I
nte
rna
t
io
na
l J
o
urna
l o
f
Rec
o
nfig
ura
ble a
nd
E
m
be
dd
e
d Sy
s
t
e
m
s
(
I
J
R
E
S)
Vo
l.
13
,
No
.
3
,
N
o
v
e
m
b
er
20
24
,
p
p
.
7
6
7
~
7
7
3
I
SS
N:
2089
-
4864
,
DOI
:
1
0
.
1
1
5
9
1
/i
j
r
es
.
v
13
.
i
3
.
pp
7
6
7
-
773
767
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
r
es.ia
esco
r
e.
co
m
Lev
erag
ing
t
he le
a
rning
f
o
ca
l poin
t
alg
o
rith
m
f
o
r e
mo
tiona
l
intelligence
Sa
la
h
E
dd
i
ne
M
a
ns
o
ur
1
,
Abdelh
a
k
Sa
k
h
i
1
,
L
a
rbi K
za
z
2
,
Abderra
hi
m
Se
kk
a
ki
1
1
El
e
c
t
r
i
c
a
l
a
n
d
I
n
d
u
st
r
i
a
l
E
n
g
i
n
e
e
r
i
n
g
I
n
f
o
r
mat
i
o
n
P
r
o
c
e
ssi
n
g
I
T
a
n
d
L
o
g
i
st
i
cs
(
G
E
I
I
L
)
,
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
s A
i
n
C
h
o
c
k
,
H
a
ssan
I
I
U
n
i
v
e
r
si
t
y
,
C
a
sa
b
l
a
n
c
a
,
M
o
r
o
c
c
o
2
D
e
H
i
g
h
e
r
I
n
st
i
t
u
t
e
o
f
C
o
mm
e
r
c
e
a
n
d
B
u
s
i
n
e
ss A
d
mi
n
i
st
r
a
t
i
o
n
,
H
a
ssa
n
I
I
U
n
i
v
e
r
si
t
y
,
C
a
s
a
b
l
a
n
c
a
,
M
o
r
o
c
c
o
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
No
v
1
7
,
2
0
2
3
R
ev
i
s
ed
J
an
2
6
,
2
0
2
4
A
cc
ep
ted
Feb
2
,
2
0
2
4
On
e
o
f
th
e
se
c
re
ts
o
f
th
e
su
c
c
e
ss
o
f
th
e
e
d
u
c
a
ti
o
n
p
r
o
c
e
ss
is
tak
in
g
in
to
a
c
c
o
u
n
t
th
e
lea
rn
e
r’s
f
e
e
li
n
g
s.
T
h
a
t
is,
t
h
e
tea
c
h
e
r
m
u
st
b
e
c
h
a
ra
c
teriz
e
d
b
y
h
ig
h
e
m
o
ti
o
n
a
l
i
n
telli
g
e
n
c
e
(
EI
)
t
o
u
n
d
e
rsta
n
d
th
e
st
u
d
e
n
t’s
f
e
e
li
n
g
s
in
o
r
d
e
r
to
f
a
c
il
it
a
te
th
e
in
d
o
c
tr
in
a
ti
o
n
p
r
o
c
e
ss
f
o
r
h
im
.
W
it
h
in
th
e
f
ra
m
e
w
o
rk
o
f
th
e
p
ro
jec
t
to
c
re
a
te
a
ro
b
o
t
tea
c
h
e
r,
we
h
a
d
to
a
d
d
t
h
is
f
e
a
tu
re
b
e
c
a
u
se
o
f
it
s
im
p
o
rtan
c
e
.
In
th
is
a
rti
c
le,
w
e
c
re
a
te
a
c
o
m
p
u
ter
a
p
p
li
c
a
ti
o
n
th
a
t
c
las
si
f
ies
stu
d
e
n
ts'
e
m
o
ti
o
n
s
b
a
se
d
o
n
d
e
e
p
lea
rn
in
g
a
n
d
le
a
rn
i
n
g
f
o
c
a
l
p
o
in
t
(L
F
P
)
a
lg
o
rit
h
m
b
y
a
n
a
l
y
z
in
g
f
a
c
ial
e
x
p
re
ss
io
n
s.
T
h
a
t
is,
t
h
e
ro
b
o
t
w
il
l
b
e
a
b
le
t
o
k
n
o
w
w
h
e
th
e
r
th
e
stu
d
e
n
t
is
h
a
p
p
y
,
e
x
c
it
e
d
,
o
r
sa
d
i
n
o
r
d
e
r
t
o
d
e
a
l
w
it
h
h
im
a
p
p
ro
p
riate
ly
.
K
ey
w
o
r
d
s
:
C
o
n
v
o
lu
tio
n
al
n
e
u
r
al
n
e
t
w
o
r
k
E
m
o
tio
n
al
i
n
telli
g
e
n
ce
L
ea
r
n
i
n
g
f
o
ca
l p
o
in
t
al
g
o
r
ith
m
Neu
r
al
n
et
w
o
r
k
P
er
ce
p
tr
o
n
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
:
Salah
E
d
d
in
e
Ma
n
s
o
u
r
E
lectr
ical
an
d
I
n
d
u
s
tr
ial
E
n
g
i
n
ee
r
in
g
I
n
f
o
r
m
a
tio
n
P
r
o
ce
s
s
in
g
I
T
an
d
lo
g
is
tics
(
GE
I
I
L
)
Facu
lt
y
o
f
s
cien
ce
s
A
i
n
C
h
o
ck
,
Hass
an
I
I
Un
iv
er
s
it
y
C
asab
lan
ca
,
Mo
r
o
cc
o
E
m
ail: 1
9
m
a
n
s
o
u
r
9
4
@
g
m
ail.
c
o
m
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
m
ai
n
te
x
t
i
n
t
h
e
er
a
o
f
r
ap
id
tech
n
o
lo
g
ica
l
p
r
o
g
r
ess
,
th
e
f
u
s
io
n
o
f
ar
tif
icia
l
in
te
lli
g
en
ce
(
A
I
)
,
an
d
r
o
b
o
tics
is
r
esh
ap
in
g
v
ar
io
u
s
asp
ec
ts
o
f
o
u
r
liv
es.
O
n
e
ar
ea
w
h
er
e
t
h
is
co
n
v
er
g
e
n
ce
h
o
ld
s
en
o
r
m
o
u
s
p
r
o
m
i
s
e
is
ed
u
ca
tio
n
.
T
h
is
r
esear
c
h
i
s
an
in
te
g
r
al
p
ar
t
o
f
a
co
m
p
r
eh
en
s
i
v
e
i
n
itia
tiv
e
ai
m
ed
at
f
o
r
m
u
lati
n
g
a
n
d
i
m
p
r
o
v
i
n
g
t
h
e
p
io
n
ee
r
in
g
teac
h
er
r
o
b
o
t,
w
h
ic
h
is
an
ad
v
a
n
ce
d
co
m
b
i
n
atio
n
o
f
AI
an
d
i
m
ag
e
p
r
o
ce
s
s
i
n
g
tech
n
o
lo
g
ies.
T
h
e
p
r
i
m
ar
y
f
o
c
u
s
o
f
o
u
r
r
esear
ch
is
to
h
ar
n
e
s
s
th
e
p
o
w
er
o
f
AI
to
p
r
o
v
id
e
r
o
b
o
t
teac
h
er
s
w
ith
e
m
o
tio
n
al
i
n
tell
ig
e
n
c
e
(
E
I
)
,
w
h
ich
is
o
f
g
r
ea
t
i
m
p
o
r
ta
n
ce
in
th
e
teac
h
in
g
p
r
o
ce
s
s
[
1
]
.
T
h
er
ef
o
r
e,
o
u
r
r
o
b
o
t
h
as
to
class
i
f
y
a
s
t
u
d
en
t
'
s
e
m
o
tio
n
s
b
y
an
al
y
zi
n
g
h
is
f
ac
ial
e
x
p
r
ess
io
n
s
.
Un
d
er
s
ta
n
d
in
g
t
h
e
cr
itical
r
o
le
o
f
E
I
in
ed
u
ca
tio
n
u
n
v
eil
s
a
p
r
o
f
o
u
n
d
co
n
n
ec
tio
n
b
et
w
ee
n
a
teac
h
er
'
s
ab
ilit
y
to
co
n
v
e
y
i
n
f
o
r
m
atio
n
an
d
a
s
tu
d
en
t
's
ca
p
ac
it
y
to
c
o
m
p
r
e
h
en
d
an
d
en
g
a
g
e
w
it
h
i
t.
T
h
e
d
y
n
a
m
ics
o
f
lear
n
in
g
ex
te
n
d
b
ey
o
n
d
th
e
m
er
e
tr
an
s
m
is
s
io
n
o
f
f
ac
t
s
;
t
h
e
y
ar
e
d
ee
p
ly
in
ter
t
w
i
n
ed
w
it
h
th
e
e
m
o
t
io
n
al
lan
d
s
ca
p
e
w
it
h
in
t
h
e
clas
s
r
o
o
m
[
2
]
,
[
3
]
.
E
x
p
lo
r
in
g
th
e
s
i
g
n
i
f
ica
n
ce
o
f
E
I
in
ed
u
ca
to
r
s
o
f
f
er
s
a
p
r
o
f
o
u
n
d
in
s
i
g
h
t
i
n
to
h
o
w
t
h
e
m
aster
y
o
f
e
m
o
tio
n
s
s
h
ap
e
s
t
h
e
le
ar
n
in
g
e
n
v
ir
o
n
m
en
t,
in
f
l
u
en
c
es
s
t
u
d
en
t
-
teac
h
er
in
ter
ac
tio
n
s
,
an
d
u
l
ti
m
atel
y
i
m
p
ac
ts
th
e
ab
s
o
r
p
tio
n
an
d
r
eten
t
io
n
o
f
k
n
o
w
led
g
e
[
4
]
.
I
n
th
i
s
w
o
r
k
,
w
e
h
av
e
cr
ea
ted
a
s
y
s
te
m
w
h
ic
h
m
a
k
e
th
e
teac
h
er
r
o
b
o
t
h
as
th
e
e
m
o
tio
n
al
i
n
tellig
e
n
ce
.
W
e
tr
ied
u
s
in
g
co
n
v
o
l
u
tio
n
al
n
eu
r
al
n
et
w
o
r
k
(
C
NN
)
w
it
h
p
o
o
lin
g
la
y
er
s
,
b
u
t
th
e
r
es
u
lt
s
w
er
e
n
o
t
s
at
is
f
ac
to
r
y
en
o
u
g
h
.
T
h
er
ef
o
r
e,
w
e
co
n
d
u
cted
an
o
th
er
e
x
p
er
i
m
e
n
t
b
y
r
ep
lacin
g
th
e
p
o
o
lin
g
la
y
er
s
with
a
lear
n
i
n
g
f
o
ca
l
p
o
in
t
(
L
FP
)
la
y
er
,
an
d
th
e
r
esu
lt
s
w
er
e
m
u
c
h
b
etter
t
h
an
t
h
e
f
ir
s
t
ex
p
er
i
m
en
t
b
y
co
m
p
a
r
in
g
ac
cu
r
ac
y
a
n
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4864
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
,
Vo
l.
13
,
No
.
3
,
No
v
e
m
b
er
20
24
:
767
-
7
73
768
o
th
er
p
ar
am
eter
s
.
Usi
n
g
t
h
e
L
FP
la
y
er
i
n
s
tead
o
f
la
y
er
p
o
o
lin
g
i
s
ex
ac
t
l
y
o
u
r
s
cie
n
ti
f
ic
co
n
tr
ib
u
tio
n
i
n
th
is
r
esear
ch
an
d
w
h
a
t
w
e
w
ill d
is
cu
s
s
in
t
h
e
r
est o
f
t
h
i
s
ar
ticle.
B
y
r
esear
ch
i
n
g
th
e
m
et
h
o
d
s
u
s
ed
in
AI
to
class
i
f
y
e
m
o
tio
n
s
th
r
o
u
g
h
f
ac
ial
ex
p
r
ess
io
n
s
,
w
e
f
o
u
n
d
th
at
m
o
s
t
o
f
t
h
e
m
r
el
y
o
n
d
ee
p
lear
n
in
g
t
h
r
o
u
g
h
tr
ai
n
i
n
g
n
eu
r
al
n
et
w
o
r
k
s
.
T
h
is
m
ea
n
s
th
at
t
h
er
e
ar
e
o
n
l
y
in
n
o
v
atio
n
s
i
n
d
ee
p
lear
n
in
g
a
r
ch
itect
u
r
e.
O
n
e
o
f
t
h
e
m
o
s
t u
s
ed
ar
ch
itect
u
r
al
s
tr
u
ct
u
r
es i
n
f
ac
ial
r
ec
o
g
n
itio
n
is
th
e
C
NN,
b
ec
au
s
e
w
e
f
in
d
m
an
y
s
o
lu
tio
n
s
a
n
d
f
r
a
m
e
w
o
r
k
s
s
u
c
h
as
Dee
p
Face
,
Face
Net,
L
i
g
h
tC
NN,
an
d
o
th
er
s
th
at
r
el
y
o
n
C
NN
w
h
ic
h
in
tu
r
n
r
ela
y
s
o
n
p
o
o
lin
g
lay
er
s
[
5
]
.
P
o
o
lin
g
h
elp
s
to
m
a
n
ag
e
co
m
p
u
tatio
n
al
r
eso
u
r
ce
s
,
r
ed
u
ce
th
e
n
u
m
b
er
o
f
p
ar
am
eter
s
,
an
d
f
o
c
u
s
o
n
th
e
m
o
s
t
i
m
p
o
r
tan
t
f
ea
t
u
r
es
in
t
h
e
d
ata.
C
NNs
h
av
e
p
r
o
v
en
h
i
g
h
l
y
ef
f
ec
ti
v
e
i
n
v
ar
io
u
s
co
m
p
u
ter
v
i
s
io
n
tas
k
s
d
u
e
to
th
eir
ab
ilit
y
to
au
to
m
at
icall
y
lear
n
h
ier
ar
ch
ical
r
ep
r
esen
tatio
n
s
o
f
f
ea
tu
r
es
f
r
o
m
i
n
p
u
t
d
ata
[
6
]
.
C
NNs
d
er
iv
e
th
e
ir
n
a
m
e
f
r
o
m
th
e
co
n
v
o
lu
tio
n
al
la
y
er
s
,
w
h
ic
h
ap
p
l
y
f
il
ter
s
o
r
k
er
n
el
s
to
t
h
e
i
n
p
u
t
d
ata.
T
h
ese
f
il
ter
s
s
l
id
e
o
v
er
t
h
e
i
n
p
u
t,
ca
p
tu
r
i
n
g
lo
ca
l
p
atter
n
s
an
d
f
ea
t
u
r
es
[
7
]
.
T
h
e
r
esu
lt
is
a
f
ea
tu
r
e
m
ap
th
at
h
ig
h
lig
h
t
s
r
elev
a
n
t
s
tr
u
ctu
r
e
s
in
th
e
i
n
p
u
t.
Am
o
n
g
th
e
co
r
e
co
m
p
o
n
e
n
ts
u
s
ed
in
C
NN,
p
o
o
lin
g
la
y
er
s
p
la
y
a
cr
u
cial
r
o
le
in
r
ed
u
cin
g
th
e
s
p
ati
al
d
im
e
n
s
io
n
ali
t
y
o
f
th
e
i
n
p
u
t
d
ata,
w
h
ich
h
elp
s
co
n
tr
o
l
h
e
n
et
w
o
r
k
'
s
co
m
p
u
ta
tio
n
al
co
m
p
le
x
it
y
,
a
n
d
p
ar
a
m
eter
co
u
n
t
[
8
]
.
P
o
o
lin
g
is
a
d
o
w
n
-
s
a
m
p
li
n
g
p
r
o
ce
s
s
a
p
p
lied
af
ter
co
n
v
o
lu
tio
n
a
l
la
y
er
s
to
r
etain
ess
en
t
ial
in
f
o
r
m
a
tio
n
w
h
i
le
r
ed
u
cin
g
s
p
atial
r
eso
lu
tio
n
.
T
h
er
e
ar
e
t
w
o
co
m
m
o
n
t
y
p
e
s
o
f
p
o
o
lin
g
la
y
er
s
:
m
ax
p
o
o
lin
g
an
av
er
a
g
e
p
o
o
lin
g
[
9
]
.
Ma
x
p
o
o
lin
g
is
a
p
o
p
u
lar
p
o
o
lin
g
t
ec
h
n
iq
u
e
th
at
s
e
lects
t
h
e
m
a
x
i
m
u
m
v
alu
e
f
r
o
m
a
g
r
o
u
p
o
f
n
eig
h
b
o
r
in
g
p
ix
el
s
in
th
e
i
n
p
u
t.
T
h
e
id
ea
is
to
r
et
ain
t
h
e
m
o
s
t
i
m
p
o
r
tan
t
f
ea
t
u
r
es
an
d
r
ed
u
ce
t
h
e
s
p
atial
d
i
m
en
s
io
n
s
.
Av
er
ag
e
p
o
o
lin
g
co
m
p
u
te
s
t
h
e
av
er
ag
e
v
alu
e
f
r
o
m
a
g
r
o
u
p
o
f
n
ei
g
h
b
o
r
in
g
p
i
x
els.
I
n
t
h
is
ar
t
icle
,
i
n
s
ec
tio
n
2
,
we
w
ill
e
x
p
lai
n
t
h
e
L
FP
al
g
o
r
it
h
m
an
d
h
o
w
w
e
ca
n
u
s
e
i
t
f
o
r
e
m
o
ti
o
n
class
i
f
icatio
n
.
I
n
s
ec
tio
n
3
,
w
e
w
ill
d
is
cu
s
s
t
h
e
r
esu
lt
s
an
d
p
er
f
o
r
m
a
n
ce
o
f
u
s
i
n
g
t
h
e
L
F
P
alg
o
r
ith
m
in
th
i
s
ca
s
e.
Fo
llo
w
ed
b
y
t
h
e
co
n
c
lu
s
io
n
.
we
w
il
l
p
r
esen
t
t
h
e
d
esi
g
n
a
n
d
m
a
th
e
m
atica
l
th
eo
r
ies
o
n
w
h
ic
h
t
h
e
L
FP
alg
o
r
ith
m
is
b
ased
.
2.
M
E
T
H
O
D
2
.
1
.
E
m
o
t
io
n c
la
s
s
if
ica
t
io
n s
y
s
t
e
m
Ou
r
s
y
s
te
m
t
h
at
clas
s
i
f
ies
e
m
o
tio
n
s
b
ased
o
n
f
ac
ia
l
ex
p
r
ess
io
n
s
;
it
g
en
er
al
l
y
co
n
s
is
ts
o
f
t
h
r
ee
m
ai
n
m
o
d
u
les a
s
w
e
s
ee
i
n
F
i
g
u
r
e
1
.
−
T
h
e
f
ir
s
t
m
o
d
u
le:
t
h
is
u
n
i
t
r
elies
o
n
th
e
o
p
en
s
o
u
r
ce
co
m
p
u
ter
v
is
io
n
(
Op
en
C
V
)
lib
r
ar
y
,
s
o
th
at
th
e
s
tu
d
e
n
t
'
s
f
ac
e
is
id
en
ti
f
ied
an
d
tr
ac
ed
b
ac
k
th
r
o
u
g
h
v
id
eo
o
r
im
ag
e
a
n
al
y
s
i
s
.
−
T
h
e
s
ec
o
n
d
m
o
d
u
le:
it
is
b
ase
d
o
n
th
e
L
FP
alg
o
r
ith
m
to
ex
t
r
ac
t
th
e
k
e
y
r
eg
io
n
s
o
f
t
h
e
f
ac
e
b
y
r
etu
r
n
in
g
th
e
co
o
r
d
in
ates o
f
t
h
e
k
e
y
s
q
u
ar
es o
f
th
e
f
ac
e.
−
T
h
e
th
ir
d
m
o
d
u
le:
its
r
o
le
is
to
ca
lcu
late
t
h
e
w
eig
h
t
s
o
f
t
h
e
n
eu
r
al
n
et
w
o
r
k
to
cla
s
s
i
f
y
f
ac
ia
l e
x
p
r
ess
io
n
s
.
Fig
u
r
e
1
.
E
m
o
tio
n
clas
s
i
f
icati
o
n
s
y
s
te
m
m
o
d
u
les
2
.
2
.
Da
t
a
s
et
T
h
e
d
ataset
is
u
s
ed
in
“
r
ep
r
esen
tat
io
n
lear
n
i
n
g
c
h
alle
n
g
e
s
:
f
ac
ial
ex
p
r
es
s
io
n
r
ec
o
g
n
iti
o
n
(
FER)
ch
alle
n
g
e”
o
n
Kag
g
le
.
I
ts
m
ain
task
is
to
class
i
f
y
f
ac
ial
ex
p
r
ess
io
n
s
in
to
d
if
f
er
en
t
em
o
tio
n
ca
teg
o
r
ies.
T
y
p
icall
y
,
t
h
e
d
ataset
co
n
s
is
t
s
o
f
i
m
a
g
e
s
lab
eled
w
it
h
o
n
e
o
f
s
ev
er
al
e
m
o
tio
n
c
las
s
es,
s
u
c
h
as
h
ap
p
in
es
s
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
I
SS
N:
2089
-
4864
Leve
r
a
g
in
g
th
e
lea
r
n
in
g
fo
ca
l
p
o
in
t a
lg
o
r
ith
m
fo
r
emo
tio
n
a
l
in
tellig
en
ce
(
S
a
la
h
E
d
d
in
e
Ma
n
s
o
u
r
)
769
s
ad
n
es
s
,
an
g
er
,
s
u
r
p
r
is
e,
f
ea
r
,
d
is
g
u
s
t,
a
n
d
n
e
u
tr
al.
W
e
u
s
ed
th
is
d
atase
t
to
tr
ain
t
h
e
n
eu
r
al
n
et
w
o
r
k
.
T
h
e
s
p
ec
if
ic
d
atab
ase
u
s
ed
i
n
th
e
Kag
g
le
FER
C
h
alle
n
g
e
m
i
g
h
t
b
e
th
e
FER
2
0
1
3
(
FER2
0
1
3
)
d
ataset,
w
h
ic
h
co
n
s
is
ts
o
f
4
8
×
48
-
p
ix
el
g
r
a
y
s
ca
le
i
m
ag
e
s
o
f
f
ac
es.
E
ac
h
i
m
ag
e
i
s
lab
eled
w
it
h
o
n
e
o
f
s
ev
e
n
e
m
o
tio
n
s
.
I
t
co
n
tain
s
ar
o
u
n
d
3
5
,
0
0
0
im
ag
e
s
,
ca
teg
o
r
ized
in
to
s
e
v
en
d
i
f
f
e
r
en
t e
m
o
tio
n
s
.
2
.
3
.
O
penCV
Op
en
C
V
lib
r
ar
y
s
er
v
es
as
a
c
o
m
p
r
e
h
en
s
iv
e
to
o
lb
o
x
f
o
r
p
er
f
o
r
m
i
n
g
v
ar
io
u
s
i
m
a
g
e
p
r
o
ce
s
s
in
g
tas
k
s
,
in
cl
u
d
in
g
i
m
a
g
e
f
ilter
i
n
g
,
tr
an
s
f
o
r
m
a
tio
n
,
e
n
h
an
ce
m
e
n
t,
a
n
d
g
eo
m
e
tr
ic
o
p
er
atio
n
s
l
ik
e
r
esi
zin
g
,
cr
o
p
p
in
g
,
a
n
d
r
o
tatio
n
[
1
0
]
,
[
1
1
]
.
I
t
p
r
o
v
id
e
s
a
w
id
e
r
a
n
g
e
o
f
to
o
ls
a
n
d
f
u
n
ctio
n
alitie
s
f
o
r
i
m
ag
e
an
d
v
id
eo
p
r
o
ce
s
s
i
n
g
,
in
cl
u
d
in
g
f
ea
tu
r
e
s
f
o
r
co
m
p
u
t
er
v
is
io
n
,
m
ac
h
i
n
e
lear
n
in
g
,
a
n
d
i
m
a
g
e
a
n
al
y
s
i
s
[
1
2
]
.
Op
en
C
V
is
w
r
itte
n
in
C
++
an
d
also
h
as i
n
ter
f
ac
es
f
o
r
P
y
t
h
o
n
,
J
av
a,
an
d
o
th
er
la
n
g
u
a
g
es
.
I
t p
r
o
v
id
es a
co
m
p
r
eh
en
s
i
v
e
s
et
o
f
f
u
n
ctio
n
s
f
o
r
b
asic
to
ad
v
an
ce
d
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
tas
k
s
,
i
n
cl
u
d
in
g
i
m
a
g
e
f
ilter
i
n
g
,
m
o
r
p
h
o
lo
g
ical
o
p
er
atio
n
s
,
a
n
d
co
lo
r
s
p
ac
e
tr
an
s
f
o
r
m
at
io
n
s
.
Op
e
n
C
V
in
cl
u
d
es
a
v
ar
iet
y
o
f
co
m
p
u
ter
v
is
io
n
al
g
o
r
ith
m
s
f
o
r
o
b
j
ec
t
d
etec
tio
n
,
f
ea
tu
r
e
ex
tr
ac
tio
n
,
i
m
a
g
e
s
titc
h
i
n
g
,
an
d
ca
m
er
a
ca
lib
r
atio
n
.
I
t
in
teg
r
ates
w
it
h
m
ac
h
in
e
lear
n
in
g
f
r
a
m
e
w
o
r
k
s
an
d
in
cl
u
d
es
m
ac
h
i
n
e
lear
n
i
n
g
al
g
o
r
ith
m
s
f
o
r
task
s
s
u
c
h
as
class
i
f
icatio
n
,
clu
s
ter
in
g
,
an
d
r
eg
r
e
s
s
io
n
.
A
l
s
o
,
Op
en
C
V
s
u
p
p
o
r
ts
d
ee
p
lear
n
in
g
f
r
a
m
e
w
o
r
k
s
li
k
e
T
en
s
o
r
Flo
w
a
n
d
P
y
T
o
r
ch
,
allo
w
in
g
u
s
er
s
to
w
o
r
k
w
it
h
p
r
e
-
tr
ain
ed
d
ee
p
lear
n
in
g
m
o
d
els
an
d
b
u
ild
th
eir
o
w
n
m
o
d
els
[
1
3
]
.
I
n
o
u
r
ca
s
e,
w
e
u
s
ed
Op
en
C
V
to
d
etec
t
an
d
ex
tr
ac
t i
m
ag
e
s
o
f
ch
ild
r
en
’
s
f
a
c
es,
as
w
e
s
ee
in
Fig
u
r
e
2
,
f
r
o
m
th
e
ca
m
er
as t
h
at
w
il
l b
e
in
s
t
alled
.
Fig
u
r
e
2
.
Face
ex
tr
a
ctio
n
a
n
d
d
etec
tio
n
u
s
in
g
Op
en
C
V
2
.
4
.
L
ea
rning
f
o
c
a
l po
int
a
lg
o
rit
h
m
T
h
e
L
FP
alg
o
r
ith
m
h
elp
s
r
ed
u
ce
th
e
n
u
m
b
er
o
f
p
ar
a
m
eter
s
a
n
d
f
o
cu
s
o
n
t
h
e
m
o
s
t
i
m
p
o
r
ta
n
t
f
ea
tu
r
e
s
in
t
h
e
d
ata.
T
h
r
o
u
g
h
t
h
e
f
lo
wch
ar
t
in
Fi
g
u
r
e
3
,
w
e
ca
n
u
n
d
er
s
tan
d
h
o
w
t
h
e
L
FP
alg
o
r
it
h
m
w
o
r
k
s
.
W
e
tak
e
a
s
et
o
f
i
m
a
g
es
o
f
th
e
s
a
m
e
s
iz
e
an
d
th
en
d
iv
id
e
ea
ch
i
m
a
g
e
in
to
s
q
u
ar
es
,
as
w
e
s
ee
i
n
F
i
g
u
r
e
4
.
W
e
p
er
f
o
r
m
p
er
ce
p
tr
o
n
tr
ain
in
g
o
n
ea
ch
s
q
u
ar
e,
th
en
w
e
ca
lcu
late
th
e
ir
ac
cu
r
ac
y
t
h
r
o
u
g
h
th
e
(
1
),
an
d
f
in
al
l
y
g
et
t
h
e
co
o
r
d
in
ates
(
x
,
y
,
w
id
t
h
an
d
h
eig
h
t)
o
f
t
h
e
h
i
g
h
-
p
r
ec
is
io
n
s
q
u
ar
es.
T
o
s
u
m
u
p
,
L
FP
alg
o
r
ith
m
r
elies
o
n
t
h
e
ac
cu
r
ac
y
o
f
p
er
ce
p
tr
o
n
tr
ain
i
n
g
o
n
d
i
f
f
er
en
t
s
q
u
ar
es
o
f
i
m
ag
es
to
r
etu
r
n
th
eir
co
o
r
d
in
ates
.
T
h
is
m
ea
n
s
t
h
at
i
t
h
as
th
e
s
a
m
e
r
o
le
as
m
a
x
p
o
o
lin
g
a
n
d
m
ea
n
p
o
o
lin
g
u
s
ed
in
C
NN.
As
a
s
cien
ti
f
ic
co
n
tr
ib
u
t
io
n
,
w
e
r
ep
lace
th
e
p
o
o
lin
g
la
y
er
s
w
ith
a
n
L
FP
lay
er
.
T
h
e
L
FP
alg
o
r
it
h
m
e
m
p
lo
y
s
a
s
y
s
te
m
atic
ap
p
r
o
ac
h
to
id
en
ti
f
y
k
e
y
f
o
ca
l
p
o
in
ts
w
i
th
in
i
n
p
u
t
i
m
a
g
es.
B
eg
in
n
i
n
g
w
it
h
i
m
a
g
e
s
e
g
m
e
n
tatio
n
i
n
to
d
is
ti
n
ct
p
ar
ts
(
Di
v
[
i]
)
,
th
e
al
g
o
r
it
h
m
u
t
ilizes
p
er
ce
p
tr
o
n
s
to
ex
tr
ac
t
r
elev
an
t
f
ea
t
u
r
es.
A
cc
u
r
ac
y
ca
lcu
latio
n
s
e
v
al
u
ate
f
o
ca
l
p
o
in
t
id
en
ti
f
icatio
n
ef
f
ec
ti
v
e
n
ess
,
f
o
llo
w
ed
b
y
s
o
r
ti
n
g
Div
[
i]
s
e
g
m
en
ts
b
ased
o
n
p
r
ec
is
io
n
.
T
h
e
al
g
o
r
ith
m
r
et
u
r
n
s
co
o
r
d
in
ates
o
f
t
h
e
s
e
g
m
en
t
s
w
it
h
t
h
e
h
i
g
h
e
s
t
p
r
ec
is
io
n
,
s
i
g
n
i
f
y
i
n
g
th
e
lo
ca
li
za
tio
n
o
f
k
e
y
f
o
ca
l
p
o
in
t
s
.
T
h
is
p
r
o
ce
s
s
d
is
till
s
i
m
ag
e
co
m
p
l
ex
it
y
,
f
ac
i
litati
n
g
a
f
o
cu
s
ed
an
al
y
s
i
s
o
f
ess
e
n
tia
l f
ea
tu
r
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4864
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
,
Vo
l.
13
,
No
.
3
,
No
v
e
m
b
er
20
24
:
767
-
7
73
770
=
+
(
1
)
Fig
u
r
e
3
.
Flo
w
c
h
ar
t o
f
t
h
e
L
F
P
alg
o
r
ith
m
Fig
u
r
e
4
.
E
x
ec
u
tio
n
o
f
p
er
ce
p
tr
o
n
o
n
s
ev
er
al
s
q
u
ar
e
2
.
5
.
T
ens
o
rF
lo
w
T
en
s
o
r
Flo
w
is
a
n
o
p
en
-
s
o
u
r
c
e
m
ac
h
i
n
e
lear
n
in
g
f
r
a
m
e
w
o
r
k
d
ev
elo
p
ed
b
y
t
h
e
Go
o
g
le
B
r
ain
tea
m
[
1
4
]
,
[
1
5
]
.
I
t'
s
d
esig
n
ed
to
f
ac
ilit
ate
t
h
e
d
ev
elo
p
m
e
n
t
an
d
d
ep
lo
y
m
e
n
t
o
f
m
ac
h
i
n
e
lear
n
i
n
g
m
o
d
els.
T
en
s
o
r
Flo
w
h
a
s
s
tr
o
n
g
s
u
p
p
o
r
t
f
o
r
b
u
ild
in
g
a
n
d
tr
ain
in
g
C
NN
[
1
6
]
.
C
NNs
ar
e
a
s
p
e
cif
ic
t
y
p
e
o
f
n
e
u
r
al
n
et
w
o
r
k
ar
ch
itec
tu
r
e
th
a
t
is
p
ar
ticu
lar
l
y
e
f
f
ec
tiv
e
f
o
r
i
m
ag
e
-
r
elate
d
task
s
,
s
u
ch
as
i
m
ag
e
cl
ass
i
f
icatio
n
,
o
b
j
ec
t
d
etec
tio
n
,
an
d
i
m
a
g
e
s
e
g
m
en
tatio
n
[
1
7
]
.
T
en
s
o
r
Flo
w
p
r
o
v
id
es
a
co
m
p
r
e
h
en
s
iv
e
ec
o
s
y
s
t
e
m
f
o
r
d
ev
elo
p
in
g
an
d
d
ep
lo
y
i
n
g
m
ac
h
i
n
e
lear
n
in
g
m
o
d
els.
I
t
o
f
f
er
s
a
h
i
g
h
-
lev
e
l
ap
p
licatio
n
p
r
o
g
r
a
m
m
i
n
g
in
ter
f
ac
e
(
A
P
I
)
ca
lled
Ker
as
th
at
s
i
m
p
li
f
ies
t
h
e
p
r
o
ce
s
s
o
f
b
u
ild
in
g
a
n
d
t
r
ain
in
g
n
eu
r
al
n
et
w
o
r
k
s
,
i
n
cl
u
d
in
g
C
NNs
[
1
8
]
.
T
en
s
o
r
Flo
w
allo
w
s
u
s
er
s
to
d
ef
i
n
e,
tr
ain
,
an
d
d
ep
lo
y
co
m
p
lex
m
o
d
els
e
f
f
ic
ien
t
l
y
.
Ker
as
is
an
o
p
en
-
s
o
u
r
ce
h
ig
h
-
le
v
el
n
eu
r
al
n
e
t
w
o
r
k
s
AP
I
th
at
is
n
o
w
tig
h
tl
y
i
n
te
g
r
a
ted
in
to
T
en
s
o
r
Flo
w
[
1
9
]
.
W
ith
Ker
a
s
,
w
e
ca
n
ea
s
il
y
b
u
ild
a
n
d
ex
p
er
i
m
e
n
t
w
it
h
v
ar
io
u
s
n
e
u
r
al
n
et
w
o
r
k
ar
ch
itect
u
r
es,
in
c
lu
d
i
n
g
C
N
N
s
,
u
s
in
g
a
clea
r
a
n
d
u
s
er
-
f
r
ie
n
d
l
y
s
y
n
ta
x
.
T
h
er
ef
o
r
e,
w
e
tr
ain
t
h
e
n
e
u
r
al
n
et
w
o
r
k
b
y
u
s
i
n
g
t
h
e
s
q
u
ar
es
f
o
u
n
d
b
y
L
FP
alg
o
r
ith
m
as
w
e
s
ee
i
n
Fi
g
u
r
e
5
.
Fig
u
r
e
5
.
T
r
ain
in
g
th
e
n
e
u
r
al
n
et
w
o
r
k
u
s
in
g
t
h
e
s
q
u
ar
es
f
o
u
n
d
b
y
t
h
e
L
FP
alg
o
r
ith
m
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
Af
ter
lear
n
in
g
ab
o
u
t
t
h
e
m
eth
o
d
s
u
s
ed
i
n
t
h
is
r
esear
ch
,
w
e
w
il
l
p
r
esen
t
t
h
e
r
es
u
lts
o
b
tain
ed
u
s
i
n
g
t
h
e
L
FP
alg
o
r
ith
m
an
d
co
m
p
ar
e
th
e
m
w
i
th
t
h
e
r
esu
lt
s
o
f
m
a
x
p
o
o
lin
g
.
W
e
u
s
ed
th
e
FER
ch
allen
g
e
d
atab
ase
o
n
Kag
g
le.
W
e
co
n
d
u
cted
tw
o
ex
p
er
im
e
n
t
s
as
w
e
s
ee
in
F
i
g
u
r
e
6
in
o
r
d
er
to
o
b
tain
th
e
m
o
d
el
s
:
th
e
f
ir
s
t
w
e
u
s
ed
th
e
L
FP
alg
o
r
ith
m
i
n
t
h
e
C
N
N
an
d
th
e
s
ec
o
n
d
w
e
u
s
ed
m
a
x
p
o
o
lin
g
.
T
h
e
p
er
f
o
r
m
an
ce
o
f
th
e
s
e
m
o
d
els
w
as
ev
alu
a
ted
b
ased
o
n
class
i
f
ic
atio
n
ac
cu
r
ac
y
(
C
A
)
,
p
r
ec
is
io
n
,
r
ec
all
,
F1
s
co
r
e,
an
d
r
ec
eiv
er
o
p
er
ati
n
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
I
SS
N:
2089
-
4864
Leve
r
a
g
in
g
th
e
lea
r
n
in
g
fo
ca
l
p
o
in
t a
lg
o
r
ith
m
fo
r
emo
tio
n
a
l
in
tellig
en
ce
(
S
a
la
h
E
d
d
in
e
Ma
n
s
o
u
r
)
771
ch
ar
ac
ter
is
tic
-
ar
ea
u
n
d
er
t
h
e
c
u
r
v
e
(
R
OC
-
A
U
C
)
v
alu
e
s
[
2
0
]
.
T
h
ese
in
d
ices
(
t
h
ese
f
u
n
ctio
n
s
)
w
er
e
g
en
er
ated
au
to
m
at
icall
y
u
s
i
n
g
T
en
s
o
r
Flo
w
lib
r
ar
y
.
A
cc
u
r
ac
y
i
n
A
I
r
ef
er
s
to
h
o
w
w
ell
a
m
ac
h
i
n
e
lear
n
i
n
g
m
o
d
el
p
er
f
o
r
m
s
i
n
m
a
k
i
n
g
co
r
r
ec
t
p
r
ed
ictio
n
s
o
r
clas
s
i
f
icatio
n
s
c
o
m
p
ar
ed
to
t
h
e
to
tal
n
u
m
b
er
o
f
p
r
ed
ictio
n
s
.
I
t
's
a
m
ea
s
u
r
e
o
f
h
o
w
o
f
te
n
th
e
m
o
d
el
is
co
r
r
ec
t.
Fo
r
class
if
icati
o
n
task
s
,
it
m
ea
s
u
r
es
t
h
e
p
er
ce
n
tag
e
o
f
co
r
r
ec
tl
y
p
r
ed
icted
in
s
ta
n
ce
s
a
m
o
n
g
all
in
s
tan
ce
s
.
W
h
ile
ac
cu
r
ac
y
is
an
ess
e
n
tial
m
etr
ic,
it
m
i
g
h
t
n
o
t
g
iv
e
a
co
m
p
lete
p
ictu
r
e,
esp
ec
iall
y
in
ca
s
es
o
f
i
m
b
alan
ce
d
d
atasets
.
P
r
ec
is
io
n
in
A
I
,
p
ar
ticu
lar
l
y
in
class
i
f
icatio
n
task
s
,
m
ea
s
u
r
es
t
h
e
r
atio
o
f
tr
u
e
p
o
s
i
tiv
e
p
r
ed
ictio
n
s
to
t
h
e
to
tal
p
r
ed
icted
p
o
s
itiv
es
[
2
1
]
.
I
t
f
o
c
u
s
es
o
n
t
h
e
r
ele
v
a
n
ce
o
f
th
e
m
o
d
el
'
s
p
r
ed
ictio
n
s
.
P
r
ec
is
io
n
is
ab
o
u
t
h
o
w
m
a
n
y
o
f
th
e
p
r
ed
icted
p
o
s
itiv
e
in
s
t
an
ce
s
ar
e
ac
tu
all
y
r
elev
an
t.
R
ec
a
ll
in
t
h
e
co
n
tex
t
o
f
A
I
an
d
m
ac
h
i
n
e
lear
n
i
n
g
r
ef
er
s
to
th
e
ab
ilit
y
o
f
a
m
o
d
el
t
o
co
r
r
ec
tly
id
e
n
ti
f
y
all
r
elev
an
t
in
s
ta
n
ce
s
o
r
d
ata
p
o
in
ts
w
it
h
in
a
d
ataset.
I
t'
s
a
m
ea
s
u
r
e
o
f
a
m
o
d
el
'
s
co
m
p
lete
n
ess
in
ca
p
tu
r
i
n
g
all
th
e
r
elev
an
t
in
f
o
r
m
atio
n
.
I
t
ca
lcu
late
s
th
e
r
atio
o
f
tr
u
e
p
o
s
itiv
e
s
to
th
e
s
u
m
o
f
tr
u
e
p
o
s
itiv
es
an
d
f
al
s
e
n
eg
at
iv
e
s
[
2
2
]
.
F1
s
co
r
e
th
i
s
m
etr
ic
co
n
s
id
er
s
b
o
th
p
r
ec
is
io
n
a
n
d
r
ec
all
to
p
r
o
v
id
e
a
s
i
n
g
le
s
co
r
e
t
h
at
r
ep
r
esen
ts
th
e
m
o
d
el
's
p
er
f
o
r
m
an
ce
.
I
n
s
u
c
h
ca
s
es,
th
e
F1
s
co
r
e
b
ec
o
m
e
s
v
al
u
ab
le.
I
t
co
n
s
id
er
s
b
o
th
f
al
s
e
p
o
s
itiv
es
(
p
r
ec
is
io
n
)
an
d
f
a
ls
e
n
e
g
ati
v
es
(
r
ec
all)
,
p
r
o
v
i
d
in
g
a
b
ala
n
ce
d
ass
e
s
s
m
e
n
t
o
f
th
e
m
o
d
el
'
s
ef
f
ec
tiv
e
n
e
s
s
.
I
t
'
s
p
ar
ticu
lar
l
y
b
en
ef
icial
w
h
e
n
th
er
e
'
s
a
n
e
ed
to
av
o
id
eith
er
m
i
s
s
i
n
g
p
o
s
itiv
e
ca
s
e
s
(
lo
w
r
ec
all)
o
r
m
is
cla
s
s
i
f
y
in
g
n
e
g
at
iv
e
ca
s
e
s
as
p
o
s
itiv
e
(
lo
w
p
r
ec
is
io
n
)
[
2
3
]
.
I
t'
s
a
u
s
ef
u
l
m
etr
ic
w
h
e
n
y
o
u
w
a
n
t
to
b
alan
ce
b
et
w
ee
n
p
r
ec
is
io
n
a
n
d
r
ec
all
an
d
n
ee
d
a
s
in
g
le
v
a
lu
e
to
ass
e
s
s
a
m
o
d
el
'
s
p
er
f
o
r
m
an
ce
.
T
h
e
R
O
C
-
A
U
C
is
v
alu
ab
le
b
ec
au
s
e
it
ev
alu
a
tes
a
m
o
d
el
'
s
ab
ilit
y
to
d
is
cr
i
m
i
n
ate
b
et
w
ee
n
p
o
s
itiv
e
a
n
d
n
eg
at
iv
e
cla
s
s
es
ac
r
o
s
s
v
ar
io
u
s
t
h
r
esh
o
ld
v
al
u
e
s
[
2
4
]
,
[
2
5
]
.
I
t'
s
co
m
m
o
n
l
y
u
s
ed
in
b
in
ar
y
clas
s
i
f
icatio
n
p
r
o
b
le
m
s
a
n
d
p
r
o
v
id
es
a
r
o
b
u
s
t a
s
s
e
s
s
m
e
n
t o
f
th
e
m
o
d
el'
s
p
er
f
o
r
m
an
ce
r
eg
ar
d
less
o
f
t
h
e
t
h
r
esh
o
ld
c
h
o
s
e
n
f
o
r
clas
s
if
ica
tio
n
.
A
h
i
g
h
er
A
U
C
g
e
n
er
all
y
s
u
g
g
e
s
ts
t
h
at
t
h
e
m
o
d
el
is
b
etter
at
d
is
ti
n
g
u
i
s
h
in
g
b
et
w
ee
n
th
e
cla
s
s
e
s
.
W
e
d
id
t
w
o
e
x
p
er
i
m
e
n
ts
as
w
e
s
ee
i
n
F
i
g
u
r
e
6
.
I
n
t
h
e
f
ir
s
t
e
x
p
er
i
m
e
n
t,
w
e
i
m
p
le
m
e
n
t
ed
th
e
L
FP
alg
o
r
ith
m
w
it
h
n
eu
r
al
n
et
w
o
r
k
an
d
in
th
e
s
ec
o
n
d
ex
p
er
im
e
n
t
w
e
j
u
s
t
u
s
ed
m
a
x
p
o
o
lin
g
.
W
e
n
o
t
in
T
ab
le
1
th
e
r
esu
lt
s
o
f
th
e
s
e
e
x
p
er
i
m
e
n
ts
w
h
ic
h
d
e
m
o
n
s
tr
ate
th
e
s
tr
en
g
th
o
f
th
e
L
FP
alg
o
r
it
h
m
,
wh
ich
p
r
es
en
t
s
h
i
g
h
t
p
r
ec
is
io
n
.
Fu
r
t
h
er
m
o
r
e,
co
m
p
ar
in
g
e
x
p
er
i
m
e
n
t
s
1
an
d
2
,
w
e
o
b
s
er
v
e
th
at
w
e
ca
n
i
n
cr
ea
s
e
th
e
CA
u
p
to
1
0
%
if
w
e
u
s
e
t
h
e
L
FP
alg
o
r
ith
m
.
Fig
u
r
e
6
.
T
r
ain
in
g
th
e
n
e
u
r
al
n
et
w
o
r
k
u
s
in
g
t
h
e
s
q
u
ar
es
f
o
u
n
d
b
y
t
h
e
L
FP
alg
o
r
ith
m
T
ab
le
1
.
R
esu
lts
o
f
tw
o
e
x
p
er
im
en
ts
Ex
p
e
r
i
me
n
t
N
°
A
l
g
o
r
i
t
h
m
CA
P
r
e
c
i
si
o
n
R
e
c
a
l
l
F1
-
S
c
o
r
e
R
O
C
-
A
U
C
1
L
F
P
a
l
g
o
r
i
t
h
m
0
.
9
3
1
0
.
9
3
1
0
.
9
3
0
0
.
9
3
0
0
.
9
4
4
2
M
a
x
p
o
o
l
i
n
g
0
.
8
2
6
0
.
8
2
5
0
.
8
2
4
0
.
8
2
4
0
.
8
3
5
4.
CO
NCLU
SI
O
N
I
n
t
h
is
w
o
r
k
,
w
e
p
r
ese
n
ted
t
h
e
s
tr
en
g
t
h
o
f
L
FP
alg
o
r
it
h
m
t
o
class
i
f
y
t
h
e
e
m
o
t
io
n
s
b
y
a
n
a
l
y
s
in
g
t
h
e
f
ac
ial
ex
p
r
ess
io
n
s
.
A
n
d
th
i
s
w
e
h
elp
to
d
ev
elo
p
o
u
r
r
o
b
o
t
teac
h
er
p
r
o
j
ec
t
b
y
ad
d
in
g
to
it
th
e
em
o
tio
n
a
l
in
telli
g
e
n
ce
.
W
e
also
p
r
ese
n
t
h
o
w
w
e
ca
n
c
h
a
n
g
e
C
N
N
a
r
ch
itect
u
r
e
b
y
r
ep
lace
m
ax
p
o
o
lin
g
a
n
d
av
er
a
g
e
p
o
o
lin
g
b
y
L
FP
alg
o
r
it
h
m
.
I
n
t
w
o
e
x
p
er
i
m
e
n
ts
,
w
e
h
a
v
e
c
o
m
p
ar
ed
t
w
o
m
e
th
o
d
s
b
y
u
s
i
n
g
s
o
m
e
e
s
ti
m
atio
n
in
d
ices
in
cl
u
d
in
g
AUC,
C
A
,
p
r
ec
is
io
n
,
F1
s
co
r
e,
an
d
r
ec
all.
T
h
e
n
u
m
er
ical
o
u
tp
u
t
r
es
u
lt
s
h
o
w
s
t
h
at
t
h
e
class
i
f
ier
b
ased
o
n
th
e
L
FP
al
g
o
r
ith
m
p
er
f
o
r
m
s
b
etter
th
a
n
i
ts
co
m
p
etito
r
in
ter
m
s
o
f
ac
c
u
r
ac
y
(
0
.
9
3
1
)
,
w
h
ic
h
m
ea
n
s
i
n
cr
ea
s
ed
CA
u
p
to
1
0
%.
T
h
e
L
FP
alg
o
r
ith
m
w
ill
o
p
en
o
u
r
e
y
es
to
a
lo
n
g
r
o
ad
o
f
s
c
ien
t
if
ic
r
esear
ch
b
ec
au
s
e
o
u
r
al
g
o
r
it
h
m
is
b
a
s
e
d
o
n
a
s
i
n
g
le
la
y
er
o
f
s
e
n
s
o
r
y
p
er
ce
p
tio
n
.
Ho
w
e
v
er
,
w
e
h
av
e
h
ad
g
r
ea
t
r
esu
lts
.
So
,
if
w
e
u
s
e
o
th
er
m
ac
h
in
e
lear
n
in
g
alg
o
r
it
h
m
s
th
a
t
ar
e
b
etter
th
an
p
er
c
ep
tr
o
n
.
I
t
is
n
ec
es
s
ar
y
to
o
b
tain
in
cr
ea
s
ed
CA
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4864
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
,
Vo
l.
13
,
No
.
3
,
No
v
e
m
b
er
20
24
:
767
-
7
73
772
RE
F
E
R
E
NC
E
S
[
1
]
K
.
A
h
mad
e
t
a
l
.
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
i
n
e
d
u
c
a
t
i
o
n
:
a
p
a
n
o
r
a
m
i
c
r
e
v
i
e
w
,
”
ML
i
n
E
d
u
c
a
t
i
o
n
a
n
d
I
n
f
o
rm
a
t
i
o
n
w
i
t
h
a
u
t
h
o
rs
,
p
p
.
1
–
5
1
,
2
0
2
0
,
d
o
i
:
1
0
.
3
5
5
4
2
/
o
sf
.
i
o
/
z
v
u
2
n
.
[
2
]
N
.
H
u
mp
h
r
e
y
,
A
.
C
u
r
r
a
n
,
E
.
M
o
r
r
i
s,
P
.
F
a
r
r
e
l
l
,
a
n
d
K
.
W
o
o
d
s,
“
Emo
t
i
o
n
a
l
i
n
t
e
l
l
i
g
e
n
c
e
a
n
d
e
d
u
c
a
t
i
o
n
:
a
c
r
i
t
i
c
a
l
r
e
v
i
e
w
,
”
Ed
u
c
a
t
i
o
n
a
l
Psy
c
h
o
l
o
g
y
,
v
o
l
.
2
7
,
n
o
.
2
,
p
p
.
2
3
5
–
2
5
4
,
A
p
r
.
2
0
0
7
,
d
o
i
:
1
0
.
1
0
8
0
/
0
1
4
4
3
4
1
0
6
0
1
0
6
6
7
3
5
.
[
3
]
K
.
K
e
e
f
e
r
,
J.
D
.
A
.
P
a
r
k
e
r
,
a
n
d
D
.
H
.
S
a
k
l
o
f
sk
e
,
Em
o
t
i
o
n
a
l
i
n
t
e
l
l
i
g
e
n
c
e
i
n
e
d
u
c
a
t
i
o
n
.
i
n
T
h
e
S
p
r
i
n
g
e
r
S
e
r
i
e
s
o
n
H
u
ma
n
Ex
c
e
p
t
i
o
n
a
l
i
t
y
.
C
h
a
m:
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
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
319
-
9
0
6
3
3
-
1
.
[
4
]
B
.
L
.
K
e
n
n
e
d
y
a
n
d
R
.
Ju
n
k
e
r
,
“
T
h
e
e
v
o
l
u
t
i
o
n
of
‘
l
o
a
d
e
d
mo
me
n
t
s’
t
o
w
a
r
d
e
sca
l
a
t
i
o
n
o
r
d
e
-
e
sca
l
a
t
i
o
n
i
n
st
u
d
e
n
t
–
t
e
a
c
h
e
r
i
n
t
e
r
a
c
t
i
o
n
s,
”
R
e
v
i
e
w
o
f
Ed
u
c
a
t
i
o
n
a
l
Re
se
a
rc
h
,
O
c
t
.
2
0
2
3
,
d
o
i
:
1
0
.
3
1
0
2
/
0
0
3
4
6
5
4
3
2
3
1
2
0
2
5
0
9
.
[
5
]
F
.
D
e
mi
r
,
A
.
M
.
I
smae
l
,
a
n
d
A
.
S
e
n
g
u
r
,
“
C
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
l
u
n
g
so
u
n
d
s
w
i
t
h
C
N
N
mo
d
e
l
u
si
n
g
p
a
r
a
l
l
e
l
p
o
o
l
i
n
g
st
r
u
c
t
u
r
e
,
”
I
EE
E
Ac
c
e
ss
,
v
o
l
.
8
,
p
p
.
1
0
5
3
7
6
–
1
0
5
3
8
3
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
3
0
0
0
1
1
1
.
[
6
]
S
.
S
r
i
n
i
v
a
s,
R
.
K
.
S
a
r
v
a
d
e
v
a
b
h
a
t
l
a
,
K
.
R
.
M
o
p
u
r
i
,
N
.
P
r
a
b
h
u
,
S
.
S
.
S
.
K
r
u
t
h
i
v
e
n
t
i
,
a
n
d
R
.
V
.
B
a
b
u
,
“
A
t
a
x
o
n
o
m
y
o
f
d
e
e
p
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
s fo
r
c
o
m
p
u
t
e
r
v
i
si
o
n
,
”
F
ro
n
t
i
e
rs
R
o
b
o
t
i
c
s
AI
,
v
o
l
.
2
,
J
a
n
.
2
0
1
6
,
d
o
i
:
1
0
.
3
3
8
9
/
f
r
o
b
t
.
2
0
1
5
.
0
0
0
3
6
.
[
7
]
A
.
K
h
a
n
,
A
.
S
o
h
a
i
l
,
U
.
Z
a
h
o
o
r
a
,
a
n
d
A
.
S
.
Q
u
r
e
sh
i
,
“
A
su
r
v
e
y
o
f
t
h
e
r
e
c
e
n
t
a
r
c
h
i
t
e
c
t
u
r
e
s
o
f
d
e
e
p
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,”
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
Re
v
i
e
w
,
v
o
l
.
5
3
,
n
o
.
8
,
p
p
.
5
4
5
5
–
5
5
1
6
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
0
4
6
2
-
020
-
0
9
8
2
5
-
6.
[
8
]
L
.
A
l
z
u
b
a
i
d
i
e
t
a
l
.
,
“
R
e
v
i
e
w
o
f
d
e
e
p
l
e
a
r
n
i
n
g
:
c
o
n
c
e
p
t
s,
C
N
N
a
r
c
h
i
t
e
c
t
u
r
e
s,
c
h
a
l
l
e
n
g
e
s,
a
p
p
l
i
c
a
t
i
o
n
s
,
f
u
t
u
r
e
d
i
r
e
c
t
i
o
n
s,
”
J
o
u
rn
a
l
o
f
Bi
g
D
a
t
a
,
v
o
l
.
8
,
n
o
.
1
,
p
p
.
1
–
7
4
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
8
6
/
s
4
0
5
3
7
-
0
2
1
-
0
0
4
4
4
-
8.
[
9
]
N
.
A
k
h
t
a
r
a
n
d
U
.
R
a
g
a
v
e
n
d
r
a
n
,
“
I
n
t
e
r
p
r
e
t
a
t
i
o
n
o
f
i
n
t
e
l
l
i
g
e
n
c
e
i
n
C
N
N
-
p
o
o
l
i
n
g
p
r
o
c
e
sse
s:
a
me
t
h
o
d
o
l
o
g
i
c
a
l
su
r
v
e
y
,
”
N
e
u
ra
l
C
o
m
p
u
t
i
n
g
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
2
,
n
o
.
3
,
p
p
.
8
7
9
–
8
9
8
,
F
e
b
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s0
0
5
2
1
-
019
-
0
4
2
9
6
-
5.
[
1
0
]
D
.
K
.
M
i
s
h
r
a
,
S
.
E
.
U
m
b
a
u
g
h
,
N
.
L
a
ma,
R
.
D
a
h
a
l
,
D
.
J.
M
a
r
i
n
o
,
a
n
d
J.
S
a
c
k
m
a
n
,
“
I
mag
e
p
r
o
c
e
ssi
n
g
a
n
d
p
a
t
t
e
r
n
r
e
c
o
g
n
i
t
i
o
n
w
i
t
h
C
V
I
P
t
o
o
l
s
M
A
TL
A
B
t
o
o
l
b
o
x
:
a
u
t
o
mat
i
c
c
r
e
a
t
i
o
n
o
f
mas
k
s
f
o
r
v
e
t
e
r
i
n
a
r
y
t
h
e
r
mo
g
r
a
p
h
i
c
i
m
a
g
e
s,”
i
n
A
p
p
l
i
c
a
t
i
o
n
s
o
f
D
i
g
i
t
a
l
I
m
a
g
e
Pr
o
c
e
ssi
n
g
XX
XI
X
,
A
.
G
.
T
e
sch
e
r
,
Ed
.
,
S
e
p
.
2
0
1
6
.
d
o
i
:
1
0
.
1
1
1
7
/
1
2
.
2
2
3
8
1
8
3
.
[
1
1
]
K
.
P
u
l
l
i
,
A
.
B
a
k
s
h
e
e
v
,
K
.
K
o
r
n
y
a
k
o
v
,
a
n
d
V
.
Er
u
h
i
mo
v
,
“
R
e
a
l
t
i
me
c
o
m
p
u
t
e
r
v
i
si
o
n
w
i
t
h
O
p
e
n
C
V
,
”
Q
u
e
u
e
,
v
o
l
.
1
0
,
n
o
.
4
,
p
p
.
40
–
5
6
,
2
0
1
2
,
d
o
i
:
1
0
.
1
1
4
5
/
2
1
8
1
7
9
6
.
2
2
0
6
3
0
9
.
[
1
2
]
D
.
I
r
e
r
i
,
E.
B
e
l
a
l
,
C
.
O
k
i
n
d
a
,
N
.
M
a
k
a
n
g
e
,
a
n
d
C
.
Ji
,
“
A
c
o
mp
u
t
e
r
v
i
si
o
n
sy
st
e
m fo
r
d
e
f
e
c
t
d
i
scr
i
mi
n
a
t
i
o
n
a
n
d
g
r
a
d
i
n
g
i
n
t
o
ma
t
o
e
s
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
i
mag
e
p
r
o
c
e
ssi
n
g
,
”
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
i
n
A
g
r
i
c
u
l
t
u
r
e
,
v
o
l
.
2
,
p
p
.
2
8
–
3
7
,
Ju
n
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
i
i
a
.
2
0
1
9
.
0
6
.
0
0
1
.
[
1
3
]
S
.
A
.
S
a
n
c
h
e
z
,
H
.
J.
R
o
me
r
o
,
a
n
d
A
.
D
.
M
o
r
a
l
e
s,
“
A
r
e
v
i
e
w
:
c
o
mp
a
r
i
so
n
o
f
p
e
r
f
o
r
man
c
e
me
t
r
i
c
s
o
f
p
r
e
t
r
a
i
n
e
d
mo
d
e
l
s
f
o
r
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
u
s
i
n
g
t
h
e
T
e
n
so
r
F
l
o
w
f
r
a
mew
o
r
k
,
”
I
O
P
C
o
n
f
e
re
n
c
e
S
e
r
i
e
s:
M
a
t
e
ri
a
l
s
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
8
4
4
,
n
o
.
1
,
p
p
.
1
–
1
6
,
J
u
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
5
7
-
8
9
9
X
/
8
4
4
/
1
/
0
1
2
0
2
4
.
[
1
4
]
G
.
A
l
-
B
d
o
u
r
,
R
.
A
l
-
Q
u
r
r
a
n
,
M
.
A
l
-
A
y
y
o
u
b
,
a
n
d
A
.
S
h
a
t
n
a
w
i
,
“
A
d
e
t
a
i
l
e
d
c
o
mp
a
r
a
t
i
v
e
st
u
d
y
o
f
o
p
e
n
so
u
r
c
e
d
e
e
p
l
e
a
r
n
i
n
g
f
r
a
mew
o
r
k
s,”
a
r
Xi
v
e
-
p
ri
n
t
s
,
p
.
a
r
X
i
v
:
1
9
0
3
.
0
0
1
0
2
,
2
0
1
9
,
d
o
i
:
1
0
.
4
8
5
5
0
/
a
r
X
i
v
.
1
9
0
3
.
0
0
1
0
2
.
[
1
5
]
A
.
I
.
K
h
a
n
a
n
d
A
.
A
l
-
B
a
d
i
,
“
O
p
e
n
s
o
u
r
c
e
mac
h
i
n
e
l
e
a
r
n
i
n
g
f
r
a
me
w
o
r
k
s
f
o
r
i
n
d
u
st
r
i
a
l
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s,”
Pro
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
7
0
,
p
p
.
5
7
1
–
5
7
7
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.
2
0
2
0
.
0
3
.
1
2
7
.
[
1
6
]
B
.
P
a
n
g
,
E
.
N
i
j
k
a
m
p
,
a
n
d
Y
.
N
.
W
u
,
“
D
e
e
p
l
e
a
r
n
i
n
g
w
i
t
h
t
e
n
so
r
f
l
o
w
:
a
r
e
v
i
e
w
,
”
J
o
u
r
n
a
l
o
f
E
d
u
c
a
t
i
o
n
a
l
a
n
d
Be
h
a
v
i
o
r
a
l
S
t
a
t
i
s
t
i
c
s
,
v
o
l
.
4
5
,
n
o
.
2
,
p
p
.
2
2
7
–
2
4
8
,
A
p
r
.
2
0
2
0
,
d
o
i
:
1
0
.
3
1
0
2
/
1
0
7
6
9
9
8
6
1
9
8
7
2
7
6
1
.
[
1
7
]
H
.
L
i
n
,
Z
.
S
h
i
,
a
n
d
Z
.
Z
o
u
,
“
F
u
l
l
y
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
t
w
o
r
k
w
i
t
h
t
a
sk
p
a
r
t
i
t
i
o
n
i
n
g
f
o
r
i
n
sh
o
r
e
sh
i
p
d
e
t
e
c
t
i
o
n
i
n
o
p
t
i
c
a
l
r
e
mo
t
e
se
n
si
n
g
i
m
a
g
e
s,”
I
EEE
G
e
o
s
c
i
e
n
c
e
a
n
d
R
e
m
o
t
e
S
e
n
si
n
g
L
e
t
t
e
rs
,
v
o
l
.
1
4
,
n
o
.
1
0
,
p
p
.
1
6
6
5
–
1
6
6
9
,
O
c
t
.
2
0
1
7
,
d
o
i
:
1
0
.
1
1
0
9
/
L
G
R
S
.
2
0
1
7
.
2
7
2
7
5
1
5
.
[
1
8
]
B
.
T
.
C
h
i
c
h
o
a
n
d
A
.
B
.
S
a
l
l
o
w
,
“
A
c
o
mp
r
e
h
e
n
si
v
e
su
r
v
e
y
o
f
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
s
b
a
se
d
o
n
k
e
r
a
s
f
r
a
me
w
o
r
k
,
”
J
o
u
r
n
a
l
o
f
S
o
f
t
C
o
m
p
u
t
i
n
g
a
n
d
D
a
t
a
Mi
n
i
n
g
,
v
o
l
.
2
,
n
o
.
2
,
p
p
.
49
–
6
2
,
O
c
t
.
2
0
2
1
,
d
o
i
:
1
0
.
3
0
8
8
0
/
j
sc
d
m.
2
0
2
1
.
0
2
.
0
2
.
0
0
5
.
[
1
9
]
D
.
G
r
a
t
t
a
r
o
l
a
a
n
d
C
.
A
l
i
p
p
i
,
“
G
r
a
p
h
n
e
u
r
a
l
n
e
t
w
o
r
k
s
i
n
t
e
n
so
r
f
l
o
w
a
n
d
k
e
r
a
s
w
i
t
h
s
p
e
k
t
r
a
l
[
a
p
p
l
i
c
a
t
i
o
n
n
o
t
e
s]
,
”
I
EEE
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
M
a
g
a
z
i
n
e
,
v
o
l
.
1
6
,
n
o
.
1
,
p
p
.
9
9
–
1
0
6
,
F
e
b
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
M
C
I
.
2
0
2
0
.
3
0
3
9
0
7
2
.
[
2
0
]
J.
M
i
a
o
a
n
d
W
.
Z
h
u
,
“
P
r
e
c
i
si
o
n
–
r
e
c
a
l
l
c
u
r
v
e
(
P
R
C
)
c
l
a
ss
i
f
i
c
a
t
i
o
n
t
r
e
e
s,”
Ev
o
l
u
t
i
o
n
a
ry
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
5
,
n
o
.
3
,
p
p
.
1
5
4
5
–
1
5
6
9
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
2
0
6
5
-
021
-
0
0
5
6
5
-
2.
[
2
1
]
M
.
S
o
k
o
l
o
v
a
a
n
d
G
.
L
a
p
a
l
me
,
“
A
s
y
st
e
mat
i
c
a
n
a
l
y
si
s
o
f
p
e
r
f
o
r
man
c
e
me
a
su
r
e
s
f
o
r
c
l
a
ssi
f
i
c
a
t
i
o
n
t
a
s
k
s,”
I
n
f
o
rm
a
t
i
o
n
Pro
c
e
ss
i
n
g
a
n
d
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
4
5
,
n
o
.
4
,
p
p
.
4
2
7
–
4
3
7
,
Ju
l
.
2
0
0
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
p
m
.
2
0
0
9
.
0
3
.
0
0
2
.
[
2
2
]
P.
A
.
F
l
a
c
h
a
n
d
M
.
K
u
l
l
,
“
P
r
e
c
i
si
o
n
-
r
e
c
a
l
l
-
g
a
i
n
c
u
r
v
e
s:
P
R
a
n
a
l
y
si
s
d
o
n
e
r
i
g
h
t
,
”
A
d
v
a
n
c
e
s
i
n
N
e
u
ra
l
I
n
f
o
rm
a
t
i
o
n
Pro
c
e
ss
i
n
g
S
y
s
t
e
m
s
,
p
p
.
8
3
8
–
8
4
6
,
2
0
1
5
.
[
2
3
]
C
.
C
a
o
,
D
.
C
h
i
c
c
o
,
a
n
d
M
.
M
.
H
o
f
f
man
,
“
T
h
e
M
C
C
-
F
1
c
u
r
v
e
:
a
p
e
r
f
o
r
man
c
e
e
v
a
l
u
a
t
i
o
n
t
e
c
h
n
i
q
u
e
f
o
r
b
i
n
a
r
y
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
a
rXi
v
p
re
p
r
i
n
t
,
p
p
.
1
–
1
7
,
2
0
2
0
.
[
2
4
]
L
.
A
.
D
a
l
t
o
n
,
“
O
p
t
i
m
a
l
R
O
C
-
b
a
se
d
c
l
a
ssi
f
i
c
a
t
i
o
n
a
n
d
p
e
r
f
o
r
man
c
e
a
n
a
l
y
si
s
u
n
d
e
r
b
a
y
e
si
a
n
u
n
c
e
r
t
a
i
n
t
y
mo
d
e
l
s,”
I
EEE/
A
C
M
T
ra
n
s
a
c
t
i
o
n
s
o
n
C
o
m
p
u
t
a
t
i
o
n
a
l
Bi
o
l
o
g
y
a
n
d
B
i
o
i
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
3
,
n
o
.
4
,
p
p
.
7
1
9
–
7
2
9
,
J
u
l
.
2
0
1
6
,
d
o
i
:
1
0
.
1
1
0
9
/
T
C
B
B
.
2
0
1
5
.
2
4
6
5
9
6
6
.
[
2
5
]
A
.
M
.
C
a
r
r
i
n
g
t
o
n
e
t
a
l
.
,
“
A
n
e
w
c
o
n
c
o
r
d
a
n
t
p
a
r
t
i
a
l
A
U
C
a
n
d
p
a
r
t
i
a
l
C
s
t
a
t
i
s
t
i
c
f
o
r
i
m
b
a
l
a
n
c
e
d
d
a
t
a
i
n
t
h
e
e
v
a
l
u
a
t
i
o
n
o
f
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
s
,
”
B
M
C
M
e
d
i
c
a
l
I
n
f
o
r
m
a
t
i
c
s
a
n
d
D
e
c
i
s
i
o
n
M
a
k
i
n
g
,
v
o
l
.
2
0
,
n
o
.
1
,
p
p
.
1
–
1
2
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
8
6
/
s
1
2
9
1
1
-
019
-
1
0
1
4
-
6.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
S
a
la
h
E
d
d
in
e
M
a
n
so
u
r
c
o
m
p
lete
d
h
is
h
ig
h
e
r
e
d
u
c
a
ti
o
n
i
n
Ca
sa
b
lan
c
a
,
M
o
r
o
c
c
o
.
He
sta
rted
h
is P
h
.
D
.
in
a
rti
f
icia
l
in
telli
g
e
n
c
e
in
2
0
2
0
.
Cu
rre
n
t
ly
,
h
e
is a p
ro
f
e
ss
o
r
o
f
in
f
o
r
m
a
ti
c
s
a
t
th
e
M
i
n
istry
o
f
Ed
u
c
a
ti
o
n
in
M
o
r
o
c
c
o
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
1
9
m
a
n
so
u
r9
4
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
I
SS
N:
2089
-
4864
Leve
r
a
g
in
g
th
e
lea
r
n
in
g
fo
ca
l
p
o
in
t a
lg
o
r
ith
m
fo
r
emo
tio
n
a
l
in
tellig
en
ce
(
S
a
la
h
E
d
d
in
e
Ma
n
s
o
u
r
)
773
Abd
e
lh
a
k
S
a
k
h
i
c
o
m
p
lete
d
h
is
h
ig
h
e
r
e
d
u
c
a
ti
o
n
i
n
Ca
sa
b
lan
c
a
,
M
o
ro
c
c
o
.
He
sta
rted
h
is
P
h
.
D
.
i
n
a
rti
f
icia
l
in
tell
ig
e
n
c
e
in
2
0
2
0
.
Cu
rre
n
t
ly
,
h
e
is a p
ro
f
e
ss
o
r
o
f
m
a
th
e
m
a
ti
c
s
a
t
th
e
M
i
n
istry
o
f
Ed
u
c
a
ti
o
n
in
M
o
r
o
c
c
o
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sa
k
h
i4
4
2
@g
m
a
il
.
c
o
m
.
La
r
b
i
K
z
a
z
re
c
e
iv
e
d
d
o
c
to
ra
te
d
e
g
re
e
in
c
o
m
p
u
ter
sc
ien
c
e
f
ro
m
L
il
le
Un
iv
e
rsit
y
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
,
F
ra
n
c
e
,
in
1
9
8
5
.
He
is
p
ro
f
e
ss
o
r
in
in
f
o
rm
a
ti
o
n
s
y
ste
m
s
a
t
IS
C
A
E
Bu
sin
e
ss
S
c
h
o
o
l,
Ca
sa
b
lan
c
a
,
M
o
ro
c
c
o
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
se
m
a
n
ti
c
in
teg
ra
ti
o
n
,
d
a
ta
wa
re
h
o
u
se
d
e
sig
n
,
m
a
c
h
in
e
lea
rn
in
g
a
n
d
b
ig
d
a
ta
a
p
p
li
c
a
ti
o
n
s
i
n
d
ig
it
a
l.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
k
z
a
z
.
larb
i@g
m
a
il
.
c
o
m
.
Abd
e
r
r
a
h
i
m
S
e
k
k
a
k
i
c
o
m
p
lete
d
h
is
g
ra
d
u
a
te
stu
d
ies
i
n
T
o
u
lo
u
se
,
F
ra
n
c
e
.
A
f
ter
h
a
v
in
g
p
a
ss
e
d
h
is
m
a
ste
r
'
s
d
e
g
r
e
e
a
n
d
h
is
DEA
in
c
o
m
p
u
ter
sc
ien
c
e
,
h
e
b
e
g
a
n
h
is
P
h
.
D.
i
n
n
e
tw
o
rk
m
a
n
a
g
e
m
e
n
t,
d
e
f
e
n
d
e
d
in
1
9
9
1
.
He
c
ro
w
n
e
d
h
is
c
a
re
e
r
in
c
o
m
p
u
ter
sc
ien
c
e
w
it
h
a
sta
te
th
e
sis
in
2
0
0
2
.
Cu
rre
n
tl
y
,
h
e
is
a
f
u
ll
p
ro
f
e
ss
o
r
in
Un
iv
e
rsity
Ha
ss
a
n
II
o
f
Ca
s
a
b
lan
c
a
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
s
e
k
k
a
b
d
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.