SMART AGRICULTURE SYSTEM*

* Note: Sub-titles are not captured in Xplore and should not be used

1st Given Name Surname 2nd Given Name Surname 3rd Given Name Surname
dept. name of organization (of Aff.) dept. name of organization (of Aff.) dept. name of organization (of Aff.)
name of organization (of Aff.) name of organization (of Aff.) name of organization (of Aff.)
City, Country City, Country City, Country
email address or ORCID email address or ORCID email address or ORCID

4th Given Name Surname 5th Given Name Surname 6th Given Name Surname
dept. name of organization (of Aff.) dept. name of organization (of Aff.) dept. name of organization (of Aff.)
name of organization (of Aff.) name of organization (of Aff.) name of organization (of Aff.)
City, Country City, Country City, Country
email address or ORCID email address or ORCID email address or ORCID

Abstract—India is an agricultural country. The agriculture sector exceedingly year by year. control of IoT devices for smart
is facing Numerous challenges such as water scarcity, climate agriculture. Different sensors in the agriculture sector play a
change, and low productivity due to outdated farming practices. significant role in IoT technologies [2]. Connecting multiple
Therefore, there is a dire need to introduce modern technology
into the agri culture sector to enhance its productivity and interconnected devices, such as several sensors, drivers and
efficiency. This project presents an IOT Based Smart Agriculture smart objects, to mobile devices through the use of the Internet
Monitoring System aimed at increasing agricultural productiv [3].The sharing of information with intelligent control and
ity by automating and optimizing crop management. The system decision-making services consists of IoT services due to the
uses various sensors to monitor environmental conditions in real many cloudbased remote data acquisition. Such capabilities
time. The data collected are processed by a microcontroller and
wirelessly transmitted to a web application that provides farmers can provide efficient production to the smart agriculture in-
with visualized information about their crops. The system is dustry. The conventional approach of agriculture is to enhance
designed to be affordable and easy to use, allowing farmers to modernized cultivation with the exploration of the IoT region
monitor their crops remotely and take the neces sary actions to of interest in the agricultural field [4].IoT development has
optimize their growth. By providing farmers with real-time data given heaps of advantages in all sectors over the last decade.
on their crops, the system can help them make informed decisions
about the use of water and fertilizers, pest control, and harvest The IoT is a key element for the integration of scalable
times. This, in turn, can lead to increased crop yields, reduced software, hardware, cost-effective process, self-sustainable,
costs, and improved profitability. The project also has future and smart decision for smart farming. Scheduling including
implica tions, including the integration of machine learning all activities such as irrigation, plant growth, identification
and artificial intelligence technologies to further optimize crop of disease by its leaf, and production management in the
management. With the increasing demand for food production
and the need to address the challenges of climate change and smart agriculture sector [5].In the overall situation, the cost
food security, this project. serves as a promising solution for is very reasonable for all farming solutions with IoTbased
sustainable agriculture smart agriculture. Researchers introduced several integrated
Index Terms—Iot(Internet of things), machine learning, agricul- advanced technologies to increase productivity in the agri-
ture, Automation cultural sector [6].Therefore, in order to achieve the target
progressively, many new innovations can be combined with
I. I NTRODUCTION traditional farming. With multiple sensors and described in
The fast-growing world population can be expected around green nature, the IoT can smartly build agriculture [7].
10 billion in the year 2060 as per the survey. However,
A. Problem Identification
the demand for food grain increases abruptly these years
due to population. Unfortunately, the food grain is indirectly Traditional agricultural practices often rely on manual moni-
proportional to growth in population. Food production should toring, which leads to inefficient resource usage, low produc-
be improved for this reason in coming years globally [1].The tivity, and delayed response to environmental changes. Farmers
IoT has also recently given a strong impression of the agri- face challenges such as unpredictable weather, water scarcity,
culture sector with a wide range of sensors used for various pest infestations, and lack of real-time data for decision-
smart agriculture targets. The IoT applications are increased making. These issues contribute to crop losses and reduced
profitability. The absence of integrated systems for monitoring
Identify applicable funding agency here. If none, delete this. soil moisture, temperature, and crop health further limits
agricultural efficiency. To address these challenges, there is a in the agricultural field, D. V. V. Devi and G. M. Kumari,
need for a smart agriculture system that leverages IoT sensors [10] found that the yield of agriculture is decreasing day by
and automation to optimize farming processes, improve crop day. However, use of technology in the field of agriculture
yield, and promote sustainable resource management. plays important role in increasing the production as well as in
reducing the extra man power efforts. Some of the research
B. Objective of the paper attempts are done for betterment of farmers which provides
The primary objective of this paper is to develop a Smart the systems that use technologies helpful for increasing the
Agriculture System that utilizes IoT technology to enhance the agricultural yield.
efficiency and sustainability of modern farming practices. The A remote sensing and control irrigation system using dis-
system aims to monitor key environmental parameters such tributed wireless sensor network aiming for variable rate
as soil moisture, temperature, humidity, and light intensity in irrigation, real time in field sensing, controlling of a site
real time using embedded sensors. By collecting and analyzing specific precision linear move irrigation system to maximize
this data, the system can support automated decision-making the productivity with minimal use of water was developed
processes for irrigation and crop management. The goal is by Y. Kim . The system described details about the design
to reduce resource wastage, improve crop yield, and provide and instrumentation of variable rate irrigation, wireless sensor
farmers with actionable insights, thereby promoting precision network and real time in field sensing and control by using
agriculture and contributing to a more productive and environ- appropriate software. The whole system was developed using
mentally friendly agricultural process. five in field sensor stations which collects the data and send
it to the base station using global positioning system (GPS)
C. Organization of the paper where necessary action was taken for controlling irrigation
Section I: Introduction provides a background on smart according to the database available with the system. The
agriculture systems, outlining the need for technology-driven system provides a promising low cost wireless solution as well
solutions in modern farming. It also presents the objectives as remote controlling for precision irrigation. [11]
and motivation behind this project. Section II: Literature In the studies related to wireless sensor network, Q. Wang, A.
Review explores previous research and existing smart farming Terzis, and A. Szalay [12] measured soil related parameters
technologies. It analyzes their approaches, strengths, and limi- such as temperature and humidity. Sensors were placed below
tations, providing a foundation for this project’s development. the soil which communicates with relay nodes by the use
Section III and Section IV: System Overview and Proposed of effective communication protocol providing very low duty
Solution explains the hardware and software architecture cycle and hence increasing the life time of soil monitoring
used to build the smart agriculture system. Section V: Data system. The system was developed using microcontroller, uni-
Collection provides the collection of our data using hardware versal asynchronous receiver transmitter (UART) interface and
module. Section VI: Results and Discussion presents the sys- sensors while the transmission was done by hourly sampling
tem’s output, analyzes the collected data, and compares it with and buffering the data, transmit it and then checking the status
expected performance. Section VII: Conclusion summarizes messages. The drawbacks of the system were its cost and
the findings and suggests possible improvements or extensions deployment of sensor under the soil which causes attenuation
for the system. of radio frequency (RF) signals.
II. LITERATURE REVIEW III. SYSTEM OVERVIEW
In this section we reviews recent work related to ”Smart The paper consist of four sections; node1, node2, node3 and
Agriculture System”. PC or mobile app to control system(Shown in Figure 1). In the
S. Nandurkar, V. Thool, and R. C. Thool discus that the present system, every node is integration with different sensors
newer scenario of decreasing water tables, drying up of rivers and devices and they are interconnected to one central server
and tanks, unpredictable environment present an urgent need via wireless communication modules. The server sends and
of proper utilization of water. To cope up with this use receives information from user end using internet connectivity.
of temperature and moisture sensor at suitable locations for There are two modes of operation of the system; auto mode
monitoring of crops is implemented in. [8] and manual mode. In auto mode system takes its own decisions
An algorithm developed with threshold values of temperature and controls the installed devices whereas in manual mode
and soil moisture can be programmed into a microcontroller- user can control the operations of system using android app
based gateway to control water quantity. The system can be or PC commands.
powered by photovoltaic panels and can have a duplex commu-
IV. PROPOSED SOLUTION
nication link based on a cellularInternet interface that allows
data inspection and irrigation scheduling to be programmed A. System Architecture
through a web page. [9] In this section we can see the circuit diagram (Shown in
The technological development in Wireless Sensor Networks Figure 2) of our project which represents an integrated smart
made it possible to use in monitoring and control of green- soil monitoring system designed around an Arduino Uno
house parameter in precision agriculture. After the research microcontroller, interfacing with multiple sensors and display
 A breadboard is employed for distributing power and simpli-
fying interconnections, especially for the 5V and GND lines
which are shared across various modules. Red wires typically
denote power (5V or 12V), while black lines are used for
ground connections, and yellow or blue wires represent data or
signal lines. The inclusion of both an OLED and LCD display
Fig. 1. System Overview
allows for simultaneous multi-format output, possibly enabling
basic readings on the LCD and more detailed graphical output
on the OLED. The OLED’s compact size makes it suitable for
modules to assess and communicate soil conditions. Central integrating into smaller form-factor devices or for dual-display
to the setup is the Arduino Uno, which acts as the main scenarios where space is limited.
processing unit. It receives data inputs from various sensors The system is likely designed for agricultural or environ-
and sends outputs to the display modules. Connected to the mental monitoring applications, where constant soil param-
Arduino is a 16x2 LCD display with an I2C driver and eter readings are essential. By combining both moisture and
a 0.96-inch OLED display. Both of these display units are nutrient sensors, it provides a comprehensive understanding
used for visualizing sensor data in real-time. The I2C driver of soil health. The Arduino processes the sensor data and
simplifies the connection of the LCD by reducing the number then displays it on the two different screens for easy reading
of data lines required, using only the SDA and SCL lines by users. This approach facilitates both local monitoring and
for communication, which are linked to the A4 and A5 pins could be extended to include wireless data transmission for
of the Arduino, respectively. Similarly, the OLED display remote monitoring in advanced implementations. The overall
also communicates via I2C, connected to the same pins, thus design reflects an efficient and modular approach to smart
sharing the I2C bus. agriculture, enabling real-time soil condition assessments with
the potential for further integration into automated irrigation
or nutrient delivery systems.
B. Component Used
The circuit design utilizes a range of components listed in
the table, each playing a vital role in the development of a
smart soil monitoring system. At the heart of the system is
the Arduino UNO, which serves as the main microcontroller
responsible for collecting, processing, and transmitting data
from various sensors and modules. The Gas Sensor (MQ-
135) is included to detect the presence of harmful gases in
the environment, ensuring the air quality around the soil is
monitored for toxic substances that may impact plant health.
To monitor the climatic conditions of the soil environment,
a Temperature and Humidity Sensor (DHT-11) is integrated,
which provides essential data on ambient temperature and
Fig. 2. System Architecture humidity levels. Soil hydration is tracked using the Soil
Moisture Sensor (REHSS2), which measures the water content
The soil moisture sensor is connected to the analog pin A0 in the soil, helping to determine when irrigation is necessary.
of the Arduino and powered through the 5V and GND pins. For displaying real-time sensor data, a 16 x 2 LCD Display
This sensor detects the volumetric water content in the soil and with I2C Module is used, which reduces the number of
sends an analog signal to the Arduino, which can be processed connection wires needed and displays readable outputs of
to determine soil dryness or wetness. Alongside this sensor is sensor values. In addition to this, an NPK Sensor is deployed
a more advanced soil NPK sensor, which measures the levels to measure the nutrient levels in the soil, specifically nitrogen,
of Nitrogen (N), Phosphorus (P), and Potassium (K) in the phosphorus, and potassium content, giving insights into soil
soil, critical for assessing soil fertility. This sensor is powered fertility. To power these components, especially high-power
by an external 12V power supply and is interfaced through ones like the NPK sensor, a 12V Power Supply using 4 x
a serial communication protocol via an RS485 module. The 3V lithium-ion cells is utilized to ensure stable and sufficient
RS485 module, which facilitates robust long-distance data voltage.
transmission, connects to the Arduino’s digital pins (D10 and On the software side, development begins with the Arduino
D11 in this diagram) and shares power and ground lines IDE, which is used to write, compile, and upload code to
with the external sensor. This communication setup ensures the Arduino UNO. For creating the web interface of the
accurate data transmission between the NPK sensor and the application, HTML and CSS are employed to build the front-
Arduino. end layout, while Node JS and Express JS handle the backend
functionality and server communication. For data storage, C. Hardware Component
MongoDB is used as the database solution to store sensor In this section we can see final look of our project 3
readings and logs efficiently. To enhance system intelligence
and data analysis, Python is used for writing scripts and
implementing machine learning algorithms. For visual rep-
resentation of collected data and trend analysis, tools like
Google Colab and Matplotlib are used, allowing for cloud-
based execution and graphical plotting of results respectively.
Each of these components, as listed in the table(shown in
Table I), work together to create a comprehensive, responsive,
and scalable soil monitoring system capable of real-time
environmental sensing and data visualization.

TABLE I
H ARDWARE AND S OFTWARE C OMPONENTS U SED Fig. 3. Final Look of Project with Arduino UNO

SL.NO COMPONENT SPECIFICATION USED

USED D. Data Flow Diagram
1 ARDUINO UNO ATmega328P Brain of the hard- In this subsection we can see the different level of Data Flow
ware module.
2 GAS SENSOR MQ-135 This device is use Diagram of our syatem. This diagram (Figure 4) represents
to detect differ- the process flow of an IoT-based smart agriculture system that
ent Toxic gases inte grates data collection, training, and prediction. It begins
which is harmful
for food and Crop with crop data retrieved from hardware and recommended
3 TEMPERATURE DHT-11 This device is use NPK(Nitrogen, Phosphorus, Potassium) values, which are used
AND to take data about to create training data. The training data feeds into a model
HUMIDITY Temperature and
SENSOR Humidity.
training process to develop a predictive model. User inputs
4 SOIL REES52 A tool that gauges such as soil nutrient levels and moisture, along with real-time
MOISTURE the quantity of sensor data, are processed through the trained model to provide
SENSOR water in the soil
is called a soil
predictions for optimizing agricultural prac tices. The system
moisture sensor. emphasizes data-driven decisions to enhance crop management
5 LCD WITH I2C 16 X 2 LCD DIS- It shows all the efficiency.
MODULE PLAY reading of varius
sensor.
6 NPK SENSOR RS-485 A tool that gauges
the quantity of ni-
trogen, potassium
and Phosphorus in
the soil.
7 12 V POWER 4 X 3V LITHIUM To powerup the
SUPPLY ION CELL NPK Sensor
8 ARDUINO IDE LATEST Write source code
VERSION to all of the men-
tioned sensor.
9 HTML, CSS HTML To design Fron-
(VERSION tend of our appli-
5) AND CSS cation.
(VERSION 3)
10 NODE JS VERSION To write Backend
22.15.0 Functionality.
11 EXPRESS JS VERSION 5.1.0 To connect hard- Fig. 4. Level 0 DFD
ware module to
our website using The diagram (figure 5) depicts the comprehensive workflow
socket.io package
available in ex- of an IoT-based smart agriculture system, combining machine
press. learning, a Flask application, and IoT hardware to enable
12 MONGO DB MongoDB 8.0 it is used for stor- efficient and automated agricultural management. The process
ing data for future
experiment.
begins with the machine learn ing component, where data
13 PYTHON VERSION 3.12 To write is collected from various sources, including environmental
machine learning sensors, historical data, and user inputs. The collected data
algorithm.
14 GOOGLE LATEST Used for write
undergoes processing to clean, normal ize, and prepare it
COLAB VERSION python code for analysis. Feature selection is then applied to identify the
environment. most relevant parameters, such as soil moisture, temperature,
nutrient levels, and weather patterns, which directly impact
crop health and productivity. These features are utilized to Algorithm 1 Read Serial Data and Send to Frontend via
train a predictive model, which is fine-tuned to deliver accurate WebSocket
and actionable insights. The final trained model is exported 1: Import required modules:
and integrated into the system for real-time use. The Flask 2: Load express to serve frontend files.
application serves as the middleware that connects the machine 3: Load http to create a server.
learning model with the IoT hardware and user interfaces. It 4: Load serialport to communicate with hardware.
merges data from the trained model and the IoT hardware, 5: Load @serialport/parser-readline to parse in-
ensuring seamless integration and accurate predictions. The coming serial data.
model processes incoming data from the hardware. 6: Load socket.io for real-time communication.
7: Initialize Express and HTTP Server:
8: Create an Express app instance.
9: Create an HTTP server using the Express app.
10: Attach socket.io to the HTTP server.
11: Serve static frontend files:
12: Use express.static("public") to serve frontend
content.
13: Configure Serial Port:
14: Open serial port (e.g., “COM3”) with a baud rate of 9600.
15: Create a line parser using Readline and pipe it to the
serial port.
16: Process incoming serial data:
17: On receiving a line of data from the serial port:
18: Split the line by commas.
19: Convert each split value to a number.
20: Assume values are: moisture, nitrogen, phosphorus,
potassium.
21: Emit these values to all connected clients via
Fig. 5. Level 1 DFD socket.io.
22: Start the server:
23: Listen on port 3000.
E. Algorithm Used
24: Log the URL to the console.
This algorithm outlines the process of reading serial data
from hardware devices and sending it to a web-based frontend
This algorithm explains how to display sensor data on a
using WebSocket technology. It begins by importing necessary
webpage and suggest suitable crops based on real-time values
Node.js modules such as express for serving web pages, http
using WebSocket communication. It begins by establishing a
for server creation, serialport to communicate with hardware,
connection to the backend server using socket.io, which en-
and @serialport/parser-readline for parsing incoming serial
ables the frontend to receive continuous data updates without
data line by line. The socket.io library is also included to
refreshing the page. Next, it accesses specific HTML elements
enable real-time communication between the server and con-
on the page—such as moistureSpan, nitrogenSpan, phospho-
nected web clients. After importing the modules, an Express
rusSpan, potassiumSpan, and suggestedCrop—by their unique
application and an HTTP server are initialized, and socket.io
IDs so they can be dynamically updated. Once the WebSocket
is attached to the server to handle WebSocket communication.
connection is active, the frontend listens for sensorData events
The algorithm serves static frontend files from a designated
from the backend. When data is received, it extracts four
directory using express.static(”public”). Next, it configures the
key parameters: moisture, nitrogen (N), phosphorus (P), and
serial port by specifying a port name (e.g., ”COM3”) and a
potassium (K). These values are then used to update the
baud rate of 9600, which is typical for Arduino communi-
text content of their corresponding HTML elements on the
cation. A line parser is created using Readline and linked
webpage, providing a live view of the current soil conditions.
to the serial port to handle incoming data. When the serial
The algorithm also includes a function called suggestCrop()
port receives data, it is processed by splitting the line into
that evaluates the sensor data against predefined thresholds
separate values using commas, converting each to a number,
to recommend a suitable crop. Based on different ranges of
and assuming they represent moisture, nitrogen, phosphorus,
moisture and nutrient levels, it suggests crops such as Rice,
and potassium levels. These values are then broadcast to all
Wheat, Maize, or Millet. If none of the conditions are met, it
connected frontend clients using socket.io. Finally, the server
alerts the user that the crop could not be detected and advises
listens on port 3000 and logs the server URL.
checking the sensors. Finally, the result of this evaluation is
displayed in the suggestedCrop HTML element, offering the
user a real-time crop recommendation.
Algorithm 2 Display Sensor Data and Suggest Crop SL.NO Date Data Location Soil Moisture N P K
1 01/11/2024 Bandel 82.00 90 42 43
1: Initialize WebSocket Connection 2 10/11/2024 Hooghly 80.31 85 58 41
2: Connect to the backend server using socket.io 3 15/11/2024 Chinsurah 82.32 60 55 44
4 15/12/2024 Chandannagar 80.15 74 35 40
5 20/12/2024 Mankundu 81.60 78 42 42
3: Get HTML Elements 6 01/01/2025 Bhadreswar 83.37 69 37 42
4: Access the following HTML elements by their IDs: 7 10/01/2025 Baidyabati 82.63 69 55 38
8 15/01/2025 Shrirampur 82.89 94 53 40
5: moistureSpan, nitrogenSpan, 9 20/01/2025 Rishra 83.53 89 54 38
phosphorusSpan, potassiumSpan, 10 30/01/2025 Bally 83.03 68 58 38
suggestedCrop TABLE II
S OIL M OISTURE AND NPK VALUES AT DIFFERENT LOCATIONS ALONG
THE G ANGES AREA IN H OOGHLY.
6: Receive Sensor Data
7: Listen for sensorData events from the backend
8: On receiving data, extract:
9: moisture, nitrogen, phosphorus, potassium VI. E XPERIMENTAL R ESULTS AND D ISCUSSION
The table (shown in table III) compares the performance of
10: Update UI three machine learning models — KNN, SVM, and Logis-
11: Set the textContent of each HTML element with the tic Regression — based on Accuracy, Precision, and Error
respective values Ratio. Among them, the KNN (K-Nearest Neighbors) model
performs the best. It achieves the highest accuracy (0.97) and
12: Suggest Crop Based on Conditions a high precision (0.98) while maintaining a very low error
13: Call suggestCrop(moisture, nitrogen, ratio (0.02). Although SVM shows perfect precision (1.00),
phosphorus, potassium) its overall accuracy (0.91) and higher error ratio (0.08) make
14: function SUGGEST C ROP(moisture, N, P, K) it less reliable compared to KNN. Logistic Regression also
15: if moisture > 700 and N > 400 and P > 300 and performs well with 0.96 accuracy and 0.96 precision, but it
K > 300 then slightly lags behind KNN. Therefore, KNN is considered the
16: return “Rice” best algorithm here because it offers a balanced combination
17: else if moisture > 500 and N < 300 and P > 250 of high accuracy, high precision, and minimal error.
and K > 200 then
18: return “Wheat” Model Accuracy Precision Error Ratio
19: else if moisture > 300 and N > 200 and P > 150 KNN 0.97 0.98 0.02
and K > 150 then SVM 0.91 1.00 0.08
Logistic Regression 0.96 0.96 0.04
20: return “Maize”
TABLE III
21: else if moisture < 300 and N < 200 and P < 150 P ERFORMANCE COMPARISON OF KNN, SVM, AND L OGISTIC
and K < 150 then R EGRESSION MODELS .
22: return “Millet”
23: else
24: return “ Crop not detected — Check sensors!” A. Accuracy Comparison graph
25: end if
26: end function

27: Display Suggested Crop

28: Show the result of suggestCrop() in the
suggestedCrop element

V. DATA COLLECTION
The provided data sheet (shown in table II) shows soil health
parameters collected from different locations along the Ganges
area in Hooghly, West Bengal. For each location, the soil
moisture percentage, along with Nitrogen (N), Phosphorus Fig. 6. Accuracy Comparison Graph
(P), and Potassium (K) values, have been recorded using IoT
sensors. In terms of accuracy (SVM, both KNN and Logistic Regres-
sion perform equally well with accuracy close to 0.95, while
SVM lags slightly behind at about 0.90. This implies that
KNN and Logistic Regression models are more consistent
overall.(shown in fig 6)
B. Precision Comparison Graph aiming for higher productivity, cost-effectiveness, and sustain-
This graph(figure 7) highlights that the SVM model has perfect ability in the agricultural sector. Future enhancements may
precision (1.0), while KNN and Logistic Regression both have include cloud integration, mobile app control, and advanced
slightly lower but still high precision values close to 0.95. This analytics for even smarter farming solutions.
suggests that all models are good at avoiding false positives. R EFERENCES
[1] G. Nisha and J. Megala, “Wireless sensor network based automated
irrigation and crop field monitoring system,” in 2014 Sixth international
conference on advanced computing (IcoAC). IEEE, 2014, pp. 189–194.
[2] A. Padyal, S. Shitole, S. Tilekar, and P. Raut, “Automated water irriga-
tion system using arduino uno and raspberry pi with android interface,”
International Research Journal of Engineering and Technology (IRJET),
vol. 5, no. 1, pp. 768–770, 2018.
[3] P. DrashtiDivani and K. Sunil, “Automated plant watering system,” in
2016 International Conference on Computation, 2016.
[4] L. Zhang, I. K. Dabipi, and W. L. Brown Jr, “Internet of things
applications for agriculture,” Internet of things A to Z: technologies and
applications, pp. 507–528, 2018.
[5] E. Sisinni, A. Saifullah, S. Han, U. Jennehag, and M. Gidlund, “Indus-
trial internet of things: Challenges, opportunities, and directions,” IEEE
transactions on industrial informatics, vol. 14, no. 11, pp. 4724–4734,
Fig. 7. Precision comparison graph 2018.
[6] J. Lin, W. Yu, N. Zhang, X. Yang, H. Zhang, and W. Zhao, “A survey
on internet of things: Architecture, enabling technologies, security and
C. Error Ratio Comparison Graph privacy, and applications,” IEEE internet of things journal, vol. 4, no. 5,
pp. 1125–1142, 2017.
The error ratio graph(figure 8) shows that the KNN model [7] X. Shi, X. An, Q. Zhao, H. Liu, L. Xia, X. Sun, and Y. Guo, “State-
has the lowest error rate at around 2%, followed by Logistic of-the-art internet of things in protected agriculture,” Sensors, vol. 19,
no. 8, p. 1833, 2019.
Regression at 4%. The SVM model performs the worst in this [8] S. Nandurkar, V. Thool, and R. C. Thool, “Design and development
metric with an error ratio of 8%, indicating more frequent of precision agriculture system using wireless sensor network,” in
prediction errors. 2014 First international conference on automation, control, energy and
systems (ACES). IEEE, 2014, pp. 1–6.
[9] J. Gutiérrez, J. F. Villa-Medina, A. Nieto-Garibay, and M. Á. Porta-
Gándara, “Automated irrigation system using a wireless sensor network
and gprs module,” IEEE transactions on instrumentation and measure-
ment, vol. 63, no. 1, pp. 166–176, 2013.
[10] D. V. V. Devi and G. M. Kumari, “Real-time automation and monitoring
system for modernized agriculture,” International Journal of Review and
Research in Applied Sciences and Engineering (IJRRASE) Vol3, vol. 1,
pp. 7–12, 2013.
[11] Y. Kim, R. G. Evans, and W. M. Iversen, “Remote sensing and control of
an irrigation system using a distributed wireless sensor network,” IEEE
transactions on instrumentation and measurement, vol. 57, no. 7, pp.
1379–1387, 2008.
[12] Q. Wang, A. Terzis, and A. Szalay, “A novel soil measuring wireless
sensor network,” in 2010 IEEE Instrumentation & Measurement Tech-
nology Conference Proceedings. IEEE, 2010, pp. 412–415.

Fig. 8. Error Ratio Comparison Graph

VII. CONCLUSION
In conclusion, the Smart Agriculture System developed in
this project demonstrates the potential of integrating IoT
technologies into modern farming practices. By using sensors
to monitor soil moisture, temperature, humidity, and other
environmental parameters, the system enables real-time data
collection and automated control of irrigation processes. This
not only helps conserve vital resources like water but also
ensures timely actions to improve crop health and yield.
The inclusion of components such as microcontrollers, relays,
and wireless communication modules allows for efficient and
scalable implementation. The system provides farmers with
valuable insights through sensor feedback and display inter-
faces, contributing to data-driven decision-making. Overall,
this project promotes the shift toward precision agriculture,