I
nte
rna
t
io
na
l J
o
urna
l o
f
Rec
o
nfig
ura
ble a
nd
E
m
be
dd
e
d Sy
s
t
e
m
s
(
I
J
R
E
S)
Vo
l.
15
,
No
.
2
,
J
u
ly
20
26
,
p
p
.
50
4
~
5
13
I
SS
N:
2089
-
4864
,
DOI
:
1
0
.
1
1
5
9
1
/i
j
r
es
.
v
1
5
.
i
2
.
p
p
5
0
4
-
513
504
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
r
es.ia
esco
r
e.
co
m
Bina
ry
h
y
brid
p
a
thf
ind
er
a
lg
o
rith
m
for
e
ff
icie
nt
f
ea
ture
s
elect
io
n in
r
eso
u
rce
-
c
o
nstra
in
ed
e
m
be
dded
s
y
ste
m
s
Ra
hu
l M
ira
j
k
a
r
1
,
P
re
m
a
na
n
d G
ha
de
k
a
r
2
,
Vij
a
y
Da
s
ha
ra
t
h
Cho
ug
ule
1
,
Renu
k
a
B
ha
n
da
ri
3
,
H
rida
y
na
t
h
K
ha
nd
a
g
a
le
4
,
M
a
ha
v
ir
A.
D
ev
m
a
ne
5
,
M
a
ng
esh
H
a
j
a
re
3
,
K
uld
ee
p B
.
Va
y
a
da
nd
e
6
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
,
B
h
a
r
a
t
i
V
i
d
y
a
p
e
e
t
h
’
s
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
,
K
o
l
h
a
p
u
r
,
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
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
(
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
)
,
V
i
s
h
w
a
k
a
r
m
a
I
n
st
i
t
u
t
e
o
f
T
e
c
h
n
o
l
o
g
y
,
P
u
n
e
,
I
n
d
i
a
3
A
r
m
y
I
n
st
i
t
u
t
e
o
f
T
e
c
h
n
o
l
o
g
y
,
P
u
n
e
,
I
n
d
i
a
4
D
e
p
a
r
t
me
n
t
o
f
T
e
c
h
n
o
l
o
g
y
,
S
h
i
v
a
j
i
U
n
i
v
e
r
si
t
y
,
K
o
l
h
a
p
u
r
,
I
n
d
i
a
5
V
a
sa
n
t
d
a
d
a
P
a
t
i
l
P
r
a
t
i
sh
t
h
a
n
's
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
a
n
d
V
i
s
u
a
l
A
r
t
s
,
M
u
mb
a
i
,
I
n
d
i
a
6
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
T
e
c
h
n
o
l
o
g
y
,
V
i
sh
w
a
k
a
r
m
a
I
n
st
i
t
u
t
e
o
f
T
e
c
h
n
o
l
o
g
y
,
P
u
n
e
,
I
n
d
i
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
1
8
,
2
0
2
5
R
ev
i
s
ed
J
u
n
3
,
2
0
2
6
A
cc
ep
ted
J
u
n
1
1
,
2
0
2
6
F
e
a
tu
re
se
lec
ti
o
n
is
c
rit
ica
l
f
o
r
e
m
b
e
d
d
e
d
m
a
c
h
in
e
lea
rn
in
g
sy
ste
m
s
w
h
e
r
e
c
o
m
p
u
tatio
n
a
l
re
so
u
rc
e
s
a
n
d
m
e
m
o
r
y
a
re
se
v
e
re
l
y
c
o
n
stra
in
e
d
.
T
h
is
p
a
p
e
r
p
re
se
n
ts
th
e
b
i
n
a
ry
q
u
a
d
ra
ti
c
a
ll
y
in
terp
o
late
d
h
y
b
rid
p
a
t
h
f
in
d
e
r
a
lg
o
rit
h
m
(BQIH
P
F
A
),
a
n
o
v
e
l
m
e
tah
e
u
risti
c
o
p
ti
m
iza
ti
o
n
m
e
th
o
d
d
e
sig
n
e
d
f
o
r
e
f
f
icie
n
t
f
e
a
tu
re
su
b
se
t
se
lec
ti
o
n
in
re
so
u
rc
e
-
li
m
it
e
d
c
las
si
f
ica
ti
o
n
tas
k
s.
BQIH
P
F
A
a
d
a
p
ts
th
e
c
o
n
t
in
u
o
u
s
QIH
P
F
A
to
b
i
n
a
ry
se
a
rc
h
sp
a
c
e
s
th
ro
u
g
h
sig
m
o
id
tran
sf
e
r
f
u
n
c
ti
o
n
s
a
n
d
e
m
p
lo
y
s
a
h
y
b
rid
tw
o
-
g
ro
u
p
e
n
h
a
n
c
e
m
e
n
t
stra
teg
y
c
o
m
b
in
in
g
p
a
t
h
f
in
d
e
r
d
y
n
a
m
ic
s
w
it
h
sa
lp
sw
a
r
m
a
lg
o
rit
h
m
-
in
sp
ired
e
x
p
lo
ra
ti
o
n
.
W
e
e
v
a
lu
a
te
BQI
HP
F
A
a
g
a
in
st
th
re
e
e
sta
b
li
sh
e
d
b
in
a
ry
o
p
ti
m
iza
ti
o
n
a
lg
o
rit
h
m
s
(
b
in
a
ry
p
a
rti
c
le
s
w
a
r
m
o
p
ti
m
iza
ti
o
n
(B
P
S
O)
,
b
in
a
ry
g
re
y
w
o
l
f
o
p
ti
m
ize
r
(B
G
WO)
,
a
n
d
b
in
a
ry
w
h
a
le
o
p
ti
m
iza
ti
o
n
(BW
O)
)
o
n
th
re
e
b
e
n
c
h
m
a
rk
d
a
tas
e
ts w
it
h
v
a
r
y
in
g
d
ime
n
sio
n
a
li
ti
e
s:
L
ín
g
u
a
Bra
sileira
d
e
S
in
a
is
(Bra
z
il
ian
S
ig
n
L
a
n
g
u
a
g
e
)
m
o
v
e
m
e
n
t
(9
0
f
e
a
tu
re
s),
P
a
rk
in
so
n
'
s
d
ise
a
se
d
e
tec
ti
o
n
(
2
2
f
e
a
tu
re
s),
a
n
d
S
o
n
a
r
Ro
c
k
v
s.
M
in
e
(6
0
f
e
a
tu
re
s).
Ex
p
e
rime
n
tal
re
su
lt
s
d
e
m
o
n
stra
te
th
a
t
BQIH
P
F
A
a
c
h
iev
e
s
c
o
m
p
e
ti
ti
v
e
c
la
s
sif
ica
ti
o
n
a
c
c
u
ra
c
y
(a
v
e
ra
g
e
8
3
.
5
7
%
)
w
it
h
su
b
sta
n
ti
a
l
f
e
a
tu
re
re
d
u
c
ti
o
n
(a
v
e
ra
g
e
6
4
.
1
%
)
w
h
il
e
e
x
e
c
u
ti
n
g
5
.
2
ti
m
e
s
fa
ste
r
th
a
n
c
o
m
p
lex
b
a
se
li
n
e
s
a
n
d
c
o
n
su
m
in
g
m
in
i
m
a
l
m
e
m
o
r
y
(p
e
a
k
:
4
5
-
5
8
M
B).
A
b
latio
n
e
x
p
e
r
ime
n
ts
d
e
m
o
n
stra
te
th
a
t
e
v
e
r
y
a
l
g
o
rit
h
m
ic
p
a
rt
m
a
k
e
s
a
8
-
24
%
c
o
n
tri
b
u
ti
o
n
t
o
t
h
e
t
o
tal
p
e
r
f
o
r
m
a
n
c
e
.
BQIH
P
F
A
o
f
f
e
rs
a
n
e
a
s
y
-
to
-
u
se
,
n
o
n
-
s
p
e
c
if
ic
f
e
a
tu
re
se
lec
ti
o
n
m
e
th
o
d
to
a
u
to
m
a
ted
re
so
u
rc
e
-
c
o
n
stra
in
e
d
e
m
b
e
d
d
e
d
c
las
si
f
ica
ti
o
n
s
y
ste
m
s,
a
p
p
li
c
a
b
le
to
b
e
d
e
p
l
o
y
e
d
to
lo
w
-
p
o
w
e
r
c
o
m
p
u
ti
n
g
e
n
v
iro
n
m
e
n
ts
,
a
n
d
in
tern
e
t
o
f
th
in
g
s
(Io
T
)
e
d
g
e
s
y
ste
m
s.
K
ey
w
o
r
d
s
:
B
in
ar
y
o
p
ti
m
izat
io
n
E
m
b
ed
d
ed
s
y
s
te
m
s
Featu
r
e
s
elec
t
io
n
I
n
ter
n
et
o
f
t
h
i
n
g
s
ed
g
e
co
m
p
u
ti
n
g
Me
tah
e
u
r
is
tic
o
p
ti
m
izatio
n
R
eso
u
r
ce
-
co
n
s
tr
ain
ed
m
ac
h
i
n
e
lear
n
in
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
:
Vij
ay
Da
s
h
ar
at
h
C
h
o
u
g
u
le
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
i
n
ee
r
in
g
,
B
h
ar
ati
Vid
y
ap
ee
th
’
s
C
o
lleg
e
o
f
E
n
g
i
n
ee
r
in
g
Ko
lh
ap
u
r
416013
,
Ma
h
ar
ash
tr
a,
I
n
d
ia
E
m
ail:
v
ij
a
y
k
u
m
ar
.
ch
o
u
g
u
le
@
b
h
ar
ati
v
id
y
ap
ee
t
h
.
ed
u
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
f
ea
tu
r
e
s
elec
tio
n
i
s
an
ex
t
r
e
m
el
y
d
elica
te
p
r
ep
r
o
ce
s
s
in
g
ac
tiv
it
y
i
n
th
e
m
ac
h
i
n
e
lear
n
in
g
t
h
at
n
o
t
o
n
l
y
id
e
n
ti
f
ies
th
e
m
o
s
t
v
a
lu
a
b
le
s
et
o
f
f
ea
t
u
r
es
b
u
t
also
eli
m
i
n
ates
r
ed
u
n
d
an
t
an
d
ir
r
ele
v
an
t
f
ea
t
u
r
es
t
h
er
eb
y
i
m
p
r
o
v
i
n
g
s
u
p
er
io
r
m
o
d
el
ex
ec
u
tio
n
a
n
d
f
e
w
er
co
m
p
u
tati
o
n
s
ar
e
p
er
f
o
r
m
ed
[
1
]
.
I
n
th
e
ca
s
e
o
f
e
m
b
ed
d
ed
m
ac
h
in
e
lear
n
in
g
s
y
s
te
m
s
w
h
er
e
th
e
in
ter
n
et
o
f
t
h
i
n
g
s
(
I
o
T
)
an
d
ed
g
e
co
m
p
u
ti
n
g
ar
e
in
v
o
lv
ed
,
th
e
r
eso
u
r
ce
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
I
SS
N:
2089
-
4864
B
in
a
r
y
h
yb
r
id
p
a
th
fin
d
er a
lg
o
r
ith
m
fo
r
efficien
t fe
a
tu
r
e
s
ele
ctio
n
in
r
eso
u
r
ce
…
(
R
a
h
u
l Mir
a
jka
r
)
505
av
ailab
le
to
th
e
s
y
s
te
m
ar
e
ex
t
r
e
m
el
y
l
i
m
ited
in
ter
m
s
o
f
p
r
o
ce
s
s
i
n
g
p
o
w
er
,
m
e
m
o
r
y
,
a
n
d
p
o
w
er
co
n
s
u
m
p
tio
n
[
2
]
.
T
h
ese
co
n
s
tr
ai
n
ts
d
e
m
an
d
g
o
o
d
f
ea
tu
r
e
s
e
lectio
n
al
g
o
r
it
h
m
s
t
h
at
ca
n
ef
f
icie
n
tl
y
o
p
er
ate
w
ith
i
n
a
s
ev
er
e
co
m
p
u
ti
n
g
co
n
s
tr
ai
n
t
w
i
th
o
u
t
l
o
s
s
o
f
cla
s
s
i
f
icatio
n
p
er
f
o
r
m
a
n
ce
[
3
]
.
T
h
is
is
a
h
ig
h
d
i
m
e
n
s
io
n
alit
y
p
r
o
b
le
m
(
th
e
cu
r
s
e
o
f
d
i
m
e
n
s
io
n
alit
y
)
p
ar
t
icu
lar
l
y
s
e
v
er
e
in
e
m
b
ed
d
ed
s
y
s
te
m
s
w
h
er
e
ev
er
y
ad
d
iti
o
n
al
f
ea
t
u
r
e
i
n
cu
r
s
in
f
er
en
ce
late
n
c
y
,
m
e
m
o
r
y
co
n
s
u
m
p
t
io
n
an
d
p
o
w
er
[
4
]
.
Me
tah
eu
r
i
s
tic
al
g
o
r
ith
m
s
h
av
e
b
ec
o
m
e
o
n
e
o
f
t
h
e
p
o
ten
t
to
o
ls
in
w
r
ap
p
er
-
b
ased
f
ea
t
u
r
e
s
elec
tio
n
[
5
]
as
a
r
esu
l
t
o
f
th
e
p
o
ten
tial
o
f
th
e
m
eta
h
eu
r
is
tic
al
g
o
r
ith
m
s
to
ef
f
ec
ti
v
el
y
s
ea
r
c
h
lar
g
e
s
p
ac
es
o
f
s
o
lu
tio
n
,
w
i
th
o
u
t
th
e
r
eq
u
ir
e
m
e
n
t
o
f
g
r
ad
ien
t
in
f
o
r
m
atio
n
,
o
r
an
y
k
n
o
w
led
g
e
o
f
t
h
e
p
r
o
b
lem
s
tr
u
ctu
r
e.
Su
c
h
m
etah
e
u
r
is
tics
as
p
ar
ticle
s
w
ar
m
o
p
ti
m
iza
tio
n
(
P
SO)
,
th
e
g
r
e
y
w
o
l
f
o
p
tim
izer
(
GW
O)
an
d
th
e
w
h
ale
o
p
ti
m
izatio
n
al
g
o
r
ith
m
(
W
OA
)
h
av
e
b
ee
n
d
e
m
o
n
s
tr
at
ed
to
b
e
s
u
p
er
io
r
to
class
ical
d
eter
m
in
i
s
tic
m
eth
o
d
s
o
n
a
n
u
m
b
er
o
f
f
ea
tu
r
e
s
e
lectio
n
ch
ar
ac
ter
is
t
ics
[
6
]
.
T
h
ese
n
at
u
r
e
-
i
n
s
p
ir
ed
alg
o
r
ith
m
s
co
m
p
r
o
m
i
s
e
ex
p
lo
r
atio
n
o
f
d
if
f
er
en
t
s
et
s
o
f
f
ea
tu
r
es
w
it
h
ex
p
lo
itatio
n
o
f
r
e
w
ar
d
ar
ea
s
an
d
ar
e
th
u
s
h
elp
f
u
l
to
d
is
cr
ete,
co
m
b
i
n
a
to
r
ic
p
r
o
b
lem
s
o
f
f
ea
t
u
r
e
ch
o
ice
[
7
]
.
T
r
an
s
f
er
s
th
e
co
m
m
o
n
b
in
ar
y
an
a
lo
g
u
es
o
f
co
n
tin
u
o
u
s
m
e
tah
e
u
r
is
t
ics
w
i
th
tr
an
s
f
er
f
u
n
ctio
n
s
h
av
e
n
o
w
b
ee
n
i
n
tr
o
d
u
ce
d
as
th
e
c
o
m
m
o
n
m
et
h
o
d
o
f
co
n
v
er
ti
n
g
r
ea
l
w
o
r
ld
p
o
s
itio
n
u
p
d
ate
to
b
in
ar
y
i
n
cl
u
s
io
n
/e
x
clu
s
io
n
ch
o
ices o
f
f
ea
t
u
r
es
[
8
]
.
Desp
ite
th
e
f
ac
t
t
h
at
a
lo
t
o
f
s
tu
d
ies
h
a
v
e
b
ee
n
co
n
d
u
cted
in
b
in
ar
y
m
eta
h
e
u
r
is
tic
f
ea
tu
r
e
s
e
lectio
n
,
th
e
cu
r
r
en
t
s
tate
o
f
r
esear
ch
is
r
ath
er
u
n
s
ati
s
f
ac
to
r
y
.
al
g
o
r
ith
m
s
h
a
v
e
f
u
n
d
a
m
e
n
tal
tr
ad
eo
f
f
s
o
f
ac
cu
r
ac
y
o
f
class
i
f
icatio
n
,
f
ea
tu
r
e
r
ed
u
ctio
n
ag
g
r
e
s
s
i
v
en
e
s
s
,
co
m
p
le
x
it
y
,
an
d
in
f
er
en
ce
to
o
th
er
p
r
o
p
er
ties
o
f
d
atasets
[
9
]
.
b
in
ar
y
g
r
e
y
w
o
l
f
o
p
ti
m
izer
(
B
GW
O
)
,
b
in
ar
y
p
ar
ticle
s
w
ar
m
o
p
ti
m
izat
io
n
(
B
P
SO
)
,
an
d
b
in
ar
y
w
h
ale
o
p
tim
izatio
n
(
BW
O
)
ar
e
d
if
f
er
en
t
tr
ad
es
o
f
f
b
et
w
ee
n
co
n
v
er
g
e
n
ce
an
d
d
i
v
er
s
it
y
co
n
s
e
r
v
atio
n
[
1
0
]
–
[
1
2
]
.
QI
HP
FA
co
m
b
i
n
es
p
at
h
f
in
d
er
u
p
d
ates
b
ased
o
n
q
u
ad
r
atic
in
t
er
p
o
latio
n
to
co
n
tin
u
o
u
s
o
p
ti
m
izatio
n
[
1
3
]
b
u
t
its
b
in
ar
y
v
er
s
io
n
b
ased
o
n
em
b
e
d
d
ed
ad
ap
tatio
n
s
s
y
s
te
m
s
r
e
m
ain
u
n
ex
p
lo
r
ed
.
Ho
w
e
v
er
,
th
er
e
w
as
ad
ap
tatio
n
o
f
th
e
QI
HP
F
A
to
b
in
ar
y
s
ea
r
c
h
s
p
ac
e
r
eq
u
ir
ed
b
y
f
ea
t
u
r
e.
Sel
ec
tio
n
p
r
o
b
lem
s
ar
e
n
o
t
m
ad
e.
Mo
r
eo
v
er
,
th
er
e
is
n
o
av
ailab
le
li
ter
atu
r
e
t
h
at
a
d
d
r
ess
es
th
e
s
p
ec
ial
n
ee
d
s
o
f
r
eso
u
r
ce
-
co
n
s
tr
ain
ed
e
m
b
e
d
d
ed
s
y
s
te
m
s
w
i
t
h
class
i
f
icatio
n
p
er
f
o
r
m
an
ce
an
d
co
m
p
u
ta
tio
n
al
ef
f
icie
n
c
y
(
r
u
n
ti
m
e
an
d
m
e
m
o
r
y
u
s
ag
e)
b
ein
g
eq
u
all
y
i
m
p
o
r
tan
t
d
esig
n
g
o
als
[
1
4
]
.
T
h
is
k
n
o
w
led
g
e
g
ap
en
co
u
r
ag
e
s
th
e
cr
ea
tio
n
o
f
a
b
in
ar
y
v
er
s
io
n
o
f
QI
HP
FA
w
h
ic
h
i
s
o
p
tim
ized
in
t
h
e
ca
s
e
o
f
e
m
b
e
d
d
ed
f
ea
tu
r
e
s
e
lectio
n
[
1
5
]
.
T
h
e
p
a
p
er
in
tr
o
d
u
ce
s
th
e
b
in
ar
y
q
u
ad
r
atica
ll
y
in
ter
p
o
lated
h
y
b
r
id
p
ath
f
i
n
d
er
alg
o
r
ith
m
(
B
QI
HP
FA
)
,
th
e
f
ir
s
t
b
i
n
ar
y
y
ea
r
n
i
n
g
o
f
QI
HP
FA
t
h
at
i
s
s
p
ec
i
f
icall
y
cr
ea
ted
to
p
er
f
o
r
m
w
r
ap
p
er
-
b
ased
f
ea
t
u
r
e
s
elec
tio
n
i
n
r
eso
u
r
ce
-
c
o
n
s
tr
ain
ed
e
m
b
ed
d
ed
class
i
f
icatio
n
s
y
s
te
m
s
.
W
e
p
r
esen
t
s
i
g
m
o
id
tr
an
s
f
er
f
u
n
ctio
n
s
to
lear
n
co
n
tin
u
o
u
s
p
ath
f
i
n
d
er
d
y
n
a
m
i
cs
in
to
b
in
ar
y
d
ec
i
s
io
n
s
p
ac
e
w
it
h
o
u
t
lo
s
s
o
f
m
o
m
en
t
u
m
d
r
iv
en
b
y
v
elo
cit
y
to
f
ac
ilit
ate
ex
p
lo
r
atio
n
[
1
6
]
.
A
h
y
b
r
id
t
w
o
-
g
r
o
u
p
i
m
p
r
o
v
e
m
e
n
t
m
et
h
o
d
s
p
lits
th
e
p
o
p
u
latio
n
i
n
to
co
m
p
le
m
en
tar
y
s
ea
r
ch
s
u
b
g
r
o
u
p
s
,
w
h
er
e
t
h
e
f
o
r
m
er
g
r
o
u
p
m
a
k
es
g
lo
b
al
ex
p
lo
r
atio
n
w
it
h
s
a
lp
s
w
ar
m
alg
o
r
ith
m
-
i
n
s
p
ir
ed
u
p
d
ates
an
d
t
h
e
latter
g
r
o
u
p
m
ak
e
s
lo
ca
l
ex
p
lo
itat
io
n
w
it
h
m
aj
o
r
ity
-
v
o
tin
g
q
u
ad
r
atic
i
n
t
er
p
o
latio
n
[
1
7
]
.
T
h
e
p
r
o
ce
s
s
o
f
an
ad
ap
tiv
e
an
n
ea
l
i
n
g
g
r
ad
u
all
y
c
h
a
n
g
e
s
th
e
s
ea
r
ch
to
an
ex
p
lo
itin
g
o
n
e
as
t
h
e
iter
atio
n
s
p
r
o
g
r
ess
an
d
th
i
s
ch
a
n
g
e
i
s
g
o
v
er
n
ed
b
y
th
e
co
e
f
f
ic
ien
t
A
=
u
2
ex
p
-
2
t/
T
[
1
8
]
.
W
e
m
ai
n
l
y
co
n
tr
ib
u
te:
i
)
th
eo
r
etica
l
co
n
v
er
g
e
n
ce
an
al
y
s
is
w
i
th
th
e
as
s
u
m
p
tio
n
o
f
Ma
r
k
o
v
ch
ain
u
n
d
er
u
n
i
f
o
r
m
er
g
o
d
icit
y
g
u
ar
an
tee
s
an
d
elitis
t
s
elec
t
io
n
;
ii
)
ex
te
n
s
i
v
e
b
en
ch
m
ar
k
in
g
ag
ai
n
s
t
th
r
ee
estab
lis
h
ed
b
in
ar
y
o
p
tim
izatio
n
a
lg
o
r
it
h
m
s
(
B
P
SO,
B
GW
O,
an
d
B
W
O)
o
n
th
r
ee
d
if
f
er
e
n
t
b
en
c
h
m
ar
k
d
ata
s
ets
[
1
9
]
-
L
I
B
R
A
S
m
o
v
e
m
e
n
t
(
9
0
f
ea
t
u
r
es
a
n
d
3
6
0
s
a
m
p
les),
P
ar
k
i
n
s
o
n
d
i
s
ea
s
e
d
etec
tio
n
(
2
2
f
ea
tu
r
es
an
d
1
9
5
s
a
m
p
les),
a
n
d
So
n
ar
R
o
ck
v
s
.
Min
e
(
6
0
f
ea
t
u
r
es
an
d
2
0
8
s
am
p
le
s
)
;
an
d
iii
)
ab
lati
o
n
s
tu
d
ie
s
co
n
f
ir
m
i
n
g
th
e
co
n
t
r
ib
u
tio
n
o
f
ea
c
h
o
f
th
e
alg
o
r
it
h
m
ic
co
m
p
o
n
e
n
ts
(
e
x
p
er
i
m
e
n
tal
f
in
d
i
n
g
s
in
d
icat
e
th
at
B
QI
HP
FA
ca
n
b
e
co
m
p
etitiv
e
in
a
v
er
ag
e
class
i
f
icatio
n
ac
cu
r
ac
y
(
8
3
.
5
7
%
)
w
it
h
s
ig
n
i
f
ica
n
t
f
ea
t
u
r
e
r
ed
u
ctio
n
(
6
4
.
1
%
)
an
d
r
u
n
5
.
2
tim
es
f
aster
th
a
n
B
W
O
at
a
lo
w
p
ea
k
m
e
m
o
r
y
r
eq
u
ir
e
m
en
t (
4
5
-
5
8
MB
)
co
m
p
ar
ed
to
B
W
O,
th
u
s
is
f
ea
s
ib
le
to
i
m
p
le
m
en
t o
n
I
o
T
ed
g
e
d
ev
ices a
n
d
lo
w
-
p
o
w
er
co
m
p
u
ter
s
[
2
0
]
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
2
.
1
.
P
r
o
ble
m
f
o
r
m
ula
t
io
n
Featu
r
e
s
elec
tio
n
ca
n
b
e
f
o
r
m
u
lated
as
a
b
in
ar
y
o
p
ti
m
izatio
n
p
r
o
b
lem
w
h
er
e
ea
ch
ca
n
d
id
ate
s
o
lu
tio
n
r
ep
r
esen
ts
a
f
ea
t
u
r
e
s
u
b
s
et
en
c
o
d
ed
as
a
b
in
ar
y
v
ec
to
r
X=
[
x
₁,
x
₂,
.
.
.
,
x
D]
,
w
h
er
e
D
is
t
h
e
to
tal
n
u
m
b
er
o
f
f
ea
t
u
r
e
s
[
9
]
.
E
ac
h
b
in
ar
y
v
ar
iab
le
x
d
∈
{0
,
1
}
in
d
icate
s
w
h
et
h
er
f
ea
t
u
r
e
d
is
s
elec
ted
(
x
d
=1
)
o
r
ex
clu
d
ed
(
x
d
=0
)
f
r
o
m
th
e
s
u
b
s
et.
T
h
e
o
b
j
ec
tiv
e
is
to
f
i
n
d
th
e
o
p
ti
m
al
b
i
n
ar
y
v
ec
to
r
X
*
t
h
at
m
i
n
i
m
ize
s
th
e
f
it
n
es
s
f
u
n
ctio
n
:
(
)
=
×
(
1
−
(
)
)
+
×
(
|
(
)
|
/
)
(
1
)
w
h
er
e
(
)
is
th
e
class
if
ica
tio
n
ac
cu
r
ac
y
ac
h
ie
v
ed
u
s
i
n
g
t
h
e
f
ea
tu
r
e
s
u
b
s
et
,
|
(
)
|
r
ep
r
esen
ts
th
e
n
u
m
b
er
o
f
s
elec
ted
f
ea
tu
r
e
s
(
Ha
m
m
i
n
g
w
eig
h
t)
,
α
a
n
d
β
ar
e
w
ei
g
h
ti
n
g
co
ef
f
icie
n
ts
co
n
tr
o
llin
g
th
e
tr
ad
e
-
o
f
f
b
et
w
ee
n
ac
cu
r
ac
y
m
a
x
i
m
izat
i
o
n
an
d
f
ea
tu
r
e
r
ed
u
ctio
n
(
α
=0
.
9
9
,
β=0
.
0
1
in
th
is
s
t
u
d
y
)
,
an
d
D
is
th
e
to
tal
f
ea
tu
r
e
d
i
m
en
s
io
n
al
it
y
[
6
]
.
A
co
n
s
tr
ai
n
t e
n
s
u
r
e
s
at
least o
n
e
f
ea
t
u
r
e
is
s
elec
ted
:
|
(
)
|
≥
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4864
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
,
Vo
l.
15
,
No
.
2
,
J
u
l
y
202
6
:
50
4
-
5
1
3
506
2
.
2
.
B
ina
ry
qu
a
dra
t
ica
lly
in
t
er
po
la
t
ed
hy
brid pa
t
hfinde
r
a
lg
o
rit
h
m
B
QI
HP
FA
ad
ap
ts
th
e
co
n
tin
u
o
u
s
q
u
ad
r
atica
ll
y
i
n
ter
p
o
lat
ed
h
y
b
r
id
p
ath
f
i
n
d
er
alg
o
r
ith
m
[
1
3
]
to
d
is
cr
ete
b
in
ar
y
s
ea
r
ch
s
p
ac
es
th
r
o
u
g
h
t
h
r
ee
co
r
e
m
ec
h
an
is
m
s
:
s
i
g
m
o
id
tr
a
n
s
f
er
f
u
n
ctio
n
s
,
p
ath
f
in
d
er
-
b
ased
p
o
s
itio
n
u
p
d
ate
s
,
an
d
h
y
b
r
id
tw
o
-
g
r
o
u
p
en
h
an
ce
m
e
n
t
s
tr
ate
g
ies.
T
h
e
alg
o
r
ith
m
m
ai
n
tai
n
s
a
p
o
p
u
latio
n
o
f
N
ca
n
d
id
ate
s
o
lu
tio
n
s
(
b
in
ar
y
v
e
cto
r
s
)
th
at
ev
o
l
v
e
o
v
er
T
m
a
x
i
m
u
m
iter
at
io
n
s
.
2
.
2
.
1
.
P
o
pu
la
t
io
n
ini
t
ia
liza
t
io
n
a
nd
t
ra
ns
f
er
f
un
ct
io
n
I
n
itialize
N=
2
0
b
in
ar
y
v
ec
to
r
s
Xi(
0
)
~
B
e
r
n
o
u
lli(0
.
5
)
,
r
ep
air
if
:
∑
,
=
0
(
2
)
T
h
e
p
ath
f
in
d
er
Xp
f
tr
ac
k
s
t
h
e
b
est s
o
lu
tio
n
.
B
in
ar
y
ad
ap
tatio
n
u
s
es si
g
m
o
id
tr
an
s
f
er
f
u
n
cti
o
n
:
(
)
=
1
/
(
1
+
(
−
)
)
(
3
)
to
m
ap
co
n
ti
n
u
o
u
s
u
p
d
ates
to
b
it
-
f
lip
p
r
o
b
ab
ilit
ies:
f
o
r
ea
ch
d
i
m
en
s
io
n
d
,
i
f
(
)
≤
(
)
,
f
lip
b
it.
T
h
is
p
r
eser
v
es e
x
p
lo
r
atio
n
w
h
ile
e
n
ab
lin
g
co
n
v
er
g
en
ce
[
8
]
,
[
1
6
]
.
2
.
2
.
2
.
P
a
t
hfinder
up
da
t
e
m
ec
ha
nis
m
Velo
cit
y
-
d
r
iv
e
n
m
o
m
en
tu
m
:
(
+
1
)
=
2
(
(
)
−
(
−
1
)
)
(
4
)
w
it
h
a
n
n
ea
l
in
g
:
=
·
(
−
2
/
)
(
5
)
co
n
tin
u
o
u
s
u
p
d
ate
(
+
1
,
)
=
(
)
+
(
+
1
)
·
at
,
b
in
ar
ized
v
ia
s
ig
m
o
id
(
3
)
,
r
ep
lace
s
i
f
f
it
n
es
s
i
m
p
r
o
v
e
s
.
2
.
2
.
3
.
Ag
ent
po
s
it
io
n upd
a
t
e
No
n
-
p
at
h
f
in
d
er
ag
e
n
ts
i=2
,
.
.
.
,
N
u
p
d
ate:
(
+
1
,
)
=
+
1
(
−
)
+
2
(
−
)
·
(
6
)
w
h
er
e
1
=
·
1
(
7
)
2
=
·
2
(
,
~
[
1
,
2
]
)
(
8
)
an
d
=
(
1
−
/
)
·
·
(
9
)
ad
d
s
d
iv
er
s
it
y
d
ec
a
y
p
r
o
p
o
r
tio
n
al
to
Ha
m
m
i
n
g
d
is
ta
n
ce
.
2
.
2
.
4
.
H
y
brid
t
w
o
-
g
r
o
up
enha
nce
m
e
nt
Sp
lit
p
o
p
u
latio
n
5
0
-
5
0
:
Gr
o
u
p
1
u
s
es
S
S
A
-
in
s
p
ir
ed
ex
p
lo
r
atio
n
ar
o
u
n
d
p
ath
f
i
n
d
er
;
Gr
o
u
p
2
u
s
e
s
m
aj
o
r
ity
-
v
o
tin
g
i
n
ter
p
o
latio
n
o
n
p
ath
f
i
n
d
er
+
2
r
an
d
o
m
a
g
en
ts
,
w
it
h
1
0
%
r
an
d
o
m
b
it
f
lip
to
p
r
ev
en
t
s
ta
g
n
atio
n
.
2
.
2
.
5
.
F
it
nes
s
ev
a
lua
t
io
n a
nd
s
elec
t
io
n
E
ac
h
ca
n
d
id
ate
s
o
lu
tio
n
_
is
ev
alu
ated
u
s
in
g
a
w
r
ap
p
er
-
b
ased
f
itn
e
s
s
f
u
n
ctio
n
w
it
h
r
an
d
o
m
f
o
r
est
class
i
f
ier
[
2
1
]
.
C
lass
if
icat
io
n
ac
cu
r
ac
y
(
_
)
is
co
m
p
u
ted
v
ia
2
-
f
o
ld
cr
o
s
s
-
v
a
lid
atio
n
[
2
2
]
o
n
th
e
tr
ain
i
n
g
s
e
t (
7
0
% o
f
d
ata)
u
s
in
g
o
n
l
y
th
e
f
ea
t
u
r
es
w
h
er
e
_
{
,
}
=
1
.
R
an
d
o
m
f
o
r
est
p
ar
a
m
eter
s
:
1
0
tr
ee
s
,
Gin
i
i
m
p
u
r
it
y
,
n
o
m
ax
i
m
u
m
d
ep
th
.
A
f
ter
ev
a
lu
at
io
n
,
elitis
t
s
elec
tio
n
r
etai
n
s
t
h
e
p
at
h
f
in
d
er
:
if
a
n
y
a
g
e
n
t
ac
h
iev
e
s
(
_
^
{
+
1
}
)
<
(
_
^
)
,
it
r
ep
la
ce
s
th
e
p
at
h
f
in
d
er
f
o
r
iter
atio
n
t+1
.
T
h
is
g
u
ar
a
n
t
ee
s
m
o
n
o
to
n
ic
i
m
p
r
o
v
e
m
e
n
t o
f
th
e
b
est
-
so
-
f
ar
s
o
lu
tio
n
.
2
.
2
.
6
.
T
er
m
i
na
t
io
n
cr
it
er
ia
T
h
e
alg
o
r
ith
m
ter
m
i
n
ates
w
h
e
n
eith
er
:
−
Ma
x
i
m
u
m
iter
atio
n
s
T
=5
0
is
r
ea
ch
ed
,
o
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
I
SS
N:
2089
-
4864
B
in
a
r
y
h
yb
r
id
p
a
th
fin
d
er a
lg
o
r
ith
m
fo
r
efficien
t fe
a
tu
r
e
s
ele
ctio
n
in
r
eso
u
r
ce
…
(
R
a
h
u
l Mir
a
jka
r
)
507
−
E
ar
ly
co
n
v
er
g
e
n
ce
:
p
at
h
f
in
d
er
f
it
n
es
s
i
m
p
r
o
v
es
b
y
les
s
t
h
a
n
ε
=1
0
⁻⁸
f
o
r
2
0
co
n
s
ec
u
ti
v
e
iter
ati
o
n
s
(
s
ta
g
n
atio
n
d
etec
tio
n
)
.
Up
o
n
ter
m
i
n
atio
n
,
t
h
e
p
ath
f
i
n
d
er
_
r
ep
r
esen
ts
t
h
e
o
p
ti
m
a
l
f
e
atu
r
e
s
u
b
s
et,
a
n
d
s
elec
ted
f
ea
t
u
r
es
{
∶
_
{
,
}
=
1
}
ar
e
u
s
ed
to
tr
ain
th
e
f
i
n
al
clas
s
if
ier
.
2
.
3
.
B
a
s
eline
a
lg
o
rit
h
m
s
T
h
e
p
e
r
f
o
r
m
a
n
ce
o
f
B
QI
HP
FA
is
co
m
p
ar
ed
to
th
r
ee
p
r
e
-
ex
is
tin
g
b
in
ar
y
m
eta
h
eu
r
i
s
tics
u
n
d
er
th
e
s
am
e
co
n
d
itio
n
s
o
f
t
h
e
e
x
p
er
i
m
e
n
t c
o
n
d
itio
n
s
:
−
B
in
ar
y
p
ar
ticle
s
w
ar
m
o
p
ti
m
i
za
tio
n
(
B
P
SO)
[
1
0
]
:
v
elo
cit
y
-
b
ased
u
p
d
ates
w
it
h
in
er
tia
w
e
ig
h
t
w
li
n
ea
r
l
y
d
ec
r
ea
s
in
g
f
r
o
m
0
.
9
to
0
.
4
,
co
g
n
i
tiv
e
a
n
d
s
o
cial
co
ef
f
icie
n
ts
₁
=
₂
=
2
,
v
elo
cit
y
cla
m
p
in
g
[
-
1
0
,
1
0
]
.
−
B
in
ar
y
g
r
e
y
w
o
l
f
o
p
ti
m
izer
(
B
GW
O
)
[
1
1
]
:
h
ier
ar
ch
ical
p
ac
k
s
tr
u
ct
u
r
e
w
it
h
alp
h
a
(
b
est),
b
et
a
(
s
ec
o
n
d
-
b
est),
d
elta
(
th
ir
d
-
b
est)
lead
er
s
h
ip
.
P
o
s
itio
n
u
p
d
ates
as
w
ei
g
h
t
ed
av
er
ag
e
o
f
alp
h
a,
b
eta,
d
elta
in
f
lu
e
n
ce
s
.
C
o
ef
f
icie
n
t
a
d
ec
r
ea
s
es
lin
ea
r
l
y
f
r
o
m
2
to
0
.
Hy
b
r
id
o
b
j
e
ctiv
e
f
u
n
c
tio
n
co
m
b
in
a
tio
n
s
h
av
e
also
b
ee
n
ex
p
lo
r
ed
in
d
o
cu
m
en
t
clu
s
ter
in
g
p
r
o
b
lem
s
,
d
e
m
o
n
s
tr
atin
g
t
h
e
ef
f
ec
tiv
e
n
e
s
s
o
f
m
u
lti
-
o
b
j
ec
tiv
e
m
etah
e
u
r
is
ti
c
f
o
r
m
u
latio
n
s
[
2
3
]
.
−
B
in
ar
y
w
h
ale
o
p
ti
m
izatio
n
(
B
W
O)
[
7
]
:
d
u
al
-
m
o
d
e
s
ea
r
ch
with
p
r
o
b
ab
ilit
y
p
=0
.
5
s
w
i
tch
i
n
g
b
et
w
ee
n
p
r
e
y
en
cir
cli
n
g
(
e
x
p
lo
itatio
n
)
an
d
s
p
ir
al
u
p
d
atin
g
(
ex
p
lo
r
atio
n
)
.
Sp
ir
al
p
ar
am
eter
b
=1
,
co
ef
f
ici
en
t
a
d
ec
r
ea
s
es
f
r
o
m
2
to
0
.
A
ll
alg
o
r
it
h
m
s
u
s
e
N=
2
0
p
o
p
u
la
tio
n
s
ize,
T
=5
0
iter
atio
n
s
,
id
en
tical
s
ig
m
o
id
tr
an
s
f
er
f
u
n
ctio
n
(
3
)
,
s
a
m
e
f
it
n
es
s
f
u
n
ctio
n
(
i
n
(
1
)
w
ith
α
=0
.
9
9
)
,
an
d
5
in
d
ep
en
d
en
t r
u
n
s
w
it
h
d
if
f
er
en
t r
an
d
o
m
s
ee
d
s
.
2
.
4
.
Da
t
a
prepro
ce
s
s
ing
T
h
r
ee
UC
I
b
en
ch
m
ar
k
d
ata
s
ets
[
1
9
]
w
er
e
s
e
lecte
d
to
ev
al
u
ate
p
er
f
o
r
m
a
n
ce
ac
r
o
s
s
v
ar
y
i
n
g
d
i
m
en
s
io
n
al
ities
,
d
ataset
c
h
ar
a
cter
is
tics
:
−
L
I
B
R
A
S
m
o
v
e
m
e
n
t
[2
4
]
: 9
0
f
ea
tu
r
es,
3
6
0
s
a
m
p
les,
1
5
class
es (
h
i
g
h
-
d
i
m
en
s
io
n
al,
2
⁹⁰
s
u
b
s
ets)
−
P
ar
k
in
s
o
n
's
d
is
ea
s
e
[2
5
]
: 2
2
f
ea
tu
r
es,
1
9
5
s
a
m
p
les,
2
class
e
s
(
lo
w
-
d
i
m
e
n
s
io
n
al)
−
So
n
ar
R
o
ck
v
s
.
Mi
n
e
[
2
6
]
: 6
0
f
ea
t
u
r
es,
2
0
8
s
am
p
le
s
,
2
class
e
s
(
m
id
-
d
i
m
e
n
s
io
n
al)
P
r
ep
r
o
ce
s
s
in
g
:
m
is
s
i
n
g
v
a
lu
e
s
(
<5
%)
r
em
o
v
ed
v
ia
lis
t
w
is
e
d
eletio
n
;
Stan
d
ar
d
Scaler
n
o
r
m
aliza
tio
n
;
70
-
3
0
tr
ain
-
test
s
tr
ati
f
ied
s
p
lit;
an
d
r
an
d
o
m
s
ee
d
=4
2
.
2
.
5
.
P
er
f
o
rm
a
nce
m
et
rics
Fiv
e
m
etr
ics e
v
al
u
ate
alg
o
r
it
h
m
p
er
f
o
r
m
a
n
ce
:
−
C
las
s
i
f
icatio
n
ac
c
u
r
ac
y
(
%):
t
est s
et
ac
cu
r
ac
y
(
3
0
% h
o
ld
o
u
t
)
−
Featu
r
e
r
ed
u
ctio
n
r
ate
(
%):
[
1
-
S(X
)
/D]
×1
0
0
−
C
o
n
v
er
g
e
n
ce
s
p
ee
d
: iter
atio
n
s
to
r
ea
ch
9
5
% o
f
f
in
al
f
it
n
es
s
−
R
u
n
ti
m
e
(
s
)
:
av
er
a
g
e
ti
m
e
o
v
e
r
5
r
u
n
s
(
5
0
iter
atio
n
s
ea
ch
)
−
P
ea
k
me
m
o
r
y
(
MB
)
:
m
a
x
i
m
u
m
r
esid
en
t
s
et
s
ize
(
p
s
u
til lib
r
a
r
y
)
2
.
6
.
E
x
peri
m
ent
a
l
s
et
up
A
ll
e
x
p
er
i
m
e
n
t
s
w
er
e
co
n
d
u
cted
o
n
a
s
y
s
te
m
eq
u
ip
p
ed
w
it
h
a
n
I
n
tel
C
o
r
e
i7
-
9
7
5
0
H
p
r
o
ce
s
s
o
r
(
2
.
6
GHz
)
,
1
6
GB
R
A
M,
a
n
d
W
in
d
o
w
s
1
0
o
p
er
atin
g
s
y
s
te
m
.
T
h
e
im
p
le
m
en
tatio
n
w
a
s
d
ev
elo
p
ed
u
s
in
g
P
y
th
o
n
3
.
8
.
1
0
w
it
h
th
e
s
ci
k
it
-
lear
n
0
.
2
4
.
2
,
Nu
m
P
y
1
.
2
1
.
0
,
an
d
p
an
d
as
1
.
3
.
0
lib
r
ar
ies.
Statis
tica
l
s
ig
n
i
f
ica
n
ce
w
as
ev
alu
a
ted
u
s
i
n
g
th
e
W
ilco
x
o
n
s
ig
n
ed
-
r
a
n
k
tes
t
[
2
7
]
at
a
s
ig
n
i
f
ica
n
ce
lev
el
o
f
α
=0
.
0
5
,
an
d
th
e
s
o
u
r
ce
co
d
e
alo
n
g
w
it
h
t
h
e
d
atasets
ar
e
p
u
b
licl
y
av
ailab
le
at
GitH
u
b
R
ep
o
s
ito
r
y
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
Cla
s
s
if
ica
t
io
n
a
cc
ura
c
y
perf
o
r
m
a
nce
T
ab
le
1
d
is
p
lay
s
ac
c
u
r
ac
y
o
f
class
i
f
icatio
n
o
f
B
QI
HP
FA
an
d
b
aselin
e
al
g
o
r
ith
m
s
in
al
l
th
e
th
r
e
e
b
en
ch
m
ar
k
d
ata
s
et
s
.
B
QI
HP
F
A
h
a
s
av
er
a
g
e
ac
cu
r
ac
y
o
f
8
3
.
5
7
%
in
all
d
atasets
an
d
t
h
e
lo
w
est
s
tan
d
ar
d
d
ev
iatio
n
(
5
.
2
1
)
in
d
icati
n
g
a
s
tr
o
n
g
p
er
f
o
r
m
a
n
ce
i
n
co
n
tr
as
t
to
B
P
SO
(
7
.
8
3
%),
B
GW
O
(
6
.
4
2
%),
an
d
B
W
O
(
8
.
1
4
%).
T
h
is
co
n
s
i
s
ten
c
y
i
m
p
lies
th
at
B
QI
HP
F
A
ca
n
g
e
n
er
alize
to
a
w
id
e
v
ar
iet
y
o
f
p
r
o
b
lem
p
r
o
p
er
ties
w
it
h
o
u
t
th
e
n
ee
d
to
ad
j
u
s
t
th
e
p
ar
a
m
eter
s
u
s
in
g
a
d
ataset
-
s
p
ec
if
ic
p
ar
a
m
eter
tu
n
er
-
w
h
ic
h
is
a
v
ital
q
u
al
it
y
o
f
e
m
b
ed
d
ed
s
y
s
te
m
s
w
h
e
n
th
e
d
ep
lo
y
m
e
n
t e
n
v
ir
o
n
m
e
n
t is
u
n
k
n
o
w
n
a
n
d
th
at
g
en
er
aliz
in
g
to
it is
r
eq
u
ir
ed
[
2
8
]
.
A
cc
u
r
ac
y
o
f
clas
s
i
f
icatio
n
is
p
r
esen
ted
in
T
ab
le
1
.
T
h
e
av
er
ag
e
(
s
td
.
d
ev
5
.
2
1
%)
o
f
B
QI
HP
FA
is
8
3
.
5
7
%
s
o
th
at
it
d
o
es
n
o
t
r
e
q
u
ir
e
d
ataset
-
s
p
ec
i
f
ic
tu
n
i
n
g
d
u
r
in
g
d
ep
lo
y
m
en
t.
B
QI
HP
F
A
is
f
aste
s
t
o
n
So
n
ar
(8
8
.
4
6
)
w
it
h
h
y
b
r
id
ex
p
lo
r
atio
n
-
e
x
p
lo
itatio
n
,
B
W
O
is
f
ast
o
n
lo
w
-
d
i
m
e
n
s
io
n
al
P
ar
k
in
s
o
n
(
9
1
.
5
3
)
,
b
u
t
at
4
.
8
×
r
u
n
ti
m
e
s
ca
le
is
u
n
ac
ce
p
tab
le
w
it
h
e
m
b
ed
d
ed
s
y
s
te
m
s
,
a
n
d
b
in
ar
y
g
r
e
y
w
o
l
f
o
p
ti
m
izer
(
B
GW
I
)
is
f
ast
o
n
h
i
g
h
-
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4864
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
,
Vo
l.
15
,
No
.
2
,
J
u
l
y
202
6
:
50
4
-
5
1
3
508
d
i
m
en
s
io
n
al
L
I
B
R
AS
(
8
5
.
1
9
)
w
it
h
eli
te
-
d
r
i
v
e
n
co
n
v
er
g
en
c
e.
T
h
e
test
s
u
s
in
g
W
ilco
x
o
n
s
u
p
p
o
r
t
th
e
n
o
f
r
ee
lu
n
c
h
h
y
p
o
th
e
s
i
s
: th
er
e
is
n
o
o
n
e
alg
o
r
it
h
m
th
at
w
i
ll o
u
tp
er
f
o
r
m
all
d
ata
s
ets.
3
.
2
.
F
e
a
t
ure
re
du
ct
io
n a
na
ly
s
is
T
ab
le
2
s
h
o
w
s
th
e
r
ate
at
w
h
ic
h
f
ea
tu
r
es a
r
e
r
ed
u
ce
d
b
y
ea
c
h
alg
o
r
ith
m
m
ea
n
in
g
h
o
w
ea
c
h
alg
o
r
ith
m
is
ab
le
to
r
ed
u
ce
th
e
d
im
en
s
io
n
alit
y
w
it
h
o
u
t
af
f
ec
ti
n
g
th
e
clas
s
if
ica
tio
n
.
B
QI
HP
FA
attain
s
an
av
er
ag
e
r
ed
u
ctio
n
r
ate
o
f
6
4
.
1
w
h
ich
i
s
a
g
o
o
d
b
alan
ce
o
f
f
ea
t
u
r
e
s
elec
tio
n
,
n
eit
h
er
o
v
er
-
p
r
u
n
i
n
g
(
w
h
ich
r
i
s
k
l
o
s
in
g
ac
cu
r
ac
y
)
n
o
r
u
n
d
er
-
p
r
u
n
i
n
g
(
w
asti
n
g
co
m
p
u
tatio
n
r
eso
u
r
ce
s
)
.
R
ed
u
ctio
n
o
f
f
ea
t
u
r
es
is
i
n
d
icate
d
in
T
a
b
le
2
.
B
QI
H
P
FA
h
a
s
th
e
h
i
g
h
est
a
v
er
ag
e
r
ed
u
ctio
n
o
f
6
4
.
1
%
an
d
b
alan
ce
s
b
et
w
ee
n
ac
cu
r
ac
y
an
d
e
f
f
icien
c
y
tr
ad
eo
f
f
s
.
B
GW
O
o
p
tim
izes
t
h
e
r
ed
u
ctio
n
in
L
I
B
R
A
S
(
5
3
.
3
%
r
ed
u
ctio
n
is
t
h
e
m
o
s
t
i
m
p
o
r
tan
t
in
r
eso
u
r
ce
co
n
s
tr
ai
n
ed
s
y
s
te
m
s
)
,
B
W
O
o
p
ti
m
izes
th
e
r
ed
u
ctio
n
o
n
P
ar
k
i
n
s
o
n
(
1
3
.
6
%
r
ed
u
ctio
n
,
9
1
.
5
3
%
ac
cu
r
ac
y
,
an
d
r
eso
u
r
ce
-
co
n
s
tr
ai
n
ed
m
ed
ical
d
iag
n
o
s
i
s
)
,
co
n
s
i
s
ten
t
w
it
h
its
d
esig
n
f
o
r
ag
g
r
ess
iv
e
b
in
ar
y
d
is
cr
ete
o
p
tim
izatio
n
[
2
9
]
an
d
B
QI
HPF
A
o
p
tim
izes
th
e
r
ed
u
ctio
n
o
n
P
ar
k
in
s
o
n
(
7
2
.
7
%
r
ed
u
ctio
n
an
d
6
f
ea
tu
r
e
s
)
.
P
ar
eto
an
al
y
s
is
e
s
tab
lis
h
es
th
a
t
th
er
e
is
n
o
g
e
n
er
al
al
g
o
r
it
hm
-
s
el
ec
tio
n
is
d
ep
en
d
e
n
t
o
n
th
e
n
ee
d
o
f
ap
p
licatio
n
.
T
ab
le
1
.
C
lass
if
icatio
n
ac
c
u
r
ac
y
co
m
p
ar
is
o
n
(
%)
A
l
g
o
r
i
t
h
m
LI
B
R
A
S
(
9
0
f
e
a
t
.
)
P
a
r
k
i
n
so
n
(
2
2
f
e
a
t
.
)
S
o
n
a
r
(
6
0
f
e
a
t
.
)
A
v
e
r
a
g
e
S
t
d
.
D
e
v
.
B
Q
I
H
P
F
A
8
2
.
7
8
8
0
.
4
9
8
8
.
4
6
8
3
.
5
7
5
.
2
1
B
P
S
O
7
9
.
1
7
8
3
.
3
3
8
6
.
5
4
8
3
.
0
1
7
.
8
3
B
G
W
O
8
5
.
1
9
7
8
.
2
1
8
5
.
9
0
8
3
.
1
0
6
.
4
2
B
W
O
7
6
.
3
9
9
1
.
5
3
8
2
.
6
9
8
3
.
5
4
8
.
1
4
T
ab
le
2
.
Featu
r
e
r
ed
u
ctio
n
r
ate
(
%)
an
d
s
elec
ted
f
ea
t
u
r
es
A
l
g
o
r
i
t
h
m
LI
B
R
A
S
P
a
r
k
i
n
so
n
S
o
n
a
r
A
v
e
r
a
g
e
(
%)
A
v
g
.
se
l
e
c
t
e
d
(
f
e
a
t
u
r
e
s)
B
Q
I
H
P
F
A
6
0
.
0
%
(
3
6
se
l
.
)
7
2
.
7
%
(
6
se
l
.
)
6
0
.
0
%
(
2
4
se
l
.
)
6
4
.
1
2
2
B
P
S
O
5
5
.
6
%
(
4
0
se
l
.
)
6
8
.
2
%
(
7
se
l
.
)
5
8
.
3
%
(
2
5
se
l
.
)
6
0
.
7
2
4
B
G
W
O
5
3
.
3
%
(
4
2
se
l
.
)
7
7
.
3
%
(
5
se
l
.
)
6
3
.
3
%
(
2
2
se
l
.
)
6
4
.
6
2
3
B
W
O
6
2
.
2
%
(
3
4
se
l
.
)
1
3
.
6
%
(
1
9
se
l
.
)
6
1
.
7
%
(
2
3
se
l
.
)
4
5
.
8
2
5
.
3
3
.
3
.
Co
nv
er
g
ence
beha
v
io
r
Fig
u
r
e
1
p
r
esen
ts
th
e
b
es
t
-
f
it
n
es
s
co
n
v
er
g
en
ce
c
u
r
v
e
s
o
f
all
f
o
u
r
al
g
o
r
ith
m
s
—
B
QI
HP
F
A
,
B
P
SO,
B
GW
O,
an
d
B
W
O
—
ac
r
o
s
s
t
h
e
th
r
ee
b
en
c
h
m
ar
k
d
ataset
s
,
w
it
h
ea
c
h
s
u
b
-
f
ig
u
r
e
co
r
r
esp
o
n
d
in
g
to
a
d
if
f
er
e
n
t
p
r
o
b
lem
d
i
m
en
s
io
n
ali
t
y
.
Fi
g
u
r
e
1
(
a)
s
h
o
w
s
co
n
v
er
g
e
n
ce
b
eh
av
io
r
o
n
th
e
L
I
B
R
A
S
m
o
v
e
m
e
n
t
d
ataset
(
9
0
f
ea
tu
r
es),
w
h
ic
h
r
ep
r
esen
t
s
a
h
ig
h
-
d
i
m
e
n
s
io
n
a
l
f
ea
t
u
r
e
s
elec
tio
n
task
w
h
er
e
th
e
s
ea
r
ch
s
p
ac
e
co
n
tain
s
2
⁹⁰
p
o
s
s
ib
le
s
u
b
s
et
s
; th
e
cu
r
v
es r
e
v
ea
l h
o
w
ea
ch
al
g
o
r
ith
m
n
a
v
i
g
ates t
h
is
lar
g
e
s
ea
r
c
h
s
p
ac
e
an
d
w
h
et
h
er
it a
v
o
id
s
p
r
e
m
at
u
r
e
co
n
v
er
g
e
n
ce
.
Fi
g
u
r
e
1
(
b
)
p
r
esen
ts
r
es
u
lt
o
n
th
e
P
ar
k
i
n
s
o
n
'
s
d
is
ea
s
e
d
etec
tio
n
d
ataset
(
2
2
f
ea
tu
r
es),
a
lo
w
-
d
i
m
e
n
s
io
n
al
p
r
o
b
le
m
i
n
w
h
ich
t
h
e
r
ela
tiv
el
y
co
m
p
ac
t
s
ea
r
ch
s
p
ac
e
(
2
²²
s
u
b
s
ets)
al
lo
w
s
m
o
s
t
al
g
o
r
ith
m
s
to
r
ea
ch
n
ea
r
-
o
p
ti
m
al
f
it
n
es
s
ea
r
l
y
—
t
h
i
s
s
u
b
-
f
i
g
u
r
e
h
i
g
h
li
g
h
ts
d
i
f
f
er
e
n
ce
s
in
co
n
v
er
g
en
ce
s
tab
ilit
y
an
d
s
tag
n
atio
n
b
eh
a
v
io
r
.
Fig
u
r
e
1
(
c)
illu
s
tr
ates
c
o
n
v
er
g
e
n
ce
o
n
th
e
So
n
ar
R
o
ck
v
s
.
Mi
n
e
d
atase
t
(
6
0
f
ea
tu
r
es),
an
in
ter
m
ed
iate
-
d
i
m
e
n
s
io
n
alit
y
s
etti
n
g
th
at
t
ests
th
e
b
alan
ce
b
et
w
ee
n
ex
p
lo
r
atio
n
s
p
ee
d
an
d
ex
p
lo
itatio
n
q
u
alit
y
.
I
n
all
th
r
ee
s
u
b
-
f
ig
u
r
es,
th
e
x
-
a
x
is
r
e
p
r
esen
ts
th
e
iter
atio
n
n
u
m
b
er
(
1
to
5
0
)
an
d
th
e
y
-
a
x
i
s
r
ep
r
esen
t
s
t
h
e
b
est
f
it
n
es
s
v
a
lu
e
ac
h
ie
v
ed
s
o
f
ar
(
lo
w
er
i
s
b
etter
,
s
i
n
ce
t
h
e
o
b
j
ec
tiv
e
f
u
n
c
tio
n
is
m
i
n
i
m
ized
)
.
Sh
ad
ed
r
eg
io
n
s
o
r
er
r
o
r
b
ar
s
in
d
icate
s
tan
d
ar
d
d
ev
iatio
n
ac
r
o
s
s
5
in
d
ep
en
d
en
t
r
u
n
s
,
r
ef
lecti
n
g
alg
o
r
ith
m
co
n
s
i
s
te
n
c
y
.
T
h
e
r
e
ad
er
s
h
o
u
ld
p
ay
p
ar
ticu
lar
atten
tio
n
to
:
i
)
th
e
s
lo
p
e
o
f
co
n
v
er
g
en
ce
in
t
h
e
f
ir
s
t 2
0
iter
atio
n
s
,
w
h
ic
h
r
e
f
lects
in
itia
l
ex
p
lo
r
atio
n
ca
p
ab
ilit
y
;
ii
)
th
e
p
latea
u
b
eh
a
v
io
r
i
n
later
iter
ati
o
n
s
,
w
h
ic
h
r
ef
lec
ts
ex
p
lo
itatio
n
q
u
ali
t
y
a
n
d
s
tag
n
atio
n
ten
d
en
c
y
;
a
n
d
iii
)
th
e
f
i
n
al
f
i
tn
e
s
s
v
a
lu
e
at
iter
atio
n
5
0
,
w
h
ic
h
d
ir
ec
tl
y
d
eter
m
in
e
s
class
if
icatio
n
ac
c
u
r
ac
y
a
n
d
f
ea
t
u
r
e
r
ed
u
ctio
n
.
C
o
n
v
er
g
e
n
ce
(
m
etr
ics)
ar
e
p
r
esen
ted
i
n
Fig
u
r
e
1
a
n
d
T
ab
le
3
.
B
P
SO
m
a
x
i
m
u
m
s
p
ee
d
(
2
6
.
8
iter
atio
n
s
)
co
in
cid
es
w
it
h
s
o
cial
lear
n
i
n
g
is
q
u
ick
e
s
t,
b
u
t
it
h
a
s
th
e
m
o
s
t
s
tag
n
atio
n
(
2
8
%
o
f
th
e
r
u
n
s
)
a
n
d
is
s
u
s
ce
p
tib
le
to
lo
ca
l
o
p
tim
a.
B
W
O
ex
h
ib
its
o
s
cillato
r
y
co
n
v
er
g
e
n
ce
(
3
4
.
7
i
ter
atio
n
s
an
d
8
.
3
s
td
.
d
ev
)
b
ec
au
s
e
o
f
p
r
o
b
ab
ilis
tic
m
o
d
e
s
w
itc
h
i
n
g
w
h
ic
h
f
o
r
m
ed
u
n
p
r
ed
ictab
le
co
n
v
er
g
e
n
ce
t
h
a
t
is
n
o
t
ap
p
licab
le
in
r
ea
l
ti
m
e
e
m
b
ed
d
ed
s
y
s
te
m
s
.
B
GW
O
d
em
o
n
s
tr
ates h
i
g
h
co
n
v
er
g
e
n
ce
at
an
ea
r
l
y
s
tag
e
(
2
4
.
3
%
)
b
u
t
th
e
g
r
ea
test
s
tag
n
atio
n
(
3
2
%
)
b
ec
au
s
e
o
f
th
e
d
ec
r
ea
s
e
in
d
iv
er
s
it
y
t
h
r
o
u
g
h
elite
d
ep
en
d
en
ce
.
B
QI
HPF
A
h
as
a
co
n
v
er
g
en
ce
w
it
h
le
ast
s
tag
n
atio
n
(
8
%,
3
1
.
2
iter
atio
n
s
,
an
d
4
.
1
s
td
.
d
ev
)
,
en
s
u
r
i
n
g
t
h
at
it is
m
o
s
t r
o
b
u
s
t
w
ith
e
m
b
ed
d
ed
s
y
s
te
m
s
t
h
at
n
ee
d
co
n
v
er
g
e
n
ce
g
u
ar
a
n
tees a
t t
h
e
lo
w
est p
o
s
s
i
b
le
co
s
t
w
it
h
o
u
t e
x
p
en
s
iv
e
r
e
-
r
u
n
s
.
T
ab
le
3
is
a
m
ea
s
u
r
e
o
f
co
n
v
er
g
en
ce
e
f
f
icien
c
y
,
w
h
ich
is
ca
lc
u
lated
b
y
th
e
ar
ea
u
n
d
er
th
e
co
n
v
er
g
en
ce
cu
r
v
e
(
A
UC
)
,
w
it
h
s
m
aller
AUC
r
ep
r
esen
ti
n
g
o
p
ti
m
iza
tio
n
s
w
i
th
h
ig
h
er
s
p
ee
d
.
B
QI
HP
F
A
h
a
s
a
s
ec
o
n
d
-
b
es
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
I
SS
N:
2089
-
4864
B
in
a
r
y
h
yb
r
id
p
a
th
fin
d
er a
lg
o
r
ith
m
fo
r
efficien
t fe
a
tu
r
e
s
ele
ctio
n
in
r
eso
u
r
ce
…
(
R
a
h
u
l Mir
a
jka
r
)
509
av
er
ag
e
AUC th
a
n
B
P
SO
(
0
.
2
8
9
)
w
ith
a
s
ig
n
i
f
ica
n
tl
y
lo
w
er
s
tag
n
atio
n
r
ate
(
8
as
co
m
p
ar
ed
to
2
8
p
er
ce
n
t)
s
o
it
is
ap
p
r
o
p
r
iate
w
h
en
e
m
b
ed
d
ed
s
y
s
te
m
s
n
ee
d
co
s
tl
y
r
e
-
e
x
ec
u
t
io
n
s
o
w
in
g
to
f
a
ilu
r
e
o
f
co
n
v
e
r
g
en
ce
[
2
8
]
.
(
a)
(
b
)
(
c)
Fig
u
r
e
1
.
C
o
n
v
er
g
en
ce
c
u
r
v
e
s
o
f
B
QI
HP
FA
an
d
b
aseli
n
e
al
g
o
r
ith
m
s
o
n
;
(
a)
L
I
B
R
AS,
(
b
)
Par
k
in
s
o
n
'
s
,
a
n
d
(
c)
So
n
ar
d
atasets
o
v
er
5
0
iter
atio
n
s
(
m
ea
n
±
SD,
5
r
u
n
s
; lo
w
er
f
itn
e
s
s
i
s
b
etter
)
T
ab
le
3
.
C
o
n
v
er
g
e
n
ce
ef
f
icie
n
c
y
m
etr
ic
s
A
l
g
o
r
i
t
h
m
A
v
g
.
i
t
e
r
a
t
i
o
n
s
t
o
9
5
%
A
U
C
(
l
o
w
e
r
=
b
e
t
t
e
r
)
S
t
a
g
n
a
t
i
o
n
r
a
t
e
(
%)
B
Q
I
H
P
F
A
3
1
.
2
0
.
3
1
2
8
B
P
S
O
2
6
.
8
0
.
2
8
9
28
B
G
W
O
2
8
.
5
0
.
3
0
1
32
B
W
O
3
4
.
7
0
.
3
3
8
12
3
.
4
.
Co
m
p
uta
t
io
na
l
ef
f
iciency
f
o
r
em
bedd
e
d deplo
y
m
ent
T
ab
le
4
s
h
o
w
s
th
e
r
u
n
t
i
m
e
an
d
m
e
m
o
r
y
v
al
u
es
w
h
ich
ar
e
s
ig
n
i
f
ica
n
t
in
d
eter
m
i
n
i
n
g
th
e
f
e
asib
ilit
y
o
f
ex
ec
u
t
in
g
t
h
e
ap
p
licatio
n
w
i
th
r
eso
u
r
ce
co
n
s
tr
ain
ed
e
m
b
ed
d
ed
s
y
s
te
m
s
.
B
QI
HP
FA
ta
k
es
a
n
av
er
ag
e
o
f
1
4
.
9
s
ec
o
n
d
s
to
ex
ec
u
te
a
d
ataset
(
r
a
n
g
e:
1
2
.
3
-
1
8
.
7
s
ec
o
n
d
s
)
a
(
m
ea
n
)
5
.
2
tim
e
s
f
as
ter
th
an
B
W
O
(
6
2
.
5
-
94.
3
s
ec
o
n
d
s
,
m
ea
n
: 7
7
.
4
s
ec
o
n
d
s
)
an
d
3
.
1
tim
e
s
f
a
s
ter
th
a
n
B
G
W
O
(
3
8
.
2
-
5
7
.
6
s
ec
o
n
d
s
an
d
m
ea
n
: 4
6
.
8
s
ec
o
n
d
s
)
.
B
P
SO
is
th
e
f
astes
t
(
w
it
h
an
a
v
er
ag
e
r
u
n
ti
m
e
o
f
1
2
.
6
s
ec
o
n
d
s
)
b
ec
au
s
e
its
co
m
p
u
ta
t
io
n
al
o
v
er
h
ea
d
is
v
er
y
m
in
i
m
al
:
v
elo
cit
y
u
p
d
ates
o
n
l
y
n
ee
d
to
u
s
e
v
ec
to
r
ar
ith
m
etic
o
p
er
atio
n
s
an
d
s
i
g
m
o
id
f
u
n
ctio
n
s
[
1
0
]
.
Nev
er
th
e
less
,
s
u
ch
a
h
ig
h
s
ta
g
n
at
io
n
r
ate
(
2
8
%
T
ab
le
3
)
o
f
B
P
SO
i
m
p
lies
t
h
at
it
w
o
u
ld
t
ak
e
s
e
v
er
al
r
es
tar
ts
w
it
h
v
ar
io
u
s
i
n
itializa
t
io
n
s
to
b
e
d
ep
lo
y
ed
in
p
r
ac
tice,
w
h
ic
h
w
o
u
ld
n
u
lli
f
y
t
h
e
s
p
ee
d
b
en
ef
it
.
T
h
e
r
e
-
r
u
n
s
s
h
o
u
ld
b
e
m
ad
e
an
d
s
ee
n
to
b
e
s
u
cc
ess
f
u
l
w
it
h
a
s
u
cc
e
s
s
r
ate
o
f
9
5
%
to
m
ak
e
t
h
e
ef
f
ec
ti
v
e
r
u
n
ti
m
e
o
f
B
P
SO
1
2
.
6
/0
.
7
2
=1
7
.
5
s
ec
o
n
d
s
-
eq
u
al
to
th
e
ef
f
ec
ti
v
e
r
u
n
ti
m
e
o
f
B
QI
HP
F
A
w
h
en
r
u
n
n
i
n
g
o
n
ce
.
T
ab
le
4
.
C
o
m
p
u
ta
tio
n
al
e
f
f
icie
n
c
y
m
etr
ics
A
l
g
o
r
i
t
h
m
LI
B
R
A
S
t
i
me
(
s)
P
a
r
k
i
n
so
n
t
i
me
(
s)
S
o
n
a
r
t
i
me
(
s)
A
v
g
.
t
i
me
P
e
a
k
me
mo
r
y
(
MB
)
B
Q
I
H
P
F
A
1
8
.
7
1
3
.
1
1
2
.
3
1
4
.
9
5
8
.
3
B
P
S
O
1
5
.
2
1
1
.
8
1
0
.
9
1
2
.
6
5
5
.
7
B
G
W
O
5
7
.
6
4
2
.
3
3
8
.
2
4
6
.
8
7
2
.
1
B
W
O
9
4
.
3
7
5
.
8
6
2
.
5
7
7
.
4
8
7
.
2
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4864
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
,
Vo
l.
15
,
No
.
2
,
J
u
l
y
202
6
:
50
4
-
5
1
3
510
B
QI
HP
FA
h
as a
m
a
x
i
m
u
m
m
e
m
o
r
y
u
s
a
g
e
o
f
4
5
.
2
-
5
8
.
3
MB a
cr
o
s
s
d
ataset
s
w
h
ich
is
r
elati
v
el
y
b
r
o
ad
co
m
p
ar
ed
to
B
P
SO
(
4
2
.
1
-
5
5
.
7
MB
)
an
d
f
ar
m
u
c
h
les
s
t
h
an
B
W
O
(
6
8
.
4
-
8
7
.
2
MB
)
.
Su
ch
f
o
o
tp
r
in
ts
ar
e
ea
s
il
y
ac
ce
s
s
ib
le
w
it
h
i
n
th
e
li
m
i
ts
o
f
cu
r
r
en
t e
m
b
ed
d
ed
s
y
s
te
m
s
[
2
8
]
:
−
R
asp
b
er
r
y
P
i 4
: 1
-
8
GB
R
A
M
(
B
QI
HP
FA
u
tili
ze
s
les
s
th
a
n
0
.
0
6
% o
f
1
GB
m
o
d
el)
.
−
NVI
DI
A
J
etso
n
Na
n
o
: 2
-
4
GB
R
A
M
(
B
QI
HP
FA
u
s
es le
s
s
t
h
an
3
%
o
f
2
GB
m
o
d
el)
.
−
S
T
M
3
2
H
7
m
i
c
r
o
c
o
n
t
r
o
l
l
e
r
:
1
-
2
M
B
R
A
M
(
s
e
l
e
c
t
i
o
n
o
f
f
e
a
t
u
r
e
s
i
s
d
o
n
e
o
f
f
l
i
n
e
;
o
n
l
y
s
e
l
e
c
t
e
d
f
e
a
t
u
r
e
s
d
e
p
l
o
y
e
d
)
.
I
n
c
o
n
tr
ast
,
d
ee
p
l
ea
r
n
in
g
-
b
as
ed
ap
p
r
o
ac
h
es
r
eq
u
i
r
e
m
o
d
el
co
m
p
r
ess
i
o
n
tech
n
i
q
u
es
s
u
ch
as
p
r
u
n
in
g
,
q
u
an
ti
za
t
io
n
,
an
d
Hu
f
f
m
a
n
co
d
in
g
to
a
ch
iev
e
co
m
p
a
r
a
b
l
e
f
o
o
t
p
r
in
ts
[
3
0
]
,
m
ak
in
g
B
QI
H
PF
A
's
lig
h
tw
eig
h
t
n
atu
r
e
p
a
r
ti
cu
la
r
ly
a
d
v
an
t
ag
e
o
u
s
f
o
r
d
i
r
e
ct
em
b
e
d
d
e
d
d
e
p
l
o
y
m
en
t.
T
o
th
e
I
o
T
e
d
g
e
d
ev
ices
w
h
er
e
o
n
l
in
e
a
d
a
p
t
iv
e
lea
r
n
in
g
is
u
s
e
d
(
th
at
is
,
p
e
r
i
o
d
ic
ally
ch
o
o
s
in
g
f
ea
tu
r
es
as
d
ata
d
is
t
r
i
b
u
ti
o
n
s
ch
an
g
e)
,
th
e
1
4
.
9
-
s
ec
o
n
d
r
u
n
tim
e
an
d
5
8
M
B
m
e
m
o
r
y
o
f
B
Q
I
H
P
FA
all
o
w
f
ea
tu
r
e
s
e
le
cti
o
n
t
o
f
in
is
h
w
ith
in
th
e
n
o
r
m
al
m
ain
ten
an
ce
w
in
d
o
w
s
(
e
.
g
.
,
n
ig
h
tly
r
et
r
ain
in
g
cy
cles)
w
ith
o
u
t c
au
s
in
g
th
e
r
e
al
-
tim
e
in
f
er
en
c
e
w
o
r
k
l
o
a
d
s
[
1
4
]
.
I
n
tel
i7
-
9
7
5
0
H
T
D
P
(
4
5
W
)
esti
m
ates
o
f
e
n
er
g
y
co
n
s
u
m
p
tio
n
B
QI
HP
F
A
:
r
o
u
g
h
l
y
0
.
1
8
7
W
h
(
1
4
.
9
s
ec
o
n
d
s
m
u
ltip
lied
b
y
4
5
W
=0
.
1
8
7
W
h
)
w
as
u
s
ed
i
n
esti
m
ati
n
g
t
h
e
e
n
er
g
y
co
n
s
u
m
p
tio
n
o
f
B
QI
HP
FA
w
h
er
ea
s
t
h
e
s
a
m
e
is
0
.
9
6
9
W
h
(
5
.
2
tim
e
s
h
i
g
h
er
)
in
B
W
O.
I
n
th
e
ca
s
e
o
f
b
atter
y
o
p
er
ated
ed
g
e
d
ev
ice
s
,
th
is
5
×
p
o
w
er
ef
f
icie
n
c
y
f
ac
to
r
d
ir
ec
tl
y
co
r
r
esp
o
n
d
s
to
t
h
e
ex
ten
d
a
b
le
lif
e
b
et
w
ee
n
c
h
ar
g
e
u
p
s
p
r
o
p
o
r
tio
n
al
to
th
e
en
er
g
y
ef
f
icie
n
c
y
-
i
m
p
o
r
tan
t
i
n
r
e
m
o
te
I
o
T
a
p
p
licatio
n
s
,
s
u
ch
a
s
w
ild
lif
e
ca
m
er
as
o
r
h
ig
h
-
r
eso
l
u
tio
n
cr
o
p
s
en
s
o
r
s
[
1
5
]
.
3
.
5
.
Abla
t
io
n
s
t
ud
y
:
co
m
po
n
ent
co
ntr
ibu
t
io
n a
na
ly
s
is
T
ab
le
5
s
h
o
w
s
th
e
r
esu
lts
o
f
th
e
ab
latio
n
s
tu
d
y
in
w
h
ic
h
th
e
s
ep
ar
ate
B
QI
H
P
FA
ele
m
e
n
ts
ar
e
d
elete
d
in
a
s
y
s
te
m
atic
m
an
n
er
to
d
ete
r
m
in
e
th
eir
co
n
tr
ib
u
tio
n
to
t
h
e
g
en
er
al
p
er
f
o
r
m
an
ce
.
T
h
e
b
ase
lin
e
f
u
ll
B
QI
HP
F
A
h
as a
n
av
er
ag
e
ac
c
u
r
ac
y
o
f
8
3
.
5
7
an
d
an
av
er
ag
e
f
ea
tu
r
e
r
ed
u
ctio
n
o
f
6
4
.
1
o
n
d
atab
ases
.
T
ab
le
5
in
d
icate
s
co
n
tr
ib
u
tio
n
o
f
co
m
p
o
n
en
t
s
.
E
ac
h
f
ac
to
r
is
i
m
p
o
r
tan
t
:
th
e
v
elo
cit
y
m
o
m
e
n
t
u
m
(
-
8
.
3
4
%
ac
cu
r
ac
y
)
,
h
y
b
r
id
g
r
o
u
p
s
(
-
4
.
1
6
%),
an
n
ea
li
n
g
(
-
5
.
6
8
%),
an
d
d
iv
er
s
it
y
o
f
Ha
m
m
i
n
g
d
i
s
ta
n
ce
(
-
2
0
.
0
5
%,
m
o
s
t
s
e
n
s
iti
v
e)
.
T
h
er
e
is
th
e
s
u
p
er
io
r
it
y
o
f
s
tr
u
ct
u
r
ed
s
ea
r
ch
o
v
er
r
an
d
o
m
b
ase
lin
e,
2
5
.
4
3
,
w
h
ich
p
r
o
v
es
th
at
th
e
s
u
cc
e
s
s
o
f
B
QI
HP
FA
is
d
u
e
to
m
ec
h
a
n
is
m
in
t
eg
r
atio
n
r
ath
er
th
a
n
th
e
s
u
cc
e
s
s
o
f
s
in
g
le
ele
m
e
n
t.
T
ab
le
5
.
A
b
latio
n
s
t
u
d
y
r
es
u
lt
s
(
av
er
ag
e
ac
r
o
s
s
3
d
atasets
)
C
o
n
f
i
g
u
r
a
t
i
o
n
A
c
c
u
r
a
c
y
(
%)
R
e
d
u
c
t
i
o
n
(
%)
R
u
n
t
i
me
(
s)
Δ A
c
c
u
r
a
c
y
(
%)
F
u
l
l
B
Q
I
H
P
F
A
8
3
.
5
7
6
4
.
1
1
4
.
9
—
W
i
t
h
o
u
t
v
e
l
o
c
i
t
y
mo
me
n
t
u
m
7
5
.
2
3
6
1
.
8
1
3
.
2
-
8
.
3
4
W
i
t
h
o
u
t
h
y
b
r
i
d
g
r
o
u
p
s
7
9
.
4
1
6
8
.
7
1
2
.
8
-
4
.
1
6
W
i
t
h
o
u
t
a
n
n
e
a
l
i
n
g
7
7
.
8
9
5
9
.
3
1
4
.
1
-
5
.
6
8
W
i
t
h
o
u
t
H
a
mm
i
n
g
d
i
st
a
n
c
e
6
3
.
5
2
5
5
.
2
1
5
.
3
-
2
0
.
0
5
R
a
n
d
o
m se
a
r
c
h
b
a
se
l
i
n
e
5
8
.
1
4
5
0
.
0
8
.
9
-
2
5
.
4
3
4.
CO
NCLU
SI
O
N
T
h
is
p
ap
er
in
tr
o
d
u
ce
s
t
h
e
b
i
n
a
r
y
f
o
r
m
o
f
QI
HP
F
A
,
B
QI
HP
FA
,
a
n
d
t
h
e
i
n
itial
b
in
ar
y
f
o
r
m
o
f
QI
HP
F
A
to
b
e
ap
p
lied
in
e
m
b
ed
d
ed
f
ea
tu
r
e
s
elec
tio
n
.
C
o
m
p
e
titi
v
e
class
i
f
icatio
n
ac
cu
r
ac
y
(
8
3
.
5
7
%
av
er
a
g
e)
ca
n
b
e
o
b
tain
ed
w
it
h
B
QI
HP
F
A
w
it
h
s
u
b
s
ta
n
tial
f
ea
t
u
r
e
r
ed
u
ctio
n
(
6
4
.
1
%),
an
d
it
is
also
5
.
2
×
f
aster
th
an
t
h
e
co
m
p
le
x
b
aselin
es
(
B
W
O)
w
it
h
a
s
m
all
m
e
m
o
r
y
f
o
o
tp
r
in
t
(
4
5
-
5
8
M
B
p
ea
k
)
,
w
h
ic
h
i
m
p
lies
it
ca
n
b
e
d
ep
lo
y
ed
o
n
th
e
ed
g
e
o
f
a
n
I
o
T
.
T
h
e
alg
o
r
ith
m
h
as
t
h
e
lea
s
t
s
ta
g
n
atio
n
(
8
%)
an
d
co
n
ti
n
u
o
u
s
co
n
v
er
g
e
n
ce
w
it
h
o
u
t
d
ata
s
et
-
d
ep
en
d
en
t
t
u
n
i
n
g
,
w
h
ic
h
is
e
s
s
e
n
tial
i
n
e
m
b
ed
d
ed
s
y
s
te
m
s
w
h
o
s
e
d
ep
lo
y
m
e
n
t
e
n
v
ir
o
n
m
en
ts
ar
e
u
n
k
n
o
w
n
.
A
b
la
tio
n
ex
p
er
i
m
e
n
t
s
v
al
id
ate
ev
er
y
ele
m
en
t
h
as
8
-
24
%
co
n
tr
ib
u
tio
n
to
t
h
e
p
er
f
o
r
m
a
n
ce
b
y
in
teg
r
ati
n
g
s
y
n
er
g
i
s
ticall
y
.
F
u
t
u
r
e
d
ir
ec
tio
n
s
ar
e:
i
)
h
y
b
r
id
v
ar
ia
n
ts
o
f
tr
an
s
f
er
f
u
n
ctio
n
s
w
it
h
1
5
-
3
0
%
e
v
alu
a
tio
n
r
ed
u
ctio
n
;
ii
)
m
u
lti
-
o
b
j
ec
tiv
e
ex
ten
s
io
n
o
f
th
is
w
i
th
P
ar
eto
d
o
m
in
a
n
ce
;
iii
)
u
ltra
-
h
i
g
h
-
d
i
m
en
s
io
n
a
l
s
ca
l
in
g
(
m
illi
o
n
+f
ea
t
u
r
es);
a
n
d
iv
)
v
al
id
atio
n
o
f
p
r
o
d
u
ctio
n
I
o
T
e
d
g
e
d
ep
lo
y
m
e
n
t.
F
UNDIN
G
I
NF
O
RM
AT
I
O
N
T
h
is
r
esear
ch
r
ec
ei
v
ed
n
o
s
p
ec
if
ic
g
r
an
t
f
r
o
m
a
n
y
f
u
n
d
in
g
a
g
en
c
y
i
n
th
e
p
u
b
lic,
co
m
m
er
ci
al,
o
r
n
o
t
-
f
o
r
-
p
r
o
f
it secto
r
s
.
AUTHO
R
CO
NT
RIB
UT
I
O
NS ST
A
T
E
M
E
NT
T
h
is
jo
u
r
n
al
u
s
e
s
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT
)
t
o
r
ec
o
g
n
ize
in
d
i
v
id
u
al
au
t
h
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
t
h
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
lla
b
o
r
atio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
I
SS
N:
2089
-
4864
B
in
a
r
y
h
yb
r
id
p
a
th
fin
d
er a
lg
o
r
ith
m
fo
r
efficien
t fe
a
tu
r
e
s
ele
ctio
n
in
r
eso
u
r
ce
…
(
R
a
h
u
l Mir
a
jka
r
)
511
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
R
ah
u
l M
ir
aj
k
ar
✓
✓
✓
✓
✓
✓
✓
P
r
em
a
n
an
d
G
h
ad
ek
ar
✓
✓
✓
✓
✓
✓
✓
Vij
ay
Da
s
h
ar
at
h
C
h
o
u
g
u
le
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
R
en
u
k
a
B
h
an
d
ar
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
Hr
id
ay
n
at
h
Kh
a
n
d
ag
ale
✓
✓
✓
✓
✓
✓
Ma
h
av
ir
A
.
De
v
m
an
e
✓
✓
✓
✓
✓
✓
✓
✓
✓
Ma
n
g
e
s
h
Haj
ar
e
✓
✓
✓
✓
✓
✓
✓
✓
Ku
ld
ee
p
B
.
Vay
ad
a
n
d
e
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
si
s
I
:
I
n
v
e
st
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
si
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
s
d
ec
lar
e
n
o
co
n
f
l
ic
ts
o
f
i
n
ter
est r
eg
ar
d
in
g
t
h
e
p
u
b
licatio
n
o
f
t
h
is
p
ap
er
.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
atasets
an
al
y
ze
d
in
t
h
i
s
s
tu
d
y
ar
e
p
u
b
licl
y
a
v
ailab
le
f
r
o
m
t
h
e
UC
I
Ma
c
h
i
n
e
L
ea
r
n
i
n
g
R
ep
o
s
ito
r
y
[
1
9
]
.
RE
F
E
R
E
NC
E
S
[
1
]
G
.
C
h
a
n
d
r
a
s
h
e
k
a
r
a
n
d
F
.
S
a
h
i
n
,
“
A
su
r
v
e
y
o
n
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
me
t
h
o
d
s
,
”
C
o
m
p
u
t
e
rs
&
El
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
4
0
,
n
o
.
1
,
p
p
.
16
–
2
8
,
Ja
n
.
2
0
1
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
e
l
e
c
e
n
g
.
2
0
1
3
.
1
1
.
0
2
4
.
[
2
]
M
.
A
.
U
d
d
i
n
,
A
.
S
t
r
a
n
i
e
r
i
,
I
.
G
o
n
d
a
l
,
a
n
d
V
.
B
a
l
a
su
b
r
a
m
a
n
i
a
n
,
“
A
s
u
r
v
e
y
o
n
t
h
e
a
d
o
p
t
i
o
n
o
f
b
l
o
c
k
c
h
a
i
n
i
n
I
o
T
:
c
h
a
l
l
e
n
g
e
s
a
n
d
so
l
u
t
i
o
n
s
,
”
Bl
o
c
k
c
h
a
i
n
:
Re
s
e
a
r
c
h
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
,
n
o
.
2
,
p
.
1
0
0
0
0
6
,
Ju
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
c
r
a
.
2
0
2
1
.
1
0
0
0
0
6
.
[
3
]
X.
-
S
.
Y
a
n
g
,
“
N
a
t
u
r
e
-
i
n
sp
i
r
e
d
o
p
t
i
m
i
z
a
t
i
o
n
a
l
g
o
r
i
t
h
ms:
C
h
a
l
l
e
n
g
e
s
a
n
d
o
p
e
n
p
r
o
b
l
e
ms,”
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
a
t
i
o
n
a
l
S
c
i
e
n
c
e
,
v
o
l
.
4
6
,
p
.
1
0
1
1
0
4
,
O
c
t
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
o
c
s.2
0
2
0
.
1
0
1
1
0
4
.
[
4
]
R
.
B
e
l
l
man
,
“
D
y
n
a
mi
c
p
r
o
g
r
a
mm
i
n
g
a
n
d
L
a
g
r
a
n
g
e
mu
l
t
i
p
l
i
e
r
s,”
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
N
a
t
i
o
n
a
l
Ac
a
d
e
m
y
o
f
S
c
i
e
n
c
e
s
,
v
o
l
.
4
2
,
n
o
.
1
0
,
p
p
.
7
6
7
–
7
6
9
,
O
c
t
.
1
9
5
6
,
d
o
i
:
1
0
.
1
0
7
3
/
p
n
a
s.
4
2
.
1
0
.
7
6
7
.
[
5
]
H
.
L
i
u
a
n
d
H
.
M
o
t
o
d
a
,
Fe
a
t
u
re
S
e
l
e
c
t
i
o
n
f
o
r
K
n
o
w
l
e
d
g
e
D
i
sc
o
v
e
ry
a
n
d
D
a
t
a
Mi
n
i
n
g
.
B
o
st
o
n
,
M
A
:
S
p
r
i
n
g
e
r
U
S
,
1
9
9
8
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
1
-
4
6
1
5
-
5
6
8
9
-
3.
[
6
]
M
.
M
a
f
a
r
j
a
a
n
d
S
.
M
i
r
j
a
l
i
l
i
,
“
W
h
a
l
e
o
p
t
i
mi
z
a
t
i
o
n
a
p
p
r
o
a
c
h
e
s
f
o
r
w
r
a
p
p
e
r
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
,
”
Ap
p
l
i
e
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
6
2
,
p
p
.
4
4
1
–
4
5
3
,
J
a
n
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
s
o
c
.
2
0
1
7
.
1
1
.
0
0
6
.
[
7
]
S
.
M
i
r
j
a
l
i
l
i
a
n
d
A
.
L
e
w
i
s,
“
T
h
e
W
h
a
l
e
O
p
t
i
mi
z
a
t
i
o
n
A
l
g
o
r
i
t
h
m,”
A
d
v
a
n
c
e
s
i
n
E
n
g
i
n
e
e
r
i
n
g
S
o
f
t
w
a
re
,
v
o
l
.
9
5
,
p
p
.
5
1
–
6
7
,
M
a
y
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
d
v
e
n
g
so
f
t
.
2
0
1
6
.
0
1
.
0
0
8
.
[
8
]
S
.
M
i
r
j
a
l
i
l
i
a
n
d
A
.
L
e
w
i
s,
“
S
-
sh
a
p
e
d
v
e
r
su
s
V
-
sh
a
p
e
d
t
r
a
n
sf
e
r
f
u
n
c
t
i
o
n
s
f
o
r
b
i
n
a
r
y
P
a
r
t
i
c
l
e
S
w
a
r
m
O
p
t
i
m
i
z
a
t
i
o
n
,
”
S
w
a
rm
a
n
d
Ev
o
l
u
t
i
o
n
a
r
y
C
o
m
p
u
t
a
t
i
o
n
,
v
o
l
.
9
,
p
p
.
1
–
1
4
,
A
p
r
.
2
0
1
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
sw
e
v
o
.
2
0
1
2
.
0
9
.
0
0
2
.
[
9
]
B
.
X
u
e
,
M
.
Z
h
a
n
g
,
W
.
N
.
B
r
o
w
n
e
,
a
n
d
X
.
Y
a
o
,
“
A
S
u
r
v
e
y
o
n
Ev
o
l
u
t
i
o
n
a
r
y
C
o
mp
u
t
a
t
i
o
n
A
p
p
r
o
a
c
h
e
s
t
o
F
e
a
t
u
r
e
S
e
l
e
c
t
i
o
n
,
”
I
EE
E
T
ra
n
s
a
c
t
i
o
n
s
o
n
Ev
o
l
u
t
i
o
n
a
r
y
C
o
m
p
u
t
a
t
i
o
n
,
v
o
l
.
2
0
,
n
o
.
4
,
p
p
.
6
0
6
–
6
2
6
,
A
u
g
.
2
0
1
6
,
d
o
i
:
1
0
.
1
1
0
9
/
T
EV
C
.
2
0
1
5
.
2
5
0
4
4
2
0
.
[
1
0
]
J.
K
e
n
n
e
d
y
a
n
d
R
.
C
.
E
b
e
r
h
a
r
t
,
“
A
d
i
scre
t
e
b
i
n
a
r
y
v
e
r
si
o
n
o
f
t
h
e
p
a
r
t
i
c
l
e
sw
a
r
m
a
l
g
o
r
i
t
h
m,
”
i
n
I
EEE
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
y
s
t
e
m
s,
Ma
n
,
a
n
d
C
y
b
e
r
n
e
t
i
c
s.
C
o
m
p
u
t
a
t
i
o
n
a
l
C
y
b
e
r
n
e
t
i
c
s
a
n
d
S
i
m
u
l
a
t
i
o
n
,
I
EEE,
1
9
9
7
,
p
p
.
4
1
0
4
–
4
1
0
8
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
S
M
C
.
1
9
9
7
.
6
3
7
3
3
9
.
[
1
1
]
E.
Emary
,
H
.
M
.
Z
a
w
b
a
a
,
a
n
d
A
.
E.
H
a
ssa
n
i
e
n
,
“
B
i
n
a
r
y
g
r
e
y
w
o
l
f
o
p
t
i
mi
z
a
t
i
o
n
a
p
p
r
o
a
c
h
e
s
f
o
r
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
,
”
N
e
u
ro
c
o
m
p
u
t
i
n
g
,
v
o
l
.
1
7
2
,
p
p
.
3
7
1
–
3
8
1
,
J
a
n
.
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m.
2
0
1
5
.
0
6
.
0
8
3
.
[
1
2
]
M
.
M
a
f
a
r
j
a
,
D
.
El
e
y
a
n
,
S
.
A
b
d
u
l
l
a
h
,
a
n
d
S
.
M
i
r
j
a
l
i
l
i
,
“
S
-
S
h
a
p
e
d
v
s.
V
-
S
h
a
p
e
d
T
r
a
n
sf
e
r
F
u
n
c
t
i
o
n
s
f
o
r
A
n
t
L
i
o
n
O
p
t
i
m
i
z
a
t
i
o
n
A
l
g
o
r
i
t
h
m
i
n
F
e
a
t
u
r
e
S
e
l
e
c
t
i
o
n
P
r
o
b
l
e
m,”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
F
u
t
u
re
N
e
t
w
o
r
k
s
a
n
d
D
i
s
t
ri
b
u
t
e
d
S
y
s
t
e
m
s
,
N
e
w
Y
o
r
k
,
N
Y
,
U
S
A
:
A
C
M
,
Ju
l
.
2
0
1
7
,
p
p
.
1
–
7
,
d
o
i
:
1
0
.
1
1
4
5
/
3
1
0
2
3
0
4
.
3
1
0
2
3
2
5
.
[
1
3
]
O
.
R
.
A
d
e
g
b
o
y
e
,
A
.
K
.
F
e
d
a
,
A
.
O
.
T
i
b
e
t
a
n
,
a
n
d
E.
B
.
A
g
y
e
k
u
m,
“
En
h
a
n
c
e
d
g
l
o
b
a
l
o
p
t
i
mi
z
a
t
i
o
n
u
s
i
n
g
q
u
a
d
r
a
t
i
c
a
l
l
y
i
n
t
e
r
p
o
l
a
t
e
d
h
y
b
r
i
d
p
a
t
h
f
i
n
d
e
r
a
l
g
o
r
i
t
h
m
,
”
C
l
u
s
t
e
r
C
o
m
p
u
t
i
n
g
,
v
o
l
.
2
8
,
n
o
.
5
,
p
.
3
3
4
,
A
u
g
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
5
8
6
-
0
2
4
-
0
4
9
9
1
-
6.
[
1
4
]
N
.
D
.
L
a
n
e
a
n
d
P
.
G
e
o
r
g
i
e
v
,
“
C
a
n
D
e
e
p
L
e
a
r
n
i
n
g
R
e
v
o
l
u
t
i
o
n
i
z
e
M
o
b
i
l
e
S
e
n
si
n
g
?
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
1
6
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
Wo
r
k
sh
o
p
o
n
M
o
b
i
l
e
C
o
m
p
u
t
i
n
g
S
y
st
e
m
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
N
e
w
Y
o
r
k
,
N
Y
,
U
S
A
:
A
C
M
,
F
e
b
.
2
0
1
5
,
p
p
.
1
1
7
–
1
2
2
,
d
o
i
:
1
0
.
1
1
4
5
/
2
6
9
9
3
4
3
.
2
6
9
9
3
4
9
.
[
1
5
]
M
.
A
.
M
a
f
a
r
j
a
a
n
d
S
.
M
i
r
j
a
l
i
l
i
,
“
W
h
a
l
e
o
p
t
i
mi
z
a
t
i
o
n
a
p
p
r
o
a
c
h
f
o
r
b
i
n
a
r
y
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
,
”
A
p
p
l
i
e
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
5
7
,
p
p
.
4
3
3
–
4
4
8
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
so
c
.
2
0
1
7
.
0
3
.
0
5
2
.
[
1
6
]
A
.
H
.
G
a
n
d
o
m
i
,
X
.
-
S
.
Y
a
n
g
,
S
.
T
a
l
a
t
a
h
a
r
i
,
a
n
d
A
.
H
.
A
l
a
v
i
,
“
F
i
r
e
f
l
y
a
l
g
o
r
i
t
h
m
w
i
t
h
c
h
a
o
s,
”
C
o
m
m
u
n
i
c
a
t
i
o
n
s
i
n
N
o
n
l
i
n
e
a
r
S
c
i
e
n
c
e
a
n
d
N
u
m
e
ri
c
a
l
S
i
m
u
l
a
t
i
o
n
,
v
o
l
.
1
8
,
n
o
.
1
,
p
p
.
8
9
–
9
8
,
Ja
n
.
2
0
1
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
n
s
n
s.
2
0
1
2
.
0
6
.
0
0
9
.
[
1
7
]
S
.
M
i
r
j
a
l
i
l
i
,
A
.
H
.
G
a
n
d
o
m
i
,
S
.
Z
.
M
i
r
j
a
l
i
l
i
,
S
.
S
a
r
e
mi
,
H
.
F
a
r
i
s,
a
n
d
S
.
M
.
M
i
r
j
a
l
i
l
i
,
“
S
a
l
p
S
w
a
r
m
A
l
g
o
r
i
t
h
m:
A
b
i
o
-
i
n
sp
i
r
e
d
o
p
t
i
m
i
z
e
r
f
o
r
e
n
g
i
n
e
e
r
i
n
g
d
e
si
g
n
p
r
o
b
l
e
ms,”
Ad
v
a
n
c
e
s
i
n
E
n
g
i
n
e
e
ri
n
g
S
o
f
t
w
a
re
,
v
o
l
.
1
1
4
,
p
p
.
1
6
3
–
1
9
1
,
D
e
c
.
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
d
v
e
n
g
so
f
t
.
2
0
1
7
.
0
7
.
0
0
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
9
-
4864
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
,
Vo
l.
15
,
No
.
2
,
J
u
l
y
202
6
:
50
4
-
5
1
3
512
[
1
8
]
J.
J.
L
i
a
n
g
,
A
.
K
.
Q
i
n
,
P
.
N
.
S
u
g
a
n
t
h
a
n
,
a
n
d
S
.
B
a
sk
a
r
,
“
C
o
m
p
r
e
h
e
n
si
v
e
l
e
a
r
n
i
n
g
p
a
r
t
i
c
l
e
sw
a
r
m
o
p
t
i
mi
z
e
r
f
o
r
g
l
o
b
a
l
o
p
t
i
m
i
z
a
t
i
o
n
o
f
mu
l
t
i
mo
d
a
l
f
u
n
c
t
i
o
n
s
,
”
I
E
EE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
Ev
o
l
u
t
i
o
n
a
r
y
C
o
m
p
u
t
a
t
i
o
n
,
v
o
l
.
1
0
,
n
o
.
3
,
p
p
.
2
8
1
–
2
9
5
,
Ju
n
.
2
0
0
6
,
d
o
i
:
1
0
.
1
1
0
9
/
T
EV
C
.
2
0
0
5
.
8
5
7
6
1
0
.
[
1
9
]
D
.
D
u
a
a
n
d
C
.
G
r
a
f
f
,
U
C
I
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
Re
p
o
si
t
o
r
y
.
I
r
v
i
n
e
,
C
A
,
U
S
A
:
U
n
i
v
e
r
si
t
y
o
f
C
a
l
i
f
o
r
n
i
a
,
S
c
h
o
o
l
o
f
I
n
f
o
r
mat
i
o
n
a
n
d
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
,
2
0
1
9
.
[
2
0
]
T
.
C
h
e
n
e
t
a
l
.
,
“
T
V
M
:
A
n
a
u
t
o
m
a
t
e
d
e
n
d
-
to
-
e
n
d
o
p
t
i
m
i
z
i
n
g
c
o
m
p
i
l
e
r
f
o
r
d
e
e
p
l
e
a
r
n
i
n
g
,
”
i
n
1
3
t
h
U
S
E
N
I
X
S
y
m
p
o
s
i
u
m
o
n
O
p
e
ra
t
i
n
g
S
y
s
t
e
m
s D
e
si
g
n
a
n
d
I
m
p
l
e
m
e
n
t
a
t
i
o
n
(
O
S
D
I
1
8
)
,
2
0
1
8
,
p
p
.
5
7
8
–
5
9
4
.
[
2
1
]
L
.
B
r
e
i
man
,
“
R
a
n
d
o
m F
o
r
e
st
s,”
Ma
c
h
i
n
e
L
e
a
r
n
i
n
g
,
v
o
l
.
4
5
,
n
o
.
1
,
p
p
.
5
–
3
2
,
O
c
t
.
2
0
0
1
,
d
o
i
:
1
0
.
1
0
2
3
/
A
:
1
0
1
0
9
3
3
4
0
4
3
2
4
.
[
2
2
]
R
.
K
o
h
a
v
i
,
“
A
st
u
d
y
o
f
c
r
o
ss
-
v
a
l
i
d
a
t
i
o
n
a
n
d
b
o
o
t
st
r
a
p
f
o
r
a
c
c
u
r
a
c
y
e
st
i
m
a
t
i
o
n
a
n
d
mo
d
e
l
se
l
e
c
t
i
o
n
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
1
4
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
i
n
t
C
o
n
f
e
r
e
n
c
e
o
n
A
rt
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
1
9
9
5
,
p
p
.
1
1
3
7
–
1
1
4
5
.
[
2
3
]
L.
M
.
A
b
u
a
l
i
g
a
h
,
A
.
T
.
K
h
a
d
e
r
,
a
n
d
E.
S
.
H
a
n
a
n
d
e
h
,
“
A
c
o
mb
i
n
a
t
i
o
n
o
f
o
b
j
e
c
t
i
v
e
f
u
n
c
t
i
o
n
s
a
n
d
h
y
b
r
i
d
K
r
i
l
l
h
e
r
d
a
l
g
o
r
i
t
h
m
f
o
r
t
e
x
t
d
o
c
u
me
n
t
c
l
u
st
e
r
i
n
g
a
n
a
l
y
si
s,”
En
g
i
n
e
e
ri
n
g
Ap
p
l
i
c
a
t
i
o
n
s
o
f
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
7
3
,
p
p
.
1
1
1
–
1
2
5
,
A
u
g
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
g
a
p
p
a
i
.
2
0
1
8
.
0
5
.
0
0
3
.
[
2
4
]
D
.
B
.
D
i
a
s
,
R
.
C
.
B
.
M
a
d
e
o
,
T
.
R
o
c
h
a
,
H
.
H
.
B
i
sca
r
o
,
a
n
d
S
.
M
.
P
e
r
e
s,
“
H
a
n
d
mo
v
e
me
n
t
r
e
c
o
g
n
i
t
i
o
n
f
o
r
B
r
a
z
i
l
i
a
n
S
i
g
n
L
a
n
g
u
a
g
e
:
A
st
u
d
y
u
s
i
n
g
d
i
st
a
n
c
e
-
b
a
se
d
n
e
u
r
a
l
n
e
t
w
o
r
k
s,”
i
n
2
0
0
9
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
i
n
t
C
o
n
f
e
re
n
c
e
o
n
N
e
u
r
a
l
N
e
t
w
o
r
k
s
,
I
EEE,
J
u
n
.
2
0
0
9
,
p
p
.
6
9
7
–
7
0
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
JC
N
N
.
2
0
0
9
.
5
1
7
8
9
1
7
.
[
2
5
]
M
.
A
.
L
i
t
t
l
e
,
P
.
E.
M
c
S
h
a
r
r
y
,
E.
J.
H
u
n
t
e
r
,
J.
S
p
i
e
l
man
,
a
n
d
L
.
O
.
R
a
m
i
g
,
“
S
u
i
t
a
b
i
l
i
t
y
o
f
D
y
sp
h
o
n
i
a
M
e
a
su
r
e
me
n
t
s
f
o
r
T
e
l
e
m
o
n
i
t
o
r
i
n
g
o
f
P
a
r
k
i
n
so
n
’
s
D
i
se
a
s
e
,
”
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
B
i
o
m
e
d
i
c
a
l
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
5
6
,
n
o
.
4
,
p
p
.
1
0
1
5
–
1
0
2
2
,
A
p
r
.
2
0
0
9
,
d
o
i
:
1
0
.
1
1
0
9
/
T
B
M
E
.
2
0
0
8
.
2
0
0
5
9
5
4
.
[
2
6
]
R
.
P
.
G
o
r
man
a
n
d
T
.
J.
S
e
j
n
o
w
sk
i
,
“
A
n
a
l
y
si
s
o
f
h
i
d
d
e
n
u
n
i
t
s
i
n
a
l
a
y
e
r
e
d
n
e
t
w
o
r
k
t
r
a
i
n
e
d
t
o
c
l
a
ssi
f
y
so
n
a
r
t
a
r
g
e
t
s,”
N
e
u
ra
l
N
e
t
w
o
rks
,
v
o
l
.
1
,
n
o
.
1
,
p
p
.
7
5
–
8
9
,
J
a
n
.
1
9
8
8
,
d
o
i
:
1
0
.
1
0
1
6
/
0
8
9
3
-
6
0
8
0
(
8
8
)
9
0
0
2
3
-
8.
[
2
7
]
F
.
W
i
l
c
o
x
o
n
,
“
I
n
d
i
v
i
d
u
a
l
C
o
mp
a
r
i
s
o
n
s
b
y
R
a
n
k
i
n
g
M
e
t
h
o
d
s,”
Bi
o
m
e
t
r
i
c
s
B
u
l
l
e
t
i
n
,
v
o
l
.
1
,
n
o
.
6
,
p
.
8
0
,
D
e
c
.
1
9
4
5
,
d
o
i
:
1
0
.
2
3
0
7
/
3
0
0
1
9
6
8
.
[
2
8
]
Z
.
Z
h
o
u
,
X
.
C
h
e
n
,
E
.
L
i
,
L
.
Ze
n
g
,
K
.
L
u
o
,
a
n
d
J
.
Z
h
a
n
g
,
“
E
d
g
e
I
n
t
e
l
l
i
g
e
n
c
e
:
P
a
v
i
n
g
t
h
e
L
a
st
M
i
l
e
o
f
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
W
i
t
h
Ed
g
e
C
o
mp
u
t
i
n
g
,”
in
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
I
E
EE
,
v
o
l
.
1
0
7
,
n
o
.
8
,
p
p
.
1
7
3
8
–
1
7
6
2
,
A
u
g
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
JP
R
O
C
.
2
0
1
9
.
2
9
1
8
9
5
1
.
[
2
9
]
A
.
G
.
H
u
ssi
e
n
,
A
.
E.
H
a
ss
a
n
i
e
n
,
E.
H
.
H
o
u
sse
i
n
,
M
.
A
mi
n
,
a
n
d
A
.
T
.
A
z
a
r
,
“
N
e
w
b
i
n
a
r
y
w
h
a
l
e
o
p
t
i
mi
z
a
t
i
o
n
a
l
g
o
r
i
t
h
m fo
r
d
i
scre
t
e
o
p
t
i
m
i
z
a
t
i
o
n
p
r
o
b
l
e
ms,”
En
g
i
n
e
e
ri
n
g
O
p
t
i
m
i
z
a
t
i
o
n
,
v
o
l
.
5
2
,
n
o
.
6
,
p
p
.
9
4
5
–
9
5
9
,
J
u
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
8
0
/
0
3
0
5
2
1
5
X
.
2
0
1
9
.
1
6
2
4
7
4
0
.
[
3
0
]
S
.
H
a
n
,
H
.
M
a
o
,
a
n
d
W
.
J.
D
a
l
l
y
,
“
D
e
e
p
c
o
mp
r
e
ssi
o
n
:
C
o
mp
r
e
ssi
n
g
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
s
w
i
t
h
p
r
u
n
i
n
g
,
t
r
a
i
n
e
d
q
u
a
n
t
i
z
a
t
i
o
n
a
n
d
H
u
f
f
man
c
o
d
i
n
g
,
”
a
rX
i
v
p
r
e
p
r
i
n
t
,
2
0
1
5
,
d
o
i
:
1
0
.
4
8
5
5
0
/
a
r
X
i
v
.
1
5
1
0
.
0
0
1
4
9
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Dr
.
Ra
h
u
l
Mi
r
a
j
k
a
r
g
ra
d
u
a
ted
f
ro
m
S
h
iv
a
ji
Un
iv
e
rsit
y
in
2
0
0
5
.
He
re
c
e
iv
e
d
M
.
T
e
c
h
.
d
e
g
re
e
f
ro
m
S
h
iv
a
ji
Un
iv
e
rsit
y
in
2
0
1
3
a
n
d
P
h
.
D.
d
e
g
re
e
fro
m
Ca
r
e
e
r
P
o
in
t
Un
iv
e
rsity
,
Ko
ta
in
2
0
2
1
.
He
w
o
rk
e
d
a
s
As
sista
n
t
P
r
o
f
e
ss
o
r
in
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
i
n
B
h
a
ra
t
i
V
i
d
y
a
p
e
e
t
h
’s
Co
ll
e
g
e
o
f
En
g
in
e
e
rin
g
,
Ko
l
h
a
p
u
r.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ra
h
u
lm
irajk
a
r9
8
2
@g
m
a
il
.
c
o
m
.
Dr
.
Pre
m
a
n
a
n
d
G
h
a
d
e
k
a
r
h
a
s
o
v
e
r
2
0
y
e
a
rs
o
f
te
a
c
h
in
g
e
x
p
e
rien
c
e
a
n
d
is
c
u
rre
n
tl
y
se
r
v
in
g
a
s
th
e
He
a
d
o
f
th
e
De
p
a
rt
m
e
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
(A
rti
f
icia
l
In
telli
g
e
n
c
e
a
n
d
M
a
c
h
i
n
e
L
e
a
rn
in
g
)
a
t
V
ish
w
a
k
a
r
m
a
In
stit
u
te
o
f
T
e
c
h
n
o
l
o
g
y
P
u
n
e
,
w
it
h
str
o
n
g
a
c
a
d
e
m
ic
a
n
d
re
se
a
rc
h
in
tere
sts
in
th
e
f
ield
s
o
f
a
rti
f
icia
l
in
telli
g
e
n
c
e
,
m
a
c
h
in
e
lea
rn
in
g
,
a
n
d
d
e
e
p
lea
rn
in
g
,
w
h
e
re
h
e
h
a
s
b
e
e
n
a
c
ti
v
e
l
y
in
v
o
lv
e
d
in
tea
c
h
in
g
,
re
se
a
r
c
h
,
a
n
d
a
c
a
d
e
m
ic
lea
d
e
rsh
ip
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
p
re
m
a
n
a
n
d
.
g
h
a
d
e
k
a
r@v
it
.
e
d
u
.
V
ija
y
Da
sha
r
a
th
C
h
o
u
g
u
le
g
ra
d
u
a
ted
f
ro
m
S
h
iv
a
ji
Un
iv
e
rsit
y
,
Ko
lh
a
p
u
r
i
n
2
0
0
7
.
He
re
c
e
i
v
e
d
M
a
ste
rs
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
d
e
g
re
e
f
ro
m
S
h
iv
a
ji
Un
iv
e
rsit
y
in
2
0
1
6
.
P
re
se
n
tl
y
w
o
rk
in
g
a
s
a
n
A
ss
istan
t
P
r
o
f
e
ss
o
r
in
Bh
a
ra
ti
V
i
d
y
a
p
e
e
th
’s
Co
ll
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
,
K
o
l
h
a
p
u
r
.
H
e
c
a
n
b
e
c
o
n
t
a
c
t
e
d
a
t
e
m
a
i
l
:
v
i
j
a
y
k
u
m
a
r
.
c
h
o
u
g
u
l
e
@
b
h
a
r
a
t
i
v
i
d
y
a
p
e
e
t
h
.
e
d
u
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
R
ec
o
n
f
i
g
u
r
ab
le
&
E
m
b
ed
d
ed
Sy
s
t
I
SS
N:
2089
-
4864
B
in
a
r
y
h
yb
r
id
p
a
th
fin
d
er a
lg
o
r
ith
m
fo
r
efficien
t fe
a
tu
r
e
s
ele
ctio
n
in
r
eso
u
r
ce
…
(
R
a
h
u
l Mir
a
jka
r
)
513
Dr
.
Re
n
u
k
a
B
h
a
n
d
a
r
i
g
ra
d
u
a
ted
f
ro
m
R
G
P
V
Un
iv
e
rsit
y
B
h
o
p
a
l
in
2
0
0
2
.
S
h
e
re
c
e
iv
e
d
M
a
ste
rs
in
e
n
g
in
e
e
ri
n
g
d
e
g
re
e
f
ro
m
D
A
V
V
Un
iv
e
rsity
in
2
0
0
5
a
n
d
t
h
e
P
h
.
D.
d
e
g
re
e
f
ro
m
S
P
P
U
P
u
n
e
in
2
0
1
9
.
P
re
se
n
tl
y
w
o
rk
in
g
a
s
a
n
A
s
so
c
iate
p
ro
f
e
ss
o
r
in
A
r
m
y
In
stit
u
te
o
f
T
e
c
h
n
o
lo
g
y
,
P
u
n
e
,
In
d
ia.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
rb
h
a
n
d
a
ri
@a
it
p
u
n
e
.
e
d
u
.
in
.
Dr
.
H
r
id
a
y
n
a
t
h
K
h
a
n
d
a
g
a
le
is
w
o
rk
in
g
a
s
A
s
sista
n
t
P
ro
f
e
ss
o
r
in
De
p
a
rtm
e
n
t
o
f
T
e
c
h
n
o
lo
g
y
,
S
h
iv
a
ji
Un
iv
e
rsity
,
Ko
lh
a
p
u
r.
His
a
re
a
o
f
i
n
tere
st
in
c
lu
d
e
s
m
a
c
h
in
e
lea
rn
in
g
a
n
d
d
e
e
p
lea
rn
in
g
.
He
h
a
s m
o
re
th
a
n
2
0
y
e
a
rs o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
k
h
a
n
d
a
g
a
leh
p
@g
m
a
il
.
c
o
m
.
Dr
.
M
a
h
a
v
ir
A.
De
v
m
a
n
e
o
b
t
a
in
e
d
h
is
B
.
E.
(
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
)
in
1
9
9
8
a
n
d
M
.
E.
(
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
)
in
2
0
0
6
f
ro
m
Walc
h
a
n
d
C
o
ll
e
g
e
o
f
En
g
in
e
e
rin
g
S
a
n
g
li
.
He
o
b
tai
n
e
d
h
is
P
h
.
D
.
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
in
2
0
1
6
.
He
is
c
u
rre
n
tl
y
w
o
rk
in
g
a
s
a
P
ro
f
e
ss
o
r
a
n
d
H.O.D.
Co
m
p
u
ter
S
c
ie
n
c
e
a
n
d
E
n
g
in
e
e
rin
g
(A
I
a
n
d
M
L
)
a
t
VPP
CO
E
&
V
A
,
M
u
m
b
a
i.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
d
m
a
h
a
v
ir@g
m
a
il
.
c
o
m
.
M
a
n
g
e
sh
H
a
j
a
r
e
g
ra
d
u
a
ted
f
ro
m
S
h
iv
a
ji
Un
iv
e
rsity
,
In
d
ia,
in
2
0
0
7
.
He
re
c
e
iv
e
d
th
e
M
.
T
e
c
h
.
d
e
g
re
e
f
ro
m
S
h
iv
a
ji
Un
iv
e
rsit
y
,
in
2
0
1
7
,
a
n
d
p
u
rs
u
in
g
P
h
.
D.
d
e
g
re
e
f
ro
m
S
a
v
it
rib
a
i
P
h
u
le
P
u
n
e
Un
iv
e
rsity
,
P
u
n
e
,
I
n
d
ia.
He
is
c
u
rre
n
tl
y
a
s
A
s
sista
n
t
P
ro
f
e
ss
o
r
o
f
Co
m
p
u
ter
En
g
in
e
e
rin
g
w
it
h
th
e
A
rm
y
In
s
ti
tu
te
o
f
T
e
c
h
n
o
lo
g
y
P
u
n
e
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
a
n
g
e
sh
.
h
a
jare
1
9
8
@g
m
a
il
.
c
o
m
.
Dr
.
K
u
ld
e
e
p
B
.
Va
y
a
d
a
n
d
e
is
w
o
rk
in
g
a
s
A
ss
o
c
iate
P
ro
f
e
ss
o
r
in
th
e
De
p
a
rtm
e
n
t
o
f
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
a
t
V
is
h
w
a
k
a
r
m
a
In
stit
u
te
o
f
T
e
c
h
n
o
lo
g
y
,
P
u
n
e
,
I
n
d
ia.
His
re
se
a
rc
h
a
re
a
s
a
re
m
a
c
h
in
e
lea
rn
in
g
,
o
p
ti
m
iz
a
ti
o
n
a
lg
o
rit
h
m
s,
e
m
b
e
d
d
e
d
s
y
ste
m
,
a
n
d
i
n
tern
e
t
o
f
t
h
in
g
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
k
u
ld
e
e
p
.
v
a
y
a
d
a
n
d
e
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.