T
E
L
KO
M
N
I
KA
T
e
lec
om
m
u
n
icat
ion
,
Com
p
u
t
i
n
g,
E
lec
t
r
on
ics
an
d
Cont
r
ol
Vol.
18
,
No.
3
,
J
une
2020
,
pp.
1475
~
1482
I
S
S
N:
1693
-
6930,
a
c
c
r
e
dit
e
d
F
ir
s
t
G
r
a
de
by
Ke
me
nr
is
tekdikti
,
De
c
r
e
e
No:
21/E
/KP
T
/2018
DO
I
:
10.
12928/
T
E
L
KO
M
NI
KA
.
v18i3.
14835
1475
Jou
r
n
al
h
omepage
:
ht
tp:
//
jour
nal.
uad
.
ac
.
id/
index
.
php/T
E
L
K
OM
N
I
K
A
T
ow
ar
d
s c
og
n
itive
a
r
t
ific
ia
l
i
n
t
e
ll
ig
e
n
c
e
d
e
vi
c
e
:
an
i
n
t
e
ll
ig
e
n
t
p
r
o
c
e
sso
r
b
ase
d
on
h
u
m
an
t
h
i
n
k
in
g
e
m
u
la
t
io
n
C
a
t
he
r
i
ne
O
l
i
v
i
a
Se
r
e
a
t
i
1
,
A
r
w
i
n
Da
t
um
a
y
a
W
a
hy
u
di
S
um
a
r
i
2
,
T
r
i
o
Ad
i
o
no
3
,
A
da
ng
S
uw
a
nd
i
A
hm
a
d
4
1
D
ep
a
rt
m
e
n
t
o
f
E
l
e
ct
r
i
c
al
E
n
g
i
n
e
e
ri
n
g
,
U
n
i
v
e
rs
i
t
as
K
at
o
l
i
k
I
n
d
o
n
es
i
a
A
t
m
a
J
a
y
a
J
ak
a
rt
a
,
In
d
o
n
es
i
a
2
D
ep
ar
t
men
t
o
f
E
l
ect
r
i
cal
E
n
g
i
n
eeri
n
g
,
St
a
t
e
Po
l
y
t
ec
h
n
i
c
o
f
Mal
an
g
,
In
d
o
n
e
s
i
a
2
Facu
l
t
y
o
f
D
efen
s
e
T
ech
n
o
l
o
g
y
,
In
d
o
n
es
i
a
D
efe
n
s
e
U
n
i
v
ers
i
t
y
,
In
d
o
n
e
s
i
a
3,
4
Sch
o
o
l
o
f
E
l
ect
r
i
cal
E
n
g
i
n
eer
i
n
g
an
d
In
f
o
rmat
i
cs
,
In
s
t
i
t
u
t
T
ek
n
o
l
o
g
i
Ba
n
d
u
n
g
,
In
d
o
n
e
s
i
a
Ar
t
icle
I
n
f
o
AB
S
T
RA
CT
A
r
ti
c
le
h
is
tor
y
:
R
e
c
e
ived
Aug
15
,
2019
R
e
vis
e
d
J
a
n
20
,
2020
Ac
c
e
pted
F
e
b
23
,
2020
T
h
e
i
n
t
er
v
en
t
i
o
n
o
f
co
m
p
u
t
er
t
ech
n
o
l
o
g
y
b
e
g
a
n
t
h
e
era
o
f
a
mo
re
i
n
t
e
l
l
i
g
e
n
t
an
d
i
n
d
e
p
en
d
en
t
i
n
s
t
ru
m
en
t
at
i
o
n
s
y
s
t
em
b
as
e
d
o
n
i
n
t
el
l
i
g
en
t
met
h
o
d
s
s
u
ch
a
s
art
i
f
i
ci
a
l
n
eu
ra
l
n
e
t
w
o
rk
s
,
fu
zzy
l
o
g
i
c,
an
d
g
e
n
et
i
c
al
g
o
ri
t
h
m
.
O
n
t
h
e
o
t
h
er
h
an
d
,
p
ro
ces
s
o
r
w
i
t
h
art
i
f
i
ci
a
l
co
g
n
i
t
i
v
e
ab
i
l
i
t
y
h
a
s
al
s
o
b
een
d
i
s
co
v
ere
d
i
n
2
0
1
6
.
T
h
e
arch
i
t
ec
t
u
re
o
f
t
h
e
p
ro
ce
s
s
o
r
w
as
d
e
s
i
g
n
e
d
b
as
e
d
o
n
k
n
o
w
l
ed
g
e
g
ro
w
i
n
g
s
y
s
t
em
(
K
G
S)
al
g
o
r
i
t
h
m,
a
n
e
w
co
n
ce
p
t
in
ar
t
i
f
i
ci
a
l
i
n
t
e
l
l
i
g
e
n
ce
(
A
I)
w
h
i
ch
i
s
fo
cu
s
ed
on
t
he
emu
l
a
t
i
o
n
o
f
t
h
e
p
ro
ce
s
s
o
f
t
h
e
g
ro
w
i
n
g
o
f
k
n
o
w
l
ed
g
e
in
h
u
ma
n
b
rai
n
aft
er
g
et
t
i
n
g
n
e
w
i
n
f
o
rm
at
i
o
n
fro
m
h
u
man
s
en
s
o
ry
o
r
g
an
s
.
K
G
S
i
s
co
n
s
i
d
ered
as
t
h
e
mai
n
me
t
h
o
d
o
f
a
n
ew
p
ers
p
ect
i
v
e
i
n
A
I
cal
l
ed
as
co
g
n
i
t
i
v
e
art
i
fi
c
i
al
i
n
t
e
l
l
i
g
e
n
ce
(CA
I).
T
h
e
d
es
i
g
n
i
s
t
o
o
b
t
a
i
n
t
h
e
arc
h
i
t
ec
t
u
re
o
f
t
h
e
d
at
a
p
a
t
h
o
f
t
h
e
p
ro
ces
s
o
r
.
W
e
fo
u
n
d
t
h
at
t
h
e
co
mp
l
ex
i
t
y
o
f
t
h
e
p
r
o
ces
s
o
r
ci
rcu
i
t
is
d
et
erm
i
n
e
d
b
y
t
h
e
n
u
mb
er
o
f
co
m
b
i
n
at
i
o
n
s
o
f
s
e
n
s
o
r
s
an
d
h
y
p
o
t
h
es
e
s
as
t
h
e
mai
n
i
n
p
u
t
s
t
o
t
h
e
p
r
o
ces
s
o
r
.
T
h
i
s
p
ap
er
a
d
d
re
s
s
e
s
t
h
e
d
e
v
el
o
p
me
n
t
o
f
an
i
n
t
e
l
l
i
g
e
n
ce
p
r
o
ces
s
o
r
b
a
s
ed
o
n
c
o
g
n
i
t
i
v
e
AI
i
n
o
rd
er
t
o
r
eal
i
ze
an
In
t
e
l
l
i
g
e
n
ce
In
s
t
r
u
me
n
t
a
t
i
o
n
Sy
s
t
em.
T
h
e
p
ro
ce
s
s
o
r
i
s
i
mp
l
emen
t
ed
in
fi
e
l
d
p
ro
g
rammab
l
e
g
a
t
e
arra
y
(
FPG
A
)
a
n
d
a
b
l
e
t
o
p
erf
o
rm
h
u
man
t
h
i
n
k
i
n
g
emu
l
a
t
i
o
n
b
y
u
s
i
n
g
K
G
S
al
g
o
r
i
t
h
m.
K
e
y
w
o
r
d
s
:
C
ognit
ive
a
r
ti
f
icia
l
i
ntelli
ge
nc
e
Huma
n
thi
nking
e
mul
a
ti
on
I
ntelli
ge
nt
i
ns
tr
umenta
ti
on
I
ntelli
ge
nt
pr
oc
e
s
s
or
K
nowle
dge
gr
owing
s
ys
tem
Th
i
s
i
s
a
n
o
p
en
a
c
ces
s
a
r
t
i
c
l
e
u
n
d
e
r
t
h
e
CC
B
Y
-
SA
l
i
ce
n
s
e
.
C
or
r
e
s
pon
din
g
A
u
th
or
:
C
a
ther
ine
Olivi
a
S
e
r
e
a
ti
,
De
pa
r
tm
e
nt
of
E
lec
tr
ica
l
E
nginee
r
ing,
Uni
v
e
r
s
i
t
a
s
Ka
t
o
l
i
k
I
n
d
o
n
e
s
i
a
At
ma
J
a
y
a
.
J
e
nde
r
a
l
S
udir
man
S
t
.
Ka
v
51
,
J
a
ka
r
ta
,
I
ndone
s
ia
E
mail:
c
a
ther
ine.
o
li
via@
a
tm
a
jaya
.
a
c
.
id
1.
I
NT
RODU
C
T
I
ON
T
h
e
de
ma
nds
o
f
i
nt
e
l
li
ge
nt
ins
t
r
u
men
ta
t
io
n
s
ys
t
e
m
a
r
e
i
nc
r
e
a
s
i
ng
.
O
ne
o
f
th
e
s
ys
tem
’
s
c
a
pa
bi
l
it
y
is
a
ut
on
o
mo
us
c
a
l
ib
r
a
t
io
n
,
w
he
r
e
s
e
ns
o
r
s
in
de
pe
nde
nt
l
y
c
a
r
r
y
ou
t
c
a
l
i
br
a
t
io
n
du
e
to
th
e
mea
s
u
r
e
me
nt
r
e
s
ul
ts
o
f
d
r
i
f
ts
t
ha
t
a
r
e
a
f
f
e
c
te
d
by
t
he
e
nv
i
r
o
n
men
t
[
1]
.
C
h
a
n
ge
s
i
n
a
na
lo
g
s
ys
t
e
ms
t
o
d
ig
i
ta
l
o
ne
s
i
nc
r
e
a
s
i
ng
ly
i
m
p
r
o
ve
t
he
p
r
e
c
is
i
on
o
f
ins
t
r
u
me
nt
a
t
io
n
s
ys
te
ms
.
T
he
de
ve
lo
p
men
t
o
f
a
r
t
if
ic
ia
l
in
te
l
li
ge
nc
e
(
A
I
)
a
dds
t
he
c
o
m
pl
e
x
i
ty
o
f
i
ns
t
r
u
me
nta
t
io
n
s
ys
t
e
ms
b
u
t
pr
e
s
e
nts
s
m
a
r
t
e
r
o
ne
s
a
nd
o
pe
ns
wi
de
o
p
p
o
r
t
un
it
ies
f
o
r
m
o
r
e
s
pe
c
i
a
l
ize
d
us
e
a
nd
a
ut
on
o
mo
us
ins
t
r
u
me
nt
a
t
io
n
[
2
]
.
T
he
d
e
ve
l
op
men
t
o
f
C
A
I
w
a
s
t
r
i
gg
e
r
e
d
b
y
t
he
d
is
c
ove
r
y
o
f
c
o
g
ni
ti
ve
c
ha
r
a
c
te
r
is
ti
c
s
ho
ws
by
th
e
b
r
a
in
w
he
n
ge
ne
r
a
ti
ng
ne
w
kn
ow
led
ge
.
W
e
c
a
ll
th
is
me
c
ha
n
is
m
a
s
kn
ow
le
dge
g
r
ow
in
g
(
K
G
)
w
he
r
e
th
e
k
no
wl
e
d
ge
is
o
b
tai
ne
d
a
f
te
r
th
e
b
r
a
in
e
x
t
r
a
c
te
d
ne
w
i
nf
e
r
e
n
c
i
ng
f
r
om
t
he
f
us
i
on
o
f
i
nf
o
r
m
a
t
io
n
de
l
i
ve
r
e
d
f
r
om
s
e
n
s
o
r
y
o
r
g
a
ns
a
f
te
r
c
a
r
r
y
in
g
o
ut
i
nte
r
a
c
ti
on
to
t
he
w
o
r
l
d
.
T
he
r
e
f
o
r
e
,
w
e
c
a
l
l
a
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
1693
-
6930
T
E
L
KO
M
NI
KA
T
e
lec
omm
un
C
omput
E
l
C
ontr
o
l
,
Vol.
18
,
No
.
3
,
J
une
2020:
1475
-
1482
1476
s
ys
t
e
m
t
ha
t
ha
s
a
b
il
it
y
t
o
g
r
o
w
i
ts
ow
n
k
no
wle
d
ge
a
s
kn
ow
led
ge
g
r
ow
in
g
s
ys
te
m
(
KG
S
)
a
l
on
g
w
it
h
i
ts
c
om
pu
ta
t
io
na
l
me
ho
d
.
T
h
e
de
v
e
l
op
me
nt
o
f
KG
S
a
s
t
he
m
a
i
n
e
ng
in
e
of
C
AI
o
pe
ns
the
o
pp
o
r
t
un
it
y
to
c
r
e
a
te
a
n
i
nt
e
l
l
ige
n
t
i
ns
t
r
u
me
nta
t
io
n
s
ys
te
m
wh
e
r
e
it
s
i
nt
e
l
li
ge
nc
e
is
s
h
ow
n
wi
th
t
he
c
o
gn
it
iv
e
a
b
il
it
y
pu
t
in
i
t
.
T
h
is
k
in
d
o
f
in
te
l
li
ge
nt
i
ns
t
r
u
me
nta
t
io
n
s
ys
te
m
c
a
n
be
r
e
a
l
iz
e
d
by
e
mb
e
dd
i
ng
a
p
r
oc
e
s
s
o
r
tha
t
ha
s
c
og
ni
ti
ve
pr
op
e
r
t
ies
,
a
s
t
he
ma
in
c
on
t
r
o
ll
e
r
of
t
he
s
ys
te
m
.
B
y
im
p
lem
e
n
t
in
g
it
,
we
a
r
e
s
u
r
e
t
ha
t
a
p
r
oc
e
s
s
o
r
wh
ich
h
a
s
c
og
n
it
iv
e
a
bi
l
it
y
n
a
me
ly
,
e
mu
la
t
in
g
t
he
wa
y
o
f
hu
ma
n
th
in
ks
c
a
n
be
r
e
a
li
z
e
d
.
T
h
e
c
o
gn
it
iv
e
-
ba
s
e
d
p
r
o
c
e
s
s
o
r
t
he
n
w
il
l
be
us
e
d
t
o
s
up
po
r
t
t
he
de
ve
l
op
me
nt
in
te
ll
i
ge
n
t
i
ns
tr
um
e
n
ta
ti
on
s
ys
t
e
m
i
n
v
a
r
i
ous
f
i
e
l
ds
[3
–
8]
.
E
m
ul
a
t
in
g
t
he
w
a
y
o
f
h
u
man
th
in
ks
i
n
to
a
s
o
f
t
wa
r
e
c
o
mp
u
te
r
w
a
s
a
l
r
e
a
d
y
a
b
ig
c
h
a
l
le
ng
e
,
a
nd
i
t
wa
s
e
v
e
n
a
bi
gg
e
r
c
ha
ll
e
n
ge
to
i
mp
le
me
nt
i
t
i
nt
o
a
h
a
r
d
wa
r
e
[9
–
11
]
.
O
t
he
r
r
e
s
e
a
r
c
h
e
r
s
ha
ve
a
ls
o
men
t
io
ne
d
tha
t
th
e
c
og
ni
ti
ve
p
r
oc
e
s
s
o
r
s
ys
tem
de
s
i
gn
is
e
xp
e
c
ted
t
o
c
on
t
r
i
bu
te
to
th
e
de
ve
lo
pm
e
n
t
o
f
a
r
ti
f
ic
ial
in
te
ll
i
ge
nc
e
-
b
a
s
e
d
p
r
o
c
e
s
s
or
de
s
ig
ns
[
1
2
,
13
]
.
I
n
th
is
p
a
p
e
r
we
d
e
l
i
ve
r
e
d
the
tec
hn
iq
ue
t
o
i
mp
le
men
t
KG
S
c
o
m
pu
tat
i
on
m
e
t
ho
d
to
c
r
e
a
t
e
a
hu
ma
n
th
in
ki
ng
e
mu
la
t
io
n
pr
o
c
e
s
s
or
c
a
l
le
d
a
s
C
AI
p
r
o
c
e
s
s
o
r
o
r
s
i
mp
l
y
c
o
gn
i
ti
ve
p
r
oc
e
s
s
o
r
,
a
n
in
te
ll
i
ge
n
t
d
e
v
ice
f
o
r
i
nt
e
l
l
ige
nt
s
ys
te
m
.
2.
RE
S
E
AR
CH
M
E
T
HO
D
C
u
r
r
e
n
t
c
o
nv
e
n
ti
on
a
l
c
om
pu
t
in
g
me
th
ods
ba
s
e
d
on
A
I
mos
tl
y
o
bta
i
n
kn
ow
le
dge
ba
s
e
d
on
pa
s
t
da
ta
o
r
e
xp
e
r
ie
nc
e
s
a
n
d
n
ot
ye
t
e
q
u
ip
pe
d
wi
th
t
he
a
bi
li
t
y
to
ge
ne
r
a
te
kn
ow
led
ge
f
r
o
m
b
r
a
n
d
ne
w
da
ta
ob
ta
ine
d
f
r
o
m
d
i
r
e
c
t
ly
in
te
r
a
c
t
in
g
w
it
h
t
he
wo
r
ld
,
in
th
is
c
a
s
e
a
p
he
no
me
no
n
be
in
g
o
bs
e
r
ve
d
.
I
n
a
d
d
it
io
n
,
t
he
k
no
w
led
ge
g
e
n
e
r
a
t
e
d
b
y
t
he
e
xis
t
in
g
A
I
me
th
ods
a
r
e
s
t
il
l
l
im
i
ted
by
us
i
ng
e
xis
t
in
g
da
ta
t
o
p
r
od
uc
e
s
pe
c
i
f
i
c
go
a
ls
(
s
u
pe
r
vis
e
d
l
e
a
r
ni
ng
)
o
r
b
y
p
r
ov
id
i
ng
a
s
e
t
o
f
da
ta
to
s
e
e
t
he
f
o
r
m
o
f
i
ts
o
ut
pu
t
(
uns
upe
r
vis
e
d
le
a
r
n
in
g)
[
14
,
1
5
]
.
T
h
is
mea
ns
that
the
c
ur
r
e
nt
AI
c
omput
a
ti
ona
l
methods
a
r
e
c
ur
r
e
ntl
y
not
e
quipped
with
a
f
e
a
tur
e
whic
h
gives
them
a
n
a
bil
it
y
to
lea
r
n
s
omething
ne
w
f
r
om
the
in
f
or
mation
obtai
ne
d
f
r
om
thei
r
s
e
ns
or
y
or
ga
ns
that
pe
r
f
o
r
m
int
e
r
a
c
t
ions
to
a
phe
nomenon.
KG
S
c
omput
a
ti
on
is
ins
pir
e
d
by
t
he
wa
y
of
the
human
br
a
in
d
r
a
ws
c
onc
lus
ions
ba
s
e
d
on
inf
or
mation
r
e
c
e
ived
f
r
om
the
e
nvir
on
men
t
[
16
,
17]
.
T
he
ba
s
ic
c
onc
e
pt
of
KG
S
is
to
e
mul
a
te
the
wa
y
of
human’
s
br
a
in
de
ve
lops
ne
w
knowle
dge
f
r
om
the
inf
or
mation
de
li
ve
r
e
d
by
human
s
e
ns
or
y
or
ga
ns
ga
ther
e
d
f
r
om
the
phe
nomenon
the
human
int
e
r
a
c
ts
with
a
s
il
lus
tr
a
ted
in
F
igur
e
1
[
18
]
.
T
he
p
r
oc
e
s
s
to
g
a
in
ne
w
knowle
dge
is
s
tar
ted
by
s
e
ns
ing
the
phe
nomenon
a
nd
r
e
c
e
ivi
ng
the
in
f
or
mation
r
e
ga
r
ding
it
f
r
om
a
ll
s
e
ns
or
y
or
ga
ns
.
T
his
c
a
n
only
be
done
by
making
in
ter
a
c
ti
o
ns
with
the
obs
e
r
ve
d
phe
nomenon
us
ing
one
o
r
mo
r
e
s
e
ns
or
y
or
ga
ns
.
M
os
tl
y,
inf
or
mation
f
r
om
only
one
s
e
ns
or
s
c
a
n
only
give
a
li
tt
le
knowle
dge
r
e
ga
r
ding
the
phe
n
omenon.
B
y
ge
tt
ing
mor
e
inf
or
mation
f
r
om
va
r
ious
s
e
ns
or
y
or
ga
ns
,
then
human
c
a
n
ha
ve
mor
e
knowle
dge
a
n
d
be
a
ble
to
e
xplain
wha
t
the
phe
nomenon
be
ing
in
ter
a
c
ted
with.
I
n
f
o
r
m
a
t
i
o
n
F
u
s
i
o
n
I
N
F
O
R
M
A
T
I
O
N
F
U
S
I
O
N
S
1
O
B
S
E
R
V
A
T
I
O
N
F
R
O
M
S
E
N
S
O
R
Y
O
R
G
A
N
S
I
N
F
O
R
M
A
T
I
O
N
F
U
S
I
O
N
S
2
I
N
F
O
R
M
A
T
I
O
N
F
U
S
I
O
N
S
3
I
N
F
O
R
M
A
T
I
O
N
F
U
S
I
O
N
S
4
I
N
F
O
R
M
A
T
I
O
N
F
U
S
I
O
N
S
5
I
N
F
O
R
M
A
T
I
O
N
I
N
F
E
R
E
N
C
I
N
G
E
A
C
H
S
E
N
S
O
R
S
I
N
F
O
R
M
A
T
I
O
N
I
N
F
E
R
E
N
C
I
N
G
F
U
S
I
O
N
:
S
1
&
S
2
I
N
F
O
R
M
A
T
I
O
N
I
N
F
E
R
E
N
C
I
N
G
F
U
S
I
O
N
:
S
1
&
S
3
I
N
F
O
R
M
A
T
I
O
N
I
N
F
E
R
E
N
C
I
N
G
F
U
S
I
O
N
:
S
1
&
S
2
&
S
4
I
N
F
O
R
M
A
T
I
O
N
I
N
F
E
R
E
N
C
I
N
G
F
U
S
I
O
N
:
A
L
L
S
E
N
S
O
R
S
D
o
C
N
e
w
K
n
o
w
l
e
d
g
e
K
n
o
w
l
e
d
g
e
D
a
t
a
B
a
s
e
(
P
r
i
o
r
K
n
o
w
l
e
d
g
e
)
K
n
o
w
l
e
d
g
e
I
n
f
e
r
e
n
c
i
n
g
F
u
s
i
o
n
U
l
t
i
m
a
t
e
K
n
o
w
l
e
d
g
e
t
n
t
n
t
n
t
n
F
igur
e
1.
KG
S
mec
ha
nis
m
in
gr
owing
knowle
dge
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KO
M
NI
KA
T
e
lec
omm
un
C
omput
E
l
C
ontr
o
l
T
ow
ar
ds
c
ognit
ive
ar
ti
fi
c
ial
int
e
ll
igenc
e
de
v
ice
:
an
int
e
ll
igent
pr
oc
e
s
s
or
b
as
e
d
....
(
C
ather
ine
Olivia
S
e
r
e
ati
)
1477
T
he
inf
o
r
mation
de
li
ve
r
e
d
f
r
om
the
s
e
ns
or
y
or
ga
ns
is
f
us
e
d
to
obtain
c
ompr
e
he
ns
ive
inf
o
r
mation
.
E
a
c
h
f
us
e
d
inf
or
mation
will
it
s
own
p
r
oba
bil
it
y
v
a
lue
or
DoC
whic
h
r
e
pr
e
s
e
nts
the
knowle
dge
obt
a
ined
by
KG
S
a
bout
the
phe
nomenon.
E
a
c
h
c
ompr
e
he
ns
ive
inf
or
mation’
s
pr
oba
bil
it
y
va
lue
then
be
c
omes
ne
w
knowle
dge
whic
h
is
mea
s
ur
e
d
with
Do
C
.
DoC
r
e
pr
e
s
e
nts
the
va
lue
of
c
e
r
tainty
f
or
e
a
c
h
ne
w
kn
owle
dge
de
pe
nding
on
the
s
e
ns
or
y
or
ga
ns
’
in
f
or
mation
that
ha
s
be
e
n
f
us
e
d.
DoC
a
ls
o
s
hows
the
be
s
t
c
ombi
na
ti
on
of
s
e
ns
or
da
ta
a
nd
hypothes
e
s
that
may
oc
c
ur
r
e
lat
e
d
to
the
obs
e
r
ve
d
phe
nomenon.
T
he
p
r
oc
e
s
s
of
KG
S
is
de
s
c
r
ibed
b
y
two
f
or
mul
a
s
na
mely
ASS
A2010
(
Ar
win
S
umar
i
-
S
uwa
ndi
Ahma
d
2010)
method
f
or
s
ingl
e
obs
e
r
va
ti
on
ti
me,
a
nd
OM
-
ASS
A2010
(
obs
e
r
va
ti
on
mul
ti
ti
m
e
Ar
win
S
umar
i
-
S
uwa
ndi
Ahma
d
2
010)
f
o
r
mul
ti
ple
obs
e
r
va
ti
on
ti
me
a
s
s
hown
in
(
1
)
.
T
h
e
r
e
s
ult
s
a
r
e
in
the
f
or
m
o
f
ne
w
knowle
dge
pr
oba
bil
it
y
dis
tr
ibut
io
n
(
NK
P
D)
na
mely
,
the
li
s
t
of
knowle
dge
of
the
s
ys
tem
r
e
ga
r
ding
the
obs
e
r
ve
d
phe
nomenon
ba
s
e
d
on
the
obs
e
r
ve
d
da
ta
f
r
om
the
s
e
ns
or
y
or
ga
ns
[
19]
.
NK
P
D
is
knowle
dge
obtaine
d
f
r
om
s
ingl
e
obs
e
r
va
t
ion
ti
me
while
NK
P
D
ove
r
t
im
e
(
NK
P
DT
)
is
the
ult
i
mate
k
nowle
dge
of
the
s
ys
tem
a
f
ter
pe
r
f
or
mi
ng
a
c
omput
a
ti
on
to
inf
or
mation
f
r
om
mul
ti
ple
ti
mes
of
obs
e
r
va
ti
on.
1
()
()
i
t
t
t
P
P
=
=
(
1)
w
he
r
e
:
=
the
number
o
f
t
im
e
s
in
mul
t
ipl
e
obs
e
r
va
ti
on,
is
r
e
plac
e
d
with
n
f
o
r
s
ingl
e
obs
e
r
va
ti
on
ti
me
;
(
)
=
the
be
s
t
va
lue
of
the
c
ombi
na
ti
on
of
s
e
ns
or
-
da
ta
a
nd
hypothes
is
a
t
e
a
c
h
obs
e
r
va
ti
on
ti
me
;
(
)
=
the
be
s
t
c
ombi
na
ti
on
o
f
s
e
ns
or
-
da
ta
a
nd
hypothes
is
va
lue
a
t
whole
obs
e
r
va
ti
on
ti
me
.
T
he
ult
im
a
te
knowle
dge
whic
h
the
be
s
t
c
ombi
na
ti
on
of
s
e
ns
or
-
da
ta
a
nd
hypothes
is
that
is
obtaine
d
f
r
om
s
e
ve
r
a
l
obs
e
r
va
ti
on
ti
mes
will
a
ls
o
be
c
a
lcula
ted
us
ing
DoC
with
the
mathe
matics
f
or
mul
a
in
(
2)
.
()
m
a
x
[
(
)
]
j
D
o
C
P
e
s
t
i
m
a
t
e
P
=
=
(
2)
whe
r
e
P(
)
e
s
t
i
m
a
t
e
is
the
va
lue
of
DoC
whic
h
is
c
om
monl
y
the
gr
e
a
tes
t
va
lue
o
f
the
c
ombi
na
ti
on
of
s
e
ns
or
-
da
ta
a
nd
hypothes
e
s
r
e
s
ult
e
d
f
r
om
the
OM
-
ASS
A2010
f
or
mul
a
c
omput
a
ti
on.
T
h
is
mec
ha
nis
m
will
be
im
pl
e
mente
d
in
ha
r
dwa
r
e
whic
h
is
,
in
thi
s
c
a
s
e
,
is
f
ield
pr
og
r
a
m
mable
ga
te
a
r
r
a
y
(
F
P
GA
)
.
B
e
f
or
e
im
pleme
nted
in
F
P
GA
a
nd
ba
s
e
d
on
the
pr
e
l
im
inar
y
de
s
igns
o
f
the
da
ta
pa
th
,
the
VH
DL
de
s
ign
f
or
C
AI
or
s
im
ply
c
ognit
ive
pr
oc
e
s
s
or
wa
s
s
uc
c
e
s
s
f
ull
y
made
[
20]
.
F
igur
e
2
s
hows
the
f
lowc
ha
r
t
o
f
the
KG
S
a
lgor
it
hm
a
s
the
ba
s
is
f
or
de
s
igni
ng
the
da
ta
pa
th
f
or
the
c
ognit
ive
pr
oc
e
s
s
or
.
T
he
pr
oc
e
s
s
is
s
tar
ted
with
the
r
e
tr
iev
a
l
o
f
da
ta
f
r
om
s
e
ns
or
s
whic
h
is
c
a
ll
e
d
a
n
indi
c
a
ti
on,
na
mely
inf
o
r
mation
r
e
ga
r
ding
the
obs
e
r
ve
d
phe
nomenon.
T
he
number
of
hypothes
e
s
is
a
ls
o
s
e
t
up
a
c
c
or
ding
to
the
number
of
s
e
ns
or
s
us
e
d
by
the
s
ys
tem.
T
he
number
of
hypothes
e
s
is
c
omput
e
d
by
us
ing
(
3)
,
w
he
r
e
is
the
maxi
mum
number
o
f
pos
s
ibl
e
hy
pothes
e
s
a
nd
is
the
number
o
f
the
s
e
ns
or
.
(
)
21
=
−
−
(
3)
T
he
s
ys
tem
will
c
he
c
k
whe
ther
e
a
c
h
s
e
ns
or
c
a
n
o
bs
e
r
ve
e
ve
r
y
c
ondit
ion
of
the
e
xis
ti
ng
hypothes
is
a
nd
put
a
binar
y
va
lue
0
or
1
de
pe
nding
on
the
r
e
s
ult
of
the
s
e
ns
or
’
s
obs
e
r
va
ti
on.
I
f
a
ll
s
e
ns
or
da
ta
is
a
lr
e
a
dy
c
ompl
e
tely
r
e
c
e
ived
a
nd
e
a
c
h
va
lue
of
the
c
ombi
n
a
ti
on
of
s
e
ns
or
da
ta
a
nd
hypothes
e
s
is
a
lr
e
a
dy
f
il
le
d
in,
then
the
ne
xt
pr
oc
e
s
s
is
the
c
a
r
r
y
out
the
in
f
or
matio
n
f
us
ion
a
nd
obtain
c
om
pr
e
he
ns
ive
inf
o
r
mation
f
or
e
a
c
h
c
ombi
na
ti
on
of
s
e
ns
or
-
da
ta
da
n
hypothes
i
s
.
T
he
c
ompr
e
he
ns
ive
inf
or
mation
be
c
omes
the
inf
e
r
e
nc
in
g
of
e
a
c
h
c
ombi
na
ti
on
of
s
e
ns
or
-
da
ta
a
nd
hypothes
is
whic
h
will
ha
ve
a
va
r
iety
of
pr
oba
bi
li
ty
va
lues
de
pe
nding
on
the
va
lues
of
a
l
l
s
e
ns
or
-
da
ta
a
nd
hypothes
e
s
f
or
e
a
c
h
hypothes
is
.
T
he
in
f
e
r
e
nc
ing
will
be
c
ome
a
ne
w
kn
owle
dge
of
the
s
ys
tem.
T
his
mec
ha
nis
m
is
c
a
r
r
ied
out
by
us
ing
(
1)
a
nd
the
a
mount
of
knowle
dge
obtaine
d
a
t
t
his
point
is
mea
s
ur
e
d
with
DoC
us
ing
(
2
)
.
T
his
mec
ha
nis
m
will
c
onti
nue
ti
me
by
ti
me
a
s
long
a
s
the
s
ys
tem
is
s
ti
ll
making
the
int
e
r
a
c
ti
on
with
the
phe
nomenon,
s
e
ns
ing
to
obtain
inf
or
mation,
a
nd
pe
r
c
e
ivi
ng
it
.
T
he
r
e
is
a
c
on
f
ir
mation
wh
e
ther
a
ll
inf
e
r
e
nc
ing
ha
s
a
lr
e
a
dy
be
e
n
done
f
r
om
t1
to
t
.
D
oC
of
e
a
c
h
obs
e
r
va
ti
on
t
im
e
is
s
tor
e
d
to
be
f
us
e
d
with
the
ne
xt
inf
e
r
e
nc
ing
i
f
the
DoC
a
t
thi
s
point
c
a
nnot
r
e
c
ognize
the
obs
e
r
ve
d
phe
nomenon.
T
he
c
ompon
e
nts
of
a
c
ognit
ive
pr
oc
e
s
s
or
that
a
r
e
de
s
igned
a
r
e
ba
s
e
d
on
OM
-
ASS
A2010
f
or
mul
a
whic
h
be
c
omes
the
a
lgo
r
it
hm
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
1693
-
6930
T
E
L
KO
M
NI
KA
T
e
lec
omm
un
C
omput
E
l
C
ontr
o
l
,
Vol.
18
,
No
.
3
,
J
une
2020:
1475
-
1482
1478
KG
S
.
T
o
im
pleme
nt
thi
s
e
qua
ti
on
int
o
ha
r
dwa
r
e
,
we
ha
d
to
f
or
m
a
s
e
r
ies
of
s
ys
tol
ic
a
r
r
a
ys
[
21
–
23]
,
with
the
matr
ix
e
qua
ti
on
a
s
s
hown
in
(
4)
,
a
nd
i
t
be
c
omes
the
ba
s
is
f
or
f
or
mi
ng
a
de
pe
nde
nc
e
gr
a
ph
to
de
ter
mi
n
e
the
c
ognit
ive
pr
oc
e
s
s
or
c
omponent
a
s
s
ho
wn
in
F
igur
e
3.
F
r
om
th
is
de
pe
nde
nc
e
g
r
a
ph,
the
c
ognit
ive
pr
oc
e
s
s
or
e
leme
nts
a
r
e
de
picte
d
in
F
igu
r
e
4.
1
1
1
1
1
1
2
1
3
1
1
1
2
2
1
2
2
2
3
2
2
2
j
1
2
3
i
1
()
P
...
()
P
..,
...
..
..
..
..
..
...
...
P
..
w
()
t
i
t
i
j
j
j
ji
t
n
P
t
v
v
v
v
w
P
v
v
v
v
w
t
v
v
v
v
P
t
−
−
−
=+
(
4)
w
he
r
e
w1
=
w2
=
…
=
wi
=
w
F
igur
e
2
.
T
he
f
lowc
ha
r
t
of
the
KG
S
a
lgo
r
it
hm
a
s
t
he
ba
s
is
f
or
the
de
s
ign
o
f
c
o
g
n
i
t
i
v
e
pr
oc
e
s
s
or
da
ta
-
pa
th
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KO
M
NI
KA
T
e
lec
omm
un
C
omput
E
l
C
ontr
o
l
T
ow
ar
ds
c
ognit
ive
ar
ti
fi
c
ial
int
e
ll
igenc
e
de
v
ice
:
an
int
e
ll
igent
pr
oc
e
s
s
or
b
as
e
d
....
(
C
ather
ine
Olivia
S
e
r
e
ati
)
1479
1
3
2
.
.
.
i
Pw
1
Pw
j
Pw
2
j
j
V
11
V
12
...
V
1
i
V
21
V
22
...
V
2
i
...
...
...
...
V
j
1
...
V
ji
V
j
2
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
w
1
w
2
wi
...
N
K
P
D
H
1
(
t
-
1
)
1
2
...
i
N
K
P
D
H
2
(
t
-
1
)
N
K
P
D
H
3
(
t
-
1
)
N
K
P
D
H
j
(
t
-
1
)
N
K
P
D
H
2
(
t
-
1
)
N
K
P
D
H
3
(
t
-
1
)
N
K
P
D
H
j
(
t
-
1
)
N
K
P
D
H
1
(
t
-
1
)
N
K
P
D
H
2
(
t
-
1
)
N
K
P
D
H
3
(
t
-
1
)
N
K
P
D
H
j
(
t
-
1
)
N
K
P
D
H
1
(
t
-
1
)
F
igur
e
3
.
De
pe
nde
nc
e
g
r
a
ph
f
o
r
c
ognit
ive
pr
oc
e
s
s
or
X
+
v
1
1
v
1
2
.
.
v
1
i
D
X
P
(
w
)
t
1
1
/
T
N
K
P
D
H
1
t
-
1
X
+
v
1
1
v
1
2
.
.
v
1
i
D
X
P
(
w
)
t
1
1
/
T
X
+
v
1
1
v
1
2
.
.
v
1
i
D
X
P
(
w
)
t
1
1
/
T
X
+
v
1
1
v
1
2
.
.
v
1
i
D
X
P
(
w
)
t
1
1
/
T
w
P
E
1
P
E
2
P
E
3
P
E
j
P
E
1
P
E
2
P
E
3
P
E
j
N
K
P
D
H
3
t
-
1
N
K
P
D
H
j
t
-
1
N
K
P
D
H
2
t
-
1
F
igur
e
4
.
T
he
e
leme
nts
of
the
c
ognit
ive
p
r
oc
e
s
s
or
I
n
F
igur
e
4
,
it
c
a
n
be
s
e
e
n
that
the
OM
-
ASS
A2010
c
omput
a
ti
ona
l
c
ir
c
uit
s
c
ons
is
t
of
mul
ti
pli
c
a
ti
on
a
nd
a
dde
r
c
omponents
.
T
he
D
-
L
a
tch
r
e
gis
ter
is
us
e
d
to
s
tor
e
the
c
a
lcula
ti
on
r
e
s
ult
s
f
r
om
the
a
dde
r
a
nd
mul
ti
pli
c
a
ti
o
n
c
omponents
.
I
n
thi
s
pr
oc
e
s
s
or
a
r
c
hit
e
c
tur
e
de
s
ign,
the
number
o
f
a
dde
r
c
omponents
is
in
f
luenc
e
d
by
the
number
of
hypo
thes
e
s
.
T
he
number
of
s
e
ns
or
s
a
f
f
e
c
ts
c
omput
ing
ti
me.
As
a
n
e
xa
mpl
e
,
a
c
ognit
ive
pr
oc
e
s
s
or
with
4
s
e
ns
or
s
with
13
pos
s
ibl
e
hypothe
s
e
s
,
bu
t
we
a
ll
oc
a
ted
only
8
hypothes
e
s
or
pos
s
ibl
e
e
ve
nts
,
it
will
take
8
a
dde
r
s
with
a
c
omput
a
ti
ona
l
ti
me
len
gth
of
4
ti
mi
ng
s
tage
s
.
3.
RE
S
UL
T
S
A
ND
AN
AL
YSI
S
T
he
t
e
s
tbenc
h
s
im
ulation
f
or
C
AI
pr
oc
e
s
s
or
is
s
hown
in
F
igur
e
5
,
whe
r
e
the
s
ys
tem
s
uc
c
e
s
s
f
ull
y
pr
oduc
e
d
D
oC
va
lue
s
a
t
the
4
th
c
omput
a
ti
on
ti
me
.
B
a
s
e
d
on
the
r
e
s
ult
s
o
f
the
modeling
a
nd
the
d
e
s
igni
ng
c
ognit
ive
pr
oc
e
s
s
or
,
its
c
ir
c
uit
is
im
pleme
nted
in
F
P
GA
modul
e
[
24,
25
]
.
W
e
us
e
d
C
yc
lone
I
VE
E
P
C
E
6F
17C
6
whic
h
ha
s
a
tot
a
l
I
/O
of
180
,
to
im
pleme
nt
th
e
de
s
igned
pr
oc
e
s
s
or
whe
r
e
in
thi
s
e
xpe
r
im
e
nt
we
us
e
d
4
hypothes
e
s
or
p
r
oba
ble
a
ns
we
r
s
.
T
he
r
e
s
ult
s
of
F
P
GA
im
pleme
ntation
f
or
c
ognit
ive
pr
oc
e
s
s
or
is
s
hown
in
F
igur
e
6
,
a
nd
the
s
ynthes
is
r
e
s
ult
s
of
the
s
im
ulation
a
r
e
given
in
F
igur
e
7
.
F
r
om
the
s
ynthes
is
r
e
s
ult
s
,
it
c
a
n
be
s
e
e
n
that
c
ognit
ive
pr
oc
e
s
s
or
with
4
hypothes
e
s
r
e
quir
e
s
527
logi
c
e
leme
nt
s
,
a
nd
86
pins
c
ons
is
ti
ng
of
3
pins
f
or
the
ti
mi
ng
e
leme
nt
(
c
lock
,
r
e
s
e
t,
a
nd
e
na
ble
)
,
4x4
pin
f
or
input
r
e
gis
ter
,
7
pins
f
o
r
dis
play
c
ounter
,
a
nd
17x4
pin
f
or
output
r
e
gis
ter
.
T
he
im
pleme
ntation
o
f
the
c
o
gnit
ive
pr
oc
e
s
s
or
in
F
P
GA
ha
s
a
ls
o
be
e
n
c
a
r
r
ied
out
f
or
a
c
ombi
na
ti
on
of
4
s
e
ns
or
input
s
a
nd
8
hypothes
e
s
.
T
he
im
pleme
ntation
r
e
s
ult
s
f
or
thi
s
c
onf
igur
a
ti
on
s
how
that
the
r
e
quir
e
d
logi
c
e
leme
nts
a
r
e
2
.
162,
a
nd
1
70
pins
c
ons
is
t
of
2
pins
f
or
the
ti
mi
ng
(
c
lo
c
k
a
nd
r
e
s
e
t)
e
leme
nts
,
4x8
pin
f
or
input
r
e
gis
ter
,
a
nd
17x8
pin
f
or
output
r
e
gis
ter
.
F
r
om
the
im
pleme
ntation
r
e
s
ul
t
s
,
it
c
a
n
be
s
e
e
n
that
the
number
of
hypothes
e
s
a
f
f
e
c
ts
the
c
ir
c
uit
c
ompl
e
xit
y
of
the
c
ognit
ive
pr
oc
e
s
s
or
.
T
he
mo
r
e
pos
s
ibl
e
e
ve
nts
that
a
r
e
s
e
t
up
then
the
wide
r
the
d
a
ta
pa
th
s
hould
be
s
e
t
up
a
nd
the
higher
the
numbe
r
of
logi
c
e
leme
nts
will
be
us
e
d.
F
r
om
the
e
xpe
r
im
e
nt
r
e
s
ult
s
,
double
the
number
of
hypothes
e
s
f
our
f
olds
the
n
umber
of
logi
c
e
leme
nts
,
f
r
om
527
f
or
4
hypothes
e
s
to
2.
162
f
or
8
h
ypothes
e
s
or
ther
e
is
a
310%
incr
e
a
s
e
.
On
t
he
other
ha
nd,
the
number
of
pins
incr
e
a
s
e
s
f
r
om
86
pins
to
170
pins
or
ther
e
is
a
98%
incr
e
a
s
e
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
1693
-
6930
T
E
L
KO
M
NI
KA
T
e
lec
omm
un
C
omput
E
l
C
ontr
o
l
,
Vol.
18
,
No
.
3
,
J
une
2020:
1475
-
1482
1480
F
igur
e
5
.
T
e
s
tbenc
h
s
im
ulation
f
or
the
c
ognit
ive
p
r
oc
e
s
s
or
F
igur
e
6
.
T
he
ha
r
dwa
r
e
im
p
leme
ntation
of
the
c
og
nit
ive
pr
oc
e
s
s
or
with
4
hypothes
e
s
F
igur
e
7
.
T
he
s
ynthes
is
r
e
s
ult
s
of
C
AI
pr
o
c
e
s
s
or
4.
CONC
L
USI
ON
F
r
om
our
e
xpe
r
im
e
nts
,
it
c
a
n
be
s
e
e
n
that
we
ha
ve
s
uc
c
e
s
s
f
ull
y
im
pleme
nted
the
KG
S
a
lgo
r
it
hm
in
to
F
P
GA
a
nd
a
ls
o
c
a
r
r
ied
out
a
s
im
ulation
to
s
how
th
a
t
it
wor
ks
we
ll
.
S
ynthes
izing
it
s
ha
r
dwa
r
e
im
plem
e
ntation,
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KO
M
NI
KA
T
e
lec
omm
un
C
omput
E
l
C
ontr
o
l
T
ow
ar
ds
c
ognit
ive
ar
ti
fi
c
ial
int
e
ll
igenc
e
de
v
ice
:
an
int
e
ll
igent
pr
oc
e
s
s
or
b
as
e
d
....
(
C
ather
ine
Olivia
S
e
r
e
ati
)
1481
we
f
ound
that
the
c
ompl
e
xit
y
of
the
c
ognit
ive
pr
o
c
e
s
s
or
incr
e
a
s
e
s
a
s
the
number
of
hypothes
e
s
incr
e
a
s
e
s
whic
h
a
r
e
a
f
f
e
c
ted
the
number
o
f
s
e
ns
or
s
.
As
c
a
n
be
s
e
e
n
f
r
om
(
3
)
that
the
number
of
s
e
ns
or
s
a
utom
a
ti
c
a
ll
y
a
f
f
e
c
ts
the
maximum
number
of
hypothes
e
s
or
pos
s
ibl
e
e
ve
nts
that
c
a
n
be
f
or
med
f
r
om
the
c
omput
a
ti
on
.
I
t
is
a
n
a
na
logy
to
humans
,
the
mor
e
s
e
ns
or
y
or
ga
ns
us
e
t
o
obs
e
r
ve
a
phe
nomenon
then
the
mor
e
pr
oba
ble
a
ns
we
r
s
that
c
a
n
be
obtaine
d
a
nd
mor
e
knowle
dge
that
c
a
n
be
a
c
quir
e
d
to
c
ha
ll
e
nge
is
how
to
r
e
duc
e
the
n
umber
of
logi
c
e
leme
nts
incr
e
a
s
e
a
s
the
nu
mber
of
hypothes
e
s
incr
e
a
s
e
.
One
of
the
wa
ys
is
to
f
ind
a
method
to
de
ter
mi
ne
the
number
o
f
the
mos
t
pr
oba
ble
hypothes
e
s
f
or
a
number
of
s
e
ns
or
s
f
or
obs
e
r
ving
a
phe
nomenon.
F
r
om
the
pe
r
s
pe
c
ti
ve
of
ha
r
dwa
r
e
im
pleme
ntatio
n,
we
c
onti
nue
our
r
e
s
e
a
r
c
h
in
de
s
ign
ing
a
much
be
tt
e
r
c
ognit
ive
pr
oc
e
s
s
or
ba
s
e
d
on
the
K
GS
a
lgor
it
hm.
W
e
be
li
e
ve
that
our
c
ognit
ive
pr
oc
e
s
s
or
if
it
is
r
e
a
dy
in
the
f
or
m
of
s
ys
tem
on
c
hip
(
S
oC
)
,
it
would
be
the
main
s
uppor
ter
f
o
r
the
a
utonom
ous
mobi
le
e
l
e
c
tr
onic
ins
tr
umenta
ti
on
s
ys
tem.
T
he
im
pleme
ntation
of
a
C
AI
-
ba
s
e
d
pr
oc
e
s
s
or
c
a
n
im
pr
ove
the
pe
r
f
o
r
manc
e
of
the
int
e
ll
igenc
e
ins
tr
umenta
ti
on
s
ys
tem
be
c
a
u
s
e
of
it
s
a
bil
it
y
to
incr
e
a
s
e
it
s
own
knowle
dge
a
s
ti
me
pa
s
s
e
s
ba
s
e
d
on
the
input
s
it
r
e
c
e
ives
f
r
om
the
phe
nomenon
in
it
s
s
ur
r
oundings
,
a
s
it
is
done
na
tur
a
ll
y
by
humans
in
their
da
il
y
li
f
e
.
AC
KNOWL
E
DGM
E
N
T
S
T
he
a
uthor
would
li
ke
to
e
xp
r
e
s
s
s
ince
r
e
thanks
to
the
C
AI
R
G
L
a
bor
a
tor
y
f
or
it
s
s
uppor
t
s
o
that
th
is
r
e
s
e
a
r
c
h
c
a
n
be
c
a
r
r
ied
out
a
nd
c
ompl
e
ted.
RE
F
E
RE
NC
E
S
[1
]
W
.
S
h
i
,
M
.
B.
A
l
a
w
i
e
h
,
X
.
L
i
,
a
n
d
H
.
Y
u
,
“
A
l
g
o
r
i
t
h
m
a
n
d
h
a
r
d
w
a
r
e
i
m
p
l
e
m
e
n
t
a
t
i
o
n
f
o
r
v
i
s
u
a
l
p
e
r
c
e
p
t
i
o
n
s
y
s
t
e
m
i
n
a
u
t
o
n
o
m
o
u
s
v
e
h
i
c
l
e
:
A
s
u
r
v
e
y
,
”
I
n
t
e
g
r
a
t
i
o
n
,
t
h
e
V
L
S
I
J
o
u
r
n
a
l
,
v
o
l
.
5
9
.
p
p
.
1
4
8
–
1
5
6
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
v
l
s
i
.
2
0
1
7
.
0
7
.
0
0
7
.
[2
]
T
.
Su
t
i
k
n
o
,
M.
Fact
a,
an
d
G
.
A
.
M.
Mark
ad
eh
,
“Pro
g
res
s
i
n
A
rt
i
fi
c
i
al
In
t
el
l
i
g
en
ce
T
ec
h
n
i
q
u
es
:
fro
m
Brai
n
t
o
E
mo
t
i
o
n
,
”
T
E
LKO
M
NIK
A
Te
l
eco
m
m
u
n
i
ca
t
i
o
n
Co
m
p
u
t
i
n
g
E
l
ec
t
r
o
n
i
cs
a
n
d
C
o
n
t
r
o
l
,
v
o
l
.
9
,
n
o
.
2
,
p
p
.
2
0
1
–
2
0
1
,
2
0
1
1
.
[3
]
K
.
O
.
Bach
r
i
,
A
.
D
.
W
.
Su
mar
i
,
B.
A
.
So
e
d
j
ar
n
o
,
a
n
d
A
.
S.
A
h
mad
,
“
T
h
e
i
mp
l
emen
t
at
i
o
n
o
f
A
3
S
i
n
fo
rma
t
i
o
n
f
u
s
i
o
n
al
g
o
ri
t
h
m
fo
r
i
n
t
erp
re
t
i
n
g
D
i
s
s
o
l
v
e
d
G
as
A
n
al
y
s
i
s
(D
G
A
)
b
as
ed
o
n
D
o
ern
e
n
b
u
rg
Rat
i
o
,
”
i
n
2
0
1
7
In
t
e
r
n
a
t
i
o
n
a
l
S
ym
p
o
s
i
u
m
o
n
E
l
ect
r
o
n
i
c
s
a
n
d
S
m
a
r
t
D
ev
i
ces
,
IS
E
S
D
2
0
1
7
,
2
0
1
8
,
d
o
i
:
1
0
.
1
1
0
9
/
ISE
SD
.
2
0
1
7
.
8
2
5
3
3
6
0
.
[4
]
H
.
R
.
A
.
T
a
l
o
m
p
o
,
A
.
S
.
A
h
m
a
d
,
Y
.
S
.
G
o
n
d
o
k
a
r
y
o
n
o
,
a
n
d
S
.
S
u
t
i
k
n
o
,
“
N
A
I
D
S
d
e
s
i
g
n
u
s
i
n
g
C
h
i
M
I
C
-
K
G
S
,
”
i
n
2
0
1
7
I
n
t
e
r
n
a
t
i
o
n
a
l
S
y
m
p
o
s
i
u
m
o
n
E
l
e
c
t
r
o
n
i
c
s
a
n
d
S
m
a
r
t
D
e
v
i
c
e
s
,
I
S
E
S
D
2
0
1
7
,
2
0
1
8
,
d
o
i
:
1
0
.
1
1
0
9
/
I
S
E
S
D
.
2
0
1
7
.
8
2
5
3
3
6
2
.
[5
]
S.
D
.
Pu
t
ra,
A
.
S
.
A
h
mad
,
an
d
S.
Su
t
i
k
n
o
,
“D
PA
-
co
u
n
t
ermea
s
u
re
w
i
t
h
k
n
o
w
l
e
d
g
e
g
r
o
w
i
n
g
s
y
s
t
em,
”
2
0
1
6
In
t
e
r
n
a
t
i
o
n
a
l
S
ym
p
o
s
i
u
m
o
n
E
l
ec
t
r
o
n
i
cs
a
n
d
S
m
a
r
t
D
ev
i
ces
,
IS
E
S
D
2
0
1
6
,
2
0
1
7
,
d
o
i
:
1
0
.
1
1
0
9
/
IS
E
SD
.
2
0
1
6
.
7
8
8
6
7
5
7
.
[6
]
W
.
A
d
i
p
raw
i
t
a,
A
.
S.
A
h
mad
,
J
.
Semb
i
r
i
n
g
,
an
d
B.
R.
T
ri
l
a
k
s
o
n
o
,
“N
ew
res
am
p
l
i
n
g
al
g
o
ri
t
h
m
fo
r
p
ar
t
i
c
l
e
fi
l
t
er
l
o
ca
l
i
za
t
i
o
n
fo
r
mo
b
i
l
e
ro
b
o
t
w
i
t
h
3
u
l
t
ras
o
n
i
c
s
o
n
ar
s
e
n
s
o
r,
”
i
n
P
r
o
cee
d
i
n
g
s
o
f
t
h
e
2
0
1
1
In
t
er
n
a
t
i
o
n
a
l
Co
n
f
e
r
en
ce
o
n
E
l
ect
r
i
c
a
l
E
n
g
i
n
eer
i
n
g
a
n
d
In
f
o
r
m
a
t
i
cs
,
ICE
E
I
2
0
1
1
,
2
0
1
1
,
d
o
i
:
1
0
.
1
1
0
9
/
IC
E
E
I.
2
0
1
1
.
6
0
2
1
7
3
3
.
[7
]
M.
N
.
W
i
b
i
s
o
n
o
a
n
d
A
.
S.
A
h
ma
d
,
“W
eat
h
er
fo
reca
s
t
i
n
g
u
s
i
n
g
K
n
o
w
l
ed
g
e
G
ro
w
i
n
g
Sy
s
t
em
(K
G
S),
”
P
r
o
ceed
i
n
g
s
2
0
1
7
2
n
d
In
t
er
n
a
t
i
o
n
a
l
C
o
n
f
er
e
n
ces
o
n
I
n
f
o
r
m
a
t
i
o
n
Te
ch
n
o
l
o
g
y,
In
f
o
r
m
a
t
i
o
n
S
y
s
t
e
m
s
a
n
d
E
l
ec
t
r
i
ca
l
E
n
g
i
n
ee
r
i
n
g
,
ICITIS
E
E
2
0
1
7
,
2
0
1
8
,
d
o
i
:
1
0
.
1
1
0
9
/
ICI
T
ISE
E
.
2
0
1
7
.
8
2
8
5
5
2
6.
[8
]
K
.
O
.
Bach
ri
,
U
.
K
h
ay
am,
B.
A
.
So
ed
j
arn
o
,
A
.
D
.
W
.
Su
mari
,
an
d
A
.
S.
A
h
mad
,
“Co
g
n
i
t
i
v
e
art
i
fi
c
i
al
-
i
n
t
el
l
i
g
en
ce
fo
r
d
o
er
n
en
b
u
r
g
d
i
s
s
o
l
v
e
d
g
a
s
an
a
l
y
s
i
s
i
n
t
erp
re
t
at
i
o
n
,
”
TE
L
KO
M
NIKA
Tel
ec
o
m
m
u
n
i
c
a
t
i
o
n
Co
m
p
u
t
i
n
g
E
l
ect
r
o
n
i
c
s
a
n
d
Co
n
t
r
o
l
,
v
o
l
.
1
7
,
n
o
.
1
,
p
p
.
2
6
8
-
2
7
4
,
2
0
1
9
,
d
o
i
:
1
0
.
1
2
9
2
8
/
t
el
k
o
m
n
i
k
a.
v
1
7
i
1
.
1
1
6
1
2
.
[9
]
T
.
K
as
a
k
a
w
a
et
a
l
.
,
“
A
n
A
rt
i
fi
c
i
al
N
e
u
ral
N
et
w
o
r
k
a
t
D
ev
i
ce
L
ev
el
U
s
i
n
g
S
i
mp
l
i
f
i
ed
A
rch
i
t
ec
t
u
re
an
d
T
h
i
n
-
Fi
l
m
T
ran
s
i
s
t
o
rs
,
”
E
l
ect
r
o
n
D
evi
ce
s
,
IE
E
E
Tr
a
n
s
.
,
2
0
1
0
,
d
o
i
:
1
0
.
1
1
0
9
/
t
ed
.
2
0
1
0
.
2
0
5
6
9
9
1
.
[1
0
]
G
.
M
.
L
o
z
i
t
o
,
A
.
L
a
u
d
a
n
i
,
F
.
R
i
g
a
n
t
i
-
F
u
l
g
i
n
e
i
,
a
n
d
A
.
S
a
l
v
i
n
i
,
“
F
P
G
A
i
m
p
l
e
m
e
n
t
a
t
i
o
n
s
o
f
f
e
e
d
f
o
r
w
a
r
d
n
e
u
r
a
l
n
e
t
w
o
r
k
b
y
u
s
i
n
g
f
l
o
a
t
i
n
g
p
o
i
n
t
h
a
r
d
w
a
r
e
a
c
c
e
l
e
r
a
t
o
r
s
,
”
A
d
v
.
E
l
e
c
t
r
.
E
l
e
c
t
r
o
n
.
E
n
g
.
,
2
0
1
4
,
d
o
i
:
1
0
.
1
5
5
9
8
/
a
e
e
e
.
v
1
2
i
1
.
8
3
1
.
[1
1
]
C.
-
F.
Ch
an
g
a
n
d
B.
J
.
Sh
e
u
,
“D
i
g
i
t
a
l
V
L
SI
m
u
l
t
i
p
ro
ce
s
s
o
r
d
e
s
i
g
n
f
o
r
n
eu
r
o
co
m
p
u
t
ers
,
”
[
P
r
o
cee
d
i
n
g
s
1
9
9
2
]
IJC
NN
In
t
.
Jt
.
Co
n
f
.
Neu
r
a
l
Net
wo
r
ks
,
v
o
l
.
2
,
p
p
.
1
–
6
,
1
9
9
2
,
d
o
i
:
1
0
.
1
1
0
9
/
IJ
CN
N
.
1
9
9
2
.
2
2
6
9
9
3
.
[1
2
]
P.
L
an
g
l
ey
,
J
.
E
.
L
ai
rd
,
an
d
S.
Ro
g
ers
,
“Co
g
n
i
t
i
v
e
arch
i
t
ect
u
res
:
Res
earch
i
s
s
u
es
an
d
ch
a
l
l
en
g
es
,
”
Co
g
n
.
S
ys
t
.
R
es
.
,
2
0
0
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
co
g
s
y
s
.
2
0
0
6
.
0
7
.
0
0
4
.
[1
3
]
C.
(U
S)
T
u
an
A
.
D
u
o
n
g
,
G
l
en
d
o
ra
an
d
C.
(U
S)
V
u
A
.
D
u
o
n
g
,
Ro
s
emea
d
,
“Sy
s
t
em
an
d
me
t
h
o
d
fo
r
c
o
g
n
i
t
i
v
e
p
ro
ce
s
s
i
n
g
fo
r
d
a
t
a
fu
s
i
o
n
,
”
2
0
1
2
.
[1
4
]
Y
.
C
h
e
n
,
E
.
A
r
g
e
n
t
i
n
i
s
,
a
n
d
G
.
W
e
b
e
r
,
“
I
B
M
W
a
t
s
o
n
:
H
o
w
C
o
g
n
i
t
i
v
e
C
o
m
p
u
t
i
n
g
C
a
n
B
e
A
p
p
l
i
e
d
t
o
B
i
g
D
a
t
a
C
h
a
l
l
e
n
g
e
s
i
n
L
i
f
e
S
c
i
e
n
c
e
s
R
e
s
e
a
r
c
h
,
”
C
l
i
n
i
c
a
l
T
h
e
r
a
p
e
u
t
i
c
s
,
v
o
l
.
3
8
,
n
o
.
4
.
p
p
.
6
8
8
–
7
0
1
,
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
l
i
n
t
h
e
r
a
.
2
0
1
5
.
1
2
.
0
0
1
.
[1
5
]
C.
Meg
h
a,
A
.
Mad
u
ra,
an
d
Y
.
Sn
eh
a,
“Co
g
n
i
t
i
v
e
Co
m
p
u
t
i
n
g
an
d
i
t
s
A
p
p
l
i
cat
i
o
n
s
,
”
In
t
er
n
a
t
i
o
n
a
l
Co
n
f
e
r
en
ce
o
n
E
n
e
r
g
y,
Co
m
m
u
n
i
ca
t
i
o
n
,
D
a
t
a
A
n
a
l
y
t
i
c
s
a
n
d
S
o
f
t
Co
m
p
u
t
i
n
g
(IC
E
CD
S
-
2
0
1
7
)
,
p
p
.
1
1
6
8
–
1
1
7
2
,
2
0
1
7
.
[1
6
]
A
.
D
.
W
.
Su
mar
i
,
A
.
S.
A
h
mad
,
A
.
I.
W
u
ry
a
n
d
a
ri
,
an
d
J
.
Semb
i
r
i
n
g
,
:
“Brai
n
-
i
n
s
p
i
re
d
K
n
o
w
l
e
d
g
e
G
ro
w
i
n
g
-
S
y
s
t
em:
T
o
w
ard
s
A
T
r
u
e
Co
g
n
i
t
i
v
e
A
g
en
t
,
”
In
t
.
J.
Co
m
p
u
t
.
S
ci
.
A
r
t
i
f
.
I
n
t
e
l
l
.
,
v
o
l
.
2
,
n
o
.
1
,
p
p
.
2
3
–
2
6
,
2
0
1
2
.
[1
7
]
S.
K
.
Card
,
T
.
P
.
Mo
ran
,
an
d
A
.
N
ew
el
l
,
“T
h
e
mo
d
el
h
u
ma
n
p
ro
ce
s
s
o
r:
an
en
g
i
n
eer
i
n
g
mo
d
e
l
fo
r
h
u
man
p
erfo
rma
n
ce,
”
H
a
n
d
b
o
o
k
o
f
p
er
ce
p
t
i
o
n
a
n
d
h
u
m
a
n
p
er
f
o
r
m
a
n
ce
.
1
9
8
6
,
d
o
i
:
1
0
.
1
1
7
7
/
1
0
7
1
1
8
1
3
8
1
0
2
5
0
0
1
8
0
.
[1
8
]
A
.
D
.
W
.
Su
mar
i
,
A
.
S.
A
h
ma
d
,
A
.
I.
W
u
r
y
an
d
ari
,
an
d
J
.
Semb
i
ri
n
g
,
“
A
n
e
w
i
n
f
o
rma
t
i
o
n
-
i
n
fere
n
ci
n
g
f
u
s
i
o
n
met
h
o
d
fo
r
i
n
t
e
l
l
i
g
e
n
t
a
g
en
t
s
,
”
P
r
o
ceed
i
n
g
s
o
f
t
h
e
2
0
0
9
In
t
er
n
a
t
i
o
n
a
l
C
o
n
f
er
e
n
ce
o
n
E
l
ect
r
i
ca
l
E
n
g
i
n
ee
r
i
n
g
a
n
d
In
f
o
r
m
a
t
i
cs
,
ICE
E
I
2
0
0
9
,
2
0
0
9
,
d
o
i
:
1
0
.
1
1
0
9
/
ICE
E
I.
2
0
0
9
.
5
2
5
4
8
1
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
1693
-
6930
T
E
L
KO
M
NI
KA
T
e
lec
omm
un
C
omput
E
l
C
ontr
o
l
,
Vol.
18
,
No
.
3
,
J
une
2020:
1475
-
1482
1482
[1
9
]
A
.
D
.
W
.
Su
mari
an
d
A
.
S.
A
h
ma
d
,
“D
es
i
g
n
a
n
d
Imp
l
e
men
t
a
t
i
o
n
o
f
M
u
l
t
i
A
g
e
n
t
-
b
as
e
d
In
f
o
rmat
i
o
n
Fu
s
i
o
n
Sy
s
t
em
fo
r
Su
p
p
o
rt
i
n
g
D
ec
i
s
i
o
n
Mak
i
n
g
(a
Cas
e
S
t
u
d
y
o
n
Mi
l
i
t
a
ry
O
p
erat
i
o
n
),
”
ITB
J.
In
f
.
Co
m
m
u
n
.
Tech
n
o
l
.
,
v
o
l
.
2
,
n
o
.
1
,
p
p
.
4
2
–
6
3
,
2
0
0
8
.
[2
0
]
C.
O
.
S
e
r
e
a
t
i
,
A
.
D
.
W
.
S
u
m
a
r
i
,
T
.
A
d
i
o
n
o
,
a
n
d
A
.
S
.
A
h
m
a
d
,
“
A
r
c
h
i
t
e
c
t
u
r
e
D
e
s
i
g
n
f
o
r
A
M
u
l
t
i
-
S
e
n
s
o
r
I
n
f
o
r
m
a
t
i
o
n
F
u
s
i
o
n
P
r
o
c
e
s
s
o
r
,
”
T
E
L
K
O
M
N
I
K
A
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
C
o
m
p
u
t
i
n
g
E
l
e
c
t
r
o
n
i
c
s
a
n
d
C
o
n
t
r
o
l
,
v
o
l
.
1
7
,
n
o
.
1
,
p
p
.
1
0
1
–
1
0
8
,
2
0
1
9
.
[2
1
]
S.
B.
V
.
G
amm
et
a
l
.
,
“T
o
w
ar
d
s
n
an
o
mag
n
et
i
c
l
o
g
i
c
s
y
s
t
ems
:
A
p
ro
g
rammab
l
e
ari
t
h
me
t
i
c
l
o
g
i
c
u
n
i
t
f
o
r
s
y
s
t
o
l
i
c
array
-
b
a
s
ed
co
m
p
u
t
i
n
g
(In
v
i
t
ed
),
”
2
0
1
5
IE
E
E
Na
n
o
t
ec
h
n
o
l
o
g
y
M
a
t
er
i
a
l
s
a
n
d
D
ev
i
ces
Co
n
f
e
r
en
ce,
NM
D
C
2
0
1
5
,
2
0
1
6
,
d
o
i
:
1
0
.
1
1
0
9
/
N
MD
C.
2
0
1
5
.
7
4
3
9
2
6
9
.
[2
2
]
R.
Mart
i
n
ez
-
A
l
o
n
s
o
,
K
.
Mi
n
o
,
an
d
D
.
T
o
rr
es
-
L
u
c
i
o
,
“A
rray
p
ro
ce
s
s
o
rs
d
es
i
g
n
e
d
w
i
t
h
V
H
D
L
fo
r
s
o
l
u
t
i
o
n
o
f
l
i
n
ear
eq
u
a
t
i
o
n
s
y
s
t
em
s
i
mp
l
emen
t
ed
i
n
a
FPG
A
,
”
i
n
P
r
o
cee
d
i
n
g
s
-
2
0
1
0
IE
E
E
E
l
ec
t
r
o
n
i
cs
,
R
o
b
o
t
i
c
s
a
n
d
A
u
t
o
m
o
t
i
ve
M
ech
a
n
i
cs
Co
n
f
e
r
en
ce,
CE
R
M
A
2
0
1
0
,
2
0
1
0
,
d
o
i
:
1
0
.
1
1
0
9
/
C
E
RMA
.
2
0
1
0
.
8
5
.
[2
3
]
C.
Ch
en
g
a
n
d
K
.
K
.
Par
h
i
,
“
A
N
o
v
e
l
Sy
s
t
o
l
i
c
A
rra
y
St
ru
ct
u
re
f
o
r
D
C
T
,
”
IE
E
E
T
r
a
n
s
.
C
i
r
c
u
i
t
s
S
ys
t
.
II
E
x
p
r
e
s
s
B
r
i
ef
s
,
2
0
0
5
,
d
o
i
:
1
0
.
1
1
0
9
/
T
CSII.
2
0
0
5
.
8
5
0
4
3
2
.
[2
4
]
A
.
K
u
mar,
S.
Fern
an
d
o
,
Y
.
H
a
,
B
.
M
e
s
m
a
n
,
a
n
d
H
.
C
o
r
p
o
r
a
a
l
,
“
M
u
l
t
i
p
r
o
c
e
s
s
o
r
s
y
s
t
e
m
s
s
y
n
t
h
e
s
i
s
f
o
r
m
u
l
t
i
p
l
e
u
s
e
-
c
a
s
e
s
o
f
m
u
l
t
i
p
l
e
a
p
p
l
i
c
a
t
i
o
n
s
o
n
F
P
G
A
,
”
A
C
M
T
r
a
n
s
.
D
e
s
.
A
u
t
o
m
.
E
l
e
c
t
r
o
n
.
S
y
s
t
.
,
2
0
0
8
,
d
o
i
:
1
0
.
1
1
4
5
/
1
3
6
7
0
4
5
.
1
3
6
7
0
4
9
.
[2
5
]
B.
J
.
L
ei
n
er,
V
.
Q
.
L
o
re
n
a,
T
.
M.
Ces
a
r,
an
d
M.
V
.
L
o
re
n
zo
,
“
H
ard
w
are
arch
i
t
ec
t
u
re
fo
r
FPG
A
i
m
p
l
eme
n
t
a
t
i
o
n
o
f
a
n
eu
ra
l
n
et
w
o
r
k
an
d
i
t
s
ap
p
l
i
ca
t
i
o
n
i
n
i
ma
g
es
p
ro
ce
s
s
i
n
g
,
”
P
r
o
cee
d
i
n
g
s
-
El
ect
r
o
n
i
cs
,
R
o
b
o
t
i
c
s
a
n
d
A
u
t
o
m
o
t
i
ve
M
ech
a
n
i
cs
Co
n
f
e
r
en
ce,
CE
R
M
A
2
0
0
8
,
2
0
0
8
,
d
o
i
:
1
0
.
1
1
0
9
/
C
E
RMA
.
2
0
0
8
.
3
2
.
B
I
OG
RA
P
H
I
E
S
OF
AU
T
HO
RS
C
a
ther
i
ne
Ol
i
v
i
a
Ser
ea
t
i
g
o
t
Bac
h
e
l
o
r
d
eg
ree
o
f
e
l
ec
t
ri
ca
l
en
g
i
n
eeri
n
g
(E
E
)
fro
m
Braw
i
j
a
y
a
U
n
i
v
er
s
i
t
y
Ma
l
an
g
,
t
h
e
n
p
u
rs
u
ed
Ma
s
t
er
o
f
T
ec
h
n
o
l
o
g
y
a
n
d
D
o
c
t
o
r
i
n
E
l
ec
t
ri
ca
l
E
n
g
i
n
eer
i
n
g
,
b
o
t
h
fro
m
In
s
t
i
t
u
t
T
e
k
n
o
l
o
g
i
Ban
d
u
n
g
(IT
B).
N
o
w
Cat
h
er
i
n
e
i
s
a
l
ect
u
rer
an
d
res
earc
h
er
at
U
n
i
v
er
s
i
t
as
K
at
o
l
i
k
In
d
o
n
es
i
a
A
t
ma
J
ay
a.
H
er
i
n
t
eres
t
s
u
b
j
ec
t
o
f
r
es
earch
e
s
are
el
ect
r
o
n
i
c
i
n
s
t
r
u
men
t
at
i
o
n
s
y
s
t
em
a
n
d
s
y
s
t
em
o
n
ch
i
p
(So
C).
S
h
e
w
a
s
a
l
s
o
i
n
v
o
l
v
ed
i
n
s
e
v
era
l
res
earc
h
p
ro
j
ect
s
t
o
d
es
i
g
n
co
g
n
i
t
i
v
e
i
n
s
t
r
u
men
t
at
i
o
n
s
y
s
t
ems
.
So
m
e
o
f
t
h
em
are
a
b
u
i
l
d
i
n
g
a
s
o
f
t
w
are
c
o
g
n
i
t
i
v
e
i
n
t
er
p
ret
a
t
i
o
n
o
f
s
h
i
p
mo
v
emen
t
s
,
f
o
r
I
n
d
o
n
e
s
i
a
n
mari
n
e
s
ecu
r
i
t
y
p
u
r
p
o
s
es
,
an
d
c
o
g
n
i
t
i
v
e
el
ec
t
ro
card
i
o
g
rap
h
(E
CG
)
d
es
i
g
n
.
Cu
rren
t
l
y
h
er
res
earc
h
p
r
o
j
ec
t
i
s
fo
c
u
s
i
n
g
t
o
d
e
s
i
g
n
i
n
g
t
h
e
arch
i
t
ec
t
u
re
o
f
co
g
n
i
t
i
v
e
p
ro
ce
s
s
o
r.
C
o
l
o
nel
A
rw
i
n
D
a
tum
a
y
a
Wa
h
y
udi
Su
m
a
r
i
i
s
1
9
9
1
I
n
d
o
n
e
s
i
a
n
A
i
r
F
o
rce
A
ca
d
emy
g
rad
u
at
e.
H
e
recei
v
e
d
Sarj
an
a
T
e
k
n
i
k
(S.
T
.
)
i
n
E
l
ec
t
ro
n
i
c
s
E
n
g
i
n
eeri
n
g
(1
9
9
6
),
Mag
i
s
t
er
T
ek
n
i
k
(M.
T
.
)
i
n
Co
mp
u
t
er
E
n
g
i
n
eeri
n
g
(
2
0
0
8
),
a
n
d
D
o
k
t
o
r
(D
r.
)
i
n
E
l
ec
t
ri
cal
E
n
g
i
n
eeri
n
g
a
n
d
I
n
fo
rma
t
i
c
s
(2
0
1
0
)
fro
m
In
s
t
i
t
u
t
T
e
k
n
o
l
o
g
i
Ban
d
u
n
g
,
In
d
o
n
es
i
a.
In
2
0
0
9
,
h
e
al
o
n
g
w
i
t
h
Pro
f.
D
r.
i
n
g
.
A
d
an
g
Su
w
a
n
d
i
A
h
ma
d
i
n
v
en
t
ed
k
n
o
w
l
ed
g
e
g
ro
w
i
n
g
s
y
s
t
em
w
h
i
c
h
i
s
t
h
e
fo
u
n
d
at
i
o
n
o
f
Co
g
n
i
t
i
v
e
A
r
t
i
f
i
ci
a
l
In
t
e
l
l
i
g
e
n
ce.
Cu
rre
n
t
l
y
,
A
r
w
i
n
i
s
Se
n
i
o
r
E
l
ect
ri
ca
l
E
n
g
i
n
eer
O
ffi
cer
a
t
A
b
d
u
l
rach
ma
n
Sal
e
h
A
FB,
Mal
an
g
.
H
e
i
s
al
s
o
A
s
s
i
s
t
a
n
t
Pro
fe
s
s
o
r
at
Facu
l
t
y
o
f
D
efen
s
e
T
ech
n
o
l
o
g
y
,
In
d
o
n
es
i
a
D
efen
s
e
U
n
i
v
er
s
i
t
y
an
d
A
d
j
u
n
c
t
Pro
fes
s
o
r
a
t
D
ep
ar
t
men
t
o
f
E
l
e
ct
ri
ca
l
E
n
g
i
n
eeri
n
g
,
St
a
t
e
Po
l
y
t
ech
n
i
c
o
f
Mal
an
g
.
H
e
h
as
b
een
d
e
v
el
o
p
i
n
g
an
d
en
h
a
n
ci
n
g
c
o
g
n
i
t
i
v
e
art
i
f
i
ci
a
l
i
n
t
e
l
l
i
g
e
n
ce
fo
r
v
ar
i
o
u
s
fi
e
l
d
es
p
ec
i
al
l
y
fo
r
D
efen
s
e
an
d
Sec
u
ri
t
y
.
A
da
ng
Suw
a
nd
i
A
hm
a
d
recei
v
ed
h
i
s
e
n
g
i
n
eer
i
n
g
d
eg
ree
i
n
E
l
ect
r
i
cal
E
n
g
i
n
eer
i
n
g
fro
m
IT
B,
D
i
p
l
o
me
E
t
u
d
e
A
p
p
ro
f
o
n
d
i
Si
g
n
a
u
x
e
t
Br
u
i
t
s
(
D
E
A
)
o
p
t
i
o
n
E
l
ect
r
o
n
i
q
u
e,
an
d
D
o
c
t
eu
r
In
g
e
n
i
e
u
r
Si
g
n
au
x
et
Bru
i
t
s
o
p
t
i
o
n
E
l
ect
r
o
n
i
q
u
e
(D
r.
-
i
n
g
)
fro
m
U
n
i
v
er
s
i
t
e
d
es
Sci
e
n
ces
d
u
L
an
g
u
e
d
o
c
M
o
n
t
p
e
l
l
i
er,
Fran
ce
b
ecame
I
n
s
t
i
t
u
t
T
e
k
n
o
l
o
g
i
Ban
d
u
n
g
’
s
Pro
fe
s
s
o
r
i
n
In
t
el
l
i
g
en
t
E
l
ec
t
ro
n
i
c
s
In
s
t
r
u
men
t
at
i
o
n
Sy
s
t
em
i
n
2
0
0
0
.
A
d
a
n
g
’
s
p
a
s
t
re
s
earch
e
s
w
ere
i
n
E
l
ect
r
o
n
i
cs
In
s
t
ru
me
n
t
a
t
i
o
n
s
y
s
t
em
s
an
d
i
n
t
el
l
i
g
en
t
el
ec
t
r
o
n
i
cs
s
y
s
t
ems
/
art
i
fi
c
i
al
i
n
t
el
l
i
g
en
ce
.
H
e
h
as
a
l
s
o
ex
p
a
n
d
e
d
h
i
s
re
s
earch
i
n
b
i
o
i
n
fo
rma
t
i
c
s
co
m
p
u
t
at
i
o
n
,
i
n
f
o
rmat
i
o
n
s
c
i
en
ce
s
,
i
n
t
e
l
l
i
g
e
n
t
co
mp
u
t
a
t
i
o
n
s
,
an
d
i
n
t
e
l
l
i
g
e
n
t
-
b
as
e
d
i
n
s
t
r
u
men
t
at
i
o
n
s
y
s
t
ems
.
I
n
2
0
0
9
-
2
0
1
8
A
d
an
g
S
u
w
a
n
d
i
A
h
ma
d
h
as
d
ev
e
l
o
p
ed
Co
g
n
i
t
i
v
e
A
rt
i
fi
c
i
al
In
t
el
l
i
g
e
n
ce
as
a
n
ew
met
h
o
d
o
f
a
rt
i
fi
c
i
al
i
n
t
el
l
i
g
en
ce
.
Evaluation Warning : The document was created with Spire.PDF for Python.