I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
1
5
,
No
.
4
,
A
u
g
u
s
t 2
0
2
6
,
p
p
.
3
6
8
3
~
3
6
9
1
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
15
.i
4
.
p
p
3
6
8
3
-
3
6
9
1
3683
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
H
y
brid d
eep l
ea
rning
mo
del f
o
r
th
e t
a
sk sche
duling
in cloud
co
mputing
K
a
v
it
a
R
a
ni
1
,
O
m
P
r
a
ka
s
h Sa
ng
wa
n
1
,
Rit
u G
a
rg
2
1
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
G
u
r
u
J
a
mb
h
e
sh
w
a
r
U
n
i
v
e
r
s
i
t
y
o
f
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
H
i
sar,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
,
N
a
t
i
o
n
a
l
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
K
u
r
u
k
s
h
e
t
r
a
,
Th
a
n
e
sar
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
2
8
,
2
0
2
5
R
ev
is
ed
J
u
n
1
0
,
2
0
2
6
Acc
ep
ted
J
u
l 9
,
2
0
2
6
Tas
k
sc
h
e
d
u
li
n
g
p
lay
s
a
c
ru
c
ial
ro
le
in
o
p
ti
m
izin
g
p
e
rfo
rm
a
n
c
e
,
re
d
u
c
in
g
c
o
sts,
a
n
d
e
n
h
a
n
c
in
g
sy
ste
m
re
li
a
b
il
it
y
b
y
e
fficie
n
tl
y
a
ll
o
c
a
ti
n
g
re
s
o
u
rc
e
s
t
o
wo
rk
l
o
a
d
s.
Tra
d
it
i
o
n
a
l
tas
k
sc
h
e
d
u
li
n
g
m
e
th
o
d
s lac
k
th
e
a
b
il
it
y
t
o
e
fficie
n
tl
y
m
a
n
a
g
e
wo
rk
l
o
a
d
s
a
n
d
re
so
u
rc
e
d
istri
b
u
ti
o
n
,
lea
d
i
n
g
to
p
o
te
n
ti
a
l
in
e
fficie
n
c
ies
in
p
e
rfo
rm
a
n
c
e
a
n
d
e
n
e
rg
y
c
o
n
su
m
p
ti
o
n
.
T
o
a
d
d
r
e
ss
th
e
se
li
m
it
a
ti
o
n
s,
a
d
v
a
n
c
e
d
tec
h
n
i
q
u
e
s lev
e
ra
g
in
g
d
e
e
p
lea
rn
i
n
g
a
n
d
re
in
fo
rc
e
m
e
n
t
lea
rn
in
g
a
re
e
x
p
lo
re
d
.
Th
is
stu
d
y
p
r
o
p
o
se
s
a
d
e
e
p
lea
rn
i
n
g
-
b
a
se
d
m
o
d
e
l
f
o
r
tas
k
sc
h
e
d
u
li
n
g
i
n
c
l
o
u
d
c
o
m
p
u
ti
n
g
.
T
h
e
m
o
d
e
l
e
m
p
lo
y
s
a
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
two
r
k
(CNN
)
to
p
re
d
ict
th
e
o
p
ti
m
a
l
m
a
c
h
in
e
s
fo
r
tas
k
a
ll
o
c
a
ti
o
n
.
Ad
d
it
i
o
n
a
ll
y
,
Q
-
lea
rn
in
g
is
i
n
teg
ra
ted
with
CNN
to
fa
c
il
it
a
te
l
o
a
d
s
h
ift
i
n
g
b
e
twe
e
n
m
a
c
h
in
e
s,
e
n
su
ri
n
g
e
ffi
c
ien
t
u
ti
l
iza
ti
o
n
o
f
re
so
u
rc
e
s.
T
h
e
d
a
tas
e
t
u
se
d
in
t
h
is
wo
rk
c
o
n
sists
o
f
tas
k
a
tt
rib
u
tes
,
su
c
h
a
s
e
x
e
c
u
ti
o
n
ti
m
e
,
re
so
u
rc
e
re
q
u
irem
e
n
ts,
wh
ic
h
we
re
lo
a
d
e
d
fro
m
a
CS
V
f
il
e
.
Co
m
p
a
ra
ti
v
e
a
n
a
ly
sis
with
e
x
isti
n
g
m
o
d
e
ls
sh
o
ws
th
a
t
th
e
p
r
o
p
o
se
d
a
p
p
r
o
a
c
h
a
c
h
iev
e
s
a
p
p
ro
x
ima
tely
9
4
%
a
c
c
u
ra
c
y
a
n
d
c
o
n
su
m
e
s
les
s
e
n
e
rg
y
th
a
n
o
th
e
r
m
o
d
e
ls,
d
e
m
o
n
stra
ti
n
g
it
s
e
ffe
c
ti
v
e
n
e
ss
in
c
lo
u
d
tas
k
sc
h
e
d
u
li
n
g
.
K
ey
w
o
r
d
s
:
C
lo
u
d
co
m
p
u
tin
g
C
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
Ma
ch
in
e
lear
n
in
g
Q
-
lear
n
in
g
T
ask
s
ch
ed
u
lin
g
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Kav
ita
R
an
i
D
e
p
a
r
t
m
e
n
t
o
f
C
o
m
p
u
t
e
r
S
c
ie
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
G
u
r
u
J
a
m
b
h
e
s
h
w
a
r
U
n
i
v
e
r
s
i
t
y
o
f
Sc
i
e
n
ce
a
n
d
T
e
c
h
n
o
l
o
g
y
His
ar
,
I
n
d
ia
E
m
ail:
k
.
g
h
an
g
h
as6
7
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
I
n
r
ec
e
n
t
y
ea
r
s
,
clo
u
d
co
m
p
u
tin
g
h
as
b
ec
o
m
e
in
teg
r
al
t
o
m
an
y
o
r
g
a
n
izatio
n
s
.
I
t
em
er
g
ed
to
m
ee
t
u
s
er
s
’
d
em
an
d
s
f
o
r
ac
ce
s
s
in
g
co
m
p
u
tin
g
r
eso
u
r
ce
s
an
d
s
er
v
i
ce
s
o
n
an
as
-
n
ee
d
ed
b
asis
th
r
o
u
g
h
in
ter
n
et
-
d
r
iv
e
n
ap
p
licatio
n
s
.
C
lo
u
d
co
m
p
u
tin
g
p
r
o
v
id
es
d
iv
er
s
e
s
er
v
ices
b
ased
o
n
u
s
er
r
eq
u
i
r
em
en
ts
[
1
]
,
[
2
]
,
in
teg
r
atin
g
d
is
tr
ib
u
ted
an
d
p
ar
allel
co
m
p
u
tin
g
u
n
d
er
a
"p
ay
-
p
er
-
u
s
e
"
m
o
d
el.
T
h
is
elim
in
ates
th
e
n
ee
d
f
o
r
u
s
er
s
to
p
u
r
ch
ase
s
o
f
twar
e
o
r
h
ar
d
war
e,
o
n
ly
an
in
ter
n
et
co
n
n
ec
tio
n
is
r
eq
u
ir
ed
.
I
n
f
r
astru
ctu
r
e
as
a
s
er
v
ice
(
I
aa
S)
is
a
p
r
o
m
in
e
n
t
m
o
d
el
t
h
at
o
f
f
er
s
v
ir
tu
al
s
er
v
e
r
s
f
o
r
d
ata
p
r
o
ce
s
s
in
g
an
d
s
to
r
ag
e
[
3
]
,
[
4
]
.
I
t
allo
ws
u
s
er
s
to
r
u
n
o
p
er
atin
g
s
y
s
tem
s
o
r
ap
p
licatio
n
s
o
n
r
en
ted
s
er
v
er
s
,
elim
in
atin
g
h
ar
d
war
e
m
ain
te
n
an
ce
.
I
aa
S
also
en
h
an
ce
s
p
er
f
o
r
m
an
ce
an
d
r
e
d
u
ce
s
laten
cy
b
y
o
f
f
er
in
g
s
er
v
er
ac
ce
s
s
in
n
ea
r
b
y
lo
ca
tio
n
s
.
Ser
v
ice
s
ar
e
g
o
v
er
n
ed
b
y
q
u
ality
o
f
s
er
v
ice
(
Qo
S)
p
a
r
am
eter
s
an
d
s
er
v
ice
lev
el
ag
r
ee
m
en
ts
(
SLAs)
,
with
p
ay
m
en
ts
b
ased
o
n
u
s
er
-
p
r
o
v
id
er
ag
r
ee
m
en
ts
[
5
]
,
[
6
]
.
Vir
tu
al
m
ac
h
in
es
u
s
e
h
o
s
t r
eso
u
r
ce
s
lik
e
R
AM
an
d
C
P
U
,
wh
ich
ca
n
lead
to
u
n
eq
u
al
r
eso
u
r
ce
d
is
tr
ib
u
tio
n
.
E
f
f
icien
t
task
s
ch
ed
u
lin
g
is
ess
en
tial
to
m
in
im
ize
waitin
g
tim
es
an
d
b
alan
ce
r
eso
u
r
ce
u
tili
za
tio
n
[
7
]
,
[
8
]
.
Ass
ig
n
in
g
im
p
r
o
p
e
r
v
ir
tu
al
m
ac
h
in
es
ca
n
ca
u
s
e
a
h
ig
h
l
o
ad
o
n
an
y
v
ir
tu
al
m
ac
h
in
es
an
d
im
p
ac
t
s
y
s
tem
p
er
f
o
r
m
an
ce
.
Ma
k
esp
an
,
co
s
t,
an
d
u
tili
za
tio
n
a
r
e
c
o
n
s
id
er
ed
k
ey
s
ch
ed
u
lin
g
f
ac
to
r
s
f
o
r
d
ete
r
m
in
in
g
s
ch
ed
u
les.
Dif
f
er
en
t
s
tr
ateg
ies
h
av
e
b
ee
n
d
ev
is
ed
to
d
y
n
am
i
ca
lly
lo
ad
-
b
alan
ce
task
s
.
B
ased
o
n
u
s
er
r
eq
u
est,
clo
u
d
b
r
o
k
er
s
allo
ca
te
clo
u
d
r
eso
u
r
ce
s
ef
f
icien
tly
to
m
ee
t
d
ea
d
lin
es
o
r
SLA
r
e
q
u
ir
em
en
ts
[
9
]
,
[
1
0
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
4
,
Au
g
u
s
t 2
0
2
6
:
3
6
8
3
-
3
6
9
1
3684
Per
f
o
r
m
an
ce
is
g
u
ar
a
n
teed
with
clo
u
d
s
er
v
ice
p
r
o
v
id
er
Qo
S
b
ased
ch
ec
k
s
.
Sch
ed
u
lin
g
m
ec
h
an
is
m
s
,
in
ac
co
r
d
an
ce
to
SLAs,
ar
e
o
f
c
r
itical
im
p
o
r
tan
ce
t
o
s
atis
f
y
u
s
er
ex
p
ec
tatio
n
s
[
1
1
]
,
[
1
2
]
.
T
h
e
f
o
llo
win
g
s
h
o
ws
h
o
w
h
y
p
er
v
is
o
r
s
ca
n
s
u
p
p
o
r
t
m
u
ltip
le
v
ir
tu
al
m
ac
h
in
es
o
n
a
s
in
g
le
h
ar
d
war
e
lay
er
.
T
h
ese
ar
e
s
till
a
p
r
ev
alen
t
p
r
o
b
lem
,
s
u
ch
as
in
s
u
f
f
icien
t
s
ch
ed
u
lin
g
an
d
in
ap
p
r
o
p
r
iate
task
d
eleg
atio
n
,
b
u
t
all
ar
e
es
s
en
tial.
T
o
en
s
u
r
e
p
r
o
ce
s
s
in
g
s
p
ee
d
a
n
d
t
o
p
r
e
v
en
t
im
b
alan
ce
i
n
th
e
s
y
s
tem
,
lo
ad
b
ala
n
cin
g
is
n
ee
d
ed
[
1
3
]
,
[
1
4
]
.
Ar
tific
ial
in
tellig
en
ce
(
AI
)
h
as
s
u
b
s
tan
tially
im
p
r
o
v
ed
task
s
ch
e
d
u
lin
g
with
in
tellig
en
t
r
eso
u
r
ce
o
p
tim
izatio
n
.
AI
tech
n
iq
u
es
s
u
ch
as
m
ac
h
in
e
lear
n
i
n
g
,
d
ee
p
lear
n
i
n
g
,
an
d
r
ein
f
o
r
ce
m
e
n
t
lear
n
i
n
g
p
r
e
d
ict
r
eso
u
r
ce
r
eq
u
ir
em
e
n
ts
,
o
p
tim
ize
e
n
er
g
y
co
n
s
u
m
p
tio
n
,
an
d
ad
j
u
s
t
r
eso
u
r
ce
s
to
ac
c
o
m
m
o
d
at
e
f
lu
ctu
atio
n
s
in
wo
r
k
lo
ad
s
[
1
5
]
,
[
1
6
]
.
Heu
r
is
tic
an
d
m
etah
eu
r
is
tic
alg
o
r
ith
m
s
s
u
ch
as
an
t
co
lo
n
y
o
p
tim
izatio
n
(
AC
O)
ca
n
b
e
u
s
ed
to
s
ea
r
ch
f
o
r
p
lace
m
e
n
t
o
p
tim
izatio
n
s
,
m
in
i
m
ized
i
d
le
tim
es,
an
d
e
n
h
an
ce
d
e
n
er
g
y
ef
f
icien
cy
.
AI
als
o
ca
n
p
la
y
a
r
o
le
in
m
u
lti
-
clo
u
d
p
r
ac
tices,
im
p
r
o
v
in
g
Q
o
S
an
d
s
ca
lab
ilit
y
.
T
o
r
ed
u
ce
en
er
g
y
u
s
ag
e
an
d
m
ax
im
ize
jo
b
d
is
tr
ib
u
tio
n
,
a
n
u
m
b
er
o
f
AI
-
b
ased
s
ch
ed
u
lin
g
alg
o
r
ith
m
s
h
av
e
b
ee
n
p
u
t
f
o
r
t
h
.
W
h
ile
d
ee
p
lear
n
in
g
m
o
d
els
m
ay
ex
tr
ac
t
in
tr
icate
task
r
elatio
n
s
h
ip
s
an
d
en
h
an
ce
s
ch
ed
u
lin
g
p
o
licies,
m
ac
h
in
e
lear
n
in
g
-
b
ased
ap
p
r
o
ac
h
es
u
s
e
h
is
to
r
ical
wo
r
k
lo
ad
p
at
ter
n
s
to
f
o
r
ec
ast
r
eso
u
r
ce
d
em
an
d
.
Usi
n
g
a
tr
ial
-
an
d
-
er
r
o
r
m
eth
o
d
o
lo
g
y
,
r
ein
f
o
r
ce
m
e
n
t
lear
n
in
g
tech
n
iq
u
es
lik
e
Q
-
lear
n
in
g
d
y
n
am
ical
ly
ad
ju
s
t
to
s
h
if
tin
g
wo
r
k
lo
ad
s
.
No
twith
s
tan
d
in
g
th
ese
d
ev
elo
p
m
e
n
ts
,
cu
r
r
e
n
t
ap
p
r
o
ac
h
es
h
a
v
e
th
e
d
r
awb
ac
k
s
lik
e
s
tatic
m
ac
h
in
e
lear
n
in
g
m
o
d
els
s
tr
u
g
g
le
with
r
ea
l
-
tim
e
wo
r
k
lo
a
d
f
lu
ctu
ati
o
n
s
an
d
f
ail
to
g
en
er
alize
well
i
n
r
ap
id
ly
ch
an
g
in
g
clo
u
d
e
n
v
ir
o
n
m
en
ts
.
Dee
p
le
ar
n
in
g
-
b
ased
m
o
d
els
o
f
ten
r
e
q
u
ir
e
e
x
ten
s
iv
e
tr
ai
n
in
g
d
ata
an
d
c
o
m
p
u
tatio
n
al
r
eso
u
r
ce
s
,
m
ak
in
g
th
em
less
e
f
f
icien
t in
r
ea
l
-
tim
e
s
ch
e
d
u
lin
g
.
T
h
e
co
n
v
en
tio
n
al
clo
u
d
task
s
ch
ed
u
lin
g
a
p
p
r
o
ac
h
es
s
u
f
f
er
f
r
o
m
s
ev
er
al
d
r
awb
ac
k
s
,
th
i
s
r
esear
ch
p
r
o
p
o
s
es
a
h
y
b
r
id
d
ee
p
r
ei
n
f
o
r
ce
m
en
t
lear
n
in
g
m
eth
o
d
b
a
s
ed
o
n
c
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
(
C
NN)
an
d
Q
-
lear
n
in
g
to
o
v
er
co
m
e
th
e
lim
itatio
n
s
o
f
th
e
co
n
v
e
n
tio
n
al
ap
p
r
o
ac
h
es
f
o
r
s
ch
ed
u
l
in
g
task
s
in
clo
u
d
co
m
p
u
tin
g
en
v
ir
o
n
m
en
ts
.
T
h
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
u
s
es
C
NNs
to
lear
n
p
atter
n
s
o
f
task
attr
ib
u
tes
an
d
r
eso
u
r
ce
u
s
ag
e
d
ata
to
d
er
iv
e
th
e
f
ea
tu
r
es
o
f
t
h
e
task
s
an
d
s
elec
t
s
u
itab
le
v
ir
tu
al
m
ac
h
in
e
s
f
o
r
allo
ca
tio
n
.
T
o
im
p
r
o
v
e
th
e
u
s
e
o
f
th
e
r
es
o
u
r
ce
s
with
o
u
t
co
n
s
u
m
in
g
t
o
o
m
u
ch
en
er
g
y
,
ad
ap
tiv
e
lo
ad
b
ala
n
cin
g
is
in
co
r
p
o
r
ated
,
wh
er
e
o
p
tim
al
t
ask
m
ig
r
atio
n
s
tr
ateg
ies
ar
e
d
y
n
am
ically
s
elec
ted
b
ased
o
n
th
e
cu
r
r
en
t
s
y
s
tem
s
tate,
as
d
eter
m
in
ed
b
y
th
e
Q
-
lear
n
in
g
.
T
h
e
p
r
o
p
o
s
ed
f
r
am
e
wo
r
k
is
ev
alu
ated
ag
ain
s
t
th
e
cu
r
r
en
t
s
ch
ed
u
lin
g
m
eth
o
d
s
b
y
im
p
lem
en
tin
g
it
in
Py
th
o
n
,
a
n
d
co
m
p
a
r
in
g
it
with
th
e
o
t
h
er
s
u
s
in
g
p
e
r
f
o
r
m
an
ce
m
etr
ics
lik
e
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
e
n
er
g
y
co
n
s
u
m
p
tio
n
,
an
d
task
ex
ec
u
tio
n
tim
e.
T
h
e
r
esu
lts
o
f
th
e
ex
p
e
r
im
en
ts
s
h
o
w
th
at
th
e
h
y
b
r
id
is
m
o
r
e
ac
cu
r
ate
at
9
4
%,
wh
ile
r
e
d
u
cin
g
en
er
g
y
co
n
s
u
m
p
tio
n
an
d
in
cr
ea
s
in
g
th
e
ef
f
icien
cy
o
f
th
e
tim
e
s
p
en
t
o
n
th
e
task
co
m
p
a
r
ed
to
tr
a
d
itio
n
al
AI
-
b
ased
s
ch
ed
u
lin
g
.
2.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
Var
m
a
an
d
B
en
d
i
[
1
7
]
p
r
o
p
o
s
ed
a
h
y
b
r
id
task
s
ch
e
d
u
lin
g
ap
p
r
o
ac
h
th
at
in
teg
r
ates
th
e
Al
-
B
ir
u
n
i
ea
r
th
n
am
ib
b
ee
tle
o
p
tim
izatio
n
(
B
E
NB
O)
alg
o
r
ith
m
with
b
id
ir
ec
tio
n
al
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
B
i
-
L
STM
)
n
etwo
r
k
to
ad
d
r
ess
m
u
lti
-
o
b
jectiv
e
o
p
tim
izatio
n
ch
alle
n
g
es
in
clo
u
d
c
o
m
p
u
tin
g
.
I
n
th
is
ap
p
r
o
ac
h
,
a
co
m
b
in
atio
n
o
f
s
ch
ed
u
lin
g
s
o
l
u
tio
n
s
g
en
er
ate
d
b
y
th
e
B
E
N
B
O
o
p
tim
izer
an
d
t
h
e
B
i
-
L
STM
m
o
d
el
is
u
s
ed
t
o
g
en
er
ate
an
o
p
tim
ized
task
allo
ca
tio
n
s
tr
ateg
y
.
T
h
e
h
y
b
r
id
a
p
p
r
o
ac
h
s
u
cc
ess
f
u
lly
r
ed
u
ce
s
th
e
m
ak
esp
an
an
d
u
tili
za
tio
n
o
f
th
e
r
eso
u
r
ce
s
.
I
t
was
test
ed
with
r
esp
ec
t
to
im
p
o
r
tan
t
p
er
f
o
r
m
an
ce
cr
iter
i
a
s
u
ch
as
en
e
r
g
y
co
n
s
u
m
p
tio
n
,
r
eso
u
r
ce
u
tili
za
tio
n
,
an
d
m
ak
esp
a
n
.
T
h
e
v
alu
e
s
o
b
tain
ed
in
th
e
ex
p
er
im
en
tal
r
esu
lts
wer
e
0
.
6
6
9
,
0
.
5
3
5
,
an
d
0
.
3
8
1
in
ter
m
s
o
f
e
n
er
g
y
co
n
s
u
m
p
tio
n
,
r
eso
u
r
ce
u
tili
za
tio
n
,
an
d
m
ak
esp
an
,
r
esp
ec
tiv
ely
,
s
h
o
win
g
h
o
w
ef
f
ec
tiv
e
t
h
e
p
r
o
p
o
s
ed
s
c
h
ed
u
lin
g
tech
n
iq
u
e
was.
C
h
en
an
d
Z
h
en
g
[
1
8
]
p
r
o
p
o
s
e
d
an
AI
-
b
ased
s
ch
ed
u
lin
g
m
et
h
o
d
f
o
r
h
ete
r
o
g
e
n
eo
u
s
b
ig
d
at
a
n
etwo
r
k
in
f
o
r
m
atio
n
s
ec
u
r
ity
.
T
h
e
s
im
u
latio
n
r
esu
lts
in
d
icate
d
its
lo
ad
b
alan
cin
g
p
er
f
o
r
m
an
c
e
was
g
o
o
d
in
th
e
h
eter
o
g
en
e
o
u
s
b
i
g
d
ata
n
etwo
r
k
s
'
in
f
o
r
m
atio
n
task
s
ch
ed
u
li
n
g
.
M
o
r
eo
v
e
r
,
th
e
s
ch
ed
u
lin
g
m
eth
o
d
h
ad
a
g
r
ea
t
g
lo
b
al
s
ea
r
ch
an
d
p
a
r
allel
s
ea
r
ch
ab
ilit
y
,
wh
ich
was
s
u
itab
le
f
o
r
th
e
lar
g
e
-
s
ca
le
in
f
o
r
m
atio
n
o
p
tim
izatio
n
ap
p
licatio
n
in
h
eter
o
g
e
n
eo
u
s
b
ig
d
ata
n
etwo
r
k
s
.
T
o
p
r
ed
ict
th
e
wo
r
k
lo
ad
o
f
f
u
tu
r
e
task
s
,
h
y
b
r
i
d
p
r
ed
ictio
n
f
r
am
ewo
r
k
was
p
r
o
p
o
s
ed
L
u
e
t
a
l.
[
1
9
]
,
wh
ich
co
m
b
in
es
th
e
au
t
o
r
eg
r
ess
iv
e
in
teg
r
ated
m
o
v
in
g
a
v
e
r
ag
e
(
AR
I
MA
)
m
o
d
el
with
g
ated
r
ec
u
r
r
e
n
t
u
n
it
(
GR
U)
m
o
d
el.
T
h
e
p
r
o
p
o
s
ed
s
ch
ed
u
lin
g
s
tr
ateg
y
was
to
f
o
r
m
m
u
ltip
le
p
r
io
r
ity
q
u
eu
es,
wh
ich
will
ex
er
cise
th
e
h
ig
h
e
r
p
r
io
r
ity
task
f
ir
s
t,
an
d
lo
wer
p
r
io
r
ity
task
s
ec
o
n
d
.
Mo
r
e
o
v
er
,
f
ac
to
r
s
lik
e
co
m
p
u
tatio
n
al
r
eso
u
r
ce
co
n
s
u
m
ed
,
m
o
d
el
tr
ain
in
g
ti
m
e
,
an
d
p
r
ed
ictio
n
ac
cu
r
ac
y
wer
e
tak
e
n
in
to
ac
co
u
n
t
w
h
ile
f
o
r
m
u
latin
g
th
e
r
ein
f
o
r
ce
m
e
n
t
lear
n
in
g
r
ewa
r
d
f
u
n
ctio
n
.
As
th
e
task
s
ar
o
u
n
d
th
e
d
ee
p
lear
n
i
n
g
p
r
o
ce
s
s
r
ea
ch
ed
'
co
n
v
er
g
e'
s
tag
e,
th
e
n
u
m
b
e
r
o
f
r
eso
u
r
ce
s
b
ein
g
s
en
t
to
c
o
n
v
er
g
ed
o
r
co
m
p
leted
task
s
was
p
r
o
g
r
ess
iv
ely
s
ca
led
b
ac
k
an
d
r
ea
llo
ca
ted
to
war
d
o
th
er
p
e
n
d
in
g
task
s
in
o
r
d
er
to
o
p
tim
ize
th
e
o
v
e
r
all
r
eso
u
r
c
es
u
tili
za
tio
n
.
T
h
e
ef
f
ec
tiv
en
ess
o
f
th
e
p
r
o
p
o
s
ed
r
ein
f
o
r
ce
m
e
n
t
lear
n
in
g
-
b
ased
p
er
f
o
r
m
an
ce
-
tim
e
o
p
tim
ized
(
R
L
PTO
)
m
eth
o
d
in
s
ca
lin
g
-
u
p
to
lar
g
e
-
s
ca
le
d
ata
s
ets
was
d
em
o
n
s
tr
ated
th
r
o
u
g
h
ex
p
er
im
en
tal
test
s
co
n
d
u
c
ted
b
y
u
s
in
g
m
o
r
e
co
m
p
u
tin
g
n
o
d
es,
th
er
eb
y
s
h
o
win
g
g
o
o
d
s
ca
les an
d
ad
a
p
ts
to
d
is
tr
ib
u
ted
c
o
m
p
u
tin
g
en
v
ir
o
n
m
en
ts
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Hyb
r
id
d
ee
p
lea
r
n
in
g
mo
d
el
f
o
r
th
e
ta
s
k
s
ch
ed
u
lin
g
i
n
clo
u
d
co
mp
u
tin
g
(
K
a
vita
R
a
n
i
)
3685
Fo
r
th
e
task
s
ch
ed
u
lin
g
alg
o
r
ith
m
ev
alu
atio
n
,
C
h
h
a
b
r
a
an
d
Ar
o
r
a
[
2
0
]
ca
m
e
u
p
with
a
m
eth
o
d
o
lo
g
y
f
o
r
ass
ig
n
in
g
weig
h
ts
to
v
a
r
io
u
s
p
er
f
o
r
m
an
ce
attr
ib
u
tes
b
ased
o
n
t
h
eir
f
r
e
q
u
en
c
y
o
f
o
cc
u
r
r
en
ce
a
n
d
s
ig
n
if
ican
ce
.
T
h
e
f
o
r
m
e
r
wei
g
h
ted
attr
i
b
u
tes
wer
e
th
en
co
m
b
in
ed
to
c
alcu
late
p
r
io
r
ity
s
co
r
es
wh
ich
wer
e
in
tu
r
n
u
s
ed
to
esti
m
ate
th
e
p
er
f
o
r
m
an
ce
o
f
ea
c
h
al
g
o
r
ith
m
o
f
t
h
e
v
ar
i
o
u
s
s
ch
ed
u
lin
g
alg
o
r
ith
m
s
.
I
n
ad
d
itio
n
,
th
e
s
tu
d
y
p
r
o
p
o
s
ed
a
m
ac
h
in
e
lear
n
in
g
b
ased
ap
p
r
o
ac
h
an
d
u
tili
ze
d
f
ea
tu
r
e
s
elec
tio
n
tec
h
n
iq
u
es
to
f
in
d
th
e
m
o
s
t
s
u
itab
le
s
ch
ed
u
lin
g
tech
n
iq
u
es
f
o
r
clo
u
d
co
m
p
u
tin
g
en
v
ir
o
n
m
en
ts
.
T
h
e
f
in
d
in
g
s
d
em
o
n
s
tr
ated
th
at
in
teg
r
atin
g
AI
with
clo
u
d
r
eso
u
r
ce
m
an
a
g
em
en
t
en
h
an
ce
s
s
ch
ed
u
lin
g
ef
f
icien
cy
,
im
p
r
o
v
es
r
eso
u
r
ce
u
t
ilizatio
n
,
an
d
lead
s
to
b
etter
o
v
e
r
all
s
y
s
tem
p
er
f
o
r
m
an
ce
.
T
o
s
o
lv
e
th
e
m
u
lti
-
o
b
jectiv
e
task
s
ch
ed
u
lin
g
p
r
o
b
lem
f
o
r
in
d
ep
en
d
en
t
clo
u
d
co
m
p
u
ti
n
g
task
s
,
Kr
u
ek
ae
w
an
d
Kim
p
a
n
[
2
1
]
u
s
ed
th
e
ar
tific
ial
b
ee
co
l
o
n
y
(
AB
C
)
o
p
tim
izatio
n
alg
o
r
ith
m
an
d
th
e
Q
-
lear
n
i
n
g
r
ein
f
o
r
ce
m
e
n
t
lear
n
i
n
g
a
p
p
r
o
ac
h
.
T
h
e
co
m
b
in
atio
n
o
f
Q
-
lear
n
in
g
e
n
h
an
ce
d
th
e
ex
p
l
o
r
atio
n
/ex
p
lo
itatio
n
p
r
o
p
er
t
y
o
f
AB
C
alg
o
r
ith
m
l
ea
d
in
g
t
o
f
aster
co
n
v
er
g
en
ce
an
d
b
etter
s
ch
e
d
u
lin
g
d
ec
is
i
o
n
s
.
T
h
e
p
r
o
p
o
s
ed
m
u
lti
-
o
b
jectiv
e
ar
tific
ial
b
ee
co
lo
n
y
alg
o
r
ith
m
with
Q
-
lear
n
in
g
(
MO
AB
C
Q
)
alg
o
r
ith
m
was
ex
p
er
im
en
tally
test
ed
with
a
f
ew
o
f
th
e
ex
is
ti
n
g
s
ch
ed
u
lin
g
alg
o
r
ith
m
s
.
T
h
e
r
esu
lt
o
f
th
e
ex
p
er
im
e
n
ts
s
h
o
wed
th
at
th
e
h
y
b
r
i
d
m
eth
o
d
r
ed
u
ce
d
m
ak
esp
a
n
an
d
ex
ec
u
tio
n
co
s
t,
en
h
an
ce
d
th
e
wo
r
k
lo
ad
d
is
tr
ib
u
tio
n
,
in
cr
e
ased
th
e
th
r
o
u
g
h
p
u
t
an
d
also
im
p
r
o
v
ed
th
e
o
v
er
all
u
tili
za
tio
n
o
f
th
e
r
eso
u
r
ce
s
wh
en
co
m
p
a
r
ed
to
t
h
e
co
m
p
ar
ati
v
e
alg
o
r
ith
m
s
.
I
n
t
h
i
s
r
eg
ar
d
,
T
a
l
o
u
k
i
e
t
a
l
.
[
2
2
]
p
r
o
p
o
s
e
d
a
t
a
s
k
s
c
h
ed
u
l
i
n
g
a
l
g
o
r
i
t
h
m
b
a
s
ed
o
n
a
l
i
s
t
,
w
h
i
c
h
u
s
e
s
a
n
i
m
p
r
o
v
ed
t
a
s
k
p
r
io
r
i
t
i
z
a
t
i
o
n
s
tr
a
t
e
g
y
an
d
t
a
s
k
d
u
p
l
i
c
a
t
io
n
s
tr
a
t
e
g
ie
s
t
o
en
h
an
c
e
t
h
e
s
c
h
ed
u
l
in
g
e
f
f
i
c
i
en
cy
.
T
h
e
p
r
o
p
o
s
e
d
a
p
p
r
o
a
ch
u
s
e
s
o
p
t
im
i
s
t
i
c
co
s
t
t
a
b
l
e
d
o
wn
w
a
r
d
(
O
C
T
d
)
an
d
o
p
t
im
i
s
t
i
c
c
o
s
t
t
a
b
le
u
p
w
a
r
d
(
O
C
T
u
)
p
r
o
c
e
d
u
r
e
s
to
id
e
n
t
if
y
p
r
i
o
r
i
t
ie
s
o
f
ta
s
k
s
an
d
to
cr
e
a
t
e
a
n
o
p
t
im
i
z
e
d
s
eq
u
e
n
c
e
o
f
e
x
e
cu
t
i
o
n
.
T
h
e
p
r
o
p
o
s
e
d
ap
p
r
o
a
ch
h
a
s
b
e
e
n
e
v
a
l
u
a
t
ed
ag
a
i
n
s
t
th
e
e
x
i
s
t
i
n
g
s
ch
e
d
u
l
in
g
a
l
g
o
r
i
th
m
s
a
n
d
i
t
h
a
s
b
e
en
p
r
o
v
e
d
th
a
t
i
t
p
e
r
f
o
r
m
s
b
e
t
t
er
i
n
t
er
m
s
o
f
v
a
r
io
u
s
im
p
o
r
t
an
t
s
c
h
ed
u
l
in
g
m
e
tr
i
c
s
s
u
ch
a
s
m
a
k
e
s
p
a
n
,
s
p
ee
d
u
p
,
s
p
ee
d
u
p
-
to
-
lo
ad
r
a
t
i
o
(
S
L
R
)
,
an
d
ex
ec
u
t
i
o
n
ef
f
i
c
ie
n
cy
,
w
h
i
ch
s
h
o
w
s
i
t
s
m
er
i
t
in
ta
s
k
s
c
h
e
d
u
l
i
n
g
o
p
t
i
m
i
za
t
i
o
n
.
T
h
e
p
r
o
v
is
io
n
in
g
an
d
s
ch
e
d
u
l
in
g
o
f
r
eso
u
r
c
es
in
clo
u
d
co
m
p
u
tin
g
en
v
ir
o
n
m
en
ts
h
av
e
i
n
cr
ea
s
in
g
ly
b
ec
o
m
e
a
ch
allen
g
e
d
u
e
to
th
e
g
r
o
win
g
c
o
m
p
lex
ity
o
f
th
es
e
en
v
ir
o
n
m
en
ts
,
w
h
ich
r
ely
o
n
v
ir
tu
al
m
ac
h
in
es
h
o
s
ted
o
n
p
h
y
s
ical
in
f
r
astru
ctu
r
e
in
clo
u
d
s
er
v
ice
p
r
o
v
i
d
er
d
ata
ce
n
ter
s
[
2
3
]
.
T
h
e
au
th
o
r
s
p
r
o
p
o
s
ed
a
f
r
am
ewo
r
k
u
s
in
g
th
e
alg
o
r
ith
m
ca
lled
q
u
an
tile
r
e
g
r
ess
io
n
d
ee
p
Q
-
n
etwo
r
k
(
QR
-
DQN)
to
o
p
tim
ize
th
e
p
er
f
o
r
m
an
ce
o
f
r
eso
u
r
ce
m
a
n
a
g
em
en
t
an
d
s
ch
ed
u
lin
g
.
T
h
is
r
ein
f
o
r
ce
m
e
n
t
lear
n
in
g
m
eth
o
d
is
cr
ea
ted
to
lear
n
an
o
p
tim
al
p
o
licy
f
o
r
l
o
n
g
-
t
er
m
r
eso
u
r
ce
allo
ca
tio
n
an
d
s
ch
ed
u
lin
g
d
ec
is
io
n
s
.
R
esu
lts
in
d
icate
d
th
at
th
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
im
p
r
o
v
e
d
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
task
s
ch
ed
u
lin
g
an
d
im
p
r
o
v
e
d
th
e
ef
f
icien
cy
o
f
clo
u
d
r
eso
u
r
ce
u
tili
za
tio
n
in
th
e
co
m
p
u
tin
g
e
n
v
ir
o
n
m
en
t.
Swar
u
p
et
a
l.
[
2
4
]
d
is
cu
s
s
ed
th
e
u
s
e
o
f
clo
u
d
co
m
p
u
tin
g
f
o
r
v
ar
io
u
s
ap
p
licatio
n
s
s
u
ch
as
d
ata
an
aly
tics
,
d
ata
s
to
r
ag
e
,
an
d
in
ter
n
et
o
f
th
in
g
s
(
I
o
T
)
.
T
h
e
s
t
u
d
y
was
ce
n
ter
ed
o
n
task
s
ch
ed
u
lin
g
p
r
o
b
lem
in
clo
u
d
en
v
ir
o
n
m
en
t,
tar
g
etin
g
to
m
in
im
izin
g
co
m
p
u
tatio
n
r
eso
u
r
ce
s
r
eq
u
ir
e
d
to
s
atis
f
y
th
e
r
eso
u
r
ce
av
ailab
ilit
y
an
d
ap
p
licatio
n
d
ea
d
lin
e
co
n
s
tr
ain
t.
T
h
e
au
t
h
o
r
s
p
r
esen
ted
a
r
ein
f
o
r
ce
m
en
t
lear
n
in
g
-
b
ased
s
ch
ed
u
lin
g
m
eth
o
d
,
clip
p
e
d
d
o
u
b
le
d
ee
p
Q
-
lear
n
in
g
(
C
DDQL
)
in
o
r
d
er
to
ac
h
iev
e
t
h
is
o
b
jectiv
e.
T
h
e
ap
p
r
o
ac
h
ap
p
lied
ex
p
er
ien
ce
r
ep
lay
an
d
a
tar
g
et
n
etwo
r
k
to
ac
h
iev
e
a
m
o
r
e
s
tab
le
lear
n
in
g
an
d
b
etter
s
ch
ed
u
lin
g
d
ec
is
io
n
s
.
E
x
p
er
i
m
en
tal
r
esu
lts
s
h
o
wed
t
h
at
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
was
ab
le
to
o
p
tim
ally
s
ch
ed
u
le
task
s
wh
ile
p
r
eser
v
in
g
th
e
r
eso
u
r
ce
an
d
d
ea
d
lin
e
c
o
n
s
tr
ain
ts
.
Als
aid
y
et
a
l.
[
2
5
]
s
u
g
g
ested
an
o
p
tim
ized
e
x
ec
u
tio
n
o
f
t
h
e
p
ar
ticle
s
war
m
o
p
tim
izatio
n
(
PS
O)
u
s
ed
to
s
u
p
p
o
r
t
th
e
p
e
r
f
o
r
m
a
n
ce
o
f
task
s
ch
ed
u
lin
g
in
a
clo
u
d
co
m
p
u
tin
g
s
y
s
tem
.
T
h
e
au
th
o
r
s
u
s
ed
two
h
eu
r
is
tic
-
b
ased
in
itializatio
n
m
eth
o
d
s
wh
ich
ar
e
lo
n
g
est
jo
b
to
f
astes
t
p
r
o
ce
s
s
o
r
(
L
J
FP
)
an
d
m
in
im
u
m
co
m
p
letio
n
tim
e
(
MCT)
to
cr
ea
te
g
o
o
d
in
itial
p
ar
ticles
p
o
p
u
latio
n
to
th
e
PS
O
alg
o
r
ith
m
.
T
h
e
in
ten
tio
n
o
f
th
ese
in
itializatio
n
p
r
o
ce
d
u
r
es
was
to
f
ac
ilit
ate
th
e
s
ea
r
ch
p
r
o
ce
s
s
an
d
s
p
ee
d
u
p
th
e
c
o
n
v
er
g
en
ce
to
o
p
tim
al
s
ch
ed
u
lin
g
s
o
lu
tio
n
s
.
T
h
e
p
r
o
p
o
s
ed
L
J
FP
-
PS
O
alg
o
r
ith
m
an
d
MCT
-
PS
O
alg
o
r
ith
m
h
a
v
e
b
ee
n
test
ed
with
s
im
u
latio
n
an
d
co
m
p
ar
ed
wi
th
th
e
PS
O
alg
o
r
ith
m
an
d
s
o
m
e
ex
is
tin
g
task
s
ch
ed
u
lin
g
alg
o
r
ith
m
s
.
T
h
e
ex
p
er
im
en
tal
r
esu
lts
s
h
o
wed
t
h
at
b
o
t
h
th
e
h
y
b
r
id
m
eth
o
d
s
g
av
e
b
etter
s
ch
ed
u
lin
g
p
er
f
o
r
m
an
ce
co
m
p
ar
ed
to
th
e
b
en
ch
m
ar
k
alg
o
r
ith
m
s
an
d
wer
e
m
o
r
e
e
f
f
icien
t a
n
d
ef
f
ec
tiv
e
in
ter
m
s
o
f
o
v
er
all
p
e
r
f
o
r
m
an
ce
.
3.
M
E
T
H
O
D
I
n
th
is
r
esear
ch
,
a
h
y
b
r
i
d
d
ee
p
lear
n
in
g
m
o
d
el
in
teg
r
atin
g
C
NN
an
d
Q
-
lear
n
in
g
is
p
r
o
p
o
s
ed
f
o
r
task
s
ch
ed
u
lin
g
in
clo
u
d
co
m
p
u
ti
n
g
en
v
ir
o
n
m
e
n
ts
.
T
h
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
c
o
n
s
id
er
s
r
eso
u
r
ce
co
n
s
tr
ain
ts
,
d
y
n
am
ic
task
allo
ca
tio
n
,
an
d
m
ac
h
in
e
u
tili
za
tio
n
to
g
en
e
r
ate
ef
f
icien
t
s
ch
ed
u
lin
g
d
ec
is
io
n
s
.
B
y
co
m
b
i
n
in
g
th
e
f
ea
tu
r
e
ex
tr
ac
tio
n
ca
p
a
b
ilit
y
o
f
C
NN
with
th
e
ad
ap
tiv
e
d
ec
is
io
n
-
m
ak
in
g
ab
ilit
y
o
f
Q
-
lear
n
i
n
g
,
th
e
m
o
d
el
aim
s
to
im
p
r
o
v
e
task
allo
ca
tio
n
a
n
d
r
eso
u
r
ce
m
an
a
g
em
en
t.
T
h
e
e
f
f
ec
tiv
en
ess
o
f
th
e
p
r
o
p
o
s
ed
s
ch
ed
u
lin
g
a
p
p
r
o
ac
h
is
ev
alu
ated
u
s
in
g
k
ey
p
er
f
o
r
m
an
ce
m
etr
ics,
in
clu
d
in
g
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
en
e
r
g
y
co
n
s
u
m
p
tio
n
,
to
ass
es
s
b
o
th
s
ch
ed
u
lin
g
q
u
ality
an
d
o
v
er
all
s
y
s
tem
ef
f
icien
cy
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
4
,
Au
g
u
s
t 2
0
2
6
:
3
6
8
3
-
3
6
9
1
3686
3
.
1
.
Sy
s
t
e
m
mo
del
W
o
r
k
f
lo
w
d
iag
r
am
,
as
s
h
o
w
n
in
F
ig
u
r
e
1
,
u
s
es
r
ei
n
f
o
r
ce
m
en
t
lear
n
in
g
to
o
p
tim
ize
task
s
ch
ed
u
lin
g
u
n
d
er
r
eso
u
r
ce
co
n
s
tr
ain
ts
.
I
t
co
n
s
is
ts
o
f
th
r
ee
k
e
y
p
a
r
ts
:
th
e
en
v
ir
o
n
m
en
t,
r
ein
f
o
r
ce
m
en
t
lear
n
in
g
a
g
en
t,
a
n
d
ev
alu
atio
n
o
f
p
er
f
o
r
m
an
ce
m
o
d
u
le.
E
n
v
ir
o
n
m
e
n
t
is
a
d
y
n
am
ic
task
s
ch
ed
u
lin
g
s
y
s
tem
wit
h
task
s
r
ep
r
esen
ted
b
y
th
e
r
eso
u
r
ce
u
s
ag
e
,
an
d
s
ch
ed
u
lin
g
s
tatu
s
.
B
ased
o
n
r
eso
u
r
ce
c
o
n
s
tr
ain
ts
an
d
s
ch
ed
u
lin
g
ef
f
icien
cy
,
r
ein
f
o
r
ce
m
e
n
t
lear
n
in
g
ag
e
n
t
ch
o
o
s
es
ac
tio
n
s
(
task
as
s
ig
n
m
en
ts
)
an
d
g
ets
r
ewa
r
d
/p
u
n
is
h
m
en
t.
Q
-
v
alu
es
ar
e
p
r
ed
icted
u
s
in
g
a
d
ee
p
Q
-
lear
n
in
g
m
o
d
el
with
a
n
eu
r
al
n
et
wo
r
k
.
T
h
e
a
g
en
t
u
s
es
th
e
-
g
r
ee
d
y
alg
o
r
ith
m
to
ch
o
o
s
e
b
etwe
en
ex
p
lo
r
in
g
a
n
d
ex
p
lo
itin
g
.
T
h
e
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
MSE
)
lo
s
s
is
e
m
p
lo
y
ed
d
u
r
in
g
th
e
tr
ain
in
g
o
f
t
h
e
n
etwo
r
k
with
Ad
am
o
p
tim
izer
.
T
h
e
ac
c
u
r
a
cy
,
p
r
ec
is
io
n
,
r
ec
all
,
an
d
en
e
r
g
y
c
o
n
s
u
m
p
tio
n
is
u
s
ed
to
ass
es
s
p
er
f
o
r
m
an
ce
.
T
h
e
s
y
s
tem
is
d
e
s
ig
n
ed
to
m
an
ag
e
th
e
allo
ca
tio
n
o
f
r
eso
u
r
ce
s
ef
f
icien
tly
an
d
to
r
ed
u
ce
am
o
u
n
t
o
f
r
eso
u
r
ce
s
u
s
ed
.
Fig
u
r
e
1
.
W
o
r
k
f
lo
w
o
f
th
e
p
r
o
p
o
s
ed
task
s
ch
ed
u
lin
g
ap
p
r
o
ac
h
3.
2
.
P
urpo
s
ed
m
o
del
I
n
th
is
p
r
o
p
o
s
ed
m
et
h
o
d
o
lo
g
y
,
r
ein
f
o
r
ce
m
en
t
lear
n
in
g
,
al
o
n
g
with
th
e
C
NNs
is
s
h
o
w
n
to
b
e
an
ef
f
ec
tiv
e
co
m
b
i
n
atio
n
to
s
o
l
v
e
co
m
p
lex
task
s
ch
ed
u
lin
g
p
r
o
b
lem
s
in
clo
u
d
co
m
p
u
ti
n
g
.
T
h
is
ap
p
r
o
ac
h
co
m
b
in
es
th
e
id
ea
s
o
f
r
ein
f
o
r
ce
m
en
t
lear
n
in
g
a
n
d
C
NNs
—
r
ein
f
o
r
ce
m
e
n
t
lear
n
in
g
f
o
r
m
a
k
in
g
ad
a
p
tatio
n
s
o
f
d
ec
is
io
n
s
,
an
d
C
NNs
f
o
r
o
u
ts
t
an
d
in
g
f
ea
tu
r
e
lear
n
in
g
ca
p
ac
i
ty
,
wh
ich
is
h
el
p
f
u
l
f
o
r
ef
f
icien
t
s
ch
ed
u
lin
g
i
n
a
d
y
n
am
ic
clo
u
d
en
v
ir
o
n
m
e
n
t.
On
e
o
f
th
e
g
r
ea
test
s
tr
en
g
th
s
o
f
d
ee
p
lear
n
in
g
is
its
ab
ilit
y
to
lear
n
en
d
-
to
-
en
d
,
m
ea
n
in
g
th
at
it
ca
n
lear
n
to
e
x
tr
ac
t
m
ea
n
i
n
g
f
u
l
ch
a
r
ac
ter
is
tics
f
r
o
m
r
aw
i
n
p
u
ts
with
o
u
t
t
h
e
n
ee
d
to
h
a
n
d
cr
a
f
t
th
em
.
T
h
is
f
ea
tu
r
e
en
ab
les
a
m
o
r
e
r
eliab
le
s
ch
ed
u
lin
g
d
ec
i
s
io
n
an
d
en
ab
les
th
e
m
o
d
el
t
o
b
e
ad
ap
ted
to
a
b
r
o
ad
s
et
o
f
clo
u
d
c
o
m
p
u
tin
g
ap
p
licatio
n
s
.
1
D
-
C
NNs
h
av
e
r
ec
en
tly
b
ee
n
s
h
o
wn
to
attain
h
ig
h
p
er
f
o
r
m
a
n
ce
o
n
p
r
o
ce
s
s
in
g
s
tr
u
ctu
r
ed
clo
u
d
d
atasets
,
s
u
ch
as
task
s
ch
ed
u
lin
g
,
lo
ad
b
alan
cin
g
an
d
s
o
o
n
.
C
NNs
ar
e
a
ty
p
e
o
f
f
ee
d
-
f
o
r
war
d
d
ee
p
n
eu
r
al
n
etwo
r
k
th
at
co
n
tain
s
a
n
u
m
b
er
o
f
co
n
v
o
lu
tio
n
al
lay
er
s
wh
ich
p
r
o
g
r
ess
iv
ely
lear
n
to
r
ep
r
esen
t
f
ea
tu
r
es
at
d
if
f
er
en
t
lev
els
ab
o
v
e
wh
ich
is
p
ass
ed
to
an
o
u
tp
u
t
lay
er
th
at
u
s
es
th
e
f
ea
tu
r
es
it
h
as lea
r
n
ed
to
m
ak
e
th
e
f
in
al
p
r
ed
ictio
n
.
Fig
u
r
e
2
s
h
o
ws an
a
r
ch
itectu
r
e
o
f
th
e
p
r
o
p
o
s
ed
C
NN
.
Fig
u
r
e
2
.
Pro
p
o
s
ed
ar
c
h
itectu
r
e
o
f
C
NN
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Hyb
r
id
d
ee
p
lea
r
n
in
g
mo
d
el
f
o
r
th
e
ta
s
k
s
ch
ed
u
lin
g
i
n
clo
u
d
co
mp
u
tin
g
(
K
a
vita
R
a
n
i
)
3687
As
illu
s
tr
ated
in
Fig
u
r
e
2
,
ea
c
h
co
n
v
o
lu
tio
n
al
s
tag
e
is
co
m
p
o
s
ed
o
f
a
s
et
o
f
lear
n
a
b
le
co
n
v
o
lu
tio
n
al
f
ilter
s
f
o
llo
wed
b
y
a
p
o
o
lin
g
lay
er
.
Du
r
in
g
f
ea
tu
r
e
e
x
tr
ac
tio
n
,
th
e
in
p
u
t
d
ata
p
ass
es
s
eq
u
en
tially
th
r
o
u
g
h
th
ese
s
tag
es,
en
ab
lin
g
th
e
n
etwo
r
k
to
lear
n
i
n
cr
ea
s
in
g
ly
c
o
m
p
le
x
an
d
task
-
s
p
ec
if
ic
f
ea
tu
r
e
r
e
p
r
esen
tatio
n
s
.
T
h
is
h
ier
ar
ch
ical
lear
n
in
g
p
r
o
ce
s
s
allo
ws
th
e
C
NN
to
ca
p
tu
r
e
m
ea
n
in
g
f
u
l
p
atter
n
s
f
r
o
m
clo
u
d
c
o
m
p
u
tin
g
d
ata,
th
er
eb
y
im
p
r
o
v
in
g
th
e
e
f
f
ec
tiv
en
ess
o
f
task
s
ch
e
d
u
lin
g
.
Fig
u
r
e
3
p
r
esen
ts
th
e
o
v
e
r
all
ar
ch
itectu
r
e
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
alo
n
g
with
th
e
d
is
tr
ib
u
tio
n
o
f
its
k
ey
p
a
r
am
eter
s
.
Fig
u
r
e
3
.
Ov
e
r
all
ar
ch
itectu
r
e
o
f
th
e
p
r
o
p
o
s
ed
task
s
ch
ed
u
lin
g
m
o
d
el
T
h
e
C
NN
co
n
s
is
t
s
o
f
s
ev
er
al
im
p
o
r
tan
t
lay
er
s
s
u
ch
as
th
e
in
p
u
t
lay
er
,
co
n
v
o
l
u
tio
n
al
lay
e
r
,
p
o
o
lin
g
lay
er
,
f
u
lly
co
n
n
ec
ted
lay
er
,
an
d
o
u
tp
u
t
lay
er
.
T
h
e
in
p
u
t
lay
er
p
r
o
ce
s
s
es
m
u
ltid
im
en
s
io
n
al
d
ata
in
th
e
s
tr
u
ctu
r
ed
f
o
r
m
at,
an
d
f
ea
tu
r
e
s
to
b
e
p
ass
ed
to
th
e
n
etwo
r
k
ar
e
o
f
ten
p
r
e
p
r
o
ce
s
s
ed
to
r
em
o
v
e
d
im
en
s
io
n
ality
(
n
o
r
m
alize
d
)
b
ef
o
r
e
b
ein
g
f
ed
in
to
th
e
n
etwo
r
k
.
T
h
is
n
o
r
m
a
lizatio
n
p
r
o
ce
s
s
b
o
o
s
ts
ef
f
icien
cy
in
lear
n
in
g
an
d
o
p
tim
izes
th
e
m
o
d
el
p
er
f
o
r
m
a
n
ce
.
T
h
e
lear
n
ab
le
k
er
n
els
in
th
e
co
n
v
o
lu
tio
n
al
lay
er
c
o
n
v
o
l
v
e
its
in
p
u
t
f
ea
t
u
r
e
m
ap
s
f
r
o
m
th
e
p
r
e
v
io
u
s
lay
er
,
an
d
th
en
ap
p
ly
a
n
o
n
lin
ea
r
ac
tiv
atio
n
f
u
n
ctio
n
to
g
en
er
ate
a
f
ea
tu
r
e
m
ap
.
E
ac
h
lay
er
p
r
o
d
u
ce
s
o
u
tp
u
t
b
y
p
er
f
o
r
m
in
g
a
n
u
m
b
er
o
f
c
o
n
v
o
lu
ti
o
n
o
p
e
r
atio
n
s
o
n
t
h
e
v
ar
io
u
s
f
ea
tu
r
e
r
ep
r
esen
tatio
n
s
o
f
i
n
p
u
t.
T
h
e
c
o
r
r
esp
o
n
d
in
g
m
ath
em
atica
l f
o
r
m
u
latio
n
o
f
th
is
p
r
o
ce
s
s
is
g
iv
en
in
(
1
)
.
+
1
(
)
=
∗
(
)
+
(
1
)
I
n
th
is
in
f
o
r
m
atio
n
,
d
en
o
tes
t
h
e
weig
h
ts
o
f
th
e
ith
f
ilter
k
er
n
el
at
lay
e
r
l,
wh
ile
d
en
o
tes
th
e
b
ias
o
f
th
e
ith
f
ilter
k
er
n
el
at
la
y
er
l
,
x
(
)
r
ef
er
s
to
t
h
e
jth
lo
ca
l
r
e
g
io
n
at
lay
e
r
l,
an
d
+
1
(
)
r
ep
r
esen
ts
th
e
in
p
u
t
o
f
th
e
jth
n
e
u
r
o
n
in
f
r
am
e
i
o
f
lay
er
"l+
1
"
.
T
h
e
s
y
m
b
o
l
*
r
e
p
r
esen
ts
th
e
o
p
er
atio
n
o
f
d
o
t
p
r
o
d
u
ct
b
etwe
en
th
e
co
n
v
o
l
u
tio
n
al
k
er
n
el
an
d
th
e
l
o
ca
l
r
ec
ep
tiv
e
f
ield
it
is
u
s
ed
with
.
On
ce
t
h
e
c
o
n
v
o
lu
tio
n
p
r
o
ce
s
s
is
f
in
is
h
ed
,
a
n
ac
tiv
atio
n
f
u
n
ctio
n
is
ap
p
lied
to
th
e
g
en
er
ate
d
f
ea
tu
r
e
m
ap
s
to
ad
d
n
o
n
-
lin
ea
r
ity
in
to
th
e
f
ea
tu
r
e
m
ap
s
.
W
h
en
th
is
s
tep
is
ap
p
lied
,
th
e
m
u
lti
-
d
im
en
s
io
n
al
f
ea
t
u
r
es
ex
t
r
ac
ted
f
r
o
m
th
e
d
ata
m
a
y
n
o
t
b
e
li
n
ea
r
ly
s
ep
a
r
ab
le
i
n
th
e
o
r
ig
in
al
f
ea
tu
r
e
s
p
ac
e,
b
u
t
th
ey
b
ec
o
m
e
m
o
r
e
lin
ea
r
ly
s
ep
ar
ab
le
in
th
e
h
ig
h
er
-
d
im
e
n
s
io
n
al
s
p
ac
e.
T
h
e
r
ec
tifie
d
lin
ea
r
u
n
it (
R
eL
U)
ac
tiv
atio
n
f
u
n
ctio
n
is
u
s
ed
in
th
i
s
s
tu
d
y
.
I
t h
as sev
er
al
o
f
its
m
er
its
,
o
n
e
b
ein
g
th
at
its
g
r
ad
ien
t
is
f
ix
ed
(
eq
u
al
to
1
)
f
o
r
th
e
p
o
s
itiv
e
in
p
u
t
v
alu
es,
s
o
as
to
o
f
f
s
et
th
e
v
a
n
is
h
in
g
g
r
ad
ien
t
p
r
o
b
lem
in
tr
ain
in
g
.
T
h
e
m
ath
em
atica
l d
e
s
cr
ip
tio
n
o
f
th
e
R
eL
U
f
u
n
ctio
n
is
g
iv
en
as in
(
2
)
.
+
1
(
)
=
(
+
1
(
)
)
=
{
0
,
+
1
(
)
}
(
2
)
I
n
th
is
co
n
tex
t
+
1
(
)
r
ep
r
esen
ts
th
e
o
u
tp
u
t
v
alu
e
o
b
tain
d
af
ter
co
n
v
o
lu
tio
n
o
p
er
atio
n
,
wh
ile
+
1
(
)
s
h
o
ws
th
e
ac
tiv
atio
n
v
alu
e
o
f
+
1
(
)
.
T
h
e
aim
o
f
th
e
p
o
o
lin
g
lay
er
is
to
d
ec
r
ea
s
e
th
e
d
im
en
s
io
n
ality
o
f
th
e
f
ea
tu
r
e
m
ap
s
b
y
d
o
wn
s
am
p
lin
g
f
ea
tu
r
e
m
ap
s
th
at
ar
e
m
a
d
e
u
p
o
f
la
r
g
e
in
p
u
t
m
atr
ices
to
s
m
aller
f
ea
tu
r
e
m
ap
s
.
T
h
is
s
ig
n
if
ican
tly
d
im
in
is
h
es
th
e
am
o
u
n
t
o
f
p
a
r
am
eter
s
to
b
e
lear
n
ed
an
d
d
ec
r
ea
s
es
th
e
co
m
p
u
tatio
n
al
co
m
p
lex
ity
an
d
also
h
elp
s
p
r
ev
en
t o
v
er
f
itti
n
g
th
e
m
o
d
el.
Ma
x
p
o
o
lin
g
is
o
n
e
o
f
th
e
m
o
s
t
p
o
p
u
lar
p
o
o
lin
g
m
eth
o
d
s
,
w
h
ich
p
ick
s
o
u
t th
e
lar
g
est v
alu
e
in
e
ac
h
r
ec
ep
tiv
e
f
ield
.
Ma
th
d
ef
i
n
itio
n
o
f
m
ax
p
o
o
lin
g
is
d
ef
in
ed
in
(
3
)
.
+
1
(
)
=
{
(
)
}
(
−
1
)
+
1
≤
≤
(
3
)
Her
e,
(
)
r
ep
r
esen
ts
th
e
tth
n
eu
r
o
n
’
s
v
alu
e
in
th
e
ith
f
ea
tu
r
e
at
l
lay
er
,
(
∈
[
(
−
1
)
+
1
,
]
)
;
W
is
th
e
p
o
o
li
n
g
r
e
g
io
n
’
s
wi
d
t
h
.
Als
o
,
t
h
e
n
e
u
r
o
n
’
s
v
a
lu
e
a
t
la
y
er
"l
+
1
"
is
+
1
(
)
.
Af
te
r
t
h
e
last
p
o
o
li
n
g
l
a
y
e
r
,
t
h
e
r
e
is
a
f
u
l
ly
c
o
n
n
ec
t
e
d
la
y
er
.
T
h
is
la
s
t p
o
o
li
n
g
s
t
ag
e
g
e
n
e
r
a
tes
f
e
at
u
r
e
m
a
p
s
t
h
a
t a
r
e
f
lat
te
n
e
d
i
n
t
o
a
o
n
e
d
im
en
s
io
n
a
l
v
ec
to
r
an
d
th
at'
s
u
s
ed
as
in
p
u
t
to
th
e
f
u
lly
c
o
n
n
ec
ted
la
y
er
.
T
h
is
lay
er
h
as
ea
ch
in
p
u
t
n
eu
r
o
n
lin
k
ed
t
o
all
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
4
,
Au
g
u
s
t 2
0
2
6
:
3
6
8
3
-
3
6
9
1
3688
o
u
tp
u
t
n
eu
r
o
n
s
,
en
ab
lin
g
th
e
n
etwo
r
k
to
i
n
teg
r
ate
th
e
l
o
ca
l
p
atter
n
o
f
f
ea
tu
r
es
ca
p
t
u
r
ed
b
y
th
e
co
n
v
o
lu
tio
n
al
an
d
p
o
o
lin
g
lay
er
s
in
t
o
a
s
in
g
le,
g
lo
b
al
r
ep
r
esen
tatio
n
.
T
h
e
i
n
teg
r
ated
r
ep
r
esen
tatio
n
is
th
e
n
em
p
lo
y
ed
f
o
r
th
e
f
in
al
class
if
icatio
n
o
r
p
r
e
d
ictio
n
.
T
h
e
f
u
lly
co
n
n
ec
ted
la
y
er
c
an
b
e
m
ath
e
m
atica
lly
d
escr
ib
e
d
as
(
4
)
.
+
1
(
)
=
(
∑
∑
=
1
=
1
(
)
+
)
(
4
)
W
h
er
e
is
th
e
weig
h
t
c
o
n
n
ec
ti
n
g
th
e
tth
n
eu
r
o
n
in
th
e
ith
f
ea
tu
r
e
at
la
y
er
l
to
t
h
e
jth
n
eu
r
o
n
at
lay
er
"l+
1
".
T
h
e
lo
g
it
v
alu
e
co
r
r
esp
o
n
d
in
g
to
th
e
jth
n
eu
r
o
n
at
lay
er
"l+
1
"
is
+
1
(
)
.
Mo
r
e
o
v
er
,
th
e
n
etwo
r
k
o
f
f
s
et
is
wh
ile
(
)
is
th
e
tth
n
eu
r
o
n
’
s
o
u
t
p
u
t
v
al
u
e
in
th
e
ith
f
ea
tu
r
e
at
th
e
p
r
ec
ed
in
g
la
y
er
l.
Fin
all
y
,
(
∙
)
is
th
e
ac
tiv
atio
n
f
u
n
ctio
n
R
eL
U.
A
s
o
f
tm
ax
class
if
ier
is
g
e
n
er
ally
em
p
lo
y
ed
in
th
e
o
u
tp
u
t
lay
er
t
o
g
e
n
er
ate
th
e
f
in
al
class
lab
el
p
r
ed
ictio
n
s
.
T
h
e
s
o
f
tm
ax
f
u
n
ctio
n
is
a
n
ex
te
n
s
io
n
o
f
lo
g
is
tic
r
eg
r
ess
io
n
t
o
m
u
lti
-
class
p
r
o
b
lem
s
,
n
o
r
m
alizin
g
r
aw
s
co
r
es
f
r
o
m
th
e
lo
g
is
tic
r
eg
r
ess
io
n
o
u
tp
u
t
to
p
r
o
d
u
ce
n
o
r
m
alize
d
p
r
o
b
a
b
ilit
y
d
is
tr
ib
u
tio
n
s
.
T
h
is
p
r
o
p
e
r
ty
m
a
k
es
it
u
s
ef
u
l
in
m
u
lti
-
class
class
if
icatio
n
p
r
o
b
lem
s
f
o
r
ass
ig
n
in
g
ea
c
h
in
p
u
t
s
am
p
le
to
o
n
e
o
f
th
e
d
if
f
er
e
n
t c
lass
es a
cc
o
r
d
in
g
to
th
e
h
ig
h
est p
r
o
b
ab
ilit
y
,
as
d
ef
in
ed
in
(
5
)
.
(
)
=
(
(
)
)
=
(
)
∑
(
)
=
1
(
5
)
Her
e
(
)
r
ef
er
s
to
th
e
lo
g
it
p
r
o
d
u
ce
d
b
y
th
e
j
-
t
h
n
eu
r
o
n
i
n
th
e
o
u
tp
u
t
lay
e
r
a
n
d
is
th
e
n
u
m
b
er
o
f
ta
r
g
et
class
es.
T
h
e
C
NN
i
s
a
ty
p
e
o
f
n
eu
r
al
n
etwo
r
k
t
h
at
p
r
o
ce
s
s
es
in
f
o
r
m
atio
n
i
n
a
s
eq
u
e
n
ce
o
r
a
v
ec
to
r
o
f
d
ata,
wh
ich
is
r
ef
er
r
ed
t
o
as
a
1
D
-
C
NN.
Hen
ce
,
o
n
e
-
d
im
en
s
io
n
a
l
co
n
v
o
lu
tio
n
al
f
ilter
s
ar
e
u
s
ed
in
t
h
e
n
etwo
r
k
t
o
ca
p
tu
r
e
th
e
m
ea
n
in
g
f
u
l
p
atter
n
s
,
alo
n
g
a
s
in
g
le
d
im
en
s
io
n
.
As
a
r
esu
lt,
th
e
co
n
v
o
lu
tio
n
al
an
d
p
o
o
lin
g
lay
er
s
g
en
er
ate
o
n
e
-
d
im
e
n
s
io
n
al
f
ea
t
u
r
e
r
ep
r
esen
tatio
n
s
an
d
th
ese
a
r
e
th
en
ap
p
lied
to
class
if
icatio
n
o
r
p
r
ed
ictio
n
.
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
I
n
th
is
s
tu
d
y
,
th
e
task
s
ch
e
d
u
lin
g
f
o
r
clo
u
d
co
m
p
u
tin
g
with
m
ac
h
in
e
lear
n
in
g
tec
h
n
iq
u
es
is
d
is
cu
s
s
ed
.
T
h
e
p
r
o
p
o
s
ed
f
r
a
m
ewo
r
k
u
s
es
a
C
NN
to
p
er
f
o
r
m
m
ac
h
i
n
e
lev
el
p
r
ed
ictio
n
an
d
th
e
m
eth
o
d
o
f
Q
-
lear
n
in
g
to
h
elp
s
h
if
t
th
e
lo
ad
d
y
n
am
ically
b
etwe
en
m
ac
h
in
es.
T
h
e
ef
f
ec
tiv
en
ess
o
f
t
h
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
is
ass
e
s
s
ed
ag
ain
s
t
an
estab
lis
h
ed
ap
p
r
o
ac
h
b
ased
o
n
a
n
u
m
b
er
o
f
m
et
r
ics.
Fo
r
th
is
,
th
e
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all
,
an
d
en
e
r
g
y
co
n
s
u
m
p
tio
n
ar
e
tak
en
in
to
ac
co
u
n
t
t
o
e
v
alu
ate
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
s
ch
ed
u
lin
g
m
o
d
el.
T
h
e
r
esu
lts
o
f
p
e
r
f
o
r
m
an
ce
an
aly
s
is
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
a
r
e
s
h
o
wn
in
T
a
b
le
1
.
T
ab
le
1
.
Per
f
o
r
m
an
ce
an
aly
s
is
o
f
task
s
ch
ed
u
lin
g
m
eth
o
d
s
M
o
d
e
l
A
c
c
u
r
a
c
y
(
%)
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
N
e
u
r
a
l
n
e
t
w
o
r
k
s
[
2
6
]
8
4
.
1
0
84
84
D
y
n
a
mi
c
r
e
s
o
u
r
c
e
a
l
l
o
c
a
t
i
o
n
[
1
5
]
8
6
.
1
0
86
86
P
r
o
p
o
se
d
9
2
.
3
4
92
92
T
h
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
was
test
ed
in
ter
m
s
o
f
its
ef
f
ec
tiv
en
ess
ag
ain
s
t
th
e
ex
is
t
in
g
task
s
ch
ed
u
lin
g
m
eth
o
d
s
lik
e
n
eu
r
al
n
etwo
r
k
-
b
ased
m
o
d
els
an
d
d
y
n
am
ic
r
e
s
o
u
r
ce
allo
ca
tio
n
m
eth
o
d
s
as
s
h
o
wn
in
Fig
u
r
e
4
.
W
h
en
co
m
p
ar
in
g
th
e
p
r
o
p
o
s
e
d
m
o
d
el
with
th
e
ex
is
tin
g
m
o
d
els,
th
e
ac
c
u
r
ac
y
,
p
r
ec
is
io
n
,
an
d
r
ec
all
v
alu
es
ar
e
co
n
s
is
ten
tly
h
ig
h
er
with
ea
ch
p
er
f
o
r
m
an
ce
m
etr
ic
b
ein
g
ab
o
v
e
9
0
%.
T
h
e
r
esu
lts
f
r
o
m
th
e
af
o
r
em
en
tio
n
ed
,
clea
r
ly
s
u
r
p
ass
th
e
b
en
c
h
m
ar
k
m
eth
o
d
s
.
T
h
e
im
p
r
o
v
e
d
p
e
r
f
o
r
m
a
n
ce
m
a
y
b
e
d
u
e
to
th
e
m
o
d
el'
s
ab
ilit
y
to
r
ep
r
esen
t
th
e
co
m
p
lex
ch
a
r
ac
ter
is
tics
o
f
task
s
an
d
to
p
r
o
ce
s
s
lar
g
e
-
s
ca
le,
tim
e
-
d
ep
en
d
e
n
t
d
ata.
C
o
n
v
en
tio
n
al
n
eu
r
al
n
etwo
r
k
-
b
ased
ap
p
r
o
ac
h
es
an
d
d
y
n
a
m
ic
r
eso
u
r
ce
all
o
ca
tio
n
m
et
h
o
d
s
,
h
o
wev
er
,
te
n
d
to
wo
r
k
well
in
s
im
p
ler
s
ettin
g
s
b
u
t
h
av
e
d
r
a
wb
ac
k
s
o
f
s
ca
lab
ilit
y
an
d
p
r
e
d
ictio
n
in
lar
g
e
r
an
d
m
o
r
e
co
m
p
lex
d
ep
lo
y
m
en
t
o
f
clo
u
d
wo
r
k
l
o
ad
s
.
T
h
u
s
,
th
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
is
m
o
r
e
ap
p
r
o
p
r
iate
f
o
r
lar
g
e
-
s
ca
le
clo
u
d
co
m
p
u
tin
g
en
v
ir
o
n
m
en
ts
wh
er
e
r
ea
l
-
tim
e
s
ch
ed
u
lin
g
d
ec
is
io
n
s
m
u
s
t
b
e
tak
en
an
d
ef
f
icien
t
r
eso
u
r
ce
m
an
ag
e
m
en
t
is
d
esire
d
.
Mo
r
e
o
v
er
,
th
e
ac
h
ie
v
ed
im
p
r
o
v
e
m
en
t
d
em
o
n
s
tr
at
es
th
e
b
en
e
f
its
o
f
c
o
m
b
in
in
g
d
ee
p
lear
n
in
g
an
d
r
ein
f
o
r
ce
m
e
n
t
lear
n
in
g
to
e
n
h
an
ce
task
s
ch
ed
u
lin
g
p
e
r
f
o
r
m
an
ce
.
Ov
e
r
all,
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
m
o
d
el
p
r
esen
ted
in
Fig
u
r
e
4
is
s
at
is
f
ac
to
r
y
,
co
n
f
ir
m
in
g
th
e
r
o
b
u
s
tn
ess
an
d
ef
f
icien
c
y
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
f
o
r
v
ar
i
o
u
s
ev
alu
atio
n
m
etr
ics.
T
h
e
r
esu
lts
o
f
th
e
en
er
g
y
e
f
f
icien
cy
an
aly
s
is
o
f
th
e
n
e
u
r
al
n
etwo
r
k
s
[
2
6
]
is
1
1
.
2
jo
u
les,
d
y
n
am
ic
r
eso
u
r
ce
allo
ca
tio
n
[
1
5
]
is
9
.
5
j
o
u
les,
a
n
d
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
is
6
.
5
jo
u
les
.
As
it
i
s
s
h
o
wn
in
Fig
u
r
e
5
,
th
e
en
er
g
y
ef
f
icien
cy
o
f
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
is
co
m
p
ar
ed
with
ex
is
tin
g
alg
o
r
ith
m
s
lik
e
n
eu
r
al
n
etwo
r
k
s
an
d
d
y
n
am
ic
r
e
s
o
u
r
ce
allo
ca
tio
n
.
T
h
e
an
al
y
s
is
s
h
o
ws
th
at
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
is
th
e
m
o
s
t e
n
er
g
y
s
av
in
g
al
g
o
r
ith
m
c
o
m
p
ar
ed
to
o
t
h
er
alg
o
r
ith
m
s
.
I
n
c
lo
u
d
en
v
i
r
o
n
m
e
n
ts
wh
er
e
en
e
r
g
y
co
n
s
u
m
p
tio
n
is
s
u
p
p
o
s
ed
to
b
e
d
esire
d
,
co
n
s
u
m
in
g
to
o
m
u
ch
en
er
g
y
ca
u
s
es
o
p
er
atio
n
al
co
s
ts
to
in
cr
ea
s
e
an
d
im
p
ac
ts
to
th
e
en
v
ir
o
n
m
en
t.
T
h
e
s
u
g
g
ested
m
o
d
el
k
ee
p
s
th
e
r
eso
u
r
ce
co
n
ten
tio
n
as
lo
w
as
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Hyb
r
id
d
ee
p
lea
r
n
in
g
mo
d
el
f
o
r
th
e
ta
s
k
s
ch
ed
u
lin
g
i
n
clo
u
d
co
mp
u
tin
g
(
K
a
vita
R
a
n
i
)
3689
p
o
s
s
ib
le
an
d
e
n
er
g
y
u
s
ag
e
as
lo
w
as
p
o
s
s
ib
le
as
well.
As
s
h
o
wn
in
Fig
u
r
e
5
,
th
e
p
r
o
p
o
s
e
d
m
eth
o
d
r
esu
lts
in
th
e
lo
west
en
er
g
y
co
n
s
u
m
p
tio
n
(
6
.
5
j
o
u
les),
in
co
m
p
ar
is
o
n
with
th
e
tr
ad
itio
n
al
m
eth
o
d
s
.
T
h
is
s
u
b
s
tan
tial
cu
t
is
d
u
e
to
b
etter
task
p
r
e
d
ictio
n
an
d
th
e
m
o
r
e
ef
f
ec
tiv
e
u
s
e
o
f
r
eso
u
r
ce
s
.
I
n
o
r
d
er
to
en
c
o
u
r
ag
e
s
u
s
tain
ab
le
u
s
ag
e
o
f
clo
u
d
c
o
m
p
u
tin
g
it is
cr
u
cial
to
in
tr
o
d
u
ce
m
et
h
o
d
s
th
at
s
av
e
en
er
g
y
in
th
e
s
ch
ed
u
lin
g
p
r
o
ce
d
u
r
e.
T
h
e
en
er
g
y
-
s
av
in
g
f
ea
tu
r
e
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
r
esu
lts
in
it
b
ei
n
g
a
p
o
ten
tial
s
o
lu
tio
n
d
esig
n
f
o
r
im
p
lem
en
tatio
n
o
f
th
is
k
in
d
o
f
clo
u
d
a
p
p
licatio
n
in
r
ea
l lif
e
,
f
o
r
wh
ich
e
n
er
g
y
is
a
cr
itical
f
ac
to
r
.
Fig
u
r
e
4
.
Per
f
o
r
m
an
c
e
co
m
p
ar
is
o
n
o
f
task
s
ch
ed
u
lin
g
m
eth
o
d
s
Fig
u
r
e
5
.
E
n
er
g
y
ef
f
icien
c
y
co
m
p
ar
is
o
n
o
f
task
s
ch
ed
u
lin
g
m
eth
o
d
s
5.
CO
NCLU
SI
O
N
Ma
p
R
ed
u
ce
is
a
p
o
p
u
lar
p
r
o
g
r
am
m
in
g
p
a
r
ad
ig
m
f
o
r
th
e
p
a
r
allel
p
r
o
ce
s
s
in
g
o
f
m
ass
iv
e
am
o
u
n
ts
o
f
d
ata
in
a
clo
u
d
-
b
ased
co
m
p
u
tin
g
en
v
ir
o
n
m
e
n
t,
d
e
v
elo
p
ed
b
y
Go
o
g
le.
I
t
h
as
two
m
ain
p
h
ases
:
m
ap
a
n
d
r
ed
u
ce
.
Du
r
in
g
th
e
m
ap
p
h
ase,
th
e
lar
g
e
s
ets
o
f
u
s
er
d
ata
ar
e
b
r
o
k
en
in
t
o
s
m
aller
s
u
b
-
task
s
an
d
th
en
th
ey
ar
e
s
ch
ed
u
led
an
d
ass
ig
n
ed
t
o
th
e
av
ailab
le
clo
u
d
r
eso
u
r
ce
s
in
an
ap
p
r
o
p
r
iate
way
,
u
s
in
g
ap
p
r
o
p
r
iate
s
ch
ed
u
lin
g
s
tr
ateg
ies.
T
h
e
in
ter
m
ed
iate
r
esu
lts
ar
e
s
en
t
to
th
e
r
ed
u
ce
p
h
ase
af
ter
th
ey
ar
e
p
r
o
d
u
ce
d
o
n
th
e
d
is
tr
ib
u
ted
co
m
p
u
tin
g
n
o
d
es,
an
d
f
in
ally
th
e
r
esu
lt
is
s
en
t
to
th
e
u
s
er
.
T
h
is
way
,
it
b
ec
o
m
es
ea
s
ier
to
p
er
f
o
r
m
a
lo
t
o
f
co
m
p
lex
p
r
o
ce
s
s
in
g
task
s
,
an
d
it
also
m
ak
es
th
e
p
r
o
ce
s
s
f
aster
.
T
h
is
s
tu
d
y
aim
s
t
o
p
r
o
p
o
s
e
a
d
ee
p
lear
n
in
g
b
ased
m
o
d
el
f
o
r
task
s
ch
ed
u
lin
g
in
clo
u
d
co
m
p
u
tin
g
an
d
im
p
lem
en
t it
in
p
y
th
o
n
.
T
h
e
ef
f
ec
tiv
en
ess
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
is
co
m
p
ar
ed
to
t
h
e
ex
is
tin
g
m
eth
o
d
s
lik
e
n
eu
r
al
n
etwo
r
k
s
an
d
d
y
n
am
ic
r
eso
u
r
ce
allo
ca
tio
n
tech
n
i
q
u
es
.
E
x
p
er
i
m
en
tal
r
esu
lts
s
h
o
w
t
h
at
th
e
p
r
o
p
o
s
ed
m
o
d
el
s
h
o
ws
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
a
n
d
r
ec
all
g
r
ea
ter
th
a
n
9
2
%,
wh
ile
co
m
p
ar
ativ
e
m
o
d
els s
h
o
w
ap
p
r
o
x
im
ately
8
% less
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
4
,
Au
g
u
s
t 2
0
2
6
:
3
6
8
3
-
3
6
9
1
3690
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Kav
ita
R
an
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Om
Pra
k
ash
San
g
wan
✓
✓
✓
✓
✓
✓
✓
✓
✓
R
itu
Gar
g
✓
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
ask
d
ata
was lo
ad
ed
f
r
o
m
a
C
SV f
ile
an
d
r
an
d
o
m
ize
d
to
s
i
m
u
late
d
if
f
er
e
n
t scen
ar
io
s
.
RE
F
E
R
E
NC
E
S
[
1
]
J.
X
u
e
,
L
.
L
i
,
S
.
Z
h
a
o
,
a
n
d
L.
J
i
a
o
,
“
A
st
u
d
y
o
f
t
a
sk
s
c
h
e
d
u
l
i
n
g
b
a
se
d
o
n
d
i
f
f
e
r
e
n
t
i
a
l
e
v
o
l
u
t
i
o
n
a
l
g
o
r
i
t
h
m
i
n
c
l
o
u
d
c
o
mp
u
t
i
n
g
,
”
i
n
2
0
1
4
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
N
e
t
w
o
rks
,
N
o
v
.
2
0
1
4
,
p
p
.
6
3
7
–
6
4
0
,
d
o
i
:
1
0
.
1
1
0
9
/
C
I
C
N
.
2
0
1
4
.
1
4
2
.
[
2
]
V
.
A
h
a
r
i
,
R
.
V
e
n
k
a
t
e
sa
n
,
a
n
d
D
.
P
.
P
.
La
t
h
a
,
“
A
su
r
v
e
y
o
n
t
a
sk
s
c
h
e
d
u
l
i
n
g
u
si
n
g
i
n
t
e
l
l
i
g
e
n
t
w
a
t
e
r
d
r
o
p
s
a
l
g
o
r
i
t
h
m
i
n
c
l
o
u
d
c
o
m
p
u
t
i
n
g
,
”
i
n
2
0
1
9
3
rd
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
T
re
n
d
s
i
n
El
e
c
t
r
o
n
i
c
s
a
n
d
I
n
f
o
rm
a
t
i
c
s
,
A
p
r
.
2
0
1
9
,
p
p
.
3
9
–
45
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
O
EI
.
2
0
1
9
.
8
8
6
2
7
7
7
.
[
3
]
S
.
M
i
t
t
a
l
a
n
d
A
.
K
a
t
a
l
,
“
A
n
o
p
t
i
m
i
z
e
d
t
a
s
k
sc
h
e
d
u
l
i
n
g
a
l
g
o
r
i
t
h
m
i
n
c
l
o
u
d
c
o
mp
u
t
i
n
g
,
”
i
n
2
0
1
6
I
EE
E
6
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
A
d
v
a
n
c
e
d
C
o
m
p
u
t
i
n
g
,
F
e
b
.
2
0
1
6
,
p
p
.
1
9
7
–
202
,
d
o
i
:
1
0
.
1
1
0
9
/
I
A
C
C
.
2
0
1
6
.
4
5
.
[
4
]
X
.
C
h
e
n
e
t
a
l
.
,
“
A
W
O
A
-
b
a
se
d
o
p
t
i
mi
z
a
t
i
o
n
a
p
p
r
o
a
c
h
f
o
r
t
a
sk
s
c
h
e
d
u
l
i
n
g
i
n
c
l
o
u
d
c
o
m
p
u
t
i
n
g
sy
s
t
e
ms
,
”
I
EE
E
S
y
s
t
e
m
s
J
o
u
r
n
a
l
,
v
o
l
.
1
4
,
n
o
.
3
,
p
p
.
3
1
1
7
–
3
1
2
8
,
S
e
p
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
JS
Y
S
T
.
2
0
1
9
.
2
9
6
0
0
8
8
.
[
5
]
T.
A
l
a
d
w
a
n
i
,
“
I
mp
r
o
v
i
n
g
t
a
s
k
s
s
c
h
e
d
u
l
i
n
g
p
e
r
f
o
r
m
a
n
c
e
i
n
c
l
o
u
d
c
o
m
p
u
t
i
n
g
e
n
v
i
r
o
n
me
n
t
b
y
u
s
i
n
g
a
n
a
l
y
t
i
c
h
i
e
r
a
r
c
h
y
p
r
o
c
e
ss
mo
d
e
l
,
”
i
n
2
0
1
7
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
G
re
e
n
I
n
f
o
rm
a
t
i
c
s
,
A
u
g
.
2
0
1
7
,
p
p
.
9
8
–
1
0
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
G
I
.
2
0
1
7
.
1
3
.
[
6
]
M
.
S
.
S
a
n
a
j
a
n
d
P
.
M
.
P
r
a
t
h
a
p
,
“
A
n
e
n
h
a
n
c
e
d
r
o
u
n
d
r
o
b
i
n
(
ER
R
)
a
l
g
o
r
i
t
h
m
f
o
r
e
f
f
e
c
t
i
v
e
a
n
d
e
f
f
i
c
i
e
n
t
t
a
s
k
sc
h
e
d
u
l
i
n
g
i
n
c
l
o
u
d
e
n
v
i
r
o
n
m
e
n
t
,
”
i
n
2
0
2
0
A
d
v
a
n
c
e
d
C
o
m
p
u
t
i
n
g
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
T
e
c
h
n
o
l
o
g
i
e
s
f
o
r
H
i
g
h
Pe
rf
o
rm
a
n
c
e
A
p
p
l
i
c
a
t
i
o
n
s
,
J
u
l
.
2
0
2
0
,
p
p
.
1
0
7
–
110
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
TH
P
A
4
9
2
7
1
.
2
0
2
0
.
9
2
1
3
1
9
8
.
[
7
]
X
.
J.
W
e
i
,
W
.
B
e
i
,
a
n
d
L.
Ju
n
,
“
S
A
M
P
G
A
t
a
sk
s
c
h
e
d
u
l
i
n
g
a
l
g
o
r
i
t
h
m
i
n
c
l
o
u
d
c
o
m
p
u
t
i
n
g
,
”
i
n
2
0
1
7
3
6
t
h
C
h
i
n
e
se
C
o
n
t
r
o
l
C
o
n
f
e
re
n
c
e
,
J
u
l
.
2
0
1
7
,
p
p
.
5
6
3
3
–
5
6
3
7
,
d
o
i
:
1
0
.
2
3
9
1
9
/
C
h
i
C
C
.
2
0
1
7
.
8
0
2
8
2
5
2
.
[
8
]
J.
K
a
u
r
a
n
d
B
.
K
.
S
i
d
h
u
,
“
A
n
e
w
f
l
o
w
e
r
p
o
l
l
i
n
a
t
i
o
n
b
a
se
d
t
a
s
k
s
c
h
e
d
u
l
i
n
g
a
l
g
o
r
i
t
h
m
i
n
c
l
o
u
d
e
n
v
i
r
o
n
me
n
t
,
”
i
n
2
0
1
7
4
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
i
g
n
a
l
Pr
o
c
e
ssi
n
g
,
C
o
m
p
u
t
i
n
g
a
n
d
C
o
n
t
ro
l
,
S
e
p
.
2
0
1
7
,
p
p
.
4
5
7
–
462
,
d
o
i
:
1
0
.
1
1
0
9
/
I
S
P
C
C
.
2
0
1
7
.
8
2
6
9
7
2
2
.
[
9
]
S
.
S
r
i
c
h
a
n
d
a
n
,
T.
A
.
K
u
m
a
r
,
a
n
d
S
.
B
i
b
h
u
d
a
t
t
a
,
“
Ta
sk
sc
h
e
d
u
l
i
n
g
f
o
r
c
l
o
u
d
c
o
m
p
u
t
i
n
g
u
s
i
n
g
m
u
l
t
i
-
o
b
j
e
c
t
i
v
e
h
y
b
r
i
d
b
a
c
t
e
r
i
a
f
o
r
a
g
i
n
g
a
l
g
o
r
i
t
h
m,
”
F
u
t
u
re
C
o
m
p
u
t
i
n
g
a
n
d
I
n
f
o
rm
a
t
i
c
s
J
o
u
r
n
a
l
,
v
o
l
.
3
,
n
o
.
2
,
p
p
.
2
1
0
–
2
3
0
,
D
e
c
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
f
c
i
j
.
2
0
1
8
.
0
3
.
0
0
4
.
[
1
0
]
N
.
M
a
n
so
u
r
i
,
B
.
M
.
H
.
Za
d
e
,
a
n
d
M
.
M
.
Ja
v
i
d
i
,
“
H
y
b
r
i
d
t
a
s
k
s
c
h
e
d
u
l
i
n
g
s
t
r
a
t
e
g
y
f
o
r
c
l
o
u
d
c
o
mp
u
t
i
n
g
b
y
mo
d
i
f
i
e
d
p
a
r
t
i
c
l
e
sw
a
r
m
o
p
t
i
m
i
z
a
t
i
o
n
a
n
d
f
u
z
z
y
t
h
e
o
r
y
,
”
C
o
m
p
u
t
e
rs
&
I
n
d
u
s
t
ri
a
l
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
3
0
,
p
p
.
5
9
7
–
6
3
3
,
A
p
r
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
i
e
.
2
0
1
9
.
0
3
.
0
0
6
.
[
1
1
]
S
.
V
a
r
sh
n
e
y
a
n
d
S
.
S
i
n
g
h
,
“
A
n
o
p
t
i
ma
l
b
i
-
o
b
j
e
c
t
i
v
e
p
a
r
t
i
c
l
e
sw
a
r
m
o
p
t
i
m
i
z
a
t
i
o
n
a
l
g
o
r
i
t
h
m
f
o
r
t
a
sk
sc
h
e
d
u
l
i
n
g
i
n
c
l
o
u
d
c
o
m
p
u
t
i
n
g
,
”
i
n
2
0
1
8
2
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
T
r
e
n
d
s
i
n
E
l
e
c
t
r
o
n
i
c
s
a
n
d
I
n
f
o
rm
a
t
i
c
s
,
M
a
y
2
0
1
8
,
p
p
.
7
8
0
–
7
8
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
O
EI
.
2
0
1
8
.
8
5
5
3
7
2
8
.
[
1
2
]
G
.
G
e
e
t
h
a
,
A
.
K
h
a
r
e
,
K
.
M
a
h
a
w
a
r
,
a
n
d
B
.
B
a
j
a
j
,
“
S
t
r
a
t
e
g
i
c
l
o
a
d
b
a
l
a
n
c
i
n
g
:
g
a
m
e
t
h
e
o
r
y
a
p
p
r
o
a
c
h
f
o
r
o
p
t
i
mi
z
e
d
r
e
so
u
r
c
e
a
l
l
o
c
a
t
i
o
n
i
n
c
l
o
u
d
c
o
m
p
u
t
i
n
g
,
”
i
n
2
0
2
4
8
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
n
v
e
n
t
i
v
e
S
y
st
e
m
s
a
n
d
C
o
n
t
r
o
l
,
J
u
l
.
2
0
2
4
,
p
p
.
3
4
5
–
350
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
S
C
6
2
6
2
4
.
2
0
2
4
.
0
0
0
6
6
.
[
1
3
]
N
.
K
.
R
a
j
p
o
o
t
,
P
.
S
i
n
g
h
,
a
n
d
B
.
P
a
n
t
,
“
N
a
t
u
r
e
-
i
n
s
p
i
r
e
d
l
o
a
d
b
a
l
a
n
c
i
n
g
a
l
g
o
r
i
t
h
ms
f
o
r
r
e
s
o
u
r
c
e
a
l
l
o
c
a
t
i
o
n
i
n
c
l
o
u
d
c
o
m
p
u
t
i
n
g
,
”
i
n
2
0
2
3
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
S
u
st
a
i
n
a
b
l
e
En
g
i
n
e
e
r
i
n
g
S
o
l
u
t
i
o
n
s
,
A
p
r
.
2
0
2
3
,
p
p
.
8
2
7
–
832
,
d
o
i
:
1
0
.
1
1
0
9
/
C
I
S
ES5
8
7
2
0
.
2
0
2
3
.
1
0
1
8
3
6
3
0
.
[
1
4
]
A
.
T
h
a
k
u
r
a
n
d
M
.
S
.
G
o
r
a
y
a
,
“
R
A
F
L:
a
h
y
b
r
i
d
me
t
a
h
e
u
r
i
s
t
i
c
b
a
s
e
d
r
e
s
o
u
r
c
e
a
l
l
o
c
a
t
i
o
n
f
r
a
mew
o
r
k
f
o
r
l
o
a
d
b
a
l
a
n
c
i
n
g
i
n
c
l
o
u
d
c
o
m
p
u
t
i
n
g
e
n
v
i
r
o
n
me
n
t
,
”
S
i
m
u
l
a
t
i
o
n
Mo
d
e
l
l
i
n
g
Pra
c
t
i
c
e
a
n
d
T
h
e
o
ry
,
v
o
l
.
1
1
6
,
A
p
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
s
i
m
p
a
t
.
2
0
2
1
.
1
0
2
4
8
5
.
[
1
5
]
S
.
C
h
h
a
b
r
a
a
n
d
A
.
K
.
S
i
n
g
h
,
“
D
y
n
a
m
i
c
r
e
s
o
u
r
c
e
a
l
l
o
c
a
t
i
o
n
me
t
h
o
d
f
o
r
l
o
a
d
b
a
l
a
n
c
e
sc
h
e
d
u
l
i
n
g
o
v
e
r
c
l
o
u
d
d
a
t
a
c
e
n
t
e
r
n
e
t
w
o
r
k
s,
”
J
o
u
rn
a
l
o
f
We
b
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
0
,
n
o
.
8
,
p
p
.
2
2
6
9
–
2
2
8
4
,
N
o
v
.
2
0
2
1
,
d
o
i
:
1
0
.
1
3
0
5
2
/
j
w
e
1
5
4
0
-
9
5
8
9
.
2
0
8
3
.
[
1
6
]
S
.
S
w
a
r
n
a
k
a
r
,
R
.
K
u
mar,
S
.
K
r
i
sh
n
,
a
n
d
C
.
B
a
n
e
r
j
e
e
,
“
I
mp
r
o
v
e
d
d
y
n
a
mi
c
l
o
a
d
b
a
l
a
n
c
i
n
g
a
p
p
r
o
a
c
h
i
n
c
l
o
u
d
c
o
m
p
u
t
i
n
g
,
”
i
n
2
0
2
0
I
EEE
1
s
t
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
f
o
r
C
o
n
v
e
r
g
e
n
c
e
i
n
En
g
i
n
e
e
ri
n
g
,
S
e
p
.
2
0
2
0
,
p
p
.
1
9
5
–
199
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
E5
0
3
4
3
.
2
0
2
0
.
9
2
9
0
6
0
2
.
[
1
7
]
P
.
J.
V
a
r
ma
a
n
d
S
.
R
.
B
e
n
d
i
,
“
M
u
l
t
i
o
b
j
e
c
t
i
v
e
h
y
b
r
i
d
a
l
-
b
i
r
u
n
i
e
a
r
t
h
n
a
mi
b
b
e
e
t
l
e
o
p
t
i
m
i
z
a
t
i
o
n
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
b
a
s
e
d
t
a
s
k
sch
e
d
u
l
i
n
g
i
n
c
l
o
u
d
c
o
m
p
u
t
i
n
g
,
”
S
u
st
a
i
n
a
b
l
e
C
o
m
p
u
t
i
n
g
:
I
n
f
o
rm
a
t
i
c
s
a
n
d
S
y
s
t
e
m
s
,
v
o
l
.
4
4
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
s
u
sc
o
m
.
2
0
2
4
.
1
0
1
0
5
3
.
[
1
8
]
Y
.
C
h
e
n
a
n
d
Y
.
Z
h
e
n
g
,
“
M
u
l
t
i
-
t
a
s
k
sch
e
d
u
l
i
n
g
me
t
h
o
d
f
o
r
i
n
f
o
r
ma
t
i
o
n
s
e
c
u
r
i
t
y
o
f
h
e
t
e
r
o
g
e
n
e
o
u
s
b
i
g
d
a
t
a
n
e
t
w
o
r
k
s
b
a
s
e
d
o
n
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
t
e
c
h
n
o
l
o
g
y
,
”
i
n
2
0
2
4
I
E
EE
2
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
e
n
s
o
rs,
E
l
e
c
t
r
o
n
i
c
s
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
ri
n
g
,
A
u
g
.
2
0
2
4
,
p
p
.
5
3
–
58
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
S
EC
E
6
1
6
3
6
.
2
0
2
4
.
1
0
7
2
9
4
5
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Hyb
r
id
d
ee
p
lea
r
n
in
g
mo
d
el
f
o
r
th
e
ta
s
k
s
ch
ed
u
lin
g
i
n
clo
u
d
co
mp
u
tin
g
(
K
a
vita
R
a
n
i
)
3691
[
1
9
]
X
.
L
u
,
C
.
Li
u
,
S
.
Zh
u
,
Y
.
M
a
o
,
P
.
L
i
o
,
a
n
d
P
.
H
u
i
,
“
R
LPTO
:
a
r
e
i
n
f
o
r
c
e
me
n
t
l
e
a
r
n
i
n
g
-
b
a
s
e
d
p
e
r
f
o
r
ma
n
c
e
-
t
i
m
e
o
p
t
i
mi
z
e
d
t
a
s
k
a
n
d
r
e
so
u
r
c
e
s
c
h
e
d
u
l
i
n
g
m
e
c
h
a
n
i
sm
f
o
r
d
i
s
t
r
i
b
u
t
e
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
I
E
EE
T
ra
n
s
a
c
t
i
o
n
s
o
n
P
a
r
a
l
l
e
l
a
n
d
D
i
st
ri
b
u
t
e
d
S
y
st
e
m
s
,
v
o
l
.
3
4
,
n
o
.
1
2
,
p
p
.
3
2
6
6
–
3
2
7
9
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
TPD
S
.
2
0
2
3
.
3
3
1
7
3
8
8
.
[
2
0
]
M
.
C
h
h
a
b
r
a
a
n
d
G
.
A
r
o
r
a
,
“
T
h
e
i
m
p
a
c
t
o
f
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
(
M
L)
d
r
i
v
e
n
a
l
g
o
r
i
t
h
m
r
a
n
k
i
n
g
a
n
d
v
i
s
u
a
l
i
z
a
t
i
o
n
o
n
t
a
s
k
sc
h
e
d
u
l
i
n
g
i
n
c
l
o
u
d
c
o
mp
u
t
i
n
g
,
”
i
n
2
0
2
3
3
r
d
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Ad
v
a
n
c
e
m
e
n
t
i
n
E
l
e
c
t
r
o
n
i
c
s
&
C
o
m
m
u
n
i
c
a
t
i
o
n
E
n
g
i
n
e
e
ri
n
g
,
N
o
v
.
2
0
2
3
,
p
p
.
9
6
9
–
972
,
d
o
i
:
1
0
.
1
1
0
9
/
A
EC
E
5
9
6
1
4
.
2
0
2
3
.
1
0
4
2
8
4
7
5
.
[
2
1
]
B
.
K
r
u
e
k
a
e
w
a
n
d
W
.
K
i
m
p
a
n
,
“
M
u
l
t
i
-
o
b
j
e
c
t
i
v
e
t
a
s
k
s
c
h
e
d
u
l
i
n
g
o
p
t
i
m
i
z
a
t
i
o
n
f
o
r
l
o
a
d
b
a
l
a
n
c
i
n
g
i
n
c
l
o
u
d
c
o
mp
u
t
i
n
g
e
n
v
i
r
o
n
m
e
n
t
u
si
n
g
h
y
b
r
i
d
a
r
t
i
f
i
c
i
a
l
b
e
e
c
o
l
o
n
y
a
l
g
o
r
i
t
h
m
w
i
t
h
r
e
i
n
f
o
r
c
e
me
n
t
l
e
a
r
n
i
n
g
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
1
7
8
0
3
–
1
7
8
1
8
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
1
4
9
9
5
5
.
[
2
2
]
R
.
Ta
l
o
u
k
i
,
M
.
H
.
S
h
i
r
v
a
n
i
,
a
n
d
H
.
M
o
t
a
me
n
i
,
“
A
h
e
u
r
i
s
t
i
c
-
b
a
se
d
t
a
sk
sc
h
e
d
u
l
i
n
g
a
l
g
o
r
i
t
h
m
f
o
r
s
c
i
e
n
t
i
f
i
c
w
o
r
k
f
l
o
w
s
i
n
h
e
t
e
r
o
g
e
n
e
o
u
s
c
l
o
u
d
c
o
mp
u
t
i
n
g
p
l
a
t
f
o
r
ms,”
J
o
u
r
n
a
l
o
f
K
i
n
g
S
a
u
d
U
n
i
v
e
rs
i
t
y
-
C
o
m
p
u
t
e
r a
n
d
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
3
4
,
n
o
.
8
,
p
p
.
4
9
0
2
–
4
9
1
3
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
k
su
c
i
.
2
0
2
1
.
0
5
.
0
1
1
.
[
2
3
]
T.
O
u
d
a
a
,
H
.
G
h
a
r
se
l
l
a
o
u
i
,
a
n
d
S
.
B
.
A
h
m
e
d
,
“
A
n
a
g
e
n
t
-
b
a
se
d
mo
d
e
l
f
o
r
r
e
so
u
r
c
e
p
r
o
v
i
s
i
o
n
i
n
g
a
n
d
t
a
s
k
s
c
h
e
d
u
l
i
n
g
i
n
c
l
o
u
d
c
o
m
p
u
t
i
n
g
u
si
n
g
D
R
L,
”
Pr
o
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
9
2
,
p
p
.
3
7
9
5
–
3
8
0
4
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.
2
0
2
1
.
0
9
.
1
5
4
.
[
2
4
]
S
.
S
w
a
r
u
p
,
E
.
M
.
S
h
a
k
sh
u
k
i
,
a
n
d
A
.
Y
a
sar,
“
T
a
sk
sc
h
e
d
u
l
i
n
g
i
n
c
l
o
u
d
u
s
i
n
g
d
e
e
p
r
e
i
n
f
o
r
c
e
m
e
n
t
l
e
a
r
n
i
n
g
,
”
P
ro
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
8
4
,
p
p
.
4
2
–
5
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s
.
2
0
2
1
.
0
3
.
0
1
6
.
[
2
5
]
S
.
A
.
A
l
sa
i
d
y
,
A
.
D
.
A
b
b
o
o
d
,
a
n
d
M
.
A
.
S
a
h
i
b
,
“
H
e
u
r
i
s
t
i
c
i
n
i
t
i
a
l
i
z
a
t
i
o
n
o
f
P
S
O
t
a
sk
s
c
h
e
d
u
l
i
n
g
a
l
g
o
r
i
t
h
m
i
n
c
l
o
u
d
c
o
m
p
u
t
i
n
g
,
”
J
o
u
rn
a
l
o
f
K
i
n
g
S
a
u
d
U
n
i
v
e
rs
i
t
y
-
C
o
m
p
u
t
e
r
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
3
4
,
n
o
.
6
,
p
p
.
2
3
7
0
–
2
3
8
2
,
J
u
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
k
s
u
c
i
.
2
0
2
0
.
1
1
.
0
0
2
.
[
2
6
]
P
.
G
u
p
t
a
,
A
.
A
n
a
n
d
,
P
.
A
g
a
r
w
a
l
,
a
n
d
G
.
M
c
A
r
d
l
e
,
“
N
e
u
r
a
l
n
e
t
w
o
r
k
i
n
sp
i
r
e
d
e
f
f
i
c
i
e
n
t
sca
l
a
b
l
e
t
a
s
k
s
c
h
e
d
u
l
i
n
g
f
o
r
c
l
o
u
d
i
n
f
r
a
s
t
r
u
c
t
u
r
e
,
”
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s
a
n
d
C
y
b
e
r
-
P
h
y
si
c
a
l
S
y
s
t
e
m
s
,
v
o
l
.
4
,
p
p
.
2
6
8
–
2
7
9
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
o
t
c
p
s.
2
0
2
4
.
0
2
.
0
0
2
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
K
a
v
ita
Ra
n
i
h
o
ld
s
a
B
.
Tec
h
.
a
n
d
M
.
Tec
h
.
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
.
S
h
e
is
c
u
rre
n
tl
y
a
P
h
.
D
.
st
u
d
e
n
t
i
n
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
a
t
G
u
ru
Ja
m
b
h
e
sh
wa
r
Un
iv
e
rsity
o
f
S
c
ien
c
e
a
n
d
Te
c
h
n
o
l
o
g
y
,
Hisa
r,
Ha
ry
a
n
a
,
I
n
d
ia.
S
h
e
is
fo
c
u
si
n
g
h
e
r
re
se
a
rc
h
o
n
e
n
e
rg
y
e
fficie
n
c
y
in
c
lo
u
d
c
o
m
p
u
ti
n
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
k
.
g
h
a
n
g
h
a
s6
7
@
g
m
a
il
.
c
o
m
.
O
m
Pra
k
a
sh
S
a
n
g
wa
n
is
p
re
se
n
tl
y
wo
rk
in
g
a
s
a
p
ro
fe
ss
o
r
a
n
d
c
h
a
irma
n
,
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
,
G
u
ru
Ja
m
b
h
e
sh
wa
r
Un
iv
e
rsity
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
o
lo
g
y
,
Hisa
r,
Ha
ry
a
n
a
,
In
d
ia
.
He
is
a
lso
h
a
v
in
g
a
n
a
d
d
it
i
o
n
a
l
c
h
a
rg
e
a
s
d
e
a
n
,
in
tern
a
ti
o
n
a
l
a
ffa
irs,
G
u
ru
Ja
m
b
h
e
sh
wa
r
Un
i
v
e
rsity
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
o
l
o
g
y
w.e.f
2
4
t
h
Oc
to
b
e
r
2
0
2
5
.
He
re
c
e
iv
e
d
h
is
P
h
.
D.
in
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
a
n
d
M
a
ste
r
o
f
Tec
h
n
o
l
o
g
y
(M
.
Tec
h
.
)
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
with
d
ist
in
c
ti
o
n
in
re
se
a
rc
h
wo
rk
fro
m
G
u
ru
Ja
m
b
h
e
sh
wa
r
Un
i
v
e
rsity
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
o
lo
g
y
,
Hisa
r,
Ha
ry
a
n
a
.
He
is
a
ls
o
CI
S
CO
C
e
rti
fied
Ne
two
r
k
As
so
c
iate
(CC
NA
)
a
n
d
CIS
CO
Ce
rti
fie
d
Ac
a
d
e
m
ic
In
stru
c
to
r
(CCAI).
He
is
h
a
v
in
g
2
1
y
e
a
rs
o
f
e
x
p
e
rien
c
e
.
His
a
re
a
o
f
re
se
a
r
c
h
is
so
ftwa
re
e
n
g
i
n
e
e
rin
g
,
AI
,
a
n
d
m
a
c
h
in
e
lea
rn
in
g
.
M
o
re
t
h
a
n
1
5
0
p
u
b
li
c
a
ti
o
n
s
i
n
in
tern
a
ti
o
n
a
l/
n
a
ti
o
n
a
l
j
o
u
r
n
a
ls,
a
n
d
c
o
n
fe
re
n
c
e
s
in
h
is
c
re
d
it
with
t
h
e
h
i
g
h
e
st
imp
a
c
t
fa
c
to
r
o
f
6
.
0
.
Earlier
to
th
is,
h
e
wo
r
k
e
d
a
s
d
y
.
d
irec
to
r
wi
th
Am
it
y
Re
so
u
rc
e
Ce
n
tre
fo
r
In
f
o
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
(ARCIT)
,
a
n
d
LM
C
a
n
d
h
e
a
d
,
CI
S
CO
Re
g
i
o
n
a
l
N
e
two
rk
in
g
Ac
a
d
e
m
y
,
Am
it
y
In
stit
u
te
o
f
In
f
o
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
,
Am
it
y
Un
i
v
e
rsity
,
Uttar
P
r
a
d
e
sh
.
8
re
se
a
rc
h
sc
h
o
lars
h
a
v
e
b
e
e
n
a
wa
rd
e
d
P
h
.
D.
d
e
g
re
e
s
u
n
d
e
r
h
is
su
p
e
rv
isio
n
a
n
d
6
re
se
a
rc
h
sc
h
o
lars
a
re
p
u
rsu
in
g
P
h
.
D.
u
n
d
e
r
h
is
g
u
id
a
n
c
e
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sa
n
g
wa
n
0
8
6
3
@g
m
a
il
.
c
o
m
.
Ritu
G
a
r
g
is
a
n
a
ss
o
c
iate
p
r
o
fe
ss
o
r
in
t
h
e
De
p
a
rtme
n
t
o
f
C
o
m
p
u
ter
En
g
in
e
e
ri
n
g
a
t
th
e
Na
ti
o
n
a
l
In
st
it
u
te
o
f
Tec
h
n
o
lo
g
y
K
u
ru
k
sh
e
tra,
T
h
a
n
e
sa
r,
I
n
d
ia
.
S
h
e
h
o
l
d
s
a
B.
Tec
h
.
a
n
d
M
.
Tec
h
.
i
n
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
,
a
n
d
e
a
rn
e
d
h
e
r
P
h
.
D
.
fro
m
th
e
Na
ti
o
n
a
l
In
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
Ku
r
u
k
s
h
e
tra,
Th
a
n
e
sa
r,
In
d
ia
,
wit
h
o
v
e
r
2
0
y
e
a
rs
o
f
e
x
p
e
rien
c
e
in
tea
c
h
in
g
a
n
d
re
se
a
rc
h
.
S
h
e
h
a
s
a
u
th
o
re
d
8
6
p
u
b
li
c
a
ti
o
n
s,
in
c
lu
d
i
n
g
3
2
p
a
p
e
rs
in
S
CI/
S
c
o
p
u
s
in
d
e
x
e
d
jo
u
rn
a
ls,
n
u
m
e
ro
u
s
b
o
o
k
c
h
a
p
ters
,
a
n
d
c
o
n
fe
re
n
c
e
p
a
p
e
rs.
As
c
o
-
P
I,
sh
e
c
o
m
p
lete
d
a
TE
QIP
-
III
p
ro
jec
t
o
n
b
ra
in
t
u
m
o
r
d
e
tec
ti
o
n
u
si
n
g
M
RI
ima
g
e
s.
S
h
e
h
a
s
s
u
p
e
rv
ise
d
fi
v
e
P
h
.
D.
sc
h
o
lars
a
n
d
2
7
M
.
Tec
h
.
d
isse
rtat
io
n
s,
a
n
d
c
o
n
tri
b
u
ted
e
x
ten
siv
e
l
y
to
c
u
rricu
l
u
m
d
e
sig
n
,
NBA
a
c
c
re
d
it
a
ti
o
n
,
a
n
d
i
n
stit
u
ti
o
n
a
l
l
e
a
d
e
rsh
ip
ro
les
.
S
h
e
is
c
u
rre
n
tl
y
wo
rk
in
g
o
n
M
e
it
Y
G
OI
sp
o
n
s
o
re
d
p
r
o
o
f
-
of
-
c
o
n
c
e
p
t
p
r
o
je
c
t
ti
tl
e
d
“
Cro
p
h
e
a
lt
h
m
o
n
it
o
rin
g
a
n
d
y
iel
d
p
re
d
ictio
n
u
si
n
g
d
e
e
p
lea
rn
in
g
with
d
r
o
n
e
s
ima
g
e
ry
”
a
n
d
a
n
o
t
h
e
r
M
e
it
Y
G
OI
sp
o
n
s
o
re
d
p
ro
jec
t
e
n
ti
tl
e
d
“
Ca
p
a
c
it
y
b
u
il
d
in
g
fo
r
h
u
m
a
n
re
so
u
rc
e
d
e
v
e
lo
p
m
e
n
t
i
n
u
n
m
a
n
n
e
d
a
ircra
ft
sy
ste
m
(d
ro
n
e
a
n
d
re
late
d
tec
h
n
o
l
o
g
ies
)”
u
n
d
e
r
d
r
o
n
e
a
p
p
li
c
a
ti
o
n
s
wo
rk
t
h
e
m
e
w
o
rth
2
.
5
Cr.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
rit
u
.
5
9
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.