T
E
L
K
O
M
N
I
K
A
T
elec
o
m
m
un
ica
t
io
n,
Co
m
pu
t
ing
,
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
18
,
No
.
5
,
Octo
b
er
2
0
2
0
,
p
p
.
2
5
0
5
~
2
5
1
6
I
SS
N:
1
6
9
3
-
6
9
3
0
,
ac
cr
ed
ited
First Gr
ad
e
b
y
Kem
en
r
is
tek
d
i
k
ti,
Dec
r
ee
No
: 2
1
/E/KPT
/2
0
1
8
DOI
: 1
0
.
1
2
9
2
8
/TE
L
KOM
NI
K
A.
v
1
8
i5
.
1
4
7
0
8
2505
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//jo
u
r
n
a
l.u
a
d
.
a
c.
id
/in
d
ex
.
p
h
p
/TELK
OM
N
I
K
A
Alg
o
rithm per
for
ma
nce comp
a
riso
n f
o
r ear
thquak
e
sig
na
l
recog
nition o
n sm
a
rtphone’s a
ccel
e
ro
meter
H
a
ps
o
ro
Ag
un
g
Nug
ro
ho
1
,
H
a
ry
a
s
Su
by
a
nta
ra
Wica
k
s
a
na
2
,
H
a
riy
a
nto
3
,
Ris
t
a
H
.
Vi
rg
ia
nto
4
1
,
2,
3
De
p
a
rt
m
e
n
t
o
f
In
str
u
m
e
n
tati
o
n
fo
r
M
KG
,
S
c
h
o
o
l
o
f
M
e
teo
r
o
lo
g
y
,
C
li
m
a
to
lo
g
y
,
a
n
d
G
e
o
p
h
y
sic
s,
In
d
o
n
e
sia
4
De
p
a
rt
m
e
n
t
o
f
Cli
m
a
to
l
o
g
y
,
S
c
h
o
o
l
o
f
M
e
te
o
ro
l
o
g
y
,
Cl
ima
to
lo
g
y
,
a
n
d
G
e
o
p
h
y
sic
s,
In
d
o
n
e
sia
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
No
v
2
9
,
2
0
1
9
R
ev
is
ed
J
an
1
3
,
2
0
2
0
Acc
ep
ted
Ap
r
1
0
,
2
0
2
0
M
icro
-
e
lec
tro
-
m
e
c
h
a
n
ica
l
-
sy
ste
m
a
c
c
e
lero
m
e
ter
is
a
b
le
to
d
e
tec
t
a
c
c
e
lera
ti
o
n
sig
n
a
l
c
a
u
se
d
b
y
e
a
rth
q
u
a
k
e
.
S
u
c
h
t
y
p
e
o
f
a
c
c
e
lero
m
e
ter
is
a
l
so
u
se
d
b
y
sm
a
rtp
h
o
n
e
s.
T
h
e
re
a
re
fe
w
a
lg
o
r
it
h
m
s
th
a
t
c
a
n
b
e
u
se
d
t
o
re
c
o
g
n
i
z
e
th
e
ty
p
e
o
f
a
c
c
e
lera
ti
o
n
sig
n
a
l
fro
m
sm
a
rtp
h
o
n
e
.
T
h
is
stu
d
y
a
ims
to
f
in
d
si
g
n
a
l
re
c
o
g
n
it
i
o
n
a
lg
o
rit
h
m
i
n
o
rd
e
r
t
o
c
o
n
si
d
e
r
t
h
e
m
o
st
p
ro
p
e
r
a
lg
o
rit
h
m
f
o
r
e
a
rth
q
u
a
k
e
sig
n
a
l
d
e
tec
ti
o
n
.
Th
e
in
it
ial
sta
g
e
o
f
d
e
sig
n
in
g
th
e
re
c
o
g
n
ize
r
is
d
a
ta
c
o
ll
e
c
ti
o
n
f
o
r
e
a
c
h
ty
p
e
o
f
si
g
n
a
l
c
las
sifica
ti
o
n
.
Th
e
n
e
x
t
ste
p
is
to
a
p
p
ly
a
h
ig
h
p
a
ss
fil
ter
to
se
p
a
ra
te
t
h
e
sig
n
a
ls
c
o
ll
e
c
ted
fro
m
t
h
e
g
r
a
v
it
a
ti
o
n
a
l
a
c
c
e
ler
a
ti
o
n
sig
n
a
l.
T
h
e
sig
n
a
l
is
d
iv
i
d
e
d
i
n
t
o
se
v
e
ra
l
se
g
m
e
n
ts.
T
h
e
sy
ste
m
will
e
x
trac
t
fe
a
tu
re
s
o
f
e
a
c
h
sig
n
a
l
se
g
m
e
n
t
i
n
th
e
ti
m
e
a
n
d
fre
q
u
e
n
c
y
d
o
m
a
in
.
Eac
h
si
g
n
a
l
se
g
m
e
n
t
is
t
h
e
n
c
las
sified
a
c
c
o
rd
in
g
to
th
e
t
y
p
e
o
f
si
g
n
a
l
u
si
n
g
th
e
c
las
sifier
t
h
ro
u
g
h
a
se
ries
o
f
t
ra
in
in
g
d
a
ta
p
r
o
c
e
ss
e
s.
Th
e
c
las
sifier
wh
ich
h
a
s
th
e
h
i
g
h
e
st
a
c
c
u
ra
c
y
v
a
lu
e
is
e
x
p
o
rte
d
in
to
t
h
e
n
e
w
i
n
p
u
t
si
g
n
a
l
m
o
d
e
li
n
g
.
As
th
e
re
su
lt
,
fin
e
K
-
NN
a
lg
o
ri
th
m
h
a
s
th
e
h
ig
h
e
st
lev
e
l
o
f
a
c
c
u
ra
c
y
in
th
e
c
las
sifica
ti
o
n
.
Th
e
f
in
e
K
-
NN
a
lg
o
rit
h
m
h
a
s
a
n
a
c
c
u
ra
c
y
ra
te
o
f
9
9
.
7
5
%
i
n
th
e
c
las
sifica
ti
o
n
o
f
h
u
m
a
n
a
c
ti
v
it
y
si
g
n
a
ls
a
n
d
e
a
rth
q
u
a
k
e
sig
n
a
ls
with
a
m
e
m
o
ry
c
a
p
a
c
it
y
o
f
6
,
0
4
4
k
il
o
b
y
tes
a
n
d
p
r
o
c
e
ss
in
g
t
ime
o
f
1
5
.
9
3
se
c
o
n
d
s.
Th
is
a
lg
o
rit
h
m
h
a
s
t
h
e
b
e
st
c
la
ss
ifi
e
r
c
rit
e
ria
c
o
m
p
a
re
d
to
d
e
c
isio
n
tree
,
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
a
n
d
l
in
e
a
r
d
isc
rimin
a
n
t
a
n
a
ly
sis a
l
g
o
rit
h
m
s.
K
ey
w
o
r
d
s
:
Acc
eler
o
m
eter
E
ar
th
q
u
a
k
es
Hu
m
an
ac
tiv
ity
K
-
NN
alg
o
r
ith
m
Sig
n
al
r
ec
o
g
n
itio
n
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
:
Hap
s
o
r
o
Ag
u
n
g
Nu
g
r
o
h
o
,
Dep
ar
tm
en
t o
f
I
n
s
tr
u
m
e
n
tatio
n
f
o
r
Me
te
o
r
o
lo
g
y
C
lim
ato
lo
g
y
an
d
Geo
p
h
y
s
ics (
MK
G)
,
Sch
o
o
l o
f
Me
teo
r
o
lo
g
y
C
lim
ato
lo
g
y
a
n
d
Geo
p
h
y
s
ics,
I
/5
Per
h
u
b
u
n
g
a
n
St.,
Po
n
d
o
k
B
etu
n
g
,
Po
n
d
o
k
Ar
en
,
1
5
2
2
1
,
B
an
ten
,
I
n
d
o
n
esia.
E
m
ail: h
ap
s
o
r
o
.
a
g
u
n
g
@
b
m
k
g
.
g
o
.
id
1.
I
NT
RO
D
UCT
I
O
N
I
n
d
o
n
esia
is
s
itu
ated
in
th
e
cr
o
s
s
zo
n
e
o
f
th
r
ee
tecto
n
ic
p
la
tes,
n
am
ely
E
u
r
asia,
I
n
d
o
-
Au
s
tr
alia
an
d
Pacif
ic.
B
ased
o
n
t
h
is
co
n
d
itio
n
,
I
n
d
o
n
esia
b
ec
o
m
es
a
d
an
g
er
o
u
s
ar
ea
o
f
ea
r
th
q
u
ak
e
zo
n
e
s
[
1
,
2
]
.
T
h
o
u
s
an
d
s
o
f
s
tr
o
n
g
m
o
tio
n
ea
r
th
q
u
ak
es with
m
o
r
e
th
an
6
.
0
m
o
m
en
t m
ag
n
itu
d
e
im
p
ac
ted
I
n
d
o
n
esia
i
n
1
9
7
6
-
2
0
0
6
[
3
,
4
]
.
L
aw
n
u
m
b
er
3
1
Yea
r
2
0
0
9
o
f
I
n
d
o
n
esian
R
ep
u
b
lic
s
tates
th
a
t
th
e
Me
teo
r
o
lo
g
y
,
C
lim
ato
lo
g
y
an
d
Geo
p
h
y
s
ics
Ag
en
cy
(
B
MK
G)
is
an
ag
en
cy
au
th
o
r
ized
to
p
u
b
lis
h
in
f
o
r
m
atio
n
o
n
ea
r
th
q
u
ak
e
ev
e
n
ts
,
b
o
th
p
r
e
-
ea
r
t
h
q
u
ak
e
an
d
p
o
s
t
-
ea
r
th
q
u
ak
e
c
ases
[
5
]
.
C
o
n
f
ir
m
atio
n
o
f
th
e
in
ci
d
en
t
at
th
e
ea
r
th
q
u
ak
e
s
ite
is
n
ee
d
e
d
to
s
u
p
p
o
r
t
th
e
B
MK
G
p
er
f
o
r
m
an
ce
.
T
h
is
ce
r
tain
ly
in
v
o
lv
es
th
e
ac
tiv
e
r
o
le
o
f
th
e
c
o
m
m
u
n
ity
.
C
r
o
wd
s
o
u
r
cin
g
is
n
o
w
a
p
r
o
m
in
en
t
ter
m
in
o
lo
g
y
to
co
ll
ec
t,
p
r
o
ce
s
s
,
an
d
d
is
tr
ib
u
te
i
n
f
o
r
m
atio
n
to
s
o
ciety
.
I
t
p
o
s
s
ib
ly
b
ec
o
m
e
s
a
r
o
b
u
s
t
id
ea
to
o
v
er
c
o
m
e
t
h
e
s
m
all
n
u
m
b
er
o
f
s
eismic
m
o
n
ito
r
in
g
n
etwo
r
k
s
in
I
n
d
o
n
esia.
On
e
o
f
th
e
m
e
d
ia
f
o
r
cr
o
w
d
s
o
u
r
cin
g
is
s
m
ar
tp
h
o
n
e
.
No
wad
ay
s
,
s
m
ar
tp
h
o
n
es
ar
e
em
b
ed
d
ed
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
18
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
2
5
0
5
-
2516
2506
b
y
d
ig
ital
ac
ce
ler
o
m
eter
.
T
h
is
co
m
p
o
n
en
t
h
as
p
o
ten
tial
to
d
etec
t
g
r
o
u
n
d
s
tr
o
n
g
m
o
tio
n
p
ar
am
ete
r
s
.
T
h
e
Qu
aq
e
-
C
atch
er
Netwo
r
k
(
QNC)
an
d
C
o
m
m
u
n
ity
Seis
m
ik
Netwo
r
k
(
C
SN)
u
tili
ze
M
icr
o
elec
tr
o
m
ec
h
a
n
ical
s
y
s
tem
(
ME
MS)
ac
ce
ler
o
m
e
ter
to
d
etec
t
b
u
ild
in
g
v
ib
r
at
io
n
ca
u
s
ed
b
y
ea
r
t
h
q
u
a
k
e
[
6
]
.
Su
ch
ty
p
e
o
f
ac
ce
ler
o
m
eter
is
also
u
s
ed
b
y
s
m
ar
tp
h
o
n
es.
Ho
wev
er
,
th
e
n
o
is
e
o
f
s
m
ar
tp
h
o
n
e’
s
ac
ce
ler
o
m
eter
f
ac
es
b
i
g
o
b
s
tacle
s
,
m
ain
ly
d
u
e
t
o
h
u
m
a
n
ac
tiv
ities
[
7
]
.
An
g
u
ita
et
al.
f
r
o
m
th
e
Un
iv
er
s
ity
o
f
Ge
n
o
v
a
p
r
o
d
u
ce
d
a
s
et
o
f
ac
ce
ler
o
m
eter
d
ata
t
o
id
e
n
tify
s
ix
ty
p
es
o
f
h
u
m
an
m
o
v
em
e
n
t.
T
h
e
s
e
m
o
v
em
e
n
ts
in
clu
d
e
s
tan
d
in
g
,
walk
in
g
,
ly
in
g
d
o
wn
,
s
itti
n
g
,
g
o
in
g
u
p
an
d
d
o
wn
th
e
s
tair
s
[
8
]
.
B
ay
at,
Po
m
p
lu
n
an
d
T
r
a
n
f
r
o
m
th
e
Un
iv
er
s
ity
o
f
Ma
s
s
ac
h
u
s
etts
ex
am
in
ed
th
e
u
s
e
o
f
a
s
in
g
le
tr
iax
ial
ac
c
eler
o
m
eter
s
en
s
o
r
o
n
s
m
ar
tp
h
o
n
es b
ased
m
u
ltil
ay
er
p
er
ce
p
tr
o
n
with
an
ac
cu
r
ac
y
o
f
9
0
%
[
9
]
.
C
h
en
et
al.
s
u
cc
ee
d
ed
in
d
esig
n
in
g
a
HAR
b
ased
o
n
l
o
n
g
-
s
h
o
r
t
ter
m
m
e
m
o
r
y
(
L
STM
)
with
an
ac
cu
r
ac
y
o
f
9
2
.
1
%
[
1
0
]
.
H
o
wev
er
,
it
h
as
n
o
t
b
ee
n
im
p
r
o
v
ed
f
o
r
s
eismo
lo
g
y
.
T
h
is
s
tu
d
y
aim
s
to
co
m
p
ar
e
s
ig
n
al
r
ec
o
g
n
itio
n
alg
o
r
ith
m
i
n
o
r
d
e
r
to
d
eter
m
in
e
th
e
m
o
s
t
p
r
o
p
er
alg
o
r
ith
m
f
o
r
ea
r
th
q
u
a
k
e
s
ig
n
al
d
etec
tio
n
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
Sm
ar
tp
h
o
n
e
ac
ce
ler
o
m
et
er
s
en
s
o
r
ty
p
e
is
L
SM6
DSL.
I
t
i
s
a
tr
iax
ial
ac
ce
ler
o
m
eter
wi
th
1
6
-
b
it
r
eso
lu
tio
n
a
n
d
5
0
Hz
s
am
p
li
n
g
f
r
eq
u
e
n
cy
[
1
1
]
.
Sev
er
al
t
y
p
es
o
f
ME
MS
-
ty
p
e
ac
ce
ler
o
m
eter
s
ig
n
al
i
n
p
u
ts
in
clu
d
e
g
r
av
ity
ac
ce
ler
atio
n
s
ig
n
als,
ac
ce
ler
atio
n
d
u
e
to
h
u
m
an
b
o
d
y
m
o
v
em
en
ts
,
o
f
f
s
e
ts
an
d
n
o
is
e
[
1
2
,
1
3
]
.
T
h
e
in
itial
s
tag
e
o
f
d
esig
n
in
g
th
e
r
ec
o
g
n
izer
is
to
co
llect
d
at
a
f
o
r
ea
ch
t
y
p
e
o
f
s
ig
n
al
class
if
icatio
n
.
T
h
e
n
ex
t
s
tep
is
to
ap
p
ly
a
h
ig
h
p
ass
f
ilter
to
s
ep
ar
ate
th
e
s
ig
n
als
co
l
lecte
d
f
r
o
m
th
e
g
r
av
itatio
n
al
ac
ce
ler
atio
n
s
ig
n
al.
T
h
e
s
ig
n
al
is
d
iv
i
d
ed
in
t
o
s
e
v
er
al
s
eg
m
en
ts
.
T
h
e
s
y
s
tem
will
ex
tr
ac
t
f
ea
tu
r
es
o
f
ea
ch
s
ig
n
al
s
eg
m
en
t
in
th
e
tim
e
an
d
f
r
eq
u
en
cy
d
o
m
ai
n
.
E
ac
h
s
ig
n
al
s
eg
m
en
t
is
th
e
n
class
if
ied
ac
co
r
d
in
g
to
th
e
t
y
p
e
o
f
s
ig
n
al
u
s
in
g
th
e
class
if
ier
th
r
o
u
g
h
a
s
er
ies
o
f
tr
ai
n
in
g
d
at
a
p
r
o
ce
s
s
es.
T
h
e
class
if
ier
wh
ich
h
as
th
e
h
ig
h
e
s
t a
cc
u
r
ac
y
v
alu
e
is
ex
p
o
r
ted
in
to
t
h
e
n
ew
i
n
p
u
t
s
ig
n
al
m
o
d
elin
g
.
T
h
e
class
if
icatio
n
test
is
d
o
n
e
b
y
u
s
in
g
Py
th
o
n
3
lan
g
u
ag
e
p
r
o
g
r
am
in
L
in
u
x
U
b
u
n
tu
ter
m
in
al.
Data
ar
e
co
llected
b
y
r
ec
o
r
d
in
g
s
m
ar
tp
h
o
n
e
ac
ce
le
r
o
m
e
ter
s
ig
n
als
o
n
ac
tiv
ities
ca
r
r
ied
o
u
t
b
y
1
0
s
u
b
jects.
E
ac
h
s
u
b
ject
was
in
s
tr
u
cted
to
s
it,
s
tan
d
,
lie
d
o
wn
,
walk
an
d
r
u
n
.
T
h
e
ac
tiv
iti
es
wer
e
ca
r
r
ied
o
u
t
at
v
ar
y
in
g
s
p
ee
d
an
d
g
estu
r
es
ac
co
r
d
in
g
to
th
e
s
u
b
ject'
s
h
ab
its
.
T
h
e
ac
tiv
ities
wer
e
ca
r
r
ied
o
u
t
wh
e
n
th
e
s
m
ar
tp
h
o
n
e
is
p
lace
d
in
s
h
ir
t
p
o
ck
et
a
n
d
tr
o
u
s
er
p
o
c
k
et
with
a
v
ar
iety
o
f
t
y
p
es
ac
co
r
d
in
g
to
th
e
s
u
b
ject'
s
clo
th
in
g
d
u
r
in
g
th
e
s
tu
d
y
.
Sam
p
les
o
f
ea
r
th
q
u
ak
e
s
ig
n
als
wer
e
tak
en
f
r
o
m
B
MK
G
ac
ce
ler
o
g
r
ap
h
s
ig
n
als
th
at
r
ec
o
r
d
ea
r
t
h
q
u
a
k
e
ev
en
ts
in
L
o
m
b
o
k
an
d
Palu
.
T
h
e
am
o
u
n
t
o
f
ea
r
th
q
u
ak
e
s
ig
n
al
r
aw
d
at
a
is
2
1
4
d
ata,
wh
ile
th
e
s
u
b
ject
ac
tiv
ity
r
aw
d
ata
a
r
e
2
5
4
5
d
ata
in
t
h
e
s
h
ir
t p
o
c
k
et
an
d
2
4
3
0
d
ata
in
th
e
tr
o
u
s
er
p
o
ck
et.
Hig
h
p
ass
f
ilter
s
ar
e
d
esig
n
e
d
t
o
s
ep
ar
ate
th
e
lin
ea
r
ac
ce
ler
atio
n
s
ig
n
al
o
f
t
h
e
su
b
ject'
s
m
o
v
e
m
en
t
f
r
o
m
th
e
g
r
av
itatio
n
al
ac
ce
ler
atio
n
s
ig
n
al.
T
h
is
f
ilter
is
a
B
u
tter
w
o
r
th
ty
p
e
3
h
i
g
h
p
ass
f
ilter
with
a
cu
to
f
f
f
r
e
q
u
en
c
y
o
f
0
.
1
Hz.
Or
d
er
3
is
co
n
s
id
er
e
d
to
b
e
q
u
ite
ef
f
ec
tiv
e
to
r
ed
u
c
e
g
r
av
itatio
n
al
ac
ce
ler
atio
n
s
ig
n
als
with
d
o
m
in
an
t
f
r
eq
u
e
n
cy
r
an
g
in
g
f
r
o
m
0
.
1
-
0
.
5
Hz
[
8
]
.
Data
ex
tr
ac
tio
n
wa
s
u
n
d
er
tak
en
b
y
co
llectin
g
all
s
am
p
le
d
ata
in
to
a
d
ata
s
et.
Data
win
d
o
win
g
u
s
es
n
o
n
-
o
v
er
la
p
p
in
g
tech
n
iq
u
es with
f
r
am
e
d
u
r
atio
n
o
f
o
n
e
s
e
co
n
d
,
o
r
5
0
r
aw
d
ata
in
o
n
e
s
ig
n
al
t
y
p
e.
T
h
e
s
ig
n
al
was
ex
tr
ac
ted
to
o
b
tain
th
e
s
ig
n
al
f
ea
tu
r
es
in
t
h
e
tim
e
d
o
m
ain
an
d
f
r
eq
u
e
n
cy
d
o
m
ain
[
1
4
]
.
Fig
u
r
e
1
s
h
o
ws
a
f
lo
wch
ar
t
o
f
th
e
p
r
o
ce
s
s
u
s
ed
in
th
is
s
tu
d
y
.
2
.
1
.
Dec
is
io
n t
re
e
(
DT
)
a
lg
o
rit
hm
Dec
is
io
n
tr
ee
is
a
class
if
ier
th
at
wo
r
k
s
b
y
ar
r
a
n
g
in
g
d
ec
is
i
o
n
tr
ee
s
b
ased
o
n
p
r
ed
icto
r
s
o
r
f
ea
t
u
r
es
th
at
ex
is
t
to
d
ete
r
m
in
e
t
h
e
cl
ass
o
f
o
b
jectiv
es.
T
h
e
p
ar
am
eter
s
r
eq
u
ir
ed
ar
e
en
tr
o
p
y
an
d
in
f
o
r
m
atio
n
g
ain
o
f
ea
ch
s
ig
n
al
f
ea
tu
r
e.
I
n
f
o
r
m
atio
n
g
ain
is
a
m
ea
s
u
r
e
o
f
th
e
ef
f
ec
tiv
en
ess
o
f
a
f
ea
tu
r
e
in
class
if
y
in
g
d
ata.
T
h
e
in
f
o
r
m
atio
n
g
ain
eq
u
atio
n
is
f
o
r
m
u
lated
as f
o
llo
ws [
1
5
,
1
6
]
:
(
,
)
=
(
)
−
∑
|
|
|
|
(
)
∈
(
)
I
G
(
S,
f
)
is
th
e
in
f
o
r
m
atio
n
g
ai
n
v
alu
e
f
o
r
a
p
ar
ticu
lar
f
ea
tu
r
e
o
r
p
r
ed
icto
r
.
E
n
tr
o
p
y
(
S)
is
th
e
v
alu
e
o
f
o
v
er
all
d
ata
en
tr
o
p
y
.
V
is
a
p
o
s
s
ib
le
v
alu
e
f
o
r
p
r
ed
icto
r
f
,
wh
il
e
v
alu
e
(
f
)
is
a
s
et
o
f
p
o
s
s
ib
le
v
alu
es
f
o
r
p
r
e
d
icto
r
f
.
|
S
v
|
is
th
e
n
u
m
b
er
o
f
s
am
p
l
es f
o
r
v
alu
es V
an
d
|
S |
is
th
e
s
u
m
o
f
all
d
ata
s
am
p
les.
E
n
tr
o
p
y
(
S
V
)
is
th
e
v
al
u
e
o
f
en
tr
o
p
y
f
o
r
s
am
p
les
th
at
h
av
e
a
v
alu
e
o
f
V.
T
h
e
p
r
ed
icto
r
th
at
h
as
th
e
h
ig
h
est
I
G
will
b
e
th
e
r
o
o
t
o
f
t
h
e
o
th
e
r
p
r
ed
icto
r
s
in
th
e
d
ec
is
io
n
tr
ee
.
T
h
e
r
em
ain
in
g
I
G
p
r
e
d
i
cto
r
v
alu
e
is
r
ec
alcu
lated
to
b
ec
o
m
e
th
e
s
ec
o
n
d
r
o
o
t,
an
d
s
o
o
n
.
R
o
o
t
co
n
tin
u
es
b
r
a
n
ch
in
g
d
o
w
n
,
th
e
r
ef
o
r
e
it
will
ap
p
ea
r
a
d
esti
n
atio
n
class
at
th
e
to
p
o
f
th
e
d
ec
is
io
n
tr
ee
[
1
0
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
A
lg
o
r
ith
m
p
erfo
r
ma
n
ce
co
mp
a
r
is
o
n
fo
r
ea
r
th
q
u
a
ke
s
ig
n
a
l reco
g
n
itio
n
…
(
Ha
p
s
o
r
o
A
g
u
n
g
N
u
g
r
o
h
o
)
2507
I
nput
a
c
c
e
l
e
r
om
e
t
e
r
da
t
a
(
X
,
Y
,
Z
-
A
xi
s
)
G
r
a
vi
t
a
t
i
on
s
i
gn
a
l
f
i
l
t
e
r
S
i
gn
a
l
s
e
gm
e
nt
a
t
i
on
t
i
m
e
dom
a
i
n f
e
a
t
ur
e
e
xt
r
a
c
t
i
on
F
our
i
e
r
t
r
a
ns
f
or
m
a
t
i
on
T
r
a
i
ni
ng
c
l
a
s
s
i
f
i
e
r
s
i
gn
a
l
(
DT
,
L
D
A
,
K
N
N
,
S
V
M
)
a
c
c
ur
a
c
y
(
DT
,
L
D
A
,
K
N
N
,
S
V
M
)
e
xpo
r
t
c
l
a
s
s
i
f
i
e
r
m
ode
l
i
ng
O
ut
put
s
i
gna
l
c
l
a
s
s
i
f
i
c
a
t
i
on
S
i
t
t
i
ng
,
S
t
a
nd
i
ng
,
L
a
yi
ng
,
W
a
l
ki
ng
,
R
un
ni
ng
,
E
a
r
t
hq
ua
ke
t
he
r
e
i
s
a
n
e
a
r
t
hq
ua
ke
s
i
gn
a
l
?
S
a
ve
m
ode
l
l
i
ng
f
i
n
i
s
h
s
t
a
r
t
Y
H
um
a
n a
c
t
i
vi
t
y f
i
l
t
e
r
N
Fig
u
r
e
1
.
Flo
wch
ar
t a
ctiv
ity
s
ig
n
al
an
d
ea
r
th
q
u
ak
e
s
ig
n
al
2
.
2
.
L
inea
r
dis
cr
im
ina
nt
a
na
ly
s
is
(
L
DA)
a
lg
o
rit
hm
L
in
ea
r
d
is
cr
im
in
an
t
an
aly
s
is
is
to
r
ed
u
ce
th
e
d
im
en
s
io
n
ality
o
f
in
p
u
t
d
ata
p
r
e
d
icto
r
s
.
L
DA
aim
s
to
s
ep
ar
ate
th
e
two
d
esti
n
atio
n
class
es
b
y
d
iv
id
in
g
th
e
d
ec
i
s
io
n
r
eg
io
n
s
[
1
7
]
.
L
DA
co
n
s
i
s
ts
o
f
th
r
ee
s
tep
s
o
f
wo
r
k
[
1
8
]
.
T
h
e
f
ir
s
t
s
tep
is
to
ca
lcu
late
s
ep
ar
ab
ilit
y
b
etwe
en
class
es
u
s
in
g
th
e
v
alu
e
o
f
th
e
in
ter
class
v
ar
ian
ce
.
T
h
e
s
ec
o
n
d
s
tep
is
to
ca
lcu
late
th
e
d
is
tan
ce
b
etwe
en
th
e
clas
s
av
er
ag
e
ag
ain
s
t
ea
ch
s
am
p
le
in
th
e
class
i
ts
elf
o
r
in
tr
ac
lass
v
ar
ian
ce
.
T
h
e
th
ir
d
s
tep
is
to
r
ed
u
ce
th
e
d
im
en
s
io
n
al
s
p
ac
e
b
etwe
en
class
es
h
en
ce
th
e
v
alu
e
o
f
in
ter
class
v
ar
ian
ce
is
in
cr
ea
s
e
d
wh
ile
th
e
v
alu
e
o
f
in
tr
a
class
v
ar
ian
ce
is
d
ec
r
ea
s
ed
[
1
2
]
.
T
h
e
L
DA
alg
o
r
ith
m
is
co
h
er
en
tly
d
escr
ib
ed
as f
o
llo
ws [
1
9
]
:
−
Dete
r
m
in
e
a
d
ata
m
atr
ix
with
r
o
w
n
u
m
b
er
s
M
an
d
co
lu
m
n
n
u
m
b
er
s
N
−
C
alcu
late
th
e
av
er
ag
e
o
f
ea
ch
class
(
1
x
M)
−
C
alcu
late
th
e
av
er
ag
e
o
f
all
class
es (
1
x
M)
−
C
alcu
late
in
ter
class
v
ar
ian
ce
:
=
∑
(
−
)
=
1
(
−
)
−
C
alcu
late
in
tr
ac
lass
v
ar
ian
ce
:
=
∑
∑
(
−
)
=
1
=
1
(
−
)
−
C
alcu
late
v
ar
ian
ce
m
atr
ix
:
=
−
1
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
18
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
2
5
0
5
-
2516
2508
−
C
alcu
late
E
ig
en
v
alu
e
an
d
eig
en
v
ec
to
r
f
r
o
m
m
atr
ix
W
−
Ar
r
an
g
e
E
ig
e
n
v
ec
to
r
b
ased
o
n
E
ig
en
v
alu
e.
First E
ig
en
v
ec
to
r
is
u
s
ed
as lo
wer
d
im
en
s
io
n
al
s
p
ac
e
(
Vk
)
−
Pro
ject
all
s
am
p
les to
Vk
−
C
alcu
late
th
e
d
is
tan
ce
o
f
n
ew
s
am
p
le
to
d
ata
av
er
a
g
e
v
alu
e
wh
ich
ar
e
p
r
o
jecte
d
b
y
Vk
f
o
r
ea
ch
class
.
T
h
e
s
m
allest d
is
tan
ce
v
alu
e
is
in
clu
d
ed
in
t
o
ce
r
tain
class
.
2
.
3
.
Su
pp
o
rt
v
ec
t
o
r
ma
chine
(
SVM
)
a
lg
o
rit
hm
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
is
to
d
eter
m
in
e
t
h
e
b
est
h
y
p
er
p
l
an
e
as
a
s
ep
ar
ato
r
b
etwe
en
d
esti
n
atio
n
class
es
[
2
0
]
.
Hy
p
er
p
la
n
e
is
a
d
elim
iter
th
at
d
iv
id
es
a
v
ec
to
r
s
p
ac
e
in
to
two
p
ar
ts
,
th
e
r
ef
o
r
e
two
d
if
f
er
en
t
class
es
ca
n
b
e
s
ep
ar
ated
.
T
h
e
b
est
ch
ar
ac
ter
is
tic
o
f
h
y
p
er
p
lan
e
is
th
e
m
ax
im
u
m
m
ar
g
in
v
alu
e.
Ma
r
g
in
is
th
e
d
is
tan
ce
b
etwe
en
th
e
h
y
p
er
p
lan
e
an
d
t
h
e
n
ea
r
est
p
r
ed
icto
r
v
ec
to
r
o
f
th
e
two
clas
s
es.
T
h
is
p
r
ed
icto
r
v
ec
to
r
is
ca
lled
s
u
p
p
o
r
t v
ec
to
r
.
Hy
p
er
p
lan
e
ca
n
b
e
u
s
ed
to
s
ep
ar
ate
lin
ea
r
an
d
n
o
n
li
n
ea
r
d
ata
[
2
1
]
.
T
h
e
p
r
e
d
icto
r
is
d
e
n
o
ted
a
s
x
i
an
d
th
e
class
is
d
en
o
ted
as y
i
wh
ich
co
n
tain
s
o
f
two
class
es
th
at
ass
u
m
ed
to
b
e
-
1
an
d
1
,
wh
ile
th
e
w
v
ec
to
r
is
a
s
u
p
p
o
r
t v
ec
to
r
.
T
h
e
h
y
p
er
p
lan
e
eq
u
atio
n
f
o
r
lin
ea
r
d
ata
i
s
f
o
r
m
u
lated
as f
o
llo
ws:
⃗
⃗
=
⃗
⃗
.
⃗
⃗
⃗
+
Hy
p
er
p
lan
e
e
q
u
atio
n
⃗
⃗
.
⃗
⃗
⃗
+
≤
−
1
f
o
r
class
-
1
⃗
⃗
.
⃗
⃗
⃗
+
≥
1
f
o
r
clas
s
1
T
h
e
lar
g
est
m
ar
g
in
ca
n
b
e
d
eter
m
in
ed
b
y
m
ax
i
m
izin
g
th
e
v
alu
e
o
f
th
e
h
y
p
e
r
p
lan
e'
s
d
is
tan
ce
to
th
e
v
ec
to
r
at
its
clo
s
est
p
o
in
t.
I
f
th
e
m
ar
g
in
v
alu
e
h
as
g
r
ea
ter
v
alu
e,
th
e
n
it
h
as
b
etter
class
if
icatio
n
.
Hy
p
e
r
p
lan
e
f
o
r
n
o
n
lin
ea
r
d
ata
is
d
esig
n
ed
u
s
in
g
t
he
Ker
n
el
f
u
n
ctio
n
,
wh
i
ch
tr
an
s
f
o
r
m
s
a
2
-
D
v
ec
t
o
r
f
iel
d
in
to
a
3
-
D
v
ec
to
r
.
No
n
lin
ea
r
p
r
e
d
icto
r
s
ar
e
ea
s
ier
to
s
ep
ar
ate
in
3
-
D
v
ec
to
r
s
p
ac
e.
T
h
e
co
m
m
o
n
ly
u
s
ed
k
er
n
el
f
u
n
ctio
n
s
ar
e
th
e
p
o
ly
n
o
m
ial,
g
a
u
s
s
ian
an
d
s
ig
m
o
id
k
er
n
els [
2
2
]
.
−
Po
ly
n
o
m
ial
k
er
n
el
tr
an
s
f
o
r
m
at
io
n
eq
u
atio
n
:
(
,
⃗
⃗
⃗
⃗
⃗
⃗
⃗
)
=
(
,
⃗
⃗
⃗
⃗
⃗
⃗
,
⃗
⃗
⃗
⃗
+
1
)
,
p
is
th
e
h
ig
h
est n
u
m
b
e
r
o
f
ex
p
o
n
en
t
−
Gau
s
s
ian
k
er
n
el
tr
an
s
f
o
r
m
atio
n
eq
u
atio
n
:
(
,
⃗
⃗
⃗
⃗
⃗
⃗
⃗
)
=
e
xp
(
−
‖
⃗
⃗
⃗
−
⃗
⃗
⃗
‖
2
)
,
is
v
ar
ian
ce
o
f
v
ec
to
r
x
−
Sig
m
o
id
k
er
n
el
tr
an
s
f
o
r
m
atio
n
eq
u
atio
n
:
(
,
⃗
⃗
⃗
⃗
⃗
⃗
⃗
)
=
ta
n
h
(
⃗
⃗
⃗
⃗
⃗
⃗
+
)
,
alp
h
a
an
d
b
eta
ar
e
s
ig
m
o
id
c
o
n
s
tan
t
T
h
e
h
y
p
er
p
lan
e
eq
u
atio
n
ap
p
li
ed
to
n
o
n
lin
ea
r
d
ata
b
y
u
tili
zin
g
th
e
Ker
n
el
f
u
n
ctio
n
is
ca
lcu
lated
as f
o
llo
ws:
⃗
⃗
=
⃗
⃗
.
(
,
⃗
⃗
⃗
⃗
⃗
⃗
⃗
)
+
2
.4
.
K
-
nea
re
s
t
neig
hb
o
r
(K
-
NN)
a
lg
o
rit
hm
K
-
Nea
r
est
Neig
h
b
o
r
alg
o
r
ith
m
is
to
ca
lcu
late
th
e
d
is
tan
ce
o
f
a
n
ew
d
ata
in
p
u
t
ag
ain
s
t
th
e
K
-
d
ata
lear
n
in
g
m
o
d
el
[
2
3
]
.
T
h
is
alg
o
r
ith
m
is
also
u
s
ef
u
l
to
s
ea
r
c
h
f
o
r
th
e
n
ea
r
est
n
eig
h
b
o
r
f
r
o
m
a
n
ew
d
ata
i
n
p
u
t.
T
h
e
p
r
o
x
im
ity
o
f
n
ew
in
p
u
t
d
ata
to
th
e
m
o
d
el
d
ata
is
g
en
er
ally
ca
lcu
lated
u
s
in
g
th
e
E
u
cli
d
ea
n
Dis
tan
ce
[
2
4
]
as f
o
llo
ws:
(
,
)
=
∑
√
(
−
)
2
=
1
A
is
th
e
n
ew
in
p
u
t
d
ata,
wh
ile
B
is
th
e
lear
n
in
g
m
o
d
el
d
ata.
T
h
e
n
ew
i
n
p
u
t
d
at
a
is
test
ed
ag
ain
s
t
ea
ch
lear
n
in
g
d
ata
p
o
in
t,
th
e
n
ag
ain
s
t
th
e
n
eig
h
b
o
r
s
eq
u
en
c
e
with
th
e
s
m
alles
t
d
is
tan
ce
v
alu
e
ac
co
r
d
in
g
to
th
e
K
n
u
m
b
er
.
K
-
NN
h
as sev
e
r
al
ty
p
es o
f
p
r
o
ce
s
s
in
g
alg
o
r
ith
m
s
[
2
5
]
,
n
am
ely
:
−
Fin
e
K
-
NN,
u
s
in
g
th
e
clo
s
est n
eig
h
b
o
r
(
K=
1
)
.
−
Me
d
iu
m
K
-
NN,
u
s
in
g
te
n
clo
s
est n
eig
h
b
o
r
s
(
K=
1
0
)
.
−
C
o
ar
s
e
K
-
NN,
u
s
in
g
o
n
e
h
u
n
d
r
ed
cl
o
s
est n
eig
h
b
o
r
s
(
K=
1
0
0
)
.
−
C
o
s
in
e
K
-
NN,
u
s
in
g
d
is
tan
ce
ca
lcu
latio
n
o
f
th
e
clo
s
est n
eig
h
b
o
r
b
ased
o
n
co
s
in
e
d
is
tan
ce
m
atr
ix
:
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
A
lg
o
r
ith
m
p
erfo
r
ma
n
ce
co
mp
a
r
is
o
n
fo
r
ea
r
th
q
u
a
ke
s
ig
n
a
l reco
g
n
itio
n
…
(
Ha
p
s
o
r
o
A
g
u
n
g
N
u
g
r
o
h
o
)
2509
=
1
−
⃗
.
|
⃗
|
.
|
|
−
C
u
b
ic
K
-
N
N
, usi
ng di
s
t
an
ce
ca
l
cul
at
i
on o
f
t
h
e
c
l
ose
st
n
ei
ghbo
r
b
as
ed
on cub
i
c
di
s
t
anc
e
m
a
t
r
i
x:
=
√
∑
|
−
|
3
=
1
3
I
n
g
en
e
r
al,
th
e
K
-
NN
alg
o
r
ith
m
s
tep
s
ca
n
b
e
d
escr
ib
e
d
as f
o
llo
ws:
a.
Dete
r
m
in
e
K
v
alu
e
o
r
n
u
m
b
er
o
f
th
e
clo
s
est n
eig
h
b
o
r
b.
Calcula
te
n
ew
in
p
u
t d
is
t
an
ce
to
all
lear
n
in
g
m
o
d
els.
c.
Ar
r
an
g
e
th
e
n
ew
in
p
u
t d
is
tan
c
e
f
r
o
m
t
h
e
clo
s
est to
f
ar
d
is
tan
ce
d.
Dete
m
in
e
clo
s
est n
eig
h
b
o
r
ca
t
eg
o
r
y
b
ased
o
n
K
v
alu
e.
e.
Use m
ajo
r
ity
ca
teg
o
r
y
class
o
f
clo
s
est n
eig
h
b
o
r
t
o
p
r
e
d
ict
th
e
r
esu
lt o
f
n
ew
in
p
u
t d
ata.
3.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
T
ab
le
1
s
h
o
ws
th
e
r
esu
lts
o
f
th
e
s
m
ar
tp
h
o
n
e
ac
ce
ler
ato
r
s
ig
n
al
ex
tr
ac
tio
n
f
o
r
v
ar
io
u
s
ac
tiv
ities
in
th
e
tim
e
d
o
m
ain
.
T
a
b
le
1
p
r
o
v
es
th
at
s
ig
n
if
ican
t
d
if
f
er
en
ce
o
cc
u
r
s
in
ch
ar
ac
ter
is
tics
b
etwe
en
h
u
m
a
n
ac
tiv
it
y
s
ig
n
als
an
d
ea
r
th
q
u
a
k
e
s
ig
n
als
in
th
e
tim
e
d
o
m
ai
n
.
L
i
n
ea
r
ac
ce
ler
atio
n
s
ig
n
als
d
u
e
t
o
h
u
m
a
n
ac
tiv
ity
r
ep
o
r
ted
g
r
ea
ter
v
alu
e
f
o
r
all
f
ea
t
u
r
es c
o
m
p
ar
ed
to
ea
r
th
q
u
ak
e
s
ig
n
als
.
T
h
e
s
ig
n
al
d
is
tr
ib
u
tio
n
o
f
ac
c
eler
atio
n
o
f
h
u
m
an
ac
tiv
ity
ten
d
s
to
b
e
lep
to
k
u
r
tic,
wh
ile
ea
r
th
q
u
ak
e
s
ig
n
als
ten
d
to
b
e
p
laty
k
u
r
tic
wh
en
v
iew
ed
f
r
o
m
th
e
v
alu
e
o
f
s
ig
n
al
k
u
r
to
s
is
.
T
h
e
s
k
ewn
ess
v
alu
e
o
f
ea
c
h
s
ig
n
al
ty
p
e
d
o
es
n
o
t sh
o
w
a
s
ig
n
if
ican
t
d
if
f
er
e
n
ce
.
T
ab
le
1
.
Sig
n
al’
s
f
ea
t
u
r
e
ex
tr
a
ctio
n
r
esu
lt in
tim
e
d
o
m
ain
F
e
a
t
u
r
e
(
m
/
s
2
)
S
i
t
t
i
n
g
S
t
a
n
d
i
n
g
La
y
i
n
g
W
a
l
k
i
n
g
R
u
n
n
i
n
g
Ea
r
t
h
q
u
a
k
e
mea
n
X
1
.
65
1
.
41
1
.
88
0
.
80
0
.
97
0
.
04
mea
n
Y
2
.
77
1
.
77
2
.
31
2
.
98
3
.
39
0
.
10
mea
n
Z
1
.
88
1
.
97
2
.
58
0
.
82
0
.
98
0
.
01
med
i
a
n
1
.
68
1
.
41
1
.
87
0
.
83
1
.
17
0
.
04
med
i
a
n
2
.
83
1
.
79
2
.
39
2
.
97
4
.
49
0
.
10
med
i
a
n
Z
1
.
95
1
.
95
2
.
61
0
.
93
1
.
25
0
.
01
mad
X
0
.
93
0
.
78
1
.
20
1
.
52
3
.
74
0
.
02
mad
Y
1
.
26
0
.
90
1
.
33
2
.
70
7
.
61
0
.
04
mad
Z
1
.
16
1
.
02
1
.
32
1
.
67
3
.
60
0
.
02
r
msX
2
.
17
1
.
84
2
.
58
2
.
26
5
.
13
0
.
05
r
msY
3
.
41
2
.
25
3
.
03
4
.
97
10
.
48
0
.
12
r
msZ
2
.
57
2
.
49
3
.
28
2
.
51
5
.
29
0
.
02
st
d
e
v
X
1
.
15
0
.
97
1
.
54
2
.
03
4
.
98
0
.
02
st
d
e
v
Y
1
.
53
1
.
11
1
.
69
3
.
52
9
.
43
0
.
04
st
d
e
v
Z
1
.
42
1
.
26
1
.
68
2
.
26
5
.
11
0
.
02
max
X
2
.
77
2
.
17
3
.
80
5
.
19
13
.
04
0
.
05
max
Y
4
.
00
2
.
55
4
.
00
8
.
23
19
.
55
0
.
13
max
Z
3
.
34
3
.
10
4
.
30
6
.
22
16
.
14
0
.
02
mi
n
X
-
2
.
42
-
2
.
19
-
3
.
24
-
5
.
20
-
13
.
07
-
0
.
02
mi
n
Y
-
2
.
94
-
2
.
38
-
3
.
32
-
7
.
93
-
19
.
03
-
0
.
08
mi
n
Z
-
2
.
81
-
2
.
40
-
3
.
56
-
6
.
12
-
15
.
40
-
0
.
02
S
M
A
7
2
8
.
42
5
8
2
.
28
7
7
9
.
85
7
7
6
.
74
1
6
4
0
.
87
18
.
87
sk
e
w
n
e
ssX
-
0
.
06
0
.
01
0
.
06
0
.
01
-
0
.
01
-
0
.
06
sk
e
w
n
e
ssY
0
.
11
0
.
05
0
.
03
0
.
02
0
.
01
-
0
.
11
sk
e
w
n
e
ssZ
0
.
06
-
0
.
06
0
.
04
-
0
.
04
0
.
10
-
0
.
02
k
u
r
t
o
s
i
sX
3
.
37
3
.
15
3
.
71
4
.
19
4
.
20
1
.
19
k
u
r
t
o
s
i
sY
2
.
94
3
.
33
3
.
46
3
.
98
3
.
37
1
.
27
k
u
r
t
o
s
i
sZ
3
.
41
3
.
40
3
.
62
4
.
88
6
.
12
1
.
10
T
ab
le
2
s
h
o
ws
th
at
th
e
ac
tiv
i
ty
s
ig
n
al
en
e
r
g
y
is
m
u
c
h
g
r
e
ater
co
m
p
a
r
ed
to
th
e
ea
r
th
q
u
ak
e
s
ig
n
al
en
er
g
y
,
wh
ile
th
e
d
o
m
in
a
n
t f
r
eq
u
en
cy
o
f
ea
r
th
q
u
ak
e
s
ig
n
al
t
en
d
s
to
b
e
g
r
ea
ter
t
h
an
th
e
d
o
m
in
an
t f
r
e
q
u
en
c
y
o
f
non
-
lo
c
o
m
o
to
r
ac
tiv
ity
s
ig
n
al.
R
u
n
n
in
g
an
d
r
u
n
n
in
g
ac
tiv
ity
s
ig
n
a
ls
h
o
ld
m
o
r
e
u
n
i
q
u
e
in
f
o
r
m
atio
n
co
n
ten
t
t
h
an
o
th
e
r
ac
tiv
ity
s
ig
n
alsd
u
e
to
th
e
ir
h
ig
h
en
tr
o
p
y
v
alu
es,
th
e
r
ef
o
r
e
it is
m
o
r
e
ea
s
ily
id
en
tifie
d
.
E
ar
th
q
u
ak
e
s
ig
n
als
also
d
em
o
n
s
tr
ate
q
u
ite
d
if
f
er
en
t
f
ea
tu
r
e
v
alu
es
co
m
p
ar
ed
to
h
u
m
a
n
ac
tiv
ity
s
ig
n
als.
Pro
m
in
en
t
f
e
at
u
r
es
to
class
if
y
h
u
m
an
ac
tiv
ity
s
ig
n
a
ls
an
d
ea
r
th
q
u
ak
e
s
ig
n
als
in
c
lu
d
e
m
ax
im
u
m
a
m
p
litu
d
e,
h
ig
h
s
ch
o
o
l
v
alu
es,
d
o
m
in
an
t
f
r
eq
u
en
cy
,
s
p
ec
tr
al
ce
n
tr
o
id
s
an
d
s
ig
n
al
en
er
g
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
18
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
2
5
0
5
-
2516
2510
T
ab
le
2
.
Sig
n
al’
s
f
ea
t
u
r
e
ex
tr
a
ctio
n
r
esu
lt in
f
r
e
q
u
en
c
y
d
o
m
a
in
F
r
e
q
u
e
n
c
y
F
e
a
t
u
r
e
S
i
t
t
i
n
g
S
t
a
n
d
i
n
g
La
y
i
n
g
W
a
l
k
i
n
g
R
u
n
n
i
n
g
Ea
r
t
h
q
u
a
k
e
f
d
o
mX
(
H
z
)
1
.
11
1
.
15
1
.
28
2
.
97
4
.
17
2
.
36
f
d
o
mY
(
H
z
)
1
.
23
1
.
49
1
.
39
2
.
34
3
.
02
2
.
30
f
d
o
m
Z
(
H
z
)
1
.
00
1
.
01
1
.
21
5
.
33
12
.
24
2
.
70
e
n
e
r
g
y
X
(
k
J)
7
8.
98
56
.
90
93
.
55
64
.
57
3
4
3
.
12
0
.
48
e
n
e
r
g
y
Y
(
k
J)
1
5
3
.
25
72
.
85
1
2
0
.
60
3
3
3
.
08
1
2
4
0
.
18
3
.
86
e
n
e
r
g
y
Z
(
k
J)
85
.
44
83
.
50
1
4
0
.
17
79
.
12
3
4
5
.
94
0
.
02
c
e
n
t
r
o
i
d
X
(
H
z
)
5
.
63
5
.
55
6
.
86
9
.
36
11
.
56
41
.
69
c
e
n
t
r
o
i
d
Y
(
H
z
)
4
.
04
4
.
46
6
.
01
7
.
16
8
.
75
39
.
98
c
e
n
t
r
o
i
d
Z
(
H
z
)
5
.
07
4
.
86
6
.
56
10
.
18
14
.
26
44
.
73
e
n
t
r
o
p
y
X
(
b
i
t
s)
1
.
67
1
.
89
1
.
51
2
.
21
1
.
66
1
.
21
e
n
t
r
o
p
y
Y
(
b
i
t
s)
1
.
04
1
.
56
1
.
17
1
.
37
1
.
16
1
.
26
e
n
t
r
o
p
y
Z
(
b
i
t
s)
1
.
41
1
.
36
0
.
98
2
.
12
1
.
68
1
.
17
mea
n
f
r
e
q
X
(
H
z
)
1
.
70
1
.
68
2
.
19
4
.
33
5
.
93
45
.
12
mea
n
f
r
e
q
Y
(
H
z
)
1
.
18
1
.
48
1
.
89
2
.
86
3
.
81
43
.
75
mea
n
f
r
e
q
Z
(
H
z
)
1
.
61
1
.
42
1
.
93
5
.
01
8
.
94
47
.
09
3
.
1
.
Sig
na
l c
la
s
s
if
ica
t
io
n us
ing
decisi
o
n t
re
e
(
DT
)
a
lg
o
rit
hm
T
h
e
d
e
c
i
s
i
o
n
t
r
e
e
c
l
ass
i
f
i
c
at
i
o
n
i
s
b
u
i
l
t
b
a
s
e
d
o
n
a
d
e
c
i
s
i
o
n
t
r
e
e
s
c
h
e
m
e
.
T
h
e
t
y
p
e
s
o
f
D
T
a
l
g
o
r
i
t
h
m
s
u
s
e
d
i
n
c
l
u
d
e
s
i
m
p
l
e
D
T
,
m
e
d
iu
m
D
T
a
n
d
c
o
m
p
l
e
x
D
T
.
T
h
e
d
i
f
f
e
r
e
n
c
e
i
n
t
h
e
t
h
r
e
e
t
y
p
es
o
f
D
T
i
s
b
a
s
e
d
o
n
t
h
e
n
u
m
b
e
r
o
f
b
r
a
n
c
h
e
s
/
d
e
c
is
i
o
n
t
r
e
e
n
o
d
e
s
.
T
h
e
n
u
m
b
e
r
o
f
DT
m
e
d
i
u
m
n
o
d
e
s
is
g
r
e
a
te
r
t
h
an
t
h
a
t
o
f
s
i
m
p
l
e
DT
,
w
h
i
l
e
t
h
e
n
u
m
b
e
r
o
f
D
T
c
o
m
p
le
x
n
o
d
e
s
i
s
g
r
e
at
e
r
t
h
a
n
t
h
e
n
u
m
b
e
r
o
f
D
T
m
e
d
i
u
m
n
o
d
e
s
.
T
h
e
S
i
m
p
l
e
D
T
d
e
c
is
i
o
n
t
r
e
e
h
a
s
7
n
o
d
e
s
.
T
h
e
s
i
g
n
al
f
e
a
t
u
r
e
w
it
h
t
h
e
h
i
g
h
e
s
t
i
n
f
o
r
m
a
t
i
o
n
g
a
i
n
(
I
G
)
is
t
h
e
m
e
a
n
a
b
s
o
l
u
t
e
d
e
v
i
at
i
o
n
on
t
h
e
z
a
x
is
.
T
h
is
f
e
at
u
r
e
is
u
s
e
d
b
y
t
h
e
D
T
al
g
o
r
i
t
h
m
t
o
cl
as
s
if
y
e
a
r
t
h
q
u
a
k
e
s
i
g
n
a
ls
a
n
d
h
u
m
a
n
a
c
t
i
v
it
y
s
i
g
n
a
l
s
.
O
t
h
e
r
f
e
a
t
u
r
es
u
s
e
d
a
r
e
s
p
e
c
t
r
al
p
o
w
e
r
a
n
d
m
e
a
n
a
b
s
o
l
u
t
e
d
ev
i
a
t
i
o
n
o
n
t
h
e
y
a
x
i
s
.
T
h
e
s
i
m
p
l
e
D
T
a
l
g
o
r
i
t
h
m
is
u
n
a
b
l
e
t
o
c
l
as
s
i
f
y
s
i
g
n
a
ls
o
f
s
i
t
ti
n
g
,
s
t
a
n
d
i
n
g
a
n
d
l
y
i
n
g
a
c
ti
v
i
t
y
d
u
e
t
o
t
h
e
l
i
m
it
e
d
n
u
m
b
e
r
o
f
n
o
d
e
s
.
T
h
e
Me
d
iu
m
DT
d
ec
is
io
n
tr
e
e
h
as
3
4
n
o
d
es.
Featu
r
es
with
h
ig
h
I
G
v
alu
es
u
s
ed
b
y
th
e
m
ed
iu
m
DT
in
clu
d
e
m
ea
n
ab
s
o
lu
te
d
e
v
iatio
n
,
s
p
ec
tr
al
p
o
wer
,
s
p
ec
tr
al
ce
n
tr
o
id
s
,
r
o
o
t
m
ea
n
s
q
u
ar
e
,
m
ea
n
f
r
e
q
u
en
c
y
,
s
tan
d
ar
d
d
e
v
iatio
n
an
d
d
o
m
in
an
t
f
r
eq
u
en
cy
.
DT
m
ed
iu
m
al
g
o
r
ith
m
is
ab
le
to
class
if
y
alm
o
s
t
all
HAR
d
ata,
ex
ce
p
t
s
ig
n
al
f
r
o
m
s
itti
n
g
ac
tiv
ity
.
Sit
tin
g
ac
tiv
ity
s
ig
n
al
ca
n
n
o
t
b
e
class
if
ied
p
r
o
p
er
ly
b
ec
a
u
s
e
its
f
ea
tu
r
es
h
av
e
a
s
m
all
I
G
v
alu
e,
t
h
e
r
ef
o
r
e
i
t
is
class
if
ied
as
o
th
e
r
ac
tiv
i
ty
s
ig
n
als.
T
h
e
c
o
m
p
lex
DT
d
ec
is
io
n
tr
ee
h
as
1
9
3
n
o
d
es.
All
f
ea
tu
r
es
ar
e
u
s
ed
in
th
e
co
m
p
lex
DT
alg
o
r
ith
m
.
T
h
e
s
e
f
ea
tu
r
es
ca
n
class
if
y
s
ig
n
als
o
f
s
itti
n
g
,
s
tan
d
in
g
,
ly
in
g
,
walk
in
g
,
r
u
n
n
i
n
g
an
d
ea
r
th
q
u
ak
e
s
ig
n
als.
All si
g
n
al
f
ea
tu
r
es,
b
o
th
tim
e
an
d
f
r
eq
u
e
n
cy
d
o
m
ain
f
ea
tu
r
es,
ar
e
s
till
u
s
ed
i
n
th
e
c
o
m
p
le
x
DT
,
h
e
n
ce
t
h
is
alg
o
r
ith
m
is
m
o
r
e
co
m
p
lex
co
m
p
ar
ed
to
o
th
e
r
DT
alg
o
r
ith
m
s
an
d
th
is
alg
o
r
ig
h
m
is
ab
le
to
m
ap
n
o
d
es with
a
s
m
all
I
G.
T
ab
le
3
s
h
o
ws
th
e
r
esu
lts
o
f
t
esti
n
g
th
e
s
im
p
le
DT
,
m
ed
i
u
m
DT
an
d
c
o
m
p
lex
DT
.
T
h
e
co
m
p
lex
DT
alg
o
r
ith
m
h
as h
ig
h
er
lev
el
o
f
class
if
icatio
n
ac
cu
r
ac
y
co
m
p
a
r
ed
to
th
e
m
ed
iu
m
DT
,
b
o
t
h
w
h
en
th
e
s
m
ar
tp
h
o
n
e
is
in
s
h
ir
t
p
o
ck
et
an
d
tr
o
u
s
er
p
o
ck
et,
with
ac
cu
r
ac
y
v
alu
es
o
f
8
4
.
3
6
%
an
d
8
3
.
4
9
%,
r
esp
ec
tiv
ely
.
T
h
is
p
r
o
v
es
th
at
th
e
n
u
m
b
er
o
f
d
ec
is
io
n
tr
ee
n
o
d
esis
d
ir
ec
tly
p
r
o
p
o
r
tio
n
al
to
th
e
ac
cu
r
ac
y
o
f
th
e
DT
alg
o
r
ith
m
.
An
in
cr
ea
s
e
in
th
e
n
u
m
b
er
o
f
d
ec
is
io
n
t
r
ee
n
o
d
es c
an
in
c
r
ea
s
e
th
e
class
if
icatio
n
ab
ilit
y
o
f
t
h
e
DT
alg
o
r
i
th
m
.
T
ab
le
3
.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
DT
alg
o
r
ith
m
S
martp
h
o
n
e
P
o
si
t
i
o
n
Ty
p
e
o
f
D
T
Tr
u
e
(
TP+TF)
F
a
l
se
(
F
P
+
F
N
)
A
c
c
u
r
a
c
y
(
%)
Tr
o
u
s
e
r
P
o
c
k
e
t
S
i
mp
l
e
D
T
1
7
5
3
7
9
2
6
8
.
8
8
M
e
d
i
u
m D
T
1
8
7
7
6
6
8
7
3
.
7
5
C
o
m
p
l
e
x
D
T
2
1
4
7
3
9
8
8
4
.
3
6
S
h
i
r
t
P
o
c
k
e
t
S
i
mp
l
e
D
T
1
5
3
4
8
9
6
6
3
.
1
3
M
e
d
i
u
m D
T
1
6
9
6
7
3
4
6
9
.
7
9
C
o
m
p
l
e
x
D
T
2
0
2
9
4
0
1
8
3
.
4
9
3
.
2
.
Sig
na
l c
la
s
s
if
ica
t
io
n us
ing
lin
ea
r
dis
cr
im
ina
nt
a
na
ly
s
is
(
L
D
A)
a
lg
o
rit
hm
L
D
A
a
l
g
o
r
i
t
h
m
c
l
as
s
i
f
i
es
s
i
g
n
a
l
s
u
s
i
n
g
v
e
c
t
o
r
s
i
n
t
h
e
f
o
r
m
o
f
l
i
n
e
a
r
l
i
n
e
s
.
T
a
b
l
e
4
s
h
o
w
s
t
h
e
a
c
c
u
r
a
c
y
o
f
t
h
e
L
D
A
a
l
g
o
r
i
t
h
m
.
T
h
e
a
c
c
u
r
a
c
y
o
f
t
h
i
s
a
l
g
o
r
i
t
h
m
i
s
l
es
s
er
t
h
a
n
t
h
e
a
c
c
u
r
a
c
y
o
f
t
h
e
d
e
c
i
s
i
o
n
t
r
e
e
a
l
g
o
r
i
t
h
m
.
W
a
l
k
i
n
g
,
r
u
n
n
i
n
g
a
n
d
e
a
r
t
h
q
u
ak
e
s
i
g
n
a
ls
h
a
v
e
l
o
w
p
r
e
d
ic
t
i
v
e
e
r
r
o
r
r
a
t
e
s
i
n
t
h
e
L
D
A
a
l
g
o
r
i
t
h
m
.
F
i
g
u
r
e
2
s
h
o
ws
t
h
e
c
l
u
s
t
e
r
o
f
s
i
g
n
a
l
d
a
t
a
b
a
s
e
d
o
n
f
e
a
t
u
r
e
s
w
i
t
h
t
h
e
h
i
g
h
e
s
t
I
G
(
i
n
f
o
r
m
a
t
i
o
n
g
a
i
n
)
v
a
l
u
e
.
T
h
e
s
e
f
e
at
u
r
e
s
i
n
c
l
u
d
e
m
e
a
n
a
b
s
o
l
u
t
e
d
e
v
i
a
t
i
o
n
o
n
t
h
e
z
a
x
i
s
a
n
d
y
a
x
i
s
a
n
d
s
p
e
c
t
r
al
p
o
w
e
r
o
n
th
e
y
a
x
is
.
F
i
g
u
r
e
2
d
e
m
o
n
s
t
r
a
t
es
t
h
at
t
h
e
t
h
r
e
e
t
y
p
e
s
o
f
s
i
g
n
al
s
c
a
n
b
e
s
e
p
a
r
at
e
d
u
s
i
n
g
l
i
n
ea
r
l
i
n
es
v
e
c
t
o
r
t
o
b
e
c
l
as
s
i
f
i
e
d
p
r
o
p
e
r
l
y
.
S
i
t
ti
n
g
,
s
t
a
n
d
i
n
g
a
n
d
l
y
i
n
g
a
c
t
i
v
i
t
y
s
i
g
n
a
ls
h
a
v
e
o
v
e
r
l
a
p
p
i
n
g
c
l
u
s
t
e
r
s
.
T
h
e
r
e
f
o
r
e
,
i
f
t
h
e
s
e
a
c
ti
v
i
t
i
es
a
r
e
p
l
o
t
te
d
b
a
s
e
d
o
n
f
e
a
t
u
r
e
s
w
i
t
h
t
h
e
h
i
g
h
e
s
t
I
G
,
i
t
w
i
ll
b
e
d
i
f
f
i
c
u
l
t
t
o
s
e
p
a
r
a
t
e
u
s
i
n
g
l
i
n
e
a
r
li
n
e
v
e
c
t
o
r
s
.
T
h
i
s
c
a
u
s
es
t
h
e
s
i
g
n
a
l
o
f
s
i
t
t
i
n
g
,
s
t
a
n
d
i
n
g
a
n
d
l
y
i
n
g
a
c
t
i
v
it
y
c
a
n
n
o
t
b
e
c
l
as
s
i
f
i
e
d
p
r
o
p
e
r
l
y
b
y
t
h
e
L
D
A
a
l
g
o
r
i
t
h
m
.
F
i
g
u
r
e
3
s
h
o
ws
t
h
e
p
r
o
o
f
o
f
s
u
c
h
s
t
a
te
m
e
n
t
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
A
lg
o
r
ith
m
p
erfo
r
ma
n
ce
co
mp
a
r
is
o
n
fo
r
ea
r
th
q
u
a
ke
s
ig
n
a
l reco
g
n
itio
n
…
(
Ha
p
s
o
r
o
A
g
u
n
g
N
u
g
r
o
h
o
)
2511
T
ab
le
4
.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
L
DA
alg
o
r
ith
m
S
martp
h
o
n
e
P
o
si
t
i
o
n
Tr
u
e
(
TP+TF)
F
a
l
se
(
F
P
+
F
N
)
A
c
c
u
r
a
c
y
(
%)
Tr
o
u
s
e
r
P
o
c
k
e
t
1
9
0
0
6
4
5
7
4
.
6
7
S
h
i
r
t
P
o
c
k
e
t
1
7
4
5
6
8
5
7
1
.
8
1
Fig
u
r
e
2
.
C
lu
s
ter
d
ata
o
f
lo
co
m
o
to
r
ac
tiv
ity
s
ig
n
al
a
n
d
ea
r
th
q
u
ak
e
s
ig
n
al
Fig
u
r
e
3
.
C
lu
s
ter
d
ata
o
f
n
o
n
lo
co
m
o
to
r
ac
tiv
ity
s
ig
n
al
3
.
3
.
Sig
na
l c
la
s
s
if
ica
t
io
n us
ing
s
up
po
rt
v
ec
t
o
r
m
a
chine
(
SVM
)
a
lg
o
rit
hm
S
V
M
a
l
g
o
r
i
t
h
m
u
s
e
s
h
y
p
e
r
p
l
a
n
e
t
o
c
l
a
s
s
i
f
y
s
i
g
n
a
l
c
l
a
s
s
e
s
.
T
y
p
e
s
o
f
S
V
M
a
l
g
o
r
i
t
h
m
s
t
e
s
t
e
d
i
n
c
l
u
d
e
l
i
n
e
a
r
S
V
M
,
q
u
a
d
r
a
t
i
c
S
V
M
,
c
u
b
i
c
S
V
M
,
f
i
n
e
S
V
M
,
m
e
d
i
u
m
S
V
M
a
n
d
c
o
a
r
s
e
S
V
M
.
T
h
e
s
e
t
y
p
e
s
a
r
e
o
b
t
a
i
n
e
d
b
a
s
e
d
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
18
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
2
5
0
5
-
2516
2512
d
i
f
f
e
r
e
n
t
t
y
p
e
s
o
f
h
y
p
e
r
p
l
a
n
e
.
Q
u
a
d
r
a
t
i
c
S
V
M
a
n
d
c
u
b
i
c
S
V
M
u
s
e
p
o
l
y
n
o
m
i
a
l
k
e
r
n
e
l
s
.
T
h
i
s
k
e
r
n
e
l
p
r
o
j
e
c
t
s
h
y
p
e
r
p
l
a
n
e
f
i
e
l
d
s
w
i
t
h
n
o
n
l
i
n
e
a
r
f
u
n
c
t
i
o
n
s
i
n
t
h
r
e
e
-
d
i
m
e
n
s
i
o
n
a
l
s
p
a
c
e
.
Q
u
a
d
r
a
t
i
c
S
V
M
u
s
e
s
p
o
l
y
n
o
m
i
a
l
p
o
w
e
r
o
f
2
,
w
h
i
l
e
c
u
b
i
c
S
V
M
h
a
s
p
o
l
y
n
o
m
i
a
l
p
o
w
e
r
o
f
3
.
T
h
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
r
e
s
u
l
t
s
o
f
S
V
M
a
l
g
o
r
i
t
h
m
w
i
t
h
p
o
l
y
n
o
m
i
a
l
k
e
r
n
e
l
r
e
p
o
r
t
g
o
o
d
a
c
c
u
r
a
c
y
,
w
h
i
c
h
i
s
h
i
g
h
e
r
t
h
a
n
8
0
%
.
P
o
l
y
n
o
m
i
a
l
k
e
r
n
e
l
s
a
r
e
d
e
s
i
g
n
e
d
f
o
r
n
o
n
l
i
n
e
a
r
d
a
t
a
a
n
d
m
a
d
e
h
y
p
e
r
p
l
a
n
e
t
o
b
e
f
l
e
x
i
b
l
e
i
n
s
e
p
a
r
a
t
i
n
g
b
e
t
w
e
e
n
c
l
a
s
s
e
s
o
f
a
c
t
i
v
i
t
y
s
i
g
n
a
l
d
a
t
a
,
t
h
e
r
e
f
o
r
e
t
h
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
a
c
c
u
r
a
c
y
i
s
r
e
l
a
t
i
v
e
l
y
h
i
g
h
.
F
i
n
e
S
V
M
,
m
e
d
i
u
m
S
V
M
a
n
d
c
o
a
r
s
e
S
V
M
u
s
e
g
a
u
s
s
i
a
n
k
e
r
n
e
l
s
w
i
t
h
t
i
e
r
e
d
k
e
r
n
e
l
s
c
a
l
e
v
a
l
u
e
s
.
K
e
r
n
e
l
s
c
a
l
e
t
y
p
e
f
i
n
e
S
V
M
i
s
2
.
9
;
M
e
d
i
u
m
S
V
M
t
y
p
e
i
s
9
.
1
;
a
n
d
C
o
a
r
s
e
S
V
M
t
y
p
e
i
s
3
6
.
K
e
r
n
e
l
s
c
a
l
e
i
s
a
m
u
l
t
i
p
l
i
e
r
f
a
c
t
o
r
i
n
t
h
e
G
a
u
s
s
i
a
n
k
e
r
n
e
l
.
A
n
i
n
c
r
e
a
s
e
i
n
t
h
e
v
a
l
u
e
o
f
t
h
e
k
e
r
n
e
l
s
c
a
l
e
g
e
n
e
r
a
l
l
y
c
a
u
s
e
s
a
d
e
c
r
e
a
s
e
i
n
t
h
e
a
c
c
u
r
a
c
y
o
f
t
h
e
G
a
u
s
s
i
a
n
t
y
p
e
S
V
M
a
l
g
o
r
i
t
h
m
a
s
s
h
o
w
n
i
n
T
a
b
l
e
5
,
b
o
t
h
f
o
r
t
h
e
l
o
c
a
t
i
o
n
i
n
t
h
e
t
r
o
u
s
e
r
p
o
c
k
e
t
a
n
d
s
h
i
r
t
p
o
c
k
e
t
.
T
h
e
i
n
c
r
e
a
s
e
i
n
k
e
r
n
e
l
s
c
a
l
e
d
e
c
r
e
s
e
s
t
he
h
y
p
e
r
p
l
a
n
e
m
a
r
g
i
n
s
,
t
h
e
r
e
f
o
r
e
t
h
e
c
l
a
s
s
i
f
i
c
a
t
i
o
n
b
e
t
w
e
e
n
c
l
a
s
s
e
s
o
f
a
c
t
i
v
i
t
y
d
a
t
a
b
e
c
o
m
e
s
m
o
r
e
a
m
b
i
g
u
o
u
s
.
T
h
e
c
o
n
f
u
s
i
o
n
i
n
c
l
a
s
s
i
f
i
c
a
t
i
o
n
r
e
s
u
l
t
s
i
n
s
u
b
o
p
t
i
m
a
l
a
c
c
u
r
a
c
y
.
L
i
n
e
a
r
S
V
M
d
o
e
s
n
o
t
u
t
i
l
i
z
e
t
h
e
k
e
r
n
e
l
b
e
c
a
u
s
e
i
t
c
o
n
s
i
d
e
r
s
t
h
e
a
c
t
i
v
i
t
y
s
i
g
n
a
l
d
a
t
a
a
s
l
i
n
e
a
r
l
y
c
o
r
r
e
l
a
t
e
d
d
a
t
a
.
S
V
M
L
i
n
e
a
r
a
l
g
o
r
i
t
h
m
i
s
f
o
r
m
e
d
i
n
t
h
e
f
o
r
m
o
f
l
i
n
e
a
r
v
e
c
t
o
r
i
n
t
w
o
-
d
i
m
e
n
s
i
o
n
a
l
s
p
a
c
e
.
A
c
t
i
v
i
t
y
s
i
g
n
a
l
d
a
t
a
i
s
n
o
n
l
i
n
e
a
r
d
a
t
a
,
t
h
e
r
e
f
o
r
e
t
h
e
re
s
u
l
t
s
o
f
l
i
n
e
a
r
S
V
M
c
l
a
s
s
i
f
i
c
a
t
i
o
n
s
h
o
w
l
o
w
e
r
a
c
c
u
r
a
c
y
c
o
m
p
a
r
e
d
t
o
o
t
h
e
r
t
y
p
e
s
o
f
S
V
M
a
l
g
o
r
i
t
h
m
,
e
x
c
e
p
t
C
o
a
r
s
e
S
V
M
.
F
i
g
u
r
e
4
s
h
o
w
s
a
c
l
u
s
t
e
r
o
f
a
c
t
i
v
i
t
y
s
i
g
n
a
l
d
a
t
a
i
n
t
h
e
t
i
m
e
d
o
m
a
i
n
f
e
a
t
u
r
e
.
F
i
g
u
r
e
5
s
h
o
w
s
a
c
l
u
s
t
e
r
o
f
a
c
t
i
v
i
t
y
s
i
g
n
a
l
d
a
t
a
i
n
t
h
e
f
r
e
q
u
e
n
c
y
d
o
m
a
i
n
f
e
a
t
u
r
e
.
B
o
t
h
f
i
g
u
r
e
s
p
r
o
v
e
t
h
a
t
a
c
t
i
v
i
t
y
s
i
g
n
a
l
d
a
t
a
i
s
d
i
f
f
i
c
u
l
t
t
o
c
l
a
s
s
i
f
y
u
s
i
n
g
l
i
n
e
a
r
f
u
n
c
t
i
o
n
s
,
b
e
c
a
u
s
e
t
h
e
y
o
v
e
r
l
a
p
i
n
t
h
e
s
a
m
e
p
l
o
t
a
r
e
a
.
T
ab
le
5
.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
SVM
alg
o
r
ith
m
S
martp
h
o
n
e
P
o
si
t
i
o
n
Ty
p
e
o
f
S
V
M
Tr
u
e
(
TP+TF)
F
a
l
se
(
F
P
+
F
N
)
A
c
c
u
r
a
c
y
(
%)
Tr
o
u
s
e
r
P
o
c
k
e
t
Li
n
e
a
r
1
8
8
7
6
5
8
74
.
14
Q
u
a
d
r
a
t
i
c
2
4
3
5
1
1
0
95
.
67
C
u
b
i
c
2
2
3
3
3
1
2
87
.
74
F
i
n
e
2
3
6
7
1
8
1
92
.
89
M
e
d
i
u
m
2
0
8
4
4
9
6
80
.
77
C
o
a
r
se
1
7
8
5
7
5
9
70
.
16
S
h
i
r
t
P
o
c
k
e
t
Li
n
e
a
r
1
7
2
7
7
0
3
71
.
07
Q
u
a
d
r
a
t
i
c
2
1
6
8
2
6
2
89
.
22
C
u
b
i
c
2
3
8
0
50
97
.
94
F
i
n
e
2
2
3
2
1
9
8
91
.
85
M
e
d
i
u
m
1
8
7
8
5
5
2
77
.
28
C
o
a
r
se
1
5
8
8
8
4
2
65
.
35
Fig
u
r
e
4
.
C
lu
s
ter
d
ata
o
f
ac
tiv
i
ty
ac
ce
ler
atio
n
s
ig
n
al
in
tim
e
d
o
m
ain
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
A
lg
o
r
ith
m
p
erfo
r
ma
n
ce
co
mp
a
r
is
o
n
fo
r
ea
r
th
q
u
a
ke
s
ig
n
a
l reco
g
n
itio
n
…
(
Ha
p
s
o
r
o
A
g
u
n
g
N
u
g
r
o
h
o
)
2513
Fig
u
r
e
5
.
C
lu
s
ter
d
ata
o
f
ac
tiv
i
ty
ac
ce
ler
atio
n
s
ig
n
al
in
f
r
eq
u
en
cy
d
o
m
ain
3
.
4
.
Sig
na
l
cla
s
s
if
ica
t
io
n us
ing
K
-
nea
re
s
t
neig
hb
o
r
(
K
-
N
N)
a
lg
o
rit
hm
T
y
p
es
o
f
K
-
NN
alg
o
r
ith
m
s
test
ed
in
clu
d
e
f
in
e
K
-
NN,
Me
d
iu
m
K
-
NN,
C
o
ar
s
e
K
-
NN,
C
o
s
in
e
K
-
NN
an
d
C
u
b
ic
K
-
NN.
T
h
e
f
in
e
K
-
NN,
Me
d
iu
m
K
-
NN
an
d
C
o
ar
s
e
K
-
NN
alg
o
r
ith
m
s
a
r
e
d
is
tin
g
u
is
h
ed
b
ased
o
n
th
e
n
u
m
b
e
r
o
f
n
ea
r
est
n
eig
h
b
o
r
s
,
wh
ile
C
o
s
in
e
K
-
NN
an
d
C
u
b
ic
K
-
NN
ar
e
d
is
tin
g
u
is
h
ed
ac
co
r
d
in
g
to
th
e
p
r
o
v
is
io
n
s
o
f
th
e
ca
lcu
lati
o
n
o
f
th
e
d
is
tan
ce
to
t
h
e
n
ea
r
est
n
eig
h
b
o
r
.
T
a
b
le
6
s
h
o
ws
th
e
r
esu
lts
o
f
test
in
g
th
e
s
ig
n
al
d
ata
class
if
icatio
n
u
s
in
g
th
e
K
-
NN
alg
o
r
ith
m
.
F
in
e
K
-
NN
o
n
l
y
co
n
s
id
er
s
1
n
ea
r
est
n
eig
h
b
o
r
to
class
if
y
d
ata.
Me
d
iu
m
K
-
NN
co
n
s
id
er
s
th
e
1
0
clo
s
est
n
eig
h
b
o
r
s
,
wh
ile
C
o
ar
s
e
K
-
NN
co
n
s
id
er
s
1
0
0
clo
s
est
n
eig
h
b
o
r
s
in
a
d
ata
clu
s
ter
.
T
ab
le
6
d
em
o
n
s
tr
ates
th
at
th
e
in
cr
ea
s
e
o
f
th
e
n
u
m
b
er
o
f
n
ea
r
est
n
eig
h
b
o
r
s
as
a
co
n
s
id
er
atio
n
o
f
th
e
K
-
NN
alg
o
r
ith
m
ac
tu
ally
ca
u
s
es
a
d
ec
r
ea
s
e
in
th
e
lev
el
o
f
class
if
icatio
n
ac
cu
r
ac
y
.
T
h
e
n
u
m
b
er
o
f
n
ea
r
est
n
eig
h
b
o
r
s
as
p
r
e
d
icto
r
s
ac
tu
ally
a
d
d
s
to
th
e
lev
el
o
f
alg
o
r
it
h
m
am
b
ig
u
ity
in
d
eter
m
in
in
g
th
e
s
ig
n
al
in
p
u
t
class
.
No
n
lin
ea
r
HAR
d
ata
h
as
a
clu
s
ter
a
r
ea
with
o
v
er
lap
p
in
g
d
ata
cla
s
s
es,
th
e
r
ef
o
r
e
it
is
h
eter
o
g
en
e
o
u
s
.
T
h
e
c
r
iter
ia
to
in
cr
ea
s
e
th
e
n
u
m
b
er
o
f
n
ea
r
e
s
t
n
eig
h
b
o
r
s
ex
p
a
n
d
s
th
e
co
v
e
r
ag
e
o
f
th
e
clu
s
ter
ar
ea
,
ca
u
s
in
g
d
ata
class
es
to
b
ec
o
m
e
m
o
r
e
h
ete
r
o
g
e
n
eo
u
s
,
an
d
r
esu
ltin
g
in
co
n
f
u
s
io
n
o
v
er
th
e
r
esu
lts
o
f
class
if
icatio
n
p
r
ed
ictio
n
s
.
T
h
e
C
o
s
in
e
K
-
NN
alg
o
r
ith
m
u
s
es
co
s
in
e
m
etr
ic
d
is
tan
ce
to
d
et
er
m
in
e
th
e
d
is
tan
ce
to
th
e
n
ea
r
est
n
eig
h
b
o
r
,
w
h
ile
C
u
b
ic
K
-
NN
em
p
lo
y
s
cu
b
ic
m
etr
ic
d
is
tan
ce
.
T
h
e
ac
c
u
r
ac
y
o
f
th
e
s
e
two
d
is
tan
ce
r
u
les
ar
e
n
o
t
lo
wer
th
an
t
h
e
E
u
clid
ea
n
d
is
tan
ce
u
s
ed
b
y
f
i
n
e
K
-
NN
an
d
Me
d
iu
m
K
-
NN
to
class
if
y
s
ig
n
als.
C
o
s
in
e
K
-
NN
an
d
C
u
b
ic
K
-
NN
ac
cu
r
ac
y
lev
els ar
e
lo
we
r
th
an
f
in
e
K
-
NN
an
d
Me
d
iu
m
K
-
NN.
T
ab
le
6
.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
K
-
NN
alg
o
r
ith
m
S
martp
h
o
n
e
P
o
si
t
i
o
n
Ty
p
e
o
f
K
-
NN
Tr
u
e
(
TP+TF)
F
a
l
se
(
F
P
+
F
N
)
A
c
c
u
r
a
c
y
(
%)
Tr
o
u
s
e
r
P
o
c
k
e
t
2
5
4
3
2
99
.
92
9
9
,
9
2
1
9
3
6
6
0
9
76
.
07
7
6
,
0
7
1
7
4
2
8
0
3
68
.
45
6
8
,
4
5
1
9
1
1
6
3
4
75
.
09
7
5
,
0
9
1
9
0
3
6
4
2
74
.
77
7
4
,
7
7
S
h
i
r
t
P
o
c
k
e
t
2
4
2
0
10
99
.
59
9
9
,
5
9
1
7
8
1
6
4
9
73
.
29
7
3
,
2
9
1
6
3
1
7
9
9
67
.
12
6
7
,
1
2
1
7
7
1
6
5
9
72
.
88
7
2
,
8
8
1
7
2
9
7
0
1
71
.
15
7
1
,
1
5
3
.
5
.
Alg
o
rit
hm
perf
o
r
m
a
nce
co
m
pa
ra
t
io
n r
esu
lt
E
ac
h
alg
o
r
ith
m
h
as
a
d
if
f
er
e
n
t
lev
el
o
f
class
if
icatio
n
ac
cu
r
ac
y
.
T
h
e
alg
o
r
ith
m
s
elec
tio
n
cr
it
er
ia
d
o
n
o
t
o
n
ly
i
n
clu
d
e
th
e
lev
el
o
f
ac
c
u
r
ac
y
,
b
u
t
also
th
e
s
p
ee
d
o
f
d
ata
p
r
o
ce
s
s
in
g
an
d
m
em
o
r
y
ca
p
a
city
.
T
ab
le
7
s
h
o
ws
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
18
,
No
.
5
,
Octo
b
e
r
2
0
2
0
:
2
5
0
5
-
2516
2514
a
co
m
p
ar
is
o
n
o
f
all
class
if
ier
a
lg
o
r
ith
m
s
b
ased
o
n
th
e
s
e
cr
iter
ia.
T
h
e
ac
c
u
r
ac
y
o
f
t
h
e
alg
o
r
it
h
m
is
o
b
tain
e
d
f
r
o
m
th
e
av
er
ag
e
ac
c
u
r
ac
y
o
f
t
h
e
s
m
ar
tp
h
o
n
e
ac
tiv
ity
s
ig
n
al
clas
s
if
icatio
n
in
tr
o
u
s
er
p
o
ck
et
an
d
s
h
ir
t p
o
ck
et.
T
ab
le
7
.
T
h
e
p
er
f
o
r
m
a
n
ce
co
m
p
ar
is
o
n
o
f
th
e
alg
o
r
ith
m
s
A
l
g
o
r
i
t
h
m
A
c
c
u
r
a
c
y
(
%)
P
r
o
c
e
ss
i
n
g
Ti
m
e
(
se
c
o
n
d
s)
M
e
m
o
r
y
C
a
p
a
c
i
t
y
(
k
i
l
o
b
y
t
e
s)
S
i
mp
l
e
D
T
66
.
01
5
.
17
12
M
e
d
i
u
m D
T
71
.
77
5
.
27
22
C
o
m
p
l
e
x
D
T
83
.
93
6
.
91
54
LD
A
73
.
10
4
.
82
3
8
7
Li
n
e
a
r
S
V
M
72
.
61
1
4.
12
6
,
5
2
9
Q
u
a
d
r
a
t
i
c
S
V
M
92
.
44
21
.
97
21
,
213
C
u
b
i
c
S
V
M
92
.
84
25
.
57
16
,
564
F
i
n
e
S
V
M
92
.
37
81
.
2
65
,
411
M
e
d
i
u
m SV
M
79
.
03
32
.
05
29
,
087
C
o
a
r
se
S
V
M
67
.
76
33
.
63
29
,
641
F
i
n
e
K
-
NN
99
.
75
15
.
93
6
,
0
4
4
M
e
d
i
u
m
K
-
NN
74
.
70
13
.
36
6
,
0
4
4
C
o
a
r
se
K
-
NN
67
.
78
15
.
9
6
,
0
4
4
C
o
s
i
n
e
K
-
NN
73
.
98
13
.
24
6
,
0
4
4
C
u
b
i
c
K
-
NN
72
.
96
4
2
8
.
24
6
,
0
4
5
D
T
a
l
g
o
r
i
t
h
m
h
as
f
as
t
p
r
o
c
es
s
in
g
t
i
m
e
wi
t
h
t
h
e
s
m
a
ll
es
t
m
e
m
o
r
y
c
a
p
a
c
i
t
y
,
b
u
t
t
h
e
l
e
v
e
l
o
f
ac
c
u
r
a
c
y
i
s
l
o
w
e
r
c
o
m
p
a
r
e
d
t
o
t
h
e
f
i
n
e
K
-
NN
a
l
g
o
r
i
t
h
m
a
n
d
s
o
m
e
t
y
p
es
o
f
S
V
M
al
g
o
r
i
t
h
m
s
.
T
h
e
p
r
o
c
e
s
s
in
g
t
i
m
e
a
n
d
m
e
m
o
r
y
c
a
p
a
c
i
t
y
o
f
t
h
e
D
T
a
l
g
o
r
it
h
m
in
c
r
e
a
s
es
p
r
o
p
o
r
t
i
o
n
a
l
l
y
w
i
t
h
t
h
e
n
u
m
b
e
r
o
f
n
o
d
e
s
a
n
d
t
h
e
l
e
v
e
l
o
f
c
o
m
p
l
e
x
i
t
y
o
f
t
h
e
d
e
c
i
s
i
o
n
t
r
e
e
it
b
u
i
l
d
s
.
T
h
e
L
D
A
a
l
g
o
r
it
h
m
h
a
s
t
h
e
f
a
s
t
e
s
t
p
r
o
c
e
s
s
i
n
g
ti
m
e
wi
t
h
a
s
m
a
ll
m
e
m
o
r
y
c
a
p
a
c
i
t
y
,
b
u
t
t
h
e
l
e
v
e
l
o
f
a
c
c
u
r
a
c
y
i
s
l
o
w
e
r
th
a
n
t
h
e
a
v
e
r
a
g
e
a
c
c
u
r
a
c
y
o
f
D
T
,
S
V
M
a
n
d
K
-
N
N
al
g
o
r
i
t
h
m
s
.
S
V
M
a
l
g
o
r
i
t
h
m
h
as
t
h
e
l
a
r
g
e
s
t
m
e
m
o
r
y
c
a
p
a
c
it
y
w
it
h
a
l
o
n
g
e
r
p
r
o
c
e
s
s
i
n
g
t
i
m
e
c
o
m
p
a
r
e
d
t
o
t
h
e
D
T
a
l
g
o
r
it
h
m
,
L
D
A
a
n
d
s
o
m
e
K
-
N
N
.
T
h
e
d
e
s
i
g
n
o
f
h
y
p
e
r
p
l
a
n
e
i
n
t
h
e
S
V
M
a
l
g
o
r
i
t
h
m
p
r
o
d
u
c
e
s
g
r
ea
t
e
r
n
u
m
b
e
r
o
f
v
a
r
i
a
b
l
e
s
c
o
m
p
a
r
e
d
t
o
t
h
e
d
e
s
i
g
n
o
f
t
h
e
d
e
c
i
s
i
o
n
t
r
e
e
o
n
D
T
,
l
i
n
e
ar
l
i
n
e
s
o
n
t
h
e
L
D
A
a
n
d
c
a
lc
u
la
t
i
o
n
o
f
t
h
e
n
e
a
r
e
s
t
n
e
i
g
h
b
o
r
d
i
s
t
a
n
c
e
o
n
K
-
NN
.
T
h
e
n
u
m
b
e
r
o
f
v
a
r
i
a
b
l
e
s
a
f
f
e
c
ts
t
h
e
p
r
o
c
e
s
s
i
n
g
t
i
m
e
a
n
d
m
e
m
o
r
y
c
a
p
a
c
i
t
y
o
f
t
h
e
a
l
g
o
r
i
t
h
m
.
T
h
e
K
-
N
N
a
l
g
o
r
it
h
m
h
a
s
a
p
r
o
c
e
s
s
i
n
g
t
i
m
e
o
f
1
3
t
o
1
6
s
e
c
o
n
d
s
,
e
x
c
e
p
t
c
u
b
i
c
K
-
N
N
.
T
h
e
c
a
l
c
u
l
a
t
i
o
n
o
f
c
u
b
i
c
m
e
t
r
i
x
d
i
s
t
a
n
c
e
is
m
o
r
e
c
o
m
p
l
e
x
t
h
a
n
E
u
c
l
i
d
e
a
n
d
i
s
t
an
c
e
o
r
c
o
s
i
n
e
m
e
t
r
i
x
d
i
s
t
a
n
c
e
,
t
h
u
s
c
u
b
i
c
-
K
N
N
r
e
q
u
i
r
es
l
o
n
g
p
r
o
c
e
s
s
i
n
g
t
i
m
e.
T
h
e
a
v
e
r
a
g
e
m
e
m
o
r
y
c
a
p
a
c
i
t
y
o
f
t
h
e
K
-
N
N
al
g
o
r
i
t
h
m
is
6
,
0
4
4
k
i
l
o
b
y
t
e
s
.
T
h
is
c
a
p
ac
i
t
y
is
f
a
r
g
r
e
a
t
e
r
c
o
m
p
a
r
e
d
t
o
D
T
a
n
d
L
DA
,
b
u
t
s
m
a
ll
e
r
t
h
a
n
S
V
M
.
T
h
e
f
i
n
e
-
KN
N
al
g
o
r
i
t
h
m
h
a
s
t
h
e
h
i
g
h
e
s
t
a
c
c
u
r
ac
y
v
a
l
u
e
,
m
e
d
i
u
m
p
r
o
c
e
s
s
i
n
g
t
i
m
e
a
n
d
m
e
d
i
u
m
m
e
m
o
r
y
c
a
p
a
c
i
t
y
.
4.
CO
NCLU
SI
O
N
Fin
e
K
-
NN
alg
o
r
ith
m
h
as
th
e
h
ig
h
est lev
el
o
f
ac
cu
r
ac
y
in
th
e
class
if
icatio
n
o
f
h
u
m
an
ac
tiv
ity
s
ig
n
als
with
lo
wer
m
em
o
r
y
ca
p
ac
ity
a
n
d
s
h
o
r
ter
p
r
o
ce
s
s
in
g
tim
e.
T
h
e
n
u
m
b
er
o
f
fi
n
e
K
-
NN'
s
clo
s
est
n
eig
h
b
o
r
s
is
o
n
ly
o
n
e,
th
e
r
e
f
o
r
e
it
d
o
es
n
o
t
c
au
s
e
am
b
ig
u
ity
i
n
th
e
class
if
icatio
n
p
r
o
ce
s
s
.
T
h
e
f
in
e
K
-
NN
alg
o
r
ith
m
h
as
an
ac
cu
r
ac
y
r
ate
o
f
9
9
.
7
5
%
in
th
e
class
if
icatio
n
o
f
h
u
m
an
ac
ti
v
ity
s
ig
n
als
an
d
ea
r
th
q
u
ak
e
s
ig
n
als
with
a
m
em
o
r
y
ca
p
ac
ity
o
f
6
,
0
4
4
KB
an
d
a
p
r
o
ce
s
s
in
g
tim
e
o
f
1
5
.
9
3
s
ec
o
n
d
s
.
T
h
is
alg
o
r
it
h
m
h
as
t
h
e
b
e
s
t
class
if
ier
cr
iter
ia
co
m
p
ar
ed
to
DT
,
SVM
an
d
L
DA
alg
o
r
it
h
m
s
.
RE
F
E
R
E
NC
E
S
[
1
]
R
.
Ha
rris,
J.
M
a
j
o
r
,
“
Wav
e
s
o
f
d
e
stru
c
ti
o
n
in
th
e
Eas
t
I
n
d
ies
:
th
e
Wi
c
h
m
a
n
n
c
a
talo
g
u
e
o
f
e
a
rth
q
u
a
k
e
s
a
n
d
tsu
n
a
m
i
in
t
h
e
In
d
o
n
e
sia
n
re
g
i
o
n
fr
o
m
1
5
3
8
to
1
8
7
7
,”
Ge
o
l
S
o
c
L
o
n
d
o
n
,
v
o
l
.
4
4
1
,
n
o
.
1
,
p
p
.
9
-
46
,
2
0
1
7
[2
]
J.
F
.
Di
Leo
,
J.
W
o
o
k
e
y
,
J
.
O
.
S
.
Ha
m
m
o
n
d
,
e
t
a
l
.
,
“
M
a
n
tl
e
fl
o
w
in
re
g
i
o
n
s
o
f
c
o
m
p
lex
tec
to
n
ics
:
In
si
g
h
ts
fro
m
In
d
o
n
e
sia
,”
Ge
o
c
h
e
mistry
,
Ge
o
p
h
y
s Ge
o
sy
ste
ms
,
v
o
l.
13
,
n
o
.
12
,
2
0
1
2
.
[3
]
T.
Lay
,
H.
Ka
n
a
m
o
ri,
C.
J.
Am
m
o
n
,
e
t
a
l
.
,
“
De
p
t
h
‐v
a
r
y
in
g
r
u
p
tu
re
p
ro
p
e
rti
e
s o
f
su
b
d
u
c
ti
o
n
z
o
n
e
m
e
g
a
th
ru
st
fa
u
l
ts
,”
J
Ge
o
p
h
y
s R
e
s S
o
li
d
Ea
rt
h
,
v
o
l.
1
1
7
,
n
o
.
B4
,
2
0
1
2
.
[4
]
T.
M
.
Ra
sy
if,
S.
Ka
to
,
“
De
v
e
l
o
p
m
e
n
t
o
f
a
c
c
u
ra
te
tsu
n
a
m
i
e
stim
a
ted
ti
m
e
s
o
f
a
rriv
a
l
fo
r
tsu
n
a
m
i
-
p
ro
n
e
c
it
ies
in
Ac
e
h
,
In
d
o
n
e
sia
,”
In
t
J
Disa
ste
r R
isk
Re
d
u
c
t.
,
v
o
l.
1
4
,
p
p
.
4
0
3
-
4
10
,
2
0
1
5
.
[5
]
BM
KG
,
“
Law
3
1
Y
e
a
r
2
0
0
9
o
f
In
d
o
n
e
sia
n
Re
p
u
b
li
c
,
”
Ja
k
a
rta:
S
e
k
r
e
taria
t
Ne
g
a
ra
,
2
0
0
9
.
[6
]
M
.
D
.
Ko
h
ler,
T
.
H
.
He
a
to
n
,
M
.
H.
Ch
e
n
g
,
“
Th
e
Co
m
m
u
n
it
y
S
e
ism
ic
Ne
two
rk
a
n
d
Q
u
a
k
e
-
Ca
tch
e
r
Ne
t
wo
rk
:
En
a
b
li
n
g
stru
c
tu
ra
l
h
e
a
lt
h
m
o
n
it
o
ri
n
g
th
r
o
u
g
h
in
str
u
m
e
n
tatio
n
b
y
c
o
m
m
u
n
it
y
p
a
rt
icip
a
n
ts
,”
S
e
n
so
rs
a
n
d
S
ma
rt
S
tru
c
t
u
re
s
T
e
c
h
n
o
l
o
g
ies
fo
r
Civil,
M
e
c
h
a
n
i
c
a
l,
a
n
d
Aer
o
sp
a
c
e
S
y
ste
ms
2
0
1
3
,
In
ter
n
a
t
io
n
a
l
S
o
c
iety
f
o
r
Op
ti
c
s
a
n
d
Ph
o
to
n
ics
,
p
p
.
8
6
9
2
3
X,
2
0
1
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.