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.
3
6
,
No
.
2
,
N
o
v
em
b
e
r
20
24
,
p
p
.
1
30
1
~
1
30
8
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
6
.
i
2
.
pp
1
30
1
-
1
30
8
1301
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
E
nha
ncing
stress
detec
tion in
wea
r
a
ble Io
T dev
ices
using
federate
d learnin
g
and LS
TM
bas
ed hybrid mo
del
Na
o
ua
l Mo
uh
ni
1
,
I
btiss
a
m
Am
a
lo
u
2,
3
,
Sa
na
Cha
k
ri
3
,
M
o
ha
m
edo
u
C
heik
h
T
o
ura
d
4
,
M
o
ha
m
ed
Cha
k
ra
o
ui
5
,
Abdelm
o
un
a
im
Abda
li
2
1
GL
-
I
S
I
Te
a
m,
D
e
p
a
r
t
me
n
t
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
,
F
S
T
E,
U
M
I
-
M
e
k
n
e
s,
Er
r
a
c
h
i
d
i
a
,
M
o
r
o
c
c
o
2
C
I
S
I
EV
,
F
S
TG
,
U
n
i
v
e
r
si
t
y
C
a
d
i
A
y
y
a
d
,
M
a
r
r
a
k
e
c
h
,
M
o
r
o
c
c
o
3
LA
M
I
G
EP,
E
M
S
I
M
a
r
r
a
k
e
c
h
,
M
a
r
r
a
k
e
c
h
,
M
o
r
o
c
c
o
4
S
c
i
e
n
t
i
f
i
c
C
o
m
p
u
t
i
n
g
,
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
D
a
t
a
S
c
i
e
n
c
e
R
e
se
a
r
c
h
U
n
i
t
(
C
S
I
D
S
)
/
F
ST
U
n
i
v
e
r
si
t
y
o
f
N
o
u
a
k
c
h
o
t
t
,
N
o
u
a
k
c
h
o
t
t
,
M
a
u
r
i
t
a
n
i
a
5
LS3
M
,
P
o
l
y
D
i
sc
i
p
l
i
n
a
r
y
F
a
c
u
l
t
y
o
f
K
h
o
u
r
i
b
g
a
,
S
u
l
t
a
n
M
o
l
y
S
l
i
m
a
n
e
U
n
i
v
e
r
si
t
y
,
B
e
n
i
M
e
l
l
a
l
,
M
o
r
o
c
c
o
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
4
,
2
0
2
4
R
ev
is
ed
Au
g
6
,
2
0
2
4
Acc
ep
ted
A
ug
11
,
2
0
2
4
I
n
th
e
d
o
m
a
in
o
f
sm
a
rt
h
e
a
lt
h
d
e
v
ice
s,
th
e
a
c
c
u
ra
te
d
e
tec
ti
o
n
o
f
p
h
y
sic
a
l
in
d
ica
to
rs
le
v
e
ls
p
lay
s
a
c
ru
c
ial
ro
le
in
e
n
h
a
n
c
in
g
sa
fe
ty
a
n
d
we
ll
-
b
e
in
g
.
Th
is
p
a
p
e
r
i
n
tr
o
d
u
c
e
s
a
c
ro
ss
d
e
v
ice
fe
d
e
ra
ted
lea
rn
in
g
fra
m
e
wo
rk
u
sin
g
h
y
b
rid
d
e
e
p
lea
rn
in
g
m
o
d
e
l.
S
p
e
c
ifi
c
a
ll
y
,
th
e
p
a
p
e
r
p
r
e
se
n
ts
a
c
o
m
p
re
h
e
n
siv
e
c
o
m
p
a
riso
n
o
f
d
iffere
n
t
c
o
m
b
i
n
a
ti
o
n
o
f
l
o
n
g
sh
o
rt
-
term
m
e
m
o
ry
(LS
TM
),
g
a
ted
re
c
u
rre
n
t
u
n
it
(G
RU)
,
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
two
rk
(CNN
),
ra
n
d
o
m
f
o
re
st
(RF
),
a
n
d
e
x
trem
e
g
ra
d
ie
n
t
b
o
o
stin
g
(
XG
Bo
o
st
)
,
in
o
rd
e
r
to
fo
re
c
a
st
stre
ss
lev
e
ls
b
y
u
ti
li
z
i
n
g
ti
m
e
se
ries
i
n
fo
rm
a
ti
o
n
d
e
ri
v
e
d
fr
o
m
we
a
ra
b
le
sm
a
rt
g
a
d
g
e
ts.
Th
e
LS
TM
-
RF
m
o
d
e
l
d
e
m
o
n
stra
ted
th
e
h
ig
h
e
st
lev
e
l
o
f
a
c
c
u
ra
c
y
,
a
c
h
iev
in
g
9
3
.
5
3
%
f
o
r
u
se
r
1
,
9
9
.
4
0
%
f
o
r
u
se
r
2
,
a
n
d
9
7
.
8
8
%
f
o
r
u
se
r
3
.
S
imil
a
rly
,
t
h
e
LS
T
M
-
XG
Bo
o
st
m
o
d
e
l
y
ield
e
d
fa
v
o
ra
b
le o
u
tc
o
m
e
s,
with
a
c
c
u
ra
c
y
ra
tes
o
f
8
5
.
8
8
%
,
9
8
.
5
5
%
,
a
n
d
9
2
.
0
2
%
fo
r
u
se
r
s
1
,
2
,
a
n
d
3
,
re
sp
e
c
ti
v
e
ly
,
o
u
t
o
f
2
3
u
se
rs
stu
d
ie
d
.
Th
e
s
e
fin
d
in
g
s
h
ig
h
li
g
h
t
th
e
e
ffica
c
y
o
f
fe
d
e
ra
t
e
d
lea
rn
i
n
g
a
n
d
t
h
e
u
ti
li
z
a
ti
o
n
o
f
h
y
b
rid
m
o
d
e
ls
i
n
stre
ss
d
e
tec
ti
o
n
.
Un
li
k
e
trad
it
i
o
n
a
l
c
e
n
tralize
d
lea
rn
in
g
p
a
ra
d
ig
m
s,
th
e
p
re
se
n
ted
fe
d
e
ra
ted
a
p
p
ro
a
c
h
e
n
su
re
s
p
ri
v
a
c
y
p
re
se
rv
a
ti
o
n
a
n
d
re
d
u
c
e
s
d
a
ta t
ra
n
sm
issio
n
re
q
u
irem
e
n
ts
b
y
p
r
o
c
e
ss
in
g
d
a
ta l
o
c
a
ll
y
o
n
E
d
g
e
d
e
v
ice
s.
K
ey
w
o
r
d
s
:
Fed
er
ated
l
ea
r
n
in
g
GR
U
Hy
b
r
id
m
o
d
els
I
o
T
w
ea
r
ab
les
L
STM
R
an
d
o
m
f
o
r
est
Stre
s
s
d
etec
tio
n
XGBo
o
s
t
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
:
Nao
u
al
Mo
u
h
n
i
Dep
ar
tm
en
t
o
f
co
m
p
u
ter
s
cien
ce
,
FS
T
E
,
UM
I
o
f
Me
k
n
es
5
2
0
0
0
E
r
r
ac
h
id
ia,
Mo
r
o
cc
o
E
m
ail:
n
.
m
o
u
h
n
i@
ieee
.
o
r
g
1.
I
NT
RO
D
UCT
I
O
N
I
n
r
ec
en
t
y
ea
r
s
,
th
e
p
r
o
life
r
a
tio
n
o
f
wea
r
ab
le
in
ter
n
et
o
f
th
in
g
s
(
I
o
T
)
d
ev
ices
h
as
s
ig
n
if
ican
tly
tr
an
s
f
o
r
m
ed
t
h
e
lan
d
s
ca
p
e
o
f
p
er
s
o
n
al
h
ea
lth
ca
r
e
m
o
n
ito
r
i
n
g
,
as
s
h
o
wn
in
[
1
]
-
[
5
]
.
Stre
s
s
,
a
p
r
ev
alen
t
h
ea
lth
is
s
u
e
ass
o
ciate
d
with
v
ar
io
u
s
p
h
y
s
ical
a
n
d
m
en
tal
ail
m
en
ts
,
ca
n
cu
r
r
e
n
tly
b
e
b
e
tter
m
o
n
ito
r
ed
b
y
in
co
r
p
o
r
atin
g
wea
r
ab
le
s
en
s
o
r
s
an
d
I
o
T
tech
n
o
lo
g
ies.
Acc
u
r
ate
d
etec
tio
n
o
f
s
tr
ess
lev
els
u
s
in
g
wea
r
ab
le
d
ev
ices c
an
r
esu
lt in
tim
ely
i
n
ter
v
en
tio
n
s
,
th
e
r
eb
y
lea
d
in
g
to
n
o
tab
le
en
h
an
ce
m
en
ts
in
h
ea
lth
o
u
tco
m
es.
Desp
ite
ad
v
an
ce
m
en
ts
in
wea
r
ab
le
tech
n
o
lo
g
y
,
s
ev
er
al
ch
allen
g
es
p
er
s
is
t
in
th
e
ac
cu
r
ate
an
d
ef
f
icien
t
d
etec
tio
n
o
f
s
tr
ess
.
T
r
ad
itio
n
al
ce
n
tr
alize
d
m
o
d
els
f
o
r
s
tr
ess
d
etec
tio
n
r
aise
s
ig
n
i
f
ican
t
p
r
iv
ac
y
an
d
s
ec
u
r
ity
co
n
c
er
n
s
as
t
h
ey
r
eq
u
ir
e
d
ata
to
b
e
tr
a
n
s
m
itted
to
c
en
tr
al
s
er
v
er
s
f
o
r
p
r
o
ce
s
s
in
g
.
Ad
d
itio
n
ally
,
th
ese
m
o
d
els
o
f
ten
f
ail
to
ac
h
iev
e
h
i
g
h
ac
cu
r
ac
y
an
d
r
o
b
u
s
tn
ess
ac
r
o
s
s
d
iv
er
s
e
u
s
er
d
atasets
d
u
e
to
th
eir
in
ab
ilit
y
to
ef
f
ec
tiv
ely
ca
p
tu
r
e
tem
p
o
r
al
d
ep
en
d
en
cies in
p
h
y
s
io
lo
g
ical
d
ata.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
2
,
No
v
em
b
er
20
24
:
1
3
0
1
-
130
8
1302
Pre
v
io
u
s
r
esear
ch
h
as
ex
p
lo
r
ed
v
ar
i
o
u
s
m
eth
o
d
s
f
o
r
s
tr
ess
d
etec
tio
n
u
s
in
g
I
o
T
d
ev
ice
s
.
Ma
jo
r
co
n
tr
ib
u
to
r
s
in
th
is
f
ield
h
av
e
u
tili
ze
d
s
in
g
le
n
eu
r
al
n
etwo
r
k
ar
c
h
itectu
r
es
o
r
tr
a
d
itio
n
al
m
ac
h
in
e
lear
n
in
g
m
o
d
els.
C
an
et
a
l.
[
6
]
u
tili
ze
d
co
n
v
o
l
u
tio
n
al
n
eu
r
al
n
e
two
r
k
s
(
C
NNs)
f
o
r
s
tr
ess
d
etec
tio
n
b
u
t
f
ac
ed
lim
itatio
n
s
in
ca
p
tu
r
in
g
lo
n
g
-
t
er
m
d
ep
en
d
en
cies
in
th
e
d
ata.
Patel
et
a
l.
[
7
]
im
p
lem
en
ted
r
an
d
o
m
f
o
r
est
(
R
F)
m
o
d
els,
wh
ich
p
r
o
v
id
e
d
r
o
b
u
s
t
class
if
icatio
n
b
u
t
lack
e
d
t
h
e
ab
ilit
y
to
h
an
d
le
s
eq
u
en
ti
al
d
ata
e
f
f
ec
tiv
ely
.
C
h
en
et
a
l.
[
8
]
em
p
lo
y
e
d
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
ST
M)
n
etwo
r
k
s
,
ac
h
iev
i
n
g
b
ette
r
p
er
f
o
r
m
an
ce
with
tim
e
-
s
er
ies d
ata
b
u
t e
n
co
u
n
ter
in
g
co
m
p
u
tatio
n
al
in
e
f
f
icien
ci
es o
n
r
eso
u
r
ce
-
co
n
s
tr
ain
ed
d
e
v
ices.
T
h
e
ex
is
tin
g
liter
atu
r
e
h
i
g
h
lig
h
ts
s
ev
er
al
u
n
r
eso
lv
ed
p
r
o
b
le
m
s
,
in
clu
d
in
g
d
ata
p
r
iv
ac
y
a
n
d
s
ec
u
r
ity
is
s
u
es,
m
o
d
el
ac
cu
r
ac
y
an
d
r
o
b
u
s
tn
ess
,
an
d
th
e
ef
f
ec
tiv
e
h
an
d
lin
g
o
f
s
eq
u
e
n
tial
d
ata.
Hig
h
co
m
p
u
tatio
n
al
r
eq
u
ir
em
e
n
ts
o
f
d
ee
p
lear
n
in
g
m
o
d
els
lim
it
th
eir
p
r
ac
tical
ap
p
licatio
n
o
n
wea
r
ab
le
d
e
v
ices,
an
d
th
er
e
is
v
ar
iab
ilit
y
in
m
o
d
el
p
er
f
o
r
m
an
ce
ac
r
o
s
s
d
if
f
er
en
t
u
s
er
s
d
u
e
to
in
d
iv
id
u
al
p
h
y
s
io
lo
g
ical
d
if
f
er
en
c
es.
Fu
r
th
er
m
o
r
e
,
d
ela
y
s
in
d
ata
p
r
o
ce
s
s
in
g
h
in
d
er
r
ea
l
-
tim
e
d
ete
ctio
n
ca
p
ab
ilit
ies,
an
d
lim
ited
ev
alu
atio
n
m
et
r
ics
d
o
n
o
t
p
r
o
v
id
e
a
f
u
ll
ass
ess
m
en
t
o
f
m
o
d
el
p
e
r
f
o
r
m
an
ce
.
T
o
ad
d
r
ess
th
ese
g
ap
s
,
o
u
r
s
tu
d
y
in
tr
o
d
u
ce
s
a
f
ed
er
ated
l
ea
r
n
in
g
[
9
]
f
r
am
ew
o
r
k
c
o
m
b
in
e
d
with
a
h
y
b
r
id
d
ee
p
lear
n
in
g
m
o
d
el
f
o
r
s
tr
ess
d
etec
tio
n
u
s
in
g
d
ata
p
r
o
v
id
e
d
f
r
o
m
wea
r
ab
le
I
o
T
d
ev
ices.
T
h
e
f
ed
er
ated
l
ea
r
n
in
g
a
p
p
r
o
ac
h
e
n
h
an
ce
s
p
r
i
v
ac
y
a
n
d
s
ec
u
r
ity
,
ad
d
r
ess
in
g
s
ig
n
if
ican
t
p
r
iv
ac
y
co
n
ce
r
n
s
in
ce
n
tr
alize
d
d
ata
co
llectio
n
m
eth
o
d
s
.
Fu
r
t
h
er
m
o
r
e,
t
h
e
ev
alu
ate
d
h
y
b
r
id
m
o
d
el
s
,
s
u
ch
as
th
e
co
m
b
in
atio
n
s
L
STM
-
RF
an
d
L
STM
-
XGBo
o
s
t,
ar
e
p
r
es
en
tin
g
th
e
h
ig
h
est
ac
cu
r
ac
y
f
o
r
alm
o
s
t
all
th
e
in
v
o
lv
ed
u
s
er
s
.
T
h
ese
m
o
d
els
ar
e
o
p
tim
ized
f
o
r
co
m
p
u
tatio
n
al
ef
f
icien
cy
,
m
ak
i
n
g
th
em
s
u
itab
le
f
o
r
im
p
lem
en
ta
tio
n
o
n
r
eso
u
r
ce
-
co
n
s
tr
ain
e
d
d
ev
ices
u
s
in
g
T
in
y
ML
tech
n
i
q
u
es
.
On
th
e
o
th
er
h
an
d
,
t
h
e
f
ed
er
ated
lear
n
in
g
a
p
p
r
o
ac
h
en
s
u
r
es
th
at
th
e
s
tu
d
i
ed
m
o
d
el
s
g
en
er
alize
well
ac
r
o
s
s
d
if
f
er
en
t
u
s
er
s
b
y
tr
ain
i
n
g
o
n
d
iv
er
s
e
lo
ca
l
d
atasets
,
m
itig
atin
g
v
ar
iab
ilit
y
in
in
d
iv
i
d
u
al
p
h
y
s
io
lo
g
ical
r
e
s
p
o
n
s
es.
Mo
r
eo
v
er
,
o
u
r
e
v
alu
ated
m
o
d
el
s
s
u
p
p
o
r
t
r
ea
l
-
tim
e
s
tr
ess
d
etec
tio
n
,
en
a
b
lin
g
tim
ely
in
ter
v
e
n
tio
n
s
an
d
im
p
r
o
v
in
g
o
v
e
r
all
h
ea
lth
o
u
tco
m
es.
T
h
e
f
o
llo
win
g
s
ec
tio
n
s
o
f
th
i
s
m
an
u
s
cr
ip
t
will
d
em
o
n
s
tr
ate
th
e
r
elev
a
n
ce
an
d
im
p
ac
t
o
f
o
u
r
w
o
r
k
,
s
ec
tio
n
1
p
r
o
v
id
es
th
e
in
tr
o
d
u
ctio
n
an
d
b
ac
k
g
r
o
u
n
d
.
S
ec
tio
n
2
d
escr
ib
es
th
e
m
eth
o
d
o
lo
g
y
an
d
ex
p
er
im
e
n
tal
s
etu
p
.
S
ec
tio
n
3
p
r
esen
ts
th
e
r
esu
lts
an
d
th
eir
im
p
licatio
n
s
.
S
ec
tio
n
4
d
is
cu
s
s
es
th
e
f
in
d
i
n
g
s
an
d
co
m
p
ar
es
th
em
with
ex
is
tin
g
wo
r
k
s
,
an
d
s
ec
tio
n
5
co
n
cl
u
d
es with
f
u
tu
r
e
wo
r
k
d
ir
ec
tio
n
s
.
2.
M
O
T
I
VAT
I
O
N
AND
R
E
L
A
T
E
D
WO
RK
S
R
ec
en
t
ad
v
an
ce
m
en
ts
in
s
tr
es
s
d
etec
tio
n
u
s
in
g
wea
r
a
b
le
I
o
T
d
ev
ices
h
av
e
h
ig
h
lig
h
ted
th
e
p
o
ten
tial
o
f
f
ed
er
ated
lear
n
in
g
an
d
h
y
b
r
id
m
o
d
els
to
ad
d
r
ess
k
ey
ch
allen
g
es
in
th
e
f
ield
.
Alah
m
ad
i
et
a
l.
[
1
0
]
p
r
o
v
id
e
d
a
co
m
p
r
eh
en
s
iv
e
o
v
er
v
iew
o
f
a
p
r
iv
ac
y
-
p
r
eser
v
ed
I
o
T
-
b
ased
m
en
tal
s
tr
ess
d
etec
tio
n
f
r
am
ew
o
r
k
u
s
in
g
f
ed
er
ated
lear
n
in
g
,
em
p
h
asizi
n
g
th
e
im
p
o
r
tan
ce
o
f
d
ec
en
tr
a
lized
lear
n
in
g
m
o
d
els
in
p
r
eser
v
in
g
d
ata
p
r
iv
ac
y
wh
ile
en
ab
lin
g
ef
f
ec
tiv
e
m
o
d
el
tr
ain
in
g
ac
r
o
s
s
d
is
tr
ib
u
te
d
d
e
v
ices.
Similar
ly
,
J
ian
g
e
t
a
l.
[
1
1
]
ex
p
lo
r
e
d
p
r
iv
ac
y
-
p
r
eser
v
in
g
tech
n
iq
u
es
in
f
ed
er
ated
lear
n
in
g
,
f
o
cu
s
in
g
o
n
th
eir
in
teg
r
atio
n
with
in
I
o
T
f
r
am
ewo
r
k
s
to
en
s
u
r
e
s
ec
u
r
e
d
ata
h
a
n
d
lin
g
a
n
d
p
r
o
ce
s
s
in
g
.
T
h
ese
s
tu
d
ies
u
n
d
er
s
co
r
e
th
e
p
o
ten
tial
o
f
f
e
d
er
ated
lea
r
n
in
g
to
ad
d
r
ess
p
r
iv
ac
y
co
n
ce
r
n
s
,
wh
i
ch
is
a
cr
itical
asp
ec
t o
f
o
u
r
r
e
s
ea
r
ch
.
Sev
er
al
s
tu
d
ies
h
av
e
in
v
esti
g
ated
th
e
u
s
e
o
f
h
y
b
r
id
m
o
d
el
s
to
im
p
r
o
v
e
d
iag
n
o
s
tic
ac
cu
r
ac
y
in
I
o
T
d
ev
ices.
Yaq
o
o
b
et
a
l.
[
1
2
]
e
x
am
in
ed
th
e
i
n
teg
r
atio
n
o
f
v
ar
i
o
u
s
m
ac
h
in
e
lear
n
in
g
m
o
d
els,
d
em
o
n
s
tr
atin
g
h
o
w
h
y
b
r
id
a
p
p
r
o
ac
h
es
ca
n
s
ig
n
if
ican
tly
en
h
an
ce
d
iag
n
o
s
tic
ac
cu
r
ac
y
in
wea
r
ab
le
d
ev
ices.
Alm
ad
h
o
r
et
a
l.
[
1
3
]
p
r
esen
ted
a
d
etailed
an
aly
s
is
o
f
wr
is
t
-
b
ased
elec
tr
o
d
er
m
a
l
ac
tiv
ity
m
o
n
ito
r
in
g
f
o
r
s
tr
ess
d
etec
tio
n
u
s
in
g
f
ed
er
ated
lear
n
in
g
,
em
p
h
asizi
n
g
th
e
p
o
ten
tial
o
f
h
y
b
r
id
m
o
d
els
in
th
is
d
o
m
ain
.
Ya
q
o
o
b
e
t
a
l.
[
1
4
]
lev
er
a
g
ed
h
y
b
r
id
m
o
d
els
to
ac
h
iev
e
e
n
h
an
ce
d
d
iag
n
o
s
tic
ac
cu
r
ac
y
,
p
a
r
ticu
lar
ly
in
th
e
c
o
n
tex
t
o
f
s
k
in
lesi
o
n
d
iag
n
o
s
is
.
Kh
an
et
a
l.
[
1
5
]
p
r
o
p
o
s
ed
an
asy
n
ch
r
o
n
o
u
s
f
ed
e
r
ated
lear
n
in
g
ap
p
r
o
ac
h
f
o
r
im
p
r
o
v
ed
ca
r
d
io
v
ascu
lar
d
is
ea
s
e
p
r
ed
ictio
n
,
h
ig
h
lig
h
tin
g
th
e
p
r
ac
tical
im
p
licatio
n
s
o
f
tim
el
y
h
ea
lth
m
o
n
ito
r
in
g
.
J
u
n
i
o
r
a
n
d
Kam
ien
s
k
i
[1
6
]
ex
p
an
d
e
d
o
n
t
h
is
b
y
d
ev
elo
p
in
g
h
y
b
r
id
m
o
d
els
th
at
co
m
b
in
e
m
u
ltip
le
n
e
u
r
al
n
etwo
r
k
a
r
ch
itectu
r
es
to
im
p
r
o
v
e
t
h
e
ac
cu
r
ac
y
an
d
r
esp
o
n
s
iv
en
ess
o
f
p
er
f
o
r
m
a
n
ce
b
e
h
av
io
r
d
etec
tio
n
in
f
o
g
-
I
o
T
s
y
s
tem
s
.
Desp
ite
th
ese
ad
v
an
ce
m
en
ts
,
t
r
ad
itio
n
al
ce
n
tr
alize
d
m
o
d
els
s
till
p
o
s
e
p
r
iv
ac
y
a
n
d
s
ec
u
r
ity
r
is
k
s
,
an
d
ex
is
tin
g
m
o
d
els
o
f
ten
f
ail
to
ac
h
iev
e
h
ig
h
ac
cu
r
ac
y
ac
r
o
s
s
d
iv
er
s
e
d
atasets
d
u
e
to
lim
it
atio
n
s
in
ca
p
tu
r
in
g
tem
p
o
r
al
d
ep
e
n
d
en
cies
in
p
h
y
s
io
lo
g
ical
d
ata.
Hig
h
c
o
m
p
u
tatio
n
al
r
eq
u
ir
em
en
ts
also
lim
it
th
e
p
r
ac
tical
ap
p
licatio
n
o
f
d
ee
p
lear
n
in
g
m
o
d
els o
n
r
eso
u
r
ce
-
c
o
n
s
tr
ain
ed
wea
r
ab
le
d
ev
ices.
Nan
d
i a
n
d
Xh
af
a
[
1
7
]
f
o
cu
s
ed
o
n
o
p
tim
izin
g
h
y
b
r
i
d
m
o
d
els
f
o
r
r
ea
l
-
tim
e
em
o
tio
n
s
tate
class
if
icatio
n
,
o
f
f
er
i
n
g
in
s
ig
h
ts
in
to
th
e
p
er
f
o
r
m
an
ce
en
h
an
ce
m
e
n
ts
ac
h
iev
ab
le
th
r
o
u
g
h
m
o
d
el
i
n
teg
r
atio
n
an
d
o
p
tim
izatio
n
tech
n
iq
u
es.
T
r
ip
ath
y
et
a
l.
[
1
8
]
ad
d
r
ess
ed
th
e
s
ca
lab
ilit
y
o
f
f
e
d
er
ated
lear
n
in
g
in
I
o
T
e
n
v
ir
o
n
m
en
ts
,
d
is
cu
s
s
in
g
h
o
w
s
ca
lab
le
s
o
lu
tio
n
s
ca
n
b
e
im
p
lem
en
ted
to
h
an
d
le
g
r
o
win
g
d
ata
v
o
lu
m
es a
n
d
d
ev
ice
co
u
n
ts
in
I
o
T
n
etwo
r
k
s
.
Ou
r
s
tu
d
y
r
ep
r
esen
ts
a
s
ig
n
if
ic
an
t
ad
v
a
n
ce
m
en
t
o
v
e
r
ex
is
tin
g
wo
r
k
b
y
tak
in
g
in
to
ac
co
u
n
t
e
n
h
an
c
in
g
n
o
t
o
n
l
y
th
e
ac
cu
r
ac
y
a
n
d
r
o
b
u
s
tn
ess
o
f
s
tr
ess
d
etec
tio
n
b
u
t
also
en
s
u
r
es
ef
f
icien
t
an
d
s
ec
u
r
e
d
ata
h
a
n
d
lin
g
th
r
o
u
g
h
f
ed
er
ate
d
lear
n
in
g
a
n
d
ed
g
e
co
m
p
u
tin
g
.
B
y
ad
d
r
ess
in
g
th
e
h
eter
o
g
en
eity
o
f
d
atasets
an
d
th
e
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
E
n
h
a
n
ci
n
g
s
tr
ess
d
etec
tio
n
in
w
ea
r
a
b
le
I
o
T d
ev
ices u
s
in
g
fe
d
era
ted
lea
r
n
in
g
a
n
d
…
(
N
a
o
u
a
l Mo
u
h
n
i
)
1303
ch
allen
g
e
o
f
im
b
alan
ce
d
d
ata,
o
u
r
ap
p
r
o
ac
h
p
r
o
v
id
es
a
s
ca
lab
le
an
d
p
r
ac
tical
s
o
lu
tio
n
f
o
r
r
ea
l
-
tim
e
s
tr
ess
m
o
n
ito
r
in
g
in
wea
r
ab
le
I
o
T
d
ev
ices.
T
h
e
k
ey
to
th
e
s
u
cc
es
s
o
f
a
f
ed
er
ated
lear
n
i
n
g
s
o
lu
tio
n
u
s
in
g
a
c
r
o
s
s
-
d
ev
ice
ar
c
h
itectu
r
e
lies
in
p
r
o
p
o
s
in
g
a
n
ef
f
icien
t
an
d
ef
f
ec
tiv
e
s
o
lu
tio
n
.
T
h
is
s
o
lu
tio
n
,
m
u
s
t
tak
e
in
to
ac
c
o
u
n
t
th
e
lim
ited
co
m
p
u
tatio
n
al
r
es
o
u
r
ce
s
o
f
e
d
g
e
d
e
v
ices
an
d
t
h
e
u
n
iq
u
e
d
ata
o
f
ea
ch
u
s
er
in
m
ea
s
u
r
in
g
s
tr
ess
lev
els.
T
h
is
ca
n
b
e
d
o
n
e
b
y
co
m
b
in
in
g
L
STM
a
n
d
RF
o
r
X
G
B
o
o
s
t a
s
we
will d
is
co
v
er
in
th
e
n
ex
t sectio
n
.
3.
M
E
T
H
O
D
Ou
r
p
ap
er
a
d
d
r
ess
es
th
e
ch
allen
g
e
o
f
ac
c
u
r
ately
d
etec
tin
g
s
tr
ess
lev
els
u
s
in
g
d
ata
f
r
o
m
wea
r
ab
le
I
o
T
d
ev
ices
wh
ile
p
r
eser
v
in
g
u
s
e
r
p
r
iv
ac
y
.
T
r
ad
itio
n
al
ce
n
tr
al
ized
m
o
d
els
f
o
r
s
tr
ess
d
etec
tio
n
r
aise
p
r
iv
ac
y
co
n
ce
r
n
s
a
n
d
o
f
ten
f
ail
to
ac
h
iev
e
h
ig
h
ac
cu
r
a
cy
ac
r
o
s
s
d
iv
er
s
e
u
s
er
d
atasets
.
We
in
tr
o
d
u
ce
in
th
is
s
ec
tio
n
,
a
cr
o
s
s
-
d
ev
ice
f
ed
er
ated
lear
n
i
n
g
f
r
am
ewo
r
k
u
s
in
g
h
y
b
r
id
d
ee
p
lear
n
in
g
m
o
d
els.
T
h
is
ap
p
r
o
ac
h
aim
s
to
im
p
r
o
v
e
s
tr
ess
d
etec
tio
n
ac
cu
r
ac
y
wh
ile
m
ain
tain
in
g
d
ata
p
r
iv
ac
y
b
y
p
r
o
ce
s
s
in
g
d
ata
lo
ca
ll
y
o
n
ed
g
e
d
ev
ices.
I
n
a
f
ed
er
ated
lear
n
i
n
g
co
n
te
x
t,
d
atasets
f
r
o
m
u
s
er
s
ar
e
n
o
t
m
er
g
ed
d
u
e
to
p
r
iv
ac
y
co
n
ce
r
n
s
an
d
to
th
e
d
is
tr
ib
u
ted
n
atu
r
e
o
f
t
h
e
p
r
o
b
l
em
.
I
n
s
tead
,
s
o
m
e
co
m
p
u
tatio
n
s
ar
e
d
o
n
e
lo
ca
lly
o
n
ea
ch
u
s
er
’
s
d
ata
an
d
th
e
n
ag
g
r
eg
ate
th
e
r
esu
lt.
Fig
u
r
e
1
d
escr
ib
es th
e
ad
o
p
te
d
wo
r
k
f
lo
w
f
o
r
o
u
r
s
tu
d
y
.
Fig
u
r
e
1
.
Fed
er
ate
d
lear
n
in
g
wo
r
k
f
lo
w
f
o
r
o
u
r
s
tu
d
y
I
n
o
r
d
e
r
t
o
t
r
a
i
n
a
n
d
e
v
a
l
u
a
t
e
o
u
r
p
r
o
p
o
s
e
d
h
y
b
r
i
d
m
o
d
e
l
s
,
w
e
u
s
e
d
t
h
e
P
R
I
D
E
d
a
t
a
s
e
t
i
n
t
r
o
d
u
c
e
d
b
y
[
1
9
]
.
I
t
o
f
f
e
r
s
an
e
x
ten
s
iv
e
ar
r
ay
o
f
ch
ar
ac
ter
is
tics
th
at
en
c
o
m
p
as
s
th
e
p
h
y
s
io
lo
g
ical
an
d
b
eh
av
io
r
al
d
im
en
s
io
n
s
o
f
th
e
in
d
iv
id
u
als
p
ar
ticip
atin
g
i
n
th
e
s
tu
d
y
.
Af
ter
th
e
d
ata
p
r
ep
r
o
ce
s
s
in
g
p
h
ase,
wh
er
e
we
d
id
in
co
r
p
o
r
ate
th
e
“s
tr
ess
ed
”
v
ar
iab
le,
wh
ich
will
b
e
p
r
ed
icted
b
y
o
u
r
m
o
d
el
af
ter
tr
ain
in
g
,
f
ea
tu
r
e
en
c
o
d
in
g
,
d
ata
in
teg
r
atio
n
an
d
n
o
r
m
aliza
tio
n
,
a
f
ea
tu
r
e
i
m
p
o
r
tan
ce
an
aly
s
is
was
m
a
d
e
u
s
in
g
RF
class
if
ier
to
p
r
ep
ar
e
th
e
d
ataset
f
o
r
th
e
f
ed
er
ated
l
ea
r
n
in
g
m
o
d
el.
T
h
e
d
ataset
co
n
tain
s
tim
e
s
er
ies
d
ata
co
llected
f
r
o
m
wea
r
ab
le
d
ev
ices
o
v
er
o
n
e
wee
k
,
2
4
h
o
u
r
s
p
er
d
ay
,
f
o
r
2
3
test
s
u
b
jects.
T
h
ey
ar
e
ag
ed
b
etwe
en
2
1
an
d
5
2
y
ea
r
s
o
ld
.
Data
lo
g
s
in
clu
d
e
d
ata
f
r
o
m
0
0
:0
0
to
2
3
:5
9
ea
ch
d
ay
,
an
d
Gap
s
o
f
at
least
4
0
m
in
u
tes
th
r
ee
tim
es
a
d
ay
f
o
r
b
atter
y
r
ec
h
ar
g
in
g
.
T
h
e
d
ataset
co
n
tain
s
tim
eser
ies
d
ata
f
r
o
m
2
3
s
u
b
jects,
o
r
g
an
ized
f
o
r
ea
c
h
s
u
b
ject
as
d
e
s
cr
ib
ed
in
F
ig
u
r
e
2
.
Fig
u
r
es 3
an
d
4
p
r
esen
t a
n
ex
a
m
p
le
o
f
th
e
h
ea
r
t r
ate
an
d
t
h
e
s
k
in
tem
p
er
atu
r
e
o
v
er
tim
e
f
o
r
a
r
an
d
o
m
u
s
er
.
Fig
u
r
e
2
.
Data
s
et
c
o
lu
m
n
d
esc
r
ip
tio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
2
,
No
v
em
b
er
20
24
:
1
3
0
1
-
130
8
1304
Fig
u
r
e
3
.
Hea
r
t
r
ate
an
d
s
k
i
n
t
em
p
er
atu
r
e
o
v
er
tim
e
f
o
r
u
s
er
1
Fig
u
r
e
4
.
Dis
tr
ib
u
tio
n
p
lo
ts
f
o
r
h
ea
r
t r
ate
a
n
d
s
k
in
tem
p
er
atu
r
e
T
h
e
d
ata
b
elo
n
g
in
g
to
in
d
i
v
id
u
al
u
s
er
s
is
u
p
lo
ad
ed
o
n
to
t
h
e
r
esp
ec
tiv
e
lo
ca
l
d
ev
ice.
I
n
o
r
d
er
to
p
r
eser
v
e
p
r
i
v
ac
y
a
n
d
r
esp
ec
t
t
h
e
f
ed
er
ate
d
lear
n
in
g
ap
p
r
o
ac
h
.
T
h
e
PR
I
DE
d
ataset
co
n
tain
s
d
ata
f
r
o
m
2
3
u
s
er
s
s
ep
ar
ated
o
n
two
f
iles
f
o
r
ea
ch
u
s
er
(
all
th
e
f
iles
h
av
e
th
e
s
am
e
co
lu
m
n
s
)
.
T
h
e
f
ir
s
t
f
i
le
p
r
esen
ts
d
ata
in
n
o
r
m
al
c
o
n
d
itio
n
s
,
t
h
e
s
ec
o
n
d
co
n
tain
s
d
ata
wh
en
th
e
u
s
e
r
is
u
n
d
er
s
tr
ess
f
u
l
co
n
d
itio
n
s
.
W
e
f
ir
s
t
clea
n
ed
d
ata,
ad
d
h
ea
d
er
s
an
d
co
d
e
d
Stre
s
s
ed
co
lu
m
n
v
alu
es
(
b
in
ar
y
v
a
r
iab
le
0
=
‘
n
o
r
m
al
’
an
d
1=
‘
s
tr
ess
ed
’
)
.
At
th
e
en
d
o
f
th
is
s
tep
,
we
p
r
ep
ar
ed
o
n
e
m
er
g
ed
f
ile
f
o
r
e
v
er
y
u
s
er
wh
ic
h
will
b
e
u
s
ed
in
t
h
e
n
ex
t
s
tep
to
s
elec
t im
p
o
r
tan
t f
ea
tu
r
es th
at
i
n
f
lu
en
ce
th
e
tar
g
et
“
s
tr
ess
ed
”
.
I
n
o
r
d
er
to
r
ed
u
ce
th
e
n
u
m
b
e
r
o
f
f
ea
tu
r
es
o
n
th
e
d
ataset,
we
u
s
ed
a
RF
class
if
ier
to
d
etec
t
th
e
m
o
s
t
im
p
o
r
tan
t
f
ea
tu
r
es
f
o
r
o
u
r
s
tu
d
y
.
W
e
f
ir
s
t
ca
lcu
late
f
ea
tu
r
e
im
p
o
r
tan
ce
lo
ca
lly
f
o
r
ev
e
r
y
u
s
er
,
th
en
ag
g
r
eg
ate
th
e
r
esu
lt
to
h
a
v
e
th
e
a
b
o
v
e
class
if
icatio
n
as
o
n
th
e
F
ig
u
r
e
5
.
T
h
e
n
th
e
t
o
p
1
0
f
ea
t
u
r
e
s
with
th
e
h
ig
h
est
im
p
o
r
tan
ce
s
co
r
e
ar
e
u
s
ed
s
in
c
e
th
ey
ar
e
th
e
f
ea
tu
r
es th
at
c
o
n
tr
ib
u
te
th
e
m
o
s
t to
t
h
e
m
o
d
el
’
s
p
r
ed
ictio
n
.
Fig
u
r
e
5
.
Featu
r
e
im
p
o
r
ta
n
ce
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
E
n
h
a
n
ci
n
g
s
tr
ess
d
etec
tio
n
in
w
ea
r
a
b
le
I
o
T d
ev
ices u
s
in
g
fe
d
era
ted
lea
r
n
in
g
a
n
d
…
(
N
a
o
u
a
l Mo
u
h
n
i
)
1305
Af
ter
d
ata
an
aly
s
is
,
we
f
o
u
n
d
th
at
th
e
two
class
es
f
o
r
tar
g
et
“
s
tr
ess
ed
”
ar
e
n
o
t
b
alan
ce
d
,
w
h
ich
will
ca
u
s
e
ce
r
tain
ly
a
m
o
d
el
o
v
e
r
f
itti
n
g
.
T
h
at
’
s
wh
y
,
we
u
s
ed
SMOT
E
tech
n
ic
to
b
ala
n
ce
d
ata
f
o
r
ea
ch
u
s
er
.
W
h
en
u
tili
zin
g
alg
o
r
ith
m
s
s
u
ch
as
XGBo
o
s
t
o
r
o
th
er
m
o
d
els
th
at
o
f
f
er
f
u
n
ctio
n
ality
f
o
r
in
co
r
p
o
r
atin
g
class
weig
h
ts
,
it
is
p
o
s
s
ib
le
to
ass
i
g
n
weig
h
ts
ex
p
licitly
to
u
s
e
c
lass
weig
h
tin
g
tech
n
ic.
T
h
e
n
ex
t
s
tep
co
n
s
is
ts
o
n
tr
ain
in
g
m
o
d
els
lo
ca
lly
u
s
in
g
ea
ch
u
s
er
’
s
d
ataset,
th
e
r
esu
lt
weig
h
ts
wer
e
lo
ad
ed
af
ter
th
at
an
d
th
en
ag
g
r
eg
ated
to
u
p
d
ate
th
e
g
lo
b
al
m
o
d
el.
T
h
e
m
o
d
el
r
esu
lt
will
b
e
d
is
cu
s
s
ed
in
th
e
“r
esu
lt
an
d
d
is
cu
s
s
io
n
s
ec
tio
n
”
.
T
h
e
d
ata
th
at
was
g
ath
er
ed
th
e
n
an
aly
ze
d
u
tili
zin
g
Py
th
o
n
an
d
T
en
s
o
r
Flo
w
lib
r
ar
ies,
an
d
t
h
e
k
e
y
m
ea
s
u
r
es
u
tili
ze
d
f
o
r
th
e
e
v
al
u
atio
n
o
f
th
e
s
tr
ess
d
etec
tio
n
m
o
d
el
in
clu
d
ed
ac
c
u
r
ac
y
,
p
r
e
cisi
o
n
,
r
ec
all,
an
d
F1
-
s
co
r
e.
I
n
th
is
s
tu
d
y
,
m
u
ltip
le
n
e
u
r
al
n
etwo
r
k
a
r
ch
itectu
r
es
wer
e
ap
p
lied
to
m
ea
s
u
r
e
th
eir
e
f
f
icien
cy
in
s
tr
ess
d
etec
tio
n
with
in
th
e
f
ed
e
r
ated
lear
n
in
g
co
n
te
x
t.
T
h
e
u
tili
za
tio
n
o
f
th
e
L
STM
n
etwo
r
k
in
co
m
b
in
atio
n
with
g
ated
r
ec
u
r
r
e
n
t
u
n
it
s
(
GR
U)
,
RF
,
an
d
XGBo
o
s
t
allo
wed
f
o
r
th
e
ex
p
lo
itatio
n
o
f
L
STM
’
s
ca
p
ac
ity
to
ca
p
tu
r
e
p
r
o
lo
n
g
ed
d
ep
en
d
en
cies
in
s
eq
u
en
tial
d
ata.
GR
U,
wh
ic
h
is
a
s
im
p
lifie
d
iter
atio
n
o
f
L
STM
,
o
f
f
er
s
co
m
p
u
tatio
n
al
ef
f
icien
cy
wh
ile
u
p
h
o
l
d
in
g
p
er
f
o
r
m
an
ce
s
tan
d
ar
d
s
[
20
]
.
RF
,
as
an
e
n
s
em
b
le
tech
n
iq
u
e
co
m
p
r
is
ed
o
f
d
ec
is
io
n
tr
ee
s
,
b
o
ls
ter
s
p
r
ed
ictiv
e
p
r
ec
is
io
n
an
d
m
itig
ates
o
v
er
f
itti
n
g
,
wh
er
ea
s
XGBo
o
s
t,
an
o
p
tim
ized
g
r
ad
ien
t
b
o
o
s
tin
g
alg
o
r
ith
m
,
en
h
an
ce
s
s
p
ee
d
an
d
p
er
f
o
r
m
an
c
e
b
y
m
ea
n
s
o
f
s
eq
u
e
n
tial
tr
ee
co
n
s
tr
u
ctio
n
.
Mo
r
e
o
v
er
,
th
e
in
teg
r
atio
n
o
f
r
esid
u
al
n
etwo
r
k
s
(
R
esNet)
w
ith
L
STM
an
d
C
N
N
[
2
1
]
was
ca
r
r
ied
o
u
t
to
lev
er
ag
e
R
esNet
’
s
s
k
ip
co
n
n
ec
tio
n
s
f
o
r
th
e
tr
ain
in
g
o
f
d
ee
p
n
etwo
r
k
s
,
L
S
T
M
’
s
ca
p
ab
ilit
y
in
r
ec
o
g
n
izin
g
s
eq
u
en
tial
p
atter
n
s
,
an
d
C
NN
’
s
p
r
o
f
icien
cy
i
n
ex
tr
ac
tin
g
s
p
atial
h
ier
a
r
ch
i
es.
T
h
ese
s
p
ec
if
ic
ar
ch
itectu
r
es
wer
e
ch
o
s
en
d
u
e
to
th
eir
co
m
p
lem
en
tar
y
s
tr
e
n
g
th
s
in
ad
d
r
ess
in
g
d
iv
er
s
e
d
ata
ch
ar
ac
ter
is
tics
,
s
u
ch
as
tem
p
o
r
al
d
ep
e
n
d
en
cie
s
an
d
s
p
atial
h
ier
ar
ch
ies,
with
th
e
aim
o
f
o
p
tim
izin
g
th
e
p
r
e
d
ictiv
e
ca
p
ab
ilit
ies
o
f
th
e
s
tu
d
y
.
Aim
in
g
to
ev
alu
ate
th
e
e
f
f
ec
tiv
en
ess
o
f
o
u
r
f
e
d
er
ated
lea
r
n
in
g
m
o
d
el,
a
s
tr
atif
ied
ap
p
r
o
ac
h
was
u
tili
ze
d
to
d
iv
id
e
th
e
d
ataset
in
to
tr
ain
in
g
an
d
test
in
g
s
ets.
T
h
is
s
tr
atif
icatio
n
tech
n
iq
u
e
g
u
ar
an
tees
th
at
th
e
d
is
tr
ib
u
tio
n
o
f
class
es
r
em
ain
s
u
n
if
o
r
m
ac
r
o
s
s
b
o
th
s
ets,
t
h
er
eb
y
en
h
an
cin
g
th
e
cr
ed
ib
i
lity
o
f
th
e
m
o
d
el
’
s
p
er
f
o
r
m
an
ce
.
I
n
itially
,
d
ata
p
r
ep
r
o
ce
s
s
in
g
was
co
n
d
u
c
ted
in
d
iv
id
u
ally
f
o
r
ea
ch
u
s
er
’
s
d
ataset.
T
h
e
p
r
ep
r
o
ce
s
s
in
g
p
r
o
ce
d
u
r
e
in
v
o
l
v
ed
s
tan
d
a
r
d
izin
g
th
e
f
ea
tu
r
es
to
ac
h
iev
e
a
m
ea
n
o
f
ze
r
o
an
d
a
v
ar
ian
ce
o
f
o
n
e
,
f
o
llo
wed
b
y
r
esh
a
p
in
g
th
e
d
at
a
to
co
n
f
o
r
m
to
th
e
in
p
u
t sp
ec
i
f
icatio
n
s
o
f
th
e
h
y
b
r
id
m
o
d
el
s
.
Mo
r
e
s
p
ec
if
ically
,
th
e
Stan
d
ar
d
Scaler
to
o
l
f
r
o
m
th
e
s
cik
it
-
lear
n
lib
r
ar
y
was
u
t
ilized
to
s
tan
d
ar
d
ize
ea
ch
u
s
e
r
’
s
d
ata,
wh
ile
th
e
tar
g
et
v
ar
iab
le
was
r
esh
ap
ed
to
m
atch
th
e
ex
p
ec
ted
in
p
u
t
f
o
r
m
at.
Su
b
s
eq
u
e
n
tly
,
th
e
d
at
aset
u
n
d
er
wen
t
an
80
-
2
0
s
p
lit
to
cr
ea
te
tr
ain
in
g
an
d
test
in
g
s
u
b
s
ets.
T
h
is
allo
ca
tio
n
in
v
o
lv
ed
u
tili
zin
g
8
0
%
o
f
ea
ch
u
s
er
’
s
d
ata
f
o
r
m
o
d
el
tr
ain
i
n
g
p
u
r
p
o
s
es,
with
th
e
r
em
ain
in
g
2
0
%
d
esig
n
ated
f
o
r
p
er
f
o
r
m
an
ce
ev
alu
atio
n
.
T
h
e
d
iv
is
io
n
was
ex
ec
u
ted
th
r
o
u
g
h
th
e
im
p
lem
en
tatio
n
o
f
th
e
tr
ain
_
test
_
s
p
lit
f
u
n
ctio
n
f
r
o
m
s
cik
it
-
lea
r
n
,
wh
ich
e
n
s
u
r
ed
a
r
an
d
o
m
d
i
v
is
io
n
b
y
estab
lis
h
in
g
a
f
ix
ed
r
an
d
o
m
s
tate.
T
h
is
p
ar
titi
o
n
in
g
was
ess
en
tial
to
m
ain
tain
u
n
if
o
r
m
ity
an
d
av
o
id
p
o
s
s
ib
le
b
ias
in
th
e
m
o
d
el
’
s
p
er
f
o
r
m
an
ce
m
et
r
ics
ca
u
s
ed
b
y
d
ata
leak
ag
e
b
etwe
en
th
e
tr
ain
in
g
an
d
test
in
g
p
h
ases
.
T
o
e
n
h
an
ce
th
e
g
en
er
aliza
tio
n
ca
p
ab
ilit
y
o
f
o
u
r
h
y
b
r
id
L
STM
m
o
d
el
s
an
d
t
o
av
o
i
d
o
v
er
f
itti
n
g
,
d
r
o
p
o
u
t
lay
e
r
s
wer
e
in
c
o
r
p
o
r
a
ted
in
to
t
h
e
p
r
o
p
o
s
ed
ar
c
h
itectu
r
es
.
Dr
o
p
o
u
t
s
er
v
es
as
a
r
e
g
u
lar
izatio
n
m
eth
o
d
wh
er
e,
in
ea
c
h
tr
ain
in
g
iter
at
io
n
,
a
p
o
r
tio
n
o
f
n
eu
r
o
n
s
is
r
an
d
o
m
l
y
ch
o
s
en
to
b
e
d
is
r
e
g
ar
d
ed
.
T
h
is
ac
tio
n
p
r
ev
en
ts
an
ex
ce
s
s
iv
e
d
ep
e
n
d
en
cy
o
n
s
p
ec
if
ic
n
e
u
r
o
n
s
with
in
th
e
n
etwo
r
k
an
d
f
o
s
ter
s
th
e
f
o
r
m
atio
n
o
f
m
o
r
e
r
esil
ien
t
f
ea
tu
r
es
th
at
ex
h
i
b
it
r
ed
u
ce
d
s
en
s
itiv
ity
to
n
o
is
e
a
n
d
v
a
r
iab
ilit
y
p
r
esen
t
in
th
e
in
p
u
t
d
ata
.
A
d
r
o
p
o
u
t
r
ate
o
f
0
.
5
was
em
p
lo
y
ed
,
in
d
icatin
g
th
at
5
0
%
o
f
n
e
u
r
o
n
s
wer
e
r
an
d
o
m
l
y
ex
clu
d
e
d
d
u
r
in
g
ev
er
y
tr
ain
in
g
cy
cle.
T
h
is
p
ar
ticu
lar
r
ate
was
s
elec
ted
b
ased
o
n
em
p
ir
ical
f
in
d
in
g
s
an
d
p
r
i
o
r
r
esear
ch
[
2
1
]
-
[
2
6
]
,
s
h
o
wca
s
in
g
its
ef
f
icac
y
in
d
im
i
n
is
h
in
g
o
v
er
f
itti
n
g
with
in
a
n
alo
g
o
u
s
n
eu
r
al
n
etwo
r
k
s
tr
u
ctu
r
es.
A
co
m
p
a
r
is
o
n
was
co
n
d
u
cte
d
b
etwe
en
m
u
ltip
le
f
ed
er
ated
lear
n
in
g
ar
ch
itectu
r
e
s
u
s
in
g
d
if
f
er
en
t
h
y
b
r
id
m
o
d
els
to
ev
alu
ate
th
e
ef
f
icien
cy
o
f
th
e
f
e
d
er
ated
m
eth
o
d
o
lo
g
y
.
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
I
n
th
is
s
ec
tio
n
,
we
ar
e
g
o
i
n
g
to
p
r
esen
t
th
e
m
ai
n
f
in
d
i
n
g
o
f
o
u
r
s
tu
d
y
.
T
ab
le
1
a
n
d
Fig
u
r
e
6
s
u
m
m
ar
ize
th
e
r
esu
lts
o
f
ea
ch
ev
alu
ated
h
y
b
r
id
m
o
d
el
o
v
er
a
s
am
p
le
o
f
3
u
s
er
s
f
r
o
m
a
lis
t
o
f
2
3
to
s
im
p
lify
th
e
r
esu
lts
p
r
esen
tatio
n
.
W
e
n
o
ticed
th
at
th
e
co
m
b
in
atio
n
s
L
STM
-
RF
an
d
L
STM
-
XG
B
o
o
s
t
ar
e
p
r
esen
tin
g
th
e
h
ig
h
est
ac
cu
r
ac
y
f
o
r
alm
o
s
t
all
u
s
er
s.
T
h
o
s
e
r
esu
lts
wer
e
o
b
tain
ed
b
y
s
im
u
latin
g
t
h
e
f
ed
er
ated
lea
r
n
in
g
co
n
tex
t u
s
in
g
G
o
o
g
le
C
o
lab
w
ith
th
e
co
n
f
i
g
u
r
atio
n
d
escr
ib
ed
o
n
T
ab
le
2
.
Ho
wev
er
,
t
h
e
v
ar
y
in
g
p
er
f
o
r
m
an
ce
o
b
s
er
v
e
d
ac
r
o
s
s
u
s
er
s
o
v
er
all
s
ig
n
if
ies
th
at
th
e
m
o
d
el
’
s
ef
f
icac
y
m
ay
v
a
r
y
d
ep
en
d
in
g
o
n
th
e
u
n
iq
u
e
d
ata
ch
a
r
ac
ter
is
tics
o
f
i
n
d
iv
id
u
al
u
s
er
s
.
W
h
ile
m
ain
t
ain
in
g
c
o
n
s
is
ten
tly
h
ig
h
p
r
ec
is
io
n
,
en
d
ea
v
o
r
s
to
i
m
p
r
o
v
e
r
ec
all
f
o
r
s
p
ec
if
ic
u
s
er
s
co
u
ld
p
o
ten
tially
b
o
o
s
t
th
e
o
v
er
all
p
er
f
o
r
m
a
n
ce
an
d
ap
p
licab
ilit
y
o
f
th
e
m
o
d
el
.
T
h
is
v
ar
ia
b
ilit
y
in
m
o
d
el
p
er
f
o
r
m
an
ce
ac
r
o
s
s
d
if
f
er
en
t
u
s
er
s
,
ca
n
b
e
attr
ib
u
ted
to
in
d
iv
id
u
al
d
if
f
er
en
c
es
in
p
h
y
s
io
lo
g
ical
r
esp
o
n
s
es
to
s
tr
ess
.
T
h
is
h
ig
h
lig
h
ts
th
e
n
ee
d
f
o
r
m
o
r
e
p
er
s
o
n
alize
d
m
o
d
els
in
f
u
t
u
r
e
r
esear
ch
.
T
h
at
’
s
wh
y
we
in
ten
d
to
ex
p
l
o
r
e,
in
f
u
tu
r
e
wo
r
k
,
I
n
d
iv
id
u
al
-
b
ased
lear
n
in
g
th
at
in
v
o
lv
es
tailo
r
in
g
s
tr
ess
d
ete
ctio
n
m
o
d
els
to
s
p
ec
if
ic
in
d
iv
id
u
als
b
y
lev
er
a
g
in
g
p
er
s
o
n
alize
d
d
ata
f
r
o
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
2
,
No
v
em
b
er
20
24
:
1
3
0
1
-
130
8
1306
wea
r
ab
le
d
ev
ices.
T
h
e
co
m
b
i
n
atio
n
o
f
th
is
ap
p
r
o
ac
h
in
a
f
ed
er
ated
lear
n
in
g
co
n
tex
t
m
a
y
allo
w
f
o
r
th
e
f
in
e
-
tu
n
in
g
o
f
alg
o
r
ith
m
s
to
th
e
u
n
iq
u
e
p
h
y
s
io
lo
g
ical
an
d
b
e
h
av
io
r
al
p
atter
n
s
o
f
ea
ch
p
e
r
s
o
n
,
en
h
an
cin
g
th
e
ac
cu
r
ac
y
o
f
s
tr
ess
d
etec
tio
n
.
T
ab
le
1
.
C
o
m
p
a
r
is
o
n
o
f
th
e
u
s
ed
m
o
d
el
’
s
ef
f
icien
cy
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
s
c
o
r
e
A
c
c
u
r
a
c
y
LSTM
-
C
N
N
U
ser
1
9
1
.
1
0
%
5
5
.
9
1
%
6
9
.
2
9
%
7
5
.
1
7
%
U
ser
2
6
6
.
1
0
%
6
8
.
1
5
%
6
7
.
1
1
%
6
6
.
5
0
%
U
ser
3
9
0
.
5
0
%
7
4
.
2
3
%
8
1
.
1
6
%
8
3
.
1
4
%
LSTM
-
G
R
U
U
ser
1
9
6
.
3
1
%
4
8
%
6
4
.
0
6
%
7
3
.
0
1
%
U
ser
2
9
5
.
8
5
%
5
7
.
8
2
%
7
2
.
1
3
%
7
7
.
5
9
%
U
ser
3
9
6
.
3
3
%
9
7
.
7
3
%
9
7
.
0
2
%
9
6
.
9
9
%
LSTM
-
RF
U
ser
1
9
6
.
4
4
%
9
0
.
4
1
%
9
3
.
3
3
%
9
3
.
5
2
%
U
ser
2
9
9
%
9
9
.
8
0
%
9
9
.
3
9
%
9
9
.
3
9
%
U
ser
3
9
7
.
3
2
%
9
8
.
4
8
%
9
7
.
9
0
%
9
7
.
8
8
%
LSTM
-
X
G
B
o
o
st
U
ser
1
8
7
.
6
4
%
8
3
.
6
1
%
8
5
.
5
8
%
8
5
.
8
7
%
U
ser
2
9
7
.
7
7
%
9
9
.
3
7
%
9
8
.
5
6
%
9
8
.
5
5
%
U
ser
3
9
2
.
4
2
%
9
1
.
6
2
%
9
2
.
0
2
%
9
2
.
0
2
%
Fig
u
r
e
6
.
Mo
d
el
p
er
f
o
r
m
a
n
ce
m
etr
ics co
m
p
ar
is
o
n
f
o
r
3
u
s
er
s
as a
n
ex
am
p
le
T
ab
le
2
.
C
o
m
p
u
tin
g
e
x
p
er
im
e
n
tal
d
etails
S
p
e
c
i
f
i
c
a
t
i
o
n
D
e
t
a
i
l
s
C
o
n
n
e
c
t
i
o
n
B
a
c
k
e
n
d
G
o
o
g
l
e
c
o
m
p
u
t
e
e
n
g
i
n
e
La
n
g
u
a
g
e
P
y
t
h
o
n
3
(
G
P
U
)
To
t
a
l
R
A
M
1
2
.
6
7
G
B
G
P
U
N
V
I
D
I
A
T4
P
r
o
g
r
a
m
mi
n
g
p
l
a
t
f
o
r
m
P
y
t
h
o
n
3
.
8
w
i
t
h
T
e
n
so
r
F
l
o
w
2
.
4
N
u
mb
e
r
o
f
c
l
i
e
n
t
n
o
d
e
s
23
Le
a
r
n
i
n
g
r
a
t
e
0
.
0
0
1
(
A
d
a
m)
B
a
t
c
h
s
i
z
e
32
Ep
o
c
h
s
A
v
e
r
a
g
e
o
f
2
0
(
u
si
n
g
e
a
r
l
y
st
o
p
p
i
n
g
t
e
c
h
n
i
c
t
o
o
v
o
i
d
o
v
e
r
f
i
t
t
i
n
g
)
5.
CO
NCLU
SI
O
N
I
n
co
n
clu
s
io
n
,
o
u
r
s
tu
d
y
d
e
m
o
n
s
tr
ates
th
at
in
teg
r
atio
n
o
f
t
h
e
L
STM
with
RF
o
r
XGBo
o
s
t
with
in
a
f
ed
er
ated
lear
n
in
g
co
n
tex
t
i
m
p
r
o
v
es
s
tr
ess
d
etec
tio
n
ac
cu
r
ac
y
wh
ile
p
r
eser
v
in
g
u
s
er
p
r
iv
ac
y
.
Ho
wev
er
,
w
e
n
o
ticed
a
s
ig
n
if
ican
t
d
if
f
e
r
en
ce
in
th
e
im
p
r
o
v
em
en
t
o
f
ac
cu
r
ac
y
f
r
o
m
o
n
e
u
s
er
to
an
o
th
er
.
Fo
r
in
s
tan
ce
,
th
e
L
STM
-
XGBo
o
s
t
co
m
b
in
atio
n
d
em
o
n
s
tr
ated
n
o
tab
le
ef
f
ic
ac
y
,
esp
ec
ially
f
o
r
u
s
er
2
.
T
h
is
o
b
s
er
v
atio
n
lead
s
u
s
to
ex
p
lo
r
e
o
th
e
r
tech
n
o
lo
g
ies
th
at
co
u
ld
h
elp
en
h
an
ce
o
u
r
m
o
d
el
wh
ile
p
r
eser
v
i
n
g
u
s
er
d
ata
p
r
iv
ac
y
a
n
d
co
n
s
id
er
in
g
t
h
e
lim
ited
co
m
p
u
tatio
n
al
r
eso
u
r
ce
s
o
f
ed
g
e
d
ev
ices.
Fin
ally
,
f
u
tu
r
e
r
esear
c
h
s
h
o
u
ld
f
o
cu
s
o
n
in
d
iv
id
u
al
-
b
ased
lear
n
in
g
with
in
f
ed
er
ate
d
f
r
am
ew
o
r
k
s
to
p
er
s
o
n
alize
s
tr
ess
d
etec
tio
n
m
o
d
els,
im
p
r
o
v
in
g
r
ea
l
-
tim
e
m
o
n
ito
r
in
g
an
d
in
te
r
v
en
tio
n
ca
p
ab
ilit
ies.
T
h
is
r
es
ea
r
ch
p
r
o
v
id
es
a
r
o
b
u
s
t
f
o
u
n
d
atio
n
f
o
r
p
r
iv
ac
y
-
p
r
eser
v
ed
,
I
o
T
-
b
ased
h
ea
lth
m
o
n
ito
r
in
g
s
y
s
tem
s
,
with
ap
p
licatio
n
s
ex
ten
d
in
g
b
ey
o
n
d
s
tr
ess
d
etec
tio
n
to
v
ar
io
u
s
h
ea
lth
-
r
elate
d
d
o
m
ain
s
.
RE
F
E
R
E
NC
E
S
[
1
]
A
.
R
o
c
h
a
e
t
a
l
.
,
“
E
d
g
e
A
I
f
o
r
i
n
t
e
r
n
e
t
o
f
me
d
i
c
a
l
t
h
i
n
g
s
:
a
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
,
”
C
o
m
p
u
t
e
rs
a
n
d
El
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
1
6
,
p
.
1
0
9
2
0
2
,
M
a
y
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
e
l
e
c
e
n
g
.
2
0
2
4
.
1
0
9
2
0
2
.
[
2
]
A
.
P
r
e
sci
u
t
t
i
n
i
,
A
.
C
a
n
t
i
n
i
,
F
.
C
o
s
t
a
,
a
n
d
A
.
P
o
r
t
i
o
l
i
-
S
t
a
u
d
a
c
h
e
r
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
l
i
c
a
t
i
o
n
s
o
n
I
o
T
d
a
t
a
i
n
m
a
n
u
f
a
c
t
u
r
i
n
g
o
p
e
r
a
t
i
o
n
s
a
n
d
t
h
e
i
r
i
n
t
e
r
p
r
e
t
a
b
i
l
i
t
y
i
mp
l
i
c
a
t
i
o
n
s:
a
sy
st
e
mat
i
c
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
,
”
J
o
u
r
n
a
l
o
f
Ma
n
u
f
a
c
t
u
r
i
n
g
S
y
st
e
m
s
,
v
o
l
.
7
4
,
p
p
.
4
7
7
–
4
8
6
,
J
u
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
ms
y
.
2
0
2
4
.
0
4
.
0
1
2
.
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
E
n
h
a
n
ci
n
g
s
tr
ess
d
etec
tio
n
in
w
ea
r
a
b
le
I
o
T d
ev
ices u
s
in
g
fe
d
era
ted
lea
r
n
in
g
a
n
d
…
(
N
a
o
u
a
l Mo
u
h
n
i
)
1307
[
3
]
J.
X
u
,
B
.
S
.
G
l
i
c
k
s
b
e
r
g
,
C
.
S
u
,
P
.
W
a
l
k
e
r
,
J.
B
i
a
n
,
a
n
d
F
.
W
a
n
g
,
“
F
e
d
e
r
a
t
e
d
l
e
a
r
n
i
n
g
f
o
r
h
e
a
l
t
h
c
a
r
e
i
n
f
o
r
m
a
t
i
c
s,
”
J
o
u
r
n
a
l
o
f
H
e
a
l
t
h
c
a
re
I
n
f
o
rm
a
t
i
c
s
Re
se
a
r
c
h
,
v
o
l
.
5
,
n
o
.
1
,
p
p
.
1
–
1
9
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
1
6
6
6
-
0
2
0
-
0
0
0
8
2
-
4.
[
4
]
P
.
K
a
i
r
o
u
z
e
t
a
l
.
,
“
A
d
v
a
n
c
e
s
a
n
d
o
p
e
n
p
r
o
b
l
e
ms
i
n
f
e
d
e
r
a
t
e
d
l
e
a
r
n
i
n
g
,
”
Fo
u
n
d
a
t
i
o
n
s
a
n
d
T
r
e
n
d
s
®
i
n
Ma
c
h
i
n
e
L
e
a
r
n
i
n
g
,
v
o
l
.
1
4
,
n
o
.
1
–
2
,
p
p
.
1
–
2
1
0
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
5
6
1
/
2
2
0
0
0
0
0
0
8
3
.
[
5
]
I
.
H
.
A
h
me
d
,
A
.
D
j
e
b
b
a
r
i
,
A
.
K
a
c
h
e
n
o
u
r
a
,
a
n
d
L.
S
e
n
h
a
d
j
i
,
“
T
e
l
e
me
d
i
c
a
l
t
r
a
n
sp
o
r
t
l
a
y
e
r
sec
u
r
i
t
y
b
a
se
d
p
l
a
t
f
o
r
m
f
o
r
c
a
r
d
i
a
c
a
r
r
h
y
t
h
mi
a
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
s
i
n
g
q
u
a
d
r
a
t
i
c
t
i
me
–
f
r
e
q
u
e
n
c
y
a
n
a
l
y
si
s
o
f
H
R
V
si
g
n
a
l
,
”
T
h
e
J
o
u
r
n
a
l
o
f
S
u
p
e
r
c
o
m
p
u
t
i
n
g
,
v
o
l
.
7
8
,
n
o
.
1
1
,
p
p
.
1
3
6
8
0
–
1
3
7
0
9
,
J
u
l
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
1
2
2
7
-
0
2
2
-
0
4
3
8
7
-
6.
[
6
]
Y
.
S
.
C
a
n
,
B
.
A
r
n
r
i
c
h
,
a
n
d
C
.
Er
so
y
,
“
S
t
r
e
ss
d
e
t
e
c
t
i
o
n
i
n
d
a
i
l
y
l
i
f
e
s
c
e
n
a
r
i
o
s
u
s
i
n
g
sm
a
r
t
p
h
o
n
e
s
a
n
d
w
e
a
r
a
b
l
e
se
n
so
r
s
:
a
su
r
v
e
y
,
”
J
o
u
rn
a
l
o
f
Bi
o
m
e
d
i
c
a
l
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
9
2
,
p
.
1
0
3
1
3
9
,
A
p
r
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
b
i
.
2
0
1
9
.
1
0
3
1
3
9
.
[
7
]
S
.
P
a
t
e
l
,
H
.
P
a
r
k
,
P
.
B
o
n
a
t
o
,
L.
C
h
a
n
,
a
n
d
M
.
R
o
d
g
e
r
s
,
“
A
r
e
v
i
e
w
o
f
w
e
a
r
a
b
l
e
se
n
s
o
r
s
a
n
d
s
y
st
e
ms
w
i
t
h
a
p
p
l
i
c
a
t
i
o
n
i
n
r
e
h
a
b
i
l
i
t
a
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
N
e
u
ro
En
g
i
n
e
e
ri
n
g
a
n
d
R
e
h
a
b
i
l
i
t
a
t
i
o
n
,
v
o
l
.
9
,
n
o
.
1
,
p
.
2
1
,
D
e
c
.
2
0
1
2
,
d
o
i
:
1
0
.
1
1
8
6
/
1
7
4
3
-
0
0
0
3
-
9
-
2
1
.
[
8
]
J.
C
h
e
n
,
M
.
A
b
b
o
d
,
a
n
d
J.
-
S
.
S
h
i
e
h
,
“
P
a
i
n
a
n
d
s
t
r
e
ss
d
e
t
e
c
t
i
o
n
u
si
n
g
w
e
a
r
a
b
l
e
se
n
so
r
s
a
n
d
d
e
v
i
c
e
s
-
a
r
e
v
i
e
w
,
”
S
e
n
so
rs
,
v
o
l
.
2
1
,
n
o
.
4
,
p
.
1
0
3
0
,
F
e
b
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
1
0
4
1
0
3
0
.
[
9
]
N
.
M
o
u
h
n
i
,
A
.
E
l
k
a
l
a
y
,
M
.
C
h
a
k
r
a
o
u
i
,
A
.
A
b
d
a
l
i
,
A
.
A
mm
o
u
m
o
u
,
a
n
d
I
.
A
mal
o
u
,
“
F
e
d
e
r
a
t
e
d
l
e
a
r
n
i
n
g
f
o
r
me
d
i
c
a
l
i
ma
g
i
n
g
:
a
n
u
p
d
a
t
e
d
s
t
a
t
e
o
f
t
h
e
a
r
t
,
”
I
n
g
é
n
i
e
ri
e
d
e
s sy
s
t
è
m
e
s
d
i
n
f
o
rm
a
t
i
o
n
,
v
o
l
.
2
7
,
n
o
.
1
,
p
p
.
1
4
3
–
1
5
0
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
1
8
2
8
0
/
i
si
.
2
7
0
1
1
7
.
[
1
0
]
A
.
A
l
a
h
m
a
d
i
e
t
a
l
.
,
“
A
p
r
i
v
a
c
y
-
p
r
e
s
e
r
v
e
d
I
o
M
T
-
b
a
se
d
me
n
t
a
l
st
r
e
ss
d
e
t
e
c
t
i
o
n
f
r
a
m
e
w
o
r
k
w
i
t
h
f
e
d
e
r
a
t
e
d
l
e
a
r
n
i
n
g
,
”
T
h
e
J
o
u
rn
a
l
o
f
S
u
p
e
r
c
o
m
p
u
t
i
n
g
,
v
o
l
.
8
0
,
n
o
.
8
,
p
p
.
1
0
2
5
5
–
1
0
2
7
4
,
M
a
y
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
2
2
7
-
0
2
3
-
0
5
8
4
7
-
3.
[
1
1
]
S
.
Ji
a
n
g
,
F
.
F
i
r
o
u
z
i
,
a
n
d
K
.
C
h
a
k
r
a
b
a
r
t
y
,
“
Lo
w
-
o
v
e
r
h
e
a
d
c
l
u
st
e
r
e
d
f
e
d
e
r
a
t
e
d
l
e
a
r
n
i
n
g
f
o
r
p
e
r
so
n
a
l
i
z
e
d
st
r
e
ss
mo
n
i
t
o
r
i
n
g
,
”
I
EEE
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s
J
o
u
r
n
a
l
,
v
o
l
.
1
1
,
n
o
.
3
,
p
p
.
4
3
3
5
–
4
3
4
7
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
JI
O
T.
2
0
2
3
.
3
2
9
9
7
3
6
.
[
1
2
]
M
.
M
.
Y
a
q
o
o
b
e
t
a
l
.
,
“
M
o
d
i
f
i
e
d
a
r
t
i
f
i
c
i
a
l
b
e
e
c
o
l
o
n
y
b
a
se
d
f
e
a
t
u
r
e
o
p
t
i
mi
z
e
d
f
e
d
e
r
a
t
e
d
l
e
a
r
n
i
n
g
f
o
r
h
e
a
r
t
d
i
sea
se
d
i
a
g
n
o
si
s
i
n
h
e
a
l
t
h
c
a
r
e
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
2
,
n
o
.
2
3
,
p
.
1
2
0
8
0
,
N
o
v
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
2
2
3
1
2
0
8
0
.
[
1
3
]
A
.
A
l
ma
d
h
o
r
e
t
a
l
.
,
“
W
r
i
st
-
b
a
s
e
d
e
l
e
c
t
r
o
d
e
r
mal
a
c
t
i
v
i
t
y
mo
n
i
t
o
r
i
n
g
f
o
r
s
t
r
e
ss
d
e
t
e
c
t
i
o
n
u
si
n
g
f
e
d
e
r
a
t
e
d
l
e
a
r
n
i
n
g
,
”
S
e
n
so
rs
,
v
o
l
.
2
3
,
n
o
.
8
,
p
.
3
9
8
4
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s2
3
0
8
3
9
8
4
.
[
1
4
]
M
.
M
.
Y
a
q
o
o
b
,
M
.
A
l
su
l
a
m
i
,
M
.
A
.
K
h
a
n
,
D
.
A
l
s
a
d
i
e
,
A
.
K
.
J
.
S
a
u
d
a
g
a
r
,
a
n
d
M
.
A
l
K
h
a
t
h
a
m
i
,
“
F
e
d
e
r
a
t
e
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
sk
i
n
l
e
si
o
n
d
i
a
g
n
o
s
i
s:
a
n
a
sy
n
c
h
r
o
n
o
u
s
a
n
d
w
e
i
g
h
t
e
d
a
p
p
r
o
a
c
h
,
”
D
i
a
g
n
o
s
t
i
c
s
,
v
o
l
.
1
3
,
n
o
.
1
1
,
p
.
1
9
6
4
,
J
u
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
d
i
a
g
n
o
st
i
c
s
1
3
1
1
1
9
6
4
.
[
1
5
]
M
.
A
.
K
h
a
n
e
t
a
l
.
,
“
A
s
y
n
c
h
r
o
n
o
u
s
f
e
d
e
r
a
t
e
d
l
e
a
r
n
i
n
g
f
o
r
i
mp
r
o
v
e
d
c
a
r
d
i
o
v
a
sc
u
l
a
r
d
i
s
e
a
s
e
p
r
e
d
i
c
t
i
o
n
u
si
n
g
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
,
”
D
i
a
g
n
o
s
t
i
c
s
,
v
o
l
.
1
3
,
n
o
.
1
4
,
p
.
2
3
4
0
,
Ju
l
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
d
i
a
g
n
o
s
t
i
c
s1
3
1
4
2
3
4
0
.
[
1
6
]
F
.
M
.
R.
J
u
n
i
o
r
a
n
d
C
.
A
.
K
a
m
i
e
n
s
k
i
,
“
F
e
d
e
r
a
t
e
d
l
e
a
r
n
i
n
g
f
o
r
p
e
r
f
o
r
ma
n
c
e
b
e
h
a
v
i
o
r
d
e
t
e
c
t
i
o
n
i
n
a
f
o
g
-
I
o
T
s
y
st
e
m,
”
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s
,
v
o
l
.
2
5
,
p
.
1
0
1
0
7
8
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
o
t
.
2
0
2
4
.
1
0
1
0
7
8
.
[
1
7
]
A
.
N
a
n
d
i
a
n
d
F
.
X
h
a
f
a
,
“
A
f
e
d
e
r
a
t
e
d
l
e
a
r
n
i
n
g
me
t
h
o
d
f
o
r
r
e
a
l
-
t
i
me
e
m
o
t
i
o
n
s
t
a
t
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
f
r
o
m
m
u
l
t
i
-
m
o
d
a
l
s
t
r
e
a
m
i
n
g
,
”
Me
t
h
o
d
s
,
v
o
l
.
2
0
4
,
p
p
.
3
4
0
–
3
4
7
,
A
u
g
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
y
me
t
h
.
2
0
2
2
.
0
3
.
0
0
5
.
[
1
8
]
S
.
S
.
Tr
i
p
a
t
h
y
e
t
a
l
.
,
“
F
e
d
H
e
a
l
t
h
F
o
g
:
a
f
e
d
e
r
a
t
e
d
l
e
a
r
n
i
n
g
-
e
n
a
b
l
e
d
a
p
p
r
o
a
c
h
t
o
w
a
r
d
s
h
e
a
l
t
h
c
a
r
e
a
n
a
l
y
t
i
c
s
o
v
e
r
f
o
g
c
o
mp
u
t
i
n
g
p
l
a
t
f
o
r
m
,
”
H
e
l
i
y
o
n
,
v
o
l
.
1
0
,
n
o
.
5
,
p
.
e
2
6
4
1
6
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
h
e
l
i
y
o
n
.
2
0
2
4
.
e
2
6
4
1
6
.
[
1
9
]
A
.
Y
.
B
a
r
r
e
r
a
-
A
n
i
m
a
s,
L.
A
.
Tr
e
j
o
,
M
.
A
.
M
e
d
i
n
a
-
P
é
r
e
z
,
R
.
M
o
n
r
o
y
,
J
.
B
.
C
a
mi
ñ
a
,
a
n
d
F
.
G
o
d
í
n
e
z
,
“
O
n
l
i
n
e
p
e
r
so
n
a
l
r
i
s
k
d
e
t
e
c
t
i
o
n
b
a
s
e
d
o
n
b
e
h
a
v
i
o
u
r
a
l
a
n
d
p
h
y
s
i
o
l
o
g
i
c
a
l
p
a
t
t
e
r
n
s,
”
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
3
8
4
,
p
p
.
2
8
1
–
2
9
7
,
A
p
r
.
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
s
.
2
0
1
6
.
0
8
.
0
0
6
.
[
2
0
]
I
.
A
mal
o
u
,
N
.
M
o
u
h
n
i
,
a
n
d
A
.
A
b
d
a
l
i
,
“
M
u
l
t
i
v
a
r
i
a
t
e
t
i
m
e
ser
i
e
s
p
r
e
d
i
c
t
i
o
n
b
y
R
N
N
a
r
c
h
i
t
e
c
t
u
r
e
s
f
o
r
e
n
e
r
g
y
c
o
n
s
u
mp
t
i
o
n
f
o
r
e
c
a
st
i
n
g
,
”
E
n
e
r
g
y
Re
p
o
rt
s
,
v
o
l
.
8
,
p
p
.
1
0
8
4
–
1
0
9
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
g
y
r
.
2
0
2
2
.
0
7
.
1
3
9
.
[
2
1
]
G
.
H
i
n
t
o
n
,
A
.
K
r
i
z
h
e
v
s
k
y
,
I
.
S
u
t
s
k
e
v
e
r
,
R
.
S
a
l
a
k
h
u
t
d
i
n
o
v
,
a
n
d
N
.
S
r
i
v
a
s
t
a
v
a
,
“
D
r
o
p
o
u
t
:
a
si
m
p
l
e
w
a
y
t
o
p
r
e
v
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
s
f
r
o
m
o
v
e
r
f
i
t
t
i
n
g
,
”
J
o
u
rn
a
l
o
f
M
a
c
h
i
n
e
L
e
a
rn
i
n
g
R
e
se
a
rc
h
,
v
o
l
.
1
5
,
n
o
.
1
,
p
p
.
1
9
2
9
–
1
9
5
8
,
2
0
1
4
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
:
/
/
j
m
l
r
.
o
r
g
/
p
a
p
e
r
s/
v
1
5
/
sr
i
v
a
st
a
v
a
1
4
a
.
h
t
ml
.
[
2
2
]
G
.
E.
H
i
n
t
o
n
,
N
.
S
r
i
v
a
s
t
a
v
a
,
A
.
K
r
i
z
h
e
v
sk
y
,
I
.
S
u
t
sk
e
v
e
r
,
a
n
d
R
.
R
.
S
a
l
a
k
h
u
t
d
i
n
o
v
,
“
I
mp
r
o
v
i
n
g
n
e
u
r
a
l
n
e
t
w
o
r
k
s
b
y
p
r
e
v
e
n
t
i
n
g
co
-
a
d
a
p
t
a
t
i
o
n
o
f
f
e
a
t
u
r
e
d
e
t
e
c
t
o
r
s,
”
a
r
Xi
v
p
r
e
p
r
i
n
t
,
2
0
1
2
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
:
/
/
a
r
x
i
v
.
o
r
g
/
a
b
s/
1
2
0
7
.
0
5
8
0
.
[
2
3
]
L.
W
u
e
t
a
l
.
,
“
R
-
d
r
o
p
:
r
e
g
u
l
a
r
i
z
e
d
d
r
o
p
o
u
t
f
o
r
n
e
u
r
a
l
n
e
t
w
o
r
k
s,
”
Ad
v
a
n
c
e
s
i
n
N
e
u
r
a
l
I
n
f
o
rm
a
t
i
o
n
Pr
o
c
e
ssi
n
g
S
y
s
t
e
m
s
,
v
o
l
.
1
3
,
p
p
.
1
0
8
9
0
–
1
0
9
0
5
,
2
0
2
1
.
[
2
4
]
I
.
S
a
l
e
h
i
n
a
n
d
D
.
K
.
K
a
n
g
,
“
A
r
e
v
i
e
w
o
n
d
r
o
p
o
u
t
r
e
g
u
l
a
r
i
z
a
t
i
o
n
a
p
p
r
o
a
c
h
e
s
f
o
r
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
s
w
i
t
h
i
n
t
h
e
sc
h
o
l
a
r
l
y
d
o
m
a
i
n
,
”
E
l
e
c
t
r
o
n
i
c
s
,
v
o
l
.
1
2
,
n
o
.
1
4
,
p
.
3
1
0
6
,
Ju
l
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
1
2
1
4
3
1
0
6
.
[
2
5
]
S
.
M
i
n
,
B
.
Le
e
,
a
n
d
S
.
Y
o
o
n
,
“
D
e
e
p
l
e
a
r
n
i
n
g
i
n
b
i
o
i
n
f
o
r
m
a
t
i
c
s
,
”
Bri
e
f
i
n
g
s
i
n
b
i
o
i
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
8
,
n
o
.
5
,
p
p
.
8
5
1
–
8
6
9
,
Ju
l
.
2
0
1
7
,
d
o
i
:
1
0
.
1
0
9
3
/
b
i
b
/
b
b
w
0
6
8
.
[
2
6
]
T.
C
h
e
n
a
n
d
C
.
G
u
e
s
t
r
i
n
,
“
X
G
B
o
o
s
t
:
a
s
c
a
l
a
b
l
e
t
r
e
e
b
o
o
st
i
n
g
s
y
st
e
m,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
2
2
n
d
A
C
M
S
I
G
K
D
D
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
K
n
o
w
l
e
d
g
e
D
i
sco
v
e
ry
a
n
d
D
a
t
a
Mi
n
i
n
g
,
A
u
g
.
2
0
1
6
,
v
o
l
.
1
3
-
17
-
A
u
g
u
,
p
p
.
7
8
5
–
7
9
4
,
d
o
i
:
1
0
.
1
1
4
5
/
2
9
3
9
6
7
2
.
2
9
3
9
7
8
5
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Na
o
u
a
l
Mo
u
h
n
i
S
M
IEE
E,
h
o
l
d
s
a
P
h
.
D
.
i
n
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
is
c
u
rre
n
tl
y
a
p
ro
fe
ss
o
r
a
t
F
S
TE
Un
iv
e
rsit
y
M
o
u
la
y
Ism
a
il
o
f
M
e
k
n
e
s.
P
re
v
i
o
u
sly
,
sh
e
se
rv
e
d
a
s
th
e
Dire
c
to
r
o
f
Re
se
a
rc
h
a
n
d
De
v
e
lo
p
m
e
n
t
a
t
th
e
LAM
IG
EP
m
u
lt
id
isc
ip
li
n
a
ry
re
se
a
rc
h
lab
o
ra
to
r
y
a
t
EM
S
I
M
a
rra
k
e
c
h
.
S
h
e
h
a
s
b
e
e
n
tea
c
h
in
g
a
s
a
C
o
m
p
u
ter
S
c
ien
c
e
P
ro
fe
ss
o
r
a
t
th
e
sa
m
e
in
sti
tu
ti
o
n
sin
c
e
2
0
1
2
.
S
h
e
h
a
s
o
b
tai
n
e
d
sp
e
c
ialize
d
trai
n
in
g
s:
i
n
a
rti
ficia
l
in
telli
g
e
n
c
e
fro
m
t
h
e
NV
IDIA
De
e
p
Lea
rn
in
g
In
sti
tu
te,
e
d
u
c
a
ti
o
n
a
l
a
d
v
a
n
c
e
m
e
n
ts
fro
m
Ho
n
o
r
is
Un
i
v
e
rsity
,
e
x
p
e
rti
se
i
n
b
ig
d
a
ta
fro
m
IB
M
,
a
n
d
d
a
tab
a
s
e
Ad
m
in
istratio
n
fro
m
ORA
C
LE.
He
r
re
se
a
rc
h
fo
c
u
se
s
o
n
a
rti
f
icia
l
in
telli
g
e
n
c
e
,
re
n
e
wa
b
le
e
n
e
rg
ies
,
a
n
d
d
a
tab
a
se
tec
h
n
o
l
o
g
ies
.
S
h
e
se
rv
e
s
a
s
a
se
n
i
o
r
m
e
m
b
e
r
o
f
t
h
e
IEE
E
a
n
d
is
a
c
t
iv
e
ly
in
v
o
l
v
e
d
i
n
se
v
e
ra
l
a
c
a
d
e
m
ic an
d
p
ro
fe
ss
io
n
a
l
c
o
m
m
u
n
it
ies
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
n
.
m
o
u
h
n
i@iee
e
.
o
rg
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
6
,
No
.
2
,
No
v
em
b
er
20
24
:
1
3
0
1
-
130
8
1308
Ibti
ss
a
m
Am
a
l
o
u
is
a
d
o
c
to
ra
l
stu
d
e
n
t
a
t
th
e
F
a
c
u
lt
y
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
o
l
o
g
y
o
f
Ca
d
i
A
y
y
a
d
Un
i
v
e
rsity
,
fo
c
u
si
n
g
o
n
th
e
p
re
d
ict
i
o
n
o
f
e
n
e
rg
y
c
o
n
su
m
p
ti
o
n
th
ro
u
g
h
a
rti
ficia
l
in
telli
g
e
n
c
e
a
p
p
ro
a
c
h
e
s.
S
h
e
h
o
ld
s
a
M
a
ste
r
’
s
d
e
g
re
e
in
Da
ta
S
c
ien
c
e
a
n
d
De
c
isio
n
S
u
p
p
o
rt
fr
o
m
th
e
sa
m
e
u
n
i
v
e
rsity
.
Wi
t
h
a
stro
n
g
b
a
c
k
g
r
o
u
n
d
in
c
o
m
p
u
ter
sc
ien
c
e
,
sh
e
a
lso
se
rv
e
s
a
s
a
c
o
m
p
u
ter
s
c
ien
c
e
in
stru
c
to
r
a
t
t
h
e
M
o
ro
c
c
a
n
S
c
h
o
o
l
o
f
E
n
g
i
n
e
e
rin
g
S
c
ien
c
e
s.
He
r
a
c
a
d
e
m
ic
p
u
rsu
it
s
a
n
d
p
ro
fe
ss
io
n
a
l
r
o
les
re
flec
t
h
e
r
d
e
d
ica
ti
o
n
to
a
d
v
a
n
c
in
g
k
n
o
wle
d
g
e
i
n
th
e
fiel
d
o
f
e
n
e
r
g
y
c
o
n
su
m
p
ti
o
n
p
re
d
ictio
n
a
n
d
a
rti
f
i
c
ial
in
telli
g
e
n
c
e
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
i
b
ti
ss
a
m
a
m
a
lo
u
1
7
0
@
g
m
a
il
.
c
o
m
.
S
a
n
a
Cha
k
r
i
h
o
l
d
s
a
P
h
.
D
.
in
S
o
ftwa
re
E
n
g
i
n
e
e
rin
g
fro
m
F
S
TG
-
UC
A
M
a
rra
k
e
c
h
a
n
d
a
n
E
n
g
i
n
e
e
rin
g
d
e
g
re
e
in
S
o
ftwa
re
En
g
i
n
e
e
rin
g
fro
m
F
S
T
M
o
h
a
m
m
e
d
ia
-
UH
2
Ca
sa
b
lan
c
a
.
S
h
e
c
o
m
p
let
e
d
h
e
r
DU
T
i
n
Co
m
p
u
ter
S
c
ien
c
e
fro
m
F
S
TG
-
UCA
M
a
rra
k
e
c
h
t
h
e
ir
i
n
fl
u
e
n
ti
a
l
sc
h
o
l
a
rly
a
rti
c
les
o
n
se
m
a
n
ti
c
traje
c
t
o
ry
k
n
o
wle
d
g
e
d
isc
o
v
e
ry
h
a
v
e
il
l
u
m
in
a
ted
m
o
v
i
n
g
o
b
jec
t
b
e
h
a
v
i
o
rs
a
n
d
p
a
tt
e
r
n
e
x
trac
ti
o
n
.
He
r
e
x
p
e
rti
se
in
d
a
ta
m
in
in
g
b
r
id
g
e
s
th
e
o
re
ti
c
a
l
re
s
e
a
rc
h
a
n
d
p
ra
c
ti
c
a
l
a
p
p
li
c
a
ti
o
n
s,
a
d
d
re
ss
in
g
re
a
l
-
wo
rl
d
c
h
a
ll
e
n
g
e
s
with
in
n
o
v
a
ti
v
e
so
l
u
ti
o
n
s.
T
h
e
ir
c
o
m
m
it
m
e
n
t
t
o
c
u
tt
in
g
-
e
d
g
e
re
se
a
rc
h
in
o
u
t
li
e
r
d
e
tec
t
io
n
s
y
ste
m
s
e
n
rich
e
s
th
e
s
c
ien
ti
fic
c
o
m
m
u
n
it
y
a
n
d
in
sp
i
re
s
th
e
n
e
x
t
g
e
n
e
ra
ti
o
n
o
f
re
se
a
rc
h
e
rs.
Dr.
Ch
a
k
ri
’
s
c
u
rre
n
t
re
se
a
rc
h
fo
c
u
se
s
o
n
n
e
w
m
e
th
o
d
s
fo
r
o
u
tl
ier
d
e
tec
ti
o
n
,
a
imin
g
t
o
d
e
e
p
e
n
u
n
d
e
rsta
n
d
i
n
g
in
th
e
fiel
d
a
n
d
f
o
ste
r
t
h
e
d
e
v
e
lo
p
m
e
n
t
o
f
ro
b
u
st
o
u
tl
ier
d
e
tec
ti
o
n
s
y
ste
m
s.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
c
h
a
k
ri.
sa
n
a
@g
m
a
il
.
c
o
m
.
Mo
h
a
m
e
d
o
u
Cheik
h
T
o
u
r
a
d
is
a
re
se
a
r
c
h
p
ro
fe
ss
o
r
o
f
C
o
m
p
u
ter
S
c
ien
c
e
a
t
th
e
F
a
c
u
lt
y
o
f
S
c
ie
n
c
e
a
n
d
Tec
h
n
o
lo
g
y
,
Un
iv
e
rsity
o
f
No
u
a
k
c
h
o
tt
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
a
rti
ficia
l
in
telli
g
e
n
c
e
,
n
a
t
u
ra
l
lan
g
u
a
g
e
p
ro
c
e
ss
in
g
,
d
e
e
p
lea
rn
in
g
,
sim
il
a
rit
y
lea
rn
in
g
,
a
n
d
b
ig
d
a
ta.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
c
h
e
ik
h
t
o
u
ra
d
m
o
h
a
m
e
d
o
u
@g
m
a
il
.
c
o
m
.
Mo
h
a
m
e
d
C
h
a
k
r
a
o
u
i
c
o
m
p
lete
d
h
is
P
h
.
D.
in
Co
m
p
u
ter
S
c
ien
c
e
a
t
Ca
d
i
Ay
y
a
d
U
n
iv
e
rsit
y
,
M
o
ro
c
c
o
,
w
h
e
re
h
is
re
se
a
rc
h
fo
c
u
se
d
o
n
a
d
v
a
n
c
e
d
a
lg
o
rit
h
m
s
fo
r
d
a
tab
a
se
a
n
a
ly
sis.
He
is
c
u
rre
n
tl
y
a
n
As
so
c
iate
P
r
o
fe
ss
o
r
a
t
S
u
lt
a
n
M
o
u
lay
S
li
m
a
n
e
Un
iv
e
rsity
,
a
tt
a
c
h
e
d
to
t
h
e
P
o
ly
d
isc
ip
li
n
a
ry
F
a
c
u
lt
y
o
f
K
h
o
u
rib
g
a
.
He
r
re
se
a
rc
h
in
tere
sts
p
rima
ril
y
in
c
lu
d
e
a
rti
ficia
l
in
telli
g
e
n
c
e
a
n
d
it
s
a
p
p
li
c
a
ti
o
n
s
i
n
v
a
rio
u
s
fiel
d
s.
Wi
th
a
sig
n
ifi
c
a
n
t
re
se
a
rc
h
g
ra
n
t
fro
m
t
h
e
u
n
iv
e
rsit
y
,
su
c
h
a
s a
d
v
a
n
c
e
m
e
n
t
s in
m
e
d
ica
l
ima
g
in
g
.
His
wo
rk
in
th
is
a
re
a
in
c
l
u
d
e
s
d
e
v
e
l
o
p
i
n
g
AI
-
b
a
se
d
d
iag
n
o
st
ic
t
o
o
ls
fo
r
t
h
e
e
a
rl
y
d
e
tec
ti
o
n
o
f
d
ise
a
se
s
su
c
h
a
s
b
re
a
st
c
a
n
c
e
r.
He
is
th
e
p
re
sid
e
n
t
o
f
th
e
M
o
r
o
c
c
a
n
As
so
c
iatio
n
o
f
Artifi
c
ial
In
telli
g
e
n
c
e
a
n
d
Di
g
it
a
l
Tran
siti
o
n
,
wh
ich
o
r
g
a
n
ize
s
se
v
e
ra
l
in
te
rn
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s
a
n
d
fo
ru
m
s,
in
c
l
u
d
i
n
g
th
e
In
ter
n
a
ti
o
n
a
l
Co
n
fe
re
n
c
e
o
n
Co
m
p
u
ter
E
n
g
i
n
e
e
rin
g
a
n
d
Artifi
c
ial
In
telli
g
e
n
c
e
.
His
c
o
n
tri
b
u
ti
o
n
s
si
g
n
ifi
c
a
n
t
ly
imp
a
c
t
g
lo
b
a
l
d
isc
u
ss
io
n
s
o
n
t
h
e
a
d
v
a
n
c
e
m
e
n
ts
in
AI f
o
r
h
e
a
lt
h
c
a
re
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
.
c
h
a
k
ra
o
u
i@u
s
m
s.m
a
.
Abd
e
lm
o
u
n
a
im
Abd
a
li
Ph
.
D
.
in
S
o
li
d
M
e
c
h
a
n
ics
a
n
d
S
tr
u
c
tu
r
e
s
in
U
n
iv
e
rsit
y
P
ica
rd
ie
Ju
les
Ve
rn
e
s
o
f
Am
ien
s
in
1
9
9
6
,
F
ra
n
c
e
.
He
is
a
P
r
o
fe
ss
o
r
o
f
Co
m
p
u
ter
S
c
ien
c
e
,
De
p
u
ty
Dire
c
to
r
o
f
th
e
C
o
n
tr
o
l
a
n
d
Co
m
p
u
ter
S
c
ien
c
e
fo
r
In
tell
ig
e
n
t
S
y
ste
m
s
a
n
d
G
re
e
n
En
e
rg
y
(CI
S
IEV)
tea
m
a
t
th
e
F
a
c
u
lt
y
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
o
lo
g
y
i
n
M
a
rra
k
e
c
h
,
Ca
d
i
Ay
y
a
d
Un
iv
e
rsity
(M
o
ro
c
c
o
).
His
re
s
e
a
rc
h
in
tere
sts
in
c
l
u
d
e
b
i
g
d
a
t
a
,
d
a
ta
sc
ien
c
e
,
e
n
e
r
g
y
o
p
ti
m
iza
ti
o
n
i
n
sm
a
rt
g
rid
s
,
DTN
m
o
b
il
e
n
e
tw
o
rk
s,
b
o
n
e
re
m
o
d
e
li
n
g
,
d
a
ta
a
n
a
ly
sis,
m
a
c
h
i
n
e
lea
rn
in
g
,
d
e
e
p
lea
rn
in
g
,
a
n
d
n
u
m
e
rica
l
sim
u
latio
n
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
em
a
il
:
a
a
b
d
a
li
5
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.