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
0
43
~
1
0
51
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
0
43
-
1
0
51
1043
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Co
mpa
ra
tive a
na
ly
sis
o
n liver benc
hma
rk data
sets
a
nd
prediction
using
s
uperv
ised lea
rnin
g
t
echniqu
es
T
ila
k
a
churi Ba
la
k
rish
na
1
,
J
a
g
a
deeswa
ra
Ra
o
Anna
m
2
,
Da
s
a
ri
H
a
rit
ha
3
1
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
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
t
y
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
K
a
k
i
n
a
d
a
(
A
)
,
Jawah
a
r
l
a
l
N
e
h
r
u
T
e
c
h
n
o
l
o
g
i
c
a
l
U
n
i
v
e
r
si
t
y
K
a
k
i
n
a
d
a
(
JN
TU
K
)
,
K
a
k
i
n
a
d
a
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
(
A
I
&M
L
)
,
C
V
R
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
(
A)
,
Te
l
a
n
g
a
n
a
,
I
n
d
i
a
3
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
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
t
y
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
(A)
,
Jawah
a
r
l
a
l
N
e
h
r
u
T
e
c
h
n
o
l
o
g
i
c
a
l
U
n
i
v
e
r
si
t
y
K
a
k
i
n
a
d
a
(
JN
TU
K
)
,
K
a
k
i
n
a
d
a
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
28
,
2
0
2
4
R
ev
is
ed
J
u
n
27
,
2
0
2
4
Acc
ep
ted
J
u
l 1
4
,
202
4
Dise
a
se
d
iag
n
o
sis
is
m
o
st
c
h
a
ll
e
n
g
in
g
tas
k
to
d
a
y
.
Diffe
re
n
t
d
a
tas
e
ts
a
re
a
v
a
il
a
b
le
in
we
b
s
o
u
rc
e
th
a
t
c
o
n
tain
s
imp
o
rtan
t
fe
a
t
u
re
s
to
d
iag
n
o
se
t
h
e
d
ise
a
se
s.
Th
is
p
a
p
e
r
e
x
p
l
o
re
s
d
if
fe
re
n
t
c
las
sifica
ti
o
n
a
lg
o
rit
h
m
s
o
n
m
e
d
ica
l
li
v
e
r
b
e
n
c
h
m
a
rk
d
a
tas
e
ts
li
k
e
BU
P
A
a
n
d
In
d
ia
n
Li
v
e
r
p
a
ti
e
n
t
d
a
tas
e
t
(IL
P
D).
Th
e
IL
P
D
is
b
e
st
fit
f
o
r
th
e
m
o
d
e
l
a
n
d
a
lso
g
iv
e
s
h
ig
h
c
las
sifier
a
c
c
u
ra
c
y
.
In
p
r
o
p
o
se
d
m
o
d
e
l
t
h
e
fo
ll
o
wi
n
g
c
las
sifiers
li
k
e
Na
ï
v
e
Ba
y
e
s
(NB)
,
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(
S
VM)
,
K
-
n
e
a
re
st
n
e
ig
h
b
o
r
(KN
N)
,
d
e
c
isio
n
tree
(DT)
,
a
n
d
ra
n
d
o
m
fo
re
st
(
RF
)
c
las
sifica
ti
o
n
,
m
u
lt
i
-
la
y
e
r
p
e
rc
e
p
tro
n
(M
LP
)
,
a
rti
ficia
l
n
e
u
ra
l
n
e
two
r
k
(AN
N)
,
d
e
e
p
b
e
li
e
f
n
e
tw
o
rk
(
DBN
)
a
n
d
p
ro
b
a
b
il
isti
c
n
e
u
ra
l
n
e
two
rk
(P
N
N)
a
re
u
se
d
.
T
h
e
re
su
lt
s
s
h
o
wn
t
h
a
t
ILP
D
is
b
e
st
d
a
tas
e
t
fo
r
a
ll
c
las
sifiers
a
n
d
R
F
c
las
sifica
ti
o
n
i
n
p
a
rti
c
u
l
a
r
is
b
e
st
c
las
sifier.
K
ey
w
o
r
d
s
:
C
las
s
if
icatio
n
L
iv
er
d
iag
n
o
s
is
Ma
ch
in
e
lear
n
in
g
Me
d
ical
d
ata
m
in
in
g
So
f
t
-
co
m
p
u
ti
n
g
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
T
ilak
ac
h
u
r
i Balak
r
is
h
n
a
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
in
ee
r
in
g
,
U
n
iv
er
s
ity
C
o
lleg
e
o
f
E
n
g
in
ee
r
in
g
Kak
in
ad
a
(
A)
J
awa
h
ar
lal
Neh
r
u
T
ec
h
n
o
lo
g
ic
al
Un
iv
er
s
ity
Kak
in
ad
a
(
J
NT
UK)
Kak
in
ad
a,
An
d
h
r
a
Pra
d
esh
,
I
n
d
ia
E
m
ail: b
alak
r
is
h
n
ag
ec
@
g
m
ail
.
co
m
1.
I
NT
RO
D
UCT
I
O
N
Me
d
ical
d
atam
in
in
g
is
a
p
r
o
m
in
en
t
r
esear
ch
ar
ea
to
ex
tr
ac
t
th
e
m
ea
n
in
g
f
u
l
d
ata
f
r
o
m
th
e
g
iv
en
f
ea
tu
r
es.
A
k
ey
ch
allen
g
e
i
s
to
d
iag
n
o
s
is
th
e
d
is
ea
s
e
[
1
]
.
I
n
ea
r
lier
d
ay
s
d
o
cto
r
s
o
b
s
er
v
es
co
m
p
lete
in
f
o
r
m
atio
n
ab
o
u
t
th
e
test
s
an
d
co
m
e
to
k
n
o
w
th
e
co
n
clu
s
io
n
th
at
th
e
p
er
s
o
n
is
d
iag
n
o
s
ed
with
s
o
m
e
d
is
ea
s
e.
No
w
a
d
ay
s
,
esp
ec
ially
in
m
e
d
ical
f
ield
i
s
d
ig
itized
an
d
n
e
w
in
n
o
v
atio
n
s
tr
ateg
ies
co
m
es
in
t
o
th
e
p
ictu
r
e
to
d
iag
n
o
s
is
th
e
d
is
ea
s
e
with
o
u
t
h
u
m
an
i
n
ter
v
en
tio
n
.
On
e
s
u
c
h
in
n
o
v
atio
n
is
class
if
icatio
n
.
I
n
th
is
tech
n
iq
u
e
t
h
e
m
o
d
el
is
tr
ain
ed
with
s
o
m
e
k
n
o
wn
s
am
p
les
alo
n
g
with
th
e
class
lab
el
o
r
d
ec
is
io
n
.
W
h
e
n
a
n
ew
s
am
p
le
is
s
u
p
p
lied
to
th
e
m
o
d
el,
b
ased
o
n
th
e
tr
ain
in
g
s
am
p
les
th
e
m
o
d
el
wil
l
g
en
er
ate
th
e
d
ec
is
io
n
r
es
u
lt.
L
iv
er
d
is
ea
s
e
ac
co
u
n
ts
f
o
r
two
m
ill
io
n
d
ea
th
s
p
er
y
ea
r
an
d
is
r
e
s
p
o
n
s
ib
le
1
o
u
t
o
f
ev
er
y
2
5
d
ea
th
s
wo
r
ld
wid
e.
C
las
s
if
icatio
n
o
f
L
iv
er
d
is
ea
s
e
is
th
e
m
o
s
t
ch
allen
g
in
g
task
th
is
p
ap
er
ex
p
lo
r
es
th
e
f
o
llo
win
g
t
r
ad
itio
n
a
l
class
if
icatio
n
alg
o
r
ith
m
s
[2
]
lik
e
Naïv
e
B
ay
es
(
NB
)
,
K
-
n
ea
r
est
n
eig
h
b
o
u
r
(
KNN)
,
d
ec
is
io
n
tr
ee
(
DT
)
,
r
a
n
d
o
m
f
o
r
est
(
R
F)
class
if
icatio
n
m
o
d
el
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
(
SVM)
o
n
th
e
o
th
er
h
an
d
s
o
f
t
co
m
p
u
tin
g
-
b
ased
class
if
icatio
n
alg
o
r
ith
m
s
[3
]
lik
e
m
u
lti
-
lay
er
p
er
ce
p
tr
o
n
(
ML
P),
ar
tific
ial
n
eu
r
al
n
etwo
r
k
(
ANN)
,
d
ee
p
b
elief
n
etwo
r
k
(
DB
N)
an
d
p
r
o
b
a
b
ilis
tic
n
eu
r
al
n
etwo
r
k
(
PNN)
,
T
h
e
f
o
llo
win
g
Fig
u
r
e
1
d
ep
i
cts
c
lass
if
icat
io
n
o
f
s
u
p
er
v
is
ed
lear
n
in
g
tech
n
i
q
u
e
s
.
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
0
43
-
1
0
51
1044
Fig
u
r
e
1
.
C
lass
if
icatio
n
o
f
s
u
p
er
v
is
ed
lear
n
in
g
tech
n
iq
u
es
2.
RE
L
AT
E
D
WO
RK
I
n
R
elate
d
w
o
r
k
b
est
class
if
ier
s
[4
]
lik
e
SVM,
KNN,
DT
,
SVM,
PNN
,
an
d
ML
P
ar
e
id
en
tifie
d
esp
ec
i
ally
in
h
ea
lth
-
r
elate
d
d
atasets
.
T
h
ese
cla
s
s
if
ier
s
wer
e
f
u
r
th
er
class
if
ied
in
to
b
o
th
tr
ad
itio
n
al
an
d
s
o
f
t
-
co
m
p
u
tin
g
b
ased
an
d
th
en
tech
n
iq
u
es
w
ill b
e
ap
p
lied
to
liv
e
r
b
en
ch
m
ar
k
d
atasets
.
2
.
1
.
T
ra
ditio
na
l c
la
s
s
if
ica
t
io
n a
lg
o
rit
hm
s
2
.
1
.
1
.
NB
I
t
i
s
a
s
u
p
e
r
v
i
s
e
d
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
w
o
r
k
e
d
f
o
r
c
l
a
s
s
i
f
i
c
a
t
i
o
n
a
l
g
o
r
i
t
h
m
b
a
s
e
d
o
n
B
a
y
e
s
’
t
h
e
o
r
e
m
[
5
]
b
ased
o
n
p
r
io
r
k
n
o
wled
g
e
wh
i
ch
d
ep
e
n
d
s
o
n
c
o
n
d
itio
n
al
p
r
o
b
ab
ilit
y
.
B
ay
es’
th
eo
r
em
f
o
r
m
u
lae
is
g
iv
en
as:
(
|
)
=
(
(
|
)
∗
(
)
)
/
(
(
)
)
w
er
e
,
Po
s
ter
io
r
p
r
o
b
a
b
ilit
y
is
g
iv
en
as P(
A|
B
)
th
at
is
h
y
p
o
th
esis
o
f
A
o
n
ev
e
n
t B.
T
h
e
L
ik
elih
o
o
d
p
r
o
b
a
b
ilit
y
i.e
.
,
ev
id
en
ce
g
iv
en
th
at
h
y
p
o
th
e
s
is
is
tr
u
e.
Ad
v
an
tag
e:
−
I
t is a
s
im
p
le
class
if
ier
wo
r
k
s
o
n
s
m
all
d
ataset.
2
.
1
.
2
.
SVM
T
h
e
SVM
is
a
ty
p
e
o
f
s
u
p
er
v
is
ed
m
ac
h
in
e
lear
n
in
g
t
ec
h
n
iq
u
e
th
at
m
a
y
b
e
u
s
ed
f
o
r
b
o
t
h
class
if
icatio
n
an
d
r
eg
r
ess
io
n
task
s
.
I
ts
g
o
al
is
to
id
en
tify
a
h
y
p
er
p
lan
e
in
a
s
p
ac
e
with
N
d
im
en
s
io
n
s
th
at
ef
f
ec
tiv
ely
s
ep
ar
ates
th
e
d
ata
p
o
in
ts
in
to
d
is
cr
ete
class
e
s
.
T
h
e
s
ize
o
f
th
e
h
y
p
er
p
lan
e
is
d
eter
m
in
ed
b
y
th
e
n
u
m
b
er
o
f
f
ea
tu
r
es.
In
Fig
u
r
e
2
d
ep
icts
SVM
c
lass
if
ier
.
Fig
u
r
e
2
.
SVM
c
lass
if
ier
Ad
v
an
tag
es o
f
SVM:
i)
SVMs a
r
e
h
ig
h
ly
ef
f
ec
tiv
e
i
n
h
an
d
lin
g
h
ig
h
-
d
im
en
s
io
n
al
i
n
s
tan
ce
s
.
ii)
T
h
e
ap
p
r
o
ac
h
d
em
o
n
s
tr
ates
m
em
o
r
y
ef
f
icien
c
y
b
y
u
tili
zin
g
a
lim
ited
co
llectio
n
o
f
tr
ai
n
in
g
p
o
in
ts
,
r
ef
er
r
ed
to
as su
p
p
o
r
t
v
ec
to
r
s
,
in
th
e
d
e
cisi
o
n
f
u
n
ctio
n
.
iii)
I
t
is
p
o
s
s
ib
le
to
s
p
ec
if
y
d
if
f
er
en
t
k
er
n
el
f
u
n
ctio
n
s
f
o
r
th
e
d
ec
is
io
n
f
u
n
ctio
n
s
,
an
d
it
is
also
f
ea
s
ib
le
to
s
p
ec
if
y
cu
s
to
m
ized
k
e
r
n
els.
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
C
o
mp
a
r
a
tive
a
n
a
lysi
s
o
n
liver b
en
ch
ma
r
k
d
a
ta
s
ets a
n
d
p
r
ed
ictio
n
…
(
Til
a
ka
ch
u
r
i B
a
l
a
kris
h
n
a
)
1045
B
attin
en
i
et
a
l.
[
6
]
s
u
g
g
ested
th
e
SVM
a
class
if
icatio
n
ap
p
r
o
ac
h
to
p
r
ed
ict
th
e
d
em
en
tia
t
o
ac
h
iev
e
o
p
tim
ized
r
esu
lts
.
T
h
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
e
x
h
ib
its
an
ac
cu
r
ac
y
o
f
6
8
.
7
5
%
an
d
a
p
r
ec
is
io
n
o
f
6
4
.
1
8
.
Dem
e
n
tia
a
d
is
o
r
d
er
ca
u
s
ed
b
y
b
r
ain
d
i
s
ea
s
e
o
r
in
ju
r
y
is
o
n
e
o
f
th
e
m
ajo
r
h
ea
lth
is
s
u
es
ch
allen
g
ed
b
y
h
ea
lth
ex
p
e
r
ts
.
I
t
was
id
en
tifie
d
th
e
esp
ec
ially
th
e
s
en
io
r
citizen
p
e
o
p
le
wh
o
s
e
ag
e
is
g
r
ea
ter
th
an
6
0
.
I
t
r
esu
lts
lack
o
f
m
em
o
r
y
s
k
ills
an
d
p
er
f
o
r
m
d
aily
ac
tiv
ities
.
Fo
r
th
e
las
t
t
wo
d
ec
ad
es
lo
ts
o
f
r
esear
ch
m
ad
e
b
y
co
m
p
u
ter
s
cien
tis
t
s
an
d
h
ea
lth
ex
p
er
ts
f
o
r
th
is
d
is
ea
s
e.
S
till
,
th
er
e
i
s
an
u
r
g
e
f
o
r
d
etec
tio
n
o
f
d
e
m
en
tia.
E
C
G
d
ata
co
llected
b
y
t
h
e
Kar
d
ia
Mo
b
i
le
ap
p
ca
n
ac
cu
r
ately
f
o
r
ec
ast
th
e
r
is
k
o
f
ca
r
d
iac
illn
ess
.
T
h
e
s
tu
d
y
[
7
]
r
esu
lts
r
ev
ea
led
th
at
SVM
c
lass
if
ier
s
u
r
p
ass
ed
tr
ad
itio
n
al
s
tatis
tica
l
m
eth
o
d
s
an
d
ac
h
ie
v
ed
ac
c
u
r
ac
y
to
p
r
ed
ict
th
e
r
is
k
o
f
h
ea
r
t
illn
ess
.
2
.
1
.
3
.
K
NN
c
la
s
s
if
ier
Th
is
class
if
ier
s
er
v
es
as
s
u
p
er
v
is
ed
l
ea
r
n
in
g
tech
n
iq
u
e.
T
h
e
KNN
m
eth
o
d
u
tili
ze
s
th
e
s
im
ilar
ity
b
etwe
en
a
n
ew
s
am
p
le
an
d
th
e
tr
ain
in
g
ex
a
m
p
les
to
p
r
e
d
ict
th
e
r
esu
lts
o
f
th
e
n
ew
s
am
p
le
as
b
ein
g
clo
s
est
o
r
m
o
s
t similar
to
th
e
in
s
tan
ce
s
in
th
e
tr
ain
in
g
s
et.
Fig
u
r
e
3
d
ep
icts
KNN
c
la
s
s
if
ier
.
C
ar
d
iac
illn
ess
i
s
th
e
p
r
im
ar
y
ca
u
s
e
o
f
d
ea
th
s
in
I
n
d
ia.
T
h
e
r
ec
o
r
d
e
d
m
o
r
tality
r
ate
in
AP
ac
co
u
n
ted
f
o
r
3
2
%
o
f
all
d
ea
th
s
,
wh
ich
i
s
co
m
p
ar
ab
le
to
th
e
r
ates
o
b
s
er
v
ed
in
C
an
ad
a
(
3
5
%)
an
d
t
h
e
USA.
T
h
er
ef
o
r
e,
it
is
n
ec
ess
ar
y
to
h
av
e
a
d
ec
i
s
io
n
s
u
p
p
o
r
t
s
y
s
tem
th
at
p
r
o
v
id
es
g
u
id
an
ce
o
n
im
p
lem
en
ti
n
g
k
ey
p
r
ev
e
n
tativ
e
m
ea
s
u
r
es
in
o
r
d
er
to
p
r
ev
en
t
th
ese
elev
ated
m
o
r
tality
r
ates.
T
h
e
au
th
o
r
p
r
o
p
o
s
ed
th
e
co
m
b
in
ed
K
NN
an
d
g
en
etic
alg
o
r
ith
m
(
GA)
[
8
]
is
th
e
o
u
ts
tan
d
in
g
class
if
ier
c
o
m
p
ar
ed
with
o
th
e
r
s
to
d
iag
n
o
s
e
h
ea
r
t
d
is
ea
s
e.
T
h
e
p
r
o
p
o
s
ed
r
esu
lts
s
h
o
w
h
i
g
h
er
class
if
icatio
n
ac
cu
r
ac
y
f
o
r
m
an
y
d
atasets
p
ar
ticu
lar
ly
h
e
ar
t
d
is
ea
s
e
f
o
r
A.
P.
A
co
m
p
a
r
ativ
e
a
n
aly
s
is
was
co
n
d
u
cted
to
ca
teg
o
r
ize
an
d
p
r
ed
ict
ca
s
es
o
f
h
e
ar
t
d
is
ea
s
e
u
s
in
g
s
ev
er
al
class
if
ier
s
[
9
]
.
T
h
e
g
o
al
was
to
ac
h
iev
e
ac
c
u
r
ate
class
if
icatio
n
wh
ile
u
s
in
g
as
f
ew
attr
ib
u
tes
as
p
o
s
s
ib
le.
T
h
e
d
ataset
co
m
p
r
is
es
a
to
tal
o
f
7
6
attr
ib
u
tes,
wh
ich
in
clu
d
es
th
e
class
a
ttrib
u
te.
T
h
e
r
esu
lts
in
d
icate
th
at
KNN
o
u
tp
er
f
o
r
m
s
J
R
ip
,
J
4
8
,
an
d
d
ec
is
io
n
tab
le
,
m
ak
i
n
g
it th
e
m
o
s
t e
f
f
ec
tiv
e
class
if
ier
.
Fig
u
r
e
3
.
KNN
c
lass
if
ier
2
.
1
.
4
.
DT
I
t
is
a
b
i
n
ar
y
tr
ee
[
10
]
is
a
k
in
d
o
f
s
u
p
er
v
is
ed
lear
n
i
n
g
alg
o
r
ith
m
th
at
is
s
k
illed
in
s
o
lv
in
g
r
eg
r
ess
io
n
as
well
as
class
if
icatio
n
ch
allen
g
es.
Ho
wev
er
,
it
is
m
o
s
tly
u
s
ed
f
o
r
d
ea
lin
g
with
clas
s
if
icatio
n
.
A
tr
ee
-
s
tr
u
ctu
r
ed
class
if
ier
is
u
s
ed
,
in
clu
d
in
g
in
ter
n
al
n
o
d
es
s
ig
n
if
y
i
n
g
d
ataset
f
ea
tu
r
es,
b
r
an
c
h
es
in
d
icatin
g
d
ec
is
io
n
r
u
les,
an
d
ea
c
h
leaf
n
o
d
e
in
d
icatin
g
a
r
esu
lt.
In
Fig
u
r
e
4
s
h
o
w
th
e
m
o
d
el
o
f
DT
.
A.
At
t
ribute
s
elec
t
io
n m
ea
s
ures
(
AS
M
)
in
DT
W
h
en
im
p
lem
en
tin
g
a
DT
,
a
k
ey
ch
allen
g
e
a
r
is
es
with
th
e
s
elec
tio
n
o
f
th
e
m
o
s
t
ap
p
r
o
p
r
iat
e
attr
ib
u
te
f
o
r
b
o
th
t
h
e
r
o
o
t
n
o
d
e
a
n
d
t
h
e
s
u
b
-
n
o
d
es.
I
n
o
r
d
er
t
o
tack
le
th
ese
is
s
u
es,
th
e
u
tili
za
tio
n
o
f
a
tech
n
iq
u
e
ca
lled
ASM
m
ig
h
t
b
e
e
m
p
lo
y
e
d
.
Usi
n
g
th
is
m
etr
ic,
w
e
ca
n
r
ea
d
ily
d
eter
m
in
e
th
e
o
p
tim
al
attr
ib
u
te
f
o
r
t
h
e
n
o
d
es
i
n
th
e
tr
ee
.
T
h
er
e
ar
e
two
wid
ely
u
s
ed
ap
p
r
o
ac
h
es f
o
r
ASM
(
1
)
an
d
(
2
)
,
n
a
m
ely
:
i
n
f
o
r
m
atio
n
g
ain
,
(
,
)
=
(
)
−
∑
1
(
1
)
(
1
)
g
in
i
i
n
d
ex
,
=
−
∑
(
)
.
2
(
)
(
2
)
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
0
43
-
1
0
51
1046
Hig
h
e
n
t
r
o
p
y
:
m
o
r
e
u
n
ce
r
ta
in
t
y
L
o
w
e
n
tr
o
p
y
:
m
o
r
e
p
r
e
d
i
cta
b
i
l
ity
Fig
u
r
e
4
.
D
T
class
if
ier
2
.
1
.
5
.
RF
cla
s
s
if
ier
I
t
is
a
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
e
em
p
lo
y
ed
f
o
r
s
o
lv
in
g
b
o
t
h
r
eg
r
ess
io
n
an
d
class
if
icatio
n
p
r
o
b
lem
s
.
I
t
em
p
lo
y
s
e
n
s
em
b
le
lear
n
i
n
g
,
a
m
eth
o
d
th
at
c
o
m
b
in
es
m
u
ltip
le
class
if
ier
s
to
s
o
lv
e
ch
allen
g
in
g
p
r
o
b
lem
s
s
h
o
ws
in
Fig
u
r
e
5.
T
h
e
RF
m
eth
o
d
d
eter
m
in
es
th
e
r
esu
lt
b
y
r
ely
in
g
o
n
th
e
p
r
ed
ictio
n
s
m
ad
e
b
y
th
e
DT
s
.
I
t
m
ak
es
p
r
ed
ictio
n
s
b
y
ca
lcu
l
atin
g
th
e
av
er
a
g
e
o
r
m
ea
n
o
f
t
h
e
o
u
tp
u
t
g
en
e
r
ated
b
y
s
ev
er
a
l
tr
ee
s
.
E
n
h
an
cin
g
th
e
q
u
an
tity
o
f
tr
ee
s
en
h
an
ce
s
th
e
ac
cu
r
ac
y
o
f
th
e
r
esu
lt.
T
o
p
r
ed
ict
ch
r
o
n
ic
k
id
n
ey
d
is
ea
s
e
(
C
KD)
,
d
ata
m
in
in
g
ap
p
r
o
ac
h
es
ar
e
ap
p
lied
.
T
h
ey
s
u
g
g
ested
th
at
th
e
RF
cla
s
s
i
f
icat
io
n
ap
p
r
o
ac
h
[
1
1
]
is
th
e
m
o
s
t
ap
p
r
o
p
r
iate
c
lass
if
ier
wh
en
co
m
p
ar
ed
to
o
t
h
er
tech
n
iq
u
es
lik
e
J
4
8
,
NB
t
r
ee
,
an
d
R
E
P
t
r
ee
,
b
ased
o
n
th
e
ac
cu
r
ac
y
o
f
ca
te
g
o
r
izin
g
ex
am
p
les.
T
h
e
KNN
c
lass
if
ier
an
d
l
o
g
is
tic
r
eg
r
ess
io
n
[
1
2
]
class
if
ier
is
o
u
ts
tan
d
in
g
class
if
ie
r
co
m
p
a
r
ed
to
th
e
SVM
an
d
RF
class
if
ier
.
T
h
e
f
o
r
m
er
ac
h
iev
ed
1
0
0
%
ac
cu
r
ac
y
i
n
th
e
C
KD
d
ataset
an
d
8
5
%
ac
cu
r
ac
y
in
th
e
h
ea
r
t
d
is
ea
s
e
d
ataset.
T
h
e
s
u
g
g
ested
m
o
d
el
ad
d
itio
n
ally
s
u
g
g
ested
em
p
lo
y
in
g
p
r
i
n
cip
al
co
m
p
o
n
e
n
t
an
aly
s
is
(
PC
A)
,
a
tech
n
iq
u
e
u
s
ed
to
d
ec
r
ea
s
e
th
e
n
u
m
b
er
o
f
f
ea
tu
r
es in
a
d
at
aset.
T
h
is
p
r
o
p
o
s
ed
s
tu
d
y
[
1
3
]
em
p
lo
y
s
m
ac
h
in
e
lear
n
in
g
m
et
h
o
d
s
,
in
clu
d
in
g
K
NN
,
DT
,
an
d
RF
,
to
p
r
ed
ict
an
d
an
aly
ze
t
h
e
Pima
I
n
d
ian
d
iab
etes
d
ataset.
T
h
e
f
i
n
d
in
g
s
in
d
icate
d
th
at
th
e
RF
m
o
d
el
h
ad
s
u
p
er
i
o
r
p
er
f
o
r
m
an
ce
,
with
an
ac
cu
r
ac
y
r
ate
o
f
0
.
8
4
.
T
ar
eq
[
1
4
]
r
ec
o
m
m
en
d
s
u
s
in
g
th
e
RF
class
if
i
er
tech
n
iq
u
e
o
n
th
e
s
leep
h
ea
lth
an
d
life
s
ty
le
(
SH
L
)
d
at
aset,
wh
ich
co
n
s
is
ts
o
f
t
h
r
ee
class
es:
in
s
o
m
n
ia,
s
leep
ap
n
ea
,
an
d
n
o
n
e
,
a
n
d
th
is
class
if
ier
ac
h
iev
es 8
8
% a
cc
u
r
ac
y
.
Fig
u
r
e
5
.
RF
class
if
ier
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
C
o
mp
a
r
a
tive
a
n
a
lysi
s
o
n
liver b
en
ch
ma
r
k
d
a
ta
s
ets a
n
d
p
r
ed
ictio
n
…
(
Til
a
ka
ch
u
r
i B
a
l
a
kris
h
n
a
)
1047
2
.
2
.
So
f
t
-
c
o
m
pu
t
ing
c
la
s
s
if
ica
t
io
n a
lg
o
ri
t
hm
s
2
.
2
.
1
.
MLP
I
t
is
a
f
u
lly
co
n
n
ec
ted
f
ee
d
-
f
o
r
war
d
n
eu
r
al
n
etwo
r
k
co
n
tain
s
at
least
th
r
ee
lay
er
s
o
n
e
is
in
p
u
t
lay
er
;
s
ec
o
n
d
h
id
d
en
la
y
er
an
d
last
lay
er
is
o
u
tp
u
t
lay
er
.
T
h
is
m
o
d
el
ac
ce
p
ts
m
o
r
e
th
a
n
o
n
e
h
i
d
d
en
lay
er
also
.
E
ac
h
u
n
it
with
in
a
lay
er
is
co
n
n
ec
t
ed
to
u
n
its
in
ad
jace
n
t
lev
els,
allo
win
g
f
o
r
h
o
m
o
g
e
n
eo
u
s
c
o
m
p
u
tin
g
f
r
o
m
th
e
in
p
u
t
lay
er
to
t
h
e
o
u
tp
u
t
la
y
er
s
h
o
wn
in
Fig
u
r
e
6
.
Saf
ar
et
a
l.
[1
5
]
ML
P
n
etwo
r
k
to
id
en
ti
f
y
tr
en
d
s
in
v
ar
io
u
s
h
ea
lth
ca
r
e
d
atasets
lik
e
Diab
etes,
Hea
r
t
Dis
ea
s
e,
B
r
ea
s
t
C
an
ce
r
,
L
iv
er
,
an
d
Par
k
in
s
o
n
h
av
e
a
ch
iev
ed
ac
cu
r
ac
ies
o
f
9
7
.
6
%,
9
4
.
7
3
%,
9
8
.
7
4
%,
7
3
%,
an
d
1
0
0
%
r
es
p
ec
tiv
ely
u
s
in
g
v
a
r
io
u
s
ML
a
lg
o
r
ith
m
s
s
u
ch
as
RF
,
DT
,
ex
tr
a
tr
ee
s
,
NB
,
GB
o
o
s
t
,
KNN
,
LR
,
MLP
,
E
XGBo
o
s
t
,
an
d
SVM
.
Fig
u
r
e
6
.
MLP
class
if
ier
2
.
2
.
2
.
ANN
I
n
late
9
0
’
s
a
n
d
ea
r
ly
2
0
th
ce
n
tu
r
y
m
ajo
r
ity
o
f
r
esear
ch
wo
r
k
ca
r
r
ied
o
u
t
in
th
e
ar
ea
o
f
ANN
[
1
6
]
.
No
w,
n
eu
r
al
n
etwo
r
k
s
h
av
e
b
ee
n
u
s
ed
i
n
d
if
f
er
en
t
f
ield
s
o
f
r
esear
ch
ar
ea
s
wh
ich
in
clu
d
e
d
ef
en
s
e,
ae
r
o
s
p
ac
e,
ex
p
er
t
s
y
s
tem
s
,
r
ec
o
m
m
e
n
d
at
io
n
s
y
s
tem
s
an
d
m
an
y
.
Ozy
il
m
az
an
d
Yild
ir
im
[
1
7
]
a
h
y
b
r
id
n
etwo
r
k
co
n
ic
s
ec
tio
n
f
u
n
ctio
n
n
eu
r
al
n
etwo
r
k
(
C
SF
NN
)
h
as
th
e
b
est
clas
s
if
ier
f
o
r
d
iag
n
o
s
in
g
h
ep
atitis
.
E
ar
ly
o
v
e
r
ML
P
is
th
e
g
o
o
d
c
h
o
ice
f
o
r
t
h
e
d
atase
t
b
u
t
later
r
ad
ial
b
asis
f
u
n
ctio
n
(
RBF
)
p
r
o
d
u
ce
s
p
r
o
m
is
in
g
r
esu
lts
th
e
d
r
awb
ac
k
o
f
th
ese
m
eth
o
d
s
is
r
an
d
o
m
weig
h
t in
itializin
g
in
tr
ain
in
g
.
I
n
Fig
u
r
e
7
s
h
o
ws th
e
ANN
c
lass
if
ier
.
Fig
u
r
e
7
.
ANN
class
if
ier
2
.
2
.
3
.
D
BN
DB
N
s
ar
e
u
tili
ze
d
to
tac
k
le
th
e
lim
itatio
n
s
o
f
tr
ad
itio
n
a
l
n
eu
r
al
n
etwo
r
k
s
in
d
ee
p
h
ier
ar
ch
ical
n
etwo
r
k
s
.
Fo
r
in
s
tan
ce
,
d
ela
y
ed
lear
n
in
g
,
g
ettin
g
tr
ap
p
ed
in
lo
ca
l
m
in
im
a
d
u
e
to
i
n
a
d
eq
u
ate
p
a
r
am
eter
s
elec
tio
n
,
an
d
n
ec
ess
itatin
g
a
s
u
b
s
tan
tial
am
o
u
n
t
o
f
tr
ain
in
g
d
atasets
.
T
h
e
DB
N
m
eth
o
d
i
s
a
tech
n
iq
u
e
u
s
ed
f
o
r
u
n
s
u
p
er
v
is
ed
p
r
o
b
ab
ilis
tic
d
ee
p
lear
n
in
g
s
h
o
wn
i
n
Fig
u
r
e
8
.
E
lk
h
o
ly
et
a
l.
[1
8
]
p
r
o
p
o
s
ed
a
DB
N
clas
s
if
ier
th
at
ac
cu
r
ately
p
r
ed
icts
C
KD
with
an
ac
cu
r
ac
y
p
er
ce
n
tag
e
o
f
9
8
.
5
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
u
tili
ze
s
a
DB
N
with
s
o
f
tm
ax
class
if
ier
an
d
th
e
ca
teg
o
r
ical
cr
o
s
s
-
en
tr
o
p
y
as th
e
lo
s
s
f
u
n
ctio
n
.
In
F
ig
u
r
e
8
d
ep
icts
th
e
m
o
d
el
o
f
DB
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
0
43
-
1
0
51
1048
Fig
u
r
e
8
.
DB
N
class
if
ier
2
.
2
.
4
.
P
NN
I
t
is
a
ty
p
e
o
f
f
ee
d
f
o
r
war
d
n
e
u
r
al
n
etwo
r
k
th
at
is
s
p
ec
if
ically
d
esig
n
ed
f
o
r
th
e
p
u
r
p
o
s
e
o
f
s
o
lv
in
g
p
atter
n
r
ec
o
g
n
itio
n
an
d
class
if
icatio
n
task
s
[
1
9
]
.
T
h
e
PN
N
ap
p
r
o
ac
h
a
p
p
r
o
x
im
ates
th
e
p
ar
en
t
p
r
o
b
ab
ilit
y
d
is
tr
ib
u
tio
n
f
u
n
ctio
n
o
f
ea
c
h
c
lass
b
y
u
tili
zin
g
a
n
o
n
-
p
ar
am
e
tr
ic
f
u
n
cti
o
n
a
n
d
Par
ze
n
win
d
o
w.
T
h
e
p
r
o
b
a
b
ilit
y
d
en
s
ity
f
u
n
cti
o
n
(
PDF)
o
f
ea
ch
class
is
s
u
b
s
eq
u
en
tly
u
tili
ze
d
to
esti
m
ate
th
e
class
p
r
o
b
ab
ilit
y
o
f
n
ewly
in
p
u
tted
d
ata
[
2
0
]
.
B
ay
es
’
r
u
le
is
u
s
ed
to
d
eter
m
in
e
th
e
cla
s
s
h
av
in
g
th
e
h
ig
h
est
p
o
s
ter
io
r
p
r
o
b
a
b
ilit
y
f
o
r
th
e
n
ew
in
p
u
t
d
ata.
T
h
is
s
tr
ateg
y
r
ed
u
ce
s
th
e
lik
elih
o
o
d
o
f
m
is
class
if
icatio
n
.
In
Fig
u
r
e
9
d
ep
icts
th
e
PNN
c
lass
if
ier
.
PNN
a
lg
o
r
ith
m
[
21
]
g
iv
es
th
e
b
etter
class
if
icati
o
n
ac
cu
r
ac
y
p
er
ce
n
tag
e
o
f
9
6
.
7
%,
co
m
p
a
r
ed
to
alg
o
r
ith
m
s
lik
e
SVM,
R
B
F
,
a
n
d
ML
P
o
n
C
KD
.
Fem
il
an
d
J
ay
a
[
22
]
p
r
o
p
o
s
ed
PNN
class
if
ier
to
ac
cu
r
ately
ca
teg
o
r
ize
th
e
s
tag
es
o
f
s
k
in
lesi
o
n
s
in
a
s
k
in
ca
n
ce
r
d
at
aset.
T
h
e
en
tire
p
r
o
ject
was
im
p
lem
en
ted
u
s
in
g
MA
T
L
AB
,
an
d
th
e
r
esu
lts
d
em
o
n
s
tr
ate
th
a
t
th
e
p
r
o
p
o
s
ed
m
eth
o
d
ac
h
iev
es
id
ea
l
o
u
tco
m
es
with
a
m
ax
im
u
m
ac
cu
r
ac
y
o
f
9
7
.
8
3
%.
Fig
u
r
e
9
.
PNN
class
if
ier
3.
P
RO
P
O
SE
D
M
O
D
E
L
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
co
n
tain
s
th
e
f
o
llo
win
g
s
tag
es
s
h
o
wn
i
n
Fig
u
r
e
1
0
f
ir
s
tly
;
it
will
wo
r
k
o
n
liv
er
b
en
ch
m
a
r
k
d
atasets
.
1.
B
UPA
d
ataset
[
2
3
]
d
o
n
ated
b
y
B
UPA
m
ed
ical
r
es
ea
r
ch
L
td
.
T
h
e
d
ata
s
et
co
n
tain
s
th
e
7
f
ea
tu
r
es
n
am
ely
m
ea
n
co
r
p
u
s
lar
v
alu
e,
alk
p
h
o
s
,
s
g
p
t,
s
g
o
t,
g
a
m
m
ag
t,
d
r
in
k
s
a
n
d
s
elec
to
r
(
d
ec
is
io
n
l
ab
el)
.
2.
I
L
PD
[
2
4
]
d
o
n
ated
b
y
R
am
an
a,
B
en
d
i.
I
t
h
as
1
1
f
e
atu
r
es
n
a
m
ely
ag
e
,
g
en
d
e
r
,
tb
,
d
b
,
alk
p
h
o
s
,
s
g
p
t,
s
g
o
t,
tp
,
alb
,
A/G
R
atio
,
an
d
class
lab
el.
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
C
o
mp
a
r
a
tive
a
n
a
lysi
s
o
n
liver b
en
ch
ma
r
k
d
a
ta
s
ets a
n
d
p
r
ed
ictio
n
…
(
Til
a
ka
ch
u
r
i B
a
l
a
kris
h
n
a
)
1049
Fig
u
r
e
1
0
.
Pro
p
o
s
ed
m
o
d
el
a
r
ch
itectu
r
e
T
h
e
m
ajo
r
f
in
d
in
g
o
b
s
er
v
ed
in
b
o
th
th
e
d
ata
s
ets ar
e
th
e
f
ea
tu
r
es lik
e
alk
p
h
o
s
,
s
g
p
t,
s
g
o
t a
r
e
co
m
m
o
n
an
d
th
ese
wer
e
v
er
y
im
p
o
r
tan
t
f
o
r
d
ec
is
io
n
m
ak
in
g
p
r
o
ce
s
s
.
In
T
ab
le
1
d
e
p
icts
th
e
s
u
m
m
ar
y
o
f
d
atasets
an
d
s
am
p
le
in
f
o
r
m
atio
n
.
Seco
n
d
ly
,
in
d
ata
-
p
r
e
p
r
o
ce
s
s
in
g
s
tag
e
f
ew
n
u
ll
v
alu
es
o
f
th
e
r
ec
o
r
d
s
i
n
b
o
t
h
th
e
d
atasets
wer
e
elim
in
ated
an
d
in
L
iv
er
p
atien
t
d
ataset
th
e
g
en
d
er
co
lo
u
m
n
is
d
r
o
p
p
ed
.
T
h
ir
d
l
y
,
in
m
o
d
elli
n
g
s
tag
e
b
o
th
th
e
tr
ad
itio
n
al
an
d
s
o
f
t
-
co
m
p
u
tin
g
b
ased
class
if
ier
s
will wo
r
k
o
n
b
o
th
th
e
b
en
c
h
m
ar
k
d
ata
s
ets.
T
ab
le
1
.
Data
s
ets an
d
s
am
p
les
S
.
N
o
N
a
me
o
f
t
h
e
d
a
t
a
se
t
N
o
.
o
f
i
n
s
t
a
n
c
e
s
N
o
.
o
f
f
e
a
t
u
r
e
s
N
o
.
o
f
c
l
a
ss
e
s
1
B
U
P
A
3
4
5
7
2
2
In
d
ian
Li
v
e
r
p
a
ti
e
n
t
d
a
tas
e
t
(
I
LPD
)
5
8
3
11
2
Alg
o
r
ith
m
RF
class
if
ier
:
−
Step
1
:
r
an
d
o
m
ly
s
am
p
le
K
d
at
a
p
o
in
ts
f
r
o
m
th
e
tr
ain
i
n
g
s
et.
−
Step
2
:
c
r
ea
te
th
e
RF
with
th
e
n
_
esti
m
ato
r
s
wh
ich
r
ep
r
esen
ts
th
e
r
an
d
o
m
tr
ee
s
.
−
Step
3
:
f
ix
th
e
p
a
r
am
eter
s
f
o
r
RF
alg
o
r
ith
m
(
b
o
o
ts
tr
a
p
=
t
r
u
e,
m
a
x
_
d
e
p
th
=3
,
m
ax
_
f
ea
tu
r
es=
‘
lo
g
2
’
,
n
_
esti
m
ato
r
s
=3
1
0
)
.
−
Step
4
:
c
alcu
late
th
e
ac
cu
r
ac
y
d
ec
is
io
n
o
f
test
d
ata
b
ased
o
n
m
ajo
r
ity
v
o
tin
g
an
d
ca
lc
u
late
t
h
e
ac
cu
r
ac
y
.
Fo
u
r
th
ly
,
th
e
e
v
alu
atio
n
m
etr
ic
a
cc
u
r
ac
y
is
ca
lcu
lated
u
s
in
g
th
e
s
tan
d
ar
d
f
o
r
m
u
lae.
Acc
u
r
ac
y
is
a
q
u
an
titativ
e
m
ea
s
u
r
e
u
s
ed
to
ass
es
s
th
e
p
er
f
o
r
m
an
ce
o
f
class
if
icatio
n
m
o
d
els.
I
n
f
o
r
m
ally
,
ac
cu
r
ac
y
(
3
)
r
e
f
er
s
to
th
e
p
r
o
p
o
r
tio
n
o
f
co
r
r
ec
t
p
r
ed
ictio
n
s
m
ad
e
b
y
o
u
r
m
o
d
el.
Acc
u
r
ac
y
=
.
.
(
3
)
Fo
r
b
in
ar
y
class
if
icatio
n
,
ac
cu
r
ac
y
(
4
)
m
ay
also
b
e
co
m
p
u
te
d
b
y
c
o
n
s
id
er
in
g
t
h
e
n
u
m
b
er
o
f
tr
u
e
p
o
s
itiv
es
an
d
tr
u
e
n
eg
ativ
es in
t
h
e
f
o
llo
win
g
m
an
n
er
:
Acc
u
r
ac
y
=
+
+
+
+
(
4
)
f
in
ally
,
last
s
tag
e
is
th
e
co
m
p
ar
is
o
n
s
tag
e
wh
e
r
e
we
f
i
n
d
th
e
b
est
class
if
ier
s
an
d
b
est
d
ataset
f
it
in
to
t
h
e
m
o
d
el.
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
ex
p
e
r
im
en
t
was
d
o
n
e
u
s
in
g
An
ac
o
n
d
a
Nav
ig
ato
r
[
2
5
]
J
u
p
y
ter
No
teb
o
o
k
a
p
y
th
o
n
f
r
am
e
wo
r
k
,
T
h
e
n
ec
ess
ar
y
p
ac
k
ag
es
was
p
an
d
as,
N
um
P
y
,
M
atp
l
o
tlib
,
S
ea
b
o
r
n,
S
k
lear
n
,
K
er
as
,
an
d
N
eu
P
y
.
T
ab
le
2
s
h
o
ws
th
e
ac
cu
r
ac
y
o
f
s
u
p
er
v
is
ed
alg
o
r
ith
m
s
an
d
f
o
r
all
th
e
alg
o
r
ith
m
s
th
e
tr
ain
an
d
test
s
et
s
p
lit
wer
e
8
0
%
an
d
2
0
%.
RF
h
as
ac
h
iev
ed
b
est
ac
cu
r
ac
y
o
f
7
8
.
2
6
%
o
n
B
UPA
d
ataset
an
d
7
8
.
5
3
%
o
n
I
L
PD
co
m
p
ar
ed
t
o
o
th
er
class
if
icatio
n
ap
p
r
o
ac
h
e
s
.
Ou
r
s
tu
d
y
s
u
g
g
ests
th
at
s
o
f
t
c
o
m
p
u
tin
g
-
b
ased
class
if
ier
s
s
u
ch
a
ANN,
DB
N
an
d
PNN
ex
h
ib
its
poor
ac
cu
r
ac
y
in
B
UPA
d
ataset
a
n
d
o
n
th
e
o
th
e
r
s
id
e
.
T
h
e
I
L
PD
is
b
e
s
t
s
u
itab
le
d
at
a
s
et
f
o
r
b
o
th
tr
ad
itio
n
al
class
if
ier
s
lik
e
NB
,
SVM,
KNN,
DT
,
an
d
RF
a
n
d
s
o
f
t
c
o
m
p
u
tin
g
-
b
ased
class
if
ier
s
.
In
F
ig
u
r
e
1
1
s
h
o
w
ac
cu
r
ac
y
o
f
class
if
ier
s
wh
er
e
X
-
ax
is
r
e
p
r
esen
ts
th
e
lis
t
o
f
b
o
t
h
tr
a
d
itio
n
al
a
n
d
s
o
f
t
-
co
m
p
u
tin
g
b
ased
class
if
ier
s
an
d
Y
-
ax
is
r
ep
r
esen
ts
ac
cu
r
ac
y
p
er
ce
n
tag
e
o
n
b
o
t
h
B
UPA
an
d
I
L
PD
d
atasets
.
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
0
43
-
1
0
51
1050
T
ab
le
2
.
Acc
u
r
ac
y
o
f
s
u
p
er
v
is
ed
lear
n
in
g
alg
o
r
ith
m
s
o
n
B
UPA
an
d
I
L
PD
d
ataset
S
.
N
o
N
a
me
o
f
t
h
e
c
l
a
ss
i
f
i
e
r
B
U
P
A
d
a
t
a
s
e
t
I
LPD
d
a
t
a
s
e
t
1
NB
5
2
%
5
7
%
2
S
V
M
7
6
.
8
1
%
7
3
.
0
6
%
3
K
N
N
6
9
.
5
7
%
6
5
.
2
8
%
4
DT
6
5
.
2
2
%
7
3
.
0
6
%
5
RF
7
8
.
2
6
%
7
8
.
5
3
%
6
M
LP
7
3
.
9
1
%
7
2
.
0
2
%
7
ANN
3
9
.
1
3
%
7
3
.
0
6
%
8
D
B
N
3
9
.
1
3
%
7
2
.
0
2
%
9
P
N
N
6
5
.
2
2
%
7
5
.
2
1
%
Fig
u
r
e
1
1
.
C
o
m
p
ar
is
o
n
g
r
ap
h
5.
CO
NCLU
SI
O
N
B
ased
o
n
th
e
r
esu
lts
we
f
o
u
n
d
th
at
I
L
PD
co
r
r
elate
s
with
B
UPA
Data
s
et
.
T
h
e
to
p
class
if
ier
s
b
o
th
tr
ad
itio
n
al
b
ased
an
d
s
o
f
t
-
c
o
m
p
u
tin
g
lik
e
NB
,
SVM,
KNN,
DT
,
R
F,
ML
P,
ANN,
DB
N,
an
d
PNN
in
th
is
s
tu
d
y
ten
d
ed
to
h
av
e
an
in
o
r
d
in
ately
g
iv
es
b
est
ac
cu
r
ac
y
r
esu
lts
to
I
n
d
ian
L
PD
in
co
m
p
ar
ed
with
B
UPA
d
ataset.
Ho
wev
er
,
f
u
r
th
er
a
n
d
in
-
d
ep
th
s
tu
d
ies m
ay
b
e
n
ee
d
e
d
to
im
p
r
o
v
e
its
class
if
ier
p
er
f
o
r
m
an
ce
.
RE
F
E
R
E
NC
E
S
[
1
]
D
.
H
a
r
i
t
h
a
,
“
C
o
m
p
a
r
a
t
i
v
e
st
u
d
y
o
n
b
r
a
i
n
t
u
m
o
r
d
e
t
e
c
t
i
o
n
t
e
c
h
n
i
q
u
e
s,”
i
n
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
S
i
g
n
a
l
Pr
o
c
e
ssi
n
g
,
C
o
m
m
u
n
i
c
a
t
i
o
n
,
Po
w
e
r
a
n
d
E
m
b
e
d
d
e
d
S
y
st
e
m
,
S
C
O
PE
S
2
0
1
6
-
Pr
o
c
e
e
d
i
n
g
s
,
O
c
t
.
2
0
1
7
,
p
p
.
1
3
8
7
–
1
3
9
2
,
d
o
i
:
1
0
.
1
1
0
9
/
S
C
O
P
ES.
2
0
1
6
.
7
9
5
5
6
6
8
.
[
2
]
R.
B
a
t
t
u
r
a
n
d
J.
N
a
r
a
y
a
n
a
,
“
C
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
me
d
i
c
a
l
X
-
r
a
y
i
ma
g
e
s
u
si
n
g
s
u
p
e
r
v
i
se
d
a
n
d
u
n
s
u
p
e
r
v
i
s
e
d
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s,”
I
n
d
o
n
e
si
a
n
J
o
u
r
n
a
l
o
f
E
l
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
3
0
,
n
o
.
3
,
p
p
.
1
7
1
3
–
1
7
2
1
,
J
u
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s
.
v
3
0
.
i
3
.
p
p
1
7
1
3
-
1
7
2
1
.
[
3
]
O
.
D
a
h
ma
n
e
,
M
.
K
h
e
l
i
f
i
,
M
.
B
e
l
a
d
g
h
a
m
,
a
n
d
I
.
K
a
d
r
i
,
“
P
n
e
u
m
o
n
i
a
d
e
t
e
c
t
i
o
n
b
a
se
d
o
n
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
a
n
d
a
c
o
m
b
i
n
a
t
i
o
n
o
f
V
G
G
1
9
a
n
d
a
C
N
N
b
u
i
l
t
f
r
o
m
scr
a
t
c
h
,
”
I
n
d
o
n
e
si
a
n
J
o
u
rn
a
l
o
f
El
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
4
,
n
o
.
3
,
p
p
.
1
4
6
9
–
1
4
8
0
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
2
4
.
i
3
.
p
p
1
4
6
9
-
1
4
8
0
.
[
4
]
J.
R
.
A
n
n
a
m
,
S
.
K
a
l
y
a
n
a
p
u
,
S
.
C
h
,
J.
S
o
m
a
l
a
,
a
n
d
S
.
B
.
R
a
j
u
,
“
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
EC
G
h
e
a
r
t
b
e
a
t
a
r
r
h
y
t
h
mi
a
:
a
r
e
v
i
e
w
,
”
Pr
o
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
7
1
,
p
p
.
6
7
9
–
6
8
8
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.
2
0
2
0
.
0
4
.
0
7
4
.
[
5
]
J.
K
.
A
l
w
a
n
,
D
.
S
.
Jaa
f
a
r
,
a
n
d
I
.
R
.
A
l
i
,
“
D
i
a
b
e
t
e
s
d
i
a
g
n
o
si
s s
y
st
e
m u
si
n
g
m
o
d
i
f
i
e
d
N
a
i
v
e
B
a
y
e
s c
l
a
ss
i
f
i
e
r
,
”
I
n
d
o
n
e
si
a
n
J
o
u
r
n
a
l
o
f
El
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
8
,
n
o
.
3
,
p
p
.
1
7
6
6
–
1
7
7
4
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s
.
v
2
8
.
i
3
.
p
p
1
7
6
6
-
1
7
7
4
.
[
6
]
G
.
B
a
t
t
i
n
e
n
i
,
N
.
C
h
i
n
t
a
l
a
p
u
d
i
,
a
n
d
F
.
A
men
t
a
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
i
n
m
e
d
i
c
i
n
e
:
p
e
r
f
o
r
ma
n
c
e
c
a
l
c
u
l
a
t
i
o
n
o
f
d
e
me
n
t
i
a
p
r
e
d
i
c
t
i
o
n
b
y
su
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
s
(
S
V
M
)
,
”
I
n
f
o
rm
a
t
i
c
s i
n
Me
d
i
c
i
n
e
U
n
l
o
c
k
e
d
,
v
o
l
.
1
6
,
p
.
1
0
0
2
0
0
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
mu
.
2
0
1
9
.
1
0
0
2
0
0
.
[
7
]
T.
B
.
K
r
i
s
h
n
a
,
N
.
V
i
ma
l
a
,
P
.
V
i
n
a
y
,
N
.
S
i
d
d
h
a
r
d
h
a
,
a
n
d
P
.
M
.
M
a
n
o
h
a
r
,
“
Ea
r
l
y
h
e
a
r
t
d
i
sea
s
e
p
r
e
d
i
c
t
i
o
n
u
si
n
g
su
p
p
o
r
t
v
e
c
t
o
r
mac
h
i
n
e
,
”
i
n
L
e
c
t
u
re
N
o
t
e
s i
n
N
e
t
w
o
r
k
s a
n
d
S
y
s
t
e
m
s
,
v
o
l
.
7
1
9
LN
N
S
,
2
0
2
3
,
p
p
.
4
7
1
–
4
7
9
.
[
8
]
M
.
A
.
j
a
b
b
a
r
,
B
.
L.
D
e
e
k
s
h
a
t
u
l
u
,
a
n
d
P
.
C
h
a
n
d
r
a
,
“
C
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
h
e
a
r
t
d
i
sea
se
u
s
i
n
g
k
-
n
e
a
r
e
st
n
e
i
g
h
b
o
r
a
n
d
g
e
n
e
t
i
c
a
l
g
o
r
i
t
h
m
,
”
Pro
c
e
d
i
a
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
0
,
p
p
.
8
5
–
9
4
,
2
0
1
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
t
c
y
.
2
0
1
3
.
1
2
.
3
4
0
.
[
9
]
K
.
M
.
A
l
mu
s
t
a
f
a
,
“
P
r
e
d
i
c
t
i
o
n
o
f
h
e
a
r
t
d
i
s
e
a
s
e
a
n
d
c
l
a
ssi
f
i
e
r
s’
se
n
s
i
t
i
v
i
t
y
a
n
a
l
y
s
i
s,
”
B
MC
B
i
o
i
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
2
1
,
n
o
.
1
,
p
.
2
7
8
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
8
6
/
s
1
2
8
5
9
-
0
2
0
-
0
3
6
2
6
-
y.
[
1
0
]
T.
B
a
l
a
k
r
i
sh
n
a
e
t
a
l
.
,
“
D
i
a
g
n
o
si
s
o
f
t
h
y
r
o
i
d
d
i
s
o
r
d
e
r
s
u
si
n
g
d
e
c
i
si
o
n
t
r
e
e
c
l
a
ssi
f
i
c
a
t
i
o
n
t
e
c
h
n
i
q
u
e
,
”
C
i
i
T
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s
a
n
d
M
a
c
h
i
n
e
L
e
a
rn
i
n
g
,
v
o
l
.
8
,
n
o
.
4
,
2
0
1
6
.
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
C
o
mp
a
r
a
tive
a
n
a
lysi
s
o
n
liver b
en
ch
ma
r
k
d
a
ta
s
ets a
n
d
p
r
ed
ictio
n
…
(
Til
a
ka
ch
u
r
i B
a
l
a
kris
h
n
a
)
1051
[
1
1
]
T.
B
a
l
a
k
r
i
s
h
n
a
,
B
.
N
a
r
e
n
d
r
a
,
M
.
H
.
R
e
d
d
y
,
a
n
d
D
.
J
a
y
a
sr
i
,
“
D
i
a
g
n
o
si
s
o
f
c
h
r
o
n
i
c
k
i
d
n
e
y
d
i
sea
s
e
u
si
n
g
r
a
n
d
o
m
f
o
r
e
s
t
c
l
a
ss
i
f
i
c
a
t
i
o
n
t
e
c
h
n
i
q
u
e
,
”
H
e
l
i
x
,
v
o
l
.
7
,
n
o
.
1
,
p
p
.
8
7
3
–
8
7
7
,
2
0
1
7
,
d
o
i
:
1
0
.
2
9
0
4
2
/
2
0
1
7
-
8
7
3
-
8
7
7
.
[
1
2
]
R
.
C
h
a
n
d
r
a
,
M
.
K
a
p
i
l
,
a
n
d
A
.
S
h
a
r
m
a
,
“
C
o
mp
a
r
a
t
i
v
e
a
n
a
l
y
si
s
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
w
i
t
h
p
r
i
n
c
i
p
a
l
c
o
mp
o
n
e
n
t
a
n
a
l
y
s
i
s
o
n
k
i
d
n
e
y
a
n
d
h
e
a
r
t
d
i
se
a
se,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
2
n
d
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
El
e
c
t
r
o
n
i
c
s a
n
d
S
u
st
a
i
n
a
b
l
e
C
o
m
m
u
n
i
c
a
t
i
o
n
S
y
s
t
e
m
s,
I
C
E
S
C
2
0
2
1
,
A
u
g
.
2
0
2
1
,
p
p
.
1
9
6
5
–
1
9
7
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
ESC
5
1
4
2
2
.
2
0
2
1
.
9
5
3
3
0
1
1
.
[
1
3
]
N
.
H
u
a
n
d
J
.
G
a
o
,
“
R
e
s
e
a
r
c
h
o
n
d
i
a
b
e
t
e
s
p
r
e
d
i
c
t
i
o
n
m
o
d
e
l
b
a
s
e
d
o
n
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
2
0
2
3
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
rs
,
I
n
f
o
rm
a
t
i
o
n
Pr
o
c
e
ssi
n
g
a
n
d
A
d
v
a
n
c
e
d
Ed
u
c
a
t
i
o
n
,
C
I
PAE
2
0
2
3
,
A
u
g
.
2
0
2
3
,
p
p
.
2
0
0
–
2
0
3
,
d
o
i
:
1
0
.
1
1
0
9
/
C
I
P
A
E6
0
4
9
3
.
2
0
2
3
.
0
0
0
4
4
.
[
1
4
]
W
.
Z
.
T.
Ta
r
e
q
,
“
S
l
e
e
p
d
i
so
r
d
e
r
s
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
si
n
g
r
a
n
d
o
m
f
o
r
e
st
s
a
l
g
o
r
i
t
h
m,”
i
n
S
t
u
d
i
e
s
i
n
S
y
s
t
e
m
s,
D
e
c
i
s
i
o
n
a
n
d
C
o
n
t
r
o
l
,
v
o
l
.
5
1
3
,
2
0
2
4
,
p
p
.
2
5
7
–
2
6
6
.
[
1
5
]
A
.
A
.
S
a
f
a
r
,
D
h
i
a
d
e
e
n
M
.
S
a
l
i
h
,
a
n
d
A
.
M
.
M
u
r
s
h
i
d
,
“
P
a
t
t
e
r
n
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
t
h
e
mu
l
t
i
-
l
a
y
e
r
p
e
r
c
e
p
t
r
o
n
(
M
LP)
f
o
r
me
d
i
c
a
l
d
i
s
e
a
se
:
A
s
u
r
v
e
y
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
N
o
n
l
i
n
e
a
r
A
n
a
l
y
si
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
4
,
n
o
.
1
,
2
0
2
3
,
d
o
i
:
1
0
.
2
2
0
7
5
/
I
JN
A
A
.
2
0
2
2
.
7
1
1
4
.
[
1
6
]
A
.
R
e
m
a
i
d
a
e
t
a
l
.
,
“
A
p
p
l
i
c
a
t
i
o
n
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
s
f
o
r
p
e
r
s
o
n
a
l
i
t
y
t
r
a
i
t
s
p
r
e
d
i
c
t
i
o
n
b
a
s
e
d
o
n
h
a
n
d
w
r
i
t
i
n
g
,
”
I
n
d
o
n
e
si
a
n
J
o
u
rn
a
l
o
f
El
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
3
1
,
n
o
.
3
,
p
p
.
1
5
3
4
–
1
5
4
4
,
S
e
p
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s
.
v
3
1
.
i
3
.
p
p
1
5
3
4
-
1
5
4
4
.
[
1
7
]
L.
O
z
y
i
l
m
a
z
a
n
d
T
.
Y
i
l
d
i
r
i
m,
“
A
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
f
o
r
d
i
a
g
n
o
s
i
s
o
f
h
e
p
a
t
i
t
i
s
d
i
se
a
se
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
i
n
t
C
o
n
f
e
re
n
c
e
o
n
N
e
u
r
a
l
N
e
t
w
o
r
k
s
,
2
0
0
3
,
v
o
l
.
1
,
p
p
.
5
8
6
–
5
8
9
,
d
o
i
:
1
0
.
1
1
0
9
/
i
j
c
n
n
.
2
0
0
3
.
1
2
2
3
4
2
2
.
[
1
8
]
S
.
M
.
M
.
E
l
k
h
o
l
y
,
A
.
R
e
z
k
,
a
n
d
A
.
A
.
E.
F
.
S
a
l
e
h
,
“
E
a
r
l
y
p
r
e
d
i
c
t
i
o
n
o
f
c
h
r
o
n
i
c
k
i
d
n
e
y
d
i
s
e
a
se
u
si
n
g
d
e
e
p
b
e
l
i
e
f
n
e
t
w
o
r
k
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
9
,
p
p
.
1
3
5
5
4
2
–
1
3
5
5
4
9
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
1
1
4
3
0
6
.
[
1
9
]
K
.
R
.
K
o
d
e
p
o
g
u
e
t
a
l
.
,
“
A
n
o
v
e
l
d
e
e
p
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
d
i
a
g
n
o
s
i
s
o
f
s
k
i
n
d
i
s
e
a
s
e
,
”
T
ra
i
t
e
m
e
n
t
d
u
S
i
g
n
a
l
,
v
o
l
.
3
9
,
n
o
.
5
,
p
p
.
1
8
7
3
–
1
8
7
7
,
N
o
v
.
2
0
2
2
,
d
o
i
:
1
0
.
1
8
2
8
0
/
t
s
.
3
9
0
5
4
8
.
[
2
0
]
J.
G
a
d
a
,
A
.
S
a
v
l
a
,
S
.
C
h
h
e
d
a
,
a
n
d
P
.
B
h
o
g
a
l
e
,
“
B
r
a
i
n
t
u
mo
r
s
e
g
m
e
n
t
a
t
i
o
n
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
e
r A
p
p
l
i
c
a
t
i
o
n
s
,
|
v
o
l
.
1
3
8
,
n
o
.
1
3
,
p
p
.
6
–
8
,
2
0
1
6
,
d
o
i
:
1
0
.
5
1
2
0
/
i
j
c
a
2
0
1
6
9
0
8
9
7
5
.
[
2
1
]
E.
H
.
A
.
R
a
d
y
a
n
d
A
.
S
.
A
n
w
a
r
,
“
P
r
e
d
i
c
t
i
o
n
o
f
k
i
d
n
e
y
d
i
se
a
se
st
a
g
e
s
u
s
i
n
g
d
a
t
a
mi
n
i
n
g
a
l
g
o
r
i
t
h
ms
,
”
I
n
f
o
rm
a
t
i
c
s
i
n
Me
d
i
c
i
n
e
U
n
l
o
c
k
e
d
,
v
o
l
.
1
5
,
p
.
1
0
0
1
7
8
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
m
u
.
2
0
1
9
.
1
0
0
1
7
8
.
[
2
2
]
J.
J.
F
e
m
i
l
a
n
d
T.
Ja
y
a
,
“
A
n
e
f
f
i
c
i
e
n
t
h
y
b
r
i
d
o
p
t
i
mi
z
a
t
i
o
n
f
o
r
s
k
i
n
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
u
s
i
n
g
P
N
N
c
l
a
ssi
f
i
e
r
,
”
C
o
m
p
u
t
e
r
S
y
st
e
m
s
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
4
5
,
n
o
.
3
,
p
p
.
2
9
1
9
–
2
9
3
4
,
2
0
2
3
,
d
o
i
:
1
0
.
3
2
6
0
4
/
c
sse.
2
0
2
3
.
0
3
2
9
3
5
.
[
2
3
]
“
Li
v
e
r
d
i
so
r
d
e
r
s
M
e
d
i
c
i
n
e
,
”
U
C
I
Ma
c
h
i
n
e
L
e
a
rn
i
n
g
Re
p
o
s
i
t
o
r
y
,
1
9
9
0
,
d
o
i
:
1
0
.
2
4
4
3
2
/
C
5
4
G
6
7
.
[
2
4
]
“
I
n
d
i
a
n
l
i
v
e
r
p
a
t
i
e
n
t
d
a
t
a
s
e
t
(
I
LPD
)
,
”
U
C
I
M
a
c
h
i
n
e
L
e
a
rn
i
n
g
Re
p
o
si
t
o
r
y
,
2
0
1
2
.
[
2
5
]
“
A
n
a
c
o
n
d
a
N
a
v
i
g
a
t
o
r
|
A
n
a
c
o
n
d
a
,
”
2
0
2
4
.
h
t
t
p
s:
/
/
w
w
w
.
a
n
a
c
o
n
d
a
.
c
o
m
/
a
n
a
c
o
n
d
a
-
n
a
v
i
g
a
t
o
r
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Mr.
Til
a
k
a
c
h
u
r
i
Ba
l
a
k
r
ish
n
a
R
e
se
a
rc
h
sc
h
o
lar
(1
9
0
2
2
P
0
5
2
9
)
,
U
n
iv
e
rs
i
t
y
C
o
ll
e
g
e
o
f
E
n
g
i
n
e
e
rin
g
Ka
k
i
n
a
d
a
(A)
,
JN
TUK,
Ka
k
i
n
a
d
a
a
n
d
h
e
d
i
d
h
is
M
.
Tec
h
i
n
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
Tec
h
n
o
lo
g
y
wit
h
S
p
e
c
il
iza
ti
o
n
o
f
Artifi
c
ia
l
In
telli
g
e
n
c
e
a
n
d
Ro
b
o
t
ics
in
An
d
h
ra
Un
i
v
e
rsity
,
Visa
k
h
a
p
a
tn
a
m
.
He
d
i
d
h
is
B.
Tec
h
fr
o
m
JN
TUK
Ka
k
in
d
a
.
His
a
re
a
o
f
re
se
a
rc
h
is
m
e
d
ica
l
d
a
tam
in
in
g
a
n
d
m
a
c
h
i
n
e
lea
rn
i
n
g
.
P
re
se
n
tl
y
h
e
is
wo
rk
in
g
a
s
As
sista
n
t
P
ro
fe
ss
o
r
in
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
i
n
S
e
sh
a
d
ri
Ra
o
G
u
d
lav
a
ll
e
ru
En
g
i
n
e
e
rin
g
C
o
ll
e
g
e
,
G
u
d
lav
a
ll
e
ru
,
A
n
d
h
ra
P
ra
d
e
sh
,
In
d
ia.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
b
a
lak
rish
n
a
g
e
c
@g
m
a
il
.
c
o
m
.
Pro
f.
Dr
.
J
a
g
a
d
e
e
sw
a
r
a
Ra
o
Ann
a
m
wo
rk
in
g
a
s
p
ro
fe
ss
o
r
CVR
Co
ll
e
g
e
o
f
En
g
i
n
e
e
rin
g
(A)
,
Hy
d
e
ra
b
a
d
a
n
d
d
i
d
h
is
P
h
.
D
.
fr
o
m
Un
iv
e
rsi
ty
o
f
Hy
d
e
ra
b
a
d
.
He
is
Ex
p
e
rien
c
e
d
P
ro
fe
ss
o
r
wit
h
a
d
e
m
o
n
stra
ted
h
ist
o
ry
o
f
w
o
rk
i
n
g
in
t
h
e
re
se
a
rc
h
in
d
u
stry
.
S
tro
n
g
e
d
u
c
a
ti
o
n
p
ro
fe
ss
io
n
a
l
sk
il
led
i
n
c
o
m
p
u
ter
sc
ien
c
e
,
C+
+
,
d
a
tam
in
in
g
,
p
a
tt
e
rn
re
c
o
g
n
it
i
o
n
,
a
n
d
m
a
c
h
in
e
lea
rn
in
g
.
He
g
u
i
d
e
d
1
5
M
.
Tec
h
a
n
d
3
5
B.
Tec
h
s
tu
d
e
n
t
p
r
o
jec
ts
a
n
d
h
e
p
u
b
li
s
h
e
d
1
8
i
n
tern
a
ti
o
n
a
l
j
o
u
rn
a
ls.
He
is
M
e
m
b
e
r
o
f
I
n
stit
u
te
o
f
El
e
c
tro
n
ics
En
g
in
e
e
rs
(IE
EE
).
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
jag
a
ra
o
@g
m
a
il
.
c
o
m
.
Pro
f.
Dr
.
Da
sa
r
i
H
a
r
ith
a
wo
r
k
in
g
a
s
p
ro
fe
ss
o
r
o
f
CS
E,
Un
i
v
e
r
sity
C
o
ll
e
g
e
o
f
En
g
i
n
e
e
rin
g
Ka
k
in
a
d
a
(A)
,
Ja
wa
h
a
rlal
Ne
h
ru
Tec
h
n
o
lo
g
ica
l
Un
i
v
e
rsity
,
Ka
k
i
n
a
d
a
.
S
h
e
h
a
s
2
0
+
y
e
a
rs
o
f
e
x
p
e
rien
c
e
.
S
h
e
g
u
i
d
e
d
2
P
h
.
D
.
a
n
d
h
e
r
re
se
a
rc
h
in
tere
st
is
o
n
ima
g
e
p
ro
c
e
ss
in
g
,
p
a
tt
e
rn
re
c
o
g
n
it
i
o
n
,
so
ftwa
re
e
n
g
in
e
e
ri
n
g
a
n
d
n
e
two
rk
in
g
.
S
h
e
p
u
b
li
sh
e
d
2
3
re
se
a
rc
h
p
a
p
e
rs
in
in
tern
a
ti
o
n
a
l
j
o
u
r
n
a
ls
a
n
d
1
9
c
o
n
fe
re
n
c
e
s
a
n
d
s
h
e
h
a
d
2
p
a
ten
ts.
S
h
e
is
p
e
e
r
re
v
iew
e
r
to
th
e
In
sti
tu
ti
o
n
o
f
En
g
i
n
e
e
rin
g
a
n
d
Tec
h
n
o
l
o
g
y
f
o
r
ima
g
e
p
ro
c
e
ss
in
g
j
o
u
r
n
a
l.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
h
a
rit
h
a
d
a
sa
ri9
@y
a
h
o
o
.
c
o
m.
Evaluation Warning : The document was created with Spire.PDF for Python.