T
E
L
K
O
M
N
I
K
A
T
elec
o
m
m
un
ica
t
io
n,
Co
m
pu
t
ing
,
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
18
,
No
.
6
,
Dec
em
b
er
2
0
2
0
,
p
p
.
2
9
3
9
~2
9
4
7
I
SS
N:
1
6
9
3
-
6
9
3
0
,
ac
cr
ed
ited
First Gr
ad
e
b
y
Kem
en
r
is
tek
d
i
k
ti,
Dec
r
ee
No
: 2
1
/E/KPT
/2
0
1
8
DOI
: 1
0
.
1
2
9
2
8
/TE
L
KOM
NI
K
A.
v
1
8
i6
.
1
3
3
8
1
2939
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//jo
u
r
n
a
l.u
a
d
.
a
c.
id
/in
d
ex
.
p
h
p
/TELK
OM
N
I
K
A
Ado
pted
topic mo
deling
f
o
r b
usines
s pro
cess
and so
ft
wa
re
co
mpo
nent
co
nfo
rmity chec
king
Adha
t
us
So
lic
ha
h Ahm
a
diy
a
h
,
Riy
a
na
rt
o
Sa
rno
,
F
o
ny
Re
v
ind
a
s
a
ri
De
p
a
rtme
n
t
o
f
In
fo
rm
a
ti
c
s,
In
sti
t
u
t
Tek
n
o
l
o
g
i
S
e
p
u
l
u
h
N
o
p
e
m
b
e
r
,
In
d
o
n
e
sia
Art
icle
I
nfo
AB
S
T
RAC
T
Art
icle
his
to
r
y:
R
ec
eiv
ed
J
u
n
2
1
,
2
0
1
9
R
ev
is
ed
J
u
n
2
0
,
2
0
2
0
Acc
ep
ted
J
u
l 9
,
2
0
2
0
Bu
sin
e
ss
p
r
o
c
e
ss
e
s a
n
d
so
ftwa
re
c
o
m
p
o
n
e
n
ts,
e
sp
e
c
ially
c
las
s d
iag
ra
m
s,
h
a
v
e
a
firm
c
o
n
n
e
c
ti
o
n
.
Co
n
sid
e
ri
n
g
so
ftwa
re
c
o
m
p
o
n
e
n
ts
su
p
p
o
rt
th
e
b
u
sin
e
ss
p
ro
c
e
ss
in
p
ro
v
id
i
n
g
a
n
e
x
c
e
l
le
n
t
p
r
o
d
u
c
t
a
n
d
se
rv
ice
.
Be
sid
e
s,
b
u
si
n
e
ss
p
ro
c
e
ss
c
h
a
n
g
e
s
a
ffe
c
t
o
n
so
f
twa
re
c
o
m
p
o
n
e
n
t
d
e
sig
n
.
On
e
o
f
th
e
m
u
su
a
ll
y
a
p
p
e
a
rs
o
n
th
e
lab
e
l
o
r
n
a
m
e
o
f
t
h
e
so
ftwa
re
c
o
m
p
o
n
e
n
t
o
r
b
u
sin
e
ss
p
ro
c
e
ss
.
S
o
m
e
ti
m
e
s,
a
re
late
d
b
u
si
n
e
ss
p
r
o
c
e
ss
a
n
d
so
ftwa
re
c
o
m
p
o
n
e
n
t
a
p
p
e
a
rs i
n
t
h
e
d
iffere
n
t
la
b
e
l
b
u
t
th
e
sa
m
e
m
e
a
n
in
g
ra
t
h
e
r
th
a
n
u
sin
g
t
h
e
sa
m
e
la
b
e
l.
T
h
is
situ
a
ti
o
n
is
p
ro
b
lem
a
ti
c
wh
e
n
th
e
r
e
a
re
m
a
n
y
c
h
a
n
g
e
s
to
b
e
m
a
d
e
,
in
wh
ich
th
e
so
ftwa
re
c
o
m
p
o
n
e
n
t'
s
m
o
d
if
y
in
g
p
ro
c
e
ss
b
e
c
o
m
e
s
q
u
i
te
lo
n
g
.
Th
e
re
fo
re
,
th
e
so
ftwa
re
m
a
in
ta
in
e
rs
s
h
o
u
ld
o
b
t
a
in
a
n
e
fficie
n
t
p
r
o
c
e
d
u
re
to
s
h
o
rten
t
h
e
m
o
d
ify
i
n
g
p
r
o
c
e
ss
.
On
e
so
l
u
ti
o
n
i
s
b
y
u
sin
g
c
o
n
fo
rm
it
y
c
h
e
c
k
i
n
g
,
w
h
ich
h
e
lp
s
th
e
so
ftwa
re
m
a
in
tai
n
e
rs
k
n
o
w
wh
ich
s
o
ftwa
re
c
o
m
p
o
n
e
n
t
is
re
late
d
to
a
sp
e
c
ifi
c
b
u
si
n
e
ss
p
r
o
c
e
ss
.
Th
is
p
a
p
e
r
c
o
m
p
a
re
d
tw
o
lea
d
i
n
g
t
o
p
ic
m
o
d
e
li
n
g
tec
h
n
iq
u
e
s,
n
a
m
e
ly
p
ro
b
a
b
il
isti
c
late
n
t
se
m
a
n
ti
c
a
n
a
ly
s
is
(P
LS
A)
a
n
d
late
n
t
Dirich
let
a
ll
o
c
a
ti
o
n
(LDA)
,
to
d
e
t
e
rm
in
e
wh
ich
o
n
e
h
a
s
a
b
e
tt
e
r
p
e
rfo
rm
a
n
c
e
fo
r
p
r
o
c
e
ss
trac
e
a
b
il
it
y
.
K
ey
w
o
r
d
s
:
B
u
s
in
ess
p
r
o
ce
s
s
D
o
cu
m
en
t c
lu
s
ter
in
g
S
o
f
t
war
e
co
m
p
o
n
en
t
T
o
p
ic
m
o
d
elin
g
T
r
ac
ea
b
ilit
y
v
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
:
Ad
h
atu
s
So
lich
ah
Ah
m
a
d
iy
ah
,
Dep
ar
t
m
en
t o
f
I
n
f
o
r
m
atics,
I
n
s
titu
t T
ek
n
o
lo
g
i Sep
u
lu
h
No
v
em
b
er
,
Kam
p
u
s
I
T
S
Su
k
o
lilo
,
R
ay
a
I
T
S
St.
,
Su
r
ab
ay
a,
J
awa
T
im
u
r
6
0
1
1
1
,
(
0
3
1
)
5
9
9
4
2
5
1
,
I
n
d
o
n
e
s
ia.
E
m
ail:
ad
h
atu
s
@
if
.
its
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
E
ac
h
co
m
p
an
y
o
r
o
r
g
an
izatio
n
u
s
es
a
b
u
s
in
ess
p
r
o
ce
s
s
th
at
h
as
a
v
ital
r
o
le
in
s
u
p
p
o
r
ti
n
g
p
e
r
f
o
r
m
a
n
ce
an
d
p
r
o
v
id
in
g
th
e
b
est
s
er
v
ice
an
d
p
r
o
d
u
ct
[
1
]
.
T
h
is
f
ac
t
escalate
s
th
e
g
r
o
wth
o
f
r
esear
ch
es
in
th
is
f
iel
d
in
alig
n
in
g
b
u
s
in
ess
p
r
o
ce
s
s
e
s
an
d
s
o
f
twar
e
s
y
s
tem
s
[
2
-
1
0
]
.
At
th
e
s
am
e
ti
m
e,
[
1
1
]
d
etec
ts
f
r
au
d
u
len
c
e
in
a
p
ar
allel
b
u
s
in
ess
p
r
o
ce
s
s
.
A
b
u
s
in
ess
p
r
o
ce
s
s
is
a
b
ag
o
f
ac
tiv
ities
th
at
in
ter
co
n
n
ec
ted
with
th
eir
task
s
[
1
2
]
.
Ho
wev
er
,
th
e
co
m
p
an
y
o
r
o
r
g
an
izatio
n
ca
n
ch
an
g
e
o
n
e
o
f
th
e
p
r
o
ce
s
s
es
o
r
all
in
th
e
b
u
s
in
ess
p
r
o
ce
s
s
.
C
h
an
g
e
in
o
p
er
atio
n
s
tan
d
ar
d
o
r
s
u
p
p
o
r
tin
g
s
y
s
tem
is
o
n
e
o
f
th
e
r
e
aso
n
s
wh
y
th
e
co
m
p
an
y
ch
an
g
ed
its
b
u
s
in
ess
p
r
o
ce
s
s
.
Sm
all
ch
an
g
es
in
t
h
e
b
u
s
in
ess
p
r
o
ce
s
s
h
av
e
a
s
ig
n
if
ican
t
im
p
ac
t
o
n
th
e
o
p
er
atin
g
s
tan
d
ar
d
o
r
s
u
p
p
o
r
tin
g
s
y
s
tem
[
1
3
]
.
I
t h
a
p
p
en
s
b
ec
au
s
e
th
e
b
u
s
in
ess
p
r
o
ce
s
s
an
d
s
u
p
p
o
r
tin
g
s
y
s
tem
ar
e
in
ter
co
n
n
ec
te
d
.
I
n
th
is
r
esear
ch
,
th
e
s
u
p
p
o
r
tin
g
s
y
s
tem
h
as
a
s
o
f
twar
e
co
m
p
o
n
en
t
th
at
co
n
tain
s
class
es
in
t
h
e
f
o
r
m
o
f
a
class
d
iag
r
am
.
I
ts
class
n
am
e
an
d
class
f
u
n
ctio
n
ar
e
u
s
ed
f
o
r
r
ef
er
en
ce
.
Me
an
w
h
ile,
th
e
r
ef
er
en
ce
to
th
e
b
u
s
in
ess
p
r
o
ce
s
s
r
ef
er
s
to
its
ac
tiv
ity
n
am
e.
T
h
o
s
e
th
r
ee
r
ef
er
e
n
ce
s
co
m
p
r
is
e
a
h
in
t
to
id
en
tify
th
e
r
elatio
n
s
h
ip
o
f
a
s
p
ec
if
ic
s
o
f
twar
e
co
m
p
o
n
en
t
to
a
p
ar
tic
u
lar
b
u
s
in
ess
p
r
o
ce
s
s
.
T
h
e
s
tr
aig
h
tf
o
r
war
d
way
to
d
etec
t
th
e
c
o
n
n
ec
tio
n
b
etwe
en
th
em
is
b
y
lo
o
k
in
g
at
t
h
e
s
im
ilar
ity
b
etwe
en
ac
tiv
ity
n
am
e
in
t
h
e
b
u
s
in
ess
p
r
o
ce
s
s
an
d
class
o
r
f
u
n
ctio
n
n
a
m
e
in
th
e
s
o
f
twar
e
c
o
m
p
o
n
en
t.
I
n
f
ac
t,
b
u
s
in
ess
p
r
o
ce
s
s
es
an
d
s
o
f
twar
e
co
m
p
o
n
e
n
ts
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
18
,
No
.
6
,
Dec
em
b
e
r
2
0
2
0
:
2
9
3
9
-
2
9
4
7
2940
o
f
ten
u
s
e
a
d
if
f
er
en
t
n
am
e
b
u
t
h
av
e
th
e
s
am
e
m
ea
n
i
n
g
[
1
3
,
1
4
]
.
Alth
o
u
g
h
th
e
b
u
s
in
ess
p
r
o
c
ess
an
d
its
s
o
f
twar
e
co
m
p
o
n
en
t
u
s
e
a
d
if
f
er
e
n
t
n
am
e,
we
ca
n
s
till
ex
p
lo
r
e
th
e
s
im
ilar
ity
b
etwe
en
th
em
u
s
in
g
tr
ac
ea
b
ilit
y
.
T
r
ac
ea
b
ilit
y
ca
n
h
elp
s
o
f
twar
e
m
ain
tain
er
s
u
n
d
er
s
tan
d
wh
i
ch
s
o
f
twar
e
co
m
p
o
n
en
t
r
elat
ed
to
th
e
b
u
s
in
ess
p
r
o
ce
s
s
.
C
lu
s
ter
in
g
d
o
cu
m
en
ts
ar
e
o
b
tain
a
b
le
to
d
is
co
v
e
r
th
e
tr
ac
ea
b
ilit
y
p
r
o
ce
s
s
[
1
5
]
.
I
n
o
u
r
p
r
e
v
io
u
s
s
tu
d
ies,
[
1
6
]
an
d
[
1
7
]
wer
e
s
u
cc
ess
f
u
lly
u
s
ed
two
lead
in
g
in
f
o
r
m
atio
n
r
etr
iev
al
m
eth
o
d
s
to
r
etr
iev
e
tr
ac
ea
b
ilit
y
o
f
b
u
s
in
ess
p
r
o
ce
s
s
es
an
d
s
o
f
twar
e
co
m
p
o
n
e
n
ts
.
[
1
6
]
u
s
e
d
th
e
p
r
o
b
a
b
ilis
tic
laten
t
s
em
an
tic
an
aly
s
is
(
PL
SA)
[
1
8
]
m
et
h
o
d
,
wh
ile
[
1
7
]
u
s
ed
th
e
laten
t
Dir
ich
let
allo
ca
tio
n
(
L
DA)
[
1
9
]
m
eth
o
d
.
E
v
en
th
o
u
g
h
ea
ch
in
d
iv
id
u
al
p
er
f
o
r
m
e
d
well,
th
eir
u
s
ag
e
f
o
r
a
m
o
r
e
co
m
p
licated
c
ase
h
as
n
o
t
p
r
o
v
ed
.
I
n
th
is
s
tu
d
y
,
we
in
v
esti
g
ate
an
d
co
m
p
ar
e
t
h
e
p
er
f
o
r
m
an
ce
o
f
b
o
th
m
en
tio
n
e
d
m
eth
o
d
s
to
r
etr
ie
v
e
th
e
tr
ac
ea
b
ilit
y
b
etwe
en
s
o
f
tw
ar
e
co
m
p
o
n
en
ts
an
d
th
e
b
u
s
in
ess
p
r
o
ce
s
s
in
a
m
o
r
e
ex
te
n
s
iv
e
ca
s
e
s
tu
d
y
.
2.
L
I
T
E
R
AT
U
RE
S
T
UDY
I
n
[
2
0
]
,
Av
er
s
an
o
et
al
s
tated
th
at
tr
a
ce
ab
ilit
y
m
atr
i
x
alig
n
ed
s
o
f
twar
e
co
m
p
o
n
e
n
ts
an
d
b
u
s
in
ess
p
r
o
ce
s
s
.
E
ar
lier
,
Ma
r
cu
s
an
d
Ma
letic
[
2
1
]
co
n
d
u
cted
tr
ac
ea
b
ilit
y
b
etwe
en
d
o
cu
m
e
n
tatio
n
an
d
s
o
f
twar
e
s
o
u
r
ce
co
d
e
u
s
in
g
laten
t
s
em
an
tic
in
d
ex
in
g
(
L
SI)
.
Me
an
wh
il
e,
Pes
s
io
t
et
al
p
r
o
p
o
s
ed
to
u
s
e
u
n
s
u
p
er
v
is
ed
d
im
en
s
io
n
ality
r
ed
u
ctio
n
m
et
h
o
d
s
in
th
e
d
o
cu
m
e
n
t
clu
s
ter
in
g
[
2
2
]
.
T
h
e
au
th
o
r
s
p
r
o
p
o
s
ed
th
e
ex
ten
s
io
n
o
f
p
r
o
b
a
b
ilis
tic
laten
t
s
em
an
tic
an
aly
s
is
(
PLSA)
m
o
d
el
in
p
er
f
o
r
m
in
g
wo
r
d
a
n
d
d
o
c
u
m
en
t
clu
s
ter
in
g
co
n
cu
r
r
en
tly
in
a
s
in
g
le
asp
ec
t
m
o
d
el.
T
h
e
r
esea
r
ch
es
as
m
en
tio
n
e
d
ea
r
lier
n
ee
d
s
o
m
e
clu
s
ter
in
g
s
an
d
s
im
ilar
ity
m
ea
s
u
r
em
en
ts
.
I
n
[
2
3
]
,
Al
-
An
az
i
et
al
co
m
p
ar
ed
th
e
p
er
f
o
r
m
an
ce
o
f
s
o
m
e
clu
s
te
r
in
g
an
d
s
im
ilar
ity
m
ea
s
u
r
em
en
t
m
eth
o
d
s
.
So
m
e
r
esear
ch
er
s
em
p
lo
y
ed
laten
t
Dir
ich
let
allo
ca
tio
n
(
L
DA)
to
p
er
f
o
r
m
tr
ac
ea
b
ilit
y
o
n
s
o
f
twar
e
en
g
in
e
er
in
g
p
r
o
b
l
em
s
.
As
u
s
ed
b
y
[
1
9
]
,
L
DA
wa
s
em
p
lo
y
ed
to
c
o
u
n
t
e
r
s
o
m
e
I
R
p
r
o
b
lem
s
.
I
n
[
2
4
]
,
th
e
au
th
o
r
u
s
ed
L
DA
to
m
in
in
g
th
e
co
n
ce
p
ts
in
s
o
f
twar
e
im
p
lem
en
tatio
n
co
d
e.
W
h
ile
i
n
[
2
5
]
,
L
DA
f
o
r
m
e
d
tr
ac
ea
b
ilit
y
lin
k
s
o
f
th
e
s
o
f
twar
e
d
o
cu
m
en
tatio
n
a
r
tifa
cts d
u
r
in
g
th
e
d
e
v
elo
p
m
e
n
t p
r
o
ce
s
s
.
3.
B
US
I
NE
SS
P
RO
C
E
SS
AN
D
SO
F
T
WAR
E
C
O
M
P
O
N
E
N
T
W
e
f
o
cu
s
ed
o
n
alig
n
in
g
th
e
o
p
er
atio
n
al
in
teg
r
atio
n
v
iew
o
f
th
e
s
tr
ateg
ic
a
lig
n
m
e
n
t
m
o
d
el
(
SAM)
[
2
6
]
.
A
b
u
s
in
ess
p
r
o
ce
s
s
is
a
g
r
o
u
p
o
f
ac
tiv
ities
wh
ich
ar
e
in
ter
c
o
n
n
ec
ted
to
p
r
o
d
u
ce
a
p
r
o
d
u
c
t
o
r
s
er
v
ice.
W
h
ile,
s
o
f
twar
e
co
m
p
o
n
en
t
co
n
s
is
ts
o
f
class
e
s
an
d
ea
c
h
class
co
n
t
ain
s
f
u
n
ctio
n
s
.
I
n
a
s
o
f
twar
e
d
ev
elo
p
m
en
t
p
r
o
ce
s
s
,
a
s
eq
u
en
ce
d
iag
r
am
d
escr
i
b
es
th
e
b
u
s
in
ess
p
r
o
ce
s
s
.
Vice
v
er
s
a,
ea
ch
b
u
s
in
ess
p
r
o
ce
s
s
is
s
u
p
p
o
r
ted
b
y
I
T
-
d
r
iv
en
s
o
f
twar
e
co
m
p
o
n
e
n
ts
to
r
u
n
th
e
task
s
[
2
0
]
.
Fig
u
r
e
1
illu
s
tr
ate
s
th
e
r
elat
io
n
s
h
ip
b
etwe
en
b
u
s
i
n
ess
p
r
o
ce
s
s
es
an
d
s
o
f
twar
e
co
m
p
o
n
en
ts
.
Fig
u
r
e
1
.
R
elatio
n
s
h
ip
b
etwe
e
n
b
u
s
in
ess
p
r
o
ce
s
s
an
d
s
o
f
twa
r
e
co
m
p
o
n
en
t in
g
en
e
r
al
Fig
u
r
e
1
ex
p
lain
e
d
th
at
a
p
r
o
c
ess
o
f
b
u
s
in
ess
ar
e
co
m
p
o
s
ed
o
f
in
ter
co
n
n
ec
ted
ac
tiv
ities
.
E
ac
h
ac
tiv
ity
r
u
n
s
u
n
d
er
th
e
o
r
d
er
.
As
s
h
o
w
n
at
th
e
b
o
tto
m
o
f
th
e
b
u
s
in
ess
p
r
o
ce
s
s
b
lo
ck
,
a
s
o
f
twar
e
co
m
p
o
n
en
t
is
ass
o
ciate
d
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
A
d
o
p
ted
t
o
p
ic
mo
d
elin
g
fo
r
b
u
s
in
ess
p
r
o
ce
s
s
a
n
d
s
o
ftw
a
r
e
co
mp
o
n
en
t
…
(
A
d
h
a
tu
s
S
o
lich
a
h
A
h
ma
d
iy
a
h
)
2941
with
it,
co
n
n
ec
ted
with
th
e
d
a
s
h
lin
es.
E
ac
h
ac
tiv
ity
r
u
n
s
f
o
llo
win
g
th
e
o
r
d
er
.
At
th
e
b
o
tt
o
m
o
f
th
e
b
u
s
in
ess
p
r
o
ce
s
s
b
lo
ck
,
th
er
e
is
a
s
o
f
twar
e
co
m
p
o
n
en
t
th
at
is
ass
o
ciate
d
with
it,
s
h
o
wn
with
th
e
d
ash
lin
es.
T
h
e
s
o
f
twar
e
co
m
p
o
n
en
t
h
o
ld
s
m
an
y
class
es
to
s
u
p
p
o
r
t
its
jo
b
.
Alth
o
u
g
h
ea
ch
class
h
as
a
s
p
ec
if
ic
n
o
tio
n
,
it
ac
ce
s
s
ib
le
f
o
r
o
th
er
b
u
s
in
ess
p
r
o
ce
s
s
ac
tiv
iti
es.
E
ac
h
ac
tiv
ity
m
a
y
b
e
r
elate
d
to
o
n
e
c
lass
o
r
m
o
r
e
s
u
b
ject
t
o
its
n
ee
d
s
.
B
esid
es,
th
e
n
am
e
u
s
ed
i
n
b
u
s
in
ess
p
r
o
ce
s
s
es a
n
d
s
o
f
twar
e
co
m
p
o
n
e
n
ts
ar
e
o
f
ten
d
if
f
er
e
n
t b
u
t
h
av
e
th
e
s
am
e
m
ea
n
in
g
.
As illu
s
tr
ated
in
Fig
u
r
e
2
,
th
e
r
eg
is
tr
atio
n
p
r
o
ce
s
s
co
n
s
is
ts
o
f
f
o
u
r
co
n
s
ec
u
tiv
e
ac
tiv
ities
s
tar
tin
g
f
r
o
m
r
eg
is
ter
ac
tiv
ity
to
cr
ea
tin
g
a
n
ew
ac
co
u
n
t
ac
tiv
ity
.
T
h
e
r
eg
is
tr
atio
n
ac
tiv
ity
ca
r
r
ied
o
u
t
th
e
e
n
r
o
llm
en
t
p
r
o
ce
s
s
.
T
h
e
s
o
f
twar
e
co
m
p
o
n
en
ts
ass
o
ciate
d
with
th
is
ac
t
iv
ity
ar
e
"r
eg
is
tr
atio
n
Fo
r
m
"
an
d
"a
cc
o
u
n
t
C
o
n
tr
o
l".
T
h
e
n
am
e
o
n
th
e
d
if
f
er
en
t
ac
tiv
ities
as
s
o
ciate
d
with
th
e
r
elate
d
n
am
e
o
f
th
e
class
.
Alth
o
u
g
h
th
e
n
am
es
ar
e
d
if
f
er
en
t
th
e
m
ea
n
in
g
is
th
e
s
am
e.
I
t
is
s
o
m
etim
es
p
r
o
b
lem
atic
b
ec
au
s
e
o
f
d
i
f
f
er
en
ce
s
i
n
th
e
n
am
e
.
T
h
u
s
,
th
e
s
im
ilar
ity
is
r
eq
u
ir
ed
to
s
o
l
v
e
th
is
p
r
o
b
le
m
.
Fig
u
r
e
2
.
B
u
s
in
ess
p
r
o
ce
s
s
an
d
s
o
f
twar
e
co
m
p
o
n
e
n
t v
is
u
al
t
r
ac
ea
b
ilit
y
4.
M
E
T
H
O
DO
L
O
G
Y
T
h
is
s
ec
tio
n
d
escr
ib
es
th
e
c
alcu
latio
n
p
r
o
ce
s
s
u
s
in
g
PL
SA
an
d
L
DA
an
d
s
im
ilar
ity
p
r
o
ce
s
s
.
T
h
e
ex
ec
u
tio
n
f
r
o
m
th
e
p
r
ep
r
o
ce
s
s
in
g
p
h
ase
to
th
e
co
m
p
ar
is
o
n
m
eth
o
d
p
h
ase
ca
n
b
e
s
ee
n
in
Fig
u
r
e
3
.
A
s
eq
u
en
ce
o
f
ac
tiv
ities
ar
e
m
o
d
eled
as
a
b
u
s
in
ess
p
r
o
ce
s
s
d
escr
ip
tio
n
.
Me
an
wh
ile,
ea
ch
m
eth
o
d
a
n
d
f
u
n
ctio
n
s
ar
e
m
o
d
eled
as
s
o
f
twar
e
co
m
p
o
n
en
t
d
o
cu
m
e
n
tatio
n
.
E
ac
h
ac
tiv
ity
,
m
eth
o
d
,
a
n
d
f
u
n
ctio
n
ar
e
in
s
er
ted
in
t
o
d
o
cu
m
e
n
ts
.
T
h
e
n
,
t
h
e
d
o
c
u
m
e
n
ts
ar
e
p
r
o
ce
s
s
ed
in
to
th
e
tex
t
p
r
ep
r
o
ce
s
s
in
g
p
h
ase.
Fig
u
r
e
3
.
C
o
m
p
a
r
is
o
n
p
r
o
ce
s
s
p
h
ase
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
18
,
No
.
6
,
Dec
em
b
e
r
2
0
2
0
:
2
9
3
9
-
2
9
4
7
2942
T
ex
t
p
r
e
p
r
o
ce
s
s
in
g
p
h
ase
o
p
e
r
ates
to
k
en
izatio
n
,
s
to
p
w
o
r
d
r
e
m
o
v
al,
a
n
d
s
tem
m
in
g
.
T
o
k
en
iz
atio
n
s
p
lit
s
th
e
s
en
ten
ce
i
n
to
wo
r
d
s
in
a
d
o
cu
m
en
t
ca
lled
to
k
e
n
s
[
27
]
.
Sto
p
wo
r
d
r
em
o
v
al
elim
in
ates
tr
iv
i
al
an
d
m
ea
n
in
g
less
wo
r
d
s
,
f
o
r
e
x
am
p
le,
p
r
ep
o
s
i
t
io
n
an
d
c
o
n
ju
n
ctio
n
.
L
astl
y
,
s
tem
m
in
g
r
em
o
v
es
p
r
ef
ix
a
n
d
f
o
r
m
th
e
b
asic
wo
r
d
[
2
8
]
.
Af
ter
th
e
p
r
e
p
r
o
ce
s
s
in
g
p
h
ase,
th
e
n
e
x
t
p
h
ase
is
th
e
ca
lcu
latio
n
p
r
o
ce
s
s
u
s
in
g
PLSA
an
d
L
DA.
E
v
er
y
wo
r
d
o
r
ter
m
in
t
h
e
d
o
cu
m
en
ts
h
as
a
p
r
o
b
a
b
ilit
y
v
alu
e
an
d
g
r
o
u
p
e
d
i
n
to
c
er
tai
n
to
p
ics.
H
o
wev
er
,
th
e
s
im
ilar
ity
b
etwe
en
d
o
cu
m
en
ts
an
d
t
o
p
ics
ar
e
u
n
k
n
o
wn
.
T
h
en
,
th
e
p
r
o
ce
s
s
o
f
s
im
ilar
ity
is
r
eq
u
ir
e
d
t
o
d
eter
m
in
e
s
im
ilar
ity
b
y
u
s
in
g
c
o
s
in
e
s
im
ilar
ity
.
Nex
t
s
t
ep
is
th
e
p
r
o
ce
s
s
tr
ac
ea
b
ilit
y
m
atr
ix
.
Af
ter
all
th
e
p
r
o
ce
s
s
f
in
is
h
,
t
h
e
last
p
h
ase
is
p
er
f
o
r
m
in
g
th
e
co
m
p
ar
is
o
n
b
etwe
en
th
e
two
m
eth
o
d
s
,
i.e
.
,
PLSA
an
d
L
DA.
4
.
1
.
P
r
o
ba
bil
is
t
ic
la
t
ent
s
em
a
ntic
a
na
ly
s
is
L
ex
ical
an
d
Sem
an
tic
a
n
aly
s
is
ar
e
two
co
m
m
o
n
m
o
d
els
to
a
n
aly
ze
a
tex
t
d
o
cu
m
e
n
t.
L
ex
ic
al
an
aly
s
is
is
tex
tu
al
an
aly
s
is
th
at
f
o
cu
s
e
s
o
n
th
e
ter
m
s
in
a
d
o
cu
m
en
t
.
Me
an
wh
ile,
s
em
an
tic
o
r
co
n
tex
tu
al
an
aly
s
is
is
an
an
aly
s
is
b
ased
o
n
th
e
m
ea
n
in
g
o
f
wo
r
d
s
in
a
d
o
c
u
m
en
t.
E
ac
h
d
o
c
u
m
en
t
h
as
a
b
u
n
c
h
o
f
wo
r
d
s
(
ter
m
s
)
an
d
k
ey
wo
r
d
s
in
wh
ic
h
ea
ch
k
e
y
wo
r
d
is
a
ter
m
th
at
r
ep
r
esen
ts
th
e
d
o
cu
m
e
n
t.
T
h
e
k
ey
wo
r
d
i
n
th
e
PLSA
m
eth
o
d
r
ef
er
r
ed
to
th
e
asp
ec
t
m
o
d
el,
a
h
id
d
en
v
ar
iab
le
to
f
in
d
th
e
s
am
e
p
atter
n
in
ea
ch
d
o
c
u
m
e
n
t.
Sin
ce
th
e
wo
r
d
s
h
av
in
g
th
e
s
am
e
f
r
eq
u
en
cy
in
th
e
s
am
e
d
o
cu
m
en
t
ar
e
g
r
o
u
p
ed
in
to
o
n
e
to
p
ic.
E
ac
h
tex
t
in
th
e
d
o
cu
m
en
t
is
d
iv
id
ed
in
to
wo
r
d
s
with
m
o
r
e
t
h
an
o
n
e
m
e
an
in
g
an
d
wo
r
d
s
th
at
h
av
e
th
e
s
am
e
m
ea
n
in
g
.
Ne
x
t,
wo
r
d
s
with
s
am
e
f
r
eq
u
e
n
cy
ar
e
ca
lcu
lated
.
Fo
r
ea
ch
wo
r
d
in
t
h
e
d
o
c
u
m
en
t
w
ith
th
e
s
am
e
m
ea
n
in
g
,
it
h
as
th
e
s
am
e
f
r
eq
u
e
n
cy
v
alu
e
[
2
9
]
.
P
r
o
b
a
b
ilis
tic
laten
t
s
em
an
tic
an
aly
s
is
(
PLSA
)
an
d
l
aten
t
s
em
an
tic
a
n
aly
s
is
(
L
S
A
)
ar
e
d
ed
icate
d
t
o
an
aly
ze
th
e
r
elatio
n
s
h
ip
b
etwe
en
d
o
cu
m
e
n
ts
an
d
ter
m
s
o
r
wo
r
d
s
.
T
h
e
d
if
f
er
e
n
ce
is
in
h
o
w
th
e
ca
lcu
latio
n
s
an
d
p
r
o
ce
s
s
es.
T
h
e
p
r
o
ce
s
s
o
f
th
e
L
SA
in
v
o
lv
es
ca
lcu
latin
g
ter
m
f
r
eq
u
e
n
cy
an
d
f
o
r
m
atio
n
m
atr
ix
u
s
in
g
s
in
g
u
lar
v
alu
e
d
ec
o
m
p
o
s
itio
n
(
SVD
)
c
alcu
latio
n
.
Ho
wev
er
,
in
PLSA
th
e
r
elatio
n
s
h
ip
b
etwe
en
d
o
cu
m
en
ts
an
d
wo
r
d
a
r
e
b
r
id
g
ed
b
y
to
p
ics.
T
h
e
o
th
er
d
i
f
f
er
en
ce
is
th
at
PLSA
g
iv
e
a
p
r
o
b
ab
ilit
y
v
alu
e
o
n
d
o
c
u
m
en
ts
,
to
p
ics,
an
d
wo
r
d
s
.
T
h
e
i
n
itial
p
r
o
ce
s
s
in
PLSA
i
s
g
iv
in
g
r
an
d
o
m
p
r
o
b
a
b
ilit
y
v
alu
e
o
n
d
o
cu
m
e
n
ts
,
to
p
ics,
an
d
wo
r
d
s
.
I
n
th
e
PLSA
m
eth
o
d
,
th
e
d
o
cu
m
en
t
(
d
)
is
g
iv
en
a
p
r
o
b
ab
ilit
y
v
alu
e
ca
lled
th
e
d
o
c
u
m
en
t
p
r
o
b
ab
ilit
y
P(d
)
.
T
h
en
,
th
e
to
p
ic
is
f
o
r
m
e
d
b
ased
o
n
th
e
p
r
o
b
ab
ilit
y
o
f
t
h
e
p
r
ev
io
u
s
d
o
cu
m
e
n
t
ca
lled
p
r
o
b
ab
ilit
y
to
p
ic
o
f
d
o
cu
m
en
t
P(z
|
d
)
.
Af
ter
th
at,
t
h
e
wo
r
d
is
f
o
r
m
ed
b
ased
o
n
th
e
p
r
e
v
io
u
s
p
r
o
b
ab
ilit
y
ca
lled
p
r
o
b
ab
ilit
y
w
o
r
d
o
f
to
p
ic
P(w
|
z)
.
T
h
e
ca
lcu
latio
n
wo
r
d
in
t
h
e
d
o
cu
m
en
t u
s
in
g
j
o
in
t p
r
o
b
ab
ilit
y
is
d
escr
ib
ed
in
(
1
)
.
(
,
)
=
(
)
(
,
)
,
(
,
)
=
∑
(
|
)
(
|
)
=
1
(
1
)
I
n
PLSA,
it in
v
o
lv
es a
n
ad
d
iti
o
n
al
s
tep
n
am
ely
ex
p
ec
tatio
n
m
ax
im
izatio
n
(
E
M
s
tep
)
.
T
h
e
p
r
o
b
a
b
ilit
y
o
f
laten
t
v
ar
iab
les
(
to
p
ics)
with
in
th
e
d
o
cu
m
en
t
a
n
d
w
o
r
d
s
is
co
m
p
u
ted
u
s
in
g
th
is
E
M
s
tep
.
T
h
is
ca
lcu
latio
n
is
d
o
n
e
r
ep
ea
ted
ly
u
n
til
it
r
ea
ch
es
th
e
n
u
m
b
er
o
f
iter
atio
n
s
to
o
p
tim
i
ze
th
e
f
it
o
f
th
e
d
ata
with
a
p
r
o
b
ab
ilis
tic
m
o
d
el
an
d
f
in
d
th
e
esti
m
ated
m
a
x
im
u
m
li
k
elih
o
o
d
p
ar
am
eter
.
T
h
e
E
M
s
tep
b
eg
in
s
with
th
e
E
s
tep
co
m
p
u
tatio
n
.
I
t
is
u
s
ed
to
f
in
d
th
e
p
r
o
b
a
b
ilit
y
o
f
laten
t
v
ar
iab
les
in
th
e
d
o
c
u
m
en
t
a
n
d
th
e
w
o
r
d
as
s
h
o
wn
in
(
2
)
.
T
h
en
,
it
is
co
n
tin
u
e
d
with
th
e
M
s
tep
c
o
m
p
u
tatio
n
.
M
s
tep
u
p
d
ates
th
e
v
alu
e
o
f
th
e
p
ar
a
m
eter
in
E
s
tep
as
s
h
o
wn
in
(
3
)
an
d
(
4
)
.
E
M
iter
atio
n
p
r
o
ce
s
s
is
ca
r
r
ied
o
u
t
iter
ativ
ely
u
n
til
it
r
ea
ch
es
th
e
n
u
m
b
er
o
f
iter
atio
n
s
to
ac
h
ie
v
e
o
p
tim
al
p
ar
am
ete
r
v
al
u
es.
T
h
e
m
o
r
e
o
p
tim
al
th
e
p
ar
am
eter
v
alu
es,
th
e
m
o
r
e
f
it th
e
d
ata
an
d
p
r
o
b
ab
ilis
tic
m
o
d
els.
(
|
,
)
=
(
|
)
(
|
)
∑
(
|
)
(
|
)
=
1
(
2
)
(
|
)
=
∑
=
1
(
|
)
(
|
,
)
∑
∑
=
1
(
|
)
(
|
,
)
=
1
(
3
)
(
|
)
=
∑
=
1
(
|
)
(
|
,
)
(
)
(
4
)
T
h
e
f
in
al
p
r
o
b
ab
ilit
y
v
alu
e
is
th
en
u
s
ed
t
o
ca
lcu
late
its
s
im
ilar
ity
.
T
h
e
s
im
ilar
ity
v
alu
e
r
ep
r
esen
ts
th
e
p
r
o
x
im
ity
o
f
th
e
b
u
s
in
ess
p
r
o
ce
s
s
an
d
s
o
f
twar
e
c
o
m
p
o
n
en
ts
.
4
.
2
.
L
a
t
ent
Dirichlet
a
llo
c
a
t
i
o
n
L
aten
t
Dir
ich
let
allo
ca
tio
n
o
r
L
DA
is
a
p
r
o
b
ab
ilis
tic
g
e
n
er
ativ
e
m
o
d
el.
I
t
wo
r
k
s
o
n
a
s
et
o
f
d
o
cu
m
e
n
ts
to
d
ete
r
m
in
e
t
o
p
ic
s
tr
u
ctu
r
e
co
n
tain
ed
.
I
n
L
DA,
we
co
m
p
u
te
th
e
p
r
o
b
ab
ilit
y
d
is
tr
ib
u
tio
n
o
f
wo
r
d
s
to
f
o
r
m
to
p
ics.
T
h
e
n
,
we
cla
s
s
if
y
m
u
ltip
le
to
p
ics
in
to
d
o
c
u
m
en
ts
.
I
n
L
DA,
t
h
e
Dir
ich
l
et
p
r
io
r
d
i
s
tr
ib
u
tio
n
ex
tr
ac
ts
th
e
p
r
o
b
ab
ilit
y
d
is
tr
ib
u
tio
n
b
etwe
en
d
o
cu
m
en
ts
an
d
to
p
ics.
Me
an
wh
ile,
th
e
Po
ly
n
o
m
ial
d
is
tr
ib
u
tio
n
d
er
iv
es th
e
p
r
o
b
ab
ilit
y
d
is
tr
ib
u
tio
n
b
etwe
en
t
o
p
ics an
d
wo
r
d
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
A
d
o
p
ted
t
o
p
ic
mo
d
elin
g
fo
r
b
u
s
in
ess
p
r
o
ce
s
s
a
n
d
s
o
ftw
a
r
e
co
mp
o
n
en
t
…
(
A
d
h
a
tu
s
S
o
lich
a
h
A
h
ma
d
iy
a
h
)
2943
Fig
u
r
e
4
s
h
o
ws
th
e
g
e
n
er
ativ
e
m
o
d
el
o
f
L
DA.
T
h
e
g
en
er
atio
n
p
r
o
ce
s
s
o
f
L
DA
i
s
d
es
cr
ib
ed
as
f
o
llo
ws.
First,
it
d
eter
m
i
n
es
a
to
p
ic
d
is
tr
ib
u
tio
n
f
o
r
th
e
d
o
cu
m
en
t
(
θ)
.
T
h
en
it
ch
o
o
s
es
a
to
p
ic
f
r
o
m
th
e
to
p
ic
d
is
tr
ib
u
tio
n
f
o
r
ea
c
h
wo
r
d
in
th
e
d
o
c
u
m
en
t
(
z
)
.
T
h
en
,
it
ch
o
o
s
es
a
wo
r
d
u
s
in
g
th
e
d
eter
m
in
ed
to
p
ic
-
s
p
ec
if
ic
wo
r
d
d
is
tr
ib
u
tio
n
(
Φ
)
.
α
an
d
β
ar
e
Dir
ich
let
p
a
r
am
eter
,
esti
m
ated
b
y
u
s
er
.
As
s
ee
n
in
th
e
g
r
ap
h
ical
m
o
d
el,
W
i
o
r
wo
r
d
is
th
e
o
n
ly
o
b
s
er
v
ab
le
v
ar
iab
le,
an
d
th
e
r
est
s
u
ch
as
z
,
Φ
,
θ
ar
e
h
i
d
d
en
v
ar
iab
les
o
r
u
s
u
ally
ca
lled
laten
t
v
ar
iab
les.
Par
am
eter
esti
m
ati
o
n
is
r
eq
u
ir
ed
in
L
DA
to
ap
p
r
o
x
im
ate
th
e
p
o
s
ter
io
r
d
is
tr
ib
u
tio
n
o
f
th
e
h
id
d
e
n
v
ar
iab
le
z
(
to
p
ic)
.
Fig
u
r
e
4
.
L
DA
g
e
n
er
atio
n
m
o
d
el
On
e
way
to
esti
m
ate
th
e
p
o
s
te
r
io
r
d
is
tr
ib
u
tio
n
is
b
y
u
s
in
g
Gi
b
b
s
Sam
p
lin
g
.
Gib
b
s
s
am
p
lin
g
is
o
n
e
o
f
Ma
r
k
o
v
c
h
ain
M
o
n
te
C
ar
lo
(
MCMC
)
s
im
u
latio
n
th
at
is
a
s
im
p
le
alg
o
r
ith
m
to
esti
m
ate
in
f
er
en
ce
in
h
ig
h
d
im
en
s
io
n
al
m
o
d
els
lik
e
L
DA
an
d
ea
s
y
to
im
p
lem
en
t.
T
h
e
g
en
er
ativ
e
al
g
o
r
ith
m
f
o
r
t
h
e
L
DA
m
o
d
el
u
s
in
g
Gib
b
s
Sa
m
p
lin
g
is
p
er
f
o
r
m
ed
in
two
p
h
ases
,
i.e
.
,
in
itializatio
n
an
d
Gib
b
s
s
am
p
lin
g
,
as f
o
llo
ws:
4
.
2
.
1
.
I
nitia
liza
t
io
n pha
s
e
Fo
r
ev
er
y
d
o
cu
m
en
ts
m
in
s
et
D:
Fo
r
ev
er
y
w
o
r
d
s
w
in
d
o
cu
m
e
n
t m
:
-
Dr
aw
s
am
p
le
to
p
ic
z
r
an
d
o
m
l
y
~
Mu
lt(1
/K)
.
-
I
n
cr
em
en
t
−
,
(
)
,
−
,
(
.
)
,
−
,
(
)
,
an
d
−
.
4
.
2
.
2
.
G
ibb
s
s
a
m
pli
ng
ph
a
s
e
Fo
r
ea
ch
iter
atio
n
d
o
:
Fo
r
all
d
o
cu
m
e
n
ts
m
in
s
et
D:
Fo
r
all
wo
r
d
s
w
in
d
o
cu
m
e
n
t
m
:
-
C
an
ce
l th
e
cu
r
r
en
t
v
alu
e
o
f
z
i
n
w.
-
Dec
r
em
en
t
−
,
(
)
,
−
,
(
.
)
,
−
,
(
)
,
an
d
−
-
Fo
r
to
p
ic
j =
0
to
K
-
1:
-
C
alcu
late
(
=
|
−
,
)
-
Dr
aw
n
ew
to
p
ic
z
~
(
=
|
−
,
)
-
Ass
ig
n
n
ew
to
p
ic
z
to
wo
r
d
w
-
I
n
cr
em
en
t
−
,
(
)
,
−
,
(
.
)
,
−
,
(
)
,
an
d
−
.
Nex
t,
(
5
)
is
u
s
ed
to
ap
p
r
o
x
im
a
te
th
e
p
o
s
ter
io
r
d
is
tr
ib
u
tio
n
(
=
|
−
,
)
.
(
=
|
−
,
)
∝
−
,
(
)
+
−
,
(
.
)
+
−
,
(
)
+
−
+
(
5
)
−
,
(
)
r
ep
r
esen
ts
th
e
n
u
m
b
er
o
f
wo
r
d
p
u
t
to
to
p
ic
t.
w
h
ile
−
,
(
.
)
r
ep
r
es
en
ts
th
e
to
tal
n
u
m
b
e
r
o
f
wo
r
d
p
u
t
t
o
to
p
ic
t.
−
,
(
)
is
th
e
n
u
m
b
e
r
o
f
th
e
wo
r
d
p
u
t
t
o
to
p
ic
t
in
d
o
c
u
m
en
t
an
d
−
is
th
e
to
tal
n
u
m
b
er
o
f
th
e
wo
r
d
with
in
d
o
cu
m
e
n
t
.
Af
ter
th
e
esti
m
atio
n
p
r
o
ce
s
s
u
s
i
n
g
Gib
b
s
Sam
p
lin
g
,
th
e
p
r
o
b
a
b
ilit
y
d
is
tr
ib
u
tio
n
o
f
to
p
ics
o
v
er
d
o
c
u
m
en
ts
,
(
)
,
is
ca
lcu
lated
u
s
in
g
(
6
)
an
d
th
e
p
r
o
b
ab
ilit
y
d
is
tr
ib
u
tio
n
o
f
wo
r
d
o
v
er
a
to
p
ic
f
o
r
ea
ch
wo
r
d
i
n
th
e
v
o
ca
b
u
la
r
y
,
,
is
ca
lcu
lated
u
s
in
g
(
7
)
.
(
)
=
−
,
(
)
+
−
+
(
6
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
18
,
No
.
6
,
Dec
em
b
e
r
2
0
2
0
:
2
9
3
9
-
2
9
4
7
2944
=
−
,
(
)
+
−
,
(
.
)
+
(
7
)
4
.
3
.
Co
s
ine
s
im
ila
rit
y
Similar
ity
m
ea
s
u
r
em
en
t
d
en
o
tes
h
o
w
s
im
ilar
o
n
e
d
o
c
u
m
e
n
t
to
th
e
o
th
e
r
.
T
h
e
m
ea
s
u
r
em
en
t
is
d
escr
ib
ed
as
d
is
tan
ce
a
n
d
d
im
en
s
io
n
s
r
ep
r
esen
tin
g
th
e
f
ea
tu
r
es
o
f
th
e
o
b
ject.
T
h
e
s
im
ilar
ity
co
m
es
in
th
e
r
a
n
g
e
o
f
ze
r
o
t
o
o
n
e,
ea
ch
r
e
p
r
esen
ts
n
o
t
s
im
ilar
an
d
p
r
ec
is
ely
s
am
e,
r
esp
ec
tiv
ely
.
T
h
e
s
m
aller
th
e
d
is
tan
ce
b
etwe
en
th
e
two
d
o
cu
m
e
n
ts
,
th
e
h
ig
h
er
th
e
s
im
ilar
ity
b
etwe
en
th
em
.
Vice
v
er
s
a,
th
e
g
r
ea
ter
th
e
d
is
tan
ce
b
etwe
en
th
e
two
d
o
cu
m
e
n
ts
,
th
e
lo
we
r
th
e
s
im
ilar
ity
b
etwe
en
th
o
s
e
d
o
cu
m
en
ts
[
2
1
]
.
T
h
er
e
ar
e
co
m
m
o
n
ty
p
es
o
f
m
ea
s
u
r
em
en
ts
f
o
r
te
x
t
m
in
i
n
g
:
E
u
clid
ea
n
d
is
tan
ce
,
Ma
n
h
a
ttan
d
is
ta
n
ce
[
3
0
]
,
J
ac
ca
r
d
s
im
ilar
ity
,
an
d
c
o
s
in
e
s
im
ilar
ity
.
Am
o
n
g
th
o
s
e,
c
o
s
in
e
Similar
ity
is
p
o
p
u
lar
b
ec
au
s
e
o
f
its
ef
f
icien
t e
v
alu
atio
n
.
See
(
8
)
f
o
r
d
etails.
c
os
(
)
=
.
|
|
|
|
|
|
|
|
=
∑
=
1
√
∑
2
=
1
√
∑
2
=
1
(
8
)
Af
ter
co
m
p
letin
g
t
h
e
c
o
s
in
e
s
im
ilar
i
ty
ca
lcu
latio
n
,
th
e
n
ex
t
s
tep
is
to
d
escr
ib
e
th
e
tr
ac
ea
b
ilit
y
m
atr
ix
.
T
r
ac
ea
b
ilit
y
m
atr
ix
v
al
u
es
ar
e
r
etr
iev
ed
an
d
r
elev
a
n
t
v
alu
e.
Her
e,
we
u
s
e
r
ec
all
an
d
p
r
ec
i
s
io
n
m
ea
s
u
r
em
en
ts
[
2
0
]
as
d
escr
ib
ed
in
(
9
)
an
d
(
1
0
)
to
ca
lcu
late
th
e
ac
cu
r
ac
y
o
f
th
e
m
eth
o
d
.
R
ec
all
v
alu
e
is
o
b
tai
n
ed
f
r
o
m
r
et
r
iev
ed
an
d
r
ele
v
an
t
d
ata
d
iv
id
e
d
b
y
t
h
e
v
alu
e
th
at
m
atch
es
t
h
e
r
ele
v
an
t
d
ata.
W
h
ile
th
e
Pre
cisi
o
n
v
alu
e
is
o
b
tain
ed
f
r
o
m
r
et
r
iev
ed
a
n
d
r
elev
a
n
t d
a
ta
d
iv
id
ed
b
y
th
e
v
alu
e
in
g
ettin
g
r
etr
iev
e
d
d
ata.
=
∑
#
(
∩
)
∑
%
(
9
)
=
∑
#
(
∩
)
∑
%
(
10
)
5.
R
E
SU
L
T
S A
N
D
A
N
A
L
Y
SIS
I
n
th
is
r
esear
ch
,
th
e
d
ataset
ca
r
r
ies 1
4
p
r
o
ce
s
s
es,
4
9
ac
tiv
ities
,
an
d
2
9
class
es.
T
h
e
d
ataset
co
n
s
is
ts
o
f
a
p
air
o
f
s
eq
u
en
ce
d
iag
r
am
an
d
class
d
iag
r
am
.
I
n
th
is
r
esear
ch
,
we
in
co
r
p
o
r
ate
a
m
ed
iu
m
s
ca
le
d
ataset
wh
ich
is
m
o
r
e
co
m
p
r
eh
en
s
iv
e
th
a
n
th
e
o
n
e
u
s
ed
b
y
[
1
6
]
an
d
[
1
7
]
.
T
h
e
d
ataset
was
o
r
ig
in
ally
w
r
itten
in
I
n
d
o
n
esian
th
en
we
tr
an
s
lated
it
in
to
E
n
g
lis
h
.
T
ab
le
1
tab
u
lates
a
lis
t
o
f
b
u
s
in
ess
p
r
o
ce
s
s
ac
tiv
ities
.
E
ac
h
ac
tiv
ity
h
as
"BP
"
id
en
tifie
r
.
W
h
ile,
ea
ch
class
o
n
s
o
f
twar
e
co
m
p
o
n
en
ts
h
as "SC
"
id
en
tifie
r
a
s
s
h
o
wn
in
Fig
u
r
e
5
.
T
h
e
id
en
tifie
r
s
p
r
o
m
o
tes
th
e
t
r
ac
ea
b
ilit
y
p
r
o
c
ess
an
d
f
in
d
in
g
r
elev
an
t
v
alu
e.
PLSA
an
d
L
DA
m
eth
o
d
s
g
e
n
e
r
ated
th
e
s
am
e
f
in
al
r
esu
lt
in
ter
m
s
o
f
p
r
ec
is
io
n
a
n
d
r
ec
all
v
alu
es.
T
h
e
r
esu
lt
was
o
b
tain
ed
f
r
o
m
a
p
r
o
b
ab
ilis
tic
v
alu
e,
f
u
r
th
er
m
o
r
e
th
e
s
im
ilar
ity
was
p
r
o
d
u
ce
d
u
s
in
g
c
o
s
in
e
s
im
ilar
ity
.
Sin
ce
PLSA
an
d
L
DA
u
s
ed
a
d
i
f
f
er
en
t
ca
lcu
latio
n
ap
p
r
o
ac
h
,
in
wh
ich
th
e
PLS
A
u
s
ed
ex
p
ec
tatio
n
m
ax
im
iz
atio
n
f
o
r
o
p
tim
izin
g
t
h
e
p
r
o
b
ab
ilit
y
v
alu
e
an
d
th
e
L
DA
u
s
ed
Gib
b
s
Sam
p
lin
g
,
it a
f
f
ec
ted
t
h
e
d
is
tr
ib
u
t
io
n
o
f
th
e
d
o
c
u
m
en
t in
t
o
to
p
ics.
T
ab
le
1
.
L
is
t o
f
b
u
s
in
ess
p
r
o
ce
s
s
I
d
e
n
t
i
f
i
e
r
N
a
me
o
f
a
c
t
i
v
i
t
i
e
s
I
d
e
n
t
i
f
i
e
r
N
a
me
o
f
a
c
t
i
v
i
t
i
e
s
B
P
1
c
h
o
o
s
e
t
y
p
e
f
i
e
l
d
B
P
2
6
sav
e
t
r
a
n
s
a
c
t
i
o
n
d
e
t
a
i
l
B
P
2
v
i
e
w
sc
h
e
d
u
l
e
l
i
t
s
B
P
2
7
g
e
t
p
a
y
me
n
t
a
n
d
p
r
i
n
t
p
a
y
me
n
t
B
P
3
c
h
o
o
s
e
s
c
h
e
d
u
l
e
d
e
t
a
i
l
B
P
2
8
v
i
e
w
r
e
p
o
r
t
ma
n
a
g
e
d
B
P
4
r
e
g
i
s
t
e
r
B
P
2
9
c
h
o
o
s
e
f
i
e
l
d
r
e
n
t
a
l
i
n
c
o
m
e
r
e
p
o
r
t
B
P
5
f
i
l
l
r
e
g
i
st
r
a
t
i
o
n
f
o
r
m
B
P
3
0
c
h
o
o
s
e
f
i
e
l
d
r
e
n
t
a
l
i
n
c
o
m
e
r
e
p
o
r
t
b
a
s
e
d
t
r
a
n
s
a
c
t
i
o
n
d
a
t
e
B
P
6
c
h
e
c
k
a
v
a
i
l
a
b
l
e
a
c
c
o
u
n
t
B
P
3
1
c
h
e
c
k
d
e
t
a
i
l
f
i
e
l
d
r
e
n
t
a
l
i
n
c
o
m
e
r
e
p
o
r
t
B
P
7
c
r
e
a
t
e
n
e
w
a
c
c
o
u
n
t
B
P
3
2
p
r
i
n
t
f
i
e
l
d
r
e
n
t
a
l
i
n
c
o
m
e
r
e
p
o
r
t
B
P
8
r
e
serv
a
t
i
o
n
B
P
3
3
v
i
e
w
r
e
p
o
r
t
s ma
n
a
g
e
d
B
P
9
c
h
e
c
k
sc
h
e
d
u
l
e
c
e
r
t
a
i
n
d
a
t
e
B
P
3
4
c
h
o
o
s
e
f
a
c
i
l
i
t
y
r
e
p
o
r
t
B
P
1
0
c
h
o
o
s
e
d
e
s
i
r
e
d
sc
h
e
d
u
l
e
B
P
3
5
c
h
o
o
s
e
f
a
c
i
l
i
t
y
r
e
p
o
r
t
b
a
se
d
t
r
a
n
sa
c
t
i
o
n
d
a
t
e
B
P
1
1
c
h
o
o
s
e
f
a
c
i
l
i
t
y
B
P
3
6
c
h
e
c
k
d
e
t
a
i
l
f
a
c
i
l
i
t
y
r
e
p
o
r
t
B
P
1
2
c
r
e
a
t
e
n
e
w
r
e
ser
v
a
t
i
o
n
B
P
3
7
p
r
i
n
t
f
a
c
i
l
i
t
y
r
e
p
o
r
t
B
P
1
3
c
h
o
o
s
e
m
y
r
e
serv
a
t
i
o
n
B
P
3
8
v
i
e
w
sc
h
e
d
u
l
e
r
e
n
t
a
l
p
r
i
c
e
a
n
d
f
a
c
i
l
i
t
y
l
i
s
t
r
u
l
e
5
.
1
.
Resul
t
s
Similar
ity
v
alu
e
is
o
b
tain
ed
f
r
o
m
p
r
o
b
ab
ilis
tic
v
alu
e
in
th
e
d
o
cu
m
en
t to
to
p
ic
an
d
p
r
o
b
ab
il
is
tic
to
p
ic.
T
h
e
s
im
ilar
ity
was
ca
lcu
lated
u
s
in
g
c
o
s
in
e
s
im
ilar
ity
to
ea
ch
m
eth
o
d
u
s
ed
.
T
h
e
s
im
ilar
ity
v
alu
e
o
f
PLSA
an
d
L
DA
ar
e
p
r
esen
ted
in
T
ab
le
2
a
n
d
T
ab
le
3
,
r
esp
ec
tiv
el
y
.
T
h
e
‘
X’
an
d
‘
O’
n
o
tati
o
n
s
in
d
ic
ate
th
e
m
atch
es
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
A
d
o
p
ted
t
o
p
ic
mo
d
elin
g
fo
r
b
u
s
in
ess
p
r
o
ce
s
s
a
n
d
s
o
ftw
a
r
e
co
mp
o
n
en
t
…
(
A
d
h
a
tu
s
S
o
lich
a
h
A
h
ma
d
iy
a
h
)
2945
th
e
r
etr
iev
al.
‘
O’
m
ea
n
s
th
at
t
h
e
r
etr
iev
ed
lin
k
is
r
elev
an
t
a
n
d
c
o
r
r
ec
tly
r
etr
iev
e
d
.
Alter
n
a
tiv
ely
,
‘
X’
in
d
icate
s
th
at
th
e
r
etr
iev
ed
lin
k
is
n
o
t
r
elev
an
t.
Af
ter
co
n
s
tr
u
ctin
g
th
e
tr
ac
ea
b
ilit
y
m
atr
ix
,
th
e
n
e
x
t
s
tep
is
to
ca
lcu
la
te
th
e
v
alu
e
o
f
p
r
ec
is
io
n
an
d
r
ec
a
ll
o
f
th
e
two
m
eth
o
d
s
.
B
ef
o
r
e
c
alcu
latin
g
p
r
ec
is
io
n
an
d
r
ec
all
v
alu
es,
a
s
im
ilar
ity
th
r
esh
o
ld
was
s
et.
Fro
m
o
u
r
e
x
p
er
im
en
t,
0
.
6
a
n
d
0
.
8
ar
e
tw
o
to
p
th
r
esh
o
ld
v
alu
es.
T
a
b
le
4
s
h
o
ws
th
e
to
p
ics
u
s
ed
an
d
th
e
av
er
a
g
e
p
r
ec
is
io
n
an
d
r
ec
all
v
alu
es
o
n
ea
ch
to
p
ic
u
s
in
g
0
.
6
th
r
esh
o
ld
v
alu
e.
Me
an
tim
e,
0
.
8
th
r
esh
o
ld
co
m
p
ar
ed
th
e
p
r
ec
is
io
n
an
d
r
ec
all
v
al
u
es o
f
ea
ch
m
eth
o
d
as sh
o
wn
in
T
a
b
le
5
.
Fig
u
r
e
5
.
L
is
t o
f
s
o
f
twar
e
co
m
p
o
n
en
ts
f
o
r
d
ata
test
in
g
T
ab
le
2
.
T
r
ac
ea
b
ilit
y
m
atr
ix
o
b
t
ain
ed
u
s
in
g
PLSA
B
u
s
i
n
e
ss
P
r
o
c
e
ss
A
c
t
i
v
i
t
i
e
s
S
o
f
t
w
a
r
e
C
o
m
p
o
n
e
n
t
:
C
l
a
s
s Nam
e
r
e
g
i
s
t
r
a
t
i
o
n
F
o
r
m
a
c
c
o
u
n
t
f
e
e
d
b
a
c
k
f
e
e
d
b
a
c
k
F
o
r
m
S
o
f
t
w
a
r
e
C
o
m
p
o
n
e
n
t
:
F
u
n
c
t
i
o
n
N
a
me
C
h
o
o
se
R
e
g
i
s
t
r
a
t
i
o
n
S
how
R
e
g
i
s
t
r
a
t
i
o
n
F
o
r
m
C
h
o
o
se
S
u
b
m
i
t
D
a
t
a
S
et
R
e
t
e
r
A
c
c
o
u
n
t
G
et
A
c
c
o
u
n
t
S
et
F
eed
B
a
c
k
G
et
F
e
e
d
B
a
c
k
S
how
F
e
e
d
b
a
c
k
F
o
r
m
C
h
o
o
se
F
e
e
d
B
a
c
k
r
e
g
i
s
t
e
r
O
O
X
O
O
f
i
l
l
r
e
g
i
st
r
a
t
i
o
n
f
o
r
m
O
O
O
X
X
c
h
e
c
k
a
v
a
i
l
a
b
l
e
a
c
c
o
u
n
t
X
O
O
O
O
c
r
e
a
t
e
n
e
w
a
c
c
o
u
n
t
O
X
X
O
O
c
h
o
o
s
e
f
e
e
d
b
a
c
k
X
O
O
O
f
i
l
l
f
e
e
d
b
a
c
k
f
o
r
m
O
O
O
O
v
i
e
w
a
l
l
f
e
e
d
b
a
c
k
l
i
s
t
O
O
O
O
v
i
e
w
f
e
e
d
b
a
c
k
d
e
t
a
i
l
O
X
O
O
T
ab
le
3
.
T
r
ac
ea
b
ilit
y
m
atr
ix
o
b
tain
ed
u
s
in
g
L
DA
B
u
s
i
n
e
ss
P
r
o
c
e
ss
A
c
t
i
v
i
t
i
e
s
S
o
f
t
w
a
r
e
C
o
m
p
o
n
e
n
t
:
C
l
a
s
s Nam
e
R
e
g
i
s
t
r
a
t
i
o
n
F
o
r
m
A
c
c
o
u
n
t
f
e
e
d
b
a
c
k
F
e
e
d
b
a
c
k
F
o
r
m
S
o
f
t
w
a
r
e
C
o
m
p
o
n
e
n
t
:
F
u
n
c
t
i
o
n
N
a
me
C
h
o
o
se
R
e
g
i
s
t
r
a
t
i
o
n
S
how
R
e
g
i
s
t
r
a
t
i
o
n
F
o
r
m
C
h
o
o
se
S
u
b
m
i
t
D
a
t
a
S
et
R
e
t
e
r
A
c
c
o
u
n
t
G
et
A
c
c
o
u
n
t
S
et
F
e
e
d
B
a
c
k
G
et
F
e
e
d
b
a
c
k
S
how
F
e
e
d
b
a
c
k
F
o
r
m
C
h
o
o
se
F
e
e
d
B
a
c
k
r
e
g
i
s
t
e
r
O
O
X
O
O
f
i
l
l
r
e
g
i
st
r
a
t
i
o
n
f
o
r
m
X
X
O
O
O
c
h
e
c
k
a
v
a
i
l
a
b
l
e
a
c
c
o
u
n
t
O
O
X
O
O
c
r
e
a
t
e
n
e
w
a
c
c
o
u
n
t
O
O
X
O
O
c
h
o
o
s
e
f
e
e
d
b
a
c
k
O
O
O
O
f
i
l
l
f
e
e
d
b
a
c
k
f
o
r
m
O
O
O
O
v
i
e
w
a
l
l
f
e
e
d
b
a
c
k
l
i
s
t
O
O
O
O
v
i
e
w
f
e
e
d
b
a
c
k
d
e
t
a
i
l
X
O
O
O
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
18
,
No
.
6
,
Dec
em
b
e
r
2
0
2
0
:
2
9
3
9
-
2
9
4
7
2946
T
ab
le
4
.
Mo
d
el
ev
alu
atio
n
o
n
th
r
esh
o
ld
0
.
6
To
p
i
c
#
A
v
g
.
P
r
e
c
i
si
o
n
o
f
P
LS
A
A
v
g
.
P
r
e
c
i
si
o
n
o
f
LD
A
A
v
g
.
R
e
c
a
l
l
o
f
P
LSA
A
v
g
.
R
e
c
a
l
l
o
f
LD
A
2
7
.
01
12
.
18
1
0
0
.
00
88
.
54
3
10
.
91
15
.
89
93
.
06
90
.
97
4
11
.
32
19
.
71
91
.
67
76
.
04
5
19
.
21
19
.
81
91
.
67
67
.
01
6
15
.
23
25
.
59
87
.
50
71
.
18
7
11
.
92
26
.
83
76
.
39
67
.
36
8
16
.
46
31
.
55
86
.
81
63
.
19
9
2
0
.
16
25
.
85
77
.
78
48
.
61
10
23
.
19
25
.
10
71
.
53
41
.
67
11
22
.
13
36
.
93
72
.
92
58
.
68
T
ab
le
5
.
Mo
d
el
ev
alu
atio
n
o
n
th
r
esh
o
ld
0
.
8
To
p
i
c
#
A
v
g
.
P
r
e
c
i
si
o
n
o
f
P
LSA
A
v
g
.
P
r
e
c
i
si
o
n
o
f
LD
A
A
v
g
.
R
e
c
a
l
l
o
f
P
LSA
A
v
g
.
R
e
c
a
l
l
o
f
LD
A
2
6
.
81
12
.
08
1
0
0
.
00
86
.
46
3
11
.
32
17
.
79
78
.
82
87
.
15
4
12
.
83
22
.
23
82
.
99
64
.
58
5
19
.
22
23
.
89
87
.
85
55
.
21
6
16
.
62
33
.
09
77
.
08
47
.
57
7
13
.
57
27
.
42
65
.
63
45
.
14
8
18
.
82
30
.
28
77
.
43
47
.
92
9
20
.
79
24
.
76
73
.
61
37
.
85
10
24
.
43
25
.
17
56
.
25
30
.
56
11
25
.
62
42
.
19
64
.
93
44
.
44
5
.
2
.
Ana
ly
s
is
L
DA
a
n
d
PLSA
o
b
tain
ed
a
lo
w
v
alu
e
d
r
awn
f
r
o
m
th
eir
f
in
al
r
esu
lt.
Ma
n
y
f
ac
to
r
s
in
f
lu
en
ce
it.
Sp
ec
if
ically
,
d
atasets
,
to
tal
to
p
ics,
an
d
th
r
esh
o
ld
.
Pr
o
b
le
m
s
o
cc
u
r
r
ed
in
class
d
ata
an
d
s
u
p
p
o
r
t
f
u
n
ctio
n
s
.
C
las
s
es
ar
e
n
o
t
s
p
ec
if
icly
as
s
o
ciate
d
to
a
p
ar
ticu
lar
ac
tiv
it
y
.
Fo
r
ex
am
p
le,
th
e
ac
tiv
ity
"Reg
is
ter
"
s
h
o
u
ld
f
it
in
with
th
e
class
"r
eg
is
tr
at
io
n
Fo
r
m
"
b
u
t
s
co
r
es
lo
w
o
n
PLSA
an
d
L
DA
ca
lcu
latio
n
s
.
T
h
e
lo
w
s
co
r
es
in
th
e
class
"r
eg
is
tr
atio
n
Fo
r
m
"
f
o
r
m
ed
d
u
e
to
th
e
class
d
id
n
o
t
co
n
tain
a
s
p
ec
ial
f
u
n
ctio
n
to
"r
eg
is
t
er
"
a
lo
n
e
b
u
t
h
as
an
o
th
er
f
u
n
ctio
n
th
at
"r
eser
v
atio
n
".
I
f
th
e
class
h
as
a
s
p
ec
if
ic
f
u
n
ctio
n
,
th
en
th
e
v
al
u
e
o
b
tain
ed
in
class
"r
eg
is
tr
atio
n
Fo
r
m
"
is
h
ig
h
.
Ot
h
er
th
an
d
ataset,
th
e
n
u
m
b
e
r
o
f
to
p
ics
af
f
ec
ted
p
r
ec
is
io
n
an
d
r
ec
all
v
alu
es
o
n
PLSA
an
d
L
DA
m
eth
o
d
s
.
Alth
o
u
g
h
th
e
co
m
p
ar
is
o
n
was
p
er
f
o
r
m
ed
o
n
t
h
e
s
am
e
n
u
m
b
e
r
o
f
t
o
p
ics,
th
e
d
is
tr
ib
u
tio
n
o
f
d
o
cu
m
en
ts
ca
m
e
o
n
d
if
f
er
en
t t
o
p
ics.
T
h
e
th
r
esh
o
ld
was
o
b
tain
ed
f
r
o
m
o
b
s
er
v
atio
n
wh
en
test
in
g
.
T
h
e
0
.
6
th
r
esh
o
ld
v
alu
e
f
o
r
t
h
e
test
in
g
was
h
ig
h
er
th
an
th
e
o
n
e
u
s
ed
in
[
1
6
]
an
d
[
1
7
]
b
ec
au
s
e
th
e
r
esu
lt
s
ea
r
ch
q
u
er
y
o
n
th
e
s
o
f
twar
e
co
m
p
o
n
en
t
(
r
etr
iev
ed
r
elev
an
t
)
was
h
i
g
h
,
wh
ile
th
e
v
alu
e
th
at
f
its
th
e
r
elev
an
t
d
ata
was
lo
w.
T
h
u
s
,
th
e
n
ee
d
to
in
cr
ea
s
e
th
e
th
r
esh
o
ld
v
alu
e
to
b
e
r
etr
i
ev
ed
b
ec
am
e
less
r
elev
an
t
an
d
s
p
ec
if
ic.
T
h
e
n
ex
t
th
r
esh
o
ld
was
r
aised
to
0
.
8
.
T
h
e
lar
g
e
r
th
e
th
r
esh
o
ld
v
al
u
e,
th
e
m
o
r
e
s
p
ec
if
ic
th
e
r
e
tr
iev
ed
r
elev
a
n
t
v
al
u
e.
I
n
c
o
n
tr
ast,
th
e
s
m
aller
th
e
th
r
esh
o
ld
v
alu
e,
th
e
m
o
r
e
r
elev
an
t
an
d
wid
er
th
e
r
etr
iev
ed
v
alu
e
.
T
h
e
p
r
ec
is
io
n
u
s
in
g
0
.
6
an
d
0
.
8
th
r
esh
o
ld
s
in
th
e
L
DA
m
eth
o
d
is
h
ig
h
er
t
h
an
th
e
PLSA
m
eth
o
d
d
u
e
to
s
p
ec
if
ic
r
elev
an
t
r
etr
iev
ed
v
alu
e
o
b
tain
ed
b
y
L
DA.
Ho
wev
er
,
th
e
m
eth
o
d
PLSA
g
ets
h
ig
h
er
r
ec
all
v
alu
e
t
h
an
th
e
L
DA
m
eth
o
d
b
ec
a
u
s
e
th
e
r
elev
an
t
s
o
f
twar
e
co
m
p
o
n
en
t
v
alu
e
is
m
o
r
e
s
u
ita
b
le
to
th
e
ac
tiv
ity
in
th
e
b
u
s
in
ess
p
r
o
ce
s
s
.
6.
CO
NCLU
SI
O
N
I
n
th
is
p
ap
er
,
we
p
er
f
o
r
m
e
d
tr
ac
ea
b
ilit
y
b
etwe
en
b
u
s
in
ess
p
r
o
ce
s
s
es
an
d
s
o
f
twar
e
co
m
p
o
n
e
n
ts
.
Sp
ec
if
ically
,
f
o
r
o
n
e
p
r
o
b
lem
ca
u
s
ed
b
y
ch
a
n
g
in
g
th
e
n
am
e
o
f
an
ac
tiv
ity
in
th
e
b
u
s
in
ess
p
r
o
ce
s
s
o
r
a
class
n
am
e
in
th
e
s
o
f
twar
e
co
m
p
o
n
en
t
in
w
h
ich
th
e
n
am
e
u
s
ed
i
n
b
u
s
in
ess
p
r
o
ce
s
s
es
an
d
s
o
f
tw
ar
e
co
m
p
o
n
e
n
ts
ar
e
d
if
f
er
en
t
b
u
t
h
av
e
t
h
e
s
am
e
m
ea
n
in
g
.
PLSA
an
d
L
DA
w
er
e
ad
o
p
ted
f
o
r
p
er
f
o
r
m
in
g
t
r
ac
ea
b
ilit
y
b
etwe
en
b
u
s
in
ess
p
r
o
ce
s
s
es
an
d
s
o
f
tw
ar
e
co
m
p
o
n
en
ts
.
B
o
th
m
eth
o
d
s
s
h
ar
e
th
e
s
am
e
u
n
d
e
r
ly
in
g
ass
u
m
p
tio
n
,
i.e
.
,
a
co
ll
ec
tio
n
o
f
wo
r
d
s
c
o
m
p
r
is
e
a
to
p
ic,
th
e
n
a
s
et
o
f
to
p
ics
f
o
r
m
a
d
o
cu
m
e
n
t.
I
t
led
t
o
h
a
n
d
lin
g
th
e
b
u
s
in
ess
p
r
o
ce
s
s
es
an
d
th
e
s
o
f
twar
e
co
m
p
o
n
en
ts
as
d
o
cu
m
e
n
ts
.
Hav
in
g
o
p
tim
ized
th
e
p
r
o
b
ab
ilis
tic
to
p
ic
o
f
th
e
d
o
cu
m
en
t,
we
ca
l
c
u
lated
c
o
s
in
e
s
im
ilar
ity
.
Nex
t,
th
e
tr
ac
ea
b
ilit
y
m
atr
ix
was
g
e
n
er
ated
,
an
d
m
o
d
el
ev
alu
atio
n
was
p
er
f
o
r
m
e
d
u
s
in
g
p
r
ec
is
io
n
a
n
d
r
ec
all.
R
ec
all
v
alu
e
o
n
PLSA
is
h
i
g
h
er
th
an
L
DA
f
o
r
th
e
r
elev
an
t
v
alu
e
b
ec
au
s
e
th
e
s
o
f
twar
e
co
m
p
o
n
e
n
t
is
s
u
itab
le
f
o
r
ac
tiv
it
y
in
th
e
b
u
s
in
ess
p
r
o
ce
s
s
.
Me
a
n
wh
ile,
t
h
e
p
r
ec
is
io
n
v
alu
e
o
f
L
DA
is
h
ig
h
er
th
a
n
PLSA
b
ec
au
s
e
th
e
r
elev
an
t
r
e
tr
iev
ed
v
al
u
e
o
b
tain
ed
b
y
ca
lc
u
latin
g
th
e
L
DA
is
s
p
ec
if
ic.
T
h
e
o
p
tim
u
m
r
esu
lt c
an
b
e
d
r
awn
wh
en
th
e
d
ataset
h
as a
s
p
ec
if
ic
class
b
ased
o
n
t
h
e
s
p
ec
if
ic
a
ctiv
ity
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
A
d
o
p
ted
t
o
p
ic
mo
d
elin
g
fo
r
b
u
s
in
ess
p
r
o
ce
s
s
a
n
d
s
o
ftw
a
r
e
co
mp
o
n
en
t
…
(
A
d
h
a
tu
s
S
o
lich
a
h
A
h
ma
d
iy
a
h
)
2947
RE
F
E
R
E
NC
E
S
[1
]
Tarh
a
n
A
.
,
Tu
r
e
t
k
e
n
O
.
,
Re
ij
e
r
s
H
.
A
.
,
“
B
u
sin
e
ss
p
r
o
c
e
ss
m
a
tu
rit
y
m
o
d
e
ls
:
A
sy
ste
m
a
ti
c
li
ter
a
tu
re
re
v
iew
,
”
In
fo
rm
a
t
io
n
a
n
d
S
o
ft
wa
re
T
e
c
h
n
o
lo
g
y
,
v
o
l.
7
5
,
p
p
.
1
2
2
-
1
3
4
,
J
u
ly
2
0
1
6
.
[2
]
S
a
m
o
sir
H
.
,
S
iah
a
a
n
D
.
,
“
G
e
n
e
ra
ti
n
g
re
q
u
irem
e
n
t
d
e
p
e
n
d
e
n
c
y
g
ra
p
h
b
a
se
d
o
n
c
las
s
d
e
p
e
n
d
e
n
c
y
,
”
I
PT
EK
T
h
e
J
o
u
r
n
a
l
fo
r T
e
c
h
n
o
l
o
g
y
a
n
d
S
c
ien
c
e
,
v
o
l
.
2
9
,
n
o
.
2
,
2
0
1
8
.
[3
]
Lu
ftma
n
J
.
,
Brier
T
.
,
“
Ac
h
iev
i
n
g
a
n
d
su
sta
in
in
g
b
u
sin
e
ss
-
IT
a
li
g
n
m
e
n
t
,
”
Ca
li
fo
r
n
ia
m
a
n
a
g
e
me
n
t
r
e
v
iew
”
v
o
l.
4
2
,
n
o
.
1
,
p
p
.
1
0
9
-
1
2
2
,
1
9
9
9
.
[4
]
Ullah
A
.
,
Lai
R
.
,
“
A
sy
ste
m
a
ti
c
r
e
v
iew
o
f
b
u
sin
e
ss
a
n
d
i
n
fo
rm
a
ti
o
n
tec
h
n
o
lo
g
y
a
li
g
n
m
e
n
t
,”
AC
M
T
ra
n
sa
c
ti
o
n
s
o
n
M
a
n
a
g
e
me
n
t
In
f
o
rm
a
ti
o
n
S
y
ste
ms
(T
M
IS
)
,
v
o
l.
4
,
n
o
.
1
,
p
p
.
1
-
3
0
,
O
c
to
b
e
r
2
0
1
3
.
[5
]
Ha
b
b
a
M
.
,
e
t
a
l
.
,
“
Alig
n
m
e
n
t
b
e
t
we
e
n
b
u
si
n
e
ss
re
q
u
irem
e
n
t,
b
u
si
n
e
ss
p
ro
c
e
ss
,
a
n
d
so
f
twa
re
sy
ste
m
:
A
sy
ste
m
a
ti
c
li
tera
tu
re
re
v
iew
,”
J
o
u
r
n
a
l
o
f
En
g
in
e
e
rin
g
,
p
p
.
1
-
1
9
,
Oc
to
b
e
r
2
0
1
9
.
[6
]
Ca
ste
ll
a
n
o
s
C
.
,
C
o
rre
a
l
D.
,
“
A
F
r
a
m
e
wo
rk
fo
r
a
li
g
n
m
e
n
t
o
f
d
a
ta
a
n
d
p
ro
c
e
ss
e
s
a
rc
h
it
e
c
tu
re
s
a
p
p
li
e
d
i
n
a
g
o
v
e
rn
m
e
n
t
in
stit
u
ti
o
n
,
”
J
o
u
rn
a
l
o
n
Da
ta
S
e
ma
n
ti
c
s
,
v
o
l
.
2
,
n
o
.
2
-
3
,
Ju
n
e
2
0
1
3
.
[7
]
Do
u
m
i
K
.
,
Ba
in
a
S
.
,
Ba
in
a
K.
,
“
S
trate
g
ic
b
u
si
n
e
ss
a
n
d
IT
a
li
g
n
m
e
n
t:
re
p
re
se
n
tatio
n
a
n
d
e
v
a
lu
a
ti
o
n
,”
J
o
u
rn
a
l
o
f
T
h
e
o
re
ti
c
a
l
&
Ap
p
li
e
d
I
n
fo
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
4
7
,
n
o
.
1
,
Ja
n
u
a
ry
2
0
1
3
.
[8
]
Et
ien
A
.
,
Ro
l
lan
d
C.
,
“
M
e
a
su
rin
g
th
e
fi
tn
e
ss
r
e
latio
n
sh
i
p
,”
R
e
q
u
ire
me
n
ts
E
n
g
in
e
e
rin
g
,
v
o
l
.
1
0
,
n
o
.
3
,
p
p
.
1
8
4
-
1
9
7
,
Au
g
u
st
2
0
0
5
.
[9
]
Ka
ss
a
h
u
n
A
.
,
Tek
in
e
rd
o
g
a
n
B.
,
“
BITA*
:
Bu
sin
e
ss
-
IT
a
li
g
n
m
e
n
t
fr
a
m
e
wo
rk
o
f
m
u
lt
ip
le
c
o
ll
a
b
o
ra
ti
n
g
o
rg
a
n
isa
ti
o
n
s
,”
In
fo
rm
a
t
io
n
a
n
d
S
o
ft
wa
re
T
e
c
h
n
o
lo
g
y
,
v
o
l.
1
2
7
,
No
v
e
m
b
e
r
2
0
2
0
.
[1
0
]
M
a
rti
n
e
z
A
.
,
e
t
a
l
.
,
“
In
c
o
rp
o
ra
ti
n
g
tec
h
n
o
lo
g
y
i
n
se
rv
ice
-
o
r
ien
te
d
b
u
si
n
e
ss
m
o
d
e
ls
:
A
c
a
se
stu
d
y
,”
I
n
fo
rm
a
ti
o
n
S
y
ste
ms
a
n
d
E
-
B
u
si
n
e
ss
M
a
n
a
g
e
me
n
t
,
v
o
l.
2
,
n
o
.
1
5
,
p
p
.
4
6
1
-
4
8
7
,
2
0
1
6
.
[
1
1
]
D
a
r
m
a
wa
n
H
.
,
e
t
a
l
.
,
“
A
n
o
m
a
l
y
d
e
t
e
c
t
i
o
n
b
a
s
e
d
o
n
c
o
n
t
r
o
l
-
f
l
o
w
p
a
t
t
e
r
n
o
f
p
a
r
a
l
l
e
l
b
u
s
i
n
e
s
s
p
r
o
c
e
ss
e
s
,”
T
E
L
K
O
M
N
I
K
A
T
e
l
e
c
o
mm
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
6
,
n
o
.
6
,
p
p
.
2
8
0
8
-
2
8
1
5
,
D
e
c
e
m
b
e
r
2018
[1
2
]
Vo
n
Ro
si
n
g
M
.
,
Vo
n
S
c
h
e
e
l
H
.
,
S
c
h
e
e
r
A
.
W
.
,
“
Th
e
c
o
m
p
lete
b
u
si
n
e
ss
p
ro
c
e
ss
h
a
n
d
b
o
o
k
:
b
o
d
y
o
f
k
n
o
wle
d
g
e
fro
m
p
ro
c
e
ss
m
o
d
e
li
n
g
t
o
BP
M
,
2
0
1
4
.
[1
3
]
S
a
rn
o
R
.
,
P
a
m
u
n
g
k
a
s
E
.
W
.
,
S
u
n
a
ry
o
n
o
D
.
,
“
S
a
rwo
sri
b
u
sin
e
s
s
p
ro
c
e
ss
c
o
m
p
o
siti
o
n
b
a
se
d
o
n
m
e
ta
m
o
d
e
ls
,”
Pro
c
e
e
d
in
g
o
f
th
e
I
n
t.
S
e
min
.
I
n
te
ll
.
T
e
c
h
n
o
l.
Its
A
p
p
l
.
IS
I
T
IA
,
p
p
.
3
1
5
–
3
1
8
.
[1
4
]
Ya
n
Z
.
,
Dij
k
m
a
n
R
.
,
G
re
fe
n
P
.
,
“
F
a
st
b
u
si
n
e
ss
p
ro
c
e
ss
sim
il
a
rit
y
s
e
a
rc
h
with
fe
a
tu
re
-
b
a
se
d
sim
il
a
rit
y
e
stim
a
ti
o
n
,
”
L
e
c
t.
No
tes
Co
m
p
u
t.
S
c
i.
(in
c
l
u
d
i
n
g
S
u
b
se
r.
L
e
c
t.
No
tes
Arti
f.
I
n
tel
l.
L
e
c
t.
No
tes
Bi
o
i
n
f
o
rm
a
ti
c
s)
,
p
p
.
6
0
-
7
7
,
2
0
1
0
.
[1
5
]
Dijk
m
a
n
R
.
,
e
t
a
l
.
,
“
S
imilarity
o
f
b
u
si
n
e
ss
p
r
o
c
e
ss
m
o
d
e
ls:
m
e
tri
c
s
a
n
d
e
v
a
lu
a
t
io
n
,”
In
f
o
rm
a
ti
o
n
S
y
ste
m
,
v
o
l
.
3
6
,
n
o
.
2
,
p
p
.
4
9
8
-
5
1
6
,
A
p
ril
2
0
1
1
.
[1
6
]
Re
v
in
d
a
sa
ri
F
.
,
S
a
rn
o
R
.
,
Ah
m
a
d
iy
a
h
A
.
S
.,
“
Trac
e
a
b
il
it
y
b
e
twe
e
n
b
u
sin
e
ss
p
r
o
c
e
ss
a
n
d
so
ftwa
re
c
o
m
p
o
n
e
n
t
u
sin
g
p
ro
b
a
b
il
isti
c
late
n
t
se
m
a
n
ti
c
a
n
a
l
y
sis
,”
Pr
o
c
e
e
d
i
n
g
s
o
f
I
n
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
In
f
o
rm
a
ti
c
s
a
n
d
Co
mp
u
ti
n
g
,
ICIC
,
p
p
.
6
-
1
1
,
2
0
1
6
.
[1
7
]
Ba
sk
a
ra
A
.
R,
S
a
rn
o
R
.
,
A
h
m
a
d
iy
a
h
A
.
S.
,
“
Disc
o
v
e
ri
n
g
trac
e
a
b
il
it
y
b
e
twe
e
n
b
u
si
n
e
ss
p
ro
c
e
s
s
a
n
d
so
ftwa
re
c
o
m
p
o
n
e
n
t
u
si
n
g
late
n
t
d
ir
ich
l
e
t
a
ll
o
c
a
ti
o
n
,
”
Pr
o
c
e
e
d
in
g
s
o
f
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
In
fo
rm
a
ti
c
s
a
n
d
Co
mp
u
t
in
g
,
ICIC
,
Oc
t
2
0
1
6
.
[
1
8
]
H
o
f
m
a
n
n
T
,
“
U
n
s
u
p
e
r
v
i
s
e
d
l
e
a
r
n
in
g
b
y
p
r
o
b
a
b
i
l
i
s
t
i
c
l
a
t
e
n
t
s
e
m
a
n
t
i
c
a
n
a
l
y
s
is
,
”
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
,
p
p
.
1
7
7
-
1
9
6
,
2
0
0
1
.
[1
9
]
Blei
D.
M
.
,
Ng
A
.
Y.,
Jo
rd
a
n
M
.
I.
,
"
Late
n
t
d
iri
c
h
let
a
ll
o
c
a
ti
o
n
,
"
J
o
u
rn
a
l
o
f
M
a
c
h
i
n
e
L
e
a
r
n
in
g
Res
e
a
rc
h
,
v
o
l.
3
,
p
p
.
9
9
3
-
1
0
2
2
,
2
0
0
3
.
[2
0
]
Av
e
rsa
n
o
L
.
,
G
ra
ss
o
C
.
,
To
r
to
re
ll
a
M
.
,
“
M
a
n
a
g
i
n
g
t
h
e
a
li
g
n
m
e
n
t
b
e
twe
e
n
b
u
sin
e
ss
p
r
o
c
e
ss
e
s
a
n
d
so
ft
wa
re
sy
ste
m
s
,”
In
f
o
rm
a
t
io
n
S
o
ft
w
a
re
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
7
2
,
p
p
.
1
7
1
-
1
8
8
,
Ap
ril
2
0
1
6
.
[2
1
]
M
a
rc
u
s
A
.
,
M
a
letic
J
.
I
.
,
“
Re
c
o
v
e
rin
g
d
o
c
u
m
e
n
tatio
n
-
to
-
so
u
rc
e
-
c
o
d
e
trac
e
a
b
il
it
y
li
n
k
s
u
sin
g
l
a
ten
t
se
m
a
n
ti
c
in
d
e
x
in
g
,”
Pro
c
e
e
d
in
g
s
2
5
t
h
In
t.
Co
n
f.
S
o
ft
w.
En
g
,
p
p
.
1
2
5
-
1
3
5
,
M
a
y
2
0
0
3
.
[2
2
]
P
e
ss
io
t
J
.
F
.
,
Kim
Y
.
M
.
,
Am
in
i
M
.
R
.
,
G
a
ll
in
a
ri
P
.
,
“
Im
p
r
o
v
i
n
g
d
o
c
u
m
e
n
t
c
lu
ste
ri
n
g
i
n
a
lea
rn
e
d
c
o
n
c
e
p
t
s
p
a
c
e
”
In
f
o
rm
a
t
io
n
Pro
c
e
ss
in
g
M
a
n
a
g
e
me
n
t
,
v
o
l.
4
6
,
n
o
.
2
,
p
p
.
1
8
0
-
1
9
2
,
M
a
rc
h
2
0
1
0
.
[2
3
]
Al
-
An
a
z
i
S
.
,
e
t
a
l
.
,
“
F
in
d
in
g
sim
i
lar
d
o
c
u
m
e
n
ts
u
sin
g
d
iffere
n
t
c
lu
ste
rin
g
tec
h
n
i
q
u
e
s
,”
Pro
c
e
d
ia
C
o
mp
u
t
er
S
c
i
e
n
c
e
,
v
o
l.
8
2
,
p
p
.
2
8
-
3
4
,
2
0
1
6
.
[2
4
]
Th
o
m
a
s
S
.
W
.
,
“
M
i
n
i
n
g
so
f
twa
re
re
p
o
sito
ries
with
t
o
p
ic
m
o
d
e
l
s
,”
Pro
c
e
e
d
in
g
s
-
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
on
S
o
ft
w
a
re
En
g
in
e
e
rin
g
,
M
a
y
2
0
1
1
.
[2
5
]
As
u
n
c
io
n
H
.
U
.
,
As
u
n
c
io
n
A
.
U
.
,
Tay
lo
r
R
.
N.
,
“
S
o
ftwa
re
trac
e
a
b
il
it
y
wit
h
to
p
ic
m
o
d
e
li
n
g
c
a
teg
o
r
ies
a
n
d
su
b
jec
t
d
e
sc
rip
to
rs
,”
Pr
o
c
e
e
d
in
g
s
-
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
on
S
o
ft
wa
re
E
n
g
i
n
e
e
rin
g
,
v
o
l.
1
,
p
p
.
9
5
-
1
0
4
,
Ju
n
e
2
0
1
0
.
[2
6
]
He
n
d
e
rso
n
J
.
C
.
,
Ve
n
k
a
tram
a
n
H.
,
“
S
trate
g
ic
a
li
g
n
m
e
n
t:
lev
e
ra
g
in
g
in
f
o
rm
a
ti
o
n
tec
h
n
o
lo
g
y
f
o
r
tran
sfo
rm
in
g
o
rg
a
n
iza
ti
o
n
s
,”
IB
M
S
y
ste
ms
J
o
u
rn
a
l
,
v
o
l.
3
2
,
n
o
.
1
,
p
p
.
4
7
2
-
4
8
4
,
1
9
9
3
.
[2
7
]
Ve
rm
a
T
,
“
To
k
e
n
iza
ti
o
n
a
n
d
fil
ter
in
g
p
r
o
c
e
ss
in
ra
p
i
d
m
in
e
r
,”
I
n
t.
J
.
Ap
p
l
.
I
n
f.
S
y
st.
F
o
u
n
d
.
Co
m
p
u
t
.
S
c
i
.
F
CS
,
v
o
l
.
7
,
n
o
.
2
,
p
p
.
1
6
-
1
8
,
2
0
1
4
.
[2
8
]
F
e
ril
li
S
.
,
Esp
o
sito
F
.
,
G
riec
o
D.
,
“
Au
to
m
a
ti
c
lea
rn
i
n
g
o
f
li
n
g
u
isti
c
re
so
u
rc
e
s
fo
r
sto
p
wo
r
d
re
m
o
v
a
l
a
n
d
ste
m
m
in
g
fro
m
tex
t
,”
Pr
o
c
e
d
ia
C
o
mp
u
t
er
S
c
i
e
n
c
e
,
v
o
l.
3
8
,
p
p
.
1
1
6
-
1
2
3
,
2
0
1
4
.
[2
9
]
Ho
fm
a
n
n
T
.
,
“
Un
su
p
e
r
v
ise
d
lea
rn
in
g
b
y
p
r
o
b
a
b
il
isti
c
late
n
t
se
m
a
n
ti
c
a
n
a
ly
sis
,”
M
a
c
h
in
e
L
e
a
r
n
in
g
,
v
o
l.
4
2
,
p
p
.
1
7
7
-
1
9
6
,
2
0
0
1
.
[3
0
]
Jo
y
d
e
e
p
AS,
S
tre
h
l
A
.
,
“
Im
p
a
c
t
o
f
sim
il
a
rit
y
m
e
a
su
re
s
o
n
we
b
-
p
a
g
e
c
lu
ste
ri
n
g
,”
W
o
rk
sh
o
p
o
f
Arti
f
icia
l
I
n
telli
g
e
n
t
fo
r W
e
b
S
e
a
rc
h
,
2
0
0
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.