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.
1
6
,
No
.
3
,
J
u
n
e
20
2
6
,
p
p
.
1466
~
1
4
7
3
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
1
6
i
3
.
pp
1
4
6
6
-
1
4
7
3
1466
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Bea
ring
f
a
ult
cla
s
sifica
tion usin
g
de
cisio
n t
rees
and n
eura
l
networks
Ra
id H
o
us
s
em
E
dd
ine Sella
o
ui,
B
ra
him
B
o
ulebta
t
ec
he,
Sa
la
h B
ens
a
o
ula
La
b
o
r
a
t
o
r
y
o
f
A
u
t
o
ma
t
i
o
n
a
n
d
S
i
g
n
a
l
s An
n
a
b
a
,
D
e
p
a
r
t
m
e
n
t
o
f
E
l
e
c
t
r
o
n
i
c
s
,
F
a
c
u
l
t
y
o
f
T
e
c
h
n
o
l
o
g
y
,
B
a
d
j
i
M
o
k
h
t
a
r
A
n
n
a
b
a
U
n
i
v
e
r
s
i
t
y
,
A
n
n
a
b
a
,
A
l
g
e
r
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
3
0
,
2
0
2
5
R
ev
is
ed
Feb
2
1
,
2
0
2
6
Acc
ep
ted
Ma
r
1
6
,
2
0
2
6
In
th
is
stu
d
y
,
we
tes
t
th
re
e
m
a
c
h
in
e
lea
rn
i
n
g
m
e
th
o
d
o
l
o
g
ies
−
b
in
a
ry
tree
,
k
-
n
e
a
re
st
n
e
ig
h
b
o
rs
(
k
-
NN
),
a
n
d
n
e
u
ra
l
n
e
two
rk
s
(NN
)
−
u
sin
g
a
ra
n
g
e
o
f
h
y
p
e
r
p
a
ra
m
e
ters
.
Th
e
se
m
e
th
o
d
s
a
re
a
p
p
li
e
d
t
o
a
d
a
tas
e
t
c
o
n
sistin
g
o
f
e
x
trac
ted
ti
m
e
se
ries
c
h
a
ra
c
teristics
(
ro
o
t
m
e
a
n
s
q
u
a
re
(
RM
S
),
sk
e
wn
e
ss
,
a
n
d
k
u
rt
o
sis
fro
m
v
i
b
ra
ti
o
n
si
g
n
a
ls
o
f
v
a
ri
o
u
s
b
e
a
rin
g
s
s
u
b
jec
ted
t
o
d
iffere
n
t
fa
u
lt
c
o
n
d
i
ti
o
n
s
fro
m
th
e
in
telli
g
e
n
t
m
a
in
ten
a
n
c
e
sy
ste
m
s
(IM
S
)
d
a
tas
e
t.
We
e
v
a
lu
a
te
h
o
w
e
ffe
c
ti
v
e
ly
th
e
se
m
e
th
o
d
s
c
las
sify
th
e
c
o
n
d
it
i
o
n
o
f
th
e
b
e
a
rin
g
s
u
sin
g
th
e
p
ro
v
i
d
e
d
d
a
tas
e
t.
We
o
b
se
rv
e
th
e
t
o
p
two
m
e
th
o
d
s,
a
rti
fi
c
ial
n
e
u
ra
l
n
e
two
rk
(AN
N)
9
9
.
2
9
%
a
n
d
b
i
n
a
ry
tree
9
8
.
8
4
%
.
Wi
t
h
a
d
iff
e
re
n
c
e
o
f
0
.
4
5
%
,
th
e
b
i
n
a
ry
tree
is
p
re
fe
rre
d
o
v
e
r
t
h
e
c
o
m
p
lex
AN
N
d
u
e
to
it
s
e
a
se
o
f
in
terp
re
tatio
n
,
tran
sp
a
re
n
c
y
,
a
n
d
m
in
ima
l
c
o
m
p
u
tati
o
n
re
q
u
ire
m
e
n
ts.
Its
in
teg
ra
ti
o
n
a
s
c
o
d
e
i
n
e
m
b
e
d
d
e
d
c
o
n
tr
o
ll
e
rs
o
r
e
lec
tro
n
ic
c
o
n
tro
l
u
n
it
s
(ECUs)
is
m
o
re
e
fficie
n
t,
w
h
ich
m
a
k
e
s
th
e
m
fa
ste
r
fo
r
re
a
l
-
ti
m
e
p
ro
c
e
ss
in
g
a
n
d
sa
fe
ty
-
c
rit
ica
l
e
lec
tri
c
v
e
h
icle
(EV)
sy
ste
m
s.
K
ey
w
o
r
d
s
:
Dec
is
io
n
tr
ee
s
Diag
n
o
s
is
E
lectr
ic
v
eh
icle
Fau
lt c
lass
if
icat
io
n
Ma
ch
in
e
lear
n
in
g
Neu
r
al
n
etwo
r
k
s
R
o
llin
g
b
ea
r
in
g
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
R
aid
Ho
u
s
s
em
E
d
d
in
e
Sellao
u
i
L
a
b
o
r
at
o
r
y
o
f
Au
t
o
m
ati
o
n
an
d
Si
g
n
als
A
n
n
a
b
a
(
L
ASA
)
,
D
e
p
ar
t
m
e
n
t
o
f
E
le
ct
r
o
n
i
cs,
Fa
c
u
lt
y
o
f
T
ec
h
n
o
l
o
g
y
,
B
ad
j
i M
o
k
h
ta
r
A
n
n
a
b
a
Un
i
v
e
r
s
ity
An
n
ab
a,
Alg
er
ia
E
m
ail: r
aid
-
h
o
u
s
s
em
-
ed
d
in
e.
s
ellao
u
i@
u
n
iv
-
an
n
a
b
a.
d
z
1.
I
NT
RO
D
UCT
I
O
N
Ad
v
an
ce
m
en
ts
in
r
o
tatin
g
m
a
ch
in
er
y
h
av
e
led
to
m
o
r
e
r
ef
in
em
en
t
an
d
co
m
p
lex
ity
,
wh
ich
h
as
r
aised
th
e
d
em
a
n
d
f
o
r
r
eliab
ilit
y
.
T
h
e
h
ar
s
h
an
d
ex
tr
em
e
wo
r
k
in
g
co
n
d
itio
n
s
m
a
d
e
its
p
a
r
ts
p
r
o
n
e
to
d
e
g
r
ad
atio
n
.
E
v
en
s
m
all
d
ef
ec
ts
wh
ile
r
u
n
n
in
g
a
s
y
s
tem
ca
n
ca
u
s
e
p
ar
t
s
to
b
r
ea
k
o
r
th
e
w
h
o
le
s
y
s
tem
to
s
to
p
wo
r
k
in
g
,
wh
ich
ca
n
lead
to
m
aj
o
r
ac
cid
en
ts
an
d
d
am
ag
es.
T
h
u
s
,
r
ap
i
d
an
d
p
r
ec
is
e
ev
alu
atio
n
an
d
esti
m
atio
n
o
f
h
ea
lth
s
tatu
s
ar
e
ess
en
tial
f
o
r
m
ain
tain
in
g
its
s
af
e
an
d
d
ep
en
d
ab
le
o
p
er
atio
n
[
1
]
.
T
h
e
d
e
p
en
d
a
b
le
o
p
er
atio
n
o
f
r
o
llin
g
b
ea
r
in
g
s
is
v
ital
f
o
r
th
e
ac
cu
r
a
cy
an
d
lo
n
g
ev
ity
o
f
r
o
tatin
g
m
ac
h
in
er
y
.
Giv
en
th
ei
r
s
ig
n
if
ica
n
ce
,
en
s
u
r
i
n
g
th
eir
r
eliab
ilit
y
d
ir
ec
tly
im
p
ac
ts
th
e
o
v
e
r
all
p
e
r
f
o
r
m
an
ce
o
f
th
e
s
y
s
tem
.
B
ea
r
in
g
d
eg
r
ad
atio
n
a
cc
o
u
n
ts
f
o
r
4
0
%
t
o
5
0
%
o
f
all
f
ailu
r
es;
m
ak
in
g
it
th
e
m
o
s
t
c
o
m
m
o
n
ty
p
e.
B
ea
r
in
g
d
eg
r
a
d
atio
n
o
cc
u
r
s
at
f
o
u
r
lo
ca
tio
n
s
:
th
e
b
ea
r
in
g
ca
g
e,
r
o
llin
g
ele
m
en
ts
,
o
u
ter
r
ac
e,
a
n
d
i
n
n
er
r
ac
e.
S
ec
o
n
d
is
s
tato
r
f
ailu
r
e,
w
h
ich
h
ap
p
en
s
a
b
o
u
t
3
0
%
to
3
5
%
o
f
th
e
tim
e.
Ab
o
u
t
1
0
%
o
f
th
e
tim
e,
r
o
to
r
s
f
ail,
m
a
k
in
g
th
em
th
e
th
ir
d
m
o
s
t
co
m
m
o
n
ty
p
e
o
f
f
ailu
r
e.
T
h
e
last
f
ew
p
er
ce
n
t a
r
e
m
ad
e
u
p
o
f
all
th
e
o
th
e
r
ty
p
es o
f
f
ail
u
r
es
[
2
]
–
[
4
]
.
W
h
en
d
ef
ec
ts
b
eg
in
to
d
ev
elo
p
in
a
m
o
t
o
r
,
th
e
y
m
an
if
est
as
ab
n
o
r
m
alities
in
its
o
p
er
atio
n
al
s
ig
n
als
(
ac
ce
ler
atio
n
,
p
r
ess
u
r
e,
o
r
s
t
r
ain
ch
ar
ac
ter
is
tics
)
[
5
]
.
Det
ec
tin
g
th
ese
ab
n
o
r
m
alities
is
th
e
k
ey
f
o
r
ea
r
ly
d
iag
n
o
s
is
.
Am
o
n
g
th
ese
ap
p
r
o
ac
h
es,
v
ib
r
atio
n
s
ig
n
al
an
a
ly
s
is
i
s
esp
ec
ially
s
u
itab
le
f
o
r
d
etec
tin
g
f
a
u
lts
an
d
d
ef
ec
ts
in
b
ea
r
in
g
s
[
6
]
,
[
7
]
.
T
h
e
b
ea
r
in
g
s
p
r
o
d
u
ce
v
i
b
r
atio
n
s
ig
n
als
th
at
d
is
p
lay
n
o
n
-
s
tatio
n
ar
ity
an
d
p
er
io
d
ic
im
p
ac
t
f
ea
tu
r
es.
As
a
r
esu
lt,
s
ig
n
al
p
r
o
ce
s
s
in
g
m
eth
o
d
s
ar
e
f
r
eq
u
en
tly
em
p
lo
y
e
d
in
en
g
in
ee
r
in
g
to
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
B
ea
r
in
g
fa
u
lt c
la
s
s
ifica
tio
n
u
s
in
g
d
ec
is
io
n
tr
ee
s
a
n
d
n
eu
r
a
l
n
etw
o
r
ks
(
R
a
id
Ho
u
s
s
em
E
d
d
in
e
S
ella
o
u
i
)
1467
r
ec
o
g
n
ize
a
n
d
ex
tr
ac
t
d
ef
ec
t
ch
ar
ac
ter
is
tics
f
r
o
m
r
aw
v
ib
r
atio
n
s
ig
n
als
f
o
r
m
o
n
ito
r
in
g
a
n
d
d
ia
g
n
o
s
in
g
th
eir
co
n
d
itio
n
.
Fau
lt
d
ete
cti
o
n
an
d
is
o
la
ti
o
n
(
FD
I
)
is
a
b
r
an
ch
o
f
c
o
n
t
r
o
l
en
g
i
n
e
er
in
g
t
h
at
f
o
c
u
s
es
o
n
u
p
h
o
ld
in
g
a
s
y
s
te
m
'
s
r
eli
a
b
ili
ty
a
n
d
s
af
et
y
d
u
r
i
n
g
its
o
p
er
ati
o
n
a
l
p
e
r
i
o
d
,
a
v
o
i
d
i
n
g
p
o
s
s
i
b
le
b
r
ea
k
d
o
w
n
s
an
d
im
p
r
o
v
in
g
o
v
e
r
al
l
e
f
f
ici
e
n
c
y
[
8
]
.
As
tec
h
n
o
l
o
g
y
ad
v
an
ce
s
,
d
e
f
e
ct
d
i
ag
n
o
s
is
m
et
h
o
d
s
a
r
e
c
o
n
ti
n
u
al
ly
d
ev
el
o
p
in
g
.
M
o
d
e
r
n
ap
p
r
o
ac
h
es
d
o
th
ese
tas
k
s
b
y
co
m
b
i
n
i
n
g
a
d
v
a
n
c
e
d
s
i
g
n
al
p
r
o
ce
s
s
i
n
g
a
n
d
f
e
at
u
r
e
ex
tr
ac
tio
n
wit
h
m
a
ch
in
e
lea
r
n
i
n
g
(
ML
)
al
g
o
r
it
h
m
s
,
s
u
c
h
as u
s
i
n
g
a
K
al
m
a
n
f
i
lte
r
in
te
g
r
at
ed
wi
th
a
n
a
r
ti
f
ic
ial
n
e
u
r
al
n
et
wo
r
k
to
e
n
h
a
n
c
e
d
et
ec
ti
o
n
ac
cu
r
a
c
y
a
n
d
e
n
a
b
l
e
r
o
b
u
s
t
f
a
u
l
t
-
to
le
r
a
n
t
co
n
t
r
o
l
[
8
]
–
[
1
1
]
.
A
r
a
n
d
o
m
f
o
r
es
t
cl
ass
if
i
er
is
a
n
o
t
h
e
r
wa
y
to
f
i
n
d
o
u
t
th
e
h
e
alt
h
o
f
a
g
ea
r
b
o
x
.
T
h
e
d
a
ta
a
r
e
th
e
r
aw
v
i
b
r
ati
o
n
s
i
g
n
als
r
ec
o
r
d
ed
f
r
o
m
a
g
e
ar
b
o
x
e
x
p
e
r
i
m
e
n
t
s
im
u
la
ti
n
g
s
i
x
k
in
d
s
o
f
g
ea
r
f
ail
u
r
es
[
1
2
]
.
R
au
b
er
e
t
a
l
.
[
1
3
]
ai
m
e
d
to
i
d
e
n
t
if
y
h
ea
lt
h
c
o
n
d
it
io
n
s
o
f
r
o
t
ati
n
g
m
ac
h
i
n
es
u
s
in
g
a
la
b
el
e
d
d
ata
s
et
f
r
o
m
C
as
e
W
est
er
n
R
es
er
v
e
Un
iv
er
s
it
y
(
C
W
R
U
)
.
S
u
e
t
a
l.
[
1
4
]
d
id
a
m
u
lt
i
-
f
a
u
lt
d
ia
g
n
o
s
is
v
ia
s
u
p
p
o
r
t
v
e
cto
r
m
a
c
h
i
n
e
(
SV
M)
.
T
w
o
a
p
p
r
o
a
c
h
es
t
h
at
ac
h
ie
v
e
h
i
g
h
d
ia
g
n
o
s
ti
c
a
cc
u
r
ac
y
wh
i
le
r
ed
u
ci
n
g
c
o
m
p
u
t
ati
o
n
a
l
co
m
p
le
x
it
y
we
r
e
p
r
o
p
o
s
e
d
b
y
Alo
n
s
o
-
Go
n
zá
l
ez
et
a
l
.
[
1
5
]
a
n
d
C
h
e
n
et
a
l.
[
1
6
]
.
T
h
e
ap
p
r
o
ac
h
is
d
esi
g
n
e
d
to
i
d
en
t
if
y
b
ea
r
i
n
g
d
e
f
ec
ts
wi
th
li
m
ite
d
ch
a
r
ac
te
r
is
t
ics
a
n
d
o
b
s
e
r
v
ati
o
n
al
d
at
a.
Fo
r
th
e
p
u
r
p
o
s
es
o
f
o
u
r
wo
r
k
,
th
e
in
tellig
en
t
m
ain
ten
an
ce
s
y
s
tem
s
(
I
MS)
b
ea
r
i
n
g
d
ataset
[
1
7
]
r
ep
r
esen
ted
a
f
itti
n
g
tr
ain
in
g
d
ataset
f
o
r
o
u
r
wo
r
k
.
Var
io
u
s
r
esear
ch
s
tu
d
ies
in
f
ield
s
h
av
e
u
tili
ze
d
th
e
I
MS
d
atab
ase.
Var
io
u
s
ML
m
o
d
els
h
av
e
b
ee
n
d
ev
elo
p
ed
to
id
e
n
tify
ab
n
o
r
m
al
co
n
d
itio
n
s
in
b
ea
r
in
g
s
b
ef
o
r
e
th
ey
lead
to
ca
tast
r
o
p
h
ic
f
ailu
r
es.
On
e
s
tu
d
y
p
r
o
p
o
s
ed
a
co
m
b
i
n
atio
n
o
f
co
n
v
o
lu
tio
n
al
n
eu
r
a
l
n
etwo
r
k
s
(
C
NNs)
an
d
g
ate
d
r
ec
u
r
r
en
t
u
n
its
(
GR
Us)
f
o
r
a
n
o
m
aly
d
etec
tio
n
in
r
o
tatin
g
m
ac
h
in
er
y
[
1
8
]
.
An
o
t
h
er
s
tu
d
y
u
tili
ze
d
a
p
ar
allel
lo
n
g
-
s
h
o
r
t
ter
m
m
em
o
r
y
(
PAR
A
-
L
STM
)
m
o
d
el
to
d
etec
t
an
o
m
alies
in
b
ea
r
in
g
v
ib
r
atio
n
[
1
9
]
.
T
h
e
d
ata
s
et
was
also
u
s
ed
in
r
em
ain
in
g
u
s
ef
u
l
life
(
R
UL
)
p
r
ed
ic
tio
n
s
u
s
in
g
b
id
ir
ec
tio
n
al
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
B
iLST
M)
n
eu
r
al
n
etwo
r
k
s
[
2
0
]
.
I
t
was
also
ap
p
lied
f
o
r
p
er
f
o
r
m
an
ce
ev
al
u
atio
n
in
a
s
elf
-
s
elec
tiv
e
r
eg
r
ess
io
n
m
o
d
el
to
s
elec
t
th
e
m
o
s
t
s
u
itab
le
to
p
r
ed
ict
th
e
R
UL
o
f
th
e
b
ea
r
in
g
[
2
1
]
.
B
u
ild
in
g
o
n
t
h
ese
f
o
u
n
d
atio
n
s
,
th
is
wo
r
k
aim
s
f
o
r
a
d
iag
n
o
s
is
m
eth
o
d
u
s
in
g
tim
e
s
er
ies
f
ea
tu
r
es
ex
tr
ac
ted
f
r
o
m
th
e
r
a
w
v
ib
r
atio
n
s
ig
n
als.
Me
an
wh
ile,
th
e
s
im
p
le
an
d
e
f
f
icien
t
b
in
ar
y
tr
ee
,
k
-
n
ea
r
est
n
eig
h
b
o
r
s
(
k
-
NN)
,
an
d
a
r
tific
ial
n
eu
r
al
n
etwo
r
k
(
ANN)
ar
e
em
p
lo
y
ed
as
class
if
ier
s
to
s
h
o
r
ten
th
e
tr
ain
in
g
tim
e,
k
ee
p
in
g
h
ig
h
ac
cu
r
ac
y
wh
ile
lo
wer
in
g
alg
o
r
ith
m
co
m
p
lex
ity
.
2.
T
H
E
O
R
E
T
I
CA
L
B
A
SI
S
Ma
ch
in
e
lear
n
in
g
is
em
p
lo
y
e
d
to
in
s
tr
u
ct
m
ac
h
in
es
in
t
h
e
m
o
r
e
ef
f
icien
t
m
an
a
g
em
en
t
o
f
d
ata.
At
tim
es,
an
aly
zin
g
th
e
d
ata
to
d
is
ce
r
n
p
atter
n
s
o
r
e
x
tr
ac
t
in
f
o
r
m
atio
n
ca
n
p
r
o
v
e
ch
allen
g
i
n
g
.
W
e
u
s
e
m
ac
h
in
e
lear
n
in
g
in
th
at
ca
s
e.
T
h
e
g
r
o
win
g
n
u
m
b
e
r
o
f
d
atasets
h
as
h
eig
h
ten
ed
t
h
e
d
em
an
d
f
o
r
m
ac
h
in
e
lear
n
in
g
i
n
n
u
m
er
o
u
s
s
ec
to
r
s
,
in
clu
d
in
g
h
ea
lth
ca
r
e
an
d
d
ef
en
s
e,
u
tili
zin
g
it to
d
er
iv
e
v
alu
ab
le
in
f
o
r
m
a
tio
n
[
2
2
]
,
[
2
3
]
.
2
.
1
.
B
ina
ry
t
re
e
A
b
in
ar
y
tr
ee
is
a
b
asic
h
ier
a
r
ch
ical
d
ata
s
tr
u
ctu
r
e
th
at
o
r
g
an
izes
d
ata
in
a
tr
ee
-
lik
e
f
o
r
m
at,
wh
er
e
ea
ch
n
o
d
e
ca
n
m
ain
tain
a
m
a
x
im
u
m
o
f
two
c
h
ild
r
en
.
I
t
allo
ws
ef
f
icien
t
r
ep
r
esen
tatio
n
o
f
d
ata,
wh
ich
is
u
s
ef
u
l
in
co
m
p
u
ter
s
cien
ce
ap
p
licati
o
n
s
,
in
clu
d
in
g
b
u
t
n
o
t
lim
ite
d
to
s
ea
r
c
h
alg
o
r
ith
m
s
,
s
o
r
ti
n
g
o
p
er
atio
n
s
,
an
d
h
ier
ar
ch
ical
d
ata
m
o
d
elin
g
[
2
4
]
.
T
h
e
b
in
ar
y
tr
ee
'
s
s
tr
u
ctu
r
e
is
ch
ar
ac
ter
ized
b
y
a
r
o
o
t
n
o
d
e
at
th
e
to
p
,
wh
ich
s
er
v
es
as
th
e
e
n
tr
y
p
o
in
t
to
th
e
tr
ee
.
E
ac
h
n
o
d
e
with
in
th
e
tr
ee
ca
n
co
n
tain
a
v
alu
e
o
r
k
ey
,
a
n
d
t
h
e
r
elatio
n
s
h
ip
s
am
o
n
g
th
e
n
o
d
es
ar
e
s
u
ch
th
at
th
e
v
alu
e
o
f
th
e
lef
t b
r
an
ch
is
ty
p
ically
less
th
an
th
at
o
f
th
e
p
ar
e
n
t
n
o
d
e,
wh
ile
t
h
e
v
alu
e
o
f
th
e
r
i
g
h
t b
r
a
n
ch
is
g
r
ea
ter
th
an
o
r
e
q
u
al
to
th
e
p
ar
en
t
n
o
d
e.
I
n
th
e
f
r
am
ewo
r
k
o
f
ap
p
ly
in
g
b
in
ar
y
tr
ee
s
f
o
r
v
ar
io
u
s
co
m
p
u
tatio
n
al
task
s
,
s
p
ec
if
ic
h
y
p
er
p
ar
am
eter
s
ca
n
b
e
d
ef
in
e
d
to
o
p
tim
ize
th
e
tr
ee
'
s
co
n
s
tr
u
ctio
n
a
n
d
o
p
er
atio
n
.
I
n
th
is
s
tu
d
y
,
we
f
o
cu
s
o
n
two
h
y
p
er
p
ar
am
eter
s
:
Ma
x
im
u
m
n
u
m
b
er
o
f
s
p
lits
d
ef
in
es
th
e
u
p
p
er
lim
it
o
n
h
o
w
m
an
y
tim
es
th
e
d
ata
ca
n
b
e
s
p
lit
d
u
r
in
g
th
e
co
n
s
tr
u
ctio
n
o
f
th
e
b
in
ar
y
tr
ee
.
L
im
itin
g
th
e
n
u
m
b
er
o
f
s
p
lits
h
elp
s
in
p
r
ev
en
tin
g
o
v
er
f
itti
n
g
,
th
e
s
p
lit cr
iter
io
n
m
eth
o
d
f
o
r
d
eter
m
in
in
g
h
o
w
to
s
p
lit th
e
d
ata
at
ea
ch
n
o
d
e.
T
h
e
t
h
r
ee
m
eth
o
d
s
u
s
ed
in
th
is
p
ap
er
ar
e
Gin
i's
d
iv
er
s
ity
in
d
ex
,
s
ig
n
if
y
in
g
th
e
p
r
o
b
a
b
ilit
y
f
o
r
a
r
an
d
o
m
in
s
tan
ce
b
ein
g
m
is
class
if
ied
wh
en
ch
o
s
en
r
an
d
o
m
l
y
,
as
s
ee
n
in
(
1
)
;
m
a
x
im
u
m
d
ev
ia
n
ce
r
ed
u
ctio
n
(
cr
o
s
s
en
tr
o
p
y
)
,
w
h
ich
is
a
m
ea
s
u
r
e
o
f
u
n
ce
r
tain
ty
o
r
d
is
o
r
d
er
,
as
s
ee
n
in
(
2
)
;
a
n
d
t
h
e
to
win
g
r
u
le,
w
h
ich
is
n
o
t
a
p
u
r
ity
m
ea
s
u
r
e
f
o
r
a
n
o
d
e
b
u
t
r
ath
er
s
er
v
es
as
an
alter
n
ativ
e
cr
iter
io
n
f
o
r
d
eter
m
in
in
g
h
o
w
to
s
p
lit a
n
o
d
e,
as
s
ee
n
in
(
3
)
.
=
1
−
∑
(
)
2
=
1
(
1
)
1
−
∑
(
)
.
l
og
2
(
(
)
)
=
1
(
2
)
(
)
(
)
(
∑
|
(
)
−
(
)
|
=
1
)
2
(
3
)
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.
1
6
,
No
.
3
,
J
u
n
e
20
2
6
:
1
4
6
6
-
1
4
7
3
1468
2
.
2
.
E
ns
em
ble le
a
rning
E
n
s
em
b
le
lear
n
in
g
r
ef
er
s
to
th
e
p
r
o
ce
s
s
o
f
am
alg
am
atin
g
m
u
ltip
le
in
d
iv
id
u
al
lear
n
er
s
in
to
a
s
in
g
u
lar
lear
n
er
.
T
h
e
in
d
iv
id
u
al
lea
r
n
er
m
ay
in
cl
u
d
e
Naïv
e
B
ay
es,
a
d
ec
is
io
n
tr
ee
,
o
r
a
n
eu
r
al
n
etw
o
r
k
,
a
m
o
n
g
o
th
e
r
s
,
em
p
lo
y
ed
to
r
ed
u
ce
b
ias
an
d
v
ar
iatio
n
.
B
o
o
s
tin
g
g
e
n
er
ates
a
s
tr
o
n
g
lear
n
e
r
b
y
c
o
m
b
in
i
n
g
a
s
er
ies
o
f
wea
k
lear
n
er
s
.
I
f
a
class
if
ier
s
h
o
ws
litt
le
co
r
r
elatio
n
with
th
e
co
r
r
ec
t
class
if
icatio
n
,
it
is
co
n
s
id
er
ed
a
wea
k
lear
n
er
;
o
n
th
e
o
th
er
h
an
d
,
a
s
tr
o
n
g
le
ar
n
er
is
s
tr
o
n
g
ly
lin
k
e
d
with
ac
cu
r
ate
class
if
icatio
n
[
2
3
]
.
B
ag
g
in
g
,
o
r
b
o
o
ts
tr
ap
ag
g
r
eg
atin
g
,
e
n
h
an
ce
s
th
e
s
tab
ilit
y
an
d
ac
c
u
r
ac
y
o
f
an
ML
al
g
o
r
ith
m
.
I
t
is
ap
p
licab
le
f
o
r
r
e
g
r
ess
io
n
as
well
as
class
if
icatio
n
.
Ad
d
itio
n
ally
,
b
a
g
g
in
g
h
elp
s
to
r
e
d
u
ce
v
a
r
ian
ce
an
d
m
itig
ate
o
v
er
f
itti
n
g
[
2
3
]
.
2
.
3
.
K
-
nea
re
s
t
neig
hb
o
r
T
h
e
k
-
n
ea
r
est
n
eig
h
b
o
r
(
k
-
NN)
class
if
icat
io
n
alg
o
r
ith
m
o
p
er
ates
o
n
th
e
p
r
in
cip
le
o
f
p
r
o
x
im
ity
in
m
u
lti
-
d
im
en
s
io
n
al
f
ea
tu
r
e
s
p
a
ce
.
T
h
e
m
ain
g
o
al
o
f
k
-
NN
c
lass
if
icatio
n
is
to
g
iv
e
a
d
ata
p
o
in
t
a
class
lab
el
b
ased
o
n
th
e
class
lab
els
o
f
its
n
ea
r
est
n
eig
h
b
o
r
s
.
Sp
ec
if
i
ca
lly
,
th
e
o
u
tp
u
t
o
f
th
e
alg
o
r
ith
m
is
d
eter
m
in
e
d
th
r
o
u
g
h
a
p
l
u
r
ality
v
o
te
am
o
n
g
th
e
o
b
ject'
s
k
-
n
ea
r
est
n
eig
h
b
o
r
s
,
wh
e
r
e
th
e
o
b
ject
is
ass
ig
n
ed
to
th
e
m
o
s
t
f
r
eq
u
e
n
tly
r
ep
r
esen
ted
class
o
f
its
n
eig
h
b
o
r
s
.
T
h
is
n
o
n
-
p
a
r
am
etr
ic
m
eth
o
d
is
p
ar
ticu
lar
ly
ad
v
an
tag
e
o
u
s
in
s
ce
n
ar
io
s
wh
er
e
th
e
d
is
tr
ib
u
tio
n
o
f
d
ata
is
u
n
k
n
o
wn
o
r
co
m
p
l
ex
[
2
5
]
.
W
e
f
o
cu
s
ed
o
n
two
h
y
p
e
r
p
ar
am
eter
s
to
im
p
r
o
v
e
th
e
p
e
r
f
o
r
m
an
ce
o
f
th
e
k
-
NN
class
if
ier
we
u
s
ed
.
T
h
e
n
u
m
b
er
o
f
n
eig
h
b
o
r
s
(
k
)
s
p
ec
if
ies
h
o
w
m
an
y
o
f
t
h
e
n
ea
r
est
p
o
in
ts
ar
e
u
tili
ze
d
to
class
if
y
ea
ch
p
o
in
t
d
u
r
in
g
p
r
ed
ictio
n
,
a
lo
w
v
al
u
e
o
f
k
r
esu
lts
in
a
f
in
e
class
if
ier
,
wh
ile
a
h
i
g
h
v
alu
e
lead
s
to
a
co
ar
s
e
class
if
ier
.
T
h
e
d
is
tan
ce
m
etr
ic
is
th
e
alg
o
r
ith
m
u
s
ed
to
ca
lcu
late
d
is
tan
ce
s
b
etwe
en
p
o
in
ts
.
I
n
th
is
p
ap
er
,
we
f
o
c
u
s
o
n
two
d
is
tan
ce
m
ea
s
u
r
es:
E
u
cli
d
ea
n
d
is
tan
ce
,
t
h
e
m
o
s
t
wid
ely
u
s
ed
,
is
a
m
ea
s
u
r
e
o
f
th
e
tr
u
e
s
tr
aig
h
t
-
lin
e
d
is
tan
ce
b
etwe
en
two
p
o
in
ts
i
n
E
u
clid
ea
n
s
p
ac
e,
as
s
ee
n
in
(
4
)
,
a
n
d
Ma
n
h
attan
d
is
tan
ce
,
also
k
n
o
wn
as
city
b
lo
ck
d
is
tan
ce
,
ca
lcu
lates th
e
s
u
m
o
f
th
e
a
b
s
o
lu
te
d
if
f
e
r
en
ce
s
b
etwe
en
th
e
co
o
r
d
in
ates o
f
t
wo
p
o
in
ts
(
5
)
[
2
6
]
.
(
,
)
=
√
∑
(
−
)
2
=
1
(
4
)
(
,
)
=
∑
|
−
|
=
1
(
5
)
2
.
4
.
Art
if
ici
a
l
neura
l net
wo
rk
Ar
tific
ial
n
eu
r
al
n
etwo
r
k
s
(
A
NN
s
)
ar
e
s
im
p
lifie
d
ar
tific
ial
m
o
d
els
th
at
ar
e
b
ased
o
n
th
e
b
io
lo
g
ical
m
ec
h
an
is
m
s
o
f
n
e
u
r
o
n
s
in
h
u
m
an
b
r
ain
s
.
An
ANN
is
m
ad
e
u
p
o
f
s
ev
er
al
h
ig
h
ly
i
n
ter
co
n
n
ec
ted
a
r
tific
ial
p
r
o
ce
s
s
in
g
u
n
its
(
n
o
d
es),
wh
ic
h
ar
e
g
r
o
u
p
ed
in
to
lay
e
r
s
,
cr
ea
tin
g
a
n
etwo
r
k
.
T
h
e
n
u
m
b
e
r
o
f
n
o
d
es in
th
e
in
p
u
t
an
d
o
u
tp
u
t
lay
er
s
is
d
eter
m
in
ed
b
y
th
e
s
p
ec
if
ic
n
u
m
b
er
o
f
in
p
u
t
an
d
o
u
tp
u
t
v
ar
iab
les
n
ee
d
ed
to
d
ef
in
e
th
e
is
s
u
e.
A
tr
ial
-
an
d
-
er
r
o
r
ap
p
r
o
a
ch
ty
p
ically
d
ete
r
m
in
es th
e
n
u
m
b
er
an
d
n
o
d
e
d
e
n
s
ity
o
f
th
e
h
id
d
en
la
y
er
s
[
2
7
]
.
E
ac
h
n
o
d
e
(
ex
ce
p
t
in
th
e
in
p
u
t
lay
er
)
is
ca
lcu
lated
as
th
e
s
u
m
∑
.
=
1
o
f
its
weig
h
ted
in
p
u
ts
an
d
b
ias
.
T
h
is
s
u
m
is
th
en
p
r
o
ce
s
s
ed
b
y
a
n
o
n
-
lin
ea
r
ac
tiv
atio
n
f
u
n
ctio
n
(
)
to
p
r
o
d
u
ce
th
e
o
u
t
p
u
t
[
2
8
]
.
T
h
is
s
tu
d
y
u
s
es
th
r
ee
ac
tiv
at
io
n
f
u
n
ctio
n
s
:
Sig
m
o
id
,
a
co
m
m
o
n
n
o
n
-
lin
ea
r
f
u
n
ctio
n
t
h
at
o
u
tp
u
ts
v
alu
es
b
etwe
en
0
an
d
1
.
As
s
ee
n
in
(
7
)
.
T
an
h
(
h
y
p
er
b
o
lic
tan
g
en
t
)
,
wh
ich
is
s
im
ilar
to
s
ig
m
o
id
b
u
t
is
s
y
m
m
etr
ic
ar
o
u
n
d
ze
r
o
,
is
o
f
ten
p
r
ef
e
r
r
e
d
f
o
r
its
g
r
ad
ien
t
b
eh
av
io
r
.
As
s
ee
n
in
(
9
)
an
d
Fig
u
r
e
1
.
R
ec
tifie
d
lin
ea
r
u
n
it
(
R
eL
U
)
,
a
n
o
n
-
lin
ea
r
f
u
n
ctio
n
wh
er
e
o
n
ly
a
s
u
b
s
et
o
f
n
eu
r
o
n
s
ac
tiv
ates
at
o
n
ce
.
I
t
is
co
m
p
u
tatio
n
ally
ef
f
icien
t,
th
o
u
g
h
it c
a
n
s
o
m
eti
m
es c
au
s
e
n
eu
r
o
n
s
to
"d
ie"
(
s
t
o
p
u
p
d
atin
g
)
d
u
r
i
n
g
tr
ain
i
n
g
[
2
9
]
.
=
(
)
=
(
∑
+
=
1
)
(
6
)
(
)
=
1
1
+
−
(
7
)
(
)
=
2
(
2
)
−
1
(
9
)
Fig
u
r
e
1
.
R
eL
U
(
R
ed
)
Sig
m
o
i
d
(
Gr
ee
n
)
an
d
T
an
h
(
B
lu
e)
o
r
l
o
g
is
tic
ac
tiv
atio
n
f
u
n
ctio
n
g
r
a
p
h
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
B
ea
r
in
g
fa
u
lt c
la
s
s
ifica
tio
n
u
s
in
g
d
ec
is
io
n
tr
ee
s
a
n
d
n
eu
r
a
l
n
etw
o
r
ks
(
R
a
id
Ho
u
s
s
em
E
d
d
in
e
S
ella
o
u
i
)
1469
2
.
5
.
Da
t
a
s
et
d
escript
io
n
T
h
e
in
tellig
en
t m
ain
ten
a
n
ce
s
y
s
tem
s
(
I
MS
)
b
ea
r
in
g
d
ataset
ca
m
e
f
r
o
m
t
h
e
test
r
ig
s
h
o
wn
i
n
Fig
u
r
e
2
.
I
t
h
as
f
o
u
r
R
ex
n
o
r
d
Z
A
-
2
1
1
5
d
o
u
b
le
-
r
o
w
b
ea
r
in
g
s
(
c
h
ar
ac
t
er
is
tics
ar
e
s
ee
n
in
T
ab
le
1
)
m
o
u
n
ted
o
n
a
s
h
af
t.
An
AC
m
o
to
r
co
n
n
ec
ted
to
t
h
e
s
h
af
t
b
y
r
u
b
b
er
b
elts
k
ee
p
s
th
e
s
p
ee
d
o
f
r
o
tatio
n
at
a
s
tead
y
2
0
0
0
r
p
m
.
A
s
p
r
in
g
m
ec
h
an
is
m
p
u
ts
a
r
a
d
ial
lo
ad
o
f
6
,
0
0
0
lb
s
.
o
n
th
e
s
h
af
t
an
d
b
ea
r
i
n
g
s
.
Als
o
,
a
cir
c
u
latio
n
s
y
s
tem
th
at
co
n
tr
o
ls
b
o
th
th
e
tem
p
er
atu
r
e
an
d
f
lo
w
lu
b
r
icate
s
all
o
f
th
e
b
ea
r
in
g
s
.
E
ac
h
h
o
u
s
in
g
h
as
two
h
ig
h
-
s
en
s
itiv
ity
q
u
ar
tz
I
C
P
ac
ce
ler
o
m
eter
s
(
PC
B
3
5
3
B
3
3
)
th
at
m
ea
s
u
r
e
th
e
x
an
d
y
ax
es.
W
e
n
o
te
th
at
all
f
ailu
r
es
h
ap
p
en
ed
af
ter
1
0
0
m
illi
o
n
r
e
v
o
lu
tio
n
s
,
wh
ich
is
th
e
ex
p
ec
ted
life
s
p
a
n
o
f
th
e
b
ea
r
in
g
[
1
7
]
.
Fig
u
r
e
2
.
T
h
e
test
r
ig
o
f
I
MS
b
ea
r
in
g
d
ataset
T
ab
le
1
.
C
h
ar
ac
ter
is
tics
o
f
th
e
b
ea
r
in
g
s
u
s
ed
R
e
x
n
o
r
d
ZA
-
2
1
1
5
C
h
a
r
a
c
t
e
r
i
s
t
i
c
s
N
u
mb
e
r
o
f
r
o
l
l
i
n
g
e
l
e
me
n
t
p
e
r
r
o
w
16
16
R
o
l
l
i
n
g
e
l
e
me
n
t
d
i
a
m
e
t
e
r
0
.
3
3
1
i
n
c
h
8
.
4
mm
P
i
t
c
h
d
i
a
me
t
e
r
2
.
8
1
5
i
n
c
h
7
1
.
5
mm
C
o
n
t
a
c
t
a
n
g
l
e
1
5
.
1
7
°
1
5
.
1
7
°
S
t
a
t
i
c
l
o
a
d
6
0
0
0
l
b
s
.
2
6
6
9
0
N
T
h
e
I
MS
p
ac
k
et
co
n
tain
s
th
r
ee
test
-
to
-
f
ailu
r
e
e
x
p
er
im
e
n
t
d
atasets
.
E
ac
h
co
n
s
is
ts
o
f
m
u
ltip
le
f
iles
,
with
ea
ch
co
n
tain
in
g
1
-
s
ec
o
n
d
s
n
ap
s
h
o
ts
o
f
v
ib
r
atio
n
s
ig
n
als
r
ec
o
r
d
e
d
at
s
et
in
ter
v
a
ls
.
T
h
e
d
ata
p
ac
k
et
ch
ar
ac
ter
is
tics
ar
e
s
u
m
m
ar
ized
in
T
ab
le
2
.
E
ac
h
f
ile
co
n
tai
n
s
2
0
,
4
8
0
d
ata
p
o
in
ts
;
at
a
s
a
m
p
lin
g
f
r
eq
u
en
cy
o
f
2
0
k
Hz,
d
ata
ac
q
u
is
itio
n
o
cc
u
r
s
at
th
e
f
r
e
q
u
en
c
y
o
f
ten
m
in
u
t
es
(
th
e
f
ir
s
t
d
ataset'
s
in
itial
f
o
r
ty
-
th
r
ee
f
iles
wer
e
co
llected
ev
er
y
f
iv
e
m
in
u
tes)
[
1
7
]
.
T
ab
le
2
.
Data
s
ets ch
ar
ac
ter
is
tics
an
d
s
u
m
m
ar
y
D
a
t
a
s
e
t
N
u
mb
e
r
o
f
c
h
a
n
n
e
l
s
N
u
mb
e
r
o
f
f
i
l
e
s
En
d
u
r
a
n
c
e
d
u
r
a
t
i
o
n
A
n
n
o
u
n
c
e
d
d
a
m
a
g
e
s
D
a
t
a
s
e
t
1
8
2
1
5
6
3
4
d
a
y
s
1
2
h
B
e
a
r
i
n
g
4
:
r
o
l
l
i
n
g
e
l
e
me
n
t
|
B
e
a
r
i
n
g
3
:
i
n
n
e
r
r
a
c
e
D
a
t
a
s
e
t
2
4
9
8
4
6
d
a
y
s
2
0
h
B
e
a
r
i
n
g
1
:
o
u
t
e
r
r
a
c
e
D
a
t
a
s
e
t
3
4
4
4
4
8
3
1
d
a
y
s
1
0
h
B
e
a
r
i
n
g
3
:
o
u
t
e
r
r
a
c
e
2
.
6
.
F
e
a
t
ures f
o
r
t
i
m
e
s
er
ies a
na
ly
s
is
I
n
th
e
an
al
y
s
is
o
f
tim
e
s
er
ies
d
ata,
v
ar
io
u
s
s
tatis
tical
f
ea
tu
r
es
ar
e
em
p
lo
y
ed
to
o
f
f
e
r
i
n
f
o
r
m
atio
n
ab
o
u
t
th
e
d
is
tr
ib
u
tio
n
,
v
ar
ia
b
ilit
y
,
an
d
o
v
er
all
c
h
ar
ac
ter
is
tics
o
f
th
e
d
ata
(
r
o
o
t
m
ea
n
s
q
u
a
r
e
(
R
MS)
,
s
tan
d
ar
d
d
ev
iatio
n
(
STD)
,
ab
s
o
lu
te
m
e
an
(
AM
)
,
k
u
r
t
o
s
is
,
s
k
ewn
ess
,
an
d
p
ea
k
to
p
ea
k
)
[
3
0
]
,
all
o
f
wh
ich
ar
e
u
s
ed
as
in
p
u
ts
.
I
n
T
a
b
le
3
,
we
o
u
tlin
e
s
aid
k
ey
f
ea
tu
r
es a
lo
n
g
with
th
eir
m
ath
em
atica
l f
o
r
m
u
las.
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.
1
6
,
No
.
3
,
J
u
n
e
20
2
6
:
1
4
6
6
-
1
4
7
3
1470
T
ab
le
3
.
T
im
e
Ser
ies f
ea
tu
r
es a
n
d
th
eir
m
at
h
em
atica
l f
o
r
m
u
l
a
Ti
me
seri
e
s fe
a
t
u
r
e
s
M
a
t
h
e
ma
t
i
c
a
l
f
o
r
m
u
l
a
s
R
o
o
t
me
a
n
sq
u
a
r
e
(
R
M
S
)
=
√
1
∑
(
2
)
=
1
S
t
a
n
d
a
r
d
d
e
v
i
a
t
i
o
n
(
S
TD
)
σ
=
√
1
N
∑
(
x
i
−
̅
)
2
N
i
=
1
A
b
so
l
u
t
e
me
a
n
(
A
M
)
̅
=
1
N
∑
|
x
i
|
{
N
}
{
i
=
1
}
K
u
r
t
o
si
s
K
=
1
∑
(
x
i
−
̅
)
4
σ
4
N
i
=
1
S
k
e
w
n
e
ss
Sk
=
1
∑
(
x
i
−
̅
)
3
σ
3
N
i
=
1
P
e
a
k
t
o
p
e
a
k
2
=
max
(
x
)
−
m
i
n
(
x
)
3.
M
E
T
H
O
D
I
n
o
u
r
wo
r
k
,
all
m
o
d
u
les
wer
e
d
esig
n
ed
an
d
tr
ain
e
d
u
s
in
g
MA
T
L
AB
o
n
a
d
u
al
-
co
r
e
ce
n
tr
al
p
r
o
ce
s
s
in
g
u
n
it
(
C
PU)
with
a
1
6
-
GB
R
AM
s
y
s
tem
.
T
h
is
s
et
u
p
s
m
o
o
th
ed
ex
p
er
im
en
tatio
n
with
v
ar
io
u
s
m
o
d
el
ar
ch
itectu
r
es a
n
d
p
ar
am
eter
s
,
en
s
u
r
in
g
v
i
g
o
r
o
u
s
ass
ess
m
en
t
o
f
ea
ch
class
if
icatio
n
m
eth
o
d
’
s
p
er
f
o
r
m
a
n
ce
.
Fo
r
th
e
d
ec
is
io
n
tr
ee
s
,
we
tr
ai
n
ed
s
ev
er
al
m
o
d
els
u
s
in
g
th
r
e
e
s
p
lit
cr
ea
tio
n
m
eth
o
d
s
:
Gin
i'
s
d
iv
er
s
ity
in
d
ex
,
m
ax
im
u
m
d
e
v
ian
ce
r
e
d
u
ctio
n
,
an
d
th
e
two
in
g
r
u
le
.
E
ac
h
m
eth
o
d
was
ev
alu
ate
d
ac
r
o
s
s
a
r
an
g
e
o
f
s
p
lits
,
v
ar
y
in
g
f
r
o
m
4
to
5
0
0
.
Ad
d
itio
n
ally
,
en
s
em
b
le
tr
ee
m
eth
o
d
s
wer
e
ass
es
s
ed
,
i
n
clu
d
in
g
b
a
g
g
in
g
,
R
US
-
B
o
o
s
t,
an
d
Ad
aBo
o
s
t.
T
h
ese
en
s
em
b
le
tech
n
iq
u
es
wer
e
test
ed
with
v
ar
y
i
n
g
p
ar
am
eter
s
(
m
ax
im
u
m
n
u
m
b
er
o
f
s
p
lits
,
n
u
m
b
er
o
f
e
s
tim
ato
r
s
(
lear
n
er
s
)
,
a
n
d
th
e
l
ea
r
n
in
g
r
ate)
t
o
d
ete
r
m
in
e
o
p
t
im
al
co
n
f
ig
u
r
atio
n
f
o
r
im
p
r
o
v
e
d
p
er
f
o
r
m
a
n
ce
.
T
h
e
k
-
NN
class
if
ier
's
m
o
d
u
l
es
u
s
ed
d
if
f
e
r
en
t
d
is
tan
ce
m
etr
ics
an
d
t
h
e
n
u
m
b
er
o
f
n
eig
h
b
o
r
s
.
Sp
ec
if
ically
,
two
d
is
tan
ce
m
ea
s
u
r
es:
C
ity
b
lo
ck
(
Ma
n
h
attan
)
d
is
tan
ce
an
d
E
u
clid
ea
n
d
is
tan
ce
.
W
h
ile
th
e
n
u
m
b
er
o
f
n
eig
h
b
o
r
s
r
a
n
g
ed
f
r
o
m
1
to
1
0
0
,
allo
win
g
u
s
to
o
b
s
er
v
e
h
o
w
th
e
n
eig
h
b
o
r
h
o
o
d
s
ize
in
f
lu
en
ce
s
class
if
icatio
n
ac
cu
r
ac
y
.
Fo
r
n
eu
r
al
n
etwo
r
k
class
if
ier
s
,
m
u
ltip
le
co
n
f
i
g
u
r
atio
n
s
wer
e
u
s
ed
,
f
o
c
u
s
in
g
o
n
ac
tiv
ati
o
n
f
u
n
ctio
n
s
an
d
n
etwo
r
k
ar
c
h
itectu
r
e.
W
e
test
ed
th
r
ee
ac
tiv
atio
n
f
u
n
ctio
n
s
—
R
eL
U,
T
an
h
,
a
n
d
Sig
m
o
id
—
ap
p
lied
u
n
if
o
r
m
ly
ac
r
o
s
s
h
id
d
e
n
lay
er
s
.
T
h
e
h
id
d
en
la
y
er
s
v
ar
ied
f
r
o
m
o
n
e
to
t
h
r
ee
,
with
ea
ch
h
a
v
in
g
1
0
,
2
0
,
5
0
,
7
0
,
o
r
1
0
0
n
eu
r
o
n
s
p
er
lay
e
r
.
Var
io
u
s
lay
er
ar
r
a
n
g
em
en
ts
w
er
e
co
n
s
tr
u
cted
,
in
cl
u
d
in
g
i
n
cr
ea
s
in
g
s
eq
u
en
ce
s
(
e.
g
.
,
1
0
-
50
-
1
0
0
)
,
d
ec
r
ea
s
in
g
s
eq
u
en
ce
s
(
e.
g
.
,
5
0
-
20
-
1
0
)
,
u
n
if
o
r
m
lay
er
s
(
e
.
g
.
,
5
0
-
50
-
5
0
)
,
an
d
r
an
d
o
m
co
m
b
in
atio
n
s
(
e
.
g
.
,
7
0
-
20
-
5
0
)
.
A
So
f
tMa
x
ac
tiv
atio
n
f
u
n
cti
o
n
is
s
et
as
th
e
f
in
al
h
id
d
en
la
y
er
in
all
n
etwo
r
k
s
to
f
ac
ilit
ate
m
u
lti
-
class
clas
s
if
i
ca
tio
n
.
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
W
e
ass
e
s
s
th
e
o
u
tco
m
es
o
f
f
a
u
lt
class
if
icatio
n
u
s
in
g
two
cr
iter
ia:
tr
ain
in
g
d
u
r
atio
n
an
d
cla
s
s
if
icatio
n
test
ac
cu
r
ac
y
(
)
,
as sh
o
wn
in
(
1
0
)
.
T
r
u
e
n
eg
ativ
e
(
T
N)
an
d
t
r
u
e
p
o
s
itiv
e
(
T
P)
s
h
o
w
th
e
co
r
r
ec
tly
class
if
ied
ca
s
es,
wh
ile
f
alse p
o
s
itiv
e
(
FP
)
an
d
f
alse n
eg
ativ
e
(
FN)
s
h
o
w
ca
s
es th
at
wer
e
n
o
t.
(
%
)
=
+
+
+
+
×
100
(
1
0
)
Af
ter
co
n
d
u
ctin
g
t
h
e
tr
ain
in
g
an
d
test
in
g
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
els,
we
o
b
tain
th
e
f
o
llo
w
in
g
r
esu
lts
:
C
o
n
ce
r
n
in
g
th
e
b
in
ar
y
tr
ee
s
,
th
e
m
a
x
im
u
m
d
ev
ian
ce
r
ed
u
ctio
n
m
eth
o
d
ac
h
iev
ed
th
e
h
ig
h
est
ac
cu
r
ac
y
o
f
9
8
.
8
3
%.
W
e
also
r
em
a
r
k
t
h
a
t
th
e
in
cr
ea
s
e
o
f
m
ax
im
u
m
s
p
lits
ca
n
g
r
ea
tly
in
f
l
u
en
ce
p
er
f
o
r
m
a
n
ce
u
n
til
a
ce
r
tain
th
r
esh
o
ld
wh
er
e
it st
ar
ts
to
d
ec
r
ea
s
e.
T
ab
le
4
s
h
o
ws t
h
e
b
est p
r
ef
o
r
m
in
g
m
ax
n
u
m
b
er
o
f
s
p
lits
f
o
r
ea
ch
m
o
d
u
le
in
all
th
e
s
p
lit
cr
ea
tio
n
m
eth
o
d
s
.
T
r
ain
in
g
tim
e
ap
p
ea
r
s
to
b
e
r
elativ
ely
lo
w,
esp
ec
ially
f
o
r
co
n
f
ig
u
r
atio
n
s
with
f
ewe
r
s
p
lits
.
Fo
r
en
s
em
b
le
tr
ee
s
,
th
ey
d
em
o
n
s
tr
ated
h
ig
h
er
ac
cu
r
a
cy
,
with
Ad
aBo
o
s
t
ac
h
iev
in
g
an
ac
cu
r
ac
y
o
f
9
9
.
1
8
% u
s
in
g
3
0
0
m
ax
im
u
m
s
p
lits
an
d
5
0
lear
n
e
r
s
at
a
lear
n
in
g
r
ate
o
f
0
.
1
5
,
as seen
in
T
ab
le
4
.
T
h
is
d
em
o
n
s
tr
ates
th
e
p
o
wer
o
f
co
m
b
in
in
g
m
u
l
tip
le
lear
n
er
s
.
W
h
ile
tr
ain
in
g
tim
es
wer
e
h
ig
h
er
th
an
f
o
r
s
in
g
le
tr
ee
s
,
th
e
ac
cu
r
ac
y
g
ain
was sig
n
if
ican
t.
T
h
e
k
-
NN
alg
o
r
ith
m
s
p
e
r
f
o
r
m
ed
r
eliab
l
y
,
with
th
e
city
b
lo
ck
d
is
tan
ce
m
etr
ic
ac
h
iev
in
g
9
8
.
5
2
%
ac
cu
r
ac
y
,
o
u
td
o
in
g
E
u
clid
ea
n
d
is
tan
ce
at
9
8
.
2
5
%.
T
r
ai
n
in
g
tim
e
was
co
n
s
is
ten
tly
s
h
o
r
t,
as
s
ee
n
in
T
ab
le
4
.
Neu
r
al
n
etwo
r
k
s
ac
h
iev
e
d
t
h
e
h
ig
h
est
r
aw
ac
cu
r
ac
y
,
with
a
th
r
ee
-
lay
er
ar
ch
itectu
r
e
u
s
in
g
th
e
T
an
h
ac
tiv
atio
n
f
u
n
ctio
n
r
ea
ch
in
g
9
9
.
2
8
%;
h
o
wev
er
,
th
ese
o
u
tco
m
es
ca
m
e
at
a
s
u
b
s
tan
tial
co
m
p
u
tatio
n
al
co
s
t,
with
tr
ain
in
g
tim
es
ex
ce
ed
in
g
f
o
u
r
h
o
u
r
s
,
a
s
s
ee
n
in
T
ab
le
4
.
T
h
e
tr
ad
e
-
o
f
f
b
etwe
en
ac
c
u
r
ac
y
an
d
tr
ain
in
g
tim
e
is
ev
id
e
n
t.
T
h
e
r
esu
lts
ac
r
o
s
s
all
m
o
d
els
in
d
icate
a
s
tr
o
n
g
ca
p
ab
ilit
y
o
f
d
if
f
er
en
t
m
ac
h
in
e
lear
n
in
g
tec
h
n
iq
u
es
to
ac
h
iev
e
h
ig
h
ac
cu
r
ac
y
i
n
class
if
icatio
n
task
s
;
T
ab
le
4
h
i
g
h
lig
h
ted
th
e
b
est
p
er
f
o
r
m
er
s
,
a
n
d
Fig
u
r
e
s
3
(
a)
an
d
3
(
b
)
is
th
e
co
n
f
u
s
io
n
m
atr
ix
f
o
r
th
e
t
o
p
t
wo
o
v
er
all.
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
B
ea
r
in
g
fa
u
lt c
la
s
s
ifica
tio
n
u
s
in
g
d
ec
is
io
n
tr
ee
s
a
n
d
n
eu
r
a
l
n
etw
o
r
ks
(
R
a
id
Ho
u
s
s
em
E
d
d
in
e
S
ella
o
u
i
)
1471
T
ab
le
4
.
T
h
e
b
est p
r
ef
o
r
m
in
g
f
o
r
ea
ch
m
et
h
o
d
Ty
p
e
H
y
p
e
r
p
a
r
a
me
t
e
r
s
A
c
c
u
r
a
c
y
%
(
Te
s
t
)
Tr
a
i
n
i
n
g
t
i
me
B
i
n
a
r
y
Tr
e
e
S
p
l
i
t
m
e
t
h
o
d
:
G
i
n
i
's
d
i
v
e
r
s
i
t
y
i
n
d
e
x
|
M
a
x
i
m
u
m
sp
l
i
t
s:
2
5
0
9
8
.
5
7
3
3
1
5
7
2
1
2
.
6
5
s
S
p
l
i
t
m
e
t
h
o
d
:
Tw
o
i
n
g
r
u
l
e
|
M
a
x
i
m
u
m sp
l
i
t
s:
3
0
0
9
8
.
3
8
8
3
7
5
1
7
2
4
.
7
8
s
S
p
l
i
t
m
e
t
h
o
d
:
M
a
x
i
mum
d
e
v
i
a
n
c
e
r
e
d
u
c
t
i
o
n
|
M
a
x
i
mum
sp
l
i
t
s:
2
5
0
9
8
.
8
3
7
5
1
6
5
1
3
0
.
6
8
s
En
se
mb
l
e
Tr
e
e
s
B
a
g
g
i
n
g
|
M
a
x
i
mu
m s
p
l
i
t
s
:
2
5
0
|
N
u
m
b
e
r
o
f
l
e
a
r
n
e
r
s:
4
0
9
8
.
8
1
1
0
9
6
4
3
4
m
i
n
1
9
.
2
1
s
R
U
S
-
B
o
o
st
|
M
a
x
i
m
u
m s
p
l
i
t
s:
2
5
0
|
N
u
mb
e
r
o
f
l
e
a
r
n
e
r
s:
4
0
9
8
.
8
9
0
3
5
6
6
7
4
m
i
n
A
d
a
-
B
o
o
st
|
M
a
x
i
mu
m
sp
l
i
t
s:
3
0
0
|
N
u
mber
o
f
l
e
a
r
n
e
r
s:
5
0
9
9
.
1
8
0
9
7
7
5
4
4
m
i
n
2
1
.
3
2
s
k
-
NN
D
i
st
a
n
c
e
m
e
t
r
i
c
:
E
u
c
l
i
d
e
a
n
|
N
u
m
b
e
r
o
f
n
e
i
g
h
b
o
r
s:
7
9
8
.
2
5
6
2
7
4
7
7
3
2
s
D
i
st
a
n
c
e
m
e
t
r
i
c
:
C
i
t
y
b
l
o
c
k
|
N
u
mb
e
r
o
f
n
e
i
g
h
b
o
r
s:
1
5
9
8
.
5
2
0
4
7
5
5
6
3
m
i
n
1
.
8
3
s
ANN
1
l
a
y
e
r
|
1
st
l
a
y
e
r
s
i
z
e
:
5
0
|
f
u
n
c
t
i
o
n
:
S
i
g
mo
i
d
9
9
.
0
7
5
2
9
7
2
3
3
2
mi
n
5
7
.
5
5
s
2
l
a
y
e
r
s |
1
st
l
a
y
e
r
s
i
z
e
:
5
0
|
2
nd
l
a
y
e
r
si
z
e
:
1
0
0
|
f
u
n
c
t
i
o
n
:
R
e
LU
9
8
.
9
6
9
6
1
6
9
1
5
6
mi
n
7
.
3
2
s
3
l
a
y
e
r
s |
1
st
l
a
y
e
r
si
z
e
:
5
0
|
2
nd
&
3
rd
l
a
y
e
r
s
i
z
e
s:
1
0
0
|
f
u
n
c
t
i
o
n
:
T
a
n
h
9
9
.
2
8
6
6
5
7
8
6
4
h
1
2
m
i
n
1
.
6
3
s
(
a)
(
b
)
Fig
u
r
e
3
.
T
h
e
co
n
f
u
s
io
n
m
atr
ix
f
o
r
t
h
e
b
est p
er
f
o
r
m
e
r
s
,
(
a)
r
an
d
o
m
f
o
r
est an
d
(
b
)
ANN
Ou
r
r
esu
lts
s
h
o
w
th
at
th
e
class
if
icatio
n
m
eth
o
d
s
em
p
lo
y
ed
i
n
th
is
wo
r
k
ac
h
iev
e
h
ig
h
ac
c
u
r
ac
y
wh
ile
u
s
in
g
a
s
ig
n
if
ican
tly
lo
wer
alg
o
r
ith
m
co
m
p
le
x
ity
co
m
p
ar
ed
to
C
NNs
o
r
h
ig
h
-
d
e
n
s
ity
ANNs.
Su
ch
ch
ar
ac
ter
is
tics
wo
u
ld
r
en
d
er
th
em
m
o
r
e
ap
p
r
o
p
r
iate
f
o
r
b
ea
r
in
g
f
a
u
lt
d
iag
n
o
s
is
an
d
m
ain
ten
an
ce
o
n
a
n
in
d
u
s
tr
ial
lev
el.
T
h
e
d
ata
s
et,
h
o
wev
er
,
is
lim
ited
in
s
ize
an
d
v
ar
iety
o
f
d
ef
ec
ts
an
d
wo
r
k
in
g
co
n
d
itio
n
s
.
Fo
r
f
u
tu
r
e
test
s
,
we
p
lan
to
u
s
e
o
th
er
,
m
o
r
e
co
m
p
lex
d
atasets
an
d
tr
y
to
im
p
lem
en
t
an
d
test
r
ea
l
-
tim
e
b
ea
r
in
g
f
a
u
lt
m
o
n
ito
r
in
g
f
o
r
th
e
p
r
o
g
n
o
s
is
an
d
d
iag
n
o
s
is
o
f
elec
tr
ic
v
e
h
icles.
5.
CO
NCLU
SI
O
N
I
n
th
is
p
ap
er
,
we
tr
ain
ed
an
d
test
ed
v
ar
io
u
s
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
o
lo
g
ies,
s
p
ec
if
ically
ANNs,
k
-
NNs,
b
in
ar
y
tr
ee
s
,
an
d
en
s
e
m
b
le
tr
ee
s
,
f
o
r
b
ea
r
in
g
f
au
lt
class
if
icatio
n
u
s
in
g
tim
e
s
er
ies
d
ata
ex
tr
ac
ted
f
r
o
m
v
ib
r
atio
n
s
ig
n
als.
T
h
e
r
esu
lts
s
h
o
w
th
at
ea
ch
m
eth
o
d
h
as
its
p
r
o
s
an
d
co
n
s
wh
en
it
co
m
es
to
ac
cu
r
ac
y
,
p
r
ed
ictio
n
s
p
ee
d
,
an
d
tr
ain
in
g
ef
f
icien
c
y
.
No
tab
ly
,
th
e
A
NN
ap
p
r
o
ac
h
,
p
ar
ticu
lar
ly
w
ith
a
th
r
ee
-
lay
er
e
d
ar
ch
itectu
r
e,
ac
h
ie
v
ed
th
e
h
ig
h
est
ac
cu
r
ac
y
in
class
if
y
in
g
b
ea
r
in
g
c
o
n
d
itio
n
s
,
w
h
ile
th
e
Ad
aBo
o
s
ted
T
r
ee
m
o
d
el
d
em
o
n
s
tr
ated
a
c
o
m
m
e
n
d
ab
le
b
ala
n
ce
b
etwe
en
ac
c
u
r
ac
y
an
d
tr
ai
n
in
g
tim
e.
T
h
is
co
m
p
ar
ativ
e
an
aly
s
is
p
o
in
ts
o
u
t
th
e
ad
v
an
tag
es
o
f
le
v
er
ag
in
g
b
asic
ML
m
eth
o
d
s
to
en
h
an
ce
f
au
lt
d
etec
tio
n
in
b
ea
r
i
n
g
-
r
eli
an
t
m
ac
h
i
n
er
y
,
u
ltima
tely
co
n
tr
ib
u
tin
g
to
im
p
r
o
v
ed
m
ain
ten
an
ce
s
tr
ateg
ies
an
d
th
e
lo
n
g
ev
ity
o
f
m
ac
h
in
e
r
y
.
Fu
tu
r
e
r
esear
ch
m
ay
f
o
cu
s
o
n
r
ef
i
n
in
g
th
ese
m
o
d
els,
test
in
g
o
th
er
tech
n
iq
u
es
s
u
ch
as
SVM
an
d
k
er
n
el
-
b
a
s
ed
ML
m
eth
o
d
s
,
an
d
e
x
p
lo
r
in
g
th
ei
r
ap
p
licab
ilit
y
in
r
e
al
-
tim
e
m
o
n
ito
r
in
g
s
y
s
tem
s
.
T
h
is
w
ill
p
r
o
b
ab
ly
a
d
v
an
ce
p
r
e
d
ictiv
e
m
ain
ten
an
c
e
p
r
ac
tices
ac
r
o
s
s
v
ar
io
u
s
in
d
u
s
tr
ial
s
ec
to
r
s
.
B
y
in
teg
r
atin
g
th
ese
ad
v
an
ce
d
m
o
d
els
in
to
ex
is
tin
g
m
ai
n
ten
an
ce
f
r
am
ewo
r
k
s
,
in
d
u
s
tr
ies
ca
n
r
ed
u
ce
d
o
wn
tim
e
an
d
o
p
tim
ize
o
p
er
atio
n
al
ef
f
ic
ien
cy
,
lead
in
g
to
s
ig
n
if
ican
t c
o
s
t sav
in
g
s
an
d
in
cr
ea
s
ed
p
r
o
d
u
ctiv
ity
.
I
n
f
u
t
u
r
e
wo
r
k
,
th
e
i
n
teg
r
ati
o
n
o
f
th
ese
m
eth
o
d
o
lo
g
ies
in
elec
tr
ic
v
eh
icles
(
r
ea
l/s
im
u
latio
n
)
m
ay
ac
ce
ler
ate
th
e
d
ev
elo
p
m
e
n
t
o
f
b
etter
p
r
ed
ictiv
e
m
ain
ten
a
n
ce
s
y
s
tem
s
,
en
h
an
cin
g
th
e
r
eliab
ilit
y
an
d
ef
f
icien
cy
o
f
r
o
llin
g
co
m
p
o
n
en
ts
s
u
ch
as
wh
ee
l
b
ea
r
in
g
s
,
m
o
to
r
s
,
an
d
g
ea
r
s
y
s
tem
s
.
T
h
is
in
ter
f
ac
e
m
ay
u
ltima
tely
f
o
s
ter
s
af
er
an
d
m
o
r
e
e
f
f
icien
t
elec
t
r
ic
v
eh
icle
p
e
r
f
o
r
m
an
ce
o
n
r
o
ad
way
s
,
ex
ten
d
i
n
g
th
eir
o
p
e
r
a
tio
n
al
life
s
p
an
an
d
m
in
im
izin
g
m
ain
ten
a
n
ce
co
s
ts
f
o
r
u
s
er
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.
1
6
,
No
.
3
,
J
u
n
e
20
2
6
:
1
4
6
6
-
1
4
7
3
1472
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
th
at
th
is
r
esear
ch
r
ec
eiv
ed
n
o
f
u
n
d
s
f
r
o
m
p
u
b
l
ic
o
r
p
r
i
v
ate
o
r
g
a
n
izatio
n
s
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT
)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
R
aid
Ho
u
s
s
em
E
d
d
in
e
Sellao
u
i
✓
✓
✓
✓
✓
✓
✓
✓
B
r
ah
im
B
o
u
leb
tatec
h
e
✓
✓
✓
✓
✓
Salah
B
en
s
ao
u
la
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t th
e
f
in
d
i
n
g
s
o
f
th
is
s
tu
d
y
a
r
e
av
ailab
le
f
r
o
m
th
e
co
r
r
esp
o
n
d
in
g
au
th
o
r
,
R
HE
S,
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
A
.
B
a
n
k
o
v
a
,
“
I
n
v
e
st
i
g
a
t
i
o
n
o
f
t
h
e
q
u
a
l
i
t
a
t
i
v
e
d
e
p
e
n
d
e
n
c
e
b
e
t
w
e
e
n
t
h
e
c
h
a
r
a
c
t
e
r
o
f
w
e
a
r
a
n
d
t
h
e
m
u
t
u
a
l
l
o
c
a
t
i
o
n
o
f
w
e
a
r
i
n
g
su
p
p
o
r
t
s,
”
i
n
2
0
2
2
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
m
u
n
i
c
a
t
i
o
n
s,
I
n
f
o
r
m
a
t
i
o
n
,
El
e
c
t
r
o
n
i
c
a
n
d
E
n
e
r
g
y
S
y
s
t
e
m
s,
C
I
EE
S
2
0
2
2
-
Pro
c
e
e
d
i
n
g
s
,
2
0
2
2
,
p
p
.
1
–
4
,
d
o
i
:
1
0
.
1
1
0
9
/
C
I
EES5
5
7
0
4
.
2
0
2
2
.
9
9
9
0
8
7
0
.
[
2
]
A
.
J.
B
a
z
u
r
t
o
,
E.
C
.
Q
u
i
s
p
e
,
a
n
d
R
.
C
.
M
e
n
d
o
z
a
,
“
C
a
u
ses
a
n
d
f
a
i
l
u
r
e
s
c
l
a
s
si
f
i
c
a
t
i
o
n
o
f
i
n
d
u
st
r
i
a
l
e
l
e
c
t
r
i
c
m
o
t
o
r
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
2
0
1
6
I
E
EE
AN
D
E
S
C
O
N
,
AN
D
ES
C
O
N
2
0
1
6
,
2
0
1
7
,
p
p
.
1
–
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
N
D
ESCO
N
.
2
0
1
6
.
7
8
3
6
1
9
0
.
[
3
]
Y
.
M
e
r
i
z
a
l
d
e
,
L
.
H
e
r
n
á
n
d
e
z
-
C
a
l
l
e
j
o
,
a
n
d
O
.
D
u
q
u
e
-
P
e
r
e
z
,
“
S
t
a
t
e
o
f
t
h
e
a
r
t
a
n
d
t
r
e
n
d
s
i
n
t
h
e
m
o
n
i
t
o
r
i
n
g
,
d
e
t
e
c
t
i
o
n
a
n
d
d
i
a
g
n
o
si
s
o
f
f
a
i
l
u
r
e
s
i
n
e
l
e
c
t
r
i
c
i
n
d
u
c
t
i
o
n
mo
t
o
r
s,”
E
n
e
rg
i
e
s
,
v
o
l
.
1
0
,
n
o
.
7
,
p
.
1
0
5
6
,
2
0
1
7
,
d
o
i
:
1
0
.
3
3
9
0
/
e
n
1
0
0
7
1
0
5
6
.
[
4
]
L.
C
u
i
,
Z.
Ji
n
,
J.
H
u
a
n
g
,
a
n
d
H
.
W
a
n
g
,
“
F
a
u
l
t
s
e
v
e
r
i
t
y
c
l
a
ssi
f
i
c
a
t
i
o
n
a
n
d
si
z
e
e
st
i
ma
t
i
o
n
f
o
r
b
a
l
l
b
e
a
r
i
n
g
s
b
a
sed
o
n
v
i
b
r
a
t
i
o
n
mec
h
a
n
i
sm
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
7
,
p
p
.
5
6
1
0
7
–
5
6
1
1
6
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
1
1
3
2
3
.
[
5
]
G
.
M
.
Li
m,
D
.
M
.
B
a
e
,
a
n
d
J
.
H
.
K
i
m
,
“
F
a
u
l
t
d
i
a
g
n
o
si
s
o
f
r
o
t
a
t
i
n
g
ma
c
h
i
n
e
b
y
t
h
e
r
m
o
g
r
a
p
h
y
me
t
h
o
d
o
n
s
u
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
,
”
J
o
u
rn
a
l
o
f
Me
c
h
a
n
i
c
a
l
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
2
8
,
n
o
.
8
,
p
p
.
2
9
4
7
–
2
9
5
2
,
2
0
1
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
2
2
0
6
-
014
-
0
7
0
1
-
6.
[
6
]
K
.
B
o
u
a
o
u
i
c
h
e
,
Y
.
M
e
n
a
sr
i
a
,
a
n
d
D
.
K
h
a
l
f
a
,
“
D
i
a
g
n
o
s
i
s o
f
r
o
t
a
t
i
n
g
m
a
c
h
i
n
e
d
e
f
e
c
t
s b
y
v
i
b
r
a
t
i
o
n
a
n
a
l
y
si
s
,
”
Ac
t
a
I
M
EK
O
,
v
o
l
.
1
2
,
n
o
.
1
,
p
p
.
1
–
6
,
2
0
2
3
,
d
o
i
:
1
0
.
2
1
0
1
4
/
A
C
TA
I
M
EK
O
.
V
1
2
I
1
.
1
4
3
8
.
[
7
]
S
.
A
z
i
z
,
M
.
A
h
m
e
d
,
I
.
A
b
b
a
s,
S
.
Z.
H
.
N
a
q
v
i
,
a
n
d
M
.
U
.
K
h
a
n
,
“
V
i
b
r
a
t
i
o
n
s
i
g
n
a
l
a
n
a
l
y
s
i
s
t
o
w
a
r
d
s
e
a
r
l
y
d
e
t
e
c
t
i
o
n
o
f
mac
h
i
n
e
f
a
u
l
t
s,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
2
0
2
0
1
st
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
f
S
m
a
r
t
S
y
st
e
m
s
a
n
d
Em
e
rg
i
n
g
T
e
c
h
n
o
l
o
g
i
e
s
,
S
MA
RT
-
T
EC
H
2
0
2
0
,
2
0
2
0
,
p
p
.
8
9
–
9
3
,
d
o
i
:
1
0
.
1
1
0
9
/
S
M
A
R
T
-
TEC
H
4
9
9
8
8
.
2
0
2
0
.
0
0
0
3
4
.
[
8
]
W
.
K
u
r
n
i
a
w
a
n
,
K
.
M
.
H
a
n
g
o
s,
a
n
d
L.
M
á
r
t
o
n
,
“
F
a
u
l
t
i
so
l
a
t
i
o
n
a
n
d
e
s
t
i
m
a
t
i
o
n
i
n
n
e
t
w
o
r
k
s
o
f
l
i
n
e
a
r
p
r
o
c
e
ss
s
y
st
e
ms,
”
En
t
ro
p
y
,
v
o
l
.
2
5
,
n
o
.
6
,
p
.
8
6
2
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
e
2
5
0
6
0
8
6
2
.
[
9
]
C
.
S
.
J
i
n
g
e
t
a
l
.
,
“
F
a
u
l
t
d
e
t
e
c
t
i
o
n
a
n
d
i
so
l
a
t
i
o
n
f
o
r
c
o
mp
l
e
x
sy
st
e
m,”
i
n
AI
P
C
o
n
f
e
re
n
c
e
Pr
o
c
e
e
d
i
n
g
s
,
2
0
1
7
,
v
o
l
.
1
8
6
5
,
p
.
7
0
0
1
0
,
d
o
i
:
1
0
.
1
0
6
3
/
1
.
4
9
9
3
3
9
2
.
[
1
0
]
A
.
A
b
b
a
sp
o
u
r
,
S
.
M
o
k
h
t
a
r
i
,
A
.
S
a
r
g
o
l
z
a
e
i
,
a
n
d
K
.
K
.
Y
e
n
,
“
A
s
u
r
v
e
y
o
n
a
c
t
i
v
e
f
a
u
l
t
-
t
o
l
e
r
a
n
t
c
o
n
t
r
o
l
sy
s
t
e
ms,”
E
l
e
c
t
r
o
n
i
c
s
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
9
,
n
o
.
9
,
p
p
.
1
–
2
3
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
9
0
9
1
5
1
3
.
[
1
1
]
Y
.
A
.
G
h
o
b
a
sh
y
,
M
.
A
.
G
e
l
i
e
l
,
a
n
d
M
.
El
S
e
n
g
a
b
y
,
“
I
n
d
u
s
t
r
i
a
l
a
p
p
l
i
c
a
t
i
o
n
o
f
f
a
u
l
t
d
e
t
e
c
t
i
o
n
a
n
d
f
a
u
l
t
i
s
o
l
a
t
i
o
n
u
s
i
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
s,”
i
n
A
C
C
S
/
PEIT
2
0
1
7
-
2
0
1
7
I
n
t
l
C
o
n
f
o
n
A
d
v
a
n
c
e
d
C
o
n
t
r
o
l
C
i
rc
u
i
t
s
S
y
st
e
m
s
a
n
d
2
0
1
7
I
n
t
l
C
o
n
f
o
n
N
e
w
Pa
r
a
d
i
g
m
s
i
n
El
e
c
t
ro
n
i
c
s
a
n
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
2
0
1
7
,
v
o
l
.
2
0
1
8
-
F
e
b
r
u
a
r
y
,
p
p
.
4
8
–
5
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
S
-
P
EI
T.
2
0
1
7
.
8
3
0
2
9
9
9
.
[
1
2
]
M
.
C
e
r
r
a
d
a
,
G
.
Zu
r
i
t
a
,
D
.
C
a
b
r
e
r
a
,
R
.
V
.
S
á
n
c
h
e
z
,
M
.
A
r
t
é
s,
a
n
d
C
.
Li
,
“
F
a
u
l
t
d
i
a
g
n
o
s
i
s
i
n
sp
u
r
g
e
a
r
s
b
a
se
d
o
n
g
e
n
e
t
i
c
a
l
g
o
r
i
t
h
m
a
n
d
r
a
n
d
o
m
f
o
r
e
s
t
,
”
Me
c
h
a
n
i
c
a
l
S
y
s
t
e
m
s
a
n
d
S
i
g
n
a
l
Pr
o
c
e
ssi
n
g
,
v
o
l
.
7
0
–
7
1
,
p
p
.
8
7
–
1
0
3
,
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
y
ms
sp
.
2
0
1
5
.
0
8
.
0
3
0
.
[
1
3
]
T.
W
.
R
a
u
b
e
r
,
F
.
D
e
A
ss
i
s B
o
l
d
t
,
a
n
d
F
.
M
.
V
a
r
e
j
ã
o
,
“
H
e
t
e
r
o
g
e
n
e
o
u
s
f
e
a
t
u
r
e
m
o
d
e
l
s
a
n
d
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
a
p
p
l
i
e
d
t
o
b
e
a
r
i
n
g
f
a
u
l
t
d
i
a
g
n
o
si
s,
”
I
E
EE
T
r
a
n
sa
c
t
i
o
n
s
o
n
I
n
d
u
st
r
i
a
l
E
l
e
c
t
r
o
n
i
c
s
,
v
o
l
.
6
2
,
n
o
.
1
,
p
p
.
6
3
7
–
6
4
6
,
2
0
1
5
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
E.
2
0
1
4
.
2
3
2
7
5
8
9
.
[
1
4
]
Z.
S
u
,
B
.
Ta
n
g
,
Z.
Li
u
,
a
n
d
Y
.
Q
i
n
,
“
M
u
l
t
i
-
f
a
u
l
t
d
i
a
g
n
o
s
i
s
f
o
r
r
o
t
a
t
i
n
g
mac
h
i
n
e
r
y
b
a
s
e
d
o
n
o
r
t
h
o
g
o
n
a
l
s
u
p
e
r
v
i
se
d
l
i
n
e
a
r
l
o
c
a
l
t
a
n
g
e
n
t
sp
a
c
e
a
l
i
g
n
m
e
n
t
a
n
d
l
e
a
st
sq
u
a
r
e
s
u
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
,
”
N
e
u
r
o
c
o
m
p
u
t
i
n
g
,
v
o
l
.
1
5
7
,
p
p
.
2
0
8
–
2
2
2
,
2
0
1
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m.
2
0
1
5
.
0
1
.
0
1
6
.
[
1
5
]
M
.
A
l
o
n
so
-
G
o
n
z
a
l
e
z
,
V
.
G
.
D
i
a
z
,
B
.
Lo
p
e
z
P
e
r
e
z
,
B
.
C
r
i
s
t
i
n
a
P
e
l
a
y
o
G
-
B
u
st
e
l
o
,
a
n
d
J.
P
.
A
n
z
o
l
a
,
“
B
e
a
r
i
n
g
f
a
u
l
t
d
i
a
g
n
o
s
i
s
w
i
t
h
e
n
v
e
l
o
p
e
a
n
a
l
y
s
i
s
a
n
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
e
s
u
si
n
g
C
W
R
U
d
a
t
a
se
t
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
5
7
7
9
6
–
5
7
8
0
5
,
2
0
2
3
,
d
o
i
:
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
B
ea
r
in
g
fa
u
lt c
la
s
s
ifica
tio
n
u
s
in
g
d
ec
is
io
n
tr
ee
s
a
n
d
n
eu
r
a
l
n
etw
o
r
ks
(
R
a
id
Ho
u
s
s
em
E
d
d
in
e
S
ella
o
u
i
)
1473
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
8
3
4
6
6
.
[
1
6
]
Y
.
C
h
e
n
,
Q
.
C
h
e
n
,
a
n
d
R
.
W
a
n
g
,
“
B
e
a
r
i
n
g
f
a
u
l
t
d
i
a
g
n
o
si
s
b
a
se
d
o
n
v
i
b
r
a
t
i
o
n
e
n
v
e
l
o
p
e
s
p
e
c
t
r
a
l
c
h
a
r
a
c
t
e
r
i
s
t
i
c
s,”
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
1
5
,
n
o
.
4
,
p
.
2
2
4
0
,
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
5
0
4
2
2
4
0
.
[
1
7
]
H
.
Q
i
u
,
J.
Le
e
,
J.
Li
n
,
a
n
d
G
.
Y
u
,
“
W
a
v
e
l
e
t
f
i
l
t
e
r
-
b
a
s
e
d
w
e
a
k
s
i
g
n
a
t
u
r
e
d
e
t
e
c
t
i
o
n
me
t
h
o
d
a
n
d
i
t
s
a
p
p
l
i
c
a
t
i
o
n
o
n
r
o
l
l
i
n
g
e
l
e
m
e
n
t
b
e
a
r
i
n
g
p
r
o
g
n
o
st
i
c
s,
”
J
o
u
r
n
a
l
o
f
S
o
u
n
d
a
n
d
Vi
b
ra
t
i
o
n
,
v
o
l
.
2
8
9
,
n
o
.
4
–
5
,
p
p
.
1
0
6
6
–
1
0
9
0
,
2
0
0
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
s
v
.
2
0
0
5
.
0
3
.
0
0
7
.
[
1
8
]
K
.
Le
e
,
J.
K
.
K
i
m,
J.
K
i
m
,
K
.
H
u
r
,
a
n
d
H
.
K
i
m,
“
C
N
N
a
n
d
G
R
U
c
o
m
b
i
n
a
t
i
o
n
s
c
h
e
me
f
o
r
b
e
a
r
i
n
g
a
n
o
m
a
l
y
d
e
t
e
c
t
i
o
n
i
n
r
o
t
a
t
i
n
g
mac
h
i
n
e
r
y
h
e
a
l
t
h
m
o
n
i
t
o
r
i
n
g
,
”
i
n
1
s
t
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
K
n
o
w
l
e
d
g
e
I
n
n
o
v
a
t
i
o
n
a
n
d
I
n
v
e
n
t
i
o
n
,
I
C
K
I
I
2
0
1
8
,
2
0
1
8
,
p
p
.
1
0
2
–
1
0
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
K
I
I
.
2
0
1
8
.
8
5
6
9
1
5
5
.
[
1
9
]
Y
.
Zh
a
n
g
,
J.
W
u
,
H
.
X
i
e
,
R
.
H
u
a
,
a
n
d
Q
.
Li
,
“
N
A
S
A
sp
a
c
e
s
t
a
t
i
o
n
r
o
l
l
i
n
g
b
e
a
r
i
n
g
s
a
n
o
m
a
l
y
d
e
t
e
c
t
i
o
n
b
a
s
e
d
o
n
P
A
R
A
-
LSTM
mo
d
e
l
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
S
e
n
s
o
r
N
e
t
w
o
rks
,
v
o
l
.
4
4
,
n
o
.
1
,
p
p
.
4
9
–
6
1
,
2
0
2
4
,
d
o
i
:
1
0
.
1
5
0
4
/
I
JS
N
ET.
2
0
2
4
.
1
3
6
3
3
4
.
[
2
0
]
L.
M
a
g
a
d
á
n
,
F
.
J
.
S
u
á
r
e
z
,
J.
C
.
G
r
a
n
d
a
,
F
.
J
.
D
e
l
a
C
a
l
l
e
,
a
n
d
D
.
F
.
G
a
r
c
í
a
,
“
A
r
o
b
u
s
t
h
e
a
l
t
h
p
r
o
g
n
o
st
i
c
s
t
e
c
h
n
i
q
u
e
f
o
r
f
a
i
l
u
r
e
d
i
a
g
n
o
si
s
a
n
d
t
h
e
r
e
m
a
i
n
i
n
g
u
sef
u
l
l
i
f
e
t
i
m
e
p
r
e
d
i
c
t
i
o
n
s
o
f
b
e
a
r
i
n
g
s
i
n
e
l
e
c
t
r
i
c
m
o
t
o
r
s,”
A
p
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
3
,
n
o
.
4
,
p
.
2
2
2
0
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
3
0
4
2
2
2
0
.
[
2
1
]
S
.
Y
.
Li
,
H
.
A
.
Li
,
L.
M
.
T
a
m,
a
n
d
C
.
S
.
C
h
e
n
,
“
A
smar
t
sy
s
t
e
m
f
o
r
a
n
a
sse
ssm
e
n
t
o
f
t
h
e
r
e
ma
i
n
i
n
g
u
sef
u
l
l
i
f
e
o
f
b
a
l
l
b
e
a
r
i
n
g
s b
y
a
p
p
l
y
i
n
g
C
h
a
o
s
-
b
a
s
e
d
h
e
a
l
t
h
i
n
d
i
c
a
t
o
r
s
a
n
d
a
s
e
l
f
-
se
l
e
c
t
i
v
e
r
e
g
r
e
ssi
o
n
mo
d
e
l
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
3
,
n
o
.
3
,
p
.
1
2
6
7
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
3
0
3
1
2
6
7
.
[
2
2
]
M
.
R
a
h
ma
t
y
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
w
i
t
h
b
i
g
d
a
t
a
t
o
s
o
l
v
e
r
e
a
l
-
w
o
r
l
d
p
r
o
b
l
e
m
s,”
J
o
u
r
n
a
l
o
f
D
a
t
a
An
a
l
y
t
i
c
s
,
v
o
l
.
2
,
n
o
.
1
,
p
p
.
9
–
1
6
,
2
0
2
3
,
d
o
i
:
1
0
.
5
9
6
1
5
/
j
d
a
.
2
.
1
.
9
.
[
2
3
]
L.
S
i
n
d
a
y
i
g
a
y
a
a
n
d
A
.
D
e
y
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
:
a
r
e
v
i
e
w
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
S
c
i
e
n
c
e
a
n
d
Re
se
a
rc
h
(
I
J
S
R)
,
v
o
l
.
1
1
,
n
o
.
8
,
p
p
.
1
1
2
7
–
1
1
3
3
,
2
0
2
2
,
d
o
i
:
1
0
.
2
1
2
7
5
/
sr
2
2
8
1
5
1
6
3
2
1
9
.
[
2
4
]
E.
K
a
r
i
mo
v
,
“
B
i
n
a
r
y
t
r
e
e
,
”
i
n
D
a
t
a
S
t
ru
c
t
u
r
e
s
a
n
d
Al
g
o
ri
t
h
m
s
i
n
S
w
i
f
t
,
B
e
r
k
e
l
e
y
,
C
A
:
A
p
r
e
ss
,
2
0
2
0
,
p
p
.
7
7
–
8
6
.
[
2
5
]
P
.
C
u
n
n
i
n
g
h
a
m a
n
d
S
.
J.
D
e
l
a
n
y
,
“
K
-
n
e
a
r
e
st
n
e
i
g
h
b
o
u
r
c
l
a
ssi
f
i
e
r
s
-
a
t
u
t
o
r
i
a
l
,
”
A
C
M
C
o
m
p
u
t
i
n
g
S
u
rve
y
s
,
v
o
l
.
5
4
,
n
o
.
6
,
p
p
.
1
–
2
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
4
5
/
3
4
5
9
6
6
5
.
[
2
6
]
N
.
A
l
i
,
D
.
N
e
a
g
u
,
a
n
d
P
.
Tr
u
n
d
l
e
,
“
Ev
a
l
u
a
t
i
o
n
o
f
k
-
n
e
a
r
e
s
t
n
e
i
g
h
b
o
u
r
c
l
a
ssi
f
i
e
r
p
e
r
f
o
r
ma
n
c
e
f
o
r
h
e
t
e
r
o
g
e
n
e
o
u
s
d
a
t
a
s
e
t
s
,
”
S
N
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
,
n
o
.
1
2
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
0
7
/
s4
2
4
5
2
-
0
1
9
-
1
3
5
6
-
9.
[
2
7
]
B
.
A
.
P
a
y
a
,
I
.
I
.
Esa
t
,
a
n
d
M
.
N
.
M
.
B
a
d
i
,
“
A
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
b
a
se
d
f
a
u
l
t
d
i
a
g
n
o
s
t
i
c
s
o
f
r
o
t
a
t
i
n
g
m
a
c
h
i
n
e
r
y
u
si
n
g
w
a
v
e
l
e
t
t
r
a
n
sf
o
r
ms
a
s a
p
r
e
p
r
o
c
e
sso
r
,
”
Me
c
h
a
n
i
c
a
l
S
y
s
t
e
m
s
a
n
d
S
i
g
n
a
l
Pr
o
c
e
ss
i
n
g
,
v
o
l
.
1
1
,
n
o
.
5
,
1
9
9
7
,
d
o
i
:
1
0
.
1
0
0
6
/
mss
p
.
1
9
9
7
.
0
0
9
0
.
[
2
8
]
D
.
G
a
n
g
a
d
i
a
,
“
A
c
t
i
v
a
t
i
o
n
F
u
n
c
t
i
o
n
s:
e
x
p
e
r
i
me
n
t
a
t
i
o
n
a
n
d
c
o
m
p
a
r
i
s
o
n
,
”
i
n
2
0
2
1
6
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
f
o
r
C
o
n
v
e
r
g
e
n
c
e
i
n
T
e
c
h
n
o
l
o
g
y
,
I
2
C
T
2
0
2
1
,
A
p
r
.
2
0
2
1
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
2
C
T5
1
0
6
8
.
2
0
2
1
.
9
4
1
7
8
9
0
.
[
2
9
]
S
.
S
h
a
r
ma,
S
.
S
h
a
r
ma
,
a
n
d
A
.
A
t
h
a
i
y
a
,
“
A
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
s
i
n
n
e
u
r
a
l
n
e
t
w
o
r
k
s,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
n
g
i
n
e
e
ri
n
g
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
0
4
,
n
o
.
1
2
,
p
p
.
3
1
0
–
3
1
6
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
5
6
4
/
i
j
e
a
s
t
.
2
0
2
0
.
v
0
4
i
1
2
.
0
5
4
.
[
3
0
]
D
.
S
a
c
e
r
d
o
t
i
,
M
.
S
t
r
o
z
z
i
,
a
n
d
C
.
S
e
c
c
h
i
,
“
A
c
o
mp
a
r
i
s
o
n
o
f
s
i
g
n
a
l
a
n
a
l
y
si
s
t
e
c
h
n
i
q
u
e
s
f
o
r
t
h
e
d
i
a
g
n
o
st
i
c
s
o
f
t
h
e
I
M
S
r
o
l
l
i
n
g
e
l
e
m
e
n
t
b
e
a
r
i
n
g
d
a
t
a
se
t
,
”
A
p
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
3
,
n
o
.
1
0
,
p
.
5
9
7
7
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
3
1
0
5
9
7
7
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ra
id
H
o
u
ss
e
m
Ed
d
in
e
S
e
ll
a
o
u
i
re
c
e
iv
e
d
h
is
M
.
S
c
.
d
e
g
re
e
in
a
u
to
m
a
ti
o
n
a
n
d
in
d
u
strial
c
o
m
p
u
ter
sc
ien
c
e
fro
m
M
a
y
8
th
1
9
4
5
Un
iv
e
rsity
in
2
0
2
1
.
He
is
c
u
rre
n
tl
y
p
u
rs
u
in
g
a
P
h
.
D.
d
e
g
re
e
in
a
u
to
m
a
ti
o
n
c
o
n
tr
o
l
a
t
Ba
d
ji
M
o
k
h
tar
A
n
n
a
b
a
U
n
i
v
e
rsity
Al
g
e
ria.
His
re
se
a
rc
h
in
tere
sts
in
c
l
u
d
e
fa
u
lt
d
ia
g
n
o
si
s,
m
o
n
it
o
ri
n
g
,
m
a
c
h
in
e
lea
rn
i
n
g
,
a
n
d
th
e
ir
i
n
teg
ra
ti
o
n
in
e
lec
tri
c
a
l/
h
y
b
ri
d
v
e
h
icle
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ra
id
-
h
o
u
ss
e
m
-
e
d
d
in
e
.
se
ll
a
o
u
i@u
n
i
v
-
a
n
n
a
b
a
.
d
z
.
Br
a
h
im
Bo
u
lebta
te
c
h
e
re
c
e
iv
e
d
h
is
fiv
e
-
y
e
a
r
S
tate
En
g
in
e
e
r
De
g
re
e
(Dip
lô
m
e
d
’
In
g
é
n
ie
u
r
´d
’
Et
a
t)
wit
h
h
o
n
o
rs
fr
o
m
Na
ti
o
n
a
l
P
o
ly
tec
h
n
ic
S
c
h
o
o
l
o
f
Alg
iers
,
Alg
e
ria
(
1
9
8
4
),
h
is
M
P
h
il
fro
m
Bra
d
f
o
rd
U
n
iv
e
rs
it
y
,
Bra
d
f
o
rd
,
En
g
lan
d
,
i
n
1
9
8
8
,
a
n
d
h
is
P
h
D
fr
o
m
Un
iv
e
rsit
y
o
f
Ba
d
j
i
M
o
k
h
tar
A
n
n
a
b
a
(UBM
A),
An
n
a
b
a
,
Al
g
e
ria,
i
n
2
0
0
7
,
a
ll
in
e
lec
tri
c
a
l
a
n
d
e
lec
tro
n
ic
e
n
g
in
e
e
rin
g
.
S
i
n
c
e
1
9
8
8
,
h
e
h
a
s
b
e
e
n
with
Ba
d
j
i
M
o
k
h
tar
Un
i
v
e
rsit
y
,
A
n
n
a
b
a
(UBMA),
wh
e
re
h
e
is
c
u
rre
n
tl
y
tea
c
h
in
g
in
t
h
e
De
p
a
rtme
n
t
o
f
El
e
c
tro
n
ics
a
n
d
h
e
is
a
m
e
m
b
e
r
o
f
Lab
o
ra
to
ire
d
’Au
t
o
m
a
ti
q
u
e
e
t
S
i
g
n
a
u
x
d
e
An
n
a
b
a
,
(LAS
A).
His
c
u
rre
n
t
re
se
a
rc
h
in
tere
sts
in
c
l
u
d
e
c
o
m
p
u
ter
v
isi
o
n
,
m
a
c
h
i
n
e
lea
rn
in
g
,
r
o
b
o
ti
c
s
a
n
d
i
n
telli
g
e
n
t
c
o
n
tro
l
s
y
ste
m
s
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
b
ra
h
im.b
o
u
leb
tate
c
h
e
@u
n
iv
-
a
n
n
a
b
a
.
d
z
.
S
a
la
h
Be
n
sa
o
u
l
a
re
c
e
iv
e
d
h
is
En
g
in
e
e
r
De
g
re
e
o
f
S
ta
te
fro
m
Na
ti
o
n
a
l
P
o
ly
tec
h
n
i
q
u
e
o
f
Al
g
iers
in
1
9
8
3
.
Th
e
DEA
d
e
g
re
e
fro
m
Clerm
o
n
t
-
F
e
rra
n
d
,
F
ra
n
c
e
,
a
n
d
t
h
e
Do
c
to
ra
te
De
g
re
e
fr
o
m
S
a
in
t
-
Et
i
e
n
n
e
Un
iv
e
rsity
,
F
ra
n
c
e
,
i
n
1
9
8
4
a
n
d
1
9
8
7
,
re
sp
e
c
ti
v
e
ly
.
Hi
s
m
a
in
in
tere
sts
o
f
re
se
a
rc
h
in
c
lu
d
e
fa
u
lt
d
e
tec
ti
o
n
a
n
d
iso
lat
io
n
in
i
n
d
u
strial
s
y
ste
m
s
a
n
d
man
-
m
a
c
h
in
e
c
o
m
m
u
n
ica
ti
o
n
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sa
lah
.
b
e
n
sa
o
u
la@
u
n
i
v
-
a
n
n
a
b
a
.
d
z
.
Evaluation Warning : The document was created with Spire.PDF for Python.