I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
p
u
t
er
Science
Vo
l.
1
2
,
No
.
2
,
N
o
v
e
m
b
er
201
8
,
p
p
.
5
7
0
~
5
7
6
I
SS
N:
2502
-
4752
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ee
cs
.
v
1
2
.i
2
.
p
p
570
-
5
7
6
570
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e.
co
m/jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
ijeec
s
Da
ta M
ining
App
ro
a
ch t
o
Herbs
Cl
a
ss
ificatio
n
Adill
a
h Da
y
a
na
Ah
m
a
d Da
li
,
Nurul Asw
a
O
m
a
r,
Aida
M
us
t
a
ph
a
F
a
k
u
lt
i
S
a
in
s K
o
m
p
u
ter d
a
n
T
e
k
n
o
lo
g
i
M
a
k
lu
m
a
t,
Un
iv
e
rsiti
T
u
n
Hu
ss
e
in
On
n
M
a
lay
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
A
p
r
9
,
2
0
1
8
R
ev
i
s
ed
Ma
y
2
0
,
2
0
1
8
A
cc
ep
ted
Ju
l
11
,
2
0
1
8
He
rb
s
a
re
o
n
e
o
f
th
e
h
ig
h
-
v
a
lu
e
p
ro
d
u
c
ts
in
M
a
lay
sia
.
T
h
e
ter
m
„
h
e
rb
s‟
h
a
s
m
o
re
th
a
n
o
n
e
d
e
f
in
it
io
n
.
It
is
a
lso
d
e
m
a
n
d
in
g
b
y
m
u
lt
ip
le
m
a
n
if
o
l
d
s.
He
rb
s
a
re
u
se
d
in
m
a
n
y
se
c
to
rs
n
o
w
a
d
a
y
s.
T
h
e
a
b
il
it
y
to
id
e
n
t
ify
v
a
riety
h
e
rb
s
in
th
e
m
a
rk
e
t
is
q
u
it
e
h
a
rd
w
it
h
o
u
t
th
e
in
terv
e
n
ti
o
n
o
f
h
u
m
a
n
e
x
p
e
rts.
Un
f
o
rtu
n
a
tely
,
h
u
m
a
n
e
x
p
e
rts
a
re
p
ro
n
e
t
o
e
rro
r.
He
rb
s
c
las
sif
ica
ti
o
n
is
a
b
le
to
a
ss
ist
h
u
m
a
n
e
x
p
e
rts
a
n
d
a
t
th
e
sa
m
e
ti
m
e
m
in
i
m
izin
g
th
e
in
terv
e
n
ti
o
n
.
T
h
is
re
se
a
rc
h
p
e
rf
o
r
m
s
id
e
n
ti
f
ic
a
ti
o
n
a
n
d
c
las
sif
ica
ti
o
n
o
f
h
e
rb
s
b
a
se
d
o
n
im
a
g
e
c
a
p
tu
re
a
d
v
a
riet
y
o
f
c
la
ss
if
ic
a
ti
o
n
a
lg
o
rit
h
m
s
su
c
h
a
s
a
n
A
rti
f
icia
l
Ne
u
ra
l
Ne
tw
o
rk
(
A
NN
),
K
-
Ne
a
r
e
st
Ne
ig
h
b
o
rs
(IBK),
De
c
isio
n
T
a
b
le
(DT
)
a
n
d
M
5
P
T
re
e
a
lg
o
rit
h
m
s.
T
h
e
se
lec
ted
a
lg
o
rit
h
m
s
a
re
i
m
p
le
m
e
n
ted
a
n
d
e
v
a
lu
a
ted
to
t
h
e
ir
re
lativ
e
p
e
rf
o
rm
a
n
c
e
a
n
d
IBK
is
f
o
u
n
d
t
o
p
r
o
d
u
c
e
th
e
h
ig
h
e
st q
u
a
li
ty
o
u
tp
u
ts.
K
ey
w
o
r
d
s
:
C
las
s
i
f
icatio
n
Data
m
i
n
i
n
g
Her
b
s
Co
p
y
rig
h
t
©
2
0
1
8
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Nu
r
u
l
As
w
a
O
m
ar
,
Fak
u
lti Sai
n
s
K
o
m
p
u
ter
d
an
T
ek
n
o
lo
g
i M
ak
l
u
m
at,
Un
i
v
er
s
iti T
u
n
H
u
s
s
ei
n
On
n
Ma
la
y
s
ia,
P
ar
it R
aj
a,
8
6
4
0
0
B
atu
P
ah
at,
J
o
h
o
r
,
Ma
lay
s
ia
.
E
m
ail:
n
u
r
u
las
w
a@
u
t
h
m
.
ed
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
Ma
la
y
s
ia
is
o
n
e
o
f
th
e
lead
i
n
g
ex
p
o
r
ter
o
f
h
er
b
s
.
T
h
e
h
er
b
s
in
d
u
s
tr
y
w
as
ai
m
i
n
g
to
p
r
o
d
u
ce
h
i
g
h
-
v
alu
e
p
r
o
d
u
cts,
to
talin
g
R
M2
.
2
b
illi
o
n
o
f
th
e
Gr
o
s
s
Natio
n
al
I
n
co
m
e
(
GNI
)
as
r
ep
o
r
te
d
in
T
h
e
Ma
la
y
s
ia
n
T
im
es
n
e
w
s
p
ap
er
(
2
0
1
3
)
.
Dat
a
s
h
o
w
s
t
h
at
h
er
b
al
p
r
o
d
u
ct
d
e
m
a
n
d
h
a
s
m
u
ltip
lied
m
a
n
i
f
o
ld
s
.
Her
b
al
h
ea
lth
f
o
o
d
s
h
a
v
e
r
ea
c
h
ed
R
M2
,
3
8
0
b
illi
o
n
ar
o
u
n
d
2
0
0
1
.
P
r
io
r
to
th
a
t,
f
r
o
m
o
n
l
y
R
M2
,
0
9
3
.
8
m
illi
o
n
i
n
1
9
8
0
,
d
r
asti
c
in
cr
ea
s
e
i
n
t
h
e
w
o
r
ld
h
er
b
al
p
r
o
d
u
cts
ar
e
v
al
u
ed
at
R
M9
5
0
b
illi
o
n
in
1
9
9
6
.
C
u
r
r
e
n
t
l
y
,
t
h
e
tr
ad
e
v
alu
e
o
f
t
h
e
h
er
b
s
ec
to
r
w
a
s
e
x
p
ec
te
d
to
s
o
ar
o
v
er
R
M2
tr
ill
io
n
b
y
th
e
y
ea
r
o
f
2
0
2
0
.
T
h
e
v
al
u
e
o
f
t
h
r
ee
f
o
ld
in
cr
ea
s
e
co
m
p
ar
ed
to
th
e
R
M7
7
7
b
illi
o
n
w
o
r
th
o
f
tr
ad
e
w
a
s
esti
m
at
ed
in
th
e
h
er
b
s
s
ec
to
r
in
2
0
0
9
.
On
th
e
lo
ca
l
f
r
o
n
t,
th
e
m
i
n
is
tr
y
e
s
ti
m
ated
t
h
e
h
er
b
m
ar
k
et
to
ex
p
a
n
d
b
y
1
5
p
er
ce
n
t
a
y
ea
r
f
r
o
m
R
M7
b
illi
o
n
in
2
0
1
0
to
ar
o
u
n
d
R
M2
9
b
illi
o
n
b
y
2
0
2
0
.
Gen
er
all
y
,
it is
k
n
o
w
n
t
h
at
h
er
b
s
h
as c
o
n
tr
ib
u
ted
a
lo
t i
n
m
e
d
icin
al
p
u
r
p
o
s
ed
f
r
o
m
lo
n
g
ti
m
e
a
g
o
.
A
l
l
th
e
f
ac
t
s
,
tr
u
t
h
s
o
r
p
r
in
cip
les
o
f
h
er
b
s
h
a
s
b
ee
n
p
ass
ed
d
o
w
n
f
o
r
p
er
io
d
s
o
f
m
ille
n
ar
ia
n
o
f
y
ea
r
s
[
1
]
.
Her
b
s
ar
e
n
u
tr
i
tio
u
s
a
s
w
ell
a
s
v
a
lu
ab
le
p
lan
ts
.
T
r
u
th
f
u
ll
y
,
t
h
e
b
i
g
g
e
s
t
p
o
s
s
ib
le
f
o
r
n
e
w
h
er
b
cu
r
r
en
tl
y
lie
s
i
n
th
e
f
o
o
d
s
ec
to
r
s
.
I
t
is
b
ein
g
u
s
ed
in
f
o
o
d
p
r
e
p
ar
atio
n
an
d
n
o
t
o
n
l
y
t
h
at,
it
is
al
s
o
b
ein
g
w
id
el
y
u
s
ed
in
m
ed
ici
n
e
an
d
co
s
m
etic
in
d
u
s
tr
y
.
Her
b
s
ar
e
u
s
ed
b
y
a
l
m
o
s
t
e
v
er
y
o
n
e
n
o
wad
ay
s
eit
h
er
i
n
t
h
e
f
o
r
m
o
f
s
p
ices,
h
er
b
s
o
r
d
ail
y
f
o
o
d
-
b
ased
p
r
o
d
u
cts.
W
ith
t
h
e
in
cr
ea
s
i
n
g
u
s
e
o
f
h
er
b
s
,
t
h
er
e
is
a
n
u
r
g
e
n
t
n
ee
d
f
o
r
th
e
ab
ilit
y
to
id
en
t
if
y
v
ar
iet
y
h
er
b
s
av
ailab
le
i
n
th
e
m
ar
k
et.
Mo
s
t
h
er
b
s
g
r
o
w
in
t
h
e
j
u
n
g
le
an
d
th
e
w
a
y
t
h
e
y
id
en
ti
f
y
i
s
th
r
o
u
g
h
th
e
r
ec
o
g
n
itio
n
o
f
h
u
m
an
e
x
p
er
ts
.
I
t
is
v
er
y
i
m
p
o
r
tan
ce
to
au
to
m
atica
ll
y
ac
k
n
o
w
led
g
e
th
e
v
ar
i
o
u
s
t
y
p
e
o
f
h
er
b
s
f
o
r
h
er
b
s
cla
s
s
i
f
icatio
n
r
ef
er
r
ed
o
n
th
eir
p
ar
ticu
lar
f
ea
tu
r
es
d
u
e
to
s
h
o
r
t
n
u
m
b
er
o
f
r
eso
u
r
ce
s
alo
n
g
w
ith
k
n
o
w
led
g
ea
b
le
p
er
s
o
n
.
On
e
w
a
y
to
id
en
ti
f
y
h
er
b
s
i
s
th
r
o
u
g
h
clas
s
i
f
icatio
n
o
f
t
h
e
h
er
b
s
.
C
o
m
p
u
ter
Scie
n
ce
h
a
s
f
i
n
all
y
h
ar
n
e
s
s
ed
b
o
th
t
h
e
en
o
r
m
o
u
s
s
to
r
eh
o
u
s
e
o
f
d
ata
an
d
th
e
v
ast
co
m
p
u
ta
tio
n
al
p
o
w
er
.
W
id
el
y
d
e
f
in
ed
as
Kn
o
wled
g
e
Dis
co
v
er
y
i
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
Da
ta
Min
in
g
A
p
p
r
o
a
ch
t
o
Herb
s
C
la
s
s
i
fica
tio
n
(
A
d
illa
h
Da
ya
n
a
A
h
ma
d
Da
li
)
571
th
e
d
atab
ases
,
d
ata
m
i
n
i
n
g
i
s
co
m
p
u
ter
ized
o
r
u
s
e
f
u
l
e
x
tr
ac
tio
n
o
f
p
atter
n
s
.
I
t
r
ep
r
ese
n
ts
th
e
k
n
o
w
led
g
e
in
ev
itab
l
y
g
at
h
er
ed
in
d
atab
ases
th
at
r
eso
l
v
es c
o
m
p
lica
tio
n
.
Data
m
i
n
in
g
is
ab
o
u
t
co
n
f
ig
u
r
atio
n
o
f
co
m
p
licatio
n
b
y
e
x
a
m
i
n
e
an
d
d
eter
m
in
e
t
h
e
d
ata
th
at
alr
ea
d
y
ex
is
ted
i
n
th
e
d
atab
ases
.
I
t
f
in
d
s
th
e
i
m
p
o
r
tan
t
in
f
o
r
m
at
io
n
h
id
d
en
in
lar
g
e
v
o
l
u
m
es
o
f
d
a
ta
[
2
]
.
Data
m
i
n
in
g
is
also
d
escr
ib
ed
as
th
e
s
er
ie
s
o
f
ac
tio
n
o
f
u
n
co
v
er
i
n
g
p
a
tter
n
s
i
n
d
ata.
T
h
e
p
o
s
s
ib
le
u
s
e
o
f
d
ata
m
i
n
in
g
m
et
h
o
d
d
ef
in
es
t
h
at
th
e
ap
p
r
o
ac
h
in
w
h
ich
a
r
ep
o
s
ito
r
y
o
f
d
ata
ca
n
b
e
u
tili
ze
d
m
a
y
s
tr
et
ch
f
ar
b
e
y
o
n
d
w
h
at
w
a
s
p
er
ce
iv
e
w
h
en
t
h
e
d
ata
w
as
in
itial
l
y
g
a
th
er
ed
.
L
o
ts
o
f
a
p
p
licatio
n
s
in
m
ac
h
i
n
e
lear
n
i
n
g
to
d
ata
m
in
in
g
as
s
h
o
w
n
i
n
th
e
u
n
d
er
s
ta
n
d
in
g
.
T
h
e
i
m
p
o
r
tan
t
k
n
o
w
led
g
e
s
tr
u
c
tu
r
es
t
h
at
ar
e
g
ai
n
ed
,
th
e
f
u
n
d
a
m
e
n
ta
l
ex
p
lan
atio
n
,
ar
e
at
leas
t
as
cr
u
cial,
a
n
d
f
r
eq
u
e
n
tl
y
v
er
y
m
u
ch
m
o
r
e
s
u
b
s
tan
tia
l
co
m
p
ar
e
to
th
e
ca
p
ab
ilit
y
to
ac
co
m
p
li
s
h
w
ell
o
n
n
e
w
ex
a
m
p
les.
L
o
ts
o
f
lear
n
i
n
g
tech
n
iq
u
es
lo
o
k
f
o
r
s
tr
u
ct
u
r
al
d
e
f
in
itio
n
o
f
w
h
at
i
s
lear
n
ed
,
d
ef
i
n
itio
n
t
h
a
t
co
u
ld
b
e
q
u
ite
co
m
p
l
icate
d
an
d
ar
e
co
m
m
o
n
l
y
ar
tic
u
late
as
s
ets
o
f
r
u
les.
I
n
th
e
r
ec
en
t
d
ev
elo
p
m
en
t
o
f
a
u
to
m
ate
d
class
i
f
icatio
n
tech
n
iq
u
e
s
,
th
e
r
e
h
as
b
ee
n
a
g
r
ea
t
d
ea
l
o
f
p
r
o
g
r
ess
.
Fro
m
t
h
e
co
m
b
in
atio
n
s
o
f
ar
ti
f
icia
l
in
tell
i
g
e
n
ce
an
d
s
tat
is
tical
cl
ass
i
f
icatio
n
ap
p
r
o
ac
h
es,
a
s
ig
n
i
f
ican
t
n
u
m
b
er
o
f
n
e
w
tech
n
iq
u
e
s
h
a
v
e
ar
is
en
.
Ma
ch
i
n
e
lear
n
i
n
g
a
n
d
d
ata
m
i
n
in
g
h
a
v
e
b
o
th
f
asc
in
ated
r
ea
s
o
n
ab
le
in
ter
es
t
i
n
t
h
e
clas
s
i
f
ic
atio
n
al
g
o
r
ith
m
s
o
f
b
o
th
in
t
h
e
r
esear
c
h
ar
ea
s
.
A
f
e
w
e
x
ter
n
al
-
m
e
m
o
r
y
al
g
o
r
it
h
m
s
[
3
-
6
]
an
d
p
ar
allel
i
m
p
le
m
en
tatio
n
s
[
7
]
,
[
8
]
h
av
e
also
b
ee
n
s
p
ec
if
ied
.
I
t
h
a
v
e
b
ee
n
r
ec
o
m
m
e
n
d
ed
w
it
h
t
h
e
p
u
r
p
o
s
ed
o
f
b
o
o
s
t
u
p
th
e
i
m
p
le
m
en
ta
tio
n
ti
m
e
also
an
al
y
ze
o
n
h
u
g
e
tr
ain
i
n
g
s
ets.
A
lo
g
ical
p
r
o
g
r
a
m
m
in
g
tech
n
iq
u
e
is
p
r
o
p
o
s
ed
b
y
d
u
p
lica
t
i
n
g
th
e
m
ec
h
a
n
is
m
o
f
t
h
e
h
u
m
an
b
r
ain
,
w
h
ic
h
is
th
e
o
b
j
ec
tiv
e
o
f
A
r
t
if
icial
Ne
u
r
al
Net
w
o
r
k
(
ANN
)
.
T
h
is
tech
n
iq
u
e
s
i
m
u
lates
t
h
e
m
ai
n
b
io
lo
g
ical
o
p
er
atio
n
s
o
f
t
h
e
h
u
m
a
n
b
r
ain
u
tili
zi
n
g
a
p
ar
ticu
lar
s
o
f
t
w
a
r
e.
A
NN
is
a
n
al
g
o
r
ith
m
t
h
at
is
ab
le
to
p
er
f
o
r
m
h
u
m
a
n
b
r
ain
o
p
er
atio
n
s
,
co
m
p
o
s
in
g
d
ec
i
s
io
n
s
,
cr
ea
tin
g
r
es
u
lts
,
p
r
o
d
u
ce
co
n
cl
u
s
io
n
s
r
e
f
e
r
r
in
g
to
t
h
e
e
x
is
te
n
t
in
f
o
r
m
atio
n
i
n
ca
s
e
t
h
er
e
ar
e
in
s
u
f
f
icie
n
t
d
ata,
co
n
ti
n
u
all
y
r
ec
eiv
i
n
g
,
lear
n
in
g
a
n
d
r
e
m
e
m
b
er
in
g
d
ata
in
a
co
m
p
u
ti
n
g
e
n
v
ir
o
n
m
en
t [
9
]
.
A
t
p
r
esen
t,
it
i
s
p
r
ett
y
co
m
p
lic
ated
to
ap
p
l
y
m
ac
h
in
e
v
i
s
io
n
t
o
ca
teg
o
r
ize
h
er
b
,
d
u
e
to
t
h
e
s
u
b
s
ta
n
tial
co
m
p
u
tatio
n
al
r
eso
u
r
ce
s
alo
n
g
t
h
e
d
if
f
icu
lties
al
g
o
r
ith
m
s
n
ee
d
ed
.
T
h
e
A
NN
ca
n
d
ef
ea
t
f
e
w
o
f
th
e
co
m
p
lica
tio
n
b
y
e
x
tr
ac
tin
g
th
e
f
ea
t
u
r
es
i
n
s
tan
t
l
y
as
w
e
ll
as
e
f
f
icien
tl
y
.
A
NN
h
as
ar
is
e
n
as
t
h
e
i
m
itatio
n
o
f
t
h
e
b
io
lo
g
ical
n
er
v
o
u
s
s
y
s
te
m
.
A
m
o
d
e
o
f
w
o
r
k
i
n
g
o
f
a
co
m
p
u
ter
b
y
ass
i
m
i
lated
to
th
e
m
o
d
e
o
f
w
o
r
k
i
n
g
o
f
a
b
r
ain
,
n
eu
r
al
n
et
w
o
r
k
m
o
d
el
w
a
s
g
r
o
w
n
.
An
ev
a
lu
at
io
n
o
f
a
s
et
o
f
s
h
ap
e
f
ea
t
u
r
es [
1
0
]
.
2
.
RE
SE
ARCH
M
E
T
H
O
DO
L
O
G
Y
R
esear
ch
m
et
h
o
d
o
lo
g
y
is
a
p
r
o
ce
s
s
u
s
ed
to
g
at
h
er
in
f
o
r
m
a
ti
o
n
an
d
d
ata.
I
t
is
also
k
n
o
w
n
a
s
a
w
a
y
o
f
k
n
o
w
i
n
g
th
e
o
u
tco
m
e
o
f
a
s
p
ec
if
ic
p
r
o
b
lem
a
n
d
m
a
k
in
g
d
ec
is
io
n
s
.
R
esear
ch
er
s
co
n
s
tr
u
ct
th
eir
r
esear
ch
b
y
f
o
r
m
u
lati
n
g
an
d
d
ef
i
n
i
n
g
a
r
esear
ch
p
r
o
b
le
m
.
A
d
if
f
er
en
t
cr
iter
ia
to
d
eter
m
in
e
th
e
c
u
r
r
en
t
r
esear
ch
p
r
o
b
lem
s
in
m
eth
o
d
o
lo
g
y
b
y
r
esear
c
h
er
s
.
I
n
t
h
e
m
et
h
o
d
o
lo
g
y
,
it
ex
p
la
in
s
t
h
e
w
a
y
a
p
r
o
b
le
m
is
i
n
s
p
ec
ted
an
d
th
e
r
ea
s
o
n
f
o
r
u
s
i
n
g
a
s
p
ec
if
ic
m
et
h
o
d
an
d
tech
n
iq
u
e.
I
n
th
e
p
r
ev
io
u
s
r
esear
c
h
,
th
er
e
ar
e
m
a
n
y
t
y
p
e
s
o
f
clas
s
i
f
ic
atio
n
m
e
th
o
d
o
lo
g
ies
m
e
n
tio
n
ed
s
u
ch
a
s
A
N
N
o
r
Gab
o
r
-
W
av
elets.
T
h
i
s
s
ec
tio
n
w
ill
b
r
ief
ab
o
u
t
th
e
ch
o
s
en
m
et
h
o
d
o
lo
g
y
u
s
ed
to
d
eter
m
in
e
t
h
at
t
h
i
s
p
r
o
j
ec
t
r
u
n
s
p
er
f
ec
tl
y
.
A
p
r
o
p
er
m
eth
o
d
o
lo
g
y
p
lan
i
s
n
ec
e
s
s
ar
y
to
co
llect
t
h
e
r
eq
u
ir
ed
in
f
o
r
m
atio
n
an
d
d
ata.
Fig
u
r
e
1
s
h
o
w
s
a
clas
s
if
icat
io
n
f
r
a
m
e
w
o
r
k
f
o
r
th
i
s
r
ese
ar
ch
.
I
t
in
clu
d
ed
f
o
u
r
s
tep
s
w
h
ich
ar
e
d
ataset
ac
q
u
is
itio
n
,
p
r
e
-
p
r
o
ce
s
s
in
g
,
cl
ass
i
f
icatio
n
an
d
p
er
f
o
r
m
a
n
ce
an
al
y
s
i
s
.
Fig
u
r
e
1
.
C
lass
if
ica
tio
n
f
r
a
m
e
w
o
r
k
D
a
t
a
se
t
A
c
q
u
i
si
t
i
o
n
Pre
-
p
r
o
c
e
ssi
n
g
C
l
a
ssi
f
i
c
a
t
i
o
n
P
e
r
f
o
r
man
c
e
A
n
a
l
y
si
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l
.
1
2
,
No
.
2
,
No
v
e
m
b
er
201
8
:
5
7
0
–
5
7
6
572
Data
s
ets
ar
e
p
r
ep
ar
ed
in
f
ir
s
t
s
tep
w
h
er
e
r
esear
ch
d
ata
s
o
u
r
c
es
f
r
o
m
m
ac
h
i
n
e
lear
n
i
n
g
r
ep
o
s
ito
r
y
an
d
s
p
ec
if
ic
i
n
lea
f
d
ataset.
T
h
is
d
ataset
ca
n
b
e
d
o
w
n
lo
ad
f
r
o
m
h
ttp
://ar
ch
i
v
e.
ics.
u
ci.
ed
u
/
m
l/d
at
asets
/
L
ea
f
.
Nex
t
s
tep
is
p
r
e
-
p
r
o
ce
s
s
i
n
g
,
w
h
er
e
t
h
is
s
tep
i
s
to
e
n
s
u
r
e
th
e
q
u
a
lit
y
o
f
th
e
d
ata
r
es
u
lt
,
th
e
p
r
e
-
p
r
o
ce
s
s
in
g
d
ata
s
h
o
u
ld
b
e
i
m
p
le
m
en
ted
.
I
n
t
h
i
s
r
esear
ch
,
th
e
in
p
u
t
d
ata
is
i
n
t
h
e
ter
m
o
f
n
u
m
er
ical.
T
h
e
p
r
e
-
p
r
o
ce
s
s
in
g
tec
h
n
iq
u
e
u
s
ed
to
r
ed
u
ce
th
e
v
ar
iatio
n
o
f
h
er
b
s
d
u
e
to
illu
m
in
a
tio
n
f
ac
to
r
s
.
T
o
im
p
r
o
v
e
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
h
er
b
class
i
f
ica
tio
n
,
th
i
s
p
r
o
ce
s
s
w
ill h
e
lp
to
en
h
a
n
ce
an
d
n
o
r
m
alize
t
h
e
h
er
b
d
ataset.
B
ased
o
n
t
h
e
li
ter
atu
r
e,
f
o
u
r
class
i
f
icati
o
n
al
g
o
r
ith
m
w
h
ic
h
ar
e
A
r
ti
f
ica
l
Ne
u
r
al
Net
w
o
r
k
[
1
1
]
,
K
-
Nea
r
est
Nei
g
h
b
o
u
r
[
1
2
]
,
Dec
is
io
n
T
ab
le
an
d
M5
P
T
r
ee
alg
o
r
ith
m
s
h
av
e
b
ee
n
ch
o
s
e
n
f
o
r
th
e
ex
p
er
i
m
en
t
s
.
T
h
ese
alg
o
r
ith
m
s
ar
e
ch
o
s
e
n
b
ec
au
s
e
th
e
y
ar
e
th
e
late
s
t
al
g
o
r
ith
m
s
u
s
ed
i
n
th
e
li
ter
atu
r
e.
T
h
is
alg
o
r
ith
m
is
u
s
ed
in
s
tep
th
r
ee
.
L
ast
s
tep
is
ev
al
u
atio
n
m
e
tr
ic
o
f
th
e
h
er
b
s
d
ataset
w
h
ic
h
co
r
r
elatio
n
co
ef
f
icien
t
(
C
C
)
,
m
ea
n
ab
s
o
lu
t
e
er
r
o
r
(
MA
E
)
,
r
o
o
t
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
R
MSE
)
,
r
elativ
e
ab
s
o
lu
te
er
r
o
r
(
R
A
E
)
a
n
d
r
o
o
t
r
elativ
e
s
q
u
ar
ed
er
r
o
r
(
R
R
SE)
o
n
ea
ch
ex
p
er
i
m
en
t
w
ill
b
est
s
tated
.
Fo
r
th
is
p
u
r
p
o
s
ed
,
Mu
ltil
a
y
er
P
er
ce
p
tr
o
n
Neu
r
al
Net
w
o
r
k
(
ML
P
)
,
K
-
Nea
r
est
Nei
g
h
b
o
u
r
s
(
I
B
K)
,
Dec
is
io
n
T
ab
le
(
DT
)
an
d
M5
P
T
r
ee
alg
o
r
ith
m
s
w
il
l
b
e
co
m
p
ar
e
b
ased
o
n
th
o
s
e
m
etr
ics.
T
h
e
r
es
u
lt
s
h
o
w
n
as
f
o
llo
w
i
n
g
b
ec
au
s
e
th
e
d
atase
t
is
n
o
t
a
ca
te
g
o
r
ical
d
ataset.
I
t
i
s
a
co
n
tin
u
o
u
s
d
ataset.
T
o
d
ete
r
m
in
e
t
h
e
b
est
m
e
th
o
d
f
o
r
th
e
p
er
f
o
r
m
an
ce
f
o
r
h
er
b
s
class
i
f
icatio
n
,
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
i
s
alg
o
r
it
h
m
w
ill
b
e
r
ec
o
r
d
ed
an
d
test
e
d
.
T
h
e
tab
le
b
elo
w
s
h
o
w
s
th
e
r
esu
l
t
o
f
t
h
e
test
ed
alg
o
r
ith
m
.
T
h
e
n
e
x
t
s
ec
tio
n
w
il
l
f
o
c
u
s
o
n
th
e
p
r
o
ce
s
s
ea
c
h
s
tep
i
n
clas
s
i
f
icatio
n
f
r
a
m
e
w
o
r
k
b
ased
o
n
th
i
s
r
esear
ch
.
2
.
1
Da
t
a
s
et
A
d
ataset
i
s
a
g
r
o
u
p
o
f
d
ata
w
h
ich
i
s
co
llected
f
r
o
m
a
ce
r
tain
s
o
u
r
ce
s
u
ch
a
s
th
e
I
n
ter
n
et.
I
t
is
m
o
s
tl
y
n
o
is
y
,
i
n
co
m
p
lete
a
n
d
in
co
n
s
is
te
n
t.
Dat
aset
m
i
g
h
t
co
n
s
is
t
o
f
d
ata
f
o
r
n
o
t
j
u
s
t
o
n
e
b
u
t
m
o
r
e
m
e
m
b
er
s
eq
u
iv
ale
n
t
to
t
h
e
n
u
m
b
er
o
f
s
eq
u
en
ce
s
.
T
h
e
co
n
ce
p
t
d
ata
s
et
m
a
y
a
ls
o
b
e
u
s
ed
ar
e
m
o
r
e
r
elativ
el
y
,
to
r
ef
er
to
th
e
d
ata
in
a
co
llectio
n
o
f
clo
s
el
y
r
elate
d
tab
les,
eq
u
iv
a
len
t
to
a
p
a
r
ticu
lar
ex
p
er
i
m
e
n
ts
o
r
ev
en
t.
B
esid
es,
it
co
n
tain
s
o
n
l
y
ag
g
r
eg
ate
d
ata
o
r
o
f
ten
co
n
tai
n
s
to
o
m
u
ch
d
ata
to
an
al
y
ze
w
h
ic
h
is
lac
k
i
n
g
o
n
th
e
attr
ib
u
te
'
s
v
alu
e.
T
h
e
d
ataset
lis
ts
v
al
u
es
f
o
r
ea
ch
v
ar
iab
le,
w
h
ic
h
ca
n
b
e
a
n
u
m
b
er
s
u
ch
as
i
n
te
g
er
s
o
r
r
ea
l
n
u
m
b
er
.
T
h
is
r
esear
ch
u
s
es
th
e
L
ea
f
d
ataset,
av
ai
lab
le
f
o
r
d
o
w
n
lo
ad
f
r
o
m
h
ttp
://ar
c
h
i
v
e.
ics.u
c
i.e
d
u
/
m
l/d
ataset
s
/
L
ea
f
.
T
h
is
d
ataset
i
n
clu
d
e
s
4
0
d
if
f
e
r
en
t
p
lan
t
s
p
ec
ies
i
n
cl
u
d
in
g
h
er
b
s
an
d
th
e
d
etai
ls
o
f
s
cie
n
ti
f
ic
n
a
m
es
o
f
ea
ch
p
lan
t
as
w
ell
as
th
e
n
u
m
b
er
o
f
leaf
s
p
ec
i
m
e
n
ac
ce
s
s
i
b
le
b
y
s
p
ec
ies
ar
e
s
h
o
w
n
i
n
T
ab
le
1
.
Sp
ec
ies
n
u
m
b
er
ed
f
r
o
m
1
u
n
til
1
5
a
n
d
2
2
u
n
til
3
6
ex
h
ib
it
s
s
i
m
p
le
lea
v
es
a
n
d
s
p
ec
ies
n
u
m
b
er
ed
f
r
o
m
1
6
to
2
1
an
d
3
7
to
4
0
h
av
e
co
m
p
le
x
lea
v
es.
T
h
er
e
ar
e
a
to
tal
o
f
3
4
0
d
ata.
I
t
co
n
tain
s
1
5
n
eu
r
o
n
s
,
1
in
p
u
t
la
y
er
,
a
h
id
d
en
la
y
er
co
n
tai
n
s
o
f
2
3
n
eu
r
o
n
s
a
n
d
1
o
u
tp
u
t la
y
er
.
T
ab
le
1
.
Deta
iled
s
cien
tif
ic
n
a
m
e
o
f
ea
c
h
p
lan
t a
n
d
th
e
n
u
m
b
er
o
f
leaf
s
p
ec
i
m
e
n
ac
ce
s
s
ib
l
e
b
y
s
p
ec
ie
s
S
c
i
e
n
t
i
f
i
c
N
a
m
e
#
S
c
i
e
n
t
i
f
i
c
N
a
m
e
#
Q
u
e
r
c
u
s s
u
b
e
r
12
F
r
a
x
i
n
u
s s
p
.
10
S
a
l
i
x
a
t
r
o
c
i
n
e
r
a
10
P
r
i
mu
l
a
v
u
l
g
a
r
i
s
12
P
o
p
u
l
u
s
n
i
g
r
a
10
Er
o
d
i
u
m s
p
.
11
A
l
n
u
s s
p
.
8
B
o
u
g
a
i
n
v
i
l
l
e
a
sp
.
13
Q
u
e
r
c
u
s ro
b
u
r
12
A
r
i
saru
m v
u
l
g
a
r
e
9
C
r
a
t
a
e
g
u
s mo
n
o
g
y
n
a
8
Eu
o
n
y
mu
s
j
a
p
o
n
i
c
u
s
12
I
l
e
x
a
q
u
i
f
o
l
i
u
m
10
I
l
e
x
p
e
r
a
d
o
ssp
.
a
z
o
r
i
c
a
11
N
e
r
i
u
m o
l
e
a
n
d
e
r
11
M
a
g
n
o
l
i
a
so
u
l
a
n
g
e
a
n
a
12
B
e
t
u
l
a
p
u
b
e
sce
n
s
14
B
u
x
u
s se
mp
e
r
v
i
r
e
n
s
12
T
i
l
i
a
t
o
me
n
t
o
sa
13
U
r
t
i
c
a
d
i
o
i
c
a
12
A
c
e
r
p
a
l
mat
u
m
16
P
o
d
o
c
a
r
p
u
s s
p
.
11
C
e
l
t
i
s sp
12
A
c
c
a
se
l
l
o
w
i
a
n
a
11
C
o
r
y
l
u
s a
v
e
l
l
a
n
a
13
H
y
d
r
a
n
g
e
a
sp
.
11
C
a
st
a
n
e
a
sa
t
i
v
a
12
P
se
u
d
o
sasa
j
a
p
o
n
i
c
a
11
P
o
p
u
l
u
s
a
l
b
a
10
M
a
g
n
o
l
i
a
g
r
a
n
d
i
o
r
a
11
A
c
e
r
n
e
g
u
n
d
o
10
G
e
r
a
n
i
u
m
sp
.
10
T
a
x
u
s b
a
c
a
t
t
a
5
A
e
scu
l
u
s c
a
l
i
f
o
r
n
i
c
a
10
P
a
p
a
v
e
r
sp
.
12
C
h
e
l
i
d
o
n
i
u
m m
a
j
u
s
10
P
o
l
y
p
o
l
i
u
m v
u
l
g
a
r
e
13
S
c
h
i
n
u
s
t
e
r
e
b
i
n
t
h
i
f
o
l
i
u
s
10
P
i
n
u
s s
p
.
12
F
r
a
g
a
r
i
a
v
e
sca
11
Fig
u
r
e
2
s
h
o
w
s
th
e
v
i
s
u
aliza
ti
o
n
o
f
t
h
e
d
ata
s
et.
I
t i
s
n
o
t t
h
e
o
u
tp
u
t o
f
a
cla
s
s
i
f
icat
io
n
m
o
d
el
y
et
h
elp
s
to
v
is
u
alize
d
th
e
d
ataset
i
ts
el
f
.
I
t sh
o
w
s
a
m
a
tr
ix
o
f
t
w
o
-
d
i
m
en
s
io
n
al
s
ca
tter
p
lo
ts
o
f
e
v
er
y
t
w
o
o
f
attr
ib
u
tes.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
Da
ta
Min
in
g
A
p
p
r
o
a
ch
t
o
Herb
s
C
la
s
s
i
fica
tio
n
(
A
d
illa
h
Da
ya
n
a
A
h
ma
d
Da
li
)
573
Fig
u
r
e
2
.
Vis
u
al
izatio
n
o
f
d
ata
s
et
Fig
u
r
e
2
.
Su
m
m
ar
y
o
f
M
L
P
alg
o
r
ith
m
T
h
e
d
ataset
n
ee
d
to
b
e
in
s
er
ted
in
th
e
W
E
K
A
.
Af
ter
th
at
c
h
o
o
s
e
class
i
f
y
,
a
n
d
ch
o
o
s
e
an
a
lg
o
r
ith
m
to
u
s
e.
As
f
o
r
a
n
ex
a
m
p
le
i
n
Fi
g
u
r
e
2
,
ML
P
alg
o
r
it
h
m
h
a
s
b
ee
n
ch
o
s
e
n
a
n
d
th
e
s
u
m
m
ar
y
o
f
t
h
e
r
es
u
lt
h
as
b
ee
n
s
tated
.
2
.
2
P
re
-
pro
ce
s
s
ing
T
o
en
s
u
r
e
th
e
q
u
ali
t
y
o
f
th
e
d
ata
r
esu
lt,
t
h
e
p
r
e
-
p
r
o
ce
s
s
i
n
g
d
ata
s
h
o
u
ld
b
e
i
m
p
le
m
en
t
ed
.
I
n
th
i
s
r
esear
ch
First,
s
elec
t
s
u
b
s
et
o
f
av
ai
lab
le
d
ata.
T
h
en
,
p
r
e
-
p
r
o
ce
s
s
d
ata
w
h
ic
h
o
r
g
a
n
ize
th
e
s
elec
ted
d
ata.
L
ast
b
u
t n
o
t le
ast,
tr
a
n
s
f
o
r
m
t
h
e
d
ata
th
at
r
ea
d
y
f
o
r
m
ac
h
i
n
e
lear
n
i
n
g
.
2
.
3
Cla
s
s
if
ica
t
io
n Alg
o
rit
h
m
P
r
ed
ictin
g
a
n
e
w
d
ata
h
ap
p
en
s
b
y
tr
ee
m
o
d
elli
n
g
o
f
d
ata
w
h
ic
h
is
t
h
e
u
s
e
o
f
cla
s
s
i
f
ica
tio
n
[
2
]
.
I
n
W
E
KA
,
t
h
e
al
g
o
r
ith
m
s
ch
o
s
e
n
i
n
clu
d
e
t
h
e
B
a
y
esia
n
cla
s
s
i
f
ier
s
,
tr
ee
s
,
r
u
le
s
,
f
u
n
ctio
n
s
,
la
z
y
clas
s
i
f
ier
s
,
a
n
d
a
f
i
n
al
m
i
s
ce
llan
eo
u
s
ca
teg
o
r
y
.
On
l
y
ce
r
tai
n
al
g
o
r
ith
m
s
i
n
W
E
KA
ar
e
ca
p
ab
le
to
p
er
f
o
r
m
r
eg
r
ess
io
n
o
r
s
u
p
p
o
r
t
p
r
ed
ictin
g
co
n
ti
n
u
o
u
s
v
ar
iab
l
e.
T
h
e
f
o
llo
w
in
g
a
lg
o
r
it
h
m
s
ar
e
u
s
ed
b
ec
au
s
e
t
h
e
d
ata
s
et
co
n
tain
s
co
n
tin
u
o
u
s
class
v
ar
iab
le.
I
n
th
i
s
r
esear
ch
s
tu
d
y
,
w
e
d
escr
ib
e
s
u
c
h
an
ap
p
r
o
ac
h
.
a)
A
r
ti
f
icial
Neu
r
al
Net
w
o
r
k
:
I
t
co
u
ld
b
e
co
m
p
o
s
ed
as
m
ath
e
m
atica
l
eq
u
a
tio
n
s
in
a
r
atio
n
a
ll
y
n
atu
r
al
w
a
y
.
Mu
ltil
a
y
er
P
er
ce
p
tr
o
n
is
a
n
eu
r
al
n
et
w
o
r
k
th
at
tr
ai
n
s
th
a
t
ap
p
ly
b
ac
k
-
p
r
o
p
ag
atio
n
.
B
esid
es,
it
is
a
p
r
ec
is
e
p
r
ed
icto
r
f
o
r
th
e
u
n
d
er
l
y
i
n
g
cl
ass
i
f
icatio
n
d
if
f
ic
u
lt
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l
.
1
2
,
No
.
2
,
No
v
e
m
b
er
201
8
:
5
7
0
–
5
7
6
574
b)
K
-
Nea
r
est
Neig
h
b
o
r
:
T
h
e
tr
ain
in
g
i
n
s
tan
ce
s
is
s
to
r
ed
b
y
th
e
laz
y
lear
n
er
s
.
I
t
o
n
l
y
d
o
r
ea
l
w
o
r
k
w
h
e
n
t
h
e
class
i
f
icatio
n
ti
m
e
co
m
e.
I
B
K
class
i
f
ier
s
t
h
at
b
ein
g
u
s
ed
is
th
e
I
B
K
w
h
ich
ap
p
l
y
t
h
e
id
en
tical
d
is
ta
n
ce
m
etr
ic.
T
h
e
n
u
m
b
er
o
f
n
ea
r
es
t
n
ei
g
h
b
o
r
s
(
d
ef
au
lt
k
=1
)
co
u
l
d
also
b
e
d
escr
ib
ed
p
ar
ticu
lar
l
y
o
r
m
ig
h
t
a
s
w
ell
d
eter
m
in
ed
a
u
to
m
at
icall
y
u
tili
zi
n
g
leav
e
-
o
n
e
-
o
u
t
cr
o
s
s
v
alid
atio
n
,
s
u
b
j
ec
t
to
an
u
p
p
er
li
m
it
g
i
v
en
b
y
th
e
p
ar
ticu
lar
v
a
lu
e.
c)
Dec
is
io
n
T
ab
le:
E
x
p
lain
i
n
g
th
e
o
u
tco
m
e
h
a
s
an
ea
s
y
w
a
y
wh
ich
is
to
m
a
k
e
it
t
h
e
eq
u
i
v
al
en
t
as
i
n
p
u
t
i
n
m
ac
h
in
e
lear
n
i
n
g
.
I
t c
r
ea
tes a
d
ec
is
io
n
tab
le
m
aj
o
r
it
y
clas
s
if
i
er
s
.
d)
M5
P
:
I
t
is
a
m
o
d
el
tr
ee
lear
n
e
r
th
at
ca
p
ab
le
to
b
u
i
ld
lo
g
i
s
tic
m
o
d
el
tr
ee
s
.
M5
P
u
n
ite
a
co
m
m
o
n
d
ec
is
io
n
tr
ee
alo
n
g
t
h
e
p
r
o
b
ab
il
it
y
o
f
li
n
ea
r
r
eg
r
ess
io
n
f
u
n
ctio
n
s
at
t
h
e
n
o
d
es.
I
n
ev
er
y
lea
f
o
f
r
eg
r
ess
io
n
m
o
d
el,
th
e
M5
P
r
eg
r
ess
io
n
m
o
d
el
ar
e
co
m
p
ete
n
t
w
it
h
a
li
n
ea
r
r
eg
r
es
s
io
n
m
o
d
el.
2
.
4
E
v
a
lua
t
io
n
M
e
t
ric
B
ec
au
s
e
o
f
t
h
e
n
u
m
er
ical
n
at
u
r
e
o
f
t
h
e
d
ataset,
t
h
e
p
r
i
m
ar
y
q
u
ali
t
y
m
ea
s
u
r
e
p
r
o
p
o
s
ed
b
y
t
h
e
er
r
o
r
r
ate
is
n
o
lo
n
g
er
s
u
itab
le.
E
r
r
o
r
s
ar
e
n
o
t
ea
s
il
y
p
r
esen
t
o
r
ab
s
en
t;
t
h
e
y
co
m
e
i
n
v
ar
ie
t
y
s
izes
.
T
o
f
ig
u
r
e
o
u
t
t
h
e
o
u
tco
m
e
o
f
n
u
m
er
ical
p
r
ed
ictio
n
,
a
f
e
w
o
f
alter
n
at
iv
e
m
eth
o
d
s
ca
n
b
e
ap
p
lied
.
T
h
e
eq
u
atio
n
o
f
th
e
ev
alu
a
tio
n
i
s
s
h
o
w
n
i
n
th
e
f
o
ll
o
w
i
n
g
w
h
er
e:
n
=
th
e
n
u
m
b
er
o
f
er
r
o
r
p
=
p
r
e
d
icted
v
alu
es
a
=
th
e
ac
tu
al
v
a
lu
e
s
a)
C
o
r
r
elatio
n
co
ef
f
icie
n
t
(
C
C
)
m
ea
s
u
r
e
h
o
w
s
tr
o
n
g
a
r
ela
tio
n
s
h
ip
is
b
et
w
ee
n
t
w
o
d
at
a.
C
o
r
r
elatio
n
co
ef
f
icie
n
t c
alc
u
lated
u
s
i
n
g
t
h
e
f
o
llo
w
in
g
eq
u
atio
n
:
√
w
h
er
e:
=
∑
̅
̅
,
∑
̅
an
d
=
∑
̅
T
h
e
eq
u
atio
n
r
et
u
r
n
v
a
lu
e
b
et
w
ee
n
-
1
a
n
d
1
.
T
h
e
v
al
u
e
1
i
s
co
n
s
id
er
ed
as
s
tr
o
n
g
p
o
s
iti
v
e
r
elatio
n
s
h
ip
m
ea
n
w
h
ile
v
al
u
e
-
1
is
s
tr
o
n
g
l
y
n
eg
a
tiv
e
a
n
d
th
e
v
alu
e
0
h
as
n
o
r
elatio
n
s
h
ip
.
I
f
th
e
r
esu
lt
s
h
o
w
s
a
g
r
ea
ter
n
u
m
b
er
th
a
n
v
alu
e
1
an
d
less
t
h
a
n
-
1
,
a
m
i
s
ta
k
e
h
a
s
b
ee
n
m
ad
e.
b)
Me
an
ab
s
o
lu
te
er
r
o
r
(
MA
E
)
is
an
a
v
er
ag
e
t
h
e
m
ag
n
it
u
d
e
o
f
t
h
e
i
n
d
iv
id
u
al
er
r
o
r
s
w
ith
o
u
t
ta
k
in
g
ac
co
u
n
t
o
f
th
eir
s
i
g
n
.
T
h
e
eq
u
atio
n
f
o
r
th
e
M
A
E
is
a
s
th
e
f
o
llo
w
in
g
:
|
|
|
|
c)
R
o
o
t
Me
an
Sq
u
ar
ed
E
r
r
o
r
(
R
MSE
)
m
ea
s
u
r
es
t
h
e
d
if
f
er
en
c
es
b
et
w
ee
n
v
a
lu
e
s
.
I
t
is
a
s
ta
n
d
ar
d
d
ev
iatio
n
o
f
t
h
e
r
esid
u
als
(
p
r
ed
ictio
n
er
r
o
r
s
)
.
T
h
e
r
esid
u
al
s
ar
e
a
m
ea
s
u
r
e
o
f
h
o
w
f
ar
t
h
e
r
e
g
r
ess
io
n
l
in
e
d
ata/a
ttrib
u
te
p
o
in
ts
ar
e.
R
M
S
E
is
ca
lcu
lated
u
s
i
n
g
t
h
e
eq
u
at
io
n
as st
ated
i
n
th
e
f
o
llo
w
i
n
g
:
√
d)
R
elati
v
e
A
b
s
o
l
u
te
E
r
r
o
r
(
R
AE
)
is
r
elati
v
e
to
a
s
i
m
p
le
p
r
ed
icto
r
,
th
e
av
er
a
g
e
o
f
t
h
e
ac
t
u
al
v
al
u
e.
T
h
e
er
r
o
r
is
j
u
s
t
th
e
to
tal
ab
s
o
l
u
te
er
r
o
r
in
s
tead
o
f
t
h
e
to
tal
s
q
u
ar
ed
er
r
o
r
.
R
A
E
ta
k
es
th
e
to
tal
ab
s
o
lu
te
er
r
o
r
an
d
n
o
r
m
a
lize
it
b
y
d
iv
id
i
n
g
b
y
t
h
e
to
tal
ab
s
o
l
u
te
er
r
o
r
o
f
th
e
s
i
m
p
le
p
r
ed
icto
r
.
I
t
is
ca
lcu
l
ated
u
s
i
n
g
t
h
e
f
o
llo
w
in
g
eq
u
at
io
n
:
|
|
|
|
|
|
|
|
e)
R
o
o
t
R
elati
v
e
Sq
u
ar
ed
E
r
r
o
r
(
R
R
SE)
is
a
r
elativ
e
to
w
h
at
it
w
o
u
ld
h
av
e
b
ee
n
i
f
a
s
i
m
p
le
p
r
ed
icto
r
h
a
d
b
ee
n
u
s
ed
.
T
h
e
p
r
ed
icto
r
is
th
e
av
er
ag
e
o
f
t
h
e
ac
tu
a
l v
al
u
es.
T
h
e
eq
u
atio
n
u
s
e
i
s
as
f
o
llo
w
s
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
Da
ta
Min
in
g
A
p
p
r
o
a
ch
t
o
Herb
s
C
la
s
s
i
fica
tio
n
(
A
d
illa
h
Da
ya
n
a
A
h
ma
d
Da
li
)
575
√
3
.
RE
SUL
T
S AN
D
D
I
SCU
SS
I
O
NS
T
h
e
r
esu
lt
o
b
tain
s
is
s
tated
i
n
C
C
,
M
A
E
,
R
MSE
,
R
AE
an
d
R
R
SE.
I
t
d
o
es
n
o
t
ca
lcu
late
th
e
ac
cu
r
ac
y
b
ec
au
s
e
d
ataset
v
al
u
es
is
i
n
co
n
tin
u
o
u
s
n
u
m
b
er
in
s
tead
o
f
ca
teg
o
r
ical
o
r
n
o
m
i
n
al
v
al
u
e
s
.
T
ab
le
2
s
h
o
w
s
t
h
e
co
m
p
ar
is
o
n
r
es
u
lt o
f
t
h
e
s
elec
t
ed
alg
o
r
ith
m
s
w
h
ile
Fi
g
u
r
e
3
illu
s
tr
ates t
h
e
p
er
f
o
r
m
an
ce
.
T
ab
le
2
.
C
o
m
p
ar
is
o
n
r
es
u
lt o
f
s
elec
ted
alg
o
r
ith
m
s
A
l
g
o
r
i
t
h
m
CC
M
A
E
R
M
S
E
RAE
R
R
S
E
T
i
m
e
(
S
e
c
o
n
d
s)
M
L
P
0
.
5
9
7
.
2
5
9
.
7
5
7
0
.
2
3
8
7
.
1
5
2
.
3
7
I
B
K
0
.
6
1
5
.
0
6
9
.
9
0
4
9
.
0
0
8
8
.
4
3
0
.
0
1
DT
0
.
4
3
8
.
1
3
1
0
.
1
8
7
8
.
8
9
1
.
0
2
0
.
4
2
M5P
0
.
5
3
7
.
9
7
9
.
5
0
7
7
.
3
2
8
4
.
9
7
0
.
8
2
Fig
u
r
e
3
.
C
o
m
p
ar
ativ
e
r
es
u
lt
s
ac
r
o
s
s
all
class
i
f
icat
io
n
al
g
o
r
ith
m
s
As
s
tated
i
n
th
e
tab
le
ab
o
v
e,
I
B
K
g
av
e
t
h
e
b
est
r
esu
lt
a
m
o
n
g
s
t
t
h
o
s
e
al
g
o
r
ith
m
s
t
h
at
w
er
e
test
ed
.
Fo
r
th
e
C
C
,
I
B
K
h
as
th
e
r
esu
lt
o
f
0
.
6
1
co
m
p
ar
ed
to
ML
P
,
D
T
a
n
d
M5
P
w
h
ich
ar
e
0
.
5
9
,
0
.
4
3
an
d
0
.
5
3
.
A
s
f
o
r
th
e
ti
m
e
ta
k
en
f
o
r
ea
ch
alg
o
r
it
h
m
s
to
p
r
o
d
u
ce
r
esu
lts
,
t
h
e
K
NN
o
n
l
y
to
o
k
0
.
0
1
s
ec
o
n
d
to
p
r
o
d
u
ce
.
A
s
f
o
r
th
e
o
th
er
alg
o
r
it
h
m
s
,
DT
to
o
k
0
.
4
2
s
ec
o
n
d
s
a
n
d
M5
P
to
o
k
0
.
8
2
s
ec
o
n
d
s
m
ea
n
w
h
i
le
t
h
e
lo
n
g
e
s
t
t
i
m
e
ta
k
en
f
o
r
alg
o
r
ith
m
s
to
p
r
o
d
u
ce
s
r
esu
lts
is
2
.
3
7
w
h
ic
h
is
M
L
P
.
4
.
CO
NCLUS
I
O
N
T
h
is
r
esear
ch
h
as
ac
co
m
p
li
s
h
ed
th
e
m
ai
n
o
b
j
ec
tiv
e
o
f
ev
alu
ati
n
g
cr
u
cial
f
ea
tu
r
e
s
f
o
r
h
er
b
s
class
i
f
icatio
n
.
I
t
r
ec
o
g
n
izes
t
h
e
m
o
s
t
ap
p
licab
le
al
g
o
r
ith
m
s
f
o
r
th
e
ac
h
ie
v
e
m
en
t
o
f
h
er
b
s
clas
s
i
f
icatio
n
.
A
ll
th
o
s
e
al
g
o
r
ith
m
s
w
er
e
r
u
n
an
d
test
ed
i
n
W
E
K
A
to
o
ls
.
T
h
e
co
m
p
ar
is
o
n
o
f
all
a
lg
o
r
it
h
m
s
h
as
b
ee
n
m
ad
e
an
d
s
tated
in
o
r
d
er
to
f
in
d
w
h
ic
h
alg
o
r
ith
m
s
g
iv
e
s
th
e
m
o
s
t
ex
ce
lle
n
t
r
esu
l
t
f
o
r
th
e
h
er
b
s
.
T
h
is
class
i
f
icatio
n
alg
o
r
ith
m
is
v
er
y
ea
s
y
to
i
m
p
l
e
m
en
t in
t
h
e
clas
s
i
f
icatio
n
to
o
l
s
u
c
h
as W
E
K
A
.
B
esid
es,
it is
a
f
lex
i
b
le
f
ea
t
u
r
e.
ACK
NO
WL
E
D
G
E
M
E
NT
W
e
w
o
u
ld
li
k
e
to
s
a
y
t
h
a
n
k
y
o
u
to
Un
i
v
er
s
iti
T
u
n
H
u
s
s
ei
n
On
n
Ma
la
y
s
ia
(
UT
HM
)
an
d
Of
f
ice
f
o
r
R
esear
ch
,
I
n
n
o
v
a
tio
n
,
C
o
m
m
er
cializa
tio
n
an
d
C
o
n
s
u
lta
n
c
y
Ma
n
ag
e
m
e
n
t
(
OR
I
C
C
)
,
UT
HM
f
o
r
k
in
d
l
y
p
r
o
v
in
g
u
s
w
i
th
t
h
e
i
n
ter
n
al
f
u
n
d
in
g
(
Vo
t E
1
5
5
0
1
)
.
RE
F
E
R
E
NC
E
S
[1
]
Bro
w
n
,
D.
T
h
e
Ro
y
a
l
Ho
rti
c
u
lt
u
ra
l
S
o
c
iety
–
En
c
y
c
lo
p
e
d
ia
o
f
He
rb
s
a
n
d
T
h
e
ir
Us
e
s
.
Do
rli
n
g
Kin
d
e
rsle
y
,
L
o
n
d
o
n
.
1
9
9
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l
.
1
2
,
No
.
2
,
No
v
e
m
b
er
201
8
:
5
7
0
–
5
7
6
576
[2
]
Bh
a
rg
a
v
a
,
G
.
S
h
a
r
m
a
,
R.
Bh
a
rg
a
v
a
,
M
.
M
a
th
u
ria,
“
De
c
isio
n
T
re
e
An
a
lys
is
o
n
J
4
8
Al
g
o
rit
h
m
fo
r
Da
ta
M
in
in
g
,
”
In
tern
a
ti
o
n
a
l
Jo
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
Re
se
a
rc
h
in
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
S
o
f
tw
a
r
e
En
g
in
e
e
rin
g
,
v
o
l
3
,
n
o
6
,
p
p
.
1
1
1
4
-
1
1
1
9
.
2
0
1
3
.
[3
]
A
lsa
b
ti
,
S
.
Ra
n
k
a
,
V
.
S
in
g
h
,
“
CL
OU
DS
:
Cla
ss
if
ica
ti
o
n
f
o
r
L
a
rg
e
Ou
t
-
of
-
C
o
re
Da
ta
se
ts
”
,
P
r
o
c
.
In
t'
l
Co
n
f
.
Kn
o
w
led
g
e
Disc
o
v
e
r
y
a
n
d
Da
ta
M
in
i
n
g
,
p
p
.
2
-
8
,
1
9
9
8
.
[4
]
G
e
h
rk
e
,
V
.
G
a
n
ti
,
R.
Ra
m
a
k
ris
h
n
a
n
,
W
.
-
Y.
L
o
h
,
“
BOAT
-
O
p
ti
mistic
De
c
isio
n
T
re
e
Co
n
str
u
c
ti
o
n
”
,
P
r
o
c
.
A
CM
S
IG
M
OD
In
t'
l
Co
n
f
.
M
a
n
a
g
e
m
e
n
t
o
f
Da
ta,
p
p
.
1
6
9
-
1
8
0
,
1
9
9
9
.
[5
]
G
e
h
rk
e
,
R.
Ra
m
a
k
rish
n
a
n
,
V
.
Ga
n
ti
,
“
Ra
in
F
o
re
st
A
Fra
me
wo
rk
fo
r
F
a
st
De
c
i
sio
n
T
re
e
Co
n
stru
c
ti
o
n
o
f
L
a
rg
e
Da
ta
se
ts
”
,
Da
ta M
in
i
n
g
a
n
d
Kn
o
w
led
g
e
Disc
o
v
e
r
y
,
p
p
.
1
2
7
-
1
6
2
,
J
u
ly
2
0
0
0
.
[6
]
M
e
h
ta,
R.
A
g
ra
w
a
l,
J.
Riss
a
n
e
n
,
“
S
L
IQ:
A
Fa
st
S
c
a
l
a
b
le
Cl
a
ss
if
ier
fo
r
Da
ta
M
in
in
g
”
,
P
ro
c
.
1
9
9
6
In
tern
a
ti
o
n
a
l
Co
n
f
.
Ex
ten
d
i
n
g
Da
tab
a
se
T
e
c
h
n
o
lo
g
y
,
p
p
.
1
8
-
3
2
,
1
9
9
6
.
[7
]
Jo
sh
i,
G
.
Ka
r
y
p
is,
V
.
Ku
m
a
r,
“
S
c
a
lP
a
rC:
A
Ne
w
S
c
a
l
a
b
le
a
n
d
Ef
fi
c
ien
t
P
a
ra
ll
e
l
C
la
ss
if
ica
ti
o
n
Al
g
o
ri
th
m
f
o
r
M
in
in
g
L
a
rg
e
Da
t
a
se
ts
”
,
P
ro
c
.
1
9
9
8
In
t'
l
P
a
ra
ll
e
l
P
r
o
c
e
ss
in
g
S
y
m
p
.
a
n
d
S
y
m
p
.
P
a
ra
ll
e
l
a
n
d
Distri
b
u
t
e
d
P
r
o
c
e
ss
in
g
,
p
p
.
5
7
3
-
5
7
9
,
1
9
9
8
.
[8
]
S
riv
a
sta
v
a
,
E.
-
H.(S
a
m
)
Ha
n
,
V
.
Ku
m
a
r,
V
.
S
in
g
h
,
“
Pa
ra
ll
e
l
Fo
rm
u
la
ti
o
n
s
o
f
De
c
isio
n
-
T
re
e
Cla
ss
if
ica
ti
o
n
Al
g
o
rit
h
ms
”
,
Da
ta M
in
in
g
a
n
d
Kn
o
w
led
g
e
Disc
o
v
e
r
y
,
v
o
l.
3
,
n
o
.
3
,
p
p
.
2
3
7
-
2
6
1
,
S
e
p
t.
1
9
9
9
.
[9
]
L
i
m
,
W
.
Y.
L
o
h
,
Y.S
.
S
h
i
h
,
“
A
C
o
mp
a
ris
o
n
o
f
Pre
d
ictio
n
Acc
u
r
a
c
y
Co
mp
lex
it
y
a
n
d
T
ra
i
n
i
n
g
T
ime
o
f
T
h
irty
-
T
re
e
Old
a
n
d
Ne
w
C
la
ss
if
ica
t
io
n
Al
g
o
r
it
h
ms
”
,
M
a
c
h
i
n
e
L
e
a
rn
in
g
,
v
o
l.
4
0
,
n
o
.
3
,
p
p
.
2
0
3
-
2
2
8
,
S
e
p
t.
2
0
0
0
.
[1
0
]
S
il
v
a
,
A
.
R.
M
a
rc
a
l,
R.
M
.
A
.
d
a
S
il
v
a
,
“
Eva
lu
a
ti
o
n
o
f
fea
t
u
re
e
s
fo
r
lea
f
d
isc
rimin
a
t
io
n
,
”
I
n
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
on
Im
a
g
e
A
n
a
l
y
sis a
n
d
Re
c
o
g
n
it
io
n
[1
1
]
A
.
Ya
sa
r,
I.
S
a
rit
a
s,
M
.
A
.
S
a
h
m
a
n
,
A
.
O.
Du
n
d
a
r,
“
Cla
ss
if
ic
a
ti
o
n
o
f
L
e
a
f
T
y
p
e
Us
in
g
Arti
fi
c
ia
l
Ne
u
ra
l
Ne
two
rk
,
”
In
tern
a
ti
o
n
a
l
Jo
u
rn
a
l
o
f
In
telli
g
e
n
t
S
y
ste
m
s an
d
A
p
p
li
c
a
ti
o
n
s
in
En
g
in
e
e
rin
g
,
2
0
1
5
.
[1
2
]
D.
S
.
G
u
ru
,
Y.
H.
S
h
a
ra
th
,
S
.
M
a
n
ju
n
a
t
h
,
“
T
e
x
tu
re
Fea
tu
re
s
a
n
d
KNN
in
Cla
ss
if
ica
ti
o
n
o
f
Fl
o
we
r
Ima
g
e
s
,
”
IJCA
S
p
e
c
ial
Iss
u
e
s o
n
“
Re
c
e
n
t
T
re
n
d
s in
Im
a
g
e
P
ro
c
e
ss
in
g
a
n
d
P
a
tt
e
rn
Re
c
o
g
n
it
io
n
,
2
0
1
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.