I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
15
,
No
.
6
,
Decem
b
er
20
25
,
p
p
.
5
9
0
4
~
5
9
1
3
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
15
i
6
.
pp
5
9
0
4
-
5
9
1
3
5904
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Enha
ncing
supp
l
y
chain a
g
ility wit
h adv
a
nced weath
er
foreca
sting
I
m
a
ne
Z
er
o
ua
l,
J
a
ber
E
l Bo
uh
di
di
S
I
G
L
La
b
o
r
a
t
o
r
y
,
EN
S
A
TE,
A
b
d
e
l
m
a
l
e
k
Essa
d
i
U
n
i
v
e
r
si
t
y
,
Te
t
o
u
a
n
,
M
o
r
o
c
c
o
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
7
,
2
0
2
4
R
ev
is
ed
J
u
l 1
5
,
2
0
2
5
Acc
ep
ted
Sep
1
4
,
2
0
2
5
Th
is
a
rti
c
le
p
re
se
n
ts
a
s
o
lu
t
i
o
n
th
a
t
lev
e
ra
g
e
s
a
rti
ficia
l
in
telli
g
e
n
c
e
tec
h
n
iq
u
e
s
to
e
n
h
a
n
c
e
u
r
b
a
n
fre
ig
h
t
tran
sp
o
rtati
o
n
p
lan
n
in
g
a
n
d
o
r
g
a
n
iza
ti
o
n
th
ro
u
g
h
t
h
e
i
n
teg
ra
ti
o
n
o
f
we
a
th
e
r
fo
re
c
a
stin
g
d
a
ta.
We
id
e
n
ti
fy
k
e
y
c
h
a
ll
e
n
g
e
s
i
n
th
e
c
u
rre
n
t
u
r
b
a
n
l
o
g
isti
c
s
lan
d
sc
a
p
e
a
n
d
in
tro
d
u
c
e
a
ra
n
g
e
o
f
m
a
c
h
in
e
lea
rn
in
g
m
o
d
e
ls
d
e
sig
n
e
d
t
o
p
re
d
ict
d
e
li
v
e
ry
d
e
lay
s.
Lo
g
isti
c
re
g
re
ss
io
n
se
rv
e
s
a
s
th
e
fo
u
n
d
a
ti
o
n
a
l
m
o
d
e
l,
a
n
a
ly
z
in
g
h
ist
o
rica
l
d
e
li
v
e
ry
d
a
ta
in
c
o
n
j
u
n
c
ti
o
n
with
we
a
th
e
r
c
o
n
d
i
ti
o
n
s
t
o
a
ss
e
ss
th
e
li
k
e
li
h
o
o
d
o
f
d
e
lay
s,
th
u
s
e
n
a
b
l
in
g
in
f
o
r
m
e
d
d
e
c
isio
n
-
m
a
k
i
n
g
f
o
r
c
o
m
p
a
n
ies
.
Ad
d
it
i
o
n
a
ll
y
,
we
e
v
a
l
u
a
te
two
o
t
h
e
r
m
a
c
h
in
e
lea
rn
i
n
g
m
o
d
e
ls
t
o
d
e
term
in
e
th
e
m
o
st
e
ffe
c
ti
v
e
a
p
p
r
o
a
c
h
fo
r
o
u
r
sp
e
c
ifi
c
c
o
n
te
x
t,
a
ss
e
ss
in
g
t
h
e
i
r
a
c
c
u
ra
c
y
a
n
d
c
a
p
a
c
it
y
t
o
d
e
li
v
e
r
a
c
ti
o
n
a
b
le
in
si
g
h
ts.
By
im
p
ro
v
in
g
t
h
e
p
re
d
icti
v
e
c
a
p
a
b
il
it
ies
o
f
u
r
b
a
n
fre
ig
h
t
s
y
ste
m
s,
th
is
re
se
a
rc
h
a
ims
to
stre
a
m
li
n
e
o
p
e
ra
ti
o
n
s,
re
d
u
c
e
c
o
sts,
a
n
d
e
n
h
a
n
c
e
o
v
e
ra
ll
se
rv
ice
re
li
a
b
i
li
ty
,
c
o
n
tri
b
u
ti
n
g
to
m
o
re
e
fficie
n
t
a
n
d
re
sili
e
n
t
u
rb
a
n
tran
sp
o
rtatio
n
n
e
two
rk
s.
K
ey
w
o
r
d
s
:
Dec
is
io
n
tr
ee
Neu
r
al
n
etwo
r
k
R
an
d
o
m
f
o
r
est
Ur
b
an
lo
g
is
tic
W
ea
th
er
f
o
r
ec
asti
n
g
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
:
I
m
an
e
Z
er
o
u
al
SIG
L
L
ab
o
r
ato
r
y
,
E
NSAT
E
,
Ab
d
elm
alek
E
s
s
ad
i U
n
iv
er
s
ity
Av
.
Kh
en
if
r
a,
T
éto
u
a
n
9
3
0
0
0
,
Mo
r
o
cc
o
E
m
ail:
im
an
e.
ze
r
o
u
al
1
@
etu
.
u
ae
.
ac
.
m
a
1.
I
NT
RO
D
UCT
I
O
N
L
o
g
is
tics
in
th
e
s
u
p
p
ly
c
h
ain
i
n
v
o
lv
es
th
e
s
tr
ateg
ic
tr
an
s
p
o
r
t
atio
n
o
f
g
o
o
d
s
f
r
o
m
m
an
u
f
ac
t
u
r
in
g
s
ites
to
co
n
s
u
m
er
s
,
a
p
r
o
ce
s
s
in
cr
ea
s
in
g
ly
co
m
p
licated
b
y
u
n
p
r
ed
ictab
le
wea
th
er
co
n
d
itio
n
s
.
Sev
er
e
wea
th
e
r
ev
en
ts
s
u
ch
as
h
ea
v
y
r
ain
,
s
n
o
w,
an
d
s
tr
o
n
g
win
d
s
p
o
s
e
s
ig
n
if
ican
t
ch
allen
g
es,
lea
d
in
g
t
o
d
eliv
er
y
d
elay
s
[
1
]
,
h
az
ar
d
o
u
s
r
o
a
d
co
n
d
itio
n
s
,
a
n
d
d
is
r
u
p
tio
n
s
in
p
o
r
t
o
p
e
r
atio
n
s
.
T
h
ese
is
s
u
es
af
f
ec
t
lo
g
is
tics
ef
f
icien
cy
an
d
ca
n
r
esu
lt
in
f
in
a
n
cial
lo
s
s
es
an
d
d
im
in
is
h
ed
c
u
s
to
m
er
s
atis
f
ac
tio
n
.
T
h
e
co
r
e
p
r
o
b
lem
lies
in
th
e
in
ab
ilit
y
to
ef
f
ec
tiv
ely
p
r
ed
ict
a
n
d
r
esp
o
n
d
to
th
ese
wea
th
er
-
r
elate
d
d
is
r
u
p
tio
n
s
,
wh
ich
ca
n
ca
s
ca
d
e
t
h
r
o
u
g
h
t
h
e
s
u
p
p
ly
ch
ain
,
im
p
ac
ti
n
g
in
v
en
to
r
y
m
an
ag
em
en
t
a
n
d
o
v
er
all
o
p
e
r
atio
n
s
.
As
s
u
ch
,
lo
g
is
tics
m
an
ag
em
en
t
co
m
p
an
ie
s
m
u
s
t
im
p
lem
en
t
r
o
b
u
s
t
p
lan
n
i
n
g
s
tr
ateg
ies
to
m
itig
ate
th
ese
r
is
k
s
,
r
ely
in
g
h
ea
v
ily
o
n
tech
n
o
lo
g
y
to
m
o
n
ito
r
an
d
a
d
ap
t
to
ch
a
n
g
in
g
wea
th
er
co
n
d
itio
n
s
[
2
]
.
I
n
r
esp
o
n
s
e
to
th
is
c
h
allen
g
e,
we
p
r
o
p
o
s
e
a
s
o
lu
tio
n
th
at
in
teg
r
ates
wea
th
er
ap
p
licatio
n
p
r
o
g
r
am
m
in
g
in
ter
f
ac
e
(
API
)
in
to
s
u
p
p
ly
ch
ai
n
m
an
a
g
em
en
t
s
y
s
tem
s
.
T
h
ese
API
s
p
r
o
v
id
e
r
ea
l
-
tim
e
an
d
f
o
r
ec
asted
wea
th
er
d
ata,
en
ab
l
in
g
lo
g
is
tics
f
ir
m
s
to
o
p
tim
iz
e
r
o
u
tes
an
d
m
ak
e
in
f
o
r
m
e
d
d
ec
is
io
n
s
p
r
o
ac
tiv
e
ly
.
B
y
an
aly
zi
n
g
u
p
-
to
-
d
ate
wea
th
er
f
o
r
ec
asts
,
d
eliv
e
r
y
p
lan
n
er
s
ca
n
a
d
ju
s
t
r
o
u
tes
to
av
o
id
a
d
v
er
s
e
co
n
d
itio
n
s
,
en
s
u
r
in
g
s
af
er
a
n
d
m
o
r
e
tim
ely
d
eliv
er
ies.
Ad
d
itio
n
ally
,
p
r
e
d
ictiv
e
an
aly
tics
o
f
f
er
e
d
b
y
t
h
ese
API
s
allo
w
lo
g
is
tics
co
m
p
an
ies
to
an
ticip
ate
wea
th
er
p
atter
n
s
,
f
ac
ilit
atin
g
b
etter
r
eso
u
r
ce
allo
ca
tio
n
an
d
in
v
e
n
to
r
y
p
lan
n
in
g
.
T
h
is
s
tr
ateg
ic
a
p
p
r
o
ac
h
aim
s
to
e
n
h
an
ce
th
e
r
esil
ien
ce
o
f
u
r
b
a
n
f
r
eig
h
t tr
an
s
p
o
r
tatio
n
,
u
ltima
tely
im
p
r
o
v
in
g
s
er
v
ice
r
eliab
ilit
y
an
d
o
p
er
atio
n
al
ef
f
icien
c
y
.
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
-
8
7
0
8
E
n
h
a
n
cin
g
s
u
p
p
ly
c
h
a
in
a
g
ili
ty
w
ith
a
d
va
n
ce
d
w
ea
th
er fo
r
e
ca
s
tin
g
(
I
ma
n
e
Zer
o
u
a
l
)
5905
2.
M
E
T
H
O
D
2
.
1
.
Arc
hite
ct
ura
l o
v
er
v
iew
o
f
t
he
pro
po
s
ed
s
o
lutio
n
T
h
e
p
r
o
p
o
s
ed
ar
c
h
itectu
r
e
illu
s
tr
ated
in
Fig
u
r
e
1
(
b
lu
e
b
lo
c
)
,
th
e
Mu
leSo
f
t
b
atch
p
r
o
ce
s
s
“
lo
g
is
tics
-
wea
th
er
-
en
r
ich
m
e
n
t
-
b
c
h
”
p
lay
s
a
ce
n
tr
al
r
o
le
in
o
r
ch
estra
tin
g
th
e
d
ata
f
lo
w.
First,
it
r
et
r
iev
es
lo
g
is
tics
d
ata
f
r
o
m
a
c
o
m
m
a
-
s
ep
ar
ate
d
v
alu
es
(
C
SV
)
f
ile,
wh
ich
co
n
tain
s
d
etails
s
u
ch
as
d
eliv
er
y
lo
ca
ti
o
n
s
,
d
eliv
er
y
s
tatu
s
,
an
d
o
th
er
r
ele
v
an
t
in
f
o
r
m
atio
n
.
Nex
t,
th
e
b
atch
q
u
e
r
ies
a
h
is
to
r
ical
wea
th
er
API
f
o
r
ea
ch
d
eliv
er
y
lo
ca
tio
n
to
g
ath
er
wea
th
er
d
ata
s
u
ch
as
te
m
p
er
atu
r
e,
h
u
m
id
ity
,
o
r
p
r
ec
ip
itatio
n
at
th
e
d
eliv
er
y
tim
e
On
ce
th
e
lo
g
is
tics
an
d
wea
th
er
d
ata
ar
e
co
llected
,
th
e
b
atch
p
r
o
ce
s
s
p
er
f
o
r
m
s
a
s
er
ies
o
f
tr
an
s
f
o
r
m
atio
n
s
i
n
clu
d
in
g
clea
n
in
g
,
s
tr
u
ctu
r
in
g
t
h
e
d
ata
in
to
a
c
o
n
s
is
ten
t
f
o
r
m
at
th
at
is
s
u
itab
le
f
o
r
f
u
r
th
e
r
an
al
y
s
is
,
an
d
j
o
in
i
n
g
th
e
lo
g
is
tics
d
ata
with
th
e
co
r
r
esp
o
n
d
in
g
wea
th
er
d
ata
f
o
r
ea
c
h
d
eliv
e
r
y
,
en
s
u
r
in
g
th
at
all
th
e
n
ec
ess
ar
y
in
f
o
r
m
atio
n
is
alig
n
ed
.
T
h
e
en
r
ich
e
d
d
ata
is
th
en
s
to
r
ed
in
“
lo
g
is
tics
-
wo
r
k
in
g
-
d
b
”
d
atab
ase,
wh
er
e
it
b
ec
o
m
e
s
r
ea
d
y
f
o
r
u
s
e
in
tr
ain
in
g
m
ac
h
in
e
lear
n
in
g
m
o
d
els.
T
h
is
d
ataset
will
s
er
v
e
as
th
e
f
o
u
n
d
atio
n
f
o
r
tr
ain
in
g
a
p
r
ed
ictiv
e
m
o
d
el
th
at
ca
n
f
o
r
ec
ast
d
eliv
er
y
d
el
ay
s
b
ased
o
n
p
ast
wea
th
er
an
d
lo
g
is
tics
d
ata.
T
h
is
ap
p
r
o
ac
h
en
s
u
r
es
th
at
th
e
m
o
d
el
h
as
ac
ce
s
s
to
h
is
to
r
ic
al
d
ata
f
o
r
b
o
th
lo
g
is
tics
o
p
e
r
atio
n
s
an
d
wea
th
er
co
n
d
itio
n
s
,
m
ak
in
g
it
m
o
r
e
ac
cu
r
ate
in
its
p
r
ed
ictio
n
s
.
T
h
e
(
g
r
ee
n
b
lo
c)
o
f
Fig
u
r
e
1
f
o
cu
s
es
o
n
tr
ai
n
in
g
a
m
ac
h
in
e
lear
n
in
g
(
ML
)
m
o
d
el
f
o
r
p
r
ed
ictin
g
d
eliv
er
y
d
elay
s
b
ased
o
n
h
is
t
o
r
ical
lo
g
is
tics
d
ata
an
d
wea
t
h
er
co
n
d
itio
n
s
s
to
r
ed
in
th
e
d
atab
ase
“
lo
g
is
tics
-
wo
r
k
in
g
-
d
b
”.
T
h
e
wo
r
k
f
lo
w
i
n
v
o
lv
es
d
ata
r
etr
ie
v
al,
m
o
d
el
tr
ain
in
g
,
m
o
d
el
s
to
r
ag
e
in
a
m
o
d
el
r
eg
is
tr
y
,
a
n
d
ex
p
o
s
in
g
a
n
API
f
o
r
p
r
e
d
ictio
n
.
Her
e
i
s
h
o
w
th
e
e
n
tire
p
r
o
c
ess
wo
r
k
s
:
a.
T
h
e
p
r
o
ce
s
s
b
eg
in
s
with
r
etr
i
ev
in
g
th
e
h
is
to
r
ical
lo
g
is
tics
d
ata
an
d
wea
th
er
d
ata
s
to
r
ed
in
th
e
d
atab
ase
“
lo
g
is
tics
-
wo
r
k
in
g
-
d
b
”
wh
e
r
e
th
e
d
ata
h
as
alr
ea
d
y
b
ee
n
en
r
ich
ed
with
h
is
to
r
ical
wea
th
e
r
c
o
n
d
itio
n
s
.
T
h
is
d
ata
in
clu
d
es
d
eliv
er
y
tim
esta
m
p
s
,
lo
ca
tio
n
s
,
wea
th
er
d
ata
(
e.
g
.
,
tem
p
er
atu
r
e
an
d
p
r
ec
ip
ita
tio
n
)
,
a
n
d
o
th
er
r
elev
an
t lo
g
is
tics
in
f
o
r
m
atio
n
.
b.
On
ce
th
e
d
ata
is
r
etr
iev
e
d
,
th
e
s
cr
ip
t
p
r
o
ce
s
s
es
th
e
d
ata,
p
er
f
o
r
m
s
f
ea
tu
r
e
en
g
in
ee
r
in
g
s
u
ch
as
h
an
d
lin
g
m
is
s
in
g
v
alu
es,
en
co
d
in
g
ca
te
g
o
r
ical
f
ea
tu
r
es,
a
n
d
s
ca
lin
g
n
u
m
er
ical
v
alu
es,
a
n
d
tr
ain
s
t
h
e
m
o
d
el
u
s
in
g
two
alg
o
r
ith
m
s
: lin
ea
r
r
e
g
r
ess
io
n
an
d
r
an
d
o
m
f
o
r
ests
.
c.
Af
ter
tr
ain
in
g
,
t
h
e
m
o
d
el
is
s
av
ed
an
d
s
to
r
ed
in
a
m
o
d
el
r
eg
is
tr
y
th
at
tr
ac
k
s
d
if
f
er
en
t
v
er
s
io
n
s
o
f
th
e
m
o
d
el,
wh
ich
is
ess
en
tial
f
o
r
v
er
s
io
n
co
n
tr
o
l
an
d
r
ep
r
o
d
u
cib
ilit
y
.
E
ac
h
m
o
d
el
v
er
s
io
n
h
as
ass
o
ciate
d
m
etad
ata,
s
u
ch
as
tr
ain
in
g
c
o
n
f
ig
u
r
atio
n
(
h
y
p
er
p
ar
am
eter
s
u
s
ed
,
d
ataset
v
er
s
io
n
)
a
n
d
ev
alu
atio
n
m
etr
ics
(
e.
g
.
,
ac
c
u
r
ac
y
,
F1
s
co
r
e)
.
d.
On
ce
th
e
m
o
d
el
is
tr
ain
ed
an
d
r
eg
is
ter
ed
,
a
m
o
d
el
R
E
ST
API
is
cr
ea
ted
to
s
er
v
e
th
e
tr
ain
ed
m
o
d
el.
T
h
e
API
ac
ce
p
ts
th
e
s
am
e
ty
p
e
o
f
d
ata
(
d
eliv
er
y
d
etails,
wea
th
er
co
n
d
itio
n
s
)
th
at
th
e
m
o
d
el
was
tr
ain
ed
o
n
,
p
er
f
o
r
m
s
th
e
n
ec
ess
ar
y
p
r
e
-
p
r
o
ce
s
s
in
g
,
an
d
r
et
u
r
n
s
th
e
p
r
ed
i
cted
d
eliv
er
y
d
elay
.
e.
T
h
e
Pro
ce
s
s
API
“
lo
g
is
tics
-
w
ea
th
er
-
en
r
ich
m
en
t
-
p
r
c”
wh
ich
will
b
e
d
etailed
later
in
th
e
m
an
u
s
cr
ip
t,
ca
lls
th
e
m
o
d
el
R
E
ST
API
to
m
a
k
e
p
r
ed
ictio
n
s
.
T
h
is
in
ter
ac
ti
o
n
en
s
u
r
es
th
at
wh
e
n
n
ew
d
ata
is
p
r
o
ce
s
s
ed
th
r
o
u
g
h
th
e
p
ip
elin
e,
it c
an
tr
ig
g
er
a
p
r
ed
ictio
n
b
ased
o
n
th
e
tr
ain
ed
m
o
d
el.
Fig
u
r
e
1
.
Ar
c
h
itectu
r
e
o
f
m
ac
h
in
e
lear
n
in
g
an
d
b
atch
p
r
o
ce
s
s
in
g
p
ip
elin
es f
o
r
d
eliv
er
y
d
el
ay
p
r
ed
ictio
n
an
d
wea
th
er
-
en
r
ich
e
d
lo
g
is
tics
d
ata
On
ce
th
e
m
a
ch
in
e
lea
r
n
in
g
m
o
d
el
h
as
b
ee
n
tr
ain
ed
o
n
h
is
to
r
ical
d
ata,
th
e
ar
ch
itectu
r
e
s
h
o
wn
i
n
Fig
u
r
e
2
is
s
et
u
p
to
p
r
o
ce
s
s
i
n
co
m
in
g
d
eliv
er
y
o
r
d
er
s
in
r
e
al
-
tim
e
an
d
p
r
ed
ict
p
o
te
n
tial
d
elay
s
.
T
h
e
p
r
o
ce
s
s
b
eg
in
s
wh
en
th
e
e
x
p
er
ien
ce
API
r
ec
eiv
es
lo
g
is
tic
d
ata
f
r
o
m
th
e
in
co
m
in
g
d
eliv
er
y
o
r
d
e
r
th
r
o
u
g
h
a
d
eliv
e
r
y
W
eb
h
o
o
k
.
T
h
is
in
itiates
th
e
f
lo
w
o
f
d
ata
in
to
th
e
s
y
s
tem
.
T
h
e
e
x
p
er
ie
n
ce
API
th
en
p
ass
es
th
e
o
r
d
er
in
f
o
r
m
atio
n
to
th
e
Pro
ce
s
s
API
,
wh
ich
is
r
esp
o
n
s
ib
le
f
o
r
f
u
r
t
h
er
d
ata
p
r
o
ce
s
s
in
g
an
d
i
n
teg
r
atio
n
with
ex
ter
n
al
s
er
v
ices.
T
h
e
Pro
ce
s
s
A
PI
co
n
s
o
lid
ates
th
is
d
ata,
in
clu
d
in
g
th
e
d
eliv
er
y
d
etails
an
d
th
e
p
r
ed
icted
d
elay
,
an
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
6
,
Decem
b
e
r
20
25
:
5
9
0
4
-
5
9
1
3
5906
s
en
d
s
it
to
th
e
s
y
s
tem
API
.
T
h
e
s
y
s
tem
API
i
s
r
esp
o
n
s
ib
le
f
o
r
s
to
r
in
g
th
e
en
r
ic
h
ed
d
at
a
in
a
d
atab
ase
f
o
r
f
u
tu
r
e
r
ef
er
e
n
ce
an
d
an
al
y
s
is
.
L
et’
s
b
r
ea
k
d
o
wn
th
is
a
r
ch
it
ec
tu
r
e
illu
s
tr
ated
in
Fig
u
r
e
2
an
d
ex
p
lain
th
e
r
o
le
an
d
f
u
n
ctio
n
ality
o
f
ea
ch
API
in
d
etail:
a.
E
x
p
er
ien
ce
API
:
i
t
h
an
d
les
th
e
in
co
m
in
g
lo
g
is
tics
d
ata
an
d
s
er
v
es
as
th
e
f
ir
s
t
p
o
in
t
o
f
in
ter
ac
tio
n
f
o
r
th
e
s
y
s
tem
.
I
t
ex
p
o
s
es
an
en
d
p
o
in
t
th
at
ca
p
t
u
r
es
th
e
in
co
m
in
g
lo
g
is
tic
d
ata
p
u
s
h
ed
v
ia
t
h
e
d
e
liv
er
y
W
eb
h
o
o
k
an
d
f
o
r
war
d
s
it
to
t
h
e
Mu
leS
o
f
t
“
q
.
l
o
g
is
tics
.
d
elive
r
y.
v1
”
q
u
eu
e
wh
e
r
e
it
ca
n
b
e
s
u
b
s
eq
u
en
tly
h
a
n
d
led
b
y
th
e
Pro
ce
s
s
API
f
o
r
f
u
r
th
er
p
r
o
ce
s
s
in
g
an
d
an
al
y
s
is
.
b.
P
r
o
c
e
s
s
A
P
I
:
i
t
i
s
r
e
s
p
o
n
s
i
b
l
e
f
o
r
r
e
t
r
i
e
v
i
n
g
l
o
g
i
s
t
i
cs
d
a
t
a
f
r
o
m
t
h
e
M
u
l
e
S
o
f
t
q
u
e
u
e
“
q
.
l
o
g
i
s
t
i
c
s
.
d
el
i
v
er
y
.
v
1
”.
On
ce
it
r
ec
eiv
es
th
e
d
ata,
th
e
API
p
er
f
o
r
m
s
ess
en
tial
d
ata
en
r
ich
m
en
t
task
s
.
T
h
is
in
clu
d
es
ca
llin
g
th
e
ex
ter
n
al
W
ea
th
er
API
to
f
etch
h
is
to
r
ical
wea
th
er
d
ata
r
elev
a
n
t
to
th
e
d
eliv
er
y
lo
ca
tio
n
an
d
tim
ef
r
am
e.
T
h
e
Pro
ce
s
s
API
also
ap
p
lies
co
r
e
b
u
s
in
ess
lo
g
ic,
s
u
ch
as
d
at
a
tr
an
s
f
o
r
m
atio
n
,
v
alid
atio
n
,
an
d
n
ec
ess
ar
y
ca
lcu
latio
n
s
,
to
en
s
u
r
e
th
e
lo
g
is
tics
d
ata
i
s
p
r
o
p
er
ly
p
r
ep
a
r
e
d
f
o
r
f
u
r
th
er
an
al
y
s
is
.
I
n
ad
d
it
io
n
,
th
e
Pro
ce
s
s
API
ca
lls
th
e
p
r
ed
ictio
n
ML
API
to
g
en
er
ate
ac
c
u
r
ate
d
eli
v
er
y
d
ela
y
p
r
e
d
ictio
n
s
b
ased
o
n
th
e
e
n
r
ich
ed
d
ata.
On
ce
th
e
p
r
ed
ictio
n
is
g
en
er
ated
,
th
e
Pr
o
ce
s
s
API
i
n
d
ex
es
th
e
en
r
ich
e
d
d
ata
in
E
last
icsear
ch
to
en
ab
le
r
ea
l
-
tim
e
an
al
y
tics
.
I
t
th
en
f
o
r
war
d
s
th
e
en
r
ich
ed
an
d
p
r
e
d
icted
d
ata
to
th
e
Mu
leSo
f
t
q
u
e
u
e
“
q
.
lo
g
is
tics
.
w
ea
th
er.d
elive
r
y.
v
1
”
f
o
r
d
o
wn
s
tr
ea
m
c
o
n
s
u
m
p
tio
n
,
allo
win
g
th
e
s
y
s
tem
API
to
m
an
ag
e
s
to
r
ag
e
an
d
i
n
d
ex
in
g
f
o
r
f
u
t
u
r
e
u
s
e.
c.
Sy
s
tem
API
:
i
t
i
s
r
esp
o
n
s
ib
le
f
o
r
ca
p
tu
r
in
g
th
e
en
r
ich
ed
lo
g
is
tics
d
ata,
in
clu
d
in
g
th
e
d
eliv
er
y
p
r
ed
ictio
n
s
,
f
r
o
m
th
e
Mu
leSo
f
t
q
u
eu
e
“
q
.
lo
g
is
tics
.
w
ea
th
er.d
elive
r
y.
v1
”.
On
ce
th
e
d
ata
is
r
etr
iev
ed
,
t
h
e
s
y
s
tem
API
s
to
r
es th
e
en
r
ich
ed
d
ata,
in
clu
d
in
g
b
o
th
th
e
o
r
ig
in
al
lo
g
is
tics
d
etails an
d
th
e
g
e
n
er
ated
d
eli
v
er
y
p
r
ed
ictio
n
s
in
th
e
d
atab
ase
“
lo
g
is
tics
-
wo
r
k
in
g
-
d
b
”.
T
h
is
en
s
u
r
es
t
h
e
d
a
ta
is
s
ec
u
r
ely
s
av
ed
an
d
m
a
d
e
av
ailab
le
f
o
r
f
u
tu
r
e
r
ef
er
e
n
ce
,
r
e
p
o
r
tin
g
,
a
n
d
f
u
r
th
er
an
aly
s
is
.
T
h
is
ar
c
h
itectu
r
e
en
s
u
r
es
t
h
at
th
e
s
y
s
tem
ca
n
p
r
o
ce
s
s
an
d
p
r
ed
ict
d
eliv
er
y
d
ela
y
s
ef
f
ec
t
iv
ely
in
r
ea
l
-
tim
e,
u
s
in
g
h
is
to
r
ical
d
ata
f
o
r
p
r
e
d
ictio
n
wh
il
e
also
en
ab
lin
g
co
n
tin
u
o
u
s
m
o
n
ito
r
in
g
a
n
d
r
e
p
o
r
tin
g
t
h
r
o
u
g
h
E
last
icsear
ch
.
Fig
u
r
e
2
.
Hig
h
-
lev
el
d
esig
n
f
o
r
lo
g
is
tics
d
ata
p
r
o
ce
s
s
in
g
an
d
d
eliv
er
y
d
elay
f
o
r
ec
asti
n
g
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
-
8
7
0
8
E
n
h
a
n
cin
g
s
u
p
p
ly
c
h
a
in
a
g
ili
ty
w
ith
a
d
va
n
ce
d
w
ea
th
er fo
r
e
ca
s
tin
g
(
I
ma
n
e
Zer
o
u
a
l
)
5907
I
n
th
e
cu
r
r
en
t
ar
c
h
itectu
r
e,
th
e
s
o
lu
tio
n
is
d
esig
n
ed
to
co
n
tin
u
o
u
s
ly
ev
o
lv
e
an
d
e
n
h
an
ce
its
p
r
ed
ictio
n
s
o
v
e
r
tim
e.
B
y
in
teg
r
atin
g
r
ea
l
-
tim
e
d
ata
a
n
d
r
eg
u
lar
ly
r
etr
ain
in
g
th
e
m
ac
h
in
e
lear
n
in
g
m
o
d
el,
th
e
s
y
s
tem
en
s
u
r
es
th
at
its
p
r
e
d
ictio
n
s
r
em
ain
b
o
th
ac
cu
r
ate
an
d
r
elev
an
t.
T
h
e
s
y
s
tem
API
p
la
y
s
a
cr
u
cial
r
o
le
i
n
th
is
p
r
o
ce
s
s
b
y
tr
ig
g
er
i
n
g
m
o
d
el
r
etr
ain
in
g
.
As
s
h
o
wn
in
Fig
u
r
e
3
,
wh
en
th
e
v
o
lu
m
e
o
f
n
e
w
d
ata
s
to
r
ed
in
th
e
d
atab
ase
ex
ce
ed
s
a
p
r
e
d
ef
in
ed
th
r
esh
o
l
d
,
th
e
s
y
s
tem
API
ac
tiv
ates
a
s
ep
ar
ate
b
atch
”
lo
g
is
tics
-
wea
th
er
-
tr
ain
in
g
-
b
c
h
”
(
as
d
etailed
in
Fig
u
r
e
2
)
to
in
itiate
th
e
r
etr
ai
n
in
g
o
f
t
h
e
m
o
d
el.
T
h
is
ap
p
r
o
ac
h
en
s
u
r
es
th
at
th
e
m
ac
h
in
e
lear
n
in
g
m
o
d
el
is
co
n
tin
u
o
u
s
ly
u
p
d
ated
with
th
e
latest
d
ata,
im
p
r
o
v
in
g
its
ac
cu
r
ac
y
an
d
p
r
ed
ictiv
e
ca
p
ab
ilit
ies
[
3
]
.
Fig
u
r
e
3
.
C
o
n
tin
u
o
u
s
m
o
d
el
i
m
p
r
o
v
e
m
en
t a
n
d
r
etr
ain
in
g
p
r
o
ce
s
s
2
.
2
.
Da
t
a
e
x
plo
ra
t
io
n a
nd
prepro
ce
s
s
ing
Ou
r
s
y
s
tem
lev
e
r
ag
es
an
ap
p
licatio
n
p
r
o
g
r
a
m
m
in
g
in
ter
f
ac
e
(
API
)
to
r
etr
iev
e
h
is
to
r
ical
we
ath
er
d
ata,
p
r
o
v
id
i
n
g
cr
u
cial
in
s
ig
h
ts
in
to
p
ast
wea
th
er
co
n
d
itio
n
s
.
T
h
e
wea
th
er
R
E
ST
API
(
h
ttp
s
:
//a
r
ch
ive
-
a
p
i.o
p
en
-
mete
o
.
co
m/v1
/era
/5
)
f
u
n
cti
o
n
s
ef
f
icien
tly
b
y
u
s
in
g
th
e
in
p
u
t
d
ata
f
r
o
m
th
e
C
SV
f
ile
as
q
u
er
y
p
a
r
am
eter
s
s
p
ec
if
ied
in
T
ab
le
1
to
f
etch
th
e
r
elev
a
n
t
wea
th
er
in
f
o
r
m
at
io
n
.
B
y
in
teg
r
atin
g
th
e
wea
th
er
API
,
o
u
r
s
y
s
tem
g
ain
s
ac
ce
s
s
to
h
is
to
r
ical
wea
t
h
er
p
atter
n
s
,
wh
ich
p
lay
a
k
ey
r
o
le
in
p
r
ed
ictin
g
d
eliv
e
r
y
d
el
ay
s
.
T
h
is
h
is
to
r
ical
wea
th
er
d
ata
en
r
ich
es
o
u
r
p
r
e
d
ictio
n
s
,
im
p
r
o
v
in
g
o
u
r
f
o
r
ec
asts
’
ac
cu
r
ac
y
an
d
r
eliab
ilit
y
[
4
]
.
T
h
e
h
is
to
r
ical
wea
th
er
API
ap
p
ea
r
s
as
:
T
ab
le
1
.
W
ea
th
er
API
in
p
u
t sp
ec
if
icatio
n
s
P
a
r
a
me
t
e
r
F
o
r
mat
R
e
q
u
i
r
e
d
V
a
l
u
e
(
e
x
a
mp
l
e
)
D
e
scri
p
t
i
o
n
La
t
i
t
u
d
e
,
l
o
n
g
i
t
u
d
e
F
l
o
a
t
i
n
g
p
o
i
n
t
Y
e
s
1
8
.
3
5
9
0
9
4
6
2
6
6
.
0
7
9
9
5
6
0
6
G
e
o
g
r
a
p
h
i
c
a
l
W
G
S
8
4
c
o
o
r
d
i
n
a
t
e
o
f
t
h
e
l
o
c
a
t
i
o
n
S
t
a
r
t
_
d
a
t
e
,
e
n
d
_
d
a
t
e
S
t
r
i
n
g
(
y
y
y
y
-
mm
-
dd)
No
2
0
1
8
-
02
-
03
2
0
2
1
8
-
02
-
06
Th
e
t
i
me
i
n
t
e
r
v
a
l
t
o
g
e
t
w
e
a
t
h
e
r
d
a
t
a
Ti
me
z
o
n
e
d
a
i
l
y
S
t
r
i
n
g
No
A
u
t
o
A
l
l
t
i
m
e
st
a
mp
s
a
r
e
r
e
t
u
r
n
e
d
a
s
l
o
c
a
l
t
i
m
e
S
t
r
i
n
g
a
r
r
a
y
No
R
a
i
n
_
su
m,w
e
a
t
h
e
r
c
o
d
e
,
P
r
e
c
i
p
i
t
a
t
i
o
n
_
s
u
m,
p
r
e
c
i
p
i
t
a
t
i
o
n
_
h
o
u
r
s,
sn
o
w
f
a
l
l
_
s
u
m
A
l
i
s
t
o
f
d
a
i
l
y
w
e
a
t
h
e
r
v
a
r
i
a
b
l
e
a
g
g
r
e
g
a
t
i
o
n
s
Data
clea
n
in
g
is
a
c
r
u
cial
s
tep
in
t
h
e
m
ac
h
in
e
lear
n
in
g
p
i
p
elin
e
[
5
]
,
i
n
v
o
lv
i
n
g
th
e
i
d
en
tific
atio
n
an
d
co
r
r
ec
tio
n
o
f
er
r
o
r
s
,
in
c
o
n
s
is
ten
cies,
an
d
in
ac
cu
r
ac
ies
in
th
e
d
ataset.
Hig
h
-
q
u
ality
,
clea
n
d
ata
is
f
u
n
d
am
e
n
tal
f
o
r
b
u
ild
i
n
g
r
eliab
le
an
d
ac
c
u
r
ate
m
ac
h
in
e
lear
n
in
g
m
o
d
els
.
B
elo
w
ar
e
s
o
m
e
o
f
th
e
co
m
m
o
n
d
ata
-
clea
n
i
n
g
tech
n
iq
u
es we
ap
p
lied
to
o
u
r
d
ataset:
a.
Han
d
lin
g
m
is
s
in
g
v
al
u
es:
i
d
en
tify
an
d
ad
d
r
ess
m
is
s
in
g
d
ata
b
y
r
em
o
v
i
n
g
r
o
ws
an
d
co
lu
m
n
s
with
ex
ce
s
s
iv
e
m
is
s
in
g
v
alu
es a
n
d
u
s
in
g
im
p
u
tatio
n
tech
n
iq
u
es
[
6
]
to
f
ill in
t
h
e
g
ap
s
.
b.
Data
ty
p
e
co
n
v
er
s
io
n
:
e
n
s
u
r
e
th
at
th
e
d
ata
t
y
p
es
u
s
ed
in
t
h
e
d
ataset
ar
e
co
m
p
atib
le
wi
th
th
e
m
ac
h
i
n
e
lear
n
in
g
alg
o
r
ith
m
.
Fo
r
in
s
ta
n
ce
,
we
c
o
n
v
e
r
ted
ca
te
g
o
r
ic
al
v
ar
iab
les
in
t
o
a
n
u
m
e
r
ica
l
f
o
r
m
at
u
s
in
g
m
eth
o
d
s
lik
e
o
n
e
-
h
o
t e
n
co
d
in
g
[
7
]
a
n
d
la
b
el
en
co
d
in
g
[
8
]
.
c.
R
em
o
v
in
g
d
u
p
licates:
i
d
en
tif
y
an
d
elim
in
ate
d
u
p
licate
[
9
]
r
ec
o
r
d
s
to
av
o
id
r
ed
u
n
d
an
cy
an
d
im
p
r
o
v
e
m
o
d
el
ac
cu
r
ac
y
.
d.
E
n
co
d
in
g
ca
teg
o
r
ical
d
ata:
c
o
n
v
er
t
ca
teg
o
r
ical
v
ar
iab
les
i
n
to
a
f
o
r
m
at
s
u
itab
le
f
o
r
m
ac
h
in
e
lear
n
in
g
m
o
d
els.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
6
,
Decem
b
e
r
20
25
:
5
9
0
4
-
5
9
1
3
5908
W
e
u
s
ed
o
n
e
-
h
o
t
o
r
la
b
el
en
co
d
in
g
tech
n
iq
u
es,
wh
ich
tr
a
n
s
f
o
r
m
n
o
n
-
n
u
m
e
r
ic
d
ata
in
t
o
n
u
m
er
ical
v
al
u
es.
C
lean
in
g
tim
e
-
s
er
ies
d
ata:
f
o
r
tim
e
-
s
er
ies
d
ata,
we
ad
d
r
ess
ch
allen
g
es
s
u
ch
as
m
is
s
in
g
ti
m
estam
p
s
,
ir
r
eg
u
la
r
in
ter
v
als,
an
d
s
ea
s
o
n
ality
b
y
f
i
llin
g
g
ap
s
o
r
r
esam
p
lin
g
th
e
d
ata
to
en
s
u
r
e
co
n
s
is
ten
cy
.
E
f
f
e
ctiv
e
d
ata
clea
n
in
g
[
1
0
]
s
ig
n
if
ican
tly
im
p
r
o
v
es
th
e
p
er
f
o
r
m
a
n
ce
an
d
r
eliab
ilit
y
o
f
m
ac
h
in
e
lear
n
i
n
g
m
o
d
els
b
y
en
s
u
r
in
g
th
at
th
e
d
ata
is
well
-
p
r
ep
ar
ed
f
o
r
a
n
aly
s
is
.
T
h
e
lo
g
is
tics
d
ata
co
n
tain
s
v
ar
io
u
s
v
ar
iab
les
r
elate
d
to
th
e
d
eliv
er
y
o
f
d
if
f
er
en
t
p
r
o
d
u
cts.
T
h
ese
v
ar
iab
les in
clu
d
e
in
f
o
r
m
atio
n
s
u
ch
as
“
d
ay
s
f
o
r
s
h
ip
p
in
g
(
ac
tu
al)
,
”
“
d
ay
s
f
o
r
s
h
ip
m
en
t
(
s
ch
ed
u
led
)
,
”
“
d
eliv
er
y
s
tatu
s
,
”
“
late
d
eliv
er
y
r
is
k
,
”
an
d
m
o
r
e.
T
ab
le
2
p
r
o
v
id
es a
n
o
v
er
v
iew
o
f
s
o
m
e
o
f
t
h
e
v
alu
es
in
th
ese
co
lu
m
n
s
.
T
ab
le
2
.
E
x
am
p
les o
f
c
o
lu
m
n
v
alu
es in
th
e
lo
g
is
tics
d
ataset
C
o
l
u
m
n
n
a
me
Ty
p
e
V
a
l
u
e
s (e
x
a
mp
l
e
)
D
e
scri
p
t
i
o
n
La
t
e
d
e
l
i
v
e
r
y
r
i
s
k
N
u
meri
c
a
l
0
o
r
1
A
b
i
n
a
r
y
v
a
r
i
a
b
l
e
,
c
o
d
e
d
a
s
0
o
r
1
.
1
i
n
d
i
c
a
t
e
s t
h
a
t
t
h
e
d
e
l
i
v
e
r
y
i
s
l
a
t
e
,
w
h
i
l
e
0
i
n
d
i
c
a
t
e
s i
t
’
s
o
n
t
i
me
D
e
l
i
v
e
r
y
s
t
a
t
u
s
C
a
t
e
g
o
r
i
c
a
l
A
d
v
a
n
c
e
s
h
i
p
p
i
n
g
,
La
t
e
d
e
l
i
v
e
r
y
,
S
h
i
p
p
i
n
g
o
n
t
i
m
e
R
e
p
r
e
se
n
t
s
t
h
e
st
a
t
u
s
o
f
t
h
e
o
r
d
e
r
d
e
l
i
v
e
r
y
La
t
i
t
u
d
e
N
u
meri
c
a
l
1
8
.
3
5
9
0
9
4
6
2
R
e
p
r
e
se
n
t
s
t
h
e
g
e
o
g
r
a
p
h
i
c
a
l
l
o
c
a
t
i
o
n
o
f
t
h
e
d
e
l
i
v
e
r
y
d
e
st
i
n
a
t
i
o
n
T
h
e
d
ataset
in
clu
d
es
s
ev
er
al
c
o
lu
m
n
s
ir
r
elev
an
t
to
o
u
r
an
aly
s
is
,
as
th
ey
eith
er
lack
u
tili
ty
o
r
d
o
n
o
t
s
ig
n
if
ican
tly
co
n
tr
ib
u
te
to
th
e
p
r
ed
ictiv
e
m
o
d
elin
g
task
s
.
As
a
r
esu
lt,
we
will
i
n
itiate
a
d
at
a
s
elec
tio
n
p
r
o
ce
s
s
to
im
p
r
o
v
e
m
o
d
el
ef
f
icien
cy
.
Featu
r
e
s
elec
tio
n
is
a
k
ey
s
tep
in
th
e
m
ac
h
i
n
e
lear
n
i
n
g
p
ip
el
in
e
[
1
1
]
wh
e
r
e
we
id
en
tify
an
d
r
etain
th
e
m
o
s
t
r
elev
an
t
f
ea
tu
r
es
f
r
o
m
th
e
o
r
ig
in
al
d
ataset.
T
h
is
p
r
o
ce
s
s
is
im
p
o
r
tan
t
f
o
r
s
ev
er
al
r
ea
s
o
n
s
:
a.
Dim
en
s
io
n
ality
r
ed
u
ctio
n
:
b
y
r
em
o
v
in
g
ir
r
elev
a
n
t
o
r
r
ed
u
n
d
an
t
f
ea
tu
r
es,
we
r
ed
u
ce
t
h
e
d
i
m
en
s
io
n
ality
o
f
th
e
d
ataset
[
1
2
]
,
wh
ich
h
el
p
s
in
f
aster
m
o
d
el
t
r
ain
in
g
a
n
d
im
p
r
o
v
es m
o
d
el
g
e
n
er
aliza
tio
n
.
b.
I
m
p
r
o
v
ed
m
o
d
el
p
er
f
o
r
m
an
c
e:
s
elec
tin
g
o
n
ly
th
e
m
o
s
t
in
f
o
r
m
ativ
e
f
ea
tu
r
es
ca
n
en
h
a
n
ce
th
e
m
o
d
el’
s
ac
cu
r
ac
y
wh
ile
r
e
d
u
cin
g
th
e
r
i
s
k
o
f
o
v
e
r
f
itti
n
g
.
c.
E
n
h
an
ce
d
in
ter
p
r
etab
ilit
y
:
f
e
wer
f
ea
tu
r
es
ty
p
ically
m
ak
e
t
h
e
m
o
d
el
ea
s
ier
to
in
te
r
p
r
et
an
d
u
n
d
e
r
s
tan
d
,
wh
ich
is
p
ar
ticu
lar
ly
im
p
o
r
tan
t in
p
r
ac
tical
ap
p
licatio
n
s
.
T
h
er
e
ar
e
s
ev
er
al
m
eth
o
d
s
f
o
r
f
ea
tu
r
e
s
elec
tio
n
,
in
clu
d
in
g
:
a.
C
o
r
r
elatio
n
-
b
ased
m
et
h
o
d
s
:
i
d
en
tify
in
g
h
ig
h
ly
co
r
r
elate
d
f
ea
tu
r
es
[
1
3
]
to
elim
in
ate
r
ed
u
n
d
an
t
v
ar
iab
les.
T
r
ee
-
b
ased
m
eth
o
d
s
:
u
s
in
g
d
e
cisi
o
n
tr
ee
s
o
r
tr
ee
e
n
s
em
b
le
m
eth
o
d
s
(
e.
g
.
,
r
an
d
o
m
f
o
r
ests
)
to
r
an
k
f
ea
tu
r
e
im
p
o
r
tan
ce
[
1
4
]
.
b.
Dim
en
s
io
n
ality
r
ed
u
ctio
n
:
tec
h
n
iq
u
es
s
u
ch
as
p
r
in
cip
al
co
m
p
o
n
e
n
t
an
aly
s
is
(
PC
A)
[
1
5
]
to
r
ed
u
ce
th
e
n
u
m
b
er
o
f
f
ea
tu
r
es.
c.
Featu
r
e
im
p
o
r
tan
ce
s
co
r
es:
esti
m
atin
g
th
e
r
elev
an
ce
o
f
ea
ch
f
ea
tu
r
e
b
ased
o
n
h
o
w
it
co
n
tr
i
b
u
tes
to
m
o
d
el
p
r
ed
ictio
n
s
[
1
6
]
.
We
ha
v
e
ch
o
s
en
to
r
ely
o
n
f
ea
tu
r
e
im
p
o
r
tan
ce
s
co
r
es
b
ec
au
s
e
th
ey
ar
e
well
-
s
u
ited
to
o
u
r
d
ataset
an
d
th
e
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
we
p
lan
to
u
s
e.
Mo
r
e
o
v
er
,
it
is
o
f
ten
b
en
ef
icial
to
e
x
p
er
i
m
en
t
with
d
if
f
er
en
t
f
ea
tu
r
e
s
elec
tio
n
tech
n
i
q
u
es
an
d
ass
ess
th
eir
im
p
ac
t
o
n
m
o
d
el
p
er
f
o
r
m
a
n
ce
th
r
o
u
g
h
cr
o
s
s
-
v
alid
atio
n
[
1
7
]
.
T
h
is
p
r
o
ce
s
s
will
g
u
id
e
u
s
in
s
elec
tin
g
th
e
m
o
s
t
s
ig
n
if
ican
t
f
ea
tu
r
es
f
o
r
o
u
r
p
r
ed
ictiv
e
m
o
d
el.
W
e
p
r
o
ce
ed
e
d
to
a
f
ea
tu
r
e
im
p
o
r
tan
t
s
co
r
e
f
r
o
m
a
f
ea
tu
r
e
s
elec
tio
n
an
aly
s
is
.
T
h
e
s
co
r
es
in
T
ab
le
3
d
em
o
n
s
tr
ate
h
o
w
im
p
o
r
tan
t e
ac
h
f
ea
tu
r
e
is
in
p
r
ed
ictin
g
th
e
tar
g
et
v
ar
iab
le
(
l
ate
d
eliv
er
y
r
is
k
)
:
T
ab
le
3
.
Selecte
d
f
ea
tu
r
es f
r
o
m
th
e
f
ea
tu
r
e
s
elec
tio
n
p
r
o
ce
s
s
F
e
a
t
u
r
e
I
mp
o
r
t
a
n
c
e
4
La
t
i
t
u
d
e
0
.
2
9
0
7
4
7
5
Lo
n
g
i
t
u
d
e
0
.
2
6
1
6
0
2
0
El
e
v
a
t
i
o
n
0
.
2
2
6
2
5
7
1
R
a
i
n
a
v
g
0
.
1
2
2
5
3
3
2
P
r
e
c
i
p
i
t
a
t
i
o
n
_
h
o
u
r
s_
a
v
g
0
.
0
8
4
2
8
0
3
S
n
o
w
f
a
l
l
_
s
u
m
0
.
0
1
4
5
8
1
Featu
r
e
im
p
o
r
ta
n
ce
s
co
r
es
h
el
p
q
u
a
n
tify
th
e
co
n
t
r
ib
u
tio
n
o
f
ea
ch
v
ar
iab
le
to
th
e
m
o
d
el
’
s
p
r
ed
ictio
n
s
.
Featu
r
es
with
h
ig
h
er
s
co
r
es,
s
u
ch
as
L
atitu
d
e
an
d
L
o
n
g
itu
d
e,
ar
e
co
n
s
id
er
e
d
m
o
r
e
in
f
lu
e
n
tial
in
d
eter
m
in
in
g
th
e
tar
g
et
v
ar
ia
b
le:
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
-
8
7
0
8
E
n
h
a
n
cin
g
s
u
p
p
ly
c
h
a
in
a
g
ili
ty
w
ith
a
d
va
n
ce
d
w
ea
th
er fo
r
e
ca
s
tin
g
(
I
ma
n
e
Zer
o
u
a
l
)
5909
a.
L
o
n
g
itu
d
e:
r
a
n
k
in
g
s
ec
o
n
d
with
a
s
co
r
e
o
f
ab
o
u
t 0
.
2
6
1
6
,
L
o
n
g
itu
d
e
also
p
lay
s
a
cr
itical
r
o
le
in
f
o
r
ec
asti
n
g
th
e
tar
g
et
v
ar
ia
b
le.
L
ik
e
L
atitu
d
e,
ch
an
g
es in
L
o
n
g
itu
d
e
s
u
b
s
tan
tially
af
f
ec
t th
e
m
o
d
el’
s
p
r
e
d
ictio
n
s
.
b.
E
lev
atio
n
:
w
ith
a
f
ea
tu
r
e
im
p
o
r
tan
ce
s
co
r
e
o
f
ar
o
u
n
d
0
.
2
2
6
3
,
E
lev
atio
n
is
im
p
o
r
tan
t
b
u
t
less
s
o
th
an
latitu
d
e
an
d
l
o
n
g
itu
d
e.
Desp
it
e
its
r
elativ
ely
lo
wer
im
p
o
r
ta
n
ce
,
ch
a
n
g
es
in
E
le
v
atio
n
s
till
h
av
e
a
n
o
tab
le
ef
f
ec
t o
n
t
h
e
m
o
d
el’
s
p
r
ed
ictio
n
s
.
c.
R
ain
av
g
:
w
ith
a
s
co
r
e
o
f
a
p
p
r
o
x
im
ately
0
.
1
2
2
5
,
R
ain
av
g
co
n
tr
ib
u
tes
less
th
an
th
e
g
e
o
g
r
ap
h
ical
f
ea
t
u
r
es
(
L
atitu
d
e,
L
o
n
g
itu
d
e,
an
d
E
lev
atio
n
)
,
b
u
t it
s
till
h
o
ld
s
s
ig
n
if
ican
t p
r
ed
ictiv
e
p
o
wer
in
t
h
e
m
o
d
el.
d.
Pre
cip
itatio
n
h
o
u
r
s
av
g
:
t
h
is
f
ea
tu
r
e
h
as
a
s
ig
n
if
ican
ce
s
co
r
e
o
f
ab
o
u
t
0
.
0
8
4
3
.
W
h
ile
it
is
less
in
f
lu
en
tial
th
an
R
ain
_
av
g
,
it st
ill p
r
o
v
id
e
s
v
alu
ab
le
in
f
o
r
m
atio
n
f
o
r
th
e
m
o
d
el’
s
p
r
e
d
ictio
n
s
.
e.
Sn
o
wf
all
s
u
m
:
a
t
0
.
0
1
4
6
,
s
n
o
wf
all
s
u
m
h
as
th
e
l
o
west
f
ea
tu
r
e
im
p
o
r
tan
ce
s
co
r
e
.
T
h
i
s
in
d
icate
s
th
at
r
elativ
e
to
th
e
o
t
h
er
v
a
r
iab
les,
it h
as th
e
least in
f
lu
en
ce
o
n
p
r
ed
ictin
g
(
l
ate
d
eliv
er
y
r
is
k
)
.
2
.
3
.
M
a
chine
lea
rning
m
o
de
ls
us
e
d f
o
r
predict
ing
deliv
er
y
dela
y
s
W
e
em
p
lo
y
ed
two
m
ac
h
in
e
lear
n
in
g
m
o
d
els
to
p
r
ed
ict
d
eliv
er
y
d
ela
y
:
L
o
g
is
tic
r
e
g
r
e
s
s
io
n
an
d
r
an
d
o
m
f
o
r
est
.
T
h
ese
m
o
d
els
wer
e
ch
o
s
en
f
o
r
th
eir
p
r
o
v
e
n
ef
f
ec
tiv
en
ess
in
class
if
icati
o
n
task
s
an
d
th
ei
r
ab
ilit
y
to
h
an
d
le
d
if
f
e
r
en
t ty
p
e
s
o
f
d
ata
r
elatio
n
s
h
ip
s
:
a.
L
o
g
is
tic
r
eg
r
ess
io
n
is
a
wid
ely
u
s
ed
m
ac
h
in
e
lear
n
i
n
g
alg
o
r
ith
m
f
o
r
p
r
ed
ictiv
e
task
s
in
v
ar
i
o
u
s
d
o
m
ain
s
.
I
t
is
co
m
m
o
n
ly
u
s
ed
f
o
r
b
o
th
b
in
ar
y
a
n
d
m
u
lti
-
class
class
if
ica
tio
n
,
m
a
k
in
g
it
v
er
s
atile
f
o
r
d
if
f
er
en
t
s
ce
n
a
r
io
s
[
1
8
]
.
b.
R
an
d
o
m
f
o
r
est
is
a
p
o
p
u
lar
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
o
f
ten
u
s
ed
f
o
r
class
if
icatio
n
an
d
r
eg
r
ess
io
n
task
s
.
I
t
is
an
en
s
em
b
le
lear
n
in
g
al
g
o
r
ith
m
t
h
at
co
n
s
tr
u
cts
m
u
lti
p
le
d
ec
is
io
n
tr
ee
s
,
ea
ch
tr
ain
ed
o
n
a
r
an
d
o
m
s
u
b
s
et
o
f
f
ea
tu
r
es
at
ea
ch
s
p
lit,
to
m
in
im
ize
th
e
v
ar
ian
ce
b
etwe
en
co
r
r
elate
d
tr
ee
s
.
B
y
av
er
ag
in
g
th
e
p
r
ed
ictio
n
s
o
f
in
d
i
v
id
u
al
tr
ee
s
,
it
en
h
an
ce
s
p
r
ed
ictiv
e
ac
c
u
r
a
cy
an
d
h
elp
s
m
itig
ate
o
v
er
f
itti
n
g
,
r
esu
ltin
g
in
a
m
o
r
e
r
o
b
u
s
t m
o
d
el
[
1
9
]
.
3
.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
L
et’
s
n
o
w
ex
p
lo
r
e
th
e
ac
cu
r
ac
y
o
f
th
e
r
esu
lts
o
b
tain
ed
th
r
o
u
g
h
th
ese
m
eth
o
d
s
an
d
ex
am
i
n
e
h
o
w
ea
ch
co
n
tr
ib
u
tes
to
en
h
an
cin
g
t
h
e
o
v
er
all
p
er
f
o
r
m
a
n
ce
o
f
th
e
d
eliv
er
y
d
elay
p
r
ed
ictio
n
s
y
s
tem
.
As
s
h
o
wn
in
T
ab
le
4
,
th
e
lo
g
is
tic
r
eg
r
ess
io
n
m
o
d
el
ac
h
iev
es
a
n
ac
cu
r
a
cy
o
f
0
.
6
1
,
in
d
icatin
g
its
ab
il
ity
to
m
ak
e
c
o
r
r
ec
t
p
r
ed
ictio
n
s
.
H
o
wev
er
,
th
e
r
an
d
o
m
f
o
r
est
m
o
d
el
o
u
tp
e
r
f
o
r
m
s
it
s
ig
n
if
ican
tly
,
with
an
ac
c
u
r
ac
y
o
f
0
.
9
8
.
T
h
is
co
n
s
id
er
ab
le
d
if
f
er
en
ce
s
u
g
g
ests
th
at
th
e
r
an
d
o
m
f
o
r
est
m
o
d
el
ex
ce
ls
at
id
en
tif
y
in
g
p
atter
n
s
an
d
m
a
k
in
g
p
r
ec
is
e
p
r
ed
ictio
n
s
r
eg
a
r
d
in
g
d
eliv
er
y
d
elay
s
.
Giv
e
n
th
ese
r
esu
lts
,
th
e
r
an
d
o
m
f
o
r
est
m
o
d
el
h
as
p
r
o
v
en
to
b
e
m
o
r
e
ef
f
ec
tiv
e
f
o
r
th
is
p
r
ed
icti
o
n
task
,
o
f
f
er
in
g
v
alu
a
b
le
in
s
ig
h
ts
f
o
r
id
e
n
tify
in
g
an
d
m
itig
a
tin
g
late
d
eliv
er
ies.
T
ab
le
4
.
Acc
u
r
ac
y
m
etr
ics f
o
r
d
eliv
er
y
d
ela
y
p
r
e
d
ictio
n
m
o
d
els
M
o
d
e
l
A
c
c
u
r
a
c
y
Lo
g
i
s
t
i
c
r
e
g
r
e
ssi
o
n
0
.
6
1
R
a
n
d
o
m f
o
r
e
s
t
0
.
9
8
Nex
t,
we
em
p
lo
y
ed
a
co
n
f
u
s
io
n
m
atr
ix
to
ev
alu
ate
th
e
p
er
f
o
r
m
an
ce
o
f
b
o
th
m
o
d
els
[
2
0
]
.
T
h
e
co
n
f
u
s
io
n
m
atr
ix
is
an
N
×
N
tab
le,
wh
er
e
N
r
ep
r
esen
ts
th
e
n
u
m
b
er
o
f
tar
g
et
class
es.
I
t
is
u
s
ed
to
co
m
p
a
r
e
th
e
ac
tu
al
v
alu
es
o
f
th
e
tar
g
et
v
a
r
iab
le
ag
ain
s
t
th
e
p
r
ed
ictio
n
s
m
ad
e
b
y
th
e
m
a
ch
in
e
lea
r
n
in
g
m
o
d
el.
Sin
ce
we
ar
e
d
ea
lin
g
with
a
b
in
ar
y
class
if
icatio
n
p
r
o
b
lem
[
2
1
]
,
we
u
s
e
d
a
2
×
2
m
atr
i
x
.
T
h
e
o
u
tco
m
es
o
f
th
e
co
n
f
u
s
io
n
m
atr
ix
f
o
r
b
o
th
m
o
d
els ar
e
p
r
e
s
en
ted
b
elo
w
in
Fig
u
r
e
s
4
(
a)
a
n
d
4
(
b
)
.
T
o
f
u
r
th
er
e
v
alu
ate
th
e
p
er
f
o
r
m
an
ce
o
f
b
o
th
m
o
d
els,
we
g
en
er
ated
a
class
if
icatio
n
r
ep
o
r
t
th
at
p
r
o
v
id
es
a
co
m
p
r
eh
e
n
s
iv
e
v
ie
w
o
f
ea
ch
m
o
d
el’
s
p
r
e
d
ictiv
e
ca
p
ab
ilit
ies
as
s
h
o
wn
in
Fig
u
r
e
5
(
a)
an
d
5
(
b
)
.
T
h
e
class
if
icatio
n
r
ep
o
r
t
in
clu
d
es
k
ey
m
etr
ics
s
u
ch
as
p
r
ec
is
io
n
,
r
ec
all,
F1
-
s
co
r
e,
an
d
s
u
p
p
o
r
t,
wh
ich
g
iv
e
in
s
ig
h
t
in
to
h
o
w
well
ea
ch
m
o
d
el
p
er
f
o
r
m
s
ac
r
o
s
s
d
if
f
er
en
t
class
es
.
T
h
ese
m
etr
ics
n
o
t
o
n
ly
ass
ess
o
v
er
all
ac
cu
r
ac
y
b
u
t
also
h
ig
h
lig
h
t
th
e
m
o
d
el
’
s
b
eh
a
v
io
r
w
h
en
h
an
d
li
n
g
im
b
alan
ce
d
class
es
o
r
m
o
r
e
ch
all
en
g
in
g
p
r
e
d
ictio
n
s
.
B
y
an
aly
zin
g
th
ese
k
ey
m
et
r
ics,
we
ca
n
g
ain
a
d
ee
p
er
u
n
d
er
s
tan
d
in
g
o
f
ea
c
h
m
o
d
el’
s
s
tr
en
g
th
s
an
d
wea
k
n
ess
es.
T
h
is
is
cr
u
cial
f
o
r
id
en
tify
i
n
g
ar
ea
s
wh
er
e
th
e
m
o
d
els
m
ay
n
ee
d
im
p
r
o
v
e
m
en
t,
p
ar
ticu
lar
ly
i
n
ca
s
es
wh
er
e
a
h
i
g
h
er
p
r
ec
is
i
o
n
o
r
r
e
ca
ll
m
ig
h
t
b
e
m
o
r
e
im
p
o
r
ta
n
t
d
e
p
en
d
in
g
o
n
t
h
e
s
p
ec
if
ic
b
u
s
in
ess
r
eq
u
ir
em
e
n
ts
,
s
u
ch
as
m
in
im
izin
g
f
alse
p
o
s
itiv
es
in
d
eliv
er
y
d
elay
s
o
r
r
e
d
u
cin
g
m
is
s
ed
d
elay
s
.
L
et’
s
b
r
ea
k
d
o
wn
th
e
k
ey
m
etr
ics in
t
h
e
cl
ass
if
icatio
n
r
ep
o
r
t:
T
h
e
class
if
icatio
n
r
ep
o
r
t p
r
o
v
i
d
es a
d
etailed
ev
alu
atio
n
o
f
a
class
if
icatio
n
m
o
d
el’
s
p
er
f
o
r
m
an
ce
,
s
u
ch
as
lo
g
is
tic
r
eg
r
ess
io
n
an
d
r
an
d
o
m
f
o
r
est
,
u
s
in
g
v
ar
io
u
s
m
etr
ics.
L
et’
s
b
r
ea
k
d
o
wn
th
e
k
ey
m
etr
ics p
r
esen
ted
in
th
e
class
if
icatio
n
r
ep
o
r
t:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
6
,
Decem
b
e
r
20
25
:
5
9
0
4
-
5
9
1
3
5910
a.
L
o
g
is
tic
r
eg
r
ess
io
n
:
−
Pre
cisi
o
n
(
0
)
:
m
ea
s
u
r
es
h
o
w
m
an
y
in
s
tan
ce
s
p
r
ed
icted
as
0
(
n
o
late
d
eliv
er
y
)
wer
e
0
.
I
t
i
s
ca
lcu
lated
as
+
.
I
n
th
is
ca
s
e,
th
e
p
r
ec
is
io
n
is
0
.
6
2
,
m
ea
n
in
g
th
at
6
2
%
o
f
th
e
in
s
tan
ce
s
p
r
e
d
icted
as
(
n
o
lat
e
d
eliv
er
y
)
wer
e
co
r
r
ec
tly
class
i
f
ied
as (
No
L
ate
Deliv
er
y
)
.
−
R
ec
all
(
0
)
:
m
ea
s
u
r
es
h
o
w
m
a
n
y
ac
tu
al
0
(
No
L
ate
Deliv
er
y
)
in
s
tan
ce
s
wer
e
c
o
r
r
ec
tly
p
r
e
d
icted
as
0
.
I
t
is
ca
lcu
lated
as
+
.
T
h
e
r
ec
all
f
o
r
0
is
0
.
7
1
,
in
d
icatin
g
th
at
7
1
%
o
f
th
e
ac
tu
al
(
n
o
late
d
eliv
er
y
)
in
s
tan
ce
s
wer
e
co
r
r
ec
tly
p
r
ed
icted
.
−
F1
-
s
co
r
e
(
0
)
:
is
th
e
h
ar
m
o
n
ic
m
ea
n
o
f
p
r
ec
is
io
n
an
d
r
ec
all
[
2
2
]
,
p
r
o
v
i
d
in
g
a
b
alan
ce
b
etw
ee
n
th
e
two
.
I
t
is
ca
lcu
lated
as
2
×
(
×
)
×
.
Fo
r
class
0
,
th
e
F1
-
s
co
r
e
is
0
.
6
6
.
−
Su
p
p
o
r
t
(
0
)
:
r
e
p
r
esen
ts
th
e
n
u
m
b
er
o
f
ac
tu
al
in
s
tan
ce
s
o
f
cla
s
s
0
in
th
e
test
s
et.
I
n
th
is
ca
s
e
,
th
e
s
u
p
p
o
r
t
is
2
1
0
,
9
6
9
.
(
a)
(
b
)
Fig
u
r
e
4
.
C
o
n
f
u
s
io
n
m
atr
i
x
co
m
p
ar
is
o
n
: (
a)
lo
g
is
tic
r
eg
r
ess
io
n
an
d
(
b
)
r
an
d
o
m
f
o
r
est
(
a)
(
b
)
Fig
u
r
e
5
.
C
lass
if
icatio
n
ev
alu
a
tin
g
class
if
icatio
n
m
o
d
el
p
er
f
o
r
m
an
ce
: a
co
m
p
ar
is
o
n
o
f
(
a
)
l
o
g
is
tic
r
eg
r
ess
io
n
an
d
(
b
)
r
an
d
o
m
f
o
r
est
No
w,
let’
s
in
ter
p
r
et
th
e
m
etr
ic
s
f
o
r
class
1
(
late
d
eliv
er
y
):
−
Pre
cisi
o
n
(
1
)
:
p
r
ec
is
io
n
f
o
r
cla
s
s
1
is
0
.
6
1
,
m
ea
n
in
g
th
at
am
o
n
g
th
e
in
s
tan
ce
s
p
r
e
d
icted
as
(
late
d
eliv
er
y
)
,
6
1
%
wer
e
co
r
r
e
ctly
class
if
ied
as (
late
d
eliv
er
y
).
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
-
8
7
0
8
E
n
h
a
n
cin
g
s
u
p
p
ly
c
h
a
in
a
g
ili
ty
w
ith
a
d
va
n
ce
d
w
ea
th
er fo
r
e
ca
s
tin
g
(
I
ma
n
e
Zer
o
u
a
l
)
5911
−
R
ec
all
(
1
)
:
r
ec
all
f
o
r
class
1
is
0
.
5
1
,
in
d
icatin
g
th
at
5
1
%
o
f
th
e
ac
tu
al
(
late
d
eliv
er
y
)
in
s
tan
ce
s
wer
e
co
r
r
ec
tly
p
r
ed
icted
.
−
F1
-
Sco
r
e
(
1
)
:
t
h
e
F1
-
s
co
r
e
f
o
r
class
1
is
0
.
5
5
,
b
alan
cin
g
p
r
ec
is
io
n
an
d
r
ec
all
f
o
r
th
is
class
.
−
Su
p
p
o
r
t
(
1
)
:
t
h
e
s
u
p
p
o
r
t
f
o
r
cl
ass
1
is
1
8
9
,
2
3
1
,
r
ep
r
esen
tin
g
th
e
ac
tu
al
in
s
tan
ce
s
o
f
(
late
d
eliv
er
y
)
i
n
th
e
test
s
et.
−
Acc
u
r
ac
y
:
t
h
e
o
v
er
all
ac
c
u
r
ac
y
o
f
t
h
e
lo
g
is
tic
r
eg
r
ess
io
n
m
o
d
el
is
0
.
6
1
,
m
ea
n
in
g
th
at
t
h
e
m
o
d
el
co
r
r
ec
tly
p
r
ed
icted
th
e
class
lab
els
[
2
3
]
f
o
r
6
1
%
o
f
th
e
i
n
s
tan
ce
s
in
th
e
test
s
et.
−
Ma
cr
o
Av
g
:
t
h
e
m
ac
r
o
a
v
er
ag
e
is
th
e
av
e
r
ag
e
o
f
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
f
o
r
b
o
th
class
es,
p
r
o
v
id
i
n
g
an
o
v
er
all
s
u
m
m
ar
y
o
f
m
o
d
el
p
er
f
o
r
m
an
ce
ac
r
o
s
s
all
class
es
[
2
4
]
.
I
n
th
is
c
ase,
th
e
m
ac
r
o
av
er
ag
e
is
0
.
6
1
.
−
W
eig
h
ted
Av
g
:
t
h
e
weig
h
ted
av
er
ag
e
is
th
e
av
er
ag
e
o
f
p
r
e
cisi
o
n
,
r
ec
all,
an
d
F1
-
s
co
r
e,
weig
h
ted
b
y
th
e
n
u
m
b
er
o
f
in
s
tan
ce
s
f
o
r
ea
ch
class
[
2
5
]
.
T
h
is
g
iv
es
a
p
e
r
f
o
r
m
an
ce
m
ea
s
u
r
e
th
at
tak
es
cl
ass
im
b
alan
ce
s
in
to
ac
co
u
n
t.
I
n
t
h
is
ca
s
e,
th
e
weig
h
ted
av
er
a
g
e
is
also
0
.
6
1
.
b.
R
an
d
o
m
f
o
r
est
T
h
e
in
ter
p
r
etatio
n
o
f
th
e
class
if
icatio
n
r
ep
o
r
t
f
o
r
r
an
d
o
m
f
o
r
est
is
lik
e
th
at
o
f
lo
g
is
tic
r
eg
r
ess
io
n
.
Ho
wev
er
,
th
e
r
an
d
o
m
f
o
r
est m
o
d
el
d
em
o
n
s
tr
ates
ex
ce
p
tio
n
al
p
er
f
o
r
m
an
ce
with
s
ig
n
if
ican
tly
h
ig
h
er
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
es
f
o
r
b
o
th
class
es
(
0
an
d
1
)
.
T
h
is
in
d
ic
ates
th
at
r
an
d
o
m
Fo
r
est
ac
h
iev
ed
an
im
p
r
ess
iv
e
9
9
%
ac
cu
r
ac
y
in
co
r
r
ec
tly
class
if
y
in
g
in
s
tan
ce
s
.
I
n
s
u
m
m
ar
y
,
wh
en
c
o
m
p
ar
i
n
g
th
e
two
m
o
d
els,
r
a
n
d
o
m
Fo
r
e
s
t
o
u
tp
er
f
o
r
m
s
lo
g
is
tic
r
eg
r
ess
io
n
ac
r
o
s
s
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
a
n
d
F1
-
s
co
r
e
f
o
r
b
o
th
class
es.
T
h
is
s
u
g
g
ests
th
at
r
an
d
o
m
Fo
r
e
s
t
is
m
o
r
e
ef
f
ec
tiv
e
at
class
if
y
in
g
in
s
tan
ce
s
o
f
b
o
th
(
n
o
late
d
eliv
er
y
)
a
n
d
(
late
d
eliv
er
y
)
b
ased
o
n
t
h
e
g
i
v
e
n
f
ea
tu
r
es.
A
g
o
o
d
m
o
d
el
is
o
n
e
with
h
ig
h
tr
u
e
p
o
s
itiv
e
(
T
P)
an
d
tr
u
e
n
eg
ativ
e
(
T
N)
r
ates
an
d
lo
w
f
alse
p
o
s
i
tiv
e
(
FP
)
an
d
f
alse
n
eg
ativ
e
(
FN)
r
ates.
T
h
e
u
s
e
o
f
l
o
g
is
tic
r
eg
r
ess
io
n
an
d
r
an
d
o
m
f
o
r
est
alg
o
r
ith
m
s
to
f
o
r
ec
ast
late
d
eliv
e
r
ies
is
a
p
o
wer
f
u
l
way
to
ad
d
r
ess
a
s
ig
n
if
ican
t
ch
allen
g
e
in
th
e
lo
g
is
tics
in
d
u
s
tr
y
[
2
6
]
,
[
2
7
]
.
L
o
g
is
tic
R
eg
r
es
s
io
n
is
an
ef
f
ec
tiv
e
m
eth
o
d
f
o
r
p
r
e
d
ictin
g
b
in
ar
y
o
u
tco
m
es,
s
u
ch
as
wh
et
h
er
a
d
eliv
er
y
will
b
e
late.
B
y
a
n
aly
zin
g
h
is
to
r
ical
s
u
p
p
ly
ch
ain
d
ata,
lo
g
is
tic
r
eg
r
ess
io
n
ca
n
esti
m
ate
th
e
p
r
o
b
ab
ilit
y
o
f
late
d
eliv
er
ies
b
ased
o
n
f
ac
to
r
s
lik
e
p
r
io
r
d
eliv
er
y
tim
es,
r
o
u
tes,
an
d
s
h
i
p
m
en
t
c
h
ar
ac
ter
is
tics
.
W
h
en
c
o
m
b
in
ed
with
r
ea
l
-
tim
e
wea
th
er
d
ata
f
r
o
m
API
s
,
lo
g
is
tic
r
eg
r
ess
io
n
ca
n
f
u
r
th
er
in
co
r
p
o
r
ate
wea
th
e
r
-
r
elate
d
v
ar
iab
les
s
u
ch
as
p
r
ec
ip
itatio
n
,
tem
p
e
r
atu
r
e,
an
d
r
o
ad
c
o
n
d
itio
n
s
,
o
f
f
e
r
in
g
a
m
o
r
e
co
m
p
r
eh
e
n
s
iv
e
an
d
ac
cu
r
ate
f
o
r
ec
ast.
On
th
e
o
t
h
er
h
an
d
,
th
e
r
an
d
o
m
f
o
r
est
tech
n
iq
u
e
p
r
o
v
i
d
es a
m
o
r
e
c
o
m
p
lex
an
d
r
o
b
u
s
t m
o
d
elin
g
ap
p
r
o
ac
h
[
2
8
]
.
3.
CO
NCLU
SI
O
N
I
n
co
n
cl
u
s
io
n
,
u
s
in
g
lo
g
is
tic
r
eg
r
ess
io
n
an
d
r
an
d
o
m
f
o
r
est
alg
o
r
ith
m
s
to
p
r
ed
ict
late
d
e
liv
er
ies,
in
co
m
b
in
atio
n
with
s
u
p
p
ly
ch
a
in
d
ata
an
d
wea
th
er
API
in
t
eg
r
atio
n
,
o
f
f
er
s
a
d
ata
-
d
r
iv
en
s
tr
ateg
y
with
th
e
p
o
ten
tial
to
tr
an
s
f
o
r
m
th
e
lo
g
i
s
tics
in
d
u
s
tr
y
.
T
h
ese
alg
o
r
ith
m
s
en
ab
le
lo
g
is
tics
p
r
o
f
ess
io
n
als
to
an
ticip
ate
an
d
m
in
im
ize
d
is
r
u
p
tio
n
s
b
y
le
v
er
ag
in
g
b
o
th
h
is
to
r
ical
d
ata
an
d
r
ea
l
-
tim
e
wea
th
er
i
n
f
o
r
m
atio
n
.
As
a
r
esu
lt,
th
e
y
en
h
an
ce
d
eliv
er
y
r
eliab
ilit
y
an
d
cu
s
to
m
er
s
atis
f
ac
tio
n
in
an
in
cr
ea
s
in
g
ly
co
m
p
lex
a
n
d
u
n
p
r
ed
ictab
le
wo
r
ld
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
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
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
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
I
m
an
e
Z
er
o
u
al
J
ab
er
E
l Bo
u
h
d
id
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
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
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
6
,
Decem
b
e
r
20
25
:
5
9
0
4
-
5
9
1
3
5912
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.
DATA AV
AI
L
AB
I
L
I
T
Y
Der
iv
ed
d
ata
s
u
p
p
o
r
tin
g
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
av
ailab
le
f
r
o
m
th
e
co
r
r
esp
o
n
d
in
g
au
th
o
r
I
Z
o
n
r
eq
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
W
.
Z
h
u
,
B
.
C
a
s
t
a
n
i
e
r
,
a
n
d
B
.
B
e
t
t
a
y
e
b
,
“
A
d
y
n
a
mi
c
p
r
o
g
r
a
mm
i
n
g
-
b
a
se
d
m
a
i
n
t
e
n
a
n
c
e
mo
d
e
l
o
f
o
f
f
sh
o
r
e
w
i
n
d
t
u
r
b
i
n
e
c
o
n
s
i
d
e
r
i
n
g
l
o
g
i
s
t
i
c
d
e
l
a
y
a
n
d
w
e
a
t
h
e
r
c
o
n
d
i
t
i
o
n
,
”
Re
l
i
a
b
i
l
i
t
y
En
g
i
n
e
e
r
i
n
g
&
S
y
st
e
m
S
a
f
e
t
y
,
v
o
l
.
1
9
0
,
p
.
1
0
6
5
1
2
,
O
c
t
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
e
ss.
2
0
1
9
.
1
0
6
5
1
2
.
[
2
]
L.
B
a
k
k
e
Li
e
,
V
.
L
y
s
g
a
a
r
d
,
a
n
d
A
.
K
r
i
s
t
o
f
f
e
r
S
y
d
n
e
s,
“
A
n
t
i
c
i
p
a
t
i
n
g
c
l
i
mat
e
r
i
sk
i
n
N
o
r
w
e
g
i
a
n
mu
n
i
c
i
p
a
l
i
t
i
e
s,”
C
l
i
m
a
t
e
R
i
s
k
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
4
6
,
p
.
1
0
0
6
5
8
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
r
m.
2
0
2
4
.
1
0
0
6
5
8
.
[
3
]
C
.
P
e
l
á
e
z
-
R
o
d
r
í
g
u
e
z
,
R
.
To
r
r
e
s
-
Ló
p
e
z
,
J.
P
é
r
e
z
-
A
r
a
c
i
l
,
N
.
Ló
p
e
z
-
La
g
u
n
a
,
S
.
S
á
n
c
h
e
z
-
R
o
d
r
í
g
u
e
z
,
a
n
d
S
.
S
a
l
c
e
d
o
-
S
a
n
z
,
“
A
n
e
x
p
l
a
i
n
a
b
l
e
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
h
o
s
p
i
t
a
l
e
m
e
r
g
e
n
c
y
d
e
p
a
r
t
me
n
t
v
i
s
i
t
s
f
o
r
e
c
a
st
i
n
g
u
si
n
g
c
o
n
t
i
n
u
o
u
s
t
r
a
i
n
i
n
g
a
n
d
mu
l
t
i
-
mo
d
e
l
r
e
g
r
e
ssi
o
n
,
”
C
o
m
p
u
t
e
r
M
e
t
h
o
d
s
a
n
d
P
ro
g
r
a
m
s
i
n
B
i
o
m
e
d
i
c
i
n
e
,
v
o
l
.
2
4
5
,
p
.
1
0
8
0
3
3
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
m
p
b
.
2
0
2
4
.
1
0
8
0
3
3
.
[
4
]
A
.
M
i
s
h
r
a
,
H
.
R
.
L
o
n
e
,
a
n
d
A
.
M
i
sh
r
a
,
“
D
e
c
o
d
e
:
d
a
t
a
-
d
r
i
v
e
n
e
n
e
r
g
y
c
o
n
s
u
m
p
t
i
o
n
p
r
e
d
i
c
t
i
o
n
l
e
v
e
r
a
g
i
n
g
h
i
st
o
r
i
c
a
l
d
a
t
a
a
n
d
e
n
v
i
r
o
n
m
e
n
t
a
l
f
a
c
t
o
r
s
i
n
b
u
i
l
d
i
n
g
s
,
”
E
n
e
r
g
y
a
n
d
B
u
i
l
d
i
n
g
s
,
v
o
l
.
3
0
7
,
p
.
1
1
3
9
5
0
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
b
u
i
l
d
.
2
0
2
4
.
1
1
3
9
5
0
.
[
5
]
J.
P
e
n
g
,
D
.
S
h
e
n
,
T.
N
i
e
,
a
n
d
Y
.
K
o
u
,
“
R
Lc
l
e
a
n
:
a
n
u
n
su
p
e
r
v
i
s
e
d
i
n
t
e
g
r
a
t
e
d
d
a
t
a
c
l
e
a
n
i
n
g
f
r
a
mew
o
r
k
b
a
se
d
o
n
d
e
e
p
r
e
i
n
f
o
r
c
e
me
n
t
l
e
a
r
n
i
n
g
,
”
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
6
8
2
,
p
.
1
2
1
2
8
1
,
N
o
v
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
s.
2
0
2
4
.
1
2
1
2
8
1
.
[
6
]
M
.
Ta
h
i
r
,
A
.
A
b
d
u
l
l
a
h
,
N
.
I
.
U
d
z
i
r
,
a
n
d
K
.
A
.
K
a
sm
i
r
a
n
,
“
A
n
o
v
e
l
a
p
p
r
o
a
c
h
f
o
r
h
a
n
d
l
i
n
g
mi
ss
i
n
g
d
a
t
a
t
o
e
n
h
a
n
c
e
n
e
t
w
o
r
k
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
s
y
st
e
m,
”
C
y
b
e
r
S
e
c
u
r
i
t
y
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
,
p
.
1
0
0
0
6
3
,
D
e
c
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
sa
.
2
0
2
4
.
1
0
0
0
6
3
.
[
7
]
Y
.
S
u
n
e
t
a
l
.
,
“
M
o
d
i
f
y
i
n
g
t
h
e
o
n
e
-
h
o
t
e
n
c
o
d
i
n
g
t
e
c
h
n
i
q
u
e
c
a
n
e
n
h
a
n
c
e
t
h
e
a
d
v
e
r
sar
i
a
l
r
o
b
u
st
n
e
ss
o
f
t
h
e
v
i
s
u
a
l
m
o
d
e
l
f
o
r
s
y
mb
o
l
r
e
c
o
g
n
i
t
i
o
n
,
”
Ex
p
e
r
t
S
y
s
t
e
m
s
w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
5
0
,
p
.
1
2
3
7
5
1
,
S
e
p
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
4
.
1
2
3
7
5
1
.
[
8
]
S
.
S
.
D
a
r
,
M
.
K
.
K
a
r
a
n
d
i
k
a
r
,
M
.
Z.
U
.
R
e
h
ma
n
,
S
.
B
a
n
s
a
l
,
a
n
d
N
.
K
u
m
a
r
,
“
A
c
o
n
t
r
a
s
t
i
v
e
t
o
p
i
c
-
a
w
a
r
e
a
t
t
e
n
t
i
v
e
f
r
a
m
e
w
o
r
k
w
i
t
h
l
a
b
e
l
e
n
c
o
d
i
n
g
s
f
o
r
p
o
st
-
d
i
sa
st
e
r
r
e
so
u
r
c
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
K
n
o
w
l
e
d
g
e
-
B
a
se
d
S
y
st
e
m
s
,
v
o
l
.
3
0
4
,
p
.
1
1
2
5
2
6
,
N
o
v
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
k
n
o
sy
s
.
2
0
2
4
.
1
1
2
5
2
6
.
[
9
]
W
.
L
u
p
L
o
w
,
M
.
Li
Le
e
,
a
n
d
T
.
W
a
n
g
Li
n
g
,
“
A
k
n
o
w
l
e
d
g
e
-
b
a
se
d
a
p
p
r
o
a
c
h
f
o
r
d
u
p
l
i
c
a
t
e
e
l
i
m
i
n
a
t
i
o
n
i
n
d
a
t
a
c
l
e
a
n
i
n
g
,
”
I
n
f
o
rm
a
t
i
o
n
S
y
st
e
m
s
,
v
o
l
.
2
6
,
n
o
.
8
,
p
p
.
5
8
5
–
6
0
6
,
D
e
c
.
2
0
0
1
,
d
o
i
:
1
0
.
1
0
1
6
/
S
0
3
0
6
-
4
3
7
9
(
0
1
)
0
0
0
4
1
-
2.
[
1
0
]
N
.
H
o
u
,
H
.
Zh
o
n
g
,
L.
S
u
n
,
a
n
d
L.
C
h
e
n
,
“
E
n
h
a
n
c
i
n
g
a
c
c
e
l
e
r
a
t
i
o
n
d
a
t
a
c
l
e
a
n
i
n
g
t
h
r
o
u
g
h
t
i
me
–
f
r
e
q
u
e
n
c
y
f
e
a
t
u
r
e
i
n
t
e
g
r
a
t
i
o
n
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
,
”
S
t
r
u
c
t
u
res
,
v
o
l
.
6
8
,
p
.
1
0
7
0
4
8
,
O
c
t
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
s
t
r
u
c
.
2
0
2
4
.
1
0
7
0
4
8
.
[
1
1
]
Q
.
H
a
n
,
Z.
Z
h
a
o
,
L
.
H
u
,
a
n
d
W
.
G
a
o
,
“
En
h
a
n
c
e
d
mu
l
t
i
-
l
a
b
e
l
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
c
o
n
s
i
d
e
r
i
n
g
l
a
b
e
l
-
sp
e
c
i
f
i
c
r
e
l
e
v
a
n
t
i
n
f
o
r
ma
t
i
o
n
,
”
Ex
p
e
rt
S
y
st
e
m
s w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
6
4
,
p
.
1
2
5
8
1
9
,
M
a
r
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
4
.
1
2
5
8
1
9
.
[
1
2
]
Z.
Y
a
n
,
Y
.
Zh
o
u
,
X
.
H
e
,
C
.
S
u
,
a
n
d
W
.
W
u
,
“
H
i
g
h
-
d
i
me
n
si
o
n
a
l
e
x
p
e
n
si
v
e
o
p
t
i
m
i
z
a
t
i
o
n
b
y
K
r
i
g
i
n
g
-
a
ss
i
st
e
d
m
u
l
t
i
o
b
j
e
c
t
i
v
e
e
v
o
l
u
t
i
o
n
a
r
y
a
l
g
o
r
i
t
h
m
w
i
t
h
d
i
m
e
n
si
o
n
a
l
i
t
y
r
e
d
u
c
t
i
o
n
,
”
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
6
9
1
,
p
.
1
2
1
6
2
0
,
F
e
b
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
s.
2
0
2
4
.
1
2
1
6
2
0
.
[
1
3
]
X
.
P
a
n
,
H
.
W
a
n
g
,
M
.
Le
i
,
T.
J
u
,
a
n
d
L.
B
a
i
,
“
A
me
t
h
o
d
f
o
r
f
i
l
l
i
n
g
mi
s
si
n
g
v
a
l
u
e
s
i
n
mu
l
t
i
v
a
r
i
a
t
e
se
q
u
e
n
c
e
b
i
d
i
r
e
c
t
i
o
n
a
l
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
s
b
a
s
e
d
o
n
f
e
a
t
u
r
e
c
o
r
r
e
l
a
t
i
o
n
s
,
”
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
a
t
i
o
n
a
l
S
c
i
e
n
c
e
,
v
o
l
.
8
3
,
p
.
1
0
2
4
7
2
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
o
c
s
.
2
0
2
4
.
1
0
2
4
7
2
.
[
1
4
]
G
.
Zh
a
o
e
t
a
l
.
,
“
En
h
a
n
c
i
n
g
i
n
t
e
r
p
r
e
t
a
b
i
l
i
t
y
o
f
t
r
e
e
-
b
a
se
d
m
o
d
e
l
s
f
o
r
d
o
w
n
s
t
r
e
a
m
sa
l
i
n
i
t
y
p
r
e
d
i
c
t
i
o
n
:
D
e
c
o
mp
o
si
n
g
f
e
a
t
u
r
e
i
mp
o
r
t
a
n
c
e
u
si
n
g
t
h
e
S
h
a
p
l
e
y
a
d
d
i
t
i
v
e
e
x
p
l
a
n
a
t
i
o
n
a
p
p
r
o
a
c
h
,
”
R
e
su
l
t
s
i
n
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
2
3
,
p
.
1
0
2
3
7
3
,
S
e
p
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
r
i
n
e
n
g
.
2
0
2
4
.
1
0
2
3
7
3
.
[
1
5
]
S
.
S
a
r
a
n
y
a
a
n
d
S
.
P
o
o
n
g
u
z
h
a
l
i
,
“
P
r
i
n
c
i
p
a
l
c
o
mp
o
n
e
n
t
a
n
a
l
y
s
i
s
b
i
p
l
o
t
v
i
s
u
a
l
i
z
a
t
i
o
n
o
f
e
l
e
c
t
r
o
m
y
o
g
r
a
m
f
e
a
t
u
r
e
s
f
o
r
s
u
b
ma
x
i
m
a
l
mu
sc
l
e
st
r
e
n
g
t
h
g
r
a
d
i
n
g
,
”
C
o
m
p
u
t
e
rs
i
n
Bi
o
l
o
g
y
a
n
d
M
e
d
i
c
i
n
e
,
v
o
l
.
1
8
2
,
p
.
1
0
9
1
4
2
,
N
o
v
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
b
i
o
m
e
d
.
2
0
2
4
.
1
0
9
1
4
2
.
[
1
6
]
A
.
P
a
t
h
a
k
,
U
.
B
a
r
ma
n
,
a
n
d
T
.
S
.
K
u
mar,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
t
o
d
e
t
e
c
t
a
n
d
r
o
i
d
m
a
l
w
a
r
e
u
s
i
n
g
f
e
a
t
u
r
e
-
sel
e
c
t
i
o
n
b
a
s
e
d
o
n
f
e
a
t
u
r
e
i
mp
o
r
t
a
n
c
e
s
c
o
r
e
,
”
J
o
u
r
n
a
l
o
f
En
g
i
n
e
e
ri
n
g
R
e
se
a
rc
h
,
v
o
l
.
1
3
,
n
o
.
2
,
p
p
.
7
1
2
–
7
2
0
,
J
u
n
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
e
r
.
2
0
2
4
.
0
4
.
0
0
8
.
[
1
7
]
A
.
Y
i
l
ma
z
A
d
k
i
n
s
o
n
e
t
a
l
.
,
“
A
ss
e
ss
i
n
g
d
i
f
f
e
r
e
n
t
c
r
o
ss
-
v
a
l
i
d
a
t
i
o
n
s
c
h
e
m
e
s
f
o
r
p
r
e
d
i
c
t
i
n
g
n
o
v
e
l
t
r
a
i
t
s
u
s
i
n
g
sen
s
o
r
d
a
t
a
:
A
n
a
p
p
l
i
c
a
t
i
o
n
t
o
d
r
y
mat
t
e
r
i
n
t
a
k
e
a
n
d
r
e
si
d
u
a
l
f
e
e
d
i
n
t
a
k
e
u
s
i
n
g
m
i
l
k
s
p
e
c
t
r
a
l
d
a
t
a
,
”
J
o
u
r
n
a
l
o
f
D
a
i
ry
S
c
i
e
n
c
e
,
v
o
l
.
1
0
7
,
n
o
.
1
0
,
p
p
.
8
0
8
4
–
8
0
9
9
,
O
c
t
.
2
0
2
4
,
d
o
i
:
1
0
.
3
1
6
8
/
j
d
s.
2
0
2
4
-
2
4
7
0
1
.
[
1
8
]
F
.
W
a
n
g
,
H
.
Zh
u
,
X
.
L
i
u
,
Y
.
Zh
e
n
g
,
H
.
Li
,
a
n
d
J.
H
u
a
,
“
A
c
h
i
e
v
i
n
g
f
e
d
e
r
a
t
e
d
l
o
g
i
st
i
c
r
e
g
r
e
ssi
o
n
t
r
a
i
n
i
n
g
t
o
w
a
r
d
s
m
o
d
e
l
c
o
n
f
i
d
e
n
t
i
a
l
i
t
y
w
i
t
h
s
e
mi
-
h
o
n
e
st
TEE
,
”
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
6
7
9
,
p
.
1
2
1
1
1
5
,
S
e
p
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
s
.
2
0
2
4
.
1
2
1
1
1
5
.
[
1
9
]
A
.
B
a
l
b
o
a
,
A
.
C
u
e
s
t
a
,
J.
G
o
n
z
á
l
e
z
-
V
i
l
l
a
,
G
.
O
r
t
i
z
,
a
n
d
D
.
A
l
v
e
a
r
,
“
L
o
g
i
s
t
i
c
r
e
g
r
e
ssi
o
n
v
s
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
t
o
p
r
e
d
i
c
t
e
v
a
c
u
a
t
i
o
n
d
e
c
i
si
o
n
s
i
n
f
i
r
e
a
l
a
r
m s
i
t
u
a
t
i
o
n
s
,
”
S
a
f
e
t
y
S
c
i
e
n
c
e
,
v
o
l
.
1
7
4
,
p
.
1
0
6
4
8
5
,
J
u
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
ssc
i
.
2
0
2
4
.
1
0
6
4
8
5
.
[
2
0
]
D
.
V
a
l
e
r
o
-
C
a
r
r
e
r
a
s,
J.
A
l
c
a
r
a
z
,
a
n
d
M
.
L
a
n
d
e
t
e
,
“
C
o
m
p
a
r
i
n
g
t
w
o
S
V
M
mo
d
e
l
s
t
h
r
o
u
g
h
d
i
f
f
e
r
e
n
t
met
r
i
c
s
b
a
s
e
d
o
n
t
h
e
c
o
n
f
u
s
i
o
n
mat
r
i
x
,
”
C
o
m
p
u
t
e
rs
& O
p
e
r
a
t
i
o
n
s
Re
sea
r
c
h
,
v
o
l
.
1
5
2
,
p
.
1
0
6
1
3
1
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
r
.
2
0
2
2
.
1
0
6
1
3
1
.
[
2
1
]
A
.
F
a
z
e
k
a
s
a
n
d
G
.
K
o
v
á
c
s,
“
Te
s
t
i
n
g
t
h
e
c
o
n
s
i
st
e
n
c
y
o
f
p
e
r
f
o
r
ma
n
c
e
sc
o
r
e
s
r
e
p
o
r
t
e
d
f
o
r
b
i
n
a
r
y
c
l
a
ssi
f
i
c
a
t
i
o
n
p
r
o
b
l
e
ms
,
”
A
p
p
l
i
e
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
6
4
,
p
.
1
1
1
9
9
3
,
O
c
t
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
s
o
c
.
2
0
2
4
.
1
1
1
9
9
3
.
[
2
2
]
S
.
H
i
n
d
u
j
a
,
T.
N
o
u
r
i
v
a
n
d
i
,
J.
F
.
C
o
h
n
,
a
n
d
S
.
C
a
n
a
v
a
n
,
“
Ti
me
t
o
r
e
t
i
r
e
F
1
-
b
i
n
a
r
y
s
c
o
r
e
f
o
r
a
c
t
i
o
n
u
n
i
t
d
e
t
e
c
t
i
o
n
,
”
P
a
t
t
e
r
n
R
e
c
o
g
n
i
t
i
o
n
Le
t
t
e
r
s
,
v
o
l
.
1
8
2
,
p
p
.
1
1
1
–
1
1
7
,
J
u
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
a
t
r
e
c
.
2
0
2
4
.
0
4
.
0
1
6
.
[
2
3
]
C
.
R
a
g
u
p
a
t
h
i
,
S
.
D
h
a
n
a
s
e
k
a
r
a
n
,
N
.
V
i
j
a
y
a
l
a
k
s
h
mi
,
a
n
d
A
.
O
.
S
a
l
a
u
,
“
P
r
e
d
i
c
t
i
o
n
o
f
e
l
e
c
t
r
i
c
i
t
y
c
o
n
su
m
p
t
i
o
n
u
si
n
g
a
n
i
n
n
o
v
a
t
i
v
e
d
e
e
p
e
n
e
r
g
y
p
r
e
d
i
c
t
o
r
m
o
d
e
l
f
o
r
e
n
h
a
n
c
e
d
a
c
c
u
r
a
c
y
a
n
d
e
f
f
i
c
i
e
n
c
y
,
”
E
n
e
rg
y
Re
p
o
rt
s
,
v
o
l
.
1
2
,
p
p
.
5
3
2
0
–
5
3
3
7
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
g
y
r
.
2
0
2
4
.
1
1
.
0
1
8
.
[
2
4
]
A
.
B
e
r
g
e
r
a
n
d
S
.
G
u
d
a
,
“
T
h
r
e
s
h
o
l
d
o
p
t
i
m
i
z
a
t
i
o
n
f
o
r
F
m
e
a
s
u
r
e
o
f
m
a
c
r
o
-
a
v
e
r
a
g
e
d
p
r
e
c
i
s
i
o
n
a
n
d
r
e
c
a
l
l
,
”
P
a
t
t
e
rn
Re
c
o
g
n
i
t
i
o
n
,
v
o
l
.
1
0
2
,
p
.
1
0
7
2
5
0
,
J
u
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
a
t
c
o
g
.
2
0
2
0
.
1
0
7
2
5
0
.
[
2
5
]
J.
C
h
e
n
g
a
n
d
W
.
D
e
W
a
e
l
e
,
“
W
e
i
g
h
t
e
d
a
v
e
r
a
g
e
a
l
g
o
r
i
t
h
m
:
A
n
o
v
e
l
m
e
t
a
-
h
e
u
r
i
s
t
i
c
o
p
t
i
m
i
z
a
t
i
o
n
a
l
g
o
r
i
t
h
m
b
a
s
e
d
o
n
t
h
e
w
e
i
g
h
t
e
d
a
v
e
r
a
g
e
p
o
s
i
t
i
o
n
c
o
n
c
e
p
t
,
”
K
n
o
w
l
e
d
g
e
-
Ba
s
e
d
S
y
st
e
m
s
,
v
o
l
.
3
0
5
,
p
.
1
1
2
5
6
4
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
k
n
o
s
y
s.
2
0
2
4
.
1
1
2
5
6
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
-
8
7
0
8
E
n
h
a
n
cin
g
s
u
p
p
ly
c
h
a
in
a
g
ili
ty
w
ith
a
d
va
n
ce
d
w
ea
th
er fo
r
e
ca
s
tin
g
(
I
ma
n
e
Zer
o
u
a
l
)
5913
[
2
6
]
X
.
G
u
o
,
A
.
C
h
a
u
h
a
n
,
J.
V
e
r
sch
o
o
r
,
a
n
d
A
.
M
a
r
g
e
r
t
,
“
A
q
u
a
l
i
t
y
d
e
c
a
y
mo
d
e
l
w
i
t
h
m
u
l
t
i
n
o
m
i
a
l
l
o
g
i
st
i
c
r
e
g
r
e
ss
i
o
n
a
n
d
i
m
a
g
e
-
b
a
se
d
d
e
e
p
l
e
a
r
n
i
n
g
t
o
p
r
e
d
i
c
t
t
h
e
f
i
r
mn
e
s
s
o
f
‘
C
o
n
f
e
r
e
n
c
e
’
p
e
a
r
s
i
n
t
h
e
d
o
w
n
st
r
e
a
m
su
p
p
l
y
c
h
a
i
n
s,
”
J
o
u
r
n
a
l
o
f
S
t
o
re
d
Pr
o
d
u
c
t
s
Re
se
a
rc
h
,
v
o
l
.
1
0
9
,
p
.
1
0
2
4
5
0
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
s
p
r
.
2
0
2
4
.
1
0
2
4
5
0
.
[
2
7
]
M
.
R
.
A
l
i
,
S
.
M
.
A
.
N
i
p
u
,
a
n
d
S
.
A
.
K
h
a
n
,
“
A
d
e
c
i
s
i
o
n
s
u
p
p
o
r
t
s
y
st
e
m
f
o
r
c
l
a
ss
i
f
y
i
n
g
s
u
p
p
l
i
e
r
s
e
l
e
c
t
i
o
n
c
r
i
t
e
r
i
a
u
s
i
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
r
a
n
d
o
m
f
o
r
e
st
a
p
p
r
o
a
c
h
,
”
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
.
7
,
p
.
1
0
0
2
3
8
,
J
u
n
.
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
2
3
8
.
[
2
8
]
C
.
I
.
A
l
l
e
n
A
k
s
e
l
r
u
d
,
“
R
a
n
d
o
m
F
o
r
e
st
r
e
g
r
e
ss
i
o
n
mo
d
e
l
s
i
n
e
c
o
l
o
g
y
:
a
c
c
o
u
n
t
i
n
g
f
o
r
mes
sy
b
i
o
l
o
g
i
c
a
l
d
a
t
a
a
n
d
p
r
o
d
u
c
i
n
g
p
r
e
d
i
c
t
i
o
n
s wi
t
h
u
n
c
e
r
t
a
i
n
t
y
,
”
F
i
s
h
e
ri
e
s R
e
se
a
rc
h
,
v
o
l
.
2
8
0
,
p
.
1
0
7
1
6
1
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
f
i
sh
r
e
s
.
2
0
2
4
.
1
0
7
1
6
1
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Im
a
n
e
Ze
r
o
u
a
l
is
a
d
a
ta
e
n
g
i
n
e
e
r
c
u
rre
n
tl
y
p
u
rs
u
in
g
a
P
h
.
D.
i
n
c
o
m
p
u
ter
sc
ien
c
e
a
t
th
e
re
se
a
rc
h
lab
o
ra
to
r
y
o
f
i
n
fo
r
m
a
ti
o
n
sy
ste
m
s
a
n
d
so
ftwa
re
e
n
g
in
e
e
rin
g
(S
IG
L),
Un
iv
e
rsit
y
Ab
d
e
lma
lek
Essa
a
d
i,
Na
ti
o
n
a
l
S
c
h
o
o
l
o
f
A
p
p
l
ied
S
c
ien
c
e
s
-
Teto
u
a
n
,
M
o
ro
c
c
o
.
S
h
e
h
o
l
d
s
a
n
e
n
g
in
e
e
rin
g
d
e
g
re
e
in
in
f
o
rm
a
ti
o
n
sy
ste
m
s
a
n
d
d
e
c
isio
n
s
u
p
p
o
rt
f
ro
m
th
e
Na
ti
o
n
a
l
S
c
h
o
o
l
o
f
Ap
p
li
e
d
S
c
ien
c
e
s
in
M
o
r
o
c
c
o
a
n
d
a
m
a
ste
r’s
d
e
g
re
e
in
b
ig
d
a
ta
a
n
d
m
a
c
h
in
e
lea
rn
in
g
fr
o
m
th
e
Un
iv
e
rsity
o
f
Li
ll
e
,
F
ra
n
c
e
.
He
r
r
e
se
a
rc
h
in
tere
sts
in
c
lu
d
e
m
a
c
h
in
e
lea
rn
in
g
,
in
ter
n
e
t
o
f
t
h
i
n
g
s
(Io
T)
a
p
p
li
c
a
ti
o
n
s,
b
ig
d
a
ta
a
n
a
l
y
ti
c
s,
d
a
ta
e
n
g
in
e
e
rin
g
,
a
n
d
sc
a
lab
le
d
a
ta
p
r
o
c
e
ss
in
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ima
n
e
.
z
e
ro
u
a
l1
@e
tu
.
u
a
e
.
a
c
.
m
a
.
J
a
b
e
r
E
l
B
o
u
h
d
id
i
is
a
n
HD
R
p
ro
fe
ss
o
r
o
f
c
o
m
p
u
ter
sc
ien
c
e
a
t
t
h
e
S
IG
L
Lab
o
ra
to
r
y
,
Un
i
v
e
rsity
Ab
d
e
lma
lek
Essa
a
d
i,
Na
ti
o
n
a
l
S
c
h
o
o
l
o
f
Ap
p
li
e
d
S
c
ien
c
e
s
-
Teto
u
a
n
-
M
o
ro
c
c
o
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
we
b
se
m
a
n
ti
c
,
m
u
lt
i
-
a
g
e
n
ts’
sy
ste
m
s,
e
-
lea
rn
in
g
a
d
a
p
ti
v
e
sy
ste
m
s
a
n
d
b
i
g
d
a
ta.
H
e
h
a
s
se
v
e
ra
l
p
a
p
e
rs
in
i
n
tern
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s
a
n
d
jo
u
rn
a
ls.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ja
b
e
r.
e
lb
o
u
h
d
i
d
i@
u
a
e
.
a
c
.
m
a
.
Evaluation Warning : The document was created with Spire.PDF for Python.