I
nte
rna
t
io
na
l J
o
urna
l o
f
Adv
a
nces in Applie
d Science
s
(
I
J
AAS)
Vo
l.
14
,
No
.
2
,
J
u
n
e
2
0
2
5
,
p
p
.
618
~
6
2
6
I
SS
N:
2252
-
8
8
1
4
,
DOI
:
1
0
.
1
1
5
9
1
/ijaas
.
v
14
.
i
2
.
pp
618
-
6
2
6
618
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
a
s
.
ia
esco
r
e.
co
m
Co
mbinin
g
XG
B
o
o
st
a
nd hy
brid f
i
ltering a
lg
o
rithm
in
e
-
co
mm
erce
rec
o
mm
enda
tion sy
st
em
Vincent
iu
s
L
o
a
nk
a
Sin
a
g
a
,
Ant
o
ni Wibo
wo
G
r
a
d
u
a
t
e
P
r
o
g
r
a
m
,
M
a
s
t
e
r
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
B
i
n
a
N
u
sa
n
t
a
r
a
U
n
i
v
e
r
s
i
t
y
,
Ja
k
a
r
t
a
,
I
n
d
o
n
e
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
No
v
1
2
,
2
0
2
4
R
ev
is
ed
Ap
r
7
,
2
0
2
5
Acc
ep
ted
Ap
r
2
3
,
2
0
2
5
Th
is
st
u
d
y
p
ro
p
o
se
s
a
h
y
b
ri
d
fil
terin
g
a
lg
o
rit
h
m
(HFA)
th
a
t
c
o
m
b
in
e
s
e
x
trem
e
g
ra
d
ien
t
b
o
o
sti
n
g
(
XG
Bo
o
st
)
,
c
o
n
te
n
t
-
b
a
se
d
f
il
terin
g
(
CBF
),
a
n
d
c
o
ll
a
b
o
ra
ti
v
e
fil
teri
n
g
(CF
)
to
imp
ro
v
e
re
c
o
m
m
e
n
d
a
ti
o
n
a
c
c
u
ra
c
y
in
e
lec
tro
n
ic
c
o
m
m
e
rc
e
(
e
-
c
o
m
m
e
r
c
e
)
.
XG
Bo
o
st
first
lev
e
ra
g
e
s
d
e
m
o
g
ra
p
h
ic
d
a
ta
(e
.
g
.
,
a
g
e
,
g
e
n
d
e
r,
a
n
d
lo
c
a
ti
o
n
)
t
o
a
d
d
re
ss
c
o
l
d
sta
rt
c
o
n
d
it
io
n
s
,
p
ro
d
u
c
in
g
a
n
i
n
it
ial
p
ro
d
u
c
t
p
r
e
d
ictio
n
;
CBF
re
fin
e
s
th
is
p
re
d
ictio
n
b
y
m
e
a
su
rin
g
p
r
o
d
u
c
t
sim
il
a
rit
ies
t
h
ro
u
g
h
term
fre
q
u
e
n
c
y
-
in
v
e
rse
d
o
c
u
m
e
n
t
fre
q
u
e
n
c
y
(
TF
-
IDF
)
a
n
d
c
o
sin
e
sim
il
a
rit
y
,
wh
i
le
CF
(imp
lem
e
n
ted
v
ia
sin
g
u
lar
v
a
l
u
e
d
e
c
o
m
p
o
siti
o
n
)
f
u
rth
e
r
in
c
o
rp
o
ra
tes
u
se
r
in
tera
c
ti
o
n
p
a
tt
e
r
n
s
to
e
n
h
a
n
c
e
re
c
o
m
m
e
n
d
a
ti
o
n
s.
E
x
p
e
rime
n
tal
re
su
lt
s
a
c
ro
ss
m
u
lt
ip
l
e
d
a
tas
e
ts
d
e
m
o
n
stra
te
th
a
t
HFA
c
o
n
siste
n
tl
y
o
u
tp
e
rf
o
rm
s
sta
n
d
a
lo
n
e
XG
Bo
o
st
in
k
e
y
m
e
tri
c
s,
in
c
lu
d
i
n
g
p
re
c
isio
n
,
F
1
-
sc
o
re
,
a
n
d
h
it
ra
ti
o
(
HR
)
.
HFA’s
p
re
c
isio
n
o
ften
e
x
c
e
e
d
s
9
0
%
,
in
d
ica
ti
n
g
fe
we
r
irrele
v
a
n
t
re
c
o
m
m
e
n
d
a
ti
o
n
s.
Alth
o
u
g
h
re
c
a
ll
lev
e
ls
re
m
a
in
m
o
d
e
st,
HFA
e
x
h
ib
i
ts
stro
n
g
e
r
a
d
a
p
tab
il
it
y
u
n
d
e
r
c
o
ld
sta
rt
sc
e
n
a
rio
s
d
u
e
to
it
s
re
li
a
n
c
e
o
n
d
e
m
o
g
ra
p
h
ic
fe
a
tu
re
s
a
n
d
u
se
r
-
it
e
m
in
tera
c
ti
o
n
s.
T
h
e
se
fin
d
in
g
s
h
ig
h
li
g
h
t
t
h
e
e
ffica
c
y
o
f
c
o
m
b
in
in
g
a
d
v
a
n
c
e
d
m
a
c
h
in
e
lea
rn
in
g
wit
h
h
y
b
ri
d
fi
lt
e
rin
g
tec
h
n
iq
u
e
s,
o
ffe
ri
n
g
a
m
o
re
ro
b
u
st
a
n
d
c
o
n
tex
t
-
a
wa
re
so
lu
ti
o
n
fo
r
e
-
c
o
m
m
e
rc
e
re
c
o
m
m
e
n
d
a
ti
o
n
sy
ste
m
s.
K
ey
w
o
r
d
s
:
C
o
llab
o
r
ativ
e
f
ilter
in
g
C
o
n
ten
t
-
b
ased
f
ilter
in
g
E
-
co
m
m
er
ce
R
ec
o
m
m
en
d
atio
n
s
y
s
tem
s
X
G
B
o
o
s
t
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
:
An
to
n
i Wi
b
o
wo
Gr
ad
u
ate
Pro
g
r
am
,
Ma
s
ter
o
f
C
o
m
p
u
ter
Scien
ce
,
B
in
a
Nu
s
a
n
tar
a
Un
iv
er
s
ity
Keb
o
n
J
er
u
k
Hig
h
way
,
Kem
a
n
g
g
is
an
,
Palm
er
ah
,
J
ak
ar
ta
B
ar
at
1
1
4
8
0
,
I
n
d
o
n
esia
E
m
ail:
an
wib
o
wo
@
b
in
u
s
.
ed
u
1.
I
NT
RO
D
UCT
I
O
N
E
lectr
o
n
ic
c
o
m
m
er
ce
(
e
-
c
o
m
m
er
ce
)
r
ef
er
s
to
th
e
p
u
r
ch
asin
g
an
d
s
ellin
g
o
f
in
f
o
r
m
atio
n
,
g
o
o
d
s
,
an
d
s
er
v
ices
v
ia
th
e
i
n
ter
n
et
[
1
]
,
[
2
]
.
W
ith
th
e
ad
v
an
ce
m
en
t
o
f
th
e
in
ter
n
et
an
d
s
m
ar
t
d
ev
ice
s
,
e
-
co
m
m
er
ce
h
as
b
ec
o
m
e
an
in
teg
r
al
p
ar
t
o
f
d
ai
ly
life
,
o
f
f
er
in
g
a
wid
e
r
an
g
e
o
f
p
r
o
d
u
cts
with
s
ig
n
if
ican
t
v
ar
iatio
n
,
wh
ich
ca
n
m
ak
e
it
ch
allen
g
i
n
g
f
o
r
u
s
er
s
to
ch
o
o
s
e
item
s
th
at
m
atc
h
th
eir
p
r
ef
er
e
n
ce
s
.
T
o
a
d
d
r
ess
th
i
s
,
r
ec
o
m
m
en
d
atio
n
s
y
s
tem
s
h
av
e
b
ee
n
d
ev
elo
p
e
d
,
m
im
ic
k
in
g
n
atu
r
al
s
o
cial
b
eh
av
io
r
s
s
u
ch
as
wo
r
d
-
of
-
m
o
u
th
s
u
g
g
esti
o
n
s
to
g
u
id
e
u
s
er
d
ec
is
io
n
s
b
y
p
r
e
d
ictin
g
f
u
tu
r
e
p
r
ef
er
en
ce
s
b
ase
d
o
n
p
ast
ev
alu
atio
n
s
[
3
]
,
[
4
]
.
T
wo
wid
ely
u
s
ed
ap
p
r
o
ac
h
es
in
r
ec
o
m
m
en
d
atio
n
s
y
s
tem
s
ar
e
co
n
ten
t
-
b
ased
f
ilter
in
g
(
C
B
F)
an
d
co
llab
o
r
a
tiv
e
f
ilter
in
g
(
C
F).
C
B
F
s
u
g
g
ests
item
s
with
s
im
ilar
attr
ib
u
tes
to
th
o
s
e
a
u
s
er
h
as
p
r
ev
io
u
s
ly
s
h
o
wn
in
ter
est
i
n
[
5
]
,
[
6
]
,
wh
ile
C
F
r
ec
o
m
m
en
d
s
p
r
o
d
u
cts b
y
a
n
al
y
zin
g
s
im
ila
r
ities
b
etwe
en
u
s
er
s
b
ased
o
n
th
eir
in
ter
ac
tio
n
h
i
s
to
r
y
[
7
]
,
[
8
]
.
Ho
wev
er
,
b
o
th
m
eth
o
d
s
h
av
e
lim
itatio
n
s
.
C
B
F
ca
n
s
u
f
f
er
f
r
o
m
o
v
e
r
s
p
ec
ializatio
n
,
o
f
f
e
r
in
g
o
v
er
ly
s
im
ilar
s
u
g
g
esti
o
n
s
,
wh
ile
C
F
is
s
u
s
ce
p
tib
le
to
d
ata
s
p
ar
s
ity
an
d
co
ld
s
tar
t
p
r
o
b
lem
s
,
p
ar
ticu
lar
ly
w
h
en
d
ea
lin
g
with
n
ew
u
s
er
s
lack
in
g
s
u
f
f
icien
t
h
is
to
r
ical
d
ata
[
9
]
.
T
o
o
v
er
co
m
e
th
ese
is
s
u
es,
h
y
b
r
id
s
y
s
tem
s
th
at
co
m
b
in
e
C
F
an
d
C
B
F
h
av
e
b
ee
n
p
r
o
p
o
s
ed
.
Sh
a
r
m
a
et
a
l
.
[
1
0
]
i
n
teg
r
ated
C
F
an
d
C
B
F,
ac
h
iev
in
g
a
s
ig
n
if
ican
tly
lo
wer
m
ea
n
ab
s
o
lu
te
er
r
o
r
(
MA
E
)
th
a
n
ei
th
er
m
eth
o
d
alo
n
e,
wh
ile
L
i
et
a
l
.
[
1
1
]
a
n
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
C
o
mb
in
in
g
X
Gb
o
o
s
t a
n
d
h
yb
r
id
filt
erin
g
a
lg
o
r
ith
m
in
E
-
co
mme
r
ce
…
(
V
in
ce
n
tiu
s
Lo
a
n
k
a
S
in
a
g
a
)
619
B
ah
l
et
a
l
.
[
1
2
]
f
u
r
th
er
co
n
f
ir
m
ed
th
at
h
y
b
r
i
d
C
F
-
C
B
F
s
y
s
tem
s
o
u
tp
er
f
o
r
m
s
tan
d
alo
n
e
ap
p
r
o
ac
h
es.
Nev
er
th
eless
,
th
ese
m
o
d
els s
ti
ll d
ep
en
d
o
n
e
x
is
tin
g
u
s
er
in
te
r
ac
tio
n
d
ata
an
d
d
o
n
o
t
f
u
lly
r
eso
lv
e
th
e
co
ld
s
tar
t
p
r
o
b
lem
.
Ad
v
a
n
ce
m
en
ts
in
C
F,
s
u
ch
as
in
teg
r
atin
g
s
in
g
u
lar
v
alu
e
d
ec
o
m
p
o
s
itio
n
(
S
VD)
,
h
av
e
im
p
r
o
v
ed
ac
cu
r
ac
y
an
d
r
e
d
u
ce
d
s
p
a
r
s
ity
[
1
3
]
,
[
1
4
]
,
y
et
co
ld
s
tar
t
s
ce
n
ar
io
s
r
em
ain
a
c
h
allen
g
e
d
u
e
t
o
in
s
u
f
f
icien
t
u
s
er
in
ter
ac
tio
n
d
ata.
Par
allel
im
p
r
o
v
em
e
n
ts
in
C
B
F
h
av
e
b
ee
n
m
ad
e
th
r
o
u
g
h
en
h
an
ce
d
s
im
ilar
ity
m
ea
s
u
r
es
an
d
in
teg
r
atio
n
with
m
ac
h
in
e
lear
n
in
g
.
A
b
d
u
r
r
af
i
an
d
Nin
g
s
ih
[
1
5
]
u
s
ed
co
s
in
e
s
im
ilar
ity
with
C
B
F
to
ac
h
iev
e
h
ig
h
p
r
ec
is
io
n
,
w
h
ile
Sh
ah
b
a
zi
et
a
l.
[
1
6
]
e
n
h
an
ce
d
C
B
F
b
y
in
te
g
r
atin
g
it
with
ex
t
r
em
e
g
r
ad
ie
n
t
b
o
o
s
tin
g
(
XGBo
o
s
t
)
,
ac
h
iev
in
g
s
u
p
er
io
r
ac
cu
r
ac
y
o
v
er
v
a
r
io
u
s
m
ac
h
in
e
lear
n
in
g
m
o
d
els.
Similar
ly
,
Ma
lek
et
a
l
.
[
1
7
]
d
em
o
n
s
tr
ate
d
XGBo
o
s
t’
s
s
tr
en
g
th
in
h
an
d
lin
g
im
b
alan
ce
d
d
ata,
r
ein
f
o
r
cin
g
its
v
alu
e
as
an
in
itial
p
r
ed
icto
r
.
Desp
ite
p
r
o
m
is
in
g
r
esu
lts
f
r
o
m
h
y
b
r
i
d
C
F
-
C
B
F
s
y
s
tem
s
an
d
XGBo
o
s
t
-
en
h
an
ce
d
C
B
F
m
o
d
els,
g
ap
s
r
em
ain
-
p
ar
ticu
lar
ly
in
in
co
r
p
o
r
atin
g
d
em
o
g
r
a
p
h
ic
f
ea
tu
r
es
(
e.
g
.
,
a
g
e
,
g
en
d
e
r
,
an
d
l
o
ca
tio
n
)
an
d
f
u
lly
in
teg
r
atin
g
XGBo
o
s
t w
ith
b
o
th
C
B
F a
n
d
C
F to
b
alan
ce
co
n
ten
t a
n
d
u
s
e
r
b
eh
av
i
o
r
d
ata.
B
ased
o
n
th
ese
in
s
ig
h
ts
,
th
is
s
tu
d
y
p
r
o
p
o
s
es
a
n
o
v
el
h
y
b
r
i
d
f
ilter
in
g
alg
o
r
ith
m
(
HFA)
th
at
in
teg
r
ates
XGBo
o
s
t
,
C
B
F,
an
d
C
F
-
SV
D
to
ad
d
r
ess
th
e
co
ld
s
tar
t
p
r
o
b
lem
a
n
d
en
h
an
ce
r
ec
o
m
m
en
d
atio
n
ac
c
u
r
ac
y
.
XGBo
o
s
t
f
u
n
ctio
n
s
as
th
e
in
itial
p
r
ed
icto
r
,
u
tili
zin
g
d
em
o
g
r
ap
h
ic
d
ata,
f
o
llo
wed
b
y
r
ef
in
em
en
t
th
r
o
u
g
h
C
B
F’s
co
n
ten
t
s
im
ilar
ity
a
n
d
C
F
-
SVD’
s
in
ter
ac
tio
n
-
b
ase
d
r
ec
o
m
m
en
d
ati
o
n
s
.
T
h
e
f
i
n
al
r
ec
o
m
m
e
n
d
atio
n
o
u
tp
u
t
is
g
en
er
ated
th
r
o
u
g
h
a
weig
h
ted
s
co
r
in
g
m
ec
h
an
is
m
th
at
b
alan
ce
s
r
ele
v
an
ce
a
n
d
d
i
v
er
s
ity
.
C
o
m
p
ar
e
d
to
s
tan
d
alo
n
e
XGBo
o
s
t,
th
is
i
n
teg
r
ated
f
r
am
ewo
r
k
co
n
s
is
te
n
tly
ac
h
iev
es
h
i
g
h
er
p
r
ec
is
io
n
,
F1
-
s
co
r
es,
an
d
h
it
r
atio
s
(
HR
s
)
ac
r
o
s
s
v
ar
io
u
s
d
atasets
an
d
s
ce
n
ar
io
s
.
T
h
e
r
em
ain
d
er
o
f
th
is
p
a
p
er
is
s
tr
u
ctu
r
ed
as
f
o
ll
o
ws:
s
ec
tio
n
2
r
ev
iews
th
e
liter
atu
r
e,
s
ec
tio
n
3
p
r
esen
ts
th
e
m
eth
o
d
o
lo
g
y
,
s
ec
tio
n
4
d
is
cu
s
s
es
ex
p
er
im
en
tal
r
esu
lts
,
an
d
s
ec
tio
n
5
c
o
n
clu
d
es with
f
u
tu
r
e
r
esear
ch
d
ir
ec
tio
n
s
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
is
s
tu
d
y
h
as
in
tr
o
d
u
ce
d
a
HFA
th
at
c
o
m
b
in
es
XGBo
o
s
t,
C
B
F
,
an
d
CF
to
im
p
r
o
v
e
r
ec
o
m
m
en
d
atio
n
ac
c
u
r
ac
y
i
n
e
-
co
m
m
er
ce
,
as
illu
s
tr
ated
in
Fig
u
r
e
1
.
I
n
itially
,
XGBo
o
s
t
u
tili
ze
s
d
e
m
o
g
r
ap
h
ic
d
ata,
s
u
ch
as
ag
e,
g
en
d
er
,
a
n
d
lo
ca
tio
n
,
to
m
ak
e
p
r
elim
in
ar
y
p
r
o
d
u
ct
r
ec
o
m
m
en
d
ati
o
n
s
f
o
r
n
ew
u
s
er
s
.
Su
b
s
eq
u
en
tly
,
C
B
F
r
ef
in
es
th
ese
r
ec
o
m
m
en
d
atio
n
s
b
y
ass
ess
in
g
th
e
s
im
ilar
ity
b
etwe
en
p
r
o
d
u
cts
u
s
in
g
ter
m
f
r
eq
u
e
n
cy
-
in
v
er
s
e
d
o
cu
m
en
t
f
r
eq
u
en
c
y
(
TF
-
I
DF
)
an
d
c
o
s
in
e
s
im
ilar
ity
.
Fin
ally
,
C
F
em
p
lo
y
s
s
in
g
u
lar
v
alu
e
d
ec
o
m
p
o
s
itio
n
to
in
c
o
r
p
o
r
ate
u
s
er
in
ter
ac
tio
n
s
wit
h
p
r
o
d
u
cts,
f
u
r
th
e
r
im
p
r
o
v
in
g
th
e
o
v
er
all
r
ec
o
m
m
en
d
atio
n
s
.
Fig
u
r
e
1
.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
14
,
No
.
2
,
J
u
n
e
2
0
2
5
:
6
1
8
-
626
620
2
.
1
.
Da
t
a
s
et
T
h
e
f
ir
s
t
d
ataset
was
o
b
tain
ed
f
r
o
m
Kag
g
le
an
d
is
titl
ed
“
E
-
c
o
m
m
er
ce
s
ales
d
ata
2023
-
2
4
”
[
1
8
]
T
h
is
d
ataset
co
n
s
is
ts
o
f
tr
an
s
ac
tio
n
d
ata
f
r
o
m
2
0
2
4
(
E
-
c
o
m
m
er
ce
s
ales
d
ata
2
0
2
4
)
,
p
r
o
d
u
ct
d
etails
(
p
r
o
d
u
ct_
d
etail)
,
a
n
d
u
s
er
-
r
elate
d
d
ata
(
cu
s
to
m
er
_
d
et
ail)
.
T
h
e
s
ec
o
n
d
d
ataset
u
s
ed
is
titl
ed
“Bra
zilian
_
ec
o
m
m
er
ce
_
a
n
aly
s
es_
v
2
”
[
1
9
]
.
T
h
e
tr
a
n
s
ac
tio
n
d
ataset
is
a
c
o
m
b
in
atio
n
o
f
o
lis
t_
o
r
d
er
_
d
ataset,
o
lis
t_
o
r
d
er
_
item
s
,
a
n
d
o
lis
t_
o
r
d
er
_
r
ev
iews_
d
ataset.
Ho
wev
er
,
p
r
o
d
u
ct
d
etails
ar
e
s
o
u
r
ce
d
f
r
o
m
o
lis
t_
p
r
o
d
u
cts_
d
ataset,
wh
ile
u
s
er
d
etails ar
e
ex
tr
ac
ted
f
r
o
m
o
lis
t_
cu
s
to
m
er
_
d
ataset.
T
h
e
th
ir
d
d
ataset
is
ti
tled
“E
co
m
m
er
ce
_
b
i
g
Qu
er
y
”
[
2
0
]
.
T
h
is
d
ataset
h
as
a
s
tr
u
ctu
r
e
li
k
e
th
e
“E
-
co
m
m
er
ce
s
ales
d
at
a
2
0
2
3
-
2
4
”
d
ataset
b
u
t
with
d
if
f
er
e
n
t
n
am
in
g
co
n
v
en
tio
n
s
.
Fo
r
i
n
s
tan
ce
,
th
e
tr
an
s
ac
tio
n
d
ataset
is
lab
eled
“o
r
d
er
_
item
,
”
th
e
p
r
o
d
u
ct
d
ataset
is
n
am
ed
“p
r
o
d
u
ct_
o
ld
,
”
an
d
th
e
u
s
er
d
ataset
is
r
ef
er
r
ed
to
as “
u
s
er
_
o
ld
.
”
Alth
o
u
g
h
all
th
r
ee
d
atasets
co
n
tain
s
im
ilar
e
-
co
m
m
er
ce
ele
m
en
ts
,
f
o
cu
s
in
g
o
n
tr
an
s
ac
tio
n
s
,
p
r
o
d
u
cts,
an
d
cu
s
to
m
er
s
,
th
ey
d
if
f
er
in
d
ata
o
r
g
an
izatio
n
a
n
d
n
am
in
g
co
n
v
en
tio
n
s
.
“Bra
zilian
_
ec
o
m
m
er
ce
_
a
n
aly
s
es_
v
2
”
h
as
th
e
m
o
s
t
co
m
p
r
eh
en
s
iv
e
s
tr
u
ctu
r
e,
in
clu
d
i
n
g
r
ev
iew
d
ata
an
d
in
teg
r
ated
tr
a
n
s
ac
tio
n
in
f
o
r
m
a
tio
n
.
Ho
wev
e
r
,
s
in
ce
t
h
e
d
atas
ets
u
s
ed
ar
e
n
o
t
id
ea
l
co
m
p
ar
ed
to
t
h
o
s
e
u
til
ized
b
y
r
ea
l
-
wo
r
ld
e
-
co
m
m
er
ce
p
latf
o
r
m
s
,
th
e
au
th
o
r
s
h
a
v
e
a
p
p
lied
s
ev
er
al
m
o
d
if
icatio
n
s
to
e
n
h
an
ce
th
eir
s
u
itab
ilit
y
f
o
r
th
is
s
tu
d
y
.
2
.
2
.
Da
t
a
pre
-
pro
ce
s
s
ing
T
h
e
p
r
o
ce
s
s
b
eg
i
n
s
with
r
aw
d
ata,
wh
ich
is
f
ir
s
t
p
r
ep
r
o
ce
s
s
ed
to
en
s
u
r
e
q
u
ality
an
d
r
ele
v
an
ce
.
T
h
is
p
r
e
-
p
r
o
ce
s
s
in
g
s
tag
e
ty
p
ically
in
clu
d
es
clea
n
in
g
d
ata,
h
an
d
l
in
g
m
is
s
in
g
v
alu
es,
en
co
d
in
g
ca
teg
o
r
ical
v
alu
es,
an
d
s
elec
tin
g
f
ea
tu
r
es.
O
n
ce
p
r
e
-
p
r
o
ce
s
s
ed
,
th
e
d
ata
is
r
ea
d
y
f
o
r
th
e
m
o
d
el
tr
ain
in
g
an
d
e
v
alu
atio
n
p
h
ase.
Fo
r
th
e
p
r
o
ce
s
s
,
th
e
au
t
h
o
r
s
will u
s
e
th
e
f
ir
s
t d
ataset
f
o
r
s
im
u
latio
n
.
2
.
2
.
1
.
H
a
nd
lin
g
m
is
s
ing
v
a
lue
W
e
u
tili
ze
a
two
-
s
tep
p
r
o
c
ess
f
o
r
ad
d
r
ess
in
g
m
is
s
in
g
v
alu
es
s
p
ec
if
ically
with
in
th
e
p
r
o
d
u
ct
d
ataf
r
am
e.
T
h
e
f
ir
s
t
s
tep
in
v
o
lv
es
eli
m
in
atin
g
co
lu
m
n
s
th
at
co
n
tain
NaN
(
m
is
s
in
g
)
o
r
n
u
ll
v
alu
es,
as
d
etailed
in
T
ab
le
1
.
T
h
e
s
ec
o
n
d
s
tep
co
n
s
is
ts
o
f
r
em
o
v
in
g
co
l
u
m
n
s
th
at
ar
e
n
o
t
r
elev
an
t
f
o
r
in
p
u
t
in
to
th
e
m
o
d
el,
as
o
u
tlin
ed
in
T
a
b
le
2
.
T
ab
le
1
.
L
is
t o
f
p
r
o
d
u
cts
d
ataf
r
am
e
co
lu
m
n
s
th
at
m
o
s
tly
co
n
tain
NaN
o
r
n
u
ll
v
alu
es
B
r
a
n
d
N
a
me
A
si
n
Li
st
P
r
i
c
e
Q
u
a
n
t
i
t
y
S
k
u
S
t
o
c
k
P
r
o
d
u
c
t
d
e
t
a
i
l
s
D
i
me
n
si
o
n
C
o
l
o
r
I
n
g
r
e
d
i
e
n
t
s
D
i
r
e
c
t
i
o
n
t
o
u
se
S
i
z
e
q
u
a
n
t
i
t
y
v
a
r
i
a
n
t
P
r
o
d
u
c
t
d
e
scr
i
p
t
i
o
n
T
ab
le
2
.
L
is
t o
f
p
r
o
d
u
cts
d
ataf
r
am
e
co
lu
m
n
s
th
at
h
av
e
n
o
r
el
ev
an
ce
to
th
e
m
o
d
el
V
a
r
i
a
n
t
s
P
r
o
d
u
c
t
u
rl
I
mag
e
I
s Am
a
z
o
n
se
l
l
e
r
2
.
2
.
2
.
Cre
a
t
e
m
a
in t
ra
ns
a
ct
i
o
n da
t
a
f
ra
m
e
a
nd
s
pli
t
pro
ce
s
s
T
h
e
p
r
o
ce
s
s
o
f
u
n
if
icatio
n
i
s
cr
itical
as
it
n
ec
ess
i
tate
s
a
r
ef
er
en
ce
d
ataf
r
am
e
th
at
in
clu
d
es
th
e
co
m
p
lete
tr
an
s
ac
tio
n
h
is
to
r
y
o
f
th
e
s
y
s
tem
.
Dev
elo
p
in
g
a
p
r
im
ar
y
tr
an
s
ac
tio
n
d
ataf
r
am
e
an
d
m
an
a
g
in
g
th
e
s
p
lit
p
r
o
ce
s
s
wi
th
in
a
wo
r
k
f
lo
w
f
o
r
d
ata
m
er
g
in
g
is
a
f
u
n
d
am
en
tal
tech
n
iq
u
e
in
d
ata
p
r
e
-
p
r
o
ce
s
s
in
g
.
T
h
is
ap
p
r
o
a
c
h
is
p
ar
ticu
lar
ly
r
elev
an
t
wh
en
d
ea
lin
g
with
d
atasets
th
at
co
n
tain
tr
an
s
ac
tio
n
al
in
f
o
r
m
atio
n
.
Fig
u
r
e
2
illu
s
tr
ates th
e
u
n
if
icatio
n
p
r
o
c
ess
v
is
u
ally
.
Af
ter
co
n
s
tr
u
ctin
g
th
e
co
m
p
l
ete
tr
an
s
ac
tio
n
d
ataset
in
th
e
f
u
ll_
tr
an
s
ac
tio
n
_
d
f
d
ataf
r
a
m
e
,
th
e
n
e
x
t
s
tep
is
to
d
er
iv
e
th
r
ee
s
p
ec
iali
ze
d
d
ataf
r
am
es
r
atin
g
,
p
r
o
d
u
ct
,
an
d
u
s
er
th
at
ar
e
ess
en
tial
f
o
r
p
r
ep
ar
in
g
th
e
d
ata
f
o
r
m
o
d
el
tr
ain
in
g
.
T
h
ese
d
at
af
r
am
es
ar
e
cr
ea
ted
b
y
s
elec
tiv
ely
ex
tr
ac
tin
g
an
d
tr
a
n
s
f
o
r
m
i
n
g
r
elev
a
n
t
s
u
b
s
ets
o
f
in
f
o
r
m
atio
n
f
r
o
m
th
e
co
m
p
r
eh
en
s
iv
e
tr
a
n
s
ac
tio
n
al
d
ata.
T
h
e
r
atin
g
d
ataf
r
am
e
ty
p
ica
lly
in
clu
d
es
u
s
er
-
p
r
o
d
u
ct
in
ter
ac
tio
n
d
ata,
s
u
ch
as
r
atin
g
s
o
r
p
u
r
ch
as
e
f
r
eq
u
en
c
y
,
s
er
v
in
g
as
a
cr
itical
in
p
u
t
f
o
r
r
ec
o
m
m
en
d
atio
n
al
g
o
r
ith
m
s
.
T
h
e
p
r
o
d
u
ct
d
ata
f
r
am
e
ca
p
tu
r
es
d
etails
ab
o
u
t
in
d
iv
id
u
al
p
r
o
d
u
cts,
in
clu
d
in
g
p
r
o
d
u
ct
I
Ds,
n
am
es,
ca
te
g
o
r
i
es,
an
d
o
th
er
d
escr
ip
tiv
e
attr
i
b
u
tes.
Similar
ly
,
t
h
e
u
s
er
d
at
af
r
am
e
a
g
g
r
e
g
ates
u
s
er
-
r
elate
d
in
f
o
r
m
atio
n
,
s
u
c
h
as
u
s
er
I
Ds
an
d
d
em
o
g
r
a
p
h
ic
o
r
b
e
h
av
io
r
al
f
ea
tu
r
es
wh
en
av
ailab
le.
B
y
o
r
g
an
izin
g
th
e
d
ata
in
to
t
h
e
s
e
d
is
tin
ct
b
u
t
in
ter
r
elate
d
s
tr
u
ctu
r
es,
th
e
m
o
d
elin
g
p
r
o
c
ess
b
ec
o
m
es
m
o
r
e
s
tr
ea
m
lin
ed
an
d
in
ter
p
r
etab
le.
T
h
e
co
m
p
o
s
itio
n
an
d
s
tr
u
ct
u
r
e
o
f
ea
c
h
o
f
th
es
e
d
ata
f
r
a
m
es
ar
e
o
u
tlin
ed
in
T
ab
le
3
,
o
f
f
er
in
g
a
clea
r
o
v
er
v
iew
o
f
th
e
attr
ib
u
tes
in
clu
d
ed
an
d
th
eir
r
esp
ec
tiv
e
r
o
les
in
t
h
e
r
ec
o
m
m
e
n
d
atio
n
s
y
s
tem
p
ip
elin
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
C
o
mb
in
in
g
X
Gb
o
o
s
t a
n
d
h
yb
r
id
filt
erin
g
a
lg
o
r
ith
m
in
E
-
co
mme
r
ce
…
(
V
in
ce
n
tiu
s
Lo
a
n
k
a
S
in
a
g
a
)
621
Fig
u
r
e
2
.
Flo
w
m
er
g
in
g
d
ataf
r
am
e
T
ab
le
3
.
C
o
m
p
o
s
itio
n
o
f
r
atin
g
,
p
r
o
d
u
ct,
a
n
d
u
s
er
d
ataf
r
am
e
f
o
r
m
atio
n
D
a
t
a
f
r
a
m
e
C
o
m
p
o
n
e
n
t
D
a
t
a
Ty
p
e
(
d
a
t
a
f
r
a
me
)
D
f
_
r
a
t
i
n
g
U
ser
ID
I
n
t
3
2
P
r
o
d
u
c
t
ID
I
n
t
3
2
R
e
v
i
e
w
r
a
t
i
n
g
F
l
o
a
t
6
4
D
f
_
u
ser
U
ser
ID
I
n
t
3
2
A
g
e
I
n
t
6
4
G
e
n
d
e
r
I
n
t
3
2
Lo
c
a
t
i
o
n
I
n
t
3
2
D
f
_
P
r
o
d
u
c
t
P
r
o
d
u
c
t
ID
I
n
t
3
2
P
r
o
d
u
c
t
n
a
m
e
O
b
j
e
c
t
2
.
3
.
XG
B
o
o
s
t
XGBo
o
s
t
is
a
s
ca
lab
le
en
d
-
to
-
en
d
tr
ee
[
2
1
]
.
I
n
t
h
is
co
n
tex
t
,
th
e
XGBo
o
s
t
m
o
d
el
p
r
ed
ict
s
a
s
in
g
le
p
r
o
d
u
ct
(
p
r
o
d
u
ct
I
D)
d
ee
m
ed
m
o
s
t
r
elev
an
t
f
o
r
ea
ch
u
s
er
b
ased
o
n
d
em
o
g
r
ap
h
ic
f
ea
tu
r
es.
T
h
is
p
r
ed
ictio
n
s
er
v
e
s
as
th
e
"seed
"
o
r
s
tar
tin
g
p
o
in
t
in
th
e
h
y
b
r
id
r
ec
o
m
m
en
d
atio
n
s
y
s
tem
,
allo
win
g
th
e
r
esu
lts
to
b
e
f
u
r
th
e
r
r
ef
in
ed
u
s
in
g
t
h
e
C
B
F
ap
p
r
o
ac
h
.
T
h
e
o
u
tp
u
t
o
f
th
is
m
o
d
el
co
n
s
is
ts
o
f
a
lis
t
o
f
p
r
ed
icted
p
r
o
d
u
ct
I
Ds,
wh
ich
s
er
v
e
as
in
p
u
t
f
o
r
th
e
f
o
llo
w
in
g
r
ec
o
m
m
en
d
atio
n
s
tag
e.
T
h
e
r
o
le
o
f
XGBo
o
s
t
in
th
is
h
y
b
r
id
m
o
d
el
is
as
f
o
llo
ws
,
i)
Pre
-
p
r
e
d
ictio
n
o
f
p
r
o
d
u
cts:
b
ef
o
r
e
g
en
er
atin
g
f
u
r
th
er
r
ec
o
m
m
en
d
atio
n
s
(
e.
g
.
,
id
en
tify
i
n
g
s
im
ilar
p
r
o
d
u
cts
o
r
esti
m
atin
g
r
atin
g
s
u
s
in
g
C
F),
th
e
s
y
s
tem
aim
s
t
o
d
eter
m
in
e
an
in
itial
p
r
o
d
u
ct
th
at
is
lik
ely
to
b
e
p
r
ef
er
r
e
d
b
y
t
h
e
u
s
er
an
d
ii)
Utilizatio
n
o
f
d
em
o
g
r
ap
h
ic
f
e
atu
r
es:
f
ea
tu
r
es
s
u
ch
as
ag
e,
g
en
d
er
,
an
d
lo
ca
tio
n
o
f
ten
s
er
v
e
as in
itial in
d
icato
r
s
o
f
p
r
o
d
u
ct
p
r
ef
er
e
n
ce
s
.
T
h
e
X
GB
o
o
s
t m
o
d
el
p
r
o
ce
s
s
es th
is
d
ata
an
d
m
a
p
s
it to
a
s
p
ec
if
ic
p
r
o
d
u
ct.
2
.
4
.
Co
nte
nt
-
ba
s
ed
f
ilte
ring
wit
h
TF
-
I
DF
a
nd
co
s
i
ne
s
im
i
la
rit
y
I
n
th
is
r
esear
ch
,
CBF
will
em
p
lo
y
T
F
-
I
DF
an
d
co
s
in
e
s
im
ilar
ity
.
T
F
-
I
DF
co
n
v
er
ts
p
r
o
d
u
c
t
tex
t
d
ata
in
to
n
u
m
er
ical
v
ec
to
r
s
b
y
ca
l
cu
latin
g
th
e
p
r
o
d
u
ct
o
f
ter
m
f
r
eq
u
en
c
y
an
d
in
v
e
r
s
e
d
o
c
u
m
e
n
t
f
r
eq
u
en
cy
[
2
2
]
.
C
o
s
in
e
s
im
ilar
ity
th
en
q
u
an
tifie
s
th
e
an
g
u
lar
d
is
tan
ce
b
etwe
en
th
ese
v
ec
to
r
s
,
r
ef
lectin
g
h
o
w
clo
s
ely
r
elate
d
two
p
r
o
d
u
cts
ar
e
[
2
3
]
.
T
h
e
in
it
ial
s
tep
in
v
o
lv
es
u
tili
zin
g
T
f
id
f
Vec
to
r
izer
to
tr
an
s
f
o
r
m
tex
t d
ata
in
to
n
u
m
er
ical
v
ec
to
r
r
ep
r
esen
tatio
n
s
.
A
f
ter
o
b
tain
in
g
th
e
T
F
-
I
DF
r
ep
r
es
en
tatio
n
s
f
o
r
ea
ch
p
r
o
d
u
ct,
we
co
m
p
u
te
co
s
in
e
s
im
ilar
ity
to
ass
e
s
s
p
r
o
d
u
ct
s
im
ilar
ity
.
Af
ter
estab
lis
h
in
g
th
e
s
im
ilar
ity
m
atr
ix
,
we
p
r
o
ce
ed
to
id
en
tif
y
p
r
o
d
u
cts th
at
ar
e
s
im
ilar
to
a
r
ef
er
en
ce
p
r
o
d
u
ct,
wh
ich
is
th
e
p
r
o
d
u
ct
th
at
XGBo
o
s
t p
r
ed
icts
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
14
,
No
.
2
,
J
u
n
e
2
0
2
5
:
6
1
8
-
626
622
2
.
5
.
Co
lla
bo
r
a
t
iv
e
f
ilte
ring
us
ing
SV
D
(
s
urpri
s
e
)
C
F in
th
is
s
tu
d
y
is
im
p
lem
en
te
d
v
ia
SVD
,
a
m
atr
ix
f
ac
to
r
izatio
n
tech
n
iq
u
e
th
at
d
ec
o
m
p
o
s
e
s
th
e
u
s
er
-
item
r
atin
g
m
atr
ix
in
t
o
laten
t
f
ac
to
r
s
[
2
4
]
.
On
ce
th
e
SVD
m
o
d
el
is
tr
ain
ed
,
it
p
r
ed
icts
r
a
tin
g
s
f
o
r
e
ac
h
(
u
s
er
,
p
r
o
d
u
ct)
p
air
.
I
f
a
u
s
er
is
k
n
o
wn
(
p
r
esen
t
in
th
e
tr
ain
in
g
d
a
ta)
,
th
e
s
y
s
tem
ap
p
lies
th
e
p
r
ed
icted
r
atin
g
s
;
f
o
r
co
ld
s
tar
t scen
ar
io
s
(
n
ew
u
s
er
s
)
,
it r
etu
r
n
s
to
r
ec
o
m
m
e
n
d
in
g
p
o
p
u
lar
p
r
o
d
u
cts.
2
.
6
.
H
y
brid
m
o
del
HFA
i
s
a
r
ec
o
m
m
en
d
atio
n
s
y
s
tem
th
at
in
teg
r
ates
two
o
r
m
o
r
e
ap
p
r
o
ac
h
es
(
C
B
F
an
d
C
F
in
th
i
s
s
tu
d
y
)
to
lev
er
a
g
e
th
e
s
tr
en
g
t
h
s
o
f
ea
ch
m
eth
o
d
wh
ile
m
it
ig
atin
g
th
e
lim
itatio
n
s
o
f
in
d
iv
id
u
al
tech
n
iq
u
es.
B
ased
o
n
Fig
u
r
e
1
,
th
e
p
r
o
p
o
s
ed
h
y
b
r
id
s
y
s
tem
co
n
s
is
ts
o
f
th
r
e
e
m
ain
co
m
p
o
n
e
n
ts
,
i)
XGBo
o
s
t
a
s
p
r
e
-
p
r
ed
ictio
n
o
f
p
r
o
d
u
cts:
t
h
e
XGBo
o
s
t
m
o
d
el
g
en
e
r
ates
a
n
in
itial
p
r
e
d
ictio
n
,
id
en
tify
i
n
g
th
e
m
o
s
t
r
ele
v
an
t
p
r
o
d
u
ct
b
ased
o
n
u
s
er
f
e
atu
r
es
s
u
ch
as
ag
e,
g
e
n
d
er
,
an
d
lo
ca
tio
n
.
T
h
is
c
o
m
p
o
n
en
t
p
r
o
d
u
ce
s
an
i
n
itial
r
ec
o
m
m
en
d
atio
n
,
ac
tin
g
as
a
“seed
”
f
o
r
f
in
d
in
g
s
im
ilar
i
tem
s
;
ii)
C
B
F
:
o
n
ce
XGBo
o
s
t
h
as
id
en
tifie
d
a
p
r
o
d
u
ct,
C
B
F
is
u
s
ed
t
o
f
i
n
d
s
im
ilar
p
r
o
d
u
cts
to
th
e
p
r
e
d
icted
item
.
T
h
is
a
p
p
r
o
a
ch
e
m
p
lo
y
s
T
F
-
I
DF
to
co
n
v
er
t
p
r
o
d
u
ct
d
escr
ip
tio
n
s
o
r
n
am
es
in
to
n
u
m
e
r
ical
v
ec
to
r
r
ep
r
esen
tatio
n
s
an
d
co
s
in
e
s
im
ilar
ity
to
m
ea
s
u
r
e
th
e
d
eg
r
ee
o
f
s
im
ilar
ity
b
etwe
en
p
r
o
d
u
cts.
T
h
e
C
B
F
co
m
p
o
n
en
t
r
et
u
r
n
s
a
lis
t
o
f
p
r
o
d
u
cts
th
at
s
h
ar
e
c
o
n
ten
t
-
b
ased
s
im
ilar
ities
with
th
e
i
n
itial
p
r
o
d
u
ct
an
d
th
eir
r
esp
ec
tiv
e
s
im
ilar
ity
s
co
r
es
;
an
d
iii)
CF
:
th
e
C
F
co
m
p
o
n
en
t
u
tili
ze
s
th
e
SVD
m
o
d
el
f
r
o
m
th
e
s
u
r
p
r
is
e
lib
r
ar
y
to
p
r
ed
ict
u
s
er
r
atin
g
s
f
o
r
ea
ch
p
r
o
d
u
ct
.
I
f
a
u
s
er
h
as
an
in
ter
ac
tio
n
h
is
to
r
y
(
e
.
g
.
,
r
atin
g
s
o
r
p
ast
p
u
r
ch
ases
)
,
C
F
esti
m
ate
s
th
e
lik
elih
o
o
d
o
f
th
e
u
s
er
p
r
ef
er
r
in
g
ce
r
tain
p
r
o
d
u
cts.
I
f
t
h
e
u
s
er
i
s
n
ew
an
d
d
o
es
n
o
t
ex
is
t
in
t
h
e
tr
ain
in
g
d
ata
(
co
l
d
s
tar
t
s
c
en
ar
io
)
,
th
e
s
y
s
tem
ap
p
lies
a
f
allb
ac
k
s
tr
ateg
y
,
r
ec
o
m
m
en
d
i
n
g
p
o
p
u
lar
p
r
o
d
u
ct
s
.
T
h
is
en
s
u
r
es
th
e
g
en
er
atio
n
o
f
p
r
ed
icted
r
atin
g
s
(
p
r
ef
er
e
n
ce
s
co
r
es)
f
o
r
ea
ch
p
r
o
d
u
ct,
f
r
o
m
wh
ic
h
th
e
h
ig
h
est
-
s
co
r
in
g
p
r
o
d
u
cts ar
e
s
elec
ted
.
Af
ter
g
ettin
g
th
e
o
u
tp
u
t
f
r
o
m
ea
ch
o
f
th
e
a
b
o
v
e
co
m
p
o
n
e
n
t
s
,
th
e
n
ex
t
s
tep
is
to
c
o
m
b
in
e
th
e
s
co
r
es
f
r
o
m
C
B
F a
n
d
C
F.
T
h
is
is
d
o
n
e
u
s
in
g
th
e
weig
h
te
d
co
m
b
in
at
io
n
f
o
r
m
u
la
as in
(
1
)
.
_
=
(
∗
0
.
5
)
+
(
∗
0
.
5
)
2
(
1
)
W
h
er
e
α
is
C
F sco
r
e
an
d
β
is
C
B
F sco
r
e
.
2
.
7
.
E
v
a
lua
t
i
o
n
On
e
o
f
th
e
ev
alu
atio
n
m
et
h
o
d
s
u
s
ed
in
th
is
s
tu
d
y
is
th
e
HR
.
HR
is
a
m
etr
ic
u
s
ed
to
ev
alu
ate
th
e
p
er
f
o
r
m
an
ce
o
f
a
r
e
co
m
m
e
n
d
atio
n
s
y
s
tem
b
y
m
ea
s
u
r
in
g
h
o
w
o
f
ten
t
h
e
m
o
d
el
p
r
ed
ict
s
p
r
o
d
u
cts
th
at
a
r
e
r
elev
an
t to
th
e
u
s
er
[
2
5
]
.
T
h
e
ca
lcu
latio
n
f
o
r
m
u
la
f
o
r
HR
ca
n
b
e
s
ee
n
in
(
2
)
.
=
(
2
)
W
h
er
e
HR
is
th
e
h
it
r
atio
,
t
is
th
e
n
u
m
b
er
o
f
co
r
r
ec
t p
r
ed
icti
o
n
s
,
an
d
n
is
th
e
to
tal
n
u
m
b
er
o
f
u
s
er
in
ter
ac
tio
n
s
.
In
ad
d
itio
n
t
o
u
s
in
g
th
e
HR
ev
alu
atio
n
m
eth
o
d
,
th
e
s
tu
d
y
wil
l
u
s
e
th
e
ac
c
u
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
ev
alu
atio
n
m
eth
o
d
s
.
T
h
is
m
eth
o
d
f
u
n
ctio
n
s
to
e
v
alu
ate
th
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
r
ec
o
m
m
en
d
atio
n
s
y
s
tem
b
y
ass
ess
in
g
h
o
w
ac
cu
r
ately
th
e
m
o
d
el
p
r
ed
icts
p
r
o
d
u
cts
th
at
in
ter
ac
t
with
u
s
er
s
[
2
6
]
.
T
h
e
ca
lcu
latio
n
f
o
r
m
u
la
f
o
r
e
v
alu
atin
g
ac
c
u
r
a
cy
,
as in
(
3
)
,
p
r
e
cisi
o
n
,
as in
(
4
)
,
r
ec
all
,
as in
(
5
)
,
a
n
d
F1
-
s
co
r
e
,
as in
(
6
)
.
=
+
+
+
+
(
3
)
=
+
(
4
)
=
+
(
5
)
1
−
=
2
×
×
+
(
6
)
W
h
er
e
AC
is
ac
cu
r
ac
y
,
PC
S
is
p
r
ec
is
io
n
,
RC
is
r
ec
all
,
F1
-
s
co
r
e
is
F1
-
s
co
r
e
,
TP
is
tr
u
e
p
o
s
itiv
e
,
TN
is
tr
u
e
n
eg
ativ
e
,
FP
is
f
alse p
o
s
itiv
e
,
an
d
FN
is
f
alse n
eg
ativ
e
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
E
v
a
lua
t
i
o
n ba
s
ed
o
n
co
ld s
t
a
rt
s
ce
na
rio
T
o
ev
alu
ate
th
e
m
o
d
el'
s
ca
p
ab
ilit
y
in
h
a
n
d
lin
g
co
ld
s
tar
t
ca
s
es,
p
ar
ticu
lar
ly
th
e
u
s
er
co
ld
s
tar
t
s
ce
n
ar
io
,
th
e
au
th
o
r
s
co
n
d
u
cte
d
an
ex
p
er
im
e
n
t in
wh
ich
th
e
m
o
d
el
was r
eq
u
ir
ed
to
g
en
er
at
e
r
ec
o
m
m
en
d
atio
n
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
C
o
mb
in
in
g
X
Gb
o
o
s
t a
n
d
h
yb
r
id
filt
erin
g
a
lg
o
r
ith
m
in
E
-
co
mme
r
ce
…
(
V
in
ce
n
tiu
s
Lo
a
n
k
a
S
in
a
g
a
)
623
f
o
r
n
ew
u
s
er
s
.
T
h
is
ca
s
e
was
ac
h
iev
ed
b
y
is
o
latin
g
a
s
u
b
s
et
o
f
u
s
er
s
an
d
all
th
eir
ass
o
ciat
ed
tr
an
s
ac
tio
n
s
.
T
h
e
r
esu
lts
o
f
th
e
m
o
d
el
ev
alu
atio
n
ar
e
as f
o
llo
ws
.
R
ev
iewin
g
T
ab
le
4
,
in
h
an
d
li
n
g
u
s
er
co
ld
s
tar
t
ca
s
es,
th
e
HFA
m
o
d
el
o
u
tp
er
f
o
r
m
s
in
al
l
ev
alu
atio
n
m
etr
ics.
R
eg
ar
d
in
g
ac
cu
r
ac
y
,
HFA
d
em
o
n
s
tr
ates
a
9
%
im
p
r
o
v
em
en
t
(
4
0
%
f
o
r
XGBo
o
s
t
v
s
.
4
9
%
f
o
r
HFA)
,
in
d
icatin
g
th
at
HFA
is
m
o
r
e
ac
cu
r
ate
in
p
r
e
d
ictin
g
r
ec
o
m
m
en
d
atio
n
s
f
o
r
n
ew
u
s
er
s
.
R
eg
ar
d
in
g
p
r
e
cisi
o
n
,
HFA
ac
h
iev
es
1
0
0
%,
as
th
e
HFA
m
eth
o
d
ten
d
s
to
b
e
h
ig
h
ly
s
elec
tiv
e
in
co
ld
s
tar
t
s
ce
n
ar
io
s
,
em
p
h
asizin
g
C
B
F
an
d
/o
r
C
F
to
m
i
n
im
ize
n
o
is
e.
Fro
m
a
r
ec
all
p
e
r
s
p
ec
tiv
e,
HFA
is
m
o
r
e
e
f
f
ec
tiv
e
in
id
en
tify
in
g
r
elev
an
t
p
r
o
d
u
cts.
Desp
ite
th
e
lim
ited
in
ter
ac
tio
n
d
ata
f
o
r
n
ew
u
s
er
s
,
HFA
b
en
ef
its
f
r
o
m
C
B
F
an
d
/o
r
C
F,
wh
ich
in
cr
ea
s
es
th
e
lik
elih
o
o
d
o
f
f
i
n
d
in
g
r
elev
an
t
p
r
o
d
u
cts.
Un
lik
e
XGBo
o
s
t,
wh
ich
r
elies
s
o
le
ly
o
n
d
em
o
g
r
ap
h
ic
d
ata,
th
e
XGBo
o
s
t
-
C
B
F a
n
d
/o
r
C
F a
p
p
r
o
ac
h
e
n
h
an
ce
s
th
e
p
r
o
b
ab
ilit
y
o
f
id
en
tify
i
n
g
r
ele
v
a
n
t item
s
.
T
ab
le
4
.
XGBo
o
s
t a
n
d
HFA
c
o
m
p
ar
is
o
n
b
y
ac
c
u
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all
,
F1
-
s
co
r
e,
an
d
HR
b
ased
o
n
c
o
ld
s
tar
t
p
r
o
b
lem
X
G
B
o
o
st
(
%)
H
F
A
(
%)
A
c
c
u
r
a
c
y
40
49
P
r
e
c
i
s
i
o
n
45
1
0
0
R
e
c
a
l
l
40
49
F1
-
s
c
o
r
e
42
65
HR
2
5
.
2
5
2
9
.
2
5
T
h
e
F1
-
s
co
r
e
an
aly
s
is
in
d
icate
s
a
b
etter
b
alan
ce
b
etwe
en
p
r
e
cisi
o
n
(
1
0
0
%)
an
d
r
ec
all
(
4
9
%
)
in
HFA,
co
m
p
ar
ed
to
XGBo
o
s
t,
wh
ich
h
as
p
r
ec
is
io
n
(
4
7
%)
an
d
r
e
ca
ll
(
4
2
%).
Ho
wev
er
,
it
is
im
p
o
r
tan
t
to
n
o
te
th
at
wh
ile
h
ig
h
p
r
ec
is
io
n
(
1
0
0
%)
en
s
u
r
es
h
ig
h
ly
co
n
f
i
d
en
t
r
ec
o
m
m
en
d
atio
n
s
,
th
e
lo
w
r
ec
all
(
4
9
%)
s
u
g
g
ests
th
at
th
e
m
o
d
el
is
o
v
er
ly
c
o
n
s
er
v
a
tiv
e,
f
o
cu
s
in
g
o
n
ly
o
n
th
e
m
o
s
t
ce
r
tain
r
ec
o
m
m
e
n
d
atio
n
s
wh
ile
o
v
er
lo
o
k
in
g
s
o
m
e
r
elev
an
t
o
n
es.
T
h
e
HR
also
alig
n
s
with
t
h
e
o
v
er
all
p
er
f
o
r
m
an
ce
im
p
r
o
v
em
en
t,
as
r
ec
o
m
m
e
n
d
ati
o
n
s
g
en
er
ated
b
y
HFA
m
o
r
e
f
r
eq
u
en
tly
m
atch
th
e
ac
t
u
al
u
s
er
p
r
e
f
er
en
ce
s
,
ev
en
with
lim
ited
u
s
er
d
ata.
3
.
2
.
E
v
a
lua
t
i
o
n ba
s
ed
o
n m
o
del a
da
pta
bil
it
y
A
d
etailed
co
m
p
ar
is
o
n
o
f
th
e
XGBo
o
s
t
an
d
HFA
m
eth
o
d
s
i
s
s
h
o
wn
in
T
ab
les
5
an
d
6
,
h
i
g
h
lig
h
tin
g
h
o
w
well
th
ey
p
er
f
o
r
m
o
n
th
r
ee
d
if
f
er
e
n
t
e
-
co
m
m
e
r
ce
d
at
asets
:
e
-
co
m
m
er
ce
s
ales
d
ata
2023
–
2
4
,
B
r
az
il
e
-
co
m
m
er
ce
a
n
aly
s
is
v
2
,
a
n
d
E
co
m
m
er
ce
_
b
ig
Qu
er
y
.
T
h
ese
d
atasets
wer
e
ch
o
s
en
to
r
e
p
r
es
en
t
v
ar
io
u
s
m
ar
k
et
co
n
tex
ts
an
d
d
ata
ch
ar
ac
te
r
is
tics
,
f
ac
ilit
atin
g
a
th
o
r
o
u
g
h
ev
alu
atio
n
o
f
th
e
m
o
d
el
's
ef
f
ec
tiv
en
ess
.
T
h
e
co
m
p
ar
is
o
n
em
p
h
asizes
s
ev
er
al
k
ey
p
er
f
o
r
m
a
n
ce
m
etr
ics
co
m
m
o
n
ly
u
tili
ze
d
i
n
class
if
icatio
n
an
d
r
ec
o
m
m
en
d
atio
n
task
s
,
in
cl
u
d
in
g
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
F1
-
s
co
r
e,
a
n
d
av
er
ag
e
HR
.
Acc
u
r
ac
y
m
ea
s
u
r
es
th
e
o
v
er
all
co
r
r
ec
t
n
ess
o
f
th
e
m
o
d
el’
s
p
r
ed
ictio
n
s
,
w
h
ile
p
r
ec
is
io
n
an
d
r
ec
all
o
f
f
er
in
f
o
r
m
atio
n
ab
o
u
t
th
e
m
o
d
el’
s
ab
ilit
y
to
ac
cu
r
atel
y
id
en
tify
r
ele
v
an
t
in
s
tan
ce
s
an
d
r
etr
iev
e
all
p
o
ten
tial
r
elev
an
t
r
esu
lts
,
r
esp
ec
tiv
ely
.
T
h
e
F1
-
s
co
r
e,
wh
ich
is
th
e
h
ar
m
o
n
ic
m
ea
n
o
f
p
r
ec
is
io
n
an
d
r
e
ca
ll,
p
r
o
v
id
es
a
b
alan
ce
d
p
er
s
p
ec
tiv
e
o
n
b
o
t
h
m
etr
ics.
L
astl
y
,
th
e
av
er
a
g
e
HR
ass
ess
es
th
e
s
u
cc
ess
r
ate
o
f
th
e
r
ec
o
m
m
e
n
d
atio
n
co
m
p
o
n
en
t,
in
d
icatin
g
h
o
w
f
r
eq
u
en
tly
th
e
r
ec
o
m
m
en
d
e
d
ite
m
s
alig
n
with
ac
tu
al
u
s
er
in
te
r
ac
tio
n
s
.
B
y
lo
o
k
in
g
at
th
ese
m
etr
ics
to
g
e
th
er
,
th
e
tab
les
p
r
o
v
id
e
a
s
tr
aig
h
tf
o
r
wa
r
d
way
to
c
o
m
p
a
r
e
th
e
s
tr
en
g
t
h
s
an
d
wea
k
n
ess
es
o
f
th
e
XGBo
o
s
t a
n
d
HFA
m
et
h
o
d
s
in
d
if
f
er
en
t e
-
co
m
m
e
r
ce
d
ata
s
itu
atio
n
s
.
T
h
e
HFA
m
eth
o
d
co
n
s
is
ten
tly
d
o
es
b
etter
th
an
XGBo
o
s
t
in
all
th
r
ee
d
atasets
e
-
co
m
m
er
ce
s
ales
d
at
a
2
023
–
2
4
,
B
r
az
il
e
-
co
m
m
er
ce
an
aly
s
is
v
2
,
an
d
E
co
m
m
er
ce
_
b
ig
Qu
er
y
esp
ec
ially
in
ter
m
s
o
f
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
a
n
d
a
v
er
ag
e
HR
.
A
m
o
n
g
th
ese
m
etr
ics,
p
r
ec
is
io
n
d
em
o
n
s
tr
ates
th
e
m
o
s
t
s
ig
n
if
i
ca
n
t
an
d
co
n
s
is
ten
t
en
h
an
ce
m
e
n
t,
with
HFA
s
u
r
p
ass
in
g
XGBo
o
s
t
in
ev
e
r
y
d
at
aset.
Alth
o
u
g
h
th
e
r
ec
all
an
d
ac
cu
r
ac
y
m
ay
s
ee
s
lig
h
t
in
cr
ea
s
es,
r
em
ain
s
tab
le
,
o
r
ex
p
er
ien
ce
m
ar
g
in
al
d
ec
lin
es
d
ep
en
d
in
g
o
n
th
e
d
ataset,
th
ese
f
lu
ctu
atio
n
s
ar
e
m
in
o
r
co
m
p
a
r
ed
to
th
e
co
n
s
is
ten
tly
elev
ated
p
r
ec
is
io
n
a
ch
iev
ed
b
y
HFA.
C
o
n
s
eq
u
en
t
ly
,
th
e
F1
-
s
co
r
e
is
g
en
er
ally
h
ig
h
er
f
o
r
HFA
d
u
e
to
its
s
tr
o
n
g
p
r
ec
is
io
n
co
m
p
o
n
en
t.
T
h
e
av
er
ag
e
h
it
r
atio
also
s
ee
s
im
p
r
o
v
em
e
n
ts
with
HFA,
alth
o
u
g
h
th
e
e
x
ten
t
o
f
th
is
im
p
r
o
v
em
en
t
v
ar
ies
b
y
d
ataset.
I
n
th
e
E
co
m
m
er
ce
_
b
ig
Qu
er
y
d
ataset,
HFA
s
h
o
ws a
s
lig
h
tly
lo
wer
ac
cu
r
ac
y
o
f
2
1
% c
o
m
p
ar
e
d
to
XGBo
o
s
t
'
s
2
2
%.
Acr
o
s
s
all
d
atasets
,
HFA
ac
h
iev
es
an
im
p
r
ess
iv
e
p
r
e
cisi
o
n
r
an
g
e
o
f
9
2
–
9
8
%,
s
ig
n
if
y
in
g
its
ca
p
ab
ilit
y
to
g
e
n
er
ate
m
o
r
e
a
cc
u
r
ate
an
d
ta
r
g
eted
r
ec
o
m
m
en
d
atio
n
s
wh
ile
m
in
im
izin
g
f
alse
p
o
s
itiv
es.
T
h
is
p
er
f
o
r
m
an
ce
in
d
icate
s
t
h
at
H
FA,
wh
ich
co
m
b
i
n
es
XGBo
o
s
t
with
co
n
ten
t
-
b
ased
a
n
d
c
o
l
lab
o
r
ativ
e
f
ilter
in
g
tech
n
iq
u
es,
im
p
lem
en
ts
a
m
o
r
e
s
tr
in
g
en
t
s
elec
tio
n
p
r
o
ce
s
s
wh
en
r
ec
o
m
m
e
n
d
in
g
item
s
.
W
h
ile
th
is
ap
p
r
o
ac
h
d
ec
r
ea
s
es
th
e
n
u
m
b
er
o
f
in
c
o
r
r
ec
t
p
r
e
d
ictio
n
s
,
it
also
cr
ea
t
es
a
n
o
ticea
b
l
e
d
is
p
ar
ity
b
et
wee
n
p
r
ec
is
io
n
a
n
d
r
ec
all,
s
u
g
g
esti
n
g
th
at
s
o
m
e
r
elev
an
t
item
s
m
ay
n
o
t
b
e
in
cl
u
d
ed
.
T
h
is
tr
ad
e
-
o
f
f
u
n
d
er
s
co
r
es
HFA’
s
f
o
cu
s
o
n
d
eliv
er
in
g
h
i
g
h
-
q
u
ality
r
ec
o
m
m
en
d
atio
n
s
o
v
er
m
ax
im
izi
n
g
co
v
e
r
ag
e,
m
a
k
in
g
it
p
ar
ti
cu
lar
ly
ef
f
ec
tiv
e
in
s
ce
n
ar
io
s
wh
e
r
e
r
elev
an
ce
an
d
u
s
er
s
atis
f
ac
tio
n
ar
e
p
ar
am
o
u
n
t.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
14
,
No
.
2
,
J
u
n
e
2
0
2
5
:
6
1
8
-
626
624
T
ab
le
5
.
XGBo
o
s
t
test
r
esu
lts
with
d
if
f
er
en
t
d
atasets
D
a
t
a
s
e
t
A
c
c
u
r
a
c
y
(
%)
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
F
1
-
s
c
o
r
e
(
%)
A
v
e
r
a
g
e
HR
(
%)
E
-
c
o
mm
e
r
c
e
sa
l
e
s
d
a
t
a
2
0
2
3
-
24
32
47
32
38
2
7
.
5
B
r
a
z
i
l
i
a
n
_
e
c
o
mm
e
r
c
e
_
a
n
a
l
y
s
e
s
_
v
2
26
74
23
31
2
4
.
6
Ec
o
m
merc
e
_
b
i
g
Q
u
e
r
y
d
a
t
a
se
t
22
78
22
29
2
4
.
2
T
ab
le
6
.
HFA
test
r
esu
lts
with
d
if
f
er
en
t
d
atasets
D
a
t
a
s
e
t
A
c
c
u
r
a
c
y
(
%)
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
F
1
-
s
c
o
r
e
(
%)
A
v
e
r
a
g
e
HR
(
%)
E
-
c
o
mm
e
r
c
e
sa
l
e
s
d
a
t
a
2
0
2
3
-
24
33
92
33
46
3
4
.
4
B
r
a
z
i
l
i
a
n
_
e
c
o
mm
e
r
c
e
_
a
n
a
l
y
s
e
s
_
v
2
26
94
25
36
3
2
.
4
Ec
o
m
merc
e
_
b
i
g
Q
u
e
r
y
d
a
t
a
se
t
21
98
21
32
2
6
.
5
4.
CO
NCLU
SI
O
N
T
h
e
HFA
-
in
teg
r
atin
g
XGBo
o
s
t,
C
B
F,
an
d
C
F
co
n
s
is
ten
tly
o
u
tp
er
f
o
r
m
s
tan
d
al
o
n
e
XGBo
o
s
t
ac
r
o
s
s
v
ar
io
u
s
ev
al
u
atio
n
m
et
r
ics.
B
y
co
m
b
in
in
g
co
n
ten
t
s
im
ilar
ity
with
u
s
er
p
r
ef
e
r
en
ce
d
ata,
H
FA
ac
h
iev
es
h
ig
h
er
p
r
ec
is
io
n
,
a
b
etter
F1
-
s
co
r
e,
an
d
an
im
p
r
o
v
e
d
HR
in
b
o
th
g
en
er
al
an
d
c
o
ld
s
tar
t
s
ce
n
ar
io
s
.
T
h
is
ap
p
r
o
ac
h
ad
ap
ts
well
to
d
if
f
er
en
t
d
atasets
,
p
r
o
v
id
in
g
m
o
r
e
s
tab
le
an
d
r
elev
an
t
r
ec
o
m
m
en
d
atio
n
s
,
alth
o
u
g
h
th
er
e
r
em
ain
s
a
n
ee
d
to
e
n
h
an
ce
r
ec
all
an
d
s
ca
lab
ilit
y
f
o
r
lar
g
e
d
atasets
f
u
r
th
e
r
.
Ov
e
r
all
,
HFA’
s
p
er
f
o
r
m
a
n
ce
ad
v
an
tag
es
m
a
k
e
it
a
m
o
r
e
r
el
iab
le
ch
o
ice
f
o
r
c
o
m
p
lex
r
ec
o
m
m
en
d
atio
n
s
y
s
tem
s
th
an
XGBo
o
s
t,
wh
ich
r
elies
he
av
ily
o
n
s
tatic
f
ea
t
u
r
es
a
n
d
e
x
h
ib
its
less
s
tab
le
p
er
f
o
r
m
an
ce
.
W
ith
ad
d
itio
n
al
r
e
f
in
em
en
ts
aim
ed
at
im
p
r
o
v
in
g
r
ec
all
an
d
o
p
tim
izi
n
g
co
ld
s
tar
t
h
a
n
d
lin
g
,
HFA
h
as
th
e
p
o
ten
tial
to
ev
o
lv
e
in
t
o
a
r
o
b
u
s
t
s
o
lu
tio
n
th
at
ef
f
ec
tiv
ely
ca
p
italizes
o
n
th
e
s
tr
en
g
th
s
o
f
b
o
th
co
n
te
n
t
-
b
ased
an
d
CF
.
Nex
t
,
r
esea
r
ch
er
s
ca
n
ex
p
lo
r
e
tr
an
s
itio
n
in
g
f
r
o
m
tr
ad
itio
n
al
C
F
to
n
eu
r
al
co
llab
o
r
ativ
e
f
ilter
in
g
(
NC
F),
wh
ich
u
s
es
s
p
ec
ialized
em
b
ed
d
in
g
s
f
o
r
u
s
er
-
p
r
o
d
u
ct
in
ter
ac
tio
n
s
an
d
n
eu
r
al
n
etwo
r
k
s
f
o
r
m
o
r
e
ac
cu
r
ate
p
r
e
d
ictio
n
s
.
C
B
F
ca
n
also
b
en
ef
it
f
r
o
m
ad
v
an
ce
d
lan
g
u
ag
e
m
o
d
els
lik
e
b
id
ir
ec
tio
n
al
en
co
d
er
r
ep
r
esen
tatio
n
s
f
r
o
m
tr
an
s
f
o
r
m
er
s
(
B
E
R
T
)
o
r
o
th
er
tr
an
s
f
o
r
m
er
-
b
ased
ap
p
r
o
ac
h
es to
ca
p
tu
r
e
d
ee
p
er
c
o
n
tex
tu
al
a
n
d
s
em
an
tic
n
u
a
n
ce
s
in
p
r
o
d
u
ct
d
escr
ip
tio
n
s
.
ACK
NO
WL
E
DG
E
M
E
NT
S
Au
th
o
r
s
wo
u
ld
lik
e
to
th
an
k
B
in
a
Nu
s
an
tar
a
Un
iv
er
s
ity
f
o
r
p
r
o
v
id
in
g
s
u
p
p
o
r
t f
o
r
th
is
r
esear
ch
.
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
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
Vin
ce
n
tiu
s
L
o
an
k
a
Sin
ag
a
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
An
to
n
i Wi
b
o
wo
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
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
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
C
o
mb
in
in
g
X
Gb
o
o
s
t a
n
d
h
yb
r
id
filt
erin
g
a
lg
o
r
ith
m
in
E
-
co
mme
r
ce
…
(
V
in
ce
n
tiu
s
Lo
a
n
k
a
S
in
a
g
a
)
625
E
T
H
I
CAL AP
P
RO
V
AL
T
h
e
r
esear
ch
r
elate
d
to
h
u
m
a
n
u
s
e
h
as
b
ee
n
co
m
p
lie
d
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
in
ac
co
r
d
an
ce
with
th
e
te
n
ets
o
f
t
h
e
He
ls
in
k
i
Dec
lar
atio
n
an
d
h
as
b
ee
n
ap
p
r
o
v
e
d
b
y
th
e
au
th
o
r
s
'
in
s
titu
tio
n
al
r
ev
iew
b
o
ar
d
o
r
eq
u
i
v
alen
t c
o
m
m
ittee
.
DATA AV
AI
L
AB
I
L
I
T
Y
All d
ata
u
s
ed
in
th
is
s
tu
d
y
ar
e
p
u
b
lic
d
atasets
.
RE
F
E
R
E
NC
E
S
[
1
]
M
.
K
ü
t
z
,
I
n
t
r
o
d
u
c
t
i
o
n
t
o
E
-
c
o
m
m
e
r
c
e
:
c
o
m
b
i
n
i
n
g
b
u
s
i
n
e
ss
a
n
d
i
n
f
o
rm
a
t
i
o
n
t
e
c
h
n
o
l
o
g
y
,
B
o
o
k
b
o
o
n
,
2
0
1
6
.
[
2
]
V
.
Jai
n
,
B
.
M
a
l
v
i
y
a
,
a
n
d
S
.
A
r
y
a
,
“
A
n
o
v
e
r
v
i
e
w
o
f
e
l
e
c
t
r
o
n
i
c
c
o
mm
e
r
c
e
(
e
-
c
o
mm
e
r
c
e
)
,
”
J
o
u
r
n
a
l
o
f
C
o
n
t
e
m
p
o
r
a
ry
I
ss
u
e
s
i
n
Bu
si
n
e
ss
a
n
d
G
o
v
e
rn
m
e
n
t
,
v
o
l
.
2
7
,
n
o
.
3
,
2
0
2
1
,
d
o
i
:
1
0
.
4
7
7
5
0
/
c
i
b
g
.
2
0
2
1
.
2
7
.
0
3
.
0
9
0
.
[
3
]
F
.
T
.
A
.
H
u
ss
i
e
n
,
A
.
M
.
S
.
R
a
h
m
a
,
a
n
d
H
.
B
.
A
.
W
a
h
a
b
,
“
R
e
c
o
mm
e
n
d
a
t
i
o
n
s
y
st
e
ms
f
o
r
e
-
c
o
mm
e
r
c
e
s
y
st
e
m
s
a
n
o
v
e
r
v
i
e
w
,
”
J
o
u
rn
a
l
o
f
Ph
y
si
c
s:
C
o
n
f
e
re
n
c
e
S
e
ri
e
s
,
v
o
l
.
1
8
9
7
,
n
o
.
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
2
-
6
5
9
6
/
1
8
9
7
/
1
/
0
1
2
0
2
4
.
[
4
]
L.
L
ü
,
M
.
M
e
d
o
,
C
.
H
.
Y
e
u
n
g
,
Y
.
C
.
Z
h
a
n
g
,
Z.
K
.
Zh
a
n
g
,
a
n
d
T.
Z
h
o
u
,
“
R
e
c
o
mm
e
n
d
e
r
s
y
st
e
ms,
”
Ph
y
si
c
s
Re
p
o
r
t
s
,
v
o
l
.
5
1
9
,
n
o
.
1
,
p
p
.
1
–
4
9
,
2
0
1
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
h
y
sr
e
p
.
2
0
1
2
.
0
2
.
0
0
6
.
[
5
]
A
.
N
u
r
c
a
h
y
a
a
n
d
S
.
S
u
p
r
i
y
a
n
t
o
,
“
C
o
n
t
e
n
t
-
b
a
s
e
d
r
e
c
o
mm
e
n
d
e
r
sy
s
t
e
m
a
r
c
h
i
t
e
c
t
u
r
e
f
o
r
s
i
mi
l
a
r
e
-
c
o
mm
e
r
c
e
p
r
o
d
u
c
t
s
,
”
J
u
r
n
a
l
I
n
f
o
rm
a
t
i
k
a
,
v
o
l
.
1
4
,
n
o
.
3
,
p
.
9
0
,
2
0
2
0
,
d
o
i
:
1
0
.
2
6
5
5
5
/
j
i
f
o
.
v
1
4
i
3
.
a
1
8
5
1
1
.
[
6
]
D
.
W
a
n
g
,
Y
.
Li
a
n
g
,
D
.
X
u
,
X
.
F
e
n
g
,
a
n
d
R
.
G
u
a
n
,
“
A
c
o
n
t
e
n
t
-
b
a
se
d
r
e
c
o
mm
e
n
d
e
r
s
y
s
t
e
m
f
o
r
c
o
mp
u
t
e
r
sc
i
e
n
c
e
p
u
b
l
i
c
a
t
i
o
n
s,
”
K
n
o
w
l
e
d
g
e
-
B
a
se
d
S
y
s
t
e
m
s
,
v
o
l
.
1
5
7
,
p
p
.
1
–
9
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
k
n
o
s
y
s.
2
0
1
8
.
0
5
.
0
0
1
.
[
7
]
M
.
A
n
b
a
z
h
a
g
a
n
a
n
d
M
.
A
r
o
c
k
,
“
A
st
u
d
y
a
n
d
a
n
a
l
y
si
s
o
f
c
o
l
l
a
b
o
r
a
t
i
v
e
f
i
l
t
e
r
i
n
g
a
l
g
o
r
i
t
h
ms
f
o
r
r
e
c
o
m
men
d
e
r
s
y
s
t
e
ms
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
C
o
n
t
r
o
l
T
h
e
o
ry
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
9
,
n
o
.
2
7
,
p
p
.
1
2
7
–
1
3
6
,
2
0
1
6
.
[
8
]
K
.
Y
.
J
u
n
g
,
D
.
H
.
P
a
r
k
,
a
n
d
J.
H
.
L
e
e
,
“
H
y
b
r
i
d
c
o
l
l
a
b
o
r
a
t
i
v
e
f
i
l
t
e
r
i
n
g
a
n
d
c
o
n
t
e
n
t
-
b
a
se
d
f
i
l
t
e
r
i
n
g
f
o
r
i
m
p
r
o
v
e
d
r
e
c
o
m
me
n
d
e
r
sy
st
e
m,
”
L
e
c
t
u
re
N
o
t
e
s
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
(
i
n
c
l
u
d
i
n
g
su
b
ser
i
e
s
L
e
c
t
u
r
e
N
o
t
e
s
i
n
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
L
e
c
t
u
re
N
o
t
e
s
i
n
Bi
o
i
n
f
o
rm
a
t
i
c
s)
,
v
o
l
.
3
0
3
6
,
p
p
.
2
9
5
–
3
0
2
,
2
0
0
4
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
5
4
0
-
2
4
6
8
5
-
5
_
3
7
.
[
9
]
S
.
E
l
i
y
a
s
a
n
d
P
.
R
a
n
j
a
n
a
,
“
R
e
c
o
mm
e
n
d
a
t
i
o
n
s
y
st
e
ms:
c
o
n
t
e
n
t
-
b
a
se
d
f
i
l
t
e
r
i
n
g
v
s
c
o
l
l
a
b
o
r
a
t
i
v
e
f
i
l
t
e
r
i
n
g
,
”
2
0
2
2
2
n
d
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Ad
v
a
n
c
e
C
o
m
p
u
t
i
n
g
a
n
d
I
n
n
o
v
a
t
i
v
e
T
e
c
h
n
o
l
o
g
i
e
s
i
n
E
n
g
i
n
e
e
r
i
n
g
,
I
C
AC
I
T
E
2
0
2
2
,
p
p
.
1
3
6
0
–
1
3
6
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
C
I
TE5
3
7
2
2
.
2
0
2
2
.
9
8
2
3
7
3
0
.
[
1
0
]
S
.
S
h
a
r
ma,
V
.
R
a
n
a
,
a
n
d
M
.
M
a
l
h
o
t
r
a
,
“
A
u
t
o
m
a
t
i
c
r
e
c
o
mm
e
n
d
a
t
i
o
n
s
y
s
t
e
m
b
a
se
d
o
n
h
y
b
r
i
d
f
i
l
t
e
r
i
n
g
a
l
g
o
r
i
t
h
m
,
”
Ed
u
c
a
t
i
o
n
a
n
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
i
e
s
,
v
o
l
.
2
7
,
n
o
.
2
,
p
p
.
1
5
2
3
–
1
5
3
8
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
6
3
9
-
0
2
1
-
1
0
6
4
3
-
8.
[
1
1
]
L.
Li
,
Z
.
Z
h
a
n
g
,
a
n
d
S
.
Z
h
a
n
g
,
“
H
y
b
r
i
d
a
l
g
o
r
i
t
h
m
b
a
s
e
d
o
n
c
o
n
t
e
n
t
a
n
d
c
o
l
l
a
b
o
r
a
t
i
v
e
f
i
l
t
e
r
i
n
g
i
n
r
e
c
o
m
men
d
a
t
i
o
n
s
y
st
e
m
o
p
t
i
m
i
z
a
t
i
o
n
a
n
d
s
i
m
u
l
a
t
i
o
n
,
”
S
c
i
e
n
t
i
f
i
c
P
ro
g
r
a
m
m
i
n
g
,
v
o
l
.
2
0
2
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
1
/
7
4
2
7
4
0
9
.
[
1
2
]
D
.
B
a
h
l
,
V
.
K
a
i
n
,
A
.
S
h
a
r
m
a
,
a
n
d
M
.
S
h
a
r
m
a
,
“
A
n
o
v
e
l
h
y
b
r
i
d
a
p
p
r
o
a
c
h
t
o
w
a
r
d
s
m
o
v
i
e
r
e
c
o
mm
e
n
d
e
r
sy
s
t
e
ms,”
J
o
u
r
n
a
l
o
f
S
t
a
t
i
st
i
c
s
a
n
d
M
a
n
a
g
e
m
e
n
t
S
y
s
t
e
m
s
,
v
o
l
.
2
3
,
n
o
.
6
,
p
p
.
1
0
4
9
–
1
0
5
8
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
8
0
/
0
9
7
2
0
5
1
0
.
2
0
2
0
.
1
7
9
9
5
0
3
.
[
1
3
]
W
.
H
o
n
g
-
X
i
a
,
“
A
n
i
mp
r
o
v
e
d
c
o
l
l
a
b
o
r
a
t
i
v
e
f
i
l
t
e
r
i
n
g
r
e
c
o
mm
e
n
d
a
t
i
o
n
a
l
g
o
r
i
t
h
m,
”
2
0
1
9
4
t
h
I
EEE
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
B
i
g
D
a
t
a
A
n
a
l
y
t
i
c
s,
I
C
BD
A
2
0
1
9
,
p
p
.
4
3
1
–
4
3
5
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
B
D
A
.
2
0
1
9
.
8
7
1
3
2
0
5
.
[
1
4
]
R
.
M
.
S
a
l
l
a
m,
M
.
H
u
ss
e
i
n
,
a
n
d
H
.
M
.
M
o
u
s
a
,
“
A
n
e
n
h
a
n
c
e
d
c
o
l
l
a
b
o
r
a
t
i
v
e
f
i
l
t
e
r
i
n
g
-
b
a
se
d
a
p
p
r
o
a
c
h
f
o
r
r
e
c
o
mm
e
n
d
e
r
sy
s
t
e
ms
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
e
r
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
7
6
,
n
o
.
4
1
,
p
p
.
9
–
1
5
,
2
0
2
0
,
d
o
i
:
1
0
.
5
1
2
0
/
i
j
c
a
2
0
2
0
9
2
0
5
3
1
.
[
1
5
]
M
.
F
.
A
b
d
u
r
r
a
f
i
a
n
d
D
.
H
.
U
.
N
i
n
g
si
h
,
“
C
o
n
t
e
n
t
-
b
a
s
e
d
f
i
l
t
e
r
i
n
g
u
s
i
n
g
c
o
si
n
e
si
m
i
l
a
r
i
t
y
a
l
g
o
r
i
t
h
m
f
o
r
a
l
t
e
r
n
a
t
i
v
e
sel
e
c
t
i
o
n
o
n
t
r
a
i
n
i
n
g
p
r
o
g
r
a
ms,
”
J
o
u
r
n
a
l
o
f
S
o
f
t
C
o
m
p
u
t
i
n
g
Ex
p
l
o
r
a
t
i
o
n
,
v
o
l
.
4
,
n
o
.
4
,
p
p
.
2
0
4
–
2
1
2
,
2
0
2
3
,
d
o
i
:
1
0
.
5
2
4
6
5
/
j
o
s
c
e
x
.
v
4
i
4
.
2
3
2
.
[
1
6
]
Z.
S
h
a
h
b
a
z
i
,
Y
.
B
y
u
n
,
a
n
d
Y
.
-
C
.
B
y
u
n
,
“
P
r
o
d
u
c
t
r
e
c
o
mm
e
n
d
a
t
i
o
n
b
a
s
e
d
o
n
c
o
n
t
e
n
t
-
b
a
se
d
f
i
l
t
e
r
i
n
g
u
si
n
g
X
G
B
o
o
st
c
l
a
ssi
f
i
e
r
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
d
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
2
9
,
n
o
.
0
4
,
p
p
.
6
9
7
9
–
6
9
8
8
,
2
0
2
0
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
r
e
se
a
r
c
h
g
a
t
e
.
n
e
t
/
p
u
b
l
i
c
a
t
i
o
n
/
3
4
2
8
6
4
5
8
8
.
[
1
7
]
N
.
H
.
A
.
M
a
l
e
k
,
W
.
F
.
W
.
Y
a
a
c
o
b
,
Y
.
B
.
W
a
h
,
S
.
A
.
M
d
N
a
s
i
r
,
N
.
S
h
a
a
d
a
n
,
a
n
d
S
.
W
.
I
n
d
r
a
t
n
o
,
“
C
o
mp
a
r
i
s
o
n
o
f
e
n
s
e
mb
l
e
h
y
b
r
i
d
samp
l
i
n
g
w
i
t
h
b
a
g
g
i
n
g
a
n
d
b
o
o
s
t
i
n
g
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
i
mb
a
l
a
n
c
e
d
d
a
t
a
,
”
I
n
d
o
n
e
si
a
n
J
o
u
rn
a
l
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
9
,
n
o
.
1
,
p
p
.
5
9
8
–
6
0
8
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
2
9
.
i
1
.
p
p
5
9
8
-
6
0
8
.
[
1
8
]
A
.
A
l
i
,
“
E
-
c
o
mm
e
r
c
e
s
a
l
e
s
d
a
t
a
2
0
2
3
-
2
4
.
”
K
a
g
g
l
e
.
A
c
c
e
ss
e
d
O
c
t
.
3
0
,
2
0
2
4
.
[
O
n
l
i
n
e
.
]
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
k
a
g
g
l
e
.
c
o
m
/
d
a
t
a
se
t
s/
a
h
m
e
d
a
l
i
r
a
j
a
/
e
-
c
o
m
mere
c
e
-
sa
l
e
s
-
d
a
t
a
-
2023
-
24
[
1
9
]
A
.
S
i
o
n
e
k
,
“
B
r
a
z
i
l
i
a
n
_
e
c
o
mm
e
r
c
e
_
a
n
a
l
y
s
e
s_
v
2
.
”
K
a
g
g
l
e
.
A
c
c
e
ssed
F
e
b
.
1
9
,
2
0
2
5
.
[
O
n
l
i
n
e
.
]
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
k
a
g
g
l
e
.
c
o
m
/
d
a
t
a
se
t
s/
b
u
r
a
y
a
m
a
i
l
/
b
r
a
z
i
l
i
a
n
-
e
c
o
mm
e
r
c
e
-
a
n
a
l
y
ses
-
v2
[
20]
C
.
G
i
v
a
n
,
“
Ec
o
mm
e
r
c
e
_
b
i
g
Q
u
e
r
y
.
”
K
a
g
g
l
e
.
A
c
c
e
sse
d
F
e
b
.
1
9
,
2
0
2
5
.
[
O
n
l
i
n
e
.
]
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
k
a
g
g
l
e
.
c
o
m
/
d
a
t
a
se
t
s/
c
h
i
r
a
g
g
i
v
a
n
8
2
/
e
c
o
m
merc
e
-
b
i
g
q
u
e
r
y
[
2
1
]
T.
C
h
e
n
a
n
d
C
.
G
u
e
s
t
r
i
n
,
“
X
G
B
o
o
st
:
a
sc
a
l
a
b
l
e
t
r
e
e
b
o
o
s
t
i
n
g
s
y
st
e
m,
”
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
AC
M
S
I
G
K
D
D
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
K
n
o
w
l
e
d
g
e
D
i
sco
v
e
ry
a
n
d
D
a
t
a
M
i
n
i
n
g
,
v
o
l
.
1
3
-
17
-
A
u
g
u
s
t
-
2
0
1
6
,
p
p
.
7
8
5
–
7
9
4
,
2
0
1
6
,
d
o
i
:
1
0
.
1
1
4
5
/
2
9
3
9
6
7
2
.
2
9
3
9
7
8
5
.
[
2
2
]
A
.
A
i
z
a
w
a
,
“
A
n
i
n
f
o
r
mat
i
o
n
-
t
h
e
o
r
e
t
i
c
p
e
r
sp
e
c
t
i
v
e
o
f
TF
-
I
D
F
mea
s
u
r
e
s
,
”
I
n
f
o
rm
a
t
i
o
n
Pro
c
e
ss
i
n
g
a
n
d
M
a
n
a
g
e
m
e
n
t
,
v
o
l
.
3
9
,
n
o
.
1
,
p
p
.
4
5
–
6
5
,
2
0
0
3
,
d
o
i
:
1
0
.
1
0
1
6
/
S
0
3
0
6
-
4
5
7
3
(
0
2
)
0
0
0
2
1
-
3.
[
2
3
]
A
.
H
u
a
n
g
,
“
S
i
mi
l
a
r
i
t
y
mea
su
r
e
s
f
o
r
t
e
x
t
d
o
c
u
m
e
n
t
c
l
u
s
t
e
r
i
n
g
,
”
i
n
N
e
w
Z
e
a
l
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
R
e
se
a
rc
h
S
t
u
d
e
n
t
C
o
n
f
e
re
n
c
e
,
N
Z
C
S
R
S
C
2
0
0
8
-
Pr
o
c
e
e
d
i
n
g
s
,
2
0
0
8
,
p
p
.
4
9
–
5
6
.
[
2
4
]
D
.
K
a
l
ma
n
,
“
A
s
i
n
g
u
l
a
r
l
y
v
a
l
u
a
b
l
e
d
e
c
o
m
p
o
si
t
i
o
n
:
t
h
e
S
V
D
o
f
a
m
a
t
r
i
x
,
”
T
h
e
C
o
l
l
e
g
e
M
a
t
h
e
m
a
t
i
c
s
J
o
u
rn
a
l
,
v
o
l
.
2
7
,
n
o
.
1
,
p
p
.
2
–
2
3
,
1
9
9
6
,
d
o
i
:
1
0
.
1
0
8
0
/
0
7
4
6
8
3
4
2
.
1
9
9
6
.
1
1
9
7
3
7
4
4
.
[
2
5
]
C
.
C
h
a
n
n
a
r
o
n
g
,
C
.
P
a
o
si
r
i
k
u
l
,
S
.
M
a
n
e
e
r
o
j
,
a
n
d
A
.
Ta
k
a
s
u
,
“
H
y
b
r
i
d
B
E
R
T
4
R
e
c
:
a
h
y
b
r
i
d
(
c
o
n
t
e
n
t
-
b
a
s
e
d
f
i
l
t
e
r
i
n
g
a
n
d
c
o
l
l
a
b
o
r
a
t
i
v
e
f
i
l
t
e
r
i
n
g
)
r
e
c
o
mm
e
n
d
e
r
sy
st
e
m
b
a
se
d
o
n
B
ER
T,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
5
6
1
9
3
–
56
2
0
6
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
2
.
3
1
7
7
6
1
0
.
[
2
6
]
Z.
F
a
y
y
a
z
,
M
.
E
b
r
a
h
i
m
i
a
n
,
D
.
N
a
w
a
r
a
,
A
.
I
b
r
a
h
i
m
,
a
n
d
R
.
K
a
s
h
e
f
,
“
R
e
c
o
mm
e
n
d
a
t
i
o
n
s
y
st
e
ms:
a
l
g
o
r
i
t
h
ms,
c
h
a
l
l
e
n
g
e
s,
me
t
r
i
c
s
,
a
n
d
b
u
s
i
n
e
ss
o
p
p
o
r
t
u
n
i
t
i
e
s,”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
1
0
,
n
o
.
2
1
,
p
p
.
1
–
2
0
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
0
2
1
7
7
4
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
14
,
No
.
2
,
J
u
n
e
2
0
2
5
:
6
1
8
-
626
626
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Vin
c
e
n
tiu
s
Lo
a
n
k
a
S
in
a
g
a
is
a
c
o
m
p
u
ter
sc
ien
c
e
stu
d
e
n
t
a
n
d
r
e
se
a
rc
h
e
r
a
t
Bin
a
Nu
sa
n
tara
Un
iv
e
rsity
(BINU
S
),
I
n
d
o
n
e
sia
.
He
c
o
m
p
lete
d
h
is
u
n
d
e
rg
ra
d
u
a
te
d
e
g
re
e
a
t
BINU
S
Un
iv
e
rsity
i
n
2
0
2
4
a
n
d
wa
s
su
b
se
q
u
e
n
t
ly
a
d
m
it
te
d
to
t
h
e
M
a
ste
r
o
f
Co
m
p
u
ter
S
c
ien
c
e
p
ro
g
ra
m
a
t
th
e
BINU
S
G
ra
d
u
a
te
P
r
o
g
ra
m
in
2
0
2
3
.
Du
r
in
g
h
is
st
u
d
ies
,
h
e
p
a
rti
c
i
p
a
ted
in
t
h
e
2
0
2
2
I
n
tern
a
ti
o
n
a
l
C
o
n
fe
re
n
c
e
o
n
El
e
c
tri
c
a
l
a
n
d
I
n
fo
rm
a
ti
o
n
Te
c
h
n
o
l
o
g
y
(IE
IT)
,
wh
e
re
h
e
p
re
se
n
ted
a
p
a
p
e
r
ti
t
led
“
G
ra
p
h
a
tt
e
n
ti
o
n
n
e
two
r
k
o
n
e
x
trac
ti
n
g
fe
a
tu
re
s
fro
m
sim
p
li
fied
m
o
lec
u
lar
-
in
p
u
t
l
in
e
-
e
n
tr
y
sy
ste
m
f
o
r
HIV
c
las
sifica
ti
o
n
.
”
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
o
p
ti
m
izi
n
g
e
-
c
o
m
m
e
rc
e
re
c
o
m
m
e
n
d
a
ti
o
n
s
y
ste
m
s
u
sin
g
m
u
lt
i
p
le
e
n
se
m
b
le
c
las
sifiers
.
He
c
a
n
b
e
re
a
c
h
e
d
a
t
v
i
n
c
e
n
ti
u
s.sin
a
g
a
@
b
in
u
s.a
c
.
id
.
Dr
.
En
g
.
Ant
o
n
i
Wi
b
o
w
o
,
S
.
S
i.
,
M.
K
o
m
.
,
M.
E
n
g
.
re
c
e
iv
e
d
h
is
first
d
e
g
re
e
in
Ap
p
li
e
d
M
a
t
h
e
m
a
ti
c
s
in
1
9
9
5
a
n
d
m
a
ste
r
's
d
e
g
re
e
in
C
o
m
p
u
ter
S
c
ien
c
e
in
2
0
0
0
.
I
n
2
0
0
3
,
He
wa
s
a
w
a
rd
e
d
a
Ja
p
a
n
e
se
G
o
v
e
rn
m
e
n
t
S
c
h
o
lars
h
i
p
(M
o
n
b
u
k
a
g
a
k
u
sh
o
)
to
a
tt
e
n
d
M
a
ste
r
's
a
n
d
P
h
D
p
r
o
g
ra
m
s
in
S
y
ste
m
s
a
n
d
I
n
fo
rm
a
ti
o
n
E
n
g
i
n
e
e
rin
g
at
th
e
U
n
iv
e
rsit
y
o
f
Tsu
k
u
b
a
-
Ja
p
a
n
.
He
c
o
m
p
lete
d
h
is
se
c
o
n
d
m
a
ste
r
's
d
e
g
re
e
in
2
0
0
6
a
n
d
P
h
D
d
e
g
re
e
in
2
0
0
9
,
re
sp
e
c
ti
v
e
l
y
.
His
P
h
D
re
se
a
rc
h
fo
c
u
se
d
o
n
m
a
c
h
in
e
lea
rn
i
n
g
,
o
p
e
ra
ti
o
n
s
re
se
a
rc
h
,
m
u
lt
i
v
a
riate
sta
ti
stica
l
a
n
a
ly
sis
,
a
n
d
m
a
th
e
m
a
ti
c
a
l
p
r
o
g
ra
m
m
in
g
,
e
sp
e
c
ially
i
n
d
e
v
e
lo
p
i
n
g
n
o
n
li
n
e
a
r
ro
b
u
st
re
g
re
ss
io
n
s
u
si
n
g
sta
ti
stica
l
lea
rn
i
n
g
t
h
e
o
ry
.
He
wo
rk
e
d
fro
m
1
9
9
7
to
2
0
1
0
a
s
a
re
se
a
rc
h
e
r
in
th
e
Ag
e
n
c
y
fo
r
t
h
e
As
se
ss
m
e
n
t
a
n
d
Ap
p
li
c
a
ti
o
n
o
f
Tec
h
n
o
lo
g
y
-
In
d
o
n
e
sia
.
F
r
o
m
Ap
ril
2
0
1
0
-
S
e
p
tem
b
e
r
2
0
1
4
,
h
e
wo
rk
e
d
a
s
a
se
n
io
r
lec
tu
re
r
i
n
th
e
De
p
a
rtme
n
t
o
f
C
o
m
p
u
ter
S
c
ien
c
e
-
F
a
c
u
lt
y
o
f
C
o
m
p
u
ti
n
g
,
a
n
d
a
re
se
a
rc
h
e
r
in
th
e
Op
e
ra
ti
o
n
B
u
sin
e
ss
In
telli
g
e
n
c
e
(OBI)
Re
se
a
rc
h
G
ro
u
p
,
Un
i
v
e
rsiti
Tek
n
o
l
o
g
i
M
a
lay
sia
(UTM
)
,
M
a
lay
s
ia.
F
ro
m
Oc
to
b
e
r
2
0
1
4
to
Oc
to
b
e
r
2
0
1
6
,
h
e
wa
s
a
n
As
so
c
iate
P
ro
fe
ss
o
r
a
t
th
e
De
p
a
rtme
n
t
o
f
De
c
isio
n
S
c
ien
c
e
s,
S
c
h
o
o
l
o
f
Qu
a
n
ti
tativ
e
S
c
ien
c
e
s
at
Un
iv
e
rsiti
Uta
ra
M
a
lay
sia
(UU
M
).
Dr.
En
g
.
Wi
b
o
wo
is
c
u
rre
n
tl
y
wo
rk
i
n
g
a
t
Bi
n
u
s
G
ra
d
u
a
te
P
ro
g
ra
m
(M
a
ste
r
in
Co
m
p
u
ter
S
c
ien
c
e
)
in
Bin
a
Nu
sa
n
tara
Un
iv
e
rsity
,
In
d
o
n
e
sia
a
s
a
S
p
e
c
ialist
Lec
tu
re
r
a
n
d
c
o
n
ti
n
u
e
s
h
is
re
s
e
a
rc
h
a
c
ti
v
it
ies
in
m
a
c
h
in
e
lea
rn
in
g
,
o
p
ti
m
iza
ti
o
n
,
o
p
e
ra
ti
o
n
s
re
se
a
rc
h
,
m
u
lt
iv
a
riate
d
a
t
a
a
n
a
ly
sis,
d
a
ta
m
in
i
n
g
,
c
o
m
p
u
tati
o
n
a
l
i
n
telli
g
e
n
c
e
,
a
n
d
a
rti
ficia
l
in
telli
g
e
n
c
e
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
n
wib
o
w
o
@b
i
n
u
s.e
d
u
.
Evaluation Warning : The document was created with Spire.PDF for Python.