Cross-dataset COVID-19 transfer learning with data augmentation
International Journal of Information Technology,
Год журнала:
2025,
Номер
unknown
Опубликована: Фев. 13, 2025
Язык: Английский
Performance Improvement of Covid-19 Cough Detection Based on Deep Learning with Segmentation Methods
Journal of Applied Data Sciences,
Год журнала:
2024,
Номер
5(2), С. 520 - 531
Опубликована: Май 31, 2024
COVID-19
is
an
emergency
problem
that
being
widely
discussed
in
the
world,
one
of
which
deep
learning-based
detection
method
has
been
developed
based
on
images
patient's
chest
or
cough.
In
this
research,
we
propose
a
way
to
improve
performance
cough
by
using
segmentation
produce
several
audio
files
containing
signal
from
file
sound
signals.
addition,
enabled
two
automatic
methods,
namely
Hysteresis
Comparator
power
spectrum
and
RMS
threshold
energy
value.
The
results
obtained
show
for
sounds
can
model's
detecting
coughs
4%
8%.
process
also
remove
noise
between
signals
provide
standard
input
model
form
signal.
information
related
characteristics
evaluation
hysteresis
comparator
better
with
unweighted
accuracy
(UA)
value
83.19%
compared
UA
79.06%.
Язык: Английский
Deep Learning based Energy-Efficient Task Scheduling in Cloud Computing
2022 9th International Conference on Computing for Sustainable Global Development (INDIACom),
Год журнала:
2024,
Номер
unknown, С. 1761 - 1766
Опубликована: Фев. 28, 2024
A
growing
number
of
manufacturing
businesses
are
becoming
more
concerned
with
energy
efficiency
because
rising
costs
and
environmental
consciousness.
The
enormous
shift
an
organization's
resource
requirements
from
on-site
technology
to
cloud-based
systems
is
resulting
in
a
significant
rise
the
expenses
that
cloud
reviews
face
when
it
comes
building,
maintaining,
providing
hardware
for
servers,
storage,
networks,
processing.
Because
operate
on
such
massive
scale,
even
little
decrease
performance
can
result
increases
or
usage
expenses.
Numerous
studies
have
put
forth
techniques
designed
optimize
throughput
consumption
while
accounting
varied
settings.
This
review's
scope
reviewing
several
survey
offloading
methods
based
GGCN
discussing
advantages
drawbacks
each.
An
exhaustive
scientific
examination
latest
related
unloading.
Subsequently,
examined.
Lastly,
few
recommendations
made
further
research.
Язык: Английский