I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
3
7
,
No
.
3
,
Ma
r
ch
20
2
5
,
p
p
.
1
89
9
~
1
90
7
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
7
.
i
3
.
pp
1
89
9
-
1
90
7
1899
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Va
lue gro
up clas
s
ifier
mo
del
f
o
r e
t
hica
l decisio
n
-
ma
king
Sh
wet
a
B
ha
t
na
g
a
r
,
Ra
s
hm
i A
g
ra
wa
l
S
c
h
o
o
l
o
f
C
o
m
p
u
t
e
r
A
p
p
l
i
c
a
t
i
o
n
s,
D
e
p
a
r
t
m
e
n
t
o
f
C
o
m
p
u
t
e
r
A
p
p
l
i
c
a
t
i
o
n
s,
M
a
n
a
v
R
a
c
h
n
a
I
n
t
e
r
n
a
t
i
o
n
a
l
I
n
st
i
t
u
t
e
o
f
R
e
se
a
r
c
h
S
t
u
d
i
e
s
,
F
a
r
i
d
a
b
a
d
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
May
27
,
2
0
2
4
R
ev
is
ed
Sep
28
,
2
0
2
4
Acc
ep
ted
Oct
7
,
2
0
2
4
De
c
isio
n
-
m
a
k
e
rs
re
fe
r
to
e
th
ics
o
r
m
o
ra
l
p
h
il
o
s
o
p
h
y
d
u
ri
n
g
ti
m
e
s
o
f
e
th
ica
l
d
il
e
m
m
a
.
Dilem
m
a
s
a
re
situ
a
ti
o
n
s
o
f
i
n
n
e
r
c
o
n
fl
ict,
w
h
ich
re
q
u
ire
a
m
e
th
o
d
ica
l
a
p
p
ro
a
c
h
.
Div
e
rsit
y
in
v
iew
p
o
i
n
ts
o
n
m
o
ra
l
d
e
c
isio
n
s
e
n
su
re
s
th
e
re
c
a
n
n
o
t
b
e
a
fix
e
d
so
l
u
ti
o
n
fo
r
e
th
ica
l
d
il
e
m
m
a
s
a
s
in
th
e
c
a
s
e
o
f
n
u
m
e
rica
l
p
ro
b
lem
s.
Ex
isti
n
g
e
t
h
ica
l
a
n
d
su
sta
in
a
b
le
d
e
c
isio
n
m
o
d
e
ls
fo
r
b
u
sin
e
ss
e
s
a
re
n
o
t
a
u
to
m
a
ted
b
e
c
a
u
se
o
f
a
lac
k
o
f
a
c
o
m
p
re
h
e
n
s
iv
e
li
st
o
f
d
il
e
m
m
a
s.
To
re
so
lv
e
th
is
g
a
p
,
a
n
AI
m
o
d
e
l
wa
s
train
e
d
to
c
las
sify
a
ll
d
il
e
m
m
a
s
in
to
t
h
re
e
v
a
l
u
e
g
ro
u
p
s
b
y
u
sin
g
a
su
p
p
o
rt
v
e
c
to
r
c
la
ss
ifi
e
r
(S
VC).
Th
e
m
o
d
e
l
p
ro
v
id
e
d
sc
a
ffo
l
d
in
g
t
o
t
h
e
e
t
h
ica
l
d
e
c
isio
n
-
m
a
k
e
r
b
y
s
u
g
g
e
sti
n
g
re
lev
a
n
t
h
u
m
a
n
v
a
l
u
e
s
a
p
p
li
c
a
b
le
to
t
h
e
d
il
e
m
m
a
.
Th
e
d
e
si
g
n
wo
r
k
s
o
n
th
e
e
th
ica
l
th
e
o
r
y
o
f
sta
k
e
h
o
ld
e
r
m
a
n
a
g
e
m
e
n
t,
wh
ich
i
n
c
lu
d
e
s
su
sta
in
a
b
le
b
u
sin
e
ss
g
o
a
ls.
Th
e
st
u
d
y
wa
s
c
o
n
d
u
c
ted
with
3
0
st
u
d
e
n
ts
a
n
d
3
0
a
d
u
lt
s
t
o
id
e
n
ti
f
y
t
h
e
ir
d
il
e
m
m
a
s.
Th
e
d
il
e
m
m
a
d
a
tas
e
t
w
a
s
u
se
d
to
trai
n
a
n
e
th
ica
l
d
e
c
isio
n
-
su
p
p
o
rt
t
o
o
l
,
c
a
ll
e
d
t
h
e
v
a
lu
e
g
r
o
u
p
c
las
sifica
ti
o
n
(VG
C)
m
o
d
e
l.
Th
e
m
o
d
e
l
a
c
h
iev
e
d
a
sc
o
re
o
f
0
.
5
2
o
n
p
e
rfo
rm
a
n
c
e
.
T
h
e
VG
C
m
o
d
e
l
o
v
e
rc
o
m
e
s
th
e
b
lac
k
-
b
o
x
b
ias
e
s
o
f
sim
il
a
r
m
a
c
h
in
e
-
lea
rn
in
g
m
o
d
e
ls
b
y
a
ll
o
win
g
h
u
m
a
n
a
u
t
o
n
o
m
y
i
n
e
th
i
c
a
l
d
e
c
isio
n
s.
K
ey
w
o
r
d
s
:
Ar
tific
ial
in
tellig
en
ce
E
th
ical
d
ec
is
io
n
-
m
ak
in
g
Mo
r
al
d
ec
is
io
n
s
Sen
tim
en
t a
n
aly
s
is
Su
p
p
o
r
t
v
ec
to
r
class
if
ier
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
:
Sh
weta
B
h
atn
ag
ar
Sch
o
o
l o
f
C
o
m
p
u
ter
Ap
p
licatio
n
s
,
Dep
ar
tm
en
t
o
f
C
o
m
p
u
ter
Ap
p
licatio
n
s
,
Ma
n
av
R
ac
h
n
a
I
n
ter
n
atio
n
al
I
n
s
titu
te
o
f
R
esear
ch
Stu
d
ies,
Far
id
ab
ad
,
I
n
d
ia
E
m
ail: sh
weta
b
h
atn
ag
ar
9
9
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
E
v
er
y
r
elig
io
n
h
as
th
e
f
o
llo
win
g
co
m
p
o
n
en
ts
(
1
)
m
etap
h
y
s
ics
an
d
co
n
ce
p
t
o
f
Go
d
,
(
2
)
way
s
to
s
alv
atio
n
o
r
lib
er
atio
n
,
(
3
)
m
y
th
o
lo
g
y
,
(
4
)
cu
s
to
m
s
an
d
r
itu
a
ls
,
an
d
(
5
)
b
asic
eth
ics.
T
h
e
e
n
d
o
b
jectiv
e
o
f
all
r
elig
io
n
s
is
o
n
e,
th
e
r
ea
lizati
o
n
o
f
Go
d
.
Alth
o
u
g
h
t
h
e
wa
y
s
,
m
y
th
o
lo
g
y
,
an
d
cu
s
to
m
s
(
m
id
d
le
th
r
ee
m
ai
n
co
m
p
o
n
en
ts
)
o
f
r
elig
i
o
n
s
d
if
f
er
in
th
eir
p
r
ac
tices,
all
r
elig
i
o
n
s
ag
r
ee
o
n
b
asic
et
h
ical
p
r
in
cip
les
lik
e
tr
u
th
,
co
m
p
ass
io
n
,
an
d
s
elf
-
c
o
n
tr
o
l.
E
th
ics
ar
e
in
d
ep
en
d
en
t
o
f
r
elig
io
n
,
b
u
t
all
r
elig
i
o
n
s
m
en
tio
n
e
th
ics
in
th
eir
teac
h
in
g
s
.
No
r
m
ativ
e
eth
ics
is
th
e
s
tu
d
y
o
f
et
h
ical
b
eh
a
v
io
r
a
n
d
is
al
s
o
k
n
o
wn
as
m
o
r
al
p
h
ilo
s
o
p
h
y
.
I
t
is
a
co
llectio
n
o
f
m
u
ltip
le
th
e
o
r
ies,
wh
ich
p
r
o
v
i
d
e
a
f
o
u
n
d
atio
n
f
o
r
m
o
r
al
d
ec
is
io
n
s
.
T
h
ese
ar
e
th
e
d
eo
n
to
lo
g
ical,
co
n
s
eq
u
en
tialis
t,
an
d
v
ir
tu
e
th
eo
r
ies.
Deo
n
to
lo
g
ical
eth
ics
ev
alu
ates
m
o
r
ality
b
ase
d
o
n
ac
tio
n
,
wh
ile
co
n
s
eq
u
en
tialis
t
th
eo
r
y
ev
al
u
ates
m
o
r
ality
b
ased
o
n
th
e
co
n
s
eq
u
en
ce
o
f
th
e
ac
tio
n
.
T
h
e
v
ir
t
u
e
th
e
o
r
y
,
h
o
wev
er
,
u
s
es
th
e
in
ten
t
o
f
th
e
ac
tio
n
as
its
b
asis
o
f
ev
al
u
atio
n
f
o
r
m
o
r
al
ity
.
E
th
ics
en
s
u
r
e
th
at
in
d
iv
id
u
al
ac
tio
n
s
d
o
n
o
t a
d
v
e
r
s
ely
d
eter
m
in
e
th
e
f
u
t
u
r
e
o
f
in
d
iv
i
d
u
als
as we
ll a
s
th
at
o
f
s
o
ciety
[
1
]
.
T
h
e
th
r
ee
m
ain
ar
ea
s
o
f
n
o
r
m
ativ
e
eth
ics
ar
e
m
eta
-
eth
ics
,
ap
p
lied
eth
ics,
an
d
d
escr
ip
t
iv
e
eth
ics.
Me
ta
-
eth
ics
lo
o
k
s
at
th
e
n
at
u
r
e
o
f
m
o
r
al
lan
g
u
ag
e
an
d
wh
at
k
in
d
s
o
f
th
in
g
s
ca
n
b
e
ca
ll
ed
‘
g
o
o
d
’
o
r
‘
b
ad
’
.
Ap
p
lied
eth
ics
lo
o
k
s
at
eth
ic
al
is
s
u
es
th
at
ar
is
e
in
p
ar
ticu
l
ar
p
r
o
f
ess
io
n
s
,
s
u
ch
as
m
e
d
ic
in
e
o
r
en
g
in
ee
r
in
g
.
Descr
ip
tiv
e
eth
ics
i
s
a
b
r
an
ch
o
f
em
p
ir
ical
s
o
cio
lo
g
y
th
at
s
tu
d
ies
p
eo
p
le’
s
o
p
in
io
n
s
ab
o
u
t
wh
at
th
ey
th
in
k
t
o
b
e
m
o
r
ally
g
o
o
d
o
r
b
ad
b
eh
a
v
io
r
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
3
,
Ma
r
ch
20
2
5
:
1
89
9
-
1
90
7
1900
Valu
e
ed
u
ca
tio
n
im
p
lies
teac
h
in
g
eth
ical
m
o
tiv
es,
m
ea
n
s
,
an
d
co
n
s
eq
u
en
ce
s
.
Usu
ally
,
a
d
ilem
m
a
ar
is
es
at
th
e
tim
e
o
f
ch
o
o
s
in
g
th
e
m
ea
n
s
f
o
r
ac
h
iev
in
g
th
e
m
o
tiv
es.
T
h
ese
m
ea
n
s
an
d
m
o
tiv
es
ar
e
s
u
b
ject
to
ev
alu
atio
n
b
y
m
o
r
al
p
r
in
cip
le
s
/v
alu
es
b
ef
o
r
e
b
ein
g
c
o
n
s
id
er
ed
eth
ical.
E
th
ics
is
an
in
v
esti
g
atio
n
o
f
d
ilem
m
as
to
en
s
u
r
e
u
n
iv
e
r
s
al
an
d
lo
n
g
-
t
er
m
g
o
o
d
,
wh
ich
r
esu
lts
in
a
p
r
o
b
a
b
ilis
tic
cu
r
v
e
r
ep
r
esen
tin
g
s
o
lu
tio
n
s
.
E
th
ical
d
ec
is
io
n
s
ar
e
s
ee
n
as
a
tr
ad
e
-
o
f
f
b
etwe
en
d
if
f
er
en
t
m
o
r
a
l
p
r
in
cip
les/
v
alu
es,
r
ep
r
esen
ted
in
th
e
f
o
r
m
o
f
in
d
if
f
er
en
ce
cu
r
v
es.
T
h
e
tr
ad
e
-
o
f
f
o
r
ch
o
ice
o
f
s
o
lu
ti
o
n
d
e
p
en
d
s
o
n
th
e
r
elev
an
ce
an
d
i
n
teg
r
ity
o
f
th
e
m
o
r
al
q
u
esti
o
n
at
h
an
d
[
2
]
.
R
elig
io
n
an
d
et
h
ics
d
r
aw
u
s
clo
s
er
to
h
ar
m
o
n
y
.
T
h
e
n
at
u
r
e
o
f
h
ar
m
o
n
y
is
in
clu
s
iv
ity
,
em
p
ath
y
,
s
y
m
p
h
o
n
y
,
c
o
n
tin
u
ity
,
s
elf
-
d
is
cip
lin
e,
an
d
m
o
r
e
.
T
h
e
r
ef
o
r
e,
b
ef
o
r
e
m
ak
in
g
eth
ical
d
ec
is
io
n
s
it
is
im
p
o
r
tan
t
t
o
lo
o
k
at
th
e
d
ilem
m
a
f
r
o
m
a
m
eta
-
eth
ical
p
er
s
p
ec
tiv
e
a
n
d
id
en
tif
y
th
e
s
tak
eh
o
l
d
er
s
a
f
f
ec
ted
.
I
d
en
tif
y
in
g
s
tak
eh
o
ld
er
s
o
f
th
e
f
u
tu
r
e
is
n
o
t
p
o
s
s
ib
le
in
t
h
e
p
r
esen
t.
T
h
er
ef
o
r
e,
a
u
n
iv
er
s
al
a
p
p
r
o
ac
h
o
f
d
iv
id
in
g
all
p
r
esen
t
an
d
f
u
tu
r
e
s
tak
eh
o
ld
er
s
in
to
th
r
ee
b
r
o
ad
ca
teg
o
r
ies
b
ased
o
n
p
r
esen
t
-
d
ay
u
n
d
er
s
tan
d
in
g
th
r
o
u
g
h
laws
o
f
p
h
y
s
ics
is
ad
o
p
ted
.
T
h
e
s
tak
eh
o
ld
er
s
ar
e
g
r
o
u
p
ed
in
to
th
r
ee
ca
teg
o
r
ies n
o
n
-
s
en
tien
t
b
ei
n
g
s
,
s
en
tien
t b
ein
g
s
,
an
d
ab
s
tr
ac
t
s
itu
atio
n
s
.
T
h
ese
ca
teg
o
r
ies
en
s
u
r
e
p
r
o
tectio
n
o
f
en
v
ir
o
n
m
en
tal
r
eso
u
r
ce
s
an
d
h
u
m
an
s
f
r
o
m
ex
p
lo
itatio
n
,
a
n
d
s
o
cial
h
ar
m
o
n
y
.
T
o
ass
is
t
th
e
eth
ical
d
ec
is
io
n
-
m
ak
in
g
p
r
o
ce
s
s
,
f
ee
d
b
ac
k
b
y
m
ac
h
in
es
in
th
e
f
o
r
m
o
f
r
elev
an
t
h
u
m
a
n
v
alu
es
ap
p
licab
le
f
o
r
ea
ch
s
tak
eh
o
ld
er
g
r
o
u
p
,
as
ass
o
ciate
d
with
th
e
d
ilem
m
a
,
is
p
r
o
v
id
ed
.
I
t
h
elp
s
th
e
d
ec
is
io
n
-
m
ak
er
d
ef
i
n
e
th
e
s
co
p
e
o
f
th
e
p
r
o
b
lem
an
d
d
r
aw
r
elev
an
t
in
d
if
f
e
r
en
ce
cu
r
v
es
b
etwe
en
im
p
o
r
tan
t
v
alu
es.
An
eth
ical
d
ec
is
io
n
-
m
ak
in
g
m
ac
h
in
e
lear
n
in
g
m
o
d
el,
ca
lled
th
e
v
alu
e
g
r
o
u
p
c
lass
if
icatio
n
(
VGC)
m
o
d
el,
is
d
ev
elo
p
ed
to
p
r
o
v
i
d
e
a
s
et
o
f
r
ef
er
en
ce
m
o
r
al
v
al
u
es
f
o
r
th
e
d
ilem
m
a
,
b
ased
o
n
its
clas
s
if
icatio
n
in
o
n
e
o
f
th
e
th
r
ee
v
alu
e
g
r
o
u
p
s
.
T
h
e
m
o
d
el
is
tr
ain
ed
u
s
in
g
a
s
u
p
p
o
r
t
v
ec
to
r
class
if
ier
(
SVC
)
.
T
h
e
m
o
d
el
en
s
u
r
es h
u
m
an
au
to
n
o
m
y
i
n
d
ec
is
io
n
-
m
ak
in
g
,
wh
ile
u
s
in
g
m
ac
h
in
e
lear
n
in
g
to
s
u
p
p
o
r
t
d
ec
is
io
n
an
aly
s
is
.
T
h
is
p
ap
er
is
d
iv
id
e
d
in
to
f
o
u
r
s
ec
tio
n
s
.
Af
ter
th
e
in
t
r
o
d
u
ctio
n
,
s
ec
tio
n
two
p
e
r
f
o
r
m
s
a
lit
er
atu
r
e
r
ev
iew
o
f
ex
is
tin
g
eth
ical
d
ec
is
io
n
m
o
d
els.
Sectio
n
th
r
ee
ex
p
lain
s
th
e
m
eth
o
d
o
lo
g
y
u
s
ed
in
th
is
r
esear
ch
to
f
in
d
th
e
s
o
lu
tio
n
t
o
th
ese
g
a
p
s
.
Sectio
n
f
o
u
r
d
is
cu
s
s
es
th
e
r
es
u
lts
an
d
f
in
d
in
g
s
an
d
s
ec
tio
n
f
iv
e
co
n
clu
d
es
with
th
e
f
u
tu
r
e
s
co
p
e
o
f
wo
r
k
.
2.
E
T
H
I
CAL D
E
C
I
SI
O
N
M
O
DE
L
S
E
x
is
tin
g
eth
ical
d
ec
is
io
n
-
m
a
k
in
g
f
r
am
ewo
r
k
s
ar
e
d
ev
elo
p
ed
f
o
r
r
eso
lv
in
g
eth
ical
d
il
em
m
as.
An
eth
ical
d
ilem
m
a
im
p
lies
a
s
itu
atio
n
wh
en
th
e
d
ec
is
io
n
-
m
ak
e
r
ca
n
n
o
t
id
e
n
tify
th
e
m
o
s
t
a
p
p
r
o
p
r
iate
r
esp
o
n
s
e
in
a
s
itu
atio
n
b
ec
au
s
e
o
f
co
n
f
li
ctin
g
in
ter
ests
o
r
p
r
in
cip
les
d
u
e
to
a
lack
o
f
u
n
clea
r
s
tan
d
ar
d
s
o
r
p
r
ac
tices
p
r
escr
ib
ed
f
o
r
th
e
s
itu
atio
n
a
r
is
in
g
d
u
e
to
its
n
o
v
elty
o
r
c
o
m
p
lex
ity
.
T
h
ese
co
u
ld
ar
is
e
d
u
e
to
co
n
f
lict
in
th
e
in
ter
ests
o
f
s
tak
eh
o
ld
e
r
s
,
co
n
f
lict
b
etwe
en
a
p
p
licab
le
s
tan
d
ar
d
s
i
n
d
if
f
e
r
en
t
p
lace
s
o
r
f
o
r
d
i
f
f
er
en
t
r
o
les,
a
tr
ad
e
-
o
f
f
b
etwe
en
p
r
in
cip
les a
n
d
v
alu
es,
o
r
d
u
e
to
d
i
f
f
er
en
ce
s
in
p
r
o
m
in
e
n
t so
cial
p
r
ac
tices.
E
th
ical
d
ec
is
io
n
-
m
ak
in
g
m
o
d
els
wer
e
s
tu
d
ied
an
d
co
m
p
ar
ed
to
f
in
d
c
o
m
m
o
n
g
ap
s
,
as
g
iv
en
i
n
T
ab
le
1
.
T
h
e
ex
is
tin
g
m
o
d
els
wo
r
k
o
n
in
ter
n
al
o
r
ex
ter
n
al
d
ata
b
u
t
d
o
n
o
t
h
a
v
e
a
n
y
f
ee
d
b
ac
k
m
ec
h
an
is
m
f
o
r
th
e
d
ec
is
io
n
-
m
ak
e
r
.
T
h
e
co
m
p
ar
is
o
n
s
h
o
ws
th
at
th
e
m
o
d
e
ls
wo
r
k
o
n
p
r
o
ce
s
s
es,
b
u
t
d
o
n
o
t
lead
to
s
elf
-
tr
an
s
f
o
r
m
atio
n
,
T
r
an
s
f
o
r
m
atio
n
is
th
e
p
o
s
itiv
e
ch
an
g
e
f
r
o
m
p
ast
p
r
ac
tices
ca
u
s
ed
b
y
co
g
n
itiv
e
an
d
af
f
ec
tiv
e
s
tim
u
latio
n
.
Self
-
tr
an
s
f
o
r
m
ati
o
n
ca
n
b
e
tr
ig
g
e
r
ed
th
r
o
u
g
h
a
f
ee
d
b
ac
k
o
r
r
esp
o
n
s
e
m
ec
h
an
is
m
,
u
s
in
g
a
m
ac
h
in
e
lear
n
in
g
m
o
d
el
o
r
t
h
e
co
m
p
u
tatio
n
al
t
o
o
l.
T
h
e
f
ee
d
b
ac
k
i
n
th
e
f
o
r
m
o
f
r
ec
o
m
m
en
d
ed
v
alu
es
f
o
r
d
ec
is
io
n
-
m
ak
in
g
s
u
p
p
o
r
ts
th
e
d
ec
is
io
n
-
m
ak
er
i
n
r
ea
l
-
tim
e.
T
h
ese
eth
ical
d
ec
is
io
n
-
m
ak
in
g
m
o
d
els
lack
f
ee
d
b
ac
k
d
u
e
t
o
th
e
u
n
av
ailab
ilit
y
o
f
an
e
x
h
au
s
tiv
e
lis
t
o
f
d
ilem
m
as
with
t
h
eir
m
o
r
al
eq
u
iv
alen
ce
(
s
o
lu
tio
n
to
d
ilem
m
a)
to
g
en
er
ate
s
u
ch
f
ee
d
b
ac
k
.
I
n
a
r
esear
c
h
co
n
d
u
cte
d
to
class
if
y
s
ta
tem
en
ts
as
m
o
r
al
o
r
im
m
o
r
al,
an
E
T
HI
C
S
d
ataset
m
o
d
el
was
b
u
i
lt
b
ased
o
n
all
th
r
ee
th
eo
r
ies
o
f
n
o
r
m
ativ
e
eth
ics,
a
n
d
th
e
m
ac
h
in
e
was
tr
ain
e
d
to
class
if
y
th
e
s
tatem
en
ts
as
m
o
r
al
o
r
im
m
o
r
al
[
3
]
.
T
h
e
r
esu
lts
o
f
th
is
class
if
icatio
n
p
r
o
b
lem
s
h
o
we
d
an
ac
c
u
r
ac
y
o
f
less
th
an
7
5
%
with
t
h
e
lar
g
est
tr
ain
in
g
m
o
d
el
o
f
AL
B
E
R
T
A
-
x
x
lar
g
e.
T
h
e
m
o
d
el
s
h
o
wed
s
en
s
itiv
ity
o
f
t
h
e
tr
ain
ed
m
o
d
el
to
war
d
s
f
r
am
in
g
an
d
em
o
tio
n
al
co
n
ju
g
atio
n
in
m
o
r
al
s
tatem
en
ts
,
im
p
ly
in
g
a
n
ee
d
f
o
r
g
r
ea
ter
t
r
an
s
p
ar
en
c
y
o
n
tr
ain
in
g
m
o
d
els
u
s
ed
an
d
th
eir
b
iases
.
T
h
e
s
tu
d
y
s
h
o
wed
th
at
eth
ical
d
ec
is
io
n
m
o
d
els
ar
e
b
iased
d
u
e
to
m
ac
h
in
e
m
o
d
el
b
iases
o
r
d
iv
er
s
ity
in
th
e
s
tatu
s
o
f
n
o
r
m
ativ
e
eth
ics.
T
h
er
e
ar
e
d
i
v
er
s
e
m
eta
-
eth
ic
al
v
iews
(
v
iewp
o
in
ts
ab
o
u
t
t
h
e
n
atu
r
e,
s
co
p
e,
an
d
m
ea
n
in
g
o
f
m
o
r
al
d
ec
is
io
n
s
)
o
n
wh
at
m
o
r
als
ar
e.
T
h
ese
v
iewp
o
in
ts
ar
e
f
r
o
m
o
b
jectiv
is
ts
,
s
u
b
jectiv
is
ts
,
r
ea
lis
ts
,
co
g
n
itiv
is
ts
,
em
o
tiv
is
ts
,
an
d
e
r
r
o
r
th
e
o
r
is
ts
.
Alm
o
s
t
all
o
f
th
ese
d
iv
er
s
e
v
iewp
o
in
ts
h
o
ld
th
at
m
o
r
al
s
tatem
en
ts
ex
p
r
ess
p
r
o
p
o
s
itio
n
s
th
at
co
u
ld
b
e
tr
u
e
o
r
f
alse.
E
ac
h
o
f
th
ese
p
r
o
p
o
s
itio
n
s
r
elate
s
to
o
n
e
o
r
m
o
r
e
m
o
r
al
p
r
in
cip
les
[
4
]
.
T
h
er
ef
o
r
e,
id
en
tify
in
g
r
elev
an
t
v
alu
es
ca
n
f
ac
ilit
ate
d
ef
in
in
g
th
e
s
co
p
e
o
f
th
e
p
r
o
b
lem
,
w
h
ich
is
th
e
f
ir
s
t
s
tep
to
war
d
s
f
in
d
in
g
th
e
s
o
lu
tio
n
.
A
r
ea
s
o
n
ab
le
s
co
p
e
o
f
th
e
p
r
o
b
lem
s
h
o
u
l
d
in
v
o
lv
e
all
s
tak
eh
o
ld
er
s
,
af
f
ec
ted
p
ar
ties
,
an
d
en
v
ir
o
n
m
en
tal
co
n
ce
r
n
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
V
a
lu
e
g
r
o
u
p
cla
s
s
ifier
mo
d
el
fo
r
eth
ica
l d
ec
is
io
n
-
ma
kin
g
(
S
h
w
eta
B
h
a
tn
a
g
a
r
)
1901
T
ab
le
1
.
Su
m
m
a
r
y
o
f
eth
ical
d
ec
is
io
n
-
m
ak
in
g
m
o
d
els
Et
h
i
c
a
l
d
e
c
i
si
o
n
-
m
a
k
i
n
g
m
o
d
e
l
s
D
e
c
i
s
i
o
n
p
r
o
c
e
ss
Emp
h
a
s
i
s
o
f
t
h
e
M
o
d
e
l
F
o
c
u
s
I
n
t
e
g
r
a
t
i
v
e
d
e
c
i
si
o
n
-
mak
i
n
g
m
o
d
e
l
o
f
e
t
h
i
c
a
l
b
e
h
a
v
i
o
r
[
5
]
I
n
t
e
r
p
r
e
t
si
t
u
a
t
i
o
n
t
o
i
d
e
n
t
i
f
y
d
i
l
e
mm
a
.
D
e
t
e
r
m
i
n
e
st
a
n
d
a
r
d
s
t
h
a
t
a
p
p
l
y
t
o
d
i
l
e
mm
a
a
n
d
i
d
e
n
t
i
f
y
p
o
ss
i
b
l
e
a
n
d
p
r
o
b
a
b
l
e
c
o
u
r
ses
o
f
a
c
t
i
o
n
.
A
f
t
e
r
c
o
n
s
i
d
e
r
i
n
g
t
h
e
c
o
n
s
e
q
u
e
n
c
e
s f
o
r
e
a
c
h
c
o
u
r
se
o
f
a
c
t
i
o
n
,
s
e
l
e
c
t
a
n
a
c
t
i
o
n
b
y
w
e
i
g
h
i
n
g
c
o
m
p
e
t
i
n
g
v
a
l
u
e
s,
i
n
g
i
v
e
n
c
o
n
t
e
x
t
.
W
o
r
k
s
o
n
e
x
t
e
r
n
a
l
st
a
n
d
a
r
d
s
a
n
d
t
h
e
i
r
c
o
n
se
q
u
e
n
c
e
s
i
n
t
h
e
g
i
v
e
n
c
o
n
t
e
x
t
F
o
c
u
ses
o
n
e
x
t
e
r
n
a
l
d
a
t
a
G
o
l
d
e
n
c
i
r
c
l
e
f
r
a
mew
o
r
k
[
6
]
A
n
sw
e
r
t
h
e
w
h
y
,
h
o
w
,
a
n
d
w
h
a
t
i
n
t
h
e
seq
u
e
n
c
e
W
o
r
k
s
o
n
s
e
l
f
-
f
i
r
st
a
n
d
t
h
e
n
e
x
t
e
r
n
a
l
i
n
f
o
r
mat
i
o
n
F
o
c
u
ses
o
n
sel
f
ETH
I
C
S
m
o
d
e
l
[
7
]
Ev
a
l
u
a
t
e
t
h
e
d
i
l
e
mm
a
,
t
h
i
n
k
a
h
e
a
d
,
se
e
k
h
e
l
p
f
r
o
m c
o
n
su
l
t
a
n
t
s a
n
d
e
x
p
e
r
t
s,
c
o
n
s
i
d
e
r
a
v
a
i
l
a
b
l
e
i
n
f
o
r
m
a
t
i
o
n
,
c
a
l
c
u
l
a
t
e
r
i
s
k
,
S
e
l
e
c
t
a
n
d
a
c
t
i
o
n
W
o
r
k
s
o
n
S
e
l
f
f
i
r
s
t
b
u
t
p
u
t
s
a
l
o
t
o
f
e
mp
h
a
s
i
s
o
n
c
o
l
l
e
c
t
i
n
g
c
o
r
r
e
c
t
e
x
t
e
r
n
a
l
i
n
f
o
r
mat
i
o
n
F
o
c
u
ses
o
n
e
x
t
e
r
n
a
l
d
a
t
a
Et
h
i
c
a
l
f
r
a
mew
o
r
k
f
o
r
i
n
d
u
s
t
r
i
a
l
U
se
[
8
]
R
e
c
o
g
n
i
z
e
t
h
e
e
t
h
i
c
a
l
i
ss
u
e
,
g
a
t
h
e
r
i
n
f
o
r
mat
i
o
n
,
i
d
e
n
t
i
f
y
p
r
o
x
i
m
a
l
a
n
d
d
i
s
t
a
n
t
st
a
k
e
h
o
l
d
e
r
s,
i
d
e
n
t
i
f
y
a
l
t
e
r
n
a
t
i
v
e
a
c
t
i
o
n
s,
c
o
m
p
a
r
e
a
l
t
e
r
n
a
t
i
v
e
a
c
t
i
o
n
s,
i
m
p
l
e
me
n
t
a
c
t
i
o
n
,
a
n
d
m
o
n
i
t
o
r
o
u
t
c
o
m
e
s
I
t
i
s b
a
se
d
o
n
t
h
e
A
meri
c
a
n
P
s
y
c
h
o
l
o
g
i
c
a
l
A
sso
c
i
a
t
i
o
n
(
A
P
A
)
Et
h
i
c
a
l
P
r
i
n
c
i
p
l
e
s
o
f
P
sy
c
h
o
l
o
g
i
st
s
a
n
d
C
o
d
e
o
f
C
o
n
d
u
c
t
.
Th
e
sel
f
-
d
i
sc
o
v
e
r
y
j
o
u
r
n
e
y
i
s m
i
ssi
n
g
s
i
n
c
e
t
h
e
r
e
f
e
r
e
n
c
e
t
o
A
P
A
p
r
i
n
c
i
p
l
e
s
a
n
d
s
t
a
n
d
a
r
d
s
i
s
u
se
d
F
o
c
u
ses
o
n
e
x
t
e
r
n
a
l
d
a
t
a
3.
VALU
E
G
RO
UP
S
I
d
en
tify
in
g
th
e
r
elev
an
t v
al
u
e
g
r
o
u
p
f
o
r
th
e
d
ilem
m
a
at
h
an
d
r
eq
u
ir
es d
if
f
er
e
n
tiatio
n
b
etwe
en
s
u
b
ject
an
d
o
b
ject
in
th
e
d
ilem
m
a
s
tat
em
en
t.
T
h
e
ch
ar
ac
te
r
is
tics
o
f
th
e
s
u
b
ject
ar
e
its
p
r
esen
t
s
itu
atio
n
(
n
ee
d
wallet)
an
d
its
b
elief
s
y
s
tem
(
in
d
if
f
er
en
ce
cu
r
v
e
p
r
e
f
er
en
ce
p
o
in
ts
)
.
T
h
e
o
b
ject
is
th
e
r
eso
u
r
ce
,
r
elatio
n
s
h
ip
,
o
r
s
itu
atio
n
ca
u
s
in
g
th
e
co
n
f
lict
o
r
d
ilem
m
a.
T
h
e
n
ee
d
wallet
h
er
e
d
ef
in
es
th
e
p
e
r
s
o
n
’
s
p
er
c
eiv
ed
s
u
f
f
icien
cy
o
n
f
o
u
r
p
a
r
am
eter
s
;
p
h
y
s
io
lo
g
ic
al
n
ee
d
s
,
s
ec
u
r
ity
n
ee
d
s
,
s
o
cial
n
ee
d
s
,
an
d
s
elf
-
ac
tu
aliz
atio
n
n
ee
d
s
.
T
h
e
u
n
ce
r
tain
ty
o
f
th
e
d
esire
d
o
u
tc
o
m
e
(
p
r
o
b
ab
ilit
y
)
is
d
ef
in
ed
b
y
th
e
cu
r
v
e
b
etwe
en
s
u
b
ject’
s
ch
ar
ac
ter
is
tics
an
d
th
e
v
alu
e
g
r
o
u
p
p
r
e
d
ictio
n
s
.
I
d
en
tify
in
g
r
elev
an
t
h
u
m
an
v
alu
es/v
alu
e
g
r
o
u
p
s
/m
o
r
al
p
r
i
n
cip
les
p
r
o
v
id
es
s
ca
f
f
o
l
d
in
g
f
o
r
eth
ical
d
ec
is
io
n
-
m
ak
in
g
.
Mu
ltip
le
m
o
r
al
s
o
lu
tio
n
s
f
o
r
t
h
e
s
am
e
d
ilem
m
a,
as
s
h
o
w
n
in
Fig
u
r
e
1
,
a
r
e
ex
p
lain
e
d
u
s
in
g
th
e
in
d
if
f
er
e
n
ce
cu
r
v
es
co
n
ce
p
t
o
f
m
icr
o
ec
o
n
o
m
ics.
Fo
r
ex
am
p
le,
in
ca
s
e
o
f
d
ilem
m
as
a
b
o
u
t
r
elatio
n
s
h
i
p
s
,
h
u
m
an
v
alu
es
lik
e
f
o
r
g
iv
en
e
s
s
an
d
co
m
p
ass
io
n
ca
n
b
e
p
r
ac
ticed
in
v
ar
io
u
s
d
eg
r
ee
s
.
T
h
e
r
ig
h
t
tr
ad
e
-
o
f
f
b
etwe
en
th
e
two
v
al
u
es wo
u
ld
d
ep
en
d
o
n
t
h
e
co
n
d
itio
n
s
an
d
b
elief
s
o
f
th
e
d
ec
is
io
n
-
m
ak
er
.
T
h
e
in
d
if
f
er
en
ce
c
u
r
v
es
ar
e
f
a
ct
-
in
d
ep
en
d
en
t
an
d
h
el
p
th
e
d
ec
is
io
n
-
m
ak
er
b
alan
ce
th
e
r
ig
h
t
p
ac
k
ag
e
o
f
co
m
p
etin
g
o
r
s
u
p
p
lem
en
tin
g
p
r
in
cip
les.
I
f
th
e
r
ig
h
t
s
et
o
f
ap
p
licab
le
v
alu
es
is
id
en
tifie
d
,
th
en
th
e
d
ec
is
io
n
-
m
ak
er
ca
n
b
u
ild
a
s
u
itab
le
s
o
l
u
tio
n
f
o
r
th
e
d
ilem
m
a
b
ased
o
n
h
is
co
n
d
itio
n
s
an
d
b
elief
s
.
T
h
e
VGC
m
o
d
el
u
s
es
an
SV
C
to
class
if
y
th
e
d
ilem
m
a
s
tated
b
y
th
e
r
esp
o
n
d
e
n
t
in
to
th
r
ee
v
alu
e
o
r
s
tak
eh
o
ld
er
g
r
o
u
p
s
.
T
h
e
m
o
d
el
d
o
es
n
o
t
d
ec
lar
e
a
s
tatem
en
t
as
m
o
r
al
o
r
i
m
m
o
r
al
b
u
t
r
at
h
er
r
esp
o
n
d
s
with
a
r
elev
an
t
v
alu
e
g
r
o
u
p
to
h
elp
th
e
d
ec
is
io
n
m
ak
e
r
r
ec
o
n
s
id
er
th
e
d
ilem
m
a
i
n
th
e
m
o
r
al
c
o
n
tex
t
b
as
ed
o
n
its
p
er
s
o
n
alize
d
s
u
b
ject
c
h
ar
ac
te
r
is
tics
(
n
ee
d
s
wallet
an
d
b
eli
ef
s
y
s
tem
)
.
T
h
e
b
iases
in
th
e
p
r
ev
io
u
s
E
T
HI
C
S
d
ataset
m
o
d
el
ar
e
r
eso
lv
ed
i
n
th
e
VGC
m
o
d
el
b
y
im
p
le
m
e
n
tin
g
th
e
c
o
n
ce
p
t
o
f
tr
ad
eo
f
f
in
m
o
r
al
p
r
in
cip
les
u
s
in
g
in
d
if
f
e
r
en
ce
cu
r
v
es
[
9
]
,
wh
ich
r
em
o
v
es
th
e
r
ig
id
b
lack
-
b
o
x
in
te
r
p
r
etatio
n
s
an
d
allo
w
s
h
u
m
an
au
to
n
o
m
y
in
eth
ical
d
ec
is
io
n
-
m
ak
i
n
g
.
Stak
eh
o
ld
er
s
o
f
ea
ch
d
ilem
m
a
ar
e
g
r
o
u
p
ed
as
n
o
n
-
s
en
tien
t,
s
en
tien
t,
an
d
a
b
s
tr
ac
t;
wh
ile
k
ee
p
in
g
th
e
en
v
ir
o
n
m
en
tal
an
d
s
o
cial
co
n
ce
r
n
s
in
s
ig
h
t.
R
elev
an
t
v
alu
es
ar
e
d
er
iv
ed
f
r
o
m
m
eta
-
et
h
ics,
ap
p
lied
eth
ics
(
p
r
o
f
ess
io
n
al
s
tan
d
a
r
d
s
)
,
an
d
d
escr
ip
tiv
e
eth
ics
(
s
o
cial
a
n
d
cu
ltu
r
al
n
o
r
m
s
)
,
wh
ile
m
eta
-
et
h
ics
v
alu
es
ar
e
u
s
ed
in
th
e
tr
ain
i
n
g
s
et.
T
h
is
g
r
o
u
p
i
n
g
o
f
s
tak
eh
o
l
d
er
s
allo
ws
th
e
cr
ea
tio
n
o
f
awa
r
en
ess
an
d
willin
g
n
ess
to
in
clu
d
e
th
e
co
n
ce
r
n
s
o
f
s
tak
eh
o
ld
er
s
in
d
ec
is
io
n
-
m
ak
in
g
[
1
0
]
.
Fin
an
cial
an
d
en
v
ir
o
n
m
en
tal
s
u
s
tain
ab
ilit
y
o
f
b
u
s
in
ess
es
d
ep
en
d
s
o
n
th
e
b
u
s
in
ess
s
tr
ateg
y
an
d
d
e
cisi
o
n
s
.
T
h
ese
d
ec
is
io
n
s
ar
e
u
s
u
ally
d
ata
-
d
ep
en
d
e
n
t
[
1
1
]
.
Dec
is
io
n
to
o
ls
to
f
ac
ilit
ate
s
u
s
tain
ab
le
d
ec
is
io
n
s
f
o
s
ter
in
n
o
v
atio
n
in
s
u
s
tain
ab
le
s
o
lu
tio
n
s
[
1
2
]
.
T
h
e
VGC
to
o
l
p
r
o
v
id
es h
o
lis
tic
g
u
id
a
n
c
e
o
n
v
al
u
es a
n
d
p
r
in
cip
les ap
p
licab
le
to
th
e
b
u
s
in
ess
p
r
o
b
le
m
.
Acc
o
r
d
in
g
to
s
tak
eh
o
l
d
er
th
eo
r
y
[
1
3
]
,
th
e
v
ar
io
u
s
ac
to
r
s
in
th
e
f
ir
m
s
h
o
u
ld
b
e
in
ter
r
elate
d
,
to
en
s
u
r
e
th
e
o
u
tco
m
e
is
s
o
cially
an
d
ec
o
n
o
m
ically
d
esira
b
le.
I
n
g
en
er
al
s
tak
eh
o
l
d
e
r
m
an
ag
e
m
en
t
s
tr
ateg
ies,
th
e
s
tak
eh
o
ld
er
s
ar
e
r
a
n
k
ed
b
ased
o
n
th
eir
in
f
lu
e
n
ce
o
r
in
v
o
lv
e
m
en
t
with
t
h
e
d
ec
is
io
n
[
1
4
]
.
T
h
is
r
esear
ch
ta
k
es
a
d
iv
er
s
io
n
to
war
d
s
th
e
eth
ical
b
r
an
ch
o
f
s
tak
eh
o
ld
er
t
h
eo
r
y
[
1
5
]
b
y
p
r
io
r
itizin
g
o
n
ly
v
al
u
es,
th
er
eb
y
r
an
k
i
n
g
all
ty
p
es
o
f
s
tak
eh
o
ld
er
s
as
eq
u
al.
I
n
s
tead
o
f
m
a
n
ag
in
g
t
h
e
s
tak
eh
o
ld
er
s
,
h
u
m
an
v
al
u
es
ar
e
m
an
ag
ed
to
d
ef
in
e
th
e
s
co
p
e
o
f
th
e
p
r
o
b
lem
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
3
,
Ma
r
ch
20
2
5
:
1
89
9
-
1
90
7
1902
Fig
u
r
e
1
.
I
n
d
if
f
e
r
en
ce
c
u
r
v
e
f
o
r
m
o
r
al
d
ilem
m
a
4.
M
E
T
H
O
D
Mix
ed
m
eth
o
d
s
,
o
r
tr
ia
n
g
u
lati
o
n
[
1
6
]
is
u
s
ed
in
th
is
r
esear
ch
.
I
t
r
esu
lted
i
n
co
m
b
in
ed
ad
v
an
tag
es
o
f
q
u
an
titativ
e
an
d
q
u
alitativ
e
m
eth
o
d
s
o
f
r
esear
c
h
d
esig
n
.
T
r
i
an
g
u
latio
n
in
r
esear
ch
m
et
h
o
d
o
lo
g
y
r
ef
er
s
to
th
e
u
s
e
o
f
m
u
ltip
le
m
eth
o
d
s
o
r
d
a
ta
s
o
u
r
ce
s
to
g
ain
a
m
o
r
e
co
m
p
r
eh
en
s
iv
e
u
n
d
er
s
tan
d
in
g
o
f
a
r
esear
ch
p
r
o
b
lem
.
I
t
en
h
an
ce
s
th
e
cr
e
d
ib
ilit
y
an
d
v
alid
ity
o
f
th
e
f
in
d
in
g
s
b
y
cr
o
s
s
-
v
er
if
y
in
g
d
ata
an
d
p
er
s
p
e
ctiv
es
[
1
7
]
.
T
h
e
u
s
e
o
f
th
e
tr
ian
g
u
latio
n
m
et
h
o
d
to
g
et
d
if
f
er
en
t
p
er
s
p
ec
tiv
es
o
n
th
e
r
esear
ch
[
1
8
]
r
esu
lts
in
m
o
r
e
tr
an
s
p
ar
en
t
an
d
ex
p
lain
ab
le
r
esu
lts
.
T
h
eo
r
etic
al
an
d
m
et
h
o
d
o
lo
g
ical
tr
ian
g
u
latio
n
m
eth
o
d
s
wer
e
u
s
ed
i
n
th
e
r
esear
c
h
.
T
h
e
ch
o
ice
o
f
p
r
o
b
ab
ilis
tic
s
am
p
lin
g
[
1
9
]
f
o
r
c
o
llectin
g
p
r
i
m
ar
y
d
ata
o
n
th
e
d
ile
m
m
a
ju
s
tifie
s
th
e
eth
ical
co
n
s
id
er
atio
n
s
o
f
n
o
n
-
b
ias.
I
t
allo
ws
ev
er
y
s
ec
tio
n
o
f
s
o
ci
ety
to
h
av
e
a
n
o
n
-
ze
r
o
ch
a
n
c
e
o
f
in
clu
s
io
n
.
T
h
e
in
ter
ac
tio
n
s
with
f
o
u
r
s
eg
m
e
n
ts
o
f
th
e
s
am
p
le
p
o
p
u
latio
n
wer
e
co
n
d
u
cted
s
ep
ar
ately
.
T
h
e
s
tu
d
en
ts
,
ad
u
lts
,
s
en
io
r
s
,
an
d
eld
e
r
ly
wer
e
b
r
o
k
en
in
to
two
d
is
tin
ct
g
r
o
u
p
s
o
f
3
0
p
ar
ticip
a
n
ts
ea
ch
.
T
h
e
p
r
im
ar
y
d
ata
co
llectio
n
m
eth
o
d
f
o
r
th
e
d
ilem
m
a
was
a
g
u
id
ed
g
r
o
u
p
s
u
r
v
ey
.
T
h
e
d
ata
co
llectio
n
m
eth
o
d
o
f
g
u
id
ed
g
r
o
u
p
s
u
r
v
e
y
(
GGS)
was
d
ev
elo
p
ed
o
n
th
e
co
m
b
in
e
d
p
r
in
cip
les
o
f
f
o
cu
s
g
r
o
u
p
d
is
cu
s
s
io
n
(
FGD)
[
2
0
]
,
[
2
1
]
an
d
s
u
r
v
ey
[
2
2
]
.
W
h
ile
th
e
FGD
f
o
c
u
s
es
o
n
s
o
cial
in
ter
ac
tio
n
s
ar
o
u
n
d
a
co
n
tex
t,
a
s
u
r
v
ey
r
estricts
th
e
r
esp
o
n
s
es
[
2
3
]
.
I
n
GGS,
th
e
i
n
itial
b
r
ief
in
g
h
elp
ed
th
e
g
r
o
u
p
u
n
d
er
s
tan
d
th
e
ex
p
e
ctatio
n
s
an
d
r
ec
eiv
e
g
u
id
an
ce
wh
ile
p
er
f
o
r
m
in
g
i
n
tr
o
s
p
ec
tio
n
ab
o
u
t
t
h
e
d
ilem
m
a
in
th
e
s
u
r
v
e
y
.
T
h
e
r
e
s
p
o
n
s
es
in
GGS
ar
e
p
ap
er
o
r
s
y
s
tem
-
b
ased
q
u
alitativ
e
r
esp
o
n
s
es,
wh
ich
en
co
u
r
a
g
e
r
ef
lectio
n
th
r
o
u
g
h
in
ter
ac
ti
o
n
.
T
h
e
m
eth
o
d
is
co
m
p
ar
ed
with
f
o
c
u
s
g
r
o
u
p
d
i
s
cu
s
s
io
n
an
d
s
u
r
v
ey
in
T
ab
le
2
.
T
ab
le
2
.
C
o
m
p
a
r
is
o
n
o
f
g
u
id
e
d
g
r
o
u
p
s
u
r
v
ey
with
f
o
cu
s
g
r
o
u
p
d
is
cu
s
s
io
n
an
d
s
u
r
v
ey
P
r
i
n
c
i
p
l
e
G
u
i
d
e
d
g
r
o
u
p
s
u
r
v
e
y
F
o
c
u
s
g
r
o
u
p
d
i
sc
u
ss
i
o
n
S
u
r
v
e
y
M
o
d
e
r
a
t
i
o
n
Y
e
s
Y
e
s
No
I
n
t
e
r
a
c
t
i
v
e
e
n
v
i
r
o
n
me
n
t
Y
e
s
Y
e
s
No
G
r
o
u
p
d
y
n
a
mi
c
s
C
o
n
f
i
d
e
n
t
i
a
l
f
e
e
d
b
a
c
k
D
i
scu
ssi
o
n
P
e
r
so
n
a
l
r
e
s
p
o
n
ses
O
p
e
n
-
e
n
d
e
d
q
u
e
s
t
i
o
n
s
Y
e
s
Y
e
s
Y
e
s
A
n
o
n
y
mi
t
y
C
o
n
f
i
d
e
n
t
i
a
l
G
r
o
u
p
i
n
t
e
r
a
c
t
i
o
n
C
o
n
f
i
d
e
n
t
i
a
l
C
o
n
t
e
x
t
I
n
t
r
o
sp
e
c
t
i
v
e
a
n
d
S
o
c
i
a
l
S
o
c
i
a
l
P
e
r
so
n
a
l
N
u
mb
e
r
o
f
p
a
r
t
i
c
i
p
a
n
t
s
20
6
-
12
1
o
n
1
F
l
e
x
i
b
i
l
i
t
y
A
l
l
o
w
s
d
i
sc
u
ss
i
o
n
A
l
l
o
w
s
d
i
sc
u
ss
i
o
n
I
n
d
i
v
i
d
u
a
l
t
h
o
u
g
h
t
S
u
i
t
a
b
i
l
i
t
y
I
n
t
r
o
sp
e
c
t
i
v
e
s
o
c
i
a
l
t
h
e
mes
Ex
p
e
r
t
d
i
sc
u
ssi
o
n
s
P
e
r
so
n
a
l
i
n
si
g
h
t
s
o
f
e
x
p
e
r
t
s
D
a
t
a
q
u
a
l
i
t
y
Q
u
a
l
i
t
a
t
i
v
e
Q
u
a
l
i
t
a
t
i
v
e
Q
u
a
n
t
i
t
a
t
i
v
e
T
h
e
d
ig
ital
to
o
l
f
o
r
th
e
g
u
id
e
d
g
r
o
u
p
s
u
r
v
ey
was
d
ev
elo
p
e
d
u
s
in
g
Py
th
o
n
[
2
4
]
.
I
t
u
s
ed
E
x
ce
l
an
d
HT
ML
v
is
u
aliza
tio
n
f
o
r
r
ep
o
r
tin
g
[
2
5
]
.
T
h
e
d
ig
ital
t
o
o
l
c
o
llected
p
r
im
a
r
y
d
ata
an
d
cl
ea
n
ed
it
f
o
r
u
s
e
i
n
m
ac
h
in
e
lear
n
in
g
.
T
h
is
to
o
l
was
tr
ain
ed
to
wo
r
k
as
VGC
f
o
r
eth
ical
d
ec
is
io
n
-
m
a
k
in
g
.
T
h
e
d
ig
ital
to
o
l
d
o
cu
m
e
n
ted
th
e
d
ilem
m
a
f
ac
e
d
b
y
th
e
u
s
er
s
,
th
e
g
r
o
u
p
in
w
h
ich
th
ey
class
if
ied
th
e
d
ilem
m
a,
an
d
p
r
o
v
id
ed
a
g
u
id
ed
p
r
o
ce
s
s
to
r
ec
o
n
s
tr
u
ct
t
h
e
d
ilem
m
a,
f
ac
ilit
atin
g
a
n
eth
ical
d
ec
is
io
n
.
T
h
e
co
m
p
u
tatio
n
to
o
l
f
o
llo
wed
th
e
v
alu
e
-
s
en
s
itiv
e
d
esi
g
n
(
VSD)
ap
p
r
o
ac
h
[
2
6
]
f
o
r
eth
ics
-
by
-
d
e
s
ig
n
.
T
h
e
th
r
ee
s
tag
es
o
f
VSD
n
am
ely
,
em
p
ir
ical
in
v
esti
g
atio
n
,
co
n
ce
p
tu
al
i
n
v
esti
g
atio
n
,
an
d
tech
n
ical
in
v
esti
g
atio
n
ar
e
r
e
p
licated
in
th
e
th
r
ee
s
tep
s
o
f
id
en
tify
in
g
th
e
d
ilem
m
a
g
r
o
u
p
,
id
e
n
tify
in
g
r
elev
a
n
t
h
u
m
an
v
alu
es,
a
n
d
r
ec
o
m
m
e
n
d
in
g
t
h
e
s
et
o
f
v
alu
es
f
o
r
f
ac
ilit
atin
g
th
e
eth
ical
d
ec
is
io
n
u
s
in
g
th
e
VGC m
o
d
el
[
2
7
]
.
Data
p
r
o
ce
s
s
in
g
was
p
er
f
o
r
m
ed
to
m
ak
e
th
e
d
ata
s
u
itab
le
f
o
r
s
en
tim
en
t
an
aly
s
is
.
T
h
e
d
ilem
m
a
s
tatem
en
ts
wer
e
to
k
en
ized
to
r
em
o
v
e
s
to
p
w
o
r
d
s
an
d
wo
r
d
s
wer
e
lem
m
atize
d
to
th
eir
b
ase
f
o
r
m
to
r
e
d
u
c
e
r
ed
u
n
d
an
cy
.
T
h
e
d
ata
o
n
d
ile
m
m
as
was
u
s
ed
f
o
r
tr
ain
in
g
th
e
m
ac
h
in
e
to
class
if
y
d
ilem
m
as
in
to
th
r
ee
g
r
o
u
p
s
u
s
in
g
n
atu
r
al
la
n
g
u
a
g
e
p
r
o
ce
s
s
in
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
V
a
lu
e
g
r
o
u
p
cla
s
s
ifier
mo
d
el
fo
r
eth
ica
l d
ec
is
io
n
-
ma
kin
g
(
S
h
w
eta
B
h
a
tn
a
g
a
r
)
1903
Sen
tim
en
t
an
aly
s
is
was
p
er
f
o
r
m
ed
at
th
e
asp
ec
t
lev
el
[
2
8
]
t
o
f
ac
ilit
ate
m
u
lticlas
s
class
if
icatio
n
[
2
9
]
u
s
in
g
th
e
SVC
.
I
t
is
a
ty
p
e
o
f
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
(
SVM)
,
th
at
aim
s
to
f
in
d
th
e
h
y
p
er
p
lan
e
th
at
b
est
s
ep
ar
ates
clas
s
es
in
th
e
f
ea
tu
r
e
s
p
ac
e
[
3
0
]
.
B
y
m
ax
im
izin
g
th
e
m
ar
g
in
b
etwe
en
class
es,
S
VC
aim
s
to
im
p
r
o
v
e
g
en
er
aliza
tio
n
an
d
r
e
d
u
ce
o
v
e
r
f
itti
n
g
.
SVC
ca
n
ef
f
icien
tly
h
an
d
le
h
i
g
h
-
d
im
en
s
io
n
al
d
ata
a
n
d
is
less
p
r
o
n
e
t
o
o
v
er
f
itti
n
g
,
m
a
k
in
g
it
s
u
itab
le
f
o
r
s
m
all
d
atasets
.
Ad
d
itio
n
ally
,
SVC
ca
n
h
an
d
le
h
i
gh
-
d
im
en
s
io
n
al
d
ata
ef
f
icien
tly
th
r
o
u
g
h
t
h
e
u
s
e
o
f
k
er
n
el
f
u
n
ctio
n
s
,
wh
ich
m
a
p
th
e
in
p
u
t
d
ata
in
to
a
h
ig
h
e
r
-
d
im
en
s
io
n
al
s
p
ac
e
wh
er
e
it is
ea
s
ier
to
s
ep
ar
ate
class
es
[
3
1
]
.
C
o
n
s
id
er
in
g
a
s
m
all
m
u
lticlas
s
d
ataset
in
th
is
r
esear
ch
,
SVC
was
u
s
ed
f
o
r
tr
ain
in
g
th
e
m
ac
h
in
e
o
n
s
en
tim
en
t
an
aly
s
is
[
3
0
]
.
I
n
te
x
t
class
if
icatio
n
,
ea
ch
tex
t
s
n
ip
p
et
is
r
ep
r
esen
ted
as
a
h
ig
h
-
d
im
en
s
io
n
al
f
ea
tu
r
e
v
ec
to
r
,
wh
er
e
ea
ch
d
im
en
s
io
n
co
r
r
esp
o
n
d
s
to
a
u
n
iq
u
e
wo
r
d
o
r
n
-
g
r
a
m
.
SVMs
ar
e
well
-
s
u
ited
f
o
r
wo
r
k
in
g
in
h
ig
h
-
d
im
e
n
s
io
n
al
s
p
ac
es
an
d
ca
n
ef
f
ec
tiv
ely
h
a
n
d
le
th
e
s
p
a
r
s
e
a
n
d
h
ig
h
-
d
im
en
s
io
n
al
n
at
u
r
e
o
f
tex
t
d
ata
.
T
o
tr
ain
th
e
m
ac
h
in
e,
Sig
m
o
id
Ker
n
el
is
s
elec
ted
,
wh
ich
is
r
ep
r
e
s
en
ted
b
y
:
Κ
(
,
)
=
(
+
)
Her
e,
an
d
ar
e
th
e
in
p
u
t
v
ec
to
r
s
,
is
a
s
ca
lin
g
p
ar
am
eter
,
an
d
is
a
co
n
s
tan
t
ter
m
.
T
h
e
h
y
p
er
b
o
lic
t
an
g
en
t f
u
n
ctio
n
,
,
s
q
u
ash
es th
e
in
p
u
t in
to
th
e
r
an
g
e
[
-
1
,
1
]
.
T
h
e
ch
o
ice
o
f
k
er
n
el
d
ep
e
n
d
s
o
n
th
e
ty
p
e
o
f
d
ata
[
3
2
]
.
T
h
e
Sig
m
o
id
k
e
r
n
el
is
u
s
ed
i
n
S
VM
s
wh
en
d
ea
lin
g
with
n
o
n
-
lin
ea
r
l
y
s
ep
ar
ab
le
d
ata
f
o
r
te
x
t
class
if
icatio
n
.
T
h
e
Sig
m
o
id
k
er
n
el
allo
ws
f
o
r
m
o
r
e
co
n
tr
o
l
o
v
er
th
e
d
ec
is
io
n
b
o
u
n
d
ar
y
c
o
m
p
ar
ed
to
o
th
er
k
e
r
n
el
f
u
n
c
tio
n
s
.
B
y
ad
ju
s
tin
g
p
ar
am
eter
s
lik
e
an
d
,
o
n
e
ca
n
in
f
lu
en
ce
th
e
s
h
ap
e
a
n
d
p
o
s
itio
n
o
f
th
e
d
ec
is
io
n
b
o
u
n
d
a
r
y
.
A
d
is
tr
ib
u
tio
n
o
f
7
0
/3
0
is
u
s
ed
as
a
tr
ain
in
g
s
et
f
o
r
b
u
ild
in
g
t
h
e
class
if
icatio
n
m
o
d
el.
T
h
e
s
m
all
d
ataset
h
ad
f
ewe
r
s
am
p
les
f
o
r
s
tu
d
en
ts
an
d
ad
u
lt wo
m
en
in
th
e
n
o
n
-
s
en
tien
t
ca
t
eg
o
r
y
.
T
h
e
d
ata
d
r
if
ted
to
wa
r
d
s
r
elatio
n
s
h
ip
s
(
s
en
tien
t)
in
th
e
ca
s
e
o
f
wo
m
en
,
to
war
d
s
o
b
jects
(
n
o
n
-
s
en
tien
t)
in
th
e
ca
s
e
o
f
ad
u
lt
m
en
,
a
n
d
t
o
war
d
s
s
itu
atio
n
s
(
ab
s
tr
ac
t)
in
th
e
ca
s
e
o
f
y
o
u
n
g
s
tu
d
en
ts
.
Su
ch
im
b
al
an
ce
s
lead
to
b
iased
m
o
d
el
p
r
e
d
ictio
n
s
,
an
d
lim
ited
lear
n
in
g
b
y
m
ac
h
in
es,
le
ad
in
g
to
p
o
o
r
p
er
f
o
r
m
a
n
ce
.
T
o
ad
d
r
ess
th
ese
ch
allen
g
es,
d
ata
au
g
m
en
tatio
n
,
s
y
n
th
etic
d
ata
g
e
n
er
atio
n
,
an
d
en
s
em
b
le
lear
n
in
g
tech
n
i
q
u
es
ar
e
u
tili
ze
d
to
im
p
r
o
v
e
th
e
ac
cu
r
ac
y
o
f
th
e
class
if
ier
[
3
3
]
.
T
o
b
u
ild
a
b
alan
ce
d
t
r
ain
in
g
d
ataset
wi
th
all
p
e
r
c
ep
tio
n
s
(
class
if
ier
g
r
o
u
p
s
)
,
n
ew
d
ile
m
m
a
s
tatem
en
ts
wer
e
in
tr
o
d
u
ce
d
f
o
r
lag
g
in
g
ca
teg
o
r
ies
in
ea
ch
s
o
cial
g
r
o
u
p
u
s
in
g
s
im
ilar
wo
r
d
s
d
er
iv
ed
f
r
o
m
th
e
wo
r
d
clo
u
d
an
aly
s
is
.
Similar
ly
,
d
u
p
licate
d
ilem
m
as
wer
e
r
em
o
v
ed
f
r
o
m
ea
ch
s
o
cial
g
r
o
u
p
.
T
h
is
in
cr
ea
s
ed
th
e
tr
ain
in
g
d
ataset
to
1
0
4
d
ilem
m
as.
T
h
e
m
eth
o
d
o
lo
g
y
f
o
r
b
u
ild
in
g
SVC
is
g
iv
en
in
Fig
u
r
e
2
.
T
h
e
class
if
ier
is
a
m
u
lticlas
s
class
if
ier
o
f
lev
el
3
with
2
in
p
u
ts
:
d
ilem
m
a
an
d
v
alu
e
g
r
o
u
p
.
T
h
e
class
if
ier
tr
ain
s
it
s
elf
in
th
e
f
ir
s
t
s
tag
e
b
y
b
u
ild
in
g
th
e
ch
a
r
ac
ter
i
s
tics
o
f
th
e
m
o
d
el.
I
n
t
h
e
s
ec
o
n
d
s
tag
e,
it
p
r
ed
icts
th
e
v
alu
e
g
r
o
u
p
f
o
r
t
h
e
d
ilem
m
a,
wh
ich
is
u
s
ed
f
o
r
m
ak
in
g
r
ec
o
m
m
e
n
d
atio
n
s
f
o
r
eth
ical
d
ec
is
io
n
-
m
ak
in
g
.
Fig
u
r
e
2
.
SVC
tr
ain
in
g
p
r
o
ce
s
s
5.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
d
ilem
m
as
wer
e
g
r
o
u
p
e
d
i
n
to
th
r
ee
ca
teg
o
r
ies
b
ased
o
n
s
tak
eh
o
ld
er
s
an
d
ass
o
ciate
d
et
h
ical
v
alu
e
s
ets
ar
e
s
u
g
g
ested
f
o
r
a
g
i
v
en
d
ilem
m
a.
T
h
e
f
ir
s
t
s
et
o
f
eth
i
ca
l
v
alu
es
ap
p
lies
to
n
o
n
-
s
en
tien
t
o
b
jects
o
n
th
e
p
lan
et.
T
h
e
s
ec
o
n
d
s
et
o
f
eth
ical
v
alu
es
is
f
o
r
s
en
tien
t
b
ein
g
s
o
n
th
e
p
lan
et.
T
h
e
t
h
ir
d
ca
teg
o
r
y
o
f
eth
ical
v
alu
es r
elate
s
to
ab
s
tr
ac
t o
r
n
o
n
-
p
h
y
s
ical
co
n
ce
p
ts
.
T
h
e
d
ilem
m
as
s
tated
b
y
r
esp
o
n
d
en
ts
wer
e
d
ir
ec
tly
r
elate
d
to
th
e
p
h
ase
o
f
life
th
at
t
h
e
y
wer
e
i
n
.
Stu
d
en
ts
h
ad
ca
r
ee
r
d
ilem
m
a
s
,
w
o
m
en
h
ad
d
ilem
m
as
r
elat
ed
to
m
ar
ital
life
,
m
e
n
h
a
d
d
ilem
m
as
r
elate
d
to
s
o
cial
s
tr
u
ctu
r
e
an
d
ea
r
n
in
g
o
p
p
o
r
tu
n
ities
,
eld
er
ly
h
a
d
h
ea
lt
h
an
d
s
elf
-
ca
r
e
is
s
u
es.
B
ased
o
n
ag
e
g
r
o
u
p
s
,
f
o
u
r
Cl
ean
Da
ta
Ke
rn
e
l
Tra
in
S
VC
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
3
,
Ma
r
ch
20
2
5
:
1
89
9
-
1
90
7
1904
g
r
o
u
p
s
o
f
s
o
ciety
wer
e
id
en
ti
f
ied
:
s
tu
d
en
ts
,
ad
u
lts
,
s
en
io
r
s
,
an
d
th
e
eld
e
r
ly
.
T
h
e
d
ilem
m
a
with
in
th
ese
f
o
u
r
g
r
o
u
p
s
r
em
ain
s
s
im
ilar
,
b
u
t
t
h
e
p
er
ce
p
tio
n
o
f
th
e
d
ilem
m
a
(
class
if
ier
g
r
o
u
p
s
)
v
a
r
ies
b
ased
o
n
th
e
b
elief
s
an
d
co
n
d
itio
n
s
o
f
th
e
r
esp
o
n
d
en
t.
T
h
e
s
u
m
m
ar
y
o
f
ca
teg
o
r
ies
an
d
d
ilem
m
as
o
f
th
e
en
h
a
n
ce
d
d
ataset
is
g
iv
en
in
T
ab
le
3.
T
h
e
class
if
icatio
n
p
r
o
b
lem
o
f
th
e
eth
ical
d
ilem
m
a
was so
lv
ed
th
r
o
u
g
h
SVC
.
A
s
im
p
le
SV
C
clas
s
if
ier
was
tr
ain
ed
with
8
3
to
1
7
0
s
u
p
p
o
r
t
v
ec
t
o
r
s
o
n
a
s
m
all
d
ataset
o
f
1
0
4
r
ec
o
r
d
s
.
T
h
e
cl
ass
if
ier
m
o
d
el
was
ass
es
s
ed
f
o
r
ac
cu
r
ac
y
,
r
ec
all,
p
r
ec
is
io
n
,
an
d
f
1
,
as
g
iv
en
i
n
T
ab
le
4
.
T
h
e
lear
n
in
g
cu
r
v
e
o
f
th
e
VGC
m
o
d
el
is
g
iv
en
in
Fig
u
r
e
3
.
Tab
le
3
.
S
u
m
m
a
ry
o
f
c
a
teg
o
ries
a
n
d
d
il
e
m
m
a
s in
d
a
tas
e
t
S
o
c
i
e
t
y
g
r
o
u
p
s
N
o
n
-
se
n
t
i
e
n
t
d
i
l
e
mm
a
s
S
e
n
t
i
e
n
t
d
i
l
e
mm
a
s
A
b
st
r
a
c
t
d
i
l
e
mm
a
s
To
t
a
l
S
t
u
d
e
n
t
s
18
18
18
54
A
d
u
l
t
s
12
12
9
33
S
e
n
i
o
r
s
2
2
4
8
El
d
e
r
l
y
3
2
4
9
Tab
le
4
.
VG
C
re
su
lt
s
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
f1
-
sco
r
e
S
u
p
p
o
r
t
O
b
j
e
c
t
0
.
3
6
0
.
8
0
0
.
5
0
5
R
e
l
a
t
i
o
n
s
h
i
p
0
.
6
0
0
.
3
8
0
.
4
6
8
S
i
t
u
a
t
i
o
n
0
.
8
0
0
.
5
0
0
.
6
2
8
a
c
c
u
r
a
c
y
0
.
5
2
21
M
a
c
r
o
a
v
g
0
.
5
9
0
.
5
6
0
.
5
3
21
W
e
i
g
h
t
e
d
a
v
g
0
.
6
2
0
.
5
2
0
.
5
3
21
Fig
u
r
e
3
.
T
h
e
lear
n
in
g
cu
r
v
e
o
f
th
e
class
if
icatio
n
m
o
d
el
f
o
r
v
alu
es
T
h
e
Natu
r
al
L
an
g
u
ag
e
T
o
o
lk
it
(
NL
T
K
)
[
3
4
]
was
u
s
ed
to
r
em
o
v
e
s
to
p
wo
r
d
s
f
r
o
m
d
ile
m
m
as
an
d
u
s
in
g
lem
m
atiza
tio
n
,
th
e
w
o
r
d
s
wer
e
co
n
v
er
ted
in
to
th
eir
b
ase
f
o
r
m
.
T
h
e
f
ilter
ed
s
en
ten
ce
s
wer
e
u
s
ed
f
o
r
cr
ea
tin
g
a
wo
r
d
clo
u
d
f
o
r
ea
c
h
o
f
th
e
ca
teg
o
r
ies.
Fig
u
r
e
4
s
h
o
ws
th
e
d
is
tin
g
u
is
h
in
g
k
e
y
wo
r
d
s
o
f
th
e
th
r
ee
class
if
icatio
n
g
r
o
u
p
s
,
wh
ich
w
er
e
u
s
ed
f
o
r
f
u
r
th
er
tr
ai
n
in
g
th
e
m
o
d
el
in
class
if
icatio
n
.
Fig
u
r
e
4
.
W
o
r
d
C
lo
u
d
f
o
r
th
r
ee
class
if
icatio
n
g
r
o
u
p
s
(
o
b
ject,
r
elatio
n
s
h
ip
s
,
an
d
a
b
s
tr
ac
t
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
V
a
lu
e
g
r
o
u
p
cla
s
s
ifier
mo
d
el
fo
r
eth
ica
l d
ec
is
io
n
-
ma
kin
g
(
S
h
w
eta
B
h
a
tn
a
g
a
r
)
1905
T
h
e
VGC
m
o
d
el
r
ec
o
m
m
en
d
s
r
elev
an
t
h
u
m
an
v
alu
es
ap
p
licab
le
to
th
e
eth
ical
d
ec
is
io
n
.
T
h
e
s
u
g
g
esti
o
n
s
o
f
Ksh
am
a,
An
as
u
y
a,
a
n
d
d
ay
a
in
Fig
u
r
e
5
ar
e
ap
p
licab
le
in
th
e
ca
s
e
o
f
r
elatio
n
s
h
ip
s
o
r
s
en
tien
t
b
ein
g
s
.
T
h
is
r
ec
o
m
m
en
d
ati
o
n
b
y
VGC
is
b
ase
d
o
n
t
h
e
p
r
o
b
a
b
il
i
t
y
d
is
t
r
i
b
u
ti
o
n
s
o
f
v
a
lu
e
g
r
o
u
p
s
’
p
r
ed
icti
o
n
s
f
o
r
o
u
tc
o
m
es
.
T
h
e
c
lass
i
f
i
ca
t
io
n
o
f
d
ile
m
m
as
is
d
o
n
e
i
n
th
r
e
e
ca
t
e
g
o
r
i
es
(
n
o
n
-
s
e
n
ti
en
t,
s
e
n
tie
n
t
,
a
n
d
ab
s
tr
ac
t
)
r
at
h
er
t
h
a
n
as
b
i
n
a
r
y
(
et
h
i
ca
l
o
r
n
o
n
-
e
th
ic
al
s
t
at
em
en
ts
)
.
S
in
c
e
ea
c
h
d
ile
m
m
a
ca
n
h
a
v
e
m
u
lti
p
l
e
o
u
tc
o
m
es
b
as
ed
o
n
th
e
c
o
n
d
iti
o
n
s
a
n
d
b
elie
f
s
o
f
t
h
e
s
u
b
j
ec
t
(
d
e
cisi
o
n
-
m
a
k
e
r
)
,
th
e
m
o
d
e
l
o
n
ly
s
u
g
g
e
s
ts
r
ele
v
a
n
t
v
al
u
es
an
d
n
o
t
et
h
ic
al
s
t
ate
m
e
n
ts
.
T
h
ese
v
al
u
e
g
r
o
u
p
r
ec
o
m
m
e
n
d
ati
o
n
s
a
r
e
u
s
e
d
f
o
r
d
e
f
i
n
i
n
g
th
e
s
c
o
p
e
o
f
t
h
e
p
r
o
b
l
em
,
wh
ic
h
is
d
e
p
en
d
e
n
t
o
n
th
e
s
ta
k
e
h
o
l
d
e
r
v
al
u
es
a
n
d
e
x
p
ec
te
d
o
u
t
co
m
e
.
Fig
u
r
e
5
.
Feed
b
ac
k
f
o
r
v
al
u
e
r
ec
o
m
m
en
d
atio
n
ac
co
r
d
in
g
to
class
if
icatio
n
g
r
o
u
p
s
6.
CO
NCLU
SI
O
N
E
x
is
ti
n
g
et
h
ic
al
d
ec
is
i
o
n
-
m
a
k
i
n
g
m
o
d
els
d
esc
r
i
b
e
p
r
o
ce
s
s
es
f
o
r
d
ec
is
io
n
-
m
a
k
i
n
g
,
b
u
t
ca
n
n
o
t
g
i
v
e
a
n
u
m
er
i
ca
ll
y
a
cc
u
r
at
e
s
o
l
u
ti
o
n
f
o
r
a
d
il
em
m
a
.
A
d
ile
m
m
a
is
c
au
s
ed
b
y
co
n
f
li
cti
n
g
v
a
lu
es
o
r
in
t
er
ests
.
Si
n
c
e
t
h
e
co
n
f
li
ct
h
a
p
p
e
n
s
b
et
we
en
a
f
ew
s
e
lec
te
d
v
al
u
es,
we
lo
s
e
t
h
e
v
is
io
n
o
f
t
h
e
la
r
g
e
r
p
ic
tu
r
e
a
n
d
t
r
y
t
o
f
ix
t
h
e
im
m
e
d
ia
te
p
r
o
b
le
m
o
r
c
o
n
f
li
ct
,
l
ea
d
i
n
g
to
m
y
o
p
ic
d
e
cisi
o
n
s
.
An
A
I
m
o
d
el
t
o
s
u
g
g
est
r
e
le
v
a
n
t
h
u
m
an
v
al
u
es
to
et
h
i
ca
l
d
ec
is
io
n
-
m
ak
e
r
s
is
d
e
v
e
lo
p
ed
t
o
c
lass
i
f
y
all
d
il
em
m
as
in
to
th
r
e
e
c
ate
g
o
r
ie
s
n
o
n
-
s
e
n
t
ie
n
t
,
s
e
n
ti
en
t,
an
d
a
b
s
t
r
a
ct.
T
h
e
VGC
m
o
d
el
r
e
co
m
m
en
d
s
all
r
el
e
v
a
n
t
h
u
m
an
an
d
e
n
v
i
r
o
n
m
e
n
t
all
y
s
u
s
ta
in
a
b
le
v
a
lu
es
a
p
p
li
ca
b
l
e
to
t
h
e
d
i
le
m
m
a
a
n
d
f
ac
il
ita
tes
t
h
e
d
ec
is
i
o
n
-
m
ak
er
in
d
e
f
i
n
i
n
g
t
h
e
s
c
o
p
e
o
f
t
h
e
p
r
o
b
l
em
.
T
h
e
d
ec
is
i
o
n
-
m
a
k
e
r
s
t
r
a
d
e
-
o
f
f
b
et
wee
n
th
e
co
n
f
li
cti
n
g
v
a
lu
es
f
o
r
a
b
ala
n
ce
d
d
e
cisi
o
n
.
T
h
e
m
o
d
el
s
h
o
we
d
a
p
e
r
f
o
r
m
a
n
c
e
s
c
o
r
e
o
f
0
.
5
2
a
n
d
will
b
e
t
r
ai
n
e
d
wit
h
l
ar
g
e
r
d
at
asets
o
n
b
ig
g
e
r
tr
a
in
in
g
m
o
d
els
t
o
im
p
r
o
v
e
cl
a
s
s
if
i
ca
t
io
n
p
r
o
b
le
m
s
.
A
d
e
cisi
o
n
ca
n
b
e
m
ad
e
b
ett
er
wit
h
f
ee
d
b
a
c
k
.
R
at
h
er
t
h
a
n
e
v
al
u
ati
n
g
a
d
ec
is
io
n
as
r
i
g
h
t
o
r
wr
o
n
g
,
a
s
et
o
f
r
e
f
e
r
e
n
c
e
m
o
r
al
v
al
u
es
ca
n
b
e
s
u
g
g
est
ed
as
s
ca
f
f
o
l
d
i
n
g
t
o
th
e
d
e
cisi
o
n
-
m
ak
e
r
f
o
r
e
th
ica
l
d
e
cisi
o
n
-
m
a
k
i
n
g
.
Si
n
c
e
d
il
em
m
as
a
r
e
t
h
e
m
s
el
v
es
a
m
b
ig
u
o
u
s
s
tat
em
e
n
ts
,
cl
ass
if
y
i
n
g
t
h
e
m
as
et
h
ic
a
l
o
r
u
n
e
th
ica
l
b
ase
d
o
n
p
r
e
d
i
cti
v
e
u
n
ce
r
t
ai
n
t
y
is
n
o
t
f
ea
s
ib
le
.
Mo
r
eo
v
e
r
,
h
u
m
a
n
a
u
t
o
n
o
m
y
i
n
th
e
ca
s
e
o
f
e
th
i
ca
l
d
ec
is
i
o
n
s
s
h
o
u
l
d
n
o
t
b
e
co
m
p
r
o
m
is
e
d
b
y
a
u
t
o
m
ati
o
n
.
T
h
e
lim
ita
ti
o
n
o
f
t
h
e
r
ese
a
r
c
h
is
th
e
li
m
ite
d
n
u
m
b
e
r
o
f
clas
s
es.
A
d
i
le
m
m
a
ca
n
b
e
ass
o
ci
ate
d
wit
h
m
o
r
e
t
h
a
n
o
n
e
c
lass
in
th
e
r
ea
l
wo
r
l
d
an
d
t
h
e
ass
o
c
iat
ed
h
u
m
an
v
al
u
es
c
h
a
n
g
e
a
cc
o
r
d
i
n
g
l
y
.
As
t
h
e
d
a
ta
in
c
r
ea
s
es
o
v
e
r
t
im
e,
m
ac
h
i
n
e
s
c
a
n
b
e
t
r
a
in
ed
t
o
i
d
e
n
ti
f
y
r
e
lat
e
d
h
u
m
an
v
al
u
es
d
i
r
e
ctl
y
f
r
o
m
d
ile
m
m
a
s
tate
m
e
n
ts
.
Dat
a
p
r
o
ce
s
s
i
n
g
in
th
e
f
o
r
m
o
f
s
t
o
p
wo
r
d
r
e
m
o
v
a
l
a
n
d
l
em
m
a
tiz
ati
o
n
i
n
cr
ea
s
es
th
e
a
cc
u
r
ac
y
o
f
th
e
m
o
d
el
b
u
t
r
ed
u
ce
s
th
e
n
u
m
b
e
r
o
f
s
u
p
p
o
r
t
v
ec
t
o
r
s
u
s
e
d
f
o
r
class
i
f
y
i
n
g
d
at
a.
As
t
h
e
a
m
o
u
n
t
o
f
d
ata
i
n
c
r
e
ases
an
d
wit
h
t
h
e
u
s
e
o
f
a
d
v
an
ce
d
m
o
d
els
o
f
class
if
ica
ti
o
n
,
t
h
e
n
e
ed
f
o
r
le
m
m
ati
za
t
io
n
w
o
u
ld
a
l
s
o
r
e
d
u
c
e.
VGC
is
p
ar
t
o
f
t
h
e
E
t
h
ic
al
I
n
tel
li
g
e
n
c
e
m
o
d
el
t
h
at
c
an
b
e
e
n
h
a
n
c
ed
f
o
r
b
e
h
a
v
i
o
r
t
r
ain
in
g
a
n
d
au
t
o
m
at
e
d
as
a
p
a
r
t
o
f
f
u
tu
r
e
r
es
ea
r
c
h
t
o
s
u
g
g
est
et
h
ic
al
d
e
cisi
o
n
-
m
a
k
i
n
g
alt
er
n
ati
v
es
t
o
d
e
cisi
o
n
-
m
a
k
e
r
s
.
I
n
ad
d
it
io
n
t
o
d
ec
is
i
o
n
-
m
a
k
i
n
g
t
o
o
ls
,
t
h
er
e
is
a
wi
d
e
s
c
o
p
e
f
o
r
t
a
x
o
n
o
m
y
a
n
d
o
n
t
o
l
o
g
y
f
o
r
o
r
g
a
n
iz
in
g
h
u
m
a
n
k
n
o
w
le
d
g
e
t
o
d
er
iv
e
p
r
o
f
ess
i
o
n
al
v
a
lu
es.
T
h
e
p
r
es
en
t
p
ap
er
l
ay
s
t
h
e
f
o
u
n
d
at
io
n
f
o
r
t
h
e
d
e
v
elo
p
m
e
n
t
o
f
E
t
h
ic
al
I
n
tel
li
g
e
n
c
e
a
n
d
o
f
f
e
r
s
p
r
o
s
p
e
cts
f
o
r
e
x
p
a
n
s
i
o
n
t
h
r
o
u
g
h
t
h
e
in
co
r
p
o
r
ati
o
n
o
f
en
s
em
b
l
e
a
l
g
o
r
i
th
m
s
an
d
D
at
a
Scie
n
c
e,
f
o
s
te
r
i
n
g
f
u
r
t
h
er
r
ese
a
r
c
h
in
t
h
is
d
o
m
a
in
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
3
,
Ma
r
ch
20
2
5
:
1
89
9
-
1
90
7
1906
E
t
hica
l
a
pp
ro
v
a
l:
All
p
r
o
ce
d
u
r
es
p
er
f
o
r
m
ed
in
h
u
m
a
n
p
ar
t
icip
an
t
s
tu
d
ies
wer
e
u
n
d
er
t
h
e
E
th
ical
Gu
id
elin
es
f
o
r
R
esear
ch
I
n
v
o
lv
in
g
Hu
m
a
n
Par
ticip
an
ts
an
d
with
th
e
1
9
6
4
Helsin
k
i
Dec
lar
atio
n
an
d
its
later
am
en
d
m
en
ts
o
r
co
m
p
ar
ab
le
eth
ical
s
tan
d
a
r
d
s
.
I
nfo
rm
ed
co
ns
ent
:
I
n
f
o
r
m
ed
co
n
s
en
t w
as o
b
tain
ed
f
r
o
m
all
in
d
iv
i
d
u
al
p
ar
ticip
an
ts
in
clu
d
e
d
in
th
e
s
tu
d
y
Av
a
ila
bil
it
y
o
f
da
t
a
a
nd
ma
t
er
ia
l
:
Data
u
s
ed
f
o
r
r
esear
ch
c
an
b
e
m
a
d
e
av
ailab
le
f
o
r
r
e
f
er
en
ce
.
RE
F
E
R
E
NC
E
S
[
1
]
A
.
Th
o
mas
,
“
N
o
r
ma
t
i
v
e
e
t
h
i
c
s:
N
a
g
e
l
’
s
h
y
b
r
i
d
e
t
h
i
c
a
l
t
h
e
o
r
y
,
”
i
n
T
h
o
m
a
s
N
a
g
e
l
,
2
0
2
0
,
p
p
.
1
7
3
–
2
1
6
,
.
d
o
i
:
1
0
.
4
3
2
4
/
9
7
8
1
3
1
5
7
1
2
1
8
5
-
1
2
.
[
2
]
A
.
B
.
C
o
h
e
n
,
“
M
a
n
y
f
o
r
ms
o
f
c
u
l
t
u
r
e
,
”
Am
e
r
i
c
a
n
Ps
y
c
h
o
l
o
g
i
st
,
v
o
l
.
6
4
,
n
o
.
3
,
p
p
.
1
9
4
–
2
0
4
,
2
0
0
9
,
d
o
i
:
1
0
.
1
0
3
7
/
a
0
0
1
5
3
0
8
.
[
3
]
D
.
H
e
n
d
r
y
c
k
s
e
t
a
l
.
,
“
A
l
i
g
n
i
n
g
A
I
w
i
t
h
s
h
a
r
e
d
h
u
ma
n
v
a
l
u
e
s,
”
I
C
L
R
2
0
2
1
-
9
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
L
e
a
r
n
i
n
g
Re
p
r
e
se
n
t
a
t
i
o
n
s
,
2
0
2
1
.
[
4
]
G
.
A
.
C
o
h
e
n
,
“
F
a
c
t
s
a
n
d
p
r
i
n
c
i
p
l
e
s,
”
Ph
i
l
o
so
p
h
y
&
P
u
b
l
i
c
A
f
f
a
i
rs
,
v
o
l
.
3
1
,
n
o
.
3
,
p
p
.
2
1
1
–
2
4
5
,
J
u
l
.
2
0
0
3
,
d
o
i
:
1
0
.
1
1
1
1
/
j
.
1
0
8
8
-
4
9
6
3
.
2
0
0
3
.
0
0
2
1
1
.
x
.
[
5
]
T.
P
.
R
e
ml
e
y
a
n
d
B
.
H
e
r
l
i
h
y
,
Et
h
i
c
a
l
a
n
d
p
r
o
f
e
ssi
o
n
a
l
i
ssu
e
s i
n
c
o
u
n
se
l
i
n
g
.
N
e
w
Jerse
y
:
P
r
e
n
t
i
c
e
H
a
l
l
,
2
0
1
0
.
[
6
]
S
.
S
i
n
e
k
,
S
t
a
r
t
w
i
t
h
w
h
y
:
h
o
w
g
r
e
a
t
l
e
a
d
e
rs
i
n
s
p
i
re
e
v
e
ry
o
n
e
t
o
t
a
k
e
a
c
t
i
o
n
.
N
e
w
Y
o
r
k
:
P
e
n
g
u
i
n
P
u
b
l
i
s
h
i
n
g
G
r
o
u
p
,
2
0
0
9
.
[
7
]
T.
J
.
Li
n
g
a
n
d
J.
M
.
H
a
u
c
k
,
T
h
e
ET
H
I
C
S
m
o
d
e
l
:
c
o
m
p
re
h
e
n
s
i
v
e
,
e
t
h
i
c
a
l
d
e
c
i
si
o
n
m
a
k
i
n
g
,
v
o
l
.
1
8
,
n
o
.
2
0
1
1
.
2
0
1
7
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
w
w
w
.
c
o
u
n
se
l
i
n
g
.
o
r
g
/
d
o
c
s/
d
e
f
a
u
l
t
-
s
o
u
r
c
e
/
v
i
st
a
s/
t
h
e
-
e
t
h
i
c
s
-
mo
d
e
l
.
p
d
f
[
8
]
G
.
C
.
B
a
n
k
s,
D
.
J
.
K
n
a
p
p
,
L.
L
i
n
,
C
.
S
.
S
a
n
d
e
r
s,
a
n
d
J
.
A
.
G
r
a
n
d
,
“
E
t
h
i
c
a
l
d
e
c
i
si
o
n
m
a
k
i
n
g
i
n
t
h
e
2
1
s
t
c
e
n
t
u
r
y
:
a
u
sef
u
l
,
”
2
0
2
2
.
[
9
]
M
.
V
.
N
a
d
k
a
r
n
i
,
Et
h
i
c
s
f
o
r
o
u
r
t
i
m
e
s:
e
ssa
y
s i
n
G
a
n
d
h
i
a
n
p
e
rs
p
e
c
t
i
v
e
.
2
0
1
3
.
d
o
i
:
1
0
.
1
0
9
3
/
a
c
p
r
o
f
:
o
s
o
/
9
7
8
0
1
9
8
0
7
3
8
6
4
.
0
0
1
.
0
0
0
1
.
[
1
0
]
N
.
T.
K
.
C
h
i
,
“
Th
e
e
f
f
e
c
t
o
f
A
I
c
h
a
t
b
o
t
s
o
n
p
r
o
-
e
n
v
i
r
o
n
me
n
t
a
t
t
i
t
u
d
e
a
n
d
w
i
l
l
i
n
g
n
e
ss
t
o
p
a
y
f
o
r
e
n
v
i
r
o
n
m
e
n
t
p
r
o
t
e
c
t
i
o
n
,
”
S
a
g
e
O
p
e
n
,
v
o
l
.
1
4
,
n
o
.
1
,
Ja
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
7
7
/
2
1
5
8
2
4
4
0
2
3
1
2
2
6
0
0
1
.
[
1
1
]
S
.
N
o
sr
a
t
a
b
a
d
i
,
A
.
M
o
s
a
v
i
,
S
.
S
h
a
ms
h
i
r
b
a
n
d
,
E
.
K
.
Za
v
a
d
s
k
a
s
,
A
.
R
a
k
o
t
o
n
i
r
a
i
n
y
,
a
n
d
K
.
-
W
.
C
h
a
u
,
“
S
u
s
t
a
i
n
a
b
l
e
b
u
s
i
n
e
ss mo
d
e
l
s:
a
r
e
v
i
e
w
,
”
Pre
p
ri
n
t
,
F
e
b
.
2
0
1
9
,
d
o
i
:
1
0
.
2
0
9
4
4
/
p
r
e
p
r
i
n
t
s2
0
1
8
1
0
.
0
3
7
8
.
v
3
.
[
1
2
]
B
.
T
u
n
d
y
s,
“
S
u
s
t
a
i
n
a
b
l
e
b
u
si
n
e
ss
m
o
d
e
l
s
o
f
c
o
m
p
a
n
i
e
s,”
i
n
S
u
s
t
a
i
n
a
b
i
l
i
t
y
i
n
B
a
n
k
a
n
d
C
o
r
p
o
r
a
t
e
B
u
si
n
e
ss
Mo
d
e
l
s
,
2
0
2
1
,
p
p
.
1
4
7
–
1
8
4
,
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
0
-
7
2
0
9
8
-
8
_
6
.
[
1
3
]
A
.
La
w
e
r
e
n
c
e
,
J.
W
e
b
e
r
,
a
n
d
J.
P
o
st
,
Bu
si
n
e
ss
a
n
d
s
o
c
i
e
t
y
:
s
t
a
k
e
h
o
l
d
e
rs
,
e
t
h
i
c
s,
p
u
b
l
i
c
p
o
l
i
c
y
.
2
0
1
1
.
[
1
4
]
D
.
V
.
W
a
t
k
i
n
s
a
n
d
V
.
P
.
D
e
n
n
e
y
,
“
U
n
d
e
r
s
t
a
n
d
i
n
g
p
r
o
j
e
c
t
s
t
a
k
e
h
o
l
d
e
r
p
l
a
n
n
i
n
g
,
i
d
e
n
t
i
f
i
c
a
t
i
o
n
a
n
d
e
n
g
a
g
e
m
e
n
t
:
a
p
h
e
n
o
m
e
n
o
l
o
g
i
c
a
l
a
p
p
r
o
a
c
h
,
”
J
o
u
r
n
a
l
o
f
L
e
a
d
e
r
s
h
i
p
,
A
c
c
o
u
n
t
a
b
i
l
i
t
y
a
n
d
E
t
h
i
c
s
,
v
o
l
.
2
0
,
n
o
.
5
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
4
2
3
/
j
l
a
e
.
v
2
0
i
5
.
6
6
0
2
.
[
1
5
]
G
.
A
t
i
c
i
,
“
C
u
r
r
e
n
t
i
ss
u
e
s
o
n
c
o
r
p
o
r
a
t
e
g
o
v
e
r
n
a
n
c
e
,
r
e
sp
o
n
si
b
i
l
i
t
y
,
st
a
k
e
h
o
l
d
e
r
t
h
e
o
r
y
,
a
n
d
o
r
g
a
n
i
z
a
t
i
o
n
a
l
b
e
h
a
v
i
o
r
,
”
C
o
rp
o
r
a
t
e
G
o
v
e
r
n
a
n
c
e
a
n
d
S
u
s
t
a
i
n
a
b
i
l
i
t
y
Re
v
i
e
w
,
v
o
l
.
7
,
n
o
.
4
,
p
p
.
4
–
6
,
Ja
n
.
2
0
2
4
,
d
o
i
:
1
0
.
2
2
4
9
5
/
c
g
sr
v
7
i
4
e
d
i
t
o
r
i
a
l
.
[
1
6
]
L.
H
e
a
t
h
,
“
Tr
i
a
n
g
u
l
a
t
i
o
n
:
met
h
o
d
o
l
o
g
y
,
”
i
n
I
n
t
e
rn
a
t
i
o
n
a
l
E
n
c
y
c
l
o
p
e
d
i
a
o
f
t
h
e
S
o
c
i
a
l
&
Be
h
a
v
i
o
r
a
l
S
c
i
e
n
c
e
s:
S
e
c
o
n
d
E
d
i
t
i
o
n
,
2
0
1
5
,
p
p
.
6
3
9
–
6
4
4
,
.
d
o
i
:
1
0
.
1
0
1
6
/
B
9
7
8
-
0
-
08
-
0
9
7
0
8
6
-
8
.
4
4
0
5
9
-
6.
[
1
7
]
N
.
K
.
D
e
n
z
i
n
,
T
r
i
a
n
g
u
l
a
t
i
o
n
.
W
i
l
e
y
,
2
0
0
7
.
d
o
i
:
1
0
.
1
0
0
2
/
9
7
8
1
4
0
5
1
6
5
5
1
8
.
[
1
8
]
J.
-
F
.
M
o
r
i
n
,
C
.
O
l
sso
n
,
a
n
d
E.
Ö
.
A
t
i
k
c
a
n
,
E
d
s.
,
“
Tr
i
a
n
g
u
l
a
t
i
o
n
,
”
i
n
Re
s
e
a
r
c
h
M
e
t
h
o
d
s
i
n
t
h
e
S
o
c
i
a
l
S
c
i
e
n
c
e
s:
A
n
A
-
Z
o
f
k
e
y
c
o
n
c
e
p
t
s
,
O
x
f
o
r
d
:
O
x
f
o
r
d
U
n
i
v
e
r
s
i
t
y
P
r
e
ss,
2
0
2
1
.
d
o
i
:
1
0
.
1
0
9
3
/
h
e
p
l
/
9
7
8
0
1
9
8
8
5
0
2
9
8
.
0
0
1
.
0
0
0
1
.
[
1
9
]
J.
H
u
m
p
h
e
r
y
s
a
n
d
T
.
J.
J
a
r
v
i
s,
“
P
r
o
b
a
b
i
l
i
st
i
c
s
a
m
p
l
i
n
g
a
n
d
e
s
t
i
m
a
t
i
o
n
,
”
i
n
F
o
u
n
d
a
t
i
o
n
s
o
f
A
p
p
l
i
e
d
M
a
t
h
e
m
a
t
i
c
s
V
o
l
u
m
e
2
:
Al
g
o
r
i
t
h
m
s,
A
p
p
ro
x
i
m
a
t
i
o
n
,
O
p
t
i
m
i
z
a
t
i
o
n
,
J
.
H
u
m
p
h
e
r
y
s
a
n
d
T
.
J.
Jar
v
i
s,
Ed
s
.
,
P
h
i
l
a
d
e
l
p
h
i
a
,
P
A
:
S
o
c
i
e
t
y
f
o
r
I
n
d
u
s
t
r
i
a
l
a
n
d
A
p
p
l
i
e
d
M
a
t
h
e
m
a
t
i
c
s
,
2
0
2
0
,
p
p
.
2
4
5
–
2
8
0
,
.
d
o
i
:
1
0
.
1
1
3
7
/
1
.
9
7
8
1
6
1
1
9
7
6
0
6
9
.
c
h
6
.
[
2
0
]
S
.
Tü
me
n
A
k
y
i
l
d
i
z
a
n
d
K
.
H
.
A
h
m
e
d
,
“
A
n
o
v
e
r
v
i
e
w
o
f
q
u
a
l
i
t
a
t
i
v
e
r
e
s
e
a
r
c
h
a
n
d
f
o
c
u
s g
r
o
u
p
d
i
sc
u
ssi
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ac
a
d
e
m
i
c
Re
s
e
a
r
c
h
i
n
E
d
u
c
a
t
i
o
n
,
v
o
l
.
7
,
n
o
.
1
,
p
p
.
1
–
1
5
,
2
0
2
1
,
d
o
i
:
1
0
.
1
7
9
8
5
/
i
j
a
r
e
.
8
6
6
7
6
2
.
[
2
1
]
N
.
A
.
K
h
a
n
a
n
d
S
.
A
b
e
d
i
n
,
“
F
o
c
u
s
g
r
o
u
p
d
i
s
c
u
ssi
o
n
,
”
i
n
Pr
i
n
c
i
p
l
e
s
o
f
S
o
c
i
a
l
Re
s
e
a
r
c
h
M
e
t
h
o
d
o
l
o
g
y
,
S
i
n
g
a
p
o
r
e
:
S
p
r
i
n
g
e
r
N
a
t
u
r
e
S
i
n
g
a
p
o
r
e
,
2
0
2
2
,
p
p
.
3
7
7
–
3
8
7
,
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
19
-
5
4
4
1
-
2
_
2
6
.
[
2
2
]
I
.
A
l
i
,
A
.
A
z
m
a
n
,
S
.
M
a
l
l
i
c
k
,
T.
S
u
l
t
a
n
a
,
a
n
d
Z.
A
.
H
a
t
t
a
,
“
S
o
c
i
a
l
su
r
v
e
y
m
e
t
h
o
d
,
”
i
n
Pr
i
n
c
i
p
l
e
s o
f
S
o
c
i
a
l
R
e
se
a
r
c
h
Me
t
h
o
d
o
l
o
g
y
,
S
i
n
g
a
p
o
r
e
:
S
p
r
i
n
g
e
r
N
a
t
u
r
e
S
i
n
g
a
p
o
r
e
,
2
0
2
2
,
p
p
.
1
6
7
–
1
7
9
,
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
19
-
5
4
4
1
-
2
_
1
2
.
[
2
3
]
Z.
El
-
H
e
l
o
u
,
“
A
s
t
e
p
-
by
-
st
e
p
g
u
i
d
e
t
o
f
o
c
u
s
g
r
o
u
p
r
e
se
a
r
c
h
f
o
r
n
o
n
-
g
o
v
e
r
m
e
n
t
a
l
o
r
g
a
n
i
s
a
t
i
o
n
s.
”
p
.
9
3
,
2
0
1
2
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
w
w
w
.
N
G
O
c
o
n
n
e
c
t
.
n
e
t
[
2
4
]
D
.
X
a
n
t
h
i
d
i
s,
C
.
M
a
n
o
l
a
s
,
O
.
K
.
X
a
n
t
h
i
d
o
u
,
a
n
d
H
.
-
I
.
W
a
n
g
,
D
a
t
a
a
n
a
l
y
t
i
c
s
a
n
d
d
a
t
a
v
i
su
a
l
i
z
a
t
i
o
n
w
i
t
h
p
y
t
h
o
n
.
2
0
2
2
.
d
o
i
:
1
0
.
1
2
0
1
/
9
7
8
1
0
0
3
1
3
9
0
1
0
.
[
2
5
]
P
.
F
e
r
r
i
l
l
,
“
P
y
t
h
o
n
G
U
I
s
w
i
t
h
H
TM
L,
”
i
n
P
ro
An
d
r
o
i
d
Py
t
h
o
n
w
i
t
h
S
L
4
A
,
B
e
r
k
e
l
e
y
,
C
A
:
A
p
r
e
ss,
2
0
1
1
,
p
p
.
2
2
1
–
2
4
8
,
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
1
-
4
3
0
2
-
3
5
7
0
-
5
_
9
.
[
2
6
]
B
.
F
r
i
e
d
ma
n
a
n
d
D
.
G
.
H
e
n
d
r
y
,
Va
l
u
e
se
n
si
t
i
v
e
d
e
si
g
n
:
s
h
a
p
i
n
g
t
e
c
h
n
o
l
o
g
y
w
i
t
h
m
o
ra
l
i
m
a
g
i
n
a
t
i
o
n
,
v
o
l
.
1
2
,
n
o
.
1
.
Th
e
M
I
T
P
r
e
ss,
2
0
1
9
.
d
o
i
:
1
0
.
7
5
5
1
/
mi
t
p
r
e
ss/
7
5
8
5
.
0
0
1
.
0
0
0
1
.
[
2
7
]
M
.
S
a
d
e
k
,
M
.
C
o
n
st
a
n
t
i
n
i
d
e
s,
D
.
Q
u
e
r
c
i
a
,
a
n
d
C
.
M
o
u
g
e
n
o
t
,
“
G
u
i
d
e
l
i
n
e
s
f
o
r
i
n
t
e
g
r
a
t
i
n
g
v
a
l
u
e
se
n
s
i
t
i
v
e
d
e
si
g
n
i
n
r
e
s
p
o
n
s
i
b
l
e
A
I
t
o
o
l
k
i
t
s,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
C
H
I
C
o
n
f
e
re
n
c
e
o
n
H
u
m
a
n
Fa
c
t
o
rs
i
n
C
o
m
p
u
t
i
n
g
S
y
s
t
e
m
s
,
N
e
w
Y
o
r
k
,
N
Y
,
U
S
A
:
A
C
M
,
M
a
y
2
0
2
4
,
p
p
.
1
–
20
,
d
o
i
:
1
0
.
1
1
4
5
/
3
6
1
3
9
0
4
.
3
6
4
2
8
1
0
.
[
2
8
]
J
.
W
a
n
g
,
B
.
X
u
,
a
n
d
Y
.
Z
u
,
“
D
e
e
p
l
e
a
r
n
i
n
g
f
o
r
A
s
p
e
c
t
-
b
a
s
e
d
s
e
n
t
i
m
e
n
t
a
n
a
l
y
s
i
s
,
”
i
n
P
r
o
c
e
e
d
i
n
g
s
-
2
0
2
1
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
a
n
d
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s
E
n
g
i
n
e
e
r
i
n
g
,
M
L
I
S
E
2
0
2
1
,
2
0
2
1
,
p
p
.
2
6
7
–
2
7
1
,
d
o
i
:
1
0
.
1
1
0
9
/
M
L
I
S
E
5
4
0
9
6
.
2
0
2
1
.
0
0
0
5
6
.
[
2
9
]
G
.
E.
O
k
e
r
e
k
e
,
C
.
N
.
U
d
a
n
o
r
,
S
.
C
.
Ec
h
e
z
o
n
a
,
C
.
N
.
A
s
o
g
w
a
,
a
n
d
I
.
U
z
o
h
,
“
S
e
n
t
i
m
e
n
t
a
n
a
l
y
si
s
-
a
n
o
p
t
i
mi
z
e
d
w
e
i
g
h
t
e
d
h
o
r
i
z
o
n
t
a
l
e
n
s
e
m
b
l
e
a
p
p
r
o
a
c
h
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ad
v
a
n
c
e
d
T
r
e
n
d
s
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
3
,
n
o
.
2
,
p
p
.
7
2
–
7
9
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
3
0
5
3
4
/
i
j
a
t
c
se
/
2
0
2
4
/
0
6
1
3
2
2
0
2
4
.
[
3
0
]
K
.
M
.
S
a
g
a
r
e
t
a
l
.
,
“
M
u
l
t
i
C
l
a
ss
t
e
x
t
c
l
a
ssi
f
i
c
a
t
i
o
n
u
s
i
n
g
s
u
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
,
”
I
n
t
e
ra
n
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
S
c
i
e
n
t
i
f
i
c
R
e
se
a
rc
h
i
n
En
g
i
n
e
e
ri
n
g
a
n
d
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
0
7
,
n
o
.
1
2
,
p
p
.
1
–
1
0
,
2
0
2
3
,
d
o
i
:
1
0
.
5
5
0
4
1
/
i
j
sr
e
m
2
7
4
6
5
.
[
3
1
]
M
.
D
e
p
r
e
z
a
n
d
E.
C
.
R
o
b
i
n
s
o
n
,
“
C
l
a
ssi
f
i
c
a
t
i
o
n
,
”
i
n
M
a
c
h
i
n
e
L
e
a
rn
i
n
g
f
o
r
Bi
o
m
e
d
i
c
a
l
Ap
p
l
i
c
a
t
i
o
n
s
,
El
s
e
v
i
e
r
,
2
0
2
4
,
p
p
.
8
7
–
1
0
4
,
.
d
o
i
:
1
0
.
1
0
1
6
/
B
9
7
8
-
0
-
12
-
8
2
2
9
0
4
-
0
.
0
0
0
0
9
-
1.
[
3
2
]
S
.
A
l
i
a
n
d
K
.
A
.
S
mi
t
h
-
M
i
l
e
s,
“
A
met
a
-
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
t
o
a
u
t
o
mat
i
c
k
e
r
n
e
l
s
e
l
e
c
t
i
o
n
f
o
r
su
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
s,
”
N
e
u
ro
c
o
m
p
u
t
i
n
g
,
v
o
l
.
7
0
,
n
o
.
1
–
3
,
p
p
.
1
7
3
–
1
8
6
,
2
0
0
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m.2
0
0
6
.
0
3
.
0
0
4
.
[
3
3
]
J.
A
.
B
e
n
e
d
i
k
t
sso
n
,
J.
K
i
t
t
l
e
r
,
a
n
d
F
.
R
o
l
i
,
Mu
l
t
i
p
l
e
c
l
a
ss
i
f
i
e
r
s
y
st
e
m
s
,
v
o
l
.
5
5
1
9
.
i
n
L
e
c
t
u
r
e
N
o
t
e
s
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
5
5
1
9
,
B
e
r
l
i
n
,
H
e
i
d
e
l
b
e
r
g
:
S
p
r
i
n
g
e
r
B
e
r
l
i
n
H
e
i
d
e
l
b
e
r
g
,
2
0
0
9
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
642
-
0
2
3
2
6
-
2.
[
3
4
]
V
.
M
.
B
.
B
a
t
t
a
,
“
H
u
ma
n
l
a
n
g
u
a
g
e
d
a
t
a
p
r
o
c
e
ssi
n
g
u
s
i
n
g
N
LT
K
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
d
Re
s
e
a
rc
h
i
n
S
c
i
e
n
c
e
,
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
4
,
n
o
.
6
,
p
p
.
6
2
8
–
6
3
4
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
4
8
1
7
5
/
I
JA
R
S
C
T
-
1
7
6
8
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
V
a
lu
e
g
r
o
u
p
cla
s
s
ifier
mo
d
el
fo
r
eth
ica
l d
ec
is
io
n
-
ma
kin
g
(
S
h
w
eta
B
h
a
tn
a
g
a
r
)
1907
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
S
h
we
ta
Bh
a
t
n
a
g
a
r
is
a
n
a
c
a
d
e
m
icia
n
with
a
n
e
x
p
e
rien
c
e
o
v
e
r
a
d
e
c
a
d
e
in
e
d
u
c
a
ti
o
n
a
d
m
in
istrati
o
n
a
t
v
a
ri
o
u
s
p
u
b
li
c
a
n
d
p
ri
v
a
te
o
rg
a
n
iza
ti
o
n
s.
S
h
e
is
a
P
h
.
D
.
stu
d
e
n
t
of
th
e
F
a
c
u
lt
y
o
f
C
o
m
p
u
ter
Ap
p
li
c
a
ti
o
n
s
a
t
M
a
n
a
v
Ra
c
h
n
a
In
ter
n
a
ti
o
n
a
l
In
st
it
u
te
o
f
Re
se
a
rc
h
S
tu
d
ies
.
He
r
f
ield
o
f
re
se
a
rc
h
is
e
d
u
c
a
ti
o
n
tec
h
n
o
l
o
g
y
.
S
h
e
c
a
n
b
e
c
o
n
t
a
c
ted
a
t
sh
we
tab
h
a
tn
a
g
a
r
9
9
@g
m
a
il
.
c
o
m
.
Dr
.
Ra
shm
i
Ag
r
a
wa
l
is
P
h
.
D
.
a
n
d
UG
C
-
NET
q
u
a
li
f
ied
with
2
0
y
e
a
rs
o
f
e
x
p
e
rien
c
e
in
tea
c
h
in
g
a
n
d
re
se
a
rc
h
,
wo
rk
in
g
a
s
P
ro
fe
ss
o
r
in
De
p
a
rtme
n
t
o
f
Co
m
p
u
te
r
Ap
p
li
c
a
ti
o
n
s,
M
a
n
a
v
Ra
c
h
n
a
I
n
te
rn
a
ti
o
n
a
l
In
stit
u
te
o
f
Re
se
a
rc
h
a
n
d
S
t
u
d
ies
,
F
a
ri
d
a
b
a
d
,
In
d
ia.
S
h
e
is
a
ss
o
c
iate
d
with
v
a
rio
u
s
p
ro
fe
ss
io
n
a
l
b
o
d
ies
in
d
iffere
n
t
c
a
p
a
c
it
ies
,
li
fe
m
e
m
b
e
r
o
f
Co
m
p
u
ter
S
o
c
iety
o
f
In
d
ia
a
n
d
se
n
io
r
m
e
m
b
e
r
o
f
IEE
E
.
S
h
e
is
b
o
o
k
se
ries
e
d
it
o
r
o
f
In
n
o
v
a
ti
o
n
s
i
n
Big
Da
ta
a
n
d
M
a
c
h
in
e
Lea
rn
in
g
,
CRC
P
re
ss
,
Tay
l
o
r
a
n
d
F
ra
n
c
is
g
r
o
u
p
,
USA
a
n
d
Ad
v
a
n
c
e
s
in
C
y
b
e
rse
c
u
rit
y
i
n
W
il
e
y
.
S
h
e
h
a
s
a
u
th
o
re
d
/co
-
a
u
t
h
o
re
d
m
a
n
y
re
se
a
rc
h
p
a
p
e
rs
in
p
e
e
r
re
v
iew
e
d
n
a
ti
o
n
a
l
/
in
tern
a
ti
o
n
a
l
jo
u
rn
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s
wh
ich
a
re
S
CI/S
CIE/
E
S
CI/S
COPUS
in
d
e
x
e
d
.
S
h
e
h
a
s
a
lso
e
d
it
e
d
/au
t
h
o
re
d
b
o
o
k
s
wit
h
n
a
ti
o
n
a
l/
in
ter
n
a
ti
o
n
a
l
p
u
b
li
s
h
e
rs
(S
p
rin
g
e
r,
El
se
v
ier,
IG
I
G
lo
b
a
l,
Ap
p
le
Ac
a
d
e
m
ic
P
re
ss
,
a
n
d
CRC
P
re
ss
)
a
n
d
c
o
n
tr
ib
u
ted
c
h
a
p
ters
in
b
o
o
k
s.
C
u
rre
n
tl
y
sh
e
is
g
u
i
d
in
g
P
h
.
D
.
sc
h
o
lars
in
se
n
ti
m
e
n
t
a
n
a
ly
sis,
e
d
u
c
a
ti
o
n
a
l
d
a
ta
m
in
in
g
,
i
n
tern
e
t
o
f
t
h
i
n
g
s,
b
r
a
in
c
o
m
p
u
ter
i
n
terfa
c
e
a
n
d
n
a
tu
ra
l
la
n
g
u
a
g
e
p
ro
c
e
ss
in
g
.
S
h
e
is
As
so
c
iate
E
d
it
o
r
i
n
J
o
u
r
n
a
l
o
f
En
g
in
e
e
ri
n
g
a
n
d
Ap
p
li
e
d
S
c
ien
c
e
s a
n
d
Arra
y
Jo
u
rn
a
l
,
El
se
v
ier.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
d
rra
sh
m
iag
ra
wa
l7
8
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.