T
E
L
K
O
M
NIKA
T
elec
o
mm
un
ica
t
io
n Co
m
pu
t
i
ng
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
2
2
,
No
.
6
,
Dec
em
b
er
2
0
2
4
,
p
p
.
1
4
2
2
~1
4
3
0
I
SS
N:
1
6
9
3
-
6
9
3
0
,
DOI
:
1
0
.
1
2
9
2
8
/
T
E
L
KOM
NI
K
A
.
v
2
2
i6
.
2
6
0
5
8
1422
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//telko
mn
ika
.
u
a
d
.
a
c.
i
d
A co
m
prehe
nsiv
e
a
na
ly
sis
of eye disea
ses
and
m
edica
l
data
cla
ss
ificatio
n
Ra
ed
Ala
za
ida
h
1
,
H
a
m
za
Ab
u O
w
ida
2
,
Na
w
a
f
Als
hd
a
if
a
t
3
,
Abeda
lha
k
ee
m
I
s
s
a
4
,
Su
ha
i
la
Abuo
w
a
ida
5
,
Nida
l Y
o
u
s
ef
4
1
D
e
p
a
r
t
me
n
t
o
f
D
a
t
a
S
c
i
e
n
c
e
a
n
d
A
I
,
F
a
c
u
l
t
y
o
f
I
n
f
o
r
mat
i
o
n
T
e
c
h
n
o
l
o
g
y
,
Za
r
q
a
U
n
i
v
e
r
si
t
y
,
Z
a
r
q
a
,
Jo
r
d
a
n
2
D
e
p
a
r
t
me
n
t
o
f
M
e
d
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
En
g
i
n
e
e
r
i
n
g
,
A
l
-
A
h
l
i
y
y
a
A
mm
a
n
U
n
i
v
e
r
si
t
y
,
Al
-
S
a
l
t
,
Jo
r
d
a
n
3
F
a
c
u
l
t
y
o
f
I
n
f
o
r
mat
i
o
n
T
e
c
h
n
o
l
o
g
y
,
A
p
p
l
i
e
d
S
c
i
e
n
c
e
P
r
i
v
a
t
e
U
n
i
v
e
r
si
t
y
,
A
mm
a
n
,
Jo
r
d
a
n
4
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
F
a
c
u
l
t
y
o
f
I
n
f
o
r
mat
i
o
n
T
e
c
h
n
o
l
o
g
y
,
Z
a
r
q
a
U
n
i
v
e
r
si
t
y
,
Z
a
r
q
a
,
Jo
r
d
a
n
5
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
F
a
c
u
l
t
y
o
f
I
n
f
o
r
mat
i
o
n
T
e
c
h
n
o
l
o
g
y
,
A
l
a
l
-
B
a
y
t
U
n
i
v
e
r
si
t
y
,
M
a
f
r
a
q
,
Jo
r
d
a
n
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
7
,
2
0
24
R
ev
i
s
ed
J
u
n
24
,
2
0
24
A
cc
ep
ted
A
u
g
5
,
2
0
24
V
isio
n
lo
ss
is
a
c
rit
ica
l
h
e
a
lt
h
issu
e
th
a
t
p
re
se
n
ts
su
b
sta
n
t
ial
c
h
a
ll
e
n
g
e
s
to
b
o
t
h
i
n
d
iv
id
u
a
ls
a
n
d
c
o
m
m
u
n
i
ti
e
s.
F
o
r
t
h
o
se
a
ff
e
c
ted
,
it
c
a
n
lea
d
t
o
d
if
f
icu
lt
ies
in
p
e
rf
o
r
m
in
g
d
a
il
y
a
c
ti
v
it
ies
,
h
in
d
e
r
e
d
u
c
a
ti
o
n
a
l
a
n
d
e
m
p
lo
y
m
e
n
t
o
p
p
o
rt
u
n
it
ies
,
a
n
d
sig
n
if
ica
n
tl
y
i
m
p
a
c
t
m
e
n
tal
h
e
a
lt
h
a
n
d
o
v
e
ra
ll
q
u
a
li
ty
o
f
li
fe
.
T
h
e
in
a
b
il
it
y
to
se
e
c
a
n
a
lso
lea
d
to
in
c
re
a
se
d
d
e
p
e
n
d
e
n
c
e
o
n
o
th
e
rs,
c
re
a
ti
n
g
e
m
o
ti
o
n
a
l
a
n
d
f
in
a
n
c
ial
stra
in
s
o
n
f
a
m
il
ies
a
n
d
c
a
re
g
iv
e
rs.
T
h
is
p
a
p
e
r
h
ig
h
li
g
h
ts
th
e
b
e
n
e
f
it
o
f
m
a
c
h
in
e
lea
rn
in
g
(M
L
)
in
e
x
p
l
o
rin
g
c
o
n
d
it
i
o
n
s
th
a
t
sig
n
if
ica
n
tl
y
a
ff
e
c
t
v
isio
n
l
o
ss
.
T
h
e
g
o
a
ls
th
a
t
w
il
l
b
e
a
c
h
iev
e
d
in
t
h
is
p
a
p
e
r
a
re
to
d
e
term
in
e
th
e
b
e
st
c
las
sif
ier
c
a
p
a
b
le
o
f
d
e
a
li
n
g
w
it
h
m
e
d
ica
l
d
a
tas
e
ts
a
n
d
to
d
e
term
in
e
th
e
b
e
st
stra
teg
y
fo
r
d
e
a
li
n
g
w
it
h
m
e
d
ica
l
d
a
ta.
De
ter
m
in
e
wh
ich
f
e
a
tu
re
se
lec
ti
o
n
is
m
o
st
a
p
p
li
c
a
b
le
t
o
u
se
f
o
r
e
x
a
m
in
in
g
m
e
d
ica
l
d
a
ta
.
T
w
o
m
e
d
ica
l
d
a
tas
e
ts,
4
stra
t
e
g
ies
,
1
9
c
las
si
f
iers
,
a
n
d
2
f
e
a
tu
re
se
lec
ti
o
n
s
w
e
re
u
se
d
.
A
s
f
o
r
th
e
b
e
st
c
las
sif
ier,
th
e
sto
c
h
a
stic g
ra
d
ien
t
d
e
sc
e
n
t
(
S
G
D
)
m
o
d
e
l
w
a
s th
e
b
e
st i
n
d
a
tas
e
t
1
a
n
d
2
.
T
h
e
f
u
n
c
ti
o
n
stra
teg
y
sh
o
w
e
d
th
e
b
e
st
p
e
rf
o
rm
a
n
c
e
,
f
o
ll
o
w
e
d
b
y
th
e
r
u
les
stra
teg
y
.
Co
rre
latio
n
A
tt
rib
u
teEv
a
l
wa
s
sh
o
w
n
to
b
e
th
e
b
e
s
t
f
e
a
tu
re
se
lec
ti
o
n
,
w
h
il
e
Clas
sif
ierA
tt
ri
b
u
teEv
a
l
w
a
s
th
e
se
c
o
n
d
-
b
e
s
t
f
e
a
tu
re
se
lec
ti
o
n
.
K
ey
w
o
r
d
s
:
C
las
s
i
f
icatio
n
E
y
e
d
is
ea
s
es
Ma
ch
i
n
e
lear
n
i
n
g
Me
d
ical
d
ata
an
al
y
s
is
Vis
io
n
lo
s
s
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
:
Su
h
aila
A
b
u
o
w
aid
a
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
,
Facu
l
t
y
o
f
I
n
f
o
r
m
atio
n
T
ec
h
n
o
lo
g
y
,
A
l a
l
-
B
a
y
t U
n
i
v
er
s
it
y
Ma
f
r
aq
,
J
o
r
d
an
E
m
ail:
s
ab
u
o
w
eu
d
a
@
zu
.
ed
u
.
j
o
1.
I
NT
RO
D
UCT
I
O
N
Vis
io
n
lo
s
s
i
s
a
v
ital
h
ea
lt
h
p
r
o
b
lem
t
h
at
a
f
f
ec
ts
in
d
i
v
id
u
al
s
.
T
h
er
e
ca
n
b
e
s
e
v
er
al
ca
u
s
e
s
o
f
v
is
io
n
lo
s
s
,
b
u
t
t
h
i
s
p
ap
er
f
o
cu
s
e
s
o
n
d
is
ea
s
e
s
t
h
at
m
a
y
af
f
ec
t
v
i
s
io
n
s
i
g
n
if
ican
t
l
y
,
w
i
th
o
u
t
r
ela
tin
g
to
t
h
e
n
o
r
m
al
ele
m
e
n
ts
as
s
o
ciate
d
w
it
h
ag
i
n
g
.
E
y
e
d
is
ea
s
es
i
n
ter
m
s
o
f
t
h
eir
ef
f
ec
t
o
n
v
i
s
io
n
.
T
h
er
e
ar
e
m
a
n
y
d
i
s
ea
s
es
t
h
at
m
a
y
lead
to
v
is
io
n
lo
s
s
.
So
m
e
o
f
th
ese
d
is
ea
s
es
ca
n
b
e
s
u
d
d
en
an
d
p
r
o
g
r
ess
iv
e,
w
h
i
le
o
th
er
s
ar
e
g
r
ad
u
al
an
d
d
ev
elo
p
o
v
er
ti
m
e.
T
h
ese
d
i
s
ea
s
es
i
n
cl
u
d
e:
ca
tar
ac
ts
,
m
a
cu
lar
d
eg
e
n
er
atio
n
,
d
iab
etic
r
etin
o
p
ath
y
(
DR
)
,
g
lau
co
m
a,
o
p
tic
n
e
u
r
iti
s
,
an
d
r
etin
al
d
etac
h
m
e
n
t.
T
h
e
ca
u
s
es
o
f
v
i
s
io
n
lo
s
s
a
n
d
th
eir
i
m
p
ac
t
o
n
th
e
in
d
i
v
id
u
al
v
ar
y
d
ep
en
d
i
n
g
o
n
t
h
e
t
y
p
e
o
f
d
is
ea
s
e.
C
h
r
o
n
ic
d
is
ea
s
es
s
u
c
h
as
d
iab
etes
a
n
d
h
ea
r
t
d
is
ea
s
e
ca
n
h
av
e
a
n
eg
at
iv
e
i
m
p
ac
t o
n
v
is
io
n
,
as
w
ell
a
s
s
o
m
e
g
e
n
etic
co
n
d
itio
n
s
t
h
at
m
a
y
lead
to
v
i
s
io
n
lo
s
s
at
an
ea
r
l
y
ag
e
[
1
]
.
T
h
is
p
ap
er
ex
p
lo
its
th
e
ca
p
ab
ilit
ies
o
f
m
ac
h
i
n
e
lear
n
i
n
g
(
ML
)
in
s
t
u
d
y
i
n
g
th
e
s
e
d
is
ea
s
e
s
,
as
ML
:
is
a
b
r
an
ch
o
f
ar
ti
f
icial
i
n
tell
ig
e
n
ce
(
A
I
)
co
n
ce
r
n
ed
w
ith
d
e
v
elo
p
in
g
tech
n
o
lo
g
ie
s
t
h
at
a
llo
w
s
y
s
te
m
s
a
n
d
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
A
co
mp
r
eh
en
s
ive
a
n
a
lysi
s
o
f e
ye
d
is
ea
s
es a
n
d
med
ica
l d
a
ta
cla
s
s
ifica
tio
n
(
R
a
ed
A
la
z
a
id
a
h
)
1423
ap
p
licatio
n
s
to
au
to
m
atica
ll
y
i
m
p
r
o
v
e
th
e
ir
p
er
f
o
r
m
an
ce
b
y
i
n
ter
ac
ti
n
g
w
i
th
d
ata
a
n
d
g
ai
n
i
n
g
e
x
p
er
ien
ce
.
M
L
is
b
ased
o
n
al
g
o
r
ith
m
s
t
h
at
all
o
w
s
y
s
te
m
s
to
lear
n
f
r
o
m
d
ata
an
d
i
m
p
r
o
v
e
th
e
ir
p
er
f
o
r
m
an
c
e
w
i
th
o
u
t r
eq
u
ir
i
n
g
ex
p
licit
p
r
o
g
r
a
m
m
i
n
g
[
2
]
.
T
y
p
e
s
o
f
ML
:
s
u
p
er
v
i
s
ed
lear
n
in
g
,
t
h
e
m
o
d
el
is
tr
ai
n
ed
o
n
a
s
et
o
f
d
ata
th
at
co
n
tain
s
ex
p
ec
ted
in
p
u
ts
a
n
d
o
u
tp
u
ts
,
a
n
d
th
e
m
o
d
el
lear
n
s
h
o
w
to
p
r
ed
ict
th
e
d
esire
d
o
u
tp
u
ts
w
h
en
r
ec
ei
v
i
n
g
n
e
w
i
n
p
u
t
s
.
I
t
is
u
s
ed
i
n
i
m
a
g
e
class
i
f
icatio
n
,
m
ac
h
i
n
e
tr
a
n
s
latio
n
,
an
d
s
p
ee
ch
r
ec
o
g
n
itio
n
.
Se
m
i
-
s
u
p
er
v
i
s
ed
lear
n
in
g
:
it
u
s
e
s
a
d
ataset
t
h
at
co
n
tain
s
s
u
p
p
o
r
ted
an
d
u
n
s
u
p
p
o
r
ted
d
ata,
an
d
in
tr
o
d
u
cin
g
u
n
s
u
p
p
o
r
ted
d
ata
is
i
m
p
o
r
tan
t
to
in
cr
ea
s
e
th
e
ac
cu
r
ac
y
o
f
t
h
e
m
o
d
el.
Un
s
u
p
er
v
i
s
ed
lear
n
in
g
d
ea
ls
w
it
h
d
ata
th
at
d
o
es
n
o
t
h
av
e
a
d
ef
in
ed
o
u
tp
u
t.
I
t
ai
m
s
to
d
is
co
v
er
p
atter
n
s
,
g
r
o
u
p
an
d
cla
s
s
i
f
y
w
it
h
o
u
t
e
x
ter
n
al
g
u
id
a
n
ce
,
an
d
is
u
s
ed
i
n
clu
s
ter
a
n
al
y
s
i
s
an
d
d
i
m
en
s
io
n
alit
y
r
ed
u
ctio
n
.
R
ei
n
f
o
r
ce
m
e
n
t
lear
n
in
g
:
it
i
s
b
ased
o
n
t
h
e
co
n
ce
p
t
o
f
r
e
w
ar
d
an
d
p
u
n
i
s
h
m
e
n
t
[
3
]
-
[
1
0
]
.
T
h
e
m
o
d
el
in
ter
ac
ts
w
it
h
a
co
m
p
lex
en
v
ir
o
n
m
en
t
an
d
lear
n
s
f
r
o
m
th
e
r
es
u
lt
s
.
I
t
is
u
s
ed
in
th
e
f
ield
s
o
f
in
te
lli
g
e
n
t
to
y
s
,
co
n
tr
o
l
r
o
b
o
ts
,
an
d
in
ter
ac
ti
v
e
d
ec
is
io
n
m
a
k
in
g
.
A
p
p
licatio
n
s
o
f
ML
,
n
atu
r
al
la
n
g
u
a
g
e
p
r
o
ce
s
s
in
g
(
NL
P
)
to
u
n
d
er
s
tan
d
an
d
an
al
y
ze
h
u
m
an
lan
g
u
ag
e,
DN
A
s
eq
u
en
ce
clas
s
i
f
icatio
n
in
th
e
f
ield
o
f
g
en
o
m
ics
an
d
m
o
lecu
lar
b
io
lo
g
y
,
co
m
p
u
ter
v
is
io
n
f
o
r
o
b
j
ec
t
r
ec
o
g
n
itio
n
an
d
i
m
ag
e
a
n
al
y
s
is
,
s
ea
r
ch
en
g
i
n
es
to
i
m
p
r
o
v
e
an
d
p
er
s
o
n
alize
s
ea
r
ch
r
esu
lt
s
,
m
ed
ical
d
iag
n
o
s
tics
i
n
m
ed
ic
al
f
ield
i
m
a
g
i
n
g
a
n
d
m
ed
ical
d
ata
an
al
y
s
i
s
[
1
1
]
.
2.
RE
L
AT
E
D
WO
RK
A
co
m
p
r
e
h
e
n
s
i
v
e
s
ci
e
n
ti
f
ic
i
n
v
e
s
ti
g
atio
n
h
a
s
b
ee
n
ca
r
r
ie
d
o
u
t
r
eg
ar
d
in
g
t
h
e
u
s
e
o
f
ML
i
n
t
h
e
m
ed
ical
f
ield
an
d
it
s
f
u
n
ctio
n
i
n
id
en
ti
f
y
i
n
g
ill
n
ess
e
s
.
An
ex
t
en
s
i
v
e
s
cie
n
ti
f
ic
s
t
u
d
y
h
as b
ee
n
co
n
d
u
cted
o
n
th
e
ap
p
licatio
n
o
f
ML
in
th
e
m
ed
i
ca
l
in
d
u
s
tr
y
a
n
d
its
r
o
le
in
d
is
ea
s
e
d
et
ec
tio
n
[
1
2
]
-
[
1
6
]
.
T
h
is
s
ec
tio
n
w
ill
an
al
y
s
e
a
s
elec
tio
n
o
f
th
e
s
e
w
o
r
k
s
.
Au
to
m
at
ic
m
o
d
u
latio
n
r
ec
o
g
n
it
io
n
(
A
MR)
is
a
cr
u
cial
co
m
p
o
n
en
t
o
f
co
g
n
it
iv
e
ra
d
io
(
C
R
)
,
s
in
ce
it
is
r
esp
o
n
s
ib
le
f
o
r
d
etec
tin
g
a
n
d
ad
ap
tin
g
to
ch
an
g
es
i
n
t
h
e
s
u
r
r
o
u
n
d
i
n
g
e
n
v
ir
o
n
m
en
t
a
n
d
ad
j
u
s
tin
g
tactics a
cc
o
r
d
in
g
l
y
[
1
7
]
.
A
s
o
p
h
is
ticated
a
n
d
r
eliab
le
A
M
R
s
y
s
te
m
,
b
ased
o
n
d
ee
p
liter
ac
y
,
h
as b
ee
n
d
ev
elo
p
ed
r
ec
en
tl
y
.
Ho
w
e
v
er
,
all
o
f
t
h
eir
A
M
R
tr
ain
in
g
m
o
d
el
s
ar
e
ca
teg
o
r
is
ed
a
s
te
ch
n
ica
l
r
ath
er
t
h
a
n
g
en
er
ali
s
ed
.
T
h
er
ef
o
r
e,
th
ese
A
M
R
s
t
y
les
ar
e
d
if
f
ic
u
lt
to
ap
p
ly
to
s
cr
ip
ts
t
h
at
ar
e
n
o
t
s
p
ec
if
ic
o
r
s
p
ec
ialis
ed
.
T
h
is
r
esear
ch
p
r
esen
ts
a
b
lin
d
ch
an
n
el
id
en
ti
f
icatio
n
(
B
C
I
)
-
s
u
p
p
o
r
ted
g
en
er
alis
ed
A
MR
(
Gen
A
M
R
)
s
y
s
te
m
b
ased
o
n
d
ee
p
lear
n
in
g
.
T
h
e
s
y
s
te
m
u
t
ilis
e
s
t
w
o
s
ep
ar
ate
co
n
v
o
l
u
tio
n
a
l
n
eu
r
al
n
et
w
o
r
k
s
(
C
NNs)
f
o
r
th
e
tas
k
.
T
h
e
in
itial
C
NN
is
tr
ain
ed
o
n
in
-
p
h
ase
a
n
d
q
u
ad
r
atu
r
e
(
co
m
m
a
n
d
)
s
lice
s
i
g
n
al
s
,
a
n
d
its
p
u
r
p
o
s
e
i
s
to
d
if
f
er
e
n
tiate
c
h
an
n
el
o
r
d
er
s
s
u
ch
a
s
B
C
I
ac
tiv
itie
s
.
T
h
e
alter
n
ate
C
NN
i
s
tr
ain
ed
u
s
i
n
g
b
o
th
th
e
li
n
e
o
f
s
i
g
h
t
(
L
OS)
m
o
d
el
an
d
th
e
n
o
n
-
li
n
e
o
f
s
ig
h
t
(
NL
O
S)
m
o
d
el
s
ep
ar
atel
y
.
T
h
e
s
i
m
u
latio
n
f
i
n
d
in
g
s
v
a
lid
ate
th
at
o
u
r
s
u
g
g
e
s
ted
g
e
n
er
ali
s
ed
A
MR
s
y
s
te
m
s
u
r
p
ass
es
th
e
co
n
v
e
n
t
io
n
al
s
y
s
te
m
b
y
a
w
id
e
m
ar
g
in
.
I
n
ad
d
itio
n
,
th
e
s
tu
d
y
r
ef
er
e
n
ce
d
i
n
[
1
8
]
p
r
esen
ts
a
n
o
v
el
ap
p
r
o
ac
h
to
i
n
tr
o
d
u
cin
g
b
ac
k
d
o
o
r
s
in
to
M
L
m
o
d
els.
T
h
is
ap
p
r
o
ac
h
in
v
o
l
v
es
co
m
p
r
o
m
is
i
n
g
t
h
e
co
m
p
u
tatio
n
o
f
lo
s
s
v
al
u
es
i
n
th
e
tr
ain
i
n
g
p
r
o
ce
s
s
o
f
th
e
m
o
d
el.
W
e
u
s
e
it
to
s
h
o
w
ca
s
e
n
o
v
el
ca
teg
o
r
ies
o
f
b
ac
k
d
o
o
r
s
th
at
ar
e
s
ig
n
i
f
ican
tl
y
m
o
r
e
s
ig
n
i
f
ica
n
t
th
a
n
th
o
s
e
p
r
ev
io
u
s
l
y
d
o
cu
m
en
ted
.
T
h
ese
in
clu
d
e
s
i
n
g
le
-
p
i
x
el
an
d
p
h
y
s
ical
b
ac
k
d
o
o
r
s
in
I
m
a
g
eNe
t
m
o
d
el
s
,
b
ac
k
d
o
o
r
s
th
at
co
v
er
tl
y
s
w
itc
h
th
e
m
o
d
el
to
a
task
th
at
v
io
lates
in
s
u
lat
io
n
,
an
d
b
ac
k
d
o
o
r
s
th
at
d
o
n
o
t
ex
h
ib
it
in
p
u
t
v
ar
iatio
n
s
at
th
e
co
n
clu
s
io
n
o
f
th
e
p
r
o
ce
s
s
.
T
h
e
ap
p
r
o
ac
h
lack
s
v
i
s
ib
il
it
y
as
th
e
attac
k
er
is
u
n
ab
le
to
alte
r
th
e
tr
ain
i
n
g
d
ata,
m
o
n
ito
r
th
e
ex
ec
u
tio
n
o
f
th
e
ir
co
d
e
,
o
r
ac
ce
s
s
th
e
f
u
n
ct
i
o
n
in
g
m
o
d
el.
T
h
e
attac
k
m
et
h
o
d
o
lo
g
y
in
v
o
lv
e
s
in
j
ec
tin
g
m
alic
io
u
s
tr
ai
n
i
n
g
i
n
p
u
t
s
d
u
r
in
g
t
h
e
m
o
d
el
’
s
tr
ai
n
in
g
p
r
o
ce
s
s
,
u
ti
lis
i
n
g
m
u
lti
-
i
d
ea
l
o
p
tim
i
s
atio
n
to
o
b
tain
h
i
g
h
s
e
n
s
iti
v
it
y
i
n
b
o
th
th
e
p
r
i
m
ar
y
a
n
d
b
ac
k
d
o
o
r
tas
k
s
.
W
e
d
e
m
o
n
s
tr
ate
th
e
ca
p
ab
ilit
y
o
f
a
s
i
g
h
t
less
ass
a
u
lt to
ev
ad
e
an
y
ex
i
s
ti
n
g
f
o
r
m
o
f
p
r
o
tectio
n
an
d
s
u
g
g
est
in
n
o
v
ati
v
e
s
tr
ate
g
ies.
R
esear
ch
by
Or
tiz
-
E
c
h
ev
er
r
i
et
a
l
.
[
1
9
]
,
w
e
in
tr
o
d
u
ce
a
n
o
v
el
f
r
a
m
e
w
o
r
k
th
at
ca
n
au
t
o
m
a
ticall
y
r
ec
tify
s
ev
er
al
f
o
r
m
s
o
f
g
eo
m
etr
ic
d
is
to
r
tio
n
in
a
s
i
n
g
le
in
p
u
t
i
m
ag
e.
T
h
e
tech
n
iq
u
e
w
e
p
r
o
p
o
s
e
u
s
es
C
NN
s
th
at
ar
e
tr
ain
ed
o
n
a
h
u
g
e
d
at
aset
o
f
ar
tif
ic
iall
y
d
e
f
o
r
m
ed
i
m
ag
e
s
to
p
r
ed
ict
th
e
class
i
f
ic
atio
n
o
f
i
m
a
g
e
s
as
eith
er
m
al
f
o
r
m
ed
o
r
r
ep
air
ed
.
A
s
u
i
tab
le
m
o
d
el
e
m
p
lo
y
s
th
e
C
NN
ap
p
r
o
ac
h
to
esti
m
a
te
th
e
d
ef
o
r
m
atio
n
p
ar
am
eter
s
,
r
esu
lti
n
g
in
a
m
o
r
e
p
r
ec
is
e
p
r
e
d
ictio
n
.
T
h
e
u
lti
m
ate
r
ec
ti
f
ied
i
m
a
g
e
is
p
r
o
d
u
ce
d
b
ased
o
n
th
e
p
r
ed
icted
in
f
lo
w
u
ti
lis
i
n
g
an
ef
f
icie
n
t,
h
i
gh
-
q
u
alit
y
r
esa
m
p
lin
g
tec
h
n
iq
u
e.
T
h
e
test
r
es
u
lts
s
h
o
w
t
h
at
o
u
r
m
et
h
o
d
is
b
etter
th
a
n
o
t
h
er
co
r
r
ec
tio
n
m
et
h
o
d
s
an
d
ca
n
-
d
o
in
ter
esti
n
g
th
i
n
g
s
l
ik
e
d
e
f
o
r
m
atio
n
tr
an
s
f
er
,
d
ef
o
r
m
atio
n
m
ag
n
i
f
icat
io
n
,
an
d
co
-
o
cc
u
r
r
in
g
d
ef
o
r
m
atio
n
co
r
r
ec
tio
n
.
R
esear
ch
b
y
Al
az
aid
a
h
et
a
l.
[
2
0
]
d
is
cu
s
s
es
B
C
I
,
w
h
ich
ar
e
d
ev
ices
th
at
en
ab
le
in
ter
ac
tio
n
b
etw
ee
n
in
d
i
v
id
u
al
s
an
d
tech
n
o
l
o
g
y
b
ased
o
n
b
r
ain
ac
tiv
it
y
.
An
ef
f
ec
ti
v
e
an
d
n
o
n
in
v
asi
v
e
m
et
h
o
d
to
o
b
tain
co
m
p
ar
ab
le
in
f
o
r
m
at
io
n
is
th
r
o
u
g
h
t
h
e
u
s
e
o
f
elec
tr
o
en
ce
p
h
alo
g
r
ap
h
y
.
Ho
w
ev
er
,
th
ese
s
i
g
n
a
ls
ex
h
ib
it
a
lo
w
s
i
g
n
al
-
to
-
n
o
i
s
e
r
atio
as
w
ell
as
a
lo
w
s
p
atia
l
r
eso
lu
tio
n
.
T
h
i
s
s
t
u
d
y
p
r
esen
ts
a
n
o
v
el
s
y
s
te
m
t
h
at
co
m
b
in
es
e
y
ele
s
s
s
o
u
r
ce
s
ep
ar
atio
n
(
E
SS
)
to
o
b
tai
n
esti
m
ated
in
d
ep
en
d
en
t
v
ar
iab
les,
a
tw
o
-
d
i
m
en
s
io
n
al
r
ep
r
esen
tat
io
n
o
f
th
ese
ele
m
en
ta
l
s
ig
n
al
s
u
s
i
n
g
th
e
n
o
n
s
to
p
w
a
v
elet
tr
an
s
f
o
r
m
a
n
d
a
b
r
ac
k
et
s
ta
g
e
u
tili
s
i
n
g
a
C
NN
ap
p
r
o
ac
h
.
A
cr
iter
io
n
b
ased
o
n
t
h
e
s
p
ec
tr
al
co
r
r
elatio
n
w
it
h
a
m
o
v
e
m
e
n
t
-
r
elate
d
in
d
ep
en
d
en
t
co
m
p
o
n
e
n
t
(
MRIC)
is
e
m
p
lo
y
ed
to
ar
r
an
g
e
t
h
e
esti
m
ated
s
o
u
r
ce
s
u
s
i
n
g
b
li
n
d
s
o
u
r
ce
s
ep
ar
atio
n
(
B
SS
)
,
th
er
ef
o
r
e
m
in
i
m
is
in
g
s
p
atial
i
n
ter
f
er
en
ce
.
T
h
e
ex
p
er
im
e
n
tal
f
i
n
d
in
g
s
o
f
9
4
.
6
6
ac
h
iev
ed
u
ti
lis
i
n
g
a
k
-
f
o
ld
cr
o
s
s
v
alid
atio
n
ar
e
co
m
p
ar
ab
le
to
r
ec
en
tl
y
d
escr
ib
ed
m
et
h
o
d
s
i
n
th
e
s
tate
-
of
-
th
e
-
ar
t.
A
cc
o
r
d
in
g
to
B
an
g
alo
r
e
et
a
l.
[
2
1
]
,
DR
is
a
co
n
d
it
io
n
t
h
at
ar
i
s
es
as
a
r
es
u
lt
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
22
,
No
.
6
,
Dec
em
b
er
20
24
:
1
4
2
2
-
1430
1424
co
m
p
lica
tio
n
s
f
r
o
m
d
iab
etes,
lead
in
g
to
ir
r
ev
er
s
ib
le
d
a
m
a
g
e
to
t
h
e
b
lo
o
d
v
e
s
s
el
s
i
n
t
h
e
r
eti
n
a.
Dr
y
e
y
e
s
y
n
d
r
o
m
e
is
a
p
r
im
ar
y
f
ac
to
r
in
th
e
d
ev
elo
p
m
e
n
t
o
f
b
lin
d
n
e
s
s
if
it
is
n
o
t
id
en
tifie
d
in
ad
v
an
ce
.
C
u
r
r
en
t
l
y
,
th
e
ex
is
t
i
n
g
t
h
er
ap
ies
f
o
r
D
R
ar
e
r
estricte
d
to
h
a
lti
n
g
o
r
p
o
s
tp
o
n
in
g
th
e
d
ec
li
n
e
o
f
v
is
i
o
n
.
I
t
is
cr
u
cial
to
e
m
p
h
a
s
is
e
t
h
e
i
m
p
o
r
tan
ce
o
f
r
eg
u
lar
s
ca
n
n
i
n
g
,
u
til
is
i
n
g
h
i
g
h
l
y
e
f
f
ic
ien
t
co
m
p
u
ter
-
b
ased
te
ch
n
iq
u
es
to
d
etec
t
in
s
ta
n
ce
s
a
t
an
ea
r
l
y
s
ta
g
e.
T
h
e
p
r
esen
t
s
tu
d
y
i
n
tr
o
d
u
ce
d
en
tire
l
y
a
u
to
m
ated
o
p
in
io
n
s
y
s
te
m
s
th
at
s
u
r
p
as
s
m
an
u
al
m
eth
o
d
s
i
n
o
r
d
er
t
o
p
r
ev
en
t
m
is
d
ia
g
n
o
s
is
,
th
er
eb
y
lo
w
er
i
n
g
ti
m
e,
ef
f
o
r
t,
an
d
ex
p
en
s
es.
T
h
e
s
u
g
g
ested
tech
n
iq
u
e
ca
teg
o
r
is
e
s
DR
p
h
o
to
s
in
to
f
iv
e
s
tag
e
s
:
n
o
-
DR
,
m
ild
,
m
o
d
er
ate,
s
ev
er
e,
an
d
p
r
o
l
if
er
ativ
e
DR
.
A
d
d
itio
n
al
l
y
,
it
ac
cu
r
atel
y
id
e
n
ti
f
ies
t
h
e
s
p
ec
if
ic
lo
ca
tio
n
s
o
f
th
e
af
f
ec
ted
lesi
o
n
s
o
n
t
h
e
p
atien
t
’
s
f
ac
e.
T
h
e
s
y
s
te
m
co
n
s
is
t
s
o
f
t
w
o
h
i
g
h
l
y
in
f
o
r
m
ed
m
o
d
els.
T
h
e
in
itial
m
o
d
el
C
o
n
v
o
l
u
tio
n
al
n
eu
r
al
n
et
w
o
r
k
5
1
2
(
C
NN5
1
2
)
em
p
lo
y
ed
t
h
e
e
n
tir
e
i
m
a
g
e
as
a
n
i
n
p
u
t
to
t
h
e
C
N
N
m
o
d
el
in
o
r
d
er
to
ca
teg
o
r
is
e
it
in
to
o
n
e
o
f
t
h
e
f
i
v
e
s
tag
e
s
o
f
DR
.
I
t
o
b
tain
ed
a
p
r
ec
is
io
n
s
co
r
e
o
f
8
8
.
6
a
n
d
8
4
.
1
o
n
th
e
DR
an
d
th
e
APT
OS
Kag
g
le
2
0
1
9
p
u
b
lic
d
atasets
,
r
esp
ec
tiv
el
y
,
s
u
r
p
ass
in
g
th
e
cu
r
r
en
t
lead
in
g
r
esu
lts
.
T
h
e
alte
r
n
ate
m
o
d
el
u
tili
s
ed
a
Yo
u
On
l
y
L
o
o
k
On
ce
,
Ver
s
io
n
3
(
YOL
Ov
3
)
m
o
d
el
to
d
etec
t
an
d
l
o
ca
te
th
e
DR
lesi
o
n
s
.
I
t
ac
h
iev
ed
a
lesi
o
n
lo
ca
lizatio
n
m
ea
n
a
v
er
ag
e
p
r
ec
is
io
n
(
m
ap
)
o
f
0
.
2
1
6
o
n
th
e
DR
d
ataset
,
s
u
r
p
ass
i
n
g
t
h
e
ex
i
s
ti
n
g
s
tate
-
of
-
t
h
e
-
ar
t
r
es
u
lt
s
.
Ulti
m
a
tel
y
,
b
o
th
C
NN5
1
2
an
d
YOL
O
v
3
s
tr
u
ct
u
r
es
w
er
e
c
o
m
b
i
n
ed
to
ca
te
g
o
r
is
e
D
R
i
m
ag
es
a
n
d
lo
ca
te
D
R
lesi
o
n
s
,
ac
h
ie
v
in
g
a
s
e
n
s
i
tiv
it
y
o
f
8
9
an
d
a
s
p
ec
if
icit
y
o
f
9
7
.
3
.
3.
M
E
T
H
O
D
A
co
m
p
r
e
h
e
n
s
i
v
e
s
cie
n
ti
f
ic
i
n
v
e
s
ti
g
atio
n
h
a
s
b
ee
n
ca
r
r
ie
d
o
u
t
r
eg
ar
d
in
g
t
h
e
u
s
e
o
f
ML
i
n
t
h
e
m
ed
ical
f
ield
an
d
it
s
f
u
n
ctio
n
in
id
e
A
co
m
p
r
e
h
en
s
iv
e
s
cie
n
tif
ic
i
n
v
esti
g
atio
n
h
as
b
ee
n
ca
r
r
ied
o
u
t
r
eg
ar
d
in
g
th
e
u
s
e
o
f
M
L
in
th
e
m
ed
ic
al
f
ield
an
d
its
f
u
n
ctio
n
in
i
d
en
tify
i
n
g
illn
e
s
s
es
[
2
2
]
-
[2
7
]
.
T
h
is
r
esear
ch
h
as
h
ig
h
li
g
h
ted
t
h
e
s
i
g
n
if
ican
t p
o
t
en
tial o
f
M
L
al
g
o
r
ith
m
s
i
n
i
m
p
r
o
v
in
g
d
ia
g
n
o
s
tic
ac
c
u
r
ac
y
a
n
d
ef
f
icie
n
c
y
ac
r
o
s
s
v
ar
io
u
s
m
ed
ical
d
o
m
ai
n
s
.
T
h
e
cu
r
r
en
t
p
ap
er
b
u
ild
s
u
p
o
n
th
is
f
o
u
n
d
atio
n
,
f
o
cu
s
in
g
s
p
ec
i
f
icall
y
o
n
th
r
ee
k
e
y
o
b
j
ec
tiv
es:
d
eter
m
i
n
i
n
g
th
e
b
est
class
if
ier
,
id
en
tify
i
n
g
th
e
m
o
s
t
e
f
f
ec
tiv
e
s
tr
ateg
y
,
an
d
s
elec
tin
g
th
e
o
p
ti
m
al
f
ea
t
u
r
es
f
o
r
m
ed
ical
d
iag
n
o
s
i
s
.
T
o
ac
h
iev
e
th
e
s
e
g
o
als,
t
h
is
s
ec
tio
n
d
is
c
u
s
s
es
i
n
d
etail
th
e
m
et
h
o
d
o
lo
g
y
e
m
p
lo
y
ed
,
in
cl
u
d
in
g
t
h
e
s
y
s
te
m
atic
ap
p
r
o
ac
h
to
d
ata
co
llectio
n
an
d
th
e
r
i
g
o
r
o
u
s
an
al
y
s
is
te
ch
n
iq
u
es
u
tili
ze
d
.
3
.
1
.
Da
t
a
s
et
s
a
nd
pr
o
ce
s
s
ing
E
ig
h
teen
d
i
f
f
er
e
n
t
clas
s
if
ier
s
b
elo
n
g
in
g
to
f
o
u
r
s
tr
ate
g
ie
s
w
er
e
co
m
p
ar
ed
o
n
th
e
b
asi
s
o
f
th
eir
p
r
ed
ictiv
e
p
er
f
o
r
m
a
n
ce
w
h
en
ap
p
lied
to
th
e
t
w
o
s
tu
d
ied
d
atasets
.
A
p
p
lied
in
W
E
K
A
p
r
o
g
r
a
m
.
T
h
e
y
w
er
e
ap
p
lied
to
v
alid
ate
th
e
r
esu
l
ts
.
T
h
e
r
elativ
e
an
al
y
s
i
s
tak
es
in
to
ac
co
u
n
t
f
o
u
r
e
v
alu
a
t
io
n
cr
iter
ia.
T
h
ese
p
ar
am
eter
s
ar
e
ac
cu
r
ac
y
,
f
al
s
e
p
o
s
itiv
e
(
FP
)
r
ate,
ac
cu
r
ac
y
an
d
r
ec
o
v
er
y
,
th
e
f
ir
s
t
tab
le
s
h
o
w
s
t
h
e
d
etails
o
f
th
e
d
atasets
.
3
.
2
.
I
dentif
y
ing
t
he
bes
t
cla
s
s
if
ica
t
io
n
m
o
de
l a
nd
identif
y
ing
t
he
bes
t
s
t
ra
t
eg
y
De
ter
m
i
n
i
n
g
t
h
e
b
est
class
i
f
ic
atio
n
m
o
d
el
is
th
e
f
ir
s
t
g
o
al,
an
d
T
a
b
le
1
s
h
o
w
s
th
e
eig
h
tee
n
class
if
ier
s
o
n
th
e
t
w
o
d
atase
ts
s
t
u
d
ied
.
T
a
b
le
2
s
h
o
w
s
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
f
ir
s
t
d
ata
s
et
w
i
th
a
q
u
ar
ter
o
f
th
e
m
ea
s
u
r
e
m
e
n
t
s
ta
n
d
ar
d
s
.
T
ab
l
e
3
d
escr
ib
es
t
h
e
p
er
f
o
r
m
a
n
c
e
o
f
t
h
e
s
ec
o
n
d
d
ata
s
e
t
w
it
h
f
o
u
r
m
ea
s
u
r
e
m
e
n
t
s
tan
d
ar
d
s
.
T
ab
le
1
.
Data
in
f
o
r
m
atio
n
D
a
t
a
se
t
s
I
n
st
a
n
c
e
s
A
t
t
r
i
b
u
t
e
s
d
i
a
b
e
st
_
d
a
t
a
7
0
6
9
2
18
g
l
a
u
c
o
me
6
5
0
5
h
y
p
e
r
t
e
n
si
o
n
2
6
0
8
3
14
T
h
e
an
aly
s
is
o
f
d
ataset
1
r
ev
ea
led
s
ig
n
if
ican
t
i
n
s
i
g
h
ts
in
to
class
if
ier
an
d
lear
n
i
n
g
s
tr
ateg
y
p
er
f
o
r
m
a
n
ce
ac
r
o
s
s
m
u
ltip
le
m
etr
ics.
I
n
T
ab
le
2
,
th
e
s
to
ch
a
s
tic
g
r
ad
ie
n
t
d
escen
t
(
S
GD)
cl
ass
i
f
ier
e
m
er
g
ed
as
th
e
to
p
p
er
f
o
r
m
er
a
m
o
n
g
1
9
class
i
f
ier
s
e
v
alu
a
ted
,
w
h
i
le
th
e
f
u
n
ctio
n
s
lear
n
in
g
s
tr
ate
g
y
p
r
o
v
ed
m
o
s
t
ef
f
ec
ti
v
e
a
m
o
n
g
f
o
u
r
s
tr
ate
g
ies
e
x
a
m
i
n
ed
.
T
h
ese
f
i
n
d
i
n
g
s
w
er
e
b
ase
d
o
n
a
co
m
p
r
e
h
en
s
iv
e
a
s
s
e
s
s
m
en
t
u
s
i
n
g
f
o
u
r
k
e
y
m
etr
ics:
ac
c
u
r
ac
y
,
FP
r
ate,
p
r
ec
is
io
n
,
an
d
r
ec
all.
No
tab
l
y
,
T
ab
le
3
c
o
r
r
o
b
o
r
ated
th
ese
r
esu
lt
s
,
ag
a
i
n
id
en
ti
f
y
i
n
g
SG
D
as
th
e
s
u
p
er
io
r
class
i
f
ier
an
d
f
u
n
c
tio
n
s
as
th
e
o
p
ti
m
al
lear
n
in
g
s
tr
ateg
y
f
o
r
d
ataset
1
.
T
h
i
s
co
n
s
is
ten
c
y
ac
r
o
s
s
tab
les
u
n
d
er
s
co
r
es
th
e
r
o
b
u
s
tn
es
s
o
f
SGD
an
d
th
e
f
u
n
ctio
n
s
s
tr
ateg
y
i
n
h
a
n
d
li
n
g
t
h
e
p
ar
ticu
lar
ch
ar
ac
ter
is
t
ics
o
f
d
ataset
1
,
s
u
g
g
es
tin
g
t
h
eir
p
o
t
en
tial
v
al
u
e
f
o
r
s
i
m
ilar
d
ata
a
n
al
y
s
i
s
tas
k
s
in
th
e
f
ield
.
T
h
is
e
x
p
an
d
ed
p
ar
ag
r
ap
h
n
o
w
i
n
cl
u
d
es
a
clea
r
m
ai
n
s
en
ten
ce
(
th
e
f
ir
s
t
o
n
e)
an
d
s
u
p
p
o
r
tin
g
s
e
n
ten
ce
s
th
at
p
r
o
v
id
e
ad
d
itio
n
al
co
n
te
x
t
an
d
d
etail.
I
t
m
ai
n
tai
n
s
t
h
e
o
r
ig
i
n
al
in
f
o
r
m
a
tio
n
w
h
il
e
o
f
f
er
i
n
g
a
m
o
r
e
co
m
p
r
e
h
en
s
iv
e
o
v
er
v
ie
w
o
f
th
e
r
esu
lts
a
n
d
th
eir
i
m
p
licatio
n
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
A
co
mp
r
eh
en
s
ive
a
n
a
lysi
s
o
f e
ye
d
is
ea
s
es a
n
d
med
ica
l d
a
ta
cla
s
s
ifica
tio
n
(
R
a
ed
A
la
z
a
id
a
h
)
1425
T
ab
le
2
.
T
h
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
f
ir
s
t d
ataset
D
a
t
a
se
t
1
:
d
i
a
b
e
t
e
s
_
d
a
t
a
L
e
a
r
n
i
n
g
st
r
a
t
e
g
y
C
l
a
ssi
f
i
e
r
A
c
c
u
r
a
c
y
F
P
r
a
t
e
P
r
e
c
i
si
o
n
R
e
c
a
l
l
F
u
n
c
t
i
o
n
s
L
o
g
i
st
i
c
0
.
7
7
2
0
.
3
2
1
0
.
7
6
7
0
.
7
7
2
S
G
D
0
.
7
8
0
0
.
3
2
1
0
.
7
7
6
0
.
7
8
0
M
u
l
t
i
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
0
.
7
5
4
0
.
3
1
4
0
.
7
5
0
0
.
7
5
4
S
i
mp
l
e
l
i
n
e
a
r
p
e
r
c
e
p
t
r
o
n
0
.
7
7
5
0
.
3
2
5
0
.
7
7
0
0
.
7
7
5
S
M
O
r
e
g
0
.
7
7
3
0
.
3
3
4
0
.
7
6
9
0
.
7
7
3
A
v
e
r
a
g
e
0
.
7
7
1
0
.
3
2
3
0
.
7
6
6
0
.
7
7
1
M
e
t
a
A
t
t
r
i
b
u
t
e
se
l
e
c
t
e
d
c
l
a
ssi
f
i
e
r
0
.
7
5
0
0
.
3
4
9
0
.
7
4
3
0
.
7
5
0
R
a
n
d
o
m
c
o
mm
i
t
t
e
e
0
.
7
4
0
0
.
3
4
7
0
.
7
3
3
0
.
7
4
0
R
a
n
d
o
m
s
u
b
s
p
a
c
e
0
.
7
4
6
0
.
3
8
4
0
.
7
4
0
0
.
7
4
6
L
o
g
i
t
b
o
o
st
0
.
7
2
8
0
.
3
4
5
0
.
7
3
1
0
.
7
2
8
M
u
l
t
i
c
l
a
ss
c
l
a
ss
i
f
i
e
r
0
.
7
0
9
0
.
4
2
5
0
.
6
9
7
0
.
7
0
9
F
i
l
t
e
r
e
d
c
l
a
ssi
f
i
e
r
0
.
7
7
4
0
.
4
3
3
0
.
7
7
9
0
.
7
7
4
V
o
t
e
0
.
7
4
1
0
.
3
5
0
0
.
7
3
4
0
.
7
4
1
A
v
e
r
a
g
e
0
.
7
4
1
0
.
3
7
6
0
.
7
3
7
0
.
7
4
1
R
u
l
e
s
D
e
c
i
si
o
n
t
a
b
l
e
0
.
7
1
2
0
.
3
7
2
0
.
7
0
6
0
.
7
1
2
Jr
i
p
0
.
7
6
0
0
.
3
2
2
0
.
7
5
5
0
.
7
6
0
P
a
r
t
0
.
7
5
3
0
.
3
2
7
0
.
7
4
7
0
.
7
5
3
A
v
e
r
a
g
e
0
.
7
4
2
0
.
3
4
0
0
.
7
3
6
0
.
7
4
2
T
r
e
e
s
l
o
g
i
st
i
c
mo
d
e
l
t
r
e
e
s (
L
M
T
)
0
.
7
7
5
0
.
3
2
5
0
.
7
7
0
0
.
7
7
5
R
a
n
d
o
m
f
o
r
e
st
0
.
7
5
8
0
.
3
1
0
0
.
7
5
4
0
.
7
5
8
R
a
n
d
o
m
t
r
e
e
0
.
6
8
1
0
.
3
7
5
0
.
6
8
4
0
.
6
8
1
R
e
d
u
c
e
d
e
r
r
o
r
p
r
u
n
i
n
g
(
R
EP)
t
r
e
e
0
.
7
5
3
0
.
3
2
8
0
.
7
4
7
0
.
7
5
3
A
v
e
r
a
g
e
0
.
7
4
2
0
.
3
3
5
0
.
7
3
9
0
.
7
4
2
M
i
n
0
.
6
8
1
0
.
3
1
0
0
.
6
8
4
0
.
6
8
1
M
a
x
0
.
7
8
0
0
.
4
3
3
0
.
7
7
9
0
.
7
8
0
T
ab
le
3
.
P
er
f
o
r
m
a
n
ce
o
f
t
h
e
s
e
co
n
d
d
ataset
D
a
t
a
se
t
2
:
g
l
a
u
c
o
ma
L
e
a
r
n
i
n
g
st
r
a
t
e
g
y
C
l
a
ssi
f
i
e
r
A
c
c
u
r
a
c
y
F
P
r
a
t
e
P
r
e
c
i
si
o
n
R
e
c
a
l
l
F
u
n
c
t
i
o
n
s
L
o
g
i
st
i
c
0
.
8
9
6
0
.
0
7
7
0
.
8
9
5
0
.
8
9
6
S
G
D
0
.
9
1
7
0
.
0
5
9
0
.
9
1
7
0
.
9
1
7
M
u
l
t
i
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
0
.
9
1
6
0
.
0
5
8
0
.
9
1
6
0
.
9
1
6
S
i
mp
l
e
l
i
n
e
a
r
p
e
r
c
e
p
t
r
o
n
0
.
9
1
2
0
.
0
5
0
0
.
9
1
4
0
.
9
1
4
S
M
O
r
e
g
0
.
9
1
3
0
.
0
6
0
0
.
9
1
5
0
.
9
1
5
A
v
e
r
a
g
e
0
.
7
7
1
0
.
9
1
1
0
.
0
6
1
0
.
9
1
1
M
e
t
a
A
t
t
r
i
b
u
t
e
se
l
e
c
t
e
d
c
l
a
ssi
f
i
e
r
0
.
8
9
0
0
.
0
7
8
0
.
8
8
9
0
.
8
9
0
R
a
n
d
o
m
c
o
mm
i
t
t
e
e
0
.
9
1
4
0
.
0
6
9
0
.
9
1
4
0
.
9
1
4
R
a
n
d
o
m
s
u
b
s
p
a
c
e
0
.
9
0
6
0
.
0
7
1
0
.
9
0
5
0
.
9
0
6
L
o
g
i
t
b
o
o
st
0
.
9
1
2
0
.
0
6
0
0
.
9
1
1
0
.
9
1
2
M
u
l
t
i
c
l
a
ss
c
l
a
ss
i
f
i
e
r
0
.
9
0
4
0
.
0
6
8
0
.
9
0
4
0
.
9
0
4
F
i
l
t
e
r
e
d
c
l
a
ssi
f
i
e
r
0
.
8
9
3
0
.
0
7
7
0
.
8
9
2
0
.
8
9
3
V
o
t
e
0
.
8
6
1
0
.
1
1
6
0
.
8
6
2
0
.
8
6
1
A
v
e
r
a
g
e
0
.
7
4
1
0
.
8
9
7
0
.
0
7
7
0
.
8
9
7
R
u
l
e
s
D
e
c
i
si
o
n
t
a
b
l
e
0
.
8
8
0
0
.
1
2
1
0
.
8
8
0
0
.
8
8
0
Jr
i
p
0
.
8
9
8
0
.
0
6
7
0
.
8
9
8
0
.
8
9
8
P
a
r
t
0
.
8
8
8
0
.
0
8
2
0
.
8
8
7
0
.
8
8
8
A
v
e
r
a
g
e
0
.
7
4
2
0
.
8
8
9
0
.
0
9
0
0
.
8
8
8
T
r
e
e
s
L
M
T
0
.
9
1
4
0
.
0
5
9
0
.
9
1
4
0
.
9
1
4
R
a
n
d
o
m
f
o
r
e
st
0
.
9
1
2
0
.
0
6
6
0
.
9
1
2
0
.
9
1
2
R
a
n
d
o
m
t
r
e
e
0
.
9
0
6
0
.
0
7
4
0
.
9
0
6
0
.
9
0
6
R
EP
t
r
e
e
0
.
9
0
9
0
.
0
6
4
0
.
9
0
8
0
.
9
0
9
A
v
e
r
a
g
e
0
.
7
4
2
0
.
8
9
6
0
.
0
7
7
0
.
8
9
5
M
i
n
0
.
6
8
1
0
.
9
1
7
0
.
0
5
9
0
.
9
1
7
M
a
x
0
.
7
8
0
0
.
9
1
6
0
.
0
5
8
0
.
9
1
6
3
.
3
.
T
o
det
er
m
i
ne
t
he
m
o
s
t
s
uita
ble f
ea
t
ure
s
elec
t
io
n
m
et
ho
d f
o
r
us
e
T
h
is
s
ec
tio
n
ad
d
r
ess
es
t
h
e
t
h
ir
d
r
esear
ch
o
b
j
ec
tiv
e:
d
eter
m
in
in
g
t
h
e
m
o
s
t
ap
p
r
o
p
r
iat
e
f
ea
tu
r
e
s
elec
tio
n
m
e
th
o
d
f
o
r
u
s
e
w
i
t
h
m
ed
ical
d
atasets
.
T
h
er
ef
o
r
e,
t
w
o
d
if
f
er
en
t
d
atasets
ar
e
co
n
s
id
er
ed
in
th
is
s
ec
tio
n
.
T
ab
le
4
s
h
o
w
s
th
e
r
es
u
lts
o
f
th
e
b
est
clas
s
i
f
ier
an
d
th
e
b
est
lear
n
i
n
g
s
tr
ateg
y
f
o
r
d
ataset
1
,
ac
co
r
d
in
g
to
th
e
f
ir
s
t
f
ea
t
u
r
e
s
elec
tio
n
,
C
lass
i
f
ier
A
ttrib
u
teE
v
al,
th
e
r
esu
lts
w
er
e
t
h
e
b
est
c
las
s
i
f
ier
SG
D
lear
n
i
n
g
s
tr
ate
g
y
f
u
n
ctio
n
s
a
n
d
m
eta
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
22
,
No
.
6
,
Dec
em
b
er
20
24
:
1
4
2
2
-
1430
1426
T
ab
le
4
.
T
h
e
f
ir
s
t f
ea
t
u
r
e
s
elec
tio
n
in
t
h
e
f
ir
s
t d
ataset
D
a
t
a
se
t
1
:
d
i
a
b
e
t
e
s_
d
a
t
a
/
c
l
a
ssi
f
i
e
r
a
t
t
r
i
b
u
t
e
e
v
a
l
L
e
a
r
n
i
n
g
st
r
a
t
e
g
y
C
l
a
ssi
f
i
e
r
A
c
c
u
r
a
c
y
F
P
r
a
t
e
P
r
e
c
i
si
o
n
R
e
c
a
l
l
F
u
n
c
t
i
o
n
s
L
o
g
i
st
i
c
0
.
7
5
3
0
.
3
6
1
0
.
7
4
6
0
.
7
5
3
S
G
D
0
.
7
5
3
0
.
3
7
0
0
.
7
4
7
0
.
7
5
3
M
u
l
t
i
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
0
.
7
6
4
0
.
3
1
5
0
.
7
5
9
0
.
7
6
4
S
i
mp
l
e
l
i
n
e
a
r
p
e
r
c
e
p
t
r
o
n
0
.
7
5
3
0
.
3
6
6
0
.
7
4
6
0
.
7
5
3
S
M
O
r
e
g
0
.
7
5
9
0
.
3
6
6
0
.
7
5
5
0
.
7
5
9
A
v
e
r
a
g
e
0
.
7
5
6
0
.
3
5
6
0
.
7
5
1
0
.
7
5
6
M
e
t
a
A
t
t
r
i
b
u
t
e
se
l
e
c
t
e
d
c
l
a
ssi
f
i
e
r
0
.
7
1
5
0
.
4
1
1
0
.
7
0
3
0
.
7
1
5
R
a
n
d
o
m
c
o
mm
i
t
t
e
e
0
.
7
0
1
0
.
3
8
9
0
.
6
9
3
0
.
7
0
1
R
a
n
d
o
m
s
u
b
s
p
a
c
e
0
.
7
3
3
0
.
4
5
0
0
.
7
4
0
0
.
7
3
3
L
o
g
i
t
b
o
o
st
0
.
7
4
2
0
.
3
5
8
0
.
7
3
4
0
.
7
4
2
M
u
l
t
i
c
l
a
ss
c
l
a
ssi
f
i
e
r
0
.
7
5
3
0
.
3
7
0
0
.
7
4
7
0
.
7
5
3
F
i
l
t
e
r
e
d
c
l
a
ssi
f
i
e
r
0
.
7
3
8
0
.
3
7
1
0
.
7
3
0
0
.
7
3
8
V
o
t
e
0
.
7
3
4
0
.
3
5
9
0
.
7
2
7
0
.
7
3
4
A
v
e
r
a
g
e
0
.
7
3
1
0
.
3
8
7
0
.
7
2
5
0
.
7
3
1
R
u
l
e
s
D
e
c
i
si
o
n
t
a
b
l
e
0
.
7
4
3
0
.
3
6
6
0
.
7
3
6
0
.
7
4
3
Jr
i
p
0
.
7
5
7
0
.
3
5
4
0
.
7
5
0
0
.
7
5
7
P
a
r
t
0
.
7
1
5
0
.
4
1
6
0
.
7
0
3
0
.
7
1
5
A
v
e
r
a
g
e
0
.
7
3
8
0
.
3
7
9
0
.
7
3
0
0
.
7
3
8
T
r
e
e
s
L
M
T
0
.
7
5
3
0
.
3
6
6
0
.
7
4
6
0
.
7
5
3
R
a
n
d
o
m
f
o
r
e
st
0
.
7
3
8
0
.
3
4
5
0
.
7
3
2
0
.
7
3
8
R
a
n
d
o
m
t
r
e
e
0
.
6
8
0
0
.
3
9
0
0
.
6
7
8
0
.
6
8
0
R
EP
t
r
e
e
0
.
7
2
1
0
.
3
7
4
0
.
7
1
3
0
.
7
2
1
A
v
e
r
a
g
e
0
.
7
2
3
0
.
3
6
9
0
.
7
1
7
0
.
7
2
3
M
i
n
0
.
6
8
0
0
.
3
1
5
0
.
6
7
8
0
.
6
8
0
M
a
x
0
.
7
6
4
0
.
4
5
0
0
.
7
5
9
0
.
7
6
4
T
ab
le
5
s
h
o
w
s
th
e
r
es
u
lts
o
f
t
h
e
b
est
class
i
f
ier
an
d
th
e
b
est
lear
n
in
g
s
tr
ate
g
y
f
o
r
d
ataset
1
,
ac
co
r
d
in
g
to
th
e
f
ir
s
t
f
ea
t
u
r
e
s
elec
tio
n
,
C
o
r
r
elatio
n
A
ttrib
u
teE
v
al,
t
h
e
r
esu
lt
s
w
er
e
t
h
e
b
est
cla
s
s
i
f
ie
r
SGD
an
d
lo
g
is
t
ic
an
d
Mu
lti
C
las
s
C
lass
if
ier
lear
n
in
g
s
tr
ateg
y
f
u
n
ctio
n
s
an
d
m
e
t
a.
T
ab
le
6
s
h
o
w
s
th
e
r
es
u
lt
s
o
f
th
e
b
est
class
i
f
ier
an
d
th
e
b
est
lear
n
i
n
g
s
tr
ate
g
y
f
o
r
d
ataset
2
,
ac
co
r
d
in
g
to
th
e
f
ir
s
t
f
ea
t
u
r
e
s
elec
tio
n
,
C
la
s
s
if
ier
A
ttrib
u
teE
v
al
,
th
e
r
esu
lts
w
er
e
th
e
b
est
cla
s
s
i
f
ier
Mu
lt
ila
y
er
P
er
ce
p
tr
o
n
lear
n
in
g
s
tr
ate
g
y
f
u
n
c
tio
n
s
.
T
ab
le
7
s
h
o
w
s
th
e
r
es
u
lt
s
o
f
th
e
b
est
cla
s
s
i
f
ier
a
n
d
th
e
b
est
lear
n
in
g
s
tr
ateg
y
f
o
r
d
ataset
2
,
ac
co
r
d
in
g
to
th
e
f
ir
s
t
f
ea
tu
r
e
s
elec
tio
n
,
C
las
s
i
f
ier
A
ttrib
u
teE
v
al,
t
h
e
r
esu
lt
s
w
er
e
th
e
b
est
cla
s
s
i
f
ier
Mu
ltil
a
y
er
P
er
ce
p
tr
o
n
lear
n
in
g
s
tr
ateg
y
f
u
n
ctio
n
s
.
T
ab
le
5
.
T
h
e
s
ec
o
n
d
f
ea
tu
r
e
s
e
lectio
n
in
t
h
e
f
ir
s
t d
ataset
D
a
t
a
se
t
1
:
d
i
a
b
e
t
e
s
d
a
t
a
/
c
o
r
r
e
l
a
t
i
o
n
a
t
t
r
i
b
u
t
e
e
v
a
l
L
e
a
r
n
i
n
g
s
t
r
a
t
e
g
y
C
l
a
ssi
f
i
e
r
A
c
c
u
r
a
c
y
F
P
r
a
t
e
P
r
e
c
i
si
o
n
R
e
c
a
l
l
F
u
n
c
t
i
o
n
s
L
o
g
i
st
i
c
0
.
7
6
7
0
.
3
2
7
0
.
7
6
1
0
.
7
6
7
S
G
D
0
.
7
6
7
0
.
3
3
6
0
.
7
6
1
0
.
7
6
7
M
u
l
t
i
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
0
.
7
6
3
0
.
3
1
6
0
.
7
5
8
0
.
7
6
3
S
i
mp
l
e
l
i
n
e
a
r
p
e
r
c
e
p
t
r
o
n
0
.
7
5
5
0
.
3
5
1
0
.
7
4
9
0
.
7
5
5
S
M
O
r
e
g
0
.
7
6
0
0
.
3
4
7
0
.
7
5
4
0
.
7
6
0
A
v
e
r
a
g
e
0
.
7
6
3
0
.
3
3
5
0
.
7
5
7
0
.
7
6
2
M
e
t
a
A
t
t
r
i
b
u
t
e
se
l
e
c
t
e
d
c
l
a
ssi
f
i
e
r
0
.
7
4
6
0
.
3
3
3
0
.
7
4
0
0
.
7
4
6
R
a
n
d
o
m
c
o
mm
i
t
t
e
e
0
.
7
0
6
0
.
3
6
5
0
.
7
0
2
0
.
7
0
6
R
a
n
d
o
m
s
u
b
s
p
a
c
e
0
.
7
4
6
0
.
3
8
5
0
.
7
4
0
0
.
7
4
6
L
o
g
i
t
b
o
o
st
0
.
7
5
8
0
.
3
2
9
0
.
7
5
2
0
.
7
5
8
M
u
l
t
i
c
l
a
ss
c
l
a
ssi
f
i
e
r
0
.
7
6
7
0
.
3
2
7
0
.
7
6
1
0
.
7
6
7
F
i
l
t
e
r
e
d
c
l
a
ssi
f
i
e
r
0
.
7
6
0
0
.
3
3
8
0
.
7
5
4
0
.
7
6
0
V
o
t
e
0
.
7
4
0
0
.
3
6
5
0
.
7
3
1
0
.
7
4
0
A
v
e
r
a
g
e
0
.
7
4
6
0
.
3
4
9
0
.
7
4
0
0
.
7
4
6
R
u
l
e
s
D
e
c
i
si
o
n
t
a
b
l
e
0
.
7
2
4
0
.
3
4
9
0
.
7
2
0
0
.
7
2
4
Jr
i
p
0
.
7
5
8
0
.
3
2
9
0
.
7
5
2
0
.
7
5
8
P
a
r
t
0
.
7
1
5
0
.
4
1
6
0
.
7
0
3
0
.
7
1
5
A
v
e
r
a
g
e
0
.
7
3
2
0
.
3
6
5
0
.
7
2
5
0
.
7
3
2
T
r
e
e
s
L
M
T
0
.
7
5
5
0
.
3
5
1
0
.
7
4
9
0
.
7
5
5
R
a
n
d
o
m
f
o
r
e
st
0
.
7
4
1
0
.
3
2
9
0
.
7
3
7
0
.
7
4
1
R
a
n
d
o
m
t
r
e
e
0
.
6
9
0
0
.
3
8
6
0
.
6
8
6
0
.
6
9
0
R
EP
t
r
e
e
0
.
7
2
5
0
.
3
6
2
0
.
7
1
8
0
.
7
2
5
A
v
e
r
a
g
e
0
.
7
2
8
0
.
3
5
7
0
.
7
2
3
0
.
7
2
8
M
in
0
.
6
9
0
0
.
3
1
6
0
.
6
8
6
0
.
6
9
0
M
ax
0
.
7
6
7
0
.
4
1
6
0
.
7
6
1
0
.
7
6
7
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
A
co
mp
r
eh
en
s
ive
a
n
a
lysi
s
o
f e
ye
d
is
ea
s
es a
n
d
med
ica
l d
a
ta
cla
s
s
ifica
tio
n
(
R
a
ed
A
la
z
a
id
a
h
)
1427
T
ab
le
6
.
T
h
e
f
ir
s
t f
ea
t
u
r
e
s
elec
tio
n
in
t
h
e
s
ec
o
n
d
d
ataset
D
a
t
a
se
t
2
:
g
l
a
u
c
o
ma/
c
l
a
ssi
f
i
e
r
a
t
t
r
i
b
u
t
e
e
v
a
l
L
e
a
r
n
i
n
g
st
r
a
t
e
g
y
C
l
a
ssi
f
i
e
r
A
c
c
u
r
a
c
y
F
P
r
a
t
e
P
r
e
c
i
si
o
n
R
e
c
a
l
l
F
u
n
c
t
i
o
n
s
L
o
g
i
st
i
c
0
.
8
9
0
0
.
0
7
5
0
.
8
9
1
0
.
8
9
0
S
G
D
0
.
7
5
1
0
.
3
6
9
0
.
7
4
5
0
.
7
5
1
M
u
l
t
i
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
0
.
9
0
6
0
.
0
6
8
0
.
9
0
6
0
.
9
0
6
S
i
mp
l
e
l
i
n
e
a
r
p
e
r
c
e
p
t
r
o
n
0
.
9
0
4
0
.
0
6
8
0
.
9
0
4
0
.
9
0
4
S
M
O
r
e
g
0
.
8
7
7
0
.
0
7
5
0
.
8
8
0
0
.
8
7
7
A
v
e
r
a
g
e
0
.
8
6
6
0
.
1
3
1
0
.
8
6
5
0
.
8
6
6
M
e
t
a
A
t
t
r
i
b
u
t
e
se
l
e
c
t
e
d
c
l
a
ssi
f
i
e
r
0
.
7
2
5
0
.
3
5
2
0
.
8
3
6
0
.
7
2
5
R
a
n
d
o
m
c
o
mm
i
t
t
e
e
0
.
8
9
3
0
.
0
8
3
0
.
8
9
2
0
.
8
9
3
R
a
n
d
o
m
s
u
b
s
p
a
c
e
0
.
8
9
6
0
.
0
7
7
0
.
8
9
5
0
.
8
9
6
L
o
g
i
t
b
o
o
st
0
.
9
0
1
0
.
0
7
2
0
.
9
0
1
0
.
9
0
1
M
e
t
a
l
M
u
l
t
i
c
l
a
ss
c
l
a
ss
i
f
i
e
r
0
.
8
9
6
0
.
0
7
3
0
.
8
9
6
0
.
8
9
6
F
i
l
t
e
r
e
d
c
l
a
ssi
f
i
e
r
0
.
8
9
0
0
.
0
7
5
0
.
8
9
1
0
.
8
9
0
V
o
t
e
0
.
7
2
5
0
.
3
5
2
0
.
8
3
6
0
.
7
2
5
A
v
e
r
a
g
e
0
.
8
4
6
0
.
1
5
5
0
.
8
7
8
0
.
8
4
7
R
u
l
e
s
D
e
c
i
si
o
n
t
a
b
l
e
0
.
8
7
7
0
.
1
1
5
0
.
8
7
6
0
.
8
7
7
Jr
i
p
0
.
8
9
3
0
.
0
7
7
0
.
8
9
3
0
.
8
9
3
P
a
r
t
0
.
8
9
6
0
.
0
7
7
0
.
8
9
7
0
.
8
9
6
A
v
e
r
a
g
e
0
.
8
8
9
0
.
0
9
0
0
.
8
8
9
0
.
8
8
9
T
r
e
e
s
L
M
T
0
.
9
0
4
0
.
0
6
8
0
.
9
0
4
0
.
9
0
4
R
a
n
d
o
m
f
o
r
e
st
0
.
8
9
3
0
.
0
8
3
0
.
8
9
2
0
.
8
9
3
R
a
n
d
o
m
t
r
e
e
0
.
8
9
3
0
.
0
8
3
0
.
8
9
2
0
.
8
9
3
R
EP T
r
e
e
0
.
8
6
1
0
.
1
2
9
0
.
8
6
2
0
.
8
6
1
A
v
e
r
a
g
e
0
.
8
8
8
0
.
0
9
1
0
.
8
8
8
0
.
8
8
8
M
i
n
0
.
7
2
5
0
.
0
6
8
0
.
7
4
5
0
.
7
2
5
M
a
x
0
.
9
0
6
0
.
3
6
9
0
.
9
0
6
0
.
9
0
6
T
ab
le
7
.
T
h
e
s
ec
o
n
d
f
ea
tu
r
e
s
e
lectio
n
in
t
h
e
s
ec
o
n
d
d
ataset
D
a
t
a
se
t
2
:
g
l
a
u
c
o
ma/
c
o
r
r
e
l
a
t
i
o
n
a
t
t
r
i
b
u
t
e
e
v
a
l
L
e
a
r
n
i
n
g
st
r
a
t
e
g
y
C
l
a
ssi
f
i
e
r
A
c
c
u
r
a
c
y
F
P
r
a
t
e
P
r
e
c
i
si
o
n
R
e
c
a
l
l
F
u
n
c
t
i
o
n
s
L
o
g
i
st
i
c
0
.
8
9
0
0
.
0
7
5
0
.
8
9
1
0
.
9
0
6
S
G
D
0
.
7
5
1
0
.
3
6
9
0
.
7
4
5
0
.
7
5
1
M
u
l
t
i
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
0
.
9
0
6
0
.
0
6
8
0
.
9
0
6
0
.
9
0
6
S
i
mp
l
e
l
i
n
e
a
r
p
e
r
c
e
p
t
r
o
n
0
.
9
0
4
0
.
0
6
8
0
.
9
0
4
0
.
9
0
6
S
M
O
r
e
g
0
.
8
7
7
0
.
0
7
5
0
.
8
8
0
0
.
9
0
6
A
v
e
r
a
g
e
0
.
8
6
6
0
.
1
3
1
0
.
8
6
5
0
.
8
7
5
M
e
t
a
A
t
t
r
i
b
u
t
e
se
l
e
c
t
e
d
c
l
a
ssi
f
i
e
r
0
.
7
2
5
0
.
3
5
2
0
.
8
3
6
0
.
8
9
0
R
a
n
d
o
m
c
o
mm
i
t
t
e
e
0
.
8
9
3
0
.
0
8
3
0
.
8
9
2
0
.
9
0
6
R
a
n
d
o
m
s
u
b
s
p
a
c
e
0
.
8
9
6
0
.
0
7
7
0
.
8
9
5
0
.
9
0
4
L
o
g
i
t
b
o
o
st
0
.
9
0
1
0
.
0
7
2
0
.
9
0
1
0
.
9
0
9
M
u
l
t
i
c
l
a
ss
c
l
a
ss
i
f
i
e
r
0
.
8
9
6
0
.
0
7
3
0
.
8
9
6
0
.
9
0
9
F
i
l
t
e
r
e
d
c
l
a
ssi
f
i
e
r
0
.
8
6
6
0
.
1
0
3
0
.
8
6
6
0
.
9
0
4
V
o
t
e
0
.
7
2
5
0
.
3
5
2
0
.
8
3
6
0
.
8
3
2
A
v
e
r
a
g
e
0
.
8
4
3
0
.
1
5
9
0
.
8
7
5
0
.
8
9
3
R
u
l
e
s
D
e
c
i
si
o
n
t
a
b
l
e
0
.
8
7
7
0
.
1
1
5
0
.
8
7
6
0
.
8
6
4
Jr
i
p
0
.
8
9
3
0
.
0
7
7
0
.
8
9
3
0
.
8
9
3
P
a
r
t
0
.
8
9
6
0
.
0
7
7
0
.
8
9
7
0
.
8
1
3
A
v
e
r
a
g
e
0
.
8
8
9
0
.
0
9
0
0
.
8
8
9
0
.
8
5
7
T
r
e
e
s
L
M
T
0
.
9
0
4
0
.
0
6
8
0
.
9
0
4
0
.
9
0
4
R
a
n
d
o
m
f
o
r
e
st
0
.
8
9
3
0
.
0
8
3
0
.
8
9
2
0
.
9
0
6
R
a
n
d
o
m
t
r
e
e
0
.
8
9
3
0
.
0
8
3
0
.
8
9
2
0
.
8
9
0
R
EP
t
r
e
e
0
.
8
6
1
0
.
1
2
9
0
.
8
6
2
0
.
9
0
4
A
v
e
r
a
g
e
0
.
8
8
8
0
.
0
9
1
0
.
8
8
8
0
.
9
0
1
M
i
n
0
.
7
2
5
0
.
0
6
8
0
.
7
4
5
0
.
7
5
1
M
a
x
0
.
9
0
6
0
.
3
6
9
0
.
9
0
6
0
.
9
0
9
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
s
ec
tio
n
p
r
esen
t
s
t
h
e
r
es
u
l
ts
o
f
th
e
th
r
ee
r
esear
c
h
o
b
j
ec
tiv
es:
w
h
at
is
th
e
b
es
t
clas
s
i
f
ica
tio
n
,
w
h
at
is
t
h
e
b
est
s
tr
ateg
y
,
an
d
w
h
a
t
is
t
h
e
b
est
f
ea
t
u
r
e
s
elec
tio
n
,
T
a
b
le
8
s
h
o
w
s
t
h
e
b
est
cla
s
s
i
f
icatio
n
,
T
ab
le
9
s
h
o
w
s
t
h
e
b
est
s
tr
ate
g
y
,
an
d
T
ab
le
1
0
s
h
o
w
s
th
e
b
est
clas
s
if
ier
i
n
h
al
f
o
f
d
ata.
T
h
r
ee
m
ai
n
o
b
j
ec
tiv
es
ar
e
ad
d
r
ess
ed
in
th
i
s
p
ap
er
.
Dete
r
m
i
n
e
th
e
b
es
t
clas
s
i
f
ier
ca
p
ab
le
o
f
d
ea
lin
g
w
it
h
m
ed
ical
d
ata
s
ets.
I
n
d
atase
t
1
,
SGD
w
a
s
t
h
e
b
est
cla
s
s
i
f
ier
ac
co
r
d
in
g
to
t
h
e
f
o
u
r
cr
iter
ia.
I
n
d
ataset
2
it
w
a
s
also
SGD.
D
eter
m
i
n
in
g
t
h
e
b
es
t
s
tr
ateg
y
w
as
f
u
n
ctio
n
al
it
y
,
t
h
e
n
r
u
le
s
.
C
o
r
r
elatio
n
Attr
ib
u
teE
v
al
is
th
e
b
es
t
ch
o
ice
f
o
r
s
tr
at
eg
y
test
i
n
g
f
ea
tu
r
e
an
d
in
ter
m
s
o
f
cla
s
s
i
f
ier
test
i
n
g
it
w
a
s
C
lass
if
ier
Attr
ib
u
teE
v
al
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
22
,
No
.
6
,
Dec
em
b
er
20
24
:
1
4
2
2
-
1430
1428
T
ab
le
8
.
T
est
class
if
ier
A
l
l
d
a
t
a
D
a
t
a
se
t
1
D
a
t
a
se
t
2
A
c
c
u
r
a
c
y
S
G
D
S
G
D
F
P
r
a
t
e
R
a
n
d
o
m
f
o
r
e
st
S
G
D
,
L
M
T
P
r
e
c
i
si
o
n
F
i
l
t
e
r
e
d
c
l
a
ssi
f
i
e
r
S
G
D
R
e
c
a
l
S
G
D
S
G
D
T
ab
le
9
.
B
est cla
s
s
i
f
ier
C
l
a
ssi
f
i
e
r
A
t
t
r
i
b
u
t
e
Ev
a
l
H
a
l
f
o
f
t
h
e
d
a
t
a
D
a
t
a
se
t
1
D
a
t
a
se
t
2
C
l
a
ssi
f
i
e
r
M
u
l
t
i
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
M
u
l
t
i
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
C
o
r
r
e
l
a
t
i
o
n
A
t
t
r
i
b
u
t
e
Ev
a
l
D
a
t
a
se
t
1
D
a
t
a
se
t
2
C
l
a
ssi
f
i
e
r
L
o
g
i
st
i
c
,
S
G
D
,
M
u
l
t
i
C
l
a
ssCl
a
ss
i
f
i
e
r
M
u
l
t
i
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
G
a
i
n
A
t
t
r
i
b
u
t
e
Ev
a
l
D
a
t
a
se
t
1
D
a
t
a
se
t
2
C
l
a
ssi
f
i
e
r
L
o
g
i
st
i
c
,
S
G
D
,
M
u
l
t
i
C
l
a
ssCl
a
ss
i
f
i
e
r
M
u
l
t
i
C
l
a
ss
C
l
a
ssi
f
i
e
r
,
l
o
g
i
t
b
o
o
st
I
n
f
o
G
a
i
n
A
t
t
r
i
b
u
t
e
Ev
a
l
D
a
t
a
se
t
1
D
a
t
a
se
t
2
C
l
a
ssi
f
i
e
r
M
u
l
t
i
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
L
o
g
i
st
i
c
T
ab
le
1
0
.
B
est s
tr
ateg
y
C
l
a
ssi
f
i
e
r
A
t
t
r
i
b
u
t
e
Ev
a
l
H
a
l
f
o
f
t
h
e
d
a
t
a
D
a
t
a
se
t
1
D
a
t
a
se
t
2
S
t
r
a
t
e
g
y
F
u
n
c
t
i
o
n
s
R
u
l
e
s
C
o
r
r
e
l
a
t
i
o
n
A
t
t
r
i
b
u
t
e
Ev
a
l
D
a
t
a
se
t
1
D
a
t
a
se
t
2
S
t
r
a
t
e
g
y
F
u
n
c
t
i
o
n
s
R
u
l
e
s
G
a
i
n
A
t
t
r
i
b
u
t
e
Ev
a
l
D
a
t
a
se
t
1
D
a
t
a
se
t
2
S
t
r
a
t
e
g
y
F
u
n
c
t
i
o
n
s
T
r
e
e
s
I
n
f
o
G
a
i
n
A
t
t
r
i
b
u
t
e
Ev
a
l
D
a
t
a
se
t
1
D
a
t
a
se
t
2
S
t
r
a
t
e
g
y
F
u
n
c
t
i
o
n
s
T
r
e
e
s
5.
CO
NCLU
SI
O
N
Vis
io
n
lo
s
s
is
a
cr
u
cial
h
e
alth
i
s
s
u
e
t
h
at
p
r
ese
n
ts
co
n
s
id
er
ab
le
o
b
s
tacle
s
to
i
n
d
iv
i
d
u
als
a
n
d
co
m
m
u
n
itie
s
.
I
n
th
is
p
ap
er
,
th
r
ee
o
b
j
ec
tiv
es
ar
e
d
is
cu
s
s
ed
.
T
h
e
f
ir
s
t
is
to
id
en
tify
th
e
b
est
class
if
ier
,
th
e
s
ec
o
n
d
is
to
id
en
ti
f
y
t
h
e
b
est
s
tr
ateg
ie
s
,
an
d
th
e
t
h
ir
d
is
t
h
e
m
et
h
o
d
o
f
s
elec
ti
n
g
f
ea
t
u
r
e
d
atasets
an
d
th
u
s
i
m
p
r
o
v
i
n
g
p
er
f
o
r
m
a
n
ce
.
R
eg
a
r
d
in
g
th
e
f
ir
s
t
o
b
j
ec
tiv
e,
tw
o
class
i
f
ier
s
s
h
o
w
ed
th
e
b
est
r
esu
lts
:
SGD.
L
o
o
k
i
n
g
at
th
e
s
ec
o
n
d
o
b
j
ec
tiv
e,
it t
u
r
n
ed
o
u
t th
a
t t
h
e
b
est
s
tr
ateg
y
was j
o
b
s
,
f
o
llo
w
ed
b
y
r
u
le
s
.
T
h
e
r
esu
lt
s
o
f
th
e
th
ir
d
o
b
j
ec
tiv
e
also
s
h
o
w
ed
th
at
t
h
e
C
o
r
r
elatio
n
A
ttrib
u
teE
v
al
a
n
d
C
lass
i
f
ier
A
t
tr
ib
u
teE
v
a
l
m
e
t
h
o
d
s
ar
e
th
e
b
est.
P
er
f
o
r
m
a
n
ce
,
d
ev
elo
p
m
e
n
t
o
f
n
e
w
s
tr
ateg
ies
s
h
o
u
ld
b
e
co
n
s
id
er
ed
in
th
e
f
u
t
u
r
e,
ex
p
an
d
i
n
g
t
h
e
in
v
es
tig
a
tio
n
in
to
ad
d
itio
n
al
c
las
s
i
f
ier
s
,
an
d
i
m
p
r
o
v
i
n
g
f
ea
t
u
r
e
s
elec
tio
n
te
ch
n
iq
u
es.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
is
r
esear
ch
is
f
u
n
d
ed
b
y
th
e
Dea
n
s
h
ip
o
f
R
esear
ch
an
d
Gr
ad
u
ate
Stu
d
ie
s
in
Z
ar
q
a
Un
i
v
er
s
it
y
/J
o
r
d
an
.
RE
F
E
R
E
NC
E
S
[
1
]
G
.
T
.
R
e
d
d
y
e
t
a
l
.
,
“
A
n
e
n
se
mb
l
e
b
a
se
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
mo
d
e
l
f
o
r
d
i
a
b
e
t
i
c
r
e
t
i
n
o
p
a
t
h
y
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
i
n
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Em
e
r
g
i
n
g
T
r
e
n
d
s
i
n
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
a
n
d
E
n
g
i
n
e
e
ri
n
g
,
i
c
-
ETI
T
E
2
0
2
0
,
I
EEE,
F
e
b
.
2
0
2
0
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
i
c
-
ETI
T
E4
7
9
0
3
.
2
0
2
0
.
2
3
5
.
[
2
]
L
.
B
a
l
y
e
n
a
n
d
T
.
P
e
t
o
,
“
P
r
o
mi
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
–
mac
h
i
n
e
l
e
a
r
n
i
n
g
–
d
e
e
p
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
i
n
o
p
h
t
h
a
l
mo
l
o
g
y
,
”
Asi
a
-
Pa
c
i
f
i
c
J
o
u
r
n
a
l
o
f
O
p
h
t
h
a
l
m
o
l
o
g
y
,
v
o
l
.
8
,
n
o
.
3
,
p
p
.
2
6
4
–
2
7
2
,
2
0
1
9
,
d
o
i
:
1
0
.
2
2
6
0
8
/
A
P
O
.
2
0
1
8
4
7
9
.
[
3
]
M
.
A
l
a
m,
D
.
L
e
,
J.
I
.
L
i
m,
R
.
V
.
P
.
C
h
a
n
,
a
n
d
X
.
Y
a
o
,
“
S
u
p
e
r
v
i
se
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
b
a
se
d
m
u
l
t
i
-
t
a
s
k
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
r
e
t
i
n
o
p
a
t
h
i
e
s,”
J
o
u
r
n
a
l
o
f
C
l
i
n
i
c
a
l
Me
d
i
c
i
n
e
,
v
o
l
.
8
,
n
o
.
6
,
p
.
8
7
2
,
J
u
n
.
2
0
1
9
,
d
o
i
:
1
0
.
3
3
9
0
/
j
c
m8
0
6
0
8
7
2
.
[
4
]
M
.
A
f
i
f
,
R
.
A
y
a
c
h
i
,
Y
.
S
a
i
d
,
E.
P
i
ss
a
l
o
u
x
,
a
n
d
M
.
A
t
r
i
,
“
A
n
e
v
a
l
u
a
t
i
o
n
o
f
r
e
t
i
n
a
n
e
t
o
n
i
n
d
o
o
r
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
f
o
r
b
l
i
n
d
a
n
d
v
i
su
a
l
l
y
i
mp
a
i
r
e
d
p
e
r
so
n
s
a
ssi
s
t
a
n
c
e
n
a
v
i
g
a
t
i
o
n
,
”
N
e
u
ra
l
Pro
c
e
ss
i
n
g
L
e
t
t
e
rs
,
v
o
l
.
5
1
,
n
o
.
3
,
p
p
.
2
2
6
5
–
2
2
7
9
,
Ju
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
6
3
-
0
2
0
-
1
0
1
9
7
-
9.
[
5
]
A
.
K
.
G
a
n
g
w
a
r
a
n
d
V
.
R
a
v
i
,
“
D
i
a
b
e
t
i
c
r
e
t
i
n
o
p
a
t
h
y
d
e
t
e
c
t
i
o
n
u
s
i
n
g
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
,
”
i
n
A
d
v
a
n
c
e
s i
n
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s
a
n
d
C
o
m
p
u
t
i
n
g
,
2
0
2
1
,
p
p
.
6
7
9
–
6
8
9
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
15
-
5
7
8
8
-
0
_
6
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
A
co
mp
r
eh
en
s
ive
a
n
a
lysi
s
o
f e
ye
d
is
ea
s
es a
n
d
med
ica
l d
a
ta
cla
s
s
ifica
tio
n
(
R
a
ed
A
la
z
a
id
a
h
)
1429
[
6
]
P
.
W
a
n
g
e
t
a
l
.
,
“
Ef
f
e
c
t
o
f
a
d
e
e
p
-
l
e
a
r
n
i
n
g
c
o
mp
u
t
e
r
-
a
i
d
e
d
d
e
t
e
c
t
i
o
n
sy
st
e
m
o
n
a
d
e
n
o
ma
d
e
t
e
c
t
i
o
n
d
u
r
i
n
g
c
o
l
o
n
o
s
c
o
p
y
(
C
A
D
e
-
D
B
t
r
i
a
l
)
:
a
d
o
u
b
l
e
-
b
l
i
n
d
r
a
n
d
o
m
i
se
d
s
t
u
d
y
,
”
T
h
e
L
a
n
c
e
t
G
a
s
t
r
o
e
n
t
e
ro
l
o
g
y
a
n
d
H
e
p
a
t
o
l
o
g
y
,
v
o
l
.
5
,
n
o
.
4
,
p
p
.
3
4
3
–
3
5
1
,
A
p
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
S
2
4
6
8
-
12
5
3
(
1
9
)
3
0
4
1
1
-
X.
[
7
]
M
.
A
l
K
h
a
l
d
y
,
M
.
A
l
a
u
t
h
ma
n
,
M
.
S
.
A
l
-
S
a
n
e
a
,
a
n
d
G
.
S
a
m
a
r
a
,
"
I
mp
r
o
v
e
C
l
a
ss
P
r
e
d
i
c
t
i
o
n
B
y
B
a
l
a
n
c
i
n
g
C
l
a
ss
D
i
st
r
i
b
u
t
i
o
n
F
o
r
D
i
a
b
e
t
e
s Da
t
a
se
t
,
"
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
S
c
i
e
n
t
i
f
i
c
a
n
d
T
e
c
h
n
o
l
o
g
y
R
e
s
e
a
rc
h
,
v
o
l
.
9
,
n
o
.
4
,
2
0
2
0
.
[
8
]
N
.
S
i
k
d
e
r
,
M
.
M
a
su
d
,
A
.
K
.
B
a
i
r
a
g
i
,
A
.
S
.
M
.
A
r
i
f
,
A
.
A
l
N
a
h
i
d
,
a
n
d
H
.
A
.
A
l
h
u
my
a
n
i
,
“
S
e
v
e
r
i
t
y
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
d
i
a
b
e
t
i
c
r
e
t
i
n
o
p
a
t
h
y
u
si
n
g
a
n
e
n
se
mb
l
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
t
h
r
o
u
g
h
a
n
a
l
y
z
i
n
g
r
e
t
i
n
a
l
i
mag
e
s,”
S
y
m
m
e
t
ry
,
v
o
l
.
1
3
,
n
o
.
4
,
p
.
6
7
0
,
A
p
r
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
s
y
m1
3
0
4
0
6
7
0
.
[
9
]
A
.
Y
.
A
l
h
u
se
n
a
t
,
H
.
A
.
O
w
i
d
a
,
H
.
A
.
R
a
b
a
b
a
h
,
J.
I
.
A
l
-
N
a
b
u
l
si
,
a
n
d
S
.
A
b
u
o
w
a
i
d
a
,
"
A
S
e
c
u
r
e
d
M
u
l
t
i
-
S
t
a
g
e
s
A
u
t
h
e
n
t
i
c
a
t
i
o
n
P
r
o
t
o
c
o
l
f
o
r
I
o
T
D
e
v
i
c
e
s,"
Ma
t
h
e
m
a
t
i
c
a
l
Mo
d
e
l
l
i
n
g
o
f
E
n
g
i
n
e
e
r
i
n
g
Pro
b
l
e
m
s
,
v
o
l
.
1
0
,
n
o
.
4
,
p
p
.
1
3
5
2
-
1
3
5
8
,
d
o
i
:
1
0
.
1
8
2
8
0
/
mm
e
p
.
1
0
0
4
2
9
.
[
1
0
]
R
.
S
e
b
t
i
,
S
.
Z
r
o
u
g
,
L
.
K
a
h
l
o
u
l
,
a
n
d
S
.
B
e
n
h
a
r
z
a
l
l
a
h
,
“
A
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
t
h
e
d
i
a
b
e
t
i
c
r
e
t
i
n
o
p
a
t
h
y
d
e
t
e
c
t
i
o
n
,
”
i
n
L
e
c
t
u
r
e
N
o
t
e
s
i
n
N
e
t
w
o
rks
a
n
d
S
y
st
e
m
s
,
2
0
2
2
,
p
p
.
4
5
9
–
4
6
9
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
0
-
9
4
1
9
1
-
8
_
3
7
.
[
1
1
]
W
.
W
a
n
g
,
W
.
Z
e
n
g
,
Y
.
H
u
a
n
g
,
X
.
D
I
n
g
,
a
n
d
J.
P
a
i
sl
e
y
,
“
D
e
e
p
b
l
i
n
d
h
y
p
e
r
sp
e
c
t
r
a
l
i
mag
e
f
u
si
o
n
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
I
EEE
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
C
o
m
p
u
t
e
r V
i
s
i
o
n
,
I
EEE,
O
c
t
.
2
0
1
9
,
p
p
.
4
1
4
9
–
4
1
5
8
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
V
.
2
0
1
9
.
0
0
4
2
5
.
[
1
2
]
H
.
A
.
O
w
i
d
a
,
B
.
A
M
o
h
’
d
,
N
.
T
u
r
a
b
,
J.
A
l
-
N
a
b
u
l
si
,
a
n
d
S
.
A
b
u
o
w
a
i
d
a
,
“
T
h
e
e
v
o
l
u
t
i
o
n
a
n
d
r
e
l
i
a
b
i
l
i
t
y
o
f
mac
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
f
o
r
o
n
c
o
l
o
g
y
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
j
o
u
rn
a
l
o
f
o
n
l
i
n
e
a
n
d
b
i
o
m
e
d
i
c
a
l
e
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
9
,
n
o
.
8
,
p
p
.
1
1
0
–
1
2
9
,
Ju
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
9
9
1
/
i
j
o
e
.
v
1
9
i
0
8
.
3
9
4
3
3
.
[
1
3
]
R
.
A
l
a
z
a
i
d
a
h
,
G
.
S
a
m
a
r
a
,
M
.
A
l
j
a
i
d
i
,
M
.
H
a
j
Q
a
se
m,
A
.
A
l
sarh
a
n
,
a
n
d
M
.
A
l
sh
a
mm
a
r
i
,
“
P
o
t
e
n
t
i
a
l
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
p
r
e
d
i
c
t
i
n
g
sl
e
e
p
d
i
so
r
d
e
r
s:
a
c
o
m
p
r
e
h
e
n
si
v
e
a
n
a
l
y
si
s
o
f
r
e
g
r
e
ssi
o
n
a
n
d
c
l
a
s
si
f
i
c
a
t
i
o
n
mo
d
e
l
s,”
D
i
a
g
n
o
s
t
i
c
s
,
v
o
l
.
1
4
,
n
o
.
1
,
p
.
2
7
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
d
i
a
g
n
o
st
i
c
s
1
4
0
1
0
0
2
7
.
[
1
4
]
R
.
A
l
a
z
a
i
d
a
h
,
M
.
A
.
A
l
m
a
i
a
h
,
a
n
d
M
.
A
l
-
L
u
w
a
i
c
i
,
“
A
ss
o
c
i
a
t
i
v
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
i
n
m
u
l
t
i
-
l
a
b
e
l
c
l
a
s
s
i
f
i
c
a
t
i
o
n
:
a
n
i
n
v
e
s
t
i
g
a
t
i
v
e
s
t
u
d
y
,
”
J
o
r
d
a
n
i
a
n
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
e
r
s
a
n
d
I
n
f
o
r
m
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
7
,
n
o
.
2
,
p
p
.
1
6
6
–
1
7
9
,
2
0
2
1
,
d
o
i
:
1
0
.
5
4
5
5
/
J
J
C
I
T
.
7
1
-
1
6
1
5
2
9
7
6
3
4
.
[1
5
]
H
.
A
.
O
w
i
d
a
,
O
.
S
.
M
.
H
e
mi
e
d
,
R
.
S
.
A
l
k
h
a
w
a
l
d
e
h
,
N
.
F
.
F
.
A
l
sh
d
a
i
f
a
t
,
a
n
d
S
.
F
.
A
.
A
b
u
o
w
a
i
d
a
,
"
I
mp
r
o
v
e
d
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s
f
o
r
c
o
v
i
d
-
1
9
r
e
c
o
g
n
i
t
i
o
n
i
n
c
t
i
mag
e
s,"
J
o
u
rn
a
l
o
f
T
h
e
o
re
t
i
c
a
l
a
n
d
A
p
p
l
i
e
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
2
0
0
,
n
o
.
13
,
2
0
2
2
.
[
1
6
]
H
.
G
u
,
Y
.
W
a
n
g
,
S
.
H
o
n
g
,
a
n
d
G
.
G
u
i
,
“
B
l
i
n
d
c
h
a
n
n
e
l
i
d
e
n
t
i
f
i
c
a
t
i
o
n
a
i
d
e
d
g
e
n
e
r
a
l
i
z
e
d
a
u
t
o
mat
i
c
mo
d
u
l
a
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
b
a
se
d
o
n
d
e
e
p
l
e
a
r
n
i
n
g
,
”
I
EE
E
A
c
c
e
ss
,
v
o
l
.
7
,
p
p
.
1
1
0
7
2
2
–
1
1
0
7
2
9
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
3
4
3
5
4
.
[
1
7
]
E.
B
a
g
d
a
s
a
r
y
a
n
a
n
d
V
.
S
h
m
a
t
i
k
o
v
,
“
B
l
i
n
d
b
a
c
k
d
o
o
r
s
i
n
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
s,”
in
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
3
0
t
h
U
S
EN
I
X
S
e
c
u
r
i
t
y
S
y
m
p
o
s
i
u
m
,
p
p
.
1
5
0
5
–
1
5
2
1
,
2
0
2
1
,
d
o
i
:
1
0
.
4
8
5
5
0
/
a
r
X
i
v
.
2
0
0
5
.
0
3
8
2
3
.
[
1
8
]
X
.
L
i
,
B
.
Z
h
a
n
g
,
P
.
V
.
S
a
n
d
e
r
,
a
n
d
J.
L
i
a
o
,
“
B
l
i
n
d
g
e
o
me
t
r
i
c
d
i
s
t
o
r
t
i
o
n
c
o
r
r
e
c
t
i
o
n
o
n
i
mag
e
s
t
h
r
o
u
g
h
d
e
e
p
l
e
a
r
n
i
n
g
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
I
E
EE
C
o
m
p
u
t
e
r
S
o
c
i
e
t
y
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
e
r
Vi
s
i
o
n
a
n
d
P
a
t
t
e
r
n
Re
c
o
g
n
i
t
i
o
n
,
p
p
.
4
8
5
0
–
48
5
9
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
C
V
P
R
.
2
0
1
9
.
0
0
4
9
9
.
[
1
9
]
C
.
J.
O
r
t
i
z
-
Ec
h
e
v
e
r
r
i
,
S
.
S
a
l
a
z
a
r
-
C
o
l
o
r
e
s,
J.
R
o
d
r
í
g
u
e
z
-
R
e
sé
n
d
i
z
,
a
n
d
R
.
A
.
G
ó
m
e
z
-
L
o
e
n
z
o
,
“
A
n
e
w
a
p
p
r
o
a
c
h
f
o
r
mo
t
o
r
i
mag
e
r
y
c
l
a
ssi
f
i
c
a
t
i
o
n
b
a
se
d
o
n
so
r
t
e
d
b
l
i
n
d
s
o
u
r
c
e
se
p
a
r
a
t
i
o
n
,
c
o
n
t
i
n
u
o
u
s
w
a
v
e
l
e
t
t
r
a
n
sf
o
r
m,
a
n
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
e
n
s
o
rs
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
1
9
,
n
o
.
2
0
,
p
.
4
5
4
1
,
O
c
t
.
2
0
1
9
,
d
o
i
:
1
0
.
3
3
9
0
/
s
1
9
2
0
4
5
4
1
.
[
2
0
]
R
.
A
l
a
z
a
i
d
a
h
,
M
.
A
l
z
y
o
u
d
,
N
.
A
l
-
S
h
a
n
a
b
l
e
h
,
a
n
d
H
.
A
l
z
o
u
b
i
,
“
T
h
e
si
g
n
i
f
i
c
a
n
c
e
o
f
c
a
p
t
u
r
i
n
g
t
h
e
c
o
r
r
e
l
a
t
i
o
n
s
a
mo
n
g
l
a
b
e
l
s
i
n
mu
l
t
i
-
l
a
b
e
l
c
l
a
ssi
f
i
c
a
t
i
o
n
:
A
n
i
n
v
e
st
i
g
a
t
i
v
e
st
u
d
y
,
”
i
n
AI
P
C
o
n
f
e
r
e
n
c
e
Pr
o
c
e
e
d
i
n
g
s
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
6
3
/
5
.
0
1
7
7
3
4
0
.
[
2
1
]
M
.
B
a
n
g
a
l
o
r
e
,
B
.
S
.
H
i
r
e
mat
h
,
a
n
d
A
.
M
.
P
o
l
n
a
y
a
,
“
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
b
r
e
a
st
c
a
n
c
e
r
u
s
i
n
g
e
n
se
mb
l
e
f
i
l
t
e
r
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
w
i
t
h
t
r
i
p
l
e
t
a
t
t
e
n
t
i
o
n
b
a
se
d
e
f
f
i
c
i
e
n
t
n
e
t
c
l
a
ssi
f
i
e
r
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
Ara
b
J
o
u
r
n
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
2
1
,
n
o
.
1
,
p
p
.
1
7
–
3
1
,
Jan
.
2
0
2
4
,
d
o
i
:
1
0
.
3
4
0
2
8
/
i
a
j
i
t
/
2
1
/
1
/
2
.
[
2
2
]
R
.
V
e
n
g
a
l
o
o
r
a
n
d
R
.
M
u
r
a
l
i
d
h
a
r
,
“
D
e
e
p
l
e
a
r
n
i
n
g
b
a
se
d
f
e
a
t
u
r
e
d
i
s
c
r
i
m
i
n
a
b
i
l
i
t
y
b
o
o
st
e
d
c
o
n
c
u
r
r
e
n
t
me
t
a
l
su
r
f
a
c
e
d
e
f
e
c
t
d
e
t
e
c
t
i
o
n
sy
st
e
m
u
si
n
g
Y
O
L
O
v
-
5s
-
F
R
N
,
”
T
h
e
I
n
t
e
rn
a
t
i
o
n
a
l
Ar
a
b
J
o
u
r
n
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
2
1
,
n
o
.
1
,
p
p
.
9
4
–
1
0
6
,
2
0
2
4
,
d
o
i
:
1
0
.
3
4
0
2
8
/
i
a
j
i
t
/
2
1
/
1
/
9
.
[
2
3
]
S
.
A
l
-
F
a
h
d
a
w
i
e
t
a
l
.
,
“
F
u
n
d
u
s
-
D
e
e
p
N
e
t
:
m
u
l
t
i
-
l
a
b
e
l
d
e
e
p
l
e
a
r
n
i
n
g
c
l
a
s
s
i
f
i
c
a
t
i
o
n
s
y
s
t
e
m
f
o
r
e
n
h
a
n
c
e
d
d
e
t
e
c
t
i
o
n
o
f
m
u
l
t
i
p
l
e
o
c
u
l
a
r
d
i
s
e
a
s
e
s
t
h
r
o
u
g
h
d
a
t
a
f
u
s
i
o
n
o
f
f
u
n
d
u
s
i
m
a
g
e
s
,
”
I
n
f
o
r
m
a
t
i
o
n
F
u
s
i
o
n
,
v
o
l
.
1
0
2
,
p
.
1
0
2
0
5
9
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
f
f
u
s
.
2
0
2
3
.
1
0
2
0
5
9
.
[
2
4
]
A.
-
R
.
A
l
-
G
h
u
w
a
i
r
i
,
H
.
E
i
d
,
M
.
A
l
o
r
a
n
,
Z
.
S
a
l
a
h
,
A
.
H
.
B
a
a
r
a
h
,
a
n
d
A
.
A
.
A
l
-
o
q
a
i
l
y
,
"
A
mu
t
a
t
i
o
n
-
b
a
se
d
mo
d
e
l
t
o
r
a
n
k
t
e
st
i
n
g
a
s
a
se
r
v
i
c
e
(
T
a
a
S
)
P
r
o
v
i
d
e
r
s
i
n
c
l
o
u
d
c
o
mp
u
t
i
ng
,"
i
n
IC
C
‘
1
6
:
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
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
I
n
t
e
rn
e
t
o
f
t
h
i
n
g
s
a
n
d
C
l
o
u
d
C
o
m
p
u
t
i
n
g
,
2
0
1
6
,
d
o
i
:
1
0
.
1
1
4
5
/
2
8
9
6
3
8
7
.
2
8
9
6
4
0
3
.
[
2
5
]
A
.
A
l
sarh
a
n
,
K
.
A
l
-
S
a
r
a
y
r
e
h
,
A
.
-
R
.
A
l
-
G
h
u
w
a
i
r
i
,
a
n
d
Y
.
K
i
l
a
n
i
,
"
R
e
so
u
r
c
e
t
r
a
d
i
n
g
i
n
c
l
o
u
d
e
n
v
i
r
o
n
me
n
t
s
f
o
r
p
r
o
f
i
t
max
i
mi
sa
t
i
o
n
u
si
n
g
a
n
a
u
c
t
i
o
n
mo
d
e
l
,"
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ad
v
a
n
c
e
d
I
n
t
e
l
l
i
g
e
n
c
e
P
a
ra
d
i
g
m
s
(
I
J
AI
P)
,
v
o
l
.
6
,
n
o
.
3
,
p
p
.
176
-
1
9
0
,
2
0
1
4
,
d
o
i
:
1
0
.
1
5
0
4
/
I
J
A
I
P
.
2
0
1
4
.
0
6
5
2
1
8
.
[
2
6
]
A.
-
R
.
A
l
-
G
h
u
w
a
i
r
i
e
t
a
l
.
,
"
V
i
su
a
l
i
z
i
n
g
so
f
t
w
a
r
e
r
e
f
a
c
t
o
r
i
n
g
u
si
n
g
r
a
d
a
r
c
h
a
r
t
s,"
S
c
i
e
n
t
i
f
i
c
Re
p
o
rt
s
,
v
o
l
.
13
,
n
o
.
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
3
-
4
4
2
8
1
-
6
[
2
7
]
F
.
M
.
A
l
su
h
i
ma
t
,
F
.
S
.
M
o
h
a
ma
d
,
a
n
d
M
.
I
q
t
a
i
t
,
"
D
e
t
e
c
t
i
o
n
a
n
d
Ex
t
r
a
c
t
i
o
n
F
e
a
t
u
r
e
s
f
o
r
S
i
g
n
a
t
u
r
e
s
I
mag
e
s
V
i
a
D
i
f
f
e
r
e
n
t
T
e
c
h
n
i
q
u
e
s
,
"
J
o
u
r
n
a
l
o
f
P
h
y
s
i
c
s:
C
o
n
f
e
re
n
c
e
S
e
ri
e
s,
t
h
e
1
st
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r,
S
c
i
e
n
c
e
,
En
g
i
n
e
e
ri
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
N
o
v
.
2
0
1
8
,
v
o
l
.
1
1
7
9
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
2
-
6
5
9
6
/
1
1
7
9
/
1
/
0
1
2
0
8
7
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ra
e
d
Ala
z
a
i
d
a
h
re
c
e
i
v
e
d
th
e
B.
S
c
.
d
e
g
re
e
s
in
C
o
m
p
u
ter
I
n
f
o
rm
a
ti
o
n
S
y
ste
m
,
M
.
S
c
.
d
e
g
re
e
s
in
C
o
m
p
u
ter
S
c
ie
n
c
e
f
ro
m
AL
a
l
-
Ba
y
t
Un
iv
e
rsit
y
,
Jo
rd
a
n
,
i
n
2
0
1
2
a
n
d
2
0
1
5
,
re
sp
e
c
ti
v
e
l
y
,
a
n
d
th
e
P
h
.
D.
d
e
g
re
e
in
C
o
m
p
u
ter
S
c
ien
c
e
f
ro
m
Un
iv
e
rsiti
S
a
in
s
M
a
lay
sia
,
M
a
la
y
sia
,
in
2
0
2
3
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ra
z
a
id
a
h
@z
u
.
e
d
u
.
jo
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
22
,
No
.
6
,
Dec
em
b
er
20
24
:
1
4
2
2
-
1430
1430
H
a
m
z
a
A
b
u
O
w
id
a
h
a
s
c
o
m
p
l
e
ted
h
is P
h
.
D
.
f
ro
m
Ke
e
le
Un
iv
e
r
sity
,
UK
.
He
wa
s
a
p
o
st
d
o
c
to
ra
l
re
se
a
rc
h
a
ss
o
c
iate
:
d
e
v
e
lo
p
in
g
x
e
n
o
-
f
re
e
n
a
n
o
f
ib
ro
u
s
sc
a
ff
o
ld
m
e
th
o
d
o
lo
g
y
f
o
r
h
u
m
a
n
p
lu
rip
o
ten
t
ste
m
c
e
ll
e
x
p
a
n
sio
n
,
d
if
f
e
r
e
n
ti
a
ti
o
n
a
n
d
im
p
lan
t
a
ti
o
n
to
w
a
rd
s
a
th
e
ra
p
e
u
ti
c
p
ro
d
u
c
t,
Ke
e
le
Un
iv
e
rsit
y
,
In
stit
u
te
f
o
r
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
in
M
e
d
icin
e
(IS
T
M
),
S
taff
o
rd
sh
ire/UK
.
He
is
A
ss
o
c
i
a
te
P
r
o
f
e
ss
o
r
in
De
p
a
rtm
e
n
t
o
f
M
e
d
ica
l
En
g
in
e
e
rin
g
i
n
Al
-
A
h
li
y
y
a
Am
m
a
n
Un
iv
e
rsit
y
.
He
h
a
s
p
u
b
li
sh
e
d
m
o
re
th
a
n
1
0
p
a
p
e
rs
in
re
p
u
ted
j
o
u
rn
a
ls.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
h
a
m
z
a
.
o
w
id
a
@g
m
a
il
.
c
o
m
.
Na
w
a
f
Alsh
d
a
ifa
t
re
c
e
iv
e
d
th
e
B.
S
c
.
d
e
g
re
e
s
in
C
o
m
p
u
ter
S
c
i
e
n
c
e
f
ro
m
A
L
a
l
-
Ba
y
t
Un
iv
e
rsit
y
a
n
d
M
.
S
c
.
d
e
g
re
e
s
in
C
o
m
p
u
ter
S
c
ien
c
e
f
ro
m
th
e
U
n
iv
e
rsity
o
f
Jo
rd
a
n
,
Jo
rd
a
n
,
i
n
2
0
0
2
a
n
d
2
0
1
1
,
re
sp
e
c
ti
v
e
l
y
,
a
n
d
t
h
e
P
h
.
D.
d
e
g
re
e
in
C
o
m
p
u
ter
S
c
ien
c
e
f
ro
m
Un
iv
e
rsiti
S
a
in
s
M
a
la
y
sia
,
M
a
la
y
sia
,
in
2
0
2
3
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
d
e
e
p
lea
rn
in
g
a
n
d
m
a
c
h
in
e
lea
rn
in
g
.
He
c
a
n
b
e
c
o
n
t
a
c
ted
a
t
e
m
a
il
:
n
_
a
lsh
d
a
if
a
t@a
su
.
e
d
u
.
j
o
.
Ab
e
d
a
l
h
a
k
e
e
m
Is
sa
h
a
s
c
o
m
p
lete
d
h
is
P
h
.
D
.
in
C
o
m
p
u
ter
S
c
ien
c
e
f
ro
m
In
stit
u
te
o
f
C
y
b
e
rn
e
ti
c
s/
A
z
e
rb
a
ij
a
n
Ac
a
d
e
m
y
o
f
S
c
ien
c
e
s
2
0
0
1
,
A
z
e
rb
a
ij
a
n
re
p
u
b
li
c
.
A
n
d
re
c
e
iv
e
d
th
e
B.
S
c
.
a
n
d
M
.
Sc
.
in
C
o
m
p
u
ter
S
c
ien
c
e
,
f
ro
m
T
h
e
A
z
e
rb
a
ij
a
n
S
t
a
te
P
e
tro
le
u
m
A
c
a
d
e
m
y
in
1
9
9
6
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
s,
in
f
o
rm
a
ti
o
n
se
c
u
rit
y
,
a
n
d
m
a
n
u
f
a
c
tu
rin
g
s
y
st
e
m
s
w
it
h
d
istri
b
u
te
d
c
o
m
p
u
ti
n
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
issa
@z
u
.
e
d
u
.
jo
.
S
u
h
a
il
a
A
b
u
o
w
a
id
a
re
c
e
iv
e
d
t
h
e
B.
S
c
.
d
e
g
re
e
s in
C
o
m
p
u
ter
I
n
f
o
rm
a
ti
o
n
S
y
ste
m
,
M
.
S
c
.
d
e
g
re
e
s
in
C
o
m
p
u
ter
S
c
ie
n
c
e
f
ro
m
AL
a
l
-
Ba
y
t
Un
iv
e
rsit
y
,
Jo
rd
a
n
,
i
n
2
0
1
2
a
n
d
2
0
1
5
,
re
sp
e
c
ti
v
e
l
y
,
a
n
d
th
e
P
h
.
D.
d
e
g
re
e
in
C
o
m
p
u
ter
S
c
ien
c
e
f
ro
m
Un
iv
e
rsiti
S
a
in
s
M
a
lay
sia
,
M
a
la
y
sia
,
in
2
0
2
3
.
S
h
e
is
c
u
rre
n
t
ly
w
o
rk
in
g
a
s
a
n
A
ss
istan
t
P
r
o
f
e
s
so
r
w
it
h
t
h
e
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
,
Zarq
a
Un
iv
e
rsity
,
Jo
rd
a
n
.
He
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
d
e
e
p
lea
rn
in
g
,
d
e
p
th
e
stim
a
ti
o
n
,
p
o
i
n
t
c
lo
u
d
a
n
d
c
o
m
p
u
ter
v
isio
n
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sa
b
u
o
w
e
u
d
a
@z
u
.
e
d
u
.
jo
.
Nid
a
l
Y
o
u
s
e
f
re
c
e
iv
e
d
h
is
B.
S
.
d
e
g
re
e
in
1
9
9
7
.
I
n
2
0
0
0
,
h
e
e
a
rn
e
d
h
is
M
a
ste
r
’
s
d
e
g
re
e
in
C
o
m
p
u
ter
I
n
f
o
rm
a
ti
o
n
S
y
ste
m
.
P
h
.
D.
Re
c
e
iv
e
d
in
2
0
0
8
in
C
o
m
p
u
ter
I
n
f
o
rm
a
ti
o
n
S
y
st
e
m
.
He
jo
in
e
d
t
o
Ki
n
g
A
b
d
u
laz
iz
Un
iv
e
rsity
in
S
a
u
d
i
A
ra
b
ia
in
2
0
0
9
a
s
a
n
A
ss
istan
t
P
r
o
f
e
ss
o
r,
a
n
d
in
2
0
1
0
h
e
m
o
v
e
d
to
A
l
-
Isra
Un
iv
e
rsit
y
in
Jo
rd
a
n
a
s
a
n
A
ss
istan
t
P
ro
f
e
ss
o
r
in
th
e
Co
ll
e
g
e
o
f
Co
m
p
u
ters
a
n
d
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
.
In
2
0
1
5
,
h
e
o
b
tain
e
d
th
e
d
e
g
re
e
a
s
a
n
A
s
so
c
iate
P
r
o
f
e
ss
o
r
.
In
2
0
2
2
,
h
e
jo
i
n
e
d
th
e
Co
ll
e
g
e
o
f
I
n
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
a
t
Zarq
a
Un
iv
e
rsit
y
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
n
id
a
l.
y
o
u
se
f
@z
u
.
e
d
u
.
j
o
.
Evaluation Warning : The document was created with Spire.PDF for Python.