Mathematics,
Год журнала:
2024,
Номер
12(20), С. 3221 - 3221
Опубликована: Окт. 14, 2024
The
Arithmetic
Optimization
Algorithm
(AOA)
is
a
novel
metaheuristic
inspired
by
mathematical
arithmetic
operators.
Due
to
its
simple
structure
and
flexible
parameter
adjustment,
the
AOA
has
been
applied
solve
various
engineering
problems.
However,
still
faces
challenges
such
as
poor
exploitation
ability
tendency
fall
into
local
optima,
especially
in
complex,
high-dimensional
In
this
paper,
we
propose
Hybrid
Improved
(HIAOA)
address
issues
of
susceptibility
optima
AOAs.
First,
grey
wolf
optimization
incorporated
AOAs,
where
group
hunting
behavior
GWO
allows
multiple
individuals
perform
searches
at
same
time,
enabling
solution
be
more
finely
tuned
avoiding
over-concentration
particular
region,
which
can
improve
capability
AOA.
Second,
end
each
run,
follower
mechanism
Cauchy
mutation
operation
Sparrow
Search
are
selected
with
probability
perturbed
enhance
escape
from
optimum.
overall
performance
improved
algorithm
assessed
selecting
23
benchmark
functions
using
Wilcoxon
rank-sum
test.
results
HIAOA
compared
other
intelligent
algorithms.
Furthermore,
also
three
design
problems
successfully,
demonstrating
competitiveness.
According
experimental
results,
better
test
than
comparator.
Alexandria Engineering Journal,
Год журнала:
2024,
Номер
97, С. 267 - 282
Опубликована: Апрель 19, 2024
Nuclear
reactor
control
is
pivotal
for
the
safe
and
efficient
operation
of
nuclear
power
plants,
facilitating
regulation
reactivity.
This
study
introduces
an
optimized
fractional-order
proportional-integral-derivative
(FOPID)
controller
tailored
maintaining
reactivity
levels
in
particularly
during
load-following
operations.
The
adjusts
position
rod
to
regulate
output
effectively.
We
enhance
FOPID
controller's
performance
using
a
modification
Planet
Optimization
Algorithm
(POA-M),
leveraging
strengths
Arithmetic
(AOA)
improve
its
exploitation
capabilities.
evaluate
efficacy
POA-M-FOPID
against
traditional
techniques,
including
POA,
AOA,
Particle
Swarm
(PSO).
assess
Egyptian
Testing
Research
Reactor
(ETRR-2)
as
case
study.
Our
results
demonstrate
that
outperforms
alternative
algorithms
across
various
metrics,
exhibiting
superior
resilience
efficiency.
Notably,
utilization
yields
remarkable
improvements
performance,
achieving
significantly
reduced
settling
time
(25.27
sec)
maximum
overshoot
(0.67
%)
compared
conventional
controllers
incorporating
PSO
methods.
These
findings
underscore
effectiveness
enhancing
systems,
offering
potential
benefits
broader
industry
terms
safety,
stability,
operational
PLoS ONE,
Год журнала:
2025,
Номер
20(2), С. e0318203 - e0318203
Опубликована: Фев. 5, 2025
In
high-dimensional
scenarios,
trajectory
planning
is
a
challenging
and
computationally
complex
optimization
task
that
requires
finding
the
optimal
within
domain.
Metaheuristic
(MH)
algorithms
provide
practical
approach
to
solving
this
problem.
The
Crayfish
Optimization
Algorithm
(COA)
an
MH
algorithm
inspired
by
biological
behavior
of
crayfish.
However,
COA
has
limitations,
including
insufficient
global
search
capability
tendency
converge
local
optima.
To
address
these
challenges,
Enhanced
(ECOA)
proposed
for
robotic
arm
planning.
ECOA
incorporates
multiple
novel
strategies,
using
tent
chaotic
map
population
initialization
enhance
diversity
replacing
traditional
step
size
adjustment
with
nonlinear
perturbation
factor
improve
capability.
Furthermore,
orthogonal
refracted
opposition-based
learning
strategy
enhances
solution
quality
efficiency
leveraging
dominant
dimensional
information.
Additionally,
performance
comparisons
eight
advanced
on
CEC2017
test
set
(30-dimensional,
50-dimensional,
100-dimensional)
are
conducted,
ECOA’s
effectiveness
validated
through
Wilcoxon
rank-sum
Friedman
mean
rank
tests.
experiments,
demonstrated
superior
performance,
reducing
costs
15%
compared
best
competing
10%
over
original
COA,
significantly
lower
variability.
This
demonstrates
improved
quality,
robustness,
convergence
stability.
study
successfully
introduces
strategies
improvement,
as
well
verification
in
path
results
confirm
potential
challenges
various
engineering
applications.
CAAI Transactions on Intelligence Technology,
Год журнала:
2025,
Номер
unknown
Опубликована: Фев. 12, 2025
Abstract
In
the
era
of
big
data,
personalised
recommendation
systems
are
essential
for
enhancing
user
engagement
and
driving
business
growth.
However,
traditional
algorithms,
such
as
collaborative
filtering,
face
significant
challenges
due
to
data
sparsity,
algorithm
scalability,
difficulty
adapting
dynamic
preferences.
These
limitations
hinder
ability
provide
highly
accurate
recommendations.
To
address
these
challenges,
this
paper
proposes
a
clustering‐based
method
that
integrates
an
enhanced
Grasshopper
Optimisation
Algorithm
(GOA),
termed
LCGOA,
improve
accuracy
efficiency
by
optimising
cluster
centroids
in
environment.
By
combining
K‐means
with
GOA,
which
incorporates
Lévy
flight
mechanism
multi‐strategy
co‐evolution,
our
overcomes
centroid
sensitivity
issue,
key
limitation
clustering
techniques.
Experimental
results
across
multiple
datasets
show
proposed
LCGOA‐based
significantly
outperforms
conventional
algorithms
terms
accuracy,
offering
more
relevant
content
users
greater
customer
satisfaction
PLoS ONE,
Год журнала:
2025,
Номер
20(3), С. e0316287 - e0316287
Опубликована: Март 6, 2025
The
accurate
prediction
and
interpretation
of
corporate
Environmental,
Social,
Governance
(ESG)
greenwashing
behavior
is
crucial
for
enhancing
information
transparency
improving
regulatory
effectiveness.
This
paper
addresses
the
limitations
in
hyperparameter
optimization
interpretability
existing
models
by
introducing
an
optimized
machine
learning
framework.
framework
integrates
Improved
Hunter-Prey
Optimization
(IHPO)
algorithm,
eXtreme
Gradient
Boosting
(XGBoost)
model,
SHapley
Additive
exPlanations
(SHAP)
theory
to
predict
interpret
ESG
behavior.
Initially,
a
comprehensive
dataset
was
developed
through
extensive
literature
review
expert
interviews.
IHPO
algorithm
then
employed
optimize
hyperparameters
XGBoost
forming
IHPO-XGBoost
ensemble
model
predicting
Finally,
SHAP
used
model's
outcomes.
results
demonstrate
that
achieves
outstanding
performance
greenwashing,
with
R²,
RMSE,
MAE,
adjusted
R²
values
0.9790,
0.1376,
0.1000,
0.9785,
respectively.
Compared
traditional
HPO-XGBoost
combined
other
algorithms,
exhibits
superior
overall
performance.
analysis
using
highlights
key
features
influencing
outcomes,
revealing
specific
contributions
feature
interactions
impacts
individual
sample
features.
findings
provide
valuable
insights
regulators
investors
more
effectively
identify
assess
potential
behavior,
thereby
efficiency
investment
decision-making.
