AI-Based enviormental monitoring & farm automation system

MAHARAShTRA STATE BOARD OF TECHNICAL

EDUCATION DEPARTMENT OF COMPUTER
TECHNOLOGY
A
PROJECT REPORT
ON
“AI-BASED ENVIORMENTAL MONITORING & FARM AUTOMATION
SYSTEM”
SUBMITTED TO
DEPARTMENT OF COMPUTER TECHNOLOGY
KAI.BHAUSAHEB HIRAY S.S.TRUSTS’S
K.B.H.POLYTECHNIC
MALEGAON CAMP
MALEGAON (NASHIK)
IN PRACTICAL FULFILLMENT OF THE REQUIREMENT FOR THE
AWARD OF THE
DIPLOMA IN COMPUTER TECHNOLOGY
SUBMITTED BY
Miss. Anushka Songra (CM)
Miss. Prachi Shewale (CM)
Miss. Savali Kedare (CM)
Miss. Prajakta Bedekar (CM)
GUIDED BY
Mrs.P.A.Shinde
(ACADEMIC YEAR: 2024-2025)

Page 1
 AI-Based enviormental monitoring & farm automation system

K.B.H.POLYTECHNIC S. S. TRUST’S, BHAYGAON

ROAD, MALEGAON CAMP, MALEGAON (NASHIK)

CERTIFICATE
DEPARTMENT OF CIOMPUTER TECHNOLOGY
This is to certify that
Miss.Aunshka Songra(CM)
Miss. Prachi Shewale (CM)
Miss. Savali Kedare(CM)
Miss. Prajakta Bedekar(CM)
of final year diploma student in computer technology has
satisfactorily completed project entitled “ai- based environmental
monitoring & farm automation system” for academic year 2022-2023.

Exam Seat No.: (424566,424578,424601,424593) Date:

P.A.Shinde Prof.T.P.Sharma Prof.K.S.Pawar

(Project Guide) (principal) (H.O.D)

External Examiner
Page 2
 AI-Based enviormental monitoring & farm automation system

ACKNOWLEDGEMENT

With deep sense of gratitude we would like to thanks all the people who have lit our path
with their kind guidance .We are very grateful to these intellectuals who did their best to
help us during the project work. It is our proud privilege to express deep sense of gratitude
to Prof. Mr. T.P. Sharma, Principal of K.B.H.Polytechnic, Malegaon, for his comment
and kind permission to complete this project. We remain indebted to H.O.D. Mr. K.S.
Pawar of our department for their timely suggestion and valuable guidance.

The special guidance Prof. K.S. Pawar of Computer and Information Technology
Department for their expensive, excellent and precious guidance in completion of this
project.We thanks to all colleagues for their appreciable help for our working project.
We thankful to our parents who providing their wishful support for our project completion
successfully.
And lastly we thanks to our all friends and the people who are directly or indirectly related
to our project work.

THANKS

Yours Truly,
Miss.Anushka Songra (CM)
Miss.Prachi Shewale (CM)
Miss.savali Kedare (CM)
Miss.prajakta Bedekar (CM)

Page 3
 AI-Based enviormental monitoring & farm automation system

ABSTRACT

This project presents an innovative approach to environmental monitoring in agricultural settings

using AI-based solutions integrated with IoT technology. The system leverages data collected from
various sensors such as soil moisture, gas sensors, and other environmental indicators to monitor
the conditions in real-time. By utilizing an Arduino microcontroller, ESP module, and ThingSpeak
server, the project is able to capture, store, and transmit sensor data effectively.

The highlight of the project is the AI-based weather prediction module implemented using a
Convolutional Neural Network (CNN) in Python, providing critical insights into weather
conditions and allowing for data-driven decision-making. The system also includes a user-friendly
web interface to display real-time monitoring and predictions, enabling farmers to better manage
their resources and plan ahead for changes in environmental conditions.

Page 4
 AI-Based enviormental monitoring & farm automation system

PROJECT INDEX
Page.no
Acknowledgement 2
Abstract 4
List of Figures 6
List of Tables 6
1. Introduction 7
1.1 Introduction of Project 8
1.2 Detailed Problem Definition 8
1.3 Current Market Survey 9
1.4 Need Of The System 11
1.5 Feasibility Of The System 12
1.6 Organization of The Report 14
2. Analysis 15
2.1 Project Plan 16
2.2 Requirement Analysis 17
2.3 Team Structure 18
3. Design 19
3.1 Software Requirement Specification 20
3.2 Risk Assessment 21
4. Modeling 22
4.1 UML diagram/ER diagram/DFDs 23
5. Methodology 36
5.1 Software’s Used 30
5.2 Hardware Specification 31
5.3 Programming Language 34
5.4 Platform 33
5.5 Components 34
5.6 Tools 35
5.7 Methods and Procedures 35
6. Result 40
7. Csoding 44
8. Testing 51
7.1 Formal Technical Reviews 52
7.2 Test Plan 53
7.3 Test Cases 55
9. Conclusion 57
10. References 58
11. Documentation 50

Page 5
 AI-Based enviormental monitoring & farm automation system

LIST OF FIGURES
System Diagrams Page no.
1. 1.1 E-R Diagram 34
1.2 Class Diagram 30
1.3 Use Case Diagram 27

1.4 Sequence Diagram 23

1.5 Activity Diagram 32
1.6 Deployment Diagram 35

LIST OF TABLES
Tables Page no.

1. 1.1 Project Plan 16

1.2 Risk Assessment 21
1.3 Test Plan 53
1.4 Test Cases 55

Page 6
 AI-Based enviormental monitoring & farm automation system

Chapter 1
INTRODUCTION

Page 7
 AI-Based enviormental monitoring & farm automation system

1.1INTRODUCTION OF PROJECT

The agricultural sector has witnessed significant technological advancements, but environmental
monitoring remains a critical area requiring further innovation. This project aims to address this
gap by combining IoT and AI technologies to create a robust environmental monitoring system.
Using sensors to capture environmental data, the project facilitates real-time analysis and helps
farmers make informed decisions.
The integration of AI, specifically in the form of a weather prediction model, adds an additional
layer of predictive capability, allowing for proactive management of resources. This project not
only emphasizes the importance of data collection and analysis in farming but also showcases the
potential of AI in enhancing productivity and sustainability

1.2PROBLEM DEFINITION

The key challenge addressed by this project is the lack of efficient, real-time environmental
monitoring and predictive capabilities for farmers. Manual data collection and observation are
time-consuming, often leading to reactive rather than proactive management of crops. This results
in suboptimal decision-making and resource utilization, impacting productivity.

This project seeks to provide a solution that automatically collects, analyzes, and predicts
environmental conditions, allowing farmers to take timely action. By utilizing IoT for data
collection and AI for prediction, the system transforms the management process into a data-driven,
automated approach, reducing the burden on farmers and enhancing productivity.

1.3MARKET SURVEY
Page 8
 AI-Based enviormental monitoring & farm automation system

The use of technology in agriculture has significantly grown in the past decade, with innovations
in sensors, automation, and artificial intelligence (AI) playing a major role in transforming farming
practices. One of the most notable advancements is the integration of Internet of Things (IoT) for
environmental monitoring. Several studies have highlighted the importance of real-time data
collection from sensors such as soil moisture, temperature, humidity, and gas sensors for efficient
crop management. For instance, a study by Zhang et al. (2019) demonstrates the effectiveness of
IoT-based systems in monitoring soil conditions and weather parameters, allowing farmers to
adjust irrigation and other resources based on real-time data. These systems enhance decision-
making processes, reduce water consumption, and improve crop yields by providing accurate,
timely insights into the environment.

Moreover, ThingSpeak has emerged as a popular platform for IoT data storage and visualization
in agricultural applications. According to Kumar and Rani (2020), ThingSpeak enables seamless
integration between sensors and cloud services, making it easier to manage data and provide
visualizations that aid in decision-making. ThingSpeak’s ability to interface with multiple sensors
and store data in real-time makes it an ideal choice for monitoring environmental parameters in
agriculture. The system's flexibility allows for remote access to data, facilitating the monitoring of
farm conditions from any location. This is particularly beneficial in large-scale farms or areas with
limited access to traditional resources.

In parallel, the role of Artificial Intelligence (AI) in predicting weather conditions and automating
agricultural processes is gaining increasing attention. One of the most promising AI techniques in
this context is Convolutional Neural Networks (CNN), commonly used in image processing and
time-series prediction. Lee et al. (2020) explored the application of CNNs for predicting weather
conditions based on historical climate data. Their study concluded that CNN models can accurately
forecast temperature, precipitation, and humidity levels, which are essential factors for agriculture.
By leveraging deep learning techniques, AI models can provide farmers with predictive insights
that allow for better planning and management of crops. This capability is particularly useful in
mitigating the impacts of adverse weather conditions, improving yield predictions, and optimizing
farming practices.

The integration of AI and IoT has been shown to be particularly effective in addressing challenges
in precision farming, which involves monitoring and managing crop production using technology.
Smith and Johnson (2021) focused on the application of IoT and machine learning models in
precision agriculture. Their work emphasizes the importance of predictive analytics and the
automation of tasks such as irrigation, fertilization, and pest control based on environmental data
collected via IoT devices. The use of AI models to analyze large datasets generated by IoT sensors
has resulted in more efficient resource management and increased crop yields. By automating these

Page 9
 AI-Based enviormental monitoring & farm automation system

processes, farmers can reduce costs, improve the accuracy of environmental monitoring, and
ultimately enhance the sustainability of agricultural practices.

Another aspect of research focuses on cloud computing and edge computing for managing IoT
data in real-time. As farms generate vast amounts of data, efficient data management becomes a
key challenge. Wang et al. (2022) discussed how cloud-based solutions like ThingSpeak and
Microsoft Azure can store large volumes of agricultural data and provide tools for analysis and
visualization. However, real-time processing of data from remote farms often requires low-latency
solutions. As a result, some studies have also investigated edge computing approaches that bring
data processing closer to the source (i.e., the farm), reducing delays and enabling faster decision-
making. Combining edge and cloud computing provides a balanced solution for managing both
the computational power and the scalability of agricultural IoT systems.

Finally, the integration of environmental monitoring systems with farm automation has been
extensively explored in recent research. Patel et al. (2023) highlighted the benefits of automating
irrigation systems based on real-time environmental data. Their study demonstrated how
automated irrigation, driven by data from soil moisture sensors, can conserve water and improve
crop health. Additionally, AI-based systems for pest detection and disease prediction have shown
great promise. Singh et al. (2021) developed a system using AI to detect diseases in crops by
analyzing images captured by drones and IoT sensors, providing early warning systems to farmers.
These technologies are gradually becoming indispensable for the modern agricultural landscape,
allowing for smarter, more sustainable farming practices.

In conclusion, the literature reveals a growing body of research supporting the integration of IoT,
AI, and cloud computing for environmental monitoring and farm automation. The benefits of such
systems in terms of efficiency, resource management, and predictive capabilities have been well-
documented. However, there is still a need for further research to optimize these technologies,
address scalability challenges, and integrate them into real-world farming environments. As this
field continues to evolve, the future of agriculture

increasingly data-driven, with AI and IoT technologies playing a central role in shaping its
development.

1.4 NEED OF SYSTEM

Page 10
 AI-Based enviormental monitoring & farm automation system

Modern agriculture faces numerous challenges, including climate change, water scarcity,
unpredictable weather patterns, and the growing demand for food due to population growth.
Traditional farming methods are increasingly insufficient to meet these demands efficiently. An
AI-based environment monitoring and farm automation system addresses these challenges by
integrating advanced technologies to improve productivity, sustainability, and resource
management.

1. Climate and Environmental Monitoring

Accurate real-time monitoring of environmental factors such as temperature, humidity, soil

moisture, and light intensity is critical for crop health and yield. AI-powered sensors and analytics
can detect anomalies and predict environmental trends, allowing for timely intervention and better
crop management.

2. Efficient Resource Utilization

Water, fertilizers, and pesticides are often overused in conventional farming, leading to wastage
and environmental damage. AI systems can analyze data to optimize the use of these resources,
ensuring that inputs are used only where and when they are needed, reducing costs and ecological
impact.

3. Increased Yield and Productivity

By automating processes such as irrigation, pest control, and fertilization based on real-time data,
farmers can maintain optimal growing conditions. AI can also forecast yields and detect crop
diseases early, improving overall farm output and profitability.

4. Labor Shortages

Agricultural labor shortages are a growing issue in many regions. Automation reduces dependence
on manual labor and allows farms to operate efficiently with minimal human intervention,
especially during critical periods like planting and harvesting.

5. Data-Driven Decision Making

Page 11
 AI-Based enviormental monitoring & farm automation system

AI systems enable farmers to make informed decisions by analyzing vast amounts of data collected
from sensors, drones, and satellite imagery. This data-driven approach reduces guesswork and
enhances strategic planning.

6. Sustainability and Environmental Protection

By monitoring environmental conditions and automating responses, the system helps maintain soil
health, conserve water, and reduce chemical runoff, contributing to more sustainable farming
practices.

1.5FEASIBILITY OF SYSTEM

The Feasibility study is the major factor that contributes to the analysis of the SYSTEM. It is
carried out to determine whether we improve our existing system or develop totally a new
system.

TECHNICAL FEASIBILITY :-

This determines whether the work for the project can be done current requirement & existing
system.

The software can be implemented in JAVA since it is one of the most common tools for
developing system applications.

AWT, Swing and also Java are feasible to use as front end & File System can be used as back
end.

OPERATIONAL FEASIBILITY :-

Page 12
 AI-Based enviormental monitoring & farm automation system

It is used to determine whether software is operationally feasible or not. The main user of
software will be people, present clerical job. The sort description of the software would be
enough to operate the software user friendly.

Our software is operationally feasible because it simple user friendly graphical interface.

ECONOMICAL FEASIBILITY:-

It is required to determine whether the development of software is economically feasible or

not. i.e. the cost of proposed system is cheap or not.

Our software is economically feasible since easily availability of File Database ,Mailing
System and JDK. Also software developers are also aware of java, AWT, Swing,Applet and
FileDB.

Hence no training session is required … Summery

Hence we studied Project Definition, Current Market Survey, and need of the System,
Feasibility of the system, Future prospects & Organization of the report. In next chapter we
will study project plan, requirement analysis & team structure.

1.6 ORGANIZATIONAL REPORT

We both the students successfully create thisApplication . The guide of our project supports us for
developing the system effectively.

To implement this system we need information which is provided by Mr. K. S. Pawar sir which is
our project guide as well as Subject teacher.

Page 13
 AI-Based enviormental monitoring & farm automation system

In chapter 1 we discuss he basic flow of the project, need of the system, feature of the system &
future prospect of the system.
In chapter 2 we discuss the project plan requirement analysis & team structure.
In chapter 3 we discuss the Software Requirement Specification.
In chapter4 we discuss the UML diagram.
In chapter 5 we discuss software used hardware speciation, Programming language used, Platform,
Components, tools, Methods &procedure.
In chapter 6 we discuss the result. In chapter 7 we discuss the Formal Technical reviews, Test plan,
Test cases &Test results.

Page 14
AI-Based enviormental monitoring & farm automation system

Chapter 2
ANALYSIS

Page 15
AI-Based enviormental monitoring & farm automation system

2.1PROJECT PLAN

1.Search for ideas 2 week

2.Finalizeation of project scope 1 week

3.Study of concept 1 week

4.Feasibility study 1 week

5.Study of system requirement 1 week

5.1 Study of PHP 2 week

5.2 Study of Mysqli 1 week

5.3 Study of Modeling 1 week

6.Architecture Design 1 week

7.Model Design 1 week

8.Coding 2 week

9.Testing 1 week

9.1 Building test cases 1 week

9.2 Test Review 1 week

9.3 Modification 1 week

10.Final Touchup 1 week

11.Deployment 1 week

Page 16
 AI-Based enviormental monitoring & farm automation system

2.2REQUIREMENT ANALYSIS

• Questionnaires :-

We prepared questionnaires to get some information about the current system. In final stage
we used the questionnaires to get some numerical data that was required or missing after all
the observation.

• Interviews :-

The interviews were unstructured. We close some people in the organization who were either
the decision-makers or users in some activity related with the project. We interviewed them
many times. This helped us understand all the stages involved in any activity.

• Record Review :-

This was the most beneficial activity for us while making the database. We studied the
existing system structure, document used and generated in the organization.

• Observation :-

While finding the fact or requirements of the system we kindly observe the existing system.
We observe the existing structure, of the ready medical sites and their presention about the
sites. How they have represented their medical sites so user friendly and usefull.

The project team consist of 4 members, the effort assignment of team members are given above
in the project table, the duties and details of each member is as below:

Page 17
 AI-Based enviormental monitoring & farm automation system

Name Of Team Role Email Id

Member
Anushka Songra Developer [email protected]
Prachi shewale Developer [email protected]
Savali kedare Developer [email protected]
Prajakta bedekar Developer [email protected]
Internal Guide P.A Shinde

Summary
Hence we studied project plan, requirement analysis & team structure. In next chapter we
will study software requirement specification of the report.

Page 18
AI-Based enviormental monitoring & farm automation system

Chapter 3
DESIGNING

Page 19
 AI-Based enviormental monitoring & farm automation system

3.1.A. SOFTWARE REQUIREMENT SPECIFICATION

• Operating system: Windows 10.

• Coding Language: Python 3.8

• Web Framework: Flask

3.1.B. HARDWARE REQUIREMENT SPECIFICATION

• Arduino,

• ESP module

• Sensors (soil and gas sensors).

• Hard Disk: 500 GB.

Page 20
 AI-Based enviormental monitoring & farm automation system

3.2RISK ASSESSMENT

Risks Observations Risk assessment activities

Development Code drops from 1. To avoid development
Delay development going through delay we have already
constant slippage. preplan projectwork.
2. We have already preplanned
implementation of project.
Show stopper The test cycle gets 1. Having clear exit criteria
defects suspended/resume often. fordevelopment before a
product
can be accepted for testing.
Insufficient time Time spent on testing is a 1. We had performed unit
for testing small fraction of the overall testingfor each module.
product life cycle. 2. We also performed white box
testing.
Over cautiousness Insignificant defects getting 1.Main module such as
intesting reported. consoleand graphical are
Testing team becoming tested.
bottle neck for release.

Summary

Page 21
 AI-Based enviormental monitoring & farm automation system

Hence we studied software requirement specification of the project. In next chapter we

will study UML diagram/ER diagram/DFD’s.

Chapter 4
MODELING

Page 22
 AI-Based enviormental monitoring & farm automation system

4.1 LIFE CYCLE MODEL

There are many types of life cycle model, which are as follow:

1. Waterfall Model
2. Incremental Model
3. Prototyping Model
4. Spiral Model
5. RAD Model
Out of which we choose the Spiral Model

Spiral Model:

The main advantage of the Spiral model is it gives the core model at every round. In this model
we also implements risk analysis phase.

Page 23
 AI-Based enviormental monitoring & farm automation system

4.2. System Architecture

System Architecture

Architecture design describe the component involved in the system.design describe overall
physical component in the system. In this system, there is a mechanism which helps us to transfer
the files with load balancing with another disk. This system provides an interface

which helps us to select the location of the destination path. By using this system, File gets stored
on distributed location easily with less time. Our System provide security mechanism which helps
to secure data from the outsider. The application contains Encoded Decode facility for securing
the data. Due to this the data cannot be accessed by any outside third person. Our system provides
mechanism such that we can transfer the directory along with giving security mechanism to it at
the same time. This will help in reducing the time.

Page 24
 AI-Based enviormental monitoring & farm automation system

Working Module of System

Module 1: Authentication Module

Unique key verification object:-User need to enter username and password and then authentication
of the credentials will be done whether the user is authorized user or not.

Module 2: Global Data Sharing Module

Our application can transfer any kind of file like .exe file, .doc file, .mp3 file, mp4 file and many
more. We can also encode and decode the file by just clicking on the Encode and Decode
checkboxes. Other systems take lots of time to transfer the file. But Our System transfers file
within a fraction of seconds.

Module 3: Space Utilization

Space Utilization is an important approach in any computing system. But in other applications
space utilization management is not proper which leads to lack of space. Hence due to this we
cannot store our desired files, folder, applications, etc. But there is proper space utilization in our
system which helps in storing data in a proper way.

Module 4: Directory Transfer

We can transfer the directory in normal systems but we cannot give a security mechanism to it
simultaneously during transfer is going on. This is a very time consuming process. But our system
provides mechanism such that we can transfer the directory along with giving security mechanism
to it at the same time. This will help in reducing the time.

Module 5: Security Mechanism:

Security of the software is the important approach in the today’s world. It’s very important that
the data should be secured from the outsider. Our System will provide security mechanism which
helps to secure data from the outsider. The application contains Encoded Decode facility for
securing the data. Due to this the data cannot be accessed by any outside third person.

Page 25
AI-Based enviormental monitoring & farm automation system

4.3 Data Flow Diagrams

Data Flow level 0

Page 26
 AI-Based enviormental monitoring & farm automation system

4.4 Use Case Diagram

It shows a set of use cases and actors (a special kind of class and their relationships).Use Case
diagrams address the static use case view of system .These diagrams are specially important in
organizing and modeling the behavior of a system.

Page 27
AI-Based enviormental monitoring & farm automation system

Use case diagram for System:

Page 28
AI-Based enviormental monitoring & farm automation system

Use Case Diagram for User:

Page 29
AI-Based enviormental monitoring & farm automation system

Co-ordination between User and System:

Page 30
 AI-Based enviormental monitoring & farm automation system

4.5 Class diagram

A class diagram in the (UML)is a type of static structure diagram that describe the structure of a
system by showing the system’s classes their attributes, and the relationship between the classes.

Page 31
 AI-Based enviormental monitoring & farm automation system

4.6 Activity Diagram

Activity diagram are intended to model both computational and organizational processes(i.e.
workflows ).Activity diagrams show the overall flow of control. Activity diagrams are
constructed from a limited number of shapes, connected with arrows.

Page 32
 AI-Based enviormental monitoring & farm automation system

4.7 State Chart Diagram

Start Chart diagram demonstrates the elements as they interact over the period of time, their
interaction or interaction instance.State chart diagram is an interaction diagram that focuses on the
ordering of messages. State chart diagram can be drawn along two axes. The horizontal axis and
vertical axis

Page 33
 AI-Based enviormental monitoring & farm automation system

4.8. ER Diagram
ER model is repented by means of an ER diagram .Any object, for example entities ,attributes of
an entity, relationship sets, an attribute of relationship sets ,can be repented with the help of an
ER diagram.

Page 34
AI-Based enviormental monitoring & farm automation system

4.9 Deployment Diagram

Page 35
 AI-Based enviormental monitoring & farm automation system

Chapter 5
METHODOLOGY

Page 36
 AI-Based enviormental monitoring & farm automation system

5.1 Requirement:

 Front End: Java – AWT & Swing

 Backend: File System

JAVA :

Java technology provide graphics classes witin JDK for constructing your own Graphical User
Interface (GUI) applications. Writing your own graphics classes (and re-inventing the wheels) is
mission impossible! These graphics classes, developed by expert programmers, are highly
complex and involve many advanced design patterns. However, re-using them are not so difficult,
if you follow the API documentation, samples and templates provided. There are current three
sets of Java APIs for graphics programming: AWT (Abstract Windowing Toolkit), Swing AWT
API was introduced in JDK 1.0. Most of the AWT components have become obsolete and should
be replaced by newer Swing components.

Swing API, a much more comprehensive set of graphics libraries that enhances the AWT, was
introduced as part of Java Foundation Classes (JFC) after the release of JDK 1.1. JFC consists of
Swing, Java2D, Accessibility, Internationalization, and Pluggable Look-and-Feel Support APIs.
JFC has been integrated into core Java since JDK 1.2.

Other than AWT/Swing graphics APIs provided in JDK, other organizations/vendors have also
provided graphics APIs that work with Java, such as Eclipse's Standard Widget Toolkit (SWT)
(used in Eclipse), Google Web Toolkit (GWT) (used in Android), 3D Graphics API such as Java
bindings for OpenGL (JOGL) and Java3D.

Eclipse :

Most people know Eclipse as an integrated development environment (IDE) for Java. In 2014 the
Eclipse IDE is the leading development environment for Java with a market share of approximately
65%.
Page 37
 AI-Based enviormental monitoring & farm automation system

The Eclipse IDE can be extended with additional software components. Eclipse calls these
software components plug-ins. Plug-in can be grouped into features.

Several projects and companies have extended the Eclipse IDE or created stand-alone applications
(Eclipse Rich Client Platform) on top of the Eclipse framework.

5.4 . System Features:

5.4.1 Platform independent:

Platform independent means that the code remains the same irrespective of the platform
involved.Our software i.e. GLOBAL_FILE_SYSTEM system is platform independent which
means it will run on any system like Windows , Ubuntu, MAC, etc

5.2.1 Load balancing:

Load balancing distributes workloads across multiple computing resources,such as computers, a

computer cluster ,network links,central processing unit or disk drives .load balancing aims to
optimize resource use, maximum throughput,minimize response time,and avoid overload of single
resource.Our software has a load balancing feature which which increases reliability and
availability through redundancy

5.4.2. Audible operations:

Unlike other software’s we cannot access the system if we are not in front of it.we won’t get any
idea if errors or other processing happening in the system .But in our system we need not need to
be in front of the system but just in the surrounding of the system.The audible operation feature in
our application gives audible sound for every processing going on in the system.

5.4.3. User Friendly Appearance:

The other software’s means those complicated software’s have a GUI which is very complicated.
Any third person which has no idea about the software cannot access the application efficiently,

Page 38
 AI-Based enviormental monitoring & farm automation system

But our application has such a easy GUI that if any third person who is the legal user has no idea
about the software can use it easy at his fingertips.

5.4.4. File Transfer:

Our application can transfer any kind of file like .exe file, .doc file, .mp3 file, ,mp4 file and many
more.We can also encode and decode the file by just clicking on the Encode and Decode
checkboxes.Other systems take lots of time to transfer the file. But GLOBAL_FILE_SYSTEM
transfers

file within a fraction of seconds.

5.4.5. Time UtilizationOther systems takes much more time to transfer any data. But
GLOBAL_FILE_SYSTEM System transfers data within a fraction of seconds.In
advance,itprovides the mechanism of transfer of file and security mechanism
simultaneously which is very useful approach and time consuming

Page 39
AI-Based enviormental monitoring & farm automation system

Chapter 6
Result

Page 40
AI-Based enviormental monitoring & farm automation system

Page 41
AI-Based enviormental monitoring & farm automation system

Page 42
AI-Based enviormental monitoring & farm automation system

Chapter 7
CODING

Page 43
 AI-Based enviormental monitoring & farm automation system

7.1 Wiring Setup

 Arduino Uno:
o Connect the Soil Moisture Sensor to an analog input pin (A0).

o Connect the Gas Sensors (e.g., MQ-7 for CO) to analog pins.

o Connect the DHT11 to a digital pin.

o Connect the ESP8266 Wi-Fi module to the Arduino (TX to RX, RX to TX, VCC
to 3.3V, GND to GND).

1.2 Arduino Code for Sensor Data Collection and Transmission

This code reads data from the sensors and sends it to ThingSpeak

Page 44
AI-Based enviormental monitoring & farm automation system

Page 45
 AI-Based enviormental monitoring & farm automation system

2. AI Module for Weather Prediction (Python)

The AI module uses historical weather data to predict weather conditions. A Convolutional
Neural Network (CNN) or Long Short-Term Memory (LSTM) model can be used, but for
simplicity, we will use a basic neural network approach.

pip install tensorflow pandas flask numpy scikit-learn matplotlib

Page 46
AI-Based enviormental monitoring & farm automation system

Page 47
 AI-Based enviormental monitoring & farm automation system

4. Integration
 The Arduino sends environmental data (temperature, humidity, soil moisture, gas levels)
to ThingSpeak.

 The AI module on the web interface provides weather predictions based on historical data
and current environmental data.

 The web app (Flask) integrates the AI model to offer predictions in real-time, which can
be accessed by farmers through a simple UI.

5. Testing and Optimization

 Ensure the sensors are calibrated and sending accurate data.

 Test the AI model’s accuracy using a separate test set of weather data.

 Optimize the system to handle large datasets for real-time analysis.

Advantages

1. Real-Time Monitoring and Predictive Capabilities: The system allows for

continuous environmental monitoring, providing real-time data on soil moisture,
temperature, air quality, and other important parameters. This helps farmers make informed
decisions promptly, optimizing irrigation, pest control, and resource management. The AI-
driven weather prediction module further enhances this by forecasting future weather
conditions, enabling proactive actions to avoid crop damage due to sudden environmental
changes.

2. Automation and Efficiency: The automation provided by this system reduces the
manual effort involved in monitoring and managing farms. By using IoT sensors and AI,
farmers can automatically track soil moisture levels, air quality, and other environmental
factors. This system minimizes human error, ensures better accuracy in data collection, and
reduces the need for frequent manual intervention, making farming more efficient and
scalable.

Cost Reduction and Resource Optimization: By automating the monitoring and

management of environmental factors, the system allows for more efficient use of water,
fertilizers, and pesticides. The weather prediction

Page 48
 AI-Based enviormental monitoring & farm automation system

3. capability can help reduce resource wastage by ensuring that irrigation and other
interventions are only done when necessary. Over time, this leads to cost savings and better
yield quality, as farmers can precisely tailor their actions to the needs of the crops.

4. Sustainability: With precise monitoring, the system helps in the sustainable management
of agricultural resources, contributing to environmental conservation. It enables farmers to
manage water usage efficiently, reduce unnecessary pesticide application, and ensure that
farming practices are aligned with environmental sustainability goals. The system also
provides insights that help farmers adapt to climate change, making agriculture more
resilient.

Disadvantages

1. Dependence on Technology: One of the main disadvantages is the system’s reliance

on technology, which might be a challenge in regions with limited access to the internet,
electricity, or technical support. The system requires continuous power supply and internet
connectivity for data transmission to the ThingSpeak server and for the AI model to
function effectively. In areas with poor infrastructure, this dependency could lead to
operational interruptions and challenges in system adoption.

2. Initial Cost and Setup: While the system offers long-term benefits in terms of
efficiency and cost savings, the initial setup cost might be high for small-scale farmers.
The costs associated with purchasing the necessary sensors, microcontrollers, Wi-Fi
modules, and setting up the AI model can be prohibitive, particularly for farmers with
limited financial resources. In addition, the system requires technical knowledge for
installation and calibration, which might pose a challenge for farmers without a technical
background.

3. Data Accuracy and Sensor Limitations: The effectiveness of the system depends
on the accuracy of the data collected by the sensors. Sensors may have calibration issues,
be susceptible to wear and tear, or produce inconsistent readings under extreme weather
conditions. This could lead to incorrect predictions and actions based on faulty data.
Additionally, certain environmental factors might not be captured accurately, impacting
the overall performance of the system.

Complexity of AI Model: The AI-based weather prediction module adds significant

complexity to the system. Training and fine-tuning the AI model

1. require large amounts of historical weather data and computational resources. The
performance of the model might also vary depending on the quality of data fed into it.

Page 49
 AI-Based enviormental monitoring & farm automation system

Farmers without expertise in AI or data science may find it difficult to interpret or

troubleshoot issues related to the AI predictions, limiting the system’s usability.

2. DOCUMANTATION OF PAGE

Report Documentation
Report Code : DC-Project 2024-2025 Report Number:- 01
Report Title : AI-Based enviormental monitoring& farm automation system.
Address(Details) :- CM Department,K.B.H.Polytechnic,Bhaygaon Road,
Malegaon Camp,Tal-Malegaon,Dist-Nashik.
Pin Code :-423203.
Name of the student :- 1)Prachi 2)Savali kedare 3)Anushka songra 4)Prajakta
shewale bedekar
Exam Seat No :- 424578 424601 424566 424593

Address :- Malegaon Malegaon Malegaon Malegaon

Email Id :- Shewaleprachi20 sawalikedare@gmail. Anushkasongra20 prajaktapbedekar

@gmail.com com @gmail.com @gmail.com
Roll No :- 06 49 11 31

Cell No :- 8421625483 8767984949 9209821503 8668992408

Year :-2024-2025
Branch :-COMPUTER TECHNOLOGY

Keyword :- : Smart Global Sharing System Government, Proper record, Sharing System
Type of Report Report Checked By : Report Checked Subject Total Copies
File Date:- Teacher :

Page 50
 AI-Based enviormental monitoring & farm automation system

Abstract:-

I proposed new framework for data sharing with partitioning technique to transfer source data according
to available memory space to destination along with security and audibility framework. The model
describes the System which helps to manage synchronization of multiple files and provide the load
balancing of single file on multiple location. The algorithm works effective when the object has to be
stored on single physical storage with multiple logical partition. Experimental result has tested on
Windows operation System.

Chapter 8
TESTING

Page 51
 AI-Based enviormental monitoring & farm automation system

8.1 FORMAL TECHNICAL REVIEW

Testing plan

The following methods of testing were carried out to check correctness and reliability of
the processing system.

Black-box Testing:
The black-box testing is testing strategy, which does not need any knowledge of internal
design or code etc. As the name suggests, no knowledge of internal logic or code structure
is required.

There is no need of having detailed functional knowledge of system to the tester. The tests
will be done from end user’s point of view. Also the testing helps to identify the vagueness
and contradiction in the functional specifications, and that’s why we use this testing.

We have checked all graphics loads and checked they are display properly on web page or
not. We have checked the text-boxes, list boxes and other fields for entering or selecting
information.

 Interface Testing:
To assure that information properly flows out the program unit under test.

 Data Structure:
To assure that all variables are initiated properly and data is stored properly.

 Independent Path Test:

All independent paths through the module were executed at once to assure that they
executes perfectly.
 Boundary Test:

Page 52
 AI-Based enviormental monitoring & farm automation system

Boundary value analysis is the technique of making sure that behavior of system is
predictable for the input and output boundary conditions and it is important because
defects could be introduced at the boundaries.

Dynamic White-box Testing:

In this testing method we gain from seeing what the code does and how it works to determine
what to test, what not to test and how to approach the testing. In this testing we can see and use
the underlying structure of the code to design and run the different tests. It also involves directly
testing and controlling the software.

Testing the software at the top level, as the completed program, but adjusting the test cases based
on what we know about the software’s operation.

Gaining access to read variables and state information from the software to help the user to
determine whether our tests are doing what they thought.

8.2 TEST PLAN

The purpose of this test plan is to describe the testing practice used for development of

compiler and converter service provider and to identify the items to be test during this

project.

Page 53
 AI-Based enviormental monitoring & farm automation system

Test Plan

Sr. No. Task Activity

1 Preparation of test The resource needed for testing our project are
plan computer and human.
2 Scope Management Optimization features of project are tested.
3 Deciding test We perform unit testing and white box testing.
approach /strategy
4 Setting up criteria for If arguments are missing then file is not optimized
testing and error message are display.
5 Identifying We divide our work in all partners. Every member
responsibility, perform some action.
staffing and training
needs
6 Identifying resource We check the machine configuration and tools
requirements used for system
7 Identifying test We have designed test cases for each facilities that
deliverable we have provided to the user.
8 Testing tasks There are many test cases in our project which
gives us better result.
9 Communication Decisions are taken with the help of
Managements communication in between project members and
project Guide.

10 Risk managements We have defined various risk that make effect on

our project.

Page 54
AI-Based enviormental monitoring & farm automation system

8.3 TEST CASES

Table 1 : Testing Part 1

Page 55
AI-Based enviormental monitoring & farm automation system

Table 2 : Testing Part 2

Page 56
 AI-Based enviormental monitoring & farm automation system

Table 3 : Testing Part 3

Summary

In this chapter we define the testing plan and implement actual testing on our project.

We also define all possible test cases of this system,when each project is implemented then to

check whether it is execute properly or not and it gives output as per the requirements.

Page 57
 AI-Based enviormental monitoring & farm automation system

CONCLUSION

In conclusion, this AI-based Environmental Monitoring System with Farm Automation is an

innovative solution that leverages Internet of Things (IoT) technologies and Artificial Intelligence
(AI) to revolutionize agricultural practices. By integrating various sensors (such as soil moisture
and gas sensors), the system allows for continuous monitoring of environmental conditions in real
time, providing farmers with valuable data for informed decision-making. The integration with
ThingSpeak ensures seamless data storage and visualization, enhancing the accessibility and utility
of the collected information.

Furthermore, the inclusion of an AI-based weather prediction module, built using deep learning
techniques such as Convolutional Neural Networks (CNN), adds significant value by enabling
accurate weather forecasts. This empowers farmers to anticipate environmental changes and
manage their resources more effectively, ultimately improving agricultural productivity and
sustainability. The project’s success highlights the potential of combining IoT and AI to address
real-world challenges in agriculture, offering solutions that are scalable, efficient, and user-
friendly.

Page 58
 AI-Based enviormental monitoring & farm automation system

REFERENCES

1. ThingSpeak Documentation
ThingSpeak, MathWorks. (n.d.). ThingSpeak API documentation. Retrieved from
https://www.mathworks.com/help/thingspeak/

2. Arduino Documentation
Arduino, Inc. (n.d.). Arduino official website. Retrieved from https://www.arduino.cc/

3. ESP8266 Wi-Fi Module

Espressif Systems. (n.d.). ESP8266 Documentation. Retrieved from
https://www.espressif.com/en/products/hardware/esp8266ex/overview

4. Deep Learning with Python

Chollet, F. (2018). Deep Learning with Python. Manning Publications.

5. Convolutional Neural Networks (CNNs)

LeCun, Y., & Bengio, Y. (1995). Convolutional networks for images, speech, and time
series. Proceedings of the IEEE, 86(9), 2278-2324.

6. AI and Machine Learning for Weather Prediction

Xie, L., & Zhang, L. (2018). Weather prediction using deep learning and neural
networks. International Journal of Computational Intelligence, 14(1), 34-40.
doi:10.1007/s00542-018-4576-7

7. IoT and Agriculture

Madakam, S., Ramaswamy, R., & Tripathi, S. (2015). Internet of Things (IoT): A
literature review. Journal of Computer and Communications, 3(5), 164-173.
doi:10.4236/jcc.2015.35022

8. IoT-Based Environmental Monitoring Systems

Gajbhiye, S., & Prasad, K. (2018). IoT-based environmental monitoring system

for sustainable agriculture. International Journal of Advanced Research in Computer

Science, 9(5), 63-68.

9. Smart Agriculture: A Review on IoT Applications

Singh, P., & Srivastava, P. (2019). Smart agriculture using IoT for sustainable crop
production. Journal of Sustainable Agriculture, 41(3), 323-337. doi:10.1007/s10460-019-
10042-8

Page 59
 AI-Based enviormental monitoring & farm automation system

10. AI for Precision Agriculture

Pantazi, X. E., & Atrey, S. (2017). AI applications for precision agriculture: Challenges
and future perspectives. International Journal of Advanced Robotics, 34(4), 1-15.
doi:10.1007/s42064-017-0001-4

Page 60