I
AE
S
I
nte
rna
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
8
,
No
.
3
,
Sep
tem
b
er
201
9
,
p
p
.
2
99
~
306
I
SS
N:
2252
-
8938
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ai.
v
8
.i
3
.
p
p
2
99
-
3
0
6
299
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e
.
co
m/o
n
lin
e/in
d
ex
.
p
h
p
/I
J
A
I
Perf
o
r
m
a
nce
ana
ly
sis
of superv
ised
learning
m
o
dels
f
o
r product
tit
le
cla
ss
ificatio
n
No
rsy
ela
M
uh
a
m
m
a
d
No
o
r
M
a
t
hiv
a
na
n
1
,
No
r
Azura
M
d.G
ha
n
i
2
,
Ro
zia
h M
o
hd
J
a
no
r
3
1,
2,
3
Ce
n
ter f
o
r
S
tatisti
c
a
l
a
n
d
De
c
i
sio
n
S
c
ie
n
c
e
s S
tu
d
ies
,
F
a
c
u
lt
y
o
f
Co
m
p
u
ter &
M
a
th
e
m
a
ti
c
a
l
S
c
ien
c
e
s Un
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
A
RA
,
4
0
4
5
0
S
h
a
h
A
lam
,
S
e
lan
g
o
r,
M
a
la
y
sia
2
Na
ti
o
n
a
l
De
sig
n
Ce
n
tre Un
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
A
R
A
4
0
4
5
0
S
h
a
h
A
la
m
,
S
e
lan
g
o
r,
M
a
la
y
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
1
,
2
0
1
9
R
ev
i
s
ed
A
u
g
12
,
2
0
1
9
A
cc
ep
ted
A
u
g
2
9
,
2
0
1
9
On
li
n
e
b
u
sin
e
ss
d
e
v
e
lo
p
m
e
n
t
th
ro
u
g
h
e
-
c
o
m
m
e
r
c
e
p
lat
f
o
rm
s
is
a
p
h
e
n
o
m
e
n
o
n
w
h
ich
c
h
a
n
g
e
th
e
w
o
rld
o
f
p
ro
m
o
ti
n
g
a
n
d
se
ll
in
g
p
ro
d
u
c
ts
in
th
is
2
1
st
c
e
n
t
u
ry
.
P
ro
d
u
c
t
ti
t
le
c
las
sif
ic
a
ti
o
n
is
a
n
im
p
o
rtan
t
tas
k
in
a
ss
isti
n
g
re
tailers
a
n
d
se
ll
e
rs
t
o
l
ist
a
p
r
o
d
u
c
t
i
n
a
s
u
it
a
b
le
c
a
teg
o
ry
.
P
r
o
d
u
c
t
ti
tl
e
c
las
si
f
ica
ti
o
n
is
a
p
a
rt
o
f
te
x
t
c
las
sif
ic
a
ti
o
n
p
ro
b
lem
b
u
t
th
e
p
r
o
p
e
rti
e
s
o
f
p
ro
d
u
c
t
ti
tl
e
a
re
d
if
f
e
re
n
t
f
ro
m
g
e
n
e
ra
l
d
o
c
u
m
e
n
t.
T
h
is stu
d
y
a
i
m
s t
o
e
v
a
lu
a
te
th
e
p
e
rf
o
rm
a
n
c
e
o
f
f
iv
e
d
iffere
n
t
su
p
e
rv
ise
d
lea
rn
in
g
m
o
d
e
ls
o
n
d
a
ta
se
ts
c
o
n
sist
o
f
e
-
c
o
m
m
e
r
c
e
p
ro
d
u
c
t
t
i
tl
e
s
w
it
h
a
v
e
r
y
sh
o
rt
d
e
sc
rip
ti
o
n
a
n
d
t
h
e
y
a
re
in
c
o
m
p
lete
s
e
n
ten
c
e
s.
T
h
e
s
u
p
e
rv
ise
d
lea
rn
in
g
m
o
d
e
ls
in
v
o
lv
e
in
th
e
stu
d
y
a
re
Na
ïv
e
Ba
y
e
s,
K
-
Ne
a
re
s
t
Ne
ig
h
b
o
r
(KN
N),
De
c
isio
n
T
re
e
,
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
(S
V
M
)
a
n
d
Ra
n
d
o
m
F
o
re
st.
T
h
e
re
su
lt
s sh
o
w KN
N
m
o
d
e
l
is
th
e
b
e
st
m
o
d
e
l
w
it
h
th
e
h
ig
h
e
st
a
c
c
u
ra
c
y
a
n
d
f
a
ste
st
c
o
m
p
u
tatio
n
ti
m
e
to
c
las
si
fy
th
e
d
a
ta
u
se
d
in
th
e
st
u
d
y
.
He
n
c
e
,
KN
N
m
o
d
e
l
is
a
g
o
o
d
a
p
p
r
o
a
c
h
in
c
las
si
fy
in
g
e
-
c
o
m
m
e
rc
e
p
ro
d
u
c
ts.
K
ey
w
o
r
d
s
:
P
r
o
d
u
ct
titl
e
Su
p
er
v
i
s
ed
lear
n
i
n
g
m
o
d
el
T
ex
t c
lass
if
icatio
n
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
:
No
r
A
zu
r
a
Md
.
Gh
a
n
i,
C
en
ter
f
o
r
Statis
t
ical
an
d
Dec
i
s
io
n
Scie
n
ce
s
Stu
d
ie
s
,
Facu
lt
y
o
f
C
o
m
p
u
ter
&
Ma
t
h
e
m
atica
l Sc
ien
ce
s
,
Un
i
v
er
s
iti T
ek
n
o
lo
g
i M
A
R
A
,
4
0
4
5
0
Sh
ah
A
la
m
,
Sela
n
g
o
r
Ma
la
y
s
ia.
E
m
ail:
az
u
r
a@
t
m
s
k
.
u
it
m
.
ed
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
C
u
r
r
en
tl
y
,
e
-
co
m
m
er
ce
p
latf
o
r
m
s
b
ec
o
m
e
a
m
aj
o
r
w
a
y
to
p
r
o
m
o
te
p
r
o
d
u
cts
an
d
s
er
v
ices.
I
t
co
n
s
is
t
s
a
w
id
e
r
an
g
e
o
f
i
n
t
er
ac
tio
n
p
r
o
ce
s
s
es
b
et
w
ee
n
v
a
r
io
u
s
m
ar
k
et
u
s
er
s
f
r
o
m
o
r
d
er
in
g
a
n
d
d
eliv
er
i
n
g
p
r
o
d
u
cts u
n
til t
h
e
s
eller
s
is
s
u
e
in
v
o
ices a
n
d
u
s
er
s
m
a
k
e
p
a
y
m
en
ts
[
1
]
.
T
h
e
f
ast d
ev
e
lo
p
m
e
n
t o
f
e
-
co
m
m
er
ce
i
s
co
n
tr
ib
u
ted
th
e
m
o
s
t
b
y
t
h
e
av
ailab
ilit
y
o
f
d
i
f
f
er
en
t
p
r
o
d
u
cts
an
d
t
h
e
ea
s
i
n
es
s
o
f
tr
an
s
ac
ti
n
g
m
o
n
e
y
o
v
er
in
ter
n
et
[
2
]
.
T
h
e
r
e
ar
e
lar
g
e
i
n
v
e
n
to
r
ies
w
ith
v
ar
io
u
s
k
i
n
d
o
f
p
r
o
d
u
cts
s
o
ld
th
r
o
u
g
h
o
n
li
n
e
s
to
r
e
w
eb
s
i
tes
s
u
c
h
as
W
al
m
ar
t
,
Am
az
o
n
,
Alip
a
y
a
n
d
eB
a
y
.
User
s
ar
e
ab
le
to
v
ie
w
a
n
d
b
u
y
m
a
n
y
n
e
w
p
r
o
d
u
cts
f
r
o
m
th
e
w
eb
s
i
tes
f
r
o
m
ti
m
e
to
ti
m
e
.
Mo
s
t
o
f
th
e
w
eb
s
ites
ar
e
w
ell
-
s
tr
u
ct
u
r
ed
an
d
th
e
y
co
n
s
is
t
o
f
p
r
o
d
u
ct
in
f
o
r
m
at
io
n
s
u
c
h
as
t
h
e
p
r
o
d
u
ct
n
a
m
e,
d
es
cr
ip
tio
n
,
p
r
ice,
an
d
im
a
g
e.
T
h
e
o
f
ten
i
n
clu
s
io
n
o
f
n
e
w
p
r
o
d
u
cts
i
n
e
-
co
m
m
er
ce
w
eb
s
i
tes
lead
s
to
an
i
m
p
o
r
tan
t
task
o
f
cla
s
s
i
f
y
in
g
a
p
r
o
d
u
ct
titl
e
to
as
s
is
t
s
eller
s
lis
ti
n
g
a
n
ite
m
i
n
a
s
u
itab
le
ca
teg
o
r
y
.
So
m
e
s
y
s
te
m
w
il
l
p
er
f
o
r
m
cla
s
s
i
f
icatio
n
d
ir
ec
tl
y
af
ter
o
b
tain
i
n
g
tit
le
o
f
th
e
p
r
o
d
u
ct.
Mo
s
t
o
f
th
e
tex
t
m
i
n
i
n
g
p
r
o
ce
s
s
i
n
v
o
l
v
es
a
b
u
n
d
le
o
f
d
o
cu
m
e
n
ts
co
n
s
i
s
t
o
f
le
n
g
t
h
y
w
o
r
d
s
b
u
t
titl
e
d
esc
r
ip
tio
n
n
o
r
m
a
ll
y
is
a
s
h
o
r
t
tex
t.
T
itles
ar
e
d
if
f
er
en
t
f
r
o
m
tex
t
s
in
v
ar
io
u
s
asp
ec
ts
s
u
c
h
as
th
e
le
n
g
t
h
o
f
ea
ch
s
e
n
t
en
ce
is
v
er
y
s
h
o
r
t,
it
co
n
s
is
t
s
o
f
s
i
m
ilar
d
is
tr
ib
u
tio
n
o
f
len
g
t
h
s
,
a
n
d
t
h
e
g
r
a
m
m
atica
l
s
tr
u
c
tu
r
e
i
s
m
o
s
t
l
y
i
n
co
m
p
leted
[
3
]
.
T
h
er
e
is
a
s
t
u
d
y
r
elate
d
to
p
r
o
d
u
ct
titl
e
cla
s
s
i
f
icat
io
n
,
b
u
t
i
t
f
o
cu
s
ed
o
n
id
e
n
ti
f
y
in
g
g
e
n
er
al
p
r
o
p
er
ties
o
f
p
r
o
d
u
ct
titl
es
[
3
-
4
]
.
T
h
e
m
o
s
t
r
elate
d
b
u
t
b
r
o
ad
er
ar
ea
is
a
s
h
o
r
t
-
te
x
t
cla
s
s
i
f
icatio
n
,
w
h
ich
alr
ea
d
y
co
n
s
i
s
ts
o
f
v
ar
io
u
s
l
iter
atu
r
e.
T
h
er
e
ar
e
s
tu
d
ie
s
in
v
o
l
v
e
class
if
y
i
n
g
s
h
o
r
t
tex
t
s
u
ch
a
s
q
u
e
s
tio
n
class
i
f
ic
atio
n
[
5
-
6
]
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
8
,
No
.
3
,
Sep
tem
b
er
20
1
9
:
2
9
9
–
3
0
6
300
s
e
m
a
n
tic
a
n
n
o
tatio
n
clas
s
i
f
ic
atio
n
[
7
]
an
d
jo
b
titl
e
class
if
icatio
n
[
8
]
.
Ho
w
e
v
er
,
q
u
es
tio
n
an
d
s
e
m
a
n
tic
an
n
o
tatio
n
clas
s
i
f
icatio
n
n
o
r
m
all
y
u
s
es
co
m
p
lete
s
en
ten
c
es
an
d
j
o
b
titl
e
class
if
icat
io
n
d
ea
ls
w
it
h
s
h
o
r
ter
s
en
te
n
ce
s
co
m
p
ar
ed
to
p
r
o
d
u
ct
ti
tle.
B
esid
es
th
a
t,
t
h
er
e
ar
e
s
e
v
er
al
s
t
u
d
ies
ta
k
e
i
n
to
co
n
s
i
d
er
atio
n
o
th
er
s
o
u
r
ce
s
s
u
c
h
as
p
r
ice
o
f
th
e
p
r
o
d
u
ct
to
b
e
th
e
ad
d
itio
n
al
f
ea
t
u
r
e
w
it
h
th
e
ai
m
to
i
n
cr
ea
s
e
th
e
ac
c
u
r
ac
y
r
ate
o
f
t
h
e
class
i
f
icatio
n
m
o
d
el
[
9
-
1
0
]
.
Ho
w
e
v
er
,
th
i
s
s
t
u
d
y
s
o
lel
y
c
o
n
s
id
er
tex
t
f
r
o
m
titl
e
o
f
p
r
o
d
u
cts.
P
r
ev
io
u
s
l
y
,
it
w
a
s
f
o
u
n
d
t
h
at
t
h
e
p
r
o
p
er
ti
es
o
f
p
r
o
d
u
ct
titl
e
class
if
icati
o
n
ar
e
d
if
f
er
e
n
t
f
r
o
m
th
o
s
e
o
f
tex
t
class
if
ica
tio
n
w
h
er
e
s
te
m
m
in
g
a
n
d
s
to
p
-
w
o
r
d
r
em
o
v
a
l
ar
e
n
o
t
n
ee
d
ed
in
d
ea
lin
g
w
it
h
p
r
o
d
u
ct
titl
es
[
3
]
.
T
h
is
s
tu
d
y
i
s
i
n
th
e
s
a
m
e
d
ir
ec
tio
n
,
s
h
ar
in
g
t
h
e
s
a
m
e
s
p
ir
it
o
f
k
ee
p
in
g
m
o
d
el
s
i
m
p
licit
y
a
n
d
in
ter
p
r
etab
ilit
y
.
T
h
e
d
if
f
er
en
ce
is
th
e
p
r
ev
io
u
s
s
t
u
d
ies
f
o
cu
s
ed
o
n
p
r
o
p
er
ties
o
f
p
r
o
d
u
ct
ti
tles
,
w
h
ic
h
i
n
v
o
lv
e
tr
an
s
f
o
r
m
in
g
ea
c
h
p
air
o
f
w
o
r
d
to
k
e
n
s
f
r
o
m
t
h
e
tex
t
s
eq
u
e
n
ce
s
to
u
s
ef
u
l
f
ea
t
u
r
es.
I
n
t
h
is
p
ap
er
,
th
e
au
t
h
o
r
s
m
a
in
p
u
r
p
o
s
e
is
i
d
en
tify
i
n
g
th
e
m
o
s
t
s
u
itab
le
c
lass
if
ica
tio
n
m
o
d
els
to
d
ea
l
w
ith
s
h
o
r
t
-
te
x
t
d
ata
esp
ec
iall
y
in
v
o
lv
in
g
e
-
co
m
m
er
ce
p
r
o
d
u
ct
titl
es.
T
h
e
class
if
icat
io
n
o
f
e
-
co
m
m
e
r
ce
p
r
o
d
u
cts
b
ased
o
n
titl
e
o
f
a
p
r
o
d
u
ct
ca
n
b
e
d
o
n
e
u
s
in
g
s
u
p
er
v
is
ed
lear
n
i
n
g
m
o
d
el.
A
s
u
p
er
v
i
s
ed
lear
n
in
g
m
o
d
el
i
s
ab
le
to
s
o
lv
e
class
i
f
i
ca
tio
n
p
r
o
b
lem
s
b
ec
au
s
e
t
h
e
g
o
al
is
to
m
a
k
e
th
e
co
m
p
u
ter
lear
n
s
a
cla
s
s
i
f
icati
o
n
s
y
s
te
m
t
h
at
h
as
b
ee
n
cr
ea
ted
.
T
h
er
e
ar
e
v
ar
io
u
s
k
in
d
o
f
s
u
p
er
v
i
s
ed
lear
n
in
g
m
o
d
el
s
h
a
v
e
b
ee
n
ap
p
lied
i
n
m
an
y
f
ield
s
o
f
s
t
u
d
ies
s
u
ch
as
p
atter
n
r
ec
o
g
n
i
tio
n
[
1
1
]
,
n
atu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
[
1
2
]
,
m
ar
k
et
s
e
g
m
en
tatio
n
[
1
3
]
an
d
b
io
in
f
o
r
m
at
ics
[
1
4
]
.
Nev
er
t
h
eles
s
,
t
h
e
c
o
m
p
ar
i
s
o
n
b
et
w
ee
n
w
ell
-
k
n
o
w
n
s
u
p
er
v
i
s
ed
lear
n
i
n
g
m
o
d
els
in
c
lu
d
i
n
g
Naï
v
e
B
ay
es,
K
-
Nea
r
est
Nei
g
h
b
o
r
(
KN
N)
,
Dec
is
io
n
T
r
ee
s
,
Su
p
p
o
r
t
Vec
to
r
Ma
ch
i
n
e
(
SV
M)
an
d
R
a
n
d
o
m
Fo
r
est
is
n
o
t
y
et
to
b
e
s
ee
n
i
n
a
r
e
s
ea
r
ch
r
el
ated
to
p
r
o
d
u
ct
titl
e
class
i
f
icatio
n
.
I
t
i
s
cr
u
ci
al
to
ev
al
u
ate
th
e
p
er
f
o
r
m
a
n
ce
o
f
ea
ch
m
o
d
el
b
ec
au
s
e
t
h
e
r
es
u
lts
p
r
o
v
id
e
u
s
e
f
u
l
in
f
o
r
m
atio
n
ab
o
u
t
th
e
b
est
m
o
d
el
to
class
i
f
y
t
h
i
s
k
i
n
d
o
f
d
ata.
Hen
ce
,
th
is
p
ap
er
a
i
m
s
to
co
m
p
ar
e
th
e
p
er
f
o
r
m
a
n
ce
o
f
s
u
p
er
v
i
s
ed
lear
n
in
g
m
o
d
els
w
h
ic
h
ar
e
Naïv
e
B
a
y
es,
KNN,
Dec
i
s
io
n
T
r
ee
s
,
SVM
an
d
R
an
d
o
m
Fo
r
est
i
n
clas
s
i
f
y
i
n
g
titl
e
o
f
e
-
co
m
m
er
ce
p
r
o
d
u
cts
.
T
h
e
r
est
o
f
th
is
p
ap
er
is
o
r
g
an
ized
as
f
o
llo
w
s
:
Sectio
n
2
d
escr
ib
es
r
esear
c
h
es
r
elate
d
to
p
r
o
d
u
ct
titl
e
class
if
icatio
n
;
Sectio
n
3
p
r
esen
t
s
th
e
r
esear
ch
m
et
h
o
d
o
lo
g
y
i
n
cl
u
d
es
d
esc
r
ip
tio
n
o
f
d
ata
s
et
s
a
n
d
r
esear
ch
d
esig
n
u
s
ed
i
n
t
h
e
s
t
u
d
y
;
Se
ctio
n
4
s
h
o
w
s
th
e
r
esu
lt
s
o
b
tain
f
r
o
m
t
h
e
co
m
p
ar
i
s
o
n
o
f
th
e
s
u
p
er
v
is
ed
lear
n
in
g
m
o
d
els
to
w
ar
d
s
e
-
co
m
m
er
ce
p
r
o
d
u
ct
class
i
f
icatio
n
; Sec
tio
n
5
co
n
clu
d
es th
e
f
i
n
d
in
g
s
f
r
o
m
t
h
e
r
es
ea
r
ch
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
2
.
1
.
Da
t
a
des
cr
iptio
n
Dep
ar
t
m
en
t
o
f
Statis
tics
Ma
la
y
s
ia
(
D
OSM)
h
as
co
llected
p
r
o
d
u
ct
in
f
o
r
m
atio
n
f
r
o
m
o
n
e
o
f
th
e
m
aj
o
r
o
n
lin
e
s
to
r
e
w
eb
s
ite
t
h
r
o
u
g
h
ST
A
T
SB
DA
p
r
o
j
ec
t
k
n
o
w
n
a
s
P
r
ice
I
n
telli
g
en
ce
(
P
I
)
u
s
i
n
g
it
s
p
r
o
to
ty
p
e
w
eb
s
cr
ap
er
.
A
f
e
w
lea
f
n
o
d
es
w
er
e
u
s
ed
to
r
ep
r
esen
t
th
e
ch
o
s
e
n
ca
teg
o
r
ies
f
r
o
m
t
h
e
b
r
o
w
s
e
tr
ee
o
f
th
e
w
eb
s
ite.
T
ab
le
1
p
r
esen
ts
t
h
e
d
escr
ip
tio
n
o
f
th
e
t
w
o
co
r
p
o
r
a
s
elec
ted
f
o
r
th
is
r
esear
ch
w
h
ic
h
a
r
e
f
r
esh
f
o
o
d
an
d
h
o
u
s
e
h
o
ld
p
r
o
d
u
cts
d
ata
s
ets.
T
h
e
f
iv
e
ca
teg
o
r
ies
u
n
d
er
Fre
s
h
Fo
o
d
d
at
a
s
et
ar
e
f
r
esh
m
ea
t
&
p
o
u
ltr
y
,
f
is
h
&
s
ea
f
o
o
d
,
b
ak
er
y
,
f
r
es
h
f
r
u
its
,
a
n
d
n
o
o
d
les.
O
n
t
h
e
o
t
h
er
h
an
d
,
th
e
f
iv
e
ca
teg
o
r
ies
u
n
d
er
Ho
u
s
eh
o
ld
d
ata
s
et
ar
e
to
ilet c
lean
er
,
air
f
r
es
h
e
n
er
,
f
lo
o
r
clea
n
er
s
,
li
g
h
t b
u
lb
s
,
an
d
h
o
u
s
e
h
o
ld
s
u
n
d
r
ies.
T
ab
le
1
.
Su
m
m
ar
y
d
escr
ip
tio
n
o
f
d
ata
s
ets
D
a
t
a
se
t
C
a
t
e
g
o
r
y
I
n
st
a
n
c
e
N
u
mb
e
r
o
f
F
e
a
t
u
r
e
N
u
mb
e
r
o
f
F
e
a
t
u
r
e
a
f
t
e
r
F
e
a
t
u
r
e
S
e
l
e
c
t
i
o
n
F
r
e
sh
F
o
o
d
5
4
4
7
88
78
H
o
u
se
h
o
l
d
5
6
8
4
1
3
8
1
1
6
2
.
2
.
Resea
rc
h desi
g
n
T
h
er
e
w
er
e
s
e
v
er
al
s
tep
s
n
ee
d
to
b
e
d
o
n
e
in
th
i
s
r
esear
ch
b
ef
o
r
e
class
if
y
i
n
g
th
e
d
ata
as
p
r
esen
ted
in
Fig
u
r
e
1
.
T
h
e
s
tep
s
w
er
e
d
ata
ex
tr
ac
tio
n
,
d
ata
p
r
e
-
p
r
o
ce
s
s
i
n
g
,
f
ea
tu
r
e
e
x
tr
ac
tio
n
a
n
d
f
ea
t
u
r
e
s
elec
tio
n
.
T
h
ese
w
er
e
th
e
b
asic
p
r
o
ce
d
u
r
es
in
r
esear
c
h
r
elate
d
to
te
x
t
class
if
icatio
n
.
T
h
er
e
w
er
e
th
r
ee
p
r
ep
r
o
ce
s
s
in
g
s
tep
s
i
n
v
o
l
v
ed
a
f
ter
d
ata
e
x
tr
ac
tio
n
w
h
ich
w
er
e
to
k
e
n
iz
atio
n
,
s
to
p
w
o
r
d
r
e
m
o
v
a
l
a
n
d
s
te
m
m
i
n
g
[
1
5
]
.
T
h
e
d
ata
p
r
ep
r
o
ce
s
s
in
g
i
s
a
cr
u
cial
s
tep
to
e
n
s
u
r
e
t
h
e
d
ata
is
s
ta
n
d
ar
d
ized
an
d
in
a
p
r
o
p
er
f
o
r
m
.
T
h
e
s
tan
d
ar
d
ized
f
o
r
m
w
as
ac
h
iev
ed
a
f
ter
ap
p
ly
i
n
g
th
e
t
h
r
ee
p
r
ep
r
o
ce
s
s
in
g
s
tep
s
w
h
er
e
p
r
o
d
u
ct
d
escr
ip
tio
n
s
w
er
e
to
k
e
n
ized
i
n
to
w
o
r
d
s
at
f
ir
s
t.
T
h
en
,
s
to
p
w
o
r
d
s
w
er
e
r
em
o
v
ed
f
r
o
m
t
h
e
w
o
r
d
lis
t
an
d
th
e
r
e
m
a
in
i
n
g
w
o
r
d
s
w
er
e
s
te
m
m
ed
to
en
s
u
r
e
th
e
w
o
r
d
s
f
o
llo
w
ed
th
e
r
o
o
t
w
o
r
d
f
o
r
m
s
.
T
h
e
f
ea
t
u
r
e
ex
tr
a
ctio
n
an
d
s
elec
tio
n
ar
e
im
p
o
r
tan
t
to
m
a
k
e
s
u
r
e
th
e
d
ata
ar
e
w
ell
tr
an
s
f
o
r
m
ed
in
to
s
ig
n
i
f
ica
n
ce
an
d
g
o
o
d
f
ea
tu
r
es
b
ef
o
r
e
p
er
f
o
r
m
in
g
t
h
e
class
if
ica
tio
n
p
r
o
ce
s
s
[
1
6
]
.
T
h
e
s
elec
tio
n
o
f
f
ea
tu
r
es
m
a
y
af
f
ec
t
t
h
e
ac
cu
r
ac
y
o
f
a
class
i
f
icatio
n
m
o
d
el.
He
n
ce
,
th
e
r
esear
c
h
h
ad
u
ti
lized
th
e
b
ag
-
of
-
w
o
r
d
a
n
d
co
r
r
elatio
n
f
ea
t
u
r
e
s
elec
t
io
n
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
P
erfo
r
ma
n
ce
a
n
a
lysi
s
o
f su
p
ervis
ed
lea
r
n
in
g
mo
d
els
fo
r
…
(
N
o
r
s
ye
la
Mu
h
a
mma
d
N
o
o
r
Ma
th
iva
n
a
n
)
301
tech
n
iq
u
e
to
p
er
f
o
r
m
d
ata
e
x
tr
ac
tio
n
an
d
s
elec
tio
n
r
e
s
p
ec
tiv
e
l
y
.
T
h
en
,
t
h
e
ch
o
s
e
n
f
ea
t
u
r
es
w
er
e
u
s
ed
as i
n
p
u
ts
to
p
er
f
o
r
m
d
if
f
er
e
n
t c
las
s
i
f
icat
io
n
m
o
d
els
f
r
o
m
s
u
p
er
v
i
s
ed
lear
n
in
g
m
o
d
els.
Fig
u
r
e
1
.
Flo
w
c
h
ar
t o
f
t
h
e
R
es
ea
r
ch
Su
p
e
r
v
is
e
d
le
ar
n
in
g
m
o
d
el
is
u
s
ed
t
o
m
ak
e
p
r
e
d
ic
ti
o
n
s
b
as
ed
o
n
in
f
o
r
m
atio
n
a
b
o
u
t
th
e
ta
r
g
e
ts
an
d
th
e
f
ea
tu
r
es
o
f
d
a
ta
.
I
t
in
f
e
r
s
a
f
u
n
ctio
n
ac
co
r
d
in
g
t
o
a
g
iv
en
s
e
t
o
f
in
p
u
t
-
o
u
tp
u
t
d
a
ta
r
es
p
ec
t
iv
ely
.
No
r
m
ally
,
th
e
in
p
u
t
d
ata
p
r
o
v
i
d
es
a
s
et
o
f
o
b
s
e
r
v
ati
o
n
s
w
ith
w
h
ich
th
e
co
m
p
u
t
er
is
t
r
ain
ed
[
1
7
]
.
E
ac
h
o
b
s
e
r
v
ati
o
n
c
o
n
s
is
ts
o
f
a
n
in
p
u
t v
ec
t
o
r
an
d
a
d
es
ir
ed
o
u
tp
u
t v
alu
e.
A
s
u
p
e
r
v
is
e
d
l
ea
r
n
i
n
g
m
o
d
el
tr
ain
s
th
e
d
at
a
an
d
g
en
e
r
a
tes
a
g
en
e
r
al
r
u
le
o
r
f
u
n
cti
o
n
to
b
e
u
s
ed
f
o
r
p
r
e
d
ic
tin
g
o
r
class
if
y
in
g
n
e
w
in
p
u
ts
.
T
h
er
e
w
er
e
f
iv
e
s
u
p
e
r
v
is
e
d
lea
r
n
in
g
m
o
d
els
th
at
b
e
en
u
s
ed
in
t
h
e
s
tu
d
y
w
h
ich
ar
e
N
aïv
e
B
ay
es
,
K
-
Nea
r
est
N
eig
h
b
o
r
(
KNN
)
,
Dec
is
io
n
T
r
e
e,
Su
p
p
o
r
t
Ve
ct
o
r
M
ac
h
in
e
(
SVM
)
an
d
R
an
d
o
m
Fo
r
est.
Naïv
e
B
ay
e
s
is
a
clas
s
i
f
icatio
n
m
o
d
e
l
b
ased
o
n
B
a
y
es
th
eo
r
e
m
i
n
tr
o
d
u
ce
d
b
y
T
h
o
m
a
s
B
a
y
e
s
an
d
it
h
a
s
b
ee
n
u
s
ed
a
s
co
n
v
e
n
tio
n
al
p
ar
ad
ig
m
s
i
n
ce
l
ate
1
8
th
ce
n
tu
r
y
[
1
8
]
.
I
t is o
n
e
o
f
p
r
o
b
ab
ilis
tic
-
b
ased
cl
ass
i
f
ie
r
s
w
h
er
e
it p
r
ed
icts
th
e
p
r
o
b
ab
ilit
y
o
f
t
h
e
s
a
m
p
le
its
el
f
b
ef
o
r
e
ch
o
o
s
i
n
g
t
h
e
clas
s
w
it
h
h
ig
h
es
t
p
r
o
b
ab
ilit
y
g
i
v
en
t
h
e
o
b
s
er
v
atio
n
.
I
t
is
w
id
el
y
u
s
ed
i
n
tex
t
ca
te
g
o
r
izatio
n
,
s
en
ti
m
e
n
t
an
al
y
s
i
s
an
d
s
p
a
m
f
i
lter
in
g
[
1
5
]
.
T
h
e
alg
o
r
ith
m
f
o
r
Naï
v
e
B
ay
e
s
[
1
9
]
as sh
o
w
n
i
n
Fi
g
u
r
e
2
.
Fig
u
r
2
.
Naïv
e
B
a
y
es
A
l
g
o
r
it
h
m
KNN
i
s
t
h
e
f
u
n
d
a
m
en
tal
cla
s
s
i
f
ica
tio
n
m
o
d
el
to
clas
s
i
f
y
o
b
s
er
v
atio
n
s
ac
co
r
d
in
g
to
t
h
e
clo
s
e
s
t
tr
ain
i
n
g
ex
a
m
p
les
in
t
h
e
f
ea
t
u
r
e
s
p
ac
e
w
h
e
n
t
h
er
e
i
s
lit
tle
o
r
n
o
p
r
io
r
k
n
o
w
led
g
e
o
n
th
e
d
is
tr
ib
u
tio
n
o
f
t
h
e
d
ata
[
2
0
]
.
I
t
is
an
in
s
ta
n
ce
-
b
as
ed
lear
n
in
g
w
h
er
e
th
e
f
u
n
ctio
n
is
clo
s
e
to
lo
ca
l
v
alu
e
an
d
th
e
co
m
p
u
tat
io
n
s
ar
e
d
ef
er
r
ed
b
ef
o
r
e
th
e
class
if
y
i
n
g
p
r
o
ce
s
s
o
cc
u
r
s
.
B
asicall
y
,
t
h
e
r
u
le
h
o
ld
s
t
h
e
tr
ain
in
g
s
et
d
u
r
in
g
th
e
lear
n
in
g
p
r
o
ce
s
s
.
T
h
en
,
ea
ch
o
b
s
er
v
a
t
io
n
is
ass
ig
n
ed
to
a
cla
s
s
ac
co
r
d
in
g
to
t
h
e
m
aj
o
r
ity
lab
el
o
f
it
s
KNN
i
n
t
h
e
tr
ain
i
n
g
d
ataset.
A
s
a
m
p
le
s
h
o
u
ld
b
e
g
r
o
u
p
ed
in
to
its
s
i
m
ilar
s
u
r
r
o
u
n
d
i
n
g
s
a
m
p
le
s
.
T
h
u
s
,
t
h
e
n
ea
r
est
n
ei
g
h
b
o
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
8
,
No
.
3
,
Sep
tem
b
er
20
1
9
:
2
9
9
–
3
0
6
302
s
a
m
p
les
ca
n
b
e
co
n
s
id
er
ed
to
class
i
f
y
o
r
p
r
ed
ict
an
u
n
k
n
o
w
n
s
a
m
p
le.
T
h
e
alg
o
r
ith
m
f
o
r
KNN
[
2
1
]
as sh
o
w
n
i
n
Fi
g
u
r
e
3
.
Fig
u
r
e
3
.
K
-
Nea
r
est Ne
i
g
h
b
o
r
(
KNN)
A
l
g
o
r
ith
m
Dec
is
io
n
T
r
ee
is
a
m
o
d
el
w
i
th
f
lo
w
c
h
ar
t
-
li
k
e
s
tr
u
ct
u
r
e.
I
t
is
cr
ea
ted
b
y
a
tr
ee
an
d
a
s
et
o
f
r
u
le
s
r
ep
r
esen
tin
g
ea
ch
o
f
t
h
e
clas
s
es
f
r
o
m
a
d
ataset.
Dec
is
io
n
T
r
ee
c
o
n
s
is
ts
o
f
t
h
r
ee
m
ai
n
e
le
m
e
n
ts
w
h
ic
h
ar
e
in
ter
n
a
l
n
o
d
e,
b
r
an
ch
an
d
cla
s
s
lab
el
w
h
er
e
ea
ch
o
f
th
e
m
r
e
p
r
esen
ts
a
test
attr
ib
u
te,
a
test
o
u
tco
m
e
an
d
a
leaf
n
o
d
e
r
esp
ec
tiv
el
y
[
2
2
]
.
Fig
u
r
e
4
s
h
o
w
s
th
e
al
g
o
r
ith
m
f
o
r
Dec
is
io
n
T
r
ee
[
1
5
]
.
Fig
u
r
e
4
.
Dec
is
io
n
T
r
ee
A
lg
o
r
ith
m
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
P
erfo
r
ma
n
ce
a
n
a
lysi
s
o
f su
p
ervis
ed
lea
r
n
in
g
mo
d
els
fo
r
…
(
N
o
r
s
ye
la
Mu
h
a
mma
d
N
o
o
r
Ma
th
iva
n
a
n
)
303
Su
p
p
o
r
t
Vec
to
r
Ma
ch
i
n
e
(
S
VM
)
is
u
s
u
all
y
u
s
ed
f
o
r
cl
ass
i
f
icatio
n
a
n
d
w
as
in
tr
o
d
u
ce
d
[
2
3
]
.
I
t
w
o
r
k
s
b
ased
o
n
t
h
e
ca
lc
u
la
tio
n
o
f
m
ar
g
i
n
s
b
et
w
ee
n
t
h
e
class
es.
T
h
e
m
ar
g
i
n
s
ar
e
d
r
aw
n
to
m
i
n
i
m
ize
t
h
e
class
i
f
icatio
n
er
r
o
r
w
h
e
n
t
h
e
d
is
tan
ce
b
et
w
ee
n
th
e
m
ar
g
in
an
d
th
e
clas
s
es
i
s
a
m
a
x
i
m
u
m
.
SVM
h
ad
b
ee
n
ap
p
lied
in
to
v
ar
io
u
s
f
iel
d
s
o
f
s
tu
d
ie
s
s
u
ch
as
g
en
e
e
x
p
r
ess
io
n
,
te
x
t
class
i
f
icatio
n
an
d
i
m
a
g
e
id
en
ti
f
icat
io
n
[
2
4
]
.
T
h
is
m
o
d
el
is
c
o
n
s
id
er
ed
to
g
iv
e
g
o
o
d
g
en
er
aliza
tio
n
ac
cu
r
ac
y
,
b
u
t
it
m
a
y
ca
u
s
e
a
q
u
ad
r
atic
o
p
tim
izat
io
n
p
r
o
b
lem
w
it
h
b
o
u
n
d
co
n
s
tr
ai
n
ts
a
n
d
a
lack
o
f
lin
ea
r
eq
u
alit
y
in
t
h
e
tr
ain
i
n
g
p
r
o
ce
s
s
.
T
h
e
alg
o
r
ith
m
f
o
r
SVM
[
2
5
]
a
s
s
h
o
w
n
i
n
Fi
g
u
r
e
5
.
Fig
u
r
e
5
.
Su
p
p
o
r
t V
ec
to
r
Ma
c
h
in
e
(
S
VM
)
Alg
o
r
it
h
m
R
an
d
o
m
Fo
r
est
is
also
k
n
o
wn
as
t
h
e
en
s
e
m
b
le
o
f
d
ec
is
i
o
n
tr
ee
alg
o
r
ith
m
.
Fi
g
u
r
e
6
s
h
o
w
s
t
h
e
alg
o
r
ith
m
f
o
r
R
a
n
d
o
m
Fo
r
est
[
2
6
]
.
I
t
c
o
n
s
is
t
s
o
f
a
co
llectio
n
o
f
tr
ee
-
s
tr
u
ct
u
r
ed
class
if
ier
s
w
h
er
e
ea
ch
o
f
t
h
e
class
i
f
ier
s
i
s
a
n
i
n
d
ep
en
d
en
t
id
en
ticall
y
d
is
tr
ib
u
ted
r
an
d
o
m
v
ec
to
r
.
T
h
is
alg
o
r
it
h
m
ca
n
m
ain
tain
its
p
er
f
o
r
m
a
n
ce
ev
e
n
th
o
u
g
h
th
e
d
ata
co
n
s
is
t
s
o
f
a
lar
g
e
p
r
o
p
o
r
tio
n
o
f
m
i
s
s
i
n
g
v
al
u
es
[
2
7
]
.
A
ll
th
e
s
tep
s
w
er
e
co
m
p
u
ted
u
s
in
g
R
-
P
r
o
g
r
a
m
m
i
n
g
s
o
f
t
w
ar
e.
Fig
u
r
e
6
.
R
an
d
o
m
Fo
r
est
Alg
o
r
ith
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
8
,
No
.
3
,
Sep
tem
b
er
20
1
9
:
2
9
9
–
3
0
6
304
3.
RE
SU
L
T
S
A
ND
D
I
SCU
SS
I
O
N
T
h
e
ev
alu
atio
n
w
a
s
d
o
n
e
b
y
o
b
s
er
v
in
g
th
e
cla
s
s
i
f
icatio
n
r
esu
lt
s
o
f
f
iv
e
al
g
o
r
it
h
m
s
f
r
o
m
s
u
p
er
v
i
s
ed
lear
n
in
g
m
o
d
el.
T
h
e
an
al
y
s
is
w
a
s
m
ad
e
o
n
t
w
o
d
if
f
er
e
n
t
d
atasets
w
h
ich
w
er
e
Fre
s
h
f
o
o
d
an
d
Ho
u
s
e
h
o
ld
d
ata
s
ets
a
s
s
h
o
w
n
i
n
T
ab
le
2
.
T
h
e
h
i
g
h
e
s
t
ac
c
u
r
ac
y
f
o
r
th
e
d
ata
w
it
h
f
iv
e
ca
te
g
o
r
ies
w
as
p
er
f
o
r
m
ed
b
y
K
NN
m
o
d
el.
O
n
t
h
e
o
th
e
r
h
an
d
,
th
e
p
er
f
o
r
m
an
ce
o
f
R
an
d
o
m
Fo
r
est
m
o
d
el
w
as
h
ig
h
l
y
g
o
o
d
as
KN
N
m
o
d
el,
b
u
t
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
o
th
er
class
i
f
icatio
n
m
o
d
els
w
a
s
less
t
h
an
7
0
%.
B
esid
es
th
at,
th
e
r
esu
lt
f
r
o
m
Fre
s
h
Fo
o
d
d
ata
led
to
ap
p
r
o
x
i
m
atel
y
s
i
m
i
lar
co
n
clu
s
io
n
as
t
h
e
r
esu
l
t
o
b
tain
ed
f
r
o
m
Ho
u
s
eh
o
ld
d
ata.
T
h
e
h
ig
h
est
ac
c
u
r
ac
y
r
ate
to
class
i
f
y
th
e
d
ata
co
n
s
is
ted
o
f
f
i
v
e
ca
teg
o
r
ies
i
s
KNN
m
o
d
el
.
Sp
ec
if
icall
y
,
o
n
l
y
KNN
an
d
R
an
d
o
m
Fo
r
est
m
o
d
els
s
h
o
w
ed
g
o
o
d
ac
cu
r
ac
y
r
ates
co
m
p
ar
ed
to
o
th
er
cla
s
s
i
f
icatio
n
m
o
d
els.
T
h
e
Naïv
e
B
a
y
es
m
o
d
el
w
a
s
t
h
e
w
o
r
s
t
clas
s
i
f
i
er
a
m
o
n
g
t
h
e
f
i
v
e
al
g
o
r
ith
m
s
u
s
ed
i
n
th
e
s
t
u
d
y
to
cla
s
s
i
f
y
b
o
t
h
o
f
th
e
d
ata.
T
h
e
ex
ec
u
t
io
n
ti
m
e
f
o
r
ea
ch
o
f
t
h
e
clas
s
if
icatio
n
m
o
d
el
is
s
h
o
w
n
i
n
T
ab
le
3
.
Desp
ite
th
e
h
i
g
h
e
s
t
ac
cu
r
ac
y
r
ate
s
p
r
o
v
id
ed
b
y
K
NN
m
o
d
el
f
o
r
b
o
th
d
ata
s
ets,
it
al
s
o
th
e
f
a
s
tes
t
clas
s
i
f
ier
co
m
p
ar
ed
to
o
t
h
er
class
i
f
icatio
n
m
o
d
els
u
s
ed
i
n
t
h
e
s
tu
d
y
.
E
v
en
th
o
u
g
h
t,
th
e
p
er
f
o
r
m
an
ce
o
f
R
a
n
d
o
m
Fo
r
est
w
a
s
f
air
l
y
g
o
o
d
co
m
p
ar
ed
to
KNN
b
u
t
it
w
a
s
t
h
e
s
lo
w
est
clas
s
i
f
i
er
to
p
r
o
v
id
e
th
e
clas
s
if
icat
io
n
r
es
u
lts
a
m
o
n
g
th
e
f
iv
e
al
g
o
r
ith
m
s
.
T
ab
le
2
.
A
c
cu
r
ac
y
o
f
cla
s
s
i
f
ic
atio
n
m
o
d
els
M
e
t
h
o
d
D
a
t
a
se
t
H
o
u
se
h
o
l
d
F
r
e
sh
F
o
o
d
N
a
ï
v
e
B
a
y
e
s
1
6
.
9
9
1
4
.
0
7
K
N
N
9
4
.
6
6
8
2
.
9
6
D
e
c
i
si
o
n
T
r
e
e
8
5
.
4
4
6
7
.
4
1
S
V
M
6
9
.
4
2
4
4
.
4
4
R
a
n
d
o
m F
o
r
e
st
9
3
.
6
9
7
8
.
5
2
T
ab
le
3
.
A
cc
u
r
ac
y
o
f
cla
s
s
i
f
ic
atio
n
m
o
d
els
M
e
t
h
o
d
D
a
t
a
se
t
H
o
u
se
h
o
l
d
F
r
e
sh
F
o
o
d
N
a
ï
v
e
B
a
y
e
s
1
.
2
0
0
.
7
8
K
N
N
0
.
8
2
0
.
6
3
D
e
c
i
si
o
n
T
r
e
e
0
.
9
4
0
.
6
6
S
V
M
0
.
9
9
0
.
6
5
R
a
n
d
o
m F
o
r
e
st
1
.
5
1
1
.
1
7
Fro
m
th
e
r
esu
lts
,
it
w
as
o
b
v
i
o
u
s
th
at
KNN
m
o
d
el
o
u
tp
er
f
o
r
m
ed
o
th
er
s
u
p
er
v
is
ed
lear
n
i
n
g
m
o
d
el
s
.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
R
an
d
o
m
Fo
r
est
m
o
d
el
w
as
n
o
t
f
ar
b
e
h
in
d
t
h
e
KN
N
m
o
d
el
b
u
t
t
h
e
w
ea
k
n
e
s
es
o
f
t
h
e
m
o
d
el
ca
n
b
e
s
ee
n
in
ter
m
o
f
co
m
p
u
tat
io
n
ti
m
e.
T
h
is
r
e
s
u
lts
i
n
li
n
e
w
i
th
p
r
ev
io
u
s
s
t
u
d
y
b
y
r
ef
er
e
n
ce
[
2
8
]
w
h
er
ein
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
b
o
th
m
o
d
els
w
er
e
p
r
ef
er
ab
le
co
m
p
ar
ed
to
o
th
er
s
u
p
er
v
is
ed
lear
n
in
g
m
o
d
els
to
w
ar
d
b
r
ea
s
t
ca
n
ce
r
d
ata.
Me
an
w
h
ile,
s
ev
er
al
s
t
u
d
ies
h
ad
also
f
o
u
n
d
t
h
at
K
NN
m
o
d
el
is
s
u
p
er
io
r
in
class
i
f
y
in
g
d
i
f
f
er
en
t
k
i
n
d
o
f
d
ata
[
2
9
-
31]
.
Am
o
n
g
th
e
a
lg
o
r
it
h
m
s
b
ased
o
n
s
u
p
er
v
is
ed
lear
n
in
g
m
o
d
els
u
s
ed
in
th
e
s
tu
d
y
,
Naï
v
e
B
a
y
e
s
p
er
f
o
r
m
ed
n
o
t
as
g
o
o
d
as
t
h
e
o
t
h
er
alg
o
r
ith
m
s
.
I
t
is
p
r
o
v
ed
th
at
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
Naïv
e
B
a
y
es
m
o
d
el
is
af
f
ec
te
d
b
y
th
e
d
is
tr
ib
u
t
io
n
o
f
t
h
e
d
a
ta
[
3
2
]
.
No
r
m
all
y
,
it
p
er
f
o
r
m
e
d
w
ell
o
n
t
h
e
r
ea
l
-
w
o
r
ld
d
ata
w
h
er
e
t
h
e
n
a
tu
r
e
o
f
t
h
e
d
ata
ea
s
i
l
y
ch
a
n
g
es
o
v
er
th
e
ti
m
e.
Ho
w
e
v
er
,
t
h
e
d
at
a
u
s
ed
i
n
th
e
s
t
u
d
y
w
er
e
i
n
d
ep
en
d
en
t a
n
d
id
en
tica
ll
y
d
is
tr
ib
u
ted
d
ata.
4.
CO
NCLU
SI
O
N
T
h
e
p
a
p
er
p
r
esen
ts
co
m
p
ar
ati
v
e
ev
al
u
atio
n
o
f
f
iv
e
w
ell
-
k
n
o
w
n
a
lg
o
r
it
h
m
s
f
r
o
m
s
u
p
er
v
i
s
e
d
lear
n
in
g
m
o
d
el
f
o
r
t
h
e
p
r
o
b
le
m
r
elat
ed
to
e
-
co
m
m
er
ce
p
r
o
d
u
ct
ti
tles
cla
s
s
i
f
icatio
n
.
O
n
t
h
e
wh
o
le,
KNN
m
o
d
el
p
er
f
o
r
m
ed
t
h
e
b
est
a
m
o
n
g
t
h
e
f
iv
e
s
u
p
er
v
is
ed
lear
n
i
n
g
m
o
d
el
s
.
T
h
e
s
i
m
p
licit
y
o
f
t
h
e
m
o
d
el
s
u
its
t
h
e
r
eq
u
ir
e
m
en
t
to
class
if
y
a
s
h
o
r
t
tex
t
s
u
c
h
as
e
-
co
m
m
er
ce
p
r
o
d
u
ct
titl
es.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
KNN
m
o
d
el
ca
n
b
e
en
h
an
ce
d
b
y
i
n
v
esti
g
ati
n
g
t
h
e
o
p
ti
m
al
n
u
m
b
er
o
f
n
ei
g
h
b
o
r
s
(
K)
v
alu
e.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
e
r
esear
ch
is
f
u
ll
y
f
u
n
d
e
d
b
y
th
e
Un
i
v
er
s
i
t
y
T
ek
n
o
l
o
g
i
MA
R
A
an
d
Min
is
tr
y
o
f
E
d
u
ca
tio
n
Ma
la
y
s
ia
u
n
d
er
th
e
Gr
an
t
Sch
e
m
e
(
6
0
0
-
I
R
MI
/FR
GS 5
/3
(
1
2
0
/ 2
0
1
9
)
)
.
T
h
e
au
th
o
r
s
w
o
u
ld
l
ik
e
to
ex
p
r
ess
t
h
eir
d
ee
p
est g
r
atitu
d
e
to
th
e
Dep
ar
t
m
en
t o
f
Stat
is
tic
s
Ma
la
y
s
ia
f
o
r
p
r
o
v
id
in
g
k
n
o
w
led
g
e
a
n
d
d
ata
s
u
p
p
o
r
ts
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
P
erfo
r
ma
n
ce
a
n
a
lysi
s
o
f su
p
ervis
ed
lea
r
n
in
g
mo
d
els
fo
r
…
(
N
o
r
s
ye
la
Mu
h
a
mma
d
N
o
o
r
Ma
th
iva
n
a
n
)
305
RE
F
E
R
E
NC
E
S
[1
]
D.
Kim
,
S
.
L
e
e
,
a
n
d
J.
Ch
u
n
,
A
se
m
a
n
ti
c
c
las
si
f
ica
ti
o
n
m
o
d
e
l
f
o
r
e
-
c
a
talo
g
s,
in
:
P
ro
c
e
e
d
i
n
g
s
o
f
th
e
IEE
E
Co
n
f
e
re
n
c
e
o
n
E
-
C
o
m
m
e
r
c
e
,
2
0
0
4
.
[2
]
S
u
n
,
Ch
o
n
g
,
Na
ra
sim
h
a
n
Ra
m
p
a
ll
i,
F
ra
n
k
Ya
n
g
,
a
n
d
A
n
Ha
i
Do
a
n
.
"
Ch
im
e
ra
:
L
a
rg
e
-
sc
a
le
c
la
ss
if
ica
ti
o
n
u
sin
g
m
a
c
h
in
e
lea
rn
in
g
,
ru
les
,
a
n
d
c
ro
w
d
so
u
rc
i
n
g
.
“
P
ro
c
e
e
d
in
g
s
o
f
th
e
VL
DB E
n
d
o
wm
e
n
t
7
,
n
o
.
1
3
(2
0
1
4
).
[3
]
Hs
ian
g
-
F
u
Yu
,
C
h
ia
-
Hu
a
H
o
,
P
ra
k
a
sh
A
ru
n
a
c
h
a
la
m
,
M
a
n
a
s
S
o
m
a
i
y
a
,
a
n
d
Ch
i
h
-
Je
n
L
in
.
P
ro
d
u
c
t
ti
tl
e
c
las
si
f
ica
ti
o
n
v
e
rsu
s tex
t
c
las
si
f
ic
a
ti
o
n
.
T
e
c
h
n
ic
a
l
re
p
o
rt,
2
0
1
2
.
[4
]
M
.
W
.
L
ib
b
re
c
h
t
a
n
d
W
.
S
.
N
o
b
le.
“
M
a
c
h
i
n
e
lea
rn
in
g
a
p
p
li
c
a
ti
o
n
s
i
n
g
e
n
e
ti
c
s
a
n
d
g
e
n
o
m
ics
”
.
Na
tu
re
Re
v
ie
w
s
G
e
n
e
ti
c
s.1
6
:3
2
1
–
3
2
.
2
0
1
5
.
[5
]
D.
Zh
a
n
g
a
n
d
W
.
S
.
L
e
e
,
“
Qu
e
stio
n
c
las
sif
ica
ti
o
n
u
si
n
g
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
s,”
in
S
IG
IR,
p
p
.
2
6
–
3
2
,
2
0
0
3
.
[6
]
B.
Qu
,
G
.
Co
n
g
,
C
.
L
i,
A
.
S
u
n
,
a
n
d
H.
C
h
e
n
,
“
A
n
e
v
a
lu
a
ti
o
n
o
f
c
las
sif
ic
a
ti
o
n
m
o
d
e
ls
f
o
r
q
u
e
stio
n
t
o
p
ic
c
a
teg
o
riza
ti
o
n
,
”
Jo
u
rn
a
l
o
f
t
h
e
A
me
ric
a
n
S
o
c
iety
fo
r
In
fo
rm
a
t
io
n
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
,
v
o
l.
6
3
,
p
p
.
8
8
9
-
9
0
3
,
2
0
1
2
.
[7
]
L
u
k
a
s
Ga
lk
e
,
F
lo
rian
M
a
i,
A
lan
S
c
h
e
lt
e
n
,
De
n
n
is
Br
u
n
sc
h
,
a
n
d
A
n
sg
a
r
S
c
h
e
rp
.
“
Us
in
g
T
it
les
v
s.
F
u
ll
-
tex
t
a
s
S
o
u
rc
e
f
o
r
A
u
to
m
a
ted
S
e
m
a
n
ti
c
Do
c
u
m
e
n
t
A
n
n
o
tatio
n
”
.
In
K
-
CA
P
.
A
CM
,
2
0
:1
–
2
0
:4
,
2
0
1
7
.
[8
]
R.
Be
k
k
e
r
m
a
n
a
n
d
M
.
G
a
v
ish
,
“
Hig
h
-
p
re
c
isio
n
p
h
ra
se
-
b
a
se
d
d
o
c
u
m
e
n
t
c
las
si
f
ica
ti
o
n
o
n
a
m
o
d
e
rn
sc
a
le,”
in
KD
D,
2
0
1
1
.
[9
]
X.
-
H.
P
h
a
n
,
L
.
-
M
.
Ng
u
y
e
n
,
a
n
d
S
.
Ho
rig
u
c
h
i,
“
L
e
a
rn
in
g
to
c
las
sify
sh
o
rt
a
n
d
s
p
a
rse
tex
t
&
we
b
w
it
h
h
id
d
e
n
to
p
ics
f
ro
m
larg
e
-
sc
a
le d
a
ta co
ll
e
c
ti
o
n
s,
”
in
W
WW
,
p
p
.
9
1
–
1
0
0
,
2
0
0
8
.
[1
0
]
M
.
Ch
e
n
,
X
.
Jin
,
a
n
d
D
.
S
h
e
n
,
“
S
h
o
rt
tex
t
c
las
sif
i
c
a
ti
o
n
im
p
ro
v
e
d
b
y
lea
rn
in
g
m
u
lt
i
-
g
ra
n
u
larity
to
p
ics
,
”
in
IJCA
I,
p
p
.
1
7
7
6
–
1
7
8
,
2
0
1
1
.
[1
1
]
A
.
E.
M
o
h
a
m
e
d
,
“
Co
m
p
a
ra
ti
v
e
stu
d
y
o
f
f
o
u
r
su
p
e
rv
ise
d
m
a
c
h
in
e
lea
rn
in
g
tec
h
n
i
q
u
e
s
f
o
r
c
las
si
f
ica
ti
o
n
”
.
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
A
p
p
li
e
d
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
7
(
2
),
5
-
1
8
,
2
0
1
7
.
[1
2
]
R.
Ba
l
y
a
n
,
K.S
.
M
c
Ca
rth
y
a
n
d
D.
S
.
M
c
Na
m
a
ra
.
Co
m
b
in
in
g
M
a
c
h
in
e
L
e
a
rn
in
g
a
n
d
Na
tu
ra
l
L
a
n
g
u
a
g
e
P
ro
c
e
ss
in
g
to
A
ss
e
ss
L
it
e
ra
r
y
T
e
x
t
Co
m
p
re
h
e
n
sio
n
.
I
n
A
.
He
rsh
k
o
v
it
z
&
L
.
P
a
q
u
e
tt
e
(Ed
s.
),
I
n
P
r
o
c
e
e
d
in
g
s
o
f
th
e
1
0
t
h
In
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
Ed
u
c
a
ti
o
n
a
l
Da
ta
M
in
in
g
(EDM
),
W
u
h
a
n
,
Ch
i
n
a
:
In
ter
n
a
ti
o
n
a
l
Ed
u
c
a
ti
o
n
a
l
Da
ta
M
in
i
n
g
S
o
c
iety
,
2
0
1
7
.
[1
3
]
S
.
F
.
S
a
b
b
e
h
,
“
M
a
c
h
i
n
e
-
L
e
a
rn
in
g
T
e
c
h
n
iq
u
e
s
f
o
r
Cu
sto
m
e
r
Re
ten
ti
o
n
:
A
Co
m
p
a
ra
ti
v
e
S
tu
d
y
”
,
(
IJ
ACS
A)
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
Co
m
p
u
ter
S
c
ie
n
c
e
a
n
d
A
p
p
li
c
a
t
io
n
s
,
Vo
l.
9
,
N
o
.
2
,
2
0
1
8
.
[1
4
]
M
.
W
.
L
ib
b
re
c
h
t
a
n
d
W
.
S
.
No
b
le.
M
a
c
h
in
e
lea
rn
i
n
g
a
p
p
li
c
a
ti
o
n
s
in
g
e
n
e
ti
c
s
a
n
d
g
e
n
o
m
ics
.
N
a
tu
re
Re
v
ie
w
s
G
e
n
e
ti
c
s.1
6
:3
2
1
–
3
2
.
2
0
1
5
.
[1
5
]
Ay
o
n
De
y
.
“
M
a
c
h
in
e
Lea
rn
in
g
A
lg
o
rit
h
m
s:
A
Re
v
i
e
w
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
mp
u
te
r
S
c
ien
c
e
a
n
d
In
fo
rm
a
t
io
n
T
e
c
h
n
o
l
o
g
ies
,
Vo
l.
7
(3
),
1
1
7
4
-
1
1
7
9
,
2
0
1
6
.
[1
6
]
G
.
N.
Ra
m
a
d
e
v
i,
K.
U.
Ra
n
i
A
n
d
D.
L
a
v
a
n
y
a
.
Ev
a
lu
a
ti
o
n
o
f
Clas
s
if
iers
P
e
rf
o
r
m
a
n
c
e
u
sin
g
Re
sa
m
p
li
n
g
o
n
Bre
a
st
Ca
n
c
e
r
Da
ta.
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
S
c
ien
ti
fi
c
&
En
g
in
e
e
rin
g
Res
e
a
rc
h
,
Vo
l.
6
,
No
.
2
,
2
0
1
5
.
[1
7
]
R.
S
a
th
y
a
,
a
n
d
A
n
n
a
m
m
a
A
b
ra
h
a
m
,
“
Co
m
p
a
riso
n
o
f
S
u
p
e
rv
ise
d
a
n
d
Un
su
p
e
rv
ise
d
L
e
a
rn
in
g
Alg
o
rit
h
m
s
f
o
r
P
a
tt
e
r
n
Clas
sif
ic
a
ti
o
n
”
,
(
IJ
AR
AI)
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
d
Res
e
a
rc
h
in
Arti
fi
c
ia
l
In
tel
li
g
e
n
c
e
,
V
o
l.
2
,
N
o
.
2
,
2
0
1
3
.
[1
8
]
S
.
M
ich
a
lsk
i,
Ry
sz
a
rd
,
G
.
Ca
rb
o
n
e
ll
,
Ja
m
ie
a
n
d
T
.
M
.
M
i
tch
e
l
l,
M
a
c
h
in
e
lea
rn
in
g
:
A
n
A
rti
f
ici
a
l
In
telli
g
e
n
c
e
A
p
p
ro
a
c
h
.
M
o
rg
a
n
Ka
u
fm
a
n
n
,
1
9
8
5
.
[1
9
]
A
ja
y
S
.
P
a
ti
l,
a
n
d
B.
V.
P
a
w
a
r,
A
u
to
m
a
ted
Clas
si
f
ica
ti
o
n
o
f
W
e
b
S
it
e
s
u
sin
g
Na
iv
e
Ba
y
e
sia
n
A
lg
o
rit
h
m
,
IM
ECS
v
o
l
-
1
,
2
0
1
2
[2
0
]
De
v
ro
y
e
,
L
.
"
On
th
e
e
q
u
a
li
ty
o
f
Co
v
e
r
a
n
d
Ha
rt
in
n
e
a
re
st
n
e
ig
h
b
o
r
d
isc
rim
in
a
ti
o
n
"
,
IEE
E
T
ra
n
s.
Pa
tt
e
rn
An
a
l.
M
a
c
h
.
ln
tell
.
3
:
7
5
-
7
8
.
1
9
8
1
[2
1
]
N.S
u
g
u
n
a
,
a
n
d
K.T
h
a
n
u
sh
k
o
d
i
2
0
1
0
A
n
im
p
ro
v
e
d
K
-
N
e
a
re
st
n
e
ig
h
b
o
u
r
c
las
sif
ica
ti
o
n
u
sin
g
g
e
n
e
ti
c
a
lg
o
rit
h
m
IJCSI
Iss
u
e
4
,
Vo
l
-
7
p
p
1
8
-
2
1
.
[2
2
]
J.
Ha
n
,
J.
P
e
i
a
n
d
M
.
Ka
m
b
e
r,
Da
ta M
in
i
n
g
:
Co
n
c
e
p
ts an
d
T
e
c
h
n
iq
u
e
s,
3
r
d
e
d
.
El
se
v
ier
,
2
0
1
1
.
[2
3
]
C.
Co
rtes
a
n
d
V
.
V
a
p
n
ik
.
“
S
u
p
p
o
rt
V
e
c
to
r
Ne
tw
o
rk
s”
,
M
a
c
h
in
e
L
e
a
rn
in
g
,
2
0
:
2
7
3
-
2
9
7
,
1
9
9
5
.
[2
4
]
C.
D.
A
.
V
a
n
it
h
a
,
D.
De
v
a
ra
j,
a
n
d
M
.
V
e
n
k
a
tes
u
lu
,
“
G
e
n
e
Ex
p
re
ss
io
n
Da
ta
Clas
sif
ic
a
ti
o
n
Us
in
g
S
u
p
p
o
r
t
V
e
c
to
r
M
a
c
h
in
e
a
n
d
M
u
tu
a
l
I
n
f
o
rm
a
ti
o
n
-
b
a
se
d
G
e
n
e
S
e
lec
ti
o
n
,
”
Pro
c
e
d
i
a
Co
mp
u
ter
S
c
ien
c
e
,
2
0
1
5
.
[2
5
]
H.
Yu
a
n
d
S
.
Kim
,
“
S
V
M
T
u
t
o
r
ial:
Clas
sif
ica
ti
o
n
,
Re
g
re
ss
io
n
,
a
n
d
Ra
n
k
in
g
,
”
Ha
n
d
b
o
o
k
o
f
Na
tu
ra
l
Co
m
p
u
ti
n
g
,
2
0
0
9
.
[2
6
]
V
.
Y.
Ku
lk
a
rn
i
a
n
d
P
.
K.
S
i
n
h
a
,
“
Eff
e
c
ti
v
e
L
e
a
rn
in
g
a
n
d
Clas
sif
i
c
a
ti
o
n
u
sin
g
Ra
n
d
o
m
F
o
re
st
A
l
g
o
rit
h
m
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
r
n
a
l
o
f
E
n
g
i
n
e
e
rin
g
a
n
d
In
n
o
v
a
t
ive
T
e
c
h
n
o
lg
y
,
v
o
l.
3
,
n
o
.
1
1
,
p
p
.
2
6
7
-
2
7
3
,
2
0
1
4
.
G
o
p
a
lak
rish
n
a
M
u
rth
y
a
t
e
l.
,
“
P
e
rf
o
rm
a
n
c
e
a
n
a
ly
sis
a
n
d
e
v
a
lu
a
ti
o
n
o
f
d
if
f
e
re
n
t
d
a
ta
m
in
in
g
a
lg
o
rit
h
m
s
u
se
d
f
o
r
c
a
n
c
e
r
c
las
si
f
ica
ti
o
n
”
,
IJ
AR
AI
,
Vo
l,
N
o
.
5
,
2
0
1
3
.
[2
7
]
G
.
Krish
n
a
,
M
.
No
o
k
a
la,
N.
Ors
u
,
B.
K.
P
o
tt
u
m
u
th
u
,
a
n
d
S
.
B.
M
u
d
u
n
u
ri,
“
P
e
rf
o
rm
a
n
c
e
A
n
a
l
y
sis
a
n
d
Ev
a
lu
a
ti
o
n
o
f
Di
ff
e
re
n
t
Da
t
a
M
in
in
g
A
l
g
o
rit
h
m
s
u
se
d
f
o
r
Ca
n
c
e
r
Clas
si
f
ica
ti
o
n
,
”
(
IJ
AR
AI)
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
d
Res
e
a
rc
h
in
Arti
fi
c
ia
l
In
telli
g
e
n
c
e
,
2
0
1
3
.
[2
8
]
N.
M
.
N.
M
a
th
iv
a
n
a
n
,
N.
A
.
M
.
G
h
a
n
i,
a
n
d
R.
M
.
Ja
n
o
r,
“
Im
p
ro
v
in
g
Clas
sif
ic
a
ti
o
n
A
c
c
u
ra
c
y
U
sin
g
Clu
ste
rin
g
T
e
c
h
n
iq
u
e
,
”
Bu
ll
e
ti
n
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
a
n
d
In
f
o
rm
a
ti
c
s,
v
o
l.
7
,
n
o
.
3
,
p
p
.
4
6
5
-
4
7
0
,
2
0
1
8
.
[2
9
]
G
.
N.
Ra
m
a
d
e
v
i,
K.
U.
Ra
n
i,
a
n
d
D.
L
a
v
a
n
y
a
,
“
Ev
a
lu
a
ti
o
n
o
f
Clas
sif
ier
s
P
e
rf
o
r
m
a
n
c
e
u
sin
g
Re
sa
m
p
li
n
g
o
n
Bre
a
st
Ca
n
c
e
r
Da
ta,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
S
c
ien
ti
f
ic
&
En
g
in
e
e
rin
g
R
e
se
a
rc
h
,
v
o
l.
6
,
n
o
.
2
,
2
0
1
5
.
[3
0
]
X
.
S
h
a
o
,
H
.
L
i,
N.
W
a
n
g
,
a
n
d
Q.
Zh
a
n
g
,
“
Co
m
p
a
riso
n
o
f
d
if
f
e
re
n
t
c
las
si
f
ica
ti
o
n
m
e
th
o
d
s
f
o
r
a
n
a
ly
z
in
g
e
lec
tro
n
ic
n
o
se
d
a
t
a
t
o
c
h
a
ra
c
teriz
e
se
sa
m
e
o
il
s a
n
d
b
le
n
d
s,”
S
e
n
so
rs (S
w
it
z
e
rlan
d
),
2
0
1
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
8
,
No
.
3
,
Sep
tem
b
er
20
1
9
:
2
9
9
–
3
0
6
306
[3
1
]
D.
R.
Am
a
n
c
io
e
t
a
l.
,
“
A
s
y
ste
m
a
ti
c
c
o
m
p
a
riso
n
o
f
su
p
e
rv
ise
d
c
las
sif
iers
,
”
P
L
o
S
ON
E,
2
0
1
4
.
[3
2
]
P
.
Ho
rt
o
n
a
n
d
K.
Na
k
a
i,
“
Be
tt
e
r
p
re
d
icti
o
n
o
f
p
ro
tein
c
e
ll
u
lar
lo
c
a
li
z
a
ti
o
n
sites
w
it
h
th
e
k
n
e
a
re
st
n
e
ig
h
b
o
rs
c
las
si
f
ier.,
”
P
r
o
c
e
e
d
in
g
s/..
.
I
n
ter
n
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
In
tell
ig
e
n
t
S
y
ste
m
s
f
o
r
M
o
lec
u
lar
Bi
o
lo
g
y
;
IS
M
B.
In
tern
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
In
tell
ig
e
n
t
S
y
ste
m
s
f
o
r
M
o
lec
u
lar Bi
o
l
o
g
y
,
1
9
9
7
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
No
rsy
e
la
M
u
h
a
m
m
a
d
No
o
r
M
a
th
iv
a
n
a
n
is
n
o
w
a
d
o
c
to
ra
te
st
u
d
e
n
t
in
th
e
Ce
n
ter
f
o
r
S
tatisti
c
a
l
S
tu
d
ies
a
n
d
De
c
isio
n
S
c
ien
c
e
s,
F
a
c
u
lt
y
o
f
Co
m
p
u
ter
a
n
d
M
a
th
e
m
a
ti
c
a
l
S
c
ien
c
e
s,
Un
iv
e
r
siti
T
e
k
n
o
lo
g
i
M
A
R
A
,
M
a
la
y
sia
u
n
d
e
r
th
e
su
p
e
rv
isio
n
o
f
No
r
A
z
u
ra
M
d
.
G
h
a
n
i
a
n
d
Ro
z
iah
M
o
h
d
Ja
n
o
r.
He
r
re
se
a
rc
h
in
tere
st
re
late
d
to
b
ig
d
a
ta,
tex
t
m
in
in
g
a
n
d
m
a
c
h
in
e
lea
rn
in
g
.
E
-
m
a
il
:
s
y
e
la
m
o
h
d
n
o
o
r@g
m
a
il
.
c
o
m
No
r
A
z
u
ra
M
d
.
G
h
a
n
i
is
a
n
A
ss
o
c
iate
P
ro
f
e
ss
o
r
in
Ce
n
ter
f
o
r
S
tatisti
c
a
l
S
tu
d
ies
a
n
d
De
c
isio
n
S
c
ien
c
e
s,
F
a
c
u
lt
y
o
f
Co
m
p
u
ter
a
n
d
M
a
th
e
m
a
ti
c
a
l
S
c
ien
c
e
s,
Un
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
A
R
A
,
M
a
la
y
sia
.
S
h
e
is
a
l
so
He
a
d
o
f
Da
ta
Re
s
e
a
rc
h
Un
it
,
Re
se
a
rc
h
M
a
n
a
g
e
m
e
n
t
Ce
n
ter,
In
stit
u
te
Re
se
a
rc
h
M
a
n
a
g
e
m
e
n
t
&
In
n
o
v
a
ti
o
n
,
U
n
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
ARA
,
M
a
la
y
sia
a
n
d
V
ice
Ch
a
ir
IEE
E
Co
m
p
u
ter
S
o
c
iety
M
a
la
y
sia
Ch
a
p
ter.
He
r
e
x
p
e
rti
s
e
is
b
ig
d
a
ta,
sta
ti
stica
l
p
a
tt
e
r
n
re
c
o
g
n
it
io
n
a
n
d
f
o
re
n
sic
sta
ti
stics
.
E
-
m
a
il
:
a
z
u
ra
@t
m
s
k
.
u
it
m
.
e
d
u
.
m
y
Ro
z
iah
M
o
h
d
Ja
n
o
r
is
a
P
r
o
f
e
ss
o
r
o
f
S
tatisti
c
s
a
t
t
h
e
F
a
c
u
lt
y
o
f
Co
m
p
u
ter
a
n
d
M
a
th
e
m
a
ti
c
a
l
S
c
ien
c
e
s,
Un
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
A
R
A
(
UiT
M
),
M
a
la
y
sia
.
Cu
r
re
n
tl
y
sh
e
is
s
e
rv
in
g
a
s
th
e
A
s
sista
n
t
V
ice
Ch
a
n
c
e
ll
o
r
a
t
t
h
e
In
stit
u
te
Qu
a
li
ty
&
Kn
o
w
led
g
e
Ad
v
a
n
c
e
m
e
n
t,
UiT
M
a
n
d
sh
e
is
n
o
w
o
v
e
rse
e
in
g
a
ll
th
e
q
u
a
li
ty
in
it
iativ
e
s
o
f
th
e
u
n
iv
e
rsit
y
,
in
c
lu
d
i
n
g
in
stit
u
ti
o
n
a
l
a
c
c
re
d
it
a
ti
o
n
,
p
ro
g
ra
m
m
e
a
c
c
r
e
d
it
a
ti
o
n
,
q
u
a
li
t
y
e
x
c
e
ll
e
n
c
e
m
o
d
e
l,
q
u
a
li
ty
m
a
n
a
g
e
m
e
n
t
s
y
ste
m
s,
In
n
o
v
a
ti
o
n
@
W
o
rk
a
n
d
th
e
Un
iv
e
rsit
y
Ra
n
k
i
n
g
P
ro
jec
t.
S
in
c
e
2
0
1
8
,
sh
e
se
rv
e
s
a
s
th
e
P
re
sid
e
n
t
o
f
th
e
M
y
Q
AN
,
a
q
u
a
li
ty
a
ss
u
ra
n
c
e
n
e
tw
o
rk
f
o
r
a
ll
M
a
lay
sia
n
h
ig
h
e
r
e
d
u
c
a
ti
o
n
i
n
stit
u
ti
o
n
s.
E
-
m
a
il
:
ro
z
iah
m
j@u
it
m
.
e
d
u
.
m
y
Evaluation Warning : The document was created with Spire.PDF for Python.