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.
16
,
No
.
4
,
A
u
g
u
s
t
20
26
,
p
p
.
1
755
~
1
7
6
6
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
16
i
4
.
pp
1
7
5
5
-
1
7
6
6
1755
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Im
plementa
tion
o
f
supp
o
rt
vector
ma
chine on LVM
DP
pa
nel
with
o
v
erheati
ng
pro
tect
io
n sy
ste
m
Anna
s
Si
ng
g
ih Set
iy
o
k
o
,
Di
m
a
s
P
risto
v
a
ni Ria
na
nd
a
,
A
dia
nto
S
t
u
d
y
P
r
o
g
r
a
m
o
f
M
a
r
i
n
e
E
l
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
D
e
p
a
r
t
m
e
n
t
o
f
M
a
r
i
n
e
E
l
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
S
h
i
p
b
u
i
l
d
i
n
g
I
n
st
i
t
u
t
e
o
f
P
o
l
y
t
e
c
h
n
i
c
S
u
r
a
b
a
y
a
,
S
u
r
a
b
a
y
a
,
I
n
d
o
n
e
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
3
,
2
0
2
6
R
ev
is
ed
J
u
n
1
0
,
2
0
2
6
Acc
ep
ted
J
u
l 2
2
,
2
0
2
6
El
e
c
tri
c
it
y
is
a
c
rit
ica
l
re
q
u
ire
m
e
n
t
in
i
n
d
u
strial
o
p
e
ra
ti
o
n
s,
wh
e
re
th
e
c
o
n
ti
n
u
it
y
a
n
d
sta
b
il
it
y
o
f
p
o
w
e
r
d
istri
b
u
ti
o
n
d
irec
tl
y
a
ffe
c
t
sa
fe
ty
a
n
d
p
ro
d
u
c
ti
v
it
y
.
Th
e
l
o
w
v
o
lt
a
g
e
m
a
in
d
istri
b
u
t
io
n
p
a
n
e
l
(
LVM
DP)
fu
n
c
ti
o
n
s
a
s
th
e
m
a
in
n
o
d
e
o
f
e
lec
tri
c
a
l
p
o
we
r
d
istri
b
u
ti
o
n
;
h
o
we
v
e
r,
c
o
n
v
e
n
t
io
n
a
l
LVM
DP
sy
ste
m
s
g
e
n
e
ra
ll
y
lac
k
in
telli
g
e
n
t
p
r
o
tec
ti
o
n
m
e
c
h
a
n
ism
s
c
a
p
a
b
le
o
f
d
e
tec
ti
n
g
o
v
e
rh
e
a
ti
n
g
-
re
late
d
f
ire
h
a
z
a
rd
s
a
n
d
in
i
ti
a
ti
n
g
p
re
v
e
n
t
iv
e
a
c
ti
o
n
b
e
fo
re
fa
il
u
re
o
c
c
u
rs.
Th
is
stu
d
y
p
ro
p
o
se
s
a
n
i
n
telli
g
e
n
t
m
o
n
it
o
rin
g
a
n
d
p
ro
tec
ti
o
n
sy
ste
m
fo
r
LVM
DP
p
a
n
e
ls
th
a
t
c
o
m
b
in
e
s
re
a
l
-
ti
m
e
m
u
lt
i
-
se
n
so
r
m
o
n
it
o
r
in
g
,
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(S
VM)
b
a
se
d
h
a
z
a
rd
c
las
sifica
ti
o
n
,
a
n
d
a
n
a
u
t
o
m
a
ti
c
sh
u
t
d
o
w
n
m
e
c
h
a
n
is
m
.
Th
e
m
a
in
c
o
n
tri
b
u
ti
o
n
o
f
th
is
wo
rk
l
ies
in
th
e
in
teg
ra
t
io
n
o
f
p
re
d
icti
v
e
th
e
rm
a
l
r
isk
d
e
tec
ti
o
n
wit
h
a
u
to
n
o
m
o
u
s
p
ro
tec
ti
v
e
a
c
ti
o
n
,
e
n
a
b
l
in
g
t
h
e
sy
ste
m
n
o
t
o
n
l
y
t
o
m
o
n
it
o
r
p
a
n
e
l
c
o
n
d
it
io
n
s
b
u
t
a
lso
to
re
sp
o
n
d
imm
e
d
iate
ly
t
o
h
a
z
a
rd
o
u
s
sta
tes
b
e
fo
re
t
h
e
y
e
sc
a
late
in
t
o
fire
in
c
id
e
n
ts.
S
VM
wa
s
se
lec
ted
b
e
c
a
u
se
o
f
it
s
stro
n
g
c
a
p
a
b
il
it
y
t
o
c
las
sify
c
o
m
p
lex
a
n
d
n
o
n
l
in
e
a
r
p
a
tt
e
rn
s
f
ro
m
se
n
so
r
d
a
ta
with
h
ig
h
re
li
a
b
il
it
y
.
T
h
e
d
e
v
e
lo
p
e
d
sy
ste
m
c
o
n
ti
n
u
o
u
s
ly
e
v
a
lu
a
tes
p
a
n
e
l
c
o
n
d
i
ti
o
n
s
a
n
d
tri
g
g
e
rs
a
u
to
-
sh
u
td
o
wn
w
h
e
n
a
n
o
v
e
r
h
e
a
ti
n
g
risk
is
i
d
e
n
ti
f
ied
,
t
h
e
re
b
y
i
m
p
ro
v
i
n
g
p
re
v
e
n
ti
v
e
p
r
o
tec
ti
o
n
c
o
m
p
a
re
d
with
c
o
n
v
e
n
ti
o
n
a
l
a
larm
-
b
a
se
d
m
o
n
it
o
r
in
g
sy
ste
m
s.
Ex
p
e
rime
n
tal
re
su
lt
s
sh
o
w
t
h
a
t
t
h
e
se
n
s
o
r
m
e
a
su
re
m
e
n
ts
a
c
h
iev
e
d
e
rro
r
ra
tes
m
o
stly
b
e
lo
w
5
%
c
o
m
p
a
re
d
with
c
a
li
b
ra
ted
i
n
stru
m
e
n
ts,
in
d
ica
ti
n
g
g
o
o
d
a
c
c
u
ra
c
y
.
I
n
a
d
d
it
io
n
,
t
h
e
S
VM
m
o
d
e
l
o
b
tain
e
d
a
n
o
v
e
ra
ll
a
c
c
u
ra
c
y
o
f
9
3
%
,
wit
h
a
m
a
c
ro
-
a
v
e
ra
g
e
F
1
-
sc
o
re
o
f
9
2
%
a
n
d
a
we
ig
h
ted
-
a
v
e
ra
g
e
F
1
-
sc
o
re
o
f
9
3
%
.
T
h
e
se
re
su
lt
s
d
e
m
o
n
stra
te
t
h
a
t
t
h
e
p
r
o
p
o
se
d
sy
ste
m
is
e
ffe
c
ti
v
e
fo
r
e
a
rly
d
e
tec
ti
o
n
a
n
d
a
c
ti
v
e
p
ro
tec
ti
o
n
o
f
LVM
DP
p
a
n
e
ls ag
a
in
st
o
v
e
r
h
e
a
ti
n
g
h
a
z
a
rd
s.
K
ey
w
o
r
d
s
:
Au
to
-
s
h
u
td
o
wn
L
o
w
v
o
ltag
e
m
ai
n
d
is
tr
ib
u
tio
n
p
an
el
Mo
n
ito
r
in
g
s
y
s
tem
Ov
er
h
ea
tin
g
p
r
o
tectio
n
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
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
:
Dim
as Pr
is
to
v
an
i Ri
an
an
d
a
Dep
ar
tm
en
t o
f
Ma
r
in
e
E
lectr
i
ca
l E
n
g
in
ee
r
in
g
,
Sh
ip
b
u
ild
in
g
Po
ly
tech
n
ic
I
n
s
titu
te
o
f
Su
r
ab
ay
a
St.
T
ek
n
ik
Kim
ia,
Su
k
o
lilo
,
Su
r
ab
ay
a,
E
ast J
av
a,
I
n
d
o
n
esia
E
m
ail: d
im
asp
r
is
to
v
an
i@
p
p
n
s
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
I
n
in
d
u
s
tr
ial
en
v
i
r
o
n
m
e
n
ts
,
a
s
tab
le
an
d
h
ig
h
-
ca
p
ac
ity
elec
tr
ical
s
u
p
p
ly
is
n
ee
d
ed
to
s
u
p
p
o
r
t
co
n
tin
u
o
u
s
p
r
o
ce
s
s
es,
an
d
th
e
lo
w
v
o
ltag
e
m
ain
d
is
tr
ib
u
tio
n
p
an
el
(
L
VM
DP)
s
er
v
es
as
t
h
e
ce
n
tr
al
u
n
it
f
o
r
d
is
tr
ib
u
tin
g
th
at
p
o
wer
.
B
ec
a
u
s
e
L
VM
DP
o
p
er
ates
as
a
k
ey
n
o
d
e
in
th
e
elec
tr
ical
s
y
s
tem
,
an
y
f
ailu
r
e
with
in
th
e
p
an
el
ca
n
d
is
r
u
p
t
p
r
o
d
u
cti
o
n
an
d
c
r
ea
te
s
er
io
u
s
s
af
ety
r
i
s
k
s
.
Fo
r
th
is
r
ea
s
o
n
,
a
r
eliab
le
p
r
o
tectio
n
s
y
s
tem
is
r
eq
u
ir
ed
to
r
ed
u
ce
o
p
er
atio
n
al
h
az
ar
d
s
.
Alth
o
u
g
h
s
tan
d
ar
d
p
r
ev
e
n
tiv
e
p
r
ac
tices
s
u
ch
as
lo
ad
ca
lcu
latio
n
s
,
co
m
p
o
n
en
t
s
izin
g
,
an
d
th
e
u
s
e
o
f
h
ig
h
-
q
u
ality
eq
u
ip
m
en
t
a
r
e
co
m
m
o
n
l
y
im
p
lem
en
ted
,
o
v
er
h
ea
tin
g
r
e
m
ain
s
o
n
e
o
f
th
e
m
ajo
r
ca
u
s
es o
f
f
ail
u
r
e
in
in
d
u
s
tr
ial
elec
tr
ical
p
an
els [
1
]
,
[
2
]
.
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.
16
,
No
.
4
,
Au
g
u
s
t
20
26
:
1
7
5
5
-
1
766
1756
T
ec
h
n
ical
s
tan
d
ar
d
s
in
d
icate
th
at
elec
tr
ical
p
an
el
o
p
er
atin
g
co
n
d
itio
n
s
m
u
s
t
r
em
ain
with
in
s
af
e
lim
its
.
Acc
o
r
d
in
g
to
B
S
E
N
6
0
4
3
9
,
s
af
e
o
p
er
atin
g
tem
p
e
r
atu
r
es
f
o
r
elec
tr
ical
p
an
els
g
en
e
r
ally
r
an
g
e
b
etwe
en
50
–
5
5
°C
,
wh
ile
SP
L
N
D3
.
0
2
0
-
1
:2
0
1
9
r
e
g
u
lates
ac
ce
p
ta
b
le
h
u
m
id
ity
co
n
d
itio
n
s
.
W
h
en
th
ese
lim
its
ar
e
ex
ce
ed
ed
,
th
e
r
is
k
o
f
in
s
u
la
tio
n
d
eg
r
ad
atio
n
,
co
m
p
o
n
e
n
t
m
alf
u
n
ctio
n
,
s
h
o
r
t
cir
cu
its
,
an
d
f
ir
e
in
cr
ea
s
es
s
ig
n
if
ican
tly
[
3
]
-
[
5
]
.
Pre
v
io
u
s
s
tu
d
ies
h
av
e
p
r
o
p
o
s
ed
I
n
ter
n
et
o
f
T
h
in
g
s
(
I
o
T
)
-
b
ased
s
y
s
tem
s
f
o
r
m
o
n
ito
r
in
g
t
em
p
er
atu
r
e
an
d
h
u
m
id
ity
in
ap
p
licatio
n
s
s
u
ch
as
s
er
v
er
r
o
o
m
s
,
air
c
o
m
p
r
ess
o
r
s
,
a
n
d
2
0
k
V
cu
b
i
cles
[
6
]
-
[
1
0
]
.
T
h
ese
wo
r
k
s
d
em
o
n
s
tr
ate
th
e
v
alu
e
o
f
r
ea
l
-
tim
e
m
o
n
ito
r
i
n
g
f
o
r
i
m
p
r
o
v
i
n
g
o
p
er
atio
n
al
awa
r
en
ess
.
Ho
wev
er
,
m
o
s
t
ex
is
tin
g
s
y
s
tem
s
p
r
im
ar
ily
f
o
cu
s
o
n
m
o
n
ito
r
in
g
o
n
ly
,
m
ea
n
in
g
t
h
at
th
e
y
p
r
o
v
id
e
in
f
o
r
m
atio
n
o
r
alar
m
s
with
o
u
t
d
ir
ec
tly
p
er
f
o
r
m
in
g
p
r
o
tectiv
e
ac
tio
n
wh
en
h
az
ar
d
o
u
s
co
n
d
itio
n
s
o
cc
u
r
.
I
n
ad
d
it
io
n
,
m
an
y
o
f
th
ese
s
y
s
tem
s
r
ely
o
n
DHT
s
en
s
o
r
s
an
d
E
SP
8
2
6
6
-
b
ased
p
latf
o
r
m
s
,
wh
ich
ar
e
s
u
itab
le
f
o
r
g
en
er
al
m
o
n
ito
r
in
g
ap
p
licatio
n
s
b
u
t
m
a
y
b
e
lim
it
ed
in
m
ea
s
u
r
em
e
n
t
ac
cu
r
ac
y
,
en
v
ir
o
n
m
en
tal
r
o
b
u
s
tn
ess
,
an
d
co
n
tr
o
l
r
eliab
ilit
y
f
o
r
in
d
u
s
tr
ial
L
VM
DP e
n
v
ir
o
n
m
en
ts
[
4
]
.
Mo
r
e
im
p
o
r
tan
tly
,
p
r
io
r
s
tu
d
ies g
en
e
r
ally
d
o
n
o
t
ad
d
r
ess
th
e
s
p
ec
if
ic
n
ee
d
s
o
f
L
VM
DP
p
an
els,
wh
er
e
o
v
e
r
h
ea
tin
g
m
u
s
t
b
e
d
etec
ted
with
s
u
f
f
icien
t
p
r
ec
is
io
n
a
n
d
f
o
llo
wed
b
y
an
im
m
ed
iate
r
esp
o
n
s
e
to
p
r
ev
e
n
t e
s
ca
latio
n
in
to
f
ir
e
o
r
s
ev
er
e
e
q
u
ip
m
en
t
d
am
ag
e.
T
h
is
lim
itatio
n
r
ev
ea
ls
a
clea
r
r
esear
ch
g
ap
.
E
x
is
tin
g
s
tu
d
ie
s
h
av
e
s
h
o
w
n
th
at
I
o
T
-
b
ased
m
o
n
ito
r
in
g
ca
n
ca
p
tu
r
e
th
er
m
al
an
d
en
v
ir
o
n
m
en
tal
p
ar
am
eter
s
,
b
u
t
th
e
y
h
av
e
n
o
t
a
d
eq
u
atel
y
in
teg
r
a
ted
th
r
ee
im
p
o
r
tan
t
asp
ec
ts
in
to
a
s
in
g
le
L
VM
DP
p
r
o
tectio
n
f
r
am
ewo
r
k
:
h
ig
h
-
ac
cu
r
ac
y
s
en
s
in
g
,
in
d
u
s
tr
ial
-
g
r
ad
e
co
n
tr
o
l
r
eliab
ilit
y
,
an
d
in
tellig
en
t
d
ec
i
s
io
n
-
m
ak
in
g
f
o
r
a
u
to
n
o
m
o
u
s
p
r
o
tectio
n
.
I
n
o
t
h
er
wo
r
d
s
,
p
r
ev
io
u
s
s
y
s
tem
s
ar
e
g
en
er
ally
u
n
ab
le
to
m
o
v
e
b
e
y
o
n
d
p
ass
iv
e
o
b
s
er
v
atio
n
to
war
d
ac
tiv
e
p
r
ev
en
tio
n
.
L
i
k
e
wis
e,
co
n
v
en
tio
n
al
p
r
o
tectio
n
m
eth
o
d
s
in
p
an
els
o
f
ten
d
ep
en
d
o
n
s
im
p
le
th
r
esh
o
ld
-
b
ased
alar
m
s
o
r
o
v
e
r
lo
a
d
r
elay
s
,
wh
ich
m
ay
n
o
t
ca
p
tu
r
e
m
o
r
e
co
m
p
lex
r
el
atio
n
s
h
ip
s
b
etwe
en
tem
p
er
atu
r
e,
h
u
m
id
ity
,
a
n
d
h
az
a
r
d
o
u
s
o
p
er
atin
g
s
tates.
As
a
r
esu
lt,
d
an
g
er
o
u
s
co
n
d
itio
n
s
m
ay
s
till
p
r
o
g
r
ess
b
ef
o
r
e
ef
f
ec
ti
v
e
in
ter
v
en
tio
n
o
cc
u
r
s
[
2
]
,
[
3
]
,
[
1
0
]
-
[
1
2
]
.
T
h
e
m
ain
co
n
tr
ib
u
tio
n
o
f
t
h
is
s
tu
d
y
is
th
e
d
ev
elo
p
m
en
t
o
f
a
n
I
n
tellig
en
t
Au
to
-
Sh
u
td
o
w
n
s
y
s
tem
f
o
r
L
VM
DP
p
an
els.
Un
lik
e
p
r
e
v
io
u
s
m
o
n
ito
r
in
g
s
y
s
tem
s
th
at
s
to
p
at
v
is
u
aliza
tio
n
o
r
alar
m
n
o
tific
atio
n
,
t
h
e
p
r
o
p
o
s
ed
s
y
s
tem
in
teg
r
ates
ac
cu
r
ate
s
en
s
in
g
,
PLC
-
b
ased
co
n
tr
o
l,
an
d
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM)
-
b
ased
class
if
icatio
n
to
en
ab
le
a
u
to
m
atic
d
is
co
n
n
ec
tio
n
o
f
th
e
p
o
w
er
s
u
p
p
ly
wh
en
d
an
g
er
o
u
s
o
v
er
h
ea
tin
g
c
o
n
d
itio
n
s
ar
e
d
etec
ted
.
T
h
er
ef
o
r
e,
th
is
r
esear
ch
d
o
es
n
o
t
o
n
ly
m
o
n
ito
r
p
an
el
co
n
d
itio
n
s
in
r
ea
l
tim
e,
b
u
t
also
clo
s
es
th
e
g
ap
b
etwe
en
d
etec
tio
n
an
d
p
r
o
tectio
n
b
y
p
r
o
v
i
d
in
g
an
ac
ti
v
e,
in
tellig
en
t,
an
d
p
r
ev
e
n
tiv
e
s
af
ety
m
ec
h
an
is
m
.
T
h
is
co
n
tr
ib
u
tio
n
is
ex
p
ec
ted
to
im
p
r
o
v
e
o
p
er
atio
n
al
s
af
ety
,
r
ed
u
ce
d
o
wn
tim
e,
a
n
d
in
cr
ea
s
e
th
e
r
eliab
ilit
y
o
f
L
VM
DP sy
s
tem
s
in
in
d
u
s
tr
ial
en
v
ir
o
n
m
en
ts
[
1
3
]
-
[
1
6
]
.
2.
M
E
T
H
O
D
T
h
is
ch
ap
ter
o
u
tlin
es
th
e
r
e
s
ea
r
ch
f
r
am
ewo
r
k
a
n
d
tech
n
ical
p
r
o
ce
d
u
r
es
u
s
ed
to
d
e
v
elo
p
th
e
m
o
n
ito
r
in
g
an
d
p
r
o
tectio
n
s
y
s
tem
,
in
clu
d
in
g
p
r
o
b
lem
id
en
ti
f
icatio
n
,
s
y
s
tem
an
aly
s
is
,
h
ar
d
war
e
an
d
s
o
f
twar
e
d
esig
n
,
SVM
im
p
lem
en
tatio
n
,
an
d
p
r
o
to
ty
p
e
test
in
g
.
2
.
1
.
Resea
rc
h
f
ra
m
ewo
r
k
T
h
e
r
esear
ch
m
eth
o
d
o
l
o
g
y
is
d
esig
n
ed
as
a
s
y
s
tem
atic
p
r
o
ce
s
s
to
d
ev
elo
p
a
n
a
d
v
an
ce
d
p
r
o
tectio
n
s
y
s
tem
f
o
r
th
e
L
VM
DP
at
B
u
ild
in
g
J
,
Sh
ip
b
u
ild
in
g
I
n
s
titu
te
o
f
Po
ly
tech
n
ic
Su
r
a
b
ay
a.
T
h
is
L
VM
DP
was
s
elec
ted
d
u
e
to
its
cr
itical
r
o
le
in
s
u
p
p
ly
in
g
p
o
wer
to
a
ca
d
em
ic
an
d
in
d
u
s
tr
ial
lo
ad
s
,
wh
er
e
f
ailu
r
es
o
r
o
v
er
h
ea
tin
g
co
u
l
d
ca
u
s
e
s
ig
n
if
ican
t o
p
er
atio
n
al
d
is
r
u
p
tio
n
s
[
1
]
,
[
1
2
]
.
T
h
e
n
ex
t
s
tag
e
in
v
o
lv
es
d
ef
in
in
g
s
y
s
tem
r
eq
u
ir
em
en
ts
,
in
clu
d
in
g
k
ey
p
ar
am
eter
s
s
u
ch
as
tem
p
er
atu
r
e,
h
u
m
id
ity
,
an
d
b
u
s
b
ar
th
er
m
al
c
o
n
d
itio
n
s
,
as
well
as
th
e
s
elec
tio
n
o
f
ap
p
r
o
p
r
iate
h
ar
d
war
e
co
m
p
o
n
en
ts
.
A
k
ey
co
n
tr
ib
u
t
io
n
o
f
th
is
p
h
ase
is
th
e
im
p
lem
en
tatio
n
o
f
th
e
SVM
alg
o
r
ith
m
to
im
p
r
o
v
e
class
if
icatio
n
ac
cu
r
ac
y
an
d
r
e
d
u
ce
f
alse f
au
lt d
etec
tio
n
[
1
4
]
-
[
1
8
]
.
Su
b
s
eq
u
en
tly
,
h
ar
d
war
e
–
s
o
f
t
war
e
in
teg
r
atio
n
an
d
f
u
n
ctio
n
al
test
in
g
ar
e
co
n
d
u
cted
u
n
d
e
r
s
im
u
lated
o
p
er
atin
g
co
n
d
itio
n
s
.
A
n
y
id
e
n
tifie
d
is
s
u
es
ar
e
ad
d
r
ess
ed
th
r
o
u
g
h
iter
ativ
e
test
in
g
an
d
r
ef
in
em
en
t
t
o
e
n
s
u
r
e
s
y
s
tem
r
o
b
u
s
tn
ess
.
T
h
e
f
i
n
al
s
tag
e
f
o
cu
s
es
o
n
d
ata
ac
q
u
is
itio
n
an
d
p
e
r
f
o
r
m
an
ce
e
v
alu
atio
n
,
ass
ess
in
g
s
en
s
o
r
ac
cu
r
ac
y
an
d
t
h
e
ef
f
ec
tiv
en
ess
o
f
th
e
SVM
-
b
ased
au
to
-
s
h
u
td
o
wn
m
ec
h
an
is
m
in
p
r
ev
en
tin
g
L
VM
DP
o
v
er
h
ea
tin
g
.
T
h
e
o
v
er
all
r
esear
ch
wo
r
k
f
lo
w
is
s
u
m
m
ar
ized
i
n
Fig
u
r
e
1
.
2
.
2
.
P
ro
po
s
ed
s
y
s
t
em
a
rc
hite
ct
ure
T
h
e
p
r
o
p
o
s
ed
s
y
s
tem
ar
ch
it
ec
tu
r
e
was
d
esig
n
ed
to
c
o
m
b
in
e
ac
cu
r
ate
m
u
lti
-
s
en
s
o
r
m
o
n
ito
r
in
g
,
in
tellig
en
t
class
if
icatio
n
,
an
d
r
eliab
le
in
d
u
s
tr
ial
co
n
tr
o
l
f
o
r
L
VM
DP
p
r
o
tectio
n
.
As
s
h
o
wn
in
Fig
u
r
e
2
,
th
is
lay
er
ed
d
esig
n
was
s
elec
ted
t
o
s
ep
ar
ate
d
ata
ac
q
u
is
itio
n
,
d
ec
is
io
n
-
m
ak
in
g
,
an
d
ac
tu
atio
n
f
u
n
ctio
n
s
,
th
er
e
b
y
im
p
r
o
v
in
g
m
o
d
u
lar
ity
,
m
ain
ta
in
ab
ilit
y
,
an
d
r
eliab
ilit
y
in
in
d
u
s
tr
ial
o
p
er
atio
n
[
6
]
,
[
1
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
I
mp
leme
n
ta
tio
n
o
f su
p
p
o
r
t v
e
cto
r
ma
ch
in
e
o
n
LVMDP
p
a
n
e
l wi
th
…
(
A
n
n
a
s
S
in
g
g
ih
S
etiyo
ko
)
1757
Fig
u
r
e
1
.
Flo
wch
ar
t
o
f
th
e
r
esear
ch
m
eth
o
d
o
lo
g
y
Fig
u
r
e
2
.
B
lo
ck
d
iag
r
am
o
f
th
e
p
r
o
p
o
s
ed
m
o
n
ito
r
in
g
an
d
p
r
o
tectio
n
s
y
s
tem
At
th
e
in
p
u
t
s
en
s
in
g
lay
er
,
s
ev
er
al
s
en
s
o
r
s
ar
e
in
s
talled
to
m
o
n
ito
r
th
e
m
ain
p
a
r
am
eter
s
r
elate
d
to
o
v
er
h
ea
tin
g
r
is
k
in
s
id
e
th
e
L
VM
DP.
A
B
ME
2
8
0
s
en
s
o
r
is
u
s
ed
to
m
ea
s
u
r
e
i
n
ter
n
al
p
a
n
el
tem
p
er
atu
r
e
a
n
d
h
u
m
id
ity
,
an
MQ
-
2
s
en
s
o
r
is
u
s
ed
to
d
etec
t
s
m
o
k
e
co
n
ce
n
tr
atio
n
,
an
NT
C
s
en
s
o
r
an
d
th
r
ee
ML
X9
0
6
1
4
s
en
s
o
r
s
ar
e
u
s
ed
to
m
o
n
ito
r
b
u
s
b
ar
an
d
h
o
ts
p
o
t
tem
p
er
atu
r
es,
an
d
a
PZE
M
-
0
0
4
T
s
en
s
o
r
is
u
s
ed
to
o
b
s
er
v
e
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.
16
,
No
.
4
,
Au
g
u
s
t
20
26
:
1
7
5
5
-
1
766
1758
elec
tr
ical
p
ar
am
eter
s
ass
o
ciat
ed
with
l
o
ad
c
o
n
d
itio
n
s
.
T
h
e
u
s
e
o
f
m
u
ltip
le
s
en
s
o
r
s
is
im
p
o
r
tan
t
b
ec
au
s
e
o
v
er
h
ea
tin
g
in
L
VM
DP
p
an
e
ls
is
n
o
t
ca
u
s
ed
b
y
a
s
in
g
le
v
ar
iab
le
o
n
ly
,
b
u
t
r
at
h
er
b
y
th
e
in
ter
ac
tio
n
o
f
th
er
m
al,
en
v
ir
o
n
m
e
n
tal,
an
d
e
lectr
ical
co
n
d
itio
n
s
.
T
h
er
ef
o
r
e
,
th
e
p
r
o
p
o
s
ed
ar
ch
itectu
r
e
u
s
es
m
u
lti
-
p
ar
am
eter
m
o
n
ito
r
in
g
to
o
b
tain
a
m
o
r
e
r
ep
r
esen
tativ
e
d
escr
ip
tio
n
o
f
th
e
ac
tu
al
p
an
el
co
n
d
itio
n
[
4
]
,
[
7
]
,
[
1
1
]
.
T
h
e
s
en
s
o
r
s
ig
n
als
ar
e
co
llected
b
y
th
e
E
SP
3
2
m
icr
o
co
n
tr
o
ller
,
wh
ich
ac
ts
as
th
e
d
ata
ac
q
u
is
itio
n
u
n
it
an
d
I
o
T
g
atew
ay
.
Fo
r
th
is
r
ea
s
o
n
,
th
e
f
in
al
ac
tu
atio
n
lay
er
is
h
an
d
led
b
y
a
PLC
F
X3
U
-
2
4
MR,
wh
ich
s
er
v
es
as
th
e
m
ain
in
d
u
s
tr
ial
co
n
tr
o
ller
.
I
n
a
d
d
iti
o
n
,
th
e
PLC
p
r
o
v
id
es
a
m
o
r
e
s
u
itab
le
p
latf
o
r
m
f
o
r
f
ail
-
s
af
e
lo
g
ic,
in
ter
lo
ck
i
n
g
,
an
d
ac
tu
ato
r
p
r
io
r
ity
m
a
n
ag
em
en
t
th
an
a
m
icr
o
co
n
tr
o
ller
-
o
n
ly
a
p
p
r
o
ac
h
.
C
o
m
m
u
n
ic
atio
n
b
etwe
en
th
e
E
SP
3
2
/s
er
v
er
s
id
e
an
d
th
e
PLC
is
im
p
lem
en
ted
th
r
o
u
g
h
R
S4
8
5
u
s
in
g
th
e
Mo
d
b
u
s
R
T
U
p
r
o
to
co
l,
allo
win
g
s
en
s
o
r
-
b
ased
class
if
icatio
n
r
es
u
lts
to
b
e
tr
an
s
m
itted
as
co
n
tr
o
l
co
m
m
an
d
s
i
n
a
s
tr
u
ctu
r
e
d
a
n
d
r
eliab
le
m
a
n
n
er
.
T
h
e
h
ar
d
war
e
–
s
o
f
twar
e
in
teg
r
atio
n
is
o
r
g
an
ized
as
f
o
llo
ws.
First,
th
e
E
SP
3
2
ac
q
u
ir
es
r
ea
l
-
tim
e
d
ata
f
r
o
m
all
s
en
s
o
r
s
an
d
s
en
d
s
th
e
d
ata
t
o
th
e
s
er
v
er
.
Seco
n
d
,
th
e
s
er
v
e
r
p
er
f
o
r
m
s
p
r
e
p
r
o
ce
s
s
in
g
a
n
d
ex
ec
u
tes
th
e
SVM
class
if
icatio
n
m
o
d
el
to
d
eter
m
in
e
th
e
c
u
r
r
en
t
o
p
e
r
atin
g
s
tate
o
f
th
e
L
VM
DP.
T
h
ir
d
,
th
e
class
if
icatio
n
r
esu
lt
is
tr
an
s
m
itted
b
ac
k
to
t
h
e
PLC th
r
o
u
g
h
Mo
d
b
u
s
R
T
U
co
m
m
u
n
i
ca
tio
n
.
Fin
ally
,
th
e
PLC ex
ec
u
tes th
e
ap
p
r
o
p
r
iate
ac
tu
ato
r
co
m
m
an
d
b
ased
o
n
th
e
r
ec
eiv
ed
class
.
T
h
e
co
n
tr
o
l
lo
g
ic
is
d
iv
id
e
d
in
t
o
th
r
ee
o
p
er
atin
g
r
an
g
es.
I
n
th
e
s
af
e
co
n
d
itio
n
,
all
m
ea
s
u
r
ed
p
ar
am
eter
s
r
em
ain
with
in
ac
ce
p
tab
le
lim
its
,
s
o
n
o
p
r
o
tectiv
e
ac
tio
n
is
ac
tiv
ated
.
I
n
th
e
war
n
in
g
co
n
d
itio
n
,
th
e
PLC
ac
tiv
ates
p
r
ev
en
tiv
e
ac
tu
ato
r
s
wh
en
ea
r
ly
ab
n
o
r
m
al
co
n
d
itio
n
s
ar
e
d
etec
ted
,
s
u
ch
as
tu
r
n
in
g
o
n
th
e
s
u
ctio
n
o
r
in
tak
e
f
an
wh
en
t
h
e
p
an
el
tem
p
er
atu
r
e
e
x
ce
ed
s
4
0
°C
o
r
ac
tiv
atin
g
th
e
h
ea
ter
ca
r
tr
id
g
e
wh
e
n
h
u
m
id
ity
ex
ce
e
d
s
6
5
%.
I
n
th
e
h
az
ar
d
c
o
n
d
itio
n
,
wh
e
n
t
h
e
t
em
p
er
atu
r
e
ex
ce
ed
s
55
°C
,
h
u
m
id
ity
e
x
ce
ed
s
8
5
%
,
s
m
o
k
e
is
d
etec
ted
,
o
r
b
u
s
b
a
r
o
v
er
h
ea
tin
g
is
id
en
tifie
d
,
th
e
PLC
ac
tiv
ates
th
e
s
h
u
n
t tr
ip
m
ec
h
an
is
m
to
d
is
co
n
n
ec
t th
e
p
o
wer
s
o
u
r
ce
im
m
e
d
iately
.
I
n
th
is
way
,
th
e
PLC f
u
n
ctio
n
s
n
o
t o
n
ly
as
an
ac
tu
ato
r
d
r
iv
er
b
u
t
also
as
th
e
f
in
al
ex
ec
u
tio
n
lay
er
o
f
th
e
in
tellig
en
t
p
r
o
tectio
n
s
y
s
tem
.
T
h
is
ar
ch
itectu
r
e
en
s
u
r
es
th
at
h
az
ar
d
o
u
s
co
n
d
itio
n
s
id
en
tifie
d
b
y
th
e
SVM
m
o
d
el
ca
n
b
e
tr
an
s
lated
in
to
d
ir
ec
t
p
h
y
s
ical
p
r
o
tectio
n
ac
tio
n
s
in
r
ea
l tim
e
[
1
2
]
.
2
.
3
.
Su
pp
o
rt
v
ec
t
o
r
m
a
chine
cla
s
s
if
ica
t
io
n m
et
ho
d
SVM
is
a
m
eth
o
d
u
s
ed
f
o
r
class
if
icatio
n
an
d
r
eg
r
ess
io
n
p
r
ed
ictio
n
an
d
is
d
esig
n
ed
to
g
e
n
er
alize
b
y
class
if
y
in
g
p
atter
n
s
th
at
ar
e
n
o
t
in
clu
d
ed
in
th
e
tr
ain
in
g
d
at
a,
wh
ile
m
in
im
izin
g
e
r
r
o
r
s
with
in
th
e
tr
ain
i
n
g
s
et.
I
n
th
is
h
ig
h
-
d
im
e
n
s
io
n
al
s
p
ac
e,
an
o
p
tim
al
h
y
p
er
p
la
n
e
is
d
eter
m
in
ed
to
m
ax
im
ize
t
h
e
m
ar
g
in
b
etwe
en
d
ata
class
es,
as
illu
s
tr
ated
in
Fig
u
r
e
3
.
SVM
is
em
p
lo
y
ed
as
t
h
e
class
if
icatio
n
m
eth
o
d
in
t
h
is
s
tu
d
y
.
Prio
r
to
o
b
tain
in
g
th
e
d
esire
d
class
if
icatio
n
r
esu
lts
,
th
e
i
n
p
u
t
d
ata
ar
e
p
r
o
ce
s
s
ed
u
s
in
g
th
is
m
eth
o
d
[
1
6
]
-
[
1
8
]
.
T
h
e
d
ata
co
n
s
is
t
o
f
p
ar
am
eter
v
alu
es
ac
q
u
ir
ed
f
r
o
m
s
en
s
o
r
r
ea
d
in
g
s
in
s
talled
in
th
e
L
VM
D
P
s
y
s
tem
.
T
h
e
in
p
u
t
p
ar
am
eter
s
u
s
ed
f
o
r
t
h
e
SVM
class
if
icatio
n
p
r
o
ce
s
s
ar
e
s
u
m
m
ar
ized
in
T
ab
le
1
.
T
h
e
p
r
o
ce
s
s
ed
s
en
s
o
r
d
ata
ar
e
tr
an
s
m
itted
b
y
th
e
E
SP
3
2
to
th
e
s
er
v
e
r
,
w
h
er
e
t
h
e
class
if
icatio
n
p
r
o
ce
s
s
is
p
er
f
o
r
m
e
d
.
T
h
e
SVM
m
o
d
el
class
if
ies th
e
s
y
s
tem
s
tate
in
to
f
o
u
r
o
p
er
atin
g
class
es,
as su
m
m
ar
ized
in
T
a
b
le
2.
Fig
u
r
e
3
.
SVM
aim
s
to
f
in
d
th
e
o
p
tim
al
h
y
p
er
p
lan
e
th
at
s
ep
a
r
ates th
e
two
class
es
T
ab
le
1
.
I
n
p
u
t
p
ar
am
eter
s
u
s
e
d
f
o
r
SVM
class
if
icatio
n
P
a
r
a
me
t
e
r
D
e
s
c
r
i
p
t
i
o
n
S
e
n
s
o
r
T
y
p
e
P
a
n
e
l
i
n
t
e
r
n
a
l
t
e
m
p
e
r
a
t
u
r
e
B
M
E2
8
0
P
a
n
e
l
i
n
t
e
r
n
a
l
h
u
m
i
d
i
t
y
B
M
E2
8
0
P
r
o
t
o
t
y
p
e
p
a
n
e
l
b
u
s
b
a
r
t
e
mp
e
r
a
t
u
r
e
N
TC
LV
M
D
P
p
a
n
e
l
b
u
s
b
a
r
t
e
mp
e
r
a
t
u
r
e
M
LX
9
0
6
1
4
(
×
3
)
S
mo
k
e
c
o
n
c
e
n
t
r
a
t
i
o
n
MQ
-
2
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
I
mp
leme
n
ta
tio
n
o
f su
p
p
o
r
t v
e
cto
r
ma
ch
in
e
o
n
LVMDP
p
a
n
e
l wi
th
…
(
A
n
n
a
s
S
in
g
g
ih
S
etiyo
ko
)
1759
T
ab
le
2
.
C
lass
if
icatio
n
class
es
f
o
r
th
e
SVM
-
b
ased
p
r
o
tectio
n
s
y
s
tem
C
l
a
s
s
O
p
e
r
a
t
i
n
g
C
o
n
d
i
t
i
o
n
D
e
scri
p
t
i
o
n
1
F
a
n
a
c
t
i
v
a
t
i
o
n
Th
e
c
o
o
l
i
n
g
f
a
n
i
s a
c
t
i
v
a
t
e
d
w
h
e
n
t
h
e
i
n
t
e
r
n
a
l
p
a
n
e
l
t
e
mp
e
r
a
t
u
r
e
e
x
c
e
e
d
s t
h
e
p
r
e
d
e
f
i
n
e
d
s
e
t
p
o
i
n
t
2
H
e
a
t
e
r
c
a
r
t
r
i
d
g
e
a
c
t
i
v
a
t
i
o
n
Th
e
h
e
a
t
e
r
c
a
r
t
r
i
d
g
e
i
s
a
c
t
i
v
a
t
e
d
w
h
e
n
t
h
e
i
n
t
e
r
n
a
l
p
a
n
e
l
h
u
m
i
d
i
t
y
e
x
c
e
e
d
s
t
h
e
p
r
e
d
e
f
i
n
e
d
s
e
t
p
o
i
n
t
3
N
o
r
mal
c
o
n
d
i
t
i
o
n
A
l
l
s
e
n
s
o
r
p
a
r
a
met
e
r
s i
n
d
i
c
a
t
e
s
a
f
e
o
p
e
r
a
t
i
n
g
c
o
n
d
i
t
i
o
n
s
a
n
d
d
o
n
o
t
e
x
c
e
e
d
t
h
e
p
r
e
d
e
f
i
n
e
d
s
e
t
p
o
i
n
t
s,
i
n
d
i
c
a
t
i
n
g
n
o
p
o
t
e
n
t
i
a
l
a
b
n
o
r
ma
l
e
v
e
n
t
s
4
S
h
u
n
t
t
r
i
p
a
c
t
i
v
a
t
i
o
n
Th
e
sh
u
n
t
t
r
i
p
i
s
a
c
t
i
v
a
t
e
d
w
h
e
n
m
u
l
t
i
p
l
e
se
n
s
o
r
p
a
r
a
m
e
t
e
r
s e
x
c
e
e
d
t
h
e
p
r
e
d
e
f
i
n
e
d
s
e
t
p
o
i
n
t
s,
i
n
d
i
c
a
t
i
n
g
a
p
o
t
e
n
t
i
a
l
l
y
h
a
z
a
r
d
o
u
s
c
o
n
d
i
t
i
o
n
s
u
c
h
a
s f
i
r
e
Af
ter
th
e
class
if
icatio
n
r
esu
lts
ar
e
o
b
tain
ed
,
th
e
class
if
ied
d
ata
ar
e
tr
an
s
m
itted
t
o
th
e
p
r
o
g
r
am
m
ab
le
lo
g
ic
co
n
tr
o
ller
(
PLC)
v
ia
th
e
Mo
d
b
u
s
R
T
U
co
m
m
u
n
icatio
n
p
r
o
to
c
o
l
to
co
n
tr
o
l
ea
ch
ac
t
u
ato
r
ac
co
r
d
in
g
to
th
e
id
en
tifie
d
o
p
er
atin
g
co
n
d
i
tio
n
.
T
h
e
o
v
er
all
d
ata
p
r
o
ce
s
s
in
g
an
d
class
if
icatio
n
wo
r
k
f
lo
w
u
s
in
g
th
e
SVM
m
eth
o
d
is
ex
ec
u
ted
o
n
th
e
s
er
v
er
a
n
d
co
n
s
is
ts
o
f
s
ev
er
al
e
s
s
en
tial
s
tag
es,
as
illu
s
tr
ated
in
th
e
s
y
s
tem
b
lo
ck
d
iag
r
am
.
T
h
e
o
v
er
all
wo
r
k
f
lo
w
o
f
th
e
SVM
-
b
ased
d
ata
p
r
o
ce
s
s
in
g
an
d
class
if
icatio
n
s
y
s
tem
is
illu
s
tr
ated
in
Fig
u
r
e
4
.
Fig
u
r
e
4
.
T
h
e
f
lo
wch
a
r
t
o
f
t
h
e
SVM
-
b
ased
d
ata
p
r
o
ce
s
s
in
g
a
n
d
class
if
icatio
n
s
y
s
tem
T
h
e
p
r
o
ce
s
s
b
eg
in
s
with
d
ata
ac
q
u
is
itio
n
,
wh
er
e
s
en
s
o
r
d
ata
ar
e
c
o
llected
a
n
d
o
r
g
a
n
ized
f
o
r
tr
ain
i
n
g
an
d
test
in
g
.
T
h
e
d
ataset
in
clu
d
es
tem
p
er
atu
r
e
an
d
h
u
m
id
ity
f
r
o
m
th
e
B
ME
2
8
0
s
en
s
o
r
,
b
u
s
-
b
ar
tem
p
er
atu
r
es
f
r
o
m
NT
C
a
n
d
ML
X
9
0
6
1
4
s
en
s
o
r
s
,
elec
tr
ical
p
ar
a
m
eter
s
f
r
o
m
th
e
PZE
M
s
en
s
o
r
,
an
d
s
m
o
k
e
c
o
n
ce
n
tr
atio
n
f
r
o
m
th
e
MQ
-
2
s
en
s
o
r
.
T
h
e
d
ata
ar
e
th
en
d
iv
id
ed
in
to
tr
ain
in
g
an
d
test
in
g
s
ets.
Nex
t,
d
at
a
p
r
ep
r
o
ce
s
s
in
g
is
p
er
f
o
r
m
ed
to
im
p
r
o
v
e
d
ata
q
u
ality
th
r
o
u
g
h
clea
n
in
g
,
n
o
r
m
aliza
tio
n
,
an
d
f
ea
tu
r
e
t
r
an
s
f
o
r
m
atio
n
.
T
h
e
p
r
o
ce
s
s
ed
d
ata
ar
e
lab
eled
ac
co
r
d
in
g
t
o
s
y
s
tem
o
p
er
ati
n
g
co
n
d
itio
n
s
,
in
clu
d
i
n
g
n
o
r
m
al
o
p
er
atio
n
,
f
an
ac
tiv
atio
n
,
h
ea
ter
ca
r
tr
id
g
e
ac
tiv
atio
n
,
an
d
s
h
u
n
t
tr
ip
ac
tiv
at
io
n
,
wh
ich
s
er
v
e
as
tar
g
et
class
es
f
o
r
s
u
p
er
v
is
ed
lear
n
in
g
.
T
h
e
lab
eled
d
ata
ar
e
u
s
ed
to
tr
ain
a
SVM
m
o
d
el,
wh
er
e
th
e
o
p
tim
al
s
ep
ar
atin
g
h
y
p
er
p
lan
e
is
d
eter
m
in
ed
t
o
class
if
y
o
p
er
a
tin
g
co
n
d
itio
n
s
[
3
]
,
[
1
5
]
.
T
wo
k
er
n
el
f
u
n
ctio
n
s
ar
e
ap
p
lied
:
A
r
ad
ial
b
asis
f
u
n
ctio
n
(
R
B
F)
k
er
n
el
f
o
r
f
u
l
l
d
ataset
class
if
icatio
n
an
d
a
lin
ea
r
k
er
n
el
f
o
r
s
im
p
lifie
d
a
n
aly
s
is
an
d
m
o
d
el
in
ter
p
r
etatio
n
.
Th
at
k
er
n
el
was
u
s
ed
as
th
e
p
r
im
ar
y
k
e
r
n
el
b
ec
au
s
e
th
e
r
elatio
n
s
h
ip
a
m
o
n
g
tem
p
er
atu
r
e,
h
u
m
id
ity
,
s
m
o
k
e,
an
d
b
u
s
b
ar
tem
p
er
atu
r
e
is
n
o
n
lin
ea
r
an
d
ca
n
n
o
t
b
e
a
d
eq
u
ately
r
ep
r
e
s
en
ted
b
y
a
s
im
p
le
lin
ea
r
d
ec
is
io
n
b
o
u
n
d
ar
y
[
3
]
.
I
n
p
r
ac
tical
L
VM
DP
o
p
er
atio
n
,
h
az
ar
d
o
u
s
co
n
d
itio
n
s
d
o
n
o
t
alwa
y
s
ar
is
e
f
r
o
m
o
n
e
v
a
r
iab
le
in
d
ep
en
d
en
tly
;
i
n
s
tead
,
th
ey
o
f
ten
r
esu
lt
f
r
o
m
c
o
m
b
in
ed
m
o
d
er
ate
in
c
r
ea
s
es
in
s
ev
er
al
v
ar
iab
les.
T
h
e
R
B
F
k
er
n
el
is
th
er
ef
o
r
e
ap
p
r
o
p
r
iate
b
ec
au
s
e
it
ca
n
m
ap
th
e
in
p
u
t
f
ea
t
u
r
es
in
to
a
h
ig
h
er
-
d
im
en
s
io
n
al
s
p
ac
e
an
d
co
n
s
tr
u
ct
a
m
o
r
e
f
lex
ib
le
b
o
u
n
d
a
r
y
b
etwe
en
o
p
er
atin
g
class
es.
Fo
r
co
m
p
ar
i
s
o
n
an
d
s
im
p
lifie
d
in
ter
p
r
etatio
n
,
a
lin
ea
r
k
er
n
el
m
ay
also
b
e
u
s
ed
as
a
b
aselin
e
m
o
d
el;
h
o
wev
er
,
th
e
R
B
F
k
er
n
el
was
p
r
io
r
itized
b
ec
au
s
e
it b
etter
r
ef
lects th
e
c
o
m
p
lex
in
ter
ac
ti
o
n
o
f
L
VM
DP o
p
er
atin
g
p
ar
am
eter
s
.
T
o
o
b
tain
th
e
b
est
class
if
ic
atio
n
p
er
f
o
r
m
an
ce
,
th
e
m
ai
n
SVM
h
y
p
er
p
a
r
am
eter
s
,
n
am
ely
th
e
r
eg
u
lar
izatio
n
p
ar
am
ete
r
C
a
n
d
k
e
r
n
el
p
ar
am
eter
g
am
m
a
(
γ
)
,
wer
e
tu
n
e
d
d
u
r
in
g
m
o
d
el
d
ev
elo
p
m
en
t.
T
h
e
p
ar
am
eter
C
co
n
tr
o
ls
th
e
tr
a
d
e
-
o
f
f
b
etwe
en
m
ax
im
izin
g
t
h
e
m
ar
g
in
an
d
m
in
im
izin
g
class
if
icatio
n
er
r
o
r
,
wh
ile
g
am
m
a
co
n
tr
o
ls
th
e
in
f
lu
en
ce
r
an
g
e
o
f
ea
c
h
tr
ain
in
g
s
am
p
le
in
th
e
R
B
F
k
er
n
el.
A
lo
w
C
m
ay
p
r
o
d
u
ce
a
wid
er
m
ar
g
in
b
u
t
h
ig
h
er
tr
ai
n
in
g
e
r
r
o
r
,
wh
er
ea
s
a
h
i
g
h
C
m
ay
im
p
r
o
v
e
t
r
ain
in
g
f
it
b
u
t
in
cr
ea
s
e
th
e
r
is
k
o
f
o
v
er
f
itti
n
g
.
Similar
ly
,
an
ex
ce
s
s
iv
ely
lar
g
e
g
am
m
a
m
ay
p
r
o
d
u
ce
an
o
v
e
r
ly
co
m
p
lex
d
ec
is
io
n
b
o
u
n
d
ar
y
,
wh
ile
an
ex
ce
s
s
iv
ely
s
m
all
g
am
m
a
m
ay
f
ail
to
ca
p
tu
r
e
im
p
o
r
ta
n
t
n
o
n
lin
ea
r
p
atter
n
s
.
T
h
er
ef
o
r
e,
h
y
p
e
r
p
ar
am
eter
tu
n
in
g
was c
o
n
d
u
cted
to
id
en
t
if
y
th
e
p
ar
am
eter
c
o
m
b
in
atio
n
th
at
g
iv
es th
e
b
est b
alan
ce
b
etwe
en
ac
cu
r
ac
y
an
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.
16
,
No
.
4
,
Au
g
u
s
t
20
26
:
1
7
5
5
-
1
766
1760
g
en
er
aliza
tio
n
.
T
h
e
o
p
tim
al
p
ar
am
eter
s
wer
e
s
elec
ted
b
ased
o
n
ev
alu
atio
n
r
esu
lts
f
r
o
m
th
e
tr
ain
in
g
an
d
test
in
g
p
r
o
ce
s
s
,
with
em
p
h
asis
o
n
ac
cu
r
ac
y
,
F1
-
s
co
r
e,
an
d
r
e
d
u
ctio
n
o
f
f
alse h
az
ar
d
class
if
icatio
n
[
2
]
,
[
15
].
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3.
1
.
Da
t
a
c
o
llect
io
n
T
h
e
im
p
lem
en
tatio
n
o
f
th
e
S
VM
m
eth
o
d
b
eg
in
s
with
d
ata
ac
q
u
is
itio
n
f
r
o
m
s
ev
en
k
ey
p
ar
am
eter
s
m
ea
s
u
r
ed
b
y
in
s
talled
s
en
s
o
r
s
,
in
clu
d
i
n
g
a
B
ME
2
8
0
s
en
s
o
r
f
o
r
tem
p
er
atu
r
e
an
d
h
u
m
id
ity
,
th
r
ee
ML
X9
0
6
1
4
s
en
s
o
r
s
f
o
r
o
b
ject
tem
p
er
atu
r
e
,
an
NT
C
s
en
s
o
r
f
o
r
th
er
m
al
d
etec
tio
n
,
an
d
an
MQ
-
2
s
en
s
o
r
f
o
r
s
m
o
k
e
d
e
n
s
ity
.
T
h
e
co
llected
d
ataset
co
n
s
is
ts
o
f
1
2
5
s
am
p
les an
d
is
d
iv
id
ed
in
to
8
0
% tr
ain
in
g
d
ata
an
d
2
0
% test
in
g
d
ata.
T
h
e
o
v
er
all
d
ata
d
is
tr
ib
u
ti
o
n
is
s
h
o
wn
in
T
ab
le
3
.
T
ab
le
3
.
Data
co
llectio
n
b
y
s
e
n
s
o
r
s
Ti
me
Te
mp
1
Te
mp
2
M
B
M
MC
M
B
Z
MX
S
mo
k
e
S
t
a
t
u
s
15
-
05
-
2
5
1
7
:
3
4
2
9
.
1
7
8
6
.
5
3
2
4
.
2
2
2
5
.
2
9
2
9
.
7
3
3
0
.
1
5
4
3
5
S
H
U
N
T
TR
I
P
15
-
05
-
2
5
1
7
:
3
3
2
9
.
1
6
8
8
.
5
2
2
4
.
2
1
2
5
.
2
9
2
9
.
7
3
3
0
.
1
5
4
3
5
S
H
U
N
T
TR
I
P
⁞
⁞
⁞
⁞
⁞
⁞
⁞
⁞
⁞
15
-
05
-
2
5
1
7
:
2
8
2
9
.
1
4
7
2
.
3
4
2
4
.
0
2
2
5
.
2
9
2
9
.
6
9
3
0
.
2
1
4
3
6
H
EA
TER
C
A
R
TR
I
D
G
E
O
N
15
-
05
-
2
5
1
7
:
2
7
2
9
.
1
3
7
2
.
3
9
2
4
.
0
3
2
5
.
2
9
2
9
.
6
9
3
0
.
2
1
4
3
6
H
EA
TER
C
A
R
TR
I
D
G
E
O
N
⁞
⁞
⁞
⁞
⁞
⁞
⁞
⁞
⁞
15
-
05
-
2
5
1
7
:
0
3
3
3
.
1
6
6
4
.
8
5
2
4
.
1
0
3
0
.
2
3
3
0
.
4
3
3
0
.
4
3
4
3
2
N
O
R
M
A
L
15
-
05
-
2
5
1
7
:
0
2
3
1
.
8
6
6
3
.
9
8
2
4
.
0
4
3
0
.
2
9
3
0
.
3
9
3
0
.
3
9
4
3
2
N
O
R
M
A
L
⁞
⁞
⁞
⁞
⁞
⁞
⁞
⁞
⁞
3.
2
.
Da
t
a
p
re
pro
ce
s
s
ing
T
h
e
s
u
b
s
eq
u
e
n
t
s
tag
e
in
v
o
lv
e
s
d
ata
p
r
e
p
r
o
ce
s
s
in
g
t
o
p
r
ep
a
r
e
th
e
d
ataset
f
o
r
p
r
o
ce
s
s
in
g
u
s
in
g
th
e
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
al
g
o
r
i
th
m
.
B
ef
o
r
e
p
r
ep
r
o
ce
s
s
in
g
is
p
er
f
o
r
m
ed
,
ce
r
tain
s
en
s
o
r
r
ea
d
in
g
s
ar
e
id
e
n
tifie
d
as
n
o
is
y
o
r
in
co
n
s
is
ten
t
,
as
t
h
eir
v
alu
es
d
o
n
o
t
ac
cu
r
atel
y
r
ef
lect
th
e
ac
tu
al
o
p
er
atin
g
co
n
d
itio
n
s
d
u
e
to
in
ter
n
al
d
is
tu
r
b
a
n
ce
s
in
t
h
e
s
en
s
o
r
ac
q
u
is
itio
n
p
r
o
ce
s
s
.
Fig
u
r
es
5
a
n
d
6
illu
s
tr
ate
t
h
e
tem
p
er
at
u
r
e
a
n
d
h
u
m
id
ity
s
en
s
o
r
r
ea
d
in
g
s
,
r
es
p
ec
tiv
ely
,
c
o
m
p
ar
i
n
g
th
e
r
aw
d
ata
b
ef
o
r
e
p
r
ep
r
o
ce
s
s
in
g
wi
th
th
e
f
ilter
ed
d
ata
af
ter
p
r
ep
r
o
ce
s
s
in
g
to
d
em
o
n
s
tr
ate
th
e
r
em
o
v
al
o
f
n
o
is
e.
Fig
u
r
e
5(
a
)
p
r
esen
ts
th
e
tem
p
e
r
atu
r
e
g
r
a
p
h
b
e
f
o
r
e
p
r
ep
r
o
ce
s
s
in
g
;
Fig
u
r
e
5(
b
)
p
r
e
s
en
ts
th
e
tem
p
er
atu
r
e
g
r
ap
h
a
f
ter
p
r
ep
r
o
ce
s
s
in
g
.
(
a)
(
b
)
Fig
u
r
e
5
.
T
e
m
p
er
atu
r
e
s
en
s
o
r
d
ata
s
h
o
win
g
(
a
)
th
e
g
r
ap
h
b
ef
o
r
e
p
r
e
p
r
o
ce
s
s
in
g
an
d
(
b
)
th
e
g
r
ap
h
a
f
ter
p
r
ep
r
o
ce
s
s
in
g
B
ased
o
n
th
e
an
aly
s
is
,
th
e
tem
p
er
atu
r
e
an
d
h
u
m
id
ity
d
ata
f
r
o
m
th
e
B
ME
2
8
0
s
en
s
o
r
s
h
o
w
a
m
b
ig
u
o
u
s
v
alu
es
an
d
ar
e
t
h
er
ef
o
r
e
f
ilter
ed
to
r
em
o
v
e
n
o
is
y
o
r
ir
r
elev
an
t
d
ata.
T
h
is
p
r
e
p
r
o
ce
s
s
in
g
s
tep
im
p
r
o
v
es
ac
cu
r
ac
y
an
d
o
v
e
r
all
s
y
s
tem
p
er
f
o
r
m
a
n
ce
.
T
ab
le
4
p
r
esen
ts
t
h
e
p
r
o
ce
s
s
ed
s
en
s
o
r
d
ata,
wh
ile
Fig
u
r
es
6
(
a)
an
d
Fig
u
r
es
6
(
b
)
s
h
o
w
th
e
tem
p
er
atu
r
e
an
d
h
u
m
id
ity
d
ata
a
f
ter
p
r
ep
r
o
ce
s
s
in
g
,
d
em
o
n
s
tr
atin
g
im
p
r
o
v
ed
d
ata
q
u
ality
an
d
co
n
s
is
ten
cy
.
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
I
mp
leme
n
ta
tio
n
o
f su
p
p
o
r
t v
e
cto
r
ma
ch
in
e
o
n
LVMDP
p
a
n
e
l wi
th
…
(
A
n
n
a
s
S
in
g
g
ih
S
etiyo
ko
)
1761
(
a)
(
b
)
Fig
u
r
e
6
.
Hu
m
id
ity
s
en
s
o
r
d
at
a
s
h
o
win
g
(
a)
th
e
g
r
a
p
h
b
ef
o
r
e
p
r
ep
r
o
ce
s
s
in
g
an
d
(
b
)
th
e
g
r
a
p
h
af
ter
p
r
ep
r
o
ce
s
s
in
g
T
ab
le
4
. S
en
s
o
r
d
ata
af
ter
p
r
ep
r
o
ce
s
s
in
g
Te
mp
B
M
E
H
u
mi
B
M
E
N
TC
M
LX
1
M
LX
2
M
LX
3
S
mo
k
e
S
V
M
2
9
.
1
7
8
6
.
3
0
2
4
.
2
4
2
9
.
7
5
2
9
.
6
9
3
0
.
0
9
4
3
5
S
H
U
N
T
TR
I
P
⁞
⁞
⁞
⁞
⁞
⁞
⁞
⁞
2
9
.
1
4
9
0
.
4
5
2
4
.
1
1
2
9
.
7
5
2
9
.
7
1
3
0
.
1
7
4
3
6
S
H
U
N
T
TR
I
P
2
9
.
1
3
7
2
.
3
4
2
4
.
0
2
2
9
.
8
5
2
9
.
8
3
3
0
.
2
3
4
3
6
H
EA
TER
C
A
R
TR
I
D
G
E
O
N
⁞
⁞
⁞
⁞
⁞
⁞
⁞
⁞
2
9
.
0
9
7
2
.
7
5
2
3
.
8
6
2
9
.
7
1
2
9
.
4
3
3
0
.
0
3
3
9
1
H
EA
TER
C
A
R
TR
I
D
G
E
O
N
3
1
.
9
7
6
3
.
0
2
2
4
.
3
6
3
0
.
1
1
2
9
.
9
9
3
0
.
3
3
4
3
3
N
O
R
M
A
L
3
2
.
0
5
6
3
.
4
4
2
4
.
0
8
2
9
.
8
3
2
9
.
7
9
3
0
.
0
9
4
3
5
N
O
R
M
A
L
5
5
.
1
2
6
3
.
0
2
2
4
.
2
4
2
9
.
7
5
2
9
.
6
9
3
0
.
0
9
4
3
5
S
H
U
N
T
TR
I
P
⁞
⁞
⁞
⁞
⁞
⁞
⁞
⁞
5
6
.
9
8
6
4
.
0
7
2
4
.
1
1
2
9
.
7
5
2
9
.
7
1
3
0
.
1
7
4
3
6
S
H
U
N
T
TR
I
P
4
7
.
1
2
6
3
.
6
5
2
3
.
8
8
3
0
.
6
3
2
9
.
8
5
3
2
.
7
1
4
3
5
F
A
N
O
N
⁞
⁞
⁞
⁞
⁞
⁞
⁞
⁞
4
6
.
1
3
6
2
.
8
8
2
4
.
0
1
2
9
.
6
5
2
9
.
6
3
3
0
.
0
5
4
3
4
F
A
N
O
N
3.
3
.
Da
t
a
s
et
s
pli
t
t
ing
T
h
e
d
ataset
was
d
iv
id
ed
in
to
tr
ain
in
g
an
d
test
in
g
s
u
b
s
ets,
with
8
0
%
o
f
th
e
1
2
5
s
am
p
les
u
s
ed
f
o
r
tr
ain
in
g
an
d
2
0
%
f
o
r
test
in
g
.
T
h
is
p
r
o
p
o
r
tio
n
e
n
s
u
r
es
s
u
f
f
icien
t
d
ata
f
o
r
m
o
d
el
lear
n
in
g
wh
ile
allo
win
g
ef
f
ec
tiv
e
ev
alu
atio
n
o
f
th
e
SVM’
s
ab
ilit
y
to
class
if
y
u
n
s
ee
n
d
ata.
3.
4
.
SVM
m
o
del t
ra
ini
ng
T
h
e
SVM
tr
ain
in
g
p
r
o
ce
s
s
in
v
o
lv
es
k
er
n
el
s
elec
tio
n
,
p
ar
am
e
ter
tu
n
in
g
,
a
n
d
d
eter
m
i
n
in
g
th
e
o
p
tim
al
s
ep
ar
atin
g
h
y
p
er
p
lan
e.
I
n
th
is
s
tu
d
y
,
th
e
R
B
F
k
er
n
el
is
s
ele
cted
d
u
e
to
its
s
tr
o
n
g
a
b
ilit
y
t
o
h
a
n
d
le
n
o
n
-
lin
ea
r
d
ata
an
d
m
u
ltip
le
i
n
p
u
t
f
ea
tu
r
es.
T
h
is
is
s
u
itab
le
f
o
r
th
e
s
ev
en
r
etain
e
d
f
ea
t
u
r
es
u
s
ed
i
n
th
e
m
o
d
el:
B
ME
tem
p
er
atu
r
e,
B
ME
h
u
m
i
d
ity
,
NT
C
tem
p
er
atu
r
e,
ML
X1
,
ML
X2
,
ML
X3
tem
p
er
atu
r
es,
an
d
MQ
-
2
s
m
o
k
e
co
n
ce
n
tr
atio
n
.
Fo
r
m
an
u
al
ill
u
s
tr
atio
n
o
f
t
h
e
SVM
p
r
o
ce
s
s
,
a
lin
ea
r
k
er
n
el
is
ap
p
lied
u
s
in
g
a
s
im
p
lifie
d
d
ataset
with
f
ewe
r
p
ar
am
eter
s
.
T
h
e
m
o
d
el
im
p
lem
en
tatio
n
is
ca
r
r
ied
o
u
t
u
s
in
g
Py
th
o
n
,
wi
th
Pan
d
as
f
o
r
d
ata
h
an
d
lin
g
a
n
d
Scik
it
-
lear
n
f
o
r
SVM
tr
ain
in
g
a
n
d
e
v
alu
atio
n
.
T
h
is
ap
p
r
o
ac
h
s
im
p
lifie
s
co
m
p
u
tatio
n
an
d
im
p
r
o
v
es
ef
f
icien
cy
wh
ile
m
ain
tain
in
g
class
if
icatio
n
ac
cu
r
ac
y
.
Data
lab
elin
g
is
th
en
p
er
f
o
r
m
ed
b
y
ass
ig
n
in
g
b
in
ar
y
v
alu
es
to
ea
c
h
o
p
er
atin
g
co
n
d
itio
n
(
e.
g
.
,
FAN
ON
=
1
,
o
th
e
r
s
=
−1
)
.
T
o
s
u
p
p
o
r
t
m
an
u
al
ca
lcu
latio
n
a
n
d
v
is
u
aliza
tio
n
,
th
e
d
ataset
is
f
u
r
th
er
r
ed
u
ce
d
to
two
p
ar
am
eter
s
—
B
ME
2
8
0
te
m
p
er
atu
r
e
a
n
d
MQ
-
2
s
m
o
k
e
co
n
ce
n
tr
atio
n
—
as
p
r
esen
ted
in
th
e
co
r
r
esp
o
n
d
in
g
T
ab
le
5
a
n
d
T
a
b
le
6
.
T
ab
le
5
. T
h
e
d
ataset
b
ef
o
r
e
an
d
af
ter
lab
elin
g
Te
mp
.
B
M
E
H
u
mi
.
B
M
E
N
TC
M
LX
1
M
LX
2
M
LX
3
S
mo
k
e
S
V
M
B
e
f
o
r
e
La
b
e
l
i
n
g
S
V
M
A
f
t
e
r
La
b
e
l
i
n
g
3
0
.
4
1
5
4
.
0
7
2
4
.
9
9
4
7
.
5
1
3
8
.
1
9
5
1
.
0
1
4
3
0
F
A
N
O
N
+1
3
0
.
4
1
5
4
.
0
4
2
5
.
0
3
5
9
.
3
3
3
7
.
6
9
5
1
.
2
9
4
3
0
S
H
U
N
T
TR
I
P
-
1
2
6
.
5
7
5
1
.
4
1
2
8
.
7
2
2
6
.
5
3
2
6
.
4
9
2
6
.
7
1
1
0
7
2
S
H
U
N
T
TR
I
P
-
1
2
9
.
0
9
7
2
.
7
5
2
3
.
8
6
2
9
.
7
1
2
9
.
4
3
3
0
.
0
3
3
9
1
H
EA
TER
C
A
T
R
I
D
G
E
O
N
-
1
4
6
.
1
6
3
.
0
1
2
3
.
9
4
2
9
.
7
1
2
9
.
5
9
3
0
.
0
3
4
3
7
F
A
N
O
N
+1
3
0
.
4
8
5
3
.
6
7
2
4
.
7
3
6
1
.
3
3
3
8
.
2
9
5
1
.
0
1
4
4
6
S
H
U
N
T
TR
I
P
-
1
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.
16
,
No
.
4
,
Au
g
u
s
t
20
26
:
1
7
5
5
-
1
766
1762
T
ab
le
6
.
T
h
is
s
im
p
lifie
d
d
ataset
af
ter
lab
elin
g
Te
mp
.
B
M
E
S
mo
k
e
S
V
M
3
0
.
4
1
4
3
0
+1
3
0
.
4
1
4
3
0
-
1
2
6
.
5
7
1
0
7
2
-
1
2
9
.
0
9
3
9
1
-
1
4
6
.
1
4
3
7
+1
3
0
.
4
8
4
4
6
-
1
Select
two
s
u
p
p
o
r
t v
ec
to
r
s
:
A:
(
3
0
.
4
1
,
4
3
0
)
→
+1
B
: (
2
9
.
0
9
,
3
9
1
)
→
-
1
Fo
r
m
u
la:
ω
1
.
x
1
+
ω
2
.
x
2
+
b
=
y
(
1
)
3
0
.
4
1
ω
1
+
4
3
0
ω
2
+
b
=
+1
(
2
)
2
9
.
0
9
ω
1
+
3
9
1
ω
2
+
b
=
-
1
(
3
)
Step
1
: E
lim
in
atio
n
b.
Su
b
tr
ac
tin
g
(
2
)
an
d
(
3
)
.
(
3
0
.
4
1
–
2
9
.
0
9
)
ω
1
+
(
4
3
0
–
3
9
1
)
ω
2
+
(
b
–
b
)
=
1
–
(
-
1)
1
.
3
2
ω
1
+
3
9
ω
2
=
2
(
4
)
Step
2
:
Dete
r
m
in
in
g
th
e
v
alu
e
o
f
ω
1
f
r
o
m
(
4
)
.
ω
1
=
2
−
39
2
1
.
32
(
5
)
Step
3
: Su
b
s
titu
tin
g
(
5
)
in
to
(
2
)
.
3
0
.
4
1
(
2
−
39
2
1
.
32
)
+
4
3
0
ω
2
+
b
=
1
30
.
41
(
39
2
)
1
.
32
+
4
3
0
ω
2
+
b
=
1
60
.
82
−
1185
.
99
2
1
.
32
+
4
3
0
ω
2
+
b
=
1
(
60
.
82
1
.
32
−
1185
.
99
1
.
32
2
)
+
4
3
0
ω
2
+
b
=1
4
6
.
0
8
–
8
9
8
.
5
ω
2
+
4
3
0
ω
2
+
b
=
1
4
6
.
0
8
–
1
3
2
8
.
5
ω
2
+
b
=
1
Step
4
:
Dete
r
m
in
in
g
th
e
v
alu
e
o
f
b.
b
=
1
–
4
6
.
0
8
+
1
3
2
8
.
5
ω
2
=
–
4
5
.
0
8
+
1
3
2
8
.
5
ω
2
(
6
)
Step
5
: Su
b
s
titu
tin
g
(
5
)
an
d
(
6
)
in
to
(
3
)
.
2
9
.
0
9
(
2
−
39
2
1
.
32
)
+
3
9
1
ω
2
+
(
−
45
.
08
+
1328
.
5
2
)
=
–
1
58
.
18
−
1134
.
51
1
.
32
+
3
9
1
ω
2
+
1
2
8
3
.
4
2
ω
2
=
–
1
−
1076
.
33
1
.
32
+
1
6
7
4
.
4
2
ω
2
=
–
1
–
8
1
5
.
4
0
+
1
6
7
4
.
4
2
ω
2
=
–
1
Step
6
:
Dete
r
m
in
in
g
th
e
v
alu
e
o
f
ω
2.
1
6
7
4
.
4
2
ω
2
=
–
1
+
8
1
5
.
4
0
=
8
1
4
.
4
2
ω
2
=
814
.
42
1674
.
42
=
0
.
4
8
6
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
I
mp
leme
n
ta
tio
n
o
f su
p
p
o
r
t v
e
cto
r
ma
ch
in
e
o
n
LVMDP
p
a
n
e
l wi
th
…
(
A
n
n
a
s
S
in
g
g
ih
S
etiyo
ko
)
1763
Step
7
: D
eter
m
in
in
g
th
e
v
alu
e
o
f
ω
1
a
n
d
b
.
Usi
n
g
(
5
)
to
d
eter
m
in
e
t
h
e
v
al
u
e
o
f
ω
1
.
ω1
=
2
−
39
.
0
.
486
1
.
32
=
2
−
18
.
95
4
1
.
32
=
−
16
.
96
5
1
.
32
=
–
1
2
.
8
4
4
Usi
n
g
(
6
)
to
d
eter
m
in
e
t
h
e
v
al
u
e
o
f
b
.
b
=
–
4
5
.
0
8
+
1
3
2
8
.
5
.
0
.
4
8
6
=
–
4
5
.
0
8
+
6
4
5
.
6
5
1
=
6
0
0
.
5
7
1
T
h
er
ef
o
r
e,
Valu
e
o
f
ω1
=
–
1
2
.
8
4
4
Valu
e
o
f
ω2
=
0
.
4
8
6
Valu
e
o
f
b
=
6
0
0
.
5
7
1
T
h
u
s
,
th
e
f
o
r
m
u
la
f
o
r
d
etec
tin
g
th
e
“FAN
ON”
o
r
n
o
n
–
FAN
ON
lab
el
is
o
b
tain
ed
as f
o
llo
ws:
FAN
ON
p
r
ed
ictio
n
=
–
1
2
.
8
4
4
x
1
+
0
.
4
8
6
x
2
+
6
0
0
.
5
7
1
T
o
v
er
if
y
th
e
ac
cu
r
ac
y
o
f
t
h
e
d
er
iv
ed
f
o
r
m
u
la,
test
in
g
d
ata
ar
e
s
u
b
s
titu
ted
in
to
th
e
p
r
ed
ictio
n
eq
u
atio
n
.
Fo
r
e
x
am
p
le,
u
s
in
g
d
ata
f
r
o
m
r
o
w
5
o
f
T
ab
le
6
(
T
em
p
.
B
ME
=
4
6
.
1
an
d
S
m
o
k
e
=
4
3
7
with
a
lab
el
o
f
+1
)
,
t
h
e
r
esu
lt
is
g
r
ea
ter
th
an
ze
r
o
,
in
d
icatin
g
a
FAN
ON
co
n
d
itio
n
.
T
h
is
co
n
f
ir
m
s
th
at
th
e
f
o
r
m
u
la
co
r
r
ec
tly
class
if
ies th
e
d
ata.
T
h
e
s
am
e
v
alid
atio
n
p
r
o
ce
s
s
is
ap
p
lied
to
all
o
t
h
er
class
es.
FAN
ON
p
r
ed
ictio
n
=
–
1
2
.
8
4
4
×
4
6
.
1
+
0
.
4
8
6
×
4
3
7
+
6
0
0
.
5
7
1
=
2
2
0
.
8
4
4
6
3.
5
.
M
o
del
e
v
a
lua
t
i
o
n
Mo
d
el
ev
alu
atio
n
is
p
er
f
o
r
m
e
d
u
s
in
g
test
in
g
d
ata
to
ass
ess
th
e
ab
ilit
y
o
f
th
e
m
o
d
el
to
d
is
tin
g
u
is
h
b
etwe
en
n
o
r
m
al
an
d
ab
n
o
r
m
al
co
n
d
itio
n
s
.
Per
f
o
r
m
a
n
ce
is
m
ea
s
u
r
ed
u
s
in
g
ac
c
u
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
co
n
f
u
s
io
n
m
at
r
ix
,
an
d
F1
-
s
co
r
e.
As
s
h
o
wn
in
Fig
u
r
e
7
,
th
e
m
o
d
el
ac
h
iev
es
an
ac
cu
r
ac
y
o
f
9
3
%,
co
r
r
ec
tly
class
if
y
in
g
9
3
% o
f
th
e
1
2
5
d
at
a
s
am
p
les.
C
las
s
-
wis
e
ev
alu
atio
n
s
h
o
ws
s
tr
o
n
g
an
d
co
n
s
is
ten
t
m
o
d
el
p
er
f
o
r
m
a
n
ce
.
T
h
e
FAN
ON
cla
s
s
ac
h
iev
es
a
p
r
ec
is
io
n
o
f
0.
9
1
an
d
a
r
ec
al
l
o
f
0.
9
8
,
r
esu
ltin
g
in
a
h
ig
h
F
1
-
s
co
r
e
o
f
0.
9
4
.
Fo
r
th
e
HE
A
T
E
R
C
A
R
T
R
I
DGE
ON
clas
s
,
p
r
ec
is
io
n
an
d
r
ec
all
ar
e
0
.
8
3
an
d
1
.
0
0
,
r
esp
ec
tiv
ely
,
in
d
icatin
g
ex
ce
llen
t
d
ete
ctio
n
d
esp
ite
s
o
m
e
f
alse
p
o
s
itiv
es,
with
an
F1
-
s
co
r
e
o
f
0.
9
1
.
T
h
e
NORMAL
class
r
ec
o
r
d
s
p
r
ec
is
io
n
an
d
r
ec
all
v
alu
es
o
f
0
.
9
0
an
d
0
.
9
2
,
with
a
n
F1
-
s
co
r
e
o
f
0
.
9
1
,
d
em
o
n
s
tr
atin
g
s
tab
le
class
if
icatio
n
.
T
h
e
SHUNT
T
R
I
P
cla
s
s
ac
h
iev
es
p
er
f
ec
t
p
r
ec
is
io
n
(
1
.
0
0
)
an
d
a
r
ec
all
o
f
0
.
8
7
,
y
ield
in
g
an
F1
-
s
co
r
e
o
f
0
.
9
3
.
Ov
er
all,
th
e
m
ac
r
o
-
av
er
ag
e
F1
-
s
co
r
e
o
f
0
.
9
2
an
d
weig
h
ted
-
a
v
er
ag
e
F
1
-
s
co
r
e
o
f
0
.
9
3
co
n
f
ir
m
co
n
s
is
ten
t
an
d
r
eliab
le
m
o
d
el
p
er
f
o
r
m
an
ce
,
s
u
p
p
o
r
ted
b
y
an
o
v
er
all
ac
cu
r
ac
y
o
f
0
.
9
3
.
Fig
u
r
e
7
.
Mo
d
el
e
v
alu
atio
n
3.
6
.
T
esting
o
f
bu
s
ba
r
t
em
p
er
a
t
ure
m
o
nito
ring
in t
he
L
VM
DP
M
CCB
p
a
nel
T
h
e
test
in
g
was
co
n
d
u
cted
b
y
p
lacin
g
a
co
n
tactless
ML
X9
0
6
1
4
tem
p
er
atu
r
e
s
en
s
o
r
o
n
th
e
o
u
tg
o
i
n
g
b
o
lt
o
f
th
e
m
ain
MCC
B
in
th
e
L
VM
DP
p
an
el
o
f
B
u
ild
in
g
J
an
d
th
e
MCC
B
o
f
Of
f
ice
1
in
th
e
L
VM
DP
p
an
el
lo
ca
ted
in
th
e
s
o
u
th
er
n
p
an
el
r
o
o
m
o
f
th
e
m
o
s
q
u
e
at
th
e
Sh
ip
b
u
ild
in
g
I
n
s
titu
te
o
f
Po
ly
tech
n
ic
Su
r
ab
ay
a
(
PP
NS)
.
T
h
is
test
aim
ed
to
o
b
tain
r
ea
l
-
tim
e
b
u
s
-
b
ar
tem
p
e
r
a
tu
r
e
s
am
p
les
f
r
o
m
th
e
MCC
B
an
d
to
ev
alu
ate
th
e
r
esp
o
n
s
e
o
f
th
e
web
s
ite/ap
p
licatio
n
to
th
e
o
p
er
atio
n
o
f
t
h
e
ac
tu
ato
r
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.
16
,
No
.
4
,
Au
g
u
s
t
20
26
:
1
7
5
5
-
1
766
1764
B
ased
o
n
T
ab
le
7
,
it
ca
n
b
e
o
b
s
er
v
ed
t
h
at
th
e
MCC
B
tem
p
er
atu
r
e
r
e
m
ain
ed
lo
w
a
n
d
d
id
n
o
t
ex
ce
e
d
an
y
s
et
p
o
in
ts
th
at
wo
u
ld
tr
i
g
g
er
ac
tu
ato
r
s
tatu
s
ch
an
g
es.
T
h
er
ef
o
r
e
,
th
e
s
tatu
s
o
f
all
ac
tu
ato
r
s
d
u
r
in
g
th
e
MCC
B
tem
p
er
atu
r
e
test
o
f
th
e
m
ain
L
VM
DP
p
an
el
in
B
u
ild
i
n
g
J
,
c
o
n
d
u
cted
o
n
Ap
r
il
2
5
,
2
0
2
5
,
at
1
0
:
4
3
AM
,
r
em
ain
ed
n
o
r
m
al.
T
ab
le
7
.
Mo
n
ito
r
in
g
an
d
test
in
g
o
f
MCC
B
in
th
e
L
VM
DP o
f
b
u
ild
in
g
J
PP
NS
M
i
n
u
t
e
R
-
p
h
a
s
e
T
e
mp
e
r
a
t
u
r
e
(
°
C)
S
-
p
h
a
se
Te
m
p
e
r
a
t
u
r
e
(
°
C)
T
-
p
h
a
se
Te
m
p
e
r
a
t
u
r
e
(
°
C)
A
c
t
u
a
t
o
r
S
t
a
t
u
s
1
3
3
.
2
9
3
3
.
5
7
3
4
,
8
1
N
o
r
mal
⁞
⁞
⁞
⁞
⁞
15
2
9
,
9
7
2
9
,
6
5
3
0
.
2
3
N
o
r
mal
B
ased
o
n
T
ab
le
8
,
th
e
MCC
B
tem
p
er
atu
r
e
is
h
ig
h
er
t
h
an
i
n
th
e
p
r
ev
io
u
s
test
an
d
e
x
ce
ed
s
th
e
s
h
u
n
t
tr
ip
ac
tiv
atio
n
th
r
esh
o
ld
o
f
5
5
°C
.
A
s
a
r
esu
lt,
th
e
s
h
u
n
t
tr
ip
ac
tu
ato
r
was
ac
tiv
ated
d
u
r
in
g
th
e
test
co
n
d
u
cted
o
n
Ap
r
il
2
5
,
2
0
2
5
,
at
1
1
:1
0
a.
m
.
(
W
I
B
)
at
th
e
Of
f
ice
1
L
VM
DP
p
an
el
in
th
e
s
o
u
th
er
n
m
o
s
q
u
e
p
an
el
r
o
o
m
at
PP
NS.
Fig
u
r
e
8
s
h
o
ws th
e
d
ata
ac
q
u
is
itio
n
p
r
o
ce
s
s
f
o
r
m
o
n
i
to
r
in
g
th
e
MCC
B
L
VM
DP b
u
s
-
b
ar
.
T
ab
le
8
.
Mo
n
ito
r
in
g
t
est o
f
M
C
C
B
at
th
e
s
o
u
th
er
n
m
o
s
q
u
e
L
VM
DP
p
an
el
M
i
n
u
t
e
R
-
P
h
a
s
e
T
e
m
p
e
r
a
t
u
r
e
(
°
C
)
S
-
P
h
a
se
Te
m
p
e
r
a
t
u
r
e
(
°
C
)
T
-
P
h
a
s
e
T
e
mp
e
r
a
t
u
r
e
(
°
C
)
A
c
t
u
a
t
o
r
S
t
a
t
u
s
1
6
0
.
6
1
3
7
.
8
7
5
0
.
6
9
S
h
u
n
t
t
r
i
p
⁞
⁞
⁞
⁞
⁞
15
5
8
.
8
5
3
8
.
0
1
5
1
.
7
7
S
h
u
n
t
t
r
i
p
Fig
u
r
e
8
.
Data
ac
q
u
is
itio
n
o
f
MCC
B
L
VM
DP
B
u
s
-
b
ar
m
o
n
ito
r
in
g
3.
7
.
O
v
er
a
ll
s
y
s
t
em
perf
o
rma
nce
T
h
is
s
u
b
s
ec
tio
n
ev
alu
ates
th
e
o
v
er
all
m
o
n
ito
r
in
g
an
d
p
r
o
tectio
n
s
y
s
tem
o
n
th
e
p
r
o
to
t
y
p
e
p
a
n
el,
in
clu
d
in
g
tem
p
e
r
atu
r
e,
h
u
m
id
ity
,
b
u
s
-
b
ar
tem
p
er
atu
r
e,
s
m
o
k
e
d
etec
tio
n
,
an
d
th
e
co
r
r
esp
o
n
d
i
n
g
web
/ap
p
licatio
n
d
is
p
lay
an
d
ac
tu
ato
r
r
esp
o
n
s
es.
T
ab
le
9
s
h
o
ws
th
at
all
s
y
s
tem
co
m
p
o
n
en
ts
f
u
n
ctio
n
e
d
p
r
o
p
er
l
y
,
with
all
s
en
s
o
r
s
p
r
o
v
id
in
g
ac
c
u
r
ate
r
ea
d
in
g
s
.
Ho
wev
er
,
th
e
s
y
s
tem
o
p
er
atio
n
a
n
d
ac
tu
ato
r
s
tatu
s
in
th
is
test
wer
e
ev
alu
ated
with
o
u
t a
p
p
ly
in
g
th
e
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
m
eth
o
d
.
T
ab
el
9
.
Ov
e
r
all
s
y
s
tem
test
in
g
b
ef
o
r
e
m
eth
o
d
im
p
lem
e
n
tatio
n
T
i
m
e
V
I
P
E
PF
F
r
e
q
B
M
E
(
ᵒ
C
)
B
M
E
(
%)
N
TC
M
LX
1
M
LX
2
M
LX
3
S
mo
k
e
A
c
t
u
a
t
o
r
15
-
05
-
2
5
1
7
:
0
4
2
2
3
0
0
4
7
1
5
0
3
3
.
0
5
6
1
.
7
9
2
3
.
9
2
2
9
.
9
3
3
0
.
0
5
3
0
.
2
9
4
3
3
N
15
-
05
-
2
5
1
7
:
0
3
2
2
1
0
0
4
7
1
5
0
3
3
.
6
6
6
4
.
0
7
2
4
.
1
2
3
2
.
5
9
3
0
.
8
7
3
0
.
3
3
4
3
4
N
15
-
05
-
2
5
1
7
:
0
2
2
2
3
0
0
4
7
1
5
0
3
2
.
7
4
6
9
.
0
1
2
4
.
1
1
3
0
.
3
9
3
0
.
4
3
5
2
.
5
5
4
3
3
H
C
O
N
15
-
05
-
2
5
1
7
:
0
1
2
2
3
0
0
4
7
1
5
0
3
1
.
7
6
5
.
3
2
4
.
1
3
3
0
.
0
3
3
1
.
4
1
3
0
.
5
7
4
3
2
H
C
O
N
15
-
05
-
2
5
1
7
:
0
0
2
1
9
0
0
4
7
1
5
0
3
1
.
7
6
6
4
.
9
8
2
4
.
0
1
3
0
.
2
5
3
0
.
4
3
4
2
.
1
9
4
3
5
N
15
-
05
-
2
5
1
6
:
5
9
2
2
0
0
0
4
7
1
5
0
3
1
.
8
6
6
3
.
6
5
2
4
.
1
4
3
0
.
2
3
3
0
.
3
9
4
2
.
9
7
4
1
7
N
T
ab
le
1
0
p
r
esen
ts
s
en
s
o
r
r
ea
d
in
g
s
alo
n
g
with
th
e
class
if
icatio
n
r
esu
lts
g
en
er
ated
b
y
t
h
e
SVM
,
s
h
o
win
g
th
at
th
e
s
y
s
tem
o
p
er
ates
as
d
esig
n
ed
an
d
m
ee
ts
th
e
r
esear
ch
o
b
jectiv
es.
Alth
o
u
g
h
T
ab
les
9
an
d
1
0
ap
p
ea
r
s
im
ilar
,
th
e
k
e
y
d
if
f
er
en
ce
lies
in
th
e
d
ec
is
io
n
-
m
ak
in
g
p
r
o
ce
s
s
.
T
ab
le
9
u
s
es
f
ix
ed
th
r
esh
o
ld
v
alu
es
p
r
o
g
r
a
m
m
ed
in
th
e
co
n
tr
o
ller
,
wh
ile
T
ab
le
1
0
d
eter
m
in
es
ac
tu
ato
r
ac
tio
n
s
u
s
in
g
SVM
-
b
ased
class
if
icatio
n
.
I
n
th
is
ex
p
er
im
en
t,
b
o
t
h
ap
p
r
o
a
ch
es
s
h
o
w
s
im
ilar
r
esu
lts
d
u
e
to
s
h
o
r
t
test
in
g
d
u
r
atio
n
an
d
s
tab
le
co
n
d
itio
n
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.