I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
8
,
No
.
2
,
A
p
r
il
201
8
,
p
p
.
989
~
9
9
5
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
8
i
2
.
p
p
9
8
9
-
9
9
5
989
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
JE
C
E
So
il
C
ha
ra
cter
i
z
a
tion a
nd
C
la
ss
ific
a
tion: A
H
y
brid
A
ppro
a
ch of
C
o
m
pu
ter
V
isio
n
a
nd
S
enso
r
N
e
tw
o
rk
Abrha
m
Deba
s
u M
eng
is
t
u
,
Da
g
na
chew
M
elese
w
Ale
m
a
y
ehu
De
p
a
rte
m
e
n
t
o
f
Co
m
p
u
ti
n
g
,
Ba
h
i
r
Da
r
Un
iv
e
rsit
y
,
Et
h
io
p
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Sep
9
,
2
0
1
7
R
ev
i
s
ed
Dec
2
5
,
2
0
1
7
A
cc
ep
ted
J
an
1
1
,
2
0
1
8
T
h
is
p
a
p
e
r
p
re
se
n
ts
so
il
c
h
a
ra
c
teriz
a
ti
o
n
a
n
d
c
las
sif
ica
ti
o
n
u
sin
g
c
o
m
p
u
ter
v
isio
n
&
se
n
so
r
n
e
tw
o
rk
a
p
p
ro
a
c
h
.
G
ra
v
it
y
A
n
a
lo
g
S
o
il
M
o
ist
u
re
S
e
n
so
r
w
it
h
a
rd
u
in
o
-
u
n
o
a
n
d
im
a
g
e
p
ro
c
e
ss
in
g
is
c
o
n
sid
e
re
d
f
o
r
c
las
si
f
i
c
a
ti
o
n
a
n
d
c
h
a
ra
c
teriz
a
ti
o
n
o
f
so
il
s.
F
o
r
t
h
e
d
a
ta
se
ts,
Am
h
a
ra
re
g
io
n
s
a
n
d
Ad
d
is
A
b
a
b
a
c
it
y
o
f
Et
h
io
p
ia
a
re
c
o
n
sid
e
re
d
f
o
r
th
is
s
tu
d
y
.
In
th
is
re
se
a
rc
h
p
a
p
e
r
th
e
to
tal
o
f
6
g
ro
u
p
o
f
so
il
a
n
d
e
a
c
h
h
a
v
i
n
g
9
0
im
a
g
e
s
a
re
u
se
d
.
T
h
a
t
is,
f
o
r
m
th
e
se
5
4
0
im
a
g
e
s
we
re
c
a
p
tu
re
d
.
On
c
e
th
e
d
a
tas
e
t
is
c
o
ll
e
c
ted
,
p
re
-
p
r
o
c
e
ss
in
g
a
n
d
n
o
ise
f
il
terin
g
ste
p
s
a
re
p
e
rf
o
rm
e
d
to
a
c
h
iev
e
th
e
g
o
a
l
o
f
th
e
st
u
d
y
th
ro
u
g
h
M
AT
LAB,
2
0
1
3
.
Clas
sif
ica
ti
o
n
a
n
d
c
h
a
ra
c
teriz
a
ti
o
n
is
p
e
rf
o
rm
e
d
th
ro
u
g
h
BP
NN
(Ba
c
k
-
p
ro
p
a
g
a
ti
o
n
n
e
u
ra
l
n
e
tw
o
rk
),
th
e
n
e
u
ra
l
n
e
tw
o
rk
c
o
n
sists
o
f
7
in
p
u
ts
f
e
a
tu
re
v
e
c
to
rs
a
n
d
6
n
e
u
ro
n
s
in
it
s
o
u
tp
u
t
lay
e
r
to
c
la
ss
ify
so
il
s.
8
9
.
7
%
a
c
c
u
ra
c
y
is
a
c
h
iev
e
d
w
h
e
n
b
a
c
k
-
p
ro
p
a
g
a
ti
o
n
n
e
u
ra
l
n
e
tw
o
rk
(BP
NN
)
is
u
se
d
.
K
ey
w
o
r
d
:
A
r
d
u
i
n
o
u
n
o
B
P
NN
C
o
m
p
u
ter
v
is
io
n
Sen
s
o
r
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
:
A
b
r
h
a
m
Deb
as
u
Me
n
g
i
s
t
u
,
Dep
ar
te
m
en
t o
f
C
o
m
p
u
ti
n
g
,
B
ah
ir
Dar
Un
iv
er
s
it
y
,
E
th
io
p
ia.
E
m
ail: a
b
r
h
a
m
d
@
b
d
u
.
ed
u
.
et
1.
I
NT
RO
D
UCT
I
O
N
Ag
r
icu
ltu
r
al
p
r
o
d
u
ctio
n
h
as
b
ee
n
h
ig
h
l
y
d
ep
en
d
en
t
o
n
n
atu
r
al
r
eso
u
r
ce
s
f
o
r
ce
n
t
u
r
ies.
T
h
e
m
ai
n
ten
a
n
ce
o
f
g
o
o
d
s
o
il
q
u
alit
y
is
v
ita
l
f
o
r
t
h
e
en
v
ir
o
n
m
e
n
tal
a
n
d
ec
o
n
o
m
ic
s
u
s
ta
in
ab
ilit
y
o
f
a
n
n
u
al
cr
o
p
p
in
g
.
A
d
ec
li
n
e
i
n
s
o
il
q
u
alit
y
h
as
a
m
ar
k
ed
i
m
p
ac
t
o
n
p
lan
t
g
r
o
w
t
h
an
d
y
ield
,
g
r
ai
n
q
u
alit
y
,
p
r
o
d
u
ctio
n
co
s
ts
a
n
d
th
e
i
n
cr
ea
s
ed
r
is
k
o
f
s
o
il
er
o
s
io
n
[
1
]
.
T
h
e
f
ield
o
f
C
o
m
p
u
ter
v
is
io
n
an
d
d
i
g
ital
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
(
DI
P
)
is
co
n
tin
u
o
u
s
l
y
ev
o
l
v
i
n
g
a
n
d
is
f
i
n
d
in
g
m
a
n
y
ap
p
licatio
n
s
i
n
s
e
v
er
al
f
ield
s
.
So
i
l
class
i
f
icatio
n
an
d
ch
ar
ac
ter
izatio
n
is
a
n
i
m
p
o
r
tan
t
asp
ec
t
o
f
g
eo
tech
n
ical
e
n
g
i
n
ee
r
in
g
w
h
ich
h
a
s
b
ee
n
g
i
v
e
n
a
g
r
ea
t
am
o
u
n
t
o
f
atten
tio
n
s
in
ce
th
e
p
ast
f
e
w
y
ea
r
s
.
I
m
a
g
e
d
ata
i
n
g
eo
s
ci
en
ce
s
ar
e
co
m
m
o
n
a
n
d
r
eq
u
ir
e
p
r
o
ce
s
s
in
g
a
n
d
m
ea
s
u
r
e
m
e
n
t
s
c
h
e
m
es
th
at
r
an
g
e
f
r
o
m
s
m
a
ll
m
icr
o
s
co
p
ic
s
ca
les
to
lar
g
e
r
e
m
o
te
s
e
n
s
in
g
s
ca
les.
T
h
e
y
f
o
cu
s
e
d
m
ai
n
l
y
to
t
h
e
f
ir
s
t
ca
te
g
o
r
y
an
d
s
p
ec
if
ical
l
y
in
i
m
ag
e
s
o
f
t
h
i
n
s
o
il
s
ec
tio
n
s
.
T
h
e
g
o
al
o
f
s
o
il
m
icr
o
m
o
r
p
h
o
lo
g
y
,
as
a
b
r
an
ch
o
f
s
o
il
s
cie
n
ce
,
is
th
e
d
escr
ip
tio
n
,
in
ter
p
r
etatio
n
,
a
n
d
m
ea
s
u
r
e
m
en
t
o
f
co
m
p
o
n
e
n
t
s
,
f
ea
t
u
r
es,
a
n
d
f
ab
r
ics
in
s
o
ils
a
t
a
m
icr
o
s
co
p
ic
lev
el.
I
n
t
h
is
p
ap
er
th
e
au
t
h
o
r
f
o
c
u
s
ed
o
n
t
ex
tu
r
e
an
al
y
s
is
a
n
d
s
eg
m
e
n
tatio
n
tec
h
n
iq
u
e
s
o
f
t
h
e
g
iv
e
n
s
o
il t
y
p
e
[
2
]
.
T
h
e
tech
n
o
lo
g
y
o
f
co
m
p
u
t
er
v
is
io
n
an
d
s
en
s
o
r
n
et
wo
r
k
ad
v
an
ce
m
e
n
t
is
g
r
ad
u
a
ll
y
f
i
n
d
in
g
ap
p
licatio
n
s
in
d
i
f
f
er
en
t
p
r
o
b
le
m
d
o
m
ai
n
s
li
k
e
i
n
th
e
ar
ea
s
o
f
h
ea
lt
h
an
d
GI
S
i
n
d
u
s
tr
ies
.
E
f
f
o
r
ts
ar
e
b
ein
g
g
ea
r
ed
to
w
ar
d
s
th
e
r
ep
lace
m
e
n
t
o
f
h
u
m
a
n
o
p
er
ato
r
w
ith
au
t
o
m
a
ted
s
y
s
te
m
s
,
as
h
u
m
an
o
p
er
atio
n
s
ar
e
u
s
u
all
y
in
co
n
s
is
te
n
t
an
d
n
o
n
ef
f
icie
n
t.
Au
to
m
ated
s
y
s
te
m
s
i
n
m
o
s
t
ca
s
es
ar
e
f
aster
an
d
m
o
r
e
p
r
ec
is
e.
Ho
w
e
v
er
,
th
er
e
ar
e
s
o
m
e
b
a
s
ic
i
n
f
r
astru
c
tu
r
es
th
at
m
u
s
t
n
ec
es
s
ar
il
y
b
e
i
n
p
l
ac
e
in
au
to
m
atio
n
.
I
n
t
h
is
r
ese
ar
ch
w
e
w
ill
ap
p
l
y
b
o
th
co
m
p
u
ter
v
i
s
io
n
a
n
d
s
en
s
o
r
n
et
w
o
r
k
to
ch
ar
ac
ter
ize
s
o
ils
an
d
clas
s
i
f
ies
s
o
il
t
y
p
e
s
o
as
p
r
o
p
er
m
ea
s
u
r
e
m
e
n
t
h
as to
b
e
tak
e
n
t
o
m
a
x
i
m
ize
t
h
e
ag
r
ic
u
lt
u
r
al
p
r
o
d
u
ctio
n
[
3
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
8
,
No
.
2
,
A
p
r
il
201
8
:
9
8
9
–
9
9
5
990
Dav
id
C
.
Ma
r
v
i
n
,
et
al
.
,
in
th
e
ir
w
o
r
k
s
tated
t
h
at
r
ec
en
t
r
e
s
e
ar
ch
o
n
s
e
n
s
o
r
n
et
w
o
r
k
s
h
a
s
f
o
cu
s
ed
o
n
n
et
w
o
r
k
i
n
g
tech
n
iq
u
e
s
an
d
n
e
t
w
o
r
k
ed
i
n
f
o
r
m
atio
n
p
r
o
ce
s
s
i
n
g
s
u
i
tab
le
f
o
r
h
i
g
h
l
y
d
y
n
a
m
i
c
en
v
ir
o
n
m
e
n
t
s
an
d
r
eso
u
r
ce
-
co
n
s
tr
ain
ed
s
en
s
o
r
n
o
d
es.
Sen
s
o
r
n
o
d
es
h
a
v
e
d
ec
r
ea
s
ed
in
s
ize
a
n
d
ar
e
m
u
c
h
c
h
ea
p
er
,
r
esu
lti
n
g
i
n
th
e
e
m
er
g
e
n
ce
o
f
m
an
y
n
e
w
c
iv
ilia
n
ap
p
licatio
n
s
f
r
o
m
e
n
v
ir
o
n
m
e
n
t
m
o
n
i
to
r
in
g
to
v
e
h
ic
u
l
ar
an
d
b
o
d
y
s
en
s
o
r
n
et
w
o
r
k
s
[
4
]
Min
g
y
u
a
n
Z
h
a
n
g
,
et
al
.
,
in
th
eir
w
o
r
k
en
t
itled
as
“A
p
p
l
y
i
n
g
Sen
s
o
r
-
B
ased
T
ec
h
n
o
lo
g
y
t
o
I
m
p
r
o
v
e
C
o
n
s
tr
u
ctio
n
Sa
f
et
y
Ma
n
ag
e
m
en
t
”
s
ta
ted
t
h
at
th
e
d
ev
elo
p
m
e
n
t
o
f
s
en
s
o
r
-
b
ased
tec
h
n
o
lo
g
ies
h
as
g
r
ea
tl
y
i
m
p
r
o
v
ed
in
f
o
r
m
atio
n
co
llecti
o
n
,
d
ata
tr
an
s
m
is
s
io
n
a
n
d
p
r
o
ce
s
s
i
n
g
,
w
h
ich
ca
n
s
er
v
e
as
th
e
f
o
u
n
d
atio
n
o
f
th
e
m
o
d
er
n
izatio
n
o
f
co
n
s
tr
u
ctio
n
s
af
et
y
m
an
a
g
e
m
e
n
t.
A
f
ter
n
e
ar
l
y
t
w
o
d
ec
ad
es
o
f
d
ev
elo
p
m
en
t,
s
e
n
s
o
r
-
b
ased
tech
n
o
lo
g
ies
h
a
v
e
f
ac
ilit
ated
t
h
e
tr
an
s
f
o
r
m
atio
n
f
r
o
m
ex
p
er
i
m
en
tal
e
x
p
lo
r
atio
n
to
p
r
ac
tical
ap
p
licatio
n
s
.
T
h
e
ap
p
licatio
n
s
o
f
s
e
n
s
o
r
-
b
a
s
ed
tech
n
o
lo
g
y
i
n
co
n
s
tr
u
ctio
n
s
a
f
et
y
m
a
n
a
g
e
m
en
t
h
a
v
e
b
ec
o
m
e
th
e
f
o
cu
s
o
f
c
u
r
r
en
t
r
esear
ch
[
5
]
.
I
n
th
is
r
esear
ch
w
o
r
k
,
co
m
p
u
ter
v
is
io
n
an
d
s
e
n
s
o
r
n
et
w
o
r
k
ar
e
co
n
s
id
er
ed
to
ch
ar
ac
ter
ize
s
o
ils
an
d
class
i
f
ie
s
s
o
il t
y
p
e
s
o
as p
r
o
p
er
m
ea
s
u
r
e
m
e
n
t h
a
s
to
b
e
tak
en
to
m
ax
i
m
ize
t
h
e
a
g
r
icu
lt
u
r
al
p
r
o
d
u
ctio
n
.
Dep
en
d
in
g
o
n
th
e
k
n
o
w
led
g
e
an
d
ex
p
er
ien
ce
o
f
t
h
e
ex
p
er
t
i
t
is
d
if
f
ic
u
lt
to
ch
ar
ac
ter
ize
an
d
class
if
y
s
o
il.
So
Dif
f
er
e
n
t
m
et
h
o
d
s
h
a
v
e
b
ee
n
u
s
ed
to
class
i
f
y
s
o
il
t
o
th
eir
co
r
r
esp
o
n
d
in
g
clas
s
an
d
ch
ar
ac
ter
ize
th
e
m
o
is
t
u
r
e
lev
el.
P
r
av
at
Ku
m
ar
Sh
it
,
et
al
.,
co
n
d
u
cted
a
s
tu
d
y
to
esti
m
ate
s
o
il
cr
ac
k
f
o
r
m
o
is
tu
r
e
an
al
y
s
i
s
,
f
r
o
m
th
e
ex
p
er
i
m
en
t
7
2
.
7
%
is
ar
ch
i
v
ed
[
6
].
K.
Sru
n
ith
a,
e
t
al
.
,
co
n
d
u
cted
a
s
t
u
d
y
to
class
if
y
s
o
i
l.
T
h
e
au
th
o
r
s
h
a
v
e
u
s
ed
tex
t
u
r
e
an
d
co
lo
r
as
a
f
ea
tu
r
e
v
ec
to
r
an
d
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
to
class
i
f
y
s
o
il
t
y
p
e
s
.
B
esid
es,
th
e
y
s
tated
th
at,
S
o
il
ch
ar
ac
ter
is
ti
cs
id
en
ti
f
icatio
n
a
n
d
class
i
f
ic
atio
n
is
v
er
y
i
m
p
o
r
tan
t
i
n
a
g
r
icu
l
tu
r
e
to
av
o
id
ag
r
icu
l
tu
r
al
p
r
o
d
u
ct
q
u
a
n
tit
y
l
o
s
s
[
7
]
.
T
h
er
ef
o
r
e
t
h
is
p
ap
er
f
o
cu
s
ed
o
n
clas
s
if
icatio
n
a
n
d
ch
ar
ac
ter
izatio
n
o
f
s
o
il
u
s
in
g
a
h
y
b
r
id
ap
p
r
o
ac
h
es o
f
co
m
p
u
ter
v
i
s
io
n
a
n
d
s
en
s
o
r
n
et
w
o
r
k
ap
p
r
o
ac
h
es.
2.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
Dif
f
er
en
t
r
esear
c
h
er
s
h
a
v
e
b
ee
n
co
n
d
u
cted
th
eir
r
esear
c
h
es
i
n
ap
p
licatio
n
o
f
co
m
p
u
ter
v
is
io
n
tech
n
iq
u
es r
elate
d
to
ag
r
ic
u
lt
u
r
e.
T
h
ese
ar
e
d
is
cu
s
s
ed
as f
o
ll
o
w
.
Ash
o
k
an
d
Sn
e
h
a
m
o
y
,
i
n
t
h
eir
w
o
r
k
e
n
tit
led
as
“Co
m
p
u
ter
v
i
s
io
n
-
b
ased
li
m
es
to
n
e
r
o
ck
-
t
y
p
e
class
i
f
icatio
n
u
s
i
n
g
p
r
o
b
ab
ilis
tic
n
e
u
r
al
n
et
w
o
r
k
”
p
r
ese
n
ted
R
o
ck
-
t
y
p
e
id
e
n
ti
f
icatio
n
f
o
r
l
i
m
e
s
to
n
e
m
i
n
e.
I
n
th
is
p
ap
er
,
a
co
m
p
u
ter
v
i
s
io
n
b
ased
r
o
ck
t
y
p
e
cla
s
s
i
f
ica
t
io
n
s
y
s
te
m
i
s
p
r
o
p
o
s
ed
w
it
h
o
u
t
h
u
m
a
n
i
n
ter
v
en
tio
n
u
s
i
n
g
p
r
o
b
ab
ilis
tic
n
e
u
r
al
n
et
w
o
r
k
(
P
NN)
.
I
n
t
h
is
r
esear
c
h
p
ap
er
th
e
au
th
o
r
s
ar
e
u
s
ed
t
h
e
co
lo
r
h
is
to
g
r
a
m
f
ea
t
u
r
es a
s
an
in
p
u
t.
I
n
t
h
e
p
ap
er
th
e
co
lo
r
i
m
a
g
e
h
is
to
g
r
a
m
b
ased
f
ea
t
u
r
es i
n
cl
u
d
es
w
ei
g
h
te
d
m
ea
n
,
s
k
e
w
n
e
s
s
an
d
k
u
r
to
s
i
s
f
ea
t
u
r
es
ar
e
ex
tr
ac
ted
f
o
r
all
th
r
ee
co
l
o
r
s
p
ac
e
r
ed
,
g
r
ee
n
,
an
d
b
lu
e.
I
n
th
is
p
ap
er
,
a
t
o
tal
n
in
e
f
ea
t
u
r
es
ar
e
u
s
ed
as
i
n
p
u
t
f
o
r
th
e
P
NN
class
i
f
ica
tio
n
m
o
d
el.
T
h
en
t
h
e
y
f
o
u
n
d
o
u
t
th
e
er
r
o
r
r
ate
f
o
r
id
en
ti
f
icatio
n
i
s
b
elo
w
6
%
[
8
]
.
An
a
s
tasi
a
&
P
etr
o
s
,
p
r
esen
ted
s
o
il
i
m
ag
e
s
eg
m
e
n
tatio
n
a
n
d
tex
t
u
r
e
an
al
y
s
i
s
u
s
i
n
g
co
m
p
u
ter
v
i
s
io
n
ap
p
r
o
ac
h
.
T
h
e
au
th
o
r
p
r
o
p
o
s
ed
j
o
in
t
i
m
a
g
e
s
eg
m
e
n
tatio
n
m
et
h
o
d
s
f
o
r
s
o
il
i
m
a
g
es
an
d
f
ea
t
u
r
e
m
ea
s
u
r
e
m
en
t
s
[
9
].
Su
n
–
o
k
ch
u
n
g
,
et
al
.
,
s
t
u
d
ied
So
il
T
ex
tu
r
e
C
las
s
if
ic
atio
n
A
l
g
o
r
ith
m
U
s
i
n
g
R
GB
C
h
ar
a
cter
is
tics
o
f
So
il
I
m
a
g
es.
T
h
e
au
t
h
o
r
s
f
o
u
n
d
th
at
s
o
il
tex
tu
r
e
h
as
tr
ad
it
io
n
all
y
b
ee
n
d
eter
m
i
n
ed
in
th
e
lab
o
r
ato
r
y
u
s
in
g
p
ip
ette
an
d
h
y
d
r
o
m
eter
m
e
th
o
d
s
th
a
t r
eq
u
ir
e
a
co
n
s
id
er
ab
le
a
m
o
u
n
t o
f
t
i
m
e,
lab
o
r
,
an
d
e
x
p
en
s
e.
I
n
t
h
is
p
ap
er
,
s
o
il
tex
t
u
r
e
class
i
f
icatio
n
u
s
in
g
R
GB
h
i
s
to
g
r
a
m
s
w
as
i
n
v
e
s
t
ig
ated
to
s
o
lv
e
th
e
ab
o
v
e
m
e
n
tio
n
ed
p
r
o
b
lem
.
I
n
th
is
p
ap
er
,
w
h
e
n
s
o
ils
w
er
e
class
i
f
ied
u
s
i
n
g
USD
A
s
o
il
t
ex
tu
r
e
cla
s
s
i
f
ica
tio
n
,
t
h
e
lab
o
r
ato
r
y
m
et
h
o
d
an
d
i
m
a
g
e
p
r
o
ce
s
s
in
g
m
eth
o
d
p
r
o
d
u
ce
d
th
e
s
a
m
e
r
esu
lts
f
o
r
4
8
% o
f
th
e
s
a
m
p
le
s
[
10
]
Ma
łg
o
r
za
ta
an
d
P
io
tr
,
in
t
h
is
r
esear
ch
p
ap
er
th
e
au
th
o
r
s
h
av
e
s
h
o
w
n
t
h
at
d
etec
tio
n
o
f
s
o
il
p
o
r
e
s
tr
u
ct
u
r
e
u
s
i
n
g
a
n
i
m
a
g
e
s
e
g
m
e
n
tat
io
n
ap
p
r
o
ac
h
.
I
n
th
is
s
tu
d
y
,
a
d
e
n
s
i
t
y
b
ased
cl
u
s
ter
in
g
m
et
h
o
d
o
n
to
m
o
g
r
ap
h
y
s
ec
tio
n
s
o
f
s
o
il is
co
n
s
id
er
ed
[
11
].
B
h
a
w
n
a
,
et
al
.
,
s
t
u
d
ied
d
eter
m
i
n
atio
n
o
f
So
il
p
H
b
y
u
s
in
g
Dig
ital
I
m
ag
e
P
r
o
ce
s
s
i
n
g
T
ec
h
n
iq
u
e.
I
n
Ag
r
icu
ltu
r
e
s
ec
to
r
th
e
p
ar
a
m
e
ter
s
lik
e
q
u
an
tit
y
an
d
q
u
a
lit
y
o
f
p
r
o
d
u
ct
ar
e
th
e
i
m
p
o
r
ta
n
t
m
ea
s
u
r
es
f
r
o
m
t
h
e
f
ar
m
er
s
’
p
o
in
t
o
f
v
ie
w
.
So
il
is
r
ec
o
g
n
ized
as
o
n
e
o
f
th
e
m
o
s
t
v
al
u
ab
le
n
at
u
r
al
r
eso
u
r
ce
w
h
o
s
e
s
o
il
p
H
p
r
o
p
er
ty
u
s
ed
to
d
escr
ib
e
th
e
d
eg
r
ee
o
f
ac
id
it
y
o
r
b
asicit
y
w
h
ic
h
af
f
ec
t
s
n
u
tr
ien
t
av
ailab
ilit
y
a
n
d
u
lti
m
ate
l
y
p
lan
t g
r
o
w
t
h
[
1
2
]
.
A
li
M
,
et
al
.
,
i
n
t
h
is
r
esear
c
h
p
ap
er
,
I
m
ag
e
te
x
t
u
r
e
an
al
y
s
i
s
an
d
n
e
u
r
al
n
et
w
o
r
k
s
f
o
r
ch
ar
ac
ter
izatio
n
o
f
u
n
if
o
r
m
s
o
ils
ar
e
s
t
u
d
ied
.
Su
p
er
v
i
s
ed
b
ac
k
-
p
r
o
p
ag
atio
n
n
eu
r
al
n
et
w
o
r
k
is
u
s
ed
f
o
r
th
i
s
s
tu
d
y
.
T
h
e
au
th
o
r
s
h
av
e
te
s
ted
n
e
u
r
al
n
et
w
o
r
k
w
it
h
co
n
s
id
er
ab
le
ac
cu
r
ac
y
[
1
3
].
U
m
es
h
K
,
et
al
.
,
i
n
t
h
is
p
ap
er
th
e
au
th
o
r
s
p
r
ese
n
ted
“
T
esti
n
g
o
f
Ag
r
icu
l
tu
r
e
So
il
b
y
Di
g
ital
I
m
a
g
e
P
r
o
ce
s
s
in
g
”.
T
h
is
p
ap
er
h
elp
s
to
d
eter
m
i
n
e
th
e
a
m
o
u
n
t
o
f
f
er
tili
ze
r
an
d
p
H
o
f
s
o
il
th
at
m
u
s
t
b
e
ap
p
lied
.
8
0
s
o
il
s
a
m
p
le
s
th
eir
p
H
v
al
u
e
te
s
ted
in
g
o
v
er
n
m
en
t
s
o
il
test
i
n
g
L
ab
ar
e
co
n
s
id
er
ed
in
th
i
s
s
t
u
d
y
.
I
n
t
h
eir
w
o
r
k
,
w
h
e
n
th
e
s
o
f
t
w
ar
e
is
te
s
ted
th
e
s
o
f
t
w
ar
e
g
i
v
e
s
6
0
-
7
0
% a
cc
u
r
ac
y
[
1
4
].
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
S
o
il C
h
a
r
a
cteriz
a
tio
n
a
n
d
C
la
s
s
ifica
tio
n
:
A
Hyb
r
id
A
p
p
r
o
a
c
h
o
f Co
mp
u
ter …
.
(
A
b
r
h
a
m
D
eb
a
s
u
Men
g
is
tu
)
991
A.
V.
B
ilg
i
li
,
et
al
.
,
s
t
u
d
ied
o
n
w
a
v
elet
An
al
y
s
is
o
f
s
o
il
r
ef
lecta
n
ce
f
o
r
t
h
e
c
h
ar
a
cter
izati
o
n
o
f
s
o
il
p
r
o
p
er
ties
.
T
h
e
au
t
h
o
r
s
h
a
v
e
u
s
ed
W
a
v
elet
a
n
al
y
s
i
s
,
h
y
p
er
s
p
ec
tr
al
n
ea
r
-
i
n
f
r
ar
ed
(
NI
R
)
an
d
m
id
-
i
n
f
r
ar
ed
(
MI
R
)
r
ef
lecta
n
ce
s
p
ec
tr
a
o
f
s
o
il
m
ater
ial
to
ch
ar
ac
ter
ize
th
e
g
iv
e
n
s
o
il [
1
5
].
M.
B
ar
b
e
r
,
et
al
.
,
in
th
eir
w
o
r
k
en
titl
ed
as
“A
No
v
el
m
eth
o
d
f
o
r
2
-
D
Ag
r
icu
ltu
r
al
s
o
il
r
o
u
g
h
n
e
s
s
ch
ar
ac
ter
izatio
n
b
ased
o
n
a
laser
s
ca
n
n
in
g
tec
h
n
iq
u
e”
p
r
esen
ted
laser
p
r
o
f
iler
th
e
d
eter
m
i
n
atio
n
o
f
ag
r
icu
l
tu
r
al
s
o
il
r
o
u
g
h
n
es
s
.
W
h
en
test
ed
w
it
h
th
e
R
MS
h
e
ig
h
t
S
an
d
co
r
r
elatio
n
len
g
t
h
L
i
n
1
m
x
0
,
3
m
p
ar
ce
ls
w
it
h
a
2
0
-
3
0
% e
r
r
o
r
in
h
eig
h
t
s
an
d
1
-
10%
er
r
o
r
in
h
o
r
izo
n
tal
len
g
t
h
s
[
1
6
].
R
ich
ar
d
J
.
Fla
v
el
,
et
al
.
,
s
tu
d
ie
d
ab
o
u
t th
e
ap
p
licatio
n
s
o
f
i
m
ag
e
p
r
o
ce
s
s
i
n
g
a
n
d
a
n
al
y
s
i
s
i
n
p
lan
t r
o
o
t
s
y
s
te
m
s
i
n
s
o
il u
s
i
n
g
i
m
a
g
eJ
p
lat
f
o
r
m
.
T
h
e
au
t
h
o
r
s
h
a
v
e
u
s
e
d
x
-
r
a
y
to
m
o
g
r
ap
h
y
3
D
i
m
a
g
e
s
[
1
7
]
.
Ma
łg
o
r
za
ta
C
h
ar
y
ta
n
o
w
icz
an
d
P
io
tr
Ku
lczy
c
k
i,
i
n
th
eir
w
o
r
k
e
n
titl
ed
as,
“A
n
I
m
ag
e
An
al
y
s
i
s
A
l
g
o
r
ith
m
f
o
r
So
il
Str
u
ct
u
r
e
I
d
en
tific
atio
n
”
th
e
au
th
o
r
s
p
r
esen
ted
an
i
m
ag
e
s
e
g
m
en
t
atio
n
ap
p
r
o
ac
h
f
o
r
d
etec
tin
g
t
h
e
s
o
il
p
o
r
e
s
tr
u
ct
u
r
es
th
at
h
av
e
b
ee
n
s
tu
d
ied
b
y
w
a
y
o
f
s
o
il
to
m
o
g
r
ap
h
y
s
ec
t
io
n
s
.
I
n
t
h
is
p
ap
er
,
d
en
s
it
y
-
b
a
s
ed
clu
s
ter
i
n
g
an
d
n
o
n
p
ar
a
m
etr
ic
k
er
n
el
esti
m
atio
n
m
et
h
o
d
s
h
ad
b
ee
n
c
o
n
s
id
er
ed
f
o
r
th
is
s
tu
d
y
[1
8
]
.
Ma
s
a
y
u
k
i
T
am
u
r
a
an
d
W
eip
in
g
L
i,
s
t
u
d
ied
d
etec
tio
n
o
f
s
o
il
liq
u
ef
ac
tio
n
ar
ea
s
in
ca
s
e
o
f
Kan
to
u
r
eg
io
n
o
f
J
ap
an
.
I
n
t
h
is
p
ap
er
,
m
u
lti
-
te
m
p
o
r
al
P
A
L
S
A
R
co
h
e
r
en
ce
d
ata
is
co
n
s
id
er
ed
[
1
9
]
.
K.
Sru
n
it
h
a
a
n
d
S.
P
ad
m
a
v
at
h
i,
s
t
u
d
ied
th
e
p
er
f
o
r
m
a
n
ce
o
f
SVM
f
o
r
s
o
il
c
lass
if
ica
tio
n
u
s
in
g
i
m
a
g
e
p
r
o
ce
s
s
in
g
tec
h
n
iq
u
e
s
.
I
n
th
is
r
esear
ch
p
ap
er
,
th
e
au
th
o
r
s
s
tated
th
at
s
o
il
c
h
ar
ac
ter
is
tic
s
id
en
tific
atio
n
a
n
d
class
i
f
icatio
n
is
v
er
y
m
u
ch
i
m
p
o
r
tan
t
an
d
h
elp
s
to
av
o
id
ag
r
icu
lt
u
r
al
p
r
o
d
u
ct
q
u
an
tit
y
lo
s
s
.
T
h
e
au
th
o
r
s
h
a
v
e
u
s
ed
i
m
a
g
e
ac
q
u
is
itio
n
,
i
m
a
g
e
p
r
ep
r
o
ce
s
s
in
g
,
f
ea
t
u
r
e
e
x
tr
ac
t
io
n
a
n
d
clas
s
if
icatio
n
.
T
ex
t
u
r
e
an
d
co
lo
r
f
ea
tu
r
e
ar
e
co
n
s
id
er
ed
f
o
r
f
ea
tu
r
e
v
ec
t
o
r
;
tex
tu
r
e
f
ea
tu
r
e
ar
e
ex
tr
ac
ted
u
s
i
n
g
lo
w
p
as
s
f
i
lter
an
d
Ga
b
o
r
f
ilter
.
B
esid
es,
co
lo
r
f
ea
tu
r
es a
r
e
ex
tr
ac
ted
u
s
i
n
g
H
SV[
20
].
A
cc
o
r
d
in
g
to
Mr
u
t
y
u
n
j
a
y
a
R
.
Dh
ar
w
ad
,
et
al
.
,
Mo
is
tu
r
e
co
n
t
en
t i
n
s
o
il is
o
n
e
o
f
t
h
e
m
a
in
c
o
m
p
o
n
en
t
w
h
ic
h
p
la
y
s
i
m
p
o
r
tan
t
r
o
le
in
y
ield
o
f
cr
o
p
s
.
I
n
th
i
s
p
ap
er
t
h
e
a
u
th
o
r
s
f
o
c
u
s
ed
o
n
s
o
f
t
w
ar
e
d
ev
elo
p
m
e
n
t
f
o
r
s
o
il
m
o
is
tu
r
e
as
s
es
s
m
e
n
t.
T
h
e
m
ai
n
o
b
j
ec
tiv
e
o
f
th
e
a
u
t
h
o
r
s
w
a
s
to
tu
r
n
th
e
m
a
n
u
al
p
r
o
ce
s
s
to
a
s
o
f
t
w
ar
e
ap
p
licatio
n
u
s
i
n
g
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
tec
h
n
iq
u
e.
I
m
a
g
e
o
f
th
e
s
o
il
w
i
th
d
i
f
f
er
e
n
t
m
o
i
s
tu
r
e
co
n
ten
t
ar
e
co
llected
an
d
p
r
ep
r
o
ce
s
s
ed
to
r
em
o
v
e
th
e
n
o
is
e
o
f
s
o
u
r
ce
i
m
a
g
e.
T
h
e
au
th
o
r
s
h
a
v
e
u
s
ed
co
lo
r
an
d
tex
tu
r
e
f
ea
t
u
r
e
v
ec
to
r
as a
n
i
n
p
u
t i
n
s
o
il
m
o
i
s
t
u
r
e
ass
ess
m
en
t
s
o
f
t
w
ar
e
[
21
]
.
San
j
a
y
Ku
m
a
w
at
,
et
al
.
,
in
th
e
ir
w
o
r
k
s
tated
th
at
t
h
e
f
ar
m
er
s
a
r
e
s
u
f
f
er
in
g
f
r
o
m
t
h
e
lack
o
f
r
ain
s
an
d
s
ca
r
cit
y
o
f
w
ate.
I
n
th
is
p
ap
er
,
th
e
m
a
in
o
b
j
ec
tiv
e
w
a
s
to
p
r
o
v
id
e
an
au
to
m
atic
ir
r
ig
ati
o
n
s
y
s
te
m
t
h
er
eb
y
s
av
i
n
g
ti
m
e,
m
o
n
e
y
&
p
o
w
er
o
f
th
e
f
ar
m
er
.
I
n
t
h
is
w
o
r
k
m
o
is
tu
r
e
s
e
n
s
o
r
s
ar
e
co
n
s
id
er
ed
an
ad
in
s
talled
o
n
th
e
f
ield
.
W
h
e
n
ev
er
t
h
er
e
i
s
a
c
h
an
g
e
in
w
ater
co
n
te
n
t
o
f
s
o
il
th
ese
s
e
n
s
o
r
s
s
e
n
s
e
t
h
e
ch
a
n
g
e
g
i
v
es
a
n
i
n
ter
r
u
p
t
s
ig
n
al
to
th
e
m
icr
o
-
co
n
tr
o
ller
Fo
r
ca
p
tu
r
in
g
th
e
i
m
a
g
es,
t
h
e
p
h
o
n
e
ca
m
er
a
is
u
s
ed
an
d
af
ter
p
r
o
ce
s
s
in
g
th
e
ca
p
tu
r
ed
i
m
ag
e
t
h
e
P
H
v
alu
e
o
f
th
e
s
o
il
i
s
d
eter
m
in
ed
an
d
a
cc
o
r
d
in
g
l
y
cr
o
p
s
o
r
p
lan
ts
ar
e
s
u
g
g
e
s
ted
th
at
ca
n
b
e
g
r
o
w
n
i
n
t
h
at
f
ield
[
2
2
]
.
Ni
m
i
s
h
a
Si
n
g
h
a
n
d
R
an
a
Gill
R
eti
n
al,
s
tu
d
ied
o
n
id
en
ti
f
icat
io
n
o
f
R
eti
n
al
d
is
ea
s
e
I
n
th
i
s
p
ap
er
,
th
e
au
th
o
r
s
h
a
v
e
p
r
o
p
o
s
ed
th
e
s
e
g
m
en
tatio
n
an
d
u
s
e
m
ac
h
in
e
le
a
r
n
in
g
ap
p
r
o
ac
h
es
to
d
etec
t
th
e
tr
u
e
r
etin
al
p
ar
t i
n
ad
d
itio
n
th
e
y
s
tated
t
h
at
p
r
ep
r
o
ce
s
s
in
g
i
s
d
o
n
e
o
n
th
e
o
r
ig
in
al
i
m
a
g
e
u
s
in
g
Ga
m
m
a
No
r
m
aliza
tio
n
w
h
ic
h
h
elp
s
to
e
n
h
an
ce
th
e
i
m
a
g
e
th
at
ca
n
g
i
v
es
d
etail
in
f
o
r
m
a
tio
n
ab
o
u
t
t
h
e
i
m
a
g
e
t
h
e
n
t
h
e
s
eg
m
e
n
tatio
n
i
s
p
er
f
o
r
m
ed
o
n
t
h
e
Ga
m
m
a
No
r
m
alize
d
i
m
a
g
e
b
y
S
u
p
er
p
ix
el
m
et
h
o
d
.
Fin
all
y
f
ea
t
u
r
e
g
e
n
er
atio
n
m
u
s
t
b
e
d
o
n
e
an
d
m
ac
h
in
e
lear
n
i
n
g
ap
p
r
o
ac
h
h
elp
s
to
e
x
tr
ac
t tr
u
e
r
eti
n
al
a
r
ea
an
d
9
6
% a
cc
u
r
ac
y
i
s
ac
h
ie
v
ed
[2
3
]
.
Her
u
P
u
r
n
o
m
o
I
p
u
n
g
,
Ha
n
d
ay
an
i
T
j
an
d
r
asa,
in
th
i
s
p
ap
er
th
e
au
t
h
o
r
s
f
o
c
u
s
ed
o
n
an
u
r
b
an
r
o
ad
m
ater
ials
v
is
io
n
s
y
s
te
m
u
s
in
g
n
ar
r
o
w
b
an
d
n
ea
r
in
f
r
ar
ed
i
m
ag
i
n
g
.
T
h
is
p
ap
er
p
r
o
p
o
s
ed
im
a
g
i
n
g
i
n
d
ex
e
s
ev
alu
a
tio
n
f
r
o
m
e
x
p
er
i
m
e
n
t
r
esu
lt
s
to
id
en
tify
t
h
o
s
e
u
r
b
an
r
o
ad
m
ater
ials
.
T
h
e
p
r
o
p
o
s
ed
m
u
lti
-
s
p
ec
tr
al
i
m
a
g
in
g
i
n
d
ex
e
s
w
er
e
ab
le
to
s
h
o
w
t
h
e
p
o
ten
tial
to
clas
s
if
y
t
h
e
s
elec
ted
u
r
b
an
r
o
ad
m
ater
ials
,
an
o
t
h
er
ap
p
r
o
ac
h
m
a
y
n
ee
d
to
clea
r
l
y
d
is
tin
g
u
is
h
b
et
w
ee
n
co
n
cr
ete
an
d
ag
g
r
e
g
ates
[
2
4
]
.
3.
RE
S
E
ARCH
M
E
T
H
O
DS
T
o
c
o
llect
th
e
d
ata
s
e
t
C
a
n
o
n
E
OS
Di
g
ital
a
n
d
I
P
ca
m
er
a
is
u
s
ed
to
ca
p
t
u
r
e
th
e
i
m
a
g
e
d
ir
ec
tl
y
,
a
n
d
b
o
th
v
id
eo
an
d
o
f
f
li
n
e
i
m
a
g
e
s
ar
e
in
cl
u
d
ed
in
o
r
d
er
to
h
av
e
a
g
o
o
d
d
ata
s
et
f
o
r
m
all
p
er
s
p
ec
tiv
e.
T
h
e
d
at
a
co
n
tain
s
n
o
is
e
s
b
ec
au
s
e
t
h
e
y
w
er
e
ca
p
tu
r
ed
in
u
n
co
n
tr
o
lled
en
v
ir
o
n
m
e
n
ts
.
Ha
v
i
n
g
s
u
c
h
t
y
p
e
s
o
f
d
ata
s
et,
it
w
a
s
v
er
y
h
e
lp
f
u
l
to
class
i
f
y
a
n
d
ch
ar
ac
ter
ize
th
e
g
i
v
en
s
o
il
.
T
h
is
s
tu
d
y
ca
r
r
ied
o
u
t
o
n
Am
h
ar
a
an
d
Or
o
m
ia
r
eg
io
n
s
o
f
E
th
io
p
ia,
lo
ca
ted
at
n
o
r
th
er
n
a
n
d
s
o
u
t
h
er
n
p
ar
t o
f
E
th
io
p
ia.
T
h
e
to
tal
o
f
6
g
r
o
u
p
o
f
s
o
il
a
n
d
ea
ch
h
a
v
in
g
9
0
i
m
ag
e
s
ar
e
co
n
s
id
er
ed
f
o
r
th
is
s
tu
d
y
.
Th
at
is
,
f
o
r
m
th
ese
5
4
0
i
m
ag
e
s
w
er
e
r
ec
o
r
d
.
I
n
ad
d
itio
n
,
ea
ch
im
a
g
e
s
s
ize
is
2
5
6
b
y
2
5
6
is
tak
en
.
On
ce
th
e
d
ata
s
et
co
llected
,
p
r
e
-
p
r
o
ce
s
s
in
g
a
n
d
n
o
is
e
f
ilter
i
n
g
s
tep
s
ar
e
p
er
f
o
r
m
ed
to
ac
h
ie
v
e
t
h
e
g
o
al
o
f
th
e
s
t
u
d
y
t
h
r
o
u
g
h
MA
T
L
A
B
,
2
0
1
4
.
T
h
e
o
th
er
p
ar
t
is
m
ea
s
u
r
in
g
th
e
m
o
i
s
tu
r
e
lev
el
o
f
s
o
il
u
s
in
g
s
en
s
o
r
.
I
n
t
h
is
s
t
u
d
y
,
Gr
a
v
it
y
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
8
,
No
.
2
,
A
p
r
il
201
8
:
9
8
9
–
9
9
5
992
An
alo
g
So
il M
o
is
t
u
r
e
Se
n
s
o
r
i
s
co
n
s
id
er
ed
b
ec
au
s
e
t
h
i
s
s
e
n
s
o
r
is
ea
s
y
to
i
n
ter
f
ac
e.
B
esid
es
,
AR
DUI
NO
UN
O
is
u
s
ed
to
in
ter
f
ac
e
m
o
is
t
u
r
e
s
en
s
o
r
an
d
s
k
etch
n
o
v
AR
DUI
NO
I
DE
is
u
s
ed
to
p
r
o
g
r
a
m
m
o
is
tu
r
e
s
e
n
s
o
r
.
4.
SO
I
L
CH
AR
ACT
E
R
I
Z
A
T
I
O
N
AND
CL
A
SS
I
F
I
CA
T
I
O
N
So
il
ch
ar
ac
ter
izatio
n
an
d
clas
s
if
icatio
n
s
y
s
te
m
co
n
s
i
s
ts
o
f
t
h
r
ee
b
asic
p
ar
ts
:
co
m
p
u
ter
v
i
s
i
o
n
,
s
en
s
o
r
an
d
clas
s
if
icatio
n
.
T
h
e
i
m
a
g
es
o
f
s
o
il
s
a
m
p
les
w
er
e
ca
p
t
u
r
ed
in
d
i
f
f
er
en
t
ar
ea
s
o
f
E
t
h
io
p
ia.
B
ac
k
-
P
r
o
p
ag
atio
n
A
r
ti
f
icial
n
u
er
al
n
et
w
o
r
k
w
a
s
u
s
ed
f
o
r
clas
s
i
f
icatio
n
an
d
c
h
ar
ac
ter
izatio
n
o
f
i
m
ag
e
s
i
n
to
d
if
f
er
e
n
t
cla
s
s
e
s
a
s
s
h
o
w
n
in
F
ig
u
r
e
1
.
Fig
u
r
e
1
.
So
il c
h
ar
ac
ter
izatio
n
&
class
if
icatio
n
m
o
d
el
4
.
1
.
Co
m
pu
t
er
Vis
io
n
T
h
e
i
m
a
g
es
o
f
s
o
il
s
a
m
p
le
wer
e
co
llected
in
Go
n
d
er
,
Me
t
e
m
a,
Dej
en
an
d
A
d
d
is
A
b
ab
a
ar
ea
s
o
f
E
th
io
p
ia.
T
o
h
av
e
th
e
s
a
m
e
i
llu
m
i
n
atio
n
a
n
d
te
m
p
er
atu
r
e
i
m
ag
e
s
ar
e
r
ec
o
r
d
ed
in
b
o
th
i
n
t
h
e
m
o
r
n
i
n
g
a
n
d
af
ter
n
o
o
n
ti
m
e.
I
n
t
h
is
s
t
u
d
y
,
b
o
th
o
f
f
lin
e
c
ap
tu
r
ed
an
d
o
n
l
i
n
e
ca
p
tu
r
ed
i
m
ag
e
s
ar
e
co
n
s
id
er
ed
th
is
h
elp
s
u
s
to
en
h
a
n
ce
t
h
e
co
m
p
u
ter
v
is
io
n
s
y
s
te
m
.
Af
ter
ca
p
tu
r
i
n
g
t
h
e
i
m
ag
e
th
e
n
e
x
t
s
tep
is
e
n
h
a
n
ci
n
g
th
e
co
n
tr
ast
o
f
th
e
i
m
a
g
e
a
n
d
r
esi
zi
n
g
t
h
e
i
m
a
g
e
to
2
5
6
b
y
2
5
6
.
T
h
e
o
th
er
s
tep
in
t
h
i
s
p
ar
t
i
s
e
x
tr
a
cti
n
g
r
ep
r
esen
ti
n
g
f
ea
t
u
r
es.
I
n
th
is
p
ap
er
,
h
s
v
Hi
s
t,
au
to
C
o
r
r
elo
g
r
a
m
co
lo
r
_
m
o
m
e
n
ts
,
m
e
an
Am
p
l
itu
d
e,
m
s
E
n
er
g
y
,
w
a
v
elet_
m
o
m
e
n
ts
ar
e
ex
tr
ac
ted
f
r
o
m
t
h
e
i
m
a
g
e
an
d
m
o
is
t
u
r
es
ar
e
ex
tr
ac
ted
f
r
o
m
th
e
s
en
s
o
r
s
.
Fi
g
u
r
e
2
s
h
o
w
s
t
h
e
c
o
m
p
u
ter
v
is
io
n
p
r
o
to
ty
p
e
.
Fig
u
r
e
2
.
C
o
m
p
u
ter
v
is
io
n
p
r
o
to
t
y
p
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
S
o
il C
h
a
r
a
cteriz
a
tio
n
a
n
d
C
la
s
s
ifica
tio
n
:
A
Hyb
r
id
A
p
p
r
o
a
c
h
o
f Co
mp
u
ter …
.
(
A
b
r
h
a
m
D
eb
a
s
u
Men
g
is
tu
)
993
4
.
2
.
Sens
o
r
B
r
ett
R
o
b
in
s
o
n
[
2
5
]
,
p
o
in
ted
o
u
t
th
at
d
ev
ice
s
f
o
r
m
ea
s
u
r
i
n
g
s
o
il
m
o
i
s
tu
r
e.
B
esid
es,
th
e
d
if
f
icu
lt
y
o
f
in
ter
p
r
etin
g
s
o
il
m
o
is
t
u
r
e
d
ata,
th
e
m
ai
n
li
m
itat
io
n
s
to
d
e
p
lo
y
i
n
g
s
o
il
m
o
i
s
t
u
r
e
s
en
s
o
r
s
in
d
r
y
la
n
d
g
r
ai
n
p
r
o
d
u
c
tio
n
ar
e
lik
el
y
to
b
e:
(
a
)
co
m
p
le
x
it
y
,
(
b)
co
s
t,
(
c
)
u
n
ce
r
tain
t
y
,
(
d
)
s
af
et
y
r
eg
u
lati
o
n
s
,
(
e
)
in
s
ta
llatio
n
p
r
o
b
lem
s
an
d
(
f
)
o
p
er
atin
g
p
r
o
b
lem
s
.
T
h
e
au
th
o
r
s
also
p
o
in
ted
th
at
W
ater
m
ar
k
s
en
s
o
r
s
an
d
ten
s
io
m
eter
s
d
o
n
o
t
w
o
r
k
in
d
r
y
s
o
ils
,
a
n
d
ca
n
b
e
ex
cl
u
d
ed
f
r
o
m
Hi
g
h
f
r
eq
u
en
c
y
,
b
u
r
ied
ca
p
ac
itan
ce
s
en
s
o
r
s
(
Se
n
te
k
,
Dec
ag
o
n
a
n
d
Veg
etr
o
n
i
x
)
ar
e
th
e
b
est
b
u
t
i
n
th
is
s
t
u
d
y
Gr
a
v
it
y
An
alo
g
So
il
Mo
is
t
u
r
e
Se
n
s
o
r
Fo
r
A
r
d
u
i
n
o
is
co
n
s
id
er
ed
.
Fig
u
r
e
3
s
h
o
w
s
t
h
e
m
o
is
t
u
r
e
s
en
s
o
r
.
Fig
u
r
e
3
.
Mo
is
tu
r
e
Se
n
s
o
r
4
.
3
.
B
a
ck
-
P
ro
pa
g
a
t
io
n Ar
t
if
icia
l
Neura
l N
et
w
o
rk
As
s
h
o
w
n
in
Fi
g
u
r
e
3
t
h
e
n
et
w
o
r
k
n
ee
d
s
7
i
n
p
u
t
s
o
f
th
e
c
o
m
b
i
n
ed
f
ea
tu
r
e
v
ec
to
r
s
o
f
p
h
y
s
ical
a
n
d
m
o
is
t
u
r
e
o
f
a
g
i
v
en
s
o
il
a
n
d
6
n
eu
r
o
n
s
in
it
s
o
u
tp
u
t
la
y
er
to
class
i
f
y
s
o
il
s
.
T
h
e
h
id
d
en
la
y
er
h
as
2
6
n
eu
r
o
n
s
.
T
h
is
n
u
m
b
er
w
as
p
ick
ed
b
y
t
r
ial
an
d
er
r
o
r
m
et
h
o
d
s
,
if
th
e
n
et
w
o
r
k
h
a
s
tr
o
u
b
le
o
f
lear
n
i
n
g
ca
p
ab
ilit
ies,
an
d
th
en
n
eu
r
o
n
s
ca
n
b
e
ad
d
ed
to
t
h
is
la
y
er
.
T
h
er
e
is
a
s
ig
n
if
ican
t
ch
an
g
e
w
h
e
n
w
e
in
cr
ea
s
e
t
h
e
n
u
m
b
er
o
f
h
id
d
en
la
y
er
s
n
eu
r
o
n
s
u
n
t
il
2
1
,
2
4
an
d
2
6
b
u
t
th
er
e
is
n
o
ch
a
n
g
e
wh
en
th
e
n
u
m
b
er
o
f
h
id
d
en
la
y
er
n
eu
r
o
n
s
i
n
cr
ea
s
es
ab
o
v
e
2
6
.
E
ac
h
v
alu
e
f
r
o
m
th
e
in
p
u
t la
y
er
is
d
u
p
licated
an
d
s
en
t to
all
o
f
t
h
e
h
id
d
en
n
o
d
es.
5.
E
XP
E
R
I
M
E
NT
AND
R
E
SU
L
T
S
I
n
th
is
r
esear
c
h
,
t
w
o
d
if
f
er
en
t
m
et
h
o
d
s
ar
e
u
s
ed
.
Na
m
el
y
C
o
m
p
u
ter
v
is
io
n
an
d
Se
n
s
o
r
ar
e
u
s
ed
to
class
i
f
y
an
d
ch
ar
ac
ter
ize
t
h
e
g
iv
e
n
s
o
il.
T
o
b
eg
in
w
it
h
,
t
h
e
p
h
y
s
ical
an
d
m
o
i
s
t
u
r
e
lev
el
f
ea
tu
r
es
ar
e
u
s
ed
f
o
r
b
o
th
tr
ain
i
n
g
a
n
d
test
i
n
g
f
o
r
B
P
NN
(
B
ac
k
-
P
r
o
p
ag
atio
n
A
r
tif
icia
l
Ne
u
r
al
Net
w
o
r
k
)
a
s
s
h
o
w
n
in
Fi
g
u
r
e
4
.
T
h
er
e
ar
e
t
w
o
b
asic
p
h
ases
o
f
p
atter
n
class
i
f
icatio
n
.
T
h
ey
ar
e
tr
ain
in
g
an
d
test
i
n
g
p
h
ases
.
I
n
th
e
tr
ain
in
g
p
h
ase,
d
ata
is
r
ep
ea
ted
l
y
p
r
esen
ted
to
th
e
clas
s
i
f
ier
,
in
o
r
d
er
to
o
b
tain
a
d
esire
d
r
esp
o
n
s
e.
I
n
test
i
n
g
p
h
ase,
t
h
e
tr
ain
ed
s
y
s
te
m
is
ap
p
lied
to
d
ata
th
at
it
h
as
n
e
v
er
s
ee
n
to
ch
ec
k
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
c
lass
i
f
icatio
n
.
Hen
ce
,
w
e
n
ee
d
to
d
esi
g
n
t
h
e
cla
s
s
i
f
i
er
b
y
p
ar
titi
o
n
in
g
th
e
to
tal
d
at
a
s
et
in
to
tr
ain
i
n
g
a
n
d
te
s
ti
n
g
d
ata
s
et.
Fro
m
t
h
e
to
tal
d
ataset
o
f
5
4
0
i
m
a
g
es
7
0
%
w
a
s
u
s
ed
to
b
u
ild
tr
ain
i
n
g
an
d
t
h
e
r
e
m
ai
n
in
g
3
0
%
o
f
th
e
to
tal
w
a
s
u
s
ed
f
o
r
test
i
n
g
d
ata.
T
h
e
ex
p
er
i
m
en
t
w
a
s
co
n
d
u
cted
f
o
r
1
0
,
1
5
,
2
0
,
2
5
an
d
3
0
h
id
d
en
n
eu
r
o
n
s
t
h
i
s
h
elp
u
s
to
ex
a
m
in
e
th
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
n
et
wo
r
k
.
I
n
B
P
NN,
n
ee
d
s
7
in
p
u
ts
n
e
u
r
o
n
s
o
f
t
h
e
co
m
b
i
n
ed
f
ea
t
u
r
e
v
ec
to
r
s
o
f
p
h
y
s
ical
a
n
d
m
o
i
s
t
u
r
e
le
v
el
f
e
atu
r
es
a
n
d
6
n
eu
r
o
n
s
i
n
its
o
u
tp
u
t
la
y
er
to
cla
s
s
i
f
y
s
o
il
s
to
t
h
eir
co
r
r
esp
o
n
d
in
g
class
.
T
h
e
h
id
d
en
la
y
er
h
a
s
2
6
n
e
u
r
o
n
s
.
T
h
er
e
is
a
s
i
g
n
if
ica
n
t
ch
a
n
g
e
w
h
e
n
w
e
in
cr
ea
s
e
th
e
n
u
m
b
er
o
f
h
id
d
e
n
la
y
er
s
n
e
u
r
o
n
s
u
n
til
1
0
,
1
5
,
2
0
,
2
5
,
an
d
3
0
b
u
t
th
er
e
is
n
o
c
h
an
g
e
w
h
en
t
h
e
n
u
m
b
er
o
f
h
id
d
en
la
y
er
n
eu
r
o
n
s
in
cr
e
ases
ab
o
v
e
2
6
.
A
s
i
n
d
icate
d
in
F
i
g
u
r
e
5
,
t
h
e
r
esu
lt
s
h
o
w
ed
t
h
at
th
er
e
w
as
8
9
.
7
%
s
u
c
ce
s
s
f
o
r
2
6
h
id
d
e
n
n
eu
r
o
n
s
u
s
in
g
t
h
e
co
m
b
in
ed
f
ea
tu
r
e
v
ec
to
r
o
f
p
h
y
s
ical
an
d
m
o
is
t
u
r
e
le
v
el
f
ea
t
u
r
es.
T
h
e
a
i
m
o
f
t
h
e
r
e
s
ea
r
c
h
p
ap
er
is
to
class
if
y
a
n
d
ch
ar
ac
ter
ize
s
o
ils
u
s
i
n
g
th
e
h
y
b
r
id
ap
p
r
o
ac
h
es o
f
co
m
p
u
ter
v
i
s
io
n
a
n
d
s
en
s
o
r
n
et
w
o
r
k
.
I
n
th
is
p
ap
er
,
co
m
p
u
ter
v
is
io
n
an
d
s
en
s
o
r
n
et
w
o
r
k
to
g
et
h
er
w
ith
B
P
NN
ar
e
u
s
ed
an
d
th
e
ac
cu
r
ac
y
o
f
t
h
e
s
y
s
te
m
ar
e
p
r
esen
ted
,
an
d
t
h
e
r
esu
l
ts
o
f
B
P
NN
w
er
e
d
is
c
u
s
s
ed
an
d
p
r
o
m
i
s
i
n
g
r
esu
lts
w
er
e
o
b
tai
n
ed
.
T
h
e
co
m
p
u
ter
v
is
io
n
a
n
d
s
e
n
s
o
r
n
et
w
o
r
k
f
o
r
th
e
ch
ar
ac
ter
iz
atio
n
a
n
d
clas
s
i
f
icatio
n
o
f
s
o
il
ca
n
b
e
f
u
r
th
er
in
v
e
s
ti
g
ated
.
T
h
e
w
o
r
k
ca
n
also
b
e
s
ee
n
in
d
ep
t
h
an
d
r
esear
ch
ed
b
y
t
h
e
d
if
f
er
e
n
t
m
ac
h
in
e
le
ar
n
i
n
g
tech
n
iq
u
es,
c
h
ar
ac
ter
is
tic
s
o
f
i
ts
p
h
y
s
ical
a
n
d
ch
e
m
ica
l i
n
co
n
n
ec
t
io
n
to
i
m
a
g
e
tec
h
o
g
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
8
,
No
.
2
,
A
p
r
il
201
8
:
9
8
9
–
9
9
5
994
Fig
u
r
e
4
.
B
P
NN
Fig
u
r
e
5
.
R
esu
lt o
f
clas
s
i
f
ier
s
T
ab
le
1
s
h
o
w
s
t
h
e
co
m
p
ar
is
o
n
o
f
w
o
r
k
.
T
ab
le
1
.
C
o
m
p
ar
is
o
n
o
f
w
o
r
k
A
u
t
h
o
r
N
a
me
M
e
t
h
o
d
o
l
o
g
y
F
i
n
d
i
n
g
s
P
r
a
v
a
t
K
u
mar
S
h
i
t
,
et
al
.
ER
D
A
S
I
mag
i
n
e
v
8
.
5
a
n
d
i
m
a
g
e
p
r
o
c
e
ssi
n
g
t
e
c
h
n
i
q
u
e
s
T
h
e
p
a
p
e
r
f
o
c
u
se
d
o
n
c
r
a
c
k
p
e
r
d
i
t
i
o
n
a
n
d
t
h
e
a
u
t
h
o
r
s
h
a
v
e
n
’
t
u
se
d
a
n
y
c
l
a
ssi
f
i
c
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s.
M
a
ł
g
o
r
z
a
t
a
C
h
a
r
y
t
a
n
o
w
i
c
z
a
n
d
P
i
o
t
r
K
u
l
c
z
y
c
k
i
C
o
mp
l
e
t
e
G
r
a
d
i
e
n
t
C
l
u
s
t
e
r
i
n
g
A
l
g
o
r
i
t
h
m
f
o
r
S
o
i
l
S
t
r
u
c
t
u
r
e
I
d
e
n
t
i
f
i
c
a
t
i
o
n
.
T
h
i
s
p
a
p
e
r
p
r
e
se
n
t
s
a
n
i
mag
e
se
g
me
n
t
a
t
i
o
n
a
p
p
r
o
a
c
h
f
o
r
d
e
t
e
c
t
i
n
g
t
h
e
so
i
l
p
o
r
e
st
r
u
c
t
u
r
e
s
K
.
S
r
u
n
i
t
h
a
a
n
d
S
.
P
a
d
mav
a
t
h
i
I
mag
e
p
r
o
c
e
ssi
n
g
a
n
d
S
V
M
c
l
a
ssi
f
i
e
r
f
o
r
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
so
i
l
s
T
h
e
p
a
p
e
r
f
o
c
u
se
d
o
n
t
h
e
p
e
r
f
o
r
man
c
e
o
f
S
V
M
i
n
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
so
i
l
s
a
s
c
l
a
y
,
l
o
a
m,
sa
n
d
y
,
p
e
a
t
.
F
r
o
m
t
h
e
e
x
p
e
r
i
me
n
t
7
4
.
4
%
a
c
c
u
r
a
c
y
i
s
a
c
h
i
e
v
e
d
.
A
sh
o
k
K
u
mar
P
a
t
e
l
,
S
n
e
h
a
mo
y
C
h
a
t
t
e
r
j
e
e
I
mag
e
p
r
o
c
e
ssi
n
g
a
n
d
P
r
o
b
a
b
i
l
i
s
t
i
c
n
e
u
r
a
l
n
e
t
w
o
r
k
(
P
N
N
)
T
h
e
a
u
t
h
o
r
f
o
c
u
se
d
o
n
r
o
c
k
t
y
p
e
i
d
e
n
t
i
f
i
c
a
t
i
o
n
u
si
n
g
P
N
N
a
n
d
f
o
r
m
t
h
e
e
x
p
e
r
i
me
n
t
T
h
e
r
e
su
l
t
sh
o
w
s
t
h
a
t
f
o
r
t
h
e
G
G
L
r
o
c
k
t
y
p
e
,
t
h
e
r
e
a
r
e
mi
scl
a
ss
i
f
i
c
a
t
i
o
n
e
r
r
o
r
o
f
1
6
%.
M
r
u
t
y
u
n
j
a
y
a
R
.
D
h
a
r
w
a
d
,
et
al
.,
D
i
g
i
t
a
l
i
m
a
g
e
s
t
o
e
st
i
mat
e
so
i
l
mo
i
st
u
r
e
o
f
si
x
so
i
l
s
T
h
e
a
u
t
h
o
r
c
o
n
s
i
d
e
r
H
S
V
c
o
l
o
r
sp
a
c
e
t
o
i
d
e
n
t
i
f
y
t
h
e
mo
i
s
t
u
r
e
A
b
r
h
a
m D
e
b
a
s
u
a
n
d
D
a
g
n
a
c
h
e
w
M
e
l
e
s
e
w
S
o
i
l
c
l
a
ssi
f
i
c
a
t
i
o
n
a
n
d
c
h
a
r
a
c
t
e
r
i
z
a
t
i
o
n
u
si
n
g
c
o
mp
u
t
e
r
v
i
si
o
n
a
n
d
se
n
so
r
n
e
t
w
o
r
k
a
p
p
r
o
a
c
h
e
s.
I
n
o
u
r
r
e
s
e
a
r
c
h
p
a
p
e
r
si
x
t
y
p
e
s
o
f
so
i
l
i
s
c
o
n
si
d
e
r
e
d
a
n
d
B
P
N
N
i
s
u
se
d
t
o
c
l
a
ssi
f
y
a
n
d
c
h
a
r
a
c
t
e
r
i
z
e
t
h
e
so
i
l
T
h
e
mai
n
f
i
n
d
i
n
g
o
n
t
h
i
s
r
e
se
a
r
c
h
i
s
p
h
y
si
c
a
l
f
e
a
t
u
r
e
v
e
c
t
o
r
l
i
k
e
t
e
x
t
u
r
e
a
n
d
c
o
l
o
r
i
s
n
o
t
a
d
e
q
u
a
t
e
t
o
c
l
a
ssi
f
y
a
n
d
c
h
a
r
a
c
t
e
r
i
z
e
t
h
e
mo
i
st
u
r
e
l
e
v
e
l
s.
S
o
a
s
t
o
i
n
c
r
e
a
se
t
h
e
p
e
r
f
o
r
man
c
e
se
n
so
r
i
s
u
se
d
.
F
r
o
m
t
h
e
e
x
p
e
r
i
me
n
t
8
9
.
7
%
a
c
c
u
r
a
c
y
i
s a
c
h
i
e
v
e
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
S
o
il C
h
a
r
a
cteriz
a
tio
n
a
n
d
C
la
s
s
ifica
tio
n
:
A
Hyb
r
id
A
p
p
r
o
a
c
h
o
f Co
mp
u
ter …
.
(
A
b
r
h
a
m
D
eb
a
s
u
Men
g
is
tu
)
995
ACK
NO
WL
E
D
G
M
E
NT
S
W
e
g
r
atef
u
ll
y
ac
k
n
o
w
led
g
e
B
ah
ir
Dar
Un
i
v
er
s
it
y
,
B
ah
ir
Dar
in
s
ti
tu
te
o
f
T
ec
h
n
o
lo
g
y
f
o
r
f
u
n
d
in
g
,
g
en
er
o
u
s
as
s
is
ta
n
ce
an
d
v
alu
a
b
le
in
f
o
r
m
a
tio
n
p
r
o
v
id
ed
to
u
s
b
y
o
u
r
i
n
s
t
itu
te.
RE
F
E
R
E
NC
E
S
[1
]
M
e
n
g
istu
A
le
m
a
y
e
h
u
,
“
Co
u
n
try
P
a
stu
re
/
F
o
ra
g
e
Re
so
u
rc
e
P
ro
f
il
e
s”
,
Un
p
u
b
li
s
h
e
d
F
A
O,2
0
1
0
.
[2
]
Ks
h
it
ij
a
S
.
Na
p
h
a
d
e
,
“
S
o
il
c
h
a
ra
c
teriz
a
ti
o
n
u
sin
g
d
ig
it
a
l
im
a
g
e
p
ro
c
e
ss
in
g
”
,
L
e
h
ig
h
Un
iv
e
rsity
,
Un
p
u
b
l
ish
e
d
T
h
e
se
s an
d
Diss
e
rtatio
n
s,
2
0
0
0
.
[3
]
T
in
k
u
A
c
h
a
r
y
a
&
A
jo
y
K.
Ra
y
,
“
I
m
a
g
e
P
ro
c
e
ss
in
g
P
rin
c
i
p
les
a
n
d
A
p
p
li
c
a
ti
o
n
s”
,
A
Jo
h
n
W
il
e
y
&
S
ON
S
,
M
C.
,
P
u
b
l
ica
ti
o
n
,
2
0
0
5
.
[4
]
Da
v
id
C.
M
a
rv
in
&
e
tal,
“
In
teg
ra
ti
n
g
tec
h
n
o
l
o
g
ies
f
o
r
sc
a
lab
le ec
o
lo
g
y
a
n
d
c
o
n
se
rv
a
ti
o
n
”
,
S
c
ie
n
c
e
Dire
c
t,
2
0
1
6
.
[5
]
M
in
g
y
u
a
n
Zh
a
n
g
&
e
tal,
“
A
p
p
ly
in
g
S
e
n
so
r
-
Ba
se
d
T
e
c
h
n
o
lo
g
y
to
Im
p
ro
v
e
Co
n
stru
c
ti
o
n
S
a
f
e
t
y
M
a
n
a
g
e
m
e
n
t”,
M
DP
I
S
e
n
so
rs,
2
0
1
7
.
[6
]
P
ra
v
a
t
Ku
m
a
r
S
h
it
,
G
o
u
ri
S
a
n
k
a
r
Bh
u
n
ia,
Ra
m
k
rish
n
a
M
a
it
i,
“
S
o
il
c
ra
c
k
m
o
rp
h
o
lo
g
y
a
n
a
l
y
si
s
u
sin
g
i
m
a
g
e
p
ro
c
e
ss
in
g
tec
h
n
i
q
u
e
s”
,
S
p
rin
g
e
r
,
2
0
1
5
.
[7
]
K.
S
ru
n
it
h
a
,
S
.
P
a
d
m
a
v
a
th
i,
“
P
e
r
f
o
r
m
a
n
c
e
o
f
S
V
M
c
las
sif
ier
f
o
r
ima
g
e
b
a
se
d
so
il
c
las
sif
i
c
a
ti
o
n
”
,
I
EE
E,
2
0
1
6
.
[8
]
A
sh
o
k
Ku
m
a
r
P
a
tel
a
n
d
S
n
e
h
a
m
o
y
Ch
a
tt
e
rjee
,
“
Co
m
p
u
ter
v
isi
o
n
-
b
a
se
d
li
m
e
sto
n
e
ro
ck
-
t
y
p
e
c
l
a
ss
if
i
c
a
ti
o
n
u
sin
g
p
ro
b
a
b
il
isti
c
n
e
u
ra
l
n
e
tw
o
rk
”
,
S
c
ien
c
e
Dire
c
t
,
2
0
1
6
.
[9
]
A
n
a
sta
si
a
S
o
f
o
u
a
n
d
G
e
o
rg
io
s
Ev
a
n
g
e
lo
p
o
u
l
o
s,
“
S
o
il
Im
a
g
e
S
e
g
m
e
n
tatio
n
a
n
d
T
e
x
tu
re
A
n
a
l
y
si
s:
A
Co
m
p
u
ter
V
isio
n
A
p
p
r
o
a
c
h
”
,
IEE
E
Ge
o
sc
ien
c
e
a
n
d
Rem
o
te
S
e
n
sin
g
L
e
tt
e
rs
,
2
0
0
5
.
[1
0
]
S
u
n
–
Ok
Ch
u
n
g
,
Ki
–
Hy
u
n
Ch
o
,
Ji
n
–
W
o
o
n
g
Ch
o
,
Ki
–
Y
o
u
l
Ju
n
g
a
n
d
T
a
k
e
o
Ya
m
a
k
a
wa
,
“
S
o
il
Tex
tu
re
Clas
si
f
ica
ti
o
n
A
l
g
o
rit
h
m
Us
in
g
RG
B
Ch
a
ra
c
teri
stics
o
f
S
o
il
Im
a
g
e
s”
,
F
u
k
u
o
k
a
8
1
2
–
8
5
8
1
,
Ja
p
a
n
,
2
0
1
2
.
[1
1
]
M
a
łg
o
rz
a
ta
Ch
a
r
y
tan
o
w
icz
a
n
d
P
io
tr
Ku
lcz
y
c
k
i,
“
A
n
I
m
a
g
e
A
n
a
l
y
sis
A
lg
o
rit
h
m
f
o
r
S
o
il
S
tru
c
t
u
re
Id
e
n
ti
f
ica
ti
o
n
”
,
S
p
rin
g
e
r In
ter
n
a
ti
o
n
a
l
P
u
b
l
ish
i
n
g
S
wit
ze
rla
n
d
,
2
0
1
5
.
[1
2
]
Bh
a
w
n
a
J.
Ch
il
k
e
,
Ne
h
a
B.
Ko
a
w
a
l
e
a
n
d
Div
y
a
M
.
Ch
a
n
d
ra
n
,
“
De
ter
m
in
a
ti
o
n
o
f
S
o
il
p
H
b
y
u
sin
g
Dig
it
a
l
I
m
a
g
e
P
r
o
c
e
ss
in
g
T
e
c
h
n
iq
u
e
-
A
Re
v
ie
w”
,
IJ
RIT
CC
,
2
0
1
7
.
[1
3
]
A
li
M
.
G
h
a
li
b
,
Ro
m
a
n
D.
Hr
y
c
i
w
,
S
e
u
n
g
Ch
e
o
l
S
h
in
,
“
Im
a
g
e
tex
tu
re
a
n
a
lys
is
a
n
d
n
e
u
r
a
l
n
e
tw
o
rk
s
fo
r
c
h
a
ra
c
ter
iza
ti
o
n
o
f
u
n
if
o
rm
so
il
s
”
,
P
ro
c
e
e
d
in
g
s
o
f
th
e
2
0
0
0
I
n
tern
a
ti
o
n
a
l
Co
m
p
u
ti
n
g
Co
n
g
re
ss
o
n
Co
m
p
u
ti
n
g
i
n
Civ
il
En
g
in
e
e
rin
g
-
B
o
sto
n
,
M
A
,
USA
,
6
7
1
-
6
8
2
.
[1
4
]
U
m
e
sh
Ka
m
b
le,
P
ra
v
in
S
h
in
g
n
e
,
Ro
sh
a
n
Ka
n
k
ra
y
a
n
e
,
S
h
re
y
a
s
S
o
m
k
u
w
a
r,
P
ro
f
.
S
a
n
d
i
p
Ka
m
b
le,
“
Tes
ti
n
g
o
f
Ag
ricu
lt
u
re
S
o
i
l
b
y
Dig
it
a
l
Im
a
g
e
P
ro
c
e
ss
in
g
”
,
IJ
S
RD
,
2
0
1
7
.
[1
5
]
A
.
V
.
Bil
g
il
i,
W
.
D.
Hiv
e
l
y
,
H.
v
a
n
Es,
L
.
G
a
sto
n
,
“
W
a
v
e
let
A
n
a
l
y
s
is
o
f
S
o
il
Re
f
lec
tan
c
e
f
o
r
th
e
Ch
a
ra
c
teriz
a
ti
o
n
o
f
S
o
il
P
ro
p
e
rti
e
s”
,
c
o
n
f
e
re
n
c
e
.
if
a
s.u
f
l.
e
d
u
/S
S
C/
p
d
f
/Bi
lg
il
iA
.
p
d
f
.
[1
6
]
M
.
Ba
rb
e
r,
C.
P
e
p
e
,
P
.
P
e
r
n
a
,
F
.
G
rin
g
s,
J.
Ja
c
o
b
o
Be
rll
e
s,
M
.
T
h
i
b
e
a
u
lt
,
H.
Ka
rsz
e
n
b
a
u
m
,
“
A
n
o
v
e
l
m
e
th
o
d
f
o
r
2
-
d
a
g
ricu
lt
u
ra
l
so
il
r
o
u
g
h
n
e
ss
c
h
a
ra
c
teriz
a
ti
o
n
b
a
se
d
o
n
a
las
e
r
sc
a
n
n
i
n
g
tec
h
n
iq
u
e
”
,
IEE
E
,
7
3
1
-
7
3
3
,
2
0
0
8
.
[1
7
]
Rich
a
rd
J.
F
lav
e
l,
et
al
.
,
“
A
n
i
m
a
g
e
p
ro
c
e
ss
in
g
a
n
d
a
n
a
l
y
sis
to
o
l
fo
r
id
e
n
t
ify
in
g
a
n
d
a
n
a
l
y
sin
g
c
o
m
p
lex
p
lan
t
ro
o
t
s
y
ste
m
s in
3
D so
il
u
sin
g
n
o
n
-
d
e
stru
c
ti
v
e
a
n
a
ly
sis: Ro
o
t1
”
,
P
L
o
S
O
n
e
,
2
0
1
7
.
[1
8
]
M
a
łg
o
rz
a
ta
Ch
a
r
y
tan
o
w
ic
z
,
P
i
o
tr
Ku
lcz
y
c
k
i,
“
A
n
I
m
a
g
e
A
n
a
l
y
si
s
A
l
g
o
rit
h
m
f
o
r
S
o
il
S
tr
u
c
tu
re
Id
e
n
ti
f
ica
ti
o
n
”
,
S
p
rin
g
e
r,
In
telli
g
e
n
t
S
y
ste
ms
2
0
1
4
.
[1
9
]
M
a
sa
y
u
k
i
Ta
m
u
ra
&
Weip
in
g
L
i,
“
De
tec
ti
o
n
o
f
so
il
li
q
u
e
f
a
c
ti
o
n
a
re
a
s
in
th
e
Ka
n
t
o
u
re
g
io
n
u
sin
g
m
u
lt
i
-
te
m
p
o
ra
l
In
S
A
R
c
o
h
e
re
n
c
e
”
,
IEE
E
,
2
0
1
3
.
[2
0
]
K.
S
ru
n
it
h
a
a
n
d
S
.
P
a
d
m
a
v
a
th
i,
“
Per
fo
rm
a
n
c
e
o
f
S
VM
c
la
ss
if
ier
fo
r
ima
g
e
b
a
se
d
so
il
c
la
ss
i
fi
c
a
ti
o
n
”
,
S
ig
n
a
l
P
r
o
c
e
ss
in
g
,
Co
m
m
u
n
ica
ti
o
n
,
P
o
w
e
r
a
n
d
Em
b
e
d
d
e
d
S
y
ste
m
(S
COP
ES
),
2
0
1
6
I
n
tern
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
.
[2
1
]
M
ru
ty
u
n
jay
a
R.
Dh
a
r
w
a
d
,
et
al
.
,
”
Esti
m
a
ti
o
n
o
f
M
o
istu
re
Co
n
ten
t
in
S
o
il
Us
in
g
Im
a
g
e
P
ro
c
e
ss
in
g
”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
In
n
o
v
a
ti
v
e
Res
e
a
rc
h
&
De
v
e
lo
p
me
n
t
,
2
0
1
4
.
[2
2
]
S
a
n
jay
Ku
m
a
w
a
t,
et
al
.
,
“
S
e
n
so
r
Ba
se
d
A
u
to
m
a
ti
c
Irri
g
a
ti
o
n
S
y
st
e
m
a
n
d
S
o
il
p
H
De
tec
ti
o
n
u
sin
g
Im
a
g
e
P
r
o
c
e
ss
in
g
”
,
IRJET
,
2
0
1
7
.
[2
3
]
Nim
ish
a
S
in
g
h
a
n
d
Ra
n
a
G
il
l
Re
ti
n
a
l,
“
Re
ti
n
a
l
A
re
a
S
e
g
m
e
n
tatio
n
u
sin
g
A
d
a
p
ti
v
e
S
u
p
e
rp
ix
a
latio
n
a
n
d
it
s
Clas
sif
ic
a
ti
o
n
u
si
n
g
RBF
N”
,
IJ
E
CE
,
2
0
1
6
.
[2
4
]
He
ru
P
u
rn
o
m
o
Ip
u
n
g
,
Ha
n
d
a
y
a
n
i
T
jan
d
ra
sa
“
Urb
a
n
Ro
a
d
M
a
teria
ls
Id
e
n
ti
f
ica
ti
o
n
u
sin
g
Na
rro
w
Ne
a
r
In
f
ra
re
d
V
isio
n
S
y
ste
m
”
,
IJ
ECE
,
2
0
1
7
[2
5
]
Bre
tt
Ro
b
i
n
so
n
,
“
De
v
ice
s
f
o
r
m
e
a
su
rin
g
so
il
m
o
istu
re
:
S
e
lec
ti
n
g
se
n
so
rs
f
o
r
u
se
w
it
h
th
e
S
o
i
l
W
a
te
r
A
p
p
”
,
G
ra
in
s
re
se
a
rc
h
a
n
d
De
v
e
lo
p
m
e
n
t
Co
rp
o
ra
ti
o
n
”
,
2
0
1
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.