I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
37
,
No
.
2
,
Feb
r
u
ar
y
20
25
,
p
p
.
959
~
967
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
37.
i
2
.
p
p
959
-
9
6
7
959
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
A nov
el CN
N
-
A
N
N f
usio
n app
ro
a
c
h f
o
r imp
ro
v
ed f
a
cia
l
emo
tion dete
ction
Vira
j
Sa
wa
nt
1
,
H
us
na
Sh
a
ik
h
1
,
B
ha
k
t
i P
a
lk
a
r
2
,
Sa
na
m
K
a
zi
3
,
Wa
s
im
J
a
s
a
ni
1
,
L
a
m
iy
a
Ra
m
pu
ra
wa
la
1
,
M
o
ha
m
m
ed
Na
s
er
Sh
a
ik
h
1
1
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
Te
c
h
n
o
l
o
g
y
,
M
.
H
.
S
a
b
o
o
S
i
d
d
i
k
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
,
M
u
m
b
a
i
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
,
K
.
J.
S
o
m
a
i
y
a
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
,
M
u
mb
a
i
,
I
n
d
i
a
3
D
e
p
a
r
t
me
n
t
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
B
h
a
r
a
t
i
V
i
d
y
a
p
e
e
t
h
D
e
e
m
e
d
t
o
b
e
U
n
i
v
e
r
s
i
t
y
,
N
a
v
i
M
u
m
b
a
i
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
20
,
2
0
2
4
R
ev
is
ed
Sep
15
,
2
0
2
4
Acc
ep
ted
Sep
29
,
2
0
2
4
In
re
c
e
n
t
y
e
a
rs,
th
e
field
o
f
e
m
o
t
io
n
re
c
o
g
n
it
i
o
n
h
a
s
witn
e
ss
e
d
a
n
in
c
re
a
se
d
in
tere
st
d
u
e
t
o
th
e
rise
o
f
d
e
e
p
lea
rn
in
g
tec
h
n
i
q
u
e
s.
Ho
we
v
e
r,
o
n
e
o
f
th
e
p
e
rsiste
n
t
d
iffi
c
u
lt
ies
in
th
is
d
o
m
a
in
,
wh
ich
we
h
a
v
e
a
tt
e
m
p
ted
to
a
d
d
re
ss
,
is
th
e
v
a
riab
il
it
y
in
ima
g
e
s
ize
s
u
ti
li
z
e
d
.
In
th
is
stu
d
y
,
we
h
a
v
e
re
v
iew
e
d
th
e
wo
rk
b
y
d
iffere
n
t
re
se
a
rc
h
e
rs
a
n
d
su
m
m
a
rize
d
th
e
ir
k
e
y
fi
n
d
i
n
g
s.
I
n
o
u
r
re
se
a
rc
h
,
we
in
tro
d
u
c
e
a
n
o
v
e
l
tec
h
n
iq
u
e
th
a
t
i
n
teg
ra
tes
th
e
stre
n
g
th
s
o
f
1
D
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
two
r
k
s
(
CNN
s
)
a
n
d
a
rti
ficia
l
n
e
u
ra
l
n
e
two
rk
s
(
ANNs
)
th
ro
u
g
h
a
late
fu
sio
n
m
o
d
e
l,
lev
e
ra
g
i
n
g
CNN
s'
sh
a
re
d
we
ig
h
ts
a
n
d
a
u
to
m
a
ti
c
fe
a
tu
re
lea
rn
in
g
fo
r
s
p
a
ti
a
l
a
n
d
tem
p
o
ra
l
d
a
ta,
a
lo
n
g
si
d
e
AN
N'
s
c
o
m
p
re
h
e
n
siv
e
fe
a
tu
re
c
o
n
si
d
e
ra
ti
o
n
.
Ou
r
re
se
a
rc
h
fin
d
i
n
g
s
h
i
g
h
li
g
h
t
t
h
e
e
ffe
c
ti
v
e
n
e
ss
o
f
t
h
is
a
p
p
ro
a
c
h
,
wh
ich
a
c
h
iev
e
s
a
re
m
a
rk
a
b
le
a
c
c
u
ra
c
y
o
f
9
2
.
4
2
%
,
a
l
o
n
g
with
o
t
h
e
r
e
v
a
lu
a
ti
o
n
m
e
tri
c
s
d
e
m
o
n
stra
ti
n
g
n
o
tab
le
re
su
lt
s.
F
u
rth
e
rm
o
re
,
we
c
o
n
d
u
c
t
a
c
o
m
p
re
h
e
n
siv
e
a
n
a
ly
sis
o
f
t
h
e
p
r
o
p
o
se
d
m
e
th
o
d
,
c
o
m
p
a
rin
g
it
wi
th
a
d
v
a
n
c
e
d
m
e
th
o
d
s
in
t
h
e
fiel
d
o
f
fa
c
ial
e
m
o
ti
o
n
re
c
o
g
n
it
i
o
n
.
Th
r
o
u
g
h
th
is
c
o
m
p
a
ra
ti
v
e
a
n
a
ly
sis,
we
d
e
m
o
n
stra
te
th
e
su
p
e
rio
ri
ty
o
f
o
u
r
p
r
o
p
o
se
d
a
p
p
r
o
a
c
h
,
a
d
d
re
ss
in
g
c
h
a
ll
e
n
g
e
s
t
h
a
t
h
a
v
e
n
o
t
y
e
t
b
e
e
n
a
d
d
re
ss
e
d
ti
ll
d
a
te,
t
h
u
s
l
e
a
d
in
g
t
o
p
ro
g
re
ss
in
t
h
is f
iel
d
.
K
ey
w
o
r
d
s
:
Dee
p
lear
n
in
g
E
m
o
tio
n
class
if
icatio
n
Facial
em
o
tio
n
r
ec
o
g
n
itio
n
L
ate
f
u
s
io
n
d
ee
p
lear
n
in
g
Ma
ch
in
e
lear
n
in
g
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Hu
s
n
a
Sh
aik
h
D
e
p
ar
t
m
e
nt
of
I
nf
o
r
m
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
M.
H.
S
a
b
o
o
S
i
dd
i
k
C
ol
l
eg
e
of
E
n
gi
n
e
er
i
n
g
M
u
m
b
ai
–
4
00
0
08
,
M
a
h
a
r
a
s
ht
r
a,
I
n
di
a
E
m
ail:
h
u
s
n
as2
9
3
3
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
g
r
o
wth
o
f
ar
tific
ial
in
tellig
en
ce
m
ak
es
em
o
tio
n
al
in
tellig
en
ce
an
ar
ea
w
h
ich
is
b
ein
g
p
aid
m
o
r
e
an
d
m
o
r
e
atten
tio
n
t
o
r
ec
e
n
tly
.
T
h
is
wo
u
ld
aim
to
o
b
tain
an
in
ter
ac
tio
n
b
etwe
en
h
u
m
a
n
s
an
d
co
m
p
u
ter
s
wh
ich
ar
e
s
im
ilar
to
th
o
s
e
b
et
wee
n
p
eo
p
le.
Ho
wev
e
r
,
t
h
i
s
r
eq
u
ir
es
m
ac
h
i
n
es
to
u
n
d
er
s
tan
d
h
u
m
an
em
o
tio
n
s
,
an
d
f
ac
ial
em
o
tio
n
d
etec
tio
n
s
er
v
es
as
a
m
eth
o
d
to
r
ea
ch
th
e
g
o
al
[
1
]
.
I
n
ter
p
r
etin
g
f
ac
i
al
ex
p
r
ess
io
n
s
an
d
em
o
tio
n
s
is
s
ee
n
as a
cr
u
cial
s
tep
f
o
r
cr
ea
tin
g
m
o
r
e
n
atu
r
al
in
ter
ac
tio
n
s
b
etwe
en
h
u
m
an
s
an
d
m
ac
h
in
es.
E
m
o
tio
n
s
ca
n
b
e
c
o
n
s
id
er
ed
a
s
a
co
m
p
lex
p
h
en
o
m
e
n
o
n
o
f
a
s
u
b
ject'
s
s
en
s
i
tiv
ity
in
r
elatio
n
to
th
eir
en
v
ir
o
n
m
en
t
an
d
s
p
ec
if
ic
p
o
in
ts
o
f
ad
ap
tatio
n
,
b
ein
g
a
m
ix
tu
r
e
o
f
b
e
h
av
io
u
r
al,
p
h
y
s
io
lo
g
i
ca
l,
an
d
ex
p
r
ess
iv
e
elem
en
ts
,
f
ee
lin
g
s
,
an
d
n
er
v
o
u
s
s
y
s
tem
r
esp
o
n
s
es
ap
p
ea
r
in
g
au
to
m
atica
lly
an
d
b
ein
g
,
p
ar
tly
in
f
lu
en
ce
d
b
y
cu
ltu
r
al
f
ac
to
r
s
[
2
]
.
E
m
o
tio
n
s
p
lay
a
p
iv
o
tal
r
o
le
in
v
ar
i
o
u
s
f
ac
ets
o
f
h
u
m
an
life
,
in
cl
u
d
in
g
in
ter
p
er
s
o
n
al
r
elatio
n
s
h
ip
s
,
co
g
n
itiv
e
p
r
o
ce
s
s
es,
p
er
ce
p
tio
n
,
an
d
o
v
e
r
all
well
-
b
ein
g
[
3
]
.
T
h
e
n
ee
d
t
o
d
etec
t
an
in
d
iv
id
u
al’
s
em
o
tio
n
s
h
as
b
ec
o
m
e
i
n
cr
ea
s
in
g
ly
im
p
o
r
tan
t
f
o
r
m
an
y
r
ea
s
o
n
s
.
T
h
is
s
tem
s
f
r
o
m
th
e
f
ac
t
th
at
em
o
tio
n
s
s
er
v
e
as
in
teg
r
al
co
m
p
o
n
e
n
ts
o
f
s
o
cial
in
ter
ac
tio
n
.
Acc
o
r
d
in
g
to
r
esear
ch
[
4
]
,
o
n
ly
7
%
o
f
h
u
m
an
co
m
m
u
n
icatio
n
r
elies
o
n
lan
g
u
ag
e,
wh
ile
3
8
%
is
co
n
v
ey
e
d
th
r
o
u
g
h
p
ar
alan
g
u
ag
e,
an
d
a
s
ig
n
if
ican
t
m
ajo
r
ity
,
5
5
%,
is
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
37
,
No
.
2
,
Feb
r
u
a
r
y
20
25
:
9
5
9
-
9
6
7
960
co
m
m
u
n
icate
d
th
r
o
u
g
h
f
ac
ial
ex
p
r
ess
io
n
s
.
W
h
ile
em
o
tio
n
s
ca
n
b
e
r
ec
o
g
n
ized
th
r
o
u
g
h
E
E
G,
s
p
ee
c
h
o
r
tex
t
[
5
]
,
f
ac
ial
e
x
p
r
ess
io
n
s
er
v
es
as
a
f
u
n
d
am
e
n
tal
an
d
d
is
tin
ctiv
e
m
eth
o
d
b
y
wh
ic
h
h
u
m
an
s
co
m
m
u
n
icate
th
eir
em
o
tio
n
al
s
tates
an
d
in
ten
tio
n
s
,
s
u
r
p
ass
in
g
cu
ltu
r
al
an
d
lin
g
u
i
s
tic
b
o
u
n
d
ar
ies
[
6
]
.
W
ith
th
e
ad
v
en
t
o
f
m
ac
h
in
e
lear
n
in
g
an
d
its
co
n
tin
u
o
u
s
d
ev
elo
p
m
e
n
t,
f
ac
ial
ex
p
r
ess
io
n
r
ec
o
g
n
itio
n
(
FER)
s
y
s
tem
s
ar
e
b
ein
g
ac
tiv
ely
r
esear
ch
e
d
a
n
d
b
u
ilt
k
ee
p
in
g
i
n
m
in
d
v
ar
io
u
s
en
v
ir
o
n
m
en
tal
a
n
d
s
o
cio
lo
g
ical
f
ac
to
r
s
an
d
th
e
ap
p
licatio
n
s
o
f
th
ese
s
y
s
tem
s
.
R
esear
ch
er
s
u
s
e
ML
an
d
DL
alg
o
r
ith
m
s
o
r
ev
e
n
a
co
m
b
in
atio
n
o
f
th
em
f
o
r
F
E
R
task
s
[
7
]
.
E
k
m
an
an
d
Frie
s
en
[
8
]
r
ec
o
g
n
ized
s
ix
f
u
n
d
am
e
n
tal
em
o
tio
n
s
n
am
ely
: a
n
g
er
,
f
ea
r
,
d
is
g
u
s
t,
h
ap
p
in
ess
,
s
ad
n
ess
,
an
d
s
u
r
p
r
is
e
th
r
o
u
g
h
a
cr
o
s
s
-
cu
ltu
r
al
s
tu
d
y
[
9
]
wh
i
ch
im
p
licated
th
at
t
h
ese
em
o
ti
o
n
s
ar
e
u
n
iv
er
s
ally
r
ec
o
g
n
ized
r
e
g
ar
d
less
o
f
cu
lt
u
r
e
[
1
0
]
.
Ad
d
itio
n
ally
,
a
n
eu
t
r
al
em
o
tio
n
ca
n
also
b
e
a
d
d
e
d
,
s
u
m
m
i
n
g
u
p
th
e
class
if
icatio
n
o
f
em
o
tio
n
s
in
to
7
b
r
o
ad
ca
teg
o
r
ies [
1
1
]
,
[
1
2
]
.
A
n
u
m
b
er
o
f
r
esear
ch
es
h
av
e
b
ee
n
d
o
n
e
in
th
e
f
ield
o
f
FER
[
1
0
]
,
[
1
3
]
.
Ma
jo
r
ity
o
f
th
ese
wo
r
k
s
lev
er
ag
e
ar
tific
ial
in
tellig
en
ce
m
eth
o
d
s
s
u
ch
as
m
ac
h
in
e
lea
r
n
in
g
,
d
ee
p
lear
n
i
n
g
an
d
en
s
e
m
b
le
tech
n
iq
u
es
as
well
f
o
r
FER.
I
n
th
e
f
ield
o
f
co
m
p
u
ter
v
is
io
n
a
n
d
ML
,
th
e
r
e
is
a
d
e
d
icate
d
d
r
iv
e
to
g
en
er
ate
an
d
s
tu
d
y
th
e
FER s
y
s
tem
s
th
at
ca
n
ac
cu
r
ate
ly
r
ec
o
g
n
ize
ex
p
r
ess
io
n
s
f
r
o
m
f
ac
e
im
ag
e
d
ata.
FER
s
y
s
tem
s
u
s
u
ally
f
o
llo
w
a
g
en
er
al
s
eq
u
en
ce
wh
ich
i
n
clu
d
es
f
ac
e
r
ec
o
g
n
itio
n
,
ex
t
r
ac
tio
n
o
f
f
ea
tu
r
es,
f
ea
tu
r
e
r
ep
r
esen
tatio
n
an
d
last
ly
th
e
class
if
icatio
n
o
f
em
o
tio
n
s
.
T
h
e
f
ac
e
d
etec
tio
n
s
tep
in
clu
d
e
s
d
etec
tin
g
an
d
lo
ca
tin
g
f
ac
es
with
in
an
im
a
g
e
o
r
a
v
id
eo
f
r
am
e.
On
ce
t
h
e
f
ac
es
a
r
e
d
etec
ted
,
th
e
e
x
tr
ac
tio
n
o
f
r
eq
u
ir
ed
f
ea
tu
r
es
s
u
ch
as
f
ac
ia
l
lan
d
m
ar
k
s
,
s
h
a
p
es
an
d
m
o
v
e
m
en
ts
is
p
er
f
o
r
m
e
d
.
T
h
en
,
e
x
t
r
ac
ted
f
ea
tu
r
es
ar
e
tr
an
s
f
o
r
m
ed
o
r
r
ep
r
esen
ted
i
n
a
s
u
itab
le
f
o
r
m
at
wh
ich
ca
n
b
e
r
ec
o
g
n
ize
d
b
y
m
ac
h
in
e
lear
n
in
g
s
y
s
tem
s
.
L
astl
y
,
f
ea
tu
r
es
wh
ich
h
a
v
e
b
ee
n
tr
an
s
f
o
r
m
ed
ar
e
i
n
p
u
t
i
n
t
o
a
class
if
icatio
n
alg
o
r
ith
m
,
lik
e
n
eu
r
al
n
etwo
r
k
s
[
1
4
]
o
r
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es
[
7
]
,
to
class
if
y
th
e
d
ete
cted
f
ac
ial
ex
p
r
ess
io
n
in
to
p
r
ed
ef
in
ed
em
o
tio
n
ca
teg
o
r
ies.
T
h
e
s
tep
s
m
en
tio
n
ed
ab
o
v
e
em
p
l
o
y
v
ar
io
u
s
alg
o
r
ith
m
s
to
co
m
p
lete
ea
ch
task
.
T
h
e
r
ec
en
t
r
ev
iew
p
ap
er
s
o
n
f
ac
ial
em
o
tio
n
r
ec
o
g
n
itio
n
wer
e
r
ev
iewe
d
in
ac
co
r
d
an
ce
to
th
e
d
atasets
u
s
ed
,
p
r
o
p
o
s
ed
m
eth
o
d
o
l
o
g
y
a
n
d
th
e
o
u
tco
m
e
s
o
f
th
e
m
eth
o
d
as sh
o
wn
in
T
ab
le
1
.
I
n
o
u
r
r
ev
iew
o
f
FER
r
esear
c
h
,
we
f
o
u
n
d
a
f
ew
ch
allen
g
es.
Firstl
y
,
m
o
s
t
d
atasets
u
s
ed
in
s
tu
d
ies
ar
e
o
f
ten
s
m
all,
wh
ic
h
lim
its
th
e
d
iv
er
s
ity
o
f
f
ac
ial
ex
p
r
ess
io
n
s
c
ap
tu
r
ed
.
Ou
r
s
tu
d
y
aim
s
t
o
tac
k
le
th
ese
is
s
u
es
b
y
u
s
in
g
d
ata
au
g
m
e
n
tatio
n
tech
n
iq
u
es to
en
lar
g
e
th
e
d
ataset’
s
s
ize
s
o
as to
h
an
d
le
v
ar
io
u
s
en
v
ir
o
n
m
en
tal
f
ac
to
r
s
an
d
f
ac
ial
f
ea
tu
r
es.
Ad
d
itio
n
al
ly
,
m
o
s
t
s
tu
d
ies
u
tili
ze
im
ag
e
s
o
f
ex
tr
em
el
y
s
m
all
s
ize
f
o
r
FER.
Ho
wev
er
,
we
s
o
lv
e
th
is
b
y
r
esizin
g
th
e
im
a
g
e
to
a
h
ig
h
er
s
u
itab
le
s
ize.
W
e
also
em
p
lo
y
th
e
u
s
e
o
f
h
is
to
g
r
am
o
f
o
r
ien
te
d
g
r
ad
ien
t
(
HOG)
f
o
r
th
e
e
x
tr
a
ctio
n
o
f
r
elev
a
n
t
f
ea
tu
r
es
f
r
o
m
th
e
d
ata
.
Mo
r
e
o
v
er
,
wh
ile
m
an
y
FER
s
y
s
tem
s
h
av
e
b
ee
n
d
e
v
elo
p
e
d
u
s
in
g
s
tate
-
of
-
th
e
-
a
r
t
t
ec
h
n
iq
u
es
th
er
e
is
s
t
ill
n
ee
d
f
o
r
f
u
r
th
er
im
p
r
o
v
em
en
ts
in
th
eir
p
er
f
o
r
m
an
ce
.
Ou
r
ap
p
r
o
ac
h
ad
d
r
ess
es a
ll th
ese
g
ap
s
.
T
ab
le
1
.
C
o
m
p
a
r
is
o
n
o
f
ex
is
tin
g
FER m
eth
o
d
s
P
a
p
e
r
D
a
t
a
s
e
t
N
o
.
o
f
c
l
a
ss
e
s
P
r
o
p
o
se
d
a
p
p
r
o
a
c
h
A
c
c
u
r
a
c
y
[
1
5
]
F
ER
2
0
1
3
,
C
K
+
7
H
y
b
r
i
d
C
N
N
w
i
t
h
d
e
n
se
s
c
a
l
e
i
n
v
a
r
i
a
n
t
f
e
a
t
u
r
e
t
r
a
n
sf
o
r
m
a
g
g
r
e
g
a
t
o
r
F
ER
2
0
1
3
-
7
3
.
4
%
C
K
+
-
9
9
.
1
±
0
.
0
7
[
1
6
]
S
EED
,
C
K
+
7
S
p
a
t
i
a
l
-
t
e
mp
o
r
a
l
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
(
S
TR
N
N
)
S
EED
-
8
9
.
5
0
%
C
K
+
-
9
5
.
4
%
[
1
2
]
C
K
+
,
JA
F
F
E
7
H
i
e
r
a
r
c
h
i
c
a
l
d
e
e
p
l
e
a
r
n
i
n
g
s
t
r
u
c
t
u
r
e
C
K
+
-
9
6
.
4
6
%
JA
F
F
E
-
9
1
.
2
7
%
[
5
]
F
ER
2
0
1
3
,
C
K
+
,
F
ER
G
,
JA
F
F
E
7
A
t
t
e
n
t
i
o
n
a
l
C
N
N
F
ER
2
0
1
3
-
7
0
.
0
2
%
C
K
+
-
9
8
.
0
%
F
ER
G
-
9
9
.
3
%
JA
F
F
E
–
9
2
.
8
%
F
ER
2
0
1
3
,
C
K
+
,
F
ER
+
,
R
A
F
7
M
u
l
t
i
p
l
e
b
r
a
n
c
h
c
r
o
ss
-
c
o
n
n
e
c
t
e
d
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
(
M
B
C
C
-
C
N
N
)
F
ER
2
0
1
3
–
7
1
.
5
2
%
C
K
+
-
9
8
.
4
8
%
F
ER
+
-
8
8
.
1
0
%
R
A
F
–
8
7
.
3
4
%
[
1
7
]
F
ER
2
0
1
3
,
C
K
+
7
P
a
r
t
i
a
l
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
-
b
a
se
d
C
N
N
F
ER
2
0
1
3
-
8
2
.
1
%
C
K
+
-
6
6
.
7
%
[
1
8
]
F
ER
2
0
1
3
7
En
se
mb
l
e
o
f
m
i
n
i
-
X
c
e
p
t
i
o
n
m
o
d
e
l
s
7
5
%
[
1
9
]
R
A
F
,
A
f
f
e
c
t
N
e
t
7
n
o
v
e
l
f
u
si
o
n
me
t
h
o
d
a
n
d
e
n
s
e
m
b
l
e
l
e
a
r
n
i
n
g
R
A
F
–
9
1
.
6
6
%
A
f
f
e
c
t
N
e
t
-
7
2
.
0
6
%
[
2
0
]
F
ER
2
0
1
3
7
C
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
e
n
sem
b
l
e
7
1
.
2
7
%
[
2
1
]
F
ER
2
0
1
3
,
A
F
EW 7
.
0
7
Te
mp
o
r
a
l
e
n
s
e
m
b
l
e
o
f
m
u
l
t
i
-
l
e
v
e
l
C
N
N
F
ER
2
0
1
3
-
7
4
.
0
9
%
A
F
EW 7
.
0
-
4
9
.
3
%
[
2
2
]
A
F
EW 7
.
0
,
R
A
F
7
M
u
l
t
i
-
r
e
g
i
o
n
e
n
sem
b
l
e
C
N
N
R
A
F
–
7
6
.
7
3
%
A
F
EW
–
4
7
.
4
3
%
[
2
3
]
Emo
t
i
W
2
0
1
7
d
a
t
a
se
t
7
S
u
p
e
r
v
i
se
d
s
c
o
r
i
n
g
e
n
s
e
mb
l
e
6
0
.
3
4
%
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
n
o
ve
l CN
N
-
A
N
N
fu
s
io
n
a
p
p
r
o
a
ch
fo
r
imp
r
o
ve
d
fa
cia
l e
m
o
tio
n
d
etec
tio
n
(
V
ir
a
j S
a
w
a
n
t
)
961
T
h
e
s
ig
n
if
ican
t c
o
n
tr
ib
u
tio
n
s
o
f
th
e
au
t
h
o
r
s
ar
e
as f
o
llo
ws:
a)
Pro
p
o
s
ed
t
h
e
f
u
s
io
n
m
o
d
el
co
n
s
is
tin
g
o
f
ar
tific
ial
n
e
u
r
al
n
e
two
r
k
(
ANN
)
an
d
1
D
-
C
NN
f
o
r
FER
wh
ich
co
m
b
in
es
th
e
s
h
ar
e
d
weig
h
ts
an
d
f
ea
tu
r
e
lear
n
in
g
o
f
1
D
-
C
NN
with
ANN
'
s
ab
ilit
y
to
p
r
o
ce
s
s
all
f
ea
tu
r
es,
en
ab
lin
g
au
to
m
atic
lea
r
n
in
g
o
f
s
p
atial
an
d
tem
p
o
r
al
d
ata
f
o
r
ef
f
ec
tiv
e
h
ier
ar
c
h
ical
class
if
icatio
n
o
f
f
ac
ial
em
o
tio
n
s
.
b)
C
o
n
d
u
cted
h
y
p
er
p
ar
am
eter
t
u
n
in
g
to
e
n
h
an
ce
th
e
p
er
f
o
r
m
a
n
ce
an
d
co
m
p
ar
ativ
e
a
n
aly
s
is
o
f
th
e
m
o
d
el.
c)
C
o
m
p
ar
ativ
e
r
esu
lt a
n
aly
s
is
T
h
e
s
u
b
s
eq
u
en
t
s
ec
tio
n
s
o
f
th
e
p
ap
er
ar
e
o
r
d
e
r
ed
as:
s
ec
tio
n
2
o
u
tlin
es
th
e
im
p
lem
en
tatio
n
p
r
o
ce
d
u
r
e
;
s
ec
tio
n
3
in
tr
o
d
u
c
es
th
e
p
r
o
p
o
s
ed
m
eth
o
d
o
l
o
g
y
;
s
ec
tio
n
4
s
h
o
wca
s
es
ex
p
e
r
im
en
tal
f
in
d
in
g
s
a
n
d
an
aly
s
is
; a
n
d
s
ec
tio
n
5
o
f
f
er
s
t
h
e
p
ap
er
'
s
co
n
clu
s
io
n
s
.
2.
P
RO
CE
DUR
E
2
.
1
.
E
x
perim
ent
env
iro
n
m
e
nt
I
n
t
h
i
s
r
es
e
a
r
c
h
,
w
e
d
e
v
e
l
o
p
e
d
a
n
d
e
x
p
e
r
i
m
e
n
t
e
d
o
n
th
e
p
r
o
p
o
s
e
d
s
y
s
t
e
m
a
n
d
s
ev
e
r
a
l
o
t
h
e
r
c
o
m
p
a
r
a
t
i
v
e
alg
o
r
ith
m
s
u
s
i
n
g
t
h
e
c
o
m
p
u
t
i
n
g
r
es
o
u
r
c
e
s
p
r
o
v
i
d
e
d
b
y
G
o
o
g
l
e
C
o
l
l
a
b
o
r
a
t
o
r
y
[
2
4
]
.
T
o
c
o
n
s
t
r
u
c
t
a
n
d
p
r
o
t
o
t
y
p
e
t
h
e
m
o
d
e
ls
,
w
e
r
e
l
i
e
d
o
n
P
y
t
h
o
n
[
2
5
]
,
i
n
c
l
u
d
i
n
g
K
e
r
a
s
,
T
e
n
s
o
r
F
l
o
w
,
S
c
i
k
it
-
l
ea
r
n
,
a
n
d
M
a
t
p
l
o
t
l
i
b
.
T
o
g
e
t
h
e
r
,
t
h
e
s
e
t
o
o
l
s
a
l
l
o
w
e
d
f
o
r
e
f
f
i
c
i
e
n
t
e
x
p
e
r
i
m
e
n
t
a
t
i
o
n
a
n
d
a
n
a
l
y
s
i
s
f
o
r
f
a
c
i
a
l
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
.
2
.
2
.
Da
t
a
s
et
I
n
o
u
r
s
tu
d
y
,
we
u
tili
ze
th
e
K
ar
o
lin
s
k
a
d
ir
ec
ted
em
o
tio
n
a
l
f
ac
es
(
KDE
F)
[
2
6
]
f
o
r
th
e
t
r
ain
in
g
an
d
ass
es
s
m
en
t
o
f
o
u
r
m
eth
o
d
s
.
T
h
e
KDE
F
d
ataset
co
n
s
is
ts
o
f
a
wid
e
-
r
a
n
g
in
g
co
llectio
n
o
f
4
9
0
0
im
ag
es
ca
p
tu
r
in
g
f
ac
ial
e
x
p
r
ess
io
n
s
.
T
h
ey
f
ea
t
u
r
e
7
0
d
if
f
er
e
n
t
in
d
iv
id
u
als,
ev
e
n
ly
s
p
lit
b
etwe
en
3
5
f
e
m
ales
an
d
3
5
m
ales,
wh
o
wer
e
s
elec
ted
b
as
ed
o
n
s
p
ec
if
ic
c
r
iter
ia,
o
f
ag
e
2
0
-
3
0
y
ea
r
s
a
n
d
with
an
ab
s
en
ce
o
f
f
ac
ial
h
air
,
ac
ce
s
s
o
r
ies,
o
r
m
ak
eu
p
d
u
r
in
g
th
e
p
h
o
to
s
ess
io
n
s
.
T
h
e
s
u
b
jects
ac
cu
r
ately
p
o
r
tr
a
y
s
ev
en
d
is
tin
ct
em
o
tio
n
al
e
x
p
r
ess
io
n
s
n
am
ely
n
eu
tr
al,
h
ap
p
y
,
an
g
r
y
,
af
r
aid
,
d
is
g
u
s
ted
,
s
ad
,
an
d
s
u
r
p
r
is
ed
.
E
ac
h
s
u
b
ject'
s
f
ac
e
was
p
h
o
to
g
r
a
p
h
ed
f
r
o
m
5
d
i
f
f
er
en
t
an
g
les.
T
h
e
im
ag
es a
r
e
o
f
s
tan
d
a
r
d
ized
d
im
en
s
io
n
s
o
f
5
6
2
b
y
7
6
2
p
ix
els.
Fo
r
th
e
p
u
r
p
o
s
e
o
f
o
u
r
s
tu
d
y
,
we
h
a
v
e
s
o
lely
in
clu
d
ed
th
e
im
ag
es
th
at
h
av
e
b
ee
n
ca
p
tu
r
ed
f
r
o
m
a
s
tr
aig
h
t
an
g
le
wh
ich
s
u
m
u
p
t
o
7
2
0
s
am
p
les
in
to
tal.
Ad
d
itio
n
ally
,
we
h
av
e
also
r
esized
th
e
im
ag
es
to
a
s
ize
o
f
2
2
4
b
y
2
2
4
p
ix
els
f
o
r
o
u
r
r
esear
ch
as
co
m
p
ar
e
d
to
o
th
e
r
s
tu
d
ies
th
at
e
m
p
lo
y
th
e
u
s
e
o
f
im
ag
es
th
at
ar
e
s
m
aller
in
s
ize.
Sam
p
les f
r
o
m
th
e
d
ataset
ar
e
s
h
o
wn
in
Fig
u
r
e
1
.
Fig
u
r
e
1
.
E
x
am
p
les f
r
o
m
th
e
KDE
F d
ataset
2
.
3
.
F
a
ce
det
ec
t
io
n
Face
d
etec
tio
n
s
tan
d
s
at
th
e
f
o
r
ef
r
o
n
t
f
o
r
r
ec
o
g
n
itio
n
o
f
f
a
cial
ex
p
r
ess
io
n
s
,
b
ein
g
th
e
in
i
tial
s
tep
in
u
n
d
er
s
tan
d
i
n
g
an
d
a
n
aly
zin
g
f
ac
ial
ex
p
r
ess
io
n
s
.
I
n
o
u
r
r
esear
ch
,
we
em
p
lo
y
a
p
o
p
u
lar
an
d
p
o
we
r
f
u
l
alg
o
r
ith
m
,
Haa
r
C
ascad
e
[
2
7
]
wh
ich
is
b
ased
o
n
th
e
Vio
la
J
o
n
es
alg
o
r
ith
m
[
2
8
]
.
Op
e
n
C
V
[
2
9
]
lib
r
a
r
y
was
u
tili
ze
d
to
im
p
lem
en
t
Haa
r
C
ascad
e.
Fu
r
th
er
m
o
r
e,
af
ter
th
e
f
ac
es
ar
e
d
etec
ted
,
th
e
im
ag
e
s
ar
e
cr
o
p
p
ed
s
o
a
s
to
f
o
cu
s
o
n
th
e
f
ac
es.
T
h
is
m
o
d
el
ef
f
icien
tly
d
etec
ts
f
ac
es
in
th
e
p
r
o
v
id
ed
im
ag
es
a
n
d
cr
o
p
s
th
em
.
An
illu
s
tr
atio
n
d
ep
ictin
g
th
e
d
etec
ted
an
d
cr
o
p
p
e
d
im
ag
es is
p
r
o
v
id
ed
in
Fig
u
r
e
2.
Fig
u
r
e
2
.
C
r
o
p
p
ed
im
a
g
e
u
s
in
g
h
aa
r
ca
s
ca
d
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
37
,
No
.
2
,
Feb
r
u
a
r
y
20
25
:
9
5
9
-
9
6
7
962
2
.
4
.
Aug
m
ent
a
t
io
n
T
h
e
KDE
F
d
ataset
co
n
tain
s
lim
ited
s
am
p
les
d
u
e
to
wh
ich
u
n
d
er
-
f
itti
n
g
/o
v
er
-
f
itti
n
g
o
r
lim
ited
g
en
er
aliza
tio
n
co
u
ld
tak
e
p
lac
e.
T
h
e
6
1
3
7
im
ag
es
wer
e
p
r
o
d
u
ce
d
f
r
o
m
th
e
d
ataset
o
f
7
2
0
o
r
ig
in
al
im
ag
es
in
b
atch
es
o
f
v
ar
y
in
g
s
izes
d
ep
en
d
in
g
o
n
th
e
d
if
f
er
e
n
t
em
o
tio
n
class
es.
T
h
e
co
u
n
t
o
f
im
ag
es
in
ea
ch
clas
s
af
ter
au
g
m
en
tatio
n
a
n
d
ad
d
itio
n
to
th
e
o
r
ig
in
al
d
ataset
is
g
iv
en
in
Fig
u
r
e
3
.
T
h
e
p
ar
a
m
eter
s
ap
p
lied
o
n
th
e
im
ag
es
to
p
er
f
o
r
m
au
g
m
en
tatio
n
ar
e
m
en
tio
n
ed
as
s
h
o
wn
in
T
ab
le
2
.
Fig
u
r
e
4
illu
s
tr
ates
a
s
am
p
le
im
ag
e
a
f
ter
d
ata
au
g
m
en
tatio
n
was a
p
p
lied
.
T
ab
le
2
.
Au
g
m
en
tatio
n
p
ar
am
eter
s
P
a
r
a
me
t
e
r
s
V
a
l
u
e
s
R
e
sc
a
l
e
1
.
/
2
5
5
R
o
t
a
t
i
o
n
r
a
n
g
e
1
0
d
e
g
r
e
e
s
B
r
i
g
h
t
n
e
ss ra
n
g
e
0
.
8
,
1
.
2
H
e
i
g
h
t
s
h
i
f
t
r
a
n
g
e
10
W
i
d
t
h
sh
i
f
t
r
a
n
g
e
10
Zo
o
m ra
n
g
e
0
.
1
Fig
u
r
e
3
.
C
o
u
n
t o
f
im
a
g
es a
f
te
r
au
g
m
e
n
tatio
n
Fig
u
r
e
4
.
Or
ig
i
n
al
to
au
g
m
en
t
ed
im
ag
e
2
.
5
.
F
e
a
t
ure
ex
t
r
a
ct
io
n
T
o
t
r
a
n
s
f
o
r
m
r
a
w
i
m
a
g
e
d
a
t
a
i
n
t
o
a
m
o
r
e
i
n
f
o
r
m
a
t
i
v
e
r
e
p
r
e
s
e
n
t
a
t
i
o
n
t
h
a
t
c
a
p
t
u
r
e
s
r
e
le
v
a
n
t
p
a
t
t
e
r
n
s
a
n
d
c
h
a
r
a
c
t
e
r
is
t
i
cs
f
r
o
m
t
h
e
i
m
a
g
e
,
w
e
h
a
v
e
u
t
i
li
z
e
d
t
h
e
H
OG
[
3
0
]
m
e
t
h
o
d
o
l
o
g
y
.
T
h
i
s
t
e
c
h
n
i
q
u
e
d
i
s
s
e
c
ts
e
a
c
h
i
m
a
g
e
i
n
t
o
s
m
a
ll
e
r
r
e
g
i
o
n
s
,
c
a
p
t
u
r
i
n
g
t
h
e
p
a
t
t
e
r
n
s
o
f
g
r
a
d
i
e
n
t
c
h
a
n
g
e
s
i
n
t
h
es
e
r
e
g
i
o
n
s
.
B
y
s
t
u
d
y
i
n
g
t
h
e
s
e
c
h
a
n
g
es
i
n
t
h
e
d
i
s
t
r
i
b
u
t
i
o
n
o
f
g
r
a
d
ie
n
t
s
,
HO
G
e
x
t
r
ac
ts
t
h
e
t
e
x
t
u
r
e
a
n
d
s
h
a
p
e
v
a
r
i
a
ti
o
n
s
f
r
o
m
t
h
e
i
m
a
g
es.
A
d
d
i
t
i
o
n
a
ll
y
,
HO
G
w
a
s
e
m
p
l
o
y
e
d
s
e
p
a
r
at
e
l
y
f
o
r
e
a
c
h
c
o
l
o
u
r
c
h
a
n
n
e
l
s
o
a
s
t
o
p
r
e
s
e
r
v
e
c
r
u
c
i
a
l
i
n
f
o
r
m
a
ti
o
n
a
b
o
u
t
t
h
e
i
m
a
g
e
’
s
c
o
l
o
u
r
c
o
m
p
o
s
i
t
i
o
n
.
T
h
es
e
f
ea
t
u
r
e
s
f
r
o
m
d
i
f
f
e
r
e
n
t
c
h
a
n
n
e
ls
a
r
e
l
a
te
r
c
o
n
c
a
t
e
n
a
t
e
d
i
n
t
o
a
s
i
n
g
l
e
a
r
r
a
y
.
T
h
e
p
a
r
a
m
e
t
e
r
s
u
s
e
d
f
o
r
f
e
a
t
u
r
e
e
x
t
r
a
c
ti
o
n
a
r
e
g
i
v
e
n
i
n
T
a
b
l
e
3
.
T
ab
le
3
.
HOG
p
ar
am
eter
s
f
o
r
f
ea
tu
r
e
ex
tr
ac
tio
n
P
a
r
a
me
t
e
r
D
e
scri
p
t
i
o
n
V
a
l
u
e
O
r
i
e
n
t
a
t
i
o
n
s
N
u
mb
e
r
o
f
b
i
n
s t
o
d
i
v
i
d
e
g
r
a
d
i
e
n
t
d
i
r
e
c
t
i
o
n
s
i
n
e
a
c
h
c
e
l
l
9
P
i
x
e
l
s
p
e
r
c
e
l
l
S
i
z
e
o
f
e
a
c
h
b
l
o
c
k
w
h
e
r
e
g
r
a
d
i
e
n
t
s
a
r
e
c
o
m
p
u
t
e
d
(
8
,
8
)
C
e
l
l
s
p
e
r
b
l
o
c
k
N
u
mb
e
r
o
f
b
l
o
c
k
s i
n
w
h
i
c
h
g
r
a
d
i
e
n
t
s
a
r
e
c
a
l
c
u
l
a
t
e
d
(
2
,
2
)
V
i
su
a
l
i
z
e
G
e
n
e
r
a
t
e
a
v
i
su
a
l
r
e
p
r
e
se
n
t
a
t
i
o
n
o
f
t
h
e
H
O
G
f
e
a
t
u
r
e
s
Tr
u
e
M
u
l
t
i
c
h
a
n
n
e
l
I
n
d
i
c
a
t
e
i
f
t
h
e
i
ma
g
e
h
a
s m
u
l
t
i
p
l
e
c
o
l
o
r
c
h
a
n
n
e
l
s
o
r
g
r
a
y
s
c
a
l
e
F
a
l
se
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
n
o
ve
l CN
N
-
A
N
N
fu
s
io
n
a
p
p
r
o
a
ch
fo
r
imp
r
o
ve
d
fa
cia
l e
m
o
tio
n
d
etec
tio
n
(
V
ir
a
j S
a
w
a
n
t
)
963
3.
M
E
T
H
O
D
T
h
e
p
r
o
p
o
s
ed
ar
c
h
itectu
r
e
c
o
n
s
is
ts
o
f
2
in
d
ep
en
d
en
t
d
ee
p
lear
n
in
g
m
o
d
els,
a
1
D
c
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
(
C
NN)
an
d
a
n
ANN.
T
h
ese
m
o
d
els
o
p
e
r
at
e
in
p
ar
allel,
ex
tr
ac
tin
g
h
ig
h
-
lev
el
f
ea
tu
r
es
f
r
o
m
th
eir
r
esp
ec
tiv
e
in
p
u
ts
.
I
n
teg
r
atin
g
b
o
th
th
e
m
o
d
els
h
elp
s
i
n
lear
n
in
g
co
m
p
lex
p
atter
n
s
,
with
C
NN
s
s
e
lectin
g
r
elev
an
t
f
ea
tu
r
es
an
d
ANNs
p
r
o
ce
s
s
in
g
all
f
ea
tu
r
es.
T
h
is
h
ier
ar
ch
ical
ap
p
r
o
ac
h
e
n
h
an
c
es
th
e
ac
cu
r
ac
y
an
d
r
o
b
u
s
tn
ess
o
f
f
ac
ial
em
o
tio
n
r
ec
o
g
n
itio
n
.
T
h
e
HOG
f
ilter
ex
tr
ac
ts
lo
ca
l
tex
tu
r
e
f
ea
tu
r
es
an
d
s
h
a
p
e
in
f
o
r
m
atio
n
f
r
o
m
im
ag
es.
E
a
ch
m
o
d
el
is
d
esig
n
ed
to
ca
p
tu
r
e
d
if
f
e
r
en
t
asp
ec
ts
o
f
i
n
p
u
t
d
a
t
a
,
o
p
t
i
m
i
zi
n
g
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
c
l
as
s
i
f
i
c
at
i
o
n
t
as
k
s
.
1
D
-
C
N
N
a
r
r
a
n
g
e
s
f
e
a
t
u
r
e
s
b
a
s
e
d
o
n
a
s
s
i
g
n
e
d
we
i
g
h
t
s
w
h
e
r
e
as
t
h
e
A
N
N
h
as
i
n
d
i
v
i
d
u
al
w
ei
g
h
t
s
f
o
r
e
a
c
h
n
e
u
r
o
n
.
C
N
N
1
D
i
s
u
s
ed
t
o
p
r
o
c
e
s
s
o
n
e
-
d
i
m
e
n
s
i
o
n
al
d
a
t
a
a
s
c
o
m
p
a
r
e
d
t
o
C
N
N
2
D
w
h
i
c
h
p
r
o
c
e
s
s
e
s
tw
o
-
d
i
m
e
n
s
i
o
n
a
l
d
a
t
a
[
31
]
.
T
h
e
a
r
c
h
i
t
e
c
t
u
r
e
c
o
m
p
r
i
s
e
s
o
f
f
o
u
r
c
o
n
v
o
l
u
t
i
o
n
a
l
l
a
y
e
r
s
,
e
a
c
h
u
t
il
i
z
i
n
g
t
h
e
R
e
L
U
a
c
ti
v
a
t
i
o
n
f
u
n
c
t
i
o
n
,
f
o
ll
o
w
e
d
b
y
a
M
a
x
P
o
o
l
i
n
g
l
a
y
e
r
a
n
d
a
d
r
o
p
o
u
t
r
a
t
e
o
f
0
.
5
f
o
r
r
e
g
u
l
a
r
i
z
a
t
i
o
n
p
u
r
p
o
s
e
s
.
T
h
e
n
,
a
F
l
a
tt
e
n
l
a
y
e
r
c
o
n
v
e
r
t
s
t
h
e
o
u
t
p
u
t
i
n
t
o
a
1
D
a
r
r
a
y
b
e
f
o
r
e
c
o
n
c
a
t
e
n
a
t
i
n
g
t
o
f
o
r
m
t
h
e
f
u
s
i
o
n
m
o
d
e
l
.
T
h
e
a
r
c
h
it
e
c
tu
r
e
o
f
t
h
e
m
o
d
e
l
i
s
s
h
o
w
n
i
n
F
ig
u
r
e
5
.
Fi
g
u
r
e
5
.
Ar
c
h
itectu
r
e
o
f
ANN
-
C
NN
f
u
s
io
n
m
o
d
el
T
h
e
h
i
g
h
-
l
e
v
e
l
f
e
a
t
u
r
e
s
a
r
e
f
e
t
c
h
e
d
f
r
o
m
t
h
e
l
a
s
t
f
u
l
l
y
c
o
n
n
e
c
t
e
d
l
a
y
e
r
s
.
T
h
i
s
l
a
y
e
r
g
e
n
e
r
a
t
e
s
f
e
a
t
u
r
e
v
e
c
t
o
r
s
.
T
h
e
s
e
f
e
a
t
u
r
e
s
e
x
t
r
a
c
t
e
d
a
r
e
c
o
n
c
a
t
e
n
a
t
e
d
t
o
f
o
r
m
a
f
u
l
l
y
c
o
m
b
i
n
e
d
f
e
a
t
u
r
e
v
e
c
t
o
r
w
h
i
c
h
a
r
e
t
h
e
n
a
r
r
a
n
g
e
d
a
c
c
o
r
d
i
n
g
t
o
t
h
e
i
r
w
e
i
g
h
t
s
a
n
d
p
a
s
s
e
d
t
o
t
h
e
f
u
s
i
o
n
l
a
y
e
r
w
h
e
r
e
t
h
e
r
e
p
r
e
s
e
n
t
a
t
i
o
n
s
l
e
a
r
n
e
d
b
y
t
h
e
t
w
o
n
e
t
w
o
r
k
s
a
r
e
c
o
m
b
i
n
e
d
.
T
h
e
f
u
s
i
o
n
l
a
y
e
r
a
l
l
o
w
s
t
h
e
m
o
d
e
l
s
t
o
u
s
e
t
h
e
i
r
c
o
m
b
i
n
e
d
s
t
r
e
n
g
t
h
s
w
h
i
l
e
m
i
t
i
g
a
t
i
n
g
i
n
d
i
v
i
d
u
a
l
l
i
m
i
t
a
t
i
o
n
s
f
o
r
c
l
a
s
s
i
f
i
c
a
t
i
o
n
t
a
s
k
s
.
T
h
e
m
o
d
e
l
i
s
o
p
t
i
m
i
z
e
d
b
y
u
s
i
n
g
t
h
e
l
o
s
s
f
u
n
c
t
i
o
n
s
u
c
h
a
s
c
a
t
e
g
o
r
i
c
a
l
c
r
o
s
s
-
e
n
t
r
o
p
y
,
s
p
a
r
s
e
c
a
t
e
g
o
r
i
c
a
l
c
r
o
s
s
-
e
n
t
r
o
p
y
t
o
m
i
n
i
m
i
z
e
t
h
e
m
e
a
n
s
q
u
a
r
e
d
e
r
r
o
r
.
A
l
s
o
,
v
a
r
i
o
u
s
r
e
g
u
l
a
r
i
z
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s
a
r
e
u
s
e
d
s
u
c
h
a
s
d
r
o
p
o
u
t
a
n
d
B
a
t
c
h
n
o
r
m
a
l
i
z
a
t
i
o
n
t
o
p
r
e
v
e
n
t
t
h
e
m
o
d
e
l
f
r
o
m
o
v
e
r
f
i
t
t
i
n
g
.
T
h
e
A
d
a
m
o
p
t
i
m
i
z
e
r
[
3
2
]
,
w
h
i
c
h
i
s
c
o
n
s
i
d
e
r
e
d
a
s
o
n
e
o
f
t
h
e
b
e
s
t
f
o
r
o
p
t
i
m
i
z
a
t
i
o
n
t
a
s
k
s
,
i
s
u
s
e
d
t
o
c
o
m
p
i
l
e
t
h
e
m
o
d
e
l
.
A
n
8
0
-
2
0
s
p
l
i
t
h
a
s
b
e
e
n
p
e
r
f
o
r
m
e
d
f
o
r
t
r
a
i
n
i
n
g
a
n
d
v
a
l
i
d
a
t
i
o
n
p
u
r
p
o
s
e
s
.
T
h
e
m
o
d
e
l
i
s
t
r
a
i
n
e
d
f
o
r
a
1
0
0
e
p
o
c
h
s
w
i
t
h
a
b
a
t
c
h
s
i
z
e
o
f
6
4
.
A
d
d
i
t
i
o
n
a
l
l
y
,
e
a
r
l
y
s
t
o
p
p
i
n
g
h
a
s
b
e
e
n
i
m
p
l
e
m
e
n
t
e
d
w
i
t
h
a
p
a
t
i
e
n
c
e
o
f
1
0
e
p
o
c
h
s
t
o
a
v
o
i
d
o
v
e
r
f
i
t
t
i
n
g
.
F
a
c
i
a
l
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
i
n
v
o
l
v
e
s
t
h
e
n
o
n
-
l
i
n
e
a
r
r
e
l
a
t
i
o
n
s
h
i
p
b
e
t
w
e
e
n
t
h
e
d
a
t
a
p
o
i
n
t
s
e
x
t
r
a
c
t
e
d
d
u
e
t
o
d
i
f
f
e
r
e
n
c
e
i
s
p
o
s
e
,
l
i
g
h
t
i
n
g
c
o
n
d
i
t
i
o
n
,
s
t
r
u
c
t
u
r
e
a
n
d
s
i
z
e
o
f
f
a
c
e
f
o
r
e
a
c
h
i
n
d
i
v
i
d
u
a
l
.
A
N
N
m
o
d
e
l
p
r
o
v
e
s
t
o
b
e
a
g
o
o
d
m
o
d
e
l
t
o
d
e
a
l
w
i
t
h
s
u
c
h
n
o
n
-
l
i
n
e
a
r
r
e
l
a
t
i
o
n
s
h
i
p
s
,
w
i
t
h
o
u
t
k
n
o
w
i
n
g
t
h
e
e
x
a
c
t
f
u
n
c
t
i
o
n
.
T
h
i
s
A
lg
o
r
ith
m
1
d
escr
ib
es
th
e
p
r
o
ce
s
s
f
o
r
d
ev
elo
p
i
n
g
an
en
s
em
b
le
m
o
d
el
f
o
r
em
o
tio
n
class
if
icatio
n
u
s
in
g
two
n
eu
r
al
n
etwo
r
k
ty
p
es:
a
co
n
v
o
lu
tio
n
al
n
e
u
r
al
n
et
wo
r
k
(
C
NN)
an
d
an
ar
tifi
cial
n
eu
r
al
n
etwo
r
k
(
ANN)
.
I
t
b
eg
in
s
b
y
p
r
ep
a
r
in
g
th
e
d
ata
a
n
d
s
p
litt
in
g
it
in
to
tr
ain
in
g
a
n
d
test
in
g
s
ets.
B
o
th
m
o
d
els
a
r
e
tr
ain
e
d
o
n
th
e
s
am
e
f
ea
tu
r
es,
an
d
th
eir
p
r
ed
ictio
n
s
ar
e
co
m
b
in
ed
to
en
h
an
ce
cl
ass
if
icatio
n
ac
cu
r
ac
y
.
Fin
ally
,
th
e
tr
ain
ed
m
o
d
el
is
ev
alu
ated
an
d
u
s
ed
to
class
if
y
em
o
tio
n
s
in
to
s
ev
en
ca
teg
o
r
ies.
Alg
o
r
ith
m
1
.
P
r
o
p
o
s
ed
m
o
d
el
Input: Number of samples (1440, 2916)
–
80% for training and 20% for testing.
Output: Trained fusion model
classifier for emotion classification
BEGIN
X
_
CNN: Data for CNN (2916, 12)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
37
,
No
.
2
,
Feb
r
u
a
r
y
20
25
:
9
5
9
-
9
6
7
964
X_ANN: Data for ANN (2916, 12)
y: Training labels (1152, 7)
Base Learners = [CNN_model, ANN_model]
Meta
-
Learner (ensemble model):
Ensemble_model: CNN_model + ANN_model
Train Neural Network:
CNN_pred, ANN_pred
For i=1: num Epochs
Ensemble_model
merge = np.concatenate([CNN_pred, ANN_pred])
output = Dense (7, activation ='softmax’)
return Output
END
Evaluate and Test Neural Network
Classify and Identify Emotions.
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
4
.
1
.
E
x
perim
ent
re
s
ults
T
h
e
f
u
s
io
n
m
o
d
el
d
em
o
n
s
tr
ates
a
n
o
ta
b
le
ac
cu
r
ac
y
o
f
9
2
.
4
2
%.
T
h
e
tr
ain
in
g
an
d
v
alid
atio
n
ac
c
u
r
ac
y
an
d
lo
s
s
g
r
ap
h
s
ar
e
d
ep
icted
i
n
Fig
u
r
e
s
6
a
n
d
7
.
T
h
e
m
o
d
el's
co
n
f
u
s
io
n
m
atr
i
x
is
p
r
esen
ted
in
Fig
u
r
e
8
.
T
ab
l
e
4
d
e
p
icts
th
e
e
v
alu
atio
n
m
etr
i
cs
f
o
r
th
e
m
o
d
el.
Ad
d
itio
n
ally
,
th
e
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
a
ll
an
d
F1
-
s
co
r
e
f
o
r
ea
ch
class
is
g
iv
en
in
T
ab
le
5
.
T
ab
le
4
.
E
v
alu
atio
n
m
et
r
ics p
er
class
C
l
a
s
s L
a
b
e
l
s
A
c
c
u
r
a
c
y
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
S
c
o
r
e
A
f
r
a
i
d
0
.
9
3
0
.
9
1
0
.
8
5
0
.
8
8
A
n
g
r
y
0
.
9
2
0
.
9
1
0
.
9
2
0
.
9
2
D
i
sg
u
st
e
d
0
.
8
8
0
.
8
5
0
.
8
7
0
.
8
6
H
a
p
p
y
0
.
9
8
0
.
9
3
0
.
9
7
0
.
9
5
N
e
u
t
r
a
l
0
.
9
3
0
.
9
8
0
.
9
3
0
.
9
5
S
a
d
0
.
8
6
0
.
9
8
0
.
9
7
0
.
9
8
S
u
r
p
r
i
s
e
d
0
.
9
7
0
.
9
0
0
.
9
3
0
.
9
1
Fig
u
r
e
6
.
T
r
ain
in
g
a
n
d
v
alid
atio
n
ac
cu
r
ac
y
Fig
u
r
e
7
.
T
r
ain
in
g
a
n
d
v
alid
atio
n
lo
s
s
Fig
u
r
e
8
.
C
o
n
f
u
s
io
n
m
atr
i
x
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
n
o
ve
l CN
N
-
A
N
N
fu
s
io
n
a
p
p
r
o
a
ch
fo
r
imp
r
o
ve
d
fa
cia
l e
m
o
tio
n
d
etec
tio
n
(
V
ir
a
j S
a
w
a
n
t
)
965
T
ab
le
5
.
E
v
alu
atio
n
m
et
r
ics o
f
f
u
s
io
n
m
o
d
el
M
e
t
r
i
c
V
a
l
u
e
A
c
c
u
r
a
c
y
0
.
9
2
4
2
P
r
e
c
i
s
i
o
n
0
.
9
2
8
1
R
e
c
a
l
l
0
.
9
2
5
3
F1
-
S
c
o
r
e
0
.
9
2
6
4
4.
2
.
Co
m
pa
ra
t
iv
e
a
na
ly
s
is
A
s
u
m
m
a
r
y
o
f
t
h
e
c
o
m
p
a
r
i
s
o
n
i
s
g
i
v
e
n
i
n
T
a
b
l
e
6
.
T
h
r
o
u
g
h
o
u
r
a
n
a
l
y
s
i
s
,
w
e
h
a
v
e
o
b
s
e
r
v
e
d
t
h
a
t
o
u
r
p
r
o
p
o
s
e
d
m
o
d
e
l
d
e
m
o
n
s
t
r
a
t
e
s
a
n
a
c
c
u
r
a
c
y
h
i
g
h
e
r
t
h
a
n
t
h
e
o
t
h
e
r
m
o
d
e
l
s
u
t
i
l
i
z
e
d
f
o
r
F
E
R
.
T
h
i
s
v
a
l
i
d
a
t
e
s
t
h
e
u
s
e
f
u
l
n
e
s
s
o
f
o
u
r
f
u
s
i
o
n
m
o
d
e
l
i
n
t
h
e
f
i
e
l
d
a
n
d
i
t
s
e
f
f
e
c
t
i
v
e
n
e
s
s
i
n
d
i
s
c
e
r
n
i
n
g
t
h
e
v
a
r
i
o
u
s
e
m
o
t
i
o
n
s
.
I
n
a
d
d
i
t
i
o
n
,
t
h
r
o
u
g
h
e
x
p
e
r
i
m
e
n
t
a
t
i
o
n
,
w
e
h
a
v
e
n
o
t
i
c
e
d
t
h
a
t
t
h
e
f
u
s
i
o
n
m
o
d
e
l
h
a
s
a
h
i
g
h
e
r
a
c
c
u
r
a
c
y
t
h
a
n
t
h
e
i
n
d
i
v
i
d
u
a
l
A
N
N
a
n
d
C
N
N
m
o
d
e
l
s
w
i
t
h
9
0
.
0
1
%
a
n
d
9
1
.
4
7
%
a
c
c
u
r
a
c
y
r
e
s
p
e
c
t
i
v
e
l
y
.
T
h
r
o
u
g
h
t
h
e
a
c
q
u
i
r
e
d
r
e
s
u
l
t
s
a
n
d
c
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
s
i
s
,
i
t
i
s
o
b
s
e
r
v
e
d
t
h
a
t
o
u
r
n
o
v
e
l
A
N
N
-
C
N
N
f
u
s
i
o
n
m
o
d
e
l
g
e
n
e
r
a
t
e
s
b
e
t
t
e
r
a
c
c
u
r
a
c
y
a
n
d
o
u
t
c
o
m
e
s
.
T
ab
le
6
.
C
o
m
p
a
r
is
o
n
o
f
m
o
d
el
s
with
ex
is
tin
g
m
eth
o
d
s
A
u
t
h
o
r
D
a
t
a
s
e
t
M
e
t
h
o
d
A
c
c
u
r
a
c
y
Zh
a
n
g
e
t
a
l
.
[
1
6
]
S
EED
S
TR
N
N
8
9
.
5
0
%
S
h
e
h
a
d
a
e
t
a
l
.
[
1
7
]
F
ER
2
0
1
3
,
C
K
+
P
a
r
t
i
a
l
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
8
2
.
1
%,
6
6
.
7
%
U
l
l
a
h
e
t
a
l
.
[
1
9
]
R
A
F
-
D
B
,
A
f
f
e
c
t
N
e
t
D
e
e
p
e
n
sem
b
l
e
m
o
d
e
l
9
1
.
6
6
%
,
7
2
.
0
6
%
Ji
a
e
t
a
l
.
[
2
0
]
F
ER
2
0
1
3
C
N
N
e
n
sem
b
l
e
7
1
.
2
7
%
N
g
u
y
e
n
e
t
a
l
.
[
2
1
]
F
ER
2
0
1
3
,
A
F
EW
7
.
0
M
u
l
t
i
-
l
e
v
e
l
C
N
N
e
n
se
mb
l
e
7
4
.
0
9
%
,
4
9
.
3
%
H
u
e
t
a
l
.
[
2
3
]
Emo
t
i
W
2
0
1
7
S
u
p
e
r
v
i
se
d
S
c
o
r
i
n
g
e
n
s
e
mb
l
e
6
0
.
3
4
%
P
r
o
p
o
se
d
M
e
t
h
o
d
K
D
EF
F
u
si
o
n
m
o
d
e
l
9
2
.
4
2
%
5.
CO
NCLU
SI
O
N
T
h
r
o
u
g
h
o
u
r
s
tu
d
y
,
we
h
av
e
u
n
d
er
tak
en
a
c
o
m
p
r
eh
en
s
iv
e
in
v
esti
g
atio
n
in
to
m
eth
o
d
o
lo
g
ie
s
f
o
r
FER
th
at
h
av
e
b
ee
n
ca
r
r
ied
o
u
t
b
y
r
esear
ch
er
s
in
th
e
p
ast.
Ou
r
r
esear
ch
aim
s
to
ad
d
r
ess
th
e
c
h
allen
g
es
o
f
im
a
g
e
s
ize,
d
ataset
s
ize
an
d
v
ar
iab
ilit
y
an
d
e
x
tr
ac
tio
n
o
f
f
ea
tu
r
es
in
th
is
d
o
m
ain
,
m
ar
k
i
n
g
a
s
ig
n
if
ican
t
s
tep
f
o
r
war
d
in
tack
lin
g
th
is
is
s
u
e
.
Ou
r
p
r
i
m
ar
y
co
n
t
r
ib
u
tio
n
lies
in
th
e
i
n
tr
o
d
u
ctio
n
o
f
a
n
o
v
el
m
o
d
el
co
m
b
in
in
g
ANN
an
d
C
NN
th
r
o
u
g
h
late
f
u
s
io
n
.
T
h
i
s
m
o
d
el
is
f
ed
with
a
n
in
p
u
t
o
f
th
e
f
ea
tu
r
e
ex
tr
ac
te
d
u
s
in
g
t
h
e
HOG
tech
n
iq
u
e
.
T
h
r
o
u
g
h
ca
r
ef
u
l
ar
c
h
itectu
r
al
co
n
s
id
er
atio
n
s
an
d
h
y
p
er
p
a
r
a
m
eter
tu
n
in
g
,
th
e
Fu
s
io
n
m
o
d
el
h
as
d
em
o
n
s
tr
ated
ex
ce
p
tio
n
al
p
e
r
f
o
r
m
an
ce
,
ac
h
i
ev
in
g
an
im
p
r
ess
iv
e
ac
cu
r
ac
y
o
f
9
2
.
4
2
%.
Fu
r
t
h
er
m
o
r
e,
it
h
a
s
p
r
o
v
en
t
o
p
r
o
v
id
e
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
Sco
r
es
th
at
ar
e
n
o
tewo
r
th
y
,
u
n
d
er
s
co
r
in
g
its
ef
f
icac
y
in
ac
c
u
r
ately
d
is
ce
r
n
in
g
em
o
tio
n
s
f
r
o
m
f
ac
ial
im
ag
es.
Mo
r
eo
v
e
r
,
b
y
u
tili
zin
g
late
f
u
s
io
n
tech
n
iq
u
e,
we
h
a
v
e
s
u
c
ce
s
s
f
u
lly
in
teg
r
ated
r
aw
d
ata
an
d
f
ea
tu
r
e
v
ec
to
r
s
ex
tr
ac
ted
f
r
o
m
d
if
f
er
e
n
t
m
o
d
alities
,
r
esu
ltin
g
in
a
m
o
d
el
with
en
h
an
ce
d
class
if
icatio
n
ac
cu
r
ac
y
.
M
o
r
eo
v
er
,
in
o
u
r
c
o
m
p
ar
ativ
e
an
aly
s
is
ag
ain
s
t
ex
is
tin
g
m
eth
o
d
o
lo
g
ies,
o
u
r
m
o
d
el
h
as
o
u
tp
er
f
o
r
m
ed
s
tate
-
of
-
th
e
-
a
r
t
ap
p
r
o
ac
h
es
ac
r
o
s
s
v
ar
io
u
s
d
atasets
.
T
h
is
h
ig
h
lig
h
ts
th
e
ef
f
icien
cy
o
f
o
u
r
s
u
g
g
ested
m
eth
o
d
o
lo
g
y
.
I
n
co
n
clu
s
io
n
,
o
u
r
wo
r
k
co
n
t
r
ib
u
te
s
v
alu
ab
le
in
s
ig
h
ts
in
t
o
th
e
f
ie
ld
o
f
f
ac
ial
em
o
tio
n
r
ec
o
g
n
itio
n
,
p
r
o
v
id
in
g
a
s
o
lid
f
o
u
n
d
atio
n
f
o
r
f
u
tu
r
e
r
esear
ch
an
d
ap
p
licatio
n
s
in
th
is
ar
ea
.
RE
F
E
R
E
NC
E
S
[
1
]
C
.
S
h
i
,
C
.
T
a
n
a
n
d
L.
W
a
n
g
,
“
A
f
a
c
i
a
l
e
x
p
r
e
ssi
o
n
r
e
c
o
g
n
i
t
i
o
n
met
h
o
d
b
a
sed
o
n
a
m
u
l
t
i
b
r
a
n
c
h
c
r
o
ss
-
c
o
n
n
e
c
t
i
o
n
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
i
n
I
EEE
Ac
c
e
ss
,
v
o
l
.
9
,
p
p
.
3
9
2
5
5
-
3
9
2
7
4
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
0
6
3
4
9
3
.
[
2
]
C
.
M
o
r
d
k
a
,
“
W
h
a
t
a
r
e
e
m
o
t
i
o
n
s
?
s
t
r
u
c
t
u
r
e
a
n
d
f
u
n
c
t
i
o
n
o
f
e
m
o
t
i
o
n
s,
”
S
t
u
d
i
a
H
u
m
a
n
a
,
v
o
l
.
5
,
n
o
.
3
,
p
p
.
2
9
–
4
4
,
S
e
p
.
2
0
1
6
,
d
o
i
:
1
0
.
1
5
1
5
/
s
h
-
2
0
1
6
-
0
0
1
3
.
[
3
]
T.
B
a
l
t
r
u
s
a
i
t
i
s,
C
.
A
h
u
j
a
,
a
n
d
L.
-
P
.
M
o
r
e
n
c
y
,
“
M
u
l
t
i
m
o
d
a
l
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
:
a
s
u
r
v
e
y
a
n
d
t
a
x
o
n
o
m
y
,
”
I
EEE
T
ra
n
sa
c
t
i
o
n
s
o
n
Pa
t
t
e
r
n
An
a
l
y
si
s
a
n
d
Ma
c
h
i
n
e
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
4
1
,
n
o
.
2
,
p
p
.
4
2
3
–
4
4
3
,
F
e
b
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
t
p
a
m
i
.
2
0
1
8
.
2
7
9
8
6
0
7
.
[
4
]
A
.
M
e
h
r
a
b
i
a
n
,
“
C
o
mm
u
n
i
c
a
t
i
o
n
w
i
t
h
o
u
t
w
o
r
d
s
,
”
i
n
C
o
m
m
u
n
i
c
a
t
i
o
n
T
h
e
o
r
y
,
R
o
u
t
l
e
d
g
e
,
2
0
1
7
,
p
p
.
1
9
3
–
2
0
0
.
[
5
]
S
.
M
i
n
a
e
e
,
M
.
M
i
n
a
e
i
,
a
n
d
A
.
A
b
d
o
l
r
a
s
h
i
d
i
,
“
D
e
e
p
-
e
m
o
t
i
o
n
:
f
a
c
i
a
l
e
x
p
r
e
ssi
o
n
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
a
t
t
e
n
t
i
o
n
a
l
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
t
w
o
r
k
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
1
,
n
o
.
9
,
p
.
3
0
4
6
,
A
p
r
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
1
0
9
3
0
4
6
.
[
6
]
C
.
D
a
r
w
i
n
,
“
Th
e
e
x
p
r
e
ssi
o
n
o
f
t
h
e
e
m
o
t
i
o
n
s
i
n
ma
n
a
n
d
a
n
i
m
a
l
s
,
”
T
h
e
Ex
p
r
e
ssi
o
n
O
f
T
h
e
Em
o
t
i
o
n
s
I
n
M
a
n
An
d
An
i
m
a
l
s
.
O
x
f
o
r
d
U
n
i
v
e
r
si
t
y
P
r
e
ssN
e
w
Y
o
r
k
,
N
Y
,
p
p
.
i
i
i
–
v
i
,
A
p
r
.
1
9
9
8
,
d
o
i
:
1
0
.
1
0
9
3
/
o
s
o
/
9
7
8
0
1
9
5
1
1
2
7
1
9
.
0
0
2
.
0
0
0
2
.
[
7
]
I
.
D
a
g
h
e
r
,
E
.
D
a
h
d
a
h
,
a
n
d
M
.
A
l
S
h
a
k
i
k
,
“
F
a
c
i
a
l
e
x
p
r
e
ssi
o
n
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
t
h
r
e
e
-
st
a
g
e
s
u
p
p
o
r
t
v
e
c
t
o
r
mac
h
i
n
e
s
,
”
Vi
s
u
a
l
C
o
m
p
u
t
i
n
g
f
o
r
I
n
d
u
s
t
ry
,
B
i
o
m
e
d
i
c
i
n
e
,
a
n
d
Art
,
v
o
l
.
2
,
n
o
.
1
,
D
e
c
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
8
6
/
s
4
2
4
9
2
-
0
1
9
-
0
0
3
4
-
5.
[
8
]
P
.
E
k
ma
n
a
n
d
W
.
V
F
r
i
e
s
e
n
,
“
C
o
n
s
t
a
n
t
s
a
c
r
o
ss
c
u
l
t
u
r
e
s
i
n
t
h
e
f
a
c
e
a
n
d
e
m
o
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
Pe
rs
o
n
a
l
i
t
y
a
n
d
S
o
c
i
a
l
Psy
c
h
o
l
o
g
y
,
v
o
l
.
1
7
,
n
o
.
2
,
p
p
.
1
2
4
–
1
2
9
,
1
9
7
1
,
d
o
i
:
1
0
.
1
0
3
7
/
h
0
0
3
0
3
7
7
.
[
9
]
P
.
E
k
ma
n
,
“
S
t
r
o
n
g
e
v
i
d
e
n
c
e
f
o
r
u
n
i
v
e
r
sal
s
i
n
f
a
c
i
a
l
e
x
p
r
e
ss
i
o
n
s
:
A
r
e
p
l
y
t
o
R
u
sse
l
l
’
s
mi
s
t
a
k
e
n
c
r
i
t
i
q
u
e
.
,
”
Psy
c
h
o
l
o
g
i
c
a
l
B
u
l
l
e
t
i
n
,
v
o
l
.
1
1
5
,
n
o
.
2
,
p
p
.
2
6
8
–
2
8
7
,
1
9
9
4
,
d
o
i
:
1
0
.
1
0
3
7
/
/
0
0
3
3
-
2
9
0
9
.
1
1
5
.
2
.
2
6
8
.
[
10
]
S
.
L
i
a
n
d
W
.
D
e
n
g
,
“
D
e
e
p
f
a
c
i
a
l
e
x
p
r
e
ssi
o
n
r
e
c
o
g
n
i
t
i
o
n
:
a
s
u
r
v
e
y
,
”
I
EE
E
T
ra
n
s
a
c
t
i
o
n
s o
n
Af
f
e
c
t
i
v
e
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
3
,
n
o
.
3
,
p
p
.
1
1
9
5
–
1
2
1
5
,
Ju
l
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
T
A
F
F
C
.
2
0
2
0
.
2
9
8
1
4
4
6
.
[
1
1
]
C
.
A
.
C
o
r
n
e
a
n
u
,
M
.
O
.
S
i
m
o
n
,
J.
F
.
C
o
h
n
,
a
n
d
S
.
E.
G
u
e
r
r
e
r
o
,
“
S
u
r
v
e
y
o
n
R
G
B
,
3
D
,
t
h
e
r
m
a
l
,
a
n
d
mu
l
t
i
m
o
d
a
l
a
p
p
r
o
a
c
h
e
s
f
o
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
37
,
No
.
2
,
Feb
r
u
a
r
y
20
25
:
9
5
9
-
9
6
7
966
f
a
c
i
a
l
e
x
p
r
e
ssi
o
n
r
e
c
o
g
n
i
t
i
o
n
:
h
i
st
o
r
y
,
t
r
e
n
d
s,
a
n
d
a
f
f
e
c
t
-
r
e
l
a
t
e
d
a
p
p
l
i
c
a
t
i
o
n
s
,
”
I
EE
E
T
ra
n
s
a
c
t
i
o
n
s
o
n
P
a
t
t
e
rn
A
n
a
l
y
s
i
s
a
n
d
Ma
c
h
i
n
e
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
3
8
,
n
o
.
8
,
p
p
.
1
5
4
8
–
1
5
6
8
,
A
u
g
.
2
0
1
6
,
d
o
i
:
1
0
.
1
1
0
9
/
t
p
a
mi
.
2
0
1
6
.
2
5
1
5
6
0
6
.
[
1
2
]
J.
-
H
.
K
i
m
,
B
.
-
G
.
K
i
m,
P
.
P
.
R
o
y
,
a
n
d
D
.
-
M
.
Je
o
n
g
,
“
Ef
f
i
c
i
e
n
t
f
a
c
i
a
l
e
x
p
r
e
s
si
o
n
r
e
c
o
g
n
i
t
i
o
n
a
l
g
o
r
i
t
h
m
b
a
s
e
d
o
n
h
i
e
r
a
r
c
h
i
c
a
l
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
st
r
u
c
t
u
r
e
,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
7
,
p
p
.
4
1
2
7
3
–
4
1
2
8
5
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
a
c
c
e
ss
.
2
0
1
9
.
2
9
0
7
3
2
7
.
[
1
3
]
N
.
U
.
K
h
a
n
,
“
A
c
o
mp
a
r
a
t
i
v
e
a
n
a
l
y
s
i
s
o
f
f
a
c
i
a
l
e
x
p
r
e
ssi
o
n
r
e
c
o
g
n
i
t
i
o
n
t
e
c
h
n
i
q
u
e
s
,
”
i
n
2
0
1
3
3
r
d
I
E
EE
I
n
t
e
r
n
a
t
i
o
n
a
l
A
d
v
a
n
c
e
C
o
m
p
u
t
i
n
g
C
o
n
f
e
re
n
c
e
(
I
AC
C
)
,
F
e
b
.
2
0
1
3
,
p
p
.
1
2
6
2
–
1
2
6
8
,
d
o
i
:
1
0
.
1
1
0
9
/
i
a
d
c
c
.
2
0
1
3
.
6
5
1
4
4
0
9
.
[
1
4
]
S
.
S
i
n
g
h
a
n
d
F
.
N
a
s
o
z
,
“
F
a
c
i
a
l
e
x
p
r
e
ssi
o
n
r
e
c
o
g
n
i
t
i
o
n
w
i
t
h
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s,
”
i
n
2
0
2
0
1
0
t
h
An
n
u
a
l
C
o
m
p
u
t
i
n
g
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
W
o
rks
h
o
p
a
n
d
C
o
n
f
e
ren
c
e
(
C
C
WC
)
,
Ja
n
.
2
0
2
0
,
p
p
.
0
3
2
4
–
0
3
2
8
,
d
o
i
:
1
0
.
1
1
0
9
/
c
c
w
c
4
7
5
2
4
.
2
0
2
0
.
9
0
3
1
2
8
3
.
[1
5
]
T.
C
o
n
n
i
e
,
M
.
A
l
-
S
h
a
b
i
,
W
.
P
.
C
h
e
a
h
,
a
n
d
M
.
G
o
h
,
“
F
a
c
i
a
l
e
x
p
r
e
ssi
o
n
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
a
h
y
b
r
i
d
C
N
N
–
S
I
F
T
a
g
g
r
e
g
a
t
o
r
,
”
i
n
Mu
l
t
i
-
d
i
sci
p
l
i
n
a
r
y
T
r
e
n
d
s
i
n
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
S
p
r
i
n
g
e
r
I
n
t
e
r
n
a
t
i
o
n
a
l
P
u
b
l
i
s
h
i
n
g
,
2
0
1
7
,
p
p
.
1
3
9
–
1
4
9
.
[1
6]
T.
Z
h
a
n
g
,
W
.
Zh
e
n
g
,
Z.
C
u
i
,
Y
.
Z
o
n
g
,
a
n
d
Y
.
L
i
,
“
S
p
a
t
i
a
l
–
t
e
m
p
o
r
a
l
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
,
”
I
E
EE
T
ra
n
s
a
c
t
i
o
n
s
o
n
C
y
b
e
rn
e
t
i
c
s
,
v
o
l
.
4
9
,
n
o
.
3
,
p
p
.
8
3
9
–
8
4
7
,
M
a
r
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
t
c
y
b
.
2
0
1
7
.
2
7
8
8
0
8
1
.
[
17
]
D
.
S
h
e
h
a
d
a
,
A
.
T
u
r
k
y
,
W
.
K
h
a
n
,
B
.
K
h
a
n
,
a
n
d
A
.
H
u
ssa
i
n
,
“
A
l
i
g
h
t
w
e
i
g
h
t
f
a
c
i
a
l
e
mo
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
s
y
st
e
m
u
si
n
g
p
a
r
t
i
a
l
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
f
o
r
v
i
su
a
l
l
y
i
m
p
a
i
r
e
d
p
e
o
p
l
e
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
3
6
9
6
1
–
3
6
9
6
9
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
a
c
c
e
ss.
2
0
2
3
.
3
2
6
4
2
6
8
.
[
18
]
G
.
X
u
a
n
d
W
.
Q
.
Y
a
n
,
“
F
a
c
i
a
l
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
e
n
s
e
mb
l
e
l
e
a
r
n
i
n
g
,
”
i
n
D
e
e
p
L
e
a
rn
i
n
g
,
Re
i
n
f
o
r
c
e
m
e
n
t
L
e
a
r
n
i
n
g
,
a
n
d
t
h
e
Ri
se
o
f
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s
,
I
G
I
G
l
o
b
a
l
,
2
0
2
4
,
p
p
.
1
4
6
–
1
5
8
.
[
19
]
Z.
U
l
l
a
h
e
t
a
l
.
,
“
Em
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
f
r
o
m
o
c
c
l
u
d
e
d
f
a
c
i
a
l
i
ma
g
e
s
u
s
i
n
g
d
e
e
p
e
n
s
e
m
b
l
e
m
o
d
e
l
,
”
C
o
m
p
u
t
e
rs
,
Ma
t
e
r
i
a
l
s
&
a
m
p
;
C
o
n
t
i
n
u
a
,
v
o
l
.
7
3
,
n
o
.
3
,
p
p
.
4
4
6
5
–
4
4
8
7
,
2
0
2
2
,
d
o
i
:
1
0
.
3
2
6
0
4
/
c
mc
.
2
0
2
2
.
0
2
9
1
0
1
.
[
2
0
]
C
.
J
i
a
,
C
.
L
.
L
i
,
a
n
d
Z
.
Y
i
n
g
,
“
F
a
c
i
a
l
e
x
p
r
e
s
s
i
o
n
r
e
c
o
g
n
i
t
i
o
n
b
a
s
e
d
o
n
t
h
e
e
n
s
e
m
b
l
e
l
e
a
r
n
i
n
g
o
f
C
N
N
s
,
”
i
n
2
0
2
0
I
E
E
E
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
S
i
g
n
a
l
P
r
o
c
e
s
s
i
n
g
,
C
o
m
m
u
n
i
c
a
t
i
o
n
s
a
n
d
C
o
m
p
u
t
i
n
g
(
I
C
S
P
C
C
)
,
2
0
2
0
,
p
p
.
1
–
5
,
d
o
i
:
1
0
.
1
1
0
9
/
i
c
s
p
c
c
5
0
0
0
2
.
2
0
2
0
.
9
2
5
9
5
4
3
.
[
2
1
]
H.
-
D
.
N
g
u
y
e
n
,
S
.
-
H
.
K
i
m,
G
.
-
S
.
L
e
e
,
H
.
-
J.
Y
a
n
g
,
I
.
-
S
.
N
a
,
a
n
d
S
.
-
H
.
K
i
m
,
“
F
a
c
i
a
l
e
x
p
r
e
ssi
o
n
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
a
t
e
m
p
o
r
a
l
e
n
s
e
mb
l
e
o
f
m
u
l
t
i
-
l
e
v
e
l
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s,
”
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
Af
f
e
c
t
i
v
e
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
3
,
n
o
.
1
,
p
p
.
2
2
6
–
2
3
7
,
Jan
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
t
a
f
f
c
.
2
0
1
9
.
2
9
4
6
5
4
0
.
[
2
2
]
Y
.
F
a
n
,
J
.
C
.
K
.
La
m,
a
n
d
V
.
O
.
K
.
L
i
,
“
M
u
l
t
i
-
r
e
g
i
o
n
e
n
sem
b
l
e
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
f
a
c
i
a
l
e
x
p
r
e
s
si
o
n
r
e
c
o
g
n
i
t
i
o
n
,
”
i
n
Art
i
f
i
c
i
a
l
N
e
u
r
a
l
N
e
t
w
o
r
k
s
a
n
d
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
–
I
C
AN
N
2
0
1
8
,
S
p
r
i
n
g
e
r
I
n
t
e
r
n
a
t
i
o
n
a
l
P
u
b
l
i
s
h
i
n
g
,
2
0
1
8
,
p
p
.
8
4
–
9
4
.
[
2
3
]
P
.
H
u
,
D
.
C
a
i
,
S
.
W
a
n
g
,
A
.
Y
a
o
,
a
n
d
Y
.
C
h
e
n
,
“
Le
a
r
n
i
n
g
su
p
e
r
v
i
s
e
d
s
c
o
r
i
n
g
e
n
s
e
m
b
l
e
f
o
r
e
mo
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
i
n
t
h
e
w
i
l
d
,
”
N
o
v
.
2
0
1
7
,
d
o
i
:
1
0
.
1
1
4
5
/
3
1
3
6
7
5
5
.
3
1
4
3
0
0
9
.
[
2
4
]
E.
B
i
s
o
n
g
,
“
G
o
o
g
l
e
C
o
l
a
b
o
r
a
t
o
r
y
,
”
i
n
B
u
i
l
d
i
n
g
M
a
c
h
i
n
e
L
e
a
rn
i
n
g
a
n
d
D
e
e
p
L
e
a
rn
i
n
g
M
o
d
e
l
s
o
n
G
o
o
g
l
e
C
l
o
u
d
Pl
a
t
f
o
rm
,
A
p
r
e
ss,
2
0
1
9
,
p
p
.
5
9
–
6
4
.
[
2
5
]
S
.
R
a
sc
h
k
a
a
n
d
V
.
M
i
r
j
a
l
i
l
i
,
“
P
y
t
h
o
n
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
:
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
w
i
t
h
p
y
t
h
o
n
,
sci
k
i
t
-
l
e
a
r
n
,
a
n
d
t
e
n
so
r
f
l
o
w
,
”
P
a
c
k
t
Pu
b
l
i
s
h
i
n
g
L
t
d
,
2
0
1
9
.
[2
6
]
D
.
L
u
n
d
q
v
i
s
t
,
A
.
F
l
y
k
t
,
a
n
d
A
.
Ö
h
man
,
“
K
a
r
o
l
i
n
s
k
a
d
i
r
e
c
t
e
d
e
mo
t
i
o
n
a
l
f
a
c
e
s,
”
Psy
c
T
ES
T
S
D
a
t
a
s
e
t
.
A
m
e
r
i
c
a
n
P
s
y
c
h
o
l
o
g
i
c
a
l
A
sso
c
i
a
t
i
o
n
(
A
P
A
)
,
1
9
9
8
,
d
o
i
:
1
0
.
1
0
3
7
/
t
2
7
7
3
2
-
0
0
0
.
[
27
]
S
.
S
.
A
l
i
,
J
.
H
.
A
l
’
A
m
e
r
i
,
a
n
d
T
.
A
b
b
a
s
,
“
F
a
c
e
d
e
t
e
c
t
i
o
n
u
s
i
n
g
h
a
a
r
c
a
s
c
a
d
e
a
l
g
or
i
t
h
m
,
”
i
n
2
0
2
2
F
i
f
t
h
C
o
l
l
e
g
e
o
f
S
c
i
e
n
c
e
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
f
R
e
c
e
n
t
T
r
e
n
d
s
i
n
I
n
f
o
r
m
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
2
0
2
2
,
p
p
.
1
9
8
–
2
0
1
,
d
o
i
:
1
0
.
1
1
0
9
/
c
s
c
t
i
t
5
6
2
9
9
.
2
0
2
2
.
1
0
1
4
5
6
8
0
.
[
28
]
P
.
V
i
o
l
a
a
n
d
M
.
J.
Jo
n
e
s,
“
R
o
b
u
st
r
e
a
l
-
t
i
me
f
a
c
e
d
e
t
e
c
t
i
o
n
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
C
o
m
p
u
t
e
r
Vi
s
i
o
n
,
v
o
l
.
5
7
,
n
o
.
2
,
p
p
.
1
3
7
–
1
5
4
,
M
a
y
2
0
0
4
,
d
o
i
:
1
0
.
1
0
2
3
/
b
:
v
i
si
.
0
0
0
0
0
1
3
0
8
7
.
4
9
2
6
0
.
f
b
.
[
29
]
I
.
C
u
l
j
a
k
,
D
.
A
b
r
a
m,
T
.
P
r
i
b
a
n
i
c
,
H
.
D
z
a
p
o
,
a
n
d
M
.
C
i
f
r
e
k
,
“
A
b
r
i
e
f
i
n
t
r
o
d
u
c
t
i
o
n
t
o
O
p
e
n
C
V
,
”
2
0
1
2
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
3
5
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
v
e
n
t
i
o
n
MIPRO
,
p
p
.
1
7
2
5
–
1
7
3
0
,
2
0
1
2
.
[
3
0
]
C
.
S
h
u
,
X
.
D
i
n
g
,
a
n
d
C
.
F
a
n
g
,
“
H
i
st
o
g
r
a
m
o
f
t
h
e
o
r
i
e
n
t
e
d
g
r
a
d
i
e
n
t
f
o
r
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
,
”
T
si
n
g
h
u
a
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
6
,
n
o
.
2
,
p
p
.
2
1
6
–
2
2
4
,
A
p
r
.
2
0
1
1
,
d
o
i
:
1
0
.
1
0
1
6
/
s1
0
0
7
-
0
2
1
4
(
1
1
)
7
0
0
3
2
-
3.
[3
1
]
S
.
K
i
r
a
n
y
a
z
,
O
.
A
v
c
i
,
O
.
A
b
d
e
l
j
a
b
e
r
,
T.
I
n
c
e
,
M
.
G
a
b
b
o
u
j
,
a
n
d
D
.
J
.
I
n
ma
n
,
“
1
D
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
a
n
d
a
p
p
l
i
c
a
t
i
o
n
s
:
A
su
r
v
e
y
,
”
Me
c
h
a
n
i
c
a
l
S
y
s
t
e
m
s
a
n
d
S
i
g
n
a
l
Pro
c
e
ss
i
n
g
,
v
o
l
.
1
5
1
,
p
.
1
0
7
3
9
8
,
A
p
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
y
mss
p
.
2
0
2
0
.
1
0
7
3
9
8
.
[
3
2
]
D
.
P
.
K
i
n
g
ma
a
n
d
J.
B
a
,
“
A
d
a
m
:
A
m
e
t
h
o
d
f
o
r
st
o
c
h
a
st
i
c
o
p
t
i
mi
z
a
t
i
o
n
,
”
a
r
Xi
v
p
r
e
p
r
i
n
t
a
rX
i
v
:
1
4
1
2
.
6
9
8
0
,
2
0
1
4
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Vir
a
j
Vila
s
S
a
w
a
n
t
h
a
s
p
u
rsu
e
d
Ba
c
h
e
lo
r
o
f
E
n
g
i
n
e
e
rin
g
(B.
E.
)
fro
m
Un
iv
e
rsity
o
f
M
u
m
b
a
i
in
th
e
fiel
d
o
f
In
f
o
rm
a
ti
o
n
Tec
h
n
o
lo
g
y
.
He
h
a
s
a
m
u
lt
i
fa
c
e
ted
in
tere
st
in
a
rti
ficia
l
in
telli
g
e
n
c
e
(AI),
d
y
n
a
m
ic
p
ro
g
ra
m
m
in
g
,
we
b
d
e
v
e
l
o
p
m
e
n
t
,
a
n
d
c
h
e
ss
.
Ad
d
i
ti
o
n
a
ll
y
,
h
e
a
c
ti
v
e
ly
e
n
g
a
g
e
s
in
h
o
n
i
n
g
h
is
p
ro
b
lem
-
so
lv
i
n
g
s
k
il
ls
a
c
ro
ss
v
a
rio
u
s
d
o
m
a
in
s.
He
a
lso
p
a
rti
c
ip
a
tes
in
m
u
l
ti
p
le
h
a
c
k
a
th
o
n
s
a
n
d
c
o
d
in
g
c
o
m
p
e
ti
ti
o
n
s.
He
a
lso
is
a
c
ti
v
e
ly
e
n
g
a
g
e
d
i
n
Ka
g
g
le co
m
p
e
ti
ti
o
n
s
f
o
r
f
u
n
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sa
wa
n
tv
iraj4
6
5
@g
m
a
il
.
c
o
m
.
H
u
sna
S
h
e
h
wa
r
S
h
a
i
k
h
c
o
m
p
lete
d
h
e
r
Ba
c
h
e
lo
r
o
f
En
g
i
n
e
e
rin
g
(B.
E
.
)
in
In
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
fr
o
m
M
.
H.
S
a
b
o
o
S
id
d
ik
Co
ll
e
g
e
o
f
En
g
i
n
e
e
rin
g
.
S
h
e
is
d
e
e
p
l
y
in
tere
ste
d
in
th
e
fiel
d
s
o
f
d
a
ta
sc
ien
c
e
,
d
a
ta
a
n
a
ly
ti
c
s,
a
n
d
c
lo
u
d
c
o
m
p
u
t
in
g
.
Hu
sn
a
is
d
e
d
ica
ted
to
c
o
n
ti
n
u
o
u
sl
y
e
n
h
a
n
c
in
g
h
e
r
sk
il
ls
a
n
d
k
n
o
wle
d
g
e
i
n
t
h
e
se
a
re
a
s,
h
o
ld
in
g
se
v
e
ra
l
c
e
rti
fica
ti
o
n
s
th
a
t
d
e
m
o
n
stra
te
h
e
r
e
x
p
e
rti
se
a
n
d
c
o
m
m
it
m
e
n
t
t
o
p
r
o
fe
ss
io
n
a
l
g
r
o
wth
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
at
e
m
a
il
:
h
u
s
n
a
s2
9
3
3
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
n
o
ve
l CN
N
-
A
N
N
fu
s
io
n
a
p
p
r
o
a
ch
fo
r
imp
r
o
ve
d
fa
cia
l e
m
o
tio
n
d
etec
tio
n
(
V
ir
a
j S
a
w
a
n
t
)
967
Dr
.
Bh
a
k
t
i
P
a
lk
a
r
is
a
d
i
stin
g
u
ish
e
d
a
c
a
d
e
m
ic
a
n
d
p
r
o
fe
ss
io
n
a
l
a
ss
o
c
iate
d
with
K.
J.
S
o
m
a
iy
a
Co
ll
e
g
e
o
f
En
g
i
n
e
e
rin
g
,
S
o
m
a
iy
a
Vi
d
y
a
v
i
h
a
r
Un
iv
e
rsity
,
M
u
m
b
a
i
.
S
h
e
h
o
l
d
s
P
h
.
D.
i
n
Co
m
p
u
ter
E
n
g
in
e
e
rin
g
.
S
h
e
is
wo
rk
in
g
a
s
a
n
As
so
c
iate
P
ro
fe
ss
o
r
a
t
K.J.S
o
m
a
iy
a
Co
ll
e
g
e
o
f
En
g
in
e
e
r
i
n
g
.
He
r
re
se
a
rc
h
in
tere
sts in
c
lu
d
e
m
e
d
ica
l
im
a
g
e
p
ro
c
e
ss
in
g
,
G
e
o
g
ra
p
h
ic
In
f
o
rm
a
ti
o
n
S
y
ste
m
a
n
d
S
e
n
ti
m
e
n
t
An
a
ly
sis.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
at
e
m
a
il
:
b
h
a
k
t
irau
l@so
m
a
iy
a
.
e
d
u
.
Pro
f.
S
a
n
a
m
S
a
l
m
a
n
K
a
z
i
h
o
l
d
s
a
m
a
ste
r
d
e
g
re
e
in
En
g
i
n
e
e
rin
g
(M
.
E.
)
i
n
In
fo
rm
a
ti
o
n
Tec
h
n
o
lo
g
y
.
S
h
e
is
c
u
rre
n
tl
y
p
u
rsin
g
P
h
.
D
.
fro
m
S
o
m
a
iy
a
Vid
y
a
v
i
h
a
r
u
n
iv
e
rsit
y
,
M
u
m
b
a
i,
In
d
ia.
S
h
e
is
wo
rk
in
g
a
s
a
n
As
sista
n
t
P
ro
fe
ss
o
r
in
th
e
De
p
a
rtme
n
t
o
f
En
g
i
n
e
e
rin
g
a
n
d
Tec
h
n
o
lo
g
y
a
t
Bh
a
ra
ti
Vid
y
a
p
e
e
th
De
e
m
e
d
to
b
e
Un
iv
e
rsity
.
S
h
e
h
a
s
m
e
n
to
re
d
p
ro
jec
ts
li
k
e
Ra
il
wa
y
S
a
fe
ty
Ap
p
li
c
a
ti
o
n
fo
r
wo
m
e
n
a
n
d
b
a
g
g
e
d
a
p
rice
in
S
m
a
rt
I
n
d
ia
Ha
c
k
a
th
o
n
2
0
1
7
.
S
h
e
h
a
s
re
v
iew
e
d
p
a
p
e
rs
in
in
tern
a
t
io
n
a
l
c
o
n
fe
re
n
c
e
s.
He
r
re
se
a
rc
h
in
tere
st
is
a
rti
ficia
l
In
telli
g
e
n
c
e
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
at
e
m
a
il
:
sa
n
a
m
.
k
a
z
i1
9
@g
m
a
il
.
c
o
m
.
Wa
sim
J
a
sa
n
i
c
o
m
p
lete
d
h
i
s
B.
E.
in
In
f
o
rm
a
ti
o
n
Tec
h
n
o
lo
g
y
.
He
is
a
c
ti
v
e
ly
in
tere
ste
d
i
n
t
h
e
fiel
d
o
f
Artif
i
c
ial
In
telli
g
e
n
c
e
a
n
d
is
c
u
rre
n
tl
y
p
u
rsu
in
g
a
c
a
re
e
r
in
it
.
Was
im
h
a
s
p
a
rti
c
ip
a
ted
in
m
u
lt
i
p
le
c
o
m
p
e
ti
ti
o
n
s
a
n
d
h
a
c
k
a
t
h
o
n
s,
sh
o
wc
a
sin
g
h
is
sk
i
ll
s
a
n
d
c
o
m
p
e
ti
ti
v
e
s
p
iri
t.
He
c
o
n
ti
n
u
o
u
s
ly
b
u
il
d
s
v
a
rio
u
s
p
r
o
jec
ts
to
c
h
a
l
len
g
e
h
ims
e
lf
a
n
d
a
d
v
a
n
c
e
h
is
k
n
o
wle
d
g
e
i
n
Art
ifi
c
ial
In
telli
g
e
n
c
e
.
He
c
a
n
b
e
c
o
n
tac
ted
at
e
m
a
il
:
jas
a
n
iwa
sim
2
0
0
2
@
g
m
a
il
.
c
o
m
.
La
m
i
y
a
Ra
m
p
u
r
a
w
a
la
is
a
B.
Tec
h
st
u
d
e
n
t
p
u
rsu
i
n
g
a
d
e
g
r
e
e
in
In
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
.
S
h
e
h
a
s
a
stro
n
g
i
n
tere
st
in
a
rti
ficia
l
i
n
telli
g
e
n
c
e
(AI)
a
n
d
m
a
c
h
in
e
lea
rn
i
n
g
(M
L).
Lam
iy
a
h
a
s
g
a
in
e
d
p
ra
c
ti
c
a
l
e
x
p
e
rien
c
e
b
y
wo
rk
i
n
g
o
n
a
n
e
-
c
o
m
m
e
rc
e
b
o
o
k
se
ll
in
g
we
b
site
u
sin
g
P
y
t
h
o
n
a
n
d
D
jan
g
o
,
a
n
d
d
e
v
e
lo
p
in
g
a
h
u
m
a
n
d
e
tec
ti
o
n
sy
ste
m
with
Ten
so
r
F
lo
w
a
n
d
YO
LOv
8
.
S
h
e
is
p
a
ss
io
n
a
te
a
b
o
u
t
a
d
v
a
n
c
i
n
g
in
AI
a
n
d
M
L
a
n
d
is
c
o
m
m
it
ted
to
e
x
p
lo
ri
n
g
in
n
o
v
a
ti
v
e
so
lu
ti
o
n
s
in
th
e
se
field
s.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
emai
:
ra
m
p
u
ra
wa
ll
a
m
iy
a
@g
m
a
il
.
c
o
m
Mo
h
a
m
m
e
d
Na
se
r
S
h
a
i
k
h
re
c
e
n
tl
y
g
ra
d
u
a
te
d
wit
h
a
Ba
c
h
e
lo
r
o
f
E
n
g
i
n
e
e
rin
g
i
n
In
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
fro
m
M
u
m
b
a
i
Un
i
v
e
rsity
.
D
u
rin
g
h
is
a
c
a
d
e
m
ic
c
a
re
e
r,
h
e
sp
e
c
ialize
d
in
Artifi
c
ial
In
telli
g
e
n
c
e
(AI)
a
n
d
UX
De
sig
n
.
I
n
a
d
d
it
io
n
t
o
h
is
a
c
a
d
e
m
ic
a
c
h
iev
e
m
e
n
ts,
h
e
h
a
s
c
o
m
p
lete
d
in
ter
n
sh
i
p
s
a
t
Dr
.
Ba
las
a
h
e
b
Ko
n
k
a
n
Kris
h
i
Vi
d
y
a
p
e
e
th
a
n
d
Zen
tec
h
S
y
ste
m
s,
wh
e
re
h
e
g
a
in
e
d
h
a
n
d
s
-
o
n
e
x
p
e
ri
e
n
c
e
in
so
ftwa
re
e
n
g
i
n
e
e
rin
g
a
n
d
IT
c
o
n
su
lt
in
g
.
M
o
h
a
m
m
e
d
Na
se
r
is
p
a
ss
io
n
a
te
a
b
o
u
t
lev
e
ra
g
in
g
tec
h
n
o
lo
g
y
to
so
l
v
e
c
o
m
p
lex
p
ro
b
l
e
m
s
a
n
d
is
d
e
d
ica
ted
to
c
o
n
ti
n
u
o
u
s
lea
rn
in
g
a
n
d
p
r
o
fe
ss
io
n
a
l
d
e
v
e
lo
p
m
e
n
t.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
o
h
a
m
m
e
d
n
a
se
r1
5
7
2
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.