MSBKA: A Multi-Strategy Improved Black-Winged Kite Algorithm for Feature Selection of Natural Disaster Tweets Classification
Biomimetics,
Год журнала:
2025,
Номер
10(1), С. 41 - 41
Опубликована: Янв. 10, 2025
With
the
advancement
of
Internet,
social
media
platforms
have
gradually
become
powerful
in
spreading
crisis-related
content.
Identifying
informative
tweets
associated
with
natural
disasters
is
beneficial
for
rescue
operation.
When
faced
massive
text
data,
choosing
pivotal
features,
reducing
calculation
expense,
and
increasing
model
classification
performance
a
significant
challenge.
Therefore,
this
study
proposes
multi-strategy
improved
black-winged
kite
algorithm
(MSBKA)
feature
selection
disaster
based
on
wrapper
method's
principle.
Firstly,
BKA
by
utilizing
enhanced
Circle
mapping,
integrating
hierarchical
reverse
learning,
introducing
Nelder-Mead
method.
Then,
MSBKA
combined
excellent
classifier
SVM
(RBF
kernel
function)
to
construct
hybrid
model.
Finally,
MSBKA-SVM
performs
tweet
tasks.
The
empirical
analysis
data
from
four
shows
that
proposed
has
achieved
an
accuracy
0.8822.
Compared
GA,
PSO,
SSA,
BKA,
increased
4.34%,
2.13%,
2.94%,
6.35%,
respectively.
This
research
proves
can
play
supporting
role
risk.
Язык: Английский
Prediction of Lithium-Ion Battery State of Health Using a Deep Hybrid Kernel Extreme Learning Machine Optimized by the Improved Black-Winged Kite Algorithm
Batteries,
Год журнала:
2024,
Номер
10(11), С. 398 - 398
Опубликована: Ноя. 8, 2024
The
accurate
prediction
of
lithium-ion
battery
state
health
(SOH)
can
extend
life,
enhance
device
safety,
and
ensure
sustained
reliability
in
critical
applications.
Addressing
the
non-linear
non-stationary
characteristics
capacity
sequences,
a
novel
method
for
predicting
lithium
SOH
is
proposed
using
deep
hybrid
kernel
extreme
learning
machine
(DHKELM)
optimized
by
improved
black-winged
kite
algorithm
(IBKA).
First,
to
address
limitations
traditional
machines
(ELMs)
capturing
features
their
poor
generalization
ability,
concepts
auto
encoders
(AEs)
functions
are
introduced
ELM,
resulting
establishment
DHKELM
model
prediction.
Next,
tackle
challenge
parameter
selection
DHKELM,
an
optimal
point
set
strategy,
Gompertz
growth
model,
Levy
flight
strategy
employed
optimize
parameters
IBKA
before
training.
Finally,
performance
IBKA-DHKELM
validated
two
distinct
datasets
from
NASA
CALCE,
comparing
it
against
BKA-DHKELM.
results
show
that
achieves
smallest
error,
with
RMSE
only
0.0062,
demonstrating
exceptional
fitting
capability,
high
predictive
accuracy,
good
robustness.
Язык: Английский
An innovative complex-valued encoding black-winged kite algorithm for global optimization
Scientific Reports,
Год журнала:
2025,
Номер
15(1)
Опубликована: Янв. 6, 2025
Язык: Английский
A black-winged kite optimization algorithm enhanced by osprey optimization and vertical and horizontal crossover improvement
Scientific Reports,
Год журнала:
2025,
Номер
15(1)
Опубликована: Фев. 25, 2025
This
paper
addresses
issues
of
inadequate
accuracy
and
inconsistency
between
global
search
efficacy
local
development
capability
in
the
black-winged
kite
algorithm
for
practical
problem-solving
by
proposing
a
optimization
that
integrates
Osprey
Crossbar
enhancement
(DKCBKA).
Firstly,
adaptive
index
factor
fusion
Optimization
Algorithm
approach
are
incorporated
to
enhance
algorithm's
convergence
rate,
probability
distribution
is
updated
throughout
attack
stage.
Second,
stochastic
difference
variant
method
implemented
prevent
from
entering
optima.
Lastly,
longitudinal
transversal
crossover
technique
dynamically
alter
population's
individual
optimal
solutions.
Fifteen
benchmark
functions
chosen
test
effectiveness
enhanced
compare
efficiency
each
technique.
Simulation
experiments
performed
on
CEC2017
CEC2019
sets,
revealing
DKCBKA
surpasses
five
standard
swarm
intelligence
methods
six
improved
algorithms
regarding
solution
speed.
The
superiority
meeting
real
challenges
further
demonstrated
three
engineering
problems
DKCBKA,
with
capabilities
18.222%,
99.885%
0.561%
higher
than
BKA,
respectively.
Язык: Английский
Research on Slope Stability Prediction Based on MC-BKA-MLP Mixed Model
Applied Sciences,
Год журнала:
2025,
Номер
15(6), С. 3158 - 3158
Опубликована: Март 14, 2025
Quantifying
slope
mechanical
parameters
as
comprehensive
indicators
is
crucial
for
predicting
stability.
The
Mohr–Coulomb
(M-C)
criterion,
a
classical
method
determining
the
relevant
of
rock
mass
mechanics,
effectively
reflects
failure
characteristics
masses
in
most
types
slopes.
Based
on
this,
effective
stress
and
shear
strength
from
M-C
criterion
are
selected
key
indicators,
characteristic
dataset
constructed
by
integrating
these
with
other
influencing
factors
safety
factor,
calculated
using
Bishop
within
framework
limit
equilibrium
analysis,
serves
output
variable.
Subsequently,
novel
Black
Kite
Algorithm
(BKA)
was
developed
to
enhance
prediction
model
multilevel
perceptron
neural
network.
results
demonstrate
that
mean
square
error
(RMSE)
BKA-MLP
merely
2.41%,
significantly
lower
than
alternative
models.
Additionally,
R2
value
reaches
approximately
95%,
indicating
high
level
interpretability.
SHAP-based
interpretability
analysis
trained
highlights
stress,
strength,
angle
three
sensitive
features.
findings,
targeted
landslide
prevention
measures
were
proposed,
providing
new
approach
stability
disaster
prevention.
Язык: Английский
A Novel HGW Optimizer with Enhanced Differential Perturbation for Efficient 3D UAV Path Planning
Drones,
Год журнала:
2025,
Номер
9(3), С. 212 - 212
Опубликована: Март 16, 2025
In
general,
path
planning
for
unmanned
aerial
vehicles
(UAVs)
is
modeled
as
a
challenging
optimization
problem
that
critical
to
ensuring
efficient
UAV
mission
execution.
The
challenge
lies
in
the
complexity
and
uncertainty
of
flight
scenarios,
particularly
three-dimensional
scenarios.
this
study,
one
introduces
framework
3D
environment.
To
tackle
challenge,
we
develop
an
innovative
hybrid
gray
wolf
optimizer
(GWO)
algorithm,
named
SDPGWO.
proposed
algorithm
simplifies
position
update
mechanism
GWO
incorporates
differential
perturbation
strategy
into
search
process,
enhancing
ability
avoiding
local
minima.
Simulations
conducted
various
scenarios
reveal
SDPGWO
excels
rapidly
generating
superior-quality
paths
UAVs.
addition,
it
demonstrates
enhanced
robustness
handling
complex
environments
outperforms
other
related
algorithms
both
performance
reliability.
Язык: Английский
A New Single-Parameter Bees Algorithm
Biomimetics,
Год журнала:
2024,
Номер
9(10), С. 634 - 634
Опубликована: Окт. 18, 2024
Based
on
bee
foraging
behaviour,
the
Bees
Algorithm
(BA)
is
an
optimisation
metaheuristic
algorithm
which
has
found
many
applications
in
both
continuous
and
combinatorial
domains.
The
original
version
of
six
user-selected
parameters:
number
scout
bees,
high-performing
top-performing
or
"elite"
forager
bees
following
elite
recruited
by
other
neighbourhood
size.
These
parameters
must
be
chosen
with
due
care,
as
their
values
can
impact
algorithm's
performance,
particularly
when
problem
complex.
However,
determining
optimum
for
those
time-consuming
users
who
are
not
familiar
algorithm.
This
paper
presents
BA
Язык: Английский