Multi-modal multi-objective wolf pack algorithm with circumferential scouting and intra-niche interactions
Swarm and Evolutionary Computation,
Год журнала:
2025,
Номер
93, С. 101842 - 101842
Опубликована: Янв. 8, 2025
Язык: Английский
A Decision Support System for Wheat Powdery Mildew Risk Prediction Using Weather Monitoring, Machine Learning and Explainable Artificial Intelligence
Computers and Electronics in Agriculture,
Год журнала:
2025,
Номер
230, С. 109905 - 109905
Опубликована: Янв. 10, 2025
Язык: Английский
Contextual Information Aggregation and Multi‐Scale Feature Fusion for Single Image De‐Raining in Generative Adversarial Networks
Concurrency and Computation Practice and Experience,
Год журнала:
2025,
Номер
37(3)
Опубликована: Янв. 16, 2025
ABSTRACT
Aiming
to
address
issues
such
as
non‐uniform
rain
density
and
misjudgment
caused
by
noise
in
image
de‐raining,
we
propose
a
single‐image
de‐raining
method
based
on
generative
adversarial
network
with
contextual
information
aggregation
multi‐scale
feature
fusion.
First,
design
generator
composed
of
encoding,
context
aggregation,
decoding
stages.
Features
are
extracted
using
convolution,
while
expansion
convolution
effectively
aggregates
information.
Transposition
is
then
used
restore
the
image,
enhancing
model's
ability
perceive
details
achieve
accurate
judgment
content
reconstruction.
Second,
fusion
discriminator
structure
capture
different
kernels
scales
connect
maps
from
scales.
This
improves
understand
differentiate
between
authentic
fake
images.
Finally,
new
refinement
loss
function
reduce
grid
artifact
generation
add
Lipschitz
constraints
further
minimize
imaging
gap.
In
this
paper,
peak
signal‐to‐noise
ratio
structural
similarity
evaluation
criteria,
experiments
conducted
real
synthesized
demonstrate
superior
removal
performance
proposed
method.
Язык: Английский
Multi-label feature selection via label relaxation
Applied Soft Computing,
Год журнала:
2025,
Номер
unknown, С. 113047 - 113047
Опубликована: Март 1, 2025
Firefly Algorithm-based Optimization of Control Parameters in DC Conversion Systems
Engineering Technology & Applied Science Research,
Год журнала:
2025,
Номер
15(2), С. 20588 - 20594
Опубликована: Апрель 3, 2025
Sustainable
energy
and
electric
vehicles
require
DC-DC
converters
in
renewable
systems,
EV
charging,
smart
grids.
In
this
context,
buck
are
crucial,
providing
efficient
voltage
regulation
reliable
performance
these
advanced
systems.
While
Proportional-Integral
(PI)
controllers
widely
adopted
for
their
simplicity
dependability,
they
often
rely
on
manual
parameter
tuning,
limiting
adaptability
responsiveness.
To
address
limitation,
research
introduces
a
digital
control
strategy
that
optimizes
the
PI
parameters
using
Firefly
Algorithm
(FA).
This
optimization
significantly
enhances
stability
reduces
oscillations
converter.
A
MATLAB/Simulink
simulation
model
is
utilized
to
validate
proposed
approach,
results
demonstrate
FA-optimized
substantially
improve
converter's
performance,
making
it
highly
suitable
high-demand
applications
Язык: Английский
Optimized feature selection in high-dimensional gene expression data using weighted differential gene expression analysis
Applied Soft Computing,
Год журнала:
2025,
Номер
unknown, С. 113329 - 113329
Опубликована: Июнь 1, 2025
Язык: Английский
Multi-Objective Feature Selection Algorithm using Beluga Whale Optimization
Kiana Kouhpah Esfahani,
Behnam Mohammad Hasani Zade,
N. Mansouri
и другие.
Chemometrics and Intelligent Laboratory Systems,
Год журнала:
2024,
Номер
257, С. 105295 - 105295
Опубликована: Дек. 4, 2024
Язык: Английский
Research on the application of neural network modeling in the assessment of traditional sports training and coaches’ quality in colleges and universities
Applied Mathematics and Nonlinear Sciences,
Год журнала:
2024,
Номер
9(1)
Опубликована: Янв. 1, 2024
Abstract
Scientific
monitoring
in
sports
training
colleges
and
universities
is
particularly
important,
which
an
important
symbol
of
the
scientific
level
training,
has
a
role
promoting
ability
athletes
coaches.
In
this
paper,
we
collect
data
based
on
evaluation
index
coach
quality
then
preprocess
collected
athlete
performance
into
BP
neural
network
model.
The
firefly
algorithm
used
to
optimize
prediction
network,
model,
visualization
system
for
constructed
display
predicted
assessment
real-time.
It
been
found
that
average
error
model
0.73%,
can
be
training.
test
scores
all
aspects
assisted
by
were
significantly
better
than
those
traditional
group,
coaches
higher
group
(P<0.05).
This
paper
forms
systematic
method
college
enhance
help
improve
Язык: Английский