I
n
t
e
r
n
at
io
n
al
Jou
r
n
al
of
A
d
van
c
e
s
i
n
A
p
p
li
e
d
S
c
ie
n
c
e
s
(
I
JA
A
S
)
V
ol
.
14
, N
o.
4
,
D
e
c
e
m
be
r
20
25
, pp.
1
111
~
1
11
7
I
S
S
N
:
2252
-
8814
,
D
O
I
:
10.11591/
ij
a
a
s
.
v
14
.
i
4
.
pp
1
111
-
1
117
1111
Jou
r
n
al
h
om
e
page
:
ht
tp
:
//
ij
aas
.i
ae
s
c
or
e
.c
om
AI
-
d
r
i
ve
n
e
m
ot
i
on
r
e
c
ogn
i
t
i
on
sys
t
e
m
s f
or
su
st
ai
n
ab
l
e
m
e
n
t
al
h
e
al
t
h
c
ar
e
:
an
e
n
gi
n
e
e
r
i
n
g p
e
r
sp
e
c
t
i
ve
A
k
r
am
A
h
m
ad
1
,
V
ai
s
h
al
i
S
in
gh
1
,
K
am
al
U
p
r
e
t
i
2
1
D
e
pa
r
t
m
e
nt
of
C
om
put
e
r
S
c
i
e
nc
e
, M
a
ha
r
i
s
hi
U
ni
ve
r
s
i
t
y of
I
nf
or
m
a
t
i
on T
e
c
hn
ol
ogy, L
uc
know
, I
ndi
a
2
D
e
pa
r
t
m
e
nt
of
C
om
put
e
r
S
c
i
e
nc
e
,
C
H
R
I
S
T
(
D
e
e
m
e
d t
o be
U
ni
ve
r
s
i
t
y)
, D
e
l
hi
N
C
R
C
a
m
pu
s
, G
ha
z
i
a
b
a
d, I
ndi
a
A
r
t
ic
le
I
n
f
o
A
B
S
T
R
A
C
T
A
r
ti
c
le
h
is
to
r
y
:
R
e
c
e
iv
e
d
F
e
b
23
,
2025
R
e
vi
s
e
d
J
ul
18
,
2025
A
c
c
e
pt
e
d
S
e
p
21
,
2025
Emotion
recognition
systems
are
transforming
human
-
computer
inte
raction
(HCI)
applications
by
enabling
AI
-
driven,
adaptive,
and
responsive
mental
health
interventions.
This
study
explores
AI
-
based
emotion
reco
gnition
technologie
s
using
facial
expression
s,
voice
analysis,
text
-
based
sen
timent
processing,
and
physiological
signals
to
develop
scalable,
real
-
time
mental
health
support
systems.
Utilizing
datasets
such
as
FER2013,
JAFF
E,
and
CK+
,
our
research
examines
deep
learning
models,
including
EfficientNet
-
XGBoost,
which
achieved
over
90%
accuracy
across
key
evaluation metrics.
Unlike
traditional
mental
health
interventions,
AI
-
driven
systems
p
rovide
cost
-
effective,
accessible,
and
sustain
able
soluti
ons
through
teleme
dicine,
wearable
biosensors,
and
virtual
counselors.
The
study
also
highlights
critical
challenges
such
as
algorit
hmic
bias,
ethical
AI
complian
ce,
a
nd
the
energy
consumption
of
deep
learning
models.
By
integrating
m
achine
learning,
cloud
-
based
deployment,
and
edge
computing,
this
re
search
contribu
tes
to
the
developm
ent
of
sustain
able,
ethical,
and
user
-
cent
ric
AI
so
lutions
for
mental
health
care.
Future
directions
include
AI
model
optimization
for
energy
-
efficient
deploym
ents
and
the
creation
of
d
iverse,
inclusive da
tasets to impro
ve perf
ormance
across g
lobal populatio
ns.
K
e
y
w
o
r
d
s
:
E
nvi
r
onm
e
nt
a
l
a
w
a
r
e
ne
s
s
H
um
a
n
-
c
om
put
e
r
i
nt
e
r
a
c
ti
on
M
a
c
hi
ne
l
e
a
r
ni
ng
M
e
nt
a
l
il
ln
e
s
s
P
r
e
di
c
ti
ve
m
ode
li
ng
S
us
ta
in
a
bl
e
e
ngi
ne
e
r
in
g
This is an
open
acce
ss artic
le unde
r the
CC BY
-
SA
license.
C
or
r
e
s
pon
di
n
g A
u
th
or
:
K
a
m
a
l
U
pr
e
ti
D
e
pa
r
tm
e
nt
of
C
om
put
e
r
S
c
ie
nc
e
,
C
H
R
I
S
T
(
D
e
e
m
e
d t
o be
U
ni
ve
r
s
it
y)
, D
e
lh
i
N
C
R
C
a
m
pu
s
G
ha
z
ia
ba
d,
201003, I
ndi
a
E
m
a
il
:
ka
m
a
lu
pr
e
ti
1989@
gm
a
il
.c
om
1.
I
N
T
R
O
D
U
C
T
I
O
N
M
e
nt
a
l
he
a
lt
h
l
it
e
r
a
c
y
in
vo
lv
e
s
th
e
k
no
w
le
dge
,
be
l
ie
f
s
,
a
nd
a
tt
it
u
de
s
c
o
nc
e
r
n
in
g
m
e
n
ta
l
he
a
lt
h
di
s
o
r
d
e
r
s
,
in
f
l
ue
nc
e
d
by
in
di
vi
d
ua
l,
c
ul
tu
r
a
l,
a
nd
s
oc
ia
l
f
a
c
to
r
s
[
1
]
.
A
lt
hou
gh
te
c
hn
ol
ogy
-
b
a
s
e
d
in
t
e
r
ve
n
ti
ons
p
r
o
vi
d
e
s
c
a
la
bl
e
s
o
lu
ti
ons
,
c
os
t,
a
c
c
e
s
s
ib
il
it
y,
a
n
d s
t
ig
m
a
s
t
il
l
ha
m
pe
r
th
e
ir
r
e
a
c
h
[
2
]
.
S
t
ig
m
a
,
e
s
pe
c
ia
l
ly
,
d
is
c
o
ur
a
ge
s
pa
ti
e
nt
s
f
r
o
m
r
e
c
e
i
vi
n
g
t
r
e
a
t
m
e
n
t,
un
de
r
l
in
i
ng
t
he
ne
c
e
s
s
it
y
f
o
r
A
I
-
e
na
b
le
d
pl
a
tf
or
m
s
a
n
d
c
o
m
m
u
ni
ty
e
duc
a
ti
on
t
o
r
a
is
e
a
w
a
r
e
ne
s
s
a
n
d
e
a
r
l
y
de
te
c
t
io
n
[
3]
.
P
e
r
s
o
na
li
ty
f
a
c
t
or
s
s
uc
h
a
s
e
xt
r
a
ve
r
s
io
n
a
nd
ne
u
r
o
ti
c
is
m
,
a
c
c
o
r
d
in
g
to
t
he
b
ig
f
iv
e
th
e
or
y,
ha
ve
a
la
r
ge
b
e
a
r
in
g
on
m
e
n
ta
l
h
e
a
l
th
out
c
om
e
s
[
4
]
.
T
he
C
O
V
I
D
-
19
pa
nde
m
i
c
r
e
ve
a
le
d
d
e
f
ic
i
e
nc
i
e
s
in
m
e
nt
a
l
he
a
lt
h
s
e
r
v
ic
e
s
a
nd
a
c
c
e
le
r
a
t
e
d
th
e
us
e
o
f
A
I
-
pow
e
r
e
d
c
ha
t
bo
ts
s
uc
h
a
s
S
ir
i
a
nd
A
le
xa
t
o
s
c
r
e
e
n
a
nd
a
s
s
is
t
[
5
]
.
C
om
b
in
in
g
c
li
ni
c
a
l
a
pp
r
oa
c
he
s
w
it
h
pos
i
ti
ve
ps
yc
hol
og
y
a
n
d
di
g
it
a
l
te
c
hno
lo
gi
e
s
c
a
n
e
nha
nc
e
lo
ng
-
te
r
m
ps
yc
h
ol
ogi
c
a
l
w
e
ll
-
be
i
ng
b
y
de
ve
l
op
in
g
r
e
s
il
ie
nc
e
a
nd
e
m
o
ti
ona
l
r
e
s
i
li
e
nc
e
[
6
]
.
E
m
ot
io
n
r
e
c
og
ni
ti
on
is
vi
ta
l
f
or
s
oc
ia
l
in
t
e
r
a
c
t
io
n
th
r
ou
gh
t
he
in
te
r
p
r
e
ta
t
io
n
of
d
yna
m
ic
c
ue
s
,
s
uc
h
a
s
m
o
ve
m
e
n
t
di
r
e
c
ti
on
a
n
d
qua
li
ty
t
ha
t
a
d
d
to
e
m
o
ti
o
na
l
un
de
r
s
ta
nd
in
g
a
n
d
c
o
m
m
it
m
e
n
t
[
7
]
.
D
yn
a
m
ic
d
is
pl
a
ys
a
r
e
pa
r
t
ic
ul
a
r
l
y
e
f
f
e
c
t
iv
e
a
t
c
a
pt
u
r
i
ng
e
a
r
ly
a
t
te
n
ti
on
d
ur
in
g
di
f
f
ic
ul
t
c
on
di
ti
ons
,
f
a
c
i
l
it
a
ti
ng
e
m
ot
io
na
l
r
e
c
o
gn
it
io
n
a
nd
a
n
ti
c
ip
a
ti
on
.
W
it
h
i
nc
r
e
a
s
i
ng
im
po
r
t
a
nc
e
in
a
pp
li
c
a
t
io
ns
s
uc
h
a
s
hum
a
n
-
c
o
m
p
ut
e
r
in
te
r
a
c
t
io
n
(
H
C
I
)
,
v
ir
tu
a
l
r
e
a
li
ty
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8814
I
nt
J
A
dv A
ppl
S
c
i
,
V
ol
.
14
, N
o.
4
,
D
e
c
e
m
be
r
20
25
:
1111
-
1117
1112
a
nd
m
e
d
ic
i
ne
,
e
m
ot
io
n
r
e
c
og
ni
ti
on
is
i
nc
r
e
a
s
i
ng
ly
in
ve
s
t
ig
a
te
d
us
i
ng
e
le
c
t
r
oe
nc
e
p
ha
l
og
r
a
m
(
EEG
)
s
ig
na
ls
,
a
lt
hou
gh
s
u
bj
e
c
t
-
i
nde
p
e
nd
e
nt
a
na
l
ys
is
r
e
m
a
in
s
c
ha
ll
e
ng
in
g
[
8]
.
D
e
ve
lo
p
m
e
n
ts
in
A
I
a
n
d
de
e
p
l
e
a
r
ni
ng
,
s
pe
c
i
f
i
c
a
l
ly
E
E
G
-
ba
s
e
d
b
r
a
in
-
c
o
m
p
ut
e
r
i
nt
e
r
f
a
c
e
(
B
C
I
)
m
e
th
o
ds
,
a
r
e
f
a
c
il
it
a
t
in
g
m
a
c
h
in
e
s
t
o
be
t
te
r
c
la
s
s
i
f
y
e
m
ot
io
ns
[
9]
.
F
a
c
ia
l
e
xp
r
e
s
s
i
on
r
e
c
ogn
it
io
n,
a
id
e
d
b
y
c
on
vo
lu
ti
ona
l
ne
ur
a
l
ne
t
w
o
r
ks
(
C
N
N
s
)
a
nd
te
m
po
r
a
l
m
ode
ls
s
u
c
h
a
s
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
ne
two
r
ks
(
R
N
N
s
)
a
nd
lo
ng
s
ho
r
t
-
te
r
m
m
e
m
o
r
y
(
L
S
T
M
s
)
,
e
nha
nc
e
s
r
e
c
og
ni
ti
on
f
u
r
t
he
r
th
r
o
ug
h
th
e
us
e
o
f
ge
o
m
e
tr
i
c
a
nd
a
p
pe
a
r
a
nc
e
f
e
a
tu
r
e
s
i
nde
pe
n
de
n
t
o
f
la
r
ge
-
s
c
a
l
e
p
r
e
-
p
r
oc
e
s
s
i
ng
[
10
]
.
T
hi
s
r
e
s
e
a
r
c
h
f
il
ls
ga
ps
in
e
x
is
t
in
g
m
e
nt
a
l
he
a
lt
h
c
a
r
e
s
ys
te
m
s
b
y
i
nve
s
ti
ga
t
in
g
th
e
po
te
n
ti
a
l
of
AI
-
p
ow
e
r
e
d
e
m
ot
io
n
r
e
c
o
gn
it
io
n
f
r
om
f
a
c
ia
l
e
xp
r
e
s
s
i
o
ns
,
voi
c
e
,
a
nd
p
hys
i
ol
og
ic
a
l
s
i
gna
ls
to
f
a
c
il
it
a
te
e
m
pa
th
e
ti
c
a
n
d
t
im
e
ly
in
te
r
ve
nt
io
n
th
r
oug
h
H
C
I
.
I
t
a
d
dr
e
s
s
e
s
c
e
n
tr
a
l
c
ha
l
le
nge
s
s
uc
h
a
s
a
lg
o
r
it
hm
ic
b
ia
s
,
da
ta
p
r
iv
a
c
y,
a
nd
c
r
os
s
-
c
u
lt
ur
a
l
d
iv
e
r
s
it
y
,
p
r
o
vi
d
in
g
e
n
gi
n
e
e
r
in
g
a
n
d
e
th
ic
a
l
s
o
lu
t
io
ns
to
im
p
r
ove
s
c
a
la
b
il
it
y,
i
nc
l
us
i
vi
ty
,
a
nd
t
r
us
t.
E
m
ot
io
n
r
e
c
og
ni
ti
on
is
f
r
a
m
e
d
a
s
a
g
r
o
un
db
r
e
a
ki
n
g
te
c
hn
ol
ogy
f
o
r
ta
i
lo
r
e
d,
r
e
s
pons
ib
le
m
e
n
ta
l
h
e
a
l
th
t
r
e
a
tm
e
nt
,
w
it
h
t
he
s
ubs
e
q
ue
n
t
s
e
c
ti
ons
l
ook
in
g
in
t
o
s
om
e
o
f
th
e
m
os
t
s
ig
ni
f
ic
a
n
t
m
e
th
o
ds
,
in
c
lu
d
in
g
s
pe
e
c
h
a
na
ly
s
is
,
n
a
tu
r
a
l
la
n
gua
ge
p
r
oc
e
s
s
in
g
(
N
L
P
)
-
ba
s
e
d
te
xt
e
m
o
ti
o
n
de
te
c
ti
o
n,
f
a
c
ia
l
e
xp
r
e
s
s
i
on
r
e
c
o
gn
it
io
n
,
a
n
d
ph
ys
i
ol
o
gi
c
a
l
s
i
gna
l
m
o
ni
to
r
in
g
us
in
g
w
e
a
r
a
b
le
s
.
T
a
bl
e
1
o
ve
r
vi
e
w
s
th
e
s
e
m
e
t
ho
ds
,
o
ut
li
n
in
g
th
e
i
r
te
c
hn
i
que
s
,
a
dva
n
ta
ge
s
,
d
is
a
d
va
n
ta
ge
s
,
a
c
c
u
r
a
c
y,
a
nd
po
pul
a
r
da
ta
s
e
ts
.
T
a
bl
e
1.
S
um
m
a
r
y of
ke
y a
ppr
oa
c
he
s
i
n
e
m
ot
io
n r
e
c
ogni
ti
on
C
a
t
e
gor
y
K
e
y f
e
a
t
ur
e
s
C
or
e
t
e
c
hnol
ogi
e
s
/
m
e
t
hods
D
a
t
a
s
e
t
s
u
s
e
d
A
ppl
i
c
a
t
i
ons
P
e
r
f
or
m
a
nc
e
m
e
t
r
i
c
s
C
ha
l
l
e
nge
s
a
nd
l
i
m
i
t
a
t
i
ons
R
e
f
e
r
e
nc
e
s
F
a
c
i
a
l
e
m
ot
i
on
r
e
c
ogni
t
i
on
(
F
E
R
)
D
e
t
e
c
t
s
i
de
nt
i
t
y, a
ge
,
a
nd
ge
nde
r
.
˗
C
N
N
s
˗
T
r
a
ns
f
e
r
l
e
a
r
ni
ng
(
E
f
f
i
c
i
e
nt
N
e
t
-
X
G
B
oos
t
)
˗
C
K
+
˗
K
D
E
F
˗
J
A
F
F
E
˗
F
E
R
2013
˗
A
f
f
e
c
t
N
e
t
˗
E
duc
a
t
i
on
(
s
t
ude
nt
m
oni
t
or
i
ng)
˗
H
e
a
l
t
hc
a
r
e
(
pa
i
n
m
oni
t
or
i
ng)
˗
D
r
i
ve
r
f
a
t
i
gue
/
e
m
ot
i
on
de
t
e
c
t
i
on
˗
69.3%
:
M
a
s
ke
d
F
a
c
e
s
(
A
f
f
e
c
t
N
e
t
da
t
a
s
e
t
)
˗
99.69%
:
K
D
E
F
da
t
a
s
e
t
˗
L
ow
e
r
pe
r
f
or
m
a
nc
e
i
n
m
a
s
ke
d i
m
a
ge
s
˗
D
a
t
a
s
e
t
bi
a
s
e
s
(
e
.g., f
e
w
e
r
di
ve
r
s
e
s
a
m
pl
e
s
)
˗
H
i
gh
c
om
put
a
t
i
ona
l
c
os
t
f
or
r
e
a
l
-
t
i
m
e
pr
oc
e
s
s
i
ng
[
11]
–
[
13]
V
oi
c
e
e
m
ot
i
on
r
e
c
ogni
t
i
on
R
e
l
i
e
s
on
a
udi
o
f
e
a
t
ur
e
s
l
i
ke
pi
t
c
h,
e
ne
r
gy,
s
pe
c
t
r
ogr
a
m
s
˗
A
c
ous
t
i
c
s
i
gna
l
a
na
l
ys
i
s
(
M
F
C
C
,
L
P
C
C
c
oe
f
f
i
c
i
e
nt
s
)
˗
L
og
-
m
e
l
s
pe
c
t
r
ogr
a
m
s
˗
R
A
V
D
E
S
S
˗
L
D
C
da
t
a
ba
s
e
˗
UGA
D
a
t
a
ba
s
e
s
˗
S
pe
e
c
h
-
ba
s
e
d
m
e
nt
a
l
he
a
l
t
h
m
oni
t
or
i
ng
˗
M
ul
t
i
m
oda
l
e
m
ot
i
on
de
t
e
c
t
i
on
˗
H
um
a
n
-
r
obot
i
nt
e
r
a
c
t
i
on
˗
68%
:
L
og
-
M
e
l
s
pe
c
t
r
ogr
a
m
w
i
t
h 2D
C
N
N
s
˗
80.86%
˗
A
udi
o f
e
a
t
ur
e
s
e
l
e
c
t
i
on i
m
pa
c
t
s
a
c
c
ur
a
c
y
˗
P
oor
ge
ne
r
a
l
i
z
a
t
i
on
a
c
r
os
s
a
c
c
e
nt
s
/
l
a
ngua
g
e
s
[
14]
–
[
18]
T
e
xt
ua
l
e
m
ot
i
on
a
na
l
ys
i
s
(
T
E
A
)
˗
E
xpl
or
e
s
e
m
ot
i
ona
l
pol
a
r
i
t
y i
n
t
e
xt
us
i
ng
N
L
P
.
˗
A
na
l
yz
e
s
r
e
a
l
-
t
i
m
e
da
t
a
(
e
.g.,
C
O
V
I
D
-
19
t
w
e
e
t
s
)
.
˗
D
e
e
p
l
e
a
r
ni
ng
-
a
i
de
d
s
e
m
a
nt
i
c
t
e
xt
a
na
l
ys
i
s
(
D
L
S
T
A
)
˗
E
m
oj
i
-
or
i
e
nt
e
d
a
na
l
ys
i
s
˗
C
r
os
s
-
l
i
ngui
s
t
i
c
N
L
P
a
ppr
oa
c
he
s
˗
S
e
nt
i
m
e
nt
a
na
l
ys
i
s
t
oo
ls
˗
C
O
V
I
D
-
19
T
w
i
t
t
e
r
da
t
a
˗
UK
pa
r
l
i
a
m
e
nt
a
r
y
de
ba
t
e
s
˗
L
a
r
ge
s
oc
i
a
l
m
e
di
a
da
t
a
s
e
t
s
˗
S
e
nt
i
m
e
nt
m
oni
t
or
i
ng on
s
oc
i
a
l
m
e
di
a
˗
P
e
r
s
ona
l
i
z
e
d
A
I
s
ys
t
e
m
s
(
e
.g., c
ha
t
bot
s
)
˗
P
ol
i
t
i
c
a
l
s
e
nt
i
m
e
nt
pr
e
di
c
t
i
on
˗
97.22%
D
e
t
e
c
t
i
on
r
a
t
e
:
D
L
S
T
A
˗
98.02%
a
c
c
ur
a
c
y
L
i
m
i
t
e
d by t
he
a
va
i
l
a
bi
l
i
t
y of
l
a
r
ge
-
s
c
a
l
e
l
a
be
l
e
d da
t
a
s
e
t
s
[
19]
,
[
20]
2.
P
R
O
P
O
S
E
D
M
E
T
H
O
D
H
C
I
a
nd
a
f
f
e
c
t
r
e
c
ogni
ti
on
te
c
hnol
ogi
e
s
a
r
e
be
in
g
a
ppl
ie
d
m
o
r
e
a
nd
m
or
e
to
a
ugm
e
nt
e
m
pa
th
e
ti
c
,
r
e
s
pons
iv
e
r
e
a
c
ti
on
s
in
f
ie
ld
s
s
uc
h
a
s
m
e
nt
a
l
he
a
lt
h,
e
du
c
a
ti
on,
a
nd
he
a
lt
hc
a
r
e
.
W
hi
le
H
C
I
-
ba
s
e
d
m
e
nt
a
l
he
a
lt
h
a
ppl
ic
a
ti
ons
ha
v
e
gr
ow
n,
is
s
u
e
s
pe
r
s
is
t,
r
a
ngi
ng
f
r
om
in
a
de
qua
te
de
s
ig
n
a
s
s
e
s
s
m
e
nt
,
c
r
os
s
-
c
ul
tu
r
a
l
obs
ta
c
le
s
,
a
bs
e
nc
e
of
pa
ti
e
nt
-
f
oc
us
e
d
e
th
ic
s
[
2
1
]
,
us
a
bi
li
ty
pr
o
bl
e
m
s
[
2
2
]
,
a
nd
poor
c
om
pr
e
he
ns
io
n
of
di
gi
ta
l
th
e
r
a
pe
ut
ic
a
ll
ia
nc
e
s
(
D
T
A
)
[
2
3
]
.
R
is
in
g
s
ol
ut
io
ns
,
in
c
lu
di
ng
de
e
p
le
a
r
ni
ng
-
ba
s
e
d
e
m
ot
io
n
r
e
c
ogni
ti
on
f
r
a
m
e
w
or
ks
[
2
4
]
a
nd
hum
a
n
-
c
e
nt
e
r
e
d
m
a
c
hi
ne
le
a
r
ni
ng
(
H
C
M
L
)
ba
s
e
d
on
s
o
c
ia
l
m
e
di
a
[
2
5
]
,
hol
d
pot
e
nt
ia
l
but
de
m
a
nd a
tt
e
nt
io
n t
o pr
iv
a
c
y, e
th
ic
s
, a
nd u
s
e
r
pa
r
ti
c
ip
a
ti
on.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
dv A
ppl
S
c
i
I
S
S
N
:
2252
-
8814
AI
-
dr
iv
e
n e
m
ot
io
n r
e
c
ogni
ti
on s
y
s
te
m
s
f
o
r
s
us
ta
in
abl
e
m
e
nt
al
he
al
th
c
ar
e
…
(
A
k
r
am
A
hm
ad
)
1113
2
.1
.
E
m
ot
io
n
r
e
c
ogn
it
io
n
as
an
i
n
t
e
r
f
ac
e
in
h
u
m
an
-
c
om
p
u
t
e
r
i
n
t
e
r
ac
t
io
n
E
m
ot
i
on
p
e
r
c
e
pt
i
on
i
s
e
m
e
r
g
in
g
a
s
th
e
f
o
c
u
s
f
or
(
H
C
I
)
,
a
l
l
ow
i
ng
s
y
s
t
e
m
s
to
r
e
c
ogn
iz
e
h
um
a
n
e
m
o
ti
o
n
s
vi
a
f
a
c
i
a
l
e
x
pr
e
s
s
i
on
,
vo
ic
e
,
a
n
d
p
hy
s
i
ol
o
gy,
e
n
ha
n
c
in
g
e
m
p
a
th
y
a
nd
us
e
r
e
x
pe
r
ie
nc
e
i
n
h
e
a
l
th
,
e
du
c
a
ti
on
,
a
nd
s
e
r
v
ic
e
s
.
M
e
t
ho
ds
s
u
c
h
a
s
d
yn
a
m
i
c
f
a
c
i
a
l
e
m
o
ti
on
r
e
c
o
gn
it
io
n
f
r
om
a
c
ti
on
uni
ts
a
nd
ne
ur
a
l
ne
t
w
or
k
s
[
2
6
]
,
a
d
a
pt
iv
e
u
s
e
r
in
te
r
f
a
c
e
s
f
r
om
R
G
B
-
D
s
e
n
s
or
s
[
27
]
,
a
n
d
m
ul
ti
m
od
a
l
r
e
c
o
gn
it
io
n
f
r
om
E
E
G
a
nd
f
a
c
ia
l
e
x
pr
e
s
s
io
n
s
s
h
ow
h
ig
h
pe
r
f
or
m
a
n
c
e
a
nd
pr
om
i
s
e
.
D
e
e
p
le
a
r
ni
ng
,
tr
a
n
s
f
e
r
le
a
r
n
in
g
[
28
]
,
a
nd
pr
in
c
ip
a
l
c
om
po
ne
nt
a
na
ly
s
i
s
(
P
C
A
)
-
b
a
s
e
d
m
od
e
l
in
g
[
29
]
f
ur
th
e
r
i
m
pr
o
ve
r
e
c
ogn
it
i
on
p
e
r
f
or
m
a
n
c
e
,
w
he
r
e
a
s
th
e
r
m
a
l
vi
d
e
o
a
n
a
l
ys
i
s
w
i
th
f
a
s
t
e
r
R
-
C
N
N
a
n
d
B
C
I
e
xt
e
nd
H
C
I
c
a
p
a
b
il
i
ti
e
s
.
N
e
v
e
r
th
e
l
e
s
s
,
po
s
e
v
a
r
i
a
ti
on,
li
g
ht
i
ng
,
a
nd
th
e
a
bs
e
n
c
e
of
s
ub
je
c
t
-
in
d
e
p
e
n
de
nt
E
E
G
m
od
e
l
s
s
t
il
l
po
s
e
c
ha
l
le
ng
e
s
,
c
a
ll
i
ng
f
or
gr
e
a
t
e
r
s
o
c
i
o
-
b
e
h
a
v
io
r
a
l
in
s
ig
ht
a
n
d
e
x
pe
r
im
e
nt
a
l
f
r
a
m
e
w
or
k
s
t
ow
a
r
d
s
tr
u
s
t
w
or
th
y
H
C
I
s
ys
te
m
s
.
2
.2
.
H
u
m
an
f
ac
t
or
s
i
n
h
u
m
an
-
c
o
m
p
u
t
e
r
i
n
t
e
r
ac
t
io
n
f
or
m
e
n
t
al
h
e
al
t
h
a
p
p
li
c
at
io
n
s
H
um
a
n
f
a
c
to
r
s
of
H
C
I
f
or
m
e
nt
a
l
he
a
lt
h
a
pps
a
r
e
f
oc
us
e
d
on
us
e
r
-
or
ie
nt
e
d
de
s
ig
n
pr
in
c
ip
le
s
w
it
h
e
m
ot
io
na
l
s
e
ns
it
iv
it
y,
e
a
s
y
-
to
-
us
e
in
te
r
f
a
c
e
s
,
a
nd
pr
iv
a
c
y
t
o
e
ns
ur
e
tr
us
t
a
nd
pa
r
ti
c
ip
a
ti
on.
A
lb
e
it
th
e
in
c
r
e
a
s
e
d
pr
e
va
le
n
c
e
of
m
e
nt
a
l
he
a
lt
h
a
pps
,
poor
u
s
a
bi
li
ty
,
r
e
s
tr
ic
te
d
f
le
xi
bi
li
ty
,
a
nd
a
bs
e
nc
e
of
e
m
pa
th
ic
de
s
ig
n
s
ta
nd
in
th
e
w
a
y
of
br
oa
d
a
dopt
io
n,
a
s
s
tr
e
s
s
e
d
in
us
e
r
f
e
e
dba
c
k
[
30
]
.
R
e
s
e
a
r
c
h
in
di
c
a
te
s
th
a
t
us
in
g
hum
a
n
f
a
c
to
r
s
m
ode
ls
e
nha
n
c
e
s
u
s
a
bi
li
ty
in
he
a
lt
h
I
T
s
ys
te
m
s
[
3
1
]
,
but
num
e
r
ous
te
c
hnol
ogi
e
s
a
r
e
s
ti
ll
ha
r
d
to
us
e
,
r
e
g
a
r
dl
e
s
s
of
a
dva
nc
e
s
s
uc
h
a
s
bi
g
da
ta
a
nd
N
L
P
.
C
ul
t
ur
a
l,
s
oc
ia
l,
a
nd
pol
ic
y
ob
s
ta
c
le
s
a
l
s
o
im
pa
c
t
a
dopt
io
n,
pa
r
ti
c
ul
a
r
ly
a
m
ong
vul
ne
r
a
bl
e
popu
la
ti
ons
[
3
2
]
.
A
lt
hough
te
c
hnol
ogi
e
s
s
uc
h
a
s
m
obi
le
s
c
r
e
e
ni
ng
a
ppl
ic
a
ti
ons
,
c
ha
tb
ot
s
,
a
nd
in
te
r
ne
t
in
te
r
ve
nt
io
ns
hol
d
pr
om
is
e
,
lo
ng
-
te
r
m
us
e
is
c
ont
in
ge
nt
upon
ha
vi
ng
e
th
ic
a
l
c
ont
r
ol
s
, huma
n c
ont
a
c
t,
s
e
lf
-
r
e
f
le
c
ti
on
,
a
nd s
oc
ia
l
c
onn
e
c
ti
vi
ty
f
e
a
tu
r
e
s
.
3.
R
E
S
E
A
R
C
H
M
E
T
H
O
D
O
L
O
G
Y
T
he
s
tu
dy'
s
r
e
s
e
a
r
c
h
te
c
hni
que
is
s
ho
w
n
in
F
ig
ur
e
1,
a
s
w
im
la
ne
f
lo
w
c
ha
r
t
is
or
ie
nt
e
d.
T
he
“
s
tu
dy
de
s
ig
n
”
s
te
p,
w
hi
c
h
out
li
ne
s
a
m
ix
e
d
-
m
e
th
ods
a
ppr
oa
c
h
to
e
m
ot
io
n
id
e
nt
if
ic
a
ti
on
a
nd
H
C
I
,
c
om
e
s
f
ir
s
t.
T
he
“
in
c
lu
s
io
n
a
nd
e
xc
lu
s
io
n
c
r
it
e
r
ia
,
”
w
hi
c
h
gua
r
a
nt
e
e
th
a
t
onl
y
th
e
m
os
t
pe
r
ti
ne
nt
s
tu
di
e
s
a
r
e
in
c
lu
de
d
w
it
hi
n
th
e
s
c
ope
of
th
e
s
tu
dy,
c
om
e
a
f
te
r
th
e
“
s
e
a
r
c
h
s
tr
a
te
gy
”
pha
s
e
,
w
hi
c
h
d
e
ta
il
s
th
e
m
e
th
odi
c
a
l
s
e
a
r
c
h
f
or
pe
r
ti
ne
nt
l
it
e
r
a
tu
r
e
.
F
ig
ur
e
1. R
e
s
e
a
r
c
h
m
e
th
odol
ogy ove
r
vi
e
w
T
he
“
s
c
r
e
e
ni
ng
a
nd
s
e
l
e
c
ti
on
”
s
te
p
e
m
ph
a
s
iz
e
s
how
P
R
I
S
M
A
s
ta
nda
r
ds
a
r
e
f
ol
lo
w
e
d
w
hi
le
c
onduc
ti
ng
a
s
ys
te
m
a
ti
c
r
e
vi
e
w
of
pa
pe
r
s
.
T
h
e
“
da
ta
a
na
ly
s
is
”
s
e
c
ti
on
c
a
pt
ur
e
s
th
e
ove
r
a
ll
qua
li
ta
ti
ve
a
nd
qua
nt
it
a
ti
ve
m
e
th
odol
ogy
c
a
r
r
ie
d
out
f
or
e
xt
r
a
c
ti
ng
in
s
ig
ht
s
f
r
o
m
pe
r
f
or
m
a
nc
e
a
nd
us
e
r
e
xpe
r
ie
nc
e
r
e
ga
r
di
ng
m
ode
ls
. L
a
s
tl
y, t
he
“
a
ppl
ic
a
ti
ons
”
pha
s
e
unc
ove
r
s
t
he
pr
a
c
ti
c
a
l
a
ppl
ic
a
ti
on of
e
m
ot
io
n r
e
c
ogni
ti
on t
e
c
hnol
ogy
in
m
e
nt
a
l
he
a
lt
h a
nd w
e
ll
-
be
in
g. T
hi
s
f
lo
w
c
ha
r
t
is
a
s
tr
uc
tu
r
e
d,
vi
s
ua
li
z
e
d s
um
m
a
r
y of
r
e
s
e
a
r
c
h m
e
th
odol
ogy,
e
ns
ur
in
g c
la
r
it
y a
nd c
om
pr
e
he
ns
iv
e
ne
s
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8814
I
nt
J
A
dv A
ppl
S
c
i
,
V
ol
.
14
, N
o.
4
,
D
e
c
e
m
be
r
20
25
:
1111
-
1117
1114
3
.1
.
S
t
u
d
y
d
e
s
ig
n
T
hi
s
s
tu
dy
in
vol
ve
d
a
m
ix
e
d
-
m
e
th
od
s
r
e
vi
e
w
s
tr
a
te
gy
to
gi
ve
a
n
a
ll
-
r
ounde
d
a
ppr
e
c
ia
ti
on
of
H
C
I
a
nd
th
e
r
e
c
ogni
ti
on
of
e
m
ot
io
ns
in
ps
yc
hol
ogy
a
nd
w
e
ll
-
be
in
g.
T
e
c
hnol
ogi
c
a
l
e
f
f
e
c
ti
ve
ne
s
s
,
us
e
r
e
nga
ge
m
e
nt
,
c
ha
ll
e
nge
s
,
a
nd
th
e
s
o
c
ia
l
im
pa
c
t
of
e
m
ot
io
n
r
e
c
ogni
ti
on
a
ppl
ic
a
ti
ons
a
r
e
f
ur
th
e
r
e
xpl
or
e
d
th
r
ough
th
e
in
te
gr
a
ti
on
of
qua
nt
it
a
ti
ve
a
nd
qua
li
ta
ti
ve
da
ta
.
A
s
ys
te
m
a
ti
c
s
e
a
r
c
h
a
ppr
oa
c
h
w
a
s
us
e
d
to
f
in
d
pe
r
ti
ne
nt
s
tu
di
e
s
of
e
m
ot
io
n
r
e
c
ogni
ti
on
in
H
C
I
f
or
m
e
nt
a
l
w
e
ll
-
be
in
g,
a
s
out
li
ne
d
in
T
a
bl
e
2,
w
hi
c
h
pr
ovi
de
s
a
br
e
a
kdown
of
th
e
num
be
r
of
pa
pe
r
s
r
e
tr
ie
ve
d
f
r
om
va
r
io
us
d
a
ta
ba
s
e
s
us
in
g
ta
r
ge
te
d
ke
yw
or
d
s
.
A
r
e
vi
e
w
of
pe
e
r
-
r
e
vi
e
w
e
d
s
tu
di
e
s
s
ol
e
ly
c
e
nt
e
r
e
d
on
e
m
ot
io
n
r
e
c
ogni
ti
on
e
m
be
dde
d
w
it
hi
n
H
C
I
,
in
c
lu
di
ng
bot
h
qua
nt
it
a
ti
ve
m
e
a
s
ur
e
s
(
e
.g., a
c
c
ur
a
c
y
a
nd
e
f
f
e
c
ti
ve
n
e
s
s
)
a
nd qu
a
li
ta
ti
ve
i
nf
or
m
a
ti
on (
e
.g., us
e
r
e
xpe
r
ie
nc
e
)
f
or
a
n
e
xha
us
ti
ve
in
te
r
pr
e
ta
ti
on,
w
a
s
in
c
lu
de
d.
T
e
c
hnol
ogi
e
s
di
r
e
c
tl
y
a
ppl
ic
a
bl
e
to
m
e
nt
a
l
he
a
lt
h
in
te
r
ve
nt
io
ns
,
in
c
lu
di
ng
c
ha
tb
ot
s
,
w
e
a
r
a
bl
e
te
c
hnol
ogy,
a
nd
vi
r
tu
a
l
th
e
r
a
pi
s
ts
,
w
e
r
e
pr
io
r
it
iz
e
d
be
c
a
us
e
of
th
e
ir
di
r
e
c
t
im
pa
c
t.
N
on
-
e
m
ot
io
n
-
de
te
c
ti
on
-
f
oc
us
e
d
s
tu
di
e
s
a
nd
s
tu
di
e
s
th
a
t
w
e
r
e
not
r
e
le
v
a
nt
to
H
C
I
or
m
e
nt
a
l
he
a
lt
h
w
e
r
e
e
xc
lu
de
d,
a
s
w
e
ll
a
s
non
-
pe
e
r
-
r
e
vi
e
w
e
d
or
a
ne
c
dot
a
l
s
o
ur
c
e
s
,
in
or
de
r
to
ke
e
p
th
e
r
e
s
e
a
r
c
h
r
ig
or
ous
.
A
ppl
yi
ng
a
P
R
I
S
M
A
-
gui
de
d
s
y
s
te
m
a
ti
c
s
c
r
e
e
ni
ng
pr
oc
e
s
s
,
ti
tl
e
s
a
nd
a
b
s
tr
a
c
ts
w
e
r
e
in
it
ia
ll
y
s
c
r
e
e
ne
d
f
or
r
e
le
va
nc
e
,
f
ol
lo
w
e
d
by
f
ul
l
-
te
xt
e
xa
m
in
a
ti
on,
f
in
a
ll
y
le
a
di
ng
to
th
e
s
e
le
c
ti
on
of
55
hi
gh
-
qua
li
ty
s
tu
di
e
s
f
or
de
ta
il
e
d e
va
lu
a
ti
on.
T
a
bl
e
2. S
e
a
r
c
h
s
tr
a
te
gy s
um
m
a
r
y
K
e
yw
or
d
S
c
opus
I
E
E
E
X
pl
or
e
P
ubM
e
d
G
oogl
e
S
c
hol
a
r
S
c
i
e
nc
e
D
i
r
e
c
t
T
ot
a
l
pa
pe
r
s
f
ound
E
m
ot
i
on
r
e
c
ogni
t
i
on
85
60
25
130
45
345
H
C
I
90
110
10
180
65
455
M
e
nt
a
l
he
a
l
t
h t
e
c
hnol
ogi
e
s
70
25
95
150
80
420
D
i
gi
t
a
l
he
a
l
t
h t
ool
s
50
30
75
100
55
310
T
e
l
e
he
a
l
t
h a
nd A
I
45
55
85
120
50
355
A
da
pt
i
ve
m
e
nt
a
l
he
a
l
t
h a
pps
40
20
60
80
30
230
H
C
I
f
or
m
e
nt
a
l
w
e
l
l
-
be
i
ng
65
50
40
95
40
290
4.
R
E
S
U
L
T
S
A
N
D
D
I
S
C
U
S
S
I
O
N
T
he
s
e
le
c
te
d
e
m
ot
io
n
r
e
c
ogni
ti
on
s
tr
a
te
gy
ut
il
iz
e
s
c
ut
ti
ng
-
e
d
ge
m
e
th
ods
s
uc
h
a
s
C
N
N
s
,
tr
a
n
s
f
e
r
le
a
r
ni
ng,
a
nd
m
ul
ti
m
oda
l
a
na
ly
s
is
to
pr
ovi
de
hi
gh
a
c
c
ur
a
c
y
a
nd
s
c
a
la
bi
li
ty
a
c
r
os
s
r
e
a
l
-
w
or
ld
a
ppl
ic
a
ti
ons
.
T
he
m
e
th
ods
s
uc
c
e
s
s
f
ul
ly
s
ol
ve
i
s
s
ue
s
s
uc
h
a
s
m
a
s
ke
d
f
a
c
e
s
,
l
ow
-
li
ght
e
nvi
r
onm
e
nt
s
,
a
nd
s
ubt
le
voi
c
e
c
ue
s
,
w
hi
le
c
ont
in
uous
,
non
-
in
va
s
iv
e
e
m
ot
io
na
l
m
oni
to
r
in
g
is
f
a
c
il
i
ta
te
d
th
r
ough
th
e
in
te
gr
a
ti
on
o
f
phys
io
lo
gi
c
a
l
s
ig
na
ls
a
nd w
e
a
r
a
bl
e
t
e
c
hnol
ogi
e
s
.
B
y i
nt
e
gr
a
ti
ng de
e
p l
e
a
r
ni
ng w
it
h m
a
c
hi
ne
l
e
a
r
ni
ng, t
hi
s
hol
is
ti
c
pa
r
a
di
gm
pr
ovi
de
s
s
tr
ong,
e
m
pa
th
e
ti
c
,
a
nd
c
ont
e
xt
ua
l
s
ol
ut
io
ns
f
or
r
e
a
l
-
ti
m
e
e
m
ot
io
n
de
te
c
ti
on
in
he
a
lt
hc
a
r
e
,
e
duc
a
ti
on,
a
nd
a
ut
onomous
s
ys
te
m
s
.
D
a
ta
e
xt
r
a
c
ti
on
in
th
is
s
tu
dy
w
a
s
c
onduc
te
d w
it
h
a
s
ta
nda
r
di
z
e
d
f
or
m
to
e
ns
ur
e
th
a
t
th
e
im
por
ta
nt
de
ta
il
s
w
e
r
e
c
ol
le
c
te
d
in
a
n
or
ga
ni
z
e
d
m
a
nne
r
f
r
om
c
hos
e
n
s
tu
di
e
s
,
s
uc
h
a
s
a
ut
hor
de
ta
il
s
,
publ
ic
a
ti
on
ye
a
r
,
a
im
s
,
m
e
th
odol
ogy,
r
e
s
ul
ts
,
a
nd
te
c
hnol
ogi
e
s
us
e
d
.
Q
ua
nt
it
a
ti
ve
m
e
a
s
ur
e
s
,
f
or
in
s
ta
nc
e
,
th
e
a
c
c
ur
a
c
y
of
e
m
ot
io
n
r
e
c
ogni
ti
on,
a
s
w
e
ll
a
s
qua
li
ta
ti
ve
f
a
c
to
r
s
li
ke
us
e
r
in
te
r
a
c
ti
on
a
nd
e
th
ic
a
l
is
s
ue
s
,
w
e
r
e
not
e
d
f
or
a
n
ove
r
a
ll
unde
r
s
ta
ndi
ng.
T
he
qua
nt
it
a
ti
ve
a
na
ly
s
is
pr
e
s
e
nt
e
d
in
F
ig
ur
e
2
c
om
pa
r
e
d
f
our
m
ode
ls
of
e
m
ot
io
n
r
e
c
ogni
ti
on
ba
s
e
d
on
a
c
c
ur
a
c
y,
pr
e
c
is
io
n,
r
e
c
a
ll
,
a
nd
F
1
-
s
c
or
e
s
how
in
g
E
f
f
ic
ie
nt
N
e
t
-
X
G
B
oos
t
to
be
th
e
be
s
t,
f
ol
lo
w
e
d
by
th
e
e
ns
e
m
bl
e
c
la
s
s
if
ie
r
.
F
ig
ur
e
3
a
ls
o
s
how
s
tr
e
nds
in
da
ta
s
e
t
us
a
g
e
,
w
he
r
e
F
E
R
2013
ha
s
be
e
n
th
e
m
os
t
ut
il
iz
e
d
(
30
%
)
,
f
ol
lo
w
e
d
by
J
A
F
F
E
(
25%
)
,
C
K
+
(
20%
)
,
K
D
E
F
(
15%
)
, a
nd A
f
f
e
c
tNe
t
(
10%
)
, s
how
in
g both t
he
i
nc
r
e
a
s
e
a
nd t
r
e
nds
i
n da
ta
s
e
t
c
hoi
c
e
ove
r
t
he
ye
a
r
s
.
T
o
g
a
i
n
a
de
e
p
e
r
in
s
ig
h
t
i
nt
o
th
e
pop
ul
a
r
it
y
a
nd
pe
r
f
or
m
a
n
c
e
of
e
m
o
ti
on
r
e
c
o
gn
it
io
n
da
ta
s
e
ts
,
th
e
ir
us
a
ge
p
a
t
te
r
ns
w
e
r
e
e
x
a
m
in
e
d,
he
lp
in
g
e
va
lu
a
te
t
he
i
r
a
p
p
r
op
r
ia
te
ne
s
s
f
o
r
a
lg
o
r
i
th
m
t
r
a
i
ni
ng
a
n
d
te
s
t
in
g
.
F
ig
u
r
e
4
d
e
p
ic
ts
t
he
te
c
hn
ol
o
gy
a
d
op
ti
on
c
u
r
v
e
of
e
m
o
ti
o
n
r
e
c
og
ni
ti
on
s
o
lu
ti
o
ns
f
r
o
m
20
15
t
o
202
1
w
i
th
a
s
s
oc
ia
te
d
im
pl
e
m
e
n
ta
ti
on
c
ha
l
le
ng
e
s
.
E
ve
n
a
s
a
d
opt
io
n
ha
s
c
o
nt
in
ue
d
to
g
r
o
w
,
a
n
in
te
r
e
s
t
in
g
de
pa
r
t
ur
e
f
r
o
m
th
e
c
ha
l
le
n
ge
s
t
r
e
n
d
is
obs
e
r
ve
d
f
r
om
a
r
ou
n
d
2
01
8,
i
nd
ic
a
t
in
g
th
a
t
p
r
i
m
a
r
y
e
t
hi
c
a
l
a
n
d
te
c
h
ni
c
a
l
h
u
r
dl
e
s
ha
ve
be
e
n
s
l
ow
ly
ove
r
c
o
m
e
s
how
in
g
in
c
r
e
a
s
e
d
a
c
c
e
pt
a
nc
e
a
nd
in
c
or
po
r
a
t
io
n
o
f
e
m
o
ti
on
r
e
c
o
gn
it
io
n
te
c
hno
lo
gy
in
r
e
a
l
-
w
or
ld
a
pp
li
c
a
t
io
ns
.
A
m
ix
e
d
-
m
e
t
hods
a
pp
r
oa
c
h
w
a
s
e
m
p
lo
ye
d
t
o
e
va
lu
a
te
th
e
e
f
f
e
c
t
iv
e
ne
s
s
a
n
d
c
ha
ll
e
nge
s
o
f
A
I
-
ba
s
e
d
e
m
ot
io
n
r
e
c
og
ni
ti
o
n
i
n
m
e
n
ta
l
he
a
lt
h
a
pp
li
c
a
t
io
ns
.
Q
ua
n
ti
ta
t
iv
e
a
na
l
ys
is
a
s
s
e
s
s
e
d
m
ode
l
p
e
r
f
o
r
m
a
nc
e
h
ig
hl
ig
ht
i
ng
to
p
p
e
r
f
o
r
m
e
r
s
l
ik
e
E
f
f
ic
i
e
nt
N
e
t
-
X
G
B
o
os
t
a
nd
e
ns
e
m
bl
e
c
la
s
s
i
f
ie
r
s
ba
s
e
d
on
a
c
c
u
r
a
c
y,
p
r
e
c
is
i
on,
r
e
c
a
ll
,
a
nd
F
1
-
s
c
or
e
w
hi
le
qua
li
ta
t
iv
e
t
he
m
a
t
ic
a
na
l
ys
is
r
e
ve
a
le
d
c
r
i
ti
c
a
l
ba
r
r
ie
r
s
s
uc
h
a
s
s
oc
i
e
ta
l
s
ti
gm
a
,
p
r
iv
a
c
y
c
onc
e
r
ns
,
a
n
d
us
a
b
il
it
y
is
s
ue
s
.
T
he
in
te
g
r
a
ti
o
n
o
f
f
in
di
ngs
e
m
pha
s
iz
e
s
th
a
t
a
l
th
o
ug
h
e
m
o
ti
o
n
r
e
c
o
gni
ti
on
m
od
e
ls
s
h
ow
s
t
r
o
ng
te
c
h
no
lo
g
ic
a
l
po
te
n
ti
a
l
f
o
r
r
e
a
l
-
ti
m
e
,
pe
r
s
o
na
l
iz
e
d
m
e
n
ta
l
he
a
l
th
s
up
po
r
t
(
e
.
g.
,
v
ia
c
ha
tb
ot
s
o
r
vi
r
tu
a
l
th
e
r
a
p
is
ts
)
,
e
th
ic
a
l
,
c
ul
tu
r
a
l,
a
n
d
c
om
put
a
t
io
n
a
l
c
ha
ll
e
nge
s
m
us
t
be
a
dd
r
e
s
s
e
d
t
o
e
ns
u
r
e
e
f
f
e
c
t
iv
e
a
n
d
in
c
lu
s
i
ve
a
do
pt
io
n
in
r
e
a
l
-
w
o
r
ld
s
e
tt
in
gs
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
dv A
ppl
S
c
i
I
S
S
N
:
2252
-
8814
AI
-
dr
iv
e
n e
m
ot
io
n r
e
c
ogni
ti
on s
y
s
te
m
s
f
o
r
s
us
ta
in
abl
e
m
e
nt
al
he
al
th
c
ar
e
…
(
A
k
r
am
A
hm
ad
)
1115
F
ig
ur
e
2. M
ode
l
pe
r
f
or
m
a
nc
e
on dif
f
e
r
e
nt
m
e
tr
ic
s
F
ig
ur
e
3. D
a
ta
s
e
t
c
ont
r
ib
ut
io
n i
n e
m
ot
io
n r
e
c
ogni
ti
on
F
ig
ur
e
4. A
dopt
io
n r
a
te
vs
c
ha
ll
e
nge
s
ove
r
t
im
e
5.
C
O
N
C
L
U
S
I
O
N
E
m
ot
io
n
r
e
c
ogni
ti
on
te
c
hnol
ogi
e
s
a
r
e
tr
a
n
s
f
or
m
in
g
m
e
nt
a
l
he
a
lt
h
tr
e
a
tm
e
nt
by
pr
ovi
di
ng
in
di
vi
dua
li
z
e
d,
A
I
-
ba
s
e
d
in
te
r
ve
nt
io
ns
th
r
ough
vi
r
tu
a
l
th
e
r
a
pi
s
ts
,
a
da
pt
iv
e
pl
a
tf
or
m
s
,
a
nd
te
le
he
a
lt
h
s
ys
te
m
s
.
T
hr
ough
da
ta
s
e
ts
in
c
lu
di
ng
F
E
R
2013
(
30%
)
,
J
A
F
F
E
(
25
%
)
,
a
nd
C
K
+
(
20%
)
,
im
pr
ovi
ng
m
ode
l
pr
e
c
is
io
n
E
f
f
ic
ie
nt
N
e
t
-
X
G
B
oos
t
ove
r
90%
a
dopt
io
n
r
a
te
s
ha
ve
c
r
os
s
e
d
70%
a
s
of
2021,
in
di
c
a
ti
ng
a
dva
nc
e
m
e
nt
in
tr
a
ns
ve
r
s
in
g
e
th
ic
a
l
a
nd
te
c
hni
c
a
l
c
ha
ll
e
nge
s
.
E
ve
n
w
it
h
th
i
s
gr
ow
th
,
c
ha
ll
e
ng
e
s
s
uc
h
a
s
da
ta
pr
iv
a
c
y,
a
lg
or
it
hm
ic
bi
a
s
,
a
nd
li
m
it
e
d
da
ta
s
e
t
di
ve
r
s
it
y
ne
e
d
to
b
e
r
e
s
ol
ve
d
s
o
th
a
t
th
e
c
r
e
a
ti
on
of
de
p
e
nda
bl
e
,
a
c
c
e
s
s
ib
le
,
a
nd
s
c
a
la
bl
e
s
ol
ut
io
ns
is
pr
om
ot
e
d.
F
ut
ur
e
s
tu
di
e
s
m
us
t
ta
r
ge
t
e
th
ic
a
l
A
I
m
ode
ls
,
m
ul
ti
va
r
ia
te
da
ta
s
e
ts
,
e
ne
r
gy
-
opt
im
iz
e
d
m
ode
ls
,
a
nd
us
e
r
-
c
e
nt
e
r
e
d
de
s
ig
n
t
o
a
ugm
e
nt
th
e
s
c
a
la
bi
li
ty
a
nd
a
c
c
e
s
s
ib
il
it
y
of
e
m
ot
io
n
r
e
c
ogni
ti
on
in
m
e
nt
a
l
he
a
lt
h.
T
hi
s
r
e
s
e
a
r
c
h
a
c
knowle
dge
s
th
e
r
e
vol
ut
io
ni
z
in
g
pot
e
nt
ia
l
of
e
m
ot
io
n
r
e
c
ogni
ti
on by AI
f
or
de
ve
lo
pi
ng e
m
pa
th
e
ti
c
, a
c
c
e
s
s
ib
le
, a
nd e
f
f
e
c
ti
ve
m
e
nt
a
l
he
a
lt
h c
a
r
e
s
y
s
te
m
s
.
F
U
N
D
I
N
G
I
N
F
O
R
M
A
T
I
O
N
N
o f
undi
ng w
a
s
r
e
c
e
iv
e
d f
or
t
hi
s
w
or
k.
A
U
T
H
O
R
C
O
N
T
R
I
B
U
T
I
O
N
S
S
T
A
T
E
M
E
N
T
T
hi
s
jo
ur
na
l
us
e
s
th
e
C
ont
r
ib
ut
or
R
ol
e
s
T
a
xonomy
(
C
R
e
di
T
)
to
r
e
c
ogni
z
e
in
di
vi
dua
l
a
ut
hor
c
ont
r
ib
ut
io
ns
, r
e
duc
e
a
ut
hor
s
hi
p di
s
put
e
s
,
a
nd f
a
c
il
it
a
te
c
ol
la
bo
r
a
ti
on.
N
am
e
o
f
A
u
t
h
or
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
A
kr
a
m
A
hm
a
d
✓
✓
✓
✓
✓
✓
✓
✓
✓
V
a
is
ha
li
S
in
gh
✓
✓
✓
✓
✓
✓
✓
K
a
m
a
l
U
pr
e
ti
✓
✓
✓
✓
✓
✓
✓
✓
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8814
I
nt
J
A
dv A
ppl
S
c
i
,
V
ol
.
14
, N
o.
4
,
D
e
c
e
m
be
r
20
25
:
1111
-
1117
1116
C
:
C
onc
e
pt
ua
l
i
z
a
t
i
on
M
:
M
e
t
hodol
ogy
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
da
t
i
on
Fo
:
Fo
r
m
a
l
a
na
l
ys
i
s
I
:
I
nve
s
t
i
ga
t
i
on
R
:
R
e
s
our
c
e
s
D
:
D
a
t
a
C
ur
a
t
i
on
O
:
W
r
i
t
i
ng
-
O
r
i
gi
na
l
D
r
a
f
t
E
:
W
r
i
t
i
ng
-
R
e
vi
e
w
&
E
di
t
i
ng
Vi
:
Vi
s
ua
l
i
z
a
t
i
on
Su
:
Su
pe
r
vi
s
i
on
P
:
P
r
oj
e
c
t
a
dm
i
ni
s
t
r
a
t
i
on
Fu
:
Fu
ndi
ng a
c
qui
s
i
t
i
on
C
O
N
F
L
I
C
T
O
F
I
N
T
E
R
E
S
T
S
T
A
T
E
M
E
N
T
A
ut
hor
s
s
ta
te
no c
onf
li
c
t
of
i
nt
e
r
e
s
t.
D
A
T
A
A
V
A
I
L
A
B
I
L
I
T
Y
T
he
da
ta
th
a
t
s
uppor
t
th
e
f
in
di
ngs
of
th
is
s
tu
dy
a
r
e
a
va
il
a
bl
e
f
r
om
th
e
c
or
r
e
s
ponding
a
ut
hor
,
[
SSA
]
,
upon r
e
a
s
ona
bl
e
r
e
que
s
t.
R
E
F
E
R
E
N
C
E
S
[
1]
F
.
R
.
C
houdhr
y,
V
.
M
a
ni
,
L
.
C
.
M
i
ng,
T
.
M
.
K
ha
n
,
“
B
e
l
i
e
f
s
a
nd
pe
r
c
e
pt
i
on
a
bout
m
e
nt
a
l
he
a
l
t
h
i
s
s
ue
s
:
a
m
e
t
a
-
s
ynt
he
s
i
s
,”
N
e
ur
ops
y
c
hi
at
r
i
c
D
i
s
e
as
e
and T
r
e
at
m
e
nt
,
v
ol
.
12
, pp. 2807
-
2818,
2016
, doi
:
10.2147/
N
D
T
.S
111543
.
[
2]
C
.
E
.
G
oul
d,
F
.
M
a
,
J
.
R
.
L
oup,
C
.
J
ua
ng,
E
.
Y
.
S
a
ka
i
,
a
nd
R
.
P
e
pi
n,
“
T
e
c
hnol
ogy
-
ba
s
e
d
m
e
nt
a
l
he
a
l
t
h
a
s
s
e
s
s
m
e
nt
a
n
d
i
nt
e
r
ve
nt
i
on,”
i
n
H
andbook
of
M
e
nt
al
H
e
al
t
h
and
A
gi
ng
(
T
hi
r
d
E
d
i
t
i
on)
,
A
c
a
de
m
i
c
P
r
e
s
s
,
pp.
401
–
415
,
2020,
doi
:
10.1016/
b978
-
0
-
12
-
800136
-
3.00024
-
7.
[
3]
R
.
F
.
B
a
um
e
i
s
t
e
r
,
E
.
B
r
a
t
s
l
a
vs
ky,
C
.
F
i
nke
na
ue
r
,
a
nd
K
.
D
.
V
ohs
,
“
B
a
d
i
s
s
t
r
onge
r
t
ha
n
good,”
R
e
v
i
e
w
of
G
e
ne
r
al
P
s
y
c
hol
ogy
,
vol
. 5, no. 4, pp. 323
–
370, D
e
c
. 2001, doi
:
10.1037/
1089
-
2680.5.4.323.
[
4]
W
.
K
a
ng,
F
.
S
t
e
f
f
e
ns
,
S
.
P
i
ne
da
,
K
.
W
i
duc
h,
a
nd
A
.
M
a
l
va
s
o,
“
P
e
r
s
ona
l
i
t
y
t
r
a
i
t
s
a
nd
di
m
e
ns
i
ons
of
m
e
nt
a
l
he
a
l
t
h,”
Sc
i
e
nt
i
f
i
c
R
e
por
t
s
,
vol
. 13, no. 1, M
a
y 2023, doi
:
10.1038/
s
41598
-
023
-
33996
-
1.
[
5]
S
.
H
a
m
doun,
R
.
M
ont
e
l
e
one
,
T
.
B
ookm
a
n,
a
nd
K
.
M
i
c
h
a
e
l
,
“
A
I
-
ba
s
e
d
a
nd
di
gi
t
a
l
m
e
nt
a
l
he
a
l
t
h
a
pps
:
ba
l
a
nc
i
ng
ne
e
d
a
nd
r
i
s
k,
”
I
E
E
E
T
e
c
hnol
ogy
and Soc
i
e
t
y
M
agaz
i
ne
, vol
. 42, no. 1, pp. 25
–
36, M
a
r
. 2023, doi
:
10.1109/
m
t
s
.2023.3241309.
[
6]
B
.
K
.
W
i
e
d
e
r
hol
d,
“
C
onne
c
t
i
ng
t
hr
ough
t
e
c
hnol
ogy
dur
i
ng
t
he
c
or
ona
vi
r
us
di
s
e
a
s
e
2019
pa
nd
e
m
i
c
:
a
voi
di
ng
‘
Z
oom
F
a
t
i
gue
’
,
”
C
y
be
r
p
s
y
c
hol
ogy
B
e
hav
i
or
and So
c
i
al
N
e
t
w
o
r
k
i
ng
, vol
. 23, no. 7, pp. 437
–
438,
J
un. 2020, doi
:
10.1089/
c
ybe
r
.2020.29188.bkw
.
[
7]
E
.
G
.
K
r
um
hube
r
,
L
.
I
.
S
kor
a
,
H
.
C
.
H
.
H
i
l
l
,
a
nd
K
.
L
a
nde
r
,
“
T
he
r
ol
e
of
f
a
c
i
a
l
m
ove
m
e
nt
s
i
n
e
m
ot
i
on
r
e
c
ogni
t
i
on,”
N
at
ur
e
R
e
v
i
e
w
s
P
s
y
c
hol
ogy
, vol
. 2, no. 5, pp. 283
–
296,
M
a
r
. 2023, doi
:
10.1038/
s
4415
9
-
023
-
00172
-
1.
[
8]
A
.
M
oi
n,
F
.
A
a
d
i
l
,
Z
.
A
l
i
,
a
nd
D
.
K
a
ng
,
“
E
m
ot
i
on
r
e
c
ogn
i
t
i
o
n
f
r
a
m
e
w
or
k us
i
ng
m
ul
t
i
pl
e
m
o
da
l
i
t
i
e
s
f
o
r
a
n
e
f
f
e
c
t
i
ve
h
um
a
n
–
c
om
pu
t
e
r
i
nt
e
r
a
c
t
i
o
n,”
T
he
J
our
nal
o
f
Sup
e
r
c
om
pu
t
i
ng
,
v
ol
. 7
9,
no
.
8,
pp
. 9
32
0
–
9
34
9,
J
a
n.
202
3,
do
i
:
10
.1
007
/
s
1
122
7
-
02
2
-
05
02
6
-
w.
[
9]
S.
-
M
.
P
a
r
k
a
nd
Y
.
-
G
.
K
i
m
,
“
A
m
e
t
a
ve
r
s
e
:
t
a
xonom
y,
c
om
pone
nt
s
,
a
ppl
i
c
a
t
i
ons
,
a
nd
ope
n
c
ha
l
l
e
nge
s
,”
I
E
E
E
A
c
c
e
s
s
,
vol
.
10,
pp. 4209
–
4251, J
a
n. 2022, doi
:
10.1109/
a
c
c
e
s
s
.2021.3140175.
[
10]
J
.
W
i
r
t
z
e
t
al
.
,
“
B
r
a
ve
ne
w
w
or
l
d:
s
e
r
vi
c
e
r
obot
s
i
n
t
he
f
r
ont
l
i
ne
,”
J
our
nal
of
Se
r
v
i
c
e
M
anage
m
e
nt
,
vol
.
29,
no.
5,
pp.
907
–
931
,
S
e
p. 2018, doi
:
10.1108/
j
os
m
-
04
-
2018
-
0119.
[
11]
P
.
N
a
ga
,
S
.
D
.
M
a
r
r
i
,
a
nd
R
.
B
or
r
e
o,
“
F
a
c
i
a
l
e
m
ot
i
on
r
e
c
ogni
t
i
on
m
e
t
hods
,
da
t
a
s
e
t
s
a
nd
t
e
c
hnol
ogi
e
s
:
a
l
i
t
e
r
a
t
ur
e
s
ur
ve
y,
”
M
at
e
r
i
al
s
T
oday
P
r
oc
e
e
di
ngs
, vol
. 80, pp. 2824
–
2828, J
ul
. 2021, doi
:
10.1016/
j
.m
a
t
pr
.2021.07.046.
[
12]
Z.
-
Y
.
H
ua
ng
e
t
al
.,
“
A
s
t
udy
on
c
om
put
e
r
vi
s
i
on
f
or
f
a
c
i
a
l
e
m
ot
i
on
r
e
c
ogni
t
i
on,”
Sc
i
e
nt
i
f
i
c
R
e
por
t
s
,
vol
.
13,
no.
1,
M
a
y
2023
,
doi
:
10.1038/
s
41598
-
023
-
35446
-
4.
[
1
3]
S
.
V
i
g
ne
s
h,
M
.
S
a
vi
t
ha
de
vi
,
M
.
S
r
i
de
vi
,
a
nd
R
.
S
r
i
d
ha
r
,
“
A
no
ve
l
f
a
c
i
a
l
e
m
o
t
i
o
n
r
e
c
o
g
ni
t
i
o
n
m
o
de
l
us
i
ng
s
e
g
m
e
n
t
a
t
i
o
n
V
G
G
-
19
a
r
c
h
i
t
e
c
t
u
r
e
,”
I
n
t
e
r
n
at
i
on
a
l
J
o
ur
na
l
o
f
I
n
f
or
m
at
i
on
T
e
c
h
no
l
o
gy
,
v
o
l
.
1
5
,
no
.
4
,
p
p.
17
7
7
–
1
78
7,
20
23
,
d
o
i
:
1
0
.1
00
7
/
s
4
1
87
0
-
023
-
0
11
8
4
-
z.
[
14]
T
.
F
ong,
I
.
N
ou
r
ba
khs
h,
a
nd
K
.
D
a
ut
e
nha
hn,
“
A
s
ur
ve
y
of
s
oc
i
a
l
l
y
i
nt
e
r
a
c
t
i
ve
r
obot
s
,”
R
obot
i
c
s
and
A
ut
onom
ous
Sy
s
t
e
m
s
,
vol
. 42, no. 3
–
4, pp. 143
–
166, F
e
b. 2003, doi
:
10.1016/
s
0921
-
8890(
02)
00372
-
x.
[
15]
W
.
M
e
l
l
ouk
a
nd
W
.
H
a
ndouz
i
,
“
F
a
c
i
a
l
e
m
ot
i
on
r
e
c
ogni
t
i
on
us
i
ng
de
e
p
l
e
a
r
ni
ng:
r
e
vi
e
w
a
nd
i
ns
i
ght
s
,”
P
r
oc
e
di
a
C
om
put
e
r
Sc
i
e
nc
e
, vol
. 175, pp. 689
–
694, J
a
n. 2020, doi
:
10.1016/
j
.pr
oc
s
.2020.07.101.
[
16]
M
.
M
ukhi
ddi
nov,
O
.
D
j
ur
a
e
v,
F
.
A
khm
e
dov,
A
.
M
ukh
a
m
a
di
ye
v,
a
nd
J
.
C
ho,
“
M
a
s
k
e
d
f
a
c
e
e
m
ot
i
on
r
e
c
ogni
t
i
on
ba
s
e
d
on
f
a
c
i
a
l
l
a
ndm
a
r
ks
a
nd de
e
p l
e
a
r
ni
ng a
ppr
oa
c
he
s
f
or
vi
s
ua
l
l
y i
m
pa
i
r
e
d pe
opl
e
,”
Se
ns
o
r
s
, vol
. 23, no. 3, 2023, doi
:
10.3390/
s
23031080.
[
17]
N
.
M
e
he
nda
l
e
,
“
F
a
c
i
a
l
e
m
ot
i
on
r
e
c
ogni
t
i
on
us
i
ng
c
onvol
ut
i
ona
l
ne
ur
a
l
ne
t
w
or
ks
(
F
E
R
C
)
,”
SN
A
ppl
i
e
d
Sc
i
e
nc
e
s
,
vol
.
2,
no.
3,
F
e
b. 2020, doi
:
10.1007/
s
42452
-
020
-
2234
-
1.
[
18]
S
.
B
.
P
unur
i
e
t
al
.,
“
E
f
f
i
c
i
e
nt
N
e
t
-
X
G
B
O
O
S
T
:
a
n
i
m
pl
e
m
e
nt
a
t
i
on
f
o
r
f
a
c
i
a
l
e
m
ot
i
on
r
e
c
ogni
t
i
on
us
i
ng
t
r
a
ns
f
e
r
l
e
a
r
ni
ng,”
M
at
he
m
at
i
c
s
, vol
. 11, no. 3, F
e
b. 2023, doi
:
10.3390/
m
a
t
h11030776.
[
19]
D
.
K
.
J
a
i
n,
A
.
K
.
D
ut
t
a
,
E
.
V
e
r
dú,
S
.
A
l
s
uba
i
,
a
nd
A
.
R
.
W
.
S
a
i
t
,
“
A
n
a
ut
o
m
a
t
e
d
hype
r
pa
r
a
m
e
t
e
r
t
une
d
de
e
p
l
e
a
r
ni
ng
m
ode
l
e
na
bl
e
d
f
a
c
i
a
l
e
m
ot
i
on
r
e
c
ogni
t
i
on
f
or
a
ut
onom
ous
ve
hi
c
l
e
dr
i
ve
r
s
,”
I
m
ag
e
and
V
i
s
i
on
C
om
put
i
ng
,
vol
.
133,
M
a
r
.
2023,
doi
:
10.1016/
j
.i
m
a
vi
s
.2023.104659.
[
20]
H
.
M
.
S
ha
hz
a
d,
S
.
M
.
B
ha
t
t
i
,
A
.
J
a
f
f
a
r
,
S
.
A
kr
a
m
,
M
.
A
l
ha
j
l
a
h,
a
nd
A
.
M
a
hm
ood,
“
H
ybr
i
d
f
a
c
i
a
l
e
m
ot
i
on
r
e
c
ogni
t
i
on
us
i
ng
C
N
N
-
B
a
s
e
d f
e
a
t
ur
e
s
,”
A
ppl
i
e
d Sc
i
e
nc
e
s
, vol
. 13, no. 9, A
pr
. 2023, doi
:
10.3390/
a
pp13095572.
[
21]
S
.
G
.
T
e
s
f
a
ge
r
gi
s
h,
J
.
K
.
-
D
z
i
ki
e
n
ė
,
a
nd
R
.
D
a
m
a
š
e
vi
č
i
us
,
“
Z
e
r
o
-
s
hot
e
m
ot
i
on
de
t
e
c
t
i
on
f
or
s
e
m
i
-
s
upe
r
vi
s
e
d
s
e
nt
i
m
e
nt
a
na
l
y
s
i
s
us
i
ng
s
e
nt
e
nc
e
t
r
a
ns
f
or
m
e
r
s
a
nd
e
ns
e
m
bl
e
l
e
a
r
ni
ng,”
A
ppl
i
e
d
Sc
i
e
nc
e
s
,
vol
.
12,
no.
17,
A
ug.
2022,
doi
:
10.3390/
a
pp12178662.
[
22]
M
.
R
.
‐
F
i
s
h,
“
B
odyt
i
m
e
:
on
t
he
i
nt
e
r
a
c
t
i
on
of
body,
i
de
nt
i
t
y,
a
nd
s
oc
i
e
t
y,”
A
m
e
r
i
c
an
E
t
hnol
ogi
s
t
,
vol
.
25,
no.
1,
pp.
19
–
20,
F
e
b. 1998, doi
:
10.1525/
a
e
.1998.25.1.19.
[
23]
G
.
G
i
a
nna
ka
ki
s
,
D
.
G
r
i
gor
i
a
di
s
,
K
.
G
i
a
nna
ka
ki
,
O
.
S
i
m
a
nt
i
r
a
ki
,
A
.
R
oni
ot
i
s
,
a
nd
M
.
T
s
i
kna
ki
s
,
“
R
e
vi
e
w
on
p
s
yc
hol
ogi
c
a
l
s
t
r
e
s
s
de
t
e
c
t
i
on
us
i
ng
bi
os
i
gna
l
s
,”
I
E
E
E
T
r
ans
ac
t
i
ons
on
A
f
f
e
c
t
i
v
e
C
om
put
i
ng
,
vol
.
13,
no.
1,
pp.
440
–
460,
J
ul
.
2019,
doi
:
10.1109/
t
a
f
f
c
.2019.2927337.
[
24]
K
.
W
a
ng,
N
.
A
n,
B
.
N
.
L
i
,
Y
.
Z
ha
ng,
a
nd
L
.
L
i
,
“
S
pe
e
c
h
e
m
ot
i
on
r
e
c
ogni
t
i
on
us
i
ng
F
our
i
e
r
pa
r
a
m
e
t
e
r
s
,”
I
E
E
E
T
r
ans
ac
t
i
ons
on
A
f
f
e
c
t
i
v
e
C
om
put
i
ng
, vol
. 6, no. 1, pp. 69
–
75, J
a
n. 2015, doi
:
10.1109/
t
a
f
f
c
.201
5.2392101.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
dv A
ppl
S
c
i
I
S
S
N
:
2252
-
8814
AI
-
dr
iv
e
n e
m
ot
io
n r
e
c
ogni
ti
on s
y
s
te
m
s
f
o
r
s
us
ta
in
abl
e
m
e
nt
al
he
al
th
c
ar
e
…
(
A
k
r
am
A
hm
ad
)
1117
[
25]
S
.
P
e
ng
e
t
al
.,
“
A
s
ur
ve
y
on
de
e
p
l
e
a
r
ni
ng
f
or
t
e
xt
ua
l
e
m
ot
i
on
a
na
l
ys
i
s
i
n
s
oc
i
a
l
ne
t
w
or
ks
,”
D
i
gi
t
al
C
om
m
uni
c
at
i
ons
an
d
N
e
t
w
or
k
s
, vol
. 8, no. 5, pp. 745
–
762, O
c
t
. 2021, doi
:
10.1016/
j
.dc
a
n.2021.10.0
03.
[
26]
V
.
G
upt
a
e
t
al
.
,
“
A
n
e
m
ot
i
on
c
a
r
e
m
ode
l
us
i
ng
m
ul
t
i
m
oda
l
t
e
xt
ua
l
a
na
l
y
s
i
s
on
C
O
V
I
D
-
19,”
C
haos
Sol
i
t
ons
&
F
r
ac
t
al
s
,
vol
.
144,
J
a
n. 2021, doi
:
10.1016/
j
.c
ha
os
.2021.110708.
[
27]
J
.
D
e
ng
a
nd
F
.
R
e
n,
“
A
s
ur
ve
y
of
t
e
xt
ua
l
e
m
ot
i
on
r
e
c
ogni
t
i
on
a
nd
i
t
s
c
ha
l
l
e
n
ge
s
,”
I
E
E
E
T
r
ans
ac
t
i
ons
on
A
f
f
e
c
t
i
v
e
C
om
put
i
ng
,
vol
. 14, no. 1, pp. 49
–
67, J
a
n. 2021, doi
:
10.1109/
t
a
f
f
c
.2021.3053275.
[
28]
S
.
S
a
ga
now
s
ki
,
B
.
P
e
r
z
,
A
.
G
.
P
ol
a
k,
a
nd
P
.
K
a
z
i
e
nko,
“
E
m
ot
i
on
r
e
c
ogni
t
i
on
f
or
e
ve
r
yda
y
l
i
f
e
us
i
ng
phys
i
ol
ogi
c
a
l
s
i
gn
a
l
s
f
r
om
w
e
a
r
a
bl
e
s
:
a
s
ys
t
e
m
a
t
i
c
l
i
t
e
r
a
t
ur
e
r
e
v
i
e
w
,”
I
E
E
E
T
r
ans
ac
t
i
ons
on
A
f
f
e
c
t
i
v
e
C
o
m
put
i
ng
,
vol
.
14,
no.
3,
pp.
1876
–
1897,
M
a
y
2022,
doi
:
10.1109/
t
a
f
f
c
.2022.3176135.
[
29]
M
.
R
a
got
,
N
.
M
a
r
t
i
n,
S
.
E
m
,
N
.
P
a
l
l
a
m
i
n,
a
nd
J
.
-
M
.
D
i
ve
r
r
e
z
,
“
E
m
ot
i
on
r
e
c
o
gni
t
i
on
us
i
ng
phys
i
ol
ogi
c
a
l
s
i
gna
l
s
:
l
a
bor
a
t
or
y
vs
.
w
e
a
r
a
bl
e
s
e
n
s
or
s
,”
i
n
A
dv
anc
e
s
i
n i
nt
e
l
l
i
ge
nt
s
y
s
t
e
m
s
and c
om
put
i
ng
, 2017, pp.
15
–
22
, doi
:
10.1007/
978
-
3
-
319
-
60639
-
2_2.
[
30]
C
. H
e
, Y
.
-
J
. Y
a
o, a
nd
X
.
-
S
. Y
e
, “
A
n
e
m
ot
i
on r
e
c
ogni
t
i
on s
y
s
t
e
m
ba
s
e
d on phy
s
i
ol
ogi
c
a
l
s
i
gna
l
s
obt
a
i
n
e
d by w
e
a
r
a
bl
e
s
e
ns
or
s
,”
i
n
W
e
ar
abl
e
Se
ns
o
r
s
and R
obot
s
, 2016, pp. 15
–
25
, doi
:
10.1007/
978
-
981
-
10
-
2404
-
7_2.
[
31]
S
.
P
.
S
r
e
e
ni
l
a
ya
m
,
I
.
U
.
A
ha
d,
V
.
N
i
c
ol
os
i
,
V
.
A
.
G
a
r
z
on,
a
nd
D
.
B
r
a
ba
z
on,
“
A
dva
nc
e
d
m
a
t
e
r
i
a
l
s
of
pr
i
nt
e
d
w
e
a
r
a
bl
e
s
f
or
phys
i
ol
ogi
c
a
l
pa
r
a
m
e
t
e
r
m
oni
t
or
i
ng,”
M
at
e
r
i
al
s
T
oday
, vol
. 32, pp. 147
–
177, S
e
p. 2019, doi
:
10.1016/
j
.m
a
t
t
od.2019.08.005.
[
32]
M
.
Z
a
ne
t
t
i
e
t
al
.
,
“
A
s
s
e
s
s
m
e
nt
of
m
e
nt
a
l
s
t
r
e
s
s
t
hr
ough
t
he
a
na
l
ys
i
s
of
phy
s
i
ol
ogi
c
a
l
s
i
gna
l
s
a
c
qui
r
e
d
f
r
om
w
e
a
r
a
bl
e
de
vi
c
e
s
,”
i
n
A
m
bi
e
nt
A
s
s
i
s
t
e
d L
i
v
i
ng
,
pp. 243
–
256
,
2019,
doi
:
10.1007/
978
-
3
-
030
-
05921
-
7_
20.
B
I
O
G
R
A
P
H
I
E
S
O
F
A
U
T
H
O
R
S
Akram
Ahmad
is
a
dedicated
Research
Scholar
in
the
Departmen
t
of
Computer
Scienc
e
at
Mahar
ishi
Univer
sity
of
Infor
m
ation
Techn
ology,
Luckno
w.
His
acad
emic
pursuits
and
research
endeavors
aim
to
advance
knowledge
in
computer
s
cie
nce
and
its
applications.
With
a
passion
for
innovation
and
a
commitment
to
addressing
complex
challenges,
he
actively
engages
in
scholarly
activit
ies,
explorin
g
cutting
-
edg
e
soluti
ons
and
contributing
to
technologic
al
advance
ments.
His
work
reflects
a
deep
interest
in
fostering
progress
and
collaborat
ion
within
the
academic
and
research
communi
ty,
making
significant
strides
in
his
chosen fi
eld of s
tudy
. He can be contac
ted at email: akram.ahmad2009@gmail.com.
Vaishali
Singh
is
working
as
an
Associate
Professor
with
the
Ma
harishi
School
of
Engineering
and
Technology
at
Maharishi
University
of
Inform
ation
Technology,
Uttar
Prade
sh, Ind
ia. He
r ac
ademic
and
rese
arch
focu
s inclu
des a
wide
rang
e of
contem
porar
y topic
s
such
as
convolut
ional
neural
networks,
scalable
wireless
networks,
W
i
-
F
i
networks,
cloud
computi
ng,
artificial
intell
igence,
artificial
neural
networks,
recurre
nt
neural
networks,
and
public
key
systems
.
She
also
explores
applications
in
business
and
technology
innovation.
With
expertise
in
these
areas,
she
contribu
tes
to
advancin
g
kno
wledge
and
developing
innovative
solutions
to
address
complex
challenge
s
in
engine
ering,
technology,
and
interdisciplina
ry fields.
She ca
n be c
ontact
ed at
email:
vaisha
li05@gmail.com.
Dr.
Kamal
Upreti
is
currently
working
as
an
Associate
Pr
ofessor
in
the
Department
of
Computer
Science,
CHRIST
(Deemed
to
be
U
niversity),
Delhi
NCR,
Ghaziabad,
India.
He
completed
h
is
B.
Tech
(Hons)
Degree
from
UPTU,
M.
Tech
(Gold
Medalist),
PGDM
(Executive)
from
IMT
Ghaziabad
,
and
Ph
.
D
.
in
the
Department
of
Computer
Science
and
Engineering.
He
has
completed
a
Postdoc
from
National
Taipei
University
of
Business,
TAIWAN
,
funded
by
MHRD.
He
is
coming
in
2%
of
Top
Scientist
awarded
by
Stanford
Universi
ty,
Californ
ia
,
in
the
year
2024.
He
ha
s
published
50+
patents
,
45+
books
,
32+
magazine
issues
,
and
170+
research
papers
in
vario
us
reputed
journals
and
internationa
l
confere
nces
.
His
areas
of
interest
such
artificia
l
intellig
ence,
machine
learning,
data
analytics
,
cyber
security
,
machine
learning,
health
care,
embed
ded
system
s,
and
cloud
computi
ng
.
He
has
published
more
than
45+
authored
and
edited
boo
ks
under
CRC
Press,
IGI
Global,
Oxford
Press
,
and
Arihant
Publication.
He
is
the
main
gu
est
editor
of
more
than
10
special
issues
of
journals
,
including
Springer
, T
aylor
and
Francis,
I
nderscie
nce,
IGI
Global,
and
Elsevier
.
He
is
the
main
guest
associate
editor
in
Frontier
J
ournal
Conver
gence
of
Artificial
Intelligence
and
Cognitive
Systems
,
whi
ch
is
SCIE
and
SC
OPUS
,
having
an
impac
t
factor:
3.0
and
cite
score:
6.1.
He
has
years’
experience
in
corporate
and
teaching
experience
in Engineer
ing Colleges.
He can be contacted at email:
kamalupreti1989@
gmail.com.
Evaluation Warning : The document was created with Spire.PDF for Python.