Heliyon,
Journal Year:
2024,
Volume and Issue:
10(5), P. e26799 - e26799
Published: Feb. 28, 2024
Computer-aided
diagnosis
(CAD)
systems
play
a
vital
role
in
modern
research
by
effectively
minimizing
both
time
and
costs.
These
support
healthcare
professionals
like
radiologists
their
decision-making
process
efficiently
detecting
abnormalities
as
well
offering
accurate
dependable
information.
heavily
depend
on
the
efficient
selection
of
features
to
accurately
categorize
high-dimensional
biological
data.
can
subsequently
assist
related
medical
conditions.
The
task
identifying
patterns
biomedical
data
be
quite
challenging
due
presence
numerous
irrelevant
or
redundant
features.
Therefore,
it
is
crucial
propose
then
utilize
feature
(FS)
order
eliminate
these
primary
goal
FS
approaches
improve
accuracy
classification
eliminating
that
are
less
informative.
phase
plays
critical
attaining
optimal
results
machine
learning
(ML)-driven
CAD
systems.
effectiveness
ML
models
significantly
enhanced
incorporating
during
training
phase.
This
empirical
study
presents
methodology
for
using
technique.
proposed
approach
incorporates
three
soft
computing-based
optimization
algorithms,
namely
Teaching
Learning-Based
Optimization
(TLBO),
Elephant
Herding
(EHO),
hybrid
algorithm
two.
algorithms
were
previously
employed;
however,
addressing
issues
predicting
human
diseases
has
not
been
investigated.
following
evaluation
focuses
categorization
benign
malignant
tumours
publicly
available
Wisconsin
Diagnostic
Breast
Cancer
(WDBC)
benchmark
dataset.
five-fold
cross-validation
technique
employed
mitigate
risk
over-fitting.
approach's
proficiency
determined
based
several
metrics,
including
sensitivity,
specificity,
precision,
accuracy,
area
under
receiver-operating
characteristic
curve
(AUC),
F1-score.
best
value
computed
through
suggested
97.96%.
clinical
decision
system
demonstrates
highly
favourable
performance
outcome,
making
valuable
tool
practitioners
secondary
opinion
reducing
overburden
expert
practitioners.
IEEE Access,
Journal Year:
2022,
Volume and Issue:
10, P. 10907 - 10933
Published: Jan. 1, 2022
Many
new
algorithms
have
been
proposed
to
solve
the
mathematical
equations
formulated
describe
real-world
problems.
But
there
still
does
not
exist
one
algorithm
that
could
problems
all.
And
most
of
defects
in
some
aspects,
they
need
be
improved
application.
In
order
find
a
more
efficient
optimization
and
inspired
by
better
performance
Arithmetic
Optimization
(AOA)
Aquila
Optimizer
(AO),
we
hybridization
them
abbreviated
AOAAO
this
paper.
Considering
Harris
Hawk
(HHO)
algorithm,
an
energy
parameter
E
was
also
introduced
balance
exploration
exploitation
procedures
individuals
swarms,
furthermore,
piecewise
linear
map
decrease
randomness
parameter.
Pseudo
code
presented,
Simulation
experiments
were
carried
out
on
benchmark
functions
three
classical
engineering
involved
optimization.
Nine
popular
well
demonstrated
included
for
comparison.
Results
confirmed
would
with
faster
convergence
rate,
higher
accuracy.
IEEE Access,
Journal Year:
2021,
Volume and Issue:
9, P. 115750 - 115765
Published: Jan. 1, 2021
As
research
in
alternate
energy
sources
is
growing,
solar
radiation
catching
the
eyes
of
community
immensely.
Since
generation
depends
on
uncontrollable
natural
variables,
without
proper
forecasting,
this
source
cannot
be
trusted.
For
use
machine
learning
algorithms
one
best
choices.
This
paper
proposed
an
optimized
forecasting
ensemble
model
consisting
pre-processing
and
training
phases.
The
phase
works
advanced
sine
cosine
algorithm
(ASCA)
using
Newton's
laws
gravity
motion
for
objects
(agents).
ASCA
uses
functions
to
update
agent's
position/velocity
components
by
considering
its
mass.
then
developed
k-nearest
neighbors
(KNN)
regression.
performance
measured
a
dataset
from
Kaggle
(Solar
Radiation
Prediction,
Task
NASA
Hackathon).
evaluated
comparison
with
Particle
Swarm
Optimizer
(PSO),
Whale
Optimization
Algorithm
(WOA),
Genetic
(GA),
Grey
Wolf
(GWO),
Squirrel
Search
(SSA),
Harris
Hawks
(HHO),
Hybrid
Greedy
Sine
Cosine
Differential
Evolution
(HGSCADE),
Modified
Cuckoo
(HMSCACSA),
Marine
Predators
(MPA),
Chimp
(ChOA),
Slime
Mould
(SMA).
Obtained
results
are
compared
those
state-of-the-art
models,
significant
superiority
confirmed
statistical
analysis
such
as
ANOVA
Wilcoxon's
rank-sum
tests.
Diagnostics,
Journal Year:
2022,
Volume and Issue:
12(11), P. 2757 - 2757
Published: Nov. 11, 2022
Background:
Numerous
tools,
including
nutritional
and
inflammatory
markers,
have
been
evaluated
as
the
predictors
of
poor
outcomes
in
COVID-19
patients.
This
study
aims
to
verify
predictive
role
prognostic
index
(PNI),
CONUT
Score,
markers
(monocyte
lymphocyte
ratio
(MLR),
neutrophil
(NLR),
platelet
(PLR),
systemic
(SII),
Systemic
Inflammation
Response
Index
(SIRI),
Aggregate
(AISI))
cases
deep
vein
thrombosis
(DVT)
acute
pulmonary
embolism
(APE)
risk,
well
mortality,
Methods:
The
present
was
designed
an
observational,
analytical,
retrospective
cohort
study,
included
899
patients
over
age
18
who
had
a
infection,
confirmed
through
real
time-polymerase
chain
reaction
(RT-PCR),
were
admitted
County
Emergency
Clinical
Hospital
Modular
Intensive
Care
Unit
UMFST
“George
Emil
Palade”
Targu
Mures,
Romania
between
January
2020
March
20212.
Results:
Non-Surviving
associated
with
higher
incidence
chronic
kidney
disease
(p
=
0.01),
cardiovascular
(atrial
fibrillation
(AF)
p
0.01;
myocardial
infarction
(MI)
0.02;
peripheral
arterial
(PAD)
0.0003),
malignancy
0.0001),
tobacco
obesity
dyslipidemia
0.004),
malnutrition
<
0.0001).
Multivariate
analysis
showed
that
both
high
baseline
value
all
independent
adverse
for
enrolled
(for
presence
PAD,
malignancy,
tobacco,
also
outcomes.
Conclusions:
According
our
findings,
MLR,
NLR,
PLR,
SII,
SIRI,
AISI,
lower
PNI
values
at
admission
strongly
predict
DVT
APE
mortality
Moreover,
predicted
outcomes,
while
CKD
predicts
risk
but
not
risk.
IEEE Access,
Journal Year:
2022,
Volume and Issue:
10, P. 74449 - 74471
Published: Jan. 1, 2022
This
study
offers
an
adaptive
dynamic
sine
cosine
fitness
grey
wolf
optimizer
(ADSCFGWO)
for
optimizing
the
parameters
of
two
types
antennas.
The
antennas
are
metamaterial
and
double
T-shape
monopoles.
ADSCFGWO
algorithm
is
based
on
technique
recently
developed
powerful
optimization
techniques:
a
modified
(GWO)
value
(SCA).
suggested
approach
utilizes
capabilities
both
algorithms
to
balance
better
exploration
exploitation
responsibilities
process
while
achieving
rapid
convergence.
First,
new
feature
selection
proposed
choose
most
significant
features
from
dataset
using
ADSCFGWO-based
ensemble
model
optimal
performance.
also
optimizes
bidirectional
recurrent
neural
network
(BRNN)
estimate
monopole
antenna
characteristics.
Several
experiments
were
undertaken
demonstrate
superiority
by
comparing
their
results
those
existing
algorithms,
selectors,
regression
models.
In
addition,
statistical
analysis
offered
evaluate
algorithm's
effectiveness
stability.
achieved
findings
efficacy
method
over
numerous
competing
algorithms.
IEEE Access,
Journal Year:
2022,
Volume and Issue:
10, P. 69688 - 69699
Published: Jan. 1, 2022
Breast
Cancer
(BC)
has
become
a
critical
illness
with
high
mortality
rate
during
the
previous
decade.
It
is
considered
women's
most
common
cancer.
In
this
paper,
we
propose
two
optimum
automated
BC
classification
approaches
based
on
hybridization
of
Whale
Optimization
Algorithm
(WOA)
and
Dragonfly
(DA),
Radial
Basis
Function
Kernel
Support
Vector
Machines
(RBF-SVM),
to
increase
accuracy
(CA)
by
determining
SVM
parameters.
The
effectiveness
proposed
WOA-SVM
DA-SVM
algorithms
tested
Wisconsin
Diagnosis
(WDBC)
databases
Database
(WBCD).
Various
metric
parameters
such
as
CA,
confusion
matrix,
area
under
ROC
curve
(AUC),
sensitivity,
specificity
are
utilized
assess
consider
approaches.
results
compared
not
only
optimizers,
Particle
Swarm
(PSO)
Genetic
(GA),
that
used
for
training
artificial
neural
networks
(ANN)
classifiers,
but
also
other
models.
explored
feature
selection,
their
findings
offered
According
experimental
results,
method
outperforms
WBCD
dataset.
On
WDBC
dataset,
however,
algorithm
algorithms.
Using
typical
datasets'
partition,
resultant
CA
99.65%
100%
WBCD,
respectively.
However,
using
10-fold
cross-validation
mean
97.89%
99.27%,
