Remote Sensing,
Journal Year:
2024,
Volume and Issue:
16(9), P. 1503 - 1503
Published: April 24, 2024
Chlorophyll-a
(Chl-a)
concentration
monitoring
is
very
important
for
managing
water
resources
and
ensuring
the
stability
of
marine
ecosystems.
Due
to
their
high
operating
efficiency
prediction
accuracy,
backpropagation
(BP)
neural
networks
are
widely
used
in
Chl-a
inversion.
However,
BP
tend
become
stuck
local
optima,
accuracy
fluctuates
significantly,
thus
posing
restrictions
inversion
process.
Studies
have
found
that
metaheuristic
optimization
algorithms
can
significantly
improve
these
shortcomings
by
optimizing
initial
parameters
(weights
biases)
networks.
In
this
paper,
adaptive
nonlinear
weight
coefficient,
path
search
strategy
“Levy
flight”
dynamic
crossover
mechanism
introduced
optimize
three
main
steps
Artificial
Ecosystem
Optimization
(AEO)
algorithm
overcome
algorithm’s
limitation
solving
complex
problems,
its
global
capability,
thereby
performance
Relying
on
Google
Earth
Engine
Colaboratory
(Colab),
a
model
coastal
waters
Hong
Kong
was
built
verify
improved
AEO
networks,
proposed
herein
compared
with
17
different
algorithms.
The
results
show
based
network
optimized
using
superior
other
models
terms
stability,
obtained
via
through
respect
during
heavy
precipitation
events
red
tides
highly
consistent
measured
values
both
time
space
domains.
These
conclusions
provide
new
method
quality
management
waters.
Spectrum of Mechanical Engineering and Operational Research.,
Journal Year:
2024,
Volume and Issue:
1(1), P. 215 - 226
Published: Sept. 1, 2024
Multi-Criteria
Decision
Analysis
(MCDA)
addresses
complex
decision-making
problems
across
various
fields
such
as
logistics,
management,
medicine,
and
sustainability.
MCDA
tools
provide
a
structured
approach
to
evaluating
decisions
with
multiple
conflicting
criteria,
assisting
decision-makers
in
navigating
intricate
scenarios.
Engaging
experts
is
crucial
for
identifying
multi-criteria
models
due
the
diverse
aspects
of
problems.
Techniques
pairwise
comparisons
criterion
weight
assignment
are
commonly
used
incorporate
expert
knowledge
into
decision
models.
Criterion
allows
indicate
importance
each
criterion;
however,
issues
can
arise
if
model
parameters
lost
or
become
unavailable.
To
mitigate
these
issues,
techniques
like
entropy
standard
deviation
determine
weights
without
direct
input.
In
this
context,
Stochastic
Identification
Weights
(SITW)
method
utilizes
existing
assessment
samples
re-identify
obtain
that
replicate
rankings
reference
model.
This
study
compares
information-based
methods
(Entropy,
STD)
SITW
re-identifying
TRI
medical
function
benchmark.
The
effectiveness
evaluated
using
Spearman's
weighted
correlation
coefficient
scenarios
alternative
numbers.
Results
provides
more
significant
results
than
other
by
leveraging
previously
alternatives.
Future
research
could
explore
broader
approaches
uncertainty
ensure
comprehensive
support
contexts.
Structural Concrete,
Journal Year:
2024,
Volume and Issue:
unknown
Published: May 19, 2024
Abstract
This
paper
focuses
on
the
applicability
of
CatBoost
models
constructed
using
various
optimization
techniques
for
improved
forecasting
compressive
strength
ultra‐high‐performance
concrete
(UHPC).
Phasor
particle
swarm
(PPSO),
dwarf
mongoose
(DMO),
and
atom
search
(ASO),
which
have
been
very
popular
recently,
are
preferred
as
algorithms.
A
comprehensive
reliable
data
set
is
used
to
develop
models,
include
785
test
results
with
15
input
features.
The
performance
(PPSO‐CatBoost,
DMO‐CatBoost,
ASO‐CatBoost)
optimized
different
algorithms
thoroughly
assessed
by
means
statistical
metrics
error
analysis
determine
model
best
capability,
this
compared
obtained
from
previous
studies.
In
addition,
Shapley
additive
exPlanations
(SHAP)
ensure
interpretability
overcome
“black
box”
problem
machine
learning
(ML)
models.
demonstrate
that
all
outstandingly
forecast
UHPC.
Among
these
DMO‐CatBoost
stands
out
other
in
metrics,
such
high
coefficient
determination
(
R
2
)
values,
low
root
mean
squared
(RMSE),
absolute
percentage
(MAPE),
(MAE)
along
a
smaller
ratio.
words,
RMSE,
,
MAPE,
MAE
values
training
3.67,
0.993,
0.019,
2.35,
respectively,
whereas
those
6.15,
0.978,
0.038,
4.51.
Additionally,
ranking
optimize
hyperparameters
follows:
DMO
>
PPSO
ASO.
On
hand,
SHAP
showed
age,
fiber
dosage,
cement
dosage
significantly
influence
These
findings
can
guide
structural
engineers
design
UHPC,
thus
assisting
them
developing
strategies
improve
properties
material.
Finally,
based
developed
work,
graphical
user
interface
has
easily
UHPC
practical
applications
without
additional
tools
or
software.
Alexandria Engineering Journal,
Journal Year:
2023,
Volume and Issue:
87, P. 148 - 163
Published: Dec. 22, 2023
Vegetation
evolution
(VEGE)
is
a
newly
proposed
meta-heuristic
algorithm
(MA)
with
excellent
exploitation
but
relatively
weak
exploration
capacity.
We
thus
focus
on
further
balancing
the
and
of
VEGE
well
to
improve
overall
optimization
performance.
This
paper
proposes
an
improved
Q-learning
based
VEGE,
we
design
archive
provide
variety
search
strategies,
each
contains
four
efficient
easy-implemented
strategies.
In
addition,
online
Q-Learning,
as
ε-greedy
scheme,
are
employed
decision-maker
role
learn
knowledge
from
past
process
determine
strategy
for
individual
automatically
intelligently.
numerical
experiments,
compare
our
QVEGE
eight
state-of-the-art
MAs
including
original
CEC2020
benchmark
functions,
twelve
engineering
problems,
wireless
sensor
networks
(WSN)
coverage
problems.
Experimental
statistical
results
confirm
that
demonstrates
significant
enhancements
stands
strong
competitor
among
existing
algorithms.
The
source
code
publicly
available
at
https://github.com/RuiZhong961230/QVEGE.
