Available via license: CC BY 4.0
Content may be subject to copyright.
Email addresses: yansen.tan@sd.taylors.edu.my (Y.S. Tan), seanzhuang.tan@sd.taylors.edu.my (S.Z. Tan),
liwei.chew@sd.taylors.edu.my (L.W. Chew) and yixuen.tan@sd.taylors.edu.my (Y.X. Tan)
IJEMD-CSAI, 3 (1) (2024), 1 –14 https://doi.org/10.54938/ijemdcsai.2024.03.1.270
International Journal of Emerging Multidisciplinaries:
Computer Science and Artificial Intelligence
Research Paper
Journal Homepage: www.ojs.ijemd.com
ISSN (print): 2791-0164 ISSN (online): 2957-5036
IoT-based Smart Farming System
Yan Sen Tan1*, Sean Zhuang Tan1, Li Wei Chew1, and Yi Xuen Tan1
1 School of Computer Science, Taylor’s University, Subang Jaya, Malaysia
*Corresponding author
Abstract
The integration of Internet of Things (IoT) technologies into agricultural operations, known as smart farming, presents a
transformative opportunity to revolutionize traditional farming methodologies and bolster productivity, efficiency, and
sustainability within the agricultural sector. This paper investigates the challenges inherent to conventional farming practices,
such as inefficient resource utilization and inadequate access to real-time data to inform decision-making. By leveraging an
array of IoT sensors and devices utilized for the purpose of gathering up-to-date information on various aspects such as
environmental factors and animal natural behaviours, agricultural producers can gain actionable insights, facilitating data-driven
decision-making to optimize resource usage and enhance crop yields. The primary objectives of this study encompass enabling
automation and precision agriculture to mitigate waste and bolster productivity, while concurrently emphasizing remote
monitoring and control capabilities through mobile technologies to augment overall operational efficiency and crop quality. The
background underscores the critical importance of integrating IoT technologies into agricultural practices to streamline farm
management processes, reduce labour requirements, and increase profitability across all scales of agricultural operations.
Through the implementation of IoT-enabled smart farming solutions, this paper endeavours to bridge the divide between
advanced technology and practical agricultural needs, offering a cost-effective and user-friendly approach to modernizing
farming methodologies.
Keywords: Agricultural Technology; Internet of Things; IoT; Smart Farming
1. Introduction
Traditional agricultural practices face numerous inefficiencies and challenges hindering optimal
productivity, such as inadequate monitoring of soil conditions resulting in suboptimal resource utilization
and potentially diminished crop yields, as well as a lack of up-to-date information of weather conditions
on agriculture productivity and plant being impeding informed decision-making processes and overall farm
productivity and sustainability [1].
2 International Journal of Emerging Multidisciplinaries
A primary objective of this paper is to elucidate the implementation of an array of Internet of Things (IoT)
sensors and devices to collect up-to-date information regarding essential agricultural environment factors
and animal natural behaviours empowering agricultural producers with actionable insights to facilitate
informed decision-making concerning irrigation scheduling, pest management, and crop health monitoring,
ultimately aiming to optimize resource utilization, mitigate waste, and augment overall agricultural
productivity [2].
The background of this paper examines the evolution of agricultural practices and the pivotal role of
technology in modernizing farming operations. Notably, advancements in Internet of Things (IoT)
technology have catalyzed the advent of precision agriculture techniques, enabling site-specific
management of inputs, thereby enhancing efficiency and sustainability [3]. This section underscores the
burgeoning demand for sustainable farming practices and the exigency for innovative solutions to address
the multifaceted challenges confronting farmers in today's dynamic agricultural landscape [4]. The
integration of IoT sensors and devices enables the acquisition of up-to-date information concerning
essential environmental factors and animal natural behaviours, empowering agricultural producers with
actionable insights [5].
Related Work
The deployment of IoT-based solutions in agriculture has recently emerged as a promising approach that
can improve productivity, efficiency, and sustainability in farming practices. There are various studies that
highlight the advantages of implementing IoT in agriculture for real-time monitoring, early disease
detection, precision irrigation management, and so on. In this section, three research articles are analyzed
based on the methodologies, challenges, and future directions of their proposed IoT smart farming system.
The research done by Gagliardi et al. studies the use of information and communication technology (ICT)
in agriculture. With the help of automation, image analysis, and artificial intelligence (AI), it allows farmers
to have real-time monitoring of their crops and precise automated treatments in their farms [1]. The
proposed smart farming design integrates various smart systems, including web-based applications, UAVs,
multi-spectral cameras, sensors, etc for achieving a precision farming system that allows farmers to have
better management of their crops. The features of the proposed system include the processing of video and
images, wireless data exchange, real-time data analysis, and data evaluation from the weather data [1]. The
proposed system offers several advantages, including enhanced crop yield and quality, decreased expenses,
optimized utilization of data inputs, and reduced environmental footprint.
Moreover, another research by Jadhav et al. tackles a significant problem arising in the agricultural
industry, which is the increase in food demand leading to difficulties in ensuring sustainability and resource
efficiency. They proposed an IoT-based smart farming system that utilizes IoT devices like sensors to
collect crop field data from the farm [6]. Data analytic techniques are used to analyse the data to help
farmers make informed decisions by sending notifications to the farmer’s phone to notify the farmer about
the condition of the farm. The integration of IoT in their proposed system allows for higher crop yield
while reducing the costs and environmental impacts [6].
Furthermore, for livestock monitoring, a study by J Aparna Priya et al. proposed an IoT-based livestock
monitoring system that allows farmers to have real-time monitoring of the livestock’s health status. This
Smart Farming 3
enables farmers to perform quick treatments on animals with abnormal health conditions to prevent the
spread of infectious diseases, track grazing animals to prevent loss, optimize breeding practices, and so on
[7]. The proposed system uses IoT sensors like body temperature sensor cable, heartbeat sensor, and
rumination sensor to track the health status of the livestock, a Raspberry Pi connects the sensors and
transmits the data to a cloud server to then be accessed from the mobile application. The benefits achieved
from the proposed system are the ease of diagnosing the health conditions of the livestock and allow for
immediate veterinary consulting for any abnormality detected to ensure early treatment to prevent the
worsening of the illness [7].
Methodology
In this section, the materials and methods used in designing and implementing the IoT smart farming
system are discussed in detail. This includes the hardware and software components, system architecture,
and prototype development.
System Design
Fig. 1 shows the block diagram of the proposed smart farming system. It depicts the hardware components
used to design the prototype and how they interact with each other to achieve the smart farming practice.
Fig. 1. Block diagram of smart farming system
• NodeMCU ESP8266: The NodeMCU is a type of microcontroller that has a built-in ESP8266 Wi-Fi
module. It can be programmed using the Arduino IDE using C/C++ programming language or Lua script
[8]. This microcontroller is suitable for handling the Wi-Fi connection between the IoT sensors and devices
before connecting to the Raspberry Pi.
• Raspberry Pi: The Raspberry Pi is a low-cost and small-sized computer that can be plugged into an
external monitor, keyboard, and mouse [7]. Programming languages such as Python, C++, and Java are
normally used to program it. One of its uses is to establish a connection to the NodeMCU to then send
signals to the control valves to execute the commands from the user or application since it can handle more
complex programs.
• IoT devices: The IoT devices used include a soil moisture sensor, soil pH sensor, humidity and
temperature sensor for the crop monitoring system; temperature sensor, heartbeat sensor, and GPS tracker
are used in livestock monitoring. Besides, the control valve is essential in regulating the irrigation process
by controlling the flow of water and fertilizers.
• Arduino IDE: The Arduino IDE is a software platform that allows Arduino boards to be programmed.
Although it is generally used for programming Arduino boards, it is also designed to work with other kinds
4 International Journal of Emerging Multidisciplinaries
of microcontrollers. In this project, it is mainly used for programming the NodeMCU ESP8266
microcontroller. The programming languages supported by the Arduino IDE include C/C++ languages and
also Lua script [9].
• ThingSpeak: ThingSpeak is an IoT analytics platform service that includes services like cloud-based
data visualization and analysis of live data. The ThingSpeak API collects incoming data, timestamps it, and
gives the output for users and machines [7]. ThingSpeak enables users to create applications for data
collection, data processing, and simple data visualizations utilizing the data collected from the sensors.
• Android Module/App: The proposed smart farming system consists of a mobile application for the
farmers to utilize as a centralized dashboard. The module is installed on the farmer’s smartphone as an
Android app and they can use it to access the precision irrigation feature, and monitor of crops and livestock
conditions by connecting to the Thing Speak Cloud. Equations
Communication architecture
Based on the listed hardware and software mentioned, in this section, the communication architecture will
be discussed to describe how to connect the hardware components and software together to work as one
smart farming system.
First and foremost, the NodeMCU ESP8266 microcontroller connects to the sensors to collect the crop
field and livestock data. The ESP8266 Wi-Fi module allows the microcontroller to connect to the sensors
via Wi-Fi connection, reducing the need for complex wiring as it is difficult to use wires for connecting in
a large area like a farm. Using the Arduino IDE, some basic coding is required to set up the Wi-Fi
connectivity, initialize the sensors, and handle the data collection and transmission. After the code is
written, it can be uploaded to the NodeMCU to then establish the connection of sensors to the NodeMCU.
Moving on, the NodeMCU microcontroller is connected to the Raspberry Pi. Since the Raspberry Pi can
handle more complex programs that are written in Python scripts, data analytics programs like disease
detection for crops and livestock can be written using the Thonny IDE and then uploaded into the Raspberry
Pi. The Raspberry Pi acts as the medium that receives the sensor data from the NodeMCU and sends
commands to the motors connected to the water valves or feeders to initiate the necessary functions.
Next, in order to transmit all this data to a cloud server, in this case, the ThingSpeak Cloud, the MQTT
(Message Query Telemetry Transport) is chosen as the main communication protocol to connect the
devices to the cloud server. This is because the smart farming system requires frequent data updates from
the sensors, with the publish/subscribe model of MQTT it allows for more efficient data transmitting due
to it reducing the need for constant polling. Moreover, MQTT is a lightweight protocol, making it more
suitable for implementing the smart farming system since most farms are located in areas with limited
bandwidth. In addition, MQTT’s scalability allows for efficient communication within systems that consist
of a large number of devices [10].
Lastly, using ThingSpeak to create simple visualizations of the sensor data, these visualizations can be
uploaded to the Android app in the farmer’s smartphone for them to monitor the real-time data of the crop
field and livestock. The programmed functions like precision irrigation, smart feeding, and so on can also
Smart Farming 5
be accessed from the Android app to send commands to the Raspberry Pi to then execute the commands
by sending the signals to the motors connected to the respective end devices.
Mobile applications prototype
In this section, the prototype of the smart farming mobile application is provided in the figures below with
descriptions. The mobile application acts as a centralized dashboard for the farmers to monitor the
conditions in their farm all at one stop at their fingertips. Fig. 2 displays the crop monitoring interface that
displays the overall crop field information.
Fig. 2. Crop monitoring interface
Based on Fig. 2, data such as the soil moisture level, pH level, weather, air humidity, and air temperature
are displayed on the top of the interface. At the bottom, it displays the scheduled irrigations set previously
for different areas in the farm. If the farmer wants to look into more detailed information of each crop field,
they can press the Precision Irrigation “View” button to navigate to the next page as shown in Fig. 3.
Fig. 3. Precision irrigation interface
6 International Journal of Emerging Multidisciplinaries
In this page, the farmer can monitor each crop field’s conditions separately. Moreover, it also displays what
the crop field is lacking in terms of nutrients and recommend a fertilizer for the farmer to use to address
the lack of a specific nutrient. Farmers can also select whether to turn on the automated irrigation settings.
Lastly, the livestock monitoring interface is shown in Fig. 4 It displays the livestock’s health status and
movement heatmap. The body mass line graph allows the farmer to manually enter the livestock’s mass
after they weighted it.
Fig. 4. Livestock monitoring interface
Circuit prototype
In this section, the prototype of the component circuit for certain functionality involved in the system will
be discussed and explained clearly with the sample circuit given.
Fig. 5. Sensing Component for moisture temperature and humidity
As shown in Fig. 5, the sensors will be connected to NodeMCU which is powered by a wire cable. Once
the environmental factors are captured by the sensors, they will be converted to an electrical signal and
transmitted to the NodeMCU through the wire, and from the NodeMCU, the signal will be converted to a
data package based on the configuration and transmitted to the Raspberry Pi, which is the centralized data
processing unit.
Smart Farming 7
To ensure the mobility and reliability of the sensing component, the component will be required to be
powered with a mobile power supply, for instance, batteries. Thereby, certain research has been made by
the team, and finally, a solution will be referred to in the Fig. 6.
Fig. 6. Power supply using solar panel and lithium battery [11]
As the figure shows, the solar panels were connected to a component TP4056 which is a charging module
for circuit protection to prevent the overvoltage of rechargeable lithium batteries and also reverse the
polarity connection. Meanwhile, the power regulator component, MCP1700 was implemented followed
with the ceramic capacitor and electrolytic capacitor to smoothen the voltage peak for the operation of the
NodeMCU in our sensing component.
Fig.7. livestock monitoring block diagram [12]
In Fig. 7 shows, ATMEL328 was implemented as the microcontroller for this component in the research
[12]. The data will be transmitted to the server using the GSM module, SIM800 in the figure. However,
the design is not applicable for our project, thereby, the component ATMEL328 and GSM module will be
replaced by NodeMCU, which is smaller and cheaper. The signal from the sensors and the GPS module
will be transformed into a data package and transmitted to the centralized data processing unit through the
network connection to reduce the implementation difficulty.
8 International Journal of Emerging Multidisciplinaries
Fig. 8 Solenoid Valve for precision irrigation
To achieve precision irrigation, a simple circuit connected to NodeMCU had been designed in Fig. 8 for
the scenario. In the figure, the circuit was powered by the batteries, however the farmers could also have
the power supply and lithium in Fig. 6 as the power supply for this circuit. In this circuit, a relay module
had been implemented to the circuit to control the circuit from on and off to prevent access water or
fertilizer usage.
Architecture Diagram
Fig. 9 Architecture Diagram
Fig. 9 above shows the architecture diagram designed for the system, including the physical component, to
demonstrate how are the sensing components connected to each other.
In this system, users can only access our application using their mobile devices, including tablets or
smartphones. To maximize our market competence power, our application will be compatible with both
IOs and Android platforms, furthermore, the IoT devices in the system will have a simple structure,
allowing the components to connect to each other easily and able to connect with other IoT devices which
is not developed by the company.
The mobile system will be developed using Flatter, which is an open-source mobile application
development platform. By using Flatter, the team could develop the application without any financial
concern during the development process, as all related documentation will be open-sourced and free to
access. Meanwhile, the software will involve Python language for data analytics and data visualization
purposes.
Smart Farming 9
The database of this system will be involved in cloud solutions to prevent any extra financial costs for
device maintenance and implementation. Meanwhile, the scalability and flexibility of our system could be
ensured to fit any business expansion or user onboard. The sensing component will be designed as
mentioned above, and they will be connected to each other using WiFi connection. The data will be
captured by the sensors in the sensing components, then transmitted in a data package to the centralized
data processing unit, which is Raspberry Pi. The Raspberry Pi will need to save the data to the on-cloud
server. Hence the system could visualize the data and show it to the users through the mobile applications.
Discussion
As the industry revolution began, the terms of Artificial intelligence, IoT devices, and smart system are
getting familiar among people. Since 2010, the trends of Google responses to the term “Internet of Thing”
or “IoT” are increasing gradually [13]. Besides, the related terms, such as “Smart Farming” or “Precision
Irrigation” had been increasing since 2015 [13].
The research done by A. Khanna and S. Kaur13, indicates the public has started to pay attention to the
implementation of IoT smart systems in agriculture activities. Meanwhile, the implementation of Machine
Learning has also proven to have a positive impact on agriculture activities through IoT devices and smart
systems. For instance, the implementation of K Nearest Neighbor (KNN) had achieved fully automated
irrigation [14]. According to the research, the irrigation will be decided by the algorithm fully after
analyzing the moisture and temperature data collected by the sensors placed in the field. The experiment
had been conducted and had a very positive impact on the agriculture yield in the experiment area.
Meanwhile, the research indicates the implementation of a decision-making system along with the IoT
devices could help to predict and detect the disease among the potato plants [15]. Despite the experiments
being done in an experiment field, however, this study possesses the potential to implement the technology
the large crop farms.
From the research made, it is clearly shown that the implementation of the IoT smart system into
agricultural activities will bring various positive impacts to farm yield. By increasing the farm yield, the
farmers could earn more income by selling the farm products as well. Meanwhile, the research done by
Y.Akkem et al16 indicates that the implementation of the artificial intelligence algorithm, for instance,
ARIMA, recurrent neural network (RNN) and KNN could help in predicting the farm yield using the
collected time-series data. Meanwhile, the algorithm could also perform the predictions in the soil fertility
classification and crop selection [16-22].
From all the case studies, the implementation of the smart system to agricultural activities could help in
this industrial revolution. Compared with the studies made, the products or technology invented had only
focused on either irrigation or livestock monitoring, unlike the technology mentioned in this study which
could cover all of them with a lower cost due to the unique architectural design [23-30].
10 International Journal of Emerging Multidisciplinaries
Due to the simplicity of the system, the users or farmers will not require any technical knowledge in the
implementation of the system, which creates product differentiation from other products. In this case, the
system will have greater competence power than the others, resulting in better preference for the users.
The limitation of the product will be the limited technology level and limited computation power possessed
in the data processing unit [31-39]. To reduce the costs of the implementation, the components selected
will need to achieve maximum computational power with limited expenses. Meanwhile, to ensure the
accuracy of the analysis given the system, various numbers of sensing components and centralized
processing units will need to be implemented in the field, which might be heavy costs for the farmers with
larger areas of the farm [40-46]. In this way, it will further increase the difficulty of implementation and
concerns in component maintenance due to the large number of sensing components implemented.
2. Conclusion and future work
In conclusion, the smart farming solution presented here is a significant advancement in agricultural
technology that gives farmers new tools to increase efficiency, sustainability, and productivity. Through
the integration of precision irrigation management, smart feeding, crop monitoring, and livestock health
monitoring, the system empowers farmers to use data to make well-informed decisions and streamline
essential procedures. Farmers can easily access real-time information and control features through the user-
friendly mobile interface, which enables them to manage their operations remotely and react quickly to
changing conditions. Smart feeding, automated fertilization, and automated pest control are examples of
automated procedures that minimize labor costs and increase yield.
However, there are still certain things that could be improved and optimized. To provide more precise
predictions of crop and livestock health, future research may concentrate on improving predictive
modelling capabilities through sophisticated AI and machine learning algorithms. Exploring the potential
of edge computing can significantly enhance the efficiency and responsiveness of smart farming systems
as well. Smart farming solutions that incorporate edge computing can improve scalability and resource
efficiency, particularly in places with limited connectivity or high-cost data transmission. This method
makes smart farming more resilient and economical by reducing reliance on centralized cloud infrastructure
while simultaneously increasing system performance. Furthermore, protecting sensitive farm data and
upholding regulatory compliance will require constant efforts to enhance data security and privacy
protocols. By cost-effectively integrating new technologies like blockchain, the agricultural supply chain's
traceability and transparency may be improved, boosting consumer confidence and farmers' access to
markets.
Smart Farming 11
3. References
[1] Gagliardi, G. et al., An Internet of Things Solution for Smart Agriculture, Agronomy, 11(11), 2140,
Oct, doi: https://doi.org/10.3390/agronomy11112140 (2021).
[2] Naresh, M. & Munaswamy, P. Smart Agriculture System using IoT Technology, International Journal
of Recent Technology and Engineering (IJRTE), 5, 2277–3878, Available:
https://ieeeprojectsmadurai.com/IEEE%202019%20IOT%20BASEPAPERS/5_IOT%20SMART%20AG
RICULTURE.pdf (2019).
[3] S. V, Internet-of-Things (IoT) based Smart Agriculture in India - An Overview, Journal of ISMAC,
3(1), 1–15, Feb, doi: https://doi.org/10.36548/jismac.2021.1.001 (2021).
[4] Quy, V.K. et al., IoT-Enabled Smart Agriculture: Architecture, Applications, and Challenges, Applied
Sciences, 12(7), 3396, Mar, doi: https://doi.org/10.3390/app12073396 (2022).
[5] Dankan Gowda, V., Sandeep Prabhu, M., Ramesha, M., Kudari, J. M. & Samal, A. Smart Agriculture
and Smart Farming using IoT Technology, Journal of Physics: Conference Series, 2089(1), 012038, Nov,
doi: https://doi.org/10.1088/1742-6596/2089/1/012038 (2021).
[6] Jadhav, N., Rajnivas B., Subapriya V., Sivaramakrishnan S., & Premalatha, S. Enhancing Crop Growth
Efficiency through IoT-enabled Smart Farming System, EAI endorsed transactions on internet of things,
10, Dec, doi: https://doi.org/10.4108/eetiot.4604 (2023).
[7] Aparna Priya, J., Hemalatha, B., Amrita, S. & Kusumasree, IoT Based Animal Health Monitoring
System using Raspberry Pi, International Journal of Advanced Research in Science, Communication and
Technology, 3(7), 300–307, Apr, doi: https://doi.org/10.48175/ijarsct-9509 (2023).
[8] Kumar, G.V. & Jashuva, P. SMART FARMING MANAGEMENT SYSTEM USING
IOT, International Journal of Research in Science and Technology, 11(1), Jan, doi:
https://doi.org/10.37648/ijrst.v11i01.002 (2021).
[9] Neha, P. & Vaishali, K. IoT based smart farming system, International Journal of Advance Research,
7(1), Accessed: Mar. 05, 2024. [Online]. Available: https://www.ijariit.com/manuscripts/v7i1/V7I1-
1280.pdf (2021).
[10] Sinha,M., Rahul, M. & Singh, M. Smart Agriculture using Internet of Things and Based MQTT
Protocol, International Journal of Creative Research Thoughts (IJCRT), 9(5), 2320–2882, Accessed: Mar.
05, 2024. [Online]. Available: https://ijcrt.org/papers/IJCRT2105570.pdf (2021).
[11] Random Nerd Tutorial, Power ESP32/ESP8266 with Solar Panels and Battery | Random Nerd
Tutorials, Random Nerd Tutorial, May 02, https://randomnerdtutorials.com/power-esp32-esp8266-solar-
panels-battery-level-monitoring/ (2019).
[12] Dutta, D., Natta, D., Mandal, S. & Ghosh, N. MOOnitor: An IoT based multi-sensory intelligent device
for cattle activity monitoring, Sensors and Actuators A: Physical, 333, 113271, Jan, doi:
https://doi.org/10.1016/j.sna.2021.113271 (2022).
[13] Khanna, A. & Kaur, S. Evolution of Internet of Things (IoT) and its significant impact in the field of
Precision Agriculture, Computers and Electronics in Agriculture, 157, 218–231, Feb, doi:
https://doi.org/10.1016/j.compag.2018.12.039 (2019).
12 International Journal of Emerging Multidisciplinaries
[14] Terence, S. & Purushothaman, G. Systematic review of Internet of Things in smart
farming, Transactions on Emerging Telecommunications Technologies, 31(6), Apr, doi:
https://doi.org/10.1002/ett.3958 (2020).
[15] Foughali, K., Fathallah, K. & Frihida, A. Using Cloud IOT for disease prevention in precision
agriculture, Procedia Computer Science, 130, 575–582, doi: https://doi.org/10.1016/j.procs.2018.04.106
(2018).
[16] Akkem, Y., Biswas, S.K. & Varanasi, A. Smart farming using artificial intelligence: A
review, Engineering Applications of Artificial Intelligence, 120, 105899, Apr, doi:
https://doi.org/10.1016/j.engappai.2023.105899 (2023).
[17] Humayun, M., Ashfaq, F., Jhanjhi, N. Z. & Alsadun, M. K. Traffic management: Multi-scale vehicle
detection in varying weather conditions using yolov4 and spatial pyramid pooling
network. Electronics, 11(17), 2748 (2022).
[18] Taj, I. & Zaman, N. Towards industrial revolution 5.0 and explainable artificial intelligence:
Challenges and opportunities. International Journal of Computing and Digital Systems, 12(1), 295-320
(2022).
[19] Jhanjhi, N. Z., Brohi, S. N., Malik, N. A. & Humayun, M. Proposing a hybrid rpl protocol for rank
and wormhole attack mitigation using machine learning. In 2020 2nd International Conference on
Computer and Information Sciences (ICCIS). IEEE, 1-6 (2020).
[20] Brohi, S. N., Jhanjhi, N. Z., Brohi, N. N. & Brohi, M. N. Key applications of state-of-the-art
technologies to mitigate and eliminate COVID-19. Authorea Preprints (2023).
[21] Gopi, R. et al. Enhanced method of ANN based model for detection of DDoS attacks on multimedia
internet of things. Multimedia Tools and Applications, 1-19 (2022).
[22] Lim, M., Abdullah, A., Jhanjhi, N. Z., Khan, M. K. & Supramaniam, M. Link prediction in time-
evolving criminal network with deep reinforcement learning technique. IEEE Access, 7, 184797-184807
(2019).
[23] Muzafar, S. & Jhanjhi, N. Z. Success stories of ICT implementation in Saudi Arabia. In Employing
Recent Technologies for Improved Digital Governance, 151-163. IGI Global (2020).
[24] Gouda, W., Almurafeh, M., Humayun, M. & Jhanjhi, N. Z. (February). Detection of COVID-19 based
on chest X-rays using deep learning. In Healthcare, 10(2), 343. MDPI (2022).
[25] Humayun, M., Sujatha, R., Almuayqil, S. N. & Jhanjhi, N. Z. (June). A transfer learning approach
with a convolutional neural network for the classification of lung carcinoma. In Healthcare, 10(6), 1058.
MDPI (2022).
[26] Alkinani, M. H., Almazroi, A. A., Jhanjhi, N. Z. & Khan, N. A. 5G and IoT based reporting and
accident detection (RAD) system to deliver first aid box using unmanned aerial vehicle. Sensors, 21(20),
6905 (2021).
[27] Babbar, H. et al. Load balancing algorithm for migrating switches in software-defined vehicular
networks. Comput. Mater. Contin, 67(1), 1301-1316 (2021).
[28] Jhanjhi, N. Z., Humayun, M. & Almuayqil, S. N. Cyber security and privacy issues in industrial
internet of things. Computer Systems Science & Engineering, 37(3) (2021).
[29] Aldughayfiq, B., Ashfaq, F., Jhanjhi, N. Z. & Humayun, M. A deep learning approach for atrial
fibrillation classification using multi-feature time series data from ecg and ppg. Diagnostics, 13(14), 2442
(2023).
Smart Farming 13
[30] Prabakar, D. et al. Energy Analysis-Based Cyber Attack Detection by IoT with Artificial Intelligence
in a Sustainable Smart City. Sustainability, 15(7), 6031 (2023).
[31] Zerdoumi, S., Hashem, I. A. T. & Jhanjhi, N. Z. A new spatial spherical pattern model into interactive
cartography pattern: multi-dimensional data via geostrategic cluster. Multimedia tools and
applications, 81(16), 22903-22952 (2022).
[32] vSimon, C. G. K., Jhanjhi, N. Z., Goh, W. W. & Sukumaran, S. Applications of machine learning in
knowledge management system: a comprehensive review. Journal of Information & Knowledge
Management, 21(2), 2250017 (2022).
[33] Dash, S. & Verma, S. Kavita; Jhanjhi, NZ; Masud, M. Baz, M. Curvelet Transform Based on Edge
Preserving Filter for Retinal Blood Vessel Segmentation. Comput. Mater. Contin, 71, 2459-2476 (2022).
[34] Acharjya, Prasanna, D., Mitra, A. & Jhanjhi, N.Z. Deep learning in data analytics. Springer
International Publishing, 2022.
[35] Muhammad, Ibrahim, Humayun Mamoona, N. Z. Jhanjhi, and M. N. Talib. "Intelligent Computing
and Innovation on Data Science." (2021): 425-434.
[36] Khan, N. A., Jhanjhi, N. Z., Brohi, S. N. & Almusaylim, Z. A. Proposing an algorithm for UAVs
interoperability: MAVLink to STANAG 4586 for securing communication. In Intelligent Computing and
Innovation on Data Science: Proceedings of ICTIDS 2021, 413-423. Springer Singapore (2021).
[37] Ponnusamy, V., Rafique, K. & Zaman, N. (Eds.). Employing recent technologies for improved digital
governance. IGI Global (2019).
[38] Zaman, N., Abdullah, A. B. & Jung, L. T. (March). Optimization of energy usage in wireless sensor
network using Position Responsive Routing Protocol (PRRP). In 2011 IEEE Symposium on Computers &
Informatics, 51-55. IEEE (2011).
[39] Adhikari, S. et al. A Novel Machine Learning-Based Hand Gesture Recognition Using HCI on IoT
Assisted Cloud Platform. Computer Systems Science & Engineering, 46(2) (2023).
[40] Ashfaq, F., Ghoniem, R. M., Jhanjhi, N. Z., Khan, N. A. & Algarni, A. D. Using Dual Attention
BiLSTM to Predict Vehicle Lane Changing Maneuvers on Highway Dataset. Systems, 11(4), 196 (2023).
[41] Chouhan, K., Yadav, M., Rout, R. K., Sahoo, K. S., Jhanjhi, N. Z., Masud, M., & Aljahdali, S.
Sentiment Analysis with Tweets Behaviour in Twitter Streaming API. Comput. Syst. Sci. Eng., 45(2),
1113-1128 (2023).
[42] Zahra, F. et al. Protocol-specific and sensor network-inherited attack detection in IoT using machine
learning. Applied Sciences, 12(22), 11598 (2022).
[43] Sujatha, R., Prakash, G. & Jhanjhi, N.Z. Cyber Security Applications for Industry 4.0, Chapman and
Hall/CRC Cyber-Physical Systems Series, CRC Press, 2022.
[44] Alex, S. A., S., P., T. R., A., Jhanjhi, N. Z. & Tayyab, M. Machine Learning-Based Wearable Devices
for Smart Healthcare Application With Risk Factor Monitoring. In M. Ahmad & N. Zaman
(Eds.), Empowering Sustainable Industrial 4.0 Systems With Machine Intelligence, 174-185. IGI Global.
https://doi.org/10.4018/978-1-7998-9201-4.ch009 (2022).
[45] Majid et al. Ontology-Based System for Educational Program Counseling. Intelligent Automation &
Soft Computing 30(1) (2021).
14 International Journal of Emerging Multidisciplinaries
[46] Anandan, R., Deepak, B. S., Suseendran, G. & Jhanjhi, N. Z. Internet of Things Platform for Smart
Farming. Human Communication Technology: Internet of Robotic Things and Ubiquitous Computing, 337-
369 (2021).
