I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
3
7
,
No
.
3
,
Ma
r
ch
20
2
5
,
p
p
.
2
0
5
8
~
2
0
6
8
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
7
.
i
3
.
pp
205
8
-
2
0
6
8
2058
J
o
ur
na
l
ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Adv
a
ncements i
n
seis
mic da
ta co
lle
ction a
nd an
a
ly
sis
t
hro
ug
h
ma
chine learning
Su
j
a
t
a
K
ulk
a
rni
1
,
M
a
la
y
P
h
a
dk
e
1
,
Ash
wini Sa
wa
nt
2
,
Nee
l P
a
t
el
1
,
O
m
P
a
t
il
1
1
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
T
e
l
e
c
o
mm
u
n
i
c
a
t
i
o
n
E
n
g
i
n
e
e
r
i
n
g
,
S
a
r
d
a
r
P
a
t
e
l
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
,
A
n
d
h
e
r
i
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
T
e
l
e
c
o
mm
u
n
i
c
a
t
i
o
n
E
n
g
i
n
e
e
r
i
n
g
,
V
i
v
e
k
a
n
a
n
d
E
d
u
c
a
t
i
o
n
S
o
c
i
e
t
y
’
s I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
,
C
h
e
mb
u
r
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
ul
15
,
2
0
2
4
R
ev
is
ed
Oct
10
,
202
4
Acc
ep
ted
Oct
28
,
2
0
2
4
Th
e
e
v
o
lu
ti
o
n
o
f
se
ism
ic
d
a
ta
c
o
ll
e
c
ti
o
n
h
a
s
b
e
e
n
d
riv
e
n
b
y
t
h
e
n
e
e
d
f
o
r
sta
ti
o
n
s
t
o
c
a
p
t
u
re
larg
e
v
o
l
u
m
e
s
o
f
h
ig
h
-
fre
q
u
e
n
c
y
si
g
n
a
ls
c
o
n
t
in
u
o
u
sl
y
.
Th
e
se
sig
n
a
ls
ty
p
ica
ll
y
c
o
n
tai
n
b
o
t
h
se
ism
ic
a
n
d
n
o
n
-
se
ism
ic
in
fo
rm
a
ti
o
n
.
P
re
v
io
u
s
re
se
a
rc
h
c
o
n
v
e
rted
S
EE
D
d
a
ta
in
to
CS
V
fo
rm
a
t
a
n
d
u
se
d
p
rin
c
ip
a
l
c
o
m
p
o
n
e
n
t
a
n
a
ly
sis
(
P
CA
)
f
o
r
f
e
a
tu
re
e
x
trac
ti
o
n
fro
m
t
h
e
se
ism
ic
d
a
tas
e
t.
M
a
c
h
in
e
lea
rn
i
n
g
m
o
d
e
ls
we
re
t
h
e
n
e
m
p
l
o
y
e
d
,
s
h
o
wi
n
g
a
n
imp
r
o
v
e
m
e
n
t
in
id
e
n
ti
f
y
in
g
se
ism
ic
a
n
d
n
o
n
-
se
is
m
ic
e
v
e
n
ts.
Th
is
p
a
p
e
r
fo
c
u
se
s
o
n
a
p
p
ly
in
g
d
e
e
p
lea
rn
in
g
m
e
th
o
d
s,
sp
e
c
ifi
c
a
ll
y
d
e
e
p
n
e
u
ra
l
n
e
tw
o
rk
s
(DN
N)
a
n
d
a
h
y
b
rid
m
o
d
e
l
c
o
m
b
in
i
n
g
l
o
n
g
s
h
o
rt
-
term
m
e
m
o
ry
(L
S
TM
)
n
e
t
wo
rk
s
wit
h
DN
N
(LS
TM
+
DN
N).
Th
e
p
ro
p
o
se
d
d
e
e
p
lea
rn
in
g
m
o
d
e
ls
d
e
m
o
n
stra
te
a
n
o
tab
le
imp
ro
v
e
m
e
n
t
o
v
e
r
tr
a
d
it
io
n
a
l
m
a
c
h
in
e
lea
rn
in
g
t
e
c
h
n
iq
u
e
.
Ex
p
e
rime
n
tal
re
su
lt
s
sh
o
w
a
tes
t
a
c
c
u
ra
c
y
o
f
9
9
.
2
4
%
u
si
n
g
d
e
e
p
lea
rn
in
g
,
c
o
m
p
a
re
d
to
a
n
a
v
e
ra
g
e
o
f
9
7
.
8
0
%
a
c
h
iev
e
d
wit
h
m
a
c
h
in
e
lea
rn
in
g
m
o
d
e
ls,
in
d
ica
ti
n
g
a
1
.
4
6
%
e
n
h
a
n
c
e
m
e
n
t
in
d
e
tec
ti
o
n
a
c
c
u
ra
c
y
.
Th
is
u
n
d
e
r
sc
o
re
s
th
e
p
o
ten
ti
a
l
o
f
d
e
e
p
lea
rn
i
n
g
in
a
c
c
u
ra
tely
d
e
tec
ti
n
g
se
ism
ic
e
v
e
n
ts
in
re
a
l
-
ti
m
e
m
o
n
it
o
r
in
g
sy
ste
m
s.
K
ey
w
o
r
d
s
:
Dee
p
lear
n
in
g
E
ar
th
q
u
a
k
e
d
etec
tio
n
Featu
r
e
ex
tr
ac
tio
n
L
o
n
g
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
R
ea
l tim
e
d
ataset
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
:
Su
jata
Ku
lk
ar
n
i
Dep
ar
tm
en
t o
f
E
lectr
o
n
ics an
d
T
elec
o
m
m
u
n
icatio
n
E
n
g
in
ee
r
in
g
,
Sar
d
ar
Patel
I
n
s
titu
te
o
f
T
ec
h
n
o
lo
g
y
An
d
h
er
i
,
I
n
d
ia
E
m
ail:
s
u
jata_
k
u
lk
ar
n
i@
s
p
it.a
c.
in
1.
I
NT
RO
D
UCT
I
O
N
E
ar
ly
d
etec
tio
n
o
f
ea
r
th
q
u
ak
e
s
is
e
s
s
en
tial
f
o
r
r
ed
u
cin
g
d
a
m
ag
e
an
d
s
av
in
g
liv
es
[
1
]
.
E
ar
th
q
u
ak
e
s
ar
e
ty
p
ically
ca
u
s
ed
b
y
p
late
tecto
n
ics
an
d
th
e
s
u
d
d
e
n
r
ele
ase
o
f
elastic
en
er
g
y
s
to
r
ed
i
n
g
eo
lo
g
ical
f
a
u
lts
,
r
esu
ltin
g
in
th
e
s
h
ak
in
g
o
f
th
e
E
ar
th
'
s
s
u
r
f
ac
e.
T
h
is
en
er
g
y
r
elea
s
e
g
en
er
ates
s
eismic
wav
es,
an
d
th
e
m
ag
n
itu
d
e
o
f
an
ea
r
th
q
u
ak
e
is
p
r
o
p
o
r
tio
n
al
to
th
e
lo
g
ar
ith
m
o
f
th
e
en
er
g
y
r
elea
s
ed
.
T
ec
h
n
o
lo
g
ical
d
ev
elo
p
m
e
n
ts
h
av
e
g
r
ea
tly
in
cr
ea
s
ed
th
e
k
n
o
wled
g
e
o
f
th
e
in
ter
io
r
s
tr
u
ctu
r
e
an
d
d
y
n
am
ic
p
r
o
ce
s
s
es
o
f
th
e
E
ar
th
.
On
e
e
x
am
p
le
is
th
e
b
e
tter
r
ec
o
r
d
i
n
g
o
f
s
eismic
wav
es
u
s
in
g
s
en
s
itiv
e
s
en
s
o
r
s
s
u
ch
as
s
eismo
g
r
ap
h
s
.
T
h
ese
d
ev
elo
p
m
en
ts
ar
e
ess
en
tial
to
in
cr
ea
s
in
g
th
e
ca
p
ac
ity
to
an
ticip
ate
an
d
less
en
th
e
ef
f
ec
ts
o
f
ea
r
th
q
u
ak
es,
wh
ic
h
ar
e
am
o
n
g
th
e
m
o
s
t [
2
]
.
Ma
n
ag
in
g
th
e
lar
g
e
v
o
lu
m
es
o
f
d
ata
g
en
er
ated
b
y
s
eismic
s
tatio
n
s
,
wh
ich
co
n
tin
u
ally
r
ec
o
r
d
s
ig
n
als
at
h
ig
h
s
am
p
le
f
r
eq
u
en
cies
,
is
ch
allen
g
in
g
b
u
t
cr
u
cial
f
o
r
u
n
d
er
s
tan
d
in
g
s
eismi
c
ac
tiv
ity
.
Seis
m
o
g
r
ap
h
s
,
d
er
iv
ed
f
r
o
m
g
r
o
u
n
d
m
o
ti
o
n
d
ata
r
ec
o
r
d
ed
b
y
ac
ce
le
r
o
g
r
a
p
h
s
,
ar
e
u
s
ed
b
y
r
esear
c
h
er
s
an
d
s
eismo
lo
g
is
ts
to
d
eter
m
in
e
k
ey
p
ar
am
eter
s
s
u
c
h
as
wav
elen
g
th
,
f
r
e
q
u
en
c
y
,
m
ag
n
itu
d
e,
a
n
d
tim
in
g
o
f
s
eismic
s
ig
n
als
[
3
]
,
[
4
]
.
I
d
en
tify
in
g
th
e
p
r
im
ar
y
(
P
-
wav
e)
an
d
s
ec
o
n
d
ar
y
(
S
-
wav
e)
w
av
es
in
th
ese
s
ig
n
als
is
cr
u
cial
as
th
ey
f
r
eq
u
en
tly
co
n
tain
b
o
th
s
eismic
an
d
n
o
n
-
s
eismic
d
ata
as
s
h
o
wn
in
Fig
u
r
e
1
.
S
-
wav
es
f
o
llo
w
P
-
wav
es
d
u
r
in
g
an
ea
r
th
q
u
ak
e
,
wh
ich
ar
e
th
e
f
astes
t
s
e
is
m
ic
wav
e
s
b
u
t
ar
e
h
ar
d
to
d
ete
ct
b
ec
au
s
e
o
f
th
eir
lo
w
f
r
eq
u
en
c
y
[
5
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
d
va
n
ce
men
ts
in
s
eismic d
a
ta
co
llectio
n
a
n
d
a
n
a
lysi
s
th
r
o
u
g
h
…
(
S
u
ja
t
a
K
u
lka
r
n
i
)
2059
Fu
r
th
er
m
o
r
e
,
as
illu
s
tr
ated
i
n
Fig
u
r
e
2
,
th
r
ee
-
co
m
p
o
n
en
t
s
eismo
g
r
am
d
ata
th
at
r
ec
o
r
d
g
r
o
u
n
d
m
o
tio
n
in
v
er
tical,
n
o
r
th
-
s
o
u
th
,
an
d
ea
s
t
-
west
d
ir
ec
tio
n
s
,
alo
n
g
with
i
n
f
o
r
m
atio
n
f
r
o
m
L
o
v
e
a
n
d
R
ay
leig
h
wav
es
[
6
]
,
o
f
f
er
a
f
u
ll
p
ictu
r
e
o
f
s
eismic
o
cc
u
r
r
e
n
ce
s
.
T
h
e
u
n
d
er
s
tan
d
i
n
g
o
f
s
eismic
ac
tiv
ity
an
d
t
h
e
ca
p
ac
ity
to
id
en
tify
an
d
r
esp
o
n
d
to
e
ar
th
q
u
ak
es will b
o
th
b
e
n
ef
it f
r
o
m
th
is
th
o
r
o
u
g
h
ex
am
in
atio
n
.
Fig
u
r
e
1
.
E
a
r
th
q
u
a
k
e
with
P
-
wav
e
an
d
S
-
wav
e
ar
r
iv
als [
7
]
Fig
u
r
e
2
.
T
h
r
ee
-
c
o
m
p
o
n
en
t se
is
m
o
g
r
am
r
ec
o
r
d
s
g
r
o
u
n
d
m
o
tio
n
in
t
h
r
ee
p
e
r
p
en
d
icu
lar
d
ir
ec
tio
n
s
T
h
e
m
an
ag
e
m
en
t
o
f
d
iv
er
s
e
a
n
d
en
o
r
m
o
u
s
am
o
u
n
ts
o
f
s
eismic
d
ata
h
as
b
ee
n
g
r
ea
tly
im
p
r
o
v
e
d
b
y
th
e
d
ev
el
o
p
m
en
t
o
f
im
p
r
o
v
e
d
s
eismic
d
ata
co
llectio
n
tec
h
n
i
q
u
es.
W
ith
th
ese
m
et
h
o
d
s
,
th
e
r
e
is
n
o
lo
n
g
er
an
y
n
ee
d
f
o
r
c
o
n
tin
u
o
u
s
s
to
r
in
g
an
d
m
o
r
e
e
f
f
ec
tiv
e
d
ata
p
r
o
ce
s
s
in
g
b
ec
au
s
e
ea
ch
s
eismi
c
s
ig
n
al
is
h
an
d
led
in
d
ep
en
d
en
tly
.
I
n
o
r
d
er
to
p
r
o
v
id
e
a
co
m
p
lete
d
ataset
with
tr
u
s
two
r
th
y
ch
ar
ac
ter
is
tics
lik
e
f
r
eq
u
en
cy
,
am
p
litu
d
e,
a
n
d
d
u
r
atio
n
,
s
eismic
ev
en
ts
ar
e
u
s
u
ally
d
etec
ted
at
ea
ch
s
tatio
n
u
s
in
g
en
er
g
y
d
etec
to
r
s
.
T
h
e
r
aw
d
ata
is
th
en
tr
an
s
lated
in
to
C
SV
f
o
r
m
at
[
8
]
.
T
o
f
u
r
t
h
er
o
p
tim
ize
p
er
f
o
r
m
an
ce
,
d
im
en
s
io
n
ality
r
ed
u
ctio
n
tech
n
iq
u
es
ar
e
ap
p
lied
,
lead
i
n
g
to
b
etter
co
m
p
u
tin
g
e
f
f
i
c
ien
cy
.
Mo
d
els
s
u
ch
as
lo
g
is
tic
r
eg
r
ess
io
n
an
d
d
ec
is
io
n
tr
ee
s
h
av
e
s
h
o
wn
p
r
o
m
is
in
g
r
esu
lts
,
as
in
d
icate
d
b
y
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
s
co
r
es.
Pra
ctica
l
ap
p
licatio
n
s
o
f
th
ese
m
eth
o
d
s
[
9
]
h
a
v
e
b
ee
n
d
em
o
n
s
tr
ated
w
ith
d
ata
f
r
o
m
s
in
g
le
s
en
s
o
r
s
an
d
s
en
s
o
r
n
etwo
r
k
s
n
ea
r
B
asav
ak
aly
an
,
Kar
n
atak
a,
y
ield
in
g
lo
wer
f
alse
alar
m
r
ates
an
d
h
ig
h
lig
h
tin
g
th
eir
ef
f
ec
tiv
en
ess
in
r
ea
l
-
wo
r
ld
s
ce
n
ar
io
s
.
Dee
p
n
eu
r
al
n
etwo
r
k
s
(
DNNs)
ar
e
a
v
ital
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
e
with
s
ig
n
if
ican
t
a
p
p
licatio
n
s
in
v
ar
io
u
s
in
d
u
s
tr
ies
[
1
0
]
,
i
n
c
lu
d
in
g
s
eismo
lo
g
y
.
Dee
p
lear
n
in
g
d
etec
ts
s
ig
n
if
ican
t
ch
ar
ac
ter
is
tics
f
r
o
m
u
n
lab
eled
d
ata
m
o
r
e
s
u
cc
ess
f
u
lly
th
an
o
th
er
m
ac
h
in
e
lear
n
i
n
g
tech
n
iq
u
es
b
y
wo
r
k
in
g
d
ir
ec
tly
with
r
aw
d
ata
with
o
u
t
th
e
r
eq
u
ir
em
en
t
f
o
r
p
r
ep
ar
atio
n
.
DNNs
h
av
e
b
ee
n
s
u
g
g
ested
in
s
eismo
l
o
g
y
f
o
r
ap
p
licatio
n
s
in
clu
d
in
g
lith
o
lo
g
y
p
r
ed
ictio
n
,
s
eismic
d
ata
in
v
er
s
io
n
,
an
d
ea
r
th
q
u
ak
e
d
etec
tio
n
[
1
1
]
.
T
h
e
in
te
g
r
atio
n
o
f
m
ac
h
in
e
lear
n
in
g
in
t
o
ea
r
th
q
u
ak
e
s
eism
o
lo
g
y
h
as
ex
ten
d
e
d
to
a
r
ea
s
lik
e
g
r
o
u
n
d
m
o
tio
n
p
r
e
d
ictio
n
,
s
eismic
ity
an
aly
s
is
,
ea
r
th
q
u
ak
e
ca
talo
g
d
e
v
elo
p
m
en
t,
an
d
a
n
aly
zin
g
g
eo
d
etic
d
ata
r
elate
d
to
cr
u
s
tal
d
ef
o
r
m
atio
n
[
1
2
]
.
Ma
jo
r
s
tu
d
ies
h
av
e
h
ig
h
lig
h
ted
th
e
p
o
ten
tial
o
f
m
ac
h
in
e
lear
n
in
g
t
o
ad
v
a
n
ce
s
eismic
r
esear
ch
,
p
ar
ticu
lar
ly
th
r
o
u
g
h
clu
s
ter
in
g
an
aly
s
is
an
d
d
etec
tin
g
tecto
n
ic
s
ig
n
als
in
g
eo
d
etic
d
ata.
T
h
ese
ad
v
an
ce
m
en
ts
d
em
o
n
s
tr
ate
th
e
g
r
o
win
g
im
p
o
r
ta
n
ce
o
f
DNNs
in
en
h
an
ci
n
g
th
e
k
n
o
wled
g
e
a
n
d
p
r
e
d
ictio
n
o
f
s
eismic
ev
en
t
s
.
T
h
e
STA/L
T
A
m
eth
o
d
[
1
3
]
,
co
m
m
o
n
ly
u
s
ed
f
o
r
m
o
n
ito
r
in
g
en
er
g
y
r
atio
s
in
s
eismi
c
d
ata,
is
ef
f
ec
tiv
e
b
u
t
h
as
lim
itatio
n
s
i
n
p
r
ec
is
io
n
an
d
ca
n
b
e
s
u
s
ce
p
tib
le
to
in
ter
f
er
en
ce
,
p
ar
ticu
lar
ly
in
p
r
ed
ictin
g
s
h
ea
r
wav
e
ar
r
i
v
al
tim
es.
Fau
lt
Den
s
ity
was
d
eter
m
in
ed
u
s
in
g
Ker
n
el
Den
s
ity
E
s
tim
a
tio
n
an
d
B
iv
ar
iate
Mo
r
an
'
s
I
in
o
r
d
er
to
en
h
an
ce
ea
r
th
q
u
ak
e
d
etec
tio
n
.
I
t
was
th
en
co
m
p
ar
ed
to
o
th
er
p
a
r
am
e
ter
s
u
s
in
g
a
v
ar
iety
o
f
p
er
f
o
r
m
an
ce
cr
iter
ia,
in
clu
d
in
g
ac
cu
r
ac
y
,
s
en
s
itiv
ity
,
an
d
s
p
ec
if
icity
[
1
4
]
.
W
h
en
co
m
b
i
n
ed
with
SVM
an
d
DNN
m
o
d
els,
th
is
p
ar
am
eter
p
er
f
o
r
m
ed
v
er
y
well
f
o
r
ea
r
th
q
u
ak
es
with
a
h
ig
h
m
ag
n
itu
d
e.
Ad
d
itio
n
ally
,
th
e
ea
r
th
q
u
ak
e
s
itu
atio
n
lear
n
i
n
g
s
y
s
tem
(
E
SLS)
,
a
clo
u
d
-
b
ased
s
er
v
er
u
s
in
g
YOL
O
f
o
r
o
b
j
ec
t
d
etec
tio
n
[
1
5
]
,
ac
h
iev
ed
an
av
er
ag
e
s
er
v
ice
ti
m
e
o
f
0
.
8
s
ec
o
n
d
s
an
d
a
9
6
%
ac
cu
r
ac
y
in
i
d
en
tify
in
g
h
az
a
r
d
o
u
s
item
s
.
R
ec
u
r
r
en
t
n
e
u
r
al
n
etwo
r
k
(
R
NN)
u
n
its
,
wh
ich
ca
p
t
u
r
e
t
h
e
in
tr
in
s
i
c
tem
p
o
r
al
p
r
o
p
er
ties
o
f
s
eismic
d
ata,
ar
e
em
p
lo
y
e
d
in
th
is
s
tu
d
y
[
1
]
to
c
o
n
s
tr
u
ct
an
ef
f
icien
t
d
ee
p
n
eu
r
al
n
etwo
r
k
-
b
ased
e
ar
th
q
u
ak
e
d
etec
to
r
an
d
p
r
e
d
icto
r
.
L
ik
e
ANN
m
o
d
els,
th
e
L
STM
m
o
d
el
p
er
f
o
r
m
s
well
f
o
r
s
m
all
to
m
ed
iu
m
-
s
ized
ea
r
th
q
u
ak
es
b
u
t
h
as
tr
o
u
b
le
with
lar
g
e
-
s
ca
le
o
cc
u
r
r
e
n
ce
s
.
T
wo
h
y
b
r
i
d
m
a
ch
in
e
lear
n
in
g
m
o
d
els
(
FP
A
-
E
L
M
an
d
FP
A
-
LS
-
SVM)
wer
e
p
r
esen
ted
[
1
6
]
to
im
p
r
o
v
e
p
r
ed
ictio
n
ac
cu
r
ac
y
;
th
e
latter
m
o
d
el
d
em
o
n
s
tr
ated
s
u
p
er
io
r
ac
c
u
r
ac
y
in
p
r
ed
ictin
g
ea
r
th
q
u
ak
e
m
ag
n
itu
d
es
o
v
er
a
f
if
teen
-
d
ay
p
e
r
i
o
d
.
T
h
e
r
esear
ch
also
ex
am
i
n
es
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
s
u
ch
as
SVM
an
d
R
an
d
o
m
Fo
r
est
[
1
7
]
,
p
o
in
tin
g
o
u
t
th
at
th
e
ANN
ap
p
r
o
ac
h
h
ad
th
e
b
est
p
r
ed
ictio
n
ac
cu
r
ac
y
o
f
9
6
.
2
7
%
[
1
8
]
.
Pre
d
ictio
n
ac
c
u
r
ac
y
was
f
u
r
th
er
in
cr
ea
s
ed
b
y
u
s
i
n
g
lo
n
g
s
h
o
r
t
-
ter
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
3
,
Ma
r
ch
20
2
5
:
2
0
5
8
-
2
0
6
8
2060
m
em
o
r
y
(
L
STM
)
n
e
two
r
k
s
to
co
m
p
r
eh
e
n
d
th
e
s
p
atio
tem
p
o
r
al
r
elatio
n
s
h
ip
s
b
etwe
en
ea
r
th
q
u
ak
es,
p
ar
ticu
lar
l
y
wh
en
u
tili
zin
g
two
-
d
im
e
n
s
io
n
al
in
f
o
r
m
atio
n
[
1
9
]
.
I
n
ad
d
itio
n
,
a
tech
n
iq
u
e
k
n
o
wn
as
PR
-
KNN
was
p
r
esen
ted
[
2
0
]
to
ef
f
icien
tly
p
r
ed
ict
af
ter
s
h
o
ck
s
with
m
ag
n
itu
d
es
o
f
4
.
0
o
r
ab
o
v
e
b
y
f
u
s
in
g
Po
ly
n
o
m
ial
R
eg
r
ess
io
n
an
d
K
-
NN
m
o
d
els.
L
o
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
n
etwo
r
k
s
we
r
e
d
e
v
elo
p
ed
to
o
v
e
r
co
m
e
th
e
s
h
o
r
tco
m
in
g
s
o
f
R
NNs.
T
h
ese
n
etwo
r
k
s
h
av
e
m
em
o
r
y
ce
lls
with
in
p
u
t,
f
o
r
g
et,
an
d
o
u
tp
u
t
g
ates
th
at
aid
in
th
e
m
an
ag
em
en
t
o
f
lo
n
g
-
t
er
m
d
ep
en
d
en
cies [
2
1
]
.
Pre
v
io
u
s
r
esear
ch
in
to
ca
teg
o
r
izin
g
s
eismic
ev
en
ts
h
as
e
n
co
u
n
ter
e
d
m
u
ltip
le
r
estrictio
n
s
.
So
m
e
p
eo
p
le
d
ep
en
d
ed
o
n
h
an
d
cr
af
ted
f
ea
tu
r
e
s
ets,
p
o
s
s
ib
ly
o
v
er
lo
o
k
in
g
cr
u
cial
s
eismic
s
ig
n
al
tr
aits
[
2
2
]
.
C
o
n
v
en
tio
n
al
m
ac
h
i
n
e
lear
n
i
n
g
tech
n
i
q
u
es
lik
e
SVM
o
r
d
ec
is
io
n
tr
ee
s
h
ad
d
if
f
icu
lty
ca
p
tu
r
in
g
th
e
tim
e
-
r
elate
d
f
ea
tu
r
es
o
f
s
eismic
s
ig
n
als,
r
esu
ltin
g
in
o
m
itti
n
g
im
p
o
r
tan
t
tem
p
o
r
al
d
ata
[
2
3
]
.
Mo
r
eo
v
er
,
h
ig
h
-
d
im
en
s
io
n
al
d
atasets
f
r
eq
u
en
t
ly
led
to
o
v
er
f
itti
n
g
,
d
ec
r
ea
s
in
g
th
e
ab
ilit
y
to
g
en
er
al
ize
[
2
4
]
.
C
er
tain
s
tu
d
ies
s
tr
o
n
g
ly
em
p
h
asized
p
r
ec
is
io
n
as
a
m
ea
s
u
r
e
o
f
p
er
f
o
r
m
an
ce
,
wh
ich
m
ay
b
e
d
ec
ep
tiv
e
in
d
atasets
th
at
ar
e
n
o
t
ev
en
ly
d
is
tr
ib
u
te
d
[
2
5
]
.
T
h
e
p
r
o
p
o
s
ed
a
p
p
r
o
ac
h
is
u
s
ed
p
r
in
cip
al
c
o
m
p
o
n
en
t
a
n
aly
s
is
(
P
C
A)
to
r
ed
u
ce
d
im
en
s
io
n
ality
an
d
p
r
ev
en
t
o
v
er
f
itti
n
g
wh
ile
r
et
ain
in
g
ess
en
tial
s
ei
s
m
ic
f
ea
tu
r
es.
Var
io
u
s
m
ac
h
in
e
lear
n
in
g
m
o
d
els,
in
clu
d
in
g
lo
g
is
tic
r
eg
r
ess
io
n
,
Naiv
e
B
ay
es,
SVM,
d
ec
is
io
n
t
r
ee
s
,
an
d
r
an
d
o
m
f
o
r
ests
,
wer
e
ass
ess
ed
,
alo
n
g
with
d
ee
p
lear
n
in
g
m
o
d
els
lik
e
f
ee
d
-
f
o
r
war
d
n
eu
r
al
n
etwo
r
k
s
an
d
L
S
T
M.
L
STM
n
etwo
r
k
s
wer
e
p
a
r
ticu
lar
ly
ef
f
ec
tiv
e
in
ca
p
tu
r
in
g
tem
p
o
r
al
s
eismic
p
atter
n
s
.
E
v
alu
atio
n
m
etr
ics
s
u
ch
as
p
r
ec
is
io
n
,
r
ec
all,
F1
-
s
co
r
e,
an
d
R
O
C
AUC
wer
e
u
s
ed
,
wh
ile
cr
o
s
s
-
v
alid
a
tio
n
,
ea
r
ly
s
to
p
p
i
n
g
,
an
d
lear
n
in
g
r
ate
ad
ju
s
tm
en
ts
wer
e
e
m
p
lo
y
ed
t
o
im
p
r
o
v
e
g
en
er
aliza
tio
n
.
Sectio
n
2
c
o
v
e
r
s
th
e
m
et
h
o
d
o
lo
g
y
an
d
PC
A,
Sectio
n
3
d
etails
m
o
d
el
ev
al
u
atio
n
,
a
n
d
Sectio
n
s
4
–
6
p
r
esen
t th
e
co
n
clu
s
io
n
,
r
e
f
er
en
ce
s
,
an
d
ac
k
n
o
wled
g
m
en
ts
.
2.
M
E
T
H
O
D
2
.
1
.
Da
t
a
s
et
o
utline
T
h
e
d
ata
is
m
eticu
lo
u
s
ly
co
ll
ec
ted
f
r
o
m
t
h
e
s
ch
o
o
l
o
f
ea
r
t
h
s
cien
ce
s
at
Swam
i
R
am
an
an
d
T
ee
r
th
Ma
r
ath
wad
a
Un
iv
e
r
s
ity
in
Na
n
d
ed
,
Ma
h
ar
ash
tr
a,
I
n
d
ia,
as
well
as
f
r
o
m
d
if
f
er
e
n
t
s
tatio
n
s
s
u
ch
as
B
VSK
an
d
CU
KG.
T
h
is
ex
p
er
im
en
tal
d
ata
co
m
es
f
r
o
m
wid
e
b
an
d
s
eismic
s
ig
n
als
co
llected
b
y
T
r
illi
u
m
1
2
0
QA
b
r
o
ad
b
an
d
s
eismo
lo
g
ical
s
en
s
o
r
s
s
tr
ateg
ically
p
lace
d
clo
s
e
to
B
asav
ak
aly
a
n
a
n
d
t
h
e
ce
n
tr
al
Un
iv
er
s
ity
o
f
Kar
n
atak
a.
T
h
ese
ad
v
an
ce
d
s
en
s
o
r
s
ca
n
o
p
er
ate
e
f
f
icien
tly
at
a
f
r
eq
u
e
n
cy
o
f
1
0
0
s
am
p
l
es
p
er
s
ec
o
n
d
,
an
d
p
o
s
s
ess
a
r
em
ar
k
a
b
le
r
esp
o
n
s
iv
en
ess
o
f
2
0
0
0
V/m
/s
.
E
v
er
y
s
en
s
o
r
f
o
llo
ws
a
s
tan
d
a
r
d
ized
r
ec
o
r
d
in
g
cy
cle
th
at
last
s
f
o
r
2
m
in
u
tes.
T
h
e
d
ataset
s
p
an
s
a
co
m
p
r
eh
e
n
s
iv
e
f
iv
e
-
h
o
u
r
p
er
io
d
o
n
Octo
b
er
1
2
,
2
0
2
1
,
m
eticu
lo
u
s
l
y
s
eg
m
en
te
d
in
to
o
n
e
-
h
o
u
r
in
ter
v
als
an
d
s
am
p
led
at
a
r
ate
o
f
1
0
0
Hz.
Ad
d
itio
n
ally
,
a
co
n
tr
asti
n
g
n
o
n
-
s
eismic
o
r
n
o
is
e
s
ig
n
al
was
r
ec
o
r
d
ed
f
r
o
m
0
:0
0
to
4
:5
9
:5
9
o
n
J
u
ly
9
,
2
0
2
1
,
as
v
iv
id
l
y
illu
s
tr
ated
in
Fig
u
r
e
3
an
d
Fig
u
r
e
4
.
T
h
e
u
n
iq
u
e
ch
ar
ac
ter
is
tics
o
f
s
ig
n
als
r
ec
o
r
d
ed
at
ea
ch
s
tatio
n
ar
e
m
eth
o
d
ically
an
aly
ze
d
to
en
r
ich
t
h
e
d
ataset,
f
ac
ilit
atin
g
r
o
b
u
s
t a
n
o
m
aly
d
etec
tio
n
an
d
p
r
ec
is
e
id
en
tific
ati
o
n
o
f
s
eismic
ev
en
ts
.
Fig
u
r
e
3
.
Data
s
et
f
r
o
m
B
SVK
&
am
p
; CUKG
s
en
s
o
r
n
etwo
r
k
b
ef
o
r
e
ea
r
th
q
u
ak
e
d
ate
d
1
2
-
10
-
20
21
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
d
va
n
ce
men
ts
in
s
eismic d
a
ta
co
llectio
n
a
n
d
a
n
a
lysi
s
th
r
o
u
g
h
…
(
S
u
ja
t
a
K
u
lka
r
n
i
)
2061
Fig
u
r
e
4
.
Data
s
et
f
r
o
m
B
SVK
&
am
p
; CUKG
s
en
s
o
r
n
etwo
r
k
o
f
ea
r
th
q
u
ak
e
d
ated
1
2
-
10
-
2
0
2
1
Of
p
ar
ticu
lar
n
o
te
a
r
e
two
s
ig
n
if
ican
t
s
eismic
o
cc
u
r
r
e
n
ce
s
r
ec
o
r
d
ed
b
y
th
e
in
s
titu
te:
an
e
ar
th
q
u
ak
e
m
ea
s
u
r
in
g
3
.
6
m
a
g
n
itu
d
e
at
2
:3
6
a.
m
.
an
d
an
o
t
h
er
m
e
asu
r
in
g
2
.
8
m
ag
n
itu
d
e
at
2
:4
7
a.
m
.
,
d
etailed
co
m
p
r
eh
e
n
s
iv
ely
in
T
ab
le
1
.
T
h
is
d
ataset
n
o
t
o
n
ly
en
h
a
n
c
es
o
u
r
u
n
d
e
r
s
tan
d
in
g
o
f
s
eismic
ac
tiv
ity
b
u
t
also
s
er
v
es
as
a
v
alu
ab
le
r
eso
u
r
ce
f
o
r
ad
v
a
n
cin
g
s
eismic
r
esear
ch
an
d
m
o
n
ito
r
in
g
ca
p
ab
ilit
ie
s
.
Hy
b
r
id
d
atase
t
-
R
an
d
o
m
s
elec
tio
n
s
o
f
th
e
d
ata
p
o
in
ts
a
r
e
m
a
d
e
f
r
o
m
th
e
p
r
o
p
o
s
ed
d
ataset
t
o
cr
ea
te
th
e
h
y
b
r
id
d
ataset,
wh
ich
in
clu
d
es
d
ata
f
r
o
m
v
ar
io
u
s
s
en
s
o
r
s
s
u
ch
as
PB
A,
SHL,
MN
C
,
an
d
KB
L
,
as
well
as
a
m
ix
tu
r
e
o
f
r
an
d
o
m
s
am
p
les.
T
ab
le
1
.
T
h
e
s
eismic
ev
en
t
s
p
ec
if
ies (
Statio
n
s
B
S
VK
an
d
C
UKG)
O
r
i
g
i
n
t
i
m
e
S
t
a
t
i
o
n
La
t
i
t
u
d
e
Lo
n
g
i
t
u
d
e
D
e
p
t
h
M
a
g
2
0
2
1
-
10
-
1
2
0
2
:
3
6
:
2
7
U
T
C
B
S
V
K
C
U
K
G
1
7
.
3
6
7
7
.
3
5
k
m
3
.
6
2
0
2
1
-
10
-
1
2
0
2
:
3
6
:
2
7
U
T
C
B
S
V
K
C
U
K
G
1
7
.
3
3
7
7
.
2
9
1
0
k
m
2
.
8
2
.
2
.
P
r
o
po
s
ed
wo
rk
f
lo
w
T
h
e
p
r
im
ar
y
o
b
jectiv
e
o
f
th
i
s
s
tu
d
y
is
to
u
tili
ze
a
cu
s
to
m
d
ataset
co
n
tain
in
g
cr
itical
f
ea
tu
r
es
f
o
r
d
if
f
er
en
tiatin
g
s
eismic
an
d
n
o
n
-
s
eismic
s
ig
n
als.
An
ef
f
ec
tiv
e
f
ea
tu
r
e
ex
tr
ac
tio
n
m
et
h
o
d
will
b
e
d
esig
n
e
d
to
r
ap
id
ly
an
d
p
r
ec
is
ely
id
en
tif
y
s
eismic
ev
en
ts
.
T
h
ese
f
ea
t
u
r
es
will
en
ab
le
th
e
cr
ea
tio
n
o
f
a
r
esil
ien
t
m
o
d
el
th
a
t
co
m
b
in
es L
STM
an
d
DNN
f
o
r
ac
cu
r
ate
s
ig
n
al
class
if
icatio
n
.
T
h
e
L
STM
will
ca
p
tu
r
e
tem
p
o
r
al
d
e
p
en
d
en
cies
in
th
e
s
ig
n
als,
wh
ile
th
e
DNN
will
r
ef
in
e
th
e
class
if
icatio
n
p
r
o
ce
s
s
.
T
h
is
h
y
b
r
id
a
p
p
r
o
ac
h
e
n
s
u
r
es
im
p
r
o
v
ed
ac
cu
r
ac
y
a
n
d
r
eliab
ilit
y
f
o
r
d
etec
tin
g
s
eismic
o
cc
u
r
r
e
n
ce
s
:
-
T
h
e
p
r
o
p
o
s
ed
wo
r
k
f
lo
w
is
illu
s
tr
ated
in
Fig
u
r
e
5
,
wh
ich
p
r
o
v
id
es
a
co
m
p
r
eh
e
n
s
iv
e
o
v
er
v
iew
o
f
th
e
m
eth
o
d
o
l
o
g
y
f
o
r
id
en
tify
i
n
g
s
eismic
ev
en
ts
.
T
h
e
f
ig
u
r
e
ca
p
tu
r
es
th
e
m
ajo
r
s
tag
es
o
f
th
e
wo
r
k
f
lo
w,
s
tar
tin
g
f
r
o
m
d
ata
co
llectio
n
,
p
r
ep
r
o
ce
s
s
in
g
,
f
ea
tu
r
e
ex
tr
ac
tio
n
,
m
o
d
el
im
p
lem
e
n
tatio
n
,
an
d
co
n
clu
d
in
g
with
m
o
d
el
ev
alu
atio
n
.
I
t
em
p
h
asizes
th
e
s
eq
u
en
tial
f
lo
w
o
f
p
r
o
ce
s
s
es
n
ee
d
ed
to
d
ev
elo
p
a
n
o
p
tim
al
d
ee
p
lear
n
in
g
m
o
d
el
f
o
r
d
is
tin
g
u
is
h
in
g
s
eismic
f
r
o
m
n
o
n
-
s
eismic
s
i
g
n
als.
-
F
ig
u
r
e
5
(
a)
p
r
esen
ts
th
e
b
lo
ck
d
iag
r
a
m
,
o
u
tlin
in
g
th
e
m
ajo
r
s
tep
s
:
d
ata
co
llectio
n
,
p
r
ep
r
o
ce
s
s
in
g
,
s
licin
g
an
d
cr
ea
tin
g
th
e
d
ataset,
f
ea
t
u
r
e
ex
tr
ac
ti
o
n
,
m
o
d
el
im
p
le
m
en
tatio
n
u
s
in
g
DNN
o
r
L
S
T
M+
DNN,
an
d
m
o
d
el
e
v
alu
atio
n
b
ased
o
n
m
etr
ics
lik
e
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
a
n
d
F1
s
co
r
e
.
T
h
is
d
iag
r
am
g
iv
es
a
h
ig
h
-
lev
el
v
iew
o
f
th
e
s
y
s
tem
's wo
r
k
f
lo
w.
-
F
ig
u
r
e
5
(
b
)
p
r
o
v
id
es
th
e
d
eta
iled
f
lo
w
g
r
ap
h
f
o
r
f
ea
tu
r
e
e
x
tr
ac
tio
n
an
d
m
o
d
el
tr
ai
n
in
g
.
I
t
ex
p
lain
s
h
o
w
r
aw
s
ig
n
als
ar
e
c
o
n
v
e
r
ted
i
n
to
C
SV
f
o
r
m
at,
f
ea
t
u
r
es
a
r
e
ex
t
r
ac
ted
in
t
h
e
tim
e
an
d
f
r
e
q
u
en
c
y
d
o
m
ain
s
,
an
d
d
im
en
s
io
n
ality
r
ed
u
ctio
n
tech
n
iq
u
es lik
e
PC
A
ar
e
ap
p
lied
.
T
h
e
r
ed
u
c
ed
f
ea
tu
r
e
s
et
is
th
en
u
s
ed
to
tr
ain
th
e
DNN
an
d
L
STM
+D
NN
m
o
d
els,
en
s
u
r
in
g
im
p
r
o
v
ed
ef
f
icie
n
cy
an
d
ac
cu
r
ac
y
.
T
o
g
eth
er
,
th
ese
s
u
b
-
fi
g
u
r
es
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
3
,
Ma
r
ch
20
2
5
:
2
0
5
8
-
2
0
6
8
2062
g
iv
e
a
co
m
p
lete
r
ep
r
esen
tatio
n
o
f
th
e
p
r
o
p
o
s
ed
wo
r
k
f
lo
w.
-
Ou
tp
u
t:
Op
tim
al
d
ee
p
lear
n
in
g
m
o
d
el
f
o
r
id
e
n
tify
in
g
r
ea
l
o
cc
u
r
r
e
n
ce
s
,
an
d
d
etec
tio
n
o
f
s
eismic
ev
en
ts
.
T
h
e
s
eismic
s
ig
n
als
ar
e
d
iv
id
e
d
in
to
1
5
-
s
ec
o
n
d
in
ter
v
als
an
d
ar
r
an
g
ed
in
a
s
tr
u
ctu
r
e
d
ta
b
le
o
r
C
SV
f
o
r
m
at
to
cr
ea
te
a
d
ataset.
T
h
is
d
at
a
co
llectio
n
r
ec
o
r
d
s
im
p
o
r
ta
n
t
d
etails
f
r
o
m
s
eismic
s
ig
n
als,
s
p
ec
if
ically
em
p
h
asizin
g
o
n
am
p
litu
d
e
an
d
f
r
eq
u
e
n
cy
.
(
a)
(
b
)
Fig
u
r
e
5
.
Deta
ils
ab
o
u
t
p
r
o
p
o
s
ed
wo
r
k
(
a)
b
l
o
ck
d
ia
g
r
am
a
n
d
(
b
)
f
lo
w
g
r
a
p
h
T
h
e
ch
ar
ac
ter
is
tics
ar
e
ex
am
in
ed
in
ter
m
s
o
f
X,
Y,
an
d
Z
co
m
p
o
n
e
n
ts
.
Dif
f
er
en
t c
o
m
p
u
tat
io
n
s
b
ased
o
n
th
e
tim
e
d
o
m
ain
,
in
clu
d
in
g
th
e
in
ter
q
u
ar
tile
r
a
n
g
e
(
I
Q
R
)
,
cu
m
u
lativ
e
ab
s
o
lu
te
v
elo
c
ity
(
C
AV)
,
an
d
th
e
n
u
m
b
er
o
f
ze
r
o
cr
o
s
s
in
g
s
(
Z
C
)
,
ar
e
estab
lis
h
ed
.
Fu
r
th
er
m
o
r
e,
s
u
g
g
ested
n
ew
ass
ess
m
en
t
f
ea
tu
r
es
in
clu
d
e
ac
tiv
atio
n
th
r
esh
o
ld
,
v
ar
ia
b
ilit
y
m
ea
s
u
r
e,
a
n
d
FF
T
s
tr
en
g
th
a
n
d
f
r
e
q
u
en
c
y
.
2
.
3
.
E
x
t
r
a
ct
io
n o
f
F
ea
t
ures
T
h
e
s
eismo
g
r
am
v
ar
iab
les
p
r
esen
t
in
th
e
d
ataset
ar
e
ap
p
lic
ab
le
f
o
r
id
en
tify
in
g
an
d
f
o
r
ec
asti
n
g
r
ea
l
ea
r
th
q
u
ak
es.
T
h
e
c
o
m
p
u
te
d
d
ataset
is
th
o
r
o
u
g
h
b
ec
au
s
e
it
in
clu
d
es
d
er
iv
ed
f
ea
tu
r
es
f
r
o
m
f
ea
tu
r
es
o
f
am
p
litu
d
e,
f
r
eq
u
en
cy
,
an
d
tim
e.
Af
ter
a
p
p
ly
in
g
p
r
ep
r
o
ce
s
s
in
g
m
eth
o
d
s
f
o
r
d
ee
p
lear
n
in
g
,
t
h
e
to
tal
n
u
m
b
e
r
o
f
f
ea
tu
r
es
was
1
7
.
T
h
e
PC
A,
a
d
im
en
s
io
n
r
e
d
u
ctio
n
tec
h
n
iq
u
e
is
u
tili
ze
d
to
s
elec
t
th
e
s
alie
n
t
f
ea
tu
r
es
f
r
o
m
th
e
d
ee
p
lear
n
in
g
m
o
d
el
b
ec
a
u
s
e
it wa
s
to
o
tim
e
-
co
n
s
u
m
in
g
to
r
u
n
a
m
o
d
el
with
s
o
m
an
y
ch
a
r
ac
ter
is
tics
.
PC
A
is
a
s
tat
is
tical
tech
n
iq
u
e
th
at
u
s
es
an
o
r
th
o
g
o
n
al
tr
an
s
f
o
r
m
atio
n
to
ch
an
g
e
a
g
r
o
u
p
o
f
co
r
r
elate
d
v
ar
iab
les in
to
a
f
r
esh
s
et
o
f
u
n
co
r
r
elate
d
v
ar
iab
les.
T
y
p
ically
,
th
e
co
u
n
t o
f
p
r
in
ci
p
al
co
m
p
o
n
en
ts
is
eq
u
al
to
o
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
d
va
n
ce
men
ts
in
s
eismic d
a
ta
co
llectio
n
a
n
d
a
n
a
lysi
s
th
r
o
u
g
h
…
(
S
u
ja
t
a
K
u
lka
r
n
i
)
2063
f
ewe
r
th
an
th
e
i
n
itial v
ar
iab
les
.
PC
A
is
u
s
ef
u
l f
o
r
r
ed
u
cin
g
th
e
d
ataset’
s
d
im
en
s
io
n
ality
wh
ile
p
r
eser
v
in
g
m
o
s
t
o
f
th
e
d
ata
’
s
v
ar
ian
ce
,
w
h
ich
i
s
im
p
o
r
tan
t f
o
r
ef
f
icien
t c
o
m
p
u
tatio
n
an
d
en
h
a
n
ce
d
m
o
d
el
p
er
f
o
r
m
a
n
ce
.
C
o
m
p
o
n
en
ts
with
h
ig
h
er
eig
e
n
v
alu
es
co
m
p
ar
e
d
to
th
e
av
er
ag
e
eig
e
n
v
alu
es
o
f
all
co
m
p
o
n
en
ts
in
th
e
an
aly
s
is
ar
e
r
ec
o
g
n
ize
d
as
th
e
m
o
s
t
cr
itical
ch
ar
ac
ter
is
tics
[
5
]
.
I
n
th
e
p
r
o
p
o
s
ed
r
esear
ch
,
PC
A
i
s
ef
f
ec
tiv
ely
u
tili
ze
d
to
g
en
er
ate
a
3
-
f
ea
tu
r
e
v
ec
to
r
f
r
o
m
th
e
d
atase
t,
d
ec
r
ea
s
in
g
th
e
co
m
p
u
tatio
n
al
b
u
r
d
en
wh
ile
m
ain
tain
in
g
v
ital
in
f
o
r
m
atio
n
.
Fig
u
r
e
6
d
is
p
lay
s
th
e
clo
s
ely
r
elate
d
ch
ar
ac
ter
is
tics
th
at
wer
e
ef
f
ec
tiv
ely
obt
ain
ed
f
r
o
m
th
e
co
m
b
in
e
d
d
ataset
o
f
1
8
,
5
4
8
s
am
p
les.
Fig
u
r
e
7
s
h
o
wca
s
es
th
e
m
ain
c
h
ar
ac
ter
is
tic
v
ec
to
r
,
wh
ich
is
th
en
in
p
u
tted
in
to
d
e
ep
lear
n
in
g
m
o
d
els f
o
r
ad
d
itio
n
al
p
r
o
ce
s
s
in
g
an
d
p
r
ed
ictio
n
p
u
r
p
o
s
es.
Fig
u
r
e
6
.
C
o
r
r
elate
d
f
ea
tu
r
es
Fig
u
r
e
7
.
E
x
tr
ac
tin
g
f
ea
tu
r
es a
n
d
an
aly
zi
n
g
th
o
s
e
u
s
in
g
d
ee
p
lear
n
in
g
m
o
d
els
2
.
4
.
M
o
del
a
rc
hite
ct
ure
2
.
4
.
1
.
DNN
m
o
del a
rc
hite
ct
u
re
A
DNN
in
ten
d
ed
f
o
r
b
in
ar
y
cl
ass
if
icatio
n
task
s
i
s
s
et
u
p
u
s
i
n
g
th
e
ar
c
h
itectu
r
e
d
ep
icted
i
n
Fig
u
r
e
8
.
T
h
is
n
etwo
r
k
co
n
s
is
ts
o
f
d
r
o
p
o
u
t
lay
er
s
to
r
e
d
u
ce
o
v
er
f
it
tin
g
an
d
s
ev
er
al
f
u
lly
lin
k
ed
(
d
en
s
e)
lay
er
s
with
R
eL
U
ac
tiv
atio
n
f
u
n
ctio
n
s
.
A
n
in
p
u
t
lay
er
,
two
h
id
d
e
n
lay
er
s
with
1
2
8
n
e
u
r
o
n
s
ea
ch
,
a
th
ir
d
h
id
d
e
n
lay
e
r
with
3
2
n
eu
r
o
n
s
,
an
d
a
f
in
al
o
u
tp
u
t
lay
er
with
a
s
ig
m
o
id
ac
tiv
atio
n
to
p
r
o
d
u
ce
b
in
a
r
y
r
esu
lts
ar
e
all
in
clu
d
ed
.
T
h
e
m
o
d
el
is
ass
em
b
led
u
s
in
g
th
e
b
in
ar
y
cr
o
s
s
-
en
tr
o
p
y
lo
s
s
f
u
n
ctio
n
a
n
d
th
e
Ad
a
m
o
p
t
i
m
izer
f
o
r
tr
ain
in
g
.
E
ar
ly
s
to
p
p
in
g
an
d
lear
n
i
n
g
r
ate
d
ec
r
ea
s
e
o
n
p
latea
u
ca
llb
a
ck
s
ar
e
u
s
ed
in
its
tr
ain
in
g
to
im
p
r
o
v
e
ef
f
icien
c
y
an
d
p
r
e
v
en
t o
v
er
f
itti
n
g
.
2
.
4
.
2
.
Co
m
bin
a
t
io
n o
f
L
ST
M
a
nd
DNN
m
o
del a
rc
hite
ct
ure
A
DNN
in
ten
d
ed
f
o
r
b
in
ar
y
cl
ass
if
icatio
n
task
s
is
s
et
u
p
u
s
i
n
g
th
e
ar
ch
itectu
r
e
d
e
p
icted
in
Fig
u
r
e
9
.
T
h
is
n
etwo
r
k
co
n
s
is
ts
o
f
d
r
o
p
o
u
t
lay
er
s
to
r
e
d
u
ce
o
v
er
f
it
tin
g
an
d
s
ev
er
al
f
u
lly
lin
k
ed
(
d
en
s
e)
lay
er
s
with
R
eL
U
ac
tiv
atio
n
f
u
n
ctio
n
s
.
A
n
in
p
u
t
lay
er
,
two
h
id
d
e
n
lay
er
s
with
1
2
8
n
e
u
r
o
n
s
ea
ch
,
a
th
ir
d
h
id
d
e
n
lay
e
r
with
3
2
n
eu
r
o
n
s
,
an
d
a
f
in
al
o
u
tp
u
t
lay
er
with
a
s
ig
m
o
id
ac
tiv
atio
n
to
p
r
o
d
u
ce
b
in
a
r
y
r
esu
lts
ar
e
all
in
clu
d
ed
.
T
h
e
m
o
d
el
is
ass
em
b
led
u
s
in
g
th
e
b
in
ar
y
cr
o
s
s
-
en
tr
o
p
y
lo
s
s
f
u
n
ctio
n
a
n
d
th
e
Ad
a
m
o
p
t
im
izer
f
o
r
tr
ain
in
g
.
E
ar
ly
s
to
p
p
in
g
an
d
lear
n
i
n
g
r
ate
d
ec
r
ea
s
e
o
n
p
latea
u
ca
llb
a
ck
s
ar
e
u
s
ed
in
its
tr
ain
in
g
to
im
p
r
o
v
e
ef
f
icien
c
y
an
d
p
r
e
v
en
t o
v
er
f
itti
n
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
3
,
Ma
r
ch
20
2
5
:
2
0
5
8
-
2
0
6
8
2064
Fig
u
r
e
8
.
Ar
c
h
itectu
r
e
o
f
th
e
DNN
Mo
d
el
Fig
u
r
e
9
.
Ar
c
h
itectu
r
e
o
f
th
e
L
STM
+D
NN
Mo
d
el
3.
RE
SU
L
T
S
AND
D
I
SCU
SS
I
O
N
T
h
e
m
o
d
el’
s
ef
f
ec
tiv
e
n
ess
is
ev
alu
ated
b
y
u
tili
zin
g
th
e
h
y
b
r
id
d
ataset
wh
ich
in
clu
d
es
b
o
th
th
e
p
r
o
p
o
s
ed
s
en
s
o
r
s
an
d
ad
d
itio
n
al
s
en
s
o
r
s
.
8
0
%
o
f
d
atasets
ar
e
allo
ca
ted
f
o
r
tr
ain
i
n
g
a
n
d
o
n
e
-
f
if
t
h
o
f
th
e
am
o
u
n
t
is
d
esig
n
ated
f
o
r
test
in
g
.
B
o
th
m
o
d
els,
DNN
an
d
L
STM
+D
NN,
ar
e
test
ed
o
n
th
e
d
ataset
th
r
o
u
g
h
ex
p
er
im
en
tatio
n
.
Fig
u
r
e
1
0
an
d
Fig
u
r
e
1
1
s
h
o
w
th
e
e
x
am
p
le
r
ec
ei
v
e
o
p
er
atio
n
.
R
ec
eiv
er
o
p
er
atin
g
ch
ar
ac
ter
is
tic
(
R
OC
)
cu
r
v
es
o
f
b
o
th
m
o
d
els
d
er
iv
ed
f
r
o
m
s
u
g
g
ested
test
d
ata.
Fig
u
r
e
1
2
an
d
Fig
u
r
e
1
3
s
h
o
w
th
e
p
r
ec
is
i
on
-
r
ec
all
cu
r
v
e
f
o
r
th
e
m
o
d
els
ac
co
r
d
in
g
to
s
u
g
g
ested
test
d
ata.
R
OC
an
aly
s
is
wa
s
u
s
ed
to
d
eter
m
in
e
th
e
tr
u
e
p
o
s
itiv
e
r
ate
co
m
p
ar
ed
to
th
e
f
alse
p
o
s
itiv
e
r
ate
f
o
r
ea
ch
m
o
d
el.
Ass
es
s
m
en
ts
o
n
th
e
s
u
g
g
ested
test
d
ataset
s
h
o
w
th
at
all
m
o
d
els p
o
r
tr
a
y
s
atis
f
ac
to
r
y
ac
cu
r
ac
y
lev
els.
T
ab
le
2
h
i
g
h
lig
h
ts
th
e
p
er
f
o
r
m
an
ce
m
etr
ics
o
f
two
m
o
d
els,
DNN
an
d
a
h
y
b
r
id
L
STM
+D
NN,
in
ter
m
s
o
f
ac
c
u
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
F1
s
co
r
e,
an
d
AUC.
T
h
e
DNN
m
o
d
el
d
em
o
n
s
tr
ates
s
u
p
er
io
r
ac
cu
r
ac
y
at
9
9
.
2
4
%,
with
a
p
r
ec
is
io
n
o
f
9
9
.
5
4
%
an
d
an
F1
s
co
r
e
o
f
9
8
.
6
9
%,
in
d
icatin
g
s
tr
o
n
g
p
r
ed
ictiv
e
ca
p
ab
ilit
ies
ac
r
o
s
s
m
u
ltip
le
m
etr
ics.
Alth
o
u
g
h
s
lig
h
tly
l
o
wer
,
t
h
e
L
ST
M+
DNN
h
y
b
r
id
ac
h
iev
es
an
ac
cu
r
ac
y
o
f
9
9
.
0
9
%,
m
ain
tain
in
g
co
m
p
etitiv
e
p
r
ec
is
io
n
(
9
9
.
0
0
%)
an
d
r
ec
all
(
9
7
.
8
5
%),
s
h
o
wca
s
in
g
its
p
o
te
n
tial
f
o
r
co
m
p
lex
p
atter
n
r
ec
o
g
n
itio
n
task
s
.
T
ab
le
3
p
r
o
v
id
es
th
e
co
n
f
u
s
io
n
m
atr
ix
f
o
r
th
e
h
y
b
r
id
d
ataset,
d
etailin
g
T
r
u
e
Po
s
itiv
es,
T
r
u
e
Neg
ativ
es,
Fals
e
Po
s
itiv
e
s
,
an
d
Fals
e
Neg
ativ
es.
T
h
ese
v
alu
es
o
f
f
er
i
n
s
ig
h
ts
in
to
th
e
m
o
d
el’
s
class
if
icatio
n
r
eliab
ilit
y
an
d
er
r
o
r
d
is
tr
ib
u
ti
o
n
,
allo
win
g
f
u
r
th
er
e
v
alu
atio
n
o
f
its
s
tr
en
g
th
s
an
d
ar
ea
s
f
o
r
im
p
r
o
v
em
en
t.
An
aly
zin
g
th
ese
m
etr
ics is
cr
u
cial
f
o
r
f
in
e
-
tu
n
in
g
th
e
m
o
d
els
an
d
u
n
d
er
s
tan
d
in
g
th
eir
p
r
ac
tical
im
p
licatio
n
s
in
r
ea
l
-
wo
r
ld
s
ce
n
ar
io
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
d
va
n
ce
men
ts
in
s
eismic d
a
ta
co
llectio
n
a
n
d
a
n
a
lysi
s
th
r
o
u
g
h
…
(
S
u
ja
t
a
K
u
lka
r
n
i
)
2065
Fig
u
r
e
1
0
.
DNN
R
OC
Fig
u
r
e
1
1
.
L
STM
R
OC
Fig
u
r
e
1
2
.
DNN
PR
C
Fig
u
r
e
1
3
.
L
STM
PR
C
T
ab
le
2
.
Per
f
o
r
m
an
ce
m
etr
ics o
f
d
if
f
e
r
en
t m
o
d
els
M
o
d
e
l
A
c
c
u
r
a
c
y
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
AUC
DNN
0
.
9
9
2
4
0
.
9
9
5
4
0
.
9
7
8
5
0
.
9
8
6
9
0
.
9
8
8
4
LSTM
+
D
N
N
0
.
9
9
0
9
0
.
9
9
0
.
9
7
8
5
0
.
9
8
4
2
0
.
9
8
7
3
T
ab
le
3
.
C
o
n
f
u
s
io
n
m
atr
ix
o
f
d
if
f
er
en
t m
o
d
els
M
o
d
e
l
TP
TN
FP
FN
DNN
2
7
3
2
1
0
9
7
5
24
LSTM
+
D
N
N
2
7
2
6
1
0
9
7
11
24
3
.
1
.
Resul
t
s
o
f
DNN
m
o
del
T
h
e
m
o
d
el’
s
ac
cu
r
ac
y
is
ap
p
r
o
x
im
ately
9
9
.
2
4
%,
m
ea
n
in
g
th
at
n
ea
r
ly
all
p
r
ed
ictio
n
s
ar
e
c
o
r
r
ec
t.
T
h
e
p
r
ec
is
io
n
is
v
er
y
h
i
g
h
at
ar
o
u
n
d
9
9
.
5
4
%,
in
d
icatin
g
th
at
alm
o
s
t
all
p
o
s
itiv
e
p
r
e
d
ictio
n
s
ar
e
ac
cu
r
ate,
with
m
in
im
al
f
alse
p
o
s
itiv
es.
T
h
e
r
ec
all
r
ate
is
ab
o
u
t
9
7
.
8
5
%,
d
e
m
o
n
s
tr
atin
g
t
h
at
th
e
m
o
d
el
e
f
f
ec
tiv
ely
r
ec
o
g
n
izes
m
o
s
t
tr
u
e
p
o
s
itiv
e
ca
s
es,
with
f
ew
f
alse
n
eg
ativ
es.
Mo
r
eo
v
e
r
,
th
e
F1
s
co
r
e,
wh
ich
s
tr
ik
es
a
b
alan
ce
b
etwe
en
r
ec
all
an
d
p
r
ec
is
io
n
,
is
ap
p
r
o
x
im
ately
9
8
.
6
7
%.
T
h
is
h
ig
h
F1
s
co
r
e
s
ig
n
if
ies
a
well
-
b
al
a
n
ce
d
p
er
f
o
r
m
an
ce
b
etwe
en
p
r
ec
is
io
n
an
d
r
ec
all
,
en
s
u
r
in
g
th
e
m
o
d
el
is
r
eli
ab
le
in
b
o
th
id
en
tify
i
n
g
p
o
s
itiv
e
in
s
tan
ce
s
an
d
m
in
im
izin
g
f
alse p
o
s
itiv
es.
3
.
2
.
Resul
t
s
o
f
co
m
bin
a
t
io
n
o
f
L
ST
M
a
n
d DN
N
m
o
del
T
h
e
co
m
p
ar
is
o
n
o
f
th
e
p
r
o
p
o
s
ed
L
STM
an
d
DNN
h
y
b
r
i
d
m
o
d
el
with
p
r
ev
io
u
s
ap
p
r
o
ac
h
es,
as
p
r
esen
ted
in
T
ab
le
4
,
h
ig
h
lig
h
ts
its
s
ig
n
if
ican
t
ad
v
an
tag
es
in
p
er
f
o
r
m
a
n
ce
m
etr
ics.
T
h
e
test
ac
cu
r
ac
y
o
f
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
In
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
3
7
,
No
.
3
,
Ma
r
ch
20
2
5
:
2
0
5
8
-
2
0
6
8
2066
p
r
o
p
o
s
ed
d
ee
p
lear
n
in
g
a
p
p
r
o
ac
h
is
9
9
.
2
4
%,
wh
ich
is
an
i
m
p
r
o
v
e
m
en
t
o
f
1
.
4
6
%
o
v
er
t
h
e
b
est
-
p
er
f
o
r
m
in
g
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
s
o
u
t
lin
ed
in
th
e
s
tu
d
y
b
y
Ku
lk
a
r
n
i
et
a
l.
[
8
]
.
T
h
eir
m
eth
o
d
s
,
wh
ich
in
clu
d
e
L
o
g
is
tic
R
eg
r
ess
io
n
(
L
R
)
,
Naiv
e
B
ay
es
(
NB
)
,
Dec
is
io
n
T
r
ee
(
DT
)
,
R
an
d
o
m
Fo
r
est
(
R
F),
an
d
Su
p
p
o
r
t
Vec
to
r
Ma
ch
in
e
(
SVM)
,
ac
h
iev
e
a
m
ax
im
u
m
ac
cu
r
ac
y
o
f
9
7
.
8
0
%.
T
h
is
im
p
r
o
v
em
e
n
t
u
n
d
er
s
co
r
es
th
e
ef
f
ec
tiv
en
ess
o
f
d
ee
p
lear
n
in
g
m
eth
o
d
s
in
h
an
d
lin
g
co
m
p
lex
d
atasets
an
d
ex
tr
ac
ti
n
g
m
ea
n
i
n
g
f
u
l
p
atter
n
s
.
Similar
ly
,
th
e
F1
s
co
r
e
o
f
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
,
at
9
8
.
6
7
%,
o
u
tp
er
f
o
r
m
s
th
e
p
r
ev
io
u
s
m
o
d
els,
wh
ich
ac
h
iev
ed
an
F1
s
co
r
e
o
f
9
6
.
0
0
%.
T
h
is
in
d
icate
s
th
at
th
e
L
STM
an
d
DNN
h
y
b
r
id
m
o
d
el
p
r
o
v
id
es
a
b
etter
b
alan
ce
b
etwe
en
p
r
ec
i
s
io
n
an
d
r
ec
all,
m
in
im
izin
g
f
alse
p
o
s
itiv
es
an
d
n
eg
ativ
es.
B
y
lev
er
ag
in
g
th
e
s
tr
en
g
th
s
o
f
b
o
th
L
STM
f
o
r
s
eq
u
en
ce
m
o
d
elin
g
an
d
DNN
f
o
r
f
ea
tu
r
e
ex
tr
ac
tio
n
,
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
d
em
o
n
s
tr
ates its
ca
p
ab
ilit
y
to
o
u
tp
er
f
o
r
m
tr
a
d
itio
n
al
m
ac
h
i
n
e
lear
n
in
g
alg
o
r
ith
m
s
.
T
ab
le
4
p
r
o
v
id
es
a
c
o
m
p
r
e
h
e
n
s
iv
e
co
m
p
ar
is
o
n
o
f
th
ese
r
es
u
lts
,
clea
r
ly
s
h
o
wca
s
in
g
th
e
b
en
ef
its
o
f
u
s
in
g
d
ee
p
le
ar
n
in
g
tech
n
iq
u
es
f
o
r
im
p
r
o
v
in
g
class
if
icatio
n
p
e
r
f
o
r
m
an
ce
.
T
h
ese
f
i
n
d
in
g
s
r
ea
f
f
ir
m
th
e
p
r
o
p
o
s
ed
m
o
d
el'
s
p
o
ten
tial
to
ac
h
iev
e
m
o
r
e
r
eliab
le
an
d
ac
cu
r
ate
p
r
ed
ictio
n
s
,
m
ak
in
g
it
a
b
etter
f
it
f
o
r
ap
p
licatio
n
s
th
at
d
em
a
n
d
h
i
g
h
p
r
ec
is
io
n
an
d
r
ec
all.
T
ab
le
4
.
C
o
m
p
a
r
is
o
n
with
p
r
e
v
io
u
s
wo
r
k
S
t
u
d
y
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
e
t
h
o
d
s
D
e
e
p
l
e
a
r
n
i
n
g
me
t
h
o
d
s
Te
st
a
c
c
u
r
a
c
y
F
1
sc
o
r
e
P
r
o
p
o
se
d
a
p
p
r
o
a
c
h
-
D
N
N
& LST
M
0
.
9
9
2
4
0
.
9
8
6
7
K
u
l
k
a
r
n
i
e
t
a
l
.
[
8
]
LR
,
N
B
,
D
T,
R
F
,
S
V
M
-
0
.
9
7
8
0
0
.
9
6
4.
CO
NCLU
SI
O
N
Dee
p
lear
n
in
g
tech
n
iq
u
es,
s
u
ch
as
DNN
an
d
L
STM
m
o
d
els,
h
av
e
p
r
o
v
en
h
ig
h
ly
ef
f
ec
tiv
e
in
an
aly
zin
g
s
eismic
s
ig
n
als
an
d
im
p
r
o
v
i
n
g
ea
r
th
q
u
ak
e
d
ete
ctio
n
ac
cu
r
ac
y
.
T
h
is
is
s
u
p
p
o
r
ted
b
y
th
eir
h
ig
h
ac
cu
r
ac
y
an
d
r
ed
u
ce
d
f
alse
alar
m
r
ates,
m
ak
in
g
t
h
em
id
ea
l
f
o
r
r
ea
l
-
tim
e
m
o
n
ito
r
i
n
g
.
T
h
ese
m
o
d
els
s
ig
n
if
ican
tly
en
h
a
n
ce
th
e
ab
ili
ty
to
d
is
tin
g
u
is
h
b
etwe
en
g
en
u
in
e
s
eismic
ev
en
ts
an
d
h
u
m
a
n
-
ca
u
s
ed
an
o
m
alies,
o
p
tim
izin
g
co
m
p
u
tatio
n
al
ef
f
icien
cy
wh
ile
en
s
u
r
in
g
r
ap
id
an
d
ac
cu
r
ate
d
etec
tio
n
.
T
h
i
s
im
p
r
o
v
em
en
t
is
cr
u
cial
f
o
r
m
o
n
ito
r
in
g
ea
r
th
q
u
ak
e
-
p
r
o
n
e
r
eg
io
n
s
.
T
h
e
r
ea
l
-
ti
m
e
ac
cu
r
ac
y
o
f
th
ese
m
o
d
els
ca
n
g
r
ea
tly
e
n
h
an
ce
ea
r
ly
war
n
in
g
s
y
s
tem
s
,
r
ed
u
c
in
g
f
alse
alar
m
s
an
d
p
r
o
v
id
i
n
g
tim
ely
d
etec
tio
n
,
wh
ic
h
s
tr
en
g
th
en
s
d
is
aster
p
r
ep
ar
e
d
n
ess
,
u
ltima
tely
s
av
in
g
liv
es
an
d
m
in
im
izin
g
in
f
r
ast
r
u
ctu
r
e
d
am
a
g
e
.
A
k
ey
lim
itatio
n
o
f
th
is
r
esear
ch
is
th
at
th
e
m
o
d
el
d
etec
ts
ea
r
th
q
u
ak
es b
ased
o
n
s
eismic
s
ig
n
a
ls
r
ath
er
th
an
p
r
ed
ictin
g
th
em
in
ad
v
an
ce
,
lack
in
g
th
e
lead
tim
e
f
o
r
p
r
ev
e
n
tiv
e
m
ea
s
u
r
es.
Ad
d
itio
n
ally
,
th
e
u
s
e
o
f
a
lim
ited
d
ataset
f
r
o
m
a
f
ew
s
eismic
s
tatio
n
s
m
ay
lim
it
th
e
m
o
d
el'
s
ap
p
licab
ilit
y
to
o
th
er
r
eg
io
n
s
with
v
ar
y
in
g
s
eismic
p
atter
n
s
.
I
n
co
r
p
o
r
atin
g
p
r
ed
ictiv
e
an
aly
s
is
co
u
ld
en
ab
le
f
u
tu
r
e
m
o
d
els
to
o
f
f
er
b
o
th
d
etec
tio
n
an
d
p
r
e
d
ictio
n
,
s
ig
n
if
ican
tl
y
en
h
an
cin
g
d
is
aster
p
r
ep
ar
e
d
n
ess
.
Utilizin
g
clo
u
d
co
m
p
u
ti
n
g
an
d
g
l
o
b
al
s
eismic
n
etwo
r
k
s
,
th
e
s
y
s
tem
co
u
ld
m
o
n
ito
r
wo
r
l
d
wid
e
s
eismic
ac
tiv
ity
an
d
s
u
p
p
o
r
t
g
l
o
b
al
ea
r
th
q
u
ak
e
d
etec
tio
n
ef
f
o
r
ts
.
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
e
C
en
tr
e
o
f
E
x
ce
llen
ce
in
Seis
m
o
lo
g
y
,
Sch
o
o
l
o
f
E
a
r
t
h
Scien
ce
s
,
SR
T
M
Un
iv
e
r
s
ity
Nan
d
ed
,
Ma
h
ar
ash
tr
a,
I
n
d
ia,
s
u
p
p
o
r
ts
th
is
r
esear
ch
.
T
h
e
au
th
o
r
also
lik
e
to
ex
p
r
ess
o
u
r
ap
p
r
ec
iatio
n
to
o
u
r
co
lleag
u
es
wh
o
s
e
k
n
o
wled
g
e
an
d
in
s
ig
h
t
s
ig
n
if
ican
tly
b
en
ef
ite
d
th
e
r
es
ea
r
ch
en
v
i
r
o
n
m
e
n
t.
RE
F
E
R
E
NC
E
S
[
1
]
G
.
S
.
M
a
n
r
a
l
a
n
d
A
.
C
h
a
u
d
h
a
r
y
,
“
P
r
e
d
i
c
t
i
o
n
o
f
e
a
r
t
h
q
u
a
k
e
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
s
,
”
i
n
4
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
n
t
e
l
l
i
g
e
n
t
En
g
i
n
e
e
ri
n
g
a
n
d
Ma
n
a
g
e
m
e
n
t
,
I
C
I
E
M
2
0
2
3
,
I
E
E
E,
M
a
y
2
0
2
3
,
p
p
.
1
–
5
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
E
M
5
9
3
7
9
.
2
0
2
3
.
1
0
1
6
6
6
5
8
.
[
2
]
B
.
B
h
a
r
g
a
v
a
a
n
d
S
.
P
a
s
a
r
i
,
“
E
a
r
t
h
q
u
a
k
e
p
r
e
d
i
c
t
i
o
n
u
s
i
n
g
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
s
,
”
i
n
8
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
A
d
v
a
n
c
e
d
C
o
m
p
u
t
i
n
g
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
S
y
st
e
m
s,
I
C
A
C
C
S
2
0
2
2
,
2
0
2
2
,
p
p
.
4
7
6
–
4
7
9
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
C
C
S
5
4
1
5
9
.
2
0
2
2
.
9
7
8
5
0
1
1
.
[
3
]
Ö
.
Y
i
l
m
a
z
,
S
e
i
sm
i
c
d
a
t
a
a
n
a
l
y
s
i
s
.
so
c
i
e
t
y
o
f
e
x
p
l
o
r
a
t
i
o
n
g
e
o
p
h
y
si
c
i
s
t
s
,
2
0
0
1
.
d
o
i
:
1
0
.
1
1
9
0
/
1
.
9
7
8
1
5
6
0
8
0
1
5
8
0
.
[
4
]
B
.
K
e
n
n
e
t
t
,
S
e
i
sm
i
c
w
a
v
e
p
ro
p
a
g
a
t
i
o
n
i
n
st
r
a
t
i
f
i
e
d
m
e
d
i
a
.
A
N
U
P
r
e
ss,
2
0
0
9
.
d
o
i
:
1
0
.
2
6
5
3
0
/
O
A
P
EN
_
4
5
9
5
2
4
.
[
5
]
S
.
A
z
a
d
i
a
n
d
A
.
A
.
S
a
f
a
v
i
,
“
S
-
t
r
a
n
sf
o
r
m
b
a
se
d
P
-
w
a
v
e
a
n
d
S
-
wa
v
e
a
r
r
i
v
a
l
t
i
mes
m
e
a
s
u
r
e
m
e
n
t
s
t
o
w
a
r
d
e
a
r
t
h
q
u
a
k
e
l
o
c
a
t
i
n
g
,
”
i
n
T
h
e
2
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
n
t
ro
l
,
I
n
s
t
ru
m
e
n
t
a
t
i
o
n
a
n
d
Au
t
o
m
a
t
i
o
n
,
I
EEE,
D
e
c
.
2
0
1
1
,
p
p
.
2
4
1
–
2
4
6
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
I
A
u
t
o
m
.
2
0
1
1
.
6
3
5
6
6
6
3
.
[
6
]
G
.
Ek
s
t
r
ö
m
,
“
A
g
l
o
b
a
l
m
o
d
e
l
o
f
l
o
v
e
a
n
d
r
a
y
l
e
i
g
h
s
u
r
f
a
c
e
w
a
v
e
d
i
s
p
e
r
si
o
n
a
n
d
a
n
i
s
o
t
r
o
p
y
,
2
5
-
2
5
0
s,
”
G
e
o
p
h
y
si
c
a
l
J
o
u
rn
a
l
I
n
t
e
r
n
a
t
i
o
n
a
l
,
v
o
l
.
1
8
7
,
n
o
.
3
,
p
p
.
1
6
6
8
–
1
6
8
6
,
D
e
c
.
2
0
1
1
,
d
o
i
:
1
0
.
1
1
1
1
/
j
.
1
3
6
5
-
2
4
6
X
.
2
0
1
1
.
0
5
2
2
5
.
x
.
[
7
]
P
.
B
.
Q
u
a
n
g
,
P
.
G
a
i
l
l
a
r
d
,
a
n
d
Y
.
C
a
n
o
,
“
A
ss
o
c
i
a
t
i
o
n
o
f
a
r
r
a
y
p
r
o
c
e
ssi
n
g
a
n
d
s
t
a
t
i
s
t
i
c
a
l
m
o
d
e
l
l
i
n
g
f
o
r
se
i
smi
c
e
v
e
n
t
m
o
n
i
t
o
r
i
n
g
,
”
i
n
2
0
1
5
2
3
rd
E
u
r
o
p
e
a
n
S
i
g
n
a
l
Pro
c
e
ssi
n
g
C
o
n
f
e
r
e
n
c
e
,
EU
S
I
P
C
O
2
0
1
5
,
I
EEE,
A
u
g
.
2
0
1
5
,
p
p
.
1
9
4
5
–
1
9
4
9
.
d
o
i
:
1
0
.
1
1
0
9
/
EU
S
I
P
C
O
.
2
0
1
5
.
7
3
6
2
7
2
3
.
[
8
]
S
.
K
u
l
k
a
r
n
i
,
U
.
B
h
o
s
l
e
,
a
n
d
V
.
K
.
T,
“
A
n
a
l
y
s
i
s
o
f
se
i
sm
i
c
s
i
g
n
a
l
a
n
d
d
e
t
e
c
t
i
o
n
o
f
a
b
n
o
r
mal
i
t
i
e
s
,”
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
&
En
g
i
n
e
e
ri
n
g
:
An
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
,
v
o
l
.
1
2
,
n
o
.
6
,
p
p
.
5
3
–
6
9
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
5
1
2
1
/
c
sei
j
.
2
0
2
2
.
1
2
6
0
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
d
va
n
ce
men
ts
in
s
eismic d
a
ta
co
llectio
n
a
n
d
a
n
a
lysi
s
th
r
o
u
g
h
…
(
S
u
ja
t
a
K
u
lka
r
n
i
)
2067
[
9
]
S
.
K
u
l
k
a
r
n
i
,
U
.
B
h
o
sl
e
,
a
n
d
T.
V
i
j
a
y
k
u
mar,
“
A
n
a
l
y
si
s
o
f
r
e
a
l
t
i
m
e
se
i
smi
c
s
i
g
n
a
l
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
i
n
I
E
C
O
N
Pro
c
e
e
d
i
n
g
s
(
I
n
d
u
st
r
i
a
l
E
l
e
c
t
r
o
n
i
c
s
C
o
n
f
e
re
n
c
e
)
,
I
EEE,
O
c
t
.
2
0
2
3
,
p
p
.
1
–
6
.
d
o
i
:
1
0
.
1
1
0
9
/
I
EC
O
N
5
1
7
8
5
.
2
0
2
3
.
1
0
3
1
2
6
8
8
.
[
1
0
]
H
u
a
n
g
Y
i
,
S
u
n
S
h
i
y
u
,
D
u
a
n
X
i
u
sh
e
n
g
,
a
n
d
C
h
e
n
Z
h
i
g
a
n
g
,
“
A
st
u
d
y
o
n
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
s
f
r
a
mew
o
r
k
,
”
i
n
2
0
1
6
I
EE
E
Ad
v
a
n
c
e
d
I
n
f
o
rm
a
t
i
o
n
M
a
n
a
g
e
m
e
n
t
,
C
o
m
m
u
n
i
c
a
t
e
s,
E
l
e
c
t
r
o
n
i
c
a
n
d
A
u
t
o
m
a
t
i
o
n
C
o
n
t
r
o
l
C
o
n
f
e
re
n
c
e
(
I
MC
EC
)
,
I
EEE,
O
c
t
.
2
0
1
6
,
p
p
.
1
5
1
9
–
1
5
2
2
.
d
o
i
:
1
0
.
1
1
0
9
/
I
M
C
E
C
.
2
0
1
6
.
7
8
6
7
4
7
1
.
[
1
1
]
O
.
M
.
S
a
a
d
,
A
.
G
.
H
a
f
e
z
,
a
n
d
M
.
S
.
S
o
l
i
m
a
n
,
“
D
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
e
a
r
t
h
q
u
a
k
e
p
a
r
a
me
t
e
r
s
c
l
a
ss
i
f
i
c
a
t
i
o
n
i
n
e
a
r
t
h
q
u
a
k
e
e
a
r
l
y
w
a
r
n
i
n
g
s
y
st
e
m,
”
I
EE
E
G
e
o
s
c
i
e
n
c
e
a
n
d
Re
m
o
t
e
S
e
n
si
n
g
L
e
t
t
e
rs
,
v
o
l
.
1
8
,
n
o
.
7
,
p
p
.
1
2
9
3
–
1
2
9
7
,
Ju
l
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
LG
R
S
.
2
0
2
0
.
2
9
9
8
5
8
0
.
[
1
2
]
H
.
K
u
b
o
,
M
.
N
a
o
i
,
a
n
d
M
.
K
a
n
o
,
“
R
e
c
e
n
t
a
d
v
a
n
c
e
s
i
n
e
a
r
t
h
q
u
a
k
e
se
i
sm
o
l
o
g
y
u
si
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
E
a
rt
h
,
P
l
a
n
e
t
s
a
n
d
S
p
a
c
e
,
v
o
l
.
7
6
,
n
o
.
1
,
p
.
3
6
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
1
1
8
6
/
s
4
0
6
2
3
-
0
2
4
-
0
1
9
8
2
-
0.
[
1
3
]
W
.
Zh
u
a
n
d
G
.
C
.
B
e
r
o
z
a
,
“
P
h
a
s
e
N
e
t
:
a
d
e
e
p
-
n
e
u
r
a
l
-
n
e
t
w
o
r
k
-
b
a
se
d
se
i
sm
i
c
a
r
r
i
v
a
l
-
t
i
me
p
i
c
k
i
n
g
me
t
h
o
d
,
”
G
e
o
p
h
y
si
c
a
l
J
o
u
rn
a
l
I
n
t
e
r
n
a
t
i
o
n
a
l
,
v
o
l
.
2
1
6
,
n
o
.
1
,
p
p
.
2
6
1
–
2
7
3
,
O
c
t
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
9
3
/
g
j
i
/
g
g
y
4
2
3
.
[
1
4
]
M
.
Y
o
u
sefz
a
d
e
h
,
S
.
A
.
H
o
ss
e
i
n
i
,
a
n
d
M
.
F
a
r
n
a
g
h
i
,
“
S
p
a
t
i
o
t
e
m
p
o
r
a
l
l
y
e
x
p
l
i
c
i
t
e
a
r
t
h
q
u
a
k
e
p
r
e
d
i
c
t
i
o
n
u
si
n
g
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
S
o
i
l
D
y
n
a
m
i
c
s
a
n
d
E
a
rt
h
q
u
a
k
e
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
4
4
,
p
.
1
0
6
6
6
3
,
M
a
y
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
so
i
l
d
y
n
.
2
0
2
1
.
1
0
6
6
6
3
.
[
1
5
]
M
.
S
.
A
mi
n
a
n
d
H
.
A
h
n
,
“
Ea
r
t
h
q
u
a
k
e
d
i
sas
t
e
r
a
v
o
i
d
a
n
c
e
l
e
a
r
n
i
n
g
sy
s
t
e
m
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
,
”
C
o
g
n
i
t
i
v
e
S
y
s
t
e
m
s
Re
se
a
rc
h
,
v
o
l
.
6
6
,
p
p
.
2
2
1
–
2
3
5
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
g
s
y
s.
2
0
2
0
.
1
1
.
0
0
2
.
[
1
6
]
M
.
A
.
S
a
l
a
m,
L.
I
b
r
a
h
i
m,
a
n
d
D
.
S
.
A
b
d
e
l
mi
n
a
a
m,
“
Ea
r
t
h
q
u
a
k
e
p
r
e
d
i
c
t
i
o
n
u
si
n
g
h
y
b
r
i
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
2
,
n
o
.
5
,
p
p
.
6
5
4
–
6
6
5
,
2
0
2
1
,
d
o
i
:
1
0
.
1
4
5
6
9
/
I
JA
C
S
A
.
2
0
2
1
.
0
1
2
0
5
7
8
.
[
1
7
]
S
.
O
mm
i
a
n
d
M
.
H
a
sh
e
mi
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
i
n
t
h
e
n
o
r
t
h
z
a
g
r
o
s
e
a
r
t
h
q
u
a
k
e
p
r
e
d
i
c
t
i
o
n
,
”
A
p
p
l
i
e
d
C
o
m
p
u
t
i
n
g
a
n
d
G
e
o
sc
i
e
n
c
e
s
,
v
o
l
.
2
2
,
p
.
1
0
0
1
6
3
,
J
u
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
c
a
g
s
.
2
0
2
4
.
1
0
0
1
6
3
.
[
1
8
]
G
.
G
u
r
s
o
y
,
A
.
V
a
r
o
l
,
a
n
d
A
.
N
a
s
a
b
,
“
I
mp
o
r
t
a
n
c
e
o
f
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms
i
n
e
a
r
t
h
q
u
a
k
e
p
r
e
d
i
c
t
i
o
n
:
a
r
e
v
i
e
w
,
”
i
n
I
S
D
FS
2
0
2
3
-
1
1
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
S
y
m
p
o
si
u
m
o
n
D
i
g
i
t
a
l
F
o
r
e
n
s
i
c
s
a
n
d
S
e
c
u
ri
t
y
,
I
EEE,
M
a
y
2
0
2
3
,
p
p
.
1
–
6
.
d
o
i
:
1
0
.
1
1
0
9
/
I
S
D
F
S
5
8
1
4
1
.
2
0
2
3
.
1
0
1
3
1
7
6
6.
[
1
9
]
Q
.
W
a
n
g
,
Y
.
G
u
o
,
L
.
Y
u
,
a
n
d
P
.
L
i
,
“
E
a
r
t
h
q
u
a
k
e
p
r
e
d
i
c
t
i
o
n
b
a
sed
o
n
sp
a
t
i
o
-
t
e
mp
o
r
a
l
d
a
t
a
m
i
n
i
n
g
:
a
n
L
S
TM
n
e
t
w
o
r
k
a
p
p
r
o
a
c
h
,
”
I
E
EE
T
r
a
n
sa
c
t
i
o
n
s
o
n
E
m
e
rg
i
n
g
T
o
p
i
c
s
i
n
C
o
m
p
u
t
i
n
g
,
v
o
l
.
8
,
n
o
.
1
,
p
p
.
1
4
8
–
1
5
8
,
Ja
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
T
E
TC
.
2
0
1
7
.
2
6
9
9
1
6
9
.
[
2
0
]
A
.
Li
a
n
d
L
.
K
a
n
g
,
“
K
N
N
-
b
a
s
e
d
m
o
d
e
l
i
n
g
a
n
d
i
t
s
a
p
p
l
i
c
a
t
i
o
n
i
n
a
f
t
e
r
sh
o
c
k
p
r
e
d
i
c
t
i
o
n
,
”
i
n
I
n
t
e
r
n
a
t
i
o
n
a
l
A
si
a
S
y
m
p
o
s
i
u
m
o
n
I
n
t
e
l
l
i
g
e
n
t
I
n
t
e
ra
c
t
i
o
n
a
n
d
Af
f
e
c
t
i
v
e
C
o
m
p
u
t
i
n
g
,
A
S
I
A
2
0
0
9
,
I
EEE,
D
e
c
.
2
0
0
9
,
p
p
.
8
3
–
8
6
.
d
o
i
:
1
0
.
1
1
0
9
/
A
S
I
A
.
2
0
0
9
.
2
1
.
[
2
1
]
M
.
A
.
M
e
i
e
r
e
t
a
l
.
,
“
R
e
l
i
a
b
l
e
r
e
a
l
-
t
i
me
se
i
smi
c
si
g
n
a
l
/
n
o
i
se
d
i
scr
i
mi
n
a
t
i
o
n
w
i
t
h
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
J
o
u
rn
a
l
o
f
G
e
o
p
h
y
s
i
c
a
l
Re
se
a
rc
h
:
S
o
l
i
d
Ea
r
t
h
,
v
o
l
.
1
2
4
,
n
o
.
1
,
p
p
.
7
8
8
–
8
0
0
,
Ja
n
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
2
9
/
2
0
1
8
JB
0
1
6
6
6
1
.
[
2
2
]
S
.
M
.
M
o
u
sa
v
i
,
W
.
Zh
u
,
Y
.
S
h
e
n
g
,
a
n
d
G
.
C
.
B
e
r
o
z
a
,
“
C
R
ED
:
a
d
e
e
p
r
e
s
i
d
u
a
l
n
e
t
w
o
r
k
o
f
c
o
n
v
o
l
u
t
i
o
n
a
l
a
n
d
r
e
c
u
r
r
e
n
t
u
n
i
t
s
f
o
r
e
a
r
t
h
q
u
a
k
e
si
g
n
a
l
d
e
t
e
c
t
i
o
n
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
rt
s
,
v
o
l
.
9
,
n
o
.
1
,
p
.
1
0
2
6
7
,
J
u
l
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
3
8
/
s4
1
5
9
8
-
0
1
9
-
4
5
7
4
8
-
1.
[2
3
]
L.
Z
h
u
e
t
a
l
.
,
“
D
e
e
p
l
e
a
r
n
i
n
g
f
o
r
s
e
i
sm
i
c
p
h
a
se
d
e
t
e
c
t
i
o
n
a
n
d
p
i
c
k
i
n
g
i
n
t
h
e
a
f
t
e
r
sh
o
c
k
z
o
n
e
o
f
2
0
0
8
M
w
7
.
9
W
e
n
c
h
u
a
n
Ea
r
t
h
q
u
a
k
e
,
”
Ph
y
si
c
s
o
f
t
h
e
Ea
rt
h
a
n
d
Pl
a
n
e
t
a
ry
I
n
t
e
r
i
o
rs
,
v
o
l
.
2
9
3
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
e
p
i
.
2
0
1
9
.
0
5
.
0
0
4
.
[2
4
]
J.
W
o
o
l
l
a
m,
A
.
R
i
e
t
b
r
o
c
k
,
A
.
B
u
e
n
o
,
a
n
d
S
.
D
e
A
n
g
e
l
i
s,
“
C
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
se
i
sm
i
c
p
h
a
se
c
l
a
ssi
f
i
c
a
t
i
o
n
,
p
e
r
f
o
r
m
a
n
c
e
d
e
m
o
n
st
r
a
t
i
o
n
o
v
e
r
a
l
o
c
a
l
s
e
i
s
mi
c
n
e
t
w
o
r
k
,
”
S
e
i
sm
o
l
o
g
i
c
a
l
Re
se
a
rc
h
L
e
t
t
e
rs
,
v
o
l
.
9
0
,
n
o
.
2
A
,
p
p
.
4
9
1
–
5
0
2
,
M
a
r
.
2
0
1
9
,
d
o
i
:
1
0
.
1
7
8
5
/
0
2
2
0
1
8
0
3
1
2
.
[2
5
]
F
.
M
a
g
r
i
n
i
,
D
.
Jo
z
i
n
o
v
i
ć
,
F
.
C
a
mm
a
r
a
n
o
,
A
.
M
i
c
h
e
l
i
n
i
,
a
n
d
L.
B
o
sc
h
i
,
“
L
o
c
a
l
e
a
r
t
h
q
u
a
k
e
s
d
e
t
e
c
t
i
o
n
:
a
b
e
n
c
h
m
a
r
k
d
a
t
a
s
e
t
o
f
3
-
c
o
m
p
o
n
e
n
t
s
e
i
sm
o
g
r
a
ms
b
u
i
l
t
o
n
a
g
l
o
b
a
l
sc
a
l
e
,
”
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
i
n
G
e
o
s
c
i
e
n
c
e
s
,
v
o
l
.
1
,
p
p
.
1
–
1
0
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
i
i
g
.
2
0
2
0
.
0
4
.
0
0
1
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Pro
f.
Dr
.
S
u
j
a
t
a
K
u
lk
a
r
n
i
h
o
ld
s
P
h
.
D
.
in
El
e
c
tro
n
ics
En
g
in
e
e
rin
g
h
a
v
in
g
w
o
rk
e
x
p
e
rien
c
e
o
f
m
o
re
th
a
n
5
y
e
a
rs
in
t
h
e
i
n
d
u
stry
.
S
h
e
h
a
s
b
e
e
n
in
th
e
tea
c
h
in
g
p
ro
fe
ss
io
n
fo
r
o
v
e
r
1
6
y
e
a
rs,
o
f
w
h
ich
sh
e
h
a
s
b
e
e
n
a
ss
o
c
iate
d
a
s
a
P
ro
fe
ss
o
r
wi
th
Bh
a
rti
y
a
Vid
y
a
Bh
a
v
a
n
s’
S
a
rd
a
r
P
a
tel
I
n
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
,
M
u
m
b
a
i
Un
i
v
e
rsity
f
o
r
m
o
r
e
th
a
n
5
y
e
a
rs.
He
r
a
re
a
s
o
f
in
tere
st
a
re
i
m
a
g
e
p
ro
c
e
ss
in
g
,
m
a
c
h
in
e
l
e
a
rn
i
n
g
,
d
e
e
p
l
e
a
rn
in
g
,
a
n
d
it
s
a
p
p
li
c
a
ti
o
n
s.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
su
jata
_
k
u
lk
a
r
n
i@sp
it
.
a
c
.
i
n
.
Mr.
Ma
l
a
y
P
h
a
d
k
e
is
a
F
in
a
l
Ye
a
r
El
e
c
tro
n
ics
a
n
d
T
e
lec
o
m
m
u
n
ica
ti
o
n
En
g
i
n
e
e
rin
g
stu
d
e
n
t
fro
m
Bh
a
rt
iy
a
Vid
y
a
B
h
a
v
a
n
s’
S
a
rd
a
r
P
a
tel
In
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
,
Are
a
s
o
f
in
tere
st
-
c
o
m
p
u
ter
v
isio
n
,
m
a
c
h
in
e
lea
rn
i
n
g
a
n
d
r
o
b
o
ti
c
s
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
a
lay
.
p
h
a
d
k
e
@s
p
it
.
a
c
.
i
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.