Smart Farms: Generating Techno Environment Farming

Chapter 1
INTRODUCTION
The primary issue of Smart Farming: Techno Environment Farming horticulture is to
manage the greenhouse environment optimally in order to comply with the economic and
environmental requirements. Pests and diseases, and extremes of heat and humidity, have
to be controlled, and irrigation is necessary to provide water. The solution to these
problems is by designing an automatic controlled system. Two sensors are used in this
project. Soil moisture sensor needed to automatically control the valve of watering system.
Temperature sensor will measure the condition of the greenhouse. This project improved
the irrigation system from manual to automatic to make it easier to monitor the condition
of the Techno Environment Farming remotely.
The Techno Environment Farming is the quickest developing part of the world. Techno
Environment Farming is a method of providing favorable environmental conditions to
plants by growing them under a farmed structure covered with a transparent material.
Internet of things can be expressed as the architecture of physical things implanted with
electronic circuits, sensors and programming along with an associative system these things
to trade information from each other. Techno Environment Farming is a best option to
enhance the performance. Hand-operated Techno Environment Farming has drawbacks
like visual inspection of plant growth, turning on and off the temperature controllers.
Techno Environment Farming monitoring on Internet of Things is time consuming,
vulnerable to human error and less accurate and unreliable. So fully automized Techno
Environment Farming may be best. The humidity and temperature of air in a greenhouse
are, measured by sensor and whenever temperature is high or air moisture becomes too
low, fogger is turned on to provide the required moisture and cool down the temperature.
The purpose of the greenhouse monitoring using wireless sensor network prototype that is
targeted at transmitting and receiving data within the greenhouse infrastructure. It was used
as the target for the amount of data that is useful for an analysis of the factor that enable
proper functioning of farming.

Dept. of ECE, KLECET, Chikodi. 2022-23 1

 Smart Farms: Generating Techno Environment Farming

Chapter 2
LITERATURE SURVEY
Sujeet More, “Machine Learning Techniques with IoT in Agriculture”, International
Journal of Advanced Trends in Computer Science and Engineering 8(3):742-747
DOI:10.30534/ijatcse/2019/63832019, June 2019, Traditionally methods developed for
agriculture focused on the specific functionality/ domain-dependent such as temperature,
humidity pressure, etc and lacks of knowledge base for smart irrigation. In modern
generation, the volume of information gathered by numerous sensors over a period,
with a diverse series of applications nowadays, is acknowledged by means of Internet
of things.[1]
Geo Abraham, Raksha R, M. Nithya, “Smart Agriculture Based on IoT and Machine
Learning”, 2021 5th International Conference on Computing Methodologies and
Communication(ICCMC),80-10 April 2021, DOI: 10.1109/ICCMC51019.2021.9418392,
The IoT advancements have majorly influenced in redefining the agricultural field. A
reliable remote monitoring system is the need of the hour. In this paper, two objectives are
addressed. Firstly, an app-based solution is presented which helps in displaying the current
sensor values that efficiently aid in remotely administrating the field. Secondly, an IoT
based prototype system for surveillance is proposed that embeds the concept of multi-class
classification technique using Machine and Deep Learning for the labels clear farm, horse,
cow, wild elephant and wild boar. Support Vector Machines (SVM) and Convolutional
Neural Networks (CNN) were analysed for this purpose and the best model was chosen
based on accuracy metric.[2]
Somnath D. Bhagwat, Akash I.Hulloli, Suraj B.Patil, Abulkalam.A.Khan, Mr.A.S.Kamble,
“SMART GREENHOUSE USING IOT AND CLOUD COMPUTING”, International
Research Journal of Engineering and Technology, Volume 5,issue 3,March 2018. In this
paper, they have introduced the smart greenhouse farm using IOT and cloud computing
technology. The intention of this project is to design a simple, easy to install, user friendly
to monitor and record the values of temperature, humidity, soil-moisture and sunlight of
the natural environment that are continuously modified and controlled in order optimize
them to achieve maximum plant growth and yield. The result shows that the situation
specified in sensor ‘s database and system in actually is proper. The achieved test result
concludes that the system is working properly.[3]

Dept. of ECE, KLECET, Chikodi. 2022-23 2

 Smart Farms: Generating Techno Environment Farming
Mohammad Woli Ullah, Mohammad Golam Mortuza, Md Humayan Kabir, Zia Uddin
Ahmed, Sovan Kumar Dey Supta, ParthoDas,“Internet of Things Based Smart
Greenhouse: Remote Monitoring and Automatic Control”, International Conference on
Electric and Intelligent Vehicles(ICEIV 2018) This paper provides the information about
the system monitors temperature and humidity, soil moisture and take action according to
results. It includes with a database helpful for future analysis and reports. This system is
very suitable to be deployed at places like north pole and winter climate countries where
people live but plant does not grow due to heavy winter.[4]
Prof. D.O.Shirsath, Punam kamble, Rohini Mane, Ashwini kopla, prof.R.S.More “IOT
Based Smart Green House Automation using Arduino.”International Journal of Innovative
Research in computer Science & Technology (IJIRCST), Volume-5, Issue-2, March 2017
In this paper they have developed a project on Smart Greenhouse automation using IOT
and Arduino. They used IOT to control the Green house with android phone one of them
was Global system for mobile communication (GSM) this is used to send the notification
to the android phones, there was a biggest disadvantage in this was they had to type
message which was bit time consuming.[5]

Dept. of ECE, KLECET, Chikodi. 2022-23 3

 Smart Farms: Generating Techno Environment Farming

Chapter 3
PROBLEM STATEMENT
Can you imagine an industry that involves more risk than agriculture? You reap what you
sow, they say. But what they forget to add is “if you’re lucky.” When the weather strikes
or crops get affected by disease, farmers can hardly talk about yields. Or when a global
pandemic hits, all of a sudden it gets harder to manage various processes because most are
not digital.
At the same time, the global population is growing, and urbanization is continuing.
Disposable income is rising, and consumption habits are changing. Farmers are under a lot
of pressure to meet the increasing demand, and they need a way to increase productivity.
Thirty years from now, there will be more people to feed. And since the amount of fertile
soil is limited, there will also be a need to move beyond traditional farming.
We need to look for ways to help farmers minimize their risks, or at least make them more
manageable. Implementing artificial intelligence in agriculture on a global scale is one of
the most promising opportunities.
AI can potentially change the way we see agriculture, enabling farmers to achieve more
results with less effort while bringing many other benefits. However, AI is not a technology
that works independently. As the next step on the way from traditional to innovative
farming, AI can supplement already implemented technologies.

Why adopting Machine Learning is such a challenge for farmers

Farmers tend to perceive AI as something that applies only to the digital world. They might
not see how it can help them work the physical land. This is not because they’re
conservative or wary of the unknown. Their resistance is caused by a lack of understanding
of the practical application of AI tools.
New technologies often seem confusing and unreasonably expensive because AgriTech
providers fail to clearly explain why their solutions are useful and how exactly they should
be implemented. This is what happens with artificial intelligence in agriculture. Although
AI can be useful, there’s still a lot of work to be done by technology providers to help
farmers implement it the right way.

Dept. of ECE, KLECET, Chikodi. 2022-23 4

 Smart Farms: Generating Techno Environment Farming

Chapter 4
OBJECTIVE
Plants have had and still have a key role in the history of life on earth. They are responsible
for presence of oxygen needed for human survival on this planet. At the same time
agriculture is also important to human beings because it forms the basis for food security.
It helps human beings grow the most ideal food crops and raise the right animals with
accordance to environmental factors.
1. Agriculture plays a vital role in India's economy.
2. Over 58% of the rural households depend on agriculture as their principal means of
livelihood. Agricultural export constitutes 10% of the country's exports. So the
farmer's and even the nation's economy will be ruined if there are no proper yields
due to lack of knowledge of the soil nature, timely unavailability of water.
3. It is a smart farming stick based on IOT (Internet of things) technology which has
brought revolution to each and every field of common man’s life by making
everything smart and intelligent.
Aim of this project is to propose a novel smart IOT based agriculture stick assisting farmers
in getting live data (soil moisture, humidity, water level) for efficient environment
monitoring which will enable them to do smart farming and increase their overall yield and
quality of products. The smart agriculture being proposed via this project is integrated with
nodemcu technology, mixed with various sensors and live data feed can be obtained online
from mobile app.
Purpose of Machine learning is that to detect and monitor the disease and exact location of
that particular item (fruit & leaves) can be monitored using proximity sensors. Interfacing
the Machine Learning with Internet of Things will offer us wide range of features and helps
us to achieve a higher accuracy in terms of productivity and prediction.

Dept. of ECE, KLECET, Chikodi. 2022-23 5

 Smart Farms: Generating Techno Environment Farming

Chapter 5
HARDWARE USED
5.1 ESP32
Arduino is a great platform for beginners into the World of Microcontrollers and Embedded
Systems. With a lot of cheap sensors and modules, you can make several projects either as
a hobby or even commercial. As technology advanced, new project ideas and
implementations came into play and one particular concept is the Internet of Things or IoT.
It is a connected platform, where several “things” or devices are connected over internet
for exchange of information. In DIY community, the IOT projects are mainly focused on
Home Automation and Smart Home applications but commercial and industrial IoT
projects have far complex implementations like Machine Learning, Artificial Intelligence,
Wireless Sensor Networks etc.
5.1.1 What is ESP32?
ESP32 is a low-cost System on Chip (SoC) Microcontroller from Espressif Systems, the
developers of the famous ESP8266 SoC. It is a successor to ESP8266 SoC and comes in
both single-core and dual-core variations of the Tensilica’s 32-bit Xtensa LX6
Microprocessor with integrated Wi-Fi and Bluetooth. The good thing about ESP32, like
ESP8266 is its integrated RF components like Power Amplifier, Low-Noise Receive
Amplifier, Antenna Switch, Filters and RF Balun. This makes designing hardware around
ESP32 very easy as you require very few external components.
5.1.2 Specifications of ESP32
ESP32 has a lot more features than ESP8266 and it is difficult to include all the
specifications in this Getting Started with ESP32 guide. So, I made a list of some of the
important specifications of ESP32 here. But for complete set of specifications, I strongly
suggest you to refer to the Datasheet.
1. Single or Dual-Core 32-bit LX6 Microprocessor with clock frequency up to 240
MHz.
2. 520 KB of SRAM, 448 KB of ROM and 16 KB of RTC SRAM.
3. Supports 802.11 b/g/n Wi-Fi connectivity with speeds up to 150 Mbps.
4. Support for both Classic Bluetooth v4.2 and BLE specifications.
5. 34 Programmable GPIOs.
6. Up to 18 channels of 12-bit SAR ADC and 2 channels of 8-bit DAC
7. Serial Connectivity include 4 x SPI, 2 x I2C, 2 x I2S, 3 x UART.

Dept. of ECE, KLECET, Chikodi. 2022-23 6

 Smart Farms: Generating Techno Environment Farming
8. Ethernet MAC for physical LAN Communication (requires external PHY).
9. 1 Host controller for SD/SDIO/MMC and 1 Slave controller for SDIO/SPI.
10. Motor PWM and up to 16-channels of LED PWM.
11. Secure Boot and Flash Encryption.
12. Cryptographic Hardware Acceleration for AES, Hash (SHA-2), RSA, ECC and
RNG.

Fig 5.1: Nodemcu ESP32.

5.2 ESP32 CAM

To send the disease data to the farmer the ESP32 camera module is used. The ESP32-
CAM is a very small camera module with the ESP32-S chip. Besides the OV2640 camera,
and several GPIOs to connect peripherals, it also features a microSD card slot that can be
useful to store images taken with the camera or to store files to serve to clients.
Features:
1. The smallest 802.11b/g/n Wi-Fi BT SoC module
2. Low power 32-bit CPU, can also serve the application processor
3. Up to 160MHz clock speed, summary computing power up to 600 DMIPS
4. Built-in 520 KB SRAM, external 4MPSRAM
5. Supports UART/SPI/I2C/PWM/ADC/DAC

Dept. of ECE, KLECET, Chikodi. 2022-23 7

 Smart Farms: Generating Techno Environment Farming
6. Support OV2640 and OV7670 cameras, built-in flash lamp
7. Support image Wi-Fi upload
8. Support TF card
9. Supports multiple sleep modes
10. Embedded Lwip and FreeRTOS
11. Supports STA/AP/STA+AP operation mode
12. Support Smart Config/AirKiss technology
13. Support for serial port local and remote firmware upgrades (FOTA)

Fig 5.2: ESP32 Cam.

5.3 SOIL MOISTURE SENSOR

Soil moisture sensors measure the volumetric water content in soil. Since the direct
gravimetric measurement of free-soil moisture requires removing, drying, and weighing of
a sample, soil moisture sensors measure the volumetric water content indirectly by using
some other property of the soil, such as electrical resistance, dielectric constant, or
interaction with neutrons, as a proxy for the moisture content. The relation between the
measured proper soil moisture must be calibrated and may vary depending on
environmental factors such as soil type, temperature, or electric conductivity, reflected
microwave radiations affected by the soil moisture and is used for remote sensing in
hydrology and agriculture. Portable probe instruments can be used by farmers or gardeners.
Soil moisture sensors typically refer to sensors that estimate volumetric water content.
Another class of sensors measure another property of moisture in soils called water

Dept. of ECE, KLECET, Chikodi. 2022-23 8

 Smart Farms: Generating Techno Environment Farming
potential; these sensors are usually referred to as soil water potential sensors and include
tensiometers and gypsum blocks.

Fig 5.3: Soil Moisture Sensor.

5.4 INDUCTIVE PROXIMITY SENSOR

For the purpose of position sensing and homing of the camera guide rail actuator the
Inductive Proximity Sensors are used.
This DC 6-36V M17 Inductive 8mm NPN-NO Proximity Sensor Switch is a component
widely used in the automatic control industry for detecting, controlling, and non-contact
switching. When the proximity switch is close to some target object, it will send out the
control signal.
When the metal approaches near-proximity switch sensing area, and Eady Current
is induced in metal. Which in turn disturbs the magnetic field produced by the Inductive
Proximity Sensor. This change is sensed by the sensor.
This inductive proximity switches can be non-contact, no pressure, no spark, quickly issued
the electrical command. Accurately reflect the position and stroke movement mechanism.
Positioning accuracy, operating frequency, service life. Easy to install and suitable for
harsh environments. This 8mm proximity sensor can detect a variety of metals, miniature
size, long life, low price, shielded type installation, anti-interference ability, 1mm detection
distance, used for precise positioning of molds, precision machine tools, and robots.

Dept. of ECE, KLECET, Chikodi. 2022-23 9

 Smart Farms: Generating Techno Environment Farming

Fig 5.4: Inductive Proximity Sensors.

Features:
1. Red LED checks the state of the proximity sensor.
2. High repeated positioning accuracy.
3. High switching frequency.
4. Wide voltage range.
5. Outer (Theard) Diameter: M17.
6. Antivibration, dust, water and oil prevention.
7. Reverse power protection, short circuit protection, directly connecting with PLC.
8. It can replace small switches and limit switches.

5.5 DHT11 SENSOR

The DHT11 is a commonly used Temperature and humidity sensor that comes with a
dedicated NTC to measure temperature and an 8-bit microcontroller to output the values of
temperature and humidity as serial data. The sensor can measure temperature from 0°C to
50°C and humidity from 20% to 90% with an accuracy of ±1°C and ±1%.

DHT11 Specifications
1. Operating Voltage: 3.5V to 5.5V
2. Operating current: 0.3mA (measuring) 60uA (standby)
3. Output: Serial data
4. Temperature Range: 0°C to 50°C

Dept. of ECE, KLECET, Chikodi. 2022-23 10

 Smart Farms: Generating Techno Environment Farming
5. Humidity Range: 20% to 90%
6. Resolution: Temperature and Humidity both are 16-bit
7. Accuracy: ±1°C and ±1%

.
Fig 5.5: DHT11 Sensors.

5.6 Nema17 Stepper Motor

A stepper motor, also known as a step motor, is a brushless DC electric motor that divides
a full rotation down into equal steps. The motor’s position can then be programmed to
move and hold at any one of these individual steps without any position sensor for
feedback.
The National Electrical Manufacturers Association (NEMA) defines a set of standards used
to dictate tolerances for many products, including step motors. Step motors are categorized
by NEMA frame size, such as "size 11" or "size 23" or “size 34”. NEMA 17 stepper motors
are those that have a 1.8-degree step angle (200 steps/revolution) with a 1.7 x 1.7-inch
faceplate.
NEMA 17 steppers can be used in a number of different industrial and commercial
applications, however they are most commonly used in:
1. Robotics
2. CNC Machining
3. 3D Printers
4. Laser Cutters

Dept. of ECE, KLECET, Chikodi. 2022-23 11

 Smart Farms: Generating Techno Environment Farming
Stepper motor is used in our project to move the camera system through the farm.

Fig 5.6: NEMA17 Stepper Motor.

Stepper Motor Driver:

TB6500 Arduino Stepper Motor Driver is an easy-to-use professional stepper motor driver,
which could control a two-phase stepping motor. It is compatible with Arduino and
other microcontrollers that can output a 5V digital pulse signal.
TB6500 Arduino stepper motor driver has a wide range of power input, 9-24VDC power
supply. And it is able to output 3A peak current, which is enough for the most of stepper
motors. The stepper driver supports speed and direction control.
You can set its micro step and output current with 6 DIP switch. There are 7 kinds of micro
steps (1, 2 / A, 2 / B, 4, 8, 16, 32) and 8 kinds of current control (0.5A, 1A, 1.5A, 2A, 2.5A,
2.8A, 3.0A, 3.5A) in all. And all signal terminals adopt high-speed optocoupler isolation,
enhancing its anti-high-frequency interference ability. As a professional device, it is able
to drive 57, 42-type two-phase, four-phase, hybrid stepper motor.

5.7 SERVO MOTOR

A servo motor is a type of motor that can rotate with great precision. Normally this type
of motor consists of a control circuit that provides feedback on the current position of the

Dept. of ECE, KLECET, Chikodi. 2022-23 12

 Smart Farms: Generating Techno Environment Farming
motor shaft, this feedback allows the servo motors to rotate with great precision. If you
want to rotate an object at some specific angles or distance, then you use a servo motor. It
is just made up of a simple motor which runs through a servo mechanism. If motor is
powered by a DC power supply then it is called DC servo motor, and if it is AC-powered
motor then it is called AC servo motor. For this tutorial, we will be discussing only about
the DC servo motor working. Apart from these major classifications, there are many other
types of servo motors based on the type of gear arrangement and operating characteristics.
A servo motor usually comes with a gear arrangement that allows us to get a very high
torque servo motor in small and lightweight packages. Due to these features, they are being
used in many applications like toy car, RC helicopters and planes, Robotics, etc.
Servo motors are rated in kg/cm (kilogram per centimetre) most hobby servo motors are
rated at 3kg/cm or 6kg/cm or 12kg/cm. This kg/cm tells you how much weight your servo
motor can lift at a particular distance. For example: A 6kg/cm Servo motor should be able
to lift 6kg if the load is suspended 1cm away from the motors shaft, the greater the distance
the lesser the weight carrying capacity. The position of a servo motor is decided by
electrical pulse and its circuitry is placed beside the motor.
5.7.1 Servo Motor Working Mechanism.

Fig 5.7: Servo motor.

Solenoid valves are the most frequently used control elements in fluidics. Their tasks are
to shut off, release, dose, distribute or mix fluids. They are found in many application areas.
Solenoids offer fast and safe switching, high-reliability, long service life, good medium
compatibility of the materials used, low control power and compact design.

Dept. of ECE, KLECET, Chikodi. 2022-23 13

 Smart Farms: Generating Techno Environment Farming

5.8 RELAY CIRCUIT

Definition: The relay is the device that open or closes the contacts to cause the operation
of the other electric control. It detects the intolerable or undesirable condition with an
assigned area and gives the commands to the circuit breaker to disconnect the affected area.
Thus, protects the system from damage.
Working Principle of Relay:
It works on the principle of an electromagnetic attraction. When the circuit of the relay
senses the fault current, it energizes the electromagnetic field which produces the
temporary magnetic field. This magnetic field moves the relay armature for opening or
closing the connections. The small power relay has only one contacts, and the high-power
relay has two contacts for opening the switch. w32The inner section of the relay is shown
in the figure below. It has an iron core which is wound by a control coil. The power supply
is given to the coil through the contacts of the load and the control switch. The current
flows through the coil produces the magnetic field around it. Due to this magnetic field,
the upper arm of the magnet attracts the lower arm. Hence close the circuit, which makes
the current flow through the load. If the contact is already closed, then it moves oppositely
and hence open the contacts.

Fig 5.8: Relay Circuit.

Dept. of ECE, KLECET, Chikodi. 2022-23 14

 Smart Farms: Generating Techno Environment Farming

5.9 LCD DISPLAY

LCD stands for liquid crystal display. LCD is a flat-panel display or other electronically
Modulated optical device. LCD operates on 4.7v to 5.3v.16*2 LCD display consists of two
rows & each row can print 16 characters. This LCD has two registers, namely, Command
and Data. Command registers stores various commands given to the display. Data register
stores data to be displayed. The process of controlling the display involves putting the data
that form the image of what you want to display into the data registers, then putting
instructions in the instruction register. Contrast of the display can be adjusted by adjusting
the potentiometer.

Fig 5.9: LCD Display.

Specifications of LCD 16X2

1. The operating voltage of this display ranges from 4.7V to 5.3V
2. The display bezel is 72 x 25mm
3. The operating current is 1mA without a backlight
4. PCB size of the module is 80L x 36W x 10H mm
5. HD47780 controller
6. LED color for backlight is green or blue
7. Number of columns – 16
8. Number of rows – 2

Dept. of ECE, KLECET, Chikodi. 2022-23 15

 Smart Farms: Generating Techno Environment Farming
9. Number of LCD pins – 16
10. Characters – 32
11. It works in 4-bit and 8-bit modes

LCD 16X2 Pin Configuration

The pin configuration of LCD 16 X 2 is discussed below so that LCD 16×2 connection
can be done easily with external devices.
1. Pin1 (Ground): This pin connects the ground terminal.
2. Pin2 (+5 Volt): This pin provides a +5V supply to the LCD
3. Pin3 (VE): This pin selects the contrast of the LCD.
4. Pin4 (Register Select): This pin is used to connect a data pin of an MCU & gets
either 1 or 0. Here, data mode = 0 and command mode =1.
5. Pin5 (Read & Write): This pin is used to read/write data.
6. Pin6 (Enable): This enables the pin must be high to perform the Read/Write
procedure. This pin is connected to the data pin of the microcontroller to be held
high constantly.
7. Pin7 (Data Pin): The data pins are from 0-7 which are connected through the
microcontroller for data transmission. The LCD module can also work on the 4-bit
mode through working on pins 1, 2, 3 & other pins are free.
8. Pin8 – Data Pin 1
9. Pin9 – Data Pin 2
10. Pin10 – Data Pin 3
11. Pin11 – Data Pin 4
12. Pin12 – Data Pin 5
13. Pin13 – Data Pin 6
14. Pin14 – Data Pin 7
15. Pin15 (LED Positive): This is a +Ve terminal of the backlight LED of the display
& it is connected to +5V to activate the LED backlight.
16. Pin16 (LED Negative): This is a -Ve terminal of a backlight LED of the display &
it is connected to the GND terminal to activate the LED backlight.

Dept. of ECE, KLECET, Chikodi. 2022-23 16

 Smart Farms: Generating Techno Environment Farming

5.10 AI NPU DEVELOPMENT BOARD

The AI NPU is a system-on-chip (SoC) that integrates machine vision and machine hearing.
The NPU is dual-core 64-bit processors for better power performance, stability and
reliability. The NPU is best suit for Artificial Intelligence applications. The specifications
of the Neural processing unit are given below.
1. CPU: RISC-V dual-core 64bit, 400MHz adjustable frequency: Dual core 64 bit
2. FPU specification: IEEE754-2008 standard
3. Debugging support: JTAG Support Available
4. Camera: Onboard Camera support
5. Pinout: GPIOs, UART, I2C Pinout Available for easy interfacing of external
components.
6. Neural-Network Processor Unit (NPU):
• Support for the fixed-point model training framework
• 2 convolution kernels 1x1 and 3x3
• Activation Function support
7. Audio
• 4 channel Dual Input audio support
• Support beam forming in up to 16 directions
• Can support a valid voice stream output
• Inbuilt Audio Signal processor up to 32 Bit
• Support multi-channel raw signal direct output
• 192K sample rate Support
• 512-point FFT for input Audio
8. SARM
• 6MiB general purpose SARM
• 2MiB AI SRAM memory.
9. FPIOA/IOMUX: FIA with 255 internal functions to 48 GPIO
10. Video capture: Up to 640x480
11. Fast Fourier transform accelerator: Inbuilt
12. External supply voltage requirement: 5.0V±0.2V
13. External supply current demand: > 300mA @ 5V
14. Temperature rise: < 30K
15. Range of working temperature: -30 °C ~ 85 °CS

Dept. of ECE, KLECET, Chikodi. 2022-23 17

 Smart Farms: Generating Techno Environment Farming

Chapter 6
HARDWARE IMPLEMENTATION
6.1 Block Diagram

Fig 6.1: Block Diagram.

The basic block diagram of smart farms : generating techno environment farming is as
shown in figure. This system consists of NODEMCU Microcontroller and there are sensors
and some electronic components.These sensors act as input to the micro controller system.
The input feed provided to the micro controller is in the form of analog data. Soil moisture
sensor senses the water content in the soil, DHT11 senses the Humidity and temperature
values, Proximity Sensor is used to detect the metal object to monitor placement of camera
and also helps to know the exact location of the unhealthy products. This data is converted
by the controller into digital format. The data is shown on the LCD display and also on the
android phone/website by the means of Internet.Thus the monitoring of temperature,
moisture and other parameters is done automatically. Once the parameter values are
monitored they can be controlled by the embedded system which is built with coding. This
is automating controlling system. The android phone is operated by the user. The android
application is used for controlling as per the user knowledge and required output.
The hardware fabrication involves designing the PCB schematic in EasyEDA software and
then fabricating and making the connections to run the entire system. After the PCB

Dept. of ECE, KLECET, Chikodi. 2022-23 18

 Smart Farms: Generating Techno Environment Farming
fabrication is done the programming will be done. The printed circuit board (PCB) acts as
a linchpin for almost all of today’s modern electronics. If device needs to do some sort of
computation-such as is the case even with the simple digital clock. Chances are there is the
PCB inside of it. PCBs bring electronics to life by routing electrical signals where they
need to go to satisfy all of the device’s electronic requirements.
There are three main types of circuit boards that get manufactured on a consistent basis,
and it’s important to understand the differences between each so you can decide the right
circuit board for your requirements. The three main types of circuit boards in current
manufacture are:
1. Single-Sided Circuit Boards: These boards when made with a FR4 base have
rigid laminate of woven glass epoxy material, which is then covered on one side
with a copper coating that is applied in varying thicknesses depending on the
application
2. Double-Sided Circuit Boards: Double-sided boards have the same woven glass
epoxy base as single-sided boards — however, in the case of a double-sided board,
there is copper coating on both sides of the board, also to varying thicknesses
depending on the application.
3. Multi-Layer Boards: These use the same base material as single and double-
sided boards, but are made with copper foil instead of copper coating — the copper
foil is used to make “layers,” alternating between base material and copper foil until
the number of desired layers is reached.
Parts of PCB
1. Substrate: The first, and most important, is the substrate, usually made of
fiberglass. Fiberglass is used because it provides core strength to the PCB and helps
resist breakage. Think of the substrate as the PCB’s “skeleton”.
2. Copper Layer: Depending on the board type, this layer can either be copper foil
or a full-on copper coating. Regardless of which approach is used, the point of the
copper is still the same to carry electrical signals to and from the PCB, much like
your nervous system carries signals between your brain and your muscles.
3. Solder Mask: The third piece of the PCB is the solder mask, which is a layer of
polymer that helps protect the copper so that it doesn’t short-circuit from coming
into contact with the environment. In this way, the solder mask acts as the PCB’s
“skin”.

Dept. of ECE, KLECET, Chikodi. 2022-23 19

 Smart Farms: Generating Techno Environment Farming
4. Silk screen: The final part of the circuit board is the silkscreen. The silkscreen is
usually on the component side of the board used to show part numbers, logos,
symbols switch settings, component reference and test points. The silkscreen can
also be known as legend or nomenclature.

6.2 Schematic Diagram

The hardware is designed using an EDA software and PCB for the same is fabricated:
The first part of the hardware is the developed is to interface the different sensors and the
control systems to run the robotic vehicle. The Schematic for the same is given below. The
hardware is developed in EASY EDA schematic development software and then the
fabrication is done to develop the printed circuit board as per the schematic designed. The
schematic diagram is shown below.

Fig 6.2: Schematic Design.

Dept. of ECE, KLECET, Chikodi. 2022-23 20

 Smart Farms: Generating Techno Environment Farming

6.3 PCB Design

Fig 6.3:PCB Design.

Fabricated Hardware:

Fig 6.4:PCB Fabricated Hardware.

Dept. of ECE, KLECET, Chikodi. 2022-23 21

 Smart Farms: Generating Techno Environment Farming

Chapter 7
SOFTWARE IMPLEMENTATION
The software implementation consists of the development of the IOT application which
can be accessed using android and web. The application is developed using HTML
bootstrap and PHP framework and uses Connect IOT API hosted on aws.
HTML bootstrap
Bootstrap is an HTML, CSS and JS library that focuses on simplifying the development of
informative web pages (as opposed to web applications). The primary purpose of adding it
to a web project is to apply Bootstrap's choices of color, size, font and layout to that project.
As such, the primary factor is whether the developers in charge find those choices to their
liking. Once added to a project, Bootstrap provides basic style definitions for all HTML
elements. The result is a uniform appearance for prose, tables and form elements
across web browsers. In addition, developers can take advantage of CSS classes defined in
Bootstrap to further customize the appearance of their contents. For example, Bootstrap
has provisioned for light- and dark-colored tables, page headings, more prominent pull
quotes, and text with a highlight.
How your devices and apps access AWS IoT
AWS IoT provides the following interfaces for AWS IoT
1. AWS IoT Device SDKs: Build applications on your devices that send messages to and
receive messages from AWS IoT.
2. AWS IoT Core for LoRaWA: Connect and manage your long-range WAN
(LoRaWAN) devices and gateways by using AWS IoT Core for LoRaWAN.
3. AWS Command Line Interface (AWS CLI: Run commands for AWS IoT on
Windows, macOS, and Linux. These commands allow you to create and manage thing
objects, certificates, rules, jobs, and policies.
4. AWS IoT API: Build your IoT applications using HTTP or HTTPS requests. These
API actions allow you to programmatically create and manage thing objects,
certificates, rules, and policies.
5. AWS SDKs: Build your IoT applications using language-specific APIs. These SDKs
wrap the HTTP/ HTTPS API and allow you to program in any of the supported
languages.

Dept. of ECE, KLECET, Chikodi. 2022-23 22

 Smart Farms: Generating Techno Environment Farming
The output of the application developed is as shown:

7.1 Sensor data page

Fig 7.1: Sensor Data.

7.2 Control Page

Fig 7.2: Control Page.

7.3 Disease Detection Page:

Fig 7.3: Disease Detection Page.

Dept. of ECE, KLECET, Chikodi. 2022-23 23

 Smart Farms: Generating Techno Environment Farming

Chapter 8
MACHINE LEARNING INTERFACE
What is machine learning?
IoT and machine learning deliver insights otherwise hidden in data for rapid, automated
responses and improved decision making. Machine learning for IoT can be used to project
future trends, detect anomalies, and augment intelligence by ingesting image, video and
audio.
Why use machine learning for IoT?
Machine learning can help demystify the hidden patterns in IoT data by analyzing massive
volumes of data using sophisticated algorithms. Machine learning inference can
supplement or replace manual processes with automated systems using statistically derived
actions in critical processes.
Sample use cases
Companies are utilizing machine learning for IoT to perform predictive capabilities on a
wide variety of use cases that enable the business to gain new insights and advanced
automation capabilities.
With machine learning for IoT, you can:
1. Ingest and transform data into a consistent format
2. Build a machine learning model
3. Deploy this machine learning model on cloud, edge and device
For example, using machine learning, a company can automate quality inspection and
defect tracking on its assembly line, track activity of assets in the field and forecast
consumption & demand patterns.
Machine learning is to train the system over a large observed data to predict outcomes or
categorize observations in future data, by other means, to generate extraction patterns or
build a model and use the generated patterns or model to make predictions in the future for
unknown cases. The data set used to learn the model is known as the training data set. The
records making up the training set are referred to as training samples and are randomly
selected from the sample population. The resulting model is typically applied to new
samples to categorize or predict values of the outcome for previously unseen observations,
and its performance evaluated by comparing predicted values to actual values for a set of
test samples, this step is known as supervised learning. Machine learning techniques are
used to analyse important clinical parameters and their combinations for prognosis in

Dept. of ECE, KLECET, Chikodi. 2022-23 24

 Smart Farms: Generating Techno Environment Farming
Cancer research domain, e.g., prediction of disease progression, extraction of medical
knowledge for outcome research, therapy planning and support, and for the overall patient
management. While Data Mining is a discipline resulting from the combination of classical
statistics and computer science algorithms, such as Machine Learning, aim to the extraction
of new and useful knowledge from a large amount of data, it has become a useful
instrument in health informatics. It can depict variation of cancer incidence and mortality
by region, ethnicity, gender and socio-economic factors that contribute to the assessment
of population health needs, while it can contribute to the study of cancer burden.
Furthermore, in depth analysis of the patient’s profile using data mining methods may
uncover hidden, previously unknown relations between patient profile, cancer treatment
and surveillance. Therefore, Mining of medical data is one of most interesting, though hard,
machine learning tasks. Thus, both the data mining and healthcare industry have emerged
some of reliable early detection systems and other various healthcare related systems from
the clinical and diagnosis data related to cancer in order to predict the different stages of
the latter as well as to assisting in diagnosis for the doctors for making their clinical
decision. As we see, it seems that as the healthcare environment is becoming more and
more reliant on computing technologies. The use of ML methods and data mining
techniques can provide useful aids to assist physicians in many cases of cancer provide
rapid identification of abnormalities and enable diagnosis in real time, considering the
importance of time in detection and diagnosis of cancer. There are two categories of data
mining models, predictive model and descriptive model. Predictive data mining often apply
supervised learning functions to predict unknown or future values of other variables of
interest. Descriptive data mining, often apply the unsupervised learning functions in
finding patterns describing the data that can be interpreted humans. An overview of the
applications of Predictive and Descriptive data mining on the management of cancers is
presented in the next section of this chapter. The included studies are classified according
to data mining model applied on datasets.
We have used supervised machine learning approach to train a disease detector model.
Since it is problem related with image more specifically it is a problem related to deep
learning. We have used transfer learning approach to determine the model output.
Procedure used:
1. Dataset Collection
2. Pre-processing
3. Annotation

Dept. of ECE, KLECET, Chikodi. 2022-23 25

 Smart Farms: Generating Techno Environment Farming
4. Model training configuration
5. Training
6. Deployment
7. Dataset Collected

Infected Leaves

Fig 8.1: Infected Leaves Sample.

Normal Leaves

Fig 8.2: Normal Leaves.

Dept. of ECE, KLECET, Chikodi. 2022-23 26

 Smart Farms: Generating Techno Environment Farming

Chapter 9
ADVANTAGES AND DISADVANTAGES

9.1 The Pros/Benefits/Advantages of IoT

Internet of things (IoT) facilitates the several advantages in day-to-day life in the business
sector (for example in agriculture). Some of its benefits are given below:
1. Efficient resource utilization: If we know the functionality and the way that how
each device work we definitely increase the efficient resource utilization as well as
monitor natural resources.
2. Minimize human effort: As the devices of IoT interact and communicate with
each other and do lot of task for us, then they minimize the human effort.
3. Save time: As it reduces the human effort then it definitely saves out time. Time is
the primary factor which can save through IoT platform.
4. Improve security: Now, if we have a system that all these things are
interconnected then we can make the system more secure and efficient.

9.2 The Cons/Disadvantages/Drawbacks of IoT

As the Internet of things facilitates a set of benefits, it also creates a significant set of
challenges. Some of the IoT challenges are given below:
1. Security: As the IoT systems are interconnected and communicate over networks.
The system offers little control despite any security measures, and it can be lead the
various kinds of network attacks.
2. Privacy: Even without the active participation on the user, the IoT system provides
substantial personal data in maximum detail.
3. Complexity: The designing, developing, and maintaining and enabling the large
technology to IoT system is quite complicated.

Dept. of ECE, KLECET, Chikodi. 2022-23 27

 Smart Farms: Generating Techno Environment Farming

Chapter 10
RESULT
Smart farming based on IoT technologies enables growers and farmers to reduce waste and
enhance productivity ranging from the quantity of fertilizer utilized to the number of
journeys the farm vehicles have made, and enabling efficient utilization of resources such
as water, electricity, etc. IoT smart farming solutions is a system that is built for monitoring
the crop field with the help of sensors (light, humidity, temperature, soil moisture, crop
health, etc.) and automating the irrigation system. The farmers can monitor the field
conditions from anywhere.

Table 01: DHT11 Readings:

These are the temperature and Humidity readings recorded by DHT11 Sensor.
Date: 27-04-2023
Trails Time Temperature Humidity
1 07:00 AM 24.00 C 70.00%
2 10:00 AM 30.00 C 47.00%
3 12:00 PM 34.10 C 33.00%
4 06:30 PM 26.10 C 43.00%
5 10:30 PM 25 C 67%

Table 01: DHT11 Readings.

Table 02: Soil moisture Sensor Readings:

Soil moisture Sensor Data Readings recoded by Soil Moisture Sensor.
Date: 27-04-2023
Trails Time Soil Condition Outcome
1 07:00 AM Dry Motor ON
2 10:00 AM Wet Motor OFF
3 03:00 PM Partially Wet Motor OFF
4 09:00 PM Dry Motor ON

Table 02: Soil Moisture Sensor Readings.

Dept. of ECE, KLECET, Chikodi. 2022-23 28

 Smart Farms: Generating Techno Environment Farming

Table 03: Machine Learning Disease Detection table

Trails Objects Disease Condition Outcome

1 Healthy Tomato Not Detected No Result
2 Diseased tomato Detected Data Sent to website
3 Diseased Leaf Detected Data Sent to website

Table 03: Machine Learning Disease Detected Data.

Output of Temperature, Humidity, Moisture level and Light Intensity

Fig 10.1: Output of Weather parameters.

Output of disease detection page

Fig 10.2: Output of Disease detection page.

Dept. of ECE, KLECET, Chikodi. 2022-23 29

 Smart Farms: Generating Techno Environment Farming

REFERENCES
[1] Sujeet More, “Machine Learning Techniques with IoT in Agriculture”,
International Journal of Advanced Trends in Computer Science and
Engineering 8(3):742-747 DOI:10.30534/ijatcse/2019/63832019, June 2019.

[2] Geo Abraham, Raksha R, M. Nithya, “Smart Agriculture Based on IoT and
Machine Learning”, 2021 5th International Conference on Computing
Methodologies and Communication (ICCMC),80-10 April 2021,DOI :
10.1109/ICCMC51019.2021.9418392

[3] Somnath D. Bhagwat, Akash I.Hulloli, Suraj B.Patil, Abulkalam.A.Khan,

Mr.A.S.Kamble, “SMART GREENHOUSE USING IOT AND CLOUD
COMPUTING”, International Research Journal of Engineering and Technology,
Volume 5, issue 3, March 2018.

[4] Mohammad Woli Ullah, Mohammad Golam Mortuza, Md Humayan Kabir, Zia
Uddin Ahmed, Sovan Kumar Dey Supta, ParthoDas,“Internet of Things Based
Smart Greenhouse: Remote Monitoring and Automatic Control”, International
Conference on Electric and Intelligent Vehicles (ICEIV 2018).

[5] Prof. D.O.Shirsath, Punam kamble, Rohini Mane, Ashwini kopla, prof.R.S.More
“IOT Based Smart Green House Automation using Arduino.”International Journal
of Innovative Research in computer Science & Technology (IJIRCST), Volume-5,
Issue-2, March 2017.

Dept. of ECE, KLECET, Chikodi. 2022-23 30