I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
15
,
No
.
5
,
Octo
b
er
20
25
,
p
p
.
4
9
5
4
~
4
9
6
4
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
15
i
5
.
pp
4
9
5
4
-
4
9
6
4
4954
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Enha
ncing
i
nter
n
et
o
f
t
hing
s
ne
two
rk ef
ficiency
with
clusteri
ng
a
nd rand
o
m fores
t
fusio
n
tech
nique
s
Ahm
ed
G
a
m
a
l So
li
m
a
n So
lim
a
n De
a
bes
1
, H
a
ni At
t
a
r
2
,
3
,
J
a
f
a
r
Aba
bn
eh
4
,
H
a
la
Abd E
l
-
k
a
der
M
a
ns
o
u
r
5
,
M
icha
el
Na
s
ief
5
,
E
s
ra
a
M
.
E
id
5,
6
1
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
C
o
m
mu
n
i
c
a
t
i
o
n
En
g
i
n
e
e
r
i
n
g
,
M
o
d
e
r
n
U
n
i
v
e
r
si
t
y
f
o
r
Te
c
h
n
o
l
o
g
y
a
n
d
I
n
f
o
r
m
a
t
i
o
n
,
C
a
i
r
o
,
Eg
y
p
t
2
F
a
c
u
l
t
y
o
f
En
g
i
n
e
e
r
i
n
g
,
Z
a
r
q
a
U
n
i
v
e
r
si
t
y
,
Z
a
r
q
a
,
J
o
r
d
a
n
3
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
t
y
o
f
B
u
s
i
n
e
ss
a
n
d
Te
c
h
n
o
l
o
g
y
,
Je
d
d
a
h
,
S
a
u
d
i
A
r
a
b
i
a
4
C
y
b
e
r
S
e
c
u
r
i
t
y
D
e
p
a
r
t
m
e
n
t
,
F
a
c
u
l
t
y
o
f
I
n
f
o
r
ma
t
i
o
n
Te
c
h
n
o
l
o
g
y
,
Z
a
r
q
a
U
n
i
v
e
r
si
t
y
,
Za
r
q
a
,
J
o
r
d
a
n
5
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
E
n
g
i
n
e
e
r
i
n
g
a
t
S
h
o
u
b
r
a
,
B
e
n
h
a
U
n
i
v
e
r
si
t
y
,
S
h
o
u
b
r
a
,
E
g
y
p
t
6
F
a
c
u
l
t
y
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
,
B
e
n
h
a
N
a
t
i
o
n
a
l
U
n
i
v
e
r
si
t
y
,
B
e
n
h
a
,
Eg
y
p
t
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Au
g
1
1
,
2
0
2
4
R
ev
is
ed
Ma
r
1
8
,
2
0
2
5
Acc
ep
ted
J
u
n
3
0
,
2
0
2
5
Th
e
in
tern
e
t
o
f
t
h
in
g
s
(Io
T)
is
a
k
e
y
e
lem
e
n
t
o
f
t
h
e
fu
tu
re
i
n
tern
e
t
,
e
n
a
b
li
n
g
th
e
a
c
q
u
isit
i
o
n
a
n
d
tra
n
sfe
r
o
f
d
a
ta
to
imp
r
o
v
e
e
fficie
n
c
y
.
O
n
e
c
h
a
ll
e
n
g
e
in
Io
T
n
e
two
rk
s
is
m
a
n
a
g
i
n
g
t
h
e
e
n
e
rg
y
c
o
n
su
m
p
ti
o
n
o
f
n
o
d
e
s.
I
o
T
i
n
n
o
v
a
ti
o
n
c
o
n
sta
n
tl
y
e
v
o
lv
e
s
d
y
n
a
m
ica
ll
y
,
c
o
n
tri
b
u
t
in
g
sig
n
ifi
c
a
n
tl
y
t
o
s
u
sta
in
a
b
le
c
it
ies
a
n
d
e
c
o
n
o
m
ies
.
C
lu
ste
rin
g
tec
h
n
i
q
u
e
s
c
a
n
h
e
l
p
c
o
n
se
rv
e
e
n
e
rg
y
a
n
d
e
x
ten
d
t
h
e
o
p
e
ra
ti
o
n
a
l
li
fe
sp
a
n
o
f
n
e
two
rk
n
o
d
e
s.
C
lu
ste
r
h
e
a
d
s
(CH)
m
a
n
a
g
e
a
ll
c
lu
ste
r
m
e
m
b
e
r
(CM
)
n
o
d
e
s
with
in
t
h
e
ir
g
ro
u
p
,
e
sta
b
li
sh
in
g
in
tra
-
c
lu
ste
r
a
n
d
i
n
ter
-
c
lu
ste
r
c
o
n
n
e
c
ti
o
n
s.
E
n
h
a
n
c
i
n
g
t
h
e
CH
se
lec
ti
o
n
p
ro
c
e
ss
c
a
n
fu
rt
h
e
r
p
r
o
lo
n
g
th
e
n
e
two
rk
li
fe
sp
a
n
.
Va
rio
u
s
a
lg
o
rit
h
m
s
a
im
to
e
x
ten
d
t
h
e
a
c
ti
v
e
d
u
ra
ti
o
n
o
f
Io
T
n
o
d
e
s
a
n
d
t
h
e
o
v
e
ra
ll
n
e
two
r
k
li
fe
sp
a
n
.
A
c
o
m
p
a
riso
n
o
f
th
e
f
iv
e
a
l
g
o
ri
th
m
s
sh
o
ws
th
a
t
o
n
e
a
lg
o
rit
h
m
is b
e
tt
e
r
th
a
n
t
h
e
o
th
e
rs
i
n
s
o
m
e
c
a
se
s.
Th
is
p
a
p
e
r
d
isc
u
ss
e
s
h
o
w
f
u
sio
n
tec
h
n
iq
u
e
s
u
sin
g
th
e
ra
n
d
o
m
f
o
re
st
(RF
)
a
lg
o
rit
h
m
c
a
n
e
n
h
a
n
c
e
e
n
e
rg
y
e
fficie
n
c
y
i
n
I
o
T
n
e
two
rk
s.
F
i
v
e
a
lg
o
rit
h
m
s
a
re
c
o
m
p
a
re
d
u
si
n
g
RF
,
a
r
o
b
u
st
m
a
c
h
in
e
-
lea
rn
in
g
a
lg
o
rit
h
m
re
n
o
wn
e
d
fo
r
it
s
e
n
se
m
b
le
lea
rn
in
g
c
a
p
a
b
il
it
ies
.
It
se
lec
ts
th
e
b
e
st o
n
e
b
a
se
d
o
n
a
c
ti
v
e
n
o
d
e
s p
e
r
ro
u
n
d
,
re
si
d
u
a
l
e
n
e
rg
y
fo
r
e
a
c
h
ro
u
n
d
,
a
n
d
t
h
e
a
v
e
ra
g
e
e
n
d
-
to
-
e
n
d
d
e
lay
.
K
ey
w
o
r
d
s
:
C
lu
s
ter
h
ea
d
C
lu
s
ter
m
em
b
er
E
n
er
g
y
I
n
ter
n
et
o
f
t
h
in
g
s
R
an
d
o
m
f
o
r
est
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
:
Ah
m
ed
Gam
al
So
lim
an
So
lim
an
Dea
b
es
Dep
ar
tm
en
t o
f
E
lectr
o
n
ics an
d
C
o
m
m
u
n
icatio
n
E
n
g
in
ee
r
i
n
g
,
Facu
lty
o
f
E
n
g
in
ee
r
in
g
,
Mo
d
er
n
Un
iv
er
s
ity
f
o
r
T
ec
h
n
o
lo
g
y
an
d
I
n
f
o
r
m
atio
n
1
6
5
,
E
l
T
h
awr
a
St.,
6
t
h
d
is
tr
ict,
Nasr
C
ity
,
C
air
o
,
E
g
y
p
t
E
m
ail:
ah
m
ed
_
d
ea
b
es2
0
0
9
@
y
ah
o
o
.
c
o
m
1.
I
NT
RO
D
UCT
I
O
N
An
I
n
ter
n
et
-
b
ased
n
etwo
r
k
o
f
p
h
y
s
ical
item
s
o
r
d
ev
ices
th
at
ca
n
in
ter
ac
t
an
d
c
o
m
m
u
n
icate
with
h
u
m
an
s
an
d
ea
ch
o
th
er
is
k
n
o
wn
as
th
e
in
ter
n
et
o
f
th
in
g
s
(
I
o
T
)
[
1
]
.
W
ith
esti
m
ates
in
d
ic
atin
g
th
er
e
will
b
e
o
v
er
2
9
b
illi
o
n
ce
llu
lar
I
o
T
co
n
n
ec
tio
n
s
b
y
2
0
3
0
,
th
e
I
o
T
is
p
r
ed
icted
to
g
r
o
w
s
ig
n
if
ican
tly
[
2
]
.
T
h
e
r
a
p
id
ad
v
an
ce
m
e
n
t
o
f
I
o
T
tech
n
o
l
o
g
y
h
as
led
to
th
e
d
e
v
elo
p
m
e
n
t
o
f
n
u
m
e
r
o
u
s
ap
p
licatio
n
s
th
a
t
h
av
e
th
e
p
o
ten
tial
to
im
p
ac
t
o
u
r
d
aily
life
[
3
]
s
ig
n
if
ican
tly
.
B
y
in
teg
r
atin
g
in
tellig
en
ce
in
to
v
ar
io
u
s
d
o
m
ain
s
,
I
o
T
tech
n
o
lo
g
ies
ar
e
u
s
ed
to
en
h
an
ce
o
u
r
s
u
r
r
o
u
n
d
in
g
s
an
d
cr
ea
te
s
m
ar
t
cities,
b
u
ild
in
g
s
,
ag
r
icu
ltu
r
e,
a
n
d
f
lex
ib
le
en
er
g
y
in
f
r
astru
ctu
r
e
[
4
]
.
Sm
ar
t
ag
r
ic
u
ltu
r
e
is
th
e
s
m
ar
t
way
to
s
w
itch
ir
r
ig
atio
n
s
y
s
tem
s
o
n
an
d
o
f
f
d
ep
e
n
d
in
g
o
n
ac
tu
al
h
u
m
id
ity
s
en
s
o
r
d
ata
b
a
s
ed
o
n
th
e
f
ield
.
T
h
is
au
to
m
ati
c
s
y
s
tem
im
p
r
o
v
es
ir
r
ig
atio
n
a
n
d
allo
ws
f
ar
m
e
r
s
to
m
o
n
ito
r
an
d
m
an
ag
e
o
p
er
a
tio
n
s
r
em
o
tely
.
I
t
also
p
r
o
v
id
es
d
ata
f
o
r
d
ee
p
ev
alu
atio
n
a
n
d
an
aly
s
is
[
5
]
.
I
o
T
h
elp
s
d
ev
ices sh
ar
e
in
f
o
,
s
en
d
an
d
g
et
c
o
m
m
an
d
s
,
an
d
talk
t
o
ea
ch
o
th
er
in
d
ep
e
n
d
en
tly
with
o
u
t h
el
p
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
n
h
a
n
ci
n
g
in
tern
et
o
f t
h
in
g
s
n
etw
o
r
k
efficien
cy
w
i
th
clu
s
teri
n
g
…
(
A
h
med
Ga
ma
l S
o
lima
n
S
o
lima
n
Dea
b
es
)
4955
Hier
ar
ch
ical
r
o
u
tin
g
is
a
p
o
s
s
ib
le
s
o
lu
tio
n
f
o
r
p
r
o
lo
n
g
in
g
th
e
life
o
f
I
o
T
d
ev
ices.
T
h
is
s
y
s
tem
o
r
g
an
izes
th
e
n
o
d
es
in
to
clu
s
ter
s
.
A
lead
er
n
o
d
e
ca
lled
a
clu
s
ter
h
ea
d
s
(
CH
)
m
an
ag
es
th
e
clu
s
ter
.
I
n
t
h
e
n
etwo
r
k
,
as
s
h
o
wn
in
F
ig
u
r
e
1
,
th
e
clu
s
ter
h
ea
d
ac
ts
as
th
e
m
ed
iato
r
b
etwe
en
th
e
n
o
d
es
i
n
th
e
clu
s
ter
a
n
d
t
h
e
p
r
im
ar
y
b
ase
s
tatio
n
,
wh
ich
h
elp
s
m
in
im
ize
th
e
h
o
p
s
an
d
s
av
e
p
o
wer
[
6
]
.
I
t
en
a
b
le
s
n
etwo
r
k
s
ca
lab
ilit
y
,
r
ed
u
ce
s
tr
af
f
ic
,
an
d
im
p
r
o
v
es
p
er
f
o
r
m
an
ce
.
As
a
r
esu
lt,
it
e
n
h
an
ce
s
b
atter
y
life
s
p
an
an
d
i
m
p
r
o
v
es
th
e
o
v
er
all
n
etwo
r
k
d
u
r
atio
n
[
7
]
.
Fig
u
r
e
1
.
T
h
e
o
v
er
v
iew
co
n
tain
s
C
Hs as we
ll a
s
a
b
ase
s
ta
s
i
o
n
(
B
S)
M
u
ltip
le
clu
s
ter
m
em
b
er
(
C
M)
n
o
d
es
ar
e
co
n
n
ec
ted
to
a
s
in
g
le
C
H
n
o
d
e
[
8
]
.
T
h
e
C
M
n
o
d
es
o
p
er
ate
as
r
eg
u
lar
n
o
d
es
with
in
th
e
n
etwo
r
k
,
p
er
f
o
r
m
in
g
v
ar
io
u
s
task
s
ac
co
r
d
in
g
to
th
e
n
etwo
r
k
'
s
p
r
o
to
co
l.
T
h
e
C
H
n
o
d
e
o
v
er
s
ee
s
n
etwo
r
k
m
an
a
g
em
en
t
an
d
c
o
o
r
d
i
n
ates
th
e
ac
t
iv
ities
o
f
C
M
n
o
d
es
[
9
]
.
Gen
e
r
ally
,
th
e
C
H
n
o
d
e
h
as
m
o
r
e
ad
v
a
n
ce
d
ca
p
ab
ilit
ie
s
th
an
th
e
C
M
n
o
d
es
an
d
is
r
e
s
p
o
n
s
ib
le
f
o
r
ad
d
itio
n
al
task
s
s
u
ch
as
m
ain
tain
in
g
clu
s
ter
to
p
o
lo
g
y
a
n
d
r
o
u
tin
g
d
ata
b
etwe
en
C
M
n
o
d
es
[1
0
]
.
T
h
is
r
o
u
tin
g
s
tr
ateg
y
lead
s
t
o
s
ig
n
if
ican
t
e
n
er
g
y
s
av
in
g
s
an
d
s
u
b
s
tan
tially
d
ec
r
ea
s
ed
co
m
m
u
n
icatio
n
s
b
etwe
en
I
o
T
n
o
d
es.
T
h
e
C
H
n
o
d
e
is
r
esp
o
n
s
ib
le
f
o
r
d
ata
tr
an
s
f
er
an
d
co
n
n
ec
tio
n
with
in
a
clu
s
ter
,
ad
ap
tin
g
to
d
y
n
am
ic
n
etwo
r
k
c
o
n
d
itio
n
s
.
Nu
m
er
o
u
s
alg
o
r
ith
m
s
ar
e
d
esig
n
ed
to
en
h
an
ce
I
o
T
n
etwo
r
k
s
'
lo
n
g
ev
ity
an
d
en
er
g
y
ef
f
i
cien
cy
.
I
n
[1
1
]
,
it
f
o
c
u
s
es
o
n
co
m
p
ar
in
g
f
iv
e
alg
o
r
ith
m
s
.
T
h
is
p
ap
er
ai
m
s
to
em
p
lo
y
th
e
r
an
d
o
m
f
o
r
e
s
t
f
u
s
io
n
tech
n
iq
u
e,
a
m
ac
h
in
e
lear
n
i
n
g
alg
o
r
ith
m
,
to
s
elec
t th
e
b
est r
esu
lt v
alu
e
f
o
r
clu
s
ter
in
g
tech
n
iq
u
es.
T
h
e
f
ir
s
t
alg
o
r
ith
m
,
th
e
lo
w
e
n
er
g
y
ad
a
p
tiv
e
clu
s
ter
in
g
h
ier
ar
ch
y
(
L
E
AC
H)
,
u
s
es
clu
s
ter
in
g
to
h
elp
lo
wer
p
o
wer
co
n
s
u
m
p
tio
n
.
B
ased
o
n
clu
s
ter
r
o
tatio
n
,
it
ch
o
o
s
es
a
s
m
all
n
u
m
b
er
o
f
C
Hs,
wh
ich
ad
d
itio
n
al
n
o
d
es
th
en
j
o
in
to
c
r
ea
te
clu
s
ter
s
.
Af
ter
b
ein
g
d
eliv
e
r
ed
t
o
th
e
r
elev
a
n
t
C
H
f
o
r
ag
g
r
e
g
atio
n
,
th
e
d
ata
is
s
u
b
s
eq
u
en
tly
f
o
r
war
d
ed
t
o
th
e
B
S
b
y
t
h
e
C
H
[1
2
]
.
T
h
e
s
ec
o
n
d
alg
o
r
ith
m
is
th
e
g
en
eti
c
alg
o
r
ith
m
(
GA)
,
wh
ich
ev
alu
ates
all
ch
r
o
m
o
s
o
m
es
b
y
ca
lcu
latin
g
a
f
itn
ess
f
u
n
ctio
n
t
h
at
in
clu
d
es
th
r
ee
p
ar
am
eter
s
:
clu
s
ter
d
is
tan
ce
,
th
e
r
o
u
n
d
i
n
wh
ich
t
h
e
last
n
o
d
e
is
d
r
ai
n
ed
o
f
its
en
er
g
y
,
an
d
t
h
e
r
o
u
n
d
in
wh
i
ch
th
e
f
ir
s
t
n
o
d
e
is
also
d
r
ain
ed
o
f
its
en
er
g
y
[1
3
]
.
T
h
e
th
i
r
d
alg
o
r
ith
m
is
th
e
a
r
tific
ial
f
is
h
s
war
m
alg
o
r
ith
m
(
AFSA)
,
wh
ich
is
ch
ar
ac
ter
ized
b
y
th
r
ee
f
u
n
d
a
m
en
tal
co
m
p
o
n
en
ts
:
T
h
er
e
ar
e
t
h
r
ee
m
o
r
e
t
y
p
es
o
f
b
eh
av
io
r
s
,
n
am
ely
,
f
o
llo
win
g
b
eh
av
io
r
,
s
war
m
in
g
b
e
h
av
io
r
,
an
d
s
ea
r
ch
b
eh
av
io
r
.
I
n
a
h
ie
r
ar
ch
al
o
r
g
an
izatio
n
s
tr
u
ctu
r
e
s
u
ch
as
AFSA,
th
e
in
d
iv
id
u
al
f
is
h
im
p
r
o
v
e
th
eir
s
tan
d
in
g
b
y
r
ep
licatin
g
th
e
b
eh
av
io
r
o
f
th
e
o
p
tim
al
f
is
h
.
T
h
is
alg
o
r
ith
m
is
m
ain
ly
u
s
ed
in
I
o
T
n
etwo
r
k
s
to
d
eter
m
in
e
r
eso
u
r
ce
allo
ca
tio
n
,
r
o
u
tin
g
p
r
o
to
co
l
s
elec
tio
n
,
an
d
s
en
s
o
r
n
o
d
e
p
lace
m
en
t
to
en
h
a
n
ce
th
e
ef
f
i
cien
cy
an
d
p
e
r
f
o
r
m
an
ce
o
f
I
o
T
n
etwo
r
k
s
[1
4
]
.
T
h
e
f
o
u
r
th
a
lg
o
r
ith
m
is
e
n
er
g
y
-
ef
f
icien
t r
o
u
tin
g
u
s
in
g
r
ein
f
o
r
ce
m
en
t le
ar
n
in
g
(EER
-
R
L
)
,
wh
ich
allo
ws d
ev
ices to
en
h
a
n
c
e
r
o
u
tin
g
c
h
o
ices b
y
s
h
ar
in
g
lo
ca
lized
d
ata
with
in
th
eir
p
r
o
x
im
ity
.
W
e
ca
n
also
n
o
tice
th
at
th
is
o
p
tim
izatio
n
r
es
u
lts
in
ch
o
o
s
in
g
th
e
m
in
im
u
m
en
er
g
y
lin
k
s
f
o
r
th
e
n
ex
t
h
o
p
s
.
T
h
e
s
en
d
e
r
d
o
es
th
is
b
y
in
clu
d
in
g
lo
ca
l
d
ata
in
th
e
p
ac
k
et
'
s
h
ea
d
er
.
W
h
at
ca
n
b
e
ex
tr
ac
ted
f
r
o
m
t
h
is
f
ield
b
y
an
y
d
ev
ice
n
eig
h
b
o
r
in
g
th
e
p
ac
k
et
co
n
s
is
ts
o
f
d
ev
ice
I
D,
r
em
ain
in
g
en
er
g
y
,
p
o
s
itio
n
c
o
o
r
d
i
n
ate
,
an
d
h
o
p
co
u
n
t.
E
E
R
-
R
L
co
n
s
is
t
s
o
f
th
r
ee
m
ain
p
h
ases
:
Hav
e
b
ee
n
u
s
ed
in
n
etwo
r
k
in
itializatio
n
an
d
cl
u
s
ter
h
ea
d
s
elec
tio
n
,
clu
s
ter
f
o
r
m
atio
n
,
an
d
d
ata
tr
an
s
m
is
s
io
n
[1
5
]
.
T
h
e
f
if
th
alg
o
r
ith
m
is
th
e
m
o
d
if
ie
d
lo
w
en
er
g
y
a
d
ap
tiv
e
clu
s
ter
in
g
h
ier
ar
ch
y
(
MO
DL
E
AC
H)
,
an
e
n
h
an
ce
m
e
n
t
o
f
th
e
ea
r
lier
p
u
b
lis
h
ed
L
E
AC
H
alg
o
r
ith
m
i
n
ten
d
ed
to
r
e
d
u
ce
I
o
T
d
e
v
ice
p
o
wer
co
n
s
u
m
p
tio
n
.
I
t
d
y
n
a
m
ically
ch
o
o
s
es c
lu
s
ter
h
ea
d
s
r
esp
o
n
s
i
b
le
f
o
r
th
e
co
m
m
u
n
icatio
n
wit
h
in
clu
s
ter
s
s
o
th
at
d
ev
ices a
r
e
ev
en
ly
d
is
tr
ib
u
te
d
am
o
n
g
s
t e
n
er
g
y
-
c
o
n
s
u
m
in
g
o
p
er
atio
n
s
[1
6
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
9
5
4
-
4
9
6
4
4956
T
h
e
b
eh
av
io
r
al
p
atter
n
o
f
a
r
an
d
o
m
f
o
r
est
class
if
ier
i
s
s
im
ilar
to
th
at
o
f
d
ec
is
io
n
tr
ee
s
,
b
u
t
s
ev
er
al
d
ec
is
io
n
tr
ee
s
p
o
o
l
th
eir
r
esu
lt
s
in
s
tead
o
f
a
s
in
g
le
d
ec
is
io
n
t
r
ee
m
ak
in
g
a
p
r
ed
ictio
n
.
T
h
e
a
lg
o
r
ith
m
c
o
m
p
u
tes
p
r
ed
ictio
n
s
th
r
o
u
g
h
a
m
ea
n
o
f
av
er
ag
es
to
th
e
n
u
m
b
er
o
f
t
r
ee
s
cr
ea
ted
,
wh
er
e
p
r
ed
ictio
n
ac
cu
r
ac
y
in
c
r
ea
s
es
with
th
e
n
u
m
b
e
r
o
f
t
r
ee
s
cr
ea
ted
.
Un
lik
e
a
s
in
g
le
d
ec
is
io
n
tr
ee
alg
o
r
ith
m
,
a
r
a
n
d
o
m
f
o
r
est
ad
d
r
ess
es
lim
itatio
n
s
s
u
ch
as
o
v
er
f
itti
n
g
,
th
er
eb
y
en
h
an
cin
g
ac
cu
r
ac
y
.
Mo
r
eo
v
er
,
it
r
eq
u
ir
es
m
in
im
al
p
ac
k
ag
e
co
n
f
ig
u
r
atio
n
to
p
r
o
d
u
ce
p
r
ed
i
ctio
n
s
[1
7
]
.
T
h
is
p
ap
er
ai
m
s
to
in
cr
ea
s
e
t
h
e
en
er
g
y
ef
f
icie
n
cy
o
f
I
o
T
n
etwo
r
k
s
b
y
u
s
in
g
f
u
s
io
n
a
p
p
r
o
a
ch
es
b
ased
o
n
th
e
r
an
d
o
m
f
o
r
est
alg
o
r
ith
m
.
Usi
n
g
m
ea
s
u
r
es
lik
e
av
er
a
g
e
en
d
-
to
-
en
d
d
elay
,
r
esid
u
al
en
er
g
y
p
er
r
o
u
n
d
,
an
d
ac
tiv
e
n
o
d
es
ea
ch
r
o
u
n
d
,
r
a
n
d
o
m
f
o
r
est
an
aly
s
es
f
iv
e
alg
o
r
ith
m
s
a
n
d
c
h
o
o
s
es
th
e
b
est
o
n
e
.
T
h
is
p
ap
er
'
s
r
em
ain
in
g
s
ec
tio
n
s
ar
e
o
r
g
an
i
z
ed
as
f
o
llo
ws:
I
n
s
ec
tio
n
2
,
th
e
s
elec
ted
cl
u
s
ter
h
ea
d
m
eth
o
d
alg
o
r
ith
m
s
f
o
r
I
o
T
ar
e
r
ev
ie
wed
to
g
eth
er
with
th
e
p
er
tin
e
n
t
liter
atu
r
e.
T
h
e
d
etails
o
f
th
e
alg
o
r
ith
m
s
u
n
d
e
r
co
m
p
ar
is
o
n
an
d
th
e
f
u
s
io
n
m
e
th
o
d
ar
e
d
escr
ib
e
d
in
s
ec
tio
n
3
.
T
h
e
alg
o
r
ith
m
s
'
s
im
u
latio
n
r
esu
lts
,
p
er
f
o
r
m
an
ce
an
aly
s
is
,
an
d
MA
T
L
AB
im
p
l
em
en
tatio
n
ar
e
s
h
o
wn
in
s
ec
ti
o
n
4
.
I
n
s
ec
tio
n
5
,
th
e
co
n
clu
s
io
n
an
d
n
ex
t
s
tep
s
ar
e
p
r
esen
ted
.
2.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
T
h
e
L
E
AC
H
tech
n
iq
u
e
in
[1
8
]
s
ee
k
s
to
im
p
r
o
v
e
n
etwo
r
k
co
v
er
ag
e
wh
ile
co
n
s
u
m
in
g
less
en
er
g
y
.
C
lu
s
ter
s
h
av
e
d
ev
elo
p
e
d
in
s
id
e
s
ev
er
al
ar
ea
s
o
f
ea
ch
o
f
th
e
n
etwo
r
k
s
.
T
h
e
b
ase
s
tatio
n
d
eter
m
in
es
th
e
d
is
tan
ce
f
r
o
m
th
e
ce
n
ter
an
d
r
esid
u
al
en
er
g
y
f
o
r
ea
ch
r
o
u
n
d
b
ased
o
n
ea
c
h
ac
tiv
e
n
o
d
e'
s
p
o
s
itio
n
an
d
r
em
ain
in
g
e
n
er
g
y
in
ea
c
h
zo
n
e
.
Prio
r
ity
is
g
iv
en
to
ch
o
o
s
in
g
th
e
n
o
d
e
with
th
e
m
o
s
t
s
ig
n
i
f
ican
t
v
alu
e
to
s
er
v
e
as th
e
C
H
f
o
r
th
at
ar
ea
.
Usi
n
g
ev
o
lu
tio
n
ar
y
alg
o
r
ith
m
s
at
th
e
b
ase
s
tatio
n
,
R
ab
ah
e
t
a
l.
[
19
]
c
h
o
s
e
th
e
I
o
T
n
o
d
e
s
f
r
o
m
th
e
g
r
o
u
p
o
f
elig
ib
le
n
o
d
es
an
d
d
esig
n
ated
th
em
as
C
Hs.
T
h
ese
ass
ig
n
ed
C
Hs
ar
e
r
esp
o
n
s
ib
le
f
o
r
co
m
p
ilin
g
in
f
o
r
m
atio
n
f
r
o
m
o
th
e
r
n
o
d
es
an
d
s
en
d
in
g
it
to
th
e
b
ase
s
tatio
n
to
f
i
n
is
h
a
r
o
u
n
d
.
New
clu
s
ter
s
m
ay
f
o
r
m
d
u
e
to
th
e
b
ase
s
tatio
n
r
ee
v
alu
atin
g
th
e
I
o
T
n
o
d
es'
en
er
g
y
lev
els
af
ter
ea
ch
r
o
u
n
d
.
T
o
im
p
r
o
v
e
clu
s
ter
h
ea
d
s
elec
tio
n
in
I
o
T
n
etwo
r
k
s
,
Ou
y
an
g
et
a
l
.
[
20
]
u
s
ed
t
h
e
AFSA
,
wh
ich
s
im
u
lates
th
e
f
o
r
ag
in
g
,
s
ch
o
o
lin
g
,
an
d
f
o
llo
win
g
b
eh
a
v
io
r
s
th
at
f
is
h
n
atu
r
ally
ex
h
ib
it.
E
ac
h
ar
tific
ial
f
is
h
r
ep
r
esen
ts
a
p
o
ten
tial
s
o
lu
tio
n
,
an
d
th
e
alg
o
r
ith
m
im
p
r
o
v
e
s
th
ese
s
o
lu
tio
n
s
iter
ativ
ely
.
T
h
e
f
is
h
s
ea
r
ch
f
o
r
b
etter
p
o
s
itio
n
s
(
p
r
ey
)
,
m
o
v
e
to
war
d
s
th
e
ce
n
te
r
o
f
th
e
s
wa
r
m
if
it
is
ad
v
an
tag
e
o
u
s
(
s
war
m
)
,
o
r
f
o
llo
w
o
th
er
f
is
h
with
s
u
p
er
io
r
p
o
s
itio
n
s
(
f
o
llo
win
g
)
.
A
f
itn
ess
f
u
n
ctio
n
co
n
s
id
er
s
f
ac
to
r
s
lik
e
r
esid
u
al
en
er
g
y
a
n
d
n
o
d
e
p
r
o
x
im
ity
.
R
eg
ilan
an
d
Hem
a
[2
1
]
in
tr
o
d
u
ce
d
en
er
g
y
-
ef
f
icie
n
t r
o
u
tin
g
u
s
in
g
a
r
ein
f
o
r
ce
m
e
n
t le
ar
n
in
g
alg
o
r
ith
m
to
en
h
an
ce
cl
u
s
ter
h
ea
d
s
ele
ctio
n
in
I
o
T
n
etwo
r
k
s
b
y
le
v
er
ag
in
g
r
ein
f
o
r
ce
m
en
t
lear
n
in
g
to
d
y
n
am
ically
allo
ca
te
n
o
d
e
r
o
les
ac
co
r
d
in
g
to
th
eir
e
n
er
g
y
r
eser
v
es
a
n
d
n
etwo
r
k
s
tr
u
ctu
r
e
.
E
ac
h
n
o
d
e'
s
s
tate
is
d
ef
in
ed
b
y
its
r
em
ain
in
g
en
er
g
y
an
d
p
o
s
itio
n
,
an
d
its
ac
tio
n
s
in
v
o
lv
e
t
h
e
s
elec
tio
n
o
f
its
elf
o
r
a
d
jac
en
t
n
o
d
es
as
clu
s
ter
h
ea
d
s
.
W
h
en
I
wen
d
i
et
a
l.
[2
2
]
u
s
ed
th
e
r
an
d
o
m
f
o
r
est
tech
n
iq
u
e
o
n
a
d
ataset
o
f
co
r
o
n
av
ir
u
s
d
is
ea
s
e
(
C
OVI
D
-
19
)
p
atien
ts
,
th
ey
o
b
tain
ed
an
F1
s
co
r
e
o
f
0
.
8
6
6
,
wh
ich
th
e
Ad
aBo
o
s
t
ap
p
r
o
a
ch
th
en
en
h
a
n
ce
d
.
T
h
ey
f
o
u
n
d
th
at
th
e
B
o
o
s
ted
r
an
d
o
m
f
o
r
est
alg
o
r
ith
m
p
r
o
v
id
es
ac
cu
r
ate
p
r
ed
ictio
n
s
ev
en
f
o
r
u
n
b
alan
ce
d
d
ataset
s
.
Acc
o
r
d
in
g
to
th
eir
an
aly
s
is
,
W
u
h
an
lo
ca
ls
h
a
d
m
o
r
e
ex
ce
llen
t
d
ea
th
r
ate
s
th
an
n
o
n
-
n
ativ
es.
Ad
d
itio
n
ally
,
m
ale
p
atien
ts
wer
e
m
o
r
e
lik
ely
to
d
ie
th
an
f
e
m
ale
p
atien
ts
,
an
d
th
e
m
ajo
r
ity
o
f
th
o
s
e
im
p
ac
ted
wer
e
b
etwe
en
th
e
ag
es
o
f
2
0
a
n
d
7
0
.
A
c
c
o
r
d
i
n
g
t
o
W
a
n
g
e
t
a
l
.
[2
3
]
,
c
o
a
s
t
a
l
a
r
e
as
a
r
e
u
n
d
e
r
t
r
e
m
e
n
d
o
u
s
s
t
r
e
s
s
d
u
e
t
o
w
i
d
e
s
p
r
e
a
d
p
o
p
u
l
a
t
i
o
n
m
o
v
e
m
e
n
t
,
l
a
n
d
c
o
n
v
e
r
s
i
o
n
,
a
n
d
e
n
v
i
r
o
n
m
e
n
t
a
l
c
h
a
n
g
e
s
w
o
r
l
d
w
i
d
e
.
B
as
e
d
o
n
t
h
e
a
b
o
v
e
m
e
n
t
i
o
n
e
d
l
i
t
e
r
a
t
u
r
e
a
n
a
l
y
s
is
,
t
h
ei
r
s
t
u
d
y
u
s
e
d
s
e
v
en
r
a
n
d
o
m
f
o
r
e
s
t
-
d
e
r
i
v
e
d
v
a
r
i
ab
l
e
r
a
t
i
n
g
t
e
c
h
n
i
q
u
e
s
.
c
l
ass
i
f
i
ca
t
i
o
n
a
n
d
r
e
g
r
e
s
s
i
o
n
t
r
e
e
s
(
C
AR
T
)
a
n
d
c
o
n
d
i
t
i
o
n
a
l
i
n
f
e
r
e
n
c
e
t
r
e
e
s
(
C
I
T
)
,
t
w
o
d
e
c
is
i
o
n
t
r
e
e
t
y
p
es
,
w
e
r
e
u
s
e
d
i
n
th
e
f
e
a
t
u
r
e
r
e
d
u
c
t
i
o
n
p
r
o
c
e
s
s
es
t
o
s
e
l
e
ct
t
h
e
b
e
s
t
c
l
a
s
s
i
f
ic
a
t
i
o
n
m
o
d
e
l
.
H
o
w
e
v
er
,
t
h
e
m
o
s
t
a
c
c
u
r
a
t
e
a
p
p
r
o
a
c
h
i
s
t
h
e
c
o
n
d
i
t
i
o
n
a
l
p
e
r
m
u
t
a
t
i
o
n
v
a
r
i
a
b
l
e
i
m
p
o
r
t
a
n
c
e
m
e
a
s
u
r
e
(
C
PV
I
M
)
m
e
t
h
o
d
,
w
h
i
c
h
g
e
n
e
r
a
t
e
d
r
e
a
s
o
n
a
b
l
y
s
t
a
b
l
e
a
n
d
r
e
a
l
is
t
ic
f
e
a
t
u
r
e
r
a
n
k
s
f
r
o
m
t
h
e
c
o
r
r
e
l
ate
d
R
S
d
at
a
.
Ad
d
itio
n
ally
,
tim
e
ch
a
r
ac
ter
is
tics
ac
q
u
ir
ed
in
a
s
in
g
le
lea
d
o
f
th
e
elec
tr
o
ca
r
d
io
g
r
am
(
E
C
G
)
s
ig
n
al
wer
e
co
n
s
id
er
ed
b
y
Saen
z
-
C
o
g
o
llo
an
d
Ag
elli
[2
4
]
,
wh
ic
h
i
s
wh
y
th
e
au
th
o
r
s
co
n
ce
n
tr
ate
d
o
n
t
h
e
p
r
o
b
lem
o
f
d
ata
q
u
ality
s
elec
tio
n
o
f
th
es
e
f
ea
tu
r
es.
T
h
ey
ev
al
u
ated
th
e
h
ea
r
tb
ea
t
class
if
icatio
n
p
er
f
o
r
m
an
ce
u
s
in
g
t
h
e
cr
ea
ted
r
an
d
o
m
f
o
r
est
(
R
F)
al
g
o
r
ith
m
,
Ass
o
ciatio
n
f
o
r
th
e
Ad
v
an
ce
m
en
t
o
f
Me
d
ical
I
n
s
t
r
u
m
en
tatio
n
(
AAM
I
)
s
tan
d
ar
d
s
,
an
d
th
e
in
ter
-
p
atien
t
m
eth
o
d
.
N
o
r
m
ali
z
ed
f
ea
tu
r
es
p
r
o
p
o
r
tio
n
al
t
o
th
e
wid
th
o
f
t
h
e
QR
S
co
m
p
lex
'
s
p
r
im
ar
y
wav
e
an
d
R
-
R
in
ter
v
als
wer
e
th
e
cla
s
s
if
icatio
n
ch
a
r
ac
ter
is
tics
w
ith
th
e
m
o
s
t
s
ig
n
if
ican
t
d
is
cr
im
in
an
t
co
ef
f
icien
ts
.
T
h
ey
p
er
f
o
r
m
ed
b
est
u
s
in
g
th
e
4
0
t
r
ee
s
R
F c
las
s
if
ier
an
d
th
e
to
p
s
ix
ch
ar
ac
ter
is
tics
.
T
h
e
ex
ten
s
iv
e
u
s
e
o
f
r
em
o
te
s
en
s
in
g
im
ag
er
y
f
o
r
la
n
d
co
v
er
ca
teg
o
r
i
z
atio
n
an
d
th
e
d
ev
elo
p
m
en
t
o
f
d
if
f
er
en
t
class
if
icatio
n
m
eth
o
d
s
in
th
is
ar
ea
wer
e
em
p
h
asi
z
ed
b
y
Vali
et
a
l.
[2
5
]
.
S
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
n
h
a
n
ci
n
g
in
tern
et
o
f t
h
in
g
s
n
etw
o
r
k
efficien
cy
w
i
th
clu
s
teri
n
g
…
(
A
h
med
Ga
ma
l S
o
lima
n
S
o
lima
n
Dea
b
es
)
4957
(
SVMs)
an
d
r
an
d
o
m
f
o
r
est
s
a
r
e
two
s
u
p
er
v
is
ed
ca
teg
o
r
i
z
atio
n
tech
n
iq
u
es
th
at
h
av
e
r
ec
en
tly
b
ec
o
m
e
p
o
p
u
lar
in
r
em
o
te
s
en
s
in
g
ap
p
licatio
n
s
.
T
h
e
s
tu
d
y
aim
ed
to
ev
alu
a
te
h
o
w
well
th
e
R
F
class
if
ier
an
d
d
ec
is
io
n
tr
ee
p
er
f
o
r
m
ed
co
m
p
ar
ed
t
o
SVMs.
W
ith
a
clas
s
if
icatio
n
ac
cu
r
ac
y
o
f
u
p
to
8
6
%,
th
e
r
an
d
o
m
f
o
r
est
class
if
ier
o
u
tp
er
f
o
r
m
ed
t
h
e
d
ec
is
io
n
t
r
ee
an
d
SVMs
in
m
is
clas
s
i
f
icatio
n
s
itu
atio
n
s
an
d
class
if
icatio
n
p
r
ec
is
io
n
,
ac
co
r
d
in
g
to
p
r
elim
in
ar
y
tan
g
ib
le
r
esear
ch
.
T
h
is
p
ap
er
p
r
esen
ts
s
o
m
e
in
teg
r
atio
n
m
eth
o
d
s
b
ased
o
n
th
e
R
F
alg
o
r
ith
m
th
at
ca
n
h
elp
im
p
r
o
v
e
th
e
en
er
g
y
ef
f
icien
cy
o
f
I
o
T
n
etwo
r
k
s
.
T
h
e
p
ap
er
f
o
cu
s
e
s
o
n
id
en
tify
in
g
th
e
b
est clu
s
ter
h
ea
d
tech
n
iq
u
e,
f
o
llo
wed
b
y
im
p
lem
en
tin
g
a
n
d
t
esti
n
g
th
e
MA
T
L
AB
co
d
e.
3.
E
XP
L
A
NAT
I
O
N
O
F
F
USI
O
N
T
E
CH
N
I
Q
UE
S UT
I
L
I
Z
I
NG
T
H
E
RA
NDO
M
F
O
R
E
ST
AL
G
O
RI
T
H
M
T
h
is
s
ec
tio
n
will
d
escr
ib
e
f
u
s
io
n
m
eth
o
d
s
th
at
u
s
e
th
e
r
ad
io
f
r
eq
u
en
c
y
alg
o
r
ith
m
.
Ma
ch
in
e
lear
n
in
g
ac
h
iev
es
ar
tific
ial
in
tellig
en
ce
as
d
ef
in
e
d
.
Am
o
n
g
th
e
alg
o
r
ith
m
s
is
th
e
r
a
n
d
o
m
f
o
r
est
Alg
o
r
ith
m
,
wh
ich
is
in
cr
ed
ib
ly
s
tr
aig
h
tf
o
r
war
d
b
u
t
ef
f
ec
tiv
e.
T
h
is
is
ess
en
tially
a
v
o
tin
g
tr
ee
class
if
ier
,
in
w
h
ich
th
e
alg
o
r
ith
m
s
elec
ts
th
e
b
est
clas
s
if
icatio
n
t
r
ee
to
d
eter
m
in
e
th
e
f
in
al
class
if
icatio
n
.
I
t
is
cr
u
cial
to
co
m
p
r
eh
en
d
th
e
co
n
ce
p
t
o
f
en
s
em
b
le
lear
n
in
g
b
ef
o
r
e
d
elv
in
g
in
to
th
e
s
p
ec
if
ics
o
f
t
h
e
r
an
d
o
m
f
o
r
est
alg
o
r
ith
m
'
s
p
r
ac
tical
ap
p
licatio
n
with
in
m
ac
h
in
e
lear
n
i
n
g
.
Usi
n
g
m
an
y
m
o
d
els
r
ath
er
th
a
n
a
s
in
g
le
m
o
d
el
im
p
r
o
v
es
p
r
e
d
ictiv
e
p
er
f
o
r
m
an
ce
th
r
o
u
g
h
e
n
s
em
b
le
lear
n
i
n
g
.
S
u
ch
an
ap
p
r
o
ac
h
is
m
o
tiv
ated
b
y
th
e
d
esire
to
u
s
e
th
e
d
iv
e
r
s
ity
o
f
m
o
d
els
in
th
e
en
s
em
b
le
to
en
h
an
c
e
g
e
n
er
a
li
z
atio
n
an
d
p
r
ev
e
n
t
o
v
er
f
itt
in
g
.
T
h
e
two
p
r
im
ar
y
ca
teg
o
r
ies
o
f
en
s
em
b
le
alg
o
r
ith
m
s
ar
e
b
o
o
s
tin
g
a
n
d
b
ag
g
in
g
.
3
.
1
.
B
a
g
g
ing
A
r
an
d
o
m
f
o
r
est
al
g
o
r
ith
m
w
o
r
k
s
with
th
e
h
elp
o
f
b
o
o
ts
tr
ap
p
in
g
,
in
wh
ich
s
ev
er
al
tr
ai
n
i
n
g
s
u
b
s
ets
ar
e
b
u
ilt,
ea
ch
r
an
d
o
m
l
y
ch
o
s
en
f
r
o
m
th
e
o
r
ig
in
al
tr
ain
in
g
s
et
an
d
r
ep
lace
d
.
I
n
Fig
u
r
e
2
,
o
n
e
o
b
s
er
v
es
th
at
s
ev
er
al
m
o
d
els
ar
e
co
n
s
tr
u
ct
ed
s
im
u
ltan
eo
u
s
ly
o
n
d
if
f
er
e
n
t
s
u
b
-
s
am
p
les
o
f
d
ata,
a
u
n
iq
u
e
f
ea
tu
r
e
o
f
th
e
r
an
d
o
m
f
o
r
est
alg
o
r
ith
m
wh
er
e
th
e
f
in
al
p
r
ed
ictio
n
is
m
ad
e
b
ased
o
n
a
m
ajo
r
ity
r
u
le.
As
f
o
r
r
an
d
o
m
f
o
r
est
,
th
e
en
s
em
b
le
m
eth
o
d
i
s
b
ag
g
in
g
o
r
b
o
o
ts
tr
ap
ag
g
r
e
g
atio
n
.
Her
e
is
an
ex
p
lan
atio
n
o
f
th
e
b
a
g
g
in
g
p
r
o
ce
d
u
r
e:
a.
Su
b
s
et
s
elec
tio
n
:
s
p
ec
if
ically
,
r
an
d
o
m
s
am
p
lin
g
o
f
co
m
p
lete
d
ata
is
tak
en
.
b.
B
o
o
ts
tr
ap
s
am
p
lin
g
:
t
h
ese
s
u
b
s
ets
,
r
ef
er
r
ed
to
as
B
o
o
ts
tr
ap
s
am
p
les
,
ar
e
u
s
ed
to
tr
ain
th
e
m
o
d
els.
T
h
e
s
am
p
les ar
e
r
em
o
v
e
d
f
r
o
m
th
e
o
r
ig
in
al
d
ata
u
s
in
g
r
o
w
s
am
p
l
in
g
with
r
ep
lace
m
e
n
t.
c.
B
o
o
ts
tr
ap
p
in
g
:
t
h
is
p
h
ase
m
ea
n
s
th
e
r
o
w
s
am
p
lin
g
with
r
ep
lace
m
e
n
t
.
T
h
e
p
h
r
ase
r
e
f
er
s
to
th
e
r
o
w
s
am
p
lin
g
with
r
ep
lace
m
e
n
t.
d.
I
n
d
ep
e
n
d
en
t
m
o
d
el
tr
ain
in
g
:
e
ac
h
m
o
d
el
is
tr
ain
ed
s
ep
ar
ately
o
n
its
B
o
o
ts
tr
ap
s
am
p
le,
s
o
t
h
e
o
u
tco
m
es
o
f
th
e
m
o
d
els ar
e
d
if
f
er
en
t.
e.
Ma
jo
r
ity
v
o
tin
g
:
t
h
e
m
o
s
t
o
f
te
n
p
r
o
jecte
d
o
u
tco
m
e
f
r
o
m
ea
c
h
m
o
d
el
is
s
elec
ted
,
an
d
all
m
o
d
el
r
esu
lts
ar
e
co
m
b
in
ed
to
d
eter
m
i
n
e
th
e
f
i
n
al
f
o
r
ec
ast.
f.
Ag
g
r
eg
atio
n
:
b
ased
o
n
a
m
ajo
r
ity
v
o
te,
th
is
last
s
tag
e
i
n
teg
r
a
tes
all
th
e
r
esu
lts
to
cr
ea
te
th
e
f
in
al
p
r
o
d
u
ct.
Fig
u
r
e
2.
T
h
e
p
r
o
ce
s
s
o
f
b
o
o
ts
tr
ap
ag
g
r
eg
atio
n
3.
2
.
B
o
o
s
t
ing
A
m
ac
h
in
e
lear
n
in
g
a
p
p
r
o
ac
h
ca
lled
"b
o
o
s
tin
g
"
tu
r
n
s
m
u
ltip
le
wea
k
lear
n
er
s
in
to
one
p
o
wer
f
u
l
lear
n
er
,
in
cr
ea
s
in
g
m
o
d
el
ac
cu
r
ac
y
.
I
n
Fig
u
r
e
3
,
b
o
o
s
tin
g
m
o
d
els
ar
e
tr
ain
ed
in
d
ep
en
d
e
n
tly
an
d
s
eq
u
en
tially
.
T
h
e
b
o
o
s
tin
g
alg
o
r
ith
m
f
o
llo
w
s
th
ese
s
tep
s
:
a.
I
n
itialize
weig
h
ts
:
g
iv
e
ev
er
y
tr
ain
in
g
ex
a
m
p
le
th
e
s
am
e
in
iti
al
weig
h
t.
b.
T
r
a
i
n
a
we
a
k
l
e
a
r
n
e
r
:
t
r
ai
n
a
w
e
a
k
l
e
a
r
n
e
r
u
s
i
n
g
t
h
e
w
ei
g
h
te
d
t
r
a
i
n
i
n
g
d
a
ta
,
s
u
c
h
a
s
a
d
e
ci
s
i
o
n
t
r
e
e
wi
t
h
a
f
e
w
l
e
v
e
ls
.
A
w
e
a
k
l
e
a
r
n
e
r
is
a
s
t
r
a
i
g
h
t
f
o
r
w
a
r
d
m
o
d
e
l
t
h
a
t
p
e
r
f
o
r
m
s
m
a
r
g
i
n
a
l
l
y
b
e
tt
e
r
t
h
a
n
r
an
d
o
m
g
u
e
s
s
i
n
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
9
5
4
-
4
9
6
4
4958
c.
C
alcu
late
er
r
o
r
:
e
v
alu
ate
t
h
e
wea
k
lear
n
er
'
s
er
r
o
r
o
n
th
e
t
r
ain
in
g
s
et,
co
n
s
id
er
in
g
th
e
w
eig
h
ted
s
u
m
o
f
m
is
class
if
ied
in
s
tan
ce
s
.
d.
Up
d
ate
weig
h
ts
:
m
o
d
if
y
th
e
weig
h
ts
ac
co
r
d
in
g
to
th
e
m
is
tak
e
r
ate,
g
iv
in
g
in
co
r
r
ec
tly
class
if
ied
ex
am
p
les
a
h
ig
h
er
weig
h
t a
n
d
co
r
r
ec
tly
ca
teg
o
r
i
z
ed
o
n
es a
lo
wer
weig
h
t.
e.
R
ep
ea
t step
s
2
-
4
m
u
ltip
le
tim
e
s
,
tr
ain
in
g
a
n
ew
wea
k
lear
n
er
in
ea
ch
iter
atio
n
with
t
h
e
u
p
d
a
ted
weig
h
ts
.
f.
C
o
m
b
in
e
wea
k
lear
n
er
s
:
a
ll
w
ea
k
lear
n
er
s
tr
ai
n
ed
in
th
e
ea
r
lier
p
h
ases
m
ak
e
u
p
th
e
f
in
al
m
o
d
el.
B
ased
o
n
th
eir
ac
cu
r
ac
y
,
ea
ch
wea
k
lear
n
er
is
g
iv
en
a
weig
h
t,
an
d
th
e
weig
h
t
f
o
r
ec
asts
o
f
all
w
ea
k
lear
n
er
s
ar
e
co
m
b
in
ed
to
cr
ea
te
th
e
f
in
al
p
r
ed
ictio
n
.
g.
Pre
d
ict:
u
s
e
th
e
co
m
p
leted
m
o
d
el
to
p
r
e
d
ict
class
lab
els f
o
r
n
ew
in
s
tan
ce
s
.
Fig
u
r
e
3
.
T
h
e
p
r
o
ce
s
s
o
f
b
o
o
s
tin
g
3.
3
.
R
a
nd
o
m
f
o
rset
a
lg
o
rit
h
m
Du
r
in
g
tr
ai
n
in
g
,
th
e
r
a
n
d
o
m
f
o
r
est
alg
o
r
ith
m
cr
ea
tes
s
ev
e
r
al
d
ec
is
io
n
tr
ee
s
.
Fr
o
m
th
es
e
tr
ee
s
,
it
d
eter
m
in
es
th
e
m
ea
n
p
r
ed
ictio
n
(
f
o
r
r
eg
r
ess
io
n
)
o
r
th
e
m
o
d
e
o
f
t
h
e
class
es
(
f
o
r
class
if
icatio
n
)
.
I
t
b
u
ild
s
a
n
en
s
em
b
le
o
f
tr
ee
s
u
s
in
g
a
m
e
th
o
d
ca
lled
b
a
g
g
in
g
(
b
o
o
ts
tr
ap
ag
g
r
e
g
atin
g
)
.
A
r
an
d
o
m
p
o
r
tio
n
o
f
th
e
tr
ain
i
n
g
d
ata
an
d
a
r
an
d
o
m
s
u
b
s
et
o
f
th
e
ch
a
r
ac
ter
is
tics
ar
e
u
s
ed
to
tr
ain
ea
ch
tr
ee
.
T
h
e
t
r
ee
s
'
d
iv
er
s
ity
an
d
r
an
d
o
m
i
z
atio
n
r
ed
u
ce
o
v
er
f
itti
n
g
an
d
im
p
r
o
v
e
th
e
m
o
d
el'
s
ca
p
ac
ity
f
o
r
g
e
n
er
ali
z
atio
n
.
E
a
ch
tr
ee
in
d
iv
id
u
ally
ass
ig
n
s
a
cla
s
s
lab
el
d
u
r
in
g
th
e
p
r
ed
ictio
n
p
h
ase,
an
d
th
e
class
wi
th
th
e
m
o
s
t v
o
tes (
m
o
d
e)
is
u
s
ed
to
m
ak
e
th
e
f
in
al
p
r
e
d
ictio
n
.
T
h
e
r
an
d
o
m
f
o
r
est
class
if
ier
co
m
p
r
is
es
a
g
r
o
u
p
o
f
class
if
ier
s
with
a
tr
ee
to
p
o
l
o
g
y
.
T
h
e
r
an
d
o
m
v
ec
to
r
u
s
ed
to
cr
ea
te
ea
ch
tr
ee
is
s
ep
ar
ately
d
is
tr
ib
u
ted
f
r
o
m
ea
r
lier
r
a
n
d
o
m
v
e
cto
r
s
with
th
e
s
am
e
d
is
tr
ib
u
tio
n
.
W
h
en
g
iv
en
an
i
n
p
u
t
x
,
th
e
tr
ee
s
ca
s
t
th
eir
v
o
tes
f
o
r
th
e
m
o
s
t
p
o
p
u
lar
class
.
T
wo
p
a
r
am
eter
s
,
ac
cu
r
ac
y
an
d
th
e
i
n
ter
d
ep
e
n
d
en
ce
o
f
in
d
iv
id
u
al
class
if
ier
s
—
ar
e
u
s
ed
to
d
eter
m
i
n
e
an
u
p
p
er
b
o
u
n
d
f
o
r
th
e
g
en
er
ali
z
atio
n
er
r
o
r
o
f
r
a
n
d
o
m
f
o
r
ests
.
Fig
u
r
e
4
s
h
o
ws th
e
r
a
n
d
o
m
f
o
r
est
alg
o
r
ith
m
'
s
f
lo
wch
ar
t.
Fig
u
r
e
4
.
R
an
d
o
m
f
o
r
est f
lo
w
ch
ar
t
T
o
p
r
o
d
u
ce
a
m
o
r
e
r
eliab
le
an
d
ac
cu
r
ate
m
o
d
el,
e
n
s
em
b
le
tech
n
iq
u
es
in
m
ac
h
in
e
lear
n
in
g
ag
g
r
eg
ate
p
r
ed
ictio
n
s
f
r
o
m
s
ev
er
al
m
o
d
els.
T
h
e
f
u
n
d
a
m
en
tal
i
d
ea
is
t
o
im
p
r
o
v
e
th
e
o
v
e
r
all
ac
cu
r
ac
y
an
d
r
esil
ien
ce
o
f
th
e
f
o
r
ec
ast
b
y
co
m
b
in
in
g
th
e
p
r
ed
ictio
n
s
o
f
d
if
f
er
e
n
t
m
o
d
e
ls
to
elim
in
ate
er
r
o
r
s
.
F
ig
u
r
e
5
s
h
o
ws
th
e
r
an
d
o
m
f
o
r
est
alg
o
r
ith
m
in
ac
tio
n
.
Dec
is
io
n
tr
ee
s
an
d
en
s
em
b
le
lear
n
in
g
ar
e
u
s
ed
in
th
e
r
an
d
o
m
f
o
r
est
alg
o
r
ith
m
.
T
h
e
s
tep
s
ca
n
b
e
u
s
ed
to
d
escr
ib
e
h
o
w
it wo
r
k
s
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
n
h
a
n
ci
n
g
in
tern
et
o
f t
h
in
g
s
n
etw
o
r
k
efficien
cy
w
i
th
clu
s
teri
n
g
…
(
A
h
med
Ga
ma
l S
o
lima
n
S
o
lima
n
Dea
b
es
)
4959
Step
1
: Ch
o
o
s
e
s
am
p
les at
r
an
d
o
m
f
r
o
m
th
e
d
ataset
o
r
tr
ain
i
n
g
s
et.
Step
2
: Cre
ate
a
d
ec
is
io
n
tr
ee
f
o
r
ev
er
y
s
am
p
le
th
at
was c
h
o
s
en
.
Step
3
: U
s
e
a
v
o
tin
g
p
r
o
ce
d
u
r
e
b
y
av
e
r
ag
in
g
th
e
d
ec
is
io
n
s
o
f
ea
ch
d
ec
is
io
n
tr
ee
.
Step
4
: Ch
o
o
s
e
th
e
p
r
e
d
ictio
n
with
th
e
h
ig
h
est n
u
m
b
er
o
f
v
o
tes as th
e
f
in
al
p
r
ed
ictio
n
.
R
an
d
o
m
f
o
r
est
cr
ea
tes
m
u
ltip
le
tr
ain
in
g
s
ets
to
en
h
an
ce
th
e
d
iv
er
s
ity
am
o
n
g
class
if
icatio
n
m
o
d
els
an
d
,
th
u
s
,
th
e
e
x
tr
ap
o
lativ
e
p
r
ed
ictiv
e
ca
p
ab
ilit
y
o
f
th
e
co
m
b
in
ed
m
o
d
el
s
.
Af
ter
k
tr
ain
i
n
g
iter
atio
n
s
,
a
s
et
o
f
class
if
icatio
n
m
o
d
els
{
ℎ
1
(
)
,
ℎ
2
(
)
,
…
.
.
,
ℎ
(
)
is
o
b
tain
ed
.
A
s
im
p
le
m
ajo
r
ity
v
o
tin
g
p
r
o
ce
d
u
r
e
d
ec
id
es
t
h
e
s
y
s
tem
'
s
u
ltima
te
clas
s
if
icatio
n
o
u
tco
m
e.
T
h
e
d
ec
is
io
n
f
o
r
m
u
la
is
p
r
esen
ted
in
(
1
)
.
(
)
=
∑
(
ℎ
(
)
=
)
=
1
(
1
)
wh
er
e
is
th
e
o
u
tp
u
t
v
ar
ia
b
le
(
i.e
.
,
class
if
icatio
n
lab
el)
,
is
th
e
in
d
icato
r
f
u
n
ctio
n
,
is
th
e
r
an
d
o
m
f
o
r
est
m
o
d
el,
is
th
e
test
s
am
p
le,
an
d
ℎ
is
a
s
in
g
le
d
ec
is
io
n
tr
ee
.
Fig
u
r
e
5
.
T
h
e
r
an
d
o
m
f
o
r
est al
g
o
r
ith
m
'
s
o
p
er
atio
n
4.
P
E
RF
O
RM
A
NCE
E
VA
L
U
AT
I
O
N
T
h
e
r
a
n
d
o
m
f
o
r
est
alg
o
r
ith
m
s
im
u
latio
n
r
esu
lts
f
o
r
f
u
s
io
n
t
ec
h
n
iq
u
es
a
r
e
s
h
o
w
n
in
th
is
s
ec
tio
n
.
T
h
e
n
u
m
b
er
o
f
liv
e
n
o
d
es,
laten
c
y
,
an
d
r
esid
u
al
en
er
g
y
wer
e
th
e
t
h
r
ee
m
ain
r
esu
lts
o
f
th
e
ex
p
e
r
im
en
t.
T
h
e
s
im
u
latio
n
en
v
ir
o
n
m
e
n
t
is
d
escr
ib
ed
in
t
h
e
f
ir
s
t
s
ec
tio
n
,
an
d
th
en
th
e
s
im
u
latio
n
r
es
u
lts
ar
e
th
o
r
o
u
g
h
ly
d
is
cu
s
s
ed
.
4
.
1
.
S
im
ula
t
i
o
n e
nv
iro
nm
en
t
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
f
u
s
io
n
tech
n
iq
u
es
u
tili
zin
g
th
e
r
an
d
o
m
f
o
r
est
alg
o
r
ith
m
is
ass
ess
ed
an
d
ev
alu
ated
u
s
in
g
th
e
MA
T
L
AB
s
im
u
lato
r
.
T
h
e
k
ey
p
ar
am
eter
s
f
o
r
t
h
e
e
v
alu
atio
n
ar
e
p
r
esen
ted
in
T
ab
le
1
.
T
h
e
ex
p
er
im
en
t
in
v
o
lv
es
f
o
u
r
v
a
r
iab
les:
th
e
n
u
m
b
er
o
f
n
o
d
es,
in
itial
en
er
g
y
,
n
u
m
b
e
r
o
f
clu
s
ter
s
,
an
d
n
etwo
r
k
r
ad
iu
s
,
with
o
n
e
v
a
r
iab
le
c
h
an
g
ed
wh
ile
th
e
o
th
e
r
s
r
em
ain
ed
c
o
n
s
tan
t.
A
co
m
p
r
eh
e
n
s
iv
e
s
et
o
f
s
ix
ty
ex
p
er
im
en
ts
was
co
n
d
u
cted
,
p
r
o
d
u
cin
g
th
r
ee
o
u
tp
u
ts
f
o
r
e
ac
h
ex
p
er
im
en
t:
th
e
n
u
m
b
er
o
f
liv
e
n
o
d
es,
d
elay
,
an
d
r
esid
u
al
en
er
g
y
.
T
h
e
s
im
u
latio
n
s
wer
e
p
er
f
o
r
m
ed
o
v
er
9
0
0
r
o
u
n
d
s
,
with
th
e
B
S
lo
ca
ted
at
th
e
ce
n
ter
o
f
th
e
g
r
i
d
.
T
h
e
p
ac
k
et
s
ize
is
s
et
at
1
0
2
4
b
y
tes
to
m
atch
th
e
f
a
s
ter
tr
an
s
m
is
s
io
n
r
ate
o
f
I
o
T
n
o
d
es.
T
h
e
n
etwo
r
k
is
co
n
f
ig
u
r
e
d
in
a
cir
c
u
lar
lay
o
u
t
with
r
a
d
ii
r
an
g
in
g
f
r
o
m
2
0
0
m
to
6
0
0
m
,
c
o
m
p
r
is
in
g
1
0
0
to
5
0
0
I
o
T
n
o
d
es.
I
n
itial e
n
er
g
y
le
v
els (
E
o
)
r
a
n
g
e
f
r
o
m
0
.
5
J
to
2
.
5
J
.
T
h
e
n
u
m
b
er
o
f
cl
u
s
ter
s
(
No
=
p
×
n
)
,
wh
er
e
n
r
ep
r
esen
ts
th
e
n
u
m
b
er
o
f
n
o
d
es
an
d
p
is
s
et
b
etwe
en
0
.
0
3
to
0
.
0
7
,
r
e
p
r
ese
n
tin
g
a
p
er
ce
n
tag
e
o
f
th
e
to
ta
l
n
etwo
r
k
n
o
d
es
in
u
s
e.
T
ab
le
2
will p
r
esen
t sp
ec
i
f
icatio
n
s
f
o
r
f
o
u
r
ca
s
es selecte
d
f
r
o
m
th
e
s
ix
ty
ex
p
er
im
en
ts
.
T
ab
le
1
.
Simu
latio
n
c
o
n
f
i
g
u
r
at
io
n
P
a
r
a
me
t
e
r
s
V
a
l
u
e
s
S
i
z
e
o
f
a
d
a
t
a
p
a
c
k
e
t
1
0
2
4
b
y
t
e
1
0
/
/
2
5
0
n
J
/
b
i
t
0
.
0
0
1
3
/
/
4
5
n
J/
b
/
m
e
ssa
g
e
D
i
st
a
n
c
e
t
h
r
e
s
h
o
l
d
(
)
√
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
9
5
4
-
4
9
6
4
4960
T
ab
le
2
.
Pre
s
en
ts
s
p
ec
if
icatio
n
s
f
o
r
f
o
u
r
ca
s
es
C
a
ses
R
a
d
i
u
s
N
o
.
o
f
N
o
d
e
s
Eo
p
1
4
0
0
m
3
0
0
Eo
=
0
.
5
J
0
.
0
5
2
5
0
0
m
3
0
0
Eo
=
1
J
0
.
0
5
3
5
0
0
m
3
0
0
Eo
=
1
.
5
J
0
.
0
3
4
5
0
0
m
4
0
0
Eo
=
0
.
5
J
0
.
0
5
4
.
2
.
E
x
perim
ent
a
l
r
esu
lt
s
T
h
e
m
etr
ics
ar
e
ex
p
lain
ed
i
n
t
h
e
f
o
llo
win
g
s
ec
tio
n
s
:
r
e
m
ain
i
n
g
en
e
r
g
y
is
th
e
a
m
o
u
n
t
o
f
en
er
g
y
i
n
th
e
n
etwo
r
k
af
ter
o
n
e
s
er
v
in
g
,
lif
etim
e
is
th
e
am
o
u
n
t
o
f
tim
e
th
e
n
etwo
r
k
s
tay
s
ac
tiv
e
af
te
r
o
n
e
s
er
v
in
g
,
liv
e
n
o
d
es
ar
e
t
h
e
n
u
m
b
er
o
f
n
o
d
e
s
th
at
ar
e
cu
r
r
en
tly
ac
tiv
e
in
t
h
e
n
etwo
r
k
,
an
d
d
ela
y
is
th
e
av
er
ag
e
e
n
d
-
to
-
en
d
laten
cy
f
o
r
o
n
e
s
er
v
in
g
.
4
.
2
.
1.
Aliv
e
no
des
Fig
u
r
es
6
,
7
,
8
,
an
d
9
s
h
o
w
t
h
e
n
u
m
b
e
r
o
f
ac
tiv
e
s
en
s
o
r
n
o
d
es
ev
er
y
r
o
u
n
d
f
o
r
f
o
u
r
cir
cu
m
s
tan
ce
s
.
T
h
ese
f
ig
u
r
es
r
ev
ea
l
th
at
wh
ile
th
e
AFSA
alg
o
r
ith
m
s
h
o
wca
s
es
s
u
p
er
io
r
e
n
er
g
y
ef
f
icien
cy
,
th
e
GA
alg
o
r
ith
m
s
u
r
p
ass
es
it
in
s
p
ec
if
ic
co
n
te
x
ts
.
C
o
n
v
er
s
ely
,
th
e
L
E
AC
H,
E
E
R
-
R
L
,
an
d
MO
DL
E
AC
H
alg
o
r
ith
m
s
ex
h
ib
it
h
ig
h
er
en
er
g
y
c
o
n
s
u
m
p
tio
n
.
Sp
ec
if
ically
,
th
e
last
n
o
d
e
in
th
e
AFSA
alg
o
r
ith
m
d
ies
af
ter
9
0
0
r
o
u
n
d
s
,
co
m
p
ar
ed
to
8
0
0
r
o
u
n
d
s
in
th
e
GA
al
g
o
r
ith
m
.
Me
an
w
h
ile,
th
e
p
r
ev
i
o
u
s
n
o
d
es
in
th
e
E
E
R
-
R
L
an
d
MO
DL
E
AC
H
alg
o
r
ith
m
s
d
ie
af
ter
7
0
0
r
o
u
n
d
s
,
a
n
d
t
h
e
L
E
AC
H
alg
o
r
ith
m
'
s
last
n
o
d
e
d
i
es
af
ter
6
0
0
r
o
u
n
d
s
.
Fu
s
io
n
tech
n
iq
u
es a
r
e
e
m
p
lo
y
ed
u
s
in
g
th
e
r
an
d
o
m
f
o
r
est
alg
o
r
ith
m
to
d
eter
m
in
e
th
e
o
p
tim
u
m
alg
o
r
ith
m
.
Fig
u
r
e
6
.
s
h
o
ws h
o
w
m
an
y
n
o
d
es r
em
ain
v
iab
le
f
o
r
f
u
s
io
n
tech
n
i
q
u
es in
th
e
f
ir
s
t
ca
s
e
Fig
u
r
e
7
.
s
h
o
ws h
o
w
m
an
y
n
o
d
es r
em
ain
v
iab
le
f
o
r
f
u
s
io
n
tech
n
i
q
u
es in
th
e
s
ec
o
n
d
ca
s
e
Fig
u
r
e
8
.
s
h
o
ws th
e
n
u
m
b
er
o
f
n
o
d
es a
liv
e
f
o
r
f
u
s
io
n
tech
n
iq
u
es in
th
e
t
h
ir
d
ca
s
e
Fig
u
r
e
9
.
s
h
o
ws th
e
n
u
m
b
er
o
f
n
o
d
es a
liv
e
f
o
r
f
u
s
io
n
tech
n
iq
u
es in
th
e
f
o
u
r
th
ca
s
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
n
h
a
n
ci
n
g
in
tern
et
o
f t
h
in
g
s
n
etw
o
r
k
efficien
cy
w
i
th
clu
s
teri
n
g
…
(
A
h
med
Ga
ma
l S
o
lima
n
S
o
lima
n
Dea
b
es
)
4961
4
.
2
.
2.
R
esid
ua
l e
nerg
y
Fig
u
r
es
1
0
,
1
1
,
1
2
,
an
d
1
3
d
is
p
lay
th
e
to
tal
r
em
ai
n
in
g
e
n
er
g
y
p
er
r
o
u
n
d
ac
r
o
s
s
f
o
u
r
s
ce
n
ar
io
s
.
Alth
o
u
g
h
t
h
e
AFSA
alg
o
r
ith
m
is
ty
p
ically
m
o
r
e
en
e
r
g
y
-
ef
f
icien
t,
th
e
GA
alg
o
r
ith
m
o
u
t
p
er
f
o
r
m
s
it
in
ce
r
tain
in
s
tan
ce
s
.
Fu
s
io
n
tech
n
iq
u
es
a
r
e
u
tili
ze
d
with
th
e
r
an
d
o
m
f
o
r
est
alg
o
r
ith
m
to
id
en
tify
th
e
o
p
tim
al
alg
o
r
ith
m
.
T
h
e
g
o
al
o
f
ch
o
o
s
in
g
C
lu
s
ter
Hea
d
s
is
to
im
p
r
o
v
e
p
er
f
o
r
m
an
ce
b
y
co
n
s
id
er
i
n
g
v
a
r
iab
les
lik
e
d
is
tan
ce
,
r
esid
u
al
en
er
g
y
,
I
o
T
n
o
d
e
d
eg
r
ee
,
an
d
clu
s
ter
u
n
if
o
r
m
ity
.
I
n
co
n
tr
ast,
th
e
L
E
AC
H,
E
E
R
-
R
L
,
an
d
MO
DL
E
AC
H
alg
o
r
ith
m
s
co
n
s
u
m
e
s
u
b
s
tan
tial
en
er
g
y
d
u
r
in
g
o
p
e
r
atio
n
,
r
esu
ltin
g
i
n
th
e
least
r
em
ain
in
g
en
er
g
y
a
f
ter
9
0
0
r
o
u
n
d
s
.
Fig
u
r
e
1
0
.
S
h
o
ws th
e
to
tal
en
e
r
g
y
lef
t
o
v
er
f
o
r
f
u
s
io
n
m
eth
o
d
s
in
th
e
f
ir
s
t
ca
s
e
Fig
u
r
e
1
1
.
S
h
o
ws th
e
to
tal
en
e
r
g
y
lef
t
o
v
er
f
o
r
f
u
s
io
n
m
eth
o
d
s
in
th
e
s
ec
o
n
d
ca
s
e
Fig
u
r
e
1
2
.
S
h
o
ws th
e
to
tal
en
e
r
g
y
lef
t
o
v
er
f
o
r
f
u
s
io
n
m
eth
o
d
s
in
th
e
t
h
ir
d
ca
s
e
Fig
u
r
e
1
3
.
S
h
o
ws th
e
to
tal
en
e
r
g
y
lef
t
o
v
er
f
o
r
f
u
s
io
n
m
eth
o
d
s
in
th
e
f
o
u
r
th
ca
s
e
4
.
2
.
3.
D
ela
y
T
r
an
s
m
is
s
io
n
d
elay
is
u
s
ed
to
ev
alu
ate
n
etwo
r
k
p
er
f
o
r
m
a
n
c
e.
Fig
u
r
es
1
4
,
1
5
,
1
6
,
an
d
1
7
co
m
p
a
r
e
f
iv
e
alg
o
r
ith
m
s
b
ased
o
n
av
er
ag
e
en
d
-
to
-
en
d
laten
cy
.
Alt
h
o
u
g
h
th
e
AFSA
alg
o
r
ith
m
g
en
er
ally
p
er
f
o
r
m
s
b
etter
,
th
e
GA
alg
o
r
ith
m
ex
c
els
in
s
p
ec
if
ic
s
ce
n
ar
io
s
.
Fu
s
io
n
tech
n
i
q
u
es,
im
p
lem
e
n
ted
t
h
r
o
u
g
h
th
e
r
an
d
o
m
f
o
r
est
alg
o
r
ith
m
,
ar
e
u
s
ed
to
i
d
en
tify
th
e
m
o
s
t
ef
f
ec
tiv
e
alg
o
r
ith
m
.
T
h
e
alg
o
r
it
h
m
in
tr
o
d
u
ce
s
a
d
elay
d
u
e
t
o
th
e
r
e
-
s
elec
tio
n
o
f
o
p
tim
al
C
l
u
s
ter
Hea
d
n
o
d
es
b
ased
o
n
s
p
ec
if
ic
cr
iter
ia.
Ho
wev
er
,
s
ig
n
if
ican
t
p
er
f
o
r
m
an
ce
d
if
f
er
en
ce
s
ar
e
o
b
s
er
v
e
d
am
o
n
g
th
e
L
E
AC
H,
E
E
R
-
R
L
,
an
d
MO
DL
E
AC
H
alg
o
r
ith
m
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
9
5
4
-
4
9
6
4
4962
Fig
u
r
e
14
.
Dela
y
v
s
.
r
o
u
n
d
s
f
o
r
f
u
s
io
n
tech
n
iq
u
es in
th
e
f
ir
s
t c
ase
Fig
u
r
e
15
.
Dela
y
v
s
.
r
o
u
n
d
s
f
o
r
f
u
s
io
n
tech
n
iq
u
es in
th
e
s
ec
o
n
d
ca
s
e
5.
CO
NCLU
SI
O
N
AND
F
U
T
U
RE
WO
RK
S
T
h
e
I
o
T
is
a
p
iv
o
tal
elem
en
t
o
f
th
e
f
u
tu
r
e
i
n
ter
n
et,
en
a
b
lin
g
ef
f
icien
t
d
ata
co
llectio
n
an
d
tr
an
s
f
er
.
Ho
wev
er
,
e
n
er
g
y
co
n
s
u
m
p
tio
n
in
I
o
T
n
etwo
r
k
s
p
o
s
es
a
s
ig
n
if
ican
t
ch
allen
g
e.
I
n
n
o
v
atio
n
s
in
I
o
T
ar
e
r
ap
id
l
y
ad
v
an
cin
g
,
p
ar
ticu
lar
ly
in
o
p
ti
m
izin
g
en
e
r
g
y
u
s
ag
e
an
d
ex
te
n
d
in
g
n
etwo
r
k
life
s
p
an
.
C
lu
s
ter
in
g
is
ess
en
tial
f
o
r
r
ed
u
cin
g
p
o
wer
co
n
s
u
m
p
tio
n
,
en
h
an
cin
g
d
ata
ac
cu
r
ac
y
,
an
d
p
r
o
lo
n
g
in
g
n
etwo
r
k
lo
n
g
ev
ity
wh
en
g
ath
er
in
g
I
o
T
d
ata
.
I
o
T
n
o
d
es
ar
e
g
r
o
u
p
ed
in
t
o
clu
s
ter
s
u
s
in
g
th
is
te
ch
n
iq
u
e,
an
d
co
m
m
u
n
icatio
n
with
in
an
d
b
etwe
en
clu
s
ter
s
is
m
ad
e
ea
s
ier
b
y
C
H
o
v
er
s
ee
in
g
C
M.
Ma
n
y
alg
o
r
ith
m
s
s
ee
k
to
ex
ten
d
b
atter
y
life
,
b
o
o
s
t
n
etwo
r
k
lo
n
g
ev
ity
,
a
n
d
in
cr
ea
s
e
th
e
n
u
m
b
er
o
f
ac
tiv
e
n
o
d
es.
T
h
es
e
alg
o
r
ith
m
s
em
p
lo
y
o
p
tim
iz
atio
n
an
d
clu
s
ter
in
g
tech
n
iq
u
es
to
en
h
a
n
ce
p
e
r
f
o
r
m
an
ce
an
d
en
e
r
g
y
ef
f
icien
c
y
.
T
h
e
AFSA
alg
o
r
ith
m
h
as
p
r
o
v
en
t
o
b
e
th
e
m
o
s
t
ef
f
icien
t,
th
o
u
g
h
th
e
GA
alg
o
r
ith
m
e
x
ce
ls
in
s
p
ec
if
ic
s
ce
n
ar
io
s
.
Fu
s
io
n
tech
n
iq
u
es
ar
e
ap
p
lied
u
s
in
g
th
e
r
an
d
o
m
f
o
r
est
alg
o
r
ith
m
to
d
e
ter
m
in
e
th
e
m
o
s
t
ef
f
icien
t
a
p
p
r
o
ac
h
.
Fu
tu
r
e
wo
r
k
in
I
o
T
en
e
r
g
y
ef
f
icien
cy
an
d
n
etwo
r
k
lo
n
g
ev
ity
will
f
o
cu
s
o
n
d
ev
elo
p
in
g
d
y
n
am
ic
cl
u
s
ter
in
g
tech
n
iq
u
es
th
at
ca
n
ad
ap
t
to
ch
an
g
in
g
n
etwo
r
k
co
n
d
itio
n
s
in
r
ea
l
-
tim
e.
T
h
is
co
u
ld
f
u
r
th
e
r
o
p
ti
m
ize
en
er
g
y
u
s
ag
e
an
d
d
ata
ag
g
r
eg
atio
n
in
I
o
T
n
etwo
r
k
s
,
im
p
r
o
v
in
g
o
v
e
r
all
p
er
f
o
r
m
an
ce
a
n
d
ef
f
icien
c
y
.
Ad
d
itio
n
ally
,
in
teg
r
atin
g
en
er
g
y
h
ar
v
esti
n
g
tech
n
o
lo
g
ies
co
u
ld
b
e
e
x
p
lo
r
ed
to
s
u
p
p
lem
en
t
o
r
r
ep
lace
b
atter
y
p
o
wer
in
I
o
T
d
e
v
ices,
ex
ten
d
in
g
th
ei
r
o
p
er
atio
n
al
life
s
p
an
an
d
r
ed
u
c
in
g
en
v
ir
o
n
m
e
n
tal
im
p
ac
t.
RE
F
E
R
E
NC
E
S
[
1
]
A
.
A
.
L
a
g
h
a
r
i
,
K
.
W
u
,
R
.
A
.
L
a
g
h
a
r
i
,
M
.
A
l
i
,
a
n
d
A
.
A
.
K
h
a
n
,
“
A
r
e
v
i
e
w
a
n
d
st
a
t
e
o
f
a
r
t
o
f
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
(
I
o
T)
,
”
Ar
c
h
i
v
e
s
o
f
C
o
m
p
u
t
a
t
i
o
n
a
l
Me
t
h
o
d
s i
n
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
2
9
,
n
o
.
3
,
p
p
.
1
3
9
5
–
1
4
1
3
,
M
a
y
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
1
8
3
1
-
0
2
1
-
0
9
6
2
2
-
6.
[
2
]
S
t
a
t
i
st
a
,
“
S
t
a
t
i
st
i
c
_
I
d
1
1
8
3
4
5
7
_
N
u
m
b
e
r
-
of
-
I
o
t
-
C
o
n
n
e
c
t
e
d
-
D
e
v
i
c
e
s
-
W
o
r
l
d
w
i
d
e
-
2
0
1
9
-
2
0
2
3
-
W
i
t
h
-
F
o
r
e
c
a
s
t
s
-
To
-
2
0
3
0
.
”
2
0
2
4
.
[
3
]
S
.
K
u
mar,
P
.
Ti
w
a
r
i
,
a
n
d
M
.
Z
y
m
b
l
e
r
,
“
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s
i
s
a
r
e
v
o
l
u
t
i
o
n
a
r
y
a
p
p
r
o
a
c
h
f
o
r
f
u
t
u
r
e
t
e
c
h
n
o
l
o
g
y
e
n
h
a
n
c
e
m
e
n
t
:
a
r
e
v
i
e
w
,
”
J
o
u
r
n
a
l
o
f
B
i
g
D
a
t
a
,
v
o
l
.
6
,
n
o
.
1
,
p
.
1
1
1
,
D
e
c
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
8
6
/
s4
0
5
3
7
-
019
-
0
2
6
8
-
2.
[
4
]
S
.
P
o
l
y
me
n
i
,
D
.
N
.
S
k
o
u
t
a
s,
G
.
K
o
r
men
t
z
a
s,
a
n
d
C
.
S
k
i
a
n
i
s,
“
F
I
N
D
EA
S
:
a
f
i
n
t
e
c
h
-
b
a
s
e
d
a
p
p
r
o
a
c
h
o
n
d
e
s
i
g
n
i
n
g
a
n
d
a
ssess
i
n
g
I
o
T
sy
st
e
ms,
”
I
EE
E
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s J
o
u
r
n
a
l
,
v
o
l
.
9
,
n
o
.
2
4
,
p
p
.
2
5
1
9
6
–
2
5
2
0
6
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
JI
O
T.
2
0
2
2
.
3
1
9
5
7
7
0
.
[
5
]
H
.
A
t
t
a
r
,
R
.
M
.
B
a
h
y
,
A
.
K
h
a
l
i
f
e
h
,
M
.
H
a
f
e
z
,
a
n
d
A
.
S
o
l
y
m
a
n
,
“
H
a
r
n
e
s
si
n
g
t
h
e
p
o
w
e
r
o
f
I
o
T:
a
s
u
r
v
e
y
o
f
I
n
t
e
r
n
e
t
o
f
T
h
i
n
g
s
a
p
p
l
i
c
a
t
i
o
n
s
i
n
g
r
e
e
n
h
o
u
se
a
g
r
i
c
u
l
t
u
r
e
,
”
i
n
2
0
2
4
I
E
EE
3
0
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
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
s
(
I
C
T
)
,
I
EEE,
J
u
n
.
2
0
2
4
,
p
p
.
1
–
7
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
T
6
2
7
6
0
.
2
0
2
4
.
1
0
6
0
6
1
3
1
.
[
6
]
P
.
G
.
P
S
S
a
n
d
N
.
L
a
v
a
n
y
a
,
“
I
n
v
e
st
i
g
a
t
i
o
n
o
f
R
F
-
b
a
se
d
n
e
t
w
o
r
k
i
n
g
f
o
r
u
n
d
e
r
w
a
t
e
r
w
i
r
e
l
e
ss
se
n
s
o
r
n
e
t
w
o
r
k
s
u
s
i
n
g
d
y
n
a
m
i
c
c
l
u
st
e
r
h
e
a
d
se
l
e
c
t
i
o
n
st
r
a
t
e
g
y
,
”
i
n
2
0
2
3
1
1
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
S
y
m
p
o
si
u
m
o
n
El
e
c
t
r
o
n
i
c
S
y
s
t
e
m
s
D
e
v
i
c
e
s
a
n
d
C
o
m
p
u
t
i
n
g
(
E
S
D
C
)
,
2
0
2
3
,
p
p
.
1
–
5.
[
7
]
R
.
R
a
m
k
u
mar
a
n
d
C
.
B
a
l
a
su
b
r
a
m
a
n
i
a
n
,
“
A
n
o
v
e
l
c
l
u
s
t
e
r
h
e
a
d
se
l
e
c
t
i
o
n
s
c
h
e
me
b
a
se
d
o
n
B
C
O
f
o
r
I
n
t
e
r
n
e
t
o
f
Th
i
n
g
s,
”
i
n
2
0
2
3
T
h
i
r
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
A
d
v
a
n
c
e
s
i
n
El
e
c
t
ri
c
a
l
,
C
o
m
p
u
t
i
n
g
,
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
S
u
s
t
a
i
n
a
b
l
e
T
e
c
h
n
o
l
o
g
i
e
s
(
I
C
AE
C
T
)
,
I
EEE,
Jan
.
2
0
2
3
,
p
p
.
1
–
6
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
EC
T
5
7
5
7
0
.
2
0
2
3
.
1
0
1
1
8
0
3
1
.
[
8
]
R
.
L
V
a
n
d
R
.
S
o
u
n
d
a
r
K
,
“
A
n
a
d
v
a
n
c
e
me
n
t
i
n
e
n
e
r
g
y
e
f
f
i
c
i
e
n
t
c
l
u
st
e
r
i
n
g
a
l
g
o
r
i
t
h
m
u
s
i
n
g
c
l
u
st
e
r
c
o
o
r
d
i
n
a
t
o
r
-
b
a
se
d
C
H
e
l
e
c
t
i
o
n
mec
h
a
n
i
sm
(
C
C
C
H
)
,
”
M
e
a
s
u
r
e
m
e
n
t
:
S
e
n
so
rs
,
v
o
l
.
2
5
,
p
.
1
0
0
6
2
3
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
mea
se
n
.
2
0
2
2
.
1
0
0
6
2
3
.
[
9
]
A
.
S
o
l
i
m
a
n
S
o
l
i
ma
n
D
e
a
b
e
s
,
M
.
M
i
k
h
e
a
l
,
E
.
I
b
r
a
h
e
e
m
E
i
d
,
a
n
d
H
.
M
o
h
a
med
,
“
S
t
u
d
y
o
f
c
l
u
s
t
e
r
i
n
g
t
e
c
h
n
i
q
u
e
a
l
g
o
r
i
t
h
ms
i
n
I
o
T
n
e
t
w
o
r
k
s,”
E
n
g
i
n
e
e
r
i
n
g
Re
s
e
a
r
c
h
J
o
u
rn
a
l
(
S
h
o
u
b
r
a
)
,
v
o
l
.
5
2
,
n
o
.
4
,
p
p
.
6
3
–
7
1
,
O
c
t
.
2
0
2
3
,
d
o
i
:
1
0
.
2
1
6
0
8
/
e
r
j
sh
.
2
0
2
3
.
2
1
2
4
1
1
.
1
1
7
1
.
[1
0
]
K
.
S
a
a
d
a
t
,
N
.
W
a
n
g
,
a
n
d
R
.
Ta
f
a
z
o
l
l
i
,
“
A
I
-
e
n
a
b
l
e
d
b
l
o
c
k
c
h
a
i
n
c
o
n
s
e
n
su
s
n
o
d
e
s
e
l
e
c
t
i
o
n
i
n
c
l
u
st
e
r
-
b
a
s
e
d
v
e
h
i
c
u
l
a
r
n
e
t
w
o
r
k
s,”
I
EEE
N
e
t
w
o
rki
n
g
L
e
t
t
e
rs
,
v
o
l
.
5
,
n
o
.
2
,
p
p
.
1
1
5
–
1
1
9
,
Ju
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
LN
ET
.
2
0
2
3
.
3
2
3
8
9
6
4
.
[1
1
]
A
.
G
.
S
.
S
.
D
e
a
b
e
s,
E.
M
.
E
i
d
,
H
.
A
.
E.
M
a
n
s
o
u
r
,
a
n
d
M
.
N
a
si
e
f
,
“
C
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
si
s
o
f
e
n
e
r
g
y
-
e
f
f
i
c
i
e
n
t
c
l
u
s
t
e
r
i
n
g
a
l
g
o
r
i
t
h
ms
f
o
r
I
o
T
n
e
t
w
o
r
k
s,”
A
p
p
l
i
e
d
Ma
t
h
e
m
a
t
i
c
s
&
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
1
8
,
n
o
.
3
,
p
p
.
5
2
1
–
5
3
0
,
M
a
y
2
0
2
4
,
d
o
i
:
1
0
.
1
8
5
7
6
/
a
mi
s/
1
8
0
3
0
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
E
n
h
a
n
ci
n
g
in
tern
et
o
f t
h
in
g
s
n
etw
o
r
k
efficien
cy
w
i
th
clu
s
teri
n
g
…
(
A
h
med
Ga
ma
l S
o
lima
n
S
o
lima
n
Dea
b
es
)
4963
[1
2
]
A
.
T.
A
b
u
-
Jass
a
r
,
H
.
A
t
t
a
r
,
A
.
A
mer
,
V
.
L
y
a
s
h
e
n
k
o
,
V
.
Y
e
v
s
i
e
i
e
v
,
a
n
d
A
.
S
o
l
y
ma
n
,
“
R
e
m
o
t
e
m
o
n
i
t
o
r
i
n
g
s
y
st
e
m
o
f
p
a
t
i
e
n
t
s
t
a
t
u
s
i
n
s
o
c
i
a
l
I
o
T
e
n
v
i
r
o
n
m
e
n
t
s
u
si
n
g
a
maz
o
n
w
e
b
s
e
r
v
i
c
e
s
t
e
c
h
n
o
l
o
g
i
e
s
a
n
d
smar
t
h
e
a
l
t
h
c
a
r
e
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
C
r
o
w
d
S
c
i
e
n
c
e
,
v
o
l
.
9
,
n
o
.
2
,
p
p
.
1
1
0
–
1
2
5
,
M
a
y
2
0
2
5
,
d
o
i
:
1
0
.
2
6
5
9
9
/
I
JC
S
.
2
0
2
3
.
9
1
0
0
0
1
9
.
[1
3
]
G
.
P
a
p
a
z
o
g
l
o
u
a
n
d
P
.
B
i
s
k
a
s
,
“
R
e
v
i
e
w
a
n
d
c
o
m
p
a
r
i
so
n
o
f
g
e
n
e
t
i
c
a
l
g
o
r
i
t
h
m a
n
d
p
a
r
t
i
c
l
e
sw
a
r
m
o
p
t
i
mi
z
a
t
i
o
n
i
n
t
h
e
o
p
t
i
m
a
l
p
o
w
e
r
f
l
o
w
p
r
o
b
l
e
m,
”
E
n
e
r
g
i
e
s
,
v
o
l
.
1
6
,
n
o
.
3
,
p
.
1
1
5
2
,
Ja
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
6
0
3
1
1
5
2
.
[1
4
]
M
.
S
a
d
r
i
s
h
o
j
a
e
i
,
N
.
J
a
f
a
r
i
N
a
v
i
m
i
p
o
u
r
,
M
.
R
e
s
h
a
d
i
,
M
.
H
o
s
s
e
i
n
z
a
d
e
h
,
a
n
d
M
.
U
n
a
l
,
“
A
n
e
n
e
r
g
y
-
a
w
a
r
e
c
l
u
s
t
e
r
i
n
g
m
e
t
h
o
d
i
n
t
h
e
I
o
T
u
si
n
g
a
s
w
a
r
m
-
b
a
s
e
d
a
l
g
o
r
i
t
h
m
,
”
W
i
re
l
e
s
s
N
e
t
w
o
rk
s
,
v
o
l
.
2
8
,
n
o
.
1
,
p
p
.
1
2
5
–
1
3
6
,
J
a
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
2
7
6
-
021
-
02804
-
x.
[1
5
]
H
.
A
t
t
a
r
,
R
.
K
h
o
sr
a
v
i
,
J.
A
b
a
b
n
e
h
,
A
.
A
mer,
a
n
d
A
.
S
o
l
y
m
a
n
,
“
A
m
o
d
i
f
i
e
d
g
r
i
d
s
e
a
r
c
h
-
b
a
se
d
o
p
t
i
mi
z
a
t
i
o
n
f
o
r
p
o
ssi
b
l
y
r
e
p
e
t
i
t
i
v
e
g
l
o
b
a
l
e
x
t
r
e
m
u
m
w
i
t
h
a
n
a
p
p
l
i
c
a
t
i
o
n
t
o
e
d
g
e
i
n
t
e
l
l
i
g
e
n
c
e
i
n
I
I
o
T
t
o
w
a
r
d
s
t
i
me
-
d
o
ma
i
n
s
i
g
n
a
l
s,
”
Wi
r
e
l
e
ss N
e
t
w
o
r
k
s
,
v
o
l
.
3
0
,
n
o
.
8
,
p
p
.
7
0
1
5
–
7
0
2
7
,
2
0
2
4
.
[1
6
]
K
.
R
a
g
h
a
v
a
R
a
o
,
B
.
N
a
r
e
s
h
K
u
mar
R
e
d
d
y
,
a
n
d
A
.
S
.
K
u
mar,
“
U
si
n
g
a
d
v
a
n
c
e
d
d
i
st
r
i
b
u
t
e
d
e
n
e
r
g
y
e
f
f
i
c
i
e
n
t
c
l
u
st
e
r
i
n
g
i
n
c
r
e
a
si
n
g
t
h
e
n
e
t
w
o
r
k
l
i
f
e
t
i
me
i
n
w
i
r
e
l
e
ss
se
n
so
r
n
e
t
w
o
r
k
s,
”
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
2
7
,
n
o
.
2
0
,
p
p
.
1
5
2
6
9
–
1
5
2
8
0
,
O
c
t
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
0
0
-
0
2
3
-
0
7
9
4
0
-
4.
[1
7
]
M
.
R
.
A
l
i
,
S
.
M
.
A
.
N
i
p
u
,
a
n
d
S
.
A
.
K
h
a
n
,
“
A
d
e
c
i
s
i
o
n
s
u
p
p
o
r
t
s
y
st
e
m
f
o
r
c
l
a
ss
i
f
y
i
n
g
s
u
p
p
l
i
e
r
s
e
l
e
c
t
i
o
n
c
r
i
t
e
r
i
a
u
s
i
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
r
a
n
d
o
m
f
o
r
e
st
a
p
p
r
o
a
c
h
,
”
D
e
c
i
s
i
o
n
An
a
l
y
t
i
c
s
J
o
u
r
n
a
l
,
v
o
l
.
7
,
p
.
1
0
0
2
3
8
,
J
u
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
a
j
o
u
r
.
2
0
2
3
.
1
0
0
2
3
8
.
[1
8
]
K
.
R
e
z
a
e
e
e
t
a
l
.
,
“
I
o
M
T
-
a
ss
i
st
e
d
me
d
i
c
a
l
v
e
h
i
c
l
e
r
o
u
t
i
n
g
b
a
s
e
d
o
n
U
A
V
-
b
o
r
n
e
h
u
m
a
n
c
r
o
w
d
se
n
s
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
i
n
sm
a
r
t
c
i
t
i
e
s
,
”
I
E
EE
I
n
t
e
rn
e
t
o
f
T
h
i
n
g
s J
o
u
rn
a
l
,
v
o
l
.
1
0
,
n
o
.
2
1
,
p
p
.
1
8
5
2
9
–
1
8
5
3
6
,
N
o
v
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
JI
O
T.
2
0
2
3
.
3
2
8
4
0
5
6
.
[
19
]
S
.
R
a
b
a
h
,
A
.
B
.
Za
i
e
r
,
a
n
d
H
.
D
a
h
m
a
n
,
“
N
e
w
e
n
e
r
g
y
e
f
f
i
c
i
e
n
t
c
l
u
st
e
r
i
n
g
met
h
o
d
b
a
s
e
d
o
n
f
u
z
z
y
l
o
g
i
c
a
n
d
g
e
n
e
t
i
c
a
l
g
o
r
i
t
h
m
i
n
I
o
T
n
e
t
w
o
r
k
,
”
i
n
2
0
2
0
1
7
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
M
u
l
t
i
-
C
o
n
f
e
re
n
c
e
o
n
S
y
st
e
m
s,
S
i
g
n
a
l
s
&
D
e
v
i
c
e
s
(
S
S
D
)
,
I
EEE,
J
u
l
.
2
0
2
0
,
p
p
.
2
9
–
3
3
.
d
o
i
:
1
0
.
1
1
0
9
/
S
S
D
4
9
3
6
6
.
2
0
2
0
.
9
3
6
4
2
1
1
.
[2
0
]
M
.
O
u
y
a
n
g
,
J.
X
i
,
W
.
B
a
i
,
a
n
d
K
.
L
i
,
“
B
a
n
d
-
a
r
e
a
a
p
p
l
i
c
a
t
i
o
n
c
o
n
t
a
i
n
e
r
a
n
d
a
r
t
i
f
i
c
i
a
l
f
i
s
h
sw
a
r
m
a
l
g
o
r
i
t
h
m
f
o
r
mu
l
t
i
-
o
b
j
e
c
t
i
v
e
o
p
t
i
m
i
z
a
t
i
o
n
i
n
I
n
t
e
r
n
e
t
-
of
-
Th
i
n
g
s
c
l
o
u
d
,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
1
6
4
0
8
–
1
6
4
2
3
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
1
5
0
3
2
6
.
[2
1
]
S
.
R
e
g
i
l
a
n
a
n
d
L.
K
.
H
e
m
a
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
b
a
s
e
d
l
o
w
r
e
d
u
n
d
a
n
c
y
p
r
e
d
i
c
t
i
o
n
mo
d
e
l
f
o
r
I
o
T
-
e
n
a
b
l
e
d
w
i
r
e
l
e
ss
sen
s
o
r
n
e
t
w
o
r
k
,
”
S
N
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
4
,
n
o
.
5
,
p
.
5
4
5
,
J
u
l
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s4
2
9
7
9
-
0
2
3
-
0
1
8
9
8
-
8.
[2
2
]
C
.
I
w
e
n
d
i
e
t
a
l
.
,
“
C
O
V
I
D
-
1
9
p
a
t
i
e
n
t
h
e
a
l
t
h
p
r
e
d
i
c
t
i
o
n
u
si
n
g
b
o
o
s
t
e
d
r
a
n
d
o
m
f
o
r
e
s
t
a
l
g
o
r
i
t
h
m,”
Fr
o
n
t
i
e
rs
i
n
P
u
b
l
i
c
H
e
a
l
t
h
,
v
o
l
.
8
,
p
.
3
5
7
,
J
u
l
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
u
b
h
.
2
0
2
0
.
0
0
3
5
7
.
[2
3
]
Y
.
W
a
n
g
e
t
a
l
.
,
“
R
e
md
e
si
v
i
r
i
n
a
d
u
l
t
s
w
i
t
h
se
v
e
r
e
C
O
V
I
D
-
1
9
:
a
r
a
n
d
o
mi
se
d
,
d
o
u
b
l
e
-
b
l
i
n
d
,
p
l
a
c
e
b
o
-
c
o
n
t
r
o
l
l
e
d
,
mu
l
t
i
c
e
n
t
r
e
t
r
i
a
l
,
”
T
h
e
L
a
n
c
e
t
,
v
o
l
.
3
9
5
,
n
o
.
1
0
2
3
6
,
p
p
.
1
5
6
9
–
1
5
7
8
,
M
a
y
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
S
0
1
4
0
-
6
7
3
6
(
2
0
)
3
1
0
2
2
-
9.
[2
4
]
J.
F
.
S
a
e
n
z
-
C
o
g
o
l
l
o
a
n
d
M
.
A
g
e
l
l
i
,
“
I
n
v
e
st
i
g
a
t
i
n
g
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
a
n
d
r
a
n
d
o
m
f
o
r
e
st
s
f
o
r
i
n
t
e
r
-
p
a
t
i
e
n
t
h
e
a
r
t
b
e
a
t
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
Al
g
o
r
i
t
h
m
s
,
v
o
l
.
1
3
,
n
o
.
4
,
p
.
7
5
,
M
a
r
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
a
1
3
0
4
0
0
7
5
.
[2
5
]
A
.
V
a
l
i
,
S
.
C
o
ma
i
,
a
n
d
M
.
M
a
t
t
e
u
c
c
i
,
“
D
e
e
p
l
e
a
r
n
i
n
g
f
o
r
l
a
n
d
u
s
e
a
n
d
l
a
n
d
c
o
v
e
r
c
l
a
ssi
f
i
c
a
t
i
o
n
b
a
se
d
o
n
h
y
p
e
r
s
p
e
c
t
r
a
l
a
n
d
mu
l
t
i
s
p
e
c
t
r
a
l
e
a
r
t
h
o
b
ser
v
a
t
i
o
n
d
a
t
a
:
a
r
e
v
i
e
w
,
”
R
e
m
o
t
e
S
e
n
s
i
n
g
,
v
o
l
.
1
2
,
n
o
.
1
5
,
p
.
2
4
9
5
,
A
u
g
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
r
s1
2
1
5
2
4
9
5
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ahm
e
d
G
a
m
a
l
S
o
li
m
a
n
S
o
li
m
a
n
De
a
b
e
s
is
a
tea
c
h
i
n
g
a
ss
istan
t
a
t
th
e
M
o
d
e
rn
Un
iv
e
rsity
fo
r
Tec
h
n
o
lo
g
y
a
n
d
I
n
fo
rm
a
ti
o
n
(M
TI)
.
He
re
c
e
iv
e
d
h
is
M
.
S
c
.
fr
o
m
Be
n
h
a
Un
i
v
e
rsity
in
2
0
1
9
,
h
is
B.
S
c
.
fr
o
m
th
e
M
o
d
e
rn
Un
iv
e
rsity
fo
r
tec
h
n
o
l
o
g
y
a
n
d
in
fo
rm
a
ti
o
n
(
M
TI)
in
2
0
1
3
,
a
n
d
fro
m
th
e
Un
i
v
e
rsity
o
f
Wale
s,
U.K.,
i
n
2
0
1
4
.
He
wo
r
k
s
p
a
rt
-
ti
m
e
a
s
a
tea
c
h
in
g
a
ss
istan
t
a
t
th
e
Am
e
rica
n
Un
iv
e
rsity
in
Ca
iro
(A
UC).
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
th
e
i
n
tern
e
t
o
f
th
in
g
s
,
m
a
c
h
in
e
lea
rn
in
g
,
a
n
d
e
m
b
e
d
d
e
d
sy
ste
m
s
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
h
m
e
d
_
d
e
a
b
e
s2
0
0
9
@
y
a
h
o
o
.
c
o
m
.
H
a
n
i
Atta
r
re
c
e
iv
e
d
h
is
P
h
.
D.
fro
m
t
h
e
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ic
En
g
i
n
e
e
rin
g
,
Un
i
v
e
rsity
o
f
S
trath
c
ly
d
e
,
Un
it
e
d
Ki
n
g
d
o
m
i
n
2
0
1
1
.
S
in
c
e
2
0
1
1
,
h
e
h
a
s b
e
e
n
w
o
rk
i
n
g
a
s
a
re
se
a
rc
h
e
r
in
e
lec
tri
c
a
l
e
n
g
in
e
e
rin
g
a
n
d
e
n
e
rg
y
sy
ste
m
s.
Dr
Attar
is
n
o
w
a
u
n
i
v
e
rsity
lec
tu
re
r
a
t
Zarq
a
U
n
iv
e
rsit
y
,
Jo
r
d
a
n
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
re
n
e
wa
b
le
e
n
e
rg
y
s
y
ste
m
s,
e
fficie
n
t
c
o
m
p
u
ti
n
g
a
n
d
d
e
sig
n
,
c
y
b
e
r
-
p
h
y
sic
a
l
sy
ste
m
s,
a
n
d
wire
les
s
c
o
m
m
u
n
ica
ti
o
n
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
h
a
tt
a
r@z
u
.
e
d
u
.
jo
.
J
a
f
a
r
Aba
b
n
e
h
re
c
e
iv
e
d
a
B.
S
c
.
d
e
g
re
e
in
tele
c
o
m
m
u
n
ica
ti
o
n
e
n
g
i
n
e
e
rin
g
in
1
9
9
1
,
a
n
M
.
S
c
.
d
e
g
re
e
i
n
2
0
0
5
,
a
n
d
t
h
e
P
h
.
D.
d
e
g
re
e
in
2
0
0
9
.
He
is
a
n
a
ss
o
c
iate
p
ro
fe
ss
o
r
.
In
2
0
0
9
,
h
e
jo
in
e
d
WI
S
E
U
n
iv
e
rsit
y
a
s
t
h
e
He
a
d
o
f
Co
m
p
u
ter
I
n
fo
rm
a
t
io
n
a
n
d
Ne
two
rk
S
y
ste
m
s
in
in
fo
rm
a
ti
o
n
tec
h
n
o
l
o
g
y
(I
T)
ti
ll
2
/2
0
2
2
.
He
wa
s
th
e
d
e
a
n
o
f
th
e
IT
F
a
c
u
lt
y
a
t
WI
S
E
U
n
iv
e
rsit
y
fro
m
Au
g
u
st
2
0
1
5
to
No
v
e
m
b
e
r
2
0
2
0
;
in
2
0
2
2
,
h
e
jo
in
e
d
Ab
d
u
l
Az
iz
Al
G
h
u
ra
ir
S
c
h
o
o
l
o
f
Ad
v
a
n
c
e
d
Co
m
p
u
ti
n
g
(A
S
AC),
LUM
INU
S
Tec
h
n
ica
l
Un
i
v
e
rsity
Co
l
leg
e
(LT
UC).
He
h
a
s
p
u
b
li
sh
e
d
m
a
n
y
re
se
a
rc
h
p
a
p
e
rs,
b
o
o
k
c
h
a
p
ters
,
a
n
d
b
o
o
k
s
i
n
in
t
e
rn
a
ti
o
n
a
l
re
fe
rre
d
j
o
u
r
n
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
c
o
n
g
e
sti
o
n
a
n
d
n
e
two
rk
p
e
rfo
rm
a
n
c
e
,
wire
les
s
a
n
d
m
o
b
il
e
n
e
two
r
k
s,
e
n
c
r
y
p
ti
o
n
a
n
d
in
fo
rm
a
ti
o
n
se
c
u
rit
y
,
wire
les
s
se
n
so
r
n
e
two
r
k
s
(W
S
Ns
),
a
rti
ficia
l
in
telli
g
e
n
c
e
,
d
a
ta
m
in
in
g
a
n
d
re
tr
iev
in
g
in
fo
rm
a
ti
o
n
,
c
l
o
u
d
c
o
m
p
u
ti
n
g
,
a
n
d
E
-
lea
rn
i
n
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
jafa
r.
a
b
a
b
n
e
h
@w
ise
.
e
d
u
.
jo
.
Evaluation Warning : The document was created with Spire.PDF for Python.