Heart
disease
is
a
global
health
concern
of
paramount
importance,
causing
significant
number
fatalities
and
disabilities.
Precise
timely
diagnosis
heart
pivotal
in
pre-venting
adverse
outcomes
improving
patient
well-being,
thereby
creating
growing
demand
for
intelligent
approaches
to
predict
effectively.
This
paper
introduces
an
Ensemble
Heuristic-Metaheuristic
Feature
Fusion
Learning
(EHMFFL)
algorithm
diagnosis.
Within
the
EHMFFL
algorithm,
diverse
ensemble
learning
model
crafted,
featuring
different
feature
subsets
each
heterogeneous
base
learner,
including
support
vector
machine,
K-nearest
neighbors,
logistic
regression,
random
forest,
naive
bayes,
decision
tree,
XGBoost.
The
primary
objective
identify
most
pertinent
features
leveraging
combined
heuristic-metaheuristic
approach
that
integrates
heuristic
knowledge
Pearson
correlation
coefficient
with
metaheuristic-driven
grey
wolf
optimizer.
second
aggregate
various
learners
through
learning,
aimed
at
constructing
robust
prediction
model.
performance
rigorously
assessed
using
Cleveland
Statlog
datasets
yielding
remarkable
results
accuracy
91.8%
88.9%,
respectively,
surpassing
state-of-the-art
machine
selection
techniques
These
findings
underscore
potential
enhancing
diagnostic
providing
valuable
clinicians
making
more
informed
decisions
regarding
care.
BioMedInformatics,
Год журнала:
2023,
Номер
3(4), С. 1124 - 1144
Опубликована: Дек. 6, 2023
This
study
focuses
on
leveraging
data-driven
techniques
to
diagnose
brain
tumors
through
magnetic
resonance
imaging
(MRI)
images.
Utilizing
the
rule
of
deep
learning
(DL),
we
introduce
and
fine-tune
two
robust
frameworks,
ResNet
50
Inception
V3,
specifically
designed
for
classification
MRI
Building
upon
previous
success
V3
in
classifying
other
medical
datasets,
our
investigation
encompasses
datasets
with
distinct
characteristics,
including
one
four
classes
another
two.
The
primary
contribution
research
lies
meticulous
curation
these
paired
datasets.
We
have
also
integrated
essential
techniques,
Early
Stopping
ReduceLROnPlateau,
refine
model
hyperparameter
optimization.
involved
adding
extra
layers,
experimenting
various
loss
functions
rates,
incorporating
dropout
layers
regularization
ensure
convergence
predictions.
Furthermore,
strategic
enhancements,
such
as
customized
pooling
significantly
elevated
accuracy
models,
resulting
remarkable
accuracy.
Notably,
pairing
Nadam
optimizer
yields
extraordinary
reaching
99.34%
gliomas,
93.52%
meningiomas,
98.68%
non-tumorous
images,
97.70%
pituitary
tumors.
These
results
underscore
transformative
potential
custom-made
approach,
achieving
an
aggregate
testing
97.68%
classes.
In
a
two-class
dataset,
Resnet
Adam
excels,
demonstrating
better
precision,
recall,
F1
score,
overall
99.84%.
Moreover,
it
attains
perfect
per-class
99.62%
‘Tumor
Positive’
100%
Negative’,
underscoring
advancement
realm
tumor
categorization.
underscores
innovative
possibilities
DL
models
specialized
optimization
methods
domain
diagnosing
cancer
from
Applied Soft Computing,
Год журнала:
2024,
Номер
155, С. 111427 - 111427
Опубликована: Фев. 24, 2024
Wireless
body
area
network
(WBAN)
is
an
internet-of-things
technology
that
facilitates
remote
patient
monitoring
and
enables
medical
staff
to
administer
timely
treatments.
One
of
the
main
challenges
in
designing
WBANs
routing
problem,
which
complicated
due
dynamic
changes
topology
limited
resources
nodes.
Several
heuristic
metaheuristic
methods
have
been
presented
solve
problem
WBANs.
Although
metaheuristics
outperform
heuristics
by
producing
higher-quality
solutions,
they
cannot
respond
real-time
requests.
This
paper
introduces
a
reactive
protocol
for
combines
fuzzy
with
learning
model.
It
utilizes
Takagi-Sugeno
Fuzzy
Inference
System
conjunction
Grey
Wolf
Optimizer
(named
TSFIS-GWO).
The
objective
simultaneously
benefit
from
advantages
both
approaches,
namely,
effectiveness
offline
hyperparameter
tuning
quickness
routing.
At
every
round,
tuned
system
takes
multiple
parameters
current
state
nodes
links
construct
multi-hop
tree
under
IEEE
802.15.6.
To
optimize
performance
each
WBAN,
rules
TSFIS
model
are
automatically
adjusted
through
method
based
on
GWO.
done
accordance
specific
requirements
application,
process
place
once
before
applied.
Simulation
results
three
applications
demonstrate
proposed
TSFIS-GWO
capable
providing
solutions
while
outperforming
existing
terms
application-specific
measures.
Algorithms,
Год журнала:
2024,
Номер
17(1), С. 34 - 34
Опубликована: Янв. 14, 2024
Heart
disease
is
a
global
health
concern
of
paramount
importance,
causing
significant
number
fatalities
and
disabilities.
Precise
timely
diagnosis
heart
pivotal
in
preventing
adverse
outcomes
improving
patient
well-being,
thereby
creating
growing
demand
for
intelligent
approaches
to
predict
effectively.
This
paper
introduces
an
ensemble
heuristic–metaheuristic
feature
fusion
learning
(EHMFFL)
algorithm
using
tabular
data.
Within
the
EHMFFL
algorithm,
diverse
model
crafted,
featuring
different
subsets
each
heterogeneous
base
learner,
including
support
vector
machine,
K-nearest
neighbors,
logistic
regression,
random
forest,
naive
bayes,
decision
tree,
XGBoost
techniques.
The
primary
objective
identify
most
pertinent
features
leveraging
combined
approach
that
integrates
heuristic
knowledge
Pearson
correlation
coefficient
with
metaheuristic-driven
grey
wolf
optimizer.
second
aggregate
various
learners
through
learning.
performance
rigorously
assessed
Cleveland
Statlog
datasets,
yielding
remarkable
results
accuracy
91.8%
88.9%,
respectively,
surpassing
state-of-the-art
techniques
diagnosis.
These
findings
underscore
potential
enhancing
diagnostic
providing
valuable
clinicians
making
more
informed
decisions
regarding
care.
Diagnostics,
Год журнала:
2023,
Номер
14(1), С. 89 - 89
Опубликована: Дек. 30, 2023
Skin
cancer
poses
a
significant
healthcare
challenge,
requiring
precise
and
prompt
diagnosis
for
effective
treatment.
While
recent
advances
in
deep
learning
have
dramatically
improved
medical
image
analysis,
including
skin
classification,
ensemble
methods
offer
pathway
further
enhancing
diagnostic
accuracy.
This
study
introduces
cutting-edge
approach
employing
the
Max
Voting
Ensemble
Technique
robust
classification
on
ISIC
2018:
Task
1-2
dataset.
We
incorporate
range
of
cutting-edge,
pre-trained
neural
networks,
MobileNetV2,
AlexNet,
VGG16,
ResNet50,
DenseNet201,
DenseNet121,
InceptionV3,
ResNet50V2,
InceptionResNetV2,
Xception.
These
models
been
extensively
trained
datasets,
achieving
individual
accuracies
ranging
from
77.20%
to
91.90%.
Our
method
leverages
synergistic
capabilities
these
by
combining
their
complementary
features
elevate
performance
further.
In
our
approach,
input
images
undergo
preprocessing
model
compatibility.
The
integrates
with
architectures
weights
preserved.
For
each
lesion
under
examination,
every
produces
prediction.
are
subsequently
aggregated
using
max
voting
technique
yield
final
majority-voted
class
serving
as
conclusive
Through
comprehensive
testing
diverse
dataset,
outperformed
models,
attaining
an
accuracy
93.18%
AUC
score
0.9320,
thus
demonstrating
superior
reliability
evaluated
effectiveness
proposed
HAM10000
dataset
ensure
its
generalizability.
delivers
robust,
reliable,
tool
cancer.
By
utilizing
power
advanced
we
aim
assist
professionals
timely
accurate
diagnoses,
ultimately
reducing
mortality
rates
patient
outcomes.
Computers,
Год журнала:
2024,
Номер
13(7), С. 157 - 157
Опубликована: Июнь 21, 2024
There
are
many
different
kinds
of
skin
cancer,
and
an
early
precise
diagnosis
is
crucial
because
cancer
both
frequent
deadly.
The
key
to
effective
treatment
accurately
classifying
the
various
cancers,
which
have
unique
traits.
Dermoscopy
other
advanced
imaging
techniques
enhanced
detection
by
providing
detailed
images
lesions.
However,
interpreting
these
distinguish
between
benign
malignant
tumors
remains
a
difficult
task.
Improved
predictive
modeling
necessary
due
occurrence
erroneous
inconsistent
outcomes
in
present
diagnostic
processes.
Machine
learning
(ML)
models
become
essential
field
dermatology
for
automated
identification
categorization
lesions
using
image
data.
aim
this
work
develop
improved
predictions
ensemble
models,
combine
numerous
machine
approaches
maximize
their
combined
strengths
reduce
individual
shortcomings.
This
paper
proposes
fresh
special
approach
model
optimization
classification:
Max
Voting
method.
We
trained
assessed
five
ISIC
2018
HAM10000
datasets:
AdaBoost,
CatBoost,
Random
Forest,
Gradient
Boosting,
Extra
Trees.
Their
enhance
overall
performance
with
Moreover,
were
fed
feature
vectors
that
optimally
generated
from
data
genetic
algorithm
(GA).
show
that,
accuracy
95.80%,
significantly
improves
when
compared
individually.
Obtaining
best
results
F1-measure,
recall,
precision,
method
turned
out
be
most
dependable
robust.
novel
aspect
more
robustly
reliably
classified
technique.
Several
pre-trained
models’
benefits
approach.
Bioengineering,
Год журнала:
2023,
Номер
10(10), С. 1190 - 1190
Опубликована: Окт. 13, 2023
Pediatric
brain
tumors
are
the
second
most
common
type
of
cancer,
accounting
for
one
in
four
childhood
cancer
types.
Brain
tumor
resection
surgery
remains
treatment
option
cancer.
While
assessing
margins
intraoperatively,
surgeons
must
send
tissue
samples
biopsy,
which
can
be
time-consuming
and
not
always
accurate
or
helpful.
Snapshot
hyperspectral
imaging
(sHSI)
cameras
capture
scenes
beyond
human
visual
spectrum
provide
real-time
guidance
where
we
aim
to
segment
healthy
tissues
from
lesions
on
pediatric
patients
undergoing
resection.
With
institutional
research
board
approval,
Pro00011028,
139
red-green-blue
(RGB),
279
visible,
85
infrared
sHSI
data
were
collected
subjects
with
system
integrated
into
an
operating
microscope.
A
random
forest
classifier
was
used
analysis.
The
RGB,
sHSI,
visible
models
achieved
average
intersection
unions
(IoUs)
0.76,
0.59,
0.57,
respectively,
while
segmentation
a
specificity
0.996,
followed
by
HSI
at
0.93
0.91,
respectively.
Despite
small
dataset
considering
cases,
our
leveraged
technology
successfully
segmented
high
during
procedures.
Mathematics,
Год журнала:
2023,
Номер
11(14), С. 3080 - 3080
Опубликована: Июль 12, 2023
This
paper
introduces
a
parallel
meta-heuristic
algorithm
called
Cuckoo
Flower
Search
(CFS).
combines
the
Pollination
Algorithm
(FPA)
and
(CS)
to
train
Multi-Layer
Perceptron
(MLP)
models.
The
is
evaluated
on
standard
benchmark
problems
its
competitiveness
demonstrated
against
other
state-of-the-art
algorithms.
Multiple
datasets
are
utilized
assess
performance
of
CFS
for
MLP
training.
experimental
results
compared
with
various
algorithms
such
as
Genetic
(GA),
Grey
Wolf
Optimization
(GWO),
Particle
Swarm
(PSO),
Evolutionary
(ES),
Ant
Colony
(ACO),
Population-based
Incremental
Learning
(PBIL).
Statistical
tests
conducted
validate
superiority
in
finding
global
optimum
solutions.
indicate
that
achieves
significantly
better
outcomes
higher
convergence
rate
when
tested.
highlights
effectiveness
solving
optimization
potential
competitive
field.