IAES International Journal of Artificial Intelligence (IJ-AI)

Vol. 13, No. 3, September 2024, pp. 3588~3598

ISSN: 2252-8938, DOI: 10.11591/ijai.v13.i3.pp3588-3598  3588

Data-driven farming: implementing internet of things for

agricultural efficiency

Mohamed Ismail Lafta, Wisam Dawood Abdullah

Department Computer Science, Computer Science and Mathematics College, Tikrit University, Tikrit, Iraq

Article Info ABSTRACT

Article history: Integrating internet of things (IoT) technology into agriculture has become
essential to address challenges such as low crop productivity, which is often
Received Jan 10, 2024 due to insufficient soil nutrients and suboptimal environmental conditions.
Revised Feb 18, 2024 This paper discusses the design and implementation of an IoT-based system
Accepted Feb 28, 2024 for agriculture that aims to automate key parameters, facilitate real-time
monitoring, and promote sustainable practices. Equipped with a graphical user
interface (GUI), the system focuses on improving irrigation, regulating
Keywords: temperatures, and correcting soil nutrient deficiencies to improve crop
productivity. Our research includes the use of humidity sensors to monitor soil
Design greenhouse moisture and temperature sensors. Soil nutrient levels, especially nitrogen,
Internet of thing agriculture phosphorus, and potassium (NPK), were also assessed. We conducted
Internet of thing Blynk platform experiments on three radish varieties using this IoT system and compared the
Smart farm results with traditional farming methods. The germination rate was
Smart greenhouse impressive, reaching 98% within the first four days, while in a traditional
greenhouse, it did not exceed 50%. As for plant height and leaf area, the smart
greenhouse was better. These results were promising and demonstrated the
potential of IoT in enhancing agricultural productivity. These results highlight
the significant impact of IoT technology in enhancing agricultural
productivity and its potential for broader application in this sector.
This is an open access article under the CC BY-SA license.

Corresponding Author:
Wisam Dawood Abdullah
Department Computer Science, Computer Science and Mathematics College, Tikrit University
Tikrit, Iraq
Email: [email protected]

1. INTRODUCTION
Modern agriculture systems available to land and water are putting growing pressure on food
production [1]. It increasingly depends on information and communication technology, especially robotics,
cloud computing, sensing technologies, and artificial intelligence internet of things (IoT) [2]. IoT technology
has the potential to revolutionize the agriculture filed [3]. The IoT is a global network of connected things [4],
[5] that can be uniquely interacted with using popular communication protocols [6], [7]. It's a modern search
technology that connects physical items with the digital world, providing a path to the Internet of the future
[8]. Sensors and heterogeneous actuators are the key components of the IoT [9]. Recently, the IoT has become
one of the top trending technologies, expanding innovation and achieving standardization. It is certainly the
opportunity of digital connectivity that has transformed the original human objects into smarter electronic
devices [10]. The IoT is a holistic idea that integrates everything [11]. This reality has aided in the creation of
smart farming, which monitors crops as they grow with the use of irrigation systems and sensors [12]. Accurate
data regarding the crop, soil, and environment could be obtained via sensor-based computer applications.
Farmers are still using traditional techniques of agricultural supervision resulting in wastage of inputs and
production close to the ground due to inaccurate types and quantities of water used in agriculture [13].

Journal homepage: http://ijai.iaescore.com

Int J Artif Intell ISSN: 2252-8938  3589

Agriculture can only become self-sufficient through the use of advanced, environmentally solutions and
contemporary agricultural techniques necessary to increase productivity and reduce production costs. The
unique thing about greenhouse agriculture is that it is effective in natural crop separation and protecting plants
from the direct effects of external weather conditions [14]. Microcontrollers facilitate simple and effective job
organization and monitoring for the user throughout the smart greenhouse [15]. This centralized system's main
characteristic is its ability to monitor and regulate many agricultural system parameters, including humidity of
soil, temperature, and nutrient levels in the soil. Recently, many companies have produced hardware devices
needed by IoT, like sensors with a communication module and control equipment with self-network ability,
this means IoT's main problem is the overall system design and implementation [16], [17].
Many previous studies were reviewed that used IoT technologies in agriculture, including proposed and
implemented IoT in smart agriculture or greenhouse use some of this study. Bandara et al. [18] proposed a
system that collected information from IoT sensors, such as soil moisture, temperature, and water volume
sensors. Vandôme et al. [19] proposed developing a wireless soil moisture sensor that is open source, low power,
and affordable. This inexpensive sensor can be used to track irrigation in real time [19]. Cheruvu et al. [20]
proposed the implementation of a smart farm using the IoT. The farmer will be able to track plant and soil
vitals in real time [20]. Bappa et al. [21] proposed to develop and implement an “IoT-based greenhouse
monitoring and monitoring system” to track and regulate environmental variables to maintain the ideal climate
for small plants inside the greenhouse. Benyezza et al. [22] proposed a smart platform based on the IoT for
climate and irrigation monitoring and control. Temperature, humidity, and soil moisture were collected and
sent to a Raspberry Pi-to process it [22]. Mohabuth et al. [23] proposed a completely automation model for
greenhouses with all the features it need, including fans, pumps, sensors, and microcontrollers, to provide real-
time data for accurate plant growth monitoring. Ali et al. [24] proposed to design a smart greenhouse that relies
on Arduino to control sensors and IoT components to grow strawberries.
In this paper presents an innovative approach and proposes a new system that can help in the design
and implementation of agricultural IoT systems. Electronic circuits and sensors are designed to connect the
central control unit (ESP32) to control and provide the ideal atmosphere. In addition, a website has been
designed to monitor the operation of the system running on smartphone and computers by using Blynk
platforms. A traditional greenhouse and a smart greenhouse were created that can regulate heating and cooling
systems and make irrigation automatic, in addition to inquiring about the amount of nutrients present in the
soil (nitrogen, phosphorus, and potassium (NPK)). And control the water level in the smart greenhouse tank.
The following results will be compared, such as the level of germination, the size of the leaf area, and the plant
height rate. The smart homes project is considered one of the most important field agricultural projects in the
field of agriculture. It can be used to reduce labor and rationalize water consumption, in addition to knowing
soil fertility. This paper has been designed and implemented using ESP32 and sensors. and designed and
implemented the software App by using the Blynk platform. The proposed smart greenhouse experiment was
conducted in growing radishes, and the results were excellent compared to traditional greenhouses.

2. HARDWARE IMPLEMENTATION
The suggested system's architecture consists of a peer-to-peer connection between separate sensors
connected by a shared router [25]. The user will specify the number of sensors present, as this is only limited
by the number of sensors present in the “smart greenhouse” [26], [27]. Automated irrigation system: constant
observation and soil condition assessment are necessary to sustain crops in good health. As a result, the system
records data using several sensors and sends it to the central control system for processing. Depending upon a
few variables, like the surrounding temperature, the soil's moisture content, and the proportion of nutrients in
the soil [28]–[30]. Figure 1 shows how to connect the electrical circuit of the proposed system in terms of
connections to the inputs and outputs. The sensors will be connected to the analog ports and the outputs
will be connected to the digital ports of the ESP32 as follows: the first stage is the 5V power supply stage
of the ESP32, through which all the IoT components are controlled. When it works, the sensors connected
to it are supplied with power, each according to the required power. The data is then read from the sensor s
and the readings are compared with the ideal values stored in the ESP32, after which a decision is made.
To turn the engine on or off, then send the data over the Internet to the Blynk server to provide the app
with the data for real-time monitoring and then store a copy of the data for each sensor in a Google Sheet,
which is maintained by a pre-set timer. The smart greenhouse is monitored continuously, while storage in
Google Sheets depends on the exact storage time. The sensors will be connected to the analog and digital
pins of the ESP32 as follows:
First: Soil moisture sensor. The soil moisture sensor is supplied with a voltage of 3.3 volts, and
the data received from the sensor is read through the SVP port in the ESP32, and then the reading is
compared with the ideal value stored in the ESP32 after which the decision is made whether to turn ON,
or OFF. The irrigation actuator from port 13 to the relay that connects to the irrigation system. Second:
Data-driven farming: implementing internet of things for agricultural efficiency (Mohamed Ismail Lafta)
3590  ISSN: 2252-8938

temperature sensor. The DHT22 temperature sensor is supplied with a voltage of 3.3 volts, and the data
received from the sensor is read through port 25 on the ESP32, and then the reading is compared with the
ideal value stored in the ESP32 so that a decision is made if the value is higher or equal to the ideal value
in ESP32. A signal is sent to the relay via pin 32 of the ESP32 to turn on the cooling fans of the smart
greenhouse. However, if the value is low, a signal will be sent to the relay via port 33 to turn on the heaters
in the smart greenhouse so that the temperature remains closer to ideal. Third: Water level sensor . The
water level sensor is supplied with a voltage of 3.3 volts, and the data received from the sensor is read
through port 35 on the ESP 32, and then the reading is compared with the ideal value stored in the ESP32
so that a decision is made and a command to turn on or off the alarm is sent through the port. 26 to the
relay that connects to the alarm in the system. Fourth: NPK sensor. The NPK sensor is supplied with 12
volts from an external source because the ESP32 is the highest power port with 5 volts. Next, the MAX485
is connected between the NPK sensor and the ESP32, where the NPK sensor is connected. The MAX -485
is connected to a 5V power supply through the ESP32, the yellow cable is connected to the NPK sensor to
port A on the Max 485, and the blue cable is connected to port B on the Max 485. Next, the Max 485 is
connected to the ESP32 through the following ports: DE port 14, RE to port 12, DI to TX port, and RO to
RX port. Then a 4*20 LCD display is connected to the ESP32 device via ports 21 and 22 to display the
results to the user. After that, a copy of the data for each sensor is sent to Google sheets. every five minutes.
Figure 2 shows the final design of the proposed system after connecting all the sensors to the ESP32 and the
design was done using simulation programs before starting the real design. And explain the operation
connection for each sensor with the ESP32 as explained in Figure 1.

Figure 1. The electrical circuit method of the proposed system

Figure 2. Design of the proposed system

Int J Artif Intell, Vol. 13, No. 3, September 2024: 3588-3598

Int J Artif Intell ISSN: 2252-8938  3591

3. SOFTWARE IMPLEMENTATION
Compared to other applications, IoT infrastructure for the agricultural sector is more complicated
because of the need for real-time monitoring in the agricultural environment. Additionally, agricultural
developers should have access to source tools to build sustainable and affordable applications [31]–[33].
Figure 3 shows the architecture of the Blynk platform where the proposed system will be analyzed to see how
it communicates between the ESP32 and the server, which will use the Blynk platform to monitor the system's
work. Websites need engineering and planning regarding how the website is built or set up so that users have
a positive experience while achieving business goals. In this project, the platform is represented by
model-view-controller (MVC) architecture. The greenhouse architectural model creates user interfaces specific
to the Blynk platform based on the smart greenhouse's sensors' functionality. The system will be monitored by
the user using a smartphone or computer through the website, where the programming work is divided into two
parts: the front-end section, which is shown to the end user, and the back-end, which is responsible for the
database and how to communicate between the server and the proposed system, where it was designed. The
system was powered and monitored the greenhouse by the Blynk platform. Blynk can be defined as a
comprehensive software suite that enables prototyping, deployment, and remote management of connected
electronic devices at all IoT.
Backend: Figure 3 shows the architecture of the Blynk platform, which refers to the server-side
components of the Blynk platform responsible for processing requests from the front-end components
(Blynk console or Blynk apps). Backend components include databases to store device, user, and enterprise
data. It also includes security mechanisms such as authentication and authorization to ensure secure access to
data and devices on the platform.
Front-end: refers to the user interface (UI) components of Blynk console web app or Blynk mobile
applications allow interaction between users and the platform. Front-end components include user interface
elements, such as buttons, sliders, charts, and gauges, which visualize data from connected devices and enable
users to control them remotely. Including screens for device configuration, user management, and organization
management. Figure 4 shows how the Blynk platform works, requesting from the Blynk platform, and data is
retrieved from the platform’s database. After sending the required data from the database and configuring the
required interface, it is sent from the Blynk platform to the user’s smartphone or computer.

Figure 3. The architecture of Blynk Figure 4. Mechanism of the Blynk platform

platform

4. METHOD
This study presents the design and implementation of a smart greenhouse model through IoT -based
smart agriculture. Sensors are used and connected to the ESP32 which controls soil moisture, air
temperature, and water level in the tank. A sensor was also used to determine the amount of nutrients
present in the soil. Smart decision-making is based on real-time data from the greenhouse. We hope to help
farmers monitor greenhouses. IoT-based smart farm technology aims to help manage non-uniform elements
such as moisture, temperature, and soil nutrients [34], [35]. Farmers can expect good health and consistent
crop yields by automating irrigation systems and analyzing data to find ideal levels of moisture,
temperature, and soil nutrients. They can also easily share this information with other farmers 36. Figure 5
shows a flowchart of the sensor control mechanism using ESP32. It represents the sensor control

Data-driven farming: implementing internet of things for agricultural efficiency (Mohamed Ismail Lafta)
3592  ISSN: 2252-8938

mechanism in terms of reading data and sending it to the ESP32 to compare the data reading of each sensor
with the stored ideal threshold value and make the appropriate decision regarding turning on or off the
actuator.

Figure 5. Flowchart of sensors to control mechanism by ESP32

The work will be divided into two parts. The first part will be the admin, the ESP32, as it analyzes
data received from sensors and makes the appropriate decision after comparing the data with the ideal values
stored in it. Figure 6 shows the flowchart of a proposed system work. The soil is monitored using a soil moisture
sensor, which measures the soil's moisture level. It reads the humidity level in the soil and compares it with the
ideal value stored in ESP32. If the humidity of the soil is less than or equal to 45%, the ESP32 will turn on a
12V pump to push water to the area to be irrigated. However, if the humidity of the soil is greater than the
required level, the water pump will stop. Heating and cooling operations can also be controlled by relying on
the DHT22 sensor linked to the ESP32. If the value received from the sensor is less than or equal to 22 °C, the
ESP32 will turn on the heater inside the smart greenhouse. However, if the temperature exceeds or equals
23 °C, the ESP32 will turn on the cooling fans to bring the temperature down to the desired rate. It is also
possible to inquire about the values of nutrients in the soil by relying on the NPK sensor. The ESP32 reads data
received from the sensor and prints it on the screen so that the farmer knows whether the soil needs NPK. It
also controls the water level in the smart greenhouse tank. If the level is lower than 70%, the ESP32 turns on
the alarm, but when the level of the water in the tank is equal to or greater than the required level; then the
alarm is off. The ESP32 then sends a copy of each sensor's values to Google Sheets to save them in a preset
database. It was decided to take a copy of the reading and save it every 5 minutes in the normal condition. In
the event of a malfunction in any sensor, an inquiry will be sent to the farmer to alert him. The second part is
that the farmer will have the authority to turn off or turn on the system in the greenhouse. The system can also
be monitored through the Blynk application that was previously prepared for the system, as the system will
help the farmer monitor the environmental conditions in the smart greenhouse.

4.1. Proposed system

This section explains the design and implementation of the proposed system. Figure 7(a) shows the
internal components of the system, where the ESP32 device is connected to the sensors and placed in a plastic
plate to protect it from external damage. The board consists of an ESP32 connected to a 24-hour power supply
where the outputs are connected to a 6-pin relay used to turn on or off the cooling and heating systems, irrigation
system, and alert when there is a fault of low water level in the tank. Displays NPK values in the soil which
appear on the screen. As for the inputs, they are connected to the sensors. Figure 7(b) shows the external
appearance of the proposed system. All devices and relays were wrapped to protect them from external damage.

Int J Artif Intell, Vol. 13, No. 3, September 2024: 3588-3598

Int J Artif Intell ISSN: 2252-8938  3593

Figure 6. The Flowchart of a proposed system work

(a) (b)

Figure 7. Final design of the proposed system: (a) internal connection of devices, and (b) system experience

Table 1 shows the needs of each sensor and the amount of voltage it requires, as the ESP32 equips
each sensor with the power required to work in the proposed system. Figure 8(a) shows the placement of the
NPK sensor in the soil. Figure 8(b) shows the placement of the soil moisture sensor in the anvil. Figure 8(c)
shows the implementation of the proposed system in the smart greenhouse and links the sensors to the proposed
system to work in it.
Figure 9(a) shows the computer application. Figures 9(b) and 9(c) show the application for mobile
devices. The application works to monitor the work of sensors in the greenhouse and follow the work in
real-time, provided by the Blynk platforms. Table 2 shows the values sent from the Esp32 to the Google Sheets.
The values received from the sensors are automatically saved to the Google Sheets, where they are connected
to the farmer's Google account.

Table 1. The voltage of power sensors

Sensor Power (V)
NPK 12
Temperature 3.3
Soil moisture 3.3
Water level 3.3

Data-driven farming: implementing internet of things for agricultural efficiency (Mohamed Ismail Lafta)
3594  ISSN: 2252-8938

(a) (b) (c)

Figure 8. Implementation of the proposed system in the smart greenhouse: (a) NPK sensor in anvil,
(b) soil moisture sensor in the anvil, and (c) smart distillation in the greenhouse

(a)

(b) (c)

Figure 9. Implementing a smart greenhouse monitoring system using the Blynk platform: (a) monitoring the
system by computer, (b) monitoring the chart of the sensors by phone, and (c) monitoring sensors status
by phone

Int J Artif Intell, Vol. 13, No. 3, September 2024: 3588-3598

Int J Artif Intell ISSN: 2252-8938  3595

Table 2. Data sent from Esp32 to google sheets

K P N Watering plant Water Water pump Humidity of Fan Temperature Date
Pump level actuator soil actuator
160 190 185 OFF 100 OFF 59 ON 24C 2023/12/01
160 190 185 OFF 100 OFF 60 ON 24C 2023/12/01
160 190 185 OFF 100 OFF 60 ON 25C 2023/12/01
160 190 185 OFF 100 OFF 60 ON 25C 2023/12/01
160 190 185 OFF 100 OFF 60 ON 25C 2023/12/01
160 190 185 OFF 100 OFF 60 ON 26C 2023/12/01
160 190 185 OFF 100 OFF 60 ON 25C 2023/12/01
160 190 185 OFF 100 OFF 60 ON 26C 2023/12/01
160 190 185 OFF 100 OFF 60 ON 28C 2023/12/01
160 190 185 OFF 100 OFF 60 ON 28C 2023/12/01
160 190 185 OFF 100 OFF 62 ON 29C 2023/12/01
160 190 185 OFF 100 OFF 61 ON 31C 2023/12/01
160 190 185 OFF 100 OFF 61 ON 32C 2023/12/01
160 190 185 OFF 100 OFF 61 ON 31C 2023/12/01

5. RESULT AND DISCUSSION

Were made two greenhouses measuring 170×200×150 cm, and the first (smart) greenhouse was
equipped with a special system equipped with sensors that detect air temperature, soil humidity, the amount of
water in the tank, measure the percentage of minerals in the soil (NPK) and is connected to the internet via IoT
technology while allowing the monitoring of temperature, humidity, and the percentage of minerals in the soil
using an electronic application that was designed and linked to the Blynk platform. Three varieties of radishes:
Dutch, Syrian, and Italian; were grown in smart and traditional greenhouses on Tuesday, 28/11/2023, at three in
the afternoon, and on Friday, 1/12/2023, at ten in the evening. Whereas the germination level in the (smart)
greenhouse on Monday, 4/12/2023, at nine in the morning, the germination rate reached 98%, while in the
traditional (unattended) greenhouse, the first germination level appeared on Sunday, 4/12/2023, at three in the
afternoon, and on Monday at three o'clock in the afternoon, it did not exceed 50%, and it was noted that there
was a big difference between the two greenhouses.
The radish plants were harvested in the two greenhouses and the data for the plants was analyzed. The
symbol (S) was designated as the smart greenhouse, and the symbol (T) was designated as the traditional
greenhouse, and the results of the samples were as follows.
− Plant height rate: Table 3 shows the effect of the greenhouse and the varieties and the similarity between
the characteristics of the plant height rate. It is clear from it that the S greenhouse showed the highest
average plant height rate ratio of 63.536 mm, significantly superior to the T greenhouse, which gave the
lowest value of the plant height rate ratio of 54.553 mm.

Table 3. Plant height rate

A B C Average
S 55.743 75.640 59.223 63.536
T 53.557 68.177 41.927 54.553
Average 54.650 71.908 50.575

− Average leaf area of the plant: Table 4 shows the effect of the greenhouse, the varieties, and the similarity
between the average characteristics of the average leaf area of the plant. It is clear from this that the S
greenhouse showed the highest average plant leaf area ratio, 1243.03 mm, significantly superior to the T
greenhouse, which gave the lowest value for the average leaf area of the plant, 885.03 mm.

Table 4. Average percentage of leaf area per plant

A B C Average
S 1091.6 1480.2 1157.2 1243.03
T 757.8 1047.1 850.3 885.03
Average 924.70 1263.63 1003.76

Figure 10(a) shows the growth stage of the radish plant and germination level of the smart greenhouse.
On the fourth day of planting, the germination rate of radish plants reached 98%. Figure 10(b) shows the height
of the plant. Figure 10(c) shows the size of the leaf area of a plant in the smart greenhouse.

Data-driven farming: implementing internet of things for agricultural efficiency (Mohamed Ismail Lafta)
3596  ISSN: 2252-8938

(a) (b) (c)

Figure 10. Plant growth in smart greenhouse: (a) growth stage of plant, (b) the height of plant, and
(c) leaf area of a plant

Figure 11(a) shows the growth stage of the radish plant and the level of germination in the greenhouse
in it did not exceed 50%. Figure 11(b) shows the height of the plant. Figure 11(c) shows the size of the leaf
area of a plant in the traditional greenhouse.

(a) (b) (c)

Figure 11. Plant growth in the traditional greenhouse: (a) growth stage of plant, and (b) the height of plant,
and (c) leaf area of a plant

6. CONCLUSION
The use of the IoT in the agricultural system is necessary because there are basic requirements for
plant life that farmers do not know because they are not clear, such as the difficulty of monitoring soil moisture,
the amount of nutrients in the soil, temperature, and the amount of water in tanks. The study dealt with the
design and implementation of the smart system. The work was done in two parts, where the first part was the
design and implementation of the software part, which was the design and implementation of a website for the
proposed system and how to monitor the greenhouse in real time and then send a copy of the reading of each
sensor to Google Sheets. The second part is the design and implementation of the smart greenhouse, as the
proposed system can measure soil moisture, the amount of nutrients in the soil (NPK), the temperature of the
smart greenhouse, and the water level in its tank. In this research, the assistance of the agricultural expert
specializing in plants, Professor Dr. Harith Burhan Al-Din, was sought in terms of following the stages of plant
growth and knowing the plant’s differences. After implementing the system in the city of Samarra, it was found
that the use of the IoT in the agricultural system showed a promising and excellent result in terms of plant
growth in the first four days, and the germination rate reached 98%. In the smart greenhouse. While in
traditional greenhouses, it did not exceed 50%. As for plant height, there was a clear significant difference in
the average plant height. There was also a significant difference evident in average leaf area. So a smart
greenhouse is better than a traditional greenhouse. Our findings provide The proposed model can be
realistically applied in smart greenhouses, and for this reason, it can help reduce resource, reduce labor usage,
and increase productivity.

Int J Artif Intell, Vol. 13, No. 3, September 2024: 3588-3598

Int J Artif Intell ISSN: 2252-8938  3597

FUTURE WORKS
We faced some challenges in this research, such as plant-specific diseases, energy sources, and soil
salinity and acidity. In the future, we hope to add a camera to the proposed system to monitor plant diseases
and determine the type of disease using artificial intelligence algorithms. Adding a sensor to determine soil
acidity and basicity (PH). Adding alternative energy (solar energy) to reduce consumption power. To help
farmers reduce hand labor, and increase and improve resources and yield.

ACKNOWLEDGMENT
The author would like to thank Professor Dr. Harith Burhan Al-Din, Head of the Plant Protection
Department at the College of Agriculture, Tikrit University, for his help in following up on radish cultivation
and measuring the germination factor difference in smartgreenhouse and the traditional greenhouse.

REFERENCES
[1] J. Jung, M. Maeda, A. Chang, M. Bhandari, A. Ashapure, and J. L. -Bowles, “The potential of remote sensing and artificial
intelligence as tools to improve the resilience of agriculture production systems,” Current Opinion in Biotechnology, vol. 70, pp.
15–22, 2021, doi: 10.1016/j.copbio.2020.09.003.
[2] S. O. Araujo et al., “Intelligent data-driven decision support for agricultural systems-ID3SAS,” IEEE Access, vol. 11, pp. 115798–
115815, 2023, doi: 10.1109/ACCESS.2023.3324813.
[3] C. Brewster, I. Roussaki, N. Kalatzis, K. Doolin, and K. Ellis, “IoT in agriculture: designing a Europe-wide large-scale pilot,” IEEE
Communications Magazine, vol. 55, no. 9, pp. 26–33, 2017, doi: 10.1109/MCOM.2017.1600528.
[4] J. Wang, M. K. Lim, C. Wang, and M. L. Tseng, “The evolution of the internet of things (IoT) over the past 20 years,” Computers
and Industrial Engineering, vol. 155, p. 107174, 2021, doi: 10.1016/j.cie.2021.107174.
[5] M. S. Al-kahtani, F. Khan, and W. Taekeun, “Application of internet of things and sensors in healthcare,” Sensors, vol. 22, no. 15,
2022, doi: 10.3390/s22155738.
[6] S. N. Swamy and S. R. Kota, “An empirical study on system level aspects of internet of things (IoT),” IEEE Access, vol. 8, pp.
188082–188134, 2020, doi: 10.1109/ACCESS.2020.3029847.
[7] A. Gerodimos, L. Maglaras, M. A. Ferrag, N. Ayres, and I. Kantzavelou, “IoT: communication protocols and security threats,”
Internet of Things and Cyber-Physical Systems, vol. 3, pp. 1–13, 2023, doi: 10.1016/j.iotcps.2022.12.003.
[8] V. R. Bankar and K. N. Nandurkar, “Implementation of IoT technology for quality improvement in an automotive industry,”
Materials Today: Proceedings, Apr. 2023, doi: 10.1016/j.matpr.2023.03.485.
[9] N. Armando, J. S. Silva, and F. Boavida, “An approach to the unified management of heterogeneous IoT environments,” IEEE
Internet of Things Journal, vol. 8, no. 8, pp. 6916–6927, Apr. 2021, doi: 10.1109/JIOT.2020.3037141.
[10] P. S. Farahsari, A. Farahzadi, J. Rezazadeh, and A. Bagheri, “A survey on indoor positioning systems for IoT-based applications,”
IEEE Internet of Things Journal, vol. 9, no. 10, pp. 7680–7699, 2022, doi: 10.1109/JIOT.2022.3149048.
[11] Y. Li, S. Xie, Z. Wan, H. Lv, H. Song, and Z. Lv, “Graph-powered learning methods in the internet of things: a survey,” Machine
Learning with Applications, vol. 11, p. 100441, 2023, doi: 10.1016/j.mlwa.2022.100441.
[12] A. Vadapalli, S. Peravali, and V. R. Dadi, “Smart agriculture system using IoT technology,” International Journal of Advance
Research in Science and Engineering, vol. 9, no. 9, pp. 58–65, 2020.
[13] D. V. Gowda, S. M. Prabhu, M. Ramesha, J. M. Kudari, and A. Samal, “Smart agriculture and smart farming using IoT technology,”
Journal of Physics: Conference Series, vol. 2089, no. 1, Nov. 2021, doi: 10.1088/1742-6596/2089/1/012038.
[14] A. F. Subahi and K. E. Bouazza, “An intelligent IoT-based system design for controlling and monitoring greenhouse temperature,”
IEEE Access, vol. 8, pp. 125488–125500, 2020, doi: 10.1109/ACCESS.2020.3007955.
[15] Y. Song, J. Bi, and X. Wang, “Design and implementation of intelligent monitoring system for agricultural environment in IoT,”
Internet of Things (Netherlands), vol. 25, Apr. 2024, doi: 10.1016/j.iot.2023.101029.
[16] V. G. Sivakumar, V. V. Baskar, M. Vadivel, S. P. Vimal, and S. Murugan, “IoT and GIS integration for real-time monitoring of
soil health and nutrient status,” in International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2023 -
Proceedings, IEEE, pp. 1265–1270, 2023, doi: 10.1109/ICSSAS57918.2023.10331694.
[17] C. A. H. -Morales, J. M. L. -Rivera, and R. P. -Jimenez, “Design and deployment of a practical IoT-based monitoring system for
protected cultivations,” Computer Communications, vol. 186, pp. 51–64, 2022, doi: 10.1016/j.comcom.2022.01.009.
[18] T. M. Bandara, W. Mudiyanselage, and M. Raza, “Smart farm and monitoring system for measuring the environmental condition
using wireless sensor network - IoT technology in farming,” in CITISIA 2020 - IEEE Conference on Innovative Technologies in
Intelligent Systems and Industrial Applications, Proceedings, IEEE, Nov. 2020, doi: 10.1109/CITISIA50690.2020.9371830.
[19] P. Vandôme et al., “Making technological innovations accessible to agricultural water management: Design of a low-cost wireless
sensor network for drip irrigation monitoring in Tunisia,” Smart Agricultural Technology, vol. 4, 2023, doi:
10.1016/j.atech.2023.100227.
[20] B. Cheruvu, S. B. Latha, M. Nikhil, H. Mahajan, and K. Prashanth, “Smart farming system using NPK sensor,” in 2023 9th
International Conference on Advanced Computing and Communication Systems, ICACCS, IEEE, pp. 957–963, 2023, doi:
10.1109/ICACCS57279.2023.10112795.
[21] A. C. Bappa, M. Chowdhury, G. K. Dey, and M. R. Karim, “DIIGMCS—design and implementation of IoT-based greenhouse
monitoring and controlling system,” in Lecture Notes in Electrical Engineering, Springer Nature Singapore, pp. 629–639, 2023,
doi: 10.1007/978-981-19-8032-9_45.
[22] H. Benyezza, M. Bouhedda, R. Kara, and S. Rebouh, “Smart platform based on IoT and WSN for monitoring and control of a
greenhouse in the context of precision agriculture,” Internet of Things (Netherlands), vol. 23, 2023, doi: 10.1016/j.iot.2023.100830.
[23] A. Q. Mohabuth and D. Nem, “An IoT-based model for monitoring plant growth in greenhouses,” Journal of Information Systems
and Informatics, vol. 5, no. 2, pp. 536–549, 2023, doi: 10.51519/journalisi.v5i2.489.
[24] M. H. Ali and H. A. Hussein, “Design and implementation of smart greenhouse and experiment in strawberry cultivation,” in 2022
8th International Conference on Contemporary Information Technology and Mathematics, ICCITM, IEEE, 2022, pp. 30–33, doi:
10.1109/ICCITM56309.2022.10031689.

Data-driven farming: implementing internet of things for agricultural efficiency (Mohamed Ismail Lafta)
3598  ISSN: 2252-8938

[25] V. V. Kumar et al., “Design of peer-to-peer protocol with sensible and secure IoT communication for future internet architecture,”
Microprocessors and Microsystems, vol. 78, 2020, doi: 10.1016/j.micpro.2020.103216.
[26] M. S. T. Haque, K. A. Rouf, Z. A. Khan, A. Emran, and M. S. R. Zishan, “Design and implementation of an IoT based automated
agricultural monitoring and control system,” in 1st International Conference on Robotics, Electrical and Signal Processing
Techniques, ICREST 2019, IEEE, pp. 13–16, 2019, doi: 10.1109/ICREST.2019.8644212.
[27] R. Rayhana, G. Xiao, and Z. Liu, “Internet of things empowered smart greenhouse farming,” IEEE Journal of Radio Frequency
Identification, vol. 4, no. 3, pp. 195–211, Sep. 2020, doi: 10.1109/JRFID.2020.2984391.
[28] S. A. Hamoodi, A. N. Hamoodi, and G. M. Haydar, “Automated irrigation system based on soil moisture using arduino board,”
Bulletin of Electrical Engineering and Informatics, vol. 9, no. 3, pp. 870–876, 2020, doi: 10.11591/eei.v9i3.1736.
[29] E. A. Abioye et al., “A review on monitoring and advanced control strategies for precision irrigation,” Computers and Electronics
in Agriculture, vol. 173, 2020, doi: 10.1016/j.compag.2020.105441.
[30] K. Obaideen et al., “An overview of smart irrigation systems using IoT,” Energy Nexus, vol. 7, Sep. 2022, doi:
10.1016/j.nexus.2022.100124.
[31] M. R. M. Kassim, “IoT applications in smart agriculture: issues and challenges,” in 2020 IEEE Conference on Open Systems, ICOS
2020, IEEE, pp. 19–24, Nov. 2020, doi: 10.1109/ICOS50156.2020.9293672.
[32] B. B. Sinha and R. Dhanalakshmi, “Recent advancements and challenges of internet of things in smart agriculture: a survey,” Future
Generation Computer Systems, vol. 126, pp. 169–184, 2022, doi: 10.1016/j.future.2021.08.006.
[33] V. K. Quy et al., “IoT-enabled smart agriculture: architecture, applications, and challenges,” Applied Sciences (Switzerland), vol.
12, no. 7, 2022, doi: 10.3390/app12073396.
[34] Y. Tace, M. Tabaa, S. Elfilali, C. Leghris, H. Bensag, and E. Renault, “Smart irrigation system based on IoT and machine learning,”
Energy Reports, vol. 8, pp. 1025–1036, Nov. 2022, doi: 10.1016/j.egyr.2022.07.088.
[35] P. Rajak, A. Ganguly, S. Adhikary, and S. Bhattacharya, “Internet of things and smart sensors in agriculture: scopes and challenges,”
Journal of Agriculture and Food Research, vol. 14, 2023, doi: 10.1016/j.jafr.2023.100776.

BIOGRAPHIES OF AUTHORS

Mohamed Ismail Lafta received a bachelor's degree. He holds a computer

science degree from the Computer Science and Mathematics, Department of Computer
Science, and a master’s student in the College of Computer Science and Mathematics,
Department of Computer Science, Tikrit University. He can be contacted at email:
[email protected].

Wisam Dawood Abdullah received his B.Sc. degree in Computer Science from
Tikrit University, and his M.S. degree in Information Technology (with concentration in
Telecommunications and Networks) from the University Utara Malaysia (UUM). He
received an expert certification from Cisco Networking Academy CCNP, CCNA, CCNA
Security, IoT, Entrepreneurship, Grid, Voice, Wireless Cloud, Linux, CCNA Cyber Security
and IT, also he is a NetAcad administrator in Cisco Networking Academy, currently he is
lecturer in the Tikrit University, Cisco Networking Academy, member in IEEE. Research
interest: protocol engineering, network analysis, internet architecture and technologies,
wireless performances, network traffic engineering, data mining, future internet, internet of
things, AI, and ML. He can be contacted at email: [email protected].

Int J Artif Intell, Vol. 13, No. 3, September 2024: 3588-3598