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
.
1
8
4
5
~
1
854
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
3
7
.
i
3
.
pp
1
8
4
5
-
1
8
5
4
1845
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
Ano
ma
ly
bas
ed det
ection
in
time se
ries da
ta o
n Io
T s
y
stems
using
statistica
l m
o
dels
M
o
un
a
B
o
ujr
a
d
1
,
M
o
ha
m
m
ed
Am
ine K
a
s
m
i
2
,
No
ura
O
u
er
di
1
,
Ya
s
s
er
L
a
m
lili
E
l Ma
z
o
ui Na
do
ri
3
1
A
r
i
t
h
met
i
c
,
S
c
i
e
n
t
i
f
i
c
C
o
m
p
u
t
i
n
g
a
n
d
t
h
e
i
r
A
p
p
l
i
c
a
t
i
o
n
s
La
b
o
r
a
t
o
r
y
(
LA
C
S
A
)
,
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
s (F
S
O
)
,
M
o
h
a
mm
e
d
F
i
r
st
U
n
i
v
e
r
s
i
t
y
(
U
M
P
)
,
O
u
j
d
a
,
M
o
r
o
c
c
o
2
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
s R
e
se
a
r
c
h
L
a
b
o
r
a
t
o
r
y
(
LA
R
I
)
,
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
s (F
S
O
)
,
M
o
h
a
mm
e
d
F
i
r
st
U
n
i
v
e
r
si
t
y
(
U
M
P
)
,
O
u
j
d
a
,
M
o
r
o
c
c
o
3
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
s
(FSO)
,
M
o
h
a
mm
e
d
F
i
r
st
U
n
i
v
e
r
si
t
y
(
U
M
P
)
,
O
u
j
d
a
,
M
o
r
o
c
c
o
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Mar
22
,
2
0
2
4
R
ev
is
ed
Oct
2
,
202
4
Acc
ep
ted
Oct
7
,
2
0
2
4
Th
e
in
ter
n
e
t
o
f
t
h
in
g
s
(Io
T)
h
a
s
b
e
c
o
m
e
a
re
a
l
re
v
o
lu
ti
o
n
t
h
a
t
r
e
p
re
se
n
ts
tec
h
n
o
l
o
g
ica
l
in
n
o
v
a
ti
o
n
i
n
a
ll
d
o
m
a
in
s
,
it
b
e
c
o
m
e
s
m
o
re
a
n
d
m
o
re
in
teg
ra
ted
in
t
o
h
u
m
a
n
a
c
ti
v
it
ies
s
tartin
g
fro
m
p
e
rso
n
a
l
n
e
e
d
s,
to
p
r
o
fe
ss
io
n
a
l
e
ra
s
in
c
lu
d
in
g
i
n
d
u
stry
,
lo
g
isti
c
s,
h
e
a
lt
h
c
a
re
.
Ye
t
th
is
tec
h
n
o
lo
g
y
d
i
d
n
’t
o
n
l
y
b
rin
g
a
d
v
a
n
ta
g
e
s
to
a
ll
in
d
u
stri
e
s,
it
a
lso
c
re
a
tes
n
e
w
c
h
a
ll
e
n
g
e
s
m
o
stl
y
se
c
u
rit
y
-
re
late
d
,
d
u
e
to
t
h
e
sp
e
c
ifi
c
a
ti
o
n
s
o
f
t
h
e
I
o
T
e
n
v
ir
o
n
m
e
n
t:
i
ts
h
e
tero
g
e
n
e
it
y
,
t
h
e
re
stricte
d
re
so
u
rc
e
s,
a
n
d
t
h
e
c
o
n
ti
n
u
o
u
s
e
n
o
rm
o
u
s
se
n
siti
v
e
d
a
ta
g
e
n
e
ra
ted
a
n
d
e
x
c
h
a
n
g
e
d
o
n
t
h
e
I
o
T
e
c
o
sy
ste
m
.
I
n
t
h
is
p
a
p
e
r,
we
p
ro
p
o
se
a
stu
d
y
o
f
sta
ti
stica
l
m
o
d
e
ls
(
a
u
t
o
re
g
re
ss
io
n
,
m
o
v
i
n
g
-
a
v
e
ra
g
e
,
a
u
to
re
g
re
ss
io
n
-
m
o
v
i
n
g
a
v
e
ra
g
e
,
a
u
to
re
g
re
ss
io
n
in
teg
ra
ted
m
o
v
i
n
g
a
v
e
ra
g
e
,
se
a
so
n
a
l
a
u
to
re
g
re
ss
io
n
i
n
teg
ra
t
e
d
m
o
v
i
n
g
a
v
e
ra
g
e
)
to
b
u
il
d
a
n
a
n
o
m
a
ly
-
b
a
se
d
d
e
tec
ti
o
n
m
o
d
e
l
fo
r
ti
m
e
s
se
ries
d
a
ta,
to
d
e
tec
t
a
b
n
o
rm
a
l
b
e
h
a
v
io
r
th
a
t
c
a
n
b
e
e
x
p
lain
e
d
b
y
a
se
n
so
r
fa
il
u
re
,
o
r
a
c
o
m
p
ro
m
ise
d
se
n
so
r.
T
h
e
p
ro
p
o
se
d
a
n
o
m
a
ly
-
b
a
se
d
d
e
tec
ti
o
n
re
li
e
s
o
n
d
e
fi
n
in
g
t
h
e
d
a
ta
b
e
h
a
v
i
o
r
a
n
d
c
re
a
ti
n
g
a
p
ro
fil
e
o
n
t
h
e
a
ss
u
m
e
d
n
o
rm
a
l
sta
te,
th
e
c
re
a
ted
p
ro
fil
e
will
b
e
u
se
d
a
s
k
n
o
wle
d
g
e
t
o
p
re
d
ict
f
u
tu
re
v
a
lu
e
s
to
wh
ich
re
a
l
re
c
o
rd
s
will
b
e
c
o
m
p
a
re
d
,
a
n
y
d
e
v
iatio
n
fro
m
th
e
p
re
d
icte
d
d
a
ta
will
b
e
c
o
n
si
d
e
re
d
a
s
a
b
n
o
rm
a
l,
th
a
t
in
d
ica
tes
a
n
a
n
o
m
a
ly
h
a
s
o
c
c
u
rre
d
o
n
th
e
se
n
so
r
o
r
th
e
e
x
c
h
a
n
g
e
d
d
a
ta.
Th
e
p
ro
p
o
se
d
a
p
p
ro
a
c
h
will
h
e
l
p
imp
ro
v
e
a
c
c
u
ra
c
y
,
re
li
a
b
il
it
y
,
tr
u
st
wo
rth
i
n
e
ss
,
a
n
d
d
a
ta i
n
teg
ri
ty
.
K
ey
w
o
r
d
s
:
An
o
m
aly
d
etec
tio
n
I
n
teg
r
ity
I
o
T
Secu
r
ity
Statis
t
ical
m
o
d
els
T
r
u
s
two
r
th
in
ess
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
:
Mo
u
n
a
B
o
u
jr
a
d
Ar
ith
m
etic,
Scien
tific
C
o
m
p
u
t
in
g
an
d
th
eir
Ap
p
licatio
n
s
L
a
b
o
r
ato
r
y
(
L
AC
SA)
,
Facu
lty
o
f
Scien
ce
s
(
FS
O)
Mo
h
am
m
ed
First Un
iv
er
s
ity
(
UM
P)
Ou
jd
a,
6
0
0
0
0
,
Mo
r
o
cc
o
E
m
ail: m
o
u
n
a.
b
o
u
jr
a
d
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
I
n
th
is
ar
ticle
we
will
p
r
o
p
o
s
e
a
n
ew
an
o
m
aly
-
b
ased
d
etec
tio
n
s
y
s
tem
in
tim
e
s
er
ies
d
ata
o
n
I
o
T
s
y
s
tem
s
,
th
e
n
o
v
elty
lies
in
u
s
in
g
s
tatis
tical
tech
n
iq
u
es
n
o
t
o
n
ly
to
p
r
ed
ict
b
u
t
also
to
d
etec
t
an
o
m
alies
an
d
im
p
r
o
v
e
s
y
s
tem
in
teg
r
ity
.
Ou
r
ch
o
ice
is
ju
s
tifie
d
b
y
th
e
s
p
ec
if
icatio
n
o
f
th
e
I
o
T
s
y
s
te
m
[
1
]
its
elf
wh
ich
ca
n
b
e
d
ef
in
ed
as
lo
ca
lly
c
o
n
n
ec
te
d
o
b
jects
co
n
f
ig
u
r
ed
t
o
wo
r
k
in
a
v
e
r
y
s
p
ec
if
ic
way
d
ep
e
n
d
in
g
o
n
tim
e,
f
o
r
ex
a
m
p
le
wh
e
n
o
b
s
er
v
in
g
th
e
p
er
ce
p
tio
n
la
y
er
we
k
n
o
w
t
h
at
we
h
a
v
e
s
en
s
o
r
s
t
h
at
ar
e
r
ec
o
r
d
in
g
/r
e
p
o
r
tin
g
s
p
ec
if
ic
d
ata
[
2
]
o
n
p
r
ed
ef
in
ed
tim
e
in
te
r
v
al
d
ep
en
d
in
g
o
n
th
e
d
ata
s
en
d
(
o
n
ce
e
v
er
y
s
ec
o
n
d
,
o
n
ce
e
v
er
y
m
in
u
te,
h
o
u
r
ly
,
d
aily
,
wee
k
l
y
)
,
f
o
r
th
at
tim
e
s
er
ies
an
o
m
aly
d
etec
tio
n
ca
n
b
e
ap
p
lied
f
o
r
th
e
d
ata
s
en
t
as
we
ll
as th
e
n
etwo
r
k
tr
af
f
ic
g
e
n
er
ate
d
b
y
th
e
tim
e
o
f
s
en
d
in
g
t
h
e
d
ata
an
d
also
b
y
o
th
er
tim
e,
f
o
r
ex
am
p
le,
if
we
ad
d
p
ar
am
eter
s
to
th
e
s
en
s
o
r
to
s
en
d
r
ec
o
r
d
s
ea
ch
h
o
u
r
it
will
b
e
weir
d
if
we
d
etec
ted
a
n
etw
o
r
k
tr
af
f
ic
o
u
t
o
f
th
e
tim
e
d
ef
in
ed
to
s
en
d
r
ec
o
r
d
s
[
3
]
.
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
:
1
845
-
1
8
5
4
1846
T
h
er
e
ar
e
s
o
m
an
y
t
ec
h
n
iq
u
es
[
4
]
th
at
ca
n
b
e
u
s
ed
f
o
r
an
o
m
aly
d
etec
tio
n
b
u
t
s
o
m
e
f
its
p
er
f
ec
tly
t
o
o
u
r
s
tu
d
y
wh
ich
is
tim
e
s
er
ies
an
aly
s
is
th
at
r
elie
s
o
n
s
tatis
t
ical
m
o
d
els
[
5
]
th
at
ca
n
b
e
ap
p
lied
to
d
etec
t
an
d
p
r
e
d
ict
th
e
b
eh
a
v
io
r
o
f
th
e
ti
m
es
s
er
ies
d
ataset.
I
n
tim
e
s
er
ies
ea
ch
p
o
in
t
ca
n
a
f
f
ec
t
th
e
n
ex
t
o
n
e
p
er
io
d
ically
s
p
ea
k
in
g
,
s
o
th
at
b
ec
o
m
es
a
tr
en
d
o
r
ev
e
n
a
cy
clic
b
eh
a
v
io
r
th
e
an
o
m
aly
is
r
aised
wh
en
ac
tu
al
d
ata
is
d
ev
iatin
g
f
r
o
m
t
h
e
p
r
e
d
icted
o
n
e,
b
y
a
v
e
r
y
lo
w
o
r
h
ig
h
d
if
f
e
r
en
ce
.
T
h
e
I
o
T
s
y
s
tem
allo
ws
u
s
to
p
er
f
o
r
m
tim
e
s
er
ies
[
6
]
an
aly
s
is
f
o
r
an
o
m
al
y
d
etec
tio
n
,
it
is
th
e
b
est
en
v
i
r
o
n
m
en
t
to
d
o
s
o
d
u
e
to
its
s
p
ec
if
icatio
n
th
at
f
its
p
er
f
ec
tly
to
t
h
e
r
eq
u
ir
em
en
ts
n
ee
d
ed
to
a
p
p
ly
tim
e
s
er
ies an
a
ly
s
is
o
r
an
o
m
aly
d
etec
tio
n
[
7
]
.
2.
O
B
J
E
CT
I
V
E
O
F
T
H
E
R
E
S
E
ARCH
AND
CO
N
T
R
I
B
U
T
I
O
N
T
h
e
o
b
jectiv
e
o
f
th
is
r
esear
ch
is
to
s
u
d
y
s
tatis
tical
m
o
d
els,
an
d
th
ei
r
p
e
r
f
o
r
m
an
ce
in
a
n
o
m
aly
-
b
ased
d
etec
tio
n
in
I
o
T
d
ata,
t
h
e
ad
d
r
ess
ed
d
ata
is
th
e
o
n
e
co
llected
o
r
tr
an
s
f
er
e
d
b
y
th
e
I
o
T
s
en
s
o
r
s
,
w
e
to
o
k
in
to
co
n
s
id
er
atio
n
th
at
th
is
d
ata
is
a
tim
e
s
er
ies
d
ata
s
et,
th
e
d
ep
lo
y
ed
s
en
s
o
r
s
co
llect
an
d
tr
an
s
f
er
d
ata
at
d
if
f
er
en
t
tim
es,
d
ef
in
ed
b
ased
o
n
th
e
n
e
ed
s
o
f
th
e
s
y
s
tem
,
Ho
wev
er
an
o
m
alies m
ay
o
cc
u
r
e
o
n
th
is
d
ata,
d
u
r
in
g
th
e
tim
e
o
f
co
llectio
n
o
r
tr
an
s
f
er
,
wh
cih
o
r
ig
in
e
b
y
a
v
u
ln
er
ab
ilit
y
o
r
tech
n
ical
ca
u
s
e
s
u
ch
as
s
e
s
o
n
r
d
y
s
f
u
n
ctio
n
.
Statis
t
ical
m
o
d
els ar
e
d
esig
n
e
d
to
p
er
f
o
r
m
e
o
n
tim
e
s
er
ies d
atasets
,
b
u
t in
th
e
en
v
ir
o
n
em
e
n
t o
f
I
o
T
th
e
m
o
d
els
n
ee
d
s
to
b
e
test
ed
.
I
n
th
is
w
o
r
k
we
p
r
o
p
o
s
e
a
liter
atu
r
e
r
e
v
iew
o
n
th
e
ex
is
tin
g
c
u
r
r
e
n
t
wo
r
k
r
elate
d
to
th
e
r
esear
ch
,
th
en
an
o
v
er
v
iew
o
f
an
o
m
al
y
-
b
ased
d
etec
tio
n
an
d
s
tatis
tical
m
o
d
els,
af
ted
th
at
we
d
ef
in
e
o
u
r
p
r
o
p
o
s
ed
m
o
d
el
f
o
r
a
n
o
m
aly
-
b
ased
d
etec
tio
n
in
tim
e
s
er
ies
d
ataset,
b
ased
o
n
th
e
co
m
p
ar
ativ
e
s
tu
d
y
we
co
n
d
u
ct
o
n
th
e
ch
o
o
s
ed
s
tatis
tical
m
o
d
els,
th
e
te
s
ts
wer
e
v
alid
ated
u
s
in
g
an
I
o
T
d
a
taset
f
r
o
m
Kag
g
le
p
latef
o
r
m
e.
3.
RE
L
AT
E
D
WO
RK
I
n
2
0
1
6
,
J
ib
in
an
d
J
ian
g
[
8
]
,
im
p
r
o
v
e
d
AR
I
MA
b
ased
an
o
m
aly
d
etec
tio
n
alg
o
r
ith
m
f
o
r
wir
eless
s
en
s
o
r
n
etwo
r
k
s
,
th
e
im
p
r
o
v
e
m
en
t
was
ap
p
lied
to
th
e
s
tr
u
c
tu
r
e
o
f
th
e
AR
I
MA
m
o
d
el,
f
i
r
s
t
u
s
in
g
a
s
lid
in
g
win
d
o
w
to
d
eter
m
in
e
h
is
to
r
i
ca
l
d
ata
f
o
r
m
o
d
elin
g
,
s
ec
o
n
d
u
p
d
atin
g
th
e
m
o
d
el
a
f
ter
ea
ch
tim
e
s
lid
in
g
win
d
o
w,
an
d
last
m
ak
in
g
tr
af
f
ic
p
r
ed
ictio
n
b
y
s
h
o
r
t
s
tep
e
x
p
o
n
e
n
tial,
th
e
m
o
d
el
was
te
s
ted
o
n
r
ea
l
W
SN
n
etwo
r
k
tr
af
f
ic
u
s
in
g
s
im
u
lati
o
n
o
n
MA
T
L
AB
,
th
e
r
esu
lts
s
h
o
w
th
at
d
esp
ite
th
e
in
c
r
ea
s
e
o
f
f
alse
p
o
s
itiv
e
r
ate
o
n
th
e
p
r
o
p
o
s
ed
m
o
d
el,
it
s
till
g
iv
es
b
etter
r
esu
lts
b
y
d
ec
r
ea
s
in
g
th
e
r
ate
o
f
tr
u
e
n
eg
ativ
es
an
d
i
n
cr
ea
s
in
g
t
h
e
r
ate
o
f
tr
u
e
p
o
s
itiv
e.
I
n
2
0
1
8
,
Gian
n
o
n
i
et
a
l.
[
9
]
d
ev
elo
p
e
d
an
an
o
m
al
y
d
etec
t
io
n
alg
o
r
ith
m
f
o
r
I
o
T
tim
es
s
er
ies
d
ata,
m
u
ltip
le
alg
o
r
ith
m
s
wer
e
ap
p
l
ied
to
th
e
d
ata
to
d
etec
t
an
o
m
alies:
r
u
n
n
in
g
av
er
a
g
e
lo
w
-
h
i
g
h
p
ass
f
ilter
:
m
ak
e
u
s
e
o
f
th
e
r
u
n
n
in
g
av
er
a
g
e
co
m
p
u
ted
b
ased
o
n
th
e
last
W
a
cq
u
is
itio
n
s
(
wh
er
e
W
is
a
s
lid
in
g
win
d
o
w
o
f
f
ix
e
d
s
ize)
,
as
a
m
ea
n
s
to
id
en
tif
y
an
o
m
alies.
Un
iv
ar
iate
Gau
s
s
ian
p
r
ed
icto
r
:
th
e
m
o
d
el
c
lass
if
ies
ea
ch
n
ew
ac
q
u
is
itio
n
x
i
b
ased
o
n
th
e
p
r
o
b
ab
ilit
y
o
f
t
h
at
v
alu
e
in
t
h
e
d
is
tr
ib
u
tio
n
p
(
x
i
)
.
A
t
h
r
esh
o
l
d
h
as
to
b
e
s
et
t
o
d
ec
id
e
wh
ich
p
r
o
b
ab
ilit
ies
ar
e
to
o
lo
w
to
b
e
c
o
n
s
id
er
ed
n
o
n
-
an
o
m
alo
u
s
.
Seaso
n
al
E
SD
alg
o
r
ith
m
:
s
tatis
tical
-
b
ased
m
e
th
o
d
,
ap
p
lied
o
n
ly
o
n
tim
e
s
er
ies th
at
h
av
e
th
eir
r
esi
d
u
al
co
m
p
o
n
e
n
t sy
m
m
etr
ically
d
is
tr
ib
u
ted
.
I
n
2
0
2
0
,
B
r
ae
i
an
d
W
ag
n
e
r
[
1
0
]
p
r
esen
t
ed
in
th
eir
r
esear
ch
a
s
u
r
v
ey
o
n
th
e
s
tate
o
f
t
h
e
ar
t
o
n
d
if
f
er
en
t
tec
h
n
iq
u
es
a
n
d
m
et
h
o
d
s
u
s
ed
f
o
r
an
o
m
aly
d
etec
tio
n
in
u
n
iv
ar
iate
tim
e
-
s
er
ies
d
ata,
th
e
r
esear
ch
er
s
p
er
f
o
r
m
an
e
x
p
er
im
e
n
t
u
s
in
g
f
iv
e
d
if
f
e
r
en
t
u
n
iv
ar
iate
tim
e
s
er
ies
d
atasets
u
s
in
g
b
o
th
s
tat
i
s
tical
an
d
class
ica
l
m
ac
h
in
e
lear
n
in
g
(
AR
,
MA
,
S
E
S)
an
d
d
ee
p
lear
n
in
g
ap
p
r
o
a
ch
es
(
C
NN,
L
STM
,
G
R
U)
,
th
e
r
esu
lts
s
h
o
w
th
at
s
tatis
t
ical
tech
n
iq
u
es
p
er
f
o
r
m
b
etter
o
n
u
n
iv
a
r
iate
tim
e
s
er
ies
with
m
o
r
e
ac
cu
r
ate
d
ete
ctio
n
o
n
p
o
in
t
a
n
d
co
llectiv
e
an
o
m
alies a
n
d
less
co
m
p
u
tatio
n
tim
es.
I
n
2
0
2
0
E
r
a
n
et
a
l
.
[
1
1
]
r
ev
ie
wed
in
th
eir
p
ap
er
a
n
o
m
aly
d
etec
tio
n
o
n
s
en
s
o
r
s
,
o
n
d
if
f
er
en
t
lev
els,
co
m
p
ar
in
g
th
e
tech
n
iq
u
es
u
s
ed
to
d
etec
t
an
o
m
alies,
th
e
au
t
h
o
r
s
r
ev
ea
l
th
at
s
tatis
tical
tec
h
n
iq
u
es
d
o
n
’
t
wo
r
k
be
tter
o
n
m
u
ltiv
ar
iate
d
ata,
o
r
h
ig
h
d
im
e
n
s
io
n
al
d
atasets
,
co
m
p
ar
ed
to
m
ac
h
in
e
lear
n
in
g
te
ch
n
iq
u
es,
h
o
wev
er
,
th
e
s
tatis
tical
tech
n
iq
u
e
is
m
u
ch
ea
s
ier
to
im
p
lem
en
t a
n
d
c
o
m
p
u
tatio
n
ally
ef
f
icien
t.
I
n
2
0
2
2
Oser
et
al
.
[
1
2
]
p
r
o
p
o
s
ed
an
en
h
a
n
ce
d
v
er
s
io
n
o
f
SAFER
’
s
f
r
am
ewo
r
k
u
s
in
g
F
ac
eb
o
o
k
’
s
Pro
p
h
et
an
d
AR
I
MA
as
p
r
ed
ictio
n
m
o
d
els
an
d
s
im
p
l
e
m
o
v
in
g
av
e
r
ag
e
(
SMA
)
to
co
m
p
ar
e
th
e
p
r
ed
icte
d
r
esu
lts
,
th
e
p
r
o
p
o
s
ed
ap
p
r
o
a
c
h
ap
p
lied
to
v
u
ln
er
a
b
ilit
ies
p
a
tch
es
o
f
7
9
3
I
o
T
d
ev
ices
s
h
o
wed
h
ig
h
p
r
ed
ictio
n
r
ate
o
f
9
1
o
f
f
u
tu
r
e
r
is
k
s
.
I
n
2
0
2
2
Kalo
u
p
ts
o
g
lo
u
et
al
.
[
1
3
]
p
er
f
o
r
m
ed
a
tim
e
s
er
ies
f
o
r
ec
asti
n
g
u
s
in
g
b
o
th
s
tatis
tical
an
d
d
ee
p
lear
n
in
g
tech
n
iq
u
es,
ap
p
lied
t
o
n
atio
n
al
v
u
ln
er
a
b
ilit
ies
d
atab
ased
(
NVD)
f
o
r
d
if
f
er
e
n
t
s
o
f
twar
e
p
r
o
jects,
th
e
r
esu
lts
wer
e
v
er
y
clo
s
e
h
o
we
v
er
AR
I
MA
r
ea
ch
ed
b
etter
g
o
o
d
n
ess
o
f
f
it
lev
el
c
o
m
p
ar
e
d
to
o
th
e
r
u
s
ed
d
ee
p
lear
n
in
g
m
eth
o
d
s
.
I
n
2
0
2
2
Awa
n
g
et
al
.
[
1
4
]
p
r
o
p
o
s
ed
a
SAR
I
MA
-
b
ased
p
r
ed
ictio
n
m
o
d
el
to
h
el
p
ad
m
in
s
in
m
ak
in
g
a
d
ec
is
io
n
f
o
r
r
is
k
m
an
ag
e
m
en
t
,
th
e
r
esu
lts
r
eg
a
r
d
less
o
f
th
e
h
ig
h
r
ate
o
f
th
e
r
o
o
t
m
ea
n
s
q
u
ar
e
er
r
o
r
(
R
MSE
),
s
h
o
win
g
th
at
SAR
I
MA
is
a
g
o
o
d
m
o
d
el
to
f
o
r
ec
ast attac
k
s
an
d
th
r
ea
ts
in
th
e
f
u
tu
r
e.
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
n
o
ma
ly
b
a
s
ed
d
etec
tio
n
in
ti
me
s
eries
d
a
ta
o
n
I
o
T sys
tems
u
s
in
g
s
ta
tis
tica
l m
o
d
els
(
Mo
u
n
a
B
o
u
jr
a
d
)
1847
I
n
2
0
2
3
,
Sam
ar
ia
an
d
T
h
ak
k
ar
[
1
5
]
p
e
r
f
o
r
m
ed
a
co
m
p
r
eh
en
s
iv
e
s
u
r
v
ey
o
n
an
o
m
aly
d
etec
tio
n
alg
o
r
ith
m
s
,
ac
co
r
d
i
n
g
to
th
ei
r
r
esear
ch
,
s
tatis
tical
-
b
ased
a
lg
o
r
ith
m
s
ar
e
co
n
s
id
er
ed
v
er
y
p
o
wer
f
u
l
o
n
es
in
o
u
tlier
d
etec
tio
n
s
p
ec
ially
wh
e
n
ap
p
lied
o
n
ce
r
tain
ty
p
e
o
f
d
a
ta.
4.
ANO
M
A
L
Y
-
B
A
SE
D
D
E
T
E
CT
I
O
N
T
h
e
an
o
m
aly
-
b
ased
d
etec
tio
n
is
b
asically
ab
o
u
t
d
ef
i
n
in
g
th
e
d
ata
b
eh
av
i
o
r
a
n
d
cr
ea
tin
g
a
p
r
o
f
ile
o
r
a
m
o
d
el
o
n
th
e
ass
u
m
ed
n
o
r
m
al
s
tate
[
1
6
]
,
th
e
p
r
o
f
ile
cr
ea
te
d
will b
e
u
s
ed
as a
k
n
o
wled
g
e
to
wh
ich
r
ea
l r
ec
o
r
d
s
will
b
e
co
m
p
ar
e
d
an
y
d
ev
iati
o
n
f
r
o
m
th
at
p
r
o
f
ile
will
b
e
ac
ce
p
ted
as
ab
n
o
r
m
al
b
e
h
av
io
r
;
An
o
m
aly
d
etec
tio
n
b
ec
o
m
es
th
e
to
p
ic
o
f
th
e
h
o
u
r
s
in
ce
it
p
r
o
v
ed
its
p
er
f
o
r
m
an
ce
in
d
etec
tin
g
n
ew
attac
k
s
,
a
s
lo
n
g
as
th
e
attac
k
ca
u
s
es
a
d
ev
iatio
n
f
r
o
m
th
e
n
o
r
m
al
tr
af
f
ic
f
lo
w
o
r
d
ata
co
llected
.
Ho
wev
er
an
o
m
alie
s
d
o
n
’
t
n
ec
ess
ar
ily
in
d
ica
te
an
attac
k
o
r
th
r
ea
t,
a
b
n
o
r
m
al
b
eh
a
v
io
r
ca
n
h
av
e
s
ev
er
al
ca
u
s
es
s
u
ch
as:
s
y
s
tem
er
r
o
r
,
e
n
v
ir
o
n
m
en
t
ch
an
g
es,
n
ew
o
b
s
er
v
atio
n
s
.
Fo
r
th
at
r
ea
s
o
n
,
co
n
tr
a
d
icto
r
y
to
r
u
le
-
s
ig
n
atu
r
e
b
ased
[
1
7
]
an
o
m
aly
-
b
ased
d
etec
tio
n
is
k
n
o
w
n
f
o
r
its
h
ig
h
r
ate
o
f
f
alse
p
o
s
itiv
es
an
d
tr
u
e
n
eg
ativ
es
[
1
8
]
.
T
h
is
ca
n
le
ad
s
to
m
is
esti
m
atin
g
th
e
r
ea
l
d
an
g
er
,
an
d
th
e
r
ea
l
s
tate
o
f
th
e
s
y
s
tem
.
I
n
s
p
ite
o
f
th
at,
an
o
m
aly
is
s
till
th
e
b
est
way
to
d
etec
t
n
ew
attac
k
s
co
m
p
ar
ed
to
r
u
le
-
s
ig
n
a
tu
r
e
-
b
ased
i
n
tr
u
s
io
n
d
etec
tio
n
s
y
s
tem
s
,
th
at
r
ely
o
n
ly
o
n
th
e
ex
is
tin
g
s
ig
n
atu
r
es
in
th
eir
k
n
o
wled
g
e
b
ase.
T
o
b
u
ild
a
p
er
f
o
r
m
an
t
a
n
o
m
a
ly
-
b
ased
d
etec
tio
n
f
o
r
m
o
n
ito
r
in
g
we
f
ir
s
t
n
ee
d
to
d
ef
i
n
e
g
o
o
d
d
ata
wh
ich
is
th
e
m
ain
f
o
cu
s
ab
o
v
e
all,
th
en
we
ca
n
a
p
p
ly
th
e
d
if
f
er
en
t
e
x
is
tin
g
tech
n
iq
u
es
to
tr
ain
t
h
e
d
ata
an
d
cr
ea
te
th
e
p
r
o
f
ile
o
n
w
h
ich
w
e
will
b
ase
an
o
m
aly
d
etec
tio
n
,
Fig
u
r
e
1
s
h
o
ws
th
e
d
if
f
er
e
n
t
t
ec
h
n
iq
u
es
u
s
ed
f
o
r
in
tr
u
s
io
n
o
r
an
o
m
aly
d
etec
tio
n
ea
ch
o
n
e
ca
n
b
e
a
p
p
lied
d
i
f
f
er
en
tly
an
d
it
d
ep
en
d
s
o
n
t
h
e
ty
p
e
o
f
th
e
d
ata
its
elf
,
s
o
m
e
tech
n
iq
u
es c
o
u
l
d
p
er
f
o
r
m
b
etter
o
n
tim
e
s
er
ies d
ata
o
th
er
s
co
u
ld
g
iv
e
th
e
wo
r
s
t r
esu
lts
.
Fig
u
r
e
1
.
C
lass
if
icatio
n
o
f
I
D
S ty
p
es
4
.
1
.
T
im
e
s
er
ies da
t
a
T
im
e
s
er
ies
d
ata
[
1
9
]
is
a
v
er
y
im
p
o
r
tan
t
ter
m
in
m
o
n
ito
r
i
n
g
d
if
f
er
en
t
p
r
o
ce
s
s
es,
it
ca
n
b
e
d
ef
in
ed
as
a
s
er
ies
o
f
d
ata
p
o
in
ts
tak
en
at
d
if
f
er
en
t
tim
es,
it
allo
ws
t
r
ac
k
in
g
th
e
ch
a
n
g
es
o
r
th
e
m
o
v
em
en
t
o
f
a
v
er
y
s
p
ec
if
ic
n
u
m
er
ical
d
ata
p
o
in
t
o
v
er
tim
e,
th
e
tim
e
h
er
e
is
r
el
ev
an
t
to
t
h
e
d
ata
c
o
llected
,
it
is
a
r
eg
u
lar
i
n
ter
v
al
o
v
er
a
s
p
ec
if
ic
p
er
io
d
s
u
ch
as
h
o
u
r
ly
,
d
aily
,
wee
k
ly
o
r
ev
en
in
a
g
iv
en
p
er
s
o
n
alize
d
p
er
io
d
o
f
tim
e.
T
h
e
d
ata
co
llected
in
I
o
T
s
y
s
tem
s
[
2
0
]
v
ia
s
en
s
o
r
s
ca
n
b
e
d
ef
i
n
ed
t
h
r
o
w
tim
e
s
er
ies
d
ata
s
in
ce
t
h
e
s
en
s
o
r
s
co
llect
in
f
o
r
m
atio
n
ab
o
u
t
th
e
en
v
ir
o
n
m
en
t
o
n
a
g
iv
en
p
er
io
d
s
o
an
y
r
ec
o
r
d
s
g
i
v
en
b
y
a
n
y
s
e
n
s
o
r
ar
e
r
elate
d
to
a
s
p
ec
if
ic
m
o
m
en
t.
A
g
en
er
al
g
i
v
en
d
ataset
in
clu
d
in
g
tim
e
s
er
i
es d
ata
is
co
m
p
o
s
ed
o
f
th
r
ee
d
if
f
er
en
t p
atter
n
s
:
-
No
r
m
al:
it is
th
e
d
ata
h
o
w
it is
s
u
p
p
o
s
ed
to
b
e,
th
e
c
o
r
r
ec
t i
n
f
o
r
m
atio
n
co
llected
o
r
s
to
r
ed
.
-
An
o
m
alies:
ab
n
o
r
m
alities
,
o
u
tlier
s
,
o
r
d
ev
ian
ts
(
a
v
alu
e
th
at
d
if
f
er
s
co
n
s
id
er
ab
ly
f
r
o
m
t
h
e
o
t
h
er
o
b
s
er
v
atio
n
s
)
,
t
h
er
e
ar
e
m
an
y
r
ea
s
o
n
s
f
o
r
an
o
m
alies
s
u
ch
as
m
alicio
u
s
ac
tio
n
s
,
s
y
s
tem
f
ailu
r
e,
an
d
in
ten
tio
n
al
f
r
a
u
d
.
-
No
v
elties:
it
i
s
a
n
ew
o
b
s
er
v
atio
n
th
at
o
cc
u
r
s
in
a
n
o
n
-
m
alicio
u
s
ac
tio
n
s
u
ch
as
ch
an
g
es
in
th
e
en
v
ir
o
n
m
en
t,
it is
a
n
o
v
el
p
att
er
n
.
I
n
ad
d
itio
n
to
th
o
s
e
p
atter
n
s
,
ti
m
e
s
er
ies d
ata
ca
n
in
clu
d
e
o
th
er
p
atter
n
s
:
-
Seaso
n
al:
s
ea
s
o
n
ality
h
ap
p
en
s
wh
en
a
tim
e
s
er
ies
is
af
f
ec
ted
b
y
s
h
o
r
t
-
ter
m
v
ar
iatio
n
s
u
ch
as
s
ea
s
o
n
al
f
ac
to
r
s
s
u
ch
as th
e
tim
e
(
m
o
n
t
h
)
o
f
th
e
y
ea
r
o
r
a
d
ay
o
f
th
e
wee
k
.
Seaso
n
ality
p
r
o
d
u
ce
s
a
f
ix
ed
an
d
k
n
o
wn
f
r
eq
u
e
n
cy
.
-
T
r
en
d
:
i
n
o
p
p
o
s
ite
o
f
s
ea
s
o
n
al
tr
en
d
is
af
f
ec
ted
wh
e
n
t
h
er
e
i
s
a
lo
n
g
-
ter
m
,
it
is
d
ef
in
ed
as
a
m
o
v
e
m
en
t
i
n
th
e
d
ata
s
u
ch
as c
h
a
n
g
in
g
in
a
d
ir
ec
tio
n
f
r
o
m
in
c
r
ea
s
in
g
to
d
ec
r
ea
s
in
g
o
r
th
e
o
th
er
way
.
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
:
1
845
-
1
8
5
4
1848
-
C
y
clic:
i
t
ca
n
b
e
d
ef
in
ed
as
a
n
o
v
el
tr
en
d
it
o
cc
u
r
s
d
u
e
to
ch
an
g
es
in
s
o
m
e
r
elate
d
f
ac
to
r
s
to
th
e
g
iv
en
m
ea
s
u
r
em
en
t
f
o
r
ex
am
p
le
th
e
tem
p
er
atu
r
e
o
f
a
g
i
v
en
p
lace
will
ch
an
g
e
if
th
e
h
u
m
i
d
ity
c
h
an
g
es
b
u
t
it
will
n
o
t c
r
ea
te
a
f
r
eq
u
e
n
cy
.
4
.
2
.
T
y
pe
o
f
a
no
ma
ly
in
t
im
e
s
er
i
es
da
t
a
s
et
s
a)
Po
in
t
a
n
o
m
alies:
a
s
in
g
le
ab
n
o
r
m
al
o
b
s
er
v
atio
n
Po
in
t
th
a
t
r
ep
r
esen
ts
an
ir
r
e
g
u
lar
ity
o
r
d
ev
iatio
n
t
h
at
h
ap
p
en
s
r
a
n
d
o
m
l
y
.
b)
C
o
n
tex
tu
al
a
n
o
m
aly
:
also
k
n
o
wn
as
th
e
co
n
d
itio
n
al
an
o
m
aly
,
it
is
o
b
s
er
v
e
d
in
s
p
ec
if
i
c
in
ter
v
als,
f
o
r
ex
am
p
le,
o
b
s
er
v
in
g
m
ea
s
u
r
e
m
en
t
2
o
n
th
e
tem
p
e
r
atu
r
e
in
th
e
win
te
r
s
ea
s
o
n
ca
n
b
e
co
n
s
id
er
ed
n
o
r
m
al,
b
u
t
in
s
u
m
m
er
wo
u
ld
b
e
a
b
n
o
r
m
al
,
o
f
co
u
r
s
e,
we
ca
n
h
av
e
m
u
ltip
le
co
n
d
itio
n
s
s
u
ch
as
l
o
ca
l
b
ec
au
s
e
it
also
af
f
ec
ts
th
e
d
ata,
f
o
r
co
n
tex
tu
al
an
o
m
al
y
a
s
p
ec
if
ic
co
n
tex
t m
u
s
t b
e
d
e
f
in
ed
.
c)
Gr
o
u
p
o
r
c
o
llectiv
e
a
n
o
m
al
y
:
it
is
a
g
r
o
u
p
o
f
an
o
m
alies
t
h
at
ca
n
b
e
co
n
s
id
er
ed
as
n
o
r
m
al
p
atter
n
s
if
o
b
s
er
v
ed
in
d
iv
id
u
ally
f
r
o
m
th
e
d
ata
,
th
is
ty
p
e
o
f
an
o
m
aly
ca
n
ca
u
s
e
a
lo
t o
f
p
r
o
b
lem
s
if
th
e
d
ata
is
s
m
all.
4
.
3
.
Sta
t
is
t
ica
l
m
o
dels
I
n
th
e
f
o
llo
win
g
,
we
will
d
eta
il
m
o
r
e
s
tatis
tical
tech
n
iq
u
es
t
h
at
wo
r
k
b
etter
th
a
n
o
t
h
er
tec
h
n
iq
u
es
in
tim
e
s
er
ies an
o
m
aly
d
etec
tio
n
:
a)
T
h
r
esh
o
ld
m
etr
ic:
in
th
is
m
o
d
el,
we
d
ef
in
e
a
th
r
esh
o
l
d
(
Min
an
d
Ma
x
)
,
b
y
co
u
n
tin
g
t
h
e
ev
en
ts
o
n
a
g
iv
en
d
ataset
,
an
y
v
alu
e
th
at
is
h
ig
h
er
th
an
th
e
Ma
x
d
ef
in
ed
o
r
lo
wer
th
an
th
e
m
in
s
h
o
u
ld
r
aise
an
alar
m
an
d
b
e
ass
u
m
ed
as a
n
an
o
m
al
y
.
b)
Ma
r
k
o
v
p
r
o
ce
s
s
:
th
e
Ma
r
k
o
v
p
r
o
ce
s
s
f
ix
es
a
s
p
ec
if
ic
in
ter
v
al
o
f
th
e
d
ata
an
d
tr
ac
k
th
ese
in
ter
v
als
o
n
tim
e
,
an
y
ch
a
n
g
es o
cc
u
r
r
ed
o
n
a
g
iv
en
i
n
ter
v
al
will b
e
d
e
f
in
e
d
as a
n
an
o
m
aly
.
c)
Me
an
an
d
s
tan
d
ar
d
d
ev
iatio
n
m
o
d
el
:
th
e
s
tan
d
a
r
d
d
e
v
iatio
n
(
also
s
p
elled
s
tan
d
ar
d
d
ev
iatio
n
)
is
a
m
ea
s
u
r
e
o
f
th
e
d
is
p
er
s
io
n
o
f
t
h
e
v
alu
es
o
f
a
s
tatis
tical
s
am
p
le
o
r
p
r
o
b
a
b
ilit
y
d
is
tr
ib
u
tio
n
.
I
t
is
d
ef
in
ed
as
th
e
s
q
u
ar
e
r
o
o
t
o
f
th
e
v
ar
ian
ce
o
r
,
s
im
ilar
ly
,
as
th
e
s
q
u
ar
e
m
ea
n
o
f
t
h
e
d
e
v
iatio
n
s
f
r
o
m
th
e
m
ea
n
.
I
n
th
is
m
o
d
el,
an
y
ev
e
n
t
th
at
f
alls
o
u
ts
id
e
th
e
s
et
in
ter
v
al
d
ef
in
e
d
b
y
th
e
s
tan
d
ar
d
d
e
v
iatio
n
will
b
e
ass
u
m
ed
as
an
o
m
alo
u
s
.
d)
Mu
ltiv
ar
iate
m
o
d
el:
t
h
is
m
o
d
el
tak
es
in
to
co
n
s
id
er
atio
n
m
o
r
e
th
a
n
o
n
e
m
ea
s
u
r
em
en
t
to
d
etec
t
a
n
an
o
m
aly
,
f
o
r
ex
am
p
le
wh
en
t
alk
in
g
ab
o
u
t
h
u
m
id
ity
it
is
af
f
ec
ted
b
y
tim
e
an
d
also
b
y
tem
p
er
atu
r
e,
th
is
m
o
d
el
d
o
esn
’
t
r
aise
an
aler
t
ab
o
u
t
an
ab
n
o
r
m
al
m
ea
s
u
r
e
m
en
t
in
h
u
m
i
d
ity
if
it
is
ju
s
tifie
d
b
y
t
h
e
tem
p
er
atu
r
e
r
ec
o
r
d
e
d
,
it a
p
p
lies
co
r
r
elatio
n
b
etwe
en
two
o
r
m
o
r
e
o
b
s
er
v
atio
n
s
.
e)
T
im
e
s
er
ies
m
o
d
el
:
in
th
is
m
o
d
el,
a
th
r
esh
o
ld
is
n
’
t
d
ef
in
e
d
as
in
o
th
e
r
m
o
d
els,
s
in
ce
it
co
m
p
u
tes
th
e
ch
an
ce
o
f
h
a
v
in
g
a
s
p
ec
if
ic
m
ea
s
u
r
em
en
t
at
a
s
p
ec
if
ic
tim
e
tak
in
g
in
to
co
n
s
id
er
a
tio
n
p
r
ev
io
u
s
m
ea
s
u
r
em
en
ts
in
tim
e
an
d
also
th
e
tim
e
s
er
ies
d
ata,
it
s
tr
en
d
,
s
ea
s
o
n
ality
.
Fro
m
th
e
p
r
ev
i
o
u
s
m
o
d
els
we
ar
e
g
o
in
g
to
wo
r
k
with
tim
e
s
er
ies
d
ata
,
f
o
r
th
at
we
ar
e
g
o
in
g
to
ap
p
l
y
d
if
f
er
e
n
t
alg
o
r
it
h
m
s
to
d
etec
t
an
o
m
alies
b
y
f
o
r
ec
asti
n
g
th
e
tim
e
s
er
ies
d
ata,
th
is
ch
o
ice
is
ju
s
tifie
d
b
y
th
e
f
ac
t
th
at
it
f
its
th
e
I
o
T
ar
ch
itectu
r
e
an
d
also
with
th
e
co
llec
ted
d
ata
b
y
th
e
s
en
s
o
r
s
.
5.
P
RO
P
O
SE
D
M
O
D
E
L
I
n
th
is
s
tu
d
y
we
ar
e
p
r
o
p
o
s
in
g
a
n
ew
a
n
o
m
aly
-
b
ased
I
n
tr
u
s
io
n
d
etec
tio
n
s
y
s
tem
u
s
in
g
s
tati
s
tical
m
o
d
els
to
f
o
r
ec
ast
[
2
1
]
an
d
p
r
ed
ict
f
u
tu
r
e
v
alu
es
b
ased
o
n
a
s
m
all
h
is
to
r
y
b
ase,
th
e
p
r
ed
icted
v
alu
e
u
s
in
g
s
to
ch
asti
c
m
o
d
els
is
clo
s
e
en
o
u
g
h
t
o
th
e
co
r
r
ec
t
r
ea
l
v
alu
es
with
a
v
er
y
s
m
all
d
if
f
er
en
ce
,
o
n
ce
we
g
et
th
e
r
ea
l
r
ec
o
r
d
s
we
co
m
p
a
r
e
th
em
wit
h
th
e
p
r
ed
icte
d
o
n
e
if
th
e
d
if
f
e
r
en
ce
was
s
m
all
en
o
u
g
h
it
will
b
e
co
n
s
id
er
ed
as
a
n
o
r
m
al
o
n
e,
if
n
o
t
th
e
r
ea
l
v
alu
e
will
b
e
r
ep
o
r
ted
as
an
o
m
al
y
p
o
in
t,
t
h
is
tech
n
iq
u
e
is
h
ig
h
ly
ef
f
ec
tiv
e
s
in
ce
it
h
as
a
v
er
y
s
m
all
f
alse
p
o
s
itiv
e
r
ate
an
d
tr
u
e
n
eg
ativ
e
r
at
e
co
m
p
ar
e
d
to
o
th
er
tec
h
n
iq
u
es
s
u
ch
as
ar
tific
ial
in
tellig
en
ce
.
T
h
e
p
r
o
p
o
s
ed
in
tr
u
s
io
n
d
etec
tio
n
s
y
s
tem
Fig
u
r
e
2
c
o
u
ld
b
e
ap
p
lied
t
o
an
y
tim
e
s
er
ies
d
at
aset,
in
o
u
r
ca
s
e
we
ar
e
p
r
o
p
o
s
in
g
an
a
p
p
r
o
ac
h
to
b
e
ap
p
lied
to
th
e
co
lle
cted
in
f
o
r
m
atio
n
o
f
s
en
s
o
r
s
in
an
I
o
T
s
y
s
tem
,
th
e
p
r
o
p
o
s
ed
m
o
d
el
wi
ll
h
elp
en
h
an
ce
th
e
i
n
teg
r
ity
a
n
d
im
p
r
o
v
e
th
e
ac
cu
r
ac
y
,
a
n
d
tr
u
s
two
r
th
in
ess
o
f
th
e
d
at
a
co
llected
b
y
s
en
s
o
r
s
,
it
h
elp
s
t
o
in
d
icate
if
t
h
e
d
ata
was
n
o
t
alter
ed
b
y
an
y
u
n
au
t
h
o
r
ized
i
n
tr
u
d
er
,
in
teg
r
ity
is
v
er
y
im
p
o
r
tan
t
b
asic
in
s
ec
u
r
ity
as
well
as
in
an
y
s
y
s
te
m
in
clu
d
in
g
I
o
T
s
y
s
tem
s
[
2
2
]
an
d
th
e
co
llected
in
f
o
r
m
atio
n
b
y
t
h
e
p
er
ce
p
tio
n
lay
er
,
in
f
ac
t,
s
o
m
etim
e
s
wh
at
is
m
o
r
e
im
p
o
r
tan
t
i
n
a
n
I
o
T
esp
ec
ially
ap
p
lied
f
o
r
h
ea
lth
,
in
d
u
s
tr
y
,
en
v
i
r
o
n
m
en
t
m
o
n
ito
r
in
g
[
2
3
]
is
h
av
in
g
th
e
co
r
r
ec
t
in
f
o
r
m
atio
n
,
an
d
th
e
ac
cu
r
ate
v
alu
es,
th
ese
v
alu
es
th
at
will
b
e
u
s
ed
later
f
o
r
tak
in
g
ac
tio
n
s
a
n
d
d
ec
is
io
n
s
ab
o
u
t
th
e
wh
o
le
p
r
o
ce
s
s
.
T
h
e
m
o
d
el
p
r
o
p
o
s
ed
f
o
r
th
is
p
ar
t is d
iv
id
e
d
in
to
f
o
u
r
p
h
ases
:
a)
C
o
llected
d
ata:
th
e
d
ata
co
llec
ted
b
y
th
e
s
en
s
o
r
s
th
at
will b
e
co
m
p
ar
ed
to
th
e
p
r
ed
icted
d
at
a.
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
n
o
ma
ly
b
a
s
ed
d
etec
tio
n
in
ti
me
s
eries
d
a
ta
o
n
I
o
T sys
tems
u
s
in
g
s
ta
tis
tica
l m
o
d
els
(
Mo
u
n
a
B
o
u
jr
a
d
)
1849
b)
Pre
p
r
o
ce
s
s
an
d
an
aly
ze
th
e
d
ata
:
th
is
s
tep
wil
l
h
elp
to
r
escale
th
e
d
ata
if
n
ee
d
ed
,
clea
n
th
e
d
ata
o
f
u
n
n
ec
ess
ar
y
v
alu
es
if
f
o
u
n
d
,
an
d
also
p
lo
t
th
e
d
ata
as
co
lle
cted
,
th
at
will
h
elp
to
an
aly
ze
th
e
in
f
o
r
m
atio
n
co
llected
.
c)
Dete
ctio
n
en
g
in
e:
th
is
is
th
e
p
ar
t o
n
wh
ich
we
ar
e
g
o
in
g
t
o
i
m
p
lem
en
t o
u
r
m
o
d
el
to
p
er
f
o
r
m
th
e
p
r
ed
ictio
n
u
s
in
g
a
h
is
to
r
ical
d
ataset
th
at
is
p
r
ev
io
u
s
ly
co
llected
an
d
ch
ec
k
ed
,
in
th
e
d
etec
tio
n
en
g
in
e
we
im
p
lem
en
t
th
e
m
o
d
el,
we
p
r
e
d
ict
v
alu
es
o
f
th
e
p
er
io
d
g
iv
e
n
,
an
d
t
h
en
we
co
m
p
ar
e
th
at
v
alu
es
to
th
e
co
ll
ec
ted
o
n
e,
u
s
in
g
o
th
er
alg
o
r
ith
m
s
s
u
ch
as M
ea
n
s
q
u
ar
e
er
r
o
r
,
co
ef
f
icie
n
t o
f
d
eter
m
i
n
atio
n
(
R
2
)
.
d)
R
ep
o
r
t:
t
h
e
r
esu
lts
o
b
tain
ed
f
r
o
m
th
e
d
etec
tio
n
en
g
in
e
will
b
e
co
m
p
ar
ed
t
o
a
d
e
f
in
ed
th
r
esh
o
ld
,
if
it
is
h
ig
h
er
o
r
lo
wer
a
n
aler
t
is
r
aised
in
d
icatin
g
an
a
n
o
m
aly
,
o
t
h
er
wis
e
ev
er
y
th
in
g
will
b
e
r
e
p
o
r
ted
as
n
o
r
m
al
an
d
th
e
in
te
g
r
ity
o
f
th
e
d
ata
is
ch
ec
k
ed
.
Fig
u
r
e
2
.
Pro
p
o
s
ed
m
o
d
el
f
o
r
an
o
m
aly
-
b
ased
in
tr
u
s
io
n
d
etec
tio
n
s
y
s
tem
u
s
in
g
f
o
r
ec
asti
n
g
m
o
d
els
6.
E
XP
E
R
I
M
E
N
T
A
L
T
E
S
T
6
.
1
.
Da
t
a
a
na
ly
s
is
Data
s
et:
f
o
r
o
u
r
e
x
p
er
im
en
t
te
s
ts
we
ar
e
g
o
in
g
to
u
s
e
th
e
d
a
taset
p
r
o
v
id
ed
b
y
Kag
g
le
[
2
4
]
,
th
e
d
ata
co
n
tain
5
y
ea
r
s
o
f
h
o
u
r
ly
m
e
asu
r
em
en
t
o
f
d
if
f
e
r
en
t
en
v
ir
o
n
m
en
tal
v
alu
es
(
tem
p
er
atu
r
e,
h
u
m
id
ity
,
p
r
ess
u
r
e,
wea
th
er
d
ir
ec
tio
n
,
wea
th
er
s
p
e
ed
)
th
e
r
ec
o
r
d
s
wer
e
r
ec
o
r
d
ed
in
3
6
d
if
f
er
e
n
t
cities.
T
h
e
d
ata
f
its
p
er
f
ec
tly
with
th
e
n
ee
d
ed
m
o
d
el
,
it
g
i
v
es
u
s
ex
ac
tly
wh
at
we
n
ee
d
to
test
o
n
th
e
m
o
d
el,
we
will
n
o
t
u
s
e
th
e
en
tire
d
ataset
we
ar
e
g
o
in
g
to
r
etr
iev
e
in
ter
v
al
s
f
r
o
m
th
e
g
iv
en
d
atasets
to
p
er
f
o
r
m
th
e
test
s
with
th
e
d
if
f
er
en
t
m
o
d
els.
T
h
e
d
ataset
is
p
r
o
v
id
e
d
u
n
d
e
r
th
e
ODb
L
L
icen
s
e.
Sin
ce
we
ar
e
u
s
in
g
th
e
f
o
r
ec
asti
n
g
m
o
d
el
f
o
r
an
o
m
aly
d
etec
tio
n
we
d
o
n
’
t
n
ee
d
lar
g
e
h
is
to
r
y
f
r
o
m
th
e
d
ata
,
we
s
ea
r
ch
f
o
r
a
m
o
d
el
th
at
ca
n
f
o
r
ec
ast
f
u
t
u
r
e
v
alu
es
b
ased
o
n
s
m
all
h
is
to
r
y
d
ata,
o
f
co
u
r
s
e,
we
ca
n
u
s
e
a
lar
g
e
o
n
e
b
u
t
we
co
u
l
d
f
ac
e
th
e
p
r
o
b
lem
o
f
s
ea
s
o
n
ality
,
esp
ec
ially
in
en
v
ir
o
n
m
en
t
r
ec
o
r
d
s
s
u
ch
as
clim
ates.
W
e
u
s
ed
p
ar
tial
d
ata
in
Fig
u
r
e
3
g
o
i
n
g
f
r
o
m
2
6
-
01
-
2
0
1
7
to
3
1
-
01
-
201
f
r
o
m
tem
p
er
atu
r
e
.
csv
f
ile,
it
is
tr
ick
y
f
o
r
an
y
m
o
d
el
to
p
r
ed
ict
th
e
n
ex
t
v
alu
e
b
ased
o
n
a
s
m
all
tr
ai
n
in
g
s
et.
Data
p
r
ep
r
o
ce
s
s
in
g
:
b
ef
o
r
e
ch
o
o
s
in
g
th
e
in
ter
v
al
o
n
wh
ic
h
we
ar
e
g
o
in
g
to
wo
r
k
we
a
n
a
ly
ze
d
th
e
wh
o
le
h
o
u
r
ly
tem
p
e
r
atu
r
e
r
ec
o
r
d
s
o
f
Po
r
tlan
d
(
t
h
e
ch
o
ice
o
f
Po
r
tlan
d
was
r
an
d
o
m
ly
a
n
d
ev
er
y
th
in
g
ap
p
lied
to
Po
r
tlan
d
ca
n
b
e
ap
p
lied
to
o
th
er
cities f
r
o
m
th
e
d
atasets
p
r
o
v
id
ed
b
y
Kag
g
le)
.
Fro
m
Fig
u
r
e
3
we
ca
n
co
n
clu
d
e
d
ata
tem
p
er
atu
r
e
r
ec
o
r
d
s
(
o
r
an
y
o
th
e
r
clim
ates
r
ec
o
r
d
s
c
o
llected
b
y
s
en
s
o
r
s
)
is
a
n
o
n
-
s
tatio
n
a
r
y
o
n
e
s
in
ce
th
e
r
e
ar
e
s
o
m
an
y
f
ac
t
o
r
s
th
at
c
an
af
f
ec
t
th
e
v
alu
es
o
v
er
tim
e,
u
s
in
g
th
e
wh
o
le
d
ata
ca
n
ca
u
s
e
wr
o
n
g
p
r
ed
icted
v
alu
es,
f
o
r
th
at
we
s
p
lit
th
e
d
ata
i
n
to
th
e
ap
p
ea
r
i
n
g
s
ea
s
o
n
s
in
to
th
e
d
ata,
b
u
t
it
s
till
a
lar
g
e
d
ataset
to
u
s
e
f
o
r
an
o
m
aly
d
etec
tio
n
,
th
at
is
wh
y
we
ar
e
g
o
in
g
to
p
l
o
t
o
n
e
m
o
n
th
f
r
o
m
th
e
p
ar
tial d
ataset
an
d
th
e
n
we
ca
n
ag
ain
d
ef
in
e
a
m
o
r
e
s
m
all
p
ar
t to
wo
r
k
o
n
in
th
e
n
ex
t te
s
tin
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
:
1
845
-
1
8
5
4
1850
Fig
u
r
e
3
.
Ho
u
r
ly
tem
p
er
atu
r
e
r
ec
o
r
d
s
in
2
0
1
7
in
Po
r
tlan
d
Fro
m
Fig
u
r
e
4
we
ca
n
s
ee
th
at
ev
en
in
o
n
e
m
o
n
th
o
f
p
lo
ttin
g
th
er
e
ex
is
t
a
lo
t
o
f
s
ea
s
o
n
ality
wh
ich
is
wh
y
we
s
p
lit
o
n
ce
ag
ain
th
e
d
ata
in
to
a
m
o
r
e
s
tatio
n
ar
y
an
d
s
m
aller
d
ataset
in
o
u
r
ca
s
e
w
e
ch
o
s
e
to
wo
r
k
o
n
d
ata
g
o
i
n
g
f
r
o
m
2
6
-
01
-
2
0
1
7
t
o
3
1
-
01
-
2
0
1
7
T
h
at
will
b
e
id
ea
l
in
ter
v
al
to
b
e
a
p
p
lied
in
a
r
ea
l
ca
s
e
an
d
m
o
r
e
p
r
ec
is
ely
f
o
r
an
o
m
al
y
d
etec
tio
n
to
ch
ec
k
th
e
in
teg
r
ity
o
f
th
e
d
at
a.
T
h
e
r
ec
o
r
d
s
in
th
e
d
ata
s
et
ch
o
s
en
f
o
r
test
Fig
u
r
e
5
wer
e
alr
ea
d
y
v
er
if
ie
d
,
s
o
it
d
o
esn
’
t
i
n
clu
d
e
a
n
y
an
o
m
alies
o
r
ab
n
o
r
m
al
r
ec
o
r
d
s
Fig
u
r
e
5
(
a)
,
f
o
r
th
at
we
m
an
u
ally
r
ep
lace
d
two
r
ec
o
r
d
s
b
y
wr
o
n
g
o
n
es
to
c
h
ec
k
th
e
ch
an
g
es
th
at
o
cc
u
r
r
ed
o
n
th
e
d
ataset
F
ig
u
r
e
5
(
b
)
.
T
o
s
tu
d
y
th
e
d
is
tr
ib
u
tio
n
o
f
th
e
d
ataset
r
ec
o
r
d
s
we
p
lo
t
ted
its
h
is
to
g
r
am
with
an
d
with
o
u
t
an
an
o
m
alo
u
s
p
o
in
t
Fig
u
r
e
6
.
I
n
th
e
o
r
ig
in
al
d
ata
we
ca
n
s
ee
th
at
th
e
d
is
tr
ib
u
tio
n
o
f
th
e
v
alu
es
ca
n
b
e
s
p
lit
in
to
two
s
u
b
g
au
s
s
ian
d
is
tr
ib
u
tio
n
s
Fig
u
r
e
6
(
a)
wh
ich
is
n
o
r
m
al
s
in
ce
in
h
o
u
r
ly
te
m
p
er
atu
r
e
r
ec
o
r
d
s
in
a
d
ay
we
alwa
y
s
m
et
a
law
tem
p
er
atu
r
e
d
eg
r
ee
an
d
a
h
ig
h
o
n
e
(
ca
n
b
e
ju
s
t
if
ied
b
y
n
i
g
h
t
a
n
d
d
ay
)
,
in
th
e
i
n
f
ec
ted
d
ata
we
s
ee
th
at
th
e
d
is
tr
ib
u
tio
n
b
e
co
m
es a
g
au
s
s
ian
o
n
e
Fig
u
r
e
6
(
b
)
s
in
ce
ev
en
with
th
e
lo
w
a
n
d
h
ig
h
-
tem
p
er
atu
r
e
d
eg
r
ee
s
th
ey
s
till
clo
s
e
en
o
u
g
h
b
u
t
th
e
an
o
m
aly
p
o
in
t
e
v
en
th
o
u
g
h
th
e
y
ar
en
’
t
m
ass
iv
ely
ch
an
g
ed
th
e
y
s
till
p
lo
tted
s
ep
ar
ately
in
t
h
e
h
is
to
g
r
am
.
Fig
u
r
e
4
.
Ho
u
r
ly
tem
p
er
atu
r
e
r
ec
o
r
d
s
in
J
an
u
a
r
y
2
0
1
7
in
Po
r
tlan
d
(
a)
(
b
)
Fig
u
r
e
5
.
Ho
u
r
ly
tem
p
er
atu
r
e
r
ec
o
r
d
s
d
ataset
ch
o
s
en
f
o
r
test
in
(
a)
with
a
n
o
m
aly
p
o
in
t a
d
d
ed
an
d
(
b
)
with
o
u
t
an
o
m
alies o
r
ch
a
n
g
es o
n
th
e
d
ata
T
est
th
e
s
tat
io
n
ar
ity
o
f
th
e
d
a
taset:
t
o
te
s
t
if
th
e
d
ata
s
et
is
s
tatio
n
ar
y
en
o
u
g
h
to
ap
p
ly
th
e
alg
o
r
ith
m
o
n
it
we
ar
e
g
o
in
g
to
u
s
e
th
e
Dick
ey
-
Fu
ller
Au
g
m
e
n
ted
t
est
(
ADF)
[
2
5
]
.
T
h
e
Dick
e
y
Fu
ll
er
au
g
m
e
n
ted
test
o
r
ADF
is
a
s
ta
tis
tica
l
test
d
esig
n
ed
to
d
eter
m
in
e
wh
eth
e
r
a
tim
e
s
er
ies
i
s
s
tat
io
n
ar
y
,
i.e
.
,
w
h
eth
er
its
s
tati
s
tical
p
r
o
p
er
ties
(
h
o
p
e
,
v
a
r
ian
ce
,
a
u
to
-
co
r
r
el
atio
n
)
v
ar
y
o
v
er
tim
e.
Usi
n
g
th
e
ad
f
u
ller
f
u
n
ctio
n
f
r
o
m
s
tatem
o
d
els.ts
a
lib
r
ar
y
we
ca
n
in
ter
p
r
et
if
o
u
r
d
ataset
is
s
tat
io
n
ar
y
o
r
n
o
t.
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
n
o
ma
ly
b
a
s
ed
d
etec
tio
n
in
ti
me
s
eries
d
a
ta
o
n
I
o
T sys
tems
u
s
in
g
s
ta
tis
tica
l m
o
d
els
(
Mo
u
n
a
B
o
u
jr
a
d
)
1851
Nu
ll
h
y
p
o
th
esis
:
i
f
n
o
t
r
ejec
t
ed
,
in
th
is
ca
s
e,
th
e
tim
e
s
er
ies
h
as
a
u
n
it
r
o
o
t,
m
ea
n
in
g
it
is
n
o
n
-
s
tatio
n
ar
y
.
I
t
h
as
tim
e
-
d
ep
e
n
d
en
t
s
tr
u
ctu
r
e.
On
th
e
o
t
h
er
h
a
n
d
,
if
th
e
n
u
ll
h
y
p
o
th
esis
was
r
ejec
ted
,
we
ca
n
ass
u
m
e
th
at
th
e
tim
e
s
er
ies d
o
es n
o
t h
av
e
a
u
n
it r
o
o
t,
wh
ich
m
ea
n
s
it is
s
tatio
n
ar
y
.
Ap
p
ly
in
g
th
e
ADF
test
o
n
o
u
r
d
ataset
(
with
th
e
an
o
m
alo
u
s
p
o
in
ts
)
we
ar
e
g
ettin
g
r
esu
lt
s
o
f
-
4
.
8
5
6
0
1
9
wh
ich
is
lo
w
th
an
-
3
.
4
7
9
at
1
%
wh
ich
s
h
o
ws
th
at
th
e
d
ata
ca
n
r
ejec
t
th
e
n
u
ll
h
y
p
o
th
esis
with
a
s
ig
n
if
ican
t le
v
el
o
f
less
th
an
1
% wh
ich
m
ea
n
s
th
at
o
u
r
d
ata
i
s
s
tatio
n
ar
y
at
th
at
p
o
in
t.
(
a)
(
b
)
Fig
u
r
e
6
.
His
to
g
r
am
p
lo
t o
f
th
e
d
ataset
in
(
a)
with
an
o
m
aly
p
o
in
t a
n
d
(
b
)
with
o
u
t
a
n
o
m
aly
6
.
2
.
St
a
t
is
t
ica
l
m
o
dels
perf
o
rm
a
nce
co
m
pa
riso
n
I
n
th
is
s
tu
d
y
we
ch
o
o
s
e
to
u
s
e
5
d
if
f
e
r
en
t
s
tatis
tical
m
o
d
els:
i
)
AR
:
au
t
o
r
eg
r
ess
io
n
,
ii
)
M
A:
m
o
v
in
g
av
er
ag
e
m
o
d
el
,
iii
)
AR
MA
:
a
u
to
r
eg
r
ess
io
n
m
o
v
in
g
av
er
ag
e
,
iv
)
AR
I
MA
:
a
u
to
r
eg
r
ess
io
n
in
teg
r
ated
m
o
v
i
n
g
av
er
ag
e
[
2
6
]
,
an
d
v
)
SAR
I
MA
:
s
ea
s
o
n
al
au
to
r
eg
r
ess
io
n
m
o
v
in
g
av
er
a
g
e
.
T
o
co
m
p
a
r
e
th
e
m
o
d
els,
we
a
r
e
u
s
in
g
7
0
%
o
f
th
e
d
ata
as
tr
ain
in
g
an
d
3
0
%
as
test
in
g
,
wit
h
th
e
7
0
%
we
ar
e
g
o
in
g
to
tr
ain
th
e
m
o
d
els
an
d
m
ak
e
a
p
r
ed
ictio
n
o
n
th
e
s
a
m
e
in
ter
v
al
as
th
e
test
in
g
p
ar
t,
an
d
th
en
we
ar
e
g
o
in
g
to
co
m
p
ar
e
th
e
r
esu
lts
o
b
tain
ed
f
r
o
m
th
e
d
if
f
er
en
t
m
o
d
els
with
th
e
ac
tu
al
v
alu
e
s
o
f
test
in
g
p
ar
t
[
2
7
]
.
Fo
r
A
R
MA
,
AR
I
MA
,
an
d
SAR
I
MA
th
e
ch
o
ice
o
f
th
e
p
a
r
am
eter
s
was f
u
lf
illed
u
s
in
g
A
k
aik
e’
s
in
f
o
r
m
atio
n
cr
iter
i
o
n
(
AI
C
)
[
2
8
]
.
7.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
I
n
o
u
r
s
tu
d
y
,
th
e
d
if
f
er
en
t
s
t
atis
tical
m
o
d
els
wer
e
tr
ain
ed
u
s
in
g
7
0
%
o
f
th
e
c
h
o
s
en
d
a
taset,
e
r
r
o
r
m
ea
s
u
r
em
en
t
o
f
th
e
p
r
ed
icte
d
v
alu
es
in
th
e
m
o
d
els
.
T
o
co
m
p
ar
e
th
e
m
o
d
els
r
esu
lts
we
p
e
r
f
o
r
m
e
d
m
an
y
test
s
to
ca
lcu
late
th
e
p
r
ec
is
io
n
o
f
t
h
e
d
etec
ted
v
alu
es,
as
well
as
th
e
d
if
f
e
r
en
ce
b
etwe
en
th
e
a
ctu
al
an
d
esti
m
ated
o
n
es.
I
n
th
is
r
esear
ch
we
tr
ie
d
to
p
r
o
p
o
s
e
an
ap
p
r
o
ac
h
f
o
r
a
n
o
m
aly
d
etec
tio
n
u
s
in
g
s
tatis
tical
tech
n
iq
u
es,
T
h
e
r
esu
lts
f
r
o
m
p
lo
ttin
g
a
u
to
r
e
g
r
ess
io
n
an
d
m
o
v
in
g
av
er
a
g
e
m
o
d
els
Fig
u
r
e
7
,
clea
r
l
y
s
h
o
w
th
at
th
e
au
to
r
eg
r
ess
io
n
m
o
d
el
ten
d
s
to
b
e
s
tatio
n
ar
y
o
v
er
tim
e
w
ith
t
h
e
s
am
e
v
alu
e
Fig
u
r
e
7
(
a
)
,
th
i
s
r
esu
lt
is
th
e
s
am
e
wh
en
u
s
in
g
a
m
u
ch
la
r
g
er
d
at
aset
(
we
u
s
ed
th
e
en
tire
m
o
n
t
h
an
d
s
till
h
av
e
t
h
e
s
am
e
s
tatio
n
ar
y
ac
tio
n
f
r
o
m
AR
m
o
d
el)
t
h
at
m
ea
n
s
th
at
th
i
s
m
o
d
el
is
v
er
y
wea
k
f
o
r
p
r
ed
i
ctio
n
an
d
it
ca
n
n
o
t
b
e
u
s
ed
in
an
o
m
aly
d
etec
tio
n
,
th
is
m
o
d
el
will
w
o
r
k
f
in
e
in
a
s
tatio
n
ar
y
en
v
ir
o
n
m
en
t
wh
e
n
th
e
d
ata
te
n
d
to
b
e
f
i
x
ed
b
u
t
n
o
t
o
n
d
ata
with
s
ea
s
o
n
ality
ev
en
s
m
all
o
n
es,
th
is
r
esu
lt
was
ju
s
tifie
d
b
y
th
e
s
co
r
es
o
b
tain
e
d
b
y
th
e
d
if
f
er
en
t
test
s
,
m
ea
n
s
q
u
ar
e
er
r
o
r
(
MSE
)
o
u
tp
u
t
a
v
alu
e
o
f
1
.
1
5
6
f
o
r
th
e
AR
,
al
s
o
th
e
v
ar
ian
ce
was
v
er
y
lo
w
to
b
e
g
o
o
d
at
0
.
0
0
4
T
ab
le
1
,
p
r
o
v
es
th
er
e
is
alm
o
s
t
n
o
r
elatio
n
b
etwe
en
th
e
p
r
ed
icted
v
alu
es
an
d
th
e
ac
t
u
al
o
n
es.
Mo
v
in
g
a
v
er
ag
e
p
lo
ttin
g
d
id
n
’
t
q
u
ite
r
ef
lect
th
e
d
ata
s
in
ce
it
s
m
o
o
th
s
th
e
d
at
a
in
a
way
th
at
it
was
p
l
o
tted
with
o
u
t
s
h
o
win
g
t
h
e
d
if
f
er
en
ce
s
b
etwe
en
th
e
h
o
u
r
l
y
r
ec
o
r
d
s
Fig
u
r
e
7
(
b
)
,
th
e
MSE
s
p
o
tted
t
h
is
p
r
o
b
lem
b
y
g
iv
in
g
a
h
ig
h
s
co
r
e
o
f
1
.
2
0
4
,
th
e
m
ea
n
ab
s
o
lu
te
er
r
o
r
(
MA
E
)
s
co
r
e
was
also
h
ig
h
with
a
v
al
u
e
o
f
0
.
9
4
3
T
a
b
le
1
,
t
h
is
m
o
d
el
alth
o
u
g
h
it
g
iv
es
th
e
s
h
ap
e
o
f
th
e
d
ata
an
d
h
o
w
th
e
wh
o
le
d
ata
ac
t,
it
d
o
esn
’
t
g
iv
e
ac
cu
r
ate
an
d
clo
s
e
p
r
ed
icted
v
alu
es
th
at
ca
n
b
e
u
s
ed
in
an
o
m
aly
d
etec
tio
n
to
ch
ec
k
d
ata
in
teg
r
ity
.
I
n
Fig
u
r
e
8
s
h
o
ws
th
e
p
lo
tted
r
esu
lts
o
f
AR
MA
Fig
u
r
e
8
(
a)
a
n
d
AR
I
MA
Fig
u
r
e
8
(
b
)
p
r
ed
ictio
n
s
,
th
ey
wer
e
v
er
y
cl
o
s
e
in
th
e
p
lo
ttin
g
,
alth
o
u
g
h
AR
I
MA
p
lo
ttin
g
was
s
m
o
o
t
h
er
a
n
d
cl
o
s
er
to
th
e
ac
tu
al
o
n
e,
ev
en
i
f
th
e
e
r
r
o
r
test
s
s
h
o
w
th
at
A
R
MA
an
d
AR
I
MA
p
er
f
o
r
m
s
im
ilar
ly
with
a
s
m
all
d
if
f
er
en
ce
,
th
at
AR
I
MA
test
s
wer
e
r
elativ
ely
b
etter
,
th
e
m
ea
n
er
r
o
r
o
f
AR
MA
an
d
AR
I
MA
was
o
f
0
.
8
8
2
a
n
d
0
.
7
0
7
r
esp
ec
tiv
ely
T
a
b
le
1
,
th
ey
s
till
h
ig
h
s
co
r
es,
b
u
t
in
f
ac
t,
th
e
p
r
ed
icted
v
alu
es
wer
e
clo
s
e
e
n
o
u
g
h
to
b
e
co
n
s
id
er
e
d
as
g
o
o
d
m
o
d
els
t
o
u
s
e.
H
o
wev
er
,
th
e
c
o
ef
f
icie
n
t
o
f
d
eter
m
i
n
atio
n
(
R
2
)
was
s
ig
n
if
ican
tly
lo
w
f
o
r
b
o
th
m
o
d
els,
0
.
1
4
3
f
o
r
AR
MA
an
d
0
.
2
8
7
f
o
r
AR
I
MA
,
th
e
p
r
o
b
lem
with
th
ese
m
o
d
els
is
th
e
s
ea
s
o
n
ality
,
AR
MA
d
o
esn
’
t
h
an
d
le
s
ea
s
o
n
a
lity
,
an
d
AR
I
MA
r
em
o
v
es
th
e
d
if
f
er
en
ce
s
in
th
e
tr
ain
in
g
d
ata.
SAR
I
MA
was
th
e
b
est
m
o
d
el
t
o
u
s
e,
it
s
h
o
w
s
a
g
r
ea
t
p
lo
t
Fig
u
r
e
9
,
an
d
al
s
o
v
er
y
g
o
o
d
er
r
o
r
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
:
1
845
-
1
8
5
4
1852
test
r
esu
lt
s
,
an
MSE
o
f
0
.
0
9
9
T
ab
le
1
,
clo
s
e
to
0
wh
ich
m
ea
n
s
th
at
th
e
v
alu
es e
s
tim
ated
w
er
e
v
er
y
clo
s
e
to
th
e
r
ea
l o
n
es in
th
e
d
ataset.
(
a)
(
b
)
Fig
u
r
e
7
.
Ob
tain
e
d
p
r
ed
ictio
n
r
esu
lts
u
s
in
g
d
if
f
er
en
t
s
tatis
tical
m
o
d
els in
(
a)
b
y
AR
m
o
d
el
an
d
(
b
)
b
y
MA
m
o
d
el
T
ab
le
1
.
Me
asu
r
em
e
n
t e
r
r
o
r
o
f
d
if
f
er
en
t
m
o
d
els u
s
in
g
d
if
f
er
e
n
t te
s
ts
M
o
d
e
l
SE
V
a
r
i
a
n
c
e
R1
M
A
E
AR
1
.
1
5
6
0
.
0
0
4
-
0
.
1
6
6
0
.
9
3
1
ME
1
.
2
0
4
-
0
.
0
7
1
-
0
.
0
7
1
0
.
9
4
3
A
R
M
A
0
.
8
8
2
0
.
4
5
8
0
.
1
4
3
0
.
7
2
8
A
R
I
M
A
0
.
7
0
7
0
.
5
2
3
0
.
2
8
7
0
.
6
6
0
S
A
R
I
M
A
0
.
0
9
9
0
.
9
0
3
0
.
9
0
3
0
.
2
4
9
(
a)
(
b
)
Fig
u
r
e
8
.
Ob
tain
e
d
p
r
ed
ictio
n
r
esu
lts
u
s
in
g
d
if
f
er
en
t statis
tical
m
o
d
els in
(
a)
b
y
AR
MA
an
d
(
b
)
b
y
AR
I
MA
m
o
d
el
Fig
u
r
e
9
.
Pre
d
ictio
n
r
esu
lts
b
y
SAR
I
MA
m
o
d
el
T
h
e
o
b
tain
ed
r
esu
lts
ca
n
b
e
u
s
ed
in
an
o
m
aly
d
etec
tio
n
s
in
ce
an
y
an
o
m
al
o
u
s
p
o
in
t
will
b
e
s
p
o
tted
ev
en
if
it
was
v
er
y
s
m
all,
an
d
we
ca
n
ch
ec
k
th
e
ac
c
u
r
ac
y
o
f
th
e
in
f
o
r
m
atio
n
.
Ho
wev
e
r
s
tatis
tical
m
o
d
els
m
ay
n
o
t
b
e
s
u
f
f
icien
t
f
o
r
an
o
m
aly
d
etec
tio
n
wh
en
it
co
m
es
t
o
n
o
n
-
s
ea
s
o
n
al
o
r
b
ig
d
ata,
wh
ich
n
ee
d
s
a
m
o
r
e
co
m
p
lex
alg
o
r
ith
m
s
u
c
h
as in
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
es t
o
d
etec
t a
n
o
m
alo
u
s
p
o
i
n
ts
.
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
n
o
ma
ly
b
a
s
ed
d
etec
tio
n
in
ti
me
s
eries
d
a
ta
o
n
I
o
T sys
tems
u
s
in
g
s
ta
tis
tica
l m
o
d
els
(
Mo
u
n
a
B
o
u
jr
a
d
)
1853
8.
CO
NCLU
SI
O
N
Data
in
teg
r
ity
is
a
cr
itical
is
s
u
e
in
s
ec
u
r
ity
,
we
ca
n
n
o
t
f
o
cu
s
o
n
s
ec
u
r
in
g
th
e
n
etwo
r
k
s
y
s
tem
s
with
o
u
t
tak
in
g
in
to
co
n
s
id
er
atio
n
v
er
if
y
i
n
g
th
e
ac
cu
r
ac
y
o
f
t
h
e
d
ata
th
at
is
b
ein
g
tr
an
s
f
er
r
e
d
in
to
th
e
n
etwo
r
k
.
An
o
m
alies
d
etec
ted
in
th
e
d
a
ta
ca
n
in
d
icate
a
p
o
s
s
ib
le
m
a
licio
u
s
ac
tio
n
,
th
e
m
ain
id
ea
was
to
p
r
o
p
o
s
e
a
m
o
d
el
th
at
ca
n
d
etec
t
co
r
r
ec
t
f
u
tu
r
e
v
alu
es
th
at
co
u
l
d
b
e
co
llected
b
y
th
e
s
en
s
o
r
s
an
d
th
en
co
m
p
a
r
e
th
ese
p
r
ed
ictio
n
s
with
th
e
ac
tu
al
v
alu
es,
tak
in
g
in
to
c
o
n
s
id
er
ati
o
n
th
at
af
ter
tr
ai
n
in
g
th
e
m
o
d
el
with
h
is
to
r
ical
d
ataset,
it
will
b
e
ab
le
to
p
r
o
v
id
e
ac
c
u
r
ate
p
r
ed
ictio
n
s
,
f
o
r
th
at
we
p
r
o
p
o
s
ed
s
tatis
tic
al
m
o
d
els
th
at
f
it
p
er
f
ec
tly
with
th
is
id
ea
,
s
in
ce
I
o
T
d
ata
co
llected
b
y
s
en
s
o
r
s
ar
e
k
n
o
wn
as
tim
e
s
er
ies
o
n
es,
in
th
is
wo
r
k
we
test
ed
s
ev
er
al
s
ta
tis
t
ical
m
o
d
els
in
o
r
d
er
to
co
m
p
ar
e
th
eir
e
p
er
f
o
r
m
a
n
ce
,
th
e
r
esu
lts
s
h
o
w
th
at
SAR
I
M
A
o
u
tp
er
f
o
r
m
s
o
th
e
r
m
o
d
els
(
A
R
,
MA
,
AR
M
A,
an
d
AR
I
MA
)
,
th
e
o
b
tain
ed
r
esu
lts
wer
e
v
alid
ated
u
s
in
g
a
tem
p
er
atu
r
e
d
ataset
f
r
o
m
Kag
g
le.
T
h
e
ch
o
ice
o
f
u
s
ig
n
s
tatis
tical
m
o
d
els
co
m
e
f
r
o
m
th
e
litra
tu
r
e
r
ev
iew
we
d
id
,
f
r
o
m
wh
ich
we
co
n
cl
u
d
e
d
th
at
s
tatictical
m
o
d
els
h
av
e
a
h
ig
h
-
p
er
f
o
r
m
a
n
ce
o
n
tim
e
s
er
ies
d
atasets
.
Fo
r
o
u
r
f
u
tu
r
e
wo
r
k
we
ar
e
p
lan
n
in
g
to
ap
p
ly
th
e
b
est
m
o
d
el
o
n
d
if
f
er
en
t
d
atasets
,
to
v
alid
ate
th
e
r
esu
lts
,
an
d
also
co
m
p
ar
e
it
later
with
m
ac
h
in
e
lear
n
in
g
a
n
d
d
ee
p
lear
n
in
g
te
ch
n
iq
u
es
esp
ec
ially
s
eq
u
en
tial
alg
o
r
ith
m
s
s
u
ch
as
R
NN,
th
is
wo
r
k
will
en
with
th
e
cr
ea
tio
n
o
f
r
o
b
u
s
t a
n
d
well
d
esig
n
ed
an
o
m
aly
-
b
ased
m
o
d
el
f
o
r
I
o
T
d
atasets
.
RE
F
E
R
E
NC
E
S
[
1
]
M
.
B
o
u
j
r
a
d
,
S
.
La
z
a
a
r
,
a
n
d
M
.
H
a
ss
i
n
e
,
“
P
e
r
f
o
r
m
a
n
c
e
a
ss
e
ssm
e
n
t
o
f
o
p
e
n
s
o
u
r
c
e
I
D
S
f
o
r
i
m
p
r
o
v
i
n
g
I
o
T
a
r
c
h
i
t
e
c
t
u
r
e
s
e
c
u
r
i
t
y
i
mp
l
e
m
e
n
t
e
d
o
n
W
B
A
N
s,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
3
r
d
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
N
e
t
w
o
r
k
i
n
g
,
I
n
f
o
rm
a
t
i
o
n
S
y
s
t
e
m
s
&
S
e
c
u
r
i
t
y
,
N
e
w
Y
o
r
k
,
N
Y
,
U
S
A
:
A
C
M
,
M
a
r
.
2
0
2
0
,
p
p
.
1
–
4
,
d
o
i
:
1
0
.
1
1
4
5
/
3
3
8
6
7
2
3
.
3
3
8
7
8
9
2
.
[
2
]
V
.
C
h
a
u
d
h
a
r
y
,
A
.
K
a
u
s
h
i
k
,
H
.
F
u
r
u
k
a
w
a
,
a
n
d
A
.
K
h
o
sl
a
,
“
R
e
v
i
e
w
—
t
o
w
a
r
d
s
5
t
h
g
e
n
e
r
a
t
i
o
n
A
I
a
n
d
I
o
T
d
r
i
v
e
n
su
s
t
a
i
n
a
b
l
e
i
n
t
e
l
l
i
g
e
n
t
s
e
n
s
o
r
s
b
a
se
d
o
n
2
D
M
X
e
n
e
s
a
n
d
b
o
r
o
p
h
e
n
e
,
”
E
C
S
S
e
n
s
o
rs
Pl
u
s
,
v
o
l
.
1
,
n
o
.
1
,
p
.
0
1
3
6
0
1
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
4
9
/
2
7
5
4
-
2
7
2
6
/
a
c
5
a
c
6
.
[
3
]
M
.
N
o
o
r
i
b
a
k
h
s
h
a
n
d
M
.
M
o
l
l
a
m
o
t
a
l
e
b
i
,
“
A
r
e
v
i
e
w
o
n
s
t
a
t
i
s
t
i
c
a
l
a
p
p
r
o
a
c
h
e
s
f
o
r
a
n
o
mal
y
d
e
t
e
c
t
i
o
n
i
n
D
D
o
S
a
t
t
a
c
k
s,
”
I
n
f
o
rm
a
t
i
o
n
S
e
c
u
r
i
t
y
J
o
u
rn
a
l
,
v
o
l
.
2
9
,
n
o
.
3
,
p
p
.
1
1
8
–
1
3
3
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
8
0
/
1
9
3
9
3
5
5
5
.
2
0
2
0
.
1
7
1
7
0
1
9
.
[
4
]
A
.
W
a
h
a
b
,
O
.
A
h
ma
d
,
M
.
M
u
h
a
mm
a
d
,
a
n
d
M
.
A
l
i
,
“
A
c
o
mp
r
e
h
e
n
s
i
v
e
a
n
a
l
y
s
i
s
o
n
t
h
e
sec
u
r
i
t
y
t
h
r
e
a
t
s
a
n
d
t
h
e
i
r
c
o
u
n
t
e
r
m
e
a
s
u
r
e
s
o
f
I
o
T,
”
I
n
t
e
rn
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
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
8
,
n
o
.
7
,
2
0
1
7
,
d
o
i
:
1
0
.
1
4
5
6
9
/
i
j
a
c
s
a
.
2
0
1
7
.
0
8
0
7
6
8
.
[
5
]
H
.
Za
r
e
M
o
a
y
e
d
i
a
n
d
M
.
A
.
M
a
s
n
a
d
i
-
S
h
i
r
a
z
i
,
“
A
r
i
ma
mo
d
e
l
f
o
r
n
e
t
w
o
r
k
t
r
a
f
f
i
c
p
r
e
d
i
c
t
i
o
n
a
n
d
a
n
o
ma
l
y
d
e
t
e
c
t
i
o
n
,
”
i
n
2
0
0
8
I
n
t
e
r
n
a
t
i
o
n
a
l
S
y
m
p
o
si
u
m
o
n
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
I
EEE,
2
0
0
8
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
TSI
M
.
2
0
0
8
.
4
6
3
1
9
4
7
.
[
6
]
A
.
H
.
Y
a
a
c
o
b
,
I
.
K
.
T
.
T
a
n
,
S
.
F
.
C
h
i
e
n
,
a
n
d
H
.
K
.
Ta
n
,
“
A
R
I
M
A
b
a
s
e
d
n
e
t
w
o
r
k
a
n
o
mal
y
d
e
t
e
c
t
i
o
n
,
”
i
n
2
0
1
0
S
e
c
o
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
m
u
n
i
c
a
t
i
o
n
S
o
f
t
w
a
re
a
n
d
N
e
t
w
o
r
k
s
,
I
EEE,
2
0
1
0
,
p
p
.
2
0
5
–
2
0
9
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
S
N
.
2
0
1
0
.
5
5
.
[
7
]
E.
H
.
M
.
P
e
n
a
,
M
.
V
.
O
.
d
e
A
ssi
s,
a
n
d
M
.
L.
P
r
o
e
n
c
a
,
“
A
n
o
ma
l
y
d
e
t
e
c
t
i
o
n
u
si
n
g
f
o
r
e
c
a
st
i
n
g
me
t
h
o
d
s
A
R
I
M
A
a
n
d
H
W
D
S
,
”
i
n
2
0
1
3
3
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
f
t
h
e
C
h
i
l
e
a
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
S
o
c
i
e
t
y
(
S
C
C
C
)
,
I
EEE,
N
o
v
.
2
0
1
3
,
p
p
.
6
3
–
6
6
,
d
o
i
:
1
0
.
1
1
0
9
/
S
C
C
C
.
2
0
1
3
.
1
8
.
[
8
]
Q
.
Y
u
,
L
.
Ji
b
i
n
,
a
n
d
L
.
Ji
a
n
g
,
“
A
n
i
mp
r
o
v
e
d
A
R
I
M
A
-
b
a
se
d
t
r
a
f
f
i
c
a
n
o
m
a
l
y
d
e
t
e
c
t
i
o
n
a
l
g
o
r
i
t
h
m
f
o
r
w
i
r
e
l
e
ss
s
e
n
s
o
r
n
e
t
w
o
r
k
s
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
D
i
s
t
ri
b
u
t
e
d
S
e
n
s
o
r
N
e
t
w
o
rks
,
v
o
l
.
1
2
,
n
o
.
1
,
p
.
9
6
5
3
2
3
0
,
J
a
n
.
2
0
1
6
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
1
6
/
9
6
5
3
2
3
0
.
[
9
]
F
.
G
i
a
n
n
o
n
i
,
M
.
M
a
n
c
i
n
i
,
a
n
d
F
.
M
a
r
i
n
e
l
l
i
,
“
A
n
o
ma
l
y
d
e
t
e
c
t
i
o
n
m
o
d
e
l
s f
o
r
I
o
T
t
i
m
e
ser
i
e
s
d
a
t
a
,
”
ArX
i
v
(
Pr
e
p
i
n
t
)
,
2
0
1
8
.
[
1
0
]
M
.
B
r
a
e
i
a
n
d
S
.
W
a
g
n
e
r
,
“
A
n
o
ma
l
y
d
e
t
e
c
t
i
o
n
i
n
u
n
i
v
a
r
i
a
t
e
t
i
me
-
s
e
r
i
e
s
:
a
su
r
v
e
y
o
n
t
h
e
st
a
t
e
-
of
-
t
h
e
-
a
r
t
,
”
ArX
i
v
(
Pre
p
i
n
t
)
,
2
0
2
0
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
:
/
/
a
r
x
i
v
.
o
r
g
/
a
b
s/
2
0
0
4
.
0
0
4
3
3
[
1
1
]
L.
Er
h
a
n
e
t
a
l
.
,
“
S
mart
a
n
o
m
a
l
y
d
e
t
e
c
t
i
o
n
i
n
s
e
n
so
r
s
y
st
e
ms:
a
m
u
l
t
i
-
p
e
r
sp
e
c
t
i
v
e
r
e
v
i
e
w
,
”
I
n
f
o
rm
a
t
i
o
n
Fu
s
i
o
n
,
v
o
l
.
6
7
,
p
p
.
6
4
–
7
9
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
f
f
u
s.
2
0
2
0
.
1
0
.
0
0
1
.
[
1
2
]
P
.
O
ser,
F
.
E
n
g
e
l
ma
n
n
,
S
.
L
ü
d
e
r
s,
a
n
d
F
.
K
a
r
g
l
,
“
E
v
a
l
u
a
t
i
n
g
t
h
e
f
u
t
u
r
e
d
e
v
i
c
e
s
e
c
u
r
i
t
y
r
i
sk
i
n
d
i
c
a
t
o
r
f
o
r
h
u
n
d
r
e
d
s o
f
I
o
T
d
e
v
i
c
e
s,”
i
n
L
e
c
t
u
re
N
o
t
e
s
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
i
n
c
l
u
d
i
n
g
s
u
b
seri
e
s
L
e
c
t
u
re
N
o
t
e
s
i
n
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
L
e
c
t
u
re
N
o
t
e
s
i
n
Bi
o
i
n
f
o
rm
a
t
i
c
s)
,
v
o
l
.
1
3
8
6
7
LN
C
S
,
2
0
2
3
,
p
p
.
5
2
–
7
0
,
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
1
-
2
9
5
0
4
-
1
_
3
.
[
1
3
]
I
.
K
a
l
o
u
p
t
s
o
g
l
o
u
,
D
.
T
s
o
u
k
a
l
a
s
,
M
.
S
i
a
v
v
a
s
,
D
.
K
e
h
a
g
i
a
s
,
A
.
C
h
a
t
z
i
g
e
o
r
g
i
o
u
,
a
n
d
A
.
A
m
p
a
t
z
o
g
l
o
u
,
“
T
i
m
e
s
e
r
i
e
s
f
o
r
e
c
a
s
t
i
n
g
o
f
s
o
f
t
w
a
r
e
v
u
l
n
e
r
a
b
i
l
i
t
i
e
s
u
s
i
n
g
s
t
a
t
i
s
t
i
c
a
l
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
m
o
d
e
l
s
,
”
E
l
e
c
t
r
o
n
i
c
s
,
v
o
l
.
1
1
,
n
o
.
1
8
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
1
1
1
8
2
8
2
0
.
[
1
4
]
N
.
A
w
a
n
g
,
G
.
A
.
N
.
S
a
m
y
,
N
.
H
.
H
a
ssan
,
N
.
M
a
a
r
o
p
,
a
n
d
S
.
P
e
r
u
ma
l
,
“
I
mp
l
e
me
n
t
a
t
i
o
n
o
f
S
A
R
I
M
A
a
l
g
o
r
i
t
h
m
i
n
u
n
d
e
r
st
a
n
d
i
n
g
c
y
b
e
r
se
c
u
r
i
t
y
t
h
r
e
a
t
s
i
n
u
n
i
v
e
r
si
t
y
n
e
t
w
o
r
k
,
”
T
u
r
k
i
s
h
O
n
l
i
n
e
J
o
u
rn
a
l
o
f
Q
u
a
l
i
t
a
t
i
v
e
I
n
q
u
i
ry
(
T
O
J
Q
I
)
,
v
o
l
.
6
,
n
o
.
3
,
p
p
.
8
4
4
2
–
8
4
5
1
,
2
0
2
2
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
j
o
u
r
n
a
l
p
p
w
.
c
o
m
/
i
n
d
e
x
.
p
h
p
/
j
p
s
p
/
a
r
t
i
c
l
e
/
v
i
e
w
/
5
1
1
0
[
1
5
]
D
.
S
a
mar
i
y
a
a
n
d
A
.
T
h
a
k
k
a
r
,
“
A
c
o
m
p
r
e
h
e
n
si
v
e
s
u
r
v
e
y
o
f
a
n
o
m
a
l
y
d
e
t
e
c
t
i
o
n
a
l
g
o
r
i
t
h
ms
,
”
An
n
a
l
s o
f
D
a
t
a
S
c
i
e
n
c
e
,
v
o
l
.
1
0
,
n
o
.
3
,
p
p
.
8
2
9
–
8
5
0
,
N
o
v
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s4
0
7
4
5
-
021
-
0
0
3
6
2
-
9.
[
1
6
]
F
.
H
a
f
e
e
z
,
U
.
U
.
S
h
e
i
k
h
,
A
.
K
h
i
d
r
a
n
i
,
M
.
A
.
B
h
a
y
o
,
S
.
M
.
A
b
d
a
l
l
a
h
A
l
t
b
a
w
i
,
a
n
d
T
.
A
.
Ju
m
a
n
i
,
“
D
i
s
t
a
n
t
t
e
m
p
e
r
a
t
u
r
e
a
n
d
h
u
m
i
d
i
t
y
m
o
n
i
t
o
r
i
n
g
:
P
r
e
d
i
c
t
i
o
n
a
n
d
mea
s
u
r
e
me
n
t
,
”
I
n
d
o
n
e
s
i
a
n
J
o
u
r
n
a
l
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r S
c
i
e
n
c
e
,
v
o
l
.
2
4
,
n
o
.
3
,
p
p
.
1
4
0
5
–
1
4
1
3
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s
.
v
2
4
.
i
3
.
p
p
1
4
0
5
-
1
4
1
3
.
[
1
7
]
N
.
S
.
N
o
r
d
i
n
e
t
a
l
.
,
“
A
c
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
si
s
o
f
met
a
h
e
u
r
i
st
i
c
a
l
g
o
r
i
t
h
m
s
i
n
f
u
z
z
y
m
o
d
e
l
l
i
n
g
f
o
r
p
h
i
sh
i
n
g
a
t
t
a
c
k
d
e
t
e
c
t
i
o
n
,
”
I
n
d
o
n
e
si
a
n
J
o
u
rn
a
l
o
f
E
l
e
c
t
r
i
c
a
l
En
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
3
,
n
o
.
2
,
p
p
.
1
1
4
6
–
1
1
5
8
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
2
3
.
i
2
.
p
p
1
1
4
6
-
1
1
5
8
.
[
1
8
]
R
.
V
a
n
D
e
n
G
o
o
r
b
e
r
g
h
,
M
.
V
a
n
S
me
d
e
n
,
D
.
T
i
mm
e
r
m
a
n
,
a
n
d
B
e
n
V
a
n
C
a
l
st
e
r
,
“
T
h
e
h
a
r
m
o
f
c
l
a
ss i
m
b
a
l
a
n
c
e
c
o
r
r
e
c
t
i
o
n
s f
o
r
r
i
sk
p
r
e
d
i
c
t
i
o
n
m
o
d
e
l
s
:
I
l
l
u
s
t
r
a
t
i
o
n
a
n
d
si
mu
l
a
t
i
o
n
u
s
i
n
g
l
o
g
i
s
t
i
c
r
e
g
r
e
ssi
o
n
,
”
J
o
u
r
n
a
l
o
f
t
h
e
Am
e
ri
c
a
n
Me
d
i
c
a
l
I
n
f
o
rm
a
t
i
c
s
Asso
c
i
a
t
i
o
n
,
v
o
l
.
2
9
,
n
o
.
9
,
p
p
.
1
5
2
5
–
1
5
3
4
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
9
3
/
j
a
m
i
a
/
o
c
a
c
0
9
3
.
[
1
9
]
W
.
A
.
F
u
l
l
e
r
,
I
n
t
r
o
d
u
c
t
i
o
n
t
o
s
t
a
t
i
s
t
i
c
a
l
t
i
m
e
ser
i
e
s
,
v
o
l
.
2
0
,
n
o
.
2
.
i
n
W
i
l
e
y
S
e
r
i
e
s
i
n
P
r
o
b
a
b
i
l
i
t
y
a
n
d
S
t
a
t
i
st
i
c
s,
v
o
l
.
2
0
,
W
i
l
e
y
,
1
9
9
5
.
d
o
i
:
1
0
.
1
0
0
2
/
9
7
8
0
4
7
0
3
1
6
9
1
7
.
[
2
0
]
H
.
G
.
H
a
m
i
d
a
n
d
Z.
T
.
A
l
i
sa
,
“
A
s
u
r
v
e
y
o
n
I
o
T
a
p
p
l
i
c
a
t
i
o
n
l
a
y
e
r
p
r
o
t
o
c
o
l
s,”
I
n
d
o
n
e
si
a
n
J
o
u
rn
a
l
o
f
E
l
e
c
t
r
i
c
a
l
En
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
1
,
n
o
.
3
,
p
.
1
6
6
3
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
2
1
.
i
3
.
p
p
1
6
6
3
-
1
6
7
2
.
[
2
1
]
J.
S
c
o
t
t
A
r
mstr
o
n
g
,
“
R
e
se
a
r
c
h
n
e
e
d
s
i
n
f
o
r
e
c
a
st
i
n
g
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
F
o
rec
a
s
t
i
n
g
,
v
o
l
.
4
,
n
o
.
3
,
p
p
.
4
4
9
–
4
6
5
,
J
a
n
.
1
9
8
8
,
d
o
i
:
1
0
.
1
0
1
6
/
0
1
6
9
-
2
0
7
0
(
8
8
)
9
0
1
1
1
-
2.
[
2
2
]
A
.
A
.
A
b
b
o
o
d
,
Q
.
M
.
S
h
a
l
l
a
l
,
a
n
d
M
.
A
.
F
a
d
h
e
l
,
“
I
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
(
I
o
T)
:
A
t
e
c
h
n
o
l
o
g
y
r
e
v
i
e
w
,
s
e
c
u
r
i
t
y
i
ss
u
e
s,
t
h
r
e
a
t
s
,
a
n
d
o
p
e
n
c
h
a
l
l
e
n
g
e
s,”
I
n
d
o
n
e
s
i
a
n
J
o
u
rn
a
l
o
f
E
l
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
0
,
n
o
.
3
,
p
p
.
1
6
8
5
–
1
6
9
2
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
2
0
.
i
3
.
p
p
1
6
8
5
-
1
6
9
2
.
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
:
1
845
-
1
8
5
4
1854
[
2
3
]
S
.
C
.
P
o
h
,
Y
.
F
.
T
a
n
,
S
.
N
.
C
h
e
o
n
g
,
C
.
P
.
O
o
i
,
a
n
d
W
.
H
.
Ta
n
,
“
A
n
o
ma
l
y
d
e
t
e
c
t
i
o
n
f
o
r
h
o
m
e
a
c
t
i
v
i
t
y
b
a
se
d
o
n
s
e
q
u
e
n
c
e
p
a
t
t
e
r
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
0
,
n
o
.
7
,
p
p
.
1
2
7
6
–
1
2
8
5
,
N
o
v
.
2
0
1
9
,
d
o
i
:
1
0
.
1
4
7
1
6
/
i
j
t
e
c
h
.
v
1
0
i
7
.
3
2
3
0
.
[
2
4
]
D
.
B
e
n
i
a
g
u
e
v
,
“
H
i
st
o
r
i
c
a
l
H
o
u
r
l
y
W
e
a
t
h
e
r
D
a
t
a
2
0
1
2
-
2
0
1
7
.
”
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
k
a
g
g
l
e
.
c
o
m
/
d
a
t
a
se
t
s/
s
e
l
f
i
sh
g
e
n
e
/
h
i
st
o
r
i
c
a
l
-
h
o
u
r
l
y
-
w
e
a
t
h
e
r
-
d
a
t
a
[
2
5
]
J.
W
o
l
t
e
r
s
a
n
d
U
.
H
a
ss
l
e
r
,
“
U
n
i
t
r
o
o
t
t
e
st
i
n
g
,
”
Al
l
g
e
m
e
i
n
e
s
S
t
a
t
i
s
t
i
s
c
h
e
s
Arc
h
i
v
,
v
o
l
.
9
0
,
n
o
.
1
,
p
p
.
4
3
–
5
8
,
M
a
r
.
2
0
0
6
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
1
8
2
-
0
0
6
-
0
2
2
0
-
6.
[
2
6
]
S
.
F
.
M
.
H
u
s
sei
n
e
t
a
l
.
,
“
B
l
a
c
k
b
o
x
mo
d
e
l
l
i
n
g
a
n
d
si
m
u
l
a
t
i
n
g
t
h
e
d
y
n
a
m
i
c
i
n
d
o
o
r
a
i
r
t
e
m
p
e
r
a
t
u
r
e
o
f
a
l
a
b
o
r
a
t
o
r
y
u
s
i
n
g
(
A
R
M
A
)
mo
d
e
l
,
”
I
n
d
o
n
e
si
a
n
J
o
u
r
n
a
l
o
f
El
e
c
t
ri
c
a
l
En
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
1
,
n
o
.
2
,
p
p
.
7
9
1
–
8
0
0
,
F
e
b
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
2
1
.
i
2
.
p
p
7
9
1
-
8
0
0
.
[
2
7
]
K
.
E
.
A
r
u
n
K
u
mar,
D
.
V
.
K
a
l
a
g
a
,
C
.
M
o
h
a
n
S
a
i
K
u
m
a
r
,
M
.
K
a
w
a
j
i
,
a
n
d
T
.
M
.
B
r
e
n
z
a
,
“
C
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
si
s
o
f
G
a
t
e
d
R
e
c
u
r
r
e
n
t
U
n
i
t
s
(
G
R
U
)
,
l
o
n
g
S
h
o
r
t
-
T
e
r
m
m
e
mo
r
y
(
LST
M
)
c
e
l
l
s,
a
u
t
o
r
e
g
r
e
s
si
v
e
I
n
t
e
g
r
a
t
e
d
m
o
v
i
n
g
a
v
e
r
a
g
e
(
A
R
I
M
A
)
,
sea
s
o
n
a
l
a
u
t
o
r
e
g
r
e
ss
i
v
e
I
n
t
e
g
r
a
t
e
d
m
o
v
i
n
g
a
v
e
r
a
g
e
(
S
A
R
I
M
A
)
f
o
r
f
o
r
e
c
a
s
t
i
n
g
C
O
V
I
D
-
1
9
t
r
e
n
d
s
,
”
A
l
e
x
a
n
d
r
i
a
En
g
i
n
e
e
ri
n
g
J
o
u
r
n
a
l
,
v
o
l
.
6
1
,
n
o
.
1
0
,
p
p
.
7
5
8
5
–
7
6
0
3
,
O
c
t
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
e
j
.
2
0
2
2
.
0
1
.
0
1
1
.
[
2
8
]
H
.
B
o
z
d
o
g
a
n
,
“
M
o
d
e
l
s
e
l
e
c
t
i
o
n
a
n
d
A
k
a
i
k
e
’
s
I
n
f
o
r
mat
i
o
n
C
r
i
t
e
r
i
o
n
(
A
I
C
)
:
Th
e
g
e
n
e
r
a
l
t
h
e
o
r
y
a
n
d
i
t
s
a
n
a
l
y
t
i
c
a
l
e
x
t
e
n
s
i
o
n
s,
”
Psy
c
h
o
m
e
t
r
i
k
a
,
v
o
l
.
5
2
,
n
o
.
3
,
p
p
.
3
4
5
–
3
7
0
,
S
e
p
.
1
9
8
7
,
d
o
i
:
1
0
.
1
0
0
7
/
B
F
0
2
2
9
4
3
6
1
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Mo
u
n
a
B
o
u
jr
a
d
re
c
e
iv
e
d
h
e
r
M
a
ste
r'
s
d
e
g
re
e
in
Cy
b
e
r
-
c
ri
m
in
a
li
ty
a
n
d
c
y
b
e
rse
c
u
rit
y
fr
o
m
t
h
e
Na
ti
o
n
a
l
S
c
h
o
o
l
o
f
Ap
p
li
e
d
sc
ien
c
e
in
Ta
n
g
ier,
M
o
r
o
c
c
o
.
S
h
e
is
c
u
rre
n
tl
y
a
P
h
.
D.
stu
d
e
n
t
a
t
th
e
fa
c
u
lt
y
o
f
sc
ien
c
e
s,
M
o
h
a
m
m
e
d
F
irst
Un
iv
e
rsity
i
n
Ou
jd
a
,
M
o
ro
c
c
o
.
He
r
re
se
a
rc
h
a
re
a
is
o
n
Artifi
c
ial
I
n
telli
g
e
n
c
e
fo
r
a
n
o
m
a
ly
d
e
tec
ti
o
n
o
n
Io
T
sy
ste
m
s.
He
r
re
se
a
rc
h
in
tere
sts
i
n
c
lu
d
e
se
c
u
rit
y
,
i
n
tern
e
t
o
f
t
h
in
g
s,
so
ft
c
o
m
p
u
ti
n
g
a
n
d
a
rti
ficia
l
in
telli
g
e
n
c
e
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
o
u
n
a
.
b
o
u
jrad
@g
m
a
il
.
c
o
m
.
Mo
h
a
m
m
e
d
A
m
i
n
e
K
a
sm
i
re
c
e
iv
e
d
h
is
P
h
.
D.
i
n
c
o
m
p
u
ter
sc
ien
c
e
fro
m
M
o
h
a
m
m
e
d
F
irst
Un
iv
e
rsity
in
Ou
jd
a
,
M
o
ro
c
c
o
.
He
is
c
u
rre
n
tl
y
a
se
n
io
r
lec
tu
re
r
a
t
th
e
fa
c
u
lt
y
o
f
sc
ien
c
e
s,
M
o
h
a
m
m
e
d
F
irst
U
n
iv
e
rsit
y
i
n
Ou
j
d
a
,
M
o
ro
c
c
o
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
c
o
m
p
u
ter
sc
ien
c
e
se
c
u
rit
y
,
i
n
tern
e
t
o
f
th
i
n
g
s
a
n
d
a
rti
ficia
l
in
telli
g
e
n
c
e
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
.
k
a
sm
i@u
m
p
.
a
c
.
m
a
.
No
u
r
a
O
u
e
r
d
i
re
c
e
iv
e
d
h
e
r
P
h
.
D.
i
n
c
o
m
p
u
ter
sc
ien
c
e
fro
m
M
o
h
a
m
m
e
d
F
irst
Un
i
v
e
rsity
i
n
Ou
j
d
a
,
M
o
ro
c
c
o
.
S
h
e
is
c
u
rre
n
tl
y
a
se
n
io
r
le
c
tu
re
r
a
t
th
e
fa
c
u
lt
y
o
f
sc
ien
c
e
s,
M
o
h
a
m
m
e
d
F
irst
Un
i
v
e
rsity
i
n
O
u
jd
a
,
M
o
ro
c
c
o
.
He
r
re
se
a
rc
h
in
tere
sts
in
c
l
u
d
e
c
o
m
p
u
ter
sc
ien
c
e
se
c
u
rit
y
,
i
n
ter
n
e
t
o
f
t
h
in
g
s
a
n
d
a
rti
ficia
l
in
telli
g
e
n
c
e
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
n
.
o
u
e
rd
i@u
m
p
.
a
c
.
m
a
.
Ya
ss
e
r
La
m
li
li
E
l
M
a
z
o
u
i
N
a
d
o
r
i
is a Dr.
a
t
M
o
h
a
m
m
e
d
F
irst
Un
iv
e
rsity
i
n
th
e
F
a
c
u
lt
y
o
f
S
c
ien
c
e
s.
He
g
o
t
a
d
e
g
re
e
i
n
e
n
g
i
n
e
e
rin
g
in
Co
m
p
u
ter
S
c
ien
c
e
s
fr
o
m
t
h
e
Na
ti
o
n
a
l
S
c
h
o
o
l
o
f
A
p
p
li
e
d
S
c
i
e
n
c
e
s
a
t
Ou
jd
a
.
He
re
c
e
iv
e
d
h
is
M
.
S
c
.
d
e
g
re
e
in
Ne
w
In
fo
rm
a
ti
o
n
a
n
d
C
o
m
m
u
n
ica
ti
o
n
Tec
h
n
o
l
o
g
ies
fr
o
m
th
e
fa
c
u
lt
y
o
f
sc
ien
c
e
s
a
n
d
Tec
h
n
iq
u
e
s
a
t
S
id
i
M
o
h
a
m
e
d
Be
n
Ab
d
e
ll
a
h
Un
i
v
e
rsity
.
His
re
se
a
rc
h
a
c
ti
v
it
ies
a
t
th
e
M
ATS
I
Lab
o
ra
to
r
y
(Ap
p
li
e
d
M
a
th
e
m
a
ti
c
s,
S
ig
n
a
l
P
ro
c
e
ss
in
g
,
a
n
d
C
o
m
p
u
ter
S
c
ien
c
e
)
h
a
v
e
fo
c
u
se
d
o
n
we
b
m
a
rk
e
ti
n
g
in
so
c
ial
n
e
two
rk
s
u
si
n
g
t
h
e
M
DA
(M
o
d
e
l
Driv
e
n
Arc
h
it
e
c
tu
re
)
a
p
p
r
o
a
c
h
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
l
a
m
li
li
y
a
ss
e
r
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.