<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Archiving and Interchange DTD v1.0 20120330//EN" "JATS-archivearticle1.dtd">
<article xmlns:xlink="http://www.w3.org/1999/xlink">
  <front>
    <journal-meta />
    <article-meta>
      <title-group>
        <article-title>Informationally-technological provision of environmental nature reserves monitoring⋆</article-title>
      </title-group>
      <contrib-group>
        <contrib contrib-type="author">
          <string-name>Оleksandr Tymchenko</string-name>
          <email>olexandr.tymchenko@uwm.edu.pl</email>
          <xref ref-type="aff" rid="aff1">1</xref>
          <xref ref-type="aff" rid="aff2">2</xref>
        </contrib>
        <contrib contrib-type="author">
          <string-name>Bohdana Havrysh</string-name>
          <email>dana.havrysh@gmail.com</email>
          <xref ref-type="aff" rid="aff0">0</xref>
        </contrib>
        <contrib contrib-type="author">
          <string-name>Orest Khamula</string-name>
          <email>khamula@gmail.com</email>
          <xref ref-type="aff" rid="aff1">1</xref>
        </contrib>
        <contrib contrib-type="author">
          <string-name>Bohdan</string-name>
        </contrib>
        <contrib contrib-type="author">
          <string-name>Kovalskyi</string-name>
          <email>bkovalskyi@ukr.net</email>
          <xref ref-type="aff" rid="aff1">1</xref>
        </contrib>
        <contrib contrib-type="author">
          <string-name>Igor Bagniuk</string-name>
          <xref ref-type="aff" rid="aff1">1</xref>
        </contrib>
        <aff id="aff0">
          <label>0</label>
          <institution>Lviv Polytechnic National University</institution>
          ,
          <addr-line>Stepana Bandery Street, 12, Lviv, 79000</addr-line>
          ,
          <country country="UA">Ukraine</country>
        </aff>
        <aff id="aff1">
          <label>1</label>
          <institution>Ukrainian Academy of Printing</institution>
          ,
          <addr-line>Pidholosko st., 19, Lviv, 79020</addr-line>
          ,
          <country country="UA">Ukraine</country>
        </aff>
        <aff id="aff2">
          <label>2</label>
          <institution>University of Warmia and Mazury</institution>
          ,
          <addr-line>Ochapowskiego str,2, Olsztyn, 10-719</addr-line>
          ,
          <country country="PL">Poland</country>
        </aff>
      </contrib-group>
      <abstract>
        <p>Modern approaches to environmental protection do not always meet the requirements of science and are often based on the principles of prohibition rather than rational use of natural resources. The analysis of human society development shows the inevitability of the natural environment radical transformation by man, therefore the "prohibitive" approach cannot solve the problem of environmental preservation and stop the destruction of nature. For the harmonious development of nature and man, the policy of nature protection must be built based on the modern science achievements, first of all, on the results of evolutionary and ecological research. Ecological monitoring is the most important part of the study and protection of the environment, since the analysis of natural processes dynamics makes it possible to reveal the regularities of the ecosystems organization and the biology of individual species of animals and plants. Therefore, the development of ecological monitoring methods is urgent, especially for nature reserves, which would allow not only to record changes and violations, but also to identify the causes and predict the direction and nature of their further transformation. The physical and chemical parameters of the environment are usually measured with the help of devices: the magnitude and spectrum of noise, temperature, characteristics of electromagnetic fields, characteristics of radioactive pollution of the environment, characteristics of geophysical phenomena, concentrations of chemical pollutants in air, water, soil, etc. Remote research of ecological systems from airplanes, artificial Earth satellites, and spaceships is widely used. Monitoring methods are divided into qualitative and quantitative. Qualitative analysis usually precedes quantitative determinations. Based on the measured parameters, methods of quantitative analysis are divided into chemical, physico-chemical, physical and biological. Thus, the existing methods of environmental monitoring are narrowly focused and relate to the measurement of quantitative parameters. There is a lack of methods considering the informational and technical component of the monitoring and research process.</p>
      </abstract>
      <kwd-group>
        <kwd>eol&gt;ecological monitoring of nature reserves</kwd>
        <kwd>wireless sensor network1</kwd>
      </kwd-group>
    </article-meta>
  </front>
  <body>
    <sec id="sec-1">
      <title>1. Introduction</title>
      <p>
        Traditional methods of the environment state monitoring are based on changes observations in
individual elements of natural ecosystems (fluctuations in climatic factors, natural or
anthropogenic habitat disturbances, changes in the number of individual species of animals and
plants, etc.). In such studies, the main attention is paid to the study of the structure and nature
of connections between individual elements and the evolution of connections over time. This is
due to the dominance of the population approach noticed in recent ecological
researches.Scientists' attention was focused mainly on discovering the population structure of
individual species of organisms. The biosystems as integral aggregates of cells, as well as
individuals, and species makes a significant amendment to the traditional perception of the
organic world and the nature of its development. It was forced to raise and solve methodological
issues of studying biosystems differently than it was before. Such studies focus on the structure
and nature of the connections between individual elements and the evolution of connections
over time. These indicators allow us to characterize the biosystem as a whole and establish the
laws governing its development It is these indicators that make it possible to characterize the
biosystem as a whole and establish the laws governing its development. Therefore, it is obvious
that modern methods of environmental monitoring should be based, first of all, on the analysis
of the mechanisms of changes in the structure of the ecosystem as a whole [
        <xref ref-type="bibr" rid="ref1">1</xref>
        ].
      </p>
      <p>
        Reserves organize monitoring with the help of so-called trial sites, permanent or temporary
routes. As a rule, each site has a passport and all collected information is entered into it. The
routes and sites form a monitoring network, the collection of materials has been conducted at
the same points for many years and according to the same methodology [
        <xref ref-type="bibr" rid="ref1">1</xref>
        ].
      </p>
      <p>The large amount of data that is created because of such research already makes their manual
processing impossible, which makes the task of developing appropriate information systems
especially urgent.</p>
      <p>The trends and features analysis of the development of nature reserves and ecological
monitoring methods and the requirements for the development of specific programs for its
implementation allows us to draw conclusions about insufficient attention to the technical and
informational support of these processes. At the same time, the use of information technologies
in the processes of environmental monitoring can not only improve its individual aspects, but
also introduce fundamentally new methods of research. In particular, the use of artificial
intelligence systems, for example, the study of the state of populations of rare species.</p>
      <p>The purpose of the work is the development of methodical and algorithmic support for the
informational support of the tasks of ecological monitoring of nature reserves.</p>
    </sec>
    <sec id="sec-2">
      <title>2. Related works</title>
      <p>
        In accordance with the above, all connections in ecosystems are subordinate in nature [
        <xref ref-type="bibr" rid="ref1 ref10">1, 10</xref>
        ].
There are leading ecological factors that determine species diversity and other features of
species biology, and secondary factors that are not so significant for the structure and
functioning of communities. The identification of such factors and the nature of their
relationship on the example of background species of animals and plants makes it possible to
monitor based on the analysis of changes in hierarchically organized relationships of organisms
[
        <xref ref-type="bibr" rid="ref1 ref2 ref3">1-3</xref>
        ].
      </p>
      <p>Fire alarm system. Thousands of microscopic sensors are spread over the territory, for
example, a forest, and in a threatening situation, on the basis of continuous temperature
measurements, they inform the crisis center about the existing threat. Thanks to the sensors, a
quick reaction is possible, and because of this, losses are minimized.</p>
      <p>Flood warning system. The US uses the ALERT system, which warns against dangerous
atmospheric phenomena (floods, hurricanes). Several types of sensors monitor the amount of
precipitation, water level in rivers and other, most meteorological information, and the collected
information is forwarded to a central database and analyzed. Thanks to this, it is possible to
better predict threats.</p>
      <p>However, systematic landscape studies are not conducted in all reserves. In most of them,
only minimal observations are made: temperature, soil moisture, and information on natural
disasters that have already occurred and are recorded: avalanches, changes in the coastline,
landslides, landslides, and so on. This is due to the lack of specialists and the laboriousness of
research. Therefore, data on the dynamics of the soil cover over a long period are not available
in many reserves. The use of wireless sensor networks makes it easier to obtain relevant data,
and in many cases to predict threatening changes.</p>
      <p>
        In addition, there are many systems that monitor the preservation of animals, pollution of the
natural environment, or the condition of soils in agriculture. The importance of rare animal
species for systematic environmental monitoring is due to the fact that their existence is
supported by limited resources. Even a slight change in ecosystem connections can have a
significant impact on the state of populations of rare species. Therefore, rare species of animals
are sensitive indicators of the state of natural ecosystems [
        <xref ref-type="bibr" rid="ref4 ref6">4, 6</xref>
        ]. The use of observation sites
does not allow us to cover large areas and identify connections and threats that are important
for all populations.
      </p>
      <p>
        The application of systematic ecological monitoring using wireless sensor networks makes
it possible to significantly expand the scope and research details without human intervention.
Methods allows combining these often unrelated observations and effectively use them to
analyze the state and change in the structure of natural ecosystems [
        <xref ref-type="bibr" rid="ref5 ref6 ref7">5-7</xref>
        ].
      </p>
    </sec>
    <sec id="sec-3">
      <title>3. Selection of the monitoring structure</title>
      <p>
        Typically, a network-level environmental data collection program is characterized by the
presence of a large number of nodes that continuously receive and transmit data to base stations
that store it for later use. In general, the use of wireless sensor networks (WSNs) requires very
low data rates and extremely long operational periods. Usually, network nodes are distributed
over a controlled area. The distance between neighbouring nodes can be different, but the
length of the network is usually large [
        <xref ref-type="bibr" rid="ref8 ref9">8, 9</xref>
        ].
      </p>
      <p>Sensor networks can work in various and extreme conditions. Therefore, to perform
monitoring tasks, we can also place them in the following places:
•
•
•
•
roads;
places of biological and chemical pollution;
on animals, to monitor their conservation;
in many hard-to-reach places.</p>
      <p>In sensor networks based on wireless environment, energy consumption is very important.
Sensor nodes can be equipped with a rather limited power source (&lt;0.5Ah, 1.2V). Although
there are sensor nodes with replenishment of energy from the sun or vibrations, in many cases
it is not possible to replace the energy sources, due to which the lifetime of the node is strongly
dependent on battery resources. In addition, in sensor networks with serial data transmission,
each node must fulfil the dual role of data source and routing data. Therefore, the loss of
functions of several nodes can have a significant impact on topology changes, as well as require
data for re-routing and reorganization of the entire network.</p>
      <p>
        After deployment, individual WSNs nodes must initiate a route discovery procedure to
generate network topology and evaluate optimal routing strategies. This strategy can be used
to route measurement data to a central collection point [
        <xref ref-type="bibr" rid="ref11 ref17">11, 17</xref>
        ].
      </p>
      <p>
        Most environmental data collection applications use a tree-based routing topology, where
each routing tree is rooted at resource-intensive nodes or base stations. This data is periodically
transmitted from child nodes to parent nodes until it reaches the base station. In a typical data
collection scheme based on a tree topology, each individual node is responsible for routing or
forwarding data received from all its descendants [
        <xref ref-type="bibr" rid="ref11 ref13">11, 13</xref>
        ].
      </p>
      <p>Nodes with a large number of descendants transmit significantly more data than leaf nodes,
causing more energy consumption. As a result, these nodes can quickly become energy
consumption bottlenecks for WSNs.</p>
      <p>Node</p>
      <p>
        After setting up the WSNs, each node periodically takes sensor readings and transmits the
collected data to the main node (Fig. 1). A typical transmission period is estimated to be in the
range of 1 to 15 minutes [
        <xref ref-type="bibr" rid="ref12 ref13 ref14 ref15">12-15</xref>
        ]. In typical environmental monitoring conditions, attributes
such as air and soil temperature, light intensity, and air and soil moisture change slowly and
therefore do not require shorter reporting periods.
      </p>
      <p>Data sampling can be delayed within the network for a period of time without significantly
impacting application performance. Often, this data is stored for further analysis, not for
realtime operations.</p>
      <p>
        To meet operational requirements for WSNs, each transmission must be precisely planned.
A work/sleep protocol is often used, where nodes will sleep most of the time to save energy and
only wake up to transmit or receive data. If the nodes deviate from this schedule, then the data
transfer will fail [
        <xref ref-type="bibr" rid="ref11 ref16">11, 16</xref>
        ].
      </p>
      <p>
        Due to limited energy resources, there is always a possibility that nodes will fail and routes
will be disrupted. As a result, periodic network configuration updates must occur to redistribute
the network load or to handle node or link failure. Additionally, network users may want to
change the network topology to accommodate new information about the controlled
environment. In general, network reconfiguration is rare and has no significant impact on
overall energy consumption [
        <xref ref-type="bibr" rid="ref18 ref19">18, 19</xref>
        ].
      </p>
      <p>
        Key environmental monitoring parameters are network uptime, accurate clock
synchronization, low data rates, and static topologies. Nor is it usually important that network
data be transmitted in real time. This data may be temporarily stored, aggregated or, if
necessary, delayed in the network [
        <xref ref-type="bibr" rid="ref20">20</xref>
        ].
      </p>
      <p>To reduce the total energy consumption and increase the total monitoring time, it is
advisable to change the traditional tree-shaped structure of the WSNs to a hierarchical one (Fig.
2.).</p>
      <p>
        Hierarchical protocols (Fig. 2) (for example, LEACH protocol (Low-Energy Adaptive
Clustering Hierarchy) [
        <xref ref-type="bibr" rid="ref10 ref21">10, 21</xref>
        ] or low-energy adaptive hierarchy of groups, clusters) divide the
network into clusters consisting of groups of nodes. One of the nodes in the cluster receives the
status of the master, and other nodes in the network maintain communication within the cluster
only with it. The main node instead forwards the information further to the main node in the
network and only it maintains communication with it. The protocol allows a random change of
the main nodes in the clusters, which made it possible to reduce energy use and evenly
distribute the energy load on all nodes in the network. In addition, LEACH performs data
aggregation, which significantly limits the amount of data that is broadcast to the master node.
      </p>
      <p>
        Example. The simulation of wireless sensor networks was performed using the SNOW
simulator [
        <xref ref-type="bibr" rid="ref4">4</xref>
        ].
      </p>
      <p>Simulations of energy properties were aimed at determining the lifetime and energy
consumption for individual sensors in the network. These parameters are essential for wireless
sensor networks, because it is not desirable to have a situation in which only a few sensors in
the network operate for much longer. Obviously, the best solution is when all sensors in the
network are loaded evenly, which means that their lifetime is approximately the same. For
simulations, we used a random placement of 50 nodes on an area of 100 by 100 meters.</p>
      <p>The simulation also revealed a serious drawback of using protocols with a homogeneous
structure. Such wireless sensor networks excessively load the nodes closest to the head node.
This situation is obviously not desirable, it causes uneven load of nodes in the network, which
reduces its operation time (Fig. 3).</p>
      <p>Protocols of this type, with an increasing number of nodes are functioning worse and worse,
creating excessive traffic, which significantly reduces the network lifetime. From our point of
view, the best network is the one in which all nodes live as long as possible and "die" at the
same time. Only a hierarchical network can fulfill such requirements for a good network in
terms of energy parameters.
•</p>
      <p>Protocols with a hierarchical structure have a small delay in packet transmission, regardless
of the number of nodes. The entire network is loaded evenly and there are no situations when
some sensors remain unnecessary, being outside the network. However, the significant
advantages of protocols with a hierarchical structure are offset by the need for significant sensor
processor power, as well as the time intervals required to fix the network structure.</p>
      <sec id="sec-3-1">
        <title>3.1. Solving the tasks of ecological monitoring of nature reserves with the use of information technologies</title>
        <p>
          Let's define the tasks of ecological monitoring of reserves, which can be solved with the use of
information technologies:
the use of spatial databases to collect and store information on the values of controlled
parameters and meteorological indicators tied to specific spatial objects;
development of environmental monitoring subsystems of nature reserves to support
decision-making in the field of environmental safety and to ensure software and
analytical solutions to monitoring task;
development of standards and protocols for the exchange of information between
subsystems of environmental monitoring of all levels, including protocols for the
transfer of information received at automated environmental monitoring posts, and
protocols for the transfer of information to the international level;
use of the combined services of global data dissemination [
          <xref ref-type="bibr" rid="ref22 ref23">22, 23</xref>
          ] and global
telecommunications systems [
          <xref ref-type="bibr" rid="ref22">22</xref>
          ] for the transmission of information;
development of software interfaces for organizing user interaction with monitoring
subsystems, taking into account the level of access [
          <xref ref-type="bibr" rid="ref22 ref24">22, 24</xref>
          ].
        </p>
        <p>
          Solving the specified environmental monitoring tasks is possible in an information system
capable of performing such functions [
          <xref ref-type="bibr" rid="ref23">23</xref>
          ]:
collection and storage in a spatial database of information coming from monitoring
subjects and automated monitoring posts;
automatic notification of personnel in the event of dangerous situations by analyzing
information in real time;
informational and analytical support for decision-making in the field of environmental
monitoring at all levels;
generation of reports, including in the form of map information for system users
according to access rights;
solutions to typical problems (modeling concentration fields, forecasting the dynamics
of changes in concentrations or populations) at all levels;
information security [
          <xref ref-type="bibr" rid="ref25 ref5">5, 25</xref>
          ].
Data acquisition and
storage subsystem 1
        </p>
        <p>Data acquisition and
storage subsystem n
Regional level</p>
        <p>State level</p>
        <p>Initial processing subsystem
Emergency notification
subsystem</p>
        <p>Data presentation subsystem</p>
        <p>International level
Local data
storage</p>
        <p>Data transmission
subsystem
Archiving
subsystem
Protection
subsystem</p>
        <p>Re-processing subsystem
Operational staff</p>
        <p>Global data warehouse</p>
        <p>Protection
subsystem
Data presentation
subsystem</p>
        <p>
          To ensure such functionality, the following subsystems can be distinguished in the structure
of the information system of ecological monitoring of nature reserves (Fig. 5) [
          <xref ref-type="bibr" rid="ref25">25</xref>
          ]:
•
•
the data collection and storage subsystem is a set of the same type of automated
environmental monitoring stations and typical modular systems and is intended for
measuring the concentration of pollutants in the soil and atmosphere, monitoring
meteorological parameters, the level of solar radiation, ionizing radiation, etc.;
the initial processing subsystem (Fig. 5) is intended for preliminary processing of
information coming from the data collection and accumulation subsystem. This
subsystem allows control of data transmission at the physical and logical levels. The
•
•
•
•
•
•
•
subsystem can also carry out primary conversions, convert units of measurement
according to international standards, etc.
local data storage (LDS) is a spatial database and is designed to store observation data.
All information is stored in its original form. This makes it possible to ensure a regular
flow of data. In the LDS design process, it is necessary to take into account the possibility
of storing any information about the state of control objects in real time [
          <xref ref-type="bibr" rid="ref22 ref25">22, 25</xref>
          ];
the data reprocessing and interpretation subsystem is a software block that concentrates
a large part of the system performed functions. This subsystem is designed to solve
typical monitoring tasks (modeling concentration fields, forecasting the dynamics of
changes in concentrations or populations, supporting decision-making, etc.);
global data storage (GDS) accumulates information coming from local level objects. The
basis of the GDS is a distributed database that uses information replication technologies
and enables data recovery in the event of emergency situations;
the data exchange subsystem can use data transmission in the GDS and can be
implemented as a software module [
          <xref ref-type="bibr" rid="ref25">25</xref>
          ].
        </p>
        <p>
          Data can be transmitted in binary or XML format. The specified subsystem can also
summarize data before sending it to the GDS. The subsystem of providing data to operational
personnel is used to visualize the data obtained as a result of the analysis and presented in the
form of:
reports, the form of which corresponds to international and national standards. In the
process of developing the subsystem of providing information, modern technologies of
document formation can be used;
maps that display the state of observed values in the form of fields. Such values can be
the current levels of pollution or the distribution of meteorological parameters. Google
Maps® or Google Earth® technology can be used to build a state map. Google Maps and
Google Earth services are open resources and are intended for visualization of various
thematic data;
graphs of time series of observation parameters [
          <xref ref-type="bibr" rid="ref2 ref25">2, 25</xref>
          ].
        </p>
        <p>
          In the process of developing this subsystem, a combined approach can be used. For example,
the geographic location of monitoring posts can be displayed on a Google map, and when one
of them is selected, the related reporting documentation or observation data can be searched [
          <xref ref-type="bibr" rid="ref13 ref2 ref21">2,
13, 21</xref>
          ].
        </p>
        <p>
          •
•
•
the emergency notification subsystem is intended for automatic notification of operative
personnel in the event of dangerous situations in the territory of the region associated
with a sharp change in the values of the observed parameters. An example of a
dangerous event can be a sharp increase in the value of an observed value (for example,
the concentration of a pollutant) and its departure from the established norms.
the archiving subsystem serves for automatic archiving of collected information.
Archiving parameters can be set by the operator in wide ranges;
the information protection subsystem is designed to protect information from illegal
access (if necessary by encryption) and control access to the system [
          <xref ref-type="bibr" rid="ref13 ref2 ref25">2, 13, 25</xref>
          ].
        </p>
        <p>
          The proposed system is a concept, and the existing systems are characterized by insufficient
periodicity of data collection and insufficiently reliable methods of their preservation, limited
access to the specified information and almost complete absence of software and technical
means of its processing and decision-making support [
          <xref ref-type="bibr" rid="ref2 ref25">2, 25</xref>
          ]. Therefore, we will further consider
a possible option of formalizing the work process of the subsystem of primary information
support (subsystem of data collection and accumulation in Fig.5).
        </p>
      </sec>
      <sec id="sec-3-2">
        <title>3.2. Creation of information support for monitoring systems</title>
        <p>The class diagram for WSNs environmental monitoring is shown in Fig. 6. To collect data,
sensors use SensorGateway to transmit data over the Internet to a DataServer (smartphone,
router, etc.), where the data is stored in a database. Data sources are sensors of environmental
parameters.</p>
        <p>To use the data, the user (Client) launches the Application or the WebClient web application,
which allows him to connect via the Internet to the DataServer, which stores the data (Fig. 6).
The DataServer runs the server application, and it serves the client requests by querying the
database.</p>
        <p>Web Client</p>
        <p>Application
+id
+URL
+id</p>
        <p>In fig. 7 shows the sequence diagram of data collection and storage in the environmental
monitoring system. The Sensor reads information from sensors based on the signals of the
builtin timer and sends the data to the SensorGateway and then to the DataServer, which stores the
data in the database.</p>
        <p>The data is used in the system in the following sequence (Fig. 8):</p>
        <p>SensorGateway
1…* 1…*
displayRtading
requestData()
sendData()
collectReadings
1</p>
        <p>1…*
1…*</p>
        <p>Sensor
readSensor()
sendData</p>
        <p>1</p>
        <p>Web Client
+moteId
+channel
+id
+type</p>
        <p>Web Client</p>
        <p>Client
consumeData()</p>
        <p>DataServer
reseiveData()
sendData()
modifyData
1
1…*</p>
        <p>DataBase
+capacity
the client forms a data request to the AppServer,
AppServer requests data from DataServer,
the DataServer successfully requests data from the database.</p>
        <p>Hypothetically, smoke and fire can be detected by standard sensors of the monitoring system
- smoke and temperature sensors. But only if the ignition source is near the wireless network
node. In addition, typical WSNs are too slow to send the necessary information to the user
program in a timely manner.</p>
        <p>Therefore, parallel to the monitoring network, it is worth deploying a new one built on the
basis of wireless video cameras (Fig. 8), the main purpose of which will be to detect signs of fire
on the territory of the reserve.</p>
        <p>Wireless v</p>
        <p>cam</p>
        <p>
          Analysis of data from video cameras for the purpose of detecting signs of fire can be
implemented on the basis of artificial vision technologies with appropriate ready-made libraries
(for example, OpenCV [
          <xref ref-type="bibr" rid="ref20 ref25">20, 25</xref>
          ]) and artificial intelligence methods implemented in a number of
open libraries, for example, Keras [
          <xref ref-type="bibr" rid="ref21 ref25">21, 25</xref>
          ].
        </p>
      </sec>
    </sec>
    <sec id="sec-4">
      <title>4. Conclusions and discussion</title>
      <p>Current systems of ecological monitoring of natural reserves are characterized by insufficient
periodicity of data collection and insufficiently reliable methods of their preservation, limited
access to information and almost complete absence of software and technical means of its
processing and decision-making support. The analysis of trends and features of ecological
monitoring development methods of nature reserves allows us to draw conclusions about
insufficient attention to its technical and information support.</p>
      <p>For some reason, safety issues are often raised beyond the environmental monitoring
procedures, which violates the principle of systematic environmental monitoring. For example,
prevention or timely detection of fires.</p>
      <p>To implement the program part of the proposed WSNs structure of environmental
monitoring of nature reserves based on video surveillance systems to detect signs of fire. Fire
in a controlled area, especially with anthropogenic impact, is a very important factor leading to
the destruction of protected areas. However, the detection of smoke and fire by wireless sensor
network nodes is quite limited in terms of distance. In addition, typical wireless sensor networks
are too slow to send the necessary information to the central monitoring node in a timely
manner. With the use of appropriate technical and software tools of machine vision, ecological
monitoring of nature reserves can be not only fully automated, but also brought to a
fundamentally new level, providing continuous monitoring of a certain territory and automatic
storage and analysis of results.</p>
      <p>The presented study is proposed for the Carpathian Biosphere Reserve for areas of nature
with possible changes in relief due to anthropogenic impact.</p>
    </sec>
    <sec id="sec-5">
      <title>Acknowledgements References</title>
      <p>The authors are appreciative of colleagues for their support and appropriate suggestions, which
allowed to improve the materials of the article.</p>
    </sec>
  </body>
  <back>
    <ref-list>
      <ref id="ref1">
        <mixed-citation>
          [1]
          <string-name>
            <given-names>N.</given-names>
            <surname>Lu</surname>
          </string-name>
          ,
          <string-name>
            <given-names>H.</given-names>
            <surname>Ma</surname>
          </string-name>
          and J.
          <string-name>
            <surname>Wang</surname>
          </string-name>
          ,
          <article-title>"Thoughts on the Construction of Unified Spatial Data Manage System for Eco-Environmental Protection,"</article-title>
          <source>IEEE International Geoscience and Remote Sensing Symposium</source>
          , Yokohama, Japan,
          <year>2019</year>
          , pp.
          <fpage>4352</fpage>
          -
          <lpage>4355</lpage>
          , doi: 10.1109/IGARSS.
          <year>2019</year>
          .
          <volume>8899224</volume>
          .
        </mixed-citation>
      </ref>
      <ref id="ref2">
        <mixed-citation>
          [2]
          <string-name>
            <surname>C. -M. Yang</surname>
            ,
            <given-names>K. -P.</given-names>
          </string-name>
          <string-name>
            <surname>Shih</surname>
            and
            <given-names>S. -H.</given-names>
          </string-name>
          <string-name>
            <surname>Chang</surname>
          </string-name>
          ,
          <article-title>"A Priority-Based Energy Replenishment Scheme for Wireless Rechargeable Sensor Networks,"</article-title>
          <source>1st International Conference on Advanced Information Networking and Applications Workshops (WAINA)</source>
          , Taipei, Taiwan,
          <year>2017</year>
          , pp.
          <fpage>547</fpage>
          -
          <lpage>552</lpage>
          .
        </mixed-citation>
      </ref>
      <ref id="ref3">
        <mixed-citation>
          [3]
          <string-name>
            <given-names>O.</given-names>
            <surname>Tymchenko</surname>
          </string-name>
          ,
          <string-name>
            <given-names>B.</given-names>
            <surname>Havrysh</surname>
          </string-name>
          ,
          <string-name>
            <given-names>O.</given-names>
            <surname>Khamula</surname>
          </string-name>
          ,
          <string-name>
            <given-names>B.</given-names>
            <surname>Kovalskyi</surname>
          </string-name>
          ,
          <string-name>
            <given-names>S.</given-names>
            <surname>Vasiuta</surname>
          </string-name>
          ,
          <string-name>
            <surname>I. Lyakh.</surname>
          </string-name>
          <article-title>Methods of Converting Weight Sequences in Digital Subtraction Filtration</article-title>
          .
          <source>International Scientific and Technical Conference on Computer Sciences and Information Technologies</source>
          ,
          <volume>2</volume>
          , art. no.
          <issue>8929750</issue>
          , pp.
          <fpage>32</fpage>
          -
          <lpage>36</lpage>
          .
        </mixed-citation>
      </ref>
      <ref id="ref4">
        <mixed-citation>
          [4]
          <string-name>
            <given-names>B.</given-names>
            <surname>Durnyak</surname>
          </string-name>
          ,
          <string-name>
            <given-names>B.</given-names>
            <surname>Havrysh</surname>
          </string-name>
          ,
          <string-name>
            <given-names>O.</given-names>
            <surname>Tymchenko</surname>
          </string-name>
          ,
          <string-name>
            <given-names>M.</given-names>
            <surname>Zelyanovsky</surname>
          </string-name>
          ,
          <string-name>
            <given-names>O. O.</given-names>
            <surname>Tymchenko</surname>
          </string-name>
          and
          <string-name>
            <given-names>O.</given-names>
            <surname>Khamula</surname>
          </string-name>
          ,
          <article-title>Intelligent System for Sensor Wireless Network Access: Modeling Methods of Network Construction, IEEE 4th International Symposium on Wireless Systems within the International Conferences on Intelligent Data Acquisition and Advanced Computing Systems (IDAACS-SWS)</article-title>
          , Lviv, Ukraine,
          <year>2018</year>
          , pp.
          <fpage>93</fpage>
          -
          <lpage>97</lpage>
          , doi: 10.1109/IDAACSSWS.
          <year>2018</year>
          .
          <volume>8525792</volume>
          .
        </mixed-citation>
      </ref>
      <ref id="ref5">
        <mixed-citation>
          [5]
          <string-name>
            <given-names>T.</given-names>
            <surname>Bao</surname>
          </string-name>
          ,
          <string-name>
            <given-names>Z.</given-names>
            <surname>Huang</surname>
          </string-name>
          and
          <string-name>
            <given-names>D.</given-names>
            <surname>Li</surname>
          </string-name>
          ,
          <article-title>"Data Loss and Reconstruction for Wireless Environmental Sensor Networks," ieee 3rd international conference on big data security on cloud (bigdatasecurity), ieee international conference on high performance and smart computing (hpsc), and ieee international conference on intelligent data and security (ids</article-title>
          ), Beijing, China,
          <year>2017</year>
          , pp.
          <fpage>48</fpage>
          -
          <lpage>52</lpage>
          , doi: 10.1109/BigDataSecurity.
          <year>2017</year>
          .
          <volume>41</volume>
          .
        </mixed-citation>
      </ref>
      <ref id="ref6">
        <mixed-citation>
          [6]
          <string-name>
            <given-names>M.</given-names>
            <surname>Diván</surname>
          </string-name>
          ,
          <article-title>"Applying the Real-Time Monitoring based on Wireless Sensor Networks: The Bajo Giuliani Project," 7th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO), Noida</article-title>
          , India,
          <year>2018</year>
          , pp.
          <fpage>18</fpage>
          -
          <lpage>24</lpage>
          , doi: 10.1109/ICRITO.
          <year>2018</year>
          .
          <volume>8748648</volume>
          .
        </mixed-citation>
      </ref>
      <ref id="ref7">
        <mixed-citation>
          [7]
          <string-name>
            <given-names>V.</given-names>
            <surname>Kovtun</surname>
          </string-name>
          ,
          <string-name>
            <given-names>T.</given-names>
            <surname>Altameem</surname>
          </string-name>
          ,
          <string-name>
            <given-names>M.</given-names>
            <surname>Al-Maitah</surname>
          </string-name>
          , and W. Kempa, “
          <article-title>The Markov Concept of the Energy Efficiency Assessment of the Edge Computing Infrastructure Peripheral Server Functioning over Time,” Electronics</article-title>
          , vol.
          <volume>12</volume>
          , no. 20.
          <string-name>
            <surname>MDPI</surname>
            <given-names>AG</given-names>
          </string-name>
          , p.
          <fpage>4320</fpage>
          , Oct.
          <volume>18</volume>
          ,
          <year>2023</year>
          . doi:
          <volume>10</volume>
          .3390/electronics12204320.
        </mixed-citation>
      </ref>
      <ref id="ref8">
        <mixed-citation>
          [8]
          <string-name>
            <given-names>A.</given-names>
            <surname>Arsalis</surname>
          </string-name>
          et al.,
          <article-title>"Development of Hybrid Photovoltaic-based Nanogrids for the Energy Rehabilitation of Public Buildings: The BERLIN Project,"</article-title>
          <source>IEEE International Smart Cities Conference (ISC2)</source>
          , Pafos, Cyprus,
          <year>2022</year>
          , pp.
          <fpage>1</fpage>
          -
          <lpage>4</lpage>
          , doi: 10.1109/ISC255366.
          <year>2022</year>
          .
          <volume>9922154</volume>
          .
        </mixed-citation>
      </ref>
      <ref id="ref9">
        <mixed-citation>
          [9]
          <string-name>
            <given-names>D.</given-names>
            <surname>Yan</surname>
          </string-name>
          ,
          <string-name>
            <given-names>J.</given-names>
            <surname>Li</surname>
          </string-name>
          ,
          <string-name>
            <given-names>X.</given-names>
            <surname>Yao</surname>
          </string-name>
          and
          <string-name>
            <given-names>Z.</given-names>
            <surname>Luan</surname>
          </string-name>
          ,
          <article-title>"Quantifying the Long-Term Expansion and Dieback of Spartina Alterniflora Using Google Earth Engine and Object-Based Hierarchical Random Forest Classification,"</article-title>
          <source>in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing</source>
          , vol.
          <volume>14</volume>
          , pp.
          <fpage>9781</fpage>
          -
          <lpage>9793</lpage>
          ,
          <year>2021</year>
          , doi: 10.1109/JSTARS.
          <year>2021</year>
          .
          <volume>3114116</volume>
          .
        </mixed-citation>
      </ref>
      <ref id="ref10">
        <mixed-citation>
          [10]
          <string-name>
            <given-names>G.</given-names>
            <surname>Santhanamari</surname>
          </string-name>
          ,
          <string-name>
            <surname>M. J. P. S</surname>
          </string-name>
          , D. B,
          <string-name>
            <surname>K. S</surname>
            and
            <given-names>A. R</given-names>
          </string-name>
          ,
          <article-title>"Radar Based Target Detection and Classification,"</article-title>
          <source>International Conference on Intelligent Systems for Communication, IoT and Security (ICISCoIS)</source>
          , Coimbatore, India,
          <year>2023</year>
          , pp.
          <fpage>412</fpage>
          -
          <lpage>416</lpage>
          , doi: 10.1109/ICISCoIS56541.
          <year>2023</year>
          .
          <volume>10100358</volume>
          .
        </mixed-citation>
      </ref>
      <ref id="ref11">
        <mixed-citation>
          [11]
          <string-name>
            <given-names>B.</given-names>
            <surname>Kovalskyi</surname>
          </string-name>
          ,
          <string-name>
            <given-names>M.</given-names>
            <surname>Dubnevych</surname>
          </string-name>
          ,
          <string-name>
            <given-names>T.</given-names>
            <surname>Holubnyk</surname>
          </string-name>
          ,
          <string-name>
            <given-names>I.</given-names>
            <surname>Skarga-Bandurova</surname>
          </string-name>
          ,
          <string-name>
            <given-names>L.</given-names>
            <surname>Maik</surname>
          </string-name>
          ,
          <string-name>
            <given-names>Z.</given-names>
            <surname>Selmenska</surname>
          </string-name>
          .
          <article-title>Analysis of the Effectiveness of Means to Achieve Optimal Color Balancing in Obtaining a Digital Photographic Image (</article-title>
          <year>2022</year>
          ) CEUR Workshop Proceedings,
          <volume>3156</volume>
          , pp.
          <fpage>520</fpage>
          -
          <lpage>538</lpage>
          .
        </mixed-citation>
      </ref>
      <ref id="ref12">
        <mixed-citation>
          [12]
          <string-name>
            <given-names>G.</given-names>
            <surname>Santhanamari</surname>
          </string-name>
          ,
          <string-name>
            <surname>M. J. P. S</surname>
          </string-name>
          , D. B,
          <string-name>
            <surname>K. S</surname>
            and
            <given-names>A. R</given-names>
          </string-name>
          ,
          <article-title>"Radar Based Target Detection and Classification,"</article-title>
          <source>International Conference on Intelligent Systems for Communication, IoT and Security (ICISCoIS)</source>
          , Coimbatore, India,
          <year>2023</year>
          , pp.
          <fpage>412</fpage>
          -
          <lpage>416</lpage>
          , doi: 10.1109/ICISCoIS56541.
          <year>2023</year>
          .
          <volume>10100358</volume>
          .
        </mixed-citation>
      </ref>
      <ref id="ref13">
        <mixed-citation>
          [13]
          <string-name>
            <given-names>A.</given-names>
            <surname>Sarthi</surname>
          </string-name>
          ,
          <string-name>
            <given-names>D. S.</given-names>
            <surname>Gurjar</surname>
          </string-name>
          ,
          <string-name>
            <given-names>C.</given-names>
            <surname>Sai</surname>
          </string-name>
          ,
          <string-name>
            <given-names>P.</given-names>
            <surname>Pattanayak</surname>
          </string-name>
          and
          <string-name>
            <given-names>A.</given-names>
            <surname>Bhardwaj</surname>
          </string-name>
          ,
          <article-title>"Performance Impact of Hardware Impairments on Wireless Powered Cognitive Radio Sensor Networks,"</article-title>
          <source>in IEEE Sensors Letters</source>
          , vol.
          <volume>4</volume>
          , no.
          <issue>6</issue>
          , pp.
          <fpage>1</fpage>
          -
          <lpage>4</lpage>
          , June 2020, Art no.
          <issue>7500704</issue>
          , doi: 10.1109/LSENS.
          <year>2020</year>
          .
          <volume>2994595</volume>
          .
        </mixed-citation>
      </ref>
      <ref id="ref14">
        <mixed-citation>
          [14]
          <string-name>
            <given-names>J.</given-names>
            <surname>Gao</surname>
          </string-name>
          ,
          <string-name>
            <given-names>R.</given-names>
            <surname>Wu</surname>
          </string-name>
          ,
          <string-name>
            <given-names>J.</given-names>
            <surname>Hao</surname>
          </string-name>
          ,
          <string-name>
            <given-names>C.</given-names>
            <surname>Xu</surname>
          </string-name>
          and
          <string-name>
            <given-names>H.</given-names>
            <surname>Guo</surname>
          </string-name>
          ,
          <article-title>"SWIPT-Based Energy Scheduling for SolarPowered WSN in Full-Duplex Mode,"</article-title>
          <source>in IEEE Sensors Journal</source>
          , vol.
          <volume>22</volume>
          , no.
          <issue>13</issue>
          , pp.
          <fpage>13668</fpage>
          -
          <issue>13681</issue>
          ,
          <fpage>1</fpage>
          <lpage>July1</lpage>
          ,
          <year>2022</year>
          , doi: 10.1109/JSEN.
          <year>2022</year>
          .
          <volume>3174120</volume>
          .
        </mixed-citation>
      </ref>
      <ref id="ref15">
        <mixed-citation>
          [15]
          <string-name>
            <given-names>B.</given-names>
            <surname>Kovalskyi</surname>
          </string-name>
          ,
          <string-name>
            <given-names>M.</given-names>
            <surname>Dubnevych</surname>
          </string-name>
          ,
          <string-name>
            <given-names>T.</given-names>
            <surname>Holubnyk</surname>
          </string-name>
          ,
          <string-name>
            <given-names>N.</given-names>
            <surname>Pysanchyn</surname>
          </string-name>
          ,
          <string-name>
            <given-names>B.</given-names>
            <surname>Havrysh</surname>
          </string-name>
          .
          <article-title>Development of a technology for eliminating color rendering imperfections in digital photographic images (Open Access) (</article-title>
          <year>2019</year>
          )
          <article-title>Eastern-</article-title>
          <source>European Journal of Enterprise Technologies</source>
          ,
          <volume>1</volume>
          (
          <issue>2</issue>
          -
          <fpage>97</fpage>
          ), pp.
          <fpage>40</fpage>
          -
          <lpage>47</lpage>
          . http://journals.uran.ua/eejet doi:
          <volume>10</volume>
          .15587/
          <fpage>1729</fpage>
          -
          <lpage>4061</lpage>
          .
          <year>2019</year>
          .
          <volume>154512</volume>
          .
        </mixed-citation>
      </ref>
      <ref id="ref16">
        <mixed-citation>
          [16]
          <string-name>
            <given-names>W.</given-names>
            <surname>Chen</surname>
          </string-name>
          ,
          <string-name>
            <given-names>H.</given-names>
            <surname>Wang</surname>
          </string-name>
          ,
          <string-name>
            <given-names>H.</given-names>
            <surname>Li</surname>
          </string-name>
          ,
          <string-name>
            <given-names>Q.</given-names>
            <surname>Li</surname>
          </string-name>
          ,
          <string-name>
            <given-names>Y.</given-names>
            <surname>Yang</surname>
          </string-name>
          and
          <string-name>
            <given-names>K.</given-names>
            <surname>Yang</surname>
          </string-name>
          ,
          <article-title>"Real-Time Garbage Object Detection With Data Augmentation and Feature Fusion Using SUAV Low-Altitude Remote Sensing Images,"</article-title>
          <source>in IEEE Geoscience and Remote Sensing Letters</source>
          , vol.
          <volume>19</volume>
          , pp.
          <fpage>1</fpage>
          -
          <lpage>5</lpage>
          ,
          <year>2022</year>
          , Art no.
          <issue>6003005</issue>
          , doi: 10.1109/LGRS.
          <year>2021</year>
          .
          <volume>3074415</volume>
          .
        </mixed-citation>
      </ref>
      <ref id="ref17">
        <mixed-citation>
          [17]
          <string-name>
            <given-names>C.</given-names>
            <surname>Gao</surname>
          </string-name>
          ,
          <string-name>
            <given-names>Z.</given-names>
            <surname>Wang</surname>
          </string-name>
          and
          <string-name>
            <given-names>Y.</given-names>
            <surname>Chen</surname>
          </string-name>
          ,
          <article-title>"On the Connectivity of Highly Dynamic Wireless Sensor Networks in Smart Factory,"</article-title>
          <source>International Conference on Networking and Network Applications (NaNA)</source>
          , Daegu, Korea (South),
          <year>2019</year>
          , pp.
          <fpage>208</fpage>
          -
          <lpage>212</lpage>
          , doi: 10.1109/NaNA.
          <year>2019</year>
          .
          <volume>00045</volume>
          .
        </mixed-citation>
      </ref>
      <ref id="ref18">
        <mixed-citation>
          [18]
          <string-name>
            <given-names>Y.</given-names>
            <surname>Nishikawa</surname>
          </string-name>
          et al.,
          <article-title>"Design of stable wireless sensor network for slope monitoring,"</article-title>
          <source>IEEE Topical Conference on Wireless Sensors and Sensor Networks (WiSNet)</source>
          , Anaheim, CA, USA,
          <year>2018</year>
          , pp.
          <fpage>8</fpage>
          -
          <lpage>11</lpage>
          , doi: 10.1109/WISNET.
          <year>2018</year>
          .
          <volume>8311550</volume>
          .
        </mixed-citation>
      </ref>
      <ref id="ref19">
        <mixed-citation>
          [19]
          <string-name>
            <surname>N. I. Sulieman</surname>
          </string-name>
          and
          <string-name>
            <given-names>R. D.</given-names>
            <surname>Gitlin</surname>
          </string-name>
          ,
          <article-title>"Near-Instant Fault Recovery and Ultra-Reliable Multi-Hop Wireless Sensor Networks," SoutheastCon, Huntsville</article-title>
          , AL, USA,
          <year>2019</year>
          , pp.
          <fpage>1</fpage>
          -
          <lpage>6</lpage>
          , doi: 10.1109/SoutheastCon42311.
          <year>2019</year>
          .
          <volume>9020455</volume>
          .
        </mixed-citation>
      </ref>
      <ref id="ref20">
        <mixed-citation>
          [20]
          <string-name>
            <given-names>A.</given-names>
            <surname>Rao</surname>
          </string-name>
          ,
          <string-name>
            <given-names>H.</given-names>
            <surname>Shao</surname>
          </string-name>
          and
          <string-name>
            <given-names>X.</given-names>
            <surname>Yang</surname>
          </string-name>
          ,
          <article-title>"The Design and Implementation of Smart Agricultural Management Platform Based on UAV and Wireless Sensor Network,"</article-title>
          <source>IEEE 2nd International Conference on Electronics Technology (ICET)</source>
          , Chengdu, China,
          <year>2019</year>
          , pp.
          <fpage>248</fpage>
          -
          <lpage>252</lpage>
          , doi: 10.1109/ELTECH.
          <year>2019</year>
          .
          <volume>8839480</volume>
          .
        </mixed-citation>
      </ref>
      <ref id="ref21">
        <mixed-citation>
          [21]
          <string-name>
            <given-names>C.</given-names>
            <surname>Han</surname>
          </string-name>
          ,
          <string-name>
            <surname>L</surname>
          </string-name>
          . Ding,
          <string-name>
            <given-names>L.</given-names>
            <surname>Sun</surname>
          </string-name>
          and
          <string-name>
            <given-names>J.</given-names>
            <surname>Guo</surname>
          </string-name>
          ,
          <article-title>"A Node Task Assignment Algorithm for Energy Harvesting Wireless Multimedia Sensor Networks," ICC</article-title>
          . IEEE International Conference on Communications, Rome, Italy,
          <year>2023</year>
          , pp.
          <fpage>931</fpage>
          -
          <lpage>936</lpage>
          , doi: 10.1109/ICC45041.
          <year>2023</year>
          .
          <volume>10279261</volume>
          .
        </mixed-citation>
      </ref>
      <ref id="ref22">
        <mixed-citation>
          [22]
          <string-name>
            <surname>[</surname>
            <given-names>N.</given-names>
          </string-name>
          <string-name>
            <surname>Abbas</surname>
            and
            <given-names>F.</given-names>
          </string-name>
          <string-name>
            <surname>Yu</surname>
          </string-name>
          ,
          <article-title>"A Traffic Congestion Control Algorithm for Wireless Multimedia Sensor Networks,"</article-title>
          <source>IEEE SENSORS</source>
          , New Delhi, India,
          <year>2018</year>
          , pp.
          <fpage>1</fpage>
          -
          <lpage>4</lpage>
          , doi: 10.1109/ICSENS.
          <year>2018</year>
          .
          <volume>8589923</volume>
          .
        </mixed-citation>
      </ref>
      <ref id="ref23">
        <mixed-citation>
          [23]
          <string-name>
            <given-names>F.</given-names>
            <surname>Ertam</surname>
          </string-name>
          ,
          <string-name>
            <given-names>I. F.</given-names>
            <surname>Kilincer</surname>
          </string-name>
          ,
          <string-name>
            <given-names>O.</given-names>
            <surname>Yaman</surname>
          </string-name>
          and
          <string-name>
            <given-names>A.</given-names>
            <surname>Sengur</surname>
          </string-name>
          ,
          <article-title>"A New IoT Application for Dynamic WiFi based Wireless Sensor Network,"</article-title>
          <source>International Conference on Electrical Engineering (ICEE)</source>
          , Istanbul, Turkey,
          <year>2020</year>
          , pp.
          <fpage>1</fpage>
          -
          <lpage>4</lpage>
          , doi: 10.1109/ICEE49691.
          <year>2020</year>
          .
          <volume>9249771</volume>
          .
        </mixed-citation>
      </ref>
      <ref id="ref24">
        <mixed-citation>
          [24]
          <string-name>
            <given-names>E. M.</given-names>
            <surname>Manuel</surname>
          </string-name>
          ,
          <string-name>
            <given-names>V.</given-names>
            <surname>Pankajakshan</surname>
          </string-name>
          and
          <string-name>
            <given-names>M. T.</given-names>
            <surname>Mohan</surname>
          </string-name>
          ,
          <article-title>"Efficient Strategies for Signal Aggregation in Low-Power Wireless Sensor Networks With Discrete Transmission Ranges," in IEEE Sensors Letters</article-title>
          , vol.
          <volume>7</volume>
          , no.
          <issue>3</issue>
          , pp.
          <fpage>1</fpage>
          -
          <lpage>4</lpage>
          ,
          <year>March 2023</year>
          , Art no.
          <issue>7500304</issue>
          , doi: 10.1109/LSENS.
          <year>2023</year>
          .
          <volume>3250432</volume>
          .
        </mixed-citation>
      </ref>
      <ref id="ref25">
        <mixed-citation>
          [25]
          <string-name>
            <given-names>R.</given-names>
            <surname>Prabha</surname>
          </string-name>
          ,
          <string-name>
            <given-names>M. V.</given-names>
            <surname>Ramesh</surname>
          </string-name>
          and
          <string-name>
            <given-names>V. P.</given-names>
            <surname>Rangan</surname>
          </string-name>
          ,
          <article-title>"Building Optimal Topologies for Real-Time Wireless Sensor Networks,"</article-title>
          <source>International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET)</source>
          , Chennai, India,
          <year>2018</year>
          , pp.
          <fpage>1</fpage>
          -
          <lpage>6</lpage>
          , doi: 10.1109/WiSPNET.
          <year>2018</year>
          .
          <volume>8538721</volume>
          .
        </mixed-citation>
      </ref>
    </ref-list>
  </back>
</article>