Biomimetics,
Journal Year:
2024,
Volume and Issue:
9(5), P. 304 - 304
Published: May 19, 2024
The
prediction
of
patient
survival
is
crucial
for
guiding
the
treatment
process
in
healthcare.
Healthcare
professionals
rely
on
analyzing
patients'
clinical
characteristics
and
findings
to
determine
plans,
making
accurate
predictions
essential
efficient
resource
utilization
optimal
support
during
recovery.
In
this
study,
a
hybrid
architecture
combining
Stacked
AutoEncoders,
Particle
Swarm
Optimization,
Softmax
Classifier
was
developed
predicting
survival.
evaluated
using
Haberman's
Survival
dataset
Echocardiogram
from
UCI.
results
were
compared
with
several
Machine
Learning
methods,
including
Decision
Trees,
K-Nearest
Neighbors,
Support
Vector
Machines,
Neural
Networks,
Gradient
Boosting,
Bagging
applied
same
datasets.
indicate
that
proposed
outperforms
other
methods
both
datasets
surpasses
reported
literature
dataset.
light
obtained,
models
obtained
can
be
used
as
decision
system
determining
care
methods.
Results in Engineering,
Journal Year:
2024,
Volume and Issue:
21, P. 101750 - 101750
Published: Jan. 5, 2024
Seismic
fragility
assessment
provides
a
substantial
tool
for
assessing
the
seismic
resilience
of
these
buildings.
However,
using
traditional
numerical
methods
to
derive
curves
poses
significant
challenges.
These
often
overlook
diverse
range
buildings
found
in
different
regions,
as
they
rely
on
standardized
assumptions
and
parameters.
Consequently,
may
not
accurately
capture
response
various
building
types.
Alternatively,
extensive
data
collection
becomes
essential
address
this
knowledge
gap
by
understanding
local
construction
techniques
identifying
relevant
This
is
crucial
developing
reliable
analytical
approaches
that
can
curves.
To
overcome
challenges,
research
employs
four
Machine
Learning
(ML)
techniques,
namely
Support
Vector
Regression
(SVR),
Stochastic
Gradient
Descent
(SGD),
Random
Forest
(RF),
Linear
(LR),
probability
collapse
terms
Peak
Ground
Acceleration
(PGA).
achieve
objective,
comprehensive
input/output
dataset
consisting
on-site
collected
from
646
masonry
walls
Malawi
used.
Adopted
ML
models
are
trained
tested
entire
then
again
only
most
highly
correlated
features.
The
study
includes
comparative
analysis
efficiency
accuracy
each
approach
influence
used
analyses.
(RF)
technique
emerges
efficient
deriving
surveyed
achieved
lowest
values
evaluation
metrics
methods.
scored
Mean
Absolute
Percentage
Error
(MAPE)
16.8
%,
Root
Square
(RMSE)
0.0547.
results
highlight
potential
particularly
RF,
derivation
with
proper
levels
accuracy.
Foods,
Journal Year:
2023,
Volume and Issue:
12(3), P. 619 - 619
Published: Feb. 1, 2023
In
this
study,
a
response
surface
methodology
and
an
artificial
neural
network
coupled
with
genetic
algorithm
(RSM-ANN-GA)
was
used
to
predict
estimate
the
optimized
ultrasonic-assisted
extraction
conditions
of
Poria
cocos.
The
ingredient
yield
antioxidant
potential
were
determined
different
independent
variables
ethanol
concentration
(X1;
25–75%),
time
(X2;
30–50
min),
solution
volume
(mL)
(X3;
20–60
mL).
optimal
predicted
by
RSM-ANN-GA
model
be
55.53%
for
48.64
min
in
60.00
mL
solvent
four
triterpenoid
acids,
40.49%
30.25
20.00
activity
total
polysaccharide
phenolic
contents.
evaluation
two
modeling
strategies
showed
that
provided
better
predictability
greater
accuracy
than
P.
These
findings
guidance
on
efficient
cocos
feasible
analysis/modeling
optimization
process
natural
products.
Applied Sciences,
Journal Year:
2023,
Volume and Issue:
13(2), P. 809 - 809
Published: Jan. 6, 2023
Minarets
are
slender
and
tall
structures
that
built
from
different
types
of
materials.
Modern
materials
also
starting
to
be
used
in
such
with
the
recent
developments
material
technology.
The
seismic
vulnerability
dynamic
behavior
minarets
can
vary,
depending
on
characteristics.
Within
this
study’s
scope,
thirteen
Türkiye
were
chosen
as
variables.
A
sample
minaret
model
was
an
example
nine
heights
reveal
how
characteristic
change
affects
behavior.
Information
mechanical
characteristics
given
for
all
types.
Natural
fundamental
periods,
displacements,
base
shear
forces
attained
structural
analyses
each
selected
material.
empirical
period
formula
is
proposed
using
obtained
taken
into
consideration.
At
same
time,
natural
periods
first
ten
modes
13
study
estimated
established
Artificial
Neural
Network
(ANN)
model.
real
experimental
compared
values
by
ANN
fewer
parameters,
99%
results
successful.
In
addition,
time
history
evaluate
performance
(three
considered).
specific
case,
acceleration
record
2011
Van
(Eastern
Turkiye)
earthquake
(Mw
=
7.2)
Performance
levels
determined
according
It
has
been
concluded
significantly
affect
minarets.
Sustainability,
Journal Year:
2023,
Volume and Issue:
15(12), P. 9715 - 9715
Published: June 18, 2023
The
realistic
determination
of
damage
estimation
and
building
performance
depends
on
target
displacements
in
performance-based
earthquake
engineering.
In
this
study,
were
obtained
by
performing
pushover
analysis
for
a
sample
reinforced-concrete
model,
taking
into
account
60
different
peak
ground
accelerations
each
the
five
stories.
Three
estimation,
such
as
limitation
(DL),
significant
(SD),
near
collapse
(NC),
acceleration
numbers
stories,
respectively.
It
aims
to
develop
an
artificial
neural
network
(ANN)-based
sustainable
model
predict
under
seismic
risks
mid-rise
regular
buildings,
which
make
up
large
part
existing
stock,
using
all
data
obtained.
For
purpose,
hybrid
structure
was
established
with
particle
swarm
optimization
algorithm
(PSO),
structure’s
hyper
parameters
optimized.
models
created
order
most
successfully.
found
that
ANN
particles
best
position
revealed
produced
successful
results
calculation
score.
99%
DL
SD
NC
determining
buildings.
also
should
be
used
estimating
risks.