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.
23
,
No
.
6
,
Dec
em
b
er
20
25
,
p
p
.
1
5
7
9
~1
589
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
23
i
6
.
27103
1579
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//jo
u
r
n
a
l.u
a
d
.
a
c.
id
/in
d
ex
.
p
h
p
/TELK
OM
N
I
K
A
O
pti
m
i
z
a
tion
o
f
p
rincipa
l co
m
po
ne
nt
a
na
ly
sis
a
nd
k
-
nea
rest
neig
hbo
rs
in cul
ti
v
a
tion a
rea cla
ss
ificatio
n red
o
nio
n
Arif
Ridh
o
L
u
bis
1
,
P
urw
a
H
a
s
a
n P
utr
a
1
,
F
a
hd
i Sa
idi
L
u
bis
2
1
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
a
n
d
I
n
f
o
r
mat
i
c
s,
P
o
l
i
t
e
k
n
i
k
N
e
g
e
r
i
M
e
d
a
n
,
M
e
d
a
n
,
I
n
d
o
n
e
si
a
2
D
e
p
a
r
t
e
me
n
t
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
a
n
d
I
n
f
o
r
mat
i
o
n
T
e
c
h
n
o
l
o
g
y
,
I
n
t
e
r
n
a
si
o
n
a
l
I
sl
a
mi
c
U
n
i
v
e
r
si
t
y
M
a
l
a
y
si
a
,
S
e
l
a
n
g
o
r
,
M
a
l
a
y
si
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Mar
29
,
2
0
2
5
R
ev
i
s
ed
Oct
12
,
2
0
2
5
A
cc
ep
ted
Oct
19
,
2
0
2
5
T
h
is
re
se
a
rc
h
a
i
m
s
to
in
c
re
a
se
th
e
e
f
fe
c
ti
v
e
n
e
ss
in
c
las
sify
in
g
sh
a
ll
o
t
c
u
lt
iv
a
ti
o
n
a
re
a
s
th
ro
u
g
h
th
e
c
o
m
b
in
e
d
a
p
p
li
c
a
ti
o
n
o
f
p
rin
c
ip
a
l
c
o
m
p
o
n
e
n
t
a
n
a
ly
sis
(P
CA
)
a
n
d
k
-
n
e
a
re
st
n
e
ig
h
b
o
rs
(KN
N)
m
e
th
o
d
s.
S
h
a
ll
o
t
is
a
n
im
p
o
rtan
t
a
g
ricu
lt
u
ra
l
c
o
m
m
o
d
it
y
,
a
n
d
id
e
n
ti
f
ica
ti
o
n
o
f
o
p
t
im
a
l
a
re
a
s
f
o
r
it
s
c
u
lt
iv
a
ti
o
n
is
e
ss
e
n
ti
a
l
to
s
u
p
p
o
rt
f
o
o
d
se
lf
-
su
ff
icie
n
c
y
.
On
io
n
c
u
lt
iv
a
ti
o
n
i
s
g
e
n
e
ra
ll
y
d
o
n
e
in
th
e
h
ig
h
lan
d
s.
On
e
o
f
th
e
a
re
a
s
w
it
h
sh
a
ll
o
t
c
u
lt
iv
a
ti
o
n
i
n
No
rth
S
u
m
a
tra
P
ro
v
in
c
e
is
Be
ra
sta
g
i,
Ka
ro
Re
g
e
n
c
y
.
T
h
is
re
s
e
a
rc
h
w
a
s
co
n
d
u
c
ted
b
y
d
e
term
in
in
g
th
e
sp
a
ti
a
l
e
x
ten
t
o
f
u
p
lan
d
la
n
d
.
In
t
h
e
u
se
o
f
d
a
ta
th
e
re
a
re
2
ty
p
e
s
o
f
d
a
ta
th
a
t
w
il
l
b
e
u
se
d
:
la
n
d
s
u
it
a
b
i
li
ty
d
a
tas
e
t
a
n
d
lan
d
c
o
n
d
i
ti
o
n
d
a
tas
e
t
f
o
r
e
a
c
h
re
g
io
n
.
T
h
e
P
CA
m
e
th
o
d
is u
t
il
ize
d
t
o
si
m
p
li
fy
th
e
d
a
ta
stru
c
t
u
re
b
y
re
d
u
c
i
n
g
t
h
e
n
u
m
b
e
r
o
f
d
im
e
n
sio
n
s
a
n
d
re
m
o
v
in
g
in
sig
n
if
ica
n
t
a
tt
rib
u
tes
,
w
h
il
e
KN
N
w
a
s
u
se
d
to
c
las
sify
re
g
io
n
s
b
a
se
d
o
n
th
e
ir
su
it
a
b
il
it
y
f
o
r
sh
a
ll
o
t
c
u
lt
iv
a
ti
o
n
.
T
h
is r
e
se
a
rc
h
p
r
o
d
u
c
e
s a
c
las
sif
ic
a
ti
o
n
m
a
p
th
a
t
c
a
n
b
e
u
se
d
to
id
e
n
ti
fy
th
e
m
o
st
o
p
ti
m
a
l
a
re
a
s
f
o
r
sh
a
ll
o
t
c
u
lt
iv
a
ti
o
n
.
T
h
e
tes
t
re
su
lt
s
w
it
h
th
e
re
g
io
n
a
l
sp
a
ti
a
l
d
a
tas
e
t
u
sin
g
p
re
c
isio
n
,
re
c
a
ll
a
n
d
f
i
-
sc
o
re
tes
ti
n
g
a
c
c
u
ra
c
y
v
a
lu
e
0
.
9
2
%
,
a
n
d
m
a
c
ro
a
v
g
v
a
lu
e
0
.
9
4
%
,
w
e
ig
h
t
e
d
a
v
g
v
a
lu
e
0
.
9
3
%
.
K
ey
w
o
r
d
s
:
K
-
n
ea
r
est n
e
ig
h
b
o
r
Op
ti
m
izatio
n
P
r
in
cip
al
co
m
p
o
n
e
n
t a
n
al
y
s
is
R
ed
o
n
io
n
R
eg
io
n
clas
s
if
icatio
n
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
:
A
r
i
f
R
id
h
o
L
u
b
is
Dep
ar
te
m
en
t o
f
C
o
m
p
u
ter
E
n
g
in
ee
r
i
n
g
an
d
I
n
f
o
r
m
atic
s
,
P
o
litek
n
ik
Ne
g
er
i M
ed
an
Me
d
an
,
I
n
d
o
n
esia
E
m
ail:
ar
i
f
r
id
h
o
@
p
o
l
m
ed
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
R
ed
o
n
io
n
(
A
lliu
m
a
s
ca
lo
n
icu
m
L.
)
is
o
n
e
o
f
th
e
i
m
p
o
r
tan
t
h
o
r
ticu
lt
u
r
al
co
m
m
o
d
ities
i
n
I
n
d
o
n
esia,
esp
ec
iall
y
i
n
No
r
th
Su
m
atr
a.
T
h
is
p
lan
t
h
a
s
h
ig
h
ec
o
n
o
m
ic
v
alu
e
a
n
d
a
w
id
e
r
an
g
e
o
f
f
u
n
ct
io
n
al
b
en
e
f
i
ts
,
b
o
th
as
a
k
itc
h
e
n
s
p
ice
a
n
d
as
a
tr
ad
itio
n
al
m
ed
icin
e
[
1
]
,
[
2
]
.
I
n
ad
d
itio
n
,
s
h
allo
ts
als
o
co
n
tain
b
io
ac
tiv
e
co
m
p
o
u
n
d
s
t
h
at
ar
e
b
en
ef
icial
to
h
ea
lth
,
s
u
ch
a
s
an
t
io
x
id
an
t
s
,
an
tib
ac
ter
ial
ag
en
t
s
,
an
d
an
tira
d
icals.
Sh
allo
t
s
ar
e
o
n
e
o
f
th
e
co
u
n
tr
y
’
s
lead
in
g
co
m
m
o
d
itie
s
w
i
th
p
r
o
m
is
i
n
g
m
ar
k
et
p
r
o
s
p
ec
ts
an
d
p
la
y
a
r
o
le
in
s
u
p
p
o
r
tin
g
f
o
o
d
s
elf
-
s
u
f
f
icie
n
c
y
p
r
o
g
r
a
m
s
.
Ho
w
ev
er
,
s
h
allo
t
c
u
lt
iv
at
io
n
is
g
r
ea
tl
y
i
n
f
l
u
en
ce
d
b
y
en
v
ir
o
n
m
e
n
tal
f
ac
to
r
s
,
p
ar
ticu
lar
l
y
w
ater
av
ailab
ilit
y
,
s
o
il
ty
p
e,
an
d
cli
m
atic
co
n
d
it
io
n
s
.
T
h
is
p
lan
t
is
q
u
ite
s
en
s
it
iv
e
to
b
o
th
ex
ce
s
s
an
d
d
ef
icien
c
y
o
f
w
ater
,
w
h
i
ch
ca
n
ca
u
s
e
b
u
lb
r
o
t
o
r
s
h
r
in
k
a
g
e
[
3
]
,
[
4
]
.
I
n
No
r
th
Su
m
atr
a,
ar
ea
s
s
u
ch
as
B
er
astag
i
in
Kar
o
R
eg
e
n
c
y
a
r
e
k
n
o
w
n
a
s
m
aj
o
r
ce
n
ter
s
f
o
r
s
h
allo
t
cu
lti
v
atio
n
b
ec
au
s
e
t
h
e
y
h
a
v
e
h
i
g
h
lan
d
g
eo
g
r
ap
h
ical
c
h
ar
ac
ter
is
tic
s
th
at
ar
e
s
u
itab
le
f
o
r
th
e
g
r
o
w
th
o
f
th
is
p
lan
t.
Desp
ite
th
eir
g
r
ea
t
p
o
ten
tial,
s
h
al
lo
t
f
ar
m
er
s
in
I
n
d
o
n
esia
o
f
ten
f
ac
e
v
ar
io
u
s
tec
h
n
ica
l
o
b
s
tacle
s
,
in
cl
u
d
in
g
cr
o
p
f
ail
u
r
e
an
d
s
ig
n
if
ican
t
p
r
ice
f
l
u
ctu
a
tio
n
s
.
Fo
r
ex
a
m
p
le,
t
h
e
p
r
ice
o
f
s
h
allo
t
s
r
o
s
e
f
r
o
m
Rp
3
6
,
3
2
0
in
J
an
u
ar
y
2
0
2
4
to
R
p
4
8
,
4
0
0
in
Ma
y
2
0
2
4
,
in
d
i
ca
tin
g
h
i
g
h
m
ar
k
e
t
v
o
latili
t
y
[
4
]
,
[
5
]
.
On
e
o
f
th
e
m
ai
n
ca
u
s
es
o
f
cr
o
p
i
n
s
tab
ilit
y
i
s
t
h
e
lac
k
o
f
in
f
o
r
m
a
tio
n
r
eg
ar
d
in
g
t
h
e
s
u
itab
ili
t
y
o
f
la
n
d
f
o
r
p
r
o
p
er
s
h
allo
t
cu
lti
v
atio
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.
23
,
No
.
6
,
Dec
em
b
er
20
25
:
1
5
7
9
-
1
589
1580
C
las
s
i
f
y
i
n
g
r
eg
io
n
s
b
ased
o
n
lan
d
s
u
itab
ilit
y
r
e
m
ai
n
s
a
m
aj
o
r
ch
allen
g
e
i
n
I
n
d
o
n
esia
’
s
a
g
r
icu
l
tu
r
al
s
y
s
te
m
.
Facto
r
s
s
u
c
h
a
s
s
o
il
t
y
p
e,
altitu
d
e,
cli
m
ate,
an
d
w
ater
a
v
ailab
ilit
y
ar
e
cr
itical
to
th
e
s
u
cc
e
s
s
o
f
cu
lti
v
atio
n
.
T
h
er
ef
o
r
e,
a
m
o
r
e
s
cien
t
if
ic
a
n
d
s
y
s
te
m
at
ic
a
p
p
r
o
ac
h
is
n
ee
d
ed
to
h
elp
class
i
f
y
cu
l
tiv
a
tio
n
r
eg
io
n
s
e
f
f
ec
ti
v
el
y
a
n
d
ef
f
icie
n
tl
y
[
6
]
.
Sh
allo
t
s
ar
e
w
id
el
y
g
r
o
w
n
in
b
o
th
lo
w
la
n
d
s
a
n
d
h
ig
h
la
n
d
s
.
T
h
o
s
e
g
r
o
w
n
a
t
h
ig
h
a
ltit
u
d
es
u
s
u
all
y
h
av
e
s
m
aller
b
u
lb
s
an
d
le
s
s
s
h
in
y
co
lo
r
,
an
d
t
h
o
s
e
g
r
o
w
n
a
t
lo
w
a
ltit
u
d
es
ar
e
u
s
u
all
y
o
ld
er
.
On
e
o
f
t
h
e
m
o
s
t
co
m
m
o
n
t
ec
h
n
ical
co
n
s
tr
ai
n
t
s
is
th
e
s
u
itab
ilit
y
o
f
th
e
r
eg
io
n
in
w
h
ich
to
g
r
o
w
s
h
allo
t
s
.
T
h
r
o
u
g
h
t
h
is
p
r
o
ce
s
s
,
a
class
i
f
icatio
n
o
f
s
h
allo
t
c
u
lt
iv
atio
n
ar
ea
s
w
ill
b
e
co
n
d
u
c
t
ed
.
T
h
is
r
esear
ch
w
i
ll
i
m
p
lem
en
t
s
o
il
co
n
d
itio
n
d
ata
an
d
s
o
il c
o
n
d
itio
n
w
it
h
s
e
v
er
al
p
ar
a
m
et
er
s
u
s
i
n
g
m
ac
h
i
n
e
l
ea
r
n
in
g
[
7
]
,
[
8
]
.
T
h
e
class
if
icat
io
n
o
f
r
eg
io
n
s
b
ased
o
n
lan
d
s
u
itab
ilit
y
r
em
ai
n
s
a
m
aj
o
r
ch
allen
g
e
in
I
n
d
o
n
esia
’
s
ag
r
icu
l
tu
r
al
s
y
s
te
m
.
Facto
r
s
s
u
c
h
as
s
o
il
t
y
p
e,
al
tit
u
d
e,
cli
m
ate,
a
n
d
w
ater
av
ai
lab
ilit
y
ar
e
cr
itical
to
th
e
s
u
cc
e
s
s
o
f
c
u
lti
v
atio
n
.
T
h
er
ef
o
r
e,
a
m
o
r
e
s
cie
n
ti
f
ic
an
d
s
y
s
te
m
a
tic
ap
p
r
o
ac
h
is
n
ee
d
ed
to
h
elp
class
if
y
cu
lti
v
atio
n
ar
ea
s
e
f
f
ec
ti
v
el
y
a
n
d
ef
f
icie
n
tl
y
[
9
]
,
[
1
0
]
.
T
h
e
co
m
b
i
n
atio
n
o
f
t
h
ese
t
w
o
m
et
h
o
d
s
h
as
b
ee
n
p
r
o
v
en
ef
f
ec
tiv
e
i
n
v
ar
io
u
s
p
r
ev
io
u
s
s
tu
d
ie
s
,
s
u
c
h
as
i
n
th
e
cla
s
s
i
f
i
ca
tio
n
o
f
o
n
io
n
s
p
ec
ies
a
n
d
ap
p
le
v
ar
ieties
w
it
h
ac
cu
r
ac
ies
o
f
9
5
%
an
d
9
1
.
6
7
%,
r
esp
ec
tiv
el
y
[
1
1
]
,
[
1
2
]
.
T
h
is
s
tu
d
y
id
en
ti
f
ied
5
1
,
4
9
9
h
ig
h
-
q
u
ali
t
y
v
ar
ian
t
s
an
d
u
tili
ze
d
t
h
e
d
ata
to
b
u
ild
a
g
en
o
m
ic
e
s
ti
m
ated
b
r
ee
d
in
g
v
a
l
u
e
(
GE
B
V)
m
o
d
el,
an
d
ap
p
lie
d
m
ac
h
i
n
e
lear
n
i
n
g
m
et
h
o
d
s
to
p
r
ed
ict
tu
b
er
w
e
ig
h
t.
Valid
atio
n
r
es
u
lt
s
o
n
2
6
0
n
e
w
i
n
d
iv
id
u
als
s
h
o
w
ed
t
h
at
th
e
m
o
d
el
w
a
s
ab
le
to
ac
h
iev
e
8
3
.
2
%
p
r
ed
ictio
n
ac
c
u
r
ac
y
.
A
s
an
e
f
f
o
r
t
to
o
v
er
co
m
e
th
e
s
e
p
r
o
b
lem
s
,
w
e
also
i
m
p
le
m
e
n
ted
a
d
ig
ital
b
r
ee
d
in
g
ap
p
r
o
ac
h
b
ased
o
n
g
en
o
m
ic
d
ata
f
r
o
m
9
8
s
u
p
er
io
r
o
n
io
n
s
tr
ai
n
s
[
5
]
.
An
o
th
er
s
tu
d
y
w
a
s
co
n
d
u
cte
d
w
it
h
t
h
e
ai
m
o
f
s
i
m
p
li
f
y
in
g
t
h
e
d
ata
an
d
r
e
m
o
v
i
n
g
les
s
r
elev
a
n
t
attr
ib
u
tes
w
it
h
o
u
t
r
ed
u
ci
n
g
t
h
e
ess
en
ce
o
f
in
f
o
r
m
at
io
n
f
r
o
m
th
e
o
r
ig
i
n
al
d
ata.
T
h
is
w
a
s
d
o
n
e
th
r
o
u
g
h
t
h
e
ap
p
licatio
n
o
f
t
h
e
p
r
in
cip
al
co
m
p
o
n
en
t a
n
a
l
y
s
is
(
P
C
A
)
m
et
h
o
d
to
im
p
r
o
v
e
t
h
e
ac
c
u
r
ac
y
p
e
r
f
o
r
m
an
ce
o
f
t
h
e
k
-
n
ea
r
est
n
ei
g
h
b
o
r
(
KNN)
clas
s
if
ica
tio
n
alg
o
r
it
h
m
.
T
h
e
r
esu
lts
o
f
t
h
e
m
o
d
if
ied
m
et
h
o
d
s
h
o
w
ed
an
av
er
ag
e
ac
cu
r
ac
y
o
f
8
8
%,
w
ith
v
alu
e
s
v
ar
y
i
n
g
f
r
o
m
=
3
to
=
9
[
1
3
]
.
T
h
e
m
ai
n
co
n
tr
ib
u
tio
n
o
f
th
is
r
ese
ar
ch
is
th
e
d
ev
e
lo
p
m
en
t
o
f
a
s
p
atial
class
i
f
icatio
n
s
y
s
te
m
f
o
r
s
h
a
ll
o
t
cu
lti
v
atio
n
ar
ea
s
b
ased
o
n
m
ac
h
in
e
lear
n
i
n
g
,
u
tili
zi
n
g
lan
d
co
n
d
itio
n
d
ata
an
d
en
v
ir
o
n
m
e
n
tal
p
ar
a
m
eter
s
.
T
h
is
r
esear
ch
aim
s
to
p
r
o
d
u
ce
a
m
o
r
e
ac
cu
r
ate
an
d
ap
p
lica
b
le
class
if
icat
io
n
m
o
d
el
as
a
b
asi
s
f
o
r
d
ec
is
io
n
m
a
k
i
n
g
i
n
p
lan
n
i
n
g
s
h
al
lo
t
cu
lti
v
atio
n
i
n
th
e
h
ig
h
la
n
d
s
o
f
No
r
t
h
Su
m
atr
a
.
2.
M
E
T
H
O
D
In
ca
r
r
y
i
n
g
o
u
t
th
e
r
esear
ch
p
r
o
ce
s
s
,
a
d
esig
n
is
n
ee
d
ed
th
at
ca
n
d
eter
m
i
n
e
th
e
s
ta
g
es
i
n
th
e
p
r
o
ce
s
s
o
f
s
tar
tin
g
t
h
e
d
esig
n
,
d
ata
co
llectio
n
,
an
d
th
e
p
r
o
ce
s
s
o
f
ap
p
ly
i
n
g
th
e
cla
s
s
i
f
icatio
n
o
f
s
h
allo
t
cu
lti
v
atio
n
ar
ea
s
.
T
h
e
r
esear
ch
d
esi
g
n
a
s
a
r
o
ad
m
ap
o
f
r
esear
ch
th
at
will
b
e
co
m
p
leted
,
a
m
atu
r
e
d
es
ig
n
w
ill
p
r
o
d
u
ce
a
s
tu
d
y
th
at
ca
n
b
e
u
s
e
f
u
l
f
o
r
th
e
co
m
m
u
n
it
y
,
esp
ec
ial
l
y
i
n
th
i
s
s
tu
d
y
s
u
p
p
o
r
tin
g
t
h
e
g
o
v
er
n
m
en
t
in
i
n
cr
ea
s
i
n
g
s
h
allo
t
c
u
lti
v
atio
n
an
d
u
s
e
f
u
l
f
o
r
B
er
astag
i
f
ar
m
er
s
i
n
d
eter
m
in
in
g
t
h
e
s
p
atial
h
i
g
h
lan
d
lan
d
th
a
t
h
a
s
a
n
i
m
p
ac
t o
n
cr
o
p
y
ield
s
.
2
.
1
.
Da
t
a
s
et
s
I
n
th
is
s
t
u
d
y
t
h
e
au
t
h
o
r
s
w
i
ll
co
llect
d
ata
lo
ca
ted
in
s
ev
er
al
ar
ea
s
o
f
No
r
th
Su
m
atr
a
in
clu
d
in
g
in
Nag
ali
n
g
g
a
Vi
llag
e,
Me
r
e
k
Dis
tr
ict,
Kab
an
j
ah
e
Di
s
tr
ict,
Kar
o
R
eg
en
c
y
,
No
r
th
Su
m
atr
a
2
2
1
7
3
,
an
d
in
th
e
L
a
k
e
T
o
b
a
ar
ea
.
I
n
u
s
i
n
g
t
h
e
d
ata
th
er
e
ar
e
2
ty
p
es
o
f
d
ata
th
at
w
ill
b
e
u
s
ed
:
la
n
d
s
u
i
tab
ili
t
y
d
ataset
an
d
la
n
d
co
n
d
itio
n
d
ataset
f
o
r
ea
ch
r
eg
io
n
.
E
ac
h
tab
le,
g
en
er
ated
f
r
o
m
th
e
s
u
itab
ilit
y
o
f
f
ea
t
u
r
e
s
w
it
h
o
p
ti
m
a
l
la
n
d
p
lan
tin
g
co
n
d
itio
n
s
.
Fo
r
ex
a
m
p
le,
a
tem
p
er
at
u
r
e
o
f
2
5
-
32
°C
,
an
d
b
ein
g
at
an
altitu
d
e
o
f
0
-
4
5
0
m
eter
s
ab
o
v
e
s
ea
le
v
el,
as
w
el
l a
s
o
th
er
ca
te
g
o
r
ies,
w
i
ll g
e
n
er
all
y
f
a
ll in
to
th
e
ex
ce
l
len
t
/g
o
o
d
ca
teg
o
r
y
.
2
.
2
.
P
re
pro
ce
s
s
ing
Data
clea
n
i
n
g
is
a
n
i
m
p
o
r
tan
t
s
tep
in
d
ata
p
r
e
-
p
r
o
ce
s
s
in
g
th
at
ai
m
s
to
en
s
u
r
e
t
h
e
q
u
al
it
y
o
f
d
ata
b
ef
o
r
e
it
is
u
s
ed
in
ad
d
itio
n
al
an
al
y
s
is
o
r
m
ac
h
i
n
e
lear
n
i
n
g
m
o
d
el
s
.
Data
clea
n
in
g
u
s
es
v
a
r
io
u
s
tech
n
iq
u
e
s
to
f
i
n
d
an
d
co
r
r
ec
t
er
r
o
r
s
,
in
co
n
s
is
ten
c
ies,
a
n
d
in
ac
c
u
r
ac
ies
p
r
e
s
en
t
i
n
t
h
e
d
ata
s
e
t.
Data
p
r
ep
r
o
ce
s
s
in
g
is
th
e
ac
t
o
f
r
ef
i
n
in
g
a
n
d
ev
al
u
ati
n
g
o
l
d
d
ata
s
ets
to
p
r
o
d
u
ce
n
e
w
d
ata
s
u
itab
le
f
o
r
u
s
e
i
n
s
u
b
s
eq
u
en
t
p
r
o
ce
s
s
e
s
.
T
h
e
r
ed
u
ce
d
,
tr
an
s
f
o
r
m
ed
,
an
d
tr
an
s
f
o
r
m
ed
d
ata
in
clu
d
ed
in
t
h
is
7
0
%
w
i
ll
b
e
u
s
ed
f
o
r
te
s
tin
g
an
d
3
0
%
f
o
r
tr
ain
i
n
g
.
T
o
s
tan
d
ar
d
ize
th
e
in
p
u
t
d
ataset
f
ea
t
u
r
es,
th
e
tr
ai
n
i
n
g
a
n
d
test
i
n
g
d
ata
w
ill
b
e
s
ca
led
th
r
o
u
g
h
o
u
t
t
h
e
p
r
o
ce
d
u
r
e.
T
o
s
t
an
d
ar
d
ize
th
e
d
ata,
n
o
r
m
alize
d
Z
s
co
r
es
w
i
ll
b
e
u
s
ed
[
1
4
]
,
[
1
5
]
.
T
h
is
g
u
ar
an
tees
a
r
eliab
le
co
m
p
ar
is
o
n
o
f
f
ea
tu
r
e
s
w
it
h
d
if
f
er
en
t scale
s
b
u
t
w
i
th
t
h
e
s
a
m
e
v
er
s
io
n
.
T
h
is
d
ataset,
w
h
ic
h
h
as
p
r
e
v
i
o
u
s
l
y
b
ee
n
m
ad
e
av
ailab
le
to
ar
o
u
n
d
5
0
0
u
s
er
s
,
h
as
f
i
v
e
lab
el
ca
teg
o
r
ies:
ex
ce
l
len
t,
v
er
y
g
o
o
d
,
f
air
,
p
o
o
r
an
d
v
er
y
p
o
o
r
.
T
h
is
in
d
icate
s
t
h
e
ex
te
n
t
o
f
t
h
e
co
n
d
itio
n
o
f
t
h
e
o
n
io
n
cu
l
tiv
a
tio
n
f
ield
.
T
h
e
p
u
r
p
o
s
e
o
f
th
i
s
d
ata
is
to
tr
ain
an
d
test
th
e
P
C
A
a
n
d
K
NN
m
o
d
el
s
,
an
d
w
ill
b
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
Op
timiz
a
tio
n
o
f p
r
in
cip
a
l c
o
m
p
o
n
en
t
a
n
a
lysi
s
a
n
d
k
-
n
ea
r
est
n
ei
g
h
b
o
r
s
in
…
(
A
r
if R
id
h
o
Lu
b
is
)
1581
u
s
ed
as
tr
ain
in
g
d
ata,
th
e
f
ea
tu
r
es
u
s
ed
to
o
b
tain
th
e
ab
o
v
e
la
b
els
ar
e
th
e
co
n
d
itio
n
o
f
th
e
ar
ea
,
an
d
th
e
cr
iter
ia
o
f
th
e
a
g
r
icu
lt
u
r
al
ar
ea
.
a.
T
em
p
er
atu
r
e
(
C
els
iu
s
)
b.
R
ain
f
all
(
m
m
/
y
ea
r
)
c.
E
lev
atio
n
(
ab
o
v
e
s
ea
le
v
el)
d.
Dr
ain
ag
e
(
v
er
y
g
o
o
d
,
g
o
o
d
,
f
a
ir
,
b
ad
,
v
er
y
b
ad
)
e.
So
il tex
t
u
r
e
(
v
er
y
f
i
n
e,
f
i
n
e,
m
ed
iu
m
,
co
ar
s
e,
v
er
y
co
ar
s
e
)
f.
P
o
ten
tial o
f
h
y
d
r
o
g
e
n
(
pH
)
g.
C
atio
n
e
x
ch
a
n
g
e
c
ap
ac
it
y
(
v
er
y
g
o
o
d
,
g
o
o
d
,
f
air
,
p
o
o
r
,
v
er
y
p
o
o
r
)
h.
B
ase
s
atu
r
atio
n
(
v
er
y
g
o
o
d
,
g
o
o
d
,
f
air
,
p
o
o
r
,
v
er
y
p
o
o
r
)
i.
R
elie
f
/
s
lo
p
e
(
f
lat,
g
en
t
le,
s
lo
p
in
g
,
s
teep
,
s
teep
)
T
h
e
r
esear
ch
d
esig
n
i
s
s
h
o
w
n
in
Fi
g
u
r
e
1
.
I
n
th
is
s
tu
d
y
,
t
h
e
a
u
th
o
r
u
s
ed
a
d
ataset
o
f
lan
d
co
n
d
itio
n
s
f
o
r
s
h
allo
t c
u
lti
v
atio
n
b
ased
o
n
s
e
v
er
al
cr
iter
ia,
s
h
o
w
n
in
T
ab
le
1
.
Fig
u
r
e
1
.
R
esear
ch
p
r
o
ce
s
s
f
lo
w
m
o
d
el
T
ab
le
1
.
L
an
d
co
n
d
itio
n
d
a
tas
et
I
d
T
e
mp
e
r
a
t
u
r
e
R
a
i
n
f
a
l
l
E
l
e
v
a
t
i
o
n
D
r
a
i
n
a
g
e
S
o
i
l
t
e
x
t
u
r
e
p
H
C
a
t
i
o
n
e
x
c
h
a
n
g
e
c
a
p
a
c
i
t
y
R
e
l
i
e
f
L
a
b
e
l
1
25
1
7
0
0
4
0
0
V
e
r
y
g
o
o
d
M
e
d
i
u
m
6
.
1
V
e
r
y
g
ood
F
l
a
t
V
e
r
y
g
o
o
d
2
33
2
7
0
0
1
7
0
0
S
i
mp
l
y
R
o
u
g
h
6
.
7
V
e
r
y
b
ad
I
t
a
l
i
c
s
B
a
d
3
28
1
3
0
0
1
0
0
0
B
o
t
h
M
e
d
i
u
m
5
.
5
S
i
mp
l
y
R
a
m
p
s
B
o
t
h
4
30
1
1
0
0
2
0
0
V
e
r
y
g
ood
S
mo
o
t
h
5
.
9
V
e
r
y
g
ood
R
a
m
p
s
V
e
r
y
g
o
o
d
…
….
…
…
…
…
…
…
…
…
2
.
3
.
P
rincipa
l
co
m
po
nent
a
n
a
l
y
s
is
T
h
e
d
im
e
n
s
io
n
alit
y
r
ed
u
ctio
n
p
r
o
ce
s
s
is
ca
r
r
ied
o
u
t
th
r
o
u
g
h
th
e
ap
p
licatio
n
o
f
P
C
A
w
it
h
th
e
ai
m
o
f
r
ed
u
cin
g
th
e
n
u
m
b
er
o
f
f
ea
t
u
r
es
o
r
v
ar
iab
les
in
th
e
d
ataset
w
i
th
o
u
t
eli
m
i
n
ati
n
g
th
e
ess
e
n
tial
in
f
o
r
m
at
io
n
co
n
tain
ed
t
h
er
ei
n
[
1
6
]
,
[
1
7
]
.
T
h
e
p
u
r
p
o
s
e
o
f
t
h
is
p
r
o
ce
s
s
is
to
s
p
ee
d
u
p
p
r
o
ce
s
s
i
n
g
ti
m
e,
s
i
m
p
li
f
y
m
o
d
el
co
m
p
le
x
it
y
,
an
d
r
ed
u
ce
t
h
e
r
is
k
o
f
o
v
er
f
it
t
in
g
.
Feat
u
r
e
r
ed
u
ctio
n
i
s
d
o
n
e
b
y
tr
an
s
f
o
r
m
i
n
g
h
i
g
h
-
d
i
m
e
n
s
io
n
al
d
ata
in
to
lo
w
er
-
d
i
m
e
n
s
io
n
al
d
ata
co
n
s
is
ti
n
g
o
f
u
n
co
r
r
elate
d
attr
ib
u
tes
[
1
8
]
.
T
h
is
r
esear
ch
p
r
o
p
o
s
es
a
P
C
A
-
b
ased
f
r
am
e
w
o
r
k
to
s
elec
t
a
s
u
b
s
et
o
f
s
ig
n
i
f
ica
n
t
an
d
m
u
tu
a
ll
y
u
n
co
r
r
elate
d
f
ea
tu
r
es.
T
h
is
s
tu
d
y
u
ti
lizes
P
C
A
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.
23
,
No
.
6
,
Dec
em
b
er
20
25
:
1
5
7
9
-
1
589
1582
as
a
f
ea
t
u
r
e
s
elec
t
io
n
m
et
h
o
d
to
r
ed
u
ce
d
ata
b
y
r
etai
n
i
n
g
f
e
atu
r
es
t
h
at
ar
e
in
d
ep
en
d
e
n
t
o
f
ea
ch
o
t
h
er
[
1
9
]
.
A
v
ar
ian
ce
ca
lc
u
latio
n
is
p
er
f
o
r
m
ed
to
id
en
ti
f
y
t
h
e
d
eg
r
ee
o
f
d
is
p
er
s
io
n
i
n
t
h
e
m
ed
ical
d
ataset,
u
s
in
g
(
1
)
to
d
eter
m
in
e
h
o
w
m
u
c
h
th
e
d
ata
d
ev
iates i
n
th
e
a
n
al
y
ze
d
s
a
m
p
l
e.
(
)
=
=
1
∑
(
̃
−
)
2
=
1
(
1
)
Nex
t,
th
e
co
v
ar
ia
n
ce
w
as
ca
lc
u
lated
to
d
eter
m
i
n
e
t
h
e
r
elatio
n
s
h
ip
b
et
w
ee
n
ea
ch
cla
s
s
.
A
c
o
v
ar
ian
ce
v
alu
e
clo
s
e
to
ze
r
o
in
d
icate
s
th
at
t
h
er
e
is
n
o
r
elatio
n
s
h
ip
b
et
w
ee
n
t
h
e
t
w
o
d
i
m
en
s
io
n
s
.
T
h
e
co
v
ar
ian
ce
ca
lcu
latio
n
p
r
o
ce
s
s
is
d
o
n
e
u
s
i
n
g
(
2
)
.
(
,
)
=
1
−
1
∑
(
−
)
(
−
)
=
1
(
2
)
T
h
e
f
in
al
s
tep
in
v
o
lv
e
s
ca
lcu
l
ati
n
g
th
e
ei
g
en
v
al
u
es
an
d
ei
g
e
n
v
ec
to
r
s
o
f
t
h
e
co
v
ar
ian
ce
m
a
tr
ix
.
Nex
t,
th
e
eig
e
n
v
al
u
es a
r
e
tr
a
n
s
f
o
r
m
e
d
th
r
o
u
g
h
v
ar
i
m
a
x
o
r
th
o
g
o
n
a
l r
o
tatio
n
u
s
i
n
g
(
3
)
.
(
−
)
=
0
(
3
)
T
h
is
r
esear
ch
ap
p
lies
th
e
P
C
A
m
eth
o
d
to
th
e
f
ea
t
u
r
es c
o
n
tai
n
ed
in
t
h
e
tr
ain
i
n
g
d
ata
an
d
tes
t d
ata
.
2
.
4
.
K
-
nea
re
s
t
neig
hb
o
rs
T
h
e
KNN
class
i
f
ica
tio
n
al
g
o
r
ith
m
is
u
ti
lized
to
p
r
ed
ict
th
e
c
ateg
o
r
y
o
f
d
ata.
T
h
is
p
r
o
ce
s
s
i
s
d
o
n
e
b
y
ca
lcu
lati
n
g
th
e
d
is
ta
n
ce
b
et
w
e
en
th
e
test
d
ata
an
d
th
e
in
p
u
t
d
ata
to
d
eter
m
in
e
t
h
e
n
u
m
b
er
o
f
n
ea
r
est
n
eig
h
b
o
r
s
(
)
.
T
h
e
f
i
n
al
ca
te
g
o
r
y
o
f
t
h
e
d
ata
is
d
eter
m
i
n
ed
b
ased
o
n
t
h
e
m
aj
o
r
ity
o
f
v
o
tes
o
b
tain
ed
f
r
o
m
t
h
e
s
e
n
ea
r
es
t
n
eig
h
b
o
r
s
[
2
0
]
.
T
h
e
KNN
class
i
f
ier
u
ti
lizes
a
d
is
ta
n
ce
m
etr
ic
to
ca
lcu
late
th
e
clo
s
e
n
e
s
s
b
et
w
ee
n
te
s
t
an
d
tr
ain
i
n
g
d
ata.
W
h
e
n
t
h
e
n
u
m
b
er
o
f
s
a
m
p
les
u
s
ed
is
s
m
al
l
er
,
th
e
KNN
al
g
o
r
ith
m
i
s
ab
l
e
to
p
r
o
d
u
ce
h
ig
h
er
ac
cu
r
ac
y
w
i
t
h
a
lig
h
ter
co
m
p
u
tatio
n
a
l
b
u
r
d
en
[
2
1
]
,
[
2
2
]
.
T
h
e
co
n
ce
p
t
o
f
KNN
i
s
ill
u
s
tr
ated
in
t
h
e
f
o
llo
w
i
n
g
d
iag
r
a
m
,
s
h
o
w
n
i
n
t
h
e
f
o
llo
w
i
n
g
F
ig
u
r
e
2
.
Fig
u
r
e
2
.
E
x
p
lan
atio
n
o
f
K
NN
T
h
e
im
p
le
m
e
n
tatio
n
s
tep
s
o
f
t
h
e
KNN
s
al
g
o
r
it
h
m
ar
e:
a.
Dete
r
m
i
n
e
th
e
v
al
u
e
Dete
r
m
i
n
e
th
e
v
al
u
e
o
f
,
w
h
ic
h
is
th
e
n
u
m
b
er
o
f
n
ea
r
est
n
ei
g
h
b
o
r
s
u
s
ed
in
t
h
e
class
i
f
icati
o
n
p
r
o
ce
s
s
.
I
f
th
e
v
alu
e
is
to
o
s
m
all,
th
e
m
o
d
el
ten
d
s
to
b
e
v
er
y
s
en
s
iti
v
e
to
n
o
is
e
in
th
e
d
ata,
w
h
ich
ca
n
lead
t
o
o
v
er
f
itti
n
g
.
C
o
n
v
er
s
el
y
,
if
t
h
e
v
alu
e
is
to
o
lar
g
e,
th
e
m
o
d
el
m
a
y
l
o
s
e
f
lex
ib
il
it
y
a
n
d
r
esu
lt
in
u
n
d
er
f
itti
n
g
.
b.
C
alcu
late
th
e
d
is
tan
ce
b
et
w
ee
n
p
o
in
ts
Fo
r
ea
ch
test
d
ata,
ca
lcu
late
it
s
d
is
ta
n
ce
to
all
t
h
e
d
ata
i
n
t
h
e
tr
ain
i
n
g
d
ata
s
et.
Use
a
d
is
ta
n
ce
m
etr
ic
s
u
c
h
as
,
E
u
clid
ea
n
d
is
tan
ce
(
m
o
s
t c
o
m
m
o
n
)
:
(
,
)
=
√
∑
(
−
)
2
(
4
)
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
Op
timiz
a
tio
n
o
f p
r
in
cip
a
l c
o
m
p
o
n
en
t
a
n
a
lysi
s
a
n
d
k
-
n
ea
r
est
n
ei
g
h
b
o
r
s
in
…
(
A
r
if R
id
h
o
Lu
b
is
)
1583
c.
Nea
r
est
n
ei
g
h
b
o
r
id
en
ti
f
icatio
n
So
r
t
th
e
d
is
ta
n
ce
ca
lc
u
latio
n
r
esu
lt
s
f
r
o
m
s
m
alle
s
t
to
lar
g
e
s
t.
Select
t
h
e
n
ea
r
est
d
ata
as
th
e
n
ea
r
est
n
eig
h
b
o
r
.
d.
Gr
ad
e
o
r
g
r
ad
e
p
r
e
d
ictio
n
Fo
r
class
if
icat
io
n
:
t
ak
e
t
h
e
m
aj
o
r
ity
class
o
f
th
e
n
eig
h
b
o
r
s
(
u
s
i
n
g
m
aj
o
r
ity
v
o
ti
n
g
)
.
Fo
r
r
eg
r
ess
io
n
:
c
alcu
late
t
h
e
av
er
a
g
e
v
al
u
e
o
f
th
e
n
eig
h
b
o
r
s
.
2
.
5
.
E
v
a
lua
t
i
o
n
I
n
o
r
d
er
to
ass
ess
h
o
w
w
e
ll
a
class
i
f
icatio
n
m
o
d
el
w
o
r
k
s
,
it
is
i
m
p
o
r
ta
n
t
to
u
s
e
s
o
m
e
m
ea
s
u
r
e
o
f
j
u
d
g
m
e
n
t.
P
er
f
o
r
m
a
n
ce
ev
al
u
atio
n
o
f
class
i
f
icatio
n
m
o
d
els
r
eq
u
ir
es
th
e
u
s
e
o
f
ce
r
tain
r
ele
v
an
t
m
etr
ics.
T
h
ese
s
tep
s
ca
n
b
e
d
eter
m
i
n
ed
u
s
in
g
th
e
co
n
f
u
s
io
n
m
atr
i
x
as
an
e
v
alu
atio
n
to
o
l.
T
h
r
o
u
g
h
an
a
l
y
zi
n
g
t
h
e
ele
m
e
n
t
s
in
th
e
co
n
f
u
s
io
n
m
a
t
r
ix
,
t
h
e
p
e
r
f
o
r
m
an
ce
o
f
t
h
e
clas
s
i
f
icati
o
n
m
o
d
el
ca
n
b
e
th
o
r
o
u
g
h
l
y
ev
al
u
ated
.
I
n
t
h
is
r
esear
ch
,
a
n
u
m
b
er
o
f
m
etr
ic
s
ar
e
u
s
ed
as
ev
alu
a
tio
n
i
n
d
icato
r
s
,
in
clu
d
i
n
g
ac
c
u
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
F1
-
s
co
r
e,
an
d
ar
ea
u
n
d
er
th
e
cu
r
v
e
-
r
ec
eiv
er
o
p
er
atin
g
ch
ar
ac
ter
i
s
t
ic
(
A
UC
-
R
OC
)
[
2
3
]
,
[
2
4
]
.
I
n
m
u
l
ticlas
s
class
i
f
icatio
n
,
ac
cu
r
ac
y
is
o
n
e
o
f
th
e
m
o
s
t
co
m
m
o
n
l
y
u
s
ed
ev
al
u
atio
n
m
etr
ics
an
d
is
o
b
tain
ed
d
ir
ec
tl
y
f
r
o
m
t
h
e
c
o
n
f
u
s
io
n
m
atr
ix
.
C
las
s
i
f
icatio
n
m
o
d
els
w
it
h
h
ig
h
er
ac
cu
r
a
c
y
s
co
r
es
p
er
f
o
r
m
b
etter
.
T
h
e
ac
cu
r
ac
y
s
co
r
e
i
s
ca
lcu
lated
b
ased
o
n
t
h
e
n
u
m
b
er
o
f
co
r
r
e
ct
p
r
ed
ictio
n
s
f
o
r
ea
ch
ca
teg
o
r
y
.
A
cc
u
r
ac
y
es
ti
m
atio
n
ca
n
b
e
o
b
tain
ed
th
r
o
u
g
h
t
h
e
(
5
)
[
2
5
]
.
A
cc
=
+
+
+
+
(
5
)
I
n
d
ea
lin
g
w
it
h
o
n
io
n
d
ataset
s
,
r
ely
i
n
g
o
n
o
v
er
all
ac
cu
r
ac
y
as
t
h
e
s
o
le
in
d
icato
r
o
f
cla
s
s
i
f
ic
atio
n
p
er
f
o
r
m
a
n
ce
is
o
f
te
n
in
ap
p
r
o
p
r
iate,
esp
ec
ially
f
o
r
d
etec
tin
g
p
o
s
itiv
e
class
e
s
th
at
ar
e
in
th
e
m
i
n
o
r
it
y
.
T
h
er
ef
o
r
e,
th
is
s
tu
d
y
u
s
e
s
th
e
p
r
ec
is
io
n
m
etr
ic,
w
h
ic
h
is
w
id
el
y
ap
p
lied
in
d
ata
an
al
y
s
i
s
an
d
s
tatis
tical
test
i
n
g
.
T
h
e
p
r
ec
is
io
n
v
al
u
e
i
s
ca
lc
u
lat
ed
u
s
i
n
g
(
6
)
,
p
r
ec
is
io
n
is
m
ea
s
u
r
ed
b
y
d
iv
id
i
n
g
t
h
e
n
u
m
b
er
o
f
p
o
s
iti
v
e
s
a
m
p
le
s
co
r
r
ec
tly
cla
s
s
i
f
ied
b
y
t
h
e
m
o
d
el
b
y
t
h
e
to
tal
p
o
s
itiv
e
p
r
e
d
ictio
n
s
g
en
er
ated
.
T
h
is
ap
p
r
o
ac
h
co
n
s
id
er
s
t
h
e
s
p
ec
ial
ch
allen
g
e
s
ar
is
in
g
f
r
o
m
t
h
e
p
r
esen
ce
o
f
m
in
o
r
it
y
class
es,
th
u
s
p
r
o
v
id
in
g
a
m
o
r
e
c
o
m
p
r
eh
e
n
s
iv
e
ev
alu
a
tio
n
o
f
t
h
e
clas
s
i
f
icatio
n
p
er
f
o
r
m
a
n
ce
i
n
th
e
co
n
tex
t o
f
th
e
o
n
io
n
d
atase
t.
=
+
(
6
)
T
r
u
e
p
o
s
itiv
e
r
ate,
also
k
n
o
w
n
a
s
r
ec
all
in
th
e
co
n
tex
t
o
f
in
f
o
r
m
atio
n
r
etr
iev
al,
d
es
cr
ib
es
th
e
p
r
o
p
o
r
tio
n
o
f
r
elev
an
t
o
b
j
ec
ts
th
at
ar
e
co
r
r
ec
tly
r
ec
o
g
n
ized
o
u
t
o
f
all
o
b
j
ec
ts
p
r
ed
icted
to
b
e
r
elev
an
t.
T
h
is
m
etr
ic
ev
al
u
ate
s
th
e
ex
te
n
t
t
o
w
h
ic
h
th
e
cla
s
s
i
f
icatio
n
m
o
d
el
is
ab
l
e
to
ac
cu
r
atel
y
id
en
ti
f
y
a
n
d
r
etr
iev
e
r
elev
an
t e
x
a
m
p
les
f
r
o
m
th
e
a
v
ailab
le
d
ataset.
T
h
e
r
e
ca
ll c
alc
u
latio
n
ca
n
b
e
f
o
r
m
u
lated
as s
h
o
w
n
i
n
(
7
)
.
=
=
+
(
7
)
I
n
g
e
n
er
al,
F1
-
s
co
r
e
is
t
h
e
h
ar
m
o
n
ic
m
ea
n
o
f
r
ec
all
an
d
p
r
ec
is
io
n
v
al
u
e
s
.
I
t
p
r
o
v
id
es
a
b
alan
ce
d
m
ea
s
u
r
e
b
y
co
n
s
id
er
in
g
th
e
m
o
d
el
’
s
ab
ilit
y
to
f
in
d
r
elev
an
t
d
ata
(
r
ec
all)
as
w
ell
as
th
e
ac
cu
r
ac
y
o
f
it
s
p
r
ed
ictio
n
s
(
p
r
ec
is
io
n
)
.
B
y
in
t
eg
r
atin
g
t
h
e
t
w
o
m
etr
ics,
F1
-
s
co
r
e
p
r
o
v
id
es
a
m
o
r
e
co
m
p
r
eh
en
s
i
v
e
ev
al
u
atio
n
o
f
th
e
clas
s
i
f
icatio
n
m
o
d
el
’
s
p
er
f
o
r
m
an
ce
,
as
s
h
o
w
n
i
n
(
8
)
.
1
−
=
2
−
1
+
−
1
=
2
x
x
+
(
8
)
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
s
ec
tio
n
p
r
esen
ts
th
e
r
es
u
l
ts
o
f
th
e
r
esear
ch
ac
co
m
p
an
ie
d
b
y
an
in
-
d
ep
th
d
is
cu
s
s
io
n
.
R
esu
lt
s
ca
n
b
e
d
is
p
lay
ed
t
h
r
o
u
g
h
v
ar
io
u
s
v
is
u
al
f
o
r
m
s
s
u
ch
a
s
i
m
a
g
es,
g
r
ap
h
s
,
tab
les,
a
n
d
o
th
er
m
ed
i
a
to
f
ac
ilit
ate
r
ea
d
er
u
n
d
er
s
ta
n
d
in
g
.
T
h
e
d
is
cu
s
s
io
n
ca
n
b
e
d
iv
id
ed
in
to
s
ev
er
al
s
u
b
s
ec
tio
n
s
ac
co
r
d
in
g
to
th
e
f
o
c
u
s
o
f
t
h
e
a
n
al
y
s
is
.
3
.
1
.
T
ra
ini
ng
m
o
del
T
h
is
r
esear
ch
w
as
d
esig
n
ed
b
y
ap
p
l
y
i
n
g
th
e
w
a
ter
f
all
m
o
d
el,
w
h
o
s
e
ill
u
s
tr
atio
n
is
p
r
esen
ted
in
th
e
Fig
u
r
e
3
.
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.
23
,
No
.
6
,
Dec
em
b
er
20
25
:
1
5
7
9
-
1
589
1584
Fig
u
r
e
3
.
Sp
atial
in
n
o
v
atio
n
b
u
ild
in
g
m
o
d
el
Fig
u
r
e
3
p
r
esen
ts
th
e
d
ev
elo
p
m
en
t
m
o
d
el
o
f
s
p
atial
in
n
o
v
a
tio
n
o
f
s
h
a
llo
t
cu
lti
v
atio
n
s
tar
tin
g
f
r
o
m
th
e
a
n
al
y
s
i
s
s
ta
g
e,
w
h
ic
h
i
n
cl
u
d
es
id
en
ti
f
y
i
n
g
t
h
e
n
ee
d
s
o
f
in
n
o
v
ati
v
e
p
r
o
d
u
cts
b
a
s
ed
o
n
t
h
e
ap
p
lica
tio
n
o
f
s
p
atial
co
n
tr
o
l,
b
o
th
in
th
e
f
o
r
m
o
f
h
ar
d
w
ar
e
an
d
s
o
f
t
w
a
r
e.
T
h
e
n
ex
t
s
tag
e
i
s
in
n
o
v
a
tio
n
d
esig
n
,
w
h
i
c
h
in
cl
u
d
es
th
e
d
esig
n
o
f
s
y
s
te
m
in
p
u
ts
,
p
r
o
ce
s
s
es,
an
d
o
u
tp
u
ts
.
Nex
t,
th
e
i
m
p
le
m
en
ta
tio
n
s
tag
e
is
ca
r
r
ied
o
u
t
th
r
o
u
g
h
th
e
co
d
i
n
g
p
r
o
ce
s
s
,
f
o
llo
w
ed
b
y
t
h
e
te
s
ti
n
g
s
ta
g
e
t
o
ev
alu
ate
th
e
f
u
n
ctio
n
a
lit
y
an
d
s
u
cc
es
s
o
f
s
y
s
te
m
ac
ce
s
s
.
Af
ter
test
in
g
,
th
e
i
n
n
o
v
ati
o
n
i
s
s
o
cialize
d
an
d
p
u
t
in
to
o
p
er
ati
o
n
.
T
h
e
f
in
al
s
tag
e
o
f
th
is
m
o
d
el
is
th
e
s
y
s
te
m
r
e
f
i
n
e
m
e
n
t p
r
o
ce
s
s
,
wh
ich
i
s
ca
r
r
ied
o
u
t o
v
er
f
i
v
e
m
o
n
th
s
o
f
i
m
p
le
m
e
n
tatio
n
.
Data
is
o
b
tain
ed
f
r
o
m
ac
t
u
al
d
ata
f
o
r
ea
ch
d
is
tr
ict/cit
y
f
r
o
m
th
e
i
n
ter
n
e
t.
T
h
er
e
ar
e
s
o
m
e
d
at
a
f
ea
t
u
r
es
t
h
at
ar
e
r
ar
el
y
av
a
ila
b
le,
s
u
c
h
as
d
r
ain
a
g
e,
p
H,
ca
t
io
n
ex
c
h
a
n
g
e
ca
p
ac
it
y
,
a
n
d
b
ase
s
at
u
r
atio
n
.
T
h
e
r
est
ar
e
av
ailab
le
o
n
th
e
i
n
t
er
n
et.
F
o
r
th
e
r
ar
el
y
av
ai
lab
le
d
ata
ab
o
v
e,
an
esti
m
ate
o
f
th
e
av
er
a
g
e
lan
d
co
n
d
itio
n
in
t
h
e
p
r
o
v
in
ce
o
f
No
r
th
Su
m
at
r
a
w
as
m
ad
e
(
e.
g
th
e
av
er
a
g
e
p
H
is
ar
o
u
n
d
5
.
6
-
6
.
5
,
s
o
it
w
a
s
ch
o
s
en
w
i
th
in
t
h
at
r
an
g
e)
.
T
h
e
f
o
llo
w
in
g
is
a
d
ataset
o
f
lan
d
co
n
d
itio
n
s
f
o
r
ea
ch
r
eg
io
n
i
n
d
i
ca
ted
in
T
ab
le
2
.
T
ab
le
2
.
L
an
d
co
n
d
itio
n
d
atas
et
f
o
r
ea
ch
r
eg
io
n
I
d
R
e
g
i
o
n
a
l
T
e
mp
e
r
a
t
u
r
e
R
a
i
n
f
a
l
l
El
e
v
a
t
i
o
n
D
r
a
i
n
a
g
e
S
o
i
l
t
e
x
t
u
r
e
p
H
C
a
t
i
o
n
e
x
c
h
a
n
g
e
c
a
p
a
c
i
t
y
B
a
se
s
a
t
u
r
a
t
i
o
n
R
e
l
i
e
f
1
K
a
r
o
24
1
2
0
0
1
0
0
0
V
e
r
y
good
S
mo
o
t
h
5
.
6
V
e
r
y
g
o
o
d
V
e
r
y
g
o
o
d
Ra
m
p
s
2
S
i
mal
u
n
g
u
n
27
1
6
0
0
1
5
0
0
V
e
r
y
good
S
mo
o
t
h
5
.
8
B
o
t
h
B
o
t
h
R
a
m
p
s
3
S
a
mo
si
r
23
1
4
0
0
1
6
0
0
B
o
t
h
M
e
d
i
u
m
6
.
3
V
e
r
y
g
o
o
d
V
e
r
y
g
o
o
d
F
l
a
t
4
T
a
p
a
n
u
l
i
U
t
a
r
a
25
1
2
0
0
1
2
0
0
V
e
r
y
good
M
e
d
i
u
m
5
.
8
V
e
r
y
g
o
o
d
V
e
r
y
g
o
o
d
I
t
a
l
i
c
s
5
S
i
b
o
l
g
a
26
1
4
0
0
2
0
0
V
e
r
y
good
M
e
d
i
u
m
6
.
4
V
e
r
y
g
o
o
d
V
e
r
y
g
o
o
d
I
t
a
l
i
c
s
…
….
…
…
…
…
…
…
…
…
A
t
t
h
e
f
o
llo
w
in
g
s
ta
g
e
is
b
ef
o
r
e
th
e
d
ata
is
tr
ain
ed
,
w
h
er
e
th
e
d
ataset
h
as
b
ee
n
m
a
n
ag
ed
an
d
is
r
ea
d
y
f
o
r
tr
ain
i
n
g
s
u
c
h
as t
h
e
f
o
llo
win
g
d
ata.
T
h
e
f
o
llo
w
i
n
g
tr
ai
n
i
n
g
d
ata
b
ef
o
r
e
tr
ain
in
g
is
s
h
o
wn
in
T
a
b
le
3
.
T
ab
le
3
.
R
eg
io
n
al
s
p
atial
d
ata
I
d
R
e
g
i
o
n
a
l
T
e
mp
e
r
a
t
u
r
e
R
a
i
n
f
a
l
l
El
e
v
a
t
i
o
n
D
r
a
i
n
a
g
e
S
o
i
l
t
e
x
t
u
r
e
p
H
C
a
t
i
o
n
e
x
c
h
a
n
g
e
c
a
p
a
c
i
t
y
B
a
se
s
a
t
u
r
a
t
i
o
n
R
e
l
i
e
f
1
K
a
r
o
24
1
2
0
0
1
0
0
0
V
e
r
y
good
S
mo
o
t
h
5
.
6
V
e
r
y
g
o
o
d
V
e
r
y
g
o
o
d
R
a
m
p
s
2
S
i
mal
u
n
g
u
n
27
1
6
0
0
1
5
0
0
V
e
r
y
good
S
mo
o
t
h
5
.
8
B
o
t
h
B
o
t
h
R
a
m
p
s
3
S
a
mo
si
r
23
1
4
0
0
1
6
0
0
B
o
t
h
M
e
d
i
u
m
6
.
3
V
e
r
y
g
o
o
d
V
e
r
y
g
o
o
d
F
l
a
t
4
T
a
p
a
n
u
l
i
U
t
a
r
a
25
1
2
0
0
1
2
0
0
V
e
r
y
good
M
e
d
i
u
m
5
.
8
V
e
r
y
g
o
o
d
V
e
r
y
g
o
o
d
I
t
a
l
i
c
s
5
S
i
b
o
l
g
a
26
1
4
0
0
2
0
0
V
e
r
y
good
M
e
d
i
u
m
6
.
4
V
e
r
y
g
o
o
d
V
e
r
y
g
o
o
d
I
t
a
l
i
c
s
…
….
…
…
…
…
…
…
…
…
Fig
u
r
e
4
s
h
o
w
s
a
v
is
u
aliza
tio
n
o
f
t
h
e
la
n
d
s
u
itab
il
it
y
m
ap
p
er
r
eg
io
n
.
T
o
d
is
p
la
y
t
h
e
m
ap
,
a
s
h
ap
e
f
ile
co
n
tain
i
n
g
t
h
e
latit
u
d
e
a
n
d
l
o
n
g
it
u
d
e
o
f
ea
c
h
b
o
u
n
d
ar
y
l
in
e
o
n
th
e
m
ap
w
a
s
u
s
ed
,
t
h
en
p
lo
tted
u
s
i
n
g
m
atp
lo
tlib
.
T
h
e
d
is
tr
ict
co
lo
r
s
an
d
n
u
m
b
er
s
co
r
r
esp
o
n
d
to
t
h
e
r
eg
io
n
al
d
ataset
th
a
t
h
as
b
ee
n
p
r
o
ce
s
s
ed
an
d
p
r
ed
icted
b
y
th
e
tr
ain
ed
KNN
m
o
d
el.
T
h
e
im
ag
e
is
a
v
is
u
al
izatio
n
o
f
th
e
r
esu
lt
s
o
f
d
im
e
n
s
io
n
alit
y
r
ed
u
c
tio
n
u
s
i
n
g
P
C
A
,
w
h
ich
p
r
o
j
ec
ts
th
e
d
ata
in
to
t
w
o
m
a
in
co
m
p
o
n
e
n
ts
:
P
C
A
c
o
m
p
o
n
e
n
t
1
o
n
t
h
e
h
o
r
izo
n
tal
a
x
is
a
n
d
P
C
A
co
m
p
o
n
e
n
t
2
o
n
th
e
v
er
t
ical
ax
i
s
.
T
h
e
co
lo
r
ed
d
o
ts
r
ep
r
esen
t
t
h
e
tr
ai
n
i
n
g
d
ata
u
s
ed
to
tr
ain
th
e
m
o
d
el,
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
Op
timiz
a
tio
n
o
f p
r
in
cip
a
l c
o
m
p
o
n
en
t
a
n
a
lysi
s
a
n
d
k
-
n
ea
r
est
n
ei
g
h
b
o
r
s
in
…
(
A
r
if R
id
h
o
Lu
b
is
)
1585
w
it
h
d
if
f
er
e
n
t
co
lo
r
s
in
d
icatin
g
d
if
f
er
en
t
clas
s
es
o
r
lab
els.
Me
an
w
h
ile,
th
e
cr
o
s
s
(
X)
in
d
icate
s
th
e
test
d
ata,
w
h
er
e
t
he
r
ed
X
r
ep
r
esen
ts
th
e
m
o
d
el
’
s
p
r
ed
ictio
n
r
esu
lts
,
w
h
ile
th
e
o
th
er
co
lo
r
ed
Xs
r
e
p
r
esen
t
th
e
o
r
ig
in
a
l
lab
els
o
f
th
e
test
d
ata.
Fro
m
t
h
e
d
is
tr
ib
u
tio
n
o
f
t
h
e
p
o
in
ts
,
it
ca
n
b
e
s
ee
n
th
at
d
ata
w
ith
s
i
m
ilar
co
lo
r
s
ten
d
to
g
r
o
u
p
(
f
o
r
m
clu
s
ter
s
)
,
in
d
icati
n
g
s
i
m
il
ar
ch
ar
ac
ter
is
tic
s
b
etw
ee
n
d
ata
w
it
h
i
n
th
e
s
a
m
e
cl
ass
.
Mo
s
t
o
f
th
e
r
ed
Xs
ar
e
clo
s
e
t
o
a
s
p
ec
if
ic
co
lo
r
clu
s
ter
,
in
d
icatin
g
th
at
th
e
m
o
d
el
is
a
b
le
to
p
r
e
d
ict
f
air
ly
well.
Ho
w
ev
er
,
th
er
e
ar
e
also
r
ed
Xs th
at
ar
e
f
ar
f
r
o
m
t
h
e
ap
p
r
o
p
r
iate
clu
s
ter
,
in
d
i
ca
tin
g
a
p
r
ed
ictio
n
er
r
o
r
.
Vis
u
aliza
tio
n
s
lik
e
th
e
s
e
ar
e
u
s
ef
u
l
f
o
r
u
n
d
er
s
ta
n
d
in
g
t
h
e
f
i
t
o
f
th
e
te
s
t
d
ata
d
is
tr
ib
u
t
io
n
to
th
e
tr
ain
i
n
g
d
ata
an
d
f
o
r
id
en
tify
i
n
g
ar
ea
s
w
h
er
e
th
e
m
o
d
el
p
er
f
o
r
m
s
o
p
ti
m
all
y
an
d
ar
ea
s
t
h
at
ar
e
p
r
o
n
e
to
er
r
o
r
s
.
Fig
u
r
e
4
.
Sp
atial
im
p
le
m
en
ta
ti
o
n
r
esu
lt
s
w
it
h
tr
ain
ed
d
ata
3.
2
.
T
esting
r
esu
lt
s
Af
ter
th
e
d
ata
tr
ain
in
g
p
r
o
ce
s
s
is
ca
r
r
ied
o
u
t
u
s
i
n
g
a
p
r
ed
eter
m
in
ed
m
eth
o
d
,
th
e
n
ex
t
s
tag
e
is
to
test
ea
ch
m
o
d
el.
T
h
is
test
ai
m
s
to
ev
alu
a
te
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
m
o
d
el
in
class
i
f
y
in
g
an
d
d
et
er
m
i
n
in
g
p
o
ten
tial
ar
ea
s
f
o
r
s
h
allo
t
cu
ltiv
a
tio
n
ac
cu
r
atel
y
.
T
h
e
r
esu
lts
o
f
th
is
s
ta
g
e
w
ill
b
e
th
e
b
asis
f
o
r
ass
ess
in
g
th
e
ef
f
ec
tiv
e
n
e
s
s
o
f
t
h
e
ap
p
r
o
ac
h
u
s
ed
in
t
h
i
s
r
esear
ch
.
T
h
e
f
o
ll
o
w
i
n
g
i
s
th
e
r
es
u
lt
d
ata
af
ter
th
e
tr
ain
i
n
g
is
s
h
o
w
n
in
T
ab
le
4
.
T
ab
le
4.
R
esu
lts
o
f
s
p
atial
tes
t
in
g
o
f
r
eg
io
n
a
l d
ata
Id
R
e
g
i
o
n
a
l
T
e
mp
e
r
a
t
u
r
e
R
a
i
n
f
a
l
l
El
e
v
a
t
i
o
n
D
r
a
i
n
a
g
e
S
o
i
l
t
e
x
t
u
r
e
pH
C
a
t
i
o
n
e
x
c
h
a
n
g
e
c
a
p
a
c
i
t
y
B
a
se
sat
u
r
a
t
i
o
n
R
e
l
i
e
f
L
a
b
e
l
1
K
a
r
o
24
1
2
0
0
1
0
0
0
1
.
0
0
.
0
5
.
6
1
.
0
1
.
0
R
a
m
p
s
4
2
S
i
mal
u
n
g
u
n
27
1
6
0
0
1
5
0
0
1
.
0
0
.
0
5.
8
0
.
0
0
.
0
R
a
m
p
s
4
3
S
a
mo
si
r
23
1
4
0
0
1
6
0
0
0
.
0
2
.
0
6
.
3
1
.
0
1
.
0
F
l
a
t
4
4
T
a
p
a
n
u
l
i
U
t
a
r
a
25
1
2
0
0
1
2
0
0
1
.
0
2
.
0
5
.
8
1
.
0
1
.
0
I
t
a
l
i
c
s
4
5
S
i
b
o
l
g
a
26
1
4
0
0
2
0
0
1
.
0
2
.
0
6
.
4
1
.
0
1
.
0
I
t
a
l
i
c
s
0
…
….
…
…
…
…
…
…
…
…
T
h
e
p
r
ed
icted
lab
els
(
0
.
1
2
)
w
i
ll
b
e
d
ec
o
d
ed
in
to
ca
teg
o
r
ies
(
g
o
o
d
an
d
b
ad
)
.
T
h
en
ea
ch
ca
t
eg
o
r
y
w
i
ll
b
e
ass
ig
n
ed
a
co
lo
r
.
Fig
u
r
e
5
s
h
o
w
s
t
h
e
d
is
tr
ib
u
tio
n
o
f
la
n
d
s
u
itab
il
it
y
le
v
el
s
in
No
r
th
Su
m
atr
a
P
r
o
v
in
ce
b
ased
o
n
th
e
ca
teg
o
r
ies
“m
o
d
er
ate,
”
“
g
o
o
d
,
”
an
d
“
v
er
y
g
o
o
d
.
”
Yello
w
r
ep
r
esen
ts
ar
ea
s
w
it
h
m
o
d
er
a
te
lan
d
s
u
itab
il
it
y
,
li
g
h
t
g
r
ee
n
i
n
d
icat
es
g
o
o
d
lan
d
s
u
itab
ilit
y
,
an
d
d
ar
k
g
r
ee
n
i
n
d
icate
s
v
er
y
g
o
o
d
lan
d
s
u
itab
ilit
y
.
E
ac
h
r
eg
io
n
/c
it
y
i
s
n
u
m
b
er
ed
ac
co
r
d
in
g
to
th
e
leg
e
n
d
,
s
u
ch
as
Asa
h
an
,
B
atu
B
ar
a,
Deli
Se
r
d
an
g
,
Ma
n
d
aili
n
g
Nata
l,
an
d
o
th
er
s
.
T
h
is
m
ap
s
h
o
w
s
th
at
ar
ea
s
w
it
h
v
er
y
g
o
o
d
lan
d
s
u
itab
ilit
y
ar
e
s
p
r
ea
d
ac
r
o
s
s
s
ev
er
al
d
is
tr
icts
,
s
u
c
h
as
Ma
n
d
ailin
g
Nata
l,
P
ad
an
g
L
a
w
a
s
,
an
d
p
ar
ts
o
f
No
r
th
L
ab
u
h
a
n
B
atu
.
C
o
n
v
er
s
el
y
,
ar
ea
s
w
it
h
m
o
d
er
ate
s
u
i
tab
ilit
y
ar
e
m
o
r
e
w
id
e
s
p
r
ea
d
in
t
h
e
n
o
r
t
h
er
n
a
n
d
w
ester
n
p
ar
ts
o
f
No
r
th
S
u
m
atr
a.
T
h
is
m
ap
is
u
s
e
f
u
l
f
o
r
la
n
d
u
s
e
p
la
n
n
in
g
,
ag
r
icu
l
tu
r
e,
an
d
r
e
g
io
n
al
d
e
v
elo
p
m
e
n
t,
as
it
ca
n
h
elp
d
eter
m
i
n
e
ar
ea
s
w
it
h
o
p
tim
a
l
p
o
ten
tial
f
o
r
s
p
ec
i
f
ic
ac
tiv
itie
s
b
ased
o
n
t
h
eir
la
n
d
s
u
itab
ilit
y
le
v
els
.
Ne
x
t
ar
e
t
h
e
m
o
d
el
p
er
f
o
r
m
an
ce
r
esu
lt
s
f
o
r
ea
ch
tes
t
w
it
h
th
e
r
e
g
io
n
al
s
p
atial
d
ataset
s
h
o
w
n
i
n
T
a
b
le
5
.
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.
23
,
No
.
6
,
Dec
em
b
er
20
25
:
1
5
7
9
-
1
589
1586
T
ab
le
5
.
Mo
d
el
p
er
f
o
r
m
an
ce
r
esu
lt
s
f
o
r
ea
ch
te
s
t
w
it
h
r
eg
io
n
al
s
p
atial
d
ataset
D
a
t
a
se
t
:
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
o
n
i
o
n
c
u
l
t
i
v
a
t
i
o
n
a
r
e
a
s
A
u
t
h
o
r
s
P
r
e
c
i
si
o
n
R
e
c
a
l
l
F1
-
s
c
o
r
e
S
u
p
p
o
r
t
0
0
.
7
9
0
.
9
2
0
.
8
5
24
1
1
.
0
0
0
.
9
2
0
.
9
6
12
2
0
.
9
3
0
.
8
5
0
.
8
9
33
3
1
.
0
0
1
.
0
0
1
.
0
0
7
4
1
.
0
0
1
.
0
0
1
.
0
0
24
A
c
c
u
r
a
c
y
0
.
9
2
1
0
0
M
a
c
r
o
A
v
g
0
.
9
4
0
.
9
4
0
.
9
4
1
0
0
W
e
i
g
h
t
e
d
A
v
g
0
.
9
3
0
.
9
2
0
.
9
4
1
0
0
Ov
er
all,
t
h
e
m
o
d
el
ac
h
iev
ed
9
2
%
ac
cu
r
ac
y
.
T
h
e
m
ac
r
o
av
er
ag
e
f
o
r
p
r
ec
is
io
n
,
r
ec
all
,
an
d
F1
-
s
co
r
e
w
a
s
0
.
9
4
.
Hig
h
F1
-
s
co
r
e
v
al
u
es
ac
r
o
s
s
al
m
o
s
t
all
clas
s
es
in
d
icate
g
o
o
d
m
o
d
el
p
er
f
o
r
m
an
ce
a
n
d
b
alan
c
e
b
et
w
ee
n
clas
s
es,
al
th
o
u
g
h
t
h
e
r
e
w
a
s
a
s
lig
h
t
d
ec
r
ea
s
e
in
class
es
0
an
d
2
,
li
k
el
y
d
u
e
to
th
e
s
li
g
h
t
l
y
lo
w
er
n
u
m
b
er
o
f
co
r
r
ec
t p
r
ed
ictio
n
s
co
m
p
ar
ed
to
o
th
er
class
e
s
.
Fig
u
r
e
5
.
R
ed
o
n
io
n
lan
d
clas
s
if
icatio
n
r
es
u
lts
B
ased
o
n
th
e
ev
alu
a
tio
n
r
es
u
l
ts
s
h
o
w
n
in
t
h
e
s
h
allo
t
cu
ltiv
atio
n
ar
ea
class
i
f
icatio
n
g
r
ap
h
,
it
ca
n
b
e
s
ee
n
t
h
at
th
e
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
v
al
u
es
in
t
h
e
m
o
d
el
ten
d
to
b
e
at
a
lo
w
an
d
r
elativ
el
y
f
lat
r
an
g
e.
T
h
is
in
d
icate
s
t
h
at
th
e
m
o
d
el
’
s
ab
ilit
y
to
id
en
ti
f
y
ar
ea
s
s
u
ita
b
le
f
o
r
s
h
allo
t
cu
lt
iv
at
io
n
is
s
t
ill
n
o
t
o
p
ti
m
al
.
T
h
e
m
o
d
el
is
n
o
t
y
et
ab
le
to
d
is
tin
g
u
i
s
h
w
ell
b
et
w
ee
n
tr
u
l
y
s
u
ita
b
le
an
d
u
n
s
u
itab
le
ar
ea
s
,
s
o
t
h
e
lev
el
o
f
p
r
ec
is
io
n
an
d
th
e
le
v
el
o
f
s
u
cc
es
s
o
f
t
h
e
m
o
d
el
in
f
i
n
d
in
g
all
tr
u
e
p
o
s
iti
v
e
d
ata
(
r
ec
all)
ar
e
b
o
th
s
ti
ll
lo
w
.
T
h
e
lo
w
F1
-
s
co
r
e
v
al
u
e
i
n
d
icate
s
th
a
t
t
h
e
b
alan
ce
b
et
w
ee
n
p
r
ec
is
io
n
an
d
r
ec
all
h
as
n
o
t
b
ee
n
ac
h
ie
v
ed
,
s
o
th
e
m
o
d
el
i
s
n
o
t
s
tab
le
in
it
s
p
er
f
o
r
m
a
n
ce
s
h
o
w
n
i
n
Fi
g
u
r
e
6
.
B
ased
o
n
th
e
test
r
esu
lts
w
i
th
t
h
e
r
eg
io
n
al
s
p
atial
d
ataset
u
s
i
n
g
p
r
ec
is
io
n
,
r
ec
all
an
d
F
-
s
co
r
e
test
i
n
g
,
t
h
e
ac
cu
r
ac
y
v
al
u
e
i
s
0
.
9
2
%,
an
d
th
e
m
ac
r
o
av
g
v
alu
e
is
0
.
9
4
%,
th
e
w
ei
g
h
ted
av
g
v
al
u
e
is
0
.
9
3
%.
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
Op
timiz
a
tio
n
o
f p
r
in
cip
a
l c
o
m
p
o
n
en
t
a
n
a
lysi
s
a
n
d
k
-
n
ea
r
est
n
ei
g
h
b
o
r
s
in
…
(
A
r
if R
id
h
o
Lu
b
is
)
1587
Fig
u
r
e
6
.
Mo
d
el
ev
alu
atio
n
r
e
s
u
lt
s
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
ai
m
s
to
ad
d
r
ess
t
h
e
p
r
o
b
lem
s
t
h
at
ex
i
s
t
i
n
s
h
allo
t
cu
lti
v
atio
n
,
it
is
n
ec
es
s
ar
y
to
p
ay
atten
tio
n
to
th
e
s
u
itab
ilit
y
an
d
ch
ar
ac
ter
is
tics
o
f
lan
d
i
n
s
h
a
l
lo
t
cu
lti
v
atio
n
.
O
n
io
n
p
lan
tin
g
is
g
en
er
all
y
d
o
n
e
in
th
e
h
i
g
h
la
n
d
s
.
On
e
o
f
th
e
ar
ea
s
w
i
th
s
h
allo
t
c
u
lt
iv
atio
n
in
No
r
th
Su
m
atr
a
P
r
o
v
in
ce
is
B
er
astag
i,
Kar
o
R
eg
e
n
c
y
.
T
h
is
r
e
s
ea
r
ch
w
as
c
o
n
d
u
cted
b
y
d
eter
m
i
n
i
n
g
t
h
e
s
p
atial
ex
te
n
t
o
f
u
p
la
n
d
lan
d
.
I
n
th
e
u
s
e
o
f
d
at
a
th
er
e
ar
e
2
t
y
p
es
o
f
d
ata
th
at
w
il
l
b
e
u
s
ed
:
lan
d
s
u
itab
ili
t
y
d
ataset
an
d
la
n
d
co
n
d
itio
n
d
atas
et
f
o
r
ea
ch
r
eg
io
n
.
E
ac
h
tab
le
is
g
e
n
er
ated
b
y
m
atc
h
in
g
f
ea
tu
r
e
s
w
ith
o
p
ti
m
al
la
n
d
cu
lti
v
atio
n
co
n
d
it
io
n
s
.
Fo
r
ex
a
m
p
le,
a
te
m
p
er
atu
r
e
o
f
2
5
-
32
°C
,
an
d
an
altit
u
d
e
o
f
0
-
4
5
0
m
eter
s
ab
o
v
e
s
ea
lev
el.
T
h
e
co
m
b
in
a
tio
n
o
f
P
C
A
a
n
d
KNN
m
et
h
o
d
s
is
p
r
o
v
en
to
b
e
ab
le
to
in
cr
ea
s
e
ef
f
icie
n
c
y
a
n
d
ac
cu
r
ac
y
i
n
th
e
p
r
o
ce
s
s
o
f
class
i
f
y
in
g
s
h
allo
t
cu
lti
v
atio
n
ar
ea
s
.
T
h
is
r
e
s
ea
r
ch
p
r
o
d
u
ce
s
a
cla
s
s
i
f
icat
io
n
m
ap
th
at
ca
n
b
e
u
s
ed
to
id
e
n
ti
f
y
t
h
e
m
o
s
t
o
p
ti
m
al
ar
ea
s
f
o
r
s
h
allo
t
cu
lti
v
atio
n
.
B
y
id
en
ti
f
y
i
n
g
o
p
t
i
m
al
ar
ea
s
,
th
is
r
esear
c
h
co
n
tr
ib
u
te
s
to
ef
f
o
r
t
s
to
in
cr
ea
s
e
s
h
allo
t
p
r
o
d
u
ctio
n
a
n
d
ac
h
ie
v
e
f
o
o
d
s
elf
-
s
u
f
f
ic
ien
c
y
.
Fro
m
th
e
r
esear
ch
r
es
u
lt
s
it
ca
n
b
e
s
ee
n
,
w
h
er
e
s
p
atial
lo
ca
tio
n
s
t
h
at
h
a
v
e
d
ar
k
g
r
ee
n
co
lo
r
co
d
es
ar
e
v
er
y
g
o
o
d
ar
ea
s
f
o
r
s
h
al
lo
t
cu
l
tiv
a
tio
n
b
as
ed
o
n
m
o
d
eli
n
g
an
d
s
p
ec
if
ied
v
ar
iab
les
.
T
h
e
r
esu
l
ts
o
f
test
in
g
w
it
h
r
eg
io
n
al
s
p
atial
d
atasets
u
s
i
n
g
p
r
ec
is
io
n
,
r
ec
all
an
d
f
i
-
s
co
r
e
test
i
n
g
ac
c
u
r
ac
y
v
alu
e
0
.
9
2
%,
an
d
m
ac
r
o
av
g
v
al
u
e
0
.
9
4
%,
w
ei
g
h
ted
av
g
v
al
u
e
0
.
9
3
%.
ACK
NO
WL
E
D
G
M
E
NT
S
T
h
e
au
th
o
r
s
ex
p
r
ess
t
h
eir
ap
p
r
ec
iatio
n
f
o
r
th
e
f
u
n
d
i
n
g
s
u
p
p
o
r
t
p
r
o
v
id
ed
th
r
o
u
g
h
DI
P
A
f
u
n
d
s
o
f
P
o
litek
n
i
k
Neg
er
i M
ed
an
f
o
r
th
e
f
i
s
ca
l
y
ea
r
2
0
2
4
.
F
UNDIN
G
I
NF
O
RM
AT
I
O
N
T
h
e
au
th
o
r
s
ex
p
r
ess
t
h
eir
ap
p
r
ec
iatio
n
f
o
r
th
e
f
u
n
d
i
n
g
s
u
p
p
o
r
t
p
r
o
v
id
ed
th
r
o
u
g
h
DI
P
A
f
u
n
d
s
o
f
P
o
litek
n
i
k
Neg
e
r
i
Me
d
an
f
o
r
th
e
f
is
ca
l
y
ea
r
2
0
2
4
,
in
ac
co
r
d
an
ce
w
it
h
th
e
co
n
tr
ac
t
n
u
m
b
er
:
B
/4
2
5
/
P
L
5
/PT
.
0
1
.
0
5
/
2
0
2
4
,
A
lo
n
g
w
i
th
al
l
tea
m
m
e
m
b
er
s
w
h
o
p
la
y
a
r
o
le
i
n
t
h
e
i
m
p
le
m
e
n
tat
io
n
o
f
co
llab
o
r
ativ
e
r
esear
ch
th
r
o
u
g
h
th
is
P
T
PI
s
ch
e
m
e.
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
a
tio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
A
r
i
f
R
id
h
o
L
u
b
is
✓
✓
✓
✓
✓
✓
✓
P
u
r
w
a
Has
a
n
P
u
tr
a
✓
✓
✓
✓
Fah
d
i Said
i
L
u
b
i
s
✓
✓
✓
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
0
20
40
60
80
1
0
0
1
2
0
1
2
3
4
5
6
7
8
9
A
c
c
ur
ac
y
D
at
as
e
t
A
ut
ho
r
s
Cla
s
s
ifi
ca
t
io
n o
f
r
ed
On
io
n Cul
t
ivat
io
n Are
as
A
u
t
h
o
r
s
Pr
e
c
i
s
i
o
n
R
ec
a
l
l
F
1
-
S
c
o
r
e
S
u
p
p
o
r
t
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.
23
,
No
.
6
,
Dec
em
b
er
20
25
:
1
5
7
9
-
1
589
1588
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
d
ec
lar
es n
o
co
n
f
l
ic
t o
f
in
ter
es
t
.
I
NF
O
RM
E
D
CO
NSE
N
T
W
e
h
av
e
o
b
tain
ed
in
f
o
r
m
ed
c
o
n
s
en
t f
r
o
m
al
l in
d
i
v
i
d
u
al
s
in
c
lu
d
ed
in
th
is
s
t
u
d
y
.
E
T
H
I
CAL AP
P
RO
V
AL
R
esear
ch
r
elate
d
to
h
u
m
an
u
s
e
h
as
co
m
p
lied
w
it
h
all
r
elev
an
t
n
atio
n
al
r
eg
u
latio
n
s
a
n
d
i
n
s
ti
tu
t
io
n
al
p
o
licies
in
ac
co
r
d
an
ce
w
i
th
t
h
e
p
r
in
cip
les
o
f
t
h
e
Dec
lar
at
io
n
o
f
Helsi
n
k
i
an
d
h
as
b
ee
n
ap
p
r
o
v
ed
b
y
th
e
au
t
h
o
r
s
’
i
n
s
ti
tu
t
io
n
al
r
ev
ie
w
b
o
ar
d
o
r
eq
u
iv
alen
t c
o
m
m
i
ttee.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t t
h
e
f
i
n
d
i
n
g
s
o
f
t
h
i
s
s
t
u
d
y
ar
e
a
v
ailab
le
o
n
r
eq
u
est
f
r
o
m
t
h
e
co
r
r
esp
o
n
d
in
g
a
u
t
h
o
r
,
[
A
r
i
f
R
id
h
o
L
u
b
i
s
]
.
T
h
e
d
ata
,
w
h
ich
co
n
tain
i
n
f
o
r
m
atio
n
th
at
co
u
ld
co
m
p
r
o
m
i
s
e
th
e
p
r
iv
ac
y
o
f
r
esear
c
h
p
ar
ticip
an
ts
,
ar
e
n
o
t p
u
b
licl
y
a
v
ailab
le
d
u
e
to
ce
r
tain
r
estrict
i
o
n
s
.
RE
F
E
R
E
NC
E
S
[
1
]
N
.
A
.
B
a
sal
l
o
t
e
e
t
a
l
.
,
“
I
o
T
-
b
a
se
d
g
r
o
w
t
h
a
n
a
l
y
si
s
o
f
r
e
d
o
n
i
o
n
i
n
c
o
n
t
r
o
l
l
e
d
h
y
d
r
o
p
o
n
i
c
e
n
v
i
r
o
n
me
n
t
u
s
i
n
g
e
l
e
c
t
r
o
c
u
l
t
u
r
e
,
”
i
n
I
EEE
Re
g
i
o
n
1
0
An
n
u
a
l
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
,
Pro
c
e
e
d
i
n
g
s
/
T
EN
C
O
N
,
I
EEE,
N
o
v
.
2
0
2
2
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
T
EN
C
O
N
5
5
6
9
1
.
2
0
2
2
.
9
9
7
7
6
1
4
.
[
2
]
M
.
Y
.
P
u
c
h
k
o
v
,
M
.
M
.
S
h
a
g
a
p
o
v
,
a
n
d
K
.
K
.
Esh
a
j
i
e
v
a
,
“
T
e
c
h
n
o
l
o
g
i
e
s
o
f
c
u
l
t
i
v
a
t
i
o
n
o
f
r
e
d
o
n
i
o
n
v
a
r
i
e
t
i
e
s,”
BI
O
We
b
o
f
C
o
n
f
e
re
n
c
e
s
,
v
o
l
.
7
1
,
p
.
1
0
0
6
,
N
o
v
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
5
1
/
b
i
o
c
o
n
f
/
2
0
2
3
7
1
0
1
0
0
6
.
[
3
]
M
.
D
u
t
t
a
,
D
.
G
u
p
t
a
,
S
.
J
u
n
e
j
a
,
A
.
N
a
u
ma
n
,
a
n
d
G
.
M
u
h
a
mm
a
d
,
“
C
o
m
p
a
r
a
t
i
v
e
g
r
o
w
t
h
a
n
a
l
y
si
s
o
f
o
n
i
o
n
i
n
d
e
e
p
w
a
t
e
r
c
u
l
t
u
r
e
a
n
d
so
i
l
b
a
se
d
sy
st
e
ms:
En
h
a
n
c
i
n
g
me
d
i
c
i
n
a
l
p
l
a
n
t
c
u
l
t
i
v
a
t
i
o
n
i
n
U
r
b
a
n
i
z
e
d
e
n
v
i
r
o
n
me
n
t
s
,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
3
8
2
0
2
–
3
8
2
1
8
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
4
.
3
3
7
3
7
8
7
.
[
4
]
M
.
M
.
H
a
sa
n
,
M
.
T
.
Z
a
h
a
r
a
,
M
.
M
.
S
y
k
o
t
,
R
.
H
a
f
i
z
,
a
n
d
M
.
S
a
i
f
u
z
z
a
man
,
“
S
o
l
v
i
n
g
o
n
i
o
n
mark
e
t
i
n
st
a
b
i
l
i
t
y
b
y
f
o
r
e
c
a
st
i
n
g
o
n
i
o
n
p
r
i
c
e
u
s
i
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
2
0
2
0
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
a
t
i
o
n
a
l
P
e
rf
o
rm
a
n
c
e
E
v
a
l
u
a
t
i
o
n
,
C
o
m
PE
2
0
2
0
,
p
p
.
7
7
7
–
7
8
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
C
o
mP
E4
9
3
2
5
.
2
0
2
0
.
9
2
0
0
0
3
3
.
[
5
]
J.
C
h
o
i
e
t
a
l
.
,
“
G
e
n
o
t
y
p
e
-
d
r
i
v
e
n
p
h
e
n
o
t
y
p
e
p
r
e
d
i
c
t
i
o
n
i
n
o
n
i
o
n
b
r
e
e
d
i
n
g
:
mac
h
i
n
e
l
e
a
r
n
i
n
g
mo
d
e
l
s
f
o
r
e
n
h
a
n
c
e
d
b
u
l
b
w
e
i
g
h
t
se
l
e
c
t
i
o
n
,
”
A
g
r
i
c
u
l
t
u
r
e
(
S
w
i
t
ze
rl
a
n
d
)
,
v
o
l
.
1
4
,
n
o
.
1
2
,
p
.
2
2
3
9
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
a
g
r
i
c
u
l
t
u
r
e
1
4
1
2
2
2
3
9
.
[
6
]
A
.
A
.
W
a
o
o
a
n
d
M
.
T
i
w
a
r
i
,
“
O
p
t
i
m
i
z
i
n
g
c
r
o
p
y
i
e
l
d
a
n
d
f
e
r
t
i
l
i
t
y
man
a
g
e
me
n
t
u
si
n
g
K
N
N
a
n
d
M
l
,
”
S
h
o
d
h
K
o
s
h
:
J
o
u
rn
a
l
o
f
Vi
s
u
a
l
a
n
d
Pe
r
f
o
rm
i
n
g
Art
s
,
v
o
l
.
5
,
n
o
.
5
,
p
p
.
3
8
0
–
3
8
5
,
M
a
y
2
0
2
4
,
d
o
i
:
1
0
.
2
9
1
2
1
/
s
h
o
d
h
k
o
s
h
.
v
5
.
i
5
.
2
0
2
4
.
1
8
8
8
.
[
7
]
S
.
L
.
B
a
i
r
w
a
e
t
a
l
.
,
“
Ec
o
n
o
mi
c
a
n
a
l
y
si
s
o
f
O
n
i
o
n
p
r
o
d
u
c
t
i
o
n
i
n
B
i
h
a
r
:
I
n
si
g
h
t
i
n
t
o
c
o
s
t
o
f
c
u
l
t
i
v
a
t
i
o
n
,
p
o
st
-
h
a
r
v
e
st
ma
n
a
g
e
me
n
t
a
n
d
c
o
n
s
t
r
a
i
n
t
i
d
e
n
t
i
f
i
c
a
t
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ag
ri
c
u
l
t
u
ra
l
I
n
v
e
n
t
i
o
n
,
v
o
l
.
9
,
n
o
.
1
,
p
p
.
2
7
3
–
2
7
7
,
J
u
n
.
2
0
2
4
,
d
o
i
:
1
0
.
4
6
4
9
2
/
i
j
a
i
/
2
0
2
4
.
9
.
1
.
3
4
.
[
8
]
N
.
T
z
i
o
l
a
s,
S
.
A
.
O
r
d
o
u
d
i
,
A
.
T
a
v
l
a
r
i
d
i
s
,
K
.
K
a
r
y
o
t
i
s,
G
.
Z
a
l
i
d
i
s,
a
n
d
I
.
M
o
u
r
t
z
i
n
o
s
,
“
R
a
p
i
d
a
sse
ssm
e
n
t
o
f
a
n
t
h
o
c
y
a
n
i
n
s
c
o
n
t
e
n
t
o
f
o
n
i
o
n
w
a
st
e
t
h
r
o
u
g
h
v
i
s
i
b
l
e
‐
n
e
a
r
‐
sh
o
r
t
‐
w
a
v
e
a
n
d
mi
d
‐
i
n
f
r
a
r
e
d
s
p
e
c
t
r
o
s
c
o
p
y
c
o
mb
i
n
e
d
w
i
t
h
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
u
s
t
a
i
n
a
b
i
l
i
t
y
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
1
3
,
n
o
.
1
2
,
p
.
6
5
8
8
,
Ju
n
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
s
u
1
3
1
2
6
5
8
8
.
[
9
]
I
.
L
u
t
h
f
i
f
a
h
,
E.
H
e
r
n
a
w
a
t
i
,
H
.
N
u
g
r
o
h
o
,
B
.
R
.
A
d
i
t
y
a
,
a
n
d
P
.
A
j
i
,
“
I
mp
l
e
men
t
a
t
i
o
n
o
f
K
-
n
e
a
r
e
st
n
e
i
g
h
b
o
r
s a
l
g
o
r
i
t
h
m
f
o
r
r
e
d
o
n
i
o
n
c
r
o
p
su
i
t
a
b
i
l
i
t
y
l
a
n
d
a
sse
ss
me
n
t
i
n
S
e
l
a
a
w
i
,
I
n
d
o
n
e
si
a
,
”
I
n
g
e
n
i
e
ri
e
d
e
s
S
y
st
e
m
e
s
d
’
I
n
f
o
rm
a
t
i
o
n
,
v
o
l
.
3
0
,
n
o
.
2
,
p
p
.
3
0
1
–
3
0
6
,
F
e
b
.
2
0
2
5
,
d
o
i
:
1
0
.
1
8
2
8
0
/
i
si
.
3
0
0
2
0
1
.
[
1
0
]
X
.
C
h
e
n
g
,
M
.
L
i
a
o
,
a
n
d
J.
L
i
u
,
“
G
e
o
g
r
a
p
h
i
c
a
l
o
r
i
g
i
n
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
p
a
n
a
x
n
o
t
o
g
i
n
se
n
g
u
si
n
g
a
mo
d
i
f
i
e
d
K
-
n
e
a
r
e
st
n
e
i
g
h
b
o
r
s
mo
d
e
l
w
i
t
h
n
e
a
r
-
i
n
f
r
a
r
e
d
s
p
e
c
t
r
o
s
c
o
p
y
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
3
,
p
p
.
1
3
8
3
2
–
1
3
8
4
6
,
2
0
2
5
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
5
.
3
5
3
0
7
6
6
.
[
1
1
]
D
.
N
.
T
.
R
o
n
q
u
i
l
l
o
,
J.
M
.
S
.
S
e
l
d
a
,
a
n
d
M
.
V
.
C
.
C
a
y
a
,
“
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
o
n
i
o
n
s
p
e
c
i
e
s
i
n
t
h
e
p
h
i
l
i
p
p
i
n
e
s
u
s
i
n
g
a
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
(
C
N
N
)
,
”
i
n
2
0
2
3
I
E
E
E
1
5
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
H
u
m
a
n
o
i
d
,
N
a
n
o
t
e
c
h
n
o
l
o
g
y
,
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
C
o
n
t
r
o
l
,
E
n
v
i
r
o
n
m
e
n
t
,
a
n
d
M
a
n
a
g
e
m
e
n
t
,
H
N
I
C
EM
2
0
2
3
,
I
EEE,
N
o
v
.
2
0
2
3
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
H
N
I
C
EM
6
0
6
7
4
.
2
0
2
3
.
1
0
5
8
9
1
2
1
.
[
1
2
]
M
.
A
.
H
a
s
a
n
,
“
C
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
a
p
p
l
e
t
y
p
e
s
u
si
n
g
p
r
i
n
c
i
p
a
l
c
o
mp
o
n
e
n
t
a
n
a
l
y
si
s
a
n
d
K
-
n
e
a
r
e
st
n
e
i
g
h
b
o
r
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
S
y
st
e
m
T
e
c
h
n
o
l
o
g
y
a
n
d
D
a
t
a
S
c
i
e
n
c
e
,
v
o
l
.
1
,
n
o
.
1
,
p
p
.
1
5
–
2
2
,
Ju
n
.
2
0
2
3
,
d
o
i
:
1
0
.
6
1
3
9
8
/
i
j
i
s
t
-
d
a
s.v
1
i
1
.
1
1
.
[
1
3
]
A
.
H
.
L
u
b
i
s,
P
.
S
i
h
o
m
b
i
n
g
,
a
n
d
E
.
B
.
N
a
b
a
b
a
n
,
“
A
n
a
l
y
si
s
o
f
a
c
c
u
r
a
c
y
i
mp
r
o
v
e
me
n
t
i
n
K
-
N
e
a
r
e
st
n
e
i
g
h
b
o
r
u
s
i
n
g
p
r
i
n
c
i
p
a
l
c
o
mp
o
n
e
n
t
a
n
a
l
y
si
s
(
P
C
A
)
,
”
J
o
u
r
n
a
l
o
f
P
h
y
s
i
c
s:
C
o
n
f
e
re
n
c
e
S
e
ri
e
s
,
v
o
l
.
1
5
6
6
,
n
o
.
1
,
p
.
1
2
0
6
2
,
J
u
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
2
-
6
5
9
6
/
1
5
6
6
/
1
/
0
1
2
0
6
2
.
[
1
4
]
A
.
A
.
A
b
u
-
S
h
a
r
e
h
a
,
H
.
Q
u
t
a
i
s
h
a
t
,
a
n
d
A
.
A
l
-
Kh
a
y
a
t
,
“
A
f
r
a
mew
o
r
k
f
o
r
d
i
a
b
e
t
e
s
d
e
t
e
c
t
i
o
n
u
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
a
t
a
p
r
e
p
r
o
c
e
ssi
n
g
,
”
J
o
u
rn
a
l
o
f
A
p
p
l
i
e
d
D
a
t
a
S
c
i
e
n
c
e
s
,
v
o
l
.
5
,
n
o
.
4
,
p
p
.
1
6
5
4
–
1
6
6
7
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
4
7
7
3
8
/
j
a
d
s.v
5
i
4
.
3
6
3
.
[
1
5
]
A
.
B
r
i
j
i
t
h
,
“
D
a
t
a
p
r
e
p
r
o
c
e
ssi
n
g
f
o
r
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
CS
IM
,
v
o
l
.
3
,
2
0
2
3
.
[
1
6
]
R
.
H
.
M
a
h
a
r
r
a
n
i
,
P
.
D
.
A
b
d
a
’
u
,
a
n
d
M
.
N
.
F
a
i
z
,
“
C
l
u
st
e
r
i
n
g
me
t
h
o
d
f
o
r
c
r
i
mi
n
a
l
c
r
i
me
a
c
t
s
u
si
n
g
K
-
me
a
n
s
a
n
d
p
r
i
n
c
i
p
a
l
c
o
mp
o
n
e
n
t
a
n
a
l
y
si
s,”
I
n
d
o
n
e
s
i
a
n
J
o
u
rn
a
l
o
f
E
l
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
3
4
,
n
o
.
1
,
p
p
.
2
2
4
–
2
3
2
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.v
3
4
.
i
1
.
p
p
2
2
4
-
2
3
2
.
[
1
7
]
D
.
S
e
l
v
i
d
a
,
A
.
F
.
P
u
l
u
n
g
a
n
,
a
n
d
A
.
S
.
H
u
z
a
i
f
a
h
,
“
O
p
t
i
m
i
z
a
t
i
o
n
o
f
g
a
r
l
i
c
c
u
l
t
i
v
a
t
i
o
n
l
a
n
d
se
l
e
c
t
i
o
n
u
s
i
n
g
P
C
A
a
n
d
K
-
me
a
n
s
a
p
p
r
o
a
c
h
i
n
s
p
a
t
i
a
l
i
n
t
e
l
l
i
g
e
n
t
sy
st
e
m,”
Ea
s
t
e
r
n
-
E
u
ro
p
e
a
n
J
o
u
rn
a
l
o
f
E
n
t
e
r
p
ri
s
e
T
e
c
h
n
o
l
o
g
i
e
s
,
v
o
l
.
3
,
n
o
.
2
(
1
3
5
)
,
p
p
.
5
4
–
6
4
,
Ju
n
e
2
0
2
5
,
d
o
i
:
1
0
.
1
5
5
8
7
/
1
7
2
9
-
4
0
6
1
.
2
0
2
5
.
3
2
5
3
4
0
.
[
1
8
]
M
.
M
.
A
r
c
i
n
a
s
e
t
a
l
.
,
“
A
n
e
f
f
i
c
i
e
n
t
c
o
u
r
se
r
e
c
o
mm
e
n
d
a
t
i
o
n
sy
st
e
m
f
o
r
h
i
g
h
e
r
e
d
u
c
a
t
i
o
n
st
u
d
e
n
t
s
u
s
i
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,
”
B
u
l
l
e
t
i
n
o
f
El
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
ri
n
g
a
n
d
I
n
f
o
rm
a
t
i
c
s
(
BE
EI
)
,
v
o
l
.
1
4
,
n
o
.
2
,
p
p
.
1
4
6
8
–
1
4
7
5
,
A
p
r
.
2
0
2
5
,
d
o
i
:
1
0
.
1
1
5
9
1
/
e
e
i
.
v
1
4
i
2
.
7
7
1
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.