See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/373216860

Cloud Computing-Based Smart Agriculture

Chapter · August 2023

DOI: 10.4018/979-8-3693-0200-2.ch006

CITATIONS READS

0 591

1 author:

Kaushal Kishor
ABES Institute of Technology
43 PUBLICATIONS 250 CITATIONS

SEE PROFILE

All content following this page was uploaded by Kaushal Kishor on 21 August 2023.

The user has requested enhancement of the downloaded file.

 Cloud Computing-Based Smart Agriculture
Kaushal Kishor[0000-0002-7131-1389]
ABES Institute of Technology, Ghaziabad, U.P., India, [email protected]

Raj Kishor Verma

ABES Institute of Technology, Ghaziabad, Uttar Pradesh, India, [email protected]

Agriculture is an important source of income in the world's most populous countries. In

countries like India, China, and others, it is a major source of wealth and livelihood. Cloud
computing and the Internet of Things for agriculture will improve production cost management,
performance tracking and maintenance, benefiting both farmers and the country as a whole. The
focus of this article is on the use of smart drones, and instant data from drones for crop
management and computing technologies will help get started. Despite the use of precision
gardening in other countries, Indian agriculture needs to be modernised through the use of
technology to increase productivity, wealth distribution, and cost management. In this article, we
propose a comprehensive smart agriculture paradigm based on the following technological
advances: Sensors, Internet of Things (IoT), Cloud Computing, Mobile Computing, and Big
Data Analytics

Keywords- Cloud Computing, Internet of Things (IoT), Smart Agriculture, Smart Drone, Big-
Data Analysis, Mobile Computing.

Introduction

The agriculturalist's choice on what kind of crop to grow is frequently eclipsed by the
thoughts he has on other minor factors such as generating rapid profits, a lack of knowledge
regarding market demand, an excess of the earth's ability to sustain a specific crop, and so on. A
poor judgement by the farmer might have serious consequences for the entire family's financial
well-being. Apparently, this is one of the many factors leading to the many incidents of suicide
among farmers reported in newspapers daily. In a nation like India, farming and associated
industries account for around 20.4 percent of Gross Value Added (GVA). Such a mistaken
judgement could have a detrimental impact not just on the farmer's family, but additionally on
the entire area economy. As a result, we have discovered the agriculturalist's dilemma of
determining which crop to cultivate at what time of year. The necessity of the hour is to create a
system that can offer Indian farmers with predictable facts, allowing people to make educated
choices about what kind of crop to plant.

https://doi.org/10.4018/979-8-3693-0200-2.ch006 120
 With this issue in mind, we're suggesting an approach, an innovative one that pre-
calculates environmental variables (temperature, precipitation, where you are as a matter of
circumstance) and soil characteristics (pH value, soil type, and nutrients density) and
recommend the best produce for the consumer.
Agricultural techniques and practices play a major role in connecting devices, collecting
and distributing data amid expectations for the introduction of the Internet and cloud computing
increasing speed, thereby offering farmers a new approach, farm health inspection. In recent
years, interest in various fields has increased; Robotics is where we entered the field of
technology that supports farm health. It is monitored and data is recorded, but it is not effective
(Bac et al., 2014). Drone use starts here in agriculture; smart farming can offer a lot. Precision
farming is a form of smart agriculture where farmers use data analytics and IoT devices to
monitor soil moisture, nutrient levels, and other environmental conditions to optimize crop
development. Drones, which may be used for agricultural monitoring and spraying, and
autonomous tractors, which can be programmed to plough fields and sow seeds (Burkle 2009),
are examples of other technologies.

Challenges

There are a number of obstacles that must be overcome in order for smart agriculture to
reach its full potential, despite the fact that it has the potential to greatly benefit farmers and the
food chain. Some of the main obstacles to smart agriculture are listed below:
Cost: It may be expensive to put many of the technologies used in smart agriculture,
including sensors, drones, and autonomous tractors, into use. For small-scale farmers with little
resources, this may be a deterrent to adoption.
Infrastructure: Smart agriculture needs a solid and dependable digital infrastructure, which
may not be present in all rural locations. This includes high-speed internet connectivity. This
could make it more difficult for farmers to embrace and use these technologies.
Data management: In order to be effective, smart agriculture generates a lot of data that
must be organised and analysed. For farmers who might lack the knowledge or resources to
handle and interpret this data efficiently, this can be difficult.
Privacy and security: Data on crop yields, soil quality, and weather patterns are among the
sensitive information that is gathered and shared in the context of smart agriculture. It is crucial
to make sure that this information is secure and that farmers have a choice over how it is put to
use.
Education and training: In order to engage in smart agriculture, farmers must possess a
certain degree of technical skill, including an understanding of digital technology and data
analytics. To assist farmers in acquiring these abilities, it is crucial to offer training and
educational programs.
Regulatory obstacles: Using some smart agriculture technology, including drones and
autonomous vehicles, may present regulatory obstacles since they may be required to get
specific permits or licenses.
Collaboration amongst industries such as agriculture, technology, policy, and finance will
be necessary to address these difficulties, governments, academic institutions, and the
https://doi.org/10.4018/979-8-3693-0200-2.ch006 121
commercial sector may all play a part in fostering the growth and acceptance of smart
agricultural technologies while also making sure that they are available to and reasonably priced
for farmers of all sizes and in all areas.

Smart Agriculture Application

In order to maximise agricultural productivity and raise yields, smart agriculture makes use
of cutting-edge technologies including sensors, drones, and big data analytics. The following are
a few uses of smart agriculture:
Precision farming: Using sensors, GPS, and other technologies, precision farming keeps an
eye on the weather, crop development, and soil conditions in real-time. This enables farmers to
use resources like fertiliser, water, and other resources as efficiently as possible, thereby
increasing yields and lowering expenses.
Smart irrigation systems employ sensors and meteorological information to automatically
change watering schedules and volumes in response to plant requirements and environmental
factors. This minimises water wastage and guarantees that plants get the appropriate amount of
water at the appropriate time.
Animal health, behaviour, and production may all be tracked using sensors in livestock
management, a branch of smart agriculture. Farmers may be able to better monitor animal
welfare overall, reduce feed and water usage, and identify health issues early.
Management of pests and diseases: Pest and disease management is a function of smart
agriculture. Early indicators of infestation may be found using sensors and drones, and
epidemics can be predicted and trends found using big data analytics. This might increase
agricultural yields and lessen the demand for dangerous chemicals.
Supply chain management: From production to distribution, smart agriculture may assist
optimising the whole supply chain. Big data analytics enables farmers and distributors to
streamline operations and cut waste by tracking inventory levels, keeping track of shipment
schedules, and forecasting demand.
Smart agriculture has the ability to completely transform the agriculture sector, making it
more effective, sustainable, and lucrative.

Mobile Application Module

Applications for smartphones have to be downloaded and set up on the end user's phone. It
is divided into three sections. a. UI for farmers; b. UI for agro marketing agencies; and c. UI for
agro suppliers such as fertilisers, insecticides, and seed suppliers. At first, the end user must
register for the mobile app using a few credentials such as identification information, account
type, address, place of residence, and other pertinent information. If the end user is a farmer, he
or she must supply a few credentials containing information related to agriculture such as
approximate location and total acreage for each field. SensorKit is used to collect soil
information for each farm. SensorKit receives the necessary instructions from Mobile
Applications. The data will be delivered to be preserved on AgroCloud Big-Data repository.
When planting of crops is underway, SensorKit captures and sends soil data to cloud storage.
https://doi.org/10.4018/979-8-3693-0200-2.ch006 122
Farmers may use these apps to acquire fertiliser recommendations and dosages for improved
crop yields and cost savings. This app is also used to deliver alerts to users. When the crop has
been harvested, the farmer will send the complete production data for each crop to the cloud
storage, together with the present soil parameters following the growth of that commodity. The
aforementioned data, together with the date and time stamp, is saved in the cloud. Agro
marketing companies in charge of acquiring harvested products from farmers must deliver
quarterly information on price fluctuations and purchase needs. Fertilisers, seeds, insecticides,
and agricultural equipment are sold by agro product dealers. Agro providers must send goods
and price modification notifications on a regular basis. The mobile Application Module is shown
in Figure 1

Figure 1 Mobile Application Module

A drone is defined as an unmanned aerial vehicle (UAV) (Borenstein & Miller, 2013). The
use of drones offers possibilities, use farm time instead of going for a walk; IoT and cloud
computing technologies can help in one solution. Smart drone paired with Complementary
Technologies, IoT, and Cloud computing data captured by smart agriculture (Gupta et al., 2022).
The term "smart agriculture" refers to the employment of cutting-edge technology and data
analytics in agricultural practices to maximize crop output, minimize waste, and increase
efficiency. It entails integrating sensors, Internet of Things (IoT) devices, and other digital
technologies into farming operations so that farmers can make data-driven choices about their
crops and the environment (Kishor & Pandey, 2022).
Increased crop yields, fewer environmental effects, and higher farmer profitability are all
advantages of smart agriculture.
In order to enhance agriculturally practices and crop management, a variety of technologies and
digital solutions are referred to as "smart agriculture tools." Here are some instances of clever
farming tools:

https://doi.org/10.4018/979-8-3693-0200-2.ch006 123
 Sensors: Information on the state of the environment and the development of plants may
be gathered using soil sensors, weather sensors, and plant sensors. This information may be
utilised to improve crop management procedures such as fertiliser and irrigation applications.
Drones: Drones with cameras and sensors may be used to monitor crops, spot diseased or
stressed regions, and deliver detailed pictures of agriculture.
Autonomous tractors: These machines may be programmed to clear land, sow seeds, and
use herbicides and fertilisers. These devices can work without the need for a human operator,
which lowers labour costs and boosts productivity.
Smart irrigation systems: These systems make the best use of available water resources,
cut down on waste, and increase agricultural yields.
Crop planning, inventory control, and financial analysis are just a few of the tools that
farm management software gives farmers to run their businesses.
Livestock monitoring systems: These systems track the behaviour and health of livestock
using sensors and data analytics, giving farmers the ability to improve management techniques
including breeding and feeding.
Systems for precision agriculture: These systems provide farmers access to real-time data
on crop development so they may make informed decisions regarding pest control, fertilisation,
and irrigation. Precision agriculture systems employ data analytics and machine learning to do
this.
The IOT concept, phrase "Internet of Things" (IoT), which has gained popularity,
recently, describes a system in which the whole world is connected to the Internet through
various types of sensors. It opens up possibilities for closer integration of the physical world
with computer-based systems and reduces human intervention while improving efficiency,
accuracy, and economic benefit (Mattern & Floerkemeier, 2010). It also enables objects to be
sensed or controlled remotely across the existing network infrastructure. All household
appliances, furniture, clothing, automobiles, roadways, and smart materials, among other IOT
things, are readable, recognized, locatable, addressable, and/or controlled through the Internet.
Through combining technological advancements in pervasive communications, ambient
intelligence, and pervasive objects in a sensory and intelligent way, it combinations of
ubiquitous communications, identification technologies, sensors, and wireless, networks,
embedded systems and nanotechnology (Swathi & Guruprasad, 2014).
Cloud Computing Concept Today's term in the information technology (IT) industry,
"cloud computing," refers to a computing paradigm that gives large groups of privately, publicly,
or hybrid networked devices on-demand access to either application data or storage space
(Kishor et al., 20230. It provides a brand-new internet-based method for adding, using, and
exchanging IT services that include making available dynamic, scalable, and virtualized
resources, The core notion behind the innovative concept of cloud computing is the reusability
of IT skills, a crucial component for cost-effectiveness (Kishor & Nand, 2023). By giving a
realistic method to experience immediate cost advantages in computing, application hosting,
content distribution, and other areas, it broadens perspectives beyond organizational boundaries
(Pingli et al., 2011).
Data analytics concepts employing data analytics to practice intelligent agriculture, The
Third Green Revolution, or "smart farming," is a breakthrough in the agriculture industry
https://doi.org/10.4018/979-8-3693-0200-2.ch006 124
brought about using cutting-edge technologies. It is anticipated that this will eventually close the
technological gap between the agricultural industry, which has historically relied on more
conventional farming techniques, and most cutting-edge technological advancements. Data is
being used by farmers to estimate crop yields, the need for fertilizer, cost reductions, and even
the best optimization techniques for upcoming crops. To construct algorithms that can be used
by different farms to produce a crop yield that is profitable and sustainable, smart farming
employs data analytics tools to collect information from various agricultural practices. Farmers
will be better equipped to forecast activities in the field with this information.
These are only a few instances of clever farming implements. We can anticipate even more
creative ideas that will help farmers enhance their operations and boost output as technology
continues to evolve.

Literature Review

(Giusti & Marsili-Libelli, 2015), Utilizing research papers, journals, and articles, we
reviewed the literature on smart agriculture. According to one research, if crop and site
parameters are known, a fuzzy control system may be used to conserve water and manage
irrigation in agricultural fields. It explains a procedure for putting an irrigation system that is
completely automated into use. Another investigation (Keerthi & Kodandaramaiah, 2015)
provided a greenhouse tracking system built around an agriculture IoT with a cloud in which
devices are put on the farm's premises to collect and store data on the agricultural area on a
regular basis. Further research (Liqiang et al., 2011; Zhu et al., 2011; Jaishetty & Patil, 2016)
suggested an agricultural utilisation of wireless sensors for crop field surveillance, with these
networks outfitted with two types of nodes that sense, one that monitors various variables such
as temperature, humidity, and so on, and the other, a picture detecting node to take photographs
of the agricultural products. Irrigation in agricultural land is the main topic of the majority of
studies. One such work (Kishor, 2023) emphasized the necessity of precisely calculating the
water needs of plants as well as the Neural Computing modelling of reference crop
evapotranspiration. In a different work (Kishor, 2023; Adeloye et al., 2012), an automatic smart
irrigation decision support system (SIDSS) was presented to control irrigation in agriculture.
Internet of Things-based smart irrigation systems (Kishor, 2022; Kishor et al., 2018; Kumbar et
al., 2016). Where sensed, data is transmitted to a smart gateway over a network and
subsequently to a web service. A method for monitoring pest insect traps utilizing image sensors
and Aspic was also proposed by the GSM (Global Method for Mobile Communications). They
employed wireless sensor networks to control dispersed imaging equipment (Hemalatha &
Deepika, 2016; Kishor et al., 2022). This approach just identifies pests; it makes no
recommendations about how to get rid of them.
A few publications on smart agriculture claim that several nations are now adopting
precision agriculture. Precision agriculture is a type of satellite farming or Site-Specific Crop
Management (SSCM) that relies on monitoring crop variability both within and between fields
(Venkataramana & Padmavathamma, 2012). A methodology for using cloud computing has
been created by Fujitsu in Japan. In the majority of publications, the findings of exploratory

https://doi.org/10.4018/979-8-3693-0200-2.ch006 125
investigations are reported, or IoT systems that have been developed or tested in prototypes and
pilots are presented. While actuation and remote control are significantly less discussed in the
literature study and more sophisticated solutions are still in the experimental stage of
development, the literature review concentrates on sensing and monitoring. This article covers a
new method for using smart drones to remotely regulate and monitor a crop field's essential
agricultural land characteristics, assisting in data analysis and field prediction (Kishor, 2022;
Rupanagudi et al., 2015).
This research developed an approach dubbed the Crop Rotation Choice Method (CSM) for
addressing the crop decision issue and raises the rate of crop residue throughout the season that
afterwards approaches the world economy's greatest growth. The suggested approach has the
potential to demonstrate the residual value of agricultural yield (Kumar et al., 2015; Jain et al.,
2021).
This research created and deployed an inventive crop suggestion system that farmers across
India may simply use. This programme will assist farmers in making an informed selection
about which crop to cultivate based on numerous natural and environmental factors. We also
utilised a supplementary technique called the Rainfall Predictor to forecast the following 12
months of rainfall (Doshi et al., 2018, Jain et al., 2020).
Lee &Moon, 2014, this paper discusses the study and establishment of a proactive
agriculture yield strategy based on immediate time quarterly weather forecasts. Agriculture
production is difficult to forecast due to unpredictable meteorological circumstances throughout
the year and significant alterations in the climate in the area as a result of global warming. The
establishment of an agricultural crop forecasting system that incorporates real-time
meteorological data is critical. We present a method for analysing weather forecast data
(monthly, daily) as well as ways to change the guessing system in this study. On the basis of 33
years of agricultural climatic data in the composition, we develop a non-parametric numerical
model. We used monthly meteorological data to anticipate the ultimate production using the
model (Sharma et al., 2022). The present article offers simulation findings.
Paul et al., 2015, the aforementioned feature offers a programme that predicts the next
stage of the analysed soil database using data mining methods. Crop harvesting will be featured
in the category as expected. The yield prediction issue is formalised as the rule of separation,
which employs the Naive Bayes and K-Nearest Neighbour approaches.
(Pudumalar et al., 2017), This work proposes an option selection procedure that employs a
combination model with many voting techniques such as random tree, CHAID, K-Nearest
Neighbour, and Nave Bayes as students choose the plant of specific site boundaries with the
greatest degree of precision as well as effectiveness.

The Project Narrative

Because they can fly without an onboard pilot and serve as an aerial surveillance system,
drones have been used for a variety of business purposes. However, the usage of these drones is
only allowed in those areas and they have restricted capabilities. We mix it with intelligent
technology to enhance their capabilities and utilize the massive amounts of data generated by
drones. The suggested concept, which involves IoT and cloud computing in drones, aims to give
https://doi.org/10.4018/979-8-3693-0200-2.ch006 126
farmers intelligent agriculture control. A more recent phrase, smart drones, implies that the
UAVs' sensors flow into a network architecture where they are connected to other devices via
Internet technology, enabling communication and giving the gadgets a more sophisticated
appearance. Now, since they have real-time characteristics, gadgets are multidimensional.
The Smart Drone Architecture - Sky Drone FPV2 (First People View) technology for
drones is used in the design, which includes a camera component, a data component, and a
4G/LTE modem. The intelligent drone would function as a fixed-wing airborne aircraft capable
of carrying several sensors, reaching faster speeds, having longer bursting durations, and
covering vast areas (Kishor et al., 2017 ; Kishor et al., 2018 ). It has a robust information and
communication technology (ICT) system for processing information from sensor devices and
embedded applications for flight management and scheduling based on GPS (Global Positioning
System) tracking and Google Maps. As a consequence, the outcomes of processing will be made
available to authorised individuals as soon as the flight is available. The proposed model is
divided into three pieces. Sensory perception, dialogue, and synchronisation
Sensing: Synchronous sensors, including flying and navigation sensors as well as camera
sensors, are fitted in Smart Drones for the unique gathering of user-useful data. The drone's
status and flight parameters control the flight and navigation sensors, such as the vision sensor,
gyroscope, tilt, and current sensors, and GPS. The sensors also assist with navigation and keep
an eye on the drone's immediate and wider environment to spot and avoid unexpected obstacles
(Kishor et al., 2018). As they provide the fundamental functional load of drones used for
monitoring in agricultural applications, the camera used in the Smart Drone should have at least
a 12-megapixel resolution and varied frequency range.
 Recognize pests, weeds, and illnesses to optimize the application of pesticides and crop
sprays.
 Calculate crop yield, i.e., offer plant counts.
 By identifying nutrient inadequacies, we provide information on soil fertility.
 By locating probable water stress locations, you can measure irrigation and manage your
crop. Although thermal imaging equipment are used during nighttime vision, seeing
through smoke or fog, vegetation tracking, heat and fire identification using infrared
trends, and so on, ocular cameras are utilised for gathering images during the day.

Communication: The connection and interaction block is in the driver's seat for
transferring data and must be resistant to external variables as well as quick to adapt to
alterations in the network architecture. The Smart Drone will be equipped with a practically
isotropic in nature radiation sequence antenna and a 4G/LTE internet connection with encased
IoT connected technologies like Wi-Fi and ZigBee that have been tested for aerial connections
and aid in mobile connectivity for remote management of the drone and data collection. The
proposed drone will contain IoT-specific data collection, processing, and/or effector capabilities
in addition to a Wi-Fi networking module. The Internet of Things (IoT) device can be any
intelligent device, such as a mobile phone, laptop, iPad, etc. that serves as a gateway and
provides Internet connectivity, is provided as needed, and is offered through devices like a
laptop, iPad, etc. that serve as a gateway. Anywhere and any device may connect to the drone
using these communication technologies. The smart gadget at the remote site manages the data
https://doi.org/10.4018/979-8-3693-0200-2.ch006 127
collected from the drone. Since the suggested drone has Wi-Fi built in, the data collected may be
transmitted in real-time to the cloud and seen online. The data gathered is kept in the application
cloud and utilized for data analysis, assessment, and providing farmers with best practices and
approaches for a specific condition.
Synchronization: The coordination block concentrates on tailoring to the requirements of
the target application. There are three key parts to it: mission control, mission planning, and
sensor data analysis. To address both the static and dynamic settings, we would create
distributed and centralized coordinating mechanisms. Mission planning divides the high-level
activities into flight paths that must be travelled and specific actions for each waypoint. The
mission control unit receives the user input and distributes it to the required components. The
user is then shown a single, sizable overview image that was created by mosaicing photos
captured by several sensors.

Processing Flow:

In the suggested model, the following steps will be carried out:

Pre-planning: The preplanned path must be computed first and used to establish the drone's
search engine.
Searching: After taking off, the drone travels along the designated path while taking
pictures and processing them internally.
Detection: Depending on the drone's intended use, we modify the detection algorithm to
identify any field uncertainties using the drone's integrated sensors.
Streaming: The IoT device collects any data or photos that are taken in real-time. The
devices control the streaming appropriately as well, and the cloud system receives the data they
have gathered.
Data Analysis: The relevant researchers get the necessary data from the cloud system for
analysis and evaluation following the circumstances and the topic at hand and potential fixes that
would aid farmers in working their land are developed.
Cultivation Control: The data from the drones may aid in the management of the
cultivation. For example, sensors installed in drones can measure the soil's moisture content and
the health of the plants, providing farmers with information about their fields and the subsequent
actions that need to be taken.
Computers on the Go - Due to its accessibility and lower connection costs, mobile
computing has significantly changed how we live our daily lives. The agricultural industry is one
of the many industries that use it. For informing farmers about the availability of products and
weather on a daily and seasonal basis, a mobile computing system has been proposed.
Wireless sensor networks, the Internet of Things (IoT), and sensors - A technology known
as the "Internet of Things" aims to link all worlds’ devices to the Internet. With an integrated
Internet stack, it makes use of RFID, Wi-Fi, and other sensors. Apps are created based on IoT-
enabled devices for monitoring and controlling systems in a variety of areas, such as industrial
processes, household appliances, and apps for monitoring one's health, smart homes, and smart
cities. Few academics in the field of agriculture have suggested IoT-based designs for tracking
https://doi.org/10.4018/979-8-3693-0200-2.ch006 128
the management of the supply chain for agricultural goods. Many efforts have been made in the
area of agriculture using wireless sensor networks, which are considered a mature technology.
Many characteristics needed in the agricultural realm may be sensed and analyzed using sensors.
There are several applications that use sensors in agriculture (Kishor et al., 2023: Rai, et al.,
2022).
For monitoring the qualitiy of the soil, WSN designs were suggested, constructed, and
tested.
Mobile Technology- Mobile technology has had a large influence on many parts of our
everyday lives as a consequence of its easy accessibility and cheaper connection costs. It is used
in almost every sector, including agribusiness. A mobile computing-based system has been
designed to notify farmers about goods and environment on a weekly and monthly schedule.
Big-data sources and big-data analytics - Massive amounts of data, such as sensor data,
social networking data, and commercial data, are gathered over a longer period of time from
many sources. The biggest issue is in the areas of collection, storage, analysis, and search
(Kishor, et al., 2023). In order to find hidden patterns in the data, it is used for business data
processing in conjunction with big data analytics. Big data is utilized in the agricultural industry
to manage the supply chain for agro goods to reduce production costs.
Knowledge creation through data analysis and mining - Analyzing data to uncover hidden
patterns is a technique known as data mining. Data mining for the agriculture industry has been
studied for a long time and. To categorize soil types, data mining has been utilized to analyze
their characteristics. Additionally, using current soil nutrient information and historical crop
sequences on the same field, soil data mining is helpful for crop prediction and choosing the best
crop sequence.
Utilizing the Cloud - Resources may be shared at a low cost thanks to cloud computing
(Kishor, et al., 2023). The infrastructure, platform, and software as a service (IaaS), which are all
offered by cloud computing service providers, are reasonably priced.
Agriculture data storage has been done using cloud computing (Mattern & Floerkemeier., 2010).
It has been utilized with IoT in the agricultural industry.
India’s Agriculture Industry - Agriculture provides the majority of Indians' income and is a
significant contribution to the country's economy. However, India's agriculture industry still has
to expand and foster technology engagement and usefulness. Although the Indian government
has also made a few efforts to offer farmers internet and mobile messaging services for
agricultural inquiries, and agro vendors' information to farmers , it gives static data about the
condition of the soil in each region. The system that bases decisions on real-time data about soil
quality based on its existing quality has not been put into place. The characteristics of the soil
determine its quality. The pH of the soil and the number of elements like nitrate, phosphate, and
potassium in the soil are crucial determinants of the kind of crop production and soil quality. By
applying only the necessary amount of fertilizer, real-time monitoring of these qualities enables
soil health preservation. Analysis of the soil's moisture content enables the application of water
just when necessary, preventing water waste. Additionally, environmental factors like
temperature and moisture have an impact on crop yield and crop diseases. In this regard, a
dynamic model that gathers such real-time data is required. All agricultural enterprises must be
connected to a decision-making system to boost output and facilitate the distribution of
https://doi.org/10.4018/979-8-3693-0200-2.ch006 129
agricultural goods supplied by producers to marketing companies and vendors to producers.
Other elements, such agro product rates, will also be under the control of such a system.
Many users, especially those in remote locations, may now access smart mobile phones.
The Beagle Black Bone is a low-cost IoT device that can be connected to the soil and
environmental sensors to gather information about the quality of the soil and the environment at
a time. This encourages the development of a portable, affordable sensor kit for detecting the
soil's quality and determining the need for fertilizers at the time. To be processed further, the soil
data from agricultural areas must be acquired using a sensor kit and transferred to Argo Cloud
storage. Big data were then gathered can be examined for the production-related activities that
are necessary.

The proposed transdisciplinary Smart Agriculture model

The five components that make up the transdisciplinary model's suggested architecture are
displayed in Figure 2:

1) Sensor Kit Module,

2) Module for mobile apps.
3) AgroCloud Module.
4) Big-Data Mining, Analysis and Knowledge Building Engine Module.
5) Government & AgroBanks UI

SensorKit is a transportable IoT gadget that includes soil and environmental sensors. The
MobileApp module offers users with a dashboard. AgroCloud Module includes storage, Big-
Data mining, examination, and knowledge building engines, as well as a programme module for
communicating with users. The Ministry of Agriculture and AgroBanks graphical user interface
is a web portal for agricultural initiatives and loans.

https://doi.org/10.4018/979-8-3693-0200-2.ch006 130
 Figure 2: Recommended Structure for a Multifunctional Framework of Intelligent Farming

Component for SensorKit - This section is a vital part of collecting this design and is in
charge of soil testing at regular intervals to obtain soil-related data. Figure 3 depicts the
SensorKit module. SensorKit is a low-cost and transportable kit in which we explored the usage
of a snoopy black bone, an IoT equipped device with memory and computational capacity, as
well as a GPS sensor to detect positioning information. This kit's main components are soil
nutrient sensors that are linked to it. We considered soil pH sensor, soil moisture sensor, and
Phosphorus (P), Potassium (K), and Nitrate (N) sensors for the aforementioned model, each of
which is communicated to the IoT device.

https://doi.org/10.4018/979-8-3693-0200-2.ch006 131
 Figure 3: SensorKit Module.

The AgroCloud Component - All agricultural sector users must connect to AgroCloud via
the MobileApp. AgroCloud storage, which includes Big-Data storage, will hold all landowner,
agro advertisement, medication, and agro, vendor and service supplier details
(fertilizer/pesticide/seed and agro machinery providers) specifics, as well as government
programmes for the agricultural industry, such as bank loans for producers and concessions on
seed and/or fertilisers. The module also saves data obtained on a regular basis through soil and
environmental monitoring. As an increasing number of consumers connect to this assistance, the
data amount expands significantly over time, leading up to Big-Data. The AgroCloud
component, which includes Big-Data storage, Big-Data The mining industry, Evaluation, and
Intellectual Construction Engine. As demonstrated by Figure 4, the aforementioned module
resides in AgroCloud as well as plays a significant part in determining for fertiliser necessity
according to the present crop determined by up-to-date soil features for enhanced yields,
forecasting crop diseases based on up-to-date soil characteristics and current environmental
conditions, crop yield estimation, best crop pattern analysis from data gathered over the span of
time, best crop for associated soil parameters, and the amount of watering necessitate based on
moisture in the soil level. The system also gives data concerning region-specific production
specifics for each agricultural product, total crop output for each crop in the state at large, and
current demand among customers, which will assist consumers regulate the costs for each agro
product. As this database accumulates details regarding soil quality and agricultural product
specifics with production amounts for each farmhouse over time, inference results from data
https://doi.org/10.4018/979-8-3693-0200-2.ch006 132
mining can be generated for better crop sequencing to be carried out for optimal productivity and
soil health. Furthermore, depending on prior stock of agro goods and present-day demand
requirements, this database may recommend crops to farmers for planting on acreage with
unusual soil features. Bigdata analysis may be used to forecast future product output based on
prior knowledge bases. The cloud storage application module is used to deliver alerts to users,
make recommendations based on analysis, and notify crop diseases based upon the present
climate and past knowledge base. AgroCloud module is shown in Figure 4

Figure 4 Argo-Cloud Modules

Conclusion and Future Work

The topic of "smart agriculture" is expanding quickly and has the potential to completely
change how we produce food. Farmers can maximise their resource utilisation, increase crop
yields, and lessen waste and environmental effects by utilising cutting-edge technologies like
sensors, IoT devices, and data analytics. Smart agriculture has several advantages, including
enhanced food security for the world's expanding population, increased productivity and
profitability for farmers, and less environmental impact. Future developments in smart
agriculture technologies are anticipated to include the creation of more sophisticated sensor and
data analytics algorithms, the application of artificial intelligence and machine learning to
automate decision-making processes, and the integration of blockchain technology to improve
https://doi.org/10.4018/979-8-3693-0200-2.ch006 133
supply chain transparency and traceability. Additionally, there is a great deal of potential for
smart agriculture to assist in addressing some of the major problems that the global food system
is now confronting, including food security, population increase, and climate change. Farming
operations can be managed more effectively, more food can be produced with less resource, and
our food systems are more resilient to changing conditions because of the power of technology
and data.
Future developments in smart agriculture will concentrate on creating more integrated and
all-encompassing systems that can handle the complex issues that farmers and the food system
as a whole are experiencing. Collaboration between experts in a variety of fields, including
agriculture, engineering, data science, and policy, will be necessary for this, as well as a
dedication to innovation and ongoing development.

REFERENCES

C. W. Bac, E. J. van Henten, J. Hemming, and Y.,( 2014), “Robots for high-value crops: State-
of-the-art review and challenges”, Journal of Field Robotics, vol. 31, no. 6, pp. 888-911.

A Burkle, (2009),”Collaborating miniature drones for Surveillance &recon-renaissance,” in

Unmanned/Unattended Sensors & Sensor Networks vi vol.7480.International Society for optics
& Photonics, P.74800H.

J. Borenstein and K. Miller, (2013), “Robots and the internet: Causes for concern,” IEEE
Technology and Society Magazine, vol. 32, no. 1, pp. 60–65.

Gupta S., Tyagi S., Kishor K. (2022), “Study and Development of Self Sanitizing Smart
Elevator”. In: Gupta D., Polkowski Z., Khanna A., Bhattacharyya S., Castillo O. (eds)
Proceedings of Data Analytics and Management. Lecture Notes on Data Engineering and
Communications Technologies, vol 90. Springer, Singapore. https://doi.org/10.1007/978-981-
16-6289-8_15.

Kishor K., Pandey D. (2022). “Study and Development of Efficient Air Quality Prediction
System Embedded with Machine Learning and IoT”. In Deepak Gupta et al. (Eds), Proceeding
International Conference on Innovative Computing and Communications. Lect. Notes in
Networks, Syst., Vol. 471, Springer, Singapore, https://doi.org/10.1007/978-981-19-2535-1_24.

F. Mattern and C. Floerkemeier., (2010), “From the Internet of Computers to the Internet of
Things.” ser. From active data management to event-based systems and more, Springer, pp. 242-
259.

B. S. Swathi and H. S. Guruprasad, (2014), “Integration of wireless sensor networks and cloud
computing,” International Journal of Computer Science, vol. 2, no. 5, pp. 49–53.

https://doi.org/10.4018/979-8-3693-0200-2.ch006 134
Kaushal Kishor, Neetesh Saxena, Dilkeshwar Pandey", (2023), Book edited “Cloud-based
Intelligent Informative Engineering for Society 5.0” pp. 1-234. Chapman and Hall/CRC., eBook
ISBN: 9781003213895 Edition-First, Pub. Location- New York, DOI:
https://doi.org/10.1201/9781003213895

Kaushal Kishor, parma Nand, (2023) " Wireless Networks Based in the Cloud That Support
5G”, Book Chapter in “Cloud-based Intelligent Informative Engineering for Society 5.0” pp. 23-
40. Chapman and Hall/CRC., eBook ISBN: 9781003213895 Edition-First, Pub. Location- New
York, DOI: https://doi.org/10.1201/9781003213895-2

G. Pingli, S. Yanlei, C. Junliang, D. Miaoting, and L. Bojia, (2011), “Enterprise- oriented

communication among multiple esbs based on wsnotification and cloud queue model,”
International Journal of Advancements in Computing Technology, vol. 3, no. 7, pp. 255–263.

E. Giusti and S. Marsili-Libelli, (2015), “A fuzzy decision support system for irrigation and
water conservation in agriculture,” Environmental Modelling & Software, vol. 63, pp.73–86.

V.Keerthi and G. N. Kodandaramaiah, (2015), “Cloud iot based greenhouse monitoring system,”
International Journal of Engineering Research and Applications, vol. 5, no. 10, pp. 35– 41.

Z.Liqiang, Y. Shouyi, L. Leibo, Z. Zhen, and W. Shaojun, (2011), “A crop monitoring system
based on wireless sensor network,” Procedia Envi- ronmental Sciences, vol. 11, pp. 558–565.

Y. Zhu, J. Song, and F. Dong, (2011), “Applications of wireless sensor net- work in the
agriculture environment monitoring,” Procedia Engineering, vol. 16, pp. 608–614.

S. A. Jaishetty and R. Patil, (2016), “Iot sensor network based approach for agricultural field
monitoring and control,” IJRET: International Journal of Research in Engineering and
Technology, vol. 5, no. 06.

Kaushal Kishor, (2023)," Cloud Computing in Blockchain”, Book Chapter in “Cloud-based

Intelligent Informative Engineering for Society 5.0”, pp. 79-105. Chapman and Hall/CRC.,
eBook ISBN: 9781003213895 Edition-First, Pub. Location- New York, DOI:
https://doi.org/10.1201/9781003213895-5

Kaushal Kishor, (2023), " Impact of Cloud Computing on Entrepreneurship, Cost, and Security”,
Book Chapter in “Cloud-based Intelligent Informative Engineering for Society 5.0” pp. 171-191.
CRC Press., eBook ISBN: 9781003213895 Edition-First, Pub. Location- New York, DOI:
https://doi.org/10.1201/9781003213895-10.

A. J. Adeloye, R. Rustum, and I. D. Kariyama, (2012 ), “Neural computing modelling of the

reference crop evapotranspiration,” Environmental Modelling & Software, vol. 29, no. 1, pp.
61–73.
https://doi.org/10.4018/979-8-3693-0200-2.ch006 135
Kishor K., (2022), “Communication-Efficient Federated Learning”. In: Yadav S.P., Bhati B.S.,
Mahato D.P., Kumar S. (eds) Federated Learning for IoT Applications. EAI/Springer
Innovations in Communication and Computing. Springer, Cham. https://doi.org/10.1007/978-3-
030-85559-8_9.

Kaushal Kishor,Shivam Attri,Shashi Ranjan,Tanvi Tyagi, (2018), "SMART CART BASED ON

IOT ", International Journal of Creative Research Thoughts (IJCRT), ISSN:2320-2882,
Volume.6, Issue 1, pp.1388-1392, Available at :http://www.ijcrt.org/papers/IJCRT1803295.pdf,
DOI: 10.6084/m9.doi.one.IJCRT1803295

B. Kumbar, B. Galagi, Bheemashankar, and N. Honnalli, (2016), “Smart irrigation system using
internet of things,” Bonfring International Journal of Research in Communication Engineering,
vol. 6, no. November 2016.

D. K. M. R.Hemalatha, G.Deepika, (2016 ), “Internet of things (iot) based smart irrigation,”

International Journal Of Advanced Research in Basic Engineering Sciences and Technology
(IJARBEST), vol. 2, no. 2, pp. 128–132.

Kishor K., Sharma R., Chhabra M., (2022), “Student Performance Prediction Using Technology
of Machine Learning.”, In: Sharma D.K., Peng SL., Sharma R., Zaitsev D.A. (eds) Micro-
Electronics and Telecommunication Engineering. Lecture Notes in Networks and Systems, vol
373. Springer, Singapore. https://doi.org/10.1007/978-981-16-8721-1_53.

K. Venkataramana and M. Padmavathamma, (2012 ), “A design of framework for agri-cloud,”

IOSR Journal of Computer Engineering, vol. 4, no. 5, pp. 1–6.

Kishor K., (2022), “Personalized Federated Learning.” In: Yadav S.P., Bhati B.S., Mahato D.P.,
Kumar S. (eds) Federated Learning for IoT Applications. EAI/Springer Innovations in
Communication and Computing. Springer, Cham. https://doi.org/10.1007/978-3-030-85559-8_3.

S. R. Rupanagudi, B. S. Ranjani, P. Nagaraj, V. G. Bhat, and G. Thippeswamy, (2015 ), “A

novel cloud computing based smart farming system for early detection of borer insects in
tomatoes,” in 2015 International Conference on Communication, Information & Computing
Technology (ICCICT). IEEE, pp., 1–6.

Kumar, R., Singh, M.P., Kumar, P., & Singh, J.P. (2015). Crop Selection Method to maximize
crop yield rate using machine learning technique. 2015 International Conference on Smart
Technologies and Management for Computing, Communication, Controls, Energy and Materials
(ICSTM), 138-145.

Jain, Atishay and Sharma, Yash and Kishor, Kaushal, (2021), “ Prediction and Analysis of
Financial Trends Using Ml Algorithm” Proceedings of the International Conference on
https://doi.org/10.4018/979-8-3693-0200-2.ch006 136
Innovative Computing & Communication (ICICC) 2021, Available at SSRN:
https://ssrn.com/abstract=3884458 or http://dx.doi.org/10.2139/ssrn.3884458.

Doshi, Z., Nadkarni, S., Agrawal, R., & Shah, N.K. (2018). AgroConsultant: Intelligent Crop
Recommendation System Using Machine Learning Algorithms. 2018 Fourth International
Conference on Computing Communication Control and Automation (ICCUBEA), 1-6.

Jain, A., Sharma, Y., & Kishor, K. (2020). “Financial Supervision and Management System
Using Ml Algorithm.”, Solid State Technology, 63(6), 18974-18982.
http://solidstatetechnology.us/index.php/JSST/article/view/8080

Lee, H., & Moon, A. (2014). “Development of yield prediction system based on real-time
agricultural meteorological information.”, 16th International Conference on Advanced
Communication Technology, 1292-1295.

Sharma A., Jha N., Kishor K. (2022), “Predict COVID-19 with Chest X-ray.” In: Gupta D.,
Polkowski Z., Khanna A., Bhattacharyya S., Castillo O. (eds) Proceedings of Data Analytics and
Management. Lecture Notes on Data Engineering and Communications Technologies, vol 90.
Springer, Singapore. https://doi.org/10.1007/978-981-16-6289-8_16.

Paul, M.T., Vishwakarma, S.K., & Verma, A. (2015). Analysis of Soil Behaviour and Prediction
of Crop Yield Using Data Mining Approach. 2015 International Conference on Computational
Intelligence and Communication Networks (CICN), 766-771.

Pudumalar, S., Ramanujam, E., Rajashree, R.H., Kavya, C., Kiruthika, T., & Nisha, J. (2017).
Crop recommendation system for precision agriculture. 2016 Eighth International Conference on
Advanced Computing (ICoAC), 32-36.

Kishor, K., Nand, P., & Agarwal, P. (2017). Subnet based ad hoc network algorithm reducing
energy consumption in manet. International Journal of Applied Engineering Research, 12(22),
11796-11802.

Kishor, K., Nand, P., & Agarwal, P. (2018). “Secure and Efficient Subnet Routing Protocol for
MANET”, Indian Journal of Public Health, EXECUTIVE EDITOR, 9(12), 200. DOI:
10.5958/0976-5506.2018.01830.2

Kishor, K., Nand, P., & Agarwal, P. (2018). Notice of Retraction Design adaptive Subnetting
Hybrid Gateway MANET Protocol on the basis of Dynamic TTL value adjustment. Aptikom
Journal on Computer Science and Information Technologies, 3(2), 59-65.
https://doi.org/10.11591/APTIKOM.J.CSIT.115.

Kishor, K., Tyagi, R., Bhati, R., Rai, B.K. (2023). Develop Model for Recognition of
Handwritten Equation Using Machine Learning. In: Mahapatra, R.P., Peddoju, S.K., Roy, S.,
https://doi.org/10.4018/979-8-3693-0200-2.ch006 137
 Parwekar, P. (eds) Proceedings of International Conference on Recent Trends in Computing.
Lecture Notes in Networks and Systems, vol 600. Springer, Singapore.
https://doi.org/10.1007/978-981-19-8825-7_23.

Rai, B. K., Sharma, S., Kumar, G., & Kishor, K. (2022). Recognition of Different Bird Category
Using Image Processing. International Journal of Online and Biomedical Engineering (iJOE),
18(07), pp. 101–114. https://doi.org/10.3991/ijoe.v18i07.29639

Kishor, K., Singh, P., Vashishta, R. (2023). Develop Model for Malicious Traffic Detection
Using Deep Learning. In: Sharma, D.K., Peng, SL., Sharma, R., Jeon, G. (eds) Micro-
Electronics and Telecommunication Engineering . Lecture Notes in Networks and Systems, vol
617. Springer, Singapore. https://doi.org/10.1007/978-981-19-9512-5_8

https://doi.org/10.4018/979-8-3693-0200-2.ch006 138

View publication stats