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
.
2
,
A
p
r
il
2
0
2
1
,
p
p
.
4
0
6
~
4
1
3
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
i2
.
1
6
7
2
4
406
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
M
a
chine learning
wit
h
multis
tag
e c
la
ss
ifiers f
o
r id
ent
ificatio
n of
o
f
ectopa
ra
site i
nf
ecte
d
mud c
ra
b genus
Scylla
Ro
zniza
Ali
1
,
M
uh
a
m
a
d M
u
na
wa
r
Yus
ro
2
,
M
uh
a
m
m
a
d Suzuri H
it
a
m
3
,
M
hd
I
k
hwa
n
ud
di
n
4
1,
2,
3
F
a
c
u
l
ty
o
f
Oc
e
a
n
En
g
i
n
e
e
rin
g
Tec
h
n
o
l
o
g
y
a
n
d
In
f
o
rm
a
ti
c
s,
Un
i
v
e
rsiti
M
a
lay
sia
Tere
n
g
g
a
n
u
,
M
a
l
a
y
sia
4
In
stit
u
te
o
f
Tr
o
p
ica
l
Aq
u
a
c
u
lt
u
re
a
n
d
F
ish
e
ries
,
Un
i
v
e
rsiti
M
a
la
y
sia
Tere
n
g
g
a
n
u
,
M
a
lay
sia
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
y
1
8
,
2
0
2
0
R
ev
is
ed
Sep
7
,
2
0
2
0
Acc
ep
ted
Sep
1
6
,
2
0
2
0
Re
c
e
n
tl
y
,
t
h
e
m
u
d
-
c
ra
b
fa
rm
in
g
c
a
n
h
e
lp
t
h
e
ru
ra
l
p
o
p
u
latio
n
e
c
o
n
o
m
ica
ll
y
.
Ho
we
v
e
r,
th
e
e
x
ist
in
g
p
a
ra
site
in
th
e
m
u
d
-
c
ra
b
s
c
o
u
l
d
in
terfe
re
th
e
lo
n
g
li
v
e
o
f
th
e
m
u
d
-
c
ra
b
s.
U
n
fo
rt
u
n
a
tel
y
,
th
e
p
a
ra
site
h
a
s
b
e
e
n
id
e
n
ti
f
ied
to
li
v
e
i
n
h
u
n
d
re
d
s
o
f
m
u
d
-
c
ra
b
s,
p
a
r
ti
c
u
lar
ly
it
h
a
p
p
e
n
e
d
in
Tere
n
g
g
a
n
u
Co
a
sta
l
Wate
r,
M
a
lay
sia
.
Th
is
stu
d
y
i
n
v
e
stig
a
t
e
s
th
e
in
it
ial
id
e
n
t
ifi
c
a
ti
o
n
o
f
t
h
e
p
a
ra
site
fe
a
tu
re
s
b
a
se
d
o
n
th
e
ir
c
las
se
s
b
y
u
sin
g
m
a
c
h
in
e
lea
rn
i
n
g
tec
h
n
iq
u
e
s.
In
th
is
c
a
se
,
we
e
m
p
lo
y
e
d
fiv
e
c
las
sifiers
i.
e
lo
g
isti
c
re
g
re
ss
io
n
(LR)
,
k
-
n
e
a
re
st
n
e
ig
h
b
o
rs
(k
NN
),
G
a
u
ss
ian
Na
iv
e
Ba
y
e
s
(G
NB),
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(S
VM),
a
n
d
l
in
e
a
r
d
isc
rimi
n
a
n
t
a
n
a
ly
sis
(LDA).
We
c
o
m
p
a
re
d
th
e
se
fiv
e
c
las
sfie
rs
to
b
e
st
p
e
rfo
rm
a
n
c
e
o
f
c
las
sifica
ti
o
n
o
f
t
h
e
p
a
ra
sites
.
Th
e
c
las
sifica
ti
o
n
p
ro
c
e
ss
in
v
o
l
v
in
g
t
h
re
e
sta
g
e
s.
F
irst,
c
las
sify
th
e
p
a
ra
sites
in
to
two
c
las
se
s
(n
o
rm
a
l
a
n
d
a
b
n
o
rm
a
l)
re
g
a
rd
les
s
o
f
t
h
e
ir
v
e
n
tral
ty
p
e
s.
S
e
c
o
n
d
,
c
las
sified
se
x
u
a
li
t
y
(fe
m
a
le
o
r
m
a
le)
a
n
d
m
a
tu
rit
y
(m
a
tu
re
o
r
imm
a
tu
re
).
F
in
a
ll
y
,
we
c
o
m
p
a
re
d
th
e
fi
v
e
c
las
sifiers
to
i
d
e
n
ti
f
y
t
h
e
sp
e
c
ies
o
f
t
h
e
p
a
ra
site.
Th
e
e
x
p
e
rime
n
tal
re
su
lt
s
s
h
o
we
d
th
a
t
G
NB
a
n
d
LDA
a
re
th
e
m
o
st
e
ffe
c
ti
v
e
c
las
sifiers
fo
r
c
a
rry
in
g
o
u
t
t
h
e
in
it
ial
c
las
sifica
ti
o
n
o
f
t
h
e
rh
i
z
o
c
e
p
h
a
lan
p
a
ra
site wit
h
in
th
e
m
u
d
c
ra
b
g
e
n
u
s
S
c
y
ll
a
.
K
ey
w
o
r
d
s
:
C
las
s
if
icatio
n
Ma
ch
in
e
l
ea
r
n
in
g
Mu
d
c
r
ab
Mu
lti
-
s
tag
e
class
if
icatio
n
S
.
o
liva
ce
a
S
cy
lla
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
:
R
o
zn
iza
Ali
Facu
lty
o
f
Oce
an
E
n
g
in
ee
r
i
n
g
T
ec
h
n
o
lo
g
y
an
d
I
n
f
o
r
m
atics
Un
iv
er
s
iti Ma
lay
s
ia
T
er
en
g
g
a
n
u
Un
n
am
ed
R
o
ad
,
2
1
3
0
0
K
u
ala
T
er
en
g
g
a
n
u
,
T
e
r
en
g
g
an
u
,
Ma
lay
s
ia
E
m
ail:
r
o
zn
iza@u
m
t.e
d
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
d
em
an
d
f
o
r
m
u
d
cr
ab
,
g
e
n
u
s
S
cy
lla
h
ad
in
cr
ea
s
ed
r
a
p
id
ly
,
th
u
s
lead
in
g
t
o
th
e
g
r
o
wth
in
th
e
m
u
d
cr
ab
cu
ltiv
atio
n
b
u
s
in
ess
[
1
,
2
]
.
C
o
n
s
id
er
in
g
th
e
h
ea
lth
o
f
m
u
d
cr
a
b
p
o
p
u
latio
n
wh
ic
h
is
a
f
r
ee
-
p
ar
asit
e,
it
is
cr
u
cial
to
u
n
d
er
s
tan
d
th
e
p
ar
a
s
ite
p
r
o
f
iles
.
I
n
f
ec
ted
m
u
d
cr
ab
wo
u
ld
g
iv
e
h
u
g
e
im
p
ac
t
in
to
in
d
ig
en
o
u
s
cr
ab
s
to
ck
s
with
s
ig
n
if
ican
t
d
elete
r
io
u
s
ec
o
n
o
m
ic
co
n
s
eq
u
e
n
ce
s
[
3
]
.
I
t
is
im
p
er
ativ
e
to
ac
c
u
r
ately
an
aly
ze
th
e
co
n
tam
in
atio
n
s
o
f
th
e
m
u
d
cr
ab
s
p
ec
ies
as
ea
r
ly
as
p
o
s
s
ib
le.
I
n
th
e
ca
s
e
o
f
r
ea
s
o
n
ab
le
m
ea
s
u
r
es
o
f
p
a
r
asit
e
co
n
tr
o
l
ar
e
n
o
t
d
ev
elo
p
ed
,
at
th
at
p
o
in
t,
t
h
is
co
u
ld
h
a
v
e
a
n
eg
ativ
e
ef
f
ec
t
o
n
m
u
d
cr
ab
s
p
r
o
d
u
ctio
n
.
L
o
x
o
th
y
lacu
s
ih
lei
B
o
s
ch
m
a
a
n
d
Sacc
u
lin
a
b
ea
u
f
o
r
ti
ar
e
s
p
ec
ies
o
f
r
h
izo
ce
p
h
alan
.
I
n
an
y
c
ase,
th
e
p
ar
asit
es
o
f
m
u
d
cr
ab
s
p
u
lled
in
less
co
n
s
id
er
atio
n
f
r
o
m
an
aly
s
ts
,
it is
d
u
e
to
th
e
n
ee
d
o
f
d
ep
ictio
n
o
f
t
h
eir
co
n
tam
in
atio
n
s
is
co
m
m
er
cially
a
b
u
s
ed
,
c
o
m
p
ar
ed
with
s
h
ellf
is
h
an
d
o
th
e
r
cu
ltiv
atio
n
s
p
ec
ies
[
4
]
.
T
h
e
a
n
aly
s
is
o
f
th
e
m
u
d
cr
ab
p
ar
asit
es
h
as
n
o
t
b
ee
n
p
r
o
p
er
ly
im
p
lem
e
n
ted
.
Ho
wev
e
r
,
in
Asi
a
n
atio
n
,
d
u
e
t
o
th
e
i
m
p
r
o
p
e
r
u
s
ed
o
f
th
e
m
u
d
cr
a
b
cu
ltu
r
e
m
eth
o
d
s
,
th
e
an
aly
s
is
o
f
th
e
m
u
d
cr
a
b
p
ar
a
s
ites
h
as b
ee
n
r
ec
en
tly
b
eg
u
n
[
5
,
6
]
.
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
Ma
ch
in
e
lea
r
n
in
g
w
ith
mu
ltis
ta
g
e
cla
s
s
ifier
s
fo
r
id
en
tifi
ca
tio
n
o
f
...
(
R
o
z
n
iz
a
A
li
)
407
At
cu
r
r
en
t,
m
a
n
y
m
et
h
o
d
s
an
d
s
tr
ateg
ies d
is
s
ec
tio
n
m
icr
o
s
co
p
es,
m
o
r
p
h
o
lo
g
y
k
e
y
s
,
s
h
ap
e
o
f
ca
lcar
e
-
o
u
s
p
lates
h
av
e
b
ee
n
e
x
p
lo
r
e
d
in
id
en
tific
atio
n
o
f
t
r
u
e
s
p
ec
i
es
o
f
in
f
ec
ted
m
u
d
cr
ab
[
4
]
.
R
o
u
tin
e
s
cr
ee
n
in
g
f
o
r
th
e
p
r
esen
ce
o
f
i
n
f
ec
ted
s
p
ec
i
es
h
as
th
e
p
o
ten
tial
to
g
en
er
a
te
h
u
g
e
v
o
lu
m
es
o
f
s
am
p
les,
p
ar
ticu
lar
ly
d
u
r
in
g
p
er
io
d
s
o
f
a
s
u
s
p
ec
ted
o
u
tb
r
ea
k
,
wh
ich
m
u
s
t
b
e
id
en
tifie
d
r
a
p
id
ly
an
d
co
r
r
ec
tly
.
T
h
es
e
m
et
h
o
d
s
,
h
o
wev
er
,
ar
e
s
till
d
o
n
e
m
an
u
ally
in
a
B
io
lo
g
y
lab
[
3
]
.
I
n
th
is
s
tu
d
y
,
a
s
em
i
-
au
to
m
ati
c
m
eth
o
d
in
v
o
lv
in
g
th
e
m
ac
h
i
n
e
lear
n
in
g
tec
h
n
iq
u
es
was
d
e
v
elo
p
ed
to
ea
r
ly
d
etec
t
th
e
in
f
ec
ted
m
u
d
cr
ab
s
.
T
h
is
p
r
o
ce
s
s
in
v
o
lv
in
g
class
if
icatio
n
o
f
th
e
p
ar
asit
e
f
ea
tu
r
es
in
th
e
m
u
d
cr
ab
,
g
e
n
u
s
S
cy
lla
b
y
u
s
in
g
m
u
ltis
tag
e
class
if
ier
s
s
u
ch
as lo
g
is
tic
r
eg
r
ess
io
n
(
L
R
)
,
k
-
n
ea
r
e
s
t n
eig
h
b
o
r
s
(
k
NN)
,
Gau
s
s
ian
Naiv
e
B
ay
es
(
GNB),
s
u
p
p
o
r
t
v
ec
t
o
r
m
ac
h
in
e
(
SVM)
,
an
d
lin
ea
r
d
is
cr
im
in
an
t
a
n
aly
s
is
(
L
DA)
.
T
h
e
in
v
esti
g
atio
n
o
f
s
ch
em
e
is
b
as
ed
o
n
p
r
o
v
e
n
s
tu
d
y
th
at
an
in
te
g
r
ated
e
n
s
em
b
le
m
et
h
o
d
h
as
s
h
o
wn
t
h
e
ca
p
a
b
ilit
y
to
lear
n
in
te
r
p
r
etab
le
m
u
lti
-
tar
g
et
m
o
d
els
wh
ich
ca
n
p
r
ed
ict
s
ev
er
al
tar
g
et
class
es
s
im
u
ltan
eo
u
s
ly
[
7
]
.
E
n
s
em
b
le
b
ased
m
eth
o
d
s
h
av
e
r
ec
en
tly
g
r
ea
t
atten
tio
n
d
u
e
to
th
eir
r
ep
o
r
ted
s
u
p
er
io
r
ity
o
v
er
s
in
g
le
m
eth
o
d
-
b
ased
s
y
s
te
m
g
en
er
aliza
tio
n
p
e
r
f
o
r
m
an
ce
[
8
,
9
]
.
T
h
e
aim
o
f
en
s
em
b
le
class
if
icatio
n
is
to
co
m
b
in
e
m
u
ltip
le
m
o
d
els
(
class
if
ier
s
o
r
f
ea
tu
r
es)
to
s
o
lv
e
p
ar
ticu
lar
p
r
o
b
lem
s
[
1
0
]
.
E
n
s
em
b
le
m
et
h
o
d
ca
n
b
e
d
iv
id
e
d
in
to
a
n
u
m
b
er
o
f
ca
te
g
o
r
ies,
s
u
ch
as e
n
s
em
b
le
class
if
ier
s
,
en
s
em
b
le
f
ea
tu
r
es,
an
d
en
s
em
b
l
e
f
ea
tu
r
e
an
d
class
if
ier
s
[
1
1
–
1
3
]
.
2.
M
UD
CRA
B
,
S
C
Y
L
L
A
OL
I
V
A
C
E
S
cy
lla
tr
a
n
q
u
e
b
a
r
ica
,
S
cy
lla
p
a
r
a
ma
mo
s
a
in
an
d
S
cy
lla
o
liva
ce
a
ar
e
s
p
ec
ies
o
f
m
u
d
cr
a
b
in
Ma
lay
s
ia
th
at
h
av
e
b
ee
n
r
ec
o
g
n
ized
,
an
d
S
.
o
liv
a
ce
a
is
th
e
s
p
ec
ies
th
at
ar
e
ty
p
ically
f
o
u
n
d
[
4
]
.
I
n
Ma
lay
s
ia,
m
u
d
c
r
a
b
s
o
r
lo
ca
lly
k
n
o
wn
as
k
etam
n
i
p
ah
o
r
k
etam
b
a
k
au
,
is
in
h
a
b
it
m
an
g
r
o
v
e
f
o
r
ests
an
d
r
iv
er
m
o
u
th
s
in
estu
ar
in
e
s
u
r
r
o
u
n
d
in
g
s
[
1
4
]
.
Fr
o
m
2
0
0
8
to
2
0
1
5
,
in
s
h
o
r
e
f
is
h
er
ies
in
Ma
lay
s
ia
wer
e
p
er
s
is
ten
tly
g
r
ea
ter
in
am
o
u
n
t
an
d
v
alu
e
t
h
a
n
th
e
r
em
o
te
-
o
ce
a
n
f
i
s
h
er
ies.
Mu
d
cr
ab
s
a
p
p
ea
r
e
d
t
h
e
m
o
s
t
n
o
tewo
r
t
h
y
litt
ler
f
is
h
er
ies
lan
d
in
g
s
p
ec
ies
ar
r
iv
als
with
in
t
h
e
ea
s
t
c
o
ast
a
n
d
west
c
o
ast
o
f
Pen
in
s
u
lar
M
alay
s
ia
an
d
E
ast
Ma
lay
s
ia.
M
u
d
c
r
ab
s
wh
ich
ar
e
am
az
in
g
ly
l
o
o
k
e
d
f
o
r
,
b
o
th
lo
ca
lly
an
d
o
v
e
r
s
ea
s
,
in
co
n
s
is
t
o
f
th
e
s
ig
n
if
ican
t f
is
h
er
y
f
ield
in
Ma
lay
s
ia.
D
u
r
i
n
g
p
r
ev
io
u
s
s
am
p
lin
g
wo
r
k
s
,
s
u
r
v
ey
d
is
co
v
er
ed
th
at
a
f
ew
s
h
ap
e
s
of
ab
n
o
r
m
alities
wer
e
s
h
o
w
wi
th
in
th
e
mud
c
r
a
b
s
p
ec
ies
in
Ma
r
u
d
u
B
a
y
,
Sab
ah
,
Ma
lay
s
ia
[
1
5
]
.
L
o
ca
l
p
e
o
p
le
li
k
ewise
p
ick
u
n
u
s
u
al
cr
ab
s
in
lig
h
t
of
t
h
eir
to
tality
in
m
ea
t
d
ep
en
d
en
t
o
n
th
eir
h
ig
h
er
b
o
d
y
weig
h
t
(
B
W
)
co
n
tr
as
ted
with
th
e
ty
p
ical
d
ev
elo
p
ed
m
u
d
cr
ab
s
an
d
t
h
i
s
ev
en
t
h
as
b
ee
n
f
a
r
r
ea
c
h
in
g
f
o
r
v
er
y
f
iv
e
y
ea
r
s
.
T
h
is
is
r
em
a
r
k
ab
le
i
n
lig
h
t
o
f
th
e
f
ac
t
th
at
m
o
s
t
h
o
s
ts
p
lag
u
e
d
with
r
h
izo
ce
p
h
alan
p
ar
asit
es h
av
e
lo
wer
ad
v
an
ce
m
e
n
t su
m
s
an
d
lo
wer
tak
in
g
ca
r
e
o
f
co
n
d
u
ct
an
d
th
e
ef
f
ec
t
o
f
cr
ab
u
tili
za
tio
n
o
n
h
u
m
an
well
b
ein
g
is
o
f
im
p
er
ativ
e
co
n
ce
r
n
.
R
h
izo
ce
p
h
alan
p
a
r
asit
es
ar
e
n
o
tab
le
to
ca
u
s
e
th
eir
h
o
s
ts
to
b
e
s
ter
ilized
an
d
f
em
i
n
ized
.
T
h
e
m
o
s
t
d
is
tin
g
u
is
h
ed
f
ea
tu
r
e
o
f
r
h
izo
c
ep
h
alan
co
n
tam
in
ati
o
n
s
is
th
e
ap
p
ea
r
an
ce
o
f
a
y
ello
w
s
ac
-
lik
e
s
h
ap
e
n
o
tab
le
as
ex
ter
n
a
(
co
n
tain
s
th
e
f
em
ale
p
ar
asit
e’
s
r
ep
r
o
d
u
ctiv
e
o
r
g
an
s
)
with
in
its
h
o
s
t’
s
o
u
ter
ab
d
o
m
e
n
ca
v
ity
[
1
5
]
.
T
h
e
p
ar
asit
e
n
o
u
r
is
h
es
th
e
n
u
tr
ien
t
r
em
o
v
e
d
f
r
o
m
its
h
o
s
t’
s
h
e
m
o
ly
m
p
h
v
ia
th
e
in
ter
n
al
(
r
o
o
t
-
lik
e
s
h
ap
e)
an
d
in
f
ec
ted
cr
ab
s
ca
n
n
o
t
m
o
u
lt
af
ter
th
e
cr
ea
tio
n
o
f
ex
ter
n
a
[
1
6
,
1
7
]
.
W
h
en
a
v
ir
g
in
f
e
m
ale’
s
ex
ter
n
a
is
f
er
tili
ze
d
b
y
a
p
r
e
d
o
m
in
ate
m
ale,
th
e
d
i
s
ea
s
ed
cr
ab
ca
n
watc
h
o
u
t
o
f
th
e
in
tr
u
d
er
s
’
f
er
tili
ze
d
eg
g
s
u
n
til
th
ey
h
atch
.
T
h
e
d
is
ea
s
ed
m
ale
will
be
f
em
i
n
ized
an
d
d
em
o
n
s
tr
atio
n
s
ty
p
ical
m
o
r
p
h
o
lo
g
i
cal
an
d
b
eh
av
i
o
r
al
ch
an
g
es
in
f
em
ales
,
lik
e
d
ec
r
ea
s
e
in
ch
ela
s
ize,
wi
d
en
in
g
o
f
th
e
ab
d
o
m
en
,
an
d
t
y
p
ical
eg
g
ca
r
in
g
[
1
7
,
1
8
]
.
Mo
s
tly
tar
g
etin
g
cr
ab
s
,
th
is
p
ar
asit
e
in
f
esta
tio
n
will
r
esu
lt
in
o
v
er
ex
p
lo
itatio
n
,
th
r
ea
ten
in
g
th
e
w
o
r
l
d
-
wid
e
f
is
h
er
ies
in
d
u
s
tr
y
.
T
h
e
s
ter
ilizatio
n
im
p
ac
t o
f
p
a
r
asit
es a
r
is
in
g
f
r
o
m
c
h
an
g
es i
n
m
o
r
p
h
o
lo
g
ical
ch
ar
ac
ter
an
d
h
o
r
m
o
n
al
co
n
ce
n
tr
atio
n
s
r
ed
u
ce
s
g
en
er
al
r
e
p
r
o
d
u
ctiv
e
r
ates,
th
u
s
r
ed
u
cin
g
p
o
p
u
latio
n
d
en
s
ities
o
v
er
tim
e.
3.
M
ACH
I
N
E
L
E
AR
NING
C
L
ASSI
F
I
CA
T
I
O
N
T
o
d
a
y
,
m
ac
h
in
e
lear
n
in
g
is
th
e
f
astes
t
s
p
r
ea
d
in
g
f
ield
in
co
m
p
u
ter
s
cien
ce
th
at
en
co
m
p
ass
es
v
a
r
ied
ar
ea
s
as
in
f
o
r
m
atio
n
s
ec
u
r
ity
,
m
an
u
f
ac
tu
r
in
g
,
m
ar
k
etin
g
,
tr
an
s
p
o
r
tatio
n
an
d
h
ea
lth
ca
r
e
[
1
9
–
2
3
]
.
Ma
ch
i
n
e
lear
n
in
g
is
a
s
u
b
s
et
o
f
ar
tific
i
al
in
tellig
en
ce
th
at
o
f
f
er
s
co
m
p
u
t
er
s
an
d
co
m
p
u
ter
s
y
s
tem
s
with
th
e
ca
p
ac
ity
to
lear
n
an
d
en
h
an
ce
s
ep
ar
ately
f
r
o
m
p
r
io
r
ex
p
e
r
ien
ce
s
with
o
u
t
ex
p
licit
h
u
m
an
p
r
o
g
r
am
m
in
g
.
Ma
ch
in
e
lear
n
in
g
is
b
ased
on
co
m
p
u
ter
p
r
o
g
r
am
s
th
at
ca
n
co
llect
in
f
o
r
m
atio
n
an
d
lear
n
f
o
r
t
h
em
s
elv
es
[
2
0
,
2
1
]
.
Ma
ch
in
e
lea
r
n
in
g
’
s
p
i
o
n
ee
r
,
A
r
th
u
r
Sam
u
el,
id
e
n
tifie
d
m
ac
h
i
n
e
lear
n
in
g
as
a
r
esear
c
h
f
ield
t
h
at
en
ab
les
co
m
p
u
ter
s
to
lear
n
with
o
u
t
ex
p
licit
p
r
o
g
r
am
m
in
g
[
2
4
]
.
Ma
ch
i
n
e
lear
n
in
g
is
th
e
a
p
p
licatio
n
f
o
r
tr
en
d
p
r
ed
ictio
n
,
ca
teg
o
r
izatio
n
,
or
d
elin
ea
tio
n
of
s
p
ec
if
ic
alg
o
r
ith
m
s
to
d
atas
ets
an
d
th
e
m
eth
o
d
s
h
av
e
tr
ad
itio
n
ally
b
ee
n
ap
p
lied
to
b
ig
d
atab
ases
o
f
h
i
g
h
d
im
e
n
s
io
n
s
[
2
3
]
.
I
n
t
h
is
r
esear
ch
,
f
iv
e
m
ac
h
in
e
-
lear
n
in
g
class
if
ier
(
L
R
,
K
-
NN,
G
N
B
,
SVM
an
d
L
DA)
ar
e
u
s
ed
t
o
cl
ass
if
y
in
g
th
e
p
ar
asit
e
in
th
e
m
u
d
cr
ab
g
en
u
s
S
cy
l
la
.
4.
DATAS
E
T
Mu
d
cr
ab
s
with
in
th
e
g
en
u
s
S
cy
lla
ca
n
b
e
f
o
u
n
d
in
m
u
d
d
y
m
an
g
r
o
v
e
zo
n
es
an
d
estu
ar
ies.
T
h
er
e
a
r
e
p
r
o
f
o
u
n
d
l
y
n
am
e
d
as
an
im
p
er
ativ
e
s
o
u
r
ce
f
o
r
little
s
ca
le
f
i
s
h
er
s
all
th
r
o
u
g
h
th
e
Asi
a
Pacif
i
c.
Gen
u
s
S
cy
lla
ar
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.
19
,
No
.
2
,
Ap
r
il 2
0
2
1
:
4
0
6
-
413
408
th
e
f
o
r
em
o
s
t
ex
ch
an
g
ed
f
is
h
p
r
o
d
u
ct
in
Asi
a
an
d
th
e
th
er
ef
o
r
e
th
e
cu
ltu
r
in
g
p
r
ac
ticed
is
alr
ea
d
y
wo
r
n
out
m
o
s
t
of
Asi
an
co
u
n
tr
y
s
o
m
e
y
ea
r
s
p
ast.
T
h
e
r
eq
u
est
f
o
r
mud
cr
ab
s
h
as
ex
p
an
d
ed
q
u
ic
k
ly
o
v
er
th
e
last
d
ec
ad
e,
g
i
v
i
n
g
ex
tr
ao
r
d
i
n
ar
y
p
o
ten
tial f
o
r
th
e
ad
v
an
ce
m
e
n
t o
f
th
e
m
u
d
cr
ab
aq
u
ac
u
ltu
r
e
in
d
u
s
tr
y
.
S
.
o
liva
ce
a
,
S
.
p
a
r
a
ma
mo
s
a
i
n
an
d
S
.
tr
a
n
q
u
eb
a
r
ica
a
r
e
th
r
ee
s
p
ec
ies
o
f
m
u
d
cr
ab
th
at
h
av
e
b
e
e
n
id
en
tifie
d
in
Ma
lay
s
ia
[
2
5
]
.
S
.
o
liva
ce
a
is
th
at
th
e
co
m
m
o
n
es
t
s
p
ec
ies
co
m
p
ar
ed
to
alter
n
ati
v
e
s
p
ec
ies
[
2
6
]
.
S
.
p
a
r
a
ma
mo
s
a
in
is
s
in
g
le
s
p
ec
ie
s
co
m
p
ar
ed
to
o
th
er
s
p
ec
ies
w
h
ich
is
f
o
u
n
d
with
in
th
e
b
o
u
n
d
s
p
ac
e.
In
an
y
c
a
s
e
,
th
e
s
cien
tific
class
if
icatio
n
an
d
s
p
ec
ies
s
tatu
s
o
f
m
u
d
cr
a
b
i
n
Ma
lay
s
ia
ar
e
h
o
wev
e
r
y
et
to
b
e
ch
ar
ac
ter
ize
d
.
I
n
th
is
s
t
u
d
y
,
o
n
ly
S
.
o
liva
ce
a
is
tak
en
f
o
r
an
aly
s
is
an
d
class
if
icatio
n
.
Ma
r
u
d
u
B
ay
-
Sab
a
h
(
6
°4
4
J
N,
1
1
7
°1
J
E
)
,
L
u
n
d
u
–
Sar
awa
k
(
1
°4
0
J
N,
1
0
9
°5
8
J
E
)
,
T
aip
in
g
-
Per
ak
(
4
°4
5
J
N,
1
0
0
°3
7
J
E
)
an
d
Setiu
-
T
er
e
n
g
g
an
u
(
5
°3
9
J
N,
1
0
2
°4
3
J
E
)
ar
e
f
o
u
r
lo
ca
tio
n
s
f
o
r
s
cr
ee
n
i
n
g
o
f
th
e
m
u
d
cr
a
b
g
en
u
s
Scy
lla
i
n
Ma
lay
s
ia.
T
h
e
s
cr
ee
n
in
g
was
co
m
m
en
ce
d
f
r
o
m
J
u
n
e
2
0
1
2
u
n
ti
l
J
u
ly
2
0
1
3
.
E
x
tr
a
m
u
d
cr
a
b
s
cr
ee
n
in
g
at
Ma
r
u
d
u
B
ay
,
S
a
b
ah
was
co
m
m
en
ce
d
u
n
til
De
ce
m
b
er
2
0
1
3
.
All
lo
ca
tio
n
s
w
er
e
s
elec
t
b
ased
o
n
th
eir
h
ig
h
m
u
d
c
r
ab
lan
d
in
g
s
[
2
7
]
.
I
d
en
tific
atio
n
o
f
t
h
e
S
.
o
liva
ce
a
was b
ased
o
n
m
o
r
p
h
o
lo
g
ical
ch
ar
ac
ter
s
d
escr
ib
e
d
b
y
W
a
i
h
o
et
a
l
.
[
6
]
.
T
h
o
s
e
ar
e
ca
r
ap
ac
e
wid
th
(
C
W
)
,
b
o
d
y
weig
h
t
(
B
W
)
,
ab
d
o
m
en
wid
th
(
A
W
)
,
g
o
n
o
p
o
d
len
g
th
(
GL
)
,
e
x
t
e
r
n
a
d
iam
eter
(
E
D)
an
d
p
leo
p
o
d
le
n
g
th
(
PL)
.
Fig
u
r
e
1
s
h
o
ws
t
h
e
v
en
tr
al
v
iew
o
f
n
o
r
m
al
a
n
d
ab
n
o
r
m
al
S
.
o
liva
ce
a
.
Oth
er
f
ea
tu
r
es
also
co
n
s
id
er
e
d
ar
e
lev
el
o
r
n
o
r
m
ality
(
n
o
r
m
al
o
r
ab
n
o
r
m
al)
,
s
ex
u
ality
(
f
em
ale
o
r
m
ale)
an
d
m
atu
r
ity
(
m
atu
r
e
or
im
m
atu
r
e
)
.
In
to
tal,
1
1
0
0
d
ata
p
o
in
ts
wer
e
u
s
ed
in
th
is
a
n
aly
s
is
an
d
class
if
icatio
n
.
Fig
u
r
e
1
.
T
h
e
v
e
n
tr
al
v
iew
o
f
n
o
r
m
al
an
d
ab
n
o
r
m
al
m
u
d
c
r
a
b
s
p
ec
ies (
S
.
o
liva
ce
a
)
5.
M
E
T
H
O
DO
L
O
G
Y
An
ass
o
r
tm
en
t
of
m
ac
h
i
n
e
lear
n
in
g
class
if
ier
s
an
d
th
eir
p
e
r
f
o
r
m
an
ce
in
class
if
y
in
g
th
e
d
ata
h
av
e
b
ee
n
in
v
esti
g
ated
.
T
h
e
f
r
am
ewo
r
k
f
o
r
th
e
class
if
icatio
n
o
f
th
e
p
ar
asit
e
in
m
u
d
cr
ab
,
g
en
u
s
S
cy
lla
is
illu
s
tr
ated
i
n
Fig
u
r
e
2
.
I
t
in
v
o
lv
es
d
ata
co
llectio
n
,
d
ata
p
r
ep
a
r
atio
n
,
an
d
c
lass
if
icatio
n
.
T
h
er
e
ar
e
f
o
u
r
s
t
ag
es
in
v
o
lv
ed
in
t
h
e
class
if
icatio
n
o
f
th
e
s
p
ec
ies
(
Fig
u
r
e
3
)
.
In
th
e
f
ir
s
t
s
tag
e,
th
e
mud
cr
ab
s
p
ec
ies
ar
e
clas
s
if
i
ed
in
to
two
g
r
o
u
p
s
,
n
am
ely
n
o
r
m
al
an
d
a
b
n
o
r
m
al.
I
n
th
is
s
t
u
d
y
,
o
n
l
y
th
e
n
o
r
m
al
g
r
o
u
p
is
b
r
o
u
g
h
t
f
o
r
f
u
r
t
h
er
c
lass
if
icatio
n
.
I
n
th
e
s
ec
o
n
d
s
tag
e,
th
e
n
o
r
m
al
g
r
o
u
p
is
th
en
class
if
ied
b
etwe
en
m
al
e
an
d
f
em
ale.
T
h
ese
two
g
r
o
u
p
s
,
o
n
th
e
n
ex
t
s
tag
e,
ar
e
class
if
ied
to
id
en
tif
y
eith
e
r
th
ey
ar
e
m
atu
r
e
or
im
m
atu
r
e
s
p
ec
ies.
L
astl
y
,
th
e
ac
cu
r
ac
y
l
e
v
e
l
f
o
r
ea
c
h
class
if
ier
o
f
ea
ch
s
tag
e
is
co
m
p
u
ted
b
y
u
s
in
g
(
1
)
[
28
]
.
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
Ma
ch
in
e
lea
r
n
in
g
w
ith
mu
ltis
ta
g
e
cla
s
s
ifier
s
fo
r
id
en
tifi
ca
tio
n
o
f
...
(
R
o
z
n
iz
a
A
li
)
409
=
+
+
+
+
(
1
)
W
h
er
e:
-
T
P
: th
e
o
b
s
er
v
atio
n
is
p
o
s
itiv
e,
a
n
d
is
p
r
ed
icted
to
b
e
p
o
s
itiv
e
.
-
TN
:
th
e
o
b
s
er
v
atio
n
is
n
eg
ativ
e,
a
n
d
is
p
r
ed
icted
to
b
e
n
eg
ativ
e
.
-
FP
:
th
e
o
b
s
er
av
tio
n
is
n
eg
ativ
e,
b
u
t is p
r
ed
icted
to
b
e
p
o
s
itiv
e.
-
FN
: th
e
o
b
s
er
v
atio
n
is
p
o
s
itiv
e,
b
u
t
is
p
r
ed
icted
to
b
e
p
o
s
itiv
e
.
Fig
u
r
e
2
.
Fra
m
ewo
r
k
f
o
r
th
e
m
u
ltis
tag
e
class
if
icatio
n
o
f
th
e
p
ar
asit
e
in
m
u
d
cr
ab
,
g
en
u
s
S
cy
lla
Fig
u
r
e
3
.
Deta
il st
ag
es in
v
o
lv
e
in
class
if
y
in
g
s
p
ec
ies
5
.
1
.
Da
t
a
c
o
llect
io
n
T
h
er
e
ar
e
1
1
0
0
d
ata
o
f
m
u
d
cr
ab
s
wer
e
u
s
ed
in
th
is
s
t
u
d
y
.
T
o
co
llect
th
e
d
ata,
f
ir
s
tly
,
th
e
s
c
r
ee
n
in
g
o
f
th
e
mud
cr
ab
,
S.
o
liva
ce
a
is
p
er
f
o
r
m
ed
.
T
h
e
n
,
we
ca
r
r
y
o
u
t
th
e
id
en
tific
atio
n
of
t
h
e
m
u
d
cr
a
b
,
S.
o
liva
ce
a
b
ased
on
m
o
r
p
h
o
lo
g
ical
c
h
ar
ac
ter
s
.
T
h
ese
in
clu
d
e
t
h
e
ca
r
a
p
ac
e
wid
th
(
C
W
)
,
b
o
d
y
weig
h
t
(
B
W
)
,
ab
d
o
m
en
wid
th
(
A
W
)
,
g
o
n
o
p
o
d
le
n
g
th
(
GL
)
,
ex
ter
n
a
d
iam
eter
(
E
D)
a
n
d
p
le
o
p
o
d
len
g
t
h
(
PL)
.
T
h
e
o
u
tco
m
e
of
th
is
d
ata
co
llectio
n
s
tep
is
th
at
we
o
n
l
y
p
r
o
p
o
s
ed
th
e
f
ea
tu
r
es
th
at
l
ea
d
to
p
o
s
s
ib
le
s
em
i
-
au
to
m
at
ic
id
en
tific
atio
n
o
f
p
ar
asit
e
.
5
.
2
.
Cla
s
s
if
ica
t
io
n
t
ec
hn
iqu
es
Ma
ch
in
e
lear
n
in
g
class
if
ier
s
,
i.e
.
L
DA,
L
R
,
K
-
NN,
Gau
s
s
ian
Naiv
e
B
ay
es,
an
d
SVM
ar
e
u
s
ed
in
clas
-
s
if
y
in
g
an
d
th
u
s
id
en
tify
i
n
g
p
ar
asit
es
s
p
ec
ies
th
at
in
f
ec
ted
t
h
e
m
u
d
cr
a
b
.
T
h
r
o
u
g
h
ex
p
er
i
m
en
tal
in
v
esti
g
atio
n
,
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
.
2
,
Ap
r
il 2
0
2
1
:
4
0
6
-
413
410
th
ese
class
if
ier
s
wer
e
u
s
ed
to
f
in
d
th
e
ac
cu
r
ac
y
class
if
icatio
n
r
ate
of
n
o
r
m
ality
p
r
esen
t
in
th
e
m
ales
an
d
f
em
ales
g
en
u
s
S
cy
lla
.
T
h
e
ac
cu
r
ac
y
an
d
co
n
f
u
s
io
n
m
atr
ix
wer
e
u
s
ed
to
m
ea
s
u
r
e
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
class
if
ier
s
.
L
in
ea
r
d
is
cr
im
in
a
n
t
an
aly
s
is
(
L
DA)
,
n
o
r
m
al
d
is
cr
im
in
a
n
t
a
n
aly
s
is
(
NDA)
,
o
r
d
is
cr
im
in
a
n
t
f
u
n
ctio
n
an
aly
s
is
ar
e
th
e
g
en
e
r
aliza
tio
n
o
f
Fis
h
er
’
s
lin
ea
r
d
is
cr
im
in
an
t.
T
h
is
m
eth
o
d
is
u
s
ed
i
n
s
tatis
tics
,
p
atter
n
r
ec
o
g
n
itio
n
,
a
n
d
m
ac
h
i
n
e
lear
n
in
g
to
f
in
d
a
lin
ea
r
co
m
b
in
ati
o
n
of
f
ea
tu
r
es
th
at
ch
ar
ac
ter
ize
s
or
s
ep
ar
ates
two
or
more
class
es
o
f
o
b
jects
o
r
ev
en
ts
.
T
h
e
r
esu
ltin
g
co
m
b
in
a
tio
n
m
ay
b
e
u
s
ed
as
a
lin
ea
r
class
if
ier
o
r
m
o
r
e
co
m
m
o
n
l
y
,
f
o
r
d
im
en
s
io
n
alit
y
r
ed
u
ctio
n
b
e
f
o
r
e
later
class
if
icatio
n
.
Fis
h
er
’
s
lin
ea
r
d
is
cr
im
in
an
t
an
aly
s
is
(
FLDA
)
tr
ies
to
f
in
d
a
p
r
o
jec
tio
n
m
atr
ix
th
at
p
r
o
jects
th
e
t
r
ain
in
g
d
ata
o
n
to
a
l
o
w
-
d
im
e
n
s
io
n
al
s
p
ac
e
th
at
m
ax
im
izes
b
etwe
en
-
class
v
ar
i
an
ce
as
well
as
m
i
n
im
izin
g
with
in
-
class
v
ar
ian
ce
[
2
9
]
.
T
h
e
r
e
ar
e
f
iv
e
g
en
e
r
al
s
tep
s
f
o
r
p
er
f
o
r
m
in
g
a
lin
ea
r
d
is
cr
im
in
an
t a
n
aly
s
is
,
n
am
ely
li
s
ted
as f
o
llo
ws:
a.
C
o
m
p
u
te
th
e
d
-
d
im
en
s
io
n
al
m
ea
n
v
ec
to
r
s
f
o
r
th
e
d
if
f
er
e
n
t c
lass
es f
r
o
m
th
e
d
ataset.
b.
C
o
m
p
u
te
th
e
s
ca
tter
m
atr
ices
(
in
-
b
etwe
en
-
class
an
d
with
in
-
cl
ass
s
ca
tter
m
atr
ix
)
.
c.
C
o
m
p
u
te
th
e
eig
en
v
ec
to
r
s
(
e
1
,
e
2
,
.
.
.
,
e
d
)
an
d
co
r
r
esp
o
n
d
i
n
g
ei
g
en
v
alu
es
(
T
1
,
T
2
,
.
.
.
,
T
d
)
f
o
r
th
e
s
ca
tter
m
atr
ices.
d.
So
r
t
th
e
eig
e
n
v
ec
to
r
s
b
y
d
e
cr
ea
s
in
g
eig
en
v
alu
es
an
d
ch
o
o
s
e
k
eig
e
n
v
ec
to
r
s
with
th
e
lar
g
est
eig
en
v
alu
es to
f
o
r
m
a
d
×
k
d
im
en
s
io
n
al
m
atr
ix
W
(
wh
e
r
e
e
v
er
y
c
o
lu
m
n
r
e
p
r
esen
ts
an
eig
en
v
ec
to
r
)
.
e.
Use
th
is
d
×
k
eig
en
v
ec
to
r
m
a
tr
ix
to
tr
an
s
f
o
r
m
th
e
s
am
p
les
o
n
to
th
e
n
ew
s
u
b
s
p
ac
e.
T
h
is
can
be
s
u
m
m
a
-
r
ized
b
y
t
h
e
m
atr
ix
m
u
ltip
licatio
n
:
Y
=
X
×
W
(
w
h
er
e
W
is
a
k
×
d
-
d
im
e
n
s
io
n
al
m
atr
ix
r
ep
r
esen
tin
g
th
e
n
s
am
p
les,
a
n
d
Y
be
k
×
d
tr
a
n
s
f
o
r
m
e
d
k
×
d
-
d
im
e
n
s
io
n
al
s
am
p
les
in
t
h
e
n
ew
s
u
b
s
p
ac
e)
.
T
h
e
k
-
Nea
r
est
Neig
h
b
o
r
s
(
k
N
N)
class
if
ier
a
s
s
ig
n
s
an
y
test
v
ec
to
r
to
th
e
r
esp
ec
tiv
e
class
th
at
its
k
-
n
ea
r
est
n
eig
h
b
o
r
s
b
elo
n
g
at
m
o
s
t,
co
n
s
id
er
in
g
th
e
d
is
tan
ce
s
b
etwe
en
th
e
test
an
d
tr
ain
in
g
v
ec
to
r
s
in
th
e
f
ea
tu
r
e
s
p
ac
e
[
2
4
]
.
Alth
o
u
g
h
it
is
o
b
v
i
o
u
s
th
at
class
if
icatio
n
p
er
f
o
r
m
an
ce
is
d
ir
ec
tly
r
elate
d
to
th
e
p
ar
am
eter
k
,
th
e
r
e
is
no
o
b
v
io
u
s
i
n
f
o
r
m
atio
n
on
th
e
s
elec
tio
n
of
k
,
ex
ce
p
t
th
at
it
s
h
o
u
ld
be
p
o
s
itiv
e
an
d
not
a
m
u
ltip
le
of
t
h
e
to
tal
n
u
m
b
er
o
f
class
es
[
1
0
]
.
T
h
e
k
NN
f
o
r
m
u
la
s
h
o
u
ld
b
e
in
ter
p
r
eted
as
av
er
ag
in
g
th
e
ca
teg
o
r
i
es
o
f
a
cir
cle
with
k
d
ata
-
p
o
in
ts
ar
o
u
n
d
a
ce
r
tain
x
i
.
If
k
=
1
th
en
ea
c
h
d
ata
p
o
i
n
t
is
ca
teg
o
r
ized
co
r
r
ec
tly
.
In
th
e
ca
s
e
of
k
=
1
th
e
n
th
e
k
NN
f
o
r
m
u
la
im
p
lies
f
o
r
e
ac
h
x
i
.
T
h
e
s
p
ec
if
ic
class
if
icatio
n
Yi
ca
n
b
e
c
o
m
p
u
ted
as f
o
l
lo
ws;
=
1
∑
=
∈
1
(
)
(
2
)
Gau
s
s
ian
Naiv
e
B
ay
es
(
GNB)
class
if
ier
im
p
lem
en
ts
th
e
Naïv
e
B
ay
es
th
eo
r
e
m
f
o
r
class
if
icatio
n
[
3
0
]
.
T
h
e
f
o
r
m
u
la
o
f
GNB ca
n
b
e
m
ath
em
atica
lly
wr
itten
as f
o
llo
ws
(
|
)
=
1
√
2
2
(
−
(
−
)
2
2
2
)
(
3
)
wh
er
e
P(X
i|
y
)
ar
e
Gau
s
s
ian
n
u
m
b
er
,
X
i
: t
h
e
i
-
th
v
a
r
iab
le,
x
i
: th
e
v
alu
e
o
f
th
e
i
-
t
h
v
ar
ia
b
le,
Y
: c
lass
,
y
j
: su
b
class
o
f
Y
th
at
y
o
u
ar
e
lo
o
k
in
g
f
o
r
,
v
: M
ea
n
,
t
h
e
av
er
a
g
e
o
f
all
attr
ib
u
tes,
an
d
: stan
d
ar
d
d
ev
iatio
n
.
.
T
h
e
class
if
icatio
n
o
f
th
e
m
u
d
cr
ab
s
is
s
p
ec
if
ied
in
to
th
r
ee
s
t
ag
es,
wh
ich
ar
e
a.
Stag
e
1
:
C
las
s
if
icatio
n
in
n
o
r
m
ality
.
At
t
h
is
s
tag
e
m
u
d
cr
ab
d
ataset
is
s
ep
ar
ated
in
to
two
class
es:
n
o
r
m
al
o
r
ab
n
o
r
m
al
u
s
in
g
th
e
f
iv
e
class
if
ier
s
.
b.
Stag
e
2
:
C
lass
if
icatio
n
in
s
ex
.
At
th
is
s
ec
o
n
d
s
tag
e,
th
e
class
if
icatio
n
o
f
th
e
f
ir
s
t
s
tag
e
is
co
n
tin
u
ed
to
o
b
tain
th
e
n
o
r
m
al
a
n
d
ab
n
o
r
m
al
d
ata.
In
th
is
s
tag
e,
th
e
d
ata
is
tr
ain
e
d
so
th
at
we
class
if
y
th
e
g
r
o
u
p
s
in
to
two
:
m
ale
an
d
f
e
m
ale.
T
h
e
r
esu
lts
ar
e
s
u
m
m
ar
ized
in
a
c
o
n
f
u
s
io
n
m
atr
i
x
c.
Stag
e
3
:
C
las
s
if
icatio
n
in
m
at
u
r
ity
,
i
n
th
is
s
tag
e,
th
e
g
r
o
u
p
s
m
ale
an
d
f
em
ale
o
b
tain
ed
f
r
o
m
th
e
s
ec
o
n
d
s
tag
e,
is
class
if
ied
in
to
m
atu
r
e
an
d
im
m
atu
r
e.
T
h
is
last
s
tag
e
o
f
th
e
class
if
icatio
n
p
r
o
ce
s
s
is
cr
u
cial
s
in
ce
we
o
n
ly
e
x
p
ec
t th
e
m
atu
r
e
g
r
o
u
p
wh
ich
is
f
r
ee
o
f
p
ar
asit
e
.
6.
E
XP
E
R
I
M
E
N
T
A
L
RE
SUL
T
S
T
o
em
p
l
o
y
th
e
f
iv
e
m
ac
h
in
e
le
ar
n
in
g
class
if
ier
s
,
th
e
d
ata
s
ets
ar
e
s
p
lit
in
to
tr
ai
n
in
g
a
n
d
test
d
ata.
T
h
e
tr
ain
in
g
d
ata
s
et
co
n
tain
s
th
e
k
n
o
wn
v
a
r
iab
les
an
d
th
e
m
o
d
el
lear
n
s
on
th
is
d
ata
in
o
r
d
er
to
g
en
er
alize
d
th
e
d
ata.
E
ac
h
s
tag
e
of
class
if
icatio
n
s
r
e
co
r
d
ed
co
n
f
u
s
io
n
m
atr
ix
tab
le.
T
h
e
ac
cu
r
ac
y
lev
el
of
each
cla
s
s
if
ier
is
co
m
p
u
ted
b
y
u
s
in
g
(
1
)
.
B
ased
o
n
th
e
r
e
s
u
lts
o
f
th
e
co
n
f
u
s
io
n
m
atr
ice
s
p
r
o
v
id
ed
in
t
a
b
l
e
s
1
,
2
,
an
d
3
,
we
o
b
t
ain
ed
th
e
ac
cu
r
ac
y
lev
el
o
f
GNB
an
d
L
D
A
wer
e
d
ef
in
itely
1
0
0
%
in
an
y
s
tag
es
an
d
b
ec
o
m
e
th
e
h
ig
h
est
r
ate
o
f
class
if
icatio
n
.
T
h
e
L
R
cla
s
s
if
i
er
h
as
th
e
ac
cu
r
ac
y
lev
el
r
an
g
in
g
f
r
o
m
9
8
.
5
%
to
1
0
0
%.
Fu
r
th
er
m
o
r
e,
th
e
SVM
class
if
ier
p
r
o
d
u
ce
d
ac
cu
r
ac
y
in
ter
v
al
o
f
8
1
.
8
%
u
n
til
9
9
.
8
%.
Fin
ally
th
e
p
o
o
r
est
o
f
ac
cu
r
ac
y
r
ates
o
f
class
if
icatio
n
in
th
is
s
tu
d
y
is
KNN
wh
ich
p
r
o
d
u
ce
d
th
e
ac
c
u
r
ac
y
lev
el
b
etwe
en
7
7
.
8
% u
n
til
9
7
.
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
Ma
ch
in
e
lea
r
n
in
g
w
ith
mu
ltis
ta
g
e
cla
s
s
ifier
s
fo
r
id
en
tifi
ca
tio
n
o
f
...
(
R
o
z
n
iz
a
A
li
)
411
T
ab
el
1
.
C
lass
if
icatio
n
b
ased
o
n
th
e
n
o
r
m
ality
;
(
a
)
SVM,
(
b
)
GNB,
(
c)
L
R
,
(
d
)
L
DA,
(
e)
KNN
(
a)
N
o
r
mal
A
b
n
o
r
ma
l
N
o
r
mal
6
0
6
6
A
b
n
o
r
ma
l
1
4
3
8
(
b
)
N
o
r
mal
A
b
n
o
r
ma
l
N
o
r
mal
6
0
6
6
A
b
n
o
r
ma
l
1
43
9
(
c)
N
o
r
mal
A
b
n
o
r
ma
l
N
o
r
mal
6
0
6
6
A
b
n
o
r
ma
l
1
43
9
(
d
)
N
o
r
mal
A
b
n
o
r
ma
l
N
o
r
mal
6
0
6
6
A
b
n
o
r
ma
l
1
43
9
(
e)
N
o
r
mal
A
b
n
o
r
ma
l
N
o
r
mal
4
5
4
1
5
2
A
b
n
o
r
ma
l
73
3
6
6
T
ab
le
2
.
C
lass
if
icatio
n
b
ased
o
n
s
ex
;
(
a)
SVM,
(
b
)
GNB,
(
c)
L
R
,
(
d
)
L
DA,
(
e
)
KNN
(
a)
M
a
l
e
F
e
mal
e
M
a
l
e
3
2
7
0
F
e
mal
e
1
2
7
6
(
b
)
M
a
l
e
F
e
mal
e
M
a
l
e
3
2
7
0
F
e
mal
e
0
2
7
7
(
c)
M
a
l
e
F
e
mal
e
M
a
l
e
3
2
7
0
F
e
mal
e
0
2
7
7
(
d
)
M
a
l
e
F
e
mal
e
M
a
l
e
3
2
7
0
F
e
mal
e
0
2
7
7
(
e)
M
a
l
e
F
e
mal
e
M
a
l
e
3
1
3
14
F
e
mal
e
0
2
7
7
T
ab
le
3
.
C
lass
if
icatio
n
o
f
m
al
e
b
ased
o
n
m
atu
r
ity
;
(
a
)
SVM,
(
b
)
GNB,
(
c)
L
R
,
(
d
)
L
DA,
(
e
)
KNN
(
a)
M
a
t
u
r
e
I
mm
a
t
u
r
e
M
a
t
u
r
e
2
8
6
0
I
mm
a
t
u
r
e
1
3
1
7
(
b
)
M
a
t
u
r
e
I
mm
a
t
u
r
e
M
a
t
u
r
e
2
8
6
0
I
mm
a
t
u
r
e
0
3
1
8
(
c)
M
a
t
u
r
e
I
mm
a
t
u
r
e
M
a
t
u
r
e
2
8
6
0
I
mm
a
t
u
r
e
0
3
1
8
(
d
)
M
a
t
u
r
e
I
mm
a
t
u
r
e
M
a
t
u
r
e
2
8
6
0
I
mm
a
t
u
r
e
0
3
1
8
(
e)
M
a
t
u
r
e
I
mm
a
t
u
r
e
M
a
t
u
r
e
2
4
2
44
I
mm
a
t
u
r
e
94
2
2
4
T
ab
le
4
.
C
lass
if
icatio
n
o
f
f
em
ale
b
ased
o
n
th
e
m
atu
r
ity
;
(
a)
SVM,
(
b
)
GNB,
(
c)
L
R
,
(
d
)
L
DA,
(
e)
KNN
(
a)
M
a
t
u
r
e
I
mm
a
t
u
r
e
M
a
t
u
r
e
1
2
0
37
I
mm
a
t
u
r
e
22
1
4
6
(
b
)
M
a
t
u
r
e
I
mm
a
t
u
r
e
M
a
t
u
r
e
1
5
7
0
I
mm
a
t
u
r
e
0
1
6
8
(
c)
M
a
t
u
r
e
I
mm
a
t
u
r
e
M
a
t
u
r
e
1
5
7
5
I
mm
a
t
u
r
e
0
1
6
8
(
d
)
M
a
t
u
r
e
I
mm
a
t
u
r
e
M
a
t
u
r
e
1
5
7
0
I
mm
a
t
u
r
e
0
1
6
8
(
e)
M
a
t
u
r
e
I
mm
a
t
u
r
e
M
a
t
u
r
e
1
1
6
41
I
mm
a
t
u
r
e
11
1
5
7
7.
CO
NCLU
SI
O
N
T
h
e
s
elec
tio
n
of
ef
f
ec
tiv
e
an
d
b
etter
m
u
ltis
tag
e
class
if
i
ca
tio
n
m
o
d
el
f
o
r
th
e
id
e
n
tif
icatio
n
of
E
cto
p
ar
asit
ed
in
f
ec
ted
m
u
d
cr
ab
,
S.
o
liva
ce
a
,
wer
e
in
v
esti
g
ated
in
th
is
p
ap
er
.
I
n
th
is
s
t
u
d
y
,
f
iv
e
m
ac
h
in
e
lear
n
in
g
class
if
ier
s
wer
e
u
tili
ze
d
to
ev
alu
ate
th
eir
p
er
f
o
r
m
an
ce
in
co
r
r
ec
tly
class
if
y
in
g
th
e
in
f
estatio
n
o
f
r
h
i
z
o
ce
p
h
alan
p
ar
asit
e
in
th
e
m
u
d
cr
ab
S
.
o
liva
ce
a
was
b
a
s
ed
o
n
m
o
r
p
h
o
lo
g
ical
ch
ar
ac
t
er
s
.
T
h
e
m
u
ltis
tag
e
class
if
ier
u
s
ed
in
t
h
is
p
a
p
e
r
p
r
o
d
u
ce
d
a
g
o
o
d
p
e
r
f
o
r
m
an
ce
f
o
r
th
e
id
en
tific
atio
n
of
E
c
t
o
p
a
r
-
a
s
ited
in
f
ec
ted
mud
cr
ab
as
co
m
p
ar
ed
with
p
r
e
v
io
u
s
in
d
iv
id
u
al
m
ac
h
in
e
lear
n
i
n
g
ap
p
r
o
ac
h
es,
i.e
SVM
an
d
KN
N.
T
h
e
r
esu
lts
f
r
o
m
th
e
ex
p
e
r
im
en
t
d
em
o
n
s
tr
ated
th
at,
L
D
A
an
d
GNB
p
r
o
d
u
ce
th
e
h
ig
h
est
r
ate
o
f
class
if
icati
o
n
was
s
u
cc
ee
d
ed
wh
ich
co
r
r
ec
tly
ass
ig
n
ed
1
0
0
%.
T
h
e
L
R
h
as
ac
cu
r
ac
y
o
f
9
8
.
5
-
1
0
0
%,
wh
ile
SVM
class
if
i
er
p
r
o
d
u
ce
ac
cu
r
ac
y
of
8
1
.
8
-
9
9
.
8
%.
T
h
e
p
o
o
r
e
r
o
f
ac
cu
r
ac
y
r
ates
of
class
if
icatio
n
is
KNN
wh
ich
p
r
o
d
u
ce
d
7
7
.
2
-
9
7
.
7
%.
I
n
th
e
f
u
tu
r
e
wo
r
k
,
KNN
class
if
ier
s
h
o
u
l
d
b
e
r
ejec
ted
f
r
o
m
th
e
a
n
aly
s
es.
I
n
th
e
n
ea
r
f
u
tu
r
e
wo
r
k
,
we
will
c
o
n
tin
u
e
t
o
d
e
v
elo
p
o
th
er
k
in
d
s
o
f
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
s
f
o
r
th
e
id
en
tific
ati
o
n
o
f
ec
to
p
a
r
asit
ed
in
f
ec
ted
m
u
d
c
r
ab
an
d
test
f
o
r
o
th
er
ex
p
er
im
en
tal
s
etu
p
.
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
.
2
,
Ap
r
il 2
0
2
1
:
4
0
6
-
413
412
ACK
NO
WL
E
DG
E
M
E
NT
S
Gr
atef
u
lly
ac
k
n
o
wled
g
es
th
e
co
llab
o
r
ato
r
s
an
d
th
is
p
r
o
je
ct
was
f
u
n
d
ed
b
y
T
ale
n
t
&
Pu
b
licatio
n
E
n
h
an
ce
m
e
n
t Res
ea
r
ch
Gr
an
t
(
5
5
1
6
8
)
.
RE
F
E
R
E
NC
E
S
[1
]
D.
B
Hu
n
g
ria,
e
t
a
l.
,
“
G
lo
b
a
l
sta
t
u
s
o
f
p
ro
d
u
c
ti
o
n
a
n
d
c
o
m
m
e
rc
ializa
ti
o
n
of
so
ft
-
sh
e
ll
c
ra
b
s,”
S
p
rin
g
e
r
In
ter
n
a
ti
o
n
a
l
Pu
b
li
s
h
in
g
,
2
0
1
7
.
[2
]
T.
N
.
Du
y
Kh
o
a
,
F.S
Ha
rriso
n
,
“
De
v
e
lo
p
m
e
n
t
of
m
u
d
c
ra
b
b
re
e
d
in
g
tec
h
n
o
lo
g
y
f
o
r
c
o
n
se
rv
a
ti
o
n
a
n
d
c
o
m
m
u
n
a
l
li
v
e
li
h
o
o
d
s
in
t
h
e
S
e
ti
u
Wetlan
d
s,
Tere
n
g
g
a
n
u
,
M
a
lay
sia
,
”
Asia
n
J
o
u
rn
a
l
o
f
Ag
ric
u
lt
u
re
a
n
d
Bi
o
l
ogy
,
p
p
.
1
1
-
1
6
,
2
0
1
9
.
[3
]
A.
A.
Laith
,
M
.
Am
b
a
k
,
A.
B.
A
b
o
l
-
M
u
n
a
fi
,
W.
W.
I
.
N
u
rh
a
fiza
h
,
a
n
d
M
.
Na
ji
a
h
,
“
M
e
tab
o
lo
m
ic
a
n
a
ly
sis
o
f
m
a
rin
e
a
n
d
m
u
d
c
ra
b
s
b
a
se
d
on
a
n
ti
b
a
c
teria
l
a
c
t
i
v
i
t
y
,
”
Aq
u
a
c
u
lt
u
re
Rep
o
rts
,
v
o
l.
7,
pp
7
-
1
5
,
2
0
1
7
.
[4
]
M
.
Ih
wa
n
,
W
.
W
a
h
a
b
,
A.
Am
b
a
k
,
M
.
Ik
h
wa
n
u
d
d
i
n
,
a
n
d
M
.
Ha
ss
a
n
,
“
In
v
e
stig
a
ti
o
n
o
f
p
a
ra
sites
a
n
d
e
c
to
-
sy
m
b
i
o
n
t
in
wild
m
u
d
c
ra
b
,
G
e
n
u
s
S
c
y
ll
a
fr
o
m
Tere
n
g
g
a
n
u
C
o
a
sta
l
wa
ter,
M
a
lay
sia
:
P
re
v
a
len
c
e
a
n
d
m
e
a
n
i
n
t
e
n
s
i
t
y
,
”
I
n
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Z
o
o
l
o
g
y
Res
e
a
rc
h
,
v
o
l
.
1
1
,
p
p
.
1
5
1
-
1
5
9
,
2
0
1
5
.
[5
]
D.
Jo
h
n
sto
n
,
D.
Y
e
o
h
,
D.
Ha
rris,
a
n
d
E
.
F
ish
e
r,
“
Blu
e
sw
imm
e
r
c
ra
b
(P
o
rt
u
n
u
s
a
rm
a
tu
s)
a
n
d
m
u
d
c
ra
b
(
S
c
y
ll
a
se
rra
ta
a
n
d
S
c
y
ll
a
o
li
v
a
c
e
a
)
re
so
u
rc
e
s
i
n
t
h
e
n
o
rt
h
c
o
a
st
a
n
d
g
a
sc
o
y
n
e
c
o
a
st
b
io
re
g
io
n
s,
w
e
s
t
e
rn
Au
str
a
li
a
,
”
Res
o
u
rc
e
Asse
ss
me
n
t
Rep
o
rt.
De
p
a
rtme
n
t
o
f
Prima
ry
I
n
d
u
strie
s
a
n
d
Reg
i
o
n
a
l
De
v
e
lo
p
me
n
t,
W
e
s
t
e
r
n
A
u
stra
li
a
,
p
p
.
1
8
6
,
2
0
2
0
.
[6
]
K.
W
a
i
h
o
,
H.
F
a
z
h
a
n
,
a
n
d
M
.
Ik
h
wa
n
u
d
d
i
n
,
“
S
ize
d
istri
b
u
t
io
n
,
len
g
t
h
–
we
ig
h
t
re
latio
n
s
h
ip
a
n
d
siz
e
a
t
th
e
o
n
se
t
o
f
se
x
u
a
l
m
a
tu
rit
y
o
f
th
e
o
ra
n
g
e
m
u
d
c
ra
b
,
sc
y
ll
a
o
li
v
a
c
e
a
,
in
m
a
lay
sia
n
w
a
t
e
r
s
,
”
M
a
rin
e
Bi
o
l
o
g
y
R
e
se
a
rc
h
,
v
o
l.
1
2
,
p
p
.
7
2
6
-
7
3
8
,
2
0
1
6
.
[7
]
K.
P
li
a
k
o
s,
P.
G
e
u
rts,
a
n
d
C.
V
e
n
s
,
“
G
lo
b
a
l
m
u
lt
i
-
o
u
tp
u
t
d
e
c
isio
n
tre
e
s
fo
r
in
tera
c
ti
o
n
p
re
d
icti
o
n
,
”
Ma
c
h
in
e
L
e
a
rn
i
n
g
,
v
o
l.
1
0
7
,
p
p
.
1
2
5
7
-
1
2
8
1
,
2
0
1
8
.
[8
]
I.
K.
Nti,
e
t
a
l
.
,
“
A
c
o
m
p
re
h
e
n
siv
e
e
v
a
lu
a
ti
o
n
o
f
e
n
se
m
b
le
lea
rn
in
g
f
o
r
sto
c
k
m
a
rk
e
t
p
re
d
icti
o
n
,
”
J
o
u
rn
a
l
o
f
Bi
g
Da
t
a
,
v
o
l.
7
,
n
o
.
1
,
M
a
r
ch
2
0
2
0
.
[9
]
H.
Alsh
a
z
ly
,
C.
Li
n
se
,
E.
Ba
rth
,
a
n
d
T.
M
a
rti
n
e
tz,
“
En
se
m
b
les
of
d
e
e
p
lea
rn
i
n
g
m
o
d
e
ls
a
n
d
tra
n
sfe
r
lea
rn
in
g
f
o
r
e
a
r
re
c
o
g
n
it
i
o
n
,
”
S
e
n
so
rs
,
v
o
l.
1
9
,
n
o
.
1
9
,
p
p
.
4
1
3
9
,
2
0
1
9
.
[1
0
]
N.
Ho
q
u
e
,
M.
S
i
n
g
h
a
n
d
D.
K.
Bh
a
tt
a
c
h
a
ry
y
a
,
“
E
F
S
-
M
I:
an
e
n
se
m
b
le
fe
a
tu
re
se
le
c
ti
o
n
m
e
th
o
d
fo
r
c
las
si
fic
a
ti
o
n
,
”
Co
mp
lex
&
In
telli
g
e
n
t
S
y
ste
ms
,
v
o
l.
4
,
p
p
.
1
0
5
-
1
1
8
,
2
0
1
8
.
[1
1
]
M.
V
il
l
a
v
e
rd
e,
D.
A
l
ed
o
,
D.
P
e
´
r
e
z,
an
d
F
.
M
o
r
e
n
o
,
“
On
th
e
a
d
ap
t
ab
i
l
it
y
of
en
s
e
m
b
l
e
m
e
th
o
d
s
fo
r
d
is
tri
b
u
ted
c
las
sifica
ti
o
n
s
y
ste
m
s:
A
c
o
m
p
a
ra
ti
v
e
a
n
a
l
y
sis,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
of
Distri
b
u
te
d
S
e
n
s
o
r
N
e
t
wo
rk
s
,
v
o
l.
1
5
,
n
o
.
7
,
2
0
1
9
.
[1
2
]
S.
T
e
w
a
r
i
,
U.
D.
Dw
iv
e
d
i
,
“
A
c
o
m
p
a
ra
ti
v
e
stu
d
y
of
h
e
tero
g
e
n
e
o
u
s
e
n
se
m
b
le
m
e
th
o
d
s
fo
r
th
e
i
d
e
n
ti
fica
ti
o
n
o
f
g
e
o
lo
g
ica
l
li
th
o
fa
c
ies
,
”
J
o
u
rn
a
l
o
f
Petro
leu
m E
x
p
lo
ra
ti
o
n
a
n
d
Pro
d
u
c
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
1
0
,
p
p
.
1
8
4
9
-
1
8
6
8
,
2
0
2
0
.
[1
3
]
F.
L
o
tt
e
,
L.
B
o
u
g
ra
in
,
et
al
.
,
“
A
re
v
iew
o
f
c
las
sifica
ti
o
n
a
lg
o
rit
h
m
s
fo
r
EEG
-
b
a
se
d
b
ra
in
-
c
o
m
p
u
ter
in
terfa
c
e
s:
a
1
0
-
y
e
a
r
u
p
d
a
te
,
”
J
o
u
rn
a
l
o
fNeu
ra
l
En
g
i
n
e
e
rin
g
,
v
o
l.
1
5
,
n
o
.
3
,
2
0
1
8
.
[1
4
]
H.
A.
M
.
R
o
s
l
y
,
S.
A.
M
o
h
d
N
o
r,
a
n
d
D.
M
d
.
Na
im,
“
P
h
y
l
o
g
e
n
e
ti
c
re
latio
n
s
h
ip
s
with
in
th
e
S
c
y
l
la
(
P
o
rt
u
n
i
d
a
e
)
a
ss
e
ss
e
d
by
t
h
e
m
it
o
c
h
o
n
d
rial
D
N
A
se
q
u
e
n
c
e
,
”
Bi
o
d
ive
rs
it
a
s
,
v
o
l.
18
,
n
o
.
4,
p
p
.
1
6
9
6
-
1
7
0
4
,
2
0
1
7
.
[1
5
]
D.
Re
e
s
a
n
d
H.
G
len
n
e
r,
“
Co
n
tro
l
re
g
io
n
se
q
u
e
n
c
e
s
in
d
ica
te
th
a
t
m
u
lt
ip
le
e
x
ter
n
a
e
re
p
re
se
n
t
m
u
lt
ip
le
in
fe
c
ti
o
n
s
b
y
sa
c
c
u
li
n
a
c
a
rc
in
i
(Cirri
p
e
d
ia:
Rh
i
z
o
c
e
p
h
a
la),”
Eco
lo
g
y
a
n
d
Evo
l
u
ti
o
n
,
v
o
l.
4
,
p
p
.
3
2
9
0
-
3
2
9
7
,
2
0
1
4
.
[1
6
]
C.
Na
g
ler,
M
.
K
Ho
r
n
i
g
,
J.
T
.
Ha
u
g
,
C.
N
o
e
v
e
r
,
J.
T
.
H
ø
e
g
,
H.
G
len
n
e
r,
“
Th
e
b
ig
g
e
r
,
t
h
e
b
e
tt
e
r?
V
o
l
u
m
e
m
e
a
su
re
m
e
n
ts
of
p
a
ra
sites
a
n
d
h
o
s
ts:
P
a
ra
siti
c
b
a
rn
a
c
les
(Cirri
p
e
d
ia,
Rh
izo
c
e
p
h
a
l)
a
n
d
th
e
ir
d
e
c
a
p
o
d
h
o
s
t
s
,
”
PL
o
S
ONE
,
v
o
l.
1
2
,
n
o
.
7
,
2
0
1
7
.
[1
7
]
KA
Ly
c
e
tt
,
J.
S
Ch
u
n
g
,
J.
S
P
it
u
l
a
,
“
Th
e
re
latio
n
s
h
ip
of
b
lu
e
c
ra
b
(Ca
ll
in
e
c
tes
sa
p
id
u
s)
siz
e
c
las
s
a
n
d
m
o
lt
sta
g
e
to
d
ise
a
se
a
c
q
u
isit
io
n
a
n
d
in
ten
sity
o
f
He
m
a
to
d
in
iu
m
p
e
re
z
i
in
fe
c
ti
o
n
s
,
”
J
o
u
rn
a
l
PL
o
S
On
e
,
v
o
l
1
3
,
n
o
.
2
,
2
0
1
8
.
[1
8
]
J.
M.
S.
Tete
lep
ta,
Y.
Na
tan
,
On
g
T.
S.
On
g
k
e
rs,
J.
A.
P
a
tt
ik
a
wa
,
“S
o
m
e
p
o
p
u
lati
o
n
b
io
l
o
g
y
a
sp
e
c
ts
of
Ed
-
i
b
le
Ora
n
g
e
M
u
d
Cra
b
S
c
y
l
la
Oliv
a
c
e
a
(He
rb
st,
1
7
9
6
)
of
Ko
tan
ia
B
a
y
,
we
ste
rn
S
e
ra
m
District,
In
d
o
n
e
sia
,
”
AA
CL
Bi
o
fl
u
x
,
v
o
l.
1
1
,
no.
4,
2
0
1
8
.
[1
9
]
S
.
Kim
,
P.
J
o
sh
i,
P.
S
.
Ka
lsi,
a
n
d
P.
T
a
h
e
r
i
,
“
Crime
a
n
a
ly
sis
t
h
ro
u
g
h
m
a
c
h
in
e
lea
rn
i
n
g
,
”
An
n
u
a
l
I
n
f
o
r
ma
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
El
e
c
tro
n
ics
a
n
d
M
o
b
i
le Co
mm
u
n
ic
a
ti
o
n
C
o
n
fer
e
n
c
e
(I
EM
CON)
,
2
0
1
8
,
p
p
.
4
1
5
-
4
2
0
.
[2
0
]
U.
S.
R
e
d
d
y
,
A.
V.
Th
o
ta,
a
n
d
A.
Dh
a
ru
n
,
“
M
a
c
h
i
n
e
lea
rn
i
n
g
tec
h
n
i
q
u
e
s
fo
r
stre
ss
p
re
d
ictio
n
in
w
o
r
k
i
n
g
e
m
p
lo
y
e
e
s
,”
In
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
on
C
o
mp
u
t
a
ti
o
n
a
l
In
telli
g
e
n
c
e
a
n
d
C
o
mp
u
ti
n
g
Res
e
a
rc
h
(ICCIC)
,
2
0
1
8
,
p
p
.
1
-
4
.
[2
1
]
J.
W
a
¨
ld
ch
en
an
d
P
.
M
a
¨
de
r
,
“
M
a
c
h
in
e
L
e
a
rn
in
g
fo
r
I
m
ag
e
B
a
s
ed
S
p
e
c
i
e
s
Id
en
t
if
ic
at
io
n
”
M
e
th
o
d
s
in
E
c
o
l
o
g
y
a
n
d
Evo
lu
ti
o
n
,
v
o
l.
9
,
p
p
.
2
2
1
6
-
2
2
2
5
,
2
0
1
8
.
[2
2
]
B.
V
.
De
e
p
a
n
d
R.
Da
sh
,
“
Un
d
e
rwa
ter
fish
sp
e
c
ies
re
c
o
g
n
it
io
n
u
si
n
g
d
e
e
p
lea
rn
i
n
g
t
e
c
h
n
i
q
u
e
s
,
”
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
on
S
i
g
n
a
l
Pro
c
e
ss
in
g
and
I
n
teg
ra
ted
Ne
two
rk
s
(S
PIN)
,
2
0
1
9
,
p
p
.
6
6
5
-
6
6
9
.
[2
3
]
S.
S.
P
a
n
e
sa
r,
R.
N.
D’So
u
z
a
,
F.
C.
Y
e
h
,
a
n
d
J.
C.
F
e
rn
a
n
d
e
z
-
M
iran
d
a
,
“
M
a
c
h
i
n
e
lea
rn
in
g
v
e
r
s
u
s
lo
g
isti
c
re
g
re
ss
io
n
m
e
th
o
d
s
f
o
r
2
-
y
e
a
r
m
o
rtalit
y
p
r
o
g
n
o
st
ica
ti
o
n
in
a
sm
a
ll
,
h
e
ter
o
g
e
n
e
o
u
s
g
li
o
m
a
d
a
t
a
b
a
s
e
,
”
W
o
r
l
d
N
e
u
ro
su
rg
e
ry
:
X
,
v
o
l.
2
,
2
0
1
9
.
[2
4
]
Y.
Xin
,
L.
Ko
n
g
,
Z.
Li
u
,
Y
.
C
h
e
n
,
Y
.
Li
,
H.
Zh
u
,
e
t
a
l.
,
“
M
a
c
h
in
e
lea
rn
i
n
g
a
n
d
d
e
e
p
lea
rn
i
n
g
m
e
t
h
o
d
s
fo
r
c
y
b
e
rse
c
u
rit
y
,
”
IE
EE
Acc
e
ss
,
v
o
l.
6
,
p
p
.
3
5
3
6
5
-
3
5
3
8
1
,
2
0
1
8
.
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
Ma
ch
in
e
lea
r
n
in
g
w
ith
mu
ltis
ta
g
e
cla
s
s
ifier
s
fo
r
id
en
tifi
ca
tio
n
o
f
...
(
R
o
z
n
iz
a
A
li
)
413
[2
5
]
D
.
M
d
.
Na
im,
S.
A.
M
No
r,
S.
M
a
h
b
o
o
b
,
“
Re
a
ss
e
ss
m
e
n
t
of
sp
e
c
ies
d
istri
b
u
ti
o
n
a
n
d
o
c
c
u
rre
n
c
e
of
m
u
d
c
r
a
b
(S
c
y
ll
a
sp
p
.
,
P
o
rtu
n
id
a
e
)
in
M
a
lay
sia
th
r
o
u
g
h
m
o
r
p
h
o
l
o
g
ica
l
a
n
d
m
o
lec
u
l
a
r
id
e
n
ti
fica
ti
o
n
,
”
S
a
u
d
i
J
o
u
rn
a
l
o
f
B
i
o
l
o
g
i
c
a
l
S
c
i
e
n
c
e
s
,
v
o
l
.
2
,
p
p
6
4
3
-
6
5
2
,
2
0
2
0
.
[2
6
]
W
.
R.
W
a
n
Y
u
s
o
f
,
F.
B
Ah
m
a
d
,
a
n
d
M
.
S
w
a
m
y
,
“
A
b
rief
re
v
iew
o
n
th
e
a
n
ti
o
x
id
a
n
ts
a
n
d
a
n
ti
m
icro
b
ial
p
e
p
ti
d
e
s
re
v
e
a
led
in
m
u
d
c
ra
b
s fr
o
m
th
e
g
e
n
u
s o
f
s
c
y
l
l
a
,
”
J
o
u
rn
a
l
o
f
M
a
rin
e
Bi
o
l
o
g
y
,
v
o
l.
2
0
1
7
,
2
0
1
7
.
[2
7
]
N.
A.
M.
S
h
a
rif,
e
t
a
l
.
,
“
S
p
e
c
ies
d
iv
e
rsit
y
a
n
d
d
istri
b
u
ti
o
n
o
f
m
u
d
c
ra
b
i
n
M
a
r
u
d
u
Ba
y
m
a
n
g
ro
v
e
fo
re
st
re
se
rv
e
,
S
a
b
a
h
,
M
a
lay
sia
,
“
Bo
rn
e
o
J
o
u
rn
a
l
o
f
M
a
ri
n
e
S
c
ien
c
e
a
n
d
Aq
u
a
c
u
lt
u
re
(BJo
M
S
A)
,
p
p
1
8
-
2
4
,
2
0
1
9
.
[2
8
]
A.
Th
a
rwa
t,
Y.
S.
M
o
e
m
e
n
,
A.
E
Ha
ss
a
n
ien
,
“
Clas
sifica
ti
o
n
o
f
to
x
icit
y
e
ffe
c
ts
o
f
b
i
o
tran
sfo
rm
e
d
h
e
p
a
ti
c
d
ru
g
s
u
sin
g
w
h
a
le o
p
ti
m
ize
d
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
s,”
J
o
u
r
n
a
l
o
f
Bi
o
me
d
ica
l
I
n
fo
rm
a
ti
c
s
,
v
o
l
6
8
,
pp
1
3
2
-
1
4
6
,
2
0
1
7
.
[2
9
]
R.
Ali,
A.
Hu
ss
a
in
,
J.
E.
Br
o
n
,
a
n
d
A.
P
.
S
h
i
n
n
,
“
M
u
lt
i
-
sta
g
e
c
las
sifica
t
io
n
o
f
G
y
ro
d
a
c
ty
lu
s
sp
e
c
ie
s
u
s
in
g
m
a
c
h
in
e
lea
rn
in
g
a
n
d
fe
a
tu
re
se
lec
ti
o
n
tec
h
n
iq
u
e
s,”
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
I
n
telli
g
e
n
t
S
y
s
t
e
m
s
De
sig
n
a
n
d
A
p
p
li
c
a
ti
o
n
s
,
2
0
1
1
,
p
p
.
4
5
7
-
4
6
2
.
[3
0
]
D.
Li
,
e
t
a
l
.
,
“
Lea
rn
i
n
g
to
d
e
tec
t
traffic
in
c
id
e
n
ts
fro
m
d
a
ta
b
a
se
d
o
n
tree
a
u
g
m
e
n
te
d
n
a
iv
e
b
a
y
e
sia
n
c
las
sifiers
,”
Disc
re
te
Dy
n
a
mic
s
in
Na
t
u
re
a
n
d
S
o
c
iety
,
2
0
1
7
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Ro
z
n
iza
Ali
o
b
tain
e
d
B.
S
c
fro
m
Ko
lej
Un
iv
e
rsiti
S
u
lt
a
n
Zain
a
l
Ab
id
i
n
,
M
S
c
.
fr
o
m
Un
iv
e
rsiti
Tek
n
o
l
o
g
i
M
ARA
a
n
d
P
h
.
D
i
n
C
o
m
p
u
ter
S
c
ien
c
e
fr
o
m
S
ti
rl
in
g
Un
iv
e
rsity
,
Un
it
e
d
Ki
n
g
d
o
m
.
No
w
sh
e
se
rv
e
d
a
t
U
n
iv
e
rsiti
M
a
lay
sia
Tere
n
g
g
a
n
u
a
s
se
n
i
o
r
lec
tu
re
r
a
t
th
e
F
a
c
u
lt
y
Oc
e
a
n
En
g
in
e
e
ri
n
g
T
e
c
h
n
o
l
o
g
y
a
n
d
I
n
f
o
rm
a
ti
c
s.
He
r
r
e
se
a
rc
h
a
re
a
o
f
in
tere
st
is
o
n
ima
g
e
p
ro
c
e
ss
in
g
a
n
d
p
a
tt
e
rn
r
e
c
o
g
n
it
i
o
n
Mu
h
a
m
a
d
Mu
n
a
w
a
r
Yusr
o
o
b
t
a
in
e
d
h
is
Ba
c
h
e
lo
r
a
n
d
M
a
ste
r
o
f
Co
m
p
u
ter
S
c
ien
c
e
fro
m
Un
iv
e
r
sitas
G
a
d
jah
M
a
d
a
,
I
n
d
o
n
e
sia
.
He
c
u
rre
n
tl
y
r
u
n
P
ro
g
ra
m
m
in
g
sc
h
o
o
l
s
fo
r
k
i
d
s
a
n
d
tee
n
a
g
e
rs
in
Yo
g
y
a
k
a
rta
a
n
d
P
u
r
wo
k
e
rto
,
I
n
d
o
n
e
sia
.
His
re
se
a
rc
h
in
tere
sts
a
re
fo
c
u
se
d
o
n
F
u
z
z
y
d
e
c
isio
n
m
a
k
in
g
,
Co
n
v
o
lu
t
io
n
a
l
Ne
u
ra
l
Ne
two
rk
,
Im
a
g
e
p
ro
c
e
ss
in
g
a
n
d
In
f
o
rm
a
ti
o
n
sy
ste
m
s.
Mu
h
a
m
m
a
d
S
u
z
u
r
i
H
it
a
m
o
b
tain
e
d
h
is
Ba
c
h
e
lo
r
o
f
I
n
d
u
stri
a
l
Tec
h
n
o
l
o
g
y
(B
.
Tec
h
(Ho
n
s.)
f
r
o
m
Un
iv
e
rsiti
S
a
in
s
M
a
lay
sia
a
n
d
P
h
.
D
d
e
g
re
e
fro
m
U
n
i
v
e
rsity
o
f
Le
e
d
s,
Un
it
e
d
Kin
g
d
o
m
.
He
is
c
u
r
re
n
tl
y
a
P
ro
f
e
ss
o
r
at
th
e
F
a
c
u
lt
y
Oc
e
a
n
En
g
in
e
e
rin
g
Tec
h
n
o
lo
g
y
a
n
d
In
fo
rm
a
ti
c
s,
Un
i
v
e
rsiti
M
a
lay
sia
Tere
n
g
g
a
n
u
.
His
re
se
a
rc
h
in
tere
s
ts
a
re
fo
c
u
se
d
o
n
ima
g
e
p
ro
c
e
ss
in
g
,
c
o
m
p
u
tatio
n
a
l
i
n
telli
g
e
n
c
e
a
n
d
ro
b
o
t
ics
.
Mu
h
a
m
a
d
Ikh
wa
n
u
d
d
in
Abd
u
ll
a
h
o
b
tain
e
d
h
is
Ba
c
h
e
lo
r
o
f
F
ish
e
ries
S
c
ien
c
e
fro
m
Un
iv
e
rsiti
P
u
tra
M
a
lay
sia
a
n
d
P
h
.
D
d
e
g
re
e
fro
m
Un
i
v
e
rsiti
M
a
lay
si
a
S
a
ra
wa
k
,
M
a
lay
sia
.
He
is
c
u
rre
n
tl
y
a
P
ro
fe
ss
o
r
a
t
th
e
I
n
stit
u
te
of
Tro
p
ica
l
Aq
u
a
c
u
lt
u
re
(
A
K
U
A
T
R
O
P
)
,
Un
iv
e
rsiti
M
a
lay
sia
Tere
n
g
g
a
n
u
.
His
re
se
a
rc
h
in
tere
sts
a
re
fo
c
u
se
d
o
n
Ag
ric
u
lt
u
re
S
c
ien
c
e
,
Aq
u
a
c
u
lt
u
re
,
F
is
h
Re
p
ro
d
u
c
t
io
n
a
n
d
M
a
rin
e
S
c
ien
c
e
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.