I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
201
9
,
p
p
.
4
9
3
9
~4
9
5
0
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
ij
ece
.
v9
i
6
.
p
p
4
9
3
9
-
4950
4939
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e
.
co
m/
jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
I
JE
C
E
H
y
brid
a
ppro
a
ch
o
f
the
fu
zz
y
C
-
m
e
a
ns a
nd t
he
K
-
ne
a
rest
n
eig
hbo
rs
m
etho
ds
d
uring
the
r
etr
iev
e
p
ha
se o
f
d
y
na
m
ic
c
a
se
b
a
sed
r
ea
so
ning
f
o
r
p
erso
na
liz
e
d
f
o
llo
w
-
up of
lea
rn
ers in r
ea
l t
i
m
e
E
l G
ho
uch Ni
ha
d
1
,
En
-
Na
i
mi E
l M
o
k
hta
r
2
,
Z
o
u
ha
ir
Abd
elha
m
id
3
,
Al
Ac
hh
a
b M
o
ha
mm
e
d
4
1,
2
L
IS
T
Lab
o
ra
to
ry
,
th
e
F
a
c
u
lt
y
o
f
S
c
ien
c
e
s a
n
d
T
e
c
h
n
o
lo
g
ies
,
A
b
d
e
lma
lek
Ess
a
a
d
i
Un
iv
e
rsit
y
,
T
a
n
g
ier,
M
o
r
o
c
c
o
3
T
h
e
Na
ti
o
n
a
l
S
c
h
o
o
l
o
f
A
p
p
li
e
d
S
c
ien
c
e
s,
A
b
d
e
l
m
a
lek
Ess
a
a
d
i
Un
iv
e
rsity
,
A
l
-
Ho
c
e
i
m
a
,
M
o
ro
c
c
o
4
T
h
e
Na
ti
o
n
a
l
S
c
h
o
o
l
o
f
A
p
p
li
e
d
S
c
ien
c
e
s,
A
b
d
e
l
m
a
lek
Ess
a
a
d
i
Un
iv
e
rsity
,
T
e
to
u
a
n
,
M
o
ro
c
c
o
Art
icle
I
nfo
AB
ST
RAC
T
Ar
ticle
his
to
r
y:
R
ec
eiv
ed
J
a
n
21
,
2
0
1
9
R
ev
i
s
ed
Mar
31
,
2
0
1
9
A
cc
ep
ted
J
u
n
25
,
2
0
1
9
T
h
e
g
o
a
l
o
f
a
d
a
p
ti
v
e
lea
rn
in
g
s
y
ste
m
s
is
to
h
e
lp
th
e
lea
rn
e
r
a
c
h
iev
e
th
e
ir
g
o
a
ls
a
n
d
g
u
id
e
th
e
ir
lea
rn
in
g
.
T
h
e
se
s
y
ste
m
s
m
a
k
e
it
p
o
ss
ib
le
to
a
d
a
p
t
th
e
p
re
se
n
tatio
n
o
f
lea
rn
in
g
re
so
u
rc
e
s
a
c
c
o
rd
in
g
to
lea
rn
e
rs'
n
e
e
d
s,
c
h
a
ra
c
teristics
a
n
d
lea
rn
in
g
sty
l
e
s,
b
y
o
ff
e
rin
g
th
e
m
p
e
rso
n
a
li
z
e
d
c
o
u
rse
s.
W
e
p
ro
p
o
se
a
n
a
p
p
ro
a
c
h
to
a
n
a
d
a
p
ti
v
e
lea
rn
i
n
g
sy
ste
m
th
a
t
tak
e
s
in
to
a
c
c
o
u
n
t
th
e
i
n
it
ial
lea
rn
i
n
g
p
ro
f
il
e
b
a
se
d
o
n
F
e
ld
e
r
S
il
v
e
rm
a
n
'
s
lea
rn
in
g
sty
l
e
m
o
d
e
l
in
o
rd
e
r
to
p
ro
p
o
se
a
n
in
it
i
a
l
lea
rn
in
g
p
a
th
a
n
d
th
e
d
y
n
a
m
ic
c
h
a
n
g
e
o
f
h
is b
e
h
a
v
io
r
d
u
ri
n
g
th
e
lea
rn
in
g
p
ro
c
e
ss
u
sin
g
th
e
In
c
re
m
e
n
tal
D
y
n
a
m
ic Cas
e
Ba
se
d
Re
a
so
n
in
g
a
p
p
r
o
a
c
h
to
m
o
n
it
o
r
a
n
d
c
o
n
tro
l
it
s
b
e
h
a
v
io
r
in
re
a
l
ti
m
e
,
b
a
se
d
o
n
th
e
su
c
c
e
ss
f
u
l
e
x
p
e
rie
n
c
e
s
o
f
o
th
e
r
lea
rn
e
rs,
to
p
e
rso
n
a
li
z
e
th
e
lea
rn
in
g
.
T
h
e
se
l
e
a
rn
e
r
e
x
p
e
rien
c
e
s
a
re
g
ro
u
p
e
d
in
to
h
o
m
o
g
e
n
e
o
u
s
c
las
s
e
s
a
t
th
e
b
e
h
a
v
io
ra
l
lev
e
l,
u
sin
g
th
e
F
u
z
z
y
C
-
M
e
a
n
s
u
n
su
p
e
rv
ise
d
m
a
c
h
in
e
lea
rn
in
g
m
e
th
o
d
to
f
a
c
il
it
a
te
th
e
se
a
rc
h
f
o
r
lea
rn
e
rs
w
it
h
si
m
il
a
r
b
e
h
a
v
io
rs
u
sin
g
th
e
s
u
p
e
rv
ise
d
m
a
c
h
in
e
lea
rn
in
g
m
e
th
o
d
K
-
Ne
a
re
st Ne
ig
h
b
o
rs
.
K
ey
w
o
r
d
s
:
A
d
ap
tiv
e
lear
n
i
n
g
s
y
s
te
m
s
C
lu
s
ter
Feld
er
-
s
il
v
er
m
an
lear
n
i
n
g
s
t
y
l
e
m
o
d
el
(
F
S
L
SM)
Fu
zz
y
C
-
m
ea
n
s
m
e
th
o
d
(
FC
M
)
I
n
cr
e
m
e
n
tal
d
y
n
a
m
ic
c
ase
b
ased
r
ea
s
o
n
in
g
(
I
DC
B
R
)
K
-
Nea
r
est
n
ei
g
h
b
o
r
s
m
eth
o
d
(
KNN)
L
ea
r
n
i
n
g
p
ath
L
ea
r
n
i
n
g
s
t
y
le
Co
p
y
rig
h
t
©
2
0
1
9
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
E
l
Gh
o
u
c
h
Ni
h
ad
,
L
I
ST
L
ab
o
r
ato
r
y
,
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
,
Facu
lt
y
o
f
Sc
ien
ce
s
an
d
T
ec
h
n
o
lo
g
ies,
A
b
d
el
m
a
lek
E
s
s
aa
d
i
Un
iv
er
s
it
y
,
St
r
ee
t o
f
ch
ar
f
B
.
P
4
1
0
,
T
an
g
i
er
,
Mo
r
o
cc
o
.
E
m
ail:
n
i
h
ad
_
elg
h
o
u
ch
@
h
o
t
m
ail.
f
r
1.
I
NT
RO
D
UCT
I
O
N
A
d
ap
tiv
e
lear
n
i
n
g
s
y
s
te
m
s
ar
e
in
ten
d
ed
to
p
r
o
v
id
e
th
e
n
e
ce
s
s
ar
y
p
ed
ag
o
g
ical
to
o
ls
an
d
to
cr
ea
te
th
e
ap
p
r
o
p
r
iate
at
m
o
s
p
h
er
e
t
o
p
r
o
m
o
te
lear
n
in
g
a
m
o
n
g
l
ea
r
n
er
s
.
T
h
ese
s
y
s
te
m
s
n
ee
d
to
tailo
r
lear
n
i
n
g
ac
co
r
d
in
g
to
th
e
p
r
ef
er
en
ce
s
,
n
ee
d
s
an
d
lear
n
i
n
g
s
t
y
les
o
f
ea
ch
lear
n
er
to
p
r
o
v
id
e
a
p
er
s
o
n
alize
d
f
o
llo
w
-
u
p
i
n
r
ea
l
ti
m
e.
I
n
d
iv
id
u
alize
d
lea
r
n
er
f
o
llo
w
-
u
p
p
la
y
s
a
n
i
m
p
o
r
tan
t
r
o
le
in
ad
ap
tiv
e
lear
n
in
g
s
y
s
te
m
s
,
s
i
n
ce
w
it
h
o
u
t
th
e
in
f
o
r
m
a
tio
n
o
n
th
e
p
r
o
g
r
ess
io
n
an
d
th
e
r
esu
lt
s
o
b
tain
ed
b
y
t
h
e
lear
n
er
s
,
it
w
il
l
b
e
v
er
y
d
if
f
icu
lt
to
ac
co
m
p
a
n
y
a
n
d
co
n
tr
o
l
th
e
ir
b
eh
av
io
r
s
.
T
o
ac
h
iev
e
r
ea
l
-
t
i
m
e
m
o
n
ito
r
in
g
o
f
lear
n
er
s
,
we
w
il
l
n
ee
d
"
s
m
ar
t"
co
m
p
o
n
e
n
t
s
to
d
ef
in
e
in
r
ea
l
t
i
m
e
th
e
lear
n
er
's
p
r
o
f
ile
an
d
p
r
ef
er
en
ce
s
f
o
r
ad
ap
tin
g
lear
n
i
n
g
to
ea
ch
m
o
m
e
n
t
o
f
t
h
e
lear
n
in
g
p
r
o
ce
s
s
to
a
v
o
id
p
r
o
b
lem
s
o
f
f
ail
u
r
e
a
n
d
d
e
m
o
tiv
a
tio
n
.
T
h
i
s
ad
ap
tatio
n
s
h
o
u
ld
b
e
b
ased
o
n
th
e
ex
p
er
ien
ce
s
o
f
o
th
er
lear
n
er
s
w
h
o
w
i
ll
b
e
g
r
o
u
p
ed
in
to
class
es
u
s
i
n
g
d
ata
m
in
in
g
tec
h
n
iq
u
es
[
1
]
,
w
h
ich
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
2
0
1
9
:
4
9
3
9
-
495
0
4940
ca
n
e
x
tr
ac
t
a
n
d
d
is
co
v
er
i
m
p
o
r
tan
t
d
ata
f
r
o
m
a
co
llec
tio
n
o
f
lar
g
e
a
m
o
u
n
ts
o
f
d
ata
to
f
a
cilitate
t
h
e
r
esear
c
h
an
d
class
i
f
ic
at
io
n
o
f
lear
n
er
s
.
I
n
t
h
is
p
ap
er
,
w
e
p
r
o
p
o
s
e
an
a
p
p
r
o
ac
h
to
an
ad
ap
tiv
e
lear
n
i
n
g
s
y
s
te
m
b
ased
o
n
th
e
Feld
er
-
Sil
v
er
m
a
n
lear
n
in
g
s
t
y
le
m
o
d
el
(
FS
L
S
M)
an
d
I
n
cr
e
m
a
n
tal
D
y
n
a
m
ic
C
ase
B
ase
R
ea
s
o
n
i
n
g
(
I
DC
B
R
)
to
f
o
llo
w
th
e
lear
n
er
i
n
d
if
f
ic
u
lt
y
i
n
r
ea
l
ti
m
e
b
y
o
f
f
er
i
n
g
h
i
m
a
p
ath
a
d
ap
ted
to
h
is
p
r
o
f
ile
an
d
th
e
d
y
n
a
m
ic
c
h
an
g
e
o
f
h
is
b
e
h
av
io
r
d
u
r
in
g
t
h
e
lear
n
i
n
g
p
r
o
ce
s
s
.
T
o
p
er
f
o
r
m
th
i
s
d
y
n
a
m
ic
tr
ac
k
i
n
g
,
w
e
u
s
ed
a
c
ascad
e
o
f
t
h
e
F
u
zz
y
C
-
Me
a
n
s
m
et
h
o
d
(
FC
M)
an
d
th
e
K
-
Nea
r
est
Nei
g
h
b
o
r
s
m
e
th
o
d
(
KNN)
in
th
e
s
ec
o
n
d
s
t
ep
o
f
th
e
D
y
n
a
m
ic
C
ase
B
ase
R
ea
s
o
n
in
g
to
p
r
o
p
o
s
e
a
p
ath
ad
a
p
ted
to
ea
ch
m
o
m
e
n
t
o
f
lear
n
in
g
b
ased
o
n
th
e
b
eh
av
io
r
o
f
o
th
er
lear
n
er
s
w
h
o
ar
e
cla
s
s
i
f
ied
a
s
h
o
m
o
g
e
n
eo
u
s
g
r
o
u
p
s
.
I
n
t
h
e
s
ec
o
n
d
s
ec
tio
n
,
w
e
p
r
ese
n
t
t
h
e
tec
h
n
iq
u
es
u
s
ed
:
th
e
in
cr
e
m
en
tal
D
y
n
a
m
ic
C
a
s
e
B
aseR
ea
s
o
n
i
n
g
A
p
p
r
o
ac
h
,
th
e
K
-
Nea
r
est
Neig
h
b
o
r
s
m
et
h
o
d
(
KNN)
an
d
th
e
F
u
zz
y
C
-
Me
a
n
s
m
et
h
o
d
(
FC
M)
.
I
n
th
e
t
h
ir
d
s
ec
tio
n
,
we
d
escr
ib
e
o
u
r
ap
p
r
o
ac
h
b
y
d
etailin
g
t
h
e
o
p
er
atio
n
an
d
th
e
d
if
f
er
en
t
s
tep
s
o
f
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
.
T
h
e
f
o
u
r
t
h
s
ec
tio
n
w
i
ll
p
r
ese
n
t
t
h
e
r
es
u
lt
s
o
f
t
h
e
e
x
p
er
i
m
e
n
t
o
f
th
e
co
m
b
i
n
atio
n
o
f
t
h
e
FC
M
m
et
h
o
d
an
d
t
h
e
KN
N
m
et
h
o
d
o
n
a
s
a
m
p
le
o
f
2
2
lear
n
er
s
u
s
i
n
g
th
e
"
ME
R
I
SE"
m
et
h
o
d
as
a
le
ar
n
in
g
m
ater
ial,
th
e
r
e
s
u
l
ts
ar
e
p
r
esen
ted
b
y
th
e
Ma
tlab
s
o
f
t
w
ar
e
a
n
d
w
e
f
i
n
is
h
w
it
h
a
co
n
cl
u
s
io
n
.
2.
M
E
T
H
O
D
O
L
O
G
I
E
S
2
.
1
.
Ca
s
e
ba
s
ed
re
a
s
o
nin
g
C
ase
B
ased
R
ea
s
o
n
in
g
(
C
B
R
)
is
a
p
r
o
b
le
m
-
s
o
l
v
i
n
g
ap
p
r
o
ac
h
t
h
at
u
s
e
s
p
ast e
x
p
er
ien
ce
s
to
s
o
lv
e
n
e
w
p
r
o
b
lem
s
[
2
]
.
A
v
er
y
i
m
p
o
r
ta
n
t
f
ea
t
u
r
e
o
f
th
e
C
B
R
is
it
s
r
e
latio
n
s
h
ip
w
i
th
lear
n
i
n
g
,
it
a
ll
o
w
s
u
p
d
ati
n
g
ca
s
es
an
d
lear
n
in
g
n
e
w
ca
s
e
s
.
So
lv
i
n
g
a
p
r
o
b
lem
u
s
i
n
g
t
h
e
C
ase
B
ased
R
ea
s
o
n
in
g
ap
p
r
o
ac
h
ca
n
b
e
d
o
n
e
th
r
o
u
g
h
a
t
y
p
ical
c
y
cle
w
i
th
a
s
et
o
f
s
t
ep
s
.
T
h
ese
s
tep
s
ar
e
m
o
r
e
d
etailed
in
[
3
-
5
]
.
T
h
e
tr
a
d
itio
n
al
c
y
cle
o
f
th
e
C
B
R
in
cl
u
d
es t
h
e
f
o
llo
w
i
n
g
s
tep
s
:
E
lab
o
r
atio
n
,
R
etr
iev
e,
R
e
u
s
e,
R
ev
i
s
e
a
n
d
R
e
t
ain
.
W
h
er
ea
s
,
i
n
t
h
e
D
y
n
a
m
ic
C
ase
B
ased
R
ea
s
o
n
i
n
g
(
DC
B
R
)
c
y
cle,
th
e
tar
g
e
t
ca
s
e
(
t
h
e
p
r
o
b
le
m
to
s
o
l
v
e)
is
p
r
ese
n
ted
b
y
d
y
n
a
m
ic
d
escr
ip
to
r
s
th
at
c
h
an
g
e
o
v
er
ti
m
e,
a
n
e
w
s
tar
C
B
R
c
y
cle
i
s
p
r
o
p
o
s
ed
b
y
[
4
,
5
]
in
Fi
g
u
r
e
1
,
t
h
is
is
th
e
I
n
cr
e
m
e
n
tal
D
y
n
a
m
ic
C
a
s
e
B
ased
R
ea
s
o
n
i
n
g
(
I
D
C
B
R
)
.
T
h
is
n
e
w
c
y
cle
h
as r
es
u
lted
i
n
c
h
an
g
e
s
i
n
t
h
e
o
r
d
er
an
d
co
n
ten
t o
f
th
e
tr
ad
itio
n
al
C
B
R
c
y
cle
(
s
o
m
e
s
tep
s
ca
n
b
e
r
ep
ea
ted
s
ev
er
al
ti
m
es).
Fig
u
r
e
1
.
I
DC
B
R
c
y
cle
[
4
,
5
]
2
.
2
.
Cla
s
s
if
ica
t
io
n w
it
h
k
-
nea
re
s
t
neig
hb
o
rs
T
h
e
K
-
Nea
r
est
Neig
h
b
o
r
s
(
KNN)
alg
o
r
ith
m
[
6
]
is
n
o
n
-
p
ar
a
m
etr
ic
an
d
s
u
p
er
v
i
s
ed
m
et
h
o
d
o
f
class
i
f
icatio
n
[
7
]
an
d
in
tr
o
d
u
ce
d
in
[
8
]
,
I
t
ca
n
b
e
u
s
ed
b
o
th
f
o
r
class
i
f
icatio
n
a
n
d
p
r
ed
ictio
n
.
I
t
is
b
as
ed
o
n
a
s
i
m
p
le
an
d
in
tu
i
tiv
e
p
r
in
cip
l
e
o
f
g
r
o
u
p
in
g
d
ata
ac
co
r
d
in
g
to
th
eir
n
eig
h
b
o
r
h
o
o
d
.
T
h
e
p
u
r
p
o
s
e
o
f
th
is
alg
o
r
ith
m
is
to
cla
s
s
i
f
y
n
e
w
d
ata
b
ased
o
n
attr
ib
u
tes
an
d
d
at
a
s
a
m
p
les.
E
ac
h
d
ata
is
ass
i
g
n
ed
to
th
e
class
m
o
s
t
r
ep
r
esen
ted
a
m
o
n
g
its
k
n
ea
r
e
s
t n
ei
g
h
b
o
r
s
[
9
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
Hyb
r
id
a
p
p
r
o
a
c
h
o
f th
e
f
u
z
z
y
C
-
mea
n
s
a
n
d
th
e
K
-
n
e
a
r
est n
eig
h
b
o
r
s
meth
o
d
s
d
u
r
in
g
.
.
.
(
E
l
Gh
o
u
ch
N
ih
a
d
)
4941
T
h
e
K
-
Nea
r
est Ne
i
g
h
b
o
r
s
al
g
o
r
ith
m
i
s
ess
e
n
tial
l
y
b
ased
o
n
t
w
o
m
ain
p
r
i
n
cip
les:
a.
A
n
u
m
b
er
o
f
n
ea
r
e
s
t n
ei
g
h
b
o
r
s
(
K)
to
u
s
e
[
1
0
]
;
b.
A
m
etr
ic
to
m
ea
s
u
r
e
n
ea
r
est
n
eig
h
b
o
r
s
[
1
1
]
.
T
h
is
m
ea
s
u
r
e
m
en
t
is
n
ec
es
s
ar
y
to
d
eter
m
i
n
e
th
e
d
is
ta
n
ce
s
,
it in
f
l
u
en
ce
s
o
n
th
e
r
es
u
lt o
f
th
e
class
i
f
icatio
n
an
d
th
e
q
u
alit
y
o
f
th
e
p
r
ed
ictio
n
s
.
T
h
e
K
-
Nea
r
est Ne
i
g
h
b
o
r
s
al
g
o
r
ith
m
:
a.
L
et
k
b
e
th
e
n
u
m
b
er
o
f
n
ea
r
est
n
eig
h
b
o
r
s
an
d
D
th
e
s
et
o
f
tr
a
in
i
n
g
d
ata
(
y
j
).
b.
Fo
r
ea
ch
n
e
w
o
b
s
er
v
atio
n
x
i,
c
alcu
late
d
(
x
i
,
y
j
)
u
s
i
n
g
a
m
ea
s
u
r
e
o
f
d
is
t
a
n
ce
f
o
r
ea
ch
d
ata
y
j
o
f
D.
c.
Select
th
e
k
n
ea
r
es
t d
ata
(
y
j
)
o
f
th
e
n
e
w
o
b
s
er
v
atio
n
x
i.
d.
C
las
s
i
f
y
t
h
e
n
e
w
o
b
s
er
v
atio
n
x
i a
cc
o
r
d
in
g
to
t
h
e
m
aj
o
r
it
y
cl
ass
a
m
o
n
g
its
n
eig
h
b
o
r
s
.
A
lt
h
o
u
g
h
th
e
KNN
m
et
h
o
d
is
ea
s
y
to
i
m
p
le
m
e
n
t,
it
h
as
s
o
m
e
li
m
itatio
n
s
s
u
ch
as
:
th
e
h
i
gh
co
m
p
u
tatio
n
al
co
m
p
le
x
it
y
to
f
i
n
d
t
h
e
k
n
ea
r
est
n
ei
g
h
b
o
r
s
a
m
p
les,
t
h
e
co
m
p
u
ta
tio
n
ti
m
e
to
co
m
p
u
te
th
e
s
i
m
ilar
ities
[
1
2
]
.
B
u
t
th
er
e
ar
e
h
e
u
r
is
tic
s
to
r
ed
u
ce
t
h
e
s
et
o
f
d
ata
to
clas
s
i
f
y
,
to
in
cr
ea
s
e
th
e
s
p
ee
d
o
f
class
i
f
icatio
n
[
1
3
,
1
4
]
an
d
to
ac
ce
ler
ate
th
e
K
-
NN
al
g
o
r
ith
m
b
a
s
ed
o
n
clu
s
ter
i
n
g
a
n
d
attr
ib
u
te
f
ilter
i
n
g
[
1
5
]
.
T
h
er
e
is
s
o
m
e
w
o
r
k
i
n
te
g
r
atin
g
th
e
KNN
m
et
h
o
d
in
t
h
e
C
B
R
c
y
cle,
w
e
q
u
o
te
th
e
w
o
r
k
o
f
[
1
6
]
,
w
h
ich
s
h
o
w
ed
th
at
t
h
e
KNN
al
g
o
r
ith
m
is
s
u
i
t
ab
le
f
o
r
u
s
e
in
t
h
e
C
B
R
ap
p
r
o
ac
h
.
2
.
3
.
F
uzzy
c
-
m
ea
ns
T
h
e
Fu
zz
y
C
-
Me
a
n
s
(
C
M
F)
is
a
f
u
zz
y
cl
u
s
ter
in
g
tech
n
i
q
u
e
[
1
7
]
th
at
g
en
er
alize
s
th
e
C
-
Me
a
n
s
tech
n
iq
u
e,
d
er
iv
ed
f
r
o
m
th
e
K
-
Me
a
n
s
alg
o
r
it
h
m
.
T
h
e
Fu
zz
y
C
-
Me
a
n
s
alg
o
r
ith
m
allo
w
s
ele
m
en
ts
to
b
elo
n
g
to
s
ev
er
al
clu
s
ter
s
s
i
m
u
lta
n
eo
u
s
l
y
[
1
8
]
,
it
is
b
ased
o
n
th
e
o
p
t
i
m
izatio
n
o
f
a
q
u
ad
r
atic
class
if
ica
tio
n
cr
iter
io
n
w
h
er
e
ea
ch
clas
s
is
r
ep
r
esen
te
d
b
y
its
ce
n
ter
o
f
g
r
av
it
y
[
1
9
,
2
0
]
.
T
h
is
iter
ativ
e
al
g
o
r
ith
m
as
s
ig
n
s
a
m
e
m
b
er
s
h
ip
o
f
a
n
o
b
j
ec
t
t
o
a
clu
s
ter
,
b
ased
o
n
th
e
s
i
m
il
ar
it
y
o
f
a
n
o
b
j
ec
t
w
it
h
a
p
ar
ticu
lar
clu
s
ter
to
all
o
th
e
r
clu
s
ter
s
.
F
C
M
m
i
n
i
m
izes t
h
e
f
o
llo
w
i
n
g
o
b
j
ec
tiv
e
f
u
n
ctio
n
[
2
1
]
:
∑
∑
|
−
|
2
=
1
=
1
w
it
h
a.
m
>
1
is
a
p
ar
a
m
eter
co
n
tr
o
llin
g
th
e
d
eg
r
ee
o
f
f
u
zz
i
n
ess
(
u
s
u
all
y
m
=
2
)
;
b.
c
j
is
th
e
ce
n
ter
o
f
a
clu
s
ter
;
c.
x
i
,
d
en
o
tes t
h
e
ith
ele
m
e
n
t o
f
t
h
e
m
ea
s
u
r
ed
d
ata
d.
u
ij
r
ep
r
esen
t
s
t
h
e
d
eg
r
ee
o
f
m
e
m
b
er
s
h
ip
o
f
an
ele
m
en
t
x
i
i
n
t
h
e
j
th
clu
s
ter
,
th
e
lar
g
er
u
i
j
is
th
e
s
tr
o
n
g
er
th
e
clu
s
ter
m
e
m
b
er
s
h
ip
(
[
0
,
1
]
an
d
∑
=
1
=1
)
.
T
h
e
m
ai
n
s
tep
s
o
f
th
e
Fu
zz
y
C
-
Me
a
n
s
al
g
o
r
ith
m
ar
e:
a.
C
h
o
o
s
e
t
h
e
n
u
m
b
er
o
f
cl
u
s
ter
s
[
2
2
,
23]
;
b.
I
n
itialize
t
h
e
m
e
m
b
er
s
h
ip
m
at
r
ix
u
ij
;
c.
C
alcu
late
th
e
ce
n
tr
o
id
s
c
j
:
=
(
∑
(
)
.
)
(
∑
(
)
)
⁄
d.
Re
-
ad
j
u
s
t
t
h
e
m
e
m
b
er
s
h
ip
m
atr
ix
ac
co
r
d
in
g
to
th
e
p
o
s
itio
n
o
f
t
h
e
ce
n
tr
o
id
s
:
=
1
(
∑
(
⁄
)
(
2
(
−
1
)
⁄
)
=
1
,
)
⁄
w
it
h
:
=
|
−
|
e.
I
f
‖
(
+
1
)
−
(
)
‖
<
ε
(
th
r
es
h
o
ld
r
ep
r
esen
tin
g
th
e
c
o
n
v
er
g
e
n
ce
er
r
o
r
)
,
th
en
th
e
al
g
o
r
ith
m
s
to
p
s
,
o
th
er
w
is
e
th
e
r
etu
r
n
to
s
tep
b
.
T
h
e
Fu
zz
y
C
-
Me
an
s
m
et
h
o
d
h
as
a
h
y
b
r
id
ch
ar
ac
ter
(
t
h
e
co
n
ce
p
t
o
f
ce
n
ter
o
f
g
r
av
i
t
y
an
d
th
e
F
u
zz
y
co
n
ce
p
t)
,
m
ak
e
s
it
s
i
m
p
le
a
n
d
f
as
t.
T
h
e
FC
M
r
eq
u
ir
es
i
n
p
u
t
p
ar
am
e
ter
s
,
an
d
t
h
at
h
e
p
ar
tit
io
n
m
a
tr
ix
is
f
u
zz
y
,
w
h
ic
h
n
ee
d
s
to
b
e
in
it
ialized
in
an
ap
p
r
o
p
r
iate
m
a
n
n
er
.
3.
DE
SCR
I
P
T
I
O
N
O
F
O
UR
AP
P
RO
ACH
Ou
r
ap
p
r
o
ac
h
is
to
p
r
o
v
id
e
a
p
er
s
o
n
alize
d
an
d
i
n
d
iv
id
u
aliz
e
d
f
o
llo
w
-
u
p
o
f
t
h
e
lear
n
er
in
r
ea
l
ti
m
e,
ac
co
r
d
in
g
to
h
is
FS
L
SM
lear
n
in
g
s
t
y
le,
h
i
s
o
b
s
er
v
ed
lear
n
in
g
tr
ac
es
a
n
d
th
e
p
ast
s
u
cc
e
s
s
f
u
l
ex
p
er
ien
ce
s
o
f
o
th
er
lear
n
er
s
.
Si
n
ce
ea
c
h
le
ar
n
er
's
lear
n
in
g
p
r
o
ce
s
s
ev
o
l
v
es
o
v
er
ti
m
e,
it
r
eq
u
ir
es
th
e
u
s
e
o
f
in
te
lli
g
en
t
tech
n
iq
u
es
to
au
to
m
atica
ll
y
ad
ap
t
t
o
d
y
n
a
m
ic
ch
a
n
g
es
in
th
e
lear
n
er
'
s
b
eh
a
v
io
r
in
r
ea
l
ti
m
e
d
u
r
in
g
th
e
lear
n
i
n
g
p
r
o
ce
s
s
.
Ou
r
ap
p
r
o
ac
h
allo
w
s
:
a.
Dete
ctin
g
t
h
e
lear
n
er
p
r
o
f
ile
u
s
in
g
t
h
e
Feld
er
-
S
ilv
er
m
a
n
lear
n
in
g
s
t
y
le
m
o
d
el,
cr
ea
tin
g
p
r
o
f
ile
clas
s
es
a
n
d
p
r
o
v
i
d
in
g
a
n
in
i
tial le
ar
n
i
n
g
p
ath
f
o
r
ea
ch
lear
n
er
to
s
tar
t le
ar
n
in
g
.
b.
Fo
llo
w
i
n
g
th
e
lear
n
er
w
h
o
h
a
s
en
co
u
n
ter
ed
lear
n
in
g
p
r
o
b
le
m
s
i
n
r
ea
l
ti
m
e
b
y
u
s
in
g
th
e
I
DC
B
R
to
o
f
f
er
a
p
er
s
o
n
alize
d
p
ath
ac
co
r
d
in
g
t
o
th
e
d
y
n
a
m
ic
ch
a
n
g
e
o
f
h
i
s
b
eh
av
io
r
.
T
h
is
ap
p
r
o
ac
h
is
tr
i
g
g
er
ed
w
it
h
ea
ch
ch
an
g
e
i
n
t
h
e
lear
n
i
n
g
p
r
o
ce
s
s
b
y
o
b
s
er
v
i
n
g
a
n
d
a
n
al
y
zin
g
th
e
lear
n
i
n
g
tr
ac
es
le
f
t
in
t
h
e
s
y
s
te
m
.
T
h
e
I
DC
B
R
in
te
g
r
ates
in
th
e
s
ec
o
n
d
s
tep
a
co
m
b
i
n
atio
n
o
f
t
w
o
m
et
h
o
d
s
o
f
m
ac
h
in
e
lea
r
n
in
g
,
t
h
e
F
C
M
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
2
0
1
9
:
4
9
3
9
-
495
0
4942
m
et
h
o
d
to
g
r
o
u
p
lear
n
er
s
in
to
h
o
m
o
g
e
n
eo
u
s
a
n
d
s
i
m
i
lar
class
es
i
n
o
r
d
er
to
f
ac
ilit
at
e
th
e
s
ea
r
ch
o
f
th
e
clo
s
est lea
r
n
er
s
t
h
r
o
u
g
h
t
h
e
KNN
m
et
h
o
d
.
Sch
e
m
atica
ll
y
,
w
e
ca
n
p
r
ese
n
t
o
u
r
ap
p
r
o
a
ch
as f
o
llo
w
s
r
e
f
er
Fig
u
r
e
2
.
Fig
u
r
e
2
.
Diag
r
a
m
o
f
o
u
r
ap
p
r
o
ac
h
3
.
1
.
P
re
li
m
ina
ry
cla
s
s
if
i
ca
t
io
n o
f
lea
rner
pro
f
iles
I
n
o
u
r
lear
n
i
n
g
s
y
s
te
m
,
w
e
u
s
ed
th
e
Feld
er
-
Sil
v
er
m
a
n
L
ea
r
n
in
g
St
y
le
Mo
d
el
(
FS
L
SM)
[
2
4
]
to
d
etec
t
th
e
lear
n
in
g
s
t
y
le
o
f
ea
ch
lear
n
er
.
T
h
is
m
o
d
el
clas
s
i
f
ies
t
h
e
lear
n
er
in
to
f
o
u
r
d
i
m
e
n
s
io
n
s
:
"
Sen
s
in
g
/
I
n
tu
i
tiv
e"
(
p
er
ce
p
tio
n
)
,
"
Vis
u
al
/
Ver
b
al"
(
in
p
u
t)
,
"
A
ctiv
e
/
r
ef
l
ec
tiv
e"
(
p
r
o
ce
s
s
)
an
d
"
Seq
u
en
t
ial
/
Glo
b
al
"
(
co
m
p
r
eh
e
n
s
io
n
)
,
b
y
p
r
o
v
id
in
g
a
test
q
u
e
s
tio
n
n
air
e
to
h
i
m
.
W
e
ar
e
in
ter
ested
i
n
t
w
o
d
i
m
en
s
io
n
s
o
f
th
e
FS
L
SM
Mo
d
el:
"
Sen
s
in
g
/
I
n
t
u
iti
v
e"
an
d
"
Vis
u
al
/
Ver
b
al"
.
T
h
e
ch
o
ice
o
f
t
h
e
s
e
t
w
o
d
i
m
en
s
io
n
s
is
d
u
e
to
t
h
e
f
ac
t
t
h
at
o
u
r
s
y
s
te
m
d
o
es
n
o
t
allo
w
i
n
ter
ac
tio
n
s
b
et
w
ee
n
lear
n
er
s
(
A
cti
v
e
/
r
e
f
lectiv
e)
an
d
co
n
s
id
er
s
t
h
at
f
r
e
ed
o
m
o
f
n
a
v
i
g
atio
n
i
s
i
m
p
l
ici
tl
y
i
n
cl
u
d
ed
in
o
u
r
s
y
s
te
m
(
Seq
u
e
n
tia
l
/
Glo
b
al)
.
T
h
er
ef
o
r
e,
th
e
lear
n
in
g
s
t
y
le
o
f
ea
ch
lear
n
er
is
p
r
esen
ted
b
y
th
e
"
Sen
s
i
n
g
/
I
n
tu
i
tiv
e"
d
i
m
en
s
io
n
w
h
ich
i
n
d
icate
s
th
e
p
r
ef
er
r
ed
lear
n
in
g
r
eso
u
r
ce
s
f
o
r
lear
n
er
s
an
d
th
e
"
Vis
u
al
/
Ver
b
al"
d
i
m
en
s
io
n
w
h
ic
h
i
n
d
icate
s
t
h
e
f
o
r
m
at
s
o
f
t
h
e
p
r
ef
er
r
ed
p
e
d
ag
o
g
ical
o
b
j
ec
ts
a
m
o
n
g
lear
n
er
s
.
A
cc
o
r
d
in
g
to
th
e
r
es
u
lt
s
o
b
tai
n
ed
f
r
o
m
th
e
FS
L
SM
test
,
th
e
lear
n
er
is
cla
s
s
i
f
ied
ac
co
r
d
in
g
to
4
g
r
o
u
p
s
o
f
p
r
o
f
iles
(
Se
n
s
i
n
g
/
Vis
u
a
l,
Sen
s
i
n
g
/ V
er
b
al,
I
n
t
u
i
tiv
e
/ V
i
s
u
al
a
n
d
I
n
t
u
iti
v
e
/ V
e
r
b
al)
.
3
.
2
.
P
ro
po
s
a
l o
f
a
n initia
l le
a
rning
pa
t
h
Ou
r
s
y
s
te
m
p
r
o
p
o
s
es
in
i
tial
l
ea
r
n
in
g
p
at
h
s
w
h
ic
h
ar
e
co
n
s
titu
ted
b
y
a
s
er
ies
o
f
lear
n
in
g
o
b
j
ec
ts
.
T
h
ese
p
ath
s
ar
e
co
n
s
tr
u
cted
th
r
o
u
g
h
t
h
e
co
r
r
esp
o
n
d
en
ce
b
et
w
ee
n
t
h
e
FS
L
S
M
lear
n
i
n
g
s
t
y
le
o
f
ea
c
h
lear
n
er
an
d
th
e
m
e
tad
ata
d
escr
ib
in
g
th
e
lear
n
i
n
g
o
b
j
ec
ts
[
2
5
]
.
T
h
e
T
ab
le
1
s
h
o
w
s
th
e
co
r
r
esp
o
n
d
en
ce
b
et
w
ee
n
th
e
FS
L
SM
lear
n
i
n
g
s
t
y
le
an
d
th
e
lear
n
i
n
g
o
b
j
ec
ts
.
T
ab
le
1
.
C
o
r
r
esp
o
n
d
en
ce
b
et
w
ee
n
FS
L
S
M
lear
n
i
n
g
s
t
y
le
an
d
lear
n
in
g
o
b
j
ec
t m
etad
ata
P
r
o
f
i
l
e
s
I
n
i
t
i
a
l
l
e
a
n
i
n
g
p
a
t
h
S
e
n
si
n
g
/
V
i
s
u
a
l
Ex
a
mp
l
e
,
e
x
e
r
c
i
se
a
n
d
q
u
i
z
i
n
t
h
e
f
o
r
m o
f
a
p
i
c
t
u
r
e
,
a
v
i
d
e
o
S
e
n
si
n
g
/
V
e
r
b
a
l
Ex
a
mp
l
e
,
e
x
e
r
c
i
se
a
n
d
q
u
i
z
i
n
t
h
e
f
o
r
m o
f
a
t
e
x
t
,
a
n
a
u
d
i
o
I
n
t
u
i
t
i
v
e
/
V
i
su
a
l
N
o
t
i
o
n
,
d
e
f
i
n
i
t
i
o
n
,
a
l
g
o
r
i
t
h
m o
f
a
p
i
c
t
u
r
e
,
a
v
i
d
e
o
I
n
t
u
i
t
i
v
e
/
V
e
r
b
a
l
N
o
t
i
o
n
,
d
e
f
i
n
i
t
i
o
n
,
a
l
g
o
r
i
t
h
m i
n
t
h
e
f
o
r
m o
f
a
t
e
x
t
,
a
n
a
u
d
i
o
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
Hyb
r
id
a
p
p
r
o
a
c
h
o
f th
e
f
u
z
z
y
C
-
mea
n
s
a
n
d
th
e
K
-
n
e
a
r
est n
eig
h
b
o
r
s
meth
o
d
s
d
u
r
in
g
.
.
.
(
E
l
Gh
o
u
ch
N
ih
a
d
)
4943
3
.
3
.
B
eg
inn
ing
o
f
lea
rning
Af
ter
d
etec
ti
n
g
t
h
e
lear
n
i
n
g
s
t
y
le
o
f
t
h
e
lear
n
er
th
at
o
f
f
er
s
h
i
m
a
lear
n
in
g
p
ath
ac
co
r
d
in
g
to
h
is
s
t
y
le.
T
h
e
lear
n
in
g
p
r
o
ce
s
s
o
f
ea
c
h
l
ea
r
n
er
tak
es t
w
o
s
ce
n
ar
io
s
:
a.
No
r
m
a
l:
t
h
e
s
y
s
te
m
g
o
es
d
ir
ec
tl
y
to
th
e
las
t
s
tep
o
f
D
y
n
a
m
ic
C
ase
B
ased
R
ea
s
o
n
i
n
g
,
w
h
ic
h
r
ec
o
r
d
s
lear
n
in
g
s
t
y
le,
lear
n
i
n
g
p
at
h
,
an
d
i
n
ter
ac
tio
n
tr
ac
es
o
f
ea
ch
lear
n
er
a
s
a
n
e
w
ca
s
e
(
a
n
e
w
s
u
cc
e
s
s
f
u
l
ex
p
er
ien
ce
)
in
t
h
e
b
ase
o
f
ca
s
e
s
(
Fig
u
r
e
2
g
r
ee
n
li
n
e)
;
b.
A
b
n
o
r
m
al:
W
h
e
n
t
h
e
s
y
s
te
m
d
etec
ts
an
an
o
m
al
y
o
r
p
r
o
b
lem
d
u
r
i
n
g
t
h
e
lear
n
i
n
g
p
r
o
ce
s
s
,
D
y
n
a
m
i
c
C
ase
B
ased
R
ea
s
o
n
i
n
g
i
s
tr
ig
g
er
ed
to
p
r
o
v
id
e
a
r
ea
l
-
ti
m
e
co
ac
h
in
g
(
Fig
u
r
e
2
r
ed
lin
e)
.
I
n
t
h
e
s
ec
o
n
d
s
i
tu
atio
n
,
t
h
e
DC
B
R
ad
ap
ts
th
e
lear
n
i
n
g
p
r
o
ce
s
s
ac
co
r
d
in
g
to
t
h
e
p
r
o
f
i
le
o
f
ea
c
h
lear
n
er
th
r
o
u
g
h
:
a.
T
h
e
o
b
s
er
v
atio
n
o
f
th
e
lear
n
in
g
p
r
o
ce
s
s
o
f
th
e
lear
n
er
(
h
is
le
ar
n
in
g
p
ath
)
;
b.
T
h
e
co
m
p
ar
is
o
n
o
f
t
h
e
b
eh
a
v
io
r
o
f
th
e
lear
n
er
in
d
if
f
ic
u
lt
y
at
ea
ch
m
o
m
en
t
t
i
w
it
h
t
h
e
b
eh
av
io
r
s
o
f
th
e
o
th
er
lear
n
er
s
r
ea
lized
d
u
r
i
n
g
t
h
e
p
r
ev
io
u
s
in
s
ta
n
ts
(
f
r
o
m
t
0
to
t
i
-
1
).
3
.
4
.
E
la
bo
ra
t
io
n o
f
t
he
lea
rning
pro
ble
m
3
.
4
.
1
.
G
ener
a
t
io
n o
f
t
he
lea
rning
pro
ble
m
Data
co
llected
f
r
o
m
t
h
e
lear
n
in
g
p
r
o
ce
s
s
i
s
p
r
o
ce
s
s
ed
to
ex
tr
ac
t
r
elev
a
n
t
i
n
f
o
r
m
atio
n
t
h
at
w
i
ll
b
e
m
o
d
eled
as
ca
s
e
s
.
T
h
ese
ca
s
es
ch
ar
ac
ter
ize
lear
n
er
’
s
b
eh
av
io
r
s
(
lear
n
in
g
p
ath
s
)
th
r
o
u
g
h
th
e
tr
ac
es
s
a
v
ed
in
th
e
b
ase
o
f
k
n
o
w
led
g
e
(
b
ase
o
f
ca
s
es).
T
h
e
o
b
s
er
v
ed
lear
n
in
g
p
ath
o
f
ea
ch
lear
n
er
is
co
m
p
o
s
ed
o
f
a
s
er
ies
o
f
lear
n
i
n
g
o
b
j
ec
ts
n
u
m
b
er
ed
ac
co
r
d
in
g
to
th
e
in
d
e
x
i (
w
it
h
i =
{0
.
.
.
Nb
r
_
Ob
j
})
.
E
ac
h
lear
n
in
g
o
b
j
ec
t c
o
n
s
u
lted
at
ea
c
h
i
n
s
ta
n
t t
i r
ep
r
esen
t
s
a
tr
ac
e
at
ti
m
e
ti
w
h
ich
co
n
tai
n
s
i
n
d
icato
r
s
th
at
w
e
co
n
s
id
er
ed
r
elev
an
t:
a.
t
i
: th
e
ep
is
o
d
e
ti c
o
r
r
esp
o
n
d
s
to
a
co
n
s
u
ltatio
n
o
f
a
lear
n
i
n
g
o
b
j
ec
t n
u
m
b
er
ed
i;
b.
C
r
s
: c
h
o
s
en
co
u
r
s
e;
c.
VSC
r
s
: le
ar
n
i
n
g
o
b
j
ec
t;
d.
DtVSC
r
s
: d
ate
o
f
th
e
v
is
it o
f
t
h
e
lear
n
i
n
g
o
b
j
ec
t;
e.
Nb
r
Vst
VS
C
r
: n
u
m
b
er
o
f
v
is
it
s
to
th
e
lear
n
i
n
g
o
b
j
ec
t;
f.
Dv
VS
C
r
: d
u
r
atio
n
o
f
th
e
v
is
it
o
f
th
e
lear
n
in
g
o
b
j
ec
t
;
g.
R
VS
C
r
s
: r
eso
u
r
ce
o
f
t
h
e
lear
n
in
g
o
b
j
ec
t;
h.
FVSC
r
s
: n
at
u
r
e
o
f
t
h
e
lear
n
i
n
g
o
b
j
ec
t.
T
h
e
lear
n
in
g
tr
ac
es
ar
e
p
r
esen
ted
b
y
a
v
ec
to
r
E
p
is
o
d
e
(ti,
j)
w
h
ich
d
escr
ib
es
a
tr
ac
e
o
f
th
e
lear
n
er
j
at
ti
m
e
t
i
.
(
,
)
=
(
)
(
1
)
I
n
o
u
r
ap
p
r
o
ac
h
,
t
h
e
lear
n
i
n
g
p
ath
(
tar
g
et
ca
s
e
/
s
o
u
r
ce
ca
s
e
)
is
p
r
ese
n
ted
i
n
a
n
o
b
j
ec
t
r
ep
r
esen
tatio
n
f
o
r
m
at
(
Fig
u
r
e
3
)
t
h
at
ad
ap
ts
t
o
th
e
d
y
n
a
m
ic
s
id
e
o
f
ad
ap
tiv
e
lear
n
i
n
g
s
y
s
te
m
s
.
I
t i
s
m
o
d
eled
b
y
an
o
b
j
ec
t th
at
is
ch
ar
ac
ter
ized
b
y
a
"
T
r
ac
es
"
o
b
j
ec
t
v
ec
to
r
an
d
a
"
Valid
atio
n
"
attr
ib
u
tes
i
n
d
icatin
g
t
h
e
v
alid
atio
n
o
f
th
is
lear
n
in
g
p
ath
.
Fig
u
r
e
3
.
Ob
j
ec
t
r
ep
r
esen
tatio
n
o
f
a
lear
n
i
n
g
p
ath
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
2
0
1
9
:
4
9
3
9
-
495
0
4944
3
.
4
.
2
.
Descript
io
n o
f
t
he
lea
rning
p
ro
ble
m
T
h
e
p
u
r
p
o
s
e
o
f
th
is
s
tep
is
t
h
e
r
ec
o
g
n
itio
n
o
f
a
n
e
w
lear
n
i
n
g
p
ath
,
w
h
ic
h
is
w
h
y
o
u
r
s
y
s
te
m
m
u
s
t
a.
Dete
ct
th
e
i
n
s
ta
n
t t
p
,
i
n
cl
u
d
in
g
:
1.
T
h
e
lear
n
er
d
o
es n
o
t f
o
llo
w
t
h
e
p
r
o
p
o
s
ed
p
ath
;
2.
T
h
e
lear
n
er
is
b
lo
ck
ed
at
th
e
lev
el
o
f
a
lear
n
i
n
g
o
b
j
ec
t;
3.
T
h
e
lear
n
er
s
co
r
ed
n
eg
ativ
el
y
d
u
r
in
g
th
e
as
s
es
s
m
en
t.
b.
Descr
ib
e
th
e
A
PC
lear
n
er
(
tar
g
et
ca
s
e)
b
y
co
llec
tin
g
th
e
tr
a
ce
s
t
h
at
ar
e
r
ep
r
ese
n
ted
as
a
n
e
w
,
i
n
v
alid
ated
lear
n
in
g
p
at
h
(
a
n
e
w
ca
s
e
t
h
a
t
n
ee
d
s
to
b
e
s
o
l
v
ed
)
,
th
r
o
u
g
h
t
h
e
cr
ea
tio
n
o
f
th
e
"
E
pis
o
d
e
(ti,
j)
"
v
ec
to
r
s
at
ea
ch
in
s
ta
n
t t
i
(
i f
r
o
m
0
to
p
-
1
)
.
3
.
5
.
G
ro
up
i
ng
us
ing
F
CM
T
o
s
o
lv
e
th
e
KNN
alg
o
r
ith
m
p
r
o
b
lem
s
(
in
ter
m
s
o
f
clas
s
if
icatio
n
ti
m
e
an
d
s
a
m
p
le
s
iz
e)
an
d
to
f
ac
ilit
ate
t
h
e
s
ea
r
c
h
f
o
r
s
i
m
il
ar
ca
n
d
id
a
te
lear
n
er
s
,
w
e
u
s
e
d
th
e
FC
M
m
eth
o
d
to
g
r
o
u
p
lear
n
er
s
b
y
s
i
m
ilar
d
eg
r
ee
.
W
e
u
s
e
t
h
is
m
e
th
o
d
t
o
cr
ea
te
clu
s
ter
s
w
h
o
s
e
lear
n
er
s
h
a
v
e
s
i
m
ilar
b
e
h
av
io
r
s
b
ased
o
n
t
h
e
lear
n
i
n
g
tr
ac
es p
r
esen
ted
as
E
p
is
o
de
(ti,
j
)
at
ea
ch
m
o
m
en
t t
i
o
f
th
e
lear
n
in
g
p
r
o
ce
s
s
.
T
h
e
p
u
r
p
o
s
e
o
f
th
is
s
tep
i
s
t
o
id
en
tify
t
h
e
CL
A
PS
clu
s
ter
clo
s
est
to
th
e
lear
n
er
in
d
i
f
f
icu
lt
y
A
PC
.
T
h
is
clu
s
ter
co
n
tai
n
s
a
ll
lear
n
er
s
w
i
th
s
i
m
i
lar
b
eh
a
v
io
r
s
t
o
th
e
lear
n
er
A
PC
(
ev
e
n
if
t
h
e
y
h
a
v
e
d
if
f
er
en
t
p
r
o
f
iles
)
.
I
n
t
h
is
s
tep
,
w
e
r
et
r
iev
e
t
h
e
I
Ds
o
f
t
h
e
lear
n
e
r
s
b
elo
n
g
i
n
g
to
th
e
CL
A
PS
clu
s
ter
as
a
V_
CL
A
PS
v
ec
to
r
.
3
.
6
.
Cla
s
s
if
ica
t
io
n
us
ing
K
NN
T
h
e
p
r
ev
io
u
s
s
tep
allo
w
s
li
m
i
tin
g
th
e
n
u
m
b
er
o
f
lear
n
er
s
to
m
ak
e
t
h
e
s
ea
r
c
h
o
f
t
h
e
n
ea
r
e
s
t
lear
n
er
s
ea
s
y
a
n
d
f
ast.
I
n
o
r
d
er
to
ca
r
r
y
o
u
t
t
h
e
class
i
f
ica
tio
n
u
s
i
n
g
th
e
KNN
m
et
h
o
d
,
w
e
w
ill
e
x
ec
u
te
th
e
f
o
llo
w
i
n
g
s
tep
s
:
a.
C
r
ea
te
t
h
e
Co
ns
ulta
t
io
n_
E
pi
s
o
de
(ti)
m
atr
ix
f
o
r
ea
c
h
m
o
m
en
t
t
i
(
i
f
r
o
m
0
to
p
-
1
)
f
r
o
m
th
e
M_
C
L
A
P
S
m
atr
i
x
cr
ea
ted
in
th
e
p
r
ev
io
u
s
s
tep
,
b
ased
o
n
eq
u
atio
n
(
1
)
:
_
(
)
=
{
∑
(
,
)
_
=
1
,
=
0
∑
∑
(
,
)
_
=
1
−
1
=
0
,
≥
1
(
2
)
b.
C
alcu
late
th
e
s
i
m
i
lar
it
y
"
d
"
b
e
t
w
ee
n
(
,
)
an
d
ea
ch
lin
e
o
f
th
e
Co
ns
ulta
t
io
n_
E
pi
s
o
de
(ti)
m
a
tr
ix
f
o
r
ea
ch
m
o
m
en
t t
i
(
i f
r
o
m
0
to
p
-
1
)
.
c.
Sav
e
th
e
d
is
ta
n
ce
s
d
0
.
.
.
d
p
-
1
in
a
tab
le
D
ti
an
d
s
o
r
t
th
is
tab
le
in
in
cr
ea
s
i
n
g
o
r
d
er
f
o
r
ea
ch
m
o
m
e
n
t
t
i
(
i
f
r
o
m
0
to
p
-
1
)
.
d.
R
etr
iev
e
t
h
e
lear
n
er
s
ac
co
r
d
in
g
to
th
e
d
is
ta
n
ce
tab
le
s
o
r
ted
f
o
r
ea
ch
m
o
m
e
n
t t
i
(
i f
r
o
m
0
to
p
b
-
1
)
.
e.
Get
th
e
f
ir
s
t
k
lear
n
er
s
f
o
r
ea
ch
m
o
m
en
t t
i
(
i f
r
o
m
0
to
p
-
1
)
.
f.
C
alcu
late
∑
−
1
=
0
g.
Fin
d
t
h
e
A
PS
lear
n
er
w
h
o
h
as
a
m
in
i
m
u
m
d
is
ta
n
ce
m
in
∑
−
1
=
0
h.
Ass
i
g
n
A
PS
b
eh
a
v
io
r
to
A
PC
an
d
u
p
d
ate
th
e
A
PC
p
r
o
f
ile.
3
.
7
.
Ada
pta
t
io
n a
nd
re
v
is
io
n o
f
a
new
lea
rning
pa
t
h
T
h
e
lear
n
er
in
d
if
f
ic
u
lt
y
w
ill
in
h
er
it
th
e
s
a
m
e
b
e
h
av
io
r
an
d
l
ea
r
n
in
g
p
ath
o
f
t
h
e
n
ea
r
es
t
n
ei
g
h
b
o
r
lear
n
er
w
h
o
h
a
s
a
m
in
i
m
al
d
i
s
tan
ce
.
I
f
t
h
e
s
y
s
te
m
d
etec
t
s
an
o
th
er
lear
n
i
n
g
p
r
o
b
le
m
i
n
th
e
lear
n
in
g
p
r
o
ce
s
s
,
it
r
etu
r
n
s
to
th
e
elab
o
r
atio
n
o
f
l
ea
r
n
in
g
p
r
o
b
le
m
s
tep
,
o
th
er
w
i
s
e
a
co
n
tr
o
l
o
f
th
e
ad
ap
ted
le
ar
n
in
g
p
at
h
w
ill
b
e
ex
ec
u
ted
t
h
r
o
u
g
h
t
h
e
ac
t
u
al
o
b
s
er
v
atio
n
o
f
th
e
lear
n
i
n
g
p
r
o
ce
s
s
o
r
th
e
r
es
u
lt
s
o
b
tain
ed
d
u
r
in
g
t
h
e
e
v
alu
a
tio
n
.
I
f
th
e
s
y
s
te
m
d
etec
t
s
an
o
t
h
e
r
lear
n
in
g
p
r
o
b
le
m
i
n
t
h
e
le
ar
n
in
g
p
r
o
ce
s
s
,
i
t
r
et
u
r
n
s
to
th
e
elab
o
r
atio
n
o
f
th
e
lear
n
i
n
g
p
r
o
b
lem
.
3
.
8
.
Sa
v
ing
a
lea
rn
ing
pa
t
h
I
f
th
e
s
y
s
te
m
d
etec
ts
n
o
ch
a
n
g
e
in
th
e
r
ev
i
s
ed
lear
n
in
g
p
ath
.
T
h
e
n
e
w
lear
n
i
n
g
p
ath
o
f
th
e
l
ea
r
n
er
in
d
if
f
ic
u
lt
y
A
PC
a
n
d
th
e
ir
lear
n
i
n
g
tr
ac
e
s
b
ec
o
m
es
a
n
e
w
lear
n
in
g
e
x
p
er
ien
ce
t
h
at
is
s
o
lv
ed
an
d
m
ai
n
tai
n
ed
in
th
e
lear
n
i
n
g
b
ase
to
s
o
lv
e
f
u
t
u
r
e
lea
r
n
in
g
p
r
o
b
lem
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
Hyb
r
id
a
p
p
r
o
a
c
h
o
f th
e
f
u
z
z
y
C
-
mea
n
s
a
n
d
th
e
K
-
n
e
a
r
est n
eig
h
b
o
r
s
meth
o
d
s
d
u
r
in
g
.
.
.
(
E
l
Gh
o
u
ch
N
ih
a
d
)
4945
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
NS
4
.
1
.
P
re
s
ent
a
t
io
n o
f
t
he
da
t
a
I
n
t
h
is
s
ec
tio
n
,
w
e
test
th
e
e
f
f
ec
tiv
e
n
e
s
s
o
f
t
h
e
co
m
b
in
a
ti
o
n
o
f
th
e
F
C
M
m
et
h
o
d
an
d
th
e
K
NN
m
et
h
o
d
in
th
e
R
etr
iev
e
s
tep
o
f
I
DC
B
R
r
ec
all
s
tep
.
W
e
f
ir
s
t
ap
p
ly
t
h
e
KNN
m
et
h
o
d
an
d
th
en
w
e
co
m
b
i
ne
th
e
F
C
M
an
d
KNN
to
f
in
d
t
h
e
n
ea
r
est lea
r
n
er
s
,
u
s
i
n
g
th
e
Ma
tlab
s
o
f
t
w
ar
e.
W
e
d
ef
in
e
t
h
e
f
o
llo
w
i
n
g
ele
m
e
n
ts
:
a.
T
h
e
n
u
m
b
er
o
f
lear
n
er
s
: 2
2
lear
n
er
s
.
b.
T
h
e
Me
r
is
e
co
u
r
s
e
co
n
tain
s
5
lear
n
in
g
u
n
i
ts
,
ea
ch
u
n
it o
f
t
h
e
co
u
r
s
e
is
p
r
esen
ted
b
y
d
i
f
f
er
e
n
t v
er
s
io
n
s
.
c.
T
h
e
in
itials
p
r
o
f
ile
s
o
f
th
e
lea
r
n
er
s
:
4
p
r
o
f
iles
(
Sen
s
in
g
/
Vi
s
u
al,
Se
n
s
i
n
g
/
Ver
b
al,
I
n
tu
iti
v
e
/
Ver
b
al
an
d
I
n
tu
i
tiv
e
/ V
is
u
al)
d.
T
h
e
n
u
m
b
er
o
f
K
n
eig
h
b
o
r
s
:
i
n
g
e
n
er
al,
th
e
g
o
o
d
v
alu
e
o
f
K
is
√
w
h
er
e
n
i
s
th
e
p
o
p
u
latio
n
[
2
6
]
.
I
n
o
u
r
ca
s
e,
n
is
t
h
e
n
u
m
b
er
o
f
lear
n
e
r
s
w
h
o
v
alid
ated
th
e
co
u
r
s
e.
e.
T
h
e
m
ea
s
u
r
e
o
f
d
is
t
a
nce
: t
h
e
E
u
clid
ea
n
d
is
ta
n
ce
(
d
)
;
W
e
h
av
e
g
r
o
u
p
ed
t
h
e
lear
n
er
s
'
tr
ac
e
s
i
n
t
h
e
d
i
f
f
er
e
n
t
i
n
s
tan
t
s
t
i
(
i
f
r
o
m
0
to
4
)
in
t
h
e
T
ab
le
2
.
E
ac
h
r
o
w
o
f
th
e
tab
le
p
r
esen
ts
t
h
e
m
atr
ix
_
(
)
(
w
it
h
i
f
r
o
m
0
to
4
an
d
j
is
th
e
I
d
o
f
th
e
lear
n
er
)
an
d
ea
c
h
r
o
w
o
f
t
h
is
m
a
tr
ix
co
n
tai
n
s
t
h
e
v
ec
to
r
(
,
)
w
h
ich
p
r
ese
n
t
s
t
h
e
tr
ac
e
o
f
th
e
lear
n
er
j
in
m
o
m
e
n
t
t
i
.
T
h
e
tr
ac
e
co
n
tain
s
a
s
et
o
f
i
n
f
o
r
m
atio
n
o
n
t
h
e
ac
ti
v
it
y
ca
r
r
ied
o
u
t
b
y
th
e
lear
n
er
at
ea
ch
m
o
m
en
t
t
i
s
u
c
h
as
th
e
d
u
r
atio
n
o
f
co
n
s
u
ltatio
n
o
f
t
h
e
lear
n
i
n
g
o
b
j
ec
t
(
D)
,
th
e
n
u
m
b
er
o
f
ti
m
es
o
f
co
n
s
u
ltatio
n
(
T
)
,
th
e
f
o
r
m
at
(
F
)
an
d
th
e
r
eso
u
r
ce
(
R
)
o
f
th
is
l
ea
r
n
in
g
o
b
j
ec
t
.
T
ab
le
2
.
T
r
ac
es
o
f
lear
n
er
s
at
ea
ch
ep
is
o
d
e
t
i
T
h
e
T
ab
le
3
p
r
esen
ts
t
h
e
n
u
m
b
er
o
f
lear
n
er
s
b
y
p
r
o
f
ile
.
O
f
th
e
2
2
s
tu
d
e
n
ts
,
1
7
v
alid
ated
t
h
e
co
u
r
s
e
(
I
d
1
-
17
)
an
d
th
e
o
th
er
s
t
u
d
en
ts
h
a
v
e
lear
n
i
n
g
p
r
o
b
lem
s
(
I
d
1
8
-
22
).
T
ab
le
4
s
h
o
w
l
ea
r
n
er
s
th
a
t
h
a
v
e
a
lear
n
in
g
p
r
o
b
lem
.
W
e
tak
e
b
y
te
s
t,
th
e
lear
n
er
in
d
if
f
ic
u
lt
y
w
h
o
s
e
I
D
is
1
8
w
h
o
h
as
a
lear
n
in
g
p
r
o
b
lem
i
n
lear
n
in
g
u
n
it 3
(
m
o
m
e
n
t t
2
).
T
h
e
F
i
g
u
r
e
4
ill
u
s
tr
ated
b
y
th
e
Ma
tlab
s
o
f
t
w
ar
e
s
h
o
w
s
t
h
e
d
is
tr
ib
u
tio
n
o
f
lear
n
er
s
ac
co
r
d
in
g
to
th
e
f
ir
s
t
3
attr
ib
u
tes
at
m
o
m
e
n
t
t
0
,
b
ef
o
r
e
clas
s
i
f
icatio
n
in
cl
u
s
ter
s
(
th
e
d
u
r
ati
o
n
o
f
co
n
s
u
lta
tio
n
,
th
e
n
u
m
b
er
o
f
v
is
it,
th
e
r
e
s
o
u
r
ce
an
d
th
e
f
o
r
m
at
o
f
t
h
e
o
b
ject
lear
n
i
n
g
)
.
T
h
e
lear
n
er
I
D
1
8
is
p
r
esen
ted
b
y
th
e
s
i
g
n
+.
T
ab
le
3
.
Nu
m
b
er
o
f
lear
n
er
s
b
y
p
r
o
f
ile
P
r
o
f
i
l
e
s
N
u
mb
e
r
o
f
l
e
a
r
n
e
r
s
S
e
n
si
n
g
/
V
i
s
u
a
l
15
S
e
n
si
n
g
/
V
e
r
b
a
l
3
I
n
t
u
i
t
i
v
e
/
V
e
r
b
a
l
3
I
n
t
u
i
t
i
v
e
/
V
i
su
a
l
1
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
2
0
1
9
:
4
9
3
9
-
495
0
4946
T
ab
le
4
.
L
ea
r
n
er
s
h
a
v
e
a
lear
n
in
g
p
r
o
b
le
m
L
e
a
r
n
e
r
I
n
i
t
i
a
l
p
r
o
f
i
l
e
18
S
e
n
si
n
g
/
V
i
s
u
a
l
19
S
e
n
si
n
g
/
V
i
s
u
a
l
20
S
e
n
si
n
g
/
V
i
s
u
a
l
21
I
n
t
u
i
t
i
v
e
/
V
i
su
a
l
22
I
n
t
u
i
t
i
v
e
/
V
e
r
b
a
l
Fig
u
r
e
4
.
Dis
tr
ib
u
tio
n
o
f
lear
n
er
s
b
ef
o
r
e
class
i
f
icatio
n
4
.
2
.
Cla
s
s
if
ica
t
io
n us
i
ng
K
NN
W
e
ap
p
ly
th
e
K
Nea
r
est
Nei
g
h
b
o
r
s
alg
o
r
it
h
m
b
y
co
m
p
ar
i
n
g
t
h
e
t
r
ac
es
o
f
th
e
lear
n
er
I
d
1
8
w
it
h
th
e
tr
ac
es
o
f
1
7
lear
n
er
s
w
h
o
v
alid
ated
th
e
co
u
r
s
e
,
w
e
o
b
tain
th
e
I
d
s
o
f
th
e
K
n
ea
r
est
w
ith
t
h
e
Ma
tlab
s
o
f
t
w
ar
e
a
s
s
h
o
w
n
i
n
T
ab
le
5
.
W
e
ap
p
ly
th
e
K
Nea
r
e
s
t
Neig
h
b
o
r
s
alg
o
r
it
h
m
at
ea
ch
in
s
ta
n
t
t
i
,
w
e
o
b
tain
th
e
f
o
llo
w
i
n
g
r
esu
lts
w
it
h
t
h
e
Ma
tlab
s
o
f
t
w
ar
e
as
s
h
o
w
n
in
T
ab
le
6
.
T
ab
le
5
.
I
d
o
f
lear
n
er
s
ac
co
r
d
i
n
g
to
KNN
N
u
mb
e
r
o
f
t
h
e
K
n
e
a
r
e
st
l
e
a
r
n
e
r
s
2
3
4
Id
d
Id
d
Id
d
1
3
1
,
0
2
1
3
1
,
0
2
1
3
1
,
0
2
3
4
6
,
2
2
3
4
6
,
2
2
3
4
6
,
2
2
11
4
6
,
3
2
11
4
6
,
32
5
4
9
,
1
6
T
ab
le
6
.
I
D
o
f
lear
n
er
s
ac
co
r
d
in
g
to
KNN
f
o
r
ea
ch
m
o
m
e
n
t t
i
N
u
mb
e
r
o
f
t
h
e
K
n
e
a
r
e
st
l
e
a
r
n
e
r
s
K
=
2
N
u
mb
e
r
o
f
t
h
e
K
n
e
a
r
e
st
l
e
a
r
n
e
r
s
K
=
3
N
u
mb
e
r
o
f
t
h
e
K
n
e
a
r
e
st
l
e
a
r
n
e
r
s
K
=
4
t
0
t
1
t
0
t
1
t
0
t
1
Id
d
Id
d
Id
D
Id
d
Id
d
Id
d
1
31
1
1
,
2
6
1
31
1
1
,
2
6
1
31
1
1
,
2
6
13
3
2
,
0
1
3
4
,
4
7
13
3
2
,
0
1
3
4
,
4
7
13
3
2
,
0
1
3
4
,
4
7
7
3
8
,
1
1
11
11
7
3
8
,
1
1
11
11
4
4
1
,
7
7
5
1
6
,
2
9
4
.
3
.
Co
m
bin
a
is
o
n o
f
K
NN
a
nd
F
CM
W
e
ap
p
ly
t
h
e
F
u
zz
y
C
-
Me
a
n
s
al
g
o
r
ith
m
;
w
e
o
b
tain
th
e
r
esu
lt
s
p
r
esen
ted
in
t
h
e
T
ab
le
7
w
it
h
th
e
Ma
t
lab
s
o
f
t
w
ar
e,
w
h
ich
in
d
icate
th
e
n
u
m
b
er
o
f
lear
n
er
s
ex
is
t
in
g
i
n
th
e
clu
s
ter
o
f
w
h
ic
h
t
h
e
lear
n
er
I
d
1
8
b
el
o
n
g
s
,
ac
co
r
d
in
g
to
th
e
n
u
m
b
er
o
f
cl
u
s
ter
s
.
W
e
ar
e
r
u
n
n
i
n
g
th
e
K
Nea
r
es
t
Neig
h
b
o
r
s
alg
o
r
ith
m
i
n
th
e
clu
s
ter
o
f
w
h
ich
t
h
e
L
e
ar
n
er
I
d
1
8
b
elo
n
g
s
,
w
e
g
e
t
th
e
f
o
llo
w
i
n
g
r
esu
l
ts
as
s
h
o
w
n
i
n
T
ab
le
8
.
T
h
e
F
ig
u
r
e
5
s
h
o
w
s
t
h
e
g
r
o
u
p
in
g
o
f
lear
n
er
s
in
t
h
e
4
clu
s
ter
s
(
r
ed
,
g
r
ee
n
,
y
ello
w
,
b
lu
e)
,
ac
co
r
d
in
g
to
th
e
f
ir
s
t
th
r
ee
attr
ib
u
tes
at
ti
m
e
t
0
.
W
e
r
u
n
t
h
e
K
-
P
lu
s
Nea
r
est
Neig
h
b
o
r
s
alg
o
r
it
h
m
i
n
th
e
clu
s
ter
o
f
w
h
ic
h
th
e
lear
n
er
I
d
1
8
b
elo
n
g
s
to
ea
ch
t
i
as s
h
wo
n
in
T
ab
le
s
9
-
11
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
Hyb
r
id
a
p
p
r
o
a
c
h
o
f th
e
f
u
z
z
y
C
-
mea
n
s
a
n
d
th
e
K
-
n
e
a
r
est n
eig
h
b
o
r
s
meth
o
d
s
d
u
r
in
g
.
.
.
(
E
l
Gh
o
u
ch
N
ih
a
d
)
4947
T
ab
le
7
.
Nu
m
b
er
o
f
lear
n
er
s
b
y
clu
s
ter
N
u
mb
e
r
o
f
C
l
u
s
t
e
r
s C
N
u
mb
e
r
o
f
l
e
a
r
n
e
r
s
2
16
3
12
4
11
T
ab
le
8
.
I
D
o
f
K
n
ea
r
est lea
r
n
er
s
b
y
cl
u
s
ter
n
u
m
b
er
N
u
mb
e
r
o
f
C
l
u
s
t
e
r
s C
N
u
mb
e
r
o
f
t
h
e
K
n
e
a
r
e
st
l
e
a
r
n
e
r
s
K
2
3
4
Id
D
Id
D
Id
d
2
1
3
1
,
0
2
1
3
1
,
0
2
1
3
1
,
0
2
3
4
6
,
2
2
3
4
6
,
22
3
4
6
,
2
2
10
4
6
,
3
2
10
4
6
,
3
2
5
4
9
,
1
6
3
1
3
1
,
0
2
1
3
1
,
0
2
1
3
1
,
0
2
2
4
6
,
2
2
2
4
6
,
2
2
2
4
6
,
2
2
8
4
6
,
3
2
8
4
6
,
3
2
4
4
9
,
1
6
4
1
3
1
,
0
2
1
3
1
,
0
2
1
3
1
,
0
2
2
4
6
,
2
2
2
4
6
,
2
2
2
4
6
,
2
2
8
4
6
,
3
2
8
4
6
,
3
2
4
4
9
,
1
6
Fig
u
r
e
5
.
R
ep
ar
titi
o
n
o
f
lear
n
e
r
s
af
ter
class
if
icatio
n
i
n
to
4
clu
s
ter
s
T
ab
le
9
.
I
D
o
f
K
n
ea
r
est lea
r
n
er
s
b
y
cl
u
s
ter
n
u
m
b
er
(
C
=
2
)
f
o
r
ea
ch
m
o
m
en
t t
i
N
u
mb
e
r
o
f
C
l
u
st
e
r
s C
N
u
mb
e
r
o
f
t
h
e
K
n
e
a
r
e
st
l
e
a
r
n
e
r
s
K
=
2
N
u
mb
e
r
o
f
t
h
e
K
n
e
a
r
e
st
l
e
a
r
n
e
r
s
K
=
3
N
u
mb
e
r
o
f
t
h
e
K
n
e
a
r
e
st
l
e
a
r
n
e
r
s
K
=
4
t
0
t
1
t
0
t
1
t
1
t
0
Id
d
Id
Id
D
Id
Id
d
Id
Id
d
Id
2
1
31
1
1
,
2
6
1
31
1
1
,
2
6
1
31
1
1
,
2
6
12
3
2
,
0
1
3
4
,
4
7
12
3
2
,
0
1
3
4
,
4
7
12
3
2
,
0
1
3
4
,
4
7
7
3
8
,
1
1
10
11
7
3
8
,
1
1
10
11
4
4
1
,
7
7
5
1
6
,
2
9
T
ab
le
10
.
I
D
o
f
K
n
ea
r
est lea
r
n
er
s
b
y
cl
u
s
ter
n
u
m
b
er
(
C
=
3
)
f
o
r
ea
ch
m
o
m
e
n
t t
i
N
u
mb
e
r
o
f
C
l
u
st
e
r
s C
N
u
mb
e
r
o
f
t
h
e
K
n
e
a
r
e
st
l
e
a
r
n
e
r
s
K
=
2
N
u
mb
e
r
o
f
t
h
e
K
n
e
a
r
e
st
l
e
a
r
n
e
r
s
K
=
3
N
u
mb
e
r
o
f
t
h
e
K
n
e
a
r
e
st
l
e
a
r
n
e
r
s
K
=
4
t
0
t
1
t
0
t
1
t
1
t
0
Id
d
Id
d
Id
d
Id
D
Id
d
Id
d
3
1
31
1
1
,
2
6
1
31
1
1
,
2
6
1
31
1
1
,
2
6
9
3
2
,
0
1
2
4
,
4
7
9
3
2
,
0
1
2
4
,
4
7
9
3
2
,
0
1
2
4
,
4
7
6
3
8
,
1
1
8
11
6
3
8
,
1
1
8
11
3
4
1
,
7
7
4
1
6
,
2
9
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
2
0
1
9
:
4
9
3
9
-
495
0
4948
T
ab
le
11
.
I
D
o
f
K
n
ea
r
est lea
r
n
e
r
s
b
y
cl
u
s
ter
n
u
m
b
er
(
C
=
4
)
f
o
r
ea
ch
m
o
m
e
n
t t
i
N
u
mb
e
r
o
f
C
l
u
st
e
r
s C
N
u
mb
e
r
o
f
t
h
e
K
n
e
a
r
e
st
l
e
a
r
n
e
r
s
K
=
2
N
u
mb
e
r
o
f
t
h
e
K
n
e
a
r
e
st
l
e
a
r
n
e
r
s
K
=
3
N
u
mb
e
r
o
f
t
h
e
K
n
e
a
r
e
st
l
e
a
r
n
e
r
s
K
=
4
t
0
t
1
t
0
t
1
t
1
t
0
Id
d
Id
Id
d
Id
Id
d
Id
Id
d
Id
4
1
31
1
1
,
2
6
1
31
1
1
,
2
6
1
31
1
1
,
2
6
12
3
2
,
0
1
3
4
,
4
7
12
3
2
,
0
1
3
4
,
4
7
9
3
2
,
0
1
2
4
,
4
7
7
3
8
,
1
1
10
11
6
3
8
,
1
1
8
11
3
4
1
,
7
7
4
1
6
,
2
9
4
.
4
.
G
ra
ph
ic
r
epre
s
ent
a
t
io
ns
&
d
is
cu
s
s
io
n
s
Fro
m
T
ab
le
5
an
d
T
ab
le
8
,
w
e
g
e
n
er
ate
t
h
e
f
o
llo
w
i
n
g
g
r
ap
h
as
s
h
o
w
n
in
Fi
g
u
r
e
6
t
o
p
r
esen
t
th
e
d
if
f
e
r
en
t
lear
n
er
I
d
s
b
y
d
is
tan
ce
u
s
i
n
g
K
NN
an
d
co
m
b
i
n
i
n
g
K
NN
w
it
h
F
C
M.
Fro
m
T
ab
le
6
an
d
T
ab
le
1
1
,
w
e
g
e
n
er
ate
t
h
e
f
o
llo
w
i
n
g
g
r
a
p
h
s
a
s
s
h
o
w
n
in
Fi
g
u
r
e
7
to
p
r
esen
t
th
e
d
if
f
er
en
t
lear
n
er
I
D
s
b
y
d
is
ta
n
ce
u
s
i
n
g
KNN
f
o
r
th
e
m
o
m
e
n
t t
1
a
s
s
h
o
w
n
i
n
Fi
g
u
r
e
8
.
Fig
u
r
e
6
.
I
D
o
f
lear
n
er
s
ac
co
r
d
in
g
to
d
is
ta
n
ce
s
acc
o
r
d
in
g
to
KNN
&
co
m
b
i
n
a
tio
n
FC
M
an
d
KNN
(
w
ith
K
=
4
)
Fig
u
r
e
7
.
K
(
k
=
4
)
n
ea
r
est lea
r
n
er
s
ac
co
r
d
in
g
to
th
e
co
m
b
i
n
atio
n
o
f
KNN
a
n
d
FC
M
(
C
=
2
,
3
,
4
)
f
o
r
t
0
A
cc
o
r
d
in
g
to
F
i
g
u
r
e
6
,
Fig
u
r
e
7
an
d
Fig
u
r
e
8,
t
h
e
r
es
u
lt
s
o
b
tain
ed
b
y
KNN
an
d
th
e
co
m
b
in
atio
n
o
f
KNN
w
it
h
FC
M
g
iv
e
s
i
m
ila
r
r
esu
lt
s
.
B
u
t
th
e
r
es
u
lts
o
f
th
e
co
m
b
i
n
atio
n
o
f
KNN
w
i
th
FC
M
ar
e
m
o
r
e
ac
cu
r
ate.
T
h
e
lear
n
er
I
d
1
is
th
e
n
ea
r
est
lear
n
er
to
th
e
lear
n
er
I
d
1
8
(
in
d
if
f
ic
u
lt
y
)
at
ti
m
es
t
0
an
d
t
1
,
u
s
in
g
KNN
o
r
th
e
co
m
b
in
atio
n
o
f
KNN
an
d
FC
M.
T
h
e
d
if
f
er
en
ce
r
em
ai
n
s
in
t
h
e
n
u
m
b
er
o
f
lear
n
er
s
to
co
m
p
ar
e
an
d
th
e
ti
m
e
o
f
ca
lc
u
lat
io
n
o
f
s
i
m
i
lar
it
y
.
Usi
n
g
th
e
KNN
m
et
h
o
d
,
th
e
n
u
m
b
er
o
f
s
a
m
p
les
is
1
7
lear
n
er
s
h
o
w
ev
er
w
it
h
t
h
e
co
m
b
i
n
atio
n
o
f
F
C
M
a
n
d
KNN
m
e
th
o
d
s
,
th
e
n
u
m
b
er
o
f
s
a
m
p
le
is
1
1
lear
n
er
s
w
h
ic
h
r
ed
u
ce
s
th
e
cla
s
s
i
f
icatio
n
ti
m
e
.
Fig
u
r
e
8
.
K
(
k
=
4
)
n
ea
r
est lea
r
n
er
s
ac
co
r
d
in
g
to
th
e
co
m
b
i
n
atio
n
o
f
KNN
a
n
d
FC
M
(
C
=
2
,
3
,
4
)
f
o
r
t
1
Evaluation Warning : The document was created with Spire.PDF for Python.