I
nte
rna
t
io
na
l J
o
urna
l o
f
I
nfo
rm
a
t
ics a
nd
Co
m
m
un
ica
t
io
n T
ec
hn
o
lo
g
y
(
I
J
-
I
CT
)
Vo
l.
1
5
,
No
.
4
,
D
e
c
em
b
er
20
2
6
,
p
p
.
1
8
7
1
~
1
8
8
0
I
SS
N:
2252
-
8
7
7
6
,
DOI
:
1
0
.
1
1
5
9
1
/iji
ct
.
v
1
5
i
4
.
pp
1
8
7
1
-
1
8
8
0
1871
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ict.
ia
esco
r
e.
co
m
A hybrid
AI fram
ewo
rk f
o
r
hy
per
-
perso
na
lized
recom
menda
tions
and custo
mer
en
g
a
g
ement pre
dic
t
io
n
in e
-
co
mm
e
rce
P
a
ra
s
hiv
a
M
urt
hy
B
.
M
.
1
,
S
ca
ria
Alex
2
,
I
s
a
iv
a
ni M
a
riy
a
pp
a
n
3
,
K
a
ly
a
n De
v
a
pp
a
B
a
m
a
ne
4
,
K
a
v
it
ha
.
R
5
, S
.
At
hin
a
ra
y
a
na
n
6
,
Su
nd
er
.
R
7
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
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
JS
S
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
U
n
i
v
e
r
s
i
t
y
,
M
y
su
r
u
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
Te
c
h
n
o
l
o
g
y
,
A
ma
l
J
y
o
t
h
i
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
,
K
o
t
t
a
y
a
m,
I
n
d
i
a
3
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
i
c
a
l
a
n
d
El
e
c
t
r
o
n
i
c
s E
n
g
i
n
e
e
r
i
n
g
,
S
R
M
M
a
d
u
r
a
i
C
o
l
l
e
g
e
f
o
r
En
g
i
n
e
e
r
i
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
P
o
t
t
a
p
a
l
a
y
a
m
,
I
n
d
i
a
4
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
,
I
n
d
i
r
a
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
M
a
n
a
g
e
m
e
n
t
,
P
u
n
e
,
I
n
d
i
a
5
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
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
S
a
v
e
e
t
h
a
S
c
h
o
o
l
o
f
En
g
i
n
e
e
r
i
n
g
,
S
a
v
e
e
t
h
a
I
n
st
i
t
u
t
e
o
f
M
e
d
i
c
a
l
a
n
d
Te
c
h
n
i
c
a
l
S
c
i
e
n
c
e
s
,
C
h
e
n
n
a
i
,
In
d
i
a
6
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
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
V
e
l
T
e
c
h
R
a
n
g
a
r
a
j
a
n
D
r
.
S
a
g
u
n
t
h
a
l
a
R
&D
I
n
st
i
t
u
t
e
o
f
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
A
v
a
d
i
,
C
h
e
n
n
a
i
,
I
n
d
i
a
7
S
c
h
o
o
l
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
G
a
l
g
o
t
i
a
s U
n
i
v
e
r
si
t
y
,
G
r
e
a
t
e
r
N
o
i
d
a
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
l 9
,
2
0
2
5
R
ev
is
ed
J
u
n
1
,
2
0
2
6
Acc
ep
ted
J
u
l 5
,
2
0
2
6
Th
e
e
x
p
lo
si
o
n
o
f
e
-
c
o
m
m
e
rc
e
h
a
s
led
to
a
n
i
n
c
re
a
se
in
t
h
e
d
e
m
a
n
d
fo
r
sm
a
rt
sy
ste
m
s
th
a
t
c
a
n
p
ro
v
id
e
h
y
p
e
r
-
p
e
rso
n
a
li
z
e
d
e
x
p
e
rie
n
c
e
s
a
n
d
e
n
h
a
n
c
e
c
u
sto
m
e
r
e
n
g
a
g
e
m
e
n
t.
T
h
is
stu
d
y
p
ro
p
o
se
s
a
h
y
p
e
r
p
e
rso
n
a
li
z
e
d
e
-
c
o
m
m
e
rc
e
fra
m
e
wo
rk
b
y
i
n
c
o
rp
o
ra
ti
n
g
th
e
d
e
e
p
lea
rn
i
n
g
(
DL)
b
a
se
d
h
y
b
rid
re
c
o
m
m
e
n
d
a
ti
o
n
m
o
d
e
ls
a
lo
n
g
wit
h
th
e
e
n
se
m
b
le
c
las
sifiers
fo
r
e
n
g
a
g
e
m
e
n
t
p
re
d
icti
o
n
.
Re
a
l
wo
rl
d
p
u
b
li
c
e
-
c
o
m
m
e
rc
e
d
a
tas
e
ts
we
re
u
se
d
in
a
two
-
sta
g
e
e
v
a
lu
a
ti
o
n
th
a
t
m
e
a
su
re
d
re
c
o
m
m
e
n
d
a
ti
o
n
e
ffe
c
ti
v
e
n
e
ss
o
n
P
re
c
isio
n
@1
0
,
Re
c
a
ll
@1
0
a
n
d
ND
C
G
@1
0
,
a
n
d
e
n
g
a
g
e
m
e
n
t
p
r
e
d
ictio
n
o
n
Ac
c
u
ra
c
y
,
F
1
-
S
c
o
re
,
a
n
d
ROC
-
AU
C.
Th
e
re
su
lt
s
o
f
t
h
e
p
ro
p
o
se
d
f
ra
m
e
wo
rk
we
re
c
o
m
p
a
re
d
with
t
h
e
b
a
se
li
n
e
a
p
p
ro
a
c
h
e
s
i
n
term
s
o
f
P
re
c
isio
n
@
1
0
,
Re
c
a
ll
@1
0
,
a
n
d
ND
CG
@1
0
,
w
h
i
c
h
g
a
v
e
P
re
c
isio
n
@
1
0
=
0
.
3
8
2
,
R
e
c
a
ll
@1
0
=
0
.
4
4
1
,
a
n
d
ND
CG
@1
0
=
0
.
4
6
9
,
Ac
c
u
ra
c
y
=
9
1
.
2
%
,
F
1
-
S
c
o
re
=
0
.
8
8
6
,
a
n
d
ROC
-
AU
C
=
0
.
9
3
7
.
T
h
e
se
re
su
lt
s
sh
o
w
th
a
t
a
n
e
n
se
m
b
l
e
o
f
D
L
a
rc
h
it
e
c
tu
re
s
a
n
d
g
ra
d
ien
t
b
o
o
sti
n
g
tec
h
n
i
q
u
e
s
str
o
n
g
ly
imp
ro
v
e
s
t
h
e
q
u
a
li
ty
o
f
p
e
rso
n
a
li
z
a
ti
o
n
a
n
d
b
e
h
a
v
i
o
u
r
p
re
d
ictio
n
.
T
h
is
stu
d
y
h
ig
h
li
g
h
ts
th
e
g
a
m
e
-
c
h
a
n
g
i
n
g
p
o
we
r
o
f
re
c
o
m
m
e
n
d
e
r
a
n
d
p
re
d
icti
v
e
AI
sy
ste
m
s
in
d
ri
v
in
g
c
u
sto
m
e
r
e
x
p
e
rien
c
e
a
n
d
d
a
ta
-
d
r
i
v
e
n
d
ig
it
a
l
c
o
m
m
e
rc
e
a
p
p
ro
a
c
h
e
s.
K
ey
w
o
r
d
s
:
E
-
co
m
m
er
ce
a
n
aly
tics
Hy
b
r
id
AI
m
o
d
els
Per
s
o
n
alize
d
r
ec
o
m
m
e
n
d
atio
n
C
u
s
to
m
er
en
g
ag
em
e
n
t
p
r
ed
ictio
n
Sm
ar
t c
o
m
m
er
ce
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
:
Su
n
d
er
R
Sch
o
o
l o
f
C
o
m
p
u
ter
Scien
ce
a
n
d
E
n
g
in
ee
r
in
g
,
Galg
o
tias
Un
i
v
er
s
ity
Gr
ea
ter
No
id
a,
I
n
d
ia
E
m
ail:
s
u
n
d
er
.
r
@
g
alg
o
tias
u
n
i
v
er
s
ity
.
ed
u
.
in
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
ac
ce
ler
atin
g
in
c
r
ea
s
e
in
u
s
e
o
f
th
e
in
ter
n
et,
th
e
r
ap
i
d
u
p
tak
e
in
m
o
b
ile
co
n
n
ec
tiv
i
ty
an
d
th
e
ch
an
g
e
i
n
co
n
s
u
m
er
e
x
p
ec
tati
o
n
s
,
p
lace
s
th
e
e
-
co
m
m
er
ce
c
h
an
n
el
as
a
ce
n
tr
al
p
ar
t
o
f
th
e
r
etail
an
d
s
er
v
ice
co
n
s
u
m
er
p
u
r
c
h
asin
g
c
h
an
n
el
s
.
T
o
d
ay
'
s
d
ig
ital
co
n
s
u
m
er
s
d
em
an
d
n
o
t
o
n
ly
co
n
v
en
ien
c
e,
b
u
t
p
er
s
o
n
alize
d
ex
p
er
ien
ce
s
th
at
alig
n
with
th
eir
p
r
io
r
in
te
r
ac
tio
n
s
,
u
n
iq
u
e
d
ec
is
io
n
jo
u
r
n
e
y
s
,
an
d
o
th
er
ex
p
r
ess
ed
p
r
ef
er
en
ce
s
.
Fo
r
th
is
r
ea
s
o
n
,
s
m
ar
t
co
m
m
er
ce
was
b
o
r
n
a
n
d
ex
is
ts
to
cr
ea
te
in
tellig
en
t
,
p
er
s
o
n
alize
d
,
an
d
en
g
ag
in
g
s
h
o
p
p
in
g
e
x
p
er
ien
ce
s
u
s
in
g
a
v
ar
iety
o
f
tech
n
o
lo
g
i
es a
n
d
ad
v
a
n
ce
m
en
ts
in
AI
a
n
d
ML
[
1
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
5
,
No
.
4
,
D
e
c
em
b
er
20
2
6
:
1
8
7
1
-
1
8
8
0
1872
T
r
ad
itio
n
al
e
-
co
m
m
e
r
ce
p
latf
o
r
m
s
ar
e
v
er
y
g
o
o
d
at
attr
ac
tin
g
au
d
ien
ce
s
,
b
u
t
th
e
y
o
f
ten
p
r
o
v
id
e
litt
le
in
th
e
wa
y
o
f
tar
g
eted
c
u
s
to
m
er
jo
u
r
n
ey
s
.
As
co
n
s
u
m
e
r
s
ex
p
ec
t
m
o
r
e
a
n
d
co
m
p
etitio
n
in
cr
ea
s
es,
r
etailer
s
h
av
e
to
ad
o
p
t
m
o
r
e
in
tellig
en
t
,
d
ata
-
d
r
iv
en
s
y
s
tem
s
th
at
ca
n
ac
cu
m
u
late,
lear
n
f
r
o
m
,
an
d
a
p
p
ly
la
r
g
e
a
m
o
u
n
ts
o
f
cu
s
to
m
er
d
ata
to
co
n
tin
u
o
u
s
ly
m
ak
e
m
o
r
e
in
f
o
r
m
e
d
an
d
tim
ely
d
ec
is
io
n
s
.
AI
/ML
ca
n
p
r
o
v
id
e
th
is
ca
p
ab
i
lity
f
aster
,
b
etter
,
d
ee
p
er
,
an
d
at
s
ca
le
b
y
au
t
o
m
ati
n
g
p
atter
n
r
ec
o
g
n
itio
n
,
u
s
er
m
o
d
elin
g
,
co
n
ten
t
p
er
s
o
n
aliza
tio
n
,
an
d
en
g
a
g
em
en
t
f
o
r
ec
asts
[
2
]
.
Hy
p
e
r
-
p
er
s
o
n
aliza
tio
n
,
a
k
ey
elem
e
n
t
o
f
Sm
ar
t
C
o
m
m
er
ce
,
tak
es
ad
v
an
tag
e
o
f
r
ea
l
-
tim
e
d
ata
an
d
AI
-
b
ased
an
aly
t
ics
to
d
eliv
er
v
e
r
y
in
d
i
v
id
u
aliz
ed
co
n
ten
t,
p
r
o
d
u
ct
r
ec
o
m
m
en
d
atio
n
s
,
an
d
e
x
p
er
ien
ce
s
.
Hy
p
er
-
p
er
s
o
n
aliza
t
io
n
is
d
if
f
e
r
en
tiated
f
r
o
m
m
o
r
e
tr
ad
itio
n
al
p
er
s
o
n
aliza
tio
n
t
h
r
o
u
g
h
th
e
c
o
n
s
id
er
atio
n
o
f
b
eh
a
v
io
r
al
d
ata,
co
n
tex
t
u
al
s
ig
n
als,
an
d
p
r
ed
ictiv
e
a
n
aly
tics
a
llo
win
g
it to
ass
u
m
e
wh
at
u
s
er
s
wan
t a
n
d
p
r
o
ac
tiv
e
ly
p
r
esen
t th
em
with
s
o
lu
tio
n
s
[
3
]
.
AI
h
as
a
n
e
q
u
ally
im
p
o
r
tan
t
im
p
ac
t
o
n
en
g
a
g
em
en
t.
E
n
g
ag
in
g
cu
s
to
m
e
r
s
is
n
o
t
o
n
ly
ab
o
u
t
tr
an
s
ac
tio
n
s
,
b
u
t
it
in
v
o
lv
es
em
o
tio
n
al
co
n
n
ec
tio
n
,
b
r
a
n
d
lo
y
alty
,
an
d
r
eten
tio
n
.
N
ew
AI
m
o
d
els
also
ca
n
b
e
u
s
ed
to
d
e
v
elo
p
a
n
d
m
ea
s
u
r
e
en
g
ag
em
e
n
t
th
r
o
u
g
h
b
eh
a
v
io
r
al
s
ig
n
als
s
u
ch
as
click
th
r
o
u
g
h
r
ates
(
C
T
R
)
[
4
]
,
s
ess
io
n
len
g
th
,
f
r
eq
u
e
n
cy
o
f
in
ter
ac
tio
n
s
,
an
d
p
r
o
p
e
n
s
ity
t
o
ch
u
r
n
.
B
y
r
esear
ch
i
n
g
b
eh
av
io
r
al
in
d
icato
r
s
,
co
m
p
an
ies
ca
n
d
esig
n
in
ter
v
e
n
tio
n
s
to
r
etain
u
s
er
s
an
d
t
u
r
n
th
em
in
to
b
r
an
d
ad
v
o
ca
tes.
T
h
e
s
tu
d
y
d
escr
ib
es
r
ea
l
-
tim
e
AI
p
er
s
o
n
aliza
tio
n
a
n
d
h
o
w
co
m
p
an
ies
ca
n
d
e
v
el
o
p
AI
an
d
m
ac
h
i
n
e
lear
n
in
g
to
p
r
e
d
ict
cu
s
to
m
er
en
g
ag
em
e
n
t o
u
tco
m
es.
T
h
e
o
b
jectiv
es o
f
th
e
s
tu
d
y
a
r
e
as f
o
ll
o
ws.
-
T
o
p
r
o
p
o
s
e
a
h
y
b
r
id
AI
/M
L
-
b
ased
r
ec
o
m
m
en
d
atio
n
en
g
in
e
th
at
o
f
f
er
s
h
y
p
er
-
p
er
s
o
n
alize
d
p
r
o
d
u
ct
r
ec
o
m
m
en
d
atio
n
s
th
at
tak
e
i
n
to
co
n
s
id
er
atio
n
th
e
u
s
er
'
s
r
ea
l
-
tim
e
ac
tiv
ities
in
co
m
b
in
atio
n
with
th
e
ch
ar
ac
ter
is
tics
o
f
th
e
p
r
o
d
u
ct.
-
T
o
cr
ea
te
a
p
r
ed
ictiv
e
m
o
d
el
o
f
u
s
er
e
n
g
ag
e
m
en
t
th
r
o
u
g
h
cl
ass
if
icatio
n
m
o
d
el
to
p
r
ed
ict
u
s
er
en
g
ag
em
e
n
t
an
d
r
ea
l
-
tim
e
ev
alu
atio
n
o
f
th
e
u
s
er
’
s
en
g
ag
em
en
t b
y
way
o
f
m
ak
in
g
u
s
e
o
f
b
eh
a
v
io
r
al
an
d
tr
an
s
ac
tio
n
s
o
f
th
e
u
s
er
.
-
T
o
ev
alu
ate
th
e
p
r
o
p
o
s
ed
s
y
s
tem
in
co
m
p
a
r
is
o
n
to
a
tr
a
d
itio
n
al
b
aselin
e
s
y
s
tem
,
in
clu
d
i
n
g
p
er
f
o
r
m
a
n
ce
m
etr
ics (
e.
g
.
,
Pre
cisi
o
n
@
K,
R
ec
all@
K,
ND
C
G,
Acc
u
r
ac
y
,
F1
-
Sco
r
e,
R
OC
-
AUC).
T
h
e
s
tu
d
y
is
d
iv
id
ed
in
to
f
i
v
e
s
ec
tio
n
s
:
Sectio
n
1
d
is
cu
s
s
es
th
e
r
esear
ch
b
ac
k
g
r
o
u
n
d
,
r
esear
ch
o
b
jectiv
es
an
d
s
tr
u
ctu
r
e.
Sectio
n
2
co
n
s
is
ts
o
f
a
r
elate
d
w
o
r
k
r
ev
iew
o
n
AI
/ML
-
b
ased
p
er
s
o
n
aliza
tio
n
an
d
en
g
ag
em
e
n
t
p
r
e
d
ictio
n
.
Secti
o
n
3
co
n
tain
s
t
h
e
m
eth
o
d
o
lo
g
y
,
m
o
d
els,
an
d
ex
p
er
im
en
ta
l
s
etu
p
.
Sectio
n
4
p
r
o
v
id
es
th
e
ex
p
er
im
en
tal
r
es
u
lts
,
d
is
cu
s
s
io
n
s
b
ased
o
n
th
e
f
in
d
in
g
s
f
o
llo
we
d
b
y
c
o
n
clu
s
io
n
an
d
f
u
tu
r
e
wo
r
k
s
in
s
ec
tio
n
5
.
2.
RE
L
AT
E
D
WO
RK
S
I
n
t
h
e
p
ast
f
ew
y
ea
r
s
,
s
ig
n
i
f
ica
n
t
a
d
v
a
n
c
em
e
n
ts
i
n
r
e
c
o
m
m
e
n
d
ati
o
n
s
y
s
te
m
s
b
ase
d
o
n
A
I
h
av
e
em
e
r
g
e
d
.
C
o
l
la
b
o
r
ati
v
e
f
il
te
r
i
n
g
,
co
n
t
e
n
t
-
b
ase
d
f
ilt
er
i
n
g
,
a
n
d
h
y
b
r
i
d
m
o
d
e
ls
h
av
e
im
p
r
o
v
e
d
wit
h
d
ee
p
le
ar
n
i
n
g
(
DL
)
a
r
c
h
it
ec
tu
r
es
a
n
d
t
h
e
t
r
an
s
f
o
r
m
e
r
-
b
ase
d
m
o
d
els
h
a
v
e
r
ec
en
tl
y
g
a
in
e
d
t
r
ac
t
io
n
as
h
as
u
s
i
n
g
en
s
em
b
l
e
lea
r
n
i
n
g
,
g
r
a
d
i
en
t
b
o
o
s
ti
n
g
,
a
n
d
n
e
u
r
al
n
et
wo
r
k
s
to
p
r
ed
ic
t
c
o
n
s
u
m
e
r
s
at
is
f
ac
t
io
n
,
b
r
a
n
d
en
g
ag
em
e
n
t,
a
n
d
cu
s
t
o
m
e
r
l
if
eti
m
e
v
al
u
e
.
W
h
il
e
ea
c
h
o
f
th
ese
a
r
ea
s
h
av
e
m
a
d
e
in
d
ep
en
d
en
t
s
t
r
i
d
es
,
f
ew
if
an
y
h
a
v
e
i
n
cl
u
d
e
d
a
r
es
ea
r
c
h
a
g
e
n
d
a
th
at
b
r
i
n
g
s
p
e
r
s
o
n
ali
za
ti
o
n
f
o
r
en
g
ag
em
en
t
p
r
e
d
i
cti
o
n
t
o
g
e
th
er
i
n
a
f
o
r
m
ali
z
ed
f
r
am
ew
o
r
k
[
5
]
.
L
iu
[
6
]
p
r
o
p
o
s
e
th
e
ar
ch
itect
u
r
e
o
f
th
e
e
-
co
m
m
e
r
ce
r
ec
o
m
m
en
d
atio
n
s
y
s
tem
af
ter
c
o
n
d
u
ctin
g
a
th
o
r
o
u
g
h
an
aly
s
is
o
f
th
e
tech
n
iq
u
es
an
d
alg
o
r
ith
m
.
T
h
ak
u
r
et
a
l.
[
7
]
s
p
ec
if
ies
th
e
s
tan
d
ar
d
s
b
y
wh
ich
th
eir
s
u
cc
ess
wi
ll b
e
ju
d
g
ed
in
ter
m
s
o
f
p
er
s
o
n
alis
ed
an
d
o
p
tim
al
d
ec
is
io
n
-
m
ak
in
g
in
o
n
lin
e
b
u
y
in
g
s
ettin
g
s
.
Up
r
eti
et
a
l.
[
8
]
ex
p
l
o
r
es
h
o
w
AI
i
s
ch
an
g
in
g
th
e
e
-
c
o
m
m
er
ce
in
d
u
s
tr
y
an
d
o
p
en
i
n
g
u
p
n
e
w
o
p
p
o
r
tu
n
ities
f
o
r
b
u
s
in
ess
es
to
im
p
r
o
v
e
th
eir
o
p
er
atio
n
s
an
d
p
r
o
m
o
te
g
r
o
wth
.
AI
tech
n
o
lo
g
y
,
wh
ic
h
h
elp
s
b
u
s
in
ess
es
im
p
r
o
v
e
th
eir
p
r
o
ce
s
s
es
an
d
p
r
o
v
id
e
m
o
r
e
p
er
s
o
n
alis
ed
co
n
s
u
m
e
r
ex
p
er
ien
ce
s
,
h
as
b
ec
o
m
e
an
ess
en
tial
p
ar
t
o
f
th
e
e
-
c
o
m
m
er
ce
in
d
u
s
tr
y
.
L
iu
et
a
l.
[
9
]
p
r
esen
ts
s
tate
-
of
-
th
e
-
ar
t
DL
m
eth
o
d
s
with
th
e
g
o
al
o
f
im
p
r
o
v
in
g
e
-
co
m
m
er
ce
s
h
o
p
p
in
g
s
y
s
tem
s
'
u
s
er
ex
p
er
ien
ce
an
d
r
ec
o
m
m
en
d
atio
n
ac
c
u
r
ac
y
.
T
h
e
s
tu
d
y
o
n
o
n
lin
e
p
u
r
ch
asin
g
an
d
co
n
s
u
m
er
b
e
h
av
io
u
r
f
o
cu
s
es
o
n
th
e
tr
an
s
f
o
r
m
ativ
e
ef
f
ec
ts
o
f
AI
-
d
r
iv
en
cu
s
to
m
izatio
n
o
n
m
ar
k
et
tr
en
d
s
.
E
-
c
o
m
m
er
ce
s
y
s
tem
s
will
b
e
ab
le
to
p
er
s
o
n
alis
e
u
s
er
e
x
p
er
ien
ce
s
as
AI
d
ev
elo
p
s
.
AI
-
d
r
iv
en
p
er
s
o
n
aliza
tio
n
in
clu
d
es
p
r
ep
r
o
ce
s
s
in
g
,
f
ea
tu
r
e
ex
t
r
ac
tio
n
,
an
d
m
o
d
el
tr
ain
in
g
.
First,
co
n
s
u
m
er
in
f
o
r
m
atio
n
is
g
a
th
e
r
ed
f
r
o
m
in
ter
n
et
m
ar
k
etp
lace
s
[
1
0
]
.
Dh
a
r
wad
k
ar
e
t
a
l
.
[
1
1
]
p
r
esen
ts
Sm
ar
tC
ar
t,
a
cu
ttin
g
-
ed
g
e
we
b
s
ite
th
at
u
s
es
im
ag
e
u
p
lo
ad
s
to
p
r
o
v
id
e
cu
s
to
m
ized
p
r
o
d
u
c
t
r
ec
o
m
m
en
d
atio
n
s
b
y
in
teg
r
atin
g
s
tate
-
of
-
th
e
-
ar
t
AI
alg
o
r
ith
m
s
.
Z
h
an
g
a
n
d
Xio
n
g
[
1
2
]
i
n
v
e
s
tig
ates
th
e
cr
ea
tio
n
o
f
AI
-
p
o
wer
ed
s
u
g
g
esti
o
n
s
f
o
r
e
-
co
m
m
er
ce
en
v
ir
o
n
m
en
ts
'
p
r
o
d
u
ct
d
esig
n
,
s
ales,
an
d
cu
s
to
m
er
ex
p
er
ie
n
ce
.
T
h
e
s
tu
d
y
u
s
es
a
q
u
an
titativ
e
m
eth
o
d
o
lo
g
y
to
in
v
esti
g
ate
th
e
way
s
in
wh
ich
AI
tech
n
o
lo
g
y
ca
n
im
p
r
o
v
e
m
an
y
asp
ec
ts
o
f
o
n
lin
e
r
e
tail
.
X
u
et
a
l.
[
13
]
s
u
g
g
est
a
n
ew
s
y
s
tem
to
co
llect
d
ata
in
r
ea
l
-
tim
e
an
d
an
aly
ze
h
o
w
C
I
o
T
d
ev
ices
m
ig
h
t
im
p
ac
t
an
d
tr
ac
k
cu
s
to
m
e
r
in
ter
ac
tio
n
s
an
d
p
er
s
o
n
aliza
tio
n
in
e
-
co
m
m
er
ce
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
A
h
yb
r
id
A
I
fr
a
mewo
r
k
fo
r
h
y
p
er
-
p
ers
o
n
a
liz
ed
r
ec
o
mme
n
d
a
tio
n
s
a
n
d
…
(
P
a
r
a
s
h
iva
Mu
r
th
y
B
.
M
.
)
1873
W
h
i
l
e
p
r
e
v
i
o
u
s
r
es
e
a
r
c
h
h
as
i
n
d
i
c
a
t
e
d
v
a
r
i
o
u
s
t
y
p
es
o
f
A
I
a
n
d
D
L
m
o
d
e
ls
f
o
r
e
-
c
o
m
m
e
r
c
e
r
e
c
o
m
m
e
n
d
e
r
s
y
s
t
e
m
s
,
m
o
s
t
s
tu
d
i
e
s
u
s
e
s
t
a
ti
c
d
a
t
as
e
ts
a
n
d
c
a
n
n
o
t
u
t
i
l
i
z
e
f
l
e
x
i
b
l
y
as
c
u
s
t
o
m
e
r
p
r
e
f
e
r
e
n
c
e
s
s
h
i
f
t.
F
u
r
t
h
e
r
m
o
r
e
,
t
h
e
r
e
is
n
'
t
a
l
o
t
o
f
r
e
s
e
a
r
c
h
a
v
ai
l
a
b
l
e
w
h
i
c
h
c
o
m
b
i
n
e
s
f
u
l
l
-
f
le
d
g
e
d
e
d
g
e
c
o
m
p
u
te
a
n
d
C
I
o
T
d
e
v
i
c
es
.
M
o
r
e
o
v
e
r
,
e
n
d
o
r
s
i
n
g
t
h
e
c
o
m
p
l
e
x
i
t
y
o
f
i
n
t
e
r
p
r
e
t
a
b
i
l
it
y
o
f
m
o
d
e
l
s
s
u
c
h
as
g
e
n
e
r
a
ti
v
e
ad
v
e
r
s
a
r
i
a
l
n
et
w
o
r
k
s
(
GAN
s)
a
n
d
T
r
a
n
s
f
o
r
m
e
r
s
r
e
m
a
i
n
s
a
p
o
t
e
n
t
i
a
l
b
a
r
r
i
e
r
f
o
r
t
h
e
p
r
a
c
t
i
c
a
l
u
s
e
o
f
t
h
e
s
e
m
o
d
e
l
s
.
A
d
d
i
ti
o
n
a
l
l
y
,
t
h
e
i
m
p
a
c
t
s
o
f
f
e
a
t
u
r
e
e
n
g
i
n
e
e
r
in
g
o
r
p
r
e
p
r
o
c
e
s
s
i
n
g
c
a
n
o
f
t
e
n
b
e
i
g
n
o
r
e
d
i
n
t
h
e
c
o
n
t
e
x
t
o
f
l
a
r
g
e
-
s
c
a
l
e
,
h
e
t
e
r
o
g
e
n
e
o
u
s
e
-
c
o
m
m
e
r
c
e
d
a
t
a
.
Fe
w
r
e
c
o
m
m
e
n
d
a
ti
o
n
s
y
s
t
e
m
s
c
a
n
t
a
c
k
l
e
l
a
r
g
e
,
s
p
a
r
s
e
d
a
t
a
,
c
o
l
d
-
s
t
a
r
t
p
r
o
b
l
e
m
s
,
a
n
d
c
r
o
s
s
-
p
l
at
f
o
r
m
u
s
e
.
L
a
s
t
l
y
,
m
o
s
t
o
f
t
h
e
e
x
is
ti
n
g
r
e
s
e
a
r
c
h
i
s
d
o
n
e
i
n
l
i
m
i
t
e
d
g
e
o
g
r
a
p
h
i
c
a
l
c
o
n
t
e
x
ts
i
m
p
a
i
r
i
n
g
s
y
s
t
e
m
at
i
c
g
e
n
e
r
a
li
za
t
i
o
n
o
f
f
i
n
d
i
n
g
s
a
c
r
o
s
s
d
i
v
e
r
s
e
g
l
o
b
a
l
e
-
c
o
m
m
e
r
c
e
m
a
r
k
e
ts
.
3.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
e
m
eth
o
d
o
lo
g
y
s
u
g
g
ests
a
s
m
ar
t
co
m
m
er
ce
f
r
am
ewo
r
k
to
p
r
o
v
id
e
h
y
p
er
-
p
er
s
o
n
alize
d
r
ec
o
m
m
en
d
atio
n
s
an
d
p
r
ed
ict
cu
s
to
m
er
e
n
g
ag
e
m
en
t
in
e
-
c
o
m
m
er
ce
.
Pu
b
licly
a
v
ailab
le
d
atasets
,
as
well
as
s
y
n
th
etic
d
atasets
co
n
s
is
t
in
g
o
f
u
s
er
in
ter
ac
tio
n
s
with
d
ig
i
tal
p
r
o
d
u
cts,
p
r
o
d
u
ct
m
etad
at
a,
an
d
b
eh
a
v
io
r
al
m
etr
ics,
wer
e
u
tili
ze
d
.
DL
m
o
d
els
wer
e
d
ev
elo
p
ed
u
s
in
g
Au
to
en
co
d
e
r
s
f
o
r
p
er
s
o
n
alize
d
r
ec
o
m
m
en
d
atio
n
s
,
r
ec
u
r
r
en
t
n
e
u
r
al
n
etwo
r
k
s
(
R
NNs
)
f
o
r
r
ec
o
m
m
en
d
atio
n
s
b
ased
o
n
s
eq
u
en
ce
s
,
an
d
T
r
an
s
f
o
r
m
er
s
f
o
r
g
en
er
al
r
ec
o
m
m
en
d
atio
n
s
.
T
h
e
co
m
b
a
tan
t
u
s
ed
to
p
r
e
d
ict
cu
s
to
m
er
en
g
ag
em
e
n
t
f
r
o
m
t
h
e
d
ata
u
til
ized
b
o
th
XGBo
o
s
t
an
d
ML
P,
co
m
b
in
ed
i
n
a
weig
h
ted
en
s
em
b
le
to
e
n
ab
le
c
lass
if
icatio
n
o
f
u
s
er
s
b
ased
o
f
f
o
f
e
n
g
ag
em
e
n
t le
v
el.
3
.
1
.
Da
t
a
s
et
s
elec
t
io
n a
nd
co
llect
io
n
Pu
b
lic
d
atasets
l
ik
e
R
etai
lR
o
c
k
et
an
d
Am
az
o
n
p
r
o
d
u
ct
r
e
v
iews
wer
e
u
s
ed
to
d
ev
elo
p
an
d
ass
es
s
th
e
p
r
o
p
o
s
ed
s
m
ar
t
co
m
m
er
ce
f
r
am
ewo
r
k
.
Su
c
h
d
ata
ca
n
b
e
u
s
ef
u
l
f
o
r
r
e
co
m
m
en
d
ati
o
n
an
d
p
r
ed
ictiv
e
en
g
ag
em
e
n
t
ap
p
licatio
n
s
as
th
ey
co
n
tain
a
wea
lth
o
f
in
f
o
r
m
atio
n
ab
o
u
t
p
r
o
d
u
ct
attr
ib
u
tes,
u
s
er
in
ter
ac
ti
o
n
s
,
an
d
b
eh
a
v
io
u
r
al
s
ig
n
als.
W
h
en
p
r
o
p
r
ietar
y
d
ata
was
n
o
t
av
ailab
le
o
r
s
ca
r
ce
,
s
y
n
th
etic
d
ata
g
en
er
atio
n
m
eth
o
d
s
wer
e
u
s
ed
to
in
c
r
ea
s
e
d
ata
d
iv
er
s
ity
,
co
n
tr
o
l
d
at
a
s
p
ar
s
ity
an
d
r
ed
u
ce
a
p
r
iv
a
cy
co
n
ce
r
n
,
wh
ich
f
u
r
th
er
b
o
o
s
ts
th
e
r
o
b
u
s
tn
ess
o
f
th
e
m
o
d
el.
T
h
e
g
ath
e
r
ed
d
ata
in
clu
d
ed
s
ev
er
al
asp
ec
ts
cr
u
cial
f
o
r
h
y
p
er
-
p
er
s
o
n
aliza
tio
n
.
T
h
e
b
eh
a
v
io
r
al
d
ata,
s
u
ch
as
u
s
er
click
s
,
v
iews
,
an
d
p
u
r
ch
ase
h
is
to
r
y
,
h
elp
ed
to
c
r
ea
te
m
o
d
els
o
f
u
s
er
p
r
e
f
er
en
ce
s
an
d
in
ter
ac
tio
n
p
atter
n
s
.
Patter
n
s
o
f
u
s
er
in
ter
ac
tio
n
an
d
p
r
ef
er
e
n
ce
s
wer
e
m
o
d
eled
u
s
in
g
b
eh
a
v
io
r
al
d
a
ta,
wh
ich
in
v
o
l
v
ed
u
s
er
clic
k
s
,
v
iews,
an
d
p
u
r
ch
ase
r
ec
o
r
d
s
.
C
o
n
ten
t
-
b
ase
d
f
ilter
in
g
an
d
s
em
an
tic
f
ea
tu
r
e
ex
tr
ac
tio
n
was
s
u
p
p
o
r
ted
b
y
p
r
o
d
u
ct
m
etad
ata
lik
e
ca
teg
o
r
y
,
p
r
ice
an
d
b
r
an
d
.
User
p
r
o
f
ile
in
f
o
r
m
atio
n
s
u
ch
as
d
e
m
o
g
r
ap
h
ics
a
n
d
p
r
ef
er
en
ce
s
,
wh
e
r
e
a
v
ailab
le,
allo
wed
f
o
r
m
o
r
e
p
er
s
o
n
aliza
tio
n
.
Mo
r
eo
v
er
,
u
s
er
b
e
h
av
io
r
was
ex
p
lo
r
ed
u
s
i
n
g
e
n
g
ag
em
e
n
t
m
etr
ics
s
u
ch
as
s
ess
io
n
d
u
r
atio
n
,
b
o
u
n
ce
r
ate,
an
d
r
ete
n
tio
n
r
ate
,
with
th
ei
r
aim
b
ein
g
t
o
f
o
r
ec
ast
u
s
er
in
ter
ac
tio
n
an
d
e
n
g
ag
em
en
t.
T
h
e
o
v
er
all
h
y
p
er
-
p
er
s
o
n
aliza
tio
n
p
r
o
ce
s
s
s
h
o
wn
in
Fig
u
r
e
1
.
Fig
u
r
e
1
.
Hy
p
er
p
e
r
s
o
n
aliza
tio
n
p
r
o
ce
s
s
u
s
in
g
DL
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
5
,
No
.
4
,
D
e
c
em
b
er
20
2
6
:
1
8
7
1
-
1
8
8
0
1874
3.
2
.
Da
t
a
p
re
pro
ce
s
s
ing
C
lean
in
g
th
e
d
ata:
T
h
e
o
b
jecti
v
e
is
to
s
im
p
ly
clea
n
in
g
th
e
d
a
ta
to
im
p
r
o
v
e
c
o
n
s
is
ten
cy
,
s
tab
ilit
y
,
an
d
ass
es
s
in
g
th
e
v
alid
ity
o
f
th
e
d
ata.
T
h
er
e
wer
e
m
is
s
in
g
v
alu
es,
wh
ich
m
u
s
t
b
e
c
o
n
s
id
er
ed
(
eith
er
u
s
in
g
im
p
u
tatio
n
,
o
r
s
im
p
ly
r
em
o
v
in
g
th
e
r
ec
o
r
d
s
)
,
wh
ile
in
co
m
p
lete
r
ec
o
r
d
s
wo
u
ld
n
eg
ativ
el
y
af
f
ec
t
th
e
m
o
d
el
p
er
f
o
r
m
an
ce
.
O
u
tlier
s
wer
e
d
etec
ted
th
r
o
u
g
h
s
tatis
tical
m
ea
s
u
r
es
an
d
wer
e
eith
e
r
d
ea
lt
with
o
r
r
em
o
v
ed
,
b
ased
o
n
r
elev
an
cy
.
Du
p
lica
te
r
ec
o
r
d
s
f
r
o
m
r
ep
ea
t
in
ter
a
ctio
n
s
p
er
u
s
er
,
o
r
d
u
p
licate
en
tr
ies
wer
e
also
d
is
co
v
er
ed
an
d
r
em
o
v
ed
,
to
a
v
o
id
b
ias
in
o
u
r
tr
ain
in
g
an
d
t
esti
n
g
o
f
o
u
r
m
o
d
els.
T
h
e
cle
an
in
g
p
h
ase
is
v
ital
to
g
u
ar
a
n
tee
th
e
d
ataset
is
ac
cu
r
ate,
n
o
is
e
-
f
r
ee
,
an
d
v
alid
f
o
r
an
aly
s
is
.
Featu
r
e
en
g
i
n
ee
r
i
ng
:
T
o
im
p
r
o
v
e
th
e
lear
n
i
n
g
ab
ilit
y
o
f
t
h
e
m
o
d
els,
a
s
er
ies
o
f
f
ea
t
u
r
e
e
n
g
in
ee
r
in
g
was
p
er
f
o
r
m
ed
.
T
h
e
u
s
er
-
p
r
o
d
u
ct
in
ter
ac
tio
n
m
atr
ices,
wh
ich
d
o
cu
m
en
ted
h
o
w
m
an
y
ti
m
es
u
s
er
s
in
ter
ac
ted
with
th
e
p
r
o
d
u
cts,
th
e
ty
p
es
o
f
in
ter
ac
tio
n
s
u
s
er
s
h
a
d
with
t
h
e
p
r
o
d
u
c
ts
(
v
iews,
click
s
,
p
u
r
ch
ases
)
,
wer
e
m
o
s
t
p
r
o
m
in
e
n
t,
as
th
ese
wo
u
ld
b
e
co
m
e
f
o
u
n
d
atio
n
al
t
o
co
llab
o
r
ativ
e
f
ilter
in
g
.
T
em
p
o
r
al
d
y
n
a
m
ics
wer
e
m
o
d
eled
u
s
in
g
tem
p
o
r
al
f
ea
tu
r
es
s
u
c
h
as
r
ec
en
cy
(
tim
e
s
in
ce
la
s
t
in
ter
ac
tio
n
)
,
f
r
eq
u
e
n
cy
(
c
o
u
n
t
o
f
in
ter
ac
tio
n
s
th
r
o
u
g
h
o
u
t
th
e
s
p
ec
if
ied
tim
e
win
d
o
w)
,
an
d
last
d
ate
p
u
r
c
h
ased
,
wh
ich
allo
wed
u
s
to
b
etter
p
r
ed
ict
u
s
er
b
eh
av
io
r
.
Fo
r
co
n
ten
t
-
b
ased
f
ea
tu
r
e
g
en
er
atio
n
,
p
r
o
d
u
ct
e
m
b
ed
d
in
g
s
wer
e
p
r
o
d
u
ce
d
b
y
lev
er
a
g
in
g
NL
P
m
eth
o
d
s
(
e.
g
.
,
W
o
r
d
2
Vec
o
r
tr
an
s
f
o
r
m
er
-
b
ased
m
o
d
els)
o
n
th
e
p
r
o
d
u
ct
d
escr
ip
tio
n
s
,
w
h
ich
allo
wed
u
s
to
ca
p
tu
r
e
th
e
u
n
d
e
r
ly
in
g
s
em
an
t
ics o
f
item
s
.
No
r
m
alis
e
o
r
en
co
d
e
:
C
ateg
o
r
ical
v
ar
iab
les
lik
e
ca
teg
o
r
ies
o
f
p
r
o
d
u
cts,
u
s
er
lo
ca
tio
n
s
,
o
r
b
r
an
d
s
h
ad
to
b
e
en
co
d
ed
in
o
r
d
e
r
to
g
et
th
e
d
ata
r
ea
d
y
f
o
r
ML
alg
o
r
ith
m
s
.
Fo
r
b
asic
m
o
d
els,
ea
c
h
ca
teg
o
r
y
was
co
d
e
d
(
o
r
o
n
e
-
h
o
t
en
c
o
d
ed
)
with
a
n
ap
p
r
o
p
r
iate
tech
n
iq
u
e
to
c
o
n
v
er
t
th
e
ca
te
g
o
r
ies
in
to
b
in
ar
y
v
ec
to
r
s
.
Fo
r
DL
m
o
d
els
em
b
e
d
d
in
g
lay
e
r
s
ar
e
also
allo
wed
to
m
ap
ca
teg
o
r
i
ca
l
v
alu
es
in
t
o
d
en
s
e
v
ec
to
r
r
ep
r
esen
tatio
n
,
with
th
e
p
o
s
s
ib
ilit
y
o
f
th
e
m
o
d
el
lear
n
in
g
laten
t
r
elatio
n
s
h
ip
s
b
etwe
en
ca
teg
o
r
ies.
T
h
er
e
wer
e
also
n
u
m
er
ical
f
ea
tu
r
es.
T
h
ese
n
u
m
er
ical
f
ea
t
u
r
es
u
n
d
er
wen
t
s
o
m
e
n
o
r
m
ali
z
atio
n
to
o
b
tain
a
co
m
m
o
n
s
ca
le
an
d
to
av
o
id
o
n
e
f
ea
tu
r
e
d
o
m
in
atin
g
t
h
e
lear
n
in
g
p
r
o
ce
s
s
b
ec
au
s
e
o
f
d
if
f
er
en
c
es in
s
ca
le.
3.
2
.
M
o
del desig
n a
nd
s
elec
t
io
n
-
hy
per
-
perso
na
liza
t
io
n
Au
to
en
co
d
e
r
s
(
AE
s
)
:
Neu
r
al
n
etwo
r
k
s
ca
lled
AE
s
ar
e
d
esig
n
ed
to
lear
n
c
o
n
d
e
n
s
ed
d
ata
r
ep
r
esen
tatio
n
s
.
L
aten
t
f
ac
to
r
s
,
wh
ich
s
tan
d
f
o
r
u
s
er
p
r
e
f
er
e
n
ce
s
an
d
p
r
o
d
u
ct
attr
ib
u
tes,
ar
e
l
ea
r
n
ed
b
y
AE
s
in
r
ec
o
m
m
en
d
atio
n
s
y
s
tem
s
to
s
im
u
late
u
s
er
-
item
in
ter
ac
tio
n
m
atr
ices.
T
h
e
en
co
d
e
r
cr
ea
tes
a
lo
wer
-
d
im
en
s
io
n
al
laten
t
s
p
ac
e
th
at
en
co
d
es
u
s
er
-
item
in
ter
ac
tio
n
d
ata
b
y
co
m
p
r
ess
in
g
th
e
h
ig
h
-
d
im
en
s
io
n
al
u
s
er
-
item
in
ter
ac
tio
n
d
ata
.
On
th
e
o
t
h
er
ha
nd,
t
h
e
d
ec
o
d
er
r
ec
o
n
s
tr
u
ct
s
th
e
d
ata
b
ac
k
in
t
o
its
o
r
ig
in
al
s
tate
u
tili
zin
g
th
e
co
m
p
r
ess
ed
laten
t
v
ar
ia
b
les.
T
o
elab
o
r
ate,
af
ter
f
in
d
in
g
p
a
tter
n
s
an
d
f
o
r
m
in
g
late
n
t
f
ac
t
o
r
s
th
at
r
elate
u
s
er
s
an
d
item
s
,
AE
s
will
p
r
o
v
id
e
u
s
er
-
item
in
ter
ac
tio
n
s
th
at
th
ey
ass
u
m
e
u
s
er
s
will
p
r
ef
er
.
AE
s
also
h
av
e
a
g
r
ea
ter
r
o
b
u
s
tn
ess
to
s
p
ar
s
e
d
ata.
T
h
e
s
ep
ar
atio
n
f
r
o
m
a
f
ew
p
er
c
en
t
o
f
th
e
r
atin
g
s
allo
wed
th
e
au
th
o
r
s
to
test
AE
s
b
ased
o
n
s
tan
d
ar
d
m
at
r
ix
f
ac
to
r
izatio
n
an
d
r
atin
g
s
p
r
ed
icti
o
n
task
s
with
in
a
p
er
s
o
n
alize
d
r
ec
o
m
m
e
n
d
at
io
n
s
y
s
tem
,
an
d
f
o
u
n
d
n
o
s
tatis
tically
s
ig
n
if
ican
t d
if
f
er
en
ce
s
in
t
h
e
r
esu
lts
[
1
4
]
.
R
NNs
:
R
NN
s
ar
e
b
u
ilt
to
lear
n
o
v
er
s
eq
u
en
ce
s
o
f
d
ata
a
n
d
ar
e
th
er
ef
o
r
e
a
g
o
o
d
o
p
tio
n
f
o
r
lear
n
in
g
a
u
s
er
'
s
p
u
r
ch
ase
h
is
to
r
y
in
tim
e.
B
ec
au
s
e
R
NNs
ca
n
r
em
em
b
er
th
e
p
ast
elem
e
n
ts
(
ap
ar
t
f
r
o
m
th
e
f
in
al
o
u
t
p
u
t
)
o
f
a
s
er
ies
o
f
e
v
en
ts
,
th
ey
ca
n
lev
er
ag
e
th
is
m
em
o
r
y
to
u
n
d
er
s
tan
d
wh
en
f
ea
tu
r
es
in
a
u
s
er
'
s
b
eh
av
io
r
d
ep
e
n
d
u
p
o
n
o
t
h
er
f
ea
tu
r
es
o
f
th
eir
b
eh
av
io
r
-
s
u
c
h
as
s
h
o
p
p
in
g
p
att
er
n
s
,
ca
teg
o
r
ies
o
f
item
s
th
at
ar
e
o
f
in
ter
est,
an
d
p
r
o
m
o
tio
n
s
th
ey
r
esp
o
n
d
to
.
F
o
r
ex
am
p
le,
i
f
an
R
NN
h
as
a
s
eq
u
en
ce
o
f
p
ast
p
u
r
ch
ases
,
it
ca
n
in
f
er
th
e
n
ex
t
lik
ely
p
u
r
c
h
ase
an
d
m
o
r
e
im
p
o
r
tan
tly
,
r
ec
o
m
m
en
d
item
s
in
a
tim
e
-
s
en
s
itiv
e
m
an
n
er
[
1
5
]
,
[
1
6
]
.
T
r
an
s
f
o
r
m
e
r
-
b
ased
m
o
d
els
:
T
r
an
s
f
o
r
m
e
r
s
h
av
e
ch
a
n
g
ed
th
e
g
am
e
wh
en
it
c
o
m
es
to
s
eq
u
en
tial
m
o
d
elin
g
with
th
e
ad
v
en
t
o
f
s
elf
-
atten
tio
n
m
ec
h
a
n
is
m
s
th
a
t
allo
w
f
o
r
m
o
d
elin
g
b
o
th
s
h
o
r
t
-
an
d
lo
n
g
-
r
a
n
g
e
d
ep
en
d
e
n
cies
in
u
s
er
b
e
h
av
io
r
.
W
ith
r
esp
ec
t
to
r
ec
o
m
m
en
d
a
tio
n
s
,
tr
an
s
f
o
r
m
e
r
ar
ch
itectu
r
e
s
(
lik
e
SASR
ec
o
r
B
E
R
T
4
R
ec
)
ca
n
m
o
d
el
a
u
s
e
r
'
s
en
tire
s
eq
u
en
ce
o
f
in
ter
ac
tio
n
s
in
p
ar
allel
an
d
ea
ch
ac
tio
n
(
v
iews,
click
s
,
p
u
r
ch
ases
,
etc.
)
wo
u
ld
r
e
v
ea
l
its
co
n
tex
tu
al
s
ig
n
if
ican
ce
in
r
elatio
n
to
o
th
e
r
s
.
As
a
r
esu
lt,
co
n
tex
tu
ally
awa
r
e
o
r
d
y
n
a
m
ic
r
ec
o
m
m
en
d
atio
n
s
in
r
ea
l
tim
e
b
ec
o
m
e
p
o
s
s
ib
le,
allo
win
g
f
o
r
r
ap
id
ad
a
p
tatio
n
to
ch
an
g
es
in
u
s
er
b
eh
av
io
r
f
r
o
m
o
n
e
in
ter
ac
tio
n
to
th
e
n
ex
t.
I
n
ad
d
itio
n
t
o
th
e
ab
ilit
y
to
m
o
d
el
in
ter
ac
t
io
n
s
in
s
eq
u
en
ce
s
,
tr
an
s
f
o
r
m
er
-
b
ased
m
o
d
els
m
ay
also
b
e
f
in
e
-
tu
n
ed
o
n
p
r
o
d
u
ct
d
esc
r
ip
tio
n
s
an
d
u
s
er
q
u
er
i
es,
allo
win
g
f
o
r
th
e
co
m
b
in
atio
n
o
f
co
n
ten
t
-
b
ased
an
d
co
llab
o
r
ativ
e
s
ig
n
als
in
to
a
p
o
wer
f
u
l
h
y
b
r
id
p
er
s
o
n
aliza
tio
n
m
ec
h
an
is
m
[
1
7
]
,
[
1
8
]
.
3.
4
.
Cus
t
o
m
er
eng
a
g
e
m
ent
predict
io
n
C
u
s
to
m
er
en
g
ag
em
en
t
p
r
e
d
ictio
n
'
s
g
o
al
i
s
to
cla
s
s
if
y
u
s
er
s
i
n
to
g
r
o
u
p
s
o
f
"L
ik
ely
to
r
etu
r
n
,
"
"lik
ely
to
ch
u
r
n
,
"
an
d
"h
ig
h
ly
en
g
ag
e
d
,
"
b
ased
o
n
th
eir
h
is
to
r
ical
r
ec
o
r
d
s
o
f
e
n
g
ag
i
n
g
with
th
e
p
latf
o
r
m
,
an
d
b
ased
o
n
an
y
r
elativ
ely
s
tatio
n
ar
y
p
r
o
f
ile
in
f
o
r
m
atio
n
[
19
].
XGBo
o
s
t
is
an
en
s
em
b
le
lear
n
in
g
ap
p
r
o
ac
h
b
ased
o
n
g
r
ad
ien
t
b
o
o
s
tin
g
f
r
o
m
d
ec
is
io
n
tr
ee
s
.
Fro
m
ea
ch
u
p
d
ate
d
t
r
ee
,
we
h
ad
th
e
o
p
p
o
r
tu
n
ity
to
r
ed
u
ce
th
e
er
r
o
r
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
A
h
yb
r
id
A
I
fr
a
mewo
r
k
fo
r
h
y
p
er
-
p
ers
o
n
a
liz
ed
r
ec
o
mme
n
d
a
tio
n
s
a
n
d
…
(
P
a
r
a
s
h
iva
Mu
r
th
y
B
.
M
.
)
1875
th
e
p
r
ev
io
u
s
tr
ee
s
f
r
o
m
th
e
la
s
t
s
eq
u
en
tial
en
s
em
b
le
o
f
tr
ee
s
u
n
til
th
e
b
est
p
o
s
s
ib
le
lo
s
s
h
as
b
ee
n
ac
h
iev
ed
.
T
h
e
o
v
e
r
all
o
b
jectiv
e
in
XGBo
o
s
t is
(
1
)
:
(
)
=
∑
(
,
̂
)
+
∑
Ω
(
)
=
1
=
1
(
1
)
wh
er
e
(
,
̂
)
is
th
e
lo
s
s
f
u
n
ctio
n
,
∈
ℱ
is
a
d
ec
is
io
n
tr
ee
,
Ω
(
)
is
a
r
eg
u
lar
izatio
n
ter
m
an
d
̂
=
∑
Ω
(
)
=
1
.
E
ac
h
a
d
d
ed
tr
ee
m
in
i
m
izes
th
e
lo
s
s
b
y
u
s
in
g
g
r
ad
ie
n
t
d
escen
t
o
n
t
h
e
r
esid
u
als
f
r
o
m
th
e
last
en
s
em
b
le.
I
n
th
is
ca
s
e
o
f
p
r
ed
ictin
g
cu
s
t
o
m
er
en
g
a
g
em
en
t,
th
e
M
u
ltil
a
y
er
p
er
ce
p
t
r
o
n
u
s
e
o
n
e
o
r
m
o
r
e
p
o
s
s
ib
le
en
co
d
ed
in
p
u
t
f
ea
tu
r
es,
u
s
er
ac
tiv
ity
m
etr
ics
(
click
s
,
p
u
r
ch
ases
,
an
d
s
ess
io
n
len
g
th
)
an
d
u
s
er
o
r
p
r
o
d
u
ct
m
etad
ata.
E
ac
h
o
f
th
ese
in
p
u
t
s
is
co
n
n
ec
ted
th
r
o
u
g
h
o
n
e
o
r
m
o
r
e
h
id
d
en
la
y
er
s
o
f
f
u
lly
co
n
n
ec
ted
n
eu
r
o
n
s
,
wh
er
e
ea
ch
n
e
u
r
o
n
h
as
a
n
o
n
-
lin
ea
r
ac
tiv
atio
n
ap
p
lied
t
o
it
ty
p
ically
th
e
R
eL
U
ac
tiv
atio
n
f
u
n
cti
o
n
.
E
ac
h
o
f
th
ese
h
id
d
en
lay
er
s
ca
p
tu
r
es
all
o
f
th
e
co
m
p
lex
r
elatio
n
s
h
i
p
s
f
r
o
m
th
e
f
ir
s
t
h
id
d
en
lay
er
to
th
e
n
e
x
t,
to
th
e
n
ex
t
an
d
s
o
o
n
,
u
n
til
th
e
o
u
tp
u
t
lay
er
is
ac
ce
s
s
ib
le.
I
n
th
e
o
u
t
p
u
t
lay
e
r
,
t
h
e
m
o
d
el
u
s
es
a
s
o
f
tm
ax
ac
tiv
atio
n
t
o
s
tr
u
ctu
r
e
o
u
t
p
u
t
in
t
o
a
p
r
o
b
ab
ilit
y
d
is
tr
ib
u
tio
n
a
m
o
n
g
s
t
a
f
ew
d
ef
in
e
d
class
es
o
f
en
g
ag
em
en
t
s
u
c
h
as;
"L
ik
ely
to
ch
u
r
n
",
"L
ik
ely
to
r
etu
r
n
",
o
r
"Hig
h
ly
en
g
a
g
ed
"
o
r
ev
e
n
s
o
m
e
o
r
i
g
in
al
o
r
a
r
tific
ial
d
er
iv
ed
o
u
tp
u
t
class
es,
b
u
t
n
o
m
in
ally
h
er
e
it
will
as
s
ig
n
th
e
m
o
s
t
lik
ely
en
g
a
g
em
en
t
s
tatu
s
.
T
h
e
m
ath
em
atica
l
f
o
r
m
u
latio
n
s
ar
e
as
(
2
)
-
(
4
)
:
ℎ
(
1
)
=
(
(
1
)
+
(
1
)
(
2
)
ℎ
(
2
)
=
(
(
2
)
ℎ
(
1
)
+
(
2
)
)
(
3
)
̂
=
(
(
3
)
ℎ
(
2
)
+
(
3
)
)
(
4
)
wh
er
e
is
th
e
ac
tiv
atio
n
f
u
n
ctio
n
,
x
is
th
e
in
p
u
t
v
ec
to
r
,
(
)
,
(
)
ar
e
th
e
weig
h
ts
an
d
b
iases
o
f
lay
er
i
an
d
̂
is
th
e
p
r
ed
icted
class
p
r
o
b
ab
ilit
ies.
T
h
e
en
s
em
b
le
co
m
b
in
es
th
e
ad
v
a
n
tag
es
o
f
XG
B
o
o
s
t
an
d
ML
P.
XGBo
o
s
t
ca
p
tu
r
es
th
e
s
tr
u
ctu
r
ed
r
elatio
n
s
h
ip
s
an
d
d
ec
is
io
n
b
o
u
n
d
ar
ies.
ML
P
lear
n
s
th
e
co
m
p
lex
,
n
o
n
-
lin
ea
r
in
ter
ac
tio
n
s
an
d
r
e
p
r
esen
tatio
n
s
.
T
h
e
f
u
s
io
n
a
p
p
r
o
ac
h
es a
r
e
s
o
f
t v
o
tin
g
an
d
s
tack
in
g
ar
e
r
ep
r
esen
ted
as
(
5
)
:
̂
=
.
̂
̂
+
(
1
−
)
.
̂
(
5
)
wh
er
e
∈
[
0
.
1
]
is
a
weig
h
t
p
ar
am
eter
b
alan
cin
g
b
o
th
m
o
d
els.
T
h
e
s
tack
in
g
o
f
XGBo
o
s
t
an
d
ML
P
p
r
o
d
u
ce
in
ter
m
ed
iate
p
r
e
d
ictio
n
s
.
T
h
es
e
p
r
ed
ictio
n
s
b
ec
o
m
e
f
ea
t
u
r
es f
o
r
th
e
m
eta
class
if
ier
.
T
h
e
p
r
o
p
o
s
ed
s
m
ar
t
co
m
m
er
c
e
f
r
am
ewo
r
k
is
a
co
m
b
in
atio
n
o
f
h
y
p
er
-
p
er
s
o
n
alize
d
r
ec
o
m
m
en
d
atio
n
g
en
er
atio
n
with
p
r
ed
ictiv
e
cu
s
to
m
er
en
g
ag
em
en
t
in
a
u
n
if
ied
p
ip
elin
e.
Un
lik
e
p
r
ev
io
u
s
h
y
b
r
i
d
im
p
lem
en
tatio
n
s
,
wh
ich
o
n
ly
wo
r
k
o
n
eith
er
co
llab
o
r
ativ
e
-
co
n
ten
t
r
ec
o
m
m
en
d
atio
n
o
r
s
eq
u
e
n
tial
u
s
er
b
eh
av
io
r
th
is
f
r
am
ewo
r
k
i
n
c
o
r
p
o
r
ates
au
to
en
c
o
d
er
s
,
R
NNs,
an
d
T
r
an
s
f
o
r
m
er
-
b
ased
m
o
d
els
f
o
r
d
y
n
a
m
ic
p
er
s
o
n
aliza
tio
n
an
d
at
th
e
s
am
e
tim
e
th
e
en
g
a
g
em
en
t le
v
els
u
s
in
g
a
weig
h
ted
XGBo
o
s
t
-
M
L
P e
n
s
em
b
le.
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
E
x
p
er
im
en
ts
wer
e
p
e
r
f
o
r
m
ed
o
n
a
wo
r
k
s
tatio
n
with
Nv
id
ia
R
T
X
3
0
9
0
GPU,
6
4
GB
R
AM
an
d
an
I
n
tel
i9
C
PU.
T
h
ese
s
p
ec
if
icatio
n
s
m
ad
e
s
u
r
e
th
e
r
e
was su
f
f
icien
t c
o
m
p
u
tatio
n
al
p
o
wer
f
o
r
DL
m
o
d
el
tr
ain
in
g
an
d
ef
f
icien
t
d
ata
h
an
d
lin
g
o
f
m
ass
iv
e
am
o
u
n
ts
o
f
e
-
c
o
m
m
e
r
ce
d
ata.
T
o
m
ak
e
th
e
e
x
p
er
i
m
en
ts
r
ep
r
o
d
u
cib
le,
all
th
e
e
x
p
er
im
en
ts
wer
e
im
p
lem
en
ted
in
p
y
th
o
n
with
T
en
s
o
r
Flo
w/Ker
as
f
o
r
DL
an
d
Sc
ik
it
-
lear
n
/XGB
o
o
s
t
f
o
r
tr
ad
itio
n
al
a
n
d
en
s
em
b
le
m
o
d
els.
R
an
d
o
m
s
ee
d
s
wer
e
r
an
d
o
m
l
y
f
ix
ed
in
Nu
m
Py
,
T
en
s
o
r
Flo
w
an
d
Py
th
o
n
'
s
r
an
d
o
m
m
o
d
u
le.
Fo
r
b
o
th
t
h
e
r
ec
o
m
m
en
d
atio
n
a
n
d
en
g
a
g
em
en
t
p
r
ed
i
ctio
n
task
s
,
t
h
e
tr
ain
in
g
s
et
(
7
0
%)
was
u
s
ed
to
tr
ain
th
e
m
o
d
els,
th
e
v
alid
atio
n
s
et
(
1
5
%
)
was
u
s
ed
f
o
r
h
y
p
e
r
-
p
a
r
am
ete
r
s
tu
n
in
g
an
d
ea
r
ly
s
to
p
p
in
g
an
d
th
e
test
s
et
(
1
5
%
)
was k
ep
t f
o
r
test
in
g
f
in
al
p
e
r
f
o
r
m
an
ce
.
4
.
1
.
H
y
perpa
ra
m
e
t
er
s
et
t
ing
s
T
h
e
Au
to
en
co
d
er
m
o
d
el
f
o
r
r
e
co
m
m
en
d
atio
n
co
n
s
is
ted
o
f
a
n
en
co
d
er
a
n
d
a
d
e
co
d
er
with
t
h
r
ee
f
u
lly
co
n
n
ec
ted
lay
er
s
o
f
5
1
2
,
2
5
6
an
d
1
2
8
n
e
u
r
o
n
s
th
at
c
o
m
p
r
ess
ed
th
e
u
s
er
-
item
in
ter
ac
tio
n
m
atr
ix
to
a
64
-
d
im
e
n
s
io
n
al
laten
t
s
p
ac
e.
T
r
ain
in
g
was
d
o
n
e
u
s
in
g
Ad
a
m
o
p
tim
izer
with
lear
n
in
g
r
ate
as
0
.
0
0
1
,
b
atch
s
ize
as
2
5
6
an
d
1
0
0
e
p
o
ch
s
b
u
t
we
ap
p
lied
ea
r
ly
s
to
p
p
in
g
a
f
ter
1
0
n
o
n
-
im
p
r
o
v
in
g
ep
o
ch
s
o
n
v
alid
atio
n
d
ata.
I
n
th
e
R
NN
m
o
d
el,
th
e
m
o
d
el
c
o
n
s
is
ted
o
f
a
s
in
g
le
lay
e
r
L
S
T
M
with
1
2
8
h
id
d
e
n
u
n
its
.
5
0
in
ter
ac
tio
n
s
f
r
o
m
e
ac
h
u
s
er
wer
e
p
ad
d
ed
o
r
tr
i
m
m
ed
.
T
h
e
T
r
a
n
s
f
o
r
m
er
m
o
d
el
is
a
f
o
u
r
atten
tio
n
h
ea
d
s
s
i
n
g
le
lay
er
en
co
d
er
with
h
id
d
e
n
d
im
en
s
io
n
1
2
8
,
p
o
s
itio
n
al
en
co
d
in
g
,
an
d
d
r
o
p
o
u
t
0
.
1
a
n
d
is
t
r
ain
ed
u
s
in
g
Ad
am
W
,
lear
n
in
g
r
ate
0
.
0
0
0
5
,
an
d
b
atc
h
s
ize
6
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
5
,
No
.
4
,
D
e
c
em
b
er
20
2
6
:
1
8
7
1
-
1
8
8
0
1876
Fo
r
en
g
a
g
em
en
t
p
r
e
d
ic
tio
n
,
a
m
ax
tr
ee
d
ep
t
h
o
f
6
,
5
0
0
tr
ee
s
an
d
lear
n
in
g
r
ate
o
f
0
.
1
wer
e
u
s
ed
f
o
r
th
e
XGBo
o
s
t
class
if
ier
with
L
1
an
d
L
2
r
eg
u
lar
izatio
n
p
ar
am
eter
s
s
ea
r
ch
as
a
=
0
.
1
an
d
l
=
1
.
T
h
e
ML
P
co
n
s
is
ted
o
f
two
h
i
d
d
en
lay
e
r
s
(
1
2
8
/6
4
n
eu
r
o
n
s
)
,
R
eL
U
a
ctiv
atio
n
,
d
r
o
p
o
u
t
r
at
e
(
0
.
2
)
,
an
d
s
o
f
tm
a
x
o
u
tp
u
t
lay
er
,
Ad
a
m
o
p
tim
izer
,
1
0
0
e
p
o
ch
s
,
a
n
d
b
atch
s
ize
(
1
2
8
)
.
T
h
e
en
s
em
b
le
was
a
co
m
b
i
n
atio
n
o
f
XGBo
o
s
t
an
d
ML
P with
s
o
f
t v
o
tin
g
a
=
0
.
6
an
d
0
.
4
,
r
es
p
ec
tiv
ely
,
f
o
r
XGBo
o
s
t a
n
d
ML
P.
4
.
1
.
P
er
f
o
r
m
a
nce
e
v
a
lua
t
io
n
R
ec
o
m
m
en
d
atio
n
m
o
d
el
p
e
r
f
o
r
m
an
ce
was
m
ea
s
u
r
ed
b
y
Pre
c
is
io
n
@
1
0
,
R
ec
all@
1
0
,
an
d
NDCG
@
1
0
to
ass
ess
th
e
r
elev
an
ce
a
n
d
th
e
q
u
ality
o
f
th
e
r
an
k
in
g
o
f
t
h
e
r
ec
o
m
m
en
d
atio
n
s
in
th
e
t
o
p
1
0
.
E
n
g
a
g
em
en
t
p
r
ed
ictio
n
m
o
d
els
wer
e
test
e
d
to
ca
p
tu
r
e
th
e
co
r
r
ec
tn
ess
o
f
th
e
p
r
ed
ictio
n
,
b
ala
n
ce
b
et
w
ee
n
p
r
ec
is
io
n
an
d
r
ec
all
an
d
o
v
er
all
d
is
cr
im
in
at
iv
e
ab
ilit
y
o
f
p
r
ed
ictio
n
s
b
et
wee
n
en
g
ag
em
en
t
class
es.
T
h
e
r
esu
lts
lis
ted
in
T
ab
le
1
m
ak
e
a
co
m
p
ar
is
o
n
o
f
th
e
p
r
o
p
o
s
ed
h
y
b
r
i
d
DL
m
o
d
el
with
SVD,
T
F
-
I
DF,
an
d
p
o
p
u
lar
ity
b
ased
.
T
ab
le
1
r
esu
lts
in
d
icate
th
at,
o
n
t
h
e
wh
o
le,
n
e
v
er
d
id
th
e
Pro
p
o
s
ed
Hy
b
r
i
d
DL
Mo
d
el
f
ail
to
o
u
tp
er
f
o
r
m
all
o
f
th
e
b
aselin
e
m
eth
o
d
s
f
o
r
all
th
r
ee
o
f
th
e
m
etr
ics.
T
h
e
b
est
Pre
cisi
o
n
@
1
0
(
0
.
3
8
2
)
,
R
ec
all
@
1
0
(
0
.
4
4
1
)
,
an
d
ND
C
G
@
1
0
(
0
.
4
6
9
)
wer
e
ac
h
ie
v
ed
b
y
th
e
s
u
g
g
ested
h
y
b
r
i
d
DL
m
o
d
el.
T
h
is
d
em
o
n
s
tr
ates
th
at
th
e
s
u
g
g
est
ed
h
y
b
r
id
DL
m
o
d
el
was
ab
le
to
r
a
n
k
th
e
m
o
s
t
r
ele
v
an
t
ite
m
s
h
ig
h
er
,
r
etu
r
n
th
e
h
ig
h
est p
er
ce
n
ta
g
e
o
f
all
r
elev
an
t item
s
,
an
d
p
r
o
p
o
s
e
th
e
m
o
s
t r
elev
an
t item
s
.
Fig
u
r
e
2
s
h
o
ws
th
at
th
r
ee
d
if
f
er
en
t
r
ec
o
m
m
e
n
d
atio
n
a
p
p
r
o
a
ch
es
p
er
f
o
r
m
b
etter
,
wo
r
s
e,
o
r
ab
o
u
t
th
e
s
am
e
ac
co
r
d
in
g
to
ea
c
h
o
f
t
h
e
th
r
ee
m
etr
ics:
Pre
cisi
o
n
,
R
ec
all
an
d
NDCG,
wh
en
ev
alu
ated
o
n
th
e
s
am
e
f
ig
u
r
e.
T
h
e
p
r
o
p
o
s
ed
h
y
b
r
id
DL
m
o
d
el
o
u
tp
er
f
o
r
m
ed
o
th
e
r
m
o
d
els
in
ter
m
s
o
f
th
e
r
ec
o
m
m
en
d
atio
n
ac
cu
r
ac
y
an
d
r
a
n
k
in
g
q
u
ality
with
s
co
r
e
s
0
.
3
8
2
,
0
.
4
4
1
a
n
d
0
.
4
6
9
r
esp
e
ctiv
ely
.
SVD
p
er
f
o
r
m
e
d
r
ea
s
o
n
ab
ly
well
b
u
t T
F
-
I
DF
p
r
o
d
u
ce
d
r
elativ
ely
lo
wer
p
er
f
o
r
m
an
ce
.
T
h
e
Po
p
u
lar
ity
B
ased
R
ec
o
m
m
en
d
atio
n
m
eth
o
d
was
th
e
p
o
o
r
est
o
f
all
th
e
ev
alu
atio
n
m
etr
ics.
Ov
er
all,
r
esu
lts
s
h
o
w
th
at
th
e
p
r
o
p
o
s
ed
h
y
b
r
id
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
is
ab
le
to
en
h
an
ce
th
e
p
er
s
o
n
alize
d
r
e
co
m
m
en
d
atio
n
a
b
ilit
y
,
r
etr
ie
v
al
ef
f
ec
tiv
e
n
ess
an
d
r
an
k
in
g
r
elev
a
n
ce
m
o
r
e
ef
f
ec
tiv
ely
th
an
th
e
tr
ad
itio
n
al
r
ec
o
m
m
en
d
atio
n
tec
h
n
iq
u
es.
T
ab
le
2
s
h
o
ws
th
e
p
er
f
o
r
m
an
c
e
co
m
p
ar
is
o
n
o
f
t
h
e
E
n
s
em
b
le
C
las
s
if
ier
with
R
F,
L
R
an
d
DT
u
s
in
g
ev
alu
atio
n
s
tatis
tics
,
wh
ich
in
clu
d
e
ac
cu
r
ac
y
,
F1
-
Sco
r
e,
an
d
R
O
C
-
AUC.
T
h
e
p
r
o
p
o
s
ed
en
s
em
b
le
class
if
ier
,
a
co
m
b
in
atio
n
o
f
XGBo
o
s
t
an
d
a
ML
P,
o
u
tp
er
f
o
r
m
e
d
all
o
th
er
m
o
d
els
with
th
e
h
ig
h
est
s
co
r
es
o
n
all
th
r
ee
m
etr
ics:
Acc
u
r
ac
y
(
0
.
9
1
2
)
,
F1
-
Sco
r
e
(
0
.
8
8
6
)
an
d
R
OC
-
AUC
(
0
.
9
3
7
)
.
T
h
is
s
u
g
g
ests
th
at
n
o
t
o
n
ly
is
th
e
en
s
em
b
le
class
if
ier
ab
le
to
cl
ass
if
y
a
h
ig
h
er
p
er
ce
n
ta
g
e
o
f
in
s
tan
ce
s
co
r
r
ec
tly
,
it
h
as
ef
f
ec
tiv
ely
m
an
ag
ed
to
b
alan
ce
p
r
ec
is
io
n
a
n
d
r
ec
all,
a
n
d
is
b
etter
at
d
is
tin
g
u
is
h
in
g
c
lass
es a
t th
r
esh
o
ld
v
a
lu
es.
As
s
h
o
wn
in
F
ig
u
r
e
3
,
t
h
e
p
r
o
p
o
s
ed
E
n
s
em
b
le
C
lass
if
ier
(
XGBo
o
s
t
+
ML
P)
o
u
tp
er
f
o
r
m
ed
o
th
e
r
m
o
d
els,
with
0
.
9
1
2
Acc
u
r
ac
y
,
0
.
8
8
6
F1
-
Sco
r
e,
an
d
0
.
9
3
7
R
OC
-
AU
C
,
d
em
o
n
s
tr
atin
g
its
ab
ilit
y
to
class
if
y
wi
th
h
ig
h
ac
c
u
r
ac
y
a
n
d
r
eliab
ilit
y
.
R
F
s
h
o
wed
co
m
p
etitiv
e
p
er
f
o
r
m
an
ce
,
b
u
t
was
s
till
n
o
t
as
h
ig
h
as
th
e
p
r
o
p
o
s
ed
en
s
em
b
le
ap
p
r
o
ac
h
.
Oth
er
class
if
ier
s
s
u
ch
as
L
R
o
r
DT
g
av
e
a
r
elativ
ely
p
o
o
r
p
er
f
o
r
m
an
ce
o
n
all
th
e
ass
es
s
m
en
t
cr
iter
ia.
I
n
g
e
n
er
al,
th
e
r
esu
lts
v
alid
ate
th
e
p
o
s
itiv
e
ef
f
ec
ts
o
f
th
e
en
s
em
b
le
-
b
ased
h
y
b
r
id
lear
n
in
g
m
o
d
el
in
ter
m
s
o
f
ac
cu
r
ac
y
,
r
o
b
u
s
tn
ess
,
an
d
ef
f
ec
ti
v
en
ess
o
f
en
g
ag
em
en
t
p
r
ed
icti
o
n
,
co
m
p
ar
e
d
with
tr
ad
itio
n
al
m
ac
h
in
e
lear
n
in
g
-
b
ased
m
eth
o
d
s
.
T
ab
le
1
.
Per
s
o
n
aliza
tio
n
p
er
f
o
r
m
an
ce
co
m
p
ar
is
o
n
M
e
t
h
o
d
/
M
o
d
e
l
P
r
e
c
i
s
i
o
n
@
1
0
R
e
c
a
l
l
@
1
0
N
D
C
G
@
1
0
P
r
o
p
o
se
d
h
y
b
r
i
d
D
L
m
o
d
e
l
0
.
3
8
2
0
.
4
4
1
0
.
4
6
9
S
V
D
[
2
0
]
0
.
2
7
6
0
.
3
1
2
0
.
3
2
8
TF
-
I
D
F
[
2
1
]
0
.
2
4
1
0
.
2
8
9
0
.
2
9
5
P
o
p
u
l
a
r
i
t
y
-
B
a
se
d
R
e
c
o
mm
e
n
d
a
t
i
o
n
[
2
2
]
0
.
1
9
4
0
.
2
1
6
0
.
2
3
8
Fig
u
r
e
2
.
C
o
m
p
a
r
ativ
e
an
aly
s
i
s
o
f
r
ec
o
m
m
e
n
d
atio
n
p
er
f
o
r
m
an
ce
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
A
h
yb
r
id
A
I
fr
a
mewo
r
k
fo
r
h
y
p
er
-
p
ers
o
n
a
liz
ed
r
ec
o
mme
n
d
a
tio
n
s
a
n
d
…
(
P
a
r
a
s
h
iva
Mu
r
th
y
B
.
M
.
)
1877
T
ab
le
2
.
E
n
g
ag
em
e
n
t p
r
e
d
ictio
n
p
er
f
o
r
m
a
n
ce
co
m
p
ar
is
o
n
M
o
d
e
l
/
M
e
t
h
o
d
A
c
c
u
r
a
c
y
F1
-
S
c
o
r
e
R
O
C
-
AUC
P
r
o
p
o
se
d
e
n
s
e
m
b
l
e
c
l
a
ss
i
f
i
e
r
(
X
G
B
o
o
st
+
M
LP)
0
.
9
1
2
0
.
8
8
6
0
.
9
3
7
R
a
n
d
o
m f
o
r
e
s
t
c
l
a
ss
i
f
i
e
r
(
R
F
)
[
2
3
]
0
.
8
7
4
0
.
8
4
2
0
.
9
0
2
Lo
g
i
s
t
i
c
r
e
g
r
e
ssi
o
n
(
L
R
)
[
2
4
]
0
.
7
9
4
0
.
7
2
1
0
.
8
1
2
D
e
c
i
s
i
o
n
t
r
e
e
c
l
a
ss
i
f
i
e
r
(
D
T)
[
2
5
]
0
.
7
8
1
0
.
7
0
3
0
.
7
9
5
Fig
u
r
e
3
.
C
o
m
p
a
r
is
o
n
o
f
en
g
a
g
em
en
t p
r
e
d
ictio
n
p
e
r
f
o
r
m
an
c
e
5.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
d
em
o
n
s
tr
ates
th
e
e
f
f
ec
tiv
en
ess
o
f
lev
e
r
ag
in
g
AI
an
d
ML
to
en
h
a
n
ce
p
er
s
o
n
aliza
tio
n
an
d
cu
s
to
m
er
en
g
ag
e
m
en
t
in
s
m
ar
t
co
m
m
er
ce
en
v
ir
o
n
m
en
ts
.
B
y
in
teg
r
atin
g
DL
-
b
ased
r
ec
o
m
m
en
d
atio
n
s
y
s
tem
s
with
p
r
ed
ictiv
e
en
g
a
g
em
en
t
m
o
d
els,
th
e
p
r
o
p
o
s
ed
f
r
a
m
ewo
r
k
s
ig
n
if
ican
tly
o
u
tp
er
f
o
r
m
ed
tr
a
d
itio
n
al
ap
p
r
o
ac
h
es
in
b
o
th
r
ec
o
m
m
e
n
d
atio
n
ac
cu
r
ac
y
an
d
b
eh
a
v
i
o
r
al
p
r
ed
ictio
n
.
T
h
e
h
y
b
r
id
m
o
d
el
ac
h
iev
ed
h
ig
h
s
co
r
es
ac
r
o
s
s
k
ey
m
etr
ics,
af
f
ir
m
in
g
its
ab
ilit
y
to
d
eliv
er
r
elev
an
t,
tim
ely
,
an
d
e
n
g
ag
in
g
u
s
er
ex
p
er
ie
n
ce
s
.
T
h
ese
f
in
d
in
g
s
s
u
p
p
o
r
t
th
e
s
tr
ateg
ic
im
p
lem
en
tatio
n
o
f
in
te
llig
en
t
s
y
s
tem
s
f
o
r
d
r
iv
in
g
cu
s
to
m
er
s
atis
f
ac
tio
n
an
d
r
ete
n
tio
n
in
c
o
m
p
etitiv
e
e
-
co
m
m
er
ce
m
ar
k
ets.
Fo
r
f
u
tu
r
e
wo
r
k
,
s
ev
er
al
d
ir
ec
tio
n
s
ca
n
b
e
ex
p
lo
r
ed
.
I
n
co
r
p
o
r
atin
g
r
ea
l
-
tim
e
d
ata
s
tr
ea
m
s
an
d
r
ein
f
o
r
ce
m
en
t
lear
n
in
g
ca
n
en
a
b
le
ad
ap
tiv
e
p
er
s
o
n
aliza
tio
n
th
at
ev
o
lv
es
with
u
s
er
b
e
h
av
io
r
.
A
d
d
itio
n
ally
,
in
teg
r
atin
g
m
u
ltimo
d
al
d
ata
s
o
u
r
ce
s
s
u
c
h
as
p
r
o
d
u
ct
im
a
g
es,
u
s
er
-
g
en
er
ated
co
n
ten
t,
an
d
s
o
cial
m
ed
ia
s
en
tim
en
t
ca
n
f
u
r
th
e
r
en
r
ich
u
s
er
p
r
o
f
iles
an
d
r
ec
o
m
m
en
d
atio
n
q
u
ality
.
Ad
d
r
ess
in
g
co
ld
-
s
tar
t
p
r
o
b
le
m
s
an
d
e
n
s
u
r
in
g
f
air
n
ess
an
d
tr
an
s
p
ar
en
cy
i
n
AI
r
ec
o
m
m
en
d
atio
n
s
also
r
em
ain
cr
itical
ar
ea
s
f
o
r
r
esear
ch
a
n
d
d
ev
elo
p
m
e
n
t.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
No
f
u
n
d
in
g
in
v
o
lv
e
d
.
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
Par
ash
iv
a
Mu
r
th
y
B
.
M
.
✓
✓
✓
✓
✓
✓
✓
✓
✓
Scar
ia
Alex
✓
✓
✓
✓
I
s
aiv
an
i
Ma
r
iy
ap
p
a
n
✓
✓
✓
✓
✓
✓
✓
Kaly
an
Dev
ap
p
a
B
am
an
e
✓
Kav
ith
a
R
.
✓
✓
✓
✓
✓
S Ath
in
ar
ay
an
an
✓
✓
✓
✓
✓
✓
✓
Su
n
d
er
R
.
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
5
,
No
.
4
,
D
e
c
em
b
er
20
2
6
:
1
8
7
1
-
1
8
8
0
1878
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
er
e
is
n
o
c
o
n
f
lict o
f
in
ter
est
.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
i
n
d
in
g
s
o
f
th
is
s
tu
d
y
a
r
e
o
p
e
n
ly
av
ailab
le
in
h
ttp
s
://www.
k
ag
g
le.
co
m
/
d
atasets
/ m
lg
-
u
lb
/cr
ed
itcar
d
f
r
a
u
d
.
RE
F
E
R
E
NC
E
S
[
1
]
N
.
M
.
A
l
k
u
d
a
h
a
n
d
T.
O
.
A
l
mo
m
a
n
i
,
“
Th
e
i
n
t
e
g
r
a
t
i
o
n
o
f
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
t
e
c
h
n
i
q
u
e
s
i
n
e
-
c
o
m
merc
e
:
E
n
h
a
n
c
i
n
g
o
n
l
i
n
e
sh
o
p
p
i
n
g
e
x
p
e
r
i
e
n
c
e
a
n
d
p
e
r
so
n
a
l
i
z
a
t
i
o
n
,
”
G
l
o
b
a
l
J
o
u
r
n
a
l
o
f
Ec
o
n
o
m
i
c
a
n
d
B
u
si
n
e
ss
,
v
o
l
.
1
4
,
n
o
.
6
,
p
p
.
6
4
0
–
6
5
8
,
D
e
c
.
2
0
2
4
,
d
o
i
:
1
0
.
3
1
5
5
9
/
g
j
e
b
2
0
2
4
.
1
4
.
6
.
8
.
[
2
]
V
.
M
.
R
e
d
d
y
a
n
d
L
.
N
.
N
a
l
l
a
,
“
P
e
r
so
n
a
l
i
z
a
t
i
o
n
i
n
e
-
c
o
mm
e
r
c
e
m
a
r
k
e
t
i
n
g
:
l
e
v
e
r
a
g
i
n
g
b
i
g
d
a
t
a
f
o
r
t
a
i
l
o
r
e
d
c
o
n
s
u
mer e
n
g
a
g
e
m
e
n
t
,
”
Re
v
i
st
a
D
e
I
n
t
e
l
i
g
e
n
c
i
a
A
rt
i
f
i
c
i
a
l
E
n
Me
d
i
c
i
n
a
,
v
o
l
.
1
5
,
n
o
.
1
,
p
p
.
6
9
1
–
7
2
5
,
2
0
2
4
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
r
e
d
c
r
e
v
i
s
t
a
s
.
c
o
m/
i
n
d
e
x
.
p
h
p
/
R
e
v
i
s
t
a
[
3
]
A
.
G
.
A
i
s
h
w
a
r
y
a
G
o
w
d
a
,
H
.
K
.
S
u
,
a
n
d
W
.
K
.
K
u
o
,
“
P
e
r
so
n
a
l
i
z
e
d
E
-
c
o
mm
e
r
c
e
:
En
h
a
n
c
i
n
g
C
u
s
t
o
m
e
r
E
x
p
e
r
i
e
n
c
e
t
h
r
o
u
g
h
M
a
c
h
i
n
e
Le
a
r
n
i
n
g
-
d
r
i
v
e
n
P
e
r
s
o
n
a
l
i
z
a
t
i
o
n
,
”
i
n
2
0
2
4
I
EE
E
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
El
e
c
t
ro
n
i
c
s
a
n
d
I
n
t
e
l
l
i
g
e
n
t
C
o
m
m
u
n
i
c
a
t
i
o
n
S
y
st
e
m
s (I
C
I
T
EI
C
S
)
,
I
EEE,
J
u
n
.
2
0
2
4
,
p
p
.
1
–
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
TEI
C
S
6
1
3
6
8
.
2
0
2
4
.
1
0
6
2
4
9
0
1
.
[
4
]
K
.
K
a
l
i
u
t
a
,
“
P
e
r
s
o
n
a
l
i
z
i
n
g
t
h
e
u
s
e
r
e
x
p
e
r
i
e
n
c
e
i
n
S
a
l
e
sf
o
r
c
e
u
s
i
n
g
A
I
t
e
c
h
n
o
l
o
g
i
e
s
,
”
C
o
m
p
u
t
e
r
-
I
n
t
e
g
r
a
t
e
d
T
e
c
h
n
o
l
o
g
i
e
s
:
E
d
u
c
a
t
i
o
n
,
S
c
i
e
n
c
e
,
Pr
o
d
u
c
t
i
o
n
,
n
o
.
5
2
,
p
p
.
4
8
–
5
3
,
2
0
2
3
,
d
o
i
:
1
0
.
3
6
9
1
0
/
6
7
7
5
-
2524
-
0560
-
2023
-
52
-
06.
[
5
]
X
.
Z
h
a
n
g
,
F
.
G
u
o
,
T.
C
h
e
n
,
L.
P
a
n
,
G
.
B
e
l
i
a
k
o
v
,
a
n
d
J.
W
u
,
“
A
b
r
i
e
f
s
u
r
v
e
y
o
f
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
f
o
r
e
-
c
o
m
merc
e
r
e
sea
r
c
h
,
”
J
o
u
rn
a
l
o
f
T
h
e
o
r
e
t
i
c
a
l
a
n
d
A
p
p
l
i
e
d
E
l
e
c
t
r
o
n
i
c
C
o
m
m
e
rce
Re
se
a
rc
h
,
v
o
l
.
1
8
,
n
o
.
4
,
p
p
.
2
1
8
8
–
2
2
1
6
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
j
t
a
e
r
1
8
0
4
0
1
1
0
.
[
6
]
L.
L
i
u
,
“
E
-
c
o
mm
e
r
c
e
p
e
r
s
o
n
a
l
i
z
e
d
r
e
c
o
mm
e
n
d
a
t
i
o
n
b
a
se
d
o
n
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
o
l
o
g
y
,
”
M
o
b
i
l
e
I
n
f
o
rm
a
t
i
o
n
S
y
s
t
e
m
s
,
v
o
l
.
2
0
2
2
,
n
o
.
1
,
p
.
1
7
6
1
5
7
9
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
1
7
6
1
5
7
9
.
[
7
]
H
.
K
.
T
h
a
k
u
r
,
J
.
S
i
n
g
h
,
A
.
S
a
x
e
n
a
,
D
.
B
h
a
s
k
a
r
,
A
.
P
.
S
i
n
g
h
,
a
n
d
P
.
K
.
G
a
r
g
,
“
E
n
h
a
n
c
i
n
g
c
u
s
t
o
mer
e
x
p
e
r
i
e
n
c
e
t
h
r
o
u
g
h
A
I
-
p
o
w
e
r
e
d
p
e
r
s
o
n
a
l
i
z
a
t
i
o
n
:
a
d
a
t
a
sc
i
e
n
c
e
p
e
r
sp
e
c
t
i
v
e
i
n
e
-
c
o
mm
e
r
c
e
,
”
i
n
2
0
2
4
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
m
u
n
i
c
a
t
i
o
n
,
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
s
a
n
d
E
n
g
i
n
e
e
r
i
n
g
(
I
C
3
S
E)
,
I
EEE,
M
a
y
2
0
2
4
,
p
p
.
5
0
1
–
506
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
3
S
E
6
2
0
0
2
.
2
0
2
4
.
1
0
5
9
2
8
9
3
.
[
8
]
K
.
U
p
r
e
t
i
,
D
.
G
a
n
g
w
a
r
,
P
.
V
a
t
s,
R
.
B
h
a
r
d
w
a
j
,
V
.
K
h
a
t
r
i
,
a
n
d
V
.
G
a
u
t
a
m,
“
A
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s fo
r
e
n
h
a
n
c
i
n
g
e
-
c
o
mm
e
r
c
e
:
a
st
u
d
y
o
n
i
mp
r
o
v
i
n
g
p
e
r
s
o
n
a
l
i
z
a
t
i
o
n
,
r
e
c
o
m
me
n
d
a
t
i
o
n
,
a
n
d
c
u
s
t
o
mer
e
x
p
e
r
i
e
n
c
e
,
”
i
n
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
El
e
c
t
r
i
c
a
l
a
n
d
El
e
c
t
r
o
n
i
c
s
E
n
g
i
n
e
e
r
i
n
g
,
2
0
2
4
,
p
p
.
1
4
1
–
1
5
3
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
99
-
8
6
6
1
-
3
_
1
1
.
[
9
]
Q
.
L
i
u
,
H
.
Ta
n
g
,
L.
W
u
,
a
n
d
Z.
C
h
a
o
,
“
D
e
e
p
l
e
a
r
n
i
n
g
-
d
r
i
v
e
n
e
-
c
o
mm
e
r
c
e
mark
e
t
i
n
g
c
o
mm
u
n
i
c
a
t
i
o
n
f
o
r
r
e
c
o
m
men
d
i
n
g
s
h
o
p
p
i
n
g
sy
st
e
m
a
n
d
o
p
t
i
mi
z
i
n
g
u
ser
e
x
p
e
r
i
e
n
c
e
,
”
J
o
u
rn
a
l
o
f
O
r
g
a
n
i
za
t
i
o
n
a
l
a
n
d
En
d
U
s
e
r
C
o
m
p
u
t
i
n
g
,
v
o
l
.
3
6
,
n
o
.
1
,
p
p
.
1
–
2
8
,
M
a
y
2
0
2
4
,
d
o
i
:
1
0
.
4
0
1
8
/
JO
EU
C
.
3
4
3
2
5
8
.
[
1
0
]
G
.
K
u
mar,
G
.
D
e
v
a
y
a
n
i
,
C
.
S
a
r
a
sw
a
t
h
i
,
R
.
M
e
l
b
a
K
a
n
i
,
S
.
D
o
n
g
r
e
,
a
n
d
M
.
S
.
M
.
M
a
l
l
i
c
k
,
“
E
x
p
l
o
r
i
n
g
c
o
n
su
mer
b
e
h
a
v
i
o
r
i
n
e
-
c
o
mm
e
r
c
e
w
i
t
h
A
I
p
e
r
s
o
n
a
l
i
z
a
t
i
o
n
a
n
d
mar
k
e
t
t
r
e
n
d
s
a
n
a
l
y
si
s
mo
d
e
l
s,
”
i
n
2
0
2
5
3
r
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
n
t
e
g
r
a
t
e
d
C
i
rc
u
i
t
s
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
S
y
s
t
e
m
s
(
I
C
I
C
AC
S
)
,
I
EEE,
F
e
b
.
2
0
2
5
,
p
p
.
1
–
6
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
C
A
C
S
6
5
1
7
8
.
2
0
2
5
.
1
0
9
6
7
9
0
4
.
[
1
1
]
V
.
D
h
a
r
w
a
d
k
a
r
,
R
.
V
e
e
n
a
,
S
.
M
a
n
o
h
a
r
,
M
.
G
.
Ja
y
a
n
t
h
i
,
a
n
d
P
.
K
a
n
n
a
d
a
g
u
l
i
,
“
S
mar
t
c
a
r
t
:
r
e
v
o
l
u
t
i
o
n
i
z
i
n
g
e
-
c
o
mm
e
r
c
e
i
n
i
n
d
i
a
w
i
t
h
a
i
-
p
o
w
e
r
e
d
p
e
r
so
n
a
l
i
z
e
d
p
r
o
d
u
c
t
r
e
c
o
m
me
n
d
a
t
i
o
n
s
o
v
e
r
v
i
e
w
,
”
i
n
2
0
2
4
5
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
i
rc
u
i
t
s,
C
o
n
t
r
o
l
,
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
C
o
m
p
u
t
i
n
g
(
I
4
C
)
,
I
EEE,
O
c
t
.
2
0
2
4
,
p
p
.
8
7
–
9
2
.
d
o
i
:
1
0
.
1
1
0
9
/
I
4
C
6
2
2
4
0
.
2
0
2
4
.
1
0
7
4
8
5
2
1
.
[
1
2
]
Q
.
Zh
a
n
g
a
n
d
Y
.
X
i
o
n
g
,
“
H
a
r
n
e
s
si
n
g
A
I
p
o
t
e
n
t
i
a
l
i
n
E
-
C
o
mm
e
r
c
e
:
i
mp
r
o
v
i
n
g
u
ser
e
n
g
a
g
e
me
n
t
a
n
d
sal
e
s
t
h
r
o
u
g
h
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
s
e
d
p
r
o
d
u
c
t
r
e
c
o
mm
e
n
d
a
t
i
o
n
s
,
”
C
u
rren
t
Ps
y
c
h
o
l
o
g
y
,
v
o
l
.
4
3
,
n
o
.
3
8
,
p
p
.
3
0
3
7
9
–
3
0
4
0
1
,
O
c
t
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
2
1
4
4
-
024
-
0
6
6
4
9
-
3.
[
1
3
]
X
.
X
u
,
A
.
B
.
R
o
sl
i
,
X
.
Y
a
n
g
,
M
.
W
u
,
a
n
d
J
.
H
u
,
“
R
o
l
e
o
f
c
o
n
s
u
mer
I
o
T
s
mart
d
e
v
i
c
e
s
f
o
r
s
a
f
e
t
y
a
n
d
se
c
u
r
i
t
y
o
f
d
a
t
a
p
r
i
v
a
c
y
t
o
e
n
h
a
n
c
e
u
s
e
r
e
x
p
e
r
i
e
n
c
e
o
f
e
-
c
o
m
mer
c
e
,
”
I
EEE
T
r
a
n
s
a
c
t
i
o
n
s o
n
C
o
n
su
m
e
r
El
e
c
t
r
o
n
i
c
s
,
v
o
l
.
7
1
,
n
o
.
2
,
p
p
.
5
3
0
0
–
5
3
0
9
,
M
a
y
2
0
2
5
,
d
o
i
:
1
0
.
1
1
0
9
/
TC
E
.
2
0
2
5
.
3
5
7
1
0
4
4
.
[
1
4
]
M
a
n
u
V
a
l
l
a
b
h
M
i
s
h
r
a
,
“
A
I
-
d
r
i
v
e
n
p
e
r
s
o
n
a
l
i
z
a
t
i
o
n
:
g
e
n
e
r
a
t
i
v
e
m
o
d
e
l
s
i
n
e
-
c
o
m
m
e
r
c
e
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
d
R
e
s
e
a
r
c
h
i
n
S
c
i
e
n
c
e
,
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
T
e
c
h
n
o
l
o
g
y
,
p
p
.
1
1
0
–
1
1
6
,
J
a
n
.
2
0
2
5
,
d
o
i
:
1
0
.
4
8
1
7
5
/
i
j
a
r
s
c
t
-
2
3
1
1
2
.
[
1
5
]
C
.
Zh
a
o
a
n
d
Y
.
X
u
n
,
“
T
h
e
a
n
a
l
y
si
s
o
f
d
y
n
a
mi
c
e
v
a
l
u
a
t
i
o
n
o
f
o
n
l
i
n
e
sh
o
p
p
i
n
g
s
a
t
i
sf
a
c
t
i
o
n
b
a
se
d
o
n
t
h
e
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
mo
d
e
l
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
rt
s
,
v
o
l
.
1
5
,
n
o
.
1
,
p
.
2
1
7
2
4
,
J
u
l
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
3
8
/
s4
1
5
9
8
-
0
2
5
-
0
6
6
8
9
-
0.
[
1
6
]
N
.
A
k
r
a
m
,
S
.
V
i
c
t
o
r
,
D
.
R
a
g
h
a
v
a
,
M
.
V
.
U
n
n
i
,
P
.
G
o
t
t
u
m
u
k
k
a
l
a
,
a
n
d
S
.
G
a
r
g
,
“
D
i
g
i
t
a
l
mar
k
e
t
i
n
g
s
t
r
a
t
e
g
y
t
o
i
n
c
r
e
a
s
e
s
a
l
e
s
c
o
n
v
e
r
si
o
n
o
n
e
-
c
o
m
merc
e
p
l
a
t
f
o
r
ms
b
a
s
e
d
o
n
LST
M
-
R
N
N
mo
d
e
l
,
”
i
n
H
y
b
ri
d
a
n
d
A
d
v
a
n
c
e
d
T
e
c
h
n
o
l
o
g
i
e
s
,
Lo
n
d
o
n
:
C
R
C
P
r
e
ss
,
2
0
2
5
,
p
p
.
3
5
8
–
3
6
3
.
d
o
i
:
1
0
.
1
2
0
1
/
9
7
8
1
0
0
3
5
5
9
1
1
5
-
6
0
.
[
1
7
]
S
.
S
h
a
n
,
J.
S
u
n
,
a
n
d
R
.
M
.
C
.
M
a
c
a
w
i
l
e
,
“
Ex
a
m
i
n
i
n
g
c
u
s
t
o
mer
sa
t
i
sf
a
c
t
i
o
n
t
h
r
o
u
g
h
t
r
a
n
sf
o
r
mer
-
b
a
s
e
d
s
e
n
t
i
men
t
a
n
a
l
y
si
s
f
o
r
i
mp
r
o
v
i
n
g
b
i
l
i
n
g
u
a
l
e
-
c
o
mm
e
r
c
e
e
x
p
e
r
i
e
n
c
e
s,
”
I
EE
E
A
c
c
e
ss
,
v
o
l
.
1
3
,
p
p
.
5
1
0
2
7
–
5
1
0
4
1
,
2
0
2
5
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
5
.
3
5
5
1
6
6
6
.
[
1
8
]
F
.
M
a
n
c
i
n
i
,
V
.
A
.
S
.
P
r
e
c
o
m
a
,
L.
A
.
D
e
O
l
i
v
e
i
r
a
,
a
n
d
F
.
Te
i
x
e
i
r
a
,
“
C
l
i
c
k
s
t
r
e
a
mG
P
T:
a
t
r
a
n
sf
o
r
mer
-
b
a
se
d
g
e
n
e
r
a
t
i
v
e
A
I
a
p
p
r
o
a
c
h
t
o
c
l
i
c
k
s
t
r
e
a
m
p
r
e
d
i
c
t
i
o
n
f
o
r
E
-
c
o
mm
e
r
c
e
p
l
a
t
f
o
r
ms,
”
E
l
e
c
t
r
o
n
i
c
C
o
m
m
e
r
c
e
R
e
se
a
rc
h
,
p
p
.
1
–
2
5
,
A
p
r
.
2
0
2
6
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
6
6
0
-
0
2
5
-
1
0
0
7
1
-
7.
[
1
9
]
C
.
V
e
r
ma,
P
.
V
i
j
a
y
a
l
a
k
sh
m
i
,
N
.
C
h
a
t
u
r
v
e
d
i
,
U
.
U
m
e
sh
,
A
.
R
a
i
,
a
n
d
A
.
Y
.
A
.
B
a
n
i
A
h
ma
d
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
i
n
mar
k
e
t
i
n
g
man
a
g
e
me
n
t
:
e
n
h
a
n
c
i
n
g
c
u
st
o
m
e
r
e
n
g
a
g
e
m
e
n
t
a
n
d
p
e
r
so
n
a
l
i
z
a
t
i
o
n
,
”
i
n
2
0
2
5
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
P
e
rv
a
si
v
e
C
o
m
p
u
t
a
t
i
o
n
a
l
T
e
c
h
n
o
l
o
g
i
e
s (I
C
P
C
T
)
,
I
EEE,
F
e
b
.
2
0
2
5
,
p
p
.
3
9
7
–
4
0
1
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
P
C
T
6
4
1
4
5
.
2
0
2
5
.
1
0
9
4
0
6
2
6
.
[
2
0
]
G
.
M
a
h
a
l
i
sa,
S
.
R
a
t
n
a
,
a
n
d
M
.
M
u
f
l
i
h
,
“
D
e
v
e
l
o
p
me
n
t
o
f
a
c
o
l
l
a
b
o
r
a
t
i
v
e
r
e
c
o
mm
e
n
d
a
t
i
o
n
s
y
s
t
e
m
b
a
s
e
d
o
n
si
n
g
u
l
a
r
v
a
l
u
e
d
e
c
o
m
p
o
si
t
i
o
n
(
S
V
D
)
o
n
e
-
c
o
mm
e
r
c
e
d
a
t
a
,
”
J
o
u
r
n
a
l
o
f
A
p
p
l
i
e
d
I
n
f
o
rm
a
t
i
c
s
a
n
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
9
,
n
o
.
6
,
p
p
.
3
7
6
9
–
3
7
7
3
,
D
e
c
.
2
0
2
5
,
d
o
i
:
1
0
.
3
0
8
7
1
/
j
a
i
c
.
v
9
i
6
.
1
1
6
8
8
.
[
2
1
]
W
.
S
i
l
f
i
a
n
t
i
,
R
.
D
.
S
y
a
h
,
A
.
S
u
h
e
n
d
r
a
,
A
.
I
sr
a
,
A
.
D
a
r
m
a
y
a
n
t
i
e
,
a
n
d
N
.
R
.
O
h
o
r
e
l
l
a
,
“
A
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
t
o
u
r
i
s
m
d
e
s
t
i
n
a
t
i
o
n
r
e
c
o
mm
e
n
d
a
t
i
o
n
u
s
i
n
g
I
n
d
o
B
E
R
T
a
n
d
TF
-
I
D
F
,
”
I
L
K
O
M
J
u
rn
a
l
I
l
m
i
a
h
,
v
o
l
.
1
7
,
n
o
.
3
,
p
p
.
2
4
1
–
2
5
1
,
O
c
t
.
2
0
2
5
,
d
o
i
:
1
0
.
3
3
0
9
6
/
i
l
k
o
m.
v
1
7
i
3
.
3
0
6
9
.
2
4
1
-
2
5
1
.
[
2
2
]
Y
.
M
o
a
n
d
H
.
W
a
n
g
,
“
S
e
s
si
o
n
-
b
a
s
e
d
r
e
c
o
mm
e
n
d
a
t
i
o
n
me
t
h
o
d
u
s
i
n
g
p
o
p
u
l
a
r
i
t
y
-
st
r
a
t
i
f
i
e
d
p
r
e
f
e
r
e
n
c
e
mo
d
e
l
i
n
g
,
”
M
a
t
h
e
m
a
t
i
c
s
,
v
o
l
.
1
3
,
n
o
.
6
,
p
.
9
6
0
,
M
a
r
.
2
0
2
5
,
d
o
i
:
1
0
.
3
3
9
0
/
ma
t
h
1
3
0
6
0
9
6
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
A
h
yb
r
id
A
I
fr
a
mewo
r
k
fo
r
h
y
p
er
-
p
ers
o
n
a
liz
ed
r
ec
o
mme
n
d
a
tio
n
s
a
n
d
…
(
P
a
r
a
s
h
iva
Mu
r
th
y
B
.
M
.
)
1879
[
2
3
]
C
.
S
.
M
.
A
l
i
a
n
d
S
.
R
.
M
.
Ze
e
b
a
r
e
e
,
“
P
e
r
s
o
n
a
l
i
z
a
t
i
o
n
i
n
d
i
g
i
t
a
l
m
a
r
k
e
t
i
n
g
:
l
e
v
e
r
a
g
i
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
e
-
c
o
m
merc
e
,”
A
si
a
n
J
o
u
r
n
a
l
o
f
Re
se
a
rc
h
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
8
,
n
o
.
3
,
p
p
.
1
0
5
–
1
2
9
,
F
e
b
.
2
0
2
5
,
d
o
i
:
1
0
.
9
7
3
4
/
a
j
r
c
o
s
/
2
0
2
5
/
v
1
8
i
3
5
8
2
.
[
2
4
]
A
.
M
u
s
t
a
f
a
a
n
d
N
.
M
a
z
h
e
r
,
“
D
e
c
o
d
i
n
g
D
r
o
p
-
O
f
f
P
o
i
n
t
s
:
A
m
u
l
t
i
-
f
a
c
t
o
r
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
f
o
r
c
a
r
t
a
b
a
n
d
o
n
me
n
t
i
n
,
”
T
h
i
n
k
T
i
d
e
G
l
o
b
a
l
Re
s
e
a
r
c
h
J
o
u
rn
a
l
,
v
o
l
.
6
,
n
o
.
3
,
p
p
.
9
–
2
6
,
2
0
2
5
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
t
h
i
n
k
t
i
d
e
j
o
u
r
n
a
l
.
c
o
m
/
i
n
d
e
x
.
p
h
p
/
TG
R
J/
a
r
t
i
c
l
e
/
v
i
e
w
/
5
[
2
5
]
A
.
S
y
a
i
f
u
d
d
i
n
,
R
.
S
a
p
t
o
n
o
,
A
.
R
o
h
mad
i
,
B
.
W
i
d
o
y
o
n
o
,
a
n
d
B
.
H
e
n
d
r
a
su
r
y
a
w
a
n
,
“
O
p
t
i
mi
z
i
n
g
e
-
c
o
mm
e
r
c
e
p
e
r
s
o
n
a
l
i
z
a
t
i
o
n
t
h
r
o
u
g
h
h
y
b
r
i
d
d
e
c
i
s
i
o
n
t
r
e
e
–
n
e
a
r
e
s
t
n
e
i
g
h
b
o
r
r
e
c
o
mm
e
n
d
a
t
i
o
n
i
n
t
e
g
r
a
t
i
o
n
,”
J
u
r
n
a
l
T
e
k
n
i
k
I
n
f
o
rm
a
t
i
k
a
(
J
u
t
i
f
)
,
v
o
l
.
7
,
n
o
.
2
,
p
p
.
1
0
2
8
–
1
0
3
9
,
A
p
r
.
2
0
2
6
,
d
o
i
:
1
0
.
5
2
4
3
6
/
1
.
j
u
t
i
f
.
2
0
2
6
.
7
.
2
.
5
4
1
8
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Dr
.
Pa
r
a
shi
v
a
M
u
r
th
y
B
.
M
.
wo
rk
i
n
g
a
s
As
sista
n
t
P
r
o
fe
ss
o
r
in
o
f
C
o
m
p
u
t
e
r
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
,
JS
S
S
c
i
e
n
c
e
a
n
d
Tec
h
n
o
lo
g
y
Un
iv
e
rsity
,
M
y
su
r
u
,
Ka
rn
a
tak
a
,
h
a
s
1
2
y
e
a
rs o
f
a
c
a
d
e
m
ic se
rv
ice
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
p
a
ra
sh
iv
a
m
u
rth
y
@s
jce
.
a
c
.
in
.
Dr
.
S
c
a
r
ia
Ale
x
wo
rk
in
g
a
s
As
sista
n
t
P
ro
fe
ss
o
r
in
De
p
a
rtme
n
t
o
f
In
f
o
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
,
Am
a
l
Jy
o
th
i
Co
ll
e
g
e
o
f
En
g
in
e
e
ri
n
g
,
Ko
t
tay
a
m
.
He
h
a
v
e
+
1
3
Ye
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sc
a
riaa
lex
@a
m
a
lj
y
o
th
i.
a
c
.
in
.
Dr
.
Is
a
iv
a
n
i
M
a
r
iy
a
p
p
a
n
is
c
u
rre
n
tl
y
wo
rk
in
g
a
s
a
n
As
sista
n
t
P
ro
fe
ss
o
r
i
n
t
h
e
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ics
En
g
i
n
e
e
rin
g
,
S
RM
M
a
d
u
ra
i
Co
ll
e
g
e
f
o
r
E
n
g
i
n
e
e
rin
g
a
n
d
Tec
h
n
o
lo
g
y
,
S
i
v
a
g
a
n
g
a
Dis
tri
c
t,
Tam
il
Na
d
u
,
In
d
ia
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
isa
in
e
c
0
6
@g
m
a
il
.
c
o
m
.
Dr
.
K
a
ly
a
n
De
v
a
p
p
a
Ba
m
a
n
e
a
c
a
d
e
m
i
c
ian
a
n
d
re
se
a
rc
h
e
r
wi
th
o
v
e
r
1
9
y
e
a
r
s
o
f
e
x
p
e
rien
c
e
.
He
is
c
u
rre
n
tl
y
a
n
As
so
c
iate
P
ro
fe
ss
o
r
i
n
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
te
r
En
g
i
n
e
e
rin
g
,
In
d
ira Co
ll
e
g
e
o
f
En
g
in
e
e
rin
g
a
n
d
M
a
n
a
g
e
m
e
n
t,
P
a
ra
n
d
wa
d
i,
P
u
n
e
,
M
a
h
a
ra
sh
tra,
In
d
ia
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
k
a
l
y
a
n
d
b
a
m
a
n
e
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
5
,
No
.
4
,
D
e
c
em
b
er
20
2
6
:
1
8
7
1
-
1
8
8
0
1880
Dr
.
K
a
v
ith
a
R
.
with
o
v
e
r
1
2
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rie
n
c
e
in
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
h
o
l
d
s
a
P
h
.
D.
fro
m
M
a
n
o
n
m
a
n
iam
S
u
n
d
a
ra
n
a
r
Un
iv
e
rsity
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
th
i
k
a
v
i
8
8
@
g
m
a
il
.
c
o
m
.
Dr
.
S
.
Athi
n
a
r
a
y
a
n
a
n
As
so
c
iate
P
ro
fe
ss
o
r
a
t
Ve
l
Tec
h
,
Ch
e
n
n
a
i,
h
a
s
o
v
e
r
1
6
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
,
in
c
lu
d
in
g
7
p
o
st
-
P
h
.
D.
His
e
x
p
e
rti
se
sp
a
n
s
m
e
d
ica
l
ima
g
e
p
ro
c
e
ss
in
g
,
m
a
c
h
in
e
lea
rn
in
g
,
b
l
o
c
k
c
h
a
in
,
a
n
d
sy
ste
m
so
ftwa
re
.
b
o
o
k
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
a
th
it
h
e
@g
m
a
il
.
c
o
m
.
Dr
.
S
u
n
d
e
r
R
.
P
r
o
fe
ss
o
r
i
n
S
c
h
o
o
l
o
f
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
i
n
e
e
rin
g
a
t
G
a
lg
o
ti
a
s
Un
iv
e
rsity
,
h
o
l
d
s
2
0
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
with
P
h
.
D
fr
o
m
M
a
n
o
n
m
a
n
iam
S
u
n
d
a
ra
n
a
r
Un
i
v
e
rsity
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
su
n
d
e
r.
r@
g
a
l
g
o
ti
a
su
n
iv
e
rsit
y
.
e
d
u
.
i
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.