agronomy

Article
A Smart Decision System for Digital Farming
Carlos Cambra Baseca 1 , Sandra Sendra 2,3, * , Jaime Lloret 3 and Jesus Tomas 3
1 Grupo de Inteligencia Computacional Aplicada (GICAP), Departamento de Ingeniería Civil,
Escuela Politécnica Superior, Universidad de Burgos, 09006 Burgos, Spain; ccbaseca@ubu.es
2 Department of Signal Theory, Telematics and Communications, Universidad de Granada,
18071 Granada, Spain
3 Instituto de Investigación para la Gestión Integrada de zonas Costeras, Universitat Politècnica de València,
46730 Valencia, Spain; jlloret@dcom.upv.es (J.L.); jtomas@upv.es (J.T.)
* Correspondence: ssendra@ugr.es; Tel.: +34-696-322-321




Received: 26 January 2019; Accepted: 23 April 2019; Published: 27 April 2019


Abstract: New technologies have the potential to transform agriculture and to reduce environmental
impact through a green revolution. Internet of Things (IoT)-based application development platforms
have the potential to run farm management tools capable of monitoring real-time events when
integrated into interactive innovation models for fertirrigation. Their capabilities must extend to
flexible reconfiguration of programmed actions. IoT platforms require complex smart decision-making
systems based on data-analysis and data mining of big data sets. In this paper, the advantages are
demonstrated of a powerful tool that applies real-time decisions from data such as variable rate
irrigation, and selected parameters from field and weather conditions. The field parameters, the index
vegetation (estimated using aerial images), and the irrigation events, such as flow level, pressure level,
and wind speed, are periodically sampled. Data is processed in a decision-making system based on
learning prediction rules in conjunction with the Drools rule engine. The multimedia platform can be
remotely controlled, and offers a smart farming open data network with shared restriction levels for
information exchange oriented to farmers, the fertilizer provider, and agricultural technicians that
should provide the farmer with added value in the form of better decision making or more efficient
exploitation operations and management.

Keywords: smart farming; IoT farming; agriculture smart system; WSN agriculture; digital farming

1. Introduction
Precision agriculture (PA) consists of managing crops by observing, measuring, and acting against
the many variable factors that affect them. Systems for PA can be based on satellite navigation
systems or terrestrial systems for geographic information and sensors located in the plot. These
systems collect information to be used to make decisions with greater precision and to optimize crop
yields. PA contributes to producing a more efficient and ecological agriculture. It allows saving
on phytosanitary products, fertilizers, and reducing the amount of nitrogen used. PA reduces costs
and optimizes agriculture. It also reduces the environmental impact by optimizing the use of water,
pesticides, and machinery fuel; thus, greater production is obtained with fewer resources.
In order to develop efficient PA systems, there is an increasing trend towards using smart decision
systems (SDS). The acceptance of SDS solutions in many industrial sectors that specialize in agriculture
is limited by the fact that building an SDS requires a significant investment of time and knowledge. If it
is to benefit from technological advances, agricultural activity has therefore to absorb not only technical
expertise, but also skilled knowledge of engineering. The Internet of Things (IoT) [1] can be used
for that purpose, despite several immense challenges linked to big data analytics, cloud computing,
and new business models in SDS.

Agronomy 2019, 9, 216; doi:10.3390/agronomy9050216 www.mdpi.com/journal/agronomy

Agronomy 2019, 9, x FOR PEER REVIEW 2 of 21

knowledge. If it is to benefit from technological advances, agricultural activity has therefore to

absorb not only technical expertise, but also skilled knowledge of engineering. The Internet of
Agronomy 2019, 9, 216 2 of 19
Things (IoT) [1] can be used for that purpose, despite several immense challenges linked to big data
analytics, cloud computing, and new business models in SDS.
Thesefeatures
These featurestypically
typicallyinclude
include intelligent
intelligent assistance
assistance withwith
the the implementation
implementation of technology
of technology and
and
its its maintenance
maintenance and use.
and use. The concept
The concept of smart
of smart farming
farming is summarized
is summarized in Figure
in Figure 1, together
1, together withwith
the
the management cycle as a cyber-physical system, leading eventually to smart
management cycle as a cyber-physical system, leading eventually to smart online devices capable of online devices
capable of controlling
controlling a range systems.
a range of farming of farming systems.

Figure 1.1.The
Figure Thecycle
cycleof
of smart farmingdata
smart farming data management.
management.

Sundmaeker
Sundmaeker [2] [2] reported
reported rapid
rapid developments
developments in in the
the IoT
IoT and
and cloud
cloud computing,
computing, applied
applied in in this
this
paper
papertotoa field known
a field known as smart farming.
as smart Algorithmic
farming. training
Algorithmic processes
training for decision-making
processes support
for decision-making
are highlyare
support complex
highlytasks, with many
complex problematic
tasks, with many issues found in models
problematic issuesthat are automatically
found in models inducedthat are
from data through
automatically big data
induced fromapplications
data through [3]. big
Perhaps the most problematic
data applications [3]. Perhapsis thethe
value
most chain that refers
problematic is
to
thethevalue
sequence
chainofthat
activities
refersfrom
to thedatasequence
capture toofdecision
activitiesmaking,
from involving
data capture datatomarketing,
decision decision
making,
trees, and rule
involving datainjection
marketing, procedures.
decisionThe advantage
trees, and ruleofinjection
these models is that they
procedures. Theconsist
advantageof individual
of these
units
models of knowledge
is that they (rules)
consist that can be separately
of individual units of viewed,
knowledge evaluated,
(rules) thatprocessed, deleted, and
can be separately even
viewed,
edited. In a business process [4], for example, work laid out in a set of logically
evaluated, processed, deleted, and even edited. In a business process [4], for example, work laid out related tasks can be
performed to achieve
in a set of logically a defined
related tasksbusiness outcome. to achieve a defined business outcome.
can be performed
Big
Big data
data represents
represents the theinformation
information assets assets that
that are
arecharacterized
characterized by byhighhighvolumes,
volumes,high-speed
high-speed
processing
processing and and aa variety
varietyof ofinputs.
inputs. Processing
Processing such such information
information requires
requires specific
specific technology
technology and and
analytical
analyticalmethods
methods[5] [5]for
fortheir
theirtransformation
transformationinto intoaavalue
valuechain.
chain.
This
This paper
paper presents
presents aa complete
complete implementation
implementation of of aa smart
smart decision
decision support
support system
system prototype,
prototype,
which
whichautomatically
automaticallylearnslearnsdecision
decisionrulesrules from
fromdata, thereby
data, thereby permitting
permitting thethedomain
domainexpert to edit
expert the
to edit
resulting rule base,
the resulting rule which can apply
base, which can the
applyrulesthe
to achieve
rules toincoming objects. Asobjects.
achieve incoming agriculture consumes
As agriculture
about
consumes70% of all fresh
about 70% water
of all resources,
fresh water oneresources,
important one aspect of green aspect
important farming ofisgreen
economical
farming andis
efficient
economicaluse and
of water [6]. use
efficient Water consumption
of water [6]. Water percentages
consumption canpercentages
be decreased through
can efficient
be decreased water
through
management,
efficient waterwhere irrigationwhere
management, needs irrigation
are adjusted needsto supply.
are adjustedDecision trees generate
to supply. Decisionrules to enhance
trees generate
the
rulesuse
to of irrigation
enhance the water, fertilizers,water,
use of irrigation pesticides, etc. A
fertilizers, web platform
pesticides, etc. Acan webconvert
platform thecanresults
convertof
data-based
the results of decision making
data-based into user-friendly
decision public information
making into user-friendly public that is only posted
information that is following
only posted a
following
decision a decision
maker review maker
process.review
The majorprocess. The major
advantage advantage
is integration intoisa unique
integration into to
platform a control
unique
platformdecisions
farming to control farming
such decisions
as irrigation systemsuchcontrol,
as irrigation systempesticides,
fertilization, control, fertilization,
and an openpesticides,
data network, and
an inopen
all one.data network,
In addition, ourallsystem
in one.includes
In addition, our system
rules based includes rules
on variable-rate based
irrigation on variable-rate
(VRI) [7]. VRI is a
new technique that allows optimization of irrigation application, considering the status of field and
weather. In most cases, these systems are implemented by using a center pivot irrigation system that
Agronomy 2019, 9, 216 3 of 19

can reduce the total irrigation water volume required to grow field crops. According to Reference [8],
this kind of system is able to reduce irrigation water use by 8% compared to uniform irrigation
application. Considering this idea, we designed [9], developed, and tested an intelligent system for
irrigation control of urban lawns. The system is based on the use of a multisensor node composed by
humidity and temperature for soil and air, as well as a rain sensor. The multisensor node is controlled
by an intelligent algorithm that takes into account the real time values provided by the sensors and the
stored data of previous measurements. The intelligent algorithm is responsible for analyzing the data
and deciding on the amount of water to be used in a given area. Using actual annual meteorological
values of a city with different water requirements, the system’s operation was simulated. The results
showed that for a landscaped area of about 140 ha, we could save around 6% of the irrigation water,
which would be equivalent to about 22 million liters of water. Finally, the complete system behaves
as a collaborative platform, taking into account the experience of other users and previous events
introduced into the system. A system with these features can help farmers to enhance the activity
sustainability, at the same time, that a more controlled use of chemical products and natural resources
will protect our environment and groundwater resources.
This study is organized as follows. Section 2 will present the reasoning behind the study and
related works. Section 3 will describe the individual steps of the preparation process of a classification
rule set. Section 4 will then detail the software components of the engine and, in Section 5, the web
platform and the processing of open data will be outlined. Finally, in Section 6, the conclusions will
present the advantages of the demonstrated model and future avenues of work will be suggested.

2. Related Works
The generation of “business rules” from data-mining results is an emerging research area. To the
best of our knowledge, the only publicly available software solution to business rule learning is
Rule Learner, which forms part of the Open-Rules Decision Management System. According to
the SOA paradigm, software should function as cooperating services, as described in a previous
work [1]. However, there have been several experimental systems developed in the machine learning
community with related functionality. The Drools system [3], used in our solution, is a business rules
management system that combines user needs and constraints in the search space with interactive
mining. The interactive nature of both systems, MIME and Drools, can help to address the excessive
number of rules that typically form the output of rule learning. Additionally, in Reference [4],
we showed that the database-pruning algorithm can significantly reduce the number of rules that
Drools outputs, without adversely impacting on the quality of the classifier. The smart farming decision
system proposed in this paper is called PLATEM. Drools is the core of this system, which is integrated
in a single web application. The user can launch multiple farm functionalities, export the results that
are selected, and apply the rules on test data in auto mode. The rule-learning algorithm used in Drools
for building the classifier from association rules is evaluated and described in detail in the following
sections. The software solution is presented and implemented in demo form. Its main contribution,
with respect to the previous results in References [5,6], is in the integration of the periodically sampled
indoor and outdoor irrigation system linked to a wireless sensor network, the SDS, and the web,
which together form the complete PLATEM system.
This pervasive paradigm [10] of the Internet of Things (IoT) is to increase the value of the
information generated by the number of interconnections between people and gadgets, denoted by
things, and to transform of the processed information into knowledge for the benefit of mankind
and society.
The architecture of the IoT unit [11] is built from a man-like neural network (MLN) model and
its modified model. Ubiquitous IoT refers to the global IoT and its integration in multiple-unit IoTs.
Its architecture employs a social organization framework (SOF) model. The models for future IoTs are
not only helpful to interpret the relationship between IoT and the real world, but are also beneficial for
the implementation of IoT in its current form.
Agronomy 2019, 9, 216 4 of 19

Vazquez et al. explored [12] the different criteria for designing IoT architectural solutions, together
with illustrative examples of prototypes that have implemented these approaches. Likewise, Misra [13]
proposed a community detection scheme in an integrated Internet of Things (IoT) and social network
(SN) architecture. The paper follows a graph mining approach to solve the problem in a complex
network of IoT and SN. There are a few studies in the literature on community detection in SNs;
however, to the best of our knowledge, there are no specific studies that address the integration of IoT
and SN architecture.
Atzori [14] analyzed the major opportunities arising from the integration of social networking
concepts in the Internet of Things, presenting the mainstream research activities and pointing to the
most critical technical challenges.
Smart farming technology is continuously reinventing new business models using real-time data
with automated data-acquisition devices. The sector needs open infrastructure between technologies,
because of a concern that key data processing techniques may become the exclusive domain of
multinational AgTech corporations. In the current market, applications developed by AgTech
corporations and AgBusiness companies, with patented specifications, are commonly found for
machine manufacturing processes. There are also applications that function exclusively with irrigation.
These underlying reasons prompt us to work towards integrated components in technology, both for
device interaction, such as fertirrigation controllers, and for data processing, to produce information
for greater agricultural efficiency. Basing our work on agricultural knowledge, and in consultation
with individual farmers and agronomists, the focus of this work is on the development of a platform
that integrates the core control operations and that monitors data on crop yields, in order to build
on synergetic results from multidisciplinary expertise. PLATEM PA is a combination of a smart
fertirrigation manager application that displays historical data, and social networking forums that
share productive data.
The main complexity of such applications is that they require collaboration between many different
elements with different contributions to the data values and related decisions over the consequential
actions. An overview of current European applications in PA is presented below, identifying the major
functions of each one in comparison with PLATEM PA.
Table 1 shows the aspects that PLATEM introduces in relation to the different elements of other
smart farming platforms. The integration of several tools in the main user profile is central to PLATEM,
enabling the development of a social network between professionals in different areas where they can
discuss data acquisitions, notifications, and crops risks. The ultimate goal is an open communication
protocol and open data platform between large precision agriculture technologies, oriented towards
indoor and outdoor VRF and VRI.
Smart-Akis [15] represents the application of modern information and communication technologies
(ICT) in agriculture, leading to what can be called a third Green Revolution.
Agrivi [16] is a crop management software for crop planning, monitoring, and analysis. Advice
and relevant data on tillage, sowing, fumigation, fertilization, irrigation, and harvesting, and almost
all other activities, can be accessed with a few clicks. In addition, volumetric calculations, and costs
and hours of work are suggested for each activity. The processes, based on best practices gathered in
relation to over 100 crops, are designed to improve productivity.
The main objective of the sigAGROasesor [17] project is the development of decision support tools
for the agricultural sector, through a web platform for online services to farmers, assisting efficient,
effective, and competitive farming activities, based on environmental and social sustainability.
Agronomy 2019, 9, 216 5 of 19

Table 1. Smart farming platforms comparison.

Business Process Alarm Notification Communication Protocol
Technology Key Objective Data Management Social Network Postings & Open Data
Module Module? Open or Private Protocol
YES YES
APOLLO Controlling crop growth and conditions VRI estimation YES Crop Growth Monitoring and Crop NO NO
module Yield estimation
YES
SMART AKIS Management Information NO NO Flexible and adaptive platform of Smart NO YES
farming Technologies
YES
SIG AGRO ASESOR Crop SIG Manager YES YES NO YES
VRF &VRI modules
YES
YES
Agrivi Plan, monitor and analyze crop activities Crops seasons & Pest YES NO NO
Crop data & inputs cost management
monitor alert
Intelligent irrigation programmer with YES YES
Smart Water-Saving NO NO NO
sensory connectivity Soil moisture data acquisition Private Protocol
Management Information with an Business-Rule Engine
Notification module Communication Protocol Implemented Farmers and providers access on-line
intelligent VRF & VRI Based on data Historical data acquisition is represented
PLATEM PA in Multimedia based on Open Standard protocol forums to post results, crop failures,
Open Data, Farmers/Providers & acquisition and in graphs and downloaded files
platform in VRF & VRI devices alerts, crop yield, . . .
Social network historical data
Agronomy 2019, 9, 216 6 of 19

In relation to a smart water-saving irrigation system [18], X, Kehui et al. published a scientific
paper based on an intelligent irrigation programmer with sensory connectivity and 433 MHz ISM
communication. The research focused on applications in precision agriculture, using a wireless
humidity sensor. A network of wireless sensors was configured to monitor the moisture content and
the amount of water in the field soil samples. The architectures of both the wireless sensor network and
the intelligent system were based on the network of sampled irrigation controllers. The irrigation test
was performed with real-time humidity data and expert inputs. A feasible system was demonstrated in
the rice cultivation process, and a good exploration in the field of precision agriculture and sustainable
water resources.
The APOLLO project [19] shares similarities with the PLATEM PA project proposal design.
The technology was analyzed in depth for the consolidation of the PLATEM PA system, improving
its potential for use with other innovative ultra-low power communications and dynamic routing
protocols, and in the latest business rule engine models applied to the multimedia platform.
APOLLO aims to bring the benefits of precision agriculture to farmers through affordable
information services, making extensive use of free and open Earth observation data, such as those
provided by the EU Copernicus program. These services are intended to assist agricultural decision
making, while observing crop growth and conditions, providing advice on irrigation and tilling,
and providing crop estimations. Ultimately, these interventions are designed to reduce agricultural
inputs and increase competitive production levels and benefits.
As Table 1 shows, the novelty of our platform is that PLATEM PA can be considered as a
collaborative tool where farmers can post their experiences. It is able to monitor the different
parameters of soil and environment to better growth of crops. In addition, PLATEM PA is able to
improve their decision, regarding to actions to be performed over the field, taking into account previous
stored information and farmers posts. Finally, its operation is based on the use of an intelligent Virtual
Routing and Forwarding (VRF) and Virtual Router Instances (VRI). PLATEM PA therefore represents a
competitive sample of European supplier networks focused on Precision Agriculture management and
a multimedia platform with basic group tools to control and monitor data and relations between all
participants for sharing results.
The PLATEM system presented in this paper can be used to accomplish the task through a
chain of web-based graphical tools, running on standard BRMS software with open-source formats.
Our technological solution is capable of adapting “high-tech tools” to be used by farmers, many of whom
may have little or no technical hi-tech expertise. One problem is the necessary automatization of several
systems (irrigation controller, fertirrigation pump, pH sensor node, . . . ) from different manufacturers
that need to be adapted to specific communication protocol. PLATEM PA combines several data
integration processes in a single easy-to-use platform with a standard communication protocol.
Although the final system will be composed by both hardware part (in charge of collecting
data from the field) and software part (in charge of processing data), this paper is focused on
data computation and not in the agronomic side and to perform the tests we will take a data base
with the needs of fertilization, weekly irrigation liters and different Kc for corn varieties of alfalfa,
barley and wheat.

3. Rule-Based Preparation Work

The first step to develop our management platform was to know the variable inputs the system
has and how they have to be processed by using the rules. Taking into account that the final goal is
to enhance the sustainability and competitiveness of the activity, the system also includes business
process management (BPM) and business rules. It is also important to define the platform architecture.
This section therefore presents the server-based decision-making structure for decision making on
irrigation device settings, which processes data inputs on edaphic and environmental conditions,
images of crop growth, and crop status.
Agronomy 2019, 9, 216 7 of 19

The objective of this server-based decision-making structure is the integration of a BPMS and a
business rules management system. A middleware data-exchange system serves as a link between
both. The middleware that serves to relay data from Bonita BPM and Drools includes the following
developments:

• Performance of an integrated architecture for a business rules management system and a business
rule management system (BRMS).
• Dialogue through the intermediate middleware component that is responsible for the data
management model and the rule-based activities.

Bonita Soft provides connectors to interact with the Drools manager that connect with the Drools
API Engine to run the execution of a certain rule, in order to obtain results that conclude with the
previously triggered decision-making process.
The process of preparing a rule base in Drools can be divided into several consecutive steps
that are presented in Figure 2, wherein several layers are created: data preparation, association rule
learning, rule selection, classification model testing, rule set editing, and deployment of rules.
Agronomy 2019, 9, x FOR PEER REVIEW 7 of 21

Start

Irrigation
Crop data Weather data
status data

Parsing data

Business Data
Processes Base

Inject new Historical

Analysis & Mining
rule data

Results
actions values

Variable rate Variable rate

irrigation fertilization

End

Figure
Figure 2. Farming
2. Farming smart
smart decisionsystems
decision systems (SDS)
(SDS)flow
flowdiagram.
diagram.
Data are collected for the smart decision system, (soil sensors, leaf sensor, etc.) weather and
These steps, which can be performed with a standard web browser, are described below in
environmental conditions, and machinery (pivot irrigation, controllers, pumps, etc.) from a range of
Figure 2: devices, and the information is then transmitted through the network coordinator to the
Data are collectedThese
middleware. for the
data,smart decision system,
once pre-processed (soil sensors,
and formatted, are sentleaf
to sensor,
the rule etc.)
engineweather
for and
rule-based
environmental processing
conditions, andto produce
machinery relevant results.
(pivot Historical controllers,
irrigation, database information
pumps, may be required
etc.) from a range of
for some rules.
devices, and the information is then transmitted through the network coordinator to the middleware.
Having obtained the results, the coordinator module communicates with the appropriate
These data,services
once pre-processed and formatted,
(e.g., pumps, irrigation controllers,are
etc.),sent totheir
sends the rule engine for rule-based
recommendations processing to
via virtual routing
produce relevant results.(VRF)
and forwarding Historical database
and virtual information
router instances (VRI), may be required
and reports either to for some profile
the farmer rules. or
Havingdirectly
obtainedto systems installed
the results, theoncoordinator
the farm for module
automatedcommunicates
implementation,with
if thethe
system device is services
appropriate
configured to do so. The type of setting and the basic information for a range of settings—i.e., turn
(e.g., pumps, irrigation controllers, etc.), sends their recommendations via virtual routing and
on, watering time, turn off—are configurable by the farmer with appropriate permissions for
automatic SDS adjustment.

3.1. Data Preparation

The user starts with a dataset for training the classification model. Typically, the dataset is
divided into a training and a testing part. The design of data management and processing
procedures, associated with a long-term wireless monitoring system, can join all these farming
Agronomy 2019, 9, 216 8 of 19

forwarding (VRF) and virtual router instances (VRI), and reports either to the farmer profile or directly
to systems installed on the farm for automated implementation, if the system device is configured to
do so. The type of setting and the basic information for a range of settings—i.e., turn on, watering time,
turn off—are configurable by the farmer with appropriate permissions for automatic SDS adjustment.

3.1. Data Preparation

The user starts with a dataset for training the classification model. Typically, the dataset is
divided into a training and a testing part. The design of data management and processing procedures,
associated with a long-term wireless monitoring system, can join all these farming systems and data
acquisition elements
Agronomy 2019, 9, x (see backend
FOR PEER REVIEWstructure in Figure 2). The data from WSN is stored 8inofa21MySQL

database via middleware through a management process and a communication socket. The user can,
socket. The user can, for instance, upload a profile of crops and fields that will be stored in the
for instance, upload a profile of crops and fields that will be stored in the MySQL database.
MySQL database.
The weather forecastforecast
The weather updates from afrom
updates weather serverserver
a weather can then
canbe added,
then including
be added, field coordinates
including field
and responses with forecasts in XML, which will also be stored in MySQL as the weather
coordinates and responses with forecasts in XML, which will also be stored in MySQL as the weatherprofile.
Data from aerial images (drone or satellite) may be manually uploaded for users via web view
profile.
Data from
(Image and NDVI indexaerial images (drone or satellite) may be manually uploaded for users via web view
file).
(Image and NDVI index file).
The general structure of the system is shown in Figure 3, where the server layers are described:
The general structure of the system is shown in Figure 3, where the server layers are described:
database, middleware, Server Web, BPM, and responsive web view.
database, middleware, Server Web, BPM, and responsive web view.

Figure 3. Farming SDS backend structure.

Figure 3. Farming SDS backend structure.
The system supports several types of pre-processing. Middleware prepares information to
The system supports several types of pre-processing. Middleware prepares information to store,
store, and the user can do pre-processing using intervals of determinate values. The user can then
and the merge
user can doatpre-processing
values using intervals of determinate values. The user can then merge
different intervals.
values at different intervals.
3.2. Association Ruler Learner
3.2. Association Ruler Learner
As a rule-learning algorithm, the current version uses a simple procedure implemented in the
As system. The user algorithm,
a rule-learning is required totheinput a defined
current versionruleuses
pattern for theprocedure
a simple crop and field profile to in the
implemented
commence the associative rule learning process in Drools. The user then selects the attributes from
system. The user is required to input a defined rule pattern for the crop and field profile to commence
attributes and selects a list in a rule pattern container DB. By default, the attributes are connected
the associative rule learning process in Drools. The user then selects the attributes from attributes and
with a conjunction, but the system also supports disjunction and negation connectives.
selects a list New
in a rule
rulespattern
may becontainer
introducedDB.forBy default,
each theinattributes
attribute are connected
the rule pattern as a set with
of its avalues
conjunction,
but the system also
considered supports
during disjunction
the matching and negation connectives.
process.

3.3. Rule Selection

The user can then change the parameters of the rule-learning task, typically by introducing
changes to the rule pattern, sometimes with a different location or season; some values will therefore
Agronomy 2019, 9, 216 9 of 19

New rules may be introduced for each attribute in the rule pattern as a set of its values considered
during the matching process.

3.3. Rule Selection

The user
Agronomy 2019, can then
9, x FOR change
PEER REVIEW the parameters of the rule-learning task, typically by introducing 9 of 21
changes to the rule pattern, sometimes with a different location or season; some values will therefore
need
need adjusting.
adjusting. The The rules
rules areare saved,
saved, grouped
grouped byby data
data mining
mining tasks,and
tasks, andthe
therule
rulecontainer
containerupdates
updatesthe
the attributes of
attributes of each one. each one.
ForFor classification,ititisisessential
classification, essentialthat
that the
the rules
rules entered
entered on
on the
the clipboard
clipboardbebechosen
chosentotomaximize
maximize
data accuracy. The accuracy is computed either on the training dataset
data accuracy. The accuracy is computed either on the training dataset or on a separateor on a separate test dataset.
test dataset.
The system exports the rule results saved in the Rule Clipboard to the MySQL, where middleware is
The system exports the rule results saved in the Rule Clipboard to the MySQL, where middleware is
then able, for example, to send reconfiguration instructions to the irrigation controller. The system
then able, for example, to send reconfiguration instructions to the irrigation controller. The system can
can also be used to post user friendly data in web view, informing users of the results of certain
also be used to post user friendly data in web view, informing users of the results of certain rules.
rules.
3.4. Rule Editor
3.4. Rule Editor
The results can be suitably combined (association rules) for the construction of a classification
The results can be suitably combined (association rules) for the construction of a classification
model selected from multiple data-mining tasks. The user can export/import rules from the Rule
model selected from multiple data-mining tasks. The user can export/import rules from the Rule
section into the “business rules” base. For practical purposes, the rules are internally saved in a JSON
section into the “business rules” base. For practical purposes, the rules are internally saved in a
format.
JSON The system
format. The then converts
system the rules
then converts theinto the
rules Drools
into DRL format.
the Drools DRL format.
The user can display the rules saved in the “business rules”
The user can display the rules saved in the “business rules” knowledge
knowledgebasebase
andand
editedit
them using
them
a web
usinginterface. An irrigation
a web interface. schedule
An irrigation business
schedule process
business is displayed
process in Figure
is displayed 4. 4.
in Figure

Figure
Figure4.4.Diagram
Diagramof
ofbusiness
business process management(BMP)
process management (BMP)process.
process.

4. Software Components
4. Software Components
OnceOnce thetheplatform
platformarchitecture
architectureand and the
the rules
rules association
association hadhadbeen
beendefined,
defined,it itwas
wasrequired
required to to
develop the software part that would
develop the software part that would implement our implement our web platform. To perform that,
platform. To perform that, this section this section
presents
presents the the
implementation
implementation of server rules in
of server the Drools
rules in the engine. The server
Drools engine. Thehas three has
server mainthree components.
main
Thecomponents.
first one is an Theapplication
first one isthatan isapplication
able to register
that isthe external
able sensor
to register data
the in thesensor
external system.data A device
in the or
system. Asimply
application device registers
or application simply
as a data registers
source as a data
by sending source by via
information sending information
socket communication via socket
to the
communication
middleware, which tothen
the middleware,
prepares thewhich data inthen preparesformat,
a specified the data in a specified
depending format,
on the type depending
of sensor.
onThethe type
system of sensor.
architecture is divided into the following layers:
The system architecture is divided into the following layers:
1. User interface: enables farmers, providers, and technics to interact with the system and execute
1. User interface: enables farmers, providers, and technics to interact with the system and execute
computerized workflow activities. To do so, it invokes operations of the interfaces published by
computerized workflow activities. To do so, it invokes operations of the interfaces published by
the business layer. It is a set of HTML and Php pages hosted on an Apache web server that are
the business layer. It is a set of HTML and Php pages hosted on an Apache web server that are
displayed in a web browser.
displayed in a web browser.
2. 2. Business
Businesslayer:
layer: responsible
responsible for for making calculations, queries,
making calculations, queries,and
andinvoking
invokingthe theexecution
execution of of
business
business rules.
rules.ToTodo dothis,
this,ititaccesses
accesses the
the data layer and
data layer and thetherules
rulesservices
serviceslayer.
layer.It Itis is a set
a set of of PHP
PHP
pages hosted on an Apache
pages hosted on an Apache web server. web server.
3. 3. DataData layer:
layer:inincharge
chargeofofmanaging
managing the the system’s database,which
system’s database, whichcontains
containsinformation
information about
about allall
thethedata
dataofofthetheprocess
processand andits itsstages
stages for
for each
each field. ItIt provides
providesinterfaces
interfacessosothat
thatthe the business
business
layer
layer can can access
access it. it.
ToTo implement
implement thisthis layer,
layer, the the MySQL
MySQL database
database management
management system systemwaswasused.
used.
4. Service layer of business rules: exposes interfaces through web services to business rules. It is
invoked from the business layer and executes the rules contained in the rules layer. It is made
up of web services, programmed in Java, which run on a Tomcat web server.
Agronomy 2019, 9, 216 10 of 19

4. Service layer of business rules: exposes interfaces through web services to business rules. It is
invoked from the business layer and executes the rules contained in the rules layer. It is made up
of web
Agronomy 2019,services, programmed
9, x FOR PEER REVIEW in Java, which run on a Tomcat web server. 10 of 21
5. Rules layer: makes it possible to manage business rules, for which it provides interfaces to the
5. rules
Rulesservices
layer: makes
layer. it
Topossible
implement to manage business
this layer, rules,source,
a free, open for which it provides interfaces
java-developed BRMS was toused.
the
rules services layer. To implement
The BRMS is deployed on a Tomcat web server. this layer, a free, open source, java-developed BRMS was
used. The BRMS is deployed on a Tomcat web server.
Figure 5 shows the architecture of BRMS used by our platform. As we can see, the main component
Figure 5 shows the architecture of BRMS used by our platform. As we can see, the main
of our BRMS is an Apache web server, which uses the data stored in our database (DB). In order to
component of our BRMS is an Apache web server, which uses the data stored in our database (DB).
enhance our server, we used a Tomcat web server. Tomcat is an extension of Apache that works as a
In order to enhance our server, we used a Tomcat web server. Tomcat is an extension of Apache that
container of servlets, and can help us to include new functionalities to our server. Using the servlets,
works as a container of servlets, and can help us to include new functionalities to our server. Using
we can extend applications held in web servers to be seen as JAVA Applets. To generate and manage
the servlets, we can extend applications held in web servers to be seen as JAVA Applets. To generate
the different rules we need to enhance the system performance, we used Drools, a common tool used
and manage the different rules we need to enhance the system performance, we used Drools, a
for managing business rules that we have adapted to our application. These rules are sent to the
common tool used for managing business rules that we have adapted to our application. These rules
Tomcat
are sentweb server
to the through
Tomcat web the API.through
server These rules are sent
the API. Thesetorules
the Apache
are sentweb server,
to the which
Apache webcombines
server,
them
which combines them with the data stored in the DB. Finally, the users can see the results ofusing
with the data stored in the DB. Finally, the users can see the results of these decisions by thesea
web browser
decisions by and
using surfing
a webthe different
browser andoptions
surfing the
the platform
different offers.
options the platform offers.

MySQL
Java
DB
Tomcat Web
Apache Web
Web Browser Server Drools
Server
Views Rules Components API

Figure
Figure 5. System
5. System architecturethat
architecture that integrates
integrates Drools
Droolsinto
intothe workflow.
the workflow.

The
Thefollowing
followingsection
section introduces
introduces the
the Drools
Drools management based on
management based on the
the Rete
Rete pattern-matching
pattern-matching
algorithm
algorithm[20].
[20]. It
It provides
provides the
the basis for aa more
basis for more efficient implementation that
efficient implementation that can
can check
checkeach
eachrule
rule
against facts in a knowledge base, firing the rule if necessary. Figure 6 shows the *.drl file
against facts in a knowledge base, firing the rule if necessary. Figure 6 shows the *.drl file where where basic
rules
basicfor operating
rules with Drools
for operating are located.
with Drools are located.
There are several benefits of this algorithm, such as reducing or removing redundancy and efficient
memory erasure when the facts are retracted. The rule container refers to the part of the database
where the rules of the system are saved. There are internal entities that contain the parameter rules of
each individual rule set: system irrigation functionality, fertilization, pest control, agronomy parameter,
and weather; there is a rule for each type only in the basic demo mode. The system needs to gain
experiences and broker new rule-based relations. Each rule contains two main sections: the conditions
section and the actions section.
The next table, Table 2, is a resume of tools and related main features were used in the PLATEM
development of its different levels.

Table 2. SW technologies used in the PLATEM system.

Technology Development Level Running on Commercial or Own Development

MySQL Database Server Commercial
PHP Backend Server Commercial
HTML5 Frontend Server Commercial
Java Middleware Server Own
Drools/Decision trees Business Layer Server Commercial/Own
C/Python RF Firmware Nodes Own + Libraries
C/Python Figure 6.Firmware
Controller SDS verificationNodes
rule definition. Own + Libraries

There are several benefits of this algorithm, such as reducing or removing redundancy and
efficient memory erasure when the facts are retracted. The rule container refers to the part of the
database where the rules of the system are saved. There are internal entities that contain the
parameter rules of each individual rule set: system irrigation functionality, fertilization, pest control,
agronomy parameter, and weather; there is a rule for each type only in the basic demo mode. The
 Figure 5. System architecture that integrates Drools into the workflow.

The following section introduces the Drools management based on the Rete pattern-matching
algorithm [20]. It provides the basis for a more efficient implementation that can check each rule
against
Agronomy facts
2019, 9,in216
a knowledge base, firing the rule if necessary. Figure 6 shows the *.drl file where
11 of 19
basic rules for operating with Drools are located.

Figure
Figure6.6.SDS
SDSverification ruledefinition.
verification rule definition.

5. Web Platform
There View benefits of this algorithm, such as reducing or removing redundancy and
are several
efficient
The memory erasure
last step to make when theplatform
the web facts areusable
retracted. The
was to rule container
develop a graphicrefers
user to the part
interface of the
(GUI) to
database where the rules of the system are saved. There are internal entities that
facilitate its use by farmers. Additionally, PLATEM should be tested in terms of data collected and contain the
parameter
operation. rules of section,
In this each individual
the webrule
viewset: system irrigation
development functionality,
is presented, fertilization,
with the pest control,
aim of offering a high
agronomy parameter, and weather; there is a rule for each type only in the
usability level for non-IT-experts. PLATEM incorporates a web-based data-mining system basic demo mode. The
[21,22].
The web provides an important interaction model for the smart farming IoT by letting users obtain
device-related information and, in some cases, control their devices through the ubiquitous web
browser. The conventional web is a convenience we enjoy as we search for information, irrigation Tele
Management control, and post historical data in social networking. Users can refer to devices that are
part of the IoT and that are directly accessed, monitored, and controlled by web technologies as the
Physical Web: web technology + IoT. The web interface supports pre-processing definitions such as
uploading data to DB, and post processing ones such as the data results viewer [23]. The backend is
written in PHP; the frontend is based on PHP/HTML5, CSS3, and JavaScript libraries.
The PLATEM platform is a web view application written in PHP. The user module can share
restricted postings and control security. Communication is performed through a MySQL extension.
MySQL is great at performance database technology, but we see databases becoming more popular
when they simply provide more and more features that are easily connectable and manageable with
existing systems. The more features a database has, the easier it will be for users to develop their
systems, thus making them better and raising the general level of the applications that are made
through MySQL. Since MySQL is very popular, any major improvements or added features affect many
people. The web view uses direct communication with Drools only in parts, with specific functionality
where it is accessible through REST web services in JSON. The remaining fields interact, such as: make
a post, likes, upload images, write commentaries to status or in images, search and list friends, friend
request (send and accept), send messages to friends. They are all accessible through the web interface
without setters to the rule engine.
In addition, there is a settings view to update user profiles that is accessible to friends, which can
be edited (clicking on Edit Information). The next important point is a notifications menu located
on the top-right of the screen in main view, where the notification icons flash for alerts/notifications,
friends, and messages.
The user can search for other users in the database by writing the name in edit text “Search
People,” and can view an open profile, send a message, and add a name to a list of friends. Figure 7
shows the My Friends list with a “View profile” button and “Send message” button.
Agronomy 2019, 9, 216 12 of 19

Agronomy 2019, 9, x FOR PEER REVIEW 12 of 21

Figure 7. My Friends list.

Figure 7. My Friends list.
Testing Scenario
Testing Scenario
In this section, the performance results will be explained at the level of erroneous data, in the
In this2019,
Agronomy section, the performance
9, x FOR results will be explained at the level of erroneous data, 12 ofin21the
sensor environments, and inPEERtheREVIEW
traffic generated for two different transmission scenarios.
sensor environments, and in the traffic generated for two different transmission scenarios. The
The network
server analysis, another important aspect, shows the server bandwidth.
network server analysis, another important aspect, shows the server bandwidth.
A real scenario was simulated
A real scenario was simulated withwith virtual
virtual users wherethey
users where they pretended
pretended to beto be farmers
farmers in action,in action,
making queries and publications in their virtual profiles to check the server response capacity, in
making queries and publications in their virtual profiles to check the server response capacity, in which
a query which a query was
was analyzed andanalyzed
the dataand werethe simultaneously
data were simultaneously
fed into fed the into the database
database and the and the
connections.
connections. The results were very positive, with low usage of system capacity.
The results were very positive, with low usage of system capacity.
Figure 8 shows a sample of the server test. On the first graphs, the number of queries appear,
Figure
and a8login
shows a sample
action of with
test period the server test. Onqueries.
several database the first graphs, the number of queries appear,
and a login action test period with several database queries.
Figure 9 shows a sample of the server test. The graph shows that the number of connections to
100
DB is in a period of login90 action.
Network traffic can 80 be displayed, as shown in Figure 10. The insert process starts when PLATEM
Quantity (n packets)

adds the user as new70friend, and a request can then be sent to the user.
60 Figure 7. My Friends list.
The capture generated by Wireshark of the server bandwidth and response time test during user
50
posting of an uploaded
Testing Scenario image on the social network can be seen in Figure 11. This scenario implies the
40
dedication of network 30 server
In this section, the resources
performanceatresults
a high level.
will Optimal
be explained performance
at the of this
level of erroneous task
data, is the key to
in the
the propersensor
functioning of
environments,
20 the system.
and in the It is
trafficpossible
generatedto analyze
for two user
differentqueries and
transmission server data
scenarios. The responses,
network server
where the length of each analysis, another important aspect, shows the server bandwidth.
10 package is marked with the server response time. It may be the case that the
A real scenario
data are images or big0data was sets.simulated with virtual users where they pretended to be farmers in action,
The server was capable of facilitating basic navigation for many users
making queries and publications in their virtual profiles to check the server response capacity, in
on the multimedia platform where many
which a query was analyzed and the data were sender packets are ACKs,
simultaneously fedbut
intoserver communications
the database and the were
congested connections.
when respondingThe results towere
big very
data,positive,
such as images,
with tables
low usage of historical
of system capacity. data, and some user posts.
Figure 8 shows
The network analysis a sample
was based onofuploaded
the server test. Time
On the first
messages with graphs,
image theposting,
number ofandqueries
theappear,
server network
and a login action test period with several database queries.
had to allocate additional resources for uploading and saving images.
Figure 8. Database access analysis of query actions.

100
Figure 9 shows a sample of the server test. The graph shows that the number of connections to
90
DB is in a period of login action.
80
Quantity (n packets)

70
60
50
40
30
20
10
0

Time

Figure Database
8. 8.
Figure Databaseaccess
access analysis ofquery
analysis of queryactions.
actions.

Figure 9 shows a sample of the server test. The graph shows that the number of connections to
DB is in a period of login action.
 Agronomy 2019, 9, x FOR PEER REVIEW 13 of 21

Processes Connections
Agronomy 2019, 9, 216 14 13 of 19
Agronomy 2019, 9, x FOR PEER REVIEW 13 of 21

Quantity( n packets)
12
10
Processes Connections
8
14
6

Quantity( n packets)
12
4
10
2
8
0
6
4
2 Time
0

Figure 9. Connections to DB by processes.

Network traffic can be displayed, asTime

shown in Figure 10. The insert process starts when
PLATEM adds the user asFigure
new friend, and a request
9. Connections to DBcan
bythen be sent to the user.
processes.
Figure 9. Connections to DB by processes.
Bytes sent Bytes received
35 can be displayed, as shown in Figure 10. The insert process starts when
Network traffic
PLATEM adds the user as new friend, and a request can then be sent to the user.
30
Bytes sent Bytes received
35 25
Data (Bytes)

30 20

25 15
Data (Bytes)

20 10

15 5

10 0
0

10

20

30

40

50

60

70

5 Time (sec)
Agronomy 2019, 9, x FOR PEER REVIEW 14 of 21
Figure 10. Network traffic in the test scenario.
0
Figure 10. Network traffic in the test scenario.
0

10

20

30

40

50

60

70

Data Packets in transmission Packet erros

400
The capture generated by Wireshark Time of the(sec)
server bandwidth and response time test during
user posting of an uploaded image on the social network can be seen in Figure 11. This scenario
350
implies the dedication ofFigure
network
10. server
Network resources
traffic inatthe
a high
test level. Optimal performance of this task
scenario.
is the key 300
to the proper functioning of the system. It is possible to analyze user queries and server
Number of Packets

data
Theresponses, where theby
capture generated length of eachof
Wireshark package is marked
the server with the
bandwidth andserver response
response time time. It may be
test during
250
usertheposting
case that theuploaded
of an data areimage
images onorthebig datanetwork
social sets. Thecan server wasincapable
be seen of facilitating
Figure 11. This scenario basic
navigation
implies 200
for manyofusers
the dedication on the
network multimedia
server resourcesplatform
at a highwhere
level. many sender
Optimal packets are
performance ACKs,
of this taskbut
server
is the key communications were congested
to the proper functioning when responding
of the system. It is possibletotobig data, user
analyze suchqueries
as images, tables of
and server
150
datahistorical data,
responses, and the
where some userofposts.
length each The network
package analysis
is marked withwasthebased
serveron uploaded
response messages
time. It may bewith
theimage
case that 100
posting,
the and
datathe
areserver
imagesnetwork
or bighaddatato allocate
sets. The additional
server was resources forofuploading
capable andbasic
facilitating saving
images. for many users on the multimedia platform where many sender packets are ACKs, but
navigation
50
server communications were congested when responding to big data, such as images, tables of
historical data, 0and some user posts. The network analysis was based on uploaded messages with
10
15
20
25
30
35
40
45
50
55
60
65
70
75
80
85
90
95
0
5

100

image posting, and the server network had to allocate additional resources for uploading and saving
images. Time Interval (sec)

Figure 11. Network

Figure11. Network analysis,
analysis, server
server traffic.
traffic.

Additionally, through the platform, we can collect data from sensors placed in the field, such as
temperature (see Figure 12) or wind speed (see Figure 13). Figures 12 and 13 show the average
temperature per day (in °C) and average wind speed per day (in m/s), respectively, measured over
10 months. These values are used to calculate the irrigation needs.
An example of the rules implementation on the server is given to solve a problem involving
nitrogen application with an irrigation system. The dosages can be tuned with a nitrogen adjustment
rule, e.g., as shown in Figure 14, in this case a PossibleFertiEvent rule that is capable of detecting the
Agronomy 2019, 9, 216 14 of 19

Additionally, through the platform, we can collect data from sensors placed in the field, such as
temperature (see Figure 12) or wind speed (see Figure 13). Figures 12 and 13 show the average
temperature per day (in ◦ C) and average wind speed per day (in m/s), respectively, measured over
Agronomy
10 2019,
months. 9, x FOR
These PEERare
values REVIEW
used to calculate the irrigation needs. 15 of 21

45
40
Average Temperature (°C)

35
30
25
20
15
10
5
0
-5
-10

Figure
Figure 12.12. Averagetemperature
Average temperature measured
measured over 10 10
over months.
months.

An example 14
of the rules implementation on the server is given to solve a problem involving
nitrogen application with an irrigation system. The dosages can be tuned with a nitrogen adjustment
12
rule, e.g., as shown in Figure 14, in this case a PossibleFertiEvent rule that is capable of detecting the
Wind Speed (m/s)

10
potentially low vegetation index in one part of a field, labelled area 1. The rule conditions determine
8
when theAgronomy
action2019,
has9, to be implemented. In this example, two events must occur: manual15user
x FOR PEER REVIEW of 21
upload
6
of the index calculation data of the field, with an NDVI level lower than 0.42, and pressure sensor
detection of an4operational
45 irrigation system ready to begin fertilization. These real-life events are
40
mapped to events 2 in
35 the system, dependent on LowNDVI and WaterPressureEvent. When all the
Average Temperature (°C)

30
conditions are fulfilled,
0 25
the new event can be created. The last line of the actions section inserts this
event in the rule engine.20 In this way, the new event can be used by other rules. Rules give great
15
flexibility to the user10to combine low level events and higher-level events, which should trigger proper
services and generate5 user notifications. Drools Guvnor rule management tools provide a user-friendly
0
interface for building-5 rules so13.
Figure theAverage
user doeswind
not have to measured
speed know all the language
over details, e.g., possible Low
10 months.
level on Vegetation-10Index detected in Aerial Mapping Data changes. Integration with service layers
was also tested with sensor data and notification services. Complex events added several additional
dimensions to the monitoring process. It was proven in the test scenario that the decisions based on
extra assumptions were more Figureaccurate.
12. Average temperature measured over 10 months.

14

12
Wind Speed (m/s)

10

8 Figure 14. Event triggered.

6

Users have the 4option of sharing an NDVI index image in PLATEM view. The data is stored in
numerical form in the
2 DB, and as an image for visual display of the NDVI index. See Figure 15.

Figure 13.Average
13.
Figure Averagewind
windspeed
speed measured over 10
measured over 10months.
months.

Figure 14. Event triggered.

Users have the option of sharing an NDVI index image in PLATEM view. The data is stored in
 4

Agronomy 2019, 9, 216 15 of 19

Figure 13. Average wind speed measured over 10 months.

Figure 14.Event
Figure14. Eventtriggered.
triggered.

Users have
Usersthe option
have of sharing
the option anan
of sharing NDVI
NDVIindex
index image
image ininPLATEM
PLATEM view.
view. The The data
data is is stored
stored in in
numerical form inform
numerical the in
DB,theand
DB, as
andanas image forforvisual
an image visualdisplay ofthe
display of theNDVI
NDVI index.
index. See Figure
See Figure 15. 15.
Agronomy 2019, 9, x FOR PEER REVIEW 16 of 21

Agronomy 2019, 9, x FOR PEER REVIEW 16 of 21

Figure 15. User post sharing NDVI results.

Figure 15. User post sharing NDVI results.
Figure
PLATEM supports the auto 15. User post
notification sharing
mode whenNDVI results.
posting directly via JSON to the user web
PLATEM supports the auto notification mode when posting directly via JSON to the user web
profile and when posting new alerts either for user friends or for the general public with the
profile and PLATEM
when supports
posting newthealerts
auto notification
eitherPLATEMmodefriends
for user when posting
oroffor directly via JSON to the userthe
webbusiness
business rules engine. Figure 16 shows predictions thethe general
fungal public
mildew with
risk factor based
profile
rules engine. and when
Figure 16 posting
shows new
PLATEMalerts either for
predictionsuser friends or for the general public with the on the
on the historical weather DB, the forecast, and thermalof the fungal mildew risk factor based
integral.
business rules engine. Figure 16 shows PLATEM predictions of the fungal mildew risk factor based
historical weather DB, the forecast, and thermal integral.
on the historical weather DB, the forecast, and thermal integral.

Figure 16. Auto post, rule triggered.

The irrigation management Figure 16. Auto

application haspost, rule
a high triggered.
usable visual functionality backed up by an
Figure 16. Auto post, rule triggered.
intelligent system, which adjusts the irrigation schedules that are introduced on the basis of the
The irrigation management application has a high usable visual functionality backed up by an
variables acquired by the sensors. In this way, intelligent programming can be achieved for farmers
intelligent system, which adjusts the irrigation schedules that are introduced on the basis of the
with simple programming settings. Smart conditions come from weather environment data, plant
variables acquired by the sensors. In this way, intelligent programming can be achieved for farmers
growth status, edaphic data, and aerial data from NDVI images (UAV or Satellite). The irrigation
with simple programming settings. Smart conditions come from weather environment data, plant
manager needs a basic irrigation configuration that will eventually be capable of auto-tuning with
growth status, edaphic data, and aerial data from NDVI images (UAV or Satellite). The irrigation
sufficient inputs. Figure 17 shows the irrigation sectors of a single controller.
manager needs a basic irrigation configuration that will eventually be capable of auto-tuning with
sufficient inputs. Figure 17 shows the irrigation sectors of a single controller.
Agronomy 2019, 9, 216 16 of 19

The irrigation management application has a high usable visual functionality backed up by
an intelligent system, which adjusts the irrigation schedules that are introduced on the basis of the
variables acquired by the sensors. In this way, intelligent programming can be achieved for farmers
with simple programming settings. Smart conditions come from weather environment data, plant
growth status, edaphic data, and aerial data from NDVI images (UAV or Satellite). The irrigation
manager needs a basic irrigation configuration that will eventually be capable of auto-tuning with
Agronomy 2019,
sufficient 9, x FOR PEER17
REVIEW 17 of 21
Agronomy inputs. Figure
2019, 9, x FOR shows the irrigation sectors of a single controller.
PEER REVIEW 17 of 21

Figure 17.
17.Irrigation
Irrigationcontroller
controller view.
Figure17.
Figure Irrigation controllerview.
view.
Eachprogram
Each programcan
canbebemodified
modified byby clicking
clickingon
onaaprogram
programnumber
number that will
that launch
will thethe
launch editedit
view.
view.
Each
Basic
programcan
parameters
canbebeadjusted
modifiedto
by clicking
start the
on(see
work
a program
Figure
number
18). The
that will
system will
launch
adjust
the edit
itself on
view.
thethe
Basic parameters can be adjusted to start the work (see Figure 18). The system will adjust itself on
Basic parameters
basis can be adjusted to images,
start the work (see Figure 18). The systemofwill adjust itself on
orthe
basis ofofinformation
information from
from sensors,
sensors, images, andand weather
weatherconditions.
conditions.The Thetype
type ofstart (weekdays
start (weekdays or
basis of information
intervals), from sensors,
add restrictions, images,
time start, and weather
and additional startsconditions. The type of start (weekdays or
can all be added.
intervals), add restrictions, time start, and additional starts can all be added.
intervals), add restrictions, time start, and additional starts can all be added.

Figure 18. Irrigation edition parameters view.

A graphic view of the Figure 18.

18.Irrigation
historical
Figure irrigationedition
Irrigation schedule
edition parameters view. to monitor total water
was introduced
parameters view.
consumption, and to establish water consumption levels in each irrigation sector, irrigation cycle,
andAfertirrigation
graphic viewevent, the
of the historicalas
historical
all presented irrigation schedule
basic visual data in was introducedway
a user-friendly to for
monitor total
farmers. water
When
consumption,
consumption, and
and to
to establish
establish water
water consumption
consumption levels
levels in in each
each irrigation
irrigation sector,
sector, irrigation
irrigation
the crops are harvested, and at any other time, the irrigation records (see Figure 19) can be compared cycle,
cycle, and
and fertirrigation
fertirrigation event, all
event,conditions
with past weather presented
all presented as basic visual
as basicrelationships
to establish visual data indata in a user-friendly
a user-friendly
between them. way for farmers.
way for farmers. When the When
the crops are harvested, and at any other time, the irrigation records (see Figure 19) can be compared
with past weather conditions to establish relationships between them.
Agronomy 2019, 9, 216 17 of 19

crops are harvested, and at any other time, the irrigation records (see Figure 19) can be compared with
past weather conditions
Agronomy 2019, to establish
9, x FOR PEER REVIEW relationships between them. 18 of 21
Agronomy 2019, 9, x FOR PEER REVIEW 18 of 21

Figure 19. Historical water programs.

Figure 19. Historical water programs.
Figure 19. Historical water programs.
Finally, PLATEM allows the farmers to graphically see the irrigation needs as a function of the
Finally, PLATEM allows the farmers to graphically see the irrigation needs as a function of the
measured
Finally, values
PLATEM in the fieldthe
allows andfarmers
weather
to(see Figure 20).
graphically see the irrigation needs as a function of the
measured values in the field and weather (see Figure 20).
measured values in the field and weather (see Figure 20).

Figure 20. View of irrigation needs of PLATEM.

Figure
Figure 20.20. View
View ofof irrigation
irrigation needs
needs ofof PLATEM.
PLATEM.
6. Conclusions and Future Work
6. Conclusions
6. Conclusions and
andFuture
FutureWork
Work
In this work, we have presented the results of new decision rules to create variable rate
In this work,
irrigation
In this we we
have
parameters
work, presented
andpresented
have the the
variable results of new
rateresults decision
fertirrigation
of new rules rules to create
forrules
decision parametric variable
to create raterate
optimization
variable irrigation
of
agricultural
irrigation
parameters and inputs.
parameters
variableInand
addition,
rate we tested
variable a new
rate rules
fertirrigation formultimedia
fertirrigation rules platform
parametric for for userof
parametric
optimization manager
optimization(farmer)
agricultural ofinputs.
profiles we
agricultural
In addition, to inputs.
notify
testedevents,
In to
addition,
a new share
we postings
multimediatested a and
new data
platform for with
user the
multimedia community,
platform
manager andprofiles
for user
(farmer) to interact
manager with the
to(farmer)
notify events,
irrigation–fertirrigation
profiles to notify events, system
to share controller.
postings andComparing
data with our
the study with
community, other
and
to share postings and data with the community, and to interact with the irrigation–fertirrigation applications,
to interact withwethecan
system
irrigation–fertirrigation system controller. Comparing our study with other applications, we can
Agronomy 2019, 9, 216 18 of 19

controller. Comparing our study with other applications, we can highlight the potential of PLATEM:
that integrates all the tools that a farmer may need on a day-to-day basis, so that many fertirrigation
operations can bring in results with a rule engine and a list of rules or models based on historical
data acquisition and user-inserted values. Another important function is information sharing through
forums with input from agronomists, agricultural technicians, and other farmers on doses, plagues,
water restrictions, etc. Work continues on expansions of the rules for the integration of the business
engine system. The goal of this integration is to present the basic user-demanded rules defined in
the system, enabling a simple and unique functional platform for smart farming in irrigation areas,
both under cover and in the field, for fertilization and pest control.
In future work, further development of smart system applications will be necessary, and is likely
to produce two opposing supply chain scenarios: one with further integration of the supply chain, in
which farmers have private data, and another in which farmers are empowered by big data and open
collaboration and can easily switch between suppliers, sharing data with agricultural organizations
and the Ministry of Agriculture, and participating in short supply chains rather than integrated long
supply chains.
Currently, PLATEM is working well for relatively small data sets. A further action required
to process bigger amount of data is to apply different decision-making tools, since the rule engine
and decision tree become inefficient because of the swapping of training tuples in and out of the
main memory.
The situation is likely to navigate a steady course between these two extremes differentiated by
cropping methods, commodity, market structure, etc. In this work, the use of open data is fostered with
the aim of promoting communication channels between farmer, researcher, commercial intermediary,
and technological expert.
Another focus is on the extension of the system that would allow mixing rules from multiple
datasets in a single knowledge base and a common communication protocol through various sources,
e.g., manufacturers of irrigation controllers, real-time information from satellites, and weather
forecasting servers. Finally, we have to consider supporting alternative backend rule learning adjusted
to each user profile (horticulture, cereal, and fruit farmers, etc.) to classify the rules on use in the
rule container. The promise of big data in agriculture is alluring, but the above challenges have to
be addressed for increased uptake of big data applications. Although there are certainly technical
issues to be resolved, we recommend focusing on the most significant obstacles above all, the initially
identified governance issues, and the design of suitable business models.

Author Contributions: C.C.B. designed the platform. J.L. and S.S. conceived the test platforms. J.T. contributed
to the results discussion. All authors have contributed writing the paper.
Funding: This paper has been partially supported by the European Union through the ERANETMED
(Euromediterranean Cooperation through ERANET joint activities and beyond) project ERANETMED3-227
SMARTWATIR and by the “Ministerio de Ciencia, Innovación y Universidades” through the “Ayudas para
la adquisición de equipamiento científico-técnico, Subprograma estatal de infraestructuras de investigación y
equipamiento científico-técnico (plan Estatal i+d+i 2017-2020)” (project EQC2018-004988-P).
Acknowledgments: This paper has been partially supported by the European Union through the ERANETMED
(Euromediterranean Cooperation through ERANET joint activities and beyond) project ERANETMED3-227
SMARTWATIR and by the “Ministerio de Ciencia, Innovación y Universidades” through the “Ayudas para
la adquisición de equipamiento científico-técnico, Subprograma estatal de infraestructuras de investigación y
equipamiento científico-técnico (plan Estatal i+d+i 2017-2020)” (project EQC2018-004988-P).
Conflicts of Interest: The authors declare no conflict of interest.

References
1. Atzori, L.; Lera, A.; Morabito, G. The Internet of Things: A survey. Comput. Netw. J. 2010, 54, 2787–2805.
[CrossRef]
Agronomy 2019, 9, 216 19 of 19

2. Sundmaeker, H.; Verdouw, C.; Wolfert, S.; Pérez Freire, L. Internet of food and farm 2020. In Digitising
the Industry-Internet of Things Connecting Physical, Digital and Virtual Worlds; Vermesan, O., Friess, P., Eds.;
River Publishers: Delft, The Netherlands, 2016; pp. 129–151.
3. Chen, M.; Mao, S.; Liu, Y. Big Data: A survey. Mob. Netw. 2014, 19, 171–209. [CrossRef]
4. Davenport, T.H.; Short, J.E. The new industrial-engineering-information technology and business process
redesign. Sloan Manag. Rev. 1990, 31, 11–27.
5. De Mauro, A.; Greco, M.; Grimaldi, M. A formal definition Big Data based on its essential features. Lib. Rev.
2016, 65, 122–135. [CrossRef]
6. Fry, A. Facts and Trends, Water. In World Business Council for Sustainable Development; Earthprint Ltd.:
Stevenage, UK, 2005.
7. Haghverdi, A.; Leib, B.G.; Washington-Allen, R.A.; Ayers, P.D.; Buschermohle, M.J. Perspectives on
delineating management zones for variable rate irrigation. Comput. Electron. Agric. 2015, 117, 154–167.
[CrossRef]
8. Sadler, E.J.; Evans, R.; Stone, K.C.; Camp, C.R. Opportunities for Conservation with Precision Irrigation.
J. Soil Water Conserv. 2005, 60, 371–379.
9. Marín, J.; Sendra, S.; Parra, L.; Lloret, J.; Mauri, P.V.; Masaguer, A. Smart Irrigation System for the Sustainable
Watering of Urban Lawns. In Proceedings of the New Engineering Concepts for a Valued Agricultura
Conference (AgEng 2018), Wageningen, The Netherlands, 8–12 July 2018.
10. Cambra, C.; Sendra, S.; Lloret, J.; Garcia, L. An IoT Service-Oriented System for Agriculture Monitoring.
In Proceedings of the IEEE 2017 International Conference on Communications (ICC 2017), Paris, France,
21–25 May 2017.
11. Goethals, B.; Moens, S.; Vreeken, J. MIME: A framework for interactive visual pattern mining. In Proceedings
of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Diego,
CA, USA, 21–24 August 2011; pp. 757–760.
12. Vazquez, J.I.; Ruiz-de-Garibay, J.; Eguiluz, X.; Rentería, S.; Ayerbe, A. Communication architectures and
experiences for web-connected physical Smart objects. In Proceedings of the 8th IEEE International
Conference on Pervasive Computing and Communications Workshops (PERCOM Workshops), Mannheim,
Germany, 29 March–2 April 2010; pp. 684–689. [CrossRef]
13. Misra, S.; Barthwal, R.; Obaidat, M.S. Community detection in an integrated Internet of Things and social
network architecture. In Proceedings of the IEEE Global Communications Conference (GLOBECOM),
Anaheim, CA, USA, 3–7 December 2012; pp. 1647–1652. [CrossRef]
14. Atzori, L.; Lera, A.; Morabito, G. From “smart objects” to “social objects”: The next evolutionary step of the
internet of things. IEEE Commun. Mag. 2014, 52, 97–105. [CrossRef]
15. Garriz, I.; Gorroti, I.; Cambra, C. Smart Agriculture European Platform; Navarra Agraria INTIA: Navarra,
Spain, 2017; p. 223. ISBN 0214-6401.
16. Agrivi App. Available online: http://www.agrivi.com/en/re (accessed on 13 March 2019).
17. Armesto, A.; Lafarga, A.; Goñi, J.; Orcaray, L. La HAD NITRO de sigAGROsesor; Navarra Agraria INTIA:
Navarra, Spain, 2017; pp. 26–37. ISSN 0214-6401.
18. Xiao, K.; Xiao, D.; Luo, X. Smart water-saving irrigation system in precision agriculture based on wireless
sensor network. Trans. CSAE 2010, 26, 170–175.
19. Apollo Project. Available online: http://apollo-h2020.eu/ (accessed on 13 March 2019).
20. Cambra, C.; Sendra, S.; Lloret, J.; Lacuesta, R. Smart system for bicarbonate control in irrigation for hydroponic
precision farming. Sensors 2018, 18, 1333. [CrossRef] [PubMed]
21. Ortiz, A.M.; Hussein, D.; Park, S.; Han, S.N.; Crespi, N. The Cluster Between Internet of Things and Social
Networks: Review and Research Challenges. IEEE Internet Things J. 2014, 1, 206–215. [CrossRef]
22. Ji, Z.; Ganchev, I.; Xueji, Z. A Cloud-Based Car Parking Middleware for IoT-Based Smart Cities: Design and
Implementation. Sensors 2014, 14, 22372–22393. [CrossRef] [PubMed]
23. Ning, H.; Wang, Z. Future Internet of Things Architecture: Like Mankind Neural System or Social
Organization Framework? IEEE Commun. Lett. 2011, 15, 461–463. [CrossRef]

© 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access
article distributed under the terms and conditions of the Creative Commons Attribution
(CC BY) license (http://creativecommons.org/licenses/by/4.0/).