I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
1
5
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
,
p
p
.
374
~
382
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
15
.i
1
.
p
p
3
7
4
-
3
8
2
374
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
TAHR
F:
e
nha
nci
ng
perso
na
lized t
o
urism
rec
o
mm
e
nda
tions
with
dy
na
mic
ada
ptatio
n
M
o
ha
m
ed
B
a
do
uch
1
,
M
e
hd
i
B
o
uta
o
un
t
e
2
1
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
s,
I
b
n
o
u
Z
o
h
r
U
n
i
v
e
r
s
i
t
y
,
A
g
a
d
i
r
,
M
o
r
o
c
c
o
2
N
a
t
i
o
n
a
l
S
c
h
o
o
l
o
f
C
o
mm
e
r
c
e
a
n
d
M
a
n
a
g
e
me
n
t
,
I
b
n
o
u
Z
o
h
r
U
n
i
v
e
r
s
i
t
y
,
D
a
k
h
l
a
,
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
Au
g
6
,
2
0
2
5
R
ev
is
ed
Dec
2
1
,
2
0
2
5
Acc
ep
ted
J
an
1
0
,
2
0
2
6
Th
e
ra
p
i
d
g
ro
wt
h
o
f
o
n
li
n
e
t
o
u
r
ism
d
a
ta
in
te
n
sifies
in
f
o
rm
a
ti
o
n
o
v
e
rlo
a
d
,
wh
il
e
c
o
n
v
e
n
ti
o
n
a
l
re
c
o
m
m
e
n
d
e
r
sy
ste
m
s
stru
g
g
le
with
sp
a
rsity
,
c
o
ld
-
sta
rt
issu
e
s,
a
n
d
sin
g
le
-
c
rit
e
ria
ra
ti
n
g
s.
Th
is
p
a
p
e
r
p
re
se
n
ts
th
e
tr
u
st
-
a
wa
re
h
y
b
rid
re
c
o
m
m
e
n
d
a
ti
o
n
fra
m
e
wo
rk
(T
AH
RF
),
wh
ich
i
n
teg
ra
tes
u
se
r
-
it
e
m
tru
st
p
ro
p
a
g
a
ti
o
n
,
m
u
l
ti
-
c
rit
e
ria
ra
ti
n
g
s,
a
n
d
d
y
n
a
m
ic
p
re
fe
re
n
c
e
a
d
a
p
tatio
n
.
TAHRF
e
m
p
lo
y
s
E
u
c
li
d
e
a
n
-
Ja
c
c
a
rd
tru
st
m
e
tri
c
s,
it
e
m
c
o
n
n
e
c
ti
v
it
y
,
a
n
d
ra
ti
n
g
c
o
n
siste
n
c
y
,
c
o
m
b
in
e
d
wit
h
a
fe
e
d
b
a
c
k
-
d
ri
v
e
n
we
ig
h
ti
n
g
m
e
c
h
a
n
ism
.
Ex
p
e
rime
n
ts
o
n
Tri
p
Ad
v
iso
r
d
a
tas
e
ts
sh
o
w
su
p
e
rio
r
p
e
rfo
rm
a
n
c
e
:
m
e
a
n
a
b
so
lu
te
e
rro
r
(
M
AE)
re
d
u
c
e
d
to
0
.
9
8
(re
sta
u
ra
n
ts)
a
n
d
0
.
7
1
(h
o
tels),
o
u
t
p
e
rfo
rm
in
g
m
u
lt
i
-
c
rit
e
ria
ten
s
o
r
-
b
a
se
d
c
o
ll
a
b
o
ra
ti
v
e
fil
teri
n
g
(
MC
-
TeCF
)
b
a
se
li
n
e
s.
TAHRF
a
lso
a
c
h
iev
e
s
h
ig
h
e
r
p
re
c
isio
n
@5
,
with
c
o
v
e
ra
g
e
m
a
in
tain
e
d
u
n
d
e
r
e
x
t
re
m
e
sp
a
rsity
.
A
b
latio
n
st
u
d
ies
c
o
n
f
irm
th
e
c
rit
ica
l
ro
l
e
o
f
tru
st p
ro
p
a
g
a
ti
o
n
,
m
u
lt
i
-
c
rit
e
ri
a
a
n
a
ly
sis,
a
n
d
a
d
a
p
ti
v
e
we
ig
h
ti
n
g
.
TAHRF
a
d
v
a
n
c
e
s p
e
rso
n
a
li
z
e
d
,
tran
s
p
a
re
n
t,
a
n
d
a
d
a
p
ti
v
e
to
u
rism
re
c
o
m
m
e
n
d
a
ti
o
n
s.
K
ey
w
o
r
d
s
:
C
o
llab
o
r
ativ
e
f
ilter
in
g
Dy
n
am
ic
ad
ap
tatio
n
Mu
lti
-
cr
iter
ia
r
atin
g
s
R
ec
o
m
m
en
d
er
s
y
s
tem
s
T
o
u
r
is
m
r
ec
o
m
m
en
d
atio
n
s
T
r
u
s
t n
etwo
r
k
s
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
:
Mo
h
am
ed
B
ad
o
u
ch
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
,
Facu
lty
o
f
Scien
ce
s
,
I
b
n
o
u
Z
o
h
r
Un
iv
er
s
ity
Ag
ad
ir
,
Mo
r
o
cc
o
E
m
ail: m
o
h
am
ed
.
b
ad
o
u
ch
@
ed
u
.
u
iz.
ac
.
m
a
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
r
ap
id
d
ig
itizatio
n
o
f
th
e
to
u
r
is
m
in
d
u
s
tr
y
h
as
tr
an
s
f
o
r
m
ed
h
o
w
tr
av
eler
s
d
is
co
v
er
an
d
p
lan
ex
p
er
ien
ce
s
,
with
p
latf
o
r
m
s
lik
e
T
r
ip
Ad
v
is
o
r
an
d
B
o
o
k
in
g
.
co
m
o
f
f
er
i
n
g
m
illi
o
n
s
o
f
u
s
er
-
g
en
er
ated
r
e
v
iews
an
d
lis
tin
g
s
.
Ho
wev
e
r
,
th
is
ab
u
n
d
an
ce
o
f
d
ata
c
r
ea
te
s
s
ev
er
e
in
f
o
r
m
atio
n
o
v
e
r
l
o
ad
,
lea
v
in
g
u
s
er
s
o
v
er
wh
elm
ed
b
y
ch
o
ice
an
d
u
n
ab
le
to
ef
f
icien
tly
id
en
tify
o
p
tio
n
s
alig
n
ed
with
th
eir
p
r
ef
e
r
en
ce
s
.
T
r
ad
itio
n
al
r
ec
o
m
m
en
d
er
s
y
s
tem
s
,
wh
ile
ef
f
ec
tiv
e
in
d
o
m
ain
s
lik
e
e
-
co
m
m
er
ce
,
s
tr
u
g
g
le
to
a
d
d
r
ess
th
e
u
n
iq
u
e
co
m
p
lex
ities
o
f
t
o
u
r
is
m
,
wh
e
r
e
d
ec
is
io
n
s
d
ep
e
n
d
o
n
m
u
lti
-
d
im
en
s
io
n
al
cr
iter
ia
(
e.
g
.
,
b
u
d
g
et,
lo
ca
tio
n
,
an
d
s
ea
s
o
n
ality
)
an
d
d
y
n
am
ic
u
s
e
r
b
eh
av
io
r
[
1
]
,
[
2
]
.
Fo
r
in
s
tan
ce
,
a
tr
av
eler
m
ig
h
t
p
r
io
r
iti
ze
"f
am
ily
-
f
r
ien
d
l
y
am
en
ities
"
f
o
r
a
s
u
m
m
er
v
ac
a
tio
n
b
u
t
s
h
if
t
to
"a
d
v
en
tu
r
e
ac
tiv
ities
"
d
u
r
in
g
win
ter
—
a
n
u
an
ce
r
ar
ely
ca
p
tu
r
e
d
b
y
s
tatic
m
o
d
els [
3
]
.
R
ec
en
t
r
esear
ch
h
as
m
ad
e
s
ig
n
if
ican
t
s
tr
id
es
i
n
a
d
d
r
ess
in
g
to
u
r
is
m
r
ec
o
m
m
en
d
atio
n
c
h
allen
g
es.
R
icci
[
1
]
p
r
o
v
id
es
a
c
o
m
p
r
e
h
en
s
iv
e
o
v
er
v
iew
o
f
r
ec
o
m
m
e
n
d
er
s
y
s
tem
in
to
u
r
is
m
,
h
ig
h
l
ig
h
tin
g
th
e
n
ee
d
f
o
r
co
n
tex
t
-
awa
r
e
ap
p
r
o
ac
h
es.
J
an
n
ac
h
an
d
Z
an
k
er
[
3
]
em
p
h
a
s
ize
th
e
im
p
o
r
tan
ce
o
f
in
ter
ac
tiv
e
s
y
s
tem
s
,
wh
ile
Ad
o
m
av
iciu
s
an
d
Kwo
n
[
4
]
p
io
n
ee
r
ed
m
u
lti
-
cr
iter
ia
r
atin
g
s
y
s
tem
s
th
at
ca
p
tu
r
e
g
r
a
n
u
lar
p
r
ef
er
en
ce
s
.
So
cial
r
o
b
o
ts
,
as
ex
p
lo
r
ed
b
y
T
o
ll
e
et
a
l
.
[
5
]
,
d
em
o
n
s
tr
ate
h
ig
h
u
s
er
s
atis
f
ac
tio
n
(
4
.
6
6
/5
lik
ab
ilit
y
)
b
u
t
lack
s
ca
lab
ilit
y
f
o
r
lar
g
e
d
atasets
[
6
]
.
Hy
b
r
id
s
y
s
tem
s
lik
e
d
esti
n
atio
n
f
in
d
e
r
[
7
]
en
a
b
le
d
y
n
am
i
c
p
r
ef
er
e
n
ce
tu
n
in
g
v
ia
m
ap
in
ter
f
ac
es
b
u
t
o
m
it
tr
u
s
t
p
r
o
p
ag
atio
n
m
ec
h
an
is
m
s
.
Ad
v
an
ce
d
tech
n
iq
u
es
s
u
ch
as
n
o
n
n
e
g
ativ
e
m
atr
ix
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
TAHR
F
:
en
h
a
n
ci
n
g
p
ers
o
n
a
liz
ed
to
u
r
is
m
r
ec
o
mme
n
d
a
tio
n
s
w
ith
d
yn
a
mic
a
d
a
p
ta
tio
n
(
Mo
h
a
med
B
a
d
o
u
c
h
)
375
f
ac
to
r
izatio
n
with
tr
u
s
t
r
elatio
n
s
h
ip
s
[
8
]
a
n
d
s
im
ilar
ity
-
b
ased
co
llab
o
r
ativ
e
f
ilter
in
g
[
9
]
h
av
e
s
h
o
wn
p
r
o
m
is
e
in
ad
d
r
ess
in
g
d
ata
s
p
a
r
s
ity
,
y
e
t n
o
s
o
lu
tio
n
h
o
lis
tically
in
teg
r
ates th
ese
ap
p
r
o
ac
h
es.
T
h
r
ee
k
ey
c
h
allen
g
es
p
er
s
is
t
in
to
u
r
is
m
r
ec
o
m
m
en
d
e
r
s
y
s
tem
s
.
First,
d
ata
s
p
ar
s
ity
r
em
ain
s
a
cr
itical
is
s
u
e,
with
o
v
er
9
0
%
o
f
u
s
er
s
r
atin
g
f
ewe
r
th
an
5
item
s
,
c
r
ip
p
lin
g
s
im
ilar
ity
c
o
m
p
u
tatio
n
s
in
co
llab
o
r
ativ
e
f
ilter
in
g
[
1
0
]
.
T
h
is
p
r
o
b
lem
is
p
ar
ticu
lar
ly
ac
u
te
in
to
u
r
is
m
,
wh
er
e
u
s
er
s
in
ter
ac
t
in
f
r
eq
u
e
n
tly
[
1
1
]
.
Seco
n
d
,
m
u
lti
-
cr
iter
ia
co
m
p
le
x
ity
p
r
e
s
en
ts
s
ig
n
if
ican
t
h
u
r
d
les,
as
s
in
g
le
-
r
atin
g
s
y
s
tem
s
f
ail
t
o
ca
p
tu
r
e
g
r
a
n
u
lar
p
r
ef
er
en
ce
s
—
f
o
r
ex
am
p
le,
a
h
o
tel
r
ated
4
/5
m
ay
e
x
ce
l
in
"c
lean
lin
ess
"
b
u
t
lag
in
"lo
ca
tio
n
"
[
4
]
.
T
o
u
r
is
m
d
ec
is
io
n
s
in
v
o
lv
e
c
o
n
tex
t
-
d
ep
en
d
en
t
cr
iter
ia
t
h
at
v
ar
y
ac
r
o
s
s
tr
av
eler
ty
p
es
[
1
2
]
.
T
h
ir
d
,
d
y
n
am
ic
ad
ap
tatio
n
is
lar
g
ely
u
n
s
u
p
p
o
r
ted
b
y
ex
is
tin
g
s
y
s
tem
s
,
y
et
t
r
av
el
p
lan
n
in
g
is
in
h
er
en
tly
iter
ativ
e,
r
eq
u
ir
in
g
r
ea
l
-
tim
e
ad
ju
s
tm
en
ts
to
ev
o
lv
in
g
p
r
e
f
er
en
ce
s
lik
e
b
u
d
g
et
ch
an
g
es o
r
s
ea
s
o
n
al
s
h
if
ts
[
1
3
]
,
[
1
4
]
.
Desp
ite
th
ese
ad
v
an
ce
s
,
ex
is
tin
g
s
o
lu
tio
n
s
e
x
h
ib
it
c
r
itical
lim
itatio
n
s
th
at
o
u
r
w
o
r
k
ad
d
r
ess
es.
T
r
u
s
t
-
en
h
an
ce
d
m
o
d
els f
o
c
u
s
s
o
lely
o
n
u
s
er
-
u
s
er
r
elatio
n
s
h
i
p
s
wh
ile
ig
n
o
r
in
g
item
-
item
tr
u
s
t p
r
o
p
ag
atio
n
[
7
]
.
Mu
lti
-
cr
iter
ia
s
y
s
tem
s
lack
r
ea
l
-
tim
e
ad
ap
tatio
n
m
ec
h
an
is
m
s
[
4
]
,
a
n
d
h
y
b
r
id
ap
p
r
o
ac
h
es
d
o
n
o
t
jo
in
tly
o
p
tim
ize
tr
u
s
t
n
etwo
r
k
s
,
m
u
l
ti
-
cr
iter
ia
an
aly
s
is
,
an
d
d
y
n
a
m
ic
f
ee
d
b
ac
k
[
7
]
.
Ou
r
n
o
v
el
tr
u
s
t
-
awa
r
e
h
y
b
r
id
r
ec
o
m
m
en
d
atio
n
f
r
am
ew
o
r
k
(
T
AHRF
)
b
r
id
g
es
th
ese
g
ap
s
t
h
r
o
u
g
h
th
r
ee
k
ey
in
n
o
v
atio
n
s
.
First,
i
t
in
tr
o
d
u
ce
s
u
n
if
ied
tr
u
s
t
p
r
o
p
ag
atio
n
th
at
in
teg
r
ates
b
o
th
u
s
er
-
u
s
er
an
d
i
tem
-
item
tr
u
s
t
n
etwo
r
k
s
u
s
in
g
E
u
clid
ea
n
-
J
ac
ca
r
d
m
etr
ics,
en
ab
lin
g
1
6
-
4
0
%
l
o
wer
m
ea
n
ab
s
o
lu
te
e
r
r
o
r
(
MA
E
)
th
an
b
en
ch
m
ar
k
s
.
Se
co
n
d
,
it
co
m
b
i
n
es
m
u
lti
-
cr
iter
ia
d
y
n
am
ic
a
d
ap
tat
io
n
with
r
ea
l
-
tim
e
p
r
ef
er
e
n
ce
tu
n
in
g
v
ia
in
ter
ac
tiv
e
m
a
p
in
t
er
f
ac
es,
ac
h
iev
in
g
8
9
%
co
v
er
a
g
e
u
n
d
er
9
9
.
8
%
s
p
ar
s
ity
.
T
h
ir
d
,
it
im
p
lem
en
ts
co
n
tex
t
-
awa
r
e
h
y
b
r
i
d
weig
h
ti
n
g
th
at
d
y
n
am
ically
b
alan
ce
s
tr
u
s
t
an
d
r
atin
g
s
ig
n
a
ls
u
s
in
g
f
ee
d
b
ac
k
-
d
r
iv
en
α
-
ad
j
u
s
tm
en
t,
v
alid
ated
th
r
o
u
g
h
T
r
i
p
Ad
v
is
o
r
d
atasets
(
2
8
,
8
2
9
r
atin
g
s
)
an
d
u
s
er
s
tu
d
ies
(
N=
1
3
0
)
.
U
n
lik
e
p
r
io
r
wo
r
k
,
T
AHRF
h
o
lis
tica
lly
ad
d
r
ess
es
th
e
"sp
ar
s
ity
-
ad
ap
tatio
n
-
tr
a
n
s
p
ar
e
n
cy
"
tr
iad
in
to
u
r
is
m
r
ec
o
m
m
en
d
er
s
y
s
tem
,
ad
v
a
n
cin
g
th
e
s
tate
-
of
-
th
e
-
a
r
t
in
th
r
ee
I
E
E
E
T
r
an
s
ac
tio
n
s
p
ap
e
r
an
d
two
AC
M
R
ec
Sy
s
co
n
tr
ib
u
tio
n
s
.
Ou
r
co
n
tr
i
b
u
tio
n
s
in
clu
d
e
a
n
o
v
el
t
r
u
s
t
m
etr
ic
co
m
b
in
in
g
E
u
clid
ea
n
s
im
ilar
ity
an
d
J
ac
ca
r
d
co
n
f
id
en
ce
,
an
in
ter
ac
tiv
e
m
ap
i
n
ter
f
ac
e
ac
h
iev
in
g
u
n
p
r
ec
e
d
en
ted
s
p
a
r
s
ity
co
v
er
ag
e,
an
d
em
p
ir
ical
v
alid
atio
n
s
h
o
win
g
8
1
%
u
s
er
p
r
ef
er
en
ce
f
o
r
r
ea
l
-
tim
e
ad
ap
tatio
n
.
T
h
is
co
m
p
r
e
h
en
s
iv
e
ap
p
r
o
ac
h
r
e
p
r
esen
ts
a
s
i
g
n
if
ican
t
lea
p
f
o
r
war
d
in
p
e
r
s
o
n
alize
d
to
u
r
is
m
r
ec
o
m
m
en
d
atio
n
s
,
p
ar
ticu
la
r
ly
in
s
p
ar
s
e
d
ata
en
v
i
r
o
n
m
e
n
ts
wh
er
e
tr
ad
itio
n
al
s
y
s
tem
s
f
ail.
2.
M
E
T
H
O
D
2
.
1
.
T
AH
RF
a
rc
hite
ct
ure
T
h
e
T
AHRF
ar
ch
itectu
r
e
as
s
h
o
wn
in
Fig
u
r
e
1
is
d
esig
n
e
d
to
m
itig
atin
g
t
h
e
lim
itatio
n
s
i
n
h
er
en
t
i
n
class
ical
co
llab
o
r
ativ
e
f
ilter
in
g
b
y
lev
er
a
g
in
g
tr
u
s
t
b
etwe
en
u
s
er
s
[
1
0
]
,
item
-
b
ased
tr
u
s
t,
an
d
d
y
n
am
ic
h
y
b
r
id
weig
h
tin
g
.
T
h
e
s
y
s
tem
co
m
p
r
is
es
th
r
ee
in
ter
co
n
n
ec
te
d
m
o
d
u
les.
T
h
is
ar
ch
itectu
r
e
en
s
u
r
es
r
o
b
u
s
t
p
er
f
o
r
m
an
ce
in
s
p
ar
s
e
d
atasets
wh
ile
m
ain
tain
in
g
s
ca
lab
ilit
y
an
d
ad
ap
tab
ilit
y
t
o
d
y
n
am
i
c
u
s
er
p
r
ef
er
en
ce
s
.
Key
f
ea
tu
r
es o
f
t
h
ese
m
o
d
u
les ar
e
s
u
m
m
ar
ized
i
n
T
ab
le
1
.
User
-
b
ased
tr
u
s
t
co
llab
o
r
ativ
e
f
ilter
in
g
C
F:
th
is
m
o
d
u
le
co
m
p
u
tes
tr
u
s
t
s
co
r
es
b
etwe
en
u
s
er
s
to
m
itig
ate
d
ata
s
p
ar
s
ity
an
d
e
n
h
an
ce
r
ec
o
m
m
e
n
d
atio
n
ac
cu
r
ac
y
[
1
1
]
.
I
t e
m
p
lo
y
s
th
r
ee
k
ey
m
etr
ics:
i)
Dir
ec
t
tr
u
s
t:
m
ea
s
u
r
es
th
e
r
es
em
b
lan
ce
am
o
n
g
two
elem
en
ts
(
u
s
er
)
b
ased
o
n
c
o
-
r
ated
el
em
en
ts
u
s
in
g
E
u
clid
ea
n
d
is
tan
ce
an
d
J
ac
ca
r
d
co
n
f
i
d
en
ce
.
T
h
e
f
o
r
m
u
latio
n
o
f
d
ir
ec
t tr
u
s
t is g
iv
en
in
(
1
)
.
,
=
,
×
,
(
1
)
W
h
er
e
,
is
th
e
E
u
clid
ea
n
s
im
ilar
ity
an
d
,
is
th
e
J
ac
ca
r
d
co
n
f
id
e
n
ce
.
ii)
Pro
p
ag
ated
tr
u
s
t:
in
f
er
s
tr
u
s
t
b
etwe
en
in
d
ir
ec
tly
co
n
n
ec
ted
u
s
er
s
th
r
o
u
g
h
i
n
ter
m
ed
iar
y
n
eig
h
b
o
r
s
.
T
h
e
p
r
o
p
a
g
ated
tr
u
s
t c
o
m
p
u
tatio
n
i
s
ex
p
r
ess
ed
in
(
2
)
.
,
=
∑
,
∈
(
,
)
×
,
(
2
)
W
h
er
e
(
,
)
d
en
o
tes th
e
s
et
o
f
co
m
m
o
n
n
ei
g
h
b
o
r
s
b
etwe
en
u
s
er
s
x
an
d
z
.
iii)
Ov
er
all
tr
u
s
t:
co
m
b
in
es
d
ir
ec
t
an
d
p
r
o
p
ag
ate
d
tr
u
s
t
with
u
s
er
r
atin
g
b
e
h
av
io
r
an
d
c
o
n
n
ec
tiv
ity
.
T
h
e
o
v
er
all
u
s
er
tr
u
s
t is d
ef
in
ed
in
(
3
)
.
=
e
xp
(
−
∑
|
,
−
̅
̅
̅
|
∈
|
|
)
×
√
|
|
|
|
(
3
)
I
n
th
is
co
n
tex
t,
,
is
th
e
r
atin
g
g
iv
en
b
y
u
s
er
x
'
s
to
item
i
,
̅
i
s
th
e
m
ea
n
r
atin
g
o
f
item
i
;
a
n
d
∣
Ux
∣
in
d
icate
s
h
o
w
m
an
y
u
s
er
s
ar
e
lin
k
ed
to
x
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
:
374
-
3
8
2
376
Fig
u
r
e
1
.
T
AHRF
ar
ch
itectu
r
e
T
ab
le
1
.
Key
f
ea
tu
r
es o
f
T
AHRF
M
o
d
u
l
e
K
e
y
m
e
t
r
i
c
s
P
u
r
p
o
se
U
ser
-
b
a
se
d
t
r
u
s
t
C
F
D
i
r
e
c
t
,
p
r
o
p
a
g
a
t
e
d
,
a
n
d
o
v
e
r
a
l
l
t
r
u
st
M
i
t
i
g
a
t
e
s
p
a
r
si
t
y
,
e
n
h
a
n
c
e
u
s
e
r
si
mi
l
a
r
i
t
y
I
t
e
m
-
b
a
se
d
t
r
u
s
t
C
F
I
t
e
m c
o
n
n
e
c
t
i
v
i
t
y
,
r
a
t
i
n
g
d
e
v
i
a
t
i
o
n
A
d
d
r
e
ss
c
o
l
d
-
st
a
r
t
,
e
v
a
l
u
a
t
e
i
t
e
m
t
r
u
st
w
o
r
t
h
i
n
e
ss
H
y
b
r
i
d
r
e
c
o
mm
e
n
d
e
r
D
y
n
a
mi
c
w
e
i
g
h
t
i
n
g
B
a
l
a
n
c
e
u
s
e
r
-
i
t
e
m
p
r
e
d
i
c
t
i
o
n
s,
i
m
p
r
o
v
e
a
c
c
u
r
a
c
y
I
t
e
m
-
b
a
s
e
d
c
o
l
la
b
o
r
a
t
i
v
e
f
i
lte
r
i
n
g
w
e
i
g
h
t
e
d
b
y
u
s
e
r
c
r
e
d
i
b
i
l
i
t
y
:
t
h
is
m
o
d
u
l
e
e
v
a
l
u
a
t
e
s
it
e
m
t
r
u
s
t
w
o
r
t
h
i
n
e
s
s
b
a
s
e
d
o
n
c
o
n
n
e
c
t
i
v
i
t
y
a
n
d
r
a
ti
n
g
c
o
n
s
is
t
e
n
c
y
,
a
d
d
r
e
s
s
i
n
g
c
o
l
d
-
s
t
a
r
t
a
n
d
s
p
a
r
s
it
y
c
h
a
l
l
e
n
g
es
[
1
2
]
.
i)
I
tem
co
n
n
ec
tiv
ity
:
co
u
n
ts
h
o
w
m
an
y
lin
k
s
an
elem
en
t
h
as
to
o
th
er
elem
en
ts
in
th
e
el
em
en
t
-
elem
en
t
in
ter
co
n
n
ec
tio
n
r
elatio
n
s
.
T
h
e
item
co
n
n
ec
tiv
ity
is
d
ef
i
n
ed
in
(
4
)
.
=
|
|
|
|
(
4
)
Her
e
∣
ti
∣
d
en
o
tes co
u
n
t o
f
o
th
e
r
item
s
r
elate
d
with
elem
en
t
i
,
∣
I
∣
d
en
o
tes th
e
g
lo
b
al
c
o
u
n
t
o
f
elem
en
ts
.
ii)
R
a
ti
n
g
d
e
v
i
a
t
i
o
n
:
q
u
a
n
t
i
f
i
es
h
o
w
m
u
c
h
u
s
e
r
s
’
r
a
ti
n
g
s
f
o
r
a
g
i
v
e
n
i
t
e
m
d
i
f
f
e
r
f
r
o
m
i
ts
a
v
e
r
a
g
e
—
t
h
a
t
i
s
,
i
t
c
a
p
t
u
r
e
s
c
o
n
s
i
s
t
e
n
c
y
o
f
t
h
o
s
e
r
a
t
i
n
g
s
.
A
l
o
w
e
r
d
e
v
i
a
ti
o
n
m
e
a
n
s
u
s
e
r
s
t
e
n
d
t
o
a
g
r
e
e
m
o
r
e
o
n
th
e
i
t
e
m
,
w
h
i
le
a
h
i
g
h
e
r
d
e
v
i
a
t
i
o
n
i
n
d
i
c
at
e
s
m
o
r
e
d
i
s
a
g
r
e
e
m
e
n
t
o
r
v
a
r
i
a
b
i
l
it
y
.
T
h
e
r
a
t
i
n
g
d
e
v
i
a
t
i
o
n
is
f
o
r
m
u
l
at
e
d
i
n
(
5
)
.
=
(
−
∑
|
,
−
̅
̅
̅
|
∈
|
|
)
(
5
)
W
h
er
e
̅
is
th
e
av
er
ag
e
r
atin
g
g
i
v
en
b
y
u
s
er
x
.
iii)
I
tem
tr
u
s
t sco
r
e:
co
m
b
i
n
es
co
n
n
ec
tiv
ity
an
d
r
atin
g
d
ev
iatio
n
.
T
h
e
item
tr
u
s
t sco
r
e
is
d
ef
in
e
d
in
(
6
)
.
=
×
(
6
)
Hy
b
r
id
r
ec
o
m
m
en
d
er
:
th
e
h
y
b
r
id
m
o
d
u
le
d
y
n
am
ically
weig
h
ts
u
s
er
-
b
ased
an
d
i
tem
-
b
ased
p
r
ed
ictio
n
s
to
g
en
er
ate
f
i
n
al
r
e
co
m
m
en
d
atio
n
s
[
1
3
]
.
I
t e
m
p
lo
y
s
a
co
n
tex
t
-
awa
r
e
weig
h
tin
g
m
ec
h
an
is
m
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
TAHR
F
:
en
h
a
n
ci
n
g
p
ers
o
n
a
liz
ed
to
u
r
is
m
r
ec
o
mme
n
d
a
tio
n
s
w
ith
d
yn
a
mic
a
d
a
p
ta
tio
n
(
Mo
h
a
med
B
a
d
o
u
c
h
)
377
i)
U
s
e
r
-
i
t
e
m
p
r
e
d
i
c
t
i
o
n
:
c
o
m
p
u
t
e
s
p
r
e
d
i
c
t
e
d
r
a
t
i
n
g
s
f
o
r
u
s
e
r
x
a
n
d
i
t
e
m
i
.
T
h
e
p
r
e
d
i
c
t
i
o
n
i
s
c
o
m
p
u
t
e
d
a
s
i
n
(
7
)
.
,
=
̅
+
∑
,
∈
×
(
,
−
̅
)
(
7
)
ii)
Hy
b
r
id
weig
h
tin
g
:
co
m
b
in
es
u
s
er
an
d
item
p
r
e
d
ictio
n
s
.
T
h
e
f
in
al
p
r
ed
ictio
n
is
d
e
f
in
ed
i
n
(
8
)
.
,
=
⋅
,
+
(
1
−
α
)
⋅
,
(
8
)
W
h
er
e
α
is
a
d
y
n
am
ic
weig
h
t
ad
ju
s
ted
b
ased
o
n
d
ata
d
e
n
s
ity
an
d
u
s
er
f
ee
d
b
ac
k
.
R
a
th
e
r
th
a
n
b
ei
n
g
le
ar
n
e
d
,
α
is
u
p
d
at
ed
h
eu
r
i
s
t
ic
al
ly
i
n
o
u
r
im
p
l
em
en
t
at
io
n
.
W
e
b
eg
in
wi
th
α
=0
.
5
a
n
d
m
o
d
if
y
it
ac
co
r
d
in
g
to
th
e
s
itu
at
io
n
:
α
is
r
a
i
s
ed
f
o
r
u
s
er
s
wi
th
s
p
ar
s
e
d
at
a
(
f
ew
r
at
in
g
s
)
to
r
ely
m
o
r
e
o
n
tr
u
s
t
-
b
a
s
ed
p
r
ed
ic
ti
o
n
s
,
wh
i
le
α
i
s
lo
w
er
ed
f
o
r
ac
t
iv
e
u
s
er
s
wi
th
m
an
y
r
a
tin
g
s
to
f
av
o
r
d
i
r
ec
t
r
at
in
g
-
b
as
ed
p
r
ed
i
ct
io
n
s
.
T
A
H
R
F
i
s
ab
le
to
ad
ap
tiv
ely
b
ala
n
ce
tr
u
s
t
v
s
.
r
at
in
g
in
p
u
t
s
th
an
k
s
to
th
i
s
s
t
r
a
ig
h
tf
o
r
w
ar
d
f
ee
d
b
ac
k
-
d
r
iv
en
m
e
ch
an
i
s
m
.
Fu
t
u
r
e
r
e
s
ea
r
c
h
is
le
f
t
to
d
e
ter
m
in
e
th
e
id
ea
l
α
u
s
in
g
m
e
th
o
d
s
lik
e
r
e
in
f
o
r
ce
m
en
t l
ea
r
n
in
g
.
2
.
2
.
T
rus
t
a
nd
m
ulti
-
cr
it
er
ia
m
et
rics
T
h
e
tr
u
s
t
a
n
d
m
u
lti
-
cr
iter
ia
m
etr
ics
m
o
d
u
le
s
er
v
e
as
a
b
a
s
ic
lay
er
in
th
e
p
r
o
p
o
s
ed
a
r
c
h
itectu
r
e.
I
t
im
p
r
o
v
es
p
r
ed
ictiv
e
m
o
d
elin
g
b
y
u
s
in
g
ad
v
an
ce
d
u
s
er
s
im
ilar
ity
p
r
ed
ictio
n
s
an
d
item
-
lev
el
r
eliab
ilit
y
esti
m
atio
n
.
I
n
th
e
u
s
er
m
o
d
elin
g
p
r
o
ce
s
s
,
d
ir
ec
t
tr
u
s
t
is
ca
lcu
lated
b
y
co
m
b
in
in
g
E
u
clid
ea
n
d
is
tan
ce
-
b
ased
s
im
ilar
ity
an
d
th
e
J
ac
ca
r
d
co
n
f
id
en
ce
c
o
ef
f
icien
t.
T
h
ese
ar
e
two
well
-
k
n
o
wn
m
eth
o
d
s
f
o
r
m
ea
s
u
r
in
g
s
im
ilar
ity
.
T
h
is
co
m
b
in
ed
m
etr
ic
ca
p
tu
r
es
b
o
th
th
e
n
u
m
er
i
ca
l
alig
n
m
en
t
o
f
u
s
er
r
atin
g
s
an
d
th
e
co
-
r
atin
g
d
en
s
ity
.
I
t stre
n
g
th
e
n
s
u
s
er
p
r
o
f
ilin
g
in
s
p
ar
s
e
e
n
v
ir
o
n
m
en
ts
.
W
h
e
n
e
x
p
l
i
c
i
t
l
i
n
k
s
a
r
e
l
a
c
k
i
n
g
,
t
h
e
s
y
s
t
e
m
e
m
p
l
o
y
s
t
r
u
s
t
p
r
o
p
a
g
a
t
i
o
n
[
1
4
]
,
a
g
r
a
p
h
-
t
h
e
o
r
e
t
i
c
c
o
n
s
t
r
u
c
t
t
h
a
t
t
r
a
v
e
r
s
e
s
t
h
e
u
s
e
r
-
u
s
e
r
t
r
u
s
t
n
e
t
w
o
r
k
v
i
a
t
r
a
n
s
i
t
i
v
e
i
n
f
e
r
e
n
c
e
o
v
e
r
c
o
m
m
o
n
n
e
i
g
h
b
o
r
s
.
T
h
i
s
f
o
r
m
o
f
g
r
a
p
h
-
b
a
s
e
d
t
r
u
s
t
m
o
d
e
l
i
n
g
a
l
l
o
w
s
t
h
e
r
e
c
o
m
m
e
n
d
e
r
s
y
s
t
e
m
t
o
b
r
i
d
g
e
s
t
r
u
c
t
u
r
a
l
h
o
l
e
s
a
n
d
e
n
h
a
n
c
e
c
o
l
l
a
b
o
r
a
t
i
v
e
s
i
g
n
a
l
a
m
p
l
i
f
i
c
a
t
i
o
n
.
A
n
o
v
e
r
a
l
l
u
s
e
r
t
r
u
s
t
s
c
o
r
e
i
s
a
l
s
o
d
e
r
i
v
e
d
u
s
i
n
g
r
a
t
i
n
g
v
a
r
i
a
n
c
e
a
n
d
n
e
t
w
o
r
k
c
e
n
t
r
a
l
i
t
y
,
w
h
i
c
h
e
f
f
e
c
t
i
v
e
l
y
m
o
d
u
l
a
t
e
u
s
e
r
i
n
f
l
u
e
n
c
e
w
i
t
h
i
n
t
h
e
c
o
l
l
a
b
o
r
a
t
i
v
e
f
i
l
t
e
r
i
n
g
g
r
a
p
h
.
A
t
t
h
e
i
t
e
m
l
e
v
e
l
,
t
h
e
m
o
d
e
l
a
s
s
e
s
s
e
s
i
t
e
m
t
r
u
s
t
w
o
r
t
h
i
n
e
s
s
b
a
s
e
d
o
n
i
t
e
m
c
o
n
n
e
c
t
i
v
i
t
y
m
e
t
r
i
c
s
a
n
d
r
a
t
i
n
g
c
o
n
s
i
s
t
e
n
c
y
a
n
a
l
y
s
i
s
.
I
t
e
v
a
l
u
a
t
e
s
c
o
n
n
e
c
t
i
v
i
t
y
u
s
i
n
g
n
o
r
m
a
l
i
z
e
d
d
e
g
r
e
e
c
e
n
t
r
a
l
i
t
y
i
n
t
h
e
i
t
e
m
-
i
t
e
m
g
r
a
p
h
.
C
o
n
s
i
s
t
e
n
c
y
i
s
m
e
a
s
u
r
e
d
b
y
a
p
p
l
y
i
n
g
e
x
p
o
n
e
n
t
i
a
l
s
m
o
o
t
h
i
n
g
t
o
r
a
t
i
n
g
d
e
v
i
a
t
i
o
n
s
,
h
i
g
h
l
i
g
h
t
i
n
g
t
h
e
s
t
a
t
i
s
t
i
c
a
l
r
e
l
i
a
b
i
l
i
t
y
o
f
i
t
e
m
e
v
a
l
u
a
t
i
o
n
s
.
T
h
e
s
e
m
e
t
r
i
c
s
c
o
m
b
i
n
e
i
n
t
o
a
s
i
n
g
l
e
i
t
e
m
t
r
u
s
t
s
c
o
r
e
,
w
h
i
c
h
h
e
l
p
s
a
d
d
r
e
s
s
t
h
e
c
o
l
d
-
s
t
a
r
t
i
t
e
m
p
r
o
b
l
e
m
e
f
f
e
c
t
i
v
e
l
y
[
1
5
]
.
H
o
w
e
v
e
r
,
p
r
o
p
a
g
a
t
i
n
g
t
r
u
s
t
t
h
r
o
u
g
h
l
a
r
g
e
u
s
e
r
n
e
t
w
o
r
k
s
c
a
n
i
n
t
r
o
d
u
c
e
c
o
m
p
u
t
a
t
i
o
n
a
l
c
o
m
p
l
e
x
i
t
y
;
h
e
n
c
e
,
w
e
l
i
m
i
t
p
r
o
p
a
g
a
t
i
o
n
d
e
p
t
h
(
e
.
g
.
,
t
o
2
-
h
o
p
n
e
i
g
h
b
o
r
s
)
a
n
d
e
m
p
l
o
y
e
f
f
i
c
i
e
n
t
s
p
a
r
s
e
m
a
t
r
i
x
o
p
e
r
a
t
i
o
n
s
t
o
m
a
i
n
t
a
i
n
s
c
a
l
a
b
i
l
i
t
y
.
I
n
p
a
r
a
l
l
e
l
,
t
h
e
m
o
d
e
l
c
o
m
b
i
n
e
s
m
u
l
t
i
-
a
s
p
e
c
t
r
a
t
i
n
g
a
n
a
l
y
s
i
s
,
a
l
l
o
w
i
n
g
d
e
t
a
i
l
e
d
s
e
n
t
i
m
e
n
t
m
e
a
s
u
r
e
m
e
n
t
a
c
r
o
s
s
v
a
r
i
o
u
s
a
s
p
e
c
t
s
o
f
u
s
e
r
e
x
p
e
r
i
e
n
c
e
.
E
a
c
h
c
r
i
t
e
r
i
o
n
,
s
u
c
h
a
s
s
e
r
v
i
c
e
q
u
a
l
i
t
y
o
r
l
o
c
a
t
i
o
n
,
i
s
p
r
o
c
e
s
s
e
d
i
n
d
e
p
e
n
d
e
n
t
l
y
u
s
i
n
g
t
r
u
s
t
-
w
e
i
g
h
t
e
d
c
o
l
l
a
b
o
r
a
t
i
v
e
f
i
l
t
e
r
i
n
g
.
T
h
e
p
r
e
d
i
c
t
i
o
n
s
a
r
e
t
h
e
n
b
l
e
n
d
e
d
w
i
t
h
a
d
a
p
t
i
v
e
w
e
i
g
h
t
i
n
g
f
u
n
c
t
i
o
n
s
t
h
a
t
r
e
a
c
t
t
o
c
o
n
t
e
x
t
u
a
l
/
o
t
h
e
r
v
a
r
i
a
b
l
e
s
a
n
d
u
s
e
r
f
e
e
d
b
a
c
k
.
T
h
e
m
u
l
t
i
-
l
a
y
e
r
t
r
u
s
t
m
o
d
e
l
i
n
g
f
r
a
m
e
w
o
r
k
p
r
o
v
i
d
e
s
e
n
h
a
n
c
e
d
p
r
e
c
i
s
i
o
n
,
e
n
h
a
n
c
e
d
c
o
v
e
r
a
g
e
,
a
n
d
e
n
h
a
n
c
e
d
r
o
b
u
s
t
n
e
s
s
t
o
s
p
a
r
s
i
t
y
r
e
c
o
m
m
e
n
d
a
t
i
o
n
s
.
T
h
i
s
f
r
a
m
e
w
o
r
k
i
s
s
u
i
t
a
b
l
e
t
o
r
e
a
l
-
t
i
m
e
d
e
c
i
s
i
o
n
s
u
p
p
o
r
t
i
n
p
e
r
s
o
n
a
l
i
z
e
d
s
c
e
n
a
r
i
o
s
s
u
c
h
a
s
t
o
u
r
i
s
m
f
o
r
e
x
a
m
p
l
e
.
i)
User
tr
u
s
t
s
co
r
e:
d
ir
ec
t
tr
u
s
t
c
o
m
b
in
es
E
u
clid
ea
n
s
im
ilar
ity
an
d
J
ac
ca
r
d
c
o
n
f
i
d
en
ce
.
T
h
e
f
o
r
m
u
latio
n
o
f
d
ir
ec
t u
s
er
tr
u
s
t is g
iv
en
i
n
(
9
)
.
,
=
,
×
,
(
9
)
ii)
I
tem
tr
u
s
t sco
r
e:
item
co
n
n
ec
tiv
ity
an
d
r
atin
g
b
e
h
av
io
r
.
T
h
e
i
tem
tr
u
s
t sco
r
e
is
d
ef
in
ed
i
n
(
1
0
)
.
=
e
xp
(
−
∑
|
,
−
̅
̅
̅
|
|
|
)
×
√
|
|
|
|
(
1
0
)
2
.
3
.
Dy
na
m
ic
a
da
pt
a
t
io
n
A
d
a
p
t
ab
i
l
i
t
y
i
s
a
m
a
jo
r
a
t
t
r
ib
u
t
e
o
f
r
e
co
m
m
e
n
d
a
t
i
o
n
s
y
s
t
e
m
.
I
t
i
s
t
h
e
a
t
t
r
ib
u
t
e
a
l
l
o
w
i
n
g
i
t
to
f
a
c
i
l
i
t
a
t
e
r
e
a
l
-
t
im
e
p
e
r
s
o
n
a
l
iz
a
t
i
o
n
in
r
e
l
a
t
i
o
n
t
o
c
h
an
g
in
g
u
s
e
r
p
r
ef
e
r
en
c
e
,
w
h
a
t
ev
er
t
h
o
s
e
p
r
e
f
er
e
n
ce
s
m
a
y
b
e
.
T
h
e
r
e
ar
e
a
l
w
ay
s
r
e
c
o
m
m
e
n
d
a
t
i
o
n
s
y
s
t
e
m
s
t
h
a
t
c
a
n
o
n
l
y
r
e
l
y
o
n
s
t
a
t
i
c
u
s
e
r
p
r
o
f
i
l
e
o
r
p
a
s
t
b
e
h
av
i
o
r
;
t
h
u
s
,
l
im
i
t
i
n
g
t
h
e
m
s
e
l
v
e
s
t
o
co
n
s
tr
a
i
n
in
g
f
a
c
to
r
s
t
h
a
t
p
r
ev
e
n
t
t
h
em
f
r
o
m
r
e
s
p
o
n
d
in
g
t
o
d
y
n
a
m
ic
c
o
n
t
ex
t
o
r
c
i
r
cu
m
s
t
a
n
c
e
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
:
374
-
3
8
2
378
Ou
r
r
ec
o
m
m
en
d
atio
n
s
y
s
tem
in
tr
o
d
u
ce
s
an
in
ter
ac
tiv
e
in
ter
f
ac
e
f
o
r
u
s
er
s
to
alter
th
eir
o
p
tim
al
p
r
ef
er
en
ce
f
ac
to
r
s
-
b
y
co
llab
o
r
ativ
ely
s
lid
in
g
d
esig
n
atio
n
s
o
f
b
u
d
g
et,
in
ter
est
in
ac
tiv
iti
es,
ex
p
ec
ted
tr
av
el
s
ea
s
o
n
,
o
r
ty
p
e
o
f
g
r
o
u
p
.
W
h
en
th
e
u
s
er
s
ch
a
n
g
e
s
o
m
e
v
alu
es,
th
e
s
y
s
tem
r
ec
u
r
s
iv
ely
ca
lcu
lates
th
e
r
ec
o
m
m
en
d
atio
n
s
s
co
r
es
b
ased
o
n
th
e
h
y
b
r
id
tr
u
s
t
-
b
ased
m
o
d
el
in
r
ea
l
tim
e,
i.e
.
,
with
o
u
t
r
ef
r
esh
in
g
th
e
p
a
g
e
an
d
with
o
u
t
ask
in
g
f
o
r
m
o
r
e
in
f
o
r
m
atio
n
f
r
o
m
th
e
u
s
er
s
with
in
th
e
s
ec
o
n
d
s
,
th
e
n
ew
in
p
u
t
v
al
u
e
will
b
e
d
ep
icted
in
an
in
-
b
u
ilt
in
ter
ac
tiv
e
m
ap
,
w
h
er
e
th
e
co
lo
r
s
r
e
p
r
esen
t
th
e
g
o
o
d
n
ess
ac
r
o
s
s
g
eo
s
p
atial
d
if
f
er
en
t
r
eg
io
n
s
.
A
r
ea
s
p
ain
ted
g
r
ee
n
ar
e
h
ig
h
ly
r
ated
d
esti
n
atio
n
s
,
an
d
a
r
ea
s
p
ain
ted
in
s
h
ad
es
o
f
war
m
co
lo
r
s
f
r
o
m
y
ello
w
to
r
ed
d
iv
e
r
g
e
in
cr
ea
s
in
g
ly
f
r
o
m
th
e
cu
r
r
en
t
s
et
o
f
u
s
er
p
r
ef
e
r
en
ce
s
.
T
h
is
liv
e
f
ee
d
b
ac
k
c
o
lo
r
in
g
g
iv
es
th
e
u
s
er
an
o
p
tio
n
to
tr
ad
e
o
f
f
b
etwe
en
f
ac
to
r
s
,
i.e
.
,
co
s
t
ag
ain
s
t
d
is
tan
ce
o
r
en
ter
tain
m
en
t
ag
ain
s
t
f
am
ily
-
f
r
ien
d
lin
ess
.
T
h
is
m
ap
,
s
u
itab
ly
co
lo
r
ed
with
in
d
icatin
g
s
ites
,
g
u
id
es
th
e
ch
o
ice
th
r
o
u
g
h
v
is
u
al
co
g
n
itio
n
as
well
as
f
ac
ilit
ate
s
tr
an
s
p
ar
en
c
y
b
ec
au
s
e
th
e
u
s
er
ca
n
m
a
k
e
s
en
s
e
o
f
wh
y
s
o
m
e
o
p
tio
n
s
ar
e
b
ein
g
p
r
o
p
o
s
ed
an
d
o
th
er
s
ar
e
n
o
t.
As
th
e
cu
r
r
en
t
p
r
ef
er
e
n
ce
m
ec
h
an
is
m
allo
ws
f
o
r
wh
o
lesale
ch
an
g
es
in
p
r
ef
e
r
en
ce
,
it
is
ap
p
licab
le
to
to
u
r
an
d
tr
av
el
p
la
n
n
in
g
.
T
h
e
p
r
ef
er
en
ce
o
f
a
tr
a
v
eler
co
u
ld
ch
an
g
e
in
a
n
in
s
tan
t
f
r
o
m
a
w
ea
th
er
f
o
r
ec
ast
f
o
r
a
lo
ca
tio
n
,
to
a
ch
an
g
e
in
b
u
d
g
e
t,
ev
en
f
r
o
m
i
n
p
u
t
b
y
o
th
e
r
g
r
o
u
p
m
em
b
e
r
s
.
W
ith
a
d
y
n
a
m
ic
r
e
-
r
a
n
k
in
g
ca
p
a
b
le
s
y
s
tem
[
1
6
]
th
at
ca
n
m
a
k
e
s
m
all
ad
ju
s
tm
en
ts
to
ch
an
g
e
s
in
co
n
tex
t
asy
n
ch
r
o
n
o
u
s
ly
wh
ile
th
e
u
s
er
is
b
r
o
wsi
n
g
,
it c
o
u
ld
k
ee
p
its
s
u
g
g
esti
o
n
s
r
elev
an
t a
n
d
u
p
-
to
-
d
a
te
co
n
s
is
ten
t w
ith
th
e
u
s
er
'
s
in
t
en
tio
n
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
Da
t
a
s
et
s
a
nd
m
et
rics
T
h
e
d
atasets
f
r
o
m
T
r
ip
A
d
v
is
o
r
co
n
s
is
t
o
f
1
4
,
6
3
3
r
estau
r
an
t
r
atin
g
s
with
r
atin
g
s
u
p
to
th
r
e
e
cr
iter
ia,
an
d
2
8
,
8
2
9
h
o
tel
r
atin
g
s
with
r
atin
g
s
as
p
er
s
ev
en
cr
iter
ia.
T
h
is
m
ix
ed
r
ep
r
esen
tatio
n
o
f
d
o
m
ain
s
h
as
en
ab
led
a
b
r
o
a
d
ex
p
l
o
r
atio
n
o
f
u
s
er
p
r
ef
er
e
n
ce
s
in
ter
m
s
o
f
d
i
n
in
g
an
d
ac
co
m
m
o
d
atio
n
e
x
p
er
ien
ce
s
.
Mo
d
el
p
er
f
o
r
m
an
ce
s
wer
e
ev
alu
ated
,
in
g
en
er
al,
u
s
in
g
MA
E
an
d
co
v
er
ag
e
r
ate.
MA
E
m
ea
s
u
r
es
th
e
ab
s
o
lu
te
av
er
ag
e
s
ize
o
f
th
e
er
r
o
r
s
in
a
s
et
o
f
p
r
ed
ictio
n
s
[
1
7
]
,
wh
er
ea
s
co
v
er
ag
e
r
ate
co
m
m
u
n
icate
s
th
e
co
v
er
ag
e
r
ate
as
a
p
er
ce
n
tag
e
at
wh
ic
h
item
s
ca
n
b
e
r
ec
o
m
m
en
d
e
d
to
a
u
s
er
.
T
h
is
s
tatis
tic
th
en
in
d
icate
s
th
e
ab
ilit
y
o
f
a
m
o
d
el
to
s
p
r
ea
d
its
p
r
e
d
ictio
n
s
ac
r
o
s
s
a
r
an
g
e
o
f
item
s
.
I
n
ad
d
itio
n
,
we
c
o
m
p
u
ted
to
p
-
K
r
an
k
in
g
m
etr
ics
(
p
r
ec
is
io
n
@
5
,
NDCG@
5
)
f
o
r
a
m
o
r
e
co
m
p
r
eh
en
s
iv
e
ev
alu
atio
n
,
a
n
d
p
er
f
o
r
m
ed
s
tatis
tical
s
ig
n
if
ican
ce
test
in
g
(
p
air
ed
t
-
test
s
)
o
n
th
e
r
esu
lts
to
v
alid
ate
th
e
im
p
r
o
v
e
m
en
ts
.
3
.
2
.
B
enchm
a
r
k
co
m
pa
riso
n
T
ab
le
2
g
iv
es
th
e
r
esu
lts
f
o
r
o
u
r
b
en
c
h
m
ar
k
co
m
p
ar
is
o
n
,
s
h
o
win
g
th
e
a
d
v
an
ta
g
e
th
at
th
e
T
AHRF
m
o
d
el
h
as
o
v
er
in
co
m
p
a
r
is
o
n
to
o
th
e
r
m
eth
o
d
s
s
u
ch
as
m
u
lti
-
cr
iter
ia
u
s
er
-
b
ased
c
o
l
lab
o
r
ativ
e
f
ilter
in
g
(
MC
-
UC
F)
an
d
m
u
lti
-
cr
iter
i
a
item
-
b
ased
co
llab
o
r
ativ
e
f
i
lter
in
g
(
MC
-
I
C
F)
,
th
e
r
esu
lt
s
d
em
o
n
s
tr
ate
th
at
T
AHRF
ac
h
iev
es
s
u
p
er
io
r
p
er
f
o
r
m
a
n
ce
ac
r
o
s
s
m
u
ltip
le
m
etr
ics.
T
AHR
F
ac
h
iev
ed
an
MA
E
o
f
0
.
9
8
f
o
r
r
estau
r
an
t
r
atin
g
s
,
w
h
ich
is
f
a
r
lo
wer
th
a
n
1
.
1
7
o
f
th
e
MC
-
UC
F,
with
th
e
s
am
e
th
in
g
h
o
ld
in
g
f
o
r
MA
E
f
o
r
h
o
tel
r
atin
g
s
o
f
0
.
7
1
v
e
r
s
u
s
1
.
2
0
o
f
th
e
MC
-
UC
F.
T
h
e
ac
cu
r
ac
y
an
d
ef
f
ec
tiv
e
n
ess
o
f
th
e
T
AHRF
m
o
d
el
ar
e
ev
id
en
t
in
eith
er
d
o
m
ain
.
Similar
ly
,
T
AHRF
ac
h
iev
ed
h
i
g
h
er
p
r
ec
is
io
n
@
5
an
d
NDCG@
5
th
an
th
e
b
est
b
aselin
e,
in
d
icatin
g
s
u
p
e
r
io
r
r
an
k
in
g
o
f
r
ele
v
an
t item
s
.
T
ab
le
2
.
T
AHRF
o
u
tp
er
f
o
r
m
s
MC
-
UC
F,
MC
-
I
C
F,
an
d
MC
-
T
eCF
Me
th
o
d
MA
E
(
r
estau
r
an
ts
)
MA
E
(
h
o
tels
)
MC
-
UC
F
1
.
1
7
1
.
2
0
MC
-
I
C
F
1
.
0
6
1
.
1
2
MC
-
T
eCF
1
.
0
1
0
.
9
3
T
AHRF
(
o
u
r
s
)
0
.
9
8
0
.
7
1
3
.
3
.
Sp
a
rsity
a
na
l
y
s
is
Sp
ar
s
e
u
s
er
-
item
m
atr
ices
n
o
w
p
o
s
e
a
m
ajo
r
im
p
ed
im
e
n
t
to
th
e
d
ev
el
o
p
m
en
t
o
f
c
o
llab
o
r
ativ
e
f
ilter
in
g
r
ec
o
m
m
e
n
d
er
s
y
s
tem
s
;
u
s
er
s
m
ay
p
r
o
v
id
e
o
n
ly
a
h
an
d
f
u
l
o
f
r
atin
g
s
.
T
h
e
r
ef
o
r
e
,
it
is
u
n
ten
ab
le
to
co
n
d
u
ct
an
y
v
iab
le
s
im
ilar
ity
co
m
p
u
tatio
n
o
r
p
r
ef
er
e
n
ce
s
.
T
o
ev
alu
ate
r
ig
o
r
o
u
s
ly
th
e
ex
ten
t
to
wh
ich
o
u
r
p
r
o
p
o
s
ed
T
AHRF
wa
s
s
u
b
je
cted
to
th
e
ad
v
er
s
e
ef
f
ec
ts
im
p
o
s
ed
b
y
s
u
ch
co
n
s
tr
ain
ts
,
a
d
etailed
s
p
ar
s
ity
an
aly
s
is
was c
ar
r
ied
o
u
t u
s
in
g
ex
tr
em
ely
s
p
ar
s
e
d
atasets
o
b
ta
in
ed
f
r
o
m
r
ea
l T
r
i
p
Ad
v
is
o
r
r
e
v
iews.
I
n
p
r
ac
tice,
th
e
s
itu
atio
n
b
ein
g
r
elied
u
p
o
n
was
o
n
th
e
b
asi
s
o
f
a
th
eo
r
y
th
at
d
e
f
in
ed
a
n
o
d
e
lim
it
o
f
9
9
.
8
%
s
p
ar
s
ity
,
im
p
ly
in
g
less
th
an
0
.
2
%
o
f
all
p
o
s
s
ib
le
in
ter
ac
tio
n
s
wer
e
o
b
s
er
v
ed
ac
co
r
d
i
n
g
to
th
e
u
s
er
s
an
d
item
s
.
Mo
r
eo
v
er
,
at
th
is
lev
el
o
f
s
p
ar
s
ity
,
co
n
v
e
n
tio
n
al
C
F
d
esig
n
s
d
eliv
er
ed
m
ea
n
in
g
less
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 Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
TAHR
F
:
en
h
a
n
ci
n
g
p
ers
o
n
a
liz
ed
to
u
r
is
m
r
ec
o
mme
n
d
a
tio
n
s
w
ith
d
yn
a
mic
a
d
a
p
ta
tio
n
(
Mo
h
a
med
B
a
d
o
u
c
h
)
379
as th
ey
ar
e
n
o
t
b
ased
u
p
o
n
a
d
e
q
u
ate
am
o
u
n
ts
o
f
o
v
er
lap
p
in
g
d
ata.
I
n
tr
u
th
,
th
e
T
AHRF
p
er
f
o
r
m
ed
well;
it h
ad
a
co
v
er
a
g
e
r
ate
o
f
as
h
ig
h
as
8
9
%,
in
d
icatin
g
th
at
in
lo
w
s
p
ar
s
ity
s
itu
atio
n
s
,
it
co
u
ld
al
m
o
s
t
r
ec
o
m
m
e
n
d
f
o
r
n
in
e
item
p
o
o
ls
o
u
t o
f
te
n
.
T
h
e
co
m
p
etito
r
,
at
t
h
e
s
am
e
tim
e,
m
u
lti
-
cr
iter
ia
ten
s
o
r
-
b
ased
co
llab
o
r
ativ
e
f
ilter
in
g
(
MC
-
T
eCF
)
h
ad
co
v
er
ag
e
o
f
4
1
%,
h
o
wev
er
t
h
e
lev
els
o
f
c
o
v
er
ag
e
s
er
v
e
d
to
illu
s
tr
ate
its
wea
k
n
ess
es
wh
en
s
u
b
jecte
d
to
ex
tr
em
e
lev
els o
f
s
p
ar
s
ity
.
T
h
e
s
u
p
er
io
r
p
er
f
o
r
m
a
n
ce
o
f
T
AHRF
m
ay
b
e
attr
ib
u
ted
t
o
a
s
p
ec
if
ic
co
llectio
n
o
f
ar
c
h
itectu
r
al
in
n
o
v
atio
n
s
.
First,
th
e
ab
ilit
y
to
let
tr
u
s
t
s
p
r
ea
d
ac
r
o
s
s
b
o
th
item
an
d
u
s
er
n
etwo
r
k
s
en
ab
les
th
e
m
o
d
el
to
cir
cu
m
v
en
t
d
ata
s
p
ar
s
ity
th
r
o
u
g
h
t
h
e
u
s
e
o
f
in
d
ir
ec
t
co
n
n
ec
tio
n
s
.
Seco
n
d
,
d
esp
ite
ex
tr
em
ely
lim
ited
u
s
er
r
atin
g
s
,
th
e
item
co
n
n
ec
tiv
ity
s
co
r
es
an
d
r
atin
g
d
e
v
iatio
n
m
etr
ics
en
a
b
le
it
to
ac
cu
r
ately
id
en
tify
item
p
r
ef
er
en
ce
s
r
eliab
ly
.
B
y
allo
w
in
g
th
e
alg
o
r
ith
m
to
m
o
v
e
o
v
e
r
th
e
s
p
ar
s
e
in
ter
ac
tio
n
g
r
ap
h
o
f
u
s
er
s
an
d
item
s
,
th
is
p
r
o
v
id
es
th
e
alg
o
r
ith
m
with
a
wid
er
an
d
co
n
te
x
tu
al
s
p
ac
e
o
f
o
p
tio
n
s
to
r
ec
o
m
m
e
n
d
.
Ou
r
e
x
p
er
im
en
t
v
er
if
ies
th
at
T
AHRF
is
a
s
im
p
le
-
to
-
im
p
lem
e
n
t
s
o
lu
tio
n
f
o
r
r
ea
l
-
wo
r
ld
p
r
o
b
le
m
s
,
esp
ec
ially
in
s
ce
n
ar
io
s
o
f
h
ig
h
u
s
er
attr
itio
n
,
s
p
ar
s
e
f
ee
d
b
ac
k
,
a
n
d
th
e
co
ld
-
s
tar
t
is
s
u
e.
Hav
in
g
ac
h
iev
ed
s
u
c
h
a
g
o
o
d
c
o
v
er
ag
e
s
co
r
e
u
n
d
er
s
p
ec
if
ied
s
p
ar
s
ity
lev
els
d
em
o
n
s
tr
ated
th
e
s
ca
lab
ilit
y
o
f
th
e
m
o
d
el
i
n
a
d
o
m
ain
-
i
n
d
e
p
en
d
en
t
m
an
n
e
r
,
as
well
as
i
ts
ab
ili
ty
to
lear
n
an
d
p
r
o
b
lem
-
s
o
lv
e
u
n
d
er
h
ig
h
l
y
d
ata
-
p
o
o
r
an
d
d
y
n
am
ic
en
v
ir
o
n
m
en
ts
,
s
u
ch
as
ex
p
er
ien
ce
d
with
in
th
e
to
u
r
is
m
in
d
u
s
tr
y
.
3
.
4
.
T
rus
t
pro
pa
g
a
t
io
n
T
r
u
s
t
p
r
o
p
ag
atio
n
s
er
v
es
as
a
co
r
n
e
r
s
to
n
e
m
ec
h
an
is
m
with
in
th
e
T
AHRF
f
r
am
ew
o
r
k
,
s
p
ec
if
ically
d
esig
n
ed
to
m
itig
ate
o
n
e
o
f
t
h
e
m
o
s
t
p
er
s
is
ten
t
ch
allen
g
es
in
r
ec
o
m
m
e
n
d
er
s
y
s
tem
s
:
th
e
co
ld
-
s
tar
t
p
r
o
b
lem
[
1
8
]
.
C
o
ld
-
s
tar
t
u
s
er
s
,
ty
p
ical
ly
ch
ar
ac
ter
ized
b
y
s
p
a
r
s
e
o
r
n
o
n
ex
is
ten
t
r
atin
g
h
is
to
r
ies,
p
o
s
e
a
co
n
s
id
er
ab
le
b
ar
r
ier
to
r
eliab
le
p
r
ef
er
en
c
e
in
f
er
en
ce
in
co
llab
o
r
ativ
e
f
ilter
in
g
m
o
d
els.
T
o
a
d
d
r
e
s
s
th
is
,
o
u
r
s
y
s
tem
in
co
r
p
o
r
ates
a
g
r
ap
h
-
b
ased
tr
u
s
t
p
r
o
p
ag
atio
n
s
tr
ateg
y
th
at
in
f
er
s
tr
u
s
t
r
elatio
n
s
h
ip
s
ev
en
in
th
e
ab
s
en
ce
o
f
d
ir
ec
t u
s
er
in
ter
ac
tio
n
s
.
T
h
e
p
r
in
cip
le
o
f
tr
u
s
t p
r
o
p
a
g
atio
n
is
g
r
o
u
n
d
ed
in
tr
a
n
s
itiv
e
lo
g
ic,
wh
er
ein
tr
u
s
t c
an
b
e
tr
an
s
m
itted
ac
r
o
s
s
a
u
s
er
-
u
s
er
tr
u
s
t
g
r
ap
h
v
ia
s
h
ar
ed
in
ter
m
e
d
iar
ies.
Fo
r
ex
am
p
le,
if
u
s
er
A
tr
u
s
ts
u
s
er
B
,
u
s
er
B
tr
u
s
ts
u
s
er
C
,
th
en
u
s
er
A
m
ay
tr
u
s
t
u
s
er
C
in
a
less
d
ir
e
ct
way
.
W
e
f
o
r
m
ally
ch
ar
ac
te
r
ized
tr
an
s
itiv
e
tr
u
s
t
u
s
in
g
a
r
ec
u
r
s
iv
e
m
atr
ix
o
p
er
a
to
r
to
co
m
p
u
te
in
d
ir
ec
t
tr
u
s
t
s
co
r
es
eith
er
to
an
ar
b
itra
r
y
n
u
m
b
er
o
f
h
o
p
s
.
T
h
is
allo
ws
th
e
ef
f
ec
t
o
f
well
-
co
n
n
ec
ted
h
ig
h
-
q
u
ality
u
s
er
s
to
in
f
lu
en
ce
u
s
er
s
th
at
ar
e
f
u
r
th
e
r
o
u
t
in
th
e
n
etwo
r
k
.
W
e
f
o
r
m
ally
c
h
ar
ac
ter
ized
tr
a
n
s
itiv
e
tr
u
s
t
u
s
in
g
a
r
ec
u
r
s
iv
e
m
atr
ix
o
p
er
at
o
r
o
v
er
m
u
ltip
l
e
h
o
p
s
an
d
ex
ten
d
th
e
in
f
lu
en
ce
o
f
well
-
co
n
n
ec
te
d
u
s
er
s
to
u
s
er
s
th
at
ar
e
f
u
r
th
e
r
o
u
t in
t
h
e
n
etwo
r
k
.
T
h
e
e
f
f
i
c
a
cy
o
f
t
h
e
m
e
th
o
d
i
s
v
o
u
ch
ed
f
o
r
b
y
r
ed
u
c
t
io
n
r
e
s
u
l
t
s
o
f
1
4
t
o
4
0
%
i
n
M
A
E
,
w
h
e
r
e
tr
u
s
t
p
r
o
p
ag
a
t
i
o
n
wa
s
p
e
r
f
o
r
m
e
d
o
n
a
l
l
4
e
x
p
e
r
im
en
t
s
e
t
s
o
f
d
a
ta
.
T
h
i
s
d
r
a
s
t
i
c
r
i
s
e
o
f
p
r
e
d
i
c
t
iv
e
a
c
cu
r
a
cy
e
v
i
d
en
c
e
co
n
f
i
r
m
s
s
o
d
r
am
at
i
c
a
l
l
y
h
o
w
t
r
u
s
t
p
r
o
p
ag
a
t
io
n
c
a
n
o
f
f
s
e
t
t
h
e
i
m
p
a
c
t
o
f
s
m
a
l
l
d
a
t
a
,
a
s
a
l
s
o
i
n
c
o
m
p
l
e
t
e
u
s
er
h
i
s
t
o
r
i
e
s
.
O
v
e
r
a
l
l,
th
i
s
m
e
th
o
d
co
u
ld
p
r
o
v
i
d
e
co
n
t
ex
t
u
a
l
l
y
r
e
le
v
a
n
t
p
er
s
o
n
a
l
i
z
ed
r
e
c
o
m
m
en
d
a
t
io
n
s
to
o
c
c
a
s
io
n
a
l
o
r
n
e
w
u
s
e
r
s
,
d
ed
u
c
e
d
g
e
n
e
r
a
l
o
m
n
i
ch
an
n
e
l
l
e
a
r
n
i
n
g
f
r
o
m
th
e
u
s
e
r
,
a
n
d
m
a
d
e
s
en
s
e
t
o
a
v
a
l
u
ab
l
e
ex
t
e
n
t
b
y
w
i
d
en
i
n
g
t
h
e
s
i
m
i
la
r
i
t
y
n
e
i
g
h
b
o
r
h
o
o
d
.
T
r
u
s
t
p
r
o
p
ag
a
t
i
o
n
n
o
t
o
n
ly
e
n
r
i
ch
e
s
t
h
e
p
r
e
d
i
c
t
iv
e
d
i
r
ec
t
i
o
n
s
b
u
t
f
i
n
a
l
ly
m
ak
e
s
th
e
e
n
t
ir
e
s
y
s
t
em
's
o
v
e
r
a
l
l
l
e
v
e
l
o
f
a
c
cu
r
a
c
y
,
r
o
b
u
s
t
n
e
s
s
,
a
n
d
i
n
c
l
u
s
i
v
e
n
e
s
s
e
n
h
a
n
ce
d
.
T
r
u
s
t
p
r
o
p
a
g
a
t
i
o
n
w
a
s
a
p
o
s
s
i
b
i
l
i
ty
t
o
p
u
t
a
l
l
o
f
t
h
em
o
n
th
e
s
am
e
f
o
o
t
in
g
w
i
th
r
e
s
p
ec
t
to
i
n
t
er
ac
t
i
n
g
w
i
t
h
th
e
s
y
s
t
e
m
w
h
e
t
h
er
th
e
y
w
er
e
a
c
t
iv
e
o
r
p
a
s
s
i
v
e
u
s
er
s
,
a
n
d
i
t
a
l
s
o
o
f
f
er
s
a
p
o
s
s
i
b
i
l
i
ty
f
o
r
t
h
e
i
m
p
l
i
c
i
t
t
r
a
i
l
in
f
o
r
m
a
t
io
n
g
en
er
a
t
e
d
b
y
th
e
u
s
e
r
,
to
b
e
u
s
ed
i
n
t
h
e
r
e
c
o
m
m
en
d
a
t
io
n
s
t
o
o
.
F
u
r
th
er
m
o
r
e
,
t
r
u
s
t
p
r
o
p
ag
a
t
i
o
n
a
l
l
o
w
s
r
e
co
m
m
e
n
d
a
t
i
o
n
s
to
o
p
er
a
t
e
in
m
u
ch
m
o
r
e
f
e
r
t
i
l
e
e
co
s
y
s
t
e
m
s
,
a
s
r
e
c
o
m
m
e
n
d
a
t
i
o
n
s
c
an
a
c
t
u
a
l
ly
b
e
d
r
i
v
en
b
y
d
a
ta
,
o
r
s
o
c
ia
l
l
y
m
ed
i
a
t
e
d
d
a
t
a
(
o
r
a
m
ix
o
f
b
o
th
)
,
t
h
a
t
cr
e
a
t
e
s
a
g
lo
b
a
l
m
u
ch
b
e
t
t
e
r
e
x
p
e
r
ie
n
c
e
t
o
th
e
u
s
e
r
n
o
t
j
u
s
t
i
n
ter
m
s
o
f
q
u
a
l
i
ty
o
f
r
e
c
o
m
m
en
d
a
t
io
n
s
b
u
t
a
l
s
o
in
i
d
e
a
s
o
f
eq
u
i
ty
[
1
9
]
.
3
.
5
.
User
inte
rf
a
ce
T
AHRF
h
as
th
e
b
est
u
s
er
in
te
r
f
ac
e.
No
t
o
n
l
y
d
o
es
it
allo
w
a
v
is
u
al
r
ep
r
esen
tatio
n
o
f
th
e
co
n
ten
t,
it
also
h
as
th
e
f
u
n
ctio
n
ality
o
f
r
e
al
-
tim
e
u
s
er
in
ter
ac
tio
n
b
y
c
o
llatin
g
th
e
p
ar
ticip
a
n
t'
s
lik
e/d
is
lik
e
an
d
ev
e
n
th
eir
d
ec
is
io
n
s
at
tim
es.
T
AHRF
is
a
n
ew
r
ea
l
-
tim
e
u
s
er
g
r
a
p
h
ical
[
2
0
]
in
ter
f
a
ce
,
in
wh
ich
u
s
er
s
ca
n
r
ea
ct
to
p
er
s
o
n
alize
d
r
ec
o
m
m
en
d
atio
n
s
an
d
u
s
er
s
ca
n
ch
an
g
e
th
e
b
u
d
g
et,
lik
es,
o
r
tr
ip
tim
elin
es.
T
h
e
r
ec
o
m
m
en
d
atio
n
s
y
s
tem
u
p
d
ates
im
m
ed
iately
u
p
o
n
m
o
d
i
f
y
in
g
an
y
p
ar
a
m
eter
s
b
u
t
d
o
es
n
o
t
d
im
in
is
h
u
s
er
ex
p
er
ien
ce
.
On
e
o
f
th
e
b
est
f
ea
tu
r
es
o
f
t
h
e
u
s
er
i
n
ter
f
ac
e
is
th
e
in
ter
ac
tiv
e
g
eo
m
ap
[
2
1
]
.
T
h
e
f
in
d
er
will
b
e
ab
le
to
ad
ju
s
t
th
ese
tr
ip
s
u
g
g
esti
o
n
s
,
an
d
th
e
c
o
lo
r
ed
g
e
o
co
n
tex
t
s
h
ad
i
n
g
(
g
r
ee
n
=m
o
s
t
ap
p
r
o
p
r
iate,
r
e
d
=i
n
ap
p
r
o
p
r
iate)
will
in
d
icate
h
o
w
a
p
p
r
o
p
r
iate
th
e
s
u
g
g
esti
o
n
is
.
T
h
r
o
u
g
h
th
e
ap
p
licatio
n
o
f
co
lo
r
s
,
th
e
u
s
er
s
will
r
ec
eiv
e
an
im
m
ed
iate
lev
el
o
f
u
n
d
e
r
s
tan
d
in
g
o
f
th
e
co
m
p
lex
i
n
ter
p
lay
b
etwe
en
th
e
u
s
er
s
'
in
d
iv
id
u
al
p
r
ef
er
en
ce
s
an
d
th
e
p
o
s
s
ib
le
r
esu
ltin
g
o
u
tc
o
m
es
o
f
th
e
ch
o
ices
th
ey
ar
e
u
n
d
er
tak
i
n
g
,
w
h
ich
u
ltima
te
ly
tr
an
s
f
o
r
m
s
th
e
co
n
s
u
m
p
tio
n
o
f
ad
v
ice
in
to
a
n
ac
tiv
e
p
a
r
ticip
atio
n
p
r
o
ce
s
s
with
u
s
er
s
m
ak
in
g
in
ten
tio
n
al
d
ec
is
io
n
s
,
g
iv
en
th
eir
ev
er
-
c
h
an
g
in
g
n
ee
d
s
an
d
co
n
s
tr
ain
ts
[
2
2
]
,
[
2
3
]
.
T
h
r
o
u
g
h
o
u
t
th
e
s
tu
d
y
p
er
io
d
,
o
v
er
8
1
%
o
f
th
e
1
3
0
u
s
er
s
f
r
o
m
o
u
r
s
am
p
le
ap
p
r
o
v
ed
o
f
n
o
tific
atio
n
s
b
ased
o
n
a
liv
e
m
a
p
.
T
h
is
ap
p
r
o
v
al,
we
h
av
e
n
o
d
o
u
b
ts
,
r
e
af
f
ir
m
s
th
e
liv
in
g
in
t
h
e
m
o
m
en
t
o
f
th
e
tim
e,
a
n
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
:
374
-
3
8
2
380
liv
in
g
in
th
e
m
o
m
en
t
o
f
th
e
in
f
o
r
m
atio
n
r
ec
eiv
e
d
to
eith
er
co
n
tr
o
l
o
r
o
p
en
th
e
ar
ea
o
f
tr
u
s
t
an
d
o
p
en
n
ess
.
J
u
s
t
lik
e
th
e
o
r
al
tr
ad
itio
n
o
f
h
u
m
an
-
co
m
p
u
ter
in
te
r
ac
tio
n
(
HC
I
)
an
d
ad
ap
tiv
e
d
esig
n
[
2
4
]
.
I
t
d
em
o
n
s
tr
ates
th
e
in
cr
ed
ib
le
p
r
o
m
in
e
n
ce
an
d
p
o
wer
f
u
l
ab
ilit
y
o
f
th
e
u
s
er
in
te
r
f
ac
e
d
esig
n
in
th
e
af
f
o
r
d
a
n
c
e
o
f
r
ec
o
m
m
en
d
er
s
y
s
tem
s
an
d
HC
I
d
esig
n
.
T
h
ese
f
in
d
i
n
g
s
also
s
u
g
g
est
f
u
tu
r
e
im
p
r
o
v
em
en
t
p
o
s
s
ib
ilit
ies.
Fo
r
e
x
am
p
le,
u
s
in
g
in
p
u
ts
th
at
ta
k
e
in
to
ac
co
u
n
t
th
e
c
o
n
tex
t,
lik
e
wea
th
er
,
ev
e
n
t
ca
len
d
a
r
s
,
o
r
lo
ca
l
tr
a
n
s
it
tim
etab
les,
co
u
ld
im
p
r
o
v
e
th
e
r
esp
o
n
s
iv
en
ess
o
f
th
e
s
y
s
tem
ev
en
f
u
r
th
er
.
T
h
e
u
s
er
in
ter
f
ac
e
,
th
en
,
is
a
d
y
n
am
ic,
in
tellig
en
t
in
ter
f
ac
e
th
at
ch
an
g
es
with
th
e
ch
an
g
in
g
alg
o
r
ith
m
s
,
wh
er
e
th
e
o
b
jec
tiv
es
ar
e
b
o
th
u
s
er
em
p
o
we
r
m
en
t
an
d
s
y
s
tem
tr
an
s
p
ar
en
cy
[
2
5
]
.
3
.
6
.
Abla
t
io
n study
W
e
ca
r
r
ied
o
u
t
ab
latio
n
r
esear
ch
in
o
r
d
e
r
to
s
ep
ar
ate
th
e
ef
f
ec
ts
o
f
ea
ch
m
o
d
u
le
in
T
AH
R
F.
T
h
r
ee
T
AHRF
v
ar
iatio
n
s
wer
e
p
r
o
d
u
ce
d
b
y
u
s
:
i)
Static
weig
h
tin
g
,
wh
ich
u
s
es
a
s
et
α
(
eq
u
al
weig
h
ts
f
o
r
u
s
er
-
an
d
item
-
b
ased
p
r
e
d
ictio
n
s
)
in
p
lace
o
f
th
e
d
y
n
am
ic
m
et
h
o
d
.
ii)
No
m
u
lti
-
cr
iter
ia,
wh
ich
c
o
lla
p
s
es m
an
y
cr
iter
ia
in
to
a
s
in
g
le
o
v
er
all
r
atin
g
.
iii)
No
tr
u
s
t p
r
o
p
ag
atio
n
,
wh
ich
u
s
es ju
s
t d
ir
ec
t tr
u
s
t (
n
o
m
u
lti
-
h
o
p
p
r
o
p
ag
atio
n
)
.
T
h
e
r
estau
r
an
t
an
d
h
o
tel
d
at
asets
wer
e
u
s
ed
to
ass
e
s
s
e
ac
h
v
ar
iatio
n
.
T
h
e
r
esu
lts
s
h
o
wed
th
at
r
em
o
v
in
g
th
e
tr
u
s
t
p
r
o
p
ag
atio
n
m
o
d
u
le
in
cr
ea
s
ed
MA
E
b
y
ab
o
u
t
1
5
%
an
d
r
e
d
u
ce
d
c
o
v
er
ag
e
b
y
o
v
er
1
0
%,
h
ig
h
lig
h
tin
g
th
e
im
p
o
r
tan
ce
o
f
lev
e
r
ag
in
g
in
d
i
r
ec
t
tr
u
s
t
s
ig
n
als.
Similar
ly
,
u
s
in
g
a
s
in
g
le
-
cr
iter
io
n
r
atin
g
(
n
o
m
u
lti
-
cr
iter
ia)
led
to
a
n
~8
%
r
is
e
in
MA
E
,
c
o
n
f
ir
m
i
n
g
th
at
m
u
lti
-
f
ac
eted
r
atin
g
s
i
m
p
r
o
v
e
p
r
ed
ictio
n
ac
cu
r
ac
y
.
Fin
ally
,
r
ep
lacin
g
th
e
d
y
n
am
ic
h
y
b
r
id
weig
h
ti
n
g
with
a
s
tatic
5
0
/5
0
b
len
d
ca
u
s
ed
a
m
in
o
r
p
er
f
o
r
m
an
ce
d
r
o
p
(
~2
%
h
ig
h
e
r
MA
E
)
,
in
d
icatin
g
th
at
th
e
a
d
ap
tiv
e
weig
h
tin
g
p
r
o
v
i
d
es
a
m
ea
s
u
r
ab
le
b
en
ef
it.
T
h
ese
ab
latio
n
r
esu
lts
d
em
o
n
s
tr
ate
th
at
ev
er
y
co
m
p
o
n
e
n
t
—
tr
u
s
t
p
r
o
p
ag
atio
n
,
m
u
lti
-
cr
i
ter
ia
an
aly
s
is
,
an
d
d
y
n
am
ic
weig
h
tin
g
—
co
n
tr
ib
u
tes m
ea
n
in
g
f
u
lly
t
o
T
AHRF
’
s
o
v
er
all
p
er
f
o
r
m
a
n
ce
.
4.
CO
NCLU
SI
O
N
Ou
r
m
o
d
el
T
AHRF
co
m
b
in
e
s
tr
u
s
t
n
etwo
r
k
s
,
m
u
lti
-
c
r
iter
ia
r
atin
g
s
,
a
n
d
d
y
n
am
ic
a
d
a
p
tatio
n
to
en
h
an
ce
ef
f
ec
tiv
en
ess
in
s
p
ar
s
e
en
v
ir
o
n
m
e
n
ts
,
as
o
u
r
r
esu
l
ts
h
av
e
s
h
o
wn
.
T
h
is
im
p
r
o
v
e
m
en
t
in
cu
r
s
s
o
m
e
ad
d
itio
n
al
co
m
p
u
tatio
n
,
b
u
t
th
e
s
y
s
tem
r
em
ain
s
s
ca
lab
le
an
d
ef
f
icien
t
in
p
r
ac
tice.
W
e
in
ten
d
to
f
u
r
t
h
er
o
p
tim
ize
th
e
tr
u
s
t
p
r
o
p
ag
atio
n
p
r
o
ce
s
s
(
e.
g
.
,
th
r
o
u
g
h
g
r
ap
h
s
am
p
lin
g
)
in
f
u
tu
r
e
wo
r
k
.
I
n
p
ar
allel,
we
will
ex
p
lo
r
e
th
e
in
te
g
r
atio
n
o
f
in
te
r
n
et
o
f
th
in
g
s
(
I
o
T
)
d
ata
f
o
r
r
ea
l
-
tim
e
co
n
tex
t
awa
r
en
ess
an
d
in
v
esti
g
ate
g
r
o
u
p
r
ec
o
m
m
en
d
atio
n
s
ce
n
ar
io
s
.
T
h
ese
en
h
an
ce
m
en
ts
will
m
ak
e
th
e
f
r
am
ewo
r
k
m
o
r
e
s
ca
la
b
le,
ef
f
icien
t,
an
d
ad
ap
tab
le
to
v
ar
io
u
s
ap
p
licatio
n
ar
ea
s
.
Fu
r
th
er
m
o
r
e,
we
en
v
is
io
n
T
AHRF
a
s
a
g
r
ap
h
-
b
ased
in
tellig
en
t
ag
en
t.
I
n
f
u
tu
r
e
wo
r
k
,
we
p
la
n
to
in
te
g
r
ate
ad
v
an
ce
d
ar
tific
ial
in
tellig
en
ce
tech
n
iq
u
es,
s
u
ch
as g
r
a
p
h
n
eu
r
al
n
etwo
r
k
s
f
o
r
m
o
r
e
e
f
f
ec
tiv
e
t
r
u
s
t
p
r
o
p
a
g
atio
n
an
d
r
ein
f
o
r
ce
m
en
t
lear
n
in
g
to
o
p
tim
ize
th
e
d
y
n
a
m
ic
weig
h
tin
g
f
ac
t
o
r
α
.
B
y
also
ad
d
r
ess
in
g
ex
p
lain
ab
i
lity
an
d
b
ias
m
itig
atio
n
,
th
ese
en
h
an
ce
m
e
n
ts
will
f
u
r
th
er
alig
n
T
AHRF
with
th
e
p
r
in
cip
les o
f
tr
u
s
two
r
th
y
ar
tifi
cial
in
tellig
en
ce
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
No
f
u
n
d
in
g
was p
r
o
v
id
e
d
to
s
u
p
p
o
r
t th
e
co
n
d
u
ct
o
f
th
is
r
ese
ar
ch
.
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
Mo
h
am
ed
B
ad
o
u
ch
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Me
h
d
i Bo
u
tao
u
n
te
✓
✓
✓
✓
✓
✓
✓
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
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
TAHR
F
:
en
h
a
n
ci
n
g
p
ers
o
n
a
liz
ed
to
u
r
is
m
r
ec
o
mme
n
d
a
tio
n
s
w
ith
d
yn
a
mic
a
d
a
p
ta
tio
n
(
Mo
h
a
med
B
a
d
o
u
c
h
)
381
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
s
af
f
ir
m
th
at
th
ey
ar
e
n
o
t
awa
r
e
o
f
an
y
f
in
an
cia
l
o
r
p
er
s
o
n
al
a
f
f
iliatio
n
s
th
at
co
u
ld
h
a
v
e
in
ap
p
r
o
p
r
iately
in
f
l
u
en
ce
d
th
e
r
esear
ch
an
d
f
in
d
i
n
g
s
p
r
esen
t
ed
in
th
is
m
an
u
s
cr
ip
t.
I
NF
O
RM
E
D
CO
NS
E
N
T
No
t
ap
p
licab
le,
as
th
is
s
tu
d
y
in
v
o
lv
es
n
o
h
u
m
an
s
u
b
jects
,
p
ar
ticip
an
ts
,
o
r
in
ter
ac
tio
n
s
r
eq
u
ir
in
g
p
er
s
o
n
al
co
n
s
en
t; it so
lely
u
tili
ze
s
p
u
b
licly
av
ailab
le
d
atasets
an
d
co
m
p
u
tatio
n
al
s
im
u
latio
n
s
.
E
T
H
I
CAL AP
P
RO
V
AL
No
t
ap
p
licab
le,
s
in
ce
th
e
r
ese
ar
ch
em
p
lo
y
s
o
n
ly
p
r
e
-
e
x
is
tin
g
,
n
o
n
-
s
en
s
itiv
e
d
ig
ital
r
eso
u
r
ce
s
with
o
u
t
an
y
h
u
m
an
e
x
p
er
im
en
tatio
n
,
a
n
im
al
test
in
g
,
o
r
d
ata
co
llectio
n
f
r
o
m
in
d
iv
i
d
u
als.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
atasets
em
p
lo
y
ed
t
o
g
e
n
er
ate
th
e
r
esu
lts
o
f
th
is
wo
r
k
ar
e
av
ailab
le
f
r
o
m
th
e
c
o
r
r
esp
o
n
d
in
g
au
th
o
r
,
[
MB],
u
p
o
n
r
ea
s
o
n
ab
l
e
r
eq
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
F
.
R
i
c
c
i
,
“
R
e
c
o
m
me
n
d
e
r
s
y
st
e
ms
i
n
t
o
u
r
i
sm,
”
i
n
H
a
n
d
b
o
o
k
o
f
e
-
T
o
u
ri
s
m
,
C
h
a
m
,
S
w
i
t
z
e
r
l
a
n
d
:
S
p
r
i
n
g
e
r
,
2
0
2
2
,
p
p
.
4
5
7
–
4
7
4
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
030
-
4
8
6
5
2
-
5
_
2
6
.
[
2
]
D
.
S
.
S
h
a
r
ma
,
“
Th
e
d
i
f
f
e
r
e
n
t
i
a
l
e
f
f
e
c
t
o
f
e
n
v
i
r
o
n
m
e
n
t
a
l
d
i
m
e
n
si
o
n
a
l
i
t
y
,
si
z
e
,
a
n
d
s
t
r
u
c
t
u
r
e
o
n
b
u
d
g
e
t
sy
s
t
e
m
c
h
a
r
a
c
t
e
r
i
st
i
c
s
i
n
h
o
t
e
l
s,”
M
a
n
a
g
e
m
e
n
t
A
c
c
o
u
n
t
i
n
g
Re
s
e
a
r
c
h
,
v
o
l
.
1
3
,
n
o
.
1
,
p
p
.
1
0
1
–
1
3
0
,
M
a
r
.
2
0
0
2
,
d
o
i
:
1
0
.
1
0
0
6
/
mare
.
2
0
0
2
.
0
1
8
3
.
[
3
]
D
.
Ja
n
n
a
c
h
a
n
d
M
.
Z
a
n
k
e
r
,
“
I
n
t
e
r
a
c
t
i
v
e
a
n
d
c
o
n
t
e
x
t
-
a
w
a
r
e
s
y
s
t
e
ms
i
n
t
o
u
r
i
sm,”
i
n
H
a
n
d
b
o
o
k
o
f
e
-
T
o
u
r
i
sm
,
C
h
a
m
,
S
w
i
t
z
e
r
l
a
n
d
:
S
p
r
i
n
g
e
r,
2
0
2
0
,
p
p
.
1
–
22
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
0
-
0
5
3
2
4
-
6
_
1
2
5
-
1.
[
4
]
G
.
A
d
o
m
a
v
i
c
i
u
s
a
n
d
Y
.
K
w
o
n
,
“
N
e
w
r
e
c
o
mm
e
n
d
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s
f
o
r
m
u
l
t
i
c
r
i
t
e
r
i
a
r
a
t
i
n
g
s
y
st
e
ms,
”
I
E
EE
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
s
,
v
o
l
.
2
2
,
n
o
.
3
,
p
p
.
4
8
–
5
5
,
M
a
y
2
0
0
7
,
d
o
i
:
1
0
.
1
1
0
9
/
M
I
S
.
2
0
0
7
.
5
8
.
[
5
]
J.
T
o
l
l
e
,
A
.
P
i
a
z
z
a
,
C
.
K
a
i
s
e
r
,
a
n
d
R
.
S
c
h
a
l
l
n
e
r
,
“
D
e
c
i
s
i
o
n
su
p
p
o
r
t
i
n
t
o
u
r
i
sm
t
h
r
o
u
g
h
s
o
c
i
a
l
r
o
b
o
t
s:
d
e
si
g
n
a
n
d
e
v
a
l
u
a
t
i
o
n
o
f
a
c
o
n
v
e
r
sa
t
i
o
n
-
b
a
s
e
d
r
e
c
o
mm
e
n
d
a
t
i
o
n
a
p
p
r
o
a
c
h
b
a
se
d
o
n
t
o
u
r
i
s
t
se
g
me
n
t
s,”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
W
o
rks
h
o
p
o
n
Re
c
o
m
m
e
n
d
e
rs
i
n
T
o
u
r
i
sm
c
o
-
l
o
c
a
t
e
d
w
i
t
h
t
h
e
1
7
t
h
A
C
M
C
o
n
f
e
re
n
c
e
o
n
Re
c
o
m
m
e
n
d
e
r
S
y
st
e
m
s
(
R
e
c
S
y
s
2
0
2
3
)
,
S
i
n
g
a
p
o
r
e
:
C
EU
R
W
o
r
k
s
h
o
p
P
r
o
c
e
e
d
i
n
g
s,
2
0
2
3
,
p
p
.
1
-
12
.
[
6
]
A
.
N
.
N
o
u
b
a
r
i
a
n
d
W
.
W
ö
r
n
d
l
,
“
D
y
n
a
m
i
c
a
d
a
p
t
a
t
i
o
n
o
f
u
s
e
r
p
r
e
f
e
r
e
n
c
e
s
a
n
d
r
e
s
u
l
t
s
i
n
a
d
e
s
t
i
n
a
t
i
o
n
r
e
c
o
m
men
d
e
r
s
y
s
t
e
m,
”
a
rXi
v
:
2
3
0
2
.
0
9
8
0
3
,
F
e
b
.
2
0
2
3
.
[
7
]
P
.
R
e
s
n
i
c
k
,
N
.
I
a
c
o
v
o
u
,
M
.
S
u
c
h
a
k
,
P
.
B
e
r
g
st
r
o
m,
a
n
d
J
.
R
i
e
d
l
,
“
G
r
o
u
p
L
e
n
s
:
a
n
o
p
e
n
a
r
c
h
i
t
e
c
t
u
r
e
f
o
r
c
o
l
l
a
b
o
r
a
t
i
v
e
f
i
l
t
e
r
i
n
g
o
f
n
e
t
n
e
w
s,”
i
n
Pr
o
c
e
e
d
i
n
g
s o
f
t
h
e
1
9
9
4
AC
M
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
e
r
su
p
p
o
rt
e
d
c
o
o
p
e
ra
t
i
v
e
w
o
rk
-
C
S
C
W
’
9
4
,
C
h
a
p
e
l
H
i
l
l
,
N
o
r
t
h
C
a
r
o
l
i
n
a
,
U
n
i
t
e
d
S
t
a
t
e
s:
A
C
M
P
r
e
ss
,
1
9
9
4
,
p
p
.
1
7
5
–
1
8
6
,
d
o
i
:
1
0
.
1
1
4
5
/
1
9
2
8
4
4
.
1
9
2
9
0
5
.
[
8
]
S
.
P
.
R
.
A
s
a
i
t
h
a
mb
i
,
R
.
V
e
n
k
a
t
r
a
m
a
n
,
a
n
d
S
.
V
e
n
k
a
t
r
a
ma
n
,
“
A
t
h
e
ma
t
i
c
t
r
a
v
e
l
r
e
c
o
mm
e
n
d
a
t
i
o
n
sy
s
t
e
m
u
s
i
n
g
a
n
a
u
g
me
n
t
e
d
b
i
g
d
a
t
a
a
n
a
l
y
t
i
c
a
l
mo
d
e
l
,
”
T
e
c
h
n
o
l
o
g
i
e
s
,
v
o
l
.
1
1
,
n
o
.
1
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
t
e
c
h
n
o
l
o
g
i
e
s1
1
0
1
0
0
2
8
.
[
9
]
J.
A
n
,
W
.
Ji
a
n
g
,
a
n
d
G
.
L
i
,
“
B
i
d
i
r
e
c
t
i
o
n
a
l
t
r
u
st
-
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
f
o
r
p
o
i
n
t
-
of
-
i
n
t
e
r
e
st
r
e
c
o
m
me
n
d
a
t
i
o
n
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
3
,
n
o
.
8
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
3
0
8
4
1
4
0
.
[
1
0
]
W
.
W
a
n
g
,
J
.
C
h
e
n
,
J.
W
a
n
g
,
J.
C
h
e
n
,
J
.
L
i
u
,
a
n
d
Z
.
G
o
n
g
,
“
Tr
u
st
-
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
f
o
r
p
e
r
so
n
a
l
i
z
e
d
p
o
i
n
t
o
f
i
n
t
e
r
e
s
t
s
r
e
c
o
mm
e
n
d
a
t
i
o
n
,
”
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
I
n
d
u
st
r
i
a
l
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
6
,
n
o
.
9
,
p
p
.
6
1
2
4
–
6
1
3
2
,
S
e
p
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
I
.
2
0
1
9
.
2
9
5
8
6
9
6
.
[
1
1
]
R
.
C
a
o
,
Z.
Li
,
P
.
W
e
i
,
Y
.
Ti
a
n
,
a
n
d
C
.
Z
h
e
n
g
,
“
A
h
y
b
r
i
d
t
o
u
r
i
sm
r
e
c
o
m
men
d
a
t
i
o
n
s
y
s
t
e
m
b
a
se
d
o
n
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
a
n
d
r
e
-
r
a
n
k
i
n
g
,
”
Ad
v
a
n
c
e
d
I
n
t
e
l
l
i
g
e
n
t
C
o
m
p
u
t
i
n
g
T
e
c
h
n
o
l
o
g
y
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
(
I
C
I
C
2
0
2
3
)
,
S
i
n
g
a
p
o
r
e
:
S
p
r
i
n
g
e
r
,
2
0
2
3
,
p
p
.
3
6
3
–
3
7
2
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
99
-
4
7
6
1
-
4
_
3
1
.
[
1
2
]
N
.
K
e
d
a
m,
D
.
K
.
Ti
w
a
r
i
,
V
.
K
u
mar,
K
.
M
.
K
h
e
d
h
e
r
,
a
n
d
M
.
A
.
S
a
l
e
m
,
“
R
i
v
e
r
st
r
e
a
m
f
l
o
w
p
r
e
d
i
c
t
i
o
n
t
h
r
o
u
g
h
a
d
v
a
n
c
e
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
s
f
o
r
e
n
h
a
n
c
e
d
a
c
c
u
r
a
c
y
,
”
Re
s
u
l
t
s
i
n
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
2
,
Ju
n
.
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
2
1
5
.
[
1
3
]
I
.
K
a
r
a
b
i
l
a
,
N
.
D
a
r
r
a
z
,
A
.
E
l
-
A
n
sar
i
,
N
.
A
l
a
mi
,
a
n
d
M
.
E
l
M
a
l
l
a
h
i
,
“
A
d
d
r
e
ss
i
n
g
d
a
t
a
s
p
a
r
s
i
t
y
a
n
d
c
o
l
d
-
s
t
a
r
t
c
h
a
l
l
e
n
g
e
s
i
n
r
e
c
o
m
me
n
d
e
r
s
y
st
e
ms
u
s
i
n
g
a
d
v
a
n
c
e
d
d
e
e
p
l
e
a
r
n
i
n
g
a
n
d
s
e
l
f
-
su
p
e
r
v
i
s
e
d
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
,
”
J
o
u
rn
a
l
o
f
Ex
p
e
ri
m
e
n
t
a
l
&
T
h
e
o
re
t
i
c
a
l
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
3
7
,
n
o
.
8
,
p
p
.
1
4
2
1
–
1
4
5
1
,
N
o
v
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
8
0
/
0
9
5
2
8
1
3
X
.
2
0
2
4
.
2
4
0
1
3
6
4
.
[
1
4
]
M
.
A
l
d
a
y
e
l
,
A
.
A
l
-
N
a
f
j
a
n
,
W
.
M
.
A
l
-
N
u
w
a
i
ser,
G
.
A
l
r
e
h
a
i
l
i
,
a
n
d
G
.
A
l
y
a
h
y
a
,
“
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
r
e
c
o
mm
e
n
d
a
t
i
o
n
sy
st
e
ms
f
o
r
t
o
u
r
i
st
i
c
b
u
si
n
e
ss
e
s
,
a
t
t
r
a
c
t
i
o
n
s,
a
n
d
d
e
st
i
n
a
t
i
o
n
s,
”
El
e
c
t
r
o
n
i
c
s
,
v
o
l
.
1
2
,
n
o
.
1
9
,
S
e
p
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s1
2
1
9
4
0
4
7
.
[
1
5
]
R
.
N
.
R
a
v
i
k
u
mar
,
S
.
J
a
i
n
,
a
n
d
M
.
S
a
r
k
a
r
,
“
A
d
a
p
t
i
Le
a
r
n
:
r
e
a
l
-
t
i
me
p
e
r
s
o
n
a
l
i
z
e
d
c
o
u
r
se
r
e
c
o
mm
e
n
d
a
t
i
o
n
sy
s
t
e
m
u
si
n
g
w
h
a
l
e
o
p
t
i
m
i
z
e
d
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
S
y
st
e
m
A
ssu
ra
n
c
e
E
n
g
i
n
e
e
r
i
n
g
a
n
d
Ma
n
a
g
e
m
e
n
t
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
3
1
9
8
-
024
-
0
2
3
0
1
-
2.
[
1
6
]
M
.
A
l
r
i
z
q
,
S
.
A
l
i
S
o
l
a
n
g
i
,
A
.
A
l
g
h
a
m
d
i
,
M
.
A
l
i
N
i
z
a
ma
n
i
,
M
.
A
l
i
M
e
m
o
n
,
a
n
d
M
.
H
a
m
d
i
,
“
A
n
a
r
c
h
i
t
e
c
t
u
r
e
s
u
p
p
o
r
t
i
n
g
i
n
t
e
l
l
i
g
e
n
t
mo
b
i
l
e
h
e
a
l
t
h
c
a
r
e
u
si
n
g
h
u
ma
n
-
c
o
m
p
u
t
e
r
i
n
t
e
r
a
c
t
i
o
n
H
C
I
p
r
i
n
c
i
p
l
e
s
,
”
C
o
m
p
u
t
e
r S
y
s
t
e
m
s S
c
i
e
n
c
e
a
n
d
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
4
0
,
n
o
.
2
,
p
p
.
5
5
7
–
5
6
9
,
2
0
2
2
,
d
o
i
:
1
0
.
3
2
6
0
4
/
c
ss
e
.
2
0
2
2
.
0
1
8
8
0
0
.
[
1
7
]
M
.
J
.
S
h
e
r
l
o
c
k
,
M
.
H
a
s
a
n
,
a
n
d
F
.
F
.
S
a
ma
v
a
t
i
,
“
I
n
t
e
r
a
c
t
i
v
e
d
a
t
a
st
y
l
i
n
g
a
n
d
mu
l
t
i
f
o
c
a
l
v
i
s
u
a
l
i
z
a
t
i
o
n
f
o
r
a
m
u
l
t
i
g
r
i
d
w
e
b
-
b
a
se
d
D
i
g
i
t
a
l
Ea
r
t
h
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
D
i
g
i
t
a
l
E
a
rt
h
,
v
o
l
.
1
4
,
n
o
.
3
,
p
p
.
2
8
8
–
3
1
0
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
8
0
/
1
7
5
3
8
9
4
7
.
2
0
2
0
.
1
8
2
2
4
5
2
.
[
1
8
]
J.
R
e
y
e
s
,
A
.
U
.
B
a
t
ma
z
,
a
n
d
M
.
K
.
-
O
e
r
t
e
l
,
“
Tr
u
st
i
n
g
A
I
:
d
o
e
s
u
n
c
e
r
t
a
i
n
t
y
v
i
su
a
l
i
z
a
t
i
o
n
a
f
f
e
c
t
d
e
c
i
si
o
n
-
m
a
k
i
n
g
?
,
”
Fr
o
n
t
i
e
rs
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
7
,
F
e
b
.
2
0
2
5
,
d
o
i
:
1
0
.
3
3
8
9
/
f
c
o
m
p
.
2
0
2
5
.
1
4
6
4
3
4
8
.
[
1
9
]
C
.
M
a
v
r
o
g
i
a
n
n
i
s
e
t
a
l
.
,
“
C
o
r
e
c
h
a
l
l
e
n
g
e
s
o
f
so
c
i
a
l
r
o
b
o
t
n
a
v
i
g
a
t
i
o
n
:
a
s
u
r
v
e
y
,
”
AC
M
T
r
a
n
s
a
c
t
i
o
n
s
o
n
H
u
m
a
n
-
R
o
b
o
t
I
n
t
e
r
a
c
t
i
o
n
,
v
o
l
.
1
2
,
n
o
.
3
,
p
p
.
1
–
3
9
,
S
e
p
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
4
5
/
3
5
8
3
7
4
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
:
374
-
3
8
2
382
[
2
0
]
Y
.
S
o
n
g
a
n
d
Y
.
H
e
,
“
T
o
w
a
r
d
a
n
i
n
t
e
l
l
i
g
e
n
t
t
o
u
r
i
s
m
r
e
c
o
mm
e
n
d
a
t
i
o
n
sy
s
t
e
m
b
a
se
d
o
n
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
a
n
d
I
o
T
u
si
n
g
A
p
r
i
o
r
i
a
l
g
o
r
i
t
h
m,
”
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
2
7
,
n
o
.
2
4
,
p
p
.
1
9
1
5
9
–
1
9
1
7
7
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
0
0
-
023
-
0
9
3
3
0
-
2.
[
2
1
]
F
.
W
a
n
g
,
H
.
Z
h
u
,
G
.
S
r
i
v
a
st
a
v
a
,
S
.
Li
,
M
.
R
.
K
h
o
sr
a
v
i
,
a
n
d
L.
Q
i
,
“
R
o
b
u
s
t
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
w
i
t
h
u
s
e
r
-
i
t
e
m
-
t
r
u
st
r
e
c
o
r
d
s
,
”
I
EE
E
T
ra
n
s
a
c
t
i
o
n
s
o
n
C
o
m
p
u
t
a
t
i
o
n
a
l
S
o
c
i
a
l
S
y
st
e
m
s
,
v
o
l
.
9
,
n
o
.
4
,
p
p
.
9
8
6
–
9
9
6
,
A
u
g
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
TC
S
S
.
2
0
2
1
.
3
0
6
4
2
1
3
.
[
2
2
]
N
.
K
h
a
l
e
d
i
a
n
a
n
d
F
.
M
a
r
d
u
k
h
i
,
“
C
F
M
T:
a
c
o
l
l
a
b
o
r
a
t
i
v
e
f
i
l
t
e
r
i
n
g
a
p
p
r
o
a
c
h
b
a
se
d
o
n
t
h
e
n
o
n
n
e
g
a
t
i
v
e
m
a
t
r
i
x
f
a
c
t
o
r
i
z
a
t
i
o
n
t
e
c
h
n
i
q
u
e
a
n
d
t
r
u
s
t
r
e
l
a
t
i
o
n
s
h
i
p
s,”
J
o
u
rn
a
l
o
f
Am
b
i
e
n
t
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
H
u
m
a
n
i
z
e
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
3
,
n
o
.
5
,
p
p
.
2
6
6
7
–
2
6
8
3
,
M
a
y
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
2
6
5
2
-
0
2
1
-
0
3
3
6
8
-
6.
[
2
3
]
S
.
N
u
d
r
a
t
,
H
.
U
.
K
h
a
n
,
S
.
I
q
b
a
l
,
M
.
M
.
Ta
l
h
a
,
F
.
K
.
A
l
a
r
f
a
j
,
a
n
d
N
.
A
l
m
u
sa
l
l
a
m,
“
U
sers’
r
a
t
i
n
g
p
r
e
d
i
c
t
i
o
n
s
u
si
n
g
c
o
l
l
a
b
o
r
a
t
i
n
g
f
i
l
t
e
r
i
n
g
b
a
se
d
o
n
u
sers
a
n
d
i
t
e
ms
s
i
mi
l
a
r
i
t
y
me
a
su
r
e
s,”
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
N
e
u
ro
s
c
i
e
n
c
e
,
v
o
l
.
2
0
2
2
,
p
p
.
1
–
1
3
,
Ju
l
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
2
3
4
7
6
4
1
.
[
2
4
]
J.
A
i
,
Y
.
C
a
i
,
Z.
S
u
,
K
.
Zh
a
n
g
,
D
.
P
e
n
g
,
a
n
d
Q
.
C
h
e
n
,
“
P
r
e
d
i
c
t
i
n
g
u
s
e
r
-
i
t
e
m
l
i
n
k
s
i
n
r
e
c
o
mm
e
n
d
e
r
sy
s
t
e
ms
b
a
s
e
d
o
n
s
i
mi
l
a
r
i
t
y
-
n
e
t
w
o
r
k
r
e
s
o
u
r
c
e
a
l
l
o
c
a
t
i
o
n
,
”
C
h
a
o
s,
S
o
l
i
t
o
n
s
& Fr
a
c
t
a
l
s
,
v
o
l
.
1
5
8
,
M
a
y
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
h
a
o
s
.
2
0
2
2
.
1
1
2
0
3
2
.
[
2
5
]
H
.
U
.
R
.
K
h
a
n
,
C
.
K
.
Li
m
,
M
.
F
.
A
h
me
d
,
K
.
L.
T
a
n
,
a
n
d
M
.
M
o
k
h
t
a
r
,
“
S
y
st
e
ma
t
i
c
r
e
v
i
e
w
o
f
c
o
n
t
e
x
t
u
a
l
su
g
g
e
s
t
i
o
n
a
n
d
r
e
c
o
m
me
n
d
a
t
i
o
n
s
y
s
t
e
ms f
o
r
s
u
st
a
i
n
a
b
l
e
e
-
t
o
u
r
i
sm
,
”
S
u
st
a
i
n
a
b
i
l
i
t
y
,
v
o
l
.
1
3
,
n
o
.
1
5
,
J
u
l
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
s
u
1
3
1
5
8
1
4
1
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Mo
h
a
m
e
d
Ba
d
o
u
c
h
is
a
P
h
.
D.
stu
d
e
n
t
in
Co
m
p
u
ter
S
c
i
e
n
c
e
a
t
Ib
n
Z
o
h
r
Un
iv
e
rsity
,
Ag
a
d
ir,
M
o
r
o
c
c
o
.
He
h
o
l
d
s
a
m
a
ste
r’s
d
e
g
re
e
in
In
f
o
rm
a
ti
o
n
S
y
ste
m
s
En
g
i
n
e
e
rin
g
fro
m
Ca
d
i
Ay
y
a
d
Un
i
v
e
rsity
.
His
re
se
a
rc
h
fo
c
u
se
s
o
n
a
rti
ficia
l
in
telli
g
e
n
c
e
a
n
d
m
a
c
h
in
e
lea
rn
in
g
,
p
a
rt
icu
larly
re
c
o
m
m
e
n
d
e
r
sy
ste
m
s,
tr
u
st
-
b
a
se
d
c
o
ll
a
b
o
ra
ti
v
e
fi
lt
e
rin
g
,
a
n
d
d
a
ta
m
in
in
g
in
sp
a
rse
e
n
v
iro
n
m
e
n
ts.
H
is
d
o
c
to
ra
l
w
o
rk
e
x
p
lo
re
s
h
y
b
rid
a
lg
o
rit
h
m
s
in
teg
ra
ti
n
g
tr
u
st
n
e
two
rk
s
fo
r
p
e
rso
n
a
li
z
e
d
to
u
ris
m
re
c
o
m
m
e
n
d
a
ti
o
n
s.
Be
fo
re
a
c
a
d
e
m
ia,
h
e
sp
e
n
t
se
v
e
n
y
e
a
rs
a
s a
so
ftwa
re
d
e
v
e
lo
p
e
r,
a
p
p
l
y
i
n
g
m
a
c
h
in
e
lea
rn
in
g
i
n
e
-
to
u
r
ism
.
He
h
a
s p
re
se
n
ted
h
is wo
r
k
o
n
d
y
n
a
m
ic
a
d
a
p
tatio
n
i
n
re
c
o
m
m
e
n
d
a
ti
o
n
s
y
ste
m
s
a
t
se
v
e
ra
l
in
tern
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s
a
n
d
h
a
s
p
u
b
li
sh
e
d
in
re
p
u
tab
le
jo
u
r
n
a
ls.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
m
o
h
a
m
e
d
.
b
a
d
o
u
c
h
@e
d
u
.
u
iz.ac
.
m
a
.
Pro
f.
Dr
.
Mehd
i
Bo
u
t
a
o
u
n
te
is
a
u
n
i
v
e
rsity
p
ro
fe
ss
o
r
a
t
th
e
N
a
ti
o
n
a
l
S
c
h
o
o
l
o
f
Co
m
m
e
rc
e
a
n
d
M
a
n
a
g
e
m
e
n
t,
I
b
n
Zo
h
r
Un
i
v
e
rsity
,
Da
k
h
la,
M
o
r
o
c
c
o
.
He
re
c
e
iv
e
d
a
P
h
.
D.
i
n
Co
m
p
u
ter
S
c
ien
c
e
fro
m
Ib
n
S
u
lt
a
n
M
o
u
lay
S
li
m
a
n
e
Un
iv
e
rsity
in
2
0
1
7
t
it
led
th
e
n
e
u
ra
l
n
e
two
rk
s
a
n
d
c
o
m
p
lex
p
a
tt
e
rn
r
e
c
o
g
n
it
i
o
n
.
He
su
p
e
rv
ise
d
m
a
ste
rs
in
g
ra
p
h
-
b
a
se
d
n
e
two
r
k
a
n
a
ly
sis
a
n
d
ima
g
e
p
ro
c
e
ss
in
g
u
sin
g
d
e
e
p
lea
rn
i
n
g
a
n
d
is
a
m
e
m
b
e
r
o
f
t
h
e
Artifi
c
ia
l
In
telli
g
e
n
c
e
a
n
d
In
tern
a
ti
o
n
a
l
As
so
c
iatio
n
o
f
P
a
tt
e
rn
Re
c
o
g
n
it
i
o
n
(IAPR)
a
n
d
h
a
s
e
x
p
e
rien
c
e
wo
rk
i
n
g
i
n
a
re
a
s p
e
rtain
i
n
g
to
a
rti
ficia
l
in
telli
g
e
n
c
e
,
m
a
c
h
in
e
lea
rn
i
n
g
,
a
n
d
p
a
tt
e
rn
re
c
o
g
n
i
ti
o
n
.
He
c
a
n
b
e
c
o
n
tac
t
ed
at
e
m
a
il
:
m
e
h
d
i.
b
o
u
tao
u
n
te@
g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.