IJGIE (International Journal of Graduate of Islamic Education),
Год журнала:
2024,
Номер
4(2), С. 412 - 426
Опубликована: Янв. 10, 2024
Neuronal
synchronization,
a
captivating
and
intricate
phenomenon
within
the
realm
of
neuroscience,
unfolds
as
mesmerizing
dance
coordinated
firing
among
groups
neurons,
ultimately
giving
rise
to
distinctive
brain
rhythms.
This
paper
embarks
on
comprehensive
exploration,
delving
into
profound
impact
neuronal
synchronization
cognition,
particularly
educational
landscape.
The
journey
navigates
nexus
neuroscience
education
from
unraveling
fundamental
mechanisms
underlying
this
elucidating
its
far-reaching
cognitive
consequences
practical
applications
in
teaching.
exploration
extends
beyond
theoretical
discussions
embrace
real-world
applications,
with
case
studies
examples
illustrating
successful
implementations
principles
settings.
These
instances
serve
beacons,
shedding
light
how
understanding
leveraging
can
significantly
enhance
teaching
learning
experience.
As
we
peer
future,
emerging
trends
neuroeducation
come
forefront.
trajectory
holds
promise
for
personalized
adaptive
experiences
dynamically
shaped
by
synchronization.
potential
benefits
inclusive
become
apparent,
emphasizing
importance
recognizing
accommodating
diverse
profiles
learners.
In
essence,
positions
not
merely
scientific
concept
but
guiding
principle
poised
revolutionize
pedagogy.
interplay
between
showcased
through
lens
beckons
future
where
insights
do
just
inform
strategies
intricately
woven
fabric
our
processes.
abstract
invites
readers
embark
that
transcends
disciplinary
boundaries,
illuminating
transformative
evolution
education.
Structural Concrete,
Год журнала:
2025,
Номер
unknown
Опубликована: Март 3, 2025
Abstract
Cracks
are
an
important
indicator
of
the
decline
in
load‐bearing
capacity
buildings.
Therefore,
it
is
great
significance
to
detect
and
classify
cracks
reinforced
concrete
(RC)
building
exterior
walls.
Accurately
automatically
classifying
remains
challenging
due
highly
irregular
nature
crack
images,
lighting
conditions,
background
texture
noise.
An
EfficientNet
network
model
combined
with
a
HiLo
attention
mechanism
was
proposed
achieve
precise
identification
classification
RC
wall
cracks.
Firstly,
existing
datasets
were
categorized,
combination
classical
data
augmentation
conditional
generative
adversarial
networks
used
augment
data,
improving
model's
generalization
ability
under
different
imaging
conditions
mitigating
adverse
effects
unbalanced
dataset.
Furthermore,
images
divided
into
high‐frequency
(Hi‐Fi)
low‐frequency
(Lo‐Fi)
feature
maps
by
applying
mechanism.
Hi‐Fi
module
suppressed
noise
captured
edge
details
retaining
relatively
high‐resolution
maps.
Lo‐Fi
extracts
global
features
through
window
segmentation
average
pooling
operations,
thereby
enhancing
capability
model.
The
experimental
results
showed
that
HiLo‐EfficientNet
achieved
best
image
performance
overall
accuracy
91.63%
compared
original
mainstream
deep
learning
models.
Advances in computational intelligence and robotics book series,
Год журнала:
2025,
Номер
unknown, С. 431 - 486
Опубликована: Май 8, 2025
Civil
Engineering
is
the
oldest
branch
of
engineering
which
was
essential
in
development
any
civilization
human
history
and
eventually
led
to
other
branches
with
progress
pages
history.
The
same
goes
for
current
times,
but
technological
developments
implementation
are
usually
seen
at
a
slower
rate
this
compared
existing
engineering.
Over
recent
decade,
AI
&
IoT
have
developed
very
fast
pace.
Their
applications
effect
could
be
noticed
field
civil
as
well,
will
covered
chapter.
Then,
some
important
new
area
because
discussed
order
understand
evolution
future
mentioned
field.
graphical
analyses
based
on
available
data
performed
support
study
understanding
prospects.
International Journal of Advanced Computer Science and Applications,
Год журнала:
2024,
Номер
15(5)
Опубликована: Янв. 1, 2024
This
research
paper
investigates
the
application
of
deep
learning
techniques,
specifically
convolutional
neural
networks
(CNNs),
for
crack
detection
in
historical
buildings.
The
study
addresses
pressing
need
non-invasive
and
efficient
methods
assessing
structural
integrity
heritage
conservation.
Leveraging
a
dataset
comprising
images
building
surfaces,
proposed
CNN
model
demonstrates
high
accuracy
precision
identifying
surface
cracks.
Through
integration
fully
connected
layers,
effectively
distinguishes
between
positive
negative
instances
cracks,
facilitating
automated
processes.
Visual
representations
finding
cases
ancient
buildings
validate
model's
efficacy
real-world
applications,
offering
tangible
evidence
its
capability
to
detect
anomalies.
While
highlights
potential
algorithms
preservation
efforts,
it
also
acknowledges
challenges
such
as
generalization,
computational
complexity,
interpretability.
Future
endeavors
should
focus
on
addressing
these
exploring
new
avenues
innovation
enhance
reliability
accessibility
technologies
cultural
Ultimately,
this
contributes
development
sustainable
solutions
safeguarding
architectural
heritage,
ensuring
future
generations.
Accurately
predicting
concrete
compressive
strength
is
fundamental
for
optimizing
mix
designs,
ensuring
structural
integrity,
and
advancing
sustainable
construction
practices.
Increased
demands
safer,
more
durable
infrastructure
necessitate
effective
predictive
models.
This
research
aims
to
compare
the
effectiveness
of
six
machine
learning
models
such
as
Linear
Regression,
Random
Forest,
Support
Vector
Regression
(SVR),
K-Nearest
Neighbors
(KNN),
Gradient
Boosting,
XGBoost
predict
strength.
Used
a
dataset
1030
instances
with
varying
mixture
compositions,
conducted
extensive
exploratory
data
analysis,
applied
feature
engineering
scaling
enhance
model
performance.
Assessments
were
performed
5-fold
cross-validation
approach
R-squared
(R²)
metric.
In
addition,
SHAP
value
used
understand
influence
each
on
results.
The
results
revealed
that
significantly
outperformed
other
models,
achieving
an
average
R²
0.9178
standard
deviation
0.0296.
Notably,
Forest
Boosting
also
demonstrated
robust
capabilities.
Based
our
experiment,
these
effectively
predicted
strengths
close
actual
measured
values,
confirming
their
practical
applicability
in
civil
engineering.
values
provided
insights
into
significant
impact
age
cement
quantity
outputs.
These
highlight
advanced
ensemble
methods'
prediction
underscore
importance
enhancing
accuracy.
