I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
1
5
,
No
.
2
,
A
p
r
il 2
0
2
6
,
p
p
.
1
7
6
2
~
1
7
7
0
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
15
.i
2
.
p
p
1
7
6
2
-
1
7
7
0
1762
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Deep learni
ng
f
o
r
mental h
ea
lth
a
n
a
ly
sis
:
lo
ng
sho
rt
-
term
memo
ry
a
ppro
a
ch t
o
t
e
x
t
-
ba
sed
co
ndition
clas
sifica
t
io
n
Z
a
qq
i Y
a
m
a
ni
1
,
Dind
a
L
e
s
t
a
rini
2
,
Sa
rif
a
h P
utr
i R
a
f
lesi
a
2
,
P
urwit
a
Sa
ri
3
,
G
hita
At
ha
li
na
4
1
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
S
y
s
t
e
ms
,
F
a
c
u
l
t
y
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
U
n
i
v
e
r
si
t
a
s
S
r
i
w
i
j
a
y
a
,
P
a
l
e
m
b
a
n
g
,
I
n
d
o
n
e
s
i
a
2
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
i
z
e
d
A
c
c
o
u
n
t
i
n
g
,
F
a
c
u
l
t
y
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
U
n
i
v
e
r
si
t
a
s
S
r
i
w
i
j
a
y
a
,
P
a
l
e
m
b
a
n
g
,
I
n
d
o
n
e
s
i
a
3
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
c
s
M
a
n
a
g
e
m
e
n
t
,
F
a
c
u
l
t
y
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
,
U
n
i
v
e
r
si
t
a
s Sr
i
w
i
j
a
y
a
,
P
a
l
e
mb
a
n
g
,
I
n
d
o
n
e
si
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
,
F
a
c
u
l
t
y
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
,
U
n
i
v
e
r
si
t
a
s Sr
i
w
i
j
a
y
a
,
P
a
l
e
mb
a
n
g
,
I
n
d
o
n
e
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
l 2
6
,
2
0
2
5
R
ev
is
ed
Feb
6
,
2
0
2
6
Acc
ep
ted
Ma
r
5
,
2
0
2
6
Th
e
in
c
re
a
sin
g
p
re
v
a
len
c
e
o
f
m
e
n
tal
h
e
a
lt
h
d
iso
rd
e
rs
h
ig
h
li
g
h
ts
th
e
n
e
e
d
fo
r
sc
a
lab
le
a
n
d
a
u
to
m
a
ted
a
p
p
ro
a
c
h
e
s
to
e
a
rly
d
e
tec
ti
o
n
.
T
h
is
stu
d
y
p
ro
p
o
se
s
a
d
e
e
p
lea
rn
in
g
–
b
a
se
d
tex
t
c
las
sifi
c
a
ti
o
n
fra
m
e
wo
rk
u
sin
g
a
lo
n
g
sh
o
rt
-
term
m
e
m
o
ry
(LS
T
M
)
n
e
two
rk
to
i
d
e
n
ti
fy
m
e
n
tal
h
e
a
lt
h
c
o
n
d
it
i
o
n
s
fr
o
m
u
se
r
-
g
e
n
e
ra
ted
tex
tu
a
l
d
a
ta.
A
c
o
rp
u
s
o
f
1
0
3
,
4
8
8
lab
e
led
tex
ts
re
p
re
se
n
ti
n
g
a
n
x
iety
,
stre
ss
,
b
i
p
o
lar
d
iso
r
d
e
r,
d
e
p
re
ss
io
n
,
p
e
rso
n
a
li
t
y
d
is
o
rd
e
r
,
su
icid
a
l
id
e
a
ti
o
n
,
a
n
d
n
o
rm
a
l
sta
tes
wa
s
p
re
p
ro
c
e
ss
e
d
th
ro
u
g
h
to
k
e
n
iza
ti
o
n
,
p
a
d
d
i
n
g
,
a
n
d
wo
rd
e
m
b
e
d
d
in
g
.
T
h
e
p
ro
p
o
s
e
d
LS
TM
m
o
d
e
l
a
c
h
iev
e
d
o
v
e
ra
ll
a
c
c
u
ra
c
y
o
f
8
7
%
o
n
tes
t
se
t,
wit
h
stro
n
g
c
las
s
-
wise
p
e
rfo
rm
a
n
c
e
re
flec
ted
b
y
p
re
c
isio
n
,
re
c
a
ll
,
a
n
d
F
1
-
sc
o
r
e
s,
p
a
rti
c
u
larly
f
o
r
a
n
x
iety
,
p
e
rso
n
a
li
t
y
d
iso
rd
e
r,
a
n
d
n
o
rm
a
l
c
las
se
s.
C
o
m
p
a
ra
ti
v
e
e
rro
r
a
n
a
ly
sis
u
sin
g
a
c
o
n
fu
si
o
n
m
a
tri
x
re
v
e
a
led
c
h
a
ll
e
n
g
e
s
in
d
isti
n
g
u
ish
in
g
d
e
p
re
ss
io
n
fro
m
su
icid
a
l
id
e
a
ti
o
n
,
in
d
ica
ti
n
g
se
m
a
n
ti
c
o
v
e
rlap
b
e
twe
e
n
th
e
se
c
o
n
d
i
ti
o
n
s.
T
h
e
re
su
lt
s
d
e
m
o
n
stra
te
t
h
a
t
L
S
TM
-
b
a
se
d
m
o
d
e
ls
c
a
n
e
ffe
c
ti
v
e
ly
c
a
p
tu
re
se
q
u
e
n
ti
a
l
li
n
g
u
isti
c
p
a
tt
e
rn
s
re
le
v
a
n
t
to
m
e
n
tal
h
e
a
lt
h
c
las
sifica
ti
o
n
.
T
h
is
f
ra
m
e
wo
rk
sh
o
ws
p
o
ten
ti
a
l
a
s
a
d
e
c
isio
n
-
su
p
p
o
rt
to
o
l
f
o
r
e
a
rly
sc
re
e
n
in
g
a
n
d
d
ig
i
tal
m
e
n
tal
h
e
a
lt
h
a
p
p
li
c
a
ti
o
n
s,
c
o
m
p
lem
e
n
ti
n
g
c
li
n
ica
l
a
ss
e
ss
m
e
n
t
ra
th
e
r
th
a
n
re
p
lac
in
g
i
t.
K
ey
w
o
r
d
s
:
Dee
p
lear
n
in
g
L
o
n
g
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
Me
n
tal
h
ea
lth
d
is
o
r
d
e
r
Natu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
T
ex
t c
lass
if
icatio
n
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
:
Pu
r
wita
Sar
i
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atics M
an
ag
em
en
t,
Facu
lty
o
f
C
o
m
p
u
t
er
Scien
ce
,
Un
iv
er
s
itas
Sriwij
ay
a
Palem
b
an
g
,
I
n
d
o
n
esia
E
m
ail: w
ita@
i
lk
o
m
.
u
n
s
r
i.a
c.
i
d
1.
I
NT
RO
D
UCT
I
O
N
Me
n
tal
h
ea
lth
is
a
f
u
n
d
am
en
tal
co
m
p
o
n
e
n
t
o
f
o
v
er
all
well
-
b
ein
g
an
d
h
as
in
cr
ea
s
in
g
ly
b
ec
o
m
e
a
g
lo
b
al
p
u
b
lic
h
ea
lth
co
n
ce
r
n
.
C
o
n
d
itio
n
s
s
u
ch
as
an
x
iety
,
s
tr
ess
,
d
ep
r
ess
io
n
,
b
ip
o
lar
d
is
o
r
d
er
,
an
d
p
er
s
o
n
ality
d
is
o
r
d
er
s
s
ig
n
if
ican
tly
af
f
ec
t
in
d
iv
id
u
als’
q
u
ality
o
f
life
,
s
o
cial
f
u
n
ctio
n
i
n
g
,
an
d
p
r
o
d
u
cti
v
ity
.
Acc
o
r
d
in
g
to
th
e
W
o
r
ld
Hea
lth
Or
g
an
izatio
n
(
W
HO)
,
ap
p
r
o
x
im
ately
o
n
e
in
eig
h
t
p
eo
p
le
wo
r
l
d
wid
e
ex
p
er
ien
ce
s
a
m
e
n
tal
d
is
o
r
d
er
[
1
]
,
[
2
]
Desp
ite
g
r
o
win
g
awa
r
en
ess
,
ac
ce
s
s
to
tim
ely
an
d
ac
cu
r
ate
m
e
n
tal
h
e
alth
ass
ess
m
en
t
an
d
in
ter
v
en
tio
n
r
em
ain
s
lim
ited
f
o
r
m
an
y
p
o
p
u
latio
n
s
[
3
]
.
Sev
er
al
s
y
s
tem
ic
ch
allen
g
es
c
o
n
tin
u
e
to
h
in
d
e
r
e
f
f
ec
tiv
e
m
en
tal
h
ea
lth
ca
r
e,
in
clu
d
in
g
s
h
o
r
tag
es
o
f
tr
ain
ed
p
r
o
f
ess
io
n
als,
d
elay
ed
d
iag
n
o
s
is
,
an
d
f
r
eq
u
e
n
t
m
is
class
if
icatio
n
o
f
p
s
y
ch
o
lo
g
ical
co
n
d
itio
n
s
[
4
]
–
[
1
0
]
.
T
h
ese
lim
itatio
n
s
ar
e
p
ar
ticu
lar
ly
p
r
o
n
o
u
n
ce
d
in
lo
w
-
an
d
m
id
d
le
-
in
co
m
e
s
ettin
g
s
,
wh
er
e
th
e
g
ap
b
etwe
en
d
em
an
d
a
n
d
s
er
v
ice
ca
p
ac
ity
is
s
u
b
s
tan
tial
[
1
1
]
,
[
1
2
]
.
As
a
r
esu
lt,
th
er
e
is
an
in
cr
ea
s
in
g
n
ee
d
f
o
r
s
ca
lab
le,
co
s
t
-
ef
f
ec
tiv
e
ap
p
r
o
ac
h
es
th
at
ca
n
s
u
p
p
o
r
t
ea
r
ly
d
etec
tio
n
an
d
s
cr
ee
n
in
g
as
p
ar
t
o
f
b
r
o
ad
er
m
en
tal
h
ea
lth
s
er
v
ice
d
eliv
er
y
f
r
am
ewo
r
k
s
[
1
3
]
–
[
1
5
]
.
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
Dee
p
lea
r
n
in
g
fo
r
men
ta
l
h
ea
l
th
a
n
a
lysi
s
:
lo
n
g
s
h
o
r
t
-
term me
mo
r
y
a
p
p
r
o
a
ch
to
…
(
Za
q
q
i
Ya
ma
n
i
)
1763
T
h
e
wid
esp
r
ea
d
u
s
e
o
f
o
n
lin
e
p
latf
o
r
m
s
,
s
u
ch
as
s
o
cial
m
ed
ia
an
d
m
en
tal
h
ea
lth
f
o
r
u
m
s
,
h
as
led
in
d
iv
id
u
als
to
o
p
e
n
ly
ex
p
r
ess
em
o
tio
n
al
d
is
tr
ess
,
p
s
y
ch
o
lo
g
ical
ex
p
er
ie
n
ce
s
,
an
d
ch
an
g
es
in
m
en
tal
s
tates
th
r
o
u
g
h
tex
t
[
3
]
,
[
6
]
,
[
1
6
]
–
[
1
8
]
.
T
h
ese
u
s
er
-
g
e
n
er
ated
te
x
ts
p
r
o
v
id
e
v
alu
ab
le
i
n
s
ig
h
ts
in
to
p
s
y
ch
o
lo
g
ical
co
n
d
itio
n
s
an
d
p
r
esen
t
o
p
p
o
r
tu
n
ities
f
o
r
co
m
p
u
tatio
n
al
an
al
y
s
is
.
Sy
s
tem
atic
an
aly
s
i
s
o
f
s
u
ch
tex
tu
al
d
ata
m
ay
en
ab
le
ea
r
ly
id
e
n
tific
atio
n
o
f
m
en
tal
h
ea
lth
r
is
k
s
an
d
s
u
p
p
o
r
t p
r
ev
en
tiv
e
i
n
ter
v
en
tio
n
s
.
R
ec
en
t
ad
v
an
ce
s
in
n
atu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
(
NL
P)
an
d
d
ee
p
lear
n
in
g
h
av
e
s
h
o
w
n
p
r
o
m
is
e
in
an
aly
zin
g
m
en
tal
h
ea
lth
–
r
elat
ed
tex
t.
I
n
p
ar
ticu
lar
,
r
ec
u
r
r
e
n
t
n
eu
r
al
n
etwo
r
k
(
R
NN)
ar
c
h
itectu
r
es,
s
u
ch
as
lo
n
g
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
(
L
S
T
M)
,
ar
e
well
-
s
u
ited
f
o
r
m
o
d
elin
g
s
eq
u
en
tial
lan
g
u
ag
e
p
att
er
n
s
an
d
ca
p
tu
r
in
g
co
n
tex
tu
al
d
ep
en
d
en
cies
th
at
ar
e
o
f
ten
cr
itical
in
p
s
y
ch
o
l
o
g
ical
ex
p
r
ess
io
n
[
1
9
]
,
[
2
0
]
.
Un
lik
e
tr
ad
itio
n
al
m
ac
h
in
e
lear
n
in
g
ap
p
r
o
ac
h
es
th
at
r
ely
o
n
s
tatic
f
ea
tu
r
es,
L
STM
m
o
d
els
ca
n
r
ep
r
esen
t
tem
p
o
r
al
an
d
s
em
an
tic
r
elatio
n
s
h
ip
s
with
in
tex
t m
o
r
e
ef
f
ec
tiv
ely
.
Ho
wev
er
,
e
x
is
tin
g
s
tu
d
ies
o
f
t
en
f
o
c
u
s
o
n
lim
ited
d
iag
n
o
s
ti
c
ca
teg
o
r
ies,
s
m
all
d
atasets
,
o
r
s
h
allo
w
lin
g
u
is
tic
r
ep
r
esen
tatio
n
s
,
w
h
ich
r
estrict
th
eir
g
e
n
er
aliz
ab
ilit
y
an
d
r
o
b
u
s
tn
ess
.
Mo
r
eo
v
er
,
c
o
m
p
ar
ativ
e
ev
alu
atio
n
s
o
f
m
u
lti
-
class
m
en
tal
h
ea
lth
class
if
icatio
n
u
s
in
g
lar
g
e
-
s
ca
le
tex
t
co
r
p
o
r
a
r
e
m
ain
lim
ited
.
T
h
is
s
tu
d
y
ad
d
r
ess
es
th
ese
g
ap
s
b
y
ap
p
ly
in
g
a
n
L
STM
-
b
ased
d
ee
p
lear
n
in
g
f
r
a
m
ewo
r
k
to
class
if
y
m
u
ltip
le
m
en
tal
h
ea
lth
co
n
d
itio
n
s
u
s
in
g
a
lar
g
e
an
n
o
tated
d
ataset
o
f
u
s
er
-
g
en
er
ated
tex
t.
B
y
f
o
c
u
s
in
g
o
n
s
eq
u
en
tial
tex
tu
al
r
ep
r
esen
tatio
n
s
,
th
is
r
esear
ch
aim
s
to
co
n
tr
ib
u
te
em
p
ir
ical
e
v
id
en
ce
o
n
th
e
ef
f
ec
tiv
en
ess
o
f
L
STM
m
o
d
els
f
o
r
s
ca
lab
le
an
d
au
to
m
ate
d
m
en
ta
l h
ea
lth
tex
t c
lass
if
icatio
n
.
2.
M
E
T
H
O
D
W
e
d
escr
ib
e
th
e
p
r
o
ce
d
u
r
al
s
tep
s
f
o
r
d
ev
el
o
p
in
g
a
n
d
em
p
ir
ically
ass
es
s
in
g
th
e
L
STM
m
o
d
el
f
o
r
p
r
ed
ictin
g
m
e
n
tal
h
ea
lth
d
is
o
r
d
er
s
u
s
in
g
u
s
er
-
g
en
er
ated
te
x
tu
al
co
m
m
en
ts
.
T
h
e
wo
r
k
f
lo
w
is
co
m
p
o
s
ed
o
f
d
ata
co
llectio
n
an
d
in
ter
p
r
etatio
n
,
d
ata
p
r
e
-
p
r
o
ce
s
s
in
g
,
tex
t
r
ep
r
esen
tatio
n
,
m
o
d
el
s
elec
tio
n
,
tr
ain
in
g
,
an
d
p
er
f
o
r
m
an
ce
esti
m
atio
n
[
2
1
]
,
[
2
2
]
.
E
ac
h
s
tag
e
is
ca
r
ef
u
lly
d
esig
n
ed
to
p
r
o
d
u
ce
a
r
o
b
u
s
t
an
d
p
r
e
d
ictio
n
-
b
ased
m
o
d
el
f
o
r
n
o
v
el
in
s
tan
ce
s
o
f
n
atu
r
al
lan
g
u
a
g
e,
wh
ich
a
r
e
th
e
s
ig
n
s
o
f
p
s
y
ch
o
l
o
g
ical
d
is
o
r
d
e
r
s
.
2
.
1
.
Da
t
a
c
o
llect
io
n
T
h
e
co
r
p
u
s
u
tili
ze
d
in
t
h
is
wo
r
k
is
th
e
m
en
tal
h
ea
lth
t
ex
t
co
r
p
u
s
f
o
r
em
o
tio
n
an
d
co
n
d
itio
n
class
if
icatio
n
,
co
n
s
is
tin
g
o
f
m
o
r
e
th
an
1
0
3
,
4
8
8
ex
a
m
p
les
o
f
p
s
y
ch
o
lo
g
ical
lan
g
u
ag
e
ex
p
r
ess
io
n
s
.
E
v
er
y
r
ec
o
r
d
in
th
e
d
ataset
is
tag
g
ed
with
a
s
p
ec
if
ic
m
e
n
tal
h
ea
lth
illn
ess
,
e.
g
.
,
a
n
x
i
ety
,
s
tr
ess
,
b
ip
o
lar
d
is
o
r
d
er
,
d
ep
r
ess
io
n
,
p
er
s
o
n
a
lity
d
is
o
r
d
er
,
o
r
s
u
icid
al
i
d
e
atio
n
.
T
h
e
d
ata
s
et
co
n
tain
s
a
wid
e
v
ar
iety
o
f
lin
g
u
is
tic
s
ty
les,
em
o
tio
n
s
,
an
d
p
s
y
ch
o
l
o
g
ical
co
n
ce
p
ts
ty
p
i
ca
lly
s
ee
n
o
n
m
e
n
tal
h
ea
lth
r
e
lated
u
s
er
g
en
er
ate
d
tex
t.
T
h
e
in
p
u
t
r
o
w
in
th
e
d
at
aset
h
as
two
m
ain
f
ield
s
:
i)
t
e
x
t,
a
f
r
ee
-
f
o
r
m
s
en
ten
ce
o
r
p
a
r
ag
r
ap
h
d
escr
ib
in
g
th
e
em
o
tio
n
al
o
r
m
en
tal
co
n
d
itio
n
o
f
a
u
s
er
;
an
d
ii)
s
tatu
s
,
a
lab
el
th
at
d
e
n
o
tes
a
p
e
r
s
o
n
’
s
o
r
u
s
er
’
s
s
tate
o
f
m
in
d
.
T
o
t
h
e
b
est
o
f
o
u
r
k
n
o
wled
g
e,
it
is
a
lar
g
e
d
ataset
to
tr
ai
n
a
n
d
ev
alu
ate
d
ee
p
l
ea
r
n
in
g
m
o
d
els
f
o
r
au
to
m
atic
m
en
tal
illn
ess
class
i
f
icatio
n
.
2
.
2
.
P
re
pro
ce
s
s
ing
o
f
da
t
a
Pre
p
r
o
ce
s
s
in
g
is
o
n
e
o
f
th
e
cr
i
tical
task
s
o
f
NL
P
to
m
ak
e
r
a
w
tex
t
d
ata
r
ea
d
y
in
a
f
o
r
m
s
u
i
tab
le
to
b
e
in
p
u
t
to
m
ac
h
in
e
lear
n
in
g
an
d
d
ee
p
lear
n
in
g
m
o
d
els
[
2
2
]
,
[
2
3
]
.
So
m
e
p
r
ep
r
o
ce
s
s
in
g
tech
n
iq
u
es
h
av
e
b
e
en
u
s
ed
in
th
is
wo
r
k
o
n
th
e
m
e
n
tal
h
ea
lth
tex
t
d
ataset
f
o
r
em
o
tio
n
an
d
co
n
d
itio
n
class
if
icatio
n
to
s
tan
d
ar
d
ize
th
e
d
ata
an
d
g
et
it
r
ea
d
y
.
T
o
s
tar
t
with
,
all
o
f
th
e
tex
t
was
co
n
v
er
ted
to
lo
wer
ca
s
e
s
o
th
at
th
er
e
was
co
n
s
is
ten
t
o
u
tp
u
t
an
d
r
e
d
u
n
d
an
cy
d
id
n
o
t
tak
e
p
lace
b
ec
au
s
e
ca
s
es
wer
e
s
en
s
itiv
e.
T
o
k
en
izatio
n
was
th
en
p
er
f
o
r
m
e
d
u
s
in
g
Ker
as'
to
k
en
izer
,
w
h
ich
s
ep
ar
ated
ev
er
y
p
ar
a
g
r
ap
h
o
r
s
en
ten
ce
in
t
o
in
d
iv
id
u
al
to
k
en
s
(
wo
r
d
s
)
.
Dep
en
d
in
g
o
n
ex
p
er
im
e
n
tal
co
n
f
ig
u
r
atio
n
s
,
s
to
p
wo
r
d
r
e
m
o
v
al
was
also
p
er
f
o
r
m
ed
to
elim
in
ate
co
m
m
o
n
wo
r
d
s
(
s
u
ch
as
"th
e"
,
"is",
"a
n
d
")
th
at
m
ay
n
o
t
b
e
s
ig
n
if
ican
t
in
d
if
f
er
en
tiatin
g
class
es.
Seco
n
d
,
s
in
ce
n
eu
r
a
l
n
etwo
r
k
s
ac
ce
p
t
f
ix
ed
-
s
ize
in
p
u
ts
[
2
4
]
,
all
to
k
en
ize
d
s
eq
u
e
n
ce
s
wer
e
p
ad
d
ed
o
r
s
h
o
r
ten
e
d
to
a
s
ize
o
f
u
p
to
1
0
0
to
k
en
s
.
L
astl
y
,
t
h
e
ca
teg
o
r
ical
class
lab
els
in
th
e
s
tatu
s
co
lu
m
n
wer
e
tr
an
s
lated
in
to
n
u
m
er
ical
f
o
r
m
v
i
a
L
ab
elE
n
co
d
e
r
an
d
th
en
o
n
ce
a
g
ain
o
n
e
-
h
o
t
en
co
d
ed
to
co
r
r
e
s
p
o
n
d
with
th
e
So
f
tMa
x
ac
tiv
atio
n
f
u
n
ctio
n
u
s
ed
in
th
e
o
u
tp
u
t
lay
er
o
f
th
e
L
STM
m
o
d
el.
T
h
ese
p
r
ep
r
o
ce
s
s
in
g
task
s
en
s
u
r
ed
th
e
tex
t
in
p
u
ts
an
d
class
lab
els
wer
e
in
th
e
s
am
e
m
o
d
el
-
f
r
ien
d
ly
f
o
r
m
at.
2
.
3
.
Wo
rd
re
presenta
t
io
n
W
o
r
d
em
b
ed
d
in
g
s
wer
e
em
p
lo
y
ed
to
r
ep
r
esen
t th
e
to
k
e
n
ized
tex
t in
a
f
o
r
m
at
th
at
p
r
eser
v
es sem
an
tic
m
ea
n
in
g
[
2
2
]
,
[
2
3
]
,
[
2
5
]
,
[
2
6
]
.
W
o
r
d
em
b
e
d
d
in
g
s
ar
e
d
en
s
e
v
ec
to
r
s
p
ac
es
s
u
m
m
ar
izin
g
s
em
an
tic
r
elatio
n
s
h
ip
s
b
etwe
en
wo
r
d
s
f
r
o
m
th
eir
co
n
tex
t
u
s
e
[
2
7
]
.
An
em
b
ed
d
in
g
lay
er
w
as
em
p
lo
y
ed
with
a
v
o
ca
b
u
lar
y
s
ize
cu
t
o
f
f
at
th
e
to
p
2
0
,
0
0
0
m
o
s
t
f
r
eq
u
e
n
t
wo
r
d
s
in
th
e
d
ataset,
an
d
ev
er
y
wo
r
d
was
r
ep
r
esen
ted
in
a
1
2
8
-
d
im
en
s
i
o
n
al
v
ec
to
r
s
p
ac
e.
E
m
b
ed
d
in
g
s
wer
e
r
an
d
o
m
ly
in
itialized
an
d
lear
n
ed
d
u
r
in
g
tr
ain
in
g
[
2
3
]
,
[
2
7
]
allo
win
g
th
e
m
o
d
el
to
lear
n
h
o
w
to
ad
ap
t
th
e
v
ec
to
r
r
e
p
r
esen
tatio
n
s
to
th
e
s
p
ec
if
ic
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
2
,
Ap
r
il 2
0
2
6
:
1
7
6
2
-
1
7
7
0
1764
lin
g
u
is
tic
p
atter
n
s
an
d
d
o
m
ai
n
-
s
p
ec
if
ic
ter
m
in
o
lo
g
y
f
o
u
n
d
in
m
en
tal
h
ea
lth
lan
g
u
ag
e.
B
y
lear
n
in
g
th
ese
co
n
tex
t
em
b
ed
d
in
g
s
f
r
o
m
s
cr
atch
,
th
e
m
o
d
el
was
b
etter
p
o
s
itio
n
ed
to
ca
p
tu
r
e
n
u
an
ce
d
em
o
tio
n
al
cu
es
a
n
d
s
em
an
tics
th
at
d
if
f
er
en
tiate
b
e
twee
n
p
s
y
ch
o
lo
g
ical
co
n
d
itio
n
class
es.
2
.
4
.
L
ST
M
m
o
del desig
n
T
h
e
p
r
o
p
o
s
ed
d
ee
p
lea
r
n
in
g
m
o
d
el
in
t
h
is
wo
r
k
is
an
L
ST
M
n
etwo
r
k
t
h
at
is
id
ea
lly
wel
l
-
s
u
ited
f
o
r
p
r
o
ce
s
s
in
g
s
eq
u
en
tial
d
ata
a
n
d
m
o
d
ellin
g
lo
n
g
d
ep
en
d
en
cies
in
tex
t
[
2
8
]
.
L
STM
is
a
s
p
ec
ialized
ty
p
e
o
f
R
NN
d
esig
n
ed
to
o
v
e
r
co
m
e
t
h
e
v
a
n
is
h
in
g
g
r
a
d
ien
t
p
r
o
b
lem
i
n
R
NN
[
2
9
]
.
T
h
e
k
ey
c
o
m
p
o
n
en
t
s
o
f
an
L
STM
u
n
it
in
clu
d
e
th
e
in
p
u
t g
ate,
f
o
r
g
et
g
ate,
an
d
o
u
tp
u
t
g
ate.
In
(
1
)
d
en
o
tes
th
e
in
p
u
t
g
ate
f
u
n
ctio
n
,
wh
ich
is
r
esp
o
n
s
ib
le
f
o
r
g
en
er
atin
g
a
n
ew
m
e
m
o
r
y
s
tate
wh
en
th
e
in
co
m
in
g
wo
r
d
h
o
ld
s
s
ig
n
if
ican
t
im
p
o
r
tan
ce
.
B
y
ev
al
u
atin
g
th
e
cu
r
r
en
t
in
p
u
t
alo
n
g
with
th
e
p
r
ev
i
o
u
s
h
id
d
en
s
tate,
th
e
in
p
u
t
g
ate
d
eter
m
in
es
th
e
v
alu
e
o
f
r
etai
n
in
g
th
e
n
ew
wo
r
d
a
n
d
ac
co
r
d
in
g
ly
e
n
ab
les
th
e
f
o
r
m
atio
n
o
f
u
p
d
ated
m
em
o
r
y
.
=
(
.
[
ℎ
(
−
1
)
,
]
+
)
(
1
)
At
ea
ch
tim
e
s
tep
,
th
e
f
o
r
g
et
g
ate
is
em
p
lo
y
ed
to
d
eter
m
in
e
wh
eth
er
th
e
p
r
ev
io
u
s
ce
ll
s
tate
is
u
s
ef
u
l
f
o
r
th
e
co
m
p
u
tatio
n
o
r
n
o
t.
T
h
e
f
o
r
g
et
g
ate
p
r
o
ce
s
s
es
th
e
cu
r
r
en
t
in
p
u
t
alo
n
g
with
th
e
p
r
ev
i
o
u
s
h
id
d
en
s
tate
t
o
g
en
er
ate
th
e
f
o
r
g
et
s
ig
n
al,
d
en
o
ted
as
,
as d
escr
ib
ed
i
n
(
2
)
.
=
(
.
[
ℎ
(
−
1
)
,
]
+
)
(
2
)
T
h
e
n
ew
m
em
o
r
y
,
d
en
o
ted
as
C
in
(
3
)
,
is
ca
lcu
lated
b
y
in
teg
r
atin
g
f
ea
tu
r
es
f
r
o
m
th
e
cu
r
r
e
n
t
in
p
u
t
wo
r
d
xₜ
an
d
th
e
p
r
ev
io
u
s
h
id
d
e
n
s
tate
h
ₜ₋₁
.
C
=
ℎ
(
C
.
[
ℎ
(
−
1
)
,
]
+
C
)
(
3
)
T
h
e
n
ex
t step
is
to
u
p
d
ate
th
e
ce
ll st
ate
b
y
co
m
b
in
in
g
r
etain
e
d
an
d
n
ew
in
f
o
r
m
atio
n
,
as d
escr
ib
ed
in
(
4
)
.
=
×
−
1
+
×
C
(
4
)
In
(
5
)
is
u
s
ed
to
ca
lcu
late
th
e
o
u
tp
u
t
g
ate
to
d
eter
m
in
e
th
e
tim
in
g
o
f
r
elea
s
in
g
th
e
s
to
r
ed
m
em
o
r
y
v
alu
e
t
o
th
e
h
id
d
en
la
y
er
.
Fin
ally
,
th
e
n
ew
h
id
d
en
s
tate,
hₜ
,
is
co
m
p
u
ted
b
y
p
e
r
f
o
r
m
in
g
m
u
ltip
licatio
n
b
etwe
en
th
e
o
u
tp
u
t
g
ate
an
d
th
e
u
p
d
ated
ce
ll st
ate
as d
escr
ib
ed
in
(
6
)
.
=
(
.
[
ℎ
(
−
1
)
,
]
+
)
(
5
)
ℎ
=
×
ta
n
h
(
)
(
6
)
I
n
th
is
r
esear
c
h
,
th
e
ar
c
h
itectu
r
e
b
e
g
in
s
with
a
n
em
b
ed
d
i
n
g
lay
er
th
at
m
a
p
s
in
p
u
t
to
k
en
s
to
d
en
s
e
wo
r
d
v
ec
to
r
s
o
f
s
ize
1
2
8
.
T
h
is
is
th
en
f
o
llo
wed
b
y
an
L
STM
lay
er
o
f
6
4
m
em
o
r
y
u
n
its
to
h
an
d
le
th
e
em
b
ed
d
e
d
s
eq
u
en
ce
s
a
n
d
d
er
i
v
e
th
e
tem
p
o
r
al
s
tr
u
ct
u
r
e
a
n
d
wo
r
d
-
to
-
w
o
r
d
c
o
n
tex
t
u
al
r
elat
io
n
s
h
ip
s
.
T
o
h
an
d
le
o
v
er
f
itti
n
g
r
is
k
,
a
d
r
o
p
o
u
t
la
y
er
with
a
r
ate
0
.
5
was
in
clu
d
e
d
th
at
r
an
d
o
m
ly
s
ets
a
f
r
ac
tio
n
o
f
n
e
u
r
o
n
s
to
ze
r
o
d
u
r
in
g
tr
ain
in
g
.
T
h
e
L
STM
o
u
tp
u
t
is
th
en
r
o
u
ted
to
a
f
u
lly
c
o
n
n
ec
ted
lay
er
em
p
lo
y
in
g
th
e
r
ec
tifie
d
lin
ea
r
u
n
it
(
R
eL
U
)
ac
tiv
atio
n
f
u
n
ctio
n
,
wh
ich
in
f
u
s
es
th
e
n
etwo
r
k
with
n
o
n
-
lin
ea
r
ity
an
d
au
g
m
en
ts
its
ex
p
r
ess
iv
e
ca
p
ac
ity
.
T
h
e
c
u
lm
in
atin
g
la
y
er
is
a
So
f
tMa
x
f
u
n
ctio
n
th
at
r
en
d
er
s
class
-
s
p
ec
if
ic
p
r
o
b
ab
ilit
y
d
is
tr
ib
u
tio
n
s
ac
r
o
s
s
th
e
tar
g
et
m
en
tal
h
ea
lth
co
n
d
itio
n
s
.
As
s
h
o
wn
in
(
7
)
,
N
d
en
o
tes
th
e
n
u
m
b
er
o
f
n
o
d
es
in
th
e
o
u
tp
u
t
lay
er
s
,
an
d
d
en
o
tes
th
e
o
u
tp
u
t
s
co
r
e
f
o
r
class
i
.
(
)
=
∑
=
1
(
7
)
T
h
e
m
o
d
el
u
s
ed
ca
teg
o
r
ical
cr
o
s
s
-
en
tr
o
p
y
as
its
lo
s
s
f
u
n
ctio
n
,
a
s
tan
d
ar
d
ch
o
ice
f
o
r
p
r
o
b
lem
s
in
v
o
lv
in
g
m
o
r
e
th
an
two
class
es.
T
h
e
lo
s
s
is
ca
lcu
lated
u
s
in
g
(
8
)
.
=
−
∑
l
og
(
̂
)
=
1
(
8
)
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
Dee
p
lea
r
n
in
g
fo
r
men
ta
l
h
ea
l
th
a
n
a
lysi
s
:
lo
n
g
s
h
o
r
t
-
term me
mo
r
y
a
p
p
r
o
a
ch
to
…
(
Za
q
q
i
Ya
ma
n
i
)
1765
T
h
e
r
esu
lt
was
o
p
tim
ized
with
th
e
Ad
am
o
p
tim
i
z
er
,
wh
ich
is
well
r
eg
ar
d
ed
f
o
r
its
ab
ilit
y
to
ad
ap
tiv
ely
ad
ju
s
t
th
e
lear
n
in
g
r
ate
.
I
t
also
ef
f
ec
tiv
ely
m
an
ag
e
s
s
p
ar
s
e
g
r
ad
ien
ts
th
r
o
u
g
h
o
u
t
th
e
tr
ain
in
g
p
r
o
ce
s
s
.
T
h
is
co
m
b
in
atio
n
o
f
ar
ch
itectu
r
al
elem
en
ts
an
d
tr
a
in
in
g
s
tr
ateg
ies
allo
ws
th
e
m
o
d
el
to
id
en
tify
an
d
class
if
y
m
en
tal
h
ea
lth
-
r
elate
d
ex
p
r
ess
io
n
s
in
tex
t d
ata
ef
f
ec
tiv
ely
.
2
.
5
.
M
o
del
t
ra
ini
ng
T
r
ain
in
g
was
ca
r
r
ied
o
u
t
u
s
i
n
g
th
e
s
tan
d
ar
d
s
u
p
er
v
is
ed
lear
n
in
g
,
k
ee
p
i
n
g
8
0
%
o
f
th
e
d
ata
f
o
r
tr
ain
in
g
p
u
r
p
o
s
es
an
d
2
0
%
f
o
r
test
in
g
.
Fo
r
f
u
r
th
er
m
o
n
ito
r
in
g
an
d
m
o
d
el
ass
ess
m
en
t
o
f
b
ei
n
g
ca
p
ab
le
o
f
g
en
er
alizin
g
d
u
r
i
n
g
tr
ai
n
in
g
,
2
0
%
o
f
th
e
tr
ain
in
g
d
ata
was
k
ep
t
asid
e
as
a
v
alid
atio
n
s
et.
T
r
ain
in
g
was
ca
r
r
ied
o
u
t
with
a
b
atc
h
s
ize
o
f
1
2
8
f
o
r
5
e
p
o
ch
s
.
T
h
e
m
o
d
el
was
th
en
o
p
tim
ized
u
s
in
g
th
e
Ad
a
m
o
p
tim
izer
with
t
h
e
d
ef
au
lt
lear
n
in
g
r
ate,
a
n
d
a
c
ateg
o
r
ical
cr
o
s
s
-
en
tr
o
p
y
lo
s
s
f
u
n
ctio
n
was
em
p
lo
y
ed
,
wh
ic
h
is
ap
p
r
o
p
r
iate
f
o
r
m
u
lti
-
class
clas
s
if
icatio
n
p
r
o
b
lem
s
.
E
ar
ly
s
to
p
p
in
g
m
eth
o
d
was
u
tili
ze
d
to
ter
m
in
ate
t
r
ain
in
g
in
ca
s
e
th
e
v
alid
atio
n
lo
s
s
s
to
p
p
ed
im
p
r
o
v
in
g
,
th
er
e
f
o
r
e
a
v
o
id
in
g
o
v
er
f
itti
n
g
.
Alo
n
g
th
e
way
,
m
ea
s
u
r
em
en
ts
o
f
p
er
f
o
r
m
an
ce
,
s
u
ch
as
tr
ai
n
in
g
an
d
v
alid
atio
n
ac
cu
r
ac
y
a
n
d
l
o
s
s
,
wer
e
tr
ac
k
ed
,
en
a
b
lin
g
a
clo
s
e
in
s
p
ec
tio
n
o
f
h
o
w
th
e
m
o
d
el
lear
n
e
d
o
v
e
r
ti
m
e.
2
.
6
.
M
o
del
ev
a
lua
t
i
o
n
Fo
llo
win
g
tr
ain
in
g
,
m
o
d
el
p
e
r
f
o
r
m
a
n
ce
was
ass
ess
ed
o
n
th
e
h
eld
-
o
u
t
test
s
et
with
a
f
u
ll
r
an
g
e
o
f
ev
alu
atio
n
m
etr
ics
to
d
eter
m
i
n
e
b
o
th
o
v
er
all
ac
cu
r
ac
y
a
n
d
class
-
wi
s
e
p
er
f
o
r
m
an
ce
.
Acc
u
r
ac
y
was
em
p
lo
y
ed
as
a
g
en
er
al
co
r
r
ec
tn
ess
m
etr
ic,
d
escr
ib
in
g
th
e
p
r
o
p
o
r
tio
n
o
f
to
tal
p
r
ed
ictio
n
s
th
at
ag
r
ee
d
with
tr
u
e
lab
els.
Fu
r
th
er
m
o
r
e
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
wer
e
ca
lcu
lated
f
o
r
ea
ch
class
to
a
s
s
es
s
th
e
m
o
d
el'
s
ca
p
ab
ilit
y
to
ac
cu
r
ately
d
etec
t
s
p
ec
if
ic
m
en
tal
h
ea
lth
d
is
o
r
d
er
s
an
d
b
alan
ce
s
en
s
itiv
ity
an
d
s
p
ec
if
icity
.
T
h
e
s
u
p
p
o
r
t
m
etr
ic
was
also
r
ep
o
r
ted
to
s
p
ec
if
y
t
h
e
n
u
m
b
er
o
f
tr
u
e
in
s
tan
ce
s
p
er
class
,
p
r
o
v
id
in
g
cr
u
cial
co
n
tex
t
f
o
r
in
ter
p
r
etin
g
p
er
f
o
r
m
an
ce
m
et
r
ics,
esp
ec
ially
in
th
e
ev
en
t
o
f
class
im
b
ala
n
ce
.
A
co
n
f
u
s
io
n
m
atr
ix
was
also
em
p
lo
y
ed
as
a
v
is
u
al
d
iag
n
o
s
tic
aid
to
u
n
co
v
er
f
r
eq
u
e
n
t
m
is
class
if
i
ca
tio
n
p
atter
n
s
,
in
clu
d
in
g
co
n
f
u
s
io
n
b
etwe
en
s
em
an
tically
r
elate
d
class
es
s
u
ch
as
an
x
iety
an
d
s
tr
ess
.
B
o
th
th
e
class
if
icatio
n
r
ep
o
r
t
an
d
co
n
f
u
s
io
n
m
atr
i
x
wer
e
g
en
e
r
ated
with
th
e
Scik
it
-
lear
n
lib
r
a
r
y
,
wh
ile
tr
ai
n
in
g
h
is
to
r
y
p
l
o
ts
an
d
ev
al
u
atio
n
v
is
u
aliza
tio
n
s
wer
e
cr
ea
ted
u
s
in
g
Ma
tp
lo
tlib
t
o
f
ac
ilit
ate
f
u
r
th
er
an
aly
s
is
o
f
m
o
d
e
l b
eh
av
io
r
.
2
.
7
.
B
a
s
eline
co
m
pa
riso
n a
n
d m
o
del j
us
t
if
ica
t
io
n
T
h
e
L
STM
ar
c
h
itectu
r
e
wa
s
s
elec
ted
d
u
e
to
its
p
r
o
v
en
ca
p
ab
ilit
y
in
m
o
d
elin
g
lo
n
g
-
ter
m
d
ep
en
d
e
n
cies
an
d
c
o
n
tex
tu
al
in
f
o
r
m
atio
n
in
s
eq
u
en
tial
tex
t
d
ata
.
T
h
is
ca
p
a
b
ilit
y
is
cr
itical
f
o
r
m
e
n
tal
h
ea
lt
h
lan
g
u
ag
e
an
aly
s
is
.
Un
lik
e
tr
a
d
itio
n
al
m
ac
h
in
e
lear
n
in
g
cla
s
s
if
ier
s
th
at
r
ely
o
n
s
tatic
f
ea
tu
r
e
r
e
p
r
esen
tatio
n
s
,
L
STM
n
etwo
r
k
s
d
y
n
am
ically
ca
p
tu
r
e
tem
p
o
r
al
wo
r
d
d
ep
e
n
d
en
cies th
at
r
ef
lect
em
o
tio
n
al
p
r
o
g
r
ess
io
n
in
tex
t
.
W
h
ile
th
is
s
tu
d
y
p
r
im
ar
ily
f
o
cu
s
es
o
n
L
STM
p
er
f
o
r
m
a
n
ce
,
p
r
io
r
liter
atu
r
e
co
n
s
is
ten
tly
r
ep
o
r
ts
th
at
r
ec
u
r
r
en
t
ar
c
h
itectu
r
es
o
u
tp
e
r
f
o
r
m
b
aselin
e
m
o
d
els
s
u
ch
as
n
aïv
e
B
ay
es,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
s
,
an
d
co
n
v
en
tio
n
al
n
eu
r
al
n
etwo
r
k
s
in
em
o
tio
n
an
d
m
en
tal
h
ea
lth
class
if
icatio
n
task
s
.
T
h
e
ch
o
s
e
n
h
y
p
e
r
p
ar
am
eter
s
,
em
b
ed
d
in
g
d
im
e
n
s
io
n
o
f
1
2
8
,
6
4
L
STM
u
n
its
,
d
r
o
p
o
u
t
r
ate
o
f
0
.
5
,
b
atch
s
ize
o
f
1
2
8
,
an
d
Ad
am
o
p
tim
izer
,
wer
e
s
elec
ted
b
ased
o
n
em
p
ir
ical
v
alid
atio
n
an
d
co
m
m
o
n
ly
ad
o
p
ted
b
est
p
r
ac
tices
in
NL
P
-
b
ased
d
ee
p
lear
n
in
g
s
tu
d
ies.
T
h
is
co
n
f
i
g
u
r
atio
n
b
alan
ce
s
m
o
d
el
ex
p
r
ess
iv
en
ess
an
d
g
en
er
aliza
tio
n
wh
ile
av
o
id
i
n
g
ex
ce
s
s
iv
e
co
m
p
u
tatio
n
al
c
o
m
p
lex
ity
.
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
a
d
etai
led
an
aly
s
is
o
f
th
e
ex
p
er
im
e
n
tal
r
esu
lts
o
b
tain
ed
f
r
o
m
ap
p
ly
in
g
th
e
L
STM
ar
ch
itectu
r
e
to
m
en
tal
h
ea
lth
s
tate
p
r
ed
ictio
n
an
d
p
r
o
v
id
es
an
i
n
-
d
e
p
th
d
is
cu
s
s
i
o
n
o
f
t
h
e
m
o
d
el’
s
lear
n
in
g
b
eh
av
io
r
an
d
class
if
icatio
n
p
er
f
o
r
m
a
n
ce
.
T
h
e
L
ST
M
m
o
d
el
is
p
ar
ticu
la
r
ly
well
-
s
u
ited
f
o
r
th
is
task
d
u
e
to
its
r
o
b
u
s
tn
ess
in
h
an
d
l
in
g
s
eq
u
en
tial
d
ata
an
d
its
ab
ilit
y
to
lear
n
lo
n
g
-
ter
m
d
ep
en
d
en
cies,
wh
ich
ar
e
ess
en
tial
f
o
r
ca
p
tu
r
in
g
co
n
te
x
tu
al
an
d
em
o
tio
n
al
p
atter
n
s
in
m
en
tal
h
ea
lth
–
r
elate
d
te
x
t.
T
h
e
m
o
d
el
was
tr
ain
ed
u
s
in
g
a
ca
r
ef
u
lly
p
r
e
p
r
o
ce
s
s
ed
an
d
lab
eled
d
ataset,
an
d
its
p
er
f
o
r
m
a
n
ce
was
ev
alu
ated
u
s
in
g
s
tan
d
ar
d
class
if
icatio
n
m
etr
ics,
in
clu
d
in
g
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e.
T
h
ese
m
etr
ics
co
llectiv
ely
p
r
o
v
id
e
a
co
m
p
r
e
h
en
s
iv
e
ass
ess
m
en
t
o
f
b
o
th
o
v
er
all
p
r
ed
ictiv
e
ca
p
ab
ilit
y
an
d
class
-
lev
el
d
is
cr
im
in
atio
n
.
T
h
e
ex
p
er
im
en
tal
r
esu
lts
in
d
icate
th
at
th
e
L
STM
ar
c
h
itectu
r
e
a
ch
iev
es
co
n
s
is
ten
tly
s
tr
o
n
g
p
er
f
o
r
m
a
n
ce
ac
r
o
s
s
m
u
ltip
le
m
en
tal
h
ea
lth
ca
teg
o
r
ies,
s
u
p
p
o
r
tin
g
its
p
o
ten
tial u
ti
lity
as a
d
ec
is
io
n
-
s
u
p
p
o
r
t to
o
l
f
o
r
ea
r
ly
s
cr
ee
n
i
n
g
an
d
m
o
n
ito
r
in
g
in
m
en
tal
h
ea
l
th
ap
p
licatio
n
s
.
Fig
u
r
e
1
illu
s
tr
ates
th
e
tr
ain
i
n
g
an
d
v
alid
atio
n
ac
cu
r
ac
y
an
d
lo
s
s
tr
ajec
to
r
ies
o
v
er
f
iv
e
ep
o
ch
s
,
o
f
f
er
in
g
in
s
ig
h
t
in
to
th
e
m
o
d
el’
s
lear
n
in
g
d
y
n
am
ics.
T
r
a
in
in
g
ac
cu
r
ac
y
e
x
h
ib
its
a
s
te
ad
y
u
p
war
d
tr
en
d
,
in
cr
ea
s
in
g
f
r
o
m
7
2
.
5
%
in
th
e
f
ir
s
t
ep
o
ch
to
9
2
.
7
%
b
y
t
h
e
f
in
al
ep
o
ch
.
T
h
is
p
r
o
g
r
ess
iv
e
im
p
r
o
v
em
e
n
t
in
d
icate
s
th
at
th
e
m
o
d
el
ef
f
ec
tiv
ely
lear
n
s
r
ep
r
esen
tativ
e
lin
g
u
is
tic
p
atter
n
s
an
d
d
is
cr
im
in
ativ
e
f
ea
tu
r
es
f
r
o
m
th
e
tr
ain
in
g
d
ata.
Valid
atio
n
a
cc
u
r
ac
y
also
im
p
r
o
v
es
d
u
r
in
g
th
e
ea
r
ly
s
tag
es
o
f
tr
ain
in
g
,
r
is
in
g
f
r
o
m
8
1
.
4
%
i
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
2
,
Ap
r
il 2
0
2
6
:
1
7
6
2
-
1
7
7
0
1766
ep
o
ch
1
to
a
p
p
r
o
x
im
ately
8
6
.
8
%
b
y
ep
o
ch
4
.
T
h
is
s
u
g
g
ests
t
h
at
th
e
m
o
d
el
in
itially
g
en
er
al
izes
well
to
u
n
s
ee
n
d
ata
an
d
s
u
cc
ess
f
u
lly
ca
p
t
u
r
es r
elev
an
t c
o
n
tex
tu
al
in
f
o
r
m
ati
o
n
b
ey
o
n
d
th
e
tr
ain
in
g
s
et.
Ho
wev
er
,
af
ter
th
e
s
ec
o
n
d
ep
o
ch
,
th
e
r
ate
o
f
im
p
r
o
v
em
en
t in
v
alid
atio
n
ac
cu
r
ac
y
b
eg
i
n
s
to
s
lo
w,
an
d
a
n
o
ticea
b
le
g
ap
em
e
r
g
es
b
et
wee
n
tr
ain
in
g
an
d
v
alid
atio
n
a
cc
u
r
ac
y
s
tar
tin
g
f
r
o
m
ep
o
ch
3
.
T
h
is
d
iv
er
g
en
ce
is
in
d
icativ
e
o
f
th
e
m
o
d
el
in
c
r
e
asin
g
ly
f
itti
n
g
to
t
r
ain
in
g
-
s
p
e
cif
ic
p
atter
n
s
r
ath
er
th
an
lear
n
in
g
g
en
er
aliza
b
le
r
ep
r
esen
tatio
n
s
.
Su
ch
b
eh
av
io
r
s
u
g
g
ests
th
e
o
n
s
et
o
f
o
v
er
f
itt
in
g
,
a
co
m
m
o
n
c
h
allen
g
e
in
d
e
ep
lear
n
in
g
m
o
d
els
with
h
ig
h
r
e
p
r
esen
tatio
n
al
ca
p
ac
ity
,
p
ar
ticu
lar
ly
w
h
en
tr
ain
e
d
o
n
c
o
m
p
lex
an
d
e
m
o
tio
n
ally
n
u
an
ce
d
tex
t d
ata.
T
h
e
lo
s
s
cu
r
v
es
f
u
r
t
h
er
s
u
p
p
o
r
t
th
is
in
ter
p
r
etatio
n
.
T
r
ain
in
g
lo
s
s
d
ec
r
ea
s
es
s
h
ar
p
ly
f
r
o
m
0
.
6
9
in
th
e
f
ir
s
t
ep
o
ch
to
0
.
2
0
b
y
th
e
f
if
th
ep
o
ch
,
r
ef
lectin
g
im
p
r
o
v
ed
co
n
f
id
en
ce
an
d
c
o
r
r
ec
tn
e
s
s
in
th
e
m
o
d
el’
s
p
r
ed
ictio
n
s
o
n
t
h
e
tr
ain
i
n
g
d
at
a.
I
n
co
n
t
r
ast,
v
alid
atio
n
lo
s
s
i
n
itially
d
ec
r
ea
s
es
an
d
r
ea
ch
es
its
lo
west
v
alu
e
o
f
0
.
3
6
at
ep
o
ch
2
,
in
d
icatin
g
e
f
f
ec
tiv
e
ea
r
l
y
lear
n
in
g
an
d
g
en
er
aliza
tio
n
.
B
ey
o
n
d
th
is
p
o
in
t,
v
alid
atio
n
lo
s
s
s
h
o
ws
a
g
r
ad
u
al
in
cr
ea
s
e,
r
ea
ch
in
g
0
.
4
1
b
y
ep
o
ch
5
.
T
h
i
s
u
p
war
d
tr
en
d
,
d
esp
ite
co
n
ti
n
u
ed
r
ed
u
ctio
n
s
in
tr
ain
in
g
lo
s
s
,
r
ein
f
o
r
ce
s
ev
id
e
n
ce
o
f
o
v
er
f
itti
n
g
an
d
h
ig
h
lig
h
ts
th
e
tr
ad
e
-
o
f
f
b
etwe
en
m
o
d
el
co
m
p
lex
it
y
an
d
g
en
er
aliza
tio
n
p
er
f
o
r
m
an
ce
.
Ov
er
all,
th
ese
o
b
s
er
v
atio
n
s
s
u
g
g
est
th
at
wh
ile
th
e
L
STM
m
o
d
el
is
h
ig
h
ly
e
f
f
ec
tiv
e
i
n
lear
n
in
g
d
is
cr
im
in
ativ
e
f
ea
tu
r
es
f
r
o
m
m
en
tal
h
ea
lth
tex
t,
ca
r
ef
u
l
r
eg
u
latio
n
th
r
o
u
g
h
tech
n
i
q
u
es
s
u
ch
as
ea
r
ly
s
to
p
p
in
g
,
d
r
o
p
o
u
t,
o
r
a
r
ch
itectu
r
al
r
ef
i
n
em
en
t
is
n
ec
ess
ar
y
to
m
ain
tain
o
p
tim
al
g
en
er
aliza
tio
n
.
T
h
e
lear
n
in
g
tr
e
n
d
s
d
em
o
n
s
tr
ate
th
at
th
e
m
o
d
el
ac
h
iev
es
its
b
est
b
alan
ce
b
etwe
en
b
ias
an
d
v
ar
ian
ce
in
th
e
ea
r
lier
ep
o
ch
s
,
s
u
p
p
o
r
tin
g
th
e
u
s
e
o
f
v
alid
atio
n
-
b
ased
s
to
p
p
in
g
cr
iter
ia
in
f
u
tu
r
e
im
p
lem
e
n
tatio
n
s
.
T
h
ese
f
in
d
in
g
s
u
n
d
er
s
co
r
e
b
o
th
t
h
e
s
tr
en
g
th
s
an
d
lim
it
atio
n
s
o
f
L
STM
-
b
ased
ap
p
r
o
ac
h
es
f
o
r
m
e
n
tal
h
ea
lth
tex
t
class
if
icatio
n
an
d
p
r
o
v
id
e
a
f
o
u
n
d
atio
n
f
o
r
f
u
r
th
er
o
p
tim
izatio
n
i
n
s
u
b
s
eq
u
en
t
s
tu
d
ies.
Fig
u
r
e
1
.
Mo
d
el
ac
cu
r
ac
y
an
d
m
o
d
el
lo
s
s
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
m
o
d
el
was
ev
alu
ated
u
s
in
g
a
co
n
f
u
s
io
n
m
atr
ix
(
F
ig
u
r
e
2
)
a
n
d
a
class
if
icatio
n
r
ep
o
r
t
(
T
ab
le
1
)
d
etailin
g
th
e
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
f
o
r
ea
ch
o
f
th
e
s
ev
e
n
m
e
n
tal
h
ea
lth
-
r
elate
d
ca
teg
o
r
ies:
an
x
i
ety
,
b
ip
o
lar
,
d
ep
r
ess
io
n
,
n
o
r
m
al,
p
er
s
o
n
ality
d
is
o
r
d
e
r
,
s
tr
ess
,
an
d
s
u
icid
al.
T
h
e
co
n
f
u
s
io
n
m
atr
i
x
s
h
o
wed
s
tr
o
n
g
class
if
icatio
n
ca
p
ab
ilit
y
,
with
h
ig
h
co
r
r
ec
t
p
r
e
d
ictio
n
co
u
n
ts
alo
n
g
th
e
d
iag
o
n
al,
s
u
ch
as
3
,
1
9
7
co
r
r
e
ctly
id
en
tifie
d
ca
s
es
o
f
an
x
iet
y
,
2
,
5
5
3
o
f
b
ip
o
lar
,
an
d
3
,
0
1
1
o
f
n
o
r
m
al.
T
h
ese
r
esu
lts
wer
e
s
u
p
p
o
r
ted
b
y
h
ig
h
F1
-
s
co
r
es
f
o
r
th
o
s
e
class
es,
0
.
9
3
f
o
r
b
o
th
an
x
iety
an
d
b
ip
o
lar
,
an
d
0
.
9
2
f
o
r
n
o
r
m
al,
in
d
icatin
g
th
at
t
h
e
m
o
d
el
was b
o
th
p
r
e
cise a
n
d
co
n
s
is
ten
t in
its
p
r
ed
ictio
n
s
f
o
r
t
h
ese
ca
teg
o
r
ies.
Ho
wev
er
,
th
e
p
er
f
o
r
m
a
n
ce
was
les
s
r
o
b
u
s
t
f
o
r
d
ep
r
ess
io
n
an
d
s
u
icid
al
class
es.
T
h
e
d
ep
r
es
s
io
n
class
,
with
a
p
r
ec
is
io
n
o
f
0
.
7
1
an
d
r
ec
all
o
f
0
.
7
4
,
h
ad
an
F1
-
s
co
r
e
o
f
0
.
7
3
.
Similar
ly
,
th
e
s
u
icid
al
class
h
ad
th
e
lo
west
s
co
r
es
o
v
er
all,
with
a
p
r
ec
is
io
n
o
f
0
.
6
9
,
r
ec
all
o
f
0
.
6
8
,
an
d
an
F1
-
s
co
r
e
o
f
0
.
6
8
.
T
h
ese
f
in
d
in
g
s
co
r
r
esp
o
n
d
with
p
atter
n
s
o
b
s
e
r
v
ed
in
th
e
c
o
n
f
u
s
io
n
m
atr
ix
,
wh
er
e
d
ep
r
ess
io
n
was
f
r
eq
u
e
n
tly
co
n
f
u
s
ed
with
s
u
icid
al
(
6
0
6
in
s
tan
ce
s
)
,
a
n
d
s
u
icid
al
in
s
tan
ce
s
wer
e
also
m
is
class
if
ied
as
d
ep
r
ess
io
n
(
6
3
7
)
an
d
ev
e
n
as
n
o
r
m
al
(
7
5
)
.
T
h
is
m
is
class
if
ic
atio
n
is
p
ar
ticu
lar
ly
cr
itical
in
m
en
tal
h
ea
lth
s
cr
ee
n
in
g
,
wh
er
e
f
alse
n
eg
ativ
es
in
id
en
tify
in
g
s
u
icid
al
i
d
ea
tio
n
c
o
u
ld
lead
t
o
s
er
io
u
s
co
n
s
eq
u
en
ce
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Dee
p
lea
r
n
in
g
fo
r
men
ta
l
h
ea
l
th
a
n
a
lysi
s
:
lo
n
g
s
h
o
r
t
-
term me
mo
r
y
a
p
p
r
o
a
ch
to
…
(
Za
q
q
i
Ya
ma
n
i
)
1767
Fig
u
r
e
2
.
C
o
n
f
u
s
io
n
m
atr
i
x
o
f
th
e
m
o
d
el
f
o
r
s
ev
en
m
en
tal
h
e
alth
ca
teg
o
r
ies
T
ab
le
1
.
C
lass
if
icatio
n
r
ep
o
r
t
o
f
th
e
m
o
d
el
f
o
r
s
ev
en
m
en
tal
h
ea
lth
ca
teg
o
r
ies
P
e
r
so
n
a
l
i
t
y
d
i
so
r
d
e
r
c
a
t
e
g
o
r
y
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
s
c
o
r
e
S
u
p
p
o
r
t
A
n
x
i
e
t
y
0
.
9
4
0
.
9
2
0
.
9
3
3
4
9
2
B
i
p
o
l
a
r
0
.
9
4
0
.
9
2
0
.
9
3
2
7
6
4
D
e
p
r
e
ss
i
o
n
0
.
7
1
0
.
7
4
0
.
7
3
3
1
8
6
N
o
r
mal
0
.
9
0
0
.
9
3
0
.
9
2
3
2
2
3
P
e
r
so
n
a
l
i
t
y
d
i
so
r
d
e
r
0
.
9
5
0
.
9
6
0
.
9
6
2
8
2
3
S
t
r
e
ss
0
.
9
1
0
.
8
9
0
.
9
0
2
9
6
3
S
u
i
c
i
d
a
l
0
.
6
9
0
.
6
8
0
.
6
8
2
2
4
7
A
c
c
u
r
a
c
y
0
.
8
7
2
0
6
9
8
M
a
c
r
o
a
v
g
0
.
8
6
0
.
8
6
0
.
8
6
0
.
8
6
W
e
i
g
h
t
e
d
a
v
g
0
.
8
7
0
.
8
7
0
.
8
7
2
0
6
9
8
T
h
e
m
o
d
el
p
er
f
o
r
m
e
d
b
est
o
n
th
e
p
er
s
o
n
ality
d
is
o
r
d
er
ca
te
g
o
r
y
,
ac
h
iev
in
g
th
e
h
ig
h
est
F1
-
s
co
r
e
o
f
0
.
9
6
,
alo
n
g
with
a
p
r
ec
is
io
n
an
d
r
ec
all
o
f
0
.
9
5
an
d
0
.
9
6
,
r
esp
ec
tiv
ely
.
Stre
s
s
also
s
h
o
wed
s
tr
o
n
g
m
etr
ics
(
F1
-
s
co
r
e
o
f
0
.
9
0
)
,
alth
o
u
g
h
th
er
e
was
s
o
m
e
co
n
f
u
s
io
n
with
an
x
iety
a
n
d
d
e
p
r
ess
io
n
class
es,
ag
ain
lik
ely
d
u
e
to
o
v
er
lap
p
in
g
s
y
m
p
to
m
ato
l
o
g
y
.
T
h
e
m
ac
r
o
av
er
a
g
e
(
0
.
8
6
)
an
d
weig
h
te
d
av
er
a
g
e
(
0
.
8
7
)
F1
-
s
co
r
es
co
n
f
ir
m
th
at
th
e
m
o
d
el
g
en
e
r
alize
s
well
ac
r
o
s
s
m
u
ltip
le
class
e
s
with
o
u
t
b
ein
g
s
k
ewe
d
h
ea
v
ily
b
y
a
n
y
s
in
g
le
ca
teg
o
r
y
.
T
h
e
r
esu
lts
s
u
g
g
est
th
at
th
e
m
o
d
el
is
h
ig
h
ly
ca
p
ab
le
o
f
d
is
ti
n
g
u
is
h
in
g
b
etwe
en
clea
r
l
y
d
ef
in
ed
ca
teg
o
r
ies
lik
e
n
o
r
m
al,
p
er
s
o
n
ality
d
is
o
r
d
e
r
,
an
d
a
n
x
iety
,
b
u
t
s
tr
u
g
g
les
m
o
r
e
with
s
em
a
n
tically
an
d
cli
n
ically
o
v
e
r
lap
p
in
g
class
es
s
u
ch
as
d
ep
r
ess
io
n
an
d
s
u
icid
al
id
ea
tio
n
.
T
o
ad
d
r
es
s
th
ese
lim
itatio
n
s
,
f
u
tu
r
e
wo
r
k
s
h
o
u
ld
f
o
cu
s
o
n
im
p
r
o
v
in
g
class
s
ep
ar
atio
n
th
r
o
u
g
h
s
tr
ateg
ies
s
u
ch
as
d
o
m
ai
n
-
s
p
ec
if
ic
p
r
etr
ai
n
in
g
,
h
ier
ar
c
h
ical
class
if
icatio
n
s
ch
em
es,
an
d
th
e
in
teg
r
atio
n
o
f
co
n
tex
tu
al
o
r
s
eq
u
en
tial
f
e
atu
r
es.
Fu
r
th
er
m
o
r
e,
a
p
p
ly
in
g
class
weig
h
tin
g
o
r
f
o
ca
l lo
s
s
m
ay
h
elp
e
n
h
an
ce
p
er
f
o
r
m
a
n
ce
o
n
m
in
o
r
ity
o
r
h
ig
h
-
r
is
k
class
es lik
e
s
u
icid
al.
C
o
m
p
ar
ed
to
r
esu
lts
r
ep
o
r
te
d
in
p
r
i
o
r
m
en
tal
h
ea
lth
tex
t
class
if
icatio
n
s
tu
d
ies
u
s
in
g
tr
ad
itio
n
al
m
ac
h
in
e
lear
n
in
g
o
r
s
h
allo
w
n
eu
r
al
m
o
d
els,
th
e
p
r
o
p
o
s
ed
L
STM
f
r
am
ewo
r
k
d
em
o
n
s
tr
at
es
co
m
p
etitiv
e
an
d
o
f
ten
s
u
p
er
io
r
p
er
f
o
r
m
a
n
ce
,
p
ar
ticu
lar
ly
f
o
r
an
x
iety
,
p
e
r
s
o
n
ality
d
is
o
r
d
er
,
an
d
n
o
r
m
al
cla
s
s
es.
T
h
e
ab
ilit
y
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
2
,
Ap
r
il 2
0
2
6
:
1
7
6
2
-
1
7
7
0
1768
L
STM
to
ca
p
t
u
r
e
s
eq
u
en
tial
s
em
an
tic
cu
es
c
o
n
tr
ib
u
tes
to
im
p
r
o
v
e
d
d
is
cr
im
in
atio
n
am
o
n
g
class
es
with
clea
r
er
lin
g
u
is
tic
p
atter
n
s
.
Ho
wev
er
,
r
ed
u
ce
d
p
er
f
o
r
m
a
n
ce
f
o
r
d
e
p
r
ess
io
n
an
d
s
u
icid
al
id
ea
tio
n
al
ig
n
s
with
p
r
ev
i
o
u
s
f
in
d
in
g
s
th
at
th
ese
ca
teg
o
r
ie
s
ex
h
ib
it
h
ig
h
s
em
an
tic
an
d
em
o
tio
n
al
o
v
er
la
p
.
T
h
is
s
u
g
g
ests
th
at
f
u
tu
r
e
im
p
r
o
v
em
e
n
ts
m
ay
r
eq
u
ir
e
h
y
b
r
id
ar
c
h
itectu
r
es,
atten
tio
n
m
ec
h
an
is
m
s
,
o
r
d
o
m
ai
n
-
s
p
e
cif
ic
p
r
etr
ain
in
g
to
en
h
an
ce
s
en
s
itiv
ity
f
o
r
h
ig
h
-
r
i
s
k
class
es.
4.
CO
NCLU
SI
O
N
T
h
i
s
w
o
r
k
e
v
a
l
u
a
t
ed
L
S
T
M
a
r
c
h
i
t
ec
t
u
r
e
d
e
s
i
g
n
ed
f
o
r
th
e
c
l
a
s
s
i
f
i
c
a
t
io
n
o
f
t
ex
t
u
a
l
a
v
a
t
a
r
s
o
f
m
e
n
t
a
l
h
e
a
l
th
s
t
a
t
e
s
.
V
i
a
c
u
s
to
m
-
d
e
s
i
g
n
e
d
d
ee
p
-
le
a
r
n
i
n
g
m
e
t
h
o
d
s
,
th
e
ar
c
h
i
te
c
t
u
r
e
d
e
v
e
lo
p
ed
th
e
ab
i
l
i
t
y
t
o
d
i
f
f
e
r
en
t
i
a
t
e
i
n
to
th
e
f
o
l
l
o
w
in
g
s
e
v
en
d
i
ag
n
o
s
t
i
c
m
a
n
if
o
ld
s
:
a
n
x
i
e
t
y
,
b
i
p
o
l
a
r
d
i
s
o
r
d
e
r
,
d
e
p
r
e
s
s
i
o
n
,
n
o
r
m
a
l,
p
e
r
s
o
n
a
l
i
ty
d
i
s
o
r
d
er
,
s
t
r
e
s
s
,
a
n
d
s
u
i
c
id
a
l
i
d
e
a
t
i
o
n
b
y
r
e
l
y
in
g
ex
c
l
u
s
iv
e
l
y
o
n
f
e
a
tu
r
e
s
d
er
i
v
ed
f
r
o
m
u
s
e
r
-
g
e
n
e
r
a
t
ed
wr
i
t
t
e
n
t
ex
t
.
O
n
th
e
q
u
an
t
i
t
a
t
iv
e
ev
a
lu
a
t
i
o
n
,
s
tr
o
n
g
p
er
f
o
r
m
an
c
e
i
n
m
o
s
t
d
i
a
g
n
o
s
t
i
c
l
an
e
s
w
a
s
o
b
s
er
v
ed
;
b
o
th
p
r
ec
i
s
i
o
n
a
n
d
r
e
c
a
l
l
(
o
v
er
a
l
l
a
n
d
l
an
e
-
s
p
e
c
i
f
ic
)
f
o
r
th
e
p
er
s
o
n
a
l
i
t
y
d
i
s
o
r
d
er
,
a
n
x
i
e
t
y
,
a
n
d
n
o
r
m
a
l
s
t
a
t
e
s
w
er
e
g
en
e
r
a
l
ly
h
i
g
h
a
cr
o
s
s
a
l
l
ex
p
e
r
i
m
en
t
a
l
s
e
t
t
in
g
s
.
N
o
n
e
t
h
e
le
s
s
,
t
h
e
c
l
a
s
s
i
f
i
e
r
e
n
c
o
u
n
te
r
ed
p
e
r
s
i
s
t
e
n
t
d
if
f
i
cu
l
t
y
in
s
ep
a
r
a
t
in
g
d
e
p
r
e
s
s
i
o
n
f
r
o
m
s
u
i
c
i
d
a
l
i
d
e
a
t
i
o
n
,
y
i
e
ld
i
n
g
a
p
r
o
n
o
u
n
c
ed
c
r
o
s
s
-
co
n
t
am
i
n
a
t
io
n
o
f
p
r
ed
ic
t
i
o
n
s
b
e
t
w
e
en
th
e
t
wo
d
i
ag
n
o
s
t
i
c
a
l
ly
p
r
o
x
i
m
a
t
e
c
at
e
g
o
r
i
e
s
.
T
h
e
s
e
r
e
s
u
l
t
s
u
n
d
e
r
s
c
o
r
e
t
h
e
ch
a
l
l
e
n
g
e
o
f
e
n
c
o
d
i
n
g
s
u
b
t
l
e
p
s
y
c
h
o
l
o
g
i
ca
l
g
r
a
d
ie
n
t
s
f
r
o
m
t
e
x
tu
a
l
d
a
ta
a
n
d
i
n
d
i
c
a
t
e
t
h
a
t
t
h
e
i
n
t
eg
r
a
t
i
o
n
o
f
b
r
o
ad
e
r
c
o
n
t
ex
t
u
a
l
a
w
a
r
e
n
e
s
s
w
i
l
l
li
k
e
l
y
b
e
n
e
c
e
s
s
a
r
y
f
o
r
f
in
e
r
d
i
s
c
r
i
m
i
n
a
t
i
o
n
.
W
h
i
l
e
t
h
e
o
v
er
a
l
l
a
r
ch
i
t
e
c
tu
r
e
w
a
s
e
f
f
e
c
t
i
v
e
,
i
t
s
p
o
i
n
t
s
o
f
f
a
i
l
u
r
e
s
i
g
n
a
l
t
h
e
im
p
o
r
t
an
c
e
o
f
e
m
b
e
d
d
i
n
g
d
i
s
c
i
p
l
i
n
e
-
s
p
ec
i
f
i
c
k
n
o
w
l
ed
g
e
,
en
h
an
c
in
g
t
h
e
i
n
t
eg
r
i
ty
o
f
th
e
tr
a
i
n
in
g
c
o
r
p
u
s
,
a
n
d
d
e
p
lo
y
i
n
g
co
n
t
em
p
o
r
ar
y
t
e
c
h
n
iq
u
e
s
.
T
h
e
L
S
T
M
-
c
e
n
t
e
r
e
d
a
p
p
r
o
a
c
h
d
e
m
o
n
s
tr
a
t
es
t
a
n
g
ib
l
e
p
o
t
en
t
i
a
l
f
o
r
e
x
p
e
d
i
t
in
g
b
o
th
t
h
e
i
d
e
n
t
if
i
c
a
t
i
o
n
a
n
d
c
l
a
s
s
i
f
i
c
a
ti
o
n
o
f
m
e
n
t
a
l
h
e
a
l
t
h
co
n
d
it
i
o
n
s
a
s
i
n
f
e
r
r
ed
f
r
o
m
l
a
n
g
u
a
g
e
d
a
t
a
.
A
s
a
p
r
o
o
f
-
of
-
c
o
n
c
e
p
t
s
t
r
a
te
g
y
,
i
t
m
ay
s
er
v
e
a
s
a
f
o
u
n
d
a
t
io
n
a
l
i
n
cr
e
m
en
t
t
o
w
ar
d
f
u
t
u
r
e
,
t
ex
t
-
b
a
s
e
d
d
i
ag
n
o
s
t
i
c
t
o
o
l
s
th
a
t
c
o
m
p
l
e
m
e
n
t
c
l
i
n
i
c
ia
n
s
’
ev
a
lu
a
t
i
v
e
ex
p
er
t
i
s
e
.
R
ea
l
i
z
i
n
g
t
h
i
s
p
o
t
e
n
t
i
a
l,
n
o
n
e
t
h
el
e
s
s
,
d
ep
e
n
d
s
u
p
o
n
c
a
r
e
f
u
l
n
a
v
ig
a
t
i
o
n
o
f
e
th
i
c
a
l
c
o
n
s
i
d
e
r
a
t
io
n
s
,
r
o
b
u
s
t
d
a
t
a
p
r
o
t
e
c
t
i
o
n
p
r
o
to
co
l
s
,
an
d
an
o
n
g
o
i
n
g
co
m
m
i
t
m
en
t
t
o
m
o
d
e
l
t
r
an
s
p
ar
e
n
cy
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
es
ea
r
c
h
r
ec
e
iv
e
d
n
o
s
p
e
c
if
i
c
g
r
a
n
t
f
r
o
m
a
n
y
f
u
n
d
in
g
a
g
en
cy
,
c
o
m
m
e
r
c
ial
,
o
r
n
o
n
-
p
r
o
f
it
-
s
ec
t
o
r
s
.
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
Z
aq
q
i Y
am
an
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
Din
d
a
L
estar
in
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
Sar
if
ah
Pu
tr
i Raf
lesi
a
✓
✓
✓
✓
✓
✓
✓
✓
Pu
r
wita
Sar
i
✓
✓
✓
✓
✓
✓
Gh
ita
Ath
alin
a
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
t
h
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
a
r
e
av
ailab
l
e
f
r
o
m
t
h
e
co
r
r
esp
o
n
d
in
g
a
u
th
o
r
,
[
PS
]
,
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
est.
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
Dee
p
lea
r
n
in
g
fo
r
men
ta
l
h
ea
l
th
a
n
a
lysi
s
:
lo
n
g
s
h
o
r
t
-
term me
mo
r
y
a
p
p
r
o
a
ch
to
…
(
Za
q
q
i
Ya
ma
n
i
)
1769
RE
F
E
R
E
NC
E
S
[
1
]
P
.
M
.
K
u
mar
e
t
a
l
.
,
“
E
p
i
d
e
m
i
o
l
o
g
y
a
n
d
r
i
sk
f
a
c
t
o
r
s
o
f
men
t
a
l
d
i
s
o
r
d
e
r
s,”
i
n
A
R
e
v
i
e
w
o
n
D
i
v
e
rse
N
e
u
ro
l
o
g
i
c
a
l
D
i
so
r
d
e
r
s:
Pa
t
h
o
p
h
y
si
o
l
o
g
y
,
M
o
l
e
c
u
l
a
r
Me
c
h
a
n
i
sm
s,
a
n
d
T
h
e
r
a
p
e
u
t
i
c
s
,
A
c
a
d
e
mi
c
P
r
e
ss,
2
0
2
4
,
p
p
.
3
–
12
,
d
o
i
:
1
0
.
1
0
1
6
/
B
9
7
8
-
0
-
323
-
9
5
7
3
5
-
9
.
0
0
0
0
3
-
6.
[
2
]
W
o
r
l
d
H
e
a
l
t
h
O
r
g
a
n
i
z
a
t
i
o
n
,
Wo
r
l
d
m
e
n
t
a
l
h
e
a
l
t
h
re
p
o
rt
:
T
r
a
n
sf
o
rm
i
n
g
m
e
n
t
a
l
h
e
a
l
t
h
f
o
r
a
l
l
.
G
e
n
e
v
a
,
S
w
i
t
z
e
r
l
a
n
d
:
W
H
O
,
2
0
2
3
.
[
3
]
E.
G
.
L
a
t
t
i
e
,
C
.
S
.
-
S
h
i
e
l
d
s
,
a
n
d
A
.
K
.
G
r
a
h
a
m
,
“
A
n
o
v
e
r
v
i
e
w
o
f
a
n
d
r
e
c
o
mm
e
n
d
a
t
i
o
n
s
f
o
r
m
o
r
e
a
c
c
e
ssi
b
l
e
d
i
g
i
t
a
l
me
n
t
a
l
h
e
a
l
t
h
serv
i
c
e
s
,
”
N
a
t
u
re
Re
v
i
e
w
s
Psy
c
h
o
l
o
g
y
,
v
o
l
.
1
,
n
o
.
2
,
p
p
.
8
7
–
1
0
0
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
4
1
5
9
-
0
2
1
-
0
0
0
0
3
-
1.
[
4
]
P
.
D
.
M
c
G
o
r
r
y
,
C
.
M
e
i
,
A
.
C
h
a
n
e
n
,
C
.
H
o
d
g
e
s,
M
.
A
.
-
Ji
m
e
n
e
z
,
a
n
d
E.
K
i
l
l
a
c
k
e
y
,
“
D
e
s
i
g
n
i
n
g
a
n
d
sc
a
l
i
n
g
u
p
i
n
t
e
g
r
a
t
e
d
y
o
u
t
h
men
t
a
l
h
e
a
l
t
h
c
a
r
e
,
”
W
o
rl
d
Ps
y
c
h
i
a
t
ry
,
v
o
l
.
2
1
,
n
o
.
1
,
p
p
.
6
1
–
7
6
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
2
/
w
p
s.
2
0
9
3
8
.
[
5
]
N
.
C
.
C
o
o
m
b
s
,
W
.
E.
M
e
r
i
w
e
t
h
e
r
,
J.
C
a
r
i
n
g
i
,
a
n
d
S
.
R
.
N
e
w
c
o
m
e
r
,
“
B
a
r
r
i
e
r
s
t
o
h
e
a
l
t
h
c
a
r
e
a
c
c
e
ss
a
mo
n
g
U
.
S
.
a
d
u
l
t
s
w
i
t
h
m
e
n
t
a
l
h
e
a
l
t
h
c
h
a
l
l
e
n
g
e
s
:
a
p
o
p
u
l
a
t
i
o
n
-
b
a
s
e
d
st
u
d
y
,
”
S
S
M
-
P
o
p
u
l
a
t
i
o
n
H
e
a
l
t
h
,
v
o
l
.
1
5
,
S
e
p
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
ssm
p
h
.
2
0
2
1
.
1
0
0
8
4
7
.
[
6
]
X
.
X
u
a
n
d
T.
Z
h
a
n
g
,
“
I
n
t
e
l
l
i
g
e
n
t
c
l
a
ssi
f
i
c
a
t
i
o
n
a
n
d
p
r
e
d
i
c
t
i
o
n
o
f
st
u
d
e
n
t
s
’
men
t
a
l
h
e
a
l
t
h
i
n
o
n
l
i
n
e
l
e
a
r
n
i
n
g
e
n
v
i
r
o
n
m
e
n
t
s
u
si
ng
b
o
o
s
t
i
n
g
a
l
g
o
r
i
t
h
m
a
n
d
LI
W
C
f
e
a
t
u
r
e
s,”
S
c
i
e
n
t
i
f
i
c
Re
p
o
r
t
s
,
v
o
l
.
1
5
,
n
o
.
1
,
D
e
c
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
5
-
0
4
6
8
1
-
2.
[
7
]
E.
O
h
,
J.
C
h
o
,
C
.
K
i
m,
H
.
L
i
m,
a
n
d
K
.
N
.
K
i
m,
“
I
d
e
n
t
i
f
y
i
n
g
f
a
c
t
o
r
s
a
ss
o
c
i
a
t
e
d
w
i
t
h
m
e
n
t
a
l
h
e
a
l
t
h
st
a
t
u
s
f
o
l
l
o
w
i
n
g
c
l
i
m
a
t
e
-
r
e
l
a
t
e
d
d
i
s
a
st
e
r
s:
a
n
a
t
i
o
n
w
i
d
e
l
o
n
g
i
t
u
d
i
n
a
l
p
a
n
e
l
s
t
u
d
y
i
n
K
o
r
e
a
,
”
E
p
i
d
e
m
i
o
l
o
g
y
a
n
d
H
e
a
l
t
h
,
v
o
l
.
4
7
,
2
0
2
5
,
d
o
i
:
1
0
.
4
1
7
8
/
e
p
i
h
.
e
2
0
2
5
0
1
4
.
[
8
]
M
.
C
.
-
L
y
o
n
,
A
.
C
a
r
t
e
r
,
M
.
M
a
n
u
e
l
i
t
o
,
K
.
B
e
l
g
a
r
d
e
,
a
n
d
M
.
M
a
r
t
i
n
,
“
R
a
c
i
a
l
m
i
sc
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
A
meri
c
a
n
I
n
d
i
a
n
a
n
d
A
l
a
s
k
a
n
n
a
t
i
v
e
s
o
n
d
e
a
t
h
c
e
r
t
i
f
i
c
a
t
e
s
i
n
t
h
e
U
n
i
t
e
d
S
t
a
t
e
s
,
”
R
e
p
o
r
t
f
o
r
N
a
t
i
o
n
a
l
N
e
t
w
o
rk
o
f
Pu
b
l
i
c
H
e
a
l
t
h
I
n
s
t
i
t
u
t
e
s
,
2
0
2
4
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
c
o
mm
o
n
s.
u
n
d
.
e
d
u
/
i
h
-
f
a
c
/
3
0
[
9
]
L.
B
r
a
d
l
e
y
,
R
.
S
h
a
w
,
S
.
B
.
-
C
o
h
e
n
,
a
n
d
S
.
C
a
ss
i
d
y
,
“
A
u
t
i
st
i
c
a
d
u
l
t
s’
e
x
p
e
r
i
e
n
c
e
s
o
f
c
a
m
o
u
f
l
a
g
i
n
g
a
n
d
i
t
s
p
e
r
c
e
i
v
e
d
i
mp
a
c
t
o
n
men
t
a
l
h
e
a
l
t
h
,
”
A
u
t
i
sm
i
n
A
d
u
l
t
h
o
o
d
,
v
o
l
.
3
,
n
o
.
4
,
p
p
.
3
2
0
–
3
2
9
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
8
9
/
a
u
t
.
2
0
2
0
.
0
0
7
1
.
[
1
0
]
A
.
A
.
A
h
a
d
,
M
.
S
.
-
G
o
n
z
a
l
e
z
,
a
n
d
P
.
J
u
n
q
u
e
r
a
,
“
U
n
d
e
r
st
a
n
d
i
n
g
a
n
d
a
d
d
r
e
ss
i
n
g
m
e
n
t
a
l
h
e
a
l
t
h
st
i
g
ma
a
c
r
o
ss c
u
l
t
u
r
e
s
f
o
r
i
m
p
r
o
v
i
n
g
p
sy
c
h
i
a
t
r
i
c
c
a
r
e
:
a
n
a
r
r
a
t
i
v
e
r
e
v
i
e
w
,
”
C
u
r
e
u
s
,
M
a
y
2
0
2
3
,
d
o
i
:
1
0
.
7
7
5
9
/
c
u
r
e
u
s.
3
9
5
4
9
.
[
1
1
]
J.
Tr
o
u
p
,
D
.
C
.
F
u
h
r
,
A
.
W
o
o
d
w
a
r
d
,
E.
S
o
n
d
o
r
p
,
a
n
d
B
.
R
o
b
e
r
t
s,
“
B
a
r
r
i
e
r
s
a
n
d
f
a
c
i
l
i
t
a
t
o
r
s
f
o
r
sc
a
l
i
n
g
u
p
m
e
n
t
a
l
h
e
a
l
t
h
a
n
d
p
sy
c
h
o
s
o
c
i
a
l
s
u
p
p
o
r
t
i
n
t
e
r
v
e
n
t
i
o
n
s
i
n
l
o
w
-
a
n
d
mi
d
d
l
e
-
i
n
c
o
m
e
c
o
u
n
t
r
i
e
s
f
o
r
p
o
p
u
l
a
t
i
o
n
s
a
f
f
e
c
t
e
d
b
y
h
u
ma
n
i
t
a
r
i
a
n
c
r
i
ses
:
a
sy
st
e
ma
t
i
c
r
e
v
i
e
w
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
M
e
n
t
a
l
H
e
a
l
t
h
S
y
s
t
e
m
s
,
v
o
l
.
1
5
,
n
o
.
1
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
8
6
/
s1
3
0
3
3
-
0
2
0
-
0
0
4
3
1
-
1.
[
1
2
]
C
.
E
.
O
k
e
c
h
u
k
w
u
,
“
A
c
a
l
l
f
o
r
i
m
p
r
o
v
e
d
me
n
t
a
l
h
e
a
l
t
h
w
o
r
k
f
o
r
c
e
i
n
l
o
w
-
i
n
c
o
me
c
o
u
n
t
r
i
e
s,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
S
o
c
i
a
l
Psy
c
h
i
a
t
r
y
,
v
o
l
.
6
8
,
n
o
.
2
,
p
p
.
4
6
5
–
4
6
7
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
7
7
/
0
0
2
0
7
6
4
0
2
1
1
0
3
9
2
5
5
.
[
1
3
]
P
.
T.
D
.
Le
e
t
a
l
.
,
“
B
a
r
r
i
e
r
s
a
n
d
f
a
c
i
l
i
t
a
t
o
r
s
t
o
i
mp
l
e
m
e
n
t
a
t
i
o
n
o
f
e
v
i
d
e
n
c
e
-
b
a
s
e
d
t
a
sk
-
s
h
a
r
i
n
g
me
n
t
a
l
h
e
a
l
t
h
i
n
t
e
r
v
e
n
t
i
o
n
s
i
n
l
o
w
-
a
n
d
m
i
d
d
l
e
-
i
n
c
o
me
c
o
u
n
t
r
i
e
s
:
a
s
y
st
e
mat
i
c
r
e
v
i
e
w
u
si
n
g
i
mp
l
e
m
e
n
t
a
t
i
o
n
s
c
i
e
n
c
e
f
r
a
m
e
w
o
r
k
s,”
I
m
p
l
e
m
e
n
t
a
t
i
o
n
S
c
i
e
n
c
e
,
v
o
l
.
1
7
,
n
o
.
1
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
8
6
/
s
1
3
0
1
2
-
0
2
1
-
0
1
1
7
9
-
z.
[
1
4
]
M
.
C
o
l
i
z
z
i
,
A
.
L
a
sa
l
v
i
a
,
a
n
d
M
.
R
u
g
g
e
r
i
,
“
P
r
e
v
e
n
t
i
o
n
a
n
d
e
a
r
l
y
i
n
t
e
r
v
e
n
t
i
o
n
i
n
y
o
u
t
h
me
n
t
a
l
h
e
a
l
t
h
:
I
s
i
t
t
i
me
f
o
r
a
mu
l
t
i
d
i
s
c
i
p
l
i
n
a
r
y
a
n
d
t
r
a
n
s
-
d
i
a
g
n
o
st
i
c
m
o
d
e
l
f
o
r
c
a
r
e
?
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
M
e
n
t
a
l
H
e
a
l
t
h
S
y
s
t
e
m
s
,
v
o
l
.
1
4
,
n
o
.
1
,
M
a
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
8
6
/
s
1
3
0
3
3
-
0
2
0
-
0
0
3
5
6
-
9.
[
1
5
]
A
.
S
t
a
i
n
t
o
n
,
A
.
C
h
a
n
e
n
,
C
.
D
a
v
e
y
,
G
.
B
e
d
i
,
P
.
D
.
M
c
G
o
r
r
y
,
a
n
d
E.
B
r
o
w
n
,
“
Ea
r
l
y
i
n
t
e
r
v
e
n
t
i
o
n
a
c
r
o
ss
m
e
n
t
a
l
h
e
a
l
t
h
ser
v
i
c
e
s
,
”
i
n
T
a
sm
a
n
’
s
p
s
y
c
h
i
a
t
r
y
,
F
i
f
t
h
Ed
i
t
i
o
n
,
C
h
a
m:
S
p
r
i
n
g
e
r
I
n
t
e
r
n
a
t
i
o
n
a
l
P
u
b
l
i
s
h
i
n
g
,
2
0
2
4
,
p
p
.
3
4
9
1
–
3
5
1
8
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
0
-
5
1
3
6
6
-
5
_
1
7
1
.
[
1
6
]
D
.
H
a
r
r
i
s,
“
E
x
p
l
o
r
i
n
g
d
i
g
i
t
a
l
a
f
f
o
r
d
a
n
c
e
s
i
n
o
n
l
i
n
e
m
e
n
t
a
l
h
e
a
l
t
h
r
e
so
u
r
c
e
s:
a
sco
p
i
n
g
r
e
v
i
e
w
o
f
me
t
h
o
d
o
l
o
g
i
e
s
a
n
d
p
o
p
u
l
a
t
i
o
n
s,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
H
u
m
a
n
-
C
o
m
p
u
t
e
r
I
n
t
e
r
a
c
t
i
o
n
,
v
o
l
.
4
1
,
n
o
.
1
0
,
p
p
.
6
0
8
9
–
6
1
0
5
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
8
0
/
1
0
4
4
7
3
1
8
.
2
0
2
4
.
2
3
7
5
6
8
7
.
[
1
7
]
H
.
L
e
e
,
“
C
h
a
n
g
e
s
i
n
w
o
r
k
p
l
a
c
e
p
r
a
c
t
i
c
e
s
d
u
r
i
n
g
t
h
e
C
O
V
I
D
-
1
9
p
a
n
d
e
mi
c
:
t
h
e
r
o
l
e
s
o
f
e
m
o
t
i
o
n
,
p
s
y
c
h
o
l
o
g
i
c
a
l
s
a
f
e
t
y
a
n
d
o
r
g
a
n
i
sa
t
i
o
n
su
p
p
o
r
t
,
”
J
o
u
r
n
a
l
o
f
O
r
g
a
n
i
za
t
i
o
n
a
l
E
f
f
e
c
t
i
v
e
n
e
ss
,
v
o
l
.
8
,
n
o
.
1
,
p
p
.
9
7
–
1
2
8
,
F
e
b
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
8
/
JO
EPP
-
06
-
2
0
2
0
-
0
1
0
4
.
[
1
8
]
J.
W
r
i
g
h
t
a
n
d
J.
Ja
y
a
w
i
c
k
r
a
m
a
,
“
'
W
e
n
e
e
d
o
t
h
e
r
h
u
m
a
n
b
e
i
n
g
s
i
n
o
r
d
e
r
t
o
b
e
h
u
ma
n
’
:
e
x
a
m
i
n
i
n
g
t
h
e
i
n
d
i
g
e
n
o
u
s
p
h
i
l
o
s
o
p
h
y
o
f
u
mu
n
t
h
u
a
n
d
st
r
e
n
g
t
h
e
n
i
n
g
m
e
n
t
a
l
h
e
a
l
t
h
i
n
t
e
r
v
e
n
t
i
o
n
s,
”
C
u
l
t
u
r
e
,
M
e
d
i
c
i
n
e
a
n
d
Psy
c
h
i
a
t
r
y
,
v
o
l
.
4
5
,
n
o
.
4
,
p
p
.
6
1
3
–
6
2
8
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
1
3
-
0
2
0
-
0
9
6
9
2
-
4.
[
1
9
]
G
.
J
u
n
,
“
P
sy
c
h
o
l
o
g
i
c
a
l
a
n
d
m
e
n
t
a
l
h
e
a
l
t
h
e
v
a
l
u
a
t
i
o
n
o
f
E
n
g
l
i
sh
l
a
n
g
u
a
g
e
st
u
d
e
n
t
s
u
si
n
g
r
e
c
u
r
r
e
n
t
n
e
u
r
a
l
n
e
t
w
o
r
k
s,
”
M
o
b
i
l
e
N
e
t
w
o
rks
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
1
0
3
6
-
024
-
0
2
3
8
5
-
x.
[
2
0
]
P
.
G
u
n
h
a
l
,
“
S
e
ma
n
t
i
c
c
o
h
e
r
e
n
c
e
a
n
d
N
LP:
r
e
d
e
si
g
n
i
n
g
p
o
st
-
C
O
V
I
D
men
t
a
l
h
e
a
l
t
h
d
i
a
g
n
o
st
i
c
s
w
i
t
h
C
N
N
s
a
n
d
LST
M
s,
”
Asi
a
n
J
o
u
rn
a
l
o
f
c
o
n
v
e
r
g
e
n
c
e
i
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
0
,
n
o
.
3
,
p
p
.
1
–
7
,
2
0
2
4
,
d
o
i
:
1
0
.
3
3
1
3
0
/
a
j
c
t
.
2
0
2
4
v
1
0
i
0
3
.
0
0
2
.
[
2
1
]
S
.
A
l
l
a
d
i
a
n
d
B
.
B
,
“
C
o
g
n
i
t
e
x
t
@
D
r
a
v
i
d
i
a
n
La
n
g
Te
c
h
2
0
2
5
:
f
a
k
e
n
e
w
s
c
l
a
s
si
f
i
c
a
t
i
o
n
i
n
M
a
l
a
y
a
l
a
m
u
s
i
n
g
mBE
R
T
a
n
d
LST
M
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
D
ra
v
i
d
i
a
n
L
a
n
g
T
e
c
h
2
0
2
5
,
2
0
2
5
,
p
p
.
3
6
1
–
365
,
d
o
i
:
1
0
.
1
8
6
5
3
/
v
1
/
2
0
2
5
.
d
r
a
v
i
d
i
a
n
l
a
n
g
t
e
c
h
-
1
.
6
4
.
[
2
2
]
S
.
V
e
l
a
m
p
a
l
l
i
,
C
.
M
u
n
i
y
a
p
p
a
,
a
n
d
A
.
S
a
x
e
n
a
,
“
P
e
r
f
o
r
ma
n
c
e
e
v
a
l
u
a
t
i
o
n
o
f
s
e
n
t
i
m
e
n
t
a
n
a
l
y
s
i
s
o
n
t
e
x
t
a
n
d
e
m
o
j
i
d
a
t
a
u
si
n
g
e
n
d
-
to
-
e
n
d
,
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
,
d
i
s
t
r
i
b
u
t
e
d
a
n
d
e
x
p
l
a
i
n
a
b
l
e
A
I
mo
d
e
l
s
,
”
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
s
i
n
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
3
,
n
o
.
2
,
p
p
.
1
6
7
–
1
7
2
,
A
p
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
2
7
2
0
/
j
a
i
t
.
1
3
.
2
.
1
6
7
-
1
7
2
.
[
2
3
]
L.
A
.
A
.
-
S
a
e
n
z
,
J.
I
.
-
R
e
y
e
s,
a
n
d
R
.
B
.
-
B
e
l
l
o
,
“
E
x
p
l
o
r
i
n
g
si
n
g
l
e
-
h
e
a
d
a
n
d
mu
l
t
i
-
h
e
a
d
C
N
N
a
n
d
LST
M
-
b
a
se
d
mo
d
e
l
s
f
o
r
r
o
a
d
su
r
f
a
c
e
c
l
a
s
si
f
i
c
a
t
i
o
n
u
si
n
g
o
n
-
b
o
a
r
d
v
e
h
i
c
l
e
m
u
l
t
i
-
I
M
U
d
a
t
a
,
”
S
c
i
e
n
t
i
f
i
c
R
e
p
o
rt
s
,
v
o
l
.
1
5
,
n
o
.
1
,
D
e
c
.
2
0
2
5
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
5
-
1
0
5
7
3
-
2.
[
2
4
]
M
.
H
a
s
h
e
mi
,
“
E
n
l
a
r
g
i
n
g
sma
l
l
e
r
i
m
a
g
e
s
b
e
f
o
r
e
i
n
p
u
t
t
i
n
g
i
n
t
o
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
:
z
e
r
o
-
p
a
d
d
i
n
g
v
s.
i
n
t
e
r
p
o
l
a
t
i
o
n
,
”
J
o
u
rn
a
l
o
f
Bi
g
D
a
t
a
,
v
o
l
.
6
,
n
o
.
1
,
D
e
c
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
8
6
/
s
4
0
5
3
7
-
0
1
9
-
0263
-
7.
[
2
5
]
D
.
B
e
e
r
a
m
,
“
O
p
t
i
mi
z
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
p
i
p
e
l
i
n
e
s
f
o
r
n
a
t
u
r
a
l
l
a
n
g
u
a
g
e
p
r
o
c
e
ss
i
n
g
t
a
s
k
s,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
n
o
v
a
t
i
v
e
Re
se
a
rc
h
i
n
S
c
i
e
n
c
e
,
E
n
g
i
n
e
e
r
i
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
9
0
0
1
,
2
0
0
8
,
d
o
i
:
1
0
.
1
5
6
8
0
/
I
J
I
R
S
ET.
2
0
2
4
.
1
3
0
8
0
1
6
.
[
2
6
]
G
.
T
.
A
d
e
w
a
l
e
,
A
.
U
.
V
i
c
t
o
r
,
A
.
E
.
S
y
l
v
i
a
,
T
.
S
o
n
u
b
i
,
a
n
d
A
.
O
.
M
e
s
o
g
b
o
r
i
w
o
n
,
“
I
n
t
e
g
r
a
t
i
n
g
b
i
g
d
a
t
a
a
n
d
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
i
n
man
a
g
e
me
n
t
i
n
f
o
r
ma
t
i
o
n
s
y
st
e
ms
f
o
r
p
r
e
d
i
c
t
i
v
e
a
n
a
l
y
t
i
c
s:
a
f
o
c
u
s o
n
d
a
t
a
p
r
e
p
r
o
c
e
ss
i
n
g
a
n
d
t
e
c
h
n
o
l
o
g
i
c
a
l
a
d
v
a
n
c
e
me
n
t
s,”
W
o
rl
d
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
d
R
e
se
a
rc
h
a
n
d
R
e
v
i
e
w
s
,
v
o
l
.
2
4
,
n
o
.
2
,
p
p
.
7
7
4
–
7
8
9
,
N
o
v
.
2
0
2
4
,
d
o
i
:
1
0
.
3
0
5
7
4
/
w
j
a
r
r
.
2
0
2
4
.
2
4
.
2
.
3
4
2
7
.
[
2
7
]
P
.
J.
W
o
r
t
h
,
“
W
o
r
d
e
m
b
e
d
d
i
n
g
s
a
n
d
s
e
ma
n
t
i
c
s
p
a
c
e
s
i
n
n
a
t
u
r
a
l
l
a
n
g
u
a
g
e
p
r
o
c
e
ssi
n
g
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
I
n
t
e
l
l
i
g
e
n
c
e
S
c
i
e
n
c
e
,
v
o
l
.
1
3
,
n
o
.
1
,
p
p
.
1
–
2
1
,
2
0
2
3
,
d
o
i
:
1
0
.
4
2
3
6
/
i
j
i
s.
2
0
2
3
.
1
3
1
0
0
1
.
[
2
8
]
A
.
S
g
h
i
r
a
n
d
A
.
I
r
o
sh
a
n
,
“
U
n
l
e
a
s
h
i
n
g
t
h
e
p
o
w
e
r
o
f
LST
M
s
:
a
d
v
a
n
c
e
me
n
t
s
a
n
d
a
p
p
l
i
c
a
t
i
o
n
s
i
n
se
q
u
e
n
t
i
a
l
d
a
t
a
p
r
o
c
e
ss
i
n
g
,
”
S
S
R
N
,
p
p
.
1
–
1
5
,
2
0
2
4
,
d
o
i
:
1
0
.
2
1
3
9
/
ssr
n
.
5
0
3
2
0
4
5
.
[
2
9
]
D
.
C
.
Ed
a
r
a
,
L.
P
.
V
a
n
u
k
u
r
i
,
V
.
S
i
s
t
l
a
,
a
n
d
V
.
K
.
K
.
K
o
l
l
i
,
“
S
e
n
t
i
m
e
n
t
a
n
a
l
y
s
i
s
a
n
d
t
e
x
t
c
a
t
e
g
o
r
i
z
a
t
i
o
n
o
f
c
a
n
c
e
r
me
d
i
c
a
l
r
e
c
o
r
d
s
w
i
t
h
LST
M
,
”
J
o
u
r
n
a
l
o
f
Am
b
i
e
n
t
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
H
u
m
a
n
i
ze
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
4
,
n
o
.
5
,
p
p
.
5
3
0
9
–
5
3
2
5
,
M
a
y
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
2
6
5
2
-
019
-
0
1
3
9
9
-
8.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
2
,
Ap
r
il 2
0
2
6
:
1
7
6
2
-
1
7
7
0
1770
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Za
q
q
i
Y
a
m
a
n
i
is
a
n
a
c
ti
v
e
l
e
c
tu
re
r
a
n
d
re
se
a
rc
h
e
r
a
t
th
e
F
a
c
u
lt
y
o
f
Co
m
p
u
ter
S
c
ien
c
e
,
Un
iv
e
rsitas
S
riwij
a
y
a
.
His
a
c
a
d
e
m
ic
a
n
d
p
r
o
fe
ss
io
n
a
l
e
x
p
e
rti
se
sp
a
n
s
b
u
sin
e
ss
p
ro
c
e
ss
m
a
n
a
g
e
m
e
n
t,
IT
se
rv
ice
m
a
n
a
g
e
m
e
n
t,
a
n
d
i
n
telli
g
e
n
t
wo
r
k
flo
w
sy
ste
m
,
wit
h
a
stro
n
g
e
m
p
h
a
sis
o
n
p
r
o
c
e
ss
a
u
to
m
a
ti
o
n
a
n
d
o
p
ti
m
iza
ti
o
n
a
s
we
ll
a
s
d
ig
it
a
li
z
e
d
in
n
o
v
a
ti
o
n
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
z
a
q
q
i
_
y
a
m
a
n
i
@u
n
sri.
a
c
.
id
.
Din
d
a
Le
sta
r
in
i
is
a
lec
tu
re
r
a
t
th
e
F
a
c
u
lt
y
o
f
C
o
m
p
u
ter
S
c
i
e
n
c
e
,
Un
iv
e
rsitas
S
riwij
a
y
a
.
S
h
e
c
o
m
p
lete
d
h
e
r
m
a
ste
r’s
d
e
g
re
e
in
In
fo
rm
a
ti
c
s
a
t
th
e
S
c
h
o
o
l
o
f
El
e
c
tri
c
a
l
a
n
d
In
fo
rm
a
ti
c
s
ITB.
S
h
e
sp
e
c
ialize
s
in
k
n
o
wle
d
g
e
m
a
n
a
g
e
m
e
n
t,
b
u
s
in
e
ss
p
r
o
c
e
ss
m
a
n
a
g
e
m
e
n
t,
IT
se
rv
ice
m
a
n
a
g
e
m
e
n
t,
a
n
d
d
a
ta
sc
ien
c
e
.
S
h
e
is
a
n
a
c
ti
v
e
re
s
e
a
rc
h
e
r
a
n
d
h
a
s
p
re
se
n
ted
h
e
r
fin
d
i
n
g
s
a
t
n
u
m
e
ro
u
s
re
sp
e
c
ted
jo
u
r
n
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
d
in
d
a
.
les
tarin
i@g
m
a
il
.
c
o
m
.
S
a
r
ifa
h
Pu
tr
i
Ra
fles
ia
p
o
ss
e
ss
e
s
a
d
e
e
p
u
n
d
e
rsta
n
d
i
n
g
o
f
sy
st
e
m
d
e
v
e
lo
p
m
e
n
t,
b
u
sin
e
ss
p
ro
c
e
ss
re
e
n
g
in
e
e
rin
g
,
a
n
d
se
rv
ice
e
x
c
e
ll
e
n
c
e
.
As
a
n
u
n
d
e
rg
ra
d
u
a
te,
s
h
e
a
tt
e
n
d
e
d
th
e
S
c
h
o
o
l
o
f
El
e
c
tri
c
a
l
a
n
d
I
n
fo
rm
a
ti
c
s
a
t
th
e
In
stit
u
t
Tek
n
o
l
o
g
i
B
a
n
d
u
n
g
(I
TB),
wh
e
re
ITB
c
o
n
d
u
c
ted
re
se
a
rc
h
b
e
twe
e
n
2
0
1
4
-
2
0
1
6
.
A
d
d
i
ti
o
n
a
ll
y
,
sh
e
se
rv
e
d
a
s a
n
u
n
d
e
rg
ra
d
u
a
te t
e
a
c
h
in
g
a
ss
istan
t
fo
r
th
e
ITB
re
se
a
rc
h
a
n
d
in
f
o
rm
a
ti
o
n
s
y
ste
m
s
p
ro
jec
ts.
S
in
c
e
2
0
1
6
,
sh
e
h
a
s
b
e
e
n
a
lec
tu
re
r
a
n
d
re
se
a
rc
h
e
r
a
t
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
,
Un
iv
e
rsitas
S
riwij
a
y
a
.
S
h
e
h
a
s
p
u
b
li
sh
e
d
e
x
te
n
siv
e
l
y
in
re
p
u
tab
le
jo
u
r
n
a
ls
a
n
d
a
t
i
n
tern
a
t
io
n
a
l
c
o
n
fe
re
n
c
e
s.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sa
rifah
@u
n
sri
.
a
c
.
id
.
Pu
r
wita
S
a
r
i
wo
rk
s
a
s
a
lec
tu
re
r
a
t
th
e
De
p
a
rtme
n
t
o
f
I
n
fo
rm
a
t
ics
M
a
n
a
g
e
m
e
n
t
u
n
d
e
r
t
h
e
F
a
c
u
lt
y
o
f
Co
m
p
u
ter
S
c
ien
c
e
,
Un
iv
e
rsitas
S
riwij
a
y
a
.
S
h
e
o
b
tain
e
d
a
b
a
c
h
e
lo
r'
s
d
e
g
re
e
fro
m
th
e
sa
m
e
u
n
iv
e
rsity
in
I
n
fo
rm
a
ti
o
n
S
y
ste
m
s
a
n
d
a
m
a
ste
r'
s
d
e
g
re
e
fro
m
Bin
a
Da
rm
a
Un
iv
e
rsity
in
I
n
fo
rm
a
t
ics
En
g
i
n
e
e
rin
g
.
He
r
a
re
a
s
o
f
c
o
n
c
e
rn
wh
ic
h
in
c
l
u
d
e
m
a
n
a
g
e
m
e
n
t
in
fo
rm
a
ti
o
n
s
y
ste
m
s
a
n
d
I
T
se
rv
ice
s,
h
a
v
e
re
g
a
rd
e
d
h
e
r
a
s
a
lea
d
in
g
f
ig
u
re
in
th
e
re
lev
a
n
t
re
se
a
rc
h
IT
field
.
S
h
e
h
a
s
p
u
b
li
sh
e
d
se
v
e
ra
l
p
a
p
e
rs
in
re
p
u
tab
le
j
o
u
r
n
a
ls.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
wita@
il
k
o
m
.
u
n
sri.
a
c
.
id
.
G
h
ita
Ath
a
li
n
a
c
u
rre
n
tl
y
,
s
h
e
se
rv
e
s
a
s
a
lec
tu
re
r
a
t
th
e
F
a
c
u
lt
y
o
f
Co
m
p
u
ter
S
c
ien
c
e
o
f
Un
iv
e
rsitas
S
riwij
a
y
a
,
wh
e
re
sh
e
e
a
rn
e
d
h
e
r
M
a
ste
r
o
f
E
n
g
in
e
e
rin
g
fr
o
m
Th
e
Un
iv
e
rsity
o
f
El
e
c
tro
Co
m
m
u
n
ica
ti
o
n
in
Ja
p
a
n
a
n
d
h
e
r
Ba
c
h
e
lo
r
o
f
En
g
i
n
e
e
rin
g
fr
o
m
Th
e
P
o
ly
tec
h
n
ic
U
n
iv
e
rsit
y
.
He
r
re
se
a
rc
h
in
tere
sts
e
n
c
o
m
p
a
ss
th
e
fiel
d
s
o
f
a
rti
ficia
l
i
n
telli
g
e
n
c
e
,
c
o
n
tro
l
sy
ste
m
s
,
a
n
d
ro
b
o
t
ics
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
g
h
it
a
a
th
a
li
n
a
@u
n
sri.
a
c
.
id
.
Evaluation Warning : The document was created with Spire.PDF for Python.