I
nte
rna
t
io
na
l J
o
urna
l o
f
I
nfo
r
m
a
t
ics a
nd
Co
mm
u
n
ica
t
io
n T
ec
hn
o
lo
g
y
(
I
J
-
I
CT
)
Vo
l.
8
,
No
.
2
,
A
u
g
u
s
t
201
9
,
p
p
.
63
~
70
I
SS
N:
2252
-
8776
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ict.
v
8
i2
.
p
p
6
3
-
70
63
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
JI
C
T
Efficien
t
da
ta
m
in
ing
m
o
del
f
o
r p
re
diction o
f
chro
nic
kidney
disea
se using
w
ra
pper
m
e
thods
Ra
m
a
s
w
a
m
y
re
dd
y
A
,
Sh
iv
a
P
ra
s
a
d
S
,
K
V
Ra
ng
a
ra
o
,
A
Sa
ra
ny
a
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
,
V
F
S
T
R
Un
iv
e
rsity
,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
1
2
,
2
0
1
8
R
ev
i
s
ed
Ma
r
2
0
,
2
0
1
9
A
cc
ep
ted
A
p
r
1
2
,
2
0
1
9
In
th
e
p
re
se
n
t
g
e
n
e
ra
ti
o
n
,
m
a
jo
rit
y
o
f
th
e
p
e
o
p
le
a
re
h
ig
h
ly
a
ff
e
c
ted
b
y
k
id
n
e
y
d
ise
a
se
s
.
Am
o
n
g
th
e
m
,
c
h
ro
n
ic
k
id
n
e
y
is
th
e
m
o
st
c
o
m
m
o
n
li
f
e
th
re
a
ten
in
g
d
ise
a
se
w
h
ich
c
a
n
b
e
p
re
v
e
n
ted
b
y
e
a
rl
y
d
e
tec
ti
o
n
.
Histo
l
o
g
ica
l
g
ra
d
e
in
c
h
ro
n
ic
k
id
n
e
y
d
ise
a
s
e
p
ro
v
id
e
s
c
li
n
ica
ll
y
i
m
p
o
rtan
t
p
ro
g
n
o
stic
in
f
o
r
m
a
ti
o
n
.
T
h
e
re
f
o
re
,
m
a
c
h
in
e
lea
rn
in
g
tec
h
n
iq
u
e
s
a
re
a
p
p
li
e
d
o
n
t
h
e
i
n
f
o
rm
a
ti
o
n
c
o
ll
e
c
ted
f
ro
m
p
re
v
io
u
sly
d
iag
n
o
se
d
p
a
ti
e
n
ts
in
o
r
d
e
r
to
d
isc
o
v
e
r
th
e
k
n
o
w
led
g
e
a
n
d
p
a
tt
e
rn
s
f
o
r
m
a
k
in
g
p
re
c
ise
p
re
d
icti
o
n
s
.
A
larg
e
n
u
m
b
e
r
o
f
f
e
a
tu
re
s
e
x
ist
in
th
e
ra
w
d
a
ta
in
w
h
ich
so
m
e
m
a
y
c
a
u
se
lo
w
in
f
o
rm
a
ti
o
n
a
n
d
e
rro
r;
h
e
n
c
e
f
e
a
tu
re
se
lec
ti
o
n
tec
h
n
iq
u
e
s
c
a
n
b
e
u
se
d
t
o
re
tri
e
v
e
u
se
f
u
l
su
b
se
t
o
f
f
e
a
tu
re
s
a
n
d
to
im
p
ro
v
e
th
e
c
o
m
p
u
tatio
n
p
e
rf
o
rm
a
n
c
e
.
In
th
is
m
a
n
u
sc
rip
t
w
e
u
se
a
se
t
o
f
F
il
ter,
W
ra
p
p
e
r
m
e
th
o
d
s
f
o
ll
o
w
e
d
b
y
Ba
g
g
in
g
a
n
d
B
o
o
sti
n
g
m
o
d
e
ls
w
it
h
p
a
ra
m
e
ter
tu
n
in
g
tec
h
n
i
q
u
e
t
o
c
las
sify
c
h
ro
n
i
c
k
id
n
e
y
d
ise
a
se
.
Ca
p
a
b
il
it
y
o
f
Ba
g
g
in
g
a
n
d
B
o
o
sti
n
g
c
las
sif
iers
a
re
c
o
m
p
a
r
e
d
a
n
d
t
h
e
b
e
st
e
n
se
m
b
le
c
las
si
f
ier
w
h
ich
a
tt
a
in
s
h
ig
h
sta
b
il
it
y
w
it
h
b
e
tt
e
r
p
ro
m
isin
g
re
su
lt
s is
id
e
n
ti
f
ied
.
K
ey
w
o
r
d
s
:
B
ag
g
i
n
g
B
o
o
s
tin
g
Fil
ter
m
et
h
o
d
s
W
r
ap
p
e
r
m
et
h
o
d
s
Co
p
y
rig
h
t
©
2
0
1
9
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
:
R
a
m
a
s
w
a
m
y
r
ed
d
y
A
,
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
i
n
ee
r
in
g
,
VFST
R
Un
i
v
er
s
it
y
,
Vad
la
m
u
d
i,
I
n
d
ia
.
E
m
ail:
r
a
m
as
w
a
m
y
r
ed
y
y
m
ai
l
@
g
m
ai
l.c
o
m
1.
I
NT
RO
D
UCT
I
O
N
Kid
n
e
y
s
ar
e
th
e
im
p
o
r
tan
t
f
u
n
ctio
n
al
u
n
it
in
th
e
h
u
m
an
b
o
d
y
w
h
ic
h
is
s
itu
a
ted
b
elo
w
th
e
s
p
in
al
co
r
d
o
f
th
e
b
o
d
y
.
Kid
n
e
y
s
w
o
r
k
s
li
k
e
w
ater
f
il
ter
h
o
w
w
ater
f
il
te
r
p
u
r
if
ies
t
h
e
w
ater
s
i
m
ilar
l
y
i
t
p
u
r
if
ie
s
th
e
b
lo
o
d
an
d
r
em
o
v
es
th
e
w
as
te
m
ate
r
ials
f
r
o
m
th
e
b
o
d
y
,
s
o
k
id
n
e
y
s
ca
n
b
e
ca
lled
as
Fil
tr
atio
n
u
n
it.
T
h
e
o
th
er
f
u
n
ctio
n
alit
y
o
f
k
id
n
e
y
s
i
s
R
eg
u
lates
th
e
b
lo
o
d
p
r
ess
u
r
e
an
d
c
o
n
tr
o
ls
t
h
e
s
u
g
ar
lev
el
i
n
s
id
e
t
h
e
b
o
d
y
.
Fail
u
r
e
o
f
th
e
k
id
n
e
y
o
cc
u
r
s
w
h
en
it
ca
n
n
o
t
b
e
ab
le
to
p
u
r
if
ies
th
e
b
lo
o
d
an
d
ca
n
n
o
t
b
e
ab
le
t
o
er
ad
icate
th
e
w
a
s
te
co
n
ten
t
s
f
o
r
m
t
h
e
b
o
d
y
,
t
h
en
t
h
e
b
o
d
y
i
s
f
u
ll
y
f
i
lled
u
p
w
it
h
h
i
g
h
to
x
i
n
s
w
h
ic
h
lead
s
to
th
e
d
ea
th
o
f
a
p
er
s
o
n
.
Kid
n
e
y
d
is
ea
s
e
s
ca
n
b
e
ca
teg
o
r
ized
in
to
t
w
o
t
y
p
es
(
i)
A
cu
te
Kid
n
e
y
Di
s
ea
s
e
(
ii)
C
h
r
o
n
i
c
Kid
n
e
y
Dis
ea
s
e.
A
cu
te
k
id
n
e
y
Di
s
e
a
s
e
is
u
s
u
all
y
ca
u
s
ed
b
y
an
e
v
en
t
t
h
at
lead
s
to
k
id
n
e
y
m
a
lf
u
n
ct
io
n
,
s
u
c
h
as
d
eh
y
d
r
atio
n
,
b
lo
o
d
lo
s
s
f
r
o
m
m
aj
o
r
s
u
r
g
er
y
o
r
in
j
u
r
y
,
o
r
th
e
u
s
e
o
f
m
ed
ici
n
es.
C
h
r
o
n
ic
k
i
d
n
e
y
d
is
ea
s
e
(
C
KD)
is
u
s
u
al
l
y
ca
u
s
ed
b
y
a
lo
n
g
-
t
er
m
d
is
ea
s
e,
s
u
c
h
as
h
i
g
h
b
lo
o
d
p
r
ess
u
r
e
o
r
d
ia
b
etes
th
at
s
lo
w
l
y
d
a
m
a
g
es
t
h
e
k
id
n
e
y
s
a
n
d
r
ed
u
ce
s
t
h
eir
f
u
n
ctio
n
o
v
er
t
i
m
e.
C
h
r
o
n
ic
k
id
n
e
y
d
is
ea
s
e
m
a
y
n
o
t
s
h
o
w
a
n
y
s
y
m
p
to
m
s
i
f
l
ittl
e
k
id
n
e
y
f
u
n
ctio
n
r
e
m
a
in
s
s
o
it
is
d
if
f
icu
lt
to
p
r
ed
ict
w
h
eth
er
a
p
er
s
o
n
is
s
u
f
f
er
i
n
g
f
r
o
m
d
is
ea
s
e
o
r
n
o
t.
A
lo
n
g
w
it
h
c
h
r
o
n
ic
k
id
n
e
y
d
is
ea
s
e
o
th
er
p
r
o
b
lem
s
m
a
y
ar
is
e
s
s
u
c
h
as
an
e
m
ia,
h
y
p
o
p
h
o
s
p
h
a
te
m
ia
w
h
ic
h
s
h
o
w
s
h
i
g
h
co
m
p
lica
tio
n
s
in
k
id
n
e
y
f
a
ilu
r
e.
T
h
e
o
b
j
ec
tiv
e
o
f
th
is
p
ap
er
is
to
p
r
ed
ict
th
e
ch
r
o
n
ic
k
id
n
e
y
d
is
ea
s
e
w
it
h
th
e
h
elp
o
f
en
s
e
m
b
le
class
i
f
ier
s
.
T
h
is
p
ap
er
is
o
r
g
an
ized
in
to
s
i
x
s
ec
tio
n
s
.
Sectio
n
2
s
h
o
w
s
th
e
o
v
er
v
ie
w
o
f
L
iter
atu
r
e
w
o
r
k
,
Feat
u
r
e
s
elec
tio
n
tec
h
n
iq
u
es
ar
e
ex
p
lai
n
ed
in
th
e
Sectio
n
3
,
Sectio
n
4
illu
s
tr
ates
th
e
cla
s
s
i
f
icatio
n
tech
n
iq
u
es,
P
r
o
p
o
s
ed
Me
th
o
d
o
lo
g
y
is
p
r
esen
ted
in
th
e
Sectio
n
5
an
d
f
in
all
y
S
ec
t
io
n
6
d
em
o
n
s
tr
ates
th
e
R
esu
lt
a
n
al
y
s
is
an
d
co
n
clu
s
io
n
p
ar
t.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8776
I
n
t J
I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
8
,
No
.
2,
A
u
g
u
s
t
201
9
:
63
–
70
64
2.
L
I
T
E
R
AT
U
RE
WO
RK
R
esear
ch
er
s
h
av
e
p
r
o
p
o
s
ed
v
ar
io
u
s
m
et
h
o
d
s
o
n
p
r
ed
ictin
g
th
e
ch
r
o
n
ic
k
id
n
e
y
d
is
ea
s
e
p
r
o
b
lem
an
d
s
o
m
e
o
f
t
h
ese
w
o
r
k
s
ar
e
s
p
ec
if
ied
h
er
e.
R
u
b
in
i
et
al
[
1
]
s
p
ec
if
ied
th
e
cla
s
s
i
f
ier
s
l
ik
e
M
u
ltil
a
y
er
p
er
ce
p
tr
o
n
(
ML
P
)
,
lo
g
is
tic
r
e
g
r
ess
io
n
,
r
ad
ial
b
asis
f
u
n
c
tio
n
n
et
w
o
r
k
an
d
th
e
y
a
n
al
y
ze
d
t
h
at
M
u
lt
ila
y
er
p
er
ce
p
tr
o
n
(
ML
P
)
h
as
g
i
v
e
n
t
h
e
b
est
ac
c
u
r
ac
y
.
B
ab
y
et
al
[
2
]
i
m
p
le
m
e
n
ted
t
h
e
s
ix
c
lass
if
icatio
n
a
lg
o
r
it
h
m
s
in
p
r
ed
ictin
g
t
h
e
ch
r
o
n
ic
k
id
n
e
y
d
is
ea
s
e.
T
h
e
class
i
f
ier
s
ar
e
k
s
tar
,
J
4
8
,
Naiv
e
B
ay
e
s
,
R
an
d
o
m
Fo
r
est,
A
D
T
r
ee
s
an
d
co
n
clu
d
ed
th
at
Nai
v
e
B
a
y
es i
s
g
i
v
i
n
g
h
i
g
h
est ac
c
u
r
ac
y
.
Dh
a
y
an
a
n
d
et
al
[
3
]
u
s
ed
SV
M
an
d
Naiv
e
B
ay
es
clas
s
i
f
ie
r
s
in
p
r
ed
ictin
g
th
e
r
en
al
d
is
e
ase.
T
h
ey
co
m
p
ar
ed
th
e
t
w
o
cla
s
s
i
f
ier
s
a
n
d
id
en
ti
f
ied
t
h
at
SVM
i
s
t
h
e
b
est o
n
e
in
r
e
n
al
d
is
ea
s
e
p
r
ed
ictio
n
.
J
en
a
et
al
[
4
]
s
u
g
g
e
s
ted
th
e
c
lass
if
icatio
n
a
lg
o
r
ith
m
s
lik
e
Su
p
p
o
r
t
Vec
to
r
Ma
ch
in
e,
Nai
v
e
B
a
y
e
s
,
co
n
j
u
n
ctiv
e
r
u
le,
J
4
8
,
Mu
ltil
a
y
er
p
er
ce
p
tr
o
n
,
d
ec
is
io
n
tab
le.
T
h
ese
class
i
f
ier
s
ar
e
i
m
p
le
m
e
n
ted
o
n
w
e
k
a
to
o
l
an
d
f
o
u
n
d
th
at
M
u
lt
ila
y
er
p
er
ce
p
tr
o
n
h
as sh
o
w
n
th
e
h
i
g
h
est ac
cu
r
ac
y
.
Sed
ig
h
i
et
a
l
[
5
]
d
ev
elo
p
ed
a
d
ec
is
io
n
s
u
p
p
o
r
t
s
y
s
te
m
f
o
r
c
h
r
o
n
ic
k
id
n
e
y
d
i
s
ea
s
e
p
r
ed
icti
o
n
an
d
t
h
e
y
ap
p
lied
th
e
f
ea
t
u
r
e
s
elec
tio
n
te
ch
n
iq
u
es
o
n
k
id
n
e
y
d
ata.
T
h
e
y
o
b
s
er
v
ed
th
at
t
h
e
clas
s
i
f
ier
w
i
th
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
e
h
as
s
h
o
w
n
b
etter
p
er
f
o
r
m
a
n
ce
.
C
h
ett
y
et
al
[
6
]
d
em
o
n
s
tr
ated
th
e
r
o
le
o
f
f
ea
tu
r
e
s
el
ec
tio
n
i
n
d
etec
ti
n
g
th
e
ch
r
o
n
ic
k
id
n
e
y
d
is
ea
s
e.
T
h
e
y
u
s
ed
th
e
W
r
ap
p
er
m
et
h
o
d
w
ith
B
est
f
ir
s
t
s
ea
r
c
h
f
o
r
s
ele
cti
n
g
th
e
m
o
s
t
r
ele
v
an
t
attr
ib
u
tes a
n
d
co
n
clu
d
ed
th
at
t
h
e
class
if
ier
s
o
n
r
ed
u
ce
d
d
ata
s
et
h
a
v
e
s
h
o
w
n
t
h
e
b
est p
er
f
o
r
m
an
ce
.
Ku
n
w
ar
et
al
[
7
]
u
s
ed
th
e
clas
s
if
ier
s
lik
e
Nai
v
e
B
a
y
es,
A
r
ti
f
i
cial
Neu
r
al
Net
w
o
r
k
(
A
NN)
in
d
etec
tin
g
th
e
ch
r
o
n
ic
d
is
ea
s
e.
T
h
ese
class
i
f
ier
s
ar
e
i
m
p
le
m
e
n
ted
o
n
R
ap
id
m
i
n
er
to
o
l a
n
d
c
o
n
clu
d
ed
th
at
Naiv
e
B
a
y
es is
g
iv
in
g
t
h
e
b
est
p
er
f
o
r
m
a
n
ce
.
T
az
in
et
al
[
8
]
u
s
ed
th
e
clas
s
i
f
icatio
n
alg
o
r
it
h
m
s
li
k
e
SV
M,
Dec
is
io
n
T
r
ee
,
k
-
Nea
r
est
Neig
h
b
o
r
,
Naiv
e
B
ay
e
s
alg
o
r
ith
m
in
c
h
r
o
n
ic
k
id
n
e
y
d
is
e
ase
d
etec
t
io
n
.
T
h
e
y
u
s
ed
th
e
r
an
k
in
g
al
g
o
r
ith
m
to
s
elec
t
th
e
m
o
s
t
r
ele
v
an
t
attr
i
b
u
tes
an
d
co
m
p
ar
ed
th
e
class
i
f
ier
s
o
n
T
o
p
1
0
,
1
5
,
2
0
,
2
5
attr
ib
u
tes.
T
h
ey
o
b
s
er
v
ed
th
at
t
h
e
class
if
ier
s
o
n
to
p
1
5
attr
ib
u
tes
h
as
s
h
o
w
n
t
h
e
b
ette
r
p
er
f
o
r
m
a
n
ce
.
B
o
u
k
e
n
ze
et
al
[
9
]
u
s
ed
k
-
Nea
r
e
s
t
Neig
h
b
o
r
,
Dec
is
io
n
T
r
ee
,
Su
p
p
o
r
t
Vec
to
r
Ma
ch
in
e
,
M
u
ltil
a
y
er
p
er
ce
p
tr
o
n
,
B
ay
e
s
ian
Net
w
o
r
k
c
lass
if
icatio
n
alg
o
r
ith
m
s
f
o
r
ch
r
o
n
ic
d
is
ea
s
e
p
r
ed
ictio
n
an
d
th
e
y
id
en
ti
f
ied
th
at
Dec
is
io
n
tr
ee
h
as
g
iv
e
n
th
e
b
est
p
er
f
o
r
m
an
ce
.
I
n
[
6
,
8
]
R
esear
ch
er
s
h
a
s
u
s
ed
Feat
u
r
e
s
elec
tio
n
tech
n
iq
u
es
f
o
r
s
elec
tin
g
th
e
s
i
g
n
i
f
ican
t a
ttrib
u
tes an
d
o
b
s
er
v
ed
th
at
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
m
o
d
el
is
i
n
cr
ea
s
ed
w
h
en
s
i
g
n
if
ica
n
t
attr
ib
u
tes
ar
e
co
n
s
id
er
ed
.
So
in
th
i
s
p
ap
er
w
e
u
s
e
Fi
lter
an
d
W
r
ap
p
er
m
et
h
o
d
s
o
f
f
ea
tu
r
e
s
elec
ti
o
n
tech
n
iq
u
e
s
to
s
elec
t th
e
s
i
g
n
i
f
ican
t a
ttrib
u
tes.
R
esear
ch
er
s
h
as
ap
p
lied
v
ar
io
u
s
clas
s
if
icatio
n
alg
o
r
it
h
m
s
i
n
ch
r
o
n
ic
k
id
n
e
y
d
is
ea
s
e
p
r
ed
ictio
n
b
u
t
th
er
e
is
n
o
s
tab
ilit
y
i
n
ter
m
s
o
f
ac
cu
r
ac
y
it
i
s
d
u
e
to
,
w
h
ile
tr
a
in
i
n
g
m
o
d
el
s
o
m
e
in
s
tan
ce
s
m
a
y
co
v
er
a
n
d
s
o
m
e
m
a
y
b
e
n
o
t
,
s
u
p
p
o
s
e
i
f
t
h
e
te
s
t
d
ata
co
n
s
is
ts
o
f
t
h
e
i
n
s
ta
n
ce
s
wh
ich
m
a
y
n
o
t
b
e
co
v
er
ed
t
h
e
m
o
d
el
w
h
ile
tr
ai
n
i
n
g
.
T
h
en
th
e
class
i
f
ier
m
a
y
p
r
ed
ic
ts
in
co
r
r
ec
tl
y
.
T
o
o
v
er
co
m
e
th
is
p
r
o
b
lem
,
m
o
d
els
n
ee
d
to
b
e
s
tab
ilized
f
o
r
th
at
w
e
u
s
e
B
ag
g
i
n
g
a
n
d
B
o
o
s
tin
g
class
i
f
ier
s
w
h
ic
h
ar
e
also
ca
lle
d
en
s
e
m
b
le
cla
s
s
i
f
ier
s
.
A
clas
s
i
f
icatio
n
al
g
o
r
ith
m
co
n
s
is
t
s
o
f
p
ar
am
eter
s
,
r
an
d
o
m
l
y
if
w
e
ass
i
g
n
v
a
lu
e
s
to
th
e
p
ar
a
m
eter
s
f
o
r
a
g
iv
e
n
class
i
f
ier
.
Dep
en
d
s
o
n
th
e
v
alu
e,
s
o
m
eti
m
e
s
th
e
p
er
f
o
r
m
a
n
ce
o
f
a
class
if
ier
m
a
y
b
e
h
ig
h
s
o
m
eti
m
es
i
t
ma
y
b
e
lo
w
.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
a
class
if
ier
is
f
lu
c
tu
at
in
g
d
u
e
to
r
an
d
o
m
l
y
as
s
i
g
n
i
n
g
t
h
e
p
ar
am
eter
v
al
u
es,
s
o
to
m
ai
n
tain
th
e
s
tab
ilit
y
w
e
n
e
ed
to
g
iv
e
o
p
ti
m
al
v
alu
e
s
f
o
r
a
g
i
v
en
p
ar
a
m
e
ter
.
T
o
f
in
d
th
e
o
p
tim
a
l
v
al
u
e
s
f
o
r
a
g
iv
e
n
p
ar
a
m
eter
w
e
u
s
e
p
ar
a
m
eter
tu
n
i
n
g
tech
n
iq
u
e.
3.
F
E
AT
U
RE
S
E
L
E
C
T
I
O
N
Featu
r
e
s
elec
t
io
n
is
t
h
e
p
r
o
ce
d
u
r
e
o
f
f
i
n
d
in
g
th
e
s
u
b
s
e
t
o
f
m
o
s
t
s
i
g
n
i
f
ica
n
t
f
ea
t
u
r
es
u
s
ed
in
m
o
d
el
co
n
s
tr
u
ct
io
n
.
A
lter
n
a
tiv
e
n
a
m
es
f
o
r
Featu
r
e
s
elec
tio
n
ar
e
v
ar
iab
le
s
elec
tio
n
,
attr
ib
u
te
s
e
lect
io
n
,
v
ar
iab
le
s
u
b
s
e
t
s
elec
t
io
n
.
T
h
e
ad
v
an
tag
e
s
o
f
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
es
ar
e
ab
le
to
tr
ain
th
e
al
g
o
r
ith
m
v
er
y
f
a
s
ter
,
i
m
p
r
o
v
es
th
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
m
o
d
el,
av
o
id
s
c
u
r
s
e
o
f
d
i
m
en
s
io
n
al
it
y
a
n
d
it r
ed
u
ce
s
t
h
e
m
o
d
el
co
m
p
lex
i
t
y
an
d
m
a
k
es
th
e
m
o
d
el
v
er
y
s
i
m
p
le
w
h
ich
c
an
b
e
ea
s
ier
t
o
u
n
d
er
s
ta
n
d
.
Fea
tu
r
e
s
elec
tio
n
a
lg
o
r
it
h
m
s
ar
e
cl
ass
i
f
ied
i
n
to
Fil
ter
m
et
h
o
d
s
,
W
r
ap
p
er
m
et
h
o
d
s
an
d
E
m
b
ed
d
ed
m
eth
o
d
s
.
F
ilte
r
M
et
ho
ds
:
Fil
ter
m
eth
o
d
s
s
elec
t
th
e
attr
ib
u
tes
i
n
d
ep
en
d
en
t
o
f
a
n
y
al
g
o
r
ith
m
.
I
t
u
s
es
s
tatis
tica
l
m
et
h
o
d
s
to
ass
i
g
n
s
co
r
es
to
e
ac
h
f
ea
tu
r
e
f
o
r
th
eir
co
r
r
elati
o
n
w
it
h
t
h
e
o
u
tco
m
e
v
ar
iab
le.
E
x
a
m
p
le
s
o
f
Fil
ter
m
et
h
o
d
s
ar
e
I
n
f
o
r
m
at
io
n
g
a
in
,
Gain
r
atio
,
C
o
n
s
is
te
n
c
y
,
O
n
e
R
,
C
h
i
-
Sq
u
ar
ed
T
est etc
.
P
s
eudo
co
de
I
np
ut:
Feat
u
r
e
s
et
S
1
.
I
d
en
tify
ca
n
d
id
ate
s
u
b
s
et
sS
2
.
W
h
ile!
Sto
p
cr
iter
io
n
(
)
2
.
1
.
A
s
s
es
s
u
t
ilit
y
f
u
n
ctio
n
J
u
s
in
g
s
.
2
.
2
.
A
d
o
p
t su
b
s
et
s
.
3
.
R
etu
r
n
s.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8776
E
fficien
t d
a
ta
min
in
g
mo
d
el
fo
r
p
r
ed
ictio
n
o
f c
h
r
o
n
ic
kid
n
ey
d
is
ea
s
e
u
s
in
g
w
r
a
p
p
er
…
(
R
a
ma
s
w
a
myred
d
y
A
)
65
Wra
pp
er
M
et
ho
ds
:W
r
ap
p
er
m
et
h
o
d
s
u
s
e
B
est
First,
Sto
ch
asti
c
a
n
d
Heu
r
i
s
tic
Sear
ch
tec
h
n
iq
u
es
f
o
r
s
elec
ti
n
g
t
h
e
s
u
b
s
et
o
f
f
ea
tu
r
e
s
.
A
m
o
d
el
is
tr
ai
n
ed
u
s
i
n
g
d
if
f
er
en
t
co
m
b
in
at
io
n
s
o
f
f
ea
t
u
r
e
s
u
b
s
et
s
an
d
s
co
r
e
is
ass
i
g
n
ed
to
f
ea
t
u
r
es
b
ased
o
n
th
e
m
o
d
el
ac
cu
r
ac
y
a
n
d
th
e
c
o
n
clu
s
io
n
s
d
r
a
w
n
f
r
o
m
t
h
e
p
r
ev
io
u
s
m
o
d
el
th
e
n
a
d
ec
is
io
n
i
s
co
n
s
id
er
ed
w
h
et
h
er
to
ad
d
o
r
r
em
o
v
e
f
ea
tu
r
es
f
r
o
m
th
e
s
u
b
s
et.
E
x
a
m
p
le
s
o
f
w
r
ap
p
er
m
et
h
o
d
s
ar
eFo
r
w
ar
d
Featu
r
e
Selectio
n
,
B
ac
k
w
ar
d
Feat
u
r
e
Selectio
n
an
d
R
ec
u
r
s
i
v
e
Feat
u
r
e
E
li
m
i
n
ati
o
n
.
P
s
eudo
co
de
I
np
ut:
Feat
u
r
e
s
et
S
1.
I
d
en
tify
ca
n
d
id
ate
s
u
b
s
et
sS
2.
W
h
ile!
Sto
p
cr
iter
io
n
(
)
2
.
1
.
A
s
s
es
s
th
e
er
r
o
r
o
f
a
class
if
ier
u
s
i
n
g
s.
2
.
2
.
A
d
o
p
t su
b
s
et
s.
3
.
R
etu
r
n
s.
E
m
be
dd
ed
M
et
ho
d:
T
h
is
m
et
h
o
d
is
a
h
y
b
r
id
ap
p
r
o
ac
h
;
it
co
m
b
in
e
s
b
o
th
Fil
ter
an
d
W
r
ap
p
er
m
et
h
o
d
s
f
o
r
s
elec
ti
n
g
o
p
ti
m
al
f
ea
t
u
r
e
s
u
b
s
et.
4.
CL
AS
SI
F
I
CAT
I
O
N
AL
G
O
RIT
H
M
S
T
h
e
class
i
f
icatio
n
alg
o
r
it
h
m
s
w
e
u
s
e
in
th
e
p
ap
er
ar
e
T
r
ee
B
ag
,
A
d
aB
o
o
s
t,
Gr
ad
ien
t B
o
o
s
tin
g
(
GB
M)
an
d
R
a
n
d
o
m
Fo
r
est.U
n
d
er
b
ag
g
i
n
g
tec
h
n
iq
u
e
T
r
ee
B
ag
,
R
a
n
d
o
m
Fo
r
est
clas
s
if
ier
s
ar
e
u
s
ed
.
A
d
aB
o
o
s
t,
GB
M
co
m
e
s
u
n
d
er
b
o
o
s
tin
g
tec
h
n
iq
u
e.
4
.
1
.
T
re
eBa
g
T
r
ee
B
ag
is
a
n
e
n
s
e
m
b
le
m
ac
h
i
n
e
lear
n
in
g
m
eta
alg
o
r
it
h
m
i
s
u
s
ed
f
o
r
b
o
th
c
lass
if
ica
tio
n
a
n
d
r
eg
r
ess
io
n
m
o
d
el
s
an
d
it
i
s
an
e
x
a
m
p
le
o
f
b
ag
g
i
n
g
tec
h
n
iq
u
e.
T
r
ee
B
ag
u
s
e
s
d
ec
is
io
n
tr
ee
s
class
if
ier
s
,
th
ese
d
ec
is
io
n
tr
ee
s
ar
e
b
u
ilt
o
n
m
u
ltip
le
s
a
m
p
le
d
ata
w
h
er
e
s
a
m
p
le
s
ar
e
tak
en
f
r
o
m
r
an
d
o
m
w
it
h
r
ep
lace
m
e
n
t
f
r
o
m
th
e
o
r
ig
i
n
al
d
ata
an
d
th
e
class
i
f
ier
s
ar
e
ag
g
r
eg
ated
to
f
o
r
m
an
en
s
e
m
b
le
class
i
f
ier
.
I
n
o
r
d
er
to
p
r
ed
ict
th
e
class
lab
el
o
f
test
d
ata,
th
e
test
d
ata
is
g
iv
e
n
as i
n
p
u
t to
t
h
e
en
s
e
m
b
le
cla
s
s
i
f
ier
.
B
ased
o
n
th
e
o
u
tp
u
t
s
o
f
t
h
e
i
n
d
iv
id
u
al
clas
s
i
f
ier
,
en
s
e
m
b
le
clas
s
if
ier
tak
es t
h
e
m
aj
o
r
ity
a
n
d
ass
i
g
n
s
t
h
e
clas
s
lab
el
to
th
e
test
d
ata.
P
s
eudo
co
de
1
.
R
e
p
ea
t '
k
'
ti
m
e
s
.
1
.
1
.
C
r
ea
te
a
r
an
d
o
m
tr
ain
i
n
g
s
et.
1
.
2
.
T
r
ain
a
class
i
f
ier
o
n
r
an
d
o
m
tr
ain
in
g
s
et.
2
.
T
o
test
,
r
u
n
ea
ch
tr
ain
ed
cla
s
s
i
f
ier
.
3.
E
ac
h
class
i
f
ier
v
o
tes o
n
t
h
e
o
u
tp
u
t t
h
en
ta
k
es
m
aj
o
r
it
y
.
4
.
2
.
Ada
B
o
o
s
t
A
d
aB
o
o
s
t
is
an
ex
a
m
p
le
o
f
b
o
o
s
tin
g
tec
h
n
iq
u
e
a
n
d
it
is
a
n
e
n
s
e
m
b
le
m
ac
h
i
n
e
lear
n
in
g
m
eta
alg
o
r
it
h
m
u
s
ed
f
o
r
b
o
th
clas
s
i
f
icatio
n
a
n
d
r
eg
r
ess
io
n
p
r
o
b
le
m
s
.
A
d
aB
o
o
s
t p
r
o
d
u
ce
s
s
tr
o
n
g
cla
s
s
i
f
ier
b
y
co
m
b
in
i
n
g
w
ea
k
class
i
f
ier
s
;
th
e
s
tr
o
n
g
class
if
ie
r
co
v
er
s
th
e
i
n
s
ta
n
ce
s
w
h
ic
h
a
r
e
n
o
t
co
v
er
ed
b
y
i
n
d
i
v
i
d
u
al
w
ea
k
clas
s
i
f
ier
s
s
o
th
at
th
e
p
er
f
o
r
m
an
ce
o
f
m
o
d
el
is
p
r
o
d
u
ce
d
.
A
d
aB
o
o
s
t
u
s
es
d
ec
is
io
n
tr
ee
alg
o
r
ith
m
s
f
o
r
class
i
f
icatio
n
an
d
th
e
p
r
o
ce
d
u
r
e
f
o
r
A
d
aB
o
o
s
t
class
i
f
ier
is
g
i
v
en
in
th
e
p
s
e
u
d
o
co
d
e.
T
h
e
d
ec
is
io
n
tr
ee
in
A
d
aB
o
o
s
t
co
n
s
i
s
ts
o
f
o
n
e
lev
el
tr
ee
ca
lled
Dec
is
io
n
s
t
u
m
p
s
.
P
s
eudo
co
de
1.
T
h
e
d
ata
s
et
co
n
s
is
ts
o
f
(
x
1
,
y
1
)
,
(
x
2
,
y
2
)
,
(
Xn
,
y
n
)
in
s
t
an
ce
s
,
w
eig
h
t
s
ar
e
ass
ig
n
ed
to
all
in
s
ta
n
ce
s
.
0
1
:
(
)
i
D
i
N
w
h
er
e
N
i
s
th
e
to
tal
n
u
m
b
er
o
f
in
s
ta
n
ce
s
.
2.
A
r
an
d
o
m
s
a
m
p
le
D
k
is
ta
k
en
f
r
o
m
t
h
e
Data
(
D)
.
3.
Tr
ain
th
e
class
i
f
ier
h
k
o
n
D
k
(
s
a
m
p
le
d
ata)
.
4.
T
est th
e
class
i
f
ier
h
k
o
n
o
v
er
all
Data
(
D)
an
d
ca
lcu
late
t
h
e
E
r
r
o
r
r
ate
(
E
k
)
o
n
h
k
.
5.
C
alcu
late
t
h
e
v
o
ti
n
g
p
o
w
er
o
f
class
i
f
ier
o
n
k
th
s
a
m
p
le.
1
1
l
o
g
2
k
k
k
E
E
h
er
e
k
is
th
e
v
o
ti
n
g
p
o
w
er
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8776
I
n
t J
I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
8
,
No
.
2,
A
u
g
u
s
t
201
9
:
63
–
70
66
6.
Up
d
ate
th
e
w
ei
g
h
ts
o
f
t
h
e
in
s
tan
ce
s
w
h
ich
ar
e
in
co
r
r
ec
tl
y
clas
s
i
f
ied
b
y
cla
s
s
i
f
ie
r
h
k
.
.
)
(
1
()
()
k
i
k
i
y
h
x
k
k
k
D
i
e
Di
Z
,
Z
k
is
th
e
n
o
r
m
al
izatio
n
f
u
n
cti
o
n
s
u
c
h
t
h
at
1
(
)
1
N
k
i
Di
.
7.
R
ep
ea
t step
2
to
s
tep
6
f
o
r
k
ti
m
es,
w
h
er
e
k
is
th
e
n
o
o
f
s
a
m
p
les.
8.
Fin
all
y
a
n
e
n
s
e
m
b
le
b
o
o
s
ted
class
i
f
ier
i
s
o
b
tain
ed
1
(
)
(
(
)
)
k
ii
i
H
x
s
ig
n
h
x
h
er
e
H(
x
)
is
a
n
en
s
e
m
b
le
clas
s
if
ier
.
4
.
3
.
G
ra
dient
B
o
o
s
t
ing
(
G
B
M
)
GB
M
is
an
en
s
e
m
b
le
m
ac
h
i
n
e
lear
n
in
g
m
eta
alg
o
r
it
h
m
wh
ich
co
m
b
in
e
s
th
e
w
ea
k
cla
s
s
if
ier
s
an
d
p
r
o
d
u
ce
s
a
s
tr
o
n
g
clas
s
i
f
ier
.
I
t
b
u
ild
s
th
e
m
o
d
el
o
n
th
e
s
a
m
p
l
e
d
ata
an
d
test
th
e
m
o
d
el
o
n
t
h
e
o
r
ig
in
al
d
ata
th
e
n
u
p
d
ates th
e
w
ei
g
h
ts
o
f
th
e
in
s
t
an
ce
s
w
h
ic
h
ar
e
in
co
r
r
ec
tl
y
cl
ass
i
f
ied
b
y
th
e
m
o
d
el.
T
h
is
p
r
o
ce
s
s
r
ep
ea
ts
ti
ll
t
h
e
m
ax
i
m
u
m
n
u
m
b
er
o
f
m
o
d
els a
r
e
r
ea
ch
ed
o
r
th
e
m
o
d
el
ac
h
ie
v
es t
h
e
h
i
g
h
est ac
c
u
r
ac
y
.
P
s
eudo
co
de
1.
I
n
itialize
f
w
i
t
h
a
co
n
s
ta
n
t.
2
.
Fo
r
k
=1
to
M
d
o
2
.
1
.
C
o
m
p
u
te
t
h
e
n
eg
at
iv
e
g
r
ad
ien
t g
k
(
x
)
.
2
.
2
Fit
a
m
o
d
el
h
(
x
,
ө
k
).
2
.
3
C
h
o
o
s
e
th
e
b
est g
r
ad
ien
t st
ep
-
s
ize
k
.
,
1
,
a
r
g
m
in
(
)
(
k
i
k
i
i
k
y
f
x
h
x
.
2
.
4
Up
d
ate
th
e
f
u
n
ct
io
n
esti
m
ate.
1
,
k
k
k
k
f
f
h
x
3
.
E
n
d
f
o
r
.
4
.
4
.
Ra
nd
o
m
F
o
re
s
t
R
an
d
o
m
Fo
r
est
i
s
a
n
e
n
s
e
m
b
le
m
ac
h
i
n
e
lear
n
in
g
m
eta
a
lg
o
r
it
h
m
w
h
ich
is
u
s
ed
f
o
r
b
o
th
c
las
s
if
ica
tio
n
an
d
r
eg
r
ess
io
n
p
r
o
b
lem
s
.
R
an
d
o
m
Fo
r
est
i
s
s
i
m
ilar
to
B
ag
g
i
n
g
tec
h
n
iq
u
e
b
u
t
w
it
h
a
s
li
g
h
t
ch
an
g
e.
I
n
b
ag
g
in
g
class
i
f
ier
s
ar
e
b
u
ilt
o
n
all
th
e
f
ea
tu
r
es
o
f
tr
ai
n
i
n
g
s
et
b
u
t
in
R
a
n
d
o
m
Fo
r
est
class
i
f
ier
s
ar
e
b
u
ilt
o
n
r
an
d
o
m
f
ea
t
u
r
es
o
f
tr
ain
in
g
s
et.
R
a
n
d
o
m
Fo
r
est
f
o
llo
w
s
a
g
e
n
er
al
r
u
l
e
it
is
“
T
h
e
n
u
m
b
er
o
f
r
a
n
d
o
m
f
ea
tu
r
e
s
(
m
)
tak
e
n
f
r
o
m
all
t
h
e
f
ea
tu
r
es (
p
)
o
f
th
e
tr
ain
in
g
s
et
(
D)
is
m
=
s
q
u
ar
e
r
o
o
t(
p
)
”
.
5.
P
RO
P
O
SE
D
M
E
T
H
O
DO
L
O
G
Y
I
n
th
i
s
s
ec
tio
n
a
m
eth
o
d
o
lo
g
y
is
p
r
o
p
o
s
ed
f
o
r
class
if
y
in
g
th
e
ch
r
o
n
ic
k
id
n
e
y
d
i
s
ea
s
e.
T
h
e
s
tep
s
in
v
o
l
v
ed
in
t
h
e
Mo
d
el
Fra
m
e
w
o
r
k
ar
e:
Ste
p 1
:
Da
t
a
s
et
C
h
r
o
n
ic
Kid
n
e
y
d
atase
t
is
tak
e
n
f
r
o
m
t
h
e
U
C
I
r
ep
o
s
ito
r
y
,
t
h
i
s
d
ataset
co
n
s
i
s
ts
o
f
2
5
attr
ib
u
t
e
an
d
4
0
0
in
s
ta
n
ce
s
.
T
h
is
d
atase
t is p
r
ep
ar
ed
f
o
r
m
t
h
e
p
r
ev
io
u
s
l
y
d
ia
g
n
o
s
ed
p
atien
ts
.
Ste
p 2
:
P
re
-
pro
ce
s
s
ing
T
h
e
d
ataset
co
n
s
i
s
t
s
o
f
m
is
s
in
g
v
al
u
es;
t
h
is
m
a
y
ca
u
s
e
tr
o
u
b
le
in
a
n
al
y
s
i
s
.
T
h
er
e
ar
e
s
e
v
er
al
t
ec
h
n
iq
u
es
to
h
an
d
le
th
e
m
i
s
s
i
n
g
v
alu
e
s
,
s
o
m
e
o
f
t
h
e
m
ar
e
ig
n
o
r
es
t
h
e
m
is
s
i
n
g
v
al
u
es,
r
ep
lace
s
t
h
e
m
is
s
i
n
g
v
al
u
es
.
T
h
e
p
o
w
er
o
f
an
al
y
s
i
s
is
d
eg
r
ad
ed
w
h
e
n
m
i
s
s
i
n
g
v
al
u
es
ar
e
ig
n
o
r
ed
;
s
o
to
s
tr
en
g
th
e
n
th
e
a
n
al
y
s
is
r
ep
lace
tech
n
iq
u
e
is
c
h
o
s
en
.
W
e
u
s
e
KNN
i
m
p
u
tatio
n
al
g
o
r
ith
m
to
r
ep
lace
t
h
e
m
is
s
i
n
g
v
al
u
es
w
it
h
t
h
e
m
o
s
t
f
r
eq
u
e
n
t
n
ea
r
er
o
b
s
er
v
atio
n
s
.
Ste
p 3
:
F
ea
t
ure
s
elec
t
io
n
On
ce
th
e
d
ata
is
p
r
e
-
p
r
o
ce
s
s
ed
,
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
e
is
ap
p
lied
o
n
th
e
d
ata
s
et
to
g
et
th
e
s
ig
n
i
f
ica
n
t a
ttrib
u
tes.
W
e
co
n
s
id
er
ed
Fil
ter
an
d
W
r
a
p
p
er
m
et
h
o
d
s
o
f
f
ea
tu
r
e
s
elec
tio
n
tec
h
n
iq
u
es.
Un
d
er
Fil
te
r
m
et
h
o
d
s
w
e
h
a
v
e
ch
o
s
e
n
I
nfo
r
m
a
t
io
n
g
a
in,
G
a
in
ra
t
io
,
Ch
i
-
s
qu
a
re
d
t
est
a
nd
co
ns
is
t
enc
y
m
ea
s
ure.
Un
d
er
W
r
ap
p
e
r
m
et
h
o
d
RF
E
m
ea
s
u
r
e
is
co
n
s
id
er
ed
.
In
ea
ch
m
ea
s
u
r
e
o
f
t
h
e
Fea
tu
r
e
s
e
lectio
n
tech
n
iq
u
e,
w
e
w
il
l
co
n
s
id
er
th
e
to
p
1
5
attr
i
b
u
tes
th
is
i
s
b
ec
au
s
e
i
n
[
6
]
r
esear
ch
er
ap
p
lied
r
an
k
in
g
alg
o
r
it
h
m
o
n
th
e
ch
r
o
n
ic
d
ata
an
d
o
b
s
er
v
ed
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
clas
s
i
f
ier
s
o
n
to
p
5
,
1
0
,
1
5
,
2
0
an
d
2
5
attr
ib
u
tes
an
d
o
b
s
er
v
ed
th
at
t
h
e
m
o
d
els
ar
e
g
iv
i
n
g
p
r
o
m
i
s
i
n
g
r
es
u
lt
s
o
n
to
p
1
5
attr
ib
u
tes.
Ste
p 4
:
Cla
s
s
if
ica
t
io
n a
lg
o
rit
h
m
s
w
it
h P
a
ra
m
et
er
T
u
nin
g
A
p
ar
a
m
eter
t
u
n
in
g
i
s
t
h
e
p
r
o
ce
s
s
o
f
f
i
n
d
in
g
th
e
b
e
s
t
p
ar
a
m
eter
f
o
r
an
al
g
o
r
ith
m
to
b
o
o
s
t
its
p
er
f
o
r
m
a
n
ce
.
T
h
er
e
is
t
w
o
wa
y
s
f
o
r
p
ar
am
e
ter
tu
n
i
n
g
:
(
i)
Gr
id
s
ea
r
ch
p
ar
a
m
eter
t
u
n
i
n
g
(
ii)
R
an
d
o
m
s
ea
r
ch
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8776
E
fficien
t d
a
ta
min
in
g
mo
d
el
fo
r
p
r
ed
ictio
n
o
f c
h
r
o
n
ic
kid
n
ey
d
is
ea
s
e
u
s
in
g
w
r
a
p
p
er
…
(
R
a
ma
s
w
a
myred
d
y
A
)
67
p
ar
am
eter
tu
n
i
n
g
.
I
n
Gr
id
s
ea
r
ch
ap
p
r
o
ac
h
,
u
s
er
w
i
ll
s
p
ec
if
y
t
h
e
d
if
f
er
en
t
v
a
lu
e
s
f
o
r
a
g
iv
en
p
ar
a
m
eter
th
e
n
m
o
d
el
e
v
al
u
ates
ea
ch
v
al
u
e
i
n
th
e
g
r
id
an
d
g
iv
e
t
h
e
b
est
v
alu
e
a
m
o
n
g
t
h
e
g
i
v
e
n
v
al
u
es.
I
n
R
an
d
o
m
s
ea
r
c
h
ap
p
r
o
ac
h
,
p
ar
am
etr
ic
v
a
lu
e
s
a
r
e
s
a
m
p
led
f
r
o
m
a
r
an
d
o
m
d
is
tr
ib
u
tio
n
f
o
r
f
i
x
ed
n
u
m
b
er
o
f
i
ter
atio
n
s
,
a
n
d
th
e
n
m
o
d
el
e
v
al
u
ates
ea
c
h
p
ar
a
m
et
r
ic
co
m
b
i
n
atio
n
a
n
d
g
i
v
e
b
est
p
ar
am
eter
co
m
b
i
n
atio
n
v
al
u
es
.
W
e
w
i
ll
co
n
s
id
er
R
an
d
o
m
s
ea
r
ch
p
ar
a
m
eter
tu
n
i
n
g
tec
h
n
iq
u
e,
b
ec
au
s
e
i
n
Gr
id
s
ea
r
ch
ap
p
r
o
ac
h
u
s
er
s
h
o
u
ld
s
u
p
p
l
y
v
al
u
es w
h
ic
h
m
a
y
n
o
t g
i
v
e
o
p
ti
m
a
l p
ar
a
m
et
er
s
.
Ste
p 5
:
P
er
f
o
rm
a
nce
a
na
ly
s
i
s
T
r
ee
B
ag
,
A
d
aB
o
o
s
t,
GB
M
an
d
R
an
d
o
m
Fo
r
est
clas
s
i
f
ier
s
ar
e
co
m
p
ar
ed
o
n
ea
ch
m
ea
s
u
r
e
o
f
t
h
e
f
ea
t
u
r
e
s
elec
tio
n
tec
h
n
iq
u
e
an
d
t
h
e
cla
s
s
i
f
ier
w
h
ich
s
h
o
w
s
b
etter
p
r
o
m
is
in
g
r
es
u
lts
i
s
id
en
ti
f
ied
.
6.
RE
SU
L
T
ANAL
YSI
S
T
o
id
en
tify
th
e
b
est
e
n
s
e
m
b
le
class
i
f
ier
f
o
r
ch
r
o
n
ic
k
i
d
n
e
y
d
is
ea
s
e
p
r
ed
ictio
n
w
e
p
er
f
o
r
m
ed
ex
p
er
i
m
e
n
ts
i
n
R
.
6
.
1
.
T
re
e
B
a
g
T
r
ee
B
ag
class
i
f
ier
i
s
b
ased
o
n
b
ag
g
i
n
g
tec
h
n
iq
u
e.
P
er
f
o
r
m
a
n
ce
o
f
t
h
e
T
r
ee
B
ag
class
i
f
ier
i
s
co
m
p
ar
ed
o
n
ea
ch
m
ea
s
u
r
e
o
f
f
il
ter
an
d
w
r
ap
p
er
m
eth
o
d
s
w
h
ic
h
ca
n
b
e
v
ie
w
ed
in
T
ab
le
1
.
T
ab
le
1
.
T
r
ee
B
ag
C
lass
i
f
ier
P
er
f
o
r
m
an
ce
o
n
Fil
ter
an
d
W
r
ap
p
er
Me
th
o
d
s
Fe
a
t
u
r
e
s
e
l
e
c
t
i
o
n
Ka
p
p
a
A
c
c
u
r
a
c
y
(
%
)
Fi
l
t
e
r
m
e
t
h
o
d
I
n
f
o
r
mat
i
o
n
g
a
i
n
0
.
9
3
4
9
9
6
.
9
7
G
a
i
n
r
a
t
i
o
0
.
9
3
4
9
9
6
.
9
7
C
h
i
-
sq
u
a
r
e
d
t
e
st
0
.
9
3
4
9
9
6
.
9
7
C
o
n
si
s
t
e
n
c
y
0
.
9
5
6
4
9
6
.
9
7
W
r
a
p
p
e
r
m
e
t
h
o
d
R
F
E
0
.
9
5
6
4
9
7
.
9
8
6.
2
.
Ada
B
o
o
s
t
A
d
aB
o
o
s
t
class
if
ier
i
s
b
ased
o
n
b
o
o
s
tin
g
tec
h
n
iq
u
e
an
d
R
an
d
o
m
s
ea
r
ch
p
ar
a
m
eter
t
u
n
i
n
g
is
ap
p
lied
o
n
A
d
aB
o
o
s
t p
ar
a
m
eter
s
(
i)
n
I
ter
(
n
u
m
b
er
o
f
iter
at
io
n
s
)
a
n
d
(
ii)
Me
th
o
d
ca
n
b
e
v
ie
w
ed
in
T
ab
le
2
.
T
ab
le
2
.
P
er
f
o
r
m
a
n
ce
o
f
t
h
e
Ad
aB
o
o
s
t
C
lass
i
f
ier
o
n
E
ac
h
M
ea
s
u
r
e
o
f
Fi
lter
a
n
d
W
r
ap
p
er
Me
th
o
d
s
Fe
a
t
u
r
e
s
e
l
e
c
t
i
o
n
Pa
r
a
m
e
t
e
r
s
Ka
p
p
a
A
c
c
u
r
a
c
y
(
%
)
Fi
l
t
e
r
m
e
t
h
o
d
s
n
It
e
r
M
e
t
h
o
d
I
n
f
o
r
mat
i
o
n
g
a
i
n
50
A
d
a
B
o
o
st
.
M
1
0
.
9
3
4
9
9
6
.
9
7
G
a
i
n
r
a
t
i
o
50
R
e
a
l
A
d
a
B
o
o
st
0
.
9
5
6
4
9
7
.
9
8
C
h
i
-
sq
u
a
r
e
d
t
e
st
50
A
d
a
B
o
o
st
.
M
1
0
.
9
3
4
9
9
6
.
9
7
C
o
n
si
s
t
e
n
c
y
50
A
d
a
B
o
o
st
.
M
1
0
.
9
3
4
9
9
6
.
9
7
W
r
a
p
p
e
r
m
e
t
h
o
d
R
F
E
50
R
e
a
l
A
d
a
B
o
o
st
0
.
9
5
6
8
9
7
.
9
8
6
.
3
.
G
B
M
GB
M
a
Gr
ad
ien
t
B
o
o
s
tin
g
M
ac
h
in
e
lear
n
i
n
g
a
lg
o
r
it
h
m
is
b
ased
o
n
b
o
o
s
tin
g
tech
n
iq
u
e
a
n
d
R
an
d
o
m
s
ea
r
ch
t
u
n
i
n
g
tech
n
iq
u
e
is
ap
p
lied
w
it
h
th
e
GB
M
p
ar
a
m
et
er
s
n
.
tr
ee
s
(
n
u
m
b
er
o
f
tr
ee
s
)
,
I
n
ter
ac
tio
n
.
d
ep
th
,
s
h
r
i
n
k
a
g
e
a
n
d
n
.
m
i
n
o
b
s
in
n
o
d
e
(
m
i
n
i
m
u
m
n
u
m
b
er
o
f
o
b
s
er
v
atio
n
s
in
ter
m
in
al
n
o
d
e
o
f
a
tr
ee
)
.
P
ar
am
eter
s
Sh
r
i
n
k
a
g
e
an
d
I
n
ter
ac
t
io
n
.
De
p
th
d
ef
au
lt
s
et
s
o
th
e
v
al
u
es o
f
0
.
1
an
d
1
0
as sh
o
w
n
i
n
T
ab
le
3
.
T
ab
le
3
.
GB
M
C
lass
if
ier
P
er
f
o
r
m
a
n
ce
o
n
E
ac
h
Me
a
s
u
r
e
o
f
Fil
ter
an
d
W
r
ap
p
er
Me
th
o
d
s
Fe
a
t
u
r
e
s
e
l
e
c
t
i
o
n
Pa
r
a
m
e
t
e
r
s
Ka
p
p
a
A
c
c
u
r
a
c
y
(
%
)
Fi
l
t
e
r
m
e
t
h
o
d
s
n
.
t
r
e
e
s
In
t
e
r
a
c
t
i
o
n
.
D
e
p
t
h
I
n
f
o
r
mat
i
o
n
g
a
i
n
1
5
0
1
0
.
9
7
8
5
99
G
a
i
n
r
a
t
i
o
1
0
0
2
0
.
9
7
8
5
99
C
h
i
-
sq
u
a
r
e
d
t
e
st
1
5
0
2
0
.
9
7
8
5
99
C
o
n
si
s
t
e
n
c
y
1
5
0
1
0
.
9
7
8
5
99
W
r
a
p
p
e
r
m
e
t
h
o
d
R
F
E
50
2
0
.
9
7
8
3
99
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8776
I
n
t J
I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
8
,
No
.
2,
A
u
g
u
s
t
201
9
:
63
–
70
68
6.
4
.
Ra
nd
o
m
F
o
re
s
t
R
an
d
o
m
Fo
r
est
i
s
a
n
e
n
s
e
m
b
l
e
class
i
f
ier
a
n
d
r
an
d
o
m
s
ea
r
c
h
tech
n
iq
u
e
is
ap
p
lied
w
it
h
t
h
e
p
ar
am
eter
m
tr
y
.
P
er
f
o
r
m
a
n
ce
o
f
r
an
d
o
m
f
o
r
est cla
s
s
if
ier
o
n
ea
c
h
m
et
h
o
d
s
ca
n
b
e
v
ie
w
ed
in
T
ab
le
4
.
T
ab
le
4
.
P
er
f
o
r
m
a
n
ce
o
f
R
a
n
d
o
m
Fo
r
est C
la
s
s
i
f
ier
o
n
E
ac
h
Me
asu
r
e
o
f
F
ilter
an
d
W
r
ap
p
e
r
Me
th
o
d
s
Fe
a
t
u
r
e
s
e
l
e
c
t
i
o
n
p
a
r
a
m
e
t
e
r
M
t
r
y
Ka
p
p
a
A
c
c
u
r
a
c
y
(
%
)
Fi
l
t
e
r
m
e
t
h
o
d
I
n
f
o
r
mat
i
o
n
g
a
i
n
2
0
.
9
7
8
3
99
G
a
i
n
r
a
t
i
o
2
0
.
9
7
8
3
99
C
h
i
-
sq
u
a
r
e
d
t
e
st
2
0
.
9
7
8
3
99
C
o
n
si
s
t
e
n
c
y
2
0
.
9
3
4
1
9
6
.
9
7
W
r
a
p
p
e
r
m
e
t
h
o
d
R
F
E
2
0
.
9
5
6
8
9
7
.
9
8
6
.
1
.
1
.
Co
m
pa
riso
n
o
f
perf
o
r
m
a
nce
o
f
T
re
eB
a
g
,
Ada
B
o
o
s
t
,
G
B
M
a
nd
Ra
nd
o
m
F
o
re
s
t
cla
s
s
if
iers
o
n
ea
ch
m
ea
s
ure
o
f
F
ilte
r
m
et
ho
d
s
a
nd
Wra
pp
er
m
et
ho
ds
E
n
s
e
m
b
le
class
i
f
ier
s
T
r
ee
B
ag
,
A
d
aB
o
o
s
t,
GB
M
an
d
R
an
d
o
m
Fo
r
est
ar
e
co
m
p
ar
ed
o
n
ea
c
h
m
ea
s
u
r
e
o
f
Featu
r
e
s
e
lectio
n
t
ec
h
n
iq
u
e
s
w
h
ic
h
ca
n
b
e
s
h
o
w
n
i
n
t
h
e
F
ig
u
r
e
1
,
2
,
3
,
4
an
d
5
.
P
er
f
o
r
m
a
nce
o
f
t
he
cla
s
s
if
iers a
t
I
nfo
r
m
a
t
io
n G
a
i
n M
ea
s
ure
T
r
ee
B
ag
,
A
d
aB
o
o
s
t,
GB
M
an
d
R
an
d
o
m
Fo
r
est
cla
s
s
i
f
ier
s
ar
e
co
m
p
ar
ed
at
I
n
f
o
r
m
atio
n
g
ai
n
m
ea
s
u
r
e
w
h
ic
h
is
s
h
o
w
n
i
n
th
e
Fig
u
r
e
1
an
d
o
b
s
er
v
ed
t
h
at
GB
M,
R
an
d
o
m
Fo
r
est
h
as
g
i
v
en
h
ig
h
es
t
ac
cu
r
ac
y
o
f
9
9
%
w
h
e
n
co
m
p
ar
ed
to
o
th
er
class
i
f
ier
s
.
Fig
u
r
e
1
.
C
o
m
p
ar
is
o
n
o
f
cla
s
s
if
ier
s
at
i
n
f
o
r
m
atio
n
g
ai
n
m
ea
s
u
r
e
P
er
f
o
r
m
a
nce
o
f
t
he
cla
s
s
if
iers a
t
G
a
in ra
t
io
m
ea
s
ure
T
r
ee
B
ag
,
A
d
aB
o
o
s
t,
GB
M
an
d
R
an
d
o
m
Fo
r
est
cla
s
s
i
f
ier
s
ar
e
co
m
p
ar
ed
at
Gai
n
r
atio
m
ea
s
u
r
e
w
h
ic
h
is
s
h
o
w
n
in
t
h
e
Fi
g
u
r
e
2
an
d
o
b
s
er
v
ed
th
at
GB
M,
R
an
d
o
m
Fo
r
est
h
as
g
i
v
e
n
h
i
g
h
e
s
t
ac
c
u
r
ac
y
o
f
9
9
%
w
h
e
n
co
m
p
ar
ed
to
an
o
th
er
clas
s
i
f
ier
s
.
Fig
u
r
e
2
.
C
o
m
p
ar
is
o
n
o
f
cla
s
s
if
ier
s
at
g
ai
n
r
atio
m
ea
s
u
r
e
95
96
97
98
99
100
T
re
e
Ba
g
A
d
aB
o
o
s
t
G
BM
R
an
d
o
m
F
o
re
s
t
A
c
c
u
ra
c
y
A
c
c
u
racy
95
96
97
98
99
100
T
re
e
Ba
g
A
d
aB
o
o
s
t
G
BM
R
an
d
o
m
F
o
re
s
t
A
c
c
u
ra
c
y
A
c
c
u
racy
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8776
E
fficien
t d
a
ta
min
in
g
mo
d
el
fo
r
p
r
ed
ictio
n
o
f c
h
r
o
n
ic
kid
n
ey
d
is
ea
s
e
u
s
in
g
w
r
a
p
p
er
…
(
R
a
ma
s
w
a
myred
d
y
A
)
69
P
er
f
o
r
m
a
nce
o
f
t
he
cla
s
s
if
iers a
t
Chi
-
s
qu
a
re
d t
est
T
r
ee
B
ag
,
A
d
aB
o
o
s
t,
GB
M
an
d
R
an
d
o
m
Fo
r
est
c
lass
if
ier
s
ar
e
co
m
p
ar
ed
at
C
h
i
-
s
q
u
ar
ed
test
m
ea
s
u
r
e
w
h
ic
h
is
s
h
o
w
n
i
n
th
e
Fig
u
r
e
3
an
d
o
b
s
er
v
ed
th
at
GB
M,
R
an
d
o
m
Fo
r
est
h
as
g
i
v
en
h
ig
h
es
t
ac
cu
r
ac
y
o
f
9
9
%
w
h
e
n
co
m
p
ar
ed
t
o
o
th
er
class
i
f
ier
s
.
Fig
u
r
e
3
.
C
o
m
p
ar
is
o
n
o
f
cla
s
s
if
ier
s
at
c
h
i
-
s
q
u
ar
ed
test
m
ea
s
u
r
e
P
er
f
o
r
m
a
nce
o
f
t
he
cla
s
s
if
iers a
t
Co
ns
is
t
ency
m
ea
s
ure
T
r
ee
B
ag
,
A
d
aB
o
o
s
t,
GB
M
an
d
R
an
d
o
m
Fo
r
est
cla
s
s
i
f
ier
s
ar
e
co
m
p
ar
ed
at
co
n
s
is
ten
c
y
m
ea
s
u
r
e
w
h
ic
h
is
s
h
o
w
n
i
n
t
h
e
F
ig
u
r
e
4
a
n
d
o
b
s
er
v
ed
th
at
GB
M
h
as
g
i
v
en
h
ig
h
e
s
t
ac
c
u
r
ac
y
o
f
9
9
%
w
h
e
n
co
m
p
ar
ed
to
a
n
o
th
e
r
class
i
f
ier
s
.
Fig
u
r
e
4
.
C
o
m
p
ar
is
o
n
o
f
cla
s
s
if
ier
s
at
co
n
s
is
ten
c
y
m
ea
s
u
r
e
P
er
f
o
r
m
a
nce
o
f
t
he
cla
s
s
if
iers a
t
RF
E
m
ea
s
ure
T
r
ee
B
ag
,
A
d
aB
o
o
s
t,
GB
M
an
d
R
an
d
o
m
Fo
r
est
clas
s
i
f
ier
s
ar
e
co
m
p
ar
ed
at
R
FE
m
ea
s
u
r
e
w
h
ich
i
s
s
h
o
w
n
i
n
th
e
Fi
g
u
r
e
5
an
d
o
b
s
er
v
ed
th
at
GB
M
h
as
g
iv
e
n
h
i
g
h
est
ac
cu
r
ac
y
o
f
9
9
%
w
h
e
n
co
m
p
ar
ed
to
an
o
th
er
class
i
f
ier
s
.
Fig
u
r
e
5
.
C
o
m
p
ar
is
o
n
o
f
c
la
s
s
if
ier
s
at
R
FE
m
ea
s
u
r
e
95
96
97
98
99
100
T
re
e
Ba
g
A
d
aB
o
o
s
t
G
BM
R
an
d
o
m F
o
re
s
t
A
c
c
u
ra
c
y
A
c
c
u
racy
95
96
97
98
99
100
T
re
e
Ba
g
A
d
aB
o
o
s
t
G
BM
R
an
d
o
m F
o
re
s
t
A
c
c
u
ra
c
y
A
c
c
u
racy
97
97.5
98
98
.5
99
99.5
T
re
e
Ba
g
A
d
aB
o
o
s
t
G
BM
R
an
d
o
m F
o
re
s
t
A
c
c
u
ra
c
y
A
c
c
u
racy
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8776
I
n
t J
I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
8
,
No
.
2,
A
u
g
u
s
t
201
9
:
63
–
70
70
T
r
ee
B
ag
,
A
d
aB
o
o
s
t,
GB
M
an
d
R
an
d
o
m
Fo
r
est
class
i
f
ier
s
ar
e
co
m
p
ar
ed
at
ea
ch
m
ea
s
u
r
e
o
f
Fil
ter
an
d
W
r
ap
p
e
r
m
eth
o
d
s
.
Fro
m
t
h
e
a
n
al
y
s
i
s
it
is
id
e
n
ti
f
ied
t
h
at
G
B
M
is
g
iv
in
g
co
n
s
i
s
ten
t
ac
cu
r
ac
y
o
f
9
9
%
at
ea
c
h
m
ea
s
u
r
e.
6
.
2
.
2
.
Co
m
pa
riso
n o
f
G
B
M
w
it
h no
r
m
a
l c
la
s
s
if
ier
s
Fro
m
th
e
o
b
s
er
v
atio
n
s
o
n
p
r
ed
ictio
n
o
f
ch
r
o
n
ic
k
id
n
e
y
d
is
ea
s
e
u
s
in
g
en
s
e
m
b
le
class
i
f
ier
s
lik
e
T
r
ee
B
ag
,
A
d
aB
o
o
s
t,
GB
M
an
d
R
an
d
o
m
Fo
r
est.
GB
M
cla
s
s
if
ier
h
a
s
s
h
o
w
n
b
e
s
t
p
r
o
m
is
i
n
g
r
esu
lts
w
h
ic
h
ca
n
b
e
v
ie
w
ed
i
n
T
ab
le
5
.
T
ab
le
5
.
C
o
m
p
ar
is
o
n
o
f
GB
M
w
it
h
t
h
e
E
x
i
s
ted
C
la
s
s
i
f
ier
s
A
p
p
r
o
a
c
h
A
c
c
u
r
a
c
y
(
%
)
N
a
ï
v
e
B
a
y
e
s
96
S
V
M
9
8
.
5
D
e
c
i
si
o
n
T
r
e
e
98
K
N
N
9
7
.
5
GBM
99
GB
M
class
if
ier
is
co
m
p
ar
ed
w
ith
n
o
r
m
a
l
class
i
f
ier
s
an
d
it
is
s
h
o
w
n
t
h
at
GB
M
w
it
h
m
o
r
e
s
t
ab
ilit
y
ca
n
ab
le
to
p
r
e
d
ict
th
e
k
id
n
e
y
d
is
e
ase
w
ith
9
9
% a
cc
u
r
ac
y
.
7.
CO
NCLU
SI
O
N
I
n
th
i
s
Ma
n
u
s
cr
ip
t,
p
r
ed
ictio
n
o
f
ch
r
o
n
ic
k
id
n
e
y
d
i
s
ea
s
e
h
as
b
ee
n
d
o
n
e
b
y
u
s
i
n
g
en
s
e
m
b
le
class
i
f
ier
s
lik
e
T
r
ee
B
ag
,
A
d
aB
o
o
s
t,
Gr
ad
ien
t
B
o
o
s
tin
g
(
GB
M)
an
d
R
an
d
o
m
Fo
r
est
to
attain
m
o
r
e
s
tab
ilit
y
in
p
r
ed
ictio
n
.
A
R
a
n
d
o
m
s
ea
r
c
h
p
ar
am
e
ter
tu
n
i
n
g
tech
n
iq
u
e
i
s
ap
p
lied
alo
n
g
w
it
h
t
h
e
en
s
e
m
b
le
class
if
ie
r
s
to
g
et
th
e
o
p
tim
a
l
p
ar
am
eter
s
an
d
f
ea
t
u
r
e
s
elec
ti
o
n
tech
n
iq
u
es
ar
e
ap
p
lied
to
r
e
tr
iev
e
th
e
s
ig
n
i
f
ica
n
t
f
ea
tu
r
es.
W
e
h
av
e
ch
o
s
e
n
t
h
e
d
if
f
er
e
n
t
m
ea
s
u
r
es o
f
f
ea
t
u
r
es
s
elec
tio
n
tec
h
n
iq
u
e
s
an
d
w
e
c
o
m
p
ar
ed
th
e
e
n
s
e
m
b
le
clas
s
i
f
i
er
s
at
ea
ch
m
ea
s
u
r
e
an
d
f
o
u
n
d
t
h
at
GB
M
is
g
i
v
in
g
h
i
g
h
est
ac
c
u
r
ac
y
o
f
9
9
%
at
all
m
ea
s
u
r
es
o
f
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
es.
w
e
co
n
d
u
cted
th
e
e
x
p
er
i
m
e
n
t
s
o
n
s
m
al
l
a
m
o
u
n
t
o
f
d
ata
(
4
0
0
in
s
t
an
ce
s
)
b
u
t
d
ata
i
s
i
n
cr
ea
s
i
n
g
d
a
y
to
d
a
y
.
I
n
f
u
t
u
r
e,
en
o
r
m
o
u
s
a
m
o
u
n
t
o
f
d
ata
w
il
l
g
e
n
er
ates
o
n
ch
r
o
n
ic
k
id
n
e
y
d
is
ea
s
e
s
o
w
e
w
o
u
ld
lik
e
to
e
x
ten
d
o
u
r
w
o
r
k
o
n
h
an
d
li
n
g
s
u
ch
lar
g
e
s
ca
le
d
ata
f
o
r
d
is
ea
s
e
p
r
ed
ictio
n
.
RE
F
E
R
E
NC
E
S
[1
]
Ru
b
i
n
i,
L
.
Je
rli
n
,
a
n
d
P
.
Esw
a
ra
n
.
"
G
e
n
e
ra
ti
n
g
c
o
m
p
a
ra
ti
v
e
a
n
a
ly
sis
o
f
e
a
rl
y
sta
g
e
p
re
d
ictio
n
o
f
Ch
ro
n
ic
Ki
d
n
e
y
Dise
a
se
.
"
In
ter
n
a
ti
o
n
a
l
OPEN
A
CCES
S
J
o
u
rn
a
l
of
M
o
d
e
rn
E
n
g
i
n
e
e
rin
g
Res
e
a
rc
h
.
V
o
l.
5
,
n
o
.
7
(
2
0
1
5
):
4
9
-
5
5
.
[2
]
Ba
b
y
,
P
.
S
w
a
th
i,
a
n
d
T
.
P
a
n
d
u
ra
n
g
a
V
it
a
l.
"
S
tatisti
c
a
l
a
n
a
ly
sis
a
n
d
p
re
d
ictin
g
k
i
d
n
e
y
d
ise
a
se
s
u
sin
g
m
a
c
h
in
e
lea
rn
in
g
a
lg
o
rit
h
m
s."
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
E
n
g
in
e
e
rin
g
Res
e
a
rc
h
a
n
d
T
e
c
h
n
o
l
o
g
y
,
Vo
l.
4
,
n
o
.
0
7
,
(2
0
1
5
):
2
0
6
-
2
1
0
.
[3
]
V
ij
a
y
a
ra
n
i,
S
.
,
a
n
d
S
.
Dh
a
y
a
n
a
n
d
.
"
Da
ta
m
in
in
g
c
las
si
f
ica
ti
o
n
a
lg
o
rit
h
m
s
f
o
r
k
id
n
e
y
d
ise
a
s
e
p
re
d
ictio
n
."
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
n
Cy
b
e
rn
e
ti
c
s
a
n
d
In
fo
r
ma
ti
c
s (
IJ
CI)
,
V
o
l.
4
,
No
.
4
,
(2
0
1
5
)
:
1
3
-
25
.
[4
]
Je
n
a
,
L
a
m
b
o
d
a
r,
a
n
d
Na
re
n
d
ra
Ku
Ka
m
il
a
.
"
Distrib
u
ted
d
a
ta
m
in
in
g
c
las
sif
ica
ti
o
n
a
lg
o
rit
h
m
s
fo
r
p
re
d
ictio
n
o
f
c
h
ro
n
ic
k
id
n
e
y
d
ise
a
se
.
"
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Eme
rg
in
g
Res
e
a
rc
h
in
M
a
n
a
g
e
me
n
t
a
n
d
T
e
c
h
n
o
lo
g
y
,
V
o
l
.
4
,
n
o
.
1
1
(2
0
1
5
):
1
1
0
-
11
8.
[5
]
S
e
d
ig
h
i,
Zein
a
b
,
Ho
ss
e
in
E
b
ra
h
im
p
o
u
r
-
Ko
m
leh
,
a
n
d
S
e
y
e
d
Ja
lale
d
d
in
M
o
u
sa
v
irad
.
"
Fea
t
u
e
se
lec
ti
o
n
e
f
fec
ts
o
n
k
id
n
e
y
d
e
se
a
se
a
n
a
lys
is."
I
n
T
e
c
h
n
o
l
o
g
y
,
Co
m
m
u
n
ica
ti
o
n
a
n
d
K
n
o
w
led
g
e
(ICT
CK),
2
0
1
5
In
tern
a
ti
o
n
a
l
C
o
n
g
re
ss
o
n
,
p
p
.
455
-
4
5
9
.
IE
EE
,
2
0
1
5
.
[6
]
Ch
e
tt
y
,
Na
g
a
n
n
a
,
Ku
n
w
a
r
S
in
g
h
V
a
isla,
a
n
d
S
i
th
u
D.
S
u
d
a
rsa
n
.
"
Ro
le
o
f
a
tt
ri
b
u
tes
se
lec
ti
o
n
i
n
c
la
ss
if
ica
ti
o
n
o
f
Ch
ro
n
ic
Ki
d
n
e
y
Dise
a
se
p
a
ti
e
n
ts."
In
C
o
m
p
u
ti
n
g
,
Co
m
m
u
n
ica
ti
o
n
a
n
d
S
e
c
u
rit
y
(ICCCS
),
2
0
1
5
In
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
,
p
p
.
1
-
6
.
IEE
E
,
2
0
1
5
.
[7
]
Ku
n
w
a
r,
V
e
e
n
it
a
,
Kh
u
sh
b
o
o
Ch
a
n
d
e
l,
A
.
S
a
iS
a
b
it
h
a
,
a
n
d
A
b
h
a
y
Ba
n
sa
l.
"
Ch
ro
n
ic
Kid
n
e
y
Dise
a
se
a
n
a
l
y
sis
u
sin
g
d
a
ta
min
in
g
c
la
ss
if
ic
a
ti
o
n
tec
h
n
iq
u
e
s."
In
Cl
o
u
d
S
y
ste
m
a
n
d
Big
Da
ta
En
g
in
e
e
rin
g
(Co
n
f
lu
e
n
c
e
),
2
0
1
6
6
t
h
In
ter
n
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
,
p
p
.
3
0
0
-
3
0
5
.
IEE
E
,
2
0
1
6
.
[8
]
T
a
z
in
,
Nu
sra
t,
S
h
a
h
e
d
A
n
z
a
ru
sSab
a
b
,
a
n
d
M
u
h
a
m
m
e
d
T
a
wf
iq
Ch
o
w
d
h
u
ry
.
"
Dia
g
n
o
sis
o
f
Ch
ro
n
ic
Kid
n
e
y
Dise
a
se
u
sin
g
e
ff
e
c
ti
v
e
c
la
ss
if
ica
ti
o
n
a
n
d
fea
tu
re
se
lec
ti
o
n
tec
h
n
iq
u
e
.
"
In
M
e
d
ica
l
E
n
g
in
e
e
rin
g
,
He
a
lt
h
I
n
f
o
r
m
a
ti
c
s
a
n
d
T
e
c
h
n
o
lo
g
y
(M
e
d
iT
e
c
),
2
0
1
6
I
n
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
,
p
p
.
1
-
6
.
I
EE
E,
2
0
1
6
.
[9
]
Bo
u
k
e
n
z
e
,
Ba
sm
a
,
A
b
d
e
lk
ri
m
Ha
q
iq
,
a
n
d
Ha
jar
M
o
u
sa
n
n
if
.
“
Pre
d
i
c
ti
n
g
C
h
ro
n
ic
Ki
d
n
e
y
F
a
il
u
re
Dise
a
se
Us
in
g
D
a
t
a
M
in
in
g
T
e
c
h
n
iq
u
e
s.
”
I
n
tern
a
ti
o
n
a
l
S
y
m
p
o
siu
m
o
n
Ub
i
q
u
it
o
u
s
Ne
t
w
o
rk
in
g
.
A
d
v
a
n
c
e
s
in
U
b
iq
u
it
o
u
s
Ne
tw
o
rk
in
g
2
,
p
p
.
7
0
1
-
7
1
2
.
S
p
rin
g
e
r
S
i
n
g
a
p
o
re
,
2
0
1
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.