I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
1
5
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
,
p
p
.
604
~
614
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
15
.i
1
.
p
p
6
0
4
-
6
1
4
604
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Web
-
ba
sed g
eo
t
h
erma
l drilling
st
u
ck pipe
predic
tio
n using
decisio
n t
re
e alg
o
rithm
Ro
s
y
iha
n M
u
hta
dlo
r
1
,
Nur
Ro
hm
a
n Ro
s
y
id
1
,
Anni
K
a
rim
a
t
ul F
a
uziy
y
a
h
1
,
L
a
lu H
endra
P
er
m
a
na
Set
ia
wa
n
2
,
I
rf
a
n Sa
pu
t
ra
2
,
P
a
v
el
Sta
s
a
3
,
F
ilip
B
enes
3
,
M
u
ha
m
m
a
d Sy
a
f
rudin
4
,
G
a
nja
r
Alf
ia
n
1
1
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
a
n
d
I
n
f
o
r
m
a
t
i
c
s,
V
o
c
a
t
i
o
n
a
l
C
o
l
l
e
g
e
,
U
n
i
v
e
r
si
t
a
s
G
a
d
j
a
h
M
a
d
a
,
S
l
e
m
a
n
,
I
n
d
o
n
e
s
i
a
2
P
T.
P
a
r
a
ma
D
a
t
a
U
n
i
t
,
J
a
k
a
r
t
a
,
I
n
d
o
n
e
si
a
3
D
e
p
a
r
t
me
n
t
o
f
Ec
o
n
o
m
i
c
s
a
n
d
C
o
n
t
r
o
l
S
y
s
t
e
ms
,
F
a
c
u
l
t
y
o
f
M
i
n
i
n
g
a
n
d
G
e
o
l
o
g
y
,
V
S
B
-
T
e
c
h
n
i
c
a
l
U
n
i
v
e
r
s
i
t
y
o
f
O
st
r
a
v
a
,
O
st
r
a
v
a
,
C
z
e
c
h
R
e
p
u
b
l
i
c
4
D
e
p
a
r
t
me
n
t
o
f
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
D
a
t
a
S
c
i
e
n
c
e
,
S
e
j
o
n
g
U
n
i
v
e
r
si
t
y
,
S
e
o
u
l
,
R
e
p
u
b
l
i
c
o
f
K
o
r
e
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
3
0
,
2
0
2
4
R
ev
is
ed
Dec
2
8
,
2
0
2
5
Acc
ep
ted
J
an
1
0
,
2
0
2
6
In
g
e
o
th
e
rm
a
l
d
ril
li
n
g
o
p
e
ra
ti
o
n
s,
d
a
ta
fro
m
ri
g
-
m
o
u
n
ted
se
n
so
rs
p
lay
a
c
ru
c
ial
ro
le
i
n
m
a
i
n
tain
i
n
g
o
p
e
ra
ti
o
n
a
l
e
fficie
n
c
y
a
n
d
p
re
v
e
n
t
in
g
d
ril
li
n
g
fa
il
u
re
s.
Ho
we
v
e
r,
se
n
so
r
u
n
c
e
rt
a
in
ti
e
s
a
n
d
c
o
m
p
lex
su
b
su
rfa
c
e
c
o
n
d
i
ti
o
n
s
c
a
n
lea
d
to
stu
c
k
p
i
p
e
i
n
c
id
e
n
ts,
c
a
u
sin
g
sig
n
ifi
c
a
n
t
n
o
n
-
p
r
o
d
u
c
ti
v
e
ti
m
e
a
n
d
fin
a
n
c
ial
l
o
ss
e
s.
T
h
is
st
u
d
y
p
r
o
p
o
se
s
we
b
-
b
a
se
d
d
ril
li
n
g
m
o
n
it
o
ri
n
g
sy
ste
m
in
teg
ra
ted
wit
h
m
a
c
h
in
e
lea
rn
in
g
(M
L)
to
p
re
d
ict
stu
c
k
p
i
p
e
o
c
c
u
rre
n
c
e
s
in
g
e
o
th
e
rm
a
l
d
ril
l
in
g
.
S
e
v
e
ra
l
M
L
a
lg
o
rit
h
m
s
—
d
e
c
isio
n
tree
(DT),
ra
n
d
o
m
fo
re
st
(RF
)
,
n
a
ïv
e
Ba
y
e
s
(NB),
m
u
lt
il
a
y
e
r
p
e
rc
e
p
tro
n
(M
LP
)
,
a
n
d
s
u
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(S
VM)
—
we
re
e
v
a
lu
a
ted
u
sin
g
g
e
o
t
h
e
rm
a
l
d
ril
l
in
g
d
a
ta
fro
m
a
n
In
d
o
n
e
sia
n
g
e
o
t
h
e
rm
a
l
p
r
o
jec
t
c
o
n
d
u
c
ted
i
n
2
0
2
3
.
T
o
a
d
d
r
e
ss
c
las
s
imb
a
lan
c
e
,
th
e
sy
n
th
e
ti
c
m
i
n
o
rit
y
o
v
e
rsa
m
p
li
n
g
tec
h
n
i
q
u
e
(
S
M
OTE)
wa
s
a
p
p
li
e
d
t
o
th
e
trai
n
in
g
d
a
tas
e
t.
F
e
a
tu
re
se
lec
ti
o
n
wa
s
p
e
rfo
rm
e
d
u
sin
g
t
h
e
c
o
rre
latio
n
c
o
e
fficie
n
t
m
e
th
o
d
,
a
n
d
p
re
d
ictio
n
s
we
re
g
e
n
e
ra
ted
u
sin
g
a
5
-
m
in
u
te
slid
i
n
g
win
d
o
w
.
Am
o
n
g
th
e
e
v
a
lu
a
ted
m
o
d
e
ls,
t
h
e
DT
c
o
n
siste
n
tl
y
d
e
m
o
n
stra
ted
su
p
e
rio
r
p
e
rfo
rm
a
n
c
e
a
c
ro
ss
m
u
lt
ip
le
p
re
d
icti
o
n
h
o
rizo
n
s
(P
H)
,
a
c
h
iev
in
g
a
n
a
c
c
u
ra
c
y
o
f
9
7
.
4
%
,
p
re
c
isio
n
o
f
9
8
.
6
%
,
re
c
a
ll
o
f
7
2
.
9
%
,
a
n
d
a
ROC
-
AU
C
o
f
0
.
7
2
9
u
si
n
g
th
e
to
p
fi
v
e
se
lec
ted
fe
a
tu
re
s.
T
h
e
train
e
d
m
o
d
e
l
wa
s
in
teg
ra
ted
in
to
we
b
-
b
a
se
d
m
o
n
it
o
rin
g
p
latf
o
rm
th
a
t
p
ro
v
id
e
s
v
isu
a
li
z
a
ti
o
n
a
n
d
p
re
d
icti
v
e
a
lerts.
Th
is
sy
ste
m
e
n
a
b
les
e
a
rly
d
e
tec
ti
o
n
a
n
d
b
e
tt
e
r
d
e
c
isio
n
-
m
a
k
in
g
,
h
e
l
p
in
g
imp
ro
v
e
d
ri
ll
in
g
e
fficie
n
c
y
,
re
d
u
c
e
stu
c
k
p
ip
e
ris
k
s,
a
n
d
e
n
h
a
n
c
e
o
p
e
ra
ti
o
n
a
l
sa
fe
ty
.
K
ey
w
o
r
d
s
:
Dec
is
io
n
tr
ee
s
Dr
illi
n
g
Geo
th
er
m
als
Ma
ch
in
e
lear
n
in
g
Stu
ck
p
ip
e
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
:
Gan
jar
Alf
ian
Dep
ar
tm
en
t o
f
E
lectr
ical
E
n
g
i
n
ee
r
in
g
a
n
d
I
n
f
o
r
m
atics,
Vo
ca
tio
n
al
C
o
lleg
e,
Un
iv
er
s
itas
Gad
jah
Ma
d
a
St
.
Yac
ar
an
d
a,
Dep
o
k
,
Slem
an
,
Yo
g
y
ak
a
r
ta
5
5
2
8
1
,
I
n
d
o
n
esi
a
E
m
ail: g
an
jar
.
alf
ian
@
u
g
m
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
Geo
th
er
m
al
en
er
g
y
is
d
er
iv
ed
f
r
o
m
th
e
e
ar
th
'
s
in
ter
n
al
h
ea
t,
wh
ich
is
co
n
tin
u
ally
g
en
er
ate
d
th
r
o
u
g
h
th
e
r
ad
io
ac
tiv
e
d
ec
ay
o
f
is
o
to
p
es
with
in
th
e
cr
u
s
t
an
d
m
a
n
tle.
T
h
is
h
ea
t
ca
n
b
e
tr
an
s
f
e
r
r
ed
to
th
e
s
u
r
f
ac
e
th
r
o
u
g
h
th
er
m
al
co
n
d
u
ctio
n
a
n
d
s
u
b
s
u
r
f
ac
e
f
lu
id
ci
r
cu
latio
n
,
m
ak
in
g
it
ac
ce
s
s
ib
le
f
o
r
e
n
er
g
y
a
p
p
licatio
n
s
d
ep
en
d
i
n
g
o
n
g
e
o
lo
g
ical
co
n
d
itio
n
s
[
1
]
.
T
o
h
ar
n
ess
th
is
en
er
g
y
,
wellb
o
r
es
m
u
s
t
b
e
d
r
illed
to
estab
lis
h
f
lo
w
p
ath
way
s
co
n
n
ec
tin
g
th
e
s
u
r
f
ac
e
with
s
u
b
s
u
r
f
ac
e
g
eo
t
h
er
m
al
r
eser
v
o
ir
s
[
2
]
.
Ge
o
th
er
m
al
d
r
illi
n
g
aim
s
to
ac
ce
s
s
s
u
b
s
u
r
f
ac
e
th
er
m
al
r
eser
v
o
ir
s
b
u
t
f
ac
es
n
u
m
er
o
u
s
o
p
er
atio
n
al
ch
allen
g
es,
in
clu
d
i
n
g
h
ar
d
an
d
a
b
r
asiv
e
r
o
ck
f
o
r
m
atio
n
s
,
h
ig
h
tem
p
er
a
tu
r
es,
an
d
s
ev
er
e
f
lu
id
lo
s
s
es,
wh
ich
o
f
ten
r
esu
lt
in
s
tu
ck
p
i
p
es
an
d
s
ig
n
if
ican
t
co
s
t
o
v
er
r
u
n
s
[
3
]
.
Giv
en
th
e
u
n
ce
r
tain
an
d
co
m
p
lex
n
atu
r
e
o
f
s
u
b
s
u
r
f
ac
e
co
n
d
itio
n
s
,
h
is
to
r
ical
d
ata
f
r
o
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Web
-
b
a
s
ed
g
e
o
th
erma
l d
r
illi
n
g
s
tu
ck
p
ip
e
p
r
ed
ictio
n
u
s
in
g
d
ec
is
io
n
tr
ee
a
lg
o
r
ith
m
(
R
o
s
yi
h
a
n
Mu
h
t
a
d
lo
r
)
605
p
r
ev
io
u
s
d
r
illi
n
g
b
ec
o
m
es
h
i
g
h
ly
v
alu
a
b
le,
ev
e
n
th
o
u
g
h
it
m
ay
n
o
t
co
v
e
r
all
p
o
s
s
ib
le
s
ce
n
ar
io
s
.
T
h
e
r
ef
o
r
e
,
s
im
u
latio
n
an
d
ex
p
er
im
e
n
tal
ap
p
r
o
ac
h
es
ca
n
co
m
p
lem
en
t
an
d
en
r
ich
th
e
in
f
o
r
m
atio
n
p
r
o
v
id
ed
b
y
h
is
to
r
ical
d
ata
to
s
u
p
p
o
r
t
m
o
r
e
ac
c
u
r
at
e
d
ec
is
io
n
-
m
ak
in
g
in
d
r
illi
n
g
o
p
er
atio
n
s
[
4
]
.
T
h
ese
d
ata
ca
n
b
e
u
tili
ze
d
with
p
r
o
v
e
n
ef
f
ec
tiv
e
a
p
p
r
o
a
ch
es
s
u
ch
as
an
o
f
f
s
h
o
o
t
o
f
ar
tifi
cial
in
tellig
en
ce
(
AI
)
,
n
am
el
y
m
ac
h
in
e
lear
n
in
g
(
ML
)
,
to
p
r
ev
e
n
t
s
tu
ck
p
ip
es
in
d
r
illi
n
g
.
T
h
is
ap
p
r
o
ac
h
en
a
b
les
p
r
ed
ictio
n
o
f
s
tu
ck
p
i
p
e
s
o
th
at
p
r
ev
en
tiv
e
ac
tio
n
ca
n
b
e
tak
en
,
r
esu
ltin
g
i
n
m
o
r
e
ec
o
n
o
m
ical
d
r
illi
n
g
c
o
s
ts
[
5
]
.
Pre
v
io
u
s
s
tu
d
y
p
r
o
p
o
s
ed
class
if
icatio
n
ML
m
o
d
els,
n
am
ely
d
ec
is
io
n
tr
ee
(
DT
)
w
h
ich
was
co
m
p
ar
ed
with
lo
g
is
tic
r
eg
r
ess
io
n
(
L
R
)
,
an
d
n
aï
v
e
B
ay
es
(
NB
)
.
T
h
ese
m
o
d
els
wer
e
ch
o
s
en
f
o
r
th
eir
s
im
p
licity
,
s
u
itab
ilit
y
to
lar
g
e
d
atasets
,
f
a
s
t tr
ain
in
g
tim
e,
an
d
g
o
o
d
p
r
e
d
ictiv
e
ab
ilit
y
[
6
]
–
[
1
0
]
.
I
n
ad
d
itio
n
,
DT
m
o
d
el
h
as
s
ev
er
al
ad
v
an
tag
es
c
o
m
p
ar
e
d
to
r
an
d
o
m
f
o
r
est
(
R
F)
ev
en
th
o
u
g
h
R
F
is
a
co
m
b
in
atio
n
o
f
m
an
y
DT
,
n
am
ely
f
aster
d
ata
tr
ain
in
g
an
d
d
ec
is
io
n
m
ak
i
n
g
.
T
h
is
is
s
u
itab
le
f
o
r
th
e
ca
s
e
o
f
clo
g
g
ed
p
i
p
e
p
r
e
d
ictio
n
,
wh
ich
m
u
s
t
b
e
d
o
n
e
in
r
ea
l
-
tim
e,
r
eq
u
ir
i
n
g
s
p
ee
d
in
m
o
d
elin
g
an
d
p
r
ed
ictio
n
[
1
1
]
.
I
n
ad
d
itio
n
,
s
lid
in
g
win
d
o
w
an
d
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
s
wer
e
also
ad
d
ed
to
im
p
r
o
v
e
th
e
p
e
r
f
o
r
m
a
n
ce
o
f
p
r
ed
ictio
n
m
o
d
el
[
1
2
]
,
[
1
3
]
.
Pre
v
io
u
s
s
tu
d
ies
h
av
e
ex
p
lo
r
e
d
th
e
u
s
e
o
f
ML
m
o
d
els
to
p
r
e
d
ict
s
tu
ck
p
ip
e
in
cid
e
n
ts
,
an
d
t
ec
h
n
iq
u
es
s
u
ch
as
s
lid
in
g
win
d
o
ws
an
d
f
ea
tu
r
e
s
elec
tio
n
h
av
e
also
p
r
o
d
u
ce
d
e
n
co
u
r
ag
in
g
o
u
tco
m
e
s
.
Nev
er
th
eless
,
n
o
p
r
io
r
s
tu
d
y
h
as
co
m
b
in
e
d
t
h
ese
th
r
ee
elem
en
ts
—
ML
m
o
d
els,
s
lid
in
g
win
d
o
w
tech
n
iq
u
es,
an
d
f
ea
tu
r
e
s
elec
tio
n
—
with
in
a
web
-
b
ased
m
o
n
ito
r
i
n
g
p
latf
o
r
m
th
at
d
eliv
er
s
p
r
ed
ictiv
e
in
s
ig
h
ts
to
d
r
illi
n
g
o
p
er
at
o
r
s
.
T
h
is
s
tu
d
y
s
ee
k
s
to
d
ev
elo
p
s
u
ch
a
s
y
s
tem
,
w
h
ich
in
clu
d
es
aler
t
n
o
tific
atio
n
s
g
e
n
er
ated
f
r
o
m
ML
p
r
ed
ictio
n
s
an
d
lin
e
-
g
r
a
p
h
v
is
u
aliza
tio
n
s
o
f
d
r
illi
n
g
p
ar
am
eter
s
to
s
u
p
p
o
r
t
clea
r
er
in
ter
p
r
etatio
n
an
d
an
aly
s
is
.
T
h
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
is
an
ticip
ated
to
en
h
an
ce
th
e
ef
f
icien
c
y
o
f
g
eo
t
h
er
m
al
d
r
illi
n
g
o
p
er
atio
n
s
b
y
e
n
ab
lin
g
ac
cu
r
ate
d
etec
tio
n
o
f
s
tu
ck
p
ip
e
r
is
k
s
an
d
r
ed
u
cin
g
p
o
ten
tial
o
p
er
atio
n
al
lo
s
s
es.
2.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
Kh
an
et
a
l
.
[
1
4
]
ex
am
i
n
ed
t
h
e
u
tili
za
tio
n
o
f
ML
f
o
r
s
tu
ck
p
ip
es
in
o
il
d
r
illi
n
g
.
T
h
is
r
esear
ch
u
s
es
ar
tific
ial
n
eu
r
al
n
etwo
r
k
(
AN
N)
an
d
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM)
m
eth
o
d
s
.
B
ased
o
n
th
e
r
esear
ch
,
it
was
co
n
clu
d
e
d
th
at
ANN
is
b
etter
th
an
SVM
with
8
8
.
8
9
%
ac
cu
r
ac
y
,
9
1
.
8
9
%
r
ec
all,
an
d
8
6
.
3
6
%
s
p
ec
if
icity
.
Qo
d
ir
o
v
an
d
Sh
estak
o
v
[
1
5
]
u
s
ed
ANN
an
d
s
lid
in
g
win
d
o
w
m
eth
o
d
s
.
T
h
is
s
tu
d
y
co
n
cl
u
d
e
d
th
at
th
e
ac
c
u
r
ac
y
o
f
th
e
ANN
m
o
d
el
with
a
s
lid
in
g
win
d
o
w
r
ea
ch
ed
8
6
%.
T
h
e
p
r
e
d
ictio
n
m
o
d
el
b
u
ilt
ca
n
b
e
u
s
ed
in
th
e
well
d
r
illi
n
g
p
r
o
ce
s
s
to
m
in
im
ize
th
e
r
is
k
o
f
s
tu
ck
p
ip
es.
Stu
d
y
c
o
n
d
u
cte
d
b
y
E
lm
o
u
s
alam
i
an
d
E
lask
ar
y
[
1
6
]
u
s
ed
k
-
n
ea
r
est n
eig
h
b
o
r
s
(
KNN)
,
DT
,
R
F,
ex
tr
em
ely
r
an
d
o
m
ized
tr
ee
s
(
ex
tr
a
tr
ee
s
)
,
NB
,
S
VM
,
LR
,
ANN,
ex
tr
em
e
g
r
ad
ien
t
b
o
o
s
tin
g
(
XGBo
o
s
t)
,
ad
a
p
tiv
e
b
o
o
s
tin
g
(
Ad
aBo
o
s
t
)
,
an
d
s
to
ch
asti
c
g
r
ad
ie
n
t
b
o
o
s
tin
g
(
SGB
)
m
eth
o
d
s
.
So
m
e
alg
o
r
ith
m
s
ad
d
h
y
p
er
p
a
r
am
eter
s
s
o
t
h
at
th
e
r
esu
lts
b
ec
o
m
e
m
o
r
e
o
p
tim
al.
Fro
m
th
e
s
tu
d
y
,
i
t
was c
o
n
clu
d
ed
th
at
e
x
tr
a
tr
ee
s
p
r
o
v
i
d
ed
th
e
b
est cla
s
s
if
icatio
n
ac
cu
r
ac
y
o
f
1
0
0
%.
E
lah
if
ar
an
d
Ho
s
s
ein
i
[
1
7
]
co
n
d
u
cted
r
esear
ch
o
n
th
e
p
r
e
d
ictio
n
o
f
s
tu
ck
p
ip
e
d
r
illi
n
g
in
c
ase
s
tu
d
ies
o
f
d
ir
ec
tio
n
al
an
d
v
e
r
tical
d
r
illi
n
g
in
th
e
Mid
d
le
E
ast
o
il
f
ield
s
.
T
h
e
m
eth
o
d
u
s
ed
in
th
e
r
esear
ch
is
AN
N
co
m
b
in
ed
with
p
ar
ticle
s
war
m
o
p
tim
izatio
n
(
PS
O)
.
T
h
e
r
esu
lts
o
f
th
is
s
tu
d
y
r
esu
lted
in
an
ac
cu
r
ac
y
o
f
8
4
.
6
1
%
f
o
r
d
ir
ec
tio
n
al
wells
an
d
8
0
%
f
o
r
v
er
tical
wells.
Sh
ad
izad
eh
[
1
8
]
p
r
o
p
o
s
ed
s
o
lu
tio
n
to
a
d
d
r
ess
th
e
s
tu
ck
p
ip
e
is
s
u
e
in
o
il
f
ield
d
r
illi
n
g
in
I
r
an
in
v
o
lv
ed
u
s
in
g
an
ANN.
T
h
e
s
tu
d
y
d
em
o
n
s
tr
ated
th
at
th
e
ANN
m
o
d
el
ac
h
iev
e
d
9
5
%
ac
cu
r
ac
y
in
test
in
g
an
d
v
alid
atin
g
d
ata
f
o
r
d
y
n
am
ic
d
r
illi
n
g
,
a
n
d
o
v
er
9
3
%
ac
cu
r
ac
y
f
o
r
s
tatic
d
r
illi
n
g
.
Xian
an
d
Yan
g
[
1
9
]
d
is
cu
s
s
ed
a
m
o
d
el
f
o
r
e
ar
ly
war
n
in
g
wh
en
a
d
r
illi
n
g
j
am
will
o
cc
u
r
.
T
h
e
m
eth
o
d
s
u
s
ed
in
t
h
e
s
tu
d
y
wer
e
SVM,
PS
O,
tr
ad
itio
n
al
cr
o
s
s
-
v
alid
atio
n
(
C
V)
,
an
d
ar
tific
ial
f
is
h
s
war
m
alg
o
r
ith
m
(
AFSA).
T
h
e
r
esu
lt
s
o
f
th
e
s
tu
d
y
co
n
cl
u
d
ed
th
at
th
e
SVM
m
o
d
el
co
m
b
in
e
d
with
AFSA
ac
h
iev
ed
th
e
h
ig
h
est
ac
cu
r
ac
y
o
f
9
3
.
4
7
%.
B
ased
o
n
th
e
r
ev
iewe
d
liter
atu
r
e,
n
o
p
r
io
r
r
esear
ch
h
as
in
teg
r
ated
th
ese
f
o
u
r
co
m
p
o
n
en
ts
—
ML
m
o
d
els,
s
lid
in
g
win
d
o
w
tech
n
iq
u
es,
f
ea
tu
r
e
s
elec
tio
n
,
a
n
d
h
an
d
li
n
g
p
o
ten
tially
im
b
alan
ce
d
d
atasets
—
in
to
a
u
n
if
ied
web
-
b
ased
m
o
n
ito
r
in
g
p
latf
o
r
m
th
at
p
r
o
v
id
es
p
r
e
d
ictiv
e
in
s
ig
h
ts
f
o
r
d
r
illi
n
g
o
p
er
atio
n
s
.
T
h
er
ef
o
r
e,
th
is
s
tu
d
y
in
tr
o
d
u
ce
s
s
ev
er
al
s
tr
ate
g
ies,
in
clu
d
in
g
ev
alu
atin
g
f
e
atu
r
e
s
elec
tio
n
to
d
eter
m
in
e
th
e
o
p
tim
al
s
et
o
f
f
ea
tu
r
es,
ad
d
r
ess
in
g
p
o
ten
tial
d
ata
im
b
alan
ce
to
im
p
r
o
v
e
m
o
d
el
p
er
f
o
r
m
a
n
ce
,
an
d
im
p
lem
e
n
tin
g
th
e
t
r
ain
ed
p
r
ed
ictiv
e
m
o
d
el
with
in
a
web
-
b
ased
in
f
o
r
m
atio
n
s
y
s
tem
to
s
u
p
p
o
r
t
d
ec
is
io
n
-
m
ak
in
g
an
d
en
h
a
n
ce
d
r
illi
n
g
ef
f
icien
c
y
.
3.
M
E
T
H
O
DO
L
O
G
Y
Fig
u
r
e
1
s
h
o
ws
th
e
s
tag
es
o
f
th
e
p
r
o
p
o
s
ed
s
tu
d
y
th
at
in
v
o
lv
ed
d
e
v
elo
p
in
g
a
g
e
o
th
er
m
al
d
r
illi
n
g
s
tu
ck
p
ip
e
p
r
ed
ictio
n
s
y
s
tem
,
s
tar
tin
g
with
p
r
o
b
lem
an
d
g
o
al
id
e
n
tific
atio
n
,
d
at
a
co
llectio
n
,
d
ata
p
r
ep
r
o
ce
s
s
in
g
,
m
o
d
el
s
elec
tio
n
,
m
o
d
el
ev
alu
atio
n
,
an
d
m
o
d
el
d
ep
lo
y
m
en
t.
I
n
th
e
d
ata
p
r
ep
r
o
ce
s
s
in
g
s
tag
e,
th
e
s
lid
in
g
win
d
o
w
an
d
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
s
ar
e
r
e
f
in
ed
.
T
h
is
r
ef
in
e
m
en
t
is
ac
h
ie
v
ed
b
y
c
o
m
p
a
r
in
g
s
ev
er
al
m
ea
s
u
r
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
:
604
-
6
1
4
606
Fig
u
r
e
1
.
T
h
e
f
lo
wch
a
r
t o
f
p
r
o
p
o
s
ed
s
tu
d
y
f
o
r
d
r
illi
n
g
p
r
ed
ic
tio
n
3
.
1
.
Da
t
a
c
o
llect
io
n
Data
co
llectio
n
ca
n
b
e
in
te
r
p
r
eted
as
th
e
ac
tiv
ity
o
f
co
llectin
g
ac
cu
r
ate
an
d
r
elev
a
n
t
in
f
o
r
m
atio
n
f
o
r
r
esear
ch
[
2
0
]
.
T
h
is
s
tu
d
y
u
til
izes
a
tim
e
s
er
ie
s
d
ataset
o
n
g
eo
th
er
m
al
d
r
illi
n
g
f
r
o
m
a
g
eo
th
er
m
al
d
r
illi
n
g
co
m
p
an
y
in
I
n
d
o
n
esia.
T
h
e
co
m
p
an
y
s
p
ec
ializes
in
m
u
d
lo
g
g
in
g
,
d
i
r
ec
tio
n
al
d
r
illi
n
g
,
an
d
d
r
illi
n
g
f
lu
id
s
.
T
h
e
d
ataset
em
p
lo
y
ed
in
t
h
is
r
esear
ch
is
d
er
iv
ed
f
r
o
m
r
ec
o
r
d
in
g
s
ca
p
tu
r
ed
b
y
in
ter
n
et
o
f
t
h
in
g
s
(
I
o
T
)
s
en
s
o
r
s
.
T
h
e
s
en
s
o
r
r
ec
o
r
d
s
d
r
illi
n
g
d
ata
in
1
0
-
s
ec
o
n
d
in
te
r
v
als
wh
ich
a
r
e
th
en
s
en
t
t
o
th
e
s
er
v
er
s
id
e.
T
h
is
s
tu
d
y
u
s
es
th
e
d
r
illi
n
g
d
ataset
f
r
o
m
well
“A”
wh
ich
h
as
2
3
f
ea
tu
r
es
an
d
3
3
9
,
0
6
5
r
o
ws
o
f
d
ata
tak
e
n
o
n
J
u
n
e
0
2
,
2
0
2
3
,
to
J
u
ly
1
1
,
2
0
2
3
.
T
h
e
lab
el
o
n
th
e
d
ataset
is
k
n
o
wn
to
co
n
s
is
t
o
f
two
class
es,
n
am
ely
n
o
r
m
a
l
an
d
s
tu
ck
d
r
illi
n
g
.
T
h
e
d
ataset
is
im
b
alan
ce
d
,
wi
th
th
e
n
o
r
m
al
d
r
illi
n
g
class
ac
co
u
n
tin
g
f
o
r
9
2
.
5
2
%
an
d
t
h
e
s
tu
ck
d
r
illi
n
g
class
r
ep
r
esen
tin
g
o
n
ly
7
.
4
8
%.
Su
c
h
an
im
b
alan
ce
ca
n
lead
ML
m
o
d
els
to
b
ec
o
m
e
b
iased
to
war
d
th
e
m
aj
o
r
ity
class
,
r
esu
ltin
g
in
p
o
o
r
p
r
ed
ict
iv
e
p
er
f
o
r
m
a
n
ce
f
o
r
th
e
m
i
n
o
r
ity
class
,
wh
ich
in
th
is
ca
s
e
r
e
p
r
esen
ts
th
e
cr
itical
s
tu
ck
d
r
illi
n
g
co
n
d
itio
n
.
T
o
a
d
d
r
ess
th
is
is
s
u
e,
th
e
s
y
n
th
etic
m
in
o
r
ity
o
v
e
r
s
am
p
lin
g
tech
n
i
q
u
e
(
SMOT
E
)
will
b
e
ap
p
lied
to
th
e
tr
ain
i
n
g
s
et
in
th
is
s
tu
d
y
to
g
en
er
ate
s
y
n
th
e
tic
s
am
p
les
f
o
r
th
e
m
in
o
r
ity
cl
ass
.
T
h
is
ap
p
r
o
ac
h
h
elp
s
b
alan
ce
t
h
e
class
d
is
tr
ib
u
tio
n
a
n
d
e
x
p
ec
ted
to
im
p
r
o
v
e
th
e
m
o
d
el’
s
a
b
ilit
y
to
ac
c
u
r
ately
d
etec
t
s
tu
c
k
p
ip
e
in
cid
en
ts
.
T
a
b
le
1
p
r
esen
ts
th
e
f
ea
tu
r
es o
f
th
e
d
ataset
an
d
th
eir
d
escr
ip
tio
n
s
.
T
ab
le
1
.
Featu
r
es o
f
th
e
d
atase
t
No
F
e
a
t
u
r
e
s
D
e
scri
p
t
i
o
n
s
1
D
a
t
e
-
t
i
me
S
e
n
s
o
r
-
r
e
c
o
r
d
e
d
d
a
t
e
a
n
d
t
i
me
2
B
i
t
D
e
p
t
h
Th
e
b
i
t
o
r
c
a
s
i
n
g
p
o
si
t
i
o
n
,
i
n
d
i
c
a
t
i
n
g
t
h
e
l
o
w
e
st
p
o
s
i
t
i
o
n
o
n
t
h
e
d
r
i
l
l
st
r
i
n
g
3
S
c
f
m
A
i
r
r
a
t
e
t
h
a
t
p
u
mp
i
n
g
f
r
o
m
a
e
r
a
t
e
d
u
n
i
t
i
n
t
o
t
h
e
w
e
l
l
b
o
r
e
a
n
d
c
o
m
b
i
n
e
d
w
i
t
h
w
a
t
e
r
t
o
p
r
o
d
u
c
e
l
o
w
d
e
n
s
i
t
y
f
l
u
i
d
l
e
s
s t
h
e
n
w
a
t
e
r
w
h
e
n
e
n
t
e
r
i
n
g
t
h
e
l
o
ss
z
o
n
e
4
M
u
d
C
o
n
d
I
n
C
o
n
d
u
c
t
i
v
i
t
y
o
f
d
r
i
l
l
i
n
g
m
u
d
a
s
i
t
e
n
t
e
r
s t
h
e
w
e
l
l
b
o
r
e
5
B
l
o
c
k
P
o
s
S
h
o
w
s
t
h
e
p
o
si
t
i
o
n
o
f
t
h
e
t
r
a
v
e
l
i
n
g
b
l
o
c
k
6
W
O
B
F
o
r
c
e
e
x
e
r
t
e
d
o
n
t
h
e
d
r
i
l
l
b
i
t
7
R
O
P
i
D
r
i
l
l
b
i
t
s
p
e
e
d
d
r
i
l
l
i
n
g
u
n
d
e
r
g
r
o
u
n
d
f
o
r
mat
i
o
n
s
8
B
V
D
e
p
t
h
S
p
e
e
d
i
n
p
e
n
e
t
r
a
t
i
n
g
u
n
d
e
r
g
r
o
u
n
d
g
e
o
l
o
g
i
c
a
l
f
o
r
m
a
t
i
o
n
s
9
M
u
d
C
o
n
d
O
u
t
C
o
n
d
u
c
t
i
v
i
t
y
o
f
d
r
i
l
l
i
n
g
m
u
d
a
s
i
t
e
x
i
t
s t
h
e
w
e
l
l
b
o
r
e
10
To
r
q
u
e
R
o
t
a
t
i
n
g
f
o
r
c
e
g
e
n
e
r
a
t
e
d
11
R
P
M
R
o
t
a
t
i
o
n
sp
e
e
d
f
o
r
o
n
e
mi
n
u
t
e
12
H
k
l
d
To
t
a
l
o
f
t
h
e
w
e
i
g
h
t
b
o
r
n
e
b
y
t
h
e
h
o
o
k
o
n
t
h
e
d
r
i
l
l
i
n
g
e
q
u
i
p
me
n
t
13
Lo
g
D
e
p
t
h
D
e
p
t
h
o
f
t
h
e
b
o
r
e
h
o
l
e
a
t
t
h
e
t
i
m
e
o
f
l
o
g
d
a
t
a
m
e
a
s
u
r
e
m
e
n
t
14
H
2
S
_
1
R
e
f
e
r
s
t
o
t
h
e
c
o
n
c
e
n
t
r
a
t
i
o
n
l
e
v
e
l
o
f
h
y
d
r
o
g
e
n
s
u
l
f
i
d
e
(
t
o
x
i
c
a
n
d
c
o
r
r
o
s
i
v
e
g
a
s)
15
M
u
d
F
l
o
w
O
u
t
p
M
u
d
f
l
o
w
d
i
sc
h
a
r
g
e
t
h
a
t
r
i
se
s t
o
t
h
e
s
u
r
f
a
c
e
16
To
t
S
P
M
R
e
p
e
t
i
t
i
v
e
m
o
t
i
o
n
p
e
r
f
o
r
me
d
b
y
d
r
i
l
l
i
n
g
mu
d
p
u
m
p
i
n
o
n
e
mi
n
u
t
e
17
S
p
P
r
e
ss
P
r
e
ssu
r
e
i
n
t
h
e
s
u
p
p
o
r
t
p
i
p
e
sy
s
t
e
m
o
f
d
r
i
l
l
i
n
g
e
q
u
i
p
m
e
n
t
18
M
u
d
F
l
o
w
I
n
M
u
d
f
l
o
w
r
a
t
e
t
o
b
e
p
u
m
p
e
d
t
o
t
h
e
w
e
l
l
19
C
O
2
_
1
C
a
r
b
o
n
d
i
o
x
i
d
e
(
C
O
2
)
g
a
s c
o
n
c
e
n
t
r
a
t
i
o
n
20
G
a
s
C
o
n
c
e
n
t
r
a
t
i
o
n
o
f
d
i
sc
o
v
e
r
e
d
g
a
s
21
M
u
d
T
e
m
p
I
n
M
u
d
t
e
m
p
e
r
a
t
u
r
e
e
n
t
e
r
i
n
g
t
h
e
b
o
r
e
h
o
l
e
22
M
u
d
T
e
m
p
O
u
t
Te
mp
e
r
a
t
u
r
e
o
f
mu
d
e
x
i
t
i
n
g
t
h
e
b
o
r
e
h
o
l
e
a
n
d
r
e
t
u
r
n
i
n
g
t
o
t
h
e
s
u
r
f
a
c
e
23
Ta
n
k
V
o
l
T
o
t
To
t
a
l
v
o
l
u
m
e
i
n
t
h
e
t
a
n
k
3
.
2
.
F
e
a
t
ure
s
elec
t
io
n wit
h c
o
rr
ela
t
io
n c
o
ef
f
icient
C
o
r
r
elatio
n
co
ef
f
icien
t
(
r
)
is
a
m
eth
o
d
to
m
ea
s
u
r
e
th
e
r
elatio
n
s
h
ip
b
etwe
en
two
v
ar
i
ab
les.
T
h
e
r
esu
ltin
g
v
alu
e
o
f
th
is
m
eth
o
d
r
an
g
es
f
r
o
m
-
1
to
+1
,
w
ith
-
1
in
d
icatin
g
a
p
er
f
ec
t
n
eg
ativ
e
co
r
r
elatio
n
,
+1
in
d
icatin
g
a
p
er
f
ec
t
p
o
s
itiv
e
co
r
r
elatio
n
,
an
d
0
m
ea
n
in
g
th
er
e
is
n
o
co
r
r
elatio
n
b
etwe
en
th
e
v
ar
iab
les
[
2
1
]
.
I
n
th
is
s
tu
d
y
,
th
e
co
r
r
elatio
n
co
ef
f
icien
t
r
is
em
p
lo
y
ed
f
o
r
f
ea
tu
r
e
s
elec
tio
n
to
id
en
tify
th
e
m
o
s
t
in
f
lu
en
tial
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Web
-
b
a
s
ed
g
e
o
th
erma
l d
r
illi
n
g
s
tu
ck
p
ip
e
p
r
ed
ictio
n
u
s
in
g
d
ec
is
io
n
tr
ee
a
lg
o
r
ith
m
(
R
o
s
yi
h
a
n
Mu
h
t
a
d
lo
r
)
607
f
ea
tu
r
es
af
f
ec
tin
g
th
e
o
u
tp
u
t
class
.
W
e
ch
o
s
e
th
e
to
p
5
,
1
0
,
an
d
1
5
f
ea
t
u
r
es
with
th
e
h
ig
h
est
co
r
r
elatio
n
co
ef
f
icien
ts
f
r
o
m
T
ab
le
1
to
s
er
v
e
as
in
p
u
t
f
ea
t
u
r
es
f
o
r
th
e
ML
m
o
d
els.
T
h
e
f
o
r
m
u
la
f
o
r
ca
lcu
latin
g
t
h
e
Pear
s
o
n
co
r
r
elatio
n
co
ef
f
icien
t
is
s
h
o
wn
in
(
1
)
.
=
∑
−
∑
∑
=
1
=
1
=
1
√
∑
2
−
(
∑
=
1
)
2
=
1
√
∑
2
−
(
∑
=
1
)
2
=
1
(
1
)
3
.
3
.
Da
t
a
t
r
a
ns
f
o
rma
t
io
n wit
h sl
idi
ng
wind
o
w
T
o
p
r
o
ce
s
s
a
tim
e
s
er
ies
d
ata
s
et
wh
er
e
f
u
tu
r
e
p
r
e
d
ictio
n
s
ar
e
b
ased
o
n
v
al
u
es
f
r
o
m
p
r
e
v
io
u
s
tim
e
p
er
io
d
s
,
th
e
s
lid
in
g
win
d
o
w
m
eth
o
d
is
s
elec
ted
as
an
ap
p
r
o
p
r
iate
ap
p
r
o
ac
h
[
2
2
]
.
Sli
d
in
g
w
in
d
o
w
is
a
m
eth
o
d
o
f
an
aly
zin
g
a
s
u
b
s
et
o
f
d
ata
th
at
“r
o
lls
”
o
v
er
tim
e.
T
h
is
alg
o
r
ith
m
is
h
ig
h
ly
a
d
ap
tab
le
an
d
th
u
s
r
o
b
u
s
t
to
v
ar
iatio
n
s
in
d
ata
th
at
ch
a
n
g
e
s
u
d
d
en
ly
[
2
3
]
.
Sli
d
in
g
win
d
o
ws
ca
n
b
e
u
s
ed
in
v
ar
i
o
u
s
co
m
p
u
tin
g
f
ield
s
s
u
ch
as
d
ata
an
aly
s
is
an
d
p
atter
n
m
atch
in
g
alg
o
r
ith
m
s
.
Sli
d
in
g
win
d
o
ws
u
s
e
th
e
co
n
ce
p
t
o
f
a
co
n
s
tan
t
-
s
ized
“win
d
o
w”
ap
p
lied
to
ea
c
h
in
p
u
t
d
ata
to
h
an
d
le
s
u
cc
ess
iv
e
p
o
r
tio
n
s
o
f
th
e
d
ata.
B
asically
,
th
is
tech
n
iq
u
e
u
s
es
a
p
r
e
-
ex
is
tin
g
d
ata
s
et
to
p
r
e
d
ict
f
u
tu
r
e
v
al
u
es
[
2
4
]
.
Fig
u
r
e
2
illu
s
tr
ates
a
s
lid
in
g
win
d
o
w
m
eth
o
d
,
u
s
in
g
d
ata
f
r
o
m
th
e
p
r
ev
i
o
u
s
5
m
i
n
u
tes as in
p
u
t to
f
o
r
ec
ast th
e
n
ex
t
5
-
m
in
u
te
p
r
e
d
ictio
n
h
o
r
izo
n
(
PH)
.
Fig
u
r
e
2
.
Sli
d
in
g
win
d
o
w
illu
s
tr
atio
n
3
.
4
.
Dec
is
io
n
t
re
e
m
o
del
DT
is
a
p
r
ed
ictio
n
m
o
d
el
th
at
is
v
er
y
s
u
itab
le
f
o
r
class
i
f
icatio
n
[
2
5
]
.
T
h
is
m
o
d
el
is
a
d
ir
ec
ted
ac
y
clic
g
r
ap
h
th
at
b
eg
in
s
at
a
r
o
o
t
n
o
d
e,
wh
er
e
ea
ch
i
n
ter
n
a
l
(
n
o
n
-
ter
m
in
al)
n
o
d
e
test
s
a
s
in
g
le
f
ea
tu
r
e
.
E
ac
h
b
r
an
ch
c
o
r
r
esp
o
n
d
s
to
th
e
o
u
tco
m
e
o
f
th
at
test
,
g
u
i
d
in
g
t
h
e
in
s
tan
ce
d
o
wn
a
s
p
ec
if
ic
p
ath
.
T
h
is
p
r
o
ce
s
s
co
n
tin
u
es
th
r
o
u
g
h
s
u
cc
ess
iv
e
f
ea
tu
r
e
e
v
alu
atio
n
s
u
n
til
a
ter
m
in
al
(
leaf
)
n
o
d
e
is
r
ea
ch
e
d
,
wh
ich
p
r
o
v
id
es
th
e
f
in
al
class
p
r
ed
ictio
n
[
2
6
]
.
T
h
e
DT
m
o
d
el
was
ch
o
s
en
b
ec
au
s
e
th
e
m
o
d
el
is
s
im
p
le,
s
u
itab
le
f
o
r
lar
g
e
d
atasets
,
f
ast
tr
ain
in
g
tim
e,
an
d
g
o
o
d
p
r
ed
ictio
n
a
b
ilit
y
s
o
th
at
it
is
s
u
itab
le
f
o
r
u
s
e
in
th
e
ca
s
e
o
f
s
tu
ck
p
ip
e
p
r
ed
ictio
n
in
d
r
illi
n
g
[
6
]
,
[
7
]
,
[
2
5
]
.
I
n
a
d
d
itio
n
,
in
t
h
is
ca
s
e
th
e
DT
m
o
d
el
h
as
s
e
v
er
al
ad
v
an
tag
es
co
m
p
ar
ed
to
R
F,
n
am
ely
f
aster
d
ata
tr
ain
in
g
an
d
d
ec
is
io
n
m
ak
in
g
w
h
ich
is
s
u
itab
le
f
o
r
s
tu
ck
p
i
p
e
p
r
ed
ictio
n
ca
s
es
th
at
r
eq
u
ir
e
s
p
ee
d
in
m
o
d
elin
g
an
d
p
r
e
d
ictio
n
[
1
1
]
.
Fig
u
r
e
3
s
h
o
ws
th
e
DT
f
o
r
m
at
io
n
f
lo
wch
ar
t.
Hy
p
er
p
ar
a
m
eter
o
p
tim
izatio
n
was
co
n
d
u
cte
d
f
o
r
th
e
DT
m
o
d
el,
r
esu
ltin
g
in
th
e
o
p
tim
al
co
n
f
i
g
u
r
atio
n
o
f
m
a
x
_
d
e
p
th
=5
,
m
in
_
s
am
p
les_
s
p
lit=2
,
m
in
_
s
am
p
les_
leaf
=2
,
an
d
cr
it
er
io
n
=e
n
tr
o
p
y
.
T
o
en
s
u
r
e
th
e
r
eliab
ilit
y
o
f
th
e
m
o
d
el,
ea
c
h
p
r
e
d
ictiv
e
m
o
d
el
was e
x
ec
u
ted
r
ep
ea
ted
l
y
u
n
d
e
r
id
en
tical
co
n
d
itio
n
s
to
v
alid
a
te
its
r
o
b
u
s
tn
ess
an
d
co
n
s
is
ten
cy
.
3
.
5
.
E
v
a
lua
t
i
o
n m
et
rics f
o
r
t
he
m
o
dels
E
v
alu
atio
n
m
etr
ics
m
ea
s
u
r
e
m
o
d
el
p
er
f
o
r
m
an
ce
b
y
p
r
ed
ic
tin
g
test
in
g
s
et
th
at
th
e
m
o
d
el
h
as
n
ev
er
s
ee
n
b
ef
o
r
e.
T
h
u
s
,
it
ca
n
b
e
k
n
o
wn
h
o
w
well
th
e
m
o
d
el
p
e
r
f
o
r
m
s
in
s
o
lv
i
n
g
th
e
g
iv
en
task
[
2
7
]
,
[
2
8
]
.
T
h
is
s
tu
d
y
em
p
lo
y
s
a
h
o
ld
-
o
u
t
v
a
lid
atio
n
m
eth
o
d
,
wh
ich
is
m
o
r
e
ap
p
r
o
p
r
iate
f
o
r
tim
e
s
er
ies
d
ata
to
p
r
eser
v
e
tem
p
o
r
al
d
e
p
en
d
e
n
cies.
I
n
th
i
s
ap
p
r
o
ac
h
,
th
e
d
ataset
is
d
iv
i
d
ed
in
to
two
p
o
r
tio
n
s
,
with
th
e
f
ir
s
t
4
7
%
u
s
ed
f
o
r
tr
ain
in
g
a
n
d
th
e
r
em
ain
in
g
5
3
%
r
eser
v
ed
f
o
r
test
in
g
.
W
e
en
s
u
r
ed
th
at
th
e
m
in
o
r
ity
class
was
r
ep
r
esen
ted
in
b
o
th
th
e
tr
ain
in
g
an
d
test
in
g
s
ets.
T
h
er
ef
o
r
e,
th
is
r
atio
was
ch
o
s
en
to
m
ain
tain
a
s
tr
atif
ied
d
is
tr
ib
u
tio
n
,
en
s
u
r
in
g
t
h
at
th
e
m
i
n
o
r
ity
class
ap
p
ea
r
s
in
b
o
t
h
s
u
b
s
ets,
as
th
e
s
tu
ck
c
o
n
d
itio
n
o
cc
u
r
s
a
p
p
r
o
x
im
ately
in
t
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
:
604
-
6
1
4
608
m
id
d
le
o
f
th
e
tim
e
s
er
ies
d
ataset.
T
ab
le
2
s
h
o
ws
an
ex
p
lan
a
tio
n
o
f
th
e
co
n
f
u
s
io
n
m
atr
i
x
co
m
p
o
n
en
ts
,
wh
er
e
tr
u
e
p
o
s
itiv
e
(
T
P)
is
a
t
r
u
e
p
o
s
itiv
e
p
r
ed
ictio
n
,
f
alse
p
o
s
itiv
e
(
FP
)
is
a
f
alse
p
o
s
itiv
e
p
r
e
d
i
ctio
n
,
tr
u
e
n
e
g
ativ
e
(
T
N)
is
a
tr
u
e
n
eg
ativ
e
p
r
e
d
ictio
n
,
an
d
f
alse
n
e
g
ativ
e
(
FN)
is
a
f
alse
n
eg
ativ
e
p
r
ed
ictio
n
[
2
9
]
.
T
h
e
p
o
s
itiv
e
lab
el
in
d
icate
s
a
s
tu
ck
p
ip
e
co
n
d
itio
n
,
wh
ile
th
e
n
e
g
ativ
e
l
ab
el
co
r
r
esp
o
n
d
s
to
n
o
r
m
al
d
r
illi
n
g
co
n
d
itio
n
s
.
Mo
d
el
p
er
f
o
r
m
a
n
ce
was
ev
al
u
ated
u
s
in
g
s
ev
e
r
al
m
etr
ics,
in
c
lu
d
in
g
ac
c
u
r
ac
y
,
p
r
ec
is
io
n
,
r
e
ca
ll,
F1
-
s
co
r
e,
a
n
d
r
ec
eiv
er
o
p
e
r
atin
g
ch
a
r
ac
ter
is
tic
ar
ea
u
n
d
er
th
e
c
u
r
v
e
(
R
OC
-
AUC
)
,
all
d
er
iv
ed
f
r
o
m
v
alu
es
in
th
e
co
n
f
u
s
io
n
m
atr
ix
.
Acc
u
r
ac
y
m
ea
s
u
r
es
th
e
p
r
o
p
o
r
tio
n
o
f
co
r
r
ec
tly
class
if
ied
in
s
tan
ce
s
am
o
n
g
all
s
am
p
les.
Pre
cisi
o
n
r
ef
lects th
e
p
r
o
p
o
r
tio
n
o
f
co
r
r
ec
tly
id
en
tifie
d
p
o
s
itiv
e
ca
s
es
o
u
t o
f
all
p
r
ed
icted
p
o
s
itiv
e
ca
s
es,
wh
ile
r
ec
al
l (
o
r
s
en
s
itiv
ity
)
in
d
icate
s
th
e
m
o
d
el’
s
ab
ilit
y
to
d
etec
t
ac
tu
al
p
o
s
itiv
e
ca
s
es.
T
h
e
F1
-
s
co
r
e,
r
ep
r
esen
tin
g
th
e
h
ar
m
o
n
ic
m
e
an
o
f
p
r
ec
is
io
n
an
d
r
ec
all,
p
r
o
v
id
es
a
b
alan
c
ed
ass
ess
m
en
t
o
f
b
o
th
m
etr
ic
s
.
Ad
d
itio
n
ally
,
th
e
R
OC
-
AU
C
ev
alu
ates
th
e
m
o
d
el’
s
ab
ilit
y
to
d
is
tin
g
u
is
h
b
etwe
en
p
o
s
itiv
e
an
d
n
eg
ativ
e
class
es,
o
f
f
er
in
g
an
o
v
er
all
m
ea
s
u
r
e
o
f
class
if
icatio
n
ef
f
ec
tiv
en
ess
.
T
o
ad
d
r
ess
class
im
b
alan
ce
,
th
e
SMOT
E
was
ap
p
lied
to
th
e
tr
ain
in
g
s
et,
en
s
u
r
in
g
a
m
o
r
e
b
alan
ce
d
class
d
is
tr
ib
u
tio
n
d
u
r
in
g
m
o
d
el
tr
ain
in
g
.
3
.
6
.
M
o
del deplo
y
m
ent
On
ce
th
e
o
p
tim
al
m
o
d
el
is
o
b
tain
ed
,
it
is
d
ep
lo
y
ed
in
to
a
web
-
b
ased
s
y
s
tem
u
s
in
g
th
e
Stre
am
lit
f
r
am
ewo
r
k
.
T
h
is
web
ap
p
licatio
n
s
er
v
es
as
a
p
r
ed
ictio
n
t
o
o
l
th
at
p
r
o
ce
s
s
es
h
is
to
r
ical
d
r
illi
n
g
d
ata
to
i
d
en
tify
p
o
ten
tial
s
tu
ck
p
ip
e
in
cid
en
ts
.
I
n
p
r
ac
tical
im
p
lem
en
tatio
n
,
th
e
d
ata
is
co
llected
f
r
o
m
s
en
s
o
r
s
in
s
talled
o
n
th
e
d
r
illi
n
g
r
ig
an
d
s
to
r
ed
in
a
c
en
tr
al
d
atab
ase
f
o
r
an
aly
s
is
.
W
h
en
v
alid
in
p
u
t
d
ata
is
p
r
o
v
id
ed
,
th
e
s
y
s
tem
g
en
er
ates
p
r
ed
ictio
n
s
in
d
icatin
g
eith
er
n
o
r
m
al
d
r
illi
n
g
co
n
d
it
io
n
s
o
r
p
o
te
n
tial
s
tu
ck
p
ip
e
ev
en
ts
.
Ad
d
itio
n
ally
,
th
e
p
latf
o
r
m
f
ea
t
u
r
es
in
ter
ac
ti
v
e
v
is
u
aliza
tio
n
t
o
o
ls
th
at
allo
w
u
s
er
s
to
m
o
n
ito
r
an
d
an
aly
z
e
h
is
to
r
ical
d
r
illi
n
g
p
ar
am
eter
s
o
v
e
r
tim
e,
s
u
p
p
o
r
ti
n
g
ea
r
ly
d
etec
tio
n
an
d
in
f
o
r
m
e
d
d
ec
is
io
n
-
m
a
k
in
g
d
u
r
in
g
d
r
ill
in
g
o
p
e
r
atio
n
s
.
Fig
u
r
e
3
.
Dec
is
io
n
tr
ee
f
lo
wch
ar
t
T
ab
le
2
.
C
o
n
f
u
s
io
n
m
atr
ix
A
c
t
u
a
l
P
r
e
d
i
c
t
e
d
P
o
si
t
i
v
e
N
e
g
a
t
i
v
e
P
o
si
t
i
v
e
Tr
u
e
p
o
si
t
i
v
e
(
TP)
F
a
l
se
n
e
g
a
t
i
v
e
(
F
N
)
N
e
g
a
t
i
v
e
F
a
l
se
p
o
si
t
i
v
e
(
F
P
)
Tr
u
e
n
e
g
a
t
i
v
e
(
TN
)
4.
RE
SU
L
T
AND
DI
SCUS
SI
O
N
4
.
1
.
M
o
del per
f
o
rma
nce
ev
a
lua
t
io
n
I
n
th
is
s
ec
tio
n
,
we
co
m
p
ar
ed
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
p
r
o
p
o
s
ed
DT
m
o
d
el
with
o
th
er
ML
alg
o
r
ith
m
s
,
n
am
ely
NB
,
R
F,
m
u
ltil
ay
er
p
er
ce
p
tr
o
n
(
ML
P),
an
d
SVM.
I
n
a
d
d
itio
n
,
we
also
in
v
esti
g
ate
th
e
im
p
ac
t
o
f
ap
p
ly
in
g
th
e
SMOT
E
o
n
m
o
d
el
p
er
f
o
r
m
a
n
ce
.
T
ab
les
3
to
5
s
u
m
m
ar
ized
th
e
r
esu
lts
o
f
ea
ch
m
o
d
el
at
th
r
ee
PH:
5
m
in
u
tes
(
PH5
)
,
1
0
m
in
u
tes
(
PH1
0
)
,
an
d
1
5
m
in
u
tes
(
PH1
5
)
.
T
h
e
m
o
d
els
u
tili
ze
th
e
last
f
iv
e
m
in
u
tes
o
f
d
r
illi
n
g
d
ata
to
p
r
ed
ict
wh
et
h
e
r
a
s
tu
ck
p
ip
e
in
cid
en
t w
ill o
cc
u
r
in
th
e
n
ex
t 5
,
1
0
,
o
r
1
5
m
in
u
tes,
r
esp
ec
tiv
ely
.
B
ased
o
n
th
e
r
esu
lts
p
r
esen
ted
in
T
ab
les
3
to
5
,
th
e
DT
co
n
s
is
ten
tly
ac
h
iev
es
s
tr
o
n
g
an
d
s
tab
le
p
er
f
o
r
m
an
ce
ac
r
o
s
s
all
PH
.
T
h
e
p
r
o
p
o
s
ed
DT
m
o
d
el,
d
ev
elo
p
ed
u
s
in
g
th
e
to
p
f
iv
e
s
elec
ted
f
ea
tu
r
es,
ac
h
iev
ed
an
ac
cu
r
ac
y
o
f
0
.
9
7
3
-
0
.
9
7
4
,
p
r
ec
is
io
n
o
f
0
.
9
8
6
,
an
d
r
ec
all
o
f
0
.
7
2
8
-
0
.
7
2
9
.
T
h
e
F1
-
s
co
r
e,
r
an
g
in
g
b
etwe
en
0
.
6
2
4
-
0
.
6
2
9
,
in
d
icate
s
a
b
alan
ce
d
p
e
r
f
o
r
m
an
ce
b
etwe
en
p
r
ec
is
io
n
an
d
r
ec
all,
wh
ile
th
e
R
OC
-
AU
C
v
alu
es
(
ar
o
u
n
d
0
.
7
2
8
-
0
.
7
2
9
)
f
u
r
th
er
c
o
n
f
ir
m
th
e
m
o
d
el’
s
g
o
o
d
d
is
cr
im
in
ativ
e
ca
p
ab
ilit
y
in
id
en
tif
y
in
g
th
e
s
tu
ck
p
ip
e
class
.
W
h
en
co
m
p
ar
ed
to
o
t
h
er
alg
o
r
ith
m
s
,
th
e
DT
m
o
d
el
o
u
tp
er
f
o
r
m
s
NB
an
d
ML
P
in
ter
m
s
o
f
b
o
th
p
r
ec
is
io
n
an
d
o
v
er
all
s
tab
ilit
y
.
Alth
o
u
g
h
th
e
R
F
m
o
d
el
s
h
o
ws
co
m
p
ar
ab
le
r
esu
lts
,
DT
o
f
f
er
s
a
s
im
p
ler
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Web
-
b
a
s
ed
g
e
o
th
erma
l d
r
illi
n
g
s
tu
ck
p
ip
e
p
r
ed
ictio
n
u
s
in
g
d
ec
is
io
n
tr
ee
a
lg
o
r
ith
m
(
R
o
s
yi
h
a
n
Mu
h
t
a
d
lo
r
)
609
s
tr
u
ctu
r
e
with
lo
wer
c
o
m
p
u
tatio
n
al
co
m
p
le
x
ity
,
m
a
k
in
g
it
m
o
r
e
s
u
itab
le
f
o
r
in
te
g
r
atio
n
in
to
th
e
p
r
o
p
o
s
ed
web
-
b
ased
m
o
n
ito
r
in
g
s
y
s
te
m
.
T
h
e
SVM,
in
co
n
tr
ast,
d
em
o
n
s
tr
ates
th
e
wea
k
est
p
er
f
o
r
m
an
ce
ac
r
o
s
s
all
m
etr
ics,
p
ar
ticu
lar
ly
in
F1
-
s
co
r
e
an
d
R
OC
-
AUC,
s
u
g
g
esti
n
g
lim
ited
ca
p
a
b
ilit
y
in
h
a
n
d
lin
g
th
e
n
o
n
-
lin
ea
r
ch
ar
ac
ter
is
tics
o
f
th
e
d
ataset.
T
ab
le
3
.
Per
f
o
r
m
an
ce
o
f
p
r
ed
i
ctio
n
m
o
d
el
f
o
r
PH 5
M
o
d
e
l
A
c
c
u
r
a
c
y
R
e
c
a
l
l
P
r
e
c
i
s
i
o
n
F1
-
sc
o
r
e
R
O
C
A
U
C
NB
0
.
9
3
3
0
.
7
1
5
0
.
6
6
7
0
.
4
1
0
0
.
7
3
6
RF
0
.
9
7
4
0
.
7
2
9
0
.
9
8
6
0
.
6
2
9
0
.
7
3
0
M
LP
0
.
9
0
1
0
.
6
8
7
0
.
6
0
2
0
.
3
0
8
0
.
5
1
4
S
V
M
0
.
9
1
1
0
.
4
8
9
0
.
4
8
7
0
.
0
2
2
0
.
5
0
0
DT
0
.
9
7
3
0
.
7
2
8
0
.
9
8
6
0
.
6
2
6
0
.
7
2
8
N
B
+
S
M
O
TE
0
.
9
3
7
0
.
7
1
7
0
.
6
7
7
0
.
4
2
3
0
.
7
1
5
R
F
+
S
M
O
TE
0
.
9
7
3
0
.
7
2
9
0
.
9
8
6
0
.
6
2
8
0
.
7
3
1
M
LP+S
M
O
TE
0
.
9
6
6
0
.
7
1
1
0
.
8
6
8
0
.
5
4
9
0
.
5
0
0
S
V
M
+
S
M
O
TE
0
.
9
0
8
0
.
5
0
5
0
.
5
0
5
0
.
0
5
8
0
.
5
0
0
D
T+
S
M
O
T
E
0
.
9
7
3
0
.
7
2
7
0
.
9
8
6
0
.
6
2
4
0
.
7
2
7
T
ab
le
4
.
Per
f
o
r
m
an
ce
o
f
p
r
ed
i
ctio
n
m
o
d
el
f
o
r
PH1
0
M
o
d
e
l
A
c
c
u
r
a
c
y
R
e
c
a
l
l
P
r
e
c
i
s
i
o
n
F1
-
sc
o
r
e
R
O
C
A
U
C
NB
0
.
9
3
3
0
.
7
1
7
0
.
6
6
7
0
.
4
1
1
0
.
7
3
8
RF
0
.
9
7
4
0
.
7
3
0
0
.
9
8
7
0
.
6
3
1
0
.
7
3
2
M
LP
0
.
9
0
2
0
.
6
9
5
0
.
6
0
6
0
.
3
1
7
0
.
5
0
6
S
V
M
0
.
9
4
9
0
.
5
1
1
0
.
6
1
7
0
.
0
4
8
0
.
5
0
0
DT
0
.
9
7
4
0
.
7
2
9
0
.
9
8
6
0
.
6
2
8
0
.
7
2
9
N
B
+
S
M
O
TE
0
.
9
3
7
0
.
7
1
7
0
.
6
7
7
0
.
4
2
3
0
.
7
1
5
R
F
+
S
M
O
TE
0
.
9
7
3
0
.
7
2
9
0
.
9
8
6
0
.
6
2
8
0
.
7
3
1
M
LP+S
M
O
TE
0
.
9
6
6
0
.
7
1
1
0
.
8
6
8
0
.
5
4
9
0
.
5
0
0
S
V
M
+
S
M
O
TE
0
.
9
0
8
0
.
5
0
5
0
.
5
0
5
0
.
0
5
8
0
.
5
0
0
D
T+
S
M
O
T
E
0
.
9
7
3
0
.
7
2
7
0
.
9
8
6
0
.
6
2
4
0
.
7
2
7
T
ab
le
5
.
Per
f
o
r
m
an
ce
o
f
p
r
ed
i
ctio
n
m
o
d
el
f
o
r
PH1
5
M
o
d
e
l
A
c
c
u
r
a
c
y
R
e
c
a
l
l
P
r
e
c
i
s
i
o
n
F1
-
sc
o
r
e
R
O
C
A
U
C
NB
0
.
9
3
3
0
.
7
1
8
0
.
6
6
7
0
.
4
1
2
0
.
7
3
9
RF
0
.
9
7
4
0
.
7
3
1
0
.
9
8
7
0
.
6
3
2
0
.
7
3
4
M
LP
0
.
9
0
3
0
.
6
8
8
0
.
6
0
4
0
.
3
1
1
0
.
4
5
6
S
V
M
0
.
9
5
9
0
.
5
8
4
0
.
9
8
0
0
.
2
8
9
0
.
5
0
0
DT
0
.
9
7
4
0
.
7
2
8
0
.
9
8
6
0
.
6
2
7
0
.
7
2
8
N
B
+
S
M
O
TE
0
.
9
3
7
0
.
7
1
9
0
.
6
7
8
0
.
4
2
6
0
.
7
1
7
R
F
+
S
M
O
TE
0
.
9
7
4
0
.
7
3
1
0
.
9
8
7
0
.
6
3
2
0
.
7
3
4
M
LP+S
M
O
TE
0
.
9
6
5
0
.
7
1
2
0
.
8
6
2
0
.
5
4
9
0
.
5
0
0
S
V
M
+
S
M
O
TE
0
.
9
3
1
0
.
5
2
3
0
.
5
4
1
0
.
0
9
2
0
.
5
0
0
D
T+
S
M
O
T
E
0
.
9
7
4
0
.
7
2
9
0
.
9
8
6
0
.
6
2
9
0
.
7
2
9
4
.
2
.
M
o
s
t
influent
ia
l f
ea
t
ure
s
T
h
e
p
r
e
d
ictio
n
m
o
d
els
p
r
esen
ted
in
T
ab
les
3
to
5
wer
e
d
ev
elo
p
e
d
u
s
in
g
th
e
f
iv
e
m
o
s
t
r
elev
an
t
f
ea
tu
r
es
id
en
tifie
d
th
r
o
u
g
h
c
o
r
r
elatio
n
co
ef
f
icien
t
-
b
ased
f
ea
tu
r
e
s
elec
tio
n
.
T
ab
le
6
lis
t
s
th
ese
f
ea
tu
r
es
in
d
escen
d
in
g
o
r
d
er
o
f
th
eir
c
o
r
r
elatio
n
with
t
h
e
s
tu
ck
p
ip
e
l
ab
el,
with
Scf
m
,
Hk
ld
,
B
itDep
th
,
B
VDe
p
th
,
an
d
L
o
g
Dep
th
em
e
r
g
in
g
as
th
e
to
p
co
n
tr
ib
u
to
r
s
.
T
h
ese
f
ea
tu
r
es
r
ef
lect
k
ey
o
p
er
atio
n
al
p
ar
am
eter
s
th
at
in
f
lu
en
ce
d
r
illi
n
g
p
e
r
f
o
r
m
an
ce
,
p
ar
ticu
l
ar
ly
th
e
m
ec
h
an
ical
an
d
h
y
d
r
au
lic
co
n
d
itio
n
s
ass
o
ciate
d
w
ith
p
o
ten
tial
s
tu
ck
p
ip
e
in
cid
e
n
ts
.
B
y
f
o
cu
s
in
g
o
n
th
ese
f
iv
e
f
ea
t
u
r
es,
th
e
p
r
o
p
o
s
ed
DT
m
o
d
el
e
f
f
ec
t
iv
ely
r
ed
u
ce
s
d
ata
d
im
en
s
io
n
ality
an
d
c
o
m
p
u
tati
o
n
al
co
m
p
lex
it
y
wh
ile
m
ain
tain
in
g
r
o
b
u
s
t
p
r
ed
ictiv
e
ca
p
a
b
ilit
y
.
T
h
is
s
elec
tiv
e
ap
p
r
o
ac
h
h
elp
s
m
in
i
m
ize
th
e
r
is
k
o
f
o
v
er
f
itti
n
g
a
n
d
e
n
h
an
c
es
m
o
d
el
in
ter
p
r
etab
ilit
y
—
im
p
o
r
tan
t
f
ac
t
o
r
s
f
o
r
d
ep
lo
y
m
e
n
t
in
a
p
r
ac
tical,
w
eb
-
b
ased
m
o
n
ito
r
in
g
en
v
ir
o
n
m
en
t.
T
h
e
s
tr
o
n
g
c
o
r
r
elatio
n
v
alu
es
o
f
Scf
m
an
d
Hk
ld
in
d
icate
th
at
air
f
lo
w
an
d
h
o
o
k
lo
ad
p
lay
a
s
ig
n
if
ic
an
t
r
o
le
in
id
en
tify
in
g
ea
r
l
y
s
ig
n
s
o
f
s
tu
ck
p
ip
e
co
n
d
itio
n
s
,
r
ei
n
f
o
r
ci
n
g
th
eir
i
m
p
o
r
tan
ce
i
n
p
r
e
d
ictiv
e
an
aly
s
is
f
o
r
g
eo
th
er
m
al
d
r
illi
n
g
o
p
e
r
atio
n
s
.
T
ab
le
6
.
Fiv
e
m
o
s
t r
elev
an
t f
e
atu
r
es
F
e
a
t
u
r
e
C
o
r
r
e
l
a
t
i
o
n
c
o
e
f
f
i
c
i
e
n
t
sc
o
r
e
S
c
f
m
0
.
4
8
6
9
4
2
H
k
l
d
0
.
4
4
2
0
7
8
B
i
t
D
e
p
t
h
0
.
2
9
2
3
9
4
B
V
D
e
p
t
h
0
.
2
8
4
1
4
5
Lo
g
D
e
p
t
h
0
.
2
7
4
1
2
4
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
:
604
-
6
1
4
610
T
h
e
ap
p
licatio
n
o
f
SMOT
E
s
h
o
ws
o
n
ly
m
ar
g
i
n
al
im
p
r
o
v
e
m
en
ts
in
m
o
d
el
p
e
r
f
o
r
m
an
ce
,
p
ar
ticu
lar
ly
f
o
r
alg
o
r
ith
m
s
s
u
c
h
as
NB
an
d
ML
P.
Fo
r
th
e
DT
m
o
d
el,
S
MO
T
E
d
id
n
o
t
s
ig
n
if
ica
n
tly
a
lter
th
e
p
e
r
f
o
r
m
an
ce
m
etr
ics,
wh
ich
in
d
icate
s
th
at
th
e
m
o
d
el
ca
n
ef
f
ec
tiv
el
y
h
an
d
le
th
e
im
b
alan
ce
d
d
at
aset
ev
en
with
o
u
t
o
v
er
s
am
p
lin
g
.
Nev
er
th
eless
,
ap
p
ly
in
g
SMOT
E
h
elp
e
d
en
s
u
r
e
f
air
er
lear
n
in
g
co
n
d
itio
n
s
ac
r
o
s
s
m
o
d
els
an
d
p
r
o
v
id
e
d
c
o
n
s
is
ten
t
m
in
o
r
ity
class
r
ep
r
esen
tatio
n
d
u
r
in
g
tr
ain
in
g
.
O
v
er
all,
th
e
r
esu
lts
d
em
o
n
s
tr
ate
th
at
t
h
e
p
r
o
p
o
s
ed
DT
m
o
d
el
p
r
o
v
id
e
s
th
e
m
o
s
t
r
eliab
le
an
d
in
ter
p
r
etab
le
s
o
lu
tio
n
f
o
r
s
tu
ck
p
ip
e
p
r
e
d
ictio
n
.
I
ts
co
n
s
is
ten
t
p
er
f
o
r
m
an
ce
ac
r
o
s
s
all
PHs
,
co
m
b
in
ed
with
its
s
im
p
licity
an
d
s
u
itab
ilit
y
f
o
r
d
e
p
lo
y
m
en
t
with
in
a
web
-
b
ased
m
o
n
ito
r
in
g
p
latf
o
r
m
,
s
u
p
p
o
r
ts
its
s
elec
tio
n
as
th
e
b
est
-
p
er
f
o
r
m
in
g
p
r
e
d
ictiv
e
m
o
d
el
in
th
is
s
tu
d
y
.
Fig
u
r
e
4
p
r
esen
ts
th
e
co
n
f
u
s
io
n
m
atr
ix
o
f
th
e
DT
m
o
d
el,
wh
i
le
Fig
u
r
e
5
illu
s
tr
ates
th
e
co
n
f
u
s
io
n
m
atr
ix
o
f
th
e
DT
m
o
d
el
co
m
b
in
ed
with
SMOT
E
.
Me
an
wh
ile,
Fig
u
r
e
6
d
is
p
lay
s
th
e
R
O
C
cu
r
v
es
f
o
r
all
p
r
ed
ictio
n
m
o
d
els
,
p
r
o
v
id
i
n
g
a
c
o
m
p
ar
ativ
e
v
is
u
a
lizatio
n
o
f
th
eir
class
if
icatio
n
p
er
f
o
r
m
an
ce
.
Fig
u
r
e
4
.
C
o
n
f
u
s
io
n
m
atr
i
x
f
o
r
DT
m
o
d
el
Fig
u
r
e
5
.
C
o
n
f
u
s
io
n
m
atr
i
x
f
o
r
DT
+SM
OT
E
m
o
d
el
Fig
u
r
e
6
.
R
OC
C
u
r
v
es f
o
r
all
p
r
ed
ictio
n
m
o
d
els
4.
3
.
M
o
del deplo
y
m
ent
Af
ter
th
e
o
p
tim
al
m
o
d
el
was
s
u
cc
ess
f
u
lly
tr
ain
ed
,
it
wa
s
i
n
teg
r
ated
in
to
a
web
-
b
ased
in
f
o
r
m
atio
n
s
y
s
tem
.
T
h
e
s
y
s
tem
b
eg
in
s
with
a
lo
g
in
p
ag
e
(
Fig
u
r
e
7
)
,
w
h
ich
s
er
v
es
as
th
e
en
tr
y
p
o
in
t
f
o
r
u
s
er
s
to
ac
ce
s
s
th
e
ap
p
licatio
n
.
User
s
ar
e
r
e
q
u
ir
ed
t
o
en
ter
th
eir
r
e
g
is
ter
ed
u
s
er
n
am
e
an
d
p
ass
wo
r
d
to
g
ain
ac
ce
s
s
.
Up
o
n
s
u
cc
ess
f
u
l
lo
g
in
,
th
e
d
ash
b
o
a
r
d
in
ter
f
ac
e
is
d
is
p
lay
ed
,
p
r
o
v
i
d
in
g
n
av
i
g
atio
n
to
s
ev
er
al
k
e
y
f
ea
tu
r
es,
in
clu
d
in
g
th
e
p
r
e
d
ictio
n
p
a
g
e
a
n
d
th
e
d
ata
s
o
u
r
ce
p
ag
e
f
o
r
d
ata
v
i
s
u
aliza
tio
n
.
A
lo
g
o
u
t
o
p
tio
n
is
also
av
ailab
le
to
s
ec
u
r
ely
en
d
th
e
s
ess
io
n
.
T
h
e
p
r
ed
ictio
n
p
ag
e,
ac
c
ess
ib
le
th
r
o
u
g
h
th
e
n
a
v
ig
atio
n
m
en
u
,
d
is
p
lay
s
th
e
p
r
ed
ictio
n
r
esu
lts
g
en
e
r
ated
f
r
o
m
th
e
in
p
u
t
d
ata,
as
illu
s
tr
ated
in
Fig
u
r
e
8
.
Me
an
wh
ile,
th
e
v
is
u
aliza
tio
n
p
ag
e
allo
ws
u
s
er
s
to
v
iew
h
is
to
r
ical
d
r
illi
n
g
d
atasets
s
to
r
ed
in
th
e
d
atab
ase,
p
r
esen
ted
as
in
ter
ac
tiv
e
lin
e
ch
ar
ts
.
User
s
ca
n
s
p
ec
if
y
a
d
esire
d
tim
e
r
an
g
e
th
r
o
u
g
h
an
i
n
p
u
t
f
o
r
m
to
v
is
u
alize
d
ata
with
in
th
at
p
er
io
d
.
Fig
u
r
e
9
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Web
-
b
a
s
ed
g
e
o
th
erma
l d
r
illi
n
g
s
tu
ck
p
ip
e
p
r
ed
ictio
n
u
s
in
g
d
ec
is
io
n
tr
ee
a
lg
o
r
ith
m
(
R
o
s
yi
h
a
n
Mu
h
t
a
d
lo
r
)
611
s
h
o
ws
an
ex
am
p
le
o
f
th
e
g
e
o
th
er
m
al
d
r
illi
n
g
d
ata
v
is
u
ali
za
tio
n
in
ter
f
ac
e,
d
em
o
n
s
tr
atin
g
h
o
w
th
e
s
y
s
tem
s
u
p
p
o
r
ts
m
o
n
ito
r
in
g
a
n
d
a
n
aly
s
is
o
f
d
r
illi
n
g
co
n
d
itio
n
s
.
Fig
u
r
e
7
.
L
o
g
in
p
ag
e
Fig
u
r
e
8
.
Pre
d
ictio
n
p
a
g
e
Fig
u
r
e
9
.
Vis
u
aliza
tio
n
p
a
g
e
5.
CO
NCLU
SI
O
N
T
h
e
p
r
o
p
o
s
ed
DT
m
o
d
el,
d
e
v
elo
p
ed
u
s
in
g
th
e
to
p
f
iv
e
f
e
atu
r
es
id
en
tifie
d
th
r
o
u
g
h
t
h
e
co
r
r
elatio
n
co
ef
f
icien
t
m
et
h
o
d
,
ac
h
ie
v
ed
t
h
e
m
o
s
t
o
p
tim
al
p
er
f
o
r
m
an
ce
am
o
n
g
all
ev
alu
ate
d
m
o
d
els
f
o
r
p
r
ed
ictin
g
s
tu
ck
p
ip
e
in
cid
en
ts
in
g
eo
th
er
m
al
d
r
illi
n
g
o
p
e
r
atio
n
s
.
W
ith
an
a
cc
u
r
ac
y
o
f
9
7
.
3
-
9
7
.
4
%,
p
r
ec
is
io
n
o
f
9
8
.
6
%,
r
ec
all
o
f
7
2
.
8
-
7
2
.
9
%,
a
n
d
R
OC
-
AUC
o
f
ap
p
r
o
x
im
ately
0
.
7
2
8
-
0
.
7
2
9
,
th
e
DT
m
o
d
el
d
em
o
n
s
tr
ated
s
u
p
er
io
r
p
r
ed
ictiv
e
ca
p
ab
ilit
y
an
d
b
ala
n
ce
d
p
e
r
f
o
r
m
an
ce
ac
r
o
s
s
ev
al
u
atio
n
m
etr
ics.
T
h
e
in
c
o
r
p
o
r
a
tio
n
o
f
a
5
-
m
in
u
te
s
lid
in
g
win
d
o
w
a
n
d
th
e
f
iv
e
m
o
s
t
r
elev
an
t
f
ea
tu
r
es
c
o
n
tr
ib
u
ted
to
im
p
r
o
v
in
g
b
o
th
co
m
p
u
tatio
n
al
ef
f
icien
c
y
an
d
m
o
d
el
in
ter
p
r
etab
ilit
y
.
W
h
en
co
m
p
ar
ed
with
o
th
er
ML
alg
o
r
ith
m
s
—
NB
,
R
F,
M
L
P,
an
d
SVM
—
th
e
p
r
o
p
o
s
ed
DT
co
n
s
is
ten
tly
ac
h
iev
ed
co
m
p
ar
a
b
le
o
r
b
etter
r
esu
lts
ac
r
o
s
s
al
l
PH
s
.
W
h
ile
th
e
R
F
m
o
d
el
s
h
o
wed
s
im
ilar
ac
cu
r
ac
y
,
th
e
DT
was
f
av
o
r
ed
f
o
r
its
s
im
p
ler
s
tr
u
ctu
r
e,
lo
wer
co
m
p
u
tatio
n
al
co
s
t
,
an
d
s
u
itab
ilit
y
f
o
r
d
ep
lo
y
m
e
n
t
in
a
web
-
b
ased
s
y
s
tem
.
T
h
e
tr
ai
n
ed
DT
m
o
d
e
l
was
s
u
cc
ess
f
u
lly
in
teg
r
ated
in
to
a
web
-
b
ased
d
r
illi
n
g
m
o
n
ito
r
in
g
p
latf
o
r
m
,
p
r
o
v
id
i
n
g
p
r
e
d
ictio
n
-
b
ased
aler
ts
an
d
d
ata
v
is
u
aliza
tio
n
to
ass
i
s
t
o
p
er
ato
r
s
in
id
en
tify
in
g
p
o
te
n
tial
s
tu
ck
p
i
p
e
ev
en
ts
.
T
h
is
s
y
s
tem
is
ex
p
ec
ted
to
im
p
r
o
v
e
o
p
er
atio
n
a
l
d
ec
is
io
n
-
m
ak
i
n
g
,
en
h
an
ce
d
r
illi
n
g
ef
f
icien
c
y
,
an
d
r
ed
u
ce
th
e
lik
elih
o
o
d
o
f
co
s
tly
d
o
wn
tim
e.
Fo
r
f
u
tu
r
e
r
esear
ch
,
f
u
r
th
er
en
h
an
ce
m
e
n
t
o
f
m
o
d
el
p
er
f
o
r
m
an
ce
is
p
lan
n
ed
b
y
in
c
o
r
p
o
r
atin
g
d
ee
p
lear
n
in
g
ap
p
r
o
a
ch
es
an
d
ad
v
a
n
ce
d
f
ea
tu
r
e
ex
tr
ac
tio
n
tech
n
i
q
u
es
to
b
etter
ca
p
tu
r
e
co
m
p
lex
te
m
p
o
r
al
d
e
p
en
d
e
n
cies.
E
x
p
a
n
d
in
g
th
e
d
ataset
with
lar
g
er
an
d
m
o
r
e
d
iv
er
s
e
d
r
illi
n
g
r
ec
o
r
d
s
is
also
r
ec
o
m
m
en
d
e
d
to
s
tr
en
g
th
e
n
th
e
m
o
d
el’
s
g
e
n
er
aliza
tio
n
ac
r
o
s
s
v
ar
y
in
g
g
eo
lo
g
ical
an
d
o
p
er
ati
o
n
al
co
n
d
itio
n
s
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
:
604
-
6
1
4
612
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
t
r
ib
u
to
r
R
o
les
T
a
x
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
i
d
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
R
o
s
y
ih
an
Mu
h
tad
lo
r
✓
✓
✓
✓
✓
✓
✓
✓
✓
Nu
r
R
o
h
m
an
R
o
s
y
id
✓
✓
✓
✓
✓
A
n
n
i
K
a
r
i
m
a
t
u
l
F
a
u
z
i
y
y
a
h
✓
✓
✓
✓
✓
L
alu
Hen
d
r
a
Per
m
a
n
a
Setiawan
✓
✓
✓
✓
✓
✓
I
r
f
an
Sap
u
tr
a
✓
✓
✓
✓
✓
✓
Pav
el
Stas
a
✓
✓
✓
✓
✓
✓
Fil
ip
B
en
es
✓
✓
✓
✓
✓
✓
Mu
h
am
m
ad
Sy
a
f
r
u
d
in
✓
✓
✓
✓
✓
✓
Gan
jar
Alf
ian
✓
✓
✓
✓
✓
✓
✓
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
s
i
s
I
:
I
n
v
e
s
t
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
s
i
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
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
t
h
at
s
u
p
p
o
r
t
th
e
f
in
d
in
g
s
o
f
t
h
is
s
tu
d
y
ar
e
av
ailab
l
e
f
r
o
m
th
e
c
o
r
r
esp
o
n
d
in
g
au
t
h
o
r
,
[
GA]
,
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
J.
Z
h
e
n
g
e
t
a
l
.
,
“
F
e
a
s
i
b
i
l
i
t
y
o
f
sh
a
l
l
o
w
g
e
o
t
h
e
r
ma
l
e
n
e
r
g
y
f
o
r
i
n
d
u
st
r
i
a
l
h
e
a
t
i
n
g
u
s
i
n
g
h
i
g
h
-
t
e
m
p
e
r
a
t
u
r
e
h
e
a
t
p
u
mp
s
i
n
S
i
c
h
u
a
n
P
r
o
v
i
n
c
e
,
C
h
i
n
a
,
”
En
e
r
g
y
f
o
r
S
u
s
t
a
i
n
a
b
l
e
D
e
v
e
l
o
p
m
e
n
t
,
v
o
l
.
8
8
,
O
c
t
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
s
d
.
2
0
2
5
.
1
0
1
7
8
5
.
[
2
]
X
.
S
o
n
g
e
t
a
l
.
,
“
R
e
v
i
e
w
o
f
h
i
g
h
-
t
e
m
p
e
r
a
t
u
r
e
g
e
o
t
h
e
r
ma
l
d
r
i
l
l
i
n
g
a
n
d
e
x
p
l
o
i
t
a
t
i
o
n
t
e
c
h
n
o
l
o
g
i
e
s
,
”
G
o
n
d
w
a
n
a
R
e
sea
r
c
h
,
v
o
l
.
1
2
2
,
p
p
.
3
1
5
–
3
3
0
,
O
c
t
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
g
r
.
2
0
2
2
.
1
0
.
0
1
3
.
[
3
]
C
.
V
i
v
a
s
,
S
.
S
a
l
e
h
i
,
J
.
D
.
T
u
t
t
l
e
,
a
n
d
B
.
R
i
c
k
a
r
d
,
“
C
h
a
l
l
e
n
g
e
s
a
n
d
o
p
p
o
r
t
u
n
i
t
i
e
s
o
f
g
e
o
t
h
e
r
ma
l
d
r
i
l
l
i
n
g
f
o
r
r
e
n
e
w
a
b
l
e
e
n
e
r
g
y
g
e
n
e
r
a
t
i
o
n
,
”
T
ra
n
s
a
c
t
i
o
n
s
-
G
e
o
t
h
e
rm
a
l
Re
so
u
rc
e
s
C
o
u
n
c
i
l
,
v
o
l
.
4
4
,
p
p
.
9
0
4
–
9
1
8
,
2
0
2
0
.
[
4
]
S
.
C
.
H
.
G
e
e
k
i
y
a
n
a
g
e
,
A
.
T
u
n
k
i
e
l
,
a
n
d
D
.
S
u
i
,
“
D
r
i
l
l
i
n
g
d
a
t
a
q
u
a
l
i
t
y
i
m
p
r
o
v
e
m
e
n
t
a
n
d
i
n
f
o
r
m
a
t
i
o
n
e
x
t
r
a
c
t
i
o
n
w
i
t
h
c
a
se
st
u
d
i
e
s
,”
J
o
u
rn
a
l
o
f
Pe
t
ro
l
e
u
m
Ex
p
l
o
r
a
t
i
o
n
a
n
d
Pro
d
u
c
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
1
,
n
o
.
2
,
p
p
.
8
1
9
–
8
3
7
,
F
e
b
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
3
2
0
2
-
020
-
0
1
0
2
4
-
x.
[
5
]
V
.
S
.
d
e
M
.
S
i
q
u
e
i
r
a
,
M
.
A
.
S
.
L.
C
u
a
d
r
o
s,
C
.
J.
M
u
n
a
r
o
,
a
n
d
G
.
M
.
d
e
A
l
m
e
i
d
a
,
“
E
x
p
e
r
t
s
y
s
t
e
m
f
o
r
e
a
r
l
y
si
g
n
s
t
u
c
k
p
i
p
e
d
e
t
e
c
t
i
o
n
:
f
e
a
t
u
r
e
e
n
g
i
n
e
e
r
i
n
g
a
n
d
f
u
z
z
y
l
o
g
i
c
a
p
p
r
o
a
c
h
,
”
En
g
i
n
e
e
ri
n
g
Ap
p
l
i
c
a
t
i
o
n
s
o
f
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
2
7
,
Ja
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
g
a
p
p
a
i
.
2
0
2
3
.
1
0
7
2
2
9
.
[
6
]
V
.
F
.
C
.
S
o
u
z
a
,
F
.
C
i
c
a
l
e
se,
E.
S
.
L
a
b
e
r
,
a
n
d
M
.
M
o
l
i
n
a
r
o
,
“
D
e
c
i
s
i
o
n
t
r
e
e
s
w
i
t
h
sh
o
r
t
e
x
p
l
a
i
n
a
b
l
e
r
u
l
e
s,”
T
h
e
o
ret
i
c
a
l
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
0
4
7
,
S
e
p
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
t
c
s
.
2
0
2
5
.
1
1
5
3
4
4
.
[
7
]
C
.
W
a
n
g
,
X
.
C
u
i
,
a
n
d
S
.
A
n
,
“
N
e
i
g
h
b
o
r
h
o
o
d
r
o
u
g
h
d
e
c
i
s
i
o
n
t
r
e
e
,
”
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
7
1
7
,
N
o
v
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
s
.
2
0
2
5
.
1
2
2
2
6
6
.
[
8
]
A
.
B
a
i
l
l
y
e
t
a
l
.
,
“
Ef
f
e
c
t
s
o
f
d
a
t
a
se
t
s
i
z
e
a
n
d
i
n
t
e
r
a
c
t
i
o
n
s
o
n
t
h
e
p
r
e
d
i
c
t
i
o
n
p
e
r
f
o
r
ma
n
c
e
o
f
l
o
g
i
st
i
c
r
e
g
r
e
ssi
o
n
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
s
,
”
C
o
m
p
u
t
e
r
Me
t
h
o
d
s
a
n
d
Pr
o
g
ra
m
s
i
n
B
i
o
m
e
d
i
c
i
n
e
,
v
o
l
.
2
1
3
,
Ja
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
m
p
b
.
2
0
2
1
.
1
0
6
5
0
4
.
[
9
]
J.
K
.
H
a
r
r
i
s,
“
P
r
i
m
e
r
o
n
b
i
n
a
r
y
l
o
g
i
st
i
c
r
e
g
r
e
ssi
o
n
,
”
F
a
m
i
l
y
Me
d
i
c
i
n
e
a
n
d
C
o
m
m
u
n
i
t
y
H
e
a
l
t
h
,
v
o
l
.
9
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
3
6
/
f
m
c
h
-
2
0
2
1
-
0
0
1
2
9
0
.
[
1
0
]
S
.
C
h
e
n
,
G
.
I
.
W
e
b
b
,
L.
L
i
u
,
a
n
d
X
.
M
a
,
“
A
n
o
v
e
l
sel
e
c
t
i
v
e
n
a
ï
v
e
B
a
y
e
s
a
l
g
o
r
i
t
h
m,
”
K
n
o
w
l
e
d
g
e
-
B
a
s
e
d
S
y
s
t
e
m
s
,
v
o
l
.
1
9
2
,
M
a
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
k
n
o
s
y
s.
2
0
1
9
.
1
0
5
3
6
1
.
[
1
1
]
L.
R
o
k
a
c
h
a
n
d
O
.
M
a
i
mo
n
,
D
a
t
a
m
i
n
i
n
g
w
i
t
h
d
e
c
i
si
o
n
t
re
e
s:
t
h
e
o
ry
a
n
d
a
p
p
l
i
c
a
t
i
o
n
s
,
2
n
d
e
d
.
H
a
c
k
e
n
sac
k
,
N
e
w
Jerse
y
:
W
o
r
l
d
S
c
i
e
n
t
i
f
i
c
,
2
0
1
5
.
[
1
2
]
H
.
G
o
n
g
,
Y
.
L
i
,
J.
Zh
a
n
g
,
B
.
Zh
a
n
g
,
a
n
d
X
.
W
a
n
g
,
“
A
n
e
w
f
i
l
t
e
r
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
a
l
g
o
r
i
t
h
m
f
o
r
c
l
a
ssi
f
i
c
a
t
i
o
n
t
a
sk
b
y
e
n
s
e
mb
l
i
n
g
p
e
a
r
s
o
n
c
o
r
r
e
l
a
t
i
o
n
c
o
e
f
f
i
c
i
e
n
t
a
n
d
m
u
t
u
a
l
i
n
f
o
r
m
a
t
i
o
n
,
”
E
n
g
i
n
e
e
r
i
n
g
A
p
p
l
i
c
a
t
i
o
n
s
o
f
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
3
1
,
M
a
y
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
g
a
p
p
a
i
.
2
0
2
4
.
1
0
7
8
6
5
.
[
1
3
]
F
.
Y
u
e
,
L.
M
i
a
o
,
a
n
d
Z.
Z
h
o
u
,
“
A
n
e
q
u
i
v
a
l
e
n
t
b
a
c
k
t
r
a
c
k
i
n
g
c
o
a
r
s
e
a
l
i
g
n
me
n
t
m
e
t
h
o
d
w
i
t
h
d
y
n
a
m
i
c
o
p
t
i
ma
l
sl
i
d
i
n
g
w
i
n
d
o
w
i
n
t
e
g
r
a
t
i
o
n
,
”
M
e
a
s
u
r
e
m
e
n
t
:
J
o
u
r
n
a
l
o
f
t
h
e
I
n
t
e
rn
a
t
i
o
n
a
l
Me
a
s
u
reme
n
t
C
o
n
f
e
d
e
r
a
t
i
o
n
,
v
o
l
.
2
5
6
,
D
e
c
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
m
e
a
s
u
r
e
m
e
n
t
.
2
0
2
5
.
1
1
8
2
9
0
.
[
1
4
]
J.
A
.
K
h
a
n
e
t
a
l
.
,
“
C
o
m
p
a
r
i
s
o
n
o
f
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
c
l
a
ssi
f
i
e
r
s
f
o
r
a
c
c
u
r
a
t
e
p
r
e
d
i
c
t
i
o
n
o
f
r
e
a
l
-
t
i
m
e
s
t
u
c
k
p
i
p
e
i
n
c
i
d
e
n
t
s
,
”
En
e
r
g
i
e
s
,
v
o
l
.
1
3
,
n
o
.
1
4
,
J
u
l
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
3
1
4
3
6
8
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Web
-
b
a
s
ed
g
e
o
th
erma
l d
r
illi
n
g
s
tu
ck
p
ip
e
p
r
ed
ictio
n
u
s
in
g
d
ec
is
io
n
tr
ee
a
lg
o
r
ith
m
(
R
o
s
yi
h
a
n
Mu
h
t
a
d
lo
r
)
613
[
1
5
]
S
.
Q
o
d
i
r
o
v
a
n
d
A
.
S
h
e
s
t
a
k
o
v
,
“
D
e
v
e
l
o
p
m
e
n
t
o
f
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
p
r
e
d
i
c
t
i
n
g
d
r
i
l
l
p
i
p
e
s
t
i
c
k
i
n
g
i
n
r
e
a
l
-
t
i
m
e
w
e
l
l
d
r
i
l
l
i
n
g
p
r
o
c
e
ss,
”
i
n
2
0
2
0
G
l
o
b
a
l
S
m
a
r
t
I
n
d
u
st
r
y
C
o
n
f
e
re
n
c
e
,
G
l
o
S
I
C
2
0
2
0
,
N
o
v
.
2
0
2
0
,
p
p
.
1
3
9
–
144
,
d
o
i
:
1
0
.
1
1
0
9
/
G
l
o
S
I
C
5
0
8
8
6
.
2
0
2
0
.
9
2
6
7
8
7
3
.
[
1
6
]
H
.
H
.
El
m
o
u
sa
l
a
m
i
a
n
d
M
.
El
a
s
k
a
r
y
,
“
D
r
i
l
l
i
n
g
st
u
c
k
p
i
p
e
c
l
a
s
si
f
i
c
a
t
i
o
n
a
n
d
m
i
t
i
g
a
t
i
o
n
i
n
t
h
e
G
u
l
f
o
f
S
u
e
z
o
i
l
f
i
e
l
d
s
u
si
n
g
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
,
”
J
o
u
r
n
a
l
o
f
Pe
t
ro
l
e
u
m
E
x
p
l
o
r
a
t
i
o
n
a
n
d
Pr
o
d
u
c
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
0
,
n
o
.
5
,
p
p
.
2
0
5
5
–
2
0
6
8
,
J
u
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
3
2
0
2
-
020
-
0
0
8
5
7
-
w.
[
1
7
]
B
.
El
a
h
i
f
a
r
a
n
d
E
.
H
o
ss
e
i
n
i
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
f
o
r
p
r
e
d
i
c
t
i
o
n
o
f
st
u
c
k
p
i
p
e
i
n
c
i
d
e
n
t
s
u
si
n
g
s
t
a
t
i
s
t
i
c
a
l
d
a
t
a
:
c
a
s
e
st
u
d
y
i
n
mi
d
d
l
e
e
a
s
t
o
i
l
f
i
e
l
d
s,”
J
o
u
rn
a
l
o
f
P
e
t
ro
l
e
u
m
Ex
p
l
o
ra
t
i
o
n
a
n
d
Pr
o
d
u
c
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
2
,
n
o
.
7
,
p
p
.
2
0
1
9
–
2
0
4
5
,
J
u
l
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
3
2
0
2
-
021
-
0
1
4
3
6
-
3.
[
1
8
]
S
.
S
h
a
d
i
z
a
d
e
h
,
“
D
r
i
l
l
i
n
g
s
t
u
c
k
p
i
p
e
p
r
e
d
i
c
t
i
o
n
i
n
I
r
a
n
i
a
n
o
i
l
f
i
e
l
d
s
:
a
n
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
a
p
p
r
o
a
c
h
,
”
I
r
a
n
i
a
n
J
o
u
r
n
a
l
o
f
C
h
e
m
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
7
,
n
o
.
4
,
p
p
.
2
9
–
4
1
,
2
0
1
0
.
[
1
9
]
Z
.
X
i
a
n
a
n
d
H
.
Y
a
n
g
,
“
A
n
e
a
r
l
y
w
a
r
n
i
n
g
m
o
d
e
l
f
o
r
t
h
e
s
t
u
c
k
-
i
n
m
e
d
i
c
a
l
d
r
i
l
l
i
n
g
p
r
o
c
e
s
s
b
a
s
e
d
o
n
t
h
e
a
r
t
i
f
i
c
i
a
l
f
i
s
h
s
w
a
r
m
a
l
g
o
r
i
t
h
m
a
n
d
S
V
M
,
”
D
i
s
t
r
i
b
u
t
e
d
a
n
d
P
a
r
a
l
l
e
l
D
a
t
a
b
a
s
e
s
,
v
o
l
.
4
0
,
n
o
.
4
,
p
p
.
7
7
9
–
7
9
6
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
6
1
9
-
0
2
1
-
0
7
3
4
4
-
z.
[
2
0
]
H
.
T
a
h
e
r
d
o
o
st
,
“
D
a
t
a
c
o
l
l
e
c
t
i
o
n
m
e
t
h
o
d
s
a
n
d
t
o
o
l
s
f
o
r
r
e
sea
r
c
h
;
a
st
e
p
-
by
-
s
t
e
p
g
u
i
d
e
t
o
c
h
o
o
s
e
d
a
t
a
c
o
l
l
e
c
t
i
o
n
t
e
c
h
n
i
q
u
e
f
o
r
a
c
a
d
e
m
i
c
a
n
d
b
u
si
n
e
ss
r
e
se
a
r
c
h
p
r
o
j
e
c
t
s,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
A
c
a
d
e
m
i
c
R
e
se
a
rc
h
i
n
M
a
n
a
g
e
m
e
n
t
,
v
o
l
.
2
0
2
1
,
n
o
.
1
,
p
p
.
1
0
–
3
8
,
2
0
2
1
.
[
2
1
]
E.
Te
m
i
z
h
a
n
,
H
.
M
i
r
t
a
g
i
o
g
l
u
,
a
n
d
M
.
M
e
n
d
e
s,
“
W
h
i
c
h
c
o
r
r
e
l
a
t
i
o
n
c
o
e
f
f
i
c
i
e
n
t
s
h
o
u
l
d
b
e
u
s
e
d
f
o
r
i
n
v
e
s
t
i
g
a
t
i
n
g
r
e
l
a
t
i
o
n
s
b
e
t
w
e
e
n
q
u
a
n
t
i
t
a
t
i
v
e
v
a
r
i
a
b
l
e
s,
”
Am
e
ri
c
a
n
A
c
a
d
e
m
i
c
S
c
i
e
n
t
i
f
i
c
Re
s
e
a
r
c
h
J
o
u
r
n
a
l
f
o
r
En
g
i
n
e
e
ri
n
g
,
p
p
.
2
3
1
3
–
4
4
0
2
,
2
0
2
2
.
[
2
2
]
C
.
M
a
,
W
.
L
i
,
J
.
C
a
o
,
J.
D
u
,
Q
.
L
i
,
a
n
d
R
.
G
r
a
v
i
n
a
,
“
A
d
a
p
t
i
v
e
sl
i
d
i
n
g
w
i
n
d
o
w
b
a
s
e
d
a
c
t
i
v
i
t
y
r
e
c
o
g
n
i
t
i
o
n
f
o
r
a
ssi
s
t
e
d
l
i
v
i
n
g
s,
”
I
n
f
o
rm
a
t
i
o
n
F
u
si
o
n
,
v
o
l
.
5
3
,
p
p
.
5
5
–
6
5
,
J
a
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
f
f
u
s.
2
0
1
9
.
0
6
.
0
1
3
.
[
2
3
]
J.
W
a
n
g
,
W
.
J
i
a
n
g
,
Z.
Li
,
a
n
d
Y
.
L
u
,
“
A
n
e
w
mu
l
t
i
-
sca
l
e
s
l
i
d
i
n
g
w
i
n
d
o
w
LST
M
f
r
a
mew
o
r
k
(
M
S
S
W
-
LST
M
)
:
a
c
a
se
s
t
u
d
y
f
o
r
G
N
S
S
t
i
me
-
s
e
r
i
e
s
p
r
e
d
i
c
t
i
o
n
,
”
Re
m
o
t
e
S
e
n
si
n
g
,
v
o
l
.
1
3
,
n
o
.
1
6
,
A
u
g
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s
1
3
1
6
3
3
2
8
.
[
2
4
]
C
.
C
h
e
n
e
t
a
l
.
,
“
F
o
r
e
c
a
st
o
f
r
a
i
n
f
a
l
l
d
i
st
r
i
b
u
t
i
o
n
b
a
se
d
o
n
f
i
x
e
d
s
l
i
d
i
n
g
w
i
n
d
o
w
l
o
n
g
s
h
o
r
t
-
t
e
r
m
mem
o
r
y
,
”
E
n
g
i
n
e
e
ri
n
g
Ap
p
l
i
c
a
t
i
o
n
s
o
f
C
o
m
p
u
t
a
t
i
o
n
a
l
F
l
u
i
d
Me
c
h
a
n
i
c
s
,
v
o
l
.
1
6
,
n
o
.
1
,
p
p
.
2
4
8
–
2
6
1
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
8
0
/
1
9
9
4
2
0
6
0
.
2
0
2
1
.
2
0
0
9
3
7
4
.
[
2
5
]
B
.
C
h
a
r
b
u
t
y
a
n
d
A
.
A
b
d
u
l
a
z
e
e
z
,
“
C
l
a
ssi
f
i
c
a
t
i
o
n
b
a
se
d
o
n
d
e
c
i
si
o
n
t
r
e
e
a
l
g
o
r
i
t
h
m
f
o
r
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
J
o
u
rn
a
l
o
f
A
p
p
l
i
e
d
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
T
r
e
n
d
s
,
v
o
l
.
2
,
n
o
.
0
1
,
p
p
.
2
0
–
2
8
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
3
8
0
9
4
/
j
a
s
t
t
2
0
1
6
5
.
[
2
6
]
Y
.
I
z
z
a
,
A
.
I
g
n
a
t
i
e
v
,
a
n
d
J.
M
.
-
S
i
l
v
a
,
“
O
n
e
x
p
l
a
i
n
i
n
g
d
e
c
i
s
i
o
n
t
r
e
e
s
,
”
a
rX
i
v
:
2
0
1
0
.
1
1
0
3
4
,
O
c
t
.
2
0
2
0
[
2
7
]
Ž.
V
u
j
o
v
i
ć
,
“
C
l
a
ssi
f
i
c
a
t
i
o
n
m
o
d
e
l
e
v
a
l
u
a
t
i
o
n
m
e
t
r
i
c
s,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ad
v
a
n
c
e
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
2
,
n
o
.
6
,
p
p
.
5
9
9
–
6
0
6
,
2
0
2
1
,
d
o
i
:
1
0
.
1
4
5
6
9
/
I
JA
C
S
A
.
2
0
2
1
.
0
1
2
0
6
7
0
.
[
2
8
]
D
.
M
ü
l
l
e
r
,
I
.
S
.
-
R
e
y
,
a
n
d
F
.
K
r
a
m
e
r
,
“
To
w
a
r
d
s a
g
u
i
d
e
l
i
n
e
f
o
r
e
v
a
l
u
a
t
i
o
n
m
e
t
r
i
c
s i
n
m
e
d
i
c
a
l
i
ma
g
e
s
e
g
me
n
t
a
t
i
o
n
,
”
BM
C
R
e
se
a
rc
h
N
o
t
e
s
,
v
o
l
.
1
5
,
n
o
.
1
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
8
6
/
s
1
3
1
0
4
-
0
2
2
-
0
6
0
9
6
-
y.
[
2
9
]
A
.
A
.
-
D
u
a
r
t
,
E.
M
a
r
i
o
t
t
i
,
D
.
G
.
-
G
a
s
u
l
l
a
,
a
n
d
J.
M
.
A
.
-
M
o
r
a
l
,
“
A
c
o
n
f
u
si
o
n
mat
r
i
x
f
o
r
e
v
a
l
u
a
t
i
n
g
f
e
a
t
u
r
e
a
t
t
r
i
b
u
t
i
o
n
me
t
h
o
d
s,
”
i
n
I
EEE
C
o
m
p
u
t
e
r
S
o
c
i
e
t
y
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
e
r
V
i
si
o
n
a
n
d
Pa
t
t
e
rn
Re
c
o
g
n
i
t
i
o
n
W
o
rk
sh
o
p
s
,
J
u
n
.
2
0
2
3
,
p
p
.
3
7
0
9
–
3
7
1
4
,
d
o
i
:
1
0
.
1
1
0
9
/
C
V
P
R
W
5
9
2
2
8
.
2
0
2
3
.
0
0
3
8
0
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ro
sy
ih
a
n
Mu
h
ta
d
lo
r
re
c
e
n
tl
y
g
ra
d
u
a
ted
fro
m
th
e
De
p
a
rt
m
e
n
t
o
f
El
e
c
tri
c
a
l
En
g
i
n
e
e
rin
g
a
n
d
In
f
o
rm
a
ti
c
s,
m
a
jo
rin
g
in
S
o
ftwa
re
E
n
g
i
n
e
e
rin
g
Tec
h
n
o
l
o
g
y
a
t
t
h
e
Vo
c
a
ti
o
n
a
l
Co
ll
e
g
e
,
Un
iv
e
rsitas
G
a
d
jah
M
a
d
a
,
In
d
o
n
e
sia
.
He
h
a
s
a
stro
n
g
in
tere
st
in
i
n
fo
rm
a
ti
o
n
tec
h
n
o
l
o
g
y
,
with
a
fo
c
u
s
o
n
we
b
d
e
v
e
lo
p
m
e
n
t
a
n
d
a
rti
ficia
l
in
t
e
ll
ig
e
n
c
e
.
Du
rin
g
h
is
ti
m
e
in
c
o
ll
e
g
e
,
h
e
a
c
ti
v
e
ly
p
a
rti
c
i
p
a
ted
in
v
a
rio
u
s
i
n
tern
sh
i
p
p
ro
g
ra
m
s
a
n
d
w
o
rk
e
d
o
n
n
u
m
e
ro
u
s
p
ro
jec
ts,
g
a
in
i
n
g
v
a
lu
a
b
le
e
x
p
e
ri
e
n
c
e
in
th
e
IT
in
d
u
str
y
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
m
a
c
h
in
e
lea
rn
in
g
a
n
d
we
b
d
e
v
e
l
o
p
m
e
n
t
.
H
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ro
sih
a
n
n
1
4
@m
a
il
.
u
g
m
.
a
c
.
id
.
Nur
Ro
h
m
a
n
Ro
s
y
id
h
a
s
b
e
e
n
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
i
n
th
e
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
En
g
i
n
e
e
rin
g
a
n
d
I
n
fo
r
m
a
ti
c
s
a
t
th
e
Vo
c
a
ti
o
n
a
l
Co
ll
e
g
e
,
Un
iv
e
rsitas
G
a
d
jah
M
a
d
a
,
In
d
o
n
e
sia
,
si
n
c
e
2
0
0
7
.
He
h
o
l
d
s
a
m
a
ste
r’s
d
e
g
re
e
in
El
e
c
tri
c
a
l
En
g
i
n
e
e
rin
g
fr
o
m
Un
i
v
e
rsitas
G
a
d
jah
M
a
d
a
a
n
d
a
Do
c
to
r
o
f
En
g
i
n
e
e
rin
g
(
Dr.
En
g
.
)
d
e
g
re
e
i
n
El
e
c
tri
c
a
l
E
n
g
i
n
e
e
rin
g
fro
m
Kin
g
M
o
n
g
k
u
t’s
In
sti
tu
te
o
f
Tec
h
n
o
l
o
g
y
Lad
k
ra
b
a
n
g
,
T
h
a
il
a
n
d
.
His
re
se
a
rc
h
a
re
a
s
in
c
lu
d
e
n
e
two
rk
se
c
u
rit
y
,
v
irt
u
a
li
z
a
ti
o
n
,
n
e
two
rk
a
n
a
l
y
sis,
a
n
d
a
rti
ficia
l
i
n
te
ll
ig
e
n
c
e
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
n
ro
h
m
a
n
r@
u
g
m
.
a
c
.
id
.
Ann
i
K
a
r
im
a
tu
l
F
a
u
z
i
y
y
a
h
h
a
s
b
e
e
n
a
lec
tu
re
r
in
th
e
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
En
g
i
n
e
e
rin
g
a
n
d
In
f
o
rm
a
ti
c
s
a
t
t
h
e
Vo
c
a
ti
o
n
a
l
Co
ll
e
g
e
,
U
n
iv
e
rsi
tas
G
a
d
jah
M
a
d
a
,
In
d
o
n
e
sia
,
sin
c
e
2
0
2
1
.
S
h
e
h
o
l
d
s
a
m
a
ste
r’s
d
e
g
re
e
in
I
n
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
fro
m
Un
iv
e
rsitas
G
a
d
jah
M
a
d
a
.
He
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
n
e
two
r
k
a
n
d
d
istri
b
u
te
d
sy
ste
m
s
a
s
we
ll
a
s
d
a
ta
e
n
g
in
e
e
rin
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
n
n
i.
k
a
rima
tu
l.
f@m
a
il
.
u
g
m
.
a
c
.
id
.
Evaluation Warning : The document was created with Spire.PDF for Python.