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
4
,
No
.
6
,
Dec
em
b
er
2
0
2
5
,
p
p
.
4
5
5
2
~
4
5
6
4
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
14
.i
6
.
p
p
4
5
5
2
-
4
5
6
4
4552
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
H
uma
ns’
psy
cho
lo
g
ica
l t
ra
its clas
sifica
tion f
ro
m thei
r spending
ca
tego
ries using
artificial i
ntelligen
ce alg
o
rithms
Arpit
ha
Chik
k
a
ma
g
a
luru Na
ra
s
im
he
G
o
wda
1
,
Su
nitha
M
a
da
s
i R
a
m
a
cha
nd
ra
2
1
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
A
d
i
c
h
u
n
c
h
a
n
a
g
i
r
i
I
n
s
t
i
t
u
t
e
o
f
T
e
c
h
n
o
l
o
g
y
,
A
f
f
i
l
i
a
t
e
d
t
o
V
i
s
v
e
s
v
a
r
a
y
a
Te
c
h
n
o
l
o
g
i
c
a
l
U
n
i
v
e
r
si
t
y
,
B
e
l
a
g
a
v
i
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
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
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
,
A
d
i
c
h
u
n
c
h
a
n
a
g
i
r
i
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
,
A
f
f
i
l
i
a
t
e
d
t
o
V
i
s
v
e
s
v
a
r
a
y
a
Te
c
h
n
o
l
o
g
i
c
a
l
U
n
i
v
e
r
si
t
y
,
B
e
l
a
g
a
v
i
,
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
Dec
1
0
,
2
0
2
4
R
ev
is
ed
Sep
2
6
,
2
0
2
5
Acc
ep
ted
Oct
1
8
,
2
0
2
5
Th
e
a
n
a
ly
sis
o
f
h
u
m
a
n
b
e
h
a
v
i
o
r
d
a
ta
g
e
n
e
ra
ted
b
y
d
i
g
it
a
l
tec
h
n
o
l
o
g
ies
h
a
s
g
a
in
e
d
i
n
c
re
a
sin
g
a
tt
e
n
ti
o
n
i
n
r
e
c
e
n
t
y
e
a
rs.
S
p
e
n
d
i
n
g
c
a
teg
o
r
ies
fo
rm
a
sig
n
ifi
c
a
n
t
p
a
rt
o
f
th
is
d
i
g
it
a
l
fo
o
t
p
rin
t
.
I
n
th
is
stu
d
y
,
we
in
v
e
stig
a
te
th
e
d
e
g
re
e
to
wh
ic
h
h
u
m
a
n
e
x
p
e
n
d
it
u
r
e
re
c
o
rd
s
c
a
n
b
e
u
se
d
t
o
i
n
fe
r
p
sy
c
h
o
l
o
g
ica
l
traits
fro
m
tran
sa
c
ti
o
n
d
a
ta.
A
b
ro
a
d
f
e
a
tu
re
sp
a
c
e
wa
s
c
o
n
stru
c
ted
,
c
o
n
sistin
g
o
f
o
v
e
ra
ll
sp
e
n
d
in
g
b
e
h
a
v
io
r
,
cat
e
g
o
ry
-
re
late
d
sp
e
n
d
in
g
b
e
h
a
v
io
r,
a
n
d
c
u
sto
m
e
r
c
a
teg
o
ry
p
r
o
fil
e
s.
Th
e
se
fe
a
tu
re
s we
re
e
x
a
m
in
e
d
t
o
i
d
e
n
ti
fy
t
h
e
ir
c
o
rre
latio
n
s
with
th
e
Big
F
iv
e
p
e
rso
n
a
li
ty
t
ra
it
s.
A
d
a
tas
e
t
c
o
n
tain
in
g
o
v
e
r
1
,
2
0
0
u
se
rs’
tran
sa
c
ti
o
n
h
isto
ries
o
v
e
r
th
re
e
m
o
n
th
s
wa
s
o
b
tai
n
e
d
fro
m
Ka
g
g
le.
P
e
rso
n
a
li
t
y
trait
lab
e
ls
we
re
d
e
riv
e
d
u
si
n
g
a
p
e
rc
e
n
ti
le
-
b
a
se
d
c
las
sifica
ti
o
n
m
e
th
o
d
.
M
u
lt
i
p
le
AI
a
lg
o
rit
h
m
s:
d
e
c
isio
n
tree
(DT),
ra
n
d
o
m
fo
re
st
(RF
),
lo
g
ist
ic
re
g
re
ss
io
n
(LR)
,
a
n
d
s
u
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(S
VM)
we
re
e
m
p
lo
y
e
d
,
a
lo
n
g
with
a
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
(CNN
)
to
c
las
sify
p
e
rso
n
a
li
ty
traits.
Th
e
CNN
m
o
d
e
l,
in
c
o
r
p
o
ra
ti
n
g
m
u
lt
i
-
d
im
e
n
sio
n
a
l
c
o
n
v
o
lu
t
io
n
a
l
lay
e
r
s
a
n
d
th
e
fu
ll
fe
a
tu
re
s
p
a
c
e
,
a
c
h
iev
e
d
a
h
ig
h
a
c
c
u
ra
c
y
o
f
9
9
.
0
3
%
.
Th
e
o
u
tco
m
e
s
o
f
th
e
e
x
p
e
rime
n
t
in
d
ica
te
th
e
e
fficie
n
c
y
o
f
c
o
m
b
i
n
i
n
g
b
e
h
a
v
i
o
ra
l
fe
a
tu
r
e
s
a
n
d
AI
m
o
d
e
ls
in
p
s
y
c
h
o
lo
g
ica
l
trait
c
las
sifica
ti
o
n
.
T
h
e
stu
d
y
a
lso
h
ig
h
li
g
h
ts
e
th
ica
l
c
o
n
sid
e
ra
ti
o
n
s,
i
n
c
lu
d
in
g
p
ri
v
a
c
y
risk
s
a
n
d
m
isu
se
o
f
i
n
fe
rre
d
p
e
rso
n
a
li
t
y
d
e
tails.
K
ey
w
o
r
d
s
:
Ar
tific
ial
in
tellig
en
ce
Dee
p
lear
n
in
g
al
g
o
r
ith
m
s
Ma
ch
in
e
lear
n
in
g
alg
o
r
ith
m
s
Ps
y
ch
o
lo
g
ical
tr
aits
Sp
en
d
in
g
ca
te
g
o
r
ies
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
:
Ar
p
ith
a
C
h
ik
k
am
ag
al
u
r
u
Nar
a
s
im
h
e
Go
wd
a
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atio
n
Scien
ce
an
d
E
n
g
in
ee
r
i
n
g
,
Ad
ic
h
u
n
ch
an
a
g
ir
i I
n
s
titu
te
o
f
T
ec
h
n
o
lo
g
y
Af
f
iliated
to
Vis
v
esv
ar
ay
a
T
e
ch
n
o
lo
g
ical
Un
iv
er
s
ity
B
elag
av
i
5
9
0
0
1
8
,
Kar
n
atak
a,
I
n
d
ia
E
-
m
ail: a
r
p
ith
ac
n
1
5
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
I
n
r
ec
en
t
d
ec
ad
es,
d
ig
ital
d
ev
ices
an
d
s
er
v
ices
h
av
e
b
ec
o
m
e
in
teg
r
al
to
ev
er
y
d
ay
life
.
T
h
ey
en
ab
le
in
d
iv
id
u
als
to
ex
p
lo
r
e
d
ata,
m
ain
tain
s
o
cial
co
n
n
ec
tio
n
s
,
ca
p
tu
r
e
im
p
o
r
tan
t
m
o
m
en
ts
,
s
h
ar
e
o
p
in
io
n
s
g
lo
b
ally
,
an
d
co
n
d
u
ct
f
in
a
n
cial
tr
an
s
ac
tio
n
s
with
ea
s
e.
R
ec
en
t
ad
v
an
ce
m
en
ts
in
s
o
cial
s
cien
ce
co
m
p
u
tin
g
[
1
]
s
u
g
g
est
th
at
in
d
iv
id
u
als'
d
ig
ital
f
o
o
tp
r
in
ts
ca
n
b
e
ef
f
ec
tiv
el
y
lev
er
ag
ed
to
in
f
er
th
eir
p
s
y
ch
o
lo
g
ical
tr
aits
.
Pre
v
io
u
s
s
tu
d
ies
h
av
e
d
em
o
n
s
tr
ated
th
a
t
f
ea
tu
r
es
s
u
ch
as
Face
b
o
o
k
li
k
es
[
2
]
,
lan
g
u
ag
e
u
s
ed
in
s
o
ci
al
m
ed
ia
p
o
s
ts
[
3
]
,
p
r
o
f
ile
p
h
o
to
s
[
4
]
,
m
u
s
ic
p
r
ef
e
r
en
ce
s
[
5
]
,
an
d
s
m
ar
tp
h
o
n
e
s
en
s
o
r
-
g
en
er
ate
d
d
ata
[
6
]
,
[
7
]
ca
n
all
s
er
v
e
as
r
eliab
le
p
r
ed
icto
r
s
o
f
p
er
s
o
n
ality
.
Am
o
n
g
v
a
r
io
u
s
f
o
r
m
s
o
f
d
ig
ital
f
o
o
tp
r
i
n
ts
,
s
p
en
d
in
g
b
e
h
av
io
r
is
wid
esp
r
ea
d
b
u
t
co
m
p
ar
ativ
ely
u
n
d
er
e
x
p
lo
r
ed
.
R
esear
ch
o
n
co
n
s
u
m
er
b
eh
av
i
o
r
r
ev
ea
ls
th
at
p
u
r
ch
asin
g
d
ec
i
s
io
n
s
ar
e
in
f
lu
en
ce
d
n
o
t
o
n
l
y
b
y
p
r
a
ctica
l
n
ee
d
s
b
u
t
also
b
y
p
s
y
ch
o
lo
g
ical
an
d
s
o
c
ial
f
ac
to
r
s
[
8
]
.
C
o
n
s
u
m
er
s
o
f
te
n
s
elec
t
b
r
an
d
s
t
h
at
en
ab
le
th
e
m
to
ex
p
r
ess
th
em
s
elv
es
b
o
th
in
ter
n
ally
a
n
d
ex
ter
n
ally
,
s
u
p
p
o
r
tin
g
th
e
id
ea
th
at
s
p
en
d
in
g
s
er
v
es
as
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
Hu
ma
n
s
’
p
s
yc
h
o
lo
g
ica
l tra
its
cla
s
s
ifica
tio
n
fr
o
m
th
eir
…
(
A
r
p
ith
a
C
h
ikka
ma
g
a
lu
r
u
N
a
r
a
s
imh
e
Go
w
d
a
)
4553
a
f
o
r
m
o
f
s
elf
-
e
x
p
r
ess
io
n
.
Fo
r
i
n
s
tan
ce
,
in
d
iv
id
u
als
h
ig
h
in
ex
t
r
av
er
s
io
n
m
ay
p
r
ef
er
s
p
en
d
in
g
o
n
s
o
cial
ac
tiv
ities
s
u
ch
as
d
in
in
g
o
u
t,
wh
ile
in
tr
o
v
er
ts
ar
e
m
o
r
e
in
clin
ed
to
war
d
s
o
litar
y
ex
p
er
ien
ce
s
s
u
ch
as
p
u
r
ch
asin
g
b
o
o
k
s
o
r
s
u
b
s
cr
ib
in
g
to
p
o
d
ca
s
ts
[
9
]
.
Fi
n
d
in
g
s
f
r
o
m
b
e
h
av
io
r
al
s
tu
d
ies
d
em
o
n
s
tr
ate
th
at
m
atch
i
n
g
p
r
o
d
u
cts
to
p
er
s
o
n
ality
tr
aits
en
h
an
ce
s
em
o
tio
n
al
s
atis
f
ac
tio
n
an
d
u
s
er
en
g
a
g
em
e
n
t
[
1
0
]
.
T
h
ese
ass
o
ciatio
n
s
a
r
e
o
f
te
n
u
s
in
g
t
h
e
B
ig
Fiv
e
p
er
s
o
n
ality
tr
aits
as
a
m
o
d
el
f
r
am
ew
o
r
k
,
co
m
m
o
n
ly
k
n
o
wn
as
o
p
en
n
ess
,
co
n
s
cien
tio
u
s
n
ess
,
ex
tr
av
er
s
io
n
,
a
g
r
ee
ab
le
n
ess
,
an
d
n
eu
r
o
ticis
m
(
OC
E
AN
)
[
1
1
]
.
Un
d
er
s
tan
d
in
g
th
e
lin
k
b
etwe
en
s
p
en
d
in
g
ca
teg
o
r
ies
an
d
th
ese
tr
aits
en
ab
les
d
ee
p
er
in
s
ig
h
ts
an
d
ex
p
an
d
ed
o
p
p
o
r
tu
n
ities
in
p
s
y
c
h
o
lo
g
ical
p
r
o
f
ilin
g
,
tar
g
eted
m
ar
k
etin
g
,
a
n
d
p
e
r
s
o
n
alize
d
s
er
v
ices,
th
o
u
g
h
it a
ls
o
r
aises
im
p
o
r
tan
t e
th
ical
co
n
s
id
er
atio
n
s
.
I
n
t
h
e
l
ast
f
ew
y
ea
r
s
,
c
o
n
s
id
e
r
a
b
l
e
r
ese
ar
ch
t
h
e
f
o
c
u
s
h
as
b
e
en
d
ev
o
t
e
d
t
o
p
r
ed
ict
in
g
in
d
i
v
i
d
u
als
’
p
e
r
s
o
n
ali
ties
u
til
izi
n
g
m
a
c
h
i
n
e
l
ea
r
n
i
n
g
(
ML
)
a
n
d
d
e
ep
l
e
ar
n
i
n
g
(
D
L
)
te
c
h
n
iq
u
es
t
o
a
n
aly
ze
s
o
ci
al
m
ed
ia
b
e
h
a
v
i
o
r
.
S
u
h
a
r
t
o
n
o
e
t
a
l
.
[
1
2
]
p
r
o
p
o
s
ed
a
p
e
r
s
o
n
ali
t
y
p
r
e
d
i
cti
o
n
f
r
a
m
ew
o
r
k
u
ti
liz
in
g
Fa
c
eb
o
o
k
p
o
s
ts
as
a
n
alte
r
n
at
iv
e
t
o
tr
ad
iti
o
n
al
p
er
s
o
n
alit
y
ass
ess
m
e
n
t
m
et
h
o
d
s
.
T
h
e
r
es
ea
r
c
h
e
r
s
e
m
p
l
o
y
e
d
f
i
v
e
ML
tec
h
n
i
q
u
es,
n
am
el
y
s
u
p
p
o
r
t
v
e
ct
o
r
m
ac
h
i
n
e
(
SV
M
)
,
m
u
lt
in
o
m
ia
l
n
aï
v
e
B
a
y
es
(
N
B
)
,
d
e
cisi
o
n
t
r
e
e
(
DT
)
,
k
-
n
e
a
r
e
s
t n
ei
g
h
b
o
r
(
KNN
)
,
an
d
l
o
g
is
t
ic
r
e
g
r
ess
i
o
n
(
L
R
)
t
o
b
u
il
d
a
m
o
d
el
u
s
in
g
th
e
B
i
g
Fi
v
e
p
e
r
s
o
n
a
lit
y
t
r
aits
m
o
d
el
t
o
ad
d
r
ess
class
im
b
al
an
ce
,
t
h
e
d
atas
et
w
as
a
u
g
m
e
n
te
d
,
a
n
d
s
tr
ati
f
i
ed
1
0
-
f
o
l
d
c
r
o
s
s
-
v
a
li
d
at
io
n
w
as
u
s
e
d
.
Am
o
n
g
t
h
e
m
o
d
els
,
m
u
lti
n
o
m
i
al
NB
a
c
h
ie
v
ed
t
h
e
h
i
g
h
est
F
1
-
s
c
o
r
e
f
o
r
o
p
en
n
ess
(
8
2
.
3
1
%
)
a
n
d
t
h
e
b
est
o
v
e
r
a
ll
a
v
er
ag
e
(
6
8
.
6
2
%
)
.
Na
z
e
t
a
l
.
[
1
3
]
p
r
es
e
n
te
d
a
h
y
b
r
i
d
s
tr
u
ct
u
r
e
f
o
r
ca
te
g
o
r
i
zi
n
g
u
s
er
p
e
r
s
o
n
alit
y
u
ti
liz
in
g
t
ex
tu
a
l
d
a
ta
f
o
r
o
p
en
n
ess
tr
a
it.
T
h
e
an
al
y
s
is
c
o
m
b
i
n
ed
t
e
r
m
f
r
eq
u
en
cy
-
i
n
v
e
r
s
e
d
o
c
u
m
e
n
t
f
r
e
q
u
e
n
c
y
(
T
F
-
I
DF)
a
n
d
wo
r
d
e
m
b
e
d
d
i
n
g
s
wi
th
ML
a
n
d
DL
m
o
d
e
ls
s
u
ch
as
S
VM
,
NB
,
an
d
l
o
n
g
s
h
o
r
t
-
te
r
m
m
e
m
o
r
y
(
L
ST
M)
.
T
h
e
s
t
u
d
y
r
ev
ea
l
ed
th
at
h
y
b
r
i
d
m
o
d
els,
p
a
r
t
ic
u
l
ar
l
y
T
F
-
I
DF
wit
h
L
S
T
M,
o
u
t
p
e
r
f
o
r
m
e
d
i
n
d
i
v
i
d
u
al
m
o
d
els
i
n
p
r
ed
ict
in
g
B
ig
Fi
v
e
t
r
aits
.
T
h
is
h
i
g
h
li
g
h
ts
t
h
e
e
f
f
e
cti
v
e
n
ess
o
f
c
o
m
b
in
in
g
s
h
all
o
w
a
n
d
d
ee
p
f
ea
tu
r
es
f
o
r
ac
cu
r
a
te
p
er
s
o
n
ali
ty
p
r
ed
ict
i
on
.
Dag
h
a
e
t
a
l
.
[
1
4
]
p
r
o
p
o
s
e
d
p
er
s
o
n
ali
ty
p
r
ed
ict
io
n
b
ase
d
o
n
u
s
er
s
’
t
wee
ts
,
t
h
e
w
o
r
k
em
p
h
as
iz
ed
t
h
e
s
ig
n
i
f
i
ca
n
c
e
o
f
s
ele
cti
n
g
s
u
i
ta
b
l
e
m
e
th
o
d
s
t
o
h
an
d
l
e
t
h
e
l
ar
g
e
an
d
d
y
n
a
m
i
c
n
at
u
r
e
o
f
s
o
ci
al
m
e
d
ia
d
at
a.
T
h
eir
f
i
n
d
i
n
g
s
s
u
g
g
est
th
a
t
ML
m
o
d
els
ca
n
e
f
f
ec
ti
v
el
y
cl
ass
i
f
y
p
er
s
o
n
al
it
y
t
y
p
es
w
h
en
t
r
a
in
e
d
o
n
f
e
at
u
r
es
e
x
t
r
a
cte
d
f
r
o
m
twe
ets
,
li
k
es
,
r
et
wee
ts
,
a
n
d
c
o
m
m
e
n
ts
,
wh
ile
als
o
s
tr
ess
i
n
g
t
h
e
n
e
e
d
f
o
r
e
th
i
ca
l
d
at
a
h
a
n
d
li
n
g
.
Alth
o
u
g
h
s
o
cial
m
ed
ia
d
ata
h
as
b
ee
n
a
p
r
ed
o
m
in
a
n
t
s
o
u
r
ce
in
ex
is
tin
g
s
tu
d
ies,
s
p
en
d
in
g
b
eh
av
io
r
r
em
ain
s
an
u
n
d
er
e
x
p
lo
r
e
d
y
et
p
r
o
m
is
in
g
d
o
m
ain
f
o
r
in
f
er
r
in
g
p
er
s
o
n
ality
tr
aits
.
Aq
u
in
o
an
d
L
in
s
[
1
5
]
an
al
y
ze
d
th
e
co
n
n
ec
tio
n
b
etwe
en
th
e
B
ig
Fiv
e
p
er
s
o
n
ality
d
im
e
n
s
io
n
s
an
d
th
r
ee
f
o
r
m
s
o
f
co
n
s
u
m
er
b
e
h
av
io
r
.
C
o
m
p
u
ls
iv
e,
p
an
ic,
a
n
d
im
p
u
ls
iv
e
b
u
y
in
g
,
an
d
th
eir
r
es
u
lts
r
ev
ea
led
d
is
tin
ct
ass
o
ciatio
n
s
f
o
r
ex
a
m
p
le,
co
n
s
cien
tio
u
s
n
ess
ex
h
ib
ited
a
n
eg
ativ
e
co
r
r
elatio
n
with
co
m
p
u
ls
iv
e
b
u
y
in
g
,
wh
ile
n
e
u
r
o
tic
is
m
was
p
o
s
itiv
ely
co
r
r
elate
d
with
all
th
r
ee
b
eh
a
v
io
r
al
o
u
tco
m
es.
T
h
is
h
ig
h
lig
h
t
s
th
e
p
s
y
ch
o
lo
g
ical
d
ep
t
h
em
b
ed
d
ed
in
p
u
r
ch
asin
g
d
ec
is
io
n
s
.
Glad
s
to
n
e
et
a
l
.
[
1
6
]
f
u
r
th
er
e
x
ten
d
e
d
th
is
lin
e
o
f
wo
r
k
b
y
a
n
aly
zin
g
lar
g
e
-
s
ca
le
tr
an
s
ac
tio
n
r
ec
o
r
d
s
to
in
f
er
p
s
y
c
h
o
lo
g
ical
tr
aits
.
Alth
o
u
g
h
less
ex
p
r
ess
iv
e
th
an
s
o
cial
m
ed
ia
co
n
ten
t,
s
p
e
n
d
in
g
d
ata
ca
n
s
till
y
ield
v
alu
ab
le
in
s
ig
h
ts
in
to
p
er
s
o
n
ality
tr
aits
wh
en
ex
am
in
ed
at
s
ca
le.
T
h
e
s
tu
d
y
d
if
f
er
en
tiates
b
etwe
en
id
en
tity
claim
s
(
e.
g
.
,
s
o
cial
m
ed
ia
co
n
t
en
t)
an
d
b
eh
a
v
io
r
al
r
esid
u
es
(
e
.
g
.
,
s
p
en
d
in
g
p
atter
n
s
)
,
s
h
o
win
g
th
at
th
e
latter
ca
n
u
n
co
v
e
r
p
er
s
o
n
ality
tr
aits
th
r
o
u
g
h
o
b
jectiv
e
an
d
co
n
tin
u
o
u
s
d
ata
s
tr
ea
m
s
.
T
o
p
r
o
v
id
e
a
clea
r
er
p
ictu
r
e
o
f
th
e
r
esear
ch
lan
d
s
ca
p
e
,
T
ab
le
1
s
u
m
m
ar
izes
ex
is
tin
g
p
e
r
s
o
n
ality
p
r
ed
ictio
n
m
eth
o
d
s
ac
r
o
s
s
m
o
d
alities
s
u
ch
as
tex
t,
im
ag
es,
s
en
s
o
r
d
ata,
tr
an
s
ac
tio
n
r
ec
o
r
d
s
,
an
d
m
u
ltimo
d
al
d
ata.
T
ab
le
1
.
C
o
m
p
a
r
ativ
e
s
u
m
m
ar
y
o
f
p
er
s
o
n
ality
p
r
ed
ictio
n
m
e
th
o
d
s
ac
r
o
s
s
d
if
f
er
e
n
t m
o
d
alities
D
a
t
a
so
u
r
c
e
Ty
p
i
c
a
l
m
o
d
e
l
s
B
e
n
c
h
mar
k
d
a
t
a
se
t
/
c
o
n
t
e
x
t
S
t
r
e
n
g
t
h
s
Li
mi
t
a
t
i
o
n
s
R
e
p
r
e
se
n
t
a
t
i
v
e
r
e
f
e
r
e
n
c
e
s
Te
x
t
(
s
o
c
i
a
l
me
d
i
a
p
o
s
t
s,
e
ss
a
y
s
,
t
w
e
e
t
s)
S
V
M
,
L
R
,
N
B
,
R
N
N
/
L
S
T
M
,
t
r
a
n
s
f
o
r
m
e
r
s
(
B
E
R
T
,
R
o
B
E
R
T
a
,
h
y
b
r
i
d
s
)
my
P
e
r
s
o
n
a
l
i
t
y
,
Essay
s,
Tw
i
t
t
e
r
,
F
a
c
e
b
o
o
k
p
o
st
s.
R
i
c
h
l
i
n
g
u
i
st
i
c
a
n
d
sema
n
t
i
c
c
u
e
s,
v
a
l
i
d
a
t
e
d
b
e
n
c
h
mar
k
s
a
v
a
i
l
a
b
l
e
.
S
u
sce
p
t
i
b
l
e
t
o
s
e
l
f
-
p
r
e
se
n
t
a
t
i
o
n
b
i
a
s
;
r
e
q
u
i
r
e
s
l
a
r
g
e
l
a
b
e
l
l
e
d
c
o
r
p
o
r
a
[
2
]
,
[
3
]
,
[
1
2
]
,
[
1
3
]
,
[
1
4
]
,
[
1
7
]
I
mag
e
(
p
r
o
f
i
l
e
p
h
o
t
o
s
,
se
l
f
i
e
s,
mu
l
t
i
m
o
d
a
l
p
o
s
t
s)
C
N
N
,
R
e
sN
e
t
,
v
i
s
i
o
n
t
r
a
n
sf
o
r
m
e
r
s
F
a
c
e
b
o
o
k
,
I
n
s
t
a
g
r
a
m
,
m
u
l
t
i
m
o
d
a
l
d
a
t
a
s
e
t
s
C
a
p
t
u
r
e
s
n
o
n
-
v
e
r
b
a
l
,
v
i
s
u
a
l
p
e
r
s
o
n
a
l
i
t
y
c
u
e
s
P
r
i
v
a
c
y
-
s
e
n
s
i
t
i
v
e
;
c
u
l
t
u
r
a
l
b
i
a
s
i
n
i
ma
g
e
s
h
a
r
i
n
g
[
4
]
,
[
6
]
,
[
8
]
S
e
n
s
o
r
/
s
m
a
r
t
p
h
o
n
e
d
a
t
a
C
l
a
s
si
c
a
l
M
L,
LSTM
,
m
u
l
t
i
m
o
d
a
l
f
u
si
o
n
S
t
u
d
e
n
t
l
o
g
s
,
G
P
S
,
a
n
d
a
c
c
e
l
e
r
o
m
e
t
e
r
d
a
t
a
P
a
ssi
v
e
,
c
o
n
t
i
n
u
o
u
s,
u
n
o
b
t
r
u
si
v
e
C
o
n
t
e
x
t
-
d
e
p
e
n
d
e
n
t
;
l
o
n
g
-
t
e
r
m
t
r
a
c
k
i
n
g
r
e
q
u
i
r
e
d
[
1
]
,
[
9
]
T
r
a
n
s
a
c
t
i
o
n
/
s
p
e
n
d
i
n
g
d
a
t
a
(
t
h
i
s
s
t
u
d
y
)
LR
,
D
TR
F
,
S
V
M
,
C
N
N
K
a
g
g
l
e
c
o
n
su
mer
sp
e
n
d
i
n
g
d
a
t
a
set
Le
ss
c
u
r
a
t
e
d
,
r
e
f
l
e
c
t
s
g
e
n
u
i
n
e
p
r
e
f
e
r
e
n
c
e
s
;
sca
l
a
b
l
e
F
e
w
v
a
l
i
d
a
t
e
d
b
e
n
c
h
m
a
r
k
s
;
c
u
l
t
u
r
a
l
/
e
c
o
n
o
m
i
c
v
a
r
i
a
t
i
o
n
s
[
1
0
]
,
[
1
5
]
,
[
1
6
]
,
[
1
8
]
M
u
l
t
i
m
o
d
a
l
(
t
e
x
t
+
i
ma
g
e
+
se
n
s
o
r
+
sp
e
n
d
i
n
g
)
T
r
a
n
s
f
o
r
m
e
r
s
,
m
u
l
t
i
-
m
o
d
a
l
f
u
s
i
o
n
m
o
d
e
l
s
(
B
E
R
T
+
C
N
N
+
L
S
T
M
)
my
P
e
r
s
o
n
a
l
i
t
y
,
h
y
b
r
i
d
b
e
n
c
h
mar
k
s
R
i
c
h
a
n
d
r
o
b
u
s
t
;
h
i
g
h
e
r
a
c
c
u
r
a
c
y
b
y
c
o
m
b
i
n
i
n
g
s
i
g
n
a
l
s
D
a
t
a
-
i
n
t
e
n
si
v
e
;
h
i
g
h
c
o
m
p
l
e
x
i
t
y
;
p
r
i
v
a
c
y
c
o
n
c
e
r
n
s
[
8
]
,
[
1
3
]
,
[
1
7
]
Et
h
i
c
s
a
n
d
F
a
i
r
n
e
ss
i
n
A
I
P
r
o
f
i
l
i
n
g
Ex
p
l
a
i
n
a
b
l
e
A
I
(
S
H
A
P
,
LI
M
E,
c
o
u
n
t
e
r
f
a
c
t
u
a
l
s)
R
e
g
u
l
a
t
o
r
y
f
r
a
mew
o
r
k
s
(
G
D
P
R
,
A
P
A
)
En
s
u
r
e
s
t
r
a
n
sp
a
r
e
n
c
y
,
u
ser
t
r
u
s
t
,
c
o
mp
l
i
a
n
c
e
E
x
p
l
a
i
n
a
b
i
l
i
t
y
a
l
o
n
e
d
o
e
s
n
o
t
e
n
s
u
r
e
f
a
i
r
n
e
s
s
;
m
u
s
t
a
d
d
r
e
s
s
b
i
a
s
d
i
r
e
c
t
l
y
[
1
9
]
,
[
2
0
]
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
4
,
No
.
6
,
Dec
em
b
er
2
0
2
5
:
4
5
5
2
-
4
5
6
4
4554
I
n
s
u
m
m
a
r
y
,
s
o
cia
l
m
e
d
i
a
c
o
n
te
n
t
p
r
i
m
a
r
il
y
r
ef
le
cts
s
el
f
-
p
r
ese
n
t
ati
o
n
an
d
s
o
cia
l
d
esi
r
e,
wh
e
r
ea
s
s
p
e
n
d
i
n
g
b
eh
a
v
i
o
r
p
r
o
v
i
d
es
in
s
i
g
h
ts
i
n
t
o
u
n
d
er
ly
i
n
g
v
a
l
u
es
,
p
r
i
o
r
it
ies
,
a
n
d
d
ec
is
i
o
n
-
m
a
k
i
n
g
p
r
o
c
ess
es
.
Sp
e
n
d
i
n
g
,
u
n
li
k
e
s
o
ci
al
m
e
d
ia
b
e
h
a
v
i
o
r
,
is
o
f
te
n
l
ess
c
u
r
at
ed
a
n
d
m
o
r
e
r
ef
le
cti
v
e
o
f
g
en
u
i
n
e
p
r
e
f
e
r
e
n
c
es,
m
a
k
i
n
g
it
a
r
o
b
u
s
t
d
a
ta
s
o
u
r
ce
f
o
r
p
e
r
s
o
n
al
it
y
i
n
f
e
r
e
n
c
e.
B
y
e
x
a
m
i
n
i
n
g
wh
et
h
e
r
a
m
o
r
e
e
x
t
en
s
iv
e
co
ll
ec
ti
o
n
o
f
b
e
h
a
v
i
o
r
al
in
d
ic
at
o
r
s
ca
n
e
n
h
a
n
ce
t
h
e
p
r
ec
is
i
o
n
wi
th
w
h
i
c
h
p
s
y
ch
o
l
o
g
ic
al
f
e
at
u
r
es
ca
n
b
e
d
e
d
u
c
e
d
f
r
o
m
ex
p
en
d
i
tu
r
e
r
e
co
r
d
s
,
t
o
im
p
r
o
v
e
co
m
p
r
eh
e
n
s
io
n
o
f
th
e
r
e
lat
io
n
s
h
i
p
b
etw
ee
n
s
p
e
n
d
i
n
g
p
a
tte
r
n
s
a
n
d
p
e
r
s
o
n
alit
y
tr
aits
;
i
)
o
v
er
all
s
p
e
n
d
i
n
g
p
att
er
n
s
,
ii
)
c
ate
g
o
r
y
-
r
ela
te
d
s
p
e
n
d
i
n
g
b
eh
av
io
r
,
ii
i
)
c
u
s
t
o
m
e
r
ca
te
g
o
r
y
p
r
o
f
il
e.
Mo
d
el
d
ev
el
o
p
m
en
t
in
v
o
l
v
e
d
tr
ai
n
i
n
g
an
d
e
v
a
lu
ati
n
g
al
g
o
r
i
th
m
s
,
n
a
m
e
ly
SV
M,
DT
,
r
a
n
d
o
m
f
o
r
est
(
R
F)
,
a
n
d
co
n
v
o
lu
ti
o
n
al
n
e
u
r
al
n
et
wo
r
k
(
C
N
N)
.
H
o
w
ev
er
,
s
p
en
d
i
n
g
b
e
h
a
v
i
o
r
als
o
d
if
f
e
r
s
ac
r
o
s
s
i
n
co
m
e
g
r
o
u
p
s
a
n
d
r
e
g
i
o
n
s
f
o
r
e
x
a
m
p
le
,
h
i
g
h
e
r
-
in
co
m
e
i
n
d
iv
id
u
als t
en
d
t
o
s
p
e
n
d
m
o
r
e
o
n
d
is
cr
eti
o
n
a
r
y
/
li
f
es
ty
le
ca
t
eg
o
r
i
es,
wh
ile
lo
wer
-
i
n
c
o
m
e
g
r
o
u
p
s
f
o
c
u
s
m
ai
n
l
y
o
n
ess
e
n
t
ial
n
ee
d
s
.
C
u
lt
u
r
al
f
a
ct
o
r
s
als
o
i
n
f
l
u
e
n
ce
w
h
i
ch
ca
te
g
o
r
ies p
e
o
p
l
e
p
r
i
o
r
iti
ze
; h
en
ce
,
s
u
c
h
v
a
r
i
ati
o
n
s
s
h
o
u
ld
b
e
c
o
n
s
i
d
e
r
e
d
wh
en
i
n
t
er
p
r
e
ti
n
g
p
e
r
s
o
n
alit
y
tr
aits
f
r
o
m
s
p
e
n
d
i
n
g
d
at
a.
2.
M
E
T
H
O
D
2
.
1
.
Da
t
a
R
esear
ch
d
ata
was
ac
q
u
ir
ed
f
r
o
m
th
e
Kag
g
le
p
latf
o
r
m
a
n
d
c
o
m
p
r
is
es
s
p
en
d
in
g
r
e
co
r
d
s
o
f
o
v
er
1
,
2
0
0
in
d
iv
id
u
al
cu
s
to
m
er
s
c
o
llected
o
v
er
a
p
er
i
o
d
o
f
th
r
ee
m
o
n
th
s
.
E
ac
h
tr
an
s
ac
tio
n
lo
g
en
co
m
p
ass
es
in
f
o
r
m
atio
n
lik
e
u
s
er
I
D,
g
e
n
d
er
,
y
ea
r
o
f
b
i
r
th
(
YOB),
lo
ca
tio
n
(
h
o
m
e
a
n
d
co
u
n
tr
y
)
,
p
u
r
ch
ase
ca
teg
o
r
y
,
tr
an
s
ac
tio
n
d
ate
an
d
tim
e,
p
ay
m
en
t
m
eth
o
d
,
an
d
tr
a
n
s
ac
tio
n
am
o
u
n
t.
T
o
e
n
s
u
r
e
u
s
er
p
r
iv
ac
y
an
d
d
ata
co
n
f
id
e
n
tiality
,
all
p
er
s
o
n
ally
id
en
tifia
b
le
in
f
o
r
m
atio
n
(
e.
g
.
,
n
am
es
an
d
ac
c
o
u
n
t
n
u
m
b
e
r
s
)
was
ex
clu
d
ed
f
r
o
m
a
n
aly
s
is
.
T
h
e
d
ataset
u
n
d
e
r
wen
t
p
r
ep
r
o
ce
s
s
in
g
to
ad
d
r
ess
m
is
s
in
g
v
al
u
es,
s
ca
le
n
u
m
e
r
ical
f
ea
t
u
r
es,
an
d
tr
an
s
f
o
r
m
ca
teg
o
r
ical
d
ata
in
to
a
s
u
itab
le
f
o
r
m
at.
T
o
f
ac
ilit
ate
s
u
p
er
v
is
e
d
lear
n
in
g
f
o
r
p
er
s
o
n
ality
p
r
ed
ictio
n
,
ea
ch
u
s
er
was
ass
ig
n
ed
a
p
er
s
o
n
ality
lab
el
b
ased
o
n
an
e
x
ter
n
al
p
s
y
c
h
o
m
etr
ic
m
ap
p
in
g
alig
n
ed
with
s
p
en
d
in
g
p
atter
n
s
an
d
co
n
s
u
m
er
b
eh
av
io
r
liter
atu
r
e.
Du
e
to
th
e
m
o
d
est
d
ata
s
ize,
d
ata
au
g
m
en
tat
io
n
an
d
s
tr
atif
ied
v
alid
atio
n
wer
e
em
p
lo
y
e
d
to
e
n
s
u
r
e
r
o
b
u
s
t
tr
ain
in
g
an
d
ev
alu
atio
n
.
Fig
u
r
e
1
s
h
o
ws th
e
s
u
g
g
est
ed
s
y
s
te
m
'
s
ar
ch
itectu
r
e
d
iag
r
am
.
Fig
u
r
e
1
.
Ar
c
h
itectu
r
e
d
iag
r
a
m
o
f
p
r
o
p
o
s
ed
m
eth
o
d
2
.
2
.
I
nd
iv
idu
a
l ps
y
cho
lo
g
ica
l t
ra
it
s
ba
s
ed
o
n t
heir
s
pen
di
ng
pa
t
t
er
n
T
h
e
B
ig
Fiv
e
p
er
s
o
n
ality
tr
aits
,
wh
en
co
m
b
in
ed
with
s
p
en
d
in
g
an
d
ex
p
en
s
e
m
an
ag
e
m
en
t
p
atter
n
s
,
p
r
o
v
id
e
v
alu
a
b
le
in
s
ig
h
ts
in
to
f
in
an
cial
d
ec
is
io
n
-
m
a
k
in
g
.
Per
s
o
n
ality
tr
aits
an
d
th
eir
r
elatio
n
s
h
ip
with
ty
p
ical
s
p
en
d
in
g
b
eh
av
io
r
is
s
u
m
m
ar
i
ze
d
in
T
ab
le
2
.
P
r
o
v
id
in
g
ev
i
d
en
ce
o
f
h
o
w
p
s
y
ch
o
lo
g
ical
c
h
ar
ac
ter
is
tics
s
h
ap
e
f
in
an
cial
d
ec
is
io
n
-
m
a
k
in
g
.
2
.
3
.
Da
t
a
pre
-
pro
ce
s
s
ing
T
h
e
d
ataset
co
n
s
is
ts
o
f
two
ca
teg
o
r
ies
o
f
r
ec
o
r
d
ed
ac
tiv
ity
:
cr
ed
it
tr
an
s
ac
tio
n
s
(
r
ev
en
u
e)
an
d
d
eb
it
tr
an
s
ac
tio
n
s
(
o
u
tg
o
in
g
)
.
A
d
e
b
it
tr
an
s
ac
tio
n
ca
u
s
es
th
e
b
al
an
ce
am
o
u
n
t
to
f
all
(
e.
g
.
,
wit
h
d
r
awa
l
o
f
am
o
u
n
t,
p
ay
m
en
t
f
o
r
s
o
m
e
item
s
,
an
d
p
u
r
ch
asin
g
)
an
d
a
c
r
ed
it
tr
an
s
ac
tio
n
ca
u
s
es
it
to
g
r
o
w
(
e.
g
.
,
s
alar
y
,
d
ep
o
s
it
f
r
o
m
o
th
er
s
,
an
d
o
th
e
r
r
ev
en
u
e)
.
O
n
ly
d
eb
it
tr
an
s
ac
tio
n
s
th
at
r
ef
l
ec
t
ea
ch
p
er
s
o
n
'
s
u
n
iq
u
e
ex
p
e
n
d
itu
r
e
ar
e
r
etain
e
d
f
o
r
th
e
p
u
r
p
o
s
e
to
an
al
y
ze
th
ei
r
b
eh
av
i
o
r
.
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
Hu
ma
n
s
’
p
s
yc
h
o
lo
g
ica
l tra
its
cla
s
s
ifica
tio
n
fr
o
m
th
eir
…
(
A
r
p
ith
a
C
h
ikka
ma
g
a
lu
r
u
N
a
r
a
s
imh
e
Go
w
d
a
)
4555
T
o
en
s
u
r
e
b
alan
ce
d
d
ata
an
d
r
etain
o
n
ly
in
d
iv
i
d
u
als
ac
tiv
ely
en
g
ag
e
d
in
p
u
r
ch
asin
g
ac
tiv
it
ies
an
d
to
r
etain
o
n
l
y
th
o
s
e
in
d
iv
i
d
u
als
in
th
e
d
ataset
with
in
d
iv
i
d
u
als
w
h
o
wer
e
ac
tiv
ely
en
g
a
g
ed
i
n
p
u
r
ch
asin
g
ac
tiv
ities
.
T
o
m
ak
e
th
e
d
ata
less
s
p
ar
s
e
o
f
ca
teg
o
r
y
s
p
ac
e
in
th
e
d
atas
et,
th
e
p
u
r
c
h
ase
ca
teg
o
r
ies
t
h
at
h
ad
at
least
o
n
e
tr
an
s
ac
tio
n
wer
e
m
ain
tain
ed
;
t
h
e
n
e
x
t
s
tep
was
t
o
r
etain
o
n
ly
in
d
iv
id
u
als
with
at
least
ten
tr
a
n
s
ac
tio
n
s
p
er
m
o
n
th
in
th
e
d
ataset.
Ou
t
o
f
th
e
r
em
ain
in
g
p
u
r
c
h
ase
ca
teg
o
r
ies,
th
e
ca
teg
o
r
y
g
r
o
u
p
in
g
is
f
o
r
m
e
d
.
T
h
e
1
5
p
u
r
c
h
ase
ca
teg
o
r
y
g
r
o
u
p
s
ar
e
g
r
o
ce
r
ies
,
clo
th
es,
b
o
o
k
s
,
f
o
o
d
an
d
d
i
n
in
g
o
u
t,
g
am
es/g
am
b
lin
g
,
h
o
u
s
eh
o
ld
s
p
en
d
in
g
s
,
tr
an
s
p
o
r
tatio
n
,
m
o
b
ile,
h
o
lid
a
y
,
p
e
r
s
o
n
al
ca
r
e
,
ch
ild
r
en
,
ch
ar
ities
,
h
ea
lth
ca
r
e,
in
s
u
r
an
ce
,
an
d
en
ter
tain
m
e
n
t.
Fo
r
e
x
am
p
le:
in
s
u
r
an
ce
ca
teg
o
r
y
g
r
o
u
p
in
clu
d
es
all
th
e
s
p
en
d
in
g
s
lik
e
h
ea
lth
in
s
u
r
an
ce
,
v
eh
icle
in
s
u
r
an
ce
,
life
in
s
u
r
an
ce
,
h
o
m
e
in
s
u
r
an
ce
,
a
n
d
h
o
m
e
a
p
p
lian
ce
in
s
u
r
a
n
ce
.
T
r
an
s
p
o
r
tatio
n
ca
te
g
o
r
y
g
r
o
u
p
in
clu
d
es
all
th
e
s
p
en
d
in
g
lik
e
p
u
b
lic
tr
a
n
s
p
o
r
t,
r
o
ad
c
h
ar
g
es,
p
a
r
k
in
g
ch
ar
g
es,
an
d
f
u
el.
T
h
e
p
r
e
p
r
o
ce
s
s
in
g
p
ip
elin
e
illu
s
tr
ated
in
Fig
u
r
e
2
d
escr
ib
es
th
e
s
u
cc
ess
iv
e
ac
tio
n
s
tak
en
to
p
r
ep
a
r
e
th
e
r
aw
d
ataset
f
o
r
ML
an
d
D
L
m
o
d
els.
Star
tin
g
f
r
o
m
th
e
Kag
g
le
-
s
o
u
r
ce
d
r
aw
tr
an
s
ac
tio
n
d
ata,
th
e
wo
r
k
f
lo
w
in
clu
d
es
th
e
r
em
o
v
al
o
f
p
e
r
s
o
n
ally
id
en
tifia
b
le
i
n
f
o
r
m
atio
n
(
PII
)
,
f
ilter
in
g
b
ased
o
n
u
s
er
ac
tiv
ity
,
an
d
g
r
o
u
p
in
g
o
f
p
u
r
ch
ase
ca
teg
o
r
ies.
R
elev
an
t
b
eh
av
io
r
al
f
ea
tu
r
es
ar
e
e
x
tr
ac
ted
ac
r
o
s
s
th
r
ee
d
im
en
s
io
n
s
o
v
er
all
s
p
en
d
in
g
,
ca
teg
o
r
y
-
r
elate
d
b
e
h
av
io
r
,
an
d
cu
s
to
m
er
p
r
o
f
ile
d
is
tr
ib
u
tio
n
.
Af
ter
n
o
r
m
aliza
tio
n
,
th
ese
ch
ar
ac
ter
is
tics
ar
e
lab
eled
u
s
in
g
a
p
er
ce
n
tile
-
b
ased
class
if
icatio
n
ap
p
r
o
ac
h
alig
n
ed
with
th
e
B
ig
Fiv
e
p
er
s
o
n
ality
m
o
d
el.
T
h
e
d
ataset
th
at
was p
r
ep
r
o
ce
s
s
ed
is
f
in
ally
s
ep
ar
ated
in
to
tr
a
in
in
g
an
d
test
in
g
s
ets f
o
r
m
o
d
el
ev
alu
atio
n
.
T
ab
le
2
.
R
elatio
n
s
h
ip
b
etwe
en
p
er
s
o
n
ality
tr
aits
an
d
s
p
e
n
d
in
g
b
eh
a
v
io
r
s
P
e
r
so
n
a
l
i
t
y
t
r
a
i
t
S
p
e
n
d
i
n
g
b
e
h
a
v
i
o
r
O
p
e
n
n
e
ss
En
j
o
y
s s
p
e
n
d
i
n
g
o
n
u
n
i
q
u
e
,
c
r
e
a
t
i
v
e
,
o
r
n
e
w
e
x
p
e
r
i
e
n
c
e
s
,
s
u
c
h
a
s t
r
a
v
e
l
,
a
r
t
,
o
r
n
o
v
e
l
p
r
o
d
u
c
t
s.
C
o
n
sc
i
e
n
t
i
o
u
s
n
e
ss
Te
n
d
s
t
o
b
e
c
a
r
e
f
u
l
,
p
l
a
n
n
e
d
,
a
n
d
r
e
s
p
o
n
s
i
b
l
e
w
i
t
h
mo
n
e
y
,
o
f
t
e
n
s
a
v
i
n
g
o
r
i
n
v
e
st
i
n
g
w
i
se
l
y
.
Ex
t
r
a
v
e
r
si
o
n
S
p
e
n
d
s
o
n
s
o
c
i
a
l
a
c
t
i
v
i
t
i
e
s,
e
n
t
e
r
t
a
i
n
men
t
,
d
i
n
i
n
g
o
u
t
,
a
n
d
e
x
p
e
r
i
e
n
c
e
s
t
h
a
t
i
n
v
o
l
v
e
o
t
h
e
r
s.
A
g
r
e
e
a
b
l
e
n
e
ss
P
r
e
f
e
r
s sp
e
n
d
i
n
g
o
n
g
i
f
t
s
,
c
h
a
r
i
t
a
b
l
e
d
o
n
a
t
i
o
n
s,
o
r
a
n
y
t
h
i
n
g
t
h
a
t
b
e
n
e
f
i
t
s
o
t
h
e
r
s o
r
p
r
o
mo
t
e
s
h
a
r
mo
n
y
.
N
e
u
r
o
t
i
c
i
sm
M
a
y
e
n
g
a
g
e
i
n
i
mp
u
l
si
v
e
o
r
e
m
o
t
i
o
n
a
l
s
p
e
n
d
i
n
g
d
u
r
i
n
g
st
r
e
s
s
o
r
a
n
x
i
e
t
y
,
s
o
met
i
mes
l
e
a
d
i
n
g
t
o
r
e
g
r
e
t
.
S
e
l
f
-
C
o
n
t
r
o
l
D
e
mo
n
st
r
a
t
e
s
d
i
sc
i
p
l
i
n
e
d
sp
e
n
d
i
n
g
h
a
b
i
t
s,
p
r
i
o
r
i
t
i
z
i
n
g
sa
v
i
n
g
s a
n
d
r
e
s
i
st
i
n
g
i
mp
u
l
s
i
v
e
p
u
r
c
h
a
ses
.
M
a
t
e
r
i
a
l
i
sm
S
p
e
n
d
s
m
o
r
e
o
n
l
u
x
u
r
y
i
t
e
m
s,
s
t
a
t
u
s
s
y
mb
o
l
s,
a
n
d
p
o
ssess
i
o
n
s
t
h
a
t
e
n
h
a
n
c
e
sel
f
-
i
m
a
g
e
.
Fig
u
r
e
2
.
Data
p
r
ep
r
o
ce
s
s
in
g
p
ip
elin
e
f
o
r
p
er
s
o
n
ality
tr
ait
class
if
icatio
n
b
ased
o
n
s
p
en
d
i
n
g
b
eh
av
io
r
2
.
4
.
F
e
a
t
ure
ex
t
r
a
ct
io
n
Acc
o
r
d
in
g
to
th
e
n
atu
r
e
o
f
s
p
en
d
in
g
p
atter
n
s
ex
h
ib
ited
,
b
eh
av
io
r
al
asp
ec
ts
ar
e
d
iv
id
ed
in
to
th
r
ee
g
r
o
u
p
s
to
ch
a
r
ac
ter
ize
in
d
i
v
id
u
al
s
p
en
d
in
g
b
eh
a
v
io
r
;
i)
o
v
e
r
all
s
p
en
d
in
g
b
eh
a
v
io
r
;
ii)
ca
te
g
o
r
y
-
r
elate
d
s
p
e
n
d
in
g
b
eh
av
io
r
; a
n
d
iii)
c
u
s
to
m
er
ca
t
eg
o
r
y
p
r
o
f
ile
[
1
0
]
.
2
.
4
.
1
.
O
v
er
a
ll sp
endi
ng
beha
v
io
r
T
h
is
m
eth
o
d
tak
es
a
p
er
s
o
n
'
s
to
tal
s
p
en
d
in
g
p
atter
n
s
o
v
er
a
th
r
ee
-
m
o
n
th
p
er
io
d
in
t
o
ac
co
u
n
t.
C
u
s
to
m
er
s
'
s
p
en
d
in
g
p
atter
n
s
i
n
clu
d
e
th
e
o
v
e
r
all
n
u
m
b
er
o
f
t
r
an
s
ac
tio
n
s
(
N
tot
)
,
th
e
s
u
m
o
f
a
ll th
e
ex
p
e
n
d
itu
r
es
(A
tot
)
,
an
d
t
h
e
cu
s
to
m
er
-
wis
e
av
er
ag
e
tr
a
n
s
ac
tio
n
v
alu
e
(
A
a
vg
)
o
v
er
t
h
at
tim
e
p
er
i
o
d
.
T
o
ca
p
tu
r
e
th
e
r
elativ
e
d
is
p
er
s
io
n
o
f
a
c
u
s
to
m
er
’
s
ex
p
en
d
itu
r
e
p
atter
n
s
,
a
p
p
ly
in
g
th
e
co
ef
f
icien
t
o
f
v
ar
iatio
n
(
C
V)
,
wh
ich
is
ca
lcu
lated
as
th
e
r
atio
o
f
s
tan
d
ar
d
d
e
v
iatio
n
(
σ
)
to
t
h
e
tr
an
s
ac
tio
n
v
o
l
u
m
es'
m
ea
n
(
μ
)
,
c
u
s
to
m
er
s
with
a
h
i
g
h
C
V
ten
d
to
v
ar
y
th
eir
s
p
en
d
in
g
s
ig
n
if
ican
t
ly
b
etwe
en
tr
an
s
ac
tio
n
s
,
wh
ile
th
o
s
e
with
a
lo
w
C
V
s
h
o
w
m
o
r
e
co
n
s
is
ten
cy
.
2
.
4
.
2
.
Ca
t
eg
o
ry
-
re
la
t
ed
s
pen
din
g
beha
v
io
r
T
h
e
s
ec
o
n
d
m
etr
ic
r
elate
s
to
th
e
ty
p
es
f
o
r
ev
er
y
in
d
iv
id
u
al’
s
p
u
r
ch
ases
.
T
h
ese
f
ea
tu
r
es
ta
k
e
th
e
f
o
r
m
o
f
d
iv
e
r
s
ity
,
p
er
s
is
ten
ce
,
an
d
t
u
r
n
o
v
er
o
f
s
p
en
d
in
g
p
atter
n
s
o
f
a
p
er
s
o
n
th
r
o
u
g
h
o
u
t tim
e.
‒
Div
er
s
ity
o
f
p
u
r
ch
ase:
to
an
a
ly
ze
h
o
w
b
r
o
a
d
ly
an
d
ev
e
n
ly
a
cu
s
to
m
er
s
p
r
ea
d
s
th
eir
s
p
en
d
in
g
ac
r
o
s
s
d
if
f
er
en
t
p
r
o
d
u
ct
o
r
s
er
v
ice
ca
teg
o
r
ies,
r
ev
ea
lin
g
co
n
s
u
m
e
r
p
r
ef
er
en
ce
s
an
d
b
eh
a
v
io
r
.
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
4
,
No
.
6
,
Dec
em
b
er
2
0
2
5
:
4
5
5
2
-
4
5
6
4
4556
=
−
∑
(
)
=
1
(
1
)
W
h
er
e,
N
d
en
o
tes
th
e
n
u
m
b
er
o
f
d
if
f
er
en
t
co
n
s
u
m
er
ca
teg
o
r
ies.
Pic
=
∑
=
1
an
d
is
th
e
am
o
u
n
t
o
f
m
o
n
ey
t
h
at
clien
t
i
s
p
en
t
in
c
ateg
o
r
y
c
.
A
lo
w
D
category
v
al
u
e
r
ep
r
esen
ts
th
at
t
h
e
m
ajo
r
ity
o
f
cu
s
to
m
e
r
s
p
en
d
in
g
f
ell
in
to
a
s
m
all
n
u
m
b
er
o
f
ca
teg
o
r
ies.
T
h
e
h
ig
h
er
th
e
D
category
v
al
u
e,
th
e
m
o
r
e
ev
en
l
y
th
e
cu
s
to
m
er
s
p
lits
th
eir
s
p
en
d
in
g
ac
r
o
s
s
all
th
e
ca
teg
o
r
ies th
ey
b
u
y
f
r
o
m
.
‒
Per
s
is
ten
ce
o
f
p
u
r
c
h
ase:
to
m
e
asu
r
e
th
e
co
n
s
is
ten
cy
o
r
s
tab
ili
ty
in
a
c
u
s
to
m
er
'
s
p
u
r
ch
asin
g
b
eh
av
io
r
o
v
e
r
tim
e
b
y
co
m
p
u
tin
g
th
e
av
er
ag
e
co
s
in
e
s
im
ilar
ity
b
etwe
en
th
eir
m
o
n
th
ly
ca
teg
o
r
y
-
wis
e
s
p
en
d
in
g
p
atter
n
s
.
=
∑
(
,
+
1
)
=
0
(
2
)
I
n
th
is
co
n
tex
t,
Sᵢ
r
ep
r
esen
ts
th
e
v
ec
to
r
o
f
ca
teg
o
r
y
-
wis
e
tr
an
s
ac
tio
n
p
r
o
p
o
r
tio
n
s
f
o
r
a
s
p
ec
if
ic
m
o
n
th
,
an
d
n
co
r
r
esp
o
n
d
s
to
th
e
n
u
m
b
er
o
f
m
o
n
th
s
co
v
er
ed
in
th
e
d
ataset.
‒
C
ateg
o
r
y
tu
r
n
o
v
er
:
t
o
ass
ess
tem
p
o
r
al
co
n
s
is
ten
cy
in
s
p
en
d
in
g
b
eh
av
i
o
r
,
th
e
c
h
an
g
e
in
s
p
en
d
in
g
ca
teg
o
r
ies b
etwe
en
two
co
n
s
ec
u
tiv
e
m
o
n
t
h
s
is
co
m
p
u
ted
.
=
∑
∩
+
1
∪
+
1
−
1
(
3
)
W
h
er
e
n
is
th
e
d
ataset'
s
m
o
n
th
co
u
n
t
an
d
c
i
is
th
e
co
llectio
n
o
f
p
u
r
ch
ase
ca
teg
o
r
ies
in
th
e
i
th
m
o
n
th
.
C
turnover
is
eq
u
al
to
ze
r
o
,
w
h
en
th
e
s
p
e
n
d
in
g
ca
teg
o
r
ies
in
t
h
e
two
s
u
cc
ess
iv
e
m
o
n
th
s
d
o
n
o
t
o
v
er
lap
,
an
d
wh
e
n
th
er
e
is
a
p
er
f
ec
t
o
v
er
lap
,
it e
q
u
als 1
.
2
.
4
.
3
.
Ca
t
eg
o
ry
pro
f
ile
f
ea
t
u
re
s
C
ateg
o
r
y
p
r
o
f
ile
f
ea
tu
r
es r
ep
r
esen
t su
m
m
ar
ized
in
f
o
r
m
atio
n
ab
o
u
t a
n
in
d
iv
id
u
al’
s
s
p
en
d
in
g
b
eh
av
i
o
r
ac
r
o
s
s
d
if
f
er
en
t
ex
p
en
s
e
ca
teg
o
r
ies
.
T
h
ese
ca
teg
o
r
ies
ca
n
in
clu
d
e
s
u
ch
as
f
o
o
d
,
tr
a
v
el,
tr
an
s
p
o
r
tatio
n
,
en
ter
tain
m
en
t,
a
n
d
p
e
r
s
o
n
al
ca
r
e
.
Oth
er
d
e
f
in
ed
ca
teg
o
r
y
g
r
o
u
p
s
ar
e
also
in
clu
d
e
d
in
th
e
s
u
m
m
ar
y
.
2
.
5
.
Co
rr
el
a
t
io
n a
na
ly
s
is
T
h
e
Pear
s
o
n
co
r
r
elatio
n
co
ef
f
icien
t
is
u
tili
ze
d
in
co
r
r
elatio
n
an
aly
s
is
to
ascer
tain
th
e
lin
k
b
etwe
en
th
e
b
eh
av
io
r
al
c
h
ar
ac
ter
is
tics
an
d
th
e
u
n
iq
u
e
p
s
y
ch
o
lo
g
ical
tr
aits
o
f
cu
s
to
m
er
s
[
1
8
]
,
[
2
1
]
,
[
2
2
]
.
T
h
e
f
o
r
m
u
la
f
o
r
Pear
s
o
n
’
s
co
r
r
elatio
n
co
e
f
f
icien
t
‘
r
’
r
elate
s
to
h
o
w
clo
s
ely
a
lin
e
o
f
b
est
f
it,
o
r
h
o
w
well
a
lin
ea
r
r
eg
r
ess
io
n
,
p
r
ed
icts
th
e
r
elatio
n
s
h
ip
b
etwe
en
th
e
two
v
a
r
iab
les.
I
t is p
r
es
en
ted
as
(
4
)
.
=
∑
(
−
̅
)
(
−
̅
)
√
∑
(
−
̅
)
2
∑
(
−
̅
)
2
(
4
)
W
h
er
e
x
i
an
d
y
i
r
e
p
r
esen
t
th
e
d
ata
v
alu
es
r
ep
r
esen
tin
g
s
p
en
d
in
g
b
eh
a
v
io
r
f
ea
tu
r
es
an
d
p
e
r
s
o
n
ality
tr
ait
f
o
r
ea
c
h
in
d
iv
id
u
al
r
esp
ec
tiv
el
y
,
an
d
th
e
m
ea
n
s
ar
e
r
ep
r
esen
ted
b
y
x
a
n
d
ȳ
.
2
.
5
.
1
.
O
v
er
a
ll a
nd
ca
t
eg
o
r
y
-
r
ela
t
ed
f
ea
t
ures v
s
.
ind
iv
idu
a
l
t
ra
it
s
T
h
is
s
ec
tio
n
ex
p
lo
r
es h
o
w
o
v
e
r
all
s
p
en
d
in
g
b
eh
av
i
o
r
s
r
elate
to
in
d
iv
id
u
al
p
er
s
o
n
ality
tr
aits
:
‒
E
x
t
r
a
v
e
r
s
i
o
n
:
e
x
t
r
a
v
e
r
s
i
o
n
a
n
d
B
t
o
t
w
e
r
e
s
h
o
w
n
t
o
h
a
v
e
a
p
o
s
i
t
i
v
e
c
o
r
r
e
l
a
t
i
o
n
,
s
u
g
g
e
s
t
i
n
g
t
h
a
t
t
h
o
s
e
w
h
o
p
o
s
s
e
s
s
t
h
i
s
f
e
a
t
u
r
e
t
e
n
d
t
o
b
e
m
o
r
e
i
m
p
u
l
s
i
v
e
w
i
t
h
t
h
e
i
r
e
x
p
e
n
d
i
t
u
r
e
s
i
n
c
o
m
p
a
r
i
s
o
n
t
o
t
h
e
i
r
o
t
h
e
r
p
e
o
p
l
e
,
m
o
r
e
e
x
t
r
o
v
e
r
t
e
d
p
e
r
s
o
n
s
t
y
p
i
c
a
l
l
y
h
a
d
m
o
r
e
t
r
a
n
s
a
c
t
i
o
n
s
(
N
t
o
t
)
;
f
u
r
t
h
e
r
m
o
r
e
,
w
e
d
i
s
c
o
v
e
r
e
d
a
p
o
s
i
t
i
v
e
c
o
r
r
e
l
a
t
i
o
n
b
e
t
w
e
e
n
t
h
e
t
o
p
f
i
v
e
e
x
p
e
n
d
i
t
u
r
e
c
a
t
e
g
o
r
i
e
s
(
C
5
t
u
r
n
o
v
e
r
)
a
n
d
c
a
t
e
g
o
r
y
s
i
m
i
l
a
r
i
t
y
o
v
e
r
t
i
m
e
.
‒
C
o
n
s
c
i
e
n
t
i
o
u
s
n
e
s
s
:
t
h
e
a
v
e
r
a
g
e
a
m
o
u
n
t
o
f
t
r
a
n
s
a
c
t
i
o
n
(
A
avg
)
a
n
d
t
h
e
t
o
t
a
l
a
m
o
u
n
t
s
p
e
n
t
(
A
tot
)
w
e
r
e
f
o
u
n
d
t
o
b
e
s
u
b
s
t
a
n
t
i
a
l
l
y
a
n
d
f
a
v
o
r
a
b
l
y
c
o
n
n
e
c
t
e
d
w
i
t
h
c
o
n
s
c
i
e
n
t
i
o
u
s
n
e
s
s
.
F
u
r
t
h
e
r
m
o
r
e
,
w
e
d
i
s
c
o
v
e
r
e
d
t
h
a
t
t
h
e
r
e
l
a
t
i
v
e
a
m
o
u
n
t
s
s
p
e
n
t
o
v
e
r
s
e
v
e
r
a
l
w
e
e
k
s
d
i
f
f
e
r
s
u
b
s
t
a
n
t
i
a
l
l
y
(
C
persistence
)
f
o
r
t
h
o
s
e
w
i
t
h
g
r
e
a
t
e
r
c
o
n
s
c
i
e
n
t
i
o
u
s
n
e
s
s
s
c
o
r
e
s
.
‒
Neu
r
o
ticis
m
:
o
v
er
all
ex
p
en
d
itu
r
e
(
A
tot
)
,
av
er
a
g
e
am
o
u
n
t
o
f
t
r
an
s
ac
tio
n
(
A
avg
)
,
an
d
to
tal
co
u
n
t
o
f
s
p
en
d
in
g
ca
teg
o
r
ies (
N
c
)
wer
e
all
lo
wer
am
o
n
g
m
o
r
e
n
eu
r
o
tic
p
eo
p
le.
‒
Op
en
n
ess
:
o
p
en
n
ess
to
n
ew
e
x
p
er
ien
ce
s
is
p
o
s
itiv
ely
co
r
r
e
lated
with
N
tot
;
an
in
d
iv
id
u
al
wh
o
is
m
o
r
e
r
ec
ep
tiv
e
to
o
p
en
n
ess
is
m
o
r
e
lik
ely
to
en
g
ag
e
in
b
u
r
s
ty
s
p
en
d
in
g
an
d
co
m
p
lete
m
o
r
e
tr
a
n
s
ac
tio
n
s
th
an
th
o
s
e
ar
o
u
n
d
th
em
.
‒
Ma
ter
ialis
m
:
th
e
to
p
f
iv
e
ex
p
e
n
d
itu
r
e
ca
teg
o
r
ies
(
C
5
turnover
)
s
h
o
wed
a
m
in
o
r
p
o
s
itiv
e
c
o
r
r
el
atio
n
b
etwe
e
n
m
ater
ialis
m
,
A
tot
an
d
ca
teg
o
r
y
s
im
ilar
ity
with
tim
e.
Fu
r
th
er
m
o
r
e,
a
m
ar
g
in
ally
n
eg
ativ
e
a
s
s
o
ciatio
n
with
th
e
av
er
ag
e
t
r
an
s
ac
tio
n
co
s
t (
A
avg
).
‒
Self
-
co
n
tr
o
l
:
in
d
iv
id
u
als
with
h
ig
h
e
r
s
elf
-
co
n
tr
o
l
s
co
r
es
ten
d
ed
to
ex
h
ib
it
h
ig
h
er
av
er
a
g
e
s
p
en
d
in
g
p
e
r
tr
an
s
ac
tio
n
(
A
avg
)
an
d
d
em
o
n
s
tr
ated
g
r
ea
ter
v
ar
iatio
n
in
th
eir
wee
k
ly
s
p
en
d
in
g
p
atter
n
s
(
C
persistence
).
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
Hu
ma
n
s
’
p
s
yc
h
o
lo
g
ica
l tra
its
cla
s
s
ifica
tio
n
fr
o
m
th
eir
…
(
A
r
p
ith
a
C
h
ikka
ma
g
a
lu
r
u
N
a
r
a
s
imh
e
Go
w
d
a
)
4557
2
.
5
.
2
.
Ca
t
eg
o
ry
pro
f
ile
f
ea
t
u
re
s
v
s
.
ind
iv
id
ua
l t
ra
it
s
T
h
is
s
ec
tio
n
an
aly
ze
s
h
o
w
ca
t
eg
o
r
y
p
r
o
f
ile
f
ea
tu
r
es r
elate
to
in
d
iv
id
u
al
p
er
s
o
n
ality
tr
aits
:
‒
E
x
t
r
a
v
e
r
s
i
o
n
:
s
p
e
n
d
i
n
g
i
n
c
a
t
e
g
o
r
i
e
s
s
u
c
h
a
s
t
r
a
n
s
p
o
r
t
a
t
i
o
n
,
f
o
o
d
,
d
r
i
n
k
,
a
n
d
g
o
i
n
g
o
u
t
w
a
s
p
o
s
i
t
i
v
e
l
y
a
s
s
o
c
i
a
t
e
d
w
i
t
h
e
x
t
r
a
v
e
r
s
i
o
n
,
w
h
e
r
e
a
s
e
x
p
e
n
d
i
t
u
r
e
s
o
n
g
r
o
c
e
r
i
e
s
a
n
d
s
u
p
e
r
m
a
r
k
e
t
s
s
h
o
w
e
d
a
n
e
g
a
t
i
v
e
c
o
r
r
e
l
a
t
i
o
n
.
‒
A
g
r
e
e
a
b
l
e
n
e
s
s
:
i
n
d
i
v
i
d
u
a
l
s
w
i
t
h
h
i
g
h
e
r
a
g
r
e
e
a
b
l
e
n
e
s
s
s
c
o
r
e
s
t
e
n
d
e
d
t
o
s
p
e
n
d
s
l
i
g
h
t
l
y
m
o
r
e
o
n
c
h
a
r
i
t
a
b
l
e
d
o
n
a
t
i
o
n
s
,
w
h
i
l
e
e
x
h
i
b
i
t
i
n
g
a
n
e
g
a
t
i
v
e
a
s
s
o
c
i
a
t
i
o
n
w
i
t
h
s
p
e
n
d
i
n
g
i
n
t
h
e
c
a
t
e
g
o
r
i
e
s
o
f
f
o
o
d
,
a
n
d
g
o
i
n
g
o
u
t
.
‒
C
o
n
s
cien
tio
u
s
n
ess
:
in
d
iv
id
u
als
with
h
ig
h
co
n
s
cien
tio
u
s
n
es
s
s
co
r
es
ty
p
ically
allo
ca
te
m
o
r
e
s
p
en
d
in
g
to
war
d
h
ea
lth
ca
r
e
an
d
less
to
war
d
g
am
es a
n
d
g
am
in
g
.
‒
Neu
r
o
ticis
m
:
th
e
n
eu
r
o
ticis
m
was
p
o
s
itiv
ely
ass
o
ciate
d
w
ith
s
p
en
d
in
g
o
n
p
er
s
o
n
al
ca
r
e
an
d
b
ea
u
ty
,
wh
er
ea
s
ex
p
en
d
it
u
r
es o
n
i
n
n
o
v
ativ
e
ac
tiv
ities
s
h
o
wed
a
n
eg
ativ
e
ass
o
ciatio
n
.
‒
Op
en
n
ess
to
ex
p
er
ien
ce
:
t
h
is
tr
ait
s
h
o
wed
a
p
o
s
itiv
e
c
o
r
r
elat
io
n
with
s
p
en
d
in
g
o
n
alco
h
o
l a
n
d
a
n
eg
ativ
e
co
r
r
elatio
n
with
h
o
u
s
eh
o
l
d
-
r
el
ated
ex
p
en
d
itu
r
es.
‒
Ma
ter
ialis
m
:
in
d
iv
id
u
als
with
h
ig
h
er
m
ate
r
ialis
m
s
co
r
es
ten
d
to
s
p
en
d
less
o
n
p
o
s
tag
e
an
d
s
h
ip
p
in
g
,
as
well
as in
th
e
ch
ar
ities
ca
teg
o
r
y
,
in
co
n
tr
ast to
in
d
iv
i
d
u
als with
lo
wer
s
co
r
es.
‒
Self
-
co
n
tr
o
l:
a
n
in
v
er
s
e
c
o
r
r
e
latio
n
was
id
en
tifie
d
b
etwe
en
s
elf
-
co
n
tr
o
l
with
s
p
e
n
d
in
g
i
n
th
e
m
o
b
ile
ca
teg
o
r
y
,
wh
ile
s
h
o
win
g
p
o
s
itiv
e
co
r
r
elatio
n
s
with
ex
p
en
d
it
u
r
es
o
n
g
r
o
ce
r
ies
an
d
s
u
p
er
m
ar
k
ets,
as
well
as g
as a
n
d
elec
tr
icity
.
2
.
6
.
I
nfe
rr
ing
ind
iv
idu
a
l per
s
o
na
lity
t
ra
it
s
f
ro
m
s
pend
in
g
pa
t
t
er
ns
us
ing
M
L
a
lg
o
rit
hm
s
A
p
e
r
c
e
n
t
i
l
e
-
b
a
s
e
d
c
l
a
s
s
i
f
i
c
a
t
i
o
n
a
p
p
r
o
a
c
h
w
a
s
u
s
e
d
t
o
a
s
s
i
g
n
i
n
d
i
v
i
d
u
a
l
s
i
n
t
o
l
o
w
,
m
e
d
i
u
m
,
o
r
h
i
g
h
l
e
v
e
l
s
f
o
r
e
a
c
h
o
f
t
h
e
t
r
a
i
t
s
.
T
h
i
s
c
a
t
e
g
o
r
i
z
a
t
i
o
n
w
a
s
d
r
i
v
e
n
b
y
a
n
a
l
y
z
i
n
g
b
e
h
a
v
i
o
r
a
l
i
n
d
i
c
a
t
o
r
s
s
u
c
h
a
s
o
v
e
r
a
l
l
t
r
a
n
s
a
c
t
i
o
n
c
o
u
n
t
,
a
v
e
r
a
g
e
s
p
e
n
d
i
n
g
,
c
a
t
e
g
o
r
y
d
i
v
e
r
s
i
t
y
,
a
n
d
t
e
m
p
o
r
a
l
p
a
t
t
e
r
n
s
.
S
i
n
c
e
t
h
e
d
a
t
a
s
e
t
d
i
d
n
o
t
i
n
c
l
u
d
e
v
a
l
i
d
a
t
e
d
p
s
y
c
h
o
m
e
t
r
i
c
t
e
s
t
s
c
o
r
e
s
,
t
h
i
s
m
e
t
h
o
d
s
e
r
v
e
d
a
s
a
r
e
l
i
a
b
l
e
b
e
h
a
v
i
o
r
a
l
p
r
o
x
y
,
a
s
s
u
p
p
o
r
t
e
d
b
y
p
r
i
o
r
b
e
h
a
v
i
o
r
a
l
p
s
y
c
h
o
l
o
g
y
r
e
s
e
a
r
c
h
[
1
0
]
,
[
1
5
]
,
[
1
6
]
.
I
n
d
i
v
i
d
u
a
l
s
w
e
r
e
g
r
o
u
p
e
d
u
s
i
n
g
t
h
e
3
3
r
d
a
n
d
6
6
t
h
p
e
r
c
e
n
t
i
l
e
s
o
f
f
e
a
t
u
r
e
d
i
s
t
r
i
b
u
t
i
o
n
s
,
w
h
i
c
h
p
r
o
v
i
d
e
d
a
r
e
l
a
t
i
v
e
p
o
s
i
t
i
o
n
i
n
g
w
i
t
h
i
n
t
h
e
p
o
p
u
l
a
t
i
o
n
a
n
d
e
n
a
b
l
e
d
e
f
f
e
c
t
i
v
e
m
a
p
p
i
n
g
o
f
r
e
a
l
-
w
o
r
l
d
f
i
n
a
n
c
i
a
l
a
c
t
i
v
i
t
y
t
o
p
s
y
c
h
o
l
o
g
i
c
a
l
p
r
o
f
i
l
e
s
.
T
h
e
r
e
s
u
l
t
i
n
g
l
a
b
e
l
e
d
d
a
t
a
s
e
t
w
a
s
t
h
e
n
u
s
e
d
f
o
r
t
r
a
i
n
i
n
g
a
n
d
e
v
a
l
u
a
t
i
o
n
u
s
i
n
g
b
o
t
h
M
L
a
n
d
D
L
a
l
g
o
r
i
t
h
m
s
.
T
h
e
e
v
a
l
u
a
t
e
d
r
e
s
u
l
t
s
a
r
e
o
b
t
a
i
n
e
d
f
r
o
m
f
o
u
r
d
i
f
f
e
r
e
n
t
ML
a
l
g
o
r
i
t
h
m
:
L
R
,
R
F
,
D
T
,
a
n
d
S
V
M
.
F
o
r
e
v
e
r
y
m
e
t
h
o
d
,
2
0
%
o
f
t
h
e
d
a
t
a
s
e
t
i
s
u
s
e
d
f
o
r
t
e
s
t
i
n
g
,
w
h
i
l
e
8
0
%
i
s
u
s
e
d
f
o
r
t
r
a
i
n
i
n
g
b
y
r
e
t
a
i
n
i
n
g
t
h
e
i
n
d
i
v
i
d
u
a
l
p
e
r
s
o
n
a
l
i
t
y
t
r
a
i
t
r
a
t
i
o
o
f
c
o
u
r
s
e
s
i
n
b
o
t
h
t
e
s
t
i
n
g
a
n
d
t
r
a
i
n
i
n
g
s
e
t
s
[
2
3
]
–
[
2
6
]
.
T
o
a
d
d
r
e
s
s
p
o
t
e
n
t
i
a
l
o
v
e
r
f
i
t
t
i
n
g
,
t
h
e
DT
a
n
d
RF
m
o
d
e
l
s
w
e
r
e
t
r
a
i
n
e
d
u
s
i
n
g
1
0
-
f
o
l
d
c
r
o
s
s
-
v
a
l
i
d
a
t
i
o
n
a
n
d
p
r
u
n
i
n
g
t
o
e
n
s
u
r
e
g
e
n
e
r
a
l
i
z
a
b
l
e
p
e
r
f
o
r
m
a
n
c
e
.
2
.
7
.
CNN
a
rc
hite
ct
ure
a
nd
t
ra
ini
ng
co
nfig
ura
t
io
n
T
h
e
C
NN
m
o
d
e
l
w
as
c
u
s
t
o
m
-
d
e
s
i
g
n
e
d
a
n
d
i
m
p
le
m
e
n
t
e
d
to
c
a
p
t
u
r
e
c
o
m
p
l
e
x
p
at
t
e
r
n
s
in
s
p
e
n
d
i
n
g
b
e
h
a
v
i
o
r
f
o
r
p
e
r
s
o
n
a
l
i
t
y
t
r
a
i
t
c
l
a
s
s
i
f
i
c
at
i
o
n
.
A
l
t
h
o
u
g
h
t
h
e
d
a
t
a
s
e
t
i
s
o
f
m
o
d
e
r
a
t
e
s
i
z
e
,
t
h
e
h
i
g
h
d
i
m
e
n
s
i
o
n
a
li
t
y
a
n
d
s
t
r
u
c
t
u
r
e
d
n
a
t
u
r
e
o
f
t
h
e
e
x
t
r
a
c
t
e
d
b
e
h
a
v
i
o
r
a
l
f
e
a
t
u
r
e
s
m
a
k
e
C
N
N
s
a
s
u
it
a
b
l
e
c
h
o
i
c
e
.
T
h
e
a
r
c
h
i
t
e
c
t
u
r
e
c
o
m
p
r
i
s
ed
t
w
o
1
D
c
o
n
v
o
l
u
t
i
o
n
a
l
l
a
y
e
r
s
w
it
h
6
4
a
n
d
1
2
8
f
i
l
t
e
r
s
r
e
s
p
ec
t
i
v
ely
,
e
a
c
h
u
s
i
n
g
a
k
e
r
n
e
l
s
i
z
e
o
f
3
a
n
d
r
e
c
t
i
f
i
e
d
l
i
n
e
a
r
u
n
i
t
(
R
e
L
U
)
a
ct
i
v
a
ti
o
n
,
f
o
l
l
o
w
e
d
b
y
a
M
a
x
P
o
o
l
i
n
g
l
a
y
e
r
t
o
r
e
d
u
c
e
d
i
m
e
n
s
i
o
n
a
l
i
t
y
.
T
h
e
f
e
a
t
u
r
e
m
a
p
s
w
e
r
e
c
o
n
v
e
r
t
e
d
i
n
t
o
a
1D
v
e
c
t
o
r
u
s
i
n
g
a
f
l
a
t
t
e
n
l
a
y
e
r
,
a
n
d
t
h
e
n
s
e
n
t
to
a
f
u
l
l
y
l
i
n
k
e
d
d
e
n
s
e
l
a
y
e
r
m
ad
e
u
p
o
f
1
2
8
n
e
u
r
o
n
s
t
h
a
t
w
e
r
e
a
c
t
i
v
at
e
d
b
y
R
e
L
U
.
A
d
r
o
p
o
u
t
l
a
y
e
r
w
i
t
h
a
r
a
t
e
o
f
0
.
3
w
a
s
a
d
d
e
d
t
o
r
e
d
u
c
e
o
v
e
r
f
i
t
t
i
n
g
.
T
h
e
f
i
n
a
l
c
l
a
s
s
i
f
ic
a
t
i
o
n
w
as
c
a
r
r
i
e
d
o
u
t
u
s
i
n
g
a
S
o
f
t
M
a
x
o
u
t
p
u
t
l
a
y
e
r
,
e
n
a
b
l
i
n
g
m
u
l
t
i
-
c
l
ass
p
r
e
d
i
c
t
i
o
n
a
c
r
o
s
s
t
h
r
e
e
p
e
r
s
o
n
a
l
i
t
y
t
r
ai
t
le
v
e
l
s
:
l
o
w
,
m
e
d
i
u
m
,
a
n
d
h
i
g
h
.
W
i
t
h
a
l
ea
r
n
i
n
g
r
a
t
e
o
f
0
.
0
0
1
,
t
h
e
A
d
a
m
m
e
t
h
o
d
w
a
s
u
s
e
d
t
o
o
p
t
i
m
i
z
e
t
h
e
m
o
d
e
l
,
a
n
d
c
at
e
g
o
r
i
c
a
l
c
r
o
s
s
-
e
n
t
r
o
p
y
wa
s
u
s
e
d
as
t
h
e
l
o
s
s
f
u
n
c
ti
o
n
.
T
r
a
i
n
i
n
g
w
as
c
a
r
r
i
e
d
o
u
t
u
s
i
n
g
a
b
a
t
c
h
s
i
z
e
o
f
3
2
o
v
e
r
2
0
e
p
o
c
h
s
.
2
0
%
o
f
t
h
e
d
a
t
a
s
e
t
w
as
u
s
e
d
f
o
r
t
e
s
t
i
n
g
,
a
n
d
t
h
e
r
e
m
a
i
n
i
n
g
8
0
%
w
a
s
u
s
e
d
f
o
r
t
r
a
i
n
i
n
g
a
n
d
p
e
r
f
o
r
m
a
n
c
e
e
v
a
lu
a
t
i
o
n
w
a
s
b
as
e
d
o
n
a
c
c
u
r
a
c
y
a
n
d
l
o
s
s
o
b
s
e
r
v
e
d
o
n
t
h
e
v
a
l
i
d
a
t
i
o
n
d
a
t
a
.
Al
l
h
y
p
e
r
p
a
r
a
m
e
t
e
r
s
w
e
r
e
s
e
l
e
ct
e
d
b
a
s
e
d
o
n
e
m
p
i
r
i
c
a
l
e
x
p
e
r
i
m
e
n
t
a
ti
o
n
a
n
d
t
u
n
e
d
f
o
r
o
p
t
i
m
a
l
p
er
f
o
r
m
a
n
c
e
w
i
t
h
t
h
e
a
v
a
i
l
a
b
l
e
d
a
t
as
e
t
.
T
a
b
l
e
3
l
i
s
t
s
t
h
e
k
e
y
h
y
p
e
r
p
a
r
a
m
e
t
e
r
s
u
s
e
d
d
u
r
i
n
g
t
r
a
i
n
i
n
g
.
T
o
m
i
n
i
m
i
z
e
o
v
e
r
f
i
t
t
i
n
g
,
d
r
o
p
o
u
t
r
e
g
u
l
a
r
i
z
a
t
i
o
n
w
a
s
a
p
p
l
i
e
d
,
a
n
d
m
o
d
e
l
t
r
a
i
n
i
n
g
w
as
li
m
i
te
d
t
o
2
0
e
p
o
c
h
s
b
a
s
e
d
o
n
e
a
r
l
y
c
o
n
v
e
r
g
e
n
c
e
.
V
a
l
i
d
at
i
o
n
p
e
r
f
o
r
m
a
n
c
e
w
a
s
c
o
n
s
is
t
e
n
tl
y
m
o
n
i
t
o
r
e
d
,
a
n
d
t
h
e
t
r
a
i
n
i
n
g
a
n
d
v
a
l
i
d
a
t
i
o
n
c
u
r
v
es
s
h
o
w
s
n
o
s
i
g
n
i
f
i
c
a
n
t
d
i
v
e
r
g
e
n
c
e
,
c
o
n
f
i
r
m
i
n
g
t
h
a
t
t
h
e
m
o
d
e
l
g
e
n
er
a
l
i
z
e
d
w
el
l
.
S
t
r
i
ct
t
r
a
i
n
-
te
s
t
s
ep
a
r
a
t
i
o
n
e
n
s
u
r
e
d
t
h
a
t
n
o
d
a
t
a
l
ea
k
a
g
e
o
c
c
u
r
r
e
d
.
T
ab
le
3
.
Key
h
y
p
e
r
p
ar
am
ete
r
s
u
s
ed
d
u
r
i
n
g
tr
ain
i
n
g
H
y
p
e
r
p
a
r
a
me
t
e
r
V
a
l
u
e
O
p
t
i
mi
z
e
r
A
d
a
m
Le
a
r
n
i
n
g
r
a
t
e
0
.
0
0
1
Lo
ss f
u
n
c
t
i
o
n
C
a
t
e
g
o
r
i
c
a
l
c
r
o
ss
-
e
n
t
r
o
p
y
A
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
s
R
e
LU
(
h
i
d
d
e
n
)
,
S
o
f
t
M
a
x
(
o
u
t
p
u
t
)
Ep
o
c
h
s
20
B
a
t
c
h
si
z
e
32
D
r
o
p
o
u
t
r
a
t
e
0
.
3
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
4
,
No
.
6
,
Dec
em
b
er
2
0
2
5
:
4
5
5
2
-
4
5
6
4
4558
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
s
ec
tio
n
p
r
esen
ts
th
e
r
es
u
lts
o
f
th
e
co
r
r
elatio
n
an
al
y
s
is
an
d
m
o
d
el
ac
cu
r
ac
y
in
c
lass
if
y
in
g
p
s
y
ch
o
lo
g
ical
tr
aits
f
r
o
m
s
p
e
n
d
in
g
p
atter
n
s
.
As
s
h
o
wn
in
s
ub
-
s
ec
tio
n
s
2
.
5
.
1
an
d
2
.
5
.
2
,
th
e
f
in
d
in
g
s
r
ev
ea
l
co
r
r
elatio
n
s
am
o
n
g
o
v
er
all
f
,
c
ateg
o
r
y
-
r
elate
d
f
ea
tu
r
es
,
an
d
c
ateg
o
r
y
p
r
o
f
ile
c
h
ar
ac
ter
is
tics
.
3
.
1
.
P
er
f
o
r
m
a
nce
ev
a
lua
t
io
n o
f
ma
chine le
a
rning
a
lg
o
rit
hm
s
T
a
b
le
4
r
e
p
r
ese
n
ts
t
h
e
p
e
r
f
o
r
m
an
ce
o
f
ML
al
g
o
r
it
h
m
s
f
o
r
L
R
,
D
T
,
SV
M,
a
n
d
R
F.
T
h
e
p
r
e
cis
io
n
,
r
e
ca
l
l,
F1
-
s
c
o
r
e
,
an
d
a
cc
u
r
ac
y
m
e
asu
r
es
a
r
e
u
s
e
d
t
o
ass
ess
t
h
e
m
o
d
el'
s
p
e
r
f
o
r
m
an
ce
[
2
7
]
,
[
2
8
]
.
T
h
e
r
esu
lts
p
r
ese
n
t
p
e
r
f
o
r
m
a
n
c
e
m
e
asu
r
es
(
p
r
ec
is
io
n
,
r
e
ca
l
l,
a
n
d
F
1
-
s
c
o
r
e
)
f
o
r
m
u
lti
p
l
e
p
s
y
c
h
o
l
o
g
ic
al
tr
aits
e
v
al
u
ate
d
u
s
in
g
L
R
,
DT
,
S
VM
,
a
n
d
R
F.
B
o
t
h
DT
an
d
R
F
c
o
n
s
is
t
e
n
tl
y
a
ch
ie
v
e
d
p
e
r
f
ec
t
s
c
o
r
es
(
1
.
0
0
)
ac
r
o
s
s
m
o
s
t
t
r
a
its
,
r
ef
lec
ti
n
g
s
tr
o
n
g
p
r
e
d
i
cti
v
e
c
ap
a
b
ili
ty
.
I
n
co
n
t
r
as
t,
L
R
ex
h
i
b
i
te
d
g
r
ea
te
r
v
a
r
i
ab
ilit
y
,
wi
th
c
o
m
p
ar
ati
v
el
y
lo
we
r
p
e
r
f
o
r
m
a
n
c
e
f
o
r
t
r
ai
ts
s
u
c
h
as
o
p
en
n
ess
an
d
n
e
u
r
o
tic
is
m
.
T
r
aits
i
n
cl
u
d
in
g
m
at
er
ial
is
m
a
n
d
s
el
f
-
c
o
n
tr
o
l
y
i
eld
e
d
h
i
g
h
p
r
e
cisi
o
n
an
d
F
1
-
s
co
r
es,
p
a
r
ti
c
u
la
r
l
y
w
h
e
n
m
o
d
e
le
d
wit
h
m
o
r
e
c
o
m
p
le
x
al
g
o
r
it
h
m
s
.
T
h
ese
f
i
n
d
i
n
g
s
,
s
u
m
m
ar
i
ze
d
i
n
Fig
u
r
e
3
,
r
ep
r
es
en
ts
th
e
p
er
f
o
r
m
a
n
c
e
o
f
ML
m
o
d
els
i
n
i
d
e
n
ti
f
y
in
g
p
s
y
ch
o
l
o
g
i
ca
l
t
r
ai
ts
.
T
ab
le
4
.
Per
f
o
r
m
an
ce
m
ea
s
u
r
e
s
o
f
class
if
icatio
n
m
o
d
els
P
sy
c
h
o
l
o
g
i
c
a
l
t
r
a
i
t
M
o
d
e
l
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
sc
o
r
e
O
p
e
n
n
e
ss
LR
0
.
6
8
0
.
7
5
0
.
6
4
DT
1
.
0
0
1
.
0
0
1
.
0
0
S
V
M
0
.
9
0
0
.
9
2
0
.
8
5
RF
1
.
0
0
1
.
0
0
1
.
0
0
C
o
n
sc
i
e
n
t
i
o
u
s
n
e
ss
LR
0
.
6
9
0
.
6
5
0
.
6
7
DT
1
.
0
0
1
.
0
0
1
.
0
0
S
V
M
0
.
9
1
0
.
8
0
0
.
8
5
RF
1
.
0
0
1
.
0
0
1
.
0
0
Ex
t
r
a
v
e
r
si
o
n
LR
0
.
7
4
0
.
8
6
0
.
7
9
DT
1
.
0
0
1
.
0
0
1
.
0
0
S
V
M
0
.
8
6
0
.
6
4
0
.
7
3
RF
1
.
0
0
1
.
0
0
1
.
0
0
A
g
r
e
e
a
b
l
e
n
e
ss
LR
0
.
8
4
0
.
6
4
0
.
7
4
DT
1
.
0
0
1
.
0
0
1
.
0
0
S
V
M
0
.
9
7
1
.
0
0
0
.
9
9
RF
1
.
0
0
1
.
0
0
1
.
0
0
N
e
u
r
o
t
i
c
i
sm
LR
1
.
0
0
0
.
3
1
0
.
4
7
DT
1
.
0
0
1
.
0
0
1
.
0
0
S
V
M
0
.
9
2
0
.
9
2
0
.
9
2
RF
1
.
0
0
1
.
0
0
1
.
0
0
S
e
l
f
-
c
o
n
t
r
o
l
LR
0
.
7
1
1
.
0
0
0
.
8
3
DT
1
.
0
0
1
.
0
0
1
.
0
0
S
V
M
0
.
5
3
0
.
9
0
0
.
6
7
RF
1
.
0
0
1
.
0
0
1
.
0
0
M
a
t
e
r
i
a
l
i
sm
LR
1
.
0
0
0
.
9
1
0
.
9
5
DT
1
.
0
0
1
.
0
0
1
.
0
0
S
V
M
0
.
8
9
0
.
7
3
0
.
8
0
RF
1
.
0
0
1
.
0
0
1
.
0
0
C
o
m
p
a
r
a
t
i
v
e
a
n
al
y
s
i
s
o
f
c
la
s
s
if
i
c
a
t
i
o
n
m
o
d
e
ls
a
c
r
o
s
s
t
h
e
p
e
r
f
o
r
m
a
n
c
e
m
e
a
s
u
r
e
s
i
s
s
h
o
w
n
i
n
F
i
g
u
r
e
3
.
F
o
r
o
p
e
n
n
e
s
s
(
Fi
g
u
r
e
3
(
a
)
)
,
b
o
t
h
R
F
a
n
d
D
T
m
o
d
e
l
s
r
e
a
c
h
e
d
p
e
r
f
e
c
t
a
c
c
u
r
a
c
y
,
w
h
i
l
e
t
h
e
SV
M
al
s
o
p
e
r
f
o
r
m
e
d
w
e
l
l
w
it
h
a
n
F
1
-
s
c
o
r
e
o
f
0
.
8
5
.
L
R
,
h
o
w
e
v
e
r
,
s
t
r
u
g
g
l
e
d
t
o
c
a
p
t
u
r
e
t
h
e
c
o
m
p
l
e
x
i
t
y
o
f
t
h
e
d
a
t
a
.
A
s
i
m
i
la
r
t
r
e
n
d
a
p
p
e
a
r
e
d
f
o
r
c
o
n
s
c
i
e
n
t
i
o
u
s
n
ess
(
F
i
g
u
r
e
3
(
b
)
)
,
w
h
e
r
e
e
n
s
e
m
b
l
e
m
o
d
e
l
s
c
l
e
a
r
l
y
o
u
t
p
e
r
f
o
r
m
e
d
t
h
e
s
i
m
p
l
e
r
l
i
n
e
a
r
a
p
p
r
o
a
c
h
.
I
n
t
h
e
c
a
s
e
o
f
e
x
t
r
a
v
e
r
s
i
o
n
(
F
i
g
u
r
e
3
(
c
)
)
,
R
F
a
n
d
D
T
o
n
c
e
a
g
a
i
n
c
l
a
s
s
i
f
i
e
d
f
l
aw
l
ess
l
y
,
S
V
M
a
c
h
ie
v
e
d
a
m
o
d
e
r
a
t
e
s
c
o
r
e
o
f
0
.
7
3
,
a
n
d
L
R
s
h
o
we
d
s
li
g
h
t
l
y
b
e
t
te
r
p
e
r
f
o
r
m
a
n
c
e
a
t
0
.
7
9
.
F
o
r
a
g
r
e
e
a
b
l
e
n
es
s
(
F
i
g
u
r
e
3
(
d
)
)
,
R
F
a
n
d
D
T
m
a
i
n
t
a
i
n
e
d
p
e
r
f
e
ct
r
e
s
u
l
t
s
,
b
u
t
S
V
M
p
e
r
f
o
r
m
e
d
i
m
p
r
e
s
s
i
v
e
l
y
c
l
o
s
e
t
o
t
h
e
m
wi
t
h
an
F
1
-
s
c
o
r
e
o
f
0
.
9
9
,
w
h
i
l
e
L
R
r
e
m
a
i
n
e
d
w
e
a
k
e
r
.
T
h
e
p
a
t
t
e
r
n
c
o
n
t
i
n
u
e
d
f
o
r
n
e
u
r
o
t
i
c
is
m
(
F
i
g
u
r
e
3
(
e
)
)
,
w
h
e
r
e
R
F
a
n
d
D
T
d
e
l
i
v
e
r
e
d
p
e
r
f
e
c
t
a
c
c
u
r
a
c
y
,
S
V
M
p
e
r
f
o
r
m
e
d
s
t
r
o
n
g
l
y
(
F
1
=
0
.
9
2
)
,
b
u
t
L
R
f
e
ll
s
h
o
r
t
w
i
t
h
o
n
l
y
0
.
4
7
.
F
o
r
s
e
l
f
-
c
o
n
t
r
o
l
(
F
i
g
u
r
e
3
(
f
)
)
,
e
n
s
e
m
b
l
e
m
e
t
h
o
d
s
d
o
m
i
n
a
t
e
d
,
t
h
o
u
g
h
L
R
s
h
o
w
e
d
f
a
i
r
l
y
g
o
o
d
r
e
s
u
l
t
s
(
F
1
=
0
.
8
3
)
,
o
u
t
p
e
r
f
o
r
m
i
n
g
S
V
M
,
w
h
i
c
h
a
c
h
i
e
v
e
d
0
.
6
7
.
L
as
t
l
y
,
f
o
r
m
a
t
e
r
i
a
l
is
m
(
F
i
g
u
r
e
3
(
g
)
)
,
R
F
a
n
d
D
T
a
g
ai
n
p
r
o
v
i
d
e
d
f
l
a
w
l
es
s
p
r
e
d
i
c
ti
o
n
s
,
b
u
t
i
n
t
e
r
es
t
i
n
g
l
y
,
L
R
p
e
r
f
o
r
m
ed
v
e
r
y
w
e
l
l
(
F
1
=
0
.
9
5
)
,
e
v
e
n
s
u
r
p
a
s
s
i
n
g
S
V
M
a
t
0
.
8
0
.
T
a
k
e
n
to
g
e
t
h
e
r
,
t
h
e
s
e
r
e
s
u
lt
s
s
h
o
w
t
h
a
t
e
n
s
e
m
b
l
e
m
e
t
h
o
d
s
s
u
c
h
a
s
R
F
a
n
d
D
T
c
o
n
s
i
s
t
e
n
t
l
y
d
e
l
i
v
e
r
e
d
t
h
e
s
t
r
o
n
g
e
s
t
o
u
tc
o
m
e
s
,
w
h
i
le
S
VM
o
f
f
e
r
e
d
b
a
l
a
n
c
e
d
g
e
n
e
r
a
l
i
z
at
i
o
n
,
a
n
d
L
R
p
r
o
v
e
d
u
n
e
x
p
e
c
t
e
d
l
y
e
f
f
e
c
t
i
v
e
f
o
r
s
p
e
ci
f
i
c
t
r
ai
ts
l
i
k
e
m
a
t
e
r
i
a
li
s
m
.
As
in
d
icate
d
in
T
ab
le
5
,
th
e
class
if
icatio
n
ac
cu
r
ac
y
r
esu
lts
r
ep
r
esen
t
th
at
R
F
an
d
DT
em
er
g
ed
as
th
e
b
est
-
p
er
f
o
r
m
in
g
m
o
d
els,
ac
h
i
ev
in
g
p
er
f
ec
t
ac
cu
r
ac
y
(
1
0
0
%)
an
d
ex
ce
llen
t
class
if
icatio
n
s
co
r
es.
SVM
o
f
f
er
s
g
o
o
d
p
er
f
o
r
m
a
n
ce
with
a
n
8
1
.
5
%
ac
cu
r
ac
y
.
L
R
p
er
f
o
r
m
s
with
a
7
6
%
ac
cu
r
ac
y
.
T
o
e
n
s
u
r
e
r
o
b
u
s
tn
ess
,
a
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
Hu
ma
n
s
’
p
s
yc
h
o
lo
g
ica
l tra
its
cla
s
s
ifica
tio
n
fr
o
m
th
eir
…
(
A
r
p
ith
a
C
h
ikka
ma
g
a
lu
r
u
N
a
r
a
s
imh
e
Go
w
d
a
)
4559
s
tr
atif
ied
1
0
-
f
o
ld
cr
o
s
s
-
v
alid
a
tio
n
p
r
o
ce
d
u
r
e
was
em
p
lo
y
e
d
,
an
d
th
e
m
o
d
el’
s
p
e
r
f
o
r
m
a
n
ce
is
r
ep
o
r
ted
as
m
ea
n
±
s
tan
d
ar
d
d
e
v
iatio
n
ac
r
o
s
s
f
o
ld
s
.
R
F
an
d
DT
o
b
ta
in
ed
ac
cu
r
ac
ies
o
f
0
.
9
9
±
0
.
0
1
an
d
0
.
9
8
±
0
.
0
2
,
r
esp
ec
tiv
ely
,
wh
ile
SVM
a
n
d
L
R
y
ield
ed
0
.
8
2
±
0
.
0
3
an
d
0
.
7
5
±
0
.
0
4
.
T
h
ese
r
esu
lts
in
d
ic
ate
th
at
th
e
s
tr
o
n
g
p
er
f
o
r
m
an
ce
o
f
tr
ee
-
b
ased
m
o
d
els
r
ef
lects
s
tab
le
g
en
er
aliza
ti
o
n
r
ath
er
th
an
o
v
er
f
itti
n
g
.
Fu
tu
r
e
wo
r
k
will
ap
p
ly
p
r
u
n
in
g
,
r
e
g
u
lar
izatio
n
,
an
d
e
v
alu
atio
n
o
n
lar
g
e
r
d
atasets
to
f
u
r
th
er
v
alid
ate
tr
ee
-
b
ased
p
er
f
o
r
m
a
n
ce
.
(
a)
(
b
)
(
c)
(
d
)
(
e)
(f)
(
g
)
Fig
u
r
e
3
.
C
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
s
is
o
f
c
l
as
s
i
f
i
c
a
ti
o
n
m
o
d
e
l
s
a
c
r
o
s
s
t
h
e
p
e
r
f
o
r
m
a
n
c
e
m
e
as
u
r
e
s
f
o
r
(
a
)
o
p
e
n
n
e
s
s
,
(
b
)
c
o
n
s
c
ie
n
t
i
o
u
s
n
e
s
s
,
(
c
)
e
x
t
r
a
v
e
r
s
i
o
n
,
(
d
)
a
g
r
e
ea
b
l
e
n
e
s
s
,
(
e
)
n
e
u
r
o
t
i
c
is
m
,
(
f
)
s
el
f
-
c
o
n
t
r
o
l
,
a
n
d
(
g
)
m
a
t
e
r
i
a
l
is
m
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
4
,
No
.
6
,
Dec
em
b
er
2
0
2
5
:
4
5
5
2
-
4
5
6
4
4560
T
ab
le
5
.
C
lass
if
icatio
n
alg
o
r
ith
m
s
ac
cu
r
ac
y
r
ep
o
r
t
C
l
a
s
si
f
i
c
a
t
i
o
n
m
o
d
e
l
s
M
a
c
r
o
A
v
e
r
a
g
e
W
e
i
g
h
t
e
d
a
v
e
r
a
g
e
A
c
c
u
r
a
c
y
(
%)
S
V
M
0
.
8
3
0
.
8
2
8
1
.
5
0
RF
1
.
0
0
1
.
0
0
1
0
0
DT
1
.
0
0
1
.
0
0
1
0
0
LR
0
.
7
4
0
.
7
4
76
3
.
2
.
P
er
f
o
r
m
a
nce
ev
a
lua
t
io
n o
f
CNN
m
o
del
T
h
e
tr
ain
in
g
d
ata
an
d
test
in
g
d
ata
ar
e
f
ed
in
to
th
e
C
NN
s
tr
u
ctu
r
e
co
n
s
tr
u
cted
.
W
ith
2
0
e
p
o
ch
s
,
th
e
m
o
d
el
r
ea
ch
ed
9
9
.
0
3
%
ac
cu
r
a
cy
as
s
h
o
wn
in
Fig
u
r
e
4
.
Fig
u
r
e
4
s
h
o
ws
th
e
tr
ain
in
g
p
r
o
g
r
ess
o
f
th
e
im
p
lem
en
ted
C
NN
m
o
d
el.
As
s
ee
n
in
Fig
u
r
e
4
(
a)
,
co
n
s
id
er
in
g
b
o
th
tr
ain
i
n
g
an
d
v
alid
atio
n
p
er
f
o
r
m
an
c
e
ac
cu
r
ac
y
in
cr
ea
s
e
s
tead
ily
ac
r
o
s
s
ep
o
c
h
s
,
in
d
icatin
g
ef
f
ec
tiv
e
f
ea
t
u
r
e
lear
n
in
g
.
I
n
Fig
u
r
e
4
(
b
)
,
th
e
d
ec
r
ea
s
in
g
an
d
clo
s
ely
alig
n
ed
lo
s
s
cu
r
v
es
co
n
f
ir
m
s
tab
le
co
n
v
er
g
en
ce
an
d
m
in
im
al
o
v
er
f
itti
n
g
,
v
alid
atin
g
th
e
r
o
b
u
s
t
n
ess
o
f
th
e
C
NN
ar
ch
itectu
r
e.
Alth
o
u
g
h
cr
o
s
s
-
v
alid
atio
n
d
em
o
n
s
tr
ates
s
tr
o
n
g
p
e
r
f
o
r
m
an
ce
,
th
e
a
b
s
en
ce
o
f
ex
ter
n
al
v
alid
atio
n
lim
its
co
n
clu
s
io
n
s
ab
o
u
t
g
en
e
r
aliza
b
ilit
y
.
I
n
f
u
tu
r
e
wo
r
k
,
w
e
p
lan
to
b
en
ch
m
a
r
k
o
n
in
d
e
p
en
d
en
t
d
atasets
o
r
s
im
u
late
d
o
m
ain
s
h
if
t b
y
s
p
litt
in
g
d
ata
ac
r
o
s
s
d
em
o
g
r
a
p
h
ic
o
r
b
eh
av
i
o
r
al
clu
s
ter
s
.
i)
Acc
u
r
ac
y
an
d
lo
s
s
tr
en
d
s
:
th
e
tr
ain
in
g
lo
s
s
in
itially
ex
h
ib
i
ts
a
h
ig
h
v
alu
e
a
n
d
p
r
o
g
r
ess
iv
ely
d
ec
lin
es,
in
d
icatin
g
th
at
t
h
e
m
o
d
el
is
lear
n
in
g
e
f
f
ec
tiv
ely
.
Acc
u
r
ac
y
im
p
r
o
v
es
f
r
o
m
ar
o
u
n
d
3
3
.
6
6
%
in
th
e
f
ir
s
t
ep
o
ch
to
9
9
.
0
3
% in
th
e
f
in
al
e
p
o
ch
,
s
h
o
win
g
ex
ce
llen
t le
a
r
n
i
n
g
p
r
o
g
r
ess
io
n
.
ii)
Valid
atio
n
p
er
f
o
r
m
a
n
ce
:
v
alid
atio
n
lo
s
s
s
h
o
ws
f
l
u
ctu
atio
n
s
b
u
t
g
e
n
er
ally
d
ec
r
ea
s
es,
wh
ic
h
d
em
o
n
s
tr
ates
p
o
s
itiv
e
tr
ain
in
g
p
r
o
g
r
ess
.
Va
lid
atio
n
ac
cu
r
ac
y
s
tar
ts
at
5
2
.
4
2
%
an
d
r
is
es
to
a
p
ea
k
o
f
1
0
0
%
at
th
e
7
th
ep
o
ch
,
i
n
d
icatin
g
th
e
m
o
d
el
’
s
r
o
b
u
s
t g
en
e
r
aliza
tio
n
ca
p
a
b
ilit
y
.
(
a)
(
b
)
Fig
u
r
e
4
.
T
r
ain
in
g
a
n
d
v
alid
atio
n
ac
cu
r
ac
y
o
v
er
ep
o
ch
s
o
f
(
a
)
ac
cu
r
ac
y
o
f
tr
ai
n
in
g
a
n
d
v
ali
d
atio
n
,
an
d
(
b
)
lo
s
s
o
f
tr
ain
i
n
g
an
d
v
alid
at
io
n
3
.
2
.
1
.
Co
nfusi
o
n m
a
t
rix
a
na
l
y
s
is
T
o
f
u
r
th
er
ev
alu
ate
th
e
class
if
icatio
n
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
C
NN
m
o
d
el,
a
co
n
f
u
s
io
n
m
atr
ix
was
g
en
er
ated
as
s
h
o
wn
in
Fig
u
r
e
5
.
T
h
e
m
atr
i
x
h
ig
h
lig
h
ts
th
at
m
o
s
t
s
am
p
les
wer
e
c
o
r
r
ec
tly
class
if
ied
ac
r
o
s
s
all
s
ev
en
p
s
y
ch
o
lo
g
ical
tr
aits
,
wi
th
o
n
ly
m
in
im
al
m
is
class
i
f
ica
tio
n
s
b
etwe
en
clo
s
ely
r
elate
d
ca
teg
o
r
ies
s
u
ch
as
o
p
en
n
ess
an
d
ag
r
ee
a
b
len
ess
.
T
h
e
o
v
e
r
all
class
if
icatio
n
ac
cu
r
ac
y
ac
h
iev
ed
was
9
9
.
0
3
%,
co
n
s
is
ten
t
with
th
e
p
er
f
o
r
m
an
ce
m
etr
ics
r
ep
o
r
ted
ea
r
lier
.
T
h
is
co
n
f
ir
m
s
th
e
m
o
d
el’
s
s
tr
o
n
g
ca
p
a
b
ilit
y
to
d
i
s
cr
im
in
ate
b
etwe
en
p
er
s
o
n
ality
tr
aits
b
ased
o
n
s
p
e
n
d
in
g
b
eh
av
i
o
r
.
3
.
2
.
2
.
RO
C
curv
e
a
nd
AUC
a
na
ly
s
is
R
ec
eiv
er
o
p
er
atin
g
c
h
ar
ac
ter
i
s
tic
(
R
O
C
)
cu
r
v
es
wer
e
g
en
er
ated
f
o
r
all
p
s
y
ch
o
lo
g
ical
tr
ai
ts
,
an
d
th
e
co
r
r
esp
o
n
d
in
g
ar
ea
u
n
d
er
th
e
c
u
r
v
e
(
AUC)
s
co
r
es
ar
e
s
h
o
wn
in
Fig
u
r
e
6
.
R
OC
f
o
r
o
p
en
n
ess
(
Fig
u
r
e
6
(
a)
)
,
R
OC
f
o
r
co
n
s
cien
tio
u
s
n
ess
(
Fig
u
r
e
6
(
b
)
)
,
R
OC
f
o
r
ex
tr
av
er
s
io
n
(
Fig
u
r
e
6
(
c)
)
,
R
OC
f
o
r
ag
r
ee
ab
le
n
ess
(
Fig
u
r
e
6
(
d
)
)
,
R
OC
f
o
r
n
eu
r
o
ticis
m
(
Fig
u
r
e
6
(
e)
)
,
R
OC
f
o
r
m
ater
ialis
m
(
Fig
u
r
e
6
(
f
)
)
,
a
n
d
R
OC
f
o
r
s
elf
-
co
n
tr
o
l
(
Fig
u
r
e
6
(
g
)
)
.
T
h
e
C
NN
m
o
d
el
ac
h
iev
e
d
v
e
r
y
h
ig
h
d
is
cr
im
in
atio
n
,
with
AUC
v
alu
es
th
at
r
an
g
e
f
r
o
m
0
.
9
9
3
to
0
.
9
9
5
ac
r
o
s
s
tr
aits
.
T
h
ese
n
ea
r
-
p
er
f
ec
t sco
r
es c
o
n
f
ir
m
th
e
m
o
d
el’
s
ca
p
a
b
i
lity
to
ac
cu
r
ately
class
if
y
p
er
s
o
n
ality
tr
aits
.
T
h
e
R
OC
cu
r
v
e
p
lo
ts
th
e
tr
u
e
p
o
s
itiv
e
r
ate
(
T
PR
)
ag
ain
s
t
t
h
e
f
alse
p
o
s
itiv
e
r
ate
(
FP
R
)
a
t
d
if
f
er
en
t
th
r
esh
o
ld
v
al
u
es.
Her
e,
FP
R
is
th
e
p
er
ce
n
tag
e
o
f
n
e
g
ativ
e
o
cc
u
r
r
e
n
ce
s
th
at
wer
e
in
c
o
r
r
ec
tly
class
if
ied
as
p
o
s
itiv
e,
s
er
v
in
g
as
a
m
ea
s
u
r
e
o
f
th
e
m
o
d
el’
s
f
als
e
alar
m
r
ate.
A
lo
w
FP
R
co
m
b
in
ed
with
a
h
ig
h
T
PR
r
ef
lects
ex
ce
llen
t c
lass
if
icatio
n
p
er
f
o
r
m
an
ce
.
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
Hu
ma
n
s
’
p
s
yc
h
o
lo
g
ica
l tra
its
cla
s
s
ifica
tio
n
fr
o
m
th
eir
…
(
A
r
p
ith
a
C
h
ikka
ma
g
a
lu
r
u
N
a
r
a
s
imh
e
Go
w
d
a
)
4561
Fig
u
r
e
5
.
C
o
n
f
u
s
io
n
ma
tr
i
x
o
f
C
NN
m
o
d
el
p
r
ed
ictio
n
s
ac
r
o
s
s
s
ev
en
p
s
y
ch
o
lo
g
ical
tr
aits
(
a)
(
b
)
(
c)
(
d
)
(
e)
(f)
(
g
)
Fig
u
r
e
6
.
C
NN
m
o
d
el
p
r
ed
icti
o
n
s
with
AUC v
alu
es f
o
r
R
OC
cu
r
v
es o
f
:
(
a)
o
p
en
n
ess
,
(
b
)
co
n
s
cien
tio
u
s
n
ess
,
(
c)
ex
tr
av
e
r
s
io
n
,
(
d
)
ag
r
ee
ab
le
n
ess
,
(
e)
n
eu
r
o
ticis
m
,
(
f
)
m
ate
r
ialis
m
,
an
d
(
g
)
s
elf
-
co
n
tr
o
l
Evaluation Warning : The document was created with Spire.PDF for Python.