Research Square (Research Square),
Journal Year:
2023,
Volume and Issue:
unknown
Published: Dec. 6, 2023
Abstract
Accurate
measurement
of
cable
tension
is
crucial
for
real-time
monitoring
bridge
systems,
preventing
potential
risks,
and
ensuring
safety
continuous
operation.
However,
traditional
often
faces
the
challenge
accuracy
when
dealing
with
complex
elastic
boundary
conditions.
This
article
uses
9
finite
element
model
suspension
cables
conditions
as
data
force
identification,
heuristic
algorithms
to
achieve
identification
goal
minimizing
frequency
actual
frequency.
Based
on
recognition
results
process,
reasons
inaccurate
forces
under
boundaries
were
analyzed,
a
mutual
fusion
mechanism
was
proposed
improve
identification.
The
show
that
reduces
maximum
relative
error
in
by
12.6%,
significantly
improving
accuracy,
most
initial
5%,
meeting
needs
practical
engineering.
In
addition,
non
parametric
test
statistical
method
also
proves
introduction
has
significant
impact
value
tension.
Finally,
verified
through
from
three
engineering
meet
requirements.
provides
new
technical
solution
intelligent
accurate
long
beams,
broad
application
prospects.
Scientific Reports,
Journal Year:
2023,
Volume and Issue:
13(1)
Published: Aug. 7, 2023
Abstract
Severe
air
pollution
poses
a
significant
threat
to
public
safety
and
human
health.
Predicting
future
quality
conditions
is
crucial
for
implementing
control
measures
guiding
residents'
activity
choices.
However,
traditional
single-module
machine
learning
models
suffer
from
long
training
times
low
prediction
accuracy.
To
improve
the
accuracy
of
forecasting,
this
paper
proposes
ISSA–LSTM
model-based
approach
predicting
index
(AQI).
The
model
consists
three
main
components:
random
forest
(RF)
mRMR,
improved
sparrow
search
algorithm
(ISSA),
short-term
memory
network
(LSTM).
Firstly,
RF–mRMR
used
select
influential
variables
affecting
AQI,
thereby
enhancing
model's
performance.
Next,
ISSA
employed
optimize
hyperparameters
LSTM,
further
improving
model’s
Finally,
LSTM
utilized
predict
AQI
concentrations.
Through
comparative
experiments,
it
demonstrated
that
outperforms
other
in
terms
RMSE
R
2
,
exhibiting
higher
predictive
performance
validated
across
different
time
steps,
demonstrating
minimal
errors.
Therefore,
viable
effective
accurately
AQI.
Global Challenges,
Journal Year:
2024,
Volume and Issue:
8(5)
Published: April 18, 2024
Abstract
This
study
presents
the
parameter
extraction
of
single,
double,
and
triple‐diode
photovoltaic
(PV)
models
using
weighted
leader
search
algorithm
(WLS).
The
primary
objective
is
to
develop
that
accurately
reflect
characteristics
PV
devices
so
technical
economic
benefits
are
maximized
under
all
constraints.
For
this
purpose,
24
models,
6
for
two
different
cells,
18
six
modules,
whose
experimental
data
publicly
available,
developed
successfully.
second
research
selection
most
suitable
problem.
It
a
significant
challenge
since
evaluation
process
requires
advanced
statistical
tools
techniques
determine
reliable
selection.
Therefore,
seven
brand‐new
algorithms,
including
WLS,
spider
wasp
optimizer,
shrimp
goby
association
search,
reversible
elementary
cellular
automata,
fennec
fox
optimization,
Kepler
rime
optimization
tested.
WLS
has
yielded
smallest
minimum,
average,
RMSE,
standard
deviation
among
those.
Its
superiority
also
verified
by
Friedman
Wilcoxon
signed‐rank
test
based
on
144
pairwise
comparisons.
In
conclusion,
it
demonstrated
superior
in
developing
accurate
models.
Axioms,
Journal Year:
2025,
Volume and Issue:
14(4), P. 235 - 235
Published: March 21, 2025
Air
pollution
poses
significant
threats
to
public
health
and
ecological
sustainability,
necessitating
precise
air
quality
prediction
facilitate
timely
preventive
measures
policymaking.
Although
Long
Short-Term
Memory
(LSTM)
networks
demonstrate
effectiveness
in
prediction,
their
performance
critically
depends
on
appropriate
hyperparameter
configuration.
Traditional
manual
parameter
tuning
methods
prove
inefficient
prone
suboptimal
solutions.
While
conventional
swarm
intelligence
algorithms
have
been
proved
be
effective
optimizing
the
hyperparameters
of
LSTM
models,
they
still
face
challenges
accuracy
model
generalizability.
To
address
these
limitations,
this
study
proposes
an
improved
chaotic
game
optimization
(ICGO)
algorithm
incorporating
multiple
improvement
strategies,
subsequently
developing
ICGO-LSTM
hybrid
for
Chengdu’s
prediction.
The
experimental
validation
comprises
two
phases:
First,
comprehensive
benchmarking
23
mathematical
functions
reveals
that
proposed
ICGO
achieves
superior
mean
values
across
all
test
optimal
variance
metrics
22
functions,
demonstrating
enhanced
global
convergence
capability
algorithmic
robustness.
Second,
comparative
analysis
with
seven
swarm-optimized
models
six
machine
learning
benchmarks
dataset
shows
model’s
performance.
Extensive
evaluations
show
minimal
error
metrics,
MAE
=
3.2865,
MAPE
0.720%,
RMSE
4.8089,
along
exceptional
coefficient
determination
(R2
0.98512).
These
results
indicate
significantly
outperforms
predictive
reliability,
suggesting
substantial
practical
implications
urban
environmental
management.
Machines,
Journal Year:
2024,
Volume and Issue:
12(3), P. 210 - 210
Published: March 21, 2024
The
paper
analyzes
the
correlation
features
between
stress
strength,
multiple
failure
mechanisms,
and
components.
It
investigates
effects
of
different
on
reliability
proposes
a
method
for
structural
analysis
that
considers
joint
features.
To
portray
stress–strength
structure,
Copula
function
is
utilized
influence
degree
parameter
clarified.
text
describes
introduction
time-varying
characteristics
strength
parameters.
A
then
constructed
to
calculate
under
characteristics.
Additionally,
hybrid
characterize
intricate
mechanisms
article
variational
adaptive
sparrow
search
algorithm
(VASSA)
obtain
optimal
parameters
Copula.
effectiveness
accuracy
proposed
are
verified
through
actual
cases.
results
indicate
significantly
reliability.
Incorporating
into
solution
yields
safer
align
with
engineering
practice.
