Buildings,
Год журнала:
2024,
Номер
14(9), С. 2834 - 2834
Опубликована: Сен. 9, 2024
Pervious
concrete
is
desirable
for
water
drainage
in
building
systems,
but
achieving
both
high
strength
and
good
permeability
can
be
challenging.
Also,
the
importance
of
compaction
energy
significant
determining
efficiency
pervious
concrete.
However,
research
on
development
unconfined
compressive
(UCS)
prediction
models
materials
that
incorporate
parameters
remains
unexplored.
Therefore,
this
study
aimed
to
balance
while
optimizing
required
production.
A
Central
Composite
Design
(CCD)
was
used
design
experiments
within
response
surface
methodology
(RSM)
evaluate
UCS,
porosity
specimens
produced
with
varying
cement
content
(280.00–340.00
kg/m3),
water-to-cement
ratio
(0.27–0.33),
aggregate-to-cement
(4:1–4.5:1),
(represented
by
VeBe
time,
13–82
s).
regression
model
goodness
fit
(R2adjusted
>
0.87)
calibrated
estimate
UCS
as
a
function
mix
time
(Tvc).
This
potentially
guide
field
practices
recommending
strategies
designs
concrete,
between
mechanical
hydraulic
construction
applications.
Sustainability,
Год журнала:
2024,
Номер
16(17), С. 7489 - 7489
Опубликована: Авг. 29, 2024
Floods,
caused
by
intense
rainfall
or
typhoons,
overwhelming
urban
drainage
systems,
pose
significant
threats
to
areas,
leading
substantial
economic
losses
and
endangering
human
lives.
This
study
proposes
a
methodology
for
flood
assessment
in
areas
using
multiclass
classification
approach
with
Deep
Neural
Network
(DNN)
optimized
through
hyperparameter
tuning
genetic
algorithms
(GAs)
leveraging
remote
sensing
data
of
dataset
the
Ibadan
metropolis,
Nigeria
Metro
Manila,
Philippines.
The
results
show
that
DNN
model
significantly
improves
risk
accuracy
(Ibadan-0.98)
compared
datasets
containing
only
location
precipitation
(Manila-0.38).
By
incorporating
soil
into
model,
as
well
reducing
number
classes,
it
is
able
predict
risks
more
accurately,
providing
insights
proactive
mitigation
strategies
planning.
Research Square (Research Square),
Год журнала:
2025,
Номер
unknown
Опубликована: Фев. 14, 2025
Abstract
This
paper
presents
a
novel
crack
detection
approach
in
railroads
using
electromagnetic
acoustic
transducers
(EMATs)
that
can
be
integrated
with
multi-domain
signal
processing
techniques
and
scalogram-driven
deep
learning
approach.
In
the
study
nine
different
scenarios
across
three
critical
sections
of
railway
track
were
investigated.
Several
useful
signals
techniques,
including
time-domain,
frequency-domain,
Power
Spectrum,
Periodogram,
Welch
Method,
short-time
Fourier
transform
(STFT),
wavelet
transform,
are
implemented
to
evaluate
data
acquired
through
EMAT
sensors.
Wavelet
transformations
applied
proposed
segments
generate
scalogram
images,
which
used
as
an
input
model
training.
When
results
compared
conventional
machine
classifiers,
performs
better,
exhibiting
higher
accuracy
identifying
types
cracks
from
images.
The
demonstrate
EMAT-based
fracture
identification,
advanced
processing,
greatly
enhance
inspection
safety,
even
though
system
currently
processes
batches
rather
than
real
time.
Future
work
will
focus
on
real-time
acquisition
further
optimization
architecture.
Healthcare,
Год журнала:
2025,
Номер
13(4), С. 408 - 408
Опубликована: Фев. 14, 2025
Background/Objectives:
The
increasing
utilization
of
artificial
intelligence
(AI)
in
the
medical
field
holds
potential
to
address
global
shortage
doctors.
However,
various
challenges,
such
as
usability,
privacy,
inequality,
and
misdiagnosis,
complicate
its
application.
This
literature
review
focuses
on
AI's
role
cardiology,
specifically
impact
diagnostic
accuracy
AI
algorithms
analyzing
12-lead
electrocardiograms
(ECGs)
detect
left
ventricular
hypertrophy
(LVH).
Methods:
Following
PRISMA
2020
guidelines,
we
conducted
a
comprehensive
search
PubMed,
CENTRAL,
Google
Scholar,
Web
Science,
Cochrane
Library.
Eligible
studies
included
randomized
controlled
trials
(RCTs),
observational
studies,
case-control
across
settings.
is
registered
PROSPERO
database
(registration
number
531468).
Results:
Seven
significant
were
selected
our
review.
Meta-analysis
was
performed
using
RevMan.
Co-CNN
(with
incorporated
demographic
data
clinical
variables)
demonstrated
highest
weighted
average
sensitivity
at
0.84.
2D-CNN
models
features)
showed
balanced
performance
with
good
(0.62)
high
specificity
(0.82);
excelled
(0.84)
but
had
lower
(0.71).
Traditional
ECG
criteria
(SLV
CV)
maintained
specificities
low
sensitivities.
Scatter
plots
revealed
trends
between
factors
metrics.
Conclusions:
can
rapidly
analyze
sensitivity.
variable
generally
comparable
classical
criteria.
Clinical
training
population
play
critical
their
efficacy.
Future
research
should
focus
collecting
diverse
different
populations
improve
generalizability
algorithms.
Energy & Fuels,
Год журнала:
2025,
Номер
39(9), С. 4549 - 4564
Опубликована: Фев. 19, 2025
The
axial
mixing/segregation
behavior
of
single
plastic
particles
in
a
bubbling
fluidized
bed
reactor
has
been
investigated
by
noninvasive
X-ray
imaging
techniques
the
temperature
range
500–650
°C
and
under
pyrolysis
conditions.
Experimental
results
showed
that
extent
mixing
between
particle
increases
as
both
fluidization
velocity
increase.
Three
modeling
approaches
were
proposed
to
describe
particle,
i.e.,
purely
mechanistic
model,
physics-informed
neural
network
(PINN),
an
augmented
PINN
(augPINN).
former
model
is
based
on
second
law
motion.
standard
PINN,
built
simply
embedding
motion
loss
function.
third
approach
involves
introduction
new
interphase
distribution
parameter,
P,
into
model.
This
parameter
represents
relative
importance
effects
emulsion
bubble
phases
particle.
was
obtained
training
using
displacement
data.
augPINN
shown
outperform
models
describing
polypropylene
particles.
Moreover,
P
found
be
physically
interpretable.
main
novelty
this
work
show
how
different
frameworks
concept
machine
learning
can
successfully
applied
complex
real-world
hydrodynamic
data
sets.
