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.
1
9
,
No
.
2
,
A
p
r
il
2
0
2
1
,
p
p
.
49
1
~
498
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
9
i
2
.
1
5
9
4
8
491
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
The
impo
rtance
of data
clas
sifica
tio
n using
ma
chine
l
ea
rning
metho
ds in
micro
a
rray
data
Aws Na
s
er
J
a
ber
1
,
K
o
hb
a
la
n M
o
o
rt
hy
2
,
L
o
g
ent
hira
n M
a
cha
p
3
,
Sa
f
a
a
i D
er
is
4
1
,2
Co
ll
e
g
e
o
f
Co
m
p
u
ti
n
g
a
n
d
A
p
p
li
e
d
S
c
ien
c
e
s,
F
a
c
u
lt
y
o
f
Co
m
p
u
ti
n
g
,
U
n
iv
e
rsit
i
M
a
lay
sia
P
a
h
a
n
g
,
M
a
lay
sia
3
De
p
a
rtme
n
t
o
f
Co
m
p
u
ti
n
g
a
n
d
I
n
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
,
T
u
n
k
u
Ab
d
u
l
Ra
h
m
a
n
U
n
iv
e
rsit
y
Co
l
leg
e
M
a
lay
sia
,
M
a
lay
sia
4
F
a
c
u
lt
y
o
f
Bi
o
e
n
g
in
e
e
rin
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
U
n
iv
e
rsiti
M
a
lay
sia
Ke
lan
tan
,
M
a
lay
sia
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
2
9
,
2
0
2
0
R
ev
is
ed
A
u
g
1
3
,
2
0
2
0
Acc
ep
ted
Au
g
2
9
,
2
0
2
0
Th
e
d
e
tec
ti
o
n
o
f
g
e
n
e
ti
c
m
u
tati
o
n
s
h
a
s
a
tt
ra
c
ted
g
lo
b
a
l
a
tt
e
n
ti
o
n
.
se
v
e
ra
l
m
e
th
o
d
s
h
a
v
e
p
r
o
p
o
se
d
to
d
e
tec
t
d
ise
a
se
s
su
c
h
a
s
c
a
n
c
e
rs
a
n
d
tu
m
o
u
rs.
On
e
o
f
t
h
e
m
is
m
icro
a
rra
y
s,
wh
ich
is
a
ty
p
e
o
f
re
p
re
se
n
tati
o
n
fo
r
g
e
n
e
e
x
p
re
ss
io
n
th
a
t
is
h
e
lp
f
u
l
in
d
iag
n
o
sis.
T
o
u
n
lea
sh
th
e
fu
ll
p
o
ten
ti
a
l
o
f
m
icro
a
rra
y
s,
m
a
c
h
in
e
-
lea
rn
in
g
a
lg
o
rit
h
m
s
a
n
d
g
e
n
e
se
lec
ti
o
n
m
e
th
o
d
s
c
a
n
b
e
imp
lem
e
n
ted
to
fa
c
il
it
a
te
p
r
o
c
e
ss
in
g
o
n
m
icro
a
rra
y
s
a
n
d
t
o
o
v
e
rc
o
m
e
o
th
e
r
p
o
ten
ti
a
l
c
h
a
ll
e
n
g
e
s.
On
e
o
f
t
h
e
se
c
h
a
ll
e
n
g
e
s
in
v
o
l
v
e
s
h
i
g
h
d
ime
n
sio
n
a
l
d
a
ta
th
a
t
a
re
re
d
u
n
d
a
n
t,
irrele
v
a
n
t,
a
n
d
n
o
isy
.
To
a
ll
e
v
iate
th
is
p
r
o
b
lem
,
th
is
re
p
re
se
n
tatio
n
sh
o
u
l
d
b
e
sim
p
li
fied
.
F
o
r
e
x
a
m
p
le,
t
h
e
fe
a
tu
re
se
lec
ti
o
n
p
ro
c
e
ss
c
a
n
b
e
imp
lem
e
n
ted
b
y
r
e
d
u
c
in
g
th
e
n
u
m
b
e
r
o
f
fe
a
tu
re
s
a
d
o
p
ted
in
c
lu
ste
rin
g
a
n
d
c
las
sifica
ti
o
n
.
A
s
u
b
se
t
o
f
g
e
n
e
s c
a
n
b
e
se
lec
ted
fro
m
a
p
o
o
l
o
f
g
e
n
e
e
x
p
re
ss
io
n
d
a
ta
re
c
o
rd
e
d
o
n
DN
A
m
icro
-
a
rra
y
s.
Th
is
p
a
p
e
r
re
v
iew
s
e
x
isti
n
g
c
las
sifica
ti
o
n
tec
h
n
iq
u
e
s
a
n
d
g
e
n
e
se
lec
ti
o
n
m
e
th
o
d
s
.
T
h
e
e
ffe
c
ti
v
e
n
e
ss
o
f
e
m
e
rg
in
g
tec
h
n
iq
u
e
s,
su
c
h
a
s
th
e
sw
a
rm
in
telli
g
e
n
c
e
te
c
h
n
iq
u
e
in
fe
a
tu
re
se
lec
ti
o
n
a
n
d
c
las
sifica
ti
o
n
in
m
icro
a
rra
y
s,
a
re
re
p
o
rted
a
s
we
ll
.
Th
e
se
e
m
e
rg
in
g
tec
h
n
i
q
u
e
s
c
a
n
b
e
u
se
d
in
d
e
tec
ti
n
g
c
a
n
c
e
r.
Th
e
sw
a
rm
in
telli
g
e
n
c
e
tec
h
n
iq
u
e
c
a
n
b
e
c
o
m
b
i
n
e
d
wi
th
o
t
h
e
r
sta
ti
stic
a
l
m
e
th
o
d
s
fo
r
a
tt
a
in
i
n
g
b
e
tt
e
r
re
su
lt
s
.
K
ey
w
o
r
d
s
:
C
an
ce
r
s
DNA
Gen
e
ex
p
r
ess
io
n
Ma
ch
in
e
lear
n
in
g
Mic
r
o
ar
r
ay
s
R
NA
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
:
Ko
h
b
alan
Mo
o
r
th
y
C
o
lleg
e
o
f
C
o
m
p
u
tin
g
an
d
Ap
p
lied
Scien
ce
s
,
Facu
lty
o
f
C
o
m
p
u
ti
n
g
,
Un
iv
er
s
iti Ma
lay
s
ia
Pah
an
g
Ku
an
tan
,
Pah
an
g
2
6
3
0
0
,
Ma
la
y
s
ia
E
m
ail:
k
o
h
b
alan
@
u
m
k
.
ed
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
B
io
in
f
o
r
m
atics
in
v
o
lv
es
th
e
u
s
e
o
f
c
o
m
p
u
ter
s
in
m
an
a
g
in
g
b
io
lo
g
ical
in
f
o
r
m
atio
n
[
1
]
.
I
n
g
e
n
er
al,
B
io
in
f
o
r
m
atics
in
v
o
lv
es
m
icr
o
ar
r
ay
s
class
if
icatio
n
,
o
r
g
an
iz
atio
n
,
an
d
in
ter
p
r
etatio
n
.
T
h
is
tech
n
o
lo
g
y
ca
n
b
e
em
p
lo
y
ed
t
o
s
o
lv
e
v
a
r
io
u
s
p
r
o
b
lem
s
r
elate
d
to
th
e
b
i
o
lo
g
ical
f
ield
.
Fo
r
ex
a
m
p
le,
th
e
p
r
ed
ic
tio
n
p
r
o
ce
s
s
ca
n
b
e
u
s
ed
to
co
n
tr
o
l
an
d
p
r
e
v
en
t
m
an
y
d
is
ea
s
es
s
u
ch
as
C
an
ce
r
.
T
h
e
p
r
o
ce
s
s
ca
n
also
b
e
u
s
ed
to
d
is
co
v
e
r
n
ew
d
is
ea
s
e
m
ar
k
er
s
.
Dete
ctio
n
o
f
m
u
tatio
n
s
in
g
e
n
e
ex
p
r
e
s
s
io
n
p
atter
n
s
wo
u
ld
ess
en
tially
lead
to
th
e
d
ev
elo
p
m
e
n
t
o
f
a
n
ef
f
icien
t
t
h
er
ap
y
m
eth
o
d
[
2
]
.
T
h
e
g
e
n
e
co
n
tr
o
ls
ce
ll
d
ev
elo
p
m
e
n
t,
a
n
d
m
alf
u
n
ctio
n
o
f
g
en
es
lead
s
to
tu
m
o
u
r
f
o
r
m
ati
o
n
o
r
ca
n
ce
r
.
Deo
x
y
r
ib
o
n
u
clei
c
ac
id
(
DNA)
m
icr
o
ar
r
ay
a
p
p
r
o
ac
h
is
a
p
o
wer
f
u
l
ap
p
r
o
ac
h
th
at
h
elp
s
ex
p
lo
r
e
th
e
g
en
etic
d
ef
ec
ts
in
th
e
h
u
m
an
b
o
d
y
[
3
]
.
Fo
r
ex
am
p
le,
m
icr
o
ar
r
ay
tech
n
o
lo
g
y
h
as
led
to
s
u
cc
ess
f
u
l
ca
n
ce
r
d
iag
n
o
s
is
[
4
,
5
]
.
Ge
n
e
ex
p
r
ess
io
n
s
tu
d
ies
th
at
in
v
o
lv
e
g
en
e
s
elec
tio
n
,
class
if
icatio
n
an
d
clu
s
ter
in
g
h
av
e
b
ee
n
ca
r
r
ied
o
u
t
[
6
]
.
A
s
u
itab
le
h
y
b
r
id
s
y
s
tem
in
b
io
in
f
o
r
m
atics
h
as
b
ee
n
d
ev
elo
p
e
d
to
d
etec
t c
a
n
ce
r
(
g
e
n
e
m
u
tatio
n
)
an
d
o
th
e
r
d
is
ea
s
es in
a
m
o
r
e
ac
c
u
r
ate
m
an
n
er
[
7
]
.
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 Co
n
tr
o
l
,
Vo
l.
1
9
,
No
.
2
,
Ap
r
il
202
1
:
49
1
-
498
492
2.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
C
an
ce
r
in
v
o
lv
es
ab
n
o
r
m
al
ce
ll
-
g
r
o
wth
s
,
wh
ich
is
f
atal
if
it
i
s
ig
n
o
r
ed
as
th
e
d
ev
elo
p
ed
tu
m
o
u
r
m
ay
s
p
r
ea
d
to
o
th
er
b
o
d
y
p
ar
ts
v
ia
b
lo
o
d
s
tr
ea
m
[
8
]
.
T
h
er
e
ar
e
s
ev
er
al
co
m
m
o
n
ca
n
ce
r
s
:
lu
n
g
,
p
r
o
s
tate,
b
r
ea
s
t
,
an
d
o
r
al
ca
n
ce
r
s
an
d
co
lo
n
s
[
9
]
.
A
n
ex
am
p
le
o
f
th
e
ca
n
ce
r
lev
el
s
h
o
wn
in
Fig
u
r
e
1
,
an
d
f
o
r
th
i
s
,
we
n
ee
d
to
k
n
o
w
wh
at
th
e
DNA
m
icr
o
ar
r
a
y
tec
h
n
o
lo
g
y
an
d
wh
at
k
in
d
th
e
m
a
ch
in
e
is
lear
n
in
g
t
h
at
ap
p
lied
t
o
th
e
m
icr
o
a
r
r
ay
.
Fig
u
r
e
1
.
C
an
ce
r
p
r
o
g
r
ess
io
n
i
n
th
e
co
lo
n
2
.
1
.
M
icro
a
rr
a
y
t
ec
hn
o
lo
g
y
I
n
B
io
lo
g
y
,
DNA
is
th
e
b
lu
ep
r
in
t
o
f
an
o
r
g
a
n
is
m
an
d
th
er
e
f
o
r
e
it
h
as
all
th
e
in
f
o
r
m
atio
n
n
ec
ess
ar
y
f
o
r
th
e
b
io
lo
g
ical
p
r
o
ce
s
s
.
W
h
en
it
co
m
es
to
c
o
m
p
u
tat
io
n
al
b
io
lo
g
y
,
th
is
in
f
o
r
m
atio
n
is
r
eq
u
ir
ed
f
o
r
p
r
ed
ictio
n
,
an
al
y
s
is
an
d
s
o
m
u
ch
m
o
r
e.
Hen
ce
,
th
is
in
f
o
r
m
atio
n
is
r
eq
u
ir
ed
to
b
e
p
r
esen
t
in
a
f
o
r
m
wh
er
e
co
m
p
u
tatio
n
ally
r
elev
a
n
t
f
o
r
p
r
o
ce
s
s
in
g
a
n
d
a
n
aly
s
is
.
T
h
e
r
ef
o
r
e,
g
e
n
e
e
x
p
r
ess
io
n
p
r
o
f
iles
in
th
e
f
o
r
m
o
f
n
u
m
er
ical
r
ep
r
esen
tatio
n
ar
e
u
s
ed
to
p
er
f
o
r
m
f
e
atu
r
e
s
elec
tio
n
,
an
d
class
if
icatio
n
.
Mic
r
o
ar
r
ay
tech
n
o
l
o
g
y
is
th
e
s
o
lu
tio
n
to
s
u
c
h
a
r
e
q
u
ir
e
m
en
t.
DNA
m
icr
o
ar
r
ay
(
also
co
m
m
o
n
l
y
k
n
o
wn
as
DNA
ch
ip
o
r
b
io
ch
ip
)
ca
n
b
e
ad
ap
ted
to
r
ev
ea
l
th
e
ex
p
r
ess
io
n
lev
els
o
f
m
an
y
g
en
es
in
a
s
in
g
le
r
ea
ctio
n
co
n
cu
r
r
en
tl
y
[
1
0
]
.
Firstl
y
,
th
e
s
tr
u
ctu
r
e
o
f
th
e
p
r
o
tein
is
d
if
f
er
en
t
f
r
o
m
t
h
e
s
tr
u
ctu
r
e
o
f
th
e
g
en
e
an
d
its
an
aly
s
is
is
s
till
d
if
f
icu
lt.
T
h
er
ef
o
r
e,
th
e
an
aly
s
is
o
f
th
o
u
s
an
d
s
o
f
p
r
o
tein
s
will
tak
e
a
g
r
ea
t
d
ea
l
o
f
tim
e.
W
e
also
s
aw
th
at
o
n
e
am
in
o
ac
id
ca
n
b
e
en
co
d
ed
b
y
s
ev
er
al
co
d
o
n
s
,
s
eq
u
en
ce
o
f
am
in
o
ac
id
s
in
th
e
p
r
o
tein
W
e
will
h
av
e
s
ev
er
al
p
r
o
b
a
b
ilit
ies
f
o
r
th
e
g
en
e
f
o
r
m
u
la
th
at
p
r
o
d
u
ce
d
th
is
p
r
o
tein
.
T
h
e
ea
s
iest
way
is
to
ex
tr
ac
t
t
h
e
m
R
NA
in
th
e
c
ell
an
d
m
ea
s
u
r
e
its
p
er
ce
n
tag
e.
Gen
e
r
ally
,
th
e
h
y
b
r
id
izatio
n
p
r
in
cip
le
is
u
s
ed
in
Mic
r
o
ar
r
ay
tech
n
o
lo
g
y
to
m
ea
s
u
r
e
th
e
g
en
e
ex
p
r
ess
io
n
lev
els in
th
e
h
u
m
a
n
b
o
d
y
[
1
1
]
.
Fig
u
r
e
2
s
h
o
ws
th
e
b
asic
p
r
o
ce
s
s
in
v
o
lv
ed
in
m
icr
o
ar
r
a
y
t
ec
h
n
o
lo
g
y
.
T
o
co
n
d
u
ct
g
e
n
e
ex
p
r
ess
io
n
p
r
o
f
ilin
g
,
DNA
s
am
p
le
an
d
co
n
tr
o
l
s
am
p
le
f
r
o
m
a
p
atien
t
is
o
b
tain
ed
.
T
h
en
,
DNA
in
th
e
s
am
p
le
is
d
en
atu
r
ed
in
to
s
in
g
le
-
s
tr
an
d
ed
m
o
lecu
le
s
.
Af
ter
th
at,
th
e
s
in
g
le
-
s
tr
an
d
ed
m
o
lecu
les
ar
e
c
u
t
in
to
s
m
a
ller
f
r
ag
m
en
ts
an
d
th
en
lab
el
it
with
a
f
lu
o
r
esce
n
t
d
y
e.
T
h
e
g
r
ee
n
d
y
e
is
f
o
r
th
e
co
n
tr
o
l
s
am
p
le
an
d
r
ed
d
y
e
is
f
o
r
a
n
o
r
m
al
s
am
p
le.
B
o
th
s
am
p
les
ar
e
in
s
er
ted
in
to
th
e
c
h
ip
to
h
y
b
r
i
d
i
ze
o
r
b
in
d
with
th
e
s
y
n
th
etic
DNA
o
n
th
e
ch
ip
.
Af
ter
th
e
h
y
b
r
id
izatio
n
,
th
e
g
en
e
ex
p
r
ess
io
n
ca
n
b
e
i
d
en
tif
ied
th
r
o
u
g
h
th
e
ch
a
n
g
es
o
f
c
o
lo
u
r
o
n
th
e
ch
ip
.
T
h
er
ef
o
r
e,
th
is
tech
n
o
lo
g
y
c
an
b
e
u
s
ed
in
ca
n
ce
r
d
iag
n
o
s
is
an
d
d
r
u
g
r
esp
o
n
s
e
[
1
2
]
.
T
h
u
s
,
v
ia
m
ac
h
in
e
le
ar
n
in
g
,
s
ig
n
if
ican
t
in
f
o
r
m
ati
o
n
ab
o
u
t
g
en
es
r
ep
r
esen
tin
g
a
d
is
ea
s
e
s
tate
an
d
th
o
s
e
h
ig
h
ly
ass
o
ciate
d
g
en
es
th
at
s
h
ar
ed
b
io
l
o
g
ical
f
ea
tu
r
es
ca
n
b
e
ex
tr
ac
te
d
[
1
3
]
.
An
ac
cu
r
ate
ca
n
ce
r
d
ia
g
n
o
s
is
ca
n
b
e
attain
ed
b
y
e
x
ec
u
tin
g
th
e
m
icr
o
ar
r
ay
d
ata
class
if
icatio
n
b
y
s
im
p
ly
b
u
ild
i
n
g
class
if
ier
s
to
co
m
p
ar
e
th
e
g
en
e
ex
p
r
ess
io
n
p
r
o
f
iles
o
f
tis
s
u
es
o
f
k
n
o
wn
a
n
d
u
n
k
n
o
wn
ca
n
ce
r
s
tatu
s
[
1
4
]
.
As
a
r
esu
lt,
th
e
class
if
icatio
n
p
r
o
ce
s
s
co
u
ld
b
e
m
is
lead
in
g
d
u
e
to
th
e
e
x
is
ten
ce
o
f
n
o
is
y
a
n
d
ir
r
elev
an
t
d
ata.
T
h
er
ef
o
r
e,
a
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
s
h
o
u
l
d
b
e
d
ev
is
ed
to
r
ed
u
ce
th
e
s
ize
o
f
th
e
f
ea
tu
r
e
s
et,
o
r
g
en
e
s
et
[
1
5
]
.
I
n
g
en
e
r
al,
a
m
icr
o
ar
r
ay
d
ia
g
n
o
s
is
p
r
o
ce
s
s
in
v
o
lv
es
f
ea
t
u
r
e
s
elec
tio
n
an
d
class
if
icatio
n
[
1
6
]
.
T
o
u
p
d
ate,
m
an
y
m
ac
h
in
e
le
ar
n
in
g
al
g
o
r
ith
m
s
h
a
v
e
b
ee
n
d
ev
elo
p
e
d
f
o
r
d
etec
tin
g
m
u
t
atio
n
s
,
e.
g
.
,
ANN,
SVM,
clu
s
ter
in
g
,
a
n
d
s
war
m
i
n
tellig
en
ce
alg
o
r
ith
m
.
B
y
u
s
in
g
th
ese
m
et
h
o
d
s
,
an
o
p
tim
al
s
u
b
s
et
o
f
g
e
n
es
ca
n
th
en
b
e
c
h
o
s
en
to
b
u
ild
a
class
if
icatio
n
m
o
d
el.
2
.
2
.
F
ea
t
ure
s
elec
t
io
n t
ec
hn
iqu
e
s
T
h
er
e
ar
e
th
r
ee
f
ea
tu
r
e
s
e
lec
tio
n
tech
n
iq
u
es
in
class
if
icatio
n
,
i.e
.
,
f
ilter
,
wr
a
p
p
er
,
an
d
em
b
ed
d
e
d
m
eth
o
d
s
as
s
h
o
wn
in
Fig
u
r
e
3
.
Fil
ter
b
ased
ap
p
r
o
ac
h
es
ar
e
well
k
n
o
wn
f
o
r
d
ata
f
ilter
in
g
o
r
p
r
e
-
p
r
o
ce
s
s
in
g
t
o
r
an
k
t
h
e
g
e
n
es
an
d
th
en
th
e
h
ig
h
ly
r
an
k
e
d
g
e
n
es
will
b
e
u
s
e
d
in
f
u
r
th
e
r
a
n
al
y
s
is
.
T
h
en
f
o
r
th
e
wr
ap
p
er
-
b
ased
m
eth
o
d
,
g
e
n
e
s
elec
tio
n
is
d
o
n
e
u
s
in
g
th
e
m
ac
h
in
e
lea
r
n
in
g
m
eth
o
d
a
n
d
u
s
es
cr
o
s
s
-
v
alid
atio
n
to
ass
ess
th
e
f
ea
tu
r
e
s
u
b
s
et
s
co
r
e
.
W
h
er
ea
s
em
b
ed
d
ed
b
ased
.
Ho
we
v
er
,
m
icr
o
ar
r
ay
d
ata
co
n
tain
m
a
n
y
n
o
n
-
s
ig
n
if
ican
t
f
ea
tu
r
es th
at
w
o
u
ld
d
eg
r
a
d
e
th
e
p
er
f
o
r
m
an
ce
o
f
m
o
s
t o
f
th
e
l
ea
r
n
in
g
alg
o
r
ith
m
s
[
1
7
]
.
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
Th
e
imp
o
r
ta
n
ce
o
f d
a
ta
cla
s
s
ifica
tio
n
u
s
in
g
ma
c
h
in
e
lea
r
n
in
g
meth
o
d
s
in
micro
a
r
r
a
y
d
a
t
a
(
A
w
s
N
a
s
e
r
Ja
b
er
)
493
Fig
u
r
e
2
.
DNA
m
icr
o
a
r
r
ay
s
Fig
u
r
e
3
.
T
h
e
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
s
2
.
3
.
Dif
f
er
ent
m
et
ho
ds
o
f
f
e
a
t
ure
s
elec
t
io
n
No
r
m
aliza
tio
n
in
v
o
lv
es
r
ed
u
c
in
g
u
n
wa
n
ted
v
a
r
iatio
n
with
i
n
ar
r
ay
s
.
T
y
p
ical
ass
u
m
p
tio
n
s
m
ad
e
in
s
o
m
e
m
ajo
r
n
o
r
m
aliza
tio
n
m
eth
o
d
s
ar
e:
−
O
n
l
y
a
s
m
al
l
n
u
m
b
e
r
o
f
g
e
n
e
s
a
r
e
d
i
f
f
e
r
e
n
t
i
a
ll
y
e
x
p
r
e
s
s
e
d
i
n
te
r
m
s
o
f
c
o
n
d
i
t
i
o
n
.
−
A
n
n
o
t
a
t
i
o
n
:
T
h
is
p
r
o
c
e
s
s
i
n
v
o
lv
e
s
g
e
n
e
c
h
a
r
a
c
t
e
r
i
z
a
ti
o
n
.
−
S
u
m
m
a
r
i
z
a
ti
o
n
:
P
e
r
f
o
r
m
i
n
g
o
n
l
y
a
s
i
n
g
l
e
m
e
a
s
u
r
e
m
e
n
t
a
f
t
e
r
p
e
r
f
o
r
m
i
n
g
a
c
o
m
b
i
n
a
t
i
o
n
i
n
a
ce
r
t
a
i
n
m
a
n
n
e
r
−
S
t
a
ti
s
t
i
c
al
A
n
a
l
y
s
is
:
F
r
o
m
a
s
t
at
i
s
t
i
c
al
p
o
i
n
t
o
f
v
i
e
w
,
t
h
e
n
u
m
b
e
r
o
f
g
e
n
e
s
c
o
u
l
d
b
e
l
a
r
g
e
r
t
h
an
t
h
e
n
u
m
b
e
r
o
f
s
a
m
p
l
es
,
t
h
u
s
l
ea
d
i
n
g
t
o
f
a
u
l
t
y
c
l
a
s
s
i
f
i
ca
t
i
o
n
.
F
ea
t
u
r
e
s
el
e
c
tio
n
s
h
o
u
l
d
b
e
p
e
r
f
o
r
m
e
d
b
y
s
e
l
e
c
t
i
n
g
t
h
e
m
o
s
t
i
n
f
o
r
m
a
t
i
v
e
g
e
n
e
t
o
i
m
p
r
o
v
e
th
e
a
c
c
u
r
a
c
y
a
n
d
e
f
f
i
c
i
e
n
c
y
o
f
t
h
e
c
l
as
s
i
f
i
c
a
ti
o
n
p
r
o
c
e
s
s
a
n
d
t
o
a
d
d
r
e
s
s
t
h
e
p
r
o
b
l
e
m
o
f
d
i
m
e
n
s
i
o
n
a
l
i
t
y
.
−
B
i
o
l
o
g
i
ca
l
I
n
t
e
r
p
r
e
t
at
i
o
n
:
T
o
i
n
t
e
r
p
r
e
t
m
i
c
r
o
a
r
r
a
y
d
a
ta
,
o
n
e
m
u
s
t
h
a
v
e
a
n
a
d
e
q
u
a
t
e
n
u
m
b
e
r
o
f
r
e
p
l
i
c
a
te
m
e
a
s
u
r
e
m
e
n
ts
t
o
d
e
t
e
r
m
i
n
e
r
es
u
l
ts
t
h
at
h
a
v
e
r
e
a
l
p
r
e
d
i
c
ti
v
e
v
a
l
u
e
.
D
i
m
e
n
s
i
o
n
a
l
it
y
r
e
d
u
c
ti
o
n
i
s
t
h
e
r
e
f
o
r
e
e
s
s
e
n
t
i
a
l
.
I
n
m
icr
o
ar
r
ay
class
if
icatio
n
,
s
am
p
les
ar
e
class
if
ied
in
to
b
o
t
h
ab
n
o
r
m
al
(
ca
n
ce
r
)
an
d
n
o
r
m
al
d
atasets
b
ased
o
n
m
icr
o
a
r
r
ay
m
ea
s
u
r
e
m
en
ts
[
1
8
,
1
9
]
.
I
t
is
ch
allen
g
in
g
to
tr
ain
t
h
e
class
if
ier
s
o
n
s
u
ch
d
atasets
o
f
h
ig
h
d
im
en
s
io
n
ality
[
2
0
]
.
Pre
p
r
o
ce
s
s
in
g
is
an
ess
en
tial
s
tep
to
ad
d
r
ess
th
is
d
im
en
s
io
n
ality
p
r
o
b
lem
,
an
d
th
e
n
ap
p
ly
th
e
class
if
icatio
n
alg
o
r
ith
m
f
o
r
m
o
n
ito
r
in
g
m
o
d
el
c
o
m
p
lex
it
y
v
ia
r
e
g
u
lar
izatio
n
.
Ma
ch
in
e
lear
n
in
g
e
n
ab
les
a
s
y
s
tem
to
au
to
m
atica
lly
p
er
f
o
r
m
th
e
lear
n
in
g
p
r
o
ce
s
s
.
I
t
is
n
o
t
a
r
ea
l
lear
n
in
g
p
r
o
ce
s
s
;
h
o
wev
er
,
th
e
s
y
s
tem
ca
n
r
ec
o
g
n
ize
co
m
p
lex
d
ata
p
atter
n
s
an
d
m
ak
e
in
tellig
en
t
d
ec
is
io
n
s
b
ased
o
n
co
m
p
u
tatio
n
al
m
eth
o
d
s
.
C
las
s
if
icatio
n
is
a
p
r
o
ce
d
u
r
e
u
s
ed
to
ca
teg
o
r
ize
s
am
p
le
d
ata
in
to
a
f
ew
class
es.
So
m
e
p
o
p
u
lar
class
if
icatio
n
m
eth
o
d
s
em
p
lo
y
ed
in
d
ata
m
i
n
in
g
a
n
d
o
th
er
f
ield
s
ar
e
a
r
tifi
cial
n
eu
r
al
n
etwo
r
k
(
ANN)
,
d
ec
is
io
n
tr
ee
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
(
SVM)
an
d
s
war
m
in
tellig
en
ce
.
Ar
tific
ial
n
eu
r
al
n
etwo
r
k
(
ANN)
o
r
n
eu
r
al
n
etwo
r
k
(
NN)
is
a
m
eth
o
d
in
ar
tific
ial
in
tellig
en
ce
th
at
m
im
ics th
e
co
m
p
lex
p
r
o
ce
s
s
es a
s
in
th
e
h
u
m
an
b
r
ain
.
ANN
r
eq
u
ir
es a
h
u
g
e
n
u
m
b
er
o
f
u
n
its
’
co
llectio
n
th
at
is
in
ter
co
n
n
ec
ted
t
o
p
er
m
it
co
m
m
u
n
icatio
n
b
etwe
en
th
e
u
n
its
.
T
h
e
u
n
it
also
d
en
o
ted
as
n
o
d
es
o
r
n
eu
r
o
n
s
.
T
h
ey
ar
e
s
im
p
le
p
r
o
ce
s
s
er
s
f
u
n
ctio
n
in
p
ar
allel.
Ne
x
t
is
th
e
d
ec
is
io
n
tr
ee
m
eth
o
d
;
th
is
is
a
p
r
ed
ict
iv
e
m
o
d
ellin
g
to
o
l
th
at
f
alls
u
n
d
er
s
u
p
er
v
is
ed
lea
r
n
in
g
.
T
h
er
e
a
r
e
two
m
ain
en
t
ities
in
d
ec
is
io
n
tr
ee
ca
lled
n
o
d
es.
B
esid
es,
th
er
e
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 Co
n
tr
o
l
,
Vo
l.
1
9
,
No
.
2
,
Ap
r
il
202
1
:
49
1
-
498
494
ar
e
two
ty
p
es
o
f
d
ec
is
io
n
tr
ee
s
s
u
ch
as
clas
s
if
icatio
n
an
d
r
eg
r
ess
io
n
tr
ee
s
.
SVM
is
an
o
th
er
p
o
p
u
lar
s
u
p
e
r
v
is
ed
class
if
icatio
n
m
eth
o
d
.
T
h
e
b
asic
p
r
in
cip
le
o
f
SVM
is
,
cr
ea
tes
h
y
p
er
p
lan
e
th
at
s
ep
ar
at
es
th
e
d
ataset
in
to
class
es.
Fu
r
th
er
m
o
r
e,
th
e
s
war
m
in
telli
g
en
ce
m
eth
o
d
is
to
u
s
e
n
u
m
er
o
u
s
s
im
p
le
ag
en
ts
wit
h
n
o
r
u
le
to
in
ter
ac
t
lo
ca
lly
an
d
g
lo
b
ally
.
Po
p
u
lar
s
war
m
in
tellig
en
ce
alg
o
r
ith
m
s
ar
e
an
t
c
o
lo
n
y
o
p
tim
izatio
n
(
AC
O)
,
ar
tific
ial
b
ee
co
lo
n
y
o
p
tim
izatio
n
(
AB
C
)
,
a
n
d
p
ar
ticle
s
war
m
o
p
tim
izatio
n
(
PS
O)
.
3.
RE
L
AT
E
D
WO
RK
Sev
er
al
m
icr
o
ar
r
ay
a
p
p
licatio
n
s
h
av
e
b
ee
n
r
ep
o
r
ted
in
r
elat
ed
r
ev
iew
[
2
1
]
.
Ho
wev
er
,
m
ic
r
o
ar
r
ay
ca
n
b
e
h
y
b
r
id
ized
with
m
ac
h
in
e
lear
n
in
g
al
g
o
r
ith
m
s
s
u
ch
as
n
o
n
-
s
war
m
in
tellig
en
ce
a
n
d
s
war
m
in
tellig
en
ce
alg
o
r
ith
m
s
.
Af
ter
d
etec
tin
g
a
n
d
f
ilter
in
g
g
en
e
e
x
p
r
ess
io
n
d
atasets
,
s
am
p
les
s
h
o
u
ld
b
e
a
cc
u
r
ately
class
if
ied
in
to
k
n
o
wn
g
r
o
u
p
s
b
y
th
e
f
ea
tu
r
es
o
f
g
en
e
ex
p
r
ess
io
n
.
He
n
ce
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es
(
SVM)
,
p
r
ed
ictio
n
an
aly
s
is
o
f
m
icr
o
ar
r
ay
s
(
PAM)
,
class
if
icatio
n
an
d
r
e
g
r
ess
io
n
tr
ee
s
(
C
AR
T
)
,
K
n
ea
r
est
-
n
eig
h
b
o
r
(
K
-
NN
)
m
eth
o
d
s
ca
n
b
e
em
p
lo
y
ed
.
T
u
r
g
u
t,
et
a
l.,
ap
p
lied
a
m
ac
h
in
e
lear
n
in
g
class
if
ier
f
o
r
m
icr
o
a
r
r
ay
b
r
ea
s
t
ca
n
ce
r
.
First,
th
ey
p
er
f
o
r
m
t
h
e
r
ig
h
t
ty
p
es
o
f
m
ac
h
in
e
lear
n
in
g
alg
o
r
i
th
m
s
with
o
u
t
ap
p
ly
in
g
an
y
f
ea
tu
r
e
s
elec
tio
n
,
an
d
th
en
th
ey
u
s
ed
two
d
if
f
er
e
n
t
f
ea
tu
r
e
s
elec
tio
n
s
.
E
x
a
m
p
le
s
o
f
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
KNN,
SVM,
d
ec
is
io
n
tr
ee
s
,
ML
P,
r
an
d
o
m
f
o
r
est,
lo
g
is
tic
r
eg
r
ess
io
n
,
ad
a
b
o
o
s
t
an
d
g
r
ad
ien
t
b
o
o
s
tin
g
m
ac
h
in
e
[
2
2
]
.
T
h
ey
claim
ed
th
at
ML
P d
id
n
o
t im
p
r
o
v
e
ac
cu
r
ac
y
.
B
h
ar
ath
i,
A.
M.
Nata
r
ajan
m
in
im
ized
th
e
g
en
e
s
et
f
o
r
m
o
r
e
ac
cu
r
ate
class
if
icatio
n
u
s
in
g
ANOVA
[
2
3
]
.
T
h
e
r
an
k
in
g
o
f
a
g
e
n
e
was
co
m
p
u
ted
u
s
in
g
ANOV
A.
SVM
was
u
s
ed
as
a
class
if
ier
.
T
h
e
tech
n
iq
u
e
was
co
m
p
a
r
ed
with
th
e
T
-
test
class
if
ier
.
I
n
ter
esti
n
g
ly
,
th
e
h
y
b
r
id
izatio
n
tech
n
iq
u
e
o
f
ANOV
A
an
d
SVM
was
ac
cu
r
ate
ev
en
u
s
in
g
a
m
in
im
u
m
n
u
m
b
er
o
f
g
en
es.
W
h
ile,
an
o
th
er
r
esear
ch
p
r
o
p
o
s
ed
an
ar
tific
ial
im
m
u
n
e
r
ec
o
g
n
itio
n
s
y
s
tem
to
class
if
y
m
icr
o
ar
r
a
y
d
ata
(
ca
n
ce
r
,
d
is
ea
s
e
o
r
n
o
r
m
al
tis
s
u
e
s
)
[
2
4
]
.
T
h
e
r
esu
lt
was
th
en
c
o
m
p
ar
e
d
with
th
o
s
e
o
f
o
th
e
r
class
if
ie
r
s
.
I
n
AI
R
S,
a
m
em
o
r
y
ce
ll
is
u
s
ed
f
o
r
tr
ain
in
g
s
am
p
les
to
b
u
ild
a
class
if
ier
.
T
h
e
ex
p
er
im
en
t
was
ap
p
lied
to
co
lo
n
ca
n
c
er
,
b
r
ain
tu
m
o
u
r
,
an
d
n
i
n
e
tu
m
o
u
r
d
atasets
.
AI
R
S
p
er
f
o
r
m
ed
b
etter
th
an
o
th
er
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
s
s
u
ch
as KN
N,
On
eR,
an
d
Naïv
e
B
ay
es.
Kar
ay
ian
n
i,
et
a
l
.,
em
p
lo
y
e
d
th
e
f
u
zz
y
clu
s
ter
in
g
m
eth
o
d
with
v
iewp
o
in
ts
to
id
en
tif
y
u
n
lab
eled
s
am
p
les
[
2
4
]
.
T
h
e
clu
s
ter
s
ar
e
id
en
tifie
d
b
y
ca
lcu
latin
g
th
e
ex
p
r
ess
io
n
m
ea
n
o
f
ea
ch
f
e
atu
r
e
with
lab
elled
s
am
p
les.
T
h
is
tech
n
iq
u
e
was
ap
p
lied
to
b
r
ea
s
t
ca
n
ce
r
,
b
r
ai
n
ca
n
ce
r
,
AM
L
,
an
d
ML
L
d
ata
s
ets.
Su
d
ip
Ma
n
d
al
an
d
I
n
d
r
o
jit
B
an
er
jee
ap
p
lie
d
ANN
to
d
iag
n
o
s
e
an
d
d
et
ec
t
ca
n
ce
r
[
2
5
]
.
A
s
p
ec
ial
k
in
d
o
f
ANN
ca
lled
m
u
ltil
ay
er
f
ee
d
f
o
r
war
d
n
eu
r
al
n
etwo
r
k
(
ML
FF
)
was
u
s
ed
.
T
h
e
p
e
r
f
o
r
m
an
ce
o
f
AN
N
is
d
ep
en
d
en
t
o
n
p
ar
am
eter
s
s
u
ch
as
th
e
n
u
m
b
e
r
o
f
h
id
d
en
lay
er
s
,
n
u
m
b
er
o
f
n
o
d
es
an
d
weig
h
ts
.
Dif
f
er
e
n
t
d
atasets
co
n
s
is
t
in
g
o
f
b
r
ea
s
t
an
d
lu
n
g
ca
n
ce
r
o
u
s
ce
lls
wer
e
em
p
lo
y
ed
.
T
wo
an
aly
s
es
wer
e
p
er
f
o
r
m
e
d
:
cr
o
s
s
-
v
alid
atio
n
a
n
d
n
ew
d
ataset
test
in
g
.
Data
s
ets
wer
e
d
iv
id
ed
in
to
tr
ain
in
g
(
8
0
%)
an
d
test
in
g
(
2
0
%)
d
atasets
.
Du
e
to
th
e
n
o
is
e
in
th
e
d
ataset,
th
e
ac
cu
r
ac
y
was
9
6
%
af
ter
cr
o
s
s
-
v
alid
atio
n
an
d
9
4
%
f
o
r
n
ew
d
ataset
test
in
g
.
ANN
was
d
esig
n
ed
with
a
s
in
g
le
h
id
d
en
lay
er
,
b
u
t
th
e
s
tr
u
ctu
r
e
o
f
ANN
ca
n
b
e
t
u
n
ed
f
o
r
b
etter
ac
cu
r
ac
y
.
In
[
2
6
]
,
th
e
y
u
s
ed
t
h
e
α
d
e
p
en
d
ed
o
n
t
h
e
d
eg
r
ee
-
b
ased
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
to
s
o
lv
e
th
e
im
b
alan
ce
p
r
o
b
lem
b
etwe
en
th
e
f
ea
tu
r
e
n
u
m
b
er
an
d
th
e
in
s
tan
ce
n
u
m
b
er
in
m
ic
r
o
ar
r
a
y
d
ata
-
b
ased
g
en
e
ex
p
r
ess
io
n
.
T
h
e
class
if
icatio
n
ac
cu
r
ac
y
o
f
s
m
aller
g
e
n
e
s
ize
was
b
etter
th
an
th
at
o
f
lar
g
er
g
en
e
s
ize.
Nin
e
d
atasets
h
av
e
b
ee
n
u
s
ed
in
th
i
s
s
tu
d
y
s
u
ch
as
co
lo
n
tu
m
o
u
r
,
ce
n
tr
al
n
er
v
o
u
s
s
y
s
tem
tu
m
o
u
r
,
d
if
f
u
s
e
lar
g
e
B
ce
ll
ly
m
p
h
o
m
a,
le
u
k
em
ia
1
,
AM
L
,
lu
n
g
ca
n
ce
r
,
p
r
o
s
tate
c
an
ce
r
,
b
r
ea
s
t
ca
n
ce
r
,
an
d
leu
k
ae
m
ia.
T
h
e
r
esu
lts
wer
e
co
m
p
ar
ed
with
o
th
e
r
tech
n
iq
u
es
s
u
ch
as
NB
(
Naïv
e
B
ay
es),
DT
(
d
ec
is
io
n
tr
ee
)
,
SVM
(
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
)
an
d
K
-
NN
(
K
-
n
ea
r
e
s
t
n
eig
h
b
o
u
r
)
.
As
r
ep
o
r
ted
,
th
e
k
-
NN
class
if
ier
h
ad
b
etter
p
er
f
o
r
m
an
ce
u
n
d
er
s
ev
en
α
v
alu
es.
L
i
an
d
co
lleag
u
es
ass
es
s
ed
f
iv
e
f
ea
tu
r
e
s
el
ec
tio
n
m
eth
o
d
s
s
u
ch
as
KNN,
C
4
.
5
,
Naïv
e
B
ay
es
an
d
SVM
with
leu
k
em
ia
an
d
o
v
ar
ia
n
ca
n
ce
r
d
atasets
[
2
7
,
2
8
]
h
as
p
r
esen
ted
a
co
m
p
ar
at
iv
e
s
tu
d
y
o
n
th
r
ee
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
s
with
f
o
u
r
d
ata
s
ets.
T
h
ey
u
s
ed
p
r
o
s
tate,
co
lo
n
tu
m
o
u
r
,
an
d
L
e
u
k
em
ia
an
d
Hep
at
o
d
atasets
.
SVM
p
er
f
o
r
m
s
b
etter
o
n
all
th
e
d
atasets
.
C
h
an
h
o
an
d
Su
n
g
-
B
ae
co
n
d
u
c
ted
an
an
aly
s
is
o
f
co
lo
n
ca
n
ce
r
an
d
L
y
m
p
h
o
m
a
d
atasets
b
y
s
ev
en
g
en
e
s
elec
tio
n
m
eth
o
d
s
an
d
s
ix
cla
s
s
if
ier
s
.
B
esid
e
s
,
J
i
-
Gan
g
an
d
Ho
n
g
-
W
en
d
ev
elo
p
e
d
a
g
en
e
s
elec
tio
n
m
eth
o
d
b
ased
o
n
B
ay
es
e
r
r
o
r
f
ilter
(
B
B
F)
[
2
9
]
.
B
B
F
ca
n
s
elec
t
s
ig
n
if
ican
t
g
en
es
wh
ile
r
em
o
v
in
g
n
o
n
-
s
ig
n
if
ican
t
g
en
es.
T
h
is
ev
alu
ated
u
s
in
g
d
atasets
in
clu
d
e
co
lo
n
,
p
r
o
s
tate
,
ly
m
p
h
o
m
a,
le
u
k
em
ia
,
a
n
d
D
SLBC
L
.
T
h
ey
h
ad
u
s
ed
SVM
an
d
KNN
f
o
r
m
ea
s
u
r
in
g
ac
cu
r
ac
ies.
T
h
e
y
o
b
s
er
v
ed
th
at
SVM
p
er
f
o
r
m
ed
well
o
n
all
th
e
d
atasets
u
s
ed
.
Xin
g
,
J
o
r
d
a
n
,
an
d
Kar
p
s
tu
d
ied
d
if
f
er
en
t c
lass
if
ier
s
s
u
ch
as th
e
Gau
s
s
ian
clas
s
if
ier
,
r
eg
r
ess
io
n
class
if
ier
,
an
d
KNN.
Featu
r
e
r
ed
u
ctio
n
b
y
th
ese
th
r
ee
m
eth
o
d
s
s
h
o
ws
b
etter
r
esu
lts
.
T
h
ey
p
r
o
p
o
s
ed
a
h
y
b
r
id
ap
p
r
o
ac
h
o
f
f
ilter
an
d
w
r
ap
p
er
f
o
r
f
ea
tu
r
e
s
elec
tio
n
in
h
ig
h
d
im
en
s
io
n
al
d
ata.
Ma
in
ly
th
ey
h
av
e
u
s
ed
Ma
r
k
o
v
B
lan
k
et
f
ilter
in
g
an
d
th
en
class
if
ied
w
ith
th
e
u
s
e
o
f
t
h
r
ee
d
i
f
f
er
en
t
c
lass
if
ier
s
.
T
h
u
s
,
th
ese
class
if
i
er
s
ab
le
to
p
er
f
o
r
m
b
etter
with
th
e
r
ed
u
ce
d
s
ig
n
if
i
ca
n
t
f
ea
tu
r
e
s
p
ac
e
c
o
m
p
ar
e
d
t
o
f
u
ll f
ea
tu
r
e
s
p
ac
e
[
3
0
]
.
On
to
p
o
f
th
at,
On
s
k
o
g
a
n
d
co
lleag
u
es
h
ad
p
r
esen
te
d
m
icr
o
ar
r
ay
s
class
if
icatio
n
o
n
s
ev
en
ca
n
ce
r
-
r
elate
d
d
ata.
Do
u
b
le
c
r
o
s
s
-
v
alid
atio
n
m
eth
o
d
s
ar
e
ap
p
lied
to
o
b
tain
a
s
tr
o
n
g
er
r
o
r
r
ate.
T
h
e
r
esu
lts
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
Th
e
imp
o
r
ta
n
ce
o
f d
a
ta
cla
s
s
ifica
tio
n
u
s
in
g
ma
c
h
in
e
lea
r
n
in
g
meth
o
d
s
in
micro
a
r
r
a
y
d
a
t
a
(
A
w
s
N
a
s
e
r
Ja
b
er
)
495
s
h
o
w
th
at
SVM
with
a
r
ad
ial
b
asis
k
er
n
el
an
d
lin
ea
r
k
er
n
el
p
er
f
o
r
m
ed
s
tead
ily
with
th
ese
d
ata
s
ets.
Mo
r
eo
v
er
,
b
ased
o
n
th
e
t
-
test
th
er
e
is
a
s
y
n
er
g
i
s
tic
as
s
o
ciatio
n
b
etwe
en
th
e
m
eth
o
d
s
an
d
g
en
e
s
elec
tio
n
p
r
o
ce
s
s
[
3
1
]
.
B
esid
es
th
is
,
[
3
2
]
p
r
o
p
o
s
ed
a
m
ac
h
in
e
lear
n
in
g
s
tu
d
y
o
n
p
r
o
s
tate
ca
n
ce
r
d
at
a
s
et.
I
n
p
ar
ticu
lar
,
th
e
t
-
test
an
d
in
ter
q
u
ar
tile
r
an
g
e
ar
e
co
m
b
i
n
ed
f
o
r
f
ea
tu
r
e
s
elec
tio
n
.
T
h
e
r
esu
lts
p
r
o
d
u
c
e
d
s
h
o
w
th
at
B
ay
es
Netwo
r
k
is
o
u
tp
er
f
o
r
m
ed
,
Na
ïv
e
B
ay
es.
I
n
[
3
3
]
d
if
f
e
r
en
t
d
is
cr
im
in
atio
n
m
eth
o
d
s
ar
e
u
s
ed
f
o
r
class
if
icatio
n
o
n
th
r
ee
ca
n
ce
r
g
en
e
ex
p
r
ess
io
n
d
ata
s
ets.
T
h
e
m
eth
o
d
s
ar
e
n
ea
r
est
-
n
eig
h
b
o
u
r
class
if
ier
s
,
lin
ea
r
d
is
cr
im
in
a
n
t
an
aly
s
is
,
an
d
class
i
f
icat
io
n
tr
ee
s
.
Fro
m
th
e
o
u
tp
u
t,
th
e
n
ea
r
est
n
eig
h
b
o
u
r
class
if
ies
b
ette
r
co
m
p
ar
ed
to
th
e
d
ec
is
io
n
tr
ee
class
if
ier
.
Fu
r
th
er
m
o
r
e
,
Su
n
g
B
ae
a
n
d
c
o
lleag
u
es
u
s
ed
th
r
ee
m
icr
o
a
r
r
ay
d
ata
s
ets
n
am
ely
,
L
eu
k
em
ia,
co
lo
n
,
an
d
L
y
m
p
h
o
m
a
with
f
ea
t
u
r
e
s
elec
tio
n
an
d
class
i
f
ier
s
.
T
h
e
in
v
esti
g
atio
n
r
esu
lts
s
h
o
w
th
at
th
e
e
n
s
em
b
le
class
if
ier
s
p
r
o
d
u
ce
d
th
e
b
est
class
if
icatio
n
r
ate
co
m
p
ar
ed
to
o
th
er
m
et
h
o
d
s
[
3
4
]
.
Ab
u
s
am
r
a
h
as
d
o
n
e
an
in
v
esti
g
atio
n
o
n
eig
h
t
d
if
f
er
en
t
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
s
an
d
th
r
ee
class
if
icatio
n
m
eth
o
d
s
.
T
h
e
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
s
in
clu
d
e
m
a
x
m
in
o
r
ity
,
in
f
o
r
m
atio
n
g
ain
,
Gin
i
in
d
ex
,
t
-
s
tatis
tics
,
th
e
s
u
m
o
f
v
ar
ian
ce
s
an
d
one
-
d
im
e
n
s
io
n
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
was
co
m
p
ar
ed
.
T
h
e
class
if
icatio
n
m
eth
o
d
s
ar
e
SVM,
KNN,
an
d
r
an
d
o
m
f
o
r
est.
T
wo
ty
p
es
o
f
g
lio
m
a
ex
p
r
ess
io
n
d
ata
s
ets
a
r
e
u
s
ed
in
th
is
ex
p
er
im
en
t.
T
h
e
r
esu
lts
s
h
o
w
th
at
th
e
s
elec
tio
n
o
f
s
ig
n
if
ican
t g
en
es h
ad
b
o
o
s
ted
class
if
icatio
n
ac
cu
r
ac
y
.
I
n
b
o
th
d
atasets
,
SV
M
p
er
f
o
r
m
e
d
b
etter
th
an
o
th
er
class
if
icatio
n
m
eth
o
d
s
[
3
5
]
.
T
h
e
m
ax
im
u
m
r
ele
v
an
ce
m
in
i
m
u
m
r
ed
u
n
d
an
c
y
(
m
R
MR)
alg
o
r
ith
m
is
a
s
p
ec
ial
g
r
o
u
p
o
f
f
ilter
-
b
ased
ap
p
r
o
ac
h
es
wh
ich
ab
le
to
s
el
ec
t
co
n
cu
r
r
e
n
tly
h
ig
h
ly
p
r
ed
i
ctiv
e
b
u
t
u
n
c
o
r
r
elate
d
f
ea
tu
r
es.
T
h
is
alg
o
r
ith
m
m
ain
ly
s
elec
ts
f
ea
tu
r
es
s
u
b
s
et
h
av
in
g
th
e
m
ax
im
u
m
ass
o
ci
atio
n
with
a
class
(
r
elev
an
ce
)
an
d
th
e
m
i
n
im
u
m
ass
o
ciatio
n
b
etwe
en
th
em
s
elv
es
(
r
ed
u
n
d
an
c
y
)
.
T
h
e
f
ea
t
u
r
e’
s
r
an
k
in
g
is
g
iv
en
b
ased
o
n
m
in
im
al
-
r
ed
u
n
d
an
c
y
-
m
ax
im
al
-
r
elev
an
ce
m
ea
s
u
r
es.
Hen
ce
F
-
s
tatis
tic
s
is
u
s
ed
to
ca
lcu
late
th
e
r
elev
an
ce
a
n
d
Pear
s
o
n
co
r
r
elatio
n
co
ef
f
icien
t
is
u
s
ed
to
ca
lcu
late
th
e
r
ed
u
n
d
a
n
cy
[
3
6
]
.
B
esid
es
th
is
,
[
3
7
]
d
ev
elo
p
ed
th
e
Mo
n
te
C
ar
lo
f
ea
tu
r
e
s
elec
tio
n
(
MCF
S)
alg
o
r
ith
m
to
id
en
tify
in
f
o
r
m
ativ
e
f
e
atu
r
es.
T
h
e
MCF
S
alg
o
r
ith
m
is
in
teg
r
atin
g
in
ter
d
ep
en
d
en
cies
am
o
n
g
f
ea
tu
r
es.
I
t
h
as
s
o
m
e
s
im
ilar
ity
as
in
r
an
d
o
m
f
o
r
est
m
eth
o
d
o
lo
g
y
b
u
t
d
i
f
f
er
s
i
n
ter
m
s
o
f
f
ea
tu
r
e
r
an
k
in
g
ca
lcu
l
atio
n
[
3
7
]
.
B
esid
es
th
i
s
,
Als
h
am
lan
an
d
co
lleag
u
es
p
r
o
p
o
s
ed
a
n
ew
f
e
atu
r
e
s
elec
tio
n
m
eth
o
d
ca
lled
m
in
im
u
m
r
ed
u
n
d
an
cy
m
ax
im
u
m
r
elev
a
n
ce
(
m
R
MR)
h
y
b
r
id
with
an
ar
tific
ial
b
ee
co
lo
n
y
(
AB
C
)
.
T
h
is
alg
o
r
ith
m
is
s
p
ec
if
ical
ly
to
s
elec
t
s
ig
n
if
ica
n
t
g
en
es
f
r
o
m
t
h
e
m
icr
o
ar
r
a
y
.
T
h
e
ex
p
er
im
en
t
is
co
n
d
u
cted
with
s
ix
b
in
a
r
y
an
d
m
u
lticlas
s
d
ata
s
ets.
T
h
e
p
r
o
d
u
ce
d
r
esu
lt
s
h
o
ws
th
at
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
h
as
ac
h
iev
ed
b
etter
class
if
icatio
n
ac
cu
r
ac
y
co
m
p
ar
ed
to
m
R
MR
-
GA
an
d
m
R
MR
-
PS
O
alg
o
r
it
h
m
s
[
3
8
]
.
J
ay
g
er
,
Sen
g
u
p
ta,
a
n
d
R
u
zz
o
[
3
9
]
s
tu
d
y
v
ar
io
u
s
g
en
e
s
elec
tio
n
m
eth
o
d
s
f
o
r
m
icr
o
a
r
r
ay
d
ata
class
if
icatio
n
.
T
h
ey
u
s
ed
v
ar
io
u
s
s
tatis
tics
test
with
g
en
e
s
elec
tio
n
m
eth
o
d
s
.
T
h
e
s
tatis
tics
test
s
in
clu
d
e
Fis
h
er
,
Go
lu
b
,
W
ilco
x
o
n
,
T
No
M,
a
n
d
t
-
test
.
Hu
awe
n
,
L
ei
an
d
Hu
ijie
co
m
p
ar
ed
v
ar
io
u
s
g
en
e
s
elec
tio
n
m
eth
o
d
s
[
4
0
]
.
T
h
ey
co
m
p
ar
e
d
en
s
em
b
le
g
en
e
s
elec
tio
n
by
g
r
o
u
p
in
g
with
th
e
o
th
er
th
r
ee
g
en
e
s
elec
tio
n
m
eth
o
d
s
FC
B
F,
m
R
M
R
,
an
d
E
C
R
P.
T
h
ey
u
s
ed
f
iv
e
d
atasets
with
th
ese
t
ec
h
n
iq
u
es.
T
h
ey
u
s
ed
two
cla
s
s
if
ic
atio
n
m
eth
o
d
s
Naïv
e
B
ay
es
an
d
KNN.
T
h
ey
co
m
p
ar
ed
a
n
d
an
al
y
ze
d
wh
ic
h
class
if
icatio
n
m
eth
o
d
is
ef
f
ec
tiv
e.
W
h
ile,
in
[
2
5
]
,
th
ey
e
m
p
lo
y
ed
t
h
e
f
u
zz
y
clu
s
ter
in
g
m
eth
o
d
with
v
iewp
o
in
ts
to
id
en
tify
u
n
lab
eled
s
am
p
les.
T
h
e
v
iewp
o
in
ts
we
r
e
co
n
s
tr
u
cted
b
y
co
m
p
u
tin
g
th
e
av
er
ag
e
ex
p
r
ess
io
n
f
o
r
ea
ch
f
ea
tu
r
e
(
p
r
o
b
e/g
en
e)
in
th
e
s
am
p
les with
a
lab
el.
I
n
th
eir
wo
r
k
,
th
e
p
r
ev
io
u
s
ly
av
ailab
le
m
icr
o
ar
r
ay
ex
p
r
ess
io
n
d
ata
was
in
tr
o
d
u
ce
d
as
v
iewp
o
in
ts
in
th
e
clu
s
ter
in
g
p
r
o
ce
s
s
.
T
h
e
tech
n
iq
u
e
was
a
p
p
lied
t
o
b
r
ea
s
t
ca
n
ce
r
,
b
r
ain
ca
n
ce
r
,
AM
L
,
an
d
ML
L
d
atasets
.
T
h
e
m
eth
o
d
was
f
o
u
n
d
to
b
e
b
etter
th
an
o
t
h
er
clu
s
ter
in
g
alg
o
r
ith
m
s
s
u
ch
as
K
m
ea
n
s
,
f
u
zz
y
c
-
m
ea
n
s
,
af
f
i
n
ity
p
r
o
p
ag
atio
n
,
an
d
t
h
e
clu
s
ter
in
g
m
eth
o
d
b
ased
o
n
p
r
io
r
b
io
lo
g
ical
k
n
o
wled
g
e.
Ho
wev
er
,
T
ab
le
1
s
h
o
ws
th
e
m
o
s
t
r
elate
d
wo
r
k
s
in
m
icr
o
ar
r
ay
DNA.
T
ab
le
1
.
Mo
s
t r
elate
d
w
o
r
k
f
o
r
th
e
Mic
r
o
ar
r
a
y
DNA
D
a
t
a
s
e
t
R
e
f
e
r
e
n
c
e
s
A
c
u
t
e
l
y
m
p
h
o
b
l
a
st
i
c
l
e
u
k
e
m
i
a
(
A
LL),
A
M
L
,
M
LL,
D
LB
C
L
,
L
y
m
p
h
o
m
a
,
S
R
B
C
T
[
2
6
]
[
2
7
,
2
9
,
4
4
]
B
r
e
a
s
t
C
a
n
c
e
r
[
3
2
]
C
o
l
o
n
C
a
n
c
e
r
[
2
9
,
4
4
]
P
r
o
st
a
t
e
[
1
6
,
2
9
,
4
4
]
O
v
a
r
i
a
n
c
a
n
c
e
r
[
2
7
]
Lu
n
g
C
a
n
c
e
r
[
1
6
,
2
6
]
G
l
i
o
ma,
B
r
a
i
n
t
u
m
o
u
r
,
C
N
S
(
C
e
n
t
r
a
l
N
e
u
r
a
l
S
y
st
e
m)
[
1
6
,
3
5
]
H
e
p
a
t
i
c
[
4
4
]
D
i
a
b
e
t
e
s
[
3
2
]
Fu
r
th
er
m
o
r
e
,
[
4
1
]
h
y
b
r
id
ce
llu
lar
au
to
m
ata
a
n
d
a
n
t
co
l
o
n
y
o
p
tim
izatio
n
m
eth
o
d
to
s
elec
t
th
e
s
ig
n
if
ican
t
g
en
es
th
en
u
s
ed
f
o
r
class
if
icatio
n
.
T
h
u
s
,
it
h
as
p
r
o
d
u
ce
d
h
i
g
h
ac
cu
r
ac
y
co
m
p
ar
ed
to
o
th
er
s
elec
ted
m
eth
o
d
s
as
s
h
o
w
n
in
th
e
p
ap
e
r
.
Mo
r
e
o
v
er
in
[
4
2
]
,
a
n
a
r
tific
ial
n
eu
r
al
n
etwo
r
k
(
ANN)
is
a
p
p
lied
to
AL
L
a
n
d
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 Co
n
tr
o
l
,
Vo
l.
1
9
,
No
.
2
,
Ap
r
il
202
1
:
49
1
-
498
496
AM
L
d
atasets
.
T
h
is
r
esear
ch
h
ad
g
en
er
ated
9
8
%
ac
cu
r
ac
y
,
wh
er
e
th
er
e
is
n
o
er
r
o
r
in
AL
L
d
atasets
an
d
o
n
e
er
r
o
r
in
AM
L
d
ataset.
T
h
e
ca
n
ce
r
g
en
o
m
e
atlas
(
T
C
GA)
i
s
a
p
ilo
t
p
r
o
ject
lau
n
ch
ed
b
y
th
e
Natio
n
al
I
n
s
titu
te
o
f
Hea
lth
(
NI
H)
.
T
h
is
is
b
asically
to
cr
ea
te
a
co
m
p
r
eh
en
s
iv
e
atlas
o
f
ca
n
ce
r
g
en
o
m
ic
p
r
o
f
iles
.
Hen
ce
,
m
o
s
t
o
f
th
e
g
en
e
e
x
p
r
ess
io
n
d
ata
a
r
e
p
u
b
licly
av
ailab
le
at
T
C
GA
th
a
t a
r
e
u
s
ed
in
p
r
o
g
n
o
s
is
an
d
d
ia
g
n
o
s
is
[
4
3
]
.
4.
CO
NCLU
SI
O
N
T
h
is
p
ap
er
r
e
v
iews
th
e
ex
is
tin
g
class
if
icatio
n
tech
n
iq
u
es
a
p
p
lied
in
m
icr
o
ar
r
a
y
s
th
at
co
n
tain
h
ig
h
d
im
en
s
io
n
al
d
ata.
T
h
e
h
ig
h
d
i
m
en
s
io
n
al
d
ata
p
r
o
b
lem
ca
n
b
e
s
o
lv
ed
u
s
in
g
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
s
.
Ma
n
y
g
en
e
s
elec
tio
n
m
eth
o
d
s
h
av
e
b
ee
n
u
s
ed
to
class
if
y
ca
n
ce
r
o
u
s
ly
o
r
an
y
o
th
e
r
d
is
ea
s
e
d
atasets
wi
th
m
u
lti
o
r
b
in
ar
y
class
es.
T
h
e
u
n
d
er
l
y
in
g
ch
allen
g
e
is
t
h
e
ef
f
icien
t
d
e
tectio
n
o
f
d
i
f
f
er
en
t
in
f
ec
ted
g
en
es
with
d
if
f
er
en
t
ch
ar
ac
ter
is
tics
s
u
ch
as
m
u
tate
d
g
en
es
ca
u
s
ed
b
y
v
i
r
u
s
es,
r
a
d
iatio
n
,
m
u
tag
en
ic
c
h
em
icals.
Ma
c
h
in
e
lear
n
in
g
tech
n
iq
u
es
h
av
e
b
ee
n
p
r
o
p
o
s
e
d
to
an
aly
ze
m
icr
o
a
r
r
ay
d
ata.
Hy
b
r
id
ized
m
eth
o
d
s
ca
n
elim
i
n
ate
n
o
is
e,
r
ed
u
ce
th
e
n
u
m
b
e
r
o
f
f
ea
tu
r
es a
n
d
ea
s
e
class
if
icatio
n
.
Swar
m
in
telli
g
en
ce
alg
o
r
ith
m
s
s
u
ch
as
an
t c
o
lo
n
y
o
p
tim
izatio
n
(
AC
O)
,
ar
tific
ial
b
ee
co
lo
n
y
o
p
tim
izatio
n
(
AB
C
)
,
p
ar
ticle
s
war
m
o
p
tim
izatio
n
(
PS
O)
ar
e
p
o
wer
f
u
l
in
f
ea
tu
r
e
s
elec
tio
n
.
Hy
b
r
id
izatio
n
b
et
wee
n
th
e
class
ical
m
ac
h
in
e
lear
n
in
g
tec
h
n
iq
u
es
an
d
th
e
em
er
g
in
g
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
es
s
u
ch
as
s
war
m
in
tellig
en
ce
alg
o
r
ith
m
s
ca
n
y
ield
b
etter
r
esu
lts
in
d
iag
n
o
s
is
an
d
class
if
icatio
n
.
C
u
r
r
en
tly
,
r
es
ea
r
ch
er
s
h
av
e
d
e
v
elo
p
ed
h
y
b
r
id
ized
co
m
p
u
tatio
n
al
m
e
th
o
d
s
with
s
war
m
in
tellig
en
ce
(
SI)
m
eth
o
d
s
an
d
p
r
o
v
e
n
th
at
th
ese
h
y
b
r
id
ized
s
y
s
tem
s
ar
e
m
o
r
e
ac
cu
r
ate.
Nev
er
th
eless
,
a
m
o
d
el
th
at
s
o
lely
r
elies o
n
s
war
m
in
t
ellig
en
ce
alg
o
r
ith
m
s
s
h
o
u
ld
b
e
b
u
ilt an
d
a
n
aly
ze
d
.
5.
ACK
NO
WL
E
DG
E
M
E
NT
S
W
e
wo
u
ld
lik
e
to
t
h
an
k
Un
iv
e
r
s
iti
Ma
lay
s
ia
Pah
an
g
f
o
r
s
u
p
p
o
r
tin
g
th
is
wo
r
k
u
n
d
er
th
e
R
DU
Gr
an
t,
Gr
an
t
n
u
m
b
er
:
R
DU1
9
0
3
7
3
.
W
e
also
ap
p
r
ec
iate
th
e
Min
is
tr
y
o
f
E
d
u
ca
tio
n
f
o
r
s
u
p
p
o
r
tin
g
th
is
wo
r
k
u
n
d
er
th
e
Gr
an
t N
u
m
b
er
: RAC
E
R
/1
/2
0
1
9
/I
C
T
0
2
/UMP//4
.
RE
F
E
R
E
NC
E
S
[1
]
K.
Lan
,
D.
T
.
Wan
g
,
S
.
F
o
n
g
,
L
.
S
.
Li
u
,
K.
K.
Wo
n
g
,
a
n
d
N.
De
y
,
"
A
su
r
v
e
y
o
f
d
a
ta
m
in
i
n
g
a
n
d
d
e
e
p
lea
rn
in
g
in
b
io
i
n
fo
rm
a
ti
c
s,"
J
o
u
rn
a
l
o
f
me
d
ic
a
l
sy
ste
ms
,
v
o
l
.
4
2
,
n
o
.
8
,
p
p
.
1
-
28
,
2
0
1
8
.
[2
]
Y.
Do
r
a
n
d
H.
Ce
d
a
r,
"
P
r
in
c
ip
l
e
s
o
f
DN
A
m
e
th
y
lati
o
n
a
n
d
t
h
e
ir
imp
li
c
a
ti
o
n
s
fo
r
b
i
o
l
o
g
y
a
n
d
m
e
d
icin
e
,
"
T
h
e
L
a
n
c
e
t,
v
o
l.
3
9
2
,
p
p
.
7
7
7
-
7
8
6
,
2
0
1
8
.
[3
]
H.
Q.
Tru
o
n
g
,
L.
T
.
Ng
o
,
a
n
d
W.
P
e
d
ry
c
z
,
"
G
ra
n
u
lar
fu
z
z
y
p
o
ss
ib
il
isti
c
C
-
m
e
a
n
s
c
lu
ste
rin
g
a
p
p
ro
a
c
h
to
DN
A
m
icro
a
rra
y
p
ro
b
lem
,
"
K
n
o
wled
g
e
-
Ba
se
d
S
y
ste
ms
,
v
o
l.
1
3
3
,
p
p
.
5
3
-
6
5
,
2
0
1
7
.
[4
]
S
.
M
it
tal,
H.
Ka
u
r,
N.
G
a
u
tam
,
a
n
d
A.
K.
M
a
n
th
a
,
"
Bi
o
se
n
s
o
rs
f
o
r
b
re
a
st
c
a
n
c
e
r
d
iag
n
o
sis:
A
re
v
iew
o
f
b
io
re
c
e
p
to
rs
,
b
io
tra
n
sd
u
c
e
rs
a
n
d
sig
n
a
l
a
m
p
li
f
ica
ti
o
n
stra
teg
i
e
s,"
Bi
o
se
n
s
o
rs
a
n
d
Bi
o
e
lec
tro
n
ics
,
v
o
l.
8
8
,
p
p
.
2
1
7
-
2
3
1
,
2
0
1
7
.
[5
]
C.
Xu
a
n
d
S
.
A.
Ja
c
k
so
n
,
"
M
a
c
h
i
n
e
lea
rn
in
g
a
n
d
c
o
m
p
le
x
b
io
l
o
g
ic
a
l
d
a
ta,"
Ge
n
o
me
Bi
o
l
o
g
y
,
v
o
l.
2
0
,
n
o
.
1
,
p
p
.
1
-
4
,
2
0
1
9
.
[6
]
F
.
P
.
Ba
rth
e
l,
W.
Wei,
M
.
Ta
n
g
,
E.
M
a
rt
in
e
z
-
Led
e
sm
a
,
X.
Hu
,
S
.
B.
Am
in
,
e
t
a
l
.
,
"
S
y
ste
m
a
ti
c
a
n
a
l
y
sis
o
f
tel
o
m
e
re
len
g
t
h
a
n
d
so
m
a
ti
c
a
lt
e
ra
ti
o
n
s
in
3
1
c
a
n
c
e
r
t
y
p
e
s,"
N
a
t
u
re
g
e
n
e
ti
c
s
,
v
o
l.
4
9
,
n
o
.
3
,
p
p
.
3
4
9
-
3
5
7
2
0
1
7
.
[7
]
P
.
M
a
m
o
sh
i
n
a
,
A.
Vie
ira,
E.
P
u
ti
n
,
a
n
d
A.
Zh
a
v
o
ro
n
k
o
v
,
"
Ap
p
li
c
a
ti
o
n
s
o
f
d
e
e
p
lea
rn
in
g
i
n
b
i
o
m
e
d
icin
e
,
"
M
o
lec
u
l
a
r p
h
a
rm
a
c
e
u
ti
c
s,
v
o
l.
1
3
,
p
p
.
1
4
4
5
-
1
4
5
4
,
2
0
1
6
.
[8
]
Y.
Li
n
,
J.
C
.
M
a
u
r
o
,
a
n
d
G
.
Ka
u
r,
"
Bio
a
c
ti
v
e
G
las
se
s f
o
r
Ca
n
c
e
r
Th
e
ra
p
y
,
"
in
Bi
o
me
d
ic
a
l,
T
h
e
ra
p
e
u
ti
c
a
n
d
Cli
n
ica
l
Ap
p
li
c
a
ti
o
n
s
o
f
Bi
o
a
c
ti
v
e
Gl
a
ss
e
s
,
e
d
:
El
se
v
ier,
2
0
1
9
,
p
p
.
2
7
3
-
3
1
2
.
[9
]
V.
G
u
p
ta,
M
.
S
e
n
g
u
p
ta,
J.
P
ra
k
a
sh
,
a
n
d
B.
C
.
Tri
p
a
th
y
,
B
a
sic
a
n
d
a
p
p
li
e
d
a
sp
e
c
ts o
f
b
i
o
tec
h
n
o
lo
g
y
:
S
p
ri
n
g
e
r,
2
0
1
7
.
[1
0
]
D.
O
fe
n
g
e
im,
N.
G
iag
tzo
g
l
o
u
,
D
.
Hu
h
,
C.
Z
o
u
,
a
n
d
J.
Y
u
a
n
,
"
S
i
n
g
le
-
c
e
ll
RNA
se
q
u
e
n
c
in
g
:
u
n
ra
v
e
li
n
g
t
h
e
b
ra
i
n
o
n
e
c
e
ll
a
t
a
ti
m
e
,
"
T
re
n
d
s
in
m
o
l
e
c
u
la
r me
d
icin
e
,
v
o
l.
2
3
,
n
o
.
6
,
p
p
.
5
6
3
-
5
7
6
,
2
0
1
7
.
[1
1
]
M
.
Afz
a
l,
I.
M
a
n
z
o
o
r,
a
n
d
O.
P
.
Ku
ip
e
rs,
"
A
fa
st
a
n
d
re
l
iab
le
p
i
p
e
li
n
e
f
o
r
b
a
c
teria
l
tran
sc
rip
t
o
m
e
a
n
a
ly
sis
c
a
se
stu
d
y
:
se
rin
e
-
d
e
p
e
n
d
e
n
t
g
e
n
e
re
g
u
latio
n
i
n
S
trep
to
c
o
c
c
u
s
p
n
e
u
m
o
n
iae
,
"
J
o
V
E
(J
o
u
rn
a
l
o
f
Vi
s
u
a
l
ize
d
Exp
e
rime
n
ts
)
,
2
0
1
5
.
[1
2
]
S.
-
B.
L
ian
g
a
n
d
L.
-
W
.
F
u
,
"
Ap
p
li
c
a
ti
o
n
o
f
si
n
g
le
-
c
e
ll
tec
h
n
o
lo
g
y
in
c
a
n
c
e
r
re
se
a
r
c
h
,
"
Bi
o
tec
h
n
o
l
o
g
y
A
d
v
a
n
c
e
s,
v
o
l.
3
5
,
p
p
.
4
4
3
-
4
4
9
,
2
0
1
7
.
[1
3
]
R.
C.
T
h
o
m
p
s
o
n
,
A.
F
.
S
e
a
sh
o
lt
z
,
J.
O.
D
o
u
g
las
s,
a
n
d
E.
He
rb
e
rt,
"
Clo
n
i
n
g
a
n
d
d
istri
b
u
t
io
n
o
f
e
x
p
re
ss
io
n
o
f
th
e
ra
t
c
o
rti
c
o
tro
p
i
n
-
re
lea
sin
g
fa
c
to
r
(CRF
)
g
e
n
e
,
"
i
n
Co
rtic
o
tro
p
in
-
Rele
a
s
in
g
Fa
c
to
r
,
e
d
:
CRC
P
re
ss
,
2
0
1
8
,
p
p
.
1
-
12.
[1
4
]
L.
Ch
e
n
,
X
.
P
a
n
,
X.
Hu
,
Y.
H.
Zh
a
n
g
,
S
.
Wa
n
g
,
T.
Hu
a
n
g
,
e
t
a
l
.
,
"
G
e
n
e
e
x
p
re
ss
io
n
d
iffere
n
c
e
s
a
m
o
n
g
d
iffere
n
t
M
S
I
sta
tu
se
s in
c
o
l
o
re
c
tal
c
a
n
c
e
r,
"
In
ter
n
a
ti
o
n
a
l
j
o
u
r
n
a
l
o
f
c
a
n
c
e
r,
v
o
l.
1
4
3
,
p
p
.
1
7
3
1
-
1
7
4
0
,
2
0
1
8
.
[1
5
]
G
.
T
a
şk
ın
,
H.
Ka
y
a
,
a
n
d
L.
Br
u
z
z
o
n
e
,
"
F
e
a
tu
re
se
lec
ti
o
n
b
a
se
d
o
n
h
i
g
h
d
ime
n
sio
n
a
l
m
o
d
e
l
re
p
re
se
n
tatio
n
f
o
r
h
y
p
e
rs
p
e
c
tral
ima
g
e
s,"
IEE
E
T
ra
n
sa
c
ti
o
n
s o
n
Ima
g
e
Pro
c
e
ss
in
g
,
v
o
l.
2
6
,
n
o
.
6
,
p
p
.
2
9
1
8
-
2
9
2
8
,
2
0
1
7
.
[1
6
]
R.
Li
u
,
X.
Wan
g
,
K.
Aih
a
ra
,
a
n
d
L.
Ch
e
n
,
"
Early
d
iag
n
o
sis
o
f
c
o
m
p
lex
d
ise
a
se
s
b
y
m
o
lec
u
lar
b
io
m
a
rk
e
rs,
n
e
two
r
k
b
io
m
a
rk
e
rs,
a
n
d
d
y
n
a
m
ica
l
n
e
two
rk
b
i
o
m
a
rk
e
rs,"
M
e
d
icin
a
l
re
se
a
r
c
h
re
v
iews
,
v
o
l.
3
4
,
n
o
.
3
,
p
p
.
4
5
5
-
4
7
8
,
2
0
1
4
.
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
Th
e
imp
o
r
ta
n
ce
o
f d
a
ta
cla
s
s
ifica
tio
n
u
s
in
g
ma
c
h
in
e
lea
r
n
in
g
meth
o
d
s
in
micro
a
r
r
a
y
d
a
t
a
(
A
w
s
N
a
s
e
r
Ja
b
er
)
497
[1
7
]
F
.
Li
,
D.
M
ia
o
,
a
n
d
W.
P
e
d
r
y
c
z
,
"
G
ra
n
u
lar
m
u
lt
i
-
la
b
e
l
fe
a
tu
re
se
lec
ti
o
n
b
a
se
d
o
n
m
u
tu
a
l
in
f
o
rm
a
ti
o
n
,
"
P
a
tt
e
r
n
Rec
o
g
n
it
io
n
,
v
o
l.
6
7
,
p
p
.
4
1
0
-
4
2
3
,
2
0
1
7
.
[1
8
]
J.
Li
,
J.
Wan
g
,
Y.
Z
h
e
n
g
,
a
n
d
H.
Xia
o
,
"
M
icro
a
rra
y
c
las
sifica
ti
o
n
with
n
o
ise
v
ia
we
ig
h
te
d
a
d
a
p
t
iv
e
e
las
ti
c
n
e
t,
"
i
n
2
0
1
7
6
th
Da
t
a
Dr
ive
n
Co
n
tro
l
a
n
d
L
e
a
r
n
in
g
S
y
ste
ms
(DD
CL
S
)
,
2
0
1
7
,
p
p
.
4
1
6
-
4
2
0
.
[1
9
]
C.
Ka
n
g
,
Y.
Hu
o
,
L.
Xi
n
,
B.
Ti
a
n
,
a
n
d
B.
Yu
,
"
F
e
a
tu
re
se
lec
ti
o
n
a
n
d
t
u
m
o
r
c
las
sifica
ti
o
n
fo
r
m
icro
a
rra
y
d
a
ta
u
sin
g
re
lax
e
d
Las
so
a
n
d
g
e
n
e
ra
li
z
e
d
m
u
lt
i
-
c
las
s
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
,
"
J
o
u
rn
a
l
o
f
T
h
e
o
re
ti
c
a
l
Bi
o
lo
g
y
,
v
o
l
.
4
6
3
,
p
p
.
7
7
-
9
1
,
p
p
.
7
7
-
9
1
,
2
0
1
9
.
[2
0
]
D.
Yo
g
a
tam
a
,
C.
Dy
e
r,
W.
L
in
g
,
a
n
d
P
.
Bl
u
n
s
o
m
,
"
G
e
n
e
ra
ti
v
e
a
n
d
d
isc
rimin
a
ti
v
e
tex
t
c
las
sifica
ti
o
n
with
re
c
u
rre
n
t
n
e
u
ra
l
n
e
tw
o
rk
s,
"
a
rXiv
p
re
p
rin
t
a
rXiv:1
7
0
3
.
0
1
8
9
8
,
2
0
1
7
.
[2
1
]
C.
Hu
a
n
g
,
R.
M
e
z
e
n
c
e
v
,
J.
F
.
M
c
Do
n
a
ld
,
a
n
d
F
.
Va
n
n
b
e
r
g
,
"
Op
e
n
so
u
rc
e
m
a
c
h
in
e
-
lea
rn
i
n
g
a
lg
o
rit
h
m
s
f
o
r
t
h
e
p
re
d
ictio
n
o
f
o
p
ti
m
a
l
c
a
n
c
e
r
d
r
u
g
th
e
ra
p
ies
,
"
P
L
o
S
On
e
,
v
o
l.
1
2
,
2
0
1
7
.
[2
2
]
S
.
T
u
rg
u
t,
M
.
Da
ğ
te
k
in
,
a
n
d
T.
En
sa
ri,
"
M
icro
a
rra
y
b
re
a
st
c
a
n
c
e
r
d
a
ta
c
las
sifica
ti
o
n
u
si
n
g
m
a
c
h
in
e
lea
rn
i
n
g
m
e
th
o
d
s,"
i
n
2
0
1
8
El
e
c
tric
El
e
c
tro
n
ics
,
C
o
mp
u
ter
S
c
ien
c
e
,
Bi
o
me
d
ic
a
l
E
n
g
in
e
e
rin
g
s'
M
e
e
ti
n
g
(E
BB
T
)
,
p
p
.
1
-
3
,
2
0
1
8
.
[2
3
]
A.
Bh
a
ra
th
i
a
n
d
A.
Na
tara
jan
,
"
C
a
n
c
e
r
c
las
sifica
ti
o
n
o
f
b
io
in
f
o
rm
a
ti
c
s
d
a
ta
u
sin
g
a
n
o
v
a
,
"
In
ter
n
a
ti
o
n
a
l
j
o
u
rn
a
l
o
f
c
o
mp
u
ter
t
h
e
o
ry
a
n
d
e
n
g
i
n
e
e
rin
g
,
v
o
l
.
2
,
n
o
.
3
,
p
p
.
3
6
9
-
3
7
3
,
2
0
1
0
.
[2
4
]
K.
N.
Ka
ra
y
ian
n
i,
G
.
M
.
S
p
y
ro
u
,
a
n
d
K.
S
.
Nik
it
a
,
"
Cl
u
ste
rin
g
m
icro
a
rra
y
d
a
ta
u
sin
g
fu
z
z
y
c
lu
ste
rin
g
wi
t
h
v
iew
p
o
i
n
ts,"
in
2
0
1
2
I
EE
E
1
2
t
h
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
Bi
o
in
f
o
rm
a
ti
c
s
&
Bi
o
e
n
g
i
n
e
e
rin
g
(BI
BE
)
,
2
0
1
2
,
p
p
.
3
6
2
-
3
6
7
.
[2
5
]
S
.
M
a
n
d
a
l
a
n
d
I.
Ba
n
e
rjee
,
"
C
a
n
c
e
r
c
las
sifica
ti
o
n
u
sin
g
n
e
u
ra
l
n
e
two
rk
,
"
I
n
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Eme
rg
in
g
En
g
i
n
e
e
rin
g
Res
e
a
rc
h
a
n
d
T
e
c
h
n
o
lo
g
y
,
v
o
l.
3
,
n
o
.
7
,
p
p
.
1
7
2
-
1
7
8
,
2
0
1
5
.
[2
6
]
H.
Li
u
,
J.
Li
,
a
n
d
L.
Wo
n
g
,
"
A
c
o
m
p
a
ra
ti
v
e
stu
d
y
o
n
fe
a
tu
re
s
e
lec
ti
o
n
a
n
d
c
las
sifica
ti
o
n
m
e
t
h
o
d
s
u
sin
g
g
e
n
e
e
x
p
re
ss
io
n
p
ro
f
il
e
s a
n
d
p
r
o
teo
m
ic p
a
tt
e
rn
s,"
Ge
n
o
me
i
n
fo
rm
a
ti
c
s,
v
o
l.
1
3
,
p
p
.
5
1
-
6
0
,
2
0
0
2
.
[2
7
]
T.
Li
,
C.
Z
h
a
n
g
,
a
n
d
M
.
O
g
ih
a
ra
,
"
A
c
o
m
p
a
ra
ti
v
e
stu
d
y
o
f
fe
a
tu
r
e
se
lec
ti
o
n
a
n
d
m
u
lt
icla
ss
c
las
sifi
c
a
ti
o
n
m
e
th
o
d
s
fo
r
ti
ss
u
e
c
las
sifica
ti
o
n
b
a
se
d
o
n
g
e
n
e
e
x
p
re
ss
io
n
,
"
Bi
o
in
f
o
rm
a
ti
c
s,
v
o
l
.
2
0
,
n
o
.
1
5
,
p
p
.
2
4
2
9
-
2
4
3
7
,
2
0
0
4
.
[2
8
]
P
.
A.
M
u
n
d
ra
a
n
d
J.
C.
Ra
jap
a
k
se
,
"
S
VM
-
R
F
E
wit
h
M
R
M
R
fi
lt
e
r
fo
r
g
e
n
e
se
lec
ti
o
n
,
"
IEE
E
t
ra
n
sa
c
ti
o
n
s
o
n
n
a
n
o
b
io
sc
ien
c
e
,
v
o
l.
9
,
n
o
.
1
,
p
p
.
3
1
-
3
7
,
2
0
0
9
.
[2
9
]
J.
-
G
.
Zh
a
n
g
a
n
d
H.
-
W
.
De
n
g
,
"
G
e
n
e
se
lec
ti
o
n
fo
r
c
las
sifica
ti
o
n
o
f
m
icro
a
rra
y
d
a
ta
b
a
se
d
o
n
t
h
e
Ba
y
e
s
e
rro
r,
"
BM
C
b
io
i
n
fo
rm
a
ti
c
s,
v
o
l.
8
,
n
o
.
1
,
p
p
.
1
-
9
,
2
0
0
7
.
[3
0
]
E.
P
.
Xi
n
g
,
M
.
I.
Jo
rd
a
n
,
a
n
d
R.
M
.
Ka
rp
,
"
F
e
a
tu
re
se
lec
ti
o
n
f
o
r
h
ig
h
-
d
ime
n
si
o
n
a
l
g
e
n
o
m
ic
m
icr
o
a
rra
y
d
a
ta,"
in
Ic
ml
,
2
0
0
1
,
p
p
.
6
0
1
-
6
0
8
.
[3
1
]
J.
Ön
sk
o
g
,
E
.
F
re
y
h
u
lt
,
M
.
Lan
d
fo
rs,
P
.
Ry
d
é
n
,
a
n
d
T
.
R.
Hv
i
d
ste
n
,
"
C
las
sifica
ti
o
n
o
f
m
icro
a
rra
y
s;
sy
n
e
rg
isti
c
e
ffe
c
ts b
e
twe
e
n
n
o
rm
a
l
iza
ti
o
n
,
g
e
n
e
se
lec
ti
o
n
a
n
d
m
a
c
h
in
e
lea
rn
in
g
,
"
B
M
C
b
i
o
i
n
fo
rm
a
ti
c
s,
v
o
l.
1
2
,
2
0
1
1
.
[3
2
]
K.
Ra
z
a
a
n
d
A.
N.
Ha
sa
n
,
"
A
c
o
m
p
re
h
e
n
siv
e
e
v
a
lu
a
ti
o
n
o
f
m
a
c
h
i
n
e
lea
rn
in
g
tec
h
n
i
q
u
e
s
f
o
r
c
a
n
c
e
r
c
las
s
p
re
d
ictio
n
b
a
se
d
o
n
m
icro
a
rra
y
d
a
ta,
"
a
rX
iv
p
re
p
rin
t
a
rXiv:1
3
0
7
.
7
0
5
0
,
2
0
1
3
.
[3
3
]
S
.
Du
d
o
i
t,
J.
F
ri
d
ly
a
n
d
,
a
n
d
T.
P
.
S
p
e
e
d
,
"
C
o
m
p
a
riso
n
o
f
d
isc
rimin
a
ti
o
n
m
e
th
o
d
s
f
o
r
t
h
e
c
las
sifica
ti
o
n
o
f
tu
m
o
rs
u
sin
g
g
e
n
e
e
x
p
re
ss
io
n
d
a
ta,
"
J
o
u
r
n
a
l
o
f
t
h
e
Ame
ric
a
n
sta
ti
stic
a
l
a
ss
o
c
ia
ti
o
n
,
v
o
l.
9
7
,
n
o
.
4
5
7
,
p
p
.
7
7
-
8
7
,
2
0
0
2
.
[3
4
]
S.
-
B.
Ch
o
a
n
d
H.
-
H.
Wo
n
,
"
M
a
c
h
in
e
lea
rn
in
g
in
DN
A
m
i
c
ro
a
rra
y
a
n
a
ly
sis
fo
r
c
a
n
c
e
r
c
las
sifica
ti
o
n
,
"
i
n
Pro
c
e
e
d
in
g
s
o
f
t
h
e
Fi
rs
t
Asia
-
Pa
c
if
ic
b
io
i
n
f
o
rm
a
ti
c
s
c
o
n
fer
e
n
c
e
o
n
Bi
o
in
f
o
rm
a
ti
c
s
2
0
0
3
-
V
o
l
u
me
1
9
,
2
0
0
3
,
p
p
.
1
8
9
-
1
9
8
.
[3
5
]
H.
Ab
u
sa
m
ra
,
"
A
c
o
m
p
a
ra
ti
v
e
st
u
d
y
o
f
fe
a
tu
re
se
lec
ti
o
n
a
n
d
c
las
sifica
ti
o
n
m
e
th
o
d
s
fo
r
g
e
n
e
e
x
p
r
e
ss
io
n
d
a
ta
o
f
g
li
o
m
a
,
"
Pro
c
e
d
i
a
Co
m
p
u
ter
S
c
ien
c
e
,
v
o
l.
2
3
,
p
p
.
5
-
1
4
,
2
0
1
3
.
[3
6
]
C.
DIN
G
a
n
d
H.
P
ENG
,
"
M
in
i
m
u
m
Re
d
u
n
d
a
n
c
y
F
e
a
tu
re
S
e
lec
ti
o
n
fr
o
m
M
icro
a
rra
y
G
e
n
e
Ex
p
re
ss
io
n
Da
ta
,
"
J
o
u
rn
a
l
o
f
Bi
o
in
f
o
rm
a
ti
c
s
a
n
d
Co
mp
u
ta
ti
o
n
a
l
Bi
o
lo
g
y
,
v
o
l.
0
3
,
p
p
.
1
8
5
-
2
0
5
,
2
0
0
5
.
[3
7
]
M
.
Dra
m
iń
sk
i,
A.
Ra
d
a
-
Ig
les
ias
,
S
.
En
r
o
t
h
,
C.
Wa
d
e
li
u
s,
J.
K
o
ro
n
a
c
k
i,
a
n
d
J.
K
o
m
o
ro
ws
k
i,
"
M
o
n
t
e
Ca
rlo
fe
a
tu
re
se
lec
ti
o
n
fo
r
s
u
p
e
rv
ise
d
c
las
sifica
ti
o
n
,
"
B
io
i
n
fo
rm
a
ti
c
s,
v
o
l.
2
4
,
n
o
.
1
,
p
p
.
1
1
0
-
1
1
7
,
2
0
0
7
.
[3
8
]
H.
Alsh
a
m
lan
,
G
.
Ba
d
r,
a
n
d
Y.
Alo
h
a
li
,
"
m
RM
R
-
ABC:
a
h
y
b
r
id
g
e
n
e
se
lec
ti
o
n
a
l
g
o
rit
h
m
fo
r
c
a
n
c
e
r
c
las
sifica
ti
o
n
u
sin
g
m
icro
a
rra
y
g
e
n
e
e
x
p
re
ss
io
n
p
ro
fi
li
n
g
,
"
Bi
o
me
d
re
se
a
rc
h
in
ter
n
a
ti
o
n
a
l,
v
o
l.
2
0
1
5
,
n
o
.
9
,
p
p
.
1
-
1
5
,
2
0
1
5
.
[3
9
]
J.
Jä
g
e
r,
R.
S
e
n
g
u
p
ta,
a
n
d
W.
L
.
Ru
z
z
o
,
"
Im
p
r
o
v
e
d
g
e
n
e
se
lec
ti
o
n
fo
r
c
las
sifica
ti
o
n
o
f
m
icro
a
rr
a
y
s,"
in
P
a
c
if
ic
S
y
mp
o
si
u
m o
n
Bi
o
c
o
mp
u
ti
n
g
.
Pa
c
if
ic S
y
mp
o
si
u
m o
n
Bi
o
c
o
mp
u
ti
n
g
,
v
o
l.
8
,
2
0
0
3
,
p
p
.
53
-
64
.
[4
0
]
H.
Li
u
,
L
.
Li
u
,
a
n
d
H.
Zh
a
n
g
,
"
En
se
m
b
le
g
e
n
e
se
lec
ti
o
n
f
o
r
c
a
n
c
e
r
c
las
s
ifi
c
a
ti
o
n
,
"
Pa
tt
e
rn
Rec
o
g
n
it
i
o
n
,
v
o
l.
4
3
,
n
o
.
8
,
p
p
.
2
7
6
3
-
2
7
7
2
,
2
0
1
0
.
[4
1
]
F
.
Va
fa
e
e
S
h
a
rb
a
f,
S
.
M
o
sa
fe
r,
a
n
d
M
.
H.
M
o
a
t
tar,
"
A
h
y
b
ri
d
g
e
n
e
se
lec
ti
o
n
a
p
p
r
o
a
c
h
fo
r
m
icro
a
rra
y
d
a
ta
c
las
sifica
ti
o
n
u
si
n
g
c
e
ll
u
lar
lea
rn
in
g
a
u
t
o
m
a
ta
a
n
d
a
n
t
c
o
l
o
n
y
o
p
ti
m
iza
ti
o
n
,
"
Ge
n
o
mic
s,
v
o
l.
1
0
7
,
n
o
.
6
,
p
p
.
2
3
1
-
2
3
8
,
2
0
1
6
.
[4
2
]
A.
K.
Dw
iv
e
d
i,
"
Artifi
c
ial
n
e
u
ra
l
n
e
two
rk
m
o
d
e
l
f
o
r
e
ffe
c
ti
v
e
c
a
n
c
e
r
c
las
sifica
ti
o
n
u
sin
g
m
icro
a
rra
y
g
e
n
e
e
x
p
re
ss
io
n
d
a
ta,"
Ne
u
ra
l
C
o
mp
u
ti
n
g
a
n
d
A
p
p
li
c
a
ti
o
n
s,
v
o
l
.
2
9
,
n
o
.
1
2
,
p
p
.
1
5
4
5
-
1
5
5
4
,
2
0
1
8
.
[4
3
]
K.
To
m
c
z
a
k
,
P
.
Cz
e
rwiń
sk
a
,
a
n
d
M
.
Wi
z
n
e
r
o
wic
z
,
"
T
h
e
Ca
n
c
e
r
G
e
n
o
m
e
Atlas
(TC
G
A):
a
n
imm
e
a
su
ra
b
le
so
u
rc
e
o
f
k
n
o
wle
d
g
e
,
"
Co
n
tem
p
o
r
a
ry
o
n
c
o
lo
g
y
(
Po
zn
a
n
,
P
o
la
n
d
),
v
o
l.
1
9
,
n
o
.
1
A,
p
p
.
A6
8
-
A7
7
,
2
0
1
5
.
[4
4
]
K.
-
B.
Du
a
n
,
J.
C.
Ra
jap
a
k
se
,
H.
Wan
g
,
a
n
d
F
.
Az
u
a
je,
"
M
u
lt
ip
le
S
VM
-
RF
E
fo
r
g
e
n
e
se
lec
ti
o
n
i
n
c
a
n
c
e
r
c
las
sifica
ti
o
n
with
e
x
p
re
ss
io
n
d
a
t
a
,
"
IEE
E
tra
n
s
a
c
ti
o
n
s o
n
n
a
n
o
b
io
sc
ien
c
e
,
v
o
l.
4
,
n
o
.
3
,
p
p
.
2
2
8
-
2
3
4
,
2
0
0
5
.
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 Co
n
tr
o
l
,
Vo
l.
1
9
,
No
.
2
,
Ap
r
il
202
1
:
49
1
-
498
498
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Aw
s
Na
se
r
J
a
b
e
r
is
c
u
rre
n
tl
y
a
n
In
f
o
rm
a
ti
o
n
S
e
c
u
rit
y
Ex
p
e
rt
a
t
Earth
Li
n
k
Tele
c
o
m
m
u
n
ica
ti
o
n
s.
He
re
c
e
iv
e
d
h
is
BS
c
fro
m
Al
-
M
u
sta
n
siri
y
a
Un
iv
e
rsity
,
h
is
M
S
c
fro
m
Un
iv
e
rsiti
S
a
i
n
s
M
a
lay
sia
,
a
n
d
h
is
P
h
D
fr
o
m
Un
i
v
e
rsiti
M
a
lay
sia
P
a
h
a
n
g
.
His
e
x
p
e
rti
se
in
c
lu
d
e
s c
ry
p
t
o
g
ra
p
h
y
,
c
y
b
e
rse
c
u
rit
y
,
a
rti
f
icia
l
in
tell
ig
e
n
c
e
,
a
n
d
b
i
o
in
f
o
rm
a
ti
c
s.
K
o
h
b
a
l
a
n
M
o
o
r
th
y
is
c
u
rre
n
tl
y
a
S
e
n
io
r
Lec
tu
re
r
a
t
th
e
F
a
c
u
lt
y
o
f
Co
m
p
u
ti
n
g
a
t
Un
i
v
e
rsit
i
M
a
lay
sia
P
a
h
a
n
g
.
He
re
c
e
iv
e
d
h
i
s
BS
c
a
n
d
P
h
D
fro
m
Un
iv
e
rsiti
Tek
n
o
lo
g
i
M
a
lay
sia
in
th
e
a
re
a
o
f
Co
m
p
u
ter
S
c
ie
n
c
e
.
His
a
re
a
o
f
e
x
p
e
rti
se
in
c
l
u
d
e
s
Bio
in
f
o
rm
a
ti
c
s,
M
e
d
ica
l
In
fo
rm
a
ti
c
s,
Co
m
p
u
tati
o
n
a
l
B
io
l
o
g
y
,
Artifi
c
ial
In
telli
g
e
n
c
e
,
I
o
T
a
n
d
o
th
e
r
re
late
d
field
s
i
n
Co
m
p
u
ter
S
c
ien
c
e
.
He
h
a
s
wo
n
m
a
n
y
re
se
a
rc
h
a
wa
rd
s
o
n
b
o
t
h
t
h
e
lo
c
a
l
a
n
d
i
n
tern
a
ti
o
n
a
l
lev
e
ls.
He
is
a
lso
a
M
icro
so
ft
C
e
rti
fied
P
ro
fe
ss
io
n
a
l
(M
CP
)
a
n
d
P
ro
fe
ss
io
n
a
l
Tec
h
n
o
lo
g
ist
(P
.
Tec
h
).
He
is
c
u
rre
n
tl
y
a
c
ti
v
e
in
Re
se
a
rc
h
,
M
a
n
a
g
e
m
e
n
t,
Tea
c
h
in
g
&
Lea
rn
in
g
i
n
th
e
Un
iv
e
rsity
M
a
lay
sia
P
a
h
a
n
g
.
Lo
g
e
n
th
ir
a
n
M
a
c
h
a
p
is
c
u
rr
e
n
t
ly
wo
r
k
in
g
a
s
a
Lec
tu
re
r
a
t
t
h
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ti
n
g
a
n
d
In
f
o
rm
a
ti
o
n
Tec
h
n
o
lo
g
y
in
Tu
n
k
u
A
b
d
u
l
Ra
h
m
a
n
Un
i
v
e
rsit
y
Co
ll
e
g
e
.
He
c
o
m
p
lete
d
B.
S
c
.
Bio
i
n
fo
rm
a
ti
c
s
fro
m
Na
ti
o
n
a
l
Un
iv
e
rsit
y
o
f
M
a
lay
sia
(UK
M
)
a
n
d
M
a
ste
r
o
f
Co
m
p
u
te
r
S
c
ien
c
e
fro
m
U
n
iv
e
rsit
y
o
f
T
e
c
h
n
ica
l
M
a
lay
sia
M
e
lak
a
(UTe
M
).
He
is
a
P
h
D
c
a
n
d
i
d
a
te
fo
r
c
o
m
p
u
ter
sc
ien
c
e
fro
m
th
e
Un
iv
e
rsity
o
f
Tec
h
n
o
l
o
g
y
M
a
lay
sia
(UTM
).
He
is
wo
rk
i
n
g
o
n
th
e
co
-
c
lu
ste
rin
g
a
l
g
o
rit
h
m
a
n
d
it
s
a
p
p
li
c
a
ti
o
n
o
n
c
a
n
c
e
r
m
icro
a
rra
y
g
e
n
e
e
x
p
re
ss
io
n
d
a
ta.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
d
a
ta
m
in
in
g
,
m
a
c
h
in
e
lea
rn
in
g
,
a
rti
ficia
l
in
telli
g
e
n
c
e
,
a
n
d
b
io
i
n
fo
rm
a
ti
c
s.
S
a
fa
a
i
De
r
is
is
a
P
r
o
fe
ss
o
r
a
t
t
h
e
F
a
c
u
lt
y
o
f
B
io
e
n
g
in
e
e
ri
n
g
a
n
d
Tec
h
n
o
lo
g
y
,
Un
i
v
e
rsity
M
a
lay
sia
Ke
lan
tan
.
He
wa
s a
P
ro
fe
ss
o
r
o
f
Artifi
c
ial
In
telli
g
e
n
c
e
a
n
d
S
o
ftwa
re
En
g
i
n
e
e
rin
g
a
t
th
e
F
a
c
u
lt
y
o
f
Co
m
p
u
ti
n
g
,
Un
i
v
e
rsiti
Tek
n
o
lo
g
i
M
a
lay
sia
.
He
is
th
e
CIO
a
n
d
Dire
c
to
r
o
f
th
e
Ce
n
ter
fo
r
In
fo
rm
a
ti
o
n
a
n
d
Co
m
m
u
n
ica
ti
o
n
Tec
h
n
o
l
o
g
y
.
His
p
re
v
io
u
s
p
o
sit
io
n
s
i
n
c
lu
d
e
De
p
u
ty
De
a
n
o
f
t
h
e
S
c
h
o
o
l
o
f
G
ra
d
u
a
te
S
tu
d
ies
a
n
d
He
a
d
o
f
S
o
f
twa
re
En
g
i
n
e
e
rin
g
De
p
a
rtme
n
t.
He
is
a
lso
He
a
d
o
f
Artifi
c
ial
In
tell
ig
e
n
c
e
a
n
d
B
io
i
n
f
o
rm
a
ti
c
s
Re
se
a
rc
h
G
ro
u
p
,
He
re
c
e
iv
e
d
th
e
M
.
E
n
g
.
d
e
g
re
e
in
In
d
u
strial
E
n
g
in
e
e
rin
g
,
a
n
d
th
e
D.
E
n
g
.
d
e
g
re
e
i
n
Co
m
p
u
ter
a
n
d
S
y
ste
m
S
c
ien
c
e
s,
b
o
th
fr
o
m
th
e
Os
a
k
a
P
re
fe
c
tu
re
Un
iv
e
rsity
,
Ja
p
a
n
.
His
re
se
a
rc
h
in
tere
sts
in
c
l
u
d
e
so
ftw
a
re
e
n
g
i
n
e
e
rin
g
,
a
p
p
li
c
a
ti
o
n
s
o
f
in
telli
g
e
n
t
tec
h
n
i
q
u
e
s
i
n
p
lan
n
in
g
,
sc
h
e
d
u
li
n
g
,
b
i
o
in
f
o
rm
a
ti
c
s,
a
n
d
s
y
ste
m
b
io
l
o
g
y
.
He
h
a
s
p
u
b
li
sh
e
d
m
o
re
th
a
n
2
0
0
jo
u
r
n
a
ls an
d
c
o
n
fe
re
n
c
e
re
fe
re
e
d
p
a
p
e
rs.
Evaluation Warning : The document was created with Spire.PDF for Python.