Content uploaded by Ahmed Alkhayyat
Author content
All content in this area was uploaded by Ahmed Alkhayyat on Jul 20, 2022
Content may be subject to copyright.
Applications of Cognitive Radio in Emerging Technologies – Review
International Journal of Distributed
Sensor Networks
2022, Vol. 18(7)
ÓThe Author(s) 2022
DOI: 10.1177/15501329221113508
journals.sagepub.com/home/dsn
Fuzzy logic, genetic algorithms, and
artificial neural networks applied to
cognitive radio networks: A review
Ahmed Alkhayyat
1
, Firas Abedi
2
, Ashish Bagwari
3
,
Pooja Joshi
4
, Haider Mahmood Jawad
5
,SarmadNozadMahmood
6
and Yousif K Yousif
7
Abstract
Cognitive radios are expected to play an important role in capturing the constantly growing traffic interest on remote
networks. To improve the usage of the radio range, a cognitive radio hub detects the weather, evaluates the open-air
qualities, and then makes certain decisions and distributes the executives’ space assets. The cognitive radio works in tan-
dem with artificial intelligence and artificial intelligence methodologies to provide a flexible and intelligent allocation for
continuous production cycles. The purpose is to provide a single source of information in the form of a survey research
to enable academics better understand how artificial intelligence methodologies, such as fuzzy logics, genetic algorithms,
and artificial neural networks, are used to various cognitive radio systems. The various artificial intelligence approaches
used in cognitive radio engines to improve cognition capabilities in cognitive radio networks are examined in this study.
Computerized reasoning approaches, such as fuzzy logic, evolutionary algorithms, and artificial neural networks, are used
in the writing audit. This topic also covers cognitive radio network implementation and the typical learning challenges
that arise in cognitive radio systems.
Keywords
Cognitive radio, fuzzy logics, artificial neural networks, artificial intelligence, genetic algorithm
Date received: 31 January 2022; accepted: 20 June 2022
Handling Editor: Yanjiao Chen
Introduction
According to the Cisco Visual Networking Index, glo-
bal IP traffic will increase by 168 bytes per month by
2019, with multiple times the global population.
Furthermore, assets such as power and data transport
speed are limited. As a result, smart adjustments are
required to reduce energy consumption while updating
asset designation. Joseph Mitola III and Gerald Q
Maguire
1
proposed cognitive radio (CR) as a solution
for universal range access in 1999. CR is defined as a
combination of model-based thinking with radio pro-
gramming innovation.
2
In 2005, Simon Haykin
3
inves-
tigated CR and labeled it as ‘‘mind-engaged remote
correspondences.’’
1
College of Technical Engineering, The Islamic University, Najaf, Iraq
2
Department of Mathematics, College of Education, Al-Zahraa University
for Women, Karbala, Iraq
3
Department of Electronics and Communication Engineering, Women
Institute of Technology Dehradun (WIT), Uttarakhand Technical
University (UTU), Dehradun, India
4
Department of Computer Science and Engineering, Uttaranchal
University, Dehradun, India
5
Communication Engineering Department, Al-Rafidain University
College, Baghdad, Iraq
6
Computer Technology Engineering, College of Engineering Technology,
Al-Kitab University, Kirkuk, Iraq
7
Department of Computer Technical Engineering, Al-Hadba University
College, Mosul, Iraq
Corresponding author:
Ashish Bagwari, Department of Electronics and Communication
Engineering, Women Institute of Technology Dehradun (WIT),
Uttarakhand Technical University (UTU), Dehradun 248007,
Uttarakhand, India.
Email: ashishbagwari@ieee.org
Creative Commons CC BY: This article is distributed under the terms of the Creative Commons Attribution 4.0 License
(https://creativecommons.org/licenses/by/4.0/) which permits any use, reproduction and distribution of the work
without further permission provided the original work is attributed as specified on the SAGE and Open Access pages
(https://us.sagepub.com/en-us/nam/open-access-at-sage).
CR is a framework that recognizes the climate, ana-
lyzes its transmission boundaries, and then makes deci-
sions about dynamic time–recurrence space asset
identification and the board to improve the utilization
of the radio electromagnetic range.
4
The radio asset
board, in general, wants to increase the use of various
radio assets so that the radio framework’s exposure is
improved. Consider the boundaries of the barrier tem-
perature range; as an example, the inventors of Zhao
and Morales-Tirado
5
introduced an ideal asset (power
and transmission capacity) assignment in cognitive
radio networks (CRNs), explicitly in the range of fun-
damental conditions. In some cases, the improvement
recipes yield perfect asset assignment arrangements at
the expense of global intermingling, calculation time,
and complexity. To reduce complexity and achieve fea-
sible continual asset allocations, CRNs should be given
learning and reasoning capabilities. The intellectual
motor should make the CR’s activities easier using arti-
ficial intelligence (AI) methods.
6
CR, according to Gavrilovska,
7
is a clever remote
communication structure that is aware of your current
position and uses the agreement to benefit from the cli-
mate and establish approaches to accommodate factual
variance in upgrading information.
As a result of interacting with its Radio Frequency
(RF) environment, a CR should be astute and ready to
profit from its interactions. As a result, learning is an
important component of CR, which can be delivered
using computerized reasoning as AI approaches.
8
The
CR framework standard and its essential assets, traits,
and points are discussed in this review. Then we will
look at how AI handles the learning cycle, the impor-
tance of learning in CRs, and the learning capacity of
CRs. The focus then moves to a written examination of
the most recent advances in CRs that employ learning
methodologies. Several investigations of learning
approaches in CR-assignment tasks have been per-
formed, but they lack key components of a comprehen-
sive study on CR frameworks.
9
Wyglinski et al.
10
provided a brief overview of artifi-
cial reasoning methodologies, but their focus was on
the sequence of events and layout of CR applications
and proving grounds.
11
Support learning, game
hypothesis, artificial neural networks (ANNs) or neural
networks (NNs), support vector machines, and the
Markov model were among the learning methods stud-
ied. They also talked about the benefits, limitations,
and difficulty of implementing these tactics in CR exer-
cises. Game theory, reinforcement learning, Bayesian
networks, fuzzy logic (FL), and case-based logic are all
investigated by the author of this article.
12
Instead of
writing, we present a complete study that considers all
learning approaches used in intellectual networks.
ANNs, FL, and genetic algorithms (GAs) are among
the automated reasoning techniques used in the
summary.
12
The intellectual cycle is depicted in Figure 1. The
remote correspondence framework, as shown in Figure
1, is made up of base stations (BSs) and radio networks,
with some serving as fundamental/ primary users (PUs)
or networks within its range, and others serving as aux-
iliary/ secondary users (SUs) who may use it when it is
not in use by other networks. CRs are expected to play
a key role in meeting the constantly growing traffic
demands on wireless networks.
13
A CR node detects
the surroundings, analyzes the outside features, and
then makes decisions for dynamic time–frequency–
space resource allocation and management to optimize
the use of the radio spectrum.
14
The CRN, as shown in Figure 2, followed the intel-
lectual cycle, the board, and network execution for an
ideal asset. It begins by identifying the climate, asses-
sing external variables, and then deciding on dynamic
asset distribution and executive decisions to improve
the usage of radio electromagnetic range.
15
An elemen-
tal analysis of them will follow. It should be highlighted
that, in this situation, the learning agent is not passive
and can not only observe but can also actively change
the state of the system through its activities, potentially
moving the environment to a desirable condition that
rewards the agent with the maximum reward.
16
Environmental sensing
In CRNs, the virtual network requires the auxiliary
network for range use. The optional network may use
Figure 1. Wireless networking developed by cognitive radio
networks.
2International Journal of Distributed Sensor Networks
the available range if it does not interfere with the vir-
tual network. As a result, it should first assess and
detect boundaries in a short amount of time, such as
(1) channel qualities between the BS and clients; (2)
range and power accessibility; (3) range opening acces-
sibility focusing on recurrence, time, and space; (4) cli-
ent and application requirements; (5) power utilization;
and (6) nearby strategies and other imperatives.
17
Dissecting the boundaries of the climate
The discovered climate boundaries will be used as con-
tributions for the executives’ asset in all aspects, such as
time, recurrence, and space. Some of the major asset
component aims in CR are (1) limiting piece blunder
rate, (2) limiting power use, (3) limiting obstruction, (4)
expanding throughput, (5) working on nature of admin-
istration, (6) boosting range productivity, and (7)
increasing client nature of involvement. In general,
18
CR seeks to achieve many goals; combining specific
goals may result in incompatible arrangements, such as
lowering power consumption and spot blunder rate at
the same time.
Literature review
The application of CR sensor networks (CRSNs) was
described by Suh et al.
19
and Kaur et al.
20
Several
information systems for elderly care have been devel-
oped using cognitive sensor networks to address the
dilemma of a super-aging society. However, many
sensor-network-based systems that monitor radios,
resources, habitats, and other factors are not practical
or useful for the elderly. As a result, the goal of this
research is to present novel research methodologies for
constructing smart living environments for the elderly
using converging information technologies, such as
cognitive sensor networks and architectural design. In
this article, we review the literature to clarify the con-
cept of smart houses and look at cognitive sensor-net-
work-based systems for smart elder housing. Following
that, this research explores research avenues for cogni-
tive wireless sensor networks, not only for geriatric
smart home services but also for integrating architec-
tural technologies. The proposed directions are to use
CR technologies, to category sensor networking devices
according to the types of elderly people, to expand
environmental sensing services for elderly housing to a
wider area, to integrate sensor network circuits into
Building Information Modeling (BIM) systems, and to
investigate network architecture that is appropriate for
construction projects.
Furthermore, in 2018, Liu et al.
21
suggested CR as a
potential strategy for boosting spectrum utilization by
allowing cognitive users (CUs) access to the licensed
spectrum when the Primary User (PUs) are unavail-
able. They developed a resource allocation paradigm
for spectrum assignment in CRNs based on graph the-
ory in this article. The concept considers the interfer-
ence restrictions for principal users and the possibility
of CU collision. They created a system utility function
based on the provided model to optimize the system
benefit. They design an improved ant colony optimiza-
tion algorithm (IACO) from two perspectives based on
the proposed model and objective problem: first, they
introduce a differential evolution (DE) process to accel-
erate convergence speed via a monitoring mechanism;
and second, they design a variable neighborhood
search (VNS) process to avoid the algorithm falling
into the local optimal. According to simulation data,
the updated technique performs better.
A CR engine platform is proposed in this study
22–24
for exploiting available frequency channels for a tacti-
cal wireless sensor network while attempting to protect
incumbent communication devices, referred to as the
principal user (PU), from unintended negative interfer-
ence. There is a compelling need in tactical communica-
tion networks to identify accessible frequencies for
opportunistic and dynamic access to channels when the
PU is active. This article offers a cognitive engine plat-
form for locating available channels using a case-based
reasoning technique, which can be used as a crucial
capacity on a CR engine to enable high-fidelity
dynamic spectrum access (DSA). To this purpose, a
credible learning engine to describe the channel use pat-
tern is developed to extract the optimal channel option
for the tactical cognitive radio node (TCRN).
Simulation tests were used to assess the performance of
the proposed cognitive engine, demonstrating the
dependability of the functional element, which includes
Figure 2. Cognitive radio’s learning process.
Alkhayyat et al. 3
the learning engine and the case-based reasoning
engine. Furthermore, the TCRN’s effectiveness in
avoiding contact with the PU operation, as measured
by the etiquette SU, was demonstrated.
El Morabit et al.
25
provide a comprehensive analysis
of various AI methodologies used in CR engines to
improve cognition capabilities in CRNs. Learning,
thinking, decision-making, self-adaptation, self-organi-
zation, and self-stability are only few of the human bio-
logical processes that AI can emulate. The employment
of AI techniques is investigated in applications related
to CR’s key objectives, such as spectrum sensing, spec-
trum sharing, spectrum mobility, and decision-making
for issues, such as DSA, resource allocation, parameter
modification, and optimization. The goal is to provide
a single source as a survey study to help academics bet-
ter understand the many AI methodologies used in dif-
ferent CR designs and to connect interested readers to
current AI research in CRNs.
Guru et al.
26
show that in the year 2022, the CRN
has the following sensing procedure, in which the selec-
tion and selecting of a trustworthy channel from a list
of free channels is critical for assignment to CUs for
communication with Quality of Service (QoS). In this
study, a consistent spectrum selection and decision
scheme based on a twofold NN is provided, and its per-
formance is compared to that of GA and back-
propagation neural network (BPNN) schemes. The
BPNN-adaptive neuro-fuzzy inference system (ANFIS)
is a twofold spectrum selection and judging system that
combines the BPNN and ANFIS techniques. The fac-
tors such as PU status signal intensity, spectrum
demand, velocity, and distance are used to select a
channel with the required QoS. The simulation analysis
shows that the BPNN-ANFIS strategy reduces the risk
of blocking and dropping, resulting in an accuracy of
more than 92% for reliable channel selection for CU
usage. The suggested approach’s blocking probability
ranges from 1% to 3%, which is significantly lower
than the GA (9%–50%) and BPNN (8%–40%). The
advised method has a 4% chance of falling, which is
lower than the other two plans’ 20% chance of falling.
Abd El-Malek et al.
27
in the year 2020, evolutionary
computation methods will be thoroughly examined in
the study of energy harvesting (EH) approaches in
multiple-input single-output CRNs (MISO-CRNs). An
SU with multiple antennas gathers energy from a
hybrid base station (HBS) during the downlink time
slot, in addition to harvesting from the PU transmis-
sion. As a result, the SU transmits data across
Nakagami-m fading channels on the uplink. The SU
total transmission power is limited by a certain toler-
able PU interference in the underlay paradigm. The
HBS has no previous knowledge of the state of the SU
battery. For the high signal-to-noise ratio (SNR) area,
a closed-form expression for the SU exact outage
probability is derived and simplified to its asymptotic
formula. The system average symbol error probability
(ASEP) and ergodic capacity have closed-form formu-
las.
28
To reduce the complicated formula of the exact
outage probability, the particle swarm optimization
(PSO) algorithm is employed to discover the best SU
transmission power. The effect of crucial system para-
meters on total system performance is revealed through
simulations and numerical results, which confirm the
resulting mathematical analysis. Furthermore, as com-
pared to the standard evenly distributed model, the
optimum solution of the power optimization problem
demonstrates a significant improvement in system
performance.
AI in CR
Experts in AI want machines to tackle tasks in the
same way as humans do. The intelligent machine will
take note of its surroundings and improve its function-
ality.
29
The most common concerns in AI brainpower
include derivation, thinking, critical thinking, informa-
tion description, and learning.
There are three basic AI techniques: FL, GAs, and
NNs, and their mixtures in one domain and three other
areas. Each of the technologies has brought successful
answers to a wide range of issues in various sectors.
Figure 2 depicts the CR AI learning process. They are
as follows: (1) detecting radio recurrence (DRR)
boundaries, such as channel quality, (2) noticing the cli-
mate and dissecting criticism, such as Acknowledgment
(ACK) reactions, (3) learning, (4) recording choices and
perceptions for refreshing the model and further devel-
oping future dynamic exactness, and (5) settling on
asset the board issues and changing transmission blun-
ders as needs are.
30
Chen et al.
31
proposed CR stan-
dards based on computational thinking and AI. In
addition, the developers discussed the expected uses
and key concepts that will aid in the development of
CR. Some of the learning techniques used in AI are FL,
ANNs, GAs, game theory, support vector machines,
reinforcement learning, case-based logics, decision-
making trees, Bayesian, Entropy, Markov model,
multi-agent systems, and artificial bee colony algo-
rithms. The strategies outlined above, however, are the
most often used and applied techniques in CRNs.
32
Functions of CRN
The IEEE 802.22 standards are used by the CR to
adjust its parameters (such as transmission power,
modulation scheme, bandwidth, operating frequency,
and so on) in response to environmental variables. The
cycle of CRNs is seen in Figure 3. The existence of all
four elements is required to establish CRNs.
33
4International Journal of Distributed Sensor Networks
Spectrum sensing
Between PUs and SUs in CRNs, the spectrum sensing
network is critical. PUs broadcast data through their
licensed spectrum during data transmission. SUs per-
ceive the PU spectrum for data transmission, according
to IEEE 802.22 specifications. There are two types of
spectrum sensing:
1. Fast sensing, the time frame is 1 ms per channel;
2. Fine sensing is animatedly computed by the BS,
depends on the outcomes of the fast sensing,
and its work is to detect the frequency band
deeply.
The CRs detect the licensed frequency band, and the
BS announces whether the licensed band is available or
not based on the data given by the CRs to the BS.
33
The energy detection technique is preferred by IEEE
802.22 because it is simple and has a low processing
complexity. A number of additional strategies, aside
from ‘‘Energy Detection,’’ have been proposed in the
writing, for example,
1. Matched filter detection;
2. Cyclo-stationary-based detection;
3. Radio identification-based detection;
4. Waveform-based detection.
Spectrum sharing
CR users transmit frequency band information with
neighboring CRs once the frequency band has been
determined. CR users must coordinate their actions
because wireless channels are shared. Architecture
(centralized and distributed), spectrum allocation beha-
vior (cooperative and non-cooperative), spectrum
access technique (overlay spectrum sharing and under-
lay spectrum sharing), and scope (overlay spectrum
sharing and underlay spectrum sharing; has two types:
intra-network and inter-network spectrum sharing) are
the four categories of spectrum sharing.
34
Spectrum management
It allocates the best spectrum available for the user’s
communication while minimizing interference to other
(primary) users. To meet quality-of-service criteria, CR
optimizes the spectral band. As a result, spectral man-
agement skills are required for CR.
35
The key issue with implementing spectrum manage-
ment capabilities is that they are sophisticated and
multi-user at the same time. Because, it requires a vari-
ety of technical and regulatory restrictions to detect
other users’ thresholds. This could indicate that
national law specifies radio spectrum access laws and
restrictions.
Spectrum mobility
When PU requires its licensed band for this function,
CR users shift/move to the other licensed band to
ensure a smooth connection. In CRNs, spectrum mobi-
lity strives to deliver a smooth and quick transition out
of a spectrum handoff with minimal performance loss.
A network protocol may require updates to the opera-
tional settings when a CR user alters its frequency of
operation.
CR with various emerging technologies
Fuzzy logic
The FL sets of hypotheses were declared by Lotfi in
1965; A Zadeh
17
used numerical and observational
models to tackle and demonstrate vulnerability, equi-
vocalness, imprecision, and dubiousness. In FL, factors
are not restricted to just two qualities (True or False),
as in old style and fresh sets.
8
Genetic algorithms
Algorithms with genetic elements, Friedberg (1958),
endeavored to prompt learning by altering short
FORTRAN software engineers, which prompted the
improvement of GAs. Therefore, a software engineer
with elite execution for a specific straightforward
undertaking can be produced by making a suitable
series of small changes to a machine code developer.
36
Figure 3. The cycle of cognitive radio networks.
Alkhayyat et al. 5
Artificial neural network
A sort of computer network is ANNs. ANNs were
invented by Warren McCulloch and Walter Pitts in
1943, with inspiration from the focused sensory system.
The ANN, like the natural NN, will be made up of
hubs, also known as neurons or handling components,
that are connected to the network’s framework. ANNs
gather data from nearby nodes and generate outcomes
based on their weights and beginning capabilities. The
variable loads could be used to reflect the strength of
neuronal connections. The loads should be modified
until the network’s result matches the ideal outcome
to complete the learning system. To enable the CR to
learn from its surroundings and make decisions to
improve the correspondence framework’s nature of
administration, counterfeit ANNs were utilized.
37,38
Table 1 also provides a detailed overview of new
technologies in CRNs, such as AI, FL, and GAs.
Applications of CRN
To ensure the end clients’ administration, the modern
wireless network must fulfill the constantly increasing
data transfer capacity requirements (QoS). The board
can increase data transfer capacity beyond its usual
cut-off points with a productive electromagnetic range
and CR innovation.
39
The CRNs’ innovative range the
board considers unlicensed (intellectual) clients using
the officeholder range band without interfering with
occupier clients.
40
The CRN is a smart and adaptable
remote communication system in which CR devices
learn from environmental elements and complete
activity-dependent learning. CR devices are particularly
intelligent in that they can gradually select transporter
frequency, transfer speed, transmission rate, transmis-
sion power, and other parameters. As a result of CR
advances, several new CR network applications are
being created.
41
These outstanding issue centers pre-
sented cutting-edge research findings on the use of
CRN. It is founded on a thought-provoking and
insightful discussion of recent developments in the
application of CRNs and future directions. The appli-
cation of CRSN’s in-body sensors is discussed in this
article by H Serrano Han et al.
42
It depicts a lovely
home and sketches out an antique dwelling framework
using the CRSN. This post suggests CRSN research
headlines for older, more experienced property manag-
ers. As a result, the focus of the article is on embracing
CRSN progress to adapt to dense sensors and hetero-
geneous network conditions.
Public security communication
A CRN is used for public safety communications using
white space. CR is a type of wireless communication
that allows a transceiver to distinguish between active
and inactive communication channels. To do so, avoid
the busy channel and immediately move to the open
one.
43
It has no effect on the interference of licensed
users.
DSA
In the investigation of DSA networks, CR is quite use-
ful. It can quickly identify the band when the PUs are
displayed. A wireless sensor network with hundreds of
sensor nodes spread across the sensing region and a few
meters between neighboring nodes uses CR.
44
It also
looks at how sensor/network groups are evolving in
relation to prior types and how sensor network devel-
opments are being combined with building pushes.
Sensor virtualization module
‘‘Estimation of main channel activity statistics in CR
based on imperfect spectrum sensing,’’ by Pandit and
Singh
45
describes the Sensor Virtualization Module
(SVM). Few IoT assets use apps because of the typical
smokestack programming architecture, in which suppli-
ers supply support programming from start to comple-
tion. Alabama et al.
46
describe a lightweight and
powerful solution that correctly detects channel choice
correspondence in their work ‘‘SVM: Virtualizing IoT
Devices on Mobile Smart Phones for Effective Sensor
Data Management.’’ Another organizational paradigm
depicted in this article is cognitive body sensor net-
works (CBSNs). In this network of local networks,
consistent accessibility is crucial and must be ensured.
Setbacks in the network during an emergency could
prevent a patient from receiving timely clinical care,
which could be fatal.
Detection of primary user emulation attack
The proposed approach principal user emulation attack
(PUEA) relies on cryptographic local persons that
require a little amount of memory and low energy con-
sumption, making it more suitable for devices with lim-
ited resources. It ensures the safety of control data
provided by CBSN sensors to select a certain channel.
L Liu et al. present an energy-efficient layered video
multimedia (LVM) transmission over an Orthogonal
Frequency Division Multiplexing (OFDM)-based CR
framework for video networks using ‘‘A new spectrum
scheduling technique with ant colony optimization
algorithm.’’ van Otterlo M and Wiering M, Yau K-L,
and Barve S and Kulkarni P offer a power fragment
computation using inadequate programming and a
sub-propensity technique based on energy utility (EU).
When the unit transmit power is consumed, the main
show meter EU is supplied to measure the refined
6International Journal of Distributed Sensor Networks
Table 1. Detailed analysis of emerging technologies in CR.
Parameters AI FL GAs
Description An NN is an information
processing system that is based on
how biological nerve systems, such
as the brain, process data.
FL is a computing method based on
‘‘degrees of truth’’ instead of the
standard ‘‘true or false’’ ‘‘ (1 or 0)
binary logic used by modern
computers.
A GA is a technique toward
addressing limited and unregulated
optimization issues that uses a
natural selection process similar to
biological evolution.
Basis of system
algorithms
The algorithm reflects natural
selection, based on Darwin’s
theory of survival of the fittest.
It naturally represents the
process of selecting the fittest
part.
Define linguistic terminology
and variables (start).
For them, create membership
functions (start).
Create a rule knowledge based
(start).
Using membership functions,
convert crisp data into fuzzy
datasets (fuzzification).
In the rule basis, evaluate the
rules (inference engine).
Combine the outcomes of each
rule (inference engine).
Convert the output data into values
that are not fuzzy.
The program chooses a fitness
function based on the starting
population.
The fitness function aids in the
generation of an optimal or
near-optimal solution by the
algorithm.
The population is maintained
and evolved via the algorithm’s
screening, crossover, and
mutation procedures.
It creates numerous
populations until the
optimization restrictions are
met.
Complexity It being more complex than FL. It is being less complex. Depends on fitness/ objective
function.
Processing time Little High Minimum elapse time.
Flexibility This system is difficult to modify. This system is easy to modify. This is an artificially intelligent and
adaptable system.
Utilization It assists in performing the
predictions, makes decisions to
improve the correspondence
framework’s nature of
administration
and to enable the CR to learn from
its surroundings.
Performing pattern recognition.
Having the potential to direct
machines and consumer goods.
May not provide exact logic,
but it does provide adequate
reasoning.
Used by engineers to deal with
ambiguity.
Utilized in a variety of
optimization issues.
Framework utilizes more
contentions, as this string
develops longer.
It is resolving multi-objective
issues.
System’s training It trains itself by learning from
dataset.
It may necessitate extensive
verification and testing.
It can retrieve new patterns for
network classification
Applications Pattern recognition; likewise,
spam detection in email and
cancer detection in the human
body.
Forecast, that is, weather
forecasting and stock market
prediction
In information transmission
task,
obstacle and power the board,
range openness examination
methods, and resource segment.
It can empower mindfulness
handling,
Navigation and learning,
the traveling salesperson
problem (TSP),
GPS system
(continued)
Alkhayyat et al. 7
notion of reproduced video at all partners.
50
The goal
is to expand the EU as a whole while also developing
the intersession/interlayer subcarriers that come and go
in terms of control responsibilities. To achieve the fair,
it does a subcarrier job for the base layer and updates
layers with appropriate estimations, resulting in an
optimal power task evaluation for constructing the
future EU using fragmented programming.
FL with cross-layer approach
In this research by Arunthavanathan et al.,
51
the crea-
tors offer a dynamic frequency allocation, unusually
termed CRN. The purpose of this research is that
rerouting is costly to the amount of energy, time, and
throughput. This approach is more intelligent to choose
a path, needing smaller channel trading. This research
examines how tactical things may perform over
dynamic frequencies out the hypothesis for directly
trading the degree of circumstances and present an
intriguing course confirmation framework to coordi-
nate the constant channel exchanging. Since unneeded
commitment on a certain place point causes network
dispersing and starts to continue rerouting, the sug-
gested demonstrate circles the network lifespan is pro-
longed by the organizational overheads among
academic consumers in the network. This displays the
join’s capacity to mind and gets at data using a cross-
layer method.
52–54
Challenges, limitations, and strength
Fuzzy logics
Challenges. Fuzzy controllers provide the benefit of
allowing specialists to apply their qualitative under-
standing of operations. Experts, however, find design-
ing fuzzy controllers using their heuristic approach
difficult.
Limitations. The accuracy of these systems is harmed
since they rely on incorrect data and inputs. There is
no one-size-fits-all approach to solve the problem with
FL.
55
Because the results are frequently erroneous, it is
not commonly recognized.
Strength. FL enables enhanced and more efficient
machine control while also lowering costs. Although
FL has been criticized for being imprecise, the conclu-
sions are acceptable, especially when dealing with
faulty inputs. FL is essential for forecasting future
events.
FL is adaptable, taking into account both natural
knowledge and direct computation, execution, and
translation.
56
As a result, the main advantage of FL for
Table 1. Continued
Parameters AI FL GAs
Working factors Quality and the quantity of the
data provided.
Initial weights.
Cumulative weight adjustment
versus incremental updating.
The steepness of the activation
function l
Learning constant hand
momentum method.
Recombination operator is the
real factor behind the whole
system.
Crossover probability specifies
how frequently crossover will
be conducted.
Mutation probability indicates
how frequently chromosomal
segments will be modified.
The middle recurrence,
transmission power, and
regulation sort.
They utilize historical data to
take the search to the best
performing region within the
solution space.
Employ the concept of genetics
and natural selection to
provide solutions to problems.
Knowledge source Sample sets Human experts Chromosomes set
Learning mechanism Adjusting weights Induction Optimization technique
Reasoning mechanism Parallel computation Heuristic search Metaheuristic
History Warren McCulloch and Walter
Pitts concocted ANNs in 1943,
drawing motivation from the focal
sensory system.
In the 1960s, Lotfi Zadeh of the
University of California in Berkeley
proposed the concept of FL.
Algorithms with genetic elements,
Friedberg (1958), led research to
the improvement of GAs.
8International Journal of Distributed Sensor Networks
continuous applications such as CR is its simplicity
and adaptability. When the information is ambiguous,
loud, or insufficient, FL can be used to detect patterns.
Genetic algorithms
Challenges. GAs are a randomized heuristic inquiry
strategy in which the population contains rival arrange-
ments established through transformation and intersec-
tion. Moreover, GA is vital and uncomplicated because
the upsides of the well-being aim capability are used
for streamlining. Besides, GA may not merge to a
worldwide ideal, notably in populaces with numerous
individuals and execution pointers. GAs require earlier
information, which is based on learning and inferred
wellness functions: new rules are developed based on
the training instances and trends found in prior search
phrases.
22,57,58
The challenge must be set up in such a
manner that future generations are encouraged to pick
better genes, and the parameters must be chosen to
reflect the fitness function. Since the well-being evalua-
tion is computationally demanded, GAs are sluggish.
Because they depend on the examined issue, determin-
ing chromosomal representation of parameters,
domain, and range is problematic.
Limitations. Because development based on wellness
capacities cannot provide consistent enhancement reac-
tion times, the employment of continuous GAs is lim-
ited. FL is used to show frameworks that are difficult
to show due to ambiguous quality boundaries.
Strength. GA tackles a multi-objective enhancement
issue and arranges the CR progressively considering
the changing remote climate. GAs are faster and con-
sume less memory while looking through a vast region.
Artificial neural network
Challenges. The ANN is based on the natural sensory
system and is used to complete the learning system, find
new examples, group them, and improve the dynamic
interaction. To assemble NNs, a few tests are required,
reducing the complexity of the arrangement.
59
ANNs
could be integrated with Case Based Reasoning (CBR)
and GA during the preparation stage. Because they are
required, ANNs are called administered learning.
Limitations. Experimental danger minimization is the
premise of ANNs. When many needs must be accom-
plished at the same time, the technique provides for
answers. NNs may take a long time to prepare depend-
ing on the size of the network.
Strength. They provide the ability to respond to modest
climate changes and particular information about the
option. ANNs are extremely adaptable and may por-
tray a wide range of abilities. In any case, they are not
sequential or deterministic. Furthermore, once the NN
has been properly created, it will desire to work in for-
ward spread mode as an insightful device on various
types of data. The enlarged model for forward spread
run information would then be used for further analy-
sis and comprehension. Furthermore, an NN can be
over-prepared, indicating that the network is not ready.
For ANNs, infinite recursion and organized portrayals
can be excessive.
60
Conclusion
This investigation depicted a study of the use of AI
methods to CRNs. To arrive at an acceptable conclu-
sion, a fuzzy inference system is based on the experi-
ences of a group of network specialists. Data-driven
models are used to supplement physically based mod-
els. It has the potential to displace physically based
models. When physically based models are not possible
to build due to a lack of process data, AI techniques
can be used to generate a model of the process. The lit-
erary assessment of cutting-edge achievements in apply-
ing AI processes to CR is offered and organized into
the fundamental artificial reasoning techniques listed
below. This study looked into CR assignments and
roadblocks, and the critical evaluation and challenges
of using the learning technique in CRNs. Finally, the
article presented a variety of perspectives and
approaches to dealing with the use of learning in
CRNs.
Future scope
We looked at a number of AI strategies that could be
applied in CRNs. These algorithms have a lot of poten-
tial for use in CRNs. We have only recently begun
investigating the use of machine learning in the CRN.
There will be many more advancements in this sector.
NNs must be properly built for the challenge; other-
wise, performance may suffer; yet, when utilized cor-
rectly, they are a very effective tool for solving
problems.
61,62
There are more forms of NNs than
ANNs, such as convolutional neural networks (CNN),
recurrent neural networks (RNN), and long short-term
memory (LSTM). It will be fascinating to investigate
Alkhayyat et al. 9
their potential applications in CR. Combining various
NNs in a CRN can also be fascinating.
Declaration of conflicting interests
The author(s) declared no potential conflicts of interest with
respect to the research, authorship, and/or publication of this
article.
Funding
The author(s) received no financial support for the research,
authorship, and/or publication of this article.
ORCID iD
Ashish Bagwari https://orcid.org/0000-0002-6232-2772
References
1. Mitola J and Maguire GQ. Cognitive radio: making soft-
ware radiosmorepersonal. J IEEE Personal Commun
1999; 6: 13–18.
2. Mitola J III. Cognitive radio: an integrated agent architec-
ture for software defined radio. Stockholm: KTH, 2012.
3. Haykin S. Cognitive radio: brain-empowered wireless
communications. J IEEE Select Areas Commun 2005;
23(2): 200–220.
4. Wang L, Xu W, He Z, et al. Algorithms for optimal
resource allocation in heterogeneous cognitive radio net-
works. In: Proceedings of the second international confer-
ence on power electronics and intelligent transportation
system, Shenzhen, China, 19–20 December 2009, pp.396–
400. New York: IEEE.
5. Zhao Y and Morales-Tirado L. Cognitive radio technol-
ogy: principles and practice. In: Proceedings of the inter-
national conference on computing, networking, and
communications, Maui, HI, 30 January–2 February 2012,
pp.650–654. New York: IEEE.
6. Bkassiny M, Li Y and Jayaweera SK. A survey on
machine-learning techniques in cognitive radios. JIEEE
Commun Surv Tutor 2013; 15: 1136–1159.
7. Gavrilovska L, Atanasovski V, Macaluso I, et al. Learn-
ing and reasoning in cognitive radio networks. JIEEE
Commun Surv Tutor 2013; 15: 1761–1777.
8. Biglieri E, Goldsmith AJ, Greenstein LJ, et al. Principles
of cognitive radio. New York: Cambridge University
Press, 2012.
9. Khan F and Nakagawa K. Comparative study of spec-
trum sensing techniques in cognitive radio networks. In:
2013 world congress on computer and information technol-
ogy, Sousse, Tunisia, 22–24 June 2013. New York: IEEE.
10. Wyglinski M, Nekovee M and Hou T. Cognitive radio
communications and networks: principles and practice.San
Diego, CA: Elsevier, 2010.
11. Qiu RC, Hu Z, Li H, et al. Cognitive radio communica-
tions and networking: principles and practice. Chichester:
Wiley, 2012.
12. Umar R and Sheikh AUH. Cognitive radio-oriented
wireless networks: challenges and solutions. In: Proceed-
ings of the international conference on multimedia comput-
ing and systems, Tangier, Morocco, 10–12 May 2012.
New York: IEEE.
13. Ghasemi A and Sousa ES. Spectrum sensing in cognitive
radio networks: requirements, challenges, and design
trade-offs. IEEE Commun Magzine 2008; 46: 32–39.
14. Wang B and Liu KJR. Advances in cognitive radio net-
works: a survey. J IEEE Select Topics Signal Process
2011; 5: 5–23.
15. Nguyen VT, Villain F and Le Y. Cognitive radio systems:
overview and challenges. In: Proceedings of the 3rd inter-
national conference on awareness science and technology,
Dalian, China, 27–30 September 2011. New York: IEEE.
16. Russell SJ and Norvig P. Artificial intelligence a modern
approach. London: Pearson Education, 2014.
17. Zadeh L. Communication fuzzy algorithms. Inform Con-
trol 1968; 12: 94–102.
18. Dadios E. Fuzzy logic—algorithms, techniques, and imple-
mentations. Rijeka: InTech, 2012.
19. Suh S, Kim B-S and Chung JH. Convergence research
directions in cognitive sensor networks for elderly hous-
ing design. Int J Distr Sensor Networks 2015; 2015: 2.
20. Kaur P, Uddin M and Khosla A. Fuzzy-based adaptive
bandwidth allocation scheme in cognitive radio networks.
In: Proceedings of the eighth international conference on
ICT and knowledge engineering, Bangkok, Thailand, 24–
25 November 2010, pp.41–45. New York: IEEE.
21. Liu L, Wang N, Chen Z, et al. A novel spectrum schedul-
ing scheme with ant colony optimization algorithm. Algo-
rithms 2018; 11: 16.
22. Park JH, Lee WC, Choi JP, et al. Applying case-based
reasoning to tactical cognitive sensor networks for
dynamic frequency allocation. Sensors 2018; 18: 4294.
23. Qin H, Zhu L and Li D. Artificial mapping for dynamic
resource management of cognitive radio networks. In: Pro-
ceedings of the eighth international conference on wireless
communications, networking and mobile computing, Shang-
hai, China, 21–23 September 2012. New York: IEEE.
24. Lee K and El-Sharkawi M. Modern heuristic optimization
techniques: theory and applications to power systems.
Hoboken, NJ: Wiley, 2008.
25. El Morabit Y, Mrabti F and Abarkan H. Survey of artifi-
cial intelligence approaches in cognitive radio networks. J
Informat Commun Converge Eng 2019; 17: 21–40.
26. Guru R, Devi K and Marichamy P. Spectrum selection
and decision using neural and fuzzy optimization
approaches. Wireless Networks 2022; 28: 1–25.
27. Abd El-Malek AH, Aboulhassan MA and Abdou MA.
Evolutionary computation technique enhancing the per-
formance of cognitive radio networks with energy har-
vesting. Ad Hoc Networks 2020; 107: 102254.
28. Aryal S, Dhungana H and Paudyal K. A novel approach
for interference management in cognitive radio. In: Pro-
ceedings of the third Asian Himalayas international confer-
ence on Internet, Kathmandu, India, 23–25 November
2012, pp.1–5. New York: IEEE.
10 International Journal of Distributed Sensor Networks
29. Matinmikko M, Ser Del J, Rauma T, et al. Fuzzy-logic
based framework for spectrum availability assessment in
cognitive radio systems. J IEEE Select Areas Commun
2013; 31: 1136–1159.
30. Kantardzic M. Data mining: concepts, models, methods,
and algorithms. Hoboken, NJ: Wiley, 2003.
31. Chen S, Newman TR, Evans JB, et al. Genetic algorithm-
based optimization for cognitive radio networks. In:
IEEE Sarnoff symposium, Princeton, NJ, 12–14 April
2010. New York: IEEE.
32. Moghal MR, Khan MA and Bhatti HA. Spectrum opti-
mization in cognitive radios using elitism in genetic algo-
rithms. In: Proceedings of the 6th international conference
on emerging technologies, Islamabad, Pakistan, 18–19
October 2010, pp.49–54. New York: IEEE.
33. Harris JF, He D, Michel G, et al. Cognitive radio and RF
communications design optimization using genetic algo-
rithms. In: Proceedings of the IEEE military communica-
tions conference, Orlando, FL, 29–31 October 2007, pp.1–
6. New York: IEEE.
34. Zeng C and Zu Y. Cognitive radio resource allocation is
based on niche adaptive genetic algorithm. In: Proceed-
ings of the international conference on communication tech-
nology and application, Beijing, China, 14–16 October
2011. New York: IEEE.
35. Rojas R. Neural networks: a systematic introduction. Ber-
lin; Heidelberg: Springer, 1996.
36. Friedberg RM. A learning machine: Part 1. IBM J Res
Dev. 1958; 2(1): 2–13.
37. Tan X, Huang H and Ma L. Frequency allocation with
artificial neural networks in cognitive radio system. In:
Proceedings of the IEEE TENCON spring conference,
Sydney, NSW, Australia, 17–19 April 2013. New York:
IEEE.
38. Zhang T, Wu M and Liu C. Cooperative spectrum sen-
sing based on artificial neural networks for cognitive
radio systems. In: Proceedings of the 8th international
conference on wireless communications, networking and
mobile computing, Shanghai, China, 21–23 September
2012. New York: IEEE.
39. Yang Y, Jiang H, Liu C, et al. Research on cognitive
radio engine based on genetic algorithm and radial basis
function artificial neural network. In: Proceedings of the
spring congress on engineering and technology, Xian,
China, 27–30 May 2012. New York: IEEE.
40. Popoola JJ and Van Olst R. Application of artificial
neural network for sensing primary radio signals in a
cognitive radio environment. In: Proceedings of the Afri-
can conference, Livingstone, Zambia, 13–15 September
2011. New York: IEEE.
41. Bellhouse D. The problem of Waldegrave. Electronic
2007; 3: 1–12.
42. Han Z, Niyato D, Saad W, et al. Game theory in wireless
and communication networks: theory, models, and applica-
tions. New York: Cambridge University Press, 2012.
43. Abdulghfoor B, Ismail M and Nordin R. Application of
game theory to underlay ad-hoc cognitive radio networks:
an overview. In: Proceedings of the IEEE international
conference on space science and communication, Melaka,
Malaysia, 1–3 July 2013. New York: IEEE.
44. Li Y, Zhang H and Asami T. On the cooperation between
cognitive radio users and femtocell networks for coopera-
tive spectrum sensing and self-network. In: Proceedings of
the wireless communications and networking conference,
Shanghai, China, 7–10 April 2013, pp.446–451. New
York: IEEE.
45. Pandit S and Singh G. Spectrumsharing in cognitive radio
using game theory. In: Proceedings of the 3rd international
advance computing conference, Ghaziabad, India, 22–23
February 2013. New York: IEEE.
46. Alabama S, Agarwal A, Goel N, et al. Comparison of
spectrum management without game theory (SMWG)
and with game theory (SMG) for network performance
in the cognitive radio network. In: Proceedings of seventh
international conference on broadband, wireless computing,
communication, and applications, Victoria, BC, Canada,
12–14 November 2012. New York: IEEE.
47. van Otterlo M and Wiering M. Reinforcement learning:
state-of-the-art. Berlin; Heidelberg: Springer, 2012.
48. Yau K-L. Reinforcement learning approach for centra-
lized cognitive radio systems. In: Proceedings of the inter-
national conference on wireless communications and
applications, Kuala Lumpur, Malaysia, 8–10 October
2012. New York: IEEE.
49. Barve S and Kulkarni P. Dynamic channel selection and
routing through reinforcement learning in cognitive radio
networks. In: Proceedings of the international conference
on computational intelligence and computing research,
Coimbatore, India, 18–20 December 2012. New York:
IEEE.
50. Zhou P, Chang Y and Copeland JA. Reinforcement
learning for repeated power control game in cognitive
radio network. IEEE J Select Areas Commun 2012; 30:
54–69.
51. Arunthavanathan S, Kandeepan S and Evans RJ. Rein-
forcement learning-based secondary user transmissions in
cognitive radio networks. In: Proceedings of the global
communications conference, Atlanta, GA, 9–13 December
2013. New York: IEEE.
52. Han J and Kamber M. Data mining: concepts and tech-
niques. Waltham, MA: Morgan Kaufmann, 2005.
53. Kim SW, Pan M, Joshi GP, et al. Applications of cogni-
tive radio networks: recent advances and future direc-
tions. Int J Distr Sensor Networks. Epub ahead of print
14 January 2016. DOI: 10.1155/2016/4964068.
54. Leo
´n O, Herna
´ndez-Serrano J, Garrigues C, et al. A
cognitive-radio-based method for improving availability
in body sensor networks. Int J Distr Sensor Networks
2015; 2015: 1–13.
55. Joshi GP, Nam SY, Kim C-S, et al. A cross-layer-based
routing protocol for ad hoc cognitive radio networks. Int
J Distr Sensor Networks. Epub ahead of print 4 October
2015. DOI: 10.1155/2015/938191.
56. Toma OH, Lopez-Benitez MP, Patel DK, et al. Estima-
tion of primary channel activity statistics in cognitive
radio based on imperfect spectrum sensing. J IEEE Trans
Commun 2016; 68: 2016–2031.
57. Ko J, Lee B-B, Lee K, et al. Sensor virtualization mod-
ule: virtualizing IoT devices on mobile smartphones for
effective sensor data management. Int J Distr Sensor
Alkhayyat et al. 11
Networks. Epub ahead of print 4 October 2015. DOI:
10.1155/2015/730762.
58. Liu L, Wang N, Chen Z, et al. A novel spectrum schedul-
ing scheme with ant colony optimization algorithm. Algo-
rithms 2018; 11: 16.
59. Ozturk M, Akram M, Hussain S, et al. Novel QoS-aware
proactive spectrum access techniques for cognitive radio using
machine learning. J IEEE Access 2019; 7: 70811–70827.
60. Nasser A, Chaitou M, Mansour A, et al. A Deep Artifi-
cial neural Network Model for Hybrid Spectrum Sensing
in Cognitive Radio. Wireless Personal Commun 2021;
118: 281–299.
61. Darabkh K, Amro A, Al-Zubi M, et al. Yet efficient rout-
ing protocols for half-and full-duplex cognitive radio ad-
hoc networks over IoT environment. Network Comput
2021; 173: 102836.
62. Chen S, Shen B, Wang X, et al. Geo-location informa-
tion aided spectrum sensing in cellular cognitive radio
networks. Sensors 2013; 20: 213.
12 International Journal of Distributed Sensor Networks
