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.
14
,
No
.
2
,
J
u
ly
20
25
,
p
p
.
507
~
5
1
7
I
SS
N:
2089
-
4864
,
DOI
:
1
0
.
1
1
5
9
1
/i
j
r
es
.
v
14
.
i
2
.
pp
5
0
7
-
517
507
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
r
es.ia
esco
r
e.
co
m
Enha
nced f
a
ul
t
d
etec
tion
in
pho
tov
o
ltaic sy
ste
m
s
usi
ng
an
ense
m
ble
m
a
chi
n
e learning
appro
a
ch
M
o
ha
m
m
e
d Sa
la
h Ib
ra
hi
m
1
,
H
us
s
ein K
.
Al
m
u
lla
2
,
Ana
s
D.
Sa
llib
i
3
,
Ah
m
ed
Adi
l N
a
f
ea
1
,
Ay
t
he
m
K
ha
iri
K
a
re
e
m
4
,
K
ha
t
t
a
b
M
.
Ali A
lheet
i
5
1
D
e
p
a
r
t
me
n
t
o
f
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
C
o
l
l
e
g
e
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
a
n
d
I
n
f
o
r
mat
i
o
n
T
e
c
h
n
o
l
o
g
y
,
U
n
i
v
e
r
si
t
y
o
f
A
n
b
a
r
,
R
a
m
a
d
i
,
I
r
a
q
2
C
o
mp
u
t
e
r
C
e
n
t
e
r
,
U
n
i
v
e
r
si
t
y
o
f
A
n
b
a
r
,
R
a
ma
d
i
,
I
r
a
q
3
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
s,
C
o
l
l
e
g
e
o
f
S
c
i
e
n
c
e
s,
U
n
i
v
e
r
si
t
y
o
f
A
l
M
a
a
r
i
f
,
R
a
m
a
d
i
,
I
r
a
q
4
D
e
p
a
r
t
me
n
t
o
f
H
e
e
t
Ed
u
c
a
t
i
o
n
,
G
e
n
e
r
a
l
D
i
r
e
c
t
o
r
a
t
e
o
f
Ed
u
c
a
t
i
o
n
i
n
A
n
b
a
r
,
M
i
n
i
st
r
y
o
f
Ed
u
c
a
t
i
o
n
,
H
e
e
t
,
I
r
a
q
5
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
N
e
t
w
o
r
k
i
n
g
S
y
st
e
m,
C
o
l
l
e
g
e
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
a
n
d
I
n
f
o
r
mat
i
o
n
T
e
c
h
n
o
l
o
g
y
,
U
n
i
v
e
r
si
t
y
o
f
A
n
b
a
r
,
R
a
ma
d
i
,
I
r
a
q
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Sep
7
,
2
0
2
4
R
ev
i
s
ed
A
p
r
2
0
,
2
0
2
5
A
cc
ep
ted
J
u
n
1
0
,
2
0
2
5
M
a
lf
u
n
c
ti
o
n
i
n
g
o
f
p
h
o
to
v
o
lt
a
ic
(
P
V
)
sy
ste
m
s
is
a
m
a
in
issu
e
a
f
f
e
c
ti
n
g
so
lar
p
a
n
e
ls
a
n
d
o
t
h
e
r
re
late
d
c
o
m
p
o
n
e
n
ts.
De
tec
ti
n
g
su
c
h
issu
e
s
e
a
rly
lea
d
s
to
e
ff
ici
e
n
t
e
n
e
rg
y
p
ro
d
u
c
ti
o
n
w
it
h
lo
w
m
a
in
ten
a
n
c
e
c
o
sts
a
n
d
h
ig
h
sy
ste
m
p
e
rf
o
r
m
a
n
c
e
c
o
n
siste
n
c
y
.
T
h
is
p
a
p
e
r
p
r
o
p
o
se
d
a
n
e
n
se
m
b
le
m
o
d
e
l
(EM
)
f
o
r
f
a
u
lt
d
e
tec
ti
o
n
(F
D)
in
PV
sy
ste
m
s.
T
h
e
p
ro
p
o
se
d
m
o
d
e
l
u
ti
l
ize
d
a
d
v
a
n
c
e
d
m
a
c
h
in
e
lea
rn
in
g
a
lg
o
rit
h
m
s
c
o
n
tai
n
in
g
ra
n
d
o
m
f
o
re
st
(RF
),
k
-
ne
a
re
st
n
e
ig
h
b
o
rs
(KN
N),
a
n
d
g
ra
d
ie
n
t
b
o
o
sti
n
g
(G
B).
T
ra
d
it
io
n
a
l
a
p
p
r
o
a
c
h
e
s
o
f
ten
d
o
n
o
t
h
a
n
d
le
th
e
se
v
e
ra
l
situ
a
t
io
n
s
th
a
t
P
V
sy
ste
m
s
c
a
n
h
a
v
e
.
Ou
r
E
M
lev
e
ra
g
e
d
th
e
p
o
w
e
r
o
f
G
B’s
a
l
g
o
rit
h
m
in
h
a
n
d
li
n
g
c
o
m
p
lex
d
a
ta
p
a
tt
e
rn
s
th
ro
u
g
h
i
tera
ti
v
e
b
o
o
sti
n
g
,
K
NN
’s
c
a
p
a
b
il
it
y
in
c
a
p
t
u
rin
g
lo
c
a
l
d
a
t
a
stru
c
tu
re
s,
a
n
d
RF
’s
stre
n
g
th
i
n
h
a
n
d
l
in
g
o
v
e
rf
it
ti
n
g
a
n
d
n
o
ise
t
h
ro
u
g
h
it
s
tree
stru
c
tu
re
ra
n
d
o
m
n
e
ss
.
Co
m
b
in
in
g
th
e
se
m
o
d
e
ls
e
n
h
a
n
c
e
d
f
a
u
lt
d
e
tec
ti
o
n
c
a
p
a
b
il
it
ies
,
p
r
o
v
id
i
n
g
e
x
c
e
ll
e
n
t
a
c
c
u
ra
c
y
c
o
m
p
a
re
d
to
in
d
iv
id
u
a
l
m
o
d
e
ls.
T
o
e
v
a
lu
a
te
th
e
p
e
rf
o
r
m
a
n
c
e
o
f
o
u
r
EM
,
d
if
fe
re
n
t
e
x
p
e
ri
m
e
n
ts
we
re
c
o
n
d
u
c
ted
.
T
h
e
re
su
lt
s
d
e
m
o
n
stra
ted
su
b
s
tan
ti
a
l
im
p
ro
v
e
m
e
n
ts
in
d
e
tec
t
io
n
f
a
u
lt
,
a
c
h
iev
in
g
a
n
a
c
c
u
ra
c
y
ra
te
o
f
9
5
%
.
T
h
is
a
c
c
u
ra
c
y
ra
te
c
o
n
sid
e
re
d
h
ig
h
u
n
d
e
rsc
o
re
s
th
e
m
o
d
e
l’s
c
a
p
a
b
il
it
y
to
h
a
n
d
le
f
a
u
lt
d
e
tec
ti
o
n
o
f
P
V
sy
ste
m
s,
p
o
sin
g
a
c
o
n
siste
n
t
so
l
u
ti
o
n
f
o
r
in
sta
n
t
f
a
u
lt
d
e
tec
ti
o
n
a
n
d
m
a
in
ten
a
n
c
e
sc
h
e
d
u
li
n
g
.
K
ey
w
o
r
d
s
:
A
r
ti
f
icial
i
n
tel
lig
e
n
ce
E
n
s
e
m
b
le
m
o
d
els
Fau
lt d
etec
tio
n
Ma
ch
i
n
e
lear
n
i
n
g
P
h
o
to
v
o
ltaic
s
y
s
te
m
s
So
lar
en
er
g
y
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
A
d
il Na
f
ea
Dep
ar
t
m
en
t o
f
A
r
tific
ial
I
n
tel
l
ig
en
ce
,
C
o
lleg
e
o
f
C
o
m
p
u
ter
Scien
ce
a
n
d
I
n
f
o
r
m
atio
n
T
ec
h
n
o
lo
g
y
Un
i
v
er
s
it
y
o
f
An
b
ar
R
a
m
ad
i,
I
r
aq
E
m
ail:
a
h
m
ed
.
a.
n
@
u
o
an
b
ar
.
ed
u
.
iq
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
in
d
u
s
tr
y
o
f
p
h
o
to
v
o
ltai
c
(
P
V)
s
y
s
te
m
s
g
o
t
a
h
ig
h
atten
tio
n
i
n
r
ec
en
t
y
ea
r
s
d
u
e
to
th
e
en
v
ir
o
n
m
e
n
tal
a
n
d
ec
o
n
o
m
ic
ad
v
an
ta
g
es
o
f
s
o
lar
en
er
g
y
[
1
]
.
A
lth
o
u
g
h
it
is
f
r
ee
av
ailab
i
lit
y
an
d
ad
d
itio
n
al
s
en
s
u
al
a
s
p
ec
ts
,
t
h
e
PV
in
d
u
s
t
r
y
e
n
co
u
n
ter
s
c
h
alle
n
g
es
s
u
c
h
as
r
ed
u
ce
d
o
u
tp
u
t
p
o
w
er
,
r
el
iab
ilit
y
,
ex
p
o
s
u
r
e
to
f
au
lts
,
h
i
g
h
co
s
t,
an
d
i
ts
d
ep
en
d
en
ce
o
n
en
v
ir
o
n
m
e
n
tal
c
h
an
g
e
s
[
2
]
.
B
ec
au
s
e
P
V
s
y
s
te
m
's
f
u
n
ctio
n
ali
t
y
is
af
f
ec
ted
b
y
en
v
ir
o
n
m
en
t
co
n
d
itio
n
s
,
th
e
y
ar
e
af
f
ec
ted
b
y
v
a
r
io
u
s
f
au
lts
li
k
e
l
in
e
-
to
-
g
r
o
u
n
d
(
L
G)
,
lin
e
-
to
-
li
n
e
(
L
L
)
,
o
p
en
-
cir
cu
i
t (
OC
)
,
s
h
o
r
t
-
cir
cu
i
t (
SC
)
,
h
o
t sp
o
t
(
HS)
,
p
ar
tial sh
ad
i
n
g
(
P
S),
an
d
d
u
s
t.
Su
c
h
is
s
u
e
s
ca
n
lead
to
lo
w
e
n
er
g
y
p
r
o
d
u
ctio
n
a
n
d
lo
w
er
s
y
s
te
m
e
f
f
icie
n
c
y
.
I
n
ad
d
itio
n
to
th
at,
it
h
as
b
ee
n
r
ep
o
r
ted
th
at
th
ese
co
n
d
itio
n
s
ar
e
th
e
p
r
i
m
ar
y
ca
u
s
e
o
f
P
V
lif
eti
m
e
r
ed
u
ctio
n
[
3
]
.
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.
14
,
No
.
2
,
J
u
l
y
20
25
:
507
-
5
1
7
508
P
V
f
au
lts
p
ar
ts
lik
e
p
an
el
s
,
ar
r
ay
s
,
m
o
d
u
le
s
,
co
n
n
ec
tio
n
lin
es,
in
v
er
ter
s
,
an
d
co
n
v
er
ter
s
d
iv
id
ed
in
to
th
r
ee
p
r
i
m
ar
y
t
y
p
e
s
co
r
r
esp
o
n
d
in
g
to
th
eir
ti
m
e
ch
ar
ac
ter
i
s
ti
cs:
ab
r
u
p
t,
in
cip
ien
t,
o
r
in
ter
m
itten
t
[
4
]
.
E
x
ter
n
al
asp
ec
ts
li
k
e
P
S (
d
ea
d
b
ir
d
s
,
s
a
n
d
d
u
s
t,
a
n
d
f
all
o
f
lea
v
es)
o
r
in
ter
n
al
a
s
p
ec
ts
(
OS a
n
d
S
C
,
el
e
m
en
ts
p
ar
a
m
eter
s
s
w
itc
h
in
g
,
an
d
ele
m
e
n
t
s
ag
i
n
g
)
co
n
d
u
ct
th
e
h
ap
p
en
i
n
g
o
f
f
a
u
lts
i
n
th
e
P
V
o
r
in
its
i
m
m
ed
i
ate
cir
cu
it,
co
n
d
u
ct
to
th
e
g
e
n
er
al
f
ail
u
r
e
s
y
s
te
m
[
5
]
.
V
a
r
i
o
u
s
f
au
l
t
d
et
e
c
ti
o
n
(
FD
)
m
e
th
o
d
s
h
av
e
b
e
en
p
l
ac
e
d
i
n
th
e
l
a
s
t
d
e
c
a
d
e
f
o
r
PV
.
M
a
n
u
al
a
n
d
t
r
a
d
i
t
i
o
n
a
l
m
eth
o
d
s
o
f
d
e
te
c
t
in
g
f
au
lt
s
i
n
PV
a
r
e
in
a
cc
u
r
at
e
an
d
t
ak
e
a
l
o
n
g
t
im
e
.
T
h
e
c
o
n
v
ey
e
d
f
au
lt
d
i
ag
n
o
s
is
t
e
c
h
n
i
q
u
es
r
eg
a
r
d
in
g
th
e
s
en
s
in
g
p
r
in
c
i
p
l
e
s
in
c
lu
d
e
e
le
c
t
r
o
lu
m
i
n
es
c
en
c
e
im
ag
in
g
,
th
e
r
m
al
im
a
g
in
g
,
tim
e
d
o
m
a
in
r
e
f
l
ec
t
o
m
e
t
r
y
,
e
a
r
t
h
ca
p
a
c
i
ta
n
ce
m
e
asu
r
em
en
t
,
an
d
e
le
c
t
r
ic
a
l
e
l
em
en
ts
m
o
n
it
o
r
in
g
[
6
]
.
M
a
ch
in
e
l
e
a
r
n
in
g
(
ML
)
t
e
c
h
n
i
q
u
es
h
av
e
b
e
en
p
r
o
p
o
s
e
d
d
u
e
t
o
t
h
e
h
ig
h
p
e
r
f
o
r
m
an
c
e
p
r
o
v
i
d
e
d
b
y
th
es
e
t
e
ch
n
iq
u
e
s
[
7
]
,
[
8
]
.
M
L
t
e
c
h
n
i
q
u
es
h
av
e
b
e
en
p
r
o
p
o
s
e
d
d
u
e
t
o
th
e
h
ig
h
p
e
r
f
o
r
m
an
ce
p
r
o
v
i
d
e
d
b
y
th
es
e
t
e
ch
n
i
q
u
e
s
.
M
L
is
a
c
o
l
l
e
ct
i
o
n
o
f
a
l
g
o
r
ith
m
s
th
a
t
p
e
r
m
i
t
s
o
f
t
w
a
r
e
a
p
p
l
i
ca
t
i
o
n
s
w
ith
o
u
t
c
o
m
p
l
i
c
a
t
e
d
p
r
o
g
r
am
m
in
g
t
o
p
r
ed
i
c
t
p
r
o
d
u
c
t
s
m
o
r
e
a
c
c
u
r
at
e
ly
.
T
h
is
i
s
d
o
n
e
b
y
m
o
d
e
l
i
n
g
p
r
e
d
ic
t
iv
e
m
o
d
el
s
e
s
ta
b
l
i
s
h
e
d
o
n
s
t
at
i
s
t
i
c
al
m
e
ch
an
i
s
m
s
,
w
h
i
ch
,
s
e
t
o
n
p
r
o
v
i
d
in
g
i
n
p
u
t
d
a
ta
,
w
i
ll
p
r
e
d
i
c
t
o
u
tc
o
m
e
s
an
d
r
ew
o
r
k
th
e
av
a
i
la
b
i
l
ity
o
f
r
en
ew
e
d
in
p
u
t
d
a
t
a
.
I
t
u
t
il
i
z
es
d
i
f
f
e
r
en
t
a
lg
o
r
i
th
m
s
an
d
t
e
ch
n
i
q
u
es
t
o
r
e
a
ch
ex
p
e
ct
e
d
r
esu
l
ts
,
s
u
c
h
as
r
eg
r
e
s
s
i
o
n
,
d
ec
is
i
o
n
t
r
e
e
(
D
T
)
,
r
a
n
d
o
m
f
o
r
e
s
t
(
R
F
)
,
k
-
n
e
a
r
e
s
t
n
e
ig
h
b
o
r
s
(
K
NN
)
,
l
o
g
is
t
i
c
r
eg
r
ess
i
o
n
(
L
R
)
,
an
d
s
u
p
p
o
r
t
v
e
c
t
o
r
m
a
ch
in
e
(
S
V
M
)
.
T
h
e
cu
r
r
en
t
s
t
u
d
y
w
ill
e
v
al
u
at
e
th
r
ee
f
a
u
lt
t
y
p
e
s
:
O
C
,
P
S,
an
d
SC
.
T
h
u
s
,
th
i
s
s
t
u
d
y
ai
m
s
to
in
tr
o
d
u
ce
an
e
m
p
ir
ical
m
o
d
e
(
EM
)
cr
e
ated
FD
s
tr
u
ct
u
r
e
f
o
r
P
V
d
esig
n
s
m
u
lti
f
ar
io
u
s
.
T
h
e
E
M
co
n
tain
s
t
h
r
ee
alg
o
r
ith
m
s
g
r
ad
ien
t
b
o
o
s
tin
g
(
GB
)
,
KN
N
an
d
R
F
tech
n
iq
u
es
h
av
e
b
ee
n
e
m
p
lo
y
ed
f
o
r
m
o
d
el
in
v
esti
g
atio
n
s
in
P
V
d
esig
n
s
.
2.
RE
L
AT
E
D
WO
RK
S
C
h
aib
i
e
t
a
l
.
[
9
]
s
u
g
g
e
s
ted
t
h
at
P
V
s
y
s
te
m
s
d
etec
t
f
o
u
r
t
y
p
es
o
f
FD.
T
h
ese
t
y
p
es
ar
e
in
v
er
ter
d
is
co
n
n
ec
t
io
n
(
I
D)
,
P
S,
SC
,
an
d
OC
f
au
lts
ar
e
th
e
m
o
s
t
f
r
eq
u
e
n
t
f
ai
lu
r
es.
T
h
is
s
tu
d
y
p
r
o
p
o
s
es
a
s
tr
a
ig
h
t
f
o
r
w
ar
d
,
ef
f
ec
ti
v
e
tech
n
iq
u
e
f
o
r
d
etec
tin
g
th
e
m
.
T
h
e
s
u
g
g
es
ted
ap
p
r
o
ac
h
in
tr
o
d
u
ce
s
th
r
ee
in
d
icato
r
s
:
cu
r
r
en
t,
v
o
lta
g
e,
an
d
p
o
w
er
in
d
icato
r
,
w
it
h
th
e
p
r
i
m
ar
y
g
o
al
o
f
id
en
tify
i
n
g
n
o
r
m
al
a
n
d
ab
n
o
r
m
al
o
p
er
atin
g
cir
cu
m
s
ta
n
ce
s
.
T
h
e
b
est
-
y
et
ar
tif
icia
l b
ee
s
c
o
lo
n
y
(
A
B
C
)
o
p
t
i
m
izatio
n
tec
h
n
iq
u
e
i
s
u
s
ed
w
i
th
t
h
e
s
in
g
le
-
d
io
d
e
m
o
d
el
to
p
r
o
d
u
ce
a
tr
u
s
ted
P
V
m
o
d
el
a
n
d
ex
tr
ac
t
th
e
u
n
k
n
o
w
n
m
o
d
el
p
ar
a
m
eter
s
.
T
h
e
m
a
x
i
m
u
m
p
o
w
er
p
o
in
t
(
MP
P)
co
o
r
d
in
ates,
w
h
ic
h
s
i
m
u
late
th
e
ac
t
u
al
o
p
er
atio
n
al
P
V
s
y
s
te
m
,
ar
e
th
en
e
s
ti
m
ate
d
.
C
u
r
r
en
t,
v
o
lta
g
e,
an
d
p
o
w
er
in
d
icat
o
r
s
ca
n
b
e
ca
lcu
lated
u
s
in
g
m
ea
s
u
r
ed
an
d
ex
p
ec
ted
MPP
co
o
r
d
in
ates.
T
r
ial
an
d
er
r
o
r
h
av
e
b
ee
n
u
s
ed
to
d
eter
m
i
n
e
u
p
p
er
an
d
lo
w
er
cr
iter
ia
f
o
r
ea
ch
i
n
d
icatio
n
.
T
h
e
v
a
lu
e
o
f
e
v
er
y
in
d
icato
r
w
h
eth
er
it i
s
w
it
h
i
n
,
u
p
,
o
r
lo
w
er
t
h
a
n
th
e
th
r
esh
o
ld
w
ill
s
ig
n
al
t
h
e
s
it
u
atio
n
o
f
t
h
e
P
V
s
y
s
te
m
a
n
d
w
h
eth
er
it
w
o
r
k
s
co
r
r
ec
tly
o
r
n
o
t.
Dif
f
er
en
t
ex
p
er
i
m
en
ts
w
er
e
co
n
d
u
cted
u
s
i
n
g
th
e
s
t
u
d
ied
d
ata
f
r
o
m
a
3
.
2
k
W
g
r
id
-
co
n
n
ec
ted
PV
s
y
s
te
m
m
o
u
n
ted
o
n
A
lg
er
i
a’
s
r
en
e
w
ab
le
en
er
g
y
d
ev
elo
p
m
en
t c
en
tr
e
(
C
DE
R
)
.
Wa
ng
et
a
l
.
[
1
0
]
p
r
o
p
o
s
e
d
SVM
to
d
etec
t
f
au
lts
i
n
P
V
s
y
s
te
m
s
.
T
h
e
SVM
alg
o
r
it
h
m
u
tili
z
ed
th
e
OC
v
o
ltag
e,
SC
cu
r
r
e
n
t,
m
a
x
i
m
u
m
p
o
w
er
v
o
lta
g
e,
an
d
m
ax
i
m
u
m
p
o
w
er
cu
r
r
en
t
a
s
th
e
m
ai
n
s
ettin
g
p
ar
a
m
eter
s
.
T
h
is
s
elec
tio
n
w
a
s
b
ased
o
n
an
an
al
y
s
is
o
f
f
au
l
ts
a
n
d
th
e
I
-
V
f
ea
t
u
r
ed
cu
r
v
es
o
f
P
V
ar
r
a
y
s
.
T
h
e
f
au
lt
d
ataset
w
a
s
e
n
h
a
n
ce
d
u
s
i
n
g
d
ata
p
r
ep
ar
atio
n
tech
n
iq
u
e
s
,
p
r
o
v
id
i
n
g
h
i
g
h
-
q
u
alit
y
d
ata
f
o
r
t
h
e
SVM
al
g
o
r
ith
m
’
s
ef
f
icien
c
y
.
T
h
ese
p
ar
am
eter
s
w
er
e
o
p
ti
m
ized
u
s
i
n
g
g
r
id
s
e
ar
ch
an
d
k
-
f
o
ld
cr
o
s
s
-
v
alid
ati
o
n
ap
p
r
o
ac
h
es.
T
o
te
s
t
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
,
4
0
0
d
ata
p
o
in
ts
w
er
e
u
s
ed
,
an
d
th
e
r
esu
lts
o
f
th
e
ev
al
u
atio
n
s
h
o
w
ed
a
test
ac
cu
r
ac
y
o
f
9
7
%.
T
h
e
r
esu
lts
o
f
t
h
e
ex
p
er
i
m
en
ts
d
e
m
o
n
s
tr
ated
th
at
t
h
e
SVM
-
b
ased
f
a
u
lt
d
iag
n
o
s
i
s
alg
o
r
ith
m
s
u
r
p
ass
ed
m
an
y
al
g
o
r
ith
m
s
i
n
ter
m
s
o
f
a
cc
u
r
ac
y
.
W
h
i
l
e
th
is
p
ap
er
Kalo
g
er
ak
i
s
et
a
l
.
[
1
1
]
p
r
o
p
o
s
ed
a
g
l
o
b
al
m
a
x
i
m
u
m
p
o
w
er
p
o
in
t
tr
ac
k
in
g
(
GM
P
PT)
m
e
th
o
d
ai
m
ed
at
lo
ca
tin
g
t
h
e
GM
P
P
s
f
o
ca
l
p
o
in
t
r
ap
id
ly
.
U
n
li
k
e
tr
ad
itio
n
a
l
G
MP
PT
m
eth
o
d
s
,
t
h
e
ap
p
r
o
ac
h
p
r
o
p
o
s
ed
in
th
is
r
es
ea
r
ch
u
s
es
a
ML
al
g
o
r
ith
m
a
n
d
d
o
es
n
o
t
r
eq
u
ir
e
p
r
ev
io
u
s
k
n
o
w
led
g
e
o
f
t
h
e
P
V
m
o
d
u
les
'
o
p
er
atin
g
p
r
o
p
er
ties
o
r
th
eir
co
n
f
i
g
u
r
atio
n
.
T
h
is
m
et
h
o
d
is
p
ar
ticu
lar
l
y
e
f
f
ec
ti
v
e
i
n
PV
s
y
s
te
m
s
i
n
th
at
s
h
ad
i
n
g
p
atter
n
s
ca
n
v
ar
y
r
ap
id
l
y
,
s
u
c
h
as
in
w
ea
r
ab
l
e
PV
s
y
s
te
m
s
o
r
b
u
ild
in
g
-
co
m
b
in
ed
PV
s
y
s
te
m
s
,
b
ec
au
s
e
o
f
its
ch
ar
ac
te
r
i
s
tic
o
f
lear
n
in
g
ab
ili
t
y
th
a
t
allo
w
s
q
u
ick
e
r
d
etec
tio
n
o
f
th
e
GM
P
P
w
it
h
less
s
ea
r
c
h
s
p
ac
e
s
o
lu
t
io
n
s
.
Nu
m
er
ical
r
esu
lt
s
i
n
t
h
e
p
ap
er
d
e
m
o
n
s
tr
ate
th
at
th
e
d
esi
g
n
ed
Q
-
lear
n
in
g
-
b
ased
GM
P
P
T
alg
o
r
ith
m
r
ed
u
ce
s
t
h
e
ex
ec
u
ti
o
n
ti
m
e
n
ee
d
ed
to
d
etec
t
th
e
g
lo
b
al
MP
P
b
y
8
0
.
5
%
to
9
8
.
3
%
co
m
p
ar
ed
to
a
GM
P
PT
m
eth
o
d
b
u
ilt
b
ased
o
n
th
e
p
ar
ticle
s
w
ar
m
o
p
ti
m
i
za
tio
n
(
P
SO)
alg
o
r
ith
m
w
h
e
n
u
s
i
n
g
u
n
k
n
o
w
n
PS
p
atter
n
s
.
E
s
k
a
n
d
ar
i
et
a
l
.
[
1
2
]
s
u
g
g
est
a
b
r
an
d
-
n
e
w
,
in
telli
g
en
t
f
a
u
lt
m
o
n
ito
r
in
g
m
ec
h
a
n
i
s
m
.
T
h
e
cr
itica
l
ch
ar
ac
ter
is
tic
s
o
f
c
u
r
r
en
t
-
v
o
lt
ag
e
(I
-
V)
cu
r
v
es
w
i
th
v
ar
io
u
s
f
a
u
lt
s
itu
a
tio
n
s
an
d
t
y
p
ica
l
cir
cu
m
s
ta
n
ce
s
ar
e
o
b
tain
ed
f
o
r
th
is
p
u
r
p
o
s
e.
Us
in
g
t
h
e
h
ier
ar
ch
ical
cla
s
s
i
f
ica
tio
n
(
HC
)
f
r
a
m
e
w
o
r
k
,
t
h
e
f
a
u
lts
ar
e
ca
teg
o
r
ized
.
L
ater
,
M
L
tec
h
n
iq
u
e
s
ar
e
u
s
e
d
to
id
en
ti
f
y
an
d
ca
te
g
o
r
ize
t
h
e
L
L
a
n
d
L
G
p
r
o
b
le
m
s
.
C
o
m
p
ar
ed
to
e
x
i
s
ti
n
g
f
au
lt
d
iag
n
o
s
tic
ap
p
r
o
ac
h
es,
th
e
s
u
g
g
e
s
ted
m
et
h
o
d
s
ee
k
s
to
d
ec
r
ea
s
e
th
e
d
ataset
n
ee
d
ed
f
o
r
th
e
tr
ain
i
n
g
p
r
o
ce
d
u
r
e
an
d
ac
h
iev
e
ad
v
an
ce
d
ac
cu
r
ac
y
in
r
ec
o
g
n
izi
n
g
an
d
ca
teg
o
r
izin
g
t
h
e
o
cc
u
r
r
en
ce
s
o
f
f
a
u
lt
at
lo
w
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
E
n
h
a
n
ce
d
fa
u
lt
d
etec
tio
n
in
p
h
o
to
vo
lta
ic
s
ystems
u
s
in
g
a
n
en
s
emb
le
…
(
Mo
h
a
mme
d
S
a
la
h
I
b
r
a
h
im
)
509
m
is
m
atc
h
le
v
els
a
n
d
h
i
g
h
f
a
u
l
t
i
m
p
ed
an
ce
.
T
h
e
ex
p
er
i
m
e
n
t
al
r
esu
lt
s
s
h
o
w
t
h
at,
w
it
h
an
a
cc
u
r
ac
y
o
f
9
6
.
6
6
%
an
d
9
1
.
6
6
%,
th
e
p
r
esen
ted
ap
p
r
o
ac
h
ac
cu
r
atel
y
clas
s
i
f
ies
a
n
d
ca
teg
o
r
izes
L
L
a
n
d
L
G
d
e
f
ec
ts
o
n
PV
s
y
s
te
m
s
o
v
er
v
ar
io
u
s
s
it
u
atio
n
s
an
d
d
eg
r
ee
s
o
f
d
i
f
f
ic
u
lt
y
.
Kap
u
cu
a
n
d
C
u
b
u
k
c
u
[
13]
p
r
o
p
o
s
ed
en
s
e
m
b
le
lear
n
i
n
g
(
E
L
)
an
d
a
ML
tec
h
n
iq
u
e.
B
y
m
i
x
in
g
t
h
e
p
r
ed
ictio
n
s
o
f
v
ar
io
u
s
al
g
o
r
ith
m
s
,
E
L
ap
p
r
o
ac
h
es
s
tr
iv
e
t
o
ac
h
iev
e
m
o
r
e
g
en
er
aliza
b
il
it
y
a
n
d
p
r
ed
ictio
n
ac
cu
r
ac
y
t
h
an
a
s
in
g
le
M
L
al
g
o
r
ith
m
.
I
n
t
h
is
s
it
u
atio
n
,
g
r
i
d
-
s
ea
r
ch
w
i
th
cr
o
s
s
-
va
lid
atio
n
is
ap
p
lied
f
ir
s
t
to
ch
o
o
s
e
th
e
m
o
s
t
p
er
tin
e
n
t
f
ea
tu
r
es
[
1
0
]
.
T
h
en
,
th
e
p
ar
a
m
et
er
o
p
tim
izatio
n
o
f
ea
ch
lear
n
i
n
g
m
et
h
o
d
an
d
th
e
EL
m
o
d
el
t
h
at
w
o
u
ld
in
te
g
r
a
te
th
e
m
h
a
s
b
ee
n
e
n
h
an
ce
d
.
R
es
u
lts
r
e
v
ea
l
t
h
at
t
h
e
s
u
g
g
e
s
ted
m
et
h
o
d
h
as
a
n
ex
ce
lle
n
t
g
en
er
al
izat
io
n
ca
p
ac
it
y
f
o
r
P
V
s
y
s
te
m
d
e
f
ec
t
d
ia
g
n
o
s
is
an
d
i
m
p
r
o
v
es
th
e
cla
s
s
i
f
ic
atio
n
p
er
f
o
r
m
a
n
ce
w
it
h
t
h
e
co
r
r
ec
t d
ata
an
d
o
p
ti
m
u
m
s
etti
n
g
s
f
o
r
e
ac
h
al
g
o
r
ith
m
an
d
t
h
e
EL
m
o
d
el
.
P
ad
m
av
a
th
i
et
a
l
.
[
1
4
]
d
ev
elo
p
ed
a
r
eg
r
ess
io
n
co
n
tr
o
ller
-
b
ased
m
ax
i
m
u
m
p
o
w
er
p
o
in
t
t
r
ac
k
i
n
g
(
MP
PT)
to
attain
m
a
x
i
m
u
m
p
ea
k
v
o
ltag
e
u
n
d
er
p
ar
tial
s
h
ad
e.
B
ased
o
n
r
ec
o
r
d
ed
d
atasets
o
f
P
V
s
y
s
te
m
o
u
tp
u
t
v
o
lta
g
e
an
d
lo
ad
,
th
e
r
eg
r
ess
io
n
alg
o
r
it
h
m
f
o
r
ec
asts
th
e
c
y
cle
f
o
r
th
e
co
n
v
er
ter
d
u
r
in
g
p
ar
tial
s
h
ad
e
ef
f
ec
t
o
r
in
s
ta
n
t
s
ep
ar
atio
n
f
o
r
th
at
s
p
ec
i
f
ic
g
eo
g
r
ap
h
ic
lo
ca
tio
n
.
I
n
M
A
T
L
A
B
R
2
0
1
8
a
Si
m
u
l
in
k
,
t
h
e
r
eg
r
ess
io
n
-
b
ased
d
u
t
y
c
y
cle
p
r
ed
ictio
n
s
y
s
te
m
is
d
esig
n
ed
.
R
eg
r
es
s
io
n
s
y
s
te
m
is
also
u
s
e
d
in
th
e
test
b
en
ch
f
o
r
P
V
s
y
s
te
m
s
.
D
u
r
in
g
p
ar
ti
al
s
h
ad
e
co
n
d
it
io
n
s
in
P
V,
t
h
e
s
i
m
u
lat
io
n
a
n
d
h
ar
d
w
ar
e
r
esu
lt
s
o
f
r
eg
r
es
s
io
n
co
n
tr
o
ller
-
b
ased
MP
PT
o
u
tp
er
f
o
r
m
P
SO,
f
lo
w
er
p
o
llin
a
tio
n
alg
o
r
ith
m
(
FP
A
)
,
an
d
p
er
t
u
r
b
an
d
o
b
s
er
v
e
(
P
&
O
)
alg
o
r
ith
m
s
b
y
r
o
u
g
h
l
y
2
0
%,
1
6
.
9
6
%,
an
d
1
5
% in
ef
f
icie
n
c
y
,
r
esp
ec
tiv
el
y
.
3.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
e
p
r
o
p
o
s
ed
cr
ea
tes
an
E
M
u
s
in
g
th
e
v
o
ti
n
g
cl
ass
i
f
ie
r
class
.
Ma
in
l
y
,
th
e
p
r
o
p
o
s
ed
m
o
d
el
is
co
m
p
o
s
ed
o
f
t
h
r
ee
ess
e
n
tial
s
t
ag
es:
th
e
f
ir
s
t
is
t
h
e
p
r
ep
r
o
ce
s
s
in
g
s
tag
e,
a
n
d
t
h
e
E
M
co
m
b
i
n
es
t
h
e
p
r
ed
ictio
n
s
as
a
s
ec
o
n
d
s
tag
e
b
y
i
m
p
le
m
e
n
ti
n
g
t
h
r
ee
in
d
iv
id
u
al
clas
s
i
f
i
er
s
:
RF
,
GB
,
an
d
KNN.
Fin
al
l
y
,
th
r
ee
alg
o
r
it
h
m
s
th
at
h
a
v
e
b
ee
n
s
u
g
g
ested
to
p
r
ed
ict
th
e
v
o
tin
g
ca
r
d
n
ee
d
to
b
e
ev
alu
ated
.
Fig
u
r
e
1
ex
p
lain
s
th
e
p
r
o
p
o
s
ed
m
o
d
el,
w
h
er
e
it
s
h
o
w
s
t
h
e
m
ain
s
tag
e
s
an
d
th
eir
d
etails
r
ep
r
esen
ted
b
y
th
e
p
r
ep
r
o
ce
s
s
in
g
(
L
ab
elen
co
d
er
)
a
t
th
is
s
ta
g
e,
th
e
d
ataset
i
s
d
iv
id
ed
in
to
th
e
tr
ain
in
g
p
ar
t,
w
h
i
ch
h
a
s
th
e
lar
g
est
p
er
ce
n
t
(
8
0
%)
an
d
th
e
lo
w
es
t
p
er
ce
n
t
(
2
0
%)
f
o
r
th
e
test
in
g
p
ar
t.
T
h
en
th
r
ee
alg
o
r
ith
m
s
ar
e
ap
p
lied
t
o
b
o
th
d
ataset
p
ar
ts
to
o
b
tain
th
e
f
i
n
al
p
r
ed
ictio
n
,
w
h
ic
h
d
ep
en
d
s
o
n
th
e
lar
g
e
v
o
ti
n
g
r
esu
lt,
an
d
f
in
all
y
th
e
e
v
alu
a
tio
n
.
I
n
th
e
f
o
ll
o
w
i
n
g
s
ec
tio
n
s
,
t
h
e
m
ai
n
s
ta
g
es
h
av
e
b
ee
n
d
etaile
d
.
Fig
u
r
e
1
.
R
esear
ch
m
et
h
o
d
o
lo
g
y
3
.
1
.
Da
t
a
s
et
des
cr
iptio
n
I
n
th
i
s
s
ec
tio
n
P
V
f
a
u
lt
d
atase
t
th
at
h
a
s
b
ee
n
u
s
ed
to
v
alid
ate
th
e
p
r
o
p
o
s
ed
m
o
d
el.
Me
n
d
ele
y
h
as
t
h
i
s
d
ataset
av
ailab
l
e
[
1
5
]
.
T
h
is
d
ataset
p
r
o
v
id
es a
t
h
o
r
o
u
g
h
s
i
m
u
latio
n
u
s
in
g
P
y
t
h
o
n
a
n
d
s
i
m
u
latio
n
p
r
o
g
r
a
m
w
i
th
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.
14
,
No
.
2
,
J
u
l
y
20
25
:
507
-
5
1
7
510
in
te
g
r
ated
cir
cu
it
e
m
p
h
a
s
is
(
S
P
I
C
E
)
im
p
le
m
en
t
s
,
in
cl
u
d
in
g
L
T
Sp
ice.
T
h
e
d
if
f
er
en
t
P
S,
OS,
an
d
SC
f
ac
to
r
s
w
er
e
s
i
m
u
lated
u
s
i
n
g
th
e
P
y
t
h
o
n
-
i
n
d
u
ce
d
SP
I
C
E
n
etli
s
t.
Su
b
s
eq
u
en
tl
y
,
o
th
er
d
atasets
f
o
r
ad
d
itio
n
al
co
n
f
i
g
u
r
atio
n
s
at
d
i
f
f
er
en
t o
p
er
atin
g
te
m
p
er
atu
r
e
s
ar
e
g
en
er
a
ted
b
y
t
h
e
L
T
Sp
ic
e
s
i
m
u
latio
n
.
T
h
at
d
ata
is
p
r
eser
v
ed
in
a
co
m
m
a
-
s
ep
ar
ated
v
alu
es
(
C
S
V
)
f
ile
co
n
tai
n
i
n
g
6
9
6
5
2
3
4
in
s
tan
ce
s
.
E
v
er
y
s
a
m
p
le
co
n
tai
n
s
ten
attr
ib
u
te
s
.
Po
w
er
m
ea
s
u
r
ed
as
w
at
ts
(
W
)
,
s
h
ad
e
v
o
ltag
e,
f
u
l
l
v
o
ltag
e,
cu
r
r
en
t
m
ea
s
u
r
ed
as
a
m
p
er
e
(
A
)
,
te
m
p
er
atu
r
e,
v
o
l
tag
e
m
ea
s
u
r
ed
as
v
o
lt
(
V)
,
p
ar
allel
an
d
s
er
ies
ce
lls
,
a
n
d
n
u
m
b
er
o
f
ce
lls
ar
e
s
o
m
e
o
f
th
ese
q
u
alit
ies.
T
ab
le
1
d
escr
ib
es
an
in
s
tan
ce
o
f
th
e
P
V
f
ea
tu
r
es
th
at
ar
e
u
s
ed
as
illu
s
tr
ativ
e
f
ea
tu
r
es
an
d
as in
p
u
t f
o
r
th
e
M
L
m
et
h
o
d
s
.
T
ab
le
1
.
I
n
p
u
t f
ea
tu
r
es
f
o
r
P
V
d
atas
et
[
1
5
]
V
o
l
t
a
g
e
(V)
C
u
r
r
e
n
t
(A)
P
o
w
e
r
(
W
)
F
u
l
l
v
o
l
t
a
g
e
S
h
a
d
e
v
o
l
t
a
g
e
T
e
mp
e
r
a
t
u
r
e
#
of
c
e
l
l
s
S
e
r
i
e
s
c
e
l
l
s
P
a
r
a
l
l
e
l
c
e
l
l
s
0
3
.
7
3
2
.
0
9
7
.
8
0
1
0
0
0
7
0
0
40
10
5
2
1
0
.
1
8
4
.
4
8
0
.
8
1
1
0
0
0
6
0
0
30
10
2
5
2
0
.
3
4
5
.
9
8
2
.
0
3
1
0
0
0
5
0
0
40
8
2
4
3
8
.
4
2
0
.
6
7
-
5
.
6
0
1
0
0
0
6
0
0
36
9
9
1
…
…
…
…
…
…
…
…
…
…
6
9
6
5
2
3
4
6
.
9
5
1
.
0
5
7
.
3
0
8
0
0
7
0
0
40
10
10
1
6
9
6
5
2
3
5
3
.
3
4
1
.
7
9
5
.
9
9
1
0
0
0
6
0
0
38
10
5
2
6
9
6
5
2
3
6
×
1
0
c
o
l
u
m
n
s
T
h
e
d
ataset
d
eliv
er
s
6
9
6
5
2
3
6
in
s
ta
n
ce
s
;
ea
ch
i
n
s
ta
n
ce
h
a
s
t
en
f
ea
t
u
r
es
t
h
at
r
ep
r
esen
t
t
h
e
P
V
p
an
el.
T
h
ese
f
ea
tu
r
es
ar
e
cu
r
r
en
t,
v
o
ltag
e,
p
o
w
er
,
f
u
ll
v
o
lta
g
e,
s
h
a
d
e
v
o
ltag
e,
te
m
p
er
atu
r
e,
n
u
m
b
er
o
f
ce
ll
s
,
s
er
ies
ce
lls
,
an
d
p
ar
allel
ce
lls
.
T
h
is
s
tu
d
y
i
n
v
e
s
ti
g
ates t
h
r
ee
k
in
d
s
o
f
f
a
u
lt
s
in
P
V
(
OC
,
P
S,
an
d
S
C
)
.
3
.
2
.
P
re
pro
ce
s
s
ing
I
n
r
ea
l
-
w
o
r
ld
s
ce
n
ar
io
s
,
d
atas
ets
o
f
ten
co
m
e
w
it
h
is
s
u
es
li
k
e
m
i
s
s
i
n
g
v
al
u
es,
n
o
is
e,
an
d
f
o
r
m
at
s
th
at
ar
e
u
n
s
u
itab
le
f
o
r
E
M,
n
ec
ess
itati
n
g
p
r
ep
r
o
ce
s
s
in
g
to
m
ak
e
t
h
e
m
u
s
ab
le
f
o
r
d
ee
p
lear
n
in
g
m
o
d
e
ls
.
P
r
ep
r
o
ce
s
s
in
g
h
elp
s
to
e
n
h
an
ce
th
e
p
er
f
o
r
m
a
n
ce
an
d
e
f
f
ici
en
c
y
o
f
E
M
m
eth
o
d
s
b
y
ad
d
r
ess
i
n
g
t
h
ese
i
s
s
u
es
.
T
w
o
k
e
y
p
r
ep
r
o
ce
s
s
in
g
o
p
er
atio
n
s
i
n
th
i
s
co
n
te
x
t a
r
e
d
ata
n
o
r
m
aliza
tio
n
an
d
f
ea
t
u
r
e
en
co
d
i
n
g
.
3
.
2
.
1
.
Da
t
a
no
r
m
a
liza
t
io
n
T
h
is
s
tep
ad
j
u
s
ts
t
h
e
s
ca
l
e
o
f
f
ea
t
u
r
es
to
en
s
u
r
e
t
h
at
all
attr
ib
u
tes
p
ar
ticip
ate
ev
en
l
y
in
t
h
e
m
o
d
el
’
s
lear
n
in
g
p
r
o
ce
s
s
,
a
n
d
m
et
h
o
d
s
s
u
c
h
as
s
ta
n
d
ar
d
izatio
n
,
Z
-
s
co
r
e
n
o
r
m
aliza
tio
n
,
an
d
M
in
-
Ma
x
n
o
r
m
aliza
t
io
n
ar
e
co
m
m
o
n
l
y
u
s
ed
.
I
n
t
h
is
r
e
s
ea
r
ch
,
a
P
y
th
o
n
s
ta
n
d
ar
d
s
ca
ler
f
u
n
ctio
n
w
a
s
u
s
ed
.
T
h
is
f
u
n
ctio
n
s
tan
d
ar
d
izes
d
ata
to
f
it
w
it
h
in
a
p
ar
ticu
lar
r
an
g
e
r
at
h
er
t
h
an
k
ee
p
i
n
g
t
h
e
r
elatio
n
s
h
ip
s
b
et
w
ee
n
d
ata
p
o
in
ts
.
I
t
tr
an
s
f
o
r
m
s
th
e
d
ata
in
to
a
r
an
g
e
a
m
o
n
g
0
to
1
[
1
6
]
.
3
.
2
.
2
.
F
ea
t
ure
enco
din
g
T
h
is
is
a
n
o
th
er
p
r
ep
r
o
ce
s
s
in
g
s
tep
f
o
r
t
h
e
E
M
th
at
p
r
o
ce
s
s
es
o
n
l
y
n
u
m
er
ical
in
p
u
ts
.
A
f
ea
tu
r
e
en
co
d
in
g
i
s
ap
p
lied
to
co
n
v
er
t
ca
teg
o
r
ial
v
al
u
es
i
n
to
n
u
m
er
ical
v
alu
e
s
.
T
h
er
e
ar
e
a
lo
t
o
f
m
et
h
o
d
s
lik
e
On
eHo
tEn
co
d
er
an
d
L
ab
elE
n
co
d
er
a
r
e
u
s
u
all
y
u
til
ized
f
o
r
th
is
p
u
r
p
o
s
e.
Fo
r
th
is
p
r
o
p
o
s
ed
,
th
e
L
ab
elE
n
co
d
er
w
a
s
ch
o
s
e
n
.
T
h
is
m
et
h
o
d
tr
an
s
f
er
s
u
n
iq
u
e
in
te
g
er
s
to
ca
teg
o
r
ical
v
alu
es
[
1
7
]
,
[
1
8
]
.
Fo
r
e
x
a
m
p
le,
m
an
y
f
a
u
l
t
t
y
p
es
i
n
th
e
d
ataset
w
er
e
e
n
co
d
ed
as
0
,
1
,
an
d
2
,
in
s
tead
o
f
(
'
O
C
'
,
'
P
S,
'
an
d
'
S
C
'
)
,
en
ab
lin
g
th
e
m
o
d
el
to
r
ea
d
an
d
u
tili
ze
s
u
c
h
v
alu
e
s
in
i
ts
c
o
m
p
u
tatio
n
s
.
3
.
3
.
D
a
t
a
s
pli
t
t
ing
T
h
e
f
in
a
l
s
tep
i
n
p
r
ep
ar
in
g
t
h
e
d
ataset
i
n
v
o
l
v
es
d
ata
s
p
litt
i
n
g
,
w
h
ich
is
cr
u
cial
f
o
r
e
v
al
u
a
t
in
g
m
o
d
el
p
er
f
o
r
m
a
n
ce
.
I
n
t
h
is
s
t
u
d
y
,
th
e
d
ataset
w
a
s
s
ep
ar
ated
in
to
8
0
% f
o
r
tr
ain
i
n
g
an
d
2
0
% f
o
r
tes
tin
g
to
ev
al
u
ate
t
h
e
m
o
d
el
’
s
p
er
f
o
r
m
a
n
ce
.
T
h
is
s
p
litt
in
g
g
u
ar
an
tee
s
t
h
at
t
h
e
m
o
d
el
is
tr
ain
ed
o
n
a
g
o
o
d
p
o
r
tio
n
o
f
th
e
d
ata
w
h
il
s
t
p
r
eser
v
in
g
a
s
u
b
s
et
t
o
ass
e
s
s
h
o
w
w
e
ll
it
d
ea
ls
w
it
h
u
n
s
e
en
ex
a
m
p
les
k
ee
p
in
g
a
r
o
b
u
s
t
ev
al
u
atio
n
o
f
i
ts
ef
f
ec
tiv
e
n
e
s
s
.
3
.
4
.
P
r
o
po
s
ed
ens
e
m
b
le
m
o
del
T
h
is
s
tu
d
y
p
r
o
p
o
s
ed
an
E
M
th
at
co
n
tain
s
o
f
R
F,
G
B
,
an
d
KNN
alg
o
r
ith
m
s
co
m
b
in
ed
f
o
r
class
i
f
icatio
n
tas
k
s
.
R
F
i
s
w
el
l
k
n
o
w
n
f
o
r
i
ts
ca
p
ab
ilit
y
to
d
ea
l
w
ith
co
m
p
lex
d
ata
s
ets
a
n
d
r
ed
u
ce
o
v
er
f
itt
in
g
,
w
h
ile
GB
cr
e
ates
w
ea
k
m
o
d
e
ls
an
d
co
m
b
in
e
s
t
h
e
m
to
m
a
k
e
a
s
tr
o
n
g
p
r
ed
ictiv
e
m
o
d
el.
On
t
h
e
o
t
h
er
h
a
n
d
,
KNN
ca
teg
o
r
izes
n
e
w
ca
s
e
s
b
ased
o
n
th
eir
KNN
.
T
h
e
E
M
c
o
n
tr
o
ls
th
e
p
o
w
er
o
f
ev
er
y
al
g
o
r
ith
m
to
b
o
o
s
t
th
e
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
E
n
h
a
n
ce
d
fa
u
lt
d
etec
tio
n
in
p
h
o
to
vo
lta
ic
s
ystems
u
s
in
g
a
n
en
s
emb
le
…
(
Mo
h
a
mme
d
S
a
la
h
I
b
r
a
h
im
)
511
ac
cu
r
ac
y
o
f
th
e
s
y
s
te
m
.
Ho
wev
er
,
th
e
ef
f
icien
c
y
o
f
th
e
m
o
d
el
d
e
p
en
d
s
o
n
f
ac
to
r
s
s
u
ch
as
m
o
d
el
q
u
alit
y
,
d
iv
er
s
it
y
,
a
n
d
en
s
e
m
b
le
tec
h
n
i
q
u
e.
3
.
4
.
1
.
Ra
nd
o
m
f
o
re
s
t
R
F
is
a
co
m
m
o
n
l
y
u
ti
lized
in
EL
alg
o
r
ith
m
f
o
r
b
o
th
class
i
f
i
ca
tio
n
an
d
r
eg
r
ess
io
n
tas
k
s
[
1
9
]
,
[
2
0
]
.
I
t
en
h
a
n
ce
s
ac
cu
r
ac
y
v
ia
ag
g
r
eg
atin
g
th
e
r
esu
lt
s
o
f
m
an
y
d
ec
i
s
io
n
tr
ee
s
an
d
co
m
b
i
n
in
g
th
e
m
to
p
r
o
d
u
ce
a
f
in
al
p
r
ed
ictio
n
,
m
a
k
i
n
g
i
t
ef
f
ec
ti
v
e
f
o
r
co
m
p
le
x
d
atasets
.
T
h
e
co
r
e
co
n
ce
p
t
is
to
esti
m
ate
a
clas
s
if
ica
tio
n
f
u
n
ctio
n
,
w
h
er
e
a
r
an
d
o
m
v
ec
to
r
X
is
r
ep
r
esen
ted
a
s
th
e
in
p
u
t,
an
d
th
e
o
u
tp
u
t
is
th
e
s
q
u
ar
e
-
i
n
te
g
r
al
r
an
d
o
m
r
e
s
p
o
n
s
e
Y.
T
h
is
Y
i
s
co
m
p
u
ted
u
s
in
g
an
e
s
ti
m
ati
n
g
f
u
n
ctio
n
n
(
x
)
=E
[
Y
|
X=
x
]
.
An
R
F
is
a
p
r
ed
icto
r
co
n
s
is
tin
g
o
f
N
-
r
an
d
o
m
ized
class
i
f
icatio
n
tr
ee
s
,
w
it
h
th
e
it
h
tr
ee
's
p
r
ed
icted
v
alu
e
at
th
e
q
u
er
y
p
o
in
t
d
en
o
ted
b
y
n
m
(
x
;Θi,T
m
)
.
T
h
e
p
ar
am
eter
Θ
is
u
tili
z
ed
to
r
esam
p
le
t
h
e
tr
ain
i
n
g
s
e
t
b
ef
o
r
e
d
ev
elo
p
in
g
in
d
iv
id
u
al
tr
ee
s
a
n
d
s
elec
ti
n
g
s
u
cc
e
s
s
i
v
e
d
ir
ec
tio
n
s
f
o
r
s
p
litt
in
g
.
(
;
.
)
=
∑
∈
(
;
.
)
(
;
.
)
∈
(
)
(
1
)
W
h
er
e
(
)
is
t
h
e
s
et
o
f
d
ata
p
o
in
ts
c
h
o
s
e
n
b
ef
o
r
e
tr
ee
cr
ea
tio
n
,
(
;
.
)
is
th
e
ce
ll
i
n
cl
u
d
in
g
x
,
an
d
(
;
.
)
is
t
h
e
s
et
o
f
th
e
p
o
i
n
ts
th
at
f
all
i
n
to
(
;
.
)
.
A
t
th
i
s
s
tep
,
a
s
et
o
f
tr
ee
s
ar
e
co
n
q
u
er
ed
to
co
n
s
tr
u
ct
t
h
e
f
o
r
est esti
m
ate
[
1
5
]
:
.
(
;
1
.
∙
∙
∙
∙
∙
∙
∙
∙
.
.
)
=
1
∑
(
;
.
)
=
1
(
2
)
I
n
t
h
e
T
p
ac
k
ag
e
f
o
r
R
F,
th
e
n
u
m
b
e
r
o
f
t
r
ee
s
(
N)
ca
n
b
e
ar
b
itra
r
ily
lar
g
e,
co
n
s
tr
ai
n
ed
o
n
l
y
b
y
a
v
ailab
le
co
m
p
u
ti
n
g
r
eso
u
r
ce
s
.
Fro
m
a
m
o
d
eli
n
g
p
er
s
p
ec
tiv
e,
it
is
b
e
n
ef
icial
to
allo
w
N
to
a
p
p
r
o
a
ch
in
f
in
it
y
,
th
er
eb
y
co
n
s
id
er
in
g
th
e
e
s
ti
m
ate
o
f
a
n
(
in
f
i
n
ite)
f
o
r
est in
s
tead
o
f
a
f
i
n
ite
n
u
m
b
er
o
f
tr
ee
s:
∞
.
(
;
)
=
[
(
;
.
]
T
h
e
r
ef
er
to
th
e
e
x
p
ec
tatio
n
in
cl
u
d
in
g
d
etail
to
r
a
n
d
o
m
p
ar
a
m
eter
,
r
estricte
d
o
n
S
m
.
T
h
e
o
p
er
atio
n
“
→
∞
”
is
ex
p
lai
n
ed
v
ia
th
e
th
eo
r
y
o
f
b
ig
n
u
m
b
er
s
,
w
h
ic
h
d
ec
lar
es
th
at
th
i
s
e
x
p
ec
tatio
n
co
n
v
er
g
e
s
,
r
estricte
d
to
S
m
:
l
im
→
∞
.
(
;
1
.
∙
∙
∙
∙
∙
∙
∙
∙
.
.
=
∞
.
(
;
)
(
3
)
3
.
4
.
2
.
G
ra
dient
bo
o
s
t
ing
GB
is
a
p
o
p
u
lar
EL
ap
p
r
o
ac
h
th
at
h
a
s
g
ain
ed
r
ec
o
g
n
i
tio
n
f
o
r
its
e
f
f
ic
ien
c
y
i
n
s
o
lv
i
n
g
v
a
r
io
u
s
ML
task
s
[
2
1
]
.
B
y
m
er
g
i
n
g
d
if
f
er
en
t
w
ea
k
p
r
ed
ictiv
e
m
o
d
els,
GB
m
a
k
es
a
p
r
ed
ictiv
e
m
o
d
el
ca
p
ab
le
o
f
h
an
d
lin
g
co
m
p
lica
ted
d
atasets
a
n
d
ca
p
tu
r
in
g
n
o
n
-
li
n
ea
r
r
elatio
n
s
h
ip
s
.
I
ts
ab
ilit
y
to
p
r
o
v
id
e
h
i
g
h
p
r
ed
ictiv
e
ac
cu
r
ac
y
h
as
m
ad
e
it
w
id
el
y
u
s
ed
in
d
o
m
ai
n
s
s
u
c
h
as
f
in
a
n
ce
,
h
ea
l
th
c
ar
e,
an
d
n
atu
r
al
la
n
g
u
a
g
e
p
r
o
ce
s
s
i
n
g
.
Ho
w
e
v
er
,
a
p
o
in
t
to
ac
co
u
n
t
t
o
is
th
at
GB
ca
n
b
e
e
x
p
en
s
iv
e
an
d
s
e
n
s
it
iv
e
to
h
y
p
er
p
ar
a
m
e
ter
tu
n
in
g
.
C
ar
ef
u
l
o
p
ti
m
izatio
n
o
f
t
h
e
al
g
o
r
ith
m
's
p
ar
a
m
eter
s
is
n
ec
es
s
ar
y
t
o
ac
h
iev
e
o
p
ti
m
al
p
er
f
o
r
m
an
ce
.
T
h
is
p
r
o
ce
s
s
in
v
o
l
v
es
f
i
n
d
in
g
t
h
e
r
ig
h
t b
ala
n
ce
b
et
w
ee
n
m
o
d
el
co
m
p
le
x
it
y
an
d
g
e
n
er
aliza
tio
n
ab
ilit
y
.
(
)
=
∑
(
;
)
=
1
(
4
)
W
h
er
e
all
b
asis
f
u
n
ctio
n
is
(
;
)
∈
R
it
is
a
n
a
i
v
e
f
u
n
ct
io
n
o
f
t
h
e
f
ea
tu
r
e
v
ec
to
r
i
n
d
ex
ed
v
ia
a
p
ar
am
eter
an
d
is
th
e
w
ea
k
le
ar
n
er
w
h
ich
i
s
a
co
n
s
ta
n
t
o
f
t
h
e
j
th
.
w
it
h
ar
e
ch
o
s
en
in
an
ad
ap
tiv
e
m
an
n
er
to
i
m
p
r
o
v
e
d
ata
co
n
s
i
s
ten
c
y
.
L
et
(
.
(
)
)
a
r
ate
o
f
d
ata
f
id
e
l
it
y
at
t
h
e
o
b
s
er
v
at
io
n
(
y
,
x
)
f
o
r
th
e
lo
s
s
f
u
n
ctio
n
,
ex
p
ec
ted
to
b
e
d
is
tin
ct
i
n
t
h
e
s
ec
o
n
d
m
an
a
g
e.
On
e
o
f
th
e
m
a
in
g
o
als
o
f
M
L
i
s
to
d
ev
elo
p
a
f
u
n
ctio
n
th
at
m
i
n
i
m
ize
s
th
e
ac
ce
p
ted
lo
s
s
(
E
P
(
(
.
(
)
)
)
,
w
h
er
e
t
h
e
p
r
o
b
ab
ilit
y
i
s
ta
k
en
o
v
er
th
e
u
n
k
n
o
w
n
d
i
s
tr
ib
u
tio
n
o
f
(
y
,
x
)
(
d
en
o
ted
b
y
P
)
.
On
e
w
a
y
to
ac
h
iev
e
th
is
g
o
al
s
ta
y
s
to
s
t
u
d
y
t
h
e
p
r
ac
tical
lo
s
s
an
d
n
ea
r
l
y
m
in
i
m
ize
it
u
tili
zi
n
g
al
g
o
r
ith
m
s
t
h
at
f
i
n
d
s
a
h
i
g
h
v
al
u
e
o
f
v
ia
n
ea
r
l
y
m
i
n
i
m
i
zin
g
t
h
e
r
ea
lis
ti
c
lo
s
s
:
∑
(
.
(
)
)
=
1
(
5
)
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.
14
,
No
.
2
,
J
u
l
y
20
25
:
507
-
5
1
7
512
w
h
er
e
th
e
(
.
(
)
)
u
s
ed
to
p
r
o
ce
s
s
d
a
ta
co
n
f
o
r
m
it
y
f
o
r
th
e
ith
s
a
m
p
le
(
.
)
.
T
h
e
p
r
ev
io
u
s
v
er
s
io
n
o
f
GB
M.
T
h
e
GB
M
alg
o
r
ith
m
ca
n
b
e
p
r
esen
ted
:
in
itial
izatio
n
:
in
itiali
ze
w
ith
:
0
(
)
=
0
f
o
r
m
=0
,
….
.
M
-
1
d
o
:
C
o
m
p
u
te
p
s
eu
d
o
-
r
esid
u
a
l
:
=
−
[
(
.
(
)
)
(
)
]
=
1
.
∙
∙
∙
⋯
.
(
6
)
d
is
co
v
er
th
e
b
est
w
ea
k
lear
n
er
:
=
∑
(
−
(
;
)
)
2
=
1
(
7
)
se
lect
th
e
s
tep
-
s
ize
b
y
li
n
e
s
ea
r
ch
:
=
∑
(
.
(
)
)
+
(
;
)
=
1
(
8
)
u
p
d
ate
th
e
m
o
d
el
+
1
(
)
=
(
)
+
(
;
)
(
9
)
o
u
tp
u
t
:
(
)
(
1
0
)
3
.
4
.
3
.
K
-
nea
re
s
t
neig
hb
o
rs
KNN
is
o
n
e
o
f
ML
al
g
o
r
ith
m
s
w
h
ich
is
u
s
u
all
y
ap
p
lied
f
o
r
b
o
th
r
eg
r
es
s
io
n
a
n
d
clas
s
i
f
ica
tio
n
tas
k
s
.
T
h
e
w
id
esp
r
ea
d
o
f
t
h
is
a
lg
o
r
ith
m
i
s
d
u
e
to
it
s
s
i
m
p
lici
t
y
an
d
ef
f
ec
ti
v
e
n
ess
[
22]
.
I
t
is
co
n
s
id
er
ed
a
n
o
n
-
p
ar
am
etr
ic
al
g
o
r
it
h
m
b
ec
a
u
s
e
it
d
o
es
n
o
t
m
ak
e
a
n
y
ass
u
m
p
tio
n
s
ab
o
u
t
t
h
e
u
n
d
er
l
y
i
n
g
d
at
a
d
is
tr
ib
u
t
io
n
.
I
n
s
tead
,
KNN
m
a
k
es
p
r
ed
icti
o
n
s
b
ased
o
n
d
is
tan
ce
m
ea
s
u
r
e
m
en
ts
b
et
w
ee
n
i
n
p
u
t
d
ata
p
o
in
ts
.
B
y
co
m
b
i
n
i
n
g
th
e
p
r
ed
ictio
n
s
f
r
o
m
m
u
lt
ip
le
class
i
f
ier
s
,
t
h
e
E
M
ai
m
s
to
en
h
a
n
ce
p
r
ed
ictio
n
ac
cu
r
ac
y
an
d
g
en
er
al
izatio
n
.
E
ac
h
class
i
f
ier
p
o
s
s
es
s
es
its
o
w
n
s
tr
en
g
t
h
s
a
n
d
w
ea
k
n
e
s
s
e
s
,
an
d
b
y
le
v
er
ag
i
n
g
t
h
eir
co
llectiv
e
k
n
o
w
led
g
e,
th
e
E
M
ca
n
g
e
n
er
ate
m
o
r
e
r
o
b
u
s
t
p
r
ed
ictio
n
s
.
I
n
M
L
is
s
u
e
s
,
a
m
eth
o
d
to
ch
ar
ac
ter
ize
d
ata
p
o
in
ts
is
cr
u
ci
al.
A
f
ea
t
u
r
e
v
ec
to
r
,
w
it
h
le
n
g
th
M,
is
a
m
at
h
e
m
a
tical
p
r
esen
tat
io
n
o
f
d
ata
w
i
t
h
M
u
n
iq
u
e
attr
ib
u
te
s
.
KNN
class
i
f
ies
n
e
w
o
b
j
ec
ts
b
ased
o
n
attr
ib
u
tes
an
d
tr
ain
i
n
g
d
ata.
T
o
class
n
e
w
ite
m
s
,
K
NN
p
er
f
o
r
m
s
s
p
ec
i
f
ic
p
h
ase
s
:
−
E
s
ti
m
a
te
th
e
s
p
ac
e
b
et
w
ee
n
th
e
ite
m
to
b
e
class
i
f
ied
w
it
h
ev
er
y
p
o
in
t in
t
h
e
d
ataset
tr
ai
n
in
g
.
−
C
h
o
o
s
e
t
h
e
n
ea
r
est d
a
ta
p
o
in
t
s
w
it
h
t
h
e
K
lo
w
est s
p
ac
e.
−
P
er
f
o
r
m
i
n
g
a
“m
aj
o
r
it
y
v
o
te”
b
et
w
ee
n
th
o
s
e
d
ata
p
o
in
t
s
.
T
h
e
KNN
m
at
h
e
m
atica
l
m
o
d
el
u
s
e
s
t
h
e
en
t
ir
e
tr
ain
i
n
g
d
ataset
f
o
r
p
r
ed
ictio
n
,
ex
p
lo
r
in
g
m
u
l
tip
l
e
eq
u
iv
ale
n
t
s
a
m
p
les.
T
h
e
E
u
clid
ea
n
d
is
ta
n
ce
f
o
r
m
u
la
i
s
u
s
ed
to
d
eter
m
i
n
e
w
h
ic
h
K
s
a
m
p
les
ar
e
m
o
r
e
eq
u
iv
ale
n
t to
th
e
n
e
w
o
b
j
ec
t
[
1
6
]
:
(
.
)
=
∑
(
−
)
2
=
1
(
1
1
)
w
h
er
e
(
.
)
is
t
h
e
s
p
ac
e
a
m
o
n
g
tes
t
in
g
a
n
d
tr
ain
i
n
g
o
b
j
ec
t.
3
.
5
.
E
v
a
lua
t
i
o
n
P
r
ec
is
io
n
,
r
ec
all,
an
d
F
-
s
co
r
e
ar
e
w
id
el
y
u
s
ed
p
er
f
o
r
m
a
n
ce
m
etr
ics
u
s
ed
to
ass
es
s
h
o
w
a
ML
m
o
d
el
is
e
f
f
ic
ien
t.
Su
c
h
m
etr
ic
s
p
r
o
v
id
e
i
m
p
o
r
tan
t
f
ac
t
s
o
n
s
ev
er
al
s
itu
a
tio
n
s
r
elate
d
to
th
e
m
o
d
el
p
er
f
o
r
m
an
ce
.
T
h
e
f
ir
s
t
m
etr
ic,
w
h
ich
i
s
p
r
ec
is
io
n
,
m
ea
s
u
r
es
t
h
e
m
o
d
el
ab
ilit
y
to
ap
p
r
o
p
r
iately
d
etec
t
r
ig
h
t
o
u
tco
m
es
o
u
t
o
f
t
h
e
to
tal
p
r
ed
icted
p
o
s
itiv
es
o
u
tco
m
es,
s
h
o
w
i
n
g
h
o
w
lo
w
i
s
f
als
e
p
o
s
itiv
e
s
o
u
tco
m
es.
R
ec
all,
o
n
th
e
o
th
er
h
an
d
,
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
E
n
h
a
n
ce
d
fa
u
lt
d
etec
tio
n
in
p
h
o
to
vo
lta
ic
s
ystems
u
s
in
g
a
n
en
s
emb
le
…
(
Mo
h
a
mme
d
S
a
la
h
I
b
r
a
h
im
)
513
ev
alu
a
tes
t
h
e
m
o
d
el
'
s
ab
ili
t
y
t
o
id
en
tify
all
p
o
s
iti
v
e
ca
s
es
o
u
t
o
f
t
h
e
to
tal
ac
tu
a
l
p
o
s
itiv
e
s
,
h
ig
h
li
g
h
ti
n
g
a
lo
w
f
alse
n
eg
a
tiv
e
r
ate
[
2
3
]
.
Pr
e
c
ision
=
T
r
ue
Po
s
i
t
i
v
es
T
r
ue
Po
s
i
t
i
v
es
+
F
al
s
e
Po
s
i
t
i
v
es
)
(
1
2
)
R
ec
all:
r
ec
all
is
t
h
e
r
atio
o
f
co
r
r
ec
tly
p
r
ed
icted
p
o
s
itiv
e
in
s
ta
n
ce
s
to
th
e
to
tal
a
ct
u
a
l
p
o
s
itiv
e
in
s
ta
n
ce
s
.
I
t
is
a
m
ea
s
u
r
e
o
f
t
h
e
m
o
d
el's ab
ilit
y
to
f
i
n
d
all
p
o
s
iti
v
e
i
n
s
ta
n
ce
s
.
H
ig
h
r
ec
all
m
ea
n
s
t
h
at
th
e
m
o
d
el
h
as a
lo
w
f
al
s
e
n
e
g
ati
v
e
r
ate
[
2
4
]
.
R
e
c
a
l
l
=
T
r
u
e
Po
s
i
t
i
v
es
T
r
ue
Po
s
i
t
i
v
es
+
F
al
s
e
N
eg
at
i
v
es
(
1
3
)
T
h
e
o
th
er
m
etr
ic
is
F
-
s
co
r
e
m
ea
s
u
r
e
m
en
t.
I
t
r
ep
r
esen
ts
th
e
m
ea
n
o
f
p
r
ec
is
io
n
an
d
r
ec
all.
T
h
e
r
esu
lt
o
f
s
u
c
h
m
etr
ic
is
a
s
co
r
e
th
at
s
h
o
w
s
t
h
e
m
o
d
el
'
s
p
er
f
o
r
m
a
n
ce
w
h
e
n
o
p
ti
m
iz
in
g
b
o
th
p
r
ec
is
io
n
a
n
d
r
ec
all
is
d
esire
d
.
A
h
i
g
h
s
co
r
e
o
f
F
-
s
co
r
e
v
alu
e
m
ea
n
s
h
i
g
h
s
co
r
es o
f
p
r
ec
is
io
n
an
d
r
ec
all
[
2
5
]
.
F
−
me
a
s
ure
=
2
×
(
Pr
ec
i
s
i
o
n
∗
Recal
l
)
Pr
ec
i
s
i
o
n
+
Recal
l
(
1
4
)
I
n
th
e
ac
cu
r
ac
y
m
ea
s
u
r
e
m
en
t
in
(
1
5
)
,
th
e
s
co
r
e
is
ca
lcu
lated
b
ased
o
n
tr
u
e
p
o
s
itiv
es,
f
al
s
e
p
o
s
itiv
es
,
tr
u
e
n
eg
at
iv
e
s
,
an
d
f
alse
n
e
g
ativ
es.
S
u
ch
v
a
lu
e
s
co
llected
f
r
o
m
t
h
e
m
o
d
el’
s
o
u
tco
m
es
an
d
g
r
o
u
n
d
tr
u
th
d
ataset
[
2
6
]
.
=
+
+
+
+
(
1
5
)
4.
RE
SU
L
T
AND
DI
SCUS
SI
O
N
T
h
e
r
esu
lts
o
f
t
h
is
w
o
r
k
h
i
g
h
li
g
h
t
th
e
e
f
f
icie
n
c
y
o
f
t
h
e
p
r
o
p
o
s
ed
E
M
w
h
ic
h
co
m
b
i
n
es
R
F,
KNN,
an
d
GB
f
o
r
f
au
lt
d
etec
tio
n
in
P
V
s
y
s
te
m
s
.
T
h
e
m
o
d
el
ac
h
ie
v
ed
a
n
ac
cu
r
ac
y
o
f
9
5
%
in
clas
s
i
f
y
i
n
g
t
h
r
ee
m
aj
o
r
P
V
f
au
lt
t
y
p
es
(
o
p
en
cir
cu
it,
s
h
ad
ed
,
an
d
s
h
o
r
t
cir
cu
it
)
u
tili
zin
g
a
d
ataset
o
f
6
,
9
6
5
,
2
3
6
s
am
p
le
s
co
llected
in
2
0
2
3
.
T
h
is
r
e
m
ar
k
ab
le
ac
cu
r
ac
y
d
e
m
o
n
s
tr
ates
th
e
m
o
d
els
ab
il
it
y
to
e
f
f
ec
ti
v
el
y
h
a
n
d
le
lar
g
e
-
s
ca
le
d
atasets
an
d
r
eliab
l
y
d
iag
n
o
s
e
f
au
lt
t
y
p
e
s
,
m
a
k
i
n
g
it
a
v
alu
ab
le
to
o
l
f
o
r
r
ea
l
-
w
o
r
ld
P
V
s
y
s
te
m
m
o
n
ito
r
i
n
g
a
n
d
m
ai
n
ten
a
n
ce
.
T
h
e
tr
ain
in
g
an
d
v
al
id
atio
n
ac
cu
r
ac
y
c
u
r
v
es,
s
h
o
w
s
i
n
F
ig
u
r
e
2
,
p
r
o
v
id
e
v
is
u
al
e
v
id
e
n
ce
o
f
t
h
e
m
o
d
el
's
lear
n
i
n
g
p
r
o
g
r
ess
io
n
.
B
o
th
m
etr
ics
i
n
cr
ea
s
ed
s
tead
il
y
w
i
th
s
u
cc
es
s
i
v
e
ep
o
ch
s
,
in
d
icati
n
g
ef
f
ic
ien
t
lear
n
in
g
f
r
o
m
t
h
e
tr
ai
n
i
n
g
d
ata
an
d
s
tr
o
n
g
g
en
er
aliza
tio
n
to
u
n
s
ee
n
d
ata.
A
cc
o
m
p
an
y
in
g
th
is
tr
e
n
d
,
th
e
co
n
s
is
ten
t
d
ec
r
ea
s
e
i
n
tr
ai
n
i
n
g
an
d
v
alid
atio
n
lo
s
s
e
s
co
n
f
i
r
m
s
t
h
e
m
o
d
el’
s
ab
ilit
y
to
m
in
i
m
ize
er
r
o
r
s
an
d
co
n
v
er
g
e
to
w
ar
d
an
o
p
ti
m
al
s
o
lu
tio
n
.
T
h
ese
p
atter
n
s
co
llect
iv
el
y
v
alid
ate
t
h
e
r
o
b
u
s
tn
e
s
s
a
n
d
r
eliab
ilit
y
o
f
t
h
e
m
o
d
el
's tr
ain
i
n
g
p
r
o
ce
s
s
.
Fig
u
r
e
2
.
T
r
ain
in
g
an
d
v
a
lid
ati
o
n
ac
cu
r
ac
y
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.
14
,
No
.
2
,
J
u
l
y
20
25
:
507
-
5
1
7
514
T
h
e
m
o
d
els
co
n
f
u
s
io
n
m
a
tr
ix
,
s
h
o
w
n
i
n
Fi
g
u
r
e
3
,
f
u
r
th
er
s
u
p
p
o
r
ts
its
clas
s
if
icatio
n
ac
c
u
r
ac
y
.
T
h
e
d
iag
o
n
al
ele
m
e
n
ts
,
r
ep
r
esen
t
in
g
co
r
r
ec
t
p
r
ed
ictio
n
s
,
d
o
m
in
ate
t
h
e
m
a
tr
ix
,
w
h
ile
o
f
f
-
d
iag
o
n
al
ele
m
e
n
ts
,
in
d
icati
n
g
f
alse
p
o
s
iti
v
e
s
o
r
n
eg
ati
v
e
s
,
an
d
r
e
m
ai
n
m
in
i
m
al
.
T
h
is
o
u
tco
m
e
co
n
f
ir
m
s
th
e
m
o
d
el
'
s
h
i
g
h
p
r
ec
is
io
n
in
d
is
t
in
g
u
is
h
i
n
g
b
et
w
ee
n
f
a
u
lt t
y
p
es
w
it
h
n
eg
l
ig
ib
le
m
is
c
lass
if
ica
tio
n
s
.
Fig
u
r
e
3
.
A
co
n
f
u
s
io
n
m
atr
i
x
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
T
ab
le
2
s
h
o
w
s
th
e
e
v
al
u
atio
n
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el,
s
u
m
m
ar
izin
g
its
p
er
f
o
r
m
a
n
ce
an
d
c
o
m
p
ar
is
o
n
o
f
o
u
r
m
o
d
el
w
it
h
o
th
er
m
o
d
el
s
.
W
h
er
e
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all
,
an
d
F
-
m
ea
s
u
r
e
w
er
e
all
eq
u
al
to
9
5
%.
T
h
e
r
esu
lt
s
p
r
esen
ted
s
h
o
w
s
t
h
e
E
M
ef
f
icien
c
y
i
n
d
etec
tin
g
an
d
class
i
f
y
in
g
f
a
u
lt
s
in
P
V
s
y
s
t
e
m
s
.
T
h
is
a
n
al
y
s
i
s
p
r
o
v
es
th
e
ab
ilit
y
o
f
th
e
m
o
d
el
to
ac
cu
r
atel
y
d
iag
n
o
s
e
f
au
lt
s
an
d
p
r
o
v
id
es
a
f
o
u
n
d
atio
n
f
o
r
f
u
t
u
r
e
en
h
a
n
ce
m
en
ts
a
n
d
ap
p
licatio
n
s
in
s
o
lar
en
er
g
y
f
a
u
lt d
etec
tio
n
s
y
s
te
m
s
.
T
ab
le
2
.
R
esu
lts
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
P
r
e
c
i
si
o
n
R
e
c
a
l
l
F
-
m
e
a
su
r
e
A
c
c
u
r
a
c
y
P
r
o
p
o
se
d
mo
d
e
l
0.
95
0
.
9
5
0
.
9
5
0
.
9
5
P
er
f
o
r
m
a
n
ce
m
etr
ic
s
s
u
ch
as
p
r
ec
is
io
n
,
r
ec
all,
F
-
m
ea
s
u
r
e,
an
d
ac
cu
r
ac
y
r
ea
ch
ed
9
5
%,
as
d
etailed
in
T
ab
le
3
.
T
h
is
co
n
s
is
te
n
t
p
er
f
o
r
m
an
ce
ac
r
o
s
s
m
u
l
tip
le
ev
al
u
atio
n
cr
iter
ia
u
n
d
er
s
co
r
es
t
h
e
m
o
d
el
's
r
eliab
ilit
y
,
n
o
t
o
n
l
y
i
n
d
etec
ti
n
g
f
au
l
ts
b
u
t
also
in
m
i
n
i
m
i
zi
n
g
b
o
th
f
al
s
e
p
o
s
itiv
es
an
d
f
alse
n
eg
at
iv
e
s
.
T
h
e
p
r
o
p
o
s
ed
E
M
m
etr
ics
s
u
r
p
ass
th
o
s
e
o
f
ex
i
s
ti
n
g
ap
p
r
o
ac
h
es,
s
u
ch
as
th
e
s
t
u
d
y
b
y
R
a
m
ap
r
ab
h
a
an
d
Go
k
u
l
ar
a
m
an
[
2
7
]
,
w
h
ich
ac
h
iev
ed
a
n
ac
c
u
r
ac
y
o
f
9
1
.
9
1
%
u
s
in
g
a
d
ec
is
io
n
tr
ee
-
b
ased
ap
p
r
o
ac
h
.
T
ab
le
3
co
m
p
ar
es
th
e
p
er
f
o
r
m
a
n
ce
o
f
v
ar
io
u
s
m
o
d
els,
h
i
g
h
lig
h
ti
n
g
t
h
e
s
u
p
er
io
r
it
y
o
f
th
e
en
s
e
m
b
l
e
ap
p
r
o
ac
h
in
h
a
n
d
li
n
g
co
m
p
l
ex
f
au
l
t
s
ce
n
ar
io
s
.
C
o
m
p
ar
ed
to
tr
ad
itio
n
al
m
o
d
els
li
k
e
L
R
(
6
7
%),
n
ai
v
e
B
ay
e
s
(
NB
)
(
6
2
%),
an
d
SV
M
(
7
9
%),
th
e
E
M
d
em
o
n
s
tr
ate
s
a
clea
r
ad
v
an
tag
e
b
y
lev
er
a
g
i
n
g
t
h
e
s
tr
e
n
g
t
h
s
o
f
m
u
ltip
le
alg
o
r
it
h
m
s
.
B
y
co
m
b
in
i
n
g
R
F,
KNN
,
an
d
GB
,
th
e
m
o
d
el
b
en
ef
it
s
f
r
o
m
d
iv
er
s
e
lear
n
i
n
g
m
ec
h
a
n
i
s
m
s
,
i
m
p
r
o
v
i
n
g
0
its
ab
ilit
y
to
ad
ap
t
to
co
m
p
lex
an
d
d
iv
er
s
e
f
a
u
lt
p
atter
n
s
.
T
h
is
in
te
g
r
atio
n
r
esu
lts
i
n
e
n
h
a
n
c
ed
d
iag
n
o
s
tic
ac
c
u
r
ac
y
a
n
d
r
o
b
u
s
t
n
ess
,
e
s
s
e
n
tia
l
f
o
r
ap
p
licatio
n
s
in
s
o
lar
en
er
g
y
m
ai
n
te
n
a
n
ce
.
T
ab
le
3
.
A
cc
u
r
ac
y
o
f
d
i
f
f
er
en
t
m
o
d
els f
o
r
f
a
u
lt d
etec
tio
n
S
t
u
d
y
M
o
d
e
l
A
c
c
u
r
a
c
y
(
%
)
R
a
ma
p
r
a
b
h
a
a
n
d
G
o
k
u
l
a
r
a
ma
n
[
2
7
]
NB
62
LR
67
S
V
M
79
RF
83
DT
9
1
.
9
1
P
r
o
p
o
se
d
mo
d
e
l
EM
c
o
mb
i
n
e
d
(
R
F
,
G
B
,
a
n
d
K
N
N
)
95
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
E
n
h
a
n
ce
d
fa
u
lt
d
etec
tio
n
in
p
h
o
to
vo
lta
ic
s
ystems
u
s
in
g
a
n
en
s
emb
le
…
(
Mo
h
a
mme
d
S
a
la
h
I
b
r
a
h
im
)
515
T
h
e
s
tu
d
y
’
s
f
i
n
d
in
g
s
h
a
v
e
p
r
o
f
o
u
n
d
i
m
p
licat
io
n
s
f
o
r
t
h
e
s
o
lar
en
er
g
y
s
ec
to
r
.
T
h
e
E
M
ab
ilit
y
t
o
d
etec
t
f
au
lt
s
w
it
h
h
i
g
h
ac
c
u
r
ac
y
s
u
p
p
o
r
ts
ea
r
l
y
id
en
ti
f
ic
atio
n
,
w
h
ic
h
is
cr
itical
f
o
r
m
i
n
i
m
izi
n
g
s
y
s
te
m
d
o
w
n
t
i
m
e
an
d
e
n
s
u
r
i
n
g
u
n
i
n
t
er
r
u
p
ted
en
er
g
y
p
r
o
d
u
ctio
n
.
T
h
is
ca
p
ab
ilit
y
a
ls
o
r
ed
u
ce
s
m
ain
te
n
an
ce
co
s
ts
b
y
en
ab
lin
g
p
r
ec
is
e
in
ter
v
e
n
tio
n
s
r
ath
er
th
a
n
b
r
o
ad
an
d
c
o
s
t
ly
s
y
s
te
m
i
n
s
p
ec
tio
n
s
.
T
h
e
m
o
d
els
s
ca
lab
ilit
y
an
d
g
en
er
aliza
b
ili
t
y
m
ak
e
it
s
u
it
ab
le
f
o
r
lar
g
e
-
s
ca
le
d
ep
lo
y
m
en
t
ac
r
o
s
s
v
ar
io
u
s
P
V
s
y
s
te
m
s
an
d
en
v
ir
o
n
m
e
n
tal
co
n
d
itio
n
s
.
I
ts
s
u
cc
ess
s
ets
t
h
e
s
ta
g
e
f
o
r
ad
ap
tin
g
it
to
d
iv
er
s
e
o
p
er
atio
n
al
s
ce
n
ar
io
s
,
en
h
an
c
i
n
g
it
s
p
r
ac
tical
u
ti
lit
y
in
g
lo
b
al
s
o
lar
en
er
g
y
in
i
tiati
v
es.
T
h
e
E
M
s
tr
en
g
t
h
s
i
n
cl
u
d
e
it
s
h
i
g
h
p
er
f
o
r
m
an
ce
ac
r
o
s
s
ev
alu
a
tio
n
m
etr
ics,
s
ca
lab
ilit
y
to
h
an
d
le
ex
ten
s
i
v
e
d
ataset
s
,
a
n
d
ad
ap
tab
ilit
y
to
v
ar
io
u
s
P
V
f
au
l
t
s
ce
n
ar
io
s
.
Ho
w
e
v
er
,
th
e
s
t
u
d
y
’
s
li
m
ita
tio
n
s
m
u
s
t
b
e
ac
k
n
o
w
led
g
ed
.
T
h
e
d
ataset,
w
h
ile
co
m
p
r
e
h
en
s
iv
e,
m
a
y
n
o
t
f
u
ll
y
ca
p
tu
r
e
all
f
au
l
t
t
y
p
e
s
o
r
en
v
ir
o
n
m
en
tal
co
n
d
itio
n
s
en
co
u
n
ter
ed
in
d
iv
er
s
e
g
eo
g
r
ap
h
ica
l
r
eg
io
n
s
.
Fu
r
t
h
er
m
o
r
e,
th
e
m
o
d
el
cu
r
r
en
tl
y
ad
d
r
ess
es
o
n
l
y
th
r
ee
f
a
u
lt
ca
teg
o
r
ies.
E
x
p
a
n
d
in
g
it
s
s
co
p
e
t
o
in
clu
d
e
ad
d
itio
n
al
f
a
u
lt
s
w
o
u
ld
in
cr
ea
s
e
its
ap
p
licab
ilit
y
in
r
ea
l
-
w
o
r
ld
co
n
d
itio
n
s
.
I
n
t
h
e
f
u
tu
r
e
i
n
co
r
p
o
r
atin
g
d
ee
p
lear
n
in
g
tec
h
n
iq
u
es
o
r
h
y
b
r
id
m
o
d
els
th
at
co
m
b
i
n
e
d
ee
p
lear
n
in
g
w
it
h
tr
ad
itio
n
a
l
ML
m
eth
o
d
s
co
u
ld
f
u
r
t
h
er
i
m
p
r
o
v
e
d
etec
ti
o
n
ac
c
u
r
ac
y
,
p
ar
ticu
lar
l
y
u
n
d
er
d
iv
er
s
e
an
d
d
y
n
a
m
ic
o
p
er
atio
n
al
co
n
d
itio
n
s
.
A
d
d
itio
n
all
y
,
t
h
e
u
s
e
o
f
m
o
r
e
d
i
v
er
s
e
d
atase
ts
w
o
u
ld
al
lo
w
f
o
r
b
etter
ad
ap
tatio
n
to
v
ar
io
u
s
P
V
s
y
s
te
m
co
n
f
i
g
u
r
atio
n
s
a
n
d
e
n
v
ir
o
n
m
e
n
tal
in
f
l
u
en
ce
s
,
p
av
i
n
g
th
e
w
a
y
f
o
r
m
o
r
e
r
o
b
u
s
t a
n
d
ad
ap
tab
le
f
au
lt d
ete
ctio
n
s
y
s
te
m
s
i
n
t
h
e
f
u
t
u
r
e.
5.
CO
NCLU
SI
O
N
T
h
e
f
in
d
i
n
g
s
o
f
t
h
is
p
ap
er
h
a
v
e
s
i
g
n
if
ican
t
i
m
p
licat
io
n
s
f
o
r
th
e
r
esear
ch
f
ield
o
f
P
V
f
au
l
t
d
etec
tio
n
an
d
f
o
r
th
e
b
r
o
ad
er
s
o
lar
en
er
g
y
co
m
m
u
n
it
y
.
B
y
d
e
m
o
n
s
tr
atin
g
th
a
t
an
E
M
co
m
b
i
n
i
n
g
R
F,
KNN,
a
n
d
GB
ac
h
iev
e
s
9
5
%
ac
c
u
r
ac
y
in
cla
s
s
i
f
y
in
g
co
m
m
o
n
P
V
f
au
lts
-
o
p
en
cir
cu
it,
s
h
ad
ed
,
an
d
s
h
o
r
t
cir
cu
it
-
th
is
r
esear
c
h
o
f
f
er
s
a
r
o
b
u
s
t
an
d
s
ca
lab
le
s
o
lu
tio
n
f
o
r
ea
r
ly
f
au
l
t
d
etec
tio
n
in
P
V
s
y
s
te
m
s
.
T
h
is
i
s
i
m
p
o
r
tan
t
f
o
r
th
e
s
o
lar
en
er
g
y
in
d
u
s
tr
y
,
as
it
ca
n
h
e
l
p
r
ed
u
ce
d
o
w
n
t
i
m
e,
m
in
i
m
iz
e
m
a
in
te
n
a
n
ce
co
s
ts
,
an
d
u
lt
i
m
atel
y
i
m
p
r
o
v
e
t
h
e
ef
f
icien
c
y
a
n
d
lo
n
g
e
v
it
y
o
f
s
o
lar
p
o
w
er
s
y
s
te
m
s
.
T
h
e
ab
ilit
y
to
d
etec
t
f
au
lt
s
ea
r
l
y
i
n
t
h
e
o
p
er
atio
n
al
lif
ec
y
cle
en
ab
les
m
o
r
e
p
r
o
ac
tiv
e
m
ai
n
t
en
an
ce
,
r
ed
u
cin
g
th
e
n
ee
d
f
o
r
co
s
tl
y
e
m
e
r
g
en
c
y
r
ep
air
s
an
d
m
ax
i
m
izin
g
en
er
g
y
p
r
o
d
u
ctio
n
.
I
n
th
e
r
esear
ch
f
ield
,
th
ese
r
esu
lts
co
n
tr
ib
u
te
to
th
e
g
r
o
w
in
g
b
o
d
y
o
f
w
o
r
k
in
ML
-
b
ased
f
a
u
l
t
d
etec
tio
n
an
d
p
r
o
v
id
e
a
s
tr
o
n
g
ca
s
e
f
o
r
th
e
ef
f
icie
n
c
y
o
f
EL
ap
p
r
o
ac
h
es
in
r
ea
l
-
w
o
r
ld
ap
p
licatio
n
s
.
Fo
r
th
e
s
o
lar
en
er
g
y
co
m
m
u
n
it
y
,
t
h
e
m
o
d
el’
s
h
ig
h
p
er
f
o
r
m
an
ce
d
e
m
o
n
s
tr
ates
t
h
e
p
o
ten
tial
o
f
au
to
m
ated
f
au
lt
d
etec
tio
n
s
y
s
te
m
s
to
o
p
ti
m
ize
th
e
m
a
in
te
n
a
n
ce
o
f
P
V
in
s
tal
latio
n
s
,
w
h
ic
h
is
cr
itical
a
s
s
o
lar
en
er
g
y
ad
o
p
tio
n
co
n
tin
u
es
to
ex
p
an
d
.
T
h
is
r
esear
ch
p
av
es
th
e
w
a
y
f
o
r
f
u
tu
r
e
ad
v
an
ce
m
e
n
ts
,
i
n
clu
d
i
n
g
th
e
in
teg
r
atio
n
o
f
d
ee
p
lear
n
in
g
tec
h
n
iq
u
e
s
o
r
h
y
b
r
id
m
o
d
els
t
h
at
co
u
ld
en
h
an
ce
d
etec
tio
n
ca
p
ab
ilit
ies
a
n
d
ad
ap
tab
ilit
y
to
d
iv
er
s
e
f
au
lt
t
y
p
e
s
an
d
e
n
v
ir
o
n
m
e
n
tal
co
n
d
itio
n
s
,
f
u
r
t
h
e
r
i
m
p
r
o
v
in
g
th
e
r
e
s
ilie
n
ce
an
d
s
u
s
tai
n
ab
ilit
y
o
f
s
o
lar
p
o
w
e
r
s
y
s
te
m
s
g
lo
b
all
y
.
R
E
FE
R
E
N
C
E
S
[
1
]
J.
C
.
R
.
K
u
mar
a
n
d
M
.
A
.
M
a
j
i
d
,
“
F
l
o
a
t
i
n
g
so
l
a
r
p
h
o
t
o
v
o
l
t
a
i
c
p
l
a
n
t
s
i
n
I
n
d
i
a
–
A
r
a
p
i
d
t
r
a
n
s
i
t
i
o
n
t
o
a
g
r
e
e
n
e
n
e
r
g
y
mark
e
t
a
n
d
s
u
st
a
i
n
a
b
l
e
f
u
t
u
r
e
,
”
E
n
e
r
g
y
a
n
d
E
n
v
i
r
o
n
m
e
n
t
,
v
o
l
.
3
4
,
n
o
.
2
,
p
p
.
3
0
4
–
3
5
8
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
7
7
/
0
9
5
8
3
0
5
X
2
1
1
0
5
7
1
8
5
.
[
2
]
G
.
M
.
El
-
B
a
n
b
y
,
N
.
M
.
M
o
a
w
a
d
,
B
.
A
.
A
b
o
u
z
a
l
m,
W
.
F
.
A
b
o
u
z
a
i
d
,
a
n
d
E.
A
.
R
a
m
a
d
a
n
,
“
P
h
o
t
o
v
o
l
t
a
i
c
sy
st
e
m
f
a
u
l
t
d
e
t
e
c
t
i
o
n
t
e
c
h
n
i
q
u
e
s:
a
r
e
v
i
e
w
,
”
N
e
u
r
a
l
C
o
m
p
u
t
i
n
g
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
5
,
n
o
.
3
5
,
p
p
.
2
4
8
2
9
–
2
4
8
4
2
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
2
1
-
0
2
3
-
0
9
0
4
1
-
7.
[
3
]
F
.
A
z
i
z
,
A
.
U
l
H
a
q
,
S
.
A
h
ma
d
,
Y
.
M
a
h
mo
u
d
,
M
.
Jal
a
l
,
a
n
d
U
.
A
l
i
,
“
A
N
o
v
e
l
C
o
n
v
o
l
u
t
i
o
n
a
l
N
e
u
r
a
l
N
e
t
w
o
r
k
-
B
a
s
e
d
A
p
p
r
o
a
c
h
f
o
r
F
a
u
l
t
C
l
a
ssi
f
i
c
a
t
i
o
n
i
n
P
h
o
t
o
v
o
l
t
a
i
c
A
r
r
a
y
s,”
I
EEE
Ac
c
e
ss
,
v
o
l
.
8
,
p
p
.
4
1
8
8
9
–
4
1
9
0
4
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ES
S
.
2
0
2
0
.
2
9
7
7
1
1
6
.
[
4
]
A
.
M
a
l
i
k
,
A
.
H
a
q
u
e
,
V
.
S
.
B
.
K
u
r
u
k
u
r
u
,
M
.
A
.
K
h
a
n
,
a
n
d
F
.
B
l
a
a
b
j
e
r
g
,
“
O
v
e
r
v
i
e
w
o
f
f
a
u
l
t
d
e
t
e
c
t
i
o
n
a
p
p
r
o
a
c
h
e
s
f
o
r
g
r
i
d
c
o
n
n
e
c
t
e
d
p
h
o
t
o
v
o
l
t
a
i
c
i
n
v
e
r
t
e
r
s,
”
e
-
Pri
m
e
-
Ad
v
a
n
c
e
s
i
n
El
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
ri
n
g
,
E
l
e
c
t
r
o
n
i
c
s
a
n
d
E
n
e
r
g
y
,
v
o
l
.
2
,
p
.
1
0
0
0
3
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
i
me
.
2
0
2
2
.
1
0
0
0
3
5
.
[
5
]
R
.
F
a
z
a
i
e
t
a
l
.
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
se
d
st
a
t
i
s
t
i
c
a
l
t
e
st
i
n
g
h
y
p
o
t
h
e
si
s
f
o
r
f
a
u
l
t
d
e
t
e
c
t
i
o
n
i
n
p
h
o
t
o
v
o
l
t
a
i
c
sy
st
e
ms,”
S
o
l
a
r
En
e
r
g
y
,
v
o
l
.
1
9
0
,
p
p
.
4
0
5
–
4
1
3
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
so
l
e
n
e
r
.
2
0
1
9
.
0
8
.
0
3
2
.
[
6
]
U
.
H
i
j
j
a
w
i
,
S
.
L
a
k
sh
m
i
n
a
r
a
y
a
n
a
,
T
.
X
u
,
G
.
P
.
M
.
F
i
e
r
r
o
,
a
n
d
M
.
R
a
h
m
a
n
,
“
A
r
e
v
i
e
w
o
f
a
u
t
o
mat
e
d
so
l
a
r
p
h
o
t
o
v
o
l
t
a
i
c
d
e
f
e
c
t
d
e
t
e
c
t
i
o
n
sy
st
e
ms:
A
p
p
r
o
a
c
h
e
s,
c
h
a
l
l
e
n
g
e
s,
a
n
d
f
u
t
u
r
e
o
r
i
e
n
t
a
t
i
o
n
s
,
”
S
o
l
a
r
E
n
e
r
g
y
,
v
o
l
.
2
6
6
,
p
.
1
1
2
1
8
6
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
so
l
e
n
e
r
.
2
0
2
3
.
1
1
2
1
8
6
.
[
7
]
S
.
S
i
n
g
h
,
S
.
K
.
P
a
t
r
o
,
a
n
d
S
.
K
.
P
a
r
h
i
,
“
Ev
o
l
u
t
i
o
n
a
r
y
o
p
t
i
m
i
z
a
t
i
o
n
o
f
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
h
y
p
e
r
p
a
r
a
m
e
t
e
r
s
f
o
r
st
r
e
n
g
t
h
p
r
e
d
i
c
t
i
o
n
o
f
h
i
g
h
-
p
e
r
f
o
r
man
c
e
c
o
n
c
r
e
t
e
,
”
As
i
a
n
J
o
u
r
n
a
l
o
f
C
i
v
i
l
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
4
,
n
o
.
8
,
p
p
.
3
1
2
1
–
3
1
4
3
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
2
1
0
7
-
0
2
3
-
0
0
6
9
8
-
y.
[
8
]
M
.
A
l
-
M
a
h
d
a
w
i
,
A
.
K
.
K
a
r
e
e
m,
A
.
A
.
N
a
f
e
a
,
A
.
M
.
S
h
a
b
a
n
,
S
.
A
.
S
.
A
l
i
e
s
a
w
i
,
a
n
d
M
.
M
.
A
l
-
A
n
i
,
“
A
n
Ef
f
e
c
t
i
v
e
D
e
e
p
L
e
a
r
n
i
n
g
A
p
p
r
o
a
c
h
f
o
r
t
h
e
Es
t
i
m
a
t
i
o
n
o
f
P
r
o
t
o
n
En
e
r
g
y
b
y
U
si
n
g
A
r
t
i
f
i
c
i
a
l
N
e
u
r
a
l
N
e
t
w
o
r
k
,
”
i
n
2
0
2
4
2
1
s
t
I
n
t
e
r
n
a
t
i
o
n
a
l
Mu
l
t
i
-
C
o
n
f
e
r
e
n
c
e
o
n
S
y
st
e
m
s,
S
i
g
n
a
l
s
a
n
d
D
e
v
i
c
e
s,
S
S
D
2
0
2
4
,
2
0
2
4
,
p
p
.
2
5
7
–
262
,
d
o
i
:
1
0
.
1
1
0
9
/
S
S
D
6
1
6
7
0
.
2
0
2
4
.
1
0
5
4
9
7
0
6
.
[
9
]
Y
.
C
h
a
i
b
i
,
M
.
M
a
l
v
o
n
i
,
A
.
C
h
o
u
d
e
r
,
M
.
B
o
u
sse
t
t
a
,
a
n
d
M
.
S
a
l
h
i
,
“
S
i
mp
l
e
a
n
d
e
f
f
i
c
i
e
n
t
a
p
p
r
o
a
c
h
t
o
d
e
t
e
c
t
a
n
d
d
i
a
g
n
o
se
e
l
e
c
t
r
i
c
a
l
f
a
u
l
t
s
a
n
d
p
a
r
t
i
a
l
sh
a
d
i
n
g
i
n
p
h
o
t
o
v
o
l
t
a
i
c
sy
st
e
ms,”
En
e
rg
y
C
o
n
v
e
rs
i
o
n
a
n
d
M
a
n
a
g
e
m
e
n
t
,
v
o
l
.
1
9
6
,
p
p
.
3
3
0
–
3
4
3
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
c
o
n
ma
n
.
2
0
1
9
.
0
5
.
0
8
6
.
[
1
0
]
J.
W
a
n
g
,
D
.
G
a
o
,
S
.
Z
h
u
,
S
.
W
a
n
g
,
a
n
d
H
.
L
i
u
,
“
F
a
u
l
t
d
i
a
g
n
o
s
i
s
me
t
h
o
d
o
f
p
h
o
t
o
v
o
l
t
a
i
c
a
r
r
a
y
b
a
se
d
o
n
s
u
p
p
o
r
t
v
e
c
t
o
r
mac
h
i
n
e
,
”
En
e
r
g
y
S
o
u
rc
e
s,
P
a
r
t
A:
R
e
c
o
v
e
ry
,
U
t
i
l
i
z
a
t
i
o
n
,
a
n
d
E
n
v
i
ro
n
m
e
n
t
a
l
Ef
f
e
c
t
s
,
v
o
l
.
4
5
,
n
o
.
2
,
p
p
.
5
3
8
0
–
5
3
9
5
,
Ju
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
8
0
/
1
5
5
6
7
0
3
6
.
2
0
1
9
.
1
6
7
1
5
5
7
.
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.
14
,
No
.
2
,
J
u
l
y
20
25
:
507
-
5
1
7
516
[
1
1
]
C
.
K
a
l
o
g
e
r
a
k
i
s,
E.
K
o
u
t
r
o
u
l
i
s,
a
n
d
M
.
G
.
L
a
g
o
u
d
a
k
i
s,
“
G
l
o
b
a
l
M
P
P
T
b
a
se
d
o
n
mac
h
i
n
e
-
l
e
a
r
n
i
n
g
f
o
r
P
V
a
r
r
a
y
s
o
p
e
r
a
t
i
n
g
u
n
d
e
r
p
a
r
t
i
a
l
s
h
a
d
i
n
g
c
o
n
d
i
t
i
o
n
s
,
”
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s (
S
w
i
t
z
e
rl
a
n
d
)
,
v
o
l
.
1
0
,
n
o
.
2
,
p
.
7
0
0
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
0
0
2
0
7
0
0
.
[
1
2
]
A
.
Esk
a
n
d
a
r
i
,
J.
M
i
l
i
mo
n
f
a
r
e
d
,
a
n
d
M
.
A
g
h
a
e
i
,
“
F
a
u
l
t
D
e
t
e
c
t
i
o
n
a
n
d
C
l
a
ss
i
f
i
c
a
t
i
o
n
f
o
r
P
h
o
t
o
v
o
l
t
a
i
c
S
y
st
e
ms
B
a
se
d
on
H
i
e
r
a
r
c
h
i
c
a
l
C
l
a
ss
i
f
i
c
a
t
i
o
n
a
n
d
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
T
e
c
h
n
i
q
u
e
,
”
I
EEE
T
r
a
n
sa
c
t
i
o
n
s
o
n
I
n
d
u
st
r
i
a
l
El
e
c
t
r
o
n
i
c
s
,
v
o
l
.
6
8
,
n
o
.
1
2
,
p
p
.
1
2
7
5
0
–
1
2
7
5
9
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
E.
2
0
2
0
.
3
0
4
7
0
6
6
.
[
1
3
]
C
.
K
a
p
u
c
u
a
n
d
M
.
C
u
b
u
k
c
u
,
“
A
su
p
e
r
v
i
se
d
e
n
se
mb
l
e
l
e
a
r
n
i
n
g
me
t
h
o
d
f
o
r
f
a
u
l
t
d
i
a
g
n
o
si
s
i
n
p
h
o
t
o
v
o
l
t
a
i
c
st
r
i
n
g
s,”
E
n
e
r
g
y
,
v
o
l
.
2
2
7
,
p
.
1
2
0
4
6
3
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
e
r
g
y
.
2
0
2
1
.
1
2
0
4
6
3
.
[
1
4
]
N
.
P
a
d
m
a
v
a
t
h
i
,
A
.
C
h
i
l
a
m
b
u
c
h
e
l
v
a
n
,
a
n
d
N
.
R
.
S
h
a
n
k
e
r
,
“
M
a
x
i
m
u
m
P
o
w
e
r
P
o
i
n
t
T
r
a
c
k
i
n
g
D
u
r
i
n
g
P
a
r
t
i
a
l
S
h
a
d
i
n
g
Ef
f
e
c
t
i
n
P
V
S
y
st
e
m
U
si
n
g
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
R
e
g
r
e
ssi
o
n
C
o
n
t
r
o
l
l
e
r
,
”
J
o
u
rn
a
l
o
f
E
l
e
c
t
ri
c
a
l
En
g
i
n
e
e
ri
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
6
,
n
o
.
2
,
p
p
.
7
3
7
–
7
4
8
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
2
8
3
5
-
0
20
-
0
0
6
2
1
-
4.
[
1
5
]
K
.
S
o
o
d
,
N
.
R
u
p
p
e
r
t
,
a
n
d
R
.
M
a
h
t
o
,
“
P
a
r
t
i
a
l
S
h
a
d
i
n
g
a
n
d
F
a
u
l
t
S
i
mu
l
a
t
i
o
n
D
a
t
a
se
t
o
f
P
h
o
t
o
v
o
l
t
a
i
c
s
M
o
d
u
l
e
,
”
I
EE
E
D
a
t
a
p
o
rt
,
2
0
2
2
,
d
o
i
:
1
0
.
2
1
2
2
7
/
f
j
b
q
-
0
3
2
1
.
[
1
6
]
B
.
D
e
e
p
a
a
n
d
K
.
R
a
me
sh
,
“
Ep
i
l
e
p
t
i
c
se
i
z
u
r
e
d
e
t
e
c
t
i
o
n
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
t
h
r
o
u
g
h
mi
n
m
a
x
sca
l
e
r
n
o
r
mal
i
z
a
t
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
H
e
a
l
t
h
S
c
i
e
n
c
e
s
,
v
o
l
.
6
,
p
p
.
1
0
9
8
1
–
1
0
9
9
6
,
2
0
2
2
,
d
o
i
:
1
0
.
5
3
7
3
0
/
i
j
h
s.v
6
n
s
1
.
7
8
0
1
.
[
1
7
]
J.
B
a
i
,
S
.
K
o
n
g
,
a
n
d
C
.
G
o
me
s,
“
G
a
u
ssi
a
n
M
i
x
t
u
r
e
V
a
r
i
a
t
i
o
n
a
l
A
u
t
o
e
n
c
o
d
e
r
w
i
t
h
C
o
n
t
r
a
st
i
v
e
L
e
a
r
n
i
n
g
f
o
r
M
u
l
t
i
-
L
a
b
e
l
C
l
a
ssi
f
i
c
a
t
i
o
n
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
Re
se
a
rc
h
,
2
0
2
2
,
v
o
l
.
1
6
2
,
p
p
.
1
3
8
3
–
1
3
9
8
.
[
1
8
]
N
.
B
h
a
t
t
a
c
h
a
r
y
a
,
A
.
S
u
b
u
d
h
i
,
S
.
M
i
sh
r
a
,
V
.
S
h
a
r
ma,
A
.
P
.
A
d
e
r
e
mi
,
a
n
d
C
.
I
w
e
n
d
i
,
“
A
N
o
v
e
l
En
se
mb
l
e
b
a
se
d
M
o
d
e
l
f
o
r
I
n
t
r
u
si
o
n
D
e
t
e
c
t
i
o
n
S
y
st
e
m,”
i
n
Pro
c
e
e
d
i
n
g
s
-
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
ren
c
e
o
n
C
o
m
p
u
t
i
n
g
,
Po
w
e
r
,
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
T
e
c
h
n
o
l
o
g
i
e
s
,
I
C
2
P
C
T
2
0
2
4
,
2
0
2
4
,
v
o
l
.
5
,
p
p
.
6
2
0
–
624
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
2
P
C
T
6
0
0
9
0
.
2
0
2
4
.
1
0
4
8
6
5
8
4
.
[
1
9
]
O
.
J.
K
a
d
h
i
m
,
A
.
A
.
N
a
f
e
a
,
S
.
A
.
S
.
A
l
i
e
saw
i
,
a
n
d
M
.
M
.
A
l
-
A
n
i
,
“
E
n
se
mb
l
e
M
o
d
e
l
f
o
r
P
r
o
st
a
t
e
C
a
n
c
e
r
D
e
t
e
c
t
i
o
n
U
si
n
g
M
R
I
I
mag
e
s,”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
D
e
v
e
l
o
p
m
e
n
t
s
i
n
e
S
y
st
e
m
s
E
n
g
i
n
e
e
r
i
n
g
,
D
e
S
E
,
2
0
2
3
,
p
p
.
4
9
2
–
497
,
d
o
i
:
1
0
.
1
1
0
9
/
D
e
S
E6
0
5
9
5
.
2
0
2
3
.
1
0
4
6
8
8
6
6
.
[
2
0
]
H
.
T
a
o
e
t
a
l
.
,
“
D
e
v
e
l
o
p
me
n
t
o
f
i
n
t
e
g
r
a
t
i
v
e
d
a
t
a
i
n
t
e
l
l
i
g
e
n
c
e
mo
d
e
l
s
f
o
r
t
h
e
r
mo
-
e
c
o
n
o
mi
c
p
e
r
f
o
r
man
c
e
s
p
r
e
d
i
c
t
i
o
n
o
f
h
y
b
r
i
d
o
r
g
a
n
i
c
r
a
n
k
i
n
e
p
l
a
n
t
s,”
E
n
e
r
g
y
,
v
o
l
.
2
9
2
,
p
.
1
3
0
5
0
3
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
e
r
g
y
.
2
0
2
4
.
1
3
0
5
0
3
.
[
2
1
]
C
.
B
e
n
t
é
j
a
c
,
A
.
C
sö
r
g
ő
,
a
n
d
G
.
M
a
r
t
í
n
e
z
-
M
u
ñ
o
z
,
“
A
c
o
mp
a
r
a
t
i
v
e
a
n
a
l
y
si
s
o
f
g
r
a
d
i
e
n
t
b
o
o
st
i
n
g
a
l
g
o
r
i
t
h
ms,”
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
Re
v
i
e
w
,
v
o
l
.
5
4
,
n
o
.
3
,
p
p
.
1
9
3
7
–
1
9
6
7
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
4
6
2
-
020
-
0
9
8
9
6
-
5.
[
2
2
]
M
.
B
a
n
s
a
l
,
A
.
G
o
y
a
l
,
a
n
d
A
.
C
h
o
u
d
h
a
r
y
,
“
A
c
o
mp
a
r
a
t
i
v
e
a
n
a
l
y
si
s
o
f
K
-
N
e
a
r
e
st
N
e
i
g
h
b
o
r
,
G
e
n
e
t
i
c
,
S
u
p
p
o
r
t
V
e
c
t
o
r
M
a
c
h
i
n
e
,
D
e
c
i
si
o
n
T
r
e
e
,
a
n
d
L
o
n
g
S
h
o
r
t
T
e
r
m
M
e
mo
r
y
a
l
g
o
r
i
t
h
ms
i
n
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
D
e
c
i
si
o
n
An
a
l
y
t
i
c
s
J
o
u
rn
a
l
,
v
o
l
.
3
,
p
.
1
0
0
0
7
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
a
j
o
u
r
.
2
0
2
2
.
1
0
0
0
7
1
.
[
2
3
]
O
.
A
.
Eg
a
j
i
,
G
.
Ev
a
n
s,
M
.
G
.
G
r
i
f
f
i
t
h
s,
a
n
d
G
.
I
sl
a
s,
“
R
e
a
l
-
t
i
me
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
se
d
a
p
p
r
o
a
c
h
f
o
r
p
o
t
h
o
l
e
d
e
t
e
c
t
i
o
n
,
”
Ex
p
e
r
t
S
y
s
t
e
m
s
w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
8
4
,
p
.
1
1
5
5
6
2
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
1
.
1
1
5
5
6
2
.
[
2
4
]
M
.
S
.
I
.
A
l
su
mai
d
a
i
e
,
K
.
M
.
A
.
A
l
h
e
e
t
i
,
a
n
d
A
.
K
.
A
l
-
A
l
o
o
s
y
,
“
I
n
t
e
l
l
i
g
e
n
t
D
e
t
e
c
t
i
o
n
S
y
st
e
m
f
o
r
a
D
i
st
r
i
b
u
t
e
d
D
e
n
i
a
l
-
o
f
-
S
e
r
v
i
c
e
(
D
D
o
S
)
A
t
t
a
c
k
B
a
se
d
o
n
T
i
me
S
e
r
i
e
s,”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
D
e
v
e
l
o
p
m
e
n
t
s
i
n
e
S
y
st
e
m
s
En
g
i
n
e
e
r
i
n
g
,
D
e
S
E
,
2
0
2
3
,
v
o
l
.
2
0
2
3
,
p
p
.
4
4
5
–
450
,
d
o
i
:
1
0
.
1
1
0
9
/
D
e
S
E
5
8
2
7
4
.
2
0
2
3
.
1
0
1
0
0
1
8
0.
[
2
5
]
A
.
A
.
N
a
f
e
a
,
M
.
A
L
-
M
a
h
d
a
w
i
,
K
.
M
.
A
.
A
l
h
e
e
t
i
,
M
.
S
.
I
.
A
l
su
mai
d
a
i
e
,
a
n
d
M
.
M
.
A
L
-
A
n
i
,
“
A
H
y
b
r
i
d
M
e
t
h
o
d
o
f
1
D
-
C
N
N
a
n
d
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
A
l
g
o
r
i
t
h
ms f
o
r
B
r
e
a
st
C
a
n
c
e
r
D
e
t
e
c
t
i
o
n
,
”
B
a
g
h
d
a
d
S
c
i
e
n
c
e
J
o
u
r
n
a
l
,
2
0
2
4
,
d
o
i
:
1
0
.
2
1
1
2
3
/
b
sj
.
2
0
2
4
.
9
4
4
3
.
[
2
6
]
M
.
M
a
h
mo
o
d
,
F
.
M
.
Jase
m,
A
.
A
.
M
u
k
h
l
i
f
,
a
n
d
B
.
A
l
-
K
h
a
t
e
e
b
,
“
C
l
a
ssi
f
y
i
n
g
c
u
n
e
i
f
o
r
m
sy
mb
o
l
s
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
w
i
t
h
u
n
i
g
r
a
m
f
e
a
t
u
r
e
s
o
n
a
b
a
l
a
n
c
e
d
d
a
t
a
se
t
,
”
J
o
u
r
n
a
l
o
f
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
s
,
v
o
l
.
3
2
,
n
o
.
1
,
p
.
2
0
2
3
0
0
8
7
,
2
0
2
3
,
d
o
i
:
1
0
.
1
5
1
5
/
j
i
sy
s
-
2
0
2
3
-
008
7.
[
2
7
]
R
.
R
a
ma
p
r
a
b
h
a
a
n
d
S
.
R
.
G
o
k
u
l
a
r
a
m
a
n
,
“
A
n
a
l
y
si
s
a
n
d
M
o
d
i
f
i
c
a
t
i
o
n
o
f
F
a
u
l
t
D
e
t
e
c
t
i
o
n
M
e
t
h
o
d
s
i
n
P
h
o
t
o
v
o
l
t
a
i
c
A
r
r
a
y
,
”
i
n
2
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Em
e
rg
i
n
g
T
re
n
d
s
i
n
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
a
n
d
E
n
g
i
n
e
e
ri
n
g
,
i
c
-
ETI
T
E
2
0
2
4
,
2
0
2
4
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
i
c
-
ETI
T
E5
8
2
4
2
.
2
0
2
4
.
1
0
4
9
3
5
4
7
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
M
o
h
a
m
m
e
d
S
a
la
h
I
b
r
a
h
i
m
is
a
c
o
m
p
u
ter
sc
ien
c
e
tea
c
h
e
r
w
h
o
f
in
ish
e
d
h
is
P
h
.
D
.
f
ro
m
Un
iv
e
rsit
y
o
f
A
r
k
a
n
sa
s
-
F
a
y
e
tt
e
v
il
le
f
ro
m
Un
it
e
d
S
tate
s
o
f
Am
e
rica
in
2
0
2
1
.
He
g
o
t
h
is
M
.
S
c
.
f
ro
m
th
e
D
ep
a
rtm
e
n
t
o
f
Co
m
p
u
ter
S
c
ie
n
c
e
,
Un
iv
e
rsity
o
f
A
n
b
a
r
in
2
0
1
1
.
He
h
a
s
p
u
b
li
sh
e
d
m
a
n
y
p
a
p
e
rs
in
d
if
fe
r
e
n
t
f
ield
s
a
n
d
h
is
m
a
jo
r
in
tere
st
in
in
f
o
rm
a
ti
o
n
re
tri
e
v
a
l
a
n
d
tex
t
p
ro
c
e
ss
in
g
a
re
a
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
o
h
.
sa
lah
@u
o
a
n
b
a
r.
e
d
u
.
i
q
.
H
u
ss
e
in
K
.
Al
m
u
ll
a
is
a
tec
h
d
e
v
e
lo
p
e
r
a
t
th
e
Ce
n
ter
o
f
Co
m
p
u
tatio
n
a
t
Un
iv
e
rsit
y
o
f
A
n
b
a
r.
He
f
in
ish
e
d
h
is
P
h
.
D.
f
ro
m
Un
iv
e
rsit
y
o
f
S
o
u
t
h
Ca
r
o
li
n
a
f
ro
m
Un
it
e
d
S
tate
s
o
f
Am
e
rica
in
2
0
2
1
.
He
g
o
t
h
is
M
.
Sc
.
f
ro
m
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
Un
iv
e
rsit
y
o
f
A
n
b
a
r
in
2
0
1
1
.
He
h
a
s
p
u
b
l
ish
e
d
m
a
n
y
p
a
p
e
rs
in
d
i
ff
e
r
e
n
t
f
ield
s
a
n
d
h
is
m
a
jo
r
in
tere
st
in
im
a
g
e
p
ro
c
e
ss
in
g
a
n
d
m
a
c
h
in
e
lea
rn
in
g
,
a
n
d
d
e
e
p
lea
rn
in
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
h
u
ss
e
in
.
k
.
a
lm
u
ll
a
@u
o
a
n
b
a
r.
e
d
u
.
i
q
.
Evaluation Warning : The document was created with Spire.PDF for Python.