In
this
study,
we
examined
reservoir
computing
(RC)as
a
tool
for
predicting
the
macroscopic
dynamics
of
subset
oscillators
in
network
based
on
other
parts
it.
As
model
network,
utilized
300
Kuramoto
with
adaptation.
Our
results
demonstrate
that
effectively
addresses
task.
Additionally,
similar
was
applied
to
experimental
neurovisualization
data
and
exhibited
high
accuracy
reconstructing
damaged
EEG
channels
compared
classical
methods
like
spatial
interpolation.
In
the
current
study,
we
analyzed
results
of
cognitive
test
(Working
memory
task
according
to
Sternberg's
paradigm)
in
patients
with
asthenic
syndrome.
To
diagnose
severity
and
type
asthenia,
used
Multidimensional
Inventory
questionnaire
(MFI-20).
We
propose
a
new
performance
metric
that
considers
both
accuracy
answers
their
speed.
Our
findings
demonstrate
individuals
more
pronounced
syndrome
exhibit
slightly
higher
efficiency
performing
tasks
related
working
compared
those
less
asthenia.
In
this
work,
we
analyzed
the
functional
connectivity
between
different
groups
of
subjects.
The
included
patients
with
major
depressive
disorder,
and
bipolar
depression
that
were
obtained
during
experimental
research.
data
had
been
subjected
to
preprocessing
procedures
employed
in
order
identify
brain
regions
displayed
significant
variations.
In
this
work,
we
conducted
the
analysis
of
functional
magnetic
resonance
imaging
data
in
healthy
subjects
and
patients
with
major
depressive
disorder
that
were
obtained
during
experimental
research
when
resting.
The
signals
have
undergone
preprocessing
filtration
used
to
find
connectivity
between
brain
regions.
Results
demonstrate
significant
changes
connections
based
on
mutual
information
measure.
We
five
significantly
changed
connections,
four
which
increased
more
cotrol
group
over
patients.
Major
depressive
disorder
(MDD)
is
a
common
and
debilitating
psychiatric
illness
that
affects
millions
of
people
worldwide.
Despite
advancements
in
the
understanding
its
underlying
mechanisms,
diagnosis
treatment
MDD
remain
significant
challenge.
In
this
paper,
we
present
an
approach
for
classification
patients
with
based
on
their
functional
network
measures.
Our
results
demonstrate
simple
Linear
Discriminant
Analysis
achieves
high
accuracy
(83
%)
two
cases:
when
use
all
network's
couplings
or
only
strongest
ones.
Neuroscience
explores
the
anatomy,
function
and
development
of
central
peripheral
nervous
system.
Neuroscientists
lately
study
functional
brain
networks
to
understand
mental
disorders
like
depression.
Analysis
these
can
aid
in
diagnosing
Q-analysis,
a
higher-order
interaction
approach,
may
be
more
effective
identifying
regions
relevant
depression,
compared
standard
paired
approach.
This
examined
networks,
by
using
approach
with
Q-analysis
method,
depressed
patients
healthy
subjects
fMRI
data.
Results
indicated
fewer
weaker
interactions
controls.
Modularity
clustering
were
also
reduce
These
findings
highlight
importance
studying
for
understanding
We
investigate
the
capability
of
reservoir
computing
to
predict
dynamics
excitable
FitzHugh-Nagumo
model,
exposed
Gaussian
white
noise,
and
reproduce
phenomenon
coherence
resonance
in
reservoir.
train
neural
network
on
system
with
three
noise
amplitudes
then
test
different
noises.
show
that
can
exhibit
under
external
stimulus.
In
this
study,
we
examined
reservoir
computing
(RC)as
a
tool
for
predicting
the
macroscopic
dynamics
of
subset
oscillators
in
network
based
on
other
parts
it.
As
model
network,
utilized
300
Kuramoto
with
adaptation.
Our
results
demonstrate
that
effectively
addresses
task.
Additionally,
similar
was
applied
to
experimental
neurovisualization
data
and
exhibited
high
accuracy
reconstructing
damaged
EEG
channels
compared
classical
methods
like
spatial
interpolation.
