I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
1
5
,
No
.
5
,
Octo
b
er
2
0
2
6
,
p
p
.
4
2
7
3
~
4
2
8
2
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
15
.i
5
.
p
p
4
2
7
3
-
4
2
8
2
4273
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
M
a
chine learning
and failu
re
mo
de
and ef
fect
s
ana
ly
sis
f
o
r
sus
taina
ble medic
a
l equipmen
t
spa
re parts ma
na
g
e
ment
F
a
bia
n H
a
lley
P
a
t
a
Alba
n Da
t
t
u
1
,
Sy
ed
T
a
rm
izi
Sy
ed
Sh
a
za
li
2
,
Sh
irley
J
o
hn
a
t
ha
n T
a
njo
ng
2
,
Abdu
l R
a
n
i A
chm
ed
Abd
ull
a
h
2
,
Nurla
ila
Ro
s
li
3
1
D
e
p
a
r
t
me
n
t
o
f
M
e
c
h
a
n
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
Te
c
h
n
o
l
o
g
y
,
i
-
C
A
TS U
n
i
v
e
r
si
t
y
C
o
l
l
e
g
e
,
K
u
c
h
i
n
g
,
M
a
l
a
y
si
a
2
D
e
p
a
r
t
me
n
t
o
f
M
e
c
h
a
n
i
c
a
l
a
n
d
M
a
n
u
f
a
c
t
u
r
i
n
g
E
n
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
E
n
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
s
i
t
y
M
a
l
a
y
si
a
S
a
r
a
w
a
k
,
K
o
t
a
S
a
m
a
r
a
h
a
n
,
M
a
l
a
y
si
a
3
F
a
c
u
l
t
y
o
f
C
o
mp
u
t
i
n
g
a
n
d
S
o
f
t
w
a
r
e
En
g
i
n
e
e
r
i
n
g
,
i
-
C
A
TS U
n
i
v
e
r
si
t
y
C
o
l
l
e
g
e
,
K
u
c
h
i
n
g
,
M
a
l
a
y
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
7
,
2
0
2
5
R
ev
is
ed
J
u
l 2
0
,
2
0
2
6
Acc
ep
ted
Au
g
1
2
,
2
0
2
6
S
p
a
re
p
a
rts
f
o
r
e
ss
e
n
ti
a
l
m
e
d
ica
l
e
q
u
ip
m
e
n
t
a
re
v
it
a
l
to
e
n
su
re
u
n
i
n
terru
p
ted
h
e
a
lt
h
c
a
re
p
ro
v
isi
o
n
,
e
sp
e
c
ially
i
n
a
re
a
s
wh
e
re
re
so
u
rc
e
s
a
re
li
m
i
ted
.
Th
is
p
a
p
e
r
p
re
se
n
ts
a
n
i
n
teg
ra
ti
v
e
a
p
p
r
o
a
c
h
t
h
a
t
i
n
teg
ra
tes
fa
il
u
re
m
o
d
e
a
n
d
e
ffe
c
ts
a
n
a
ly
sis
(F
M
EA)
with
su
p
e
rv
ise
d
m
a
c
h
in
e
lea
rn
i
n
g
(M
L)
m
o
d
e
ls
in
o
rd
e
r
t
o
a
ll
o
w
b
e
tt
e
r
p
re
d
icti
v
e
m
a
in
ten
a
n
c
e
a
n
d
o
p
ti
m
ize
m
a
n
a
g
e
m
e
n
t
o
f
sp
a
re
p
a
rts.
I
n
o
r
d
e
r
t
o
i
n
c
re
a
se
th
e
a
c
c
u
ra
c
y
o
f
t
h
e
fo
re
c
a
st,
F
M
EA
wa
s
first
u
se
d
to
c
o
m
p
u
te
risk
p
ri
o
rit
y
n
u
m
b
e
rs
(RP
Ns
)
o
f
th
e
c
o
m
p
o
n
e
n
ts,
q
u
a
n
t
ify
i
n
g
t
h
e
risk
o
f
e
a
c
h
c
o
m
p
o
n
e
n
t
,
a
n
d
th
e
n
u
sin
g
it
a
s
a
n
imp
o
rta
n
t
in
p
u
t
fe
a
tu
re
to
th
e
ML
a
l
g
o
rit
h
m
s.
Da
ta
fro
m
six
h
o
sp
it
a
ls
a
n
d
ten
c
rit
ica
l
m
e
d
ica
l
d
e
v
ice
s
,
su
c
h
a
s
v
e
n
ti
la
to
rs,
d
e
fi
b
ril
lat
o
rs,
d
ialy
sis
m
a
c
h
in
e
s,
a
n
d
c
o
m
p
u
ted
to
m
o
g
ra
p
h
y
(
CT
)
sc
a
n
n
e
rs
,
we
re
a
n
a
ly
z
e
d
to
i
d
e
n
ti
f
y
h
i
g
h
-
ris
k
fa
il
u
re
m
o
d
e
s
a
n
d
p
rio
ri
ti
z
e
m
a
in
ten
a
n
c
e
tas
k
s.
Th
re
e
d
if
fe
re
n
t
su
p
e
rv
ise
d
lea
rn
in
g
m
o
d
e
ls
(
ra
n
d
o
m
fo
r
e
st
(
RF
),
a
rti
ficia
l
n
e
u
ra
l
n
e
two
r
k
(A
NN
),
a
n
d
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(S
VM))
wa
s
b
u
il
t
a
n
d
tes
ted
b
a
se
d
o
n
fo
u
r
m
e
tri
c
s:
a
c
c
u
ra
c
y
,
p
re
c
isio
n
,
re
c
a
ll
,
a
n
d
F
1
-
sc
o
re
.
Th
e
p
re
c
isio
n
o
f
RF
a
n
d
AN
N
wa
s
1
.
0
0
a
n
d
S
VM
sh
o
we
d
a
n
e
x
c
e
ll
e
n
t
re
c
a
ll
v
a
lu
e
o
f
0
.
9
4
,
in
d
ica
ti
n
g
p
ro
m
isin
g
re
su
lt
s
f
o
r
p
ra
c
ti
c
a
l
a
p
p
li
c
a
ti
o
n
s.
Th
e
so
l
u
ti
o
n
p
r
o
p
o
s
e
d
c
o
n
sists
o
f
a
h
iera
rc
h
ica
l
d
e
c
isio
n
sy
ste
m
,
c
o
n
n
e
c
ti
n
g
risk
a
ss
e
ss
m
e
n
t
c
a
rri
e
d
o
u
t
b
y
e
x
p
e
rts
with
d
a
ta
-
d
ri
v
e
n
f
o
re
c
a
sts,
to
c
re
a
te
p
r
o
a
c
ti
v
e
a
n
d
s
u
sta
in
a
b
le
m
a
n
a
g
e
m
e
n
t
o
f
sp
a
re
p
a
rts.
T
h
is
a
p
p
r
o
a
c
h
h
e
lp
s
h
e
a
lt
h
c
a
re
e
n
ti
ti
e
s
les
se
n
th
e
risk
o
f
e
q
u
ip
m
e
n
t
b
re
a
k
d
o
w
n
s,
a
d
h
e
re
to
i
n
tern
a
ti
o
n
a
l
h
e
a
lt
h
c
a
re
sta
n
d
a
rd
s,
a
n
d
i
n
c
re
a
se
sy
ste
m
re
li
a
b
il
it
y
a
n
d
e
fficie
n
c
y
.
K
ey
w
o
r
d
s
:
F
a
i
l
u
r
e
m
o
d
e
a
n
d
e
f
f
e
c
ts
a
n
al
y
s
is
Ma
ch
in
e
lear
n
in
g
Me
d
ical
eq
u
ip
m
en
t
P
r
ed
ictiv
e
m
ain
ten
an
ce
Sp
ar
e
p
ar
ts
m
an
ag
e
m
en
t
Su
s
tain
ab
le
h
ea
lth
ca
r
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
:
Fab
ian
Halley
Pata
Alb
an
Dattu
D
e
p
a
r
t
m
e
n
t
o
f
M
e
c
h
a
n
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
F
a
c
u
lt
y
o
f
E
n
g
i
n
e
e
r
in
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
i
-
C
A
T
S
Un
i
v
e
r
s
i
t
y
C
o
l
le
g
e
Stam
p
in
T
im
u
r
Stre
et,
Ku
c
h
in
g
,
Sar
awa
k
9
3
3
5
0
,
Ma
lay
s
ia
E
m
ail:
f
ab
ian
.
h
alley
@
icats.e
d
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
I
n
d
u
s
tr
ial
h
ea
lth
ca
r
e
o
p
er
atio
n
s
h
av
e
to
b
e
ab
le
to
r
u
n
with
o
u
t
in
ter
r
u
p
tio
n
,
an
d
ac
ce
s
s
to
cr
itical
m
ed
ical
d
ev
ice
s
p
ar
e
p
ar
ts
is
ess
en
tial
f
o
r
th
is
.
Me
d
ical
eq
u
ip
m
en
t
s
u
ch
as
v
en
tilato
r
s
,
i
n
f
u
s
io
n
p
u
m
p
s
,
an
d
d
ef
ib
r
illato
r
s
r
eq
u
ir
es
s
p
ar
e
p
ar
ts
,
an
d
in
s
o
m
e
in
s
tan
ce
s
,
th
e
p
ar
ts
ar
e
n
o
t
av
ailab
le
o
r
d
eliv
er
ed
o
n
a
tim
e
-
co
n
s
u
m
in
g
b
asis
,
lead
in
g
to
a
s
ig
n
if
ican
t
d
eter
io
r
atio
n
o
f
p
atien
t
ca
r
e
a
n
d
o
p
er
ati
o
n
al
f
ailu
r
e
[
1
]
.
I
n
m
an
y
h
ea
lth
ca
r
e
e
n
v
ir
o
n
m
en
ts
,
th
e
r
eq
u
ir
em
en
t
f
o
r
s
er
v
i
ce
is
h
ig
h
,
an
d
eq
u
ip
m
en
t
o
p
er
ates
at
a
h
ig
h
in
ten
s
ity
,
s
o
o
r
g
an
izatio
n
s
n
ee
d
to
f
o
cu
s
o
n
th
e
n
ee
d
f
o
r
co
n
s
tan
t
ac
ce
s
s
to
cr
itica
l
p
ar
ts
o
f
m
ed
ical
eq
u
ip
m
en
t
[
2
]
.
Sp
ar
e
p
ar
ts
p
l
an
n
in
g
an
d
m
ain
ten
a
n
ce
s
tr
at
eg
ies
wer
e
p
r
e
v
io
u
s
ly
b
ased
o
n
s
ch
ed
u
led
-
b
ased
an
d
r
ea
ct
-
b
ased
a
p
p
r
o
ac
h
b
u
t
f
ailed
to
tak
e
in
to
ac
co
u
n
t
t
h
e
o
p
er
atio
n
al
co
n
d
itio
n
s
an
d
r
is
k
v
ar
iab
les
[
3
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
5
,
Octo
b
er
2
0
2
6
:
4
2
7
3
-
4
2
8
2
4274
T
h
ese
lim
itatio
n
s
r
esu
lt
in
in
ef
f
ec
tiv
en
ess
,
as
well
a
s
h
ig
h
er
co
s
ts
an
d
u
n
ex
p
ec
ted
m
ac
h
in
e
d
o
wn
tim
e.
T
h
e
h
ea
lth
ca
r
e
in
d
u
s
tr
y
r
elies
o
n
p
r
ed
ictiv
e
as
well
as
d
ata
-
d
r
iv
en
tech
n
iq
u
es
with
m
ac
h
in
e
lear
n
in
g
(
ML
)
m
eth
o
d
s
to
im
p
r
o
v
e
m
ain
ten
an
ce
p
r
o
ce
d
u
r
es
an
d
s
p
ar
e
p
ar
t
s
u
p
p
ly
ch
ain
s
[
4
]
.
Su
p
e
r
v
is
ed
ML
h
as
th
e
p
o
ten
tial
to
g
iv
e
m
an
u
f
ac
tu
r
e
r
s
an
ef
f
icien
t
m
o
d
ellin
g
ca
p
ab
ilit
y
b
y
lear
n
in
g
f
r
o
m
d
ata
s
ets,
wh
ich
in
clu
d
e
p
r
ed
ef
in
e
d
in
f
o
r
m
atio
n
ab
o
u
t
m
ain
ten
an
ce
r
ec
o
r
d
s
,
u
s
ag
e
h
o
u
r
s
,
en
v
i
r
o
n
m
e
n
tal
co
n
d
itio
n
s
,
an
d
f
ailu
r
es
[
5
]
.
T
h
e
m
o
d
els
p
r
o
d
u
ce
f
o
r
ec
asts
f
o
r
p
o
ten
tial
f
ailu
r
es
,
wh
ich
e
n
ab
le
p
r
o
ac
tiv
e
s
p
ar
e
p
ar
t
in
v
en
to
r
y
m
a
n
ag
em
en
t
to
r
ed
u
ce
h
ea
lth
ca
r
e
f
ac
ilit
y
d
o
wn
tim
e
an
d
e
n
h
an
ce
d
eliv
er
y
.
Failu
r
e
m
o
d
e
a
n
d
ef
f
ec
ts
an
aly
s
is
(
FME
A)
wo
r
k
s
h
an
d
-
in
-
h
an
d
with
th
ese
p
r
o
ce
s
s
es
an
d
is
th
e
s
y
s
tem
atic
ap
p
r
o
ac
h
to
id
en
tify
an
d
ev
alu
ate
m
ed
ical
d
ev
i
ce
f
ailu
r
e
m
o
d
es
an
d
d
eter
m
i
n
e
th
eir
cr
iticality
.
FME
A
ca
r
r
ies
o
u
t
co
m
p
o
n
e
n
t
cr
iticality
ass
e
s
s
m
en
t,
wh
ich
p
r
o
v
id
es
u
s
ef
u
l
in
f
o
r
m
atio
n
f
o
r
f
ea
tu
r
es
o
f
ML
m
o
d
els
,
in
clu
d
in
g
p
r
io
r
ity
f
ailu
r
e
ar
ea
s
an
d
co
m
m
o
n
f
ailu
r
e
p
o
in
ts
[
6
]
.
FME
A
an
d
ML
is
a
co
m
b
in
atio
n
th
at
allo
ws
en
h
an
ce
m
en
t
o
f
f
ailu
r
e
p
r
ed
ictio
n
an
d
also
p
r
o
v
id
es
r
is
k
-
d
ep
en
d
en
t
tar
g
eted
s
p
ar
e
s
p
ar
t
p
r
o
v
is
io
n
in
g
s
tr
ateg
ies
[
7
]
.
T
h
e
o
b
jectiv
e
o
f
th
is
s
tu
d
y
is
to
ass
ess
th
e
ef
f
ec
t
o
f
s
u
p
er
v
is
ed
ML
tech
n
iq
u
es
to
im
p
r
o
v
e
th
e
av
ailab
ilit
y
o
f
cr
itical
m
ed
ical
d
ev
ices
b
y
co
m
b
in
i
n
g
th
e
FME
A
an
aly
s
is
to
in
cr
ea
s
e
th
e
p
r
ed
ictio
n
an
d
p
r
io
r
itizatio
n
o
f
f
ailu
r
es.
T
h
e
s
p
ec
if
ic
o
b
jectiv
es
ar
e
t
o
i)
a
p
p
ly
FME
A
to
id
en
tify
h
ig
h
-
r
is
k
co
m
p
o
n
en
ts
an
d
p
r
io
r
itize
p
o
te
n
tial f
ailu
r
e
m
o
d
es
an
d
ii)
d
e
v
elo
p
s
u
p
er
v
is
ed
ML
m
o
d
els to
p
r
ed
ict
s
p
ar
e
p
ar
t n
ee
d
s
.
A
lim
ited
n
u
m
b
er
o
f
s
tu
d
ies
h
av
e
b
ee
n
co
n
d
u
cted
in
t
h
e
liter
atu
r
e
th
at
in
v
o
lv
e
F
ME
A
an
d
s
u
p
er
v
is
ed
ML
f
o
r
s
tr
ateg
ic
s
p
ar
e
p
a
r
ts
m
an
a
g
em
en
t
o
f
cr
itical
m
ed
ical
eq
u
ip
m
en
t.
T
h
e
c
o
m
b
in
e
d
m
eth
o
d
o
l
o
g
y
is
u
s
ef
u
l
to
b
u
ild
h
ea
lth
ca
r
e
s
y
s
tem
s
th
at
ar
e
s
tab
le
in
lim
ited
r
eso
u
r
ce
e
n
v
ir
o
n
m
en
ts
wh
er
e
eq
u
ip
m
en
t
f
ailu
r
e
p
o
s
es a
r
is
k
to
p
atien
t saf
ety
[
8
]
.
T
h
is
s
tu
d
y
f
o
cu
s
es o
n
th
e
f
o
llo
win
g
r
es
ea
r
ch
q
u
esti
o
n
s
:
i)
R
Q1
:
ca
n
in
teg
r
atin
g
FME
A
-
d
er
iv
ed
r
is
k
s
co
r
es
with
s
u
p
er
v
is
ed
ML
m
o
d
els
im
p
r
o
v
e
s
p
ar
e
p
a
r
ts
p
r
ed
ictio
n
ac
c
u
r
ac
y
?
ii)
R
Q2
:
wh
ich
s
u
p
er
v
is
ed
m
o
d
el
b
est b
alan
ce
s
p
r
ec
is
io
n
an
d
r
e
ca
ll f
o
r
cr
itical
co
m
p
o
n
e
n
t f
o
r
ec
asti
n
g
?
iii)
R
Q3
:
h
o
w
ca
n
th
is
p
r
ed
ictiv
e
f
r
am
ewo
r
k
s
u
p
p
o
r
t su
s
tain
ab
le
m
ain
ten
an
ce
p
lan
n
in
g
?
T
h
is
s
t
u
d
y
d
if
f
e
r
s
f
r
o
m
th
e
p
r
e
v
i
o
u
s
s
t
u
d
ies
o
n
th
e
u
s
e
o
f
M
L
a
n
d
F
ME
A
s
e
p
a
r
a
tel
y
b
y
p
r
o
p
o
s
i
n
g
an
ML
-
FME
A
f
r
a
m
ew
o
r
k
w
h
e
r
e
t
h
e
r
is
k
-
p
r
io
r
i
tiz
ed
f
ea
tu
r
es
a
r
e
i
n
t
r
i
n
s
ic
all
y
i
n
te
g
r
at
e
d
i
n
t
o
p
r
e
d
i
cti
v
e
m
o
d
els
u
s
i
n
g
r
e
al
d
at
a
f
r
o
m
m
u
lti
p
l
e
h
o
s
p
ita
ls
.
T
h
is
i
n
te
g
r
at
io
n
n
o
t
o
n
l
y
d
eli
v
er
s
p
r
e
d
ic
ti
v
e
a
cc
u
r
ac
y
b
u
t
als
o
p
r
o
v
id
e
s
o
p
e
r
at
io
n
a
ll
y
in
te
r
p
r
eta
b
l
e
i
n
s
i
g
h
ts
,
c
o
m
b
in
in
g
t
h
e
p
o
we
r
o
f
ex
p
e
r
t
j
u
d
g
em
e
n
t
wit
h
d
ata
-
d
r
i
v
e
n
f
o
r
ec
asti
n
g
.
2.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
A
v
a
i
l
a
b
i
l
i
ty
o
f
c
r
i
t
i
c
a
l
m
ed
i
ca
l
e
q
u
i
p
m
e
n
t
s
p
a
r
e
p
ar
t
s
i
s
es
s
e
n
t
i
a
l
to
e
n
s
u
r
e
co
n
t
in
u
o
u
s
h
e
a
l
t
h
c
a
r
e
s
e
r
v
i
c
e
s
an
d
p
a
t
i
e
n
t
s
af
e
t
y
.
A
v
a
i
l
a
b
i
l
i
ty
o
f
c
o
m
p
o
n
en
ts
c
a
n
b
e
a
s
o
u
r
c
e
o
f
d
e
lay
a
n
d
c
a
u
s
e
m
a
j
o
r
d
i
s
r
u
p
t
i
o
n
i
n
o
p
er
a
t
i
o
n
s
,
w
h
i
c
h
c
an
c
o
m
p
r
o
m
i
s
e
cr
i
t
i
c
a
l
c
a
r
e
d
e
l
i
v
er
y
[
9
]
.
T
h
e
h
ea
l
th
c
a
r
e
in
d
u
s
t
r
y
h
a
s
t
r
a
d
i
t
io
n
a
l
ly
b
e
en
d
o
m
i
n
a
t
e
d
b
y
t
r
ad
i
t
i
o
n
a
l
m
a
in
t
e
n
a
n
ce
m
e
t
h
o
d
s
,
wh
i
ch
a
r
e
t
y
p
i
c
a
l
ly
b
a
s
e
d
o
n
r
e
a
c
t
iv
e
o
r
s
c
h
e
d
u
l
e
d
m
ai
n
t
en
a
n
c
e
.
H
o
we
v
e
r
,
th
e
s
e
m
e
th
o
d
s
ar
e
n
o
t
ad
a
p
t
iv
e
t
o
r
ea
l
eq
u
ip
m
en
t
c
o
n
d
i
t
io
n
s
o
r
to
n
ew
t
y
p
e
s
o
f
r
i
s
k
p
a
t
t
e
r
n
s
t
h
a
t
m
i
g
h
t
a
r
i
s
e,
r
e
s
u
l
t
in
g
i
n
i
n
ef
f
i
c
i
en
c
i
e
s
,
h
ig
h
c
o
s
t
s
,
a
n
d
u
n
f
o
r
e
s
ee
n
m
a
ch
i
n
e
d
o
w
n
t
im
e
s
[
1
0
]
.
I
n
r
ec
e
n
t
y
ea
r
s
,
to
o
v
er
c
o
m
e
t
h
ese
ch
allen
g
es,
h
ea
lth
ca
r
e
o
r
g
an
izatio
n
s
h
a
v
e
tu
r
n
ed
to
p
r
e
d
ictiv
e
an
d
d
ata
-
d
r
iv
e
n
m
ain
ten
an
ce
s
tr
ateg
ies.
ML
tech
n
iq
u
es
h
av
e
b
ee
n
wid
ely
ad
o
p
ted
in
th
e
in
d
u
s
tr
ial
an
d
m
an
u
f
ac
tu
r
in
g
d
o
m
ain
f
o
r
p
r
e
d
ictin
g
eq
u
ip
m
en
t
f
ailu
r
es
b
as
ed
o
n
th
e
h
is
to
r
ical
o
p
e
r
atio
n
a
l
d
ata,
p
ar
ticu
lar
ly
,
s
u
p
er
v
is
ed
lear
n
in
g
m
o
d
els
h
av
e
b
ee
n
u
s
ed
[
1
1
]
.
R
ec
en
t
r
esear
ch
h
as
s
h
o
w
n
h
o
w
ef
f
ec
tiv
e
A
I
-
d
r
iv
e
n
p
r
ed
ictiv
e
m
ain
te
n
an
ce
f
r
am
e
wo
r
k
s
ca
n
b
e
in
t
h
e
ar
ea
o
f
i
n
f
r
astru
ctu
r
e
an
d
f
ac
ilit
ies
m
an
ag
em
en
t,
with
th
e
p
o
ten
tial
to
b
o
o
s
t
ass
et
r
eliab
i
lity
,
m
in
im
ize
d
o
wn
tim
e,
an
d
f
ac
ilit
ate
d
ata
-
d
r
iv
en
m
ain
ten
a
n
ce
d
ec
is
io
n
s
[
1
2
]
.
L
ev
er
ag
in
g
m
o
d
els
lik
e
r
an
d
o
m
f
o
r
ests
(
R
F)
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es
(
SVM)
,
an
d
n
eu
r
al
n
etwo
r
k
s
,
s
u
p
er
v
is
ed
ML
h
as
s
tar
ted
to
b
e
u
s
ed
in
h
ea
lth
ca
r
e
to
n
o
t
o
n
ly
ass
is
t
in
th
e
d
iag
n
o
s
tic
p
r
o
ce
s
s
b
u
t
also
in
th
e
o
p
er
atio
n
o
f
h
ea
lth
ca
r
e
f
ac
ilit
ies,
s
u
ch
as
m
o
n
ito
r
in
g
e
q
u
ip
m
en
t
h
ea
lth
an
d
m
an
a
g
in
g
r
eso
u
r
ce
s
[
1
3
]
.
T
h
ese
m
o
d
els
ca
n
b
e
u
s
ed
f
o
r
p
r
o
ac
tiv
e
m
ain
ten
a
n
ce
s
ch
ed
u
lin
g
a
n
d
in
v
en
to
r
y
p
lan
n
in
g
,
b
ased
o
n
th
e
p
r
ed
ictio
n
o
f
th
e
p
o
te
n
tial
f
ail
u
r
e
o
f
c
o
m
p
o
n
en
ts
f
r
o
m
th
e
h
is
to
r
ic
m
ain
ten
an
ce
r
ec
o
r
d
s
,
t
h
e
s
en
s
o
r
s
,
a
n
d
th
e
en
v
ir
o
n
m
en
tal
co
n
d
itio
n
s
[
1
4
]
.
Ho
wev
er
,
p
r
ed
ictiv
e
m
o
d
els
in
h
ea
lth
ca
r
e
en
v
ir
o
n
m
e
n
ts
ar
e
m
ain
ly
ap
p
lie
d
to
clin
ical
d
ata
,
an
d
p
r
e
d
ictiv
e
in
f
r
astru
ctu
r
e
m
ain
ten
an
ce
,
in
p
ar
ticu
lar
f
o
r
s
p
ar
e
p
ar
ts
m
an
ag
em
en
t
,
is
an
em
er
g
in
g
r
esear
c
h
f
ield
[
1
5
]
.
W
h
ile
ML
ca
n
en
a
b
le
p
o
wer
f
u
l
p
r
ed
ictiv
e
an
aly
tics
,
ef
f
ec
tiv
e
s
p
ar
e
p
ar
ts
f
o
r
e
ca
s
tin
g
also
n
ee
d
s
s
tr
u
ctu
r
ed
r
is
k
p
r
io
r
itizatio
n
to
m
ak
e
s
u
r
e
h
ig
h
-
c
r
iticality
p
ar
ts
ar
e
p
r
o
p
er
ly
m
o
n
ito
r
ed
[
1
6
]
.
AI
-
b
ased
d
ec
is
io
n
s
u
p
p
o
r
t
s
y
s
tem
s
d
ev
elo
p
ed
u
n
d
e
r
th
e
I
n
d
u
s
tr
y
4
.
0
p
ar
ad
ig
m
h
av
e
b
ee
n
wid
ely
ap
p
lied
to
m
ain
ten
an
ce
p
lan
n
i
n
g
,
o
p
e
r
a
tio
n
o
p
tim
izatio
n
,
a
n
d
ass
et
life
cy
cle
m
an
ag
em
e
n
t
to
p
r
o
v
id
e
s
tr
u
ctu
r
e
d
in
tellig
en
ce
to
s
u
p
p
o
r
t c
o
m
p
le
x
en
g
in
ee
r
in
g
d
ec
is
io
n
s
[
1
7
]
.
FME
A
is
a
s
y
s
tem
atic
way
to
id
en
tify
p
o
s
s
ib
le
f
ailu
r
e
m
o
d
e
s
in
co
m
p
le
x
s
y
s
tem
s
an
d
to
al
s
o
b
e
ab
le
to
id
en
tify
r
is
k
b
y
u
s
in
g
r
is
k
p
r
io
r
ity
n
u
m
b
e
r
(
R
PN)
m
eth
o
d
o
lo
g
y
[
1
8
]
.
T
h
e
R
PN
is
a
q
u
a
n
titativ
e
ev
alu
atio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Ma
ch
in
e
lea
r
n
in
g
a
n
d
fa
ilu
r
e
mo
d
e
a
n
d
effec
ts
a
n
a
lysi
s
fo
r
s
u
s
ta
in
a
b
le
…
(
F
a
b
ia
n
Ha
lley
P
a
ta
A
lb
a
n
Da
ttu
)
4275
o
f
th
e
cr
iticality
o
f
th
e
co
m
p
o
n
en
t
in
ter
m
s
o
f
s
ev
er
ity
,
o
c
cu
r
r
en
ce
,
an
d
d
etec
tio
n
an
d
p
r
o
v
id
es
a
s
tr
u
ctu
r
ed
f
r
a
m
e
w
o
r
k
f
o
r
p
r
i
o
r
i
t
i
z
a
t
i
o
n
i
n
m
a
i
n
t
e
n
a
n
c
e
a
n
d
s
p
a
r
e
p
a
r
t
s
p
r
o
v
i
s
i
o
n
i
n
g
[
1
9
]
.
I
n
t
h
e
h
e
a
l
t
h
-
c
a
r
e
s
e
t
ti
n
g
,
F
M
E
A
h
as tr
ad
itio
n
ally
b
ee
n
u
s
ed
to
i
m
p
r
o
v
e
ev
alu
atio
n
s
o
f
eq
u
ip
m
en
t saf
ety
an
d
m
ain
ten
an
ce
p
l
an
n
in
g
[
2
0
]
.
R
ec
en
t
r
esear
ch
in
d
icate
s
th
at
co
m
b
in
in
g
th
e
o
u
tp
u
t
f
r
o
m
F
ME
A
with
ML
m
o
d
els
ca
n
al
s
o
en
h
an
ce
th
e
p
er
f
o
r
m
an
ce
o
f
p
r
e
d
ictiv
e
m
ain
ten
an
ce
b
y
p
r
io
r
itizin
g
th
e
lear
n
in
g
o
f
th
e
alg
o
r
ith
m
to
th
e
m
o
s
t
im
p
o
r
tan
t
f
ailu
r
e
ar
ea
s
[
2
1
]
.
T
h
is
in
teg
r
a
tio
n
h
as b
ee
n
tr
ie
d
in
m
a
n
u
f
ac
tu
r
in
g
an
d
ae
r
o
s
p
ac
e
,
b
u
t it
is
n
o
t f
u
lly
u
tili
ze
d
in
th
e
ar
ea
o
f
s
p
ar
e
p
ar
ts
m
an
a
g
em
en
t
in
h
ea
lth
ca
r
e
[
2
2
]
.
A
d
d
itio
n
ally
,
d
ee
p
lear
n
in
g
m
o
d
els
f
o
r
p
r
ed
ictiv
e
m
ain
ten
an
ce
h
a
v
e
b
ee
n
s
h
o
w
n
to
g
r
ea
tly
en
h
a
n
ce
th
e
p
e
r
f
o
r
m
an
ce
o
f
ass
et
m
an
ag
em
e
n
t
in
n
o
n
-
in
d
u
s
tr
ial
ar
ea
s
lik
e
f
in
an
ce
,
wh
er
e
a
d
v
an
ce
d
AI
m
o
d
els
ca
n
b
e
a
p
p
lied
to
d
iv
er
s
e
ass
et
-
in
ten
s
iv
e
s
ec
to
r
s
[
2
3
]
.
Fu
r
th
er
m
o
r
e
,
th
e
ad
o
p
tio
n
o
f
s
u
s
tain
ab
le
m
an
ag
em
en
t
p
r
ac
t
ices
with
tech
n
ical
ef
f
icien
cy
,
co
s
t
-
ef
f
ec
tiv
en
ess
,
an
d
lo
n
g
-
ter
m
o
p
er
atio
n
al
r
e
s
ilien
ce
is
in
cr
ea
s
in
g
ly
r
ec
o
g
n
ized
as
p
a
r
t
an
d
p
a
r
ce
l
o
f
m
o
d
er
n
h
ea
lth
ca
r
e
s
y
s
tem
s
[
2
4
]
.
T
h
is
s
tu
d
y
f
ills
th
e
g
ap
i
n
ex
is
tin
g
r
esear
c
h
an
d
p
r
esen
ts
a
n
o
v
el
ap
p
r
o
ac
h
o
f
u
s
in
g
R
PN
s
co
r
es
o
b
tain
ed
f
r
o
m
th
e
FME
A
with
s
u
p
er
v
is
ed
ML
alg
o
r
ith
m
s
to
p
r
ed
ict
th
e
n
ee
d
f
o
r
r
ep
l
ac
em
en
t
o
f
cr
itical
m
ed
ical
d
ev
ices'
s
p
ar
es.
T
h
e
p
r
o
p
o
s
ed
f
r
am
ew
o
r
k
is
a
b
len
d
o
f
d
ata
-
d
r
i
v
en
tech
n
i
q
u
es
an
d
r
is
k
-
b
ased
p
r
io
r
itizatio
n
,
with
th
e
o
b
jecti
v
e
o
f
en
h
an
cin
g
th
e
av
ailab
ilit
y
o
f
s
p
ar
e
p
ar
ts
,
m
a
x
im
izin
g
eq
u
ip
m
en
t
u
p
tim
e,
an
d
en
s
u
r
in
g
s
u
s
tain
ab
le
h
ea
lt
h
ca
r
e
o
p
e
r
atio
n
s
.
T
ab
le
1
p
r
o
v
i
d
es
a
s
u
m
m
ar
y
o
f
s
o
m
e
r
ele
v
an
t
s
tu
d
ies
in
th
e
p
ast
f
ew
y
ea
r
s
r
e
g
ar
d
in
g
th
e
u
s
e
o
f
ML
an
d
FME
A
tech
n
iq
u
es
f
o
r
p
r
e
d
ictiv
e
m
ain
ten
an
ce
an
d
p
ar
ts
m
an
ag
em
e
n
t.
Alth
o
u
g
h
th
e
u
s
e
o
f
ML
f
o
r
f
a
u
lt
d
etec
tio
n
an
d
m
an
u
f
ac
tu
r
in
g
ap
p
licatio
n
s
h
as
b
ee
n
s
h
o
wn
to
b
e
u
s
ef
u
l
in
p
r
ev
io
u
s
r
ese
ar
ch
[
1
1
]
,
[
2
4
]
f
ew
s
tu
d
ies
h
av
e
s
y
s
tem
atica
lly
co
n
s
id
er
ed
u
s
in
g
FME
A
r
is
k
m
etr
ics
to
g
eth
er
with
s
u
p
er
v
i
s
ed
ML
m
o
d
els
f
o
r
h
ea
lth
ca
r
e
s
p
ar
e
p
ar
ts
p
r
e
d
ictio
n
.
Pre
v
io
u
s
s
tu
d
ies
lo
o
k
at
eith
er
an
o
v
e
r
all
p
r
ed
ictiv
e
m
ain
ten
an
ce
m
o
d
el
with
o
u
t
r
is
k
p
r
io
r
itizatio
n
[
2
5
]
o
r
FME
A
im
p
r
o
v
em
en
t
with
o
u
t
th
e
ML
co
m
p
o
n
e
n
ts
[
6
]
.
T
o
f
ill
th
is
g
ap
,
th
is
s
tu
d
y
p
r
esen
ts
a
h
y
b
r
id
ML
-
F
ME
A
m
eth
o
d
b
ased
o
n
r
ea
l d
a
ta
p
r
o
v
id
e
d
b
y
th
e
s
ix
h
o
s
p
itals
,
in
v
o
lv
in
g
c
r
itical
m
ed
ical
d
ev
ices a
n
d
co
m
p
ar
in
g
th
e
r
esu
lts
o
f
v
ar
io
u
s
s
u
p
er
v
is
ed
lear
n
in
g
m
o
d
els to
im
p
r
o
v
e
th
e
p
r
ed
ictio
n
o
f
s
p
ar
e
p
ar
ts
n
ee
d
s
.
T
a
b
l
e
1
.
S
u
m
m
a
r
y
o
f
r
e
l
a
t
e
d
wo
r
k
s
o
n
ML
a
n
d
F
M
E
A
f
o
r
p
r
ed
i
c
t
i
v
e
m
a
i
n
t
e
n
a
n
c
e
a
n
d
s
p
a
r
e
p
a
r
t
s
m
a
n
a
g
e
m
e
n
t
R
e
f
e
r
e
n
c
e
A
p
p
l
i
c
a
t
i
o
n
M
L
t
e
c
h
n
i
q
u
e
s
I
n
t
e
g
r
a
t
i
o
n
w
i
t
h
F
M
EA
K
e
y
f
i
n
d
i
n
g
s
I
d
e
n
t
i
f
i
e
d
g
a
p
s
M
a
h
a
l
e
e
t
a
l
.
[
2
4
]
,
2
0
2
5
A
u
t
o
mo
t
i
v
e
p
r
e
d
i
c
t
i
v
e
mai
n
t
e
n
a
n
c
e
RF
a
n
d
S
V
M
N
o
t
a
p
p
l
i
e
d
M
L
m
o
d
e
l
s a
c
h
i
e
v
e
d
h
i
g
h
a
c
c
u
r
a
c
y
i
n
d
e
t
e
c
t
i
n
g
f
a
u
l
t
s
b
a
s
e
d
o
n
o
p
e
r
a
t
i
o
n
a
l
d
a
t
a
.
La
c
k
s
i
n
t
e
g
r
a
t
i
o
n
o
f
r
i
sk
a
n
a
l
y
si
s
f
o
r
s
p
a
r
e
p
a
r
t
p
r
i
o
r
i
t
i
z
a
t
i
o
n
;
f
o
c
u
s
e
d
o
n
a
u
t
o
m
o
t
i
v
e
.
La
mb
á
n
e
t
a
l
.
[
2
5
]
,
2
0
2
2
I
n
d
u
st
r
y
4
.
0
a
n
d
5
.
0
m
a
i
n
t
e
n
a
n
c
e
H
y
b
r
i
d
A
I
mo
d
e
l
s
N
o
t
a
p
p
l
i
e
d
P
r
o
p
o
se
d
p
r
e
d
i
c
t
i
v
e
f
r
a
mew
o
r
k
s fo
r
v
a
r
i
o
u
s
i
n
d
u
st
r
i
e
s
.
F
r
a
mew
o
r
k
s a
r
e
c
o
n
c
e
p
t
u
a
l
;
d
o
n
o
t
r
e
f
l
e
c
t
a
c
t
u
a
l
C
M
M
S
d
a
t
a
o
r
o
u
t
c
o
mes
o
f
t
h
e
sp
a
r
e
s.
S
o
l
t
a
n
a
l
i
a
n
d
R
a
me
z
a
n
i
[
6
]
,
2
0
2
3
S
a
f
e
t
y
-
c
r
i
t
i
c
a
l
sy
st
e
ms
F
M
EA
e
n
h
a
n
c
e
me
n
t
Y
e
s (S
mart
F
M
EA
)
P
r
o
p
o
se
d
sm
a
r
t
F
M
EA
f
o
r
r
i
s
k
p
r
i
o
r
i
t
i
z
a
t
i
o
n
i
n
I
n
d
u
st
r
y
4
.
0
.
N
o
i
n
t
e
g
r
a
t
i
o
n
w
i
t
h
M
L
a
l
g
o
r
i
t
h
ms
t
o
su
p
p
o
r
t
p
r
e
d
i
c
t
i
v
e
sp
a
r
e
p
a
r
t
s
p
l
a
n
n
i
n
g
.
K
a
u
si
k
e
t
a
l
.
[
1
1
]
,
2
0
2
5
M
a
n
u
f
a
c
t
u
r
i
n
g
q
u
a
l
i
t
y
a
ssu
r
a
n
c
e
S
V
M
a
n
d
ANN
N
o
t
a
p
p
l
i
e
d
C
o
m
p
a
r
a
t
i
v
e
st
u
d
y
o
f
M
L
p
e
r
f
o
r
ma
n
c
e
me
t
r
i
c
s
f
o
r
q
u
a
l
i
t
y
p
r
e
d
i
c
t
i
o
n
.
N
o
p
r
i
o
r
i
t
i
z
a
t
i
o
n
o
f
r
i
s
k
s,
a
n
d
m
e
d
i
c
a
l
e
q
u
i
p
m
e
n
t
c
o
n
t
e
x
t
.
Th
i
s
st
u
d
y
C
r
i
t
i
c
a
l
me
d
i
c
a
l
d
e
v
i
c
e
s
R
F
,
A
N
N
,
a
n
d
S
V
M
+
F
M
EA
Y
e
s (h
y
b
r
i
d
f
r
a
mew
o
r
k
)
A
c
h
i
e
v
e
d
1
.
0
0
a
c
c
u
r
a
c
y
a
n
d
i
mp
r
o
v
e
d
r
e
c
a
l
l
u
si
n
g
F
M
EA
f
e
a
t
u
r
e
s f
o
r
sp
a
r
e
p
a
r
t
s
p
r
e
d
i
c
t
i
o
n
.
B
r
i
d
g
e
s AI
mo
d
e
l
l
i
n
g
t
o
r
i
sk
-
b
a
se
d
m
a
i
n
t
e
n
a
n
c
e
i
n
h
e
a
l
t
h
c
a
r
e
b
a
se
d
o
n
a
c
t
u
a
l
C
M
M
S
d
a
t
a
.
3.
M
E
T
H
O
D
Fig
u
r
e
1
illu
s
tr
ates
a
r
esear
ch
m
eth
o
d
o
lo
g
y
em
p
lo
y
ed
t
o
co
n
s
tr
u
ct
a
p
r
ed
ictiv
e
m
o
d
el
f
o
r
th
e
m
an
ag
em
en
t
o
f
s
p
ar
e
p
ar
ts
i
n
m
ed
ical
eq
u
ip
m
en
t,
e
m
p
h
a
s
izin
g
s
u
s
tain
ab
ilit
y
,
an
d
ef
f
i
cien
cy
.
T
h
is
s
tu
d
y
o
u
tlin
es
th
e
a
p
p
r
o
ac
h
t
o
d
e
v
e
lo
p
in
g
a
p
r
ed
ictiv
e
s
p
ar
e
p
a
r
ts
m
an
ag
em
en
t
s
y
s
tem
f
o
r
m
e
d
ical
d
ev
ices
u
s
in
g
ML
.
T
h
e
r
esear
ch
b
eg
in
s
with
th
e
estab
lis
h
m
en
t
o
f
m
ain
o
b
jectiv
es
an
d
a
liter
atu
r
e
s
ea
r
ch
to
f
in
d
o
u
t
th
e
cu
r
r
en
t
p
r
ac
tices
an
d
lim
itatio
n
s
.
R
ec
o
r
d
s
o
n
m
ai
n
ten
an
ce
an
d
f
ailu
r
e
o
f
s
ix
im
p
o
r
tan
t
m
ed
ical
eq
u
ip
m
en
t
s
u
ch
as
v
en
tilato
r
s
,
d
ef
ib
r
illat
o
r
s
,
d
ialy
s
is
m
ac
h
in
es,
a
n
d
i
n
f
u
s
io
n
p
u
m
p
s
wer
e
o
b
tain
e
d
f
r
o
m
s
ix
h
o
s
p
itals
.
T
h
e
co
llected
d
ata
en
ab
le
FM
E
A
ex
ec
u
tio
n
b
y
id
en
tify
in
g
m
ain
f
ailu
r
e
m
o
d
es
with
cr
itical
co
m
p
o
n
e
n
ts
.
T
h
e
m
ain
ten
an
ce
d
ata
c
o
llected
r
a
n
g
ed
f
r
o
m
e
x
ten
s
iv
e
am
o
u
n
ts
o
f
p
r
e
v
en
tiv
e
m
ain
ten
an
ce
s
c
h
ed
u
les,
co
r
r
ec
tiv
e
wo
r
k
o
r
d
er
s
,
f
a
u
lt
d
escr
ip
tio
n
s
,
d
ev
ice
s
p
ec
if
icatio
n
s
,
co
m
p
o
n
e
n
t
f
ailu
r
e
h
is
to
r
y
,
an
d
FME
A
-
d
er
iv
ed
r
is
k
s
co
r
es.
T
h
e
d
ata
f
o
r
th
is
an
al
y
s
is
ca
m
e
f
r
o
m
th
e
c
o
m
p
u
te
r
ized
m
ain
ten
an
ce
m
an
ag
em
e
n
t
s
y
s
tem
(
C
MM
S)
p
latf
o
r
m
s
in
6
h
o
s
p
itals
f
o
r
t
h
e
2
0
1
8
-
2
0
2
3
p
er
io
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
5
,
Octo
b
er
2
0
2
6
:
4
2
7
3
-
4
2
8
2
4276
Fig
u
r
e
1
.
R
esear
ch
f
r
am
ewo
r
k
f
o
r
p
r
ed
ictiv
e
s
p
ar
e
p
ar
ts
m
an
ag
em
en
t in
m
e
d
ical
d
ev
ices u
s
in
g
ML
T
h
e
d
etail
o
f
th
e
d
ata
(
tim
estam
p
s
,
d
ev
ice
a
g
es,
m
ain
ten
an
c
e
h
is
to
r
ies,
an
d
d
escr
ip
tio
n
o
f
f
au
lts
)
an
d
th
e
r
ich
n
ess
o
f
th
e
d
ata
also
p
lay
an
im
p
o
r
tan
t
r
o
le
i
n
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
m
o
d
el.
Ven
tilato
r
s
,
d
ef
ib
r
illato
r
s
,
d
ialy
s
is
m
ac
h
in
es,
C
T
s
ca
n
n
er
s
an
d
in
f
u
s
io
n
p
u
m
p
s
wer
e
ch
o
s
en
b
ec
au
s
e
t
h
ey
ar
e
im
p
o
r
tan
t
to
p
atien
t
ca
r
e.
W
ith
h
ig
h
-
q
u
al
ity
an
d
co
n
s
is
ten
t
d
ata,
s
u
p
er
v
is
ed
lear
n
i
n
g
m
o
d
els
c
an
id
en
tify
co
m
p
lex
r
elatio
n
s
h
ip
s
b
etwe
en
co
m
p
o
n
en
t
d
eg
r
ad
atio
n
an
d
th
e
n
e
ed
f
o
r
r
ep
lace
m
e
n
t,
f
u
r
th
er
en
h
an
cin
g
f
ailu
r
e
p
r
ed
ictio
n
ca
p
a
b
ilit
ies.
T
h
e
FME
A
-
b
ased
ML
wo
r
k
f
lo
w
u
s
ed
in
th
e
s
tu
d
y
is
s
h
o
w
n
in
F
ig
u
r
e
2
.
T
h
e
wo
r
k
f
lo
w
s
tar
ts
with
th
e
d
ata
f
r
o
m
th
e
C
MM
S
,
wh
ich
is
f
o
llo
wed
b
y
th
e
s
ev
er
ity
,
o
cc
u
r
r
en
ce
,
an
d
d
etec
tio
n
ass
es
s
m
en
t,
R
PN
ca
lcu
latio
n
,
f
ea
tu
r
e
en
co
d
in
g
,
ML
,
m
o
d
el
d
ev
elo
p
m
en
t,
an
d
f
in
ally
th
e
p
r
e
d
ictio
n
o
f
s
p
ar
e
p
ar
ts
.
Fig
u
r
e
2
.
FME
A
-
b
ased
ML
wo
r
k
f
lo
w
T
h
e
s
ev
er
ity
(
s
)
,
o
cc
u
r
r
en
ce
(
o
)
,
a
n
d
d
etec
tio
n
(
D)
s
co
r
es
p
r
esen
ted
b
y
th
e
ex
p
er
ts
d
u
r
in
g
th
e
FME
A
wer
e
en
co
d
ed
n
u
m
er
ically
a
n
d
n
o
r
m
alize
d
b
ef
o
r
e
th
e
tr
ain
in
g
o
f
th
e
m
o
d
el.
A
c
o
m
p
o
s
ite
r
is
k
f
ea
tu
r
e
R
PN
=
S
×
O
×
D
was
ca
lcu
l
ated
an
d
u
s
ed
as
th
e
R
PN
.
E
a
ch
in
d
i
v
id
u
al
s
u
b
-
f
ac
to
r
an
d
t
h
e
r
esu
ltin
g
o
v
e
r
all
R
PN w
er
e
as
s
ess
ed
as in
p
u
ts
i
n
to
th
e
ML
m
o
d
els s
o
as to
ca
p
tu
r
e
g
r
an
u
lar
a
n
d
h
o
lis
tic
r
is
k
in
f
o
r
m
atio
n
.
T
h
e
FME
A
is
u
s
ed
to
cr
ea
te
an
ML
s
tu
d
y
u
tili
zin
g
th
r
ee
m
o
d
els,
s
u
ch
as
R
F,
ar
tific
i
al
n
eu
r
al
n
etwo
r
k
(
ANN)
,
an
d
SVM.
First,
th
ese
m
o
d
els
ar
e
d
e
s
ig
n
ed
to
f
o
r
ec
ast
p
o
s
s
ib
le
f
au
lt
to
o
p
tim
ize
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Ma
ch
in
e
lea
r
n
in
g
a
n
d
fa
ilu
r
e
mo
d
e
a
n
d
effec
ts
a
n
a
lysi
s
fo
r
s
u
s
ta
in
a
b
le
…
(
F
a
b
ia
n
Ha
lley
P
a
ta
A
lb
a
n
Da
ttu
)
4277
o
p
er
atio
n
al
e
f
f
icien
cy
.
T
h
ese
m
o
d
els
ar
e
th
e
n
ev
alu
ate
d
i
n
ter
m
s
o
f
th
ei
r
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
to
ass
ess
th
eir
p
er
f
o
r
m
an
ce
.
T
h
is
ap
p
r
o
ac
h
wo
u
l
d
f
ac
ilit
ate
a
s
tr
u
ctu
r
ed
m
ain
te
n
an
ce
p
r
o
ce
s
s
an
d
p
r
o
m
o
te
th
e
s
u
s
tain
ab
le
m
an
a
g
em
en
t
o
f
h
ea
lth
ca
r
e
eq
u
ip
m
e
n
t,
m
in
im
izin
g
d
o
w
n
tim
e
an
d
o
p
tim
izin
g
th
e
u
s
e
o
f
s
p
ar
e
p
a
r
ts
.
T
h
e
d
ata
f
o
r
th
is
s
tu
d
y
was
g
ath
er
ed
f
r
o
m
th
e
s
ix
h
o
s
p
itals
d
u
r
in
g
th
e
f
iv
e
-
y
ea
r
p
er
io
d
(
2
0
1
8
-
2
0
2
3
)
f
o
r
ten
cr
u
cial
m
ed
ical
d
ev
i
ce
s
.
A
to
tal
o
f
1
,
0
1
6
m
ain
ten
an
ce
r
ec
o
r
d
s
wer
e
ex
tr
ac
ted
,
wh
ich
in
clu
d
ed
attr
ib
u
tes
lik
e
d
e
v
ice
n
a
m
e,
f
a
ilu
r
e
d
escr
ip
tio
n
,
FME
A
s
co
r
e
s
(
S
OD)
,
R
PN,
p
r
ev
en
tiv
e
m
ai
n
ten
an
ce
h
is
to
r
ies,
d
ev
ice
ag
e,
an
d
d
e
v
ice
ty
p
e.
T
h
e
o
u
tp
u
t
lab
el
was
th
e
s
p
ar
e
p
ar
t
r
ep
lace
m
en
t
s
tatu
s
,
wh
ich
wa
s
"
r
ep
lace
m
en
t
r
eq
u
ir
ed
"
o
r
"n
o
r
ep
lace
m
en
t
r
eq
u
ir
ed
"
.
T
h
e
d
ata
was
p
ar
titi
o
n
ed
in
to
8
0
%
tr
ain
in
g
d
ata
an
d
2
0
% testi
n
g
d
ata
f
o
r
cr
ea
tin
g
a
n
d
test
in
g
ML
m
o
d
els.
R
F,
ANN
,
an
d
SV
M
alg
o
r
ith
m
s
wer
e
u
s
ed
f
o
r
th
e
m
o
d
el
d
ev
elo
p
m
e
n
t.
T
h
e
R
F
m
o
d
el
was
s
et
u
p
with
1
0
0
esti
m
ato
r
s
(
tr
ee
s
)
,
m
ax
im
u
m
d
ep
t
h
o
f
th
e
tr
ee
s
was
s
et
to
1
0
,
an
d
th
e
im
p
u
r
ity
m
ea
s
u
r
e
was
s
et
to
Gin
i.
T
h
e
ANN
was
a
th
r
ee
-
lay
er
n
etwo
r
k
with
6
4
,
3
2
,
a
n
d
1
6
n
eu
r
o
n
s
,
r
esp
ec
tiv
ely
,
w
ith
a
r
ec
tifie
d
lin
ea
r
u
n
it
(
R
eL
U
)
ac
tiv
atio
n
f
u
n
cti
o
n
an
d
tr
ain
ed
u
s
in
g
th
e
Ad
am
o
p
tim
izer
with
a
lear
n
in
g
r
ate
o
f
0
.
0
0
1
f
o
r
1
0
0
tr
ain
i
n
g
ep
o
ch
s
.
T
h
e
SV
M
was
tr
ain
ed
with
a
r
ad
ial
b
asis
f
u
n
ctio
n
(
R
B
F)
k
er
n
el,
wh
ich
was
u
s
ed
to
ca
p
tu
r
e
n
o
n
lin
ea
r
r
elatio
n
s
h
i
p
s
in
th
e
d
ata.
T
h
ese
co
n
f
ig
u
r
atio
n
s
wer
e
c
h
o
s
en
t
o
b
e
a
b
alan
ce
o
f
m
o
d
el
co
m
p
lex
ity
,
tr
ai
n
in
g
tim
e
a
n
d
p
r
ed
ictio
n
ca
p
ab
ilit
y
.
T
h
e
d
ataset
was
r
an
d
o
m
ly
p
a
r
titi
o
n
ed
in
to
8
0
%
tr
ain
in
g
d
a
ta
an
d
2
0
%
test
in
g
d
ata
b
ef
o
r
e
tr
ain
in
g
th
e
m
o
d
els.
T
h
e
d
ata
was
s
ca
led
an
d
e
n
co
d
e
d
as
n
ec
ess
ar
y
to
ac
c
o
m
m
o
d
ate
ML
alg
o
r
ith
m
s
.
Su
p
er
v
is
e
d
lear
n
in
g
m
o
d
els
wer
e
tr
ain
ed
with
in
p
u
t
p
ar
am
eter
s
in
clu
d
in
g
th
e
ty
p
e
o
f
d
ev
ice,
w
o
r
k
o
r
d
er
tr
a
d
e,
wo
r
k
o
r
d
er
s
tatu
s
,
f
au
lt
d
escr
ip
tio
n
,
an
d
FME
A
r
is
k
s
co
r
es,
an
d
th
e
o
u
t
p
u
t
la
b
el
was
wh
eth
e
r
o
r
n
o
t
s
p
ar
e
p
ar
ts
r
ep
lace
m
en
t
was n
ee
d
ed
.
Gr
id
s
ea
r
ch
was
u
s
ed
to
f
in
e
-
tu
n
e
h
y
p
er
p
ar
am
eter
s
a
n
d
m
ax
im
iz
e
p
er
f
o
r
m
an
ce
.
T
h
e
p
er
f
o
r
m
an
ce
o
f
th
e
m
o
d
els
was
ev
alu
ated
o
n
th
e
u
n
s
ee
n
test
d
ata
an
d
r
esu
lts
wer
e
co
m
p
u
te
d
u
s
in
g
co
n
f
u
s
io
n
m
atr
ices o
f
th
e
p
r
ed
icted
an
d
ac
tu
al
lab
v
alu
es; u
s
in
g
th
e
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
a
n
d
F1
-
s
co
r
e.
T
o
s
tr
en
g
th
ex
te
r
n
al
v
alid
ity
,
leav
e
o
n
e
h
o
s
p
ital
o
u
t
v
alid
ati
o
n
s
tr
ateg
y
was
im
p
lem
en
ted
.
A
to
tal
o
f
f
iv
e
h
o
s
p
ital
d
ata
wer
e
u
s
ed
f
o
r
tr
ain
in
g
an
d
th
e
r
est
was
u
s
ed
as
an
u
n
s
ee
n
test
s
et
in
ea
ch
iter
atio
n
.
I
t
was
p
er
f
o
r
m
ed
in
t
h
e
s
am
e
m
an
n
er
f
o
r
all
s
ix
h
o
s
p
itals
,
wh
ich
en
ab
led
to
g
en
er
alize
th
e
m
o
d
el
f
o
r
th
e
v
a
r
io
u
s
h
ea
lth
ca
r
e
en
v
ir
o
n
m
en
t.
T
o
p
r
ev
en
t
o
v
er
f
itti
n
g
an
d
to
m
ak
e
s
u
r
e
th
at
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
m
o
d
els
was
p
r
o
p
er
l
y
ev
alu
ate
d
,
a
1
0
-
f
o
l
d
cr
o
s
s
-
v
alid
atio
n
m
eth
o
d
was
u
s
ed
f
o
r
all
s
u
p
e
r
v
is
ed
lear
n
in
g
m
o
d
els.
T
o
ch
ec
k
th
e
ac
cu
r
ac
y
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
,
th
e
d
ata
s
et
was
d
iv
id
ed
r
an
d
o
m
ly
in
to
1
0
-
f
o
l
d
s
;
9
-
f
o
ld
s
wer
e
u
s
ed
f
o
r
tr
ain
in
g
an
d
1
-
f
o
ld
f
o
r
v
alid
atio
n
in
ea
ch
iter
atio
n
.
Per
f
o
r
m
an
ce
m
etr
ics
(
ac
c
u
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all
,
an
d
F1
-
s
co
r
e)
wer
e
ca
lcu
lated
f
o
r
ea
ch
f
o
ld
a
n
d
th
e
r
esu
lt is
r
ep
o
r
ted
as a
±
m
ea
n
s
tan
d
ar
d
d
ev
i
atio
n
o
f
all
f
o
ld
s
.
T
h
e
s
tu
d
y
co
m
b
in
ed
s
tr
u
ctu
r
ed
FME
A
r
esu
lts
with
s
o
p
h
is
ticated
ML
ar
ch
itectu
r
es
to
cr
ea
te
a
p
r
ed
ictiv
e
m
ain
ten
a
n
ce
f
r
am
e
wo
r
k
th
at
is
ab
le
to
p
r
ed
ict
s
p
ar
es with
a
h
ig
h
lev
el
o
f
ac
cu
r
ac
y
.
T
h
is
s
y
s
tem
atic
ap
p
r
o
ac
h
b
u
ild
s
o
n
tr
ad
itio
n
a
l
r
is
k
as
s
ess
m
en
t,
b
u
t
al
s
o
u
s
es
p
o
wer
f
u
l
d
ata
-
d
r
iv
e
n
r
is
k
ass
es
s
m
en
t
to
o
ls
to
im
p
r
o
v
e
th
e
ac
cu
r
ac
y
o
f
th
e
f
o
r
ec
ast,
in
k
ee
p
in
g
with
t
h
e
in
ten
t
to
cr
ea
te
a
s
u
s
tain
ab
le
a
n
d
p
r
o
-
ac
tiv
e
m
e
d
ical
d
ev
ice
m
a
n
ag
em
en
t
s
y
s
tem
.
A
p
air
ed
t
-
test
was
u
s
ed
o
n
th
e
cr
o
s
s
-
v
alid
atio
n
r
esu
lts
to
d
eter
m
in
e
if
t
h
e
d
if
f
er
en
ce
s
i
n
p
er
f
o
r
m
an
ce
b
etwe
en
th
e
m
o
d
els
was
s
tatis
tically
s
ig
n
if
ican
t.
T
h
e
n
u
ll
h
y
p
o
th
esis
was
th
at
th
er
e
was
n
o
m
o
d
el
th
at
p
er
f
o
r
m
ed
s
ig
n
if
ican
tly
b
etter
th
an
th
e
o
th
er
s
.
A
s
ig
n
if
ican
ce
lev
el
o
f
p
<
0
.
0
5
was
ad
o
p
ted
.
T
h
e
f
in
d
in
g
s
s
u
b
s
tan
tiated
th
e
co
n
clu
s
io
n
s
o
f
th
e
co
m
p
a
r
ativ
e
e
v
alu
atio
n
an
d
s
h
o
wed
th
at
th
e
p
r
o
p
o
s
ed
h
y
b
r
id
a
n
d
en
s
em
b
le
m
o
d
els y
ield
ed
s
tatis
tically
s
i
g
n
if
ican
t r
esu
lts
as c
o
m
p
ar
e
d
t
o
th
e
b
ase
m
o
d
els.
4.
RE
SU
L
T
S
AND
D
I
SCU
SS
I
O
N
T
ab
le
2
is
a
s
y
s
tem
izatio
n
o
f
v
ar
io
u
s
cr
itical
f
ailu
r
e
m
o
d
es
th
at
h
av
e
b
ee
n
id
en
tifie
d
as
a
r
esu
lt
o
f
FME
A
s
tu
d
ies,
s
u
ch
as
v
en
tilato
r
s
,
as
well
as
in
f
u
s
io
n
p
u
m
p
s
,
C
T
s
ca
n
n
er
s
an
d
p
ac
em
ak
er
s
.
Failu
r
e
ca
teg
o
r
ies
wer
e
s
h
o
w
n
in
a
s
ep
ar
ate
r
o
w
in
T
a
b
le
1
:
m
ec
h
an
ical
co
m
p
o
n
e
n
t
f
ailu
r
e
,
p
o
wer
f
ailu
r
e
,
s
en
s
o
r
m
alf
u
n
ctio
n
,
an
d
s
o
f
twar
e
er
r
o
r
.
I
t
also
c
o
n
tain
s
th
e
d
ev
ices
in
v
o
l
v
ed
with
th
ese
f
ailu
r
es,
t
h
eir
R
PNs
an
d
ML
ch
ar
ac
ter
is
tics
f
o
r
p
r
ed
ictio
n
an
aly
s
is
.
T
h
ese
v
alu
es
in
t
h
e
R
PN
r
ep
r
esen
t
th
e
s
ev
er
ity
an
d
th
e
d
a
n
g
er
o
f
f
ailu
r
e
m
o
d
es,
a
n
d
ca
n
th
u
s
i
n
f
o
r
m
th
e
m
ain
ten
a
n
ce
team
s
wh
ich
f
ailu
r
e
m
o
d
es
h
av
e
to
b
e
d
ea
lt
with
f
ir
s
t.
T
h
e
m
ec
h
an
ical
c
o
m
p
o
n
en
t
f
ailu
r
e
h
as
th
e
h
ig
h
est
R
PN
o
f
2
1
6
a
n
d
m
a
n
u
f
ac
tu
r
er
s
ar
e
a
d
v
is
ed
to
p
a
y
m
o
r
e
atten
tio
n
to
th
e
f
o
r
ec
asti
n
g
o
f
s
p
ar
e
p
ar
ts
an
d
p
r
ev
e
n
tio
n
s
to
th
is
m
o
s
t c
r
itical
f
au
lt.
Alth
o
u
g
h
FME
A
is
a
s
tr
u
ctu
r
ed
m
eth
o
d
f
o
r
r
is
k
p
r
io
r
itiza
tio
n
,
it
is
s
u
b
jectiv
e
an
d
s
tatic
b
ec
au
s
e
s
ev
er
ity
,
o
cc
u
r
r
e
n
ce
,
an
d
d
ete
ctio
n
s
co
r
es c
an
b
e
d
if
f
er
en
t i
n
d
if
f
er
en
t in
s
titu
tio
n
s
an
d
v
ar
y
with
tim
e
an
d
r
ely
o
n
ex
p
er
t
ju
d
g
em
en
t.
T
h
is
m
e
an
s
th
at
tr
ad
itio
n
al
FME
A
alo
n
e
m
ay
n
o
t
b
e
s
u
f
f
icien
t
to
r
e
f
lect
th
e
ch
an
g
in
g
f
ailu
r
e
p
atter
n
s
in
c
o
m
p
lex
h
e
alth
ca
r
e
s
ettin
g
s
.
W
h
en
p
r
o
ce
s
s
in
g
p
ast
m
ain
ten
an
ce
r
ec
o
r
d
s
,
th
e
ML
f
ea
tu
r
es,
s
u
ch
as
ass
et
d
escr
ip
tio
n
,
W
OT
r
ad
e,
an
d
wo
r
k
s
tatu
s
,
ar
e
in
clu
d
ed
,
af
f
ec
tin
g
th
e
lear
n
i
n
g
ca
p
ab
ilit
y
o
f
th
e
m
o
d
el.
T
h
ese
p
r
o
p
er
ties
allo
w
th
e
s
y
s
tem
to
id
en
tify
p
atter
n
s
s
u
ch
as
ex
ten
d
ed
p
er
io
d
s
o
f
m
ec
h
an
ical
f
ailu
r
e
an
d
s
en
s
o
r
r
ea
d
in
g
s
;
p
atter
n
s
th
at
it
co
r
r
elate
s
with
s
p
ec
if
ic
d
ev
ices
an
d
r
ep
air
tr
ad
es.
T
h
e
p
r
ed
ictiv
e
s
y
s
tem
o
p
tim
izes m
ain
ten
an
ce
p
lan
n
i
n
g
b
y
p
r
e
d
ictin
g
p
a
r
t n
ee
d
s
,
m
in
im
izin
g
s
y
s
tem
d
o
wn
tim
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
5
,
Octo
b
er
2
0
2
6
:
4
2
7
3
-
4
2
8
2
4278
T
ab
le
2
.
Failu
r
e
m
o
d
es a
n
d
M
L
f
ea
tu
r
es
f
o
r
s
p
ar
e
p
a
r
t p
r
e
d
ictio
n
in
cr
itical
m
ed
ical
d
e
v
ic
es
F
M
EA
f
a
i
l
u
r
e
mo
d
e
D
e
v
i
c
e
(
s)
R
P
N
M
L
f
e
a
t
u
r
e
s
R
e
l
e
v
a
n
c
e
t
o
s
p
a
r
e
p
a
r
t
p
r
e
d
i
c
t
i
o
n
M
e
c
h
a
n
i
c
a
l
c
o
m
p
o
n
e
n
t
f
a
i
l
u
r
e
V
e
n
t
i
l
a
t
o
r
2
1
6
A
sset
D
e
s
c
r
i
p
t
i
o
n
,
W
O
Tr
a
d
e
,
W
o
r
k
S
t
a
t
u
s
Th
e
m
o
st
c
o
mm
o
n
m
o
d
e
o
f
f
a
i
l
u
r
e
:
t
h
e
m
o
d
e
l
d
e
t
e
c
t
s
r
e
p
e
t
i
t
i
v
e
a
ss
e
t
-
t
r
a
d
e
p
a
t
t
e
r
n
s
a
sso
c
i
a
t
e
d
w
i
t
h
c
o
m
p
o
n
e
n
t
s
u
b
s
t
i
t
u
t
i
o
n
s.
P
o
w
e
r
f
a
i
l
u
r
e
I
n
c
u
b
a
t
o
r
,
P
a
c
e
m
a
k
e
r
,
I
n
f
u
si
o
n
P
u
mp
1
4
4
-
168
A
sset
D
e
s
c
r
i
p
t
i
o
n
,
W
o
r
k
S
t
a
t
u
s
M
o
d
e
l
i
d
e
n
t
i
f
i
e
s
a
sse
t
s
a
n
d
t
a
s
k
s
w
h
e
r
e
p
o
w
e
r
d
i
sr
u
p
t
i
o
n
s
i
m
p
a
i
r
d
e
v
i
c
e
f
u
n
c
t
i
o
n
a
l
i
t
y
,
r
e
su
l
t
i
n
g
i
n
t
h
e
n
e
c
e
ss
i
t
y
f
o
r
s
p
a
r
e
p
a
r
t
s.
S
e
n
s
o
r
ma
l
f
u
n
c
t
i
o
n
C
T
S
c
a
n
n
e
r
,
P
a
c
e
m
a
k
e
r
1
6
8
,
1
4
7
A
sset
D
e
s
c
r
i
p
t
i
o
n
,
W
O
Tr
a
d
e
Th
e
mo
d
e
l
i
d
e
n
t
i
f
i
e
s
d
e
v
i
c
e
s
a
n
d
t
r
a
n
sa
c
t
i
o
n
s
r
e
l
a
t
e
d
t
o
r
e
c
u
r
r
i
n
g
se
n
so
r
-
b
a
se
d
p
r
o
b
l
e
ms
r
e
q
u
i
r
i
n
g
r
e
p
l
a
c
e
me
n
t
s
.
S
o
f
t
w
a
r
e
e
r
r
o
r
P
a
c
e
m
a
k
e
r
1
4
7
P
r
o
b
l
e
m
d
e
s
c
r
i
p
t
i
o
n
s
,
W
o
r
k
S
t
a
t
u
s
A
v
a
i
l
a
b
l
e
p
r
o
b
l
e
m
d
e
scr
i
p
t
i
o
n
s
i
n
d
i
c
a
t
e
j
o
b
s
i
n
i
t
i
a
t
e
d
b
y
p
r
o
g
r
a
mm
i
n
g
o
r
c
o
n
t
r
o
l
mal
f
u
n
c
t
i
o
n
s.
T
h
e
ML
id
en
tific
atio
n
o
f
ass
e
t
f
ailu
r
e
m
o
d
es
th
at
s
ig
n
if
ican
tly
im
p
ac
t
s
p
ar
e
p
ar
t
n
ee
d
s
is
s
h
o
wn
in
th
e
last
co
lu
m
n
o
f
t
h
e
tab
le
.
T
h
is
d
o
cu
m
e
n
t
ac
ts
as
a
b
r
id
g
e
b
etwe
en
tr
ad
itio
n
al
r
i
s
k
ass
ess
m
en
t
an
d
m
ain
ten
an
ce
p
r
ep
ar
atio
n
b
as
ed
o
n
d
ata.
Mo
d
el
ev
alu
ati
o
n
was
d
o
n
e
b
ased
o
n
th
e
m
o
d
els'
p
r
ed
ictiv
e
p
er
f
o
r
m
an
ce
as
p
r
esen
ted
i
n
T
ab
le
3
.
Stan
d
ar
d
m
etr
ics
d
e
r
iv
ed
f
r
o
m
th
e
m
o
d
el
p
r
ed
ict
io
n
s
o
n
th
e
test
in
g
d
ataset
wer
e
u
s
ed
to
ev
alu
ate
t
h
e
m
o
d
els,
as d
escr
ib
e
d
as f
o
ll
o
ws
.
Sh
ap
ley
ad
d
itiv
e
ex
p
lan
atio
n
s
(
SHAP)
h
av
e
b
ee
n
u
s
ed
to
e
n
h
an
ce
in
ter
p
r
etab
ilit
y
at
b
o
th
th
e
g
lo
b
al
an
d
lo
ca
l
lev
el.
SHAP
v
alu
es
p
r
o
v
id
e
a
s
en
s
e
o
f
th
e
in
d
i
v
id
u
al'
s
co
n
tr
ib
u
tio
n
o
f
ea
ch
f
ea
t
u
r
e
to
th
e
p
r
ed
ictio
n
an
d
allo
w
to
clea
r
ly
u
n
d
e
r
s
tan
d
wh
y
a
p
ar
ticu
lar
s
p
ar
e
p
ar
t
r
ep
lace
m
en
t
d
ec
is
io
n
was
m
ad
e.
T
h
is
in
ter
p
r
etab
ilit
y
lay
e
r
en
a
b
les
b
io
m
ed
ical
en
g
in
ee
r
s
an
d
m
ai
n
ten
an
ce
m
a
n
ag
er
s
to
b
r
i
d
g
e
t
h
e
g
ap
b
etwe
en
t
h
e
m
o
d
el
o
u
tp
u
t
an
d
clin
ically
an
d
o
p
er
atio
n
ally
m
ea
n
in
g
f
u
l
f
ac
to
r
s
to
b
o
o
s
t
co
n
f
i
d
en
ce
,
au
d
ib
ilit
y
,
an
d
th
e
p
r
ac
tical
ad
o
p
tio
n
o
f
t
h
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
.
T
h
e
R
F
m
o
d
el'
s
S
HAP
s
u
m
m
ar
y
p
lo
t
is
s
h
o
wn
in
Fig
u
r
e
3
.
F
ig
u
r
e
3
s
h
o
ws
th
e
co
n
tr
ib
u
tio
n
o
f
Ass
etDe
s
cr
ip
tio
n
,
Pro
b
lem
_
Descr
ip
tio
n
,
Ass
etNu
m
b
er
,
W
o
r
k
Statu
s
,
an
d
W
OT
r
ad
e
to
th
e
p
r
ed
ictio
n
o
u
tp
u
t.
T
h
e
v
alu
e
o
f
ea
c
h
f
ea
t
u
r
e
is
r
ep
r
esen
ted
b
y
th
e
ab
s
o
lu
te
SHAP
v
alu
e
;
lar
g
er
v
alu
es
m
ea
n
th
at
th
e
f
e
atu
r
e
h
as
a
g
r
ea
te
r
im
p
ac
t
o
n
th
e
m
o
d
el;
p
o
s
itiv
e
(
n
eg
ativ
e)
v
alu
es
m
ea
n
th
at
th
e
f
ea
tu
r
e
in
c
r
ea
s
es (
d
ec
r
ea
s
es)
th
e
p
r
o
b
ab
ilit
y
o
f
p
r
ed
ictin
g
th
e
n
ee
d
f
o
r
t
h
e
s
p
ar
e
p
a
r
t r
ep
lace
m
en
t.
Fig
u
r
e
3
.
SHAP su
m
m
ar
y
p
lo
t
f
o
r
th
e
R
F
m
o
d
el
T
h
e
ev
alu
atio
n
m
et
r
ics
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
wer
e
ca
lcu
lated
b
a
s
ed
o
n
th
e
p
r
ed
ictio
n
s
m
a
d
e
b
y
ea
ch
ML
m
o
d
el
o
n
th
e
test
in
g
d
ataset,
wh
ich
co
m
p
r
is
ed
2
0
%
o
f
th
e
to
tal
m
ain
te
n
an
ce
r
ec
o
r
d
s
.
Fo
r
ea
c
h
r
ec
o
r
d
,
th
e
m
o
d
el
p
r
e
d
icted
if
a
s
p
ar
e
p
a
r
t
r
ep
lace
m
en
t
was
n
ec
ess
ar
y
an
d
co
m
p
ar
ed
th
ese
lab
els
to
th
e
ac
tu
al
o
u
tco
m
es.
B
ased
o
n
th
is
co
m
p
ar
is
o
n
,
t
h
e
n
u
m
b
er
o
f
tr
u
e
p
o
s
itiv
es
(
T
P),
tr
u
e
n
eg
ativ
es
(
T
N)
,
f
alse
p
o
s
itiv
es
(
FP
)
,
an
d
f
alse
n
eg
ativ
es
(
FN)
wer
e
o
b
tain
ed
a
n
d
u
s
ed
to
ca
lcu
lat
e
th
e
p
er
f
o
r
m
a
n
ce
m
ea
s
u
r
es.
Acc
u
r
ac
y
is
th
e
o
v
er
all
co
r
r
ec
t
n
ess
o
f
th
e
m
o
d
el,
p
r
ec
is
io
n
is
th
e
p
er
c
en
tag
e
o
f
p
r
ed
icte
d
r
ep
lace
m
en
ts
th
at
ar
e
c
o
r
r
ec
t,
an
d
r
ec
all
is
th
e
p
er
ce
n
tag
e
o
f
n
ee
d
ed
r
ep
lace
m
e
n
ts
th
at
ar
e
co
r
r
ec
tly
p
r
ed
icted
.
As
th
e
F1
-
s
co
r
e
i
s
th
e
h
ar
m
o
n
ic
m
ea
n
o
f
p
r
ec
is
io
n
an
d
r
ec
al
l,
it
in
d
icate
s
th
at
th
er
e
is
a
b
alan
ce
b
etwe
en
th
e
n
u
m
b
er
o
f
r
e
p
lace
m
en
ts
co
r
r
ec
tly
id
en
tifie
d
an
d
th
e
n
u
m
b
er
o
f
f
alse
alar
m
s
.
T
h
ese
m
etr
ics
d
o
n
o
t
o
n
ly
m
ea
s
u
r
e
th
e
co
r
r
ec
tn
ess
o
f
th
e
o
v
er
all
m
o
d
el,
b
u
t
also
a
d
etailed
ass
e
s
s
m
en
t
o
f
h
o
w
well
ea
ch
m
o
d
el
ca
n
b
e
u
s
ed
f
o
r
p
r
ed
ictiv
e
m
ain
ten
an
ce
an
d
p
la
n
n
in
g
o
f
s
p
ar
e
p
ar
ts
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Ma
ch
in
e
lea
r
n
in
g
a
n
d
fa
ilu
r
e
mo
d
e
a
n
d
effec
ts
a
n
a
lysi
s
fo
r
s
u
s
ta
in
a
b
le
…
(
F
a
b
ia
n
Ha
lley
P
a
ta
A
lb
a
n
Da
ttu
)
4279
T
ab
le
3
p
r
esen
ts
th
r
ee
p
r
e
d
ictio
n
s
o
f
ess
en
tial
m
ed
ical
eq
u
i
p
m
en
t
s
p
ar
e
p
ar
ts
th
at
h
av
e
c
o
m
e
f
r
o
m
an
ANN
an
d
R
F
alo
n
g
with
SVM.
T
h
e
d
eter
m
in
atio
n
o
f
t
h
e
p
r
e
d
ictiv
e
ac
cu
r
ac
y
an
d
d
ep
en
d
ab
ilit
y
o
f
th
e
m
o
d
els
is
d
o
n
e
u
s
in
g
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
F1
-
s
co
r
e
an
d
r
ec
all.
I
n
th
e
f
in
al
a
n
aly
s
is
,
b
o
th
ANN
an
d
R
F
wer
e
ab
le
to
ac
h
iev
e
1
.
0
0
test
ac
cu
r
ac
y
d
u
e
to
co
r
r
ec
tly
id
en
tif
y
i
n
g
1
0
0
%
o
f
test
s
am
p
les.
Stro
n
g
p
er
f
o
r
m
an
c
e
o
f
th
e
SVM
m
o
d
el
was
d
em
o
n
s
tr
ated
,
wh
ich
lead
s
to
ac
h
iev
in
g
0
.
9
3
ac
cu
r
ac
y
th
at
is
b
etter
th
an
th
e
o
th
er
m
etr
ics.
T
h
ese
ML
m
o
d
els
wer
e
s
h
o
wn
to
d
etec
t
ce
r
tain
m
ac
h
in
e
p
ar
ts
lik
ely
t
o
f
ail.
Fo
r
ex
am
p
le,
t
h
e
R
F
m
o
d
el
id
e
n
tifie
d
th
e
m
e
ch
an
ical
d
r
iv
e
ass
em
b
ly
o
f
th
e
v
en
tilato
r
as
a
co
m
m
o
n
f
ailu
r
e
p
o
in
t;
th
is
was
id
en
tifie
d
b
y
h
ig
h
R
PN
s
co
r
e
in
th
e
FME
A.
W
ith
th
e
co
m
p
u
ted
to
m
o
g
r
a
p
h
y
(
C
T
)
s
ca
n
n
er
s
,
f
r
e
q
u
en
t
f
o
r
ec
asti
n
g
’
s
wer
e
ass
o
ciate
d
with
X
-
r
ay
tu
b
e
s
en
s
o
r
f
ailu
r
e
.
L
ik
ewise,
f
o
r
in
f
u
s
io
n
p
u
m
p
s
,
th
er
e
we
r
e
ea
r
l
y
s
ig
n
s
o
f
p
o
wer
s
u
p
p
ly
b
o
ar
d
f
ailu
r
e.
T
h
e
r
esu
lts
wer
e
co
r
r
o
b
o
r
ate
d
with
m
ain
ten
an
c
e
h
is
to
r
y
r
ec
o
r
d
s
an
d
s
h
o
wed
th
at
th
e
p
r
ed
icted
p
a
r
ts
d
id
h
av
e
m
o
r
e
in
ter
v
e
n
tio
n
s
an
d
r
ep
lace
m
e
n
ts
d
u
r
in
g
th
e
p
r
e
v
io
u
s
y
ea
r
s
o
f
o
p
e
r
atio
n
.
T
ab
le
3
.
Me
an
±
SD p
er
f
o
r
m
a
n
ce
o
f
ML
m
o
d
els u
s
in
g
1
0
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
M
o
d
e
l
A
c
c
u
r
a
c
y
P
r
e
c
i
s
i
o
n
F1
-
sc
o
re
R
e
c
a
l
l
ANN
1
.
0
0
0
.
8
8
0
.
9
0
0
.
8
7
RF
1
.
0
0
0
.
8
8
0
.
9
0
0
.
9
3
S
V
M
0
.
9
3
0
.
8
3
0
.
8
8
0
.
9
4
A
s
en
s
itiv
ity
an
aly
s
is
was
d
o
n
e
to
ex
p
lo
r
e
t
h
e
ef
f
ec
t
o
f
ch
an
g
es
in
th
e
weig
h
ts
o
f
t
h
e
FMR
A
s
u
b
-
f
ac
to
r
s
o
n
th
e
m
o
d
el
p
er
f
o
r
m
an
ce
an
d
m
ain
ten
an
ce
d
ec
is
io
n
s
.
I
n
p
a
r
ticu
lar
,
th
e
weig
h
tin
g
o
f
S,
O,
a
n
d
D
was
v
ar
ied
in
th
e
r
is
k
s
co
r
in
g
ex
p
r
ess
io
n
k
ee
p
in
g
th
e
s
a
m
e
ML
p
ip
elin
e.
T
h
e
r
esu
lts
s
h
o
w
th
at
r
ec
all
is
in
cr
ea
s
ed
f
o
r
h
i
g
h
cr
iticality
c
o
m
p
o
n
en
ts
b
y
in
cr
ea
s
in
g
th
e
weig
h
tin
g
p
lace
d
o
n
s
ev
er
ity
(
m
is
s
ed
f
ailu
r
e)
,
b
u
t
to
o
m
u
c
h
weig
h
tin
g
o
n
o
cc
u
r
r
en
ce
m
ay
lea
d
to
m
o
r
e
f
alse
p
o
s
itiv
es
an
d
less
p
r
ec
is
io
n
.
I
n
s
u
m
m
ar
y
,
b
alan
ce
d
weig
h
tin
g
o
f
S
,
O
,
a
n
d
D
o
f
f
er
s
th
e
b
est
o
v
er
all
p
er
f
o
r
m
an
ce
in
ter
m
s
o
f
ac
c
u
r
ac
y
,
F1
-
s
co
r
e
,
a
n
d
r
ec
all
,
en
ab
lin
g
c
o
n
s
is
ten
t
r
is
k
-
b
ased
s
p
ar
e
p
ar
ts
p
lan
n
in
g
.
T
h
e
r
esu
lts
o
f
th
e
1
0
-
f
o
ld
cr
o
s
s
-
v
alid
atio
n
wer
e
u
s
ed
to
p
er
f
o
r
m
p
air
ed
t
-
test
s
o
n
th
e
F1
-
s
co
r
e
d
is
tr
ib
u
tio
n
s
o
f
th
e
d
if
f
e
r
en
t
m
o
d
els
to
s
tatis
tica
lly
ev
alu
ate
th
e
s
ig
n
if
ican
ce
o
f
th
e
d
if
f
er
en
ce
s
in
th
eir
p
er
f
o
r
m
an
ce
s
.
T
h
e
r
esu
lts
s
h
o
w
th
at
th
e
R
F
m
o
d
el
was
s
tatis
t
ically
s
ig
n
if
ican
t
(
p
<
0
.
0
5
)
th
a
n
SVM,
s
u
g
g
esti
n
g
th
at
b
o
th
m
o
d
els
h
av
e
s
im
ilar
p
r
ed
ictiv
e
ca
p
ab
ilit
ies.
Pre
cisi
o
n
lev
els
ar
e
c
o
n
v
er
g
in
g
b
etwe
en
ANN
an
d
R
F,
b
u
t
th
eir
F1
-
s
co
r
es
r
ev
ea
l
litt
le
d
if
f
er
en
ce
s
an
d
s
h
o
w
d
if
f
er
en
t
tr
e
n
d
s
in
th
e
r
elatio
n
s
h
ip
b
etwe
en
th
e
s
en
s
itiv
ity
an
d
th
e
p
r
ec
is
io
n
-
r
ec
all
b
alan
ce
.
T
h
e
p
er
f
o
r
m
an
ce
o
f
ANN
was
0
.
8
7
r
ec
all
,
an
d
R
F
was
0
.
9
3
r
ec
all;
R
F
in
cr
ea
s
e
d
its
ab
ilit
y
to
ca
p
tu
r
e
th
e
tr
u
e
n
ee
d
f
o
r
s
p
ar
e
p
ar
ts
.
T
h
o
u
g
h
it
h
ad
a
s
lig
h
tly
lo
wer
v
alu
e
f
o
r
p
r
ec
is
io
n
o
f
0
.
8
3
,
th
e
SVM
m
o
d
el
h
a
d
a
b
etter
p
ar
t
n
ee
d
id
e
n
tific
atio
n
,
wh
ich
g
a
v
e
it
a
s
u
p
r
em
e
r
ec
all
v
alu
e
o
f
0
.
9
4
.
B
o
th
ANN
an
d
R
F
m
o
d
els
o
f
f
er
th
e
b
est
p
r
ed
ictiv
e
ac
cu
r
ac
y
,
with
SVM
b
ein
g
th
e
b
est
o
p
tio
n
b
etwe
en
co
m
p
lex
ity
an
d
g
en
e
r
aliza
b
ilit
y
an
d
in
ter
p
r
etab
ilit
y
.
As
p
er
th
e
p
e
r
f
o
r
m
a
n
ce
cr
iter
ia,
th
e
R
F
m
o
d
el
is
th
e
b
est
o
n
e
f
o
r
th
e
s
p
ar
e
p
ar
ts
p
r
e
d
ictio
n
.
I
t
ac
h
iev
es
a
p
er
f
ec
t
p
r
ec
is
io
n
(
1
.
0
0
)
,
s
tab
ilit
y
o
n
p
r
ec
is
io
n
(
0
.
8
8
)
,
F1
-
s
co
r
e
(
0
.
9
0
)
,
an
d
r
e
ca
ll
(
0
.
9
3
3
)
,
w
h
ich
in
d
icate
h
ig
h
ac
cu
r
ac
y
an
d
r
eliab
ilit
y
in
id
en
tify
in
g
tr
u
e
n
ee
d
s
f
o
r
s
p
ar
e
p
ar
ts
.
I
t
p
er
f
o
r
m
s
well
o
n
all
m
ea
s
u
r
es
an
d
is
in
ter
p
r
etab
le
an
d
r
o
b
u
s
t,
m
ak
in
g
it th
e
b
est m
o
d
el
f
o
r
p
r
ac
tical
u
s
e.
T
h
e
r
esu
lts
o
b
tain
ed
f
r
o
m
th
es
e
ML
m
o
d
els,
wh
ich
p
r
o
v
id
e
p
r
ed
ictiv
e
in
s
ig
h
ts
,
ar
e
v
e
r
y
r
e
lev
an
t
f
o
r
th
e
o
p
er
atio
n
o
f
h
o
s
p
itals
.
B
y
p
r
o
ac
tiv
ely
id
en
tify
in
g
h
ig
h
-
r
is
k
co
m
p
o
n
e
n
ts
,
b
io
m
ed
ical
en
g
in
ee
r
in
g
d
ep
ar
tm
en
ts
ca
n
s
tr
ateg
ically
k
ee
p
cr
u
cial
s
p
ar
e
p
ar
ts
o
n
h
an
d
,
m
i
n
im
izin
g
eq
u
i
p
m
en
t
d
o
wn
tim
e
an
d
em
er
g
en
cy
p
r
o
cu
r
e
m
en
t
e
x
p
en
s
es.
T
h
e
p
r
o
p
o
s
ed
f
r
a
m
ewo
r
k
wo
u
ld
d
em
o
n
s
tr
ate
tan
g
ib
le
im
p
r
o
v
em
en
ts
to
war
d
s
s
u
s
tain
ab
ilit
y
an
d
o
p
er
atio
n
al
ef
f
icien
cies,
i
n
clu
d
i
n
g
p
o
ten
tial
r
ed
u
ctio
n
s
o
f
1
8
-
2
2
%
in
em
er
g
e
n
cy
s
p
ar
e
p
ar
ts
p
r
o
cu
r
em
e
n
t
an
d
1
2
-
1
5
h
o
u
r
s
o
f
eq
u
ip
m
en
t
d
o
wn
tim
e
p
er
d
ev
ice
an
d
y
e
ar
.
T
h
ese
r
ep
o
r
ted
r
ed
u
ctio
n
s
a
r
e
n
o
t
t
h
eo
r
etica
l
esti
m
ates
b
u
t
ar
e
b
ased
o
n
th
e
an
aly
s
is
o
f
r
etr
o
s
p
ec
tiv
e
d
ata
f
r
o
m
C
MM
S
an
d
s
im
u
latio
n
o
f
m
o
d
el
-
b
ased
p
r
ev
en
tiv
e
in
ter
v
en
tio
n
.
T
h
ese
im
p
r
o
v
em
e
n
ts
aim
at
o
p
tim
iz
in
g
r
eso
u
r
ce
s
a
n
d
s
er
v
ices,
m
ax
im
izin
g
co
s
t
-
ef
f
ec
tiv
en
ess
,
an
d
m
ain
tain
in
g
c
o
n
tin
u
ity
o
f
h
ea
lth
-
ca
r
e
p
r
o
v
i
s
io
n
in
g
.
Pre
d
ictiv
e
r
is
k
p
r
io
r
itizes s
ch
ed
u
led
m
ain
ten
an
ce
ac
tio
n
s
,
th
e
r
eb
y
im
p
r
o
v
in
g
r
eso
u
r
ce
a
n
d
tech
n
ician
ef
f
icien
cies.
Fu
r
th
er
m
o
r
e
,
s
er
v
ice
co
n
tr
ac
t
s
with
th
ir
d
p
ar
ties
ca
n
b
e
ad
ju
s
ted
,
an
d
h
ea
lth
ca
r
e
f
ac
ilit
ies
ca
n
b
e
tr
an
s
itio
n
ed
to
war
d
s
a
m
o
r
e
p
r
o
ac
tiv
e
an
d
s
u
s
tain
ab
le
ass
et
m
an
ag
em
en
t
s
tr
ateg
y
,
en
h
a
n
ci
n
g
th
e
r
eliab
ilit
y
o
f
p
atien
t
ca
r
e
d
eliv
er
y
.
T
h
ese
p
r
ed
ictiv
e
m
o
d
els
co
u
ld
p
o
te
n
tially
b
e
in
co
r
p
o
r
ated
in
to
h
o
s
p
itals
'
ex
is
tin
g
C
MM
S
s
y
s
tem
,
p
r
o
v
id
in
g
r
e
al
-
tim
e
m
o
n
ito
r
in
g
d
ash
b
o
ar
d
s
th
at
h
ig
h
lig
h
t
at
-
r
is
k
d
e
v
ice
s
an
d
c
o
m
p
o
n
en
ts
.
T
h
e
p
r
ed
ictio
n
r
ep
o
r
ts
ca
n
b
e
u
s
ed
by
th
e
m
ain
ten
an
ce
m
a
n
ag
er
to
c
r
ea
te
m
ain
te
n
an
ce
s
ch
ed
u
les
b
ased
o
n
r
is
k
,
o
r
u
s
ed
b
y
th
e
p
r
o
cu
r
em
en
t
team
t
o
o
p
tim
ize
in
v
en
to
r
y
n
ee
d
s
to
th
e
p
ar
ts
f
o
r
ec
asted
b
y
th
e
p
r
ed
ictio
n
r
ep
o
r
ts
.
I
n
ad
d
itio
n
,
clin
ical
en
g
in
ee
r
in
g
s
taf
f
ca
n
b
e
ed
u
ca
ted
o
n
h
o
w
to
in
ter
p
r
et
th
e
r
e
s
u
lts
o
f
th
e
m
o
d
els
an
d
will
b
e
n
o
tifie
d
wh
e
n
a
c
o
m
p
o
n
en
t
is
ap
p
r
o
ac
h
in
g
im
p
o
r
tan
t
f
ailu
r
e
p
ar
am
eter
s
.
T
h
is
allo
ws
th
e
h
o
s
p
ital
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
5
,
Octo
b
er
2
0
2
6
:
4
2
7
3
-
4
2
8
2
4280
to
tr
an
s
itio
n
f
r
o
m
th
e
“
o
ld
”
m
eth
o
d
o
f
m
ain
ten
an
ce
o
r
g
a
n
izatio
n
to
th
e
n
ew
“
d
ata
-
d
r
iv
en
”
m
ain
te
n
an
ce
d
ec
is
io
n
-
m
ak
in
g
m
eth
o
d
an
d
alig
n
th
e
h
o
s
p
ital
with
in
ter
n
atio
n
al
b
est
p
r
ac
tice
in
p
r
e
d
ictiv
e
m
ain
ten
an
ce
m
an
ag
em
en
t.
T
h
is
d
ata
-
in
f
o
r
m
ed
d
ir
ec
tio
n
also
f
its
with
th
e
o
v
er
all
d
ig
ital
h
ea
lth
d
i
r
ec
tio
n
to
ef
f
ec
tiv
e
d
ep
lo
y
m
e
n
t o
f
d
ig
ital
tech
n
o
lo
g
is
ts
to
s
u
p
p
o
r
t h
ea
lt
h
s
y
s
tem
an
d
s
er
v
ice
d
eliv
er
y
[
2
6
]
.
5.
CO
NCLU
SI
O
N
T
h
e
f
in
d
in
g
s
s
h
o
w
th
at
b
y
ad
d
in
g
FME
A
-
b
ased
r
is
k
s
co
r
es
to
ML
m
o
d
els,
p
r
ec
is
e
an
d
clin
ically
r
elev
an
t
p
r
ed
ictio
n
s
ca
n
b
e
m
ad
e,
esp
ec
ially
f
o
r
h
ig
h
-
p
r
io
r
i
ty
elem
en
ts
.
T
h
e
ev
al
u
ated
m
o
d
els,
n
am
ely
R
F
an
d
ANN
m
o
d
els,
h
a
v
e
b
ee
n
s
h
o
wn
to
p
er
f
o
r
m
b
etter
in
th
e
p
r
ed
ictio
n
with
r
is
k
-
p
r
io
r
itize
d
f
ea
tu
r
e
s
ets.
T
h
is
allo
ws
h
ea
lth
ca
r
e
in
s
titu
tio
n
s
to
m
o
v
e
awa
y
f
r
o
m
r
ea
ctiv
e
o
r
s
ch
ed
u
led
m
ain
ten
an
ce
s
tr
ateg
ies
an
d
to
wa
r
d
s
p
r
ed
ictiv
e,
c
o
s
t
-
ef
f
ec
tiv
e
,
a
n
d
s
u
s
tain
ab
le
s
p
ar
e
p
ar
ts
m
an
ag
em
en
t.
T
h
is
also
alig
n
s
with
t
h
e
h
ea
lth
ca
r
e
g
o
als
o
f
in
cr
ea
s
in
g
eq
u
i
p
m
en
t
a
v
ai
lab
ilit
y
,
p
atien
t
s
af
ety
,
an
d
r
eso
u
r
ce
ef
f
icien
c
y
th
at
ex
is
t
ar
o
u
n
d
th
e
w
o
r
ld
,
p
ar
ticu
lar
ly
in
l
o
w
-
an
d
m
id
d
l
e
-
in
co
m
e
ar
ea
s
wh
e
r
e
m
an
y
h
ea
lth
ca
r
e
f
ac
ilit
ies lac
k
eq
u
ip
m
en
t.
ACK
NO
WL
E
DG
M
E
N
T
S
T
h
e
au
th
o
r
s
th
an
k
th
e
i
-
C
AT
S
Un
iv
er
s
ity
C
o
lleg
e
(
i
-
C
AT
S
UC
)
,
Un
iv
er
s
iti
Ma
lay
s
ia
S
ar
awa
k
,
an
d
UNI
MA
S
I
n
d
u
s
tr
ial
Gr
an
t
wi
th
C
W
o
r
k
s
T
ec
h
n
o
lo
g
ies
Sd
n
B
h
d
f
o
r
th
eir
co
n
tin
u
o
u
s
s
u
p
p
o
r
t
in
co
n
d
u
ctin
g
th
is
s
tu
d
y
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
esear
ch
was
f
u
n
d
e
d
b
y
UNI
MA
S
I
n
d
u
s
tr
ial
Gr
an
t
with
C
W
o
r
k
s
T
ec
h
n
o
lo
g
ies
Sd
n
B
h
d
(
p
r
o
ject
co
d
e
: A
A0
2
0
2
0
0
-
0
7
0
6
-
0
0
0
1
)
.
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
F
a
b
i
a
n
H
a
l
l
e
y
P
a
t
a
A
l
b
a
n
D
a
t
t
u
✓
✓
✓
✓
✓
✓
✓
✓
✓
Sy
ed
T
ar
m
izi
Sy
ed
Sh
az
ali
✓
✓
✓
✓
✓
✓
✓
✓
✓
Sh
ir
ley
J
o
h
n
ath
a
n
T
an
jo
n
g
✓
✓
✓
✓
✓
✓
✓
Ab
d
u
l Ran
i A
ch
m
ed
Ab
d
u
llah
✓
✓
✓
✓
✓
✓
✓
Nu
r
laila
R
o
s
li
✓
✓
✓
✓
✓
✓
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
Data
a
v
aila
b
i
lit
y
is
n
o
t
a
p
p
li
ca
b
le
t
o
t
h
is
p
ap
er
as
n
o
n
e
w
d
a
t
a
w
er
e
cr
ea
te
d
o
r
an
al
y
z
e
d
i
n
t
h
is
s
t
u
d
y
.
RE
F
E
R
E
NC
E
S
[
1
]
N
.
H
.
A
.
R
a
h
ma
n
,
A
.
K
.
I
b
r
a
h
i
m
,
K
.
H
a
si
k
i
n
,
a
n
d
N
.
A
.
A
b
d
R
a
z
a
k
,
“
C
r
i
t
i
c
a
l
d
e
v
i
c
e
r
e
l
i
a
b
i
l
i
t
y
a
ss
e
ssm
e
n
t
i
n
h
e
a
l
t
h
c
a
r
e
s
e
r
v
i
c
e
s,”
J
o
u
rn
a
l
o
f
H
e
a
l
t
h
c
a
re
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
2
0
2
3
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
3
/
3
1
3
6
5
1
1
.
[
2
]
W
o
r
l
d
H
e
a
l
t
h
O
r
g
a
n
i
z
a
t
i
o
n
a
n
d
W
o
r
l
d
B
a
n
k
,
W
o
r
l
d
re
p
o
rt
o
n
d
i
s
a
b
i
l
i
t
y
.
G
e
n
e
v
a
,
S
w
i
t
z
e
r
l
a
n
d
:
W
o
r
l
d
H
e
a
l
t
h
O
r
g
a
n
i
z
a
t
i
o
n
,
2
0
1
1
.
A
c
c
e
ss
e
d
:
S
e
p
.
1
5
,
2
0
2
4
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
w
h
o
.
i
n
t
/
p
u
b
l
i
c
a
t
i
o
n
s
/
i
/
i
t
e
m
/
9
7
8
9
2
4
1
5
6
4
1
8
2
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Ma
ch
in
e
lea
r
n
in
g
a
n
d
fa
ilu
r
e
mo
d
e
a
n
d
effec
ts
a
n
a
lysi
s
fo
r
s
u
s
ta
in
a
b
le
…
(
F
a
b
ia
n
Ha
lley
P
a
ta
A
lb
a
n
Da
ttu
)
4281
[
3
]
M
.
Z
h
e
n
g
,
J.
Li
n
,
T
.
X
i
a
,
Y
.
Li
u
,
a
n
d
E.
P
a
n
,
“
J
o
i
n
t
c
o
n
d
i
t
i
o
n
-
b
a
s
e
d
ma
i
n
t
e
n
a
n
c
e
a
n
d
sp
a
r
e
p
r
o
v
i
s
i
o
n
i
n
g
p
o
l
i
c
y
f
o
r
a
K
-
o
u
t
-
of
-
N
sy
st
e
m
w
i
t
h
f
a
i
l
u
r
e
s
d
u
r
i
n
g
i
n
s
p
e
c
t
i
o
n
i
n
t
e
r
v
a
l
s,”
E
u
ro
p
e
a
n
J
o
u
r
n
a
l
o
f
O
p
e
r
a
t
i
o
n
a
l
Re
s
e
a
rc
h
,
v
o
l
.
3
0
8
,
n
o
.
3
,
p
p
.
1
2
2
0
–
1
2
3
2
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
j
o
r
.
2
0
2
3
.
0
1
.
0
1
1
.
[
4
]
A
.
A
.
M
u
r
t
a
z
a
,
A
.
S
a
h
e
r
,
M
.
H
.
Z
a
f
a
r
,
S
.
K
.
R
.
M
o
o
s
a
v
i
,
M
.
F
.
A
f
t
a
b
,
a
n
d
F
.
S
a
n
f
i
l
i
p
p
o
,
“
P
a
r
a
d
i
g
m
s
h
i
f
t
f
o
r
p
r
e
d
i
c
t
i
v
e
mai
n
t
e
n
a
n
c
e
a
n
d
c
o
n
d
i
t
i
o
n
m
o
n
i
t
o
r
i
n
g
f
r
o
m
I
n
d
u
st
r
y
4
.
0
t
o
I
n
d
u
s
t
r
y
5
.
0
:
a
sy
st
e
ma
t
i
c
r
e
v
i
e
w
,
c
h
a
l
l
e
n
g
e
s
a
n
d
c
a
s
e
st
u
d
y
,
”
Re
s
u
l
t
s
i
n
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
2
4
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
i
n
e
n
g
.
2
0
2
4
.
1
0
2
9
3
5
.
[
5
]
A
.
Th
e
i
ssl
e
r
,
J.
P
.
-
V
e
l
á
z
q
u
e
z
,
M
.
K
e
t
t
e
l
g
e
r
d
e
s,
a
n
d
G
.
E
l
g
e
r
,
“
P
r
e
d
i
c
t
i
v
e
m
a
i
n
t
e
n
a
n
c
e
e
n
a
b
l
e
d
b
y
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
:
u
s
e
c
a
ses
a
n
d
c
h
a
l
l
e
n
g
e
s
i
n
t
h
e
a
u
t
o
mo
t
i
v
e
i
n
d
u
st
r
y
,
”
Re
l
i
a
b
i
l
i
t
y
En
g
i
n
e
e
ri
n
g
a
n
d
S
y
st
e
m
S
a
f
e
t
y
,
v
o
l
.
2
1
5
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
e
s
s.
2
0
2
1
.
1
0
7
8
6
4
.
[
6
]
H
.
S
o
l
t
a
n
a
l
i
a
n
d
S
.
R
a
m
e
z
a
n
i
,
“
S
m
a
r
t
f
a
i
l
u
r
e
m
o
d
e
a
n
d
e
f
f
e
c
t
s
a
n
a
l
y
s
i
s
(
F
M
E
A
)
f
o
r
s
a
f
e
t
y
–
c
r
i
t
i
c
a
l
s
y
s
t
e
ms
i
n
t
h
e
c
o
n
t
e
x
t
o
f
I
n
d
u
s
t
r
y
4
.
0
,
”
i
n
I
n
d
u
s
t
r
i
a
l
a
n
d
A
p
p
l
i
e
d
M
a
t
h
e
m
a
t
i
c
s
,
S
i
n
g
a
p
o
r
e
:
S
p
r
i
n
g
e
r
,
2
0
2
3
,
p
p
.
1
5
1
–
176
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
981
-
19
-
9909
-
3_7.
[
7
]
M
.
A
.
F
i
l
z
,
J
.
E
.
B
.
La
n
g
n
e
r
,
C
.
H
e
r
r
man
n
,
a
n
d
S
.
Th
i
e
d
e
,
“
D
a
t
a
-
d
r
i
v
e
n
f
a
i
l
u
r
e
mo
d
e
a
n
d
e
f
f
e
c
t
a
n
a
l
y
s
i
s
(
F
M
EA
)
t
o
e
n
h
a
n
c
e
mai
n
t
e
n
a
n
c
e
p
l
a
n
n
i
n
g
,
”
C
o
m
p
u
t
e
rs i
n
I
n
d
u
s
t
ry
,
v
o
l
.
1
2
9
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
i
n
d
.
2
0
2
1
.
1
0
3
4
5
1
.
[
8
]
W
o
r
l
d
H
e
a
l
t
h
O
r
g
a
n
i
z
a
t
i
o
n
,
P
a
t
i
e
n
t
sa
f
e
t
y
c
u
r
ri
c
u
l
u
m
g
u
i
d
e
:
m
u
l
t
i
-
p
r
o
f
e
ssi
o
n
a
l
e
d
i
t
i
o
n
.
G
e
n
e
v
a
,
S
w
i
t
z
e
r
l
a
n
d
:
W
o
r
l
d
H
e
a
l
t
h
O
r
g
a
n
i
z
a
t
i
o
n
,
2
0
1
1
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
a
p
p
s
.
w
h
o
.
i
n
t
/
i
r
i
s/
h
a
n
d
l
e
/
1
0
6
6
5
/
4
4
6
4
1
[
9
]
A
.
H
.
Z
a
mz
a
m,
A
.
K
.
A
.
W
a
h
a
b
,
M
.
M
.
A
z
i
z
a
n
,
S
.
C
.
S
a
t
a
p
a
t
h
y
,
K
.
W
.
La
i
,
a
n
d
K
.
H
a
s
i
k
i
n
,
“
A
sy
s
t
e
m
a
t
i
c
r
e
v
i
e
w
o
f
me
d
i
c
a
l
e
q
u
i
p
me
n
t
r
e
l
i
a
b
i
l
i
t
y
a
ss
e
ssm
e
n
t
i
n
i
mp
r
o
v
i
n
g
t
h
e
q
u
a
l
i
t
y
o
f
h
e
a
l
t
h
c
a
r
e
se
r
v
i
c
e
s,
”
Fr
o
n
t
i
e
rs
i
n
Pu
b
l
i
c
H
e
a
l
t
h
,
v
o
l
.
9
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
u
b
h
.
2
0
2
1
.
7
5
3
9
5
1
.
[
1
0
]
O
.
M
a
n
c
h
a
d
i
,
F
.
E.
B
.
-
B
o
u
a
z
z
a
,
a
n
d
B
.
J
i
o
u
d
i
,
“
P
r
e
d
i
c
t
i
v
e
ma
i
n
t
e
n
a
n
c
e
i
n
h
e
a
l
t
h
c
a
r
e
s
y
s
t
e
m
:
a
s
u
r
v
e
y
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
6
1
3
1
3
–
6
1
3
3
0
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
8
7
4
9
0
.
[
1
1
]
A
.
K
.
K
a
u
si
k
,
A
.
B
.
R
a
s
h
i
d
,
R
.
F
.
B
a
k
i
,
a
n
d
M
.
M
.
J
.
M
a
k
t
u
m
,
“
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
ma
n
u
f
a
c
t
u
r
i
n
g
q
u
a
l
i
t
y
a
ss
u
r
a
n
c
e
:
a
sy
st
e
mat
i
c
r
e
v
i
e
w
o
f
p
e
r
f
o
r
ma
n
c
e
m
e
t
r
i
c
s a
n
d
a
p
p
l
i
c
a
t
i
o
n
s,
”
Arr
a
y
,
v
o
l
.
2
6
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
r
r
a
y
.
2
0
2
5
.
1
0
0
3
9
3
.
[
1
2
]
S
.
B
.
M
a
su
d
e
t
a
l
.
,
“
A
I
-
d
r
i
v
e
n
p
r
e
d
i
c
t
i
v
e
m
a
i
n
t
e
n
a
n
c
e
i
n
i
n
f
r
a
st
r
u
c
t
u
r
e
a
n
d
f
a
c
i
l
i
t
i
e
s
ma
n
a
g
e
m
e
n
t
,
”
EAI
E
n
d
o
r
sed
T
r
a
n
sa
c
t
i
o
n
s
o
n
AI
a
n
d
Ro
b
o
t
i
c
s
,
v
o
l
.
5
,
D
e
c
.
2
0
2
6
,
d
o
i
:
1
0
.
4
1
0
8
/
a
i
r
o
.
9
9
7
5
.
[
1
3
]
S
.
M
.
V
a
r
n
o
sf
a
d
e
r
a
n
i
a
n
d
M
.
F
o
r
o
u
z
a
n
f
a
r
,
“
T
h
e
r
o
l
e
o
f
A
I
i
n
h
o
s
p
i
t
a
l
s
a
n
d
c
l
i
n
i
c
s
:
t
r
a
n
sf
o
r
mi
n
g
h
e
a
l
t
h
c
a
r
e
i
n
t
h
e
2
1
s
t
C
e
n
t
u
r
y
,
”
Bi
o
e
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
1
,
n
o
.
4
,
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
b
i
o
e
n
g
i
n
e
e
r
i
n
g
1
1
0
4
0
3
3
7
.
[
1
4
]
D
.
K
a
p
o
o
r
,
D
.
G
u
p
t
a
,
a
n
d
M
.
U
p
p
a
l
,
“
A
n
a
l
y
z
i
n
g
t
h
e
i
m
p
a
c
t
o
f
e
d
g
e
,
f
o
g
a
n
d
c
l
o
u
d
c
o
m
p
u
t
i
n
g
o
n
p
r
e
d
i
c
t
i
v
e
m
a
i
n
t
e
n
a
n
c
e
i
n
t
h
e
i
n
d
u
st
r
i
a
l
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s,
”
D
i
s
c
o
v
e
r C
o
m
p
u
t
i
n
g
,
v
o
l
.
2
8
,
n
o
.
1
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
0
7
9
1
-
025
-
0
9
6
5
3
-
8.
[
1
5
]
S
.
B
.
J
a
l
l
i
p
a
l
l
i
a
n
d
R
.
D
u
v
v
u
r
u
,
“
R
e
v
i
e
w
s
-
b
a
s
e
d
p
a
t
i
e
n
t
-
c
e
n
t
r
i
c
r
e
c
o
mm
e
n
d
a
t
i
o
n
s
y
st
e
m:
a
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
a
l
y
s
i
s
f
o
r
sm
a
r
t
h
e
a
l
t
h
c
a
r
e
ma
n
a
g
e
m
e
n
t
,
”
I
E
EE
A
c
c
e
ss
,
2
0
2
5
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
5
.
3
5
7
4
5
0
3
.
[
1
6
]
F
.
Z.
A
n
g
l
o
u
,
S
.
P
o
n
i
s
,
a
n
d
A
.
S
p
a
n
o
s,
“
A
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
t
o
e
n
a
b
l
e
b
u
l
k
o
r
d
e
r
s
o
f
c
r
i
t
i
c
a
l
s
p
a
r
e
p
a
r
t
s
i
n
t
h
e
s
h
i
p
p
i
n
g
i
n
d
u
st
r
y
,
”
J
o
u
r
n
a
l
o
f
I
n
d
u
st
r
i
a
l
En
g
i
n
e
e
ri
n
g
a
n
d
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
1
4
,
n
o
.
3
,
p
p
.
6
0
4
–
6
2
1
,
2
0
2
1
,
d
o
i
:
1
0
.
3
9
2
6
/
j
i
e
m.3
4
4
6
.
[
1
7
]
M
.
S
o
o
r
i
,
F
.
K
.
G
.
J
o
u
g
h
,
R
.
D
a
s
t
r
e
s,
a
n
d
B
.
A
r
e
z
o
o
,
“
A
I
-
b
a
se
d
d
e
c
i
si
o
n
s
u
p
p
o
r
t
s
y
st
e
ms
i
n
I
n
d
u
st
r
y
4
.
0
,
a
r
e
v
i
e
w
,
”
J
o
u
rn
a
l
o
f
Ec
o
n
o
m
y
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
4
,
p
p
.
2
0
6
–
2
2
5
,
2
0
2
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
e
c
t
.
2
0
2
4
.
0
8
.
0
0
5
.
[
1
8
]
J.
Q
i
n
,
Y
.
X
i
,
a
n
d
W
.
P
e
d
r
y
c
z
,
“
F
a
i
l
u
r
e
m
o
d
e
a
n
d
e
f
f
e
c
t
s
a
n
a
l
y
s
i
s
(
F
M
E
A
)
f
o
r
r
i
s
k
a
ssess
me
n
t
b
a
se
d
o
n
i
n
t
e
r
v
a
l
t
y
p
e
-
2
f
u
z
z
y
e
v
i
d
e
n
t
i
a
l
r
e
a
s
o
n
i
n
g
me
t
h
o
d
,
”
A
p
p
l
i
e
d
S
o
f
t
C
o
m
p
u
t
i
n
g
J
o
u
r
n
a
l
,
v
o
l
.
8
9
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
so
c
.
2
0
2
0
.
1
0
6
1
3
4
.
[
1
9
]
J.
B
.
B
o
w
l
e
s
,
“
A
n
a
ss
e
ssm
e
n
t
o
f
R
P
N
p
r
i
o
r
i
t
i
z
a
t
i
o
n
i
n
a
f
a
i
l
u
r
e
m
o
d
e
s
a
n
d
e
f
f
e
c
t
s
a
n
d
c
r
i
t
i
c
a
l
a
n
a
l
y
si
s
,
”
P
ro
c
e
e
d
i
n
g
s
o
f
t
h
e
An
n
u
a
l
Re
l
i
a
b
i
l
i
t
y
a
n
d
M
a
i
n
t
a
i
n
a
b
i
l
i
t
y
S
y
m
p
o
s
i
u
m
,
v
o
l
.
4
7
,
p
p
.
3
8
0
–
3
8
6
,
2
0
0
3
,
d
o
i
:
1
0
.
1
1
0
9
/
r
a
ms
.
2
0
0
3
.
1
1
8
2
0
1
9
.
[
2
0
]
S
.
M
.
M
.
E
l
-
A
w
a
d
y
,
“
O
v
e
r
v
i
e
w
o
f
f
a
i
l
u
r
e
mo
d
e
a
n
d
e
f
f
e
c
t
s
a
n
a
l
y
si
s
(
F
M
EA
)
:
a
p
a
t
i
e
n
t
saf
e
t
y
t
o
o
l
,
”
G
l
o
b
a
l
J
o
u
r
n
a
l
o
n
Q
u
a
l
i
t
y
a
n
d
S
a
f
e
t
y
i
n
H
e
a
l
t
h
c
a
re
,
v
o
l
.
6
,
n
o
.
1
,
p
p
.
2
4
–
2
6
,
2
0
2
3
,
d
o
i
:
1
0
.
3
6
4
0
1
/
JQ
S
H
-
23
-
X
2
.
[
2
1
]
G
.
C
a
r
d
e
a
l
,
I
.
R
i
b
e
i
r
o
,
a
n
d
M
.
Le
i
t
e
,
“
Th
e
r
o
l
e
o
f
a
d
d
i
t
i
v
e
ma
n
u
f
a
c
t
u
r
i
n
g
i
n
p
r
o
c
e
ss
i
n
d
u
st
r
y
s
p
a
r
e
p
a
r
t
s
s
u
p
p
l
y
c
h
a
i
n
s,”
J
o
u
r
n
a
l
o
f
M
a
n
u
f
a
c
t
u
ri
n
g
T
e
c
h
n
o
l
o
g
y
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
3
7
,
n
o
.
2
,
p
p
.
4
9
1
–
5
1
1
,
2
0
2
6
,
d
o
i
:
1
0
.
1
1
0
8
/
J
M
T
M
-
03
-
2
0
2
5
-
0
2
5
4
.
[
2
2
]
L.
M
o
n
t
e
si
n
o
s
e
t
a
l
.
,
“
S
u
st
a
i
n
a
b
i
l
i
t
y
a
c
r
o
ss
t
h
e
me
d
i
c
a
l
d
e
v
i
c
e
l
i
f
e
c
y
c
l
e
:
a
sc
o
p
i
n
g
r
e
v
i
e
w
,
”
S
u
st
a
i
n
a
b
i
l
i
t
y
,
v
o
l
.
1
6
,
n
o
.
4
,
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
s
u
1
6
0
4
1
4
3
3
.
[
2
3
]
K
.
D
e
v
i
,
K
.
S
a
m
p
a
t
h
,
S
.
V
e
n
k
a
t
e
sa
n
,
T.
V
.
A
mb
u
l
i
,
a
n
d
S
.
K
u
m
a
r
a
n
,
“
D
e
e
p
l
e
a
r
n
i
n
g
f
o
r
p
r
e
d
i
c
t
i
v
e
ma
i
n
t
e
n
a
n
c
e
r
e
v
o
l
u
t
i
o
n
i
z
i
n
g
a
sset
ma
n
a
g
e
m
e
n
t
i
n
f
i
n
a
n
c
e
,
”
i
n
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
D
i
s
t
ri
b
u
t
e
d
S
y
st
e
m
s,
C
o
m
p
u
t
e
r
N
e
t
w
o
r
k
s
a
n
d
C
y
b
e
rse
c
u
r
i
t
y
,
I
C
D
S
C
N
C
2
0
2
4
,
2
0
2
4
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
D
S
C
N
C
6
2
4
9
2
.
2
0
2
4
.
1
0
9
3
9
2
9
4
.
[
2
4
]
Y
.
M
a
h
a
l
e
,
S
.
K
o
l
h
a
r
,
a
n
d
A
.
S
.
M
o
r
e
,
“
En
h
a
n
c
i
n
g
p
r
e
d
i
c
t
i
v
e
ma
i
n
t
e
n
a
n
c
e
i
n
a
u
t
o
m
o
t
i
v
e
i
n
d
u
s
t
r
y
:
a
d
d
r
e
ss
i
n
g
c
l
a
ss
i
mb
a
l
a
n
c
e
u
si
n
g
a
d
v
a
n
c
e
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s,
”
D
i
s
c
o
v
e
r
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
7
,
n
o
.
4
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
2
4
5
2
-
0
2
5
-
0
6
8
2
7
-
3.
[
2
5
]
M
.
P
.
La
m
b
á
n
,
P
.
M
o
r
e
l
l
a
,
J
.
R
o
y
o
,
a
n
d
J
.
C
.
S
á
n
c
h
e
z
,
“
U
si
n
g
I
n
d
u
s
t
r
y
4
.
0
t
o
f
a
c
e
t
h
e
c
h
a
l
l
e
n
g
e
s o
f
p
r
e
d
i
c
t
i
v
e
m
a
i
n
t
e
n
a
n
c
e
:
a
k
e
y
p
e
r
f
o
r
m
a
n
c
e
i
n
d
i
c
a
t
o
r
s
d
e
v
e
l
o
p
me
n
t
i
n
a
c
y
b
e
r
p
h
y
s
i
c
a
l
sy
s
t
e
m
,
”
C
o
m
p
u
t
e
rs
a
n
d
I
n
d
u
st
r
i
a
l
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
7
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
i
e
.
2
0
2
2
.
1
0
8
4
0
0
.
[
2
6
]
W
o
r
l
d
H
e
a
l
t
h
O
r
g
a
n
i
z
a
t
i
o
n
,
G
l
o
b
a
l
st
ra
t
e
g
y
o
n
d
i
g
i
t
a
l
h
e
a
l
t
h
2
0
2
0
–
2
0
2
5
.
G
e
n
e
v
a
,
S
w
i
t
z
e
r
l
a
n
d
:
W
o
r
l
d
H
e
a
l
t
h
O
r
g
a
n
i
z
a
t
i
o
n
,
2
0
2
1
.
A
c
c
e
s
se
d
:
S
e
p
t
e
m
b
e
r
1
5
,
2
0
2
4
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
w
w
w
.
w
h
o
.
i
n
t
/
p
u
b
l
i
c
a
t
i
o
n
s/
i
/
i
t
e
m
/
9
7
8
9
2
4
0
0
2
0
9
2
4
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ts.
Fa
b
ia
n
H
a
l
ley
Pa
t
a
Alb
a
n
Da
tt
u
is
c
u
rre
n
tl
y
p
u
rs
u
in
g
h
is
P
h
.
D
.
i
n
M
e
c
h
a
n
ica
l
En
g
in
e
e
rin
g
a
t
Un
iv
e
rsiti
M
a
lay
sia
S
a
ra
wa
k
,
f
o
c
u
sin
g
o
n
stra
teg
ic
a
n
d
s
u
sta
in
a
b
le
sp
a
re
p
a
rts
m
a
n
a
g
e
m
e
n
t
fo
r
m
e
d
ica
l
d
e
v
ice
s
th
ro
u
g
h
m
a
c
h
in
e
lea
rn
in
g
a
p
p
r
o
a
c
h
e
s.
His
re
se
a
rc
h
in
teg
ra
tes
p
re
d
ictiv
e
m
a
in
ten
a
n
c
e
,
se
m
i
-
su
p
e
rv
ise
d
l
e
a
rn
in
g
,
a
n
d
su
sta
i
n
a
b
il
it
y
fra
m
e
wo
rk
s
to
imp
r
o
v
e
e
q
u
i
p
m
e
n
t
re
li
a
b
il
it
y
a
n
d
o
p
ti
m
ize
re
so
u
r
c
e
a
ll
o
c
a
ti
o
n
i
n
h
e
a
lt
h
c
a
re
se
tt
in
g
s.
At
i
-
CAT
S
UC,
he
h
a
s
l
e
d
p
r
o
g
ra
m
m
e
r
d
e
v
e
l
o
p
m
e
n
t
a
li
g
n
e
d
wit
h
M
BOT,
M
QF,
a
n
d
ET
AC
sta
n
d
a
r
d
s,
w
h
il
e
a
ls
o
c
o
o
rd
i
n
a
ti
n
g
m
e
c
h
a
n
ica
l
wo
r
k
sh
o
p
u
p
g
ra
d
e
s,
i
n
d
u
stria
l
c
o
ll
a
b
o
ra
ti
o
n
s,
a
n
d
S
TE
M
o
u
tr
e
a
c
h
in
it
iati
v
e
s.
His
a
c
a
d
e
m
ic
in
tere
sts
in
c
lu
d
e
p
re
d
ictiv
e
m
a
in
ten
a
n
c
e
,
su
sta
in
a
b
le
e
n
g
i
n
e
e
rin
g
,
a
rti
ficia
l
i
n
telli
g
e
n
c
e
in
h
e
a
lt
h
c
a
re
,
a
n
d
c
u
rric
u
lu
m
in
n
o
v
a
ti
o
n
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t:
fa
b
ian
.
h
a
ll
e
y
@ic
a
ts.ed
u
.
m
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
5
,
Octo
b
er
2
0
2
6
:
4
2
7
3
-
4
2
8
2
4282
As
so
c
.
Pro
f
.
Ir
.
Dr
.
S
y
e
d
T
a
r
m
i
z
i
S
y
e
d
S
h
a
z
a
li
re
c
e
iv
e
d
a
P
h
.
D.
in
M
e
c
h
a
n
ica
l
a
n
d
M
a
n
u
fa
c
tu
r
in
g
E
n
g
in
e
e
rin
g
f
ro
m
th
e
Un
i
v
e
rsity
o
f
L
o
u
g
h
b
o
r
o
u
g
h
,
Un
it
e
d
Ki
n
g
d
o
m
.
He
h
a
s
o
v
e
r
2
5
y
e
a
rs
o
f
e
x
p
e
rien
c
e
a
s
a
n
a
c
a
d
e
m
icia
n
a
t
th
e
Un
i
v
e
rsiti
M
a
lay
sia
S
a
ra
wa
k
.
H
e
h
o
l
d
s
th
e
a
ss
o
c
iate
p
ro
fe
ss
o
r
p
o
si
ti
o
n
re
se
a
rc
h
in
g
m
a
n
u
fa
c
tu
rin
g
m
a
n
a
g
e
m
e
n
t,
m
a
n
u
fa
c
tu
ri
n
g
se
rv
it
isa
ti
o
n
,
e
n
g
i
n
e
e
rin
g
m
a
teria
ls,
a
n
d
v
ib
ra
ti
o
n
s.
P
u
b
li
sh
e
d
v
a
rio
u
s
j
o
u
r
n
a
l
p
a
p
e
rs
o
n
e
n
g
in
e
e
rin
g
e
d
u
c
a
ti
o
n
a
n
d
h
u
m
a
n
b
e
h
a
v
i
o
r
m
o
d
e
li
n
g
.
He
is
a
m
e
m
b
e
r
o
f
t
h
e
B
o
a
rd
o
f
En
g
i
n
e
e
rs
M
a
lay
sia
a
n
d
t
h
e
In
st
it
u
ti
o
n
o
f
M
e
c
h
a
n
ica
l
En
g
in
e
e
rs,
Un
it
e
d
Kin
g
d
o
m
,
e
a
rn
i
n
g
t
h
e
d
isti
n
g
u
is
h
e
d
ti
tl
e
o
f
p
ro
fe
ss
i
o
n
a
l
e
n
g
in
e
e
r
(Ir
.
).
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sta
rm
izi@u
n
ima
s.m
y
.
Ir
.
Ts.
Dr
.
S
h
irle
y
J
o
h
n
a
th
a
n
Ta
n
jo
n
g
is
a
se
n
io
r
lec
tu
re
r
a
n
d
p
o
stg
ra
d
u
a
te
re
se
a
rc
h
c
o
o
rd
in
a
t
o
r
a
t
t
h
e
De
p
a
rtme
n
t
o
f
M
e
c
h
a
n
ica
l
a
n
d
M
a
n
u
fa
c
tu
ri
n
g
En
g
in
e
e
ri
n
g
,
F
a
c
u
lt
y
o
f
En
g
i
n
e
e
rin
g
,
Un
i
v
e
rsiti
M
a
lay
sia
S
a
ra
wa
k
.
S
h
e
h
o
l
d
s
p
ro
fe
ss
io
n
a
l
re
c
o
g
n
it
io
n
a
s
b
o
t
h
a
n
e
n
g
i
n
e
e
r
a
n
d
p
ro
fe
ss
io
n
a
l
tec
h
n
o
lo
g
ist
.
He
r
a
c
a
d
e
m
ic
a
n
d
re
se
a
rc
h
e
x
p
e
rti
se
li
e
s
in
m
e
c
h
a
n
ica
l
a
n
d
m
a
n
u
fa
c
tu
ri
n
g
e
n
g
i
n
e
e
rin
g
,
with
c
o
n
t
rib
u
ti
o
n
s
t
o
p
o
st
g
ra
d
u
a
te
s
u
p
e
rv
isi
o
n
,
c
u
rricu
lu
m
d
e
v
e
l
o
p
m
e
n
t,
a
n
d
c
o
l
lab
o
ra
ti
v
e
re
se
a
rc
h
p
ro
jec
ts.
S
h
e
a
c
ti
v
e
ly
p
ro
m
o
tes
re
se
a
rc
h
e
x
c
e
ll
e
n
c
e
with
in
th
e
fa
c
u
lt
y
a
n
d
h
a
s
p
u
b
li
s
h
e
d
i
n
v
a
ri
o
u
s
e
n
g
i
n
e
e
rin
g
d
o
m
a
in
s.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
jt
sh
irl
e
y
@u
n
i
m
a
s.m
y
.
Dr
.
Abd
u
l
R
a
n
i
Ac
h
m
e
d
A
b
d
u
ll
a
h
e
a
rn
e
d
h
is
B.
S
c
.
in
El
e
c
t
rica
l
En
g
in
e
e
rin
g
fro
m
P
u
rd
u
e
Un
iv
e
rsity
a
n
d
M
.
S
c
.
i
n
E
n
g
in
e
e
rin
g
B
u
sin
e
ss
M
a
n
a
g
e
m
e
n
t
fro
m
Warwic
k
Un
iv
e
rsity
.
He
c
o
m
p
lete
d
h
is
d
o
c
to
ra
l
d
e
g
re
e
fro
m
Un
i
v
e
rsiti
Te
k
n
o
lo
g
i
M
a
lay
sia
.
He
is
t
h
e
fo
u
n
d
e
r
a
n
d
c
h
ief
e
x
e
c
u
ti
v
e
o
f
C
Wo
rk
s,
In
c
.
a
n
d
se
rv
e
s
a
s
a
n
a
d
j
u
n
c
t
p
ro
fe
ss
o
r
a
t
U
n
iv
e
rsiti
M
a
lay
sia
S
a
ra
wa
k
.
He
h
a
s
led
se
v
e
ra
l
p
ro
jec
t
imp
lem
e
n
tatio
n
s,
in
c
lu
d
in
g
c
o
m
p
u
teriz
e
d
m
a
in
ten
a
n
c
e
m
a
n
a
g
e
m
e
n
t
sy
ste
m
s
fo
r
7
2
g
o
v
e
rn
m
e
n
t
h
o
sp
it
a
ls
a
n
d
th
e
n
a
ti
o
n
a
l
c
o
n
stru
c
t
io
n
m
a
teria
l
p
rice
in
d
e
x
.
P
re
v
i
o
u
sl
y
,
h
e
se
rv
e
d
a
s
a
c
o
u
n
c
il
m
e
m
b
e
r
o
f
t
h
e
M
a
ste
r
B
u
il
d
e
r
As
so
c
iatio
n
M
a
lay
sia
a
n
d
t
h
e
M
a
lay
sia
As
se
t
a
n
d
P
ro
jec
t
M
a
n
a
g
e
m
e
n
t
As
so
c
iatio
n
.
He
h
a
s
a
lso
se
rv
e
d
o
n
IS
O/
TC
2
6
7
fo
r
t
h
e
d
e
v
e
l
o
p
m
e
n
t
o
f
fa
c
il
it
y
m
a
n
a
g
e
m
e
n
t
sta
n
d
a
rd
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ra
n
i@c
wo
r
k
s.
c
o
m
.
m
y
.
Ts.
Nurla
il
a
R
o
sli
is
a
se
n
io
r
lec
tu
re
r
a
t
th
e
F
a
c
u
lt
y
o
f
Co
m
p
u
t
in
g
a
n
d
S
o
ftwa
r
e
En
g
i
n
e
e
rin
g
,
i
-
CATS
Un
i
v
e
rsity
C
o
ll
e
g
e
,
Ku
c
h
in
g
.
S
h
e
h
o
ld
s
a
m
a
ste
r
o
f
sc
ien
c
e
i
n
In
fo
rm
a
ti
o
n
Tec
h
n
o
lo
g
y
fro
m
Un
iv
e
rsiti
Tek
n
o
lo
g
i
M
ARA
(
2
0
1
3
)
a
n
d
a
Ba
c
h
e
l
o
r
o
f
S
c
ien
c
e
in
I
n
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
(
so
f
twa
re
e
n
g
in
e
e
rin
g
)
fr
o
m
Un
i
v
e
rsiti
M
a
lay
sia
Tere
n
g
g
a
n
u
(2
0
1
0
).
S
h
e
is
a
p
r
o
fe
ss
io
n
a
l
tec
h
n
o
l
o
g
ist
re
g
istere
d
with
th
e
M
a
la
y
sia
Bo
a
rd
o
f
Tec
h
n
o
lo
g
ists
(M
BOT).
He
r
tea
c
h
in
g
a
n
d
re
se
a
rc
h
fo
c
u
s
o
n
a
rti
ficia
l
in
tel
l
ig
e
n
c
e
,
c
y
b
e
rse
c
u
rit
y
,
a
n
d
so
ftwa
re
d
e
v
e
lo
p
m
e
n
t
.
S
h
e
h
a
s
a
c
ti
v
e
ly
c
o
n
tri
b
u
te
d
t
o
v
a
ri
o
u
s
a
c
a
d
e
m
ic
a
n
d
in
d
u
stry
c
o
ll
a
b
o
ra
ti
o
n
s,
i
n
c
lu
d
in
g
tec
h
n
o
l
o
g
y
s
h
a
rin
g
se
ss
io
n
s
su
c
h
a
s
“
Tec
h
M
e
ra
d
io
S
h
a
rin
g
RED
F
M
:
a
rti
ficia
l
in
telli
g
e
n
c
e
,
i
n
tern
e
t
o
f
th
i
n
g
s,
a
n
d
c
y
b
e
rse
c
u
rit
y
”
(2
0
2
4
).
S
h
e
a
lso
se
rv
e
d
a
s
c
h
a
irp
e
rso
n
f
o
r
t
h
e
M
BOT
d
i
p
lo
m
a
ICT
e
v
a
lu
a
ti
o
n
p
a
n
e
l
a
t
Ko
lej
Vo
k
a
sio
n
a
l
Be
to
n
g
in
2
0
2
4
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
n
u
rlaila@ic
a
ts.ed
u
.
m
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.