I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
p
u
t
er
Science
Vo
l.
41
,
No
.
2
,
Feb
r
u
ar
y
20
2
6
,
p
p
.
64
5
~
65
4
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ee
cs
.v
41
.
i
2
.
pp
64
5
-
65
4
645
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
M
a
chine learning
m
o
dels
in
the
en
ha
nce
m
ent
of
P
S
E
in
hig
h
-
di
m
ensio
na
l
so
cio
econ
o
m
i
c da
ta: a review
G
ene
M
a
rc
k
B
.
Ca
t
edrilla
1,
2
,
J
o
ey
Av
iles
1
1
A
n
g
e
l
e
s Un
i
v
e
r
si
t
y
F
o
u
n
d
a
t
i
o
n
(
A
U
F
)
,
A
n
g
e
l
e
s,
P
h
i
l
i
p
p
i
n
e
s
2
C
o
l
l
e
g
e
o
f
C
o
mp
u
t
e
r
S
t
u
d
i
e
s,
L
a
g
u
n
a
S
t
a
t
e
P
o
l
y
t
e
c
h
n
i
c
U
n
i
v
e
r
si
t
y
,
L
o
s B
a
ñ
o
s,
P
h
i
l
i
p
p
i
n
e
s
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Au
g
12
,
2025
R
ev
i
s
ed
Dec
29
,
2
0
2
5
A
cc
ep
ted
J
an
11
,
2
0
2
6
T
h
is
stu
d
y
re
v
ie
w
s
th
e
u
se
o
f
m
a
c
h
in
e
lea
rn
in
g
(M
L
)
tec
h
n
i
q
u
e
s
t
o
im
p
ro
v
e
p
ro
p
e
n
sity
sc
o
re
(P
S
)
e
stim
a
ti
o
n
in
h
ig
h
-
d
im
e
n
sio
n
a
l
so
c
io
e
c
o
n
o
m
ic
d
a
ta.
T
ra
d
it
io
n
a
l
lo
g
isti
c
re
g
re
ss
io
n
(LR)
o
f
ten
p
e
rf
o
r
m
s
p
o
o
rly
u
n
d
e
r
n
o
n
li
n
e
a
r
a
n
d
c
o
m
p
lex
c
o
v
a
riate
stru
c
tu
re
s,
lea
d
in
g
t
o
b
ias
a
n
d
m
o
d
e
l
m
is
s
p
e
c
if
i
c
a
ti
o
n
.
A
c
ro
ss
th
e
re
v
iew
e
d
stu
d
ies
,
e
n
se
m
b
le
m
e
th
o
d
s
su
c
h
a
s
ra
n
d
o
m
f
o
re
sts
(RF
)
a
n
d
g
ra
d
i
e
n
t
b
o
o
sti
n
g
,
a
n
d
d
e
e
p
lea
rn
i
n
g
m
o
d
e
ls
c
o
n
siste
n
tl
y
a
c
h
iev
e
d
b
e
tt
e
r
c
o
v
a
riate
b
a
lan
c
e
,
lo
w
e
r
b
ias
,
a
n
d
g
re
a
ter
f
le
x
ib
il
it
y
th
a
n
c
o
n
v
e
n
ti
o
n
a
l
a
p
p
r
o
a
c
h
e
s,
w
h
il
e
c
las
sif
ic
a
ti
o
n
-
b
a
se
d
m
e
th
o
d
s
im
p
ro
v
e
d
p
e
rf
o
r
m
a
n
c
e
in
i
m
b
a
la
n
c
e
d
d
a
tas
e
ts.
T
h
e
re
v
ie
w
a
lso
h
ig
h
li
g
h
ts
p
ra
c
ti
c
a
l
c
o
n
si
d
e
ra
ti
o
n
s
,
i
n
c
lu
d
i
n
g
c
a
li
b
ra
ti
o
n
,
tran
s
p
a
re
n
t
re
p
o
rti
n
g
,
a
n
d
in
teg
ra
ti
o
n
w
it
h
d
o
u
b
ly
ro
b
u
st
e
stim
a
to
rs
to
stre
n
g
th
e
n
c
a
u
sa
l
in
f
e
r
e
n
c
e
.
T
h
e
f
in
d
in
g
s
sh
o
w
th
a
t
ML
-
b
a
se
d
p
ro
p
e
n
sity
sc
o
re
e
stim
a
ti
o
n
(P
S
E)
c
a
n
su
b
sta
n
ti
a
ll
y
e
n
h
a
n
c
e
t
h
e
v
a
l
id
it
y
a
n
d
re
li
a
b
il
it
y
o
f
so
c
io
e
c
o
n
o
m
ic
e
v
a
lu
a
ti
o
n
s,
p
r
o
v
id
e
d
t
h
a
t
it
s
im
p
le
m
e
n
tatio
n
is
c
a
re
f
u
ll
y
g
u
id
e
d
b
y
a
p
p
ro
p
riate
e
x
p
e
rti
se
a
n
d
b
e
st
-
p
ra
c
ti
c
e
sta
n
d
a
rd
s.
K
ey
w
o
r
d
s
:
E
n
s
e
m
b
le
m
o
d
el
Hig
h
-
d
i
m
e
n
s
io
n
al
d
ata
Ma
ch
i
n
e
lear
n
i
n
g
m
o
d
els
So
cio
ec
o
n
o
m
ic
ev
al
u
atio
n
S
y
s
te
m
a
tic
r
ev
ie
w
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
:
Gen
e
Ma
r
ck
B
.
C
ated
r
illa
An
g
eles U
n
i
v
er
s
it
y
Fo
u
n
d
atio
n
(
AUF)
An
g
eles,
P
h
ilip
p
in
e
s
E
m
ail: 2
4
-
2093
-
4
2
3
@
au
f
.
ed
u
.
p
h
or
ca
ted
r
illa.g
en
e
m
ar
c
k
@
ls
p
u
.
ed
u
.
p
h
1.
I
NT
RO
D
UCT
I
O
N
I
m
p
ac
t
ev
alu
a
tio
n
s
ass
es
s
th
e
ca
u
s
al
e
f
f
ec
t
s
o
f
in
ter
v
e
n
tio
n
s
b
y
co
m
p
ar
in
g
o
b
s
er
v
ed
o
u
tco
m
e
s
w
it
h
a
co
u
n
ter
f
ac
tu
al
s
ce
n
ar
io
-
w
h
at
w
o
u
ld
h
a
v
e
o
cc
u
r
r
ed
in
t
h
e
ab
s
en
ce
o
f
th
e
i
n
ter
v
en
ti
o
n
.
T
h
e
d
if
f
er
en
ce
b
et
w
ee
n
th
e
s
e
o
u
tco
m
e
s
r
ep
r
e
s
en
t
s
th
e
i
n
ter
v
e
n
tio
n
's
i
m
p
ac
t
,
w
h
ic
h
m
a
y
b
e
m
ea
s
u
r
ed
at
m
u
ltip
le
lev
el
s
an
d
is
n
o
t
li
m
ited
to
lo
n
g
-
ter
m
e
f
f
ec
ts
,
co
n
tr
ar
y
to
co
m
m
o
n
a
s
s
u
m
p
tio
n
s
.
No
n
eth
e
less
,
i
m
p
ac
t
ev
alu
a
tio
n
r
e
m
ai
n
s
th
e
p
r
i
m
ar
y
ap
p
r
o
ac
h
ca
p
ab
le
o
f
p
r
o
v
id
in
g
cr
ed
ib
le
ev
id
en
ce
o
f
lo
n
g
-
ter
m
o
u
tco
m
e
s
.
W
h
en
p
r
o
p
er
ly
d
esig
n
ed
an
d
ex
ec
u
ted
,
i
m
p
ac
t
ev
alu
atio
n
s
ca
n
in
f
o
r
m
p
o
lic
y
d
ec
is
i
o
n
s
,
s
h
ap
e
p
u
b
lic
o
p
in
io
n
,
an
d
i
m
p
r
o
v
e
p
r
o
g
r
am
o
p
er
atio
n
s
[
1
]
.
I
m
p
ac
t
ev
al
u
atio
n
i
s
e
m
b
ed
d
e
d
w
it
h
i
n
t
h
e
b
r
o
ad
er
s
h
i
f
t
to
war
d
ev
id
en
ce
-
b
ased
p
o
lic
y
m
ak
in
g
,
w
h
ic
h
e
m
p
h
a
s
izes
o
u
tco
m
es
o
v
er
in
p
u
ts
i
n
p
u
b
lic
p
o
lic
y
a
n
d
o
r
g
an
izatio
n
a
l
d
ec
is
io
n
-
m
ak
in
g
.
T
h
is
r
es
u
lt
s
-
o
r
ien
ted
ap
p
r
o
ac
h
s
u
p
p
o
r
ts
th
e
m
o
n
ito
r
in
g
o
f
n
atio
n
al
an
d
in
ter
n
a
tio
n
al
tar
g
ets
an
d
s
tr
en
g
t
h
e
n
s
ac
co
u
n
tab
ilit
y
,
b
u
d
g
e
t
allo
ca
tio
n
,
an
d
p
r
o
g
r
a
m
d
esi
g
n
[
1
]
.
B
y
p
r
o
v
id
i
n
g
cr
ed
ib
le
ev
id
en
ce
o
f
p
er
f
o
r
m
an
ce
,
i
m
p
ac
t
e
v
alu
a
tio
n
s
d
eter
m
in
e
w
h
et
h
er
p
r
o
g
r
a
m
s
h
av
e
a
c
h
iev
ed
o
r
ar
e
ac
h
iev
in
g
t
h
eir
in
te
n
d
ed
o
b
j
ec
ti
v
es
a
n
d
q
u
an
ti
f
y
i
m
p
r
o
v
e
m
en
t
s
in
b
e
n
ef
ic
iar
ies
'
q
u
ali
t
y
o
f
l
if
e
attr
ib
u
tab
le
to
th
e
in
ter
v
e
n
tio
n
.
Ho
w
e
v
er
,
a
p
er
s
is
te
n
t
ch
alle
n
g
e
in
s
o
cio
ec
o
n
o
m
ic
e
v
alu
a
tio
n
is
th
e
lack
o
f
h
i
g
h
-
q
u
a
lit
y
b
a
s
elin
e
d
ata,
w
h
ic
h
u
n
d
er
m
i
n
e
s
th
e
r
eliab
ilit
y
o
f
ca
u
s
al
es
ti
m
ates [
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
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
41
,
No
.
2
,
Feb
r
u
ar
y
20
2
6
:
64
5
-
65
4
646
P
r
o
p
en
s
it
y
s
co
r
e
(
P
S)
m
et
h
o
d
s
ar
e
w
id
el
y
ap
p
lied
in
s
o
cio
ec
o
n
o
m
ic
ev
al
u
atio
n
to
ad
d
r
ess
in
co
m
p
lete
o
r
m
is
s
in
g
b
aseli
n
e
d
ata.
B
y
cr
ea
tin
g
b
alan
ce
d
co
m
p
ar
is
o
n
g
r
o
u
p
s
,
P
S
m
e
th
o
d
s
en
ab
le
m
o
r
e
cr
ed
ib
le
ca
u
s
al
in
f
er
e
n
ce
ev
e
n
w
h
en
b
asel
in
e
i
n
f
o
r
m
atio
n
is
li
m
ited
[
3
]
.
P
S
also
r
ed
u
ce
m
u
ltid
i
m
en
s
io
n
al
co
v
ar
iate
in
f
o
r
m
atio
n
in
to
a
s
in
g
le
s
ca
lar
m
ea
s
u
r
e,
f
ac
i
litati
n
g
co
v
ar
iate
b
ala
n
ce
w
h
e
n
f
u
l
l
b
aselin
e
d
ata
ar
e
u
n
a
v
ailab
le
[
4
]
.
A
s
n
o
ted
b
y
Au
s
tin
et
a
l.
[
5
]
,
P
S
ap
p
r
o
ac
h
es
ar
e
p
a
r
ticu
lar
l
y
v
al
u
ab
le
in
lar
g
e
-
s
ca
l
e
s
o
cio
ec
o
n
o
m
ic
ev
al
u
atio
n
s
wh
er
e
co
n
s
is
ten
t
b
aseli
n
e
d
ata
co
llectio
n
is
d
if
f
ic
u
lt.
C
h
a
m
a
n
d
W
est
[
6
]
f
u
r
th
er
d
em
o
n
s
tr
ated
t
h
at
m
ac
h
i
n
e
l
ea
r
n
in
g
(
M
L
)
m
o
d
els
ca
n
i
m
p
r
o
v
e
p
r
o
p
en
s
it
y
s
co
r
e
esti
m
atio
n
(
P
SE)
u
n
d
er
m
is
s
i
n
g
d
ata
co
n
d
itio
n
s
b
y
ca
p
tu
r
in
g
n
o
n
li
n
ea
r
an
d
n
o
n
ad
d
itiv
e
r
elatio
n
s
h
ip
s
t
h
at
tr
ad
itio
n
al
lo
g
i
s
tic
r
eg
r
ess
io
n
(
L
R
)
f
ail
s
to
m
o
d
el
ef
f
ec
ti
v
el
y
.
T
h
ese
ad
v
a
n
ta
g
es
ar
e
e
s
p
ec
iall
y
i
m
p
o
r
tan
t
i
n
h
ig
h
-
d
i
m
en
s
io
n
a
l
s
o
cio
ec
o
n
o
m
ic
d
ataset
s
[
7
]
.
E
n
s
e
m
b
le
m
eth
o
d
s
a
n
d
d
e
ep
n
eu
r
al
n
et
w
o
r
k
s
(
DNN
s
)
h
a
v
e
li
k
e
w
is
e
s
h
o
w
n
s
tr
o
n
g
p
er
f
o
r
m
an
ce
i
n
h
a
n
d
li
n
g
m
i
s
s
in
g
d
ata
an
d
co
m
p
lex
c
o
v
ar
iate
s
tr
u
ct
u
r
es [
7
]
,
[
8
]
.
R
ec
en
t
ad
v
a
n
ce
s
i
n
ca
u
s
al
in
f
er
en
ce
ex
te
n
d
b
e
y
o
n
d
co
n
v
e
n
t
io
n
al
P
SE
th
r
o
u
g
h
t
h
e
i
n
te
g
r
at
io
n
o
f
M
L
w
it
h
f
r
a
m
e
w
o
r
k
s
s
u
c
h
as
d
o
u
b
le/d
eb
iased
m
ac
h
i
n
e
lear
n
in
g
(
DM
L
)
,
m
eta
-
lear
n
i
n
g
ap
p
r
o
ac
h
es
(
e.
g
.
,
T
-
lear
n
er
s
,
S
-
lear
n
er
s
,
X
-
lear
n
er
s
)
,
an
d
h
eter
o
g
en
eo
u
s
tr
ea
t
m
en
t
e
f
f
ec
t
(
HT
E
)
m
o
d
els.
T
h
ese
m
e
th
o
d
s
e
n
ab
le
esti
m
atio
n
n
o
t
o
n
l
y
o
f
a
v
er
ag
e
tr
ea
t
m
e
n
t
ef
f
ec
t
s
b
u
t
al
s
o
o
f
s
u
b
g
r
o
u
p
-
s
p
ec
i
f
ic
i
m
p
ac
ts
,
w
h
ic
h
is
cr
itica
l
f
o
r
p
u
b
lic
p
o
licy
a
n
d
d
ev
elo
p
m
en
t
p
r
o
g
r
a
m
s
[
9
]
-
[
1
1
]
.
Sit
u
atin
g
ML
-
b
ased
P
SE
w
it
h
i
n
t
h
is
b
r
o
ad
er
ca
u
s
al
in
f
er
en
ce
la
n
d
s
ca
p
e
h
i
g
h
lig
h
t
s
its
r
elev
a
n
ce
f
o
r
ad
d
r
ess
in
g
c
o
m
p
le
x
r
ea
l
-
w
o
r
ld
ev
a
lu
atio
n
ch
alle
n
g
e
s
.
Desp
ite
th
e
g
r
o
w
in
g
ad
o
p
tio
n
o
f
ML
-
b
ased
P
SE,
ex
is
tin
g
s
tu
d
ies
r
e
m
ai
n
f
r
ag
m
e
n
ted
,
w
i
th
li
m
ited
s
y
n
t
h
esi
s
ac
r
o
s
s
s
o
cio
ec
o
n
o
m
ic
d
o
m
ai
n
s
,
in
s
u
f
f
icie
n
t
co
m
p
ar
is
o
n
ac
r
o
s
s
M
L
m
o
d
el
f
a
m
il
ies,
an
d
i
n
ad
eq
u
ate
d
is
cu
s
s
io
n
o
f
p
r
ac
tical
is
s
u
es
s
u
ch
a
s
ca
lib
r
atio
n
,
f
air
n
es
s
,
an
d
i
n
ter
p
r
etab
il
it
y
.
T
h
is
g
ap
co
n
s
tr
ain
s
r
esear
ch
er
s
'
ab
ilit
y
to
s
elec
t
ap
p
r
o
p
r
iate
ML
m
o
d
els
f
o
r
h
ig
h
-
d
i
m
en
s
io
n
al
s
o
cio
ec
o
n
o
m
ic
ev
al
u
atio
n
an
d
m
o
tiv
a
tes
th
e
n
ee
d
f
o
r
a
co
m
p
r
eh
en
s
i
v
e
r
ev
ie
w
.
T
h
is
p
ap
er
ai
m
s
to
r
ev
ie
w
liter
atu
r
e
o
n
t
h
e
v
iab
ilit
y
o
f
M
L
m
o
d
el
s
in
p
r
ed
ictin
g
a
n
d
esti
m
ati
n
g
P
Ss
.
Sp
ec
i
f
icall
y
,
t
h
is
l
iter
atu
r
e
r
ev
ie
w
w
i
ll f
o
c
u
s
o
n
th
e
f
o
llo
w
i
n
g
:
1.
E
x
p
lo
r
e
th
e
d
ev
elo
p
m
e
n
t o
f
ML
m
o
d
el
ap
p
licatio
n
s
in
PS
an
al
y
s
i
s
.
2.
Hig
h
li
g
h
t
t
h
e
p
r
ac
tical
i
m
p
l
icatio
n
s
o
f
ML
i
n
p
r
ed
ictin
g
PS
s
f
o
r
r
esear
ch
er
s
an
d
ac
cr
ed
ito
r
s
in
s
o
cio
ec
o
n
o
m
ic
ev
a
lu
atio
n
.
3.
P
r
o
v
id
e
a
s
u
m
m
ar
y
o
f
h
o
w
ML
m
o
d
els
a
n
d
PS
ca
n
i
m
p
r
o
v
e
t
h
e
ef
f
ec
ti
v
e
n
es
s
o
f
s
o
cio
ec
o
n
o
m
i
c
ev
alu
a
tio
n
.
2.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
2
.
1
.
P
r
o
pens
it
y
s
co
re
a
nd
it
s
us
a
g
e
PS
m
et
h
o
d
o
lo
g
y
p
r
o
v
id
es
a
f
r
a
m
e
w
o
r
k
f
o
r
ac
h
ie
v
i
n
g
co
v
ar
i
ate
b
alan
ce
in
o
b
s
er
v
atio
n
al
s
tu
d
ies
b
y
ad
j
u
s
tin
g
f
o
r
s
y
s
te
m
atic
d
if
f
er
en
ce
s
b
et
w
ee
n
tr
ea
ted
an
d
co
n
tr
o
l
g
r
o
u
p
s
.
E
s
ti
m
ated
PS
s
ar
e
co
m
m
o
n
l
y
ap
p
lied
th
r
o
u
g
h
s
tr
ati
f
icatio
n
in
to
s
u
b
cla
s
s
e
s
,
m
atc
h
i
n
g
tr
ea
t
ed
an
d
co
n
tr
o
l
u
n
it
s
w
it
h
s
i
m
i
lar
s
co
r
es,
o
r
in
v
er
s
e
p
r
o
b
ab
ilit
y
o
f
tr
ea
t
m
en
t
w
ei
g
h
ti
n
g
(
I
P
T
W
)
,
ea
ch
ai
m
i
n
g
to
ap
p
r
o
x
i
m
ate
r
a
n
d
o
m
ized
ex
p
er
i
m
en
tal
co
n
d
itio
n
s
.
T
o
ad
d
r
ess
li
m
ita
t
io
n
s
o
f
tr
ad
itio
n
al
p
ar
a
m
e
tr
ic
m
o
d
els
u
s
ed
i
n
P
SE
,
ML
al
g
o
r
ith
m
s
h
a
v
e
b
ee
n
in
cr
ea
s
i
n
g
l
y
ad
o
p
ted
to
im
p
r
o
v
e
f
lex
ib
il
it
y
a
n
d
r
o
b
u
s
tn
e
s
s
in
m
o
d
eli
n
g
co
m
p
lex
tr
e
at
m
e
n
t
ass
i
g
n
m
en
t
m
ec
h
a
n
i
s
m
s
[
1
2
]
.
PS
m
e
th
o
d
s
ar
e
w
id
el
y
u
s
ed
a
cr
o
s
s
d
is
cip
lin
e
s
to
s
u
p
p
o
r
t
ca
u
s
al
i
n
f
er
en
ce
f
r
o
m
o
b
s
er
v
ati
o
n
al
d
ata.
I
n
h
ea
lt
h
ca
r
e
an
d
ep
id
em
io
lo
g
y
,
t
h
e
y
ar
e
ap
p
lied
to
ev
alu
ate
tr
ea
t
m
en
t
e
f
f
ec
ti
v
en
e
s
s
an
d
s
af
et
y
u
s
i
n
g
r
ea
l
-
w
o
r
ld
d
ata
s
o
u
r
ce
s
s
u
c
h
a
s
el
ec
tr
o
n
ic
h
ea
lth
r
ec
o
r
d
s
an
d
i
n
s
u
r
an
ce
c
lai
m
s
[
1
3
]
.
I
n
s
o
cial
s
cie
n
ce
r
esear
c
h
,
PS
s
ar
e
u
s
ed
to
as
s
es
s
th
e
i
m
p
ac
ts
o
f
s
o
cial
p
r
o
g
r
a
m
s
,
e
d
u
ca
tio
n
al
i
n
ter
v
en
t
io
n
s
,
a
n
d
w
o
r
k
f
o
r
ce
tr
ain
i
n
g
in
itiat
iv
e
s
b
y
b
alan
c
in
g
b
aseli
n
e
ch
ar
ac
ter
is
tics
b
et
w
ee
n
p
ar
ticip
an
ts
a
n
d
n
o
n
-
p
ar
ticip
an
t
s
[
1
4
]
.
E
co
n
o
m
is
t
s
e
m
p
lo
y
PS
an
al
y
s
is
to
esti
m
at
e
th
e
ca
u
s
al
ef
f
ec
ts
o
f
p
o
lic
y
in
ter
v
e
n
tio
n
s
,
in
cl
u
d
in
g
u
n
e
m
p
lo
y
m
e
n
t
b
en
ef
i
ts
,
m
i
n
i
m
u
m
w
a
g
e
p
o
lici
es,
an
d
d
ev
elo
p
m
e
n
t
p
r
o
g
r
a
m
s
,
o
n
l
ab
o
r
an
d
in
co
m
e
o
u
tco
m
e
s
[
1
5
]
.
B
ey
o
n
d
t
h
ese
ar
ea
s
,
PS
tech
n
iq
u
es
ar
e
in
c
r
ea
s
in
g
l
y
ap
p
lied
in
m
ar
k
eti
n
g
a
n
al
y
tics
to
ev
al
u
ate
ad
v
er
tis
in
g
an
d
lo
y
al
t
y
p
r
o
g
r
am
s
[
1
6
]
,
as
w
el
l
as
i
n
en
v
ir
o
n
m
e
n
tal
s
cie
n
ce
,
p
u
b
lic
p
o
licy
e
v
al
u
at
io
n
,
an
d
o
th
er
q
u
asi
-
ex
p
er
i
m
en
tal
r
esear
ch
s
etti
n
g
s
.
2
.
2
.
Va
ri
o
us
co
m
m
o
n a
n
d c
o
nv
ent
io
na
l
m
et
ho
d
s
o
n g
et
t
ing
pro
pens
it
y
s
co
re
T
h
e
tr
ad
itio
n
al
w
a
y
o
f
es
ti
m
atin
g
PS
s
m
o
s
tl
y
u
s
es
s
ta
tis
t
ical
m
o
d
els,
w
it
h
LR
b
ei
n
g
th
e
m
o
s
t
co
m
m
o
n
m
e
th
o
d
.
LR
m
o
d
els
th
e
lo
g
-
o
d
d
s
o
f
tr
ea
t
m
e
n
t
a
s
s
i
g
n
m
e
n
t
as
a
li
n
ea
r
f
u
n
ctio
n
o
f
t
h
e
o
b
s
er
v
ed
v
ar
iab
les.
On
ce
w
e
esti
m
ate
t
h
ese
PS
s
,
w
e
ap
p
l
y
th
e
m
th
r
o
u
g
h
s
e
v
er
al
estab
lis
h
ed
m
et
h
o
d
s
.
Stra
tif
icatio
n
,
o
r
s
u
b
clas
s
i
f
icatio
n
,
i
n
v
o
lv
e
s
d
iv
id
in
g
t
h
e
s
t
u
d
y
p
o
p
u
latio
n
in
t
o
g
r
o
u
p
s
,
o
f
ten
q
u
in
t
iles
,
b
ase
d
o
n
th
e
esti
m
ated
PS
s
.
W
e
th
en
co
m
p
ar
e
o
u
tco
m
es
b
et
w
ee
n
tr
ea
ted
an
d
co
n
tr
o
l
u
n
its
w
i
th
i
n
ea
c
h
g
r
o
u
p
.
T
h
e
o
v
er
all
tr
ea
t
m
e
n
t
ef
f
ec
t is
u
s
u
all
y
ca
lcu
la
ted
as a
w
ei
g
h
ted
av
er
ag
e
ac
r
o
s
s
t
h
e
s
e
g
r
o
u
p
s
[
1
7
]
.
Ma
tch
i
n
g
tech
n
iq
u
e
s
p
air
ea
ch
tr
ea
ted
u
n
it
w
i
t
h
o
n
e
o
r
m
o
r
e
co
n
tr
o
l u
n
its
t
h
at
h
a
v
e
v
er
y
s
i
m
ilar
PS
s
,
s
u
c
h
as
n
ea
r
est
-
n
e
ig
h
b
o
r
m
at
ch
in
g
an
d
ca
lip
er
m
a
tch
i
n
g
.
T
h
is
cr
ea
tes
a
m
atch
ed
s
a
m
p
le
w
h
er
e
co
v
ar
iat
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
Ma
ch
in
e
lea
r
n
in
g
mo
d
els in
th
e
en
h
a
n
ce
men
t o
f P
S
E
in
h
i
g
h
-
d
imen
s
io
n
a
l
…
(
Gen
e
Ma
r
ck
B
.
C
a
ted
r
illa
)
647
d
is
tr
ib
u
tio
n
s
ar
e
b
alan
ce
d
.
I
PT
W
ass
ig
n
s
w
ei
g
h
t
s
to
ev
er
y
o
n
e
b
ased
o
n
th
eir
PS
.
T
r
ea
ted
u
n
its
r
ec
ei
v
e
a
w
ei
g
h
t
o
f
*
1
/e(
X
)
*
,
w
h
ile
co
n
tr
o
l
u
n
it
s
g
et
a
w
ei
g
h
t
o
f
*
1
/(
1
-
e(
X
)
)
*
.
T
h
ese
w
e
ig
h
t
s
cr
ea
te
a
p
s
eu
d
o
-
p
o
p
u
latio
n
w
h
er
e
th
e
d
is
tr
ib
u
tio
n
o
f
co
v
ar
iates
d
o
es
n
o
t
d
ep
en
d
o
n
tr
ea
t
m
en
t
as
s
i
g
n
m
e
n
t.
T
h
is
a
llo
w
s
f
o
r
esti
m
ati
n
g
t
h
e
av
er
ag
e
tr
ea
t
m
en
t
ef
f
ec
t
i
n
t
h
e
p
o
p
u
latio
n
(
AT
E
)
o
r
th
e
av
er
ag
e
tr
ea
t
m
e
n
t
ef
f
ec
t
o
n
th
e
tr
ea
ted
(
A
T
T
)
th
r
o
u
g
h
w
ei
g
h
ted
an
al
y
s
e
s
.
A
lt
h
o
u
g
h
t
h
ese
m
et
h
o
d
s
ar
e
w
el
l
-
k
n
o
w
n
a
n
d
w
id
el
y
u
s
ed
i
n
s
tati
s
tica
l
s
o
f
t
w
ar
e,
t
h
e
y
r
el
y
h
ea
v
i
l
y
o
n
co
r
r
ec
tly
s
p
ec
if
y
i
n
g
th
e
LR
m
o
d
el.
Mi
s
s
p
ec
i
f
icatio
n
,
s
u
c
h
as
o
m
itt
in
g
r
ele
v
an
t
co
n
f
o
u
n
d
er
s
o
r
f
aili
n
g
to
in
c
lu
d
e
n
ec
ess
ar
y
i
n
ter
ac
tio
n
o
r
n
o
n
-
lin
ea
r
ter
m
s
,
ca
n
r
es
u
lt
i
n
r
esid
u
al
co
n
f
o
u
n
d
in
g
an
d
b
iased
ef
f
ec
t
e
s
ti
m
ates.
A
d
d
itio
n
al
l
y
,
co
n
v
e
n
tio
n
al
LR
f
i
n
d
s
it
ch
a
llen
g
i
n
g
to
h
an
d
le
h
ig
h
-
d
i
m
e
n
s
io
n
al
co
v
ar
iate
d
ata
[
1
8
]
.
2
.
3
.
M
a
chine le
a
rning
a
nd
pro
pens
it
y
s
co
re
PS
s
ca
n
b
e
e
s
ti
m
ated
u
s
i
n
g
ML
al
g
o
r
ith
m
s
to
ad
d
r
ess
li
m
itatio
n
s
o
f
tr
ad
itio
n
a
l
LR
,
p
ar
ticu
lar
l
y
u
n
d
er
n
o
n
li
n
ea
r
,
n
o
n
ad
d
itiv
e,
an
d
h
i
g
h
-
d
i
m
en
s
io
n
al
co
v
ar
iate
s
tr
u
ct
u
r
es.
M
L
-
b
ased
ap
p
r
o
ac
h
es
o
f
f
er
g
r
ea
ter
f
le
x
ib
ilit
y
b
y
a
u
to
m
atica
ll
y
ca
p
tu
r
in
g
co
m
p
le
x
r
elatio
n
s
h
ip
s
an
d
in
ter
ac
tio
n
s
w
it
h
o
u
t
r
eq
u
i
r
in
g
e
x
p
licit
m
o
d
el
s
p
ec
if
icatio
n
,
an
d
th
e
y
ar
e
g
e
n
er
all
y
m
o
r
e
ef
f
ec
ti
v
e
w
h
e
n
m
an
y
p
o
ten
tial
co
n
f
o
u
n
d
er
s
ar
e
p
r
esen
t.
Ho
w
e
v
er
,
in
cr
ea
s
ed
m
o
d
el
f
le
x
ib
ilit
y
al
s
o
in
tr
o
d
u
ce
s
r
is
k
s
,
as
h
i
g
h
l
y
c
o
m
p
le
x
alg
o
r
it
h
m
s
—
s
u
c
h
as
DNN
s
an
d
f
le
x
ib
le
tr
ee
en
s
e
m
b
les
—
m
a
y
o
v
er
f
it
tr
ea
t
m
e
n
t
as
s
ig
n
m
e
n
t
m
o
d
el
s
,
lead
in
g
to
s
u
b
o
p
ti
m
al
co
v
ar
iate
b
alan
ce
an
d
b
iased
ca
u
s
al
esti
m
ate
s
.
C
o
n
s
eq
u
en
tl
y
,
ca
r
ef
u
l
m
o
d
el
i
m
p
le
m
e
n
tatio
n
,
t
u
n
in
g
,
an
d
v
al
i
d
atio
n
ar
e
ess
en
tial
w
h
e
n
ap
p
l
y
in
g
M
L
to
P
SE
[
1
9
]
.
T
r
ee
-
b
ased
en
s
e
m
b
le
m
et
h
o
d
s
,
in
cl
u
d
in
g
g
r
ad
ien
t
b
o
o
s
tin
g
m
ac
h
i
n
es
(
GB
M)
an
d
r
an
d
o
m
f
o
r
est
s
(
R
F)
,
ar
e
am
o
n
g
th
e
m
o
s
t
c
o
m
m
o
n
l
y
u
s
ed
ML
ap
p
r
o
ac
h
es
f
o
r
P
SE
.
T
h
ese
m
e
th
o
d
s
d
em
o
n
s
tr
ate
s
tr
o
n
g
p
er
f
o
r
m
a
n
ce
b
y
ac
co
m
m
o
d
a
tin
g
n
o
n
li
n
ea
r
ities
a
n
d
in
ter
ac
tio
n
s
w
h
ile
m
ai
n
tai
n
i
n
g
r
o
b
u
s
tn
e
s
s
t
h
r
o
u
g
h
ag
g
r
e
g
atio
n
ac
r
o
s
s
m
u
l
tip
le
d
ec
is
io
n
tr
ee
s
[
2
0
]
.
P
en
alize
d
r
eg
r
ess
io
n
m
et
h
o
d
s
,
s
u
ch
as
L
a
s
s
o
a
n
d
R
id
g
e
r
eg
r
ess
io
n
,
ex
te
n
d
LR
b
y
i
n
tr
o
d
u
cin
g
r
e
g
u
lar
izatio
n
to
i
m
p
r
o
v
e
s
tab
ilit
y
in
h
i
g
h
-
d
i
m
en
s
i
o
n
al
s
etti
n
g
s
.
L
ass
o
p
er
f
o
r
m
s
v
ar
iab
le
s
elec
tio
n
b
y
s
h
r
i
n
k
i
n
g
s
o
m
e
co
e
f
f
icien
ts
t
o
ze
r
o
,
en
h
an
cin
g
m
o
d
el
p
ar
s
i
m
o
n
y
,
w
h
ile
R
id
g
e
r
eg
r
ess
io
n
s
tab
ilizes
esti
m
ate
s
b
y
s
h
r
in
k
i
n
g
co
ef
f
icie
n
t
s
w
ith
o
u
t
e
x
clu
s
io
n
,
w
h
ich
is
p
ar
ticu
lar
l
y
b
en
e
f
icia
l
u
n
d
er
m
u
lt
ico
llin
ea
r
it
y
[
2
1
]
.
Neu
r
al
n
et
w
o
r
k
s
o
f
f
er
h
i
g
h
r
ep
r
esen
tatio
n
al
ca
p
ac
it
y
f
o
r
m
o
d
elin
g
co
m
p
lex
tr
ea
t
m
en
t
–
co
v
ar
iate
r
elatio
n
s
h
ip
s
b
u
t
ar
e
les
s
f
r
eq
u
en
tl
y
ap
p
lied
in
P
SE
d
u
e
to
th
eir
s
e
n
s
it
iv
i
t
y
to
s
a
m
p
le
s
ize,
tu
n
i
n
g
r
eq
u
ir
e
m
en
ts
,
a
n
d
r
is
k
o
f
o
v
er
f
itti
n
g
[
2
2
]
.
T
h
eir
li
m
it
ed
in
ter
p
r
etab
ilit
y
a
n
d
r
elia
n
ce
o
n
e
x
te
n
s
i
v
e
h
y
p
er
p
ar
a
m
eter
o
p
ti
m
izat
io
n
f
u
r
th
er
co
m
p
licate
v
alid
atio
n
i
n
ap
p
lied
s
o
cio
ec
o
n
o
m
ic
s
t
u
d
ies [
2
3
]
.
E
n
s
e
m
b
le
lear
n
in
g
ap
p
r
o
ac
h
es
th
at
co
m
b
in
e
m
u
lt
ip
le
alg
o
r
ith
m
s
th
r
o
u
g
h
cr
o
s
s
-
v
alid
atio
n
—
s
u
c
h
as
s
u
p
er
lear
n
er
f
r
a
m
e
w
o
r
k
s
i
n
te
g
r
atin
g
LR
,
GB
M,
L
as
s
o
,
an
d
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
es
—
p
r
o
v
id
e
a
f
lex
ib
le
an
d
r
o
b
u
s
t
alter
n
ativ
e
to
s
in
g
le
-
mo
d
el
esti
m
atio
n
.
T
h
ese
m
et
h
o
d
s
o
f
ten
o
u
tp
er
f
o
r
m
in
d
iv
id
u
al
lear
n
er
s
,
p
ar
ticu
lar
l
y
in
h
i
g
h
-
d
i
m
e
n
s
io
n
al
an
d
h
eter
o
g
en
eo
u
s
d
atas
ets,
b
y
b
alan
ci
n
g
p
r
ed
ictiv
e
p
er
f
o
r
m
an
ce
w
it
h
i
m
p
r
o
v
ed
co
v
ar
iate
b
alan
ce
[
1
9
]
.
2
.
4
.
O
t
her
co
ns
idera
t
io
ns
f
o
r
M
L
-
ba
s
ed
pro
pen
s
it
y
s
co
ring
H
y
p
er
p
ar
am
e
ter
tu
n
in
g
—
s
u
c
h
as
ad
j
u
s
ti
n
g
lear
n
in
g
r
ate,
tr
ee
d
ep
th
,
an
d
r
eg
u
lar
izatio
n
s
tr
en
g
t
h
—
is
cr
itical
w
h
e
n
ap
p
l
y
in
g
ML
to
P
SE
.
T
ec
h
n
iq
u
es
s
u
ch
as
k
-
f
o
ld
cr
o
s
s
-
v
a
lid
atio
n
h
elp
co
n
t
r
o
l
o
v
er
f
itti
n
g
a
n
d
s
u
p
p
o
r
t
co
v
ar
iate
b
alan
ce
;
h
o
w
ev
er
,
o
p
ti
m
iz
i
n
g
tr
ea
t
m
en
t
as
s
i
g
n
m
e
n
t
p
r
ed
ictio
n
ac
cu
r
ac
y
alo
n
e
is
in
s
u
f
f
icien
t a
n
d
m
a
y
e
v
en
b
e
d
etr
i
m
en
ta
l to
ca
u
s
al
v
alid
it
y
[
2
4
]
.
R
eg
ar
d
les
s
o
f
t
h
e
ML
al
g
o
r
i
th
m
u
s
ed
,
p
o
s
t
-
esti
m
atio
n
as
s
ess
m
e
n
t
o
f
co
v
ar
iate
b
ala
n
c
e
b
et
w
ee
n
tr
ea
ted
an
d
co
n
tr
o
l g
r
o
u
p
s
r
e
m
ai
n
s
e
s
s
e
n
tial
a
f
ter
ap
p
l
y
in
g
PS
s
th
r
o
u
g
h
m
atch
in
g
,
w
ei
g
h
t
in
g
,
o
r
s
tr
ati
f
icatio
n
.
Stan
d
ar
d
d
iag
n
o
s
tic
s
in
cl
u
d
e
s
tan
d
ar
d
ized
m
ea
n
d
if
f
er
en
ce
s
(
SMD)
,
w
it
h
v
al
u
es
b
elo
w
0
.
1
ty
p
icall
y
in
d
icati
n
g
ac
ce
p
tab
le
b
alan
ce
,
v
ar
ian
ce
r
atio
s
,
an
d
v
is
u
a
l
to
o
ls
s
u
ch
as
lo
v
e
p
lo
ts
.
I
n
ad
e
q
u
ate
b
alan
ce
in
d
icate
s
f
ai
lu
r
e
o
f
th
e
PS
m
o
d
el
—
ir
r
esp
ec
tiv
e
o
f
its
c
o
m
p
le
x
it
y
—
a
n
d
n
ec
ess
itates
m
o
d
el
o
r
m
eth
o
d
r
ef
in
e
m
e
n
t
[
5
]
.
C
o
m
b
i
n
i
n
g
M
L
-
b
ased
PS
m
et
h
o
d
s
w
it
h
a
s
e
p
ar
ate
o
u
tco
m
e
r
eg
r
es
s
io
n
m
o
d
el
en
ab
les
d
o
u
b
l
y
r
o
b
u
s
t
esti
m
atio
n
,
e
n
s
u
r
in
g
c
o
n
s
is
ten
t
ca
u
s
al
es
ti
m
ates
i
f
eith
er
th
e
PS
m
o
d
el
o
r
th
e
o
u
tco
m
e
m
o
d
el
is
co
r
r
ec
tly
s
p
ec
i
f
ied
[
2
5
]
.
R
ec
en
t
liter
at
u
r
e
f
u
r
th
er
e
m
p
h
asize
s
tr
an
s
p
ar
en
c
y
an
d
f
air
n
es
s
in
M
L
-
b
ased
P
SE,
p
ar
ti
cu
lar
l
y
in
s
o
cio
ec
o
n
o
m
ic
ap
p
licatio
n
s
.
C
o
m
p
le
x
M
L
m
o
d
els
m
a
y
o
b
s
cu
r
e
tr
ea
t
m
en
t
ass
ig
n
m
en
t
m
ec
h
an
i
s
m
s
,
r
ed
u
ci
n
g
in
ter
p
r
etab
ilit
y
a
n
d
s
ta
k
e
h
o
ld
er
tr
u
s
t.
E
x
p
lain
ab
le
ar
ti
f
icial
i
n
telli
g
e
n
ce
(
X
A
I
)
to
o
ls
,
in
cl
u
d
in
g
SH
A
P
v
al
u
es,
L
I
ME
,
an
d
i
n
ter
p
r
etab
le
tr
ee
-
b
ased
m
o
d
els,
h
elp
clar
i
f
y
m
o
d
el
b
eh
av
io
r
an
d
e
n
h
a
n
ce
tr
a
n
s
p
ar
en
c
y
i
n
p
o
lic
y
ev
alu
a
tio
n
[
2
6
]
,
[
2
7
]
.
Fair
n
ess
-
a
w
ar
e
M
L
ap
p
r
o
ac
h
es
ad
d
itio
n
all
y
s
u
p
p
o
r
t
th
e
id
e
n
ti
f
icati
o
n
an
d
m
iti
g
atio
n
o
f
b
iased
tr
ea
tm
e
n
t
as
s
i
g
n
m
e
n
t
ac
r
o
s
s
d
em
o
g
r
ap
h
ic
s
u
b
g
r
o
u
p
s
,
r
ed
u
cin
g
th
e
r
is
k
th
at
P
SE
r
ein
f
o
r
ce
s
ex
i
s
ti
n
g
in
eq
u
it
ies
[
2
8
]
.
T
h
ese
co
n
s
i
d
er
atio
n
s
ar
e
in
cr
ea
s
i
n
g
l
y
cr
itical
as
M
L
-
b
ased
m
et
h
o
d
s
g
ain
ad
o
p
tio
n
i
n
g
o
v
er
n
m
e
n
t a
n
d
d
ev
elo
p
m
en
t p
r
o
g
r
am
e
v
al
u
atio
n
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
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
41
,
No
.
2
,
Feb
r
u
ar
y
20
2
6
:
64
5
-
65
4
648
3.
M
E
T
H
O
DS
T
h
is
r
ev
ie
w
p
ap
er
f
o
cu
s
e
s
o
n
t
h
e
liter
at
u
r
e
r
ev
ie
w
p
r
o
ce
s
s
.
T
h
is
p
r
o
ce
s
s
in
v
o
l
v
es
s
el
ec
tin
g
a
n
d
q
u
an
ti
f
y
i
n
g
e
x
is
t
in
g
s
t
u
d
ies
t
h
at
ap
p
l
y
ML
m
o
d
els
i
n
PS
an
al
y
s
is
.
T
h
er
ef
o
r
e,
d
if
f
er
en
t
to
o
ls
f
o
r
s
ea
r
ch
in
g
s
ch
o
lar
l
y
d
atab
ase
s
ar
e
th
e
m
a
in
m
a
ter
ials
u
s
ed
.
3
.
1
.
Sco
pe
a
nd
f
o
cus
,
a
nd
s
e
a
rc
h str
a
t
eg
y
T
h
is
liter
atu
r
e
r
ev
ie
w
e
x
a
m
in
es
th
e
ap
p
licatio
n
o
f
ML
m
o
d
els
in
PS
an
al
y
s
is
,
w
it
h
a
s
p
ec
if
ic
f
o
c
u
s
o
n
ad
d
r
ess
in
g
m
i
s
s
i
n
g
b
aseli
n
e
d
ata
in
h
i
g
h
-
d
i
m
e
n
s
io
n
al
s
o
cio
ec
o
n
o
m
ic
d
atasets
.
T
h
e
r
ev
ie
w
s
y
n
t
h
e
s
izes
p
ee
r
-
r
ev
ie
w
ed
j
o
u
r
n
al
ar
ticle
s
,
co
n
f
er
en
ce
p
ap
er
s
,
a
n
d
r
elate
d
ac
ad
e
m
ic
s
tu
d
ies
t
h
at
e
v
alu
a
te
ML
–
b
ased
ap
p
r
o
ac
h
es f
o
r
PS
E
,
m
et
h
o
d
o
lo
g
ical
i
m
p
le
m
e
n
tatio
n
,
an
d
p
er
f
o
r
m
an
ce
a
s
s
e
s
s
m
en
t.
R
elev
a
n
t
liter
at
u
r
e
w
a
s
r
etr
iev
ed
f
r
o
m
m
aj
o
r
ac
ad
em
ic
d
atab
ases
,
in
clu
d
i
n
g
SC
OP
U
S,
Go
o
g
le
Sch
o
lar
,
I
E
E
E
Xp
lo
r
e,
Sp
r
in
g
er
L
i
n
k
,
Scie
n
ce
Dir
ec
t,
an
d
t
h
e
A
C
M
Di
g
ital
L
ib
r
ar
y
.
T
h
e
P
u
b
lis
h
o
r
P
er
is
h
(P
o
P
)
to
o
l
w
as
ad
d
itio
n
all
y
u
s
ed
to
id
en
tify
s
u
p
p
le
m
e
n
tar
y
s
tu
d
ies.
L
it
m
ap
s
w
as
e
m
p
lo
y
ed
to
ass
ess
s
o
u
r
ce
r
elev
an
ce
an
d
citatio
n
co
n
n
e
ctiv
it
y
.
Sear
ch
ter
m
s
w
er
e
co
m
b
i
n
ed
s
y
s
te
m
atica
ll
y
to
r
ef
i
n
e
r
etr
iev
al,
as
s
u
m
m
ar
ized
in
T
ab
le
1
.
T
ab
le
1
.
Key
w
o
r
d
s
f
o
r
s
e
ar
ch
i
n
g
r
elate
d
liter
at
u
r
e
C
a
t
e
g
o
r
y
K
e
y
w
o
r
d
s
PS
a
n
a
l
y
si
s
PS
,
PS
a
n
a
l
y
si
s
ML
mo
d
e
l
s
ML
,
ML
mo
d
e
l
s,
ML
a
l
g
o
r
i
t
h
ms
S
o
c
i
o
e
c
o
n
o
mi
c
a
sse
ssm
e
n
t
S
o
c
i
o
e
c
o
n
o
mi
c
,
so
c
i
o
e
c
o
n
o
mi
c
a
s
se
ssm
e
n
t
,
so
c
i
o
e
c
o
n
o
mi
c
e
v
a
l
u
a
t
i
o
n
H
i
g
h
-
d
i
me
n
si
o
n
a
l
d
a
t
a
H
i
g
h
-
d
i
me
n
si
o
n
d
a
t
a
,
h
i
g
h
d
i
me
n
si
o
n
a
l
d
a
t
a
3
.
2
.
I
nclus
io
n a
nd
ex
cl
us
io
n
cr
it
er
ia
T
h
e
r
e
v
i
e
w
p
r
i
o
r
i
t
i
z
e
s
s
t
u
d
i
es
b
a
s
e
d
o
n
r
e
l
e
v
a
n
c
e
a
n
d
m
e
t
h
o
d
o
lo
g
i
c
a
l
q
u
a
l
i
t
y
.
P
u
b
l
i
ca
ti
o
n
s
w
e
r
e
p
r
i
m
a
r
i
l
y
r
e
s
t
r
i
c
t
e
d
to
t
h
o
s
e
r
e
l
e
a
s
e
d
w
i
t
h
i
n
t
h
e
l
a
s
t
t
e
n
y
e
a
r
s
;
h
o
w
e
v
e
r
,
t
h
e
t
i
m
e
f
r
a
m
e
wa
s
e
x
t
e
n
d
e
d
t
o
u
p
t
o
f
i
f
t
e
e
n
y
e
a
r
s
wh
e
n
n
e
c
e
s
s
a
r
y
t
o
e
n
s
u
r
e
s
u
f
f
i
c
i
e
n
t
c
o
v
e
r
a
g
e
o
f
r
e
l
e
v
a
n
t
w
o
r
k
a
n
d
m
a
i
n
t
a
i
n
g
e
n
e
r
a
l
i
z
a
b
i
l
i
t
y
.
O
n
l
y
p
e
e
r
-
r
e
v
i
e
w
e
d
j
o
u
r
n
a
l
ar
t
i
c
l
e
s
a
n
d
r
e
p
u
t
a
b
le
co
n
f
e
r
e
n
c
e
p
r
o
c
e
ed
i
n
g
s
p
u
b
l
i
s
h
e
d
i
n
E
n
g
l
i
s
h
we
r
e
i
n
c
l
u
d
e
d
,
w
h
i
l
e
n
o
n
-
p
e
e
r
-
r
e
v
i
e
w
e
d
s
o
u
r
c
e
s
s
u
c
h
a
s
e
d
i
t
o
r
i
a
l
s
,
b
l
o
g
p
o
s
t
s
,
a
n
d
p
r
ep
r
i
n
t
s
w
e
r
e
e
x
c
l
u
d
e
d
.
E
lig
ib
le
s
t
u
d
ies
ex
p
licitl
y
ex
a
m
i
n
ed
th
e
u
s
e
o
f
ML
alg
o
r
ith
m
s
—
in
c
lu
d
i
n
g
tr
ee
en
s
e
m
b
les
,
p
en
alize
d
r
eg
r
ess
io
n
,
s
u
p
er
lear
n
er
f
r
am
e
w
o
r
k
s
,
an
d
n
eu
r
al
n
et
w
o
r
k
s
—
f
o
r
PS
an
al
y
s
i
s
.
T
h
is
in
clu
d
e
d
ap
p
licatio
n
s
in
v
o
l
v
i
n
g
P
SE
,
w
eig
h
ti
n
g
,
o
r
m
atc
h
in
g
u
n
d
er
b
o
th
s
i
m
p
le
an
d
h
i
g
h
-
d
i
m
en
s
io
n
al
co
v
ar
iate
s
tr
u
ct
u
r
es.
Stu
d
ie
s
ap
p
ly
i
n
g
ML
to
al
ter
n
ati
v
e
c
au
s
al
in
f
er
e
n
ce
m
eth
o
d
s
w
it
h
o
u
t
a
p
r
i
m
ar
y
f
o
cu
s
o
n
p
r
o
p
e
n
s
it
y
m
o
d
elin
g
,
a
s
w
ell
a
s
th
o
s
e
u
s
in
g
PS
s
i
n
less
co
m
p
le
x
ev
al
u
atio
n
s
etti
n
g
s
,
w
er
e
ex
c
lu
d
ed
.
3
.
3
.
Co
ncept
ua
l
f
r
a
m
ew
o
rk
T
h
is
r
ev
ie
w
d
r
e
w
f
r
o
m
m
aj
o
r
s
ch
o
lar
l
y
d
atab
ases
,
in
c
lu
d
in
g
S
C
OP
US,
Go
o
g
le
Sc
h
o
lar
,
I
E
E
E
Xp
lo
r
e,
Sp
r
in
g
er
L
i
n
k
,
Scie
n
ce
Dir
ec
t,
an
d
th
e
A
C
M
Di
g
ital
L
ib
r
ar
y
.
T
h
e
s
t
u
d
y
s
elec
tio
n
p
r
o
ce
s
s
f
o
llo
w
ed
t
h
e
P
R
I
SMA
f
r
a
m
e
w
o
r
k
,
as ill
u
s
tr
ated
in
th
e
P
R
I
SM
A
f
lo
w
c
h
ar
t a
d
ap
ted
f
r
o
m
[
2
3
]
as sh
o
w
n
i
n
Fi
g
u
r
e
1
.
T
h
e
in
itial
s
ea
r
ch
id
en
tifie
d
1
,
2
4
5
r
ec
o
r
d
s
f
r
o
m
ac
ad
em
ic
d
atab
ases
an
d
an
a
d
d
itio
n
al
9
5
r
ec
o
r
d
s
f
r
o
m
g
r
e
y
li
ter
atu
r
e
an
d
r
e
f
er
en
ce
lis
ts
.
Af
ter
r
e
m
o
v
in
g
1
8
0
d
u
p
licates,
1
,
1
6
0
u
n
iq
u
e
r
ec
o
r
d
s
r
em
ai
n
ed
f
o
r
titl
e
an
d
ab
s
tr
ac
t
s
cr
ee
n
in
g
.
Of
th
e
s
e,
9
6
0
r
ec
o
r
d
s
w
er
e
ex
clu
d
ed
f
o
r
f
aili
n
g
to
m
ee
t
th
e
r
ev
ie
w
o
b
j
ec
tiv
es,
r
esu
lti
n
g
i
n
2
0
0
f
u
ll
-
te
x
t
ar
ti
cles
ass
e
s
s
ed
f
o
r
elig
ib
il
it
y
.
Fo
llo
w
i
n
g
f
u
ll
-
te
x
t
e
v
al
u
ati
o
n
,
8
5
ar
ticles
w
er
e
ex
clu
d
ed
f
o
r
n
o
t
ap
p
l
y
in
g
ML
tec
h
n
iq
u
es,
3
5
f
o
r
lack
in
g
a
d
ir
ec
t
f
o
cu
s
o
n
PS
a
n
al
y
s
i
s
,
an
d
2
0
f
o
r
n
o
n
-
s
o
cio
ec
o
n
o
m
ic
ap
p
licatio
n
s
.
T
h
e
f
i
n
al
q
u
a
litati
v
e
s
y
n
th
e
s
is
t
h
er
ef
o
r
e
in
cl
u
d
ed
6
0
s
tu
d
ies.
3
.
4
.
Repo
rt
ing
t
he
r
ev
iew
T
h
e
f
in
d
in
g
s
w
er
e
o
r
g
an
ized
in
ac
co
r
d
an
ce
w
it
h
th
e
s
tated
r
esear
ch
o
b
j
ec
tiv
es.
T
h
e
r
ev
iew
p
r
o
ce
s
s
f
o
llo
w
ed
th
e
P
R
I
SMA
f
r
a
m
e
w
o
r
k
to
en
s
u
r
e
m
et
h
o
d
o
lo
g
ical
tr
an
s
p
ar
e
n
c
y
an
d
r
ep
r
o
d
u
cib
ilit
y
,
th
er
eb
y
s
tr
en
g
th
e
n
i
n
g
th
e
cr
ed
ib
ilit
y
o
f
th
e
s
e
lecte
d
liter
atu
r
e.
St
u
d
y
s
y
n
t
h
esi
s
i
n
v
o
l
v
ed
s
y
s
te
m
atic
ev
al
u
atio
n
o
f
r
elev
an
ce
,
m
et
h
o
d
o
lo
g
ical
ap
p
r
o
ac
h
es,
an
d
ap
p
licatio
n
s
o
f
ML
i
n
PS
a
n
al
y
s
is
.
T
h
e
r
ev
ie
w
e
m
p
h
a
s
ized
id
en
ti
f
y
i
n
g
m
eth
o
d
o
lo
g
ical
tr
en
d
s
,
co
m
m
o
n
l
y
u
s
ed
al
g
o
r
it
h
m
s
,
a
n
d
p
er
f
o
r
m
an
ce
p
atter
n
s
ac
r
o
s
s
d
ataset
s
o
f
v
ar
y
i
n
g
d
i
m
e
n
s
io
n
alit
y
,
w
it
h
th
e
o
b
j
ec
tiv
e
o
f
h
i
g
h
li
g
h
ti
n
g
r
ec
e
n
t
ad
v
a
n
ce
s
,
m
et
h
o
d
o
lo
g
ical
g
ap
s
,
a
n
d
d
ir
ec
tio
n
s
f
o
r
f
u
t
u
r
e
r
esear
ch
a
t th
e
in
ter
s
ec
tio
n
o
f
ML
an
d
c
au
s
al
i
n
f
er
en
ce
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
Ma
ch
in
e
lea
r
n
in
g
mo
d
els in
th
e
en
h
a
n
ce
men
t o
f P
S
E
in
h
i
g
h
-
d
imen
s
io
n
a
l
…
(
Gen
e
Ma
r
ck
B
.
C
a
ted
r
illa
)
649
Fig
u
r
e
1
.
L
iter
at
u
r
e
r
ev
ie
w
p
r
o
ce
s
s
(
P
R
I
SMA
f
lo
w
c
h
ar
t; [
2
9
]
)
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
I
n
ev
alu
at
in
g
th
e
ef
f
ec
ti
v
e
n
es
s
o
f
ML
m
o
d
els
f
o
r
p
r
ed
ictin
g
an
d
esti
m
at
in
g
PS
s
,
th
is
r
ev
ie
w
b
r
in
g
s
to
g
eth
er
6
0
r
esear
ch
p
ap
er
s
f
r
o
m
v
ar
io
u
s
d
ig
ital
lib
r
ar
ies
.
I
t
s
h
o
w
s
th
at
n
o
s
i
n
g
le
s
o
u
r
ce
w
as
p
r
ef
er
r
ed
.
T
h
e
d
is
cu
s
s
io
n
f
o
llo
w
s
th
e
s
ta
ted
o
b
j
ec
tiv
es to
m
ai
n
tai
n
co
h
er
en
ce
an
d
r
elev
a
n
ce
.
4
.
1
.
Appl
ica
t
io
n o
f
ML
m
o
d
els in
P
S
E
T
h
e
r
ev
ie
w
i
n
d
icate
s
t
h
at
LR
r
em
a
in
s
o
n
e
o
f
t
h
e
m
o
s
t
co
m
m
o
n
l
y
u
s
ed
ap
p
r
o
ac
h
es
f
o
r
esti
m
a
tin
g
PS
s
;
h
o
w
e
v
er
,
its
w
id
e
s
p
r
ea
d
ap
p
licatio
n
h
as
b
ee
n
ac
co
m
p
a
n
ied
b
y
in
cr
ea
s
ed
m
o
d
el
m
i
s
s
p
ec
i
f
icatio
n
,
w
h
ic
h
ad
v
er
s
el
y
a
f
f
ec
t
s
th
e
ac
cu
r
ac
y
o
f
tr
ea
t
m
e
n
t
p
r
o
b
ab
il
it
y
esti
m
ate
s
[
3
0
]
.
T
o
ad
d
r
ess
th
ese
li
m
itatio
n
s
,
m
o
r
e
f
le
x
ib
le
ML
–
b
ased
m
et
h
o
d
s
h
a
v
e
b
ee
n
i
n
cr
ea
s
i
n
g
l
y
ad
o
p
ted
.
A
cr
o
s
s
th
e
r
e
v
ie
w
ed
s
tu
d
ie
s
,
en
s
e
m
b
le
lear
n
in
g
al
g
o
r
ith
m
s
a
n
d
n
e
u
r
a
l
n
et
w
o
r
k
s
d
e
m
o
n
s
tr
ated
s
u
p
e
r
io
r
p
er
f
o
r
m
an
ce
i
n
ac
h
iev
i
n
g
co
v
ar
iate
b
alan
ce
an
d
r
ed
u
cin
g
b
ias,
p
ar
ticu
lar
l
y
i
n
h
i
g
h
-
d
i
m
e
n
s
io
n
al
s
o
cio
ec
o
n
o
m
ic
d
atasets
[
3
1
]
.
E
n
s
e
m
b
le
m
et
h
o
d
s
—
in
cl
u
d
in
g
g
r
ad
ien
t
b
o
o
s
ted
tr
ee
s
,
R
Fs
,
an
d
b
ag
g
ed
tr
ee
s
—
co
n
s
i
s
te
n
tl
y
o
u
tp
er
f
o
r
m
ed
LR
b
y
i
m
p
r
o
v
in
g
co
v
ar
iate
b
alan
ce
,
r
ed
u
cin
g
b
ias,
an
d
m
ai
n
tai
n
i
n
g
v
alid
co
n
f
id
e
n
ce
in
ter
v
als,
e
s
p
ec
iall
y
u
n
d
e
r
n
o
n
l
in
ea
r
co
v
ar
iate
s
tr
u
ctu
r
e
s
[
3
1
]
.
DNN
f
u
r
th
er
s
h
o
w
ed
s
tr
o
n
g
ca
p
ab
ilit
y
i
n
m
a
n
a
g
in
g
co
m
p
lex
h
i
g
h
-
d
i
m
e
n
s
io
n
a
l
P
SE
,
o
f
ten
s
u
r
p
as
s
i
n
g
b
o
th
LR
an
d
o
th
er
M
L
ap
p
r
o
ac
h
es in
p
r
ed
ictiv
e
ac
cu
r
ac
y
an
d
s
tab
il
it
y
[
3
2
]
.
C
las
s
i
f
icatio
n
-
b
ased
ap
p
r
o
ac
h
es,
p
ar
ticu
lar
l
y
clas
s
i
f
icatio
n
tr
ee
an
al
y
s
i
s
(
C
T
A
)
,
also
e
m
er
g
ed
a
s
ef
f
ec
tiv
e
alter
n
at
iv
e
s
f
o
r
P
SE
.
C
T
A
d
e
m
o
n
s
tr
ated
i
m
p
r
o
v
e
d
ac
cu
r
ac
y
o
v
er
LR
i
n
s
e
tti
n
g
s
c
h
ar
ac
ter
ized
b
y
i
m
b
alan
ce
d
co
v
ar
iate
s
,
o
w
i
n
g
to
its
ab
ilit
y
to
ca
p
tu
r
e
n
o
n
ad
d
itiv
e
e
f
f
ec
ts
a
n
d
v
ar
iab
le
in
ter
ac
tio
n
s
[
3
3
]
.
4
.
2
.
P
r
a
ct
ica
l im
pli
ca
t
io
ns
o
f
ML
in predict
ing
pro
pen
s
it
y
s
co
re
f
o
r
s
o
cio
ec
o
no
m
ic
ev
a
lua
t
io
n
ML
m
o
d
el
s
d
e
m
o
n
s
tr
ate
clea
r
ad
v
an
ta
g
es
o
v
er
tr
ad
itio
n
a
l
LR
in
p
r
ed
ictin
g
PS
s
w
i
th
i
n
co
m
p
le
x
s
o
cio
ec
o
n
o
m
ic
d
atasets
,
p
ar
ticu
lar
l
y
w
h
e
n
m
o
d
elin
g
n
o
n
lin
ea
r
r
elatio
n
s
h
ip
s
an
d
in
ter
ac
tio
n
s
co
m
m
o
n
l
y
o
b
s
er
v
ed
in
r
ea
l
-
w
o
r
ld
d
ata
[
3
4
]
.
I
n
m
u
lti
lev
el
o
b
s
er
v
atio
n
al
s
etti
n
g
s
,
n
o
n
p
ar
a
m
etr
ic
M
L
m
et
h
o
d
s
h
a
v
e
also
b
ee
n
s
h
o
w
n
to
o
u
tp
er
f
o
r
m
p
ar
a
m
etr
ic
LR
ap
p
r
o
ac
h
es
[
3
5
]
.
A
cr
o
s
s
th
e
r
ev
ie
w
ed
s
tu
d
i
es,
ML
-
b
ased
P
SE
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
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
41
,
No
.
2
,
Feb
r
u
ar
y
20
2
6
:
64
5
-
65
4
650
co
n
s
is
ten
tl
y
ac
h
ie
v
ed
i
m
p
r
o
v
ed
co
v
ar
iate
b
alan
ce
,
r
ed
u
ce
d
b
ias,
an
d
m
o
r
e
s
tab
le
co
n
f
id
en
ce
in
ter
v
als,
esp
ec
iall
y
u
n
d
er
co
n
d
itio
n
s
o
f
n
o
n
li
n
ea
r
it
y
an
d
n
o
n
-
ad
d
iti
v
it
y
[
7
]
,
[
1
2
]
,
[
1
9
]
.
Ac
c
u
r
a
t
e
i
n
t
e
r
p
r
e
t
a
t
io
n
o
f
tr
e
a
t
m
e
n
t
e
f
f
e
c
t
s
i
s
c
e
n
t
r
a
l
t
o
s
o
c
io
e
co
n
o
m
i
c
e
v
a
l
u
a
t
i
o
n
.
M
o
d
e
l
m
i
s
s
p
e
c
i
f
i
c
a
t
i
o
n
—
f
r
e
q
u
e
n
t
l
y
e
n
c
o
u
n
t
e
r
e
d
i
n
L
R
—
c
a
n
d
i
s
t
o
r
t
ca
u
s
a
l
e
s
t
i
m
a
t
e
s
,
wh
e
r
e
a
s
M
L
m
e
t
h
o
d
s
f
l
e
x
i
b
l
y
c
a
p
t
u
r
e
co
m
p
l
e
x
t
r
e
a
t
m
e
n
t
–
c
o
v
a
r
i
a
t
e
r
e
l
a
t
io
n
s
h
i
p
s
,
t
h
e
r
eb
y
r
e
d
u
c
i
n
g
b
i
a
s
.
W
i
t
h
ap
p
r
o
p
r
i
a
te
h
y
p
e
r
p
a
r
a
m
e
t
e
r
t
u
n
i
n
g
,
M
L
-
b
a
s
e
d
a
p
p
r
o
a
c
h
e
s
i
m
p
r
o
v
e
e
s
t
i
m
a
t
i
o
n
o
f
t
r
ea
t
m
e
n
t
p
r
o
b
ab
i
l
i
t
i
e
s
a
n
d
s
a
m
p
l
e
-
l
e
v
e
l
e
f
f
e
c
t
s
[
7
]
,
[
2
4
]
.
M
o
r
e
o
v
e
r
,
i
n
t
e
g
r
a
t
i
n
g
M
L
-
b
a
s
e
d
P
S
E
w
i
t
h
d
o
u
b
l
y
r
o
b
u
s
t
m
e
t
h
o
d
s
,
wh
i
c
h
c
o
m
b
i
n
e
p
r
o
p
e
n
s
i
t
y
m
o
d
e
l
i
n
g
wi
t
h
i
n
d
e
p
e
n
d
e
n
t
o
u
t
c
o
m
e
r
e
g
r
e
s
s
i
o
n
,
p
r
o
v
i
d
e
s
ad
d
i
t
io
n
a
l
p
r
o
t
e
ct
i
o
n
a
g
a
i
n
s
t
m
o
d
e
l
m
i
s
s
p
e
c
i
f
i
c
a
t
i
o
n
a
n
d
e
n
h
a
n
c
e
s
t
h
e
r
e
l
i
a
b
i
l
i
t
y
o
f
c
a
u
s
a
l
i
n
f
e
r
e
n
c
e
[
2
5
]
.
D
e
s
p
i
t
e
t
h
e
i
r
m
e
t
h
o
d
o
l
o
g
i
c
a
l
a
d
v
a
n
t
a
g
e
s
,
m
a
n
y
e
m
p
i
r
i
c
a
l
s
t
u
d
i
e
s
p
r
o
v
i
d
e
l
i
m
i
t
e
d
r
ep
o
r
ti
n
g
o
n
m
o
d
e
l
d
ia
g
n
o
s
t
i
c
s
,
p
er
f
o
r
m
a
n
c
e
m
e
t
r
i
c
s
,
a
n
d
h
y
p
e
r
p
a
r
a
m
e
t
e
r
t
u
n
i
n
g
,
u
n
d
e
r
s
c
o
r
i
n
g
t
h
e
n
e
e
d
f
o
r
s
t
a
n
d
a
r
d
iz
e
d
b
e
s
t
p
r
a
c
t
i
ce
s
a
n
d
e
v
a
l
u
a
t
i
o
n
f
r
a
m
e
w
o
r
k
s
i
n
a
p
p
l
i
e
d
s
o
c
io
e
c
o
n
o
m
i
c
r
e
s
e
a
r
c
h
[
3
5
]
.
W
h
i
l
e
M
L
i
m
p
r
o
v
e
s
t
h
e
v
a
l
i
d
i
ty
a
n
d
r
e
l
i
a
b
i
l
i
t
y
o
f
P
S
E
i
n
h
i
g
h
-
d
i
m
e
n
s
i
o
n
a
l
s
e
t
t
i
n
g
s
,
i
t
s
e
f
f
e
c
t
i
v
e
n
e
s
s
d
e
p
e
n
d
s
o
n
c
a
r
e
f
u
l
i
m
p
l
e
m
e
n
t
a
t
i
o
n
,
c
o
n
s
i
s
t
e
n
t
m
e
t
h
o
d
o
l
o
g
y
,
a
n
d
t
r
a
n
s
p
a
r
e
n
t
r
e
p
o
r
t
i
n
g
[
3
6
]
.
C
o
m
p
u
tatio
n
al
f
ea
s
ib
ilit
y
is
also
a
cr
itical
co
n
s
id
er
atio
n
in
ap
p
lied
co
n
tex
ts
.
So
cio
ec
o
n
o
m
ic
in
s
t
itu
tio
n
s
o
f
te
n
f
ac
e
r
eso
u
r
c
e
co
n
s
tr
ain
t
s
,
an
d
ce
r
tain
M
L
ap
p
r
o
ac
h
es
—
p
ar
ticu
lar
l
y
d
ee
p
lear
n
in
g
an
d
lar
g
e
en
s
e
m
b
le
m
o
d
els
—
r
eq
u
ir
e
s
u
b
s
ta
n
tial
co
m
p
u
tatio
n
a
l
r
es
o
u
r
ce
s
an
d
tu
n
i
n
g
ef
f
o
r
t.
C
o
n
s
eq
u
e
n
tl
y
,
m
o
d
el
s
elec
tio
n
s
h
o
u
ld
b
alan
ce
p
r
ed
ictiv
e
p
er
f
o
r
m
a
n
ce
w
ith
co
m
p
u
tatio
n
al
co
s
t,
i
m
p
le
m
e
n
tati
o
n
co
m
p
le
x
it
y
,
an
d
av
ailab
le
ex
p
er
tis
e
[
12
]
,
[
3
7
]
,
esp
ec
iall
y
i
n
d
ev
elo
p
m
e
n
t a
g
e
n
cies a
n
d
p
u
b
lic
-
se
cto
r
ev
al
u
a
tio
n
s
.
4
.
3
.
K
ey
f
ind
ing
s
a
nd
s
y
nth
esis
ML
-
b
ased
P
SE
p
r
o
v
id
es
s
u
b
s
t
an
tial
m
e
th
o
d
o
lo
g
ical
an
d
p
r
ac
tical
ad
v
an
ta
g
es
o
v
er
co
n
v
e
n
tio
n
al
L
R
,
p
ar
ticu
lar
l
y
i
n
h
i
g
h
-
d
i
m
e
n
s
io
n
al
an
d
n
o
n
li
n
ea
r
s
o
cio
ec
o
n
o
m
ic
d
ataset
s
.
A
cr
o
s
s
th
e
r
e
v
i
e
w
ed
s
t
u
d
ies,
ML
ap
p
r
o
ac
h
es
m
o
r
e
ef
f
ec
ti
v
e
l
y
ca
p
tu
r
e
co
m
p
lex
tr
ea
t
m
en
t
–
co
v
ar
iate
r
elatio
n
s
h
ip
s
,
r
ed
u
ce
m
o
d
el
m
is
s
p
ec
if
icatio
n
,
a
n
d
ac
h
iev
e
i
m
p
r
o
v
ed
co
v
ar
iate
b
alan
ce
.
E
n
s
e
m
b
le
m
et
h
o
d
s
,
in
c
lu
d
i
n
g
RF
s
,
GB
M
s
,
an
d
b
ag
g
ed
tr
ee
s
,
co
n
s
i
s
te
n
tl
y
o
u
t
p
er
f
o
r
m
tr
ad
itio
n
al
p
ar
a
m
etr
ic
m
o
d
els
i
n
p
r
ed
icti
v
e
ac
cu
r
ac
y
a
n
d
b
ias
r
ed
u
ctio
n
[
3
1
]
,
[
3
4
]
,
[
3
8
]
,
[
3
9
]
.
DNN
s
d
em
o
n
s
tr
ate
s
tr
o
n
g
p
er
f
o
r
m
a
n
ce
in
h
i
g
h
l
y
co
m
p
le
x
an
d
m
u
lti
v
ar
iate
s
etti
n
g
s
,
h
ig
h
li
g
h
ti
n
g
t
h
eir
ad
ap
tab
ilit
y
to
lar
g
e
a
n
d
h
eter
o
g
e
n
eo
u
s
d
atasets
a
n
d
t
h
eir
ca
p
ac
it
y
to
m
o
d
el
n
o
n
ad
d
itiv
e
ef
f
ec
ts
a
n
d
h
i
g
h
-
o
r
d
er
in
ter
ac
t
io
n
s
[
3
2
]
,
[
3
9
]
,
[
4
0
]
.
I
n
teg
r
ati
n
g
M
L
-
b
ased
P
SE
w
it
h
d
o
u
b
l
y
r
o
b
u
s
t
est
i
m
at
i
o
n
m
e
th
o
d
s
f
u
r
th
er
s
tr
en
g
t
h
en
s
ca
u
s
a
l
in
f
er
en
ce
b
y
p
r
o
v
id
in
g
p
r
o
tectio
n
ag
ai
n
s
t
m
is
s
p
ec
if
icatio
n
o
f
eith
er
th
e
tr
ea
t
m
e
n
t
o
r
o
u
tco
m
e
m
o
d
el
[
2
2
]
,
[
2
8
]
.
I
n
m
u
ltil
e
v
el
a
n
d
h
ier
ar
ch
ical
o
b
s
er
v
atio
n
al
s
et
tin
g
s
,
n
o
n
p
ar
a
m
etr
ic
M
L
ap
p
r
o
ac
h
es
o
u
tp
er
f
o
r
m
s
tan
d
ar
d
L
R
i
n
ac
h
ie
v
i
n
g
c
o
v
ar
iate
b
alan
ce
an
d
r
ed
u
cin
g
b
ias,
u
n
d
er
s
co
r
in
g
th
eir
v
alu
e
f
o
r
co
m
p
le
x
s
o
cio
ec
o
n
o
m
ic
ev
a
lu
atio
n
s
[
3
5
]
.
C
au
s
al
tr
ee
–
b
ased
alg
o
r
ith
m
s
ar
e
p
ar
ticu
lar
l
y
ef
f
ec
ti
v
e
in
s
etti
n
g
s
w
it
h
s
ev
er
e
co
v
ar
iate
i
m
b
ala
n
ce
,
a
co
m
m
o
n
f
ea
tu
r
e
o
f
s
o
cio
ec
o
n
o
m
ic
d
ata,
d
u
e
to
t
h
eir
ab
ilit
y
to
ca
p
tu
r
e
n
o
n
li
n
ea
r
itie
s
an
d
h
eter
o
g
en
eo
u
s
as
s
i
g
n
m
e
n
t
m
ec
h
a
n
is
m
s
[
3
3
]
.
C
o
l
l
e
c
t
i
v
e
l
y
,
t
h
e
s
e
f
i
n
d
i
n
g
s
r
e
i
n
f
o
r
c
e
t
h
e
c
o
n
s
e
n
s
u
s
t
h
a
t
M
L
-
b
a
s
e
d
P
S
E
o
f
f
e
r
s
a
m
o
r
e
f
l
e
x
i
b
l
e
,
a
c
c
u
r
a
t
e
,
a
n
d
r
o
b
u
s
t
f
o
u
n
d
a
t
io
n
f
o
r
t
r
e
a
t
m
e
n
t
a
s
s
i
g
n
m
e
n
t
m
o
d
e
l
i
n
g
t
h
a
n
t
r
a
d
i
t
io
n
a
l
a
p
p
r
o
a
c
h
e
s
[
3
8
]
,
[
3
9
]
.
B
e
y
o
n
d
m
e
t
h
o
d
o
l
o
g
i
c
a
l
p
er
f
o
r
m
a
n
c
e
,
ML
-
b
a
s
e
d
P
S
E
s
u
p
p
o
r
t
s
eq
u
i
t
y
-
f
o
c
u
s
e
d
e
v
a
l
u
a
t
i
o
n
t
h
r
o
u
g
h
i
n
t
e
g
r
a
t
i
o
n
w
i
t
h
h
e
t
e
r
o
g
e
n
e
o
u
s
t
r
e
a
t
m
e
n
t
e
f
f
e
c
t
m
o
d
e
l
s
,
e
n
a
b
l
i
n
g
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
d
i
f
f
e
r
e
n
t
i
a
l
i
n
t
e
r
v
e
n
t
i
o
n
i
m
p
a
c
t
s
a
c
r
o
s
s
s
u
b
g
r
o
u
p
s
d
e
f
i
n
e
d
b
y
g
e
n
d
e
r
,
s
o
c
i
o
e
co
n
o
m
i
c
s
t
a
t
u
s
,
o
r
g
e
o
g
r
a
p
h
i
c
c
o
n
t
e
x
t
[
4
0]
–
[
4
3
]
.
E
f
f
e
c
t
i
v
e
a
p
p
l
i
c
a
t
i
o
n
o
f
t
h
e
s
e
m
e
t
h
o
d
s
n
e
v
e
r
t
h
e
l
e
s
s
r
e
q
u
i
r
e
s
c
a
r
e
f
u
l
i
m
p
l
e
m
e
n
t
a
t
i
o
n
,
i
n
c
l
u
d
i
n
g
h
y
p
e
r
p
a
r
a
m
e
t
e
r
t
u
n
i
n
g
,
m
o
d
e
l
c
a
l
ib
r
a
t
io
n
,
a
n
d
r
i
g
o
r
o
u
s
d
i
a
g
n
o
s
t
i
c
a
s
s
e
s
s
m
e
n
t
.
T
r
an
s
p
a
r
e
n
t
r
ep
o
r
t
i
n
g
r
e
m
a
i
n
s
c
r
i
t
i
c
a
l
i
n
h
i
g
h
-
d
i
m
e
n
s
i
o
n
a
l
s
e
t
t
i
n
g
s
t
o
e
n
s
u
r
e
i
n
t
e
r
p
r
e
t
ab
i
l
i
t
y
,
r
e
p
r
o
d
u
ci
b
i
l
i
t
y
,
a
n
d
p
o
l
i
c
y
r
e
l
e
v
a
n
c
e
,
a
s
e
m
p
h
a
s
i
z
e
d
i
n
r
e
c
e
n
t
m
e
t
h
o
d
o
l
o
g
i
c
a
l
g
u
i
d
a
n
c
e
[
4
4
]
–
[
4
7
]
.
W
h
e
n
a
p
p
l
i
ed
w
i
t
h
a
p
p
r
o
p
r
i
a
t
e
m
e
t
h
o
d
o
l
o
g
i
c
a
l
a
n
d
e
t
h
i
c
a
l
s
a
f
e
g
u
a
r
d
s
,
M
L
-
b
a
s
e
d
P
S
E
en
h
a
n
c
e
s
t
h
e
r
i
g
o
r
,
c
r
e
d
ib
i
l
i
t
y
,
a
n
d
p
r
ec
i
s
i
o
n
o
f
s
o
c
i
o
e
co
n
o
m
i
c
e
v
a
l
u
a
t
i
o
n
s
[
3
]
,
[
1
2
]
,
[
4
8
]
.
T
h
is
r
ev
ie
w
co
n
tr
ib
u
tes
b
y
s
y
n
t
h
esizi
n
g
M
L
-
P
SE
ev
id
en
ce
ac
r
o
s
s
p
u
b
lic
h
ea
lt
h
,
ec
o
n
o
m
ics,
ed
u
ca
tio
n
,
an
d
s
o
cial
p
o
licy
.
Un
li
k
e
p
r
io
r
w
o
r
k
f
o
cu
s
ed
o
n
in
d
iv
id
u
al
alg
o
r
it
h
m
s
,
it
co
m
p
ar
es
p
er
f
o
r
m
an
ce
p
atter
n
s
ac
r
o
s
s
m
u
ltip
le
ML
f
a
m
ilie
s
a
n
d
s
o
cio
ec
o
n
o
m
ic
co
n
tex
ts
,
e
x
te
n
d
in
g
ea
r
lier
an
a
l
y
s
es
b
y
C
a
n
n
a
s
a
n
d
A
r
p
in
o
[
3
4
]
,
T
u
[
3
1
]
,
an
d
Gu
z
m
an
-
Alv
ar
ez
et
a
l.
[
7
]
.
I
t
f
u
r
th
er
in
te
g
r
ates
e
m
er
g
in
g
p
er
s
p
ec
tiv
es
o
n
f
air
n
es
s
-
a
w
ar
e
ML
[
2
6
]
,
ex
p
lain
ab
le
ar
tif
icial
i
n
tel
lig
e
n
ce
[
2
7
]
,
an
d
m
u
ltil
e
v
el
m
o
d
elin
g
[
3
5
]
,
p
r
o
v
id
in
g
clea
r
er
g
u
id
a
n
ce
o
n
w
h
en
a
n
d
h
o
w
ML
-
b
ased
m
et
h
o
d
s
o
u
tp
er
f
o
r
m
tr
ad
itio
n
al
PS
ap
p
r
o
ac
h
es
in
p
o
lic
y
-
r
elev
a
n
t
s
etti
n
g
s
[
3
8
]
,
[
4
9
]
,
[
5
0
]
.
T
h
e
p
er
f
o
r
m
an
ce
a
n
al
y
s
i
s
o
f
m
o
d
el
s
u
s
ed
in
p
r
o
p
en
s
it
y
e
s
ti
m
atio
n
is
s
u
m
m
ar
ized
in
T
ab
le
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
Ma
ch
in
e
lea
r
n
in
g
mo
d
els in
th
e
en
h
a
n
ce
men
t o
f P
S
E
in
h
i
g
h
-
d
imen
s
io
n
a
l
…
(
Gen
e
Ma
r
ck
B
.
C
a
ted
r
illa
)
651
T
ab
le
2
.
A
n
al
y
s
i
s
o
f
m
o
d
el
p
er
f
o
r
m
an
ce
u
s
ed
i
n
p
r
o
p
en
s
it
y
esti
m
atio
n
A
u
t
h
o
r
/
s
B
e
st
m
o
d
e
l
P
e
r
f
o
r
man
c
e
R
e
mark
s
T
u
[
3
1
]
G
r
a
d
i
e
n
t
b
o
o
st
i
n
g
(
G
B
M
)
L
o
w
e
st
M
S
E
a
c
r
o
ss a
l
l
si
mu
l
a
t
i
o
n
sce
n
a
r
i
o
s
G
B
M
c
o
n
s
i
st
e
n
t
l
y
o
u
t
p
e
r
f
o
r
me
d
R
F
,
b
a
g
g
i
n
g
,
a
n
d
mu
l
t
i
n
o
mi
a
l
L
R
i
n
g
e
n
e
r
a
l
i
z
e
d
PSE
.
C
a
n
n
a
s
a
n
d
A
r
p
i
n
o
[
3
4
]
RF
(
P
S
W
)
B
e
st
A
S
A
M
(
c
o
v
a
r
i
a
t
e
b
a
l
a
n
c
e
)
;
t
o
p
b
i
a
s
r
e
d
u
c
t
i
o
n
i
n
P
S
W
R
F
p
r
o
d
u
c
e
d
s
t
r
o
n
g
e
st
o
v
e
r
a
l
l
b
a
l
a
n
c
e
;
N
N
a
l
so
st
r
o
n
g
b
u
t
sl
i
g
h
t
l
y
b
e
l
o
w
R
F
.
F
e
r
r
i
-
G
a
r
c
í
a
a
n
d
R
u
e
d
a
[
2
8
]
RF
(
l
a
r
g
e
samp
l
e
)
/
LR
(
smal
l
samp
l
e
)
L
o
w
e
st
M
S
E
i
n
mo
st
c
o
n
d
i
t
i
o
n
s
(
R
F
)
R
F
r
e
mo
v
e
d
mo
st
b
i
a
s
a
s v
o
l
u
n
t
e
e
r
samp
l
e
si
z
e
i
n
c
r
e
a
se
d
;
G
B
M
se
c
o
n
d
-
b
e
st
i
n
l
a
r
g
e
samp
l
e
s.
G
r
e
e
n
e
e
t
a
l
.
[
2
0
]
ML
-
b
a
se
d
G
P
S
(
C
D
F
me
t
h
o
d
)
B
i
a
s
=
–
0
.
0
4
5
t
o
0
.
0
2
8
V
e
r
y
l
o
w
a
b
so
l
u
t
e
b
i
a
s
;
e
x
c
e
l
l
e
n
t
st
r
a
t
i
f
i
c
a
t
i
o
n
q
u
a
l
i
t
y
f
o
r
o
r
d
i
n
a
l
e
x
p
o
su
r
e
s.
Š
i
n
k
o
v
e
c
e
t
a
l
.
[
2
1
]
R
i
d
g
e
LR
(
t
u
n
e
d
)
L
o
w
e
st
R
M
S
E
a
mo
n
g
c
o
mp
a
r
e
d
me
t
h
o
d
s
T
u
n
i
n
g
i
m
p
r
o
v
e
d
st
a
b
i
l
i
t
y
a
n
d
r
e
d
u
c
e
d
e
st
i
mat
i
o
n
e
r
r
o
r
i
n
sm
a
l
l
/
sp
a
r
se
sa
mp
l
e
s.
Z
o
u
e
t
a
l
.
[
8
]
K
e
r
n
e
l
M
L
(
p
r
o
p
o
se
d
me
t
h
o
d
)
A
T
E
me
a
n
≈
0
.
5
0
0
,
C
I
c
o
v
e
r
a
g
e
=
9
5
.
0
%
M
o
st
a
c
c
u
r
a
t
e
a
n
d
st
a
b
l
e
A
T
E
e
st
i
mat
e
s;
f
a
r
b
e
t
t
e
r
c
o
v
e
r
a
g
e
t
h
a
n
R
F
o
r
L
A
S
S
O
.
F
e
r
r
i
-
G
a
r
c
í
a
a
n
d
R
u
e
d
a
[
2
8
]
G
B
M
(
w
i
t
h
a
l
l
p
r
e
d
i
c
t
o
r
s)
L
o
w
e
st
M
S
E
f
o
r
l
a
r
g
e
samp
l
e
s
G
B
M
a
c
h
i
e
v
e
d
se
c
o
n
d
-
b
e
st
M
S
E
o
v
e
r
a
l
l
a
n
d
st
r
o
n
g
e
st
w
h
e
n
man
y
p
r
e
d
i
c
t
o
r
s
u
se
d
.
G
u
o
e
t
a
l
.
[
3
7
]
DNN
s
M
o
st
s
t
a
b
l
e
P
S
p
r
e
d
i
c
t
i
o
n
s
D
N
N
s o
u
t
p
e
r
f
o
r
m
LR
a
n
d
k
e
r
n
e
l
me
t
h
o
d
s
i
n
h
i
g
h
-
d
i
me
n
s
i
o
n
a
l
n
o
n
l
i
n
e
a
r
d
a
t
a
.
S
a
l
d
i
t
t
a
n
d
N
e
st
l
e
r
[
3
5
]
B
A
R
T
-
R
E
(
su
p
e
r
l
e
a
r
n
e
r
)
S
L
w
e
i
g
h
t
=
0
.
4
7
–
0
.
6
0
(
h
i
g
h
e
st
)
B
A
R
T
-
R
E
c
o
n
si
s
t
e
n
t
l
y
d
o
mi
n
a
t
e
s SL
;
i
n
d
i
c
a
t
e
s
b
e
st
p
e
r
f
o
r
man
c
e
i
n
m
u
l
t
i
l
e
v
e
l
s
e
t
t
i
n
g
s.
5.
CO
NCLU
SI
O
N
AND
R
E
C
O
M
M
E
NDATI
O
N
S
T
h
is
r
ev
ie
w
s
y
n
t
h
esized
e
v
id
en
ce
f
r
o
m
6
0
s
t
u
d
ies
ap
p
l
y
i
n
g
M
L
-
P
SE
in
s
o
cio
ec
o
n
o
m
ic
ev
alu
a
tio
n
.
A
cr
o
s
s
d
iv
er
s
e
e
m
p
ir
ical
an
d
s
i
m
u
la
ted
co
n
te
x
ts
,
th
e
f
i
n
d
i
n
g
s
co
n
s
is
ten
tl
y
in
d
icate
th
at
ML
-
P
SE
p
r
o
v
id
es
s
u
b
s
ta
n
tial
m
eth
o
d
o
lo
g
ical
a
d
v
an
ta
g
es
o
v
er
tr
ad
itio
n
al
lo
g
is
t
ic
r
eg
r
es
s
io
n
,
p
ar
tic
u
lar
l
y
w
h
e
n
d
ata
e
x
h
ib
it
n
o
n
li
n
ea
r
it
y
,
h
ig
h
d
i
m
e
n
s
io
n
alit
y
,
a
n
d
i
n
co
m
p
lete
b
a
s
eli
n
e
i
n
f
o
r
m
atio
n
.
E
n
s
e
m
b
le
le
ar
n
in
g
ap
p
r
o
ac
h
es,
in
cl
u
d
in
g
RF
,
g
r
ad
ien
t
b
o
o
s
tin
g
,
an
d
b
ag
g
ed
tr
ee
s
,
r
ep
ea
ted
l
y
d
e
m
o
n
s
tr
ated
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
in
ac
h
ie
v
in
g
co
v
ar
ia
te
b
alan
ce
,
r
ed
u
cin
g
b
ias,
a
n
d
i
m
p
r
o
v
in
g
p
r
ed
ictiv
e
ac
cu
r
ac
y
.
DNN
s
f
u
r
th
er
s
h
o
w
ed
s
tr
o
n
g
ca
p
ac
it
y
to
m
o
d
el
co
m
p
le
x
,
n
o
n
ad
d
itiv
e
r
elatio
n
s
h
ip
s
an
d
f
r
eq
u
en
tl
y
o
u
tp
er
f
o
r
m
ed
co
n
v
e
n
tio
n
al
m
eth
o
d
s
in
ch
alle
n
g
i
n
g
s
o
cio
ec
o
n
o
m
ic
s
e
ttin
g
s
,
u
n
d
er
s
co
r
i
n
g
t
h
e
p
o
ten
tial
o
f
f
lex
ib
le
lear
n
i
n
g
ar
ch
it
ec
tu
r
es
f
o
r
ca
u
s
a
l
ad
j
u
s
t
m
e
n
t in
co
m
p
lex
p
o
lic
y
d
ata.
Desp
ite
th
ese
ad
v
a
n
ta
g
es,
th
e
r
ev
ie
w
h
i
g
h
lig
h
t
s
th
at
s
u
cc
ess
f
u
l
i
m
p
le
m
en
ta
tio
n
o
f
M
L
-
P
S
E
d
ep
en
d
s
cr
iticall
y
o
n
ca
r
e
f
u
l
m
e
th
o
d
o
lo
g
ical
p
r
ac
tice.
A
p
p
r
o
p
r
i
ate
h
y
p
er
p
ar
a
m
eter
t
u
n
in
g
,
m
o
d
el
ca
l
ib
r
atio
n
,
d
iag
n
o
s
t
ic
ass
e
s
s
m
e
n
t,
an
d
tr
a
n
s
p
ar
en
t
r
ep
o
r
tin
g
ar
e
es
s
en
t
i
al
to
en
s
u
r
e
r
o
b
u
s
t
n
ess
an
d
cr
ed
ib
ilit
y
o
f
r
es
u
lt
s
.
I
n
ter
p
r
etab
ilit
y
r
e
m
ai
n
s
a
k
e
y
ch
allen
g
e,
p
ar
ticu
lar
l
y
f
o
r
h
i
g
h
l
y
co
m
p
le
x
m
o
d
els
s
u
c
h
a
s
DNN
s
;
h
o
w
ev
er
,
ad
v
a
n
ce
s
i
n
ex
p
lai
n
ab
le
ar
tif
i
cial
in
telli
g
e
n
ce
an
d
f
air
n
ess
-
a
w
ar
e
ML
p
r
o
v
id
e
p
r
o
m
i
s
i
n
g
p
ath
w
a
y
s
to
ad
d
r
ess
tr
an
s
p
ar
en
c
y
a
n
d
ac
co
u
n
tab
ili
t
y
co
n
ce
r
n
s
.
T
h
ese
co
n
s
id
er
atio
n
s
ar
e
esp
ec
iall
y
s
al
ien
t
i
n
p
u
b
lic
p
o
licy
a
n
d
s
o
cio
ec
o
n
o
m
ic
r
esear
ch
,
w
h
e
r
e
eq
u
ity
,
tr
u
s
t,
an
d
in
ter
p
r
etab
ilit
y
ar
e
in
teg
r
al
to
d
ec
is
io
n
-
m
a
k
i
n
g
.
Ov
er
al
l,
g
r
ad
ien
t
b
o
o
s
tin
g
m
et
h
o
d
s
,
RF
,
DNN
s
,
a
n
d
B
a
y
esia
n
ad
d
itiv
e
r
eg
r
es
s
io
n
tr
ee
s
e
m
er
g
ed
as
th
e
m
o
s
t
r
eliab
l
e
ap
p
r
o
ac
h
es
f
o
r
i
m
p
r
o
v
in
g
b
ia
s
r
ed
u
ctio
n
,
co
v
ar
iate
b
alan
ce
,
an
d
co
v
er
ag
e
p
r
o
b
ab
ilit
ies
i
n
h
i
g
h
-
d
i
m
e
n
s
io
n
al
s
o
cio
ec
o
n
o
m
ic
d
ata,
s
u
p
p
o
r
tin
g
th
e
u
s
e
o
f
M
L
-
P
SE
a
s
a
r
o
b
u
s
t
alter
n
ativ
e
to
tr
ad
itio
n
al
m
et
h
o
d
s
u
n
d
er
co
m
p
le
x
d
ata
-
g
e
n
er
atin
g
co
n
d
itio
n
s
.
T
h
e
r
ev
ie
w
a
ls
o
id
en
ti
f
ie
s
i
m
p
o
r
tan
t
av
en
u
e
s
f
o
r
f
u
t
u
r
e
r
es
ea
r
ch
.
Gr
ea
ter
e
m
p
ir
ical
v
alid
atio
n
u
s
i
n
g
r
ea
l
-
w
o
r
ld
s
o
cio
ec
o
n
o
m
ic
d
at
asets
i
s
n
ee
d
ed
,
as
m
u
c
h
o
f
t
h
e
e
x
is
ti
n
g
e
v
id
en
ce
r
e
m
ai
n
s
s
i
m
u
la
tio
n
-
b
ased
.
I
n
teg
r
ati
n
g
M
L
-
P
SE
w
it
h
h
et
er
o
g
en
eo
u
s
tr
ea
t
m
e
n
t
e
f
f
ec
t
m
o
d
eli
n
g
f
r
a
m
e
w
o
r
k
s
,
s
u
ch
a
s
ca
u
s
a
l
f
o
r
est
s
an
d
m
eta
-
lear
n
er
s
,
o
f
f
er
s
s
i
g
n
if
ica
n
t p
o
ten
tial to
u
n
co
v
er
d
if
f
er
en
tial i
m
p
ac
ts
ac
r
o
s
s
p
o
p
u
latio
n
s
u
b
g
r
o
u
p
s
d
e
f
in
e
d
b
y
g
e
n
d
er
,
in
co
m
e,
o
r
g
eo
g
r
ap
h
y
,
t
h
er
eb
y
s
u
p
p
o
r
tin
g
m
o
r
e
eq
u
itab
le
an
d
tar
g
eted
p
o
l
ic
y
d
esi
g
n
.
F
u
r
th
er
d
ev
elo
p
m
en
t
o
f
f
air
n
e
s
s
-
a
w
ar
e
PS
m
et
h
o
d
s
is
w
ar
r
an
ted
to
m
iti
g
ate
alg
o
r
it
h
m
ic
b
ias
in
tr
ea
t
m
e
n
t
ass
i
g
n
m
en
t,
alo
n
g
s
id
e
s
y
s
te
m
atic
ev
al
u
ati
o
n
o
f
co
m
p
u
tatio
n
al
ef
f
icie
n
c
y
a
n
d
s
ca
lab
ilit
y
to
in
f
o
r
m
ad
o
p
tio
n
in
r
eso
u
r
ce
-
co
n
s
tr
ain
ed
in
s
tit
u
tio
n
a
l
s
et
ti
n
g
s
.
Fi
n
all
y
,
t
h
e
e
s
tab
lis
h
m
e
n
t
o
f
s
ta
n
d
ar
d
ized
r
ep
o
r
tin
g
g
u
id
eli
n
e
s
an
d
b
e
s
t
-
p
r
ac
tice
f
r
a
m
e
w
o
r
k
s
w
i
ll
b
e
e
s
s
e
n
tial
to
p
r
o
m
o
te
tr
a
n
s
p
ar
e
n
c
y
,
r
ep
r
o
d
u
cib
ilit
y
,
an
d
r
esp
o
n
s
ib
le
u
s
e
o
f
M
L
-
P
SE
as th
ese
m
eth
o
d
s
co
n
tin
u
e
to
g
ain
p
r
o
m
i
n
en
ce
i
n
s
o
cio
e
co
n
o
m
ic
ev
a
lu
at
io
n
.
ACK
NO
WL
E
D
G
M
E
NT
S
T
h
e
au
th
o
r
s
w
o
u
ld
lik
e
to
ex
t
en
d
th
eir
g
r
atit
u
d
e
to
th
e
A
n
g
eles
Un
i
v
er
s
it
y
Fo
u
n
d
atio
n
,
an
d
L
a
g
u
n
a
State
P
o
ly
tec
h
n
ic
Un
i
v
er
s
it
y
f
o
r
th
e
s
u
p
p
o
r
t
in
th
e
co
n
d
u
cti
n
g
t
h
is
s
t
u
d
y
.
C
e
n
ter
f
o
r
L
ak
e
s
Su
s
tai
n
ab
le
Dev
elo
p
m
e
n
t
(
C
L
SD)
an
d
B
u
r
ea
u
o
f
Fi
s
h
an
d
A
q
u
at
ic
R
eso
u
r
ce
s
(
B
FAR
)
f
o
r
allo
w
i
n
g
th
e
au
t
h
o
r
s
to
u
s
e
th
eir
s
o
cio
ec
o
n
o
m
ic
d
ata
in
t
h
e
n
e
x
t
p
h
a
s
e
o
f
t
h
is
p
r
o
j
ec
t.
L
astl
y
,
th
e
Dep
ar
t
m
e
n
t
o
f
Scien
ce
an
d
T
ec
h
n
o
lo
g
y
Scien
ce
E
d
u
ca
t
io
n
I
n
s
tit
u
te
(
D
OST
-
SEI
)
f
o
r
th
e
f
i
n
a
n
cial
r
ep
o
r
t.
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
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
41
,
No
.
2
,
Feb
r
u
ar
y
20
2
6
:
64
5
-
65
4
652
F
UNDIN
G
I
NF
O
RM
AT
I
O
N
T
h
e
au
th
o
r
s
w
o
u
ld
lik
e
to
ac
k
n
o
w
led
g
e
th
e
DO
ST
-
SEI
f
o
r
t
h
e
r
esear
ch
g
r
an
t
f
o
r
th
e
w
h
o
l
e
co
n
d
u
ct
o
f
th
e
p
r
o
j
ec
t.
AUTHO
R
CO
NT
RIB
UT
I
O
NS ST
A
T
E
M
E
NT
T
h
e
task
in
co
m
p
le
tin
g
t
h
is
r
e
s
ea
r
ch
is
eq
u
a
ll
y
d
i
v
id
ed
a
m
o
n
g
t
h
e
au
th
o
r
s
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Gen
e
Ma
r
ck
B
.
C
ated
r
illa
J
o
ey
A
v
iles
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
si
s
I
:
I
n
v
e
st
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
si
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
t
h
o
r
s
s
tate
n
o
co
n
f
lic
t o
f
i
n
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
is
r
ev
ie
w
is
t
h
e
f
ir
s
t
p
h
as
e
o
f
th
is
p
r
o
j
ec
t
w
h
ic
h
d
o
es
n
o
t
in
v
o
l
v
ed
ca
teg
o
r
ical
o
r
n
u
m
er
ica
l
d
ataset.
Hen
ce
,
all
t
h
e
d
ata
u
s
ed
in
th
i
s
p
ap
er
is
av
ailab
le
in
th
e
d
o
i sectio
n
o
f
t
h
e
r
ef
er
e
n
c
es.
RE
F
E
R
E
NC
E
S
[
1
]
H
.
W
h
i
t
e
a
n
d
D
.
A
.
R
a
i
t
z
e
r
,
“
I
mp
a
c
t
e
v
a
l
u
a
t
i
o
n
o
f
d
e
v
e
l
o
p
me
n
t
i
n
t
e
r
v
e
n
t
i
o
n
s:
a
p
r
a
c
t
i
c
a
l
g
u
i
d
e
,
”
M
a
n
i
l
a
,
P
h
i
l
i
p
p
i
n
e
s,
D
e
c
.
2
0
1
7
.
d
o
i
:
1
0
.
2
2
6
1
7
/
T
C
S
1
7
9
1
8
8
-
2.
[
2
]
J.
G
a
o
,
Y
.
C
.
Z
h
a
n
g
,
a
n
d
T
.
Z
h
o
u
,
“
C
o
mp
u
t
a
t
i
o
n
a
l
so
c
i
o
e
c
o
n
o
mi
c
s,”
P
h
y
s
i
c
s
Re
p
o
rt
s
,
v
o
l
.
8
1
7
,
p
p
.
1
–
1
0
4
,
J
u
l
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
h
y
sr
e
p
.
2
0
1
9
.
0
5
.
0
0
2
.
[
3
]
K
.
N
a
r
i
t
a
,
J.
D
.
T
e
n
a
,
a
n
d
C
.
D
e
t
o
t
t
o
,
“
C
a
u
sal
i
n
f
e
r
e
n
c
e
w
i
t
h
o
b
se
r
v
a
t
i
o
n
a
l
d
a
t
a
:
a
t
u
t
o
r
i
a
l
o
n
p
r
o
p
e
n
si
t
y
sco
r
e
a
n
a
l
y
si
s,”
L
e
a
d
e
rs
h
i
p
Q
u
a
rt
e
r
l
y
,
v
o
l
.
3
4
,
n
o
.
3
,
p
.
1
0
1
6
7
8
,
J
u
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
l
e
a
q
u
a
.
2
0
2
3
.
1
0
1
6
7
8
.
[4
]
P
.
R
.
R
o
se
n
b
a
u
m
a
n
d
D
.
B
.
R
u
b
i
n
,
“
P
r
o
p
e
n
si
t
y
sco
r
e
s
i
n
t
h
e
d
e
si
g
n
o
f
o
b
se
r
v
a
t
i
o
n
a
l
s
t
u
d
i
e
s
f
o
r
c
a
u
sal
e
f
f
e
c
t
s,
”
B
i
o
m
e
t
r
i
k
a
,
v
o
l
.
1
1
0
,
n
o
.
1
,
p
p
.
1
–
1
3
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
9
3
/
b
i
o
me
t
/
a
sac
0
5
4
.
[
5
]
P
.
C
.
A
u
s
t
i
n
,
N
.
Je
mb
e
r
e
,
a
n
d
M
.
C
h
i
u
,
“
P
r
o
p
e
n
si
t
y
sco
r
e
m
a
t
c
h
i
n
g
a
n
d
c
o
mp
l
e
x
su
r
v
e
y
s,”
S
t
a
t
i
s
t
i
c
a
l
M
e
t
h
o
d
s
i
n
M
e
d
i
c
a
l
Re
se
a
rc
h
,
v
o
l
.
2
7
,
n
o
.
4
,
p
p
.
1
2
4
0
–
1
2
5
7
,
A
p
r
.
2
0
1
8
,
d
o
i
:
1
0
.
1
1
7
7
/
0
9
6
2
2
8
0
2
1
6
6
5
8
9
2
0
.
[
6
]
H
.
C
h
a
m a
n
d
S
.
G
.
W
e
st
,
“
P
r
o
p
e
n
si
t
y
sco
r
e
a
n
a
l
y
si
s
w
i
t
h
mi
ssi
n
g
d
a
t
a
,
”
Ps
y
c
h
o
l
o
g
i
c
a
l
M
e
t
h
o
d
s
,
v
o
l
.
2
1
,
n
o
.
3
,
p
p
.
4
2
7
–
4
4
5
,
S
e
p
.
2
0
1
6
,
d
o
i
:
1
0
.
1
0
3
7
/
me
t
0
0
0
0
0
7
6
.
[
7
]
A
.
G
u
z
man
-
A
l
v
a
r
e
z
,
X
.
Q
i
n
,
a
n
d
P
.
W
.
S
c
o
t
t
,
“
D
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
s
f
o
r
p
r
o
p
e
n
si
t
y
sco
r
e
e
st
i
mat
i
o
n
,
”
Mu
l
t
i
v
a
ri
a
t
e
Be
h
a
v
i
o
r
a
l
Re
se
a
rc
h
,
v
o
l
.
5
7
,
n
o
.
1
,
p
p
.
1
6
4
–
1
6
5
,
Jan
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
8
0
/
0
0
2
7
3
1
7
1
.
2
0
2
1
.
2
0
1
1
6
9
5
.
[
8
]
B
.
Z
o
u
,
X
.
M
i
,
P
.
J.
T
i
g
h
e
,
G
.
G
.
K
o
c
h
,
a
n
d
F
.
Z
o
u
,
“
O
n
k
e
r
n
e
l
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
p
r
o
p
e
n
si
t
y
sco
r
e
e
st
i
mat
i
o
n
u
n
d
e
r
c
o
mp
l
e
x
c
o
n
f
o
u
n
d
i
n
g
s
t
r
u
c
t
u
r
e
s,”
P
h
a
rm
a
c
e
u
t
i
c
a
l
S
t
a
t
i
st
i
c
s
,
v
o
l
.
2
0
,
n
o
.
4
,
p
p
.
7
5
2
–
7
6
4
,
Ju
l
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
2
/
p
st
.
2
1
0
5
.
[9
]
S
.
R
.
K
ü
n
z
e
l
,
J.
S
.
S
e
k
h
o
n
,
P
.
J.
B
i
c
k
e
l
,
a
n
d
B
.
Y
u
,
“
M
e
t
a
l
e
a
r
n
e
r
s
f
o
r
e
st
i
mat
i
n
g
h
e
t
e
r
o
g
e
n
e
o
u
s
t
r
e
a
t
me
n
t
e
f
f
e
c
t
s
u
si
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
N
a
t
i
o
n
a
l
A
c
a
d
e
m
y
o
f
S
c
i
e
n
c
e
s
o
f
t
h
e
U
n
i
t
e
d
S
t
a
t
e
s
o
f
Am
e
ri
c
a
,
v
o
l
.
1
1
6
,
n
o
.
1
0
,
p
p
.
4
1
5
6
–
4
1
6
5
,
M
a
r
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
7
3
/
p
n
a
s.
1
8
0
4
5
9
7
1
1
6
.
[
1
0
]
Z
.
S
a
d
i
q
u
e
,
R
.
G
r
i
e
v
e
,
K
.
D
i
a
z
-
O
r
d
a
z
,
P
.
M
o
u
n
c
e
y
,
F
.
L
a
mo
n
t
a
g
n
e
,
a
n
d
S
.
O
’
N
e
i
l
l
,
“
A
mac
h
i
n
e
-
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
e
st
i
m
a
t
i
n
g
su
b
g
r
o
u
p
-
a
n
d
i
n
d
i
v
i
d
u
a
l
-
l
e
v
e
l
t
r
e
a
t
me
n
t
e
f
f
e
c
t
s:
a
n
i
l
l
u
st
r
a
t
i
o
n
u
s
i
n
g
t
h
e
6
5
t
r
i
a
l
,
”
M
e
d
i
c
a
l
D
e
c
i
si
o
n
M
a
k
i
n
g
,
v
o
l
.
4
2
,
n
o
.
7
,
p
p
.
9
2
3
–
9
3
6
,
O
c
t
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
7
7
/
0
2
7
2
9
8
9
X
2
2
1
1
0
0
7
1
7
.
[
1
1
]
D
.
K
a
b
a
t
a
a
n
d
M
.
S
h
i
n
t
a
n
i
,
“
O
n
p
r
o
p
e
n
si
t
y
sco
r
e
mi
s
sp
e
c
i
f
i
c
a
t
i
o
n
i
n
d
o
u
b
l
e
/
d
e
b
i
a
se
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
c
a
u
s
a
l
i
n
f
e
r
e
n
c
e
:
e
n
se
mb
l
e
a
n
d
s
t
r
a
t
i
f
i
e
d
a
p
p
r
o
a
c
h
e
s,”
C
o
m
m
u
n
i
c
a
t
i
o
n
s
i
n
S
t
a
t
i
s
t
i
c
s:
S
i
m
u
l
a
t
i
o
n
a
n
d
C
o
m
p
u
t
a
t
i
o
n
,
v
o
l
.
5
4
,
n
o
.
5
,
p
p
.
1
2
8
3
–
1
2
9
3
,
M
a
y
2
0
2
5
,
d
o
i
:
1
0
.
1
0
8
0
/
0
3
6
1
0
9
1
8
.
2
0
2
3
.
2
2
7
9
0
2
2
.
[
1
2
]
Y
.
S
h
a
n
g
,
Y
.
H
.
C
h
i
u
,
a
n
d
L
.
K
o
n
g
,
“
R
o
b
u
st
p
r
o
p
e
n
si
t
y
sco
r
e
e
st
i
ma
t
i
o
n
v
i
a
l
o
ss
f
u
n
c
t
i
o
n
c
a
l
i
b
r
a
t
i
o
n
,
”
S
t
a
t
i
s
t
i
c
a
l
Me
t
h
o
d
s
i
n
Me
d
i
c
a
l
R
e
se
a
rc
h
,
v
o
l
.
3
4
,
n
o
.
3
,
p
p
.
4
5
7
–
4
7
2
,
M
a
r
.
2
0
2
5
,
d
o
i
:
1
0
.
1
1
7
7
/
0
9
6
2
2
8
0
2
2
4
1
3
0
8
7
0
9
.
[
1
3
]
A
.
D
a
n
g
,
“
R
e
a
l
-
w
o
r
l
d
e
v
i
d
e
n
c
e
:
a
p
r
i
me
r
,
”
P
h
a
rm
a
c
e
u
t
i
c
a
l
Me
d
i
c
i
n
e
,
v
o
l
.
3
7
,
n
o
.
1
,
p
p
.
2
5
–
3
6
,
J
a
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
0
2
9
0
-
022
-
0
0
4
5
6
-
6.
[
1
4
]
S
.
I
.
K
u
mb
h
a
r
a
n
d
C
.
M
.
Jag
t
a
p
,
“
I
m
p
a
c
t
a
sse
ssm
e
n
t
o
f
t
r
a
i
n
i
n
g
a
n
d
e
d
u
c
a
t
i
o
n
p
r
o
g
r
a
mm
e
s
o
n
t
h
e
w
o
r
k
e
r
s
q
u
a
l
i
t
y
o
f
w
o
r
k
l
i
f
e
a
n
d
q
u
a
l
i
t
y
o
f
l
i
f
e
,
”
S
c
h
o
l
a
rl
y
Re
s
e
a
r
c
h
J
o
u
r
n
a
l
f
o
r
H
u
m
a
n
i
t
y
S
c
i
e
n
c
e
a
n
d
E
n
g
l
i
s
h
L
a
n
g
u
a
g
e
,
v
o
l
.
9
,
n
o
.
4
7
,
p
p
.
1
1
4
8
5
–
1
1
4
9
4
,
O
c
t
.
2
0
2
1
,
d
o
i
:
1
0
.
2
1
9
2
2
/
sr
j
h
se
l
.
v
9
i
4
7
.
7
6
8
8
.
[
1
5
]
M
.
G
i
b
so
n
,
W
.
H
e
a
r
t
y
,
a
n
d
P
.
C
r
a
i
g
,
“
T
h
e
p
u
b
l
i
c
h
e
a
l
t
h
e
f
f
e
c
t
s
o
f
i
n
t
e
r
v
e
n
t
i
o
n
s
s
i
mi
l
a
r
t
o
b
a
si
c
i
n
c
o
me
:
a
sco
p
i
n
g
r
e
v
i
e
w
,
”
T
h
e
L
a
n
c
e
t
P
u
b
l
i
c
H
e
a
l
t
h
,
v
o
l
.
5
,
n
o
.
3
,
p
p
.
e
1
6
5
–
e
1
7
6
,
M
a
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
S
2
468
-
2
6
6
7
(
2
0
)
3
0
0
0
5
-
0.
[
1
6
]
A
.
L
e
mm
e
n
s
a
n
d
S
.
G
u
p
t
a
,
“
M
a
n
a
g
i
n
g
c
h
u
r
n
t
o
max
i
mi
z
e
p
r
o
f
i
t
s,”
M
a
r
k
e
t
i
n
g
S
c
i
e
n
c
e
,
v
o
l
.
3
9
,
n
o
.
5
,
p
p
.
9
5
6
–
9
7
3
,
S
e
p
.
2
0
2
0
,
d
o
i
:
1
0
.
1
2
8
7
/
mk
s
c
.
2
0
2
0
.
1
2
2
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
Ma
ch
in
e
lea
r
n
in
g
mo
d
els in
th
e
en
h
a
n
ce
men
t o
f P
S
E
in
h
i
g
h
-
d
imen
s
io
n
a
l
…
(
Gen
e
Ma
r
ck
B
.
C
a
ted
r
illa
)
653
[
1
7
]
P
.
C
.
A
u
st
i
n
,
“
A
sse
ssi
n
g
c
o
v
a
r
i
a
t
e
b
a
l
a
n
c
e
w
h
e
n
u
si
n
g
t
h
e
g
e
n
e
r
a
l
i
z
e
d
p
r
o
p
e
n
s
i
t
y
sco
r
e
w
i
t
h
q
u
a
n
t
i
t
a
t
i
v
e
o
r
c
o
n
t
i
n
u
o
u
s
e
x
p
o
su
r
e
s,”
S
t
a
t
i
st
i
c
a
l
Me
t
h
o
d
s
i
n
Me
d
i
c
a
l
Re
s
e
a
r
c
h
,
v
o
l
.
2
8
,
n
o
.
5
,
p
p
.
1
3
6
5
–
1
3
7
7
,
M
a
y
2
0
1
9
,
d
o
i
:
1
0
.
1
1
7
7
/
0
9
6
2
2
8
0
2
1
8
7
5
6
1
5
9
.
[
1
8
]
R
.
M
.
Jame
s
a
n
d
M
.
A
.
H
e
r
n
á
n
,
“
C
a
u
s
a
l
I
n
f
e
r
e
n
c
e
:
W
h
a
t
I
f
,
”
C
a
u
sa
l
I
n
f
e
re
n
c
e
-
W
h
a
t
I
f
,
p
.
3
0
2
,
2
0
2
0
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
w
w
w
.
h
sp
h
.
h
a
r
v
a
r
d
.
e
d
u
/
m
i
g
u
e
l
-
h
e
r
n
a
n
/
c
a
u
s
a
l
-
i
n
f
e
r
e
n
c
e
-
b
o
o
k
/
.
[
1
9
]
R
.
P
i
r
r
a
c
c
h
i
o
,
M
.
L
.
P
e
t
e
r
se
n
,
a
n
d
M
.
V
a
n
D
e
r
L
a
a
n
,
“
I
mp
r
o
v
i
n
g
p
r
o
p
e
n
si
t
y
sco
r
e
e
st
i
m
a
t
o
r
s’
r
o
b
u
st
n
e
ss
t
o
mo
d
e
l
mi
ssp
e
c
i
f
i
c
a
t
i
o
n
u
si
n
g
S
u
p
e
r
L
e
a
r
n
e
r
,
”
Am
e
r
i
c
a
n
J
o
u
r
n
a
l
o
f
E
p
i
d
e
m
i
o
l
o
g
y
,
v
o
l
.
1
8
1
,
n
o
.
2
,
p
p
.
1
0
8
–
1
1
9
,
J
a
n
.
2
0
1
5
,
d
o
i
:
1
0
.
1
0
9
3
/
a
j
e
/
k
w
u
2
5
3
.
[
2
0
]
T
.
J.
G
r
e
e
n
e
,
S
.
M
.
D
e
S
a
n
t
i
s,
D
.
W
.
B
r
o
w
n
,
A
.
V
.
W
i
l
k
i
n
so
n
,
a
n
d
M
.
D
.
S
w
a
r
t
z
,
“
A
mac
h
i
n
e
l
e
a
r
n
i
n
g
c
o
mp
a
t
i
b
l
e
me
t
h
o
d
f
o
r
o
r
d
i
n
a
l
p
r
o
p
e
n
s
i
t
y
sco
r
e
st
r
a
t
i
f
i
c
a
t
i
o
n
a
n
d
m
a
t
c
h
i
n
g
,
”
S
t
a
t
i
s
t
i
c
s
i
n
M
e
d
i
c
i
n
e
,
v
o
l
.
4
0
,
n
o
.
6
,
p
p
.
1
3
8
3
–
1
3
9
9
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
2
/
s
i
m.
8
8
4
6
.
[
2
1
]
H
.
Š
i
n
k
o
v
e
c
,
G
.
H
e
i
n
z
e
,
R
.
B
l
a
g
u
s,
a
n
d
A
.
G
e
r
o
l
d
i
n
g
e
r
,
“
T
o
t
u
n
e
o
r
n
o
t
t
o
t
u
n
e
,
a
c
a
se
st
u
d
y
o
f
r
i
d
g
e
l
o
g
i
st
i
c
r
e
g
r
e
ssi
o
n
i
n
s
mal
l
o
r
sp
a
r
se
d
a
t
a
se
t
s,”
BM
C
Me
d
i
c
a
l
R
e
s
e
a
r
c
h
Me
t
h
o
d
o
l
o
g
y
,
v
o
l
.
2
1
,
n
o
.
1
,
p
.
1
9
9
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
8
6
/
s1
2
8
7
4
-
0
2
1
-
0
1
3
7
4
-
y.
[
2
2
]
O
.
C
l
i
v
i
o
,
F
.
F
a
l
c
k
,
B
.
L
e
h
man
n
,
G
.
D
e
l
i
g
i
a
n
n
i
d
i
s
,
a
n
d
C
.
H
o
l
me
s,
“
N
e
u
r
a
l
sco
r
e
mat
c
h
i
n
g
f
o
r
h
i
g
h
-
d
i
me
n
si
o
n
a
l
c
a
u
sa
l
i
n
f
e
r
e
n
c
e
,
”
Pr
o
c
e
e
d
i
n
g
s
o
f
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
R
e
se
a
rc
h
,
v
o
l
.
1
5
1
,
p
p
.
7
0
7
6
–
7
1
1
0
,
2
0
2
2
.
[
2
3
]
Z
.
K
.
C
o
l
l
i
e
r
a
n
d
W
.
L
.
L
e
i
t
e
,
“
A
t
u
t
o
r
i
a
l
o
n
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
i
n
p
r
o
p
e
n
si
t
y
sco
r
e
a
n
a
l
y
si
s
,”
J
o
u
r
n
a
l
o
f
Ex
p
e
ri
m
e
n
t
a
l
Ed
u
c
a
t
i
o
n
,
v
o
l
.
9
0
,
n
o
.
4
,
p
p
.
1
0
0
3
–
1
0
2
0
,
O
c
t
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
8
0
/
0
0
2
2
0
9
7
3
.
2
0
2
0
.
1
8
5
4
1
5
8
.
[
2
4
]
W
.
Z
h
a
o
a
n
d
S
.
L
i
v
i
n
g
st
o
n
,
“
A
l
l
o
c
a
t
i
o
n
p
r
e
d
i
c
t
a
b
i
l
i
t
y
o
f
i
n
d
i
v
i
d
u
a
l
a
ss
i
g
n
me
n
t
s
i
n
r
e
st
r
i
c
t
e
d
r
a
n
d
o
m
i
z
a
t
i
o
n
d
e
si
g
n
s
f
o
r
t
w
o
-
a
r
m
e
q
u
a
l
a
l
l
o
c
a
t
i
o
n
t
r
i
a
l
s
,”
S
t
a
t
i
st
i
c
s
i
n
M
e
d
i
c
i
n
e
,
v
o
l
.
4
4
,
n
o
.
3
–
4
,
F
e
b
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
0
2
/
si
m
.
1
0
3
4
3
.
[
2
5
]
D
.
H
o
w
d
o
n
,
W
.
v
a
n
d
e
n
H
o
u
t
,
Y
.
v
a
n
d
e
r
L
i
n
d
e
n
,
a
n
d
K
.
S
p
e
n
c
e
r
,
“
R
e
p
l
a
c
i
n
g
p
e
r
f
o
r
man
c
e
st
a
t
u
s
w
i
t
h
a
si
mp
l
e
p
a
t
i
e
n
t
-
r
e
p
o
r
t
e
d
o
u
t
c
o
me
i
n
p
a
l
l
i
a
t
i
v
e
r
a
d
i
o
t
h
e
r
a
p
y
p
r
o
g
n
o
st
i
c
mo
d
e
l
l
i
n
g
,
”
C
l
i
n
i
c
a
l
a
n
d
T
r
a
n
s
l
a
t
i
o
n
a
l
R
a
d
i
a
t
i
o
n
O
n
c
o
l
o
g
y
,
v
o
l
.
3
7
,
p
p
.
1
3
7
–
1
4
4
,
N
o
v
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
t
r
o
.
2
0
2
2
.
0
9
.
0
0
8
.
[
2
6
]
K
.
T
.
R
o
d
o
l
f
a
,
H
.
L
a
mb
a
,
a
n
d
R
.
G
h
a
n
i
,
“
E
m
p
i
r
i
c
a
l
o
b
se
r
v
a
t
i
o
n
o
f
n
e
g
l
i
g
i
b
l
e
f
a
i
r
n
e
ss
–
a
c
c
u
r
a
c
y
t
r
a
d
e
-
o
f
f
s i
n
mac
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
p
u
b
l
i
c
p
o
l
i
c
y
,
”
N
a
t
u
r
e
Ma
c
h
i
n
e
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
3
,
n
o
.
1
0
,
p
p
.
8
9
6
–
9
0
4
,
O
c
t
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
2
2
5
6
-
0
2
1
-
0
0
3
9
6
-
x.
[
2
7
]
V
.
H
a
ss
i
j
a
e
t
a
l
.
,
“
I
n
t
e
r
p
r
e
t
i
n
g
b
l
a
c
k
-
b
o
x
mo
d
e
l
s:
a
r
e
v
i
e
w
o
n
e
x
p
l
a
i
n
a
b
l
e
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
,”
C
o
g
n
i
t
i
v
e
C
o
m
p
u
t
a
t
i
o
n
,
v
o
l
.
1
6
,
n
o
.
1
,
p
p
.
4
5
–
7
4
,
J
a
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
2
5
5
9
-
023
-
1
0
1
7
9
-
8.
[
2
8
]
R
.
F
e
r
r
i
-
G
a
r
c
í
a
a
n
d
M
.
D
e
l
M
a
r
R
u
e
d
a
,
“
P
r
o
p
e
n
si
t
y
sco
r
e
a
d
j
u
st
me
n
t
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
c
l
a
ss
i
f
i
c
a
t
i
o
n
a
l
g
o
r
i
t
h
ms
t
o
c
o
n
t
r
o
l
se
l
e
c
t
i
o
n
b
i
a
s
i
n
o
n
l
i
n
e
su
r
v
e
y
s,”
PLo
S
O
N
E
,
v
o
l
.
1
5
,
n
o
.
4
,
p
.
e
0
2
3
1
5
0
0
,
A
p
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
2
3
1
5
0
0
.
[
2
9
]
V
.
T
r
u
o
n
g
,
“
N
a
t
u
r
a
l
l
a
n
g
u
a
g
e
p
r
o
c
e
ssi
n
g
i
n
a
d
v
e
r
t
i
si
n
g
-
a
sy
st
e
mat
i
c
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
2
0
2
2
5
t
h
As
i
a
C
o
n
f
e
re
n
c
e
o
n
M
a
c
h
i
n
e
L
e
a
rn
i
n
g
a
n
d
C
o
m
p
u
t
i
n
g
,
A
C
M
L
C
2
0
2
2
,
D
e
c
.
2
0
2
2
,
p
p
.
8
9
–
9
8
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
M
L
C
5
8
1
7
3
.
2
0
2
2
.
0
0
0
2
4
.
[
3
0
]
Z
.
T
a
n
,
“
R
e
g
u
l
a
r
i
z
e
d
c
a
l
i
b
r
a
t
e
d
e
st
i
ma
t
i
o
n
o
f
p
r
o
p
e
n
si
t
y
sco
r
e
s
w
i
t
h
mo
d
e
l
mi
ssp
e
c
i
f
i
c
a
t
i
o
n
a
n
d
h
i
g
h
-
d
i
me
n
si
o
n
a
l
d
a
t
a
,
”
Bi
o
m
e
t
r
i
k
a
,
v
o
l
.
1
0
7
,
n
o
.
1
,
p
p
.
1
3
7
–
1
5
8
,
M
a
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
9
3
/
b
i
o
me
t
/
a
sz
0
5
9
.
[
3
1
]
C
.
T
u
,
“
C
o
mp
a
r
i
so
n
o
f
v
a
r
i
o
u
s
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
f
o
r
e
st
i
m
a
t
i
n
g
g
e
n
e
r
a
l
i
z
e
d
p
r
o
p
e
n
s
i
t
y
sco
r
e
,
”
J
o
u
r
n
a
l
o
f
S
t
a
t
i
st
i
c
a
l
C
o
m
p
u
t
a
t
i
o
n
a
n
d
S
i
m
u
l
a
t
i
o
n
,
v
o
l
.
8
9
,
n
o
.
4
,
p
p
.
7
0
8
–
7
1
9
,
M
a
r
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
8
0
/
0
0
9
4
9
6
5
5
.
2
0
1
9
.
1
5
7
1
0
5
9
.
[
3
2
]
M
.
P
e
n
g
,
Y
.
L
i
,
C
.
W
u
,
a
n
d
L
.
L
i
,
“
A
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
t
o
n
o
n
p
a
r
a
me
t
r
i
c
p
r
o
p
e
n
s
i
t
y
sco
r
e
e
st
i
mat
i
o
n
w
i
t
h
o
p
t
i
mi
z
e
d
c
o
v
a
r
i
a
t
e
b
a
l
a
n
c
e
,
”
ArX
i
v
,
2
0
2
4
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
:
/
/
a
r
x
i
v
.
o
r
g
/
a
b
s
/
2
4
0
4
.
0
4
7
9
4
.
[
3
3
]
A
.
L
i
n
d
e
n
a
n
d
P
.
R
.
Y
a
r
n
o
l
d
,
“
U
si
n
g
c
l
a
ssi
f
i
c
a
t
i
o
n
t
r
e
e
a
n
a
l
y
si
s
t
o
g
e
n
e
r
a
t
e
p
r
o
p
e
n
si
t
y
sco
r
e
w
e
i
g
h
t
s,”
J
o
u
rn
a
l
o
f
Ev
a
l
u
a
t
i
o
n
i
n
C
l
i
n
i
c
a
l
Pra
c
t
i
c
e
,
v
o
l
.
2
3
,
n
o
.
4
,
p
p
.
7
0
3
–
7
1
2
,
A
u
g
.
2
0
1
7
,
d
o
i
:
1
0
.
1
1
1
1
/
j
e
p
.
1
2
7
4
4
.
[
3
4
]
M
.
C
a
n
n
a
s
a
n
d
B
.
A
r
p
i
n
o
,
“
A
c
o
mp
a
r
i
so
n
o
f
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
s
a
n
d
c
o
v
a
r
i
a
t
e
b
a
l
a
n
c
e
me
a
su
r
e
s
f
o
r
p
r
o
p
e
n
s
i
t
y
sco
r
e
mat
c
h
i
n
g
a
n
d
w
e
i
g
h
t
i
n
g
,
”
Bi
o
m
e
t
ri
c
a
l
J
o
u
r
n
a
l
,
v
o
l
.
6
1
,
n
o
.
4
,
p
p
.
1
0
4
9
–
1
0
7
2
,
J
u
l
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
0
2
/
b
i
m
j
.
2
0
1
8
0
0
1
3
2
.
[
3
5
]
M
.
S
a
l
d
i
t
t
a
n
d
S
.
N
e
st
l
e
r
,
“
P
a
r
a
me
t
r
i
c
a
n
d
n
o
n
p
a
r
a
me
t
r
i
c
p
r
o
p
e
n
s
i
t
y
sco
r
e
e
st
i
mat
i
o
n
i
n
m
u
l
t
i
l
e
v
e
l
o
b
se
r
v
a
t
i
o
n
a
l
st
u
d
i
e
s,
”
S
t
a
t
i
st
i
c
s
i
n
M
e
d
i
c
i
n
e
,
v
o
l
.
4
2
,
n
o
.
2
3
,
p
p
.
4
1
4
7
–
4
1
7
6
,
O
c
t
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
2
/
si
m
.
9
8
5
2
.
[
3
6
]
M
.
E.
K
a
r
i
m,
“
H
i
g
h
-
d
i
me
n
si
o
n
a
l
p
r
o
p
e
n
si
t
y
sco
r
e
a
n
d
i
t
s
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
e
x
t
e
n
si
o
n
s i
n
r
e
si
d
u
a
l
c
o
n
f
o
u
n
d
i
n
g
c
o
n
t
r
o
l
,
”
Am
e
ri
c
a
n
S
t
a
t
i
st
i
c
i
a
n
,
v
o
l
.
7
9
,
n
o
.
1
,
p
p
.
7
2
–
9
0
,
Jan
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
8
0
/
0
0
0
3
1
3
0
5
.
2
0
2
4
.
2
3
6
8
7
9
4
.
[
3
7
]
Y
.
G
u
o
,
V
.
Y
.
S
t
r
a
u
ss
,
M
.
C
a
t
a
l
à
,
A
.
M
.
Jö
d
i
c
k
e
,
S
.
K
h
a
l
i
d
,
a
n
d
D
.
P
r
i
e
t
o
-
A
l
h
a
mb
r
a
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
me
t
h
o
d
s
f
o
r
p
r
o
p
e
n
si
t
y
a
n
d
d
i
se
a
se
r
i
sk
sco
r
e
e
st
i
mat
i
o
n
i
n
h
i
g
h
-
d
i
me
n
si
o
n
a
l
d
a
t
a
:
a
p
l
a
smo
d
e
si
m
u
l
a
t
i
o
n
a
n
d
r
e
a
l
-
w
o
r
l
d
d
a
t
a
c
o
h
o
r
t
a
n
a
l
y
si
s,”
Fro
n
t
i
e
rs
i
n
Ph
a
rm
a
c
o
l
o
g
y
,
v
o
l
.
1
5
,
O
c
t
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
h
a
r
.
2
0
2
4
.
1
3
9
5
7
0
7
.
[
3
8
]
L
.
L
i
e
t
a
l
.
,
“
C
o
m
p
a
r
a
t
i
v
e
e
f
f
e
c
t
i
v
e
n
e
ss
o
f
p
r
o
p
e
n
si
t
y
sco
r
e
e
st
i
mat
i
o
n
m
e
t
h
o
d
s
f
o
r
i
n
v
e
r
se
p
r
o
b
a
b
i
l
i
t
y
o
f
t
r
e
a
t
me
n
t
w
e
i
g
h
t
i
n
g
a
n
a
l
y
si
s
w
i
t
h
c
o
mp
l
e
x
su
r
v
e
y
d
a
t
a
:
a
si
mu
l
a
t
i
o
n
st
u
d
y
,
”
J
o
u
r
n
a
l
o
f
S
u
rv
e
y
S
t
a
t
i
st
i
c
s
a
n
d
M
e
t
h
o
d
o
l
o
g
y
,
A
p
r
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
9
3
/
j
ss
a
m/
s
maf0
0
3
.
[
3
9
]
D
.
W
e
st
r
e
i
c
h
,
J
.
L
e
ss
l
e
r
,
a
n
d
M
.
J.
F
u
n
k
,
“
P
r
o
p
e
n
si
t
y
sco
r
e
e
st
i
ma
t
i
o
n
:
n
e
u
r
a
l
n
e
t
w
o
r
k
s,
s
u
p
p
o
r
t
v
e
c
t
o
r
mac
h
i
n
e
s,
d
e
c
i
s
i
o
n
t
r
e
e
s
(
C
A
R
T
)
,
a
n
d
me
t
a
-
c
l
a
ssi
f
i
e
r
s a
s a
l
t
e
r
n
a
t
i
v
e
s t
o
l
o
g
i
st
i
c
r
e
g
r
e
ssi
o
n
,
”
J
o
u
r
n
a
l
o
f
C
l
i
n
i
c
a
l
E
p
i
d
e
m
i
o
l
o
g
y
,
v
o
l
.
6
3
,
n
o
.
8
,
p
p
.
8
2
6
–
8
3
3
,
A
u
g
.
2
0
1
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
c
l
i
n
e
p
i
.
2
0
0
9
.
1
1
.
0
2
0
.
[
4
0
]
V
.
B
o
r
i
so
v
,
T
.
L
e
e
man
n
,
K
.
S
e
b
l
e
r
,
J.
H
a
u
g
,
M
.
P
a
w
e
l
c
z
y
k
,
a
n
d
G
.
K
a
sn
e
c
i
,
“
D
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
s
a
n
d
t
a
b
u
l
a
r
d
a
t
a
:
a
su
r
v
e
y
,
”
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
N
e
u
r
a
l
N
e
t
w
o
r
k
s
a
n
d
L
e
a
r
n
i
n
g
S
y
st
e
m
s
,
v
o
l
.
3
5
,
n
o
.
6
,
p
p
.
7
4
9
9
–
7
5
1
9
,
Ju
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
T
N
N
L
S
.
2
0
2
2
.
3
2
2
9
1
6
1
.
[
4
1
]
N
.
K
r
e
i
f
,
K
.
D
.
O
r
d
a
z
,
R
.
M
o
r
e
n
o
-
S
e
r
r
a
,
A
.
M
i
r
e
l
man
,
T
.
H
i
d
a
y
a
t
,
a
n
d
M
.
S
u
h
r
c
k
e
,
“
Es
t
i
m
a
t
i
n
g
h
e
t
e
r
o
g
e
n
e
o
u
s
p
o
l
i
c
y
i
mp
a
c
t
s
u
si
n
g
c
a
u
sa
l
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
:
a
c
a
s
e
st
u
d
y
o
f
h
e
a
l
t
h
i
n
su
r
a
n
c
e
r
e
f
o
r
m
i
n
I
n
d
o
n
e
si
a
,
”
H
e
a
l
t
h
S
e
r
v
i
c
e
s
a
n
d
O
u
t
c
o
m
e
s
R
e
se
a
rc
h
Me
t
h
o
d
o
l
o
g
y
,
v
o
l
.
2
2
,
n
o
.
2
,
p
p
.
1
9
2
–
2
2
7
,
Ju
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
7
4
2
-
0
2
1
-
0
0
2
5
9
-
3.
[
4
2
]
J.
E.
B
r
a
n
d
,
J.
X
u
,
B
.
K
o
c
h
,
a
n
d
P
.
G
e
r
a
l
d
o
,
“
U
n
c
o
v
e
r
i
n
g
so
c
i
o
l
o
g
i
c
a
l
e
f
f
e
c
t
h
e
t
e
r
o
g
e
n
e
i
t
y
u
si
n
g
t
r
e
e
-
b
a
se
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
S
o
c
i
o
l
o
g
i
c
a
l
M
e
t
h
o
d
o
l
o
g
y
,
v
o
l
.
5
1
,
n
o
.
2
,
p
p
.
1
8
9
–
2
2
3
,
A
u
g
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
7
7
/
0
0
8
1
1
7
5
0
2
1
9
9
3
5
0
3
.
[
4
3
]
P
.
R
e
h
i
l
l
a
n
d
N
.
B
i
d
d
l
e
,
“
H
e
t
e
r
o
g
e
n
e
o
u
s
t
r
e
a
t
me
n
t
e
f
f
e
c
t
e
st
i
ma
t
i
o
n
w
i
t
h
h
i
g
h
-
d
i
me
n
si
o
n
a
l
d
a
t
a
i
n
p
u
b
l
i
c
p
o
l
i
c
y
e
v
a
l
u
a
t
i
o
n
,
”
2
0
2
4
.
[
4
4
]
W
.
H
u
,
X
.
S
u
n
,
Q
.
L
i
u
,
L
.
W
u
,
a
n
d
L
.
W
a
n
g
,
“
U
n
c
e
r
t
a
i
n
t
y
c
a
l
i
b
r
a
t
i
o
n
f
o
r
c
o
u
n
t
e
r
f
a
c
t
u
a
l
p
r
o
p
e
n
s
i
t
y
e
st
i
mat
i
o
n
i
n
r
e
c
o
mm
e
n
d
a
t
i
o
n
,
”
I
EEE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
K
n
o
w
l
e
d
g
e
a
n
d
D
a
t
a
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
3
7
,
n
o
.
6
,
p
p
.
3
7
8
1
–
3
7
9
3
,
J
u
n
.
2
0
2
5
,
d
o
i
:
1
0
.
1
1
0
9
/
T
K
D
E.
2
0
2
5
.
3
5
5
2
6
5
8
.
[
4
5
]
N
.
B
e
a
r
t
h
a
n
d
D
.
B
a
l
l
i
n
a
r
i
,
“
I
mp
r
o
v
i
n
g
t
h
e
f
i
n
i
t
e
sam
p
l
e
e
st
i
mat
i
o
n
o
f
a
v
e
r
a
g
e
t
r
e
a
t
me
n
t
e
f
f
e
c
t
s
u
s
i
n
g
d
o
u
b
l
e
/
d
e
b
i
a
se
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
w
i
t
h
p
r
o
p
e
n
si
t
y
sco
r
e
c
a
l
i
b
r
a
t
i
o
n
,
”
2
0
2
4
.
[
4
6
]
L
.
L
o
u
r
e
n
ç
o
,
L
.
W
e
b
e
r
,
L
.
G
a
r
c
i
a
,
V
.
R
a
mo
s,
a
n
d
J.
S
o
u
z
a
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
t
o
e
st
i
ma
t
e
p
r
o
p
e
n
si
t
y
sco
r
e
s
i
n
h
e
a
l
t
h
p
o
l
i
c
y
e
v
a
l
u
a
t
i
o
n
:
a
sco
p
i
n
g
r
e
v
i
e
w
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
E
n
v
i
ro
n
m
e
n
t
a
l
R
e
se
a
rc
h
a
n
d
P
u
b
l
i
c
H
e
a
l
t
h
,
v
o
l
.
2
1
,
n
o
.
1
1
,
p
.
1
4
8
4
,
N
o
v
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
i
j
e
r
p
h
2
1
1
1
1
4
8
4
.
[
4
7
]
K
.
F
u
r
mań
c
z
y
k
a
n
d
W
.
R
e
j
c
h
e
l
,
“
P
r
e
d
i
c
t
i
o
n
a
n
d
v
a
r
i
a
b
l
e
se
l
e
c
t
i
o
n
i
n
h
i
g
h
-
d
i
me
n
si
o
n
a
l
mi
ss
p
e
c
i
f
i
e
d
b
i
n
a
r
y
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
En
t
r
o
p
y
,
v
o
l
.
2
2
,
n
o
.
5
,
p
.
5
4
3
,
M
a
y
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
E
2
2
0
5
0
5
4
3
.
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
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
41
,
No
.
2
,
Feb
r
u
ar
y
20
2
6
:
64
5
-
65
4
654
[
4
8
]
L
.
Y
a
o
,
Z
.
C
h
u
,
S
.
L
i
,
Y
.
L
i
,
J.
G
a
o
,
a
n
d
A
.
Z
h
a
n
g
,
“
A
su
r
v
e
y
o
n
c
a
u
sal
i
n
f
e
r
e
n
c
e
,”
A
C
M
T
r
a
n
s
a
c
t
i
o
n
s
o
n
K
n
o
w
l
e
d
g
e
D
i
sc
o
v
e
ry
f
ro
m
D
a
t
a
,
v
o
l
.
1
5
,
n
o
.
5
,
p
p
.
1
–
4
6
,
O
c
t
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
4
5
/
3
4
4
4
9
4
4
.
[
4
9
]
K
.
W
a
n
g
,
L
.
R
o
sman
,
a
n
d
H
.
L
u
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
v
e
r
su
s
l
o
g
i
st
i
c
r
e
g
r
e
s
si
o
n
f
o
r
p
r
o
p
e
n
s
i
t
y
sco
r
e
e
st
i
m
a
t
i
o
n
:
a
b
e
n
c
h
mar
k
t
r
i
a
l
e
mu
l
a
t
i
o
n
a
g
a
i
n
st
t
h
e
P
A
R
A
D
I
G
M
-
H
F
r
a
n
d
o
mi
z
e
d
t
r
i
a
l
,
”
m
e
d
Rx
i
v
.
p
.
2
0
2
5
.
0
6
.
1
6
.
2
5
3
2
9
7
0
8
,
J
u
n
.
1
7
,
2
0
2
5
,
d
o
i
:
1
0
.
1
1
0
1
/
2
0
2
5
.
0
6
.
1
6
.
2
5
3
2
9
7
0
8
.
[
5
0
]
J.
T
a
z
a
r
e
e
t
a
l
.
,
“
T
r
a
n
s
p
a
r
e
n
c
y
o
f
h
i
g
h
-
d
i
me
n
s
i
o
n
a
l
p
r
o
p
e
n
si
t
y
sco
r
e
a
n
a
l
y
s
e
s:
g
u
i
d
a
n
c
e
f
o
r
d
i
a
g
n
o
st
i
c
s
a
n
d
r
e
p
o
r
t
i
n
g
,
”
Ph
a
rm
a
c
o
e
p
i
d
e
m
i
o
l
o
g
y
a
n
d
D
ru
g
S
a
f
e
t
y
,
v
o
l
.
3
1
,
n
o
.
4
,
p
p
.
4
1
1
–
4
2
3
,
A
p
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
2
/
p
d
s.
5
4
1
2
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
G
e
n
e
M
a
r
c
k
B
.
Ca
te
d
r
il
la
is
a
fa
c
u
lt
y
m
e
m
b
e
r
a
t
th
e
Co
ll
e
g
e
o
f
Co
m
p
u
ter
S
tu
d
ies
,
L
a
g
u
n
a
S
tate
P
o
ly
tec
h
n
ic
Un
iv
e
rsity
–
L
o
s
Ba
ñ
o
s
Ca
m
p
u
s.
He
e
a
rn
e
d
h
is
Ba
c
h
e
lo
r
o
f
S
c
ien
c
e
in
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
(BS
I
T
)
f
ro
m
L
S
P
U
L
o
s
Ba
ñ
o
s
a
n
d
c
o
m
p
lete
d
h
is
M
a
ste
r
in
I
n
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
(M
IT
)
a
t
th
e
T
e
c
h
n
o
lo
g
ica
l
I
n
stit
u
te
o
f
th
e
P
h
il
ip
p
in
e
s
–
M
a
n
il
a
.
Cu
rre
n
tl
y
,
h
e
is
p
u
rsu
in
g
h
is
Do
c
to
r
in
I
n
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
(DI
T
)
a
t
A
n
g
e
les
Un
iv
e
rsit
y
F
o
u
n
d
a
ti
o
n
.
His
a
c
a
d
e
m
ic
b
a
c
k
g
ro
u
n
d
is
g
r
o
u
n
d
e
d
i
n
i
n
f
o
rm
a
ti
o
n
tec
h
n
o
lo
g
y
a
n
d
re
se
a
rc
h
,
w
it
h
sp
e
c
if
ic
in
t
e
re
sts
i
n
d
a
ta
a
n
a
ly
ti
c
s,
a
rti
f
icia
l
in
telli
g
e
n
c
e
,
a
n
d
th
e
i
n
teg
ra
ti
o
n
o
f
tec
h
n
o
l
o
g
y
in
e
d
u
c
a
ti
o
n
a
n
d
g
o
v
e
rn
a
n
c
e
.
He
h
a
s
a
c
ti
v
e
l
y
c
o
n
tri
b
u
te
d
t
o
i
n
stit
u
ti
o
n
a
l
a
n
d
stu
d
e
n
t
re
se
a
rc
h
in
it
iativ
e
s,
w
it
h
re
c
e
n
t
w
o
rk
s
f
o
c
u
sin
g
o
n
t
h
e
u
se
o
f
ML
f
o
r
in
ter
p
re
ti
n
g
so
c
ial
a
n
d
h
e
a
lt
h
-
re
late
d
d
a
ta.
In
a
d
d
it
i
o
n
t
o
tea
c
h
in
g
,
h
e
is
in
v
o
lv
e
d
in
c
u
rricu
lu
m
d
e
v
e
lo
p
m
e
n
t
a
n
d
c
a
p
a
c
it
y
-
b
u
il
d
i
n
g
w
o
rk
sh
o
p
s
in
P
y
th
o
n
p
r
o
g
ra
m
m
in
g
,
d
a
ta
v
isu
a
li
z
a
ti
o
n
,
a
n
d
a
u
t
o
m
a
ted
d
a
ta
sc
ien
c
e
to
o
ls.
His
c
u
rre
n
t
re
se
a
rc
h
re
f
le
c
ts
a
c
o
m
m
it
m
e
n
t
to
u
si
n
g
d
a
ta
-
d
riv
e
n
m
e
th
o
d
s
t
o
a
d
d
re
ss
c
o
m
p
lex
,
re
a
l
-
w
o
rld
p
ro
b
lem
s.
He
h
a
s
m
e
n
to
re
d
n
u
m
e
ro
u
s
u
n
d
e
rg
ra
d
u
a
te
re
se
a
rc
h
p
r
o
jec
ts
a
n
d
p
a
rti
c
ip
a
ted
i
n
u
n
iv
e
rsity
-
f
u
n
d
e
d
stu
d
ies
e
x
p
l
o
rin
g
th
e
tran
sf
o
r
m
a
ti
v
e
ro
le
o
f
tec
h
n
o
lo
g
y
in
p
u
b
li
c
a
n
d
a
c
a
d
e
m
ic
se
c
to
rs.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
c
a
ted
ril
la.g
e
n
e
m
a
rc
k
@lsp
u
.
e
d
u
.
p
h
.
Dr
.
J
o
e
y
Av
il
e
s
is
a
se
a
so
n
e
d
a
c
a
d
e
m
ic
a
n
d
IT
e
d
u
c
a
ti
o
n
lea
d
e
r,
c
u
rre
n
tl
y
se
rv
in
g
a
s
F
a
c
u
lt
y
M
e
m
b
e
r
a
n
d
S
e
rv
ice
Un
it
Co
o
r
d
i
n
a
to
r
a
t
t
h
e
Co
ll
e
g
e
o
f
Co
m
p
u
ter
S
tu
d
ies
,
a
n
d
P
ro
g
ra
m
Ch
a
ir
f
o
r
IT
Ed
u
c
a
ti
o
n
P
r
o
g
ra
m
s
a
t
th
e
G
ra
d
u
a
te
S
c
h
o
o
l
o
f
A
n
g
e
les
Un
iv
e
rsit
y
F
o
u
n
d
a
ti
o
n
(A
UF).
He
a
lso
lea
d
s
A
UF’s
A
I
In
teg
ra
ti
o
n
F
ra
m
e
w
o
rk
,
d
riv
in
g
in
sti
tu
ti
o
n
a
l
in
n
o
v
a
ti
o
n
in
tea
c
h
in
g
,
o
p
e
ra
ti
o
n
s,
a
n
d
re
se
a
rc
h
.
He
h
a
s
h
e
ld
tea
c
h
in
g
a
n
d
lea
d
e
rsh
ip
ro
les
a
t
P
a
n
p
a
c
if
ic
Un
iv
e
rsit
y
a
n
d
A
l
F
a
ra
b
i
Co
ll
e
g
e
s
in
S
a
u
d
i
A
ra
b
ia.
He
is
a
m
e
m
b
e
r
o
f
th
e
P
h
il
i
p
p
i
n
e
S
o
c
iety
o
f
I
T
Ed
u
c
a
to
rs
(P
S
IT
E),
th
e
C
o
u
n
c
il
o
f
IT
Ed
u
c
a
ti
o
n
De
a
n
s
a
n
d
He
a
d
s,
a
n
d
a
f
o
rm
e
r
Re
g
io
n
a
l
Qu
a
li
ty
A
s
se
ss
m
e
n
t
T
e
a
m
(RQ
AT
)
e
v
a
l
u
a
to
r.
A
n
a
c
ti
v
e
re
se
a
rc
h
e
r,
Dr.
A
v
il
e
s
h
a
s
p
re
se
n
ted
a
n
d
p
u
b
li
sh
e
d
in
IEE
E
,
A
CM
,
a
n
d
S
c
o
p
u
s
-
in
d
e
x
e
d
v
e
n
u
e
s,
f
o
c
u
sin
g
o
n
A
I,
d
ig
it
a
l
tran
sf
o
r
m
a
ti
o
n
,
a
n
d
IT
in
e
d
u
c
a
ti
o
n
.
He
a
lso
h
o
l
d
s
c
e
rti
f
ica
ti
o
n
s
f
ro
m
M
icro
so
f
t
a
n
d
A
d
o
b
e
,
f
u
rth
e
r
e
n
ric
h
in
g
h
is
b
len
d
o
f
p
ra
c
ti
c
a
l
a
n
d
a
c
a
d
e
m
ic
e
x
p
e
rti
se
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
v
il
e
s.jo
e
y
@a
u
f
.
e
d
u
.
p
h
.
Evaluation Warning : The document was created with Spire.PDF for Python.