Advanced tree-based machine learning methods for predicting the seismic response of regular and irregular RC frames
Structures,
Год журнала:
2024,
Номер
64, С. 106524 - 106524
Опубликована: Май 11, 2024
Язык: Английский
Development of a framework for the prediction of slope stability using machine learning paradigms
Natural Hazards,
Год журнала:
2024,
Номер
unknown
Опубликована: Июль 25, 2024
Язык: Английский
Addressing limitations of the K-means clustering algorithm: outliers, non-spherical data, and optimal cluster selection
AIMS Mathematics,
Год журнала:
2024,
Номер
9(9), С. 25070 - 25097
Опубликована: Янв. 1, 2024
<p>Clustering
is
essential
in
data
analysis,
with
K-means
clustering
being
widely
used
for
its
simplicity
and
efficiency.
However,
several
challenges
can
affect
performance,
including
the
handling
of
outliers,
transformation
non-spherical
into
a
spherical
form,
selection
optimal
number
clusters.
This
paper
addressed
these
by
developing
enhancing
specific
models.
The
primary
objective
was
to
improve
robustness
accuracy
presence
issues.
To
handle
this
research
employed
winsorization
method,
which
uses
threshold
values
minimize
influence
extreme
points.
For
KROMD
method
introduced,
combines
Manhattan
distance
Gaussian
kernel.
approach
ensured
more
accurate
representation
data,
facilitating
better
performance.
third
focused
on
gap
statistic
selecting
achieved
standardizing
expected
value
reference
using
an
exponential
distribution,
providing
reliable
criterion
determining
appropriate
Experimental
results
demonstrated
that
effectively
handles
leading
improved
stability.
significantly
enhanced
converting
achieving
level
0.83
percent
execution
time
0.14
per
second.
Furthermore,
outperformed
other
techniques
clusters,
93.35
0.1433
These
advancements
collectively
enhance
performance
clustering,
making
it
robust
effective
complex
analysis
tasks.</p>
Язык: Английский
The effectiveness of data pre-processing methods on the performance of machine learning techniques using RF, SVR, Cubist and SGB: a study on undrained shear strength prediction
Stochastic Environmental Research and Risk Assessment,
Год журнала:
2024,
Номер
38(8), С. 3273 - 3290
Опубликована: Июнь 13, 2024
Abstract
In
the
field
of
data
engineering
in
machine
learning
(ML),
a
crucial
component
is
process
scaling,
normalization,
and
standardization.
This
involves
transforming
to
make
it
more
compatible
with
modeling
techniques.
particular,
this
transformation
essential
ensure
suitability
for
subsequent
analysis.
Despite
application
many
conventional
relatively
new
approaches
ML,
there
remains
conspicuous
lack
research,
particularly
geotechnical
discipline.
study,
ML-based
prediction
models
(i.e.,
RF,
SVR,
Cubist,
SGB)
were
developed
estimate
undrained
shear
strength
(UDSS)
cohesive
soil
from
perspective
wide
range
data-scaling
methods.
Therefore,
work
presents
novel
ML
framework
based
on
Cubist
regression
method
predict
UDSS
soil.
A
dataset
including
six
different
features
one
target
variable
used
building
models.
The
performance
was
examined
considering
impact
pre-processing
issue.
For
that
purpose,
scaling
methods,
namely
Range,
Z-Score,
Log
Transformation,
Box-Cox,
Yeo-Johnson,
generate
results
then
systematically
compared
using
sampling
ratios
understand
how
model
varies
as
various
scaling/transformation
methods
algorithms
combined.
It
observed
or
had
considerable
limited
effects
depending
algorithm
type
ratio.
Compared
SGB
models,
provided
higher
metrics
after
applying
steps.
Box-Cox
transformed
yielded
best
among
other
an
R
2
0.87
90%
training
set.
Also,
generally
when
transformed-based
Log,
Yeo-Johnson)
than
scaled-based
Range
Z-Score)
show
has
potential
prediction,
have
impacts
predictive
capacity
evaluated
Язык: Английский
Stability prediction of multi-material complex slopes based on self-attention convolutional neural networks
Stochastic Environmental Research and Risk Assessment,
Год журнала:
2024,
Номер
unknown
Опубликована: Авг. 14, 2024
Язык: Английский
Developing machine learning-based ground motion models to predict peak ground velocity in Turkiye
Journal of Seismology,
Год журнала:
2024,
Номер
unknown
Опубликована: Сен. 5, 2024
Язык: Английский
An innovative machine learning approach for slope stability prediction by combining shap interpretability and stacking ensemble learning
Environmental Science and Pollution Research,
Год журнала:
2025,
Номер
unknown
Опубликована: Май 7, 2025
Язык: Английский
Outlier Detection of Slope Deformation Monitoring Data based on WMA-3σ
Atlantis highlights in engineering/Atlantis Highlights in Engineering,
Год журнала:
2024,
Номер
unknown, С. 189 - 199
Опубликована: Янв. 1, 2024
The
outliers
in
slope
deformation
monitoring
data
often
contain
important
information.The
influence
of
external
environment,
the
failure
structure
and
instrument
are
reasons
for
outliers.Rapid
accurate
detection
is
not
only
basic
work
analysis
calculation,
but
also
an
measure
to
find
out
whether
safe
time.Slope
time
series.The
short-term
changes
smooth
stable
with
strong
autocorrelation.In
this
paper,
adaptive
weight
calculation
method
was
proposed
Weighted
Moving
Average
(WMA)
algorithm.The
algorithm
can
estimate
measured
high
precision
without
being
affected
by
outliers.Then,
difference
sequence
between
estimated
calculated,
mirror
processing
sequence.In
order
eliminate
asymmetric
distribution
caused
trend
data.Finally,
sequences
after
were
detected
using
3σ
criterion.Thus
outlier
realized.Through
example
analysis,
WMA-3σ
accurately
detect
data.It
has
reference
significance
real-time
efficient
intelligent
analysis.
Язык: Английский
Application of a semi-supervised technique for identifying unstable mine slopes
Neural Computing and Applications,
Год журнала:
2024,
Номер
unknown
Опубликована: Сен. 20, 2024
Язык: Английский
Stability Prediction Model of Transmission Tower Slope Based on ISCSO-SVM
Electronics,
Год журнала:
2024,
Номер
14(1), С. 126 - 126
Опубликована: Дек. 31, 2024
Landslides
induced
by
heavy
rainfall
are
common
in
southern
China
and
pose
significant
risks
to
the
safe
operation
of
transmission
lines.
To
ensure
reliability
line
operations,
this
paper
presents
a
stability
prediction
model
for
tower
slopes
based
on
Improved
Sand
Cat
Swarm
Optimization
(ISCSO)
algorithm
Support
Vector
Machine
(SVM).
The
ISCSO
is
enhanced
with
dynamic
reverse
learning
triangular
wandering
strategies,
which
then
used
optimize
kernel
penalty
parameters
SVM,
resulting
ISCSO-SVM
model.
In
study,
typical
slope
as
case
database
generated
through
orthogonal
experimental
design
Geo-studio
simulations.
addition
traditional
input
features,
an
additional
input—transmission
catchment
area—is
incorporated,
stable
state
set
predicted
output.
results
demonstrate
that
achieves
highest
accuracy,
smallest
errors
across
all
metrics.
Specifically,
compared
standard
MAPE,
MAE,
RMSE
values
reduced
70.96%,
71.41%,
57.37%,
respectively.
effectively
predicts
slopes,
thereby
ensuring
Язык: Английский