Alexandria Engineering Journal,
Год журнала:
2024,
Номер
87, С. 448 - 477
Опубликована: Янв. 1, 2024
This
article
presents
a
useful
application
of
the
Manta
Ray
Foraging
Optimization
(MRFO)
algorithm
for
solving
adaptive
infinite
impulse
response
(IIR)
system
identification
problem.
The
effectiveness
proposed
technique
is
validated
on
four
benchmark
IIR
models
reduced
order
identification.
stability
estimated
assured
by
incorporating
pole-finding
and
initialization
routine
in
search
procedure
MRFO
this
algorithmic
modification
contributes
to
when
seeking
stable
filter
solutions.
absence
such
scheme,
which
primarily
case
with
majority
recently
published
literature,
may
lead
generation
an
unstable
unknown
real-world
instances
(particularly
estimation
increases).
Experiments
conducted
study
highlight
that
helps
achieve
even
though
large
bounds
design
variables
are
considered.
convergence
rate,
robustness,
computational
speed
all
considered
problems
investigated.
influence
control
parameters
performances
evaluated
gain
insight
into
interaction
between
three
foraging
strategies
algorithm.
Extensive
statistical
performance
analyses
employing
various
non-parametric
hypothesis
tests
concerning
consistency
comparison
MRFO-based
approach
six
other
metaheuristic
procedures
investigate
efficiency.
results
mean
square
error
metric
also
improved
solution
quality
compared
techniques
literature.
Journal Of Big Data,
Год журнала:
2024,
Номер
11(1)
Опубликована: Янв. 2, 2024
Abstract
Beluga
Whale
Optimization
(BWO)
is
a
new
metaheuristic
algorithm
that
simulates
the
social
behaviors
of
beluga
whales
swimming,
foraging,
and
whale
falling.
Compared
with
other
optimization
algorithms,
BWO
shows
certain
advantages
in
solving
unimodal
multimodal
problems.
However,
convergence
speed
performance
still
have
some
deficiencies
when
complex
multidimensional
Therefore,
this
paper
proposes
hybrid
method
called
HBWO
combining
Quasi-oppositional
based
learning
(QOBL),
adaptive
spiral
predation
strategy,
Nelder-Mead
simplex
search
(NM).
Firstly,
initialization
phase,
QOBL
strategy
introduced.
This
reconstructs
initial
spatial
position
population
by
pairwise
comparisons
to
obtain
more
prosperous
higher
quality
population.
Subsequently,
an
designed
exploration
exploitation
phases.
The
first
learns
optimal
individual
positions
dimensions
through
avoid
loss
local
optimality.
At
same
time,
movement
motivated
cosine
factor
introduced
maintain
balance
between
exploitation.
Finally,
NM
added.
It
corrects
multiple
scaling
methods
improve
accurately
efficiently.
verified
utilizing
CEC2017
CEC2019
test
functions.
Meanwhile,
superiority
six
engineering
design
examples.
experimental
results
show
has
feasibility
effectiveness
practical
problems
than
methods.
Mathematics,
Год журнала:
2023,
Номер
11(4), С. 851 - 851
Опубликована: Фев. 7, 2023
The
jellyfish
search
(JS)
algorithm
impersonates
the
foraging
behavior
of
in
ocean.
It
is
a
newly
developed
metaheuristic
that
solves
complex
and
real-world
optimization
problems.
global
exploration
capability
robustness
JS
are
strong,
but
still
has
significant
development
space
for
solving
problems
with
high
dimensions
multiple
local
optima.
Therefore,
this
study,
an
enhanced
(EJS)
developed,
three
improvements
made:
(i)
By
adding
sine
cosine
learning
factors
strategy,
can
learn
from
both
random
individuals
best
individual
during
Type
B
motion
swarm
to
enhance
accelerate
convergence
speed.
(ii)
escape
operator,
skip
trap
optimization,
thereby,
exploitation
ability
algorithm.
(iii)
applying
opposition-based
quasi-opposition
population
distribution
increased,
strengthened,
more
diversified,
better
selected
present
new
opposition
solution
participate
next
iteration,
which
solution’s
quality,
meanwhile,
speed
faster
algorithm’s
precision
increased.
In
addition,
performance
EJS
was
compared
those
incomplete
improved
algorithms,
some
previously
outstanding
advanced
methods
were
evaluated
on
CEC2019
test
set
as
well
six
examples
real
engineering
cases.
results
demonstrate
increase
calculation
practical
applications
also
verify
its
superiority
effectiveness
constrained
unconstrained
problems,
therefore,
suggests
future
possible
such
