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.
19
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
1
,
p
p
.
31
0
~
3
16
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
i1
.
1
6
3
8
1
310
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
A genetic
alg
o
rith
m a
ppro
a
ch f
o
r p
redicting
ribo
nuc
leic acid
sequencing
da
ta
c
la
ss
ificatio
n using
K
N
N
a
nd d
ecisio
n t
ree
M
ichea
l O
la
o
lu Ar
o
wo
lo
,
M
a
rio
n O
lub
un
m
i A
debiy
i
,
Ay
o
dele
Ariy
o
Adebiy
i
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
,
Lan
d
m
a
rk
Un
i
v
e
rsity
,
Om
u
-
Ara
n
,
Kw
a
ra
S
tate
,
Nig
e
ria
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ap
r
1
4
,
2
0
2
0
R
ev
is
ed
J
u
n
9
,
2
0
2
0
Acc
ep
ted
Sep
2
4
,
2
0
2
0
M
a
laria
larv
a
e
a
c
c
e
p
t
e
x
p
lo
siv
e
v
a
riab
le
li
fe
c
y
c
le
a
s
th
e
y
sp
re
a
d
a
c
ro
ss
n
u
m
e
ro
u
s
m
o
s
q
u
i
to
v
e
c
to
r
stra
to
s
p
h
e
re
.
Tran
sc
rip
to
m
e
s
a
rise
in
th
o
u
sa
n
d
s
o
f
d
iv
e
rse
p
a
ra
sites
.
Rib
o
n
u
c
leic
a
c
id
se
q
u
e
n
c
in
g
(RNA
-
se
q
)
is a p
re
v
a
len
t
g
e
n
e
e
x
p
re
ss
io
n
t
h
a
t
h
a
s
led
t
o
e
n
h
a
n
c
e
d
u
n
d
e
rsta
n
d
in
g
o
f
g
e
n
e
ti
c
q
u
e
r
ies
.
RNA
-
se
q
tes
ts
tran
sc
rip
t
o
f
g
e
n
e
e
x
p
re
ss
io
n
,
a
n
d
p
r
o
v
i
d
e
s
m
e
th
o
d
o
lo
g
ica
l
e
n
h
a
n
c
e
m
e
n
ts
to
m
a
c
h
i
n
e
lea
rn
i
n
g
p
ro
c
e
d
u
re
s.
Re
se
a
rc
h
e
rs
h
a
v
e
p
ro
p
o
se
d
se
v
e
ra
l
m
e
th
o
d
s in
e
v
a
lu
a
ti
n
g
a
n
d
lea
rn
in
g
b
io
l
o
g
ica
l
d
a
ta.
G
e
n
e
ti
c
a
lg
o
rit
h
m
(G
A)
a
s
a
fe
a
tu
re
se
lec
ti
o
n
p
r
o
c
e
ss
is
u
se
d
i
n
t
h
is
stu
d
y
to
fe
tch
re
lev
a
n
t
in
fo
rm
a
ti
o
n
fro
m
th
e
RNA
-
S
e
q
M
o
sq
u
it
o
A
n
o
p
h
e
les
g
a
m
b
iae
m
a
laria
v
e
c
to
r
d
a
tas
e
t,
a
n
d
e
v
a
lu
a
tes
th
e
re
su
lt
s
u
sin
g
k
th
n
e
a
re
st
n
e
ig
h
b
o
r
(
KNN
)
a
n
d
d
e
c
isio
n
tree
c
las
sifica
ti
o
n
a
l
g
o
ri
th
m
s.
Th
e
e
x
p
e
rime
n
tal
re
su
lt
s
o
b
tai
n
e
d
a
c
las
sifica
ti
o
n
a
c
c
u
ra
c
y
o
f
8
8
.
3
a
n
d
9
8
.
3
p
e
rc
e
n
ts r
e
sp
e
c
ti
v
e
l
y
.
K
ey
w
o
r
d
s
:
Dec
is
io
n
tr
ee
Gen
etic
alg
o
r
ith
m
KNN
Mo
s
q
u
ito
a
n
o
p
h
eles
R
ib
o
n
u
cleic
ac
id
s
eq
u
en
ci
n
g
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
:
Mic
h
ea
l O
lao
lu
Ar
o
wo
lo
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
L
am
d
m
ar
k
Un
iv
er
s
ity
Om
u
-
Ar
an
,
Kwa
r
a
State
Nig
er
ia
E
m
ail:
ar
o
wo
lo
.
o
la
o
lu
@
lm
u
.
e
d
u
.
n
g
1.
I
NT
RO
D
UCT
I
O
N
Nex
t
-
g
en
er
atio
n
h
i
g
h
-
th
r
o
u
g
h
p
u
t
s
eq
u
e
n
cin
g
tech
n
o
lo
g
y
h
a
s
cr
ea
ted
p
r
o
f
u
s
e
wid
e
-
r
a
n
g
in
g
d
atasets
,
th
is
en
o
r
m
o
u
s
d
ata
ex
p
a
n
s
e
h
elp
s
b
io
lo
g
is
ts
to
an
aly
ze
an
d
p
er
f
o
r
m
d
a
u
n
tin
g
g
en
e
tr
an
s
cr
i
p
ts
,
s
u
ch
as d
is
ea
s
e
r
elate
d
an
d
R
NA
s
u
ch
as
in
f
ec
tio
n
s
(
m
alar
ia)
,
ca
n
ce
r
,
i
n
h
er
ited
,
g
e
n
etics,
p
h
y
s
io
lo
g
y
,
am
o
n
g
o
th
e
r
s
[
1
]
.
B
lo
o
d
-
s
u
ck
in
g
m
o
s
q
u
ito
es
s
u
ch
as
Mo
s
q
u
ito
A
n
o
p
h
eles
wi
th
v
ec
to
r
s
o
f
m
alar
ia
p
lasmo
d
iu
m
f
alcip
a
r
u
m
ar
e
f
o
u
n
d
in
Af
r
ica.
Mo
s
q
u
ito
An
o
p
h
eles
is
a
d
ea
d
ly
m
alar
ia
p
ar
asit
e,
r
esp
o
n
s
ib
le
f
o
r
d
e
m
is
es
o
f
th
o
u
s
an
d
s
o
f
h
u
m
an
s
d
ail
y
.
An
tim
alar
ia
co
m
b
at
s
u
p
p
o
s
ito
r
ies
b
lo
wo
u
ts
,
s
tate
-
of
-
th
e
-
ar
t
a
n
tim
alar
ials
tr
ea
tm
en
t
u
p
s
u
r
g
es,
f
etch
in
g
f
o
r
g
r
o
u
n
d
-
b
r
ea
k
in
g
m
ed
icatio
n
s
r
eq
u
ir
es
im
p
r
o
v
e
d
b
io
tic
s
tu
d
ies
o
f
t
h
is
i
n
f
en
c
tio
n
s
.
T
h
e
p
ar
asit
e
to
ler
ates
p
r
ec
is
e
p
ar
am
eter
o
f
g
en
e
ex
p
r
ess
io
n
q
u
er
y
e
n
o
r
m
o
u
s
ly
an
d
n
ec
ess
itates
m
ak
in
g
en
h
an
ce
d
th
o
r
o
u
g
h
ex
tr
ap
o
lativ
e
m
o
d
el
tr
an
s
cr
ip
ti
o
n
s
o
f
v
ec
t
o
r
s
[
2
]
.
Ap
p
r
o
ac
h
a
b
le
r
ev
ea
lin
g
g
e
n
et
ic
in
q
u
ir
ies h
av
e
b
ee
n
m
ad
e
in
r
ib
o
n
u
cleic
ac
i
d
s
eq
u
en
cin
g
(
R
NA
-
s
eq
)
s
tu
d
y
b
y
u
n
f
o
ld
i
n
g
a
ca
u
tio
u
s
p
u
r
p
o
s
ef
u
l
b
io
lo
g
ical
s
tr
ateg
y
f
o
r
en
h
a
n
ce
m
en
t
o
f
th
e
lear
n
i
n
g
.
R
NA
-
Seq
d
ata
r
eq
u
ir
es
r
e
m
o
v
al
o
f
ex
p
letiv
e
h
ig
h
-
d
im
en
s
io
n
,
s
u
ch
as;
n
o
i
s
es,
co
m
p
lain
ts
,
r
ep
etitio
n
,
ir
r
elev
an
t,
in
ac
tiv
ity
,
u
n
f
itti
n
g
d
ata,
an
d
o
th
er
s
[
3
]
.
New
ca
p
ab
ilit
ies
s
tr
en
g
th
en
s
o
lu
tio
n
s
to
th
e
d
ev
elo
p
m
e
n
t
o
f
g
r
o
u
n
d
-
b
r
ea
k
i
n
g
h
ea
lth
ca
r
e
f
r
am
ew
o
r
k
s
s
u
ch
as
ef
f
ec
tiv
e
p
u
b
lic
wellb
ein
g
n
u
r
s
in
g
s
y
s
tem
s
,
ad
v
an
ce
d
in
ter
v
e
n
tio
n
s
an
d
m
e
d
ical
d
iag
n
o
s
is
an
d
d
is
o
r
d
er
s
[
4
]
.
Ma
ch
in
e
lear
n
in
g
m
ea
n
s
h
a
v
e
b
ee
n
estab
lis
h
ed
with
co
n
v
in
cin
g
u
n
iq
u
en
ess
to
in
v
e
s
tig
ate
th
e
en
o
r
m
o
u
s
am
o
u
n
t
o
f
cu
ttin
g
-
ed
g
e
R
NA
-
Seq
k
n
o
wled
g
e
b
y
s
tu
d
y
in
g
t
h
e
n
atu
r
ally
m
ater
ial
s
tr
u
ctu
r
es
[
5
]
.
Scien
tis
ts
h
av
e
u
s
ed
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
with
r
elev
an
t
ac
h
iev
em
en
t
f
o
r
g
e
n
e
ex
p
r
e
s
s
io
n
d
ata
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
A
g
en
etic
a
lg
o
r
ith
m
a
p
p
r
o
a
c
h
fo
r
p
r
ed
ictin
g
r
ib
o
n
u
cleic
a
ci
d
s
eq
u
en
cin
g
d
a
t
a
… (
Mich
ea
l O
la
o
lu
A
r
o
w
o
lo
)
311
o
f
R
NA
-
Seq
[
6
-
8
]
.
I
n
th
is
s
tu
d
y
,
a
g
en
etic
alg
o
r
ith
m
(
GA)
p
r
e
-
p
r
o
ce
s
s
o
r
,
to
o
b
tain
r
e
d
u
c
ed
d
im
en
s
io
n
ality
o
f
d
ata
with
k
th
n
ea
r
est
n
eig
h
b
o
r
(
KNN
)
an
d
d
ec
is
io
n
tr
ee
cla
s
s
if
ier
s
ar
e
p
r
o
p
o
s
ed
to
class
if
y
d
is
cr
ete
g
en
etic
s
tr
u
ctu
r
es
an
d
o
b
ta
in
ad
v
an
ce
s
th
at
ar
e
s
u
itab
le
s
y
s
tem
f
o
r
p
r
e
d
ictin
g
an
d
d
etec
tin
g
i
n
n
o
v
ativ
e
g
en
es
f
o
r
m
alar
ia
ailm
en
ts
in
h
u
m
an
.
2.
RE
VI
E
W
S
C
o
m
p
u
tatio
n
al
p
r
o
ce
d
u
r
es
ar
e
b
ased
o
n
en
o
r
m
o
u
s
s
am
p
le
s
o
f
in
d
i
v
id
u
als
g
e
n
es
with
o
r
with
o
u
t
d
is
ea
s
es,
m
u
tatio
n
s
m
ay
b
e
f
o
u
n
d
ac
co
u
n
tab
le
f
o
r
th
e
p
r
ec
en
s
e
o
f
d
is
ea
s
es.
Dif
f
er
en
tial
ex
p
r
ess
ed
g
en
es
(
DE
G)
ar
e
d
ef
in
ed
th
r
o
u
g
h
s
o
m
e
m
eth
o
d
s
.
Ma
ch
in
e
L
ea
r
n
in
g
m
ea
s
u
r
es
ar
e
im
p
o
r
tan
t
f
o
r
s
p
o
ttin
g
th
e
v
ar
iatio
n
b
etwe
en
g
en
es
f
o
u
n
d
f
r
o
m
h
u
m
an
g
en
o
m
e.
Ma
ch
in
e
lear
n
in
g
tech
n
iq
u
es
h
av
e
b
ee
n
e
m
u
lated
s
ev
er
ally
in
in
v
esti
g
atin
g
an
d
class
if
y
in
g
v
ar
io
u
s
p
r
o
f
iles
o
f
d
is
ea
s
es
g
en
e
e
x
p
r
ess
io
n
s
.
Var
i
o
u
s
m
ac
h
in
e
lear
n
i
n
g
ap
p
r
o
ac
h
es a
r
e
r
ep
o
r
t
ed
a
n
d
r
e
v
iewe
d
,
u
s
in
g
r
e
ce
n
t tr
en
d
s
in
th
e
ev
alu
atio
n
s
[
4
]
.
Ma
ch
in
e
lear
n
i
n
g
f
o
r
p
r
ed
ictin
g
Au
tis
m
s
p
ec
tr
u
m
ailm
en
t
w
as
ex
p
er
im
en
te
d
a
n
d
class
if
y
tr
an
s
cr
ip
ts
,
u
s
in
g
R
NA
d
ata
f
r
o
m
g
en
e
o
m
n
ib
u
s
ex
p
r
ess
io
n
d
ata.
T
h
is
s
tu
d
y
r
an
k
ed
clu
s
ter
an
aly
s
is
an
d
r
elati
v
ely
d
is
cr
im
in
ated
,
u
s
in
g
SVM
an
d
KNN
clas
s
if
ier
s
,
an
esti
m
ate
a
cc
u
r
ac
y
o
f
9
4
%
was
ac
h
iev
ed
[
9
]
.
C
lu
s
ter
in
g
an
d
class
if
icatio
n
o
f
R
NA
-
Seq
d
ata
was
ca
r
r
ied
o
u
t
b
y
p
er
f
o
r
m
in
g
a
m
u
tu
al
v
alu
atio
n
,
a
n
d
em
p
h
asizin
g
th
e
ex
p
er
tis
e
an
d
p
lo
y
s
o
f
m
eth
o
d
s
o
cc
u
r
r
in
g
in
r
e
ce
n
t
tim
e
a
s
p
r
ed
o
m
in
a
n
t
s
h
if
ts
,
u
in
g
n
o
n
lin
ea
r
an
d
lin
ea
r
d
im
en
s
io
n
r
ed
u
ctio
n
s
y
s
tem
s
,
b
y
co
m
b
in
in
g
s
cRNA
-
s
eq
d
ata
[
1
0
]
.
Gr
o
u
p
o
f
R
NA
-
Seq
g
en
e
s
f
o
r
r
an
k
in
g
g
en
es
s
et
o
f
h
u
g
e
en
s
em
b
les
u
s
in
g
a
s
u
p
er
v
is
ed
lear
n
in
g
ap
p
r
o
ac
h
was
ca
r
r
ied
o
u
t
u
s
in
g
r
an
d
o
m
f
o
r
ests
clas
s
if
icatio
n
m
eth
o
d
,
o
n
1
2
1
0
s
am
p
les
o
f
tu
m
o
r
R
NA
-
Seq
d
atasets
s
h
o
wed
h
id
d
en
s
u
p
e
r
v
is
ed
lear
n
in
g
s
elec
tio
n
ap
p
r
o
ac
h
es
n
ec
ess
ity
o
n
a
n
aly
s
is
[
1
1
]
.
A
s
u
p
er
v
is
ed
s
in
g
le
-
ce
ll
R
NA
-
Seq
d
ata
class
if
icatio
n
m
o
d
el
wa
s
p
r
o
p
o
s
ed
u
s
in
g
a
co
m
p
r
eh
e
n
s
iv
e
ap
p
r
o
ac
h
b
y
c
o
m
b
in
in
g
in
d
ep
e
n
d
en
t
f
ea
tu
r
e
s
elec
tio
n
ap
p
r
o
ac
h
es.
s
cPr
ed
R
NA
-
s
eq
d
ataset
s
s
h
o
wed
h
ig
h
ac
cu
r
ac
y
[
1
2
]
.
R
NA
-
DNA
m
ac
h
in
e
lear
n
in
g
an
aly
s
is
was
p
r
o
p
o
s
ed
to
in
d
icate
s
m
all
g
en
o
m
e
ex
p
r
ess
io
n
to
in
f
lu
e
n
ce
PAH
ailm
en
t,
f
ea
tu
r
e
s
elec
tio
n
alg
o
r
i
th
m
was
p
r
o
p
o
s
ed
to
class
if
y
r
elev
an
t
g
en
es
with
an
o
u
tco
m
e
th
at
r
ev
e
als u
n
iq
u
e
PAH
[
1
3
]
.
Sto
m
ac
h
tu
m
o
r
g
e
n
e
ex
p
r
ess
io
n
d
ata
u
s
in
g
C
NN
class
if
icatio
n
p
r
o
ce
d
u
r
e
was
d
ev
elo
p
ed
b
ased
o
n
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
,
6
0
,
0
0
0
d
ata
m
ad
e
u
p
o
f
s
to
m
ac
h
tu
m
o
r
g
en
es
wer
e
e
v
alu
ated
u
s
i
n
g
PC
A)
,
h
ea
tm
ap
s
,
an
d
C
NN
alg
o
r
ith
m
s
with
an
ac
cu
r
ac
y
o
f
9
6
%
an
d
5
1
%
[
1
4
]
.
R
NA
-
Seq
h
id
d
en
tr
an
s
cr
ip
ts
in
m
alar
ia
p
ar
asit
es
was
p
r
o
p
o
s
ed
b
y
r
elatin
g
v
a
r
iatio
n
s
o
f
p
r
o
ce
d
u
r
es
to
d
ec
o
n
v
o
lu
te
tr
a
n
s
cr
ip
tio
n
al
d
if
f
e
r
en
ce
s
f
o
r
d
is
tin
ct
m
o
s
q
u
ito
s
an
d
r
ev
ea
led
h
id
d
e
n
d
is
tin
ct
tr
an
s
cr
ip
tio
n
al
s
ig
n
a
tu
r
es [
1
5
]
.
An
en
s
em
b
le
class
if
icatio
n
alg
o
r
ith
m
f
o
r
ca
n
ce
r
d
ataset
was
d
ev
elo
p
e
d
u
s
in
g
d
ec
is
io
n
tr
ee
,
en
s
em
b
le
d
ec
is
io
n
tr
ee
s
alg
o
r
ith
m
s
o
n
av
ailab
le
ca
n
ce
r
o
u
s
m
icr
o
ar
r
ay
,
th
e
r
esu
lts
en
h
a
n
ce
s
th
an
th
e
d
ec
is
io
n
tr
ee
s
class
if
icatio
n
[
1
6
]
.
An
in
v
esti
g
ativ
e
ca
n
ce
r
g
en
e
ex
p
r
ess
io
n
en
s
em
b
le
class
if
icat
io
n
m
eth
o
d
was
p
r
o
p
o
s
ed
u
s
in
g
a
h
y
b
r
i
d
R
FE
-
Ad
ab
o
o
s
t
alg
o
r
ith
m
to
f
etc
h
s
ig
n
if
ican
t
f
ea
tu
r
es
f
o
r
en
h
a
n
cin
g
class
if
icatio
n
p
er
f
o
r
m
an
ce
t
[
1
7
]
.
C
lass
if
icat
io
n
o
f
ca
n
ce
r
d
ata
was
ca
r
r
ie
d
o
u
t
u
s
in
g
an
ef
f
ec
tiv
e
e
n
s
em
b
le
class
if
icatio
n
m
eth
o
d
by
in
cr
ea
s
in
g
th
e
class
if
icatio
n
,
th
e
r
esu
lt
wer
e
le
s
s
co
n
tin
g
en
t
[
1
8
]
.
A
m
etah
e
u
r
is
tics
s
y
s
tem
f
o
r
f
etch
in
g
r
elev
an
t
R
NA/DNA
d
ata
g
en
es
f
o
r
class
if
icati
o
n
was
p
r
o
p
o
s
ed
b
y
b
r
ief
in
g
r
ec
en
t
d
ev
el
o
p
m
en
ts
o
f
m
etah
eu
r
is
tic
-
b
ased
m
eth
o
d
s
in
em
b
e
d
d
ed
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
s
,
u
s
ef
u
l
d
ata
f
o
r
o
p
e
r
ativ
es
f
o
r
r
an
k
in
g
co
ef
f
icien
ts
o
f
SVM
class
if
ier
is
u
s
ed
[
1
9
]
.
A
GA
p
r
esen
tin
g
a
s
tate
-
of
-
th
e
-
a
r
t
ap
p
r
o
ac
h
was
p
r
o
p
o
s
ed
u
s
in
g
f
ilter
-
wr
ap
p
er
b
ased
f
ea
tu
r
e
s
e
lectio
n
o
n
f
iv
e
b
i
o
lo
g
ical
d
ata
s
ets,
th
e
r
esu
lts
s
h
o
wed
an
im
p
o
r
tan
t r
e
d
u
ctio
n
o
f
f
ea
tu
r
es
f
o
r
class
if
icatio
n
[
2
0
]
.
An
e
n
h
an
ce
d
en
s
em
b
le
cla
s
s
if
icatio
n
f
o
r
ce
r
tain
f
ea
tu
r
e
s
was
p
r
o
p
o
s
ed
f
o
r
lear
n
in
g
a
n
en
s
em
b
le
-
b
ased
f
e
atu
r
e
s
elec
tio
n
ap
p
r
o
ac
h
with
r
an
d
o
m
tr
ee
s
u
s
in
g
a
s
u
b
s
et,
t
h
e
m
eth
o
d
r
em
o
v
es
th
e
u
n
f
itti
n
g
s
tr
u
ctu
r
es
a
n
d
p
ic
k
s
th
e
b
est
s
tr
u
ctu
r
es
b
y
m
ea
n
s
o
f
a
p
r
o
b
ab
ilit
y
weig
h
in
g
v
alu
e
f
o
r
class
if
icatio
n
ev
alu
atio
n
u
s
in
g
R
F,
SVM,
an
d
NB
[
2
1
]
.
R
ev
iew
o
f
s
ev
e
r
al
f
ea
tu
r
e
e
x
tr
ac
tio
n
alg
o
r
ith
m
s
f
o
r
g
e
n
e
e
x
p
r
ess
io
n
in
v
esti
g
atio
n
,
s
u
ch
as
th
e
PC
A,
I
C
A,
PLS,
an
d
L
L
E
was
ca
r
r
ied
o
u
t
an
d
d
is
cu
s
s
ed
f
o
r
th
e
p
u
r
p
o
s
e
o
f
t
h
e
m
ac
h
in
e
lear
n
in
g
ap
p
licatio
n
s
[
2
2
]
.
3.
M
AT
E
R
I
AL
S AN
D
M
E
T
H
O
DS
Sev
er
al
h
ig
h
-
d
im
en
s
io
n
al
d
at
a
en
h
an
ce
m
e
n
t
m
eth
o
d
s
ar
e
in
p
lace
,
th
is
p
ap
er
ca
r
r
ies
o
u
t
a
f
ea
tu
r
e
s
elec
tio
n
u
s
in
g
GA
tech
n
iq
u
e
an
d
en
s
em
b
le
class
if
icatio
n
alg
o
r
ith
m
f
o
r
f
etch
in
g
r
ele
v
an
t
i
n
f
o
r
m
atio
n
in
a
h
u
g
e
d
im
en
s
io
n
al
d
ata
an
d
class
if
icatio
n
.
A
wester
n
Ken
y
a
R
NA
-
Seq
d
ata
m
o
s
q
u
ito
s
’
g
en
es
with
2
4
5
7
i
n
s
tan
ce
s
with
7
g
en
e
attr
ib
u
tes
[
2
3
]
,
M
AT
L
AB
en
v
ir
o
n
m
en
t
to
o
l
is
u
s
ed
ca
r
r
y
o
u
t
th
e
ex
p
er
im
en
t
u
s
in
g
GA
to
s
elec
t
r
elev
an
t
s
u
b
s
et
o
f
f
ea
tu
r
es
f
r
o
m
th
e
d
ataset
as
s
h
o
wn
in
T
a
b
le
1
,
E
n
s
em
b
le
alg
o
r
ith
m
a
p
p
r
o
ac
h
is
u
s
ed
as
a
class
if
ier
o
n
th
e
s
elec
ted
f
ea
tu
r
es [
2
4
]
.
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.
19
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
1
:
31
0
-
3
16
312
T
ab
le
1
.
Featu
r
es o
f
th
e
d
ata
D
a
t
a
s
e
t
A
t
t
r
i
b
u
t
e
s
I
n
st
a
n
c
e
s
M
o
s
q
u
i
t
o
A
n
o
p
h
e
l
e
s Gam
b
i
a
e
7
2
4
5
7
3
.
1
.
G
A
GA
is
a
wr
ap
p
er
-
b
ased
f
ea
t
u
r
e
s
elec
tio
n
ap
p
r
o
ac
h
th
at
ex
a
m
in
es
s
u
itab
le
f
ea
tu
r
es
f
r
o
m
a
g
iv
en
h
ig
h
d
im
en
s
io
n
al
d
atasets
,
with
n
u
m
er
o
u
s
p
ar
am
eter
p
r
o
ce
d
u
r
es,
wh
er
e
m
u
tatio
n
an
d
cr
o
s
s
o
v
er
o
p
er
ato
r
s
ar
e
ass
o
ciate
d
with
r
elev
an
t
r
ec
o
g
n
ized
b
in
ar
y
co
n
s
tr
ain
ts
f
ea
tu
r
es
[
1
9
]
.
R
NA
f
ea
t
u
r
es
with
N
n
u
m
b
er
d
en
o
tes
a
f
ea
tu
r
e
h
av
in
g
s
elec
ted
a
n
d
u
n
s
elec
ted
v
alu
es
1
a
n
d
0
r
esp
e
ctiv
ely
.
GA
is
im
p
o
r
ta
n
t
an
d
h
elp
s
to
f
in
d
f
ea
tu
r
e
s
u
b
s
et
m
o
d
els
with
s
e
lecte
d
f
ig
u
r
e
f
ea
tu
r
es
f
o
r
co
m
p
o
s
i
te
class
if
icatio
n
s
.
GA
s
tr
u
ctu
r
e
is
ad
o
p
ted
an
d
well
-
d
ef
in
ed
in
Alg
o
r
ith
m
1
[
2
0
]
:
Algorithm 1. Genetic Algorithm
Necessitate: Set parameters nPop =
m, t
max
, t = 0;
Confirm: Optimal feature subset with the maximum suitable value.
1: while (
t<=t
max
) do
2:
Create pop
m, t
max
;
3:
For
k =
1 to
m
do
4:
Parents [
m
1
, m
2
] = system selection (m, nPop)
5:
Child =
Xor [
m
1
, m
2
]
6:
M u
= mutation [Child}
7:
End for
8:
Replace
m
with Child
1
, Child
2
, …, Child
m
9:
t = t+ 1;
10:
End while
11:
Store the Highest fitness value;
m
=
p
o
p
u
latio
n
s
ize,
r
=
r
an
d
o
m
n
u
m
b
e
r
0
to
1
,
ch
r
o
m
e
=
c
er
tain
o
r
n
o
n
-
ce
r
tain
f
ea
tu
r
e
t
h
r
o
u
g
h
th
r
esh
o
ld
δ,
s
et
v
alu
e
=
0
.
5
,
an
d
α
=
th
r
esh
o
ld
n
u
m
b
e
r
o
f
p
ick
e
d
f
ea
tu
r
es.
Selectin
g
m
ax
im
u
m
f
it
f
ea
tu
r
es
f
r
o
m
th
e
p
r
ed
ictab
le
d
atasets
is
th
e
m
ain
p
r
o
b
lem
o
f
th
e
GA
tech
n
i
q
u
e.
3
.
2
.
K
NN
A
s
u
p
er
v
is
ed
lear
n
in
g
K
-
n
e
ar
est
n
eig
h
b
o
r
class
if
icatio
n
tech
n
iq
u
e
f
o
r
g
en
e
d
atasets
,
p
er
f
o
r
m
s
n
eig
h
b
o
r
h
o
o
d
class
if
icatio
n
e
v
alu
atio
n
v
alu
e
o
f
in
n
o
v
ativ
e
ap
p
licatio
n
o
cc
u
r
r
en
ce
.
KNN
alg
o
r
ith
m
class
if
ie
s
in
n
o
v
ativ
e
en
tity
d
ev
elo
p
e
d
o
n
in
s
tan
ce
s
,
attr
ib
u
tes
as
well
as
tr
ain
in
g
m
o
d
els.
KNN
cla
s
s
if
ier
s
d
o
n
o
t
tr
ai
n
m
o
d
els
to
f
it
b
u
t
b
u
ilt
o
n
r
ete
n
tio
n
.
T
h
e
f
ea
t
u
r
es
s
elec
ted
ar
e
ass
u
m
ed
as
in
p
u
t
to
s
eg
m
en
ts
.
T
h
e
K
v
alu
e
o
f
n
ea
r
est
n
eig
h
b
o
r
s
ar
e
s
elec
ted
n
ea
r
est
to
th
e
q
u
er
y
s
p
o
t.
Deta
ch
m
en
t
b
etwe
en
q
u
er
y
-
i
n
s
tan
ce
a
n
d
t
r
ain
in
g
m
o
d
els
ar
e
co
n
s
id
er
ed
an
d
s
o
r
ted
b
ased
o
n
th
e
K
th
m
in
im
u
m
d
eter
m
in
ed
d
is
tan
ce
.
Gr
o
u
p
Y
o
f
th
e
n
ea
r
est
n
eig
h
b
o
r
s
is
f
etch
ed
.
T
h
e
u
n
as
s
u
m
in
g
co
m
m
o
n
o
f
th
e
g
r
o
u
p
o
f
n
ea
r
est
n
eig
h
b
o
r
s
as
th
e
esti
m
ate
am
o
u
n
t
o
f
th
e
q
u
er
y
i
n
s
tan
ce
is
u
s
ed
.
B
o
n
d
s
ca
n
f
r
ag
m
en
t r
an
d
o
m
ly
[
2
5
]
.
3
.
3
.
Dec
is
io
n
t
re
es
Dec
is
io
n
tr
ee
class
if
icatio
n
alg
o
r
ith
m
d
iv
id
es
r
ec
u
r
s
iv
ely
in
s
tan
ce
s
p
ac
in
g
with
h
y
p
er
p
lan
es
o
r
th
o
g
o
n
ally
.
Dec
is
io
n
tr
ee
m
o
d
el
ass
em
b
les
d
er
iv
ativ
e
n
o
d
es
s
ig
n
if
y
in
g
attr
ib
u
tes,
b
ased
o
n
in
s
tan
ce
s
p
ac
e
attr
ib
u
te
v
alu
e
r
o
les
s
elec
ted
in
v
er
s
ely
f
o
r
alg
o
r
ith
m
s
,
u
s
in
g
its
v
alu
es.
Ad
v
an
ce
d
d
ata
s
u
b
-
s
p
ac
e
iter
ativ
el
y
d
iv
id
es
till
en
d
p
r
in
cip
le
is
d
eter
m
in
ed
an
d
ter
m
in
al
n
o
d
es
(
leaf
n
o
d
es)
ar
e
allo
ca
ted
to
class
lab
els
ch
ar
ac
ter
izin
g
th
e
class
if
icatio
n
.
Acc
u
r
ate
co
n
v
en
tio
n
al
en
d
p
r
o
ce
d
u
r
e
is
a
s
ig
n
i
f
ican
t
t
r
ee
with
to
o
h
u
g
e,
ov
er
f
itted
an
d
tr
iv
ial
tr
ee
s
,
u
n
d
er
f
itted
an
d
s
u
f
f
e
r
s
lo
s
s
in
a
cc
u
r
ac
y
.
Alg
o
r
ith
m
s
h
av
e
ass
em
b
led
o
v
er
f
itti
n
g
s
tr
ateg
ies,
lab
elled
tr
im
m
in
g
,
class
if
y
in
g
n
ew
in
s
tan
ce
s
b
y
l
ea
d
in
g
th
e
tr
ee
b
asis
d
o
wn
a
leaf
,
with
r
esp
ec
t
to
th
e
ex
am
in
atio
n
r
esu
lt
alo
n
g
th
e
p
at
h
way
[
2
6
]
.
C
o
m
p
eten
t
m
o
d
els
ar
e
d
is
co
v
er
e
d
u
s
in
g
d
ec
is
io
n
tr
ee
class
if
ier
s
an
d
en
s
em
b
les,
with
u
n
b
alan
c
ed
v
ar
y
i
n
g
tr
ain
e
d
d
atasets
,
with
r
esu
ltan
t m
o
d
els to
tally
u
n
a
lik
e.
3.
4
.
P
er
f
o
r
m
a
nce
ev
a
lua
t
io
n a
nd
a
pp
lica
t
io
ns
Ma
ch
in
e
lear
n
in
g
m
o
d
el
n
ee
d
ev
alu
atio
n
an
d
v
alid
atio
n
o
f
p
er
f
o
r
m
an
ce
m
etr
ics
u
s
in
g
a
co
n
f
u
s
io
n
m
atr
ix
an
d
its
f
o
r
m
u
la
[
4
,
2
7
]
.
E
x
p
r
ess
io
n
o
f
g
en
e
a
n
aly
s
is
s
u
g
g
est
en
h
an
ce
d
R
NA
-
Seq
d
ata
p
ath
id
en
tific
atio
n
,
to
lear
n
ap
p
licab
le
h
elp
f
u
l
g
e
n
es
in
ad
v
a
n
cin
g
ap
p
licatio
n
s
s
u
ch
as
tr
ea
tm
e
n
t
m
o
d
if
icat
io
n
s
,
d
is
ea
s
es
d
iag
n
o
s
is
,
d
r
u
g
s
an
d
g
e
n
e
d
is
co
v
er
ies,
c
lass
if
icatio
n
o
f
ca
n
ce
r
s
,
ty
p
h
o
id
,
m
alar
ia,
am
o
n
g
o
th
er
ailm
en
ts
.
Desig
n
s
an
d
in
co
n
s
is
ten
cy
f
in
d
in
g
s
b
etwe
en
m
ac
h
in
e
lear
n
in
g
d
ata
h
as
d
is
co
v
er
ed
g
r
ea
t
alg
o
r
ith
m
s
ap
p
licab
le
to
m
an
y
f
ield
s
s
u
ch
as
en
g
i
n
ee
r
in
g
,
b
an
k
in
g
,
h
ea
lth
s
ec
to
r
s
am
o
n
g
o
th
er
s
.
MA
T
L
AB
2
0
1
5
A
is
p
r
o
p
o
s
ed
as
an
ex
p
er
im
en
tal
an
d
ex
ec
u
tin
g
to
o
l
f
o
r
th
e
p
r
o
g
n
o
s
is
o
f
m
ala
r
ia
in
f
ec
tio
n
s
o
n
an
iC
o
r
e2
p
r
o
ce
s
s
o
r
,
4
GB
R
AM
s
ize,
6
4
-
b
it Sy
s
tem
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
A
g
en
etic
a
lg
o
r
ith
m
a
p
p
r
o
a
c
h
fo
r
p
r
ed
ictin
g
r
ib
o
n
u
cleic
a
ci
d
s
eq
u
en
cin
g
d
a
t
a
… (
Mich
ea
l O
la
o
lu
A
r
o
w
o
lo
)
313
4.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
In
th
is
s
tu
d
y
,
2
4
5
7
in
s
tan
ce
s
o
f
R
NA
-
Seq
d
ataset
“M
o
s
q
u
ito
es
An
o
p
h
eles
Gam
b
iae”
co
n
tain
in
g
r
esis
tan
ts
an
d
s
u
s
ce
p
tib
les
o
f
g
en
es
is
u
s
ed
o
n
a
GA
to
d
r
a
w
o
p
tim
al
r
ed
u
ce
d
n
u
m
b
er
o
f
s
u
b
s
ets
in
th
e
d
ata,
tak
in
g
awa
y
u
n
co
r
r
elate
d
attr
ib
u
tes
to
p
ick
m
ax
im
u
m
v
ar
i
an
c
e
f
ea
tu
r
es.
T
h
e
r
esu
lt
s
h
o
ws
im
p
o
r
tan
t
g
en
e
ev
id
en
ce
s
u
itab
le
f
o
r
KNN
an
d
d
ec
is
io
n
tr
ee
class
if
icatio
n
a
lg
o
r
ith
m
s
tu
d
y
o
n
MA
T
L
AB
en
v
ir
o
n
m
en
t
f
o
r
th
e
m
o
d
el
ex
p
er
im
en
t.
Gen
etic
a
l
g
o
r
ith
m
m
ak
es
u
s
e
o
f
0
.
5
th
r
e
s
h
o
ld
an
d
ac
h
iev
es
7
0
8
o
p
tim
al
s
u
b
s
et
f
ea
tu
r
es
o
f
s
ig
n
if
ican
t
g
en
es.
C
lass
if
ier
s
u
s
ed
1
0
-
f
o
ld
s
cr
o
s
s
v
alid
atio
n
was
u
s
ed
o
n
KNN
a
n
d
d
ec
is
io
n
tr
ee
class
if
ier
s
,
to
im
p
lem
en
t
ev
alu
atio
n
s
o
f
th
e
m
o
d
el’
s
p
er
f
o
r
m
an
ce
with
0
.
0
5
h
o
ld
o
u
t
tr
ain
in
g
d
ata
p
ar
a
m
eter
an
d
class
if
ier
ac
cu
r
ac
y
test
s
th
e
d
ata
with
2
5
%.
A
le
ar
n
in
g
class
if
icatio
n
p
r
o
ce
d
u
r
e
e
v
alu
atio
n
tr
ain
a
n
d
test
ev
alu
ates
u
s
in
g
10
-
f
o
l
d
cr
o
s
s
v
alid
atio
n
to
r
e
m
o
v
e
th
e
p
a
r
tiality
in
s
am
p
lin
g
.
T
h
e
p
er
f
o
r
m
a
n
ce
m
etr
ics
an
d
tim
e
co
m
p
u
tatio
n
is
ev
alu
ated
[
2
7
]
a
n
d
r
elate
s
t
h
e
m
o
d
el
class
if
icatio
n
p
er
f
o
r
m
an
ce
,
b
y
m
ea
n
s
o
f
KNN
(
b
a
g
g
in
g
)
an
d
d
ec
is
io
n
tr
ee
,
with
9
8
.
3
%
a
n
d
8
8
.
3
%
ac
cu
r
ac
y
s
ep
ar
ately
u
s
in
g
c
o
n
f
u
s
io
n
m
atr
ix
an
d
r
esu
lt
o
u
tp
u
s
as
s
h
o
wn
in
Fig
u
r
e
1
.
R
elate
d
co
m
p
o
n
e
n
ts
wer
e
f
etch
ed
b
y
GA
f
r
o
m
th
e
f
u
ll
d
ata
s
h
o
wn
in
Fig
u
r
e
1
,
th
e
s
u
b
s
et
d
ata
f
ea
tu
r
es
p
ass
in
to
KNN
as
well
as
d
ec
i
s
io
n
tr
ee
an
d
s
h
o
ws
th
e
C
o
n
f
u
s
io
n
m
atix
r
esu
lt
in
th
e
Fig
u
r
e
2
an
d
Fig
u
r
e
3
to
d
er
iv
e
th
e
s
o
lu
tio
n
to
th
e
p
e
r
f
o
r
m
an
ce
m
etr
ics.
KNN
class
if
icatio
n
alg
o
r
ith
m
ac
h
iev
e
s
an
ac
cu
r
ac
y
o
f
8
8
.
3
%,
wh
ile
th
e
d
ec
is
io
n
tr
ee
clas
s
if
i
ca
tio
n
alg
o
r
ith
m
ac
h
iev
e
d
an
ac
cu
r
ac
y
o
f
9
8
.
3
%,
m
etr
ics
o
f
o
th
er
p
er
f
o
r
m
an
ce
ar
e
s
h
o
wn
in
T
a
b
le
1
.
Fig
u
r
e
1
.
L
o
ad
ed
m
o
s
q
u
ito
a
n
o
p
h
eles g
am
b
iae
o
n
MA
T
L
A
B
en
v
ir
o
n
m
e
n
t
In
th
is
s
tu
d
y
,
R
NA
-
Seq
d
ata
u
s
es
a
m
o
s
q
u
ito
an
o
p
h
eles
g
a
m
b
iae
d
ataset
[
2
8
]
,
t
o
test
th
e
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
p
er
f
o
r
m
a
n
ce
.
Gen
etic
alg
o
r
ith
m
d
im
en
s
io
n
ality
r
ed
u
ctio
n
m
o
d
el
s
elec
ts
7
0
8
s
u
b
s
et
f
ea
tu
r
es
f
r
o
m
2
4
5
7
f
ea
tu
r
es
o
f
g
en
es
f
o
r
m
th
e
d
ata.
T
h
e
s
elec
ted
co
m
p
o
n
en
ts
wer
e
class
if
ied
u
s
in
g
class
if
icatio
n
alg
o
r
ith
m
s
(
KNN
an
d
d
ec
is
io
n
tr
ee
)
p
er
f
o
r
m
an
ce
ev
alu
atio
n
.
T
h
e
ef
f
icien
c
y
o
f
m
ac
h
in
e
l
ea
r
n
in
g
ap
p
r
o
ac
h
in
g
en
es
ar
e
s
h
o
wn
in
th
e
r
esu
lts
to
co
n
f
ir
m
th
e
m
eth
o
d
,
th
e
o
u
tc
o
m
es
ar
e
r
e
v
ea
led
an
d
r
elate
d
in
T
ab
le
2
s
h
o
win
g
GA
-
d
ec
is
io
n
tr
ee
o
u
tp
er
f
o
r
m
s
GA
-
KNN
ter
m
s
o
f
ac
cu
r
ac
y
.
I
n
th
is
s
tu
d
y
,
an
im
p
r
o
v
ed
class
if
icatio
n
o
f
m
alar
ia
v
ec
to
r
d
ata
is
an
aly
ze
d
u
s
in
g
GA
with
d
ec
is
io
n
tr
ee
an
d
K
NN
alg
o
r
ith
m
s
r
esp
ec
tiv
el,
n
u
m
er
o
u
s
wo
r
k
s
h
a
v
e
b
ee
n
r
ev
iewe
d
,
th
e
r
esu
lts
p
r
o
v
e
th
at
GA
en
h
a
n
ce
s
class
if
ica
tio
n
y
ield
f
o
r
KNN
an
d
d
ec
is
io
n
tr
ee
.
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.
19
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
1
:
31
0
-
3
16
314
Fig
u
r
e
2
.
R
NA
-
Seq
co
n
f
u
s
io
n
m
atr
ix
u
s
in
g
d
ec
is
io
n
tr
ee
alg
o
r
ith
m
T
P=3
8
; T
N=
2
1
; FP=0
; FN=
1
Fig
u
r
e
3
.
R
NA
-
Seq
co
n
f
u
s
io
n
m
atr
ix
u
s
in
g
KNN
T
P=3
6
; T
N=
1
7
; FP=4
; FN=
3
T
ab
le
2
.
Per
f
o
r
m
an
ce
m
etr
ics tab
le
f
o
r
th
e
co
n
f
u
s
io
n
m
atr
ix
P
e
r
f
o
r
ma
n
c
e
M
e
t
r
i
c
s
GA
-
D
e
c
i
si
o
n
Tr
e
e
C
l
a
ssi
f
i
c
a
t
i
o
n
GA
-
K
N
N
C
l
a
ssi
f
i
c
a
t
i
o
n
A
c
c
u
r
a
c
y
(
%)
9
8
.
3
8
8
.
3
S
e
n
s
i
t
i
v
i
t
y
(
%)
9
7
.
4
9
2
.
3
S
p
e
c
i
f
i
c
i
t
y
(
%)
1
0
0
8
1
.
0
P
r
e
c
i
s
i
o
n
(
%)
1
0
0
9
0
.
0
R
e
c
a
l
l
(
%)
9
7
.
4
9
2
.
3
F
-
S
c
o
r
e
(
%)
9
8
.
7
9
1
.
1
5.
CO
NCLU
SI
O
N
In
th
is
s
tu
d
y
,
im
p
r
o
v
em
en
ts
ef
f
icien
ce
f
o
r
p
r
ed
ictin
g
an
d
d
etec
tin
g
m
alar
ia
ailm
en
ts
in
h
u
m
an
ar
e
p
r
o
p
o
s
ed
u
s
in
g
m
ac
h
i
n
e
lear
n
in
g
d
im
en
s
io
n
ality
r
ed
u
ctio
n
a
n
d
class
if
icatio
n
tech
n
iq
u
es.
GA
f
ea
tu
r
e
s
elec
tio
n
d
im
en
s
io
n
ality
r
e
d
u
ctio
n
an
d
KNN
an
d
d
ec
is
io
n
tr
ee
class
if
ier
s
wer
e
em
p
l
o
y
ed
b
y
p
e
r
f
o
r
m
in
g
e
v
alu
atin
g
an
d
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
A
g
en
etic
a
lg
o
r
ith
m
a
p
p
r
o
a
c
h
fo
r
p
r
ed
ictin
g
r
ib
o
n
u
cleic
a
ci
d
s
eq
u
en
cin
g
d
a
t
a
… (
Mich
ea
l O
la
o
lu
A
r
o
w
o
lo
)
315
an
aly
s
in
g
th
e
p
e
r
f
o
r
m
an
ce
r
esu
lts
o
b
tain
ed
.
T
h
is
s
tu
d
y
e
n
h
an
ce
d
m
alar
ia
v
ec
to
r
d
ata
class
if
icatio
n
,
an
d
co
m
p
ar
ed
with
q
u
ite
a
lo
t o
f
p
r
o
p
o
s
ed
wo
r
k
s
i
n
r
e
v
iews
b
y
n
u
m
er
o
u
s
r
esear
ch
e
r
s
,
th
e
o
u
t
co
m
es
d
em
o
n
s
tr
ates
th
at,
GA
d
im
en
s
io
n
ality
r
ed
u
ctio
n
m
o
d
el
h
el
p
s
to
d
ev
elo
p
class
if
icatio
n
o
u
tp
u
t
s
u
ch
as
d
ec
is
io
n
tr
ee
.
I
n
v
esti
g
atin
g
c
u
r
r
e
n
t
wo
r
k
s
p
r
o
p
o
s
ed
in
liter
atu
r
e
ca
n
im
p
r
o
v
e
f
ea
t
u
r
e
s
elec
tio
n
m
o
d
els
an
d
alg
o
r
ith
m
s
a
n
d
co
m
p
ar
ed
with
r
ec
en
t
o
th
er
s
t
ate
-
of
-
th
e
-
a
r
t c
lass
if
icatio
n
alg
o
r
ith
m
.
RE
F
E
R
E
NC
E
S
[1
]
S
.
S
h
a
n
we
n
,
e
t
a
l.
,
“
M
a
c
h
i
n
e
Le
a
rn
in
g
a
n
d
Its
A
p
p
l
ica
ti
o
n
s
i
n
P
l
a
n
t
M
o
lec
u
lar
S
tu
d
ies
,
”
Briefin
g
s
in
Fu
n
c
ti
o
n
a
l
Ge
n
o
mic
s
,
v
o
l.
1
9
,
n
o
.
1
,
p
p
.
4
0
-
48
,
2
0
1
9
.
[
2
]
F
.
D
a
v
i
d
.
,
e
t
a
l
.
,
“
P
r
e
d
i
c
t
i
n
g
G
e
n
e
E
x
p
r
e
s
s
i
o
n
i
n
t
h
e
H
u
m
a
n
M
a
l
a
r
i
a
P
a
r
a
s
i
t
e
P
l
a
s
m
o
d
i
u
m
F
a
l
c
i
p
a
r
u
m
U
s
i
n
g
H
i
s
t
o
n
e
M
o
d
i
f
i
c
a
t
i
o
n
,
N
u
c
l
e
o
s
o
m
e
P
o
s
i
t
i
o
n
i
n
g
,
a
n
d
3
D
L
o
c
a
l
i
z
a
t
i
o
n
F
e
a
t
u
r
e
s
,
”
P
L
O
S
C
o
m
p
u
t
a
t
i
o
n
a
l
B
i
o
l
o
g
y
,
v
o
l
.
1
5
,
n
o
.
9
,
2
0
1
9
.
[3
]
M.
Aro
wo
lo
,
e
t
a
l
.
,
“
A
Dim
e
n
sio
n
a
l
Re
d
u
c
e
d
M
o
d
e
l
fo
r
th
e
Clas
si
fica
ti
o
n
o
f
RNA
-
S
e
q
A
n
o
p
h
e
les
G
a
m
b
iae
Da
ta
,
”
J
o
u
rn
a
l
o
f
T
h
e
o
re
ti
c
a
l
a
n
d
A
p
p
l
ied
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
,
v
o
l
.
97
,
n
o
.
23
,
p
p
.
3
4
8
7
-
96
,
2
0
1
9
.
[4
]
S
.
Ka
rth
ik
,
e
t
a
l
.
,
“
A
S
u
rv
e
y
o
n
M
a
c
h
i
n
e
Lea
rn
i
n
g
Ap
p
ro
a
c
h
e
s
in
G
e
n
e
E
x
p
re
ss
io
n
Clas
sifica
ti
o
n
i
n
M
o
d
e
ll
i
n
g
Co
m
p
u
tati
o
n
a
l
Dia
g
n
o
stic
S
y
ste
m
fo
r
Co
m
p
le
x
Dise
a
se
s
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
En
g
in
e
e
rin
g
a
n
d
A
d
v
a
n
c
e
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
8
,
n
o
.
2
,
p
p
.
1
8
2
-
1
9
1
,
2
0
1
8
.
[5
]
N.
Jo
h
n
so
n
,
e
t
a
l.
,
“
Bio
l
o
g
ica
l
c
las
sifica
ti
o
n
wit
h
RNA
-
se
q
d
a
t
a
:
Ca
n
a
lt
e
rn
a
t
iv
e
ly
sp
l
ice
d
tran
sc
rip
t
e
x
p
re
ss
io
n
e
n
h
a
n
c
e
m
a
c
h
in
e
lea
rn
in
g
c
las
sifiers
?
,
”
Co
ld
S
p
ri
n
g
Ha
rb
o
r
L
a
b
o
ra
to
ry
Pre
ss
fo
r
th
e
RNA
S
o
c
iety
,
v
o
l.
24
,
n
o
.
9
,
pp.
1
1
1
9
-
1
1
3
2
,
2
0
1
8
.
[6
]
M.
L
ib
b
re
c
h
t,
e
t
a
l.
,
“
M
a
c
h
in
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
t
Rev
Ge
n
e
t
ics
,
v
o
l.
16
,
pp.
3
2
1
-
332
,
2
0
1
5
.
[7
]
Z.
Ja
g
g
a
,
e
t
a
l.
,
“
Clas
sifica
ti
o
n
m
o
d
e
ls
fo
r
c
lea
r
c
e
ll
re
n
a
l
c
a
rc
i
n
o
m
a
sta
g
e
p
ro
g
re
ss
io
n
,
b
a
se
d
o
n
tu
m
o
r
RNA
se
q
e
x
p
re
ss
io
n
train
e
d
s
u
p
e
rv
ise
d
m
a
c
h
in
e
lea
rn
i
n
g
a
l
g
o
ri
th
m
s
,
”
BM
C
Pro
c
e
e
d
in
g
s
,
v
o
l.
8
,
n
o
.
2
,
2
0
1
4
.
[8
]
An
o
p
h
e
les
g
a
m
b
iae
1
0
0
0
G
e
n
o
m
e
s
Co
n
so
rti
u
m
,
“
G
e
n
e
ti
c
d
iv
e
rsity
o
f
t
h
e
Afric
a
n
m
a
laria
v
e
c
to
r
An
o
p
h
e
les
g
a
m
b
iae
,”
Na
tu
re
,
v
o
l
.
5
5
2
,
n
o
.
7
6
8
3
,
p
p
.
96
-
1
0
0
,
2
0
1
7
.
[
9
]
D.
O
h
,
e
t
a
l
.
,
“
P
r
e
d
i
c
t
i
n
g
A
u
t
i
s
m
S
p
e
c
t
r
u
m
D
i
s
o
r
d
e
r
U
s
i
n
g
B
l
o
o
d
-
b
a
s
e
d
G
e
n
e
E
x
p
r
e
s
s
i
o
n
S
i
g
n
a
t
u
r
e
s
a
n
d
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
,
”
C
l
i
n
P
s
y
c
h
o
p
h
a
r
m
a
c
o
l
o
g
y
N
e
u
r
o
s
c
i
e
n
c
e
,
v
o
l
.
15
,
n
o
.
1
,
pp.
47
-
52
,
2
0
1
7
.
[1
0
]
Q.
Re
n
,
e
t
a
l
.
,
“
Clu
ste
ri
n
g
a
n
d
C
las
sifica
ti
o
n
M
e
th
o
d
s
f
o
r
S
i
n
g
le
-
c
e
ll
RNA
-
S
e
q
Da
ta
,
”
Briefin
g
s
in
Bi
o
i
n
fo
rm
a
ti
c
s
,
v
o
l.
2
1
,
n
o
.
4
,
p
p
.
1
-
13
,
2
0
1
9
.
[1
1
]
W.
S
tep
h
e
n
,
e
t
a
l
.
,
“
Us
in
g
S
u
p
e
r
v
ise
d
Lea
rn
in
g
M
e
th
o
d
s
fo
r
G
e
n
e
S
e
lec
ti
o
n
in
RNA
-
S
e
q
Ca
se
-
Co
n
tr
o
l
S
t
u
d
ies
,”
Fro
n
ti
e
rs
i
n
Ge
n
e
ti
c
,
v
o
l.
9
,
n
o
.
2
9
7
,
p
p
.
1
-
6
,
2
0
1
8
.
[1
2
]
J.
Alq
u
icira
-
He
rn
a
n
d
e
z
,
e
t
a
l.
,
“
s
c
P
re
d
:
Ac
c
u
ra
te
S
u
p
e
r
v
ise
d
M
e
t
h
o
d
fo
r
Ce
ll
-
ty
p
e
Clas
sifica
ti
o
n
fro
m
S
in
g
le
-
c
e
ll
RNA
-
se
q
Da
ta
,
”
Ge
n
o
me
Bi
o
lo
g
y
,
v
o
l.
20
,
n
o
.
2
6
4
,
2
0
1
9
.
[1
3
]
S
.
Cu
i,
e
t
a
l.
,
“
M
a
c
h
i
n
e
Lea
rn
in
g
-
b
a
se
d
M
icro
a
rra
y
A
n
a
ly
se
s
In
d
ica
te
Lo
w
-
Ex
p
re
ss
io
n
G
e
n
e
s
M
ig
h
t
C
o
ll
e
c
ti
v
e
l
y
In
flu
e
n
c
e
P
AH
Dise
a
se
,
”
PL
OS
C
o
mp
u
t
a
ti
o
n
a
l
B
io
l
o
g
y
,
v
o
l.
1
5
,
n
o
.
8
,
2
0
1
9
.
[
1
4
]
H
.
S
h
o
n
,
e
t
a
l
.
,
“
C
l
a
s
s
i
f
i
c
a
t
i
o
n
o
f
S
t
o
m
a
c
h
C
a
n
a
c
e
r
G
e
n
e
E
x
p
r
e
s
s
i
o
n
D
a
t
a
U
s
i
n
g
C
N
N
A
l
g
o
r
i
t
h
m
o
f
D
e
e
p
L
e
a
r
n
i
n
g
,”
J
o
u
r
n
a
l
o
f
B
i
o
m
e
d
i
c
a
l
T
r
a
n
s
l
a
t
i
o
n
R
e
s
e
a
r
c
h
,
v
o
l
.
20
,
n
o
.
1
,
pp.
15
-
20
,
2
0
1
9
.
[1
5
]
J.
R.
Ad
a
m
,
e
t
a
l.
,
“
S
in
g
le
-
c
e
ll
R
NA
-
se
q
re
v
e
a
ls
h
i
d
d
e
n
t
ra
n
sc
rip
ti
o
n
a
l
v
a
riatio
n
in
m
a
laria
p
a
ra
sites
,”
e
L
if
e
S
c
ie
n
c
e
s
,
v
o
l.
7
,
p
p
.
1
-
2
9
,
2
0
1
8
.
[1
6
]
A.
Tan
,
e
t
a
l.
,
“
E
n
se
m
b
le
M
a
c
h
in
e
Lea
rn
i
n
g
o
n
G
e
n
e
Ex
p
re
ss
io
n
Da
ta
fo
r
Ca
n
c
e
r
Clas
sifi
c
a
ti
o
n
,
”
A
p
p
li
e
d
Bi
o
in
fo
rm
a
t
ics
,
v
o
l.
2
,
n
o
.
3
,
p
p
.
75
-
83
,
2
0
0
3
.
[1
7
]
N.
S
o
n
g
,
e
t
a
l.
,
“
De
sig
n
a
n
d
An
a
l
y
sis
o
f
En
se
m
b
le
Clas
sifier
fo
r
Ge
n
e
Ex
p
re
ss
io
n
Da
ta
o
f
Ca
n
c
e
r
,”
Ad
v
a
n
c
e
me
n
t
in
Ge
n
e
ti
c
En
g
i
n
e
e
rin
g
,
v
o
l.
5
,
n
o
.
1
,
p
p
.
1
-
7
,
2
0
1
6
.
[1
8
]
S
.
Tare
k
,
e
t
a
l
.
,
“
G
e
n
e
Ex
p
re
ss
io
n
Ba
se
d
Ca
n
c
e
r
Clas
sifica
ti
o
n
,”
Eg
y
p
ti
a
n
In
f
o
rm
a
ti
c
s
J
o
u
rn
a
l
,
v
o
l.
18
,
n
o
.
3
,
p
p
.
1
5
1
-
159
,
2
0
1
7
.
[1
9
]
Du
v
a
l
,
e
t
a
l.
,
“
Ad
v
a
n
c
e
s
i
n
M
e
t
a
h
e
u
risti
c
s
fo
r
G
e
n
e
S
e
lec
ti
o
a
n
d
Clas
sifica
ti
o
n
o
f
M
icr
o
a
rra
y
Da
ta
,”
Briefin
g
s
i
n
Bi
o
in
fo
rm
a
t
ics
,
v
o
l.
11
,
n
o
.
1
,
p
p
.
1
2
7
-
1
4
1
,
2
0
1
0
.
[2
0
]
A
.
S
h
u
k
la,
e
t
a
l
.
,
“
A
Ne
w
Hy
b
r
id
F
e
a
tu
re
S
u
b
se
t
S
e
lec
ti
o
n
F
ra
m
e
wo
rk
Ba
se
d
o
n
Bin
a
r
y
G
e
n
e
ti
c
Alg
o
r
it
h
m
a
n
d
In
fo
rm
a
ti
o
n
T
h
e
o
r
y
,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
C
o
mp
u
ta
ti
o
n
a
l
I
n
tel
li
g
e
n
c
e
a
n
d
Ap
p
li
c
a
ti
o
n
s
,
v
o
l
.
18
,
n
o
.
3
,
p
p
.
1
-
11
,
2
0
1
9
.
[2
1
]
A.
Tan
,
e
t
a
l
.
,
“
E
n
se
m
b
le
M
a
c
h
in
e
Lea
rn
i
n
g
o
n
G
e
n
e
Ex
p
re
ss
io
n
Da
ta
fo
r
Ca
n
c
e
r
Clas
sifi
c
a
ti
o
n
,”
A
p
p
li
e
d
Bi
o
in
fo
rm
a
t
ics
,
v
o
l.
3
,
p
p
.
1
-
10
,
2
0
0
3
.
[2
2
]
K.
Ka
m
ra
n
,
Kia
n
a
J
.
M
.
,
M
o
jt
a
b
a
H
.
,
S
a
n
jan
a
M
.
,
La
u
ra
B
.
,
Do
n
a
l
d
B.
,
“
Tex
t
Clas
sifica
ti
o
n
Al
g
o
r
it
h
m
s:
A S
u
r
v
e
y
,”
In
fo
rm
a
t
io
n
M
DPI
,
v
o
l.
10
,
n
o
.
1
5
0
,
p
p
.
2
-
68
,
2
0
1
9
.
[2
3
]
B.
M
a
rian
g
e
la,
e
t
a
l.
,
“
RNA
-
se
q
a
n
a
ly
se
s
o
f
c
h
a
n
g
e
s
in
th
e
A
n
o
p
h
e
les
g
a
m
b
iae
tran
sc
rip
to
m
e
a
ss
o
c
iate
d
with
re
sista
n
c
e
to
p
y
re
th
ro
id
s
in
Ke
n
y
a
:
id
e
n
ti
f
ica
ti
o
n
o
f
c
a
n
d
i
d
a
te
-
re
sista
n
c
e
g
e
n
e
s
a
n
d
c
a
n
d
id
a
te
-
re
sista
n
c
e
S
NPs
,”
Pa
ra
sites
a
n
d
Vec
to
r
,
v
o
l
.
8
,
n
o
.
474
,
p
p
.
1
-
13
,
2
0
1
5
.
[2
4
]
G
.
Ja
m
e
s,
e
t
a
l.
,
“
An
i
n
tr
o
d
u
c
ti
o
n
to
sta
ti
stica
l
lea
rn
i
n
g
with
a
p
p
l
ica
ti
o
n
i
n
R
,”
Ne
w
Y
o
rk
(NY
):
S
p
ri
n
g
e
r
;
2
0
1
3
.
[2
5
]
J.
Bo
se
,
e
t
a
l.
,
“
A
Hy
b
rid
G
A/K
NN
/S
VM
Alg
o
rit
h
m
fo
r
C
las
sifica
ti
o
n
o
f
Da
ta
,
”
Bi
o
Ho
u
se
J
o
u
rn
a
l
o
f
C
o
mp
u
ter
sc
ien
c
e
, v
o
l.
2
,
n
o
.
2
,
p
p
.
5
-
11
,
2
0
1
6
.
[2
6
]
I.
P
o
lak
a
,
e
t
a
l
.
,
“
De
c
isio
n
Tree
Clas
sifiers
in
Bi
o
i
n
fo
rm
a
ti
c
s
,
”
S
c
ien
ti
fi
c
J
o
u
rn
a
l
o
f
Ri
g
a
T
e
c
h
n
ica
l
Un
ive
rs
it
y
,
p
p
.
1
1
0
-
123
,
2
0
1
0
.
[2
7
]
M.
Aro
wo
lo
,
e
t
a
l.
,
“
A
Co
m
p
a
ra
ti
v
e
An
a
ly
sis
o
f
F
e
a
tu
re
S
e
lec
ti
o
n
a
n
d
F
e
a
tu
re
Ex
trac
ti
o
n
M
o
d
e
ls
fo
r
Clas
sify
i
n
g
M
icro
a
rra
y
Da
tas
e
t
,”
Co
mp
u
ti
n
g
a
n
d
In
f
o
rm
a
ti
o
n
S
y
ste
m
,
v
o
l.
22
,
n
o
.
2
,
p
p
.
29
-
38
,
2
0
1
8
.
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.
19
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
1
:
31
0
-
3
16
316
[2
8
]
M
a
rian
g
e
la
Bo
n
izz
o
n
i
,
e
t
a
l.
,
“
Ad
d
it
i
o
n
a
l
f
il
e
4
:
o
f
RNA
-
se
q
a
n
a
ly
se
s
o
f
c
h
a
n
g
e
s
in
t
h
e
An
o
p
h
e
les
g
a
m
b
iae
tran
sc
rip
to
m
e
a
ss
o
c
iate
d
with
re
sista
n
c
e
to
p
y
re
th
r
o
id
s
i
n
Ke
n
y
a
:
id
e
n
ti
fica
ti
o
n
o
f
c
a
n
d
id
a
te
-
re
sista
n
c
e
g
e
n
e
s
a
n
d
c
a
n
d
id
a
te
-
re
sista
n
c
e
S
NPs
,
”
2
0
1
5
.
h
tt
p
s:
//
fig
s
h
a
re
.
c
o
m
/article
s/Ad
d
it
io
n
a
l_
f
il
e
_
4
_
o
f
_
RNA
se
q
_
a
n
a
l
y
se
s_
o
f_
c
h
a
n
g
e
s
_
in
_
th
e
_
An
o
p
h
e
les
_
g
a
m
b
iae
_
tra
n
sc
rip
to
m
e
_
a
ss
o
c
iate
d
_
wi
th
_
re
sista
n
c
e
_
to
_
p
y
re
t
h
ro
i
d
s_
i
n
_
Ke
n
y
a
_
id
e
n
ti
fica
ti
o
n
_
o
f_
c
a
n
d
i
d
a
tere
sista
n
c
e
_
g
e
n
e
s_
a
n
d
_
c
a
n
d
i
d
a
tere
sista
n
c
e
_
S
NPs/4
3
4
6
2
7
9
/1
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Mi
c
h
e
a
l
O
la
o
lu
Ar
o
wo
lo
,
is
a
fa
c
u
lt
y
o
f
th
e
De
p
a
rtme
n
t
o
f
C
o
m
p
u
ter
S
c
ien
c
e
a
t
Lan
d
m
a
rk
Un
iv
e
rsity
,
Om
u
-
Ara
n
Nig
e
ria.
He
h
o
ld
s
a
Ba
c
h
e
lo
r
De
g
re
e
fro
m
Al
-
Hik
m
a
h
Un
iv
e
rsity
,
Ilo
rin
,
Nig
e
ria
a
n
d
a
M
a
ste
rs
De
g
re
e
fro
m
Kw
a
ra
S
tate
Un
iv
e
rsity
,
M
a
lete
Nig
e
ria,
h
e
i
s
p
re
se
n
tl
y
a
P
h
D
S
tu
d
e
n
t
o
f
La
n
d
m
a
rk
Un
iv
e
rsit
y
,
Om
u
-
Ara
n
Ni
g
e
ria.
His
a
re
a
o
f
re
se
a
rc
h
in
tere
st
in
c
l
u
d
e
s
M
a
c
h
i
n
e
Lea
rn
in
g
,
Bi
o
in
fo
rm
a
ti
c
s,
Da
tam
in
in
g
,
C
y
b
e
r
S
e
c
u
ri
ty
a
n
d
Co
m
p
u
ter
Arith
m
e
ti
c
.
He
h
a
s
p
u
b
li
sh
e
d
wid
e
ly
i
n
lo
c
a
l
a
n
d
i
n
tern
a
t
io
n
a
l
re
p
u
tab
le
jo
u
rn
a
ls
,
h
e
is a me
m
b
e
r
o
f
IAENG
,
APIS
E,
S
DIWC,
a
n
d
a
n
Ora
c
le Certifi
e
d
Ex
p
e
rt.
Dr
.
Ma
r
io
n
O
lu
b
u
n
m
i
Adebi
y
i
,
is
a
fa
c
u
lt
y
o
f
t
h
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
t
Lan
d
m
a
rk
Un
i
v
e
rsity
,
Om
u
-
Ara
n
,
Nig
e
ria.
S
h
e
h
o
ld
s
a
BS
c
De
g
re
e
fro
m
Un
iv
e
rsity
o
f
Ilo
rin
,
Ilo
ri
n
Nig
e
ria.
S
h
e
h
a
d
h
e
r
M
Sc
a
n
d
P
h
D
De
g
re
e
in
Co
m
p
u
te
r
S
c
ien
c
e
fro
m
Co
v
e
n
a
n
t
Un
iv
e
rsity
,
Nig
e
ria
re
sp
e
c
ti
v
e
l
y
.
He
r
re
se
a
r
c
h
in
tere
sts
in
c
l
u
d
e
,
Bi
o
in
fo
rm
a
ti
c
s
o
f
I
n
fe
c
ti
o
u
s
(Africa
n
)
Dise
a
se
s/
P
o
p
u
lati
o
n
,
Org
a
n
ism
’s
In
ter
-
p
a
t
h
wa
y
a
n
a
ly
s
is,
Hig
h
th
r
o
u
g
h
p
u
t
d
a
ta
a
n
a
ly
ti
c
s,
Ho
m
o
lo
g
y
m
o
d
e
ll
i
n
a
n
d
Artifi
c
ial
I
n
telli
g
e
n
c
e
.
S
h
e
h
a
s
p
u
b
li
sh
e
d
wid
e
ly
in
lo
c
a
l
a
n
d
i
n
tern
a
ti
o
n
a
l
re
p
u
tab
le
j
o
u
r
n
a
ls
S
h
e
is
a
m
e
m
b
e
r
o
f
Ni
g
e
rian
C
o
m
p
u
ter
S
o
c
iet
y
(NCS)
,
t
h
e
Co
m
p
u
ter Reg
istrati
o
n
C
o
u
n
c
il
o
f
Ni
g
e
ria (CP
N) an
d
IEE
E
m
e
m
b
e
r.
Pro
fe
ss
o
r
Ay
o
d
e
le
Ar
iy
o
Adebi
y
i
,
is
a
fa
c
u
lt
y
a
n
d
fo
rm
e
r
He
a
d
o
f
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
a
n
d
I
n
fo
rm
a
ti
o
n
S
c
ien
c
e
s,
C
o
v
e
n
a
n
t
Un
iv
e
rsity
,
Ota
Nig
e
ria.
He
i
s
c
u
rre
n
tl
y
th
e
He
a
d
o
f
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
t
Lan
d
m
a
rk
Un
iv
e
rsity
,
Om
u
-
Ara
n
,
Nig
e
ria,
a
siste
r
Un
iv
e
rsity
to
C
o
v
e
n
a
n
t
Un
iv
e
r
sit
y
.
He
h
o
ld
s
a
BS
c
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
M
BA
d
e
g
re
e
fro
m
Un
i
v
e
rsity
o
f
Ilo
r
i
n
,
Il
o
rin
Ni
g
e
ria.
He
h
a
d
h
is
M
S
c
a
n
d
P
h
D
d
e
g
re
e
in
M
a
n
a
g
e
m
e
n
t
I
n
fo
rm
a
ti
o
n
S
y
ste
m
(M
IS
)
fro
m
Co
v
e
n
a
n
t
Un
i
v
e
rsity
,
Nig
e
ria
re
sp
e
c
ti
v
e
ly
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
,
a
p
p
li
c
a
ti
o
n
o
f
s
o
ft
c
o
m
p
u
ti
n
g
tec
h
n
iq
u
e
s
in
so
l
v
in
g
re
a
l
li
fe
p
ro
b
lem
s,
so
ftwa
re
e
n
g
in
e
e
rin
g
a
n
d
in
fo
rm
a
ti
o
n
sy
ste
m
re
se
a
r
c
h
.
He
h
a
s
su
c
c
e
s
sfu
ll
y
m
e
n
to
re
d
a
n
d
su
p
e
rv
ise
d
se
v
e
ra
l
p
o
st
g
ra
d
u
a
te
stu
d
e
n
ts
a
t
M
a
ste
rs
a
n
d
P
h
D
le
v
e
l.
He
h
a
s
p
u
b
li
sh
e
d
wid
e
l
y
i
n
lo
c
a
l
a
n
d
in
t
e
rn
a
ti
o
n
a
l
re
p
u
tab
le
j
o
u
r
n
a
ls.
He
is
a
m
e
m
b
e
r
o
f
Nig
e
ria
n
Co
m
p
u
ter
S
o
c
iety
(NCS),
t
h
e
Co
m
p
u
ter
Re
g
istrati
o
n
C
o
u
n
c
il
o
f
Nig
e
ria
(CP
N)
a
n
d
IEE
E
m
e
m
b
e
r.
Evaluation Warning : The document was created with Spire.PDF for Python.