I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
10
,
No
.
4
,
A
u
g
u
s
t
2020
,
p
p
.
3
8
1
1
~
3
8
1
8
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
10
i
4
.
p
p
3
8
1
1
-
3
8
1
8
3811
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m/in
d
ex
.
p
h
p
/I
JE
C
E
Perf
o
r
m
a
nce
ev
a
lua
tion
o
f
M
a
p
-
r
e
duce
jar
pig
hiv
e
a
nd s
pa
rk
w
ith
m
a
chi
ne lear
ning
using
big da
t
a
Sa
nto
s
h K
u
m
a
r
J
.
1
,
Ra
g
ha
v
endra
B
.
K.
2
,
Ra
g
ha
v
endra
S.
3
,
M
ee
na
k
s
hi
4
1
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
,
KSS
E
M
,
Ba
n
g
a
lo
re
,
Aff
il
iate
d
to
V
T
U Bela
g
a
v
i,
In
d
ia
2
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
,
BG
S
IT
(
A
CU
)
De
e
m
e
d
to
b
e
Un
iv
e
rsity
,
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
,
Ch
rist
De
e
m
e
d
to
b
e
Un
iv
e
rsit
y,
In
d
ia
4
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
,
Ja
in
De
e
m
e
d
to
b
e
U
n
iv
e
rsity
,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Mar
9
,
2
0
1
9
R
ev
i
s
ed
Feb
1
,
2
0
2
0
A
cc
ep
ted
Feb
1
9
,
2
0
2
0
Big
d
a
ta
is
th
e
b
ig
g
e
st
c
h
a
ll
e
n
g
e
s
a
s
we
n
e
e
d
h
u
g
e
p
ro
c
e
ss
in
g
p
o
we
r
s
y
ste
m
a
n
d
g
o
o
d
a
lg
o
rit
h
m
s
to
m
a
k
e
a
d
e
c
isio
n
.
W
e
n
e
e
d
Ha
d
o
o
p
e
n
v
iro
n
m
e
n
t
w
it
h
p
ig
h
iv
e
,
m
a
c
h
in
e
lea
rn
in
g
a
n
d
h
a
d
o
o
p
e
c
o
sy
ste
m
c
o
m
p
o
n
e
n
ts
.
T
h
e
d
a
ta
c
o
m
e
s
f
ro
m
in
d
u
stries
.
M
a
n
y
d
e
v
ice
s
a
ro
u
n
d
u
s
a
n
d
se
n
so
r,
a
n
d
f
ro
m
so
c
ial
m
e
d
ia
sites
.
A
c
c
o
rd
in
g
to
M
c
Ki
n
se
y
T
h
e
re
w
il
l
b
e
a
sh
o
rtag
e
o
f
1
5
0
0
0
0
0
0
b
ig
d
a
ta
p
r
o
f
e
ss
io
n
a
ls
b
y
th
e
e
n
d
o
f
2
0
2
0
.
T
h
e
re
a
re
lo
ts
o
f
tec
h
n
o
lo
g
ies
to
so
lv
e
th
e
p
ro
b
lem
o
f
b
ig
d
a
ta
S
to
ra
g
e
a
n
d
p
ro
c
e
ss
in
g
.
S
u
c
h
tec
h
n
o
lo
g
ies
a
re
A
p
a
c
h
e
H
a
d
o
o
p
,
A
p
a
c
h
e
S
p
a
rk
,
A
p
a
c
h
e
Ka
f
k
a
,
a
n
d
m
a
n
y
m
o
re
.
He
re
w
e
a
n
a
ly
se
th
e
p
ro
c
e
ss
in
g
sp
e
e
d
f
o
r
th
e
4
G
B
d
a
ta
o
n
c
lo
u
d
x
lab
w
it
h
Ha
d
o
o
p
m
a
p
re
d
u
c
e
w
it
h
v
a
rin
g
m
a
p
p
e
rs
a
n
d
re
d
u
c
e
rs
a
n
d
w
it
h
p
ig
sc
ri
p
t
a
n
d
Hiv
e
q
u
e
rries
a
n
d
sp
a
rk
e
n
v
iro
n
m
e
n
t
a
lo
n
g
w
it
h
m
a
c
h
in
e
lea
rn
in
g
tec
h
n
o
lo
g
y
a
n
d
f
ro
m
th
e
re
su
lt
s
w
e
c
a
n
sa
y
th
a
t
m
a
c
h
in
e
lea
rn
in
g
w
it
h
Ha
d
o
o
p
w
il
l
e
n
h
a
n
c
e
th
e
p
ro
c
e
ss
in
g
p
e
rf
o
r
m
a
n
c
e
a
lo
n
g
w
it
h
w
it
h
sp
a
rk
,
a
n
d
a
lso
w
e
c
a
n
sa
y
th
a
t
sp
a
rk
is
b
e
tt
e
r
th
a
n
Ha
d
o
o
p
m
a
p
re
d
u
c
e
p
ig
a
n
d
h
iv
e
,
sp
a
rk
w
it
h
h
iv
e
a
n
d
m
a
c
h
in
e
lea
rn
in
g
w
il
l
b
e
th
e
b
e
st
p
e
rf
o
rm
a
n
c
e
e
n
h
a
n
c
e
d
c
o
m
p
a
re
d
w
it
h
p
ig
a
n
d
h
iv
e
,
Ha
d
o
o
p
m
a
p
re
d
u
c
e
jar
.
K
ey
w
o
r
d
s
:
C
lo
u
d
x
lab
Fli
n
k
Had
o
o
p
Hb
ase
HDFS
Hiv
e
Map
-
r
ed
u
ce
P
ig
Sp
ar
k
Co
p
y
rig
h
t
©
2
0
2
0
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
:
San
to
s
h
K
u
m
ar
J
.
,
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
i
n
ee
r
in
g
,
KSSEM
B
en
g
alu
r
u
VT
U
Un
i
v
er
s
it
y
,
Ma
llas
an
d
r
a,
Kan
a
k
ap
u
r
a
R
o
ad
,
B
an
g
alo
r
e
-
5
6
0
1
0
9
,
I
n
d
ia.
C
o
n
tact:
+9
1
9
0
3
5
6
3
6
6
1
6
E
m
ail:
s
a
n
to
s
h
.
k
u
m
ar
.
j
@
k
s
s
e
m
.
ed
u
.
i
n
1.
I
NT
RO
D
UCT
I
O
N
B
ig
d
ata
r
ef
er
s
to
d
ata
s
ets
w
h
o
s
e
s
ize
is
b
e
y
o
n
d
th
e
ab
ili
t
y
o
f
t
y
p
ical
d
atab
ase
m
an
a
g
e
m
e
n
t
to
o
ls
to
ca
p
tu
r
e,
s
to
r
e,
m
a
n
a
g
e,
a
n
d
an
al
y
ze
.
C
lo
u
d
co
m
p
u
ti
n
g
a
n
d
b
ig
d
ata
,
t
w
o
d
is
r
u
p
tiv
e
tr
en
d
s
a
t
p
r
esen
t,
p
o
s
e
s
ig
n
i
f
ican
t
in
f
l
u
e
n
ce
o
n
cu
r
r
en
t
I
T
in
d
u
s
tr
y
an
d
r
es
ea
r
ch
co
m
m
u
n
itie
s
.
C
lo
u
d
co
m
p
u
ti
n
g
p
r
o
v
id
e
s
m
as
s
i
v
e
co
m
p
u
tatio
n
p
o
w
er
an
d
s
to
r
ag
e
ca
p
ac
it
y
w
h
ic
h
en
ab
le
u
s
er
s
to
d
ep
lo
y
a
p
p
licatio
n
s
w
it
h
o
u
t
in
f
r
astru
ct
u
r
e
i
n
v
est
m
e
n
t.
I
n
te
g
r
ated
w
it
h
clo
u
d
co
m
p
u
ti
n
g
,
d
ata
s
ets
h
a
v
e
b
ec
o
m
e
s
o
lar
g
e
an
d
co
m
p
le
x
t
h
at
it is
a
co
n
s
id
er
ab
le
ch
al
len
g
e
f
o
r
tr
ad
itio
n
al
d
ata
p
r
o
ce
s
s
in
g
t
o
o
ls
to
h
an
d
le
th
e
a
n
al
y
s
i
s
p
ip
elin
e
o
f
t
h
ese
d
ata.
Gen
er
all
y
,
s
u
c
h
d
ata
s
ets
ar
e
o
f
ten
f
r
o
m
v
ar
io
u
s
s
o
u
r
ce
s
an
d
o
f
d
if
f
er
en
t
v
ar
iet
y
s
u
ch
as
u
n
s
tr
u
ct
u
r
ed
s
o
cial
m
ed
ia
co
n
ten
t
an
d
s
e
mi
-
s
tr
u
ctu
r
ed
m
ed
ical
r
ec
o
r
d
s
an
d
b
u
s
i
n
ess
tr
a
n
s
a
ctio
n
s
ar
e
o
f
lar
g
e
v
o
lu
m
e
w
it
h
f
ast d
ata
[
1
]
.
T
h
e
Ma
p
R
ed
u
ce
f
r
a
m
e
w
o
r
k
h
a
s
b
ee
n
w
id
el
y
ad
o
p
ted
b
y
a
lar
g
e
n
u
m
b
er
o
f
co
m
p
an
ies
a
n
d
o
r
g
an
izatio
n
s
to
p
r
o
ce
s
s
h
u
g
e
v
o
lu
m
e
o
f
d
ata
s
ets.
U
n
li
k
e
th
e
tr
ad
itio
n
al
M
ap
R
ed
u
ce
f
r
a
m
e
w
o
r
k
,
t
h
e
o
n
e
in
co
r
p
o
r
ated
w
it
h
clo
u
d
co
m
p
u
ti
n
g
b
ec
o
m
e
s
m
o
r
e
f
lex
ib
le,
s
alab
le
an
d
co
s
t
-
e
f
f
ec
ti
v
e.
A
t
y
p
ica
l
ex
a
m
p
le
is
th
e
Am
az
o
n
E
last
ic
Ma
p
R
e
d
u
ce
s
er
v
ice.
User
s
ca
n
in
v
o
k
e
a
m
az
o
n
E
M
R
to
co
n
d
u
ct
th
eir
Ma
p
-
r
ed
u
ce
co
m
p
u
tatio
n
s
b
ased
o
n
th
e
p
o
w
er
f
u
l
i
n
f
r
a
s
tr
u
ct
u
r
e
o
f
f
er
ed
b
y
Am
az
o
n
.
W
eb
Ser
v
ices
an
d
ar
e
ch
ar
g
ed
in
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
4
,
A
u
g
u
s
t
2020
:
3
8
1
1
-
381
8
3812
p
r
o
p
o
r
tio
n
to
th
e
u
s
a
g
e
o
f
th
e
s
er
v
ice
s
.
I
n
t
h
i
s
w
a
y
,
it
i
s
ec
o
n
o
m
ical
a
n
d
co
n
v
e
n
ien
t
f
o
r
co
m
p
an
ie
s
a
n
d
o
r
g
an
izatio
n
s
to
ca
p
tu
r
e,
s
to
r
e,
o
r
g
an
ize,
s
h
ar
e
a
n
d
a
n
al
y
ze
b
i
g
d
ata
to
g
ai
n
co
m
p
e
titi
v
e
ad
v
a
n
tag
e
s
.
Ma
p
R
ed
u
ce
i
s
c
u
r
r
en
tl
y
a
m
aj
o
r
b
ig
d
ata
p
r
o
ce
s
s
in
g
p
ar
ad
ig
m
.
T
h
e
a
u
th
o
r
s
d
i
s
cu
s
s
ed
ab
o
u
t
ex
i
s
ti
n
g
p
er
f
o
r
m
a
n
ce
m
o
d
els
f
o
r
Ma
p
R
ed
u
ce
o
n
l
y
co
m
p
l
y
w
it
h
s
p
ec
if
ic
w
o
r
k
lo
ad
s
t
h
at
p
r
o
ce
s
s
a
s
m
all
f
r
ac
tio
n
o
f
th
e
en
t
ir
e
d
ata
s
et,
th
u
s
f
ai
lin
g
to
ass
ess
t
h
e
ca
p
ab
ilit
ies
o
f
t
h
e
Ma
p
R
ed
u
ce
p
ar
ad
ig
m
u
n
d
e
r
h
ea
v
y
w
o
r
k
lo
ad
s
th
at
p
r
o
ce
s
s
e
x
p
o
n
en
tiall
y
i
n
cr
ea
s
in
g
d
ata
v
o
l
u
m
es.
T
h
e
au
th
o
r
s
d
i
s
cu
s
s
ed
ab
o
u
t
b
u
il
d
in
g
a
n
d
an
a
l
y
ze
a
s
ca
lab
le
an
d
d
y
n
a
m
ic
b
i
g
d
ata
p
r
o
ce
s
s
in
g
s
y
s
te
m
,
in
c
lu
d
i
n
g
s
to
r
ag
e,
e
x
ec
u
t
io
n
en
g
i
n
e,
a
n
d
q
u
er
y
la
n
g
u
a
g
e.
T
h
e
au
th
o
r
s
m
ai
n
l
y
co
n
ce
n
tr
at
ed
in
th
e
d
esig
n
an
d
i
m
p
le
m
e
n
tatio
n
o
f
a
r
eso
u
r
ce
m
an
a
g
e
m
en
t
s
y
s
te
m
,
d
esig
n
an
d
i
m
p
le
m
en
ta
tio
n
o
f
a
b
en
c
h
m
ar
k
in
g
to
o
l
f
o
r
th
e
Ma
p
R
ed
u
ce
p
r
o
ce
s
s
in
g
s
y
s
te
m
a
n
d
th
e
ev
al
u
atio
n
an
d
m
o
d
eli
n
g
o
f
Ma
p
R
ed
u
ce
u
s
i
n
g
w
o
r
k
lo
ad
s
w
it
h
v
er
y
lar
g
e
d
ata
s
ets [
2
]
Sp
ar
k
is
t
h
e
1
0
0
ti
m
e
s
f
a
s
ter
f
r
a
m
e
w
o
r
k
th
a
n
Ma
p
R
ed
u
ce
an
d
h
d
f
s
i
n
s
to
r
ag
e
an
d
p
r
o
ce
s
s
i
n
g
it
is
also
f
r
a
m
e
w
o
r
k
li
k
e
a
n
y
o
th
er
j
av
a
f
r
a
m
e
w
o
r
k
w
h
ic
h
b
u
il
t
o
n
to
p
o
f
OS
to
u
til
ize
m
e
m
o
r
y
e
f
f
icien
tl
y
a
n
d
th
e
o
t
h
er
d
ev
ices
o
f
C
P
U
e
f
f
icien
tl
y
p
ar
tic
u
lar
l
y
d
esi
g
n
ed
f
r
a
m
e
w
o
r
k
f
o
r
b
ig
d
ata
p
r
o
ce
s
s
i
n
g
.
Sp
ar
k
h
as
m
an
y
ad
v
an
tag
e
s
a
n
d
d
is
ad
v
a
n
tag
e
s
e
f
f
icie
n
t
u
tili
za
tio
n
s
o
f
m
e
m
o
r
y
m
a
n
ag
e
m
e
n
t
is
o
n
e
o
f
t
h
e
d
is
ad
v
a
n
ta
g
e
o
f
s
p
ar
k
w
h
er
ea
s
p
r
o
ce
s
s
i
n
g
b
ig
d
ata
is
ad
v
an
ta
g
es
co
m
p
ar
ed
w
it
h
m
ap
r
ed
u
ce
f
r
a
m
e
w
o
r
k
a
n
d
HDFS
o
f
Had
o
o
p
.
Fli
n
k
is
also
a
f
r
a
m
e
w
o
r
k
f
o
r
all
co
m
p
o
n
en
t
s
o
f
Had
o
o
p
ec
o
-
s
y
s
te
m
.
Fli
n
k
is
t
h
e
f
r
a
m
e
w
o
r
k
f
o
r
Stre
a
m
i
n
g
d
ata,
f
l
in
k
late
n
c
y
is
v
er
y
less
to
p
r
o
ce
s
s
b
ig
d
ata
c
o
m
p
ar
ed
w
it
h
Sp
ar
k
Fli
n
k
h
a
s
m
a
n
y
ad
v
an
tag
e
s
,
it
p
r
o
ce
s
s
es
th
e
d
ata
w
it
h
o
u
t
laten
c
y
l
ik
e
s
p
ee
d
o
f
lig
h
t,
an
d
Me
m
o
r
y
ex
ce
p
tio
n
p
r
o
b
lem
is
also
s
o
lv
ed
b
y
Fli
n
k
.
Fli
n
k
al
s
o
in
ter
ac
t
w
it
h
m
an
y
d
ev
ice
s
o
f
w
h
ic
h
h
a
v
e
d
if
f
er
en
t
s
to
r
a
g
e
s
y
s
te
m
to
p
r
o
ce
s
s
th
e
d
ata,
an
d
it
also
o
p
ti
m
izes t
h
e
p
r
o
g
r
a
m
b
ef
o
r
e
ex
ec
u
t
io
n
.
B
ig
d
ata
P
r
o
ce
s
s
in
g
T
ec
h
n
o
lo
g
y
lik
e
Had
o
o
p
m
ap
r
ed
u
ce
,
f
lin
k
an
d
s
p
ar
k
alo
n
g
w
i
th
ca
ch
in
g
d
at
a
p
r
o
ce
s
s
in
g
e
n
g
i
n
e
an
d
s
c
h
ed
u
ler
as
s
h
o
w
n
i
n
Fi
g
u
r
e
1
.
Da
ta
P
r
o
ce
s
s
in
g
tec
h
n
iq
u
e
li
k
e
d
ata
u
n
d
er
s
ta
n
d
in
g
d
ata
p
ep
lo
r
atio
n
an
d
d
ata
m
o
d
elin
g
ar
e
as
s
h
o
w
n
i
n
Fi
g
u
r
e
2
.
B
ig
d
ata
E
c
o
s
y
s
te
m
co
m
p
o
n
en
t
s
lik
e
p
i
g
h
i
v
e
s
p
ar
k
a
m
b
ar
i z
o
o
k
ee
p
er
m
l lib
Hab
ase
an
d
m
a
n
y
a
s
s
h
o
w
n
i
n
Fi
g
u
r
e
3
.
Fig
u
r
e
1
.
B
ig
d
ata
p
r
o
ce
s
s
in
g
t
ec
h
n
o
lo
g
y
co
m
p
ar
is
io
n
Fig
u
r
e
2
.
Data
an
al
y
s
is
p
r
o
ce
s
s
in
g
s
tep
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
P
erfo
r
ma
n
ce
ev
a
lu
a
tio
n
o
f Ma
p
-
r
ed
u
ce
j
a
r
p
ig
h
ive
a
n
d
s
p
a
r
k
w
ith
.... (
S
a
n
to
s
h
K
u
ma
r
J.
)
3813
Fig
u
r
e
3
.
E
co
s
y
s
te
m
co
m
p
o
n
en
ts
o
f
b
ig
d
ata
2.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
Ma
n
y
a
u
t
h
o
r
o
f
th
e
p
ap
er
s
ai
d
ab
o
u
t
A
p
ac
h
e
Had
o
o
p
th
at
it
is
a
f
r
a
m
e
w
o
r
k
f
o
r
p
r
o
ce
s
s
in
g
lar
g
e
d
is
tr
ib
u
ted
d
ata
s
et
ac
r
o
s
s
cl
u
s
ter
o
f
co
m
p
u
ter
s
a
n
d
s
aid
ab
o
u
t
s
ca
lin
g
t
h
e
cl
u
s
ter
.
D
u
e
to
u
s
e
o
f
s
en
s
o
r
s
ac
r
o
s
s
all
d
ev
ices
an
d
n
et
w
o
r
k
to
o
ls
o
f
th
e
o
r
g
an
izat
io
n
s
g
e
n
er
atin
g
b
ig
d
ata,
all
w
a
n
ted
to
s
to
r
e
an
d
an
aly
ze
w
it
h
o
u
t
in
v
esti
n
g
m
u
c
h
co
s
t
o
n
m
an
a
g
i
n
g
an
d
s
er
v
ice
is
s
u
e
o
f
th
e
s
to
r
ag
e
an
d
p
r
o
ce
s
s
in
g
w
a
n
t
to
d
ep
lo
y
ev
er
y
t
h
i
n
g
o
n
clo
u
d
s
o
t
h
at
cl
o
u
d
m
an
a
g
e
m
e
n
t
o
r
g
an
izatio
n
s
w
ill
ta
k
e
ca
r
e
o
f
it,
t
h
ese
co
m
p
a
n
ie
s
ca
n
u
til
ize
th
e
d
ata
f
o
r
an
al
y
s
is
a
n
d
e
x
tr
a
ct
u
s
ef
u
l
k
n
o
w
led
g
e
o
u
t o
f
it.
Ma
p
R
ed
u
ce
i
s
t
h
e
f
r
a
m
e
w
o
r
k
w
h
ic
h
allo
w
s
lar
g
e
d
ata
to
b
e
s
to
r
ed
ac
r
o
s
s
all
d
ev
ices
a
n
d
p
r
o
ce
s
s
ed
b
y
d
e
v
ice
s
m
ap
f
u
n
ctio
n
s
w
il
l
d
is
tr
ib
u
t
e
th
e
d
ata
an
d
s
to
r
e
ac
r
o
s
s
th
e
d
ev
ices
w
h
er
e
a
r
ed
u
ce
w
ill
p
r
o
ce
s
s
th
e
q
u
er
y
o
f
t
h
e
clien
t
it
w
o
r
k
s
o
n
b
ases
o
f
th
e
k
e
y
v
al
u
e
p
air
.
E
ac
h
li
n
e
w
i
ll
b
e
tr
ea
ted
as
k
e
y
a
n
d
v
al
u
e
t
h
at
is
f
ir
s
t
w
o
r
d
is
t
h
e
k
e
y
an
d
r
es
t
all
w
ill
b
e
v
alu
e
w
h
en
e
v
er
clie
n
t
r
eq
u
est
to
p
r
o
ce
s
s
th
e
lar
g
e
d
ata
f
ir
s
t
clien
t
w
il
l
ap
p
r
o
ac
h
th
e
n
a
m
e
n
o
d
e
n
a
m
e
n
o
d
e
w
ill
r
esp
o
n
d
to
clien
t
w
it
h
av
ailab
le
f
r
ee
n
o
d
es
af
ter
th
at
m
ap
p
er
f
u
n
c
tio
n
s
b
y
clie
n
t
w
ill
w
r
ite
d
ata
to
r
esp
ec
tiv
e
d
ata
n
o
d
es,
an
d
w
h
en
e
v
er
clie
n
t
w
an
t
to
p
r
o
ce
s
s
th
e
d
ata
it
r
eq
u
est
to
n
a
m
e
n
o
d
e
j
o
b
tr
ac
k
er
th
en
j
o
b
tr
ac
k
er
w
ill
co
m
m
u
n
icate
to
n
a
m
e
n
o
d
e
to
g
et
d
ata
i
n
f
o
r
m
atio
n
s
to
r
ag
e
th
en
it
w
i
ll
a
s
s
i
g
n
j
o
b
s
to
task
tr
ac
k
er
to
p
r
o
ce
s
s
th
e
j
o
b
b
y
n
a
m
e
n
o
d
es
w
ill
p
r
o
ce
s
s
th
e
tas
k
b
y
t
h
eir
a
v
a
ilab
le
d
ata
t
h
en
o
n
e
o
f
t
h
e
n
o
d
e
w
ill
ag
g
r
e
g
ate
th
e
r
esu
lt a
n
d
g
iv
e
t
h
e
r
es
u
lt t
o
clien
t
[
3
]
.
Had
o
o
p
’
s
o
p
tim
iza
tio
n
f
r
a
m
e
w
o
r
k
f
o
r
Ma
p
R
ed
u
ce
clu
s
te
r
s
th
e
au
t
h
o
r
o
f
th
e
p
ap
er
s
t
ates
m
o
s
t
w
id
el
y
u
s
ed
f
r
a
m
e
w
o
r
k
s
f
o
r
d
ev
elo
p
in
g
Ma
p
R
ed
u
ce
b
ased
ap
p
licatio
n
s
is
A
p
ac
h
e
Had
o
o
p
.
B
u
t
d
ev
elo
p
er
s
f
i
n
d
n
u
m
b
er
o
f
c
h
alle
n
g
e
s
i
n
t
h
e
Had
o
o
p
f
r
a
m
e
w
o
r
k
,
w
h
ic
h
ca
u
s
es
p
r
o
b
le
m
to
m
an
a
g
e
m
e
n
t
o
f
t
h
e
r
eso
u
r
ce
s
in
t
h
e
Ma
p
R
ed
u
ce
clu
s
ter
t
h
at
w
ill
o
p
ti
m
ize
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
Ma
p
R
ed
u
ce
ap
p
licati
o
n
s
r
u
n
n
i
n
g
o
n
i
t
.
T
h
e
co
n
s
tr
ain
t
s
i
n
th
e
r
e
s
o
u
r
c
e
allo
ca
tio
n
p
r
o
ce
s
s
i
n
th
e
Ma
p
R
ed
u
ce
p
r
o
g
r
a
m
m
i
n
g
m
o
d
el
f
o
r
lar
g
e
-
s
ca
le
d
ata
p
r
o
ce
s
s
in
g
f
o
r
s
p
ee
d
u
p
p
er
f
o
r
m
an
ce
.
T
h
e
n
o
v
el
tec
h
n
iq
u
e
c
alled
D
y
n
a
m
ic
ap
p
r
o
ac
h
f
o
r
p
er
f
o
r
m
i
n
g
s
p
ee
d
u
p
o
f
th
e
av
ailab
le
r
eso
u
r
ce
s
.
I
t
co
n
tain
s
th
e
t
w
o
m
aj
o
r
o
p
e
r
a
tio
n
s
;
t
h
e
y
ar
e
s
lo
t
u
til
izatio
n
o
p
tim
izat
io
n
an
d
u
tili
za
t
io
n
ef
f
icie
n
c
y
o
p
ti
m
iza
tio
n
.
T
h
e
Dy
n
a
m
ic
tech
n
iq
u
e
h
as
t
h
e
th
r
ee
s
lo
t
allo
ca
tio
n
t
ec
h
n
iq
u
es
t
h
e
y
ar
e
d
y
n
a
m
ic
h
ad
o
o
p
s
lo
t
allo
ca
tio
n
s
p
ec
u
lati
v
e
ex
ec
u
tio
n
p
er
f
o
r
m
an
ce
b
alan
ci
n
g
an
d
S
l
o
t
P
r
e
-
s
ch
ed
u
l
in
g
.
I
t
ac
h
iev
e
s
a
p
er
f
o
r
m
a
n
ce
s
p
ee
d
u
p
b
y
a
f
ac
to
r
o
f
o
v
er
th
e
r
ec
en
tl
y
p
r
o
p
o
s
ed
co
s
t
-
b
ased
o
p
tim
izatio
n
ap
p
r
o
ac
h
.
I
n
ad
d
itio
n
,
p
er
f
o
r
m
an
ce
b
en
e
f
it i
n
cr
ea
s
es
w
it
h
i
n
p
u
t d
ata
s
et
s
ize
[
4
]
.
P
er
f
o
r
m
a
n
ce
E
v
al
u
atio
n
o
f
Had
o
o
p
an
d
Or
ac
le
P
latf
o
r
m
f
o
r
Di
s
tr
ib
u
ted
P
ar
allel
P
r
o
ce
s
s
i
n
g
i
n
b
ig
d
ata
E
n
v
ir
o
n
m
e
n
t
s
T
h
e
au
th
o
r
s
d
is
c
u
s
s
ed
ab
o
u
t
t
h
e
R
ed
u
ce
d
ata
ce
n
ter
i
m
p
le
m
e
n
tatio
n
co
s
t
u
s
in
g
co
m
m
o
d
it
y
h
ar
d
w
ar
e
to
p
r
o
v
id
e
h
ig
h
p
er
f
o
r
m
a
n
ce
C
o
m
p
u
ti
n
g
.
D
is
tr
ib
u
ted
p
r
o
ce
s
s
in
g
o
f
lar
g
e
d
ata
s
e
ts
ac
r
o
s
s
clu
s
ter
s
o
f
co
m
p
u
ter
s
u
s
i
n
g
d
is
tr
ib
u
ted
an
d
p
ar
allel
co
m
p
u
ti
n
g
ar
ch
i
tectu
r
e.
An
d
also
th
e
au
th
o
r
s
d
o
th
e
P
er
f
o
r
m
a
n
ce
co
m
p
ar
is
o
n
o
f
d
is
tr
ib
u
ted
p
ar
allel
co
m
p
u
tin
g
s
y
s
te
m
an
d
tr
ad
itio
n
a
l
s
i
n
g
le
co
m
p
u
t
in
g
s
y
s
te
m
to
w
ar
d
s
a
n
o
p
ti
m
ized
b
ig
d
ata
p
r
o
ce
s
s
in
g
s
y
s
te
m
au
th
o
r
o
f
th
e
p
ap
er
s
tated
th
at
t
h
e
au
th
o
r
s
d
is
c
u
s
s
ed
ab
o
u
t
r
eso
u
r
ce
m
an
a
g
e
m
e
n
t
s
y
s
te
m
f
o
r
Ma
p
R
ed
u
ce
b
ase
d
p
r
o
ce
s
s
in
g
s
y
s
te
m
f
o
r
d
ep
lo
y
i
n
g
a
n
d
r
esizi
n
g
Ma
p
R
ed
u
ce
clu
s
ter
s
B
en
c
h
m
ar
k
i
n
g
to
o
l
f
o
r
th
e
Ma
p
R
ed
u
ce
p
r
o
ce
s
s
in
g
s
y
s
te
m
e
v
al
u
at
io
n
an
d
m
o
d
eli
n
g
o
f
Ma
p
R
ed
u
ce
u
s
i
n
g
w
o
r
k
lo
ad
s
w
it
h
v
er
y
lar
g
e
d
ata
s
ets
an
d
t
o
o
p
tim
ize
th
e
Ma
p
R
ed
u
ce
s
y
s
te
m
to
ef
f
icie
n
tl
y
p
r
o
ce
s
s
ter
ab
y
tes
o
f
d
ata.
Ov
e
r
v
ie
w
o
n
p
er
f
o
r
m
an
ce
test
in
g
ap
p
r
o
ac
h
in
b
ig
d
ata
th
e
au
th
o
r
s
tated
th
at
m
a
n
y
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
4
,
A
u
g
u
s
t
2020
:
3
8
1
1
-
381
8
3814
o
r
g
an
izatio
n
s
ar
e
f
ac
i
n
g
ch
all
en
g
e
s
in
f
ac
i
n
g
te
s
t
s
tr
ate
g
ie
s
f
o
r
s
tr
u
ct
u
r
ed
an
d
u
n
s
tr
u
ct
u
r
ed
d
ata
v
alid
atio
n
,
s
etti
n
g
u
p
o
p
ti
m
al
te
s
t
e
n
v
ir
o
n
m
e
n
t,
w
o
r
k
i
n
g
w
it
h
n
o
n
r
el
atio
n
al
d
atab
ase
a
n
d
p
er
f
o
r
m
in
g
n
o
n
f
u
n
ct
io
n
a
l
test
i
n
g
.
T
h
ese
ch
a
llen
g
es
ca
u
s
e
p
o
o
r
q
u
ality
o
f
d
ata
in
p
r
o
d
u
ctio
n
,
d
ela
y
i
n
i
m
p
le
m
e
n
ta
t
io
n
an
d
in
cr
ea
s
e
i
n
co
s
t.
Ma
p
R
ed
u
ce
p
r
o
v
id
es
a
p
ar
allel
an
d
s
ca
lab
le
p
r
o
g
r
a
m
m
in
g
m
o
d
el
f
o
r
d
ata
-
in
te
n
s
i
v
e
b
u
s
i
n
es
s
a
n
d
s
cien
t
if
ic
ap
p
licatio
n
s
.
T
o
o
b
tain
t
h
e
ac
tu
a
l
p
er
f
o
r
m
a
n
ce
o
f
b
ig
d
ata
ap
p
licatio
n
s
,
s
u
c
h
as
r
esp
o
n
s
e
ti
m
e,
m
ax
i
m
u
m
o
n
lin
e
u
s
er
d
ata
ca
p
ac
it
y
s
ize,
a
n
d
a
ce
r
tain
m
a
x
i
m
u
m
p
r
o
ce
s
s
in
g
ca
p
ac
it
y
[
5
]
.
T
h
e
p
ap
er
au
th
o
r
s
d
is
cu
s
s
ed
b
ig
d
ata
an
d
co
m
p
u
ti
n
g
clo
u
d
m
a
n
a
g
e
m
e
n
t
ap
p
l
ian
ce
s
a
n
d
th
e
p
r
o
ce
s
s
i
n
g
p
r
o
b
le
m
s
o
f
b
i
g
d
ata,
w
it
h
r
e
f
er
en
ce
to
co
m
p
u
tin
g
clo
u
d
,
d
atab
ase
o
f
clo
u
d
,
clo
u
d
ar
ch
itec
tu
r
e,
Ma
p
R
ed
u
ce
o
p
ti
m
izatio
n
tech
n
iq
u
es
[
6
]
.
T
h
e
au
th
o
r
s
d
is
cu
s
s
ed
th
e
R
eso
u
r
ce
m
a
n
a
g
e
m
e
n
t
Ma
p
p
er
s
an
d
R
ed
u
ce
-
b
ased
ap
p
licatio
n
s
p
r
o
ce
s
s
in
g
to
d
ep
lo
y
a
n
d
r
esizin
g
Ma
p
R
ed
u
ce
B
en
c
h
m
ar
k
in
g
ap
p
licatio
n
s
a
n
d
to
o
l
ar
e
u
s
ed
f
o
r
th
e
Ma
p
R
ed
u
ce
p
r
o
ce
s
s
i
n
g
to
ex
te
n
t
t
h
e
M
ap
R
ed
u
ce
e
n
ac
t
m
en
t
u
s
i
n
g
w
o
r
k
lo
ad
s
with
b
i
g
d
ata
a
n
d
to
o
p
tim
ize
th
e
Ma
p
R
ed
u
ce
to
p
r
o
ce
s
s
ter
ab
y
tes
o
f
d
ata
p
r
o
f
icien
tl
y
an
d
C
o
s
t
Op
ti
m
izat
io
n
s
f
o
r
W
o
r
k
f
lo
w
s
i
n
th
e
C
lo
u
d
[
7
,
8
]
.
T
h
e
au
th
o
r
s
d
is
cu
s
s
ed
ab
o
u
t
s
o
f
t
w
ar
e
to
ex
p
an
d
th
e
s
ca
lab
ilit
y
o
f
d
ata
an
al
y
tics
,
C
h
alle
n
g
es
Av
ailab
ilit
y
,
p
ar
titi
o
n
i
n
g
,
v
i
r
tu
aliza
tio
n
an
d
s
ca
lab
ilit
y
,
d
is
tr
ib
u
tio
n
,
an
d
elast
icit
y
an
d
p
er
f
o
r
m
a
n
ce
b
o
tt
len
ec
k
s
f
o
r
m
an
a
g
i
n
g
b
ig
d
ata
[
9
]
.
T
h
e
au
th
o
r
s
s
aid
ab
o
u
t
B
en
ch
m
ar
k
i
n
g
a
s
ev
er
al
o
f
h
i
g
h
-
p
er
f
o
r
m
an
c
e
co
m
p
u
ti
n
g
(
HP
C
)
ar
ch
itect
u
r
es
f
o
r
d
ata,
n
a
m
e
n
o
d
e
an
d
d
ata
n
o
d
e
ar
ch
itectu
r
es
w
it
h
lar
g
e
m
e
m
o
r
y
a
n
d
b
an
d
w
id
t
h
ar
e
b
etter
s
u
ited
f
o
r
b
ig
d
ata
an
aly
t
ics
o
n
HP
C
h
/
w
an
d
B
u
d
g
et
-
Dr
i
v
e
n
Sch
ed
u
l
in
g
A
l
g
o
r
ith
m
s
f
o
r
B
atch
es
o
f
Ma
p
R
ed
u
ce
J
o
b
s
i
n
Hete
r
o
g
e
n
eo
u
s
C
lo
u
d
s
[
1
0
,
1
1
]
.
Ma
p
R
ed
u
ce
p
r
o
v
id
es
a
p
ar
allel
an
d
s
ca
lab
l
e
p
r
o
g
r
am
m
i
n
g
m
o
d
el
f
o
r
d
ata
-
i
n
ten
s
i
v
e
b
u
s
i
n
es
s
a
n
d
s
cie
n
ti
f
i
c
ap
p
licatio
n
s
.
T
o
o
b
tain
t
h
e
a
ctu
al
p
er
f
o
r
m
an
c
e
o
f
b
ig
d
ata
ap
p
licatio
n
s
,
s
u
c
h
as
r
esp
o
n
s
e
ti
m
e,
m
ax
i
m
u
m
o
n
li
n
e
u
s
er
d
ata
ca
p
ac
it
y
s
ize,
an
d
a
ce
r
tain
ma
x
i
m
u
m
p
r
o
ce
s
s
in
g
ca
p
ac
it
y
[
1
2
].
On
th
e
o
th
er
p
ap
er
au
th
o
r
h
av
e
d
is
c
u
s
s
ed
ab
o
u
t
th
e
p
ar
allel
p
r
o
ce
s
s
in
g
tech
n
iq
u
es
[
13
]
.
Oth
er
a
u
t
h
o
r
o
f
th
e
p
ap
er
d
is
cu
s
s
ed
ab
o
u
t
p
er
f
o
r
m
a
n
ce
i
s
s
u
e
w
it
h
C
lo
u
d
an
d
b
ig
d
ata
[
1
4
]
.
T
h
e
au
th
o
r
s
aid
ab
o
u
t
tesi
n
g
tech
n
iq
u
e
s
an
d
p
er
f
o
r
m
a
n
c
e
en
h
a
n
c
e
m
e
n
t
p
ar
a
m
eter
s
[
1
5
]
an
d
th
e
ao
th
er
au
th
o
r
s
d
is
c
u
s
s
ed
ab
o
u
t
m
u
lt
ico
r
e
ar
ch
itectu
r
e
o
f
Had
o
o
p
p
er
f
o
r
m
a
n
ce
[
1
6
].
T
h
e
au
th
o
r
d
is
cu
u
s
ed
ab
o
u
t
th
e
Ma
c
h
i
n
e
lear
n
in
g
tech
n
iq
u
es
w
it
h
Had
o
o
p
m
a
y
e
n
h
a
n
c
es
t
h
e
p
er
f
o
r
m
a
n
ce
[
1
7
].
T
h
e
au
th
o
r
o
f
t
h
e
p
ap
er
s
aid
ab
o
u
t
Had
o
o
p
s
elf
tu
n
i
n
g
m
ap
p
er
an
d
r
ed
u
ce
r
w
it
h
m
la
n
d
clu
s
ter
s
o
f
ar
ch
i
tectu
r
an
d
o
p
tim
izatio
n
o
f
b
i
g
d
ata
p
er
f
o
r
m
a
n
ce
p
ar
a
m
eter
s
[
1
8
,
1
9
].
T
h
e
au
t
h
o
r
d
is
cu
s
s
ed
t
h
e
p
er
f
o
r
m
a
n
ce
w
i
th
o
r
ac
le
an
d
Had
o
o
p
an
d
s
aid
Had
o
o
p
en
h
an
ce
s
t
h
e
p
er
f
o
r
m
an
ce
[
2
0
]
.
T
h
e
au
th
o
r
s
d
is
cu
s
s
e
d
Map
-
r
ed
u
ce
ex
ec
u
tio
n
ti
m
e
B
ig
.
tx
t
i
n
p
u
t
f
ile.
W
ith
clo
u
d
x
la
b
Had
o
o
p
b
ig
d
ata
f
r
a
m
e
w
o
r
k
[
2
1
]
.
T
h
e
au
t
h
o
r
s
d
is
c
u
s
s
ed
Ma
p
-
r
ed
u
ce
ex
ec
u
tio
n
ti
m
e
R
a
m
a
y
a
n
a
tex
t
i
n
p
u
t
f
ile.
W
ith
clo
u
d
x
la
b
Had
o
o
p
b
ig
d
at
a
f
r
a
m
e
w
o
r
k
[
2
2
].
T
h
e
au
th
o
r
d
is
cu
s
s
ed
ab
o
u
t
th
e
A
W
S
C
o
s
tb
ased
Op
ti
m
iza
tio
n
o
f
Ma
p
-
R
ed
u
ce
P
r
o
g
r
am
s
m
a
y
e
n
h
a
n
ce
th
e
p
er
f
o
r
m
a
n
ce
[
2
3
].
T
h
e
au
th
o
r
s
aid
ab
o
u
t
ef
f
icie
n
t
u
tili
za
tio
n
o
f
m
ap
p
er
an
d
r
ed
u
ce
r
m
a
y
en
h
an
ce
t
h
e
p
er
f
o
r
m
an
ce
[
24
]
.
T
h
e
au
th
o
r
d
is
cu
s
s
ed
ab
o
u
t
R
eso
u
r
ce
-
a
war
e
A
d
ap
ti
v
e
Sc
h
ed
u
lin
g
f
o
r
Ma
p
R
ed
u
ce
C
lu
s
ter
s
[
25
].
T
h
e
au
t
h
o
r
d
is
c
u
s
s
ed
ab
o
u
t p
er
f
o
r
m
a
n
ce
o
f
P
ig
h
i
v
e
an
d
Had
o
o
p
j
ar
f
ile
[
2
6
]
.
3.
RE
SU
L
T
S
A
ND
D
I
SCU
SS
I
O
N
Fig
u
r
e
4
i
s
t
h
e
Ma
p
R
ed
u
ce
ar
ch
itect
u
r
al
f
r
a
m
e
w
o
r
k
f
o
r
w
o
r
d
co
u
n
t
p
r
o
g
r
a
m
w
h
er
e
h
u
g
e
i
n
p
u
t
f
i
le
i
s
s
p
lit
as
b
lo
ck
s
o
f
p
a
g
es
an
d
e
ac
h
p
ag
es
s
p
li
t
as
li
n
es
an
d
ea
ch
lin
e
s
s
p
it
as
w
o
r
d
s
b
y
s
p
ac
es
to
g
et
n
u
m
b
er
o
f
w
o
r
d
s
t
h
e
n
all
w
o
r
d
s
ar
e
s
h
u
f
f
led
w
i
th
all
th
e
d
ata
n
o
d
es
m
ap
p
er
s
t
o
co
u
n
t
o
cc
u
r
r
en
ce
o
f
ea
ch
w
o
r
d
s
i
n
ea
c
h
d
ata
n
o
d
es
f
in
all
y
u
s
in
g
r
ed
u
c
es
co
m
b
i
n
es
t
h
e
r
esu
l
ts
ac
h
ie
v
ed
b
y
ea
ch
d
ata
n
o
d
e.
R
u
n
n
i
n
g
C
h
ar
ac
ter
C
o
u
n
t
J
o
b
in
C
lo
u
d
x
lab
h
ad
o
o
p
j
ar
/u
s
r
/
h
d
p
/2
.
3
.
4
.
0
-
3
4
8
5
/h
ad
o
o
p
-
m
ap
r
e
d
u
ce
/
h
ad
o
o
p
-
s
tr
ea
m
in
g
.
j
ar
-
in
p
u
t
/d
ata/
m
r
/
w
o
r
d
co
u
n
t
/in
p
u
t
-
o
u
tp
u
t
letter
_
co
u
n
t
-
m
ap
p
er
m
ap
p
er
.
p
y
-
f
i
le
m
ap
p
er
.
p
y
-
r
ed
u
ce
r
r
ed
u
ce
r
.
p
y
f
ile
r
ed
u
ce
r
.
p
y
.
T
h
e
T
ab
le
1
s
h
o
w
s
t
h
e
o
u
t
o
f
th
e
c
h
ar
ac
ter
co
u
n
t
j
o
b
,
w
h
ic
h
r
ea
d
s
t
h
e
i
n
p
u
t
f
ile
a
n
d
ca
lc
u
late
t
h
e
n
u
m
b
er
o
f
o
cc
u
r
r
en
ce
s
o
f
th
e
c
h
ar
ac
ter
a
n
d
s
to
r
e
th
e
o
u
tp
u
t
i
n
o
u
tp
u
t
f
i
le.
Fig
u
r
es
4
-
7
s
h
o
w
s
th
e
e
x
ec
u
tio
n
ti
m
e
o
f
w
o
r
d
co
u
n
t p
r
o
g
r
a
m
o
f
p
ig
s
cr
ip
t a
n
d
Hiv
e
Q
u
er
y
.
First,
w
e
cr
ea
te
a
tab
le
ca
lled
d
o
c
th
e
n
w
il
l lo
ad
a
in
p
u
t
f
ile
a
f
ter
th
at
w
o
r
d
co
u
n
t
q
u
er
y
p
r
o
g
r
am
e
x
ec
u
tio
n
w
h
ich
s
h
o
w
s
a
ti
m
e
o
f
1
4
Sec
to
e
x
ec
.
T
o
tal
o
f
2
0
Sec
to
ex
ec
u
te
a
w
o
r
d
co
u
n
t
p
r
o
g
r
a
m
f
o
r
in
p
u
t
f
ile
(
1
4
s
ec
+
6
s
ec
=
2
0
Sec)
.
T
o
tal
o
f
3
6
s
ec
+
1
6
s
ec
=
5
2
s
ec
o
f
ti
m
e
to
ex
ec
u
te
t
h
e
w
o
r
d
co
u
n
t
p
r
o
g
r
a
m
f
o
r
in
p
u
t
f
ile.
T
ab
le
1
s
h
o
w
s
th
e
c
h
ar
ac
ter
s
an
d
its
c
o
u
n
t
o
n
m
ap
r
ed
u
ce
Had
o
o
p
af
ter
ex
ec
u
tio
n
.
Ma
p
r
ed
u
ce
f
r
a
m
e
w
o
r
k
f
o
r
th
e
w
o
r
d
co
u
n
t
as
s
h
o
w
n
i
n
F
i
g
u
r
e
4
,
h
u
g
e
in
p
u
t
d
ata
is
d
iv
id
ed
an
d
g
iv
e
n
to
m
ap
p
er
b
ased
o
n
k
ey
v
al
u
e
p
air
f
o
r
th
e
d
ata.
T
h
en
th
e
s
u
f
f
le
ac
tio
n
later
r
ed
u
ce
r
w
ill
b
e
u
s
ed
f
o
r
co
m
b
i
n
i
n
g
t
h
e
r
es
u
lts
o
f
m
ap
p
er
.
T
h
e
w
o
r
d
co
u
n
t
p
r
o
g
r
a
m
is
g
i
v
en
f
o
r
th
e
ex
ec
u
tio
n
w
i
th
Sp
ar
k
Hi
v
e
an
d
m
ac
h
in
e
lear
n
in
g
q
u
er
y
a
n
d
E
x
ec
u
t
io
n
ti
m
e
o
f
6
s
ec
o
n
d
s
as
s
h
o
w
n
i
n
Fi
g
u
r
e
5
.
T
h
e
w
o
r
d
co
u
n
t
p
r
o
g
r
a
m
is
g
iv
e
n
f
o
r
th
e
e
x
ec
u
t
io
n
w
it
h
Sp
ar
k
Hiv
e
q
u
er
y
an
d
E
x
ec
u
tio
n
ti
m
e
o
f
1
4
s
ec
o
n
d
s
as
s
h
o
w
n
i
n
Fi
g
u
r
e
6
.
T
h
e
w
o
r
d
co
u
n
t
p
r
o
g
r
a
m
i
s
g
i
v
en
f
o
r
th
e
e
x
ec
u
tio
n
w
it
h
Sp
ar
k
Hiv
e
q
u
er
y
a
n
d
E
x
ec
u
tio
n
ti
m
e
o
f
1
6
s
ec
o
n
d
s
as
s
h
o
w
n
i
n
F
ig
u
r
e
7
.
T
h
e
w
o
r
d
co
u
n
t
p
r
o
g
r
a
m
i
s
g
iv
e
n
f
o
r
th
e
e
x
ec
u
t
io
n
w
it
h
P
I
G
q
u
er
y
an
d
E
x
ec
u
tio
n
ti
m
e
o
f
3
6
s
ec
o
n
d
s
as sh
o
w
n
i
n
Fi
g
u
r
e
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
P
erfo
r
ma
n
ce
ev
a
lu
a
tio
n
o
f Ma
p
-
r
ed
u
ce
j
a
r
p
ig
h
ive
a
n
d
s
p
a
r
k
w
ith
.... (
S
a
n
to
s
h
K
u
ma
r
J.
)
3815
T
ab
le
1
.
C
h
ar
ac
ter
C
o
u
n
t o
u
tp
u
t
C
h
a
r
a
c
t
e
r
a
n
d
i
t
s
C
o
u
n
t
C
h
a
r
a
c
t
e
r
a
n
d
i
t
s
C
o
u
n
t
a
.
0
8
0
9
6
n
.
3
6
9
0
1
8
b
.
7
3
1
6
8
o
.
3
8
6
8
6
7
c
.
1
4
4
9
7
4
p
.
9
8
9
1
3
d
.
2
1
5
7
0
6
q
.
4
5
7
1
e
.
6
3
3
8
2
1
r
.
3
0
9
5
5
8
f
.
1
2
0
8
7
5
s
.
3
3
4
9
0
1
g
.
9
6
9
1
6
t
.
4
6
0
7
4
8
h
.
2
9
4
6
8
3
u
.
1
3
8
7
3
2
i
.
3
6
5
6
4
1
v
.
5
2
3
7
8
j
.
6
4
3
6
w
.
1
0
0
8
3
1
k
.
3
2
7
9
8
x
.
9
8
1
0
l
.
1
9
8
6
4
8
y
.
9
0
4
8
1
m.
1
2
7
0
6
3
z
.
3
7
9
6
Fig
u
r
e
4
.
Ma
p
R
ed
u
ce
f
r
a
m
e
wo
r
k
f
o
r
w
o
r
d
co
u
n
t
Fig
u
r
e
5
.
Hiv
e
Qu
er
y
ex
ec
u
tio
n
ti
m
e
6
s
ec
f
o
r
in
p
u
t f
ile
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
4
,
A
u
g
u
s
t
2020
:
3
8
1
1
-
381
8
3816
Fig
u
r
e
6
.
Hiv
e
Qu
er
y
ex
ec
u
tio
n
ti
m
e
1
4
Sec
f
o
r
in
p
u
t
f
ile
Fig
u
r
e
7
.
W
o
r
d
co
u
n
t p
r
o
g
r
a
m
ex
ec
u
tio
n
ti
m
e
1
6
Sec
f
o
r
in
p
u
t f
ile
Fig
u
r
e
8
.
W
o
r
d
co
u
n
t p
r
o
g
r
a
m
ex
ec
u
tio
n
ti
m
e
3
6
Sec
f
o
r
th
e
in
p
u
t
f
ile
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
P
erfo
r
ma
n
ce
ev
a
lu
a
tio
n
o
f Ma
p
-
r
ed
u
ce
j
a
r
p
ig
h
ive
a
n
d
s
p
a
r
k
w
ith
.... (
S
a
n
to
s
h
K
u
ma
r
J.
)
3817
4.
CO
NCLU
SI
O
N
Had
o
o
p
is
s
o
f
t
w
ar
e
f
r
a
m
e
w
o
r
k
f
o
r
v
ar
iet
y
,
v
o
l
u
m
e
a
n
d
v
elo
cit
y
o
f
d
ata
p
r
o
ce
s
s
in
g
,
co
m
p
an
ies
li
k
e
g
o
o
g
le
y
a
h
o
o
an
d
Am
az
o
n
h
av
e
th
eir
o
w
n
f
r
a
m
e
w
o
r
k
f
o
r
p
r
o
ce
s
s
in
g
t
h
e
b
ig
d
ata
also
th
e
y
p
r
o
v
id
e
clo
u
d
b
ased
b
ig
d
ata
ec
o
-
s
y
s
te
m
i
n
f
r
astr
u
ctu
r
e
to
s
to
r
e
(
u
s
in
g
H
DFS)
an
d
p
r
o
ce
s
s
(
u
s
in
g
m
a
p
-
R
ed
u
ce
)
b
i
g
d
ata,
f
r
o
m
ab
o
v
e
r
es
u
lt
s
w
e
s
a
y
t
h
a
t
Hiv
e
Qu
er
y
ex
ec
u
tio
n
ti
m
e
i
s
2
0
Seco
n
d
s
,
w
h
er
ea
s
p
ig
s
c
r
ip
t
ex
ec
u
tio
n
ti
m
e
is
5
2
Seco
n
d
s
f
o
r
th
e
s
a
m
e
i
n
p
u
t
f
ile
w
it
h
o
u
t
m
ac
h
i
n
e
lea
r
n
in
g
an
d
w
it
h
m
ac
h
i
n
e
lear
n
in
g
i
ts
e
n
h
a
n
ce
d
to
1
6
s
ec
o
n
d
s
w
ith
co
m
b
in
at
io
n
o
f
m
l
a
n
d
s
p
ar
k
w
i
th
h
i
v
e
als
o
,
w
e
ca
n
s
a
y
th
at
w
o
r
d
co
u
n
t
p
r
o
g
r
am
f
o
r
g
i
v
e
n
in
p
u
t
f
ile
Hi
v
e
is
b
etter
th
a
n
P
ig
,
Hiv
e
e
n
h
a
n
ce
s
t
h
e
ex
ec
u
ti
o
n
ti
m
e,
f
r
o
m
ab
o
v
e
r
es
u
lt
s
w
e
ca
n
w
e
m
a
y
s
tate
th
at
m
ac
h
i
n
e
lear
n
i
n
g
,
s
p
ar
k
w
it
h
h
iv
e
g
iv
e
s
en
h
a
n
ce
d
p
er
f
o
r
m
a
n
ce
th
a
n
h
ad
o
o
p
m
ap
r
e
d
u
ce
an
d
p
ig
s
p
ar
k
an
d
f
li
n
k
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
I
w
o
u
ld
li
k
e
ex
p
r
ess
m
y
d
ee
p
g
r
atitu
d
e
to
th
e
P
r
in
cip
al,
Ho
D
an
d
Staf
f
o
f
C
o
m
p
u
ter
Scien
ce
a
n
d
E
n
g
i
n
ee
r
i
n
g
d
ep
ar
t
m
e
n
t o
f
K
S
SEM
,
B
an
g
alo
r
e
f
o
r
s
u
p
p
o
r
tin
g
m
e
i
n
d
o
in
g
th
i
s
r
esear
ch
w
o
r
k
.
RE
F
E
R
E
NC
E
S
[1
]
M
d
.
A
r
m
a
n
u
r
Ra
h
m
a
n
,
J.
Ho
ss
e
n
,
“
A
S
u
rv
e
y
o
f
M
a
c
h
in
e
L
e
a
rn
in
g
T
e
c
h
n
iq
u
e
s
f
o
r
S
e
lf
-
tu
n
i
n
g
Ha
d
o
o
p
P
e
rf
o
rm
a
n
c
e
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
Co
m
p
u
ter
E
n
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
8
,
n
o
.
3
,
p
p
.
1
8
5
4
-
1
8
6
2
,
2
0
1
8
.
[2
]
Am
a
n
L
o
d
h
a
,
“
Ha
d
o
o
p
’s
O
p
ti
m
iza
ti
o
n
F
ra
m
e
w
o
rk
f
o
r
M
a
p
Re
d
u
c
e
Clu
ste
rs
,
”
Imp
e
ria
l
J
o
u
r
n
a
l
o
f
In
ter
d
isc
ip
li
n
a
ry
Res
e
a
rc
h
(
IJ
IR)
,
v
o
l
3
,
no
4
,
p
p
.
1
6
4
8
-
1
6
5
0
,
2
0
1
7
.
[3
]
Da
n
W
a
n
g
,
Jia
n
g
c
h
u
a
n
L
iu
,
“
Op
t
im
izin
g
Big
Da
ta
P
ro
c
e
ss
in
g
P
e
rf
o
rm
a
n
c
e
in
th
e
P
u
b
li
c
Cl
o
u
d
:
O
p
p
o
rt
u
n
it
ies
a
n
d
A
p
p
ro
a
c
h
e
s
,
”
IEE
E
Ne
two
rk
,
S
e
p
tem
b
e
r/O
c
to
b
e
r
2
0
1
5
.
[4
]
A
.
K
.
M
.
M
a
h
b
u
b
u
l
Ho
ss
e
n
,
A
.
B.
M
.
M
o
n
iru
z
z
a
m
a
n
e
t.
a
l.
,
“
P
e
rf
o
rm
a
n
c
e
Ev
a
lu
a
ti
o
n
o
f
Ha
d
o
o
p
a
n
d
Ora
c
le
P
latf
o
rm
f
o
r
Distrib
u
ted
P
a
ra
ll
e
l
P
r
o
c
e
ss
in
g
in
Big
Da
ta
En
v
iro
n
m
e
n
ts
,
”
In
tern
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
D
a
ta
b
a
se
T
h
e
o
ry
a
n
d
Ap
p
li
c
a
ti
o
n
,
v
o
l
.
8
,
n
o
.
5
,
p
p
.
1
5
-
26
,
2
0
1
5
.
[5
]
Ch
a
n
g
q
in
g
Ji,
Y
u
L
i,
W
e
n
m
in
g
Qiu
e
t.
a
l.
,
“
Big
Da
ta
P
r
o
c
e
ss
in
g
in
Clo
u
d
C
o
m
p
u
ti
n
g
e
n
v
iro
n
m
e
n
ts
,”
In
ter
n
a
ti
o
n
a
l
S
y
mp
o
si
u
m o
n
Per
v
a
siv
e
S
y
ste
ms
,
Al
g
o
rith
ms
a
n
d
Ne
two
rk
s
,
2
0
1
2
.
[6
]
Am
a
n
L
o
d
h
a
,
“
Ha
d
o
o
p
’s
Op
ti
m
iza
ti
o
n
F
r
a
m
e
w
o
rk
f
o
r
M
a
p
Re
d
u
c
e
Clu
ste
rs”
Imp
e
ria
l
J
o
u
rn
a
l
o
f
I
n
ter
d
isc
ip
li
n
a
ry
Res
e
a
rc
h
(
IJ
IR)
,
v
o
l
-
3
,
no
4
,
2
0
1
7
[7
]
Da
n
W
a
n
g
,
Jia
n
g
c
h
u
a
n
L
iu
,
“
Op
t
im
izin
g
Big
Da
ta
P
ro
c
e
ss
in
g
P
e
rf
o
rm
a
n
c
e
in
th
e
P
u
b
li
c
Cl
o
u
d
:
O
p
p
o
rt
u
n
it
ies
a
n
d
A
p
p
ro
a
c
h
e
s”
IEE
E
Ne
two
rk
,
S
e
p
t
e
m
b
e
r/Oc
to
b
e
r
2
0
1
5
.
[8
]
C.
Zh
o
u
,
B.
S
.
He
,
“
T
ra
n
sf
o
r
m
a
t
io
n
-
b
a
se
d
M
o
n
e
tary
Co
st
Op
ti
m
iz
a
ti
o
n
s
f
o
r
W
o
rk
f
lo
w
s
in
th
e
Clo
u
d
,
”
IEE
E
T
ra
n
sa
c
ti
o
n
o
n
Cl
o
u
d
Co
m
p
u
ti
n
g
,
2
0
1
4
.
[9
]
A
.
K.
M
.
M
a
h
b
u
b
u
lHo
ss
e
n
1
,
A
.
B.
M
.
M
o
n
iru
z
z
a
m
a
n
e
t.
a
l.
“
P
e
rf
o
rm
a
n
c
e
Ev
a
lu
a
ti
o
n
o
f
Ha
d
o
o
p
a
n
d
Ora
c
le
P
latf
o
rm
f
o
r
Distrib
u
ted
P
a
ra
ll
e
l
P
r
o
c
e
ss
in
g
in
Big
Da
ta
En
v
iro
n
m
e
n
ts
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
D
a
ta
b
a
se
T
h
e
o
ry
an
d
Ap
p
li
c
a
ti
o
n
,
v
o
l
.
8
,
n
o
.
5
,
p
p
.
1
5
-
26
,
2
0
1
5
.
[1
0
]
Ch
a
n
g
q
in
g
Ji,
Yu
L
i,
W
e
n
m
in
g
Qiu
e
t.
a
l.
“
Big
Da
ta
P
ro
c
e
ss
in
g
i
n
Clo
u
d
Co
m
p
u
ti
n
g
e
n
v
iro
n
m
e
n
ts,”
In
ter
n
a
ti
o
n
a
l
S
y
mp
o
si
u
m o
n
Per
v
a
siv
e
S
y
ste
m
s,
Al
g
o
rith
ms
a
n
d
Ne
two
rk
s
,
2
0
1
2
[1
1
]
Y.
W
a
n
g
,
W
.
S
h
i,
“
Bu
d
g
e
t
-
Driv
e
n
S
c
h
e
d
u
li
n
g
A
lg
o
rit
h
m
s
f
o
r
Ba
tch
e
s
o
f
M
a
p
Re
d
u
c
e
Jo
b
s
in
He
tero
g
e
n
e
o
u
s
Clo
u
d
s,
”
IEE
E
T
ra
n
sa
c
ti
o
n
o
n
C
l
o
u
d
Co
m
p
u
ti
n
g
,
2
0
1
4
[1
2
]
Bo
g
d
a
n
G
h
iţ
e
t.
a
l.
“
T
o
wa
rd
s
a
n
Op
ti
m
ize
d
Big
Da
t
a
P
ro
c
e
ss
in
g
S
y
ste
m
”
1
3
th
IEE
E/
A
CM
In
tern
a
ti
o
n
a
l
S
y
m
p
o
siu
m
o
n
Clu
ste
r,
Cl
o
u
d
,
a
n
d
G
rid
Co
m
p
u
ti
n
g
,
2
0
1
3
[1
3
]
K
y
o
n
g
-
Ha
Lee
e
t.
a
l.
“
P
a
ra
ll
e
l
Da
ta
P
ro
c
e
ss
in
g
w
it
h
M
a
p
Re
d
u
c
e
:
A
S
u
rv
e
y
,
”
S
IGM
OD
Rec
o
rd
,
v
o
l.
4
0
,
n
o
.
4
,
De
c
e
m
b
e
r
2
0
1
1
.
[1
4
]
Ja
li
y
a
E
k
a
n
a
y
a
k
e
a
n
d
Ge
o
ff
re
y
F
o
x
“
Hig
h
P
e
rf
o
r
m
a
n
c
e
P
a
ra
ll
e
l
C
o
m
p
u
ti
n
g
w
it
h
Clo
u
d
s
a
n
d
Cl
o
u
d
T
e
c
h
n
o
lo
g
ies
”
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
Cl
o
u
d
Co
m
p
u
ti
n
g
,
2
0
0
9
.
[1
5
]
A
sh
les
h
a
S
.
Na
g
d
iv
e
e
t
a
l,
“
O
v
e
rv
ie
w
o
n
P
e
rf
o
r
m
a
n
c
e
T
e
stin
g
Ap
p
r
o
a
c
h
in
Big
Da
ta,”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Ad
v
a
n
c
e
d
Res
e
a
rc
h
in
Co
mp
u
ter
S
c
ien
c
e
,
v
o
l.
5
,
n
o
.
8
,
No
v
–
De
c
,
p
p
.
1
6
5
-
1
6
9
,
2
0
1
4
.
[1
6
]
Y.
Zh
a
n
g
,
“
Op
ti
m
ize
d
ru
n
ti
m
e
s
y
ste
m
s
f
o
r
M
a
p
Re
d
u
c
e
a
p
p
l
ica
ti
o
n
s
in
m
u
lt
i
-
c
o
re
c
lu
ste
rs,
”
T
h
e
sis,
Rice
Un
iv
e
rsit
y
,
T
e
x
a
s.
2
0
1
4
.
[
O
n
li
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s://
w
ww
.
se
m
a
n
ti
c
sc
h
o
lar.o
rg
/p
a
p
e
r/Op
t
i
m
iz
e
d
-
Ru
n
ti
m
e
-
S
y
st
e
m
s
-
f
o
r
-
M
a
p
Re
d
u
c
e
-
in
-
Clu
st
e
rs
-
Zh
a
n
g
/1
0
f
a
1
4
d
4
c
7
8
4
6
b
f
9
b
3
5
e
8
5
0
7
a
8
d
c
d
c
b
7
e
e
7
9
a
6
7
2
[1
7
]
M
d
.
A
r
m
a
n
u
r
Ra
h
m
a
n
,
a
n
d
J.
Ho
ss
e
n
,
“
A
S
u
rv
e
y
o
f
M
a
c
h
in
e
L
e
a
rn
in
g
T
e
c
h
n
iq
u
e
s
f
o
r
S
e
lf
-
t
u
n
i
n
g
Ha
d
o
o
p
P
e
rf
o
rm
a
n
c
e
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
tric
a
l
a
n
d
Co
m
p
u
ter
E
n
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
8
,
n
o
.
3
,
p
p
.
1
8
5
4
-
1
8
6
2
,
Ju
n
e
2
0
1
8
.
[1
8
]
Am
a
n
L
o
d
h
a
,
“
Ha
d
o
o
p
’s
O
p
ti
m
iza
ti
o
n
F
r
a
m
e
w
o
rk
f
o
r
M
a
p
Re
d
u
c
e
Clu
ste
rs,”
Imp
e
ria
l
J
o
u
r
n
a
l
o
f
In
ter
d
isc
ip
li
n
a
ry
Res
e
a
rc
h
(
IJ
IR)
,
v
o
l
-
3
,
n
o
.
-
4
,
p
p
.
1
6
4
8
-
1
6
5
0
,
2
0
1
7
.
[1
9
]
Da
n
W
a
n
g
,
Jia
n
g
c
h
u
a
n
L
iu
,
“
Op
ti
m
izin
g
Big
Da
ta
P
ro
c
e
ss
in
g
P
e
r
f
o
r
m
a
n
c
e
in
th
e
P
u
b
li
c
Clo
u
d
:
Op
p
o
rt
u
n
it
ies
a
n
d
A
p
p
ro
a
c
h
e
s
”
IEE
E
Ne
tw
o
rk
,
S
e
p
tem
b
e
r/O
c
to
b
e
r
2
0
1
5
.
[2
0
]
A
.
K.
M
.
M
a
h
b
u
b
u
l
Ho
ss
e
n
,
A
.
B.
M
.
M
o
n
iru
z
z
a
m
a
n
e
t.
a
l.
,
“
P
e
rf
o
rm
a
n
c
e
Ev
a
lu
a
ti
o
n
o
f
Ha
d
o
o
p
a
n
d
Ora
c
le
P
la
tf
o
rm
f
o
r
Distrib
u
ted
P
a
ra
ll
e
l
P
r
o
c
e
ss
in
g
in
Big
Da
ta
En
v
iro
n
m
e
n
ts
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
D
a
ta
b
a
se
T
h
e
o
ry
a
n
d
Ap
p
li
c
a
ti
o
n
,
v
o
l
.
8
,
n
o
.
5
,
p
p
.
1
5
-
26
,
2
0
1
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
4
,
A
u
g
u
s
t
2020
:
3
8
1
1
-
381
8
3818
[2
1
]
J
.
S
a
n
to
sh
K
u
m
a
r,
S
.
Ra
g
h
a
v
e
n
d
ra
,
B
.
K
.
Ra
g
h
a
v
e
n
d
ra
e
t.
a
l.
,
“
Big
d
a
ta
P
e
rf
o
rm
a
n
c
e
Ev
a
lu
ti
o
n
o
f
M
a
p
-
Re
d
u
c
e
P
ig
a
n
d
Hiv
e
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
E
n
g
i
n
e
e
rin
g
a
n
d
A
d
v
a
n
c
e
d
T
e
c
h
n
o
lo
g
y
(
IJ
EA
T
)
,
v
o
l
-
8
,
n
o
.
-
6
,
A
u
g
u
st
2
0
1
9
.
[2
2
]
J
.
S
a
n
to
sh
K
u
m
a
r,
S
.
Ra
g
h
a
v
e
n
d
ra
,
B
.
K
.
Ra
g
h
a
v
e
n
d
ra
e
t.
a
l.
,
“
Big
d
a
ta
P
ro
c
e
ss
in
g
Co
m
p
a
riso
n
u
sin
g
P
ig
a
n
d
Hiv
e
,
”
I
n
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
C
o
mp
u
ter
S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
(
IJ
CS
E)
,
v
o
l.
7
,
n
o
.
3
,
M
a
rc
h
2
0
1
9
.
[2
3
]
H.
He
ro
d
o
to
u
a
n
d
S
.
Ba
b
u
,
P
r
o
f
il
in
g
,
“
W
h
a
t
-
i
f
A
n
a
l
y
sis,
a
n
d
Co
stb
a
se
d
Op
t
im
iza
ti
o
n
o
f
M
a
p
Re
d
u
c
e
P
ro
g
ra
m
s,”
In
Pro
c
.
o
f
th
e
V
L
DB
E
n
d
o
wme
n
t
,
v
o
l.
4
,
n
o
.
1
1
,
2
0
1
1
.
[2
4
]
Z.
H
.
G
u
o
,
G
.
F
o
x
,
M
.
Z
h
o
u
,
Y.
Ru
a
n
,
“
Im
p
ro
v
in
g
Re
so
u
rc
e
Util
iza
ti
o
n
in
M
a
p
Re
d
u
c
e
,
”
In
I
EE
E
Cl
u
ste
r’1
2
,
p
p
.
4
0
2
-
4
1
0
,
2
0
1
2
.
[2
5
]
J.
P
o
lo
,
C.
Ca
stil
lo
,
D.
Ca
rre
ra
,
e
t
a
l.
,
“
Re
so
u
rc
e
-
a
w
a
r
e
A
d
a
p
ti
v
e
S
c
h
e
d
u
li
n
g
f
o
r
M
a
p
Re
d
u
c
e
Clu
ste
rs,”
I
n
M
id
d
lewa
re
’1
1
,
p
p
.
1
8
7
-
2
0
7
,
2
0
1
1
.
[2
6
]
J
.
S
a
n
t
o
sh
K
u
m
a
r,
S
.
Ra
g
h
a
v
e
n
d
ra
,
B
.
K
.
Ra
g
h
a
v
e
n
d
ra
e
t.
a
l.
,
“
Bi
g
d
a
ta
P
e
rf
o
rm
a
n
c
e
e
v
a
lu
a
ti
o
n
o
f
m
a
p
re
d
u
c
e
p
ig
h
iv
e
,”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
E
n
g
i
n
e
e
rin
g
a
n
d
A
d
v
a
n
c
e
d
T
e
c
h
n
o
lo
g
y
(
IJ
EA
T
)
,
v
o
l.
8
n
o
.
6
,
A
u
g
.
2
0
1
9
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Sa
nto
s
h
K
u
m
a
r
J
.
is
c
u
rre
n
tl
y
w
o
rk
in
g
a
s
A
ss
o
c
iate
P
ro
f
e
ss
o
r
in
th
e
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
a
t
K
.
S
.
S
c
h
o
o
l
o
f
E
n
g
in
e
e
rin
g
a
n
d
M
a
n
a
g
e
m
e
n
t
,
Ba
n
g
a
lo
re
.
Aff
il
iate
d
to
V
T
U
Be
lag
a
v
i,
He
is
p
u
rsu
in
g
P
h
.
D.
i
n
V
T
U,
Be
lg
a
u
m
,
In
d
ia.
He
h
a
s
1
0
y
e
a
rs
o
f
te
a
c
h
in
g
a
n
d
3
y
e
a
rs
o
f
in
d
u
stry
e
x
p
e
rien
c
e
.
He
isIn
tere
ste
d
in
Big
d
a
ta
stre
a
m
i
n
g
a
n
a
l
y
sis
.
His
re
s
e
ra
c
h
to
p
ics
in
c
lu
d
e
sBig
d
a
ta w
it
h
m
a
c
h
in
e
lea
rn
in
g
.
Dr.
Ra
g
ha
v
endra
B
.
K
.
P
u
rsu
e
d
P
.
h
d
F
r
o
m
Dr.
M
G
R
Ed
u
c
a
ti
o
n
a
l
&
Re
se
a
rc
h
In
stit
u
te,
Ch
e
n
n
a
i
a
n
d
M
a
ste
rs
f
ro
m
P
ES
CE,
M
a
n
d
y
a
b
e
n
g
a
lu
ru
u
n
iv
e
rsity
a
n
d
Ba
c
h
e
lo
rs
f
ro
m
G
CE,
Ra
m
a
n
a
g
a
ra
Be
n
g
a
lu
ru
Un
iv
e
rsity
K
a
rn
a
tak
a
He
p
u
b
li
sh
e
d
n
e
a
rl
y
1
5
re
p
u
ted
jo
u
rn
a
ls
a
n
d
His
A
re
a
o
f
in
tere
st
is
Da
ta
m
in
in
g
a
n
d
Big
d
a
ta
He
c
u
rre
n
tl
y
w
o
rk
in
g
in
BG
S
I
T
B
G
Na
g
a
r
(
A
CU)
M
a
n
d
y
a
a
s P
ro
f
e
s
so
r
a
n
d
He
a
d
d
e
p
a
rtm
e
n
t
c
o
m
p
u
ter sc
ien
c
e
a
n
d
e
n
g
in
e
e
rin
g
.
Dr
.
Ra
g
h
a
v
e
n
d
r
a
S
.
is
c
u
rre
n
tl
y
w
o
rk
in
g
a
s
As
so
c
iate
P
ro
f
e
ss
o
r
in
t
h
e
De
p
a
rtm
e
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
a
t
CHR
IS
T
DEEM
ED
T
O
BE
UN
IV
ER
S
IT
Y,
Ba
n
g
a
lo
re
.
He
c
o
m
p
lete
d
h
is
P
h
.
D.
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
f
ro
m
V
TU,
Be
lg
a
u
m
,
In
d
ia
in
2
0
1
7
a
n
d
h
a
s 1
4
y
e
a
rs o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
.
His i
n
tere
sts in
c
lu
d
e
Da
ta M
in
in
g
a
n
d
Big
d
a
ta.
M
e
e
n
a
k
s
h
i
is
c
u
rre
n
tl
y
w
o
rk
in
g
a
s
As
sista
n
t
P
ro
f
e
ss
o
r
in
th
e
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
sp
e
c
ializa
ti
o
n
a
t
Ja
in
De
e
m
e
d
to
b
e
u
n
iv
e
rsity
Ba
n
g
a
lo
re
.
S
h
e
c
o
m
p
lete
d
m
a
ste
r
s
f
ro
m
V
T
U
Be
lag
a
v
i
a
n
d
h
a
s
1
y
e
a
r
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
.
sh
e
is
I
n
tere
ste
d
in
Big
d
a
ta
stre
a
m
in
g
a
n
a
ly
sis
.
Evaluation Warning : The document was created with Spire.PDF for Python.