Intelligent Plant Growth Monitoring

and Management System

PROJECT REPORT

Submitted by
*** VARGHESE (Reg.No.VJC18EC014)
*** KURIAN (Reg.No.VJC18EC026)
*** JOHNY (Reg.No.VJC18EC042)
in partial fulfillment for the award of

degree of

BACHELOR OF TECHNOLOGY
in

ELECTRONICS AND COMMUNICATION ENGINEERING

(Affiliated to APJ Abdul Kalam Technlogical University, Trivandrum)

DEPARTMENT OF ELECTRONICS AND COMMUNICATION ENGINEERING

VISWAJYOTHI COLLEGE OF ENGINEERING AND TECHNOLOGY
VAZHAKULAM
2018 - 2022 BATCH

MAY 2022
 VISWAJYOTHI COLLEGE OF ENGINEERING AND TECHNOLOGY
VAZHAKULAM
Department of Electronics and Communication Engineering

Vision
Moulding Electronics Engineers with Professional Competence and Global Outlook

Mission
To create a vibrant academic ambience conductive for progressive learning.
Build up excellent infrastructure and lab facilities to train the students in the current &
emerging technology.
Maintain well qualified faculty who are willing to upgrade their knowledge continuously.
Groom students towards successful careers by facilitating industry-institute relationships
and value addition through regular skill-development programmes.

Programme Educational Objectives

Our Graduates shall be,
Suitably employed in allied industries/services with professional competency and
knowledge of modern tools.
Capable of developing economically viable, technically, feasible eco-friendly electronic
systems.
Capable to pursue higher studies/research in the field of engineering and management.

Programme Outcomes
Engineering knowledge: Apply the knowledge of mathematics, science, engineering
fundamentals, and an engineering specialization to the solutions of complex engineering
problems.

Program analysis: Identify, formulate, review research literature, and analyze complex
engineering problems reaching substantiated conclusions using first principles of
mathematics, natural sciences, and engineering sciences.

Design / development of solutions: Design solutions for complex engineering problems

and design system components or processes that meet the specified needs with
appropriate consideration for the public health and safety, and the cultural, societal, and
environmental considerations.
Conduct investigations of complex problems: Use research-based knowledge and
research methods including design of experiments, analysis and interpretation of data, and
synthesis of the information to provide valid conclusions.

Modern tool usage: Create, select, and apply appropriate techniques, resources, and
modern engineering and IT tools including prediction and modelling to complex
engineering activities with an understanding of the limitations.

The engineer and society: Apply reasoning informed by the contextual knowledge to
assess societal, health, safety, legal and cultural issues and the consequent responsibilities
relevant to the professional engineering practice.

Environment and sustainability: Understand the impact of the professional engineering

solutions in societal and environmental contexts, and demonstrate the knowledge of, and
need for sustainable development.

Ethics: Apply ethical principles and commit to professional ethics and responsibilities
and norms of the engineering practice.

Individual and team work: Function effectively as an individual, and as a member or

leader in diverse teams, and in multidisciplinary settings.

Communication: Communication effectively on complex engineering activities with the

engineering community and with society at large, such as being able to comprehend and
write effective reports and design documentation, make effective presentation, and give
and receive clear instructions.

Project management and finance: Demonstrate knowledge and understanding of the

engineering and management principles and apply this to one’s own work as a member
and leader in a team, to manage projects and multidisciplinary environments.

Life-long learning: Recognize the need for and have the preparations and ability to
engage in independent and life-long learning in broadcast context of technological
change.
 Program Specific Outcomes
Our studemts ahall be able
to,

Analyze and modify electronic products which will find applications in the field of
communication and automation.

Apply the concepts of signal processing and develop algorithms to solve real-world
electronics and communication engineering problems.

Design and manage cost effective low power electronic systems to address global
challenges with a strong social commitment and ethical values.
 VISWAJYOTHI COLLEGE OF ENGINEERING AND TECHNOLOGY,
VAZHAKULAM

Department of Electronics and Communications Engineering

BONAFIDE CERTIFICATE
This is to certi fy that the project report enti tled " Intelligent Plant Growth
Monitoring and Management System" is a bonafi de record of the work done by
*** VARGHESE(Reg.No.VJC18EC014), **** KURIAN(Reg.No.VJC18EC026) and ***
JOHNY(Reg.No.VJC18EC042) in partial fulfillment of the requirements for the award of the
degree of Bachelor of Technology in Electronics and Communications Engineering of APJ
Abdul Kalam Technological University, Trivandrum.

Date :
Place : Vazhakulam

Dr. Cyriac M Odackal

Project Guide External Supervisor
Associate Professor
Dept. of ECE, VJCET

Mrs. Anitta Thomas

Mrs. Smitha Cyriac
Project Coordinator
HOD
Assistant Professor
Dept. of ECE, VJCET
Dept. of ECE, VJCET
 ABSTRACT
Process-based models are capable of simulating plant biophysical processes
considering the effects of soil, weather, management, and genetics. However, there is a
limitation to these models mainly due to availability, uncertainty, and spatial variation
of model parameters. To solve these problems, Intelligent plant growth monitoring and
management system is developed. This paper automates plant monitoring and
management system in the Raspberry Pi platform. The main purpose of this system is to
provide comfort to the people by reducing manual work and to improve the overall
performance of any system without manual interaction. The important parameters for
the quality and productivity of plant growth are soil and air temperature, humidity,
sunlight, soil moisture, and pH. Information to the user about the plant's health and
growth may be provided to the user by continuously monitoring and recording these
various parameters. It provides a better understanding of how each parameter affects
the growth of plants. All the sensors (Temperature, moisture, humidity, pH...) used in
this project interface with a Raspberry Pi controller. And the information about the
growth and health of the plant can be directly monitored and controlled by the owner
through his/her smartphone.
 ACKNOWLEDGEMENT

First and foremost, we thank God Almighty for His divine grace and
blessings in making all this possible. May he continue to lead us in the years to come. It
is our privilege to render our heartfelt thanks and gratitude to our most beloved
manager, Rev Msgr. Dr. Pius Malekandathil and our Principal, Dr. K K Rajan for
providing us the opportunity to do this main project during the fourth year (August
2021- June 2022) of our B-Tech degree course. We are deeply thankful to our Head of
the Department, Mrs. Smitha Cyriac for her support and encouragement. We would
like to express our sincere thanks to the project coordinator Mrs. Anitta Thomas, Asst.
Professor, Department of Electronics and Communication Engineering for her guidance
and support.We also express our sincere gratitude to our Project guide Dr.Cyriac M
Odackal, Assoc. Professor, Department of Electronics and Communication Engineering
for her motivation, assistance and help for the project. We also thank all the staff
members of the Electronics and Communication Engineering for providing their
assistance and support. Last, but not the least, we thank all our friends and family for
their valuable feedback from time to time as their help and encouragement.
***A VARGHESE
*** KURIAN
** JOHNY
 CONTENTS
Chapter No. Title Page No.

LIST OF ABBREVIATIONS i

LIST OF FIGURES ii

LIST OF TABLES iii

1 INTRODUCTION 1

1.1 GENERAL BACKGROUND 1

1.2 OBJECTIVE 1

2 LITERATURE REVIEW 2

3 PROJECT OVERVIEW 4

3.1 BLOCK DIAGRAM 4

3.2 WORKING 5

3.3 COMPONENTS REQUIRED 6

3.3.1 Raspberry Pi 4 model B 4GB RAM 6

3.3.2 Logitech C270 HD Webcam 9
3.3.3 Capacitive Soil Moisture Sensor 10
3.3.4 DHT11 Digital Humanidity and 11
Temperature Sensor

Light Sensor(LDR) 12
PH Sensor Module 14
Four Channel Bidirectional Logic 15
level Converter
Aluminum Heat Sink Case With 16
Double fans
DC 3-6 Mini Micro submersible 17
Water Pump

100K Ohm1W Carbon Film 18

Resistor
18
Momentary Switch
SanDisk Ultra 16 GB MicroSDHC 19
Class 10 48 MB/s Memory Card
 3.3.13 Light emitting diode 20

3.3.14 DC Power supply SMPS(5V 5A) 21

3.4 CIRCUIT DIAGRAM 22

3.5 SOFTWARE USED 23

3.6 METHODOLOGY 23

4 RESULTS 24

4.1AI-ML Based Recognition Results 24

4.2 Tomato Count Results 25

4.3 Temperature Results 25

4.4 Humidity Results 26

4.5 Moisture Results 26

Light intensity Results 27

pH Results 27

5 CONCLUSSION 30

6 REFERENCES 31
 LIST OF ABBREVIATIONS

AI-ML USB :

GPIO
:

GPU
:

GND
:

HD
:

I2C
:

IoT
:

LED
:

LAN
:

pH :

PoE :

RAM
:

SPI
:

TTL
:

UART
:

i
 e & Machine Learning General-Purpose
A
Input-Output
r
Graphic Processing Unit
t
Ground
i
High Definition
f
Inter-Integrated Circuit
i
Internet of Things
c
Light-Emitting Diode
i
Local Area Network
a
Potential of Hydrogen
l
Power of Ethernet

Random Access Memory

I
Serial Peripheral Interface
n
Time to Live
t
Universal Asynchronous Receiver Transmitter
e
Universal Serial Bus
l

i
 LIST OF FIGURES
Fig. No. Title Page No.
ram of Intelligent Plant 4
Monitoring & Management System
Raspberry Pi 4 Model B 4GB RAM 6

Logitech C270 HD Webcam 9

Capacitive Soil Moisture Sensor 10

DHT11 Digital Humidity & Temperature Sensor 11

Light Dependent Resistor (LDR) 12

pH Sensor Module 14

Four Channel Bidirectional Logic Level Converter 15

Aluminum Heat Sink Case with Double Fans 16

DC 3-6 V Mini Micro Submersible Water Pump 17

100K Ohm 1W Carbon Film Resistor 18

Momentary Switch 18

SanDisk Ultra 16 GB MicroSDHC Class 10 48 MB/s 19

Memory Card
Light Emitting Diode 20

DC Power supply SMPS(5V 5A) 21

Schematic Diagram 22

Power Supply Network 22

Google Colab Logo 23

tion of Tomatoes using AI-ML 24

ii
Fig. No. Title Page No.

Results obtained after the sensors made their readings 24

Tomato Count Results 25

Final Product 28

Monitoring Section 29

iii
 LIST OF TABLES
Table. No. Title Page No.

4.1 Temperature Readings 25

4.2 Humidity Readings 26

4.3 Soil Moisture Readings 26

4.4 Light Intensity Readings 27

4.5 pH Readings 27

iv
 Intelligent Plant Growth Monitoring and Management
System

CHAPTER 1

INTRODUCTION
The past decade has been significant advancement in the field of agriculture
industry. Various smart appliances are set to realize the concept of a new smart farming
with the help of latest technologies.

GENERAL BACKGROUND
Intelligent plant growth monitoring and management system will help to ease the
most tedious job of gardening for plant lovers. The system brings more convenience and
comfort to people’s lives by taking care of their plant’s growth. The proposed system is
designed and implemented using a low-cost credit card-sized Raspberry Pi, which is
monitored through a remote monitoring sensor. This helps to solve plants' thrive by
tracking the environmental conditions and monitoring them. The system gives a timely
alert to the user’s Android phone by gathering and analyzing the data about the changing
soil moisture condition, weather, and temperature with the help of various sensors. All
the parameters like humidity, temperature, soil, moisture, light intensity, and pH, are
tracked by the system, and this information is uploaded to the database. This system also
helps to monitor the plant’s condition from any part of the world like the user’s
workplace. This intelligent plant growth monitoring system will continuously monitor the
condition of the plant and alert the user to make the changes that require immediate
action for the plants.

OBJECTIVE
Intelligent management of agriculture systems, aiming at optimizing profitability,
productivity, and sustainability, comprises a set of technologies including sensors,
information systems, and informed management, etc. The main purpose of this system is
to provide comfort to the people by reducing the manual work and to improve overall
performance of the system without manual interaction. Intelligent plant growth
monitoring system will help to ease the tedious job of gardening and it will helps to solve
plants thrive by tracking the environmental conditions and monitoring them. The system
also gives a timely alert to the user by gathering and analyzing the data.

Dept. of ECE, VJCET 1

 Intelligent Plant Growth Monitoring and Management
System

CHAPTER 2

LITERATURE REVIEW
For plant growth monitoring tasks, a process-based model is widely used to
stimulate plants' biophysical process using agro-meteorological data, soil properties, and
plant management. The limitation of these models is mainly due to the availability,
uncertainty, and spatial variation of model parameters. To solve these problem empirical
models built using a machine learning algorithm is developed to monitor the growth and
health of the plant. The performance of the built model is evaluated with a comparison of
the statistical model and machine learning model.

Visual Classification of Lettuce Growth Stage based on Morphological Attributes

using Unsupervised Machine Learning models [1]
This study specifically solves the predicament of identifying the developmental
growth of plants from seed leaves to amend the techniques of plant science and
cultivation management. With a view to this, the paper shows coupled color-based
superpixels and multifold watershed transformation in segmenting the lettuce image from
the background. To fathom it out, a comparative analysis of three unsupervised machine
learning algorithms. These were done by modeling each algorithm from the features
extracted from morphological computations of the lettuce images raised in a smart
aquaponics setup. Each of the models was optimized to increase cross and holdout
validations.

Machine learning approaches for growth monitoring using multi-temporal and multi-
variety remotely sensed data [2]
The main goal of this paper is to build a machine learning model based on the
data derived from the sensor, with a combination of agro-meteorological data. This
methodology will also consider the temporal variation of the input data set acquired in
multiple development phases along the crop season. The dataset used for modeling was
built from two kinds of sources. The first source is sugar cane sucrose data from ripening
sugar cane fields, obtained for a different plot across three harvest seasons, from 2014-to
2016. The second source is remotely sensed data. The performance of the built model and
previous model will be evaluated according to the error between estimated and observed
values.

Dept. of ECE, VJCET 2

 Intelligent Plant Growth Monitoring and Management
System
Classification of Chili Plant Growth using Deep Learning [3]
The paper discussed the potential deep learning algorithm in classifying chili
plant growth images from a small dataset. The experiment is performed on 256 chili plant
images under various conditions, where the images were captured using a camera. The
data is divided into two models training and testing. The results showed that both models
were able to detect the correct age of the chili plant with 96% accuracy.

A Smart Agriculture System [4]

The system has an easy-to-upgrade bank of inference rules to control the
agriculture environment. This system mainly looks at inputs, such as temperature,
humidity, and pH. The system is ubiquitous as it enables distant access. This system is an
addition to current-state-of-art Internet-of-things.

An automated detection and classification of citrus plant diseases using image

processing techniques: A review [5]
A thorough literature review of image preprocessing, segmentation, and feature
extraction using machine vision affirms to lessen the threats and requisition of the
detection and classification systems. It also authenticates the efficiency and high
accuracy compared to other methods. But still, the automated vision-based detection and
classification methods are in their infancy stage. In current days, farm monitoring is still
contingent on the instinctive human decisions showing low accuracy due to the visual
limitations of the human eye and lacking knowledge and specialization. Unfolding the
issue, Machine vision can be a considerate field that involves making a machine ‘‘see”.

Dept. of ECE, VJCET 3

 Intelligent Plant Growth Monitoring and Management
System

CHAPTER 3

PROJECT OVERVIEW
This section deals with the block diagram and working of the project, followed by
the various hardware components used in this project.

BLOCK DIAGRAM
This sub-chapter discusses the block diagram of the intelligent plant growth monitoring
and management system.

Fig 3.1 Block Diagram of Intelligent Plant Growth Monitoring and Management System

Dept. of ECE, VJCET 4

 Intelligent Plant Growth Monitoring and Management
System
WORKING
To monitor plant growth, the process-based model is widely used to stimulate plants'
biophysical processes using agrometeorological data, soil properties, and plant management.
The limitation of these models is mainly due to the availability, uncertainty, and spatial
variation of model parameters. To solve these problem empirical models built using a machine
learning algorithm is developed to monitor the growth and health of the plant. The
performance of the built model is evaluated with a comparison of the statistical model and
machine learning model.

By analyzing the above studies, here we are planning to design an Intelligent plant
monitoring and management system with the help of a Raspberry Pi controller. In this system,
various parameters like temperature, humidity, light, and pH. are controlled with the help of a
sensor. The growth and health of the plant can be directly controlled and monitored by the
owner from any part of the world via the internet.

Our block diagram consists of a monitoring area. The plant to be monitored is placed in
this area. And there is a plant health monitoring system. It consists of sensors and actuators. It
will sense various parameters like temperature, humidity, pH, and light. . A camera is provided
and it can move 360 degrees and it will capture the images of the monitoring plant. The data
from the monitoring area and health monitoring system will be given to the machine learning
model. Here Raspberry Pi 4 is used. A machine learning model is trained data. Here the data
given to the machine learning model is saved into two folders test and train. Then this tested
data is compared against the trained data. If the error rate is near 0.1, then the model is
assumed to be trained otherwise an anomaly is detected. The data is then given to another
device via the internet. So the user can monitor the plant's condition from any part of the
world.

Dept. of ECE, VJCET 5

 Intelligent Plant Growth Monitoring and Management
System
COMPONENTS REQUIRED
This sub-chapter discusses the different hardware components used in the project.

Raspberry Pi 4 model B 4GB RAM

Raspberry Pi 4 Model B is the latest product in the popular Raspberry Pi range of
computers. It offers ground-breaking increases in processor speed, multimedia
performance, memory, and connectivity compared to the prior-generation Raspberry Pi 3
Model B+, while retaining backwards compatibility and similar power consumption. For
the end user, Raspberry Pi 4 Model B provides desktop performance comparable to entry-
level x86 PC system.

Fig 3.2 Raspberry Pi 4 model B 4GB RAM

This product’s key features include a high-performance 64-bit quad-core processor,

dualdisplay support at resolutions up to 4K via a pair of micro-HDMI ports, hardware
video decode at up to 4Kp60, up to 8GB of RAM, dual-band 2.4/5.0 GHz wireless LAN,
Bluetooth 5.0, Gigabit Ethernet, USB 3.0, and PoE capability (via a separate PoE HAT add-
on). The dual-band wireless LAN and Bluetooth have modular compliance certification,
allowing the board to be designed into end products with significantly reduced compliance
testing, improving both cost and time to market.

Dept. of ECE, VJCET 6

 Intelligent Plant Growth Monitoring and Management
System
Raspberry Pi Pin Description
The Raspberry Pi 4 can be used in the external embedded system to communicate.
It has a total of 40 pins of which 28 are GPIO pins and the rest of them are power pins.
GPIO pins don’t only perform the simple I/O functions. They could give the UART, SPI,
and I2C communications. These communications are specific to every pin and all their
function are discussed below:
Power Supply Pins:
Power In: In Raspberry pi, there is two power in method, one is from the USB-C
power port and the second one is from any 5V pin. The 5-volt pin is directly connected to
the USB-C adapter port. The input on the 5V pin should be stable and according to its
specifications. In the case of higher voltage, the device could get burned. 5V input pins
will bypass any fuse and regulator in case of power input, so the power supply from 5V
should according to its specification to avoid any kind of harm. The power input pin of
the Raspberry Pi 4 is given below:
Pin 2-6 —> +5V
Pin 6 —–> GND
Power Out: There are two types of power output pin in the Raspberry pi 4 3V3
and 5V. 5V is directly connected to the USB port but 3V3 is connected to through the
regulator which gives the stable 3 volts output. All power out pins are given below:
3V3 – Pin 1, Pin 17
5V – Pin 2, Pin 6
Ground: Raspberry Pi 4 has multiple ground pin which is connected internally and
any ground pin can be used by the power supply or external device to make the common
ground. The list of the ground pins is given below:
Pin 6
Pin 9
Pin 14
Pin 20
Pin 25
Pin 30
Pin 34
Pin 39

Dept. of ECE, VJCET 7

 Intelligent Plant Growth Monitoring and Management
System
Digital Input/Output Pins:
Almost every device needs input and output pins to communicate. In this device
there are 28 GPIO pins available these pins can be used for any digital input and output
operating. The GPIO pins in the controller have some default values. GPIO pins from 0-9
will be at a HIGH state and from 10 to above the pins will be at a LOW state. All those
pins in the Raspberry Pi 4 are given below:
GPIO0 – Pin27
GPIO1 – Pin28
GPIO2 – Pin3
GPIO3 – Pin5
GPIO4 – Pin7
GPIO5 – Pin29
GPIO6 – Pin31
GPIO7 – Pin26
GPIO8 – Pin24
GPIO9 – Pin21
GPIO10 – Pin19
GPIO11 – Pin23
GPIO12 – Pin32
GPIO13 – Pin33
GPIO14 – Pin8
GPIO15 – Pin10
GPIO16 – Pin36
GPIO17 – Pin11
GPIO18 – Pin12
GPIO19 – Pin35
GPIO20 – Pin38
GPIO21 – Pin40
GPIO22 – Pin15
GPIO23 – Pin16
GPIO24 – Pin18
GPIO25 – Pin22
GPIO26 – Pin37
GPIO27 – Pin13

All GPIO pins in Raspberry Pi 4 are not only for input-output function. Each GPIO pin
can be used as other functions, which will be specified through programming.

Dept. of ECE, VJCET 8

 Intelligent Plant Growth Monitoring and Management
System
Logitech C270 HD Webcam

Fig 3.3 Logitech C270 HD Webcam

About:
HD 720p video calling and HD video recording, 2.4 Giga Hertz Intel Core2 Duo, 2
GB RAM,200 MB hard drive space
Video capture: Upto 1280 x 720 pixels, Logitech fluid crystal. Focus type: Fixed
focus
Crisp 3 MP photos technology, Hi speed USB 2.0
Compatible with: Windows 10 or later, Windows 8, Windows 7, Works in USB video
device class (UVC) mode with supported video calling clients: MacOS 10.10 or later,
Chrome OS, Android v 5.0 or above
Built in microphone filters out background noise. System Requirements: Windows 7
Windows 8 or Windows 10 or later mac OS 10.10 or later chrome OS Android v 5.0
or above USB port Internet access visit your preferred video calling solution
provider's website for exact information on system and performance requirements.
Visit your preferred video calling solution provider's website for exact information
on system and performance requirements. Works with Skype google hangouts face
time for Mac.FoV: 60°
2 years limited

Dept. of ECE, VJCET 9

 Intelligent Plant Growth Monitoring and Management
System

3.3.3. Capacitive Soil Moisture Sensor

Fig 3.4 Capacitive Soil Moisture Sensor

Soil moisture can be measured using a variety of different techniques: gravimetric,

nuclear, electromagnetic, tensiometric, hygrometric, among others [read about the
specifics types of soil moisture sensors here]. The technique explored here uses a
gravimetric technique to calibrate a capacitive-type electromagnetic soil moisture sensor.
Capacitive soil moisture sensors exploit the dielectric contrast between water and soil,
where dry soils have a relative permitti vity between 2-6 and water has a value of roughly
80 [find more specific values here]. Accurate measurement of soil water content is
essential for applications in agronomy and botany - where the under- and over-watering
of soil can result in ineffective or wasted resources.
With water occupying up to 60% of certain soils by volume, depending on the
specific porosity of the soil, calibration must be carried out in every environment to
ensure accurate prediction of water content [more on this here Luckily, the accuracy of
measurement devices has been increasing while the cost of the sensors have been
decreasing. In this experiment, an Arduino board will be used to read the analog signal
from the capacitive sensor, which will output voltage values which can be calibrated to
volumetric soil moisture content via gravimetric methods (using volume and weight of
dry and wet soil).

Dept. of ECE, VJCET 10

 Intelligent Plant Growth Monitoring and Management
System
Calibrating Capacitive Soil Moisture Sensor
Procedures:
1. Measure the mass of the soil sample container
2. Fill container to 200ml (or any volume) with dry soil
3. Measure mass of the dry soil in the container
4. Wet the soil with 10ml of water (this is 5%, but any higher % is okay)
5. Mix the wet soil around to ensure the water is evenly distributed, then refill the
container to 200ml
6. Measure the mass of the wet soil
7. Repeat steps 4., 5., and 6. until the soil is saturated and starts to seep water
8. Once the procedure of watering has reached saturation, lay the 200ml of soil out on
an array of wax paper to allow it to dry out
9. When the soil is dry, measure the mass of this dry soil - this will be the mass of the
dry soil used for soil density

The above procedure can take up to 7 days, when factoring the drying procedure. The
experimental process can take roughly 10-minutes per measurement (packing, watering,
settling), and with about 6-10 measurements per experiment - the actual work can be 1-2
hours. Thus, after the initial few days of drying the soil, plus 2 hours of experiments,
along with a few days of drying the soil out - the full-scale experiment takes about 7
days. The way to ensure the fastest experimentation is to lay the soil out very thinly on
the wax paper. This will give about 7 days per soil calibration.

DHT11 Digital Humidity and Temperature Sensor

Fig 3.5 DHT11 Digital Humidity and Temperature Sensor

Dept. of ECE, VJCET 11

 Intelligent Plant Growth Monitoring and Management
System
The DHT11 is a basic, ultra low-cost digital temperature and humidity sensor.
It uses a capacitive humidity sensor and a thermistor to measure the surrounding air, and
spits out a digital signal on the data pin (no analog input pins needed). Its fairly simple to
use, but requires careful timing to grab data. You can get new data from it once every 2
seconds, so when using the library from Adafruit, sensor readings can be up to 2 seconds
old.
Comes with a 4.7K or 10K resistor, which you will want to use as a pullup from the data
pin to VCC.

Specifications:
3 to 5V power and I/O
2.5mA max current use during conversion (while requesting data)
Good for 20-80% humidity readings with 5% accuracy
Good for 0-50 °C temperature readings +-2 °C accuracy
No more than 1 Hz sampling rate (once every second)
Body size 15.5mm x 12mm x 5.5mm
4 pins with 0.1" spacing
RoHS compliant

Light Sensor(LDR)

Fig 3.6 Light Sensor(LDR)

Dept. of ECE, VJCET 12

 Intelligent Plant Growth Monitoring and Management
System

Light Dependent Resistors (LDR) are also called photoresistors. They are made of
high resistance semiconductor material. When light hits the device, the photons give
electrons energy. This makes them jump into the conductive band and thereby conduct
electricity.
Light dependent resistors, LDRs or photoresistors are often used in circuits where it is
necessary to detect the presence or the level of light. They can be described by a variety
of names from light dependent resistor, LDR, photoresistor, or even photo cell, photocell
or photoconductor.
However, when light shines onto the LDR its resistance falls and current flows into the
base of the first transistor and then the second transistor. The LED lights. The preset
resistor can be turned up or down to increase or decrease resistance, in this way it can
make the circuit more or less sensitive.

Features
Epoxy Encapsulated
Small Size Reliable Performance
Quick Response
High Sensitivity
Good Characteristic of Spectrum
Can be used to sense Light
Easy to use on Breadboard or Perf Board
Easy to use with Microcontrollers or even with normal Digital/Analog IC
Small, cheap and easily available
Available in PG5 ,PG5-MP, PG12, PG12-MP, PG20 and PG20-MP series

A photoresistor or LDR (Light Dependent Resistor), as the name suggests will

change it resistance based on the light around it. That is when the resistor is placed in a
dark room it will have a resistance of few Mega ohms and as we gradually impose light
over the sensor its resistance will start to decrease from Mega Ohms to few Ohms.
This property helps the LDR to be used as a Light Sensor. It can detect the amount of
light falling on it and thus can predict days and nights. So if you are looking for a sensor
to sense light or to distinguish between days and nights then this sensor is the cheap and
modest solution for you.

Dept. of ECE, VJCET 13

 Intelligent Plant Growth Monitoring and Management
System
PH Sensor Module

Fig 3.7 PH Sensor Module

This PH Sensor Module is Compatible for Arduino. The pH stands for the power of
hydrogen, which is a measurement of the hydrogen ion concentration in the body. This is
used in Water quality testing and Aquaculture. The total pH scale ranges from 1 to 14,
with 7 considered to be neutral. A pH less than 7 is said to be acidic and solutions with a
pH greater than 7 are basic or alkaline.The PH electrode has a single cylinder that allows
direct connection to the input terminal of a pH meter, controller, or any pH device which
has a BNC input terminal. The pH electrode probe is accurate and reliable that can give
almost instantaneous readings.
Note: PH Probe and Temperature sensor are not included with this kit.

Specifications:
Heating voltage: 5 ± 0.2V (AC - DC)
Working current: 5-10 mA
Detection concentration range: PH 0-14
Detection temperature range: 0-80 centigrade
Response time: ≤5s
Stability time: ≤60s
Component power consumption:≤0.5W
Working temperature: -10 to 50 degree (nominal temperature 20 degree)

Dept. of ECE, VJCET 14

 Intelligent Plant Growth Monitoring and Management
System

Four Channel Bidirectional Logic Level Converter

Fig 3.8 Four Channel Bidirectional Logic Level Converter

Now a days, there are many Development Boards and Modules/Sensors available;
most of them supporting either 3.3V or 5V logic. It becomes quite a task when it comes
to connecting a 3.3V device to a 5V system. This module offers a simple, safe and
convenient way to step down 5V signal to 3.3V logic and step up 3.3V to 5V at the same
time. It can also support 1.8V and 2.8V Logics. The module has the option of converting
4 pins on the high side to 4 pins on the low side with two inputs and two outputs
provided for each side. The board is required to be powered by the desired level of
voltage sources (high and low voltages) that the two sides of systems are working at for
example 5V to HV pin and 3.3V to LV and ground to the GND pin on both side while
working with 3.3V device and 5V system.

Specifications and Features:

1. Mutual transform between 5V TTL and 3.3V TTL
2. Four channels of logic and high voltage low voltage logic can two-way transform
3. Portable and lightness, with 2 rows 6 pin contact pins
4. Level Converter- 4 ChannelCompatible with the bread plate, can be used directly put
on the breadboard
5. 4 Channel Module (great for I2C or SPI) and will work with all microcontrollers,
Arduino, Raspberry Pi, Intel Edison, NXP Mbed

Dept. of ECE, VJCET 15

 Intelligent Plant Growth Monitoring and Management
System
Aluminum Heat Sink Case with Double Fans

Fig 3.9 Aluminum Heat Sink Case with Double Fans

This is a must-have accessory to experience the high performance of the Raspberry Pi

4 Models. The Aluminium Alloy Case with Double Dual Cooling Fan Heat Sink Metal
Case is designed especially for Raspberry Pi 4 Model B.
This is a premium quality heat sink for industrial and continuous use applications for the
Raspberry Pi 4. This heat sink enables the Raspberry Pi to function with very high
reliability and at higher effi ciencies for applications which require the maximum
computing power of the Pi 4.

Specifications
Compatibility-Raspberry Pi 4
Material-Aluminum Alloy
Color-Black
Length (mm)-88
Width (mm)-56
Height (mm)-24
Weight (gm)-110
Shipment Weight-0.12 kg
Shipment Dimensions-7 × 4 × 2 cm

Dept. of ECE, VJCET 16

 Intelligent Plant Growth Monitoring and Management
System
DC 3-6 V Mini Micro Submersible Water Pump

Fig 3.10 DC 3-6 V Mini Micro Submersible Water Pump

It operates on 3-6 V and gives an output of above 70 L/H then this could be the
best choice for your project.This DC 3-6 V Mini Micro Submersible Water Pump is a
low- cost, small-size Submersible Pump Motor that can be operated from a 2.5 ~ 6V power
supply. It can take up to 120 liters per hour with a very low current consumption of
220mA. Just connect the tube pipe to the motor outlet, submerge it in water, and power
it.

Specifications
Operating Voltage (VDC)-2.5 to 6
Operating Current (mA)-130 to 220
Flow Rate (L/H)-80 to 120
Maximum Lift (mm)-40 to 110
Continuous Working Life (hours)-500
Driving Mode-DC, Magnetic Driving
Material-Plastic
Inner Diameter (ID) (mm)-5
Outer Diameter (OD)(mm)-7.5
Shipment Weight-0.06 kg
Shipment Dimensions-5 × 4 × 3 cm

Dept. of ECE, VJCET 17

 Intelligent Plant Growth Monitoring and Management
System
100K Ohm 1W Carbon Film Resistor

Fig 3.11 100K Ohm 1W Carbon Film Resistor

100K Ohm 1W High Quality Carbon Film Resistor (CFR) with ±5% Tolerance and Tin
Plated Copper Leads.
100K Ohm Resistor Color Code: Brown, Black, Yellow, Golden.
Resistance: 100K Ohm, Power Rating: 1 Watt, Approximate Maximum Current: 3.16mA

Momentary Switch

Fig 3.12 Momentary Switch

Dept. of ECE, VJCET 18

 Intelligent Plant Growth Monitoring and Management
System
This momentary switch is a unit capable of turning any electronic device to either
an on or off state when an end-user presses the switch. This type of switch can actually
represent one of two types with the alternative being the traditional on or off switch.
They can be found in all manner of electronic devices and usually take the form of a
button to help initiate the state change in a device. The two types of momentary switch
commonly used throughout industry are push-to-break and push-to-make types.

SanDisk Ultra 16 GB MicroSDHC Class 10 48 MB/s Memory Card

Fig 3.13.SanDisk Ultra 16 GB MicroSDHC Class 10 48 MB/s Memory Card

Features:
Add up to 16 GB (1) of storage space to Android or other smartphone or tablet
Class 10 for recording Full HD (2) video
Read speeds up to 48 MB/s (5) for fast file transfer
SanDisk Memory Zone app (6) supports automatic file transfer to free up space on
your device
Waterproof, temperature proof, X-ray proof, and magnet proof (3)
Includes SD adapter
Lifetime warranty (7)

Dept. of ECE, VJCET 19

 Intelligent Plant Growth Monitoring and Management System

Light Emitting Diode

Fig 3.14 Light Emittting diode

A light-emitting diode (LED) is a semiconductor light source that emits light when
current flows through it. Electrons in the semiconductor recombine with electron holes,
releasing energy in the form of photons. The color of the light (corresponding to the
energy of the photons) is determined by the energy required for electrons to cross the
band gap of the semiconductor.[5] White light is obtained by using multiple
semiconductors or a layer of light-emitting phosphor on the semiconductor device

Light Generated by LED is Directional. A. LED is all forward directional lighting,

not Omni as conventional light bulb.
LED can Generate Different Light Color.
Temperature will Affect LED Efficacy.
Low Energy Consumption.
Long Life.

Dept. of ECE, VJCET 20

 Intelligent Plant Growth Monitoring and Management System

DC Power supply SMPS(5V 5A)

Fig 3.15 DC Power supply SMPS(5V 5A)

Specifications:

Input Voltage: AC 100 - 264V 50 / 60Hz

Output Voltage: 5V DC, 5A
Protections: Overload / Over Voltage / Short Circuit
Auto-Recovery After Protection
Universal AC input / Full range
100% Full Load Burn-in Test
Cooling by Free Air Convection
High Quality and High Performance
LED power supply with a metal body for hidden installation for LED lighting
Design with Built-in EMI Filter, improve signal precision.
Certifications: CE & RoHs
No Minimum Load.
Compact Size Light Weight.
High Efficiency, Reliabiltiy & low energy consumption
Category - Switch Mode Power Adaptor (SMPS)
MTBF >50,000 hours
Output Type - DC
Output - 5Volts 5Amp
Shell Material: Metal Case / Aluminum Base
Color: Sliver
IN-DOOR USE ONLY!

Dept. of ECE, VJCET 21

 Intelligent Plant Growth Monitoring and Management System

CIRCUIT DIAGRAM

This sub-section shows the schematic diagram of the working model of the
intelligent plant monitoring and management system and its power supply network. It
shows how the various coponents are connected in the corresponding working model.

Fig 3.16 Schematic Diagram

Fig 3.17 Power Supply Network

Dept. of ECE, VJCET 22

 Intelligent Plant Growth Monitoring and Management System

SOFTWARE USED

Google Colaboratory
Colaboratory, or “Colab” for short, is a product from Google Research. Colab allows
anybody to write and execute arbitrary python code through the browser and is especially
well suited to machine learning, data analysis, and education. More technically, Colab is
a hosted Jupyter notebook service that requires no setup to use, while providing access
free of charge to computing resources including GPUs.

Fig 3.18 Google Colab Logo

METHODOLOGY

Create a dataset that contains the images of tomatoes. For this, we take clear and
unclear images of tomatoes from different angles with different variations and kept
them in a common folder. But this is difficult in our case, so we take an opensource
tomatoes image. Thus the primary base model is done with this open-source dataset.
These images are of different sizes so first, we resize all the images into a standard
size of 640*640. This is because coding is done using the Yolo algorithm. This
provides graphical performance and algorithm performance of the system.
Draw a bounty box for detecting objects or classes. label IMG is the library for
labeling. For this, we need to browse the path of the folder where the image is stored.
Simultaneously images are loaded one by one. By drawing the bounty box, the image
is saved by the same name as the image.
The bounty box data is saved. XML format. Once these steps are completed, the
process is stopped.

Dept. of ECE, VJCET 23

 Intelligent Plant Growth Monitoring and Management System

CHAPTER 4

RESULTS
This chapter deals with the results obtained after running 10 test images through
the algorithm, ie, 10 iterations were completed.

AI-ML BASED RECOGNITION RESULTS

This sub-chapter shows how the video camera captures images and how the
captured image is processed. It shows the results after the image is run through the
algorithm.

Fig 4.1 Identification of Tomatoes using AI-ML

Fig 4.2 Results obtained after the sensors made their readings

Dept. of ECE, VJCET 24

 Intelligent Plant Growth Monitoring and Management System

TOMATO COUNT RESULTS

This sub-chapter shows a graph, which compares the number of tomatoes detected
in each of the 10 test images.

Fig 4.3 Tomato Count Results

TEMPERATURE RESULTS

This sub-chapter shows a table comparing the different temperature readings obtained
by the temperature & humidity sensor.

Table 4.1. Temperature Readings

Dept. of ECE, VJCET 25

 Intelligent Plant Growth Monitoring and Management System

HUMIDITY RESULTS

This sub-chapter shows a table comparing the different humidity readings obtained
by the temperature & humidity sensor.

Table 4.2. Humidity Readings

MOISTURE RESULTS

This sub-chapter shows a table comparing the different soil moisture readings
obtained by the soil moisture sensor.

Table 4.3. Soil Moisture Readings

Dept. of ECE, VJCET 26

 Intelligent Plant Growth Monitoring and Management System

LIGHT INTENSITY RESULTS

This sub-chapter shows a table comparing the different light intensity readings
obtained by the LDR.

Table 4.4. Light Intensity Readings

pH RESULTS

This sub-chapter shows a table comparing the different pH value readings

obtained by the pH sensor.

Table 4.5. pH Readings

Dept. of ECE, VJCET 27

 Intelligent Plant Growth Monitoring and Management System

FINAL HARDWARE PRODUCT

This sub-chapter shows the images of the final product with its various components.

Fig 4.4 Final Product

Dept. of ECE, VJCET 28

 Intelligent Plant Growth Monitoring and Management System

Fig 4.5 Monitoring Section

Dept. of ECE, VJCET 29

 Intelligent Plant Growth Monitoring and Management
System

CHAPTER 5

CONCLUSION

Intelligent plant growth monitoring and management system will help to ease the
most tedious job of gardening for plant lovers. The system brings more convenience and
comfort to people’s lives by taking care of their plant’s growth. The proposed system is
designed and implemented using a low-cost credit card-sized Raspberry Pi, which is
monitored through a remote monitoring sensor. This helps to solve plants' thrive by
tracking the environmental conditions and monitoring them. The system gives a timely
alert to the user’s Android phone by gathering and analyzing the data about the changing
soil moisture condition, weather, and temperature with the help of various sensors. All
the parameters like humidity, temperature, soil, moisture, light intensity, and pH, are
tracked by the system, and this information is uploaded to the database. This system also
helps to monitor the plant’s condition from any part of the world like the user’s
workplace. This intelligent plant growth monitoring system will continuously monitor the
condition of the plant and alert the user to make the changes that require immediate
action for the plants.

Dept. of ECE, VJCET 30

 Intelligent Plant Growth Monitoring and Management
System

CHAPTER 6

REFERENCES

[1] Jonnel Alejandrino"Visual Classification of Lettuce GrowthStage based on

Morphological Attributes using Unsupervised Machine Learning models"2020 IEEE
REGION 10 CONFERENCE (TENCON)Osaka, Japan, November 16-19, 2020

[2] "Machine learning approaches for crop growth monitoring using multi-temporal and
multi-variety remotely sensed data"YU ZHAO; DIEGO DELLA JUSTINA
HITACHI, Ltd.; University of Campinas

[3] A. D. A. Aldabbagh, C. Hairu, M. Hanafi "Classification of Chili Plant Growth

using DeepLearning"2020 IEEE 10th International Conference on System
Engineering and Technology (ICSET), 9 November 2020, Shah Alam, Malaysia

[4] Tomen:A Plant monitoring and smart gardening system using IoT March 2018
International Journal of Pure and Applied mathematics volume 119 (No. 7)

[5] Z. Iqbal, M. A. Khan, M. Sharif, J. H. Shah, M. H. ur Rehman, and K. Javed, “An

automated detection and classification of citrus plant diseases using image
processing techniques: A review,” Comput. Electron. Agric., vol. 153, no. August,
pp. 12–32, 2018.

Dept. of ECE, VJCET 31