T
E
L
K
O
M
NIKA
T
elec
o
mm
un
ica
t
io
n Co
m
pu
t
i
ng
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
2
3
,
No
.
2
,
A
p
r
il
2
0
2
5
,
p
p
.
435
~
446
I
SS
N:
1
6
9
3
-
6
9
3
0
,
DOI
: 1
0
.
1
2
9
2
8
/
T
E
L
KOM
NI
K
A
.
v
2
3
i
2
.
260
44
435
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//telko
mn
ika
.
u
a
d
.
a
c.
i
d
K
-
M
ea
ns cl
usteri
ng
int
erpr
etation
u
sing
recency,
f
re
quency
,
a
nd
m
o
ne
tary
fac
tor for r
etail cus
t
o
m
ers seg
m
e
ntati
o
n
Ag
un
g
Nug
ra
ha
1
,
Yut
ik
a
A
m
e
lia
E
f
f
endi
2
,
Nic
ho
la
s
1
,
Z
e
j
in T
a
o
1
,
M
o
k
h Af
if
ud
din
3
,
Na
nia
Nuzulita
4
1
D
e
p
a
r
t
me
n
t
o
f
I
n
d
u
s
t
r
i
a
l
a
n
d
D
a
t
a
E
n
g
i
n
e
e
r
i
n
g
,
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
,
P
u
k
y
o
n
g
N
a
t
i
o
n
a
l
U
n
i
v
e
r
si
t
y
,
B
u
sa
n
,
S
o
u
t
h
K
o
r
e
a
2
R
o
b
o
t
i
c
s
a
n
d
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
En
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
A
d
v
a
n
c
e
d
T
e
c
h
n
o
l
o
g
y
a
n
d
M
u
l
t
i
d
i
sc
i
p
l
i
n
e
,
U
n
i
v
e
r
si
t
a
s A
i
r
l
a
n
g
g
a
,
S
u
r
a
b
a
y
a
,
I
n
d
o
n
e
si
a
3
A
k
a
d
e
mi
K
o
mu
n
i
t
a
s I
n
d
u
st
r
i
T
e
k
st
i
l
d
a
n
P
r
o
d
u
k
T
e
k
st
i
l
S
u
r
a
k
a
r
t
a
,
S
u
r
a
k
a
r
t
a
,
I
n
d
o
n
e
si
a
4
I
n
f
o
r
mat
i
o
n
S
y
st
e
m
s
,
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
U
n
i
v
e
r
si
t
a
s
A
i
r
l
a
n
g
g
a
,
S
u
r
a
b
a
y
a
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
2
,
2024
R
ev
i
s
ed
J
an
1
0
,
2
0
2
5
A
cc
ep
ted
J
an
2
3
,
2
0
2
5
Eff
o
rts
to
re
tain
c
u
sto
m
e
rs
r
e
p
re
se
n
t
a
c
ru
c
ial
c
u
sto
m
e
r
re
latio
n
sh
i
p
m
a
n
a
g
e
m
e
n
t
(CRM
)
stra
teg
y
in
e
v
e
r
y
b
u
sin
e
ss
,
o
f
f
e
rin
g
th
e
p
o
ten
ti
a
l
to
e
n
h
a
n
c
e
p
r
o
f
it
s,
p
a
rti
c
u
larly
f
o
r
s
m
a
ll
a
n
d
m
e
d
iu
m
e
n
terp
rise
s
(S
M
Es).
I
n
th
e
c
o
n
tex
t
o
f
th
is
st
u
d
y
,
w
h
ich
fo
c
u
se
s
o
n
th
e
tran
sa
c
ti
o
n
d
a
tas
e
t
o
f
re
tailers
in
a
d
e
v
e
lo
p
i
n
g
m
a
r
k
e
t,
In
d
o
n
e
si
a
,
th
e
e
m
p
h
a
sis
h
a
s
p
re
d
o
m
in
a
n
tl
y
b
e
e
n
o
n
c
u
sto
m
e
r
a
tt
ra
c
ti
o
n
ra
th
e
r
th
a
n
th
e
im
p
le
m
e
n
tatio
n
o
f
c
u
sto
m
e
r
re
ten
ti
o
n
stra
teg
ies
.
T
h
e
p
rim
a
r
y
o
b
jec
ti
v
e
o
f
th
is
re
se
a
rc
h
w
a
s
to
sc
ru
ti
n
ize
c
u
sto
m
e
r
tran
sa
c
ti
o
n
d
a
ta
w
it
h
in
t
h
e
d
a
tas
e
t.
T
h
e
K
-
M
e
a
n
s
c
lu
ste
rin
g
(KMC
)
m
e
t
h
o
d
,
in
teg
ra
ted
w
it
h
re
c
e
n
c
y
,
f
re
q
u
e
n
c
y
,
a
n
d
m
o
n
e
tary
(RF
M
)
a
tt
ri
b
u
tes
,
w
a
s
e
m
p
lo
y
e
d
to
c
las
sify
c
u
sto
m
e
r
s
a
n
d
f
o
rm
u
late
e
ff
e
c
ti
v
e
stra
t
e
g
ies
f
o
r
c
u
sto
m
e
r
re
ten
ti
o
n
.
Co
n
d
u
c
ted
t
h
ro
u
g
h
a
d
e
sc
rip
ti
v
e
re
se
a
rc
h
m
e
th
o
d
w
it
h
a
q
u
a
n
t
it
a
ti
v
e
a
p
p
ro
a
c
h
,
t
h
e
stu
d
y
in
v
o
lv
e
d
se
q
u
e
n
ti
a
l
sta
g
e
s
o
f
d
a
ta
p
re
p
ro
c
e
ss
in
g
a
n
d
RF
M
a
n
a
ly
sis
f
o
r
c
o
m
p
re
h
e
n
siv
e
d
a
ta
a
n
a
l
y
sis.
T
h
e
o
u
tco
m
e
s
re
v
e
a
led
th
e
id
e
n
ti
f
ica
ti
o
n
o
f
5
d
isti
n
c
t
c
lu
ste
rs
w
it
h
a
ss
o
c
iate
d
stra
teg
ies
b
a
se
d
o
n
th
e
RF
M
sc
o
re
s
o
b
tain
e
d
.
T
h
e
se
stra
teg
ies
,
tailo
re
d
t
o
each
c
lu
ste
r,
se
rv
e
a
s
v
a
lu
a
b
le
in
sig
h
ts
in
i
n
d
u
strial
a
n
d
in
n
o
v
a
ti
o
n
f
o
r
m
a
rk
e
ti
n
g
a
n
d
b
u
sin
e
ss
stra
teg
i
c
tea
m
s,
o
f
f
e
rin
g
p
ra
c
ti
c
a
l
a
p
p
r
o
a
c
h
e
s
to
c
u
sto
m
e
r
re
ten
ti
o
n
t
h
a
t
c
a
n
lea
d
t
o
in
c
re
a
se
d
b
e
n
e
f
it
s f
o
r
S
M
Es.
K
ey
w
o
r
d
s
:
C
u
s
to
m
er
s
e
g
m
en
tatio
n
I
n
d
u
s
tr
ial
a
n
d
in
n
o
v
at
io
n
K
-
Me
a
n
s
al
g
o
r
ith
m
Ma
ch
i
n
e
lear
n
i
n
g
R
ec
en
c
y
,
f
r
eq
u
e
n
c
y
,
an
d
m
o
n
etar
y
an
al
y
s
is
S
m
all
a
n
d
m
ed
i
u
m
e
n
ter
p
r
is
es
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
:
Yu
ti
k
a
Am
elia
E
f
f
e
n
d
i
R
o
b
o
tics
an
d
A
r
tif
ic
ial
I
n
tell
i
g
en
ce
E
n
g
in
ee
r
i
n
g
,
Fac
u
lt
y
o
f
A
d
v
a
n
ce
d
T
ec
h
n
o
lo
g
y
a
n
d
M
u
ltid
is
c
ip
lin
e
Un
i
v
er
s
ita
s
A
ir
lan
g
g
a
St
.
Dr
.
I
r
.
H.
So
ek
ar
n
o
UNA
I
R
Ka
m
p
u
s
C
,
Mu
l
y
o
r
ej
o
,
Su
r
ab
ay
a,
E
ast J
av
a
6
0
1
1
5
,
I
n
d
o
n
esia
E
m
ail:
y
u
tik
a.
e
f
f
en
d
i
@
f
t
m
m
.
u
n
air
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
I
n
to
d
ay
’
s
co
m
p
etiti
v
e
b
u
s
i
n
e
s
s
lan
d
s
ca
p
e,
s
m
al
l
an
d
m
ed
i
u
m
e
n
ter
p
r
is
es
(
SME
s
)
f
in
d
t
h
e
m
s
el
v
es
n
av
i
g
ati
n
g
a
co
m
p
le
x
ter
r
ain
,
w
h
er
e
th
e
p
u
r
s
u
it
o
f
s
u
s
tain
ab
le
g
r
o
w
t
h
i
s
in
tr
ica
tel
y
t
ied
to
th
e
t
w
i
n
ch
a
llen
g
es
o
f
cu
s
to
m
er
ac
q
u
is
itio
n
an
d
r
ev
en
u
e
ex
p
a
n
s
io
n
[
1
]
.
Am
id
s
t
in
ten
s
e
co
m
p
etitio
n
an
d
ev
er
-
ev
o
l
v
i
n
g
co
n
s
u
m
er
p
r
ef
er
en
ce
s
,
SME
s
m
u
s
t
n
o
t
o
n
l
y
s
tr
iv
e
to
attr
ac
t
n
e
w
c
u
s
to
m
er
s
b
u
t
a
ls
o
s
tr
ate
g
icall
y
s
ec
u
r
e
t
h
e
o
n
g
o
in
g
lo
y
a
lt
y
an
d
e
n
g
ag
e
m
e
n
t o
f
th
e
ir
ex
is
tin
g
c
u
s
to
m
er
b
ase
[
2
]
.
T
h
is
d
u
alit
y
o
f
ch
al
len
g
es
u
n
d
er
s
co
r
es th
e
cr
itica
l
i
m
p
o
r
tan
ce
o
f
c
u
s
to
m
er
-
ce
n
tr
i
c
ap
p
r
o
ac
h
es in
s
h
ap
i
n
g
t
h
e
tr
aj
ec
to
r
y
o
f
SME
s
.
Fo
llo
w
i
n
g
t
h
e
P
ar
eto
p
r
in
cip
le,
it
’
s
n
o
te
w
o
r
t
h
y
th
a
t
2
0
%
o
f
cu
s
to
m
er
s
s
i
g
n
i
f
ica
n
tl
y
co
n
tr
i
b
u
te
m
o
r
e
to
th
e
co
m
p
a
n
y
’
s
r
ev
en
u
e
t
h
an
th
e
r
e
m
a
in
i
n
g
8
0
%
[
3
]
.
T
h
is
p
h
en
o
m
e
n
o
n
i
s
ex
p
lai
n
ed
b
y
th
e
f
ac
t
th
at
o
b
tain
in
g
a
n
e
w
c
u
s
to
m
er
ca
n
in
cu
r
e
x
p
en
s
e
s
f
iv
e
ti
m
e
s
h
i
g
h
er
th
a
n
m
a
in
ta
in
i
n
g
an
e
x
is
ti
n
g
o
n
e
[
4
]
.
A
m
er
e
5
%
in
cr
ea
s
e
in
cu
s
to
m
er
r
eten
tio
n
ca
n
lead
to
p
r
o
f
it
b
o
o
s
ts
r
an
g
i
n
g
f
r
o
m
2
5
%
to
9
5
%.
Sel
lin
g
to
an
ex
is
ti
n
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
2
3
,
No
.
2
,
A
p
r
il
20
2
5
:
4
3
5
-
446
436
cu
s
to
m
er
h
as
a
s
u
cc
e
s
s
r
ate
o
f
6
0
-
7
0
%,
w
h
ile
w
i
th
n
e
w
c
u
s
t
o
m
er
s
,
it
i
s
o
n
l
y
5
-
20%
[
5
]
.
Mo
r
eo
v
er
,
cu
s
to
m
er
s
w
h
o
ar
e
lo
y
al
d
e
m
o
n
s
tr
ate
a
p
r
o
b
ab
ilit
y
f
i
v
e
ti
m
es
g
r
ea
te
r
o
f
m
a
k
i
n
g
r
ep
ea
t
p
u
r
ch
ases
,
f
o
u
r
ti
m
e
s
m
o
r
e
in
cli
n
ed
to
r
ec
o
m
m
e
n
d
to
o
th
er
s
,
an
d
s
ev
e
n
ti
m
es
m
o
r
e
p
r
o
n
e
to
tr
y
i
n
g
a
n
e
w
p
r
o
d
u
ct
o
r
s
er
v
ice
[
6
]
.
Giv
e
n
th
e
s
i
g
n
if
ican
ce
o
f
p
r
io
r
i
tizin
g
cu
s
to
m
er
r
eten
tio
n
o
v
er
ac
q
u
ir
in
g
n
e
w
c
u
s
to
m
er
s
t
o
en
h
an
ce
co
m
p
a
n
y
p
r
o
f
its
,
t
h
e
i
m
p
le
m
e
n
tatio
n
o
f
a
cu
s
to
m
er
s
eg
m
e
n
tatio
n
m
o
d
el
b
ec
o
m
es
i
m
p
er
a
tiv
e
[
7
]
.
C
u
s
to
m
er
s
eg
m
e
n
tatio
n
i
n
v
o
lv
e
s
u
til
izin
g
v
ar
io
u
s
d
is
ti
n
cti
v
e
cu
s
to
m
er
ch
ar
ac
ter
is
tics
to
as
s
is
t
b
u
s
i
n
ess
p
r
o
f
ess
io
n
als
i
n
tailo
r
in
g
m
ar
k
eti
n
g
s
tr
ate
g
ie
s
,
r
ec
o
g
n
izi
n
g
tr
en
d
s
,
p
la
n
n
in
g
p
r
o
d
u
ct
d
ev
elo
p
m
en
t,
ad
v
er
ti
s
i
n
g
ca
m
p
ai
g
n
s
,
a
n
d
d
eliv
er
in
g
r
elev
a
n
t
p
r
o
d
u
cts
[
8
]
.
T
h
is
ap
p
r
o
ac
h
en
ab
les
p
e
r
s
o
n
alize
d
m
es
s
ag
i
n
g
to
in
d
iv
id
u
al
s
,
f
ac
ilit
a
tin
g
m
o
r
e
e
f
f
ec
ti
v
e
co
m
m
u
n
icati
o
n
w
it
h
tar
g
e
ted
g
r
o
u
p
s
.
T
h
e
t
y
p
ical
attr
ib
u
te
s
e
m
p
l
o
y
ed
i
n
c
u
s
to
m
er
s
eg
m
e
n
tatio
n
i
n
cl
u
d
e
lo
ca
tio
n
,
ag
e,
g
en
d
er
,
in
co
m
e,
li
f
est
y
le,
an
d
p
ast p
u
r
ch
ase
b
eh
a
v
io
r
[
9
]
.
T
h
is
s
tu
d
y
ai
m
s
to
f
o
cu
s
o
n
a
p
iv
o
tal
q
u
esti
o
n
o
n
h
o
w
S
ME
s
ca
n
in
cr
ea
s
e
r
ev
e
n
u
e
b
y
d
ee
p
en
in
g
th
eir
r
elatio
n
s
h
ip
s
w
i
th
c
u
s
to
m
er
s
.
T
h
e
o
b
j
ec
tiv
es
o
f
th
i
s
s
tu
d
y
ar
e
t
w
o
f
o
ld
.
F
ir
s
tl
y
,
we
ai
m
to
d
eter
m
i
n
e
cu
s
to
m
er
s
eg
m
e
n
tatio
n
w
it
h
i
n
th
e
tr
a
n
s
ac
tio
n
d
ataset
o
f
r
etailer
s
in
a
d
ev
elo
p
in
g
m
a
r
k
et,
I
n
d
o
n
esia
b
y
i
m
p
le
m
en
t
in
g
t
h
e
r
ec
en
c
y
,
f
r
e
q
u
en
c
y
,
an
d
m
o
n
etar
y
(
R
FM)
m
et
h
o
d
in
co
n
j
u
n
ctio
n
w
it
h
K
-
M
ea
n
s
cl
u
s
ter
in
g
(
KM
C
)
.
Seco
n
d
l
y
,
w
e
s
ee
k
to
p
r
o
v
id
e
in
s
i
g
h
ts
in
to
t
h
e
i
n
te
r
p
r
etatio
n
o
f
cu
s
to
m
er
cl
u
s
ter
i
n
g
a
s
s
i
g
n
m
en
t
s
b
y
lev
er
ag
i
n
g
th
e
R
FM
f
ac
to
r
.
I
n
th
i
s
s
t
u
d
y
,
s
e
g
m
en
ta
tio
n
i
s
ca
r
r
ied
o
u
t
u
s
i
n
g
b
eh
a
v
io
r
al
d
ata,
w
h
ic
h
is
ea
s
il
y
ac
ce
s
s
ib
le
an
d
co
n
s
is
ten
tl
y
ev
o
l
v
es,
p
r
o
v
id
in
g
in
s
ig
h
ts
i
n
to
th
e
o
n
g
o
i
n
g
c
h
an
g
e
s
in
cu
s
to
m
er
p
u
r
ch
a
s
e
h
is
to
r
y
.
T
h
e
w
id
el
y
r
ec
o
g
n
ized
R
FM
an
a
l
y
s
is
is
u
tili
ze
d
as
a
m
e
th
o
d
o
lo
g
y
f
o
r
ass
es
s
in
g
c
u
s
to
m
er
s
b
ased
o
n
th
eir
p
u
r
ch
as
in
g
b
eh
av
io
r
[
1
0
]
.
A
s
co
r
in
g
s
y
s
t
e
m
is
d
ev
is
ed
to
ass
ess
in
d
i
v
id
u
al
R
FM
s
co
r
es,
en
ab
lin
g
th
e
an
ticip
atio
n
o
f
f
u
tu
r
e
p
atter
n
s
b
y
e
x
a
m
in
i
n
g
t
h
e
cu
s
to
m
er
’
s
p
r
ese
n
t
a
n
d
p
ast
h
is
to
r
ies
[
1
1
]
.
I
m
p
o
r
tan
tl
y
,
it
h
as
b
ee
n
o
b
s
er
v
ed
th
at
t
h
e
s
co
r
es
f
o
r
th
e
th
r
ee
R
FM
f
ac
t
o
r
s
ex
h
ib
it
a
d
ir
ec
t
co
r
r
elatio
n
w
it
h
t
h
e
c
u
s
to
m
er
’
s
li
f
eti
m
e
a
n
d
r
eten
tio
n
[
1
2
]
.
Af
ter
co
m
p
u
ti
n
g
t
h
e
v
al
u
es
f
o
r
R
FM,
t
h
e
K
-
Me
a
n
s
al
g
o
r
ith
m
is
e
m
p
lo
y
e
d
o
n
th
ese
v
ar
iab
les
to
g
en
er
ate
clu
s
ter
s
w
it
h
i
n
t
h
e
cu
s
to
m
er
b
ase.
An
al
y
z
in
g
t
h
e
b
eh
av
io
r
o
f
ea
ch
clu
s
ter
aid
s
in
id
en
ti
f
y
i
n
g
g
r
o
u
p
s
o
f
cu
s
to
m
er
s
th
at
co
n
tr
ib
u
te
m
o
r
e
p
r
o
f
its
to
th
e
co
m
p
an
y
.
W
it
h
th
e
id
en
ti
f
icat
io
n
o
f
cu
s
to
m
er
cl
u
s
ter
s
,
u
n
d
er
s
ta
n
d
in
g
th
e
d
is
ti
n
ctio
n
s
b
et
w
ee
n
t
h
ese
g
r
o
u
p
s
b
ec
o
m
es
ess
e
n
tia
l.
A
co
m
p
r
eh
e
n
s
iv
e
an
al
y
s
i
s
o
f
th
e
clu
s
ter
s
is
co
n
d
u
cted
to
f
ac
ilit
ate
th
e
id
en
ti
f
ica
tio
n
o
f
tar
g
et
cu
s
to
m
er
s
an
d
tailo
r
ap
p
r
o
p
r
i
ate
p
r
o
m
o
tio
n
s
an
d
o
f
f
er
s
to
t
h
e
m
.
T
h
e
r
es
u
lta
n
t
o
u
tco
m
e
o
f
t
h
is
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
is
a
m
ea
n
i
n
g
f
u
l
c
u
s
to
m
er
s
eg
m
e
n
tatio
n
th
a
t
p
r
o
v
es
b
en
ef
icia
l
f
o
r
th
e
m
ar
k
eti
n
g
a
n
d
b
u
s
i
n
es
s
s
tr
ate
g
i
c
tea
m
s
i
n
SME
s
.
T
h
e
s
tr
u
ctu
r
e
o
f
th
e
d
o
cu
m
e
n
t
i
s
o
u
tlin
ed
a
s
f
o
llo
w
s
:
s
ec
tio
n
2
ex
p
lo
r
es
th
e
liter
at
u
r
e
r
ev
i
e
w
,
s
ec
tio
n
s
3
a
n
d
4
p
r
esen
t
th
e
m
eth
o
d
o
lo
g
ie
s
,
ex
p
er
i
m
e
n
tal
r
es
u
lts
,
a
n
d
d
is
c
u
s
s
io
n
,
r
esp
ec
ti
v
el
y
,
w
h
ile
s
ec
tio
n
5
p
r
o
v
id
es th
e
co
n
cl
u
s
io
n
o
f
th
i
s
r
esear
ch
.
2.
RE
L
AT
E
D
WO
RK
S
I
n
th
i
s
s
ec
t
io
n
,
w
e
w
i
ll
co
n
d
u
ct
a
liter
at
u
r
e
r
ev
ie
w
e
x
a
m
i
n
in
g
p
r
ev
io
u
s
r
esear
c
h
o
n
cu
s
to
m
er
s
eg
m
e
n
tatio
n
.
T
h
e
d
is
c
u
s
s
io
n
w
i
ll
e
m
p
h
asize
s
i
g
n
if
ica
n
t
d
is
co
v
er
ies
a
n
d
p
er
s
p
ec
tiv
e
s
g
lean
ed
f
r
o
m
p
r
io
r
s
tu
d
ie
s
in
t
h
is
d
o
m
a
in
.
2
.
1
.
C
us
t
o
m
er
s
eg
m
ent
a
t
io
n
Seg
m
en
tatio
n
r
e
m
ai
n
s
a
cr
u
c
i
al
m
ar
k
e
tin
g
co
n
ce
p
t,
p
ar
ticu
l
ar
l
y
w
it
h
i
n
th
e
f
r
a
m
e
w
o
r
k
o
f
r
elatio
n
s
h
ip
m
ar
k
et
in
g
.
E
n
h
an
c
in
g
cu
s
to
m
er
r
elatio
n
s
h
ip
s
b
ec
o
m
e
s
m
o
r
e
co
m
p
elli
n
g
,
y
ield
i
n
g
a
d
ee
p
er
u
n
d
er
s
tan
d
i
n
g
o
f
cu
s
to
m
er
n
ee
d
s
.
Seg
m
e
n
tati
o
n
in
v
o
l
v
es
ca
te
g
o
r
izin
g
cu
s
to
m
er
s
i
n
to
clu
s
ter
s
w
it
h
lo
y
al
t
y
d
is
t
in
ctio
n
s
,
f
o
r
m
i
n
g
t
h
e
b
asis
f
o
r
a
tailo
r
ed
m
ar
k
e
tin
g
s
tr
ate
g
y
.
C
u
s
to
m
er
s
eg
m
e
n
tatio
n
s
tan
d
s
o
u
t
as
an
in
itia
l
s
tep
in
s
h
ap
i
n
g
a
b
u
s
i
n
e
s
s
m
o
d
el
[
13
].
T
h
is
cu
s
to
m
er
s
e
g
m
e
n
t
atio
n
ali
g
n
s
w
it
h
t
h
e
p
r
in
c
i
p
les
o
f
c
u
s
to
m
er
r
elatio
n
s
h
ip
m
an
a
g
e
m
en
t
(
C
R
M)
,
a
s
tr
ate
g
ic
ap
p
r
o
ac
h
th
at
s
ee
k
s
to
o
p
ti
m
ize
p
r
o
f
its
a
n
d
cu
s
to
m
er
s
atis
f
ac
tio
n
,
u
lt
i
m
a
tel
y
e
lev
ati
n
g
th
e
v
al
u
e
o
f
c
u
s
to
m
er
lo
y
a
lt
y
[
14
]
.
T
h
e
o
b
j
ec
tiv
e
o
f
C
R
M
is
f
o
r
b
u
s
i
n
ess
e
s
to
co
m
p
r
eh
en
d
cu
s
to
m
er
n
e
ed
s
,
f
o
s
ter
in
g
clo
s
e,
p
o
s
itiv
e,
an
d
tr
an
s
p
ar
en
t
b
u
s
in
e
s
s
r
elatio
n
s
h
ip
s
an
d
co
m
m
u
n
icatio
n
,
t
h
er
eb
y
m
iti
g
atin
g
th
e
r
is
k
o
f
c
u
s
to
m
er
s
s
h
i
f
ti
n
g
to
co
m
p
eti
n
g
co
m
p
an
ie
s
[
1
5
].
2
.
2
.
R
ec
ency
,
f
re
qu
ency
,
a
nd
m
o
net
a
ry
a
na
ly
s
is
R
FM
an
a
l
y
s
is
e
m
er
g
e
as
a
p
o
w
er
f
u
l
an
d
estab
lis
h
ed
m
et
h
o
d
w
it
h
in
t
h
e
f
ield
o
f
d
atab
ase
m
ar
k
et
in
g
.
W
id
ely
u
tili
ze
d
,
it
i
n
v
o
l
v
es
t
h
e
r
an
k
i
n
g
o
f
cu
s
to
m
er
s
b
ased
o
n
th
eir
h
is
to
r
ical
p
u
r
c
h
asi
n
g
p
atter
n
s
,
p
r
o
v
in
g
to
b
e
in
v
a
lu
ab
le
in
d
iv
er
s
e
d
o
m
ai
n
s
lik
e
o
n
li
n
e
p
u
r
ch
ase
s
an
d
r
etaili
n
g
.
T
h
is
ap
p
r
o
ac
h
ad
ep
tl
y
clas
s
i
f
ies
cu
s
to
m
er
s
b
y
co
n
s
id
er
in
g
t
h
r
e
e
cr
u
cial
d
i
m
e
n
s
io
n
s
:
r
ec
en
c
y
(
R
)
,
f
r
eq
u
en
c
y
(
F),
a
n
d
m
o
n
e
t
ar
y
(
M)
,
p
r
o
v
id
in
g
a
co
m
p
r
eh
en
s
i
v
e
m
ea
n
s
o
f
co
m
p
r
e
h
e
n
d
in
g
an
d
s
eg
m
e
n
ti
n
g
cu
s
to
m
er
b
eh
a
v
io
r
.
R
FM
a
n
al
y
s
i
s
is
p
ar
tic
u
lar
l
y
u
s
e
f
u
l
i
n
s
ce
n
ar
io
s
w
it
h
a
lar
g
e
c
u
s
to
m
er
b
ase,
p
r
o
v
id
in
g
b
u
s
i
n
ess
e
s
w
i
th
ac
tio
n
ab
le
i
n
s
ig
h
t
s
f
o
r
tar
g
eted
s
tr
ateg
ie
s
an
d
p
er
s
o
n
alize
d
m
a
r
k
etin
g
ap
p
r
o
ac
h
es [
1
6
]
,
[
1
7
]
.
R
ec
en
c
y
(
R
)
,
r
ef
er
r
in
g
to
th
e
ti
m
i
n
g
o
f
t
h
e
cu
s
to
m
er
’
s
m
o
s
t
r
ec
en
t
p
u
r
ch
ase,
is
q
u
a
n
ti
f
i
ed
b
y
th
e
n
u
m
b
er
o
f
d
a
y
s
b
et
w
ee
n
t
w
o
t
r
an
s
ac
tio
n
s
.
A
lo
w
er
r
ec
en
c
y
v
alu
e
i
n
d
icate
s
f
r
eq
u
e
n
t
v
i
s
its
f
r
o
m
th
e
cu
s
to
m
er
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
K
-
Mea
n
s
clu
s
teri
n
g
in
terp
r
eta
tio
n
u
s
in
g
r
ec
en
cy
,
fr
eq
u
e
n
cy
,
a
n
d
mo
n
eta
r
y
fa
cto
r
fo
r
…
(
A
g
u
n
g
N
u
g
r
a
h
a
)
437
w
it
h
i
n
a
b
r
ief
ti
m
e
f
r
a
m
e,
w
h
il
e
a
h
ig
h
er
v
al
u
e
s
u
g
g
e
s
ts
a
r
e
d
u
ce
d
lik
eli
h
o
o
d
o
f
th
e
cu
s
to
m
er
r
etu
r
n
in
g
to
th
e
co
m
p
a
n
y
in
t
h
e
n
e
ar
f
u
t
u
r
e.
I
n
ess
e
n
ce
,
r
ec
en
c
y
s
er
v
es
as
a
m
etr
ic
t
h
at
r
e
f
lects
t
h
e
cu
s
to
m
er
’
s
v
i
s
iti
n
g
p
atter
n
s
,
in
f
l
u
e
n
cin
g
t
h
e
co
m
p
an
y
’
s
u
n
d
er
s
tan
d
i
n
g
o
f
th
e
ir
en
g
a
g
e
m
en
t o
v
er
ti
m
e
[
1
6
]
.
Fre
q
u
en
c
y
(
F)
,
in
q
u
ir
i
n
g
ab
o
u
t
th
e
n
u
m
b
er
o
f
ti
m
e
s
a
cu
s
to
m
er
h
a
s
m
ad
e
a
p
u
r
ch
ase,
i
s
ch
ar
ac
ter
ized
b
y
th
e
q
u
a
n
tit
y
o
f
tr
an
s
ac
tio
n
s
w
it
h
in
a
d
esig
n
ated
ti
m
e
f
r
a
m
e.
A
h
ei
g
h
ten
e
d
f
r
eq
u
en
c
y
v
a
lu
e
s
ig
n
i
f
ies
a
g
r
ea
ter
d
eg
r
ee
o
f
cu
s
to
m
er
lo
y
a
lt
y
to
th
e
co
m
p
an
y
.
I
n
ess
e
n
ce
,
th
e
m
o
r
e
f
r
e
q
u
en
tl
y
a
c
u
s
to
m
er
en
g
a
g
es
i
n
p
u
r
c
h
ase
s
w
it
h
in
a
s
p
ec
if
ied
p
er
io
d
,
th
e
s
tr
o
n
g
er
th
eir
alleg
ia
n
ce
to
th
e
co
m
p
a
n
y
is
p
er
ce
iv
ed
.
T
h
is
m
e
tr
ic
s
er
v
es
as
a
v
al
u
ab
le
in
d
icato
r
o
f
cu
s
to
m
er
co
m
m
it
m
e
n
t
an
d
th
e
ex
te
n
t
to
w
h
i
ch
th
e
y
co
n
s
is
ten
t
l
y
ch
o
o
s
e
th
e
co
m
p
a
n
y
f
o
r
th
eir
p
u
r
ch
asi
n
g
n
ee
d
s
[
1
7
]
.
Mo
n
etar
y
(
M)
,
ass
ess
i
n
g
th
e
f
i
n
an
cia
l
ex
p
en
d
it
u
r
e
o
f
a
cu
s
to
m
er
,
is
ch
ar
ac
ter
ized
b
y
t
h
e
s
u
m
o
f
m
o
n
e
y
s
p
en
t
d
u
r
i
n
g
a
s
p
ec
if
i
c
ti
m
e
f
r
a
m
e.
A
g
r
ea
ter
m
o
n
e
tar
y
v
al
u
e
in
d
icate
s
a
h
i
g
h
er
co
n
tr
ib
u
tio
n
to
th
e
co
m
p
a
n
y
’
s
r
ev
en
u
e.
E
s
s
e
n
tial
l
y
,
th
e
m
o
r
e
m
o
n
e
y
a
cu
s
to
m
er
s
p
en
d
s
w
it
h
i
n
a
d
esig
n
ate
d
p
er
io
d
,
th
e
m
o
r
e
s
u
b
s
ta
n
tial
th
e
ir
f
i
n
a
n
cial
i
m
p
ac
t
o
n
th
e
co
m
p
a
n
y
[
1
6
]
.
T
h
is
m
etr
ic
i
s
a
k
e
y
in
d
icat
o
r
o
f
a
cu
s
to
m
er
’
s
ec
o
n
o
m
ic
v
al
u
e
an
d
u
n
d
er
s
co
r
es
th
eir
f
in
a
n
cial
s
i
g
n
i
f
ican
c
e
to
th
e
o
v
er
all
s
u
cc
ess
an
d
p
r
o
f
itab
ilit
y
o
f
th
e
b
u
s
i
n
ess
[
1
7
]
.
2
.
3
.
Clus
t
er
ing
a
nd
K
-
M
ea
n
s
a
lg
o
rit
h
m
C
lu
s
ter
i
n
g
i
s
a
tech
n
iq
u
e
e
m
p
lo
y
ed
to
id
en
ti
f
y
a
n
d
ca
teg
o
r
ize
d
ata
s
h
ar
in
g
s
i
m
i
lar
itie
s
w
i
th
o
n
e
an
o
th
er
[
1
8
]
.
I
t
is
a
d
ata
an
al
y
s
i
s
m
eth
o
d
co
m
m
o
n
l
y
i
n
t
eg
r
ated
in
to
d
ata
m
i
n
i
n
g
,
ai
m
i
n
g
to
g
r
o
u
p
d
ata
ex
h
ib
it
in
g
s
i
m
i
lar
ch
ar
ac
ter
i
s
tics
[
1
9
].
K
-
Me
an
s
is
a
wid
el
y
u
t
ilized
alg
o
r
it
h
m
th
at
n
ec
ess
itates
i
n
p
u
t
p
ar
am
eter
s
,
in
cl
u
d
in
g
th
e
s
p
e
cif
ied
n
u
m
b
er
o
f
clu
s
ter
s
,
to
p
ar
titi
o
n
th
e
d
ata
w
it
h
th
e
o
b
j
ec
tiv
e
o
f
en
s
u
r
i
n
g
h
ig
h
in
tr
a
-
cl
u
s
ter
s
i
m
ilar
it
y
.
T
h
e
alg
o
r
ith
m
o
p
er
ates
ite
r
ati
v
el
y
,
in
v
o
l
v
in
g
t
h
e
ca
lc
u
lat
io
n
o
f
ce
n
tr
o
id
v
a
lu
e
s
b
ef
o
r
e
ea
ch
iter
atio
n
.
S
u
b
s
e
q
u
en
tl
y
,
d
ata
p
o
in
ts
ar
e
r
ea
s
s
i
g
n
ed
a
m
o
n
g
d
i
f
f
er
en
t
clu
s
ter
s
b
ased
o
n
t
h
e
ce
n
tr
o
id
s
co
m
p
u
ted
d
u
r
in
g
ea
ch
iter
atio
n
.
T
h
is
iter
ativ
e
p
r
o
ce
s
s
co
n
tin
u
e
s
u
n
t
il
f
u
r
t
h
er
r
ed
u
ctio
n
in
th
e
s
u
m
b
ec
o
m
e
s
u
n
a
ttain
ab
le.
A
l
g
o
r
ith
m
1
o
f
f
er
s
a
d
etailed
ex
p
lan
atio
n
o
f
th
e
K
-
Me
a
n
s
alg
o
r
ith
m
.
T
h
e
co
m
p
u
tatio
n
al
co
m
p
lex
it
y
o
f
th
e
K
-
Me
a
n
s
al
g
o
r
ith
m
is
ex
p
r
ess
ed
as
O(
n
+
k
+i)
,
w
h
e
r
e
‘
n
’
s
i
g
n
i
f
ie
s
th
e
n
u
m
b
er
o
f
in
s
ta
n
ce
s
,
‘
k
’
d
en
o
t
es th
e
n
u
m
b
er
o
f
clu
s
ter
s
,
an
d
‘
i
’
r
ep
r
esen
ts
t
h
e
n
u
m
b
er
o
f
it
er
atio
n
s
[
2
0
]
.
A
l
g
o
r
ith
m
1
.
K
-
Me
a
n
s
clu
s
ter
in
g
al
g
o
r
it
h
m
Input: Dataset containing
‘
n
’
instances
‘
k
’
represents the number of clusters
Output: Data divided into k clusters
Algorithm:
1.
Initially,
k
random
po
in
t
s
ar
e
se
le
ct
ed
as
in
it
ia
l
ce
nt
ro
id
s
ba
se
d
on
th
e
va
lu
e
of
k.
2.
Th
e
Eu
cl
id
ea
n
di
st
an
ce
is
ca
lc
ul
at
ed
fo
r
ea
ch
da
ta
po
in
t
fr
om
th
e
pr
ev
io
us
ly
selected centroids.
3.
The distances are compared, and each data point is
assigned to the centroid
with the
shortest
Euclidean distance value.
4.
Th
e
pr
ec
ed
in
g
st
ep
s
ar
e
it
er
at
ed
.
Th
e
pr
oc
es
s
co
n
cl
ud
es
wh
en
th
e
ob
ta
in
ed
cl
us
te
rs
match those from the previous step.
2
.
4
.
Rela
t
ed
re
s
ea
rc
h
C
u
s
to
m
er
s
eg
m
e
n
tatio
n
p
r
o
b
le
m
s
ar
e
p
r
ev
alen
t
in
in
d
u
s
t
r
y
an
d
i
n
n
o
v
atio
n
m
ar
k
eti
n
g
co
n
ce
p
ts
.
Nu
m
er
o
u
s
s
t
u
d
ies
h
av
e
e
x
p
lo
r
ed
cu
s
to
m
er
s
eg
m
e
n
tatio
n
u
s
in
g
v
ar
io
u
s
ap
p
r
o
ac
h
es
.
T
h
e
s
tu
d
y
d
escr
ib
ed
in
r
ef
er
en
ce
[
2
1
]
ce
n
ter
ed
ar
o
u
n
d
th
e
i
m
p
le
m
e
n
tatio
n
o
f
e
x
p
la
in
ab
le
c
u
s
to
m
er
s
eg
m
e
n
tatio
n
th
r
o
u
g
h
KM
C
.
T
h
is
r
esear
ch
ai
m
ed
to
m
er
g
e
e
x
p
lain
ab
ilit
y
w
i
th
cl
u
s
ter
i
n
g
,
an
u
n
s
u
p
er
v
is
ed
m
et
h
o
d
.
T
o
en
h
an
ce
in
ter
p
r
etab
ilit
y
,
th
is
s
tu
d
y
in
tr
o
d
u
ce
d
a
d
ec
is
i
o
n
tr
ee
-
b
ased
ap
p
r
o
ac
h
f
o
r
ex
p
lain
ab
ilit
y
i
n
c
u
s
to
m
er
s
eg
m
en
tatio
n
,
ap
p
licab
le
to
b
o
th
s
m
all
an
d
lar
g
e
d
ataset
s
.
T
h
r
o
u
g
h
th
e
u
t
ilizatio
n
o
f
th
e
e
lb
o
w
m
eth
o
d
an
d
s
il
h
o
u
ette
s
co
r
e,
th
e
r
esear
ch
d
eter
m
in
ed
a
n
o
p
tim
al
n
u
m
b
er
o
f
clu
s
ter
s
,
s
u
b
s
eq
u
en
tl
y
i
m
p
le
m
en
tin
g
t
h
e
ex
p
lain
ab
le
K
M
C
(
E
x
KM
C
)
al
g
o
r
ith
m
f
o
r
b
o
th
d
atasets
.
T
h
e
s
tu
d
y
p
r
esen
ted
b
y
[
2
2
]
co
n
ce
n
tr
ated
o
n
cu
s
to
m
er
s
e
g
m
e
n
tat
io
n
a
n
d
p
er
s
o
n
alize
d
m
ar
k
et
in
g
th
r
o
u
g
h
t
h
e
u
tili
za
tio
n
o
f
K
-
Me
an
s
an
d
A
P
R
I
OR
I
alg
o
r
it
h
m
s
.
T
h
is
p
ap
er
em
p
lo
y
s
R
FM
an
d
KM
C
f
o
r
cu
s
to
m
er
s
e
g
m
en
ta
tio
n
.
A
d
d
itio
n
all
y
,
it
in
tr
o
d
u
ce
s
a
co
m
b
o
o
f
f
er
r
ec
o
m
m
en
d
atio
n
f
ea
t
u
r
e
th
a
t
ca
n
b
e
in
te
g
r
ated
in
to
an
y
co
m
m
er
ci
al
w
eb
s
ite
u
s
i
n
g
th
e
E
C
L
A
T
an
d
A
P
R
I
OR
I
alg
o
r
it
h
m
s
.
T
h
is
f
ea
tu
r
e
aid
s
i
n
an
al
y
z
in
g
p
r
o
d
u
ct
p
er
f
o
r
m
a
n
c
e
an
d
id
en
ti
f
y
i
n
g
c
u
s
to
m
er
s
w
h
o
ca
n
b
e
tar
g
eted
m
o
r
e
e
f
f
ec
tiv
el
y
f
o
r
p
r
o
d
u
ct
s
ales.
R
esear
ch
co
n
d
u
cted
b
y
[
2
3
]
-
[
2
7
]
d
elv
ed
in
to
elu
cid
ati
n
g
t
h
e
p
r
o
ce
s
s
o
f
v
is
u
a
lizi
n
g
c
u
s
to
m
er
clu
s
ter
s
th
r
o
u
g
h
g
r
ap
h
p
lo
ttin
g
an
d
s
tu
d
y
i
n
g
d
ata
u
s
i
n
g
t
h
e
KM
C
a
lg
o
r
ith
m
.
T
h
e
u
lti
m
a
te
d
ata
-
d
r
iv
e
n
d
ec
is
io
n
-
m
ak
in
g
,
d
er
iv
ed
f
r
o
m
ex
a
m
i
n
in
g
th
e
f
in
al
cl
u
s
ter
s
,
p
r
o
v
id
es
b
u
s
in
e
s
s
es
w
it
h
v
al
u
ab
l
e
in
s
ig
h
t
s
.
I
n
th
e
m
ea
n
ti
m
e,
[
16
]
p
r
o
v
id
ed
a
c
o
m
p
ar
i
s
o
n
o
f
t
h
r
ee
alg
o
r
it
h
m
s
in
th
e
r
ea
l
m
o
f
c
u
s
to
m
er
s
eg
m
en
tatio
n
,
n
a
m
e
l
y
KM
C
,
f
u
zz
y
C
-
Me
a
n
s
,
a
n
d
r
ep
etitiv
e
m
e
d
ian
K
-
Me
a
n
s
.
Ad
d
itio
n
all
y
,
i
n
th
e
ir
w
o
r
k
[
28
]
,
in
tr
o
d
u
ce
d
th
r
ee
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
2
3
,
No
.
2
,
A
p
r
il
20
2
5
:
4
3
5
-
446
438
d
is
tin
ct
cl
u
s
ter
i
n
g
al
g
o
r
ith
m
s
(
K
-
Me
an
s
,
Ag
g
lo
m
er
ati
v
e,
an
d
Me
an
s
h
i
f
t)
f
o
r
cu
s
to
m
er
s
eg
m
en
tatio
n
,
u
lti
m
atel
y
co
m
p
ar
in
g
t
h
e
o
u
tc
o
m
e
s
o
f
cl
u
s
ter
s
d
er
iv
ed
f
r
o
m
th
ese
al
g
o
r
ith
m
s
.
3.
ME
T
H
O
D
I
n
th
i
s
s
ec
tio
n
,
w
e
w
ill
o
f
f
er
a
co
m
p
r
eh
en
s
i
v
e
o
v
er
v
ie
w
,
co
v
er
i
n
g
t
h
e
u
ti
lized
d
ataset,
d
ata
p
r
ep
r
o
ce
s
s
in
g
tec
h
n
iq
u
e
s
,
an
d
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
o
lo
g
y
.
T
h
is
d
etailed
e
x
p
lan
atio
n
w
i
ll
p
r
o
v
id
e
v
al
u
ab
le
in
s
i
g
h
ts
i
n
to
th
e
m
et
h
o
d
o
lo
g
ie
s
e
m
p
lo
y
ed
f
o
r
d
eter
m
i
n
i
n
g
r
e
tail c
u
s
to
m
er
s
e
g
m
en
tat
io
n
.
3
.
1
.
Da
t
a
s
et
a
nd
da
t
a
prepro
ce
s
s
ing
T
h
is
s
tu
d
y
u
tili
ze
d
t
h
e
tr
an
s
a
ctio
n
d
ataset
o
f
r
etailer
s
in
a
d
ev
elo
p
in
g
m
ar
k
et,
I
n
d
o
n
e
s
ia
,
co
v
er
in
g
th
e
p
er
io
d
f
r
o
m
A
p
r
il
1
,
2
0
2
0
to
J
u
ly
3
1
,
2
0
2
0
.
T
h
e
R
AW
d
ataset
co
m
p
r
is
ed
t
h
r
ee
t
y
p
es:
tr
an
s
ac
tio
n
d
ata,
cu
s
to
m
er
d
ata,
an
d
s
to
r
e
d
at
a.
T
h
e
tr
an
s
ac
tio
n
d
ata
en
co
m
p
a
s
s
ed
9
,
6
4
0
tr
an
s
ac
tio
n
s
w
it
h
s
i
x
co
lu
m
n
s
,
in
cl
u
d
in
g
tr
a
n
s
ac
tio
n
I
D
(
T
r
x
I
D)
,
tr
an
s
ac
tio
n
d
ate
(
T
r
x
Date
)
,
s
to
r
e
I
D
(
Sto
r
eI
d
)
,
cu
s
to
m
e
r
I
D
(
C
u
s
to
m
er
I
d
)
,
tr
an
s
ac
tio
n
s
tat
u
s
(
T
r
x
Statu
s
)
,
an
d
am
o
u
n
t.
I
n
t
h
e
cu
s
to
m
er
d
ata,
th
er
e
w
er
e
9
5
8
cu
s
to
m
er
s
w
it
h
s
i
x
co
lu
m
n
s
,
in
cl
u
d
in
g
cu
s
to
m
er
I
D,
f
ir
s
t
n
a
m
e,
las
t
n
a
m
e,
e
m
ail,
b
ir
th
d
ay
,
an
d
g
e
n
d
er
.
L
ast
l
y
,
th
e
s
to
r
e
d
ata
in
clu
d
ed
in
f
o
r
m
atio
n
o
n
s
e
v
en
s
to
r
es,
f
ea
tu
r
in
g
t
w
o
co
lu
m
n
s
:
s
to
r
e
I
D
an
d
s
to
r
e
lo
ca
tio
n
.
I
n
t
h
is
s
t
u
d
y
,
d
ata
p
r
ep
r
o
ce
s
s
i
n
g
is
u
n
d
er
tak
e
n
,
i
n
v
o
l
v
i
n
g
b
o
th
d
ata
clea
n
i
n
g
an
d
d
ata
f
r
a
m
e
f
ilter
i
n
g
f
r
o
m
th
e
r
a
w
d
atase
t.
Data
clea
n
s
i
n
g
is
e
m
p
lo
y
ed
to
en
s
u
r
e
th
e
ac
cu
r
ac
y
an
d
co
m
p
lia
n
ce
o
f
in
f
o
r
m
atio
n
w
it
h
i
n
th
e
d
ataset.
Sin
ce
o
u
r
r
a
w
d
ataset
is
s
tr
u
ct
u
r
ed
as
h
eter
o
g
en
eo
u
s
tab
u
lar
d
ata
w
it
h
l
ab
eled
ax
es
(
r
o
w
s
an
d
co
lu
m
n
s
)
,
w
e
co
n
d
u
cted
d
ata
f
r
am
e
f
ilter
i
n
g
,
s
elec
ti
n
g
o
n
l
y
T
r
x
I
D,
C
u
s
to
m
er
I
d
,
T
r
x
Date
,
an
d
Am
o
u
n
t
f
o
r
f
u
r
t
h
er
p
r
o
ce
s
s
in
g
i
n
th
e
s
u
b
s
eq
u
e
n
t step
s
.
T
h
e
d
etailed
d
ataset
ca
n
b
e
s
ee
n
i
n
Fi
g
u
r
e
1
.
Fig
u
r
e
1
.
T
r
an
s
ac
tio
n
d
ataset
o
f
r
etailer
s
in
I
n
d
o
n
esia
3
.
2
.
P
r
o
po
s
ed
m
et
ho
d
Fig
u
r
e
2
illu
s
tr
ate
s
o
u
r
p
r
o
p
o
s
ed
m
eth
o
d
.
Fo
llo
w
i
n
g
d
ata
p
r
ep
r
o
ce
s
s
in
g
,
th
e
i
n
f
o
r
m
atio
n
u
n
d
er
g
o
e
s
in
p
u
t
in
to
th
e
R
FM
m
o
d
el
f
o
r
th
e
co
m
p
u
ta
tio
n
o
f
R
FM
v
al
u
es.
T
h
ese
attr
ib
u
te
s
ar
e
s
u
b
s
e
q
u
en
tl
y
f
ed
i
n
to
t
h
e
K
-
Me
a
n
s
al
g
o
r
ith
m
.
P
r
io
r
to
clu
s
ter
i
n
g
u
s
i
n
g
t
h
e
K
-
Me
a
n
s
alg
o
r
ith
m
,
d
ata
s
ca
li
n
g
is
p
e
r
f
o
r
m
ed
.
T
o
d
etec
t
o
u
tlier
s
d
u
r
in
g
s
ca
li
n
g
,
th
e
R
o
b
u
s
t
Scaler
is
e
m
p
lo
y
ed
,
d
em
o
n
s
tr
ati
n
g
its
ca
p
ab
ilit
y
to
h
an
d
le
o
u
tlier
s
ef
f
ec
tiv
e
l
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
K
-
Mea
n
s
clu
s
teri
n
g
in
terp
r
eta
tio
n
u
s
in
g
r
ec
en
cy
,
fr
eq
u
e
n
cy
,
a
n
d
mo
n
eta
r
y
fa
cto
r
fo
r
…
(
A
g
u
n
g
N
u
g
r
a
h
a
)
439
Fig
u
r
e
2
.
P
r
o
p
o
s
ed
m
eth
o
d
T
h
e
R
FM
m
o
d
el
is
co
m
p
r
is
ed
o
f
th
r
ee
co
m
p
o
n
en
ts
:
R
(
r
ec
en
c
y
)
,
w
h
ic
h
r
ef
lect
s
th
e
cu
s
to
m
er
’
s
m
o
s
t
r
ec
en
t
tr
an
s
ac
tio
n
d
ate.
Det
er
m
in
in
g
t
h
e
R
v
alu
e
i
n
v
o
lv
es
as
s
es
s
in
g
t
h
e
r
an
g
e
o
f
th
e
cu
s
to
m
er
’
s
la
s
t
tr
an
s
ac
tio
n
d
ate.
F
(
f
r
eq
u
e
n
c
y
)
i
n
d
icate
s
th
e
n
u
m
b
er
o
f
p
u
r
ch
ase
s
a
cu
s
to
m
er
m
ak
e
s
w
it
h
i
n
a
s
p
ec
i
f
ic
ti
m
e
f
r
a
m
e.
C
alc
u
lati
n
g
t
h
e
F
v
alu
e
en
ta
ils
s
u
m
m
i
n
g
th
e
to
t
als
ac
r
o
s
s
all
co
lu
m
n
s
f
r
o
m
Ap
r
il
1
,
2
0
2
0
,
to
J
u
l
y
3
1
,
2
0
2
0
.
Me
an
w
h
ile,
M
(
m
o
n
etar
y
)
co
r
r
esp
o
n
d
s
to
th
e
a
m
o
u
n
t
o
f
m
o
n
e
y
s
p
e
n
t
b
y
t
h
e
cu
s
to
m
er
d
u
r
in
g
a
s
p
ec
i
f
ied
p
er
io
d
.
T
h
e
ca
lcu
latio
n
o
f
th
e
M
v
alu
e
in
v
o
lv
e
s
s
u
m
m
i
n
g
th
e
to
tal
a
m
o
u
n
t
o
f
cu
s
to
m
er
d
ata
f
r
o
m
A
p
r
il 1
to
J
u
l
y
3
1
,
2
0
2
0
.
I
n
th
e
s
u
b
s
eq
u
e
n
t
p
h
a
s
e,
Al
g
o
r
ith
m
1
,
th
e
K
-
Me
an
s
alg
o
r
ith
m
e
x
p
lain
ed
i
n
s
u
b
s
ec
ti
o
n
2
.
3
,
is
ap
p
lied
.
T
h
e
d
eter
m
in
a
tio
n
o
f
t
h
e
o
p
ti
m
a
l
n
u
m
b
er
o
f
cl
u
s
ter
s
is
n
o
t
ar
b
itra
r
y
.
T
w
o
p
r
i
m
ar
y
m
et
h
o
d
s
ar
e
e
m
p
lo
y
ed
f
o
r
th
is
p
u
r
p
o
s
e:
th
e
elb
o
w
m
et
h
o
d
an
d
s
ilh
o
u
ette
an
al
y
s
is
[
1
8
]
,
[
2
0
]
.
T
h
e
elb
o
w
m
et
h
o
d
,
f
r
eq
u
en
tl
y
e
m
p
lo
y
ed
,
en
tails
ap
p
ly
i
n
g
KM
C
to
th
e
d
ataset
w
it
h
a
r
an
g
e
o
f
K
v
alu
e
s
.
Fo
r
ea
ch
K
v
alu
e,
an
av
er
ag
e
s
co
r
e
f
o
r
all
cl
u
s
ter
s
is
ca
lc
u
lated
,
u
s
i
n
g
th
e
s
u
m
o
f
s
q
u
ar
e
d
is
ta
n
ce
s
,
al
s
o
k
n
o
w
n
as
E
u
clid
ea
n
d
is
tan
ce
,
f
r
o
m
ea
c
h
p
o
in
t
to
its
ass
i
g
n
ed
ce
n
ter
as
t
h
e
d
ef
au
l
t
s
co
r
e
.
Sim
u
lta
n
eo
u
s
l
y
,
t
h
e
s
i
lh
o
u
ette
m
et
h
o
d
is
u
tili
ze
d
to
g
au
g
e
t
h
e
q
u
a
lit
y
o
f
clu
s
ter
i
n
g
,
w
h
er
e
a
h
i
g
h
s
i
lh
o
u
ette
s
co
r
e
in
d
icate
s
e
f
f
ec
t
iv
e
cl
u
s
ter
i
n
g
.
T
h
is
s
tu
d
y
in
co
r
p
o
r
ates b
o
th
th
e
el
b
o
w
m
et
h
o
d
an
d
s
il
h
o
u
ette
a
n
al
y
s
i
s
f
o
r
clu
s
ter
d
eter
m
i
n
atio
n
.
Af
ter
id
en
ti
f
y
i
n
g
t
h
e
o
p
ti
m
al
n
u
m
b
er
o
f
clu
s
ter
s
,
t
h
is
al
g
o
r
ith
m
s
e
g
m
e
n
t
s
cu
s
to
m
er
s
a
n
d
ass
ig
n
s
a
r
an
k
i
n
g
f
r
o
m
b
est
to
lo
w
b
ased
o
n
t
h
e
R
FM
m
o
d
el.
S
u
b
s
eq
u
en
tl
y
,
p
o
s
t
-
an
a
l
y
s
is
is
co
n
d
u
cted
f
o
r
ea
c
h
cu
s
to
m
er
clu
s
ter
in
co
n
n
ec
tio
n
w
it
h
th
e
R
FM
m
o
d
el.
F
u
r
th
er
m
o
r
e,
s
p
ec
if
ic
b
u
s
i
n
es
s
s
tr
at
eg
ies
ar
e
p
r
o
p
o
s
ed
f
o
r
d
ee
p
en
in
g
r
elat
io
n
s
h
ip
s
w
i
th
cu
s
to
m
er
s
w
it
h
in
ea
c
h
cl
u
s
t
er
.
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
s
ec
tio
n
d
eli
v
er
s
a
n
elab
o
r
ate
p
r
esen
tatio
n
o
f
t
h
e
r
esear
ch
f
in
d
i
n
g
s
,
p
r
o
v
id
in
g
i
n
s
i
g
h
t
s
in
to
t
h
e
ac
h
iev
ed
r
es
u
lt
s
.
I
t a
ls
o
en
g
a
g
es in
a
n
ex
te
n
s
i
v
e
d
is
c
u
s
s
io
n
t
o
f
u
r
t
h
er
clar
if
y
th
e
s
ig
n
i
f
ica
n
ce
o
f
th
e
o
u
tco
m
es.
4
.
1
.
E
x
peri
m
ent
a
l
r
esu
lt
s
Ou
r
ex
p
er
i
m
e
n
tal
r
es
u
lt
s
w
er
e
o
b
tain
ed
u
s
in
g
th
e
P
y
t
h
o
n
p
r
o
g
r
a
m
m
i
n
g
la
n
g
u
a
g
e
an
d
th
e
Ma
tp
lo
tlib
lib
r
ar
y
.
W
e
ex
tr
ac
ted
d
ata
f
r
o
m
Fi
g
u
r
e
1
an
d
p
r
o
ce
s
s
ed
it
in
to
an
R
FM
m
o
d
el.
E
ac
h
v
ar
iab
le
o
f
R
FM
w
a
s
ca
lcu
lated
as
d
etailed
in
s
u
b
s
ec
tio
n
3
.
2
an
d
th
e
r
esu
l
t
s
wer
e
co
m
b
in
ed
,
as
ill
u
s
tr
ated
in
Fi
g
u
r
e
3
.
T
h
ese
attr
ib
u
tes
w
er
e
th
e
n
i
n
p
u
t
i
n
to
th
e
K
-
Me
a
n
s
alg
o
r
it
h
m
.
B
ef
o
r
e
clu
s
ter
i
n
g
u
s
i
n
g
K
-
Me
a
n
s
,
it
w
a
s
n
ec
es
s
ar
y
to
s
ca
le
th
e
d
ata,
tak
in
g
in
to
co
n
s
id
er
atio
n
th
e
p
r
esen
ce
o
f
o
u
tlier
s
.
T
h
e
s
ea
b
o
r
n
.
d
is
tp
lo
t(
)
f
u
n
ctio
n
w
a
s
e
m
p
lo
y
ed
to
v
is
u
alize
t
h
e
d
is
tr
ib
u
tio
n
o
f
th
e
R
FM
a
n
al
y
s
i
s
f
o
r
m
ed
ea
r
lier
,
s
p
ec
if
ic
all
y
,
th
e
u
n
iv
ar
iat
e
d
is
tr
ib
u
tio
n
o
f
a
v
ar
iab
le
ag
ai
n
s
t
t
h
e
d
en
s
it
y
d
is
tr
ib
u
tio
n
.
F
o
llo
w
i
n
g
t
h
is
,
t
h
e
R
o
b
u
s
t
Sca
ler
w
as
u
tili
ze
d
to
id
en
ti
f
y
o
u
tlier
s
d
u
r
i
n
g
th
e
s
ca
lin
g
p
r
o
ce
s
s
.
T
h
e
R
o
b
u
s
t
Scaler
is
ef
f
ec
ti
v
e
i
n
r
ed
u
cin
g
th
e
i
n
f
l
u
en
ce
o
f
o
u
tlier
s
b
y
s
tan
d
ar
d
izin
g
f
ea
tu
r
es,
r
em
o
v
i
n
g
t
h
e
m
ed
ian
,
an
d
d
iv
id
in
g
ea
c
h
f
ea
tu
r
e
b
y
t
h
e
in
ter
q
u
ar
tile
r
an
g
e
[
2
9
]
.
A
f
ter
s
ca
li
n
g
,
th
e
d
ata
p
r
ep
r
o
ce
s
s
in
g
is
co
m
p
lete,
r
esu
ltin
g
in
9
5
4
r
o
w
s
w
i
th
4
co
lu
m
n
s
:
R
ec
e
n
c
y
Ne
w
,
Fre
q
u
en
c
y
,
Mo
n
etar
y
,
a
n
d
C
u
s
to
m
er
I
d
,
as p
r
esen
ted
in
Fi
g
u
r
e
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
2
3
,
No
.
2
,
A
p
r
il
20
2
5
:
4
3
5
-
446
440
Fig
u
r
e
3
.
R
FM
an
al
y
s
is
f
o
r
ea
ch
cu
s
to
m
er
T
o
in
itiate
clu
s
ter
i
n
g
w
ith
t
h
e
K
-
Me
a
n
s
al
g
o
r
ith
m
,
d
eter
m
i
n
in
g
th
e
ap
p
r
o
p
r
iate
v
alu
e
f
o
r
K
is
ess
e
n
tial.
T
h
is
d
eter
m
i
n
atio
n
ca
n
b
e
ac
h
iev
ed
th
r
o
u
g
h
th
e
u
t
i
lizatio
n
o
f
b
o
th
th
e
elb
o
w
m
et
h
o
d
an
d
s
ilh
o
u
ette
an
al
y
s
is
.
T
h
e
elb
o
w
m
eth
o
d
p
r
o
v
id
es
an
in
itial
esti
m
ate
o
f
a
s
u
itab
le
r
an
g
e
f
o
r
K,
an
d
th
e
s
u
b
s
eq
u
e
n
t
ap
p
licatio
n
o
f
s
i
lh
o
u
ette
a
n
al
y
s
i
s
r
ef
i
n
e
s
th
e
s
elec
tio
n
w
it
h
in
th
a
t
r
an
g
e.
E
m
p
lo
y
in
g
t
h
is
d
u
al
ap
p
r
o
ac
h
en
s
u
r
es t
h
at
th
e
c
h
o
s
e
n
K
y
iel
d
s
clu
s
ter
s
th
at
ar
e
n
o
t o
n
l
y
s
t
atis
ticall
y
m
ea
n
i
n
g
f
u
l b
u
t a
ls
o
w
ell
-
d
ef
in
ed
[
3
0
]
.
I
n
th
e
i
m
p
le
m
e
n
tatio
n
p
h
a
s
e,
w
e
u
til
ize
a
d
ataf
r
a
m
e
co
n
tai
n
in
g
at
tr
ib
u
tes
ac
q
u
ir
ed
in
th
e
p
r
ev
io
u
s
s
tag
e,
a
s
ill
u
s
tr
ated
i
n
F
ig
u
r
e
4
.
T
h
ese
th
r
ee
attr
ib
u
te
s
u
n
d
er
g
o
clu
s
ter
i
n
g
th
r
o
u
g
h
t
h
e
K
-
Me
a
n
s
al
g
o
r
ith
m
w
it
h
K
v
alu
e
s
r
a
n
g
i
n
g
f
r
o
m
1
to
5
0
.
T
h
e
r
esu
l
ts
o
f
t
h
e
el
b
o
w
m
eth
o
d
v
is
u
aliza
t
io
n
i
n
Fig
u
r
e
5
lead
to
t
h
e
co
n
clu
s
io
n
t
h
at
t
h
e
o
p
ti
m
al
K
v
al
u
e,
ac
co
r
d
in
g
to
th
e
e
l
b
o
w
m
et
h
o
d
,
f
all
s
w
it
h
i
n
th
e
r
an
g
e
o
f
5
to
1
0
.
Su
b
s
eq
u
e
n
tl
y
,
s
ilh
o
u
ette
a
n
al
y
s
is
i
s
p
er
f
o
r
m
ed
.
E
x
p
er
i
m
en
ta
l
f
i
n
d
in
g
s
r
e
v
ea
l
t
h
at
t
h
e
a
v
er
ag
e
s
il
h
o
u
e
tte
s
co
r
e
f
o
r
K(
5
)
is
0
.
4
2
4
5
,
f
o
r
K(
6
)
it
is
0
.
4
0
6
0
,
f
o
r
K(
7
)
it
is
0
.
4
0
8
4
,
f
o
r
K(
8
)
it
is
0
.
3
8
0
8
,
f
o
r
K(
9
)
it
is
0
.
3
8
2
3
,
an
d
f
o
r
K(
1
0
)
it
is
0
.
3
8
5
0
,
as
s
h
o
w
n
i
n
Fi
g
u
r
e
6
.
T
h
u
s
,
it
i
s
d
ed
u
ce
d
th
at
th
e
o
p
ti
m
al
v
alu
e
o
f
K,
o
r
th
e
n
u
m
b
er
o
f
clu
s
ter
s
f
o
r
m
ed
,
is
5
.
Fig
u
r
e
4
.
Scaled
d
ata
Fig
u
r
e
5
.
E
lb
o
w
a
n
al
y
s
i
s
Fo
llo
w
i
n
g
t
h
e
cl
u
s
ter
i
n
g
p
r
o
ce
s
s
,
w
e
n
o
w
h
a
v
e
f
i
v
e
c
lu
s
ter
s
,
r
ep
r
esen
ti
n
g
d
is
ti
n
ct
cu
s
to
m
er
s
eg
m
e
n
ts
o
r
,
as
r
ef
er
r
ed
to
,
cu
s
to
m
er
le
v
el
s
.
T
h
e
R
F
M
m
o
d
el
is
e
m
p
lo
y
ed
to
in
ter
p
r
et
t
h
e
o
u
tco
m
e
s
o
f
KM
C
an
d
an
al
y
ze
th
e
u
n
iq
u
e
c
h
ar
ac
ter
is
tics
o
f
cu
s
to
m
er
s
w
i
th
in
e
ac
h
id
en
ti
f
ied
le
v
el.
A
s
d
ep
ict
ed
in
Fig
u
r
e
7
,
ea
ch
cu
s
to
m
er
lev
el
is
ch
ar
ac
ter
ize
d
b
y
s
p
ec
if
ic
R
FM
v
al
u
es.
C
u
s
to
m
er
s
d
is
p
la
y
in
g
th
e
h
i
g
h
e
s
t
v
alu
es
i
n
all
th
r
ee
v
ar
iab
les
—
R
FM
—
ar
e
ca
teg
o
r
ized
as
‘
5
-
s
tar
’
in
th
e
c
u
s
to
m
er
lev
el,
an
d
v
ice
v
er
s
a.
Acc
o
r
d
in
g
l
y
,
f
o
r
all
cu
s
to
m
er
s
id
en
ti
f
ied
b
y
C
u
s
t
o
m
er
I
d
,
th
eir
r
esp
ec
ti
v
e
cu
s
t
o
m
er
le
v
el
is
d
eter
m
in
ed
b
ased
o
n
th
eir
R
FM
attr
ib
u
tes,
g
r
o
u
p
ed
in
to
lab
els,
as ill
u
s
tr
ated
i
n
Fi
g
u
r
e
8
.
W
e
u
t
il
i
z
e
a
m
a
p
p
in
g
m
e
ch
a
n
is
m
to
a
s
s
ig
n
s
ta
r
r
a
t
in
g
s
t
o
c
u
s
t
o
m
e
r
s
b
a
s
e
d
o
n
th
e
i
r
c
l
u
s
t
e
r
i
n
g
l
a
b
e
ls
.
I
f
a
cu
s
t
o
m
e
r
’
s
l
a
b
e
l
i
s
2
,
th
ey
a
r
e
ca
t
eg
o
r
i
z
e
d
as
‘
1
-
s
t
a
r
.
’
Si
m
i
lar
l
y
,
a
lab
el
o
f
0
co
r
r
es
p
o
n
d
s
to
‘
2
-
s
tar
’,
a
lab
el
o
f
1
is
ass
i
g
n
ed
‘
3
-
s
tar
,
’
a
n
d
i
f
th
e
lab
el
is
3
,
t
h
e
cu
s
to
m
er
is
lab
eled
as
‘
4
-
s
t
ar
.
’
I
n
ca
s
es
w
h
er
e
n
o
n
e
o
f
th
e
s
p
ec
if
ied
co
n
d
itio
n
s
ar
e
m
e
t,
th
e
d
ef
a
u
lt
ass
i
g
n
m
e
n
t is
‘
5
-
s
tar
.
’
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
K
-
Mea
n
s
clu
s
teri
n
g
in
terp
r
eta
tio
n
u
s
in
g
r
ec
en
cy
,
fr
eq
u
e
n
cy
,
a
n
d
mo
n
eta
r
y
fa
cto
r
fo
r
…
(
A
g
u
n
g
N
u
g
r
a
h
a
)
441
Fig
u
r
e
6
.
S
ilh
o
u
e
tte
an
al
y
s
is
s
co
r
es
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
2
3
,
No
.
2
,
A
p
r
il
20
2
5
:
4
3
5
-
446
442
Fig
u
r
e
7
.
C
u
s
to
m
er
lev
e
l s
u
m
m
ar
y
Fig
u
r
e
8
.
T
h
e
ass
ig
n
m
e
n
t o
f
a
lev
el
f
o
r
ea
ch
cu
s
to
m
er
4
.
2
.
Dis
cus
s
io
n
A
c
c
o
r
d
i
n
g
t
o
F
ig
u
r
e
8
,
e
ac
h
cu
s
t
o
m
e
r
is
a
s
s
ig
n
e
d
th
r
e
e
s
c
o
r
es
f
o
r
R
F
M
v
a
r
ia
b
l
e
s
,
r
an
g
in
g
f
r
o
m
5
t
o
1
,
a
s
i
llu
s
t
r
a
t
e
d
in
F
ig
u
r
e
7
,
d
en
o
t
e
d
a
s
t
h
e
cu
s
t
o
m
e
r
l
ev
e
l
.
I
n
th
is
l
ev
el
,
th
e
t
o
p
q
u
in
ti
l
e
is
ass
ig
n
e
d
a
s
c
o
r
e
o
f
5
,
w
h
ile
t
h
e
r
e
m
ain
in
g
c
u
s
to
m
er
s
r
ec
eiv
e
s
co
r
es
o
f
4
,
3
,
2
,
an
d
1
r
esp
ec
tiv
el
y
.
T
h
e
co
m
b
in
a
tio
n
o
f
R
FM
s
co
r
es
is
u
tili
ze
d
to
d
eter
m
i
n
e
th
e
le
v
el
o
f
cu
s
to
m
er
lo
y
alt
y
,
g
u
id
in
g
t
h
e
f
o
r
m
u
latio
n
o
f
s
tr
ateg
i
es
ap
p
licab
le
to
th
e
r
esp
ec
tiv
e
SME
s
.
T
h
e
d
is
tr
ib
u
tio
n
o
f
c
u
s
to
m
er
lo
y
a
lt
y
l
ev
els
i
n
ca
te
g
o
r
ies
b
ased
o
n
th
e
R
FM
s
co
r
e
i
s
p
r
esen
ted
in
T
ab
le
1
.
T
ab
le
1
.
R
FM
s
co
r
e
d
escr
ip
tio
n
S
c
o
r
e
C
h
a
r
a
c
t
e
r
i
st
i
c
s
5
C
h
a
mp
i
o
n
s
4
P
o
t
e
n
t
i
a
l
l
o
y
a
l
i
st
3
N
e
e
d
a
t
t
e
n
t
i
o
n
2
A
t
r
i
sk
1
H
i
b
e
r
n
a
t
i
n
g
W
e
a
l
s
o
c
o
n
d
u
c
t
p
o
s
t
-
an
a
ly
s
is
r
e
l
at
e
d
t
o
cu
s
t
o
m
e
r
s
eg
m
en
t
a
t
i
o
n
,
c
at
eg
o
r
i
z
e
d
in
o
u
r
ex
p
e
r
im
en
t
a
l
r
e
s
u
l
ts
as
cu
s
t
o
m
e
r
l
ev
e
ls
b
ase
d
o
n
th
e
R
FM
m
o
d
e
l
,
as
p
r
es
en
t
e
d
in
F
ig
u
r
e
9
.
T
h
e
5
-
s
t
a
r
c
u
s
t
o
m
e
r
s
eg
m
en
t
,
i
d
e
n
tif
i
e
d
as
C
lu
s
t
e
r
4
,
r
e
p
r
es
en
ts
th
e
e
p
i
t
o
m
e
o
f
cu
s
t
o
m
e
r
l
o
y
a
lty
w
it
h
in
th
e
d
at
a
s
et
.
T
h
es
e
c
u
s
t
o
m
e
r
s
b
o
a
s
t
th
e
h
ig
h
es
t
R
F
M
s
c
o
r
e
s
,
s
ig
n
if
y
in
g
a
b
l
en
d
o
f
f
a
c
t
o
r
s
c
o
n
t
r
i
b
u
t
in
g
t
o
th
e
i
r
p
r
em
iu
m
s
t
a
tu
s
.
S
p
e
ci
f
i
c
a
lly
,
th
ey
ex
h
i
b
it
a
r
em
a
r
k
a
b
ly
s
h
o
r
t
p
r
o
c
u
r
em
en
t
in
t
e
r
v
al
,
i
n
d
ic
a
t
e
d
b
y
an
i
n
c
r
e
a
s
e
in
r
e
c
en
cy
(
▲
r
e
c
e
n
cy
n
ew
)
.
A
d
d
i
ti
o
n
a
l
ly
,
t
h
es
e
cu
s
t
o
m
e
r
s
en
g
a
g
e
i
n
t
r
a
n
s
a
c
ti
o
n
s
w
i
th
im
p
r
es
s
iv
e
r
e
g
u
l
a
r
i
ty
,
h
ig
h
lig
h
t
in
g
a
n
e
l
ev
a
t
e
d
f
r
e
q
u
e
n
cy
o
f
p
u
r
ch
a
s
es
(
▲
f
r
e
q
u
en
cy
)
.
M
o
r
e
o
v
e
r
,
th
ei
r
m
o
n
e
t
a
r
y
c
o
n
t
r
i
b
u
t
i
o
n
i
s
s
u
b
s
t
an
ti
a
l
,
r
ef
l
e
c
t
e
d
i
n
a
h
ig
h
s
p
en
d
in
g
v
a
lu
e
(
▲
m
o
n
e
t
a
r
y
)
.
T
h
is
c
o
m
b
in
a
ti
o
n
o
f
c
h
a
r
a
c
t
e
r
i
s
ti
cs
p
o
s
i
ti
o
n
s
th
e
5
-
s
t
a
r
s
e
g
m
en
t
a
s
th
e
m
o
s
t
v
a
lu
a
b
l
e
a
n
d
e
n
g
ag
e
d
g
r
o
u
p
o
f
cu
s
t
o
m
e
r
s
,
s
h
o
w
c
as
in
g
a
c
o
n
s
i
s
t
en
t
an
d
lu
cr
a
t
iv
e
in
t
e
r
ac
t
i
o
n
w
ith
th
e
b
u
s
in
es
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
K
-
Mea
n
s
clu
s
teri
n
g
in
terp
r
eta
tio
n
u
s
in
g
r
ec
en
cy
,
fr
eq
u
e
n
cy
,
a
n
d
mo
n
eta
r
y
fa
cto
r
fo
r
…
(
A
g
u
n
g
N
u
g
r
a
h
a
)
443
Fig
u
r
e
9
.
C
u
s
to
m
er
s
e
g
m
en
ta
t
io
n
b
ased
o
n
R
FM
f
ac
to
r
s
C
o
n
v
er
s
el
y
,
t
h
e
1
-
s
tar
cu
s
to
m
er
s
e
g
m
e
n
t,
id
en
tifie
d
as
c
lu
s
ter
2
,
r
ep
r
esen
ts
c
u
s
to
m
er
s
w
ith
th
e
lo
w
es
t
R
FM
s
co
r
es,
in
d
icati
n
g
a
less
f
a
v
o
r
ab
le
en
g
a
g
e
m
e
n
t
p
atter
n
.
T
h
ese
cu
s
to
m
er
s
e
x
h
ib
it
a
n
ex
ten
d
ed
p
r
o
cu
r
em
e
n
t
in
ter
v
al,
as
r
ef
le
cted
in
a
d
ec
r
ea
s
e
in
r
ec
en
cy
(
▼
r
ec
en
cy
n
e
w
)
.
Fu
r
t
h
er
m
o
r
e,
th
ey
e
n
g
a
g
e
in
f
e
w
er
tr
an
s
ac
tio
n
s
,
s
i
g
n
i
f
y
i
n
g
a
r
ed
u
ce
d
f
r
eq
u
e
n
c
y
o
f
p
u
r
c
h
ase
s
(
▼
f
r
eq
u
en
c
y
)
.
I
n
ad
d
it
io
n
to
th
e
s
e
f
ac
to
r
s
,
th
e
s
p
e
n
d
in
g
v
al
u
e
o
f
t
h
i
s
s
e
g
m
en
t
is
r
elativ
e
l
y
lo
w
(
▼
m
o
n
etar
y
)
.
C
o
llecti
v
el
y
,
t
h
e
s
e
att
r
ib
u
tes
p
o
s
itio
n
t
h
e
1
-
s
tar
s
e
g
m
e
n
t
as
h
av
i
n
g
a
les
s
ac
tiv
e
an
d
f
in
a
n
ciall
y
i
m
p
ac
t
f
u
l
r
elatio
n
s
h
ip
w
it
h
th
e
b
u
s
in
ess
.
Un
d
er
s
ta
n
d
in
g
th
ese
d
is
ti
n
ctio
n
s
b
et
w
ee
n
c
u
s
to
m
er
s
e
g
m
e
n
t
s
en
ab
les
b
u
s
i
n
es
s
es
to
tailo
r
s
tr
ateg
ies
to
en
h
a
n
ce
th
e
lo
y
a
lt
y
an
d
v
al
u
e
o
f
ea
ch
g
r
o
u
p
.
I
n
co
n
clu
s
io
n
,
w
e
p
r
esen
t
s
u
g
g
ested
b
u
s
in
e
s
s
s
tr
ate
g
ie
s
th
at
ca
n
b
e
ex
ec
u
ted
b
y
th
e
m
ar
k
etin
g
an
d
b
u
s
i
n
ess
s
tr
ate
g
ic
tea
m
s
i
n
S
ME
s
,
ali
g
n
i
n
g
w
i
th
th
e
5
cu
s
t
o
m
er
lev
e
ls
id
e
n
ti
f
ied
i
n
o
u
r
ex
p
er
i
m
e
n
tal
r
e
s
u
lt
s
.
T
h
e
p
r
o
p
o
s
ed
ac
tio
n
s
en
co
m
p
ass
o
f
f
er
in
g
r
e
w
ar
d
s
o
n
s
p
ec
ial
o
cc
asio
n
s
,
s
u
g
g
esti
n
g
d
is
co
u
n
ted
p
r
o
d
u
cts
b
ased
o
n
p
ast
p
u
r
ch
ase
p
atter
n
s
,
an
d
s
en
d
i
n
g
p
er
s
o
n
alize
d
em
ail
s
co
n
tain
in
g
r
eg
u
lar
d
is
co
u
n
t
p
r
o
g
r
a
m
s
.
Fu
r
t
h
er
d
etails ca
n
b
e
f
o
u
n
d
i
n
Fig
u
r
e
1
0
.
Fig
u
r
e
10
.
C
u
s
to
m
er
s
eg
m
e
n
ta
tio
n
an
d
p
r
o
p
o
s
ed
b
u
s
in
es
s
s
tr
ateg
ies
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
2
3
,
No
.
2
,
A
p
r
il
20
2
5
:
4
3
5
-
446
444
5.
CO
NCLU
SI
O
N
Seg
m
en
tin
g
c
u
s
to
m
er
s
p
r
o
v
e
s
in
s
tr
u
m
e
n
tal
i
n
f
o
s
ter
i
n
g
s
tr
o
n
g
er
c
u
s
to
m
er
r
elatio
n
s
h
ip
s
i
n
in
d
u
s
tr
ial
an
d
in
n
o
v
atio
n
.
W
h
ile
ac
q
u
ir
i
n
g
n
e
w
c
u
s
to
m
er
s
is
cr
u
cial
f
o
r
b
u
s
in
e
s
s
g
r
o
w
t
h
,
r
etain
in
g
e
x
is
t
in
g
clie
n
ts
h
o
ld
s
ev
en
g
r
ea
ter
s
i
g
n
i
f
ica
n
ce
.
T
h
e
m
ain
f
i
n
d
i
n
g
s
o
f
th
i
s
s
tu
d
y
ce
n
ter
ar
o
u
n
d
th
e
a
n
a
l
y
s
i
s
o
f
cu
s
to
m
e
r
co
n
s
u
m
p
tio
n
b
eh
av
io
r
,
e
m
p
lo
y
in
g
a
n
i
m
p
r
o
v
ed
R
FM
m
o
d
e
l
th
r
o
u
g
h
t
h
e
u
tili
za
tio
n
o
f
t
h
e
KM
C
alg
o
r
it
h
m
.
T
h
e
ap
p
licatio
n
o
f
t
h
e
KM
C
alg
o
r
ith
m
f
ac
il
itates
th
e
clas
s
i
f
icatio
n
o
f
cu
s
to
m
er
b
e
h
av
io
r
in
d
icato
r
s
,
w
i
th
a
th
o
r
o
u
g
h
e
x
a
m
in
a
tio
n
o
f
t
h
e
r
esu
lt
s
.
Gi
v
en
th
a
t
s
e
g
m
en
tati
o
n
r
elies
o
n
R
FM
v
al
u
es,
S
ME
s
n
o
w
ca
n
tailo
r
th
eir
m
ar
k
eti
n
g
s
tr
ate
g
ies
to
alig
n
w
it
h
cu
s
to
m
er
b
u
y
i
n
g
b
eh
av
io
r
.
F
u
t
u
r
e
w
o
r
k
w
ill
i
n
v
o
lv
e
ass
e
s
s
i
n
g
th
e
p
er
f
o
r
m
a
n
ce
o
f
c
u
s
to
m
er
s
with
i
n
ea
c
h
s
e
g
m
en
t,
f
o
c
u
s
i
n
g
o
n
f
r
eq
u
en
t
l
y
p
u
r
ch
a
s
ed
p
r
o
d
u
cts
b
y
s
eg
m
e
n
t
m
e
m
b
er
s
.
T
h
is
ap
p
r
o
ac
h
en
ab
les
m
o
r
e
tar
g
eted
an
d
e
f
f
ec
tiv
e
p
r
o
m
o
tio
n
al
o
f
f
er
s
f
o
r
s
p
ec
if
ic
p
r
o
d
u
cts,
co
n
tr
ib
u
ti
n
g
to
a
m
o
r
e
n
u
a
n
ce
d
an
d
s
tr
ateg
ic
cu
s
to
m
er
en
g
a
g
e
m
e
n
t.
ACK
NO
WL
E
D
G
E
M
E
NT
S
Au
t
h
o
r
s
e
x
p
r
ess
t
h
eir
ap
p
r
ec
iatio
n
to
t
h
e
Dep
ar
t
m
en
t
o
f
I
n
d
u
s
tr
ial
a
n
d
Data
E
n
g
i
n
ee
r
in
g
,
P
u
k
y
o
n
g
Natio
n
al
Un
iv
er
s
it
y
a
n
d
th
e
R
o
b
o
tics
,
Me
ch
atr
o
n
ics,
an
d
I
n
tellig
e
n
t
S
y
s
te
m
R
esear
c
h
Gr
o
u
p
at
th
e
Facu
lt
y
o
f
A
d
v
an
ce
d
T
ec
h
n
o
lo
g
y
a
n
d
M
u
ltid
is
c
ip
lin
e,
A
ir
la
n
g
g
a
Un
i
v
er
s
it
y
,
f
o
r
th
eir
v
al
u
ab
le
s
u
p
p
o
r
t
th
r
o
u
g
h
o
u
t
th
e
r
esear
ch
p
r
o
ce
s
s
.
RE
F
E
R
E
NC
E
S
[
1
]
R.
M
a
r
t
í
n
e
z
-
P
e
l
á
e
z
e
t
a
l
.
,
“
R
o
l
e
o
f
D
i
g
i
t
a
l
T
r
a
n
sf
o
r
mat
i
o
n
f
o
r
A
c
h
i
e
v
i
n
g
S
u
st
a
i
n
a
b
i
l
i
t
y
:
M
e
d
i
a
t
e
d
R
o
l
e
o
f
S
t
a
k
e
h
o
l
d
e
r
s,
K
e
y
C
a
p
a
b
i
l
i
t
i
e
s,
a
n
d
T
e
c
h
n
o
l
o
g
y
,
”
S
u
s
t
a
i
n
a
b
i
l
i
t
y
,
v
o
l
.
1
5
,
n
o
.
1
4
,
p
p
.
1
-
2
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s
u
1
5
1
4
1
1
2
2
1
.
[
2
]
K
.
N
.
L
e
mo
n
a
n
d
P
.
C
.
V
e
r
h
o
e
f
,
“
U
n
d
e
r
st
a
n
d
i
n
g
C
u
s
t
o
me
r
Ex
p
e
r
i
e
n
c
e
T
h
r
o
u
g
h
o
u
t
t
h
e
C
u
s
t
o
me
r
Jo
u
r
n
e
y
,
”
J
o
u
r
n
a
l
o
f
M
a
r
k
e
t
i
n
g
,
v
o
l
.
80
,
n
o
.
6
,
p
p
.
69
-
96
,
2
0
1
6
,
d
o
i
:
1
0
.
1
5
0
9
/
j
m.
1
5
.
0
4
2
0
.
[
3
]
R
.
S
r
i
v
a
st
a
v
a
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
c
u
s
t
o
me
r
c
l
u
st
e
r
s
u
s
i
n
g
R
F
M
mo
d
e
l
:
a
c
a
se
o
f
d
i
v
e
r
se
p
u
r
c
h
a
se
r
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Bu
s
i
n
e
ss
An
a
l
y
t
i
c
s
a
n
d
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
4
,
n
o
.
2
,
p
p
.
45
–
50
,
2
0
1
6
.
[
4
]
P
.
P
f
e
i
f
e
r
,
“
T
h
e
o
p
t
i
m
a
l
r
a
t
i
o
o
f
a
c
q
u
i
si
t
i
o
n
a
n
d
r
e
t
e
n
t
i
o
n
c
o
st
s
,
”
J
o
u
r
n
a
l
o
f
T
a
r
g
e
t
i
n
g
,
Me
a
s
u
rem
e
n
t
a
n
d
A
n
a
l
y
s
i
s
f
o
r
M
a
rke
t
i
n
g
,
v
o
l
.
1
3
,
p
p
.
1
7
9
–
1
8
8
,
2
0
0
5
,
d
o
i
:
1
0
.
1
0
5
7
/
p
a
l
g
r
a
v
e
.
j
t
.
5
7
4
0
1
4
2
.
[
5
]
V
.
B
a
l
i
,
V
.
B
h
a
t
n
a
g
a
r
,
S
.
S
i
n
h
a
,
a
n
d
P
.
Jo
h
r
i
,
“
D
i
sr
u
p
t
i
v
e
T
e
c
h
n
o
l
o
g
i
e
s
f
o
r
S
o
c
i
e
t
y
5
.
0
:
Ex
p
l
o
r
a
t
i
o
n
o
f
N
e
w
I
d
e
a
s,
T
e
c
h
n
i
q
u
e
s,
a
n
d
T
o
o
l
s,
”
C
R
C
Pr
e
ss
,
2
0
2
2
,
d
o
i
:
1
0
.
1
2
0
1
/
9
7
8
1
0
0
3
1
5
4
6
8
6
.
[
6
]
O
.
K
o
l
l
a
n
d
A
.
P
l
a
n
k
,
“
D
o
sh
o
p
p
e
r
s
c
h
o
o
se
t
h
e
same
b
r
a
n
d
o
n
t
h
e
n
e
x
t
t
r
i
p
w
h
e
n
f
a
c
i
n
g
t
h
e
same
c
o
n
t
e
x
t
?
A
n
e
mp
i
r
i
c
a
l
i
n
v
e
st
i
g
a
t
i
o
n
i
n
F
M
C
G
r
e
t
a
i
l
i
n
g
,
”
J
o
u
rn
a
l
o
f
Re
t
a
i
l
i
n
g
,
v
o
l
.
9
8
,
n
o
.
4
,
p
p
.
5
7
6
-
5
9
2
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
r
e
t
a
i
.
2
0
2
2
.
0
1
.
0
0
3
.
[
7
]
N
.
L
.
R
a
n
e
,
A
.
A
c
h
a
r
i
,
a
n
d
S
.
P
.
C
h
o
u
d
h
a
r
y
,
“
En
h
a
n
c
i
n
g
c
u
s
t
o
me
r
l
o
y
a
l
t
y
t
h
r
o
u
g
h
q
u
a
l
i
t
y
o
f
se
r
v
i
c
e
:
Ef
f
e
c
t
i
v
e
st
r
a
t
e
g
i
e
s
t
o
i
mp
r
o
v
e
c
u
st
o
me
r
sa
t
i
sf
a
c
t
i
o
n
,
e
x
p
e
r
i
e
n
c
e
,
r
e
l
a
t
i
o
n
sh
i
p
,
a
n
d
e
n
g
a
g
e
me
n
t
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
Re
se
a
rc
h
J
o
u
r
n
a
l
o
f
Mo
d
e
r
n
i
z
a
t
i
o
n
i
n
En
g
i
n
e
e
ri
n
g
T
e
c
h
n
o
l
o
g
y
a
n
d
S
c
i
e
n
c
e
,
v
o
l
.
5
,
n
o
.
5
,
p
p
.
3
8
1
0
4
,
M
a
y
2
0
2
3
,
doi
:
1
0
.
5
6
7
2
6
/
I
R
JM
ET
S
3
8
1
0
4
.
[
8
]
M
.
A
.
C
a
mi
l
l
e
r
i
,
“
M
a
r
k
e
t
S
e
g
me
n
t
a
t
i
o
n
,
T
a
r
g
e
t
i
n
g
a
n
d
P
o
si
t
i
o
n
i
n
g
,
”
i
n
Tr
a
v
e
l
M
a
rk
e
t
i
n
g
,
T
o
u
ri
sm
Ec
o
n
o
m
i
c
s
a
n
d
t
h
e
A
i
rl
i
n
e
Pro
d
u
c
t
,
S
p
r
i
n
g
e
r,
C
h
a
m
,
S
w
i
t
z
e
r
l
a
n
d
,
2
0
1
8
,
p
p
.
6
9
-
83
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
3
1
9
-
4
9
8
4
9
-
2
_
4
.
[
9
]
T
.
T
a
v
o
r
,
L
.
D
.
G
o
n
e
n
,
a
n
d
U
.
S
p
i
e
g
e
l
,
“
C
u
st
o
me
r
S
e
g
me
n
t
a
t
i
o
n
a
s
a
R
e
v
e
n
u
e
G
e
n
e
r
a
t
o
r
f
o
r
P
r
o
f
i
t
P
u
r
p
o
se
s,
”
Ma
t
h
e
m
a
t
i
c
s
,
v
o
l
.
1
1
,
n
o
.
2
1
,
p
p
.
1
-
20
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
ma
t
h
1
1
2
1
4
4
2
5
.
[
1
0
]
M
.
A
.
R
a
h
i
m,
M
.
M
u
sh
a
f
,
S
.
K
h
a
n
,
a
n
d
Z
.
A
.
A
r
a
i
n
,
“
R
F
M
-
b
a
se
d
r
e
p
u
r
c
h
a
se
b
e
h
a
v
i
o
r
f
o
r
c
u
st
o
me
r
c
l
a
ssi
f
i
c
a
t
i
o
n
a
n
d
se
g
me
n
t
a
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
R
e
t
a
i
l
i
n
g
a
n
d
C
o
n
su
m
e
r
S
e
rv
i
c
e
s
,
v
o
l
.
6
1
,
p
p
.
1
-
9
,
J
u
l
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
r
e
t
c
o
n
se
r
.
2
0
2
1
.
1
0
2
5
6
6
.
[
1
1
]
M
.
Y
.
S
m
a
i
l
i
a
n
d
H
.
H
a
c
h
i
mi
,
“
N
e
w
R
F
M
-
D
c
l
a
ssi
f
i
c
a
t
i
o
n
mo
d
e
l
f
o
r
i
mp
r
o
v
i
n
g
c
u
s
t
o
me
r
a
n
a
l
y
si
s
a
n
d
r
e
sp
o
n
se
p
r
e
d
i
c
t
i
o
n
,
”
Ai
n
S
h
a
m
s
En
g
i
n
e
e
ri
n
g
J
o
u
rn
a
l
,
v
o
l
.
1
4
,
n
o
.
1
2
,
p
p
.
1
-
9
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
se
j
.
2
0
2
3
.
1
0
2
2
5
4
.
[
1
2
]
S
.
N
g
u
y
e
n
,
H
.
N
g
u
y
e
n
,
N
.
N
g
u
y
e
n
,
D
.
-
S
.
M
a
n
,
a
n
d
T
.
-
G
.
L
e
,
“
A
n
Ex
t
e
n
d
e
d
R
F
M
M
o
d
e
l
f
o
r
C
u
s
t
o
me
r
B
e
h
a
v
i
o
u
r
a
n
d
D
e
mo
g
r
a
p
h
i
c
A
n
a
l
y
si
s
i
n
R
e
t
a
i
l
I
n
d
u
st
r
y
,
”
Bu
s
i
n
e
ss
S
y
st
e
m
s
R
e
se
a
rc
h
,
v
o
l
.
1
4
,
n
o
.
1
,
p
p
.
2
6
-
5
3
,
2
0
2
3
,
d
o
i
:
1
0
.
2
4
7
8
/
b
sr
j
-
2
0
2
3
-
0
0
0
2
.
[
1
3
]
L
.
A
b
e
d
n
e
g
o
,
C
.
E
.
N
u
g
r
a
h
e
n
i
,
a
n
d
A
.
S
a
l
s
a
b
i
n
a
,
“
C
u
s
t
o
m
e
r
s
e
g
m
e
n
t
a
t
i
o
n
:
T
r
a
n
s
f
o
r
m
a
t
i
o
n
f
r
o
m
d
a
t
a
t
o
m
a
r
k
e
t
i
n
g
s
t
r
a
t
e
g
y
,
”
i
n
I
A
I
C
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
S
e
r
i
e
s
,
2
0
2
3
,
v
o
l
.
4
,
n
o
.
1
,
p
p
.
1
3
9
–
1
5
2
,
d
o
i
:
1
0
.
3
4
3
0
6
/
c
o
n
f
e
r
e
n
c
e
se
r
i
e
s
.
v
4
i
1
.
6
4
5
.
[
1
4
]
V
.
G
u
e
r
o
l
a
-
N
a
v
a
r
r
o
,
H
.
G
i
l
-
G
o
mez
,
R
.
O
l
t
r
a
-
B
a
d
e
n
e
s,
a
n
d
P
.
S
o
t
o
-
A
c
o
st
a
,
“
C
u
st
o
me
r
r
e
l
a
t
i
o
n
s
h
i
p
ma
n
a
g
e
me
n
t
a
n
d
i
t
s i
m
p
a
c
t
o
n
e
n
t
r
e
p
r
e
n
e
u
r
i
a
l
m
a
r
k
e
t
i
n
g
:
a
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
En
t
re
p
re
n
e
u
rs
h
i
p
a
n
d
M
a
n
a
g
e
m
e
n
t
J
o
u
r
n
a
l
,
v
o
l
.
2
0
,
n
o
.
2
,
p
p
.
5
0
7
-
5
4
7
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
3
6
5
-
022
-
0
0
8
0
0
-
x.
[
1
5
]
C
.
L
e
d
r
o
,
A
.
N
o
s
e
l
l
a
,
a
n
d
I
.
D
.
P
o
z
z
a
,
“
I
n
t
e
g
r
a
t
i
o
n
o
f
A
I
i
n
C
R
M
:
C
h
a
l
l
e
n
g
e
s
a
n
d
g
u
i
d
e
l
i
n
e
s,
”
J
o
u
rn
a
l
o
f
O
p
e
n
I
n
n
o
v
a
t
i
o
n
:
T
e
c
h
n
o
l
o
g
y
,
M
a
rk
e
t
,
a
n
d
C
o
m
p
l
e
x
i
t
y
,
v
o
l
.
9
,
n
o
.
4
,
p
p
.
1
-
13
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
o
i
t
m
c
.
2
0
2
3
.
1
0
0
1
5
1
.
[
1
6
]
A
.
J.
C
h
r
i
st
y
,
A
.
U
mama
k
e
sw
a
r
i
,
L
.
P
r
i
y
a
t
h
a
r
s
i
n
i
,
a
n
d
A
.
N
e
y
a
a
,
“
R
F
M
r
a
n
k
i
n
g
–
A
n
e
f
f
e
c
t
i
v
e
a
p
p
r
o
a
c
h
t
o
c
u
st
o
me
r
se
g
me
n
t
a
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
K
i
n
g
S
a
u
d
U
n
i
v
e
rsi
t
y
-
C
o
m
p
u
t
e
r
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
3
3
,
n
o
.
1
0
,
p
p
.
1
2
5
1
-
1
2
5
7
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
k
su
c
i
.
2
0
1
8
.
0
9
.
0
0
4
.
[
1
7
]
D
.
S
.
R
a
c
h
ma
h
w
a
t
i
,
R
.
A
n
d
r
e
sw
a
r
i
,
a
n
d
F
.
H
a
mam
i
,
“
C
u
st
o
me
r
S
e
g
me
n
t
a
t
i
o
n
o
f
C
e
l
l
u
l
a
r
Te
l
e
c
o
mm
u
n
i
c
a
t
i
o
n
C
o
mp
a
n
y
U
si
n
g
K
-
M
e
a
n
s
A
l
g
o
r
i
t
h
m
(
C
a
se
S
t
u
d
y
o
f
P
T
I
n
d
o
sat
)
,
”
i
n
2
0
2
2
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
f
S
c
i
e
n
c
e
a
n
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
i
n
S
m
a
r
t
A
d
m
i
n
i
st
r
a
t
i
o
n
(
I
C
S
I
N
T
ES
A)
,
D
e
n
p
a
sar
,
B
a
l
i
,
I
n
d
o
n
e
si
a
,
2
0
2
2
,
p
p
.
4
5
-
5
0
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
S
I
N
T
ES
A
5
6
4
3
1
.
2
0
2
2
.
1
0
0
4
1
5
3
2
.
[
1
8
]
M
.
C
.
U
n
t
o
r
o
,
N
.
T
r
i
a
w
a
t
i
,
Y
.
A
.
Ef
f
e
n
d
i
,
H
.
N
a
t
a
l
i
a
,
a
n
d
M
.
S
.
W
i
sn
u
b
r
o
t
o
,
“
C
o
mp
a
r
i
so
n
o
f
K
-
me
a
n
s
a
n
d
K
-
me
d
o
i
d
s
a
l
g
o
r
i
t
h
m
i
n
g
r
o
u
p
i
n
g
d
e
n
g
u
e
f
e
v
e
r
p
a
t
i
e
n
t
d
a
t
a
(
C
a
se
st
u
d
y
:
K
a
l
i
a
si
n
h
e
a
l
t
h
c
e
n
t
e
r
)
,
”
AI
P
C
o
n
f
e
re
n
c
e
Pr
o
c
e
e
d
i
n
g
s
,
v
o
l
.
2
5
3
6
,
n
o
.
1
,
p
.
0
2
0
0
0
9
,
M
a
y
1
9
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
6
3
/
5
.
0
1
1
9
1
6
5
.
[
1
9
]
Y
.
A
.
Ef
f
e
n
d
i
a
n
d
N
.
N
u
z
u
l
i
t
a
,
“
I
mp
l
e
me
n
t
a
t
i
o
n
o
f
f
u
z
z
y
mu
l
t
i
-
c
r
i
t
e
r
i
a
d
e
c
i
si
o
n
m
a
k
i
n
g
f
o
r
d
e
t
e
r
mi
n
i
n
g
st
u
d
e
n
t
r
a
n
k
(
C
a
se
s
t
u
d
y
:
B
i
m
b
e
l
p
l
u
s I
K
A
)
,
”
AI
P
C
o
n
f
e
re
n
c
e
Pro
c
e
e
d
i
n
g
s
,
v
o
l
.
2
5
3
6
,
n
o
.
1
,
p
.
0
6
0
0
0
4
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
6
3
/
5
.
0
1
2
3
4
7
9
.
[
2
0
]
X
.
Ji
n
a
n
d
J.
H
a
n
,
“
K
-
M
e
a
n
s
C
l
u
s
t
e
r
i
n
g
,
”
i
n
E
n
c
y
c
l
o
p
e
d
i
a
o
f
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
E
d
s.
S
p
r
i
n
g
e
r
,
B
o
st
o
n
,
M
A
,
2
0
1
1
,
p
p
.
5
2
5
-
532
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
0
-
387
-
3
0
1
6
4
-
8
_
4
2
5
.
[
2
1
]
R
.
H
.
K
h
a
n
,
D
.
F
.
D
o
f
a
d
a
r
,
a
n
d
M
.
G
.
R
.
A
l
a
m,
“
Ex
p
l
a
i
n
a
b
l
e
C
u
s
t
o
me
r
S
e
g
me
n
t
a
t
i
o
n
U
s
i
n
g
K
-
me
a
n
s
C
l
u
st
e
r
i
n
g
,
”
in
2
0
2
1
I
E
E
E
Evaluation Warning : The document was created with Spire.PDF for Python.