Hindawi
Journal of Food Quality
Volume 2022, Article ID 4721547, 17 pages
https://doi.org/10.1155/2022/4721547
Research Article
Implementing Machine Learning for Smart Farming to Forecast
Farmers’ Interest in Hiring Equipment
Manik Rakhra ,1 Sumaya Sanober ,2 Noorulhasan Naveed Quadri ,3 Neha Verma ,4
Samrat Ray ,5 and Evans Asenso 6
1Department of Computer Science and Engineering, Lovely Professional University, Phagwara, Punjab-14411, India
2Prince Sattam Bin Abdul Aziz University, Wadi Aldwassir 1191, Saudi Arabia
3College of Computer Science King Khalid University Abha, Abha, Saudi Arabia
4Department of Physics, KRM DAV College, Nakodar 144040, India
5Sunstone Eduversity, Gurugram, India
6Department of Agricultural Engineering, University of Ghana, Accra, Ghana
Correspondence should be addressed to Manik Rakhra; rakhramanik786@gmail.com and Evans Asenso; easenso@ug.edu.gh
Received 18 December 2021; Accepted 10 January 2022; Published 11 February 2022
Academic Editor: Rijwan Khan
Copyright © 2022Manik Rakhra et al.*is is an open access article distributed under the Creative Commons Attribution License,
which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Farmers’ physical labor and debt are reduced as a result of agricultural automation, which emphasizes efficient and effective use of
various machines in farming operations with the purpose of reducing physical labor and debt. It is a revolutionary idea in
agriculture to create custom hiring centers, which are intended to make it easier for like-minded farmers to embrace technology/
machinery for enhanced resource management practices. *e study in question examines the significance of tool renting and
sharing in the workplace. Rental and sharing equipment are two approaches that might be used to enable farmers to borrow
equipment at a cheaper cost than they would otherwise have to pay for it. *e following is a manual pilot study of 562 farmers in
India to address the numerous challenges farmers face when looking for tools and equipment, as well as to determine their strong
interest in the process of renting and sharing equipment. *e study was conducted to address the numerous challenges farmers
face when looking for tools and equipment and to determine their strong interest in the process of renting and sharing equipment.
Farmers are divided into three groups according to the results of this poll: small, moderate, and large. Training and testing splits
were used on the same data set in order to get a better understanding of the target variables. *e data set for the survey was
standardized in order to remove ambiguity. In this research, three different machine learning models were utilized: nearest
neighbors, logistic regression, and decision trees. K-nearest neighbors was the most often used model, followed by logistic
regression and decision trees. In order to get the best possible result, a comparison of the aforementioned algorithm models was
carried out, which revealed that the decision tree is the better model among the others in this regard. Because the decision tree
model is completely reliant on a large number of input factors, such as the kind of crop, the time/month of harvest, and the type of
equipment necessary for the crops, it has the potential to have a social and economic impact on farmers and their livelihoods.
1. Introduction yield comes into play. Without the optimal use of machines,
agriculture production cannot be hiked. *e developing
*e exponential population growth has strained agriculture. countries lag behind in farm productivity owing to improper
*e agricultural land size is decreasing, but the demand to use of machines in various agriculture operations. On the
feed more and more mouths is increasing day by day. other hand, automation of farming operations contributes
Natural and man-made factors have further hit food pro- significantly to rural and agricultural growth in many de-
ductivity. *erefore, mechanization is a panacea to most of veloping countries. *erefore, farmers must be encouraged
the ills that afflict agriculture. Herein, the role of machines to to use machines in the field to increase efficiency and the
carry out agriculture operations to maximize efficiency and produce of their products. It is also necessary to put
2 Journal of Food Quality
agriculture on automation the current rate of agricultural
production required to feed the world population cannot be
realized without mechanization [1]. Unfortunately, the use Low incomeof farmers
of farm machinery, unfortunately, is still under consider-
ation in most parts of the world, including in some parts of
India. It is high time that both the government and the
private sectors should put their head together to push the Low Low saving of
country towards mechanized farming. Researchers are de- productivity farmers
veloping strategies to introduce the innovative system of
mechanized farming to boost productivity and economy [2]. Low
Mechanized farming has boosted their productivity besides Agriculture
strengthening the economy of their respective states. mechanism
demand
1.1. CustomHiring. Custom hiring center is a novel concept Figure 1: Various cycles of agriculture mechanisms under
in farming that intends to stimulate the adoption of im- development.
proved resource management strategies. *ese resource-
sharing techniques at a cheaper cost to individual farmers
are prevalent in some specific parts of the country. Under into various financing schemes meant for the farmers [18, 19].
this innovative programme/strategy, agricultural equipment Custom hiring empowers small andmarginal farmers tomake
and tools are shared with the farming community [3–5]. use of expensive agricultural equipment. It enables farmers to
Custom hiring centers enable needy farmers to gain the operate expensive techniques and technology and complete
advantages of automation via the utilization of costly the harvesting task in a short span of time. Also, it cuts labor
equipment. Some cooperative organizations have taken the and boosts crop intensity.
initiative to offer agricultural equipment services to the Custom hiring is not a cumbersome programme/strat-
farming community. egy. It does not burden farmers. Under the programme, the
*e role of the tractor in farming is undoubtedly im- user only needs to pay the contract/rental charges and se-
mense. But studies revealed that a tractor was used for an curity. Each model has been designed to determine the best
average of 2 hours each day to carry out farming operations. hardware and asset assignment to reduce farming costs and
In a developed village in Punjab, rented out tractor hours convenience. *e model is designed to choose appropriate
amount to 76 hours per year, and ploughing account for 61% agricultural tools and power sources with the purpose of
of those hours. *us, it is concluded that a farmer might run accomplishing the task on time. *is eliminates the shortage
his farm with the help of custom-hired tools [6–8]. Farmers of produce, which is otherwise a consequence of delayed
with less than 2.8 hectares of land are prospective consumers agricultural operations. *e operationalization of the asset
of agricultural tools via hiring/rental services. *e state’s assignment programme in the year 2007 to minimize the
mechanization level has also expanded dramatically [9, 10]. cost turned out to be a success. Consequently, more in-
CHCs have thus played a major role in popularizing terpretation was performed on supply chain measures and
mechanized farming among farmers. CHCs make farm financial productivity in Punjab.
tools, machinery, and equipment available to farmers on a *e small farmers saw their financial productivity go up
rental basis [11, 12]. While crop-specific tools and equip- by 17.02%, but large farmers displayed much higher eco-
ment (power units, tractors, tillers, and harvesters) are nomic productivity. *e larger farmers have access to su-
universally employed, resource sharing, mainly farm ma- perior equipment. *e smaller farmers cannot afford it. Yet
chinery and implements at a reduced cost to individual mechanized farming pays to the smaller farmers. About 90%
farmers, is a trend in some regions of the country [13–15]. of the farmers in Punjab who own tractors use them less than
Figure 1 displays a cycle of agricultural mechanisms that are 400 hours annually. Mechanization in this scenario plays a
under development. big role as it boosts growth. Custom hiring centers should
Mechanization introduces accuracy and timeliness into pitch in here (they are already doing it) to make farming
agricultural activities, higher field covering over a shorter tools and equipment available to the small farmers at the
period of time, resource consumption, conservation of appropriate time to get the intended results. *is would
moisture content under stressful conditions, and supply of mitigate the loan burden for the farmers as they usually
proper drainage [16, 17]. In 100 NICRA communities custom borrow loans at a high rate of interest from commission
hiring centers (CHCs), farm tools are built, enabling farmers agents [20].
to overcome labor shortages and increase agricultural pro- All disciplines benefit from artificial intelligence-based
ductivity. *e custom hiring center is managed by a panel of technologies, which also assist to handle the issues en-
farmers appointed by the Panchayati Raj. *e Village Climate countered by numerous businesses, including the agricul-
and Risk Management Committee determines the fees for tural sector, in areas such as crop yield, irrigation, soil
renting the machines/implements (VCRMC). Additionally, content sensing, crop monitoring, weeding, crop estab-
this committee utilizes the cash earned by hiring costs to lishment, and other domains In order to supply high-valued
repair and maintain tools, with the remaining amount going applications of artificial intelligence in the indicated area,
Journal of Food Quality 3
agricultural robots are being developed. *e agriculture farmers’ deaths in Punjab.*is unfortunate trend of farmer’s
industry is experiencing a crisis as the world’s population suicide is attributed to the restructuring of the agricultural
continues to grow. Artificial intelligence has the potential to system; crop failure, especially cotton in recent times;
provide a much-needed solution to this pressing problem, mounting debt; and joblessness [26–28]. *e media report
however. Technological solutions powered by artificial in- calls for deep introspection of agriculture-related laws be-
telligence have allowed farmers to generate more output sides looking for other causes that push farmers to the death
with less input and even increase the quality of their product trap. In order to find out the factors/causes that induce
while also guaranteeing that their crops reach the market farmers to suicide in Punjab, this research study was per-
more quickly. In the year 2020, 75 million linked devices formed [29].
were used by farmers worldwide. Farms are predicted to
create an average of 4.1 million data points per day by 2050,
according to industry predictions. 1.2.1. Suicide Loss Overview. A check at the agricultural
Farmers often spend between 25% and 30% of their suicide profile revealed that small and marginal farmers with
revenues on the purchase of equipment. Since this equip- land ownership of up to 5 acres were more prone to suicides.
ment is purchased from the local entrepreneurs at expensive *ese farmers of the Malwa belt of Punjab [14] would acquire
prices, they increase the farming input cost. Labor is also extra land on lease at the cost of Rs 30,000–40,000 per year.
hard to come by in Punjab as the rural population often *ese small and marginal farmers accounted for 70%–80% of
migrate to cities in search of better employment avenues. In farmers’ suicides in the government records.
such a grim scenario, the role of mechanized farming In the present era, Farmer’s financial burden is increased
assisted by CHCs increases manifold. *is can accelerate by routine fixed expenses such as the maintenance and depth
agriculture growth, boost the economy, and also allow the of submersible pumps that cost in lakhs. Making such in-
Indian market to grow. *is also has the potential to end the vestments is financially unfeasible for a small or marginal
protracted issue of rural indebtedness and low profitability farmer, so they borrow from informal sources for which they
besides retaining small farmers in the agriculture business. have to the exorbitant rate of interest (18%–36%).*erefore,
Over 20 crores Indian farmers lack access to agricultural in this study, we are going to design an intelligent decision
equipment, and many of them have not even used them. Yet support system. *rough this system, the user who wants to
small farmers who own 86% of India’s farmland are doing give their equipment on a lease can update the data on the
their best to transform agriculture production and revenue framework, and the end-user, who is in search of the tool,
dramatically. can hire the needed tool at the peak season. With this
According to a report by NCRB, around 97% of suicides framework, the different farmers who live in provincial
in the Malwa region were triggered by “agricultural debt.” zones get updated about the new innovation. *us, by using
*e bulk of unfortunate among them are small and marginal them, their crops can be saved from ruins and disasters. *is
farmers, who own between 1 and 5 acres of land. Around system will help farmers get their crops harvested in peak
2.55% of farmers in the Majha and Doaba areas commit time without any fear of the nonavailability of equipment.
suicide. Of these suicides, 1.81% are linked to agricultural *is framework will help the farmers by getting login into
debt [5, 21, 22]. *e economic condition of small/marginal the framework and by the accessibility of the needed
farmers is quite weak, and they cannot acquire agricultural equipment. Once a farmer gets accessibility to the correct
equipment on their own or via institutional finance. To tide asset, he has to pay the sum for taking the tool on rent/lease
over the situation, custom hiring centers are established for for a specific time. In this way, a farmer’s dependency on
small/marginal landowners to access agricultural equipment banks/commission agents for borrowing loans will end. *is
[23, 24]. proposed framework, in turn, will enhance the financialstrength of farmers [30].
1.2. Issues 6at Force Farmers to Face Death. Farmers 1.2.2. Exploitation by Commission Agent (Arhtiyas).
commit suicide to take the extreme step for putting their life Many farmers with no other income other than agriculture
to an end for innumerable reasons. Floods, famines, in- depend on the loan to build farm infrastructure and also to
debtedness, geographical remoteness, loss in productivity, sustain their daily agriculture operations. Since cooperative
distress sale, inability to pay off debt, and many more factors societies provide short-term official loans for seasonal ag-
push farmers to the wall, which often results in suicides. A ricultural needs and do not lend loans for other agriculture-
host of other factors such as illness, climate change, and based operations, including loans against leased lands and
illogical national policy on agriculture also compel farmers farmers borrow loans from commission agents. *ese loans
to take resort to suicide. *e inability of the farmers to pay are borrowed at a high rate of interest.
off the debts borrowed from the bank/commission agents
often acts as a trigger and forces them to end their life [25]. 2. Smart Farming Systems
*emismatch between input cost and net profit is so skewed
that it frustrates farmers beyond repair, which finally gets *e integration of modern information and communication
culminated in their death. As their revenue goes down, technologies (ICT) with agriculture, resulting in a*ird Green
farmers are left with no other alternative except to commit Revolution, is referred to as smart farming. *e agricultural
suicide. Of late, the media highlighted the significant spike in world is currently experiencing the *ird Green Revolution,
4 Journal of Food Quality
which is based on the integration of ICT solutions such as Smart Sensing & Monitoring
precision equipment, the internet of things (IoT), sensors and
actuators, geo-positioning systems, big data, unmanned aerial
vehicles (UAVs and drones), robotics, and other technologies.
*ese changes are necessary for the future of agriculture to
enhance productivity and save time [31, 32]. By using remote
sensing, the smart farming system saves money, boosts output,
and enables better resource management. Constant crop
growing in distant areas demands more attention, soil, and
water. Because they are linked to smart irrigation and man- Cloud Based
agement, which saves time and resources by doing things
including testing the pH balance of the soil, analyzing tem-
perature, and finding all the available time, farmers can
concentrate on important matters such as pest control, irri- Smart Control Smart Analysis & Planning
gation, andmodifying soil conditions. Figure 2 shows the smart Figure 2: Smart farming supply.
farming supply.
Remote data are vital for precision farming, along with
computer and equipment mechanization that supports in- predict equipment prices based on the attributes such as type
creasing issues and production assistance. In resource of equipment, location, and demanding days. Figure 3
management, it is a market approach that balances buyers represents the basic regression plot.
and sellers [2]. Figure 3 depicts a regression plot where︷y1,︷y2, and
︷y3 are the predicted values on a regression line and y1, y2,
and y3 are actual values. Here, in the graph in the figure, r1,
2.1. 6e Real Purpose of Smart Farming. Public concern r2, and r3 are called residual values on the vertical axis and
about food safety is on the rise, in part, due to a number of explain the difference between actual and predicted values
food crises. Clio metrics are used to follow, predict, and on the vertical axis [35, 36]. *is regression interpretation
guide all stages of the growing and harvesting process for a can perform with various effective algorithms such as simple
crop.With the concept of smart farming, the user can get the linear regression, multiple linear regression, polymer linear
right equipment at the right time for harvesting the crop to regression, decision tree, and support vector machine. In
get a better yield. In such systems, networks are more Figure 3, a partial regression plot is used in applied statistics
complicated. Many agricultural items are sold using a to demonstrate the impact of adding another variable to a
strategy of reducing costs, which results in low profitability. model that already contains one or more independent
In this growth, smart data technologies play a key shared variables. Partially regressed plots are also known as addi-
role: computers are fitted with all kinds of sensors that tional variable plots, adjusted variable plots, and individual
provide secure, machine-based data in their environment. coefficient plots, among other terms.
Preharvesting, harvesting, and postharvesting are the
three primary categories of agricultural activity. Machine
learning technologies have contributed to boosting agri- 2.2.2. Clustering. It is an unsupervised learning technique.
cultural gains. Machine learning is a recent technology that *is technique does not have any output information for the
is assisting farmers in reducing farming losses by offering training process [37]. Clusters can organize a bunch of data
detailed crop suggestions and insights. Machine learning is based on the different clusters. Clustering starts with a data
becoming more efficient and accurate because of deep point, and these data points can be measured like length and
learning algorithms. Using automated machine learning, width. Clustering is used to create a group of data that is
one may reduce the need for ML expertise while also au- called clusters. *e clustering happens fully automatically.
tomating the ML workflow with greater precision [33, 34]. Clustering is the process of separating a population or set
of data sets into a number of groups such that data points
2.2.Machine Learning Techniques. *e following models are belonging to the same group are more identical to one
the ones that have been implemented in this present work: another and different from data sets belonging to othergroups. It is essentially a collection of items based on their
(i) Regression similarity and dissimilarity [38–40]. Figure 4 demonstrates
(ii) Clustering that the system has a large number of data set in the form of
(iii) Instance-based model clusters. Content-based clusters will be formed automati-cally using our technology. For instance, in the scenario of
(iv) Decision trees renting and sharing agricultural equipment, our system
would get the user’s current position from the whole India
map. In the current study, we have implemented Google
2.2.1. Regression. *is concept comes from supervised API, which identifies the location of the equipment to be
machine learning, which can help us predict and explain hired. Clustering is critical as it implies the fundamental
objects based on categorical data. For example, we can classification among data sets. Clustering is totally
Journal of Food Quality 5
ŷ = b0 + bŷ 1
x
3
y2 
r2 = (y2 – ŷ )
r3 = (y3 – ŷ3)
2
y3
ŷ1 ŷ2
r1 = (y1 – ŷ1)
y1
Figure 3: Regression plot.
2.2.4. Instance-BasedModel. Instance-basedmeans building
5 hypotheses directly from training samples. It is a memory-
based model that can compare trained instances with the
new problem instance. One of the most important advan-
4 tages of this based model on the other methods is the unseen
data can be easily adapted by this model, that is, it is a
3 memory-based model; it may simply store the new instance.
*is model is exactly linked with the renting and sharing of
2 the equipment, that is, how this system can get the infor-
mation about the number of equipment used by the user in
1 the past years.
0 2.2.5. Artificial Neural Network. Artificial neural networks
-2 -1 0 1 2 3 are machine learning algorithms that simulate the human
brain. As stated above, the neurons in our nervous system can
Cluster 1 Cluster 3 learn from history; in the same way, the ANN is capable of
Cluster 2 Cluster 4 learning from the data to produce forecasts or categories.
Figure 4: Clusters in the scattered plot. ANNs are time-varying mathematical methods that discover
a new sequence in complex relationships between outputs and
inputs [43]. Neural network networks are commonly used in
subjective. It depends on the consumer what criterion sat- tasks such as machine vision, voice recognition, text mining,
isfies their requirements. An example of this would be: we and diagnosis. Because ANNs learn from illustration data sets,
may be interested in identifying representatives for ho- they have a major advantage. Most commonly, the ANN is
mogenous groups (data reduction), as well as discovering discrete structure estimation.With these tools, it is possible to
“natural clusters” and describing their previously unknown arrive at distribution solutions at a cost-effective rate. ANN is
attributes. *is method makes hypotheses that will provide also capable of taking a data set and returning the final output.
clusters of points with varying validity. ANNs can improve current statistical tools due to their
advanced meaningful insights.
2.2.3. Decision Trees. A decision tree is one of the best 3. Research Methodology
modeling techniques used in machine learning. It is one of
the predictive modeling approaches used in machine 3.1. Data Collection. Farmer fluctuations are driven by a
learning w; here, the data is continuously split according to multitude of factors that primarily include educational
the particular parameters, namely, decision nodes and qualifications, age, yearly income, spending, the number of
leaves. *ese are the basic fundamental steps to explain this family members, lack of technical expertise, the load of
tree. *e leaves represent the final outcomes, and the de- debts, and many other contributing factors.
cision nodes represent the points at which the data is split *e foregoing concerns contributed to the demise of
[41, 42]. Training data may be used for both regression tasks farming in India. Considering this issue, in this present
but is mostly employed for addressing classification issues. study, a socioeconomic study is undertaken in Punjab, and a
Figure 5 depicts a representation of the decision tree. An technical solution is found to encourage agricultural
internal node represents a data set feature; a branch rep- equipment rental and sharing. *is chapter includes
resents a rule base; and each leaf node represents a result. A methods and methodology used for the development of the
decision tree has two nodes: a decision node and a leaf node. Internet-based smart agricultural resource sharing frame-
Selection nodes serve to make any decision, while leaf nodes work. *e purpose of this research is to modify the farming
act as the results of such choices. *e judgments of the tests production in Punjab. For this, recent supplementary data
are based primarily mostly on the data set’s characteristics. has been gathered and interpreted from a wide range of
6 Journal of Food Quality
Outcome
Option
Outcome
Option 1
Option
Decision
Outcome
Option 2
Outcome
Figure 5: Representation of decision tree.
sources. In this applied research, we gathered the data from access to modern technology. It will increase farmer income
562 farmers in Punjab from different districts, villages of through increasing productivity by farm mechanization.
Majha, Malwa, and Doaba regions of Punjab. *e data has Farmers will not have to purchase tractors or other vehicles
been collected by an open-end questionnaire, which includes because they will be available for rent at a fraction of the cost
various parameters as shown in Table 1. *e questionnaire of ownership.
was created in English and Punjabi languages taking into Farmers who cannot afford to buy high-end agricultural
concern the education level of the farmers. *e purpose of machinery and equipment can hire farm equipment and
this collected data is to explore the major concerns faced by machinery from custom hiring centers. A custom hiring
the farmers. By the parameters loan source, the purpose of center is an effective mechanism for most small farmers to
debt, interested to hire manufacturing tools, and interested gain access to agricultural machinery services. In custom
in mobile application, we anticipated the need for renting hiring, farmers do not have to worry about start-ups costs or
and sharing of the equipment. repair and maintenance costs. *ey only pay for chargeable
To know the financial and educational situation of services and personalized service prices. Literature reported
farmers in Punjab, a survey was done using Google Forms as that the custom hiring centers have the potential application
well as door-to-door questioning. Table 1 shows the study for renting and sharing of equipment.
from the sample count of 562 farmers fromMajha district of After reviewing the many challenges encountered by
Punjab shows that most of the farmers are having small to farmers, we have built a support structure the smart tillage
moderate landholdings and the farmers are not educated that helps farmers rent and share equipment. For this
enough to know the latest techniques or latest farming renting sharing of equipment, we have implemented the
mechanization that can help them get more revenue from concept in Python language.*e systematic steps to establish
the same farming land. Table 2 depicts the details of the type the information management system are implemented by
of farmers. artificial intelligence and machine learning algorithms. *e
Manually obtained data infers the need for rental and classification of machine learning falls into different cate-
sharing of equipment. It includes several contributing as- gories such as linear regression, instance-based model,
pects such as they are drowning in debt, ignorance of clustering, decision tree, and many more. We have devel-
technical options, and government regulations. *erefore, oped a model that embeds the decision tree, which would
during the harvesting period, they are unable to use the provide the ideal solution for farmers. Decision trees are
equipment owing to its high demand. Farming operations helpful because they require us to think about all conceivable
also rely on a lot of bank loans and financial support. Fi- outcomes and follow each route to a conclusion. It gathers
nancial inclusion is critical for farmers. *e financial in- and analyzes information across the branches to identify
clusion gap for India’s farmers remains persistent, despite decision nodes for additional study.
several initiatives. Most farmers commit suicide due to their
financial load, which is further aggravated by various in-
direct factors. Banking facilities are tough to get for small 3.2.Machine LearningWorkflow. To assess the data set from
and marginal farmers. As mechanization, as well as the the selected smart tillage, we employed multiple classifiers
underutilization tendency, raise production costs or reduce such as logistic regression, k-neighbors, and decision tree.
net returns to farmers, farming becomes expensive. *e trained model’s accuracy was projected using data from
Equipment is costly to purchase and maintain, and over 562 farmers polled. Our training data set has 447 obser-
that, the loan's monthly/yearly EMI adds on. A farming vations, whereas our testing data set contains 115 obser-
equipment rental for agriculture aims to provide small vations. *e model in Figure 6 utilizes farmer data as input,
farmers who cannot afford to buy costly machinery with in which many criteria including land, gain from farming,
Journal of Food Quality 7
Table 1: Snapshot of sample collected data set.
1 2 3 4 5 6 7 8 9 10 11 12
Farm Aware of
Name Village Land Age Gender Education Family Per month Agriculture Farmer newmembers expense experience category registeredor not farmingtools
Banger
Buta Singh MuhabatSingh, 3 acre 38 Male Graduate 4 10,000–25,000 18 Small No Yes
Bathinda
Banger
Gurdev Muhabat
Singh Singh, 1 acre 40 Male Secondary 4 10,000–25,000 20 Small No No
Bathinda
Banger
Gurjant Muhabat
Singh Singh, 2 acres 39 Male Secondary 6 25,000–50,000 19 Small No No
Bathinda
Banger
Mahinder Muhabat
Singh Singh, 3 acres 44 Male Secondary 5 25,000–50,000 24 Small No Yes
Bathinda
Banger
Mejor Muhabat
singh Singh, 3 acres 48 Male Secondary 6 25,000–50,000 28 Small No Yes
Bathinda
Banger
Parminder Muhabat
Singh Singh, 6 acres 55 Male Secondary 5 25,000–50,000 35 Medium No Yes
Bathinda
Banger
Gurtek Muhabat
Singh Singh, 5 acres 60 Male Graduate 5 25,000–50,000 40 Medium No Yes
Bathinda
Banger
Rajinder Muhabat
Singh Singh, 5 acres 39 Male Secondary 4 10,000–25,000 19 Medium No Yes
Bathinda
predict the accuracy of the trained model. Our training data
Table 2: Detail of type of farmers. set consists of 447 observations, and the testing data set
Sl. No. Type of farmers Percentage (%) consists of 115 observations. We input the trained data set
2 Small 67.06 into the model and trained the model, and then we get the
3 Moderate 31.08 predication for test and trained data sets. *is model would
4 Large 1.06 improve quality of life by bringing them together for win-
win trades. Farmers can gain some extra cash without much
effort by simply posting items that are no longer in use,
per month expenditure, awareness of new technologies, giving them the opportunity to find equipment at reasonable
availability of loans, usage of smartphones, and information prices. *e steps for the proposed model are given in al-
on interested users are examined. In this, the comparison is gorithm 1 are as follows:
done with the following three techniques:
Step 1: inputting the farmers’ data into the system
(i) Logistic regression Step 2: dropping the duplicate columns
(ii) K-neighbors classifier Step 3: understanding the target variables
(iii) Decision tree Step 4: initializing and fitting the model
In order to view the number of farmers/users who are Step 5: predicting the values of test data
interested to hire manufacturing tools. From the selected
smart tillage, we have tested the data set by different clas- Step 6: preparing classification reports
sifiers named logistic regression, k-neighbors, and decision Step 7: evaluating model
tree. Herein, surveyed data of 562 farmers have been used to Step 8: depicting accuracy
8 Journal of Food Quality
Hyperparameter
Tuning
Data Collection Analysis Feature Data Pre- Model Model Optimal Prediction
By Surveys Selection Processing Training Evaluation Model
Logistic
Regression
Recommendation Demand and Supply
System KNeighbors Optimization
Classifier
Searching Decision Input
Trees Date &
Price Location Hour
Name Month Season
Equipment
Price Demand
No. of Equipment
Available
Figure 6: Accuracy model.
3.2.1. Step-by-Step Procedure: Smart Tillage. In terms of the for. Search is done via a database in order to locate a machine
procedure, only users who have been granted permission by matching the specifications set by the customers. *e cost
the system administrator are permitted to rent or hire their per day is fixed, which will be invoiced after computing the
equipment. *e user who wants to hire equipment must cost for the number of days specified using the calendar
submit the necessary information in the form of a picture of function to and from filters. *e model was built using
the equipment, the distance for which it may be leased, and machine learning for data Interpretation and report pro-
the fee per day for leasing the unit. As soon as the data is duction. Table 3 shows the methodology/tools/instruments
submitted by the user, it will be cross-checked by the sys- to be used.
tem’s administrator before being made accessible in the
client and search lists. *e customer is responsible for
uploading all of the properties that the client wishes to have 3.3. Client Approach. Figure 9 represents the systematic
listed for hire or rental.*e smart tillage is shown in Figure 7 approach for renting equipment. *e client here can rent
as a layout. and hire the equipment. *e client once gets registered will
*e client after selecting the location through Google upload the equipment details using the name, dates for
Maps’ longitude and latitude will be able to search for the displaying in the search list, cost per day, and image of the
equipment using filters. From the displayed list, the client product. Once the details are filled the request will be
who wants to hire the equipment selects the product and submitted. When it gets approved by the admin, the product
clicks on it; it will pop up showing all the details such as cost will be shown on the client dashboard, and a message will be
of hiring, available for how many days. If it matches with the received by the client.
requirement of the client, he will have to select the hiring
dates from the day he wants to hire and till the day it will be 3.4. Location PredictionApproach. *is is the step where the
hired for. Once the days are fixed for hiring, the system will system identifies the location using Google Maps’ longitude
display the total rent it will cost. *e client then has to send a and latitude clicked by the users logged in to the system,
request to the admin for authentication. It will be listed on searches the locations within the range selected by the user,
the client dashboard only after the admin approves the and displays the list of results. Figure 10 depicts the location
request. Along with this, the equipment will be removed prediction approach used in the system. We have incor-
from the main search list for other clients for the same porated the Google Astro Library and OpenLayer Map,
equipment for the same dates. In Figure 8, the system is which reveals the current location of the user.
having password-based security. Only those users who are
having an account in this system can access and update
details of their own profile only. *ere are number of pa- 3.5. Distance and Cost Predication Approach. *e distance
rameters used for the filtration of data such as location, here is used for search and distance of client who is hiring
distance, cost per day, and number of days. Machine the rented equipment. It will allow the client to have a cost
learning is employed to determine the location, pricing variation that depends on the distance from where the
information, and number of days the equipment is rented equipment is hired. Normally distance parameter is used to
Journal of Food Quality 9
INPUT: S, where S� set of classified instances
OUTPUT: decision tree
Require: S ≠ Φ, num_attributes >0
(1) Procedure BUILD TREE
(2) Repeat
(3) maxGain< - 0
(4) Split A< - null
(5) e< - Entropy(Attributes)
(6) For all attributes a in S do
(7) Gain< - Information Gain (a, e)
(8) If gain>maxGain then
(9) maxGain< - gain
(10) splitA< - a
(11) End if
(12) End for
(13) Partition (S, split A)
(14) until all partitions processed
(15) End procedure
ALGORITHM 1: Decision tree.
Farmer
Interact with Different Platform
Client Admin
Authentication
Smart Tillage Response Smart Tillage
Website Mobile Application
Storing of Data
Request Request
Send Send
Cloud Fire Store Sending Approval
Message
Figure 7: Layout of smart tillage framework.
display all the clients who are offering the required product. Pre-Processing
Figure 11 predicts the distance and cost approach. To utilize
the equipment; one must search the tool by product name, Accessing Database
price, month, and location. Caching will occur if he is in the
exploring module. *e user will be recommended by the
product via a content-based recommendation system.When
the user goes to the booking module, he will get his first and Security By Authentication Database
final hiring dates. *e total cost includes the equipment cost
and the travelling cost. Figure 8: Flow chart of the proposed approach.
*e emphasis of the study was on specific aspects of the
proposed method. *e very first step is to collect infor- 4. Results and Discussion
mation, and the second is to incorporate it into the process.
*e technical points in the first section of the report detailed In order to analyze the data, the farmers are divided into
the characteristics of 562 farmers from various Punjab re- three types: small, moderate, and large. Of the total 562
gions, as well as their interpretation based on various cat- farmers, 377 farmers fall under the type of small farmers; 179
egories. *e information gathered from actual farmers has fall under the type of moderate, and 6 farmers fall under the
been organized. large farmers type.
*e whole application would allow the development of a *e main issue of the farmers is that they are not sen-
method for determining farmer expectations and demands sitized with modern equipment and tools, and on the flip
for resource sharing and the rental of agricultural equipment side, they are falling under the burden of debt that forces
and machinery. *e steps for building a knowledge network them to commit suicide. In order to resolve this concern of
that combines artificial intelligence and machine learning in the farmers, we have developed a uberized model that deals
a standardized manner. with the renting and sharing of farming equipment. So, in
10 Journal of Food Quality
Table 3: Methodology/tools/instruments to be used.
Objective Sample size (number of participants) Instrument/tool/sample design, etc. to be used
1 562 Primary data collection, Google Form
(i) HTML language
(ii) CSS language
2 Smart tillage framework (iii) Django framework
(iv) Python 3.7
(v) Machine learning
3 Smart tillage mobile application
Client
Rent Page Select Equipment
by Image
Rent Equipment Form
Decision
Equipment Name
Tree
Fee
Machine
Sharing
Learning
Algorithm Available Till
Choose File
Figure 9: Systematic approach for renting equipment.
Interpretation of farmer’s type with interest in the mobile
application.
Out of these, all the small farmers, that is, 377 and 178
Client moderate and 1 large farmer are interested in smartphones.
Authentication *e concept of this parameter selection is reached to the
view of a custom hiring system so that farmers can rent and
hire their equipment accordingly.
Storing of Data
Predicting database on the 4.1. Basic Information. 4.2.Monthly Expense of Ranchers and
basic of location 6eir Productivity from Agriculture. Figure 13 depicts the
comparison of small, moderate, and large farmers on the
basis of their expenses, count, gain from farming, and
Pre-Processing number of agriculturists. Table 5 represents all types of
Accessing Database farmers who experienced their monthly expenditures in the
using location range of 10,000–25,000, 25,000–50,000, and more than
50,000. *ese expenses are labelled as A, B, and C under the
three different types: small, moderate, and large. For label A,
146 farmers fall in the small; 56 fall in the moderate; and 3
Security By Authentication Database farmers fall under the type of large farmers. For label B, 225
10: Location prediction approach. fall in the small; 120 fall in the moderate; and 3 farmers fallFigure under the large type. Similarly, in the case of C, 6 fall under
the small; 3 fall under themoderate; and no farmer lies under
order to run this uberized model, our first concern is to find the large type. However, the next part of Table 5 represents
how many farmers have their own smartphone. Table 4 farmer’s type with gain from farming and their number of
represents the out of these collected information: in case of counts. In order to consider this gain from farming is
small type out of 377 farmers, 155 farmers have smart- categorized into three groups: 50,000–2,00,000,
phones: out of total 177 moderate farmers, 144 have 2,00,000–5,00,000, and more than 5,00,000. *is income
smartphones; and out of 6 large farmers, 5 large farmers have from agriculture is labelled asD, E, and F. In the case of label
their smartphones. Figure 12 depicts the plot of D, 377, 19, and 1 farmers lie in the small, moderate, and large
Journal of Food Quality 11
Choose equipment based on
State District Village
Client
Hire Page
Product Distance
Duration
First & Last date of hiring Confirmation
Figure 11: Distance and cost approach.
Table 4: Type of farmers interested in mobile apps and smartphones.
Farmer group interested in mobile application Farmers using smartphone
Type of farmers Interested in app Type of farmers Mobile use
Small 376 Small 145
Moderate 177 Moderate 144
Big 1 Big 5
INTERESTED IN SMART PHONE
APP USE
SMALL SMALL
MEDIUM MEDIUM
LARGE LARGE
(a) (b)
Figure 12: Interpretation of type of farmers versus interested in mobile app.
types, respectively. For the label E, 1, 159, and 0 farmers fall (i) Plantation and fertilization
in the small, moderate, and large types. For the label, 0, 1, (ii) Latest tools
and 5 farmers fall in the small, moderate, and large types. (iii) Buying land
(iv) Education
4.3. Interpretation between Type of Farmers, Debt Cause, and Figure 14 represents that out of 377 small farmers, 179
6eir Interest to Hire Manufacturing Tools. Table 6 depicts are interested in loans, 198 are not interested in loans, and all
based on the three categories of the farmers: small, moderate, 179 are interested in hiring machinery. In the moderate type,
and large. Out of these all categories, some of the farmers are out of 179 farmers, 53 are availing loan, and all are interested
interested in loans, while others are not. Loan is one of themain in custom hiring; others 126 are not interested in loans, and
causes that force the farmers to commit suicide. From this 121 are interested in hiring machinery. Of the large type of
mentioned interpretation, this inference depicts that the max- farmers, out of 6, 4 farmers are interested in loans, and all are
imum farmers from different categories have taken loans to buy interested in hiring machinery, and the other 2 do not want
the latest tools. *is survey reached the result that farmers are to avail the loan, but they are interested in hiring machinery.
under the burden of loans due to the following reasons: Figure 14 also depicts the debt caused for the farmers. *is
12 Journal of Food Quality
SMALL-EXPENSE SMALL-INCOME
PER MONTH FROM AGRICULTURE
6 01
146
225
376
10000-25000 50000-200000
25000-50000 200000-500000
MORE THAN 50000
MEDIUM-EXPENSE MEDIUM-INCOME
PER MONTH FROM AGRICULTURE
3 1
56 19
120
159
10000-25000 50000-200000
25000-50000 200000-500000
MORE THAN 50000
LARGE -EXPENSE LARGE -INCOME
PER MONTH FROM AGRICULTURE
0
1 0
3 3
5
10000-25000 50000-200000
25000-50000 200000-500000
MORE THAN 50000
Figure 13: Farmers type versus expenses per month and gain from farming.
Table 5: Expense of ranchers and their productivity.
Type of farmers Monthly expenditure Number of agriculturist Gain from farming Number of agriculturist
10,000–25,000 146 50,000–200,000 376
Small 25,000–50,000 225 200,000–500,000 1
More than 50,000 6 More than 500,000 0
10,000–25,000 56 50,000–200,000 19
Moderate 25,000–50,000 120 200,000–500,000 159
More than 50,000 3 More than 500,000 1
10,000–25,000 3 50,000–200,000 1
Large 25,000–50,000 3 200,000–500,000 0
More than 50,000 0 More than 500,000 5
interpretation reached up to the mark that this is the reason collected data set of 562 farmers. *e average value is
why farmers are under suicide. represented by mean, and the standard deviation is used to
find the difference in value and the other range of values are
represented by maximum and minimum.
4.4. Feature Selection. *e overview of the data has been *e association between knowledge of new technologies
represented in Figure 15 that tells us about mean, standard and agricultural experience is seen in Figure 16. To facilitate
deviation, and minimum and maximum value of the this, farmers are classified into three categories: small,
Journal of Food Quality 13
Table 6: Interpretation between the type of farmers and they availed loan or not with reason and their interest to hire manufacturing tools.
Type of farmers Availed loan or not Purpose of debt Count of reason Interest to hire manufacturing tools.
New seeds 10
Latest tools 127
Small� 377 Yes� 179 Buying land 42 179
Education 0
No� 198 No debt 198 197
New seeds 0
Yes 53 Latest tools 28Moderate� 179 � Buying land 25 51
Education 0
No� 126 No debt 126 121
New seeds 0
Yes 4 Latest tools 4Large� 6 � Buying land 0 2
Education 0
No� 2 No debt 2 2
Small
250 Medium
200 198 140
120 126
150 100
127
100 8060
50 42 4020 28 25
0 10 0 0 0 0
(a) (b)
4.5
4 4
3.5
3
2.5
2 2
1.5
1
0.5
0 0 0 0
(c)
Figure 14: Relationship between the type of farmers and their reason and interest to hire manufacturing tools.
Data Description
70
60
50
40
30
20
10
0
land age family_members agri_experience
mean 25%
std 50%
max 75%
min
Figure 15: Overview of collected data.
14 Journal of Food Quality
New tools awareness, among farmers at scale
50
40
30
20
10
0
SMALL MEDIUM LARGE
farmer_category
aware_of_new_tools
YES
NO
Figure 16: New tools awareness with farmers’ type.
moderate, and large. *is result indicates that small farmers, farmers want to hire equipment, while 96.4% want to use a
despite their increased agricultural expertise, are still un- mobile application. We discovered a correlation between
aware of farming implements. It is used to represent sym- these two variables, which is that farmers who wish to hire
metrical data. However, as their agricultural expertise grows, equipment are particularly interested in mobile applications.
they become more conscious of new instruments. Large
farmers type includes that with the age of agriculture ex-
periences, all the farmers have the awareness of new tools. 4.5. Comparative Interpretation of the Machine Learning
*e relationship between two variables is measured by Algorithm. *ree machine learning classifiers are used for
correlation, which is a statistical term that quantifies how the interpretation: logistic regression, k-neighbors classi-
linearly related two variables are (meaning they change fiers, and a decision tree. *is research indicates how many
together at a constant rate). In the world of correlation, there farmers would want to use our technology. To summarize,
are two kinds. Both a positive and a negative association may the model was trained using training data that included 446
be found. In the case of positive correlation, the rise in observations and then was tested on a test data set of 116
dependent parameters will result in an increase in the in- farmers. By using the decision tree, we are obtaining the
dependent parameters as well, but in the case of negative highest accuracy of the model from our test observations of
correlation, the increase in dependent parameters will result 116 people. Figure 18 depicts the comparative analysis by
in a drop in the independent parameters. When the cor- different classifiers models. *e formula to calculate accu-
relation coefficient is between +1 and –1, it is referred to racy is as follows.
have a high correlation coefficient. *is matrix depicts the TP + TN
relationship between family members who were born on Accuracy � , (1)
land and those who have agricultural experience. *e first TP + TN + FP + FN
row (land) in Figure 17 illustrates the best association be- where TP, FN, FP, and TN represent the number of true
tween agricultural experience and land, and no correlation is positives, false negatives, false positives, and true negatives,
identified between land and family members. respectively.
Figure 17: Agriculture experience and land correlation. Logistic regression: out of 5 negative predictions, the
When it comes to ages, row 2 displays the best associ- model gave 1 false positive, and out of 111 positive pre-
ation with agricultural experience and vice versa. According dictions got all of them correct.
to the land, the third-row family member has the greatest K-neighbors classifier: out of 5 negative and 111 positive
relationship with it. predictions, this model got all of them correct.
Figure 17 shows the association between the interest in Decision tree classifier: out of 5 negative and 111 positive
machinery and mobile application. Totally 95.7% of the predictions, our tree model got all predictions correct.
agri_experience
Journal of Food Quality 15
Correlation Graph
1.0
land 1 -0.13 0.09 -0.48 0.8
0.6
age -0.13 1 0.0035 0.8 0.4
0.2
family_members 0.09 0.0035 1 -0.07 0.0
-0.2
agri_experience -0.48 0.8 -0.07 1
-0.4
land age family_members agri_experience
Figure 17: Correlation graph of land with different parameters.
Logistic Regression KNeighbors Classifier Decision Trees
100 100 100
No Interest 4 1 No Interest 5 0 No Interest 5 0
75 75 75
50 50 50
Interest 0 111 25 Interest 0 111 25 Interest 0 111 25
0 0 0
No Interest Interest No Interest Interest No Interest Interest
Predicted lable Predicted lable Predicted lable
Figure 18: Comparative interpretation by different classifier models.
After performing classification with different models tasks employing various machine learning techniques were
such as logistic regression, k-neighbors classifier, and de- developed as a result of exploratory and highly experimental
cision tree, it is found that decision trees and k-neighbors work; future work is expected to include new experiments
were the better performers; we have chosen decision trees as and tasks that exploit other sensor types and data sets, as well
our model of choice because of it being a nondistance-based as related method and result optimization, in order to meet
algorithm, its white-box approach, and excellent perfor- the great heterogeneity of agriculture companies and the
mance on our data set. hardware sensor market.
5. Conclusion Data Availability
*is research polled 562 Punjabi farmers. *e poll revealed *e data used are available from the corresponding author
many critical findings, including why farmers are not har- upon request.
vesting more. *e difficulties confronting agriculture were
examined in terms of farmer education, land ownership,
awareness, mobile phone use, debt burden, loan source, and Conflicts of Interest
interest in renting equipment. *e research found that
farmers lack awareness of current technology, which is *e authors declare that there are no conflicts of interest
extensively used in agricultural operations worldwide. An- regarding the publication of this paper.
other barrier is the financial status of farmers, especially
small and marginal farms. Farm management loans from References
commission agents or private firms progressively enslave the
farmers. Landlords continue to adopt traditional [1] L. M. Anka, “Agricultural research management in Nigeria:
manufacturing methods despite their ignorance of current historical antecedents and contemporary issues,” SSRN
production methods. *is project developed smart tillage, a Electronic Journal, pp. 1–35, 2014.
platform that enables farmers to rent and lease equipment. [2] R. Devkota, L. P. Pant, H. N. Gartaula et al., “Responsibleagricultural mechanization innovation for the sustainable
*e study also built a machine learning model. Decision development of Nepal’s hillside farming system,” Sustain-
trees are ideal for machine learning and tool and equipment ability, vol. 12, no. 1, p. 374, 2020.
hiring. It also tries to improve farmers’ quality of life by [3] G. *omas and J. De Tavernier, “Farmer-suicide in India:
decreasing labor-intensive tasks.*is thesis focuses on smart debating the role of biotechnology,” Life Sciences, Society and
farming via equipment sharing and leasing. *e proposed Policy, vol. 13, no. 1, 2017.
True lable
True lable
16 Journal of Food Quality
[4] J. E. Ashburner and J. Kienzie, Investment in Agricultural [20] S. K. Goyal, Prabha, S. R. Singh, J. P. Rai, and S. N. Singh,
Mechanization in Africa: Conclusions and Recommendations “Agricultural mechanization for sustainable agricultural and
of a Round Table Meeting of Experts, Food and Agriculture rural development in eastern U.P.—a review,” Agronomy for
Organization of the United Nations, Rome, Italy, 2011. Sustainable Development, vol. 2, no. 1, pp. 192–198, 2014.
[5] SyedMutahirMohiuddin, “Agricultural robotics and its scope [21] ICAR-CIAE, Feed 6e Future India Triangular Training (FTF
in India,” International Journal of Engineering Research, ITT) International Training Programme on, “Farm Mecha-
vol. V4, no. 7, pp. 1215–1218, 2015. nization of Small Farm” ICAR-CIAE, Bhopal, India, 2017.
[6] S. Saralch, V. Jagota, D. Pathak, and V. Singh, “Response [22] A. Kumar, V. Jagota, R. Q. Shawl et al., “Wire EDM process
surface methodology-based analysis of the impact of nanoclay parameter optimization for D2 steel,” Materials Today Pro-
addition on the wear resistance of polypropylene,” 6e Eu- ceedings, vol. 37, no. 2, pp. 2478–2482, 2021.
ropean Physical Journal - Applied Physics, vol. 86, pp. 1–13, [23] M. Rakhra and R. Singh, “Internet based resource sharing
Article ID 10401, 2019. platform development for agriculture machinery and tools in
[7] K. Mulungu and J. Ng’ombe, “Sources of economic growth in Punjab, India,” in Proceedings of the 2020 8th International
Zambia, 1970-2013: a growth accounting approach,” Econo- Conference on Reliability, Infocom Technologies and Optimi-
mies, vol. 5, no. 2, pp. 15–23, 2017. zation (Trends and Future Directions) (ICRITO), pp. 636–642,
[8] J. P. Aryal, D. B. Rahut, G. *apa, and F. Simtowe, “Mech- Noida, India, June 2020.
anisation of small-scale farms in South Asia: empirical evi- [24] F. Cossar, “Impact of mechanization on smallholder agri-
dence derived from farm households survey,” Technology in cultural production: evidence from Ghana,” in Proceedings of
Society, vol. 65, Article ID 101591, 2021. the Agricultural Economics Society Conference, pp. 1–72,
[9] X. Diao, F. Cossar, N. Houssou, and S. Kolavalli, “Mecha- Leuven, Belgium, 2019.
nization in Ghana: emerging demand, and the search for [25] B. Jyoti and N. S. Chandel, “Application of robotics in ag-
alternative supply models,” Food Policy, vol. 48, pp. 168–181, riculture: an indian perspective,” in Proceedings of the 8th
2014. Asian-Australasian Conference on Precision Agriculture,
[10] K. A. Mottaleb, T. J. Krupnik, and O. Erenstein, “Factors Ludhiana, June 2020.
associated with small-scale agricultural machinery adoption [26] D. Alfer’ev, “Artificial intelligence in agriculture,”Agricultural
in Bangladesh: census findings,” Journal of Rural Studies, and Lifestock Technology/A[rpIppTfyojla, vol. 4, no. 4,
vol. 46, pp. 155–168, 2016. 2018.
[11] A. Rahman, R. Ali, S. N. Kabir, M. Rahman, R. Al Mamun, [27] P. Samui, “Application of artificial intelligence in geo-engi-
and A. Hossen, “Agricultural mechanization in Bangladesh: neering,” Information Technology in Geo-Engineering, vol. 8,
statusand challenges towards achieving the sustainable de- no. 4, pp. 30–44, 2020.
velopment goals (SDGs),” AMA, Agricultural Mechanization [28] V. Bhatia, S. Kaur, K. Sharma, P. Rattan, V. Jagota, and
in Asia, Africa and Latin America, vol. 51, no. 4, pp. 106–120, M. A. Kemal, “Design and Simulation of Capacitive MEMS
2020. Switch for Ka Band Application,” Wireless Communications
[12] U. Paman, H. A. Wahyudy, and U. I. Riau, “Management and Mobile Computing, vol. 2021, Article ID 2021513, 8 pages,
system of small farm machinery hiring business for rice 2021.
farming operations in kampar region, Indonesia,” in Pro- [29] R. Ben Ayed and M. Hanana, “Artificial intelligence to im-
ceedings of the European Conference on Agricultural and prove the food and agriculture sector,” Journal of Food
Biosystems Engineering, *e Netherlands, November 2018. Quality, vol. 2021, Article ID 5584754, 7 pages, 2021.
[13] G. Acciaioli, “Environmentality reconsidered: indigenous to [30] A. Gulati and R. Juneja, “Farm mechanization in Indian
lindu conservation strategies and the reclaiming of the agriculture with focus on tractors,” SSRN Electronic Journal,
commons in central sulawesi, Indonesia greg,” People, Pro- 2020.
tected Areas and Global Change, pp. 401–430, NCCR, North- [31] G. Rastogi, S. Narayan, G. Krishan, and R. Sushil, “Deploy-
South, 2006. ment of cloud using open-source virtualization: study of vm
[14] X. Huang, V. Jagota, E. Espinoza-Muñoz, and J. Flores- migration methods and benefits,” in Big Data Analytics,
Albornoz, “Tourist hot spots prediction model based on pp. 553–563, Springer, Singapore, 2018, Advances in Intel-
optimized neural network algorithm,” International Journal of ligent Systems and Computing.
System Assurance Engineering and Management, 2021. [32] S. Saxena, S. Vyas, B. S. Kumar, and S. Gupta, “Survey on
[15] Z. Rozaki, “Decrease of agricultural land and industry growth in online electronic paymentss security,” in Proceedings of the
Special Region of Yogyakarta,” IOP Conference Series: Earth and 2019 Amity International Conference on Artificial Intelligence
Environmental Science, vol. 458, no. 1, Article ID 012033, 2020. (AICAI), pp. 756–751, IEEE, Dubai, February 2019.
[16] W. Li, X. Wei, R. Zhu, and K. Guo, “Study on factors affecting [33] S. O. Mezan, S. M. A. Absi, A. H. Jabbar, M. S. Roslan, and
the agricultural mechanization level in China based on M. A. Agam, “Synthesis and characterization of enhanced
structural equation modeling,” Sustainability, vol. 11, no. 1, silica nanoparticle (SiO2) prepared from rice husk ash
pp. 51–16, 2018. immobilized of 3-(chloropropyl) triethoxysilanea,” Materials
[17] C. Agency, Ex-ost Project Evaluation 2015, vol. 5, Package Today Proceedings, vol. 42, pp. 2464–2468, 2021.
I-5 Japan International Cooperation Agency, Japan, 2016. [34] S. Gupta, S. Vyas, and K. P. Sharma, “A survey on security for
[18] R. C. Gifford, Agricultural Mechanization in Development: IoT via machine learning,” in Proceedings of the 2020 Inter-
Guidelines for Strategy Formulation, Food and Agriculture national Conference on Computer Science, Engineering and
Organization of the United Nations, Rome, Italy, 1981. Applications (ICCSEA), pp. 1–5, IEEE, Gunupur, India, March
[19] J. Huang, K. Otsuka, and S. Rozelle,6e Role of Agriculture in 2020.
China ’ S Development: Past Failures; Present Successes and [35] C. Oduma and C. Ile, “ICTenabled education and ICTdriven
Future Challenges January 2007 the Role of Agriculture in e-learning strategies: benefits and setbacks in Nigeria edu-
China ’ S Development: Past Failures; Present Successes and cation system,” AFRREV STECH: An International Journal of
Future Challenges Jikun Huang, Keijiro Otsuka, 2014. Science and Technology, vol. 3, no. 2, pp. 108–126, 2014.
Journal of Food Quality 17
[36] CG. Okeke and S. Oluka, “A survey of rice production and
processing in South East Nigeria,” Nigerian Journal of
Technology, vol. 36, no. 1, pp. 227–234, 2017.
[37] M. Rakhra, R. Singh, T. K. Lohani, and M. Shabaz, “Meta-
heuristic and machine learning-based smart engine for
renting and sharing of agriculture equipment,”Mathematical
Problems in Engineering, vol. 2021, Article ID 5561065,
13 pages, 2021.
[38] R. Khan, N. Tyagi, and N. Chauhan, “Safety of food and food
warehouse using VIBHISHAN,” Journal of Food Quality,
vol. 2021, Article ID 1328332, 12 pages, 2021.
[39] R. Khan, S. Kumar, N. Dhingra, and N. Bhati, “*e use of
different image recognition techniques in food safety: a
study,” Journal of Food Quality, vol. 2021, Article ID 7223164,
10 pages, 2021.
[40] M. Rakhra and R. Singh, “Smart data in innovative farming,”
Materials Today Proceedings, vol. 2021, 2021.
[41] N. Hatibu, “Investing in agricultural mechanization for de-
velopment in East Africa,” Mechanization for Rural Devel-
opment: A Review of Patterns and Progress from around the
World, Vol. 20, Food and Agriculture Organization, Rome,
Italy, 2013.
[42] R. Kumar, S. Yadav, M. Kumar, J. Kumar, and M. Kumar,
“Artificial intelligence: new technology to improve Indian
agriculture,” International Journal of Chemical Studies, vol. 8,
no. 2, pp. 2999–3005, 2020.
[43] J. Sumberg, T. Yeboah, J. Flynn, and N. A. Anyidoho, “Young
people’s perspectives on farming in Ghana: a Q study,” Food
Security, vol. 9, no. 1, pp. 151–161, 2017.