I
AE
S
I
nte
rna
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
7
,
No
.
3
,
Sep
tem
b
er
201
8
,
p
p
.
13
8
~
1
42
I
SS
N:
2252
-
8938
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ai.
v
7
.
i
3
.
p
p
13
8
-
1
42
138
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e.
co
m/jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
I
JA
I
Applica
tion o
f
Multi
L
a
y
er Ar
tif
i
ci
a
l Ne
ura
l Ne
tw
o
r
k
in t
he
Dia
g
no
sis
Sys
te
m
:
A
Sy
ste
m
a
tic
Re
v
ie
w
Arv
ind
Sin
g
h Ra
w
a
t
1
,
Art
i
Ra
na
2
,
Adesh
K
u
m
a
r
3,
Ash
is
h B
a
g
w
a
ri
4
1,
2
,4
Uttara
k
h
a
n
d
T
e
c
h
n
ica
l
Un
iv
e
rsity
,
De
h
ra
d
u
n
,
In
d
ia
3
UP
E
S
De
h
ra
d
u
n
,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
r
25
,
2
0
1
8
R
ev
i
s
ed
Ma
y
2
4
,
2
0
1
8
A
cc
ep
ted
J
u
n
22
,
2
0
1
8
Ba
sic
h
a
rd
w
a
re
c
o
m
p
re
h
e
n
sio
n
o
f
a
n
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
(A
N
N),
to
a
m
a
jo
r
sc
a
le
d
e
p
e
n
d
s
o
n
th
e
p
r
o
f
icie
n
trea
li
z
a
ti
o
n
o
f
a
d
ist
in
c
tn
e
u
ro
n
.
F
o
r
h
a
rd
w
a
re
e
x
e
c
u
ti
o
n
o
f
NN
s,
m
o
stl
y
F
P
G
A
-
d
e
si
g
n
e
d
re
c
o
n
f
ig
u
ra
b
le
c
o
m
p
u
ti
n
g
s
y
ste
m
s
a
re
f
a
v
o
ra
b
le
.
F
P
GA
c
o
m
p
re
h
e
n
sio
n
o
f
AN
Ns
th
ro
u
g
h
a
h
u
g
e
a
m
o
u
n
t
o
f
n
e
u
r
o
n
s
is
m
a
in
ly
a
n
e
x
ig
e
n
tas
si
g
n
m
e
n
t.
T
h
is
w
o
rk
c
o
n
v
e
rse
s
th
e
re
v
iew
s
o
n
v
a
rio
u
s
re
se
a
rc
h
a
rti
c
les
o
f
n
e
u
ra
l
n
e
tw
o
r
k
s
w
h
o
se
c
o
n
c
e
rn
sf
o
c
u
se
d
in
e
x
e
c
u
ti
o
n
o
f
m
o
re
th
a
n
o
n
e
in
p
u
t
n
e
u
r
o
n
a
n
d
m
u
lt
il
a
y
e
r
w
it
h
o
r
w
it
h
o
u
t
li
n
e
a
rit
y
p
ro
p
e
rty
b
y
u
sin
g
F
P
GA
.
A
n
e
x
e
c
u
ti
o
n
tec
h
n
iq
u
e
th
ro
u
g
h
re
se
rv
e
su
b
st
it
u
ti
o
n
is
p
r
o
jec
ted
t
o
a
d
ju
st
sig
n
e
d
d
e
c
im
a
l
f
a
c
ts.
A
d
e
tailed
re
v
iew
o
f
m
a
n
y
re
s
e
a
rc
h
p
a
p
e
rs
h
a
v
e
b
e
e
n
d
o
n
e
f
o
r
th
e
p
ro
p
o
se
d
w
o
rk
.
K
ey
w
o
r
d
:
FP
GA
Neu
r
al
Net
w
o
r
k
VHDL
Co
p
y
rig
h
t
©
2
0
1
8
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
A
r
v
in
d
Si
n
g
h
R
a
w
at
,
Ut
tar
ak
h
an
d
T
ec
h
n
ical
U
n
i
v
er
s
it
y
,
Deh
r
ad
u
n
,
I
n
d
ia
.
E
m
ail:
r
a
w
at.
s
.
ar
v
in
d
@
g
m
ai
l.c
o
m
1.
I
NT
RO
D
UCT
I
O
N
T
o
d
ay
,
n
e
u
r
al
n
et
w
o
r
k
s
(
NN
s
)
ar
ea
u
n
it
u
s
u
all
y
u
s
ed
in
m
a
n
y
f
ield
s
an
d
al
s
o
b
ac
k
-
p
r
o
p
ag
atio
n
(
B
P)
h
as
b
ee
n
b
r
o
ad
ly
ac
ce
p
ted
as
f
l
o
u
r
is
h
in
g
k
n
o
w
led
g
e
r
u
les
to
s
ee
k
o
u
t
th
e
ap
p
r
o
p
r
iate
v
alu
es
o
f
th
e
w
ei
g
h
ts
f
o
r
n
eu
r
al
n
et
w
o
r
k
s
.
D
u
e
to
th
e
ad
v
an
ce
ar
ch
itect
u
r
e
an
d
ea
s
e
o
f
i
m
p
le
m
e
n
tatio
n
s
,
th
e
y
'r
e
g
o
in
g
to
b
e
ap
p
lie
d
d
u
r
in
g
a
v
er
y
w
id
e
s
elec
tio
n
o
f
m
ed
ical
f
ield
s
.
I
n
l
u
n
g
d
is
ea
s
e
lik
e
a
s
th
m
a
,
a
p
er
s
o
n
'
s
air
w
a
y
s
tu
r
n
in
to
in
f
la
m
ed
,
th
i
n
an
d
s
w
el
l d
u
e
to
ex
tr
a
m
u
cu
s
,
r
es
u
lti
n
g
d
i
f
f
icu
lt to
b
r
ea
th
e.
2.
ARTI
F
I
CI
AL
N
E
URA
L
NE
T
WO
RK
A
r
ti
f
icial
n
eu
r
al
n
et
w
o
r
k
s
ar
ea
u
n
it
e
x
ten
d
ed
w
ith
in
t
h
e
b
asis
o
f
b
r
ain
s
tr
u
ctu
r
e.
L
ik
e
t
h
e
b
r
ain
,
ANNs
w
il
l
ac
k
n
o
w
led
g
e
p
atter
n
s
,
h
a
n
d
le
f
ac
ts
a
n
d
f
ig
u
r
es
a
n
d
b
e
tr
ain
ed
.
T
h
e
y
’
r
e
r
ea
d
y
b
y
ar
ti
f
icial
n
e
u
r
o
n
s
th
a
t
e
m
p
lo
y
t
h
e
q
u
i
n
tes
s
en
ce
o
f
g
en
etic
n
e
u
r
o
n
s
.
I
t
ac
q
u
ir
es
an
a
m
o
u
n
t
o
f
i
n
p
u
t
s
(
f
r
o
m
d
is
tin
ctiv
e
k
n
o
w
led
g
e
o
r
f
r
o
m
o
u
tp
u
t
o
f
er
s
t
w
h
ile
r
ela
ted
to
n
eu
r
o
n
s
)
.
E
v
er
y
in
p
u
t
ap
p
r
o
ac
h
es
th
r
o
u
g
h
an
af
f
ilia
tio
n
,
th
at
is
n
a
m
ed
s
y
n
ap
s
es
a
n
d
t
h
at
f
ea
tu
r
e
s
a
weig
h
t.
A
n
er
v
e
ce
ll
co
n
j
o
in
tl
y
f
ea
tu
r
es
a
t
h
r
es
h
o
ld
w
o
r
t
h
.
I
f
t
h
e
s
u
m
m
atio
n
o
f
t
h
e
w
ei
g
h
ts
i
s
b
e
y
o
n
d
t
h
is
w
o
r
th
,
t
h
an
t
h
e
n
er
v
e
ce
ll is
s
tirr
ed
u
p
.
T
h
e
s
ti
m
u
latio
n
i
n
d
icatio
n
co
n
s
tr
u
cts
t
h
e
o
u
tp
u
t
o
f
t
h
e
n
er
v
e
ce
ll.
T
h
is
o
u
tp
u
t
is
o
f
ten
t
h
e
r
esu
lts
o
f
th
e
m
atter
o
r
ar
e
o
f
ten
m
ea
s
u
r
ed
A
N
i
n
p
u
t
f
o
r
an
ad
d
itio
n
al
n
er
v
e
ce
ll.
T
o
co
n
s
tr
u
ct
a
s
y
n
t
h
etic
n
eu
r
al
n
et
w
o
r
k
is
n
ee
d
ed
to
p
lace
co
n
j
o
in
tl
y
v
ar
iet
y
o
f
n
eu
r
o
n
s
.
T
h
e
y
’
r
e
o
r
g
an
ized
o
n
la
y
er
s
.
A
n
et
w
o
r
k
h
as
A
N
in
p
u
t
la
y
er
(
w
h
ich
h
o
ld
s
th
e
v
al
u
es
o
f
o
u
td
o
o
r
ca
p
r
icio
u
s
)
An
d
an
o
u
tp
u
t
la
y
er
(
t
h
e
f
o
r
ec
asts
o
r
th
e
u
lti
m
ate
o
u
tco
m
e
s
)
.
I
n
p
u
ts
an
d
o
u
tp
u
t
s
co
m
m
u
n
ic
ate
to
s
en
s
o
r
y
an
d
m
o
to
r
n
er
v
es
f
r
o
m
p
h
y
s
iq
u
e.
T
h
e
n
et
w
o
r
k
co
n
j
o
in
tl
y
co
n
s
i
s
t
o
n
e
h
id
d
en
la
y
er
(
s
)
o
f
n
e
u
r
o
n
s
,
t
h
at
p
er
f
o
r
m
s
a
n
i
n
s
id
e
p
er
f
o
r
m
w
it
h
i
n
t
h
e
n
et
w
o
r
k
.
An
A
r
ti
f
icial
Neu
r
al
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
A
p
p
lica
tio
n
o
f Mu
lti la
ye
r
A
r
tifi
cia
l Neu
r
a
l Net
w
o
r
k
in
th
e
Dia
g
n
o
s
is
S
ystem:
…
(
A
r
vin
d
S
in
g
h
R
.
)
139
Net
w
o
r
k
ca
n
b
e
r
ep
r
esen
ted
as
an
ar
it
h
m
etica
li
n
te
r
p
r
etatio
n
o
f
t
h
e
i
n
d
iv
id
u
al
n
eu
r
al
d
e
s
ig
n
,
r
ef
lec
tiv
e
it’s
“
lear
n
in
g
”
an
d
“g
e
n
er
aliza
tio
n
”
ca
p
ab
ilit
ies.
T
h
er
ef
o
r
e,
A
NNs
r
elate
s
to
th
e
w
o
r
ld
o
f
co
m
p
u
ter
s
cien
ce
a
n
d
ad
v
an
ce
ar
ti
f
icial
i
n
telli
g
e
n
ce
.
3.
M
AT
H
E
M
AT
I
CAL B
ACK
G
RO
UND
B
asicall
y
a
n
eu
r
al
n
et
w
o
r
k
is
f
o
r
m
ed
b
y
a
s
y
s
te
m
atic
ar
r
an
g
e
m
e
n
t
o
f
“n
e
u
r
o
n
s
”
an
d
a
g
ain
t
h
ese
ar
r
an
g
e
m
en
t
s
ar
e
s
tr
u
ct
u
r
ed
i
n
t
h
e
n
o
.
o
f
la
y
er
s
.
All
t
h
e
n
e
u
r
o
n
s
o
f
a
la
y
er
ar
e
r
elate
d
to
th
e
n
e
x
t
la
y
er
s
o
f
n
eu
r
o
n
s
w
it
h
s
o
m
e
w
ei
g
h
ted
f
ash
io
n
.
T
h
e
n
u
m
b
er
o
f
t
h
e
b
u
r
d
en
w
ij
m
er
e
t
h
e
f
o
r
ce
o
f
th
e
lin
k
a
m
o
n
g
th
e
i
th
v
eg
eta
tiv
e
ce
ll
i
n
a
v
er
y
la
y
er
an
d
also
th
e
j
-
th
v
e
g
etati
v
e
c
ell
in
s
u
b
s
eq
u
e
n
t
o
n
e.
T
h
e
f
o
r
m
atio
n
o
f
a
n
eu
r
al
n
et
w
o
r
k
i
s
cr
ea
ted
b
y
a
n
“
i
n
p
u
t”
la
y
er
,
o
n
e
o
r
q
u
ite
o
n
e
“
h
id
d
en
”
la
y
er
(
s
)
,
an
d
also
t
h
e
“
o
u
tp
u
t”
la
y
er
.
T
h
e
f
i
n
al
m
e
th
o
d
o
lo
g
y
o
f
a
p
ar
ticu
lar
th
r
ee
-
la
y
er
ed
n
eu
r
al
n
et
w
o
r
k
d
esig
n
is
g
i
v
en
i
n
Fi
g
u
r
e
1.
Her
e,
th
e
in
f
o
ar
ea
u
n
it
m
a
th
e
m
atica
ll
y
d
ev
elo
p
ed
an
d
also
th
e
r
es
u
lt
'
s
s
ettled
to
th
e
n
eu
r
o
n
s
w
it
h
i
n
th
e
n
e
x
t
la
y
er
.
E
v
e
n
tu
al
l
y
,
t
h
e
n
e
u
r
o
n
s
w
it
h
i
n
t
h
e
f
i
n
al
la
y
er
o
f
n
et
w
o
r
k
g
i
v
e
th
e
n
et
w
o
r
k
’
s
o
u
tp
u
t.
Ma
th
e
m
atica
ll
y
it i
s
o
b
s
er
v
ed
th
at
j
-
t
h
n
eu
r
o
n
o
f
a
h
id
d
en
la
y
er
o
b
s
er
v
es
th
e
i
n
w
a
r
d
b
o
u
n
d
d
ata
(
x
i
)
b
y
f
o
llo
w
in
g
th
r
ee
ca
lcu
latio
n
s
:
1.
W
eig
h
ted
est
i
m
at
io
n
ca
n
b
e
ca
lcu
lated
an
d
ad
d
itio
n
o
f
a
“
b
ia
s
”
ter
m
(
θ
j
)
ac
co
r
d
in
g
to
E
q
u
atio
n
1:
n
et
j
=
∑
(
∗
W
ij
+
Ø
)
j
=
1
,
2
,
…
.
,
n
=
1
…
(
1
)
Fig
u
r
e
1
.
C
o
n
v
e
n
tio
n
al
Fo
r
m
a
tio
n
o
f
Ne
u
r
al
Net
w
o
r
k
w
it
h
2
-
h
id
d
en
L
a
y
er
s
2.
T
r
an
s
f
o
r
m
atio
n
o
f
n
et
j
v
ia
ap
p
r
o
p
r
iate
m
at
h
e
m
atica
l
“
tr
an
s
f
er
f
u
n
ctio
n
”
3.
T
r
an
s
f
er
r
in
g
t
h
e
co
n
cl
u
d
in
g
r
esu
lt
s
to
n
eu
r
o
n
s
in
th
e
u
p
co
m
i
n
g
la
y
er
.
Fo
r
th
e
ac
tiv
atio
n
o
f
a
n
eu
r
o
n
m
a
n
y
tr
an
s
f
er
f
u
n
c
tio
n
ca
n
b
e
u
s
ed
b
u
t si
g
m
o
id
f
u
n
ctio
n
i
s
u
s
ed
th
e
m
o
s
t f
r
eq
u
e
n
tl
y
.
(
x
)
=
1
1
+
…
(
2
)
Fo
r
th
e
ap
p
licatio
n
o
f
n
e
u
r
al
n
et
w
o
r
k
i
n
t
h
e
v
ar
io
u
s
d
iag
n
o
s
i
s
s
y
s
te
m
a
s
y
s
te
m
atic
a
n
d
d
ee
p
liter
atu
r
e
s
u
r
v
e
y
i
s
d
o
n
e.
W
h
ich
i
s
as
f
o
llo
w
s
:
S
.
N
o
.
P
a
p
e
r
T
i
t
l
e
/
P
u
b
l
i
c
a
t
i
o
n
/
Y
e
a
r
D
e
scri
p
t
i
o
n
1.
“
Pre
d
i
c
t
i
n
g
Ast
h
m
a
O
u
t
c
o
m
e
U
si
n
g
P
a
r
t
i
a
l
L
e
a
st
S
q
u
a
re
Re
g
ress
i
o
n
a
n
d
Ar
t
i
f
i
c
i
a
l
N
e
u
ra
l
N
e
t
w
o
r
k
s”
E.
C
h
a
t
z
i
m
i
c
h
a
i
l
,
E
.
P
a
r
a
sk
a
k
i
s,
a
n
d
A
.
R
i
g
a
s,
H
i
n
d
a
w
i
P
u
b
l
i
s
h
i
n
g
C
o
r
p
o
r
a
t
i
o
n
A
d
v
a
n
c
e
s
i
n
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
V
o
l
u
me
2
0
1
3
,
A
r
t
i
c
l
e
I
D
4
3
5
3
2
1
,
7
p
a
g
e
s
I
n
t
h
i
s
p
a
p
e
r
,
a
n
a
d
v
a
n
c
e
m
a
c
h
i
n
e
i
n
t
e
l
l
i
g
e
n
c
e
me
t
h
o
d
o
l
o
g
y
f
o
r
t
h
e
p
r
e
d
i
c
t
i
o
n
o
f
p
e
r
si
st
e
n
t
r
e
sp
i
r
a
t
o
r
y
d
i
s
o
r
d
e
r
i
n
y
o
u
n
g
st
e
r
s
i
s
me
n
t
i
o
n
e
d
.
B
y
d
i
s
c
r
i
mi
n
a
t
i
o
n
p
a
r
t
i
a
l
l
e
a
st
s
q
.
r
e
g
r
e
ssi
o
n
,
n
i
n
e
o
u
t
o
f
f
o
r
t
y
e
i
g
h
t
e
x
t
r
a
p
o
l
a
t
i
v
e
a
sp
e
c
t
s
r
e
l
a
t
e
d
t
o
t
h
e
t
e
n
a
c
i
o
u
s
r
e
sp
i
r
a
t
o
r
y
d
i
so
r
d
e
r
a
r
e
i
d
e
n
t
i
f
i
e
d
.
M
u
l
t
i
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
a
r
r
a
n
g
e
me
n
t
s
a
r
e
f
o
u
n
d
so
a
s
t
o
u
r
g
e
t
h
e
mo
st
e
f
f
e
c
t
i
v
e
e
st
i
mat
e
a
c
c
u
r
a
c
y
.
I
n
t
h
e
r
e
su
l
t
s,
i
t
's
d
e
l
i
n
e
a
t
e
t
h
a
t
t
h
e
g
i
v
e
n
sy
st
e
m i
s re
a
d
y
t
o
p
r
e
d
i
c
t
t
h
e
a
st
h
m
a
c
o
n
se
q
u
e
n
c
e
s w
i
t
h
9
9
.
7
7
%.
2.
“
N
e
u
r
a
l
Pro
g
e
n
i
t
o
r
C
e
l
l
s
D
e
r
i
v
e
d
f
ro
m
H
u
m
a
n
Em
b
ry
o
n
i
c
S
t
e
m
C
e
l
l
s
a
s
a
n
O
ri
g
i
n
o
f
D
o
p
a
m
i
n
e
r
g
i
c
N
e
u
ro
n
s”
P
a
r
i
n
y
a
N
o
i
sa,
T
a
n
e
l
i
R
a
i
v
i
o
,
a
n
d
W
e
i
C
u
i
H
i
n
d
a
w
i
P
u
b
l
i
s
h
i
n
g
C
o
r
p
o
r
a
t
i
o
n
S
t
e
m
C
e
l
l
s
I
n
t
e
r
n
a
t
i
o
n
a
l
V
o
l
u
me
2
0
1
5
,
A
r
t
i
c
l
e
I
D
6
4
7
4
3
7
,
1
0
p
a
g
e
s
H
u
ma
n
e
mb
r
y
o
n
i
c
st
e
m
c
e
l
l
s
(
h
ESCs)
me
a
su
r
e
s
i
n
v
i
t
ro
i
n
d
e
t
e
r
mi
n
a
t
e
l
y
w
h
i
l
e
n
o
t
t
r
a
i
l
i
n
g
t
h
e
i
r
c
a
p
a
b
i
l
i
t
y
t
o
d
i
s
t
i
n
g
u
i
sh
i
n
n
u
me
r
o
u
sce
l
l
v
a
r
i
e
t
i
e
s
u
p
o
n
e
x
p
o
su
r
e
t
o
a
c
c
e
p
t
a
b
l
e
si
g
n
s.
D
u
r
i
n
g
t
h
i
s
st
u
d
y
,
a
u
t
h
o
r
se
g
r
e
g
a
t
e
d
h
ESCs
t
o
d
o
p
a
m
i
n
e
r
g
i
c
n
e
u
r
o
n
s
v
i
a
a
t
r
a
n
si
t
i
o
n
a
l
st
a
g
e
,
n
e
u
r
a
l
r
o
o
t
c
e
l
l
s.
3.
“
Art
i
f
i
c
i
a
l
N
e
u
r
a
l
N
e
t
w
o
r
k
Ap
p
l
i
c
a
t
i
o
n
i
n
t
h
e
D
i
a
g
n
o
s
i
s
o
f
D
i
s
e
a
s
e
C
o
n
d
i
t
i
o
n
s
w
i
t
h
L
i
v
e
r
U
l
t
r
a
so
u
n
d
I
m
a
g
e
s”
T
h
e
i
n
t
r
o
d
u
c
t
o
r
y
st
u
d
y
o
f
t
h
i
s
w
o
r
k
sh
o
w
s
a
a
b
so
l
u
t
e
st
u
d
y
o
f
a
sso
r
t
e
d
t
e
x
t
u
r
e
o
p
t
i
o
n
s
e
x
t
r
a
c
t
e
d
f
r
o
m
u
l
t
r
a
so
n
i
c
i
m
a
g
e
s
o
f
t
h
e
l
i
v
e
r
b
y
u
s
i
n
g
M
u
l
t
i
l
a
y
e
r
P
e
r
c
e
p
t
r
o
n
(
M
L
P
)
,
t
o
r
e
v
i
e
w
t
h
e
p
r
e
se
n
c
e
o
f
si
c
k
n
e
ss
c
o
n
d
i
t
i
o
n
s.
A
n
e
c
h
o
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
7
,
No
.
3
,
Sep
tem
b
er
20
1
8
:
13
8
–
1
42
140
K
a
r
t
h
i
k
K
a
l
y
a
n
,
B
i
n
a
l
Ja
k
h
i
a
,
R
a
ma
c
h
a
n
d
r
a
D
a
t
t
a
t
r
a
y
a
L
e
l
e
,
M
u
k
u
n
d
Jo
sh
i
,
a
n
d
A
b
h
a
y
C
h
o
w
d
h
a
r
y
,
H
i
n
d
a
w
i
P
u
b
l
i
s
h
i
n
g
C
o
r
p
o
r
a
t
i
o
n
A
d
v
a
n
c
e
s
i
n
B
i
o
i
n
f
o
r
mat
i
c
s
V
o
l
u
me
2
0
1
4
,
A
r
t
i
c
l
e
I
D
7
0
8
2
7
9
,
1
4
p
a
g
e
s
t
e
x
t
u
r
e
p
a
t
t
e
r
n
c
a
n
b
e
i
d
e
n
t
i
f
i
e
d
b
y
a
n
a
l
y
z
i
n
g
t
h
e
se
i
mag
e
s.
.
L
i
v
e
r
i
n
f
e
c
t
i
o
n
c
i
r
c
u
mst
a
n
c
e
s
l
i
k
e
f
a
t
t
y
l
i
v
e
r
,
c
i
r
r
h
o
si
s,
a
n
d
a
b
n
o
r
mal
i
t
y
sq
u
a
r
e
me
a
su
r
e
r
e
c
o
g
n
i
z
e
d
f
o
r
p
r
o
d
u
c
i
n
g
d
i
s
t
i
n
g
u
i
sh
i
n
g
e
c
h
o
p
a
t
t
e
r
n
s
t
h
r
o
u
g
h
o
u
t
A
me
r
i
c
a
i
mag
i
n
g
;
a
l
t
h
o
u
g
h
t
h
e
se
d
e
scri
p
t
i
o
n
s
a
l
so
a
r
e
k
n
o
w
n
t
o
b
e
v
i
s
u
a
l
l
y
d
i
f
f
i
c
u
l
t
f
o
r
d
e
c
i
p
h
e
r
i
n
g
t
h
e
m s
i
n
c
e
o
f
t
h
e
i
r
i
m
a
g
i
n
g
r
e
l
i
c
a
n
d
s
p
o
i
l
n
o
i
se
.
4.
“
H
a
rd
w
a
r
e
N
e
u
r
a
l
N
e
t
w
o
rks
Mo
d
e
l
i
n
g
f
o
r
C
o
m
p
u
t
i
n
g
D
i
f
f
e
re
n
t
P
e
rf
o
rm
a
n
c
e
Pa
ra
m
e
t
e
rs
o
f
Re
c
t
a
n
g
u
l
a
r
,
C
i
rc
u
l
a
r
,
a
n
d
T
ri
a
n
g
u
l
a
r
M
i
c
r
o
s
t
ri
p
An
t
e
n
n
a
s”
T
a
i
mo
o
r
K
h
a
n
a
n
d
A
so
k
D
e
,
H
i
n
d
a
w
i
P
u
b
l
i
sh
i
n
g
C
o
r
p
o
r
a
t
i
o
n
C
h
i
n
e
se
Jo
u
r
n
a
l
o
f
E
n
g
i
n
e
e
r
i
n
g
V
o
l
u
me
2
0
1
4
,
A
r
t
i
c
l
e
I
D
9
2
4
9
2
7
,
1
1
p
a
g
e
s
F
P
G
A
b
a
se
d
n
e
u
r
a
l
n
e
t
w
o
r
k
i
s
d
e
mo
n
st
r
a
t
e
d
i
n
t
h
i
s
w
o
r
k
.
D
i
f
f
e
r
e
n
t
p
a
r
a
me
t
e
r
s
o
f
r
e
c
t
a
n
g
u
l
a
r
,
t
r
i
a
n
g
u
l
a
r
a
n
d
c
i
r
c
u
l
a
r
a
n
t
e
n
n
a
a
r
e
a
n
a
l
y
z
e
d
t
h
r
o
u
g
h
F
P
G
A
b
a
se
d
N
N
.
T
h
i
s
p
a
p
e
r
g
i
v
e
s
a
n
i
d
e
a
t
o
e
v
o
l
v
e
a
l
o
w
p
r
i
c
e
n
e
u
r
a
l
n
e
t
w
o
r
k
b
a
se
d
F
P
G
A
w
h
i
c
h
i
s
b
e
n
e
f
i
c
i
a
l
f
o
r
t
h
e
m
i
c
r
o
w
a
v
e
a
p
p
l
i
c
a
t
i
o
n
s.
5.
“
S
i
m
u
l
t
a
n
e
o
u
s
Pe
r
t
u
r
b
a
t
i
o
n
L
e
a
r
n
i
n
g
Ru
l
e
f
o
r
Re
c
u
rre
n
t
N
e
u
r
a
l
N
e
t
w
o
rks
a
n
d
I
t
s
F
PG
A
I
m
p
l
e
m
e
n
t
a
t
i
o
n
”
Y
u
t
a
k
a
M
a
e
d
a
,
Me
m
b
e
r
,
I
EEE,
a
n
d
M
a
sa
t
o
sh
i
W
a
k
a
mu
r
a
,
I
EEE
T
R
A
N
S
A
C
TI
O
N
S
O
N
N
EU
R
A
L
N
ETW
O
R
K
S
,
V
O
L
.
1
6
,
N
O
.
6
,
N
O
V
EM
B
ER
2
0
0
5
I
n
t
h
i
s
w
o
r
k
,
a
u
t
h
o
r
s
w
e
l
l
t
h
o
u
g
h
t
-
o
u
t
a
sso
c
i
a
t
e
F
P
G
A
r
e
a
l
i
z
a
t
i
o
n
o
f
H
o
p
f
i
e
l
d
n
e
u
r
a
l
n
e
t
w
o
r
k
(
H
N
N
)
w
i
t
h
t
h
e
e
n
c
y
c
l
o
p
e
d
i
c
r
u
l
e
t
h
r
o
u
g
h
p
r
o
mp
t
a
g
i
t
a
t
i
o
n
.
N
e
u
r
a
l
n
e
t
w
o
r
k
s
(
N
N
s)
a
r
e
a
u
n
i
t
e
x
t
e
n
si
v
e
l
y
w
o
r
n
i
n
n
u
me
r
a
b
l
e
f
i
e
l
d
s.
A
t
t
h
e
s
a
me
t
i
me
,
b
a
c
k
-
p
r
o
p
a
g
a
t
i
o
n
(
B
P
)
i
s
e
x
t
e
n
si
v
e
l
y
e
n
f
o
r
c
e
d
a
s
a
t
r
i
u
mp
h
a
n
t
e
n
c
y
c
l
o
p
e
d
i
c
r
u
l
e
t
o
f
i
n
d
t
h
e
o
p
p
o
si
t
e
e
t
h
i
c
s
o
f
t
h
e
w
e
i
g
h
t
s
f
o
r
N
N
s.
A
s
a
n
e
x
a
mp
l
e
,
t
h
e
H
o
p
f
i
e
l
d
n
e
u
r
a
l
n
e
t
w
o
r
k
(
H
N
N
)
c
o
u
l
d
b
e
a
d
i
s
t
i
n
c
t
i
v
e
p
e
r
si
st
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
w
i
t
h
p
r
o
p
o
r
t
i
o
n
e
d
a
b
so
l
u
t
e
l
y
i
n
t
e
r
c
o
n
n
e
c
t
e
d
w
e
i
g
h
t
s.
P
e
r
si
s
t
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
s
h
a
v
e
a
t
t
e
n
t
i
o
n
-
g
r
a
b
b
i
n
g
p
r
o
p
e
r
t
i
e
s
a
n
d
m
i
g
h
t
h
a
n
d
l
e
d
y
n
a
mi
c
I
P
i
n
c
o
n
t
r
a
st
t
o
s
t
a
n
d
a
r
d
f
e
e
d
f
o
r
w
a
r
d
n
e
u
r
a
l
n
e
t
w
o
r
k
s.
T
h
i
s
p
a
p
e
r
s
h
o
w
s,
a
n
a
l
g
o
r
i
t
h
mi
c
l
e
a
r
n
i
n
g
t
h
e
me
f
o
r
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
s
mi
st
r
e
a
t
me
n
t
t
h
e
sy
n
c
h
r
o
n
i
c
p
e
r
t
u
r
b
a
t
i
o
n
t
e
c
h
n
i
q
u
e
.
6.
“
A
S
t
o
c
h
a
st
i
c
D
i
g
i
t
a
l
I
m
p
l
e
m
e
n
t
a
t
i
o
n
o
f
a
N
e
u
ra
l
N
e
t
w
o
rk
C
o
n
t
ro
l
l
e
r
f
o
r
S
m
a
l
l
Wi
n
d
T
u
rb
i
n
e
S
y
s
t
e
m
s”
H
u
i
L
i
,
S
e
n
i
o
r
M
e
m
b
e
r,
I
EE
E
,
D
a
Z
h
a
n
g
,
S
t
u
d
e
n
t
Me
m
b
e
r,
I
EEE
,
a
n
d
S
i
mo
n
Y
.
F
o
o
,
I
EEE
T
R
A
N
S
A
C
TI
O
N
S
O
N
P
O
W
ER
EL
EC
T
R
O
N
I
C
S
,
V
O
L
.
2
1
,
N
O
.
5
,
S
EPT
EM
B
ER
2
0
0
6
A
r
e
c
o
n
f
i
g
u
r
a
b
l
e
h
a
r
d
w
a
r
e
e
x
e
c
u
t
i
o
n
o
f
f
e
e
d
f
o
r
w
a
r
d
N
N
s
b
a
se
d
o
n
st
o
c
h
a
st
i
c
me
t
h
o
d
o
l
o
g
y
i
s
p
r
e
se
n
t
e
d
i
n
t
h
i
s
p
a
p
e
r
.
T
h
e
n
o
n
l
i
n
e
a
r
s
i
g
mo
i
d
a
c
t
i
v
a
t
i
o
n
s
i
g
n
a
l
w
i
t
h
mi
n
i
mu
m
d
i
g
i
t
a
l
l
o
g
i
c
i
n
p
u
t
s
i
s
e
st
i
m
a
t
e
d
b
y
u
si
n
g
st
o
c
h
a
st
i
c
c
o
mp
u
t
a
t
i
o
n
t
h
e
o
r
y
.
7.
“
H
a
rd
w
a
r
e
R
e
a
l
i
z
a
t
i
o
n
o
f
Art
i
f
i
c
i
a
l
N
e
u
r
a
l
N
e
t
w
o
rk
Ba
se
d
I
n
t
r
u
s
i
o
n
D
e
t
e
c
t
i
o
n
&
Pre
v
e
n
t
i
o
n
S
y
st
e
m
”
I
n
d
r
a
n
e
e
l
M
u
k
h
o
p
a
d
h
y
a
y
,
M
o
h
u
y
a
C
h
a
k
r
a
b
o
r
t
y
,
Jo
u
r
n
a
l
o
f
I
n
f
o
r
mat
i
o
n
S
e
c
u
r
i
t
y
,
2
0
1
4
,
5
,
1
5
4
-
1
6
5
P
u
b
l
i
s
h
e
d
O
n
l
i
n
e
O
c
t
o
b
e
r
2
0
1
4
i
n
S
c
i
R
e
s.
I
n
t
h
i
s
r
e
se
a
r
c
h
w
o
r
k
,
a
n
a
d
v
a
n
c
e
t
e
c
h
n
i
q
u
e
i
s
p
r
o
p
o
se
d
f
o
r
e
x
e
c
u
t
i
o
n
o
f
I
n
t
r
u
si
o
n
D
e
t
e
c
t
i
o
n
a
n
d
p
r
e
v
e
n
t
i
o
n
sy
st
e
m.
T
h
i
s
sy
st
e
m
i
s
c
o
mp
l
e
t
e
l
y
i
mp
l
e
me
n
t
e
d
o
n
F
P
G
A
w
h
i
c
h
c
a
n
i
d
e
n
t
i
f
y
d
i
f
f
e
r
e
n
t
n
e
t
w
o
r
k
s
o
u
t
b
r
e
a
k
s
a
n
d
p
r
e
v
e
n
t
t
h
e
m fr
o
m fu
r
t
h
e
r
t
r
a
n
smiss
i
o
n
.
8.
“
Re
f
e
re
n
c
e
V
a
l
u
e
s
f
o
r
L
u
n
g
F
u
n
c
t
i
o
n
T
e
s
t
s
i
n
A
d
u
l
t
S
a
u
d
i
Po
p
u
l
a
t
i
o
n
”
N
a
sr
A
.
B
e
l
a
c
y
A
b
d
u
l
l
a
h
H
.
A
l
t
e
m
a
n
i
,
M
o
st
a
f
a
H
.
A
b
d
e
l
sal
a
m1
,
M
a
g
d
i
A
.
El
-
D
a
mara
w
i
,
B
a
se
m
M
.
El
sawy
,
N
o
h
a
A
.
N
a
si
f
,
E
man
A
.
El
-
B
a
ss
u
o
n
i
1
,
8
,
I
n
t
e
r
n
a
t
i
o
n
a
l
Jo
u
r
n
a
l
o
f
I
n
t
e
r
n
a
l
M
e
d
i
c
i
n
e
2
0
1
4
,
3
(
3
)
:
4
3
-
5
2
D
O
I
:
1
0
.
5
9
2
3
/
j
.
i
j
i
m
.
2
0
1
4
0
3
0
3
.
0
2
F
o
r
t
h
e
d
i
a
g
n
o
si
s
o
f
ma
n
y
r
e
sp
i
r
a
t
o
r
y
sy
n
d
r
o
me
,
L
u
n
g
f
u
n
c
t
i
o
n
t
e
st
i
n
g
i
s
a
q
u
i
t
e
i
mp
o
r
t
a
n
t
.
I
n
t
h
i
s
p
a
p
e
r
,
i
t
h
a
s
b
e
e
n
d
i
sco
v
e
r
e
d
t
h
a
t
r
e
f
e
r
e
n
c
e
d
a
t
a
i
s
v
e
r
y
smal
l
f
o
r
S
a
u
d
i
a
d
u
l
t
s.
9.
“
Art
i
f
i
c
i
a
l
N
e
u
r
a
l
N
e
t
w
o
r
k
M
o
d
e
l
i
n
g
f
o
r
S
p
a
t
i
a
l
a
n
d
T
e
m
p
o
ra
l
V
a
ri
a
t
i
o
n
s
o
f
P
o
re
-
Wa
t
e
r
P
ressu
r
e
M
.
R
.
M
u
s
t
a
f
a
,
1
R
.
B
.
R
e
z
a
u
r
,
2
H
.
R
a
h
a
r
d
j
o
,
3
M
.
H
.
I
sa,
1
a
n
d
A
.
A
r
i
f
,
H
i
n
d
a
w
i
P
u
b
l
i
s
h
i
n
g
C
o
r
p
o
r
a
t
i
o
n
A
d
v
a
n
c
e
s
i
n
M
e
t
e
o
r
o
l
o
g
y
V
o
l
u
me
2
0
1
5
,
A
r
t
i
c
l
e
I
D
2
7
3
7
3
0
,
1
2
p
a
g
es
T
h
i
s
p
a
p
e
r
sh
o
w
s
t
h
e
r
e
sp
o
n
se
s
t
o
r
a
i
n
f
a
l
l
a
p
p
l
i
c
a
t
i
o
n
o
f
A
N
N
.
I
t
i
s
n
o
t
e
a
sy
t
o
me
a
su
r
e
t
h
e
so
i
l
p
o
r
e
w
a
t
e
r
p
r
e
ssu
r
e
b
e
c
a
u
se
i
t
i
s
t
e
d
i
o
u
s,
t
i
me
t
a
k
i
n
g
a
n
d
e
x
p
e
n
si
v
e
t
a
sk
.
T
h
i
s
a
r
t
i
c
l
e
g
i
v
e
s
t
h
e
r
e
l
e
v
a
n
c
e
o
f
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
(
A
N
N
)
sy
st
e
m
f
o
r
d
e
mo
n
st
r
a
t
i
n
g
so
i
l
p
o
r
e
-
w
a
t
e
r
p
r
e
ssu
r
e
d
i
ssi
m
i
l
a
r
i
t
i
e
s
a
t
se
v
e
r
a
l
so
i
l
d
e
p
t
h
s
f
r
o
m t
h
e
st
a
t
i
s
t
i
c
s
o
f
r
a
i
n
f
a
l
l
p
a
t
t
e
r
n
s.
1
0
.
“
Fe
e
d
f
o
rw
a
r
d
N
e
u
ra
l
N
e
t
w
o
rk
I
m
p
l
e
m
e
n
t
a
t
i
o
n
i
n
FPG
A
U
si
n
g
L
a
y
e
r
M
u
l
t
i
p
l
e
x
i
n
g
f
o
r
Ef
f
e
c
t
i
v
e
Re
so
u
r
c
e
U
t
i
l
i
z
a
t
i
o
n
”
S
.
H
i
mav
a
t
h
i
,
D
.
A
n
i
t
h
a
,
a
n
d
A
.
M
u
t
h
u
r
a
mal
i
n
g
a
m,
I
EEE
T
R
A
N
S
A
C
TI
O
N
S
O
N
N
EU
R
A
L
N
ETW
O
R
K
S
,
V
O
L
.
1
8
,
N
O
.
3
,
M
A
Y
2
0
0
7
M
u
l
t
i
l
a
y
e
r
n
e
u
r
a
l
n
e
t
w
o
r
k
w
i
t
h
f
e
e
d
f
o
r
w
a
r
d
t
e
c
h
n
i
q
u
e
b
a
se
d
F
P
G
A
i
s
i
mp
l
e
me
n
t
e
d
i
n
t
h
i
s
a
r
t
i
c
l
e
.
Ev
e
n
t
h
o
u
g
h
e
n
h
a
n
c
e
me
n
t
s
i
n
F
P
G
A
b
u
l
k
s,
t
h
e
v
a
r
i
o
u
s
mu
l
t
i
p
l
i
e
r
s
i
n
a
sso
c
i
a
t
e
d
e
g
r
e
e
N
N
l
i
m
i
t
t
h
e
sc
a
l
e
o
f
t
h
e
n
e
t
w
o
r
k
t
h
a
t
may
b
e
e
n
f
o
r
c
e
d
e
mp
l
o
y
i
n
g
a
s
i
n
g
l
e
F
P
G
A
,
t
h
e
r
e
f
o
r
e
c
r
e
a
t
i
n
g
N
N
a
p
p
l
i
c
a
t
i
o
n
s
n
o
t
f
e
a
si
b
l
e
p
r
o
f
i
t
a
b
l
y
.
1
1
.
“
I
m
p
l
e
m
e
n
t
a
t
i
o
n
I
ssu
e
s
o
f
N
e
u
r
o
-
F
u
zzy
H
a
rd
w
a
r
e
:
G
o
i
n
g
T
o
w
a
r
d
H
W
/
S
W
C
o
d
e
s
i
g
n
”
L
e
o
n
a
r
d
o
M
a
r
i
a
R
e
y
n
e
r
i
I
EEE
T
R
A
N
S
A
C
TI
O
N
S
O
N
N
EU
R
A
L
N
ETW
O
R
K
S
,
V
O
L
.
1
4
,
N
O
.
1
,
JA
N
U
A
R
Y
G
l
o
ss
y
su
mm
a
r
y
o
f
p
r
e
v
a
i
l
i
n
g
h
a
r
d
w
a
r
e
i
mp
l
e
me
n
t
a
t
i
o
n
o
f
A
N
N
a
n
d
F
u
z
z
y
l
o
g
i
c
st
r
u
c
t
u
r
e
s
a
r
e
p
r
e
se
n
t
e
d
i
n
t
h
i
s
a
r
t
i
c
l
e
.
T
h
i
s
p
a
p
e
r
a
l
so
d
e
scri
b
e
s
r
e
st
r
i
c
t
i
o
n
s,
u
p
si
d
e
s a
n
d
d
o
w
n
si
d
e
s o
f
d
i
f
f
e
r
e
n
t
i
mp
l
e
me
n
t
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s.
4.
CO
NCLU
SI
O
N
T
h
e
u
lti
m
ate
ai
m
o
f
d
es
ig
n
i
n
g
an
ef
f
icie
n
t
d
iag
n
o
s
i
s
s
y
s
te
m
is
to
m
a
k
e
b
est
u
s
e
o
f
th
e
cla
s
s
if
ica
tio
n
ac
cu
r
ac
y
an
d
at
th
e
s
a
m
e
ti
m
e
r
ed
u
ce
th
e
f
ea
tu
r
e
s
ize.
ANN
ca
n
co
n
f
id
e
n
tl
y
b
e
u
s
ed
to
im
p
l
e
m
en
t
an
y
d
iag
n
o
s
i
s
s
y
s
te
m
b
ec
a
u
s
e:
-
1.
I
t h
as c
ap
ab
ilit
y
to
h
a
n
d
le
a
h
u
g
e
a
m
o
u
n
t o
f
f
ac
t
s
an
d
f
ig
u
r
es
.
2.
C
o
n
d
en
s
ed
ch
a
n
ce
o
f
ig
n
o
r
ab
le
p
er
tin
en
t d
ata.
3.
Di
m
i
n
u
tio
n
o
f
id
en
ti
f
icatio
n
ti
m
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
A
p
p
lica
tio
n
o
f Mu
lti la
ye
r
A
r
tifi
cia
l Neu
r
a
l Net
w
o
r
k
in
th
e
Dia
g
n
o
s
is
S
ystem:
…
(
A
r
vin
d
S
in
g
h
R
.
)
141
T
h
e
o
u
tco
m
e
t
h
at
h
as
b
ee
n
o
b
tain
ed
f
r
o
m
ab
o
v
e
r
esear
ch
ar
ticles
s
h
o
w
s
th
at
a
n
y
m
ed
ical
d
iag
n
o
s
i
s
s
y
s
te
m
b
ased
o
n
A
N
N
ca
n
at
tain
q
u
ite
h
i
g
h
p
r
ed
ictio
n
ac
c
u
r
ac
y
.
A
NN
s
s
y
m
b
o
lize
a
n
i
n
f
lu
e
n
tial
to
o
ls
a
n
d
tech
n
iq
u
e
to
f
ac
il
itate
an
d
h
el
p
p
h
y
s
icia
n
s
to
co
m
p
lete
d
ia
g
n
o
s
is
a
n
d
m
a
n
y
o
t
h
er
test
s
.
RE
F
E
R
E
NC
E
S
[1
]
E.
Ch
a
tzim
ich
a
il
,
E.
P
a
ra
sk
a
k
is,
a
n
d
A
.
Rig
a
s,
“
Pre
d
icti
n
g
Asth
ma
Ou
tco
me
Us
in
g
Pa
rt
ia
l
L
e
a
st S
q
u
a
re
Reg
re
ss
io
n
a
n
d
Arti
fi
c
ia
l
Ne
u
ra
l
Ne
two
rk
s”
Hin
d
a
w
i
P
u
b
li
sh
in
g
Co
rp
o
ra
ti
o
n
A
d
v
a
n
c
e
s
in
A
rti
f
icia
l
In
telli
g
e
n
c
e
V
o
l
u
m
e
2
0
1
3
,
A
rti
c
le ID
4
3
5
3
2
1
,
7
p
a
g
e
s
[2
]
P
a
ri
n
y
a
No
isa
,
T
a
n
e
li
Ra
iv
io
,
a
n
d
W
e
i
Cu
i
“
Ne
u
ra
l
Pr
o
g
e
n
i
to
r
Ce
ll
s
De
riv
e
d
fro
m
Hu
ma
n
Emb
ry
o
n
i
c
S
tem
Ce
ll
s
a
s
an
Orig
in
o
f
D
o
p
a
min
e
rg
ic
Ne
u
ro
n
s”
Hi
n
d
a
w
i
P
u
b
li
s
h
in
g
C
o
rp
o
ra
ti
o
n
S
tem
Ce
ll
s
In
tern
a
ti
o
n
a
l
V
o
lu
m
e
2
0
1
5
,
A
rti
c
le ID
6
4
7
4
3
7
,
1
0
p
a
g
e
s
[3
]
Ka
rth
ik
Ka
l
y
a
n
,
Bin
a
lJa
k
h
ia,
Ra
m
a
c
h
a
n
d
ra
Da
tt
a
tra
y
a
L
e
le,
M
u
k
u
n
d
Jo
sh
i,
a
n
d
A
b
h
a
y
Ch
o
w
d
h
a
r
y
,
A
rtif
icia
l
Ne
u
ra
l
Ne
two
rk
Ap
p
l
ica
ti
o
n
in
th
e
Di
a
g
n
o
sis
o
f
Dise
a
se
Co
n
d
i
ti
o
n
s
wit
h
L
ive
r
Ultra
so
u
n
d
Ima
g
e
s”
Hin
d
a
w
i
P
u
b
l
ish
i
n
g
Co
rp
o
ra
ti
o
n
A
d
v
a
n
c
e
s in
Bio
in
f
o
rm
a
ti
c
s V
o
lu
m
e
2
0
1
4
,
A
rti
c
le ID
7
0
8
2
7
9
,
1
4
p
a
g
e
s
[4
]
T
a
i
m
o
o
r
Kh
a
n
a
n
d
A
so
k
De
,
“
Ha
rd
wa
re
Ne
u
ra
l
Ne
t
w
o
rk
s
M
o
d
e
li
n
g
f
o
r
Co
m
p
u
ti
n
g
Diff
e
re
n
t
P
e
rf
o
rm
a
n
c
e
P
a
ra
m
e
ters
o
f
Re
c
t
a
n
g
u
lar,
Circu
l
a
r,
a
n
d
T
rian
g
u
lar
M
icro
strip
A
n
t
e
n
n
a
s
”
Hin
d
a
wi
P
u
b
l
ish
i
n
g
Co
r
p
o
ra
ti
o
n
C
h
in
e
se
J
o
u
rn
a
l
o
f
E
n
g
i
n
e
e
rin
g
Vo
lu
m
e
2
0
1
4
,
A
rti
c
le ID
9
2
4
9
2
7
,
1
1
p
a
g
e
s
[5
]
Yu
tak
a
M
a
e
d
a
,
M
a
sa
to
sh
i
W
a
k
a
m
u
ra
“
S
i
m
u
lt
a
n
e
o
u
s
P
e
rtu
r
b
a
ti
o
n
L
e
a
rn
in
g
Ru
le
f
o
r
Re
c
u
rre
n
t
Ne
u
r
a
l
Ne
tw
o
rk
s
a
n
d
Its
F
P
GA
I
m
p
le
m
e
n
tatio
n
”.
IEE
E
T
ra
n
s
a
c
ti
o
n
s
on
Ne
u
ra
l
Ne
two
rk
s
,
No
v
e
m
b
e
r
2
0
0
5
,
V
OL
.
1
6
,
NO
.
6
.
[6
]
Bim
a
l
K.
Bo
se
“
Ne
u
ra
l
Ne
t
w
o
rk
A
p
p
li
c
a
ti
o
n
s
i
n
P
o
w
e
r
El
e
c
t
ro
n
ics
a
n
d
M
o
t
o
r
Driv
e
s
-
A
n
In
tro
d
u
c
ti
o
n
a
n
d
P
e
rsp
e
c
ti
v
e
.
”
IEE
E
T
ra
n
s
a
c
ti
o
n
s
on
I
n
d
u
stria
l
El
e
c
tro
n
ics
,
F
e
b
r
u
a
ry
2
0
0
7
,
V
OL
.
5
4
,
NO
.
1
,
[7
]
In
d
ra
n
e
e
lM
u
k
h
o
p
a
d
h
y
a
y
,
M
o
h
u
y
a
Ch
a
k
ra
b
o
rty
“
Ha
rd
w
a
re
Re
a
li
z
a
ti
o
n
o
f
A
rti
f
icia
l
Ne
u
ra
l
Ne
t
w
o
rk
Ba
se
d
In
tru
si
o
n
De
tec
ti
o
n
&
P
re
v
e
n
ti
o
n
S
y
ste
m
”
J
o
u
rn
a
l
o
f
I
n
fo
rm
a
ti
o
n
S
e
c
u
rity
,
2
0
1
4
,
5
,
1
5
4
-
1
6
5
P
u
b
li
sh
e
d
On
li
n
e
Oc
to
b
e
r
2
0
1
4
in
S
c
iRes
.
[8
]
Na
sr
A
.
Be
lac
y
Ab
d
u
ll
a
h
H.
A
lt
e
m
a
n
i,
M
o
sta
f
a
H.
A
b
d
e
lsa
la
m
1
,
M
a
g
d
i
A
.
El
-
Da
m
a
ra
w
i,
Ba
s
e
m
M
.
El
sa
wy
,
No
h
a
A
.
Na
si
f
,
E
m
a
n
A
.
El
-
Ba
ss
u
o
n
i1
“
Re
f
e
re
n
c
e
V
a
lu
e
s
f
o
r
L
u
n
g
F
u
n
c
ti
o
n
T
e
sts
in
A
d
u
lt
S
a
u
d
i
P
o
p
u
lati
o
n
”
.
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
I
n
ter
n
a
l
M
e
d
icin
e
2
0
1
4
,
3
(
3
):
4
3
-
5
2
DO
I:
1
0
.
5
9
2
3
/
j.
ij
im
.
2
0
1
4
0
3
0
3
.
0
2
[9
]
M
.
R.
M
u
sta
f
a
,
R.
B.
Re
z
a
u
r,
H.
Ra
h
a
rd
jo
,
3
M
.
H.
Isa
,
a
n
d
A
.
A
ri
f
,
“
Arti
fi
c
i
a
l
Ne
u
ra
l
Ne
tw
o
rk
M
o
d
e
li
n
g
fo
r S
p
a
ti
a
l
a
n
d
T
e
mp
o
ra
l
Va
ri
a
ti
o
n
s
o
f
P
o
re
-
W
a
ter
Pre
ss
u
re
Re
sp
o
n
se
s
to
Ra
i
n
fa
ll
”
,
Hi
n
d
a
wi
Pu
b
li
sh
i
n
g
Co
r
p
o
ra
ti
o
n
Ad
v
a
n
c
e
s i
n
M
e
teo
ro
lo
g
y
V
o
l
u
m
e
2
0
1
5
,
A
rti
c
le ID
2
7
3
7
3
0
,
1
2
p
a
g
e
s
[1
0
]
S
.
Him
a
v
a
th
i,
D.
A
n
it
h
a
,
a
n
d
A
.
M
u
th
u
ra
m
a
li
n
g
a
m
“
Fee
d
fo
rwa
r
d
Ne
u
ra
l
Ne
two
rk
Imp
lem
e
n
ta
ti
o
n
in
F
PGA
Us
in
g
L
a
y
e
r
M
u
lt
ip
lex
in
g
f
o
r
Ef
fec
ti
v
e
Res
o
u
rc
e
Util
iza
ti
o
n
”
,
IEE
E
T
r
a
n
sa
c
ti
o
n
s
o
n
Ne
u
ra
l
Ne
tw
o
rk
s
,
v
o
l.
1
8
,
n
o
.
3
,
m
a
y
2
0
0
7
[1
1
]
Le
o
n
a
rd
o
M
a
ria
Re
y
n
e
ri
“
Imp
lem
e
n
ta
ti
o
n
Iss
u
e
s
o
f
Ne
u
ro
-
F
u
zz
y
Ha
rd
w
a
re
:
Go
i
n
g
T
o
wa
r
d
HW
/
S
W
Co
d
e
sig
n
”
,
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Ne
u
ra
l
Ne
t
wo
rk
s
,
Ja
n
u
a
ry
2
0
0
3
,
V
OL
.
1
4
,
NO
.
1
,
,
p
p
(1
7
6
-
1
9
4
)
[1
2
]
Hu
i
L
i
,
Da
Zh
a
n
g
,
a
n
d
S
im
o
n
Y.
F
o
o
“
A
S
t
o
c
h
a
stic
Di
g
it
a
l
Im
p
lem
e
n
ta
ti
o
n
o
f
a
Ne
u
r
a
l
Ne
tw
o
rk
Co
n
tro
ll
e
r
fo
r
S
ma
l
l
W
in
d
T
u
rb
i
n
e
S
y
ste
ms
”
I
EE
E
T
ra
n
sa
c
ti
o
n
s On
Po
we
r E
lec
tro
n
ics
,
V
o
l
.
2
1
,
N
o
.
5
,
S
e
p
tem
b
e
r
2
0
0
6
[1
3
]
Ch
e
o
l
-
T
a
e
k
Ki
m
a
n
d
Ju
-
Ja
n
g
L
e
e
“
T
ra
i
n
in
g
T
wo
-
L
a
y
e
re
d
Fee
d
f
o
rwa
rd
Ne
tw
o
rk
s
W
it
h
Va
ri
a
b
le
Pro
jec
ti
o
n
M
e
th
o
d
”
I
EE
E
T
ra
n
s
a
c
ti
o
n
s o
n
Ne
u
ra
l
Ne
two
rk
s
,
V
o
l.
1
9
,
No
.
2
,
F
e
b
ru
a
ry
2
0
0
8
.
[1
4
]
Ch
e
rin
J
o
se
p
h
,
A
n
u
G
u
p
ta
“
A
No
v
e
l
Ha
rd
wa
re
Ef
fi
c
ien
t
Di
g
it
a
l
Ne
u
ra
l
Ne
two
rk
Arc
h
it
e
c
tu
re
Imp
le
me
n
ted
in
1
3
0
n
m
T
e
c
h
n
o
l
o
g
y
“
IEE
E
9
7
8
-
1
-
4
2
4
4
-
5
5
8
6
-
7
/
1
0
/
2
0
1
0
[1
5
]
Ch
e
o
l
-
T
a
e
k
Ki
m
a
n
d
Ju
-
Ja
n
g
L
e
e
“
T
ra
i
n
i
n
g
T
wo
-
L
a
y
e
re
d
Fee
d
f
o
rwa
rd
Ne
two
rk
sW
it
h
V
a
ria
b
le
Pr
o
j
e
c
ti
o
n
M
e
th
o
d
”
IEE
E
T
ra
n
sa
c
ti
o
n
s
on
Ne
u
ra
l
Ne
t
wo
rk
s
,
Vo
l.
1
9
,
No
.
2
,
F
e
b
r
u
a
ry
2
0
0
8
.
[1
6
]
W
.
Weish
u
i,
“
Im
p
lem
e
n
ti
n
g
o
n
li
n
e
n
a
tu
ra
l
g
ra
d
ien
t
lea
rn
in
g
:
P
ro
b
l
e
m
s
a
n
d
so
l
u
ti
o
n
s,”
IEE
E
T
ra
n
s.
Ne
u
ra
l
Ne
tw
.
,
v
o
l
.
1
7
,
n
o
.
2
,
p
p
.
3
1
7
–
3
2
9
,
M
a
r.
2
0
0
6
.
[1
7
]
W
.
W
.
T
a
n
a
n
d
H.
Hu
o
,
A
G
e
n
e
ri
c
Ne
u
ro
-
“
F
u
z
z
y
M
o
d
e
l
-
Ba
se
d
A
p
p
ro
a
c
h
f
o
r
De
tec
ti
n
g
F
a
u
lt
s
in
I
n
d
u
c
ti
o
n
M
o
t
o
rs”
.
IEE
E
T
ra
n
s.
I
n
d
u
stria
l
El
e
c
tro
n
ic
s
,
Vo
l.
5
2
,
No
.
5
,
Oc
t.
2
0
0
5
,
p
p
.
1
4
2
0
-
1
4
2
7
.
[1
8
]
M
.
S
.
Ba
ll
a
l,
Z.
J.
K
h
a
n
,
H.
M
.
S
u
ry
a
wa
n
sh
i
a
n
d
R.
L
.
S
o
n
o
li
k
a
r,
“
A
d
a
p
ti
v
e
Ne
u
ra
l
F
u
z
z
y
In
f
e
re
n
c
e
S
y
ste
m
f
o
r
th
e
De
tec
ti
o
n
o
f
In
ter
-
T
u
rn
In
su
latio
n
a
n
d
Be
a
rin
g
W
e
a
r
F
a
u
lt
s
in
In
d
u
c
ti
o
n
M
o
to
r
,
”
IEE
E
T
ra
n
s.
I
n
d
u
st
ria
l
El
e
c
tro
n
ics
,
V
o
l
.
5
4
,
N
o
.
1
,
F
e
b
.
2
0
0
7
,
p
p
.
2
5
0
–
2
5
8
.
[1
9
]
R.
H.
A
b
iy
e
v
a
n
d
O.
Ka
y
n
a
k
,
“
F
u
z
z
y
Wav
e
l
e
t
Ne
u
ra
l
Ne
tw
o
rk
s f
o
r
Id
e
n
t
if
ica
ti
o
n
a
n
d
C
o
n
tr
o
l
o
f
Dy
n
a
m
ic
P
lan
ts
-
A
No
v
e
l
S
tru
c
t
u
re
a
n
d
a
C
o
m
p
a
ra
ti
v
e
S
tu
d
y
”
,
IEE
E
T
ra
n
s.
I
n
d
u
stria
l
El
e
c
tro
n
ics
,
Vo
l.
5
5
,
No
.
8
,
A
u
g
.
2
0
0
8
,
p
p
.
3
1
3
3
–
3
1
4
0
.
[2
0
]
M
.
B.
K.
Bo
u
z
id
,
G
.
Ch
a
m
p
e
n
o
is,
N.
M
.
Be
ll
a
a
j,
L
.
S
ig
n
a
c
a
n
d
K.
Je
las
si,
“
A
n
E
ff
e
c
ti
v
e
N
e
u
ra
l
A
p
p
ro
a
c
h
f
o
r
th
e
A
u
t
o
m
a
ti
c
L
o
c
a
ti
o
n
o
f
S
tat
o
r
I
n
te
r
-
T
u
rn
F
a
u
l
ts
i
n
I
n
d
u
c
ti
o
n
M
o
t
o
r”
,
IEE
E
T
ra
n
s
.
I
n
d
u
stria
l
El
e
c
tro
n
i
c
s
,
Vo
l.
5
5
,
N
o
.
1
2
,
De
c
.
2
0
0
8
,
p
p
.
4
2
7
7
-
4
2
8
9
.
[2
1
]
A
.
S
id
d
i
q
u
e
a
n
d
G
.
S
.
Ya
d
a
v
a
,
“
A
Re
v
ie
w
o
f
S
tato
r
F
a
u
lt
M
o
n
it
o
rin
g
T
e
c
h
n
iq
u
e
s
o
f
In
d
u
c
ti
o
n
M
o
to
rs
,
”
IEE
E
T
ra
n
s
.
E
n
e
rg
y
Co
n
v
e
rs
io
n
,
Vo
l.
2
0
,
No
.
1
,
M
a
r.
2
0
0
5
,
p
p
.
1
0
6
–
1
1
4
.
[2
2
]
F
e
n
g
,
F
.
,
W
u
,
Y.,
W
u
,
Y.,
Nie
,
G
.
,
&
Ni,
R.
“
T
h
e
Eff
e
c
t
o
f
Artifi
c
ial
Ne
u
ra
l
Ne
t
w
o
rk
M
o
d
e
l
Co
m
b
in
e
d
w
it
h
S
ix
T
u
m
o
r
M
a
rk
e
rs i
n
A
u
x
il
iar
y
Dia
g
n
o
sis
o
f
L
u
n
g
Ca
n
c
e
r”
J
o
u
rn
a
l
o
f
M
e
d
ica
l
S
y
ste
ms
,
3
6
(5
)
,
2
9
7
3
-
2
9
8
0
,
2
0
1
2
[2
3
]
A
l
k
i
m
E,
G
ü
rb
ü
z
E,
Kil
iç
E.
“
A
fa
st
a
n
d
a
d
a
p
ti
v
e
a
u
to
ma
ted
d
ise
a
se
d
i
a
g
n
o
sis
me
t
h
o
d
wit
h
a
n
i
n
n
o
v
a
t
ive
n
e
u
ra
l
n
e
tw
o
rk
mo
d
e
l
Ne
u
ra
l
Ne
tw
o
rk
s.
3
3
:
8
8
–
9
6
,
2
0
1
2
.
[2
4
]
S
p
e
lt
L
,
A
n
d
e
rss
o
n
B,
Nilsso
n
J,
A
n
d
e
rss
o
n
R
.
P
r
o
g
n
o
stic
m
o
d
e
ls
fo
r
o
u
tc
o
m
e
f
o
ll
o
w
in
g
li
v
e
r
re
se
c
ti
o
n
f
o
r
c
o
lo
re
c
tal
c
a
n
c
e
r
m
e
tas
ta
se
s:
A
s
y
ste
m
a
ti
c
r
e
v
ie
w
.
Eu
r J
S
u
rg
On
c
o
l
.
3
8
:
1
6
–
2
4
,
2
0
1
2
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
7
,
No
.
3
,
Sep
tem
b
er
20
1
8
:
13
8
–
1
42
142
[2
5
]
M
o
rtaz
a
v
i
D,
Ko
u
z
a
n
i
A
,
S
o
lt
a
n
i
a
n
-
Zad
e
h
H.
S
e
g
m
e
n
tatio
n
o
f
m
u
lt
ip
le
sc
lero
sis
les
io
n
s
i
n
M
R
im
a
g
e
s:
a
re
v
ie
w
.
Ne
u
ro
ra
d
i
o
l
o
g
y
.
5
4
:
2
9
9
–
3
2
0
,
2
0
1
2
[2
6
]
S
iri
sta
t
id
is
C,
Ch
re
li
a
s
C,
P
o
u
l
iak
is
A
,
Ka
tsi
m
a
n
is
E,
Ka
ss
a
n
o
s
D.
Arti
fi
c
i
a
l
n
e
u
ra
l
n
e
two
rk
s
i
n
g
y
n
e
a
c
o
l
o
g
ic
a
l
d
ise
a
se
s
:
Cu
rr
e
n
t
a
n
d
p
o
ten
t
ia
l
fu
tu
re
a
p
p
li
c
a
ti
o
n
s.
M
e
d
S
c
iM
o
n
i
t.
1
6
:
2
3
1
–
2
3
6
,
2
0
1
0
.
[2
7
]
S
h
a
n
k
a
ra
c
h
a
r
y
a
,
Od
e
d
ra
D,
S
a
m
a
n
ta
S
,
V
id
y
a
rth
i
A
.
Co
mp
u
t
a
ti
o
n
a
l
in
telli
g
e
n
c
e
i
n
e
a
rly
d
i
a
b
e
t
e
s
d
ia
g
n
o
sis:
a
re
v
iew.
Re
v
Dia
b
e
t
S
tu
d
.
7
:
2
5
2
–
2
6
2
,
2
0
1
0
.
[2
8
]
P
a
c
e
F
,
S
a
v
a
rin
o
V
.
T
h
e
u
se
o
f
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
in
g
a
stro
e
n
tero
lo
g
y
:
th
e
e
x
p
e
rien
c
e
o
f
th
e
f
ir
st 1
0
y
e
a
rs
.
Eu
r
J
Ga
stro
e
n
ter
o
lHe
p
a
to
l
.
1
9
:
1
0
4
3
–
1
0
4
5
,
2
0
0
7
.
[2
9
]
Ka
ra
b
u
l
u
t
E,
Ib
rik
ç
i
T
.
Ef
fe
c
ti
v
e
d
iag
n
o
sis
o
f
c
o
ro
n
a
ry
a
rter
y
d
ise
a
se
u
sin
g
t
h
e
ro
tatio
n
f
o
re
st
e
n
se
m
b
le
m
e
th
o
d
.
J
M
e
d
S
y
st
.
3
6
:
3
0
1
1
–
3
0
1
8
,
2
0
1
2
.
[3
0
]
A
t
k
o
v
O,
G
o
ro
k
h
o
v
a
S
,
S
b
o
e
v
A
,
G
e
n
e
ro
z
o
v
E,
M
u
ra
se
y
e
v
a
E,
M
o
r
o
sh
k
in
a
S
a
n
d
C
h
e
rn
iy
N.
Co
ro
n
a
r
y
h
e
a
rt
d
ise
a
se
d
iag
n
o
sis
b
y
a
rti
f
icia
l
n
e
u
ra
l
n
e
two
rk
s
in
c
lu
d
in
g
g
e
n
e
ti
c
p
o
ly
m
o
rp
h
ism
s
a
n
d
c
li
n
ica
l
p
a
ra
m
e
ters
.
J
Ca
rd
io
l
.
5
9
:
1
9
0
–
1
9
4
,
2
0
1
2
.
[3
1
]
Uğ
u
z
H.
A
b
io
m
e
d
ica
l
s
y
ste
m
b
a
se
d
o
n
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
a
n
d
p
r
in
c
ip
a
l
c
o
m
p
o
n
e
n
t
a
n
a
ly
sis
f
o
r
d
iag
n
o
sis
o
f
th
e
h
e
a
rt
v
a
lv
e
d
ise
a
s
e
s.
J
M
e
d
S
y
st
.
3
6
:
6
1
–
7
2
,
2
0
1
2
.
[3
2
]
Öz
b
a
y
Y.
A
n
e
w
a
p
p
ro
a
c
h
to
d
e
tec
ti
o
n
o
f
ECG
a
rrh
y
th
m
ias
:
Co
m
p
lex
d
isc
re
te
w
a
v
e
let
tran
sf
o
r
m
b
a
se
d
c
o
m
p
lex
v
a
lu
e
d
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
.
J
M
e
d
S
y
st
.
3
3
:
4
3
5
–
4
4
5
,
2
0
0
9
.
6
3
1
–
6
3
6
,
2
0
1
2
.
[3
3
]
Bro
u
g
h
a
m
D,
Iv
a
n
o
v
a
G
,
G
o
tt
sc
h
a
lk
M
,
Co
ll
i
n
s
D,
E
u
sta
c
e
A
,
O’Co
n
n
o
r
R,
Ha
v
e
l
J.
A
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
s
f
o
r
c
las
si
f
ica
ti
o
n
in
m
e
tab
o
lo
m
ic
stu
d
ies
o
f
w
h
o
le
c
e
ll
s
u
sin
g
1
H
n
u
c
lea
r
m
a
g
n
e
ti
c
re
so
n
a
n
c
e
.
J
Bi
o
me
d
Bi
o
tec
h
n
o
l
.
2
0
1
1
:
1
5
8
0
9
4
,
2
0
1
1
.
[3
4
]
Ca
talo
g
n
a
M
,
Co
h
e
n
E,
F
ish
m
a
n
S
,
Ha
lp
e
rn
Z,
Ne
v
o
U,
Be
n
-
Ja
c
o
b
E.
Arti
fi
c
ia
l
n
e
u
ra
l
n
e
two
rk
s
b
a
se
d
c
o
n
tro
ll
e
r
fo
r
g
lu
c
o
se
mo
n
it
o
rin
g
d
u
rin
g
c
l
a
mp
tes
t
.
P
lo
S
On
e
.
7
:
e
4
4
5
8
7
,
2
0
1
2
.
[3
5
]
Ch
a
n
K,
L
in
g
S
,
Dill
o
n
T
,
Ng
u
y
e
n
H
.
Dia
g
n
o
sis
o
f
h
y
p
o
g
ly
c
e
m
ic
e
p
iso
d
e
s
u
sin
g
a
n
e
u
ra
l
n
e
t
w
o
rk
b
a
se
d
ru
le
d
isc
o
v
e
r
y
s
y
ste
m
.
Exp
e
rt S
y
st A
p
p
l.
3
8
:
9
7
9
9
–
9
8
0
8
,
2
0
1
1
.
[3
6
]
Da
y
h
o
ff
J,
De
leo
J.
Arti
fi
c
ia
l
Ne
u
r Ne
two
rk
s: Op
e
n
in
g
t
h
e
Bl
a
c
k
B
o
x
.
Ca
n
c
e
r
.
9
1
:
1
6
1
5
–
1
6
3
5
,
2
0
0
1
.
[3
7
]
Da
z
z
i
D,
T
a
d
d
e
i
F
,
G
a
v
a
rin
i
A
,
Ug
g
e
ri
E,
Ne
g
ro
R,
P
e
z
z
a
ro
ss
a
A
.
Th
e
c
o
n
tr
o
l
o
f
b
lo
o
d
g
l
u
c
o
se
in
th
e
c
rit
ica
l
d
iab
e
ti
c
p
a
ti
e
n
t:
a
n
e
u
ro
-
f
u
z
z
y
m
e
th
o
d
.
J
Dia
b
e
tCo
m
p
li
c
a
t
.
1
5
:
8
0
–
8
7
,
2
0
0
1
.
[3
8
]
d
e
Bru
ij
n
M
,
ten
B
o
sc
h
L
,
Ku
ik
D,
L
a
n
g
e
n
d
ij
k
J,
Lee
m
a
n
s
C,
V
e
rd
o
n
c
k
-
d
e
L
e
e
u
w
I.
A
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
a
n
a
ly
sis
to
a
ss
e
ss
h
y
p
e
rn
a
sa
li
t
y
in
p
a
ti
e
n
ts
trea
ted
f
o
r
o
ra
l
o
r
o
ro
p
h
a
ry
n
g
e
a
lca
n
c
e
r.
L
o
g
o
p
e
d
P
h
o
n
iatr
V
o
c
o
l.
3
6
:
1
6
8
–
1
7
4
,
2
0
1
1
.
[3
9
]
De
y
P
,
L
a
m
b
a
A
,
Ku
m
a
ri
S
,
M
a
rw
a
h
a
N.
A
p
p
li
c
a
ti
o
n
o
f
a
n
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
in
th
e
p
ro
g
n
o
sis
o
f
c
h
ro
n
ic
m
y
e
lo
id
leu
k
e
m
ia.
An
a
l
Qu
a
n
t
C
y
to
lHisto
l.
3
3
:
3
3
5
–
3
3
9
,
2
0
1
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.