I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
p
u
t
er
Science
Vo
l.
1
2
,
No
.
1
,
Octo
b
er
201
8
,
p
p
.
1
0
2
~
1
0
6
I
SS
N:
2502
-
4752
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ee
cs
.
v
1
2
.i
1
.
p
p
102
-
1
0
6
102
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e.
co
m/jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
ijeec
s
M
a
chine Lea
rnin
g
w
ith
PySpa
r
k
-
Rev
iew
Ra
s
w
it
ha
B
a
nd
i
1
,
J
A
m
ud
ha
v
el
2
,
R
K
a
rt
hik
3
1
De
p
a
rtme
n
t
o
f
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
M
L
R
In
stit
u
te o
f
T
e
c
h
n
o
lo
g
y
,
H
y
d
e
ra
b
a
d
,
In
d
ia
3
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
,
KL
Un
iv
e
rsit
y
,
G
u
n
tu
r,
In
d
ia
1
,2
M
L
R
In
stit
u
te o
f
T
e
c
h
n
o
lo
g
y
,
H
y
d
e
ra
b
a
d
,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
1
0
,
2
0
1
8
R
ev
i
s
ed
A
p
r
2
1
,
2
0
1
8
A
cc
ep
ted
Ju
n
1
8
,
2
0
1
8
A
r
e
a
so
n
a
b
le
d
istri
b
u
ted
m
e
m
o
ry
-
b
a
s
e
d
Co
m
p
u
ti
n
g
s
y
ste
m
f
o
r
m
a
c
h
in
e
lea
rn
in
g
is
A
p
a
c
h
e
S
p
a
rk
.
S
p
a
rk
is
b
e
in
g
su
p
e
rio
r
in
c
o
m
p
u
ti
n
g
w
h
e
n
c
o
m
p
a
re
d
w
it
h
Ha
d
o
o
p
.
A
p
a
c
h
e
S
p
a
rk
is
a
q
u
ick
,
si
m
p
le
to
u
se
f
o
r
h
a
n
d
li
n
g
b
ig
d
a
ta
th
a
t
h
a
s
w
o
rk
e
d
in
m
o
d
u
les
o
f
M
a
c
h
in
e
L
e
a
rn
in
g
,
stre
a
m
in
g
S
QL,
a
n
d
g
ra
p
h
p
r
o
c
e
ss
in
g
.
W
e
c
a
n
a
p
p
ly
m
a
c
h
in
e
lea
rn
in
g
a
lg
o
rit
h
m
s
to
b
ig
d
a
ta
e
a
sil
y
,
w
h
ich
m
a
k
e
s it
si
m
p
le b
y
u
sin
g
S
p
a
rk
a
n
d
it
s m
a
c
h
in
e
lea
rn
in
g
li
b
ra
ry
M
L
li
b
,
e
v
e
n
th
is
c
a
n
b
e
m
a
d
e
s
im
p
ler
b
y
u
sin
g
th
e
P
y
th
o
n
A
P
I
P
y
S
p
a
rk
.
T
h
is
p
a
p
e
r
p
re
se
n
ts
th
e
stu
d
y
o
n
h
o
w
to
d
e
v
e
lo
p
m
a
c
h
in
e
lea
rn
in
g
a
lg
o
rit
h
m
s
in
P
y
S
p
a
rk
.
K
ey
w
o
r
d
s
:
A
p
ac
h
e
s
p
ar
k
Ma
ch
i
n
e
L
ea
r
n
i
n
g
P
y
Sp
ar
k
SC
AL
A
Co
p
y
rig
h
t
©
2
0
1
8
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
R
as
w
i
th
a
B
an
d
i
,
KL
U
n
i
v
er
s
it
y
,
I
n
d
ia
.
E
m
ail:
r
as
w
i
th
a.
2
9
r
ed
d
y
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
v
o
lu
m
e
o
f
i
n
f
o
r
m
atio
n
g
ath
er
ed
h
as
b
ein
g
p
u
t
a
w
a
y
,
w
h
at
’
s
m
o
r
e,
b
r
o
k
e
d
o
w
n
h
as
d
eto
n
ated
,
s
p
ec
if
icall
y
i
n
co
n
n
ec
t
io
n
to
th
e
ac
tio
n
o
n
t
h
e
W
eb
an
d
c
ell
p
h
o
n
es,
an
d
in
ad
d
itio
n
i
n
f
o
r
m
atio
n
f
r
o
m
t
h
e
p
h
y
s
ical
w
o
r
ld
g
at
h
er
ed
th
r
o
u
g
h
s
e
n
s
o
r
s
y
s
te
m
s
.
At
th
e
p
o
in
t
w
h
e
n
lo
o
k
ed
w
ith
t
h
i
s
a
m
o
u
n
t
o
f
in
f
o
r
m
atio
n
r
ap
id
ly
w
in
d
u
p
n
o
ticea
b
l
y
i
n
f
ea
s
ib
le
[
1
]
.
T
h
is
h
a
s
p
r
o
m
p
t
ed
an
a
s
ce
n
t
w
h
ich
is
ca
lled
as
h
u
g
e
i
n
f
o
r
m
atio
n
an
d
m
ac
h
in
e
lear
n
i
n
g
f
r
a
m
e
wo
r
k
s
.
I
n
th
e
er
a
o
f
o
p
en
s
o
u
r
ce
ad
v
an
ce
s
w
h
ich
ca
n
b
e
u
s
ed
to
d
ea
l
w
it
h
en
o
r
m
o
u
s
d
ata.
T
h
e
m
o
s
t
o
f
th
e
s
e
in
n
o
v
atio
n
s
i
s
A
p
ac
h
e
Had
o
o
p
(
b
y
m
ea
n
s
o
f
Had
o
o
p
Ma
p
R
ed
u
ce
,
a
s
tr
u
ctu
r
e
to
p
e
r
f
o
r
m
ca
lc
u
latio
n
in
p
ar
allel
cr
o
s
s
w
i
s
e
o
v
er
n
u
m
er
o
u
s
n
o
d
es).
E
v
en
t
h
o
u
g
h
,
Ma
p
R
ed
u
ce
h
as
s
o
m
e
i
m
p
er
ati
v
e
w
ea
k
n
e
s
s
es,
co
u
n
tin
g
n
u
m
b
er
o
f
o
v
er
h
ea
d
s
to
d
is
p
atch
ea
c
h
ac
t
iv
i
t
y
an
d
a
s
s
u
r
a
n
ce
o
f
s
to
r
i
n
g
d
ata
a
n
d
i
n
ter
m
ed
iate
r
es
u
lts
,
b
o
th
o
f
w
h
ic
h
m
a
k
e
Had
o
o
p
m
o
d
er
atel
y
u
n
s
u
itab
le
o
r
u
tili
ze
in
s
ta
n
ce
s
o
f
a
n
iter
ativ
e
a
n
d
lo
w
-
i
n
er
tn
e
s
s
n
at
u
r
e.
A
p
ac
h
e
Sp
ar
k
is
an
o
th
er
s
tr
u
ct
u
r
e
w
h
ich
i
s
ap
p
r
o
p
r
iate
d
f
ig
u
r
in
g
t
h
at
i
s
in
ten
d
ed
to
b
e
u
p
g
r
ad
ed
f
o
r
lo
w
-
in
er
t
n
es
s
er
r
an
d
s
,
f
o
r
s
to
r
in
g
in
ter
m
ed
iate
d
ata
r
esu
lts
i
n
m
e
m
o
r
y
.
I
t
is
a
ap
p
r
o
p
r
iate
f
o
r
an
ap
p
licatio
n
w
h
ic
h
is
it
er
ativ
e
an
d
m
ac
h
i
n
e
lear
n
in
g
.
P
y
t
h
o
n
is
a
u
s
ed
f
o
r
h
i
g
h
le
v
el
p
r
o
g
r
a
m
m
in
g
lan
g
u
ag
e
f
o
r
g
e
n
er
a
l
p
u
r
p
o
s
e
p
r
o
g
r
a
m
m
i
n
g
.
I
n
t
h
ese
d
ay
s
P
y
th
o
n
b
ec
o
m
es
m
o
s
t
p
o
p
u
lar
lan
g
u
ag
e
f
o
r
d
ata
s
cien
tis
ts
.
Fo
r
a
d
ata
s
cien
tis
t
it
is
d
if
f
ic
u
lt
to
d
ev
elo
p
ML
al
g
o
r
ith
m
s
w
i
th
p
y
th
o
n
with
o
u
t i
n
cl
u
d
in
g
S
C
AL
A
la
n
g
u
ag
e
[
1
-
2
]
.
I
n
th
i
s
p
ap
er
,
th
e
f
ir
s
t
s
ec
tio
n
d
escr
ib
es
ab
o
u
t
s
p
ar
k
co
r
e
tech
n
o
lo
g
ies
an
d
co
m
p
o
n
e
n
t
s
.
Seco
n
d
s
ec
tio
n
d
escr
ib
es h
o
w
to
d
ev
el
o
p
m
ac
h
in
e
lear
n
i
n
g
al
g
o
r
ith
m
s
i
n
P
y
Sp
ar
k
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
Ma
ch
in
e
Lea
r
n
in
g
w
ith
P
yS
p
a
r
k
-
R
ev
iew
(
R
a
s
w
ith
a
B
a
n
d
i
)
103
2.
SPAR
K
CO
RE
T
E
CH
NO
L
O
G
I
E
S AN
D
I
T
S CO
M
P
O
NE
NT
S
Sp
ar
k
is
a
f
r
a
m
e
w
o
r
k
f
o
r
Dis
tr
ib
u
ted
co
m
p
u
tin
g
w
h
ic
h
d
ep
e
n
d
s
o
n
Had
o
o
p
Ma
p
R
ed
u
ce
a
lg
o
r
ith
m
s
.
I
t
in
g
e
s
ts
t
h
e
p
o
in
t
s
o
f
i
n
ter
e
s
t
o
f
Had
o
o
p
Ma
p
R
ed
u
ce
,
y
et
n
o
t
at
all
li
k
e
Ma
p
R
ed
u
ce
,
s
p
ar
k
ca
n
s
to
r
e
i
n
m
e
m
o
r
y
th
e
i
n
ter
m
ed
iate
d
ata
an
d
r
esu
lt
s
,
w
h
ic
h
i
s
ca
lled
Me
m
o
r
y
C
o
m
p
u
ti
n
g
[
3
]
.
Me
m
o
r
y
C
o
m
p
u
ti
n
g
e
n
h
a
n
ce
s
t
h
e
p
r
o
d
u
ctiv
it
y
o
f
d
ata
c
o
m
p
u
ti
n
g
.
Sp
ar
k
is
m
o
r
e
q
u
alif
ied
f
o
r
iter
ativ
e
ap
p
licatio
n
s
,
f
o
r
ex
a
m
p
le,
Data
Min
in
g
a
n
d
Ma
c
h
in
e
L
ea
r
n
i
n
g
.
T
h
e
R
DD
(
R
esil
ie
n
t
Di
s
tr
ib
u
te
d
Data
s
et)
i
n
Sp
ar
k
i
s
a
Fa
u
lt
t
o
ler
an
t
co
llectio
n
o
f
co
m
p
o
n
en
ts
t
h
at
ca
n
b
e
w
o
r
k
ed
i
n
p
ar
allel
an
d
p
er
m
its
c
lien
t
s
to
ex
p
r
ess
l
y
s
to
r
e
th
e
in
f
o
r
m
atio
n
i
n
co
m
p
ac
t
d
i
s
k
a
n
d
m
e
m
o
r
y
[
4
]
.
On
e
ca
n
u
t
ilize
R
D
D
to
ac
co
m
p
li
s
h
s
o
m
e
n
e
w
h
i
g
h
li
g
h
t
s
t
h
at
is
n
'
t
b
o
ls
ter
ed
b
y
t
h
e
v
a
s
t
m
aj
o
r
ity
o
f
cu
r
r
en
t
b
u
n
c
h
p
r
o
g
r
a
m
m
i
n
g
m
o
d
el
s
an
d
p
r
io
r
p
r
o
g
r
am
m
i
n
g
m
o
d
els.
Fo
r
ex
a
m
p
le,
I
ter
ati
v
e
A
l
g
o
r
ith
m
s
,
SQ
L
q
u
er
y
,
B
atch
,
Flo
w
.
R
DD
i
s
p
er
u
s
ed
j
u
s
t
i
n
f
o
r
m
atio
n
s
et
s
,
an
d
it
ca
n
r
ec
all
t
h
e
o
p
er
atio
n
s
o
f
d
iag
r
a
m
.
R
DD
g
i
v
es
a
w
ell
ar
r
an
g
e
m
e
n
t
o
f
o
p
er
atio
n
s
to
co
n
tr
o
l th
e
in
f
o
r
m
atio
n
[
5
]
.
Sp
ar
k
p
r
o
v
id
es
A
P
I
s
in
J
av
a,
Scala,
P
y
th
o
n
an
d
R
,
is
a
n
o
p
ti
m
ized
e
n
g
i
n
e
w
h
ic
h
s
u
p
p
o
r
ts
ex
ec
u
tio
n
g
r
ap
h
s
g
en
er
all
y
.
I
t
lik
e
w
i
s
e
b
o
ls
ter
s
a
h
u
g
e
ar
r
an
g
e
m
e
n
t
o
f
m
o
r
e
elev
ated
a
m
o
u
n
t
d
ev
ices
co
u
n
t
in
g
Sp
ar
k
SQL
f
o
r
SQ
L
,
ML
lib
f
o
r
m
ac
h
in
e
lear
n
i
n
g
,
Gr
ap
h
X
f
o
r
ch
a
r
t p
r
ep
ar
in
g
,
an
d
Sp
ar
k
Stre
am
i
n
g
.
Sp
ar
k
C
o
r
e
co
m
p
r
is
es
o
f
g
e
n
er
al
ex
ec
u
tio
n
e
n
g
in
e
f
o
r
s
p
ar
k
p
latf
o
r
m
t
h
at
all
r
eq
u
ir
e
d
b
y
o
th
er
u
s
e
f
u
ln
e
s
s
w
h
ic
h
is
b
ased
u
p
o
n
ac
co
r
d
in
g
to
t
h
e
p
r
er
eq
u
is
ite
ap
p
r
o
ac
h
.
I
t
p
r
o
v
id
es
in
-
b
u
i
lt
m
e
m
o
r
y
co
m
p
u
ti
n
g
a
n
d
r
ef
er
en
c
in
g
d
at
a
s
ets s
to
r
ed
in
ex
ter
n
al
s
to
r
ag
e
[
7
-
8
]
.
Sp
ar
k
en
ab
le
s
th
e
d
esi
g
n
er
s
to
co
m
p
o
s
e
co
d
e
r
a
p
id
ly
w
it
h
th
e
ass
i
s
ta
n
ce
o
f
r
ich
o
p
er
ato
r
s
.
W
h
ile
it
tak
es
a
co
n
s
id
er
ab
le
m
ea
s
u
r
e
o
f
lin
es
o
f
co
d
e,
it
tak
es
f
e
w
e
r
lin
es
to
co
m
p
o
s
e
a
s
i
m
ilar
c
o
d
e
in
Sp
ar
k
Scala.
Fig
u
r
e
1
s
h
o
w
s
t
h
e
co
r
e
tech
n
o
lo
g
ies
an
d
co
m
p
o
n
e
n
t
s
o
f
Sp
a
r
k
.
E
ac
h
co
m
p
o
n
e
n
t
o
f
Sp
ar
k
co
r
e
ar
e
ex
p
lain
ed
in
th
e
u
p
co
m
i
n
g
s
ec
tio
n
s
o
f
t
h
e
p
ap
er
.
Fig
u
r
e
1
.
A
p
ac
h
e
Sp
ar
k
co
r
e
2
.
1
.
Sp
a
rk
SQ
L
Sp
ar
k
SQ
L
is
a
s
eg
m
e
n
t
o
v
e
r
Sp
ar
k
co
r
e
th
at
g
iv
es
a
n
o
th
er
ar
r
an
g
e
m
e
n
t
o
f
d
ata
r
ef
lec
tio
n
ca
lled
R
DD,
w
h
ich
o
f
f
er
s
h
elp
f
o
r
b
o
th
th
e
o
r
g
a
n
ized
an
d
u
n
s
tr
u
ct
u
r
ed
in
f
o
r
m
atio
n
[
6
]
.
T
h
e
ex
a
m
p
le
o
f
Hi
v
e
Qu
er
y
:
/s
co
n
te
x
t is a
c
u
r
r
en
t Sp
ar
k
C
o
n
tex
t.
Val
s
q
lC
o
n
tex
t =
Ne
w
o
r
g
.
ap
ac
h
e.
s
p
ar
k
.
s
q
l.h
i
v
e.
Hi
v
eCo
n
te
x
t(
s
co
n
tex
t)
s
q
lC
o
n
te
x
t.sq
l(
"
C
R
E
A
T
E
T
A
B
L
E
I
F NO
T
E
XI
S
T
S src
(
k
ey
I
NT
,
esteem
ST
R
I
NG)
"
)
s
q
lC
o
n
te
x
t.sq
l(
"
L
O
A
D
D
A
T
A
L
OC
AL
I
NP
A
T
H
'
ca
s
es/
s
r
c/p
r
im
ar
y
/as
s
ets/
k
v
1
.
tx
t
'
I
NT
O
T
A
B
L
E
s
r
c"
)
/Qu
er
ies ar
e
co
m
m
u
n
icate
d
in
Hiv
eQ
L
s
q
lC
o
n
te
x
t.sq
l(
"
FR
OM
s
r
c
SEL
E
C
T
k
e
y
,
v
al
u
e"
)
.
co
llect(
)
.
f
o
r
ea
ch
(
p
r
in
tln
)
.
2
.
2
.
Sp
a
rk
Str
ea
m
i
ng
T
h
is
p
ar
t
en
ab
les
Sp
ar
k
to
p
r
o
ce
s
s
r
ea
l
-
t
i
m
e
s
tr
ea
m
i
n
g
d
at
a.
I
t
g
iv
e
s
a
n
A
P
I
to
co
n
tr
o
l
d
ata
s
tr
ea
m
s
th
at
m
atc
h
es
w
i
th
R
DD
A
P
I
.
I
t
en
ab
les
t
h
e
d
ev
elo
p
er
s
t
o
co
m
p
r
eh
e
n
d
t
h
e
tas
k
a
n
d
s
w
itc
h
th
r
o
u
g
h
t
h
e
ap
p
licatio
n
s
th
at
co
n
tr
o
l
th
e
d
ata
an
d
g
iv
i
n
g
r
es
u
lt
co
n
tin
u
o
u
s
l
y
.
L
i
k
e
Sp
ar
k
C
o
r
e,
Sp
ar
k
Stre
a
m
i
n
g
en
d
ea
v
o
r
s
to
in
f
l
u
en
ce
t
h
e
f
r
am
e
w
o
r
k
to
b
la
m
e
to
ler
an
t a
n
d
ad
ap
tab
le
[
9
-
1
0
]
.
RDD
AP
I
E
x
a
m
p
le
I
n
th
is
e
x
a
m
p
le,
u
s
e
a
f
e
w
tr
an
s
f
o
r
m
atio
n
s
th
at
ar
e
i
m
p
le
m
en
ted
to
b
u
ild
a
d
atase
t
o
f
(
s
tr
in
g
,
in
t)
p
air
s
ca
lled
co
u
n
ts
a
n
d
th
e
n
s
a
v
e
it to
a
f
ile.
T
ex
t
-
f
i
le
=
s
co
n
te
x
t.te
x
tf
ile(
“
h
d
f
s
://
…”)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l
.
1
2
,
No
.
1
,
Octo
b
er
201
8
:
1
0
2
–
106
104
C
o
u
n
ts
=
te
x
t
-
f
i
le.
f
lat
m
ap
(
la
m
b
d
a
lin
e:lin
e.
s
p
lit(
“
”)
)
.
Ma
p
(
la
m
d
a
w
o
r
d
,
1
)
)
.
r
ed
u
ce
B
y
K
e
y
(
la
m
b
d
a
a,
b
:a+
b
)
.
Sav
e
t
h
e
f
i
le
as:
C
o
u
n
ts
.
s
a
v
e
AsT
ex
tFi
le(
“h
d
f
s
:
//…”)
2
.
3
.
M
L
lib
(
M
a
chine
L
ea
rni
ng
L
ibra
ry
)
A
p
ac
h
e
Sp
ar
k
i
s
o
u
tf
i
tted
w
it
h
a
r
ich
lib
r
ar
y
k
n
o
w
n
a
s
M
L
li
b
.
T
h
is
lib
r
ar
y
co
n
tai
n
s
a
w
id
e
ex
h
ib
it o
f
m
ac
h
in
e
lear
n
i
n
g
ca
lc
u
latio
n
s
,
clas
s
i
f
icatio
n
,
cl
u
s
ter
in
g
an
d
co
llab
o
r
atio
n
,
an
d
s
o
o
n
.
I
t
ad
d
itio
n
all
y
in
co
r
p
o
r
ates
f
e
w
lo
w
er
-
le
v
el
p
r
im
iti
v
es.
E
v
er
y
o
n
e
o
f
th
e
s
e
f
u
n
ctio
n
a
liti
es
e
n
ab
le
Sp
ar
k
to
s
ca
le
o
u
t
o
v
er
a
b
u
n
c
h
[
1
1
]
.
2
.
3
.
1
F
o
re
ca
s
t
w
it
h L
o
g
is
t
ic
Reg
re
s
s
io
n
I
n
th
i
s
ill
u
s
tr
atio
n
,
w
e
tak
e
a
d
ataset
estee
m
s
as
f
ar
as
n
a
m
es
an
d
h
i
g
h
li
g
h
t
v
ec
to
r
s
.
W
e
f
i
g
u
r
e
o
u
t
h
o
w
to
f
o
r
esee
t
h
e
m
ar
k
s
f
r
o
m
h
i
g
h
lig
h
t
v
ec
to
r
s
u
tili
zi
n
g
th
e
s
tr
ateg
y
f
o
r
L
o
g
is
tic
R
e
g
r
ess
io
n
ca
lcu
la
tio
n
u
tili
zi
n
g
th
e
p
y
th
o
n
d
ialec
t:
#
E
v
er
y
r
ec
o
r
d
o
f
th
i
s
Data
Fra
m
e
co
n
tai
n
s
t
h
e
n
a
m
e
a
n
d
#
f
ea
tu
r
es r
ep
r
esen
ted
b
y
a
v
e
cto
r
.
d
f
=
s
q
lC
o
n
te
x
t.c
r
ea
teDa
ta
Fra
m
e(
d
ata,
[
"
lab
el
"
,
"
f
ea
tu
r
es"
]
)
#
Set p
ar
am
eter
s
f
o
r
th
e
ca
lc
u
l
atio
n
.
#
Her
e,
w
e
r
estra
i
n
t
h
e
q
u
an
tit
y
o
f
e
m
p
h
ase
s
s
to
1
0
.
lr
=
L
o
g
is
ticR
e
g
r
es
s
io
n
(
m
ax
I
t
er
=1
0
)
#
Fit
th
e
m
o
d
el
to
th
e
i
n
f
o
r
m
at
io
n
.
d
is
p
la
y
=
lr
.
f
it(d
f
)
#
Giv
en
a
d
ataset,
a
n
ticip
ate
e
ac
h
p
o
in
t
'
s
n
a
m
e,
an
d
d
e
m
o
n
s
t
r
ate
th
e
o
u
tco
m
e
s
.
m
o
d
el.
tr
a
n
s
f
o
r
m
(
d
f
)
.
s
h
o
w
(
)
2
.
4
.
G
ra
ph
X
Sp
ar
k
ac
co
m
p
a
n
ies
a
lib
r
ar
y
to
co
n
tr
o
l
th
e
g
r
ap
h
s
a
n
d
p
er
f
o
r
m
i
n
g
ca
lc
u
latio
n
s
,
ca
lled
a
s
Gr
ap
h
X
.
Mu
ch
t
h
e
s
a
m
e
as
Sp
ar
k
Stre
a
m
i
n
g
a
n
d
Sp
ar
k
SQ
L
,
Gr
ap
h
X
ad
d
itio
n
all
y
ex
p
a
n
d
s
Sp
ar
k
R
DD
A
P
I
w
h
ic
h
m
ak
e
s
a
co
o
r
d
in
ated
g
r
ap
h
.
I
t
ad
d
itio
n
all
y
co
n
tai
n
s
v
ar
i
o
u
s
ad
m
in
i
s
tr
ato
r
s
s
o
a
s
to
co
n
tr
o
l
th
e
g
r
ap
h
s
alo
n
g
s
id
e
d
iag
r
a
m
ca
lc
u
latio
n
s
.
C
o
n
s
id
er
th
e
ac
co
m
p
an
y
i
n
g
c
ase
to
d
is
p
la
y
clien
ts
a
n
d
ite
m
s
as a
b
ip
a
r
tite g
r
ap
h
w
e
m
a
y
t
ak
e
af
ter
:
C
las
s
Ver
tex
P
r
o
p
er
ty
(
)
C
ase
clas
s
User
P
r
o
p
er
ty
(
Val
n
a
m
e
: Str
i
n
g
)
ex
p
a
n
d
s
Ver
tex
P
r
o
p
er
ty
C
ase
clas
s
P
r
o
d
u
ct
P
r
o
p
er
ty
(
Val
n
a
m
e:
Stri
n
g
,
Val
v
al
u
e:
Do
u
b
le)
ex
p
an
d
s
Ver
te
x
P
r
o
p
er
t
y
/T
h
e
ch
ar
t
m
a
y
t
h
e
n
h
a
v
e
t
h
e
s
o
r
t:
V
ar
d
iag
r
a
m
: G
r
ap
h
[
Ver
tex
P
r
o
p
er
ty
,
Strin
g
]
=
in
v
alid
3
.
DE
VE
L
O
P
M
E
NT
O
F
M
ACH
I
NE
L
E
AR
NIN
G
A
L
G
O
RI
T
H
M
S USI
N
G
P
YSP
ARK
P
y
t
h
o
n
is
a
n
i
n
te
n
s
e
p
r
o
g
r
a
m
m
i
n
g
d
ialec
t
f
o
r
d
ea
lin
g
w
it
h
co
m
p
le
x
d
ata
a
n
al
y
s
i
s
a
n
d
d
ata
m
u
n
g
i
n
g
task
s
[
1
]
,
[
3
]
,
[
1
2
]
.
I
t
h
as
a
f
e
w
i
n
-
co
n
s
tr
u
cted
lib
r
ar
ies
an
d
s
y
s
te
m
s
to
d
o
in
f
o
r
m
at
io
n
m
i
n
i
n
g
er
r
an
d
s
p
r
o
f
icien
tl
y
.
I
n
an
y
ca
s
e,
n
o
p
r
o
g
r
am
m
i
n
g
d
ialec
t
alo
n
e
ca
n
d
ea
l
w
it
h
en
o
r
m
o
u
s
i
n
f
o
r
m
at
io
n
h
a
n
d
li
n
g
p
r
o
d
u
ctiv
el
y
.
T
h
er
e
is
co
n
s
ta
n
tl
y
r
eq
u
ir
e
m
en
t
f
o
r
a
co
n
v
e
y
e
d
r
eg
is
te
r
in
g
s
tr
u
ct
u
r
e
lik
e
Ha
d
o
o
p
o
r
Sp
ar
k
.
A
p
ac
h
e
Sp
ar
k
b
o
ls
ter
s
t
h
r
ee
m
o
s
t in
te
n
s
e
p
r
o
g
r
a
m
m
i
n
g
d
ialec
ts
:
1
.
Scala
2
.
J
av
a
3
.
P
y
th
o
n
ML
lib
al
g
o
r
ith
m
A
P
I
s
.
T
h
er
e
ar
e
t
w
o
m
aj
o
r
ty
p
e
s
o
f
alg
o
r
it
h
m
s
: T
r
an
s
f
o
r
m
er
s
an
d
E
s
ti
m
ato
r
s
:
T
r
an
s
f
o
r
m
er
s
ar
e
al
g
o
r
ith
m
s
t
h
at
ta
k
e
an
in
p
u
t
d
ataset
a
n
d
m
o
d
i
f
y
it
u
s
i
n
g
tr
an
s
f
o
r
m
(
)
f
u
n
ctio
n
to
p
r
o
d
u
ce
an
o
u
tp
u
t
d
ataset.
E
s
ti
m
ato
r
s
ar
e
ML
al
g
o
r
ith
m
s
th
at
tak
e
a
tr
ain
i
n
g
d
ata
s
et,
u
s
e
a
f
it()
f
u
n
c
tio
n
to
tr
ain
a
n
M
L
m
o
d
el
a
n
d
o
u
tp
u
t t
h
at
m
o
d
el.
E
x
a
m
p
l
e
s
o
f
E
s
ti
m
ato
r
s
ar
e
L
o
g
is
tic
R
eg
r
es
s
io
n
a
n
d
R
a
n
d
o
m
Fo
r
ests
.
Gen
er
all
y
P
r
o
g
r
a
m
m
er
s
o
f
te
n
co
m
b
i
n
e
m
u
l
tip
le
T
r
an
s
f
o
r
m
er
s
an
d
E
s
ti
m
ato
r
s
in
to
a
d
ata
an
al
y
t
ics
f
lo
w
.
M
L
P
ip
elin
e
p
r
o
v
id
e
an
A
P
I
f
o
r
c
h
ain
in
g
al
g
o
r
it
h
m
s
,
f
ee
d
in
g
t
h
e
o
u
tp
u
t
o
f
ea
c
h
a
lg
o
r
it
h
m
i
n
t
o
T
r
an
s
f
o
r
m
er
s
a
n
d
E
s
ti
m
a
to
r
s
[
1
4
-
1
5
]
.
T
h
e
f
o
llo
w
i
n
g
E
x
a
m
p
le
p
ip
e
lin
e
w
it
h
2
T
r
an
s
f
o
r
m
er
s
(
T
o
k
en
izer
,
Has
h
i
n
g
T
F)
an
d
1
E
s
ti
m
ato
r
(
L
o
g
i
s
tic
R
e
g
r
es
s
io
n
)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
Ma
ch
in
e
Lea
r
n
in
g
w
ith
P
yS
p
a
r
k
-
R
ev
iew
(
R
a
s
w
ith
a
B
a
n
d
i
)
105
P
ipelin
e
(
E
s
t
i
m
a
t
o
r)
T
o
k
en
izer
Has
h
i
n
g
T
F
L
o
g
is
tic
R
e
g
r
es
s
io
n
P
ipelin
e.
f
it
(
)
R
a
w
T
ex
t
W
o
r
d
s
Feat
u
r
e
Vec
to
r
s
L
o
g
i
s
tic
R
e
g
r
es
s
io
n
Mo
d
el
I
f
a
Data
Scien
tis
t
w
a
n
t
to
in
cl
u
d
e
a
cu
s
to
m
T
r
an
s
f
o
r
m
er
an
d
E
s
ti
m
ato
r
First,t
h
e
d
ata
s
cien
t
is
t
w
r
i
tes
a
class
t
h
at
e
x
te
n
d
s
T
r
an
s
f
o
r
m
er
o
r
E
s
ti
m
ato
r
an
d
t
h
en
i
m
p
le
m
e
n
t
s
t
h
e
co
r
r
esp
o
n
d
in
g
tr
an
s
f
o
r
m
(
)
o
r
f
it()
m
et
h
o
d
s
.
On
e
o
b
s
tacl
e
i
n
M
L
lib
is
ML
P
er
s
is
ta
n
ce
.
I
t
al
lo
w
s
u
s
er
s
to
s
a
v
e
m
o
d
els
an
d
p
ip
elin
es
to
s
tab
le
s
to
r
ag
e,
f
o
r
lo
ad
in
g
a
n
d
r
eu
s
i
n
g
later
o
r
f
o
r
g
o
in
g
to
a
n
o
th
er
g
r
o
u
p
.
T
h
e
A
P
I
is
b
asic;
th
e
ac
co
m
p
an
y
i
n
g
co
d
e
p
iece
f
its
a
m
o
d
el
u
tili
zi
n
g
C
r
o
s
s
Valid
ato
r
f
o
r
p
ar
am
eter
tu
n
in
g
,
s
p
ar
es th
e
f
itted
m
o
d
el,
an
d
lo
ad
s
it b
ac
k
:
v
al1
cv
Mo
d
el1
=
cv
.
f
i
t(
tr
ain
i
n
g
)
cv
Mo
d
el1
.
s
av
e(
"
C
VM
o
d
elP
at
h
"
)
v
al1
s
a
m
eCVMo
d
el1
=
C
r
o
s
s
Valid
ato
r
Mo
d
el.
lo
ad
(
"
C
VM
o
d
elP
ath
"
)
ML
P
er
s
is
te
n
ce
s
a
v
es
m
o
d
els
an
d
P
ip
elin
es
as
J
SON
m
eta
d
ata
+
P
a
r
q
u
et
d
is
p
lay
i
n
f
o
r
m
atio
n
,
an
d
it
ca
n
b
e
u
tili
ze
d
to
ex
c
h
an
g
e
m
o
d
el
s
an
d
P
ip
elin
es c
r
o
s
s
w
i
s
e
o
v
er
S
p
ar
k
b
u
n
c
h
es,
ar
r
an
g
e
m
e
n
t
s
,
an
d
g
r
o
u
p
s
[
1
6
]
.
4.
P
YT
H
O
N
P
E
RSI
ST
E
N
CE
M
I
XINS
T
o
im
p
le
m
e
n
t
M
L
al
g
o
r
ith
m
s
u
s
i
n
g
P
y
th
o
n
-
o
n
l
y
L
an
g
u
ag
e,
w
e
u
s
e
s
tr
u
ct
u
r
e
in
t
h
e
P
y
Sp
ar
k
A
P
I
s
i
m
ilar
to
th
e
o
n
e
i
n
t
h
e
Scala
A
P
I
.
W
ith
t
h
is
s
y
s
te
m
,
w
h
ile
ac
tu
alizi
n
g
a
c
u
s
to
m
T
r
an
s
f
o
r
m
er
o
r
E
s
ti
m
ato
r
in
P
y
t
h
o
n
,
it
i
s
n
e
v
er
ag
ai
n
i
m
p
o
r
tan
t
to
ex
ec
u
te
t
h
e
b
asic
ca
lcu
latio
n
in
Scala.
R
at
h
er
,
o
n
e
ca
n
u
til
ize
m
i
x
i
n
class
es
w
i
th
a
c
u
s
to
m
T
r
an
s
f
o
r
m
er
o
r
E
s
t
i
m
ato
r
to
e
m
p
o
w
er
P
er
s
is
ten
ce
[
1
2
]
.
Fo
r
b
asic
al
g
o
r
ith
m
s
f
o
r
w
h
ic
h
t
h
e
m
aj
o
r
it
y
o
f
t
h
e
p
ar
a
m
e
t
er
s
ar
e
J
SON
-
s
er
ializab
le
(
b
asic
s
o
r
ts
lik
e
s
tr
i
n
g
,
f
lo
at)
,
th
e
al
g
o
r
ith
m
cla
s
s
ca
n
ex
te
n
d
t
h
e
clas
s
es
De
f
au
lt
P
ar
a
m
s
R
ea
d
ab
le
an
d
De
f
a
u
lt
P
ar
am
s
W
r
itab
le
to
en
a
b
le
au
to
m
at
ic
p
er
s
is
ten
ce
.
T
h
is
d
ef
au
lt
i
m
p
le
m
e
n
tatio
n
o
f
P
er
s
is
ten
ce
w
ill
allo
w
th
e
c
u
s
to
m
al
g
o
r
ith
m
to
b
e
s
av
ed
an
d
lo
ad
ed
w
ith
in
P
y
Sp
ar
k
[
1
1
,
1
3
]
.
T
h
ese
m
ix
i
n
s
s
i
g
n
i
f
ica
n
tl
y
d
i
m
in
is
h
th
e
ad
v
a
n
ce
m
en
t
ex
er
tio
n
r
eq
u
ir
ed
to
m
a
k
e
c
u
s
to
m
ML
alg
o
r
ith
m
s
o
v
er
P
y
Sp
ar
k
.
St
u
d
y
t
h
at
u
s
ed
to
ta
k
e
m
a
n
y
li
n
es
o
f
ad
d
itio
n
al
co
d
e
s
h
o
u
ld
n
o
w
b
e
p
o
s
s
ib
le
i
n
a
s
in
g
le
l
in
e
m
u
c
h
o
f
t
h
e
t
i
m
e.
T
h
e
f
o
llo
w
i
n
g
co
d
e
s
n
ip
p
et
d
e
m
o
n
s
tr
ates
u
s
i
n
g
t
h
ese
Mix
i
n
s
f
o
r
a
P
y
t
h
o
n
-
o
n
l
y
i
m
p
le
m
en
ta
tio
n
o
f
P
er
s
is
ta
n
ce
:
C
las
s
s
h
if
tT
r
an
s
f
o
r
m
er
(
u
n
ar
y
T
r
an
s
f
o
r
m
er
,
Def
a
u
ltp
ar
a
m
s
r
e
ad
ab
le,
Def
au
ltp
ar
a
m
s
w
r
itab
le
)
;
T
h
ese
Mix
i
n
s
De
f
a
u
ltp
ar
a
m
s
r
ea
d
ab
le
an
d
Def
au
l
tp
ar
a
m
s
w
r
i
tab
le
to
th
e
s
h
if
t
tr
an
s
f
o
r
m
er
c
lass
allo
w
eli
m
i
n
ati
n
g
a
lo
t o
f
co
d
e.
5
.
CO
NCLUS
I
O
N
T
h
is
p
ap
er
d
is
cu
s
s
es
ab
o
u
t
t
h
e
p
r
o
ce
d
u
r
e
to
w
r
ite
a
c
u
s
t
o
m
Ma
ch
i
n
e
L
ea
r
n
in
g
al
g
o
r
ith
m
s
u
s
i
n
g
P
y
Sp
ar
k
w
it
h
t
h
e
h
elp
o
f
P
y
th
o
n
L
a
n
g
u
a
g
e
an
d
u
s
e
th
e
m
in
P
ip
elin
es
an
d
s
a
v
e
a
n
d
l
o
ad
th
e
m
w
i
th
o
u
t
to
u
ch
i
n
g
Scala.
T
h
ese
i
m
p
r
o
v
e
m
e
n
t
s
w
ill
m
a
k
e
th
e
d
ev
el
o
p
er
s
to
u
n
d
er
s
tan
d
an
d
w
r
it
e
cu
s
to
m
Ma
ch
i
n
e
L
ea
r
n
i
n
g
al
g
o
r
it
h
m
s
ea
s
il
y
.
RE
F
E
R
E
NC
E
S
[1
]
Nic
k
P
e
n
trea
th
,
M
a
c
h
i
n
e
L
e
a
rn
in
g
w
it
h
S
p
a
rk
,
Be
ij
in
g
,
p
p
.
1
-
1
4
0
,
2
0
1
5
.
[2
]
Zh
ij
ie
Ha
n
,
a
n
d
Y
u
ji
e
Zh
a
n
g
,
“
A
Bi
g
Da
t
a
P
ro
c
e
ss
in
g
P
latf
o
rm
Ba
se
d
On
M
e
m
o
r
y
Co
m
p
u
ti
n
g
”
2
0
1
5
S
e
v
e
n
th
In
tern
a
ti
o
n
a
l
S
y
m
p
o
siu
m
o
n
in
P
a
ra
ll
e
l
A
r
c
h
it
e
c
tu
re
s,
A
l
g
o
rit
h
m
s
a
n
d
P
r
o
g
ra
m
m
in
g
(P
AA
P
),
Na
n
ji
n
g
,
p
p
.
1
7
2
-
1
7
6
,
2
0
1
5
.
[3
]
A
a
ro
n
N.
Rich
ter,
T
a
g
h
i
M
.
K
h
o
sh
g
o
f
taa
r,
S
a
ra
Lan
d
se
t,
a
n
d
T
a
wfi
q
Ha
sa
n
in
,
“
A
M
u
lt
i
-
Dim
e
n
sio
n
a
l
C
o
m
p
a
riso
n
o
f
T
o
o
lk
it
s
f
o
r
M
a
c
h
in
e
L
e
a
rn
in
g
w
it
h
Big
Da
ta
”
,
2
0
1
5
IEE
E
In
t
e
rn
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
In
f
o
rm
a
ti
o
n
Re
u
se
a
n
d
In
teg
ra
ti
o
n
(IRI),
S
a
n
F
ra
n
c
isc
o
CA
,
p
p
.
1
-
8
,
2
0
1
5
.
[4
]
S
a
u
p
ti
k
D
h
a
r,
C
o
n
g
ru
i
Yi,
Na
v
e
e
n
Ra
m
a
k
rish
n
a
n
,
a
n
d
M
o
h
a
k
S
h
a
h
,
A
DMM
b
a
se
d
S
c
a
lab
le
M
a
c
h
i
n
e
L
e
a
rn
in
g
o
n
S
p
a
rk
,
in
B
ig
Da
ta (Bi
g
Da
ta),
2
0
1
5
IE
EE
I
n
tern
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
,
S
a
n
ta
Clara
CA
,
2
0
1
5
,
p
p
.
1
1
7
4
-
1
1
8
2
[5
]
A
s
m
e
las
h
T
e
k
a
Ha
d
g
u
,
A
a
sth
a
Nig
a
m
,
a
n
d
Ern
e
sto
Dia
z
Av
il
e
s
L
a
rg
e
-
sc
a
le
lea
rn
in
g
w
it
h
A
d
a
G
r
a
d
o
n
S
p
a
rk
,
in
Big
Da
ta (Bi
g
Da
ta),
2
0
1
5
IEE
E
In
ter
n
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
,
S
a
n
ta Cl
a
ra
C
A
,
2
0
1
5
,
p
p
.
2
8
2
8
-
2
8
3
0
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l
.
1
2
,
No
.
1
,
Octo
b
er
201
8
:
1
0
2
–
106
106
[6
]
Ha
n
g
T
a
o
,
Bin
W
u
,
a
n
d
X
iu
q
i
n
L
in
,
Bu
d
g
e
ted
m
in
i
-
b
a
tch
p
a
ra
ll
e
l
g
ra
d
ien
t
d
e
sc
e
n
t
f
o
r
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
s
o
n
S
p
a
rk
,
in
2
0
1
4
2
0
t
h
IEE
E
In
ter
n
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
P
a
ra
ll
e
l
a
n
d
Distrib
u
ted
S
y
ste
m
s
(ICP
AD
S
),
Hs
in
c
h
u
,
2
0
1
4
,
p
p
.
9
4
5
-
950
[7
]
A
n
d
re
L
u
c
k
o
w
,
Ke
n
Ke
n
n
e
d
y
,
F
a
b
ian
M
a
n
h
a
rd
t,
Em
i
l
Dje
re
k
a
ro
v
,
Be
n
n
ie V
o
rste
r,
a
n
d
Am
y
A
p
o
n
,
A
u
to
m
o
ti
v
e
b
ig
d
a
ta:
A
p
p
li
c
a
ti
o
n
s,
w
o
rk
lo
a
d
s
a
n
d
in
f
ra
stru
c
tu
re
s,
in
Big
Da
ta(Bi
g
Da
ta),2
0
1
5
IE
EE
In
ter
n
a
ti
o
n
a
lCo
n
f
e
re
n
c
e
o
n
,
S
a
n
ta
Clara
CA
,
2
0
1
5
,
p
p
.
1
2
0
1
-
1
2
1
0
[8
]
M
a
rk
G
a
te
s,
Ha
rt
w
ig
A
n
z
t,
Ja
k
u
b
Ku
rz
a
k
,
a
n
d
Ja
c
k
Do
n
g
a
r
ra
,
Ac
c
e
lera
ti
n
g
c
o
ll
a
b
o
ra
ti
v
e
fi
lt
e
rin
g
u
sin
g
c
o
n
c
e
p
ts
f
ro
m
h
ig
h
p
e
rf
o
rm
a
n
c
e
c
o
m
p
u
ti
n
g
,
in
Big
Da
ta (Bi
g
Da
ta),
2
0
1
5
I
EE
E
In
ter
n
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
,
S
a
n
ta Cl
a
ra
CA
,
2
0
1
5
,
p
p
.
6
6
7
6
7
6
[9
]
Yic
h
e
n
g
Hu
a
n
g
,
X
i
n
g
tu
L
a
n
,
X
in
g
C
h
e
n
,
a
n
d
W
e
n
z
h
o
n
g
G
u
o
,
T
o
w
a
rd
s
M
o
d
e
l
Ba
se
d
A
p
p
r
o
a
c
h
to
Ha
d
o
o
p
De
p
lo
y
m
e
n
t
a
n
d
Co
n
fi
g
u
ra
ti
o
n
,
i
n
2
0
1
5
1
2
t
h
W
e
b
In
f
o
r
m
a
ti
o
n
S
y
ste
m
a
n
d
A
p
p
li
c
a
ti
o
n
C
o
n
f
e
re
n
c
e
(W
IS
A
),
Jin
a
n
,
2
0
1
5
,
p
p
.
7
9
-
84
[1
0
]
E.
De
d
e
,
B.
S
e
n
d
ir,
P
.
K
u
z
lu
,
J.W
e
a
c
h
o
c
k
,
M
.
G
o
v
in
d
a
ra
ju
,
a
n
d
L
.
R
a
m
a
k
rish
n
a
n
,
P
ro
c
e
ss
in
g
Ca
ss
a
n
d
ra
Da
tas
e
ts
w
it
h
H
a
d
o
o
p
-
S
trea
m
in
g
Ba
se
d
A
p
p
ro
a
c
h
e
s,
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
S
e
rv
ice
s Co
m
p
u
ti
n
g
,
2
0
1
5
,
p
p
.
4
6
-
58
[1
1
]
A
le
x
a
n
d
e
r
J.S
ti
m
p
so
n
,
a
n
d
M
a
ry
L
.
Cu
m
m
in
g
s,
A
ss
e
s
sin
g
In
terv
e
n
ti
o
n
T
im
in
g
in
Co
m
p
u
ter
-
Ba
se
d
Ed
u
c
a
ti
o
n
Us
in
g
M
a
c
h
in
e
L
e
a
rn
in
g
A
lg
o
rit
h
m
s,
in
IEE
E
A
c
c
e
ss
,
2
0
1
4
,
p
p
.
7
8
-
87.
[1
2
]
X
ian
q
in
g
Yu
,
P
e
n
g
Nin
g
,
a
n
d
M
l
a
d
e
n
A
.
V
o
u
k
,
En
h
a
n
c
in
g
se
c
u
rit
y
o
f
Ha
d
o
o
p
in
a
p
u
b
li
c
c
lo
u
d
,
i
n
I
n
f
o
rm
a
ti
o
n
a
n
d
Co
m
m
u
n
ica
ti
o
n
S
y
ste
m
s (ICICS
)
,
2
0
1
5
6
t
h
I
n
tern
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
,
2
0
1
5
,
Am
m
a
n
,
p
p
.
3
8
-
4
3
.
[1
3
]
Ra
s
w
it
h
a
Ba
n
d
i,
S
h
e
ik
h
G
o
u
se
,
J
Am
u
d
h
v
e
l,
“
A
Co
m
p
a
rit
iv
e
a
n
a
l
y
sis
f
o
r
b
ig
d
a
ta
c
h
a
ll
e
n
g
e
s
a
n
d
b
ig
d
a
ta
issu
e
s
u
sin
g
in
f
o
rm
a
ti
o
n
se
c
u
rit
y
e
n
c
r
y
p
ti
o
n
tec
h
n
i
q
u
e
s”
,
In
tern
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
P
u
re
a
n
d
A
p
p
li
e
d
M
a
th
e
m
a
ti
c
s,
V
o
l
1
1
5
,
No
8
,
p
p
.
2
4
5
-
2
5
1
,
(2
0
1
7
).
[1
4
]
S
u
b
a
sh
i
n
i,
M
.
M
.
,
Da
s,
S
.
,
He
b
le,
S
.
,
Ra
j,
U.
,
Ka
rth
ik
,
R.
,
“
In
tern
e
t
o
f
th
i
n
g
s
b
a
se
d
w
irele
ss
p
lan
t
se
n
so
r
f
o
r
sm
a
rt
f
a
r
m
in
g
”
,
In
d
o
n
e
sia
n
J
o
u
r
n
a
l
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
a
n
d
Co
m
p
u
ter
S
c
ien
c
e
,
Vo
l.
1
0
,
Iss
u
e
2
,
p
p
.
4
5
6
-
4
6
8
,
(2
0
1
8
).
[1
5
]
Na
g
a
r
a
ju
,
J.,
J
y
o
th
i,
K.,
Ka
rth
ik
,
R.
,
Bh
a
sk
a
ra
R
e
d
d
y
,
P
.
,
V
u
c
h
a
,
M
.
,
“
Distrib
u
te
d
o
p
t
im
a
l
r
e
la
y
se
l
e
c
ti
o
n
in
w
irele
ss
se
n
so
r
n
e
tw
o
rk
s”
,
In
d
o
n
e
sia
n
Jo
u
rn
a
l
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
a
n
d
Co
m
p
u
ter
S
c
ien
c
e
,
V
o
l
.
7
,
Iss
u
e
1
,
p
p
.
7
1
-
7
4
,
(2
0
1
7
).
[1
6
]
Ra
n
ji
th
,
S
.
,
S
h
re
y
a
s,
P
ra
d
e
e
p
Ku
m
a
r,
K.,
Ka
rth
ik
,
R.
,
“
A
u
to
m
a
ti
c
b
o
rd
e
r
a
lert
s
y
ste
m
f
o
r
f
ish
e
r
m
e
n
u
sin
g
G
P
S
a
n
d
G
S
M
tec
h
n
iq
u
e
s”
,
In
d
o
n
e
sia
n
Jo
u
rn
a
l
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
a
n
d
Co
m
p
u
ter
S
c
ien
c
e
,
V
o
l.
7
,
Iss
u
e
1
,
p
p
.
8
4
-
8
9
,
(2
0
1
7
).
Evaluation Warning : The document was created with Spire.PDF for Python.