Journal of Healthcare Engineering,
Год журнала:
2020,
Номер
2020, С. 1 - 15
Опубликована: Май 22, 2020
Functional
near-infrared
spectroscopy
(fNIRS)
is
one
of
the
latest
noninvasive
brain
function
measuring
technique
that
has
been
used
for
purpose
brain-computer
interfacing
(BCI).
In
this
paper,
we
compare
and
analyze
effect
six
most
commonly
filtering
techniques
(i.e.,
Gaussian,
Butterworth,
Kalman,
hemodynamic
response
filter
(hrf),
Wiener,
finite
impulse
response)
on
classification
accuracies
fNIRS-BCI.
To
conclude
with
best
optimal
a
specific
cortical
task
owing
to
region,
divided
our
experimental
tasks
according
three
main
regions:
prefrontal,
motor,
visual
cortex.
Three
different
experiments
were
performed
prefrontal
motor
execution
while
stimuli.
The
include
rest
(R)
vs
mental
arithmetic
(MA),
R
object
rotation
(OB),
OB
MA.
Similarly,
execution,
left
finger
tapping
(LFT),
right
(RFT),
LFT
RFT.
Likewise,
cortex,
stimuli
(VS)
task.
These
ten
trials
five
subjects.
For
consistency
among
extracted
data,
statistical
features
evaluated
using
oxygenated
hemoglobin,
namely,
slope,
mean,
peak,
kurtosis,
skewness,
variance.
Combination
these
was
classify
data
by
nonlinear
support
vector
machine
(SVM).
obtained
from
SVM
hrf
Gaussian
significantly
higher
MA,
OB,
RFT,
VS
Wiener
found
be
significant
p<0.05.
results
show
feasibility
effective
removal
noises
fNIRS
data.
Frontiers in Human Neuroscience,
Год журнала:
2018,
Номер
12
Опубликована: Июнь 28, 2018
In
this
study,
a
brain-computer
interface
(BCI)
framework
for
hybrid
functional
near-infrared
spectroscopy
(fNIRS)
and
electroencephalography
(EEG)
locked-in
syndrome
(LIS)
patients
is
investigated.
Brain
tasks,
channel
selection
methods,
feature
extraction
classification
algorithms
available
in
the
literature
are
reviewed.
First,
we
categorize
various
types
of
with
cognitive
motor
impairments
to
assess
suitability
BCI
each
them.
The
prefrontal
cortex
identified
as
suitable
brain
region
imaging.
Second,
activity
that
contributes
generation
hemodynamic
signals
Mental
arithmetic
word
formation
tasks
found
be
use
LIS
patients.
Third,
since
specific
targeted
needed
BCI,
methods
determining
interest
combination
bundled-optode
configuration
threshold-integrated
vector
phase
analysis
turns
out
promising
solution.
Fourth,
usable
fNIRS
features
EEG
For
signal
peak
mean
highest
band
powers
promising.
classification,
linear
discriminant
has
been
most
widely
used.
However,
further
research
on
classifier
multiple
commands
desirable.
Overall,
proper
identification
will
improve
accuracy.
conclusion,
five
future
issues
identified,
new
scheme,
including
therapy
using
fNIRS-EEG
provided.
Technological
advances
in
multi-articulated
prosthetic
hands
have
outpaced
the
methods
available
to
amputees
intuitively
control
these
devices.
Amputees
often
cite
difficulty
of
use
as
a
key
contributing
factor
for
abandoning
their
prosthesis,
creating
pressing
need
improved
technology.
A
major
challenge
traditional
myoelectric
strategies
using
surface
electromyography
electrodes
has
been
achieving
intuitive
and
robust
proportional
multiple
degrees
freedom.
In
this
paper,
we
describe
new
method,
proprioceptive
sonomyographic
that
overcomes
several
limitations
control.
sonomyography,
muscle
mechanical
deformation
is
sensed
ultrasound,
compared
electrical
activation,
therefore
resulting
signals
can
directly
position
end
effector.
Compared
which
controls
velocity
end-effector
device,
more
congruent
with
residual
proprioception
limb.
We
tested
our
approach
5
upper-extremity
able-bodied
subjects
virtual
target
achievement
holding
task.
participants
demonstrated
ability
achieve
positional
freedom
an
hour
training.
Our
results
demonstrate
potential
dexterous
multiarticulated
prostheses.
Frontiers in Neuroscience,
Год журнала:
2020,
Номер
14
Опубликована: Июнь 23, 2020
Cognitive
workload
is
one
of
the
widely
invoked
human
factor
in
areas
Human
Machine
Interaction
(HMI)
and
Neuroergonomics.
The
precise
assessment
cognitive
mental
(MWL)
vital
requires
accurate
neuroimaging
to
monitor
evaluate
states
brain.
In
this
study,
we
have
decoded
four
classes
using
long-short
term
memory
(LSTM)
with
89.31%
average
accuracy
for
brain-Computer
Interface
(BCI).
brain
activity
signals
are
acquired
functional
Near-Infrared
Spectroscopy
(fNIRS)
from
prefrontal
cortex
(PFC)
region
We
performed
a
supervised
MWL
experimentation
varying
levels
on
15
participants
(both
male
female)
10
trials
each
per
participant.
Real-time
four-level
assessed
fNIRS
system
initial
classification
three
strong
machine
learning
(ML)
techniques,
Support
Vector
(SVM),
k-Nearest
Neighbor
(k-NN)
Artificial
Neural
Network
(ANN)
obtained
accuracies
54.33%,
54.31%,
69.36%
respectively.
novel
Deep
(DL)
frameworks
proposed
which
utilizes
Convolutional
(CNN)
Long
Short-Term
Memory
87.45%
respectively,
solve
high-dimensional
problem.
Statistical
analysis,
t-
test
one-way
F-test
(ANOVA)
also
through
deep
algorithms.
Results
show
that
DL
(LSTM
CNN)
algorithms
significantly
improve
performance
as
compared
ML
(SVM,
ANN,
k-NN)
Frontiers in Robotics and AI,
Год журнала:
2022,
Номер
8
Опубликована: Янв. 3, 2022
We
performed
an
electronic
database
search
of
published
works
from
2012
to
mid-2021
that
focus
on
human
gait
studies
and
apply
machine
learning
techniques.
identified
six
key
applications
using
data:
1)
Gait
analysis
where
analyzing
techniques
certain
biomechanical
factors
are
improved
by
utilizing
artificial
intelligence
algorithms,
2)
Health
Wellness,
with
in
monitoring
for
abnormal
detection,
recognition
activities,
fall
detection
sports
performance,
3)
Human
Pose
Tracking
one-person
or
multi-person
tracking
localization
systems
such
as
OpenPose,
Simultaneous
Localization
Mapping
(SLAM),
etc.,
4)
Gait-based
biometrics
person
identification,
authentication,
re-identification
well
gender
age
5)
“Smart
gait”
ranging
smart
socks,
shoes,
other
wearables
homes
retail
stores
incorporate
continuous
control
6)
Animation
reconstructs
motion
data,
simulation
Our
goal
is
provide
a
single
broad-based
survey
the
technology
identify
future
areas
potential
study
growth.
discuss
have
been
used
tasks
they
perform,
problems
attempt
solve,
trade-offs
navigate.
Frontiers in Human Neuroscience,
Год журнала:
2021,
Номер
14
Опубликована: Янв. 25, 2021
Human
gait
is
a
complex
activity
that
requires
high
coordination
between
the
central
nervous
system,
limb,
and
musculoskeletal
system.
More
research
needed
to
understand
latter
coordination's
complexity
in
designing
better
more
effective
rehabilitation
strategies
for
disorders.
Electroencephalogram
(EEG)
functional
near-infrared
spectroscopy
(fNIRS)
are
among
most
used
technologies
monitoring
brain
activities
due
portability,
non-invasiveness,
relatively
low
cost
compared
others.
Fusing
EEG
fNIRS
well-known
established
methodology
proven
enhance
brain–computer
interface
(BCI)
performance
terms
of
classification
accuracy,
number
control
commands,
response
time.
Although
there
has
been
significant
exploring
hybrid
BCI
(hBCI)
involving
both
different
types
tasks
human
activities,
remains
still
underinvestigated.
In
this
article,
we
aim
shed
light
on
recent
development
analysis
using
EEG-fNIRS-based
The
current
review
followed
guidelines
preferred
reporting
items
systematic
reviews
meta-Analyses
(PRISMA)
during
data
collection
selection
phase.
review,
put
particular
focus
commonly
signal
processing
machine
learning
algorithms,
as
well
survey
potential
applications
analysis.
We
distill
some
critical
findings
follows.
First,
hardware
specifications
experimental
paradigms
should
be
carefully
considered
because
their
direct
impact
quality
assessment.
Second,
since
modalities,
fNIRS,
sensitive
motion
artifacts,
instrumental,
physiological
noises,
quest
robust
sophisticated
algorithms.
Third,
temporal
spatial
features,
obtained
by
virtue
fusing
associated
with
cortical
activation,
can
help
identify
correlation
activation
gait.
conclusion,
hBCI
(EEG
+
fNIRS)
system
not
yet
much
explored
lower
limb
its
higher
limb.
Existing
systems
tend
only
one
modality.
foresee
vast
adopting
Imminent
technical
breakthroughs
expected
assistive
devices
Monitor
neuro-plasticity
neuro-rehabilitation.
However,
although
those
perform
controlled
environment
when
it
comes
them
certified
medical
device
real-life
clinical
applications,
long
way
go.
Sensors,
Год журнала:
2022,
Номер
22(5), С. 1932 - 1932
Опубликована: Март 1, 2022
This
research
presents
a
brain-computer
interface
(BCI)
framework
for
brain
signal
classification
using
deep
learning
(DL)
and
machine
(ML)
approaches
on
functional
near-infrared
spectroscopy
(fNIRS)
signals.
fNIRS
signals
of
motor
execution
walking
rest
tasks
are
acquired
from
the
primary
cortex
in
brain's
left
hemisphere
nine
subjects.
DL
algorithms,
including
convolutional
neural
networks
(CNNs),
long
short-term
memory
(LSTM),
bidirectional
LSTM
(Bi-LSTM)
used
to
achieve
average
accuracies
88.50%,
84.24%,
85.13%,
respectively.
For
comparison
purposes,
three
conventional
ML
support
vector
(SVM),
k-nearest
neighbor
(k-NN),
linear
discriminant
analysis
(LDA)
also
classification,
resulting
73.91%,
74.24%,
65.85%,
study
successfully
demonstrates
that
enhanced
performance
fNIRS-BCI
can
be
achieved
terms
accuracy
compared
approaches.
Furthermore,
control
commands
generated
by
these
classifiers
initiate
stop
gait
cycle
lower
limb
exoskeleton
rehabilitation.
Frontiers in Physiology,
Год журнала:
2023,
Номер
14
Опубликована: Март 30, 2023
Introduction:
Drowsy
driving
is
a
significant
factor
causing
dire
road
crashes
and
casualties
around
the
world.
Detecting
it
earlier
more
effectively
can
significantly
reduce
lethal
aftereffects
increase
safety.
As
physiological
conditions
originate
from
human
brain,
so
neurophysiological
signatures
in
drowsy
alert
states
may
be
investigated
for
this
purpose.
In
preface,
A
passive
brain-computer
interface
(pBCI)
scheme
using
multichannel
electroencephalography
(EEG)
brain
signals
developed
spatially
localized
accurate
detection
of
drowsiness
during
tasks.
Methods:
This
pBCI
modality
acquired
electrophysiological
patterns
12
healthy
subjects
prefrontal
(PFC),
frontal
(FC),
occipital
cortices
(OC)
brain.
Neurological
are
recorded
six
EEG
channels
spread
over
right
left
hemispheres
PFC,
FC,
OC
sleep-deprived
simulated
post-hoc
analysis,
spectral
δ,
θ,
α,
β
rhythms
extracted
terms
band
powers
their
ratios
with
temporal
correlation
complete
span
experiment.
Minimum
redundancy
maximum
relevance,
Chi-square,
ReliefF
feature
selection
methods
used
aggregated
Z-score
based
approach
global
ranking.
The
attributes
classified
decision
trees,
discriminant
logistic
regression,
naïve
Bayes,
support
vector
machines,
k-nearest
neighbors,
ensemble
classifiers.
binary
classification
results
reported
confusion
matrix-based
performance
assessment
metrics.
Results:
inter-classifier
comparison,
optimized
model
achieved
best
85.6%
accuracy
precision,
89.7%
recall,
87.6%
F1-score,
80%
specificity,
70.3%
Matthews
coefficient,
70.2%
Cohen's
kappa
score,
91%
area
under
receiver
operating
characteristic
curve
76-ms
execution
time.
inter-channel
were
obtained
at
F8
electrode
position
FC
significance
all
was
validated
p-value
less
than
0.05
statistical
hypothesis
testing
methods.
Conclusions:
proposed
has
better
accomplishment
multiple
objectives.
predictor
importance
reduced
extraction
cost
computational
complexity
minimized
use
conventional
machine
learning
classifiers
resulting
low-cost
hardware
software
requirements.
channel
most
promising
region
only
single
(F8)
which
reduces
physical
intrusiveness
normal
operation.
good
potential
practical
applications
requiring
earlier,
accurate,
disruptive
information
biosignals.
Journal of NeuroEngineering and Rehabilitation,
Год журнала:
2020,
Номер
17(1)
Опубликована: Фев. 26, 2020
The
Hand
Extension
Robot
Orthosis
(HERO)
Grip
Glove
was
iteratively
designed
to
meet
requests
from
therapists
and
persons
after
a
stroke
who
have
severe
hand
impairment
create
device
that
extends
all
five
fingers,
enhances
grip
strength
is
portable,
lightweight,
easy
put
on,
comfortable
affordable.Eleven
minimal
or
no
active
finger
extension
(Chedoke
McMaster
Stage
of
1-4)
post-stroke
were
recruited
evaluate
how
well
they
could
perform
activities
daily
living
function
assessments
with
without
wearing
the
HERO
Glove.The
11
participants
showed
statistically
significant
improvements
(p
<
0.01),
while
Glove,
in
water
bottle
grasp
manipulation
task
(increase
2.3
points,
SD
1.2,
scored
using
Chedoke
Arm
Inventory
scale
1
7)
index
147o,
44)
range
motion
145o,
36).
provided
12.7
N
(SD
8.9
N)
force
11.0
4.8)
pinch
their
affected
hands,
which
enabled
those
manipulate
blocks,
fork
bottle,
as
write
pen.
'more
less
satisfied'
an
assistive
(average
3.3
out
5
on
Quebec
User
Evaluation
Satisfaction
Assistive
Technology
2.0
Scale).
highest
satisfaction
scores
given
for
safety
security
(4.6)
ease
use
(3.8)
lowest
donning
(2.3),
required
under
min
assistance.
most
common
greater
smaller
glove
size
small
hands.The
safe
effective
tool
enabling
incorporate
into
living,
may
motivate
upper
extremity
life
stimulate
neuromuscular
recovery.