Frontiers in Neuroscience,
Journal Year:
2023,
Volume and Issue:
17
Published: March 16, 2023
Children
with
benign
childhood
epilepsy
centro-temporal
spikes
(BECT)
have
spikes,
sharps,
and
composite
waves
on
their
electroencephalogram
(EEG).
It
is
necessary
to
detect
diagnose
BECT
clinically.
The
template
matching
method
can
identify
effectively.
However,
due
the
individual
specificity,
finding
representative
templates
in
actual
applications
often
challenging.
This
paper
proposes
a
spike
detection
using
functional
brain
networks
based
phase
locking
value
(FBN-PLV)
deep
learning.
To
obtain
high
effect,
this
uses
specific
'peak-to-peak'
phenomenon
of
montages
set
candidate
spikes.
With
(FBN)
are
constructed
(PLV)
extract
features
network
structure
during
discharge
synchronization.
Finally,
time
domain
structural
FBN-PLV
input
into
artificial
neural
(ANN)
Based
ANN,
EEG
data
sets
four
cases
from
Children's
Hospital,
Zhejiang
University
School
Medicine
tested
AC
97.6%,
SE
98.3%,
SP
96.8%.
Signal Image and Video Processing,
Journal Year:
2023,
Volume and Issue:
18(1), P. 899 - 909
Published: Oct. 19, 2023
Abstract
Epileptic
seizure
is
one
of
the
most
common
neurological
disorders
characterized
by
sudden
abnormal
discharge
neurons
in
brain.
Automated
detection
using
electroencephalograph
(EEG)
recordings
would
improve
quality
treatment
and
reduce
medical
overhead.
The
purpose
this
paper
to
design
an
automated
framework
that
can
effectively
identify
non-seizure
events
discovering
connectivity
between
brain
regions.
In
work,
a
weighted
directed
graph-based
method
with
effective
(EBC)
proposed
for
detection.
graph
built
analyzing
correlation
among
different
regions
Then,
theory-based
measures
are
used
extract
features
classification.
Furthermore,
we
illustrate
ability
achieve
patient-specific
model
cross-patient
model.
results
show
achieves
accuracy
values
99.97%
98.29%
CHB-MIT
dataset,
respectively.
These
demonstrate
classification
performance
be
provide
assistance
automatic
clinical
diagnosis.
AIMS Mathematics,
Journal Year:
2024,
Volume and Issue:
9(6), P. 16605 - 16622
Published: Jan. 1, 2024
<abstract><p>Electroencephalography
(EEG)
is
essential
for
diagnosing
neurological
disorders
such
as
epilepsy.
This
paper
introduces
a
novel
approach
that
employs
the
Allen-Cahn
(AC)
energy
function
extraction
of
nonlinear
features.
Drawing
on
concept
multifractals,
this
method
facilitates
acquisition
features
across
multi-scale.
Features
extracted
by
our
are
combined
with
support
vector
machine
(SVM)
to
create
AC-SVM
classifier.
By
incorporating
additional
measures
Kolmogorov
complexity,
Shannon
entropy,
and
Higuchi's
Hurst
exponent,
we
further
developed
AC-MC-SVM
Both
classifiers
demonstrate
excellent
performance
in
classifying
epilepsy
conditions.
The
classifier
achieves
89.97%
accuracy,
94.17%
sensitivity,
89.95%
specificity,
while
reaches
97.19%,
97.96%,
94.61%,
respectively.
Furthermore,
proposed
significantly
reduces
computational
costs
demonstrates
substantial
potential
tool
analyzing
medical
signals.</p></abstract>
Sensors,
Journal Year:
2023,
Volume and Issue:
23(4), P. 2061 - 2061
Published: Feb. 11, 2023
Adaptive
machine
learning
has
increasing
importance
due
to
its
ability
classify
a
data
stream
and
handle
the
changes
in
distribution.
Various
resources,
such
as
wearable
sensors
medical
devices,
can
generate
with
an
imbalanced
distribution
of
classes.
Many
popular
oversampling
techniques
have
been
designed
for
batch
rather
than
continuous
stream.
This
work
proposes
self-adjusting
window
improve
adaptive
classification
based
on
minimizing
cluster
distortion.
It
includes
two
models;
first
chooses
only
previous
instances
that
preserve
coherence
current
chunk’s
samples.
The
second
model
relaxes
strict
filter
by
excluding
examples
last
chunk.
Both
models
include
generating
synthetic
points
actual
points.
evaluation
proposed
using
Siena
EEG
dataset
showed
their
performance
several
classifiers.
best
results
obtained
Random
Forest
which
Sensitivity
reached
96.83%
Precision
99.96%.
Frontiers in Neuroscience,
Journal Year:
2023,
Volume and Issue:
17
Published: March 16, 2023
Children
with
benign
childhood
epilepsy
centro-temporal
spikes
(BECT)
have
spikes,
sharps,
and
composite
waves
on
their
electroencephalogram
(EEG).
It
is
necessary
to
detect
diagnose
BECT
clinically.
The
template
matching
method
can
identify
effectively.
However,
due
the
individual
specificity,
finding
representative
templates
in
actual
applications
often
challenging.
This
paper
proposes
a
spike
detection
using
functional
brain
networks
based
phase
locking
value
(FBN-PLV)
deep
learning.
To
obtain
high
effect,
this
uses
specific
'peak-to-peak'
phenomenon
of
montages
set
candidate
spikes.
With
(FBN)
are
constructed
(PLV)
extract
features
network
structure
during
discharge
synchronization.
Finally,
time
domain
structural
FBN-PLV
input
into
artificial
neural
(ANN)
Based
ANN,
EEG
data
sets
four
cases
from
Children's
Hospital,
Zhejiang
University
School
Medicine
tested
AC
97.6%,
SE
98.3%,
SP
96.8%.
