I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
15
,
No
.
3
,
J
u
n
e
20
25
,
p
p
.
3291
~
3
3
0
8
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
15
i
3
.
pp
3
2
9
1
-
3
3
0
8
3291
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Applica
tion o
f
art
ificial int
ellig
ence
and ma
chine
lea
r
ning
in
ex
per
t
sy
stems
fo
r t
he
mining
ind
u
stry
:
mo
dern
met
ho
ds a
nd
technolo
g
ies
Na
t
a
ly
a
M
uto
v
ina
,
M
a
rg
ula
n Nurt
a
y
,
Alex
ey
K
a
lin
in,
Al
ek
s
a
nd
r
T
o
m
ilo
v
,
Na
dezhda
T
o
m
ilo
v
a
I
n
f
o
r
mat
i
o
n
a
n
d
C
o
m
p
u
t
i
n
g
S
y
st
e
ms
D
e
p
a
r
t
me
n
t
,
F
a
c
u
l
t
y
o
f
I
n
n
o
v
a
t
i
o
n
Te
c
h
n
o
l
o
g
i
e
s,
A
b
y
l
k
a
s Sa
g
i
n
o
v
K
a
r
a
g
a
n
d
a
Te
c
h
n
i
c
a
l
U
n
i
v
e
r
si
t
y
,
K
a
r
a
g
a
n
d
a
,
K
a
z
a
k
h
st
a
n
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Au
g
2
6
,
2
0
2
4
R
ev
is
ed
Dec
2
4
,
2
0
2
4
Acc
ep
ted
J
an
1
6
,
2
0
2
5
Th
e
m
in
in
g
in
d
u
str
y
h
a
s
c
h
a
n
g
e
d
sig
n
if
ica
n
tl
y
i
n
re
c
e
n
t
d
e
c
a
d
e
s
with
th
e
in
tro
d
u
c
ti
o
n
o
f
a
d
v
a
n
c
e
d
tec
h
n
o
l
o
g
ies
s
u
c
h
a
s
a
rti
ficia
l
i
n
telli
g
e
n
c
e
(AI)
a
n
d
m
a
c
h
in
e
lea
rn
in
g
(M
L)
.
T
h
e
se
in
n
o
v
a
ti
o
n
s
c
o
n
tri
b
u
te
to
th
e
c
r
e
a
ti
o
n
o
f
e
x
p
e
rt
s
y
ste
m
s
th
a
t
h
e
l
p
in
o
p
ti
m
izin
g
p
ro
c
e
ss
e
s,
i
n
c
re
a
sin
g
th
e
sa
fe
ty
a
n
d
su
sta
in
a
b
il
it
y
o
f
o
p
e
ra
ti
o
n
s.
T
h
is
a
rti
c
le
is
a
li
tera
tu
re
re
v
iew
o
f
m
o
d
e
rn
AI
a
n
d
M
L
m
e
th
o
d
s
a
n
d
tec
h
n
o
lo
g
i
e
s
u
se
d
in
th
e
m
in
i
n
g
i
n
d
u
stry
.
Disc
u
ss
e
s
v
a
rio
u
s
i
n
telli
g
e
n
t
a
n
d
e
x
p
e
rt
sy
s
tem
s
u
se
d
to
imp
ro
v
e
p
r
o
d
u
c
ti
v
i
t
y
,
re
d
u
c
e
o
p
e
ra
ti
n
g
c
o
sts,
imp
ro
v
e
o
c
c
u
p
a
ti
o
n
a
l
sa
fe
ty
,
e
n
v
iro
n
m
e
n
tal
su
st
a
in
a
b
il
it
y
,
m
a
c
h
in
e
a
u
to
m
a
ti
o
n
,
p
re
d
icti
v
e
a
n
a
ly
ti
c
s,
q
u
a
li
ty
m
o
n
it
o
r
in
g
a
n
d
c
o
n
tr
o
l,
a
n
d
i
n
v
e
n
to
r
y
a
n
d
l
o
g
isti
c
s
m
a
n
a
g
e
m
e
n
t.
T
h
e
a
d
v
a
n
tag
e
s
a
n
d
d
isa
d
v
a
n
ta
g
e
s
o
f
d
iffere
n
t
a
p
p
r
o
a
c
h
e
s
a
re
a
n
a
l
y
z
e
d
,
a
s
we
ll
a
s
th
e
ir
p
o
ten
ti
a
l
imp
a
c
t
o
n
th
e
fu
tu
re
o
f
th
e
m
in
i
n
g
i
n
d
u
stry
.
Th
e
re
v
iew
h
i
g
h
l
ig
h
ts
t
h
e
im
p
o
rtan
c
e
o
f
in
teg
ra
ti
n
g
AI
a
n
d
M
L
i
n
to
m
i
n
i
n
g
p
ro
c
e
ss
e
s
to
a
c
h
iev
e
m
o
re
e
fficie
n
t
a
n
d
sa
fe
r
so
lu
ti
o
n
s.
K
ey
w
o
r
d
s
:
Ar
tific
ial
in
tellig
en
ce
Dee
p
lear
n
in
g
I
n
ter
n
et
o
f
th
in
g
s
Ma
ch
in
e
lear
n
in
g
Min
in
g
in
d
u
s
tr
y
Pre
d
ictiv
e
an
aly
s
is
R
ein
f
o
r
ce
m
en
t le
ar
n
i
n
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
:
Nata
ly
a
Mu
to
v
in
a
I
n
f
o
r
m
atio
n
an
d
C
o
m
p
u
tin
g
S
y
s
tem
s
Dep
ar
tm
en
t,
Facu
lty
o
f
I
n
n
o
v
atio
n
T
ec
h
n
o
lo
g
ies,
Ab
y
lk
as Sag
in
o
v
Kar
ag
an
d
a
T
ec
h
n
ical
Un
iv
er
s
i
ty
5
6
N.
Naz
ar
b
a
y
ev
a
v
.
,
Kar
ag
a
n
d
a,
Kaz
ak
h
s
tan
E
m
ail: m
u
to
v
in
a
_
n
ataly
a@
m
ail.
r
u
1.
I
NT
RO
D
UCT
I
O
N
Ar
tific
ial
in
tellig
en
ce
(
AI
)
a
n
d
m
ac
h
i
n
e
lear
n
in
g
(
ML
)
ar
e
p
iv
o
tal
tech
n
o
lo
g
ies
tr
an
s
f
o
r
m
in
g
n
u
m
er
o
u
s
s
ec
to
r
s
,
m
in
in
g
in
clu
d
ed
.
AI
en
co
m
p
ass
es
th
e
r
e
alm
o
f
co
m
p
u
ter
s
cien
ce
f
o
c
u
s
ed
o
n
d
ev
elo
p
in
g
s
y
s
tem
s
th
at
ca
n
p
er
f
o
r
m
task
s
tr
ad
itio
n
ally
r
eq
u
ir
in
g
h
u
m
a
n
in
tellig
en
ce
,
lik
e
s
p
ee
ch
r
ec
o
g
n
itio
n
,
d
ec
is
io
n
-
m
ak
in
g
,
an
d
p
r
o
b
lem
-
s
o
lv
in
g
[
1
]
–
[
3
]
.
Ma
ch
in
e
lear
n
in
g
,
a
s
u
b
s
et
o
f
AI
,
s
p
ec
if
ically
co
n
ce
n
tr
ates
o
n
d
ev
is
in
g
alg
o
r
ith
m
s
th
at
en
ab
le
c
o
m
p
u
ter
s
to
lear
n
f
r
o
m
d
ata
an
d
e
n
h
an
ce
th
eir
p
er
f
o
r
m
an
ce
o
v
e
r
tim
e.
T
h
e
m
in
in
g
in
d
u
s
tr
y
,
as
o
n
e
o
f
t
h
e
o
ld
e
s
t
an
d
m
o
s
t
r
eso
u
r
ce
-
in
ten
s
iv
e
s
ec
to
r
s
,
h
as
alwa
y
s
b
ee
n
in
p
u
r
s
u
it
o
f
n
ew
tech
n
o
lo
g
ies
ca
p
ab
le
o
f
en
h
a
n
cin
g
th
e
ef
f
icien
cy
a
n
d
s
af
ety
o
f
m
in
er
al
ex
tr
ac
tio
n
.
Ma
ch
i
n
e
lear
n
in
g
h
as
th
e
p
o
ten
tial
to
p
r
ev
en
t
o
r
a
n
ticip
ate
v
ar
io
u
s
in
cid
en
ts
at
in
d
u
s
tr
ial
f
ac
ilit
ies
[
4
]
.
T
h
e
a
p
p
licatio
n
o
f
AI
a
n
d
ML
i
n
m
in
in
g
o
p
en
s
u
p
n
ew
p
o
s
s
ib
ilit
ies
f
o
r
ad
d
r
ess
in
g
m
an
y
c
h
a
llen
g
es
f
ac
ed
b
y
m
i
n
in
g
co
m
p
an
ies
[
5
]
–
[
7
]
.
T
h
e
u
s
e
o
f
AI
en
ab
les
en
h
an
ce
d
p
r
o
d
u
ctiv
ity
,
l
o
wer
o
p
er
atio
n
al
co
s
ts
,
im
p
r
o
v
ed
wo
r
k
p
lace
s
af
ety
,
an
d
r
e
d
u
ce
d
en
v
ir
o
n
m
en
tal
im
p
ac
t.
T
h
e
u
s
e
o
f
ML
alg
o
r
ith
m
s
m
ak
es
it
p
o
s
s
ib
le
to
o
p
tim
ize
t
h
e
p
r
o
ce
s
s
es
o
f
m
in
in
g
an
d
p
r
o
ce
s
s
in
g
o
f
m
in
er
als.
Fo
r
in
s
tan
ce
,
ML
-
b
ased
s
y
s
tem
s
ca
n
an
aly
ze
m
in
i
n
g
d
ata
i
n
r
ea
l
tim
e,
s
u
g
g
est
o
p
tim
al
r
o
u
tes
f
o
r
m
in
in
g
eq
u
ip
m
en
t,
a
n
d
p
r
ed
ict
th
e
m
o
s
t
ef
f
icien
t
m
in
in
g
m
eth
o
d
s
[
8
]
,
[
9
]
.
Pre
d
ictiv
e
an
aly
tics
b
ased
o
n
ML
im
p
r
o
v
es
th
e
p
r
e
d
ictio
n
o
f
eq
u
ip
m
e
n
t
b
r
ea
k
d
o
wn
s
an
d
p
la
n
s
its
m
ain
ten
an
ce
,
w
h
ich
r
ed
u
ce
s
th
e
co
s
t
o
f
r
ep
air
a
n
d
r
ep
lace
m
en
t
o
f
e
q
u
ip
m
e
n
t.
Su
ch
ap
p
r
o
ac
h
is
esp
ec
ially
im
p
o
r
tan
t
f
o
r
lar
g
e
an
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
3
,
J
u
n
e
20
25
:
3
2
9
1
-
3
3
0
8
3292
ex
p
en
s
iv
e
m
in
in
g
eq
u
ip
m
en
t
[
1
0
]
.
AI
an
d
ML
ca
n
a
n
aly
ze
d
ata
f
r
o
m
s
en
s
o
r
s
a
n
d
s
u
r
v
e
illan
ce
ca
m
er
as
to
id
en
tify
p
o
ten
tially
d
an
g
er
o
u
s
s
itu
atio
n
s
an
d
war
n
wo
r
k
er
s
a
b
o
u
t p
o
s
s
ib
le
ac
cid
en
ts
.
Fo
r
e
x
am
p
le,
m
o
n
ito
r
in
g
s
y
s
tem
s
ca
n
m
o
n
ito
r
th
e
co
n
d
itio
n
o
f
m
in
es
an
d
p
r
e
d
ict
co
llap
s
es
o
r
m
eth
an
e
em
is
s
io
n
s
,
wh
ich
all
o
ws
wo
r
k
er
s
to
b
e
ev
ac
u
ate
d
in
a
t
im
ely
m
an
n
e
r
an
d
p
r
ec
a
u
tio
n
s
tak
en
[
1
1
]
–
[
1
3
]
.
ML
ca
n
also
b
e
u
s
ed
to
m
o
n
ito
r
an
d
m
a
n
ag
e
en
v
ir
o
n
m
e
n
tal
a
s
p
ec
ts
o
f
m
in
i
n
g
o
p
er
atio
n
s
,
s
u
ch
as
air
a
n
d
wate
r
p
o
llu
tio
n
co
n
tr
o
l,
waste
m
an
ag
em
en
t
a
n
d
lan
d
r
ec
la
m
atio
n
.
I
t
also
r
e
d
u
ce
s
n
eg
ativ
e
en
v
ir
o
n
m
en
tal
im
p
ac
ts
an
d
co
m
p
lies
with
en
v
ir
o
n
m
en
tal
r
eg
u
latio
n
s
an
d
s
tan
d
ar
d
s
.
L
ea
d
in
g
m
in
in
g
c
o
m
p
an
ies
ar
e
d
ep
lo
y
in
g
a
u
to
n
o
m
o
u
s
v
eh
icles
an
d
AI
-
d
r
iv
en
d
r
illi
n
g
r
ig
s
,
r
e
d
u
ci
n
g
th
e
r
is
k
to
h
u
m
a
n
life
a
n
d
in
cr
ea
s
in
g
m
in
in
g
ef
f
icien
cy
.
ML
alg
o
r
ith
m
s
ar
e
u
s
ed
to
a
n
aly
ze
lar
g
e
v
o
lu
m
e
s
o
f
d
ata
co
llected
f
r
o
m
s
en
s
o
r
s
an
d
eq
u
i
p
m
en
t
t
o
p
r
ed
ict
p
o
ten
tial
eq
u
ip
m
en
t
f
ailu
r
es
an
d
p
lan
p
r
ev
e
n
tiv
e
m
ain
ten
an
ce
[
1
4
]
–
[
1
6
]
.
AI
s
y
s
tem
s
h
elp
m
o
n
ito
r
th
e
q
u
alit
y
o
f
ex
tr
ac
ted
r
aw
m
ater
ials
in
r
ea
l
tim
e,
an
aly
zin
g
s
am
p
les
an
d
p
r
ed
ictin
g
p
o
s
s
ib
le
d
ev
iatio
n
s
f
r
o
m
th
e
s
tan
d
ar
d
.
ML
allo
ws
o
p
tim
izatio
n
o
f
s
u
p
p
ly
ch
ain
s
an
d
in
v
en
t
o
r
y
m
an
a
g
em
en
t
,
wh
ich
r
ed
u
ce
s
co
s
ts
an
d
in
cr
ea
s
es
o
p
er
atio
n
a
l
ef
f
icien
cy
[
1
7
]
–
[
2
0
]
.
T
h
e
a
p
p
licatio
n
o
f
AI
a
n
d
ML
in
t
h
e
m
in
in
g
in
d
u
s
tr
y
r
e
p
r
esen
t
s
a
s
ig
n
if
ican
t
s
tep
f
o
r
war
d
i
n
th
e
d
e
v
elo
p
m
e
n
t o
f
th
e
in
d
u
s
tr
y
as sh
o
wn
in
Fig
u
r
e
1
.
Fig
u
r
e
1
.
Ad
v
an
tag
es a
n
d
o
p
p
o
r
tu
n
ities
o
f
u
s
in
g
AI
an
d
ML
in
th
e
m
in
in
g
in
d
u
s
tr
y
T
h
ese
tech
n
o
lo
g
ies
n
o
t
o
n
l
y
i
n
cr
ea
s
e
p
r
o
d
u
ctiv
ity
an
d
r
ed
u
ce
co
s
ts
,
b
u
t
also
s
ig
n
if
ican
tly
im
p
r
o
v
e
o
cc
u
p
atio
n
al
r
eliab
ilit
y
an
d
m
in
im
ize
n
eg
ativ
e
en
v
ir
o
n
m
en
tal
im
p
ac
ts
.
W
ith
in
cr
ea
s
in
g
d
em
an
d
s
f
o
r
ef
f
icien
cy
an
d
s
u
s
tain
ab
ilit
y
,
m
in
in
g
co
m
p
an
ies
u
s
in
g
AI
a
n
d
ML
g
ain
c
o
m
p
etitiv
e
ad
v
a
n
tag
es
an
d
o
p
e
n
u
p
n
ew
o
p
p
o
r
t
u
n
ities
f
o
r
f
u
r
th
er
g
r
o
wth
an
d
d
e
v
elo
p
m
e
n
t.
T
h
is
r
ev
iew
will
p
r
o
v
id
e
a
c
o
m
p
r
e
h
en
s
iv
e
an
al
y
s
is
o
f
all
asp
ec
ts
an
d
p
o
ten
tial
p
r
o
b
l
em
s
th
at
o
cc
u
r
in
th
e
p
r
o
ce
s
s
o
f
ex
p
e
r
t
s
y
s
tem
s
d
ev
elo
p
m
en
t
to
s
o
lv
e
p
r
o
b
lem
s
in
th
e
m
i
n
in
g
i
n
d
u
s
tr
y
.
A
th
o
r
o
u
g
h
an
aly
s
is
o
f
ex
is
tin
g
s
tu
d
i
es
o
n
th
e
ap
p
licatio
n
o
f
ar
tific
ial
alg
o
r
ith
m
s
wer
e
u
s
ed
to
s
o
lv
e
s
p
ec
if
ic
p
r
ac
tic
al
is
s
u
es
in
th
e
m
in
in
g
in
d
u
s
t
r
y
.
Sin
ce
th
e
a
u
th
o
r
s
'
f
u
r
th
er
g
o
al
is
to
d
ev
elo
p
I
n
tellig
en
ce
m
eth
o
d
s
in
m
in
in
g
will
h
elp
id
e
n
tify
t
h
e
m
o
s
t
r
elev
an
t
an
d
p
r
i
o
r
ity
ar
ea
s
f
o
r
f
u
r
th
er
d
ev
elo
p
m
en
t
in
th
is
s
u
b
ject
ar
ea
.
T
h
r
o
u
g
h
th
e
r
ev
iew
au
th
o
r
s
will
an
aly
ze
s
tu
d
ies
in
wh
ich
ML
an
d
d
ee
p
lear
n
in
g
an
ex
p
er
t
s
y
s
tem
f
o
r
s
o
lv
in
g
p
r
o
b
lem
s
o
f
m
in
e
w
o
r
k
in
g
s
s
u
p
p
o
r
t,
s
p
ec
ial
atten
tio
n
in
th
e
r
e
v
iew
s
h
o
u
ld
b
e
p
aid
to
s
tu
d
ies aim
ed
at
p
r
ed
ictin
g
an
d
d
iag
n
o
s
in
g
v
ar
io
u
s
s
itu
atio
n
s
th
at
ar
is
e
d
u
r
i
n
g
m
in
i
n
g
.
2.
M
E
T
H
O
D
2
.
1
.
T
he
g
o
a
l
a
nd
o
bje
ct
iv
es
o
f
t
he
s
t
ud
y
T
h
e
m
ain
o
b
jectiv
e
o
f
th
is
s
tu
d
y
is
to
p
r
o
v
id
e
a
co
m
p
r
eh
en
s
iv
e
r
ev
iew
o
f
t
h
e
ap
p
licatio
n
o
f
AI
a
n
d
ML
in
th
e
m
in
in
g
in
d
u
s
tr
y
,
wi
th
a
f
o
cu
s
o
n
ex
p
er
t sy
s
tem
s
.
T
o
ac
h
iev
e
th
is
g
o
al,
th
e
f
o
llo
win
g
task
s
wer
e
s
et:
Q1
: I
d
en
tific
atio
n
o
f
th
e
m
ain
d
ir
ec
tio
n
s
an
d
a
p
p
licatio
n
s
o
f
AI
an
d
ML
in
th
e
m
in
in
g
in
d
u
s
tr
y
.
Q2
: A
n
aly
s
is
o
f
ex
is
tin
g
ex
p
e
r
t sy
s
tem
s
,
th
eir
ad
v
an
tag
es a
n
d
d
is
ad
v
an
tag
es.
Q3
:
I
d
en
tific
atio
n
o
f
p
r
o
m
is
in
g
tech
n
o
lo
g
ies
an
d
m
eth
o
d
s
f
o
r
th
e
f
u
r
t
h
er
d
ev
el
o
p
m
en
t
an
d
im
p
lem
en
tatio
n
o
f
AI
an
d
ML
in
m
in
in
g
p
r
o
c
ess
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
p
p
lica
tio
n
o
f a
r
tifi
cia
l in
tellig
en
ce
a
n
d
ma
ch
i
n
e
lea
r
n
in
g
in
ex
p
ert s
ystems
fo
r
…
(
N
a
ta
l
ya
Mu
to
vin
a
)
3293
T
h
is
r
ev
iew
aim
s
to
h
ig
h
lig
h
t
b
o
th
th
e
th
eo
r
etica
l
ad
v
an
ce
m
en
ts
an
d
p
r
ac
tical
ap
p
licatio
n
s
o
f
AI
an
d
ML
in
im
p
r
o
v
in
g
m
in
in
g
o
p
er
atio
n
s
.
B
y
a
d
d
r
ess
in
g
t
h
ese
k
ey
q
u
esti
o
n
s
,
th
e
s
tu
d
y
s
ee
k
s
to
p
r
o
v
id
e
a
c
r
itical
an
aly
s
is
o
f
th
e
c
u
r
r
en
t
s
tate
o
f
AI
an
d
ML
tech
n
o
lo
g
ies
in
m
in
in
g
a
n
d
th
eir
p
o
te
n
tial
f
o
r
f
u
tu
r
e
in
n
o
v
atio
n
.
Fu
r
th
er
m
o
r
e
,
th
e
f
in
d
in
g
s
w
ill
o
f
f
er
in
s
ig
h
ts
in
to
h
o
w
e
x
p
er
t
s
y
s
tem
s
ca
n
b
e
o
p
tim
ized
f
o
r
e
n
h
an
c
ed
d
ec
is
io
n
-
m
ak
in
g
an
d
o
p
er
atio
n
al
ef
f
icien
cy
i
n
v
ar
i
o
u
s
m
in
in
g
en
v
ir
o
n
m
en
ts
.
2
.
2
.
F
o
rm
ula
t
i
o
n o
f
lite
ra
t
ure
s
elec
t
io
n c
rit
er
ia
T
o
co
n
d
u
ct
a
q
u
alitativ
e
liter
atu
r
e
r
ev
iew,
t
h
e
f
o
llo
win
g
s
elec
tio
n
cr
iter
ia
wer
e
id
e
n
tifie
d
:
a.
Ar
ticles p
u
b
lis
h
ed
in
p
ee
r
-
r
ev
i
ewe
d
jo
u
r
n
als an
d
co
n
f
er
en
ce
s
.
b.
R
esear
ch
co
n
d
u
cted
o
v
er
th
e
l
ast 1
0
y
ea
r
s
to
en
s
u
r
e
d
ata
is
u
p
to
d
ate.
c.
W
o
r
k
s
r
elate
d
to
th
e
u
s
e
o
f
AI
an
d
ML
d
ir
ec
tly
i
n
th
e
m
in
in
g
in
d
u
s
tr
y
.
R
esear
ch
c
o
n
t
ain
in
g
em
p
ir
ical
d
ata,
test
r
esu
lts
,
an
d
ca
s
e
s
tu
d
ies o
f
AI
an
d
ML
.
I
n
ad
d
itio
n
,
p
r
ef
er
e
n
ce
was
g
iv
en
to
s
tu
d
ies
th
at
p
r
o
v
id
ed
a
co
m
p
ar
ativ
e
an
aly
s
is
o
f
d
if
f
er
en
t
AI
a
n
d
ML
m
eth
o
d
o
l
o
g
ies
em
p
lo
y
ed
in
m
in
in
g
.
Pap
er
s
th
at
ad
d
r
ess
ed
th
e
o
b
s
tacle
s
an
d
p
r
ac
tical
ap
p
licatio
n
s
o
f
im
p
lem
en
tin
g
th
ese
tech
n
o
l
o
g
ies
in
r
ea
l
-
wo
r
ld
m
in
in
g
en
v
ir
o
n
m
e
n
ts
wer
e
also
p
r
io
r
itized
.
L
astl
y
,
in
ter
d
is
cip
lin
ar
y
r
esear
ch
th
a
t
co
m
b
in
ed
AI
,
ML
,
an
d
o
t
h
er
f
ield
s
s
was
in
clu
d
ed
to
ca
p
tu
r
e
a
b
r
o
ad
er
p
er
s
p
ec
tiv
e
o
n
in
n
o
v
atio
n
in
th
e
m
in
in
g
in
d
u
s
tr
y
.
2
.
3
.
So
urce
s
o
f
inf
o
rm
a
t
io
n
s
ea
rc
h
T
h
e
f
o
llo
win
g
d
atab
ases
an
d
r
eso
u
r
ce
s
wer
e
u
s
ed
to
f
in
d
f
o
r
p
er
tin
en
t
liter
atu
r
e:
Sco
p
u
s
,
W
eb
o
f
Scien
ce
,
I
E
E
E
Xp
lo
r
e,
an
d
Go
o
g
le
Sch
o
lar
.
Mo
r
e
o
v
er
,
s
cien
tific
jo
u
r
n
als
an
d
co
n
f
e
r
en
ce
p
r
o
ce
e
d
in
g
s
d
ev
o
ted
t
o
th
e
u
s
e
o
f
AI
an
d
ML
in
th
e
m
in
in
g
in
d
u
s
tr
y
we
r
e
an
aly
ze
d
.
T
h
e
s
ea
r
ch
also
in
clu
d
ed
s
p
ec
ialized
m
in
in
g
e
n
g
in
ee
r
in
g
p
u
b
licatio
n
s
an
d
in
d
u
s
tr
y
r
ep
o
r
ts
to
ca
p
tu
r
e
th
e
latest
ad
v
an
ce
m
en
ts
an
d
p
r
ac
tical
ap
p
licatio
n
s
o
f
AI
an
d
ML
i
n
m
in
in
g
.
I
n
ad
d
itio
n
,
ca
s
e
s
t
u
d
ies
an
d
tech
n
ical
p
ap
er
s
f
r
o
m
lead
in
g
m
in
in
g
co
m
p
an
ies
wer
e
r
ev
iewe
d
t
o
ass
es
s
r
ea
l
-
wo
r
ld
im
p
lem
e
n
tatio
n
s
.
T
h
is
co
m
p
r
eh
e
n
s
iv
e
ap
p
r
o
ac
h
e
n
s
u
r
ed
t
h
at
th
e
liter
atu
r
e
r
ev
iew
co
v
er
ed
b
o
th
ac
ad
e
m
ic
an
d
in
d
u
s
tr
y
p
er
s
p
ec
tiv
es
o
n
th
e
ap
p
licatio
n
o
f
AI
an
d
ML
in
m
in
in
g
in
d
u
s
tr
y
.
2
.
4
.
L
it
er
a
t
ure
s
ea
rc
h a
nd
s
elec
t
io
n pro
ce
s
s
T
h
e
l
i
t
e
r
a
t
u
r
e
s
e
a
r
c
h
wa
s
c
o
n
d
u
c
t
e
d
u
s
i
n
g
k
e
y
w
o
r
d
s
a
n
d
p
h
r
a
s
e
s
s
u
c
h
a
s
“A
I
i
n
m
i
n
i
n
g
,
”
“
M
L
i
n
m
i
n
i
n
g
i
n
d
u
s
t
r
y
,
”
“
e
x
p
e
r
t
s
y
s
te
m
s
i
n
m
i
n
i
n
g
,
”
“
A
I
a
p
p
l
i
c
a
t
io
n
s
i
n
m
i
n
i
n
g
,
”
“
M
L
i
n
m
i
n
i
n
g
p
r
o
c
e
s
s
e
s
,
”
a
n
d
o
t
h
e
r
s
.
A
l
l
r
et
r
i
e
v
e
d
a
r
t
ic
l
es
w
e
r
e
p
r
e
-
e
v
a
l
u
a
t
e
d
b
a
s
e
d
o
n
t
h
e
i
r
a
b
s
t
r
a
ct
s
a
n
d
k
e
y
w
o
r
d
s
t
o
d
e
t
e
r
m
i
n
e
t
h
e
i
r
r
e
l
e
v
a
n
c
e
.
A
f
t
e
r
t
h
e
i
n
i
ti
a
l
s
c
r
e
e
n
i
n
g
,
f
u
l
l
-
t
e
x
t
a
r
ti
c
l
es
w
e
r
e
o
b
t
a
i
n
e
d
f
o
r
a
m
o
r
e
d
e
t
a
i
l
e
d
e
v
a
l
u
a
t
i
o
n
o
f
t
h
e
i
r
m
e
t
h
o
d
o
l
o
g
i
e
s
a
n
d
f
i
n
d
i
n
g
s
.
T
h
e
i
n
c
l
u
s
i
o
n
c
r
it
e
r
i
a
a
ls
o
f
o
cu
s
e
d
o
n
t
h
e
d
i
v
e
r
s
i
t
y
o
f
A
I
an
d
M
L
a
p
p
l
i
ca
t
i
o
n
s
a
c
r
o
s
s
v
a
r
i
o
u
s
s
t
a
g
es
o
f
m
i
n
i
n
g
o
p
e
r
a
t
i
o
n
s
,
s
u
c
h
a
s
e
x
p
l
o
r
a
tio
n
,
e
x
t
r
a
c
t
i
o
n
,
p
r
o
c
e
s
s
i
n
g
,
a
n
d
s
a
f
e
t
y
m
o
n
i
t
o
r
i
n
g
.
S
t
u
d
i
es
t
h
a
t
o
f
f
e
r
e
d
i
n
n
o
v
a
t
i
v
e
a
p
p
r
o
a
c
h
e
s
o
r
p
r
o
p
o
s
e
d
n
o
v
e
l
a
l
g
o
r
i
t
h
m
s
w
e
r
e
p
a
r
t
i
cu
l
a
r
l
y
e
m
p
h
a
s
i
z
e
d
.
A
d
d
i
t
i
o
n
a
l
l
y
,
t
h
e
g
e
o
g
r
a
p
h
i
c
al
d
i
s
t
r
i
b
u
t
i
o
n
o
f
r
es
e
a
r
c
h
wa
s
c
o
n
s
i
d
e
r
e
d
t
o
e
n
s
u
r
e
a
g
l
o
b
a
l
p
e
r
s
p
e
c
ti
v
e
o
n
t
h
e
a
d
o
p
t
i
o
n
o
f
A
I
a
n
d
M
L
i
n
m
i
n
i
n
g
.
F
i
n
a
l
l
y
,
a
r
t
ic
l
es
t
h
a
t
p
r
o
v
i
d
e
d
k
n
o
w
l
e
d
g
e
a
b
o
u
t
t
h
e
f
u
t
u
r
e
p
o
t
e
n
t
i
a
l
a
n
d
d
i
f
f
i
c
u
l
t
i
es
o
f
A
I
-
d
r
i
v
e
n
t
e
c
h
n
o
l
o
g
i
e
s
i
n
t
h
e
i
n
d
u
s
t
r
y
we
r
e
p
r
i
o
r
i
t
i
z
e
d
f
o
r
i
n
-
d
e
p
t
h
a
n
a
l
y
s
is
.
2
.
5
.
Da
t
a
a
na
ly
s
is
a
nd
cla
s
s
i
f
ica
t
io
n
Data
an
aly
s
is
an
d
class
if
icati
o
n
p
lay
a
cr
u
cial
r
o
le
in
u
n
d
e
r
s
tan
d
in
g
th
e
d
iv
er
s
e
ap
p
licat
io
n
s
o
f
AI
an
d
ML
in
th
e
m
in
in
g
in
d
u
s
tr
y
.
B
y
s
y
s
tem
atica
lly
ca
teg
o
r
izin
g
th
e
f
in
d
in
g
s
f
r
o
m
t
h
e
s
elec
ted
ar
ticles,
v
alu
ab
le
in
s
ig
h
ts
in
to
th
e
cu
r
r
en
t
tr
en
d
s
an
d
c
h
allen
g
es
f
ac
e
d
in
th
e
f
ield
ca
n
b
e
g
ain
e
d
.
All
s
elec
ted
ar
ticle
s
wer
e
an
aly
ze
d
a
n
d
class
if
ied
in
to
th
e
f
o
llo
win
g
ca
teg
o
r
ies:
a.
Ap
p
licatio
n
s
o
f
AI
an
d
ML
in
d
if
f
er
en
t
f
ac
ets
o
f
th
e
m
in
in
g
s
ec
to
r
(
e.
g
.
,
au
to
m
atio
n
,
p
r
e
d
ictiv
e
an
aly
tics
,
m
o
n
ito
r
in
g
an
d
q
u
ality
c
o
n
tr
o
l
)
.
b.
T
y
p
es
o
f
ex
p
er
t
s
y
s
tem
s
an
d
alg
o
r
ith
m
s
u
s
ed
(
e.
g
.
,
n
eu
r
a
l
n
etwo
r
k
s
,
d
ee
p
lea
r
n
in
g
m
e
th
o
d
s
,
d
ec
is
io
n
s
u
p
p
o
r
t sy
s
tem
s
)
.
c.
Ad
v
an
tag
es a
n
d
d
is
ad
v
an
ta
g
es o
f
ap
p
ly
in
g
AI
an
d
ML
in
m
i
n
in
g
p
r
o
ce
s
s
es.
d.
Pra
ctica
l e
x
am
p
les o
f
im
p
lem
en
tatio
n
an
d
r
esu
lts
o
f
u
s
in
g
e
x
p
er
t sy
s
tem
s
in
th
e
m
in
in
g
in
d
u
s
tr
y
.
2
.
6
.
Sy
nthesis
a
nd
inte
rpre
t
a
t
io
n o
f
re
s
ults
B
ased
o
n
th
e
an
aly
s
is
an
d
class
if
icatio
n
o
f
d
ata,
a
s
y
n
th
esis
o
f
k
ey
f
in
d
in
g
s
an
d
tr
en
d
s
was
co
n
d
u
cte
d
.
T
h
e
k
ey
a
r
ea
s
wh
er
e
AI
an
d
ML
s
h
o
w
th
e
m
o
s
t
p
o
ten
tial
f
o
r
ap
p
licatio
n
h
av
e
b
ee
n
r
ec
o
g
n
ized
,
as
well
as
th
e
c
u
r
r
en
t
p
r
o
b
lem
s
an
d
ch
allen
g
es
t
h
at
th
e
m
in
in
g
in
d
u
s
tr
y
f
ac
es
wh
e
n
i
m
p
lem
en
tin
g
th
ese
tech
n
o
lo
g
ies.
T
h
e
s
y
n
th
esis
r
ev
ea
led
th
at
AI
an
d
ML
h
a
v
e
th
e
g
r
ea
test
p
o
ten
tial
in
ar
ea
s
s
u
ch
as
p
r
ed
ictiv
e
m
ain
ten
an
ce
,
o
r
e
g
r
ad
e
esti
m
atio
n
,
an
d
o
p
tim
izin
g
d
r
illi
n
g
a
n
d
b
last
in
g
p
r
o
ce
s
s
es.
Ho
wev
er
,
ch
allen
g
es
s
u
ch
as
th
e
lack
o
f
h
ig
h
-
q
u
ality
d
ata,
in
teg
r
atio
n
with
ex
is
tin
g
s
y
s
tem
s
,
an
d
h
ig
h
im
p
lem
e
n
tatio
n
co
s
ts
r
em
ain
s
ig
n
if
ican
t
b
ar
r
ie
r
s
.
T
h
e
a
n
al
y
s
is
also
h
ig
h
lig
h
ted
th
e
n
ee
d
f
o
r
m
o
r
e
r
o
b
u
s
t
cy
b
er
s
ec
u
r
ity
m
ea
s
u
r
es
as
AI
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
3
,
J
u
n
e
20
25
:
3
2
9
1
-
3
3
0
8
3294
s
y
s
tem
s
b
ec
o
m
e
in
cr
ea
s
in
g
ly
in
teg
r
ated
in
to
m
in
in
g
o
p
er
ati
o
n
s
.
Ad
d
itio
n
ally
,
th
e
im
p
o
r
ta
n
ce
o
f
d
ev
elo
p
i
n
g
s
k
illed
p
er
s
o
n
n
el
ca
p
ab
le
o
f
m
an
ag
in
g
an
d
m
ain
tain
i
n
g
AI
tech
n
o
lo
g
ies
was
u
n
d
er
s
co
r
e
d
.
Up
co
m
in
g
s
tu
d
ies
s
h
o
u
ld
c
o
n
ce
n
tr
ate
o
n
o
v
er
co
m
in
g
th
ese
ch
allen
g
es
to
co
m
p
letely
r
ea
lize
th
e
ca
p
a
b
ilit
ies
o
f
AI
an
d
ML
i
n
th
e
m
in
in
g
in
d
u
s
tr
y
.
Fu
r
th
e
r
m
o
r
e,
co
llab
o
r
atio
n
b
etwe
en
ac
ad
em
ic
in
s
titu
tio
n
s
,
in
d
u
s
tr
y
s
tak
eh
o
ld
er
s
,
an
d
tech
n
o
lo
g
y
p
r
o
v
id
e
r
s
is
ess
en
tial
to
s
p
ee
d
u
p
t
h
e
ad
v
an
ce
m
en
t
an
d
im
p
le
m
en
tatio
n
o
f
AI
an
d
ML
tech
n
o
lo
g
ies in
th
e
m
in
in
g
in
d
u
s
tr
y
.
I
n
v
estme
n
t in
r
esear
ch
a
n
d
in
n
o
v
atio
n
will b
e
cr
u
cial
f
o
r
ad
d
r
ess
in
g
b
o
t
h
tech
n
ical
an
d
p
r
ac
tical
ch
allen
g
es,
en
ab
lin
g
m
o
r
e
e
f
f
icien
t a
n
d
s
u
s
tain
ab
le
m
in
in
g
p
r
ac
tice
s
in
th
e
f
u
tu
r
e
.
2
.
7
.
Dis
cus
s
io
n a
nd
f
o
rm
ula
t
io
n o
f
re
co
m
mend
a
t
io
ns
T
h
e
f
in
al
p
ar
t
o
f
th
e
r
ev
iew
d
i
s
cu
s
s
es
th
e
o
b
tain
ed
r
esu
lts
,
d
r
aws
co
n
clu
s
io
n
s
a
b
o
u
t
th
e
cu
r
r
en
t
s
tate
o
f
ap
p
licatio
n
o
f
AI
a
n
d
ML
in
m
in
in
g
in
d
u
s
tr
y
,
a
n
d
f
o
r
m
u
lates
r
ec
o
m
m
en
d
atio
n
s
f
o
r
f
u
r
th
er
r
esear
c
h
an
d
p
r
ac
tical
im
p
lem
en
tatio
n
o
f
e
x
p
er
t
s
y
s
tem
s
.
Sp
ec
ial
f
o
cu
s
i
s
g
iv
en
t
o
th
e
p
r
o
s
p
ec
ts
f
o
r
t
h
e
d
ev
elo
p
m
e
n
t
o
f
tech
n
o
lo
g
ies
an
d
t
h
eir
p
r
o
s
p
e
ctiv
e
in
f
lu
en
ce
o
n
th
e
f
u
t
u
r
e
o
f
th
e
m
in
in
g
s
ec
to
r
.
T
h
e
r
ev
iew
em
p
h
asizes
th
e
n
ee
d
f
o
r
co
n
tin
u
ed
ad
v
an
ce
m
e
n
ts
in
AI
alg
o
r
ith
m
s
,
p
ar
ticu
lar
ly
in
h
an
d
lin
g
c
o
m
p
lex
an
d
u
n
s
tr
u
ctu
r
ed
m
in
in
g
d
ata.
Ad
d
itio
n
ally
,
it
h
i
g
h
lig
h
ts
th
e
im
p
o
r
ta
n
ce
o
f
d
e
v
elo
p
i
n
g
m
o
r
e
s
ca
lab
le
a
n
d
c
o
s
t
-
ef
f
ec
tiv
e
s
o
lu
tio
n
s
to
m
ak
e
AI
an
d
ML
tech
n
o
lo
g
ie
s
ac
ce
s
s
ib
le
to
m
in
in
g
co
m
p
a
n
ies
o
f
all
s
ize
s
.
T
h
e
in
teg
r
atio
n
o
f
AI
with
o
th
er
em
er
g
in
g
tec
h
n
o
lo
g
ies,
s
u
ch
a
s
in
ter
n
et
o
f
th
in
g
s
(
I
o
T
)
an
d
r
o
b
o
tics
,
is
id
en
tifie
d
as
a
cr
it
ical
ar
ea
f
o
r
f
u
tu
r
e
ex
p
lo
r
atio
n
.
Fu
r
t
h
er
m
o
r
e,
th
e
r
ev
iew
s
tr
ess
es
th
e
im
p
o
r
ta
n
c
e
o
f
r
eg
u
lato
r
y
f
r
am
ew
o
r
k
s
a
n
d
eth
ical
g
u
id
elin
es
to
en
s
u
r
e
r
esp
o
n
s
ib
le
AI
im
p
le
m
en
tatio
n
in
th
e
m
in
in
g
s
ec
to
r
.
3.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
T
h
is
r
ev
iew
an
aly
ze
s
th
e
lead
in
g
s
tu
d
ies
u
s
in
g
AI
m
eth
o
d
s
in
th
e
m
in
in
g
in
d
u
s
tr
y
.
Ap
p
licatio
n
s
o
f
ML
,
in
clu
d
i
n
g
r
eg
r
ess
io
n
an
al
y
s
is
,
clu
s
ter
in
g
,
a
n
d
class
if
icatio
n
,
to
p
r
ed
ict
o
r
e
g
r
ad
e
an
d
o
p
tim
ize
p
r
o
d
u
ctio
n
p
r
o
ce
s
s
es
ar
e
d
is
cu
s
s
ed
.
C
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
s
,
wh
ich
ar
e
u
s
ed
t
o
an
aly
z
e
r
o
ck
s
am
p
les,
an
d
r
ec
u
r
r
en
t
n
e
u
r
al
n
etwo
r
k
s
,
wh
ich
ar
e
u
s
ed
f
o
r
tim
e
s
er
ies
an
ticip
atin
g
in
th
e
m
in
in
g
in
d
u
s
tr
y
,
ar
e
h
ig
h
lig
h
te
d
as
s
h
o
wn
in
Fig
u
r
e
2
.
E
ac
h
s
tu
d
y
is
an
aly
ze
d
in
r
elatio
n
to
i
ts
p
o
s
itiv
e
s
id
e
s
an
d
d
r
awb
ac
k
s
.
B
en
ef
its
in
clu
d
e
in
cr
ea
s
ed
f
o
r
ec
asti
n
g
ac
cu
r
ac
y
an
d
im
p
r
o
v
ed
r
eso
u
r
ce
m
an
ag
em
en
t
th
an
k
s
to
th
e
ca
p
ac
it
y
to
id
en
tify
v
ar
io
u
s
tr
en
d
s
an
d
d
ep
en
d
en
cies
o
f
in
f
o
r
m
atio
n
b
ase.
Ho
wev
er
,
d
is
ad
v
an
tag
es
in
clu
d
e
d
if
f
icu
lty
in
in
ter
p
r
etin
g
r
esu
lts
,
h
ig
h
co
m
p
u
tatio
n
al
r
eq
u
ir
em
en
ts
,
an
d
th
e
r
eq
u
ir
e
m
en
t
f
o
r
s
u
b
s
tan
tial
d
ata
to
tr
ain
m
o
d
els.
T
h
is
r
ev
iew
s
ee
k
s
to
o
f
f
er
a
c
o
m
p
r
eh
en
s
iv
e
s
u
m
m
ar
y
o
f
r
ec
en
t d
ev
elo
p
m
en
ts
in
t
h
e
u
s
ag
e
o
f
in
tellig
en
t
s
y
s
tem
s
in
m
in
in
g
in
d
u
s
tr
y
,
h
ig
h
lig
h
t
t
h
e
p
o
ten
tial
an
d
d
if
f
ic
u
lties
o
f
e
ac
h
o
f
th
e
r
ev
iewe
d
tec
h
n
iq
u
e
s
,
an
d
co
n
t
r
ib
u
te
to
th
e
f
u
r
th
e
r
d
ev
el
o
p
m
en
t
o
f
th
i
s
im
p
o
r
tan
t a
r
ea
o
f
s
cien
ce
an
d
tech
n
o
l
o
g
y
.
Fig
u
r
e
2
.
Dir
ec
tio
n
s
o
f
AI
in
m
in
in
g
3
.
1
.
Cla
s
s
ica
l
ma
chine le
a
rning
m
o
dels
T
h
i
s
p
a
p
e
r
u
s
e
s
ML
t
o
f
o
r
e
c
a
s
t
b
o
l
t
f
a
i
l
u
r
e
s
i
n
a
m
i
n
i
n
g
e
n
v
i
r
o
n
m
e
n
t
.
T
h
e
a
d
v
a
n
t
a
g
e
s
i
n
c
l
u
d
e
t
h
e
a
b
i
l
i
t
y
t
o
a
n
a
l
y
z
e
r
e
a
l
d
a
t
a
f
r
o
m
u
n
d
e
r
g
r
o
u
n
d
m
i
n
e
s
.
T
h
e
a
u
t
h
o
r
s
a
p
p
l
i
e
d
d
i
f
f
e
r
e
n
t
v
a
r
i
a
t
i
o
n
s
o
f
t
h
e
s
u
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
i
n
e
s
(
S
V
M
)
m
o
d
e
l
s
u
c
h
a
s
p
r
i
n
c
i
p
a
l
c
o
m
p
o
n
e
n
t
s
a
n
a
l
y
s
i
s
(
P
C
A
-
S
V
M
)
a
n
d
g
r
a
d
i
e
n
t
t
r
e
e
b
o
o
s
t
i
n
g
(
G
T
B
-
S
V
M
)
t
o
a
s
s
e
s
s
t
h
e
f
a
i
l
u
r
e
r
i
s
k
o
f
b
o
l
t
s
u
p
p
o
r
t
s
i
n
u
n
d
e
r
g
r
o
u
n
d
c
o
a
l
m
i
n
e
s
.
T
h
e
P
C
A
-
S
V
M
m
o
d
e
l
s
t
a
n
d
s
o
u
t
a
n
d
s
h
o
w
e
d
s
i
g
n
i
f
i
c
a
n
t
a
d
v
a
n
t
a
g
e
s
o
v
e
r
t
h
e
o
t
h
e
r
t
w
o
a
p
p
r
o
a
c
h
e
s
.
B
y
a
p
p
l
y
i
n
g
P
C
A
-
S
V
M
,
t
h
e
a
u
t
h
o
r
s
w
e
r
e
a
b
l
e
t
o
s
o
l
v
e
t
h
e
p
r
o
b
l
e
m
o
f
m
u
l
t
i
c
o
l
l
i
n
e
a
r
i
t
y
o
f
f
e
a
t
u
r
e
s
a
n
d
s
e
l
e
c
t
o
n
l
y
t
h
e
m
o
s
t
i
m
p
o
r
t
a
n
t
o
n
e
s
,
a
s
w
e
l
l
a
s
a
c
h
i
e
v
e
a
n
a
r
e
a
u
n
d
e
r
t
h
e
R
O
C
c
u
r
v
e
(
A
U
C
)
s
c
o
r
e
o
f
0
.
8
5
o
n
t
h
e
t
r
a
i
n
i
n
g
s
e
t
a
n
d
a
n
A
U
C
s
c
o
r
e
o
f
0
.
8
6
o
n
t
h
e
t
e
s
t
s
e
t
.
T
h
e
G
T
B
m
o
d
e
l
a
l
s
o
r
e
d
u
c
e
d
t
h
e
n
u
m
b
e
r
o
f
f
e
a
t
u
r
e
s
,
b
u
t
i
t
s
A
U
C
w
a
s
0
.
8
2
o
n
t
h
e
t
r
a
i
n
i
n
g
s
e
t
a
n
d
0
.
8
1
o
n
t
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
p
p
lica
tio
n
o
f a
r
tifi
cia
l in
tellig
en
ce
a
n
d
ma
ch
i
n
e
lea
r
n
in
g
in
ex
p
ert s
ystems
fo
r
…
(
N
a
ta
l
ya
Mu
to
vin
a
)
3295
t
e
s
t
s
e
t
,
i
n
d
i
c
a
t
i
n
g
a
s
i
g
n
i
f
i
c
a
n
t
l
o
s
s
o
f
d
a
t
a
f
o
l
l
o
w
i
n
g
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
.
T
h
e
u
t
i
l
i
z
e
d
d
a
t
a
s
e
t
i
n
t
h
e
s
t
u
d
y
i
n
c
l
u
d
e
s
b
o
t
h
c
o
n
t
i
n
u
o
u
s
d
a
t
a
a
n
d
d
i
s
c
r
e
t
e
s
p
a
t
i
a
l
d
a
t
a
.
A
d
d
i
t
i
o
n
a
l
l
y
,
t
h
e
o
u
t
c
o
m
e
s
r
e
v
e
a
l
e
d
t
h
a
t
P
C
A
,
a
s
a
f
e
a
t
u
r
e
c
o
n
v
e
r
s
i
o
n
m
e
t
h
o
d
,
a
l
l
o
w
s
f
o
r
b
e
t
t
e
r
e
x
t
r
a
c
t
i
o
n
o
f
c
o
m
p
l
e
x
d
a
t
a
c
o
m
p
a
r
e
d
t
o
t
h
e
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
m
e
t
h
o
d
.
T
h
e
a
u
t
h
o
r
s
a
l
s
o
n
o
t
e
d
t
h
a
t
t
h
e
i
r
f
u
t
u
r
e
w
o
r
k
w
i
l
l
b
e
a
i
m
e
d
a
t
t
e
s
t
i
n
g
n
o
n
l
i
n
e
a
r
f
e
a
t
u
r
e
t
r
a
n
s
f
o
r
m
a
t
i
o
n
m
e
t
h
o
d
s
,
s
u
c
h
a
s
a
u
t
o
e
n
c
o
d
e
r
s
,
a
s
w
e
l
l
a
s
m
o
r
e
c
o
m
p
l
e
x
d
a
t
a
s
e
t
s
[
2
1
]
.
T
h
e
au
th
o
r
s
co
n
s
id
er
e
d
p
r
em
a
tu
r
e
f
ailu
r
e
o
f
r
o
c
k
b
o
lts
in
u
n
d
er
g
r
o
u
n
d
m
i
n
es.
I
t is b
ec
o
m
in
g
a
m
ajo
r
cr
itical
is
s
u
e
d
u
e
to
th
e
co
m
p
lex
m
ec
h
an
is
m
s
an
d
m
u
ltip
le
in
f
lu
en
cin
g
f
ac
to
r
s
,
wh
ich
m
ak
es
lab
o
r
ato
r
y
p
r
ed
ictio
n
s
o
f
ten
u
n
r
eliab
le.
T
h
e
s
tu
d
y
ad
d
r
ess
es
th
is
is
s
u
e
b
y
ap
p
licatio
n
o
f
th
e
ca
te
g
o
r
ica
l
g
r
ad
ie
n
t
b
o
o
s
tin
g
(
C
at
B
o
o
s
t)
alg
o
r
ith
m
an
d
Sh
ap
ley
ad
d
itiv
e
e
x
p
lan
atio
n
s
(
SHAP)
to
p
r
ed
ict
r
o
ck
b
o
lt
f
ailu
r
es
with
h
ig
h
ac
cu
r
ac
y
an
d
tr
an
s
p
ar
en
cy
.
Usi
n
g
a
d
ataset
f
r
o
m
an
u
n
d
er
g
r
o
u
n
d
co
al
m
in
e,
th
e
C
at
B
o
o
s
t
alg
o
r
ith
m
d
em
o
n
s
tr
ated
e
x
ce
llen
t
p
r
ed
ic
tio
n
ca
p
ab
ilit
ies,
with
h
ig
h
A
UC
v
alu
es
an
d
b
etter
p
er
f
o
r
m
an
ce
th
an
R
an
d
o
m
Fo
r
est.
T
h
e
SHAP
an
aly
s
is
s
h
o
wed
th
at
"r
o
ad
way
len
g
th
"
is
th
e
m
ain
f
ac
to
r
co
n
tr
ib
u
tin
g
to
r
o
ck
b
o
lt
f
ailu
r
e
,
with
in
cr
ea
s
in
g
r
is
k
s
in
r
o
a
d
way
s
lo
n
g
er
th
a
n
3
0
m
eter
s
an
d
in
th
e
p
r
esen
ce
o
f
h
ig
h
-
s
u
lf
u
r
g
r
o
u
n
d
wate
r
.
R
o
ck
b
o
lts
y
o
u
n
g
er
th
an
f
i
v
e
y
ea
r
s
wer
e
f
o
u
n
d
to
b
e
s
ig
n
if
ican
tly
less
s
u
s
ce
p
tib
le
t
o
f
ailu
r
e.
T
h
e
s
tu
d
y
d
em
o
n
s
tr
ates
v
alu
a
b
le
u
n
d
er
s
tan
d
in
g
o
f
t
h
e
in
tr
icate
r
elatio
n
s
h
ip
s
b
etwe
en
r
o
ck
b
o
lt
f
a
ilu
r
es
an
d
v
ar
io
u
s
g
eo
tech
n
ical
a
n
d
ec
o
lo
g
ical
v
ar
iab
les,
h
ig
h
lig
h
tin
g
th
e
im
p
o
r
tan
ce
o
f
e
x
p
lain
ab
le
ML
to
im
p
r
o
v
e
s
af
ety
a
n
d
r
eliab
ilit
y
in
u
n
d
er
g
r
o
u
n
d
m
i
n
in
g
.
T
h
u
s
,
th
is
s
tu
d
y
illu
m
i
n
ates
th
e
co
m
p
lex
r
elatio
n
s
h
ip
s
b
etwe
en
r
o
ck
b
o
lt
f
ailu
r
es
an
d
th
e
im
p
ac
t
o
f
g
eo
tech
n
ical
an
d
en
v
ir
o
n
m
e
n
tal
v
ar
iab
les.
T
h
e
p
r
o
p
o
s
ed
ap
p
r
o
a
ch
h
as
clar
ity
an
d
in
ter
p
r
etab
ilit
y
,
wh
ich
ca
n
f
ac
ilit
ate
th
e
im
p
lem
en
tatio
n
o
f
tr
an
s
p
ar
en
t
ML
f
o
r
r
o
c
k
b
o
lt
f
ailu
r
e
r
is
k
ev
alu
atio
n
in
s
u
b
ter
r
an
ea
n
m
i
n
in
g
o
p
er
atio
n
s
[
2
2
]
.
T
h
is
r
ev
iew
p
r
esen
ts
th
e
cu
r
r
en
t
s
tate
o
f
th
e
ar
t
in
ap
p
ly
in
g
ML
to
s
tr
ess
co
r
r
o
s
io
n
cr
a
ck
in
g
r
is
k
ass
es
s
m
en
t.
T
h
er
e
ar
e
m
an
y
f
o
r
m
s
o
f
c
o
r
r
o
s
io
n
,
s
o
m
e
o
f
wh
ich
ca
r
r
y
m
in
o
r
r
is
k
s
wh
il
e
o
th
er
s
ca
n
lead
to
ca
tast
r
o
p
h
ic
f
ailu
r
es
o
f
e
n
g
in
ee
r
in
g
m
ater
ials
.
Stre
s
s
co
r
r
o
s
io
n
cr
ac
k
in
g
(
SC
C
)
is
a
h
ig
h
ly
s
ev
er
e
f
o
r
m
o
f
co
r
r
o
s
io
n
th
at
is
c
h
allen
g
in
g
t
o
d
etec
t.
I
t
r
esu
lts
f
r
o
m
cr
ac
k
p
r
o
p
a
g
atio
n
i
n
a
co
r
r
o
s
iv
e
en
v
ir
o
n
m
en
t
co
m
b
i
n
ed
with
th
e
a
p
p
licatio
n
o
f
ten
s
ile
s
tr
es
s
to
m
etal
s
o
r
allo
y
s
.
Pre
d
ictin
g
an
d
id
en
tify
in
g
SC
C
o
cc
u
r
r
en
ce
s
r
em
ain
s
a
cr
itical
ch
allen
g
e
f
o
r
co
r
r
o
s
io
n
s
cien
tis
ts
an
d
en
g
in
ee
r
s
[
2
2
]
.
T
h
e
p
r
o
g
r
ess
io
n
o
f
tech
n
o
l
o
g
y
an
d
th
e
f
o
u
r
th
in
d
u
s
tr
ial
r
ev
o
lu
tio
n
h
a
v
e
led
to
an
u
n
p
r
ec
e
d
en
ted
in
cr
ea
s
e
in
av
ailab
le
d
ata.
L
ev
er
ag
in
g
th
is
d
ata
to
ad
d
r
ess
r
ea
l
-
wo
r
ld
ch
allen
g
es h
as g
ain
ed
s
ig
n
if
ican
t a
tten
tio
n
in
r
ec
e
n
t y
ea
r
s
.
T
h
e
ac
ce
s
s
ib
ilit
y
o
f
t
h
is
d
ata
en
ab
les
AI
an
d
ML
to
s
er
v
e
as
ad
v
an
ce
d
tech
n
o
lo
g
ies
f
o
r
tac
k
lin
g
c
o
m
p
lex
is
s
u
es
an
d
u
n
co
v
e
r
in
g
in
s
ig
h
ts
th
at
wo
u
ld
o
th
er
wis
e
b
e
u
n
attain
a
b
le.
ML
is
p
ar
ticu
lar
ly
u
s
ef
u
l
i
n
co
r
r
o
s
io
n
p
r
ed
ictio
n
ap
p
licatio
n
s
,
allo
win
g
th
e
u
s
e
o
f
co
r
r
o
s
io
n
-
i
n
f
lu
en
ci
n
g
d
ata
s
u
c
h
as
en
v
ir
o
n
m
en
tal
p
ar
a
m
eter
s
(
tem
p
er
atu
r
e
an
d
h
u
m
id
ity
)
,
p
r
o
ce
s
s
co
n
d
itio
n
s
(
f
lo
w
cir
c
u
m
s
tan
ce
s
,
f
lo
w
t
em
p
er
atu
r
e
an
d
p
r
ess
u
r
e)
,
m
ater
ial
ch
ar
ac
ter
is
tics
(
m
at
er
ial
ty
p
e,
m
ater
ial
th
ick
n
ess
,
p
r
o
ce
s
s
d
ev
ice
d
im
en
s
io
n
s
)
,
ex
is
tin
g
co
r
r
o
s
io
n
p
r
o
tectio
n
m
ea
s
u
r
es,
an
d
v
is
u
al
co
n
d
itio
n
s
[
2
2
]
.
All
th
ese
d
ata
ca
n
b
e
u
tili
ze
d
in
ML
alg
o
r
ith
m
s
to
m
o
d
el
an
d
p
r
ed
ict
th
e
o
cc
u
r
r
e
n
ce
o
f
s
tr
ess
co
r
r
o
s
io
n
cr
ac
k
in
g
an
d
c
o
n
d
u
ct
r
is
k
ass
ess
m
en
ts
.
T
h
is
p
a
p
er
attem
p
ts
t
o
r
e
v
ie
w
th
e
av
ailab
le
r
esear
ch
o
n
th
e
ap
p
licatio
n
o
f
ML
to
SC
C
.
I
t a
ls
o
p
r
esen
ts
th
e
cu
r
r
en
t a
d
v
an
ce
s
in
ML
an
d
SC
C
,
id
en
tifie
s
cu
r
r
en
t g
a
p
s
in
k
n
o
wled
g
e,
as we
ll a
s
o
u
tlin
es p
o
ten
tial a
v
e
n
u
es f
o
r
f
u
tu
r
e
r
esear
c
h
in
th
e
f
ield
o
f
d
eter
io
r
atio
n
r
is
k
ass
ess
m
en
t
u
s
in
g
ML
[
2
3
]
.
T
h
is
s
tu
d
y
aim
s
to
q
u
ick
l
y
an
d
ac
cu
r
ately
p
r
ed
ict
g
as
ex
p
lo
s
io
n
s
in
co
al
m
in
es
u
s
in
g
th
e
r
ea
l
-
tim
e
d
ata
g
ath
e
r
ed
b
y
th
e
s
m
ar
t
s
y
s
tem
o
f
m
in
in
g
,
c
o
v
er
i
n
g
m
o
n
ito
r
in
g
o
f
m
i
n
in
g
s
af
ety
,
wo
r
k
er
tr
ac
k
in
g
,
an
d
v
is
u
al
m
o
n
ito
r
in
g
s
y
s
tem
s
.
I
n
itially
,
th
e
m
in
e
ac
cid
e
n
t
p
r
ev
en
tio
n
s
o
f
twar
e
h
as
d
iv
i
d
ed
o
n
s
u
b
s
y
s
tem
s
co
n
s
id
er
in
g
ac
ci
d
en
t
co
n
tr
ib
u
t
in
g
f
ac
to
r
s
,
s
u
r
r
o
u
n
d
in
g
co
n
d
i
tio
n
s
an
d
v
u
ln
er
ab
le
o
b
jects,
wh
ich
ca
n
estab
lis
h
a
p
r
o
ac
tiv
e
war
n
i
n
g
s
y
s
tem
t
o
p
r
ed
ict
g
as
lev
els
e
x
p
lo
s
io
n
s
.
T
h
er
ef
o
r
e,
a
d
ataset
to
tr
ain
i
s
ch
o
s
en
ar
b
itra
r
ily
b
eg
in
n
in
g
f
r
o
m
th
e
id
e
n
tifie
d
co
al
m
in
e
s
am
p
les,
wh
ich
is
a
n
aly
ze
d
an
d
p
r
o
ce
s
s
ed
u
s
in
g
MA
T
L
AB
s
o
f
twar
e.
Nex
t,
a
lear
n
in
g
alg
o
r
ith
m
f
o
r
m
ed
f
r
o
m
t
h
e
b
ag
g
in
g
class
if
icatio
n
alg
o
r
ith
m
(
K
o
p
eć
et
a
l
.
)
is
b
u
ilt,
wh
ich
is
en
h
an
ce
d
u
s
in
g
th
e
p
ar
am
eter
s
Mtr
y
an
d
Ntr
ee
.
As
a
r
esu
lt
o
f
c
o
m
p
a
r
in
g
t
h
e
b
u
ilt
m
o
d
e
l
with
th
e
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
class
if
icatio
n
m
o
d
el,
s
p
ec
ial
co
al
m
in
e
ca
s
e
s
ar
e
ca
r
r
ied
o
u
t
to
v
alid
ate
t
h
e
ef
f
ec
tiv
e
n
ess
o
f
th
e
im
p
r
o
v
ed
g
as
ex
p
lo
s
io
n
war
n
in
g
alg
o
r
ith
m
.
T
h
e
p
r
ac
t
ical
o
u
tco
m
es
r
ev
ea
l
th
at
t
h
e
im
p
r
o
v
ed
b
a
g
g
in
g
class
if
icatio
n
alg
o
r
ith
m
ac
h
ie
v
es
1
0
0
%
ac
cu
r
ac
y
in
f
o
r
ec
a
s
tin
g
r
esu
lts
in
co
al
m
in
es,
wh
ile
th
e
p
r
ec
is
io
n
m
etr
ics
o
f
th
e
SVM
m
o
d
el
i
s
o
n
ly
7
5
%.
T
h
e
im
p
r
o
v
ed
alg
o
r
ith
m
also
d
em
o
n
s
tr
ates
r
ed
u
ce
d
m
o
d
el
d
ev
iatio
n
an
d
p
r
o
p
o
r
tio
n
al
er
r
o
r
,
co
n
f
ir
m
in
g
its
s
u
p
er
io
r
p
e
r
f
o
r
m
an
c
e
in
ea
r
ly
d
etec
tio
n
s
y
s
tem
s
f
o
r
co
al
m
in
e
g
as
ex
p
lo
s
io
n
s
.
T
h
e
ad
v
a
n
tag
es
o
f
th
is
ap
p
r
o
ac
h
i
n
clu
d
e
h
ig
h
p
r
ed
ictio
n
in
d
icato
r
an
d
d
ep
en
d
ab
ilit
y
o
f
th
e
war
n
in
g
s
y
s
tem
,
ca
p
ab
ilit
y
to
o
p
er
ate
in
r
ea
l
-
tim
e,
an
d
th
e
u
s
e
o
f
m
u
ltiv
ar
iate
d
ata
an
aly
s
i
s
to
im
p
r
o
v
e
s
af
ety
m
an
ag
em
en
t
i
n
co
al
m
in
es.
Ho
wev
er
,
th
e
s
tu
d
y
h
as
lim
itatio
n
s
,
in
clu
d
in
g
t
h
e
lim
ited
n
u
m
b
e
r
o
f
s
tu
d
y
s
am
p
les
an
d
o
n
ly
f
o
c
u
s
in
g
o
n
th
e
p
r
ev
e
n
tio
n
o
f
g
as
ex
p
lo
s
io
n
s
,
n
o
t
co
v
er
in
g
o
th
er
p
o
t
en
tial
r
is
k
s
s
u
ch
a
s
f
ir
es a
n
d
g
e
o
lo
g
ical
d
is
aster
s
[
2
4
]
.
Min
in
g
ac
tiv
ities
lead
to
ad
v
er
s
e
en
v
ir
o
n
m
en
tal
im
p
ac
ts
,
an
d
s
u
ch
r
eg
io
n
s
d
em
an
d
co
n
tin
u
o
u
s
o
b
s
er
v
atio
n
,
w
h
ich
ca
n
b
e
d
o
n
e
u
s
in
g
r
em
o
te
m
o
n
ito
r
e
d
d
ata
.
T
h
e
p
ap
e
r
ex
am
in
es
th
e
ef
f
e
cts
o
f
s
u
b
ter
r
an
ea
n
co
al
ex
tr
ac
tio
n
in
o
n
e
m
in
e
o
f
Po
lan
d
.
Sp
ec
tr
al
in
d
ices,
s
atellite
-
b
ased
r
ad
ar
in
ter
f
er
o
m
etr
y
,
g
e
o
g
r
a
p
h
ic
in
f
o
r
m
atio
n
s
y
s
tem
(
GI
S)
to
o
ls
an
d
ML
alg
o
r
ith
m
s
wer
e
em
p
lo
y
ed
.
A
s
p
atial
m
o
d
e
l
was
cr
ea
ted
th
at
d
eter
m
in
es
th
e
s
tatis
tical
im
p
o
r
tan
ce
o
f
th
e
im
p
ac
t
o
f
v
ar
i
o
u
s
elem
en
ts
o
n
t
h
e
em
er
g
en
ce
o
f
s
wam
p
s
.
T
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
3
,
J
u
n
e
20
25
:
3
2
9
1
-
3
3
0
8
3296
f
in
d
in
g
s
d
em
o
n
s
tr
ated
th
at
ch
an
g
es
in
th
e
n
o
r
m
alize
d
d
if
f
e
r
en
ce
v
eg
etatio
n
in
d
ex
,
ter
r
ain
elev
atio
n
,
wate
r
tab
le
lev
el
an
d
s
u
r
f
ac
e
d
e
f
o
r
m
atio
n
s
ig
n
if
ican
tly
a
f
f
ec
t
th
e
em
er
g
en
ce
o
f
wetlan
d
s
.
T
h
e
m
o
d
el
b
ased
o
n
th
e
r
an
d
o
m
f
o
r
est
(
R
F)
class
if
ier
ef
f
ec
tiv
ely
i
d
en
tifie
d
p
o
t
en
tial
f
lo
o
d
z
o
n
es
with
an
ac
cu
r
ac
y
o
f
7
6
%.
Geo
g
r
ap
h
ically
weig
h
ted
r
e
g
r
ess
io
n
(
GW
R
)
an
aly
s
is
allo
wed
u
s
t
o
id
e
n
tify
lo
ca
l
a
n
o
m
al
ies
in
th
e
in
f
lu
en
ce
o
f
th
e
ch
o
s
en
v
ar
iab
les
in
th
e
f
o
r
m
atio
n
o
f
s
wam
p
s
,
wh
ich
co
n
tr
ib
u
ted
to
u
n
d
er
s
tan
d
in
g
t
h
e
r
ea
s
o
n
s
f
o
r
t
h
eir
d
ev
elo
p
m
e
n
t.
T
h
e
u
s
e
o
f
RF
an
d
GW
R
allo
wed
u
s
to
o
b
tain
ac
cu
r
ate
an
d
d
etailed
d
ata
o
n
th
e
in
f
lu
en
ce
o
f
v
ar
io
u
s
f
ac
to
r
s
o
n
t
h
e
f
o
r
m
atio
n
o
f
wetlan
d
s
.
T
h
e
s
tu
d
y
tak
es
in
to
ac
co
u
n
t
v
ar
io
u
s
p
ar
am
eter
s
(
o
p
tical,
r
ad
a
r
,
g
eo
lo
g
ical,
h
y
d
r
o
lo
g
ical
an
d
m
eteo
r
o
lo
g
ical
d
ata)
,
wh
ich
al
lo
ws
u
s
to
o
b
tain
a
c
o
m
p
r
e
h
e
n
s
iv
e
u
n
d
e
r
s
tan
d
in
g
o
f
th
e
p
r
o
b
lem
.
T
h
e
u
s
e
o
f
av
ailab
le
r
em
o
te
s
en
s
in
g
d
at
a
m
ak
es
th
e
m
eth
o
d
o
l
o
g
y
ac
ce
s
s
ib
le
an
d
co
s
t
-
ef
f
ec
tiv
e
f
o
r
wid
esp
r
ea
d
u
s
e.
T
h
e
m
o
d
el
ca
n
s
o
m
etim
es
in
co
r
r
ec
tly
class
if
y
f
l
o
o
d
z
o
n
es,
wh
ich
r
eq
u
i
r
es
ad
d
itio
n
al
d
ata
f
ilter
in
g
e
f
f
o
r
t
s
.
T
h
e
s
co
r
e
o
f
ML
m
o
d
els
is
s
tr
o
n
g
ly
r
elian
t
o
n
th
e
q
u
al
ity
an
d
v
o
lu
m
e
o
f
av
ailab
le
d
ataset,
wh
ich
m
ay
l
im
it th
eir
u
s
e
in
s
o
m
e
r
eg
io
n
s
.
T
o
en
h
an
ce
t
h
e
m
o
d
el
p
r
ec
is
io
n
,
it is
ess
en
tial to
u
tili
ze
m
o
r
e
ac
cu
r
ate
g
e
o
lo
g
ic
al
an
d
h
y
d
r
o
l
o
g
ical
d
ata,
as
w
ell
as
ex
p
a
n
d
th
e
m
o
d
el
with
a
d
d
itio
n
al
v
ar
iab
les,
wh
ich
ca
n
co
m
p
licate
t
h
e
a
n
aly
s
is
p
r
o
ce
s
s
[
2
5
]
.
C
o
al
a
n
d
g
as
e
m
is
s
io
n
s
ar
e
o
n
e
o
f
th
e
m
ajo
r
f
ac
t
o
r
s
co
n
tr
ib
u
tin
g
to
f
atalities
in
u
n
d
er
g
r
o
u
n
d
co
al
m
in
es
an
d
ass
o
ciate
d
r
is
k
s
to
co
al
-
f
ir
ed
o
p
er
atio
n
s
g
lo
b
al
en
er
g
y
p
r
o
d
u
cin
g
f
r
o
m
co
al.
C
u
r
r
en
tly
,
m
eth
o
d
s
s
u
ch
as
tr
ac
k
in
g
m
eth
an
e
co
n
ce
n
tr
at
io
n
s
with
s
en
s
o
r
s
,
co
n
d
u
ctin
g
g
eo
p
h
y
s
ical
in
v
e
s
tig
atio
n
s
to
d
etec
t
g
eo
l
o
g
ic
al
f
o
r
m
atio
n
s
an
d
e
m
is
s
io
n
-
p
r
o
n
e
zo
n
es,
an
d
em
p
ir
ical
m
o
d
elin
g
t
o
p
r
ed
i
ct
em
is
s
io
n
s
ar
e
u
s
ed
to
p
r
ev
en
t
th
em
.
Ho
wev
e
r
,
with
th
e
d
ev
elo
p
m
en
t
o
f
in
d
u
s
tr
y
4
.
0
ad
v
an
ce
s
,
n
u
m
er
o
u
s
ex
a
m
in
atio
n
s
h
av
e
ex
p
lo
r
ed
th
e
u
s
e
o
f
AI
m
eth
o
d
s
f
o
r
f
o
r
ec
asti
n
g
em
is
s
io
n
s
.
T
h
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
es
an
d
th
eir
o
u
tc
o
m
es
s
h
o
w
co
n
s
id
er
a
b
le
v
a
r
iatio
n
i
n
t
h
e
p
u
b
licatio
n
s
.
T
h
e
r
esear
ch
[
2
6
]
ex
a
m
in
es
h
o
w
ML
is
u
s
ed
to
f
o
r
ec
ast
co
al
an
d
g
as
em
is
s
io
n
s
in
s
u
b
ter
r
a
n
e
an
m
in
es
em
p
lo
y
in
g
a
h
y
b
r
i
d
m
eth
o
d
.
T
h
e
m
ajo
r
it
y
p
ar
t
o
f
th
e
f
o
u
n
d
wo
r
k
s
f
o
c
u
s
in
g
o
n
p
r
ed
ictio
n
o
f
t
h
e
co
a
l
an
d
g
as
em
is
s
io
n
s
u
s
in
g
ML
was r
ev
iewe
d
in
C
h
in
a
[
2
6
]
.
T
h
e
r
esu
lts
s
h
o
w
t
h
at
au
th
o
r
s
tr
ain
ed
v
a
r
io
u
s
ML
m
o
d
els,
m
ain
ly
co
m
b
in
in
g
th
em
with
v
ar
io
u
s
o
p
tim
izatio
n
tech
n
iq
u
es,
in
co
r
p
o
r
atin
g
an
aly
s
is
o
f
p
ar
ticle
s
war
m
,
g
en
etic
alg
o
r
ith
m
s
,
th
e
th
eo
r
y
o
f
r
o
u
g
h
s
ets,
an
d
in
v
er
ted
alg
o
r
ith
m
o
f
f
ly
o
p
tim
izatio
n
t
o
f
o
r
ec
a
s
t
th
e
em
is
s
io
n
.
T
h
e
q
u
an
tity
an
d
k
in
d
o
f
in
p
u
t
v
ar
iab
les
f
o
r
f
o
r
ec
asti
n
g
v
ar
ie
d
s
u
b
s
tan
tially
,
wh
er
e
th
e
in
iti
al
g
as
v
elo
city
is
th
e
m
o
s
t
s
ig
n
if
ican
t
v
ar
iab
le
to
f
in
d
g
as
em
is
s
io
n
s
an
d
d
ep
th
o
f
th
e
co
al
s
ea
m
b
ein
g
th
e
m
o
s
t
s
ig
n
if
ican
t
ar
g
u
m
en
t
o
f
co
al
em
is
s
io
n
s
.
T
h
e
tr
ain
in
g
an
d
test
in
g
s
et
o
f
th
e
m
o
d
els
p
r
o
p
o
s
ed
in
th
e
liter
atu
r
e
s
h
o
wed
s
ig
n
if
ican
t
v
ar
i
atio
n
,
y
et
th
ey
wer
e
in
ad
eq
u
ate
in
m
o
s
t
ca
s
es,
wh
ich
ca
s
ts
d
o
u
b
t
o
n
t
h
e
d
e
p
en
d
ab
ilit
y
o
f
ce
r
tain
a
p
p
lied
m
o
d
els.
Up
co
m
in
g
s
tu
d
ies
will
ex
p
lo
r
e
h
o
w
d
ata
s
ize
an
d
in
p
u
t
p
ar
a
m
eter
s
in
f
l
u
en
ce
th
e
f
o
r
ec
asti
n
g
o
f
co
al
an
d
g
as
em
is
s
io
n
s
.
T
h
e
ad
v
a
n
tag
es
o
f
ap
p
l
y
in
g
ML
m
eth
o
d
s
t
o
em
is
s
io
n
f
o
r
ec
asti
n
g
in
clu
d
e
th
e
ca
p
ac
ity
to
h
a
n
d
le
h
u
g
e
d
atasets
an
d
a
u
to
m
atica
lly
e
n
h
an
ce
m
o
d
els
as
n
ew
d
ata
b
ec
o
m
es
a
v
ai
lab
le,
en
h
an
cin
g
th
e
p
r
e
cisi
o
n
an
d
d
ep
en
d
ab
ilit
y
o
f
f
o
r
e
ca
s
ts
.
Su
ch
d
is
ad
v
an
ta
g
es
in
clu
d
e
th
e
r
elian
ce
o
n
th
e
q
u
ality
an
d
q
u
an
tity
o
f
in
p
u
t
d
ata,
an
d
th
e
n
ee
d
f
o
r
co
m
p
lex
m
o
d
el
tu
n
in
g
to
o
b
tain
r
eliab
le
r
esu
lts
.
3
.
2
.
Dee
p
neura
l net
wo
rk
s
A
s
m
ar
t
id
en
tific
atio
n
an
d
lo
ca
lizatio
n
s
y
s
tem
m
eth
o
d
f
o
r
s
teel
b
elt
an
ch
o
r
h
o
le
in
u
n
d
er
g
r
o
u
n
d
co
al
m
in
e
was
p
r
o
p
o
s
ed
b
ased
o
n
th
e
im
p
r
o
v
e
d
y
o
u
o
n
ly
lo
o
k
o
n
ce
v
er
s
io
n
5
(
YOL
Ov
5
)
m
o
d
el.
T
h
e
m
ai
n
ad
v
an
tag
es
o
f
th
is
ap
p
r
o
ac
h
in
clu
d
e
th
e
im
p
r
o
v
ed
d
etec
tio
n
ac
cu
r
ac
y
o
f
an
ch
o
r
h
o
l
es
b
y
u
s
in
g
s
u
p
er
-
r
eso
lu
tio
n
(
SR
)
m
eth
o
d
s
to
e
n
h
an
ce
im
a
g
e
clar
ity
an
d
im
p
lem
en
tin
g
th
e
co
o
r
d
in
ate
atte
n
tio
n
(
C
A)
m
o
d
u
le
in
to
th
e
YOL
Ov
5
s
b
ac
k
b
o
n
e
n
etwo
r
k
.
T
h
is
m
o
d
el
is
ca
p
ab
le
o
f
ac
cu
r
ately
d
etec
tin
g
th
e
ch
ar
ac
ter
is
tics
o
f
s
m
all
tar
g
et
o
b
jects,
a
n
d
im
p
r
o
v
e
th
e
d
etec
tio
n
s
u
cc
ess
r
ate.
I
n
ad
d
itio
n
,
th
e
SR
-
CA
-
YOL
Ov
5
s
m
o
d
el
ac
h
iev
es
h
ig
h
av
er
ag
e
d
etec
ti
o
n
ac
cu
r
ac
y
(
9
6
.
8
%)
an
d
is
ca
p
ab
le
o
f
r
ea
l
-
tim
e
o
p
er
atio
n
wh
ile
m
ain
tain
in
g
a
h
ig
h
p
r
o
ce
s
s
in
g
s
p
ee
d
(
1
6
6
.
7
f
p
s
)
,
wh
ich
m
ee
ts
th
e
r
e
q
u
ir
em
en
ts
f
o
r
r
esp
o
n
s
iv
en
e
s
s
.
T
h
u
s
,
SR
-
CA
-
YOL
Ov
5
s
is
a
m
o
d
if
ied
v
er
s
io
n
o
f
YOL
Ov
5
s
with
a
C
A
m
ec
h
an
is
m
an
d
lik
ely
ad
d
itio
n
al
SR
o
p
tim
izatio
n
to
im
p
r
o
v
e
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
m
o
d
el
a
n
d
ac
cu
r
ac
y
in
im
a
g
e
p
r
o
ce
s
s
in
g
.
Ho
we
v
er
,
d
is
ad
v
an
tag
es
o
f
m
o
d
el
in
clu
d
e
a
d
ec
r
ea
s
e
in
th
e
f
r
a
m
e
r
ate
o
f
1
8
.
5
f
p
s
an
d
th
e
n
ee
d
f
o
r
h
ig
h
-
p
er
f
o
r
m
an
ce
c
o
m
p
u
tin
g
to
tr
ai
n
an
d
o
p
er
ate
th
e
m
o
d
el
in
an
u
n
d
er
g
r
o
u
n
d
m
in
e
en
v
ir
o
n
m
e
n
t
[
2
7
]
.
T
h
is
p
ap
er
o
u
tlin
es th
e
f
in
d
in
g
s
o
f
r
esear
ch
o
n
h
o
w
a
m
eth
o
d
b
ased
o
n
ar
tific
ial
n
eu
r
al
n
et
wo
r
k
h
av
e
b
ee
n
ap
p
lied
t
o
s
im
u
late
th
e
tu
n
n
el
b
o
r
in
g
m
ac
h
in
e
(
T
B
M)
ad
v
an
ce
m
e
n
t
r
ate.
T
h
e
a
d
v
an
ce
m
en
t
r
ate
o
f
a
T
B
M
in
r
o
ck
co
n
d
itio
n
s
is
an
ess
en
tial
f
ac
to
r
f
o
r
th
e
s
u
cc
ess
f
u
l
co
m
p
letio
n
o
f
a
tu
n
n
el
c
o
n
s
tr
u
ctio
n
p
r
o
ject.
A
d
atab
ase
was
cr
ea
ted
in
clu
d
in
g
th
e
r
ea
l
T
B
M
ad
v
an
ce
m
e
n
t
in
d
icato
r
s
,
s
in
g
le
-
ax
is
c
o
m
p
r
ess
iv
e
s
tr
en
g
th
o
f
r
o
ck
,
s
p
ac
in
g
b
etwe
en
p
lan
es
o
f
f
laws
in
th
e
m
ass
es
o
f
r
o
ck
s
an
d
t
h
e
r
o
c
k
q
u
ality
in
d
ex
.
T
h
e
d
ata
wer
e
g
ath
er
ed
f
r
o
m
th
r
ee
d
is
tin
ct
T
B
M
p
r
o
jects.
An
o
p
tim
al
ar
ch
itectu
r
e
was
d
eter
m
in
ed
to
b
e
a
f
iv
e
-
lay
e
r
n
e
u
r
al
n
etwo
r
k
with
th
r
ee
n
eu
r
o
n
s
in
th
e
in
p
u
t
la
y
er
,
9
,
7
,
an
d
3
n
e
u
r
o
n
s
in
t
h
e
f
ir
s
t,
s
ec
o
n
d
,
an
d
th
ir
d
h
id
d
en
lay
e
r
s
r
esp
ec
tiv
ely
,
an
d
a
s
in
g
le
n
e
u
r
o
n
in
th
e
o
u
t
p
u
t
lay
er
.
T
h
e
c
o
r
r
elatio
n
h
as
b
ee
n
ca
lcu
lated
f
o
r
th
e
ad
v
an
ce
m
en
t
r
ate
f
o
r
ec
asted
b
y
ar
tific
ial
n
e
u
r
al
n
etwo
r
k
was
s
u
f
f
icien
tly
h
ig
h
.
T
h
e
co
r
r
elatio
n
co
ef
f
icien
t
o
f
0
.
9
4
in
d
icate
s
a
h
ig
h
ac
cu
r
ac
y
o
f
T
B
M
a
d
v
an
ce
m
en
t
in
d
icato
r
p
r
ed
ictio
n
s
th
at
is
ca
p
ab
le
to
s
ig
n
if
ica
n
tly
im
p
r
o
v
e
p
r
o
ject
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
A
p
p
lica
tio
n
o
f a
r
tifi
cia
l in
tellig
en
ce
a
n
d
ma
ch
i
n
e
lea
r
n
in
g
in
ex
p
ert s
ystems
fo
r
…
(
N
a
ta
l
ya
Mu
to
vin
a
)
3297
p
lan
n
in
g
an
d
im
p
lem
en
tatio
n
.
T
h
e
m
o
d
el
was
tr
ain
ed
o
n
d
a
ta
f
r
o
m
th
r
ee
d
if
f
e
r
en
t
p
r
o
ject
s
,
wh
ich
in
cr
ea
s
es
its
ap
p
licab
ilit
y
in
d
if
f
e
r
en
t
g
e
o
lo
g
ical
co
n
d
itio
n
s
.
T
h
e
s
tu
d
y
allo
wed
u
s
to
d
eter
m
in
e
th
e
o
p
tim
al
s
tr
u
ctu
r
e
o
f
th
e
n
eu
r
al
n
etwo
r
k
f
o
r
th
is
task
,
wh
ich
im
p
r
o
v
es
its
p
er
f
o
r
m
an
ce
an
d
r
eliab
ilit
y
.
As
a
d
r
aw
b
ac
k
,
we
n
o
ted
t
h
e
d
ep
en
d
e
n
ce
o
n
d
ata
q
u
ality
;
th
e
m
o
d
el
r
eq
u
i
r
es
h
ig
h
-
q
u
ality
an
d
r
ep
r
esen
tativ
e
in
f
o
r
m
at
io
n
,
wh
ich
ca
n
b
e
co
m
p
lex
to
p
r
o
v
id
e.
T
u
n
in
g
an
d
o
p
tim
izin
g
th
e
n
e
u
r
al
n
e
two
r
k
p
ar
am
eter
s
r
e
q
u
ir
e
s
ig
n
if
ican
t
co
m
p
u
tin
g
r
eso
u
r
ce
s
an
d
s
p
ec
ialized
k
n
o
wled
g
e.
T
h
e
m
o
d
el
m
a
y
b
e
less
ef
f
ec
tiv
e
wh
en
u
s
ed
o
n
p
r
o
je
cts with
g
eo
lo
g
ical
co
n
d
itio
n
s
th
at
ar
e
v
er
y
d
if
f
er
en
t
f
r
o
m
th
o
s
e
o
n
wh
ich
i
t
was
tr
ain
ed
.
T
h
u
s
,
th
e
u
tili
za
tio
n
o
f
th
e
d
ee
p
lear
n
in
g
m
eth
o
d
s
f
o
r
T
B
M
p
e
n
etr
atio
n
r
ate
m
o
d
elin
g
o
f
f
e
r
s
s
ig
n
if
ican
t
ad
v
an
ta
g
es
in
ter
m
s
o
f
ac
cu
r
ac
y
an
d
o
p
tim
izatio
n
,
b
u
t
r
e
q
u
ir
es
tak
i
n
g
in
to
ac
co
u
n
t
th
e
lim
itatio
n
s
ass
o
ciate
d
with
d
ata
q
u
ality
an
d
th
e
co
m
p
le
x
ity
o
f
m
o
d
el
tu
n
in
g
[
2
8
]
.
I
n
th
is
p
ap
er
,
th
e
an
ticip
atio
n
o
f
r
o
ck
-
ca
u
s
ed
s
tr
ess
d
u
r
i
n
g
p
illar
ex
tr
ac
tio
n
is
in
v
esti
g
ated
u
s
in
g
ML
m
eth
o
d
s
[
2
9
]
.
T
h
e
m
o
d
els
tak
e
in
to
ac
co
u
n
t
f
ac
to
r
s
s
u
ch
as
wo
r
k
in
g
d
ep
t
h
(
H)
,
p
a
n
el
wid
th
/len
g
th
(
W
/L)
,
p
illar
wid
th
/wo
r
k
h
eig
h
t
(
w/h
)
,
g
o
a
f
len
g
t
h
,
an
d
ex
tr
ac
tio
n
ar
ea
[
2
9
]
.
T
h
e
p
a
p
er
em
p
h
asizes
th
e
s
ig
n
if
ican
ce
o
f
o
p
er
atio
n
al
p
ar
am
eter
s
i
n
c
o
m
p
ar
is
o
n
to
g
eo
lo
g
ical
o
n
es.
I
n
t
h
e
ca
s
es
an
aly
ze
d
,
th
e
co
r
r
elatio
n
co
ef
f
icien
t
f
o
r
r
o
c
k
-
in
d
u
ce
d
s
tr
ess
is
ap
p
r
o
x
im
ately
8
0
%
f
o
r
th
e
RF
m
o
d
el
an
d
ab
o
u
t
7
6
%
f
o
r
th
e
m
u
ltil
ay
er
p
er
ce
p
tr
o
n
(
ML
P)
,
d
em
o
n
s
tr
atin
g
th
e
s
u
p
er
io
r
p
er
f
o
r
m
a
n
ce
o
f
th
e
RF
m
o
d
el.
T
h
e
d
e
v
elo
p
ed
m
o
d
e
ls
p
r
ed
ict
th
e
s
tr
ess
co
n
d
itio
n
s
o
f
p
illar
s
.
Desp
ite
m
an
y
a
d
v
an
tag
es,
ML
also
h
as
its
d
r
awb
ac
k
s
.
ML
m
o
d
els
r
eq
u
ir
e
tr
ain
in
g
o
n
h
is
to
r
ical
d
ata
to
o
b
tain
ac
c
u
r
ate
p
r
ed
ictio
n
s
,
an
d
t
h
e
al
g
o
r
ith
m
’
s
p
r
ec
is
io
n
r
elies
o
n
th
e
q
u
an
tity
a
n
d
d
ep
en
d
a
b
ilit
y
in
th
is
d
ataset.
Ho
wev
er
,
ML
h
as
lim
ited
to
b
e
ap
p
lied
o
n
l
y
to
s
p
ec
if
ic
ar
ea
s
,
an
d
ad
d
itio
n
al
tr
ain
in
g
o
f
th
e
m
o
d
el
is
r
eq
u
ir
ed
to
wo
r
k
with
n
ew
d
ata.
I
n
t
h
is
s
tu
d
y
,
o
n
ly
f
o
u
r
p
an
els
o
f
co
n
tin
u
o
u
s
m
in
er
s
ar
e
an
aly
ze
d
,
c
o
n
s
id
er
in
g
th
e
lim
itatio
n
s
o
f
d
ata
co
llectio
n
an
d
th
e
lim
itatio
n
s
f
r
o
m
o
n
e
co
al
m
in
e.
Go
in
g
f
o
r
war
d
,
ad
d
itio
n
al
p
an
els
a
n
d
v
a
r
ied
g
e
o
-
m
in
in
g
co
n
d
it
io
n
s
ca
n
b
e
co
n
s
id
er
e
d
to
i
m
p
r
o
v
e
th
e
m
o
d
el.
T
h
er
ef
o
r
e,
s
tr
ess
p
r
ed
ictio
n
i
n
s
u
b
s
u
r
f
ac
e
co
al
m
in
es
r
em
ain
s
as
th
e
m
o
s
t
im
p
o
r
tan
t
o
b
s
tacle
s
f
o
r
m
in
in
g
en
g
in
ee
r
s
,
d
esp
ite
au
t
o
m
atio
n
,
ad
v
an
ce
d
to
o
ls
,
an
d
n
u
m
er
ica
l m
o
d
elin
g
m
eth
o
d
s
[
2
9
]
.
E
f
f
ec
tiv
e
f
o
r
ec
asti
n
g
g
r
o
u
n
d
v
ib
r
atio
n
s
r
esu
ltin
g
f
r
o
m
b
last
in
g
in
o
p
en
ca
s
t
m
in
in
g
p
lay
s
a
s
ig
n
if
ican
t
r
o
le
in
m
in
im
izin
g
en
v
ir
o
n
m
en
tal
g
r
ie
v
an
ce
s
.
T
h
is
s
tu
d
y
p
r
o
p
o
s
es
a
n
ew
h
y
b
r
id
ev
o
lu
tio
n
ar
y
ar
tific
ial
n
eu
r
al
n
etwo
r
k
(
ANN)
o
p
tim
ized
u
s
in
g
a
g
en
e
tic
alg
o
r
ith
m
(
GA)
f
o
r
p
r
ed
i
ctin
g
p
ea
k
p
ar
ticle
v
elo
city
(
PP
V)
.
T
h
e
o
p
tim
i
ze
d
GA
-
ANN
m
o
d
el
au
t
o
m
atica
lly
s
elec
ts
th
e
o
p
tim
al
ANN
ar
ch
itectu
r
e
in
clu
d
in
g
t
h
e
q
u
a
n
tity
o
f
n
eu
r
al
u
n
its
,
f
u
n
ctio
n
s
o
f
ac
tiv
atio
n
,
lear
n
in
g
alg
o
r
ith
m
an
d
th
e
n
u
m
b
er
o
f
e
p
o
ch
s
.
T
h
e
d
ataset,
c
o
m
p
r
is
in
g
m
a
x
im
u
m
c
h
ar
g
e
m
ass
p
er
d
elay
,
h
o
r
izo
n
tal
d
is
tan
ce
(
HD)
,
r
a
d
ial
d
is
tan
ce
(
R
D)
,
an
d
a
n
ewly
m
o
d
if
ie
d
r
ad
ial
d
is
tan
ce
(
MRD)
b
etwe
en
th
e
m
o
n
ito
r
in
g
an
d
b
last
in
g
s
tatio
n
s
,
was
u
tili
ze
d
to
ev
alu
ate
th
e
p
r
o
p
o
s
ed
m
eth
o
d
at
th
e
Su
n
g
u
n
co
p
p
er
m
i
n
e
in
I
r
an
.
A
p
er
f
o
r
m
a
n
ce
ev
alu
ati
o
n
o
f
th
e
GA
-
ANN
m
o
d
el
u
s
in
g
s
tatis
tical
in
d
ica
to
r
s
d
em
o
n
s
tr
ates
its
s
u
p
er
io
r
ity
o
v
er
em
p
ir
ical
p
r
ed
ictio
n
m
eth
o
d
s
an
d
t
h
e
n
eu
r
o
-
f
u
zz
y
in
f
er
en
ce
s
y
s
tem
.
A
s
ig
n
if
ican
t
r
esu
lt
i
s
th
at
u
s
in
g
m
o
d
if
ied
r
ad
ial
d
is
tan
ce
(
MRD)
in
s
tead
o
f
tr
ad
itio
n
al
HD
an
d
R
D
d
is
tan
ce
s
im
p
r
o
v
es
th
e
p
r
ed
ictio
n
a
cc
u
r
ac
y
.
I
n
s
u
m
m
a
r
y
,
th
e
r
esu
lts
d
em
o
n
s
tr
ate
th
e
ef
f
ec
tiv
en
ess
o
f
th
e
p
r
o
p
o
s
e
d
GA
-
ANN
m
eth
o
d
f
o
r
id
e
n
tify
in
g
t
h
e
o
p
tim
al
ANN
a
r
ch
itectu
r
e
f
o
r
PP
V
f
o
r
ec
asti
n
g
.
T
h
e
ad
v
an
tag
es
o
f
u
s
in
g
th
e
n
o
v
el
h
y
b
r
id
e
v
o
lu
tio
n
ar
y
ANN
ar
e:
in
c
r
ea
s
ed
f
o
r
ec
asti
n
g
ac
cu
r
ac
y
d
u
e
to
th
e
u
s
e
o
f
MRD,
o
p
tim
izatio
n
o
f
th
e
ANN
ar
ch
itectu
r
e
u
s
in
g
GA
p
r
o
v
id
es
h
ig
h
er
m
o
d
el
p
er
f
o
r
m
a
n
ce
,
an
d
a
s
y
s
tem
atic
an
d
au
to
m
ated
ap
p
r
o
ac
h
to
s
elec
tin
g
A
NN
p
ar
am
eter
s
.
T
h
e
d
is
ad
v
an
tag
es
n
o
ted
ar
e:
a
s
u
b
s
tan
tial
v
o
lu
m
e
o
f
d
ata
f
o
r
m
o
d
el
to
ac
h
iev
e
h
ig
h
ac
c
u
r
ac
y
,
th
e
m
o
d
el
m
ay
b
e
lim
ited
b
y
th
e
s
p
ec
if
icity
o
f
th
e
ap
p
licatio
n
d
o
m
ain
a
n
d
n
o
t
ad
ap
t
to
n
ew
co
n
d
itio
n
s
with
o
u
t
ad
d
itio
n
al
t
r
ain
in
g
,
a
lim
ited
am
o
u
n
t
o
f
d
ata
an
d
test
s
m
ay
af
f
ec
t
th
e
a
b
ilit
y
o
f
th
e
m
o
d
el
t
o
g
en
e
r
alize
an
d
its
r
ea
l
-
wo
r
ld
ap
p
licab
ili
ty
to
o
th
er
m
in
in
g
d
ev
elo
p
m
e
n
ts
[
3
0
]
.
An
attem
p
t
was
m
ad
e
to
esti
m
ate
an
d
f
o
r
ec
ast
b
last
-
in
d
u
ce
d
g
r
o
u
n
d
v
ib
r
atio
n
s
an
d
f
r
eq
u
en
cies
b
ased
o
n
r
o
ck
v
ar
iab
les,
m
o
d
elin
g
o
f
b
last
s
an
d
ex
p
lo
s
iv
e
p
ar
am
eter
s
th
r
o
u
g
h
an
ar
tific
i
al
n
eu
r
al
n
etwo
r
k
.
A
th
r
ee
-
lay
er
,
f
ee
d
-
f
o
r
war
d
,
b
ac
k
-
p
r
o
p
ag
atio
n
n
eu
r
al
n
etwo
r
k
with
1
5
h
id
d
e
n
u
n
its
,
1
0
i
n
p
u
t
v
a
r
iab
les,
an
d
two
o
u
tp
u
t
v
ar
iab
les
was
d
ev
elo
p
ed
u
s
in
g
1
5
4
ex
p
e
r
im
en
ta
l
an
d
m
o
n
ito
r
in
g
b
last
d
ata
f
r
o
m
a
lar
g
e
s
u
r
f
ac
e
co
al
m
in
e
in
I
n
d
ia.
T
wen
ty
n
ew
b
last
d
atasets
wer
e
u
tili
ze
d
to
v
alid
ate
an
d
co
m
p
a
r
e
th
e
p
r
ed
ictio
n
o
f
p
ea
k
p
ar
ticle
v
elo
city
an
d
f
r
eq
u
en
cy
u
s
in
g
ANN
an
d
o
th
er
f
o
r
ec
asti
n
g
m
eth
o
d
s
.
T
o
en
h
an
c
e
r
eliab
ilit
y
in
th
e
s
u
g
g
ested
ap
p
r
o
ac
h
,
t
h
e
s
am
e
d
atasets
wer
e
em
p
lo
y
ed
t
o
p
r
ed
ict
PP
V
u
s
in
g
b
o
th
estab
lis
h
ed
v
ib
r
atio
n
p
r
ed
icto
r
s
a
n
d
m
u
ltiv
ar
iate
r
e
g
r
ess
io
n
an
aly
s
is
.
T
h
e
o
u
tco
m
es
wer
e
ev
alu
ated
b
y
c
o
m
p
ar
in
g
t
h
e
co
r
r
elatio
n
an
d
m
ea
n
ab
s
o
lu
te
er
r
o
r
b
et
wee
n
th
e
o
b
s
er
v
ed
an
d
f
o
r
ec
asted
PP
V
an
d
f
r
e
q
u
en
c
y
in
d
icato
r
s
.
T
h
e
ANN
r
esu
lts
s
h
o
wed
a
v
er
y
clo
s
e
m
atch
with
th
e
ex
p
e
r
im
en
t
al
d
ata,
in
d
icatin
g
h
i
g
h
ac
cu
r
ac
y
in
co
n
tr
ast
to
tr
ad
itio
n
al
an
ticip
ato
r
s
an
d
m
u
ltiv
ar
iate
r
eg
r
ess
io
n
an
aly
s
is
(
MV
R
A)
.
ANN
h
as
th
e
ab
ilit
y
to
r
ec
o
g
n
ize
n
ew
p
atter
n
s
th
at
wer
e
n
o
t
p
r
ev
i
o
u
s
ly
p
r
esen
ted
in
th
e
tr
ain
p
ar
t a
n
d
r
e
f
r
esh
its
u
n
d
er
s
tan
d
in
g
o
v
er
tim
e
wh
en
n
ew
tr
ain
in
g
d
ata
is
ad
d
ed
.
As
a
d
is
ad
v
an
tag
e,
it
is
n
o
ted
th
at
th
e
d
ev
el
o
p
m
en
t
an
d
tu
n
in
g
o
f
ANN
r
eq
u
ir
es
s
ig
n
if
ican
t
co
m
p
u
tatio
n
al
r
e
s
o
u
r
ce
s
an
d
s
p
ec
ialized
k
n
o
wled
g
e
to
o
p
tim
ize
th
e
n
etwo
r
k
ar
c
h
itectu
r
e
.
Alth
o
u
g
h
ANN
tak
es
in
to
ac
co
u
n
t
m
o
r
e
p
ar
am
ete
r
s
th
an
tr
ad
itio
n
al
p
r
ed
icto
r
s
,
it
m
ay
s
till
n
o
t
tak
e
in
to
ac
co
u
n
t a
ll p
o
s
s
ib
le
in
f
lu
en
cin
g
f
ac
to
r
s
,
wh
ich
m
ay
lim
it th
e
ac
cu
r
ac
y
o
f
f
o
r
ec
asts
in
s
o
m
e
ca
s
es
[
3
1
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
3
,
J
u
n
e
20
25
:
3
2
9
1
-
3
3
0
8
3298
T
h
is
s
tu
d
y
f
o
cu
s
es
o
n
th
e
a
p
p
licatio
n
o
f
m
eth
o
d
s
,
n
a
m
ely
b
ag
g
i
n
g
m
o
d
els
an
d
one
-
lay
er
n
eu
r
al
n
etwo
r
k
,
to
f
o
r
ec
ast
s
tr
ess
c
o
n
d
itio
n
s
ca
u
s
ed
b
y
m
in
in
g
ac
tiv
ities
o
f
I
n
d
ian
s
u
b
s
u
r
f
ac
e
co
al
ex
ca
v
atio
n
s
.
Fo
cu
s
is
o
n
p
r
ed
ictin
g
th
e
b
e
h
av
io
r
o
f
s
tr
ata
in
m
in
in
g
zo
n
es
wh
er
e
th
e
co
b
b
lest
o
n
e
an
d
p
illar
m
eth
o
d
is
u
s
ed
.
T
h
e
s
tu
d
y
r
ev
ea
led
th
at
o
p
er
atio
n
al
p
a
r
am
eter
s
s
u
ch
as
wo
r
k
in
g
d
ep
th
,
p
a
n
el
wid
t
h
an
d
len
g
th
,
p
illar
wid
th
an
d
wo
r
k
in
g
h
eig
h
t
,
co
r
r
u
g
atio
n
len
g
th
an
d
m
in
in
g
a
r
ea
p
lay
a
k
ey
r
o
le
in
th
e
m
o
d
els
b
u
ilt
to
p
r
ed
ict
m
in
in
g
in
d
u
ce
d
s
tr
ess
.
As
o
p
p
o
s
ed
to
g
eo
lo
g
ical
f
ac
to
r
s
,
o
p
er
atio
n
al
p
ar
am
ete
r
s
wer
e
f
o
u
n
d
to
b
e
m
o
r
e
im
p
o
r
tan
t
f
o
r
th
e
ac
cu
r
ac
y
o
f
p
r
ed
ictio
n
s
.
T
h
e
d
ev
el
o
p
ed
m
o
d
els
ex
h
ib
ited
h
ig
h
co
r
r
elatio
n
co
ef
f
icien
t
(
R
2
)
r
ea
ch
in
g
8
5
%
f
o
r
b
ag
g
in
g
m
o
d
el
an
d
7
6
%
f
o
r
one
-
lay
er
n
eu
r
al
n
etwo
r
k
,
in
d
icatin
g
th
eir
ef
f
ec
tiv
en
ess
in
p
r
ed
ictin
g
p
illar
s
tr
ess
co
n
d
itio
n
s
u
n
d
er
d
if
f
e
r
en
t
o
p
er
atin
g
co
n
d
itio
n
s
.
T
h
ese
f
in
d
in
g
s
h
el
p
m
an
a
g
er
s
to
tak
e
p
r
o
ac
tiv
e
m
ea
s
u
r
es
to
m
in
im
i
ze
r
is
k
s
in
th
e
co
al
in
d
u
s
tr
y
i
n
clu
d
in
g
d
ev
elo
p
in
g
e
m
er
g
e
n
cy
r
esp
o
n
s
e
p
la
n
s
.
T
h
e
s
tu
d
y
also
f
o
u
n
d
th
at
RF
d
em
o
n
s
tr
ated
h
ig
h
er
ac
cu
r
ac
y
co
m
p
ar
e
d
to
MLP
,
alth
o
u
g
h
th
e
latter
s
h
o
wed
a
h
ig
h
er
m
ea
n
ab
s
o
lu
te
er
r
o
r
.
I
n
th
e
r
ea
lm
o
f
s
u
b
s
u
r
f
ac
e
co
al
m
in
in
g
,
th
e
a
p
p
licatio
n
o
f
ML
to
o
ls
is
in
n
o
v
ativ
e
an
d
ca
n
s
ig
n
if
ican
tly
i
m
p
r
o
v
e
th
e
s
af
ety
an
d
ef
f
icien
cy
o
f
p
r
o
ce
s
s
es.
Fu
tu
r
e
r
esear
ch
ca
n
b
e
aim
ed
at
im
p
r
o
v
in
g
th
e
m
o
d
els,
as
wel
l
as
ex
p
lo
r
in
g
o
th
er
c
o
m
p
u
tat
io
n
al
tech
n
iq
u
es,
s
u
ch
as
th
e
f
in
ite
elem
en
t
way
an
d
f
in
ite
d
if
f
e
r
en
ce
ap
p
r
o
ac
h
,
wh
ich
will
allo
w
f
o
r
m
o
r
e
in
-
d
ep
th
an
d
ac
cu
r
ate
p
r
ed
ictio
n
s
o
f
r
o
ck
b
e
h
av
io
r
u
n
d
er
d
if
f
er
e
n
t
o
p
er
atin
g
c
o
n
d
itio
n
s
.
T
h
u
s
,
wh
ile
t
h
e
ap
p
l
icatio
n
o
f
AI
an
d
ML
tech
n
i
q
u
es
o
f
s
tr
u
ctu
r
al
h
ea
lth
m
o
n
ito
r
in
g
o
f
f
er
s
s
ig
n
i
f
ican
t
b
e
n
ef
its
,
it
is
im
p
o
r
ta
n
t
to
co
n
s
id
er
th
eir
lim
itatio
n
s
t
o
d
e
v
elo
p
ef
f
ec
tiv
e
an
d
r
eliab
le
d
a
m
ag
e
d
etec
tio
n
s
y
s
tem
s
[
3
2
]
.
T
h
is
s
tu
d
y
f
o
cu
s
es
o
n
th
e
u
s
e
o
f
ex
p
l
o
s
iv
es
as
a
p
o
wer
s
o
u
r
ce
f
o
r
b
r
ea
k
in
g
r
o
ck
m
ater
ial
.
Mo
s
t
o
f
th
e
b
last
p
o
wer
is
m
i
s
p
lace
d
a
s
ea
r
th
q
u
ak
es,
n
o
is
e,
air
b
u
r
s
ts
,
an
d
o
th
er
f
ac
to
r
s
.
E
ar
th
q
u
a
k
es
ca
u
s
ed
b
y
b
last
s
d
ep
en
d
o
n
n
u
m
e
r
o
u
s
elem
en
t
s
in
clu
d
in
g
r
o
ck
m
ass
co
m
p
o
s
itio
n
,
ex
p
lo
s
iv
e
p
r
o
p
e
r
ties
,
an
d
b
last
p
lan
n
in
g
.
Fo
r
ec
asti
n
g
o
f
b
last
-
in
d
u
ce
d
ea
r
th
q
u
ak
es
th
o
u
g
h
r
eg
r
ess
io
n
m
eth
o
d
s
is
at
tim
es,
o
v
er
ly
ca
u
tio
u
s
,
wh
ich
cr
ea
tes
o
b
s
tacle
s
f
o
r
ef
f
icien
t
an
d
s
af
e
m
in
e
o
p
er
atio
n
.
T
h
e
s
ca
led
d
is
tan
ce
a
p
p
r
o
ac
h
r
em
ain
s
a
r
eliab
le
m
eth
o
d
f
o
r
p
r
e
d
ictin
g
v
i
b
r
ati
o
n
s
,
h
o
wev
er
,
th
er
e
ar
e
o
th
er
alter
n
ativ
e
m
eth
o
d
s
th
at
s
h
o
w
s
im
ilar
o
u
tco
m
es
with
s
tr
o
n
g
co
r
r
elatio
n
co
e
f
f
ic
ien
ts
[
3
3
]
.
C
o
n
tem
p
o
r
ar
y
an
aly
s
is
an
d
an
ticip
atio
n
to
o
ls
s
u
ch
as
ANN
h
av
e
d
e
m
o
n
s
tr
ated
t
o
b
e
an
o
u
ts
tan
d
in
g
m
eth
o
d
o
f
v
ib
r
atio
n
p
r
ed
ictio
n
,
as
co
n
f
ir
m
e
d
b
y
m
an
y
r
ese
ar
ch
er
s
in
th
eir
w
o
r
k
.
An
o
th
er
m
eth
o
d
u
s
ed
in
th
e
s
tu
d
y
is
an
en
s
em
b
le
lear
n
in
g
m
eth
o
d
s
u
ch
as
RF
,
wh
ich
b
u
ild
s
m
u
ltip
le
d
ec
is
io
n
tr
ee
s
an
d
s
h
o
ws
g
o
o
d
r
esu
lts
in
b
o
th
class
if
icatio
n
an
d
r
eg
r
ess
io
n
.
T
h
e
wo
r
k
m
ak
es
an
ef
f
o
r
t
was
m
ad
e
t
o
f
o
r
ec
ast
m
ax
im
u
m
f
r
ag
m
en
t
v
el
o
cities
in
ex
p
lo
s
io
n
s
at
d
if
f
er
en
t
d
is
tan
ce
s
u
s
in
g
th
e
RF
,
ANN
an
d
s
ca
led
r
eg
r
ess
io
n
m
eth
o
d
s
.
E
ac
h
m
eth
o
d
,
c
o
r
r
elatio
n
c
o
e
f
f
icien
ts
wer
e
o
b
tain
ed
u
s
in
g
d
if
f
er
en
t
in
itiatio
n
s
y
s
tem
s
,
wh
ich
r
ev
ea
led
th
at
ANN
d
em
o
n
s
tr
ates
th
e
h
ig
h
e
s
t
v
alu
es
o
f
co
r
r
elatio
n
co
ef
f
i
cien
ts
,
s
h
o
win
g
th
e
m
o
s
t
ac
cu
r
ate
r
esu
lts
am
o
n
g
th
e
th
r
ee
co
n
s
id
er
ed
m
eth
o
d
s
.
RF
al
s
o
s
h
o
wed
g
o
o
d
r
esu
lts
,
alth
o
u
g
h
lo
wer
co
m
p
ar
e
d
to
ANN,
b
u
t
s
u
p
er
io
r
to
th
e
s
ca
led
r
eg
r
ess
io
n
m
et
h
o
d
s
.
T
h
e
au
th
o
r
s
m
ad
e
th
e
f
o
llo
win
g
u
s
ef
u
l c
o
n
clu
s
io
n
s
:
a.
Ou
t
o
f
th
e
t
h
r
ee
m
eth
o
d
s
u
tili
ze
d
to
p
r
ed
ict
b
last
-
in
d
u
ce
d
v
ib
r
atio
n
s
,
ANN
an
ticip
ated
th
e
m
o
s
t
r
eliab
le
v
alu
es o
f
th
e
b
ig
g
est co
r
r
elati
o
n
in
d
icato
r
s
.
T
h
is
m
ak
es AN
N
th
e
p
r
ef
er
r
ed
to
o
l to
an
ticip
ate
b
last
-
in
d
u
ce
d
o
s
cillatio
n
s
in
m
in
in
g
.
b.
T
h
e
s
tr
o
n
g
est
co
r
r
elatio
n
in
d
i
ca
to
r
v
alu
es
f
o
r
all
o
f
th
ese
ap
p
r
o
ac
h
es
wer
e
ac
h
iev
ed
u
s
in
g
th
e
elec
tr
o
n
ic
in
itiatio
n
s
y
s
tem
.
T
h
is
d
em
o
n
s
tr
ates
th
e
ac
cu
r
ac
y
o
f
s
u
ch
a
s
y
s
tem
,
wh
ich
co
n
tr
ib
u
tes
to
a
m
o
r
e
ac
cu
r
ate
p
r
ed
ictio
n
o
f
v
i
b
r
atio
n
s
ca
u
s
e
d
b
y
e
x
p
lo
s
io
n
s
.
c.
B
ased
o
n
th
e
co
n
d
u
cted
s
tu
d
y
,
it
ca
n
b
e
co
n
clu
d
ed
th
at
it
is
r
ec
o
m
m
en
d
e
d
to
u
s
e
elec
tr
o
n
ic
d
eto
n
ato
r
s
with
th
e
p
r
ed
ictiv
e
ANN
m
o
d
el
to
ac
cu
r
ately
p
r
ed
ict
th
e
v
i
b
r
atio
n
s
ca
u
s
ed
b
y
b
last
s
in
co
n
tr
o
lled
b
last
in
g
o
p
er
atio
n
s
to
ca
lcu
late
th
e
p
e
ak
v
alu
e
in
r
e
g
u
lated
b
last
in
g
o
p
er
atio
n
s
,
in
s
tead
o
f
th
e
b
a
g
g
in
g
m
o
d
el
an
d
s
ca
led
r
eg
r
ess
io
n
m
eth
o
d
s
.
T
h
is
ca
n
g
r
ea
tly
h
elp
m
in
e
o
p
er
ato
r
s
wh
en
co
n
d
u
ctin
g
co
n
tr
o
lled
b
last
in
g
o
p
er
atio
n
s
n
ea
r
p
o
p
u
lated
a
r
ea
s
.
T
h
e
p
a
p
er
e
x
p
lo
r
es
h
o
w
d
ee
p
lear
n
in
g
is
u
s
ed
to
d
etec
t
o
p
en
-
p
it
m
in
in
g
o
p
er
atio
n
s
u
s
in
g
s
p
ac
e
im
ag
er
y
,
tr
ea
tin
g
it
as
a
la
n
d
u
tili
za
tio
n
an
d
la
n
d
c
o
v
er
cl
ass
if
icatio
n
p
r
o
b
lem
.
Usi
n
g
c
o
n
v
o
lu
ti
o
n
al
n
eu
r
al
n
etwo
r
k
s
(
C
NN)
an
d
p
r
e
-
tr
ai
n
ed
v
is
u
al
g
eo
m
etr
y
g
r
o
u
p
(
VGG)
,
r
esid
u
al
n
etwo
r
k
(
R
esNet
)
an
d
d
en
s
ely
co
n
n
ec
ted
co
n
v
o
lu
tio
n
al
n
etwo
r
k
s
(
De
n
s
eNe
t
)
ar
ch
itectu
r
es
,
a
h
u
g
e
tr
ain
d
ata
o
f
“c
o
al
m
in
e”
im
ag
es
a
n
d
a
lar
g
e
n
u
m
b
er
o
f
“n
o
n
-
c
o
al
m
i
n
e”
im
ag
es
was
p
r
ep
a
r
ed
.
T
h
e
VGG
m
o
d
el
u
s
in
g
tr
an
s
f
er
le
ar
n
in
g
ac
h
iev
e
d
th
e
h
ig
h
est
m
o
d
el
p
r
ec
is
io
n
o
f
ap
p
r
o
x
im
ately
1
0
0
%
o
n
th
e
v
ali
d
atio
n
s
et.
T
h
ese
r
esu
lts
in
d
icate
h
ig
h
ac
cu
r
ac
y
an
d
th
e
p
o
ten
tial
f
o
r
ap
p
ly
i
n
g
m
o
d
el
to
d
etec
t
co
al
o
p
e
r
atio
n
s
in
d
if
f
er
e
n
t
co
u
n
tr
ies.
T
h
e
m
o
d
el
s
h
o
wed
9
8
%
ac
cu
r
ac
y
o
n
th
e
v
alid
atio
n
d
ataset
an
d
m
o
r
e
th
a
n
9
5
%
o
n
test
im
ag
es
f
r
o
m
o
th
er
co
u
n
tr
ies,
w
h
ich
d
em
o
n
s
tr
ates
its
r
eliab
ilit
y
.
U
s
in
g
C
NN
ca
n
g
r
ea
tly
s
im
p
lify
th
e
p
r
o
ce
s
s
o
f
m
o
n
ito
r
in
g
an
d
d
etec
tin
g
co
al
m
in
es
co
m
p
ar
ed
to
tr
ad
itio
n
al
m
eth
o
d
s
.
T
h
e
m
o
d
el
ca
n
b
e
u
p
d
ated
an
d
im
p
r
o
v
ed
with
n
ew
d
ata,
allo
win
g
it
to
r
em
ain
r
elev
an
t
a
n
d
e
f
f
ec
ti
v
e.
We
wo
u
ld
lik
e
to
n
o
te
th
a
t
th
e
m
o
d
el
is
p
r
o
n
e
to
f
alse
p
o
s
itiv
es,
wh
ich
ca
n
lead
to
ad
d
itio
n
al
wo
r
k
to
f
ilt
er
o
u
t
in
co
r
r
ec
t
d
ata.
T
h
e
m
o
d
el
m
ay
m
is
class
if
y
o
th
er
ty
p
es
o
f
m
in
es,
s
u
ch
as
co
p
p
er
,
wh
ich
r
e
q
u
ir
es a
d
d
itio
n
al
d
ata
p
r
e
p
r
o
ce
s
s
in
g
m
ea
s
u
r
es
[
3
4
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
p
p
lica
tio
n
o
f a
r
tifi
cia
l in
tellig
en
ce
a
n
d
ma
ch
i
n
e
lea
r
n
in
g
in
ex
p
ert s
ystems
fo
r
…
(
N
a
ta
l
ya
Mu
to
vin
a
)
3299
A
s
a
f
u
n
d
a
m
e
n
t
a
l
c
o
m
p
o
n
e
n
t
o
f
AI
,
ML
o
f
f
e
r
s
s
u
b
s
t
a
n
ti
a
l
b
e
n
e
f
i
t
s
i
n
m
u
l
t
i
-
c
r
i
t
e
r
ia
i
n
t
e
l
li
g
e
n
t
a
s
s
e
s
s
m
e
n
t
a
n
d
d
e
ci
s
i
o
n
-
m
a
k
i
n
g
.
T
h
e
d
e
g
r
e
e
o
f
m
a
i
n
t
a
i
n
a
b
le
p
r
o
g
r
e
s
s
is
o
f
c
r
u
c
ia
l
r
o
l
e
i
n
e
v
a
l
u
a
t
i
n
g
t
h
e
s
a
f
et
y
o
f
c
o
a
l
m
i
n
i
n
g
c
o
m
p
a
n
i
e
s
.
A
t
t
h
i
s
w
o
r
k
,
t
h
e
B
a
c
k
p
r
o
p
a
g
a
t
io
n
n
e
u
r
a
l
n
e
t
w
o
r
k
a
p
p
r
o
a
c
h
i
s
e
m
p
l
o
y
e
d
t
o
m
a
k
e
s
o
l
u
t
i
o
n
s
o
n
t
h
e
i
n
d
i
c
a
t
o
r
o
f
m
a
i
n
t
a
i
n
a
b
l
e
d
e
v
el
o
p
m
e
n
t
an
d
a
s
s
es
s
t
h
e
s
a
f
et
y
o
f
c
o
a
l
m
i
n
i
n
g
e
n
t
e
r
p
r
i
s
es
.
D
r
a
w
i
n
g
f
r
o
m
t
h
e
r
es
e
a
r
c
h
o
f
m
e
t
h
o
d
s
f
o
r
a
s
s
es
s
i
n
g
t
h
e
s
u
s
t
ai
n
a
b
l
e
d
e
v
e
l
o
p
m
e
n
t
o
f
c
o
a
l
c
o
m
p
a
n
i
e
s
,
a
s
y
s
t
e
m
o
f
e
v
a
l
u
a
t
i
o
n
i
n
d
i
c
es
i
s
c
r
e
at
e
d
an
d
a
m
u
l
t
i
l
a
y
e
r
f
o
r
w
a
r
d
n
e
u
r
a
l
n
e
t
w
o
r
k
i
s
b
u
i
l
t
b
as
e
d
o
n
t
h
e
b
a
c
k
p
r
o
p
a
g
a
t
i
o
n
a
l
g
o
r
i
t
h
m
.
A
c
c
o
r
d
i
n
g
t
o
t
h
e
h
u
m
a
n
-
m
a
c
h
i
n
e
-
e
n
v
i
r
o
n
m
e
n
t
-
c
o
n
t
r
o
l
s
y
s
t
e
m
t
h
e
o
r
y
a
n
d
t
a
k
i
n
g
t
h
e
f
o
u
r
i
n
d
i
v
i
d
u
a
l
e
l
e
m
e
n
ts
a
n
d
t
h
e
e
n
t
i
r
e
c
o
a
l
o
p
e
r
a
t
i
o
n
s
s
y
s
t
e
m
as
t
h
e
s
u
b
j
ec
t
o
f
t
h
e
r
e
s
e
a
r
c
h
,
a
s
y
s
te
m
a
n
a
l
y
s
is
a
n
d
e
x
a
m
i
n
a
t
i
o
n
h
a
s
b
e
e
n
d
o
n
e
t
o
a
s
s
es
s
a
n
d
s
im
u
l
t
a
n
e
o
u
s
l
y
e
n
h
a
n
c
e
t
h
e
i
n
t
e
r
n
a
l
r
e
l
i
a
b
il
i
t
y
o
f
m
i
n
es
[
3
5
]
.
T
h
e
b
e
n
ef
its
o
f
b
ac
k
p
r
o
p
ag
atio
n
n
e
u
r
al
n
etwo
r
k
ar
e
th
at
it
av
o
id
s
s
u
b
jectiv
ity
an
d
co
m
p
lex
m
ath
em
atics
o
f
tr
ad
itio
n
al
esti
m
atio
n
ap
p
r
o
ac
h
es,
a
n
d
it
is
c
ap
ab
le
to
p
r
o
d
u
ce
s
tead
y
an
d
ac
cu
r
ate
o
u
tc
o
m
es
ev
en
in
th
e
p
r
esen
ce
o
f
s
o
m
e
in
co
m
p
lete
d
ata
an
d
a
r
g
u
m
e
n
t
d
ev
iatio
n
.
B
ac
k
p
r
o
p
ag
ati
o
n
p
r
o
v
id
es
r
esear
ch
-
b
ased
an
d
co
n
c
ep
tu
al
in
s
tr
u
cti
o
n
f
o
r
d
ec
is
io
n
-
m
ak
i
n
g
o
n
co
n
tin
u
o
u
s
ad
v
an
ce
m
en
t
f
o
r
co
a
l
m
in
in
g
co
m
p
a
n
ies
an
d
h
as
s
o
m
e
s
cien
tific
ass
ess
m
en
t.
T
h
e
d
is
ad
v
an
tag
es
o
f
m
eth
o
d
a
r
e
th
e
d
ep
e
n
d
en
ce
o
n
th
e
q
u
ality
o
f
t
h
e
in
itial
d
ata
an
d
th
e
n
ee
d
t
o
f
i
n
e
-
tu
n
e
t
h
e
m
o
d
el
to
ac
h
iev
e
h
ig
h
ac
cu
r
ac
y
.
Pro
g
r
ess
iv
e
s
tu
d
y
will
c
o
n
ce
n
tr
ate
o
n
s
u
ch
ar
ea
s
as
en
h
a
n
cin
g
t
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
'
s
an
aly
zin
g
ef
f
icien
cy
an
d
ac
c
u
r
ac
y
,
an
d
lev
er
a
g
in
g
b
i
g
d
ata
tech
n
o
lo
g
ies
to
an
aly
ze
tex
t
d
ata
co
llected
d
u
r
in
g
co
al
m
in
e
o
p
e
r
atio
n
s
to
s
tr
en
g
t
h
en
th
e
p
r
ed
ictiv
e
co
n
tr
o
l
o
f
wo
r
k
p
lace
s
af
ety
r
is
k
s
in
co
al
m
in
es.
T
h
e
o
b
jec
tiv
e
o
f
co
al
s
u
p
p
lier
s
is
to
p
r
o
v
id
e
a
s
u
b
s
tan
tial
v
o
lu
m
e
o
f
c
o
al
o
f
th
e
n
ec
ess
ar
y
lev
el
with
m
in
im
al
co
s
ts
f
o
r
its
ex
tr
ac
tio
n
.
Su
b
s
eq
u
en
tl
y
,
p
r
ed
ictin
g
p
o
wer
ch
ar
ac
ter
is
tics
is
o
n
e
o
f
th
e
m
o
s
t
cr
u
cial
task
s
aim
ed
at
o
p
tim
al
u
s
e
o
f
th
e
en
er
g
y
in
d
icat
o
r
.
T
h
e
g
o
al
o
f
th
e
au
th
o
r
s
'
wo
r
k
is
to
f
in
d
,
in
v
e
s
tig
ate,
an
d
ass
ess
th
e
m
o
s
t
ca
p
ab
le
AI
alg
o
r
ith
m
s
ex
ten
s
i
v
ely
ad
o
p
ted
in
th
e
m
in
in
g
in
d
u
s
tr
y
in
p
r
ac
tical
ap
p
licatio
n
s
p
r
ed
ictio
n
p
r
o
b
lem
.
T
h
e
r
esear
c
h
was
co
n
d
u
cted
u
s
in
g
d
ata
co
llected
f
r
o
m
lab
o
r
ato
r
y
c
o
n
d
itio
n
s
o
v
er
a
p
er
io
d
o
f
f
iv
e
y
ea
r
s
(
2
0
0
5
-
2
0
1
0
)
,
in
clu
d
i
n
g
3
3
,
2
5
6
co
al
s
am
p
les
f
r
o
m
th
e
Kr
ek
a
C
o
al
Min
e
co
m
p
an
y
.
I
t w
as a
im
ed
at
b
u
ild
i
n
g
a
p
r
ed
ictio
n
m
o
d
el
b
ased
o
n
th
e
d
escr
ib
ed
d
ata,
wh
ich
will
b
e
u
tili
ze
d
to
p
r
e
d
ict
th
e
q
u
ality
ca
teg
o
r
y
o
f
u
n
ce
r
tain
c
o
al
u
n
its
.
As
p
ar
t
o
f
t
h
e
wo
r
k
,
f
o
u
r
alg
o
r
ith
m
s
wer
e
d
eter
m
in
ed
:
C
4
.
5
,
k
-
n
ea
r
est n
eig
h
b
o
r
(
KN
N)
,
n
aiv
e
B
ay
es
(
NB
)
an
d
ML
P
[
3
6
]
.
T
h
e
g
o
al
was
to
i
d
en
tify
t
h
e
o
p
tim
al
m
o
d
el
b
y
f
o
llo
win
g
th
ese
s
tep
s
:
ea
ch
alg
o
r
ith
m
is
tu
n
ed
to
id
en
tify
ap
p
r
o
p
r
iate
m
o
d
el
p
a
r
titi
o
n
in
g
m
eth
o
d
s
th
at
en
h
an
ce
alg
o
r
ith
m
p
r
ec
is
io
n
,
th
e
s
i
g
n
if
ican
ce
o
f
in
p
u
t
f
ea
tu
r
es
is
ev
alu
ated
,
a
n
d
f
in
ally
,
th
e
alg
o
r
ith
m
s
ar
e
co
m
p
ar
ed
b
ased
o
n
th
eir
e
f
f
ec
tiv
en
ess
T
h
e
f
in
al
ev
alu
atio
n
o
f
th
e
r
esu
lts
id
en
tifie
d
ML
P
as
th
e
b
est
f
o
r
ec
asti
n
g
m
eth
o
d
f
o
r
th
is
f
ield
with
an
id
ea
l
co
n
f
ig
u
r
atio
n
f
o
r
th
e
in
p
u
t,
h
id
d
en
,
an
d
o
u
t
p
u
t
la
y
er
s
.
T
h
e
p
r
ed
ictiv
e
m
o
d
el
f
o
r
th
e
f
ield
was
attain
ed
th
e
o
p
tim
al
co
m
p
o
s
itio
n
(
1
4
-
24
-
7
)
f
o
r
all
o
f
th
e
n
etwo
r
k
lay
er
s
.
T
h
e
o
u
tco
m
es
s
h
o
w
th
at
t
h
e
m
o
d
el
ca
n
b
e
a
cr
u
cial
in
s
tr
u
m
en
t f
o
r
f
o
r
ec
ast
in
g
co
al
q
u
ality
.
New
in
s
ig
h
ts
ca
n
s
er
v
e
as
a
c
r
u
cial
s
u
p
p
o
r
t to
m
ak
e
a
d
ec
is
io
n
an
d
co
n
t
r
o
l
th
e
d
i
f
f
er
en
t
s
y
s
t
em
s
,
ass
u
r
in
g
p
r
o
d
u
ct
an
d
p
r
o
d
u
ctio
n
q
u
ality
.
Fo
r
u
p
c
o
m
in
g
r
esear
ch
,
it
is
p
lan
n
ed
to
s
tu
d
y
th
e
p
o
s
s
ib
ilit
y
o
f
in
tr
o
d
u
cin
g
th
e
r
esu
ltin
g
p
r
ed
ictiv
e
m
o
d
el
i
n
to
a
n
o
n
lin
e
o
b
s
er
v
in
g
s
y
s
tem
o
f
th
e
r
ea
l
in
d
icato
r
s
o
f
th
e
m
ater
ial
o
f
co
al
m
o
v
in
g
alo
n
g
th
e
co
n
v
e
y
o
r
,
wh
ich
will
p
r
o
v
id
e
in
f
o
r
m
atio
n
ab
o
u
t
th
e
q
u
ality
o
f
co
al
in
r
ea
l
tim
e.
T
h
is
s
tu
d
y
h
ig
h
lig
h
t
s
th
e
cr
itical
v
u
ln
er
ab
ilit
y
o
f
co
al
m
in
es
d
u
e
to
in
s
u
f
f
icien
t
air
f
lo
w,
wh
ich
p
o
s
es
s
ig
n
if
ican
t
r
is
k
s
to
r
el
iab
ilit
y
an
d
p
er
s
o
n
n
el
m
a
n
a
g
em
en
t.
T
h
er
e
f
o
r
e,
o
n
g
o
in
g
s
u
r
v
eillan
ce
o
f
air
f
l
o
w
in
u
n
d
er
g
r
o
u
n
d
m
in
es
is
ess
en
tial
to
d
etec
t
p
o
ten
tial
d
is
aster
s
.
Var
io
u
s
AI
m
eth
o
d
s
ar
e
u
s
ed
to
esti
m
ate
n
o
n
lin
ea
r
air
f
lo
w
p
ar
am
eter
s
in
m
in
es,
b
u
t
o
f
ten
en
co
u
n
te
r
p
r
o
b
lem
s
s
u
c
h
as
lo
ca
l
m
in
im
a
a
n
d
p
o
o
r
co
n
v
e
r
g
en
ce
s
p
ee
d
[
3
7
]
.
Sem
in
an
d
Ko
r
m
s
h
ch
ik
o
v
[
3
7
]
p
r
o
p
o
s
es
a
n
ew
m
o
d
el
t
h
at
co
m
b
in
es
ad
a
p
tiv
e
n
eu
r
o
-
f
u
z
zy
in
ter
f
ac
e
s
y
s
tem
(
ANFI
S)
with
GA
to
f
o
r
ec
ast
p
o
wer
u
s
ag
e
as
well
as
ai
r
f
lo
w
in
u
n
d
er
g
r
o
u
n
d
m
in
e
v
e
n
tilatio
n
s
y
s
tem
s
.
GA
is
u
s
ed
to
au
to
m
ate
th
e
d
is
co
v
er
y
a
n
d
co
n
f
ig
u
r
atio
n
o
f
n
etwo
r
k
ar
ch
itectu
r
es,
r
e
d
u
ci
n
g
th
e
n
ee
d
to
m
a
n
u
ally
co
n
f
ig
u
r
e
o
p
tim
al
n
etwo
r
k
d
esig
n
.
As
a
co
m
p
ar
is
o
n
,
two
p
r
ed
ictiv
e
b
en
ch
m
ar
k
m
o
d
els,
p
ar
ticle
s
war
m
o
p
tim
izat
io
n
an
d
B
ay
es
o
p
tim
izatio
n
(
B
O)
,
ar
e
p
r
esen
ted
to
illu
s
tr
ate
th
e
e
f
f
ec
tiv
en
ess
o
f
GA
in
d
etec
tin
g
th
e
b
est
h
y
p
er
p
ar
a
m
eter
s
f
o
r
ANFI
S
an
d
ANN
m
o
d
els.
E
x
p
er
im
en
tal
an
al
y
s
is
v
alid
ates
th
e
p
r
o
p
o
s
ed
m
o
d
el
ag
ai
n
s
t
s
ev
er
al
b
aselin
e
ap
p
r
o
ac
h
e
s
u
s
in
g
s
tatis
t
ical
p
ar
am
eter
s
s
u
ch
as
r
o
o
t
m
ea
n
s
q
u
ar
e
er
r
o
r
,
m
ea
n
a
b
s
o
lu
te
er
r
o
r
,
an
d
co
ef
f
icien
t
o
f
d
eter
m
in
atio
n
(
R
s
q
u
ar
e)
.
T
h
e
f
in
d
in
g
s
r
ev
ea
l
o
u
tp
er
f
o
r
m
an
ce
o
f
th
e
d
ev
elo
p
ed
m
o
d
el
ag
ain
s
t
b
aselin
e
m
o
d
els
o
n
th
ese
p
er
f
o
r
m
an
ce
m
etr
ics.
T
h
u
s
,
th
is
wo
r
k
ad
v
an
ce
s
v
en
tilatio
n
an
d
m
o
n
i
to
r
in
g
tech
n
o
lo
g
ies
in
m
in
es
with
th
e
g
o
al
o
f
im
p
r
o
v
in
g
o
p
er
atio
n
al
r
eliab
i
lity
,
im
p
r
o
v
in
g
s
af
ety
an
d
h
ea
lth
co
n
d
itio
n
s
,
r
ed
u
cin
g
e
n
er
g
y
a
n
d
o
p
er
atin
g
co
s
ts
,
an
d
in
cr
ea
s
in
g
o
v
e
r
all
m
in
e
p
r
o
d
u
ctiv
ity
.
T
h
is
s
tu
d
y
also
d
e
m
o
n
s
tr
ates
a
d
is
tin
ctiv
e
h
y
b
r
id
n
eu
r
o
-
g
en
etic
s
y
s
tem
(
ANFI
S
-
GA)
to
o
p
tim
izin
g
alg
o
r
ith
m
s
tr
u
c
tu
r
es,
wh
ich
n
o
t
o
n
l
y
r
ed
u
ce
s
co
m
p
u
tatio
n
tim
e
an
d
co
s
t,
b
u
t a
ls
o
lev
er
ag
es th
e
ca
p
ab
ilit
y
o
f
GA
to
p
r
o
d
u
ce
m
o
r
e
o
p
tim
ized
m
o
d
el
s
tr
u
ctu
r
es.
3
.
3
.
Rec
urre
nt
neura
l net
wo
rk
s
T
h
e
au
th
o
r
s
o
f
s
u
g
g
ested
s
o
lu
tio
n
b
ased
o
n
u
n
if
ie
d
m
an
if
o
l
d
ap
p
r
o
x
im
atio
n
an
d
p
r
o
jectio
n
(
UM
AP)
an
d
l
o
n
g
s
h
o
r
t
-
te
r
m
m
em
o
r
y
(
L
STM
)
m
eth
o
d
s
to
f
o
r
ec
ast
f
i
r
e
co
n
d
itio
n
s
i
n
s
ea
led
zo
n
es
o
f
u
n
d
er
g
r
o
u
n
d
co
al
o
p
er
atio
n
s
.
T
h
is
m
o
d
el
p
r
o
tec
ts
th
e
liv
es
o
f
m
in
er
s
b
y
p
r
o
v
id
in
g
ea
r
ly
war
n
i
n
g
o
f
im
p
en
d
in
g
d
an
g
er
s
.
T
h
e
s
u
g
g
ested
p
r
ed
ictiv
e
m
o
d
el
v
i
s
u
ally
p
r
esen
ts
th
e
f
ir
e
co
n
d
itio
n
s
in
th
e
f
o
r
m
at
o
f
an
E
llico
tt
ex
p
an
s
io
n
p
lo
t.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
3
,
J
u
n
e
20
25
:
3
2
9
1
-
3
3
0
8
3300
E
f
f
ec
tiv
en
ess
o
f
t
h
e
s
u
g
g
ested
f
o
r
ec
asti
n
g
m
o
d
el
is
ex
p
e
r
im
en
tally
m
ea
s
u
r
ed
in
c
o
n
tr
as
t
o
f
c
u
r
r
en
t
m
o
d
els
s
u
ch
as
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVR
)
an
d
a
u
to
r
eg
r
ess
iv
e
in
teg
r
ated
m
o
v
in
g
av
e
r
ag
e
(
AR
I
MA
)
.
I
t
was
o
b
s
er
v
ed
t
h
at
th
e
UM
AP
-
L
STM
m
o
d
el
d
e
m
o
n
s
tr
ated
t
h
e
lo
west
r
o
o
t
m
ea
n
s
q
u
ar
e
er
r
o
r
in
p
r
e
d
ictin
g
g
as
co
n
ce
n
tr
atio
n
s
ac
r
o
s
s
v
ar
io
u
s
ty
p
es,
in
d
icatin
g
a
h
ig
h
er
e
f
f
i
cien
cy
o
f
th
e
p
r
o
p
o
s
ed
f
o
r
ec
a
s
tin
g
m
o
d
els.
Fire
s
in
m
in
es
f
r
eq
u
en
tly
r
esu
lt
in
ex
p
lo
s
io
n
s
ca
u
s
ed
b
y
g
as
an
d
co
al
d
u
s
t,
w
h
ich
p
o
s
e
a
d
a
n
g
er
to
th
e
liv
es
o
f
m
in
er
s
an
d
co
m
p
licate
r
escu
e
ef
f
o
r
ts
.
T
h
e
r
ef
o
r
e
,
it
is
n
ec
e
s
s
ar
y
to
m
o
n
ito
r
th
e
s
tate
o
f
th
e
g
as
m
ix
tu
r
e
in
s
ea
led
ar
ea
s
an
d
s
tu
d
y
tr
en
d
s
in
th
e
ex
p
lo
s
iv
en
ess
o
f
th
e
g
as
m
ix
tu
r
e
o
v
e
r
tim
e.
Kn
o
w
led
g
e
o
f
f
u
tu
r
e
g
as
co
n
ce
n
tr
atio
n
s
allo
ws im
m
ed
i
ate
ac
tio
n
to
b
e
ta
k
en
to
elim
i
n
ate
th
e
h
az
ar
d
[
3
8
]
.
T
h
is
s
tu
d
y
in
t
r
o
d
u
ce
s
a
d
ee
p
n
e
u
r
al
n
etwo
r
k
d
esig
n
ed
t
o
p
r
e
d
ict
g
as
c
o
n
ce
n
tr
atio
n
s
in
s
ea
led
s
ec
tio
n
s
o
f
u
n
d
er
g
r
o
u
n
d
co
al
m
in
es,
u
tili
zin
g
v
a
r
io
u
s
I
o
T
s
en
s
o
r
s
p
lace
d
in
a
m
etal
g
as
r
eser
v
o
ir
.
Air
is
au
to
m
atica
lly
d
r
awn
f
r
o
m
th
e
s
ea
led
ar
ea
at
s
et
p
er
io
d
s
u
s
in
g
a
s
o
len
o
id
v
alv
e,
s
u
ctio
n
p
u
m
p
,
an
d
p
r
o
g
r
a
m
m
ab
le
m
icr
o
co
n
tr
o
ll
er
.
Gas
lev
el
m
eter
s
co
n
tin
u
o
u
s
ly
o
b
s
er
v
e
th
e
g
as
lev
els
with
in
th
e
co
al
o
p
er
atio
n
a
n
d
r
elay
t
h
e
d
en
s
it
y
d
ata
to
a
s
er
v
er
r
o
o
m
o
n
th
e
s
u
r
f
ac
e
v
ia
a
wir
eless
n
etwo
r
k
,
with
clo
u
d
d
ata
s
to
r
ag
e
f
o
r
f
u
r
th
er
p
r
o
ce
s
s
in
g
.
I
n
th
is
s
tu
d
y
,
a
f
o
r
ec
asti
n
g
m
o
d
el
is
p
r
o
p
o
s
ed
th
at
co
m
b
in
es
d
im
en
s
io
n
ality
r
ed
u
ctio
n
tech
n
iq
u
es
with
r
ec
u
r
r
en
t
m
o
d
els
ca
p
ab
le
o
f
r
e
tain
in
g
m
em
o
r
y
,
aim
in
g
to
i
m
p
r
o
v
e
p
r
ed
ictio
n
ac
cu
r
ac
y
.
T
h
e
t
-
SNE
m
o
d
el
m
eth
o
d
is
u
s
ed
t
o
r
ed
u
ce
th
e
co
m
p
lex
ity
o
f
r
ec
o
r
d
e
d
g
as
co
n
ce
n
tr
atio
n
d
ata,
wh
ile
th
e
VAE
lay
er
r
ec
o
n
s
tr
u
cts
th
e
in
ter
n
al
f
ea
tu
r
es
o
f
t
h
e
lo
w
-
d
im
e
n
s
io
n
al
g
as
co
n
c
en
tr
atio
n
s
.
T
h
e
B
i
-
L
STM
lay
er
is
th
en
em
p
lo
y
ed
to
p
r
ed
ict
th
e
co
n
ce
n
t
r
atio
n
s
o
f
g
ases
.
T
h
e
ad
v
an
tag
es
o
f
s
u
g
g
ested
r
ec
u
r
r
en
t
m
o
d
el
f
o
r
p
r
ed
ictin
g
g
as
co
n
ce
n
tr
atio
n
s
in
s
ea
led
ar
ea
s
o
f
co
al
m
in
es
in
clu
d
e
h
ig
h
p
r
e
d
ictio
n
ac
cu
r
ac
y
,
as
ev
id
en
ce
d
b
y
lo
w
m
ea
n
s
q
u
a
r
e
er
r
o
r
(
MSE
)
v
alu
es
co
m
p
ar
e
d
to
alter
n
ativ
e
au
t
o
r
e
g
r
ess
iv
e
in
teg
r
ated
m
o
v
in
g
av
er
ag
e
(
AR
I
MA
)
an
d
c
h
ao
s
tim
e
s
er
ies
(
C
HAOS)
m
o
d
els.
T
h
e
m
o
d
el
is
ab
le
t
o
ef
f
ec
tiv
ely
ac
co
u
n
t
f
o
r
th
e
co
m
p
lex
r
elatio
n
s
h
ip
s
b
etwe
e
n
th
e
co
n
ce
n
tr
atio
n
s
o
f
v
ar
io
u
s
g
ases
an
d
tim
e,
wh
ich
m
ak
es it m
o
r
e
ad
ap
tiv
e
to
ch
an
g
es
in
th
e
m
in
e
en
v
ir
o
n
m
en
t.
I
n
a
d
d
itio
n
,
t
h
e
u
s
e
o
f
t
-
d
i
s
tr
ib
u
ted
s
to
ch
asti
c
n
eig
h
b
o
r
e
m
b
ed
d
in
g
(t
-
SNE)
an
d
v
a
r
iatio
n
al
au
t
o
en
c
o
d
er
(
VAE
)
tech
n
o
lo
g
ies
ca
n
r
e
d
u
ce
d
ata
d
im
en
s
io
n
ality
an
d
ex
tr
ac
t
im
p
o
r
ta
n
t
f
ea
tu
r
es,
wh
ich
en
h
a
n
ce
th
e
o
v
er
all
p
r
o
d
u
ctiv
ity
o
f
th
e
s
o
lu
tio
n
.
Ho
wev
e
r
,
th
e
m
o
d
el
also
h
as
d
is
ad
v
a
n
tag
es.
Par
ticu
lar
ly
,
th
e
co
m
p
lex
ity
o
f
s
ettin
g
u
p
an
d
in
ter
p
r
etin
g
th
e
r
esu
lts
ca
n
b
e
h
ig
h
d
u
e
to
th
e
u
s
e
o
f
s
ev
er
al
co
m
p
lex
alg
o
r
ith
m
s
(
t
-
SNE,
VAE
,
an
d
bi
-
L
STM
)
th
at
r
eq
u
ir
e
d
ee
p
u
n
d
e
r
s
tan
d
in
g
an
d
ex
p
er
ien
ce
in
ML
an
d
g
eo
lo
g
y
.
I
n
ad
d
itio
n
,
th
e
m
o
d
el
r
eq
u
ir
es
s
ig
n
if
ica
n
t
co
m
p
u
t
atio
n
al
r
eso
u
r
ce
s
a
n
d
t
r
ain
in
g
tim
e
d
u
e
t
o
its
d
ee
p
ar
ch
itectu
r
e
an
d
th
e
n
ee
d
to
p
r
o
ce
s
s
lar
g
e
am
o
u
n
ts
o
f
d
ata
[
3
9
]
.
E
ar
ly
d
etec
tio
n
o
f
cr
ac
k
s
allo
ws
f
o
r
p
r
o
m
p
t
ac
tio
n
to
ad
d
r
ess
th
em
,
g
u
ar
an
teein
g
th
e
r
e
liab
ilit
y
o
f
b
o
th
wo
r
k
e
r
s
an
d
m
ac
h
in
er
y
in
s
u
r
f
ac
e
co
al
o
p
er
atio
n
s
.
Ob
s
er
v
atio
n
o
f
cr
ac
k
s
in
th
ese
ar
ea
s
is
cr
u
cial
f
o
r
s
af
eg
u
ar
d
in
g
wo
r
k
er
s
a
n
d
p
r
o
tectin
g
n
atio
n
al
r
eso
u
r
ce
s
.
Dig
ital
twin
s
(
DT
s
)
a
r
e
es
s
en
tial
f
o
r
f
r
ac
tu
r
e
id
en
tific
atio
n
in
s
u
r
f
ac
e
c
o
al
m
in
es,
o
f
f
er
in
g
co
n
tin
u
o
u
s
,
r
ea
l
-
tim
e
o
b
s
er
v
i
n
g
o
f
m
in
e
co
n
d
itio
n
s
an
d
th
e
ad
jace
n
t
ar
ea
.
Mu
ltip
le
s
en
s
o
r
s
an
d
I
o
T
t
o
o
ls
co
llect
g
r
o
u
n
d
m
o
tio
n
an
d
s
tr
ess
d
ata.
I
n
teg
r
atin
g
th
is
d
ata
in
t
o
DT
allo
ws
th
e
id
e
n
tific
atio
n
a
n
d
a
n
aly
s
is
o
f
a
n
o
m
alies
th
at
co
u
ld
s
ig
n
al
th
e
d
ev
elo
p
m
en
t
o
r
s
p
r
ea
d
o
f
cr
ac
k
s
.
T
h
is
wo
r
k
p
r
o
p
o
s
es
a
d
ee
p
n
eu
r
al
n
etwo
r
k
with
d
en
s
e
co
n
n
ec
tiv
ity
an
d
lo
w
weig
h
t
em
b
ed
d
e
d
in
DT
f
o
r
f
r
ac
tu
r
e
id
en
tific
atio
n
a
n
d
p
r
o
ac
tiv
e
m
ain
ten
an
ce
d
ec
is
io
n
m
ak
in
g
v
ia
in
teg
r
atin
g
tim
e
s
er
ies,
liv
e
d
ata
co
llected
f
r
o
m
s
en
s
o
r
s
,
an
d
in
f
o
r
m
atio
n
f
r
o
m
f
o
r
ec
asti
n
g
m
o
d
els.
T
h
e
p
r
o
p
o
s
ed
DT
s
y
s
tem
is
ca
p
ab
le
to
p
r
ed
ict
th
e
f
o
r
m
o
f
cr
ac
k
s
,
wh
ich
allo
ws
p
r
o
ac
tiv
e
m
ea
s
u
r
es
to
elim
in
ate
th
em
.
W
h
en
co
m
p
a
r
in
g
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
n
etwo
r
k
with
o
th
er
m
o
d
els,
it
was
f
o
u
n
d
to
s
u
r
p
ass
all
cu
ttin
g
-
e
d
g
e
d
e
ep
n
eu
r
al
n
etwo
r
k
s
in
s
ev
er
al
k
ey
m
etr
ics,
in
clu
d
in
g
ac
cu
r
ac
y
,
r
ec
all,
p
r
ec
is
io
n
,
av
er
a
g
e
ac
cu
r
ac
y
,
F1
-
m
e
asu
r
e.
T
h
e
m
o
d
el
d
em
o
n
s
tr
ated
s
u
p
e
r
io
r
p
e
r
f
o
r
m
an
ce
in
av
er
a
g
e
ac
cu
r
ac
y
an
d
s
u
r
p
ass
ed
s
ev
er
al
d
etec
tio
n
m
o
d
els an
d
r
ec
u
r
r
en
t
n
eu
r
al
n
etwo
r
k
s
in
b
o
th
tr
ai
n
in
g
an
d
p
r
e
d
ictio
n
tim
es.
T
h
e
ad
v
an
tag
es
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
tem
lie
in
its
h
o
lis
tic
ap
p
r
o
ac
h
to
cr
ac
k
d
etec
tio
n
,
wh
ich
co
m
b
in
es
liv
e
o
b
s
er
v
atio
n
,
f
o
r
ec
asti
n
g
an
aly
s
is
,
m
o
d
elin
g
,
v
is
u
alizin
g
,
an
d
s
o
lu
tio
n
m
ai
n
ten
an
ce
.
T
h
is
in
teg
r
atio
n
e
n
ab
les
s
p
ec
ialis
t
s
in
m
in
in
g
s
e
cto
r
to
en
f
o
r
ce
t
h
e
r
eliab
ilit
y
,
im
p
r
o
v
e
s
u
s
tain
ab
l
e
ac
tiv
ities
,
m
o
r
eo
v
er
,
to
r
e
d
u
ce
th
e
b
o
ttlen
ec
k
s
r
elate
d
to
c
r
ac
k
s
an
d
s
tr
u
ctu
r
al
v
u
ln
er
ab
ilit
y
.
Dis
ad
v
an
ta
g
es
o
f
th
e
s
y
s
tem
m
ay
in
clu
d
e
d
if
f
icu
lty
in
s
ettin
g
u
p
an
d
th
e
n
ee
d
f
o
r
a
lar
g
e
am
o
u
n
t
o
f
d
ata
to
en
s
u
r
e
h
ig
h
ac
cu
r
ac
y
an
d
r
eliab
ilit
y
o
f
f
o
r
ec
asts
[
4
0
]
.
4.
DE
V
E
L
O
P
M
E
N
T
O
F
AI A
ND
M
L
I
N
T
H
E
M
I
NING
I
NDUST
RY
T
o
ad
v
an
ce
th
e
d
ev
el
o
p
m
en
t
an
d
ap
p
licatio
n
o
f
AI
an
d
ML
in
m
in
in
g
o
p
er
atio
n
s
,
it
is
ess
en
tial
to
id
en
tify
p
r
o
m
is
in
g
tech
n
o
lo
g
i
es
an
d
m
eth
o
d
s
.
Ma
s
ter
in
g
th
ese
tech
n
o
lo
g
ies
an
d
m
eth
o
d
s
ca
n
s
ig
n
if
ican
tly
im
p
r
o
v
e
v
a
r
io
u
s
asp
ec
ts
o
f
m
i
n
in
g
p
r
o
ce
s
s
es.
As
a
r
esu
lt,
t
h
ey
ca
n
g
r
ea
tly
e
n
h
an
ce
th
e
ef
f
icien
cy
,
s
af
ety
,
an
d
s
u
s
tain
ab
ilit
y
o
f
m
in
in
g
o
p
er
at
io
n
s
.
On
e
o
f
th
e
k
e
y
ar
ea
s
is
th
e
u
s
e
o
f
I
o
T
[
4
1
]
a
n
d
in
tellig
en
t
s
en
s
o
r
s
f
o
r
tr
ac
k
i
n
g
v
ar
i
o
u
s
p
a
r
am
eter
s
o
f
m
in
in
g
o
p
er
atio
n
s
.
Sm
ar
t
s
en
s
o
r
s
ca
n
co
llect
d
ata
o
n
v
ib
r
atio
n
s
,
tem
p
er
atu
r
e,
p
r
ess
u
r
e,
g
a
s
co
n
ten
t
an
d
o
th
er
cr
itical
in
d
icato
r
s
.
I
n
teg
r
atio
n
o
f
th
is
d
ata
with
AI
[
4
2
]
an
d
ML
s
y
s
tem
s
will
allo
w
y
o
u
to
q
u
ick
ly
an
aly
ze
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.