I
AE
S
I
nte
rna
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
7
,
No
.
3
,
Sep
tem
b
er
201
8
,
p
p
.
111
~
118
I
SS
N:
2252
-
8938
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ai.
v
7
.
i3
.
p
p
1
11
-
1
18
111
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
/
I
JA
I
Cha
lleng
in
g
İss
ues
i
n Au
to
m
a
t
ed
O
il P
a
l
m
F
ruit
G
ra
ding
G
a
ura
ng
S P
a
t
k
a
r
1
,
Anj
a
ney
ulu
G
.
S.G
.
N
2
,
C
ha
nd
ra
M
o
u
li P
.
V.
S.S.R
3
1,
3
S
c
h
o
o
l
o
f
Co
m
p
u
ter S
c
ien
c
e
a
n
d
En
g
i
n
e
rin
g
,
V
IT
Un
iv
e
rsity
,
V
e
ll
o
re
,
I
n
d
ia
2
S
c
h
o
o
l
o
f
A
d
v
a
n
c
e
d
S
c
in
e
c
e
,
V
I
T
Un
iv
e
rsit
y
,
V
e
ll
o
re
,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
r
2
0
,
2
0
1
8
R
ev
i
s
ed
M
a
y
8
,
2
0
1
8
A
cc
ep
ted
Ma
y
19
,
2
0
1
8
L
a
te
a
d
v
a
n
c
e
m
e
n
t
in
A
g
ricu
lt
u
re
se
g
m
e
n
t
u
ti
li
z
in
g
I
m
a
g
e
p
re
p
a
rin
g
a
n
d
f
u
z
z
y
lo
g
ic
m
e
th
o
d
s
h
a
s
e
m
p
o
w
e
re
d
ra
n
c
h
e
rs
to
e
x
p
a
n
d
t
h
e
y
ield
o
f
h
a
rv
e
st
a
n
d
se
rv
e
d
t
h
e
n
o
u
ris
h
m
e
n
t
n
e
e
d
s
o
f
th
e
w
h
o
le
p
e
o
p
le.
L
o
o
k
in
t
o
i
n
h
o
rti
c
u
lt
u
re
is
p
o
in
te
d
to
w
a
rd
s
in
c
re
m
e
n
t
in
th
e
p
r
o
f
it
a
b
il
it
y
,
q
u
a
li
ty
a
n
d
les
se
n
in
g
th
e
li
k
e
li
h
o
o
d
o
f
b
lu
n
d
e
r
p
re
se
n
ted
b
y
p
e
o
p
le.
T
h
e
b
ig
g
e
s
t
o
il
p
a
lm
c
re
a
ti
o
n
is
in
M
a
la
y
sia
a
n
d
In
d
o
n
e
sia
a
n
d
th
e
y
s
e
n
d
o
u
t
p
a
lm
o
il
to
d
if
f
e
r
e
n
t
n
a
ti
o
n
s
o
n
t
h
e
p
lan
e
t
.
T
h
e
m
o
st
o
u
trag
e
o
u
s
e
n
th
u
sia
sm
f
o
r
p
a
lm
o
il
is
in
In
d
ia.
T
h
is
c
a
m
e
to
f
ru
it
io
n
In
d
ia
in
to
P
a
lm
Oil
a
d
v
a
n
c
e
m
e
n
t
a
n
d
e
ra
in
v
a
rio
u
s
sta
tes
.
W
it
h
a
sp
e
c
i
f
ic
e
n
d
g
o
a
l
to
e
x
p
a
n
d
t
h
e
e
ff
icie
n
c
y
o
f
p
a
l
m
o
il
o
rg
a
n
ic
p
r
o
d
u
c
ts,
p
a
lm
o
il
in
d
u
st
ry
a
n
d
in
a
d
d
it
i
o
n
a
n
a
ly
sts
u
ti
li
z
e
s
d
if
f
e
r
e
n
t
m
a
c
h
in
e
-
v
isio
n
sy
ste
m
s
to
re
v
iew
th
e
n
a
tu
ra
l
p
ro
d
u
c
ts.
T
ra
g
i
c
a
ll
y
,
th
e
in
f
o
rm
a
ti
o
n
c
a
u
g
h
t
a
n
d
p
re
p
a
re
d
is
c
o
n
f
ro
n
ted
w
it
h
re
stricte
d
lea
rn
in
g
a
n
d
a
c
c
u
ra
c
y
.
T
h
e
re
a
re
a
f
e
w
d
iff
icu
lt
ies
re
q
u
ired
w
it
h
th
e
o
u
t
li
n
e
a
n
d
u
sa
g
e
o
f
p
a
lm
o
il
o
rg
a
n
ic
p
ro
d
u
c
t
re
v
iew
in
g
.
T
h
is
p
a
p
e
r
in
tr
o
d
u
c
e
s
a
n
o
u
tl
in
e
o
f
d
if
fe
re
n
t
I
m
a
g
e
h
a
n
d
li
n
g
a
n
d
f
u
z
z
y
lo
g
ic
m
e
th
o
d
s,
d
isti
n
g
u
ish
e
s
a
n
d
a
d
d
re
ss
e
s tes
ti
n
g
issu
e
s in
c
o
m
p
u
teriz
e
d
p
a
lm
n
a
tu
ra
l
p
r
o
d
u
c
t
e
v
a
lu
a
ti
n
g
.
K
ey
w
o
r
d
:
E
laeis g
u
i
n
ee
n
s
is
Fre
s
h
f
r
u
i
t b
u
n
c
h
es
Fu
zz
y
l
o
g
ic
Me
s
o
ca
r
p
Neu
r
al
n
et
w
o
r
k
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
:
Gau
r
an
g
S P
atk
ar
,
Sch
o
o
l o
f
C
o
m
p
u
ter
Scie
n
ce
a
n
d
E
n
g
in
ee
r
i
n
g
,
VI
T
Un
iv
er
s
it
y
,
Ve
llo
r
e,
T
am
il
Nad
u
,
I
n
d
ia
E
m
ail:
g
au
r
a
n
g
p
at
k
ar
8
3
@
g
m
a
il.c
o
m
1.
I
NT
RO
D
UCT
I
O
N
P
r
o
g
r
ess
ed
g
et
r
ea
d
y
o
f
p
al
m
o
il
n
at
u
r
al
p
r
o
d
u
ct
b
u
n
ch
e
s
i
n
to
ag
r
ee
ab
le
o
il
u
s
i
n
g
d
is
ti
n
cti
v
e
I
m
a
g
e
P
r
o
ce
s
s
in
g
s
tr
ateg
ie
s
is
s
h
ar
p
en
ed
in
a
co
u
p
le
en
d
ea
v
o
r
s
.
T
h
e
o
r
d
in
ar
y
m
et
h
o
d
o
lo
g
ies
ar
e
s
i
m
ilar
l
y
o
p
en
,
litt
le
s
ca
le
m
ec
h
a
n
ical
u
n
it
s
,
m
ed
iu
m
an
d
en
d
le
s
s
s
ca
le
p
al
m
o
il
i
n
d
u
s
tr
ial
f
ac
i
liti
es.
I
t
is
ag
r
ee
d
th
at
o
r
d
in
ar
y
s
y
s
te
m
s
f
o
r
is
o
lati
n
g
p
al
m
o
il
w
er
e
g
r
i
m
an
d
in
e
f
f
icie
n
t
f
o
r
m
ak
in
g
o
il
ac
ce
s
s
ib
le
to
b
e
o
b
tain
ed
.
Hen
ce
f
o
r
th
p
r
esen
t
e
n
th
u
s
ias
m
f
o
r
litt
le
s
ca
le
p
al
m
o
il
p
la
n
t
s
is
m
o
v
in
g
f
r
o
m
c
lear
s
ta
y
s
in
g
u
l
ar
u
n
it
o
p
er
atio
n
al
m
ac
h
in
e
s
to
a
m
o
r
e
j
o
in
ed
an
d
co
m
p
lex
P
C
co
m
p
o
s
ed
s
y
s
t
e
m
w
h
ic
h
is
d
e
f
i
n
itel
y
n
o
t
h
ar
d
to
w
o
r
k
a
n
d
k
ee
p
u
p
.
T
h
is
ass
is
ta
n
ts
in
ad
d
itio
n
in
e
f
f
ec
ti
v
e
n
ess
an
d
d
ec
r
ea
s
es
t
h
e
h
u
m
a
n
ef
f
o
r
t
w
h
ich
m
a
y
ac
h
ie
v
e
p
r
esen
tatio
n
o
f
s
cr
e
w
u
p
.
T
h
is
p
ap
er
s
r
ev
ei
w
s
th
e
ex
a
m
i
n
ati
o
n
d
is
co
v
er
ie
s
o
f
d
if
f
er
en
t
cr
ea
to
r
s
an
d
f
in
d
s
t
h
e
test
i
n
g
i
s
s
u
es
w
h
ic
h
ar
e
m
is
s
e
d
b
y
s
p
ec
iali
s
ts
i
n
m
ec
h
a
n
ized
p
alm
n
at
u
r
al
p
r
o
d
u
ct
ev
alu
a
ti
n
g
.
I
n
d
ia
h
a
s
b
ee
n
r
ep
r
esen
ted
to
h
av
e
t
h
e
g
r
ea
test
r
eg
io
n
u
n
d
er
o
il
s
ee
d
i
m
p
r
o
v
e
m
e
n
t
i
n
t
h
e
W
o
r
ld
y
et
th
e
d
is
j
o
in
ted
n
es
s
is
th
at
t
h
e
p
r
iv
ate
cr
ea
tio
n
is
n
o
t
ad
eq
u
ate
to
m
ee
t
th
e
ir
r
elev
a
n
t
ag
r
ee
ab
le
o
il
n
ec
ess
itie
s
o
f
th
e
g
e
n
er
al
p
o
p
u
latio
n
.
T
h
e
f
ac
to
r
s
r
esp
o
n
s
ib
le
f
o
r
th
is
co
n
s
o
lid
ate
p
o
o
r
lan
d
co
n
d
itio
n
s
an
d
th
e
cr
ea
tin
g
p
o
p
u
latio
n
.
T
h
e
en
th
u
s
ias
m
f
o
r
p
alm
o
il
h
a
s
b
ee
n
cr
ea
ti
n
g
.
T
h
er
e
h
a
s
in
lik
e
m
a
n
n
er
b
ee
n
d
is
ce
r
n
ib
le
u
p
w
ar
d
ex
a
m
p
le
i
n
t
h
e
p
er
ca
p
ital
u
s
e
o
f
co
n
s
u
m
ab
le
o
il
a
m
o
n
g
th
e
I
n
d
ian
p
o
p
u
latio
n
.
A
lio
n
'
s
s
h
ar
e
o
f
t
h
e
I
n
d
ia
n
p
eo
p
le
en
co
u
n
ter
s
ca
lo
r
ie
d
ef
i
cien
c
y
.
I
n
f
er
ab
le
f
r
o
m
t
h
e
co
s
t
o
f
ed
ib
le
o
il,
its
u
s
ag
e
is
m
a
in
tai
n
ed
a
s
tr
ateg
ic
d
is
tan
ce
f
r
o
m
t
h
e
o
r
d
in
ar
y
m
en
u
o
f
t
h
e
f
is
ca
ll
y
b
lo
ck
e
d
an
d
tr
ied
p
o
p
u
lace
.
I
n
d
ia
h
as
b
ee
n
ac
q
u
ir
in
g
b
o
u
n
d
less
m
ea
s
u
r
es
o
f
o
ils
f
r
o
m
late
n
i
n
etee
n
th
ce
n
tu
r
y
as
cr
ea
tio
n
h
a
s
s
tag
n
ated
o
r
d
ec
li
n
ed
in
t
h
e
m
id
s
t
o
f
th
e
late
s
t
t
w
o
d
ec
ad
es.
T
h
is
is
b
y
v
ir
tu
e
o
f
t
h
e
ad
v
an
ce
m
e
n
t
o
f
p
r
iv
ate
o
il
cr
ea
tio
n
d
o
es
n
'
t
p
r
o
p
o
r
tio
n
ate
w
it
h
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
7
,
No
.
3
,
Sep
tem
b
e
r
20
1
8
:
11
1
–
11
8
112
r
elatin
g
p
o
p
u
lace
i
m
p
r
o
v
e
m
e
n
t.
C
o
n
s
id
er
in
g
t
h
e
f
u
tu
r
e
d
e
m
an
d
s
s
tar
tin
g
n
o
w
h
i
g
h
l
ig
h
ted
a
w
h
o
le
d
ea
l
p
h
ilo
s
o
p
h
y
f
o
r
a
t
h
o
r
o
u
g
h
p
r
o
g
r
ess
io
n
o
f
cr
ea
tio
n
a
n
d
ta
k
in
g
ca
r
e
o
f
ad
v
an
ce
s
o
u
g
h
t
to
b
e
p
r
o
d
u
ce
d
to
m
a
k
e
I
n
d
ia
s
u
r
e
ab
o
u
t
co
n
s
u
m
ab
le
o
ils
s
u
p
p
l
y
as
b
y
v
ir
t
u
e
o
f
o
ats
an
d
s
o
o
n
.
I
t
h
a
s
b
ee
n
r
ep
r
esen
ted
t
h
at
t
h
e
o
il
s
ee
d
s
cr
ea
tio
n
in
I
n
d
ia
is
s
ig
n
i
f
ican
tl
y
h
elp
less
a
g
ain
s
t
th
e
w
h
i
m
s
o
f
n
at
u
r
e
p
ar
ticu
lar
l
y
th
e
r
ain
s
to
r
m
.
T
h
e
m
o
v
i
n
g
ca
s
e
o
f
p
r
ec
ip
itatio
n
w
h
ic
h
is
o
u
t
s
id
e
th
e
ca
p
ac
it
y
t
o
co
n
tr
o
l
o
f
th
e
ag
r
icu
lt
u
r
is
ts
i
m
p
ac
ts
t
h
e
er
a
an
d
g
ain
f
u
l
n
es
s
o
f
o
il ite
m
s
u
n
q
u
e
s
tio
n
ab
l
y
.
T
y
p
ical
lo
w
e
f
f
ec
ti
v
en
e
s
s
o
f
o
il
s
ee
d
s
cr
ea
ted
i
n
I
n
d
ia
co
u
ld
b
e
ta
k
e
n
af
ter
f
u
n
d
a
m
e
n
tall
y
to
t
h
e
d
ep
en
d
en
ce
o
n
t
h
e
r
ain
s
to
r
m
.
T
h
e
o
ils
ee
d
s
i
n
I
n
d
ia,
w
h
ic
h
ar
e
y
ea
r
l
y
o
r
p
er
io
d
ic
y
ield
s
,
ar
e
all
th
e
m
o
r
e
u
n
p
r
o
tecte
d
to
p
r
ec
ip
itatio
n
.
T
h
e
n
atu
r
al
p
r
o
d
u
cts
ar
e
n
o
r
m
all
y
r
o
u
n
d
to
o
v
o
id
o
r
len
g
th
e
n
ed
an
d
p
r
o
tr
u
d
in
g
at
t
h
e
to
p
.
I
t
is
ar
o
u
n
d
t
w
o
to
f
iv
e
c
m
lo
n
g
an
d
w
ei
g
h
t
m
a
y
c
h
an
g
e
f
r
o
m
3
t
o
3
0
g
r
am
.
As
ap
p
ea
r
e
d
in
F
ig
u
r
e
1
,
f
u
i
t
co
m
p
r
is
e
s
o
f
an
e
x
ter
n
al
t
h
i
n
s
k
i
n
(
e
x
o
ca
r
p
)
,
o
il
b
ea
r
in
g
m
as
h
(
m
eso
ca
r
p
)
an
d
a
s
h
ell
en
d
o
ca
r
p
.
T
h
e
s
h
el
l
to
g
eth
er
w
i
th
p
o
r
tio
n
f
r
a
m
es
t
h
e
s
ee
d
.
T
h
e
p
iece
co
m
p
r
is
e
o
f
la
y
er
s
o
f
h
ar
d
o
il
en
d
o
s
p
er
m
,
w
h
ich
is
g
r
a
y
i
s
h
w
h
ite
i
n
s
h
ad
in
g
en
co
m
p
a
s
s
ed
b
y
a
d
u
ll
co
co
a
s
k
i
n
s
ec
u
r
ed
w
it
h
a
s
y
s
te
m
o
f
f
ila
m
e
n
ts
.
P
al
m
o
il
is
e
x
tr
icate
d
f
r
o
m
t
h
e
m
e
s
o
ca
r
p
.
Fig
u
r
e
1
.
Stru
ct
u
r
e
o
f
p
al
m
o
il
f
r
u
it
Ker
n
el
li
k
e
w
is
e
y
ield
s
o
il
k
n
o
w
n
a
s
k
er
n
el
o
il;
h
o
w
e
v
er
th
e
a
m
o
u
n
t
is
j
u
s
t
ar
o
u
n
d
1
/
4
o
f
th
at
ac
q
u
ir
ed
f
r
o
m
m
eso
ca
r
p
.
Oil
p
al
m
b
u
n
d
le
co
m
p
r
is
e
o
f
e
x
ter
n
al
an
d
i
n
w
ar
d
n
a
tu
r
al
p
r
o
d
u
cts.
T
h
e
in
w
ar
d
n
atu
r
al
p
r
o
d
u
cts
ar
e
le
s
s
p
ig
m
en
ted
,
f
air
l
y
lev
el,
u
n
d
ev
elo
p
ed
an
d
n
o
n
-
o
il
b
ea
r
in
g
.
B
u
n
d
le
w
e
ig
h
t
d
i
f
f
er
en
t
f
r
o
m
a
co
u
p
le
to
1
0
0
k
ilo
g
r
am
s
.
W
ell
s
et
cl
u
s
ter
s
co
n
v
e
y
1
0
0
0
t
o
3
0
0
0
o
r
g
an
ic
p
r
o
d
u
cts.
Ag
i
n
g
i
s
as
a
r
u
l
e
f
r
o
m
tip
d
o
w
n
w
ar
d
s
.
A
b
u
n
d
l
e
tak
es
ar
o
u
n
d
f
i
v
e
to
s
ix
m
o
n
th
s
f
o
r
ag
i
n
g
.
Oil
d
ev
elo
p
m
e
n
t
in
t
h
e
p
iece
an
d
m
eso
ca
r
p
h
ap
p
en
s
to
w
ar
d
s
th
e
en
d
o
f
a
tim
e
o
f
d
ev
e
lo
p
m
e
n
t
a
m
id
w
h
ich
s
h
ell
s
o
lid
i
f
ie
s
an
d
af
ter
w
ar
d
f
etu
s
g
ets
to
b
e
n
o
ticea
b
le.
T
h
r
ee
o
il p
al
m
ass
o
r
t
m
e
n
ts
h
a
v
e
b
ee
n
d
is
tin
g
u
is
h
ed
i
n
li
g
h
t o
f
t
h
e
d
i
s
tin
c
tio
n
in
o
r
g
an
ic
p
r
o
d
u
ct
s
tr
u
ctu
r
e.
T
h
e
y
ar
e
D
u
r
a,
T
en
er
a
an
d
P
is
if
er
a.
Du
r
a
h
as a
t
h
ic
k
s
h
ell
(
n
o
r
m
all
y
t
wo
to
eig
h
t
m
m
)
w
it
h
lo
w
to
m
ed
iu
m
m
e
s
o
ca
r
p
co
n
ten
t.
T
h
is
ass
o
r
t
m
en
t
i
s
n
o
t
m
o
n
etar
il
y
d
ev
elo
p
ed
at
th
i
s
p
o
in
t.
Fi
g
u
r
e
2
d
em
o
n
s
tr
ate
s
all
t
h
e
th
r
ee
as
s
o
r
t
m
en
ts
.
Fig
u
r
e
2
.
T
h
r
ee
v
ar
ieties o
f
p
al
m
o
il f
r
u
it
T
en
er
a
ass
o
r
tm
e
n
t
is
a
cr
o
s
s
o
v
er
g
o
t
b
y
i
n
ter
s
ec
tio
n
Du
r
a
(
f
e
m
ale)
an
d
p
is
if
er
a
(
m
ale)
.
I
t
h
as
a
th
i
n
s
h
ell
f
o
r
th
e
m
o
s
t
p
ar
t
a
n
d
a
m
ed
iu
m
to
h
u
g
e
m
eso
ca
r
p
s
u
b
s
tan
ce
.
T
h
er
e
is
u
n
m
is
tak
ab
l
e
f
ib
er
r
in
g
in
th
e
m
eso
ca
r
p
.
T
h
is
is
th
e
g
e
n
er
all
y
d
e
v
elo
p
ed
s
o
r
t
ev
er
y
w
h
er
e
th
r
o
u
g
h
o
u
t
t
h
e
w
o
r
ld
b
ec
au
s
e
o
f
t
h
e
h
ig
h
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
C
h
a
llen
g
in
g
İ
s
s
u
es in
A
u
to
m
a
ted
Oil P
a
lm
F
r
u
it Gra
d
in
g
(
Ga
u
r
a
n
g
S
P
a
tka
r
)
113
m
eso
ca
r
p
s
u
b
s
tan
ce
a
n
d
r
esu
lt
an
t o
il
y
ie
ld
.
P
is
if
er
a
ass
o
r
t
m
e
n
t is d
escr
ib
ed
b
y
a
s
h
ell
-
les
s
n
atu
r
al
p
r
o
d
u
ct
p
ea
lik
e
p
iece
in
s
id
e.
R
e
g
u
lar
l
y
t
h
e
p
iece
is
lik
e
w
i
s
e
m
is
s
i
n
g
.
Si
n
ce
a
lar
g
e
n
u
m
b
er
o
f
t
h
e
o
r
g
an
ic
p
r
o
d
u
cts
d
o
n
'
t
h
av
e
d
ev
elo
p
in
g
li
f
e,
s
ee
d
p
r
o
lif
er
atio
n
is
p
r
ac
ticall
y
u
n
i
m
ag
in
ab
le.
P
al
m
o
il
f
r
u
it
c
h
an
g
e
s
s
h
ad
i
n
g
as
it
ac
h
iev
e
s
le
g
iti
m
ate
co
llect
in
g
p
er
io
d
.
T
h
er
e
ar
e
ad
d
u
p
to
f
o
u
r
p
h
ases
u
n
r
ip
e,
u
n
d
er
r
ip
e,
r
ea
d
y
a
n
d
o
v
er
r
ip
e.
T
h
ese
f
o
u
r
p
h
a
s
es a
r
e
ap
p
ea
r
ed
in
Fi
g
u
r
e
3
.
I
t
is
s
ee
n
th
at
t
h
e
s
h
ad
e
o
f
th
e
o
r
g
a
n
ic
p
r
o
d
u
ct
ch
a
n
g
e
s
f
r
o
m
b
ase
to
p
in
n
ac
le.
Fig
u
r
e
3
.
Fo
u
r
d
if
f
er
e
n
t sta
g
es
o
f
p
al
m
o
il f
r
u
it a
s
it r
ip
en
s
2.
I
M
AG
E
P
RO
CE
SS
I
NG
N
D
F
U
Z
Z
Y
L
O
G
I
CM
E
T
H
O
DS
T
Z
.
Ma
y
,
M.
H.
Am
ar
an
[
1
]
d
ev
elo
p
ed
m
o
d
el
o
f
m
ec
h
a
n
ized
r
ev
ie
w
i
n
g
f
r
a
m
e
w
o
r
k
f
o
r
o
il
p
alm
o
r
g
an
ic
p
r
o
d
u
ct
is
cr
ea
ted
u
tili
zin
g
t
h
e
R
GB
co
lo
r
m
o
d
el
an
d
f
u
zz
y
lo
g
ic.
T
h
e
m
o
t
iv
atio
n
b
e
h
i
n
d
th
i
s
ev
alu
a
tin
g
f
r
a
m
e
w
o
r
k
is
to
r
ec
o
g
n
ize
t
h
e
th
r
ee
d
is
tin
c
t
class
es
o
f
o
il
p
al
m
n
at
u
r
al
p
r
o
d
u
ct
w
h
ich
ar
e
u
n
d
er
r
i
p
e,
r
ea
d
y
a
n
d
o
v
er
r
ip
e
.
T
h
is
e
x
ten
d
g
i
v
es
a
d
ec
e
n
t
s
tr
ateg
y
to
in
s
tit
u
tio
n
alize
th
e
o
il
p
al
m
o
r
g
a
n
ic
p
r
o
d
u
ct
r
ev
ie
w
in
g
f
r
a
m
e
w
o
r
k
o
v
er
a
h
u
g
e
zo
n
e
a
n
d
th
e
e
x
p
lo
r
atio
n
w
ill
k
ee
p
o
n
n
o
r
m
aliz
in
g
th
e
f
r
a
m
e
w
o
r
k
to
h
av
e
t
h
e
ca
p
ac
it
y
to
u
s
e
u
n
d
er
v
ar
io
u
s
w
ells
p
r
i
n
g
o
f
lig
h
t
in
g
.
Me
f
ta
h
Sa
le
m
M.
A
l
f
at
n
i,
[
2
]
in
th
e
ir
ex
a
m
i
n
atio
n
cr
ea
ted
r
o
b
o
tized
r
ev
ie
w
i
n
g
f
r
a
m
e
w
o
r
k
f
o
r
o
il
p
al
m
p
ac
k
s
u
tili
z
in
g
R
GB
co
lo
r
m
o
d
el.
T
h
is
ev
al
u
ati
n
g
f
r
a
m
e
w
o
r
k
i
s
p
r
o
d
u
ce
d
to
r
ec
o
g
n
ize
t
h
r
ee
class
e
s
o
f
p
al
m
o
r
g
a
n
ic
p
r
o
d
u
cts
b
u
n
c
h
.
T
h
e
d
ev
el
o
p
m
e
n
t
s
h
ad
in
g
r
e
co
r
d
d
ep
en
d
ed
o
n
v
ar
io
u
s
s
h
a
d
in
g
in
ten
s
it
y
.
T
h
e
ev
alu
a
tin
g
f
r
a
m
e
w
o
r
k
u
t
ilizes
C
o
m
p
u
ter
a
n
d
ca
m
er
a
to
d
i
s
s
ec
t
an
d
tr
an
s
late
i
m
a
g
es.
T
h
e
C
o
m
p
u
ter
p
r
o
g
r
a
m
cr
ea
ted
an
d
u
tili
ze
d
m
ea
n
s
h
a
d
in
g
f
o
r
ce
to
s
ep
ar
ate
b
etw
ee
n
v
ar
io
u
s
s
h
ad
i
n
g
a
n
d
r
ea
d
in
e
s
s
o
f
n
at
u
r
al
p
r
o
d
u
ct.
Nu
r
s
u
r
iati J
a
m
il,
A
z
lin
a
h
Mo
h
a
m
ed
,
S
y
az
w
a
n
i
A
b
d
u
llah
[
3
]
I
n
th
i
s
p
ap
er
,
ex
ter
n
al
s
u
r
f
ac
e
s
h
ad
es o
f
p
al
m
o
il
cr
is
p
n
at
u
r
al
p
r
o
d
u
ct
b
u
n
d
les
ar
e
b
r
o
k
e
d
o
w
n
to
co
n
s
eq
u
e
n
tl
y
r
e
v
ie
w
t
h
e
o
r
g
a
n
ic
p
r
o
d
u
cts
i
n
to
o
v
er
r
ea
d
y
,
r
ea
d
y
an
d
u
n
r
ip
e.
T
h
e
y
lo
o
k
ed
at
t
w
o
s
tr
ateg
ie
s
f
o
r
s
h
ad
in
g
r
e
v
ie
w
i
n
g
:
1
)
u
ti
lizi
n
g
R
GB
co
m
p
u
ter
ized
n
u
m
b
er
s
a
n
d
2
)
co
lo
r
s
c
class
if
icatio
n
p
r
ep
ar
ed
u
tili
zin
g
a
m
an
a
g
ed
lear
n
i
n
g
Heb
b
m
et
h
o
d
an
d
ev
al
u
ated
u
tili
zi
n
g
f
u
zz
y
lo
g
ic.
W
.
I
.
W
an
I
s
m
ai
l,
M.
Z
.
B
ar
d
aie,
an
d
A
.
M.
A
b
d
u
l
Ha
m
id
[
4
]
T
h
e
tr
ial
w
a
s
led
to
d
ec
id
e
th
e
H
u
e
o
p
tical
p
r
o
p
er
ties
o
f
th
e
t
h
r
ee
class
i
f
icatio
n
s
o
f
Fre
s
h
Fru
it
B
u
n
ch
e
s
i
n
p
ar
ticu
lar
u
n
r
ip
e,
u
n
d
er
r
ip
e
an
d
r
ip
e.
Nik
o
n
C
o
o
lp
ix
4
5
0
0
ad
v
an
ce
d
ca
m
er
a
w
it
h
tele
-
co
n
v
e
r
ter
zo
o
m
i
n
g
a
n
d
th
e
Ke
y
e
n
c
e
v
i
s
io
n
f
r
a
m
e
w
o
r
k
w
er
e
u
tili
ze
d
to
ca
tch
t
h
e
p
ictu
r
es
in
g
e
n
u
i
n
e
o
il
p
al
m
r
a
n
ch
.
T
h
e
r
elatio
n
s
h
ip
o
f
th
e
o
il
co
n
ten
t
f
o
r
m
e
s
o
ca
r
p
o
il p
alm
o
r
g
a
n
ic
p
r
o
d
u
cts
w
it
h
th
e
ad
v
an
ce
d
es
ti
m
atio
n
o
f
H
u
e
w
as d
is
s
ec
ted
.
A
.
N
u
r
eize
,
J
.
W
atad
a
[
5
]
,
th
e
d
esti
n
atio
n
s
o
f
th
i
s
p
ap
e
r
is
to
f
ab
r
ica
te
a
f
u
zz
y
m
u
lticr
iter
ia
ass
es
s
m
en
t
m
o
d
el
t
h
at
d
escr
ib
es
th
e
cr
iter
ia
o
f
o
il
p
alm
o
r
g
a
n
ic
p
r
o
d
u
cts
to
ch
o
o
s
e
th
e
f
u
z
z
y
w
e
ig
h
ts
o
f
t
h
ese
cr
iter
ia
in
lig
h
t o
f
a
f
u
zz
y
r
eg
r
ess
io
n
d
is
p
la
y
.
Z
A
b
d
u
l
lah
,
L
.
C
G
u
an
an
d
B
.
M.
N
Mo
h
d
A
ze
m
i
[
6
]
T
h
e
q
u
alit
y
ele
m
en
t
o
f
a
s
ta
n
d
ar
d
E
lg
ae
is
g
u
i
n
ee
n
s
i
s
o
il
p
al
m
w
a
s
e
v
al
u
ated
u
til
izin
g
a
P
C
v
i
s
io
n
d
em
o
n
s
tr
ate
a
s
a
p
ar
t
o
f
r
eq
u
est
to
as
s
es
s
a
n
d
g
r
ad
e
th
e
o
il
p
al
m
b
u
n
ch
e
s
b
y
a
r
o
b
o
tized
cr
ea
tio
n
f
r
a
m
e
w
o
r
k
.
T
h
e
ele
m
en
t
co
n
s
id
er
ed
w
a
s
s
h
ad
in
g
,
an
d
t
h
e
r
ev
ie
w
cr
iter
ia
d
ep
en
d
ed
o
n
t
h
e
P
alm
Oil
R
esear
ch
I
n
s
t
itu
te
o
f
Ma
la
y
s
ia.
T
h
e
r
elatio
n
s
h
ip
b
et
w
ee
n
o
il
s
u
b
s
ta
n
ce
an
d
s
h
ad
i
n
g
w
a
s
in
v
esti
g
a
ted
in
HSI
(
Hu
e,
Sa
tu
r
at
io
n
an
d
I
n
te
n
s
it
y
)
s
p
ac
e
f
o
r
r
ea
d
in
ess
a
s
s
u
r
an
ce
.
Ma
n
za
R
.
R
.
,
Gai
k
w
ad
B
.
P
.
an
d
Ma
n
za
G.
R
.
[
7
]
s
o
m
e
r
esear
ch
er
s
u
s
ed
d
if
f
er
e
n
t
ed
g
e
d
etec
tio
n
o
p
er
ato
r
s
an
d
p
r
o
v
ed
th
at
th
e
y
ca
n
b
e
u
s
ed
to
ca
teg
o
r
ize
t
h
e
m
a
n
g
o
f
r
u
i
ts
to
e
v
al
u
ate
t
h
e
q
u
alit
y
an
d
g
r
ad
e.
Sa
m
e
co
n
ce
p
t
ca
n
b
e
u
s
ed
in
o
il
p
alm
f
r
u
i
t
g
r
ad
in
g
.
T
h
e
Sim
u
lin
k
b
ased
ad
j
u
s
tab
le
s
tr
u
c
tu
r
e
is
i
n
ten
d
ed
f
o
r
f
ast
r
ee
n
ac
t
m
e
n
t,
e
x
e
cu
tio
n
,
a
n
d
ch
ec
k
o
f
v
id
eo
p
r
ep
ar
in
g
f
r
a
m
e
w
o
r
k
s
.
I
n
t
h
i
s
w
o
r
k
th
e
s
i
m
ilar
e
x
a
m
i
n
atio
n
o
f
d
if
f
er
en
t
m
a
n
g
o
es
v
id
eo
e
d
g
e
id
en
ti
f
ic
atio
n
tech
n
iq
u
es
r
ese
m
b
le
So
b
el
,
P
r
e
w
itt
a
n
d
C
an
n
y
is
e
x
h
ib
ited
.
Fig
u
r
e
4
g
iv
e
s
t
h
e
o
v
er
v
ie
w
o
f
d
if
f
er
e
n
t r
esear
ch
er
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
7
,
No
.
3
,
Sep
tem
b
e
r
20
1
8
:
11
1
–
11
8
114
Fig
u
r
e
4
.
Ver
tical
b
lo
ck
lis
t s
h
o
w
i
n
g
r
esear
c
h
er
s
an
d
t
h
eir
f
i
n
d
in
g
s
No
r
as
y
i
k
in
Fad
ila
h
,
J
u
n
ita
M
o
h
a
m
ad
-
Sale
h
[
8
]
th
is
p
ap
er
ex
h
ib
it
s
th
e
u
s
e
o
f
s
h
ad
i
n
g
v
is
io
n
f
o
r
m
ec
h
a
n
ized
r
ea
d
in
e
s
s
c
h
ar
ac
ter
izatio
n
o
f
o
il
p
al
m
Fre
s
h
Fru
it
B
u
n
c
h
es.
P
ictu
r
es
o
f
o
il
p
al
m
Fre
s
h
Fr
u
i
t
B
u
n
c
h
es
w
er
e
g
at
h
er
ed
an
d
b
r
o
k
e
d
o
w
n
u
t
ilizi
n
g
ad
v
a
n
ce
d
p
ictu
r
e
p
r
ep
ar
in
g
s
tr
ateg
ies
.
T
h
en
th
e
s
h
ad
in
g
ele
m
e
n
ts
w
er
e
r
e
m
o
v
ed
f
r
o
m
th
o
s
e
p
ict
u
r
es
a
n
d
u
tili
ze
d
a
s
th
e
co
n
tr
ib
u
t
io
n
s
f
o
r
A
r
ti
f
ic
ial
Neu
r
al
Net
w
o
r
k
lear
n
in
g
.
T
h
e
ex
ec
u
tio
n
o
f
t
h
e
A
N
N
f
o
r
r
ea
d
in
es
s
ch
ar
ac
te
r
izatio
n
o
f
o
il
p
al
m
FF
B
w
as
ex
a
m
in
ed
u
tili
zi
n
g
t
w
o
s
tr
ateg
ies:
p
r
ep
ar
in
g
AN
N
w
it
h
f
u
ll
ele
m
e
n
ts
an
d
p
r
ep
ar
in
g
A
NN
w
it
h
d
ec
r
ea
s
ed
ele
m
en
ts
in
li
g
h
t
o
f
th
e
P
r
in
cip
al
C
o
m
p
o
n
e
n
t
An
al
y
s
is
in
f
o
r
m
a
tio
n
le
s
s
e
n
i
n
g
s
tr
a
teg
y
.
R
es
u
lt
s
d
e
m
o
n
s
tr
ated
t
h
at
co
n
tr
as
ted
an
d
u
tili
zi
n
g
f
u
ll
co
m
p
o
n
e
n
ts
as
a
p
ar
t
o
f
ANN,
u
ti
lizin
g
th
e
ANN
p
r
ep
ar
ed
w
it
h
les
s
en
ed
el
e
m
en
ts
ca
n
en
h
a
n
ce
th
e
ch
ar
ac
ter
izat
io
n
ac
cu
r
ac
y
.
T
h
e
cr
ea
ted
r
ea
d
in
ess
cla
s
s
i
f
i
er
ca
n
g
o
ab
o
u
t
as
a
s
en
s
o
r
in
d
ec
id
in
g
t
h
e
r
ig
h
t
o
il p
alm
Fre
s
h
Fru
it
Bu
n
c
h
es r
ea
d
in
ess
cla
s
s
i
f
icat
io
n
.
Ah
m
ed
J
af
f
ar
,
R
o
s
elee
n
a
J
aa
f
ar
,
Nu
r
s
u
r
iati
J
a
m
il
[
9
]
th
is
p
ap
er
in
tr
o
d
u
ce
s
a
P
C
h
elp
ed
p
h
o
to
g
r
a
m
m
etr
ic
ap
p
r
o
ac
h
wh
ich
co
r
r
esp
o
n
d
s
t
h
e
s
h
ad
e
o
f
t
h
e
p
al
m
o
il
f
r
u
its
to
th
e
ir
r
ea
d
in
ess
an
d
i
n
t
h
e
en
d
d
ea
ls
w
i
th
th
e
m
p
h
y
s
ical
l
y
.
T
h
e
f
r
a
m
e
w
o
r
k
a
n
d
th
e
ap
p
r
o
ac
h
p
lan
n
ed
i
n
th
i
s
w
o
r
k
h
a
v
e
b
u
i
lt
u
p
a
f
in
i
s
h
r
o
b
o
tizatio
n
r
ev
ie
w
i
n
g
ar
r
an
g
e
m
en
t
o
f
o
il
p
alm
FF
B
an
d
al
o
n
g
th
e
s
e
lin
e
s
r
ad
icall
y
ex
p
a
n
d
ed
th
e
r
ev
ie
w
in
g
ef
f
icien
c
y
.
Fat
m
a
S
u
s
ila
w
ati
Mo
h
a
m
ad
,
A
ziza
h
A
b
d
u
l
Ma
n
a
f
an
d
S
u
r
ia
y
ati
C
h
u
p
r
at,
[
1
0
]
th
is
p
ap
er
u
s
es
th
e
u
tili
za
t
io
n
o
f
Dis
ta
n
ce
Me
as
u
r
e
m
en
t
s
f
o
r
h
is
to
g
r
a
m
b
ased
o
il
p
alm
r
ea
d
in
es
s
id
en
ti
f
icat
io
n
.
I
n
th
is
s
t
u
d
y
,
HSV
co
lo
r
m
o
d
el
i
s
i
n
v
esti
g
at
ed
its
ca
p
ab
ilit
y
o
f
co
lo
r
s
.
Fo
u
r
Dis
ta
n
ce
Me
a
s
u
r
e
m
en
ts
ar
e
ch
o
s
en
an
d
lo
o
k
ed
at
in
t
h
i
s
s
tu
d
y
.
S
u
n
i
lk
u
m
ar
a
n
d
D.
S.
Sp
ar
j
an
B
ab
u
[
1
1
]
Stated
T
h
e
p
r
esen
t
s
t
u
d
y
w
as
e
m
b
r
ac
ed
to
as
s
es
s
d
iv
er
s
e
d
ev
elo
p
m
e
n
t
p
h
a
s
es
o
f
o
il
p
al
m
f
r
u
it
s
as
f
ar
as
s
h
ad
in
g
a
n
d
o
il
co
n
ten
t,
s
et
u
p
t
h
e
ir
b
u
r
y
r
elat
io
n
s
h
ip
an
d
to
cr
ea
te
ex
p
ec
tatio
n
m
o
d
els
in
li
g
h
t
o
f
s
h
ad
in
g
q
u
ali
ties
s
o
th
at
n
o
n
d
an
g
er
o
u
s
r
ea
d
in
ess
a
s
s
es
s
m
en
t
co
u
ld
b
e
ac
co
m
p
li
s
h
ed
.
C
o
r
r
elatio
n
o
f
R
GB
a
n
d
L
*
a
*
b
s
h
ad
in
g
m
o
d
el
i
s
d
o
n
e.
T
h
e
L
*
a
*
b
*
b
ased
m
o
d
el
w
o
u
ld
b
e
p
er
f
ec
t
f
o
r
f
u
s
i
n
g
i
n
co
n
tr
ap
tio
n
s
lik
e
co
lo
r
i
m
eter
s
w
it
h
th
e
e
n
d
g
o
al
o
f
s
h
ad
i
n
g
b
ased
r
ev
ie
w
i
n
g
o
f
FF
B
an
d
e
x
p
ec
tatio
n
o
f
o
il
s
u
b
s
tan
ce
.
T
h
is
s
t
u
d
y
e
x
p
lo
r
es
t
h
e
co
n
n
ec
tio
n
b
et
w
ee
n
o
il
co
n
ten
t
i
n
th
e
o
il
p
al
m
f
r
u
it
a
g
ai
n
s
t
t
h
e
s
h
ad
e
o
f
th
e
o
il
p
alm
o
r
g
an
ic
p
r
o
d
u
ct.
T
h
e
f
i
n
d
in
g
o
f
t
h
is
s
t
u
d
y
i
s
h
elp
f
u
l
f
o
r
d
ec
id
in
g
r
ea
d
in
ess
o
f
o
il
p
al
m
f
o
r
g
ath
er
in
g
a
n
d
at
th
e
last
w
ill
u
s
e
i
n
b
u
ild
i
n
g
u
p
th
e
b
u
s
i
n
es
s
s
h
a
d
in
g
m
eter
to
g
au
g
e
o
r
g
an
ic
p
r
o
d
u
ct
r
ea
d
in
ess
u
tili
zin
g
n
o
n
-
co
n
tact
esti
m
atio
n
p
r
o
ce
d
u
r
e.
[
1
2
]
.
C
h
o
o
n
g
et
a
l
.
[
1
3
]
th
e
o
il
s
u
b
s
ta
n
ce
o
f
t
h
e
tis
s
u
e
o
f
m
e
s
o
ca
r
p
h
as
co
o
r
d
in
ate
ass
o
ci
atio
n
w
it
h
s
h
ad
i
n
g
g
r
o
u
p
s
r
ed
,
g
r
ee
n
an
d
b
lu
e.
B
y
r
u
n
n
in
g
escala
ted
test
s
,
it
w
as
o
b
s
er
v
ed
t
h
at
o
il
co
n
ten
t
r
elate
d
w
it
h
th
e
r
ed
s
h
ad
in
g
b
an
d
,
w
it
h
a
r
elap
s
e
esti
m
atio
n
o
f
0
.
8
6
.
T
h
e
f
in
d
i
n
g
o
f
t
h
is
s
t
u
d
y
m
i
g
h
t
b
e
v
al
u
ab
le
f
o
r
d
ec
id
in
g
th
e
r
ea
d
in
es
s
o
f
o
il p
al
m
f
o
r
co
llec
ti
n
g
a
n
d
f
o
r
t
h
e
u
tili
za
t
io
n
i
n
th
e
o
p
er
atio
n
an
d
co
n
tr
o
l o
f
n
o
n
s
to
p
s
ter
ilizer
in
p
al
m
o
il
p
r
o
ce
s
s
.
Ho
w
e
v
er
,
a
later
s
tu
d
y
b
y
G
h
az
ali
et
a
l
.
[
1
4
]
d
is
co
v
er
ed
th
at
t
h
e
r
ed
co
m
p
o
n
e
n
t
s
f
o
r
u
n
r
ip
e
a
n
d
u
n
d
er
r
ip
e
ca
teg
o
r
ies
w
er
e
a
l
m
o
s
t
th
e
s
a
m
e.
T
h
e
s
u
m
m
ar
y
o
f
r
esear
c
h
f
i
n
d
in
g
i
s
s
h
o
w
n
i
n
F
i
g
u
r
e
5
.
T
h
e
test
c
o
m
e
s
ab
o
u
t
d
e
m
o
n
s
tr
ate
th
at
[
1
5
]
Fu
zz
y
Mo
v
i
n
g
K
-
i
m
p
lie
s
h
as
ch
ar
ac
ter
ized
th
e
r
e
m
o
te
d
etec
ti
n
g
p
ictu
r
e
m
o
r
e
p
r
ec
is
el
y
t
h
a
n
o
t
h
er
th
r
ee
ca
lc
u
latio
n
s
.
R
at
h
er
t
h
an
u
tili
zi
n
g
s
in
g
le
co
m
p
o
n
e
n
t
b
u
n
c
h
in
g
ca
lc
u
lati
o
n
,
[
1
6
]
th
is
p
ap
er
in
tr
o
d
u
ce
s
d
if
f
er
e
n
t
ele
m
e
n
t
g
r
o
u
p
in
g
ca
l
cu
latio
n
w
i
th
t
h
r
ee
ele
m
e
n
ts
f
o
r
e
v
er
y
p
ix
el,
f
o
r
ex
a
m
p
le,
p
ix
el
p
o
w
er
,
s
ep
ar
ate
f
r
o
m
t
h
e
f
o
ca
l
p
o
in
t
o
f
t
h
e
s
p
o
t
an
d
m
id
d
le
o
f
en
co
m
p
as
s
in
g
p
ix
e
ls
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
C
h
a
llen
g
in
g
İ
s
s
u
es in
A
u
to
m
a
ted
Oil P
a
lm
F
r
u
it Gra
d
in
g
(
Ga
u
r
a
n
g
S
P
a
tka
r
)
115
Fig
u
r
e
5
.
Ver
tical
b
lo
ck
lis
t s
h
o
w
i
n
g
r
esear
c
h
er
s
an
d
t
h
eir
f
i
n
d
in
g
s
3.
CH
AL
L
E
N
G
I
NG
I
SS
UE
S
I
N
P
AL
M
F
RUIT
G
R
ADIN
G
Af
ter
s
tar
ti
n
g
ex
a
m
i
n
atio
n
o
f
th
e
w
r
iti
n
g
r
e
v
ie
w
it
is
f
o
u
n
d
th
at
th
er
e
ar
e
n
u
m
er
o
u
s
is
s
u
es
w
h
ic
h
m
u
s
t
b
e
talk
ed
ab
o
u
t
an
d
s
o
r
ted
to
g
et
t
h
e
b
es
t
r
es
u
lts
.
T
h
er
e
ar
e
ad
d
u
p
to
s
e
v
en
test
i
n
g
is
s
u
es
w
h
ich
w
er
e
n
o
t
co
n
s
id
er
ed
in
t
h
e
p
ast
r
es
ea
r
ch
.
T
h
er
e
ar
e
s
itu
atio
n
s
w
h
er
e
th
e
o
r
g
an
ic
p
r
o
d
u
ct
i
s
h
ar
m
ed
b
y
n
u
i
s
an
ce
i
n
lig
h
t
o
f
w
h
ich
t
h
e
n
at
u
r
al
p
r
o
d
u
ct
s
h
ad
in
g
m
a
y
c
h
an
g
e
a
n
d
p
r
o
m
p
ts
w
r
o
n
g
r
ev
ie
w
i
n
g
o
f
o
r
g
an
ic
p
r
o
d
u
ct.
T
h
er
e
ar
e
d
is
tin
ctiv
e
v
ar
ia
b
le
s
w
h
ic
h
n
ee
d
to
co
n
s
id
er
w
h
e
n
th
e
w
a
y
to
w
ar
d
ev
a
lu
at
in
g
is
co
m
p
u
ter
ized
.
A
p
o
r
tio
n
o
f
th
e
k
e
y
co
m
p
o
n
e
n
ts
w
h
ic
h
is
f
o
u
n
d
an
d
r
ec
o
g
n
ize
d
ar
e
ap
p
ea
r
ed
in
F
ig
u
r
e
6
.
Fig
u
r
e
6
.
Dif
f
er
en
t p
ar
a
m
eter
s
to
b
e
co
n
s
id
er
ed
in
p
alm
o
il
f
r
u
it g
r
ad
in
g
1.
C
o
lo
r
m
o
d
el:
So
m
e
o
f
t
h
e
r
es
ea
r
ch
er
s
h
a
v
e
p
r
o
v
ed
th
at
R
G
B
co
lo
r
m
o
d
el
o
r
HI
S
co
lo
r
m
o
d
el
i
s
th
e
b
es
t
f
o
r
g
r
ad
in
g
o
il p
al
m
f
r
u
it.
B
u
t
af
ter
liter
at
u
r
e
s
u
r
v
e
y
it i
s
f
o
u
n
d
th
at
th
e
co
lo
r
m
o
d
el
to
b
e
u
s
ed
d
ep
en
d
s
o
n
th
e
e
n
v
ir
o
n
m
en
ta
l c
o
n
d
it
io
n
wh
ich
i
s
u
n
p
r
ed
i
ctab
le.
A
l
s
o
th
e
co
lo
r
o
f
t
h
e
f
r
u
it i
s
d
i
f
f
er
e
n
t a
n
d
v
ar
ie
s
f
r
o
m
r
eg
io
n
to
r
eg
io
n
s
o
th
er
e
is
a
n
ee
d
f
o
r
i
n
v
e
s
ti
g
atio
n
an
d
d
etai
led
s
t
u
d
y
.
T
h
e
p
u
r
p
o
s
e
o
f
a
co
lo
r
m
o
d
el
is
to
f
ac
ilit
ate
t
h
e
s
p
ec
i
f
icatio
n
o
f
c
o
lo
r
s
in
s
o
m
e
s
tan
d
ar
d
g
en
er
al
l
y
ac
ce
p
tab
le
w
a
y
.
2.
C
a
m
er
a
s
p
ec
if
icat
io
n
:
W
h
e
n
th
e
i
m
ag
e
is
ca
p
t
u
r
ed
f
r
o
m
t
h
e
tr
ee
f
o
r
r
ea
l
ti
m
e
p
r
o
ce
s
s
i
n
g
,
t
h
e
ca
m
er
a
r
eso
lu
tio
n
s
an
d
p
ix
el
d
ata
also
p
lay
s
m
aj
o
r
r
o
le
in
d
ec
id
in
g
t
h
e
co
m
p
lex
it
y
o
f
alg
o
r
it
h
m
to
b
e
d
esig
n
ed
.
3.
C
a
m
er
a
lo
ca
tio
n
:
T
h
e
lo
ca
tio
n
o
f
ca
m
er
a
also
p
la
y
s
v
er
y
i
m
p
o
r
ta
n
t
r
o
le
in
d
ec
is
io
n
m
a
k
in
g
b
ec
au
s
e
th
e
co
lo
r
o
f
f
r
u
it
is
n
o
t
u
n
i
f
o
r
m
f
r
o
m
b
ase
to
ap
ex
.
T
h
e
lo
ca
tio
n
,
o
r
ien
tatio
n
a
n
d
m
o
d
e
o
f
o
p
er
atio
n
o
f
ea
c
h
ca
m
er
a
n
ee
d
to
b
e
ca
r
ef
u
ll
y
ch
o
s
en
to
en
s
u
r
e
w
ell
-
co
v
er
ed
s
c
en
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
7
,
No
.
3
,
Sep
tem
b
e
r
20
1
8
:
11
1
–
11
8
116
4.
T
im
e
co
m
p
le
x
it
y
o
f
al
g
o
r
ith
m
:
I
n
t
h
e
p
r
ev
io
u
s
r
esear
ch
th
er
e
is
n
o
ti
m
e
co
m
p
le
x
it
y
g
i
v
e
n
f
o
r
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
.
No
t e
v
en
a
s
in
g
le
al
g
o
r
ith
m
s
a
y
s
t
h
at
it
s
ti
m
e
co
m
p
le
x
it
y
is
li
n
ea
r
o
r
q
u
ad
r
atic.
5.
I
llu
m
in
a
tio
n
:
Mo
s
t
o
f
th
e
p
r
ev
io
u
s
r
esear
ch
is
ca
r
r
ied
o
u
t
in
co
n
tr
o
lled
en
v
ir
o
n
m
en
t.
T
h
e
a
lg
o
r
ith
m
s
h
o
u
ld
w
o
r
k
i
n
all
t
h
e
en
v
ir
o
n
m
en
tal
co
n
d
itio
n
s
,
ir
r
esp
ec
tiv
e
o
f
clo
u
d
y
o
r
s
u
n
n
y
w
ea
t
h
er
.
6.
Sp
ec
ies
t
y
p
e:
T
ill
n
o
w
n
o
r
esear
ch
h
a
s
b
ee
n
d
o
n
e
o
n
ca
teg
o
r
izin
g
th
e
p
al
m
o
il
f
r
u
i
ts
in
to
th
eir
t
h
r
ee
s
p
ec
ies d
u
r
a,
ten
er
a
o
r
p
is
if
er
a
.
7.
Dete
ctin
g
d
is
ea
s
e
s
/p
e
s
t:
Dete
ctin
g
th
e
t
y
p
e
o
f
d
is
ea
s
e/p
est
th
e
o
il
p
alm
f
r
u
i
t
af
f
ec
ted
w
ith
is
also
v
er
y
i
m
p
o
r
tan
t
f
o
r
f
ar
m
er
s
to
tak
e
p
r
ec
au
tio
n
s
a
g
ai
n
s
t
th
e
p
est.
F
ig
u
r
e
7
s
h
o
w
s
d
i
f
f
er
e
n
t
d
is
ea
s
es
an
d
p
est.
I
t
i
s
f
o
u
n
d
a
f
ter
liter
at
u
r
e
s
u
r
v
e
y
th
at
au
to
m
ated
d
etec
tio
n
o
f
d
is
ea
s
e
a
n
d
p
est
h
a
s
n
o
t
b
ee
n
d
o
n
e
b
y
r
esear
ch
er
s
.
8.
E
x
o
ca
r
p
co
lo
r
:
E
x
o
ca
r
p
co
lo
r
v
ar
ies
f
r
o
m
r
eg
io
n
to
r
eg
io
n
.
T
h
r
o
u
g
h
s
t
u
d
y
i
s
r
eq
u
ir
ed
to
f
in
d
o
u
t
t
h
e
d
if
f
er
e
n
t
co
lo
r
in
d
if
f
er
en
t
r
eg
io
n
s
.
W
e
ca
n
n
o
t
g
e
n
er
aliz
e
th
e
m
eso
ca
r
p
co
lo
r
.
Fig
u
r
e
8
s
h
o
w
s
th
e
r
elatio
n
s
h
ip
b
et
w
ee
n
co
lo
r
an
d
ca
teg
o
r
y
o
f
f
r
u
it.
9.
Fru
it
ca
te
g
o
r
y
:
So
m
e
r
esear
c
h
er
s
h
av
e
ta
k
en
o
n
l
y
t
h
r
ee
ca
teg
o
r
ies
n
a
m
el
y
Un
r
ip
e,
R
ip
e
an
d
Ov
er
r
ip
e.
B
u
t
th
e
tr
u
t
h
is
t
h
er
e
ar
e
to
tal
f
o
u
r
ca
teg
o
r
ies Un
d
er
r
ip
e,
Un
r
ip
e,
R
ip
e
an
d
Ov
er
r
ip
e.
10.
P
er
ce
n
tag
e
o
f
FF
A
:
Fi
n
d
in
g
t
h
e
p
er
ce
n
ta
g
e
o
f
f
r
ee
Fatt
y
Acid
(
FF
A
)
co
n
te
n
t
f
r
o
m
t
h
e
f
r
u
it
i
s
al
s
o
v
er
y
i
m
p
o
r
tan
t
i
n
au
to
m
ated
g
r
ad
in
g
.
Mo
r
e
th
e
FF
A
co
n
ten
t
l
ess
h
ea
lth
y
w
i
ll
b
e
th
e
o
il.
T
h
e
r
elatio
n
s
h
ip
b
et
w
ee
n
f
r
u
it c
ate
g
o
r
y
an
d
FF
A
co
n
ten
t i
s
s
h
o
w
n
i
n
F
i
g
u
r
e
9
.
11.
Nu
m
b
er
o
f
Deta
c
h
ed
f
r
u
it
s
:
T
h
is
is
t
h
e
m
ai
n
ele
m
e
n
t
w
h
ic
h
is
u
tili
ze
d
a
s
a
p
ar
t
o
f
m
a
n
u
a
l
ev
al
u
ati
n
g
.
So
th
er
e
i
s
s
o
m
e
co
n
n
ec
t
io
n
b
et
w
ee
n
n
u
m
b
er
o
f
n
at
u
r
al
p
r
o
d
u
cts
tu
m
b
led
f
r
o
m
tr
ee
s
to
th
e
r
ev
ie
w
i
n
g
.
T
ill
n
o
w
t
h
is
ele
m
e
n
t
h
as
n
o
t
co
n
t
e
m
p
lated
.
T
h
is
tec
h
n
iq
u
e
h
as
b
ee
n
r
eh
ea
r
s
ed
til
l
to
d
a
y
s
in
ce
it
is
p
o
s
s
ib
le
i
f
th
e
tr
ee
is
tall.
I
t
ca
n
b
e
o
b
s
er
v
ed
f
r
o
m
F
i
g
u
r
e
1
0
th
at
t
h
e
n
u
m
b
er
o
f
d
etac
h
ed
f
r
u
itlet
s
h
as
d
ir
ec
t
r
elat
io
n
s
h
ip
w
it
h
th
e
F
FB
ca
teg
o
r
y
.
T
h
e
d
ata
i
s
co
m
p
iled
f
r
o
m
s
tatis
t
ical
d
a
ta,
Go
d
r
ej
A
g
r
o
v
et
P
v
t.
L
td
.
-
Go
a.
T
h
e
m
a
n
u
al
h
ar
v
e
s
tin
g
w
o
r
k
s
w
it
h
t
h
e
n
u
m
b
er
o
f
d
etac
h
ed
f
r
u
it
s
f
alle
n
d
o
w
n
o
n
th
e
g
r
o
u
n
d
f
r
o
m
t
h
e
tr
ee
.
Sin
ce
t
h
e
tr
ee
s
ar
e
v
er
y
tall,
an
d
f
ar
m
er
s
ca
n
n
o
t
cli
m
b
th
e
tr
ee
s
b
ec
au
s
e
o
f
th
e
t
h
o
r
n
s
,
th
i
s
is
th
e
o
n
l
y
f
ea
s
ib
le
m
et
h
o
d
f
o
r
th
e
m
to
f
i
n
d
o
u
t th
e
co
r
r
ec
t h
a
r
v
est ti
m
e
o
f
o
il p
al
m
f
r
u
its
.
Fig
u
r
e
7
.
Dis
ea
s
es a
n
d
p
ests
i
n
o
il p
al
m
f
r
u
it
Fig
u
r
e
8
.
C
o
r
r
elatio
n
b
et
w
ee
n
co
lo
r
an
d
ca
teg
o
r
y
Fig
u
r
e
9
.
R
elatio
n
b
et
w
ee
n
Fr
u
it C
a
teg
o
r
y
a
n
d
FF
A
co
n
ten
t
Fig
u
r
e
1
0
.
R
elatio
n
Deta
c
h
ed
Fru
it a
n
d
Fru
it
C
ateg
o
r
y
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
C
h
a
llen
g
in
g
İ
s
s
u
es in
A
u
to
m
a
ted
Oil P
a
lm
F
r
u
it Gra
d
in
g
(
Ga
u
r
a
n
g
S
P
a
tka
r
)
117
4.
CO
NCLU
SI
O
N
I
n
th
is
p
ap
er
w
e
in
tr
o
d
u
ce
d
th
e
d
iag
r
a
m
o
f
v
ar
io
u
s
I
m
ag
e
P
r
o
ce
s
s
in
g
a
n
d
f
u
zz
y
lo
g
ic
m
et
h
o
d
s
u
tili
ze
d
f
o
r
P
alm
o
il
n
at
u
r
al
p
r
o
d
u
ct
ev
alu
ati
n
g
an
d
tal
k
ed
ab
o
u
t
th
e
d
if
f
ic
u
ltie
s
th
at
o
u
g
h
t
to
b
e
m
et
to
g
et
ex
ac
t
an
d
s
u
b
s
ta
n
tial
r
e
s
u
l
ts
.
Desp
ite
th
e
f
ac
t
t
h
at
a
f
e
w
s
cien
t
is
t
s
s
a
y
th
at
th
e
ca
lc
u
la
tio
n
an
d
s
tr
ate
g
ie
s
p
r
o
p
o
s
ed
b
y
th
e
m
is
g
r
ea
t
an
d
f
la
w
les
s
y
et
at
t
h
e
s
a
m
e
ti
m
e
th
er
e
is
ex
te
n
s
io
n
f
o
r
leg
iti
m
ate
p
r
o
ce
d
u
r
e
an
d
ch
an
g
e.
T
ill
n
o
w
t
h
er
e
w
as
n
o
m
o
d
el
in
d
icate
d
w
h
ic
h
ca
n
b
e
u
tili
ze
d
as
p
lan
f
o
r
ex
ec
u
ti
o
n
.
Sin
ce
s
h
ad
e
o
f
o
r
g
an
ic
p
r
o
d
u
ct
c
h
an
g
es
f
r
o
m
lo
ca
le
to
d
is
tr
ict,
s
a
m
e
tech
n
iq
u
e
ca
n
't
b
e
r
ec
eiv
ed
to
e
v
er
y
o
n
e
o
f
t
h
e
ca
s
es.
So
th
er
e
i
s
a
r
eq
u
ir
e
m
e
n
t
f
o
r
s
u
m
m
ed
u
p
m
o
d
el
u
tili
z
in
g
d
is
p
la
y
i
n
g
s
tr
ateg
ie
s
.
A
lo
n
g
s
id
e
s
h
ad
i
n
g
t
h
er
e
ar
e
m
o
r
e
co
m
p
o
n
e
n
ts
w
h
ic
h
ar
e
ex
p
r
ess
ed
b
ef
o
r
e
ca
n
b
e
u
tili
ze
d
to
b
u
ild
th
e
ex
ac
t
n
es
s
a
n
d
p
r
ec
is
io
n
w
h
il
e
ev
alu
a
tin
g
o
il
p
al
m
n
at
u
r
al
p
r
o
d
u
cts.
P
r
esen
tl
y
a
d
ay
's
P
C
v
is
io
n
f
r
a
m
e
w
o
r
k
is
u
tili
ze
d
w
h
er
ev
er
to
d
ec
r
ea
s
e
th
e
b
lu
n
d
er
an
d
i
n
cr
e
m
en
t
th
e
p
r
o
f
icien
c
y
an
d
p
r
o
f
itab
il
it
y
,
it
i
s
a
n
ee
d
th
a
t
P
al
m
o
il
ex
tr
ac
tio
n
f
ac
to
r
ie
s
o
u
g
h
t to
b
e
r
ec
ei
v
ed
.
I
n
t
h
i
s
m
an
n
er
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
a
n
d
f
u
zz
y
lo
g
ic
m
et
h
o
d
s
ar
e
i
n
ten
s
e
in
s
tr
u
m
en
t
s
w
h
ic
h
w
il
l
h
elp
i
n
p
lan
n
i
n
g
p
o
w
er
f
u
l
m
ac
h
in
e
-
v
is
io
n
f
r
a
m
e
w
o
r
k
f
o
r
f
ar
m
i
n
g
s
p
ac
e
if
t
h
e
ab
o
v
e
is
s
u
e
s
ar
e
ten
d
ed
to
e
f
f
ec
tiv
e
l
y
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
W
e
w
o
u
ld
li
k
e
to
t
h
an
k
Go
d
r
ej
A
g
r
o
v
et
P
v
t.
L
td
.
Go
a
f
o
r
h
elp
in
g
u
s
in
d
ata
co
llectio
n
an
d
r
eq
u
ir
ed
in
f
o
r
m
atio
n
.
Fo
r
th
eir
co
n
ti
n
u
ed
s
u
p
p
o
r
t,
g
u
id
an
ce
,
a
n
d
in
cr
ed
ib
le
p
atien
ce
,
I
w
o
u
ld
lik
e
to
th
an
k
Dr
.
G.
S.G.
N
An
j
an
e
y
u
l
u
an
d
Dr
.
C
h
a
n
d
r
a
Mo
u
li
P
.
V.
S.
S.
R
.
W
ith
o
u
t
th
eir
e
n
th
u
s
ias
m
a
n
d
g
en
er
o
s
i
t
y
,
t
h
is
r
esear
ch
w
o
u
ld
n
o
t
h
av
e
b
ee
n
s
u
cc
es
s
f
u
l.
I
w
o
u
ld
also
li
k
e
to
s
en
d
a
s
p
ec
ial
t
h
an
k
s
to
m
y
p
ar
e
n
ts
a
n
d
m
y
co
lleag
u
e
s
f
o
r
th
e
ir
en
co
u
r
a
g
e
m
en
t a
n
d
s
u
p
p
o
r
t th
r
o
u
g
h
o
u
t
m
y
e
n
tire
ac
ad
e
m
ic
ca
r
ee
r
.
RE
F
E
R
E
NC
E
S
[1
]
Z.
M
a
y
,
M
.
H.
Am
a
ra
n
,
e
t
a
l.
,
“
A
u
to
m
a
ted
Oil
P
a
lm
F
ru
it
G
ra
d
in
g
S
y
ste
m
u
sin
g
A
rti
f
i
c
ia
l
In
telli
g
e
n
c
e
”
,
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
V
id
e
o
&
Ima
g
e
Pro
c
e
ss
in
g
a
n
d
Ne
tw
o
rk
S
e
c
u
rity
IJV
I
P
NS
-
IJENS
Vo
lu
m
e
.
1
1
n
o
.
0
3
.
[2
]
M
e
f
tah
S
a
le
m
M
.
A
lfatn
i,
e
t
a
l.
,
“
Oil
P
a
lm
F
ru
it
Bu
n
c
h
G
ra
d
in
g
S
y
ste
m
U
sin
g
Re
d
,
G
re
e
n
,
a
n
d
Blu
e
Dig
it
a
l
Nu
m
b
e
r
”
,
Un
ive
rs
it
y
Pu
tra
M
a
la
y
sia
,
J
o
u
r
n
a
l
o
f
Ap
p
li
e
d
S
c
ien
c
e
s
,
Vo
l.
8
,
p
p
.
1
4
4
4
-
1
4
5
2
,
2
0
0
8
.
[3
]
Nu
rsu
riati
Ja
m
il
,
Az
li
n
a
h
M
o
h
a
m
e
d
,
S
y
a
z
w
a
n
i
A
b
d
u
ll
a
h
,
e
t
a
l
.
,
“
A
u
to
m
a
ted
G
ra
d
in
g
o
f
P
a
lm
Oi
l
F
re
sh
Bu
n
c
h
e
s
(F
F
B)
u
sin
g
Ne
u
ro
-
F
u
z
z
y
Tec
h
n
iq
u
e
”
,
Un
ive
rs
it
i
T
e
k
n
o
lo
g
i
M
A
RA
,
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
f
S
o
ft
Co
m
p
u
ti
n
g
a
n
d
Pa
tt
e
rn
Rec
o
g
n
it
io
n
,
2
0
0
9
.
[4
]
W
.
I.
W
a
n
Is
m
a
il
,
M
.
Z.
Ba
rd
a
ie,
a
n
d
A
.
M
.
A
b
d
u
l
Ha
m
id
,
e
t
a
l.
,
“
O
p
ti
c
a
l
p
r
o
p
e
rti
e
s
f
o
r
m
e
c
h
a
n
ic
a
l
h
a
rv
e
stin
g
o
f
o
il
p
a
lm
F
F
B
”
,
J
o
u
rn
a
l
o
f
Oil
P
a
lm
Res
e
a
rc
h
,
Vo
lu
m
e
.
1
2
,
n
o
.
2
,
p
p
.
3
8
-
45,
De
c
2
0
0
0
[5
]
A
.
Nu
re
ize
,
J.
W
a
t
a
d
a
,
e
t
a
l.
,
“
M
u
lt
i
-
c
rit
e
ria
F
u
z
z
y
R
e
g
re
ss
io
n
M
o
d
e
l
f
o
r
Ev
a
lu
a
ti
n
g
Oil
P
a
lm
G
r
a
d
in
g
”
,
Gr
a
d
u
a
t
e
S
c
h
o
o
l
o
f
In
f
o
rm
a
ti
o
n
,
Pro
d
u
c
ti
o
n
a
n
d
S
y
ste
m
,
W
a
se
d
a
Un
iv
e
rsit
y
,
2
-
7
Hib
ik
in
o
,
W
a
k
a
m
a
tsu
,
Kitak
y
u
sh
u
,
8
0
8
-
0
1
3
5
Ja
p
a
n
,
2
0
0
9
.
[6
]
M
.
Z
A
b
d
u
ll
a
h
,
L
.
C
G
u
a
n
a
n
d
B.
M
.
N
M
o
h
d
A
z
e
m
i,
e
t
a
l.
,
“
S
tep
w
ise
Disc
ri
m
in
a
n
t
A
n
a
l
y
sis
F
o
r
Co
lo
u
r
G
ra
d
in
g
o
f
Oil
P
a
lm
Us
in
g
M
a
c
h
in
e
V
isi
o
n
S
y
st
e
m
”
,
Un
ive
r
sity
S
c
ien
c
e
M
a
la
y
s
ia
,
In
stit
u
te
o
f
C
h
e
mic
a
l
E
n
g
i
n
e
e
rs
,
T
ra
n
s
ICh
e
me
,
Vo
l.
7
9
,
P
a
rt
C,
2
0
0
1
.
[7
]
M
a
n
z
a
R.
R.
,
Ga
ik
w
a
d
B.
P
.
a
n
d
M
a
n
z
a
G
.
R.
e
t
a
l.
,
(2
0
1
2
)
“
Us
e
o
f
Ed
g
e
De
t
e
c
ti
o
n
Op
e
ra
to
rs f
o
r
Ag
ricu
lt
u
re
V
id
e
o
S
c
e
n
e
F
e
a
tu
re
Ex
trac
ti
o
n
f
ro
m
M
a
n
g
o
F
ru
it
s
”,
Ad
v
a
n
c
e
s in
Co
m
p
u
ta
ti
o
n
a
l
Res
e
a
rc
h
,
IS
S
N:
0
9
7
5
-
3
2
7
3
&
E
-
IS
S
N:
0
9
7
5
-
9
0
8
5
,
Vo
lu
m
e
4
,
Iss
u
e
1
,
p
p
.
-
50
-
5
3
.
[8
]
No
ra
s
y
ik
in
F
a
d
il
a
h
,
Ju
n
it
a
M
o
h
a
m
a
d
-
S
a
leh
,
Zai
n
i
A
b
d
u
l
Ha
li
m
,
Ha
id
i
Ib
ra
h
im
a
n
d
S
y
e
d
S
a
li
m
S
y
e
d
A
li
,
e
t
a
l.
,
“
In
telli
g
e
n
t
Co
lo
r
V
isio
n
S
y
ste
m
f
o
r
Rip
e
n
e
ss
Clas
si
f
ica
ti
o
n
o
f
Oil
P
a
lm
F
re
sh
F
ru
it
Bu
n
c
h
”
,
S
e
n
so
rs
2
0
1
2
,
1
2
,
1
4
1
7
9
-
1
4
1
9
5
;
d
o
i:
1
0
.
3
3
9
0
/s1
2
1
0
1
4
1
7
9
,
IS
S
N 1
4
2
4
-
8
2
2
0
.
[9
]
A
h
m
e
d
Ja
ff
a
r,
Ro
se
lee
n
a
Ja
a
f
a
r,
Nu
rsu
riati
Ja
m
il
,
Ch
e
n
g
Ye
e
L
o
w
a
n
d
Bu
lan
A
b
d
u
ll
a
h
,
e
t
a
l.
,
“
P
h
o
t
o
g
ra
m
m
e
tri
c
G
ra
d
in
g
o
f
Oil
P
a
lm
F
re
sh
F
ru
it
Bu
n
c
h
e
s
”
,
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
M
e
c
h
a
n
ica
l
&
M
e
c
h
a
tro
n
i
c
s
En
g
in
e
e
rin
g
IJMM
E
-
IJENS
V
o
l:
0
9
N
o
:
10
[1
0
]
F
a
tm
a
S
u
sila
w
a
ti
M
o
h
a
m
a
d
,
A
z
iz
a
h
A
b
d
u
l
M
a
n
a
f
a
n
d
S
u
riay
a
ti
Ch
u
p
ra
t,
e
t
a
l
.
,
“
Ex
p
l
o
it
i
n
g
Dista
n
c
e
M
e
a
su
re
m
e
n
t
f
o
r
Rip
e
n
e
ss
Id
e
n
ti
f
ica
ti
o
n
”
,
IJ
CS
I
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Co
m
p
u
ter
S
c
ien
c
e
Iss
u
e
s,V
o
l.
9
,
Iss
u
e
3
,
No
3
,
p
p
1
0
7
-
1
0
8
,
M
a
y
2
0
1
2
.
[1
1
]
K.
S
u
n
i
lk
u
m
a
r
a
n
d
D.
S
.
S
p
a
rjan
Ba
b
u
,
e
t
a
l.
,
“
S
u
rf
a
c
e
c
o
lo
r
b
a
se
d
p
re
d
ictio
n
o
f
o
il
c
o
n
ten
t
i
n
o
il
p
a
lm
(El
a
e
is
g
u
in
e
e
n
sis
Ja
c
q
.
)
F
re
sh
f
ru
it
b
u
n
c
h
”
,
Af
ric
a
n
J
o
u
rn
a
l
o
f
A
g
ri
c
u
lt
u
ra
l
Res
e
a
rc
h
,
V
o
l.
8
(6
),
p
p
.
5
6
4
-
5
6
9
,
2
5
F
e
b
ru
a
ry
,
2
0
1
3
.
[1
2
]
Hu
d
z
a
ri,
R.
;
Ish
a
k
,
W
.
W
.
;
No
o
rm
a
n
M.
,
e
t
a
l.
,
”
P
a
ra
m
e
ter
a
c
c
e
p
t
a
n
c
e
o
f
so
f
t
w
a
re
d
e
v
e
lo
p
m
e
n
t
f
o
r
o
il
p
a
lm
f
ru
i
t
m
a
tu
rit
y
p
re
d
ictio
n
”
,
J
o
u
rn
a
l
o
f
S
o
ft
wa
re
E
n
g
i
n
e
e
rin
g
,
2
0
1
0
,
4
,
2
4
4
–
2
5
6
.
[1
3
]
Ch
o
o
n
g
,
T
.
;
A
b
b
a
s,
S
.
;
S
h
a
rif
f
,
A
.
;
Ha
li
m
,
R.
;
S
.
,
M
.
H.;
Yu
n
u
s
,
R.
;
A
li
,
S
.
;
a
h
m
a
d
u
n
,
F
.
R.
e
t
a
l.
,
“
Dig
it
a
l
i
m
a
g
e
p
ro
c
e
ss
in
g
o
f
p
a
lm
o
il
f
ru
it
s
”
,
In
t
e
rn
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Fo
o
d
En
g
in
e
e
rin
g
,
2
0
0
6
,
2
,
1
–
4.
[1
4
]
G
h
a
z
a
li
,
K.H.;
S
a
m
a
d
,
R.
;
A
rsh
a
d
,
N.W
.
;
Ka
ri
m
,
R.
A
.
e
t
a
l.
,
“
I
m
a
g
e
P
ro
c
e
ss
in
g
A
n
a
l
y
sis
o
f
Oil
P
a
lm
F
ru
it
s
f
o
r
A
u
to
m
a
ti
c
G
ra
d
in
g
”
,
In
tern
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
In
str
u
me
n
ta
ti
o
n
,
Co
n
tro
l
&
Au
to
ma
ti
o
n
,
Ba
n
d
u
n
g
,
In
d
o
n
e
sia
,
2
0
Oc
to
b
e
r
2
0
0
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
7
,
No
.
3
,
Sep
tem
b
e
r
20
1
8
:
11
1
–
11
8
118
[1
5
]
B.
S
a
ich
a
n
d
a
n
a
,
K.
S
ri
n
iv
a
s,
R.
Kira
n
Ku
m
a
r,
“
Clu
ste
rin
g
A
l
g
o
rit
h
m
c
o
m
b
in
e
d
w
it
h
Hill
Cli
m
b
in
g
f
o
r
C
las
sif
ic
a
ti
o
n
o
f
Re
m
o
te
S
e
n
sin
g
Im
a
g
e
s”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
(
IJ
ECE
)
,
v
o
l
4
,
No
.
6
,
p
p
9
2
3
-
9
3
0
.
[1
6
]
J.
Ha
rik
iran
,
P
.
V
.
L
a
k
sh
m
i,
R.
Kira
n
Ku
m
a
,”
M
u
lt
ip
le
F
e
a
t
u
re
F
u
z
z
y
c
-
m
e
a
n
s
Clu
ste
rin
g
A
l
g
o
rit
h
m
f
o
r
S
e
g
m
e
n
tatio
n
o
f
M
icro
a
rra
y
I
m
a
g
e
s
“
,
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
a
n
d
Co
m
p
u
ter
En
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
v
o
l
5
,
No
.
5
,
p
p
1
0
4
5
-
1
0
5
3
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
G
a
u
ra
n
g
S
P
a
tk
a
r
is
c
u
rre
n
tl
y
p
u
rsu
i
n
g
P
h
D
i
n
Co
m
p
u
ter
S
c
i
e
n
c
e
a
n
d
En
g
in
e
e
rin
g
a
t
V
IT
Un
iv
e
rsit
y
,
V
e
ll
o
re
.
He
re
c
e
i
v
e
d
h
is
B.
E
f
ro
m
G
o
a
Un
iv
e
rsit
y
in
2
0
0
5
a
n
d
M
.
T
e
c
h
(CS
E)
f
ro
m
V
isv
e
sh
v
a
ra
y
a
T
e
c
h
n
o
lo
g
ica
l
Un
iv
e
rsit
y
.
His
a
re
a
s
o
f
in
tere
st
in
c
lu
d
e
Im
a
g
e
P
ro
c
e
ss
in
g
,
F
u
z
z
y
lo
g
ic an
d
R
o
u
g
h
se
ts.
Dr.
G
.
S
.
G
.
N.
A
n
jan
e
y
u
lu
re
c
e
iv
e
d
B.
S
c
d
e
g
re
e
in
c
o
m
p
u
ter
sc
ien
c
e
w
i
th
M
a
th
e
m
a
ti
c
s,
f
ro
m
A
n
d
h
ra
Un
iv
e
rsity
,
V
ish
a
k
h
a
p
a
tn
a
m
in
1
9
9
6
,
M
.
S
c
i
n
M
a
th
e
m
a
ti
c
s
in
1
9
9
8
,
a
n
d
M
.
p
h
il
i
n
th
e
‘T
h
e
o
r
y
o
f
se
m
iri
n
g
s’
in
2
0
0
4
a
n
d
i
n
2
0
0
8
,
h
e
re
c
e
iv
e
d
h
is
P
h
.
D
in
‘Dig
it
a
l
S
ig
n
a
tu
re
s
Us
in
g
S
e
m
iri
n
g
S
tru
c
tu
re
s’
f
ro
m
S
.
V
.
Un
iv
e
rsit
y
,
T
iru
p
a
ti
,
In
d
ia.
He
h
a
s
Ei
g
h
tee
n
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
in
g
ra
d
u
a
te,
p
o
st
g
ra
d
u
a
te
a
n
d
E
n
g
in
e
e
rin
g
M
a
th
e
m
a
ti
c
s.
He
p
u
b
li
s
h
e
d
tw
e
n
ty
n
in
e
re
se
a
rc
h
p
a
p
e
rs
in
n
a
ti
o
n
a
l
a
n
d
in
tern
a
ti
o
n
a
l
jo
u
rn
a
ls.
He
a
lso
a
tt
e
n
d
e
d
n
a
t
io
n
a
l
a
n
d
in
ter
n
a
ti
o
n
a
l
c
o
n
f
e
re
n
c
e
s
f
o
r
p
re
se
n
t
in
g
re
se
a
rc
h
p
a
p
e
rs.
He
is
c
u
rre
n
tl
y
w
o
rk
in
g
a
s
p
ro
f
e
ss
o
r,
Div
isio
n
o
f
A
p
p
li
e
d
A
lg
e
b
ra
o
f
S
A
S
,
V
IT
Un
iv
e
rsit
y
,
v
e
ll
o
re
,
T
a
m
il
n
a
d
u
,
In
d
i
a
.
His c
u
rre
n
t
re
se
a
rc
h
in
tere
st
in
c
lu
d
e
s ‘Im
a
g
e
P
ro
c
e
ss
in
g
,
Cry
p
to
g
ra
p
h
y
,
Ne
t
w
o
rk
se
c
u
rit
y
,
A
l
g
e
b
ra
a
n
d
G
ra
p
h
T
h
e
o
ry
’.
Dr.
P
.
V
.
S
.
S
.
R.
C
h
a
n
d
ra
M
o
u
li
i
s
P
r
o
f
e
ss
o
r,
S
c
h
o
o
l
o
f
Co
m
p
u
ti
n
g
S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
(S
CS
E)
V
IT
Un
iv
e
rsity
,
T
a
m
il
N
a
d
u
,
I
n
d
ia.
He
o
b
tai
n
e
d
h
is
P
h
.
D.
d
e
g
re
e
f
ro
m
N
a
ti
o
n
a
l
In
stit
u
te
o
f
T
e
c
h
n
o
lo
g
y
(NI
T
)
T
rich
y
in
th
e
a
re
a
o
f
Dig
it
a
l
I
m
a
g
e
P
ro
c
e
ss
in
g
.
His
re
s
e
a
rc
h
in
tere
sts
in
c
lu
d
e
Dig
it
a
l
Im
a
g
e
P
ro
c
e
ss
in
g
,
Co
m
p
u
ter
Visio
n
,
P
a
tt
e
r
n
Re
c
o
g
n
it
io
n
,
Co
m
p
u
tati
o
n
a
l
In
telli
g
e
n
c
e
,
In
f
o
rm
a
ti
o
n
Re
tri
e
v
a
l
a
n
d
W
irele
ss
A
d
h
o
c
Ne
tw
o
rk
s.
He
e
x
e
c
u
ted
tw
o
re
se
a
rc
h
p
ro
jec
ts
sp
o
n
s
o
re
d
b
y
th
e
D
e
f
e
n
c
e
Re
s
e
a
rc
h
a
n
d
De
v
e
lo
p
m
e
n
t
Or
g
a
n
iza
ti
o
n
(DRD
O),
M
in
istry
o
f
De
f
e
n
c
e
,
G
o
v
t.
o
f
In
d
ia
d
u
ri
n
g
2
0
0
2
-
2
0
0
4
a
n
d
2
0
0
6
-
2
0
0
8
.
He
,
a
s
a
p
rin
c
ip
a
l
in
v
e
stig
a
to
r
h
a
s
b
a
g
g
e
d
a
th
ird
DRD
O
re
se
a
rc
h
p
ro
jec
t
i
n
to
h
is
c
re
d
it
.
He
is
a
m
e
m
b
e
r
o
f
v
a
rio
u
s
p
r
o
f
e
ss
io
n
a
l
b
o
d
ies
li
k
e
IEE
E,
IS
T
E,
b
e
sid
e
s
a
c
t
in
g
a
s
a
re
v
ie
w
e
r
a
n
d
e
d
it
o
ri
a
l
b
o
a
rd
m
e
m
b
e
r
f
o
r
v
a
rio
u
s
re
p
u
ted
in
tern
a
ti
o
n
a
l
jo
u
rn
a
ls an
d
c
o
n
f
e
re
n
c
e
s.
Evaluation Warning : The document was created with Spire.PDF for Python.