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.
7
,
No
.
5
,
Octo
b
e
r
2
0
1
7
,
p
p
.
2
7
9
8
~
2
805
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
7
i
5
.
pp
2
7
9
8
-
2
805
2798
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
jo
u
r
n
a
l.c
o
m/o
n
lin
e/in
d
ex
.
p
h
p
/I
JE
C
E
A Nov
el Integra
t
e
d
Fra
m
ew
o
rk
t
o
Ens
ure
Bet
ter
Da
ta Q
ua
lity
in Big
Data
Analy
tics ov
er Cloud
E
nv
iro
n
m
en
t
C.
S.
Sin
dh
u
1
,
Na
g
a
ra
t
na
P
.
H
eg
de
2
1
JN
I
A
S
,
Hy
d
e
ra
b
a
d
,
G
lo
b
a
l
Ac
a
d
e
m
y
o
f
T
e
c
h
n
o
l
o
g
y
,
Ba
n
g
a
lo
re
2
De
p
t
o
f
CS
E,
V
a
sa
v
i
Co
ll
e
g
e
o
f
En
g
in
e
e
rin
g
,
Ib
ra
h
im
b
a
g
h
,
Hy
d
e
r
a
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
Mar
23
,
2
0
1
7
R
ev
i
s
ed
J
u
n
18
,
2
0
1
7
A
cc
ep
ted
Sep
t
11
,
2
0
1
7
W
it
h
a
d
v
e
n
t
o
f
Big
Da
ta
A
n
a
l
y
ti
c
s,
th
e
h
e
a
lt
h
c
a
re
sy
ste
m
is
in
c
re
a
sin
g
l
y
a
d
o
p
t
in
g
th
e
a
n
a
ly
ti
c
a
l
se
rv
ic
e
s
t
h
a
t
is
u
lt
im
a
tel
y
f
o
u
n
d
to
g
e
n
e
ra
te
m
a
ss
iv
e
lo
a
d
o
f
h
ig
h
ly
u
n
stru
c
tu
re
d
d
a
ta.
W
e
re
v
ie
w
e
d
th
e
e
x
isti
n
g
s
y
ste
m
to
f
in
d
th
a
t
th
e
re
a
re
les
se
r
n
u
m
b
e
r
o
f
so
lu
ti
o
n
s
to
w
a
rd
s
a
d
d
re
ss
in
g
th
e
p
r
o
b
lem
s
o
f
d
a
ta
v
a
riet
y
,
d
a
ta
u
n
c
e
rtain
ty
,
a
n
d
d
a
ta
sp
e
e
d
.
I
t
is
im
p
o
rtan
t
t
h
a
t
a
n
e
rro
r
-
f
re
e
d
a
ta
sh
o
u
ld
a
rriv
e
in
a
n
a
ly
ti
c
s.
Ex
isti
n
g
s
y
ste
m
o
ff
e
rs
sin
g
le
-
h
a
n
d
so
lu
ti
o
n
to
w
a
rd
s
sin
g
le
p
latf
o
rm
.
T
h
e
re
f
o
re
,
we
in
tro
d
u
c
e
d
a
n
in
teg
ra
ted
f
ra
m
e
w
o
rk
th
a
t
h
a
s
th
e
c
a
p
a
b
il
it
y
to
a
d
d
re
ss
a
ll
t
h
e
se
th
re
e
p
r
o
b
l
e
m
s
in
o
n
e
e
x
e
c
u
ti
o
n
ti
m
e
.
Co
n
sid
e
rin
g
th
e
s
y
n
th
e
ti
c
b
ig
d
a
ta
o
f
h
e
a
lt
h
c
a
r
e
,
w
e
c
a
rried
o
u
t
t
h
e
in
v
e
stig
a
ti
o
n
to
f
in
d
t
h
a
t
o
u
r
p
r
o
p
o
se
d
sy
st
e
m
u
sin
g
d
e
e
p
lea
rn
in
g
a
rc
h
it
e
c
tu
re
o
f
f
e
rs
b
e
tt
e
r
o
p
ti
m
iza
ti
o
n
o
f
c
o
m
p
u
tatio
n
a
l
re
so
u
rc
e
s.
T
h
e
stu
d
y
o
u
tco
m
e
is
f
o
u
n
d
t
o
o
f
f
e
r
c
o
m
p
a
ra
ti
v
e
l
y
b
e
tt
e
r
re
sp
o
n
se
ti
m
e
a
n
d
h
ig
h
e
r
a
c
c
u
ra
c
y
ra
te
a
s
c
o
m
p
a
re
d
to
e
x
i
stin
g
o
p
ti
m
iza
ti
o
n
tec
h
n
q
iu
e
s
th
a
t
is
f
o
u
n
d
a
n
d
p
ra
c
ti
c
e
d
w
id
e
ly
in
li
tera
tu
re
.
K
ey
w
o
r
d
s
:
B
ig
d
ata
an
al
y
tics
Data
s
p
ee
d
Data
u
n
ce
r
ta
in
t
y
Data
v
ar
iet
y
Co
p
y
rig
h
t
©
2
0
1
7
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
:
Na
m
e
o
f
C
o
r
r
esp
o
n
d
in
g
Au
t
h
o
r
,
Dep
ar
t
m
en
t o
f
E
lectr
ical
an
d
C
o
m
p
u
ter
E
n
g
in
ee
r
i
n
g
,
Natio
n
al
C
h
u
n
g
C
h
e
n
g
Un
i
v
er
s
it
y
,
1
6
8
Un
iv
er
s
it
y
R
o
ad
,
Min
h
s
i
u
n
g
T
o
w
n
s
h
ip
,
C
h
ia
y
i
C
o
u
n
t
y
6
2
1
0
2
,
T
aiw
a
n
,
R
O
C
.
E
m
ail: l
s
n
t
l@
cc
u
.
ed
u
.
t
w
1.
I
NT
RO
D
UCT
I
O
N
C
lo
u
d
co
m
p
u
ti
n
g
i
s
n
o
t
a
n
e
w
n
a
m
e
in
th
e
i
n
d
u
s
tr
y
f
r
o
m
th
e
p
ast
h
al
f
a
d
ec
ad
e.
T
h
er
e
ar
e
v
ar
io
u
s
r
ev
o
lu
tio
n
ar
y
e
n
ter
p
r
is
e
ap
p
li
ca
tio
n
s
t
h
at
ar
e
h
i
g
h
l
y
o
p
ti
m
iz
ed
o
v
er
clo
u
d
en
v
ir
o
n
m
e
n
t
[
1
]
.
T
h
is
o
p
ti
m
izatio
n
is
m
a
in
l
y
i
n
ter
m
s
o
f
h
i
g
h
p
er
f
o
r
m
an
ce
w
h
ic
h
i
s
n
o
r
m
all
y
s
ca
led
in
t
h
e
f
o
r
m
o
f
Ser
v
ice
L
e
v
el
Ag
r
ee
m
e
n
t
(
SLA
)
an
d
Q
u
alit
y
-
of
-
E
x
p
er
i
en
ce
(
Qo
E
)
.
T
h
e
b
ig
g
es
t
b
o
o
n
o
f
clo
u
d
co
m
p
u
t
in
g
is
i
t
s
o
f
f
er
i
n
g
o
f
t
h
e
p
er
v
asiv
e
e
n
v
ir
o
n
m
e
n
t
t
h
at
o
f
f
er
s
ac
ce
s
s
ib
ilit
y
o
f
u
s
er
d
ata
at
an
y
p
o
in
t
o
f
ti
m
e
[
2
]
.
Ho
w
e
v
er
,
th
is
g
r
ea
tes
t
co
n
tr
ib
u
tio
n
o
f
p
er
v
as
iv
e
n
es
s
o
f
d
ata
b
y
clo
u
d
co
m
p
u
ti
n
g
h
as
g
i
v
e
n
r
is
e
to
a
b
i
g
g
e
s
t
i
m
p
ed
i
m
en
t
in
th
e
ar
ea
o
f
d
ata
m
i
n
i
n
g
.
I
t
is
b
ec
a
u
s
e
o
f
s
u
ch
p
er
v
asi
v
e
n
ess
,
m
u
ltip
le
t
y
p
es
o
f
d
ata
b
ea
r
in
g
d
if
f
er
e
n
t
f
o
r
m
s
o
f
in
f
o
r
m
atio
n
,
m
o
d
alit
ies,
an
d
f
o
r
m
at
s
ar
e
n
o
w
in
cr
ea
s
in
g
l
y
p
o
p
u
lated
o
v
er
clo
u
d
s
er
v
er
alm
o
s
t
in
ev
er
y
s
ec
o
n
d
[
3
]
.
C
er
tain
d
ata
a
r
e
p
h
y
s
icall
y
p
u
s
h
ed
to
clo
u
d
b
y
u
s
er
b
u
t
m
aj
o
r
it
y
o
f
t
h
e
d
ata
t
h
at
ex
is
t
s
in
clo
u
d
ar
e
g
en
er
ated
b
y
a
u
to
n
o
m
o
u
s
s
y
s
te
m
e.
g
.
s
e
n
s
o
r
s
[
4
]
.
E
v
e
n
th
o
u
g
h
th
er
e
is
ab
u
n
d
a
n
t
u
s
ag
e
o
f
s
e
n
s
o
r
s
i
n
au
to
m
at
io
n
a
n
d
s
ec
u
r
it
y
s
y
s
te
m
s
,
th
er
e
i
s
o
n
e
m
o
r
e
ar
ea
w
h
er
e
s
en
s
o
r
s
p
la
y
a
v
ital
r
o
le
i.
e.
Hea
lth
ca
r
e
s
ec
to
r
[
5
]
.
T
h
e
m
o
d
er
n
s
y
s
te
m
ex
er
cised
in
m
aj
o
r
it
y
o
f
b
ig
g
er
c
h
ain
s
o
f
h
o
s
p
itals
h
av
e
p
er
f
e
ctl
y
au
to
m
ated
all
ted
io
u
s
a
n
d
m
a
n
u
al
ta
s
k
u
s
in
g
s
en
s
o
r
s
an
d
h
a
v
e
s
i
g
n
i
f
ican
tl
y
t
u
n
ed
t
h
e
r
esp
ec
ti
v
e
i
n
f
o
r
m
a
tio
n
o
v
er
t
h
e
clo
u
d
se
r
v
er
s
i
n
ex
p
lici
t
m
a
n
n
er
.
Ap
ar
t
f
r
o
m
t
h
e
s
e
n
s
o
r
,
th
e
h
o
s
p
ital
also
ad
o
p
ts
th
e
u
s
a
g
e
o
f
E
lectr
o
n
ic
Hea
lt
h
R
ec
o
r
d
(
E
HR
)
an
d
E
lectr
o
n
ic
Me
d
ical
R
ec
o
r
d
(
E
MR),
w
h
i
ch
ca
p
tu
r
es
al
l
th
e
r
ela
ted
in
f
o
r
m
at
io
n
ab
o
u
t
t
h
e
p
atien
t
e.
g
.
i)
p
r
io
r
clin
ical
h
i
s
to
r
y
r
ec
o
r
d
,
i
i)
p
er
s
o
n
al
co
n
tact
r
ec
o
r
d
,
iii)
m
ed
icatio
n
li
s
t
,
iv
)
atten
d
i
n
g
a
n
d
r
ef
er
r
al
d
o
cto
r
in
f
o
r
m
atio
n
,
v
)
in
s
u
r
an
ce
d
etail
s
,
v
i)
s
u
r
g
er
y
-
r
elate
d
in
f
o
r
m
a
tio
n
,
etc.
T
h
e
am
o
u
n
t o
f
s
u
c
h
d
ata
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2088
-
8708
A
N
o
ve
l I
n
teg
r
a
ted
F
r
a
mewo
r
k
to
E
n
s
u
r
e
B
etter
Da
ta
Qu
a
li
ty
i
n
B
ig
Da
ta
A
n
a
lytics o
ve
r
…
(
C
.
S
.
S
in
d
h
u
)
2799
j
u
s
t
f
o
r
o
n
e
p
atien
t
is
s
o
m
a
s
s
iv
e
th
at
i
t
is
r
ea
ll
y
d
i
f
f
ic
u
lt
to
p
er
f
o
r
m
a
n
a
l
y
s
is
.
T
h
e
p
r
o
b
le
m
o
f
d
ata
an
al
y
s
i
s
w
o
r
s
e
n
s
w
h
e
n
co
m
p
lete
h
o
s
p
i
tal
d
ata
i
s
co
n
s
id
er
ed
.
B
asicall
y
,
t
h
e
p
r
i
m
e
r
ea
s
o
n
o
f
t
h
is
p
r
o
b
lem
is
o
b
v
io
u
s
l
y
th
e
s
ize
o
f
t
h
e
d
ata
w
h
ich
co
u
ld
b
e
i
n
ter
m
s
o
f
p
etab
y
tes,
h
o
w
ev
er
,
s
to
r
ag
e
i
s
s
till
n
o
t
a
b
ig
g
er
ch
a
llen
g
e
in
th
e
er
a
o
f
clo
u
d
co
m
p
u
ti
n
g
.
T
h
e
b
ig
g
er
c
h
alle
n
g
e
s
r
elate
d
t
o
p
r
o
ce
s
s
in
g
s
u
ch
d
ata
ar
e
i)
d
ata
v
ar
iet
y
,
ii)
d
ata
u
n
ce
r
tai
n
t
y
,
an
d
iii)
d
ata
v
el
o
cit
y
.
Data
v
ar
iet
y
is
r
elate
d
to
h
eter
o
g
en
eit
y
i
n
th
e
f
o
r
m
s
o
f
th
e
d
ata
w
h
ic
h
m
ak
e
s
th
e
d
ata
h
i
g
h
l
y
n
o
n
-
ap
p
licab
le
to
b
e
s
u
b
j
ec
ted
t
o
an
y
f
o
r
m
s
o
f
d
ata
an
al
y
s
is
.
Data
u
n
ce
r
tai
n
t
y
s
p
ea
k
s
ab
o
u
t
th
e
p
o
s
s
ib
ilit
y
o
f
m
is
s
in
g
d
ata
as
w
ell
a
s
p
r
esen
ce
o
f
a
m
b
ig
u
o
u
s
d
ata
d
u
e
to
w
h
ic
h
t
h
e
co
m
p
lete
v
o
lu
m
e
o
f
d
ata
b
ec
o
m
es
u
n
r
eliab
le.
T
h
is
p
r
o
b
le
m
i
s
q
u
ite
d
if
f
ic
u
lt
to
h
a
n
d
le
a
n
d
i
s
m
a
in
l
y
ca
u
s
ed
d
u
e
to
d
ef
ec
tiv
e
d
ata
s
to
r
ag
e
a
n
d
r
et
r
iev
al
p
r
o
ce
s
s
i
n
g
.
T
h
e
f
in
al
p
r
o
b
lem
i.e
.
d
ata
v
e
lo
cit
y
is
s
o
m
e
th
i
n
g
w
h
ic
h
i
s
q
u
ite
d
if
f
ic
u
lt
to
b
e
s
o
l
v
ed
as
t
h
e
d
ata
ar
r
iv
al
r
ate
is
u
n
k
n
o
w
n
.
A
t
p
r
ese
n
t,
t
h
er
e
is
n
o
s
u
c
h
m
o
d
el
o
r
p
ar
am
eter
t
h
at
h
as
b
ee
n
r
ep
o
r
ted
l
y
u
s
ed
to
g
au
g
e
t
h
e
r
ate
o
f
d
ata
ar
r
iv
al
f
r
o
m
a
p
ar
ticu
la
r
s
o
u
r
ce
in
a
h
ig
h
l
y
d
is
tr
ib
u
ted
n
et
w
o
r
k
s
y
s
te
m
.
A
lt
h
o
u
g
h
,
th
er
e
ar
e
ex
i
s
ti
n
g
s
o
f
t
w
ar
e
f
r
a
m
e
w
o
r
k
s
li
k
e
Ha
d
o
o
p
,
Ma
p
R
ed
u
ce
,
C
ass
a
n
d
r
a,
n
eo
4
j
an
d
m
a
n
y
m
o
r
e,
al
l
o
f
th
e
m
ar
e
m
ai
n
l
y
o
p
en
s
o
u
r
ce
,
w
h
ich
is
n
e
v
er
s
aid
to
b
e
s
ec
u
r
ed
as
th
e
ad
v
er
s
ar
ie
s
m
ain
l
y
u
s
es
o
p
en
s
o
u
r
ce
to
i
n
itiate
attac
k
s
o
v
er
clo
u
d
.
A
p
ar
t
f
r
o
m
t
h
i
s
,
t
h
er
e
ar
e
m
a
n
y
ca
s
es
w
h
er
ein
e
x
i
s
ti
n
g
f
r
a
m
e
w
o
r
k
s
h
av
e
r
ep
o
r
ted
p
r
o
b
lem
s
.
T
h
er
ef
o
r
e,
w
e
r
e
v
ie
w
s
o
m
e
o
f
t
h
e
ex
is
t
in
g
tec
h
n
iq
u
e
s
o
f
d
ata
an
al
y
tical
ap
p
licatio
n
w
h
ic
h
p
o
in
ts
to
w
ar
d
s
m
ed
ical
d
ata
p
r
o
ce
s
s
in
g
.
Fro
m
th
i
s
we
lear
n
th
at
th
is
is
s
till
i
n
it
s
n
a
s
ce
n
t
s
ta
g
e
an
d
h
e
n
ce
th
er
e
i
s
s
co
p
e
f
o
r
ev
o
l
v
i
n
g
u
p
w
ith
a
s
o
lu
tio
n
.
A
s
ig
n
i
f
ic
an
t r
esear
ch
g
ap
o
f
in
te
g
r
ated
f
r
a
m
e
w
o
r
k
to
w
ar
d
s
ad
d
r
ess
in
g
m
aj
o
r
it
y
o
f
p
r
o
b
le
m
s
i
n
d
ata
an
al
y
tics
i
n
cl
o
u
d
in
f
o
u
n
d
.
W
e,
th
er
ef
o
r
e,
p
r
esen
t
a
n
o
v
el
f
r
am
e
w
o
r
k
th
at
h
a
s
t
h
e
ca
p
ab
ilit
y
to
ad
d
r
ess
m
u
ltip
le
p
r
o
b
lem
s
i
n
o
n
e
p
latf
o
r
m
i
n
h
ig
h
l
y
co
s
t
e
f
f
ec
t
iv
e
m
an
n
er
u
s
i
n
g
b
i
g
d
ata
ap
p
r
o
ac
h
.
Se
ctio
n
1
.
1
d
is
cu
s
s
e
s
ab
o
u
t
th
e
ex
is
ti
n
g
liter
atu
r
e
s
w
h
er
e
d
if
f
er
en
t
tech
n
iq
u
es
ar
e
d
is
cu
s
s
ed
f
o
r
en
er
g
y
h
ar
v
esti
n
g
f
o
llo
w
ed
b
y
d
i
s
cu
s
s
io
n
o
f
p
r
o
b
le
m
id
en
ti
f
icatio
n
in
Sectio
n
1
.
2
.
Sectio
n
1
.
3
b
r
ief
s
ab
o
u
t
th
e
p
r
o
p
o
s
ed
co
n
tr
ib
u
tio
n
to
ad
d
r
ess
r
esear
ch
p
r
o
b
lem
s
.
Sectio
n
2
elab
o
r
ates
ab
o
u
t
th
e
alg
o
r
ith
m
i
m
p
le
m
e
n
tatio
n
f
o
l
lo
w
ed
b
y
r
esu
lt
d
is
c
u
s
s
io
n
i
n
Sectio
n
3
.
Fin
all
y
s
u
m
m
ar
y
o
f
t
h
e
p
ap
er
is
d
is
cu
s
s
ed
in
Sec
tio
n
4
.
1
.
1
.
B
a
ck
g
ro
un
d
T
h
is
s
ec
tio
n
d
is
c
u
s
s
es
ab
o
u
t
t
h
e
ex
i
s
ti
n
g
tec
h
n
q
iu
es
to
w
ar
d
s
b
ig
d
ata
an
al
y
tics
.
O
u
r
p
r
io
r
w
o
r
k
[
6
-
9
]
h
av
e
d
is
c
u
s
s
ed
ab
o
u
t t
h
e
e
x
is
t
in
g
tec
h
n
q
i
u
es
p
er
tain
i
n
g
to
s
i
g
n
i
f
ica
n
ce
o
f
cla
s
s
i
f
icat
io
n
ap
p
r
o
ac
h
,
to
o
ls
o
f
b
i
g
d
ata
an
al
y
t
ics,
an
d
ap
p
licab
ili
t
y
o
f
b
i
g
d
ata
an
al
y
tic
s
o
v
er
h
ea
lth
ca
r
e
s
ec
to
r
.
C
h
en
et
a
l.
[
1
0
]
h
av
e
p
r
esen
ted
ar
ch
itect
u
r
e
f
o
r
s
u
p
p
o
r
tab
il
it
y
o
f
ag
i
le
m
e
th
o
d
o
lo
g
ies
o
v
er
b
ig
d
ata.
Dab
ek
a
n
d
C
ab
a
n
[
1
1
]
h
av
e
i
n
tr
o
d
u
ce
d
a
tech
n
iq
u
e
w
h
er
e
a
v
is
u
aliza
ti
o
n
m
ec
h
a
n
is
m
i
s
d
esi
g
n
ed
f
o
r
m
o
d
elin
g
t
h
e
u
s
er
in
ter
ac
tio
n
.
Fiad
in
o
et
al.
[
1
2
]
h
av
e
p
r
esen
ted
a
d
is
c
u
s
s
io
n
to
w
ar
d
s
u
s
i
n
g
ce
ll
u
lar
n
et
w
o
r
k
i
n
t
h
e
v
ie
w
p
o
in
t
o
f
b
ig
d
ata
an
al
y
tic
s
.
Or
d
o
n
ez
e
t
al.
[
1
3
]
h
av
e
in
tr
o
d
u
ce
d
a
tech
n
iq
u
e
th
at
m
ak
e
s
u
s
e
o
f
m
atr
ix
m
u
ltip
licatio
n
in
o
r
d
er
to
p
er
f
o
r
m
s
u
m
m
ar
izatio
n
o
f
b
ig
d
ata
u
s
i
n
g
s
tatis
tical
m
o
d
eli
n
g
.
T
h
e
tech
n
iq
u
e
u
s
es
ar
r
a
y
-
b
ased
o
p
er
ato
r
s
ex
clu
s
iv
el
y
f
o
r
s
p
ar
s
e
as
w
ell
as
f
o
r
d
en
s
e
d
ataset
to
s
h
o
w
m
e
m
o
r
y
co
n
s
u
m
p
tio
n
a
n
d
s
ca
lab
ilit
y
ac
co
m
p
lis
h
m
en
t.
P
au
l
et
al.
[
1
4
]
h
av
e
u
s
ed
t
h
e
b
ig
d
ata
an
al
y
tic
s
in
o
r
d
er
to
s
o
lv
e
th
e
p
r
o
b
lem
a
s
s
o
ciate
d
w
ith
h
u
m
an
b
eh
av
io
u
r
.
T
h
e
au
th
o
r
d
is
c
u
s
s
es
ab
o
u
t
i
n
tr
o
d
u
cin
g
a
s
y
s
te
m
th
at
co
u
ld
ac
t
as
a
co
m
m
u
n
icatio
n
b
r
id
g
e
b
e
t
w
ee
n
t
h
e
in
ter
n
et
-
of
-
t
h
i
n
g
s
ap
p
licatio
n
an
d
d
ata
m
i
n
in
g
tech
n
q
iu
e
s
o
v
er
lar
g
er
d
ata
s
ca
le.
S
h
en
g
et
al.
[
1
5
]
h
av
e
e
m
p
h
as
ized
o
n
th
e
ap
p
licab
ilit
y
o
f
b
ig
d
ata
an
al
y
tics
w
it
h
r
esp
ec
t
to
i
n
f
o
r
m
atio
n
th
eo
r
y
an
d
c
y
b
er
-
p
h
y
s
ical
s
y
s
te
m
.
T
h
is
p
ap
er
p
r
esen
ts
a
s
u
p
er
io
r
f
o
r
m
o
f
m
at
h
e
m
at
ical
m
o
d
eli
n
g
co
n
n
ec
ted
w
it
h
in
f
o
r
m
at
io
n
th
eo
r
y
f
o
llo
w
ed
b
y
s
ig
n
i
f
ica
n
t
c
h
an
n
el
m
o
d
els
t
h
at
co
u
ld
b
e
p
o
ten
tiall
y
h
elp
f
u
l
f
o
r
ex
tr
ac
ti
n
g
k
n
o
w
led
g
e
f
r
o
m
b
ig
g
er
s
ca
le
o
f
d
ata.
T
aw
alb
eh
et
al.
[
1
6
]
h
av
e
d
is
cu
s
s
ed
th
e
g
e
n
er
atio
n
o
f
m
as
s
i
v
e
lo
ad
s
o
f
d
ata
f
r
o
m
h
ea
lth
ca
r
e
s
ec
to
r
a
n
d
h
o
w
s
u
ch
f
o
r
m
s
o
f
d
ata
ca
n
b
e
an
al
y
ze
d
u
s
i
n
g
b
ig
d
ata
a
n
al
y
tics
.
T
h
e
p
r
o
b
lem
s
p
er
tain
i
n
g
to
d
ata
u
n
ce
r
tai
n
t
y
is
b
ein
g
r
ec
en
t
l
y
d
is
c
u
s
s
ed
b
y
W
an
g
an
d
He
[
1
7
]
.
T
h
e
au
th
o
r
s
p
o
in
t
o
u
t
6
p
o
ten
tial
p
r
o
b
le
m
s
to
b
e
o
v
er
co
m
e
f
o
r
f
u
t
u
r
e
ap
p
licatio
n
o
f
b
ig
d
ata
an
al
y
tic
s
e.
g
.
i)
h
i
g
h
l
y
co
m
p
le
x
r
ep
r
esen
tatio
n
o
f
d
ata,
ii)
p
er
v
asi
v
e
u
n
ce
r
tai
n
t
y
,
iii)
ex
tr
e
m
e
l
y
w
ea
k
er
r
elatio
n
s
h
ip
a
m
o
n
g
d
ata,
iv
)
co
m
p
u
tat
io
n
-
s
ca
lab
ilit
y
p
r
o
b
le
m
s
,
v
)
ex
tr
ao
r
d
in
ar
y
m
a
s
s
i
v
e
s
ize
o
f
co
m
p
lex
d
ata,
an
d
v
i)
lar
g
er
n
u
m
b
er
o
f
clas
s
es
in
v
o
l
v
ed
in
m
i
n
i
n
g
p
r
o
ce
s
s
.
Si
m
i
lar
d
ir
ec
tio
n
o
f
s
t
u
d
y
co
n
s
id
er
in
g
E
lectr
o
n
ic
Hea
lth
R
e
co
r
d
s
-
b
ased
d
ata
an
d
its
ap
p
li
ca
b
ilit
y
o
v
er
m
i
n
i
n
g
ap
p
r
o
ac
h
is
d
is
cu
s
s
ed
b
y
W
u
et
al.
[
1
8
]
.
T
h
e
d
is
cu
s
s
io
n
h
ig
h
li
g
h
t
s
th
at
d
i
m
en
s
io
n
a
lit
y
r
ed
u
ctio
n
i
s
o
n
e
o
f
th
e
p
r
o
m
i
n
en
t
p
r
o
b
le
m
s
alo
n
g
w
i
th
p
r
o
ce
s
s
i
n
g
ca
p
ab
ilit
y
.
C
ast
ellan
o
et
al.
[
1
9
]
h
a
v
e
p
r
ese
n
t
ed
a
clas
s
i
f
icatio
n
-
b
ased
ap
p
r
o
ac
h
f
o
r
d
is
cr
i
m
i
n
atin
g
cr
itical
co
n
d
itio
n
o
f
ar
r
h
y
t
h
m
ia.
T
h
e
a
u
th
o
r
s
h
a
v
e
p
r
e
s
en
ted
a
u
n
iq
u
e
tech
n
iq
u
e
f
o
r
in
v
o
l
u
n
tar
y
c
lu
s
ter
in
g
o
f
elec
tr
o
g
r
a
m
s
in
p
r
es
en
ce
o
f
clo
u
d
en
v
ir
o
n
m
en
t.
T
h
e
tech
n
iq
u
e
i
s
also
clai
m
ed
to
o
f
f
er
lo
w
er
co
m
p
u
tatio
n
al
lo
ad
.
T
h
e
s
tu
d
y
o
u
tco
m
e
w
it
n
e
s
s
ar
o
u
n
d
9
0
%
ac
cu
r
ac
y
w
it
h
2
.
5
%
o
f
er
r
o
r
in
class
i
f
icatio
n
p
er
f
o
r
m
an
ce
.
C
a
v
allar
o
et
al.
[
2
0
]
h
av
e
u
s
ed
lear
n
i
n
g
alg
o
r
it
h
m
f
o
r
p
er
f
o
r
m
i
n
g
a
n
ef
f
ec
tiv
e
clas
s
i
f
icatio
n
o
f
i
m
ag
es.
L
u
e
t
al.
[
2
1
]
h
a
v
e
p
r
esen
ted
a
m
o
d
eli
n
g
o
f
a
c
o
n
ce
p
t
th
a
t
allo
ws
p
er
f
o
r
m
in
g
b
ig
d
ata
an
al
y
tics
o
v
er
th
e
clo
u
d
en
v
ir
o
n
m
e
n
t.
T
h
e
n
ex
t
s
ec
tio
n
d
i
s
cu
s
s
e
s
ab
o
u
t
th
e
p
r
o
b
lem
b
ein
g
id
en
ti
f
ied
f
r
o
m
t
h
e
ex
i
s
t
in
g
l
iter
atu
r
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
5
,
Octo
b
er
201
7
:
2
7
9
8
–
2
8
0
5
2800
1
.
2
.
P
r
o
ble
m
I
dentif
ica
t
io
n
T
h
e
ex
is
tin
g
tech
n
q
i
u
es
to
war
d
s
b
ig
d
ata
an
aly
t
ics
h
a
s
ass
o
ciate
d
ad
v
an
ta
g
es
w
itt
h
r
esp
ec
t
to
v
ar
io
u
s
i
n
d
iv
id
u
al
ap
p
licatio
n
s
;
h
o
w
e
v
er
,
it
is
also
ass
o
ci
at
ed
w
it
h
li
m
itatio
n
s
to
o
.
T
h
is
s
ec
tio
n
b
r
ief
s
ab
o
u
t
th
e
o
p
en
r
esear
ch
is
s
u
es
i
n
th
e
lin
e
o
f
v
ar
io
u
s
p
o
ten
tia
l
p
r
o
b
le
m
s
o
f
d
ata
p
r
o
ce
s
s
i
n
g
p
ar
t
icu
lar
l
y
r
elat
in
g
to
th
e
b
ig
d
ata
an
al
y
tic
s
.
T
h
e
id
en
ti
f
ied
p
r
o
b
lem
s
in
t
h
e
ex
is
ti
n
g
s
y
s
te
m
ar
e
as f
o
llo
w
s
:
Ma
j
o
r
ity
o
f
ex
is
tin
g
liter
at
u
r
e
h
av
e
n
o
t
co
n
s
id
er
ed
m
a
n
y
ca
s
es
f
r
o
m
h
ea
lt
h
ca
r
e
s
ec
to
r
.
T
h
e
d
ata
ar
r
iv
in
g
f
r
o
m
h
ea
t
h
ca
r
e
s
ec
to
r
is
h
i
g
h
l
y
co
m
p
le
x
i
n
co
m
p
ar
i
s
o
n
to
o
th
er
f
o
r
m
s
o
f
b
i
g
g
er
d
ata.
S
u
c
h
p
r
o
b
le
m
s
ar
e
less
ad
d
r
ess
ed
in
e
x
is
ti
n
g
liter
atu
r
e.
E
x
is
ti
n
g
s
y
s
te
m
i
n
tr
o
d
u
ce
s
b
i
g
d
ata
an
al
y
tic
s
w
it
h
m
o
r
e
f
o
cu
s
o
n
ap
p
l
y
in
g
m
i
n
i
n
g
o
p
er
atio
n
an
d
v
er
y
less
f
o
cu
s
o
n
p
er
f
o
r
m
i
n
g
p
r
o
ce
s
s
i
n
g
o
p
er
atio
n
o
n
t
h
e
to
p
o
f
it.
Ma
j
o
r
ity
o
f
t
h
e
p
r
o
ce
s
s
i
n
g
i
s
le
f
t
o
f
ex
is
t
in
g
s
o
f
t
w
ar
e
f
r
a
m
e
w
o
r
k
s
,
w
h
ic
h
alr
ea
d
y
h
as r
ep
o
r
ted
p
itf
all
s
.
T
h
er
e
ar
e
n
o
r
esear
ch
atte
m
p
ts
w
h
er
e
th
e
d
ata
b
ef
o
r
e
s
to
r
in
g
o
v
er
clo
u
d
u
n
d
er
g
o
es
p
r
o
ce
s
s
in
g
in
o
r
d
er
to
eli
m
i
n
ate
p
r
o
b
le
m
s
.
Mo
r
eo
v
e
r
,
th
er
e
i
s
i
n
te
g
r
ated
s
y
s
te
m
w
h
ic
h
o
f
f
er
s
m
iti
g
atio
n
p
r
o
ce
d
u
r
e
f
o
r
d
ata
v
ar
iet
y
,
d
ata
u
n
ce
r
tai
n
t
y
,
a
n
d
d
ata
s
p
ee
d
in
ex
is
ti
n
g
liter
at
u
r
e.
1
.
3
.
P
r
o
po
s
ed
So
lutio
n
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
is
a
co
n
ti
n
u
at
io
n
o
f
o
u
r
p
r
io
r
s
tu
d
y
[
2
2
-
2
3
]
,
w
h
er
e
w
e
h
a
v
e
p
r
esen
ted
an
in
d
iv
id
u
al
a
lg
o
r
it
h
m
f
o
r
s
o
lv
i
n
g
t
h
e
p
r
o
b
le
m
s
r
elate
d
to
b
i
g
d
ata
an
al
y
tic
s
e.
g
.
d
ata
v
ar
iet
y
,
d
ata
u
n
ce
r
tain
t
y
,
an
d
d
ata
s
p
ee
d
.
Fig
u
r
e
1
h
i
g
h
l
ig
h
ts
t
h
e
ar
ch
itect
u
r
e
o
f
p
r
o
p
o
s
ed
s
y
s
te
m
.
D
a
t
a
V
a
r
i
e
t
y
D
a
t
a
V
e
r
a
c
i
t
y
D
a
t
a
V
e
l
o
c
i
t
y
A
l
g
o
r
i
t
h
m
d
o
d
a
t
a
u
d
a
t
a
f
d
a
t
a
H
e
a
l
t
h
c
a
r
e
F
a
c
i
l
i
t
y
d
d
Fig
u
r
e
1
P
r
o
p
o
s
ed
ar
ch
itectu
r
e
I
t
is
alr
ea
d
y
k
n
o
w
n
t
h
at
t
h
e
r
e
ar
e
d
if
f
er
en
t
le
v
els
o
f
co
m
p
lex
i
ties
a
s
s
o
ciate
d
i
n
ad
d
r
ess
i
n
g
th
e
p
r
o
b
lem
r
elate
d
to
m
ed
ical
b
i
g
d
ata
an
al
y
tic
s
e.
g
.
d
ata
v
ar
ie
t
y
,
d
ata
u
n
ce
r
tai
n
t
y
,
a
n
d
d
ata
s
p
ee
d
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
o
f
f
er
s
an
in
teg
r
ated
f
r
a
m
e
w
o
r
k
w
h
er
e
it
is
f
ea
s
ib
l
e
to
ad
d
r
ess
all
th
e
th
r
ee
s
i
g
n
i
f
ica
n
t
p
r
o
b
le
m
s
w
it
h
o
u
t
u
s
i
n
g
an
y
s
o
p
h
is
t
icat
ed
to
o
l
o
r
ex
p
en
s
i
v
e
p
r
o
ce
s
s
.
W
e
ass
u
m
e
th
at
a
h
ea
lth
ca
r
e
f
ac
ilit
y
a
lr
ea
d
y
u
s
es
clo
u
d
s
er
v
er
i
n
o
r
d
er
to
s
tack
o
u
t
th
e
g
e
n
er
ated
in
f
o
r
m
atio
n
f
r
o
m
t
h
e
f
ac
ilit
y
.
Ho
w
ev
er
,
we
co
n
s
id
er
th
at
o
u
r
alg
o
r
ith
m
r
u
n
s
o
v
er
s
u
ch
clo
u
d
s
er
v
er
w
h
er
e
b
ef
o
r
e
s
to
r
in
g
t
h
e
d
ata,
th
e
s
y
s
te
m
i
m
p
l
e
m
en
ts
a
ch
ai
n
o
f
alg
o
r
ith
m
i
n
o
r
d
er
to
elim
in
at
e
th
e
p
r
o
b
lem
s
as
s
o
ciate
d
in
p
r
o
ce
s
s
in
g
b
ig
d
ata.
W
e
also
a
s
s
u
m
e
t
h
at
t
h
e
d
ata
g
en
er
ated
b
y
th
e
h
ea
lt
h
ca
r
e
f
ac
ilit
y
i
s
h
ig
h
l
y
u
n
s
tr
u
c
tu
r
ed
an
d
it
s
h
o
u
ld
n
o
t
b
e
s
to
r
ed
in
th
is
s
tate
t
h
at
m
a
y
f
u
r
t
h
er
in
v
ite
c
h
allen
g
e
s
d
u
r
i
n
g
a
n
al
y
ti
ca
l
o
p
er
atio
n
.
T
h
e
u
n
s
tr
u
ct
u
r
ed
d
ata
af
ter
ar
r
iv
in
g
to
clo
u
d
s
er
v
er
it
h
as
to
u
n
d
er
g
o
p
r
o
ce
s
s
i
n
g
f
r
o
m
it
s
f
ir
s
t
alg
o
r
it
h
m
t
h
at
r
e
m
o
v
es
th
e
u
n
s
tr
u
ct
u
r
ed
n
es
s
ch
ar
e
cter
is
tic
o
f
t
h
e
d
ata
an
d
m
ak
e
it
m
o
r
e
o
r
g
a
n
ized
d
ata.
T
h
is
d
ata
th
an
f
u
r
t
h
er
u
n
d
er
g
o
p
r
o
ce
s
s
in
g
w
it
h
n
e
x
t
ch
a
in
o
f
th
e
al
g
o
r
ith
m
to
ex
p
lo
r
e
b
etter
s
u
b
s
tit
u
tio
n
o
f
t
h
e
m
is
s
i
n
g
v
al
u
es
o
r
eli
m
i
n
iate
t
h
e
a
m
b
i
g
u
ities
.
T
h
e
o
b
t
ain
ed
d
ata
f
r
o
m
t
h
i
s
p
ar
t
o
f
th
e
alg
o
r
ith
m
is
th
e
n
s
u
b
j
ec
ted
to
last
p
ar
t
o
f
th
e
alg
o
r
ith
m
t
h
at
m
a
k
es
t
h
e
d
ata
m
o
d
elin
g
s
tr
u
ctu
r
e
i
n
s
u
c
h
a
w
a
y
th
at
t
h
e
s
to
r
a
g
e
s
y
s
te
m
w
ill
b
e
ab
le
to
s
to
r
e
t
h
e
ar
r
iv
ed
d
ata
ir
r
esp
ec
tiv
e
o
f
it
s
ti
m
e
o
f
ar
r
i
v
al
i.e
.
v
elo
cit
y
.
T
h
e
n
e
x
t sect
io
n
f
u
r
t
h
er
elab
o
r
ated
ab
o
u
t su
c
h
al
g
o
r
ith
m
s
d
escr
ip
tiv
e
l
y
.
2.
AL
G
O
RI
T
H
M
I
M
P
L
E
M
E
NT
A
T
I
O
N
T
h
e
f
r
a
m
e
w
o
r
k
d
is
cu
s
s
ed
in
t
h
e
p
r
io
r
s
ec
tio
n
m
a
in
l
y
i
n
co
r
p
o
r
ates
th
r
ee
t
y
p
es
o
f
alg
o
r
it
h
m
tar
g
eti
n
g
to
co
u
n
ter
m
ea
s
u
r
es
t
h
e
p
r
o
b
le
m
s
as
s
o
ciate
d
w
it
h
th
e
m
ed
ical
d
ata
an
aly
s
is
o
f
lar
g
er
s
ize.
T
h
e
alg
o
r
ith
m
tak
e
s
th
e
in
p
u
t
o
f
m
ed
ical
d
ata
w
h
i
ch
h
a
s
th
e
co
r
r
esp
o
n
d
in
g
in
f
o
r
m
atio
n
ab
o
u
t
t
h
e
p
atien
t
e.
g
.
p
atien
t
id
,
h
o
s
tp
ital
n
a
m
e,
R
e
f
er
r
al
d
o
cto
r
,
Date
,
P
atien
t
Na
m
e,
Ge
n
d
er
,
Ag
e,
A
tte
n
d
in
g
Do
cto
r
,
an
d
C
l
in
ical
Hi
s
to
r
y
a
n
d
p
er
f
o
r
m
a
s
er
ies o
f
o
p
er
atio
n
i
n
o
r
d
er
to
o
v
er
co
m
e
th
e
p
r
o
b
le
m
s
a
s
s
o
ciate
d
w
it
h
b
ig
d
ata
an
al
y
s
i
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2088
-
8708
A
N
o
ve
l I
n
teg
r
a
ted
F
r
a
mewo
r
k
to
E
n
s
u
r
e
B
etter
Da
ta
Qu
a
li
ty
i
n
B
ig
Da
ta
A
n
a
lytics o
ve
r
…
(
C
.
S
.
S
in
d
h
u
)
2801
2
.
1
.
Alg
o
ri
t
h
m
f
o
r
A
dd
re
s
s
i
ng
t
he
Va
riet
y
P
ro
ble
m
T
h
e
r
atio
n
ale
o
f
th
i
s
alg
o
r
it
h
m
is
b
ased
o
n
t
h
e
f
ac
t
th
a
t
d
ata
w
i
th
h
i
g
h
s
co
r
e
o
f
v
ar
iet
y
ar
e
h
ig
h
l
y
u
n
o
r
g
a
n
ized
a
n
d
h
e
n
ce
it
is
r
e
q
u
ir
ed
to
p
r
o
v
id
e
a
r
o
b
u
s
t
s
tr
u
ctu
r
e
to
t
h
is
d
ata
s
o
th
a
t
f
u
r
t
h
er
o
p
er
atio
n
ca
n
b
e
ca
r
r
ied
o
u
t.
T
h
is
al
g
o
r
ith
m
i
s
r
esp
o
n
s
ib
le
f
o
r
m
in
i
m
iz
in
g
t
h
e
p
r
o
b
lem
as
s
o
ciate
d
w
it
h
v
ar
iet
y
o
f
m
ed
ical
d
ata.
T
h
e
alg
o
r
ith
m
ta
k
es
t
h
e
in
p
u
t
o
f
u
n
s
tr
u
ct
u
r
ed
d
ata
d
w
h
ich
h
as
d
i
f
f
er
e
n
t
f
o
r
m
s
o
f
v
ar
iab
les
o
f
p
atien
t
in
f
o
r
m
atio
n
r
esid
i
n
g
u
n
d
er
ca
t
eg
o
r
y
C
(
L
i
n
e
-
1
)
.
T
h
e
al
g
o
r
ith
m
r
ea
d
th
e
te
x
t
f
ile
an
d
e
x
tr
a
cts
te
x
t
u
al
co
n
ten
t
s
o
n
t
h
e
b
asi
s
o
f
ca
r
d
in
al
it
y
(
c
a
r
d
)
o
f
d
if
f
er
e
n
t
e
n
tr
ies
as
well
as
p
o
s
itio
n
s
a
n
d
f
in
a
ll
y
s
t
o
r
es
it
i
n
a
m
atr
ix
(
L
in
e
-
2
)
.
T
h
e
alg
o
r
it
h
m
f
ir
s
t
f
in
d
s
t
h
e
li
s
t
o
f
ca
te
g
o
r
ies
i
n
t
h
e
f
o
r
m
o
f
i
n
d
ex
a
n
d
t
h
en
tak
es
o
n
e
b
y
o
n
e
e
n
tr
y
f
o
r
cr
ea
tin
g
n
e
w
ca
te
g
o
r
ies
(
L
i
n
e
-
3
)
.
Fi
n
all
y
,
it
is
ca
p
ab
l
e
o
f
f
i
n
d
in
g
t
h
e
f
ea
s
ib
le
n
u
m
b
er
o
f
ar
r
a
y
.
T
h
e
p
o
s
s
ib
ilit
y
o
f
e
m
p
t
y
v
al
u
e
in
th
e
d
ata
is
also
ad
d
r
ess
ed
in
th
is
s
y
s
te
m
w
h
er
e
it
ch
ec
k
s
th
e
s
ize
o
f
all
th
e
m
atr
i
x
ele
m
e
n
t
s
m
a
t
ele
m
.
I
n
c
ase,
a
m
atr
i
x
ele
m
e
n
t
i
s
f
o
u
n
d
n
u
ll
t
h
an
it
i
s
r
ep
lace
d
b
y
an
i
n
te
g
er
v
al
u
e
co
r
r
esp
o
n
d
in
g
w
i
th
t
h
e
s
in
g
le
m
atr
i
x
(
L
i
n
e
-
5
-
6
)
.
Fi
n
all
y
,
a
l
l
th
e
to
tal
en
tr
ie
s
ar
e
ac
c
u
m
u
lated
b
y
e
x
p
lo
r
in
g
th
e
s
ize
o
f
t
h
e
m
atr
i
x
.
T
h
is
p
r
o
ce
s
s
o
f
d
ata
tr
a
n
s
f
o
r
m
atio
n
f
in
all
y
g
en
er
ate
s
o
r
g
an
ized
d
ata
o
data
f
r
ee
f
o
r
d
ata
v
ar
iet
y
p
r
o
b
le
m
.
Alg
o
rit
h
m
f
o
r
Addre
s
s
i
ng
t
he
Va
riet
y
P
ro
ble
m
I
np
ut
: p
id
, h
n
,
R
d
,
D,
p
nam
e
,
G,
A
,
A
doc
,
C
his
,
C
,
d
,
E
pos
O
utput
: o
data
Sta
rt
1
.
init
d
,
r
ea
d
C
[
C
={p
id
, h
n
, R
d
,
D,
p
nam
e
,
G,
A
,
A
doc
,
C
his
,
C
}
]
2
.
R
ea
d
&
S
to
r
e
ca
r
d
(
en
tr
ie
s
)
&
E
pos
3
.
G
et
C
index
&
co
n
ten
t
4
.
If
m
at
ele
m
=0
5
.
Su
b
s
ti
tu
te
m
at
ele
m
(
S
in
g
le
Mat
)
6
.
o
data
m
at
ele
m
=[
m
at
ele
m
ii]
E
nd
2
.
2
.
Alg
o
ri
t
h
m
f
o
r
Addre
s
s
i
ng
Uncer
t
a
inty
P
ro
ble
m
T
h
e
d
esig
n
p
r
in
cip
le
o
f
th
is
al
g
o
r
ith
m
is
b
ased
o
n
th
e
f
ac
t
t
h
at
u
n
ce
r
tai
n
t
y
s
co
r
e
in
t
h
e
m
ed
ical
b
ig
d
ata
m
a
y
o
cc
u
r
d
u
e
to
in
co
m
p
leten
ess
o
f
d
ata
o
r
am
b
ig
u
iti
es
in
d
ata
s
o
u
r
cin
g
m
o
d
el.
T
h
er
ef
o
r
e,
u
n
ce
r
tain
t
y
p
r
o
b
lem
i
n
m
ed
ical
b
i
g
d
ata
ca
n
b
e
co
u
n
ter
m
ea
s
u
r
ed
i
f
in
co
m
p
lete
o
r
d
ata
a
m
b
i
g
u
it
y
i
s
ad
d
r
ess
ed
in
t
h
e
m
icr
o
-
s
ca
le.
T
h
e
in
p
u
t
to
th
e
s
tu
d
y
is
t
h
e
o
u
tp
u
t
f
r
o
m
p
r
io
r
alg
o
r
ith
m
i.e
.
o
r
g
a
n
ized
d
ata
,
w
h
ic
h
is
i
n
it
iall
y
r
ea
d
(
L
in
e
-
1
)
.
I
n
th
is
ca
s
e,
all
th
e
f
ield
o
f
t
h
e
d
ata
s
o
u
r
ce
s
ar
e
r
ea
d
an
d
c
h
ec
k
ed
if
all
o
f
th
e
m
h
a
v
e
u
n
d
er
g
o
n
e
th
e
p
r
o
ce
s
s
o
f
r
e
m
o
v
a
l
o
f
d
ata
v
ar
iet
y
p
r
o
b
lem
s
.
T
h
is
p
r
o
ce
s
s
is
t
h
e
n
f
u
r
t
h
er
f
o
llo
wed
b
y
a
n
iter
ati
v
e
o
p
er
atio
n
f
o
r
ch
ec
k
in
g
th
e
m
atch
ed
id
en
ti
f
icatio
n
o
f
t
h
e
d
ata
co
r
r
esp
o
n
d
in
g
to
all
th
e
ca
s
e
s
tu
d
ie
s
o
f
th
e
h
o
s
p
ital
d
atab
ase.
T
h
e
m
ai
n
o
b
j
ec
tiv
e
o
f
th
is
o
p
er
atio
n
is
to
ch
ek
f
o
r
s
co
r
es
o
f
m
a
tch
ed
el
e
m
en
ts
alo
n
g
w
it
h
id
en
tit
y
a
n
d
r
esp
ec
tiv
e
ca
te
g
o
r
ies.
Hen
ce
,
if
an
y
o
n
e
o
f
th
e
f
ie
ld
in
f
o
r
m
atio
n
i
s
m
i
s
s
in
g
,
t
h
e
o
th
er
k
e
y
attr
ib
u
tes
e.
g
.
atch
ed
ele
m
en
t
s
alo
n
g
w
it
h
id
en
tit
y
a
n
d
r
esp
ec
tiv
e
ca
teg
o
r
ies
w
i
ll
as
s
is
t
to
f
in
d
t
h
e
m
is
s
in
g
ele
m
e
n
ts
o
r
ev
e
n
a
m
b
i
g
u
o
u
s
ele
m
e
n
ts
i
n
t
h
e
m
atr
i
x
.
Fi
n
a
ll
y
,
b
ased
o
n
th
e
s
elec
ted
id
en
tit
y
o
f
t
h
e
n
e
w
l
y
ex
p
lo
r
ed
d
ata,
it
is
th
e
n
s
to
r
ed
.
T
h
e
m
ec
h
an
is
m
also
o
b
tai
n
s
th
e
in
i
tial
w
o
r
d
f
r
o
m
th
e
co
l
u
m
n
ar
ele
m
e
n
t
a
n
d
co
n
v
er
ts
it
to
c
h
ar
ac
ter
f
o
llo
wed
b
y
e
x
tr
ac
tio
n
o
f
m
ea
n
v
alu
e.
A
n
e
w
m
atr
i
x
i
s
t
h
en
f
o
r
m
u
lated
u
s
i
n
g
u
n
iq
u
e
ele
m
e
n
t
i
n
o
r
d
er
to
g
en
er
ate
a
r
an
d
o
m
n
u
m
b
er
w
it
h
i
n
a
r
a
n
g
e
o
f
s
ize
o
f
th
e
m
atr
ix
.
T
h
is
p
h
e
n
o
m
e
n
o
n
w
il
l
s
ig
n
i
f
ica
n
tl
y
a
v
o
id
an
y
k
in
d
o
f
a
m
b
i
g
u
i
t
y
i
n
th
e
d
ata
an
d
o
n
l
y
t
h
e
m
atc
h
ed
d
ata
w
ill
b
e
r
etr
iev
ed
.
Hen
ce
,
if
th
e
ca
te
g
o
r
y
ele
m
e
n
t
d
o
ex
i
s
t
s
(
L
i
n
e
-
2
)
th
a
n
it
w
ill
u
s
e
th
e
s
a
m
e
ca
teg
o
r
y
id
en
ti
t
y
(
L
i
n
e
-
3
)
o
r
else
it
w
i
ll
g
en
er
ate
a
n
e
w
ca
te
g
o
r
y
id
en
t
it
y
t
h
at
co
r
r
esp
o
n
d
s
w
ith
t
h
e
s
ize
o
f
ca
te
g
o
r
y
m
atr
i
x
(
L
in
e
-
5
)
.
T
h
e
m
a
tr
ix
w
it
h
n
e
w
l
y
p
o
s
itio
n
ed
d
ata
i
s
t
h
en
u
p
d
ated
f
o
llo
w
ed
b
y
ca
lc
u
lat
io
n
o
f
d
ata
p
u
r
i
t
y
a
s
t
h
e
r
an
k
in
g
m
ec
h
a
n
is
m
o
f
ad
d
r
es
s
in
g
u
n
ce
r
tain
t
y
p
r
o
b
lem
s
i
n
m
ed
ical
b
ig
d
ata
(
L
in
e
-
7
)
.
W
e
also
co
m
p
u
te
er
r
o
r
th
at
co
u
ld
p
o
s
s
ib
l
y
o
cc
u
r
d
u
r
in
g
t
h
e
s
u
b
s
tit
u
tio
n
p
r
o
ce
s
s
to
f
ill
u
p
m
is
s
in
g
o
r
am
b
i
g
u
o
u
s
d
ata
(
L
i
n
e
-
8
)
;
h
o
w
e
v
er
,
it
is
j
u
s
t
a
p
er
f
o
r
m
a
n
ce
p
ar
a
m
er
er
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
5
,
Octo
b
er
201
7
:
2
7
9
8
–
2
8
0
5
2802
Alg
o
rit
h
m
f
o
r
Addre
s
s
i
ng
Uncer
t
a
inty
P
ro
ble
m
I
np
ut
: o
data
(
Or
g
a
n
ized
Data
)
,
C
ele
m
(
C
ate
g
o
r
y
E
le
m
e
n
t)
O
utput
: u
data
(
u
p
d
ated
d
ata)
,
d
pur
(
d
ata
p
u
r
it
y
)
,
E
(
E
r
r
o
r
)
Sta
rt
1
.
R
ea
d
o
data
2
.
If
(C
elem
≠
0
)
3
.
u
s
e
C
id
4
.
E
ls
e
5
.
u
s
e
n
e
w
C
id
[C
id
,
s
ize(
C
)
]
6
.
Up
d
ate
m
at
ele
m
7
.
d
pur
s
ize(
u
n
iq
u
e(
C
)
,
m
at
ele
m
)
/ c
ar
d
(
C
ele
m
)
8
E
=E
+size(
n
e
w
E
n
tr
y
)
9
.
Up
d
ate
m
at
ele
m
u
d
ata
E
nd
2
.
3
.
Alg
o
ri
t
h
m
f
o
r
Addre
s
s
i
ng
Sp
ee
d P
ro
ble
m
T
h
e
p
r
im
e
r
atio
n
ale
o
f
t
h
i
s
al
g
o
r
ith
m
i
s
t
h
at
d
ata
s
p
ee
d
ca
n
n
o
t
b
e
co
n
tr
o
lled
b
y
a
n
y
m
e
an
s
b
u
t
w
e
co
n
s
id
er
th
at
i
f
t
h
e
s
p
ee
d
o
f
d
ata
is
k
n
o
w
n
to
s
o
m
e
ex
te
n
t
th
an
a
p
r
o
p
er
d
ata
m
a
n
ag
e
m
en
t
co
u
ld
b
e
d
o
n
e.
Hen
ce
,
w
e
o
f
f
er
a
v
er
y
s
i
m
p
le
m
o
d
el
w
h
er
e
ir
r
esp
ec
tiv
e
o
f
a
n
y
s
p
ee
d
o
f
ar
r
iv
al
o
f
th
e
in
co
m
i
n
g
d
ata,
th
e
d
ata
co
u
ld
b
e
ef
f
icie
n
tl
y
s
to
r
ed
in
o
u
t
d
atab
ase
f
r
a
m
e
w
o
r
k
.
T
h
e
alg
o
r
ith
m
ta
k
e
s
t
h
e
o
u
tp
u
t
o
f
p
r
io
r
alg
o
r
ith
m
w
h
er
e
u
n
ce
r
tain
t
y
p
r
o
b
le
m
is
ad
d
r
ess
ed
.
T
h
e
alg
o
r
ith
m
in
i
ti
all
y
r
ea
d
th
e
co
lu
m
n
v
al
u
e
o
f
th
e
in
co
m
i
n
g
d
ata
(
L
in
e
-
1
)
an
d
f
i
n
d
s
it
s
n
u
m
er
ic
al
v
al
u
e.
A
clas
s
i
f
icatio
n
o
f
d
i
f
f
er
en
t
m
atr
i
x
ar
e
g
e
n
er
ated
d
ep
en
d
in
g
o
n
t
h
e
last
co
lu
m
n
o
f
t
h
e
in
co
m
i
n
g
d
ata
(
L
i
n
e
-
2
)
f
o
llo
w
ed
b
y
e
x
tr
ac
tio
n
o
f
d
i
f
f
er
e
n
t
lab
el
s
to
o
(
L
i
n
e
-
3
)
.
B
asical
l
y
,
L
ab
els
co
r
r
esp
o
n
d
s
to
ea
c
h
i
n
d
iv
id
u
al
ce
l
l
i
n
t
h
e
m
a
tr
ix
.
W
e
f
o
r
m
u
late
a
te
m
p
o
r
ar
y
m
atr
ix
m
atc
h
t
h
at
i
s
r
esp
o
n
s
ib
le
f
o
r
id
en
t
if
y
i
n
g
s
i
m
ilar
e
le
m
e
n
t
s
i
n
in
co
m
i
n
g
d
ata
an
d
s
to
r
ag
e
ar
ea
.
I
f
th
e
i
n
co
m
in
g
d
ata
is
f
o
u
n
d
to
h
av
e
m
atch
t
h
an
th
e
d
ata
is
d
ir
ec
tl
y
d
is
ca
r
d
ed
an
d
o
n
l
y
t
h
e
co
l
u
m
n
in
d
e
x
is
u
p
d
ate
d
(
L
in
e
-
4
)
.
B
y
th
i
s
p
r
o
ce
s
s
,
th
e
alg
o
r
ith
m
e
n
s
u
r
es
co
s
t
ef
f
ec
t
iv
e
u
s
a
g
e
o
f
d
ata
s
to
r
ag
e
m
o
d
el
b
y
o
n
l
y
co
n
s
id
er
in
g
u
n
iq
u
e
in
co
m
i
n
g
d
ata
to
b
e
s
to
r
ed
.
Ho
w
e
v
er
,
if
t
h
e
in
co
m
i
n
g
d
a
ta
is
f
o
u
n
d
to
b
e
u
n
iq
u
e
i.e
.
it
h
as
n
o
m
atc
h
ed
ele
m
e
n
ts
b
et
w
ee
n
its
el
f
an
d
d
ata
s
to
r
ag
e
s
tr
u
ct
u
r
e
(
L
i
n
e
-
4
)
,
th
an
it
i
n
s
ta
n
tl
y
u
p
d
ate
its
la
b
el
w
it
h
r
esp
ec
t
to
s
ize
o
f
t
h
e
lab
el
(
L
i
n
e
-
5
)
.
I
t
w
i
ll
m
ea
n
t
h
at
a
s
i
n
g
le
lab
el
is
s
u
f
f
icie
n
t e
n
o
u
g
h
to
s
to
r
e
t
h
e
d
if
f
er
en
t
f
r
eq
u
e
n
cies
o
f
th
e
i
n
co
m
i
n
g
d
ata,
s
o
th
at
o
th
er
p
ar
t
o
f
th
e
ce
lls
o
f
f
er
s
en
o
u
g
h
b
u
f
f
er
s
f
o
r
n
e
w
ar
r
i
v
al
o
f
m
as
s
i
v
e
d
ata.
Fin
all
y
,
all
th
e
e
x
p
licit
co
l
u
m
n
ar
in
f
o
r
m
at
io
n
co
l
is
ac
co
m
p
lis
h
ed
(
L
i
n
e
-
6
)
an
d
ce
ll
s
ar
e
u
p
d
ated
w
ith
r
e
s
p
ec
t
to
lab
els
an
d
o
u
tp
u
t
ce
lls
(
L
in
e
-
7
)
.
Hen
ce
,
ir
r
esp
ec
tiv
e
o
f
an
y
f
lo
w
o
f
t
h
e
in
co
m
i
n
g
d
ata,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
ca
n
o
f
f
er
s
ig
n
i
f
ica
n
t
r
o
o
m
f
o
r
d
ata
s
to
r
ag
e
s
y
s
te
m
i
n
o
r
d
er
to
s
to
r
e
th
e
in
co
m
in
g
d
ata
ar
r
iv
i
n
g
f
r
o
m
ce
r
tai
n
h
ea
lt
h
ca
r
e
f
ac
ili
ties
.
Alg
o
rit
h
m
f
o
r
Addre
s
s
i
ng
S
peed
P
ro
ble
m
I
np
ut
:
u
data
,
co
l
v
al
O
utput
: f
data
Sta
rt
1
.
f
in
d
co
l
v
al
2
.
class
if
y
b
ased
o
n
co
l
3
.
g
et
L
ab
el
4
.
If
m
atc
h
=0
5
.
u
p
d
ate
L
ab
el
[
1
:s
ize(
lab
el)
]
6
.
Get
co
l
7
.
f
data
u
p
d
ate
ce
lls
(
L
ab
el,
O
u
tp
u
t
C
ells
)
E
nd
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2088
-
8708
A
N
o
ve
l I
n
teg
r
a
ted
F
r
a
mewo
r
k
to
E
n
s
u
r
e
B
etter
Da
ta
Qu
a
li
ty
i
n
B
ig
Da
ta
A
n
a
lytics o
ve
r
…
(
C
.
S
.
S
in
d
h
u
)
2803
T
ab
le
1
No
tatio
n
u
s
ed
in
A
l
g
o
r
ith
m
Desi
g
n
N
o
t
a
t
i
o
n
M
e
a
n
i
n
g
p
id
p
a
t
i
e
n
t
i
d
h
n
h
o
st
p
i
t
a
l
n
a
me
R
d
R
e
f
e
r
r
a
l
D
o
c
t
o
r
D
D
a
t
e
p
n
a
m
e
P
a
t
i
e
n
t
N
a
me
G
G
e
n
d
e
r
A
A
g
e
A
d
o
c
A
t
t
e
n
d
i
n
g
D
o
c
t
o
r
C
h
i
s
C
l
i
n
i
c
a
l
H
i
st
o
r
y
C
C
a
t
e
g
o
r
y
d
u
n
s
t
r
u
c
t
u
r
e
d
d
a
t
a
E
po
s
En
t
r
y
P
o
si
t
i
o
n
o
da
t
a
O
r
g
a
n
i
z
e
d
D
a
t
a
C
e
l
e
m
C
a
t
e
g
o
r
y
El
e
me
n
t
u
da
t
a
u
p
d
a
t
e
d
d
a
t
a
d
pu
r
d
a
t
a
p
u
r
i
t
y
E
Er
r
o
r
c
o
l
v
a
l
n
u
me
r
i
c
v
a
l
u
e
o
f
c
o
l
u
m
n
f
da
t
a
f
i
n
a
l
d
a
t
a
3.
RE
SU
L
T
ANAL
YSI
S
T
h
is
p
ar
t
o
f
th
e
s
t
u
d
y
d
is
c
u
s
s
es
ab
o
u
t
th
e
r
es
u
lt
s
b
ein
g
ac
c
o
m
p
li
s
h
ed
f
r
o
m
t
h
e
p
r
o
p
o
s
ed
s
tu
d
y
.
T
h
e
i
m
p
le
m
en
ta
tio
n
o
f
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
is
ca
r
r
ied
o
u
t
i
n
M
atlab
.
T
h
e
co
n
s
tr
u
cted
f
r
a
m
e
w
o
r
k
o
f
f
er
a
h
i
g
h
l
y
co
m
p
r
e
h
en
s
iv
e
s
i
n
g
le
e
n
v
ir
o
n
m
en
t
f
o
r
test
i
f
y
i
n
g
t
h
e
t
h
r
ee
s
ig
n
if
ican
t
p
r
o
b
le
m
s
a
s
s
o
ciate
d
w
it
h
m
ed
ical
b
i
g
d
ata
i.e
.
d
ata
v
ar
iet
y
,
d
ata
u
n
ce
r
tain
t
y
,
a
n
d
d
ata
s
p
ee
d
.
T
h
e
r
ea
s
o
n
f
o
r
s
elec
ti
n
g
Ma
tlab
f
o
r
d
esi
g
n
a
n
d
d
ev
elo
p
m
en
t
i
s
its
ea
s
i
n
es
s
,
co
n
v
e
n
ien
t,
an
d
s
ca
lab
le.
T
h
e
i
m
p
le
m
e
n
tat
io
n
o
f
th
e
s
tu
d
y
was
ca
r
r
ied
o
u
t
u
s
in
g
s
y
t
h
e
n
tic
m
ed
ical
d
ata
o
f
lar
g
er
s
ize.
A
s
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
is
n
ea
r
l
y
s
i
m
ilar
to
o
p
ti
m
iz
e
th
e
p
er
f
o
r
m
an
ce
o
f
a
f
r
a
m
e
w
o
r
k
f
o
r
b
ig
d
ata
an
al
y
tic
s
,
h
en
ce
,
it
is
w
i
s
e
en
o
u
g
h
to
b
e
co
m
p
ar
ed
w
it
h
s
i
m
i
lar
f
r
eq
u
en
tl
y
u
s
ed
tech
n
iq
u
eso
f
o
p
ti
m
izat
io
n
.
W
e
f
in
d
th
a
t
ad
o
p
tio
n
o
f
S
u
p
p
o
r
t
Vec
to
r
Ma
ch
in
e
h
a
s
b
ee
n
ca
r
r
ied
o
u
t
b
y
C
av
al
lar
o
et
al.
[
2
0
]
as
w
el
l
a
s
b
y
S
in
g
h
et
al.
[
2
4
]
.
On
e
o
f
th
e
o
p
ti
m
izatio
n
f
ea
t
u
r
e
o
f
S
VM
is
it
s
e
x
ce
lle
n
t
class
i
f
icatio
n
ap
p
r
o
ac
h
th
a
t
h
as
ca
p
ab
ilit
y
to
b
e
ap
p
lied
o
v
er
h
i
g
h
-
d
i
m
en
s
io
an
l
d
ata
an
d
it
is
in
d
ep
en
d
e
n
t
o
f
an
y
f
o
r
m
o
f
co
n
v
e
n
tio
n
al
f
ea
t
u
r
e
s
elec
tio
n
p
r
o
ce
d
u
r
es
in
o
v
er
to
r
esis
t
s
t
h
e
p
r
o
b
lem
a
s
s
o
ciate
d
w
it
h
lar
g
e
r
d
i
m
en
s
io
n
al
it
y
o
f
b
i
g
d
ata.
Dif
f
er
en
t
f
o
r
m
s
o
f
r
eg
u
lar
iza
tio
n
ele
m
e
n
ts
a
s
w
el
l
as
e
x
t
r
ac
ted
f
ea
tu
r
e
s
ar
e
co
n
ca
ten
ated
d
u
r
in
g
t
h
e
p
r
o
ce
s
s
o
f
lear
n
in
g
.
I
n
o
r
d
er
to
m
ak
e
t
h
e
S
VM
w
o
r
k
s
e
f
f
icie
n
tl
y
f
o
r
b
ig
d
ata,
i
t
i
s
r
eq
u
ir
ed
f
o
r
th
e
class
b
o
u
n
d
ar
y
to
b
e
v
er
y
clo
s
e
to
th
e
o
u
t
c
o
m
e
o
f
th
e
a
n
ticip
ated
s
a
m
p
le
s
o
f
tr
ain
i
n
g
.
A
p
ar
t
f
r
o
m
SVM,
w
e
also
f
in
d
t
h
e
ad
o
p
tio
n
o
f
n
eu
r
al
n
et
w
o
r
k
in
o
p
ti
m
izi
n
g
b
i
g
d
ata
an
al
y
ti
cs.
T
h
e
m
o
s
t
r
ec
en
t
w
o
r
k
ca
r
r
ied
o
u
t
b
y
C
h
u
n
g
et
al.
[
2
5
]
h
as
d
is
cu
s
s
ed
th
e
u
s
a
g
e
o
f
n
eu
r
al
n
et
w
o
r
k
f
o
r
h
ig
h
p
er
f
o
r
m
a
n
c
e
co
m
p
u
tatio
n
o
f
b
ig
d
ata.
On
e
o
f
t
h
e
s
i
g
n
i
f
ica
n
t
ad
v
a
n
ta
g
es
o
f
ap
p
l
y
i
n
g
n
e
u
r
al
n
et
w
o
r
k
o
v
er
b
ig
d
ata
a
n
al
y
s
i
s
is
its
ca
p
ab
ilit
y
o
f
ap
p
r
o
x
i
m
at
io
n
o
f
an
y
f
o
r
m
s
o
f
f
u
n
ctio
n
.
T
h
is
o
p
er
atio
n
ca
n
b
e
s
ig
n
i
f
ic
an
tl
y
h
elp
f
u
l
w
h
il
e
ex
p
lo
r
in
g
f
o
r
th
e
s
u
b
-
s
p
ac
e
clu
s
ter
i
n
g
i
n
h
ig
h
d
i
m
en
s
io
n
al
d
ata.
A
s
i
g
n
i
f
ican
t
s
i
g
m
o
id
f
u
n
ctio
n
ca
n
b
e
f
u
r
th
er
f
i
n
e
t
u
n
ed
i
n
o
r
d
er
to
ar
r
iv
e
i
n
to
ellite
o
u
tco
m
e
u
s
i
n
g
n
e
u
r
a
l
n
et
w
o
r
k
in
b
ig
d
ata
a
n
al
y
s
i
s
.
Fo
r
s
i
m
p
l
icit
y
,
w
e
i
m
p
le
m
en
t
s
u
p
p
o
r
t
v
ec
to
r
m
a
ch
in
e
a
s
th
e
tr
ain
in
g
alg
o
r
it
h
m
to
ad
d
r
ess
th
e
p
r
o
b
lem
d
is
cu
s
s
ed
in
o
u
r
p
ap
er
.
W
e
tak
e
t
h
e
f
ee
d
-
f
o
r
w
ar
d
al
g
o
r
ith
m
a
s
t
h
e
lear
n
in
g
ap
p
r
o
ac
h
f
o
r
n
e
u
r
al
n
et
w
o
r
k
to
o
.
H
en
ce
,
o
u
r
e
x
is
ti
n
g
s
y
s
te
m
i
s
a
co
m
b
i
n
ed
r
esu
lt
ar
r
iv
ed
f
r
o
m
i
m
p
le
m
en
tin
g
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
a
n
d
n
eu
r
al
n
et
w
o
r
k
.
T
h
e
co
m
p
ar
ati
v
e
as
s
es
s
m
en
t
o
f
t
h
e
s
t
u
d
y
w
as
ca
r
r
ied
o
u
t
co
n
s
id
er
in
g
ac
c
u
r
ac
y
p
ar
a
m
eter
an
d
co
m
p
u
tatio
n
al
r
esp
o
n
s
e
ti
m
e.
Fig
u
r
e
2
.
C
o
m
p
ar
ativ
e
p
er
f
o
r
m
an
ce
s
o
n
ac
c
u
r
ac
y
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
5
,
Octo
b
er
201
7
:
2
7
9
8
–
2
8
0
5
2804
T
h
e
co
m
p
ar
ativ
e
a
s
s
es
s
m
en
t
o
f
th
e
ac
c
u
r
ac
y
i
s
ca
r
r
ied
o
u
t
u
s
i
n
g
T
r
u
e
P
o
s
itiv
e,
Fals
e
P
o
s
iti
v
e,
an
d
Fals
e
Ne
g
ati
v
e
f
o
r
b
o
th
p
r
o
p
o
s
ed
s
y
s
te
m
as
w
el
l
as
e
x
is
t
in
g
s
y
s
te
m
.
T
h
e
s
tu
d
y
o
u
tco
m
e
s
h
o
w
s
t
h
at
p
r
o
p
o
s
ed
s
y
s
te
m
ac
co
m
p
l
is
h
es
b
etter
tr
u
e
p
o
s
itiv
e
f
r
o
m
s
tati
s
tical
s
c
o
r
e
(
p
r
o
b
a
b
ilit
y
)
v
ie
w
p
o
in
t,
w
h
er
ea
s
th
e
e
x
is
t
in
g
s
y
s
te
m
o
f
f
er
s
li
g
h
tl
y
r
ed
u
ce
d
ac
cu
r
ac
y
p
er
f
o
r
m
an
ce
as
co
m
p
ar
ed
to
p
r
o
p
o
s
ed
s
y
s
te
m
.
T
h
e
p
r
im
e
r
ea
s
o
n
b
eh
in
d
t
h
is
t
h
at
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
p
er
f
o
r
m
s
a
s
eq
u
e
n
tia
l
o
p
er
atio
n
w
h
er
e
o
u
tp
u
t
o
f
f
ir
s
t
o
p
er
at
io
n
b
ec
o
m
e
s
in
p
u
t
o
f
s
ec
o
n
d
p
r
o
ce
s
s
.
B
y
t
h
is
p
r
o
ce
s
s
,
th
e
p
r
o
p
o
s
ed
s
y
s
t
e
m
o
f
f
er
s
b
etter
o
p
ti
m
izatio
n
w
it
h
o
u
t
u
s
in
g
an
y
r
ec
u
r
s
iv
e
f
u
n
ctio
n
a
s
w
ell
a
s
w
it
h
e
v
er
y
i
n
cr
ea
s
i
n
g
s
tep
s
th
e
p
r
o
b
lem
s
g
et
r
ed
u
ce
d
.
T
h
is
p
r
o
ce
d
u
r
e
o
f
f
ilter
in
g
th
e
p
r
o
b
lem
s
is
m
o
r
e
iter
ativ
e
an
d
less
f
ilter
ed
an
d
h
e
n
ce
ei
x
ts
in
g
s
y
s
te
m
co
u
ld
n
’
t o
f
f
er
b
etter
ac
cu
r
ac
y
.
Fig
u
r
e
3
.
C
o
m
p
ar
ativ
e
p
er
f
o
r
m
an
ce
s
o
n
r
esp
o
n
s
e
ti
m
e
W
e
also
co
m
p
u
te
t
h
e
a
m
o
u
n
t
o
f
co
m
p
u
tat
io
n
al
co
m
p
lex
it
ies
as
s
o
ciate
d
w
it
h
b
o
t
h
p
r
o
p
o
s
ed
an
d
ex
is
t
in
g
s
y
s
te
m
w
it
h
r
esp
ec
t
to
co
m
p
u
atat
io
n
al
r
esp
o
n
s
e
ti
m
e.
Fig
u
r
e
3
clea
r
l
y
s
h
o
w
s
t
h
at
p
r
o
p
o
s
ed
s
y
s
te
m
o
f
f
er
s
b
etter
r
esp
o
n
s
e
ti
m
e
i
n
co
m
p
ar
is
o
n
to
e
x
i
s
ti
n
g
s
y
s
te
m
.
Ho
w
e
v
er
,
b
ec
au
s
e
o
f
to
o
m
a
n
y
d
ep
en
d
en
cie
s
o
n
iter
atio
n
,
t
h
e
ex
is
ti
n
g
s
y
s
te
m
e
n
co
u
n
ter
s
t
h
e
p
r
o
b
le
m
o
f
f
a
s
ter
co
n
v
er
g
e
n
ce
.
T
h
er
ef
o
r
e,
s
u
c
h
iter
ati
v
e
o
p
er
atio
n
s
ca
n
n
o
t
b
e
s
u
i
tab
l
y
ap
p
lied
o
v
er
h
ig
h
-
d
i
m
e
n
s
io
n
al
d
ata
th
er
eb
y
ca
u
s
i
n
g
ti
m
e
lag
s
to
y
ield
t
h
e
o
u
tco
m
e.
On
t
h
e
o
th
er
h
a
n
d
,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
o
f
f
er
s
th
e
r
esu
lt
s
o
w
i
n
g
to
f
aster
co
n
v
er
g
e
n
ce
w
h
ile
m
ak
in
g
tr
a
n
s
it
io
n
f
r
o
m
o
n
e
a
lg
o
r
ith
m
to
o
t
h
er
.
T
h
er
ef
o
r
e,
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
o
f
f
er
b
e
tter
co
m
p
u
tatio
n
al
r
esp
o
n
s
e
ti
m
e
as
w
ell
a
s
lo
wer
m
e
m
o
r
y
co
n
s
u
m
p
tio
n
o
v
er
n
o
r
m
al
m
ac
h
i
n
e
to
p
r
o
v
e
its
co
s
t
ef
f
ec
ti
v
e
n
ess
.
T
h
e
s
to
r
ag
e
co
m
p
le
x
it
y
is
h
i
g
h
l
y
co
n
tr
o
lled
as
t
h
e
co
m
p
l
ete
f
r
a
m
e
w
o
r
k
o
f
f
er
s
r
esu
l
ts
o
n
l
y
o
v
er
r
u
n
ti
m
e
p
r
o
ce
s
s
in
g
o
f
th
e
al
g
o
r
ith
m
a
n
d
h
en
ce
en
o
u
g
h
r
eso
u
r
ce
co
n
s
u
m
p
tio
n
is
s
av
ed
.
4.
CO
NCLU
SI
O
N
T
h
is
p
ap
er
em
p
h
asize
s
o
n
th
e
in
h
er
en
t
p
r
o
b
le
m
s
as
s
o
ciate
d
w
ith
th
e
b
ig
d
ata
a
n
al
y
tic
s
o
v
er
clo
u
d
i.e
.
d
ata
v
ar
iet
y
,
d
ata
u
n
ce
r
tai
n
t
y
,
a
n
d
d
ata
s
p
ee
d
.
W
e
h
av
e
r
ev
ie
w
ed
s
o
m
e
o
f
t
h
e
r
ec
en
t l
i
ter
atu
r
es to
f
in
d
t
h
at
th
er
e
is
a
b
ig
tr
ad
eo
f
f
in
th
e
e
x
is
t
in
g
ap
p
r
o
ac
h
es
b
et
w
e
e
n
p
r
o
b
lem
s
b
ein
g
ad
d
r
ess
ed
a
s
cla
i
m
ed
a
n
d
r
ea
l
-
ti
m
e
p
r
o
b
lem
s
.
T
h
e
p
r
o
b
lem
s
b
ein
g
ad
d
r
ess
ed
as
clai
m
ed
i
n
lit
er
atu
r
e
o
n
l
y
e
m
p
h
asize
s
o
n
p
ar
t
o
f
o
n
e
p
r
o
b
le
m
w
h
er
e
i
n
r
ea
l
-
s
e
n
s
e
th
er
e
c
o
u
ld
b
e
en
d
les
s
n
u
m
b
er
o
f
o
cc
u
r
an
ce
o
f
al
l
t
h
e
r
ep
o
r
ted
p
r
o
b
lem
s
w
h
ile
pe
r
f
o
r
m
in
g
r
ea
l
-
ti
m
e
a
n
al
y
s
is
o
v
er
clo
u
d
e
n
v
ir
o
n
m
e
n
t.
T
h
i
s
p
ap
er
d
escr
ib
es
o
n
e
n
o
v
el
r
es
ea
r
ch
m
o
d
el
w
h
ic
h
is
ex
p
er
i
m
e
n
ted
o
v
er
s
y
n
t
h
eti
c
b
ig
d
ata
o
f
h
ea
lt
h
ca
r
es
s
ec
to
r
.
T
h
e
tech
n
iq
u
e
i
n
tr
o
d
u
ce
s
a
n
o
v
el
f
r
a
m
e
w
o
r
k
w
h
er
e
all
th
e
r
ep
o
r
ted
p
r
o
b
le
m
s
e.
g
.
.
d
ata
v
ar
i
et
y
,
d
ata
u
n
c
er
tain
t
y
,
an
d
d
ata
s
p
ee
d
is
ad
d
r
ess
ed
.
A
t
p
r
esen
t,
w
e
f
i
n
d
th
a
t
it
o
f
f
er
b
etter
ac
cu
r
ac
y
a
n
d
r
esp
o
n
s
e
ti
m
e
in
co
m
p
ar
is
o
n
to
e
x
is
ti
n
g
o
p
ti
m
i
za
tio
n
s
y
s
te
m
.
O
u
r
f
u
tu
r
e
w
o
r
k
d
ir
ec
tio
n
w
il
l b
e
to
f
u
r
t
h
er
o
p
ti
m
ize
th
e
o
u
tco
m
es.
RE
F
E
R
E
NC
E
S
[1
]
M
a
n
d
a
l,
Jy
o
tsn
a
Ku
m
a
r,
Ha
n
d
b
o
o
k
o
f
Re
se
a
rc
h
o
n
Na
tu
ra
l
Co
m
p
u
ti
n
g
f
o
r
Op
ti
m
iza
ti
o
n
P
r
o
b
le
m
s,
I
G
I
G
lo
b
a
l
-
Co
m
p
u
ter,
2
0
1
6
[2
]
Cip
rian
D
o
b
re
,
F
a
to
s
Xh
a
f
a
,
P
e
rv
a
siv
e
Co
m
p
u
ti
n
g
:
Ne
x
t
G
e
n
e
r
a
ti
o
n
P
latf
o
rm
s
f
o
r
In
telli
g
e
n
t
Da
ta
Co
ll
e
c
ti
o
n
,
M
o
rg
a
n
Ka
u
fm
a
n
n
-
Co
m
p
u
ters
,
2
0
1
6
[3
]
T
S
u
ti
k
n
o
,
D
S
ti
a
w
a
n
,
IM
I
S
u
b
ro
t
o
,
"
F
o
rt
ify
in
g
b
ig
d
a
ta
in
f
ra
stru
c
tu
re
s
to
f
a
c
e
se
c
u
rit
y
a
n
d
p
riv
a
c
y
issu
e
s
,
”
T
EL
KOM
NIKA
T
e
lec
o
mm
u
n
ic
a
ti
o
n
C
o
mp
u
ti
n
g
El
e
c
tro
n
ics
a
n
d
Co
n
tro
l
.,
v
o
l.
1
2
,
n
o
.
4
,
p
p
.
7
5
1
-
7
5
2
,
2
0
1
4
.
[4
]
A
n
is
Ko
u
b
a
a
,
El
h
a
d
i
S
h
a
k
sh
u
k
i,
Ro
b
o
ts
a
n
d
S
e
n
so
r
Clo
u
d
s,
S
p
r
in
g
e
r,
2
0
1
5
[5
]
Bh
a
tt
,
Ch
in
tan
M
.
,
P
e
d
d
o
j
u
,
S
.
K,
Clo
u
d
C
o
m
p
u
ti
n
g
S
y
ste
m
s an
d
A
p
p
li
c
a
ti
o
n
s i
n
He
a
lt
h
c
a
re
,
IG
I
Glo
b
a
l,
2
0
1
6
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2088
-
8708
A
N
o
ve
l I
n
teg
r
a
ted
F
r
a
mewo
r
k
to
E
n
s
u
r
e
B
etter
Da
ta
Qu
a
li
ty
i
n
B
ig
Da
ta
A
n
a
lytics o
ve
r
…
(
C
.
S
.
S
in
d
h
u
)
2805
[6
]
S
.
P
.
M
e
n
o
n
,
N
.
P
.
He
g
d
e
,
“
Re
se
a
rc
h
o
n
Clas
sif
ica
ti
o
n
A
lg
o
rit
h
m
a
n
d
it
s
Im
p
a
c
t
o
n
W
e
b
M
i
n
i
n
g
”
,
In
tern
a
ti
o
n
a
l
Jo
u
rn
a
l
o
f
Co
m
p
u
ter E
n
g
in
e
e
rin
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
4
,
Iss
.
4
,
p
p
.
4
9
5
-
5
0
4
,
2
0
1
3
,
[7
]
S
.
P
.
M
e
n
o
n
,
N.
P
.
He
g
d
e
,
“
A
Brief
In
sig
h
t
in
to
Co
m
p
u
tatio
n
a
l
T
o
o
ls
in
Big
Da
ta
,”
In
tern
a
ti
o
n
a
l
Jo
u
rn
a
l
o
f
In
n
o
v
a
ti
o
n
&
A
d
v
a
n
c
e
m
e
n
t
in
Co
m
p
u
ter S
c
ien
c
e
,
v
o
l.
4
.
,
2
0
1
5
[8
]
S
.
P
.
M
e
n
o
n
,
N.
P
.
He
g
d
e
,
“
A
S
u
rv
e
y
o
f
T
o
o
ls
a
n
d
A
p
p
li
c
a
ti
o
n
s
in
Big
Da
ta
,”
IEE
E
9
th
In
tern
taio
n
a
l
Co
n
f
e
re
n
c
e
o
n
In
telli
g
e
n
t
S
y
ste
m
s an
d
Co
n
tr
o
ls,
2
0
1
5
[9
]
S
.
P
.
M
e
n
o
n
,
N.
P
.
He
g
d
e
,
“
T
h
e
C
rit
ica
l
Co
m
b
in
e
d
Ro
le
o
f
Bi
g
D
a
ta
A
n
a
l
y
ti
c
s
in
He
a
lt
h
Ca
re
,”
In
tern
a
ti
o
n
a
l
Jo
u
rn
a
l
o
f
I
m
a
g
in
g
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
,
2
0
1
5
[1
0
]
H.
M
.
Ch
e
n
,
R.
Ka
z
m
a
n
a
n
d
S
.
Ha
z
i
y
e
v
,
"
Ag
il
e
Big
Da
ta
A
n
a
l
y
ti
c
s
f
o
r
W
e
b
-
Ba
se
d
S
y
ste
m
s:
A
n
A
rc
h
it
e
c
tu
re
-
Ce
n
tri
c
A
p
p
ro
a
c
h
,
"
in
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Bi
g
Da
t
a
,
v
o
l
.
2
,
n
o
.
3
,
p
p
.
2
3
4
-
2
4
8
,
S
e
p
t.
1
2
0
1
6
.
[1
1
]
F
.
Da
b
e
k
a
n
d
J.
J.
Ca
b
a
n
,
"
A
G
ra
m
m
a
r
-
b
a
se
d
A
p
p
ro
a
c
h
f
o
r
M
o
d
e
l
in
g
Us
e
r
In
tera
c
ti
o
n
s
a
n
d
G
e
n
e
ra
t
in
g
S
u
g
g
e
sti
o
n
s
Du
rin
g
t
h
e
Da
ta
Ex
p
l
o
ra
ti
o
n
P
r
o
c
e
ss
,
"
in
IEE
E
T
ra
n
s
a
c
ti
o
n
s
o
n
V
isu
a
li
z
a
ti
o
n
a
n
d
C
o
mp
u
ter
Gr
a
p
h
ics
,
v
o
l.
2
3
,
n
o
.
1
,
p
p
.
4
1
-
5
0
,
Ja
n
.
2
0
1
7
.
[1
2
]
P
.
F
ia
d
in
o
,
P
.
Ca
sa
s,
A
.
D’A
l
c
o
n
z
o
,
M
.
S
c
h
iav
o
n
e
a
n
d
A
.
Ba
e
r,
"
G
r
a
sp
in
g
P
o
p
u
lar
A
p
p
li
c
a
ti
o
n
s
i
n
Ce
ll
u
la
r
Ne
tw
o
rk
s
W
it
h
Big
Da
ta
A
n
a
l
y
ti
c
s
P
latf
o
rm
s,"
in
IEE
E
T
ra
n
s
a
c
ti
o
n
s
o
n
Ne
two
rk
a
n
d
S
e
rv
ice
M
a
n
a
g
e
me
n
t
,
v
o
l
.
1
3
,
n
o
.
3
,
p
p
.
6
8
1
-
6
9
5
,
S
e
p
t.
2
0
1
6
.
[1
3
]
C.
Ord
o
n
e
z
,
Y.
Zh
a
n
g
a
n
d
W
.
Ca
b
re
ra
,
"
T
h
e
G
a
m
m
a
M
a
tri
x
to
S
u
m
m
a
rize
D
e
n
se
a
n
d
S
p
a
rse
Da
ta S
e
ts
f
o
r
Big
Da
ta
A
n
a
l
y
ti
c
s,
"
in
I
EE
E
T
r
a
n
s
a
c
ti
o
n
s o
n
K
n
o
w
led
g
e
a
n
d
Da
t
a
E
n
g
in
e
e
rin
g
,
v
o
l.
2
8
,
n
o
.
7
,
p
p
.
1
9
0
5
-
1
9
1
8
,
Ju
ly
1
2
0
1
6
.
[1
4
]
A
.
P
a
u
l,
A
.
A
h
m
a
d
,
M
.
M
.
Ra
th
o
re
a
n
d
S
.
Ja
b
b
a
r,
"
S
m
a
rtb
u
d
d
y
:
De
f
in
in
g
Hu
m
a
n
Be
h
a
v
io
rs
Us
in
g
Big
Da
ta
A
n
a
l
y
ti
c
s
in
S
o
c
ial
In
tern
e
t
o
f
T
h
in
g
s
,
"
in
IEE
E
W
ire
les
s
Co
mm
u
n
i
c
a
ti
o
n
s
,
v
o
l.
2
3
,
n
o
.
5
,
p
p
.
6
8
-
7
4
,
Oc
to
b
e
r
2
0
1
6
.
[1
5
]
G
.
S
h
e
n
g
,
X
.
Z
h
a
o
,
H.
Zh
a
n
g
,
Z.
L
v
a
n
d
H.
S
o
n
g
,
"
M
a
th
e
m
a
ti
c
a
l
M
o
d
e
ls
f
o
r
S
im
u
latin
g
Co
d
e
d
Dig
it
a
l
Co
m
m
u
n
ica
ti
o
n
:
A
Co
m
p
re
h
e
n
siv
e
T
u
to
rial
b
y
Big
D
a
ta
A
n
a
l
y
ti
c
s
in
C
y
b
e
r
-
P
h
y
sic
a
l
S
y
ste
m
s,"
i
n
IEE
E
Acc
e
ss
,
v
o
l.
4
,
n
o
.
,
p
p
.
9
0
1
8
-
9
0
2
6
,
2
0
1
6
.
[1
6
]
L
.
A
.
Ta
w
a
lb
e
h
,
R.
M
e
h
m
o
o
d
,
E.
Be
n
k
h
li
f
a
a
n
d
H.
S
o
n
g
,
"
M
o
b
il
e
Clo
u
d
Co
m
p
u
ti
n
g
M
o
d
e
l
a
n
d
Bi
g
Da
t
a
A
n
a
l
y
si
s
f
o
r
He
a
lt
h
c
a
re
A
p
p
li
c
a
ti
o
n
s,"
in
I
EE
E
Acc
e
ss
,
v
o
l.
4
,
n
o
.
,
p
p
.
6
1
7
1
-
6
1
8
0
,
2
0
1
6
.
[1
7
]
X
.
W
a
n
g
a
n
d
Y.
He
,
"
L
e
a
rn
in
g
fro
m
Un
c
e
rtain
t
y
f
o
r
Big
Da
ta:
F
u
tu
re
A
n
a
l
y
ti
c
a
l
Ch
a
ll
e
n
g
e
s
a
n
d
S
trate
g
ies
"
,
IEE
E
S
y
st
e
m
s,
M
a
n
,
a
n
d
Cy
b
e
rn
e
ti
c
s M
a
g
a
z
in
e
,
V
o
l
.
2
,
No
.
2
,
p
p
.
2
6
-
3
1
,
2
0
1
6
[1
8
]
P
.
Y.
W
u
,
C.
W
.
Ch
e
n
g
,
C.
D.
K
a
d
d
i,
J
.
V
e
n
u
g
o
p
a
lan
,
R.
Ho
f
fm
a
n
a
n
d
M
.
D.
W
a
n
g
,
"
–
Om
ic
a
n
d
El
e
c
tro
n
ic
He
a
lt
h
Re
c
o
rd
Big
Da
ta
A
n
a
ly
ti
c
s
f
o
r
P
r
e
c
isio
n
M
e
d
icin
e
,
"
i
n
IEE
E
T
r
a
n
sa
c
ti
o
n
s
o
n
Bi
o
me
d
ica
l
E
n
g
i
n
e
e
rin
g
,
v
o
l.
6
4
,
n
o
.
2
,
p
p
.
2
6
3
-
2
7
3
,
F
e
b
.
2
0
1
7
.
[1
9
]
J.
M
.
L
il
l
o
-
Ca
ste
ll
a
n
o
e
t
a
l
.
,
"
S
y
m
m
e
tri
c
a
l
Co
m
p
re
ss
io
n
Dista
n
c
e
f
o
r
A
rrh
y
th
m
ia
Disc
ri
m
in
a
ti
o
n
i
n
Clo
u
d
-
Ba
se
d
Bi
g
-
Da
ta
S
e
rv
ic
e
s,"
in
IEE
E
J
o
u
rn
a
l
o
f
Bi
o
me
d
ic
a
l
a
n
d
He
a
lt
h
In
fo
rm
a
ti
c
s
,
v
o
l.
1
9
,
n
o
.
4
,
p
p
.
1
2
5
3
-
1
2
6
3
,
Ju
ly
2
0
1
5
.
[2
0
]
G
.
C
a
v
a
ll
a
ro
,
M
.
Ried
e
l,
M
.
Ric
h
e
rz
h
a
g
e
n
,
J.
A
.
Be
n
e
d
ik
tsso
n
a
n
d
A
.
P
laz
a
,
"
On
Un
d
e
rsta
n
d
in
g
Big
Da
ta
I
m
p
a
c
ts
in
Re
m
o
tel
y
S
e
n
se
d
I
m
a
g
e
Clas
sif
ica
ti
o
n
Us
in
g
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
M
e
th
o
d
s,"
in
I
EE
E
J
o
u
rn
a
l
o
f
S
e
lec
ted
T
o
p
ics
in
A
p
p
li
e
d
Ea
rt
h
Ob
se
rv
a
ti
o
n
s
a
n
d
Rem
o
te
S
e
n
sin
g
,
v
o
l.
8
,
n
o
.
1
0
,
p
p
.
4
6
3
4
-
4
6
4
6
,
Oc
t.
2
0
1
5
.
[2
1
]
Q.
L
u
,
Z
.
L
i,
M
.
Kih
l
,
L
.
Z
h
u
a
n
d
W
.
Z
h
a
n
g
,
"
CF
4
BDA
:
A
Co
n
c
e
p
t
u
a
l
F
ra
m
e
w
o
rk
f
o
r
Big
Da
ta
A
n
a
l
y
ti
c
s
A
p
p
li
c
a
ti
o
n
s i
n
t
h
e
Clo
u
d
,
"
i
n
IE
EE
Acc
e
ss
,
v
o
l.
3
,
n
o
.
,
p
p
.
1
9
4
4
-
1
9
5
2
,
2
0
1
5
.
[2
1
]
S
.
P
.
M
e
n
o
n
,
N.
P
.
He
g
d
e
,
“
A
F
ra
m
e
w
o
rk
to
h
a
n
d
le
Da
ta
He
tero
g
e
n
e
it
y
Co
n
tex
tu
a
l
to
M
e
d
ica
l
B
ig
Da
ta”
,
IEE
E
-
In
tern
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Co
m
p
u
tati
o
n
a
l
I
n
telli
g
e
n
c
e
a
n
d
C
o
m
p
u
ti
n
g
Re
se
a
rc
h
,
2
0
1
5
[2
2
]
S
.
P
.
M
e
n
o
n
,
N.
P
.
He
g
d
e
,
“
P
re
d
ictiv
e
-
b
a
se
d
Da
ta
A
n
a
l
y
sis
f
o
r
A
d
d
re
ss
in
g
Da
ta
V
e
ra
c
it
y
P
ro
b
l
e
m
s
in
Co
m
p
lex
M
e
d
ica
l
Da
ta
k
,
”
UN
KN
O
W
N
[2
3
]
D.
S
in
g
h
,
D
.
Ro
y
a
n
d
C.
K.
M
o
h
a
n
,
"
Di
P
-
S
V
M
:
Distrib
u
ti
o
n
P
r
e
se
rv
in
g
Ke
rn
e
l
S
u
p
p
o
r
t
V
e
c
t
o
r
M
a
c
h
in
e
f
o
r
Big
Da
ta
"
,
in
IEE
E
T
r
a
n
sa
c
ti
o
n
s
o
n
B
ig
Da
t
a
,
v
o
l.
3
,
n
o
.
1
,
p
p
.
7
9
-
9
0
,
M
a
rc
h
1
2
0
1
7
.
[2
4
]
I.
H.
Ch
u
n
g
;
T
.
N.
S
a
in
a
t
h
;
B.
Ra
m
a
b
h
a
d
ra
n
;
M
.
P
ich
e
n
y
;
J.
Gu
n
n
e
ls;
V.
A
u
ste
l;
U.
C
h
a
u
h
a
ri;
B.
Kin
g
sb
u
ry
,
"
P
a
ra
ll
e
l
De
e
p
Ne
u
ra
l
Ne
t
w
o
rk
T
ra
in
in
g
f
o
r
Big
Da
ta
o
n
Blu
e
G
e
n
e
/Q,
"
in
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
P
a
ra
ll
e
l
a
n
d
Distrib
u
te
d
S
y
ste
m
s ,
v
o
l.
P
P
,
n
o
.
9
9
,
p
p
.
1
-
1
Evaluation Warning : The document was created with Spire.PDF for Python.