Research Square (Research Square),
Journal Year:
2024,
Volume and Issue:
unknown
Published: Dec. 20, 2024
Abstract
The
full
text
of
this
preprint
has
been
withdrawn,
as
it
was
submitted
in
error.
Therefore,
the
authors
do
not
wish
work
to
be
cited
a
reference.
Questions
should
directed
corresponding
author.
Scientific Reports,
Journal Year:
2025,
Volume and Issue:
15(1)
Published: March 7, 2025
In
this
study,
a
novel
hybrid
metaheuristic
algorithm,
termed
(BES-GO),
is
proposed
for
solving
benchmark
structural
design
optimization
problems,
including
welded
beam
design,
three-bar
truss
system
optimization,
minimizing
vertical
deflection
in
an
I-beam,
optimizing
the
cost
of
tubular
columns,
and
weight
cantilever
beams.
The
performance
BES-GO
algorithm
was
compared
with
ten
state-of-the-art
algorithms:
Bald
Eagle
Search
(BES),
Growth
Optimizer
(GO),
Ant
Lion
Optimizer,
Tuna
Swarm
Optimization,
Tunicate
Algorithm,
Harris
Hawk
Artificial
Gorilla
Troops
Dingo
Particle
Grey
Wolf
Optimizer.
leverages
strengths
both
BES
GO
techniques
to
enhance
search
capabilities
convergence
rates.
evaluation,
based
on
CEC'20
test
suite
selected
shows
that
consistently
outperformed
other
algorithms
terms
speed
achieving
optimal
solutions,
making
it
robust
effective
tool
Optimization.
International Journal of Communication Systems,
Journal Year:
2025,
Volume and Issue:
38(8)
Published: April 13, 2025
ABSTRACT
Multi‐antenna
wireless
systems
enhanced
by
reconfigurable
intelligent
surfaces
(RISs)
offer
improved
spectral
and
energy
efficiency.
RIS
improves
coverage
efficiency,
but
accurate
channel
estimation
is
challenging.
The
least‐squares
(LS)
strategy
sub‐optimal,
while
the
MMSE
estimator
difficult
due
to
nonlinearity
non‐Gaussianity.
To
overcome
these
issues,
RIS‐Aided
MISO
Channel
Estimation
using
Fuzzy
Embedded
Recurrent
Neural
Network
Binary
Kepler
Optimization
Algorithm
(RIS‐MISO‐
CE
‐FERNN‐BKOA)
proposed.
Initially,
Linear
Minimum
Mean
Square
Error
(LMMSE)
estimator,
optimized
with
BKOA
for
phase
shifts,
achieved
higher
accuracy
than
LS
approach.
further
enhance
efficiency
better
approximate
globally
optimal
(FERNN)
RIS‐MISO‐
‐FERNN‐BKOA
method
attain
34.56%,
25.63%,
18.89%
accuracy;
28.63%,
25.41%,
19.23%
lower
MMSE;
33.56%,
29.78%,
25.74%
SNR
when
analyzed
existing
techniques.
proposed
technique
achieves
compared
conventional
models,
making
it
a
robust
solution
RIS‐assisted
communication
systems.
Journal of King Saud University - Computer and Information Sciences,
Journal Year:
2024,
Volume and Issue:
36(6), P. 102093 - 102093
Published: June 13, 2024
This
paper
examines
the
performance
of
three
binary
metaheuristic
algorithms
when
applied
to
two
distinct
knapsack
problems
(0–1
(KP01)
and
multidimensional
(MKP)).
These
are
based
on
classical
mantis
search
algorithm
(MSA),
quadratic
interpolation
optimization
(QIO)
method,
well-known
differential
evolution
(DE).
Because
these
were
designed
for
continuous
problems,
they
could
not
be
used
directly
solve
problems.
As
a
result,
V-shaped
S-shaped
transfer
functions
propose
variants
algorithms,
such
as
(BDE),
(BQIO),
(BMSA).
evaluated
using
various
high-dimensional
KP01
examples
compared
several
techniques
determine
their
efficacy.
To
enhance
those
combined
with
repair
operator
2
(RO2)
offer
better
hybrid
variants,
namely
HMSA,
HQIO,
HDE.
Those
medium-
large-scale
MKP
instances,
well
other
demonstrate
effectiveness.
comparison
is
conducted
metrics:
average
fitness
value,
Friedman
mean
rank,
computational
cost.
The
experimental
findings
that
HQIO
strong
alternative
solving
MKP.
In
addition,
proposed
Merkle-Hellman
Knapsack
Cryptosystem
resource
allocation
problem
in
adaptive
multimedia
systems
(AMS)
illustrate
effectiveness
optimize
real
applications.
handling
knapsack-based
optimization
algorithms
play
a
crucial
role
in
solving
complex
problems
various
domains.
Single-objective
aim
to
discover
the
most
optimal
solution
for
particular
objective
function,
commonly
distinguished
by
single
criterion
or
goal.
Grey
Wolf
optimizer
(GWO)
is
swarm-based
algorithm
that
has
gained
attention
due
its
simplicity
and
efficiency
problems.
In
this
article,
we
propose
an
advanced
version
of
GWO,
which
referred
as
Advanced
Trending-based
(ATGWO),
specifically
tailored
single-objective
The
motivation
behind
modification
stems
from
need
improve
performance
metrics
original
GWO
avoid
local
optimum.
By
altering
algorithm's
coefficients,
enhance
convergence
rate,
exploration,
exploitation
abilities.
To
evaluate
proposed
ATGWO
algorithm,
conduct
simulations
using
7
multimodal
benchmark
functions.
results
suggest
although
excels
accuracy,
it
more
delay
comparison
with
GWO.
This
study
paves
way
future
research
about
algorithms.
Deleted Journal,
Journal Year:
2024,
Volume and Issue:
20(7s), P. 1534 - 1544
Published: May 16, 2024
The
expansion
of
technology
and
computer
science,
as
well
advancements
in
language
instruction
learning
methodologies,
has
enabled
computer-assisted
technologies
to
tackle
this
challenge.
In
the
field
Chinese
learning,
a
few
computerized
systems
country
abroad
concentrate
mainly
on
language,
grammar
acquisition
only
have
one
or
two
assessment
indicators
basis
evaluation,
that
definite
functional
flaws
provide
general
learners'
pronunciation.
manuscript,
Language
Dissemination
Paths
Modes
Aided
by
Computer
Technology
(LDPM-QICCNN-KOA)
are
proposed.
input
data
collected
from
Corpus
dataset.
Then
is
given
into
unscented
trainable
kalman
filter
for
preprocessing
data.
preprocessed
provided
QICCNN
Dissemination.
general,
based
Quantum-inspired
Complex
Convolutional
Neural
Network
doesn’t
express
adapting
optimization
approaches
determine
optimal
parameters
ensure
exact
identification.
Hence,
KOA
utilized
enhance
Network,
which
accurately
done
Modes.
proposed
LDPM-QICCNN-KOA
method
executed
python.
performance
technique
analyzed
with
other
existing
methods.
attains
26.36%,
20.69%
35.29%
higher
accuracy;
19.23%,
23.56%,
33.96%
F1-Score;
26.28%,
31.26%,
19.66%
precision
when
comparing
methods
such
research
network
oral
English
teaching
system
depend
machine
(LDPM-DBN),
nonlinear
speech
recognition
structure
deep
algorithm
(LDPM-DNN),
open
scoring
neural
(LDPM-BPNN).
