle time-series data, which
makes it suitable for applications that involve monitoring and tracking changes over time

Android App

An Android application is developed to visualize the data, receive notifications, and

control the system remotely. An Android app is a software application running on the
Android platform. Because the Android platform is built for mobile devices a typical

Department of Computer Science & Engineering 17

Eco-farm: Intelligent analytics for sustainable agriculture

Android app is designed for a smartphone or a tablet PC running on the Android OS

Although an Android app can be made available by developers through their websites most
Android apps are uploaded and published on the Android Market, an online store dedicated
to these applications. The Android Market features both free and priced apps Android apps
are written in the Java programming language and use Java core libraries. They are first
compiled to Dalvik executables to run on the Dalvik virtual machine, which is a virtual
machine specially designed for mobile devices.

Java

Java is a widely used object-oriented programming language and software platform

that runs on billions of devices, including notebook computers, mobile devices, gaming
consoles, medical devices and many others. The rules and syntax of Java are based on the C
and C++ languages. One major advantage of developing software with Java is its portability.
Once you have written code for a Java program on a notebook computer, it is very easy to
move the code to a mobile device. It's also important to understand that Java is much
different from JavaScript. JavaScript does not need to be compiled, while Java code does
need to be compiled. Also, JavaScript only runs on web browsers while Java can be run
anywhere.

Java is a technology consisting of both a programming language and a software

platform. To create an application using Java, you need to download the Java Development
Kit (JDK), which is available for Windows, macOS, and Linux. You write the program in the
Java programming language, then a compiler turns the program into Java bytecode-the
instruction set for the Java Virtual Machine (JVM) that is a part of the Java runtime
environment (JRE) Java bytecode runs without modification on any system that supports
JVMs, allowing your Java code to be run anywhere.

Arduino IDE

Department of Computer Science & Engineering 18

Eco-farm: Intelligent analytics for sustainable agriculture

The Arduino Software (IDE) makes it easy to write code and upload it to the board
offline. We recommend it for users with poor or no internet connection. This software can be
used with any Arduino board.

There are currently two versions of the Arduino IDE, one is the IDE 1.x.x and the other is
IDE 2 x. The IDF. 2.x is new major release that is faster and even more powerful to the IDE
1xx. In addition to a more modern editor and a more responsive interface it includes
advanced features to help users with their coding and debugging. Arduino Software (IDE) -
connects to the Arduino boards to upload programs and communicate with them. Programs
written using Arduino Software (IDE) are called sketches. These sketches are written in the
text editor and are saved with the file extension ino.

XML

XML (Extensible Markup Language) is a markup language that defines a set of rules
for encoding documents in a format that is both human-readable and machine-readable. XML
is commonly used for storing and exchanging data on the internet and in other applications. It
is a hierarchical structure where data is stored in a tree-like format with nested elements. It
uses tags to define the structure of the data, similar to HTML. It is extensible, meaning that
you can define your own tags and attributes to suit your specific needs. It is text-based,
making it easy to read and write by humans.

XML is often used in web development for storing configuration settings, data
exchange between different systems, and in conjunction with other technologies such as
XSLT for transforming data. It is a versatile and widely supported format that is used in a
variety of applications.

Embedded C

Embedded C is a variation of the C programming language that is specifically

designed for programming embedded systems – systems that are built into devices such as
microcontrollers, microprocessors, and other programmable hardware devices. Embedded
systems typically have limited memory, processing power, and storage space. Therefore,

Department of Computer Science & Engineering 19

Eco-farm: Intelligent analytics for sustainable agriculture

Embedded C programming focuses on writing code that is efficient and optimized for these
constraints. Real-time constraints: Many embedded systems have real-time requirements,
meaning that they must respond to inputs within a specified time frame. Embedded C
programming allows developers to write code that meets these timing constraints.

Embedded C allows direct access to hardware features and peripherals of the

embedded system, such as GPIO pins, timers, and analog-to-digital converters. Low-level
programming: Embedded C programming often involves low-level programming concepts
such as bit manipulation, memory management, and direct register access. Overall,
Embedded C is a powerful language for developing software for embedded systems, and it is
widely used in industries such as automotive, consumer electronics, healthcare, and
industrial automation.

Python

Python is a versatile and high-level programming language that is known for its
simplicity, readability, and flexibility. It is widely used in various fields such as web
development, data analysis, artificial intelligence, scientific computing, and automation. Easy
to learn: Python has a clean and easy-to-understand syntax, making it an ideal language for
beginners to learn programming. Interpreted: Python is an interpreted language, which means
that you can run code directly without the need for compilation. Extensive libraries: Python
has a vast collection of standard libraries and third-party libraries that provide pre-written
code to perform various tasks, making development faster and easier.

Platform-independent: Python code is platform-independent, meaning it can run on

different operating systems without modification. Object-oriented: Python supports object-
oriented programming principles, allowing developers to create reusable and maintainable
code. Python is popular for its versatility and is used in a wide range of applications, from
web development with frameworks like Django and Flask, to data analysis with libraries like
NumPy and pandas, to artificial intelligence and machine learning projects with libraries like
TensorFlow and scikit-learn. Overall, Python is a powerful and adaptable language that is in
high demand in the industry.

Department of Computer Science & Engineering 20

Eco-farm: Intelligent analytics for sustainable agriculture

5.2 Snapshots with brief description

Main Page

Fig 7: Main page

To access our Agri robot we have to develop android application let us see various
modules of android application.

Main Screen Module

In first image we can see our main of our application.

Department of Computer Science & Engineering 21

Eco-farm: Intelligent analytics for sustainable agriculture

User Login and Registration Module

Fig 8: Login Page

Registration Module

In User Login and Registration Module User have to login in the app through the
Email and Password, if user is new then user can create an account and register in app. On
this page another option is also available that is change app language user can change
language in Marathi and Hindi also. This the benefit of our application.

Department of Computer Science & Engineering 22

Eco-farm: Intelligent analytics for sustainable agriculture

Dashboard Module

Fig 8: Dashboard

Dashboard Module

On the Dashboard Module there are four modules are present that is Plant Disease
Detection Module, Sensor Data, Agri Robot, Irrigation System.

Department of Computer Science & Engineering 23

Eco-farm: Intelligent analytics for sustainable agriculture

Disease Detection

Fig 9: Disease Detection

Plant Disease Detection Module

In Plant Disease Detection Module first our Agri robot capture the live image of the
crop or plant then it display on our application then Disease Detection Module Detect the
Disease of crop and also detect the symptoms of the disease and its display on our
application.

Department of Computer Science & Engineering 24

Eco-farm: Intelligent analytics for sustainable agriculture

Sensor Data

Fig 10: Sensor Data

Sensor Data

In Sensor Data Soil Moisture Sensor and DHT11 Sensor are Present. Soil Moisture
Sensor gives Data about soil moisture of the field and its also display the content present in
the soil. DHT11(Temperature and Humidity Sensor) gives the information of Realtime
weather forecast.

Department of Computer Science & Engineering 25

Eco-farm: Intelligent analytics for sustainable agriculture

Agri Robot

Fig 11: Agri Robot

Agri Robot

In Agri Robot Module there are four operations are present that is Seeder, Spray,
Cutter, ploug. User can operate Seeder, Spray, and Cutter using on and off button and ploug
using up and down button. Our Agri Robot Work also Automatically and Manually.

Department of Computer Science & Engineering 26

Eco-farm: Intelligent analytics for sustainable agriculture

Manual Mode

Fig 12: Manual Mode

In Manual Mode there is live status of the field is display on our application and we
can operate our Agri Robot using Forword, backward, up and down button.

Department of Computer Science & Engineering 27

Eco-farm: Intelligent analytics for sustainable agriculture

Automatic Mode

Fig 13: Automatic Mode

In Automatic Mode suppose this our farm we give GPS waypoint on your map and
click on create mission whenever we click on create mission button the waypoint array send
on raspberry pi and according to that waypoint the robot will operate.

Department of Computer Science & Engineering 28

Eco-farm: Intelligent analytics for sustainable agriculture

Irrigation System

Fig 14: Irrigation System

Irrigation System

When Soil Moisture of the field is low then we can irrigate now.

Department of Computer Science & Engineering 29

Eco-farm: Intelligent analytics for sustainable agriculture

6. EXPERIMENTAL RESULT AND TESTING

The actual accuracy is 93% after the code cleaning and adding CNN layers the
accuracy of our model is 98.40%.

Department of Computer Science & Engineering 30

Eco-farm: Intelligent analytics for sustainable agriculture

7. CONCLUSION AND FUTURE SCOPE

Smart farming using IoT and ML has emerged as a revolutionary approach to
agriculture, combining advanced technologies to enhance productivity and sustainability. By
integrating IoT devices such as sensors, drones, and smart irrigation systems, farmers can
collect real-time data on various parameters like soil moisture, temperature, humidity, and
crop health. Machine learning algorithms are then used to analyze this data, identify patterns,
and make predictions regarding crop yields, disease outbreaks, and optimal harvesting times.
This enables farmers to make data-driven decisions and take timely actions to maximize crop
yields and minimize resource wastage. Smart farming has the potential to make a significant
contribution to changing agricultural practices to increase efficiency and reduce the effect of
agrochemical waste on the ecosystem. It lays out a road to sustainable agriculture that
includes technological diversity, crops. smart farming represents a revolutionary approach to
agriculture. Farmers can optimize resource use, boost productivity, and lessen their impact on
the environment by utilizing real-time data and data-driven insights.

Future Scope

The future scope of smart farming utilizing GPS technology for autonomous
navigation holds

1. Precision Agriculture:

GPS-guided autonomous navigation enables precision agriculture practices by

allowing machinery to operate with high accuracy and efficiency. This technology facilitates
precise planting, spraying, and harvesting, resulting in optimized resource use, increased crop
yields, and reduced environmental impact.

3. Cost Reduction:

By automating navigation using GPS technology, farmers can save on labor costs
associated with operating machinery. Additionally, autonomous vehicles can operate around

Department of Computer Science & Engineering 31

Eco-farm: Intelligent analytics for sustainable agriculture

the clock, maximizing operational efficiency and reducing downtime, ultimately lowering
overall production costs

5. Remote Monitoring and Control:

With GPS-enabled autonomous navigation, farmers can remotely monitor and control
farming equipment from anywhere with an internet connection. This capability provides
flexibility and convenience, allowing farmers to manage operations efficiently even when
they are off-site or during adverse weather conditions.

Department of Computer Science & Engineering 32

Eco-farm: Intelligent analytics for sustainable agriculture

8. REFERENCES
[1] Sunil S. Harakannanavar, Jayashri M. Rudagi, Veena I Puranikmathb, Ayesha Siddiquaa,
R Pramodhini. Plant leaf disease detection using computer vision and machine learning
algorithms 305-310(2020)

[2] Sherly pushpa Annabel, machine learning for plant leaf diseases detection and
classification, April 4-6, 2019

[3] Hassan amin, End-to-End Deep Learning Model for Corn Leaf Disease Classification
Hassan amin , Ashraf Darwish , Aboul ella, Hassanien, and mona soliman March 14,2022

[4] Mobeen Ahmad, Muhammad Abdullah, hyeonloon moon, and Dongil Han, Plant disease
detection in imbalanced dataset using efficient convolutional neural network ,volume 9.

[5] Adesh V. Panchal , Subhash Chandra Patel , K. Bagyalakshmi , Pankaj Kumar , Ihtiram
Raza Khan ,Mukesh Soni. Image-based Plant Diseases Detection using Deep Learning.2021

[6] Minah Jung, Jong Seob Song, ah‑Young Shin, Beomjo Choi, Sangjin Go, Suk‑Yoon
Kwon, Juhan Park, Sung Goo Park, & Yong‑Min Kim Construction of deep learning‑based
disease detection model in plants

[7] Vijaypal Singh Dhaka , Sangeeta Vaibhav Meena , Geeta Rani , Deepak Sinwar ,
Kavaita Muhammad Fazal Ijaz , and Marcin Wozniak. A Survey Deep Convolutional Neural
Network Applied for Prediction pf Plant Leaf Diseases .12 July 2021

[8] LiLi Li1, Shujuan Zhang 2, And Bin Wan, Plant Disease Detection and Classification by
Deep Learning , 19-04-2021

[9] using deep learning for image-based plant disease detection Sharada Prasanna Mohanty
David Hughe and Marcel Salathe April 15 2018.

[10] Vijaypal Singh Dhaka, Nidhi kundu ,Geeta rani, Ester zumpano, Role of Internet of
Things and Deep Learning Techniques in Plant Disease Detection and Classification,
14 September 2023

Department of Computer Science & Engineering 33

Eco-farm: Intelligent analytics for sustainable agriculture

[11] Saurabh Umarkar and Anil Karwankar, “Automated Seed Sowing Agribot Using
Arduino” International Conference on Communication and Signal Processing, April 6-8,
2016, India

[12] Vishnu Prakash K, Sathish Kumar, Venkatesh P, Chandran A,” Design and Fabrication
of Multipurpose Agricultural Robot,” International journal of Advanced Science and
Engineering Research Volume: 1, Issue: 1, June 2016, ISSN: 2455-9288

[13] Anand Nayyar, Er. Vikram Puri, Smart Farming: IoT Based Smart Sensors Agriculture
Stick for Live Temprature and Moisture Monitoring using Arduino, Cloud Computing &
Solar Technology, November 2016

[14] Lee, M., Hwang, J., & Yoe, H. (2013, December). Agricultural Production System
Based on IoT. In Computational Science and Engineering (CSE), 2013 IEEE 16th
International Conference on (pp. 833-837). IEEE

[15] Cristhian Salinas-Simón, Alvin Robles-Yovera, Daniel Burga-Durango, IoT system for
life cycle and crop harvest monitoring in the agricultural sector in Peru,22 November 2022

Department of Computer Science & Engineering 34

Eco-farm: Intelligent analytics for sustainable agriculture

9. PUBLICATION

Ecofarm: Intelligent Analytics for Sustainable Agriculture

Sayali Sawant 1, Abhijeet Chaudhari 2, Vaishnav Gaikwad 3, Mr. Sagar B.
Patil 4, Mrs. Suchita S.Patil 5
1(Department of Computer Science And Engineering, Bharati Vidyapeeth’s College Of Engineering,
Kolhapur, India, [email protected])

2(Department of Computer Science And Engineering, Bharati Vidyapeeth’s College Of Engineering,

Kolhapur, India, [email protected])

3(Department of Computer Science And Engineering, Bharati Vidyapeeth’s College Of Engineering,

Kolhapur, India, [email protected])

4(Department of Computer Science And Engineering, Bharati Vidyapeeth’s College Of Engineering,

Kolhapur, India)

5(Department of Computer Science and Engineering, KITCOE, Kolhapur, India)

ABSTRACT

Agriculture plays a major role in developing countries like India. Farming management using modern
technology to increase the quantity and quality of agricultural products, which is a new trend in Agriculture
Technology. Technology can transform agriculture and help smallholder farmers adopt new farming approaches
making them resilient to climate change. Smallholder farmers need to produce sufficient food to match the food
demand of the growing population. To achieve this sustainable farming smallholder farmers need information.
Furthermore, they need to understand how different crops perform in changing weather patterns and varying
availability of water. The Internet of Things (IoT) and firebase database with sensor technology and energy-efficient
wireless communication could help them in agriculture. The farmers get control of their farm, it extends precision
agriculture, where management is based not only on the location and on field variability but also on data that is
triggered by real-time events.

Keywords

Internet of Things (IoT), Firebase database, Android Application, Agriculture, Machine Learning, Soil moisture,
humidity, Seeder, Sprayer.

Department of Computer Science & Engineering 35

Eco-farm: Intelligent analytics for sustainable agriculture

10. OVERALL COMPLETION CHART

PERIOD WORK TO BE COMPLETED

1st Week Group creation
2nd Week Topic selection
2nd Week Discussion
3rd Week Synopsis
4th Week Requirement gathering and analysis
4th Week System planning
5th Week System designing, implementation
6th Week Agri Robot Model designing
7th Week Login and Registration Module
7th Week Dashboard Design Module
8th Week Soil Moisture, Weather Forecast Module
9th Week Agri Robot Module
10th Week Integration of all modules, Embedded
Code implementation

11th Week Firebase Connectivity, Connectivity of a

system

12th Week Testing (Fix bugs, UI generation)

13th Week Report generation and verification

Department of Computer Science & Engineering 36

 Eco-farm: Intelligent analytics for sustainable agriculture

Roll No. Name Mobile No. Email ID Signature

66 Pawar Dhananjay Shekhar 9860468378 [email protected]

67 Sawant Sayali Kishor 9604687280 [email protected]

68 Chaudhari Abhijit Bharat 9561158578 [email protected]

69 Dange Mayuri Arjun 9075942705 [email protected]

70 Gaikwad Vaishnav Sanjay 7028358373 [email protected]

Mr. Sagar B. Patil Dr. R. P. Mirajkar

PROJECT GUIDE H.O.D CSE

Department of Computer Science & Engineering 37

Eco-farm: Intelligent analytics for sustainable agriculture

11.FUNDING LETTER

Department of Computer Science & Engineering 38

Eco-farm: Intelligent analytics for sustainable agriculture

12.COMPLETION LETTER

Department of Computer Science & Engineering 39