Co
m
pu
t
er
Science
a
nd
I
nfo
r
m
a
t
io
n T
ec
hn
o
lo
g
ies
Vo
l.
6
,
No
.
2
,
J
u
ly
20
25
,
p
p
.
1
36
~
1
46
I
SS
N:
2722
-
3
2
2
1
,
DOI
:
1
0
.
1
1
5
9
1
/csi
t
.
v6
i
2
.
pp1
36
-
1
46
136
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
p
r
ime.
co
m/in
d
ex
.
p
h
p
/csi
t
Aro
wa
na
cultiva
t
io
n water q
ua
lity
foreca
sting
wi
th
multiv
a
ria
te
fuzzy tim
eseries a
nd inte
rnet
of
thi
ng
s
Ala
ud
di
n M
a
ula
na
H
irza
n,
April F
irm
a
n Da
ru,
L
enny
M
a
rg
a
re
t
t
a
H
uizen
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
m
a
t
i
o
n
Te
c
h
n
o
l
o
g
y
,
F
a
c
u
l
t
y
o
f
I
n
f
o
r
ma
t
i
o
n
T
e
c
h
n
o
l
o
g
y
a
n
d
C
o
m
mu
n
i
c
a
t
i
o
n
,
S
e
mara
n
g
U
n
i
v
e
r
si
t
y
,
S
e
mara
n
g
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
8
,
2
0
2
5
R
ev
is
ed
May
5
,
2
0
2
5
Acc
ep
ted
May
23
,
2
0
2
5
Wate
r
q
u
a
li
ty
p
la
y
s
a
c
ru
c
ial
ro
le
in
t
h
e
g
ro
wt
h
a
n
d
su
rv
iv
a
l
o
f
a
ro
wa
n
a
fish
,
with
imb
a
lan
c
e
s
i
n
k
e
y
p
a
ra
m
e
ters
(p
H,
tem
p
e
ra
tu
re
,
t
u
rb
id
it
y
,
d
isso
lv
e
d
o
x
y
g
e
n
,
a
n
d
c
o
n
d
u
c
ti
v
it
y
)
lea
d
in
g
to
i
n
c
re
a
se
d
m
o
rtalit
y
ra
tes
.
Wh
i
le
p
re
v
io
u
s
st
u
d
ies
h
a
v
e
i
n
tr
o
d
u
c
e
d
v
a
rio
u
s
m
o
n
it
o
rin
g
m
o
d
e
ls
u
sin
g
Ard
u
in
o
IDE
a
n
d
i
n
tri
n
sic
a
p
p
ro
a
c
h
e
s,
th
e
y
lac
k
p
re
d
icti
v
e
c
a
p
a
b
il
it
ie
s,
lea
v
i
n
g
c
u
lt
iv
a
t
o
rs
u
n
a
b
le
to
tak
e
p
ro
a
c
ti
v
e
m
e
a
su
re
s.
To
a
d
d
re
ss
t
h
is
g
a
p
,
th
is
stu
d
y
d
e
v
e
lo
p
s
a
p
re
d
icti
v
e
m
o
d
e
l
i
n
te
g
ra
ti
n
g
t
h
e
i
n
tern
e
t
o
f
th
i
n
g
s
(I
o
T)
with
a
fu
z
z
y
ti
m
e
se
ries
(F
TS
)
a
lg
o
r
it
h
m
.
Th
r
o
u
g
h
rig
o
ro
u
s
e
v
a
l
u
a
ti
o
n
a
n
d
v
a
li
d
a
ti
o
n
,
th
e
p
ro
p
o
se
d
F
TS
-
m
u
lt
iv
a
riate
T2
m
o
d
e
l
d
e
m
o
n
stra
te
d
su
p
e
rio
r
p
e
rfo
rm
a
n
c
e
,
a
c
h
iev
i
n
g
a
n
e
x
c
e
p
ti
o
n
a
ll
y
lo
w
e
rro
r
ra
te
o
f
0
.
0
1
7
0
4
%
,
o
u
t
p
e
rfo
rm
in
g
d
e
c
isio
n
tree
(0
.
1
3
4
1
0
%
),
F
TS
-
m
u
l
ti
v
a
riate
T
1
(
0
.
8
8
3
9
7
%
),
a
n
d
l
in
e
a
r
re
g
re
ss
io
n
(2
0
.
9
1
7
9
1
%
).
T
h
e
se
fin
d
in
g
s
c
o
n
f
irm
th
a
t
F
TS
-
m
u
lt
i
v
a
riate
T2
n
o
t
o
n
ly
a
c
c
u
ra
tely
p
re
d
icts
wa
ter
q
u
a
li
ty
b
u
t
a
ls
o
sig
n
ifi
c
a
n
t
ly
re
d
u
c
e
s
th
e
m
e
a
n
a
b
so
lu
te
p
e
rc
e
n
tag
e
e
rro
r
,
p
r
o
v
i
d
i
n
g
a
ro
b
u
st
so
lu
ti
o
n
fo
r
s
u
sta
in
a
b
le
a
r
o
wa
n
a
a
q
u
a
c
u
lt
u
re
.
K
ey
w
o
r
d
s
:
Ar
o
wan
a
I
n
ter
n
et
o
f
th
in
g
s
Mu
ltiv
ar
iate
f
u
zz
y
tim
e
s
er
ies
Pre
d
ictio
n
W
ater
q
u
ality
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Alau
d
d
in
Ma
u
lan
a
Hir
za
n
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atio
n
T
e
ch
n
o
lo
g
y
,
Facu
lty
o
f
I
n
f
o
r
m
at
io
n
T
ec
h
n
o
lo
g
y
an
d
C
o
m
m
u
n
i
ca
tio
n
Sem
ar
an
g
Un
iv
e
r
s
ity
Sem
ar
an
g
,
I
n
d
o
n
esia
E
m
ail: m
au
lan
ah
ir
za
n
@
u
s
m
.
a
c.
id
1.
I
NT
RO
D
UCT
I
O
N
Ar
o
wan
a
f
is
h
ar
e
a
t
y
p
e
o
f
d
e
co
r
atio
n
f
is
h
th
at
p
eo
p
le
u
s
u
a
lly
k
ee
p
to
f
u
r
n
is
h
t
h
eir
h
o
u
s
es.
Peo
p
le
b
eliev
e
th
at
k
ee
p
in
g
th
em
m
ay
b
r
in
g
p
r
o
s
p
er
ity
an
d
wea
lth
to
th
e
o
wn
er
.
B
ec
au
s
e
o
f
th
at
s
im
p
le
r
ea
s
o
n
,
m
an
y
f
is
h
f
ar
m
er
s
h
av
e
s
tar
te
d
cu
ltiv
atin
g
th
is
ty
p
e
o
f
f
is
h
.
T
h
is
f
is
h
is
also
k
n
o
wn
b
y
t
h
e
s
cien
tific
n
am
e
Scler
o
p
ag
es
f
o
r
m
o
s
u
s
an
d
d
r
a
g
o
n
f
is
h
in
Asi
an
co
u
n
tr
ies.
Ho
wev
er
,
cu
ltiv
atin
g
a
r
o
wa
n
a
f
is
h
is
n
o
t
an
ea
s
y
task
f
o
r
th
e
cu
ltiv
ato
r
.
T
o
all
o
w
ar
o
wan
a
f
is
h
to
g
r
o
w
o
p
t
im
ally
,
a
s
p
ec
if
ic
r
an
g
e
f
o
r
e
ac
h
p
a
r
am
eter
:
p
H,
tem
p
er
atu
r
e,
d
is
s
o
lv
ed
o
x
y
g
e
n
,
co
n
d
u
ctiv
ity
,
an
d
tu
r
b
id
ity
is
r
eq
u
ir
ed
[
1
]
–
[
3
]
.
I
f
t
h
e
cu
lt
iv
ato
r
s
f
ail
to
k
ee
p
th
ese
p
ar
am
eter
s
b
alan
ce
d
,
th
is
m
ay
r
en
d
er
ar
o
wan
a
f
is
h
g
r
o
wth
an
d
m
ay
ca
u
s
e
d
ea
th
f
o
r
th
e
f
is
h
[
4
]
.
T
o
m
itig
ate
th
is
p
r
o
b
lem
,
m
a
n
y
cu
ltiv
ato
r
s
m
ea
s
u
r
e
th
e
wat
er
q
u
ality
in
s
id
e
th
e
wate
r
m
an
u
ally
with
s
o
m
e
s
en
s
o
r
s
.
Ho
wev
er
,
th
e
c
o
n
d
iti
o
n
s
in
s
id
e
th
e
wate
r
a
r
e
s
o
m
et
im
es
u
n
p
r
e
d
ictab
le.
T
h
e
c
u
l
t
i
v
a
t
o
r
s
c
a
n
n
o
t
p
r
e
d
i
c
t
w
h
e
n
o
n
e
o
r
m
o
r
e
w
a
t
e
r
q
u
a
l
i
t
y
p
a
r
a
m
e
t
e
r
s
a
r
e
b
e
l
o
w
o
r
o
v
e
r
t
h
e
t
h
r
e
s
h
o
l
d
.
F
o
r
t
h
a
t
r
ea
s
o
n
,
m
a
n
y
s
t
u
d
i
es
p
r
o
p
o
s
e
d
a
m
o
n
i
t
o
r
i
n
g
m
o
d
e
l
t
o
d
e
t
e
c
t
w
at
e
r
q
u
a
l
it
y
w
i
t
h
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
(
I
o
T
)
t
e
c
h
n
o
l
o
g
y
[
5
]
–
[
7
]
.
T
h
i
s
t
e
c
h
n
o
l
o
g
y
a
l
l
o
w
s
c
u
l
ti
v
a
t
o
r
s
t
o
m
o
n
i
t
o
r
t
h
e
w
a
t
e
r
q
u
a
l
i
t
y
w
i
t
h
i
n
t
h
e
c
u
l
t
i
v
a
ti
o
n
a
r
e
a
a
u
t
o
m
a
t
i
c
a
ll
y
a
n
d
r
e
m
o
t
e
l
y
.
S
o
,
t
h
e
c
u
l
t
i
v
a
t
o
r
s
o
n
l
y
n
e
e
d
t
o
c
o
m
e
w
h
e
n
e
v
e
r
t
h
e
p
a
r
a
m
e
t
e
r
s
a
r
e
a
l
m
o
s
t
b
e
l
o
w
o
r
o
v
e
r
t
h
e
t
h
r
e
s
h
o
l
d
.
T
h
e
s
tu
d
y
f
r
o
m
2
0
2
0
p
r
o
p
o
s
ed
a
m
o
d
el
w
h
er
e
th
e
m
o
d
el
is
eq
u
ip
p
ed
with
an
u
ltra
s
o
n
ic
s
en
s
o
r
an
d
Ar
d
u
in
o
UNO.
T
h
is
m
o
d
el
is
ca
p
ab
le
o
f
th
e
co
n
d
itio
n
o
f
th
e
aq
u
ar
iu
m
an
d
r
ep
o
r
tin
g
th
e
r
esu
lt
to
m
an
y
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
A
r
o
w
a
n
a
cu
ltiva
tio
n
w
a
ter q
u
a
lity fo
r
ec
a
s
tin
g
w
ith
mu
ltiva
r
ia
te
fu
z
z
y
…
(
A
la
u
d
d
in
Ma
u
la
n
a
Hir
z
a
n
)
137
d
ev
ices
[
8
]
.
T
h
is
m
o
d
el
was
th
en
im
p
r
o
v
ed
in
th
e
n
ex
t
s
tu
d
y
o
f
2
0
2
1
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
in
th
at
y
ea
r
is
eq
u
ip
p
e
d
with
p
H,
tem
p
er
atu
r
e,
an
d
tu
r
b
id
it
y
s
en
s
o
r
s
.
T
h
e
m
o
d
el
s
u
cc
ess
f
u
lly
m
o
n
ito
r
s
th
e
aq
u
a
r
iu
m
with
m
in
im
u
m
e
f
f
o
r
t
[
9
]
.
T
h
e
m
o
d
el
d
ev
elo
p
m
en
t
d
id
n
o
t
s
to
p
th
er
e
an
d
s
till
im
p
r
o
v
in
g
.
I
n
2
0
2
2
,
th
e
n
ex
t
s
tu
d
y
im
p
r
o
v
e
d
th
e
p
r
e
v
io
u
s
m
o
d
el
b
y
d
esig
n
i
n
g
I
o
T
-
b
ased
wate
r
q
u
ality
m
o
n
ito
r
in
g
(
SIM
ONAI
R
)
[
1
0
]
.
T
h
e
latest
m
o
d
el
was
p
r
o
p
o
s
ed
in
2
0
2
3
wh
er
e
s
o
m
e
s
tu
d
ies
p
r
o
p
o
s
ed
a
m
o
d
el
with
b
etter
ac
cu
r
ac
y
.
T
h
is
ar
ticle
[
7
]
s
h
o
wed
th
at
its
m
o
d
el
h
as
a
l
o
w
er
r
o
r
r
ate
o
f
u
p
to
1
%
co
m
p
ar
ed
to
t
h
e
co
m
m
o
n
s
en
s
o
r
.
T
h
er
e
is
o
n
e
m
o
r
e
ar
ticle
[
1
1
]
with
a
m
o
d
el
c
o
n
n
ec
ted
to
th
e
T
h
i
n
g
s
p
ea
k
s
er
v
ice
th
at
h
as a
cc
u
r
ate
m
ea
s
u
r
e
m
e
n
ts
.
B
ased
o
n
th
e
p
r
ev
io
u
s
p
ar
a
g
r
ap
h
,
th
is
s
tu
d
y
an
aly
ze
d
t
h
e
p
r
e
v
io
u
s
m
o
d
els
an
d
f
o
u
n
d
co
m
m
o
n
wea
k
n
ess
es.
T
h
e
f
ir
s
t
p
r
o
b
lem
is
ab
o
u
t
th
e
p
r
o
ce
s
s
in
g
m
o
d
el
u
s
ed
b
y
th
e
p
r
ev
i
o
u
s
m
o
d
el.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
f
r
o
m
th
e
ar
ticle
u
s
ed
Ar
d
u
in
o
UNO
as
th
e
p
r
o
ce
s
s
in
g
b
o
ar
d
.
T
h
is
b
o
ar
d
was
n
o
t
eq
u
i
p
p
ed
with
wir
eless
co
m
m
u
n
icatio
n
an
d
o
n
ly
wo
r
k
e
d
lo
ca
lly
[
1
2
]
.
T
h
u
s
,
t
h
e
b
o
a
r
d
m
u
s
t
b
e
co
n
n
e
c
ted
t
o
a
n
a
d
d
iti
o
n
al
co
m
p
o
n
e
n
t
to
all
o
w
co
m
m
u
n
i
ca
ti
o
n
t
o
t
h
e
I
n
te
r
n
et
.
T
h
e
s
ec
o
n
d
p
r
o
b
l
em
is
th
at
t
h
e
r
e
is
n
o
m
ac
h
i
n
e
-
l
ea
r
n
in
g
alg
o
r
it
h
m
t
o
ass
is
t
t
h
e
m
o
d
e
l
i
n
p
r
e
d
ic
ti
n
g
f
u
tu
r
e
c
o
n
d
iti
o
n
s
.
Pr
ev
io
u
s
m
o
d
els
we
r
e
o
n
ly
li
m
it
ed
t
o
m
o
n
it
o
r
i
n
g
in
r
ea
l
-
tim
e,
b
u
t
t
h
e
y
c
an
n
o
t
p
r
e
d
ic
t
f
u
t
u
r
e
wa
te
r
q
u
a
lit
y
.
W
ith
o
u
t
f
u
t
u
r
e
p
r
e
d
ict
io
n
s
,
t
h
e
cu
lti
v
a
to
r
s
c
an
n
o
t
m
iti
g
ate
t
h
e
f
u
t
u
r
e
o
u
t
co
m
es
t
h
at
m
i
g
h
t
o
cc
u
r
in
t
h
e
c
u
lti
v
a
tio
n
a
r
e
as
[
1
3
]
.
W
it
h
th
e
li
m
it
ati
o
n
s
o
f
p
r
e
v
i
o
u
s
m
o
d
els,
t
h
e
c
u
l
ti
v
at
o
r
m
a
y
s
u
f
f
e
r
s
ev
e
r
e
ec
o
n
o
m
ic
l
o
s
s
i
f
a
r
o
wan
a'
s
m
o
r
ta
lit
y
r
ate
i
n
c
r
ea
s
es
.
T
h
e
cu
r
r
en
t
r
esear
ch
g
ap
t
h
at
ex
is
ts
with
in
th
e
p
r
e
v
io
u
s
s
tu
d
ies
is
th
e
m
is
s
in
g
p
r
e
d
ictio
n
alg
o
r
ith
m
to
s
u
p
p
o
r
t
f
u
tu
r
e
p
r
ed
ictio
n
b
ased
o
n
tim
e
-
s
er
ies
d
ata.
T
h
u
s
,
th
e
cu
ltiv
ato
r
s
ca
n
m
itig
ate
wh
at
will
o
cc
u
r
in
th
e
f
u
tu
r
e
.
Fo
r
th
at
r
ea
s
o
n
,
th
is
s
tu
d
y
h
as
th
e
p
u
r
p
o
s
e
o
f
s
o
lv
in
g
th
e
p
r
o
b
lem
in
th
e
p
r
e
v
io
u
s
p
ar
a
g
r
a
p
h
b
y
ex
ter
n
ally
im
p
lem
e
n
tin
g
a
f
u
z
zy
tim
eser
ies
m
u
ltiv
ar
iate
(
FTS
-
MV
)
alg
o
r
ith
m
as
th
e
p
r
e
d
ictio
n
alg
o
r
ith
m
f
o
r
th
e
I
o
T
.
T
h
is
alg
o
r
ith
m
is
s
u
itab
le
f
o
r
tim
e
s
er
ies
-
b
ased
d
ata
an
d
is
o
f
ten
im
p
lem
en
ted
in
m
an
y
s
itu
atio
n
s
.
Fo
r
ex
am
p
le,
an
a
r
ti
cle
[
1
4
]
p
u
b
lis
h
ed
in
2
0
2
0
im
p
lem
en
t
ed
a
f
u
zz
y
tim
e
s
er
ies
(
FTS)
f
o
r
p
r
e
d
ictin
g
n
o
n
-
s
tatio
n
ar
y
en
v
ir
o
n
m
e
n
t
d
ata.
I
n
d
if
f
e
r
en
t
ar
ticles
[
1
5
]
,
th
is
alg
o
r
ith
m
is
also
im
p
lem
e
n
t
ed
in
s
o
lar
e
n
er
g
y
p
r
ed
ictio
n
.
T
h
e
last
ar
ticle
[
1
6
]
w
ith
in
th
e
s
am
e
y
ea
r
2
0
2
0
also
u
s
es
a
f
u
zz
y
tim
e
-
s
er
ies
alg
o
r
ith
m
to
p
r
e
d
ict
th
e
air
q
u
ality
in
d
e
x
.
T
h
ese
ar
ticles
p
r
o
v
e
th
at
th
e
FTS
is
im
p
lem
en
tab
le
an
d
ca
p
ab
le
to
p
r
ed
ict
wate
r
q
u
ality
in
a
r
o
wan
a'
s
cu
ltiv
atio
n
.
2.
M
E
T
H
O
D
I
n
th
is
s
ec
tio
n
,
th
i
s
s
tu
d
y
ex
p
l
ain
s
h
o
w
to
g
ath
e
r
an
d
p
r
e
p
ar
e
th
e
r
eq
u
i
r
ed
d
ata
b
ef
o
r
e
d
es
ig
n
in
g
th
e
p
r
o
p
o
s
ed
I
o
T
m
o
d
el
an
d
eq
u
ip
p
in
g
it
with
a
f
u
zz
y
tim
e
-
s
er
ies
alg
o
r
ith
m
.
T
h
e
f
ir
s
t
s
te
p
is
to
g
ath
e
r
th
e
r
eq
u
ir
ed
d
ata
f
r
o
m
a
r
o
wan
a'
s
cu
ltiv
atio
n
.
I
n
th
is
ca
s
e,
th
is
s
tu
d
y
u
s
es
a
m
o
n
ito
r
in
g
I
o
T
m
o
d
el
eq
u
ip
p
e
d
with
s
ev
er
al
s
en
s
o
r
s
lik
e
PH
-
4
5
0
2
C
(
wate
r
ac
id
ity
s
en
s
o
r
)
,
a
n
alo
g
t
o
tal
d
is
s
o
lv
ed
s
o
lid
(
wate
r
co
n
d
u
ctiv
ity
s
en
s
o
r
)
,
DS1
8
B
2
0
(
wate
r
te
m
p
er
atu
r
e
s
en
s
o
r
)
,
d
is
s
o
lv
ed
o
x
g
en
a
n
d
tu
r
b
id
ity
s
en
s
o
r
s
.
T
h
e
s
ch
em
atic
in
Fig
u
r
e
1
is
th
e
illu
s
tr
atio
n
f
o
r
t
h
e
d
ata
g
ath
e
r
in
g
as we
ll a
s
th
e
p
r
ed
ictio
n
n
o
d
e
.
Fig
u
r
e
1
.
T
h
e
s
ch
em
atic
f
o
r
m
o
n
ito
r
in
g
an
d
p
r
ed
ictio
n
m
o
d
e
l
Fig
u
r
e
1
is
th
e
illu
s
tr
atio
n
o
f
th
e
m
o
d
el'
s
s
ch
em
atic.
T
h
er
e
ar
e
s
ev
er
al
co
m
p
o
n
e
n
ts
in
s
tal
led
in
th
e
m
o
d
el:
i)
E
SP
3
2
p
r
o
ce
s
s
in
g
b
o
ar
d
eq
u
ip
p
e
d
with
W
iFi
n
etwo
r
k
in
g
,
ii)
tu
r
b
id
ity
s
e
n
s
o
r
,
iii)
DS1
8
B
2
0
tem
p
er
atu
r
e
s
en
s
o
r
,
iv
)
an
alo
g
T
DS
s
en
s
o
r
,
v
)
PH
-
4
5
0
2
C
wate
r
ac
id
ity
s
en
s
o
r
,
an
d
v
i)
d
is
s
o
lv
ed
o
x
y
g
e
n
s
en
s
o
r
.
W
ith
th
at
n
o
d
e,
th
is
s
tu
d
y
g
at
h
er
s
th
e
d
ata
f
o
r
two
d
ay
s
with
an
in
ter
v
al
o
f
f
iv
e
s
e
co
n
d
s
b
etwe
en
d
ata
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
6
,
No
.
2
,
J
u
ly
20
25
:
1
36
-
1
46
138
in
a
s
m
all
-
s
ized
aq
u
ar
iu
m
with
o
n
e
a
r
o
wa
n
a.
E
ac
h
r
ec
o
r
d
e
d
d
ata
h
as
a
tim
estam
p
in
it
to
s
h
o
w
wh
en
th
e
d
ata
is
r
ec
o
r
d
ed
.
Af
ter
g
ath
er
in
g
t
h
e
d
ata,
t
h
is
s
tu
d
y
o
b
tain
ed
3
4
,
5
6
0
r
o
ws
in
a
C
SV
f
o
r
m
a
t
f
o
r
ea
s
ier
ac
ce
s
s
d
u
r
in
g
th
e
tr
ain
in
g
p
h
ase.
T
ab
le
1
co
n
tain
s
th
e
s
am
p
le
o
f
g
at
h
er
ed
d
ata.
T
ab
le
1
co
n
tain
s
th
e
s
am
p
le
f
r
o
m
g
at
h
er
ed
d
ata
o
v
e
r
two
d
a
y
s
.
T
h
e
f
ir
s
t
co
l
u
m
n
is
th
e
tim
estam
p
o
f
ea
ch
d
ata
in
UNI
X
ep
o
ch
f
o
r
m
at
[
1
7
]
.
T
h
en
th
e
n
e
x
t
co
lu
m
n
s
f
o
llo
wed
b
y
p
H,
tem
p
er
atu
r
e,
tu
r
b
id
ity
,
d
is
s
o
lv
ed
o
x
y
g
en
,
an
d
co
n
d
u
c
tiv
ity
.
Af
ter
o
b
tain
in
g
th
e
d
ata
,
th
is
s
tu
d
y
co
n
tin
u
es
th
e
s
tep
to
f
u
zz
if
y
th
e
d
ata
to
o
b
tain
wate
r
q
u
ality
.
T
h
e
wate
r
q
u
ality
o
u
tp
u
t
is
in
r
e
g
r
ess
io
n
f
o
r
m
at
[
1
8
]
,
[
1
9
]
.
T
h
is
s
tu
d
y
co
n
f
ig
u
r
es
th
e
f
u
zz
y
lo
g
ic
to
p
r
o
d
u
ce
t
h
e
o
u
tp
u
t
b
etwe
en
t
h
e
0
to
1
0
0
r
an
g
es.
T
h
e
co
n
tain
s
o
f
m
em
b
e
r
s
h
ip
co
n
f
ig
u
r
atio
n
s
f
o
r
f
u
zz
if
icatio
n
p
r
o
ce
s
s
is
s
h
o
wn
in
T
ab
le
2
.
T
ab
le
2
co
n
tain
s
th
e
f
u
zz
if
icat
io
n
tab
le
to
o
b
tain
wate
r
q
u
alit
y
.
T
h
er
e
a
r
e
f
iv
e
f
ea
t
u
r
es o
n
t
h
e
tab
le
as
th
e
in
p
u
t
an
d
o
n
e
f
ea
tu
r
e
as
th
e
o
u
tp
u
t.
E
ac
h
f
ea
tu
r
e
is
d
iv
id
ed
in
to
th
r
ee
d
if
f
er
e
n
t
co
n
f
ig
u
r
atio
n
s
th
at
ac
t
as
a
th
r
esh
o
ld
.
T
h
e
p
H
h
as
th
r
ee
d
if
f
er
e
n
t
c
o
n
f
ig
u
r
atio
n
s
:
ac
id
,
n
eu
tr
al
an
d
alk
alin
e.
T
h
e
t
e
m
p
er
atu
r
e
h
as
co
ld
,
war
m
an
d
h
o
t
c
o
n
f
ig
u
r
atio
n
s
.
T
h
e
tu
r
b
i
d
ity
,
d
is
s
o
lv
ed
o
x
y
g
en
an
d
co
n
d
u
ctiv
ity
s
h
ar
e
s
im
ilar
co
n
f
ig
u
r
atio
n
s
:
lo
w,
m
ed
iu
m
,
a
n
d
h
i
g
h
.
Me
a
n
wh
ile,
th
e
o
u
tp
u
t
m
em
b
er
s
h
i
p
(
q
u
ality
)
h
as
d
if
f
e
r
e
n
t
co
n
f
i
g
u
r
atio
n
s
:
p
o
o
r
,
f
air
,
an
d
g
o
o
d
.
Af
ter
th
e
f
u
zz
if
icati
o
n
p
r
o
ce
s
s
,
th
e
d
ataset
will h
a
v
e
an
ad
d
itio
n
al
co
lu
m
n
ca
lled
q
u
ality
with
r
an
g
e
b
etwe
en
0
t
o
1
0
0
.
T
h
e
n
e
x
t
s
tep
is
to
tr
ain
th
e
f
u
zz
y
tim
e
-
s
e
r
ies
m
u
ltiv
ar
iate
m
o
d
el.
T
h
is
alg
o
r
ith
m
is
s
im
ilar
to
o
th
er
FTS
.
Ho
wev
er
,
th
is
a
lg
o
r
ith
m
u
tili
ze
s
m
u
ltip
le
f
ea
t
u
r
es
to
p
r
ed
ict
in
s
tead
s
in
g
le
f
ea
tu
r
e.
Similar
to
m
u
ltiv
ar
iate
lin
ea
r
r
e
g
r
ess
io
n
,
b
u
t f
o
r
tim
e
s
er
ies d
ataset.
T
h
is
s
tu
d
y
cr
ea
tes
two
s
im
p
le
Py
th
o
n
s
cr
ip
ts
th
at
im
p
o
r
ts
th
e
Py
FTS
lib
r
ar
y
to
c
r
ea
te
two
FTS
m
u
ltiv
ar
iate
m
o
d
els
[
2
0
]
.
T
h
is
s
tu
d
y
n
am
es
th
e
m
o
d
el
w
ith
FTS
-
m
u
ltiv
ar
iate
T
1
an
d
T
2
b
ased
o
n
th
e
d
atase
t’
s
d
eg
r
ee
o
f
d
if
f
er
e
n
tials
.
T
h
e
f
ir
s
t
m
o
d
el
(
FTS
-
m
u
ltiv
ar
iate
T
1
)
was
tr
ain
ed
wit
h
th
e
d
ataset's
f
ir
s
t
d
if
f
er
en
tial
d
eg
r
ee
.
I
n
co
n
tr
ast,
th
e
s
ec
o
n
d
m
o
d
el
(
FTS
-
m
u
lt
iv
ar
iate
T
2
)
was
tr
ain
ed
with
th
e
d
ataset's
s
ec
o
n
d
d
if
f
er
en
tial
d
e
g
r
ee
.
Hig
h
er
d
i
f
f
er
en
tial
d
e
g
r
ee
s
lead
to
m
o
r
e
s
tatio
n
ar
y
an
d
co
n
s
is
ten
t
tim
e
s
er
ies
p
atter
n
s
.
Af
ter
th
at,
th
ese
m
o
d
els
ar
e
ex
p
o
r
ted
in
t
o
b
in
ar
y
f
o
r
m
at
f
o
r
s
er
v
er
u
s
e.
Fig
u
r
e
2
illu
s
tr
ates
th
e
p
r
ed
ictio
n
m
ec
h
an
is
m
f
r
o
m
an
I
o
T
n
o
d
e
to
th
e
s
er
v
er
a
n
d
its
d
atab
ase.
T
ab
le
1
.
Sam
p
le
o
f
g
at
h
er
ed
d
ata
Ti
mes
t
a
m
p
pH
Te
mp
e
r
a
t
u
r
e
Tu
r
b
i
d
i
t
y
D
i
sso
l
v
e
d
o
x
y
g
e
n
C
o
n
d
u
c
t
i
v
i
t
y
1
7
3
6
3
2
3
2
0
0
.
0
0
5
.
4
9
1
7
6
2
1
.
3
4
1
7
6
2
.
7
4
1
7
6
6
.
0
4
1
7
6
3
4
0
.
2
4
1
8
1
7
3
6
3
2
3
2
0
5
.
0
0
7
.
8
7
3
0
5
1
2
2
.
8
9
5
9
3
6
.
0
6
9
6
7
4
1
3
.
9
8
6
2
9
3
2
8
.
2
1
0
9
1
7
3
6
3
2
3
2
1
0
.
0
0
8
.
3
5
4
9
8
3
0
.
0
4
6
8
8
6
.
9
3
4
1
4
2
7
.
4
5
2
2
8
5
3
7
1
.
6
8
0
3
1
7
3
6
3
2
3
2
1
5
.
0
0
5
.
1
4
5
9
1
4
1
9
.
4
1
0
8
2
3
.
0
2
0
1
0
9
0
.
8
1
7
7
0
5
2
4
3
.
9
6
0
8
….
1
7
3
6
4
9
5
9
8
5
.
0
0
8
.
2
5
5
4
4
9
1
9
.
8
0
8
5
2
5
.
4
9
1
6
2
4
1
1
.
8
1
4
0
3
4
1
6
.
3
6
8
3
1
7
3
6
4
9
5
9
9
0
.
0
0
9
.
4
1
8
5
1
7
2
4
.
3
6
8
4
7
4
.
4
8
9
8
7
2
1
2
.
2
1
4
2
7
2
9
8
.
1
7
3
6
1
7
3
6
4
9
5
9
9
5
.
0
0
5
.
7
6
9
3
3
1
1
7
.
6
1
7
7
5
3
.
4
5
5
5
3
7
1
0
.
2
1
2
7
5
2
7
8
.
4
5
7
9
T
ab
le
2
.
Me
m
b
er
s
h
ip
f
u
n
ctio
n
s
f
o
r
q
u
ality
f
u
zz
if
icatio
n
C
a
t
e
g
o
r
y
I
n
d
i
c
a
t
o
r
C
o
n
f
i
g
u
r
a
t
i
o
n
1
C
o
n
f
i
g
u
r
a
t
i
o
n
2
C
o
n
f
i
g
u
r
a
t
i
o
n
3
I
n
p
u
t
pH
0
–
6
.
9
(
A
c
i
d
)
6
.
8
–
7
.
2
(
N
e
u
t
r
a
l
)
7
.
1
–
1
4
(
A
l
k
a
l
i
n
e
)
Te
mp
e
r
a
t
u
r
e
0
–
2
5
(
C
o
l
d
)
24
–
3
5
(
W
a
r
m)
34
–
1
0
0
(
H
o
t
)
Tu
r
b
i
d
i
t
y
0
–
2
0
(
L
o
w
)
15
–
6
0
(
M
e
d
i
u
m)
55
–
1
0
0
0
(
H
i
g
h
)
D
i
sso
l
v
e
d
o
x
y
g
e
n
0
–
4
(
L
o
w
)
3
–
9
(
M
e
d
i
u
m)
8
–
1
5
(
H
i
g
h
)
C
o
n
d
u
c
t
i
v
i
t
y
0
–
1
2
0
(
Lo
w
)
1
0
0
–
2
0
2
0
(
M
e
d
i
u
m)
2
0
0
0
–
5
0
0
0
(
H
i
g
h
)
O
u
t
p
u
t
Q
u
a
l
i
t
y
0
–
3
5
(
P
o
o
r
)
32
–
7
5
(
F
a
i
r
)
72
–
1
0
0
(
G
o
o
d
)
Fig
u
r
e
2
ex
p
lain
s
th
e
p
r
e
d
ictio
n
m
e
ch
an
is
m
f
r
o
m
th
e
p
r
o
p
o
s
ed
m
o
d
el,
s
tar
tin
g
f
r
o
m
an
I
o
T
n
o
d
e
s
en
d
in
g
f
iv
e
p
ar
am
eter
s
to
th
e
s
er
v
er
th
r
o
u
g
h
th
e
R
eST
p
r
o
to
co
l
[
2
1
]
,
[
2
2
]
.
W
h
en
th
e
s
er
v
er
r
ec
eiv
es
th
e
d
ata,
th
en
th
e
s
er
v
er
d
o
e
s
th
e
p
r
ed
ictio
n
with
th
e
p
r
e
v
io
u
s
ly
ex
p
o
r
te
d
FTS
m
o
d
el.
T
h
e
s
er
v
er
th
en
s
to
r
es
th
e
p
r
ed
ictio
n
r
esu
lt in
a
d
atab
ase.
Fig
u
r
e
2
.
Pre
d
ictio
n
p
r
o
ce
s
s
f
r
o
m
a
I
o
T
n
o
d
e
to
th
e
s
er
v
er
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
A
r
o
w
a
n
a
cu
ltiva
tio
n
w
a
ter q
u
a
lity fo
r
ec
a
s
tin
g
w
ith
mu
ltiva
r
ia
te
fu
z
z
y
…
(
A
la
u
d
d
in
Ma
u
la
n
a
Hir
z
a
n
)
139
T
o
ev
alu
ate
th
e
p
r
o
p
o
s
ed
m
o
d
el,
th
is
s
tu
d
y
co
m
p
ar
es
th
e
r
esu
lt
with
an
o
th
e
r
alg
o
r
ith
m
lik
e
m
u
lti
-
v
ar
iate
lin
ea
r
r
e
g
r
ess
io
n
an
d
d
ec
is
io
n
tr
ee
.
T
h
is
s
tu
d
y
u
tili
ze
s
a
s
tatis
tical
ap
p
r
o
ac
h
b
y
ca
lcu
latin
g
m
ea
n
ab
s
o
lu
te
er
r
o
r
(
MA
E
)
,
m
ea
n
ab
s
o
lu
te
p
er
ce
n
tag
e
er
r
o
r
(
MA
PE)
,
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
MSE
)
,
r
o
o
t
m
ea
n
s
q
u
ar
ed
er
r
o
r
,
R
-
s
q
u
ar
ed
(
R
²)
,
an
d
ad
ju
s
ted
R²
.
MA
E
s
h
o
ws
th
e
av
er
ag
e
s
ize
o
f
th
e
er
r
o
r
s
b
etwe
en
ac
tu
al
an
d
p
r
ed
icted
v
alu
es.
MA
PE
s
h
o
ws
th
e
av
er
ag
e
er
r
o
r
as
a
p
e
r
ce
n
tag
e,
wh
ic
h
h
el
p
s
co
m
p
a
r
e
th
e
r
esu
lts
.
MSE
f
in
d
s
th
e
av
er
ag
e
o
f
th
e
s
q
u
a
r
ed
er
r
o
r
s
,
g
iv
in
g
m
o
r
e
weig
h
t
to
s
ig
n
if
ica
n
t
er
r
o
r
s
.
R
o
o
t
m
ea
n
s
q
u
ar
ed
er
r
o
r
(
R
MSE
)
g
iv
es
a
r
esu
lt
i
n
th
e
s
am
e
u
n
its
as
th
e
d
ata.
R
-
s
q
u
ar
ed
(
R
²)
tells
h
o
w
m
u
ch
o
f
t
h
e
v
ar
iatio
n
in
th
e
d
ata.
Ad
ju
s
ted
R²
f
ix
es
th
i
s
b
y
lo
wer
in
g
th
e
s
co
r
e.
T
h
is
ap
p
r
o
ac
h
is
m
o
r
e
s
u
itab
le
th
an
th
e
co
n
f
u
s
io
n
m
atr
i
x
to
m
ea
s
u
r
e
th
e
er
r
o
r
r
ate
[
2
3
]
,
[
2
4
]
.
I
n
(
1
)
-
(
6
)
f
o
r
ea
c
h
ev
alu
a
tio
n
is
s
h
o
wn
as f
o
llo
ws:
MAE
=
1
∑
|
−
|
=
1
(
1
)
M
A
PE
=
1
∑
|
−
|
100
=
1
(
2
)
M
SE
=
1
∑
(
−
)
2
=
1
(
3
)
R
M
SE
=
√
1
∑
(
−
)
2
=
1
(
4
)
2
=
1
−
∑
(
−
)
2
=
1
∑
(
−
̅
̅
̅
̅
̅
̅
̅
̅
̅
̅
)
2
=
1
(
5
)
2
=
1
−
(
(
1
−
2
)
(
−
1
)
−
−
1
)
(
6
)
E
ac
h
v
ar
iab
le
h
as
d
if
f
e
r
en
t
m
ea
n
in
g
,
wh
e
r
e
i
r
e
f
er
s
to
r
o
w
n
u
m
b
er
o
f
d
atasets
.
T
h
e
to
tal
d
ata
r
ef
er
s
to
th
e
r
o
w
n
u
m
b
er
f
o
r
ea
ch
a
ctu
al
an
d
p
r
e
d
ictio
n
v
alu
es.
T
h
e
ac
tu
al
an
d
p
r
ed
ictio
n
r
ef
er
to
d
ataset
s
to
r
ed
in
s
id
e
th
e
d
atab
ase.
Me
an
wh
ile,
to
tal
f
ea
tu
r
es
r
ef
er
to
th
e
n
u
m
b
er
o
f
f
ea
tu
r
es
in
a
d
ataset.
T
h
is
s
tu
d
y
u
s
es two
d
if
f
er
en
t
a
p
p
r
o
ac
h
es
to
v
alid
ate
th
e
r
esu
lt.
T
h
e
f
ir
s
t
o
n
e
cr
ea
tes
a
b
aselin
e
f
r
o
m
th
e
s
to
r
ed
d
ata,
an
d
th
e
s
ec
o
n
d
o
n
e
u
s
e
s
cr
o
s
s
-
v
alid
atio
n
(
5
f
o
ld
s
)
r
esu
lts
.
T
h
e
f
ir
s
t
ap
p
r
o
ac
h
u
s
es
a
b
aselin
e
f
o
r
c
o
m
p
ar
is
o
n
with
th
e
p
r
o
p
o
s
ed
m
o
d
els,
m
u
lti
-
v
a
r
iate
lin
ea
r
r
eg
r
ess
io
n
[
2
5
]
,
[
2
6
]
a
n
d
d
ec
is
io
n
tr
ee
[
2
7
]
.
T
h
ese
alg
o
r
ith
m
s
ar
e
o
f
te
n
u
s
ed
in
m
an
y
s
itu
atio
n
s
,
in
clu
d
in
g
wate
r
q
u
ality
p
r
ed
ictio
n
s
.
B
ased
o
n
ar
ticles
[
2
8
]
,
[
2
9
]
i
n
2
0
2
2
,
b
o
th
lin
ea
r
r
eg
r
ess
io
n
an
d
d
ec
is
io
n
tr
ee
wer
e
im
p
lem
en
ted
to
p
r
ed
ict
wa
ter
q
u
ality
in
d
if
f
er
e
n
t
s
tu
d
ies.
T
h
ese
ar
ticles
ar
e
s
o
lid
ev
id
en
ce
o
f
th
e
ap
p
li
ca
tio
n
o
f
b
o
th
al
g
o
r
ith
m
s
in
wate
r
q
u
ality
p
r
ed
ictio
n
s
.
Me
a
n
wh
ile,
th
e
s
ec
o
n
d
ap
p
r
o
ac
h
u
s
es
th
e
v
alid
atio
n
m
eth
o
d
to
ca
lcu
late
th
e
ac
c
u
r
ac
y
a
n
d
er
r
o
r
p
er
ce
n
tag
es
f
r
o
m
th
e
p
r
o
p
o
s
ed
m
o
d
els tr
ain
ed
with
d
if
f
er
en
t l
en
g
th
s
o
f
tr
ai
n
in
g
a
n
d
test
d
at
a.
3.
RE
SU
L
T
S A
ND
D
I
SCU
SS
I
O
N
I
n
th
is
s
ec
tio
n
,
th
is
s
tu
d
y
ex
p
lain
s
th
e
r
esu
lts
th
at
ar
e
o
b
tain
ed
f
r
o
m
th
e
ev
al
u
atio
n
an
d
v
alid
atio
n
p
h
ases
.
T
h
e
f
ir
s
t e
x
p
lan
atio
n
is
ab
o
u
t th
e
p
r
ed
ictio
n
r
esu
lts
s
to
r
ed
in
a
d
atab
ase.
T
h
en
,
th
e
s
ec
o
n
d
ex
p
lan
atio
n
is
ab
o
u
t
th
e
ev
alu
atio
n
r
es
u
lts
wh
er
e
th
is
s
tu
d
y
co
m
p
a
r
es
with
an
o
th
er
r
e
g
r
ess
io
n
a
lg
o
r
itm
s
.
T
h
e
last
ex
p
lan
atio
n
is
ab
o
u
t
th
e
v
ali
d
atio
n
with
f
u
zz
y
lo
g
ic
as
t
h
e
b
aselin
e
to
s
tr
en
g
th
e
n
th
e
ev
alu
atio
n
r
esu
lts
.
T
ab
le
3
co
n
tain
s
th
e
s
am
p
le
o
f
th
e
f
u
zz
y
lo
g
ic
wate
r
q
u
ality
b
aselin
e
to
g
eth
er
with
p
r
ed
ict
ed
v
alu
es
f
r
o
m
two
FTS
m
o
d
els,
m
u
ltiv
ar
iate
lin
e
ar
r
eg
r
ess
io
n
,
a
n
d
d
ec
is
io
n
tr
e
e
s.
T
ab
le
3
co
n
tain
s
th
e
wate
r
q
u
ality
p
r
ed
ictio
n
s
s
to
r
ed
in
a
d
atab
ase.
T
h
is
tab
le
h
as
s
ev
er
al
co
lu
m
n
s
:
T
h
e
b
aselin
e
co
lu
m
n
was
o
b
tain
ed
f
r
o
m
f
u
zz
if
y
in
g
f
ea
t
u
r
es
with
f
u
zz
y
lo
g
ic
th
at
u
s
ed
T
ab
le
2
as
th
e
co
n
f
ig
u
r
atio
n
.
T
h
e
FTS
-
m
u
lti
v
ar
iate
T
1
was
th
e
f
ir
s
t
FT
S
m
u
ltiv
ar
iate
m
o
d
el
with
o
n
e
d
eg
r
ee
o
f
d
if
f
e
r
en
tial.
Me
an
wh
ile,
th
e
FTS
-
m
u
ltiv
ar
iate
T
2
was
th
e
s
ec
o
n
d
m
o
d
e
l
with
two
d
eg
r
ee
s
o
f
d
if
f
er
e
n
tial.
B
esid
es
th
at,
th
er
e
wer
e
two
m
o
r
e
co
lu
m
n
s
:
lin
ea
r
r
eg
r
ess
io
n
(
th
at
o
p
er
a
ted
in
m
u
ltiv
ar
iate)
an
d
d
ec
is
io
n
tr
ee
.
Ho
wev
er
,
ev
alu
atio
n
ca
n
n
o
t
b
e
d
o
n
e
alo
n
e
with
a
tab
le.
T
h
u
s
,
t
h
is
s
tu
d
y
ev
al
u
ated
th
e
r
es
u
lts
with
s
tatis
tica
l
ap
p
r
o
ac
h
es.
T
h
er
e
ar
e
s
ix
co
m
p
o
n
e
n
ts
o
f
ev
alu
atio
n
th
at
th
is
s
tu
d
y
h
as
d
o
n
e
to
m
ea
s
u
r
e
th
e
p
er
f
o
r
m
a
n
ce
o
f
all
m
o
d
els
.
Fig
u
r
e
3
ex
p
lain
s
th
e
ev
alu
atio
n
r
esu
lts
b
ased
o
n
MA
E
an
d
MA
PE
ev
alu
atio
n
s
.
Sp
ec
if
ically
,
Fig
u
r
es
3
(
a)
an
d
3
(
b
)
p
r
esen
t
th
e
d
etailed
r
esu
lts
o
f
MA
E
an
d
MA
PE
f
r
o
m
all
alg
o
r
ith
m
s
.
T
h
is
ev
alu
ati
o
n
d
eter
m
in
ed
th
e
r
eg
r
ess
io
n
ac
cu
r
ac
y
b
etwe
en
th
e
b
aselin
e
a
n
d
th
e
p
r
ed
ictio
n
r
esu
lt.
T
h
u
s
,
lo
wer
r
esu
lt
is
th
e
tar
g
et
o
f
t
h
e
ev
alu
atio
n
.
Acc
o
r
d
in
g
to
th
e
r
esu
lts
,
FTS
-
m
u
ltiv
ar
iate
T
2
h
as
th
e
lo
west
ev
alu
atio
n
r
esu
lts
wh
er
e
MA
E
was
0
.
0
0
3
3
a
n
d
MA
PE
was
0
.
0
1
7
%.
T
h
e
s
ec
o
n
d
p
lace
was
th
e
d
ec
is
io
n
t
r
ee
m
o
d
el
with
MA
E
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
6
,
No
.
2
,
J
u
ly
20
25
:
1
36
-
1
46
140
0
.
0
2
5
7
an
d
MA
PE
0
.
1
3
4
1
%.
Fo
llo
wed
in
th
e
th
ir
d
p
lace
was
FTS
-
m
u
ltiv
ar
iate
T
1
wit
h
MA
E
0
.
1
6
9
7
an
d
MA
PE
0
.
8
8
3
9
%.
T
h
e
last
p
l
ac
e
f
o
r
th
is
ev
alu
atio
n
was
l
in
ea
r
r
eg
r
ess
io
n
with
MA
E
4
.
0
1
5
5
a
n
d
MA
PE
2
0
.
9
1
7
9
%.
Fro
m
th
ese
r
esu
lts
,
th
is
s
tu
d
y
h
as
f
o
u
n
d
th
e
h
ig
h
est
r
eg
r
ess
io
n
ac
cu
r
ac
y
m
o
d
el.
Ho
wev
er
,
th
e
ev
id
en
ce
was
to
o
s
h
allo
w
to
d
ec
id
e
wh
ich
m
o
d
el
was
th
e
b
est.
T
h
e
n
e
x
t
ev
alu
atio
n
was
a
MSE
an
d
R
MSE
.
T
h
ese
ev
alu
atio
n
s
wer
e
n
ee
d
e
d
to
ev
alu
ate
t
h
e
d
if
f
e
r
en
ce
b
e
twee
n
th
e
r
esu
lts
with
lar
g
er
e
r
r
o
r
p
en
alties.
T
ab
le
3
.
Sam
p
le
o
f
wate
r
q
u
al
ity
p
r
ed
ictio
n
r
esu
lts
B
a
se
l
i
n
e
F
TS
-
m
u
l
t
i
v
a
r
i
a
t
e
T
1
F
TS
-
m
u
l
t
i
v
a
r
i
a
t
e
T
2
Li
n
e
a
r
r
e
g
r
e
s
si
o
n
D
e
c
i
s
i
o
n
t
r
e
e
1
6
.
9
4
7
4
1
6
.
9
5
0
1
1
1
6
.
9
4
7
4
1
8
.
5
2
9
4
7
1
6
.
9
4
6
9
3
1
6
.
7
6
1
1
9
1
9
.
1
0
9
1
1
1
6
.
7
6
1
1
9
1
8
.
8
8
2
9
2
1
6
.
7
6
1
1
9
1
6
.
9
5
7
2
8
1
6
.
9
5
9
9
9
1
6
.
9
5
7
2
8
1
8
.
7
3
8
8
7
1
6
.
9
5
7
4
3
…
1
6
.
7
6
1
1
9
1
6
.
7
6
3
9
1
1
6
.
7
6
1
1
9
1
8
.
8
2
1
0
9
1
6
.
7
6
1
1
9
1
7
.
0
3
0
7
4
1
7
.
0
3
3
4
6
1
7
.
0
3
0
7
4
1
8
.
9
0
6
4
8
1
7
.
0
3
7
4
5
1
6
.
9
5
2
8
3
2
0
.
0
3
4
8
2
1
6
.
9
5
2
8
3
1
8
.
9
6
5
3
5
1
6
.
9
5
2
5
6
(
a)
(
b
)
Fig
u
r
e
3
.
E
v
alu
atio
n
r
esu
lts
f
r
o
m
(
a)
MA
E
a
n
d
(
b
)
MA
PE
Fig
u
r
e
4
ex
p
lain
s
th
e
ev
alu
a
tio
n
r
esu
lts
f
r
o
m
MSE
an
d
R
MSE
a
s
p
ec
ts
.
Fig
u
r
e
4
ex
p
lain
s
th
e
d
if
f
er
en
ce
b
etwe
en
th
e
p
r
ed
ict
io
n
an
d
th
e
b
aselin
e,
with
a
la
r
g
er
p
e
n
alty
f
o
r
er
r
o
r
.
T
h
u
s
,
t
h
e
lo
wer
r
esu
lt
also
m
ea
n
s
th
at
th
e
p
en
alty
o
f
er
r
o
r
is
lo
w
a
s
wel
l.
Fig
u
r
e
4
(
a)
was
th
e
r
esu
lt
o
f
th
e
M
SE
,
an
d
Fig
u
r
e
4
(
b
)
was
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
A
r
o
w
a
n
a
cu
ltiva
tio
n
w
a
ter q
u
a
lity fo
r
ec
a
s
tin
g
w
ith
mu
ltiva
r
ia
te
fu
z
z
y
…
(
A
la
u
d
d
in
Ma
u
la
n
a
Hir
z
a
n
)
141
r
esu
lt
o
f
th
e
R
MSE
.
I
n
Fig
u
r
e
4
(
a
)
,
th
is
s
tu
d
y
f
o
u
n
d
t
h
at
FT
S
-
m
u
ltiv
ar
iate
T
2
h
as
th
e
lo
w
est
er
r
o
r
p
en
alty
o
f
0
.
0
0
4
9
.
T
h
e
s
ec
o
n
d
p
lace
was
Dec
is
io
n
tr
ee
with
an
er
r
o
r
p
en
alty
o
f
u
p
to
0
.
0
7
8
3
,
f
o
llo
we
d
b
y
FTS
-
m
u
ltiv
ar
iate
T
1
with
an
er
r
o
r
p
en
alty
o
f
u
p
to
0
.
4
5
9
8
.
T
h
e
last
p
lace
was
lin
ea
r
r
eg
r
ess
io
n
with
an
e
r
r
o
r
p
en
alty
u
p
to
7
0
.
9
7
4
7
.
Fig
u
r
e
4
(
b
)
s
h
o
ws
th
e
s
im
p
ler
in
t
er
p
r
etatio
n
o
f
Fig
u
r
e
4
(
a
)
,
w
h
er
e
th
e
r
esu
lts
ar
e
s
im
ilar
to
p
r
ev
io
u
s
e
x
p
lan
atio
n
s
.
(
a)
(
b
)
Fig
u
r
e
4
.
E
v
alu
atio
n
r
esu
lts
f
r
o
m
(
a)
MSE
an
d
(
b
)
R
MSE
T
h
e
n
ex
t
ev
al
u
atio
n
is
R
2
an
d
a
d
ju
s
ted
R
2
.
B
o
th
ev
alu
ati
o
n
s
ar
e
u
s
ed
to
e
v
alu
ate
h
o
w
well
th
e
in
d
ep
en
d
en
t
v
ar
iab
le
ex
p
lain
s
th
e
v
ar
iety
o
f
th
e
d
ep
e
n
d
en
t
v
ar
iab
les.
Ad
ju
s
ted
R
2
is
m
o
r
e
f
o
cu
s
ed
o
n
th
e
n
u
m
b
er
o
f
f
ea
t
u
r
es
to
en
s
u
r
e
a
f
air
ev
alu
atio
n
.
Hen
ce
,
a
h
ig
h
er
r
esu
lt
is
r
ec
o
m
m
en
d
e
d
.
Fi
g
u
r
e
5
e
x
p
lain
s
th
e
v
ar
ian
ce
r
esu
lts
f
r
o
m
ea
ch
m
o
d
el
f
o
r
R
2
an
d
a
d
ju
s
ted
R
2
ev
a
lu
atio
n
s
.
Acc
o
r
d
in
g
to
Fig
u
r
e
5
,
th
is
s
t
u
d
y
f
o
u
n
d
th
at
all
m
o
d
els
ex
c
ep
t
lin
ea
r
r
eg
r
ess
io
n
h
av
e
h
ig
h
v
ar
ian
ce
.
As
s
h
o
wn
in
Fig
u
r
e
5
(
a)
,
al
l
m
o
d
els
ex
ce
p
t
lin
ea
r
r
e
g
r
e
s
s
io
n
h
av
e
n
ea
r
-
p
er
f
ec
t
v
a
r
ia
n
ce
r
ea
ch
in
g
0
.
9
9
.
Pre
cisely
,
0
.
9
9
9
9
3
f
o
r
FTS
-
m
u
ltiv
ar
iate
T
2
,
0
.
9
9
8
8
9
f
o
r
d
e
cisi
o
n
tr
ee
,
an
d
0
.
9
9
3
5
1
f
o
r
FTS
-
m
u
ltiv
ar
iate
T
1
.
Me
an
wh
ile,
th
e
lin
ea
r
r
eg
r
ess
io
n
m
o
d
el
f
ailed
to
d
ete
r
m
in
e
th
e
v
a
r
ian
ce
with
r
esu
lt
-
0
.
0
0
1
7
4
.
Fig
u
r
e
5
(
b
)
s
h
ar
ed
a
s
im
ilar
r
esu
lt
wi
th
Fi
g
u
r
e
5
(
a)
e
x
ce
p
t
f
o
r
lin
ea
r
r
e
g
r
ess
io
n
,
wh
er
e
its
r
esu
lt
is
s
til
l
th
e
lo
west
w
ith
-
0
.
0
0
2
2
3
.
T
o
v
alid
ate
th
e
ev
al
u
atio
n
r
esu
lts
,
th
is
s
tu
d
y
co
m
p
ar
ed
th
e
p
r
ed
ictio
n
r
esu
lts
s
i
d
e
-
by
-
s
id
e
with
th
e
b
aselin
e.
Fig
u
r
e
6
s
h
o
ws
th
e
m
o
d
els'
p
r
ed
ictio
n
r
esu
lts
in
c
o
m
p
ar
is
o
n
with
th
e
b
aselin
e.
Sin
ce
th
e
p
r
ed
ictio
n
r
esu
lts
wer
e
to
o
m
an
y
,
th
is
s
tu
d
y
to
o
k
1
0
0
s
eq
u
e
n
ce
d
r
o
ws as a
s
am
p
le
an
d
p
lo
tted
it in
to
a
g
r
ap
h
.
Fig
u
r
e
6
s
h
o
ws
th
e
p
r
e
d
ictio
n
co
m
p
ar
is
o
n
r
esu
lts
o
f
1
0
0
s
am
p
les
b
etwe
en
t
h
e
b
aseli
n
e
an
d
th
e
m
o
d
el'
s
p
r
ed
ictio
n
s
.
Acc
o
r
d
in
g
to
th
e
tim
estep
s
am
p
le
s
h
o
wn
in
Fig
u
r
e
6
,
in
f
o
r
m
atio
n
at
ti
m
estep
2
7
s
h
o
wed
th
at
all
m
o
d
els
wer
e
clo
s
e
to
t
h
e
b
aselin
e
ex
ce
p
t
th
e
lin
ea
r
r
eg
r
ess
io
n
m
o
d
el.
FTS
-
m
u
ltiv
a
r
iate
T
2
h
as
p
r
ec
is
e
p
r
ed
ictio
n
with
2
9
.
2
3
6
2
,
f
o
llo
wed
b
y
FTS
-
m
u
ltiv
ar
iate
T
1
with
2
9
.
2
3
8
9
an
d
d
ec
is
io
n
tr
ee
with
3
0
.
5
3
3
5
.
Me
an
wh
ile,
lin
ea
r
r
eg
r
ess
io
n
was
f
ar
f
r
o
m
p
r
ed
ictio
n
wi
th
r
esu
lt
1
9
.
0
4
0
1
.
T
h
u
s
,
th
e
r
esu
lt
in
Fig
u
r
e
6
va
lid
ated
all
ev
alu
atio
n
r
esu
lts
an
d
s
h
o
wed
t
h
at
FTS
-
m
u
ltiv
a
r
iate
T
2
h
as a
cc
u
r
ate
r
e
g
r
ess
io
n
p
r
ed
ictio
n
s
.
T
h
is
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
6
,
No
.
2
,
J
u
ly
20
25
:
1
36
-
1
46
142
s
tu
d
y
u
s
ed
th
e
cr
o
s
s
-
v
alid
atio
n
m
eth
o
d
to
e
v
alu
ate
th
e
co
n
s
is
ten
cy
o
f
p
r
ed
ictio
n
ac
cu
r
ac
y
.
B
y
ap
p
ly
in
g
5
-
f
o
ld
v
alid
atio
n
,
th
e
a
v
er
ag
e
ac
c
u
r
a
cy
f
o
r
FTS
-
m
u
ltiv
ar
iate
T
2
wa
s
9
9
.
9
8
%,
with
an
e
r
r
o
r
p
er
ce
n
tag
e
o
f
0
.
0
1
6
%.
I
n
co
n
tr
ast,
th
e
ac
cu
r
ac
y
f
o
r
FTS
-
m
u
ltiv
ar
iate
T
1
was
9
9
.
1
3
%,
ac
co
m
p
an
ied
b
y
a
n
er
r
o
r
r
ate
o
f
0
.
8
6
7
%.
T
h
ese
r
esu
lts
in
d
icate
th
at
th
e
ac
cu
r
ac
y
o
f
FTS
m
u
ltiv
ar
iate
m
o
d
els
r
em
a
in
s
b
o
th
h
ig
h
a
n
d
s
tab
le,
ev
en
wh
en
d
if
f
er
en
t le
n
g
th
s
o
f
d
atasets
ar
e
u
s
ed
f
o
r
tr
ain
in
g
.
(
a)
(
b
)
Fig
u
r
e
5
.
E
v
alu
atio
n
r
esu
lts
f
r
o
m
(
a)
R
2
an
d
(
b
)
a
d
ju
s
ted
R
2
Fig
u
r
e
6
.
Pre
d
ictio
n
co
m
p
ar
is
o
n
s
am
p
le
r
esu
lts
with
th
e
b
as
elin
e
(
o
r
ig
in
al
d
ata)
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
A
r
o
w
a
n
a
cu
ltiva
tio
n
w
a
ter q
u
a
lity fo
r
ec
a
s
tin
g
w
ith
mu
ltiva
r
ia
te
fu
z
z
y
…
(
A
la
u
d
d
in
Ma
u
la
n
a
Hir
z
a
n
)
143
Af
ter
ex
p
lain
in
g
th
e
ev
alu
atio
n
an
d
v
alid
atio
n
r
esu
lts
,
th
is
s
tu
d
y
co
n
tin
u
es
to
th
e
d
is
cu
s
s
i
o
n
p
ar
t.
I
n
th
e
d
is
cu
s
s
io
n
p
ar
t,
th
is
s
tu
d
y
ex
p
lain
s
s
ev
er
al
p
o
in
ts
:
r
esu
lt
in
ter
p
r
etatio
n
s
,
co
m
p
ar
is
o
n
with
p
ast
s
tu
d
ies,
im
p
licatio
n
s
,
s
tr
en
g
th
a
n
d
w
ea
k
n
ess
,
an
d
f
u
tu
r
e
s
tu
d
y
.
T
h
e
f
ir
s
t
d
is
cu
s
s
io
n
is
ab
o
u
t
t
h
e
r
esu
lts
o
b
tain
ed
.
Acc
o
r
d
in
g
to
th
e
ev
alu
atio
n
an
d
v
alid
atio
n
r
esu
lts
,
th
e
p
r
o
p
o
s
ed
m
o
d
els
s
h
o
wed
th
e
lo
west
m
ea
n
ab
s
o
lu
te
p
er
ce
n
tag
e
e
r
r
o
r
co
m
p
ar
ed
t
o
o
th
er
m
o
d
els.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
o
f
FTS
-
m
u
ltiv
ar
iate
T
2
h
as
th
e
lo
west
er
r
o
r
o
f
0
.
0
1
7
4
%.
T
h
is
r
esu
lt
m
ea
n
s
th
at
th
e
p
r
o
p
o
s
ed
m
o
d
el
h
as
h
ig
h
ac
cu
r
ac
y
r
ea
c
h
in
g
9
9
%.
T
h
is
ex
p
lan
atio
n
is
p
r
o
v
e
d
in
th
e
v
alid
atio
n
p
h
ase
,
wh
er
e
th
e
p
r
ed
ictio
n
r
esu
lt
is
s
im
ilar
to
th
e
b
aselin
e.
T
h
e
r
u
n
n
er
-
u
p
b
ased
o
n
th
e
lo
west
er
r
o
r
p
e
r
ce
n
tag
e
was
th
e
d
ec
is
io
n
tr
ee
m
o
d
el
,
f
o
llo
wed
b
y
FTS
-
m
u
ltiv
ar
i
ate
T
1
an
d
lin
ea
r
r
eg
r
ess
io
n
.
T
h
er
e
wer
e
o
th
e
r
asp
ec
ts
lik
e
m
ea
n
s
q
u
ar
ed
er
r
o
r
,
r
o
o
t
m
ea
n
s
q
u
ar
ed
e
r
r
o
r
,
R
2
,
an
d
Ad
ju
s
ted
R
2
.
T
h
e
r
esu
lts
in
th
ese
asp
ec
t
s
wer
e
s
im
ilar
with
m
ea
n
a
b
s
o
lu
te
p
er
ce
n
tag
e
er
r
o
r
.
T
h
e
b
est
m
o
d
el
was
FTS
-
m
u
ltiv
ar
iate
T
2
,
f
o
llo
we
d
b
y
d
ec
is
io
n
tr
ee
,
FTS
-
m
u
ltiv
ar
iate
T
1
,
an
d
lin
ea
r
r
e
g
r
ess
io
n
.
T
h
e
s
ec
o
n
d
d
is
cu
s
s
io
n
is
a
b
o
u
t
th
e
co
m
p
ar
is
o
n
with
t
h
e
p
ast
m
o
d
els.
As
ex
p
lai
n
ed
in
t
h
e
in
tr
o
d
u
ctio
n
s
ec
tio
n
,
th
e
p
ast
m
o
d
els
co
u
ld
n
o
t
p
r
e
d
ict
f
u
tu
r
e
s
itu
atio
n
s
.
T
h
u
s
,
th
e
cu
ltiv
ato
r
s
ca
n
n
o
t
p
r
e
d
ict
wh
at
will
h
ap
p
en
in
th
e
f
u
tu
r
e.
T
h
is
p
r
o
b
lem
h
as
b
ee
n
s
o
lv
ed
with
th
e
p
r
o
p
o
s
ed
m
o
d
el
,
wh
er
e
th
is
m
o
d
el
(
esp
ec
ially
FTS
m
u
ltiv
ar
iate
T
2
)
ac
cu
r
ately
p
r
ed
icts
th
e
wate
r
q
u
ality
.
T
h
is
r
esu
lt
h
as
b
ee
n
v
alid
ated
with
th
e
wate
r
q
u
ality
b
aselin
e.
T
h
u
s
,
th
e
p
r
o
p
o
s
ed
m
o
d
el
p
er
f
o
r
m
e
d
b
etter
th
an
p
ast
m
o
d
els
with
th
e
ca
p
ab
ilit
y
to
p
r
ed
ict
th
e
wate
r
q
u
ality
in
th
e
f
u
tu
r
e.
T
h
e
th
ir
d
d
is
cu
s
s
io
n
is
th
e
i
m
p
licatio
n
o
f
th
is
s
tu
d
y
in
th
e
th
eo
r
etica
l
an
d
p
r
ac
tical
ar
ea
s
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
was
a
p
iece
o
f
ev
id
en
ce
f
o
r
f
u
zz
y
-
b
ased
p
r
ed
ictio
n
.
Mo
s
t
s
ch
o
lar
s
k
n
o
w
th
at
f
u
zz
y
lo
g
ic
is
m
o
s
tly
im
p
lem
en
te
d
to
tr
an
s
late
an
y
n
u
m
e
r
ic
i
n
p
u
t
f
r
o
m
a
d
e
v
ice
o
r
a
n
o
d
e
in
t
o
h
u
m
an
in
ter
p
r
etatio
n
.
Ho
wev
er
,
th
e
ca
p
ab
ilit
y
o
f
f
u
zz
y
alg
o
r
ith
m
s
d
id
n
o
t
s
to
p
th
er
e.
A
team
o
f
p
r
o
g
r
am
m
er
s
im
p
r
o
v
e
d
th
e
f
u
zz
y
alg
o
r
ith
m
s
an
d
tu
r
n
ed
it
in
to
a
r
eg
r
ess
io
n
p
r
ed
ictin
g
alg
o
r
ith
m
.
T
h
is
s
tu
d
y
h
as
s
u
cc
es
s
f
u
lly
p
r
o
v
e
d
th
is
alg
o
r
ith
m
'
s
ac
cu
r
ac
y
b
y
im
p
l
em
en
tin
g
it
as
a
wate
r
q
u
alit
y
p
r
ed
ictio
n
.
T
h
e
s
ec
o
n
d
im
p
licatio
n
is
to
war
d
p
r
ac
tical
ar
ea
s
.
T
h
is
s
tu
d
y
h
as
v
alid
ated
its
p
r
o
p
o
s
ed
m
o
d
els
an
d
p
r
o
v
ed
h
o
w
ac
cu
r
ate
th
e
p
r
ed
ictio
n
was.
T
h
is
p
r
o
p
o
s
ed
m
o
d
el
(
FTS
-
m
u
ltiv
ar
iat
e
T
2
)
is
im
p
lem
en
tab
le
in
a
r
o
wan
a
cu
ltiv
atio
n
s
.
I
t
c
an
h
elp
cu
ltiv
ato
r
s
m
itig
ate
f
u
tu
r
e
wate
r
q
u
ality
co
n
d
itio
n
s
m
o
r
e
ac
cu
r
atel
y
an
d
r
ed
u
ce
th
e
n
u
m
b
e
r
o
f
d
ea
d
f
i
s
h
.
I
t
will
lead
to
a
b
etter
ec
o
n
o
m
y
f
o
r
th
e
c
u
ltiv
a
to
r
b
y
r
ed
u
cin
g
th
e
n
u
m
b
e
r
o
f
d
ea
d
f
is
h
.
Fo
r
i
n
s
tan
ce
,
th
e
cu
l
tiv
ato
r
is
n
o
w
ab
le
to
m
o
n
ito
r
wate
r
q
u
ality
p
r
o
a
ctiv
ely
.
T
h
is
p
r
ed
ictiv
e
a
p
p
r
o
ac
h
lead
s
to
a
r
ed
u
ce
d
e
r
r
o
r
m
ar
g
in
an
d
g
r
ea
te
r
ac
cu
r
ac
y
.
T
h
e
f
o
u
r
th
d
is
cu
s
s
io
n
is
ab
o
u
t
th
e
s
tr
en
g
th
s
an
d
wea
k
n
ess
es
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
els.
B
ased
o
n
th
e
ev
a
lu
atio
n
an
d
v
alid
atio
n
p
h
a
s
es,
th
is
s
tu
d
y
f
o
u
n
d
th
at
th
e
p
r
o
p
o
s
ed
m
o
d
el
(
esp
ec
ially
FTS
-
m
u
ltiv
ar
iate
T
2
)
h
as
th
e
h
ig
h
est
ac
cu
r
ac
y
co
m
p
ar
e
d
to
an
o
th
e
r
a
lg
o
r
ith
m
.
Me
a
n
wh
ile,
th
e
o
th
er
al
g
o
r
ith
m
(
FTS
-
m
u
ltiv
ar
iate
T
1
)
p
er
f
o
r
m
ed
p
o
o
r
ly
b
el
o
w
th
e
d
e
cisi
o
n
tr
ee
m
o
d
el.
T
h
er
e
was
a
r
ea
s
o
n
wh
y
FTS
-
m
u
ltiv
ar
iate
T
2
p
er
f
o
r
m
ed
b
etter
th
an
FTS
-
m
u
ltiv
ar
ia
te
T
1
.
T
h
e
k
ey
was
in
th
e
d
eg
r
ee
o
f
d
if
f
er
e
n
tials
.
T
h
e
d
eg
r
e
e
o
f
d
if
f
er
e
n
tial
was
u
s
ed
to
r
em
o
v
e
tr
en
d
s
in
s
id
e
th
e
d
ataset
an
d
m
ak
e
i
t
m
o
r
e
s
tatio
n
ar
y
.
FTS
-
m
u
ltiv
ar
iate
T
2
p
r
ed
icte
d
m
o
r
e
ac
cu
r
ately
th
a
n
FTS
-
m
u
ltiv
ar
iate
T
1
is
ca
u
s
ed
b
y
lef
to
v
er
tr
en
d
s
in
th
e
f
ir
s
t
d
eg
r
ee
o
f
d
if
f
er
e
n
tial
(
th
e
s
ec
o
n
d
d
e
g
r
ee
o
f
d
if
f
e
r
en
tia
l
o
f
f
e
r
ed
a
clea
n
e
r
a
n
d
m
o
r
e
s
tatio
n
ar
y
d
ataset)
.
T
h
u
s
,
FTS
-
m
u
ltiv
ar
iate
T
2
ca
n
u
n
d
er
s
tan
d
th
e
s
ea
s
o
n
alit
y
o
f
th
e
d
ataset
m
o
r
e
th
an
FTS
-
m
u
ltiv
ar
iate
T
1
.
On
e
o
f
th
is
alg
o
r
ith
m
'
s
s
tr
en
g
th
s
i
s
its
s
ca
lab
ilit
y
.
T
h
e
FTS
-
m
u
ltiv
ar
iate
m
o
d
el
(
b
o
t
h
T
1
an
d
T
2
)
d
em
o
n
s
tr
ates
co
n
s
id
er
ab
le
f
le
x
ib
ilit
y
r
eg
ar
d
in
g
s
ca
lin
g
.
I
t
ca
n
b
e
im
p
l
em
en
ted
in
a
lar
g
er
a
q
u
ar
i
u
m
.
As
lo
n
g
a
s
th
e
n
ec
ess
ar
y
d
ataset
an
d
s
en
s
o
r
s
ar
e
a
v
ailab
le,
it
ca
n
b
e
s
ca
le
d
u
p
f
o
r
m
o
r
e
ex
ten
s
iv
e
ap
p
l
icatio
n
s
with
o
n
l
y
m
in
o
r
ad
j
u
s
tm
en
ts
,
s
u
ch
as a
g
g
r
eg
atin
g
d
ata
f
r
o
m
m
u
ltip
le
s
en
s
o
r
s
.
Ho
wev
er
,
th
e
d
etec
tio
n
r
an
g
e
d
ep
en
d
s
en
tire
ly
o
n
th
e
ty
p
e
an
d
q
u
ality
o
f
th
e
s
en
s
o
r
s
u
s
ed
.
Ho
wev
er
,
b
o
th
m
o
d
els
s
u
f
f
e
r
ed
s
im
ilar
wea
k
n
ess
es.
B
o
th
m
o
d
els
r
e
q
u
ir
ed
a
tim
e
s
er
ies
ty
p
e
o
f
d
ataset.
An
im
ag
e
d
ataset
is
an
ex
am
p
le
o
f
a
d
a
taset
th
at
is
d
if
f
icu
lt
to
b
e
u
s
ed
with
th
is
alg
o
r
ith
m
.
Hen
c
e,
th
is
alg
o
r
ith
m
is
u
n
s
u
itab
le
f
o
r
th
at
ty
p
e
o
f
d
at
a.
T
h
e
s
ec
o
n
d
wea
k
n
ess
o
f
th
i
s
p
r
o
p
o
s
ed
m
o
d
el
is
its
lim
ite
d
ap
p
licatio
n
.
Sin
ce
it
was
cu
r
ated
with
a
r
o
wan
a'
s
d
ataset
an
d
p
ar
am
eter
s
,
it
m
i
g
h
t
b
e
u
n
s
u
itab
le
f
o
r
an
o
th
e
r
ty
p
e
o
f
f
is
h
.
T
h
u
s
,
r
etr
ain
in
g
th
e
m
o
d
el
with
a
p
r
o
p
er
d
ataset
is
r
ec
o
m
m
en
d
e
d
.
T
h
e
last
d
is
cu
s
s
io
n
is
ab
o
u
t
th
e
f
u
tu
r
e
p
o
s
s
ib
ilit
y
o
f
th
is
s
tu
d
y
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
els
ar
e
s
till
g
r
o
win
g
.
T
h
er
e
ar
e
m
a
n
y
c
h
an
ce
s
to
im
p
r
o
v
e
th
e
cu
r
r
en
t
m
o
d
el
b
y
im
p
lem
en
tin
g
n
u
m
e
r
o
u
s
tim
e
s
er
ies
-
b
ased
alg
o
r
ith
m
s
.
Fo
r
ex
am
p
le,
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
,
au
t
o
r
eg
r
ess
iv
e
in
teg
r
ate
d
m
o
v
in
g
av
er
a
g
e,
o
r
s
ea
s
o
n
al
au
to
r
eg
r
ess
iv
e
in
teg
r
ated
m
o
v
in
g
a
v
er
ag
e.
B
ased
o
n
th
e
d
is
cu
s
s
io
n
s
,
th
is
s
tu
d
y
ca
n
co
n
clu
d
e
th
at
th
e
p
r
o
p
o
s
ed
m
o
d
els
ar
e
s
u
cc
ess
f
u
l
ly
ca
p
ab
le
to
p
r
e
d
ict
th
e
wate
r
q
u
ality
.
T
h
e
FTS
-
m
u
ltiv
ar
iate
T
2
m
o
d
el
is
th
e
b
est
m
o
d
el
with
th
e
h
ig
h
est
ac
c
u
r
ac
y
co
m
p
ar
ed
to
o
th
er
alg
o
r
ith
m
s
.
Fo
llo
wed
b
y
d
ec
is
io
n
tr
ee
,
FTS
-
m
u
ltiv
ar
iate
T
1
an
d
lin
ea
r
r
e
g
r
ess
io
n
.
I
n
s
u
m
m
ar
y
,
th
is
p
r
ed
ictiv
e
m
o
d
el
s
er
v
es
as
a
s
o
p
h
is
tica
ted
r
eso
u
r
ce
f
o
r
en
h
a
n
cin
g
wate
r
q
u
ality
m
an
ag
em
en
t
in
a
r
o
w
an
a
a
q
u
ac
u
ltu
r
e,
f
ac
ilit
atin
g
th
e
ad
o
p
tio
n
o
f
m
o
r
e
s
u
s
tain
ab
le
p
r
ac
tices.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
3
2
2
1
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
,
Vo
l.
6
,
No
.
2
,
J
u
ly
20
25
:
1
36
-
1
46
144
4.
CO
NCLU
SI
O
N
W
ater
q
u
ality
is
an
im
p
o
r
tan
t
asp
ec
t
th
at
af
f
ec
ts
a
r
o
wan
a
’
s
g
r
o
wth
.
Failin
g
to
b
alan
ce
th
e
f
iv
e
p
ar
am
eter
s
(
p
H,
tem
p
e
r
atu
r
e,
tu
r
b
id
ity
,
d
is
s
o
lv
ed
o
x
y
g
en
,
an
d
co
n
d
u
ctiv
ity
)
m
ay
r
e
n
d
er
a
r
o
wan
a'
s
g
r
o
wth
an
d
in
c
r
ea
s
e
th
e
n
u
m
b
er
o
f
d
ea
d
f
is
h
.
Ma
n
y
p
a
s
t
s
tu
d
ies
p
r
o
p
o
s
ed
m
an
y
d
i
f
f
er
en
t
m
o
d
e
ls
to
m
itig
ate
th
is
p
r
o
b
lem
.
So
m
e
p
r
o
p
o
s
ed
a
m
o
n
ito
r
in
g
m
o
d
el
with
Ar
d
u
i
n
o
I
DE
,
an
d
s
o
m
e
u
s
ed
an
i
n
tr
in
s
ic
ap
p
r
o
ac
h
to
m
ak
e
th
e
m
o
n
ito
r
in
g
r
esu
lts
e
asier
to
r
ea
d
.
Ho
wev
er
,
th
er
e
is
a
p
r
o
b
lem
with
th
e
p
ast
m
o
d
els.
T
h
ey
wer
e
n
o
t
eq
u
ip
p
e
d
with
a
p
r
ed
ictio
n
al
g
o
r
ith
m
to
p
r
e
d
ict
wh
at
wo
u
ld
h
ap
p
en
in
t
h
e
f
u
tu
r
e.
T
h
u
s
,
th
e
cu
ltiv
ato
r
s
ca
n
n
o
t
m
itig
ate
wh
en
a
s
itu
atio
n
o
cc
u
r
s
.
T
o
s
o
lv
e
th
is
p
r
o
b
lem
,
th
i
s
s
tu
d
y
d
esig
n
ed
a
p
r
e
d
ictio
n
m
o
d
el
b
ased
o
n
t
h
e
I
oT
co
m
b
in
e
d
with
a
FTS
a
lg
o
r
ith
m
.
B
ased
o
n
th
e
ev
alu
atio
n
an
d
v
alid
atio
n
,
th
e
p
r
o
p
o
s
ed
m
o
d
els (
esp
ec
ially
FTS
-
m
u
ltiv
ar
iate
T
2
)
ac
h
iev
e
d
a
lo
w
p
er
ce
n
tag
e
o
f
er
r
o
r
r
ea
ch
in
g
0
.
0
1
7
0
4
%.
Fo
llo
we
d
b
y
d
ec
is
io
n
tr
ee
0
.
1
3
4
1
0
,
FTS
-
m
u
ltiv
ar
iate
T
1
with
0
.
8
8
3
9
7
a
n
d
lin
ea
r
r
eg
r
ess
io
n
2
0
.
9
1
7
9
1
.
T
h
ese
r
esu
lts
also
al
ig
n
ed
with
th
e
b
aselin
e
in
th
e
v
alid
atio
n
p
h
ase.
T
h
is
s
tu
d
y
c
o
n
clu
d
e
d
t
h
at
th
e
p
r
o
p
o
s
ed
m
o
d
el
(
FTS
-
m
u
ltiv
ar
iate
T
2
)
is
n
o
t
o
n
ly
ca
p
ab
le
o
f
p
r
ed
ictin
g
wate
r
q
u
ality
b
u
t
also
o
f
f
er
s
lo
wer
m
ea
n
ab
s
o
lu
te
p
er
ce
n
t
a
g
e
er
r
o
r
co
m
p
ar
ed
to
o
th
er
alg
o
r
ith
m
s
.
ACK
NO
WL
E
DG
M
E
N
T
S
T
h
e
au
th
o
r
s
wo
u
l
d
lik
e
t
o
ex
p
r
ess
th
eir
s
in
ce
r
e
g
r
atitu
d
e
t
o
L
em
b
a
g
a
Pen
elitian
d
an
Pe
n
g
ab
d
ia
n
Kep
ad
a
Ma
s
y
ar
ak
at
(
L
PP
M)
Sem
ar
an
g
Un
iv
er
s
ity
f
o
r
t
h
e
in
v
al
u
ab
le
s
u
p
p
o
r
t
an
d
r
eso
u
r
ce
s
p
r
o
v
id
ed
th
r
o
u
g
h
o
u
t
th
is
r
esear
ch
.
W
e
d
ee
p
ly
ap
p
r
ec
iate
th
e
g
u
id
a
n
ce
,
f
ac
ilit
ies,
an
d
ac
a
d
em
ic
en
v
ir
o
n
m
e
n
t
th
at
co
n
tr
ib
u
ted
to
th
e
s
u
cc
ess
f
u
l
co
m
p
letio
n
o
f
th
is
s
tu
d
y
.
Sp
e
cial
th
an
k
s
to
th
e
f
ac
u
lty
m
e
m
b
er
s
,
r
esear
ch
s
taf
f
,
an
d
f
ello
w
co
lleag
u
es
f
o
r
th
e
ir
co
n
s
tr
u
ctiv
e
f
ee
d
b
ac
k
an
d
en
co
u
r
a
g
em
en
t.
T
h
is
wo
r
k
w
o
u
ld
n
o
t
h
av
e
b
ee
n
p
o
s
s
ib
le
with
o
u
t th
e
u
n
iv
er
s
ity
’
s
co
m
m
itm
en
t to
f
o
s
ter
in
g
i
n
n
o
v
atio
n
an
d
s
cien
tific
ex
p
lo
r
atio
n
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
s
tu
d
y
is
f
u
n
d
e
d
b
y
L
em
b
ag
a
Pen
elitian
d
an
Pen
g
ab
d
ian
Kep
ad
a
Ma
s
y
ar
ak
at
Sem
ar
an
g
Un
iv
er
s
ity
u
n
d
e
r
co
n
t
r
ac
t n
u
m
b
er
: 0
8
3
/USM.
H7
.
L
PP
M/L
/2
0
2
4
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
t
r
ib
u
to
r
R
o
les
T
a
x
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
i
d
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Ala
u
d
d
i
n
M
a
u
lan
a
Hirz
a
n
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Ap
ril
F
irma
n
Da
ru
✓
✓
✓
✓
✓
✓
✓
✓
Len
n
y
M
a
rg
a
re
tt
a
Hu
ize
n
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
I
NF
O
RM
E
D
CO
NS
E
N
T
W
e
h
av
e
o
b
tain
ed
in
f
o
r
m
ed
c
o
n
s
en
t f
r
o
m
all
in
d
iv
id
u
als in
c
lu
d
ed
in
t
h
is
s
tu
d
y
.
E
T
H
I
CAL AP
P
RO
V
AL
T
h
e
r
esear
ch
r
elate
d
to
an
i
m
a
l
u
s
e
h
as
b
ee
n
co
m
p
lied
with
all
th
e
r
elev
an
t
n
atio
n
al
r
eg
u
l
atio
n
s
an
d
in
s
titu
tio
n
al
p
o
licies f
o
r
th
e
ca
r
e
an
d
u
s
e
o
f
an
im
als.
Evaluation Warning : The document was created with Spire.PDF for Python.
C
o
m
p
u
t Sci
I
n
f
T
ec
h
n
o
l
I
SS
N:
2722
-
3
2
2
1
A
r
o
w
a
n
a
cu
ltiva
tio
n
w
a
ter q
u
a
lity fo
r
ec
a
s
tin
g
w
ith
mu
ltiva
r
ia
te
fu
z
z
y
…
(
A
la
u
d
d
in
Ma
u
la
n
a
Hir
z
a
n
)
145
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
a
v
ailab
l
e
f
r
o
m
th
e
co
r
r
esp
o
n
d
in
g
au
t
h
o
r
,
AM
H,
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
G
.
H
.
Y
u
e
,
A
.
C
h
a
n
g
,
A
.
Y
u
z
e
r
,
a
n
d
A
.
S
u
w
a
n
t
o
,
“
C
u
r
r
e
n
t
k
n
o
w
l
e
d
g
e
o
n
t
h
e
b
i
o
l
o
g
y
a
n
d
a
q
u
a
c
u
l
t
u
r
e
o
f
t
h
e
e
n
d
a
n
g
e
r
e
d
A
s
i
a
n
a
r
o
w
a
n
a
,
”
R
e
v
i
e
w
s
i
n
F
i
s
h
e
r
i
e
s
S
c
i
e
n
c
e
&
A
q
u
a
c
u
l
t
u
r
e
,
v
o
l
.
2
8
,
n
o
.
2
,
p
p
.
1
9
3
–
2
1
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
8
0
/
2
3
3
0
8
2
4
9
.
2
0
1
9
.
1
6
9
7
6
4
1
.
[
2
]
S
.
R
.
M
e
d
i
p
a
l
l
y
,
F
.
M
.
Y
u
s
o
f
f
,
N
.
S
h
a
r
i
f
h
u
d
d
i
n
,
a
n
d
M
.
S
h
a
r
i
f
f
,
“
S
u
s
t
a
i
n
a
b
l
e
a
q
u
a
c
u
l
t
u
r
e
o
f
A
s
i
a
n
a
r
o
w
a
n
a
-
a
r
e
v
i
e
w
,
”
J
o
u
rn
a
l
o
f
En
v
i
r
o
n
m
e
n
t
a
l
Bi
o
l
o
g
y
,
v
o
l
.
3
7
,
n
o
.
4
,
p
p
.
8
2
9
–
8
3
8
,
2
0
1
6
.
[
3
]
A
.
S
.
P
a
n
j
a
i
t
a
n
,
F
.
H
a
p
sari
,
M
.
M
a
r
g
o
n
o
,
a
n
d
H
.
A
l
-
Q
o
y
y
i
m
a
h
,
“
V
a
r
i
e
t
y
t
y
p
e
s
o
f
n
a
t
u
r
a
l
f
o
o
d
f
i
s
h
u
sa
g
e
i
n
t
h
e
g
r
o
w
t
h
o
f
s
u
p
e
r
r
e
d
a
r
o
w
a
n
a
f
i
sh
(
S
c
l
e
r
o
p
a
g
e
s
f
o
r
mo
s
u
s)
,
”
E
d
u
v
e
st
-
J
o
u
rn
a
l
o
f
U
n
i
v
e
r
sa
l
S
t
u
d
i
e
s
,
v
o
l
.
3
,
n
o
.
4
,
p
p
.
8
4
2
–
8
4
9
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
5
9
1
8
8
/
e
d
u
v
e
st
.
v
3
i
4
.
7
9
6
.
[
4
]
J.
W
.
S
e
n
d
e
r
s a
n
d
N
.
P
.
M
o
r
a
y
,
H
u
m
a
n
e
r
ro
r:
c
a
u
s
e
,
p
re
d
i
c
t
i
o
n
,
a
n
d
r
e
d
u
c
t
i
o
n
,
C
R
C
P
r
e
ss,
2
0
2
0
.
[
5
]
J.
Tr
e
v
a
t
h
a
n
a
n
d
D
.
N
g
u
y
e
n
,
“
A
d
a
p
t
i
v
e
I
o
T
t
e
c
h
n
o
l
o
g
y
f
o
r
me
a
su
r
i
n
g
sa
l
i
n
i
t
y
,
d
i
ss
o
l
v
e
d
o
x
y
g
e
n
,
a
n
d
p
H
i
n
a
q
u
a
t
i
c
e
n
v
i
r
o
n
m
e
n
t
s
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
H
y
p
e
rc
o
n
n
e
c
t
i
v
i
t
y
a
n
d
t
h
e
I
n
t
e
rn
e
t
o
f
T
h
i
n
g
s
,
v
o
l
.
6
,
n
o
.
1
,
p
p
.
1
–
2
0
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
4
0
1
8
/
I
JH
I
o
T.
2
9
4
8
9
4
.
[
6
]
A
.
R
e
h
m
a
n
,
T.
S
a
b
a
,
M
.
K
a
s
h
i
f
,
S
.
M
.
F
a
t
i
,
S
.
A
.
B
a
h
a
j
,
a
n
d
H
.
C
h
a
u
d
h
r
y
,
“
A
r
e
v
i
si
t
o
f
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
t
e
c
h
n
o
l
o
g
i
e
s
f
o
r
mo
n
i
t
o
r
i
n
g
a
n
d
c
o
n
t
r
o
l
s
t
r
a
t
e
g
i
e
s
i
n
sm
a
r
t
a
g
r
i
c
u
l
t
u
r
e
,”
Ag
r
o
n
o
m
y
,
v
o
l
.
1
2
,
n
o
.
1
,
p
p
.
1
-
2
1
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
a
g
r
o
n
o
m
y
1
2
0
1
0
1
2
7
.
[
7
]
A
.
F
.
D
a
r
u
,
F
.
W
.
C
h
r
i
s
t
a
n
t
o
,
a
n
d
V
.
V
y
d
i
a
,
“
I
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
-
b
a
s
e
d
w
a
t
e
r
p
H
l
e
v
e
l
mo
n
i
t
o
r
i
n
g
f
o
r
a
r
o
w
a
n
a
c
u
l
t
i
v
a
t
i
o
n
,
”
I
O
P
C
o
n
f
e
re
n
c
e
S
e
r
i
e
s:
E
a
r
t
h
a
n
d
E
n
v
i
r
o
n
m
e
n
t
a
l
S
c
i
e
n
c
e
,
v
o
l
.
1
1
7
7
,
n
o
.
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
5
5
-
1
3
1
5
/
1
1
7
7
/
1
/
0
1
2
0
0
4
.
[
8
]
J.
E.
d
a
C
o
s
t
a
a
n
d
A
.
W
.
R
.
Ema
n
u
e
l
,
“
I
O
T
d
e
si
g
n
mo
n
i
t
o
r
i
n
g
w
a
t
e
r
t
a
n
k
st
u
d
y
c
a
se
:
I
n
st
i
t
u
t
o
p
r
o
f
i
ssi
o
n
a
l
d
e
c
a
n
o
ssa
(
I
P
D
C
)
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
S
c
i
e
n
c
e
a
n
d
Ap
p
l
i
e
d
S
c
i
e
n
c
e
(
I
C
S
AS
)
2
0
2
0
,
AI
P
C
o
n
f
e
re
n
c
e
Pr
o
c
e
e
d
i
n
g
s
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
6
3
/
5
.
0
0
3
2
6
3
8
.
[
9
]
M
.
F
.
S
u
h
a
i
mi
,
N
.
H
u
d
a
,
M
.
Ta
h
i
r
,
S
.
N
.
M
o
h
a
m
a
d
,
a
n
d
S
.
R
.
A
w
,
“
I
O
T
b
a
s
e
d
a
u
t
o
ma
t
i
c
a
q
u
a
r
i
u
m
m
o
n
i
t
o
r
i
n
g
s
y
s
t
e
m
f
o
r
f
r
e
sh
w
a
t
e
r
f
i
sh
,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
S
y
n
e
r
g
y
i
n
E
n
g
i
n
e
e
ri
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
2
,
n
o
.
1
,
p
p
.
1
2
5
–
1
3
3
,
2
0
2
1
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
t
a
t
i
u
c
.
e
d
u
.
m
y
/
i
j
se
t
/
i
n
d
e
x
.
p
h
p
/
i
j
s
e
t
/
a
r
t
i
c
l
e
/
v
i
e
w
/
9
5
[
1
0
]
W
.
S
h
o
l
i
h
a
h
,
A
.
H
e
n
d
r
i
a
n
a
,
I
.
K
u
su
m
a
n
t
i
,
a
n
d
I
.
N
o
v
i
a
n
t
y
,
“
D
e
si
g
n
o
f
I
o
T
b
a
s
e
d
w
a
t
e
r
m
o
n
i
t
o
r
i
n
g
sy
s
t
e
m
(
si
mo
n
a
i
r
)
f
o
r
a
r
w
a
n
a
f
i
sh
c
u
l
t
i
v
a
t
i
o
n
,
”
E
d
u
v
e
s
t
-
J
o
u
rn
a
l
o
f
U
n
i
v
e
rs
a
l
S
t
u
d
i
e
s
,
v
o
l
.
2
,
n
o
.
1
2
,
p
p
.
2
8
7
2
–
2
8
8
4
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
5
9
1
8
8
/
e
d
u
v
e
st
.
v
2
i
1
2
.
7
0
8
.
[
1
1
]
F
.
L.
To
r
u
a
n
a
n
d
M
.
G
a
l
i
n
a
,
“
I
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
-
b
a
se
d
a
u
t
o
ma
t
i
c
f
e
e
d
e
r
a
n
d
m
o
n
i
t
o
r
i
n
g
o
f
w
a
t
e
r
t
e
mp
e
r
a
t
u
r
e
,
p
H
,
a
n
d
s
a
l
i
n
i
t
y
f
o
r
l
i
t
o
p
e
n
a
e
u
s
v
a
n
n
a
me
i
s
h
r
i
m
p
,
”
J
u
r
n
a
l
ELT
I
K
O
M
,
v
o
l
.
7
,
n
o
.
1
,
p
p
.
9
–
2
0
,
J
u
n
.
2
0
2
3
,
d
o
i
:
1
0
.
3
1
9
6
1
/
e
l
t
i
k
o
m.
v
7
i
1
.
6
5
8
.
[
1
2
]
A
.
C
.
B
e
n
t
o
,
“
I
o
T
:
n
o
d
e
M
C
U
1
2
e
X
a
r
d
u
i
n
o
u
n
o
,
r
e
su
l
t
s
o
f
a
n
e
x
p
e
r
i
me
n
t
a
l
a
n
d
c
o
mp
a
r
a
t
i
v
e
s
u
r
v
e
y
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ad
v
a
n
c
e
Re
s
e
a
r
c
h
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
M
a
n
a
g
e
m
e
n
t
S
t
u
d
i
e
s
,
v
o
l
.
6
,
n
o
.
1
,
p
p
.
4
6
–
5
6
,
2
0
1
8
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
s
c
i
-
h
u
b
.
s
e
/
h
t
t
p
s:
/
/
p
d
f
s
.
sem
a
n
t
i
c
sc
h
o
l
a
r
.
o
r
g
/
8
4
c
4
/
7
1
4
7
0
c
c
3
c
8
e
2
7
8
0
7
d
f
6
0
a
a
5
d
d
e
2
8
8
8
c
c
3
b
3
f
.
p
d
f
%0
A
w
w
w
.
i
j
a
r
c
sms
.
c
o
m
.
[
1
3
]
B
.
S
t
r
a
u
c
h
,
“
J
o
h
n
se
n
d
e
r
s,
h
u
ma
n
e
r
r
o
r
,
a
n
d
s
y
st
e
m
saf
e
t
y
,
”
H
u
m
a
n
Fa
c
t
o
rs
,
v
o
l
.
6
5
,
n
o
.
5
,
p
p
.
7
6
6
–
7
7
8
,
A
u
g
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
7
7
/
0
0
1
8
7
2
0
8
2
1
1
0
0
1
9
8
2
.
[
1
4
]
P
.
C
.
d
e
L.
e
S
i
l
v
a
,
C
.
A
.
S
e
v
e
r
i
a
n
o
,
M
.
A
.
A
l
v
e
s,
R
.
S
i
l
v
a
,
M
.
W
.
C
o
h
e
n
,
a
n
d
F
.
G
.
G
u
i
mar
ã
e
s,
“
F
o
r
e
c
a
s
t
i
n
g
i
n
n
o
n
-
st
a
t
i
o
n
a
r
y
e
n
v
i
r
o
n
m
e
n
t
s
w
i
t
h
f
u
z
z
y
t
i
me
s
e
r
i
e
s,”
A
p
p
l
i
e
d
S
o
f
t
C
o
m
p
u
t
i
n
g
J
o
u
r
n
a
l
,
v
o
l
.
9
7
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
so
c
.
2
0
2
0
.
1
0
6
8
2
5
.
[
1
5
]
O
.
O
r
a
n
g
,
R
.
S
i
l
v
a
,
P
.
C
.
d
e
L.
e
S
i
l
v
a
,
a
n
d
F
.
G
.
G
u
i
mar
a
e
s,
“
S
o
l
a
r
e
n
e
r
g
y
f
o
r
e
c
a
s
t
i
n
g
w
i
t
h
f
u
z
z
y
t
i
me
ser
i
e
s
u
s
i
n
g
h
i
g
h
-
o
r
d
e
r
f
u
z
z
y
c
o
g
n
i
t
i
v
e
m
a
p
s
,
”
i
n
2
0
2
0
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Fu
zzy
S
y
st
e
m
s
(
FU
Z
Z
-
I
EEE)
,
J
u
l
.
2
0
2
0
,
p
p
.
1
–
8
,
d
o
i
:
1
0
.
1
1
0
9
/
F
U
Z
Z4
8
6
0
7
.
2
0
2
0
.
9
1
7
7
7
6
7
.
[
1
6
]
Y
.
A
l
y
o
u
s
i
f
i
,
M
.
O
t
h
ma
n
,
R
.
S
o
k
k
a
l
i
n
g
a
m,
I
.
F
a
y
e
,
a
n
d
P
.
C
.
L.
S
i
l
v
a
,
“
P
r
e
d
i
c
t
i
n
g
d
a
i
l
y
a
i
r
p
o
l
l
u
t
i
o
n
i
n
d
e
x
b
a
s
e
d
o
n
f
u
z
z
y
t
i
me
seri
e
s
mar
k
o
v
c
h
a
i
n
m
o
d
e
l
,
”
S
y
m
m
e
t
r
y
,
v
o
l
.
1
2
,
n
o
.
2
,
p
.
2
9
3
,
F
e
b
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
s
y
m
1
2
0
2
0
2
9
3
.
[
1
7
]
G
.
C
o
x
a
n
d
J.
L
u
n
d
,
“
Ti
m
e
.
n
o
w
,
”
i
n
U
n
c
e
rt
a
i
n
Arc
h
i
v
e
s:
C
r
i
t
i
c
a
l
K
e
y
w
o
r
d
s
f
o
r
Bi
g
D
a
t
a
,
M
I
T
P
r
e
ss,
2
0
2
1
,
p
p
.
5
2
3
–
5
3
2
,
d
o
i
:
1
0
.
7
5
5
1
/
mi
t
p
r
e
ss
/
1
2
2
3
6
.
0
0
3
.
0
0
5
7
.
[
1
8
]
G
.
H
e
sam
i
a
n
a
n
d
M
.
G
.
A
k
b
a
r
i
,
“
A
r
o
b
u
s
t
m
u
l
t
i
p
l
e
r
e
g
r
e
ssi
o
n
m
o
d
e
l
b
a
s
e
d
o
n
f
u
z
z
y
r
a
n
d
o
m
v
a
r
i
a
b
l
e
s,”
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
a
t
i
o
n
a
l
a
n
d
A
p
p
l
i
e
d
M
a
t
h
e
m
a
t
i
c
s
,
v
o
l
.
3
8
8
,
M
a
y
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
a
m
.
2
0
2
0
.
1
1
3
2
7
0
.
[
1
9
]
J.
C
h
a
c
h
i
,
S
.
M
.
T
a
h
e
r
i
,
a
n
d
P
.
D
’
U
r
so
,
“
F
u
z
z
y
r
e
g
r
e
s
si
o
n
a
n
a
l
y
si
s
b
a
se
d
o
n
M
-
e
st
i
ma
t
e
s
,
”
Ex
p
e
r
t
S
y
st
e
m
s
w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
8
7
,
J
a
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
s
w
a
.
2
0
2
1
.
1
1
5
8
9
1
.
[
2
0
]
P
.
C
.
d
e
L
.
e
S
i
l
v
a
e
t
a
l
.
,
“
P
Y
F
TS/
p
y
F
TS:
S
t
a
b
l
e
v
e
r
si
o
n
1
.
7
,
”
Z
e
n
o
d
o
,
2
0
1
9
,
d
o
i
:
1
0
.
5
2
8
1
/
z
e
n
o
d
o
.
7
8
6
0
2
3
1
.
[
2
1
]
I
.
A
h
ma
d
,
E.
S
u
w
a
r
n
i
,
R
.
I
.
B
o
r
ma
n
,
A
smaw
a
t
i
,
F
.
R
o
ssi
,
a
n
d
Y
.
J
u
s
man
,
“
I
mp
l
e
m
e
n
t
a
t
i
o
n
o
f
R
ES
Tf
u
l
A
P
I
w
e
b
s
e
r
v
i
c
e
s
a
r
c
h
i
t
e
c
t
u
r
e
i
n
t
a
k
e
a
w
a
y
a
p
p
l
i
c
a
t
i
o
n
d
e
v
e
l
o
p
m
e
n
t
,
”
i
n
2
0
2
1
1
s
t
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
E
l
e
c
t
r
o
n
i
c
a
n
d
E
l
e
c
t
ri
c
a
l
En
g
i
n
e
e
ri
n
g
a
n
d
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
(
I
C
E3
I
S
)
,
O
c
t
.
2
0
2
1
,
p
p
.
1
3
2
–
137
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
E3
I
S
5
4
1
0
2
.
2
0
2
1
.
9
6
4
9
6
7
9
.
[
2
2
]
A
.
Eh
sa
n
,
M
.
A
.
M
.
E.
A
b
u
h
a
l
i
q
a
,
C
.
C
a
t
a
l
,
a
n
d
D
.
M
i
s
h
r
a
,
“
R
ESTf
u
l
A
P
I
t
e
st
i
n
g
me
t
h
o
d
o
l
o
g
i
e
s:
r
a
t
i
o
n
a
l
e
,
c
h
a
l
l
e
n
g
e
s
,
a
n
d
so
l
u
t
i
o
n
d
i
r
e
c
t
i
o
n
s
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
2
,
n
o
.
9
,
A
p
r
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
2
0
9
4
3
6
9
.
[
2
3
]
D
.
S
.
K
.
K
a
r
u
n
a
si
n
g
h
a
,
“
R
o
o
t
m
e
a
n
s
q
u
a
r
e
e
r
r
o
r
o
r
m
e
a
n
a
b
s
o
l
u
t
e
e
r
r
o
r
?
u
se
t
h
e
i
r
r
a
t
i
o
a
s
w
e
l
l
,
”
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
5
8
5
,
p
p
.
6
0
9
–
6
2
9
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
s
.
2
0
2
1
.
1
1
.
0
3
6
.
[
2
4
]
T.
O
.
H
o
d
s
o
n
,
“
R
o
o
t
-
mea
n
-
s
q
u
a
r
e
e
r
r
o
r
(
R
M
S
E)
o
r
m
e
a
n
a
b
s
o
l
u
t
e
e
r
r
o
r
(
M
A
E)
:
w
h
e
n
t
o
u
se
t
h
e
m
o
r
n
o
t
,
”
G
e
o
sc
i
e
n
t
i
f
i
c
M
o
d
e
l
D
e
v
e
l
o
p
m
e
n
t
,
v
o
l
.
1
5
,
n
o
.
1
4
,
p
p
.
5
4
8
1
–
5
4
8
7
,
Ju
l
.
2
0
2
2
,
d
o
i
:
1
0
.
5
1
9
4
/
g
m
d
-
15
-
5
4
8
1
-
2
0
2
2
.
[
2
5
]
J.
M
.
H
a
h
n
e
e
t
a
l
.
,
“
L
i
n
e
a
r
a
n
d
n
o
n
l
i
n
e
a
r
r
e
g
r
e
ss
i
o
n
t
e
c
h
n
i
q
u
e
s
f
o
r
s
i
m
u
l
t
a
n
e
o
u
s
a
n
d
p
r
o
p
o
r
t
i
o
n
a
l
m
y
o
e
l
e
c
t
r
i
c
c
o
n
t
r
o
l
,”
I
EE
E
T
ra
n
s
a
c
t
i
o
n
s
o
n
N
e
u
r
a
l
S
y
st
e
m
s
a
n
d
R
e
h
a
b
i
l
i
t
a
t
i
o
n
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
2
,
n
o
.
2
,
p
p
.
2
6
9
–
2
7
9
,
M
a
r
.
2
0
1
4
,
d
o
i
:
1
0
.
1
1
0
9
/
TN
S
R
E
.
2
0
1
4
.
2
3
0
5
5
2
0
.
[
2
6
]
D
.
M
.
B
l
e
i
,
“
L
i
n
e
a
r
r
e
g
r
e
ss
i
o
n
,
l
o
g
i
s
t
i
c
r
e
g
r
e
ssi
o
n
,
a
n
d
g
e
n
e
r
a
l
i
z
e
d
l
i
n
e
a
r
m
o
d
e
l
s
,”
C
o
l
u
mb
i
a
U
n
i
v
e
r
si
t
y
,
2
0
1
4
.
[
2
7
]
J.
K
.
A
f
r
i
y
i
e
e
t
a
l
.
,
“
A
su
p
e
r
v
i
s
e
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
f
o
r
d
e
t
e
c
t
i
n
g
a
n
d
p
r
e
d
i
c
t
i
n
g
f
r
a
u
d
i
n
c
r
e
d
i
t
c
a
r
d
t
r
a
n
s
a
c
t
i
o
n
s,”
D
e
c
i
s
i
o
n
An
a
l
y
t
i
c
s
J
o
u
r
n
a
l
,
v
o
l
.
6
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
a
j
o
u
r
.
2
0
2
3
.
1
0
0
1
6
3
.
[
2
8
]
A
.
M
o
k
h
t
a
r
,
A
.
E
l
b
e
l
t
a
g
i
,
Y
.
G
y
a
s
i
-
A
g
y
e
i
,
N
.
A
l
-
A
n
sari
,
a
n
d
M
.
K
.
A
b
d
e
l
-
F
a
t
t
a
h
,
“
P
r
e
d
i
c
t
i
o
n
o
f
i
r
r
i
g
a
t
i
o
n
w
a
t
e
r
q
u
a
l
i
t
y
i
n
d
i
c
e
s
b
a
s
e
d
o
n
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
r
e
g
r
e
ssi
o
n
mo
d
e
l
s,
”
Ap
p
l
i
e
d
W
a
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
2
,
n
o
.
4
,
p
p
.
1
-
1
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
3
2
0
1
-
022
-
0
1
5
9
0
-
x.
[
2
9
]
F
.
G
o
r
g
a
n
-
M
o
h
a
m
ma
d
i
,
T.
R
a
j
a
e
e
,
a
n
d
M
.
Z
o
u
n
e
ma
t
-
K
e
r
ma
n
i
,
“
D
e
c
i
si
o
n
t
r
e
e
mo
d
e
l
s
i
n
p
r
e
d
i
c
t
i
n
g
w
a
t
e
r
q
u
a
l
i
t
y
p
a
r
a
m
e
t
e
r
s
o
f
d
i
ss
o
l
v
e
d
o
x
y
g
e
n
a
n
d
p
h
o
s
p
h
o
r
u
s
i
n
l
a
k
e
w
a
t
e
r
,
”
S
u
s
t
a
i
n
a
b
l
e
W
a
t
e
r
Re
so
u
r
c
e
s
M
a
n
a
g
e
m
e
n
t
,
v
o
l
.
9
,
n
o
.
1
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
0
8
9
9
-
022
-
0
0
7
7
6
-
0.
Evaluation Warning : The document was created with Spire.PDF for Python.