T
E
L
K
O
M
NIKA
T
elec
o
mm
un
ica
t
io
n Co
m
pu
t
i
ng
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
24
,
No
.
4
,
A
u
g
u
s
t
20
26
,
p
p
.
1
197
~1
2
0
3
I
SS
N:
1
6
9
3
-
6
9
3
0
,
DOI
: 1
0
.
1
2
9
2
8
/
T
E
L
KOM
NI
K
A
.
v
24
i
4
.
27724
1197
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//telko
mn
ika
.
u
a
d
.
a
c.
i
d
Interpre
table
m
a
chine learni
ng
f
o
r
digita
l s
o
il p
H
ma
pping
using
an o
pti
m
i
z
e
d AdaB
o
o
st
a
lg
o
ri
th
m
Z
a
kiy
y
a
n
Z
a
i
n Al
k
a
f
1
, A
’
is
y
a
Nur
Aulia
Yus
uf
2
,
E
ls
a
Sa
ri
H
a
y
un
a
h Nurdini
y
a
h
2
,
T
r
i Wisu
da
w
a
t
i
1
1
D
e
p
a
r
t
me
n
t
o
f
I
n
d
u
s
t
r
i
a
l
En
g
i
n
e
e
r
i
n
g
a
n
d
M
e
c
h
a
n
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
En
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
t
a
s
Je
n
d
e
r
a
l
S
o
e
d
i
r
man
,
P
u
r
w
o
k
e
r
t
o
,
I
n
d
o
n
e
si
a
2
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
,
F
a
c
u
l
t
y
o
f
En
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
t
a
s
Je
n
d
e
r
a
l
S
o
e
d
i
r
man
,
P
u
r
w
o
k
e
r
t
o
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
17
,
2025
R
ev
i
s
ed
Mar
30
,
2
0
2
6
A
cc
ep
ted
Ma
y
25
,
2026
S
o
il
p
H
is
a
f
u
n
d
a
m
e
n
tal
p
a
r
a
m
e
ter
d
e
ter
m
in
in
g
n
u
tri
e
n
t
a
v
a
il
a
b
il
it
y
,
m
icro
b
ial
a
c
ti
v
it
y
,
a
n
d
c
ro
p
p
ro
d
u
c
ti
v
it
y
.
Un
li
k
e
p
re
v
io
u
s
stu
d
ies
th
a
t
o
f
ten
p
rio
ri
ti
z
e
p
re
d
ictio
n
a
c
c
u
ra
c
y
o
v
e
r
e
x
p
lain
a
b
il
it
y
,
th
is
stu
d
y
p
r
o
p
o
se
s
a
n
in
terp
re
tab
le
m
a
c
h
in
e
-
lea
rn
in
g
f
r
a
m
e
w
o
rk
in
teg
ra
ti
n
g
h
y
p
e
r
p
a
ra
m
e
ter
-
o
p
ti
m
ize
d
a
d
a
p
ti
v
e
b
o
o
st
in
g
(A
d
a
Bo
o
st)
w
it
h
S
h
a
p
ley
A
d
d
it
iv
e
e
x
P
la
n
a
ti
o
n
s
(S
HA
P
)
to
u
n
ra
v
e
l
th
e
sp
a
ti
a
l
d
ri
v
e
rs
o
f
so
il
p
H.
A
sy
st
e
m
a
ti
c
w
o
rk
f
lo
w
w
a
s
im
p
le
m
e
n
ted
to
e
v
a
lu
a
te
a
d
iv
e
rse
se
t
o
f
a
lg
o
rit
h
m
s,
f
o
ll
o
w
e
d
b
y
Ba
y
e
si
a
n
o
p
ti
m
iza
ti
o
n
to
f
in
e
-
tu
n
e
th
e
b
e
st
-
p
e
rf
o
rm
in
g
m
o
d
e
ls.
T
h
e
re
su
lt
s
d
e
m
o
n
stra
ted
th
a
t
th
e
o
p
ti
m
iz
e
d
A
d
a
Bo
o
st
m
o
d
e
l
y
ield
e
d
th
e
larg
e
st
p
e
rf
o
r
m
a
n
c
e
i
m
p
ro
v
e
m
e
n
t
(~
7
.
5
%
),
a
c
h
iev
in
g
e
x
c
e
ll
e
n
t
a
c
c
u
ra
c
y
o
n
in
d
e
p
e
n
d
e
n
t
tes
t
d
a
ta
w
it
h
a
c
o
e
f
f
icie
n
t
o
f
d
e
term
in
a
ti
o
n
(
R²
)
o
f
0
.
8
1
7
a
n
d
a
m
e
a
n
a
b
so
lu
te
e
rro
r
(M
A
E)
o
f
0
.
2
9
3
.
F
u
rt
h
e
rm
o
re
,
S
HA
P
a
n
a
ly
sis
id
e
n
ti
f
ied
i
ro
n
(
F
e
)
a
n
d
c
a
lciu
m
c
a
rb
o
n
a
te
(
Ca
CO₃
)
a
s
th
e
m
o
st
in
f
lu
e
n
ti
a
l
p
re
d
icto
rs,
re
v
e
a
li
n
g
th
a
t
F
e
e
x
h
ib
it
s
a
str
o
n
g
in
v
e
rse
re
latio
n
sh
i
p
w
it
h
p
H,
w
h
il
e
Ca
CO₃
sh
o
ws
a
p
o
siti
v
e
a
ss
o
c
iat
io
n
.
T
h
is
f
ra
m
e
w
o
rk
su
c
c
e
ss
f
u
ll
y
b
a
lan
c
e
s
h
ig
h
p
re
d
ictiv
e
a
c
c
u
ra
c
y
w
it
h
p
e
d
o
l
o
g
ica
l
in
terp
re
tab
i
li
ty
,
o
ff
e
rin
g
a
ro
b
u
st
to
o
l
f
o
r
d
ig
it
a
l
so
i
l
m
a
p
p
in
g
a
n
d
p
re
c
isio
n
a
g
ricu
lt
u
re
.
K
ey
w
o
r
d
s
:
A
d
aB
o
o
s
t r
eg
r
ess
o
r
B
ay
e
s
ian
o
p
ti
m
izatio
n
Dig
ital
s
o
il
m
ap
p
i
n
g
Ma
ch
i
n
e
lear
n
i
n
g
P
r
ec
is
io
n
ag
r
icu
l
tu
r
e
Sh
ap
le
y
A
d
d
iti
v
e
ex
P
la
n
atio
n
s
So
il p
H
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
:
Z
a
k
i
y
y
a
n
Z
a
in
A
l
k
a
f
Dep
ar
t
m
en
t o
f
I
n
d
u
s
tr
ial
E
n
g
i
n
ee
r
in
g
an
d
Me
c
h
an
ica
l E
n
g
i
n
ee
r
in
g
,
Fac
u
lt
y
o
f
E
n
g
i
n
ee
r
i
n
g
Un
i
v
er
s
ita
s
J
en
d
er
al
So
ed
ir
m
a
n
P
u
r
w
o
k
er
to
,
I
n
d
o
n
es
ia
E
m
ail:
Z
a
k
i
y
y
a
n
.
alk
a
f
@
u
n
s
o
ed
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
So
il
p
H
is
a
f
u
n
d
a
m
e
n
tal
p
a
r
a
m
eter
d
eter
m
i
n
i
n
g
s
o
il
q
u
a
lit
y
,
r
e
g
u
la
tin
g
n
u
tr
ien
t
b
io
av
ailab
ilit
y
,
m
icr
o
b
ial
ac
tiv
i
t
y
,
a
n
d
o
v
er
all
cr
o
p
p
r
o
d
u
ctiv
it
y
[
1
]
.
T
o
en
s
u
r
e
o
p
ti
m
al
p
lan
t
h
ea
l
th
,
m
ac
r
o
n
u
tr
ie
n
ts
(
n
itro
g
e
n
(
N
)
,
p
h
o
s
p
h
o
r
u
s
(
P
)
,
an
d
p
o
ta
s
s
i
u
m
(
K
)
)
m
u
s
t
r
e
m
ai
n
av
ail
ab
le
w
h
ile
m
ai
n
tai
n
in
g
m
icr
o
n
u
tr
ie
n
t
s
(
ir
o
n
(
Fe)
,
m
an
g
a
n
ese
(
Mn
)
,
an
d
zin
c
(
Z
n
)
)
at
n
o
n
-
to
x
ic
lev
els
[
2
]
.
C
o
n
s
eq
u
e
n
tl
y
,
u
n
d
er
s
tan
d
i
n
g
th
e
s
p
atial
d
is
tr
ib
u
tio
n
o
f
s
o
il
p
H
i
s
cr
itical
f
o
r
en
v
ir
o
n
m
e
n
tal
m
o
n
ito
r
in
g
a
n
d
p
r
ec
is
io
n
a
g
r
icu
l
tu
r
e,
e
n
ab
lin
g
s
ite
-
s
p
ec
i
f
ic
m
an
a
g
e
m
e
n
t
s
tr
ate
g
ies
s
u
c
h
as
v
ar
iab
le
-
r
ate
li
m
i
n
g
t
h
at
m
i
n
i
m
ize
en
v
ir
o
n
m
en
tal
r
is
k
s
lik
e
g
r
o
u
n
d
w
ater
p
o
llu
tio
n
[
3
]
.
A
cc
u
r
ate
d
i
g
ital
s
o
il
m
ap
p
i
n
g
s
er
v
e
s
as
t
h
e
f
o
u
n
d
atio
n
al
la
y
er
f
o
r
in
ter
n
et
o
f
th
i
n
g
s
(
I
o
T
)
-
b
ased
s
m
ar
t
f
ar
m
i
n
g
s
y
s
te
m
s
,
en
ab
lin
g
v
ar
iab
le
-
r
ate
tec
h
n
o
lo
g
y
(
VR
T
)
to
ad
j
u
s
t
in
p
u
t
s
p
r
ec
is
el
y
b
ased
o
n
t
h
e
s
p
atial
d
is
tr
ib
u
tio
n
o
f
s
o
il p
r
o
p
er
ties
.
W
h
ile
tr
ad
itio
n
al
w
et
c
h
e
m
is
t
r
y
m
e
th
o
d
s
ar
e
ac
c
u
r
ate,
t
h
e
y
ar
e
lab
o
r
-
in
te
n
s
i
v
e
a
n
d
co
s
tl
y
f
o
r
lar
g
e
-
s
ca
le
m
ap
p
in
g
.
A
lter
n
ati
v
el
y
,
m
ac
h
in
e
lear
n
in
g
(
ML
)
h
a
s
e
m
er
g
ed
as
a
p
o
w
er
f
u
l
to
o
l
f
o
r
d
ig
ital
s
o
il
m
ap
p
in
g
,
w
i
th
e
n
s
e
m
b
le
m
e
th
o
d
s
s
u
c
h
as
r
an
d
o
m
f
o
r
est
s
(
R
F)
,
g
r
ad
ien
t
b
o
o
s
tin
g
,
an
d
s
u
p
p
o
r
t
v
ec
to
r
re
gr
ess
io
n
(
SVR
)
d
e
m
o
n
s
tr
atin
g
th
e
ab
ilit
y
to
ca
p
tu
r
e
co
m
p
lex
n
o
n
li
n
ea
r
r
elatio
n
s
h
ip
s
b
et
w
ee
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
24
,
No
.
4
,
A
u
g
u
s
t
20
26
:
1
197
-
1
2
0
3
1198
en
v
ir
o
n
m
e
n
tal
co
v
ar
iates
a
n
d
s
o
il
p
H
[
4
]
,
[
5
]
ML
o
p
ti
m
i
za
tio
n
h
a
s
p
r
o
v
en
e
f
f
ec
ti
v
e
i
n
v
ar
io
u
s
d
o
m
a
in
s
,
r
an
g
i
n
g
f
r
o
m
i
n
d
u
s
tr
ial
r
e
s
o
u
r
ce
allo
ca
tio
n
[
6
]
to
co
n
s
u
m
er
p
r
ef
er
en
ce
a
n
al
y
s
i
s
i
n
e
-
co
m
m
e
r
ce
m
ar
k
et
s
[
7
]
.
Ho
w
e
v
er
,
ex
is
tin
g
s
t
u
d
ies
o
f
te
n
s
u
f
f
er
f
r
o
m
t
w
o
m
aj
o
r
li
m
it
atio
n
s
:
t
h
e
u
s
e
o
f
d
ef
a
u
lt
h
y
p
e
r
p
ar
am
eter
s
,
w
h
ic
h
lead
s
to
s
u
b
o
p
ti
m
al
m
o
d
el
p
er
f
o
r
m
a
n
ce
,
an
d
a
“
b
lack
-
box
”
n
atu
r
e
th
at
lac
k
s
i
n
ter
p
r
etab
ilit
y
.
Sp
ec
i
f
icall
y
,
f
e
w
s
tu
d
ie
s
h
a
v
e
p
r
o
p
o
s
ed
o
p
ti
m
ized
en
s
e
m
b
le
m
o
d
el
s
in
te
g
r
ated
w
it
h
i
n
ter
p
r
etab
ilit
y
t
o
o
ls
(
e.
g
.
,
Sh
ap
le
y
A
d
d
iti
v
e
ex
P
lan
atio
n
s
(
SH
A
P
)
)
f
o
r
s
o
il
p
H
m
ap
p
in
g
,
cr
ea
ti
n
g
a
g
ap
i
n
u
n
d
er
s
tan
d
i
n
g
t
h
e
p
ed
o
lo
g
ical
d
r
iv
er
s
b
eh
in
d
p
r
ed
ictio
n
[
8
]
-
[
1
0
]
.
T
h
e
p
r
im
ar
y
n
o
v
e
lt
y
o
f
t
h
is
s
t
u
d
y
lie
s
i
n
th
e
s
y
n
er
g
is
t
ic
in
te
g
r
atio
n
o
f
B
a
y
esia
n
-
o
p
ti
m
ized
ad
ap
tiv
e
b
o
o
s
tin
g
(
A
d
aB
o
o
s
t
)
w
it
h
SH
A
P
-
b
ased
i
n
ter
p
r
etab
ilit
y
.
Un
li
k
e
s
ta
n
d
ar
d
en
s
e
m
b
le
ap
p
r
o
ac
h
es,
th
i
s
f
r
a
m
e
w
o
r
k
n
o
t
o
n
l
y
i
m
p
r
o
v
es
p
r
ed
ictiv
e
ac
cu
r
ac
y
b
u
t
also
d
ec
ip
h
er
s
th
e
‘
b
lack
-
box
’
lo
g
i
c
to
r
ev
ea
l
cr
itical
p
ed
o
lo
g
ical
d
r
iv
er
s
.
F
ir
s
t,
w
e
i
m
p
le
m
en
t
a
r
ig
o
r
o
u
s
p
r
ep
r
o
ce
s
s
i
n
g
a
n
d
f
ea
tu
r
e
s
elec
tio
n
p
ip
elin
e
to
en
s
u
r
e
h
ig
h
d
ata
q
u
alit
y
.
S
e
c
o
n
d
,
w
e
s
y
s
tem
a
t
ic
a
l
ly
ev
a
lu
at
e
d
i
v
e
r
s
e
r
e
g
r
e
s
s
i
o
n
a
lg
o
r
i
th
m
s
,
o
p
t
im
i
zin
g
th
e
t
o
p
p
e
r
f
o
r
m
e
r
s
u
s
in
g
B
ay
es
i
an
o
p
tim
i
z
a
ti
o
n
t
o
en
h
an
c
e
p
r
e
d
ic
t
iv
e
a
c
cu
r
a
cy
.
F
in
a
l
ly
,
w
e
em
p
l
o
y
S
HA
P
t
o
in
t
e
r
p
r
et
t
h
e
m
o
d
e
l
o
u
t
p
u
ts
.
T
h
is
s
tu
d
y
h
o
l
d
s
s
ig
n
if
ic
an
t
p
r
a
c
ti
c
a
l
r
e
lev
an
c
e
f
o
r
p
r
e
c
is
i
o
n
a
g
r
i
cu
l
tu
r
e
w
h
il
e
th
e
o
r
e
ti
c
a
lly
b
r
i
d
g
in
g
th
e
g
a
p
b
e
t
w
e
en
ML
o
p
t
im
i
z
a
ti
o
n
an
d
ex
p
l
ain
a
b
l
e
ar
t
i
f
i
c
i
al
in
t
el
l
ig
en
c
e
(
XA
I
)
in
s
o
i
l
s
ci
en
c
e
.
2.
M
E
T
H
O
D
T
h
is
s
tu
d
y
ad
o
p
ts
a
co
m
p
r
e
h
en
s
i
v
e
en
d
-
to
-
e
n
d
ML
w
o
r
k
f
lo
w
e
n
co
m
p
as
s
i
n
g
d
ata
ac
q
u
is
itio
n
,
p
r
ep
r
o
ce
s
s
in
g
,
f
ea
t
u
r
e
s
elec
t
io
n
,
m
o
d
el
b
en
c
h
m
ar
k
i
n
g
,
h
y
p
e
r
p
ar
am
eter
t
u
n
i
n
g
v
ia
B
a
y
e
s
ia
n
o
p
ti
m
izatio
n
,
an
d
SH
A
P
-
b
ased
in
ter
p
r
etab
ilit
y
a
n
al
y
s
i
s
to
id
en
ti
f
y
k
e
y
s
o
il p
H
d
r
iv
er
s
.
2
.
1
.
Da
t
a
s
et
d
escript
io
n
T
h
e
an
al
y
s
is
u
tili
ze
s
a
d
ataset
o
f
7
8
1
s
o
il
s
a
m
p
les
co
llected
f
r
o
m
a
g
r
icu
l
tu
r
al
f
ield
s
in
t
h
e
Gr
ev
en
a
r
eg
io
n
,
No
r
th
er
n
Gr
ee
ce
,
b
etw
ee
n
2
0
1
5
an
d
2
0
1
9
.
T
h
e
s
a
m
p
les
w
er
e
tak
e
n
f
r
o
m
a
d
ep
th
o
f
0
–
3
0
cm
,
co
v
er
in
g
a
w
id
e
r
an
g
e
o
f
s
o
il
tex
tu
r
es
a
n
d
ch
e
m
ical
p
r
o
p
er
ties
t
y
p
ical
o
f
Me
d
iter
r
an
ea
n
ag
r
icu
l
tu
r
al
zo
n
e
s
.
T
h
e
d
ataset
w
a
s
o
b
tain
ed
f
r
o
m
t
h
e
So
il
a
n
d
W
ater
R
e
s
ea
r
ch
I
n
s
tit
u
te
(
SW
R
I
)
a
n
d
in
cl
u
d
es
k
e
y
p
ar
a
m
eter
s
s
u
c
h
as
p
H,
o
r
g
an
ic
m
a
tter
,
an
d
m
icr
o
-
n
u
tr
ie
n
ts
,
en
s
u
r
i
n
g
s
u
f
f
icien
t
v
ar
iab
ilit
y
f
o
r
tr
ain
i
n
g
r
o
b
u
s
t
ML
m
o
d
els
[
1
1
]
.
T
h
e
p
r
ed
icto
r
s
et
in
clu
d
es
elec
tr
ical
co
n
d
u
cti
v
it
y
(
E
C
)
,
o
r
g
an
ic
m
atter
(
OM
)
,
n
itra
t
e
n
itro
g
e
n
(N
-
N
O₃)
,
P
,
K,
m
a
g
n
e
s
i
u
m
(
M
g
)
,
an
d
Fe.
A
d
d
itio
n
all
y
,
t
h
e
d
ataset
in
co
r
p
o
r
ates
m
icr
o
n
u
tr
ie
n
ts
in
clu
d
i
n
g
Z
n
,
M
n
,
co
p
p
er
(
C
u
)
,
an
d
b
o
r
o
n
(
B
)
,
as
w
ell
as
ca
lciu
m
ca
r
b
o
n
ate
(
C
aCO₃)
,
w
h
ich
is
e
x
p
licitl
y
in
cl
u
d
ed
d
u
e
to
its
cr
itical
r
o
le
in
p
H
b
u
f
f
er
in
g
ca
p
ac
it
y
.
So
il tex
t
u
r
e
is
r
ep
r
esen
ted
b
y
s
a
n
d
,
s
ilt,
an
d
cla
y
p
er
ce
n
tag
e
s
.
2
.
2
.
Resea
rc
h
wo
rk
f
lo
w
a
nd
prepro
ce
s
s
i
ng
T
o
en
s
u
r
e
r
ep
r
o
d
u
cib
ilit
y
,
t
h
e
w
o
r
k
f
lo
w
w
a
s
s
tr
u
ct
u
r
ed
u
s
i
n
g
a
Scik
i
t
-
lear
n
P
ip
elin
e
(
Fi
g
u
r
e
1
)
.
T
h
e
d
ataset
w
a
s
p
ar
titi
o
n
ed
in
to
tr
ain
in
g
(
8
0
%)
an
d
test
in
g
(
2
0
%)
s
ets
f
o
r
u
n
b
iased
ev
al
u
a
tio
n
[
1
2
]
.
Miss
in
g
v
alu
e
s
w
er
e
h
an
d
led
u
s
in
g
m
e
d
ian
i
m
p
u
tatio
n
to
ac
co
m
m
o
d
ate
s
o
il
h
eter
o
g
en
ei
t
y
,
w
h
ile
o
u
tlier
s
w
er
e
ca
p
p
ed
u
s
i
n
g
t
h
e
i
n
ter
q
u
ar
tile
r
a
n
g
e
(
I
QR
)
m
et
h
o
d
b
ased
s
o
lel
y
o
n
tr
ai
n
in
g
s
et
s
tatis
tics
to
p
r
ev
en
t
d
ata
lea
k
ag
e.
W
in
s
o
r
izatio
n
w
as
s
u
b
s
eq
u
en
tl
y
ap
p
lied
at
t
h
e
1
s
t
an
d
9
9
th
p
er
ce
n
ti
les,
f
o
llo
w
ed
b
y
s
tan
d
ar
d
s
ca
li
n
g
to
i
m
p
r
o
v
e
m
o
d
el
co
n
v
er
g
en
ce
[
1
3
]
.
A
ll
ex
p
er
i
m
e
n
ts
w
er
e
co
n
d
u
cted
in
Go
o
g
le
C
o
lab
(
P
y
t
h
o
n
3
)
u
s
in
g
Sci
k
it
-
lear
n
w
ith
a
f
ix
ed
r
an
d
o
m
s
ee
d
o
f
4
2
t
o
g
u
ar
an
tee
r
ep
r
o
d
u
cib
ilit
y
.
C
o
m
p
lex
n
o
n
-
li
n
ea
r
tr
an
s
f
o
r
m
atio
n
s
w
er
e
d
elib
er
ately
av
o
id
ed
,
as
tr
ee
-
b
ased
en
s
e
m
b
le
m
o
d
els
ar
e
i
n
v
ar
ia
n
t
to
m
o
n
o
to
n
ic
f
ea
t
u
r
e
s
ca
li
n
g
,
th
er
eb
y
p
r
eser
v
in
g
th
e
p
h
y
s
i
ca
l i
n
ter
p
r
etab
ilit
y
o
f
s
o
il
m
ea
s
u
r
e
m
e
n
t
u
n
i
ts
.
2.
3
.
F
e
a
t
ure
s
elec
t
io
n
Featu
r
e
s
e
lectio
n
w
a
s
ap
p
lied
to
r
ed
u
ce
d
i
m
en
s
io
n
ali
t
y
a
n
d
m
it
ig
ate
o
v
er
f
i
tti
n
g
[
1
4
]
.
A
R
an
d
o
m
Fo
r
estR
e
g
r
es
s
o
r
w
as
tr
ain
ed
o
n
p
r
ep
r
o
ce
s
s
ed
d
ata,
r
etain
in
g
o
n
l
y
f
ea
t
u
r
es
w
it
h
i
m
p
o
r
tan
ce
s
co
r
es
ex
ce
ed
in
g
th
e
m
ea
n
th
r
es
h
o
ld
[
1
5
]
.
T
h
is
s
in
g
le
-
p
ass
ap
p
r
o
ac
h
ef
f
icie
n
tl
y
ca
p
tu
r
e
s
n
o
n
-
li
n
ea
r
f
ea
tu
r
e
in
ter
ac
tio
n
s
w
it
h
o
u
t
t
h
e
co
m
p
u
tatio
n
a
l
o
v
er
h
ea
d
o
f
w
r
ap
p
er
m
eth
o
d
s
s
u
c
h
as
r
ec
u
r
s
iv
e
f
ea
tu
r
e
eli
m
in
a
tio
n
(
R
FE)
,
w
h
ic
h
r
eq
u
ir
es r
ep
ea
ted
m
o
d
el
r
etr
ain
i
n
g
f
o
r
ea
ch
f
e
atu
r
e
s
u
b
s
et
[
1
6
]
,
[
1
7
]
.
2.
4
.
M
o
del
dev
elo
p
m
ent
a
nd
ev
a
lua
t
io
n
T
o
id
en
tify
th
e
m
o
s
t
ef
f
ec
ti
v
e
p
r
e
d
ictiv
e
s
tr
ateg
y
f
o
r
s
o
il
p
H,
w
e
b
en
ch
m
ar
k
ed
n
i
n
e
r
eg
r
ess
io
n
alg
o
r
ith
m
s
s
p
an
n
i
n
g
d
is
ti
n
ct
l
ea
r
n
in
g
p
ar
ad
ig
m
s
:
li
n
ea
r
ap
p
r
o
ac
h
es
(
lin
ea
r
,
r
id
g
e,
a
n
d
las
s
o
r
eg
r
ess
io
n
)
,
tr
ee
-
b
ased
en
s
e
m
b
le
s
(
d
ec
is
io
n
tr
ee
(
DT
)
,
R
F,
g
r
ad
ien
t
b
o
o
s
tin
g
,
a
n
d
A
d
aB
o
o
s
t)
,
an
d
k
er
n
el
/i
n
s
ta
n
ce
-
b
ased
m
et
h
o
d
s
(
SVR
an
d
K
-
n
ea
r
est
n
eig
h
b
o
r
s
(
KNN
)
)
.
A
u
n
i
f
ie
d
p
r
e
p
r
o
ce
s
s
in
g
p
ip
elin
e
w
as
ap
p
lied
id
en
ticall
y
ac
r
o
s
s
all
m
o
d
els.
A
lt
h
o
u
g
h
tr
ee
-
b
ased
m
o
d
els
ar
e
in
v
ar
ia
n
t
to
f
ea
tu
r
e
s
ca
l
in
g
,
d
is
ta
n
ce
-
b
a
s
ed
m
o
d
els
s
u
ch
a
s
SVR
a
n
d
KNN
r
eq
u
ir
e
s
ta
n
d
ar
d
ized
in
p
u
ts
;
t
h
er
ef
o
r
e,
all
d
atasets
u
n
d
er
w
en
t
W
i
n
s
o
r
iz
atio
n
an
d
s
tan
d
ar
d
s
ca
lin
g
p
r
io
r
to
tr
ain
in
g
to
en
s
u
r
e
a
co
n
s
is
ten
t e
v
al
u
atio
n
b
as
elin
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
I
n
terp
r
eta
b
le
ma
ch
in
e
lea
r
n
i
n
g
fo
r
d
ig
ita
l so
il p
H
ma
p
p
in
g
u
s
in
g
a
n
o
p
timiz
ed
…
(
Za
kiyy
a
n
Za
in
A
lka
f
)
1199
Fig
u
r
e
1
.
R
esid
u
al
s
ca
tter
p
lo
t a
n
d
er
r
o
r
h
is
to
g
r
a
m
Mo
d
el
g
en
er
aliza
tio
n
w
a
s
as
s
ess
ed
u
s
i
n
g
5
-
f
o
ld
cr
o
s
s
-
v
al
id
atio
n
(
C
V)
o
n
th
e
tr
ain
i
n
g
s
et
[
1
8
]
.
P
er
f
o
r
m
a
n
ce
w
as
q
u
a
n
ti
f
ied
u
s
in
g
t
h
e
co
ef
f
icien
t
o
f
d
eter
m
i
n
atio
n
(
R
²)
,
m
ea
n
ab
s
o
l
u
te
er
r
o
r
(
MA
E
)
,
an
d
r
o
o
t
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
R
MSE
)
,
r
ep
o
r
ted
w
i
th
9
5
%
co
n
f
id
en
ce
in
ter
v
als
(
C
I
)
[
1
9
]
–
[
2
1
]
.
Hy
p
er
p
ar
am
eter
tu
n
i
n
g
w
a
s
co
n
d
u
cted
v
ia
B
a
y
es
ian
o
p
tim
izat
io
n
,
w
h
ic
h
ef
f
icie
n
tl
y
n
a
v
ig
a
tes
h
i
g
h
-
d
i
m
e
n
s
io
n
al
s
ea
r
ch
s
p
ac
e
s
co
m
p
ar
ed
to
ex
h
a
u
s
ti
v
e
g
r
id
s
ea
r
ch
[
2
2
]
,
w
it
h
i
n
th
e
r
an
g
e
s
d
ef
in
ed
in
T
ab
le
1
.
T
h
e
o
p
ti
m
ized
m
o
d
el
w
as
s
u
b
s
eq
u
en
t
l
y
i
n
ter
p
r
eted
u
s
in
g
SH
A
P
,
w
h
ic
h
q
u
an
t
if
ie
s
ea
ch
f
ea
t
u
re
’
s
m
ar
g
i
n
al
co
n
tr
ib
u
tio
n
to
p
r
ed
ictio
n
s
,
p
r
o
v
id
in
g
b
o
th
g
lo
b
al
f
ea
t
u
r
e
r
an
k
i
n
g
s
a
n
d
lo
ca
l
in
s
tan
ce
-
l
ev
el
ex
p
la
n
atio
n
s
g
r
o
u
n
d
ed
i
n
co
o
p
er
ativ
e
g
a
m
e
th
eo
r
y
[
2
3
]
.
T
ab
le
1
.
R
esu
lt o
f
p
r
ed
ictio
n
M
e
t
h
o
d
M
e
a
n
R
-
s
q
u
a
r
e
d
(
C
V
)
M
A
E
(
C
V
)
M
S
E
(
C
V
)
S
V
R
0
.
7
9
7
1
0
.
2
7
5
0
.
1
5
6
7
A
d
a
B
o
o
st
r
e
g
r
e
ss
o
r
0
.
7
9
2
3
0
.
2
9
0
.
1
6
3
1
G
r
a
d
i
e
n
t
b
o
o
st
i
n
g
r
e
g
r
e
sso
r
0
.
7
8
9
8
0
.
2
7
7
8
0
.
1
6
4
K
N
N
r
e
g
r
e
sso
r
0
.
7
7
0
9
0
.
2
9
7
3
0
.
1
7
7
3
R
F
r
e
g
r
e
sso
r
0
.
7
6
2
0
.
2
9
5
8
0
.
1
8
5
9
L
i
n
e
a
r
r
e
g
r
e
ssi
o
n
0
.
7
5
9
8
0
.
3
0
4
0
.
1
8
6
3
R
i
d
g
e
0
.
7
5
9
8
0
.
3
0
4
1
0
.
1
8
6
3
D
T
r
e
g
r
e
ss
o
r
0
.
6
3
8
7
0
.
3
7
4
0
.
2
8
8
L
a
ss
o
-
0
.
0
0
8
1
0
.
7
1
8
1
0
.
7
7
7
4
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
A
co
m
p
r
e
h
en
s
i
v
e
ev
al
u
atio
n
o
f
n
i
n
e
ML
alg
o
r
it
h
m
s
r
ev
ea
led
s
u
b
s
ta
n
tial
p
er
f
o
r
m
a
n
c
e
v
ar
iatio
n
,
p
r
o
v
id
in
g
i
m
p
o
r
tan
t
in
s
i
g
h
ts
i
n
to
th
e
co
m
p
lex
i
t
y
o
f
th
e
r
elat
io
n
s
h
ip
b
et
w
ee
n
s
o
il
p
r
o
p
e
r
ties
an
d
p
H
(
T
a
b
le
1
)
.
T
o
en
s
u
r
e
s
tati
s
tical
r
o
b
u
s
t
n
ess
,
m
o
d
el
g
e
n
er
aliza
tio
n
was
ass
es
s
ed
u
s
i
n
g
d
ef
a
u
lt
cr
o
s
s
-
v
alid
atio
n
,
w
i
t
h
p
er
f
o
r
m
a
n
ce
m
etr
ics
r
ep
o
r
ted
as
m
ea
n
±
9
5
%
C
I
.
T
h
e
SVR
m
o
d
el
p
er
f
o
r
m
ed
b
est
w
it
h
R
²
=
0
.
7
9
7
1
,
MA
E
=
0
.
2
7
5
,
an
d
MSE
=
0
.
1
5
6
7
,
in
d
icatin
g
s
u
p
er
io
r
ab
ilit
y
to
ca
p
tu
r
e
th
e
co
m
p
le
x
it
y
o
f
th
e
r
e
latio
n
s
h
ip
b
et
w
ee
n
s
o
il
f
ea
t
u
r
es
a
n
d
p
H.
T
h
e
s
u
p
er
io
r
ity
o
f
SV
R
s
te
m
s
f
r
o
m
it
s
ab
ilit
y
to
m
ap
d
ata
to
a
h
ig
h
-
d
i
m
e
n
s
io
n
al
s
p
ac
e
v
ia
k
er
n
e
l
f
u
n
ct
io
n
s
,
en
ab
li
n
g
th
e
m
o
d
elin
g
o
f
co
m
p
lex
n
o
n
lin
ea
r
r
elatio
n
s
h
ip
s
w
it
h
o
u
t
e
x
p
licitl
y
co
m
p
u
tin
g
tr
an
s
f
o
r
m
ati
o
n
s
[
2
4
]
.
I
n
th
e
co
n
tex
t
o
f
s
o
il
s
y
s
te
m
s
,
m
an
y
p
ed
o
g
en
ic
a
n
d
b
io
g
eo
ch
e
m
ical
p
r
o
ce
s
s
es
t
h
at
in
f
lu
e
n
ce
p
H
ar
e
n
o
n
li
n
ea
r
an
d
in
v
o
lv
e
m
u
l
tif
ac
e
ted
in
t
er
ac
tio
n
s
s
u
ch
as
b
u
f
f
er
in
g
ca
p
ac
it
y
,
w
h
ic
h
is
in
f
lu
e
n
ce
d
b
y
in
ter
ac
tio
n
s
b
etw
ee
n
cla
y
m
in
er
al
s
,
o
r
g
an
ic
m
atter
,
an
d
b
ase
ca
tio
n
s
[
2
5
]
.
S
VR
ca
n
ca
p
tu
r
e
th
i
s
co
m
p
le
x
it
y
m
o
r
e
ef
f
ec
tiv
e
l
y
t
h
an
li
n
ea
r
m
o
d
els.
T
h
e
en
s
em
b
le
m
o
d
els
A
d
aB
o
o
s
t
r
eg
r
ess
o
r
(
R
²
=
0
.
7
9
2
3
)
,
g
r
ad
ien
t
b
o
o
s
tin
g
r
e
g
r
ess
o
r
(
R
²
=
0
.
7
8
9
8
)
,
an
d
RF
r
eg
r
e
s
s
o
r
(
R
²
=
0
.
7
6
2
0
)
also
p
er
f
o
r
m
ed
v
er
y
w
ell,
co
n
s
is
ten
t
w
it
h
t
h
e
li
ter
atu
r
e
d
e
m
o
n
s
tr
atin
g
th
e
e
f
f
ec
ti
v
e
n
ess
o
f
e
n
s
e
m
b
le
m
et
h
o
d
s
in
s
o
il
p
r
o
p
er
ty
m
o
d
eli
n
g
[
2
6
]
,
[
27]
.
L
in
ea
r
m
o
d
els
—
l
i
n
ea
r
r
eg
r
es
s
io
n
,
r
id
g
e,
a
n
d
las
s
o
s
h
o
w
ed
s
ig
n
i
f
ica
n
tl
y
lo
w
er
p
er
f
o
r
m
an
ce
(
R
²
≈
0
.
7
6
)
,
w
i
th
la
s
s
o
ev
en
p
r
o
d
u
cin
g
a
n
e
g
ati
v
e
R
²
(
-
0
.
0
0
8
1
)
,
in
d
icatin
g
it
p
er
f
o
r
m
ed
w
o
r
s
e
th
a
n
p
r
ed
ictio
n
s
b
ased
o
n
th
e
tar
g
et
av
er
ag
e.
T
h
is
s
u
g
g
es
ts
th
a
t
s
o
il
p
H
p
r
ed
ictio
n
ca
n
n
o
t
b
e
r
ed
u
ce
d
to
a
s
im
p
le
li
n
ea
r
co
m
b
i
n
atio
n
o
f
p
r
ed
icto
r
f
ea
tu
r
es.
T
ab
le
2
p
r
esen
ts
th
e
co
m
p
ar
at
iv
e
p
er
f
o
r
m
an
ce
r
esu
lts
o
f
th
e
th
r
ee
b
est
m
o
d
els
af
ter
h
y
p
er
p
ar
am
eter
o
p
tim
izatio
n
.
A
ll
t
h
r
ee
m
o
d
e
ls
s
h
o
w
ed
s
i
g
n
i
f
ica
n
t
p
er
f
o
r
m
an
ce
i
m
p
r
o
v
e
m
e
n
ts
.
SV
R
i
m
p
r
o
v
ed
m
ar
g
i
n
all
y
(
~0
.
9
%),
w
h
ile
A
d
aB
o
o
s
t
ac
h
iev
ed
th
e
lar
g
e
s
t
g
a
in
(
~7
.
5
%
)
,
i
m
p
r
o
v
in
g
M
SE
f
r
o
m
0
.
1
6
3
1
to
0
.
1
5
0
9
.
T
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
24
,
No
.
4
,
A
u
g
u
s
t
20
26
:
1
197
-
1
2
0
3
1200
alig
n
m
e
n
t
co
n
f
ir
m
s
t
h
at
th
e
m
o
d
el
g
e
n
er
alize
s
w
el
l
to
u
n
s
ee
n
d
ata
an
d
d
o
es
n
o
t
ex
h
ib
it
s
i
g
n
i
f
ican
t
o
v
er
f
itti
n
g
.
A
d
aB
o
o
s
t
’
s
p
er
f
o
r
m
an
ce
ca
n
b
e
attr
ib
u
ted
to
its
s
eq
u
en
tial
lear
n
i
n
g
ar
ch
itec
tu
r
e
[
2
8
]
.
Un
lik
e
R
F,
w
h
ic
h
is
r
o
b
u
s
t
to
d
ef
a
u
lt
s
et
tin
g
s
,
A
d
aB
o
o
s
t
is
h
i
g
h
l
y
s
e
n
s
it
iv
e
to
t
h
e
lear
n
i
n
g
r
ate
a
n
d
esti
m
ato
r
co
u
n
t;
B
ay
e
s
ian
o
p
ti
m
izatio
n
allo
w
e
d
th
e
alg
o
r
ith
m
to
p
r
ec
is
el
y
ca
lib
r
ate
th
e
s
tep
s
ize
f
o
r
co
r
r
ec
tin
g
p
r
ed
ec
ess
o
r
er
r
o
r
s
,
ef
f
ec
tiv
el
y
r
ed
u
ci
n
g
b
i
as
w
i
th
o
u
t
in
c
u
r
r
in
g
h
i
g
h
v
ar
i
an
ce
.
g
r
ad
ien
t
b
o
o
s
tin
g
also
s
h
o
w
ed
i
m
p
r
o
v
e
m
e
n
t
(
~4
.
7
%)
b
u
t
r
eq
u
ir
ed
tu
n
i
n
g
a
m
o
r
e
co
m
p
lex
h
y
p
er
p
ar
a
m
et
er
s
p
ac
e
[
2
9
]
.
SVR
w
it
h
an
r
ad
ial
b
asis
f
u
n
ctio
n
(
R
B
F)
k
er
n
el
h
as
a
r
elativ
e
l
y
co
m
p
ac
t
h
y
p
er
p
ar
a
m
eter
s
p
ac
e
(
C
,
g
a
m
m
a,
ep
s
ilo
n
)
co
m
p
ar
ed
to
co
m
p
le
x
en
s
e
m
b
le
m
e
th
o
d
s
,
an
d
t
h
e
d
ef
au
lt v
al
u
es i
n
s
c
ik
i
t
-
lear
n
m
a
y
alr
ea
d
y
b
e
clo
s
e
to
o
p
tim
al
f
o
r
th
is
d
ataset
[
3
0
]
.
T
ab
le
2
.
R
esu
lt o
f
B
a
y
e
s
ian
o
p
ti
m
izatio
n
M
o
d
e
l
M
S
E
n
e
g
a
t
i
v
e
(
C
V
)
S
V
R
-
0
.
1
5
5
3
A
d
a
B
o
o
st
r
e
g
r
e
ss
o
r
-
0
.
1
5
0
9
G
r
a
d
i
e
n
t
b
o
o
st
i
n
g
r
e
g
r
e
sso
r
-
0
.
1
5
6
3
T
ab
le
3
p
r
esen
ts
t
h
e
r
es
u
lt
s
o
f
th
e
o
p
ti
m
ized
A
d
aB
o
o
s
t Reg
r
ess
o
r
o
n
i
n
d
ep
en
d
en
t
test
d
ata.
T
h
e
f
i
n
al
m
o
d
el
ac
h
ie
v
ed
an
R
²
o
f
0
.
8
1
7
2
,
in
d
icatin
g
th
a
t
it
e
x
p
lain
e
d
ap
p
r
o
x
im
atel
y
8
1
.
7
2
%
o
f
t
h
e
to
tal
v
ar
iab
ilit
y
i
n
s
o
il
p
H.
T
h
ese
r
esu
lts
ar
e
co
m
p
e
titi
v
e
w
it
h
r
ec
en
t
s
o
il
s
p
e
ctr
o
s
co
p
y
s
tu
d
ies
[
3
1
]
,
w
h
ic
h
t
y
p
icall
y
r
ep
o
r
t
R
²
v
alu
e
s
in
t
h
e
r
an
g
e
o
f
0
.
8
–
0
.
8
5
,
th
er
eb
y
v
alid
ati
n
g
th
e
ef
f
ic
ac
y
o
f
o
u
r
p
r
o
p
o
s
ed
f
r
am
e
w
o
r
k
.
Ou
r
m
o
d
el’
s
R
2
o
f
0
.
8
1
7
n
o
tab
ly
ex
ce
ed
s
t
y
p
i
ca
l
b
en
ch
m
ar
k
s
i
n
d
ig
ital
s
o
il
p
H
m
ap
p
in
g
,
w
h
ic
h
ar
e
o
f
ten
in
th
e
r
an
g
e
o
f
0
.
7
0
in
s
i
m
ilar
p
ed
o
lo
g
ical
s
t
u
d
ies
[
3
2
]
,
v
alid
atin
g
th
e
e
f
f
icac
y
o
f
th
e
o
p
ti
m
izat
io
n
f
r
a
m
e
w
o
r
k
.
A
l
th
o
u
g
h
SV
R
p
er
f
o
r
m
ed
w
e
ll
i
n
itial
l
y
,
t
h
e
o
p
ti
m
ized
A
d
aB
o
o
s
t
r
eg
r
es
s
o
r
w
a
s
s
elec
ted
as
t
h
e
f
i
n
a
l
m
o
d
el
b
ec
au
s
e
it
ac
h
iev
ed
th
e
lo
w
es
t
(
MSE
o
f
0
.
1
5
0
9
)
co
m
p
ar
ed
to
SVR
(
0
.
1
5
5
3
)
d
u
r
in
g
th
e
r
ig
o
r
o
u
s
B
ay
esia
n
o
p
ti
m
izatio
n
p
r
o
ce
s
s
.
Fro
m
a
co
m
p
u
tatio
n
a
l
p
er
s
p
ec
tiv
e,
th
e
o
p
tim
ized
A
d
aB
o
o
s
t
m
o
d
el
is
s
tr
u
ctu
r
all
y
s
i
m
p
ler
an
d
m
o
r
e
lig
h
t
w
ei
g
h
t
co
m
p
ar
ed
to
d
ee
p
lear
n
in
g
(
D
L
)
m
o
d
els
o
r
h
ea
v
y
e
n
s
e
m
b
le
s
tack
s
.
T
h
is
l
o
w
co
m
p
u
tatio
n
a
l
co
m
p
le
x
it
y
m
ak
e
s
it
h
i
g
h
l
y
s
u
itab
le
f
o
r
d
ep
lo
y
m
e
n
t
o
n
r
eso
u
r
ce
-
co
n
s
tr
ai
n
ed
I
o
T
e
d
g
e
d
ev
ices,
en
ab
li
n
g
r
ea
l
-
ti
m
e
o
n
-
s
ite
s
o
il
an
al
y
s
is
w
i
th
o
u
t
r
el
y
i
n
g
o
n
clo
u
d
co
n
n
ec
tiv
it
y
.
T
o
f
u
r
th
er
ass
e
s
s
r
eliab
ilit
y
,
a
d
etailed
an
al
y
s
is
o
f
t
h
e
p
r
ed
ic
tio
n
er
r
o
r
s
r
ev
ea
ls
th
at
w
h
ile
th
e
m
o
d
el
ac
h
iev
e
s
h
i
g
h
ac
cu
r
ac
y
ac
r
o
s
s
th
e
m
aj
o
r
it
y
o
f
th
e
p
H
r
an
g
e,
m
in
o
r
d
ev
iatio
n
s
ar
e
o
b
s
er
v
ed
at
th
e
ex
tr
em
e
en
d
s
o
f
th
e
d
is
tr
ib
u
tio
n
.
T
h
ese
d
is
cr
ep
an
cies
lik
el
y
s
te
m
f
r
o
m
lo
ca
l
s
o
il
h
eter
o
g
en
eit
y
o
r
th
e
in
h
er
en
t
l
i
m
ita
t
io
n
o
f
r
eg
r
es
s
io
n
m
o
d
els
i
n
ex
tr
ap
o
lati
n
g
b
ey
o
n
d
th
e
d
en
s
e
r
eg
io
n
s
o
f
th
e
tr
ain
i
n
g
d
ata.
Ov
er
all,
th
e
m
etr
ic
s
ex
ce
ed
th
e
th
r
es
h
o
ld
f
o
r
“
ex
ce
llen
t
p
r
ed
ictio
n
”
(
R
²
>
0
.
7
0
)
ac
ce
p
t
ed
in
d
ig
ital so
il
m
ap
p
in
g
[
3
3
]
.
T
ab
le
3
.
E
v
alu
atio
n
o
f
o
p
ti
m
iz
e
d
A
d
aB
o
o
s
t
r
eg
r
ess
o
r
M
e
t
r
i
c
V
a
l
u
e
R
-
sq
u
a
r
e
d
0
.
8
1
7
2
M
A
E
0
.
2
9
3
0
M
S
E
0
.
1
6
6
8
As
s
h
o
w
n
i
n
Fi
g
u
r
e
1
,
th
e
r
esid
u
als
ar
e
r
an
d
o
m
l
y
d
i
s
tr
ib
u
ted
ar
o
u
n
d
th
e
h
o
r
izo
n
tal
ze
r
o
lin
e
w
it
h
o
u
t
f
o
r
m
i
n
g
a
n
y
d
is
ce
r
n
ib
le
p
atter
n
s
(
e.
g
.
,
U
-
s
h
ap
e
o
r
f
u
n
n
el
s
h
ap
e)
,
w
h
ic
h
co
n
f
ir
m
s
t
h
at
t
h
e
m
o
d
el
i
s
u
n
b
iased
ac
r
o
s
s
th
e
e
n
tire
r
an
g
e
o
f
s
o
il
p
H
v
a
lu
e
s
.
A
d
d
itio
n
all
y
,
th
e
er
r
o
r
d
is
tr
ib
u
tio
n
h
is
to
g
r
a
m
i
n
Fi
g
u
r
e
1
ap
p
r
o
x
im
a
tes
a
Gau
s
s
ia
n
b
ell
cu
r
v
e,
in
d
icati
n
g
t
h
at
th
e
p
r
ed
ictio
n
er
r
o
r
s
a
r
e
co
n
s
is
ten
t
an
d
p
r
ed
ictab
le,
s
atis
f
y
in
g
t
h
e
n
o
r
m
a
lit
y
a
s
s
u
m
p
tio
n
r
eq
u
ir
ed
f
o
r
r
o
b
u
s
t r
eg
r
ess
io
n
a
n
al
y
s
i
s
.
W
h
ile
SV
R
d
e
m
o
n
s
tr
ated
co
m
p
eti
tiv
e
ac
c
u
r
ac
y
,
A
d
aB
o
o
s
t
w
as
p
r
io
r
itized
d
u
e
to
i
ts
in
h
er
en
t
co
m
p
atib
il
it
y
w
it
h
tr
ee
-
b
ased
f
ea
tu
r
e
i
m
p
o
r
tan
ce
an
al
y
s
i
s
,
o
f
f
er
in
g
s
u
p
er
io
r
tr
an
s
p
ar
en
c
y
o
v
er
th
e
‘
b
lack
-
b
o
x
’
k
er
n
el
tr
an
s
f
o
r
m
atio
n
s
o
f
SVR
.
T
h
is
i
n
ter
p
r
etab
ilit
y
is
cr
u
c
ial
f
o
r
id
en
ti
f
y
i
n
g
k
e
y
s
o
il
d
r
iv
er
s
i
n
p
r
ec
is
io
n
ag
r
icu
ltu
r
e.
T
h
e
r
elativ
e
i
n
f
l
u
e
n
ce
o
f
ea
ch
p
r
ed
icto
r
o
n
s
o
il
p
H
is
illu
s
tr
ated
in
Fi
g
u
r
e
2
v
ia
t
h
e
SH
A
P
s
u
m
m
ar
y
p
lo
t
f
o
r
th
e
o
p
ti
m
ized
A
d
aB
o
o
s
t
r
eg
r
ess
o
r
.
A
s
tan
d
o
u
t
o
b
s
er
v
atio
n
f
r
o
m
t
h
is
v
i
s
u
aliza
tio
n
i
s
th
e
d
o
m
in
a
n
ce
o
f
Fe
as
th
e
p
r
im
ar
y
d
r
iv
er
o
f
th
e
m
o
d
el
’
s
p
r
ed
ictio
n
s
.
T
h
e
d
is
tr
ib
u
tio
n
o
f
SH
A
P
v
alu
es
f
o
r
Fe
s
h
o
w
s
a
d
i
s
ti
n
cti
v
e
p
atter
n
:
h
i
g
h
Fe
v
a
lu
e
s
(
r
ed
/p
in
k
p
o
in
ts
)
ar
e
co
n
s
is
te
n
tl
y
lo
ca
ted
o
n
t
h
e
lef
t
s
id
e
(
n
eg
a
tiv
e
SH
A
P
v
alu
e
s
)
,
in
d
icati
n
g
t
h
at
h
ig
h
F
e
co
n
ce
n
tr
atio
n
s
ar
e
s
tr
o
n
g
l
y
as
s
o
ciate
d
w
i
th
l
o
w
er
(
m
o
r
e
ac
id
ic)
p
r
ed
icted
p
H.
L
o
w
Fe
v
alu
e
s
(
b
lu
e
p
o
in
ts
)
ar
e
lo
ca
ted
o
n
th
e
r
ig
h
t
s
id
e
(
p
o
s
itiv
e
o
r
n
ea
r
-
z
er
o
SHA
P
v
al
u
es),
in
d
icati
n
g
th
a
t
lo
w
Fe
i
s
as
s
o
ciate
d
w
ith
h
ig
h
er
(
les
s
ac
id
ic
o
r
n
eu
tr
al)
p
H.
T
h
i
s
i
n
v
er
s
e
r
elatio
n
s
h
ip
b
et
w
ee
n
Fe
an
d
p
H
is
h
ig
h
l
y
co
n
s
is
te
n
t
w
it
h
t
h
e
p
r
in
cip
les
o
f
s
o
il
c
h
e
m
is
tr
y
[
3
4
]
.
C
aCO₃
e
m
er
g
ed
a
s
th
e
s
ec
o
n
d
m
o
s
t
i
m
p
o
r
tan
t
f
ea
tu
r
e
an
d
ali
g
n
s
p
er
f
ec
tl
y
w
i
th
s
o
il
c
h
e
m
is
tr
y
p
r
in
cip
les.
T
h
e
p
atter
n
o
f
SH
A
P
v
alu
e
s
s
h
o
w
s
t
h
at
h
ig
h
C
aC
O₃
v
a
lu
e
s
(
r
ed
/p
in
k
p
o
in
ts
)
ar
e
p
r
ed
o
m
i
n
a
n
tl
y
o
n
t
h
e
r
ig
h
t
(
p
o
s
iti
v
e
S
H
A
P
v
alu
es),
i
n
d
icati
n
g
a
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
I
n
terp
r
eta
b
le
ma
ch
in
e
lea
r
n
i
n
g
fo
r
d
ig
ita
l so
il p
H
ma
p
p
in
g
u
s
in
g
a
n
o
p
timiz
ed
…
(
Za
kiyy
a
n
Za
in
A
lka
f
)
1201
s
tr
o
n
g
p
o
s
iti
v
e
as
s
o
ciatio
n
with
h
ig
h
p
H
.
L
o
w
C
a
C
O₃
v
a
l
u
es
(
b
lu
e
p
o
in
t
s
)
ar
e
o
n
th
e
lef
t
s
id
e
(
n
e
g
ati
v
e
SH
A
P
v
alu
e
s
)
,
ass
o
ciate
d
w
it
h
lo
w
p
H.
T
h
e
p
o
s
itiv
e
r
elatio
n
s
h
ip
b
et
w
ee
n
C
a
C
O₃
an
d
p
H
is
a
co
r
n
er
s
to
n
e
o
f
s
o
il
ch
e
m
i
s
tr
y
[
3
2
]
.
A
g
r
o
n
o
m
icall
y
,
t
h
ese
f
in
d
i
n
g
s
s
u
g
g
est
t
h
at
f
ar
m
er
s
ca
n
u
tili
ze
SH
A
P
-
d
er
iv
ed
in
s
ig
h
ts
to
cr
ea
te
tar
g
eted
m
an
a
g
e
m
en
t
z
o
n
es,
p
r
io
r
itizin
g
s
o
il
tes
tin
g
an
d
li
m
i
n
g
in
ar
ea
s
w
i
th
h
i
g
h
Fe
v
ar
iab
ilit
y
an
d
lo
w
C
a
C
O₃
le
v
els to
n
eu
tr
aliz
e
ac
id
it
y
an
d
o
p
ti
m
ize
n
u
tr
i
en
t
u
p
tak
e.
Fig
u
r
e
2
.
SHA
P
a
n
al
y
s
is
4.
CO
NCLU
SI
O
N
T
h
is
s
t
u
d
y
d
e
m
o
n
s
tr
ated
th
a
t
n
o
n
li
n
ea
r
m
o
d
el
s
co
n
s
is
ten
tl
y
o
u
tp
er
f
o
r
m
li
n
ea
r
ap
p
r
o
ac
h
es
f
o
r
d
ig
ita
l
s
o
il
p
H
m
ap
p
i
n
g
.
Sp
ec
i
f
icall
y
,
th
e
o
p
ti
m
ized
A
d
aB
o
o
s
t
r
eg
r
ess
o
r
ac
h
ie
v
ed
s
u
p
er
io
r
p
r
ed
ictiv
e
ac
cu
r
ac
y
co
m
p
ar
ed
to
tr
ad
itio
n
al
li
n
ea
r
b
aselin
es,
h
i
g
h
l
ig
h
ti
n
g
th
e
co
m
p
le
x
it
y
o
f
s
o
il
-
lan
d
s
ca
p
e
in
ter
ac
tio
n
s
.
Me
th
o
d
o
lo
g
icall
y
,
t
h
e
in
te
g
r
atio
n
o
f
B
ay
es
ian
o
p
ti
m
izat
i
o
n
s
ig
n
i
f
ican
t
l
y
en
h
a
n
ce
d
m
o
d
el
p
er
f
o
r
m
a
n
ce
,
y
ield
i
n
g
a
~7
.
5
%
i
m
p
r
o
v
e
m
e
n
t
in
MSE
f
o
r
th
e
A
d
aB
o
o
s
t
m
o
d
el.
Fu
r
t
h
er
m
o
r
e,
th
e
ap
p
licatio
n
o
f
SH
A
P
an
al
y
s
is
p
r
o
v
id
ed
cr
itical
tr
a
n
s
p
ar
en
c
y
,
id
en
ti
f
y
i
n
g
Fe
a
n
d
C
aCO₃
a
s
t
h
e
d
o
m
i
n
an
t
d
r
i
v
er
s
o
f
s
o
il
p
H
s
p
atial
v
ar
iab
ilit
y
.
T
h
e
r
esu
lt
co
n
f
ir
m
s
t
h
e
f
r
a
m
e
w
o
r
k
’
s
ab
ilit
y
to
p
r
o
d
u
ce
n
o
t
o
n
l
y
ac
cu
r
ate
m
ap
s
b
u
t
also
ag
r
o
n
o
m
ica
ll
y
m
ea
n
in
g
f
u
l
in
s
ig
h
t
s
.
T
h
e
f
in
d
in
g
s
h
a
v
e
p
r
ac
tical
i
m
p
licatio
n
s
f
o
r
p
r
ec
is
io
n
ag
r
ic
u
lt
u
r
e,
o
f
f
er
i
n
g
a
r
o
b
u
s
t
to
o
l
f
o
r
o
p
tim
izi
n
g
s
o
il
a
m
e
n
d
m
en
t
s
tr
ate
g
ies.
C
u
r
r
en
t
li
m
itatio
n
s
i
n
clu
d
e
th
e
r
elian
ce
o
n
a
d
ataset
f
r
o
m
a
s
p
ec
if
ic
g
eo
g
r
ap
h
ic
r
eg
io
n
w
it
h
a
m
o
d
er
ate
s
a
m
p
le
s
ize
an
d
th
e
lack
o
f
ex
p
licit
u
n
ce
r
tai
n
t
y
q
u
an
ti
f
icat
io
n
.
F
u
tu
r
e
w
o
r
k
s
h
o
u
ld
f
o
cu
s
o
n
i
n
teg
r
at
in
g
s
atellite
-
b
ased
r
e
m
o
te
s
e
n
s
in
g
d
ata
to
i
m
p
r
o
v
e
g
en
er
aliza
tio
n
a
n
d
d
ep
lo
y
in
g
th
e
li
g
h
t
w
ei
g
h
t
A
d
aB
o
o
s
t
m
o
d
el
in
to
I
o
T
-
b
ased
ed
g
e
d
ev
ic
es
f
o
r
r
ea
l
-
ti
m
e,
i
n
-
s
itu
s
o
il
m
o
n
ito
r
in
g
.
ACK
NO
WL
E
D
G
M
E
NT
S
W
e
w
o
u
ld
li
k
e
to
ex
p
r
ess
o
u
r
s
in
ce
r
e
g
r
atitu
d
e
to
th
e
p
eo
p
le
w
h
o
co
n
tr
ib
u
ted
t
h
eir
ti
m
e
a
n
d
ef
f
o
r
t
to
h
elp
u
s
co
n
ti
n
u
e
w
it
h
o
u
r
r
e
s
ea
r
ch
.
W
e
also
t
h
an
k
t
h
e
J
en
d
er
al
So
ed
ir
m
an
Un
i
v
er
s
i
t
y
f
o
r
th
eir
s
ea
m
les
s
co
n
tr
ib
u
tio
n
to
o
u
r
r
esear
ch
F
UNDIN
G
I
NF
O
RM
AT
I
O
N
T
h
is
w
o
r
k
w
a
s
s
u
p
p
o
r
ted
b
y
th
e
Un
iv
er
s
itas
J
en
d
er
al
So
ed
ir
m
an
B
L
U
R
e
s
ea
r
ch
Gr
a
n
t.
AUTHO
R
CO
NT
RIB
UT
I
O
NS ST
A
T
E
M
E
NT
T
h
is
j
o
u
r
n
al
u
s
e
s
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT
)
to
r
ec
o
g
n
ize
in
d
i
v
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
t
h
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
lla
b
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
Z
a
k
i
y
y
a
n
Z
a
in
A
l
k
a
f
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
A’
i
s
y
a
N
u
r
A
u
l
ia
Yu
s
u
f
✓
✓
✓
✓
✓
✓
✓
E
ls
a
Sar
i H
a
y
u
n
ah
Nu
r
d
in
i
y
a
h
✓
✓
✓
✓
✓
✓
T
r
i
W
is
u
d
a
w
a
ti
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
si
s
I
:
I
n
v
e
st
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
si
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
24
,
No
.
4
,
A
u
g
u
s
t
20
26
:
1
197
-
1
2
0
3
1202
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
s
d
ec
lar
e
th
at
t
h
er
e
is
n
o
co
n
f
lict o
f
i
n
ter
es
t r
eg
ar
d
in
g
t
h
e
p
u
b
licatio
n
o
f
t
h
is
p
a
p
er
.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
s
u
p
p
o
r
tin
g
th
e
f
i
n
d
in
g
s
o
f
t
h
is
s
t
u
d
y
ar
e
av
a
ilab
le
in
th
is
d
ataset
:
h
ttp
s
:/
/d
ata.
m
e
n
d
ele
y
.
co
m
/d
atasets
/r
7
tj
n
6
8
r
m
w
/1
.
RE
F
E
R
E
NC
E
S
[
1
]
R
.
V
i
z
c
a
í
n
o
e
t
a
l
.
,
“
E
n
h
a
n
c
e
d
e
l
e
c
t
r
o
k
i
n
e
t
i
c
r
e
m
e
d
i
a
t
i
o
n
o
f
p
o
l
l
u
t
e
d
so
i
l
s
b
y
a
n
o
l
y
t
e
p
H
c
o
n
d
i
t
i
o
n
i
n
g
,
”
C
h
e
m
o
s
p
h
e
r
e
,
v
o
l
.
1
9
9
,
p
p
.
477
–
4
8
5
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
h
e
m
o
sp
h
e
r
e
.
2
0
1
8
.
0
2
.
0
3
8
.
[
2
]
H
.
S
i
n
g
h
,
N
.
H
a
l
d
e
r
,
B
.
S
i
n
g
h
,
J
.
S
i
n
g
h
,
S
.
S
h
a
r
m
a
,
a
n
d
Y
.
S
h
a
c
h
a
m
-
D
i
a
m
a
n
d
,
“
S
m
a
r
t
F
a
r
m
i
n
g
R
e
v
o
l
u
t
i
o
n
:
P
o
r
t
a
b
l
e
a
n
d
R
e
a
l
-
T
i
me
S
o
i
l
N
i
t
r
o
g
e
n
a
n
d
P
h
o
s
p
h
o
r
u
s
M
o
n
i
t
o
r
i
n
g
f
o
r
S
u
s
t
a
i
n
a
b
l
e
A
g
r
i
c
u
l
t
u
r
e
,
”
S
e
n
s
o
r
s
,
v
o
l
.
2
3
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
3
1
3
5
9
1
4
.
[
3
]
S
.
V
o
g
e
l
e
t
a
l
.
,
“
D
i
r
e
c
t
p
r
e
d
i
c
t
i
o
n
o
f
si
t
e
-
s
p
e
c
i
f
i
c
l
i
me
r
e
q
u
i
r
e
me
n
t
o
f
a
r
a
b
l
e
f
i
e
l
d
s
u
s
i
n
g
t
h
e
b
a
s
e
n
e
u
t
r
a
l
i
z
i
n
g
c
a
p
a
c
i
t
y
a
n
d
a
m
u
l
t
i
-
s
e
n
s
o
r
p
l
a
t
f
o
r
m
f
o
r
o
n
-
t
h
e
-
g
o
s
o
i
l
m
a
p
p
i
n
g
,
”
P
r
e
c
i
s
i
o
n
A
g
r
i
c
,
v
o
l
.
2
3
,
p
p
.
1
2
7
–
1
4
9
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
1
1
9
-
0
2
1
-
0
9
8
3
0
-
x.
[
4
]
J
.
S
c
h
m
i
d
i
n
g
e
r
e
t
a
l
.
,
“
L
i
m
e
S
o
D
a
:
A
D
a
t
a
s
e
t
C
o
l
l
e
c
t
i
o
n
f
o
r
B
e
n
c
h
m
a
r
k
i
n
g
o
f
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
R
e
g
r
e
s
s
o
r
s
i
n
D
i
g
i
t
a
l
S
o
i
l
M
a
p
p
i
n
g
,
”
G
e
o
d
e
r
m
a
,
v
o
l
.
4
5
9
,
p
.
1
1
7
3
3
7
,
J
u
l
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
g
e
o
d
e
r
m
a
.
2
0
2
5
.
1
1
7
3
3
7
.
[
5
]
C.
V
.
P
a
t
r
i
c
h
e
,
B
.
R
o
ș
c
a
,
R
.
G
.
P
î
r
n
ă
u
,
a
n
d
I
.
V
a
s
i
l
i
n
i
u
c
,
“
S
p
a
t
i
a
l
m
o
d
e
l
l
i
n
g
o
f
t
o
p
s
o
i
l
p
r
o
p
e
r
t
i
e
s
i
n
R
o
m
a
n
i
a
u
s
i
n
g
g
e
o
s
t
a
t
i
s
t
i
c
a
l
m
e
t
h
o
d
s
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
P
L
o
S
O
n
e
,
v
o
l
.
1
8
,
n
o
.
8
,
2
0
2
3
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
2
8
9
2
8
6
.
[
6
]
A
.
N
.
A
.
Y
u
s
u
f
,
Z
.
Z
.
A
l
k
a
f
,
E
.
S
.
H
.
N
u
r
d
i
n
i
y
a
h
,
T
.
W
i
s
u
d
a
w
a
t
i
,
a
n
d
M
.
I
.
F
a
w
z
i
,
“
C
l
a
s
s
i
f
i
c
a
t
i
o
n
o
f
W
o
r
k
e
r
P
r
o
d
u
c
t
i
v
i
t
y
a
n
d
R
e
s
o
u
r
c
e
A
l
l
o
c
a
t
i
o
n
O
p
t
i
m
i
z
a
t
i
o
n
w
i
t
h
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
:
G
a
r
me
n
t
I
n
d
u
s
t
r
y
,
”
J
u
r
n
a
l
T
e
k
n
i
k
I
n
f
o
r
m
a
t
i
k
a
(
J
U
T
I
F
)
,
v
o
l
.
6
,
n
o
.
5
,
p
p
.
2
9
9
1
–
3
0
0
1
,
2
0
2
5
,
d
o
i
:
1
0
.
5
2
4
3
6
/
1
.
j
u
t
i
f
.
2
0
2
5
.
6
.
5
.
5
2
6
3
.
[
7
]
Z
.
Z
.
A
l
k
a
f
,
M
.
I
.
F
a
w
z
i
,
M
.
W
.
R
.
S
a
st
y
a
w
a
n
,
a
n
d
R
.
D
.
P
u
t
e
r
a
,
“
U
n
r
a
v
e
l
i
n
g
o
f
me
n
’
s
f
r
a
g
r
a
n
c
e
p
r
e
f
e
r
e
n
c
e
s
o
n
o
n
l
i
n
e
m
a
r
k
e
t
p
l
a
c
e
s:
a
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
s
t
u
d
y
u
s
i
n
g
D
B
S
C
A
N
c
l
u
s
t
e
r
i
n
g
a
n
d
l
i
n
e
a
r
r
e
g
r
e
s
s
i
o
n
,
”
J
u
r
n
a
l
T
e
k
n
i
k
I
n
f
o
r
m
a
t
i
k
a
(
J
U
T
I
F
)
,
v
o
l
.
5
,
n
o
.
6
,
p
p
.
1
9
1
3
–
1
9
2
0
,
2
0
2
5
,
d
o
i
:
1
0
.
5
2
4
3
6
/
1
.
j
u
t
i
f
.
2
0
2
4
.
5
.
6
.
4
1
8
7
.
[
8
]
R
.
C
h
o
u
d
h
a
r
y
,
A
.
K
u
m
a
r
,
P
.
C
.
,
M
.
M
.
N
a
i
k
,
M
.
C
h
o
u
d
h
u
r
y
,
a
n
d
N
.
K
h
a
n
,
“
P
r
e
d
i
c
t
i
n
g
w
a
t
e
r
q
u
a
l
i
t
y
i
n
d
e
x
u
s
i
n
g
s
t
a
c
k
e
d
e
n
s
e
m
b
l
e
r
e
g
r
e
s
s
i
o
n
a
n
d
S
H
A
P
b
a
s
e
d
e
x
p
l
a
i
n
a
b
l
e
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
,
”
S
c
i
e
n
t
i
f
i
c
R
e
p
o
r
t
s
,
v
o
l
.
1
5
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
5
-
0
9
4
6
3
-
4.
[
9
]
S
.
S
h
i
,
N
.
W
a
n
g
,
S
.
C
h
e
n
,
B
.
H
u
,
J
.
P
e
n
g
,
a
n
d
Z
.
S
h
i
,
“
D
i
g
i
t
a
l
m
a
p
p
i
n
g
o
f
s
o
i
l
s
a
l
i
n
i
t
y
w
i
t
h
t
i
m
e
-
w
i
n
d
o
w
s
f
e
a
t
u
r
e
s
o
p
t
i
m
i
z
a
t
i
o
n
a
n
d
e
n
s
e
m
b
l
e
l
e
a
r
n
i
n
g
m
o
d
e
l
,
”
E
c
o
l
o
g
i
c
a
l
I
n
f
o
r
m
a
t
i
c
s
,
v
o
l
.
8
5
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
c
o
i
n
f
.
2
0
2
4
.
1
0
2
9
8
2
.
[
1
0
]
J
.
S
y
l
v
a
i
n
,
F
.
A
n
c
t
i
l
,
a
n
d
É
.
T
h
i
f
f
a
u
l
t
,
“
U
s
i
n
g
b
i
a
s
c
o
r
r
e
c
t
i
o
n
a
n
d
e
n
s
e
m
b
l
e
m
o
d
e
l
l
i
n
g
f
o
r
p
r
e
d
i
c
t
i
v
e
m
a
p
p
i
n
g
a
n
d
r
e
l
a
t
e
d
u
n
c
e
r
t
a
i
n
t
y
:
A
c
a
se
s
t
u
d
y
i
n
d
i
g
i
t
a
l
s
o
i
l
m
a
p
p
i
n
g
,
”
G
e
o
d
e
r
m
a
,
v
o
l
.
4
0
3
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
g
e
o
d
e
r
m
a
.
2
0
2
1
.
1
1
5
1
5
3
.
[
1
1
]
P
.
T
z
i
a
c
h
r
i
s
,
“
S
o
i
l
d
a
t
a
g
r
e
v
e
n
a
,
”
M
e
n
d
e
l
e
y
D
a
t
a
,
v
o
l
.
1
,
2
0
2
2
.
[
1
2
]
A
.
A
r
a
b
a
m
e
r
i
,
J
.
P
.
T
i
e
f
e
n
b
a
c
h
e
r
,
T
.
B
l
a
s
c
h
k
e
,
B
.
P
r
a
d
h
a
n
,
a
n
d
D
.
T
.
B
u
i
,
“
M
o
r
p
h
o
m
e
t
r
i
c
A
n
a
l
y
s
i
s
f
o
r
S
o
i
l
E
r
o
si
o
n
S
u
s
c
e
p
t
i
b
i
l
i
t
y
M
a
p
p
i
n
g
U
s
i
n
g
N
o
v
e
l
G
I
S
-
B
a
s
e
d
E
n
s
e
m
b
l
e
M
o
d
e
l
,
”
R
e
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
1
2
,
p
.
8
7
4
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s
1
2
0
5
0
8
7
4
.
[
1
3
]
P
.
G
u
o
,
T
.
L
i
,
H
.
G
a
o
,
X
.
C
h
e
n
,
Y
.
C
u
i
,
a
n
d
Y
.
H
u
a
n
g
,
“
E
v
a
l
u
a
t
i
n
g
C
a
l
i
b
r
a
t
i
o
n
a
n
d
S
p
e
c
t
r
a
l
V
a
r
i
a
b
l
e
S
e
l
e
c
t
i
o
n
M
e
t
h
o
d
s
f
o
r
P
r
e
d
i
c
t
i
n
g
T
h
r
e
e
S
o
i
l
N
u
t
r
i
e
n
t
s
U
s
i
n
g
V
i
s
-
N
I
R
S
p
e
c
t
r
o
s
c
o
p
y
,
”
R
e
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
1
3
,
p
.
4
0
0
0
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s
1
3
1
9
4
0
0
0
.
[
1
4
]
P
.
T
e
o
e
t
a
l
.
,
“
D
e
t
e
r
m
i
n
i
n
g
r
i
s
k
a
n
d
p
r
e
d
i
c
t
o
r
s
o
f
h
e
a
d
a
n
d
n
e
c
k
c
a
n
c
e
r
t
r
e
a
t
m
e
n
t
-
r
e
l
a
t
e
d
l
y
m
p
h
e
d
e
m
a
:
A
c
l
i
n
i
c
o
p
a
t
h
o
l
o
g
i
c
a
n
d
d
o
s
i
m
e
t
r
i
c
d
a
t
a
m
i
n
i
n
g
a
p
p
r
o
a
c
h
u
s
i
n
g
i
n
t
e
r
p
r
e
t
a
b
l
e
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
e
n
s
e
m
b
l
e
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
,
”
C
l
i
n
i
c
a
l
a
n
d
T
r
a
n
s
l
a
t
i
o
n
a
l
R
a
d
i
a
t
i
o
n
O
n
c
o
l
o
g
y
,
v
o
l
.
4
6
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
t
r
o
.
2
0
2
4
.
1
0
0
7
4
7
.
[
1
5
]
S
.
C
a
m
p
a
n
e
l
l
a
,
A
.
A
l
t
a
l
e
b
,
A
.
B
e
l
l
i
,
P
.
P
i
e
r
l
e
o
n
i
,
a
n
d
L
.
P
a
l
m
a
,
“
A
M
e
t
h
o
d
f
o
r
S
t
r
e
s
s
D
e
t
e
c
t
i
o
n
U
s
i
n
g
E
m
p
a
t
i
c
a
E
4
B
r
a
c
e
l
e
t
a
n
d
M
a
c
h
i
n
e
-
L
e
a
r
n
i
n
g
T
e
c
h
n
i
q
u
e
s
,
”
S
e
n
s
o
r
s
,
v
o
l
.
2
3
,
n
o
.
7
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
3
0
7
3
5
6
5
.
[
1
6
]
O
.
B
u
l
u
t
,
B
.
T
a
n
,
E
.
M
a
z
z
u
l
l
o
,
a
n
d
A
.
S
y
e
d
,
“
B
e
n
c
h
m
a
r
k
i
n
g
V
a
r
i
a
n
t
s
o
f
R
e
c
u
r
s
i
v
e
F
e
a
t
u
r
e
E
l
i
m
i
n
a
t
i
o
n
:
I
n
s
i
g
h
t
s
f
r
o
m
P
r
e
d
i
c
t
i
v
e
T
a
s
k
s
i
n
E
d
u
c
a
t
i
o
n
a
n
d
H
e
a
l
t
h
c
a
r
e
,
”
I
n
f
o
r
m
a
t
i
o
n
,
v
o
l
.
1
6
,
n
o
.
6
,
p
.
4
7
6
,
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
i
n
f
o
1
6
0
6
0
4
7
6
.
[
1
7
]
R
.
D
u
n
n
e
e
t
a
l
.
,
“
T
h
r
e
s
h
o
l
d
i
n
g
G
i
n
i
v
a
r
i
a
b
l
e
i
m
p
o
r
t
a
n
c
e
w
i
t
h
a
s
i
n
g
l
e
-
t
r
a
i
n
e
d
r
a
n
d
o
m
f
o
r
e
s
t
:
A
n
e
m
p
i
r
i
c
a
l
B
a
y
e
s
a
p
p
r
o
a
c
h
,
”
C
o
m
p
u
t
a
t
i
o
n
a
l
a
n
d
S
t
r
u
c
t
u
r
a
l
B
i
o
t
e
c
h
n
o
l
o
g
y
J
o
u
r
n
a
l
,
v
o
l
.
2
1
,
p
p
.
4
3
5
4
–
4
3
6
0
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
s
b
j
.
2
0
2
3
.
0
8
.
0
3
3
.
[
1
8
]
K
.
P
h
i
n
z
i
,
L
.
B
e
r
t
a
l
a
n
,
G
.
C
h
a
k
i
l
u
,
a
n
d
S
.
S
z
a
b
ó
,
“
I
m
p
r
o
v
i
n
g
t
h
e
s
p
a
t
i
a
l
p
r
e
d
i
c
t
i
o
n
o
f
t
o
p
s
o
i
l
p
r
o
p
e
r
t
i
e
s
i
n
a
t
y
p
i
c
a
l
g
r
a
z
i
n
g
a
r
e
a
u
s
i
n
g
m
u
l
t
i
-
s
e
a
s
o
n
P
l
a
n
e
t
S
c
o
p
e
s
p
e
c
t
r
a
l
c
o
v
a
r
i
a
t
e
s
a
n
d
d
a
t
a
m
i
n
i
n
g
t
e
c
h
n
i
q
u
e
s
,
”
E
a
r
t
h
S
c
i
e
n
c
e
I
n
f
o
r
m
a
t
i
c
s
,
v
o
l
.
1
8
,
n
o
.
2
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
2
1
4
5
-
0
2
5
-
01
7
4
8
-
6.
[
1
9
]
Y
.
S
h
e
n
e
t
a
l
.
,
“
Big
-
d
a
t
a
a
n
d
a
r
t
i
f
i
c
i
a
l
-
i
n
t
e
l
l
i
g
e
n
c
e
-
a
s
s
i
s
t
e
d
v
a
u
l
t
p
r
e
d
i
c
t
i
o
n
a
n
d
E
V
O
-
I
C
L
s
i
z
e
se
l
e
c
t
i
o
n
f
o
r
m
y
o
p
i
a
c
o
r
r
e
c
t
i
o
n
,
”
B
r
i
t
i
s
h
J
o
u
r
n
a
l
o
f
O
p
h
t
h
a
l
m
o
l
o
g
y
,
v
o
l
.
1
0
7
,
n
o
.
2
,
p
p
.
2
0
1
–
2
0
6
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
3
6
/
b
j
o
p
h
t
h
a
l
m
o
l
-
2021
-
3
1
9
6
1
8
.
[
2
0
]
S
.
Y
a
n
g
,
J
.
S
o
h
n
,
S
.
L
e
e
,
J
.
L
e
e
,
a
n
d
H
.
C
.
K
i
m
,
“
E
s
t
i
m
a
t
i
o
n
a
n
d
V
a
l
i
d
a
t
i
o
n
o
f
A
r
t
e
r
i
a
l
B
l
o
o
d
P
r
e
s
s
u
r
e
U
s
i
n
g
P
h
o
t
o
p
l
e
t
h
y
s
mo
g
r
a
m
M
o
r
p
h
o
l
o
g
y
F
e
a
t
u
r
e
s
i
n
C
o
n
j
u
n
c
t
i
o
n
W
i
t
h
P
u
l
s
e
A
r
r
i
v
a
l
T
i
m
e
i
n
L
a
r
g
e
O
p
e
n
D
a
t
a
b
a
s
e
s
,
”
I
E
E
E
J
o
u
r
n
a
l
o
f
B
i
o
m
e
d
i
c
a
l
a
n
d
H
e
a
l
t
h
I
n
f
o
r
m
a
t
i
c
s
,
v
o
l
.
2
5
,
n
o
.
4
,
p
p
.
1
0
1
8
–
1
0
3
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
j
b
h
i
.
2
0
2
0
.
3
0
0
9
6
5
8
.
[
2
1
]
F
.
O
e
t
t
l
,
A
.
W
e
i
n
b
l
a
t
t
,
B
.
C
h
a
l
m
e
r
s
,
D
.
K
o
l
i
n
,
a
n
d
G
.
D
.
V
a
l
l
e
,
“
D
e
v
e
l
o
p
i
n
g
a
n
d
v
a
l
i
d
a
t
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
s
t
o
p
r
e
d
i
c
t
a
c
e
t
a
b
u
l
a
r
c
u
p
s
i
z
e
i
n
t
o
t
a
l
h
i
p
a
r
t
h
r
o
p
l
a
s
t
y
,
”
J
o
u
r
n
a
l
o
f
O
r
t
h
o
p
a
e
d
i
c
s
,
v
o
l
.
6
7
,
p
p
.
3
4
9
–
3
5
2
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
o
r
.
2
0
2
5
.
0
7
.
0
2
1
.
[
2
2
]
K
.
M
a
e
a
n
d
D
.
A
.
K
r
i
s
t
i
y
a
n
t
i
,
“
G
r
i
d
s
e
a
r
c
h
v
s
B
a
y
e
s
i
a
n
o
p
t
i
m
i
z
a
t
i
o
n
f
o
r
i
n
t
e
n
s
i
t
y
s
c
o
r
i
n
g
c
l
a
s
s
i
f
i
c
a
t
i
o
n
a
n
d
c
h
a
n
n
e
l
r
e
c
o
m
me
n
d
a
t
i
o
n
p
r
e
d
i
c
t
i
o
n
,
”
T
E
L
K
O
M
N
I
K
A
(
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
C
o
m
p
u
t
.
E
l
e
c
t
r
o
n
.
C
o
n
t
r
o
l
,
v
o
l
.
2
3
,
n
o
.
4
,
p
p
.
1
0
2
0
–
1
0
3
1
,
2
0
2
5
,
d
o
i
:
1
0
.
1
2
9
2
8
/
t
e
l
k
o
m
n
i
k
a
.
v
2
3
i
4
.
2
6
3
4
1
.
[
2
3
]
S
.
M
.
L
u
n
d
b
e
r
g
a
n
d
S
.
-
I
.
L
e
e
,
“
A
u
n
i
f
i
e
d
a
p
p
r
o
a
c
h
t
o
i
n
t
e
r
p
r
e
t
i
n
g
m
o
d
e
l
p
r
e
d
i
c
t
i
o
n
s
,
”
A
d
v
a
n
c
e
s
i
n
N
e
u
r
a
l
I
n
f
o
r
m
a
t
i
o
n
P
r
o
c
e
s
s
i
n
g
S
y
s
t
e
m
s
,
v
o
l
.
3
0
,
2
0
1
7
.
[
2
4
]
Y
.
H
a
n
,
H
.
L
i
a
n
g
,
D
.
J
i
a
n
g
,
Z
.
W
e
i
,
J.
Y
o
u
,
a
n
d
G
.
Z
h
a
i
,
“
E
l
e
c
t
r
o
m
a
g
n
e
t
i
c
R
e
l
a
y
S
u
c
t
i
o
n
P
r
e
d
i
c
t
i
o
n
B
a
s
e
d
o
n
I
m
p
r
o
v
e
d
S
u
p
p
o
r
t
V
e
c
t
o
r
R
e
g
r
e
s
s
i
o
n
,
”
i
n
2
0
2
4
I
E
E
E
7
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
E
l
e
c
t
r
i
c
a
l
a
n
d
E
n
e
r
g
y
C
o
n
f
e
r
e
n
c
e
(
C
I
E
E
C
)
,
I
E
E
E
,
M
a
y
2
0
2
4
,
p
p
.
1
2
3
7
–
1
2
4
2
.
d
o
i
:
1
0
.
1
1
0
9
/
C
I
E
E
C
6
0
9
2
2
.
2
0
2
4
.
1
0
5
8
3
7
3
3
.
[
2
5
]
Ł
.
U
z
a
r
o
w
i
c
z
e
t
a
l
.
,
“
I
n
i
t
i
a
l
p
e
d
o
g
e
n
i
c
p
r
o
c
e
s
se
s
,
m
i
n
e
r
a
l
a
n
d
c
h
e
m
i
c
a
l
t
r
a
n
s
f
o
r
m
a
t
i
o
n
s
a
n
d
m
o
b
i
l
i
t
y
o
f
t
r
a
c
e
e
l
e
me
n
t
s
i
n
T
e
c
h
n
o
s
o
l
s
o
n
d
u
m
p
s
o
f
t
h
e
f
o
r
me
r
c
o
p
p
e
r
m
i
n
e
s
i
n
M
i
e
d
z
i
a
n
a
G
ó
r
a
a
n
d
M
i
e
d
z
i
a
n
k
a
,
t
h
e
Ś
w
i
ę
t
o
k
r
z
y
s
k
i
e
M
t
s
.
,
s
o
u
t
h
-
c
e
n
t
r
a
l
P
o
l
a
n
d
,
”
C
A
T
E
N
A
,
v
o
l
.
2
4
5
,
p
.
1
0
8
2
9
3
,
O
c
t
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
a
t
e
n
a
.
2
0
2
4
.
1
0
8
2
9
3
.
[
2
6
]
T
.
A
.
A
s
se
g
i
e
,
A
.
O
.
S
a
l
a
u
,
a
n
d
T
.
U
.
B
a
d
r
u
d
e
e
n
,
“
E
s
t
i
m
a
t
i
o
n
o
f
c
o
n
c
r
e
t
e
c
o
m
p
r
e
s
s
i
o
n
u
s
i
n
g
r
e
g
r
e
ss
i
o
n
m
o
d
e
l
s
,
”
B
u
l
l
e
t
i
n
o
f
E
l
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
a
n
d
I
n
f
o
r
m
a
t
i
c
s
(
B
E
E
I
)
,
v
o
l
.
1
1
,
n
o
.
5
,
p
p
.
2
7
9
9
–
2
8
0
4
,
O
c
t
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
9
1
/
e
e
i
.
v
1
1
i
5
.
4
2
1
0
.
[
2
7
]
M
.
A
n
j
u
m
,
K
.
K
h
a
n
,
W
.
A
h
m
a
d
,
A
.
A
h
m
a
d
,
M
.
N
.
A
m
i
n
,
a
n
d
A
.
N
a
f
e
e
s
,
“
A
p
p
l
i
c
a
t
i
o
n
o
f
E
n
s
e
m
b
l
e
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
M
e
t
h
o
d
s
t
o
E
s
t
i
m
a
t
e
t
h
e
C
o
m
p
r
e
s
s
i
v
e
S
t
r
e
n
g
t
h
o
f
F
i
b
e
r
-
R
e
i
n
f
o
r
c
e
d
N
a
n
o
-
S
i
l
i
c
a
M
o
d
i
f
i
e
d
C
o
n
c
r
e
t
e
,
”
P
o
l
y
m
e
r
s
,
v
o
l
.
1
4
,
n
o
.
1
8
,
p
.
3
9
0
6
,
S
e
p
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
I
n
terp
r
eta
b
le
ma
ch
in
e
lea
r
n
i
n
g
fo
r
d
ig
ita
l so
il p
H
ma
p
p
in
g
u
s
in
g
a
n
o
p
timiz
ed
…
(
Za
kiyy
a
n
Za
in
A
lka
f
)
1203
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
p
o
l
y
m
1
4
1
8
3
9
0
6
.
[
2
8
]
B
.
O
.
O
l
o
r
u
n
f
e
m
i
e
t
a
l
.
,
“
E
f
f
i
c
i
e
n
t
d
i
a
g
n
o
s
i
s
o
f
d
i
a
b
e
t
e
s
m
e
l
l
i
t
u
s
u
s
i
n
g
a
n
i
m
p
r
o
v
e
d
e
n
s
e
m
b
l
e
m
e
t
h
o
d
,
”
S
c
i
e
n
t
i
f
i
c
R
e
p
o
r
t
s
.
,
v
o
l
.
1
5
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
5
-
8
7
7
6
7
-
1.
[
2
9
]
M
.
F
a
n
,
K
.
X
i
a
o
,
L
.
S
u
n
,
S
.
Z
h
a
n
g
,
a
n
d
Y
.
X
u
,
“
A
u
t
o
m
a
t
e
d
H
y
p
e
r
p
a
r
a
m
e
t
e
r
O
p
t
i
m
i
z
a
t
i
o
n
o
f
G
r
a
d
i
e
n
t
B
o
o
s
t
i
n
g
D
e
c
i
s
i
o
n
T
r
e
e
A
p
p
r
o
a
c
h
f
o
r
G
o
l
d
M
i
n
e
r
a
l
P
r
o
s
p
e
c
t
i
v
i
t
y
M
a
p
p
i
n
g
i
n
t
h
e
X
i
o
n
g
’
e
r
s
h
a
n
A
r
e
a
,
”
M
i
n
e
r
a
l
s
,
v
o
l
.
1
2
,
n
o
.
1
2
,
p
.
1
6
2
1
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
m
i
n
1
2
1
2
1
6
2
1
.
[
3
0
]
C
.
D
i
n
g
,
D
.
Y
u
,
Q
.
G
u
o
,
a
n
d
S
.
Z
h
a
n
g
,
“
P
a
r
a
me
t
e
r
o
p
t
i
m
i
z
a
t
i
o
n
o
f
S
V
M
a
l
g
o
r
i
t
h
m
f
o
r
p
r
e
d
i
c
t
i
n
g
p
h
y
s
i
c
a
l
p
a
r
a
m
e
t
e
r
s
o
f
S
F
6
–
C
u
m
i
x
t
u
r
e
p
l
a
s
m
a
u
n
d
e
r
l
o
c
a
l
t
h
e
r
mo
d
y
n
a
m
i
c
e
q
u
i
l
i
b
r
i
u
m
,
”
A
I
P
A
d
v
a
n
c
e
s
,
v
o
l
.
1
3
,
n
o
.
8
,
A
u
g
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
6
3
/
5
.
0
1
5
9
4
2
7
.
[
3
1
]
H.
-
Y
.
H
u
a
n
g
,
Q
.
-
D
.
D
i
n
g
,
J
.
-
H
.
Z
h
a
n
g
,
X
.
P
a
n
,
Y
.
-
H
.
Z
h
o
u
,
a
n
d
K
.
-
L
.
J
i
a
,
“
I
n
v
e
r
s
i
o
n
o
f
s
o
i
l
s
a
l
i
n
i
t
y
a
n
d
p
H
i
n
f
a
r
m
l
a
n
d
o
f
t
h
e
H
e
t
a
o
P
l
a
i
n
b
a
s
e
d
o
n
S
e
n
t
i
n
e
l
-
2
a
n
d
e
x
p
l
a
i
n
a
b
l
e
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
.
,
”
Y
i
n
g
Y
ong
S
h
e
n
g
T
a
i
X
u
e
B
ao
,
v
o
l
.
3
6
8
,
p
p
.
2
4
0
7
–
2
4
1
9
,
2
0
2
5
.
[
3
2
]
Q
.
L
u
,
S
.
T
i
a
n
,
a
n
d
L
.
W
e
i
,
“
D
i
g
i
t
a
l
m
a
p
p
i
n
g
o
f
s
o
i
l
p
H
a
n
d
c
a
r
b
o
n
a
t
e
s
a
t
t
h
e
E
u
r
o
p
e
a
n
s
c
a
l
e
u
s
i
n
g
e
n
v
i
r
o
n
m
e
n
t
a
l
v
a
r
i
a
b
l
e
s
a
n
d
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
S
c
i
e
n
c
e
o
f
T
h
e
T
o
t
a
l
E
n
v
i
r
o
n
m
e
n
t
,
v
o
l
.
8
5
6
,
p
.
1
5
9
1
7
1
,
J
a
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
s
c
i
t
o
t
e
n
v
.
2
0
2
2
.
1
5
9
1
7
1
.
[
3
3
]
A
.
L
e
l
a
g
o
a
n
d
M
.
B
i
b
i
s
o
,
“
P
e
r
f
o
r
m
a
n
c
e
o
f
m
i
d
i
n
f
r
a
r
e
d
s
p
e
c
t
r
o
s
c
o
p
y
t
o
p
r
e
d
i
c
t
n
u
t
r
i
e
n
t
s
f
o
r
a
g
r
i
c
u
l
t
u
r
a
l
s
o
i
l
s
i
n
s
e
l
e
c
t
e
d
a
r
e
a
s
o
f
E
t
h
i
o
p
i
a
,
”
H
e
l
i
y
o
n
,
v
o
l
.
8
,
n
o
.
3
,
p
.
e
0
9
0
5
0
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
h
e
l
i
y
o
n
.
2
0
2
2
.
e
0
9
0
5
0
.
[
3
4
]
B.
-
Y
.
H
u
a
n
g
e
t
a
l
.
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
e
t
h
o
d
s
t
o
p
r
e
d
i
c
t
c
a
d
m
i
u
m
(
C
d
)
c
o
n
c
e
n
t
r
a
t
i
o
n
i
n
r
i
c
e
g
r
a
i
n
a
n
d
s
u
p
p
o
r
t
s
o
i
l
m
a
n
a
g
e
m
e
n
t
a
t
a
r
e
g
i
o
n
a
l
s
c
a
l
e
,
”
F
u
n
d
a
m
e
n
t
a
l
R
e
s
e
a
r
c
h
,
v
o
l
.
4
,
p
p
.
1
1
9
6
–
1
2
0
5
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
f
m
r
e
.
2
0
2
3
.
0
2
.
0
1
6
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Za
k
iy
y
a
n
Z
a
i
n
Al
k
a
f
re
c
e
iv
e
d
h
is
Ba
c
h
e
lo
r
’
s
d
e
g
re
e
in
In
d
u
strial
En
g
in
e
e
rin
g
f
ro
m
Un
iv
e
rsitas
Isla
m
In
d
o
n
e
sia
a
n
d
h
is
M
a
ste
r
’
s
d
e
g
re
e
f
ro
m
U
n
iv
e
rsitas
G
a
d
jah
M
a
d
a
.
He
is
c
u
rre
n
tl
y
a
l
e
c
tu
re
r
a
t
Un
iv
e
rsit
a
s
Je
n
d
e
ra
l
S
o
e
d
irm
a
n
.
His
re
s
e
a
rc
h
in
tere
sts
in
c
lu
d
e
q
u
a
li
ty
m
a
n
a
g
e
m
e
n
t,
lea
n
m
a
n
u
f
a
c
tu
rin
g
,
a
n
d
d
a
ta
a
n
a
ly
ti
c
s,
w
it
h
a
s
p
e
c
if
ic
f
o
c
u
s
o
n
a
p
p
ly
in
g
m
a
c
h
in
e
lea
rn
in
g
to
i
n
d
u
strial
p
r
o
b
lem
s
.
He
is
a
n
A
UN
/S
EE
D
-
N
e
t
sc
h
o
lars
h
ip
a
w
a
rd
e
e
a
n
d
w
a
s
h
o
n
o
re
d
w
it
h
th
e
A
stra
S
a
t
u
In
d
o
n
e
sia
Aw
a
rd
f
o
r
h
is
in
n
o
v
a
ti
o
n
in
I
o
T
-
b
a
se
d
s
m
a
rt
f
a
r
m
in
g
so
lu
ti
o
n
s.
He
c
a
n
b
e
c
o
n
t
a
c
ted
a
t
e
m
a
il
:
z
a
k
i
y
y
a
n
.
a
lk
a
f
@u
n
so
e
d
.
a
c
.
i
d
.
A
’
isy
a
Nu
r
Au
li
a
Yu
s
u
f
re
c
e
iv
e
d
th
e
Ba
c
h
e
lo
r
o
f
E
n
g
in
e
e
rin
g
d
e
g
re
e
in
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
f
ro
m
th
e
Un
iv
e
rsitas
Ga
d
jah
M
a
d
a
,
Yo
g
y
a
k
a
rta,
In
d
o
n
e
sia
,
i
n
2
0
1
8
,
a
n
d
th
e
M
a
ste
r
’
s
d
e
g
re
e
in
e
lec
tri
c
a
l
e
n
g
in
e
e
rin
g
f
ro
m
th
e
Un
iv
e
rsit
y
o
f
In
d
o
n
e
sia
,
De
p
o
k
,
In
d
o
n
e
sia
,
i
n
2
0
2
1
.
S
h
e
i
s
a
P
M
D
S
U
s
c
h
o
l
a
r
s
h
i
p
a
w
a
r
d
e
e
a
n
d
a
Do
c
t
o
r
a
l
c
a
n
d
i
d
a
t
e
a
t
t
h
e
U
n
i
v
e
rs
i
ty
o
f
I
n
d
o
n
e
s
i
a
.
S
h
e
i
s
c
u
r
r
e
n
t
ly
a
l
e
c
t
u
re
r
i
n
t
h
e
D
e
p
a
r
tm
e
n
t
o
f
E
l
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
rs
i
t
a
s
J
e
n
d
e
r
a
l
S
o
e
d
i
rm
a
n
.
H
e
r
r
e
se
a
rc
h
i
n
t
e
r
e
s
t
i
s
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
a
n
t
e
n
n
a
,
t
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
,
a
n
d
I
o
T
.
S
h
e
c
a
n
b
e
c
o
n
t
a
c
t
e
d
a
t
e
m
a
i
l
:
a
i
sy
a
.
y
u
su
f
@
u
n
s
o
e
d
.
a
c
.
i
d
.
Elsa
S
a
r
i
H
a
y
u
n
a
h
N
u
r
d
in
iy
a
h
re
c
e
iv
e
d
h
e
r
B
a
c
h
e
lo
r
’
s
d
e
g
re
e
in
En
g
i
n
e
e
rin
g
P
h
y
sic
s
f
ro
m
Un
iv
e
rsitas
G
a
d
jah
M
a
d
a
,
In
d
o
n
e
sia
,
i
n
2
0
1
8
a
n
d
M
a
ste
r
De
g
re
e
in
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
f
ro
m
th
e
S
c
h
o
o
l
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
a
n
d
I
n
f
o
rm
a
ti
c
s,
In
stit
u
t
T
e
k
n
o
lo
g
i
Ba
n
d
u
n
g
,
i
n
2
0
2
2
.
S
h
e
is
c
u
rre
n
tl
y
a
lec
tu
re
r
i
n
t
h
e
De
p
a
rtm
e
n
t
o
f
El
e
c
tri
c
a
l
E
n
g
in
e
e
rin
g
,
Un
iv
e
rsit
y
Je
n
d
e
ra
l
S
o
e
d
irm
a
n
.
He
r
re
se
a
r
c
h
in
tere
sts
a
re
in
th
e
a
re
a
s
o
f
sig
n
a
l
p
ro
c
e
ss
in
g
,
b
io
m
e
d
ica
l
sig
n
a
ls,
m
a
c
h
in
e
lea
rn
in
g
a
n
d
d
a
ta
a
n
a
ly
sis.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
e
lsa
.
n
u
rd
i
n
iy
a
h
@u
n
so
e
d
.
a
c
.
i
d
.
Tr
i
W
is
u
d
a
w
a
ti
is
a
ff
il
iate
d
w
it
h
Je
n
d
e
ra
l
S
o
e
d
irm
a
n
Un
iv
e
rsity
,
In
d
o
n
e
sia
.
S
h
e
h
a
s
p
u
b
li
s
h
e
d
o
n
h
u
m
a
n
s
y
ste
m
e
n
g
in
e
e
rin
g
a
n
d
o
c
c
u
p
a
ti
o
n
a
l
h
e
a
lt
h
a
n
d
sa
f
e
t
y
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
tri
.
w
isu
d
a
wa
ti
@u
n
so
e
d
.
a
c
.
id
.
Evaluation Warning : The document was created with Spire.PDF for Python.