Mathematics,
Journal Year:
2021,
Volume and Issue:
10(1), P. 102 - 102
Published: Dec. 29, 2021
This
paper
proposes
a
new
meta-heuristic
called
Jumping
Spider
Optimization
Algorithm
(JSOA),
inspired
by
Arachnida
Salticidae
hunting
habits.
The
proposed
algorithm
mimics
the
behavior
of
spiders
in
nature
and
mathematically
models
its
strategies:
search,
persecution,
jumping
skills
to
get
prey.
These
strategies
provide
fine
balance
between
exploitation
exploration
over
solution
search
space
solve
global
optimization
problems.
JSOA
is
tested
with
20
well-known
testbench
mathematical
problems
taken
from
literature.
Further
studies
include
tuning
Proportional-Integral-Derivative
(PID)
controller,
Selective
harmonic
elimination
problem,
few
real-world
single
objective
bound-constrained
numerical
CEC
2020.
Additionally,
JSOA’s
performance
against
several
bio-inspired
algorithms
statistical
results
show
that
outperforms
recent
literature
capable
challenging
unknown
space.
Scientific Reports,
Journal Year:
2022,
Volume and Issue:
12(1)
Published: April 15, 2022
Deep
learning
has
recently
been
utilized
with
great
success
in
a
large
number
of
diverse
application
domains,
such
as
visual
and
face
recognition,
natural
language
processing,
speech
handwriting
identification.
Convolutional
neural
networks,
that
belong
to
the
deep
models,
are
subtype
artificial
which
inspired
by
complex
structure
human
brain
often
used
for
image
classification
tasks.
One
biggest
challenges
all
networks
is
overfitting
issue,
happens
when
model
performs
well
on
training
data,
but
fails
make
accurate
predictions
new
data
fed
into
model.
Several
regularization
methods
have
introduced
prevent
problem.
In
research
presented
this
manuscript,
challenge
was
tackled
selecting
proper
value
parameter
dropout
utilizing
swarm
intelligence
approach.
Notwithstanding
algorithms
already
successfully
applied
domain,
according
available
literature
survey,
their
potential
still
not
fully
investigated.
Finding
optimal
challenging
time-consuming
task
if
it
performed
manually.
Therefore,
proposes
an
automated
framework
based
hybridized
sine
cosine
algorithm
tackling
major
issue.
The
first
experiment
conducted
over
four
benchmark
datasets:
MNIST,
CIFAR10,
Semeion,
UPS,
while
second
tumor
magnetic
resonance
imaging
task.
obtained
experimental
results
compared
those
generated
several
similar
approaches.
overall
indicate
proposed
method
outperforms
other
state-of-the-art
included
comparative
analysis
terms
error
accuracy.
Sensors,
Journal Year:
2022,
Volume and Issue:
22(5), P. 1711 - 1711
Published: Feb. 22, 2022
We
live
in
a
period
when
smart
devices
gather
large
amount
of
data
from
variety
sensors
and
it
is
often
the
case
that
decisions
are
taken
based
on
them
more
or
less
autonomous
manner.
Still,
many
inputs
do
not
prove
to
be
essential
decision-making
process;
hence,
utmost
importance
find
means
eliminating
noise
concentrating
most
influential
attributes.
In
this
sense,
we
put
forward
method
swarm
intelligence
paradigm
for
extracting
important
features
several
datasets.
The
thematic
paper
novel
implementation
an
algorithm
branch
machine
learning
domain
improving
feature
selection.
combination
with
metaheuristic
approaches
has
recently
created
new
artificial
called
learnheuristics.
This
approach
benefits
both
capability
selection
solutions
impact
accuracy
performance,
as
well
known
characteristic
algorithms
efficiently
comb
through
search
space
solutions.
latter
used
wrapper
improvements
significant.
paper,
modified
version
salp
proposed.
solution
verified
by
21
datasets
classification
model
K-nearest
neighborhoods.
Furthermore,
performance
compared
best
same
test
setup
resulting
better
number
proposed
solution.
Therefore,
tackles
demonstrates
its
success
benchmark
Journal of King Saud University - Computer and Information Sciences,
Journal Year:
2024,
Volume and Issue:
36(5), P. 102068 - 102068
Published: May 21, 2024
Long
Short-Term
Memory
(LSTM)
is
a
popular
Recurrent
Neural
Network
(RNN)
algorithm
known
for
its
ability
to
effectively
analyze
and
process
sequential
data
with
long-term
dependencies.
Despite
popularity,
the
challenge
of
initializing
optimizing
RNN-LSTM
models
persists,
often
hindering
their
performance
accuracy.
This
study
presents
systematic
literature
review
(SLR)
using
an
in-depth
four-step
approach
based
on
PRISMA
methodology,
incorporating
peer-reviewed
articles
spanning
2018-2023.
It
aims
address
how
weight
initialization
optimization
techniques
can
bolster
performance.
SLR
offers
detailed
overview
across
various
applications
domains,
stands
out
by
comprehensively
analyzing
modeling
techniques,
datasets,
evaluation
metrics,
programming
languages
associated
networks.
The
findings
this
provide
roadmap
researchers
practitioners
enhance
networks
achieve
superior
results.
Biomimetics,
Journal Year:
2024,
Volume and Issue:
9(5), P. 291 - 291
Published: May 13, 2024
The
dung
beetle
optimization
(DBO)
algorithm,
a
swarm
intelligence-based
metaheuristic,
is
renowned
for
its
robust
capability
and
fast
convergence
speed.
However,
it
also
suffers
from
low
population
diversity,
susceptibility
to
local
optima
solutions,
unsatisfactory
speed
when
facing
complex
problems.
In
response,
this
paper
proposes
the
multi-strategy
improved
algorithm
(MDBO).
core
improvements
include
using
Latin
hypercube
sampling
better
initialization
introduction
of
novel
differential
variation
strategy,
termed
"Mean
Differential
Variation",
enhance
algorithm's
ability
evade
optima.
Moreover,
strategy
combining
lens
imaging
reverse
learning
dimension-by-dimension
was
proposed
applied
current
optimal
solution.
Through
comprehensive
performance
testing
on
standard
benchmark
functions
CEC2017
CEC2020,
MDBO
demonstrates
superior
in
terms
accuracy,
stability,
compared
with
other
classical
metaheuristic
algorithms.
Additionally,
efficacy
addressing
real-world
engineering
problems
validated
through
three
representative
application
scenarios
namely
extension/compression
spring
design
problems,
reducer
welded
beam
