Mathematics,
Год журнала:
2025,
Номер
13(4), С. 668 - 668
Опубликована: Фев. 18, 2025
With
the
rapid
development
of
large
model
technology,
data
storage
as
well
collection
is
very
important
to
improve
accuracy
training,
and
Feature
Selection
(FS)
methods
can
greatly
eliminate
redundant
features
in
warehouse
interpretability
model,
which
makes
it
particularly
field
training.
In
order
better
reduce
warehouses,
this
paper
proposes
an
enhanced
Secretarial
Bird
Optimization
Algorithm
(SBOA),
called
BSFSBOA,
by
combining
three
learning
strategies.
First,
for
problem
insufficient
algorithmic
population
diversity
SBOA,
best-rand
exploration
strategy
proposed,
utilizes
randomness
optimality
random
individuals
optimal
effectively
algorithm.
Second,
address
imbalance
exploration/exploitation
phase
segmented
balance
proposed
segmenting
population,
targeting
different
natures
with
degrees
exploitation
performance,
improving
quality
FS
subset
when
algorithm
solved.
Finally,
performance
a
four-role
strengthens
effective
ability
enhances
classification
guidance
through
four
population.
Subsequently,
BSFSBOA-based
method
applied
solve
36
problems
involving
low,
medium,
high
dimensions,
experimental
results
show
that,
compared
BSFSBOA
improves
more
than
60%,
also
ranks
first
feature
size,
obtains
least
runtime,
confirms
that
robust
efficient
solution
stability,
practicality.
Neural Computing and Applications,
Год журнала:
2024,
Номер
36(33), С. 20723 - 20750
Опубликована: Авг. 16, 2024
Abstract
Accurately
predicting
crop
yield
is
essential
for
optimizing
agricultural
practices
and
ensuring
food
security.
However,
existing
approaches
often
struggle
to
capture
the
complex
interactions
between
various
environmental
factors
growth,
leading
suboptimal
predictions.
Consequently,
identifying
most
important
feature
vital
when
leveraging
Support
Vector
Regressor
(SVR)
prediction.
In
addition,
manual
tuning
of
SVR
hyperparameters
may
not
always
offer
high
accuracy.
this
paper,
we
introduce
a
novel
framework
yields
that
address
these
challenges.
Our
integrates
new
hybrid
selection
approach
with
an
optimized
model
enhance
prediction
accuracy
efficiently.
The
proposed
comprises
three
phases:
preprocessing,
selection,
phases.
preprocessing
phase,
data
normalization
conducted,
followed
by
application
K-means
clustering
in
conjunction
correlation-based
filter
(CFS)
generate
reduced
dataset.
Subsequently,
FMIG-RFE
proposed.
Finally,
phase
introduces
improved
variant
Crayfish
Optimization
Algorithm
(COA),
named
ICOA,
which
utilized
optimize
thereby
achieving
superior
along
approach.
Several
experiments
are
conducted
assess
evaluate
performance
framework.
results
demonstrated
over
state-of-art
approaches.
Furthermore,
experimental
findings
regarding
ICOA
optimization
algorithm
affirm
its
efficacy
model,
enhancing
both
computational
efficiency,
surpassing
algorithms.
Biomimetics,
Год журнала:
2024,
Номер
9(5), С. 270 - 270
Опубликована: Апрель 28, 2024
The
traditional
golden
jackal
optimization
algorithm
(GJO)
has
slow
convergence
speed,
insufficient
accuracy,
and
weakened
ability
in
the
process
of
finding
optimal
solution.
At
same
time,
it
is
easy
to
fall
into
local
extremes
other
limitations.
In
this
paper,
a
novel
(SCMGJO)
combining
sine–cosine
Cauchy
mutation
proposed.
On
one
hand,
tent
mapping
reverse
learning
introduced
population
initialization,
sine
cosine
strategies
are
update
prey
positions,
which
enhances
global
exploration
algorithm.
introduction
for
perturbation
solution
effectively
improves
algorithm’s
obtain
Through
experiment
23
benchmark
test
functions,
results
show
that
SCMGJO
performs
well
speed
accuracy.
addition,
stretching/compression
spring
design
problem,
three-bar
truss
unmanned
aerial
vehicle
path
planning
problem
verification.
experimental
prove
superior
performance
compared
with
intelligent
algorithms
verify
its
application
engineering
applications.
Biomimetics,
Год журнала:
2025,
Номер
10(1), С. 53 - 53
Опубликована: Янв. 14, 2025
Optimization
algorithms
play
a
crucial
role
in
solving
complex
problems
across
various
fields,
including
global
optimization
and
feature
selection
(FS).
This
paper
presents
the
enhanced
polar
lights
with
cryptobiosis
differential
evolution
(CPLODE),
novel
improvement
upon
original
(PLO)
algorithm.
CPLODE
integrates
mechanism
(DE)
operators
to
enhance
PLO's
search
capabilities.
The
particle
collision
strategy
is
replaced
DE's
mutation
crossover
operators,
enabling
more
effective
exploration
using
dynamic
rate
improve
convergence.
Furthermore,
records
reuses
historically
successful
solutions,
thereby
improving
greedy
process.
experimental
results
on
29
CEC
2017
benchmark
functions
demonstrate
CPLODE's
superior
performance
compared
eight
classical
algorithms,
higher
average
ranks
faster
Moreover,
achieved
competitive
ten
real-world
datasets,
outperforming
several
well-known
binary
metaheuristic
classification
accuracy
reduction.
These
highlight
effectiveness
for
both
selection.
