I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
23
,
No
.
2
,
A
u
g
u
s
t
2
0
2
1
,
p
p
.
1
2
0
0
~
1
2
1
1
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
23
.i
2
.
pp
1
2
0
0
-
1
2
1
1
1200
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
To
wa
rds dev
elo
ping
a po
cket
thera
pist:
a
n i
ntelligen
t
a
da
ptive
psy
cho
lo
g
ica
l suppo
rt
cha
tbot
ag
a
inst men
tal hea
lth
diso
rders
in a pa
ndemic
sit
ua
tion
I
ntis
s
a
r
Sa
lhi
,
K
a
m
a
l El
G
uem
m
a
t
,
M
o
ha
mm
ed
Q
ba
do
u
,
K
ha
lifa
M
a
ns
o
uri
L
a
b
o
r
a
t
o
r
y
o
f
S
i
g
n
a
l
s
,
d
i
s
t
r
i
b
u
t
e
d
s
y
s
t
e
m
s
,
a
n
d
a
r
t
i
f
i
c
ia
l
i
n
t
e
l
l
i
g
e
n
c
e
,
E
N
S
E
T
,
H
a
s
sa
n
I
I
U
n
i
v
e
r
s
i
t
y
o
f
C
a
s
a
b
la
n
c
a
,
M
o
r
o
c
c
o
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ap
r
2
9
,
2
0
2
1
R
ev
is
ed
J
u
l 8
,
2
0
2
1
Acc
ep
ted
J
u
l 1
4
,
2
0
2
1
No
wa
d
a
y
s
with
COV
ID
-
19
o
n
g
o
in
g
e
p
i
d
e
m
ic
o
u
tb
re
a
k
,
c
o
n
tain
m
e
n
t
fo
r
we
e
k
s
wa
s
o
n
e
o
f
th
e
m
o
st
e
ffe
c
ti
v
e
m
e
a
su
re
s
a
d
o
p
ted
to
d
e
a
l
with
th
e
sp
re
a
d
o
f
t
h
e
v
ir
u
s
u
n
ti
l
a
v
a
c
c
in
e
c
o
u
l
d
b
e
e
fficie
n
t
.
Ov
e
r
t
h
a
t
p
e
rio
d
,
in
c
re
a
se
d
a
n
x
iet
y
,
d
e
p
re
ss
io
n
,
s
u
icid
e
a
tt
e
m
p
ts,
a
n
d
p
o
st
-
tra
u
m
a
ti
c
stre
ss
d
iso
rd
e
r
a
re
a
c
c
u
m
u
late
d
.
S
e
v
e
ra
l
stu
d
ies
re
fe
rre
d
to
t
h
e
n
e
e
d
o
f
u
si
n
g
c
h
a
tb
o
ts,
wh
ich
re
c
o
g
n
ize
s
h
u
m
a
n
e
m
o
ti
o
n
s
i
n
su
c
h
p
a
n
d
e
m
i
c
c
o
n
tex
ts
.
M
o
re
re
c
e
n
tl
y
,
n
u
m
e
ro
u
s
re
se
a
rc
h
p
a
p
e
rs
imp
ro
v
e
d
th
e
a
b
il
i
ty
o
f
a
rti
ficia
l
in
telli
g
e
n
c
e
m
e
th
o
d
s
t
o
re
c
o
g
n
ize
h
u
m
a
n
e
m
o
ti
o
n
.
Ho
we
v
e
r,
t
h
e
y
a
re
stil
l
li
m
it
e
d
.
T
h
e
a
im
o
f
t
h
is
p
a
p
e
r
i
s
th
e
d
e
v
e
lo
p
m
e
n
t
o
f
a
c
h
a
t
b
o
t
a
g
a
in
st
t
h
e
d
istu
r
b
in
g
p
sy
c
h
ic
c
o
n
se
q
u
e
n
c
e
s
o
f
th
e
p
a
n
d
e
m
ic,
tak
in
g
h
u
m
a
n
e
m
o
ti
o
n
re
c
o
g
n
it
i
o
n
in
to
a
c
c
o
u
n
t.
Th
e
o
b
jec
t
is
to
h
e
lp
p
e
o
p
le;
e
sp
e
c
ially
stu
d
e
n
ts;
su
ffe
rin
g
fro
m
m
e
n
tal
d
iso
rd
e
rs,
b
y
p
ro
g
re
ss
iv
e
ly
u
n
d
e
rsta
n
d
in
g
t
h
e
re
a
so
n
s
b
e
h
in
d
t
h
e
m
.
T
h
is
i
n
n
o
v
a
ti
v
e
c
h
a
tb
o
t
wa
s
d
e
v
e
l
o
p
e
d
b
y
u
sin
g
th
e
n
a
t
u
ra
l
lan
g
u
a
g
e
p
r
o
c
e
ss
in
g
m
o
d
e
l
o
f
d
e
e
p
lea
rn
in
g
.
An
a
d
v
a
n
c
e
d
m
o
d
e
l
o
f
d
e
e
p
lea
rn
in
g
h
a
s
b
e
e
n
e
lab
o
ra
ted
t
h
e
i
n
ten
ti
o
n
fo
r
p
e
o
p
le,
a
n
d
th
a
t
to
h
e
lp
t
h
e
m
t
o
re
g
u
late
t
h
e
ir
m
o
o
d
a
n
d
to
re
d
u
c
e
d
isto
rt
io
n
o
f
n
e
g
a
ti
v
e
t
h
o
u
g
h
ts,
th
a
t
wh
y
a
c
o
ll
e
c
ti
o
n
o
f
a
n
e
w
d
a
tab
a
se
wa
s
d
o
n
e
.
T
h
e
s
e
q
u
e
n
c
e
-
to
-
s
e
q
u
e
n
c
e
m
o
d
e
l
e
n
c
o
d
e
r
a
n
d
d
e
c
o
d
e
r
c
o
n
sist
o
f
Lo
n
g
sh
o
rt
-
term
m
e
m
o
ry
c
e
ll
s,
a
n
d
it
is
d
e
fin
e
d
wit
h
t
h
e
b
i
-
d
irec
ti
o
n
a
l
d
y
n
a
m
ic rec
u
rre
n
t
n
e
u
ra
l
n
e
two
r
k
p
a
c
k
e
ts.
K
ey
w
o
r
d
s
:
C
h
atb
o
t
C
OVI
D
-
19
L
STM
NL
P
Ps
y
ch
ic
d
is
o
r
d
er
s
R
NN
Seq
u
en
ce
-
to
-
s
eq
u
en
ce
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
I
n
tis
s
ar
Salh
i
L
ab
o
r
ato
r
y
o
f
Sig
n
als,
d
is
tr
ib
u
ted
s
y
s
tem
s
,
an
d
ar
tific
ial
in
tellig
en
ce
E
NSET
,
Un
iv
er
s
ity
Hass
an
I
I
Un
iv
er
s
ity
o
f
C
asab
lan
ca
E
NSET
M,
B
P 1
5
9
B
d
Hass
an
I
I
Mo
h
am
m
ed
ia
2
8
0
0
0
,
Mo
r
o
cc
o
E
m
ail:
s
alh
i9
4
7
7
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
I
n
a
p
an
d
em
ic
s
itu
atio
n
,
th
e
p
s
y
ch
o
lo
g
ical
r
ea
ctio
n
s
o
f
th
e
p
o
p
u
latio
n
ar
e
an
ess
en
tial
f
ac
to
r
o
f
th
e
v
ir
u
s
s
p
r
ea
d
[
1
]
.
C
h
an
g
es
an
d
co
u
n
ter
m
ea
s
u
r
es
ar
e
tak
en
to
co
n
tr
o
l
it
led
to
th
e
ap
p
ea
r
an
ce
o
f
em
o
tio
n
al
d
is
tr
ess
an
d
/o
r
m
en
tal
h
ea
lth
p
r
o
b
lem
s
b
o
th
d
u
r
in
g
an
d
a
f
t
er
th
at
p
an
d
em
ic
[
2
]
.
Desp
ite
th
is
f
ac
t,
r
eso
u
r
ce
s
ar
e
n
o
t
g
en
er
ally
s
u
f
f
icien
t
f
o
r
m
an
ag
in
g
a
n
d
m
itig
atin
g
th
e
im
p
ac
t
th
at
p
an
d
em
ics
m
ig
h
t
o
th
er
wis
e
ca
u
s
e
to
th
e
m
en
tal
h
ea
lth
an
d
wellb
ein
g
o
f
th
e
p
o
p
u
latio
n
[
3
]
.
W
h
ile
th
is
m
ay
b
e
u
n
d
er
s
to
o
d
d
u
r
i
n
g
th
e
ac
u
te
s
tag
es
o
f
a
p
an
d
em
ic
wh
e
n
h
ea
lt
h
ca
r
e
s
y
s
tem
s
p
r
io
r
itize
test
in
g
,
t
r
an
s
m
is
s
io
n
r
ed
u
ctio
n
,
as
wel
l
as
cr
itical
p
atien
t
ca
r
e,
th
e
p
s
y
ch
o
lo
g
ical
an
d
p
s
y
ch
o
lo
g
ical
r
e
q
u
ir
em
e
n
ts
,
ca
n
n
o
t
b
e
n
eg
lecte
d
at
an
y
p
h
ase
in
p
an
d
em
ic
m
an
ag
em
en
t
[
4
]
.
Me
n
tal
He
al
th
s
tan
d
s
f
o
r
c
o
g
n
itiv
e,
em
o
ti
o
n
al,
an
d
b
e
h
av
io
r
al
wellb
ein
g
[
5
]
,
[
6
]
.
I
t
is
ab
o
u
t
h
o
w
p
e
o
p
le
a
r
e
th
in
k
in
g
,
f
ee
li
n
g
,
a
n
d
b
eh
av
i
n
g
.
I
t
is
th
e
wa
y
p
eo
p
le
th
i
n
k
,
f
ee
l,
a
n
d
b
eh
a
v
e.
As
r
ep
o
r
ted
b
y
th
e
wo
r
ld
h
ea
lth
o
r
g
an
izatio
n
(
W
HO)
,
th
e"
m
en
tal
h
ea
lth
"
t
er
m
m
a
y
b
e
u
s
ed
s
o
m
etim
es
a
s
a
ter
m
to
i
n
d
icate
th
e
ab
s
en
ce
o
f
a
m
en
tal
d
is
o
r
d
er
[
7
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
To
w
a
r
d
s
d
ev
elo
p
in
g
a
p
o
ck
et
t
h
era
p
is
t:
a
n
in
tellig
en
t
a
d
a
p
tive
p
s
yc
h
o
lo
g
ica
l su
p
p
o
r
t
…
(
I
n
tis
s
a
r
S
a
lh
i
)
1201
R
ec
en
tly
,
th
e
im
p
o
r
tan
t
r
o
le
o
f
m
en
tal
h
ea
lth
in
th
e
ac
h
iev
e
m
en
t
o
f
g
lo
b
al
d
ev
elo
p
m
en
tal
ch
allen
g
es
h
as
b
ee
n
in
cr
ea
s
in
g
ly
r
ec
o
g
n
i
ze
d
,
as
illu
s
tr
ated
b
y
t
h
e
in
cl
u
s
io
n
o
f
m
en
t
al
h
ea
lth
i
n
th
e
g
o
als
o
f
s
u
s
tain
ab
le
d
ev
elo
p
m
e
n
t
[
8
]
.
On
e
o
f
th
e
m
ajo
r
ca
u
s
es
o
f
d
is
ab
ilit
ies
c
an
b
e
d
ep
r
ess
io
n
[
9
]
,
[
1
0
]
.
S
u
icid
e
r
em
ain
s
th
e
s
ec
o
n
d
ca
u
s
e
o
f
d
ea
th
am
o
n
g
1
5
–
to
2
9
-
y
ea
r
ag
e
-
o
ld
s
[
1
1
]
,
[
1
2
]
.
Peo
p
le
with
s
er
io
u
s
m
en
tal
h
ea
lth
co
n
d
itio
n
s
ar
e
d
y
in
g
p
r
e
m
atu
r
ely
b
y
u
p
t
o
two
d
ec
ad
es b
ec
a
u
s
e
o
f
p
r
ev
en
tab
le
p
h
y
s
ical
im
p
air
m
en
t [
1
3
]
.
At
th
e
tim
e
o
f
a
p
a
n
d
em
ic,
as
with
C
OVI
D
-
1
9
,
f
ea
r
,
an
x
iety
,
an
d
s
tr
ess
m
ay
b
e
co
n
s
id
er
ed
as
n
o
r
m
al
r
ea
ctio
n
s
to
war
d
s
t
h
e
p
er
ce
iv
ed
an
d
ac
tu
al
th
r
ea
ts
.
W
h
en
we
ar
e
c
o
n
f
r
o
n
ted
with
th
e
u
n
ce
r
tain
ty
a
n
d
s
tr
u
g
g
les
o
f
th
e
u
n
f
am
iliar
[
1
4
]
.
Asi
d
e
f
r
o
m
f
ea
r
to
co
n
tr
ac
t
th
is
v
ir
u
s
,
th
er
e
ar
e
also
d
r
am
atic
ch
an
g
es
in
o
u
r
d
aily
liv
es
[
1
5
]
,
d
u
e
to
th
e
li
m
ited
m
o
b
ilit
y
r
eq
u
ir
e
d
to
s
u
s
tain
ef
f
o
r
ts
aim
ed
to
co
n
tain
an
d
s
lo
wd
o
wn
th
at
v
ir
u
s
'
s
s
p
r
ea
d
.
Dea
lin
g
with
th
ese
n
ew
r
ea
liti
es
in
clu
d
in
g
h
o
m
e
-
s
ch
o
o
lin
g
f
o
r
c
h
ild
r
en
,
te
lewo
r
k
,
m
o
m
e
n
tar
y
u
n
em
p
lo
y
m
en
t,
an
d
th
e
lim
ite
d
co
n
tact
with
f
r
ien
d
s
,
o
th
e
r
f
am
ily
m
em
b
er
s
,
a
n
d
co
lleag
u
es;
we
m
u
s
t
en
s
u
r
e
th
at
o
u
r
m
e
n
tal
an
d
p
h
y
s
ical
h
ea
lth
,
ar
e
well
ca
r
ed
f
o
r
.
On
e
o
f
th
e
m
ain
tech
n
o
lo
g
i
ca
l
s
o
lu
tio
n
s
to
th
e
lack
o
f
s
taf
f
in
th
e
f
ield
o
f
m
en
ta
l
h
ea
lth
is
ch
atb
o
ts
[
1
6
]
-
[
1
8
]
,
co
m
m
o
n
l
y
k
n
o
wn
as
co
n
v
er
s
atio
n
al
a
g
en
ts
,
co
n
v
er
s
atio
n
al
r
o
b
o
ts
,
o
r
ch
atter
b
o
ts
[
1
9
]
.
Su
ch
s
y
s
tem
s
ca
n
s
im
u
late
h
u
m
an
c
o
n
v
er
s
atio
n
al
s
k
ills
v
ia
n
atu
r
al
la
n
g
u
a
g
e
[
2
0
]
.
At
t
h
e
ac
u
te
s
tag
e
o
f
C
OVI
D
-
19
,
h
ea
lth
ca
r
e
s
y
s
tem
s
p
r
io
r
itized
test
in
g
,
tr
an
s
m
is
s
io
n
r
ed
u
ctio
n
,
an
d
cr
itical
p
atien
t
ca
r
e.
Su
ch
co
n
v
er
s
atio
n
al
ag
e
n
ts
ca
n
b
e
v
alu
ab
le
to
o
ls
,
as
th
ey
ca
n
s
u
b
s
titu
te
a
th
er
ap
is
t
an
d
ca
n
talk
to
p
eo
p
le
an
d
p
r
o
v
id
e
s
o
m
e
r
ea
s
s
u
r
an
ce
.
N
u
m
er
o
u
s
t
r
ials
h
av
e
b
ee
n
ca
r
r
ied
o
u
t
to
d
esig
n
a
n
d
im
p
lem
en
t
co
n
v
er
s
atio
n
al
ag
en
ts
to
s
u
p
p
o
r
t in
d
iv
id
u
als in
m
an
y
ar
ea
s
o
f
d
aily
life
,
in
cl
u
d
in
g
h
ea
lth
ca
r
e,
ac
ad
em
ia,
c
o
m
m
er
ce
,
f
in
a
n
ce
s
,
in
d
u
s
tr
y
,
an
d
law
[
2
1
]
-
[
2
4
]
.
T
h
ey
ca
n
p
r
o
ce
s
s
u
s
er
in
p
u
ts
th
r
o
u
g
h
n
atu
r
al
lan
g
u
a
g
e
p
r
o
ce
s
s
in
g
to
o
ls
,
th
en
m
atch
th
ese
in
p
u
ts
with
th
e
in
ten
t
an
d
g
e
n
er
ate
o
u
t
p
u
ts
[
2
5
]
.
T
h
ey
ar
e
p
r
o
g
r
am
m
e
d
s
o
th
at
th
ey
ca
n
in
ter
ac
t
with
u
s
er
s
as
a
r
ea
l
p
er
s
o
n
[
2
6
]
an
d
h
a
v
e
th
e
ca
p
ac
ity
t
o
f
o
ll
o
w
b
o
th
co
n
tex
t
an
d
wo
r
d
lis
ts
.
Fu
r
th
er
m
o
r
e,
w
e
ca
n
class
if
y
th
em
u
n
d
e
r
th
r
ee
d
if
f
er
e
n
t
class
es,
d
ee
p
l
ea
r
n
in
g
,
en
d
-
to
-
en
d
,
a
n
d
s
e
q
u
en
ce
-
to
-
s
eq
u
en
ce
ch
atb
o
ts
[
2
7
]
-
[
2
9
]
.
T
h
e
m
ed
ical
f
ield
is
an
ar
ea
w
h
er
e
ch
atb
o
ts
ar
e
m
o
r
e
an
d
m
o
r
e
ad
o
p
ted
as
a
to
o
l
to
ea
s
e
i
n
f
o
r
m
atio
n
ac
ce
s
s
b
y
th
e
p
atien
t
an
d
to
r
e
d
u
ce
th
e
wo
r
k
lo
ad
o
n
th
e
clin
ician
.
p
s
y
ch
o
th
e
r
ap
y
h
as
b
ee
n
th
e
f
ir
s
t
d
is
cip
lin
e
u
s
in
g
co
n
v
er
s
atio
n
al
ag
en
ts
.
I
t
s
tar
ted
in
1
9
6
4
with
E
L
I
Z
A
wh
o
was
ca
p
ab
le
to
s
im
u
late
a
p
s
y
ch
o
th
er
a
p
is
t
b
y
r
ef
o
r
m
u
latin
g
alm
o
s
t
all
th
e
ass
er
tio
n
s
o
f
a
p
atien
t
in
to
q
u
esti
o
n
s
b
y
ask
in
g
h
im
.
T
h
is
was
d
o
n
e
b
ased
o
n
n
atu
r
al
lan
g
u
a
g
e
p
r
o
ce
s
s
in
g
[
3
0
]
.
Ho
wev
er
,
th
e
ch
atb
o
t
h
a
d
s
o
m
e
lim
itatio
n
s
,
f
o
r
in
s
tan
ce
,
it
was
in
ca
p
ab
le
o
f
an
s
wer
in
g
ac
c
o
r
d
in
g
to
th
e
co
n
tex
t,
an
d
it
was
u
n
ab
le
to
h
an
d
le
t
h
e
lo
s
t
q
u
esti
o
n
s
in
an
y
m
ea
n
i
n
g
f
u
l
way
.
T
h
is
is
wh
y
h
e
co
u
ld
n
'
t
p
ass
th
e
T
u
r
in
g
test
[
3
1
]
.
B
y
th
e
y
ea
r
1
9
7
2
,
a
n
o
th
er
c
h
atb
o
t
k
n
o
wn
as
Par
r
y
;
was
p
r
o
p
o
s
ed
b
y
a
r
esear
c
h
er
i
n
th
e
Stan
f
o
r
d
la
b
s
th
at
wer
e
ab
le
o
f
s
im
u
latin
g
an
in
d
i
v
id
u
al
with
Par
a
n
o
iac
Sch
izo
p
h
r
en
ia.
Par
r
y
s
u
cc
ess
f
u
lly
p
ass
ed
th
e
T
u
r
i
n
g
test
a
n
d
h
ad
s
ev
er
al
c
o
n
v
e
r
s
atio
n
s
w
ith
E
L
I
Z
A
[
3
2
]
.
I
n
r
ec
en
t
y
ea
r
s
,
as
m
ac
h
i
n
e
lea
r
n
in
g
an
d
ar
tific
ial
in
tellig
en
ce
ap
p
r
o
ac
h
es
ar
e
g
r
a
d
u
ally
b
ein
g
ad
o
p
ted
in
d
if
f
er
en
t
ap
p
licatio
n
ar
ea
s
,
ad
v
an
ce
d
d
ialo
g
u
e
g
e
n
er
atio
n
a
n
d
m
an
ag
e
m
en
t
m
eth
o
d
s
ar
e
in
cr
ea
s
in
g
ly
u
s
in
g
m
ac
h
in
e
lear
n
in
g
an
d
d
ee
p
le
ar
n
in
g
tech
n
iq
u
es.
A
lar
g
e
n
u
m
b
er
o
f
c
o
m
m
e
r
cial
ch
atb
o
t
a
p
p
s
,
o
f
f
er
ed
as
web
o
r
m
o
b
ile
-
b
ased
s
o
lu
tio
n
s
,
wer
e
d
e
v
elo
p
ed
as
a
way
to
i
n
ter
ac
t
d
ir
ec
tly
with
p
atie
n
ts
.
So
m
e
ex
am
p
les
o
f
h
ea
lth
ca
r
e
ch
atb
o
ts
in
clu
d
e
O
n
eRem
is
s
io
n
1
,
wh
ich
h
as
b
ee
n
d
esig
n
ed
t
o
ass
is
t
ca
n
ce
r
s
u
r
v
iv
o
r
s
,
th
e
B
ab
y
l
o
n
Hea
lth
,
wh
o
is
a
s
y
m
p
to
m
-
ch
ec
k
in
g
to
o
l,
an
d
W
y
s
a
[
3
3
]
,
w
h
ich
is
a
m
en
tal
h
ea
lth
ch
atb
o
t
th
at
in
ter
ac
ts
with
th
e
u
s
er
to
h
el
p
h
im
/h
er
r
ec
o
g
n
ize
s
ig
n
s
o
f
an
x
iety
an
d
d
ep
r
ess
io
n
[
3
4
]
,
[
3
5
]
.
2.
T
H
E
P
RO
P
O
SE
D
M
E
T
H
O
D
T
h
e
d
esig
n
o
f
co
n
v
e
r
s
atio
n
al
ag
en
ts
r
eq
u
ir
es
p
er
s
o
n
aliza
t
io
n
to
s
u
it
th
e
ap
p
licatio
n
's
co
n
tex
t.
T
h
er
e
ar
e
s
p
ec
if
ic
r
eq
u
ir
em
en
ts
wh
e
n
wo
r
k
in
g
o
n
ch
at
b
o
t
s
o
lu
tio
n
s
.
T
o
d
eliv
er
a
tech
n
o
lo
g
y
th
at
p
r
o
v
id
es
a
s
er
v
ice
m
ee
tin
g
u
s
er
n
ee
d
s
,
o
n
e
m
u
s
t
co
n
s
id
er
th
e
u
s
er
d
em
o
g
r
ap
h
y
,
d
o
m
ain
,
in
ter
ac
tio
n
d
ata
an
d
d
ialo
g
u
e
s
tr
u
ctu
r
e
[
3
6
]
.
T
o
im
p
r
o
v
e
th
e
p
s
y
ch
ic
co
n
d
itio
n
o
f
i
n
d
iv
id
u
als
in
th
e
C
OVI
D
-
19
s
ce
n
ar
io
,
th
e
c
h
atb
o
t
is
h
er
e
to
im
p
r
o
v
e
th
e
p
s
y
ch
ic
s
tate
an
d
th
u
s
m
u
s
t
ad
ap
t
its
elf
to
ea
ch
p
er
s
o
n
b
ased
o
n
th
e
p
r
e
v
io
u
s
ly
m
en
tio
n
ed
f
ea
tu
r
es.
L
ately
,
ar
tific
ial
in
tellig
en
ce
(
AI
)
h
as
m
ad
e
s
ig
n
if
i
ca
n
t
p
r
o
g
r
ess
in
m
ed
ical
f
ield
s
,
n
o
tab
ly
af
ter
th
e
r
is
e
o
f
n
eu
r
o
n
al
n
etwo
r
k
s
a
n
d
d
ee
p
lear
n
in
g
[
3
7
]
.
I
n
th
is
s
ec
tio
n
,
we
ar
e
g
o
in
g
th
e
s
u
g
g
e
s
t
a
co
n
v
er
s
atio
n
al
ag
en
t a
r
ch
itectu
r
e
,
d
ef
i
n
e
an
d
ex
p
lain
its
co
m
p
o
n
en
ts
,
o
n
e
b
y
o
n
e
i
n
d
etail.
T
h
is
r
esear
ch
s
tu
d
y
in
tr
o
d
u
c
es
a
th
er
ap
is
t
ch
atb
o
t
with
in
C
OVI
D
-
19
,
th
at
s
h
o
u
ld
s
u
p
p
o
r
t
p
eo
p
le
s
u
f
f
er
in
g
f
r
o
m
m
en
tal
d
is
o
r
d
e
r
s
to
er
ad
icate
n
eg
ativ
e
th
o
u
g
h
ts
af
f
ec
tin
g
th
eir
m
en
tal
h
ea
l
th
.
T
h
is
c
h
atb
o
t
h
as
b
ee
n
im
p
lem
en
ted
with
a
s
eq
u
en
ce
-
by
-
s
eq
u
e
n
ce
a
r
ch
it
e
ctu
r
e
with
n
atu
r
al
la
n
g
u
a
g
e
p
r
o
ce
s
s
in
g
.
I
t
is
em
o
tio
n
al
an
d
ad
a
p
tiv
e.
T
h
u
s
,
ca
p
ab
le
o
f
em
p
ath
y
an
d
u
n
e
x
p
ec
ted
ev
en
ts
.
I
n
th
is
p
ap
er
,
we
im
p
lem
en
ted
a
th
er
ap
is
t
ch
atb
o
t
as
a
to
o
l
to
ass
is
t
h
ea
lth
ca
r
e
s
taf
f
in
th
e
C
OVI
D
-
1
9
p
an
d
em
ic
s
itu
atio
n
.
T
h
is
s
o
lu
tio
n
is
b
ased
o
n
r
ec
u
r
s
iv
e
n
eu
r
al
n
etwo
r
k
s
.
T
h
e
p
ap
er
h
as
b
ee
n
s
tr
u
ctu
r
ed
:
T
h
e
f
ir
s
t
s
ec
tio
n
is
a
cr
itical
liter
atu
r
e
o
v
er
v
iew,
wh
ile
in
th
e
s
ec
o
n
d
s
ec
tio
n
t
h
e
m
ate
r
ials
an
d
m
eth
o
d
s
wer
e
p
r
esen
ted
th
at
h
a
v
e
u
s
ed
to
g
en
er
ate
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
23
,
No
.
2
,
Au
g
u
s
t 2
0
2
1
:
1
2
0
0
-
1
2
1
1
1202
th
e
d
ata
s
et,
to
p
r
o
ce
s
s
an
d
tr
ain
i
t.
T
h
e
th
ir
d
s
ec
tio
n
is
d
ed
icate
d
to
th
e
im
p
lem
en
tat
io
n
o
f
th
e
ch
atb
o
t,
r
esu
lts
,
an
d
d
is
cu
s
s
io
n
,
an
d
f
in
ally
to
co
n
clu
d
e
an
d
ev
o
k
e
s
o
m
e
r
ec
o
m
m
e
n
d
atio
n
s
f
o
r
f
u
tu
r
e
s
tu
d
ies.
2
.
1
.
T
he
new
a
pp
ro
a
ch
o
f
ch
a
t
bo
t
ba
s
ed
o
n dee
p lea
rning
T
h
is
p
ap
er
o
f
f
er
s
a
ch
atb
o
t
th
at
p
r
o
v
id
es
a
ch
at
s
er
v
ice
f
o
r
p
s
y
ch
iatr
ic
m
o
n
ito
r
in
g
.
I
t
c
o
llects
an
d
s
u
m
m
ar
izes
d
ialo
g
u
es
with
te
x
tu
al
d
ata
to
r
ec
o
g
n
ize
th
e
u
s
er
'
s
f
ee
lin
g
s
.
B
ased
o
n
th
is
d
a
ta,
th
e
s
er
v
ice'
s
aim
co
n
s
is
ts
o
f
d
ev
elo
p
in
g
p
er
s
o
n
alize
d
ch
at
th
at
em
o
tio
n
ally
co
n
v
ey
s
th
e
u
s
er
th
r
o
u
g
h
t
ex
t
an
d
v
o
ice.
T
o
ac
h
iev
e
th
is
g
o
al,
th
e
m
eth
o
d
o
lo
g
y
ad
o
p
ted
is
to
f
ir
s
t
u
n
d
e
r
s
tan
d
th
e
co
n
te
x
t
o
f
th
e
co
n
v
er
s
atio
n
,
th
e
n
t
h
e
em
o
tio
n
al
r
ec
o
g
n
itio
n
,
a
n
d
f
i
n
ally
th
e
g
en
er
atio
n
o
f
ca
n
d
i
d
ate
r
esp
o
n
s
es
ad
ap
ted
to
th
e
p
atien
t'
s
s
itu
atio
n
.
Sectio
n
3
.
2
d
escr
ib
es th
e
p
r
o
p
o
s
ed
ar
ch
itectu
r
e
o
f
th
e
p
s
y
ch
i
atr
ic
ch
atb
o
t.
2
.
2
.
T
he
pro
po
s
ed
t
ec
hn
ica
l a
rc
hite
ct
ure
T
h
is
p
ar
t
p
r
o
v
id
es
th
e
tec
h
n
i
ca
l
ar
ch
itectu
r
e
o
f
th
e
c
h
atb
o
t
b
ased
o
n
d
ee
p
lea
r
n
in
g
.
I
t
co
n
s
is
ts
o
f
th
r
ee
m
ajo
r
c
o
m
p
o
n
en
ts
th
at
a
r
e:
th
e
n
atu
r
al
lan
g
u
ag
e
u
n
d
er
s
tan
d
in
g
u
n
it,
t
h
e
d
ialo
g
u
e
m
a
n
ag
em
en
t
u
n
it,
an
d
th
e
n
atu
r
al
la
n
g
u
a
g
e
g
e
n
er
ati
n
g
u
n
it;
wh
ich
will
b
e
ex
p
lai
n
ed
in
d
etails
in
th
e
n
ex
t
s
ec
t
io
n
.
Fig
u
r
e
1
s
h
o
ws
th
e
s
eq
u
en
cin
g
o
f
t
h
o
s
e
th
r
ee
u
n
its
.
Fig
u
r
e
1
.
Dee
p
lear
n
in
g
-
b
ased
p
s
y
ch
iatr
ic
ch
atb
o
t
L
et's
tak
e
an
illu
s
tr
atio
n
to
ex
p
lain
th
e
wa
y
o
u
r
ch
at
b
o
t
wo
r
k
s
.
On
ce
t
h
e
u
s
er
p
u
ts
a
q
u
er
y
o
r
q
u
est
io
n
to
th
e
ch
at
b
o
t
,
th
e
c
h
atb
o
t
tak
es
c
h
ar
g
e
o
f
it,
th
e
n
th
e
n
atu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
u
n
it
(
NL
P)
is
ac
tiv
ated
.
I
t
p
ic
k
s
u
p
th
e
r
e
q
u
est
an
d
s
p
lits
it
in
to
u
n
d
er
s
tan
d
ab
le
elem
e
n
ts
b
ein
g
t
h
e
k
e
y
wo
r
d
s
o
n
wh
ich
it
will
f
o
cu
s
.
Af
ter
war
d
,
h
e
u
s
es
th
e
n
atu
r
al
l
a
n
g
u
a
g
e
u
n
d
er
s
ta
n
d
in
g
u
n
it
(
NL
U)
t
o
co
m
p
ar
e
th
e
q
u
e
r
y
to
s
im
ilar
q
u
er
ies
m
ad
e
in
R
ed
d
it;
wh
ich
is
a
c
o
m
m
u
n
ity
web
s
ite
f
o
r
s
o
cial
n
ews
in
wh
ich
p
eo
p
le
ca
n
ask
q
u
esti
o
n
s
a
n
d
g
et
an
s
wer
s
;
an
d
tr
ies
to
u
n
d
er
s
tan
d
wh
at
t
h
e
u
s
er
is
ask
in
g
f
o
r
.
O
n
ce
th
e
ch
atb
o
t
h
as
u
n
d
er
s
to
o
d
wh
at
t
h
e
u
s
er
wan
ts
to
s
ay
,
it
s
co
u
r
s
th
e
web
s
ite
to
f
i
n
d
t
h
e
co
n
ten
t
t
h
at
b
est
an
s
wer
s
th
e
q
u
e
r
y
.
I
t
ex
tr
ac
ts
th
e
r
ele
v
an
t
d
ata
an
d
p
r
o
v
id
es
it
in
s
im
p
le
lan
g
u
ag
e
u
s
in
g
th
e
n
atu
r
al
la
n
g
u
ag
e
g
en
er
atio
n
(
NL
G)
u
n
it
.
T
h
e
u
s
er
ca
n
th
en
ask
as
m
an
y
q
u
esti
o
n
s
as
th
ey
wan
t
an
d
th
e
p
r
o
ce
s
s
s
tar
ts
al
l
o
v
er
ag
ain
.
T
h
e
ad
v
a
n
tag
e
o
f
m
ac
h
in
e
lear
n
in
g
is
th
at,
if
th
e
u
s
er
r
eg
u
lar
ly
as
k
s
th
e
s
am
e
q
u
esti
o
n
s
,
th
e
ch
a
tb
o
t c
an
s
tar
t to
an
ticip
ate
h
is
r
eq
u
est an
d
a
d
ap
t to
h
is
ca
s
e.
T
h
e
co
m
p
o
n
en
ts
o
f
o
u
r
ar
ch
itect
u
r
e
ar
e
d
escr
ib
e
d
.
3.
RE
S
E
ARCH
M
E
T
H
O
DS
I
n
th
is
s
ec
tio
n
,
all
th
e
u
n
its
o
f
th
e
ch
atb
o
t
as
well
a
s
th
e
tec
h
n
o
lo
g
ies
an
d
alg
o
r
ith
m
s
u
s
ed
in
all
o
f
th
em
will b
e
d
escr
ib
e.
3
.
1
.
T
he
na
t
ura
l la
ng
ua
g
e
p
ro
ce
s
s
ing
un
it
T
h
e
f
ir
s
t
s
tep
f
o
r
a
u
s
er
r
eq
u
est
is
th
e
p
r
e
-
p
r
o
ce
s
s
in
g
th
at
tak
es
p
lace
at
th
e
NL
P
u
n
it.
T
h
e
p
r
e
-
p
r
o
ce
s
s
in
g
u
n
it
is
ch
ar
g
ed
b
y
th
e
NL
P
wh
ich
co
n
s
is
ts
o
f
s
ev
er
al
s
tag
es,
h
en
ce
th
e
n
am
ed
p
ip
elin
e.
T
h
e
p
ip
elin
e
s
tag
es
ar
e
m
ain
ly
p
r
o
ject
-
d
ep
en
d
e
n
t.
As
o
u
r
s
o
l
u
tio
n
is
b
ased
o
n
Dee
p
L
ea
r
n
in
g
,
th
e
tex
t
h
as
to
b
e
co
n
v
er
ted
in
to
a
s
p
r
ea
d
s
h
ee
t.
T
h
er
ef
o
r
e,
th
e
p
ip
elin
e
u
s
ed
i
n
s
en
tim
en
t
an
aly
s
is
is
s
h
o
wn
in
F
ig
u
r
e
2
.
An
d
,
u
n
its
o
f
th
e
p
ip
elin
e
s
y
s
tem
as d
escr
ib
ed
h
e
r
ea
f
ter
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
To
w
a
r
d
s
d
ev
elo
p
in
g
a
p
o
ck
et
t
h
era
p
is
t:
a
n
in
tellig
en
t
a
d
a
p
tive
p
s
yc
h
o
lo
g
ica
l su
p
p
o
r
t
…
(
I
n
tis
s
a
r
S
a
lh
i
)
1203
Fig
u
r
e
2
.
Natu
r
al
lan
g
u
a
g
e
p
r
o
ce
s
s
in
g
p
i
p
elin
e
a)
Data
C
lean
in
g
:
Stem
m
in
g
r
ef
e
r
s
to
th
e
g
e
n
er
atio
n
o
f
m
o
r
p
h
o
lo
g
ical
v
ar
iatio
n
s
o
f
a
r
o
o
t o
r
b
ase
wo
r
d
.
T
h
e
f
ilter
in
g
p
r
o
g
r
am
s
ar
e
c
o
m
m
o
n
ly
ca
lled
f
ilter
in
g
alg
o
r
ith
m
s
o
r
"steam
er
s
".
Stem
m
in
g
alg
o
r
ith
m
s
r
ed
u
ce
wo
r
d
s
to
s
tem
ter
m
s
.
T
h
e
s
t
em
is
an
im
p
o
r
tan
t
p
ar
t
o
f
t
h
e
p
r
o
ce
s
s
o
f
p
ip
ettin
g
in
n
atu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
.
Stem
in
p
u
t
is
d
o
n
e
u
s
in
g
s
y
m
b
o
lic
wo
r
d
s
.
Als
o
,
in
th
is
p
ar
t
p
u
n
ctu
atio
n
s
ar
e
d
elete
d
b
ec
au
s
e
th
ey
ar
e
a
u
s
eless
ad
d
itio
n
an
d
th
ey
d
o
n
o
t a
d
d
v
alu
e
o
r
m
ea
n
in
g
to
t
h
e
NL
P m
o
d
el.
b)
T
o
k
en
izatio
n
:
I
n
th
is
ce
ll,
th
e
co
n
v
er
tin
g
p
r
o
ce
s
s
o
f
a
s
tr
in
g
o
f
tex
t
in
to
a
lis
t
o
f
to
k
en
s
o
r
elem
en
ts
is
d
o
n
e.
T
h
ese
to
k
e
n
s
m
ay
b
e
w
o
r
d
s
th
at
a
r
e
elem
en
ts
o
f
a
s
en
ten
ce
,
as
well
as
a
s
en
ten
ce
th
at
is
an
elem
en
t
o
f
a
p
a
r
ag
r
ap
h
.
c)
Po
s
t
T
ag
g
in
g
:
T
alk
i
n
g
a
b
o
u
t
m
ar
k
in
g
th
e
p
a
r
t
o
f
th
e
s
p
ee
c
h
,
ca
n
b
e
d
ef
i
n
ed
as
th
e
p
r
o
ce
s
s
o
f
attr
ib
u
tin
g
a
p
ar
t
o
f
s
p
ee
ch
t
o
a
p
ar
ticu
lar
wo
r
d
.
T
h
is
is
u
s
u
ally
ca
lled
p
ar
t
o
f
s
p
ee
ch
m
a
r
k
in
g
(
POS).
I
n
s
im
p
le
ter
m
s
,
POS
tag
g
in
g
is
a
p
r
o
ce
s
s
o
f
l
ab
elin
g
all
t
h
e
wo
r
d
s
in
a
s
en
t
en
ce
with
th
e
i
r
co
r
r
esp
o
n
d
in
g
p
ar
t
o
f
s
p
ee
ch
.
W
e
alr
ea
d
y
k
n
o
w
t
h
at
p
ar
ts
o
f
s
p
ee
ch
in
clu
d
e
n
o
u
n
s
,
v
er
b
s
,
ad
jectiv
es,
p
r
o
n
o
u
n
s
,
ad
v
er
b
s
,
co
n
ju
n
ctio
n
s
,
an
d
th
eir
s
u
b
ca
teg
o
r
ies.
d)
L
em
m
atizin
g
:
L
em
m
atiza
tio
n
r
ef
er
s
to
th
e
p
r
o
ce
s
s
o
f
co
m
b
i
n
in
g
t
h
e
d
if
f
er
e
n
t
in
f
lecte
d
as
p
ec
ts
o
f
a
wo
r
d
to
b
e
an
aly
ze
d
as
o
n
e
s
in
g
le
e
lem
en
t.
L
em
m
atiza
tio
n
wo
r
k
s
s
im
ilar
ly
to
in
f
lectio
n
,
b
u
t
it
g
iv
es
co
n
tex
t
to
wo
r
d
s
.
I
t th
u
s
co
n
n
ec
ts
wo
r
d
s
th
at
h
av
e
a
s
im
ilar
m
ea
n
i
n
g
to
th
e
wo
r
d
.
e)
R
em
o
v
e
s
to
p
-
wo
r
d
:
A
s
to
p
wo
r
d
is
a
co
m
m
o
n
ly
u
s
ed
wo
r
d
(
s
u
ch
as
"th
e"
,
"a
",
"a
n
",
"in
")
th
at
a
s
ea
r
ch
en
g
in
e
h
as
b
ee
n
p
r
o
g
r
am
m
e
d
to
ig
n
o
r
e,
b
o
th
wh
e
n
in
d
ex
in
g
en
tr
ies
f
o
r
s
ea
r
ch
a
n
d
wh
e
n
r
etr
iev
in
g
th
e
m
as
a
r
esu
lt
o
f
a
s
ea
r
ch
q
u
er
y
.
I
n
d
ee
d
,
th
ese
wo
r
d
s
s
h
o
u
ld
n
o
t
o
cc
u
p
y
s
p
ac
e
in
th
e
d
atab
ase
an
d
s
h
o
u
ld
n
o
t
waste
p
r
o
ce
s
s
in
g
tim
e
eith
er
.
I
t
is
p
o
s
s
ib
le
to
elim
in
ate
t
h
e
m
ea
s
ily
b
y
s
to
r
in
g
a
lis
t
o
f
w
o
r
d
s
co
n
s
id
er
ed
as e
m
p
ty
wo
r
d
s
.
3
.
2
.
T
he
na
t
ura
l la
ng
ua
g
e
c
o
m
prehens
io
n uni
t
-
det
ec
t
in
g
inte
nt
T
h
is
u
n
it
is
in
ch
a
r
g
e
o
f
th
e
co
n
v
er
s
io
n
o
f
th
e
u
s
er
'
s
s
tate
m
en
t
in
to
a
p
r
eselecte
d
s
em
a
n
tic
p
atter
n
u
n
d
er
th
e
s
y
s
tem
'
s
r
eq
u
ir
em
en
ts
,
i.e
.
,
in
a
s
y
s
tem
Un
d
er
s
tan
d
ab
le
f
o
r
m
at.
T
h
at
in
clu
d
es
a
lo
ca
tio
n
-
f
illi
n
g
task
with
in
ten
tio
n
d
etec
tio
n
.
Fo
r
in
s
tan
ce
,
th
e
in
t
e
n
tio
n
c
an
b
e
a
g
r
ee
tin
g
,
it
ca
n
b
e
i
n
f
o
r
m
a
tiv
e
wh
er
e
t
h
e
u
s
er
g
iv
es
ex
tr
a
tex
t
d
ata
[
3
8
]
.
T
h
e
task
o
f
p
ad
d
in
g
lo
ca
tio
n
s
a
n
d
in
ten
tio
n
d
etec
tio
n
is
p
er
c
eiv
ed
as
a
s
eq
u
en
ce
lab
elin
g
p
r
o
b
lem
.
As
a
r
esu
lt,
NL
U
is
g
en
er
ally
im
p
lem
e
n
ted
as
an
L
STM
-
b
ased
r
ec
u
r
r
e
n
t
n
eu
r
al
n
etwo
r
k
with
a
co
n
d
itio
n
al
r
an
d
o
m
f
i
eld
(
C
R
F)
lay
er
u
p
war
d
o
f
i
t.
T
h
e
p
r
esen
ted
p
r
o
to
ty
p
e
is
a
Seq
2
Seq
m
o
d
el
u
tili
zin
g
a
b
i
-
d
ir
ec
tio
n
al
L
STM
n
eu
r
al
n
etwo
r
k
,
th
at
f
u
lf
ills
th
e
in
ter
v
als
an
d
p
r
ed
icts
in
ten
tio
n
s
im
u
ltan
eo
u
s
ly
.
Alter
n
ativ
ely
,
th
is
m
o
d
el
d
o
es
th
e
s
am
e
th
in
g
b
y
u
s
in
g
th
e
atten
tio
n
-
b
ased
R
NN.
T
o
co
m
p
lete
th
is
r
eq
u
est,
lab
els in
th
e
d
ata
s
et
co
n
s
is
t o
f
th
e
f
o
l
lo
win
g
: c
o
n
ca
ten
ated
s
tar
t
-
in
s
id
e
-
o
u
ts
id
e
(
B
-
I
-
O
)
m
ar
k
e
r
tag
s
,
in
ten
tio
n
m
a
r
k
er
tag
,
an
d
a
u
x
iliar
y
e
n
d
o
f
s
tr
in
g
(E
-
O
-
S)
m
a
r
k
er
tag
.
a)
L
o
n
g
-
ter
m
an
d
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
m
o
d
el
L
STM
is
a
p
ar
ticu
lar
ty
p
e
o
f
R
NN
th
at
is
s
u
itab
le
f
o
r
tem
p
o
r
al
d
ata
o
r
wh
at
we
ca
ll
s
eq
u
en
tial
d
ata.
L
STM
s
p
r
eser
v
e
th
e
in
f
o
r
m
atio
n
o
v
e
r
tim
e
wh
ich
im
p
lies
th
at
th
ey
ca
n
r
em
e
m
b
er
th
ei
r
p
r
ev
io
u
s
in
p
u
ts
,
th
is
is
wh
y
th
ey
ar
e
h
ig
h
ly
r
ec
o
m
m
en
d
e
d
f
o
r
tim
e
-
s
er
ies
p
r
ed
ictio
n
s
.
with
s
p
ec
if
ic
f
o
r
g
ettin
g
p
o
r
ts
,
b
esid
es
th
e
en
tr
y
an
d
ex
it
p
o
r
ts
o
f
a
s
im
p
le
R
NN.
L
STM
is
m
ad
e
t
o
k
ee
p
r
e
m
em
b
er
i
n
g
t
h
e
en
tr
y
s
tate
f
o
r
a
lo
n
g
er
d
u
r
atio
n
th
an
a
s
in
g
le
R
NN,
th
u
s
en
s
u
r
in
g
ac
c
u
r
ac
y
in
t
h
e
p
r
o
ce
s
s
in
g
o
f
lo
n
g
s
eq
u
en
ce
s
.
Fig
u
r
e
3
s
h
o
ws th
e
lay
o
u
t o
f
a
n
L
STM
ce
ll.
b)
T
h
e
co
n
d
itio
n
al
r
an
d
o
m
f
ield
s
m
o
d
el
(
C
R
F)
T
h
e
m
o
d
el
C
R
F
m
o
d
el
p
(
y
⁄
x,
ω
)
,
u
s
ed
to
p
r
ed
ict
th
e
n
u
m
b
er
o
f
lab
els
(
y
)
f
r
o
m
th
e
s
eq
u
en
ce
s
o
f
m
ea
s
u
r
em
en
ts
(
x
)
,
is
g
iv
en
in
(
1
)
,
wh
er
e
th
e
m
o
d
el
p
ar
am
eter
s
ar
e
g
iv
en
,
ψ
(
x
,
y
)
is
th
e
ch
o
s
en
ch
ar
ac
ter
is
tic
v
ec
to
r
an
d
Ζ
(
ω
,
x
)
is
th
e
cu
m
u
lativ
e
s
u
m
o
f
p
(
y
⁄
x,
ω
)
f
o
r
all
p
o
s
s
ib
le
y
'
s
.
T
h
e
p
ar
am
eter
s
o
f
th
is
m
o
d
el
x
a
n
d
y
ar
e
lear
n
ed
f
r
o
m
a
tr
ai
n
in
g
s
et.
(
,
)
=
{
,
}
,
=
1
,
…
.
,
.
W
ith
=
a
r
g
(
⁄
,
)
th
e
co
n
d
itio
n
al
m
ax
im
u
m
p
r
o
b
ab
ilit
y
.
Fig
u
r
e
4
is
a
r
ep
r
esen
tatio
n
o
f
th
e
L
STM
-
C
R
b
id
ir
ec
tio
n
al
atten
tio
n
m
o
d
el.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
23
,
No
.
2
,
Au
g
u
s
t 2
0
2
1
:
1
2
0
0
-
1
2
1
1
1204
Fig
u
r
e
3
.
L
STM
ce
ll a
r
c
h
itectu
r
e
Fig
u
r
e
4
.
R
ep
r
esen
tatio
n
o
f
b
id
ir
ec
tio
n
al
L
STM
-
C
R
F
atten
ti
o
n
m
o
d
el
(
⁄
,
)
=
(
(
,
)
)
(
,
)
(
1
)
3
.
3
.
T
he
na
t
ura
l la
ng
ua
g
e
g
ener
a
t
io
n uni
t
(
NL
G
)
T
h
is
is
wh
er
e
th
e
g
en
er
atio
n
o
f
tex
t
f
r
o
m
a
r
ep
r
esen
tatio
n
o
f
m
ea
n
in
g
h
a
p
p
en
s
.
T
h
at
p
r
o
ce
s
s
ca
n
b
e
co
n
s
id
er
ed
as
th
e
o
p
p
o
s
ite
o
f
u
n
d
er
s
tan
d
i
n
g
t
h
e
n
at
u
r
al
lan
g
u
ag
e.
W
ith
in
th
e
NL
G,
it
an
s
wer
s
as
a
s
em
an
tic
f
r
am
ewo
r
k
,
co
r
r
esp
o
n
d
in
g
to
a
s
en
ten
ce
in
n
atu
r
al
lan
g
u
a
g
e,
wh
ich
is
u
n
d
e
r
s
to
o
d
b
y
th
e
en
d
-
u
s
er
.
NL
G
co
m
p
o
n
en
ts
ca
n
b
e
m
o
d
el
-
b
a
s
ed
,
r
u
le
-
b
ased
,
o
r
Hy
b
r
id
I
n
s
o
m
e
s
ce
n
ar
io
s
.
T
h
e
r
u
le
-
b
ased
NL
G
p
r
o
d
u
ce
s
p
r
ed
ef
in
e
d
m
o
d
el
s
tatem
en
ts
f
o
r
a
g
iv
en
s
em
an
tic
f
r
am
ew
o
r
k
,
s
o
th
e
y
ar
e
v
er
y
lim
ited
a
n
d
h
av
e
n
o
p
o
we
r
o
f
g
en
er
aliza
tio
n
.
E
v
e
n
th
o
u
g
h
s
ev
er
al
g
en
er
al
-
p
u
r
p
o
s
e
r
u
le
-
b
ased
s
y
s
tem
s
h
av
e
alr
ea
d
y
b
ee
n
d
ev
elo
p
e
d
,
th
ese
ar
e
o
f
ten
d
if
f
icu
lt to
a
d
ap
t to
s
m
all
task
-
o
r
ien
ted
ap
p
licatio
n
s
g
iv
in
g
th
eir
g
en
er
aliza
tio
n
.
Ma
ch
in
e
-
lear
n
in
g
-
b
ased
NL
G
s
y
s
tem
s
h
av
e
b
ec
o
m
e
in
cr
e
asin
g
ly
u
s
ed
in
to
d
a
y
'
s
d
ialo
g
s
y
s
tem
s
.
T
h
ese
NL
G
s
y
s
tem
s
u
s
e
m
u
ltip
le
s
o
u
r
ce
s
as
in
p
u
ts
,
in
cl
u
d
in
g
th
e
c
o
n
ten
t
m
ap
,
wh
ic
h
is
a
m
ea
n
in
g
f
u
l
r
ep
r
esen
tatio
n
o
f
wh
at
n
ee
d
s
to
b
e
d
eliv
er
e
d
to
th
e
u
s
er
.
A
k
n
o
wled
g
e
b
ase,
as
a
s
tr
u
ctu
r
ed
d
atab
ase
th
at
p
r
o
v
id
es
d
o
m
ain
-
sp
ec
if
ic
ch
a
r
ac
ter
is
tics
.
T
h
e
User
Mo
d
el
p
r
o
v
id
es
co
n
s
tr
ain
ts
to
th
e
o
u
tp
u
t
s
tatem
en
t.
T
h
e
d
ialo
g
h
is
to
r
y
g
iv
es in
f
o
r
m
ati
o
n
o
n
th
e
p
r
ev
io
u
s
r
o
u
n
d
s
t
o
p
r
ev
en
t r
ef
e
r
en
ce
e
x
p
r
ess
io
n
s
a
n
d
r
ep
etitio
n
.
3
.
4
.
Dia
lo
g
m
a
na
g
e
m
ent
(
D
M
)
T
h
e
DM
ca
n
b
e
co
n
n
ec
ted
to
an
e
x
ter
n
al
d
atab
ase
o
r
a
k
n
o
wled
g
e
b
ase
to
tr
ig
g
e
r
m
o
r
e
m
ea
n
in
g
f
u
l
r
esp
o
n
s
es
[
3
9
]
.
T
h
e
d
ialo
g
u
e
m
an
ag
e
r
h
as
two
co
m
p
o
n
en
ts
:
Dialo
g
u
e
s
tate
tr
ac
k
in
g
(
DST)
an
d
p
o
licy
lear
n
in
g
th
at
is
th
e
r
ein
f
o
r
ce
m
en
t
lear
n
in
g
ag
en
t
(
R
L
)
.
DST
is
a
co
m
p
lex
an
d
cr
u
cial
co
m
p
o
n
en
t
to
co
r
r
ec
tly
in
f
er
th
e
s
tate
o
f
co
n
v
ictio
n
o
f
d
ialo
g
u
e,
co
n
s
id
er
in
g
th
e
w
h
o
le
h
is
to
r
y
u
p
to
th
is
p
o
in
t.
Po
licy
L
ea
r
n
in
g
is
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
To
w
a
r
d
s
d
ev
elo
p
in
g
a
p
o
ck
et
t
h
era
p
is
t:
a
n
in
tellig
en
t
a
d
a
p
tive
p
s
yc
h
o
lo
g
ica
l su
p
p
o
r
t
…
(
I
n
tis
s
a
r
S
a
lh
i
)
1205
r
esp
o
n
s
ib
le
f
o
r
s
elec
tin
g
th
e
b
est
ac
tio
n
,
i.e
.
,
th
e
s
y
s
tem
'
s
a
n
s
wer
to
th
e
u
s
er
'
s
s
ta
tem
en
t,
to
b
r
in
g
th
e
u
s
er
to
r
ea
ch
its
o
b
jecti
v
e
in
a
m
in
im
u
m
n
u
m
b
er
o
f
d
ialo
g
u
e
c
y
cles.
3
.
5
.
Respo
ns
e
g
ener
a
t
io
n:
re
info
rc
em
ent
lea
rning
wit
h
Seq2
Seq
R
ein
f
o
r
ce
d
L
ea
r
n
in
g
is
a
f
i
eld
o
f
m
ac
h
i
n
e
lear
n
in
g
.
I
t
in
v
o
lv
es
tak
in
g
a
p
p
r
o
p
r
iate
ac
tio
n
s
to
m
ax
im
ize
r
ewa
r
d
s
in
a
p
a
r
ticu
lar
s
itu
atio
n
.
R
ein
f
o
r
ce
m
e
n
t
lear
n
in
g
is
u
s
ed
b
y
a
v
ar
ie
ty
o
f
s
o
f
twar
e
an
d
m
ac
h
in
es
to
f
in
d
th
e
b
est
b
e
h
av
io
r
o
r
p
ath
i
n
a
s
p
ec
if
ic
s
itu
atio
n
.
I
t
d
if
f
er
s
f
r
o
m
s
u
p
er
v
i
s
ed
lear
n
in
g
in
th
e
s
en
s
e
th
at
in
s
u
p
er
v
is
ed
lear
n
in
g
,
th
e
tr
ain
in
g
d
ata
is
ac
co
m
p
an
ied
b
y
an
an
s
wer
k
ey
,
s
o
th
at
th
e
m
o
d
el
is
tr
ain
ed
with
th
e
c
o
r
r
ec
t
a
n
s
wer
its
elf
,
wh
er
ea
s
in
r
ein
f
o
r
ce
m
en
t
lear
n
in
g
,
th
er
e
is
n
o
an
s
we
r
b
u
t
th
e
r
ein
f
o
r
ce
r
d
ec
id
es
wh
at
to
d
o
to
ac
co
m
p
l
is
h
th
e
g
iv
en
task
s
.
I
n
ab
s
en
ce
o
f
a
s
et
o
f
tr
ai
n
in
g
d
ata,
h
o
wev
er
,
it
is
ex
p
ec
ted
to
lear
n
f
r
o
m
its
ex
p
er
ie
n
ce
.
a)
R
ec
u
r
r
en
t n
eu
r
al
n
etwo
r
k
A
r
ec
u
r
r
en
t
n
eu
r
al
n
etwo
r
k
(
R
NN)
[
4
0
]
is
d
esig
n
ed
to
p
r
eser
v
e
th
e
p
r
ev
io
u
s
s
tate
o
f
n
eu
r
o
n
s
.
T
h
is
allo
ws
th
e
n
eu
r
al
n
etwo
r
k
to
p
r
eser
v
e
th
e
co
n
tex
t
an
d
p
r
o
d
u
ce
a
r
esu
lt
b
ased
o
n
th
e
p
r
ev
io
u
s
s
tate.
T
h
i
s
ap
p
r
o
ac
h
m
a
k
es
R
NNs
d
esira
b
le
f
o
r
ch
atb
o
ts
,
as
it
is
ess
en
tial
t
o
p
r
eser
v
e
th
e
co
n
te
x
t
o
f
a
co
n
v
e
r
s
atio
n
to
u
n
d
e
r
s
tan
d
th
e
u
s
er
.
b)
Seq
u
en
ce
to
s
eq
u
e
n
ce
m
o
d
el
T
h
e
s
eq
2
Seq
m
o
d
els
[
4
1
]
a
r
e
b
ased
o
n
R
NN
ar
ch
itectu
r
e
an
d
c
o
n
s
is
t
o
f
two
R
NNs:
o
n
e
en
co
d
er
a
n
d
o
n
e
d
ec
o
d
er
.
W
h
ile
th
e
en
co
d
er
p
r
o
ce
s
s
es
th
e
in
p
u
t,
th
e
d
ec
o
d
er
d
ea
ls
with
th
e
o
u
tp
u
t.
T
h
ese
m
o
d
els
ca
n
b
e
c
o
n
s
id
er
ed
as
a
d
ec
o
d
er
n
o
d
e
th
at
p
r
o
d
u
ce
s
a
c
o
r
r
e
s
p
o
n
d
in
g
o
u
t
p
u
t
to
an
e
n
co
d
er
n
o
d
e.
T
h
is
m
o
d
el
is
ea
s
y
to
u
s
e
in
m
ac
h
i
n
e
tr
an
s
latio
n
b
ec
au
s
e
a
wo
r
d
co
r
r
esp
o
n
d
in
g
to
t
h
e
o
u
tp
u
t
lan
g
u
ag
e
ca
n
b
e
g
en
er
ated
b
y
th
e
d
ec
o
d
e
r
ea
s
ily
b
y
lo
o
k
i
n
g
at
o
n
ly
o
n
e
wo
r
d
o
f
th
e
in
p
u
t
lan
g
u
ag
e
at
a
tim
e.
T
h
e
f
o
llo
win
g
f
ig
u
r
e
s
h
o
ws
a
s
im
p
le
s
eq
u
en
ce
m
o
d
el.
W
ith
is
in
p
u
t
s
eq
u
e
n
ce
at
s
tep
I
,
ℎ
th
e
h
id
d
en
s
tate
f
o
r
ea
ch
tim
e
s
tep
,
an
d
is
o
u
tp
u
t
s
eq
u
en
ce
at
s
tep
i.
Fig
u
r
e
5
is
a
r
ep
r
esen
tatio
n
o
f
th
e
s
eq
u
en
c
e
m
o
d
el.
Fig
u
r
e
5
.
T
h
e
s
eq
u
e
n
ce
-
to
-
s
eq
u
en
ce
m
o
d
el
s
tr
u
ctu
r
e
T
h
e
en
c
o
d
er
an
d
th
e
d
ec
o
d
er
ar
e
L
STM
m
o
d
els
(
o
r
s
o
m
etim
es
GR
U
m
o
d
els).
T
h
e
en
co
d
e
r
in
ter
p
r
ets
th
e
in
p
u
t
s
eq
u
en
ce
an
d
s
y
n
th
esizes
th
e
d
ata
in
to
wh
at
is
k
n
o
wn
as
in
ter
n
al
s
tat
e
v
ec
to
r
s
as
well
a
s
co
n
tex
t
v
ec
to
r
s
(
in
th
e
ca
s
e
o
f
th
e
L
STM
th
ey
ar
e
ca
lled
th
e
h
id
d
en
s
tate
v
ec
to
r
s
o
r
ce
ll
s
t
ates)
.
T
h
e
en
co
d
er
o
u
tp
u
ts
ar
e
elim
in
ated
s
o
th
at
o
n
ly
th
e
in
ter
n
al
s
tates
ar
e
r
etain
ed
.
T
h
e
p
u
r
p
o
s
e
o
f
th
e
c
o
n
tex
t
v
ec
to
r
is
th
e
in
teg
r
atio
n
o
f
d
ata
f
r
o
m
all
in
p
u
ts
to
ass
is
t
th
e
d
ec
o
d
er
t
o
m
ak
e
ac
cu
r
ate
p
r
ed
ictio
n
s
.
T
h
e
h
id
d
en
s
tates
ℎ
ar
e
ca
lcu
lated
u
s
in
g
th
e
(
2
)
.
ℎ
=
(
(
ℎℎ
)
ℎ
−
1
+
(
ℎ
)
ℎ
)
(
2
)
T
h
e
L
STM
r
ea
d
s
th
e
d
ata,
s
eq
u
en
ce
a
f
ter
s
eq
u
e
n
ce
.
T
h
u
s
,
if
th
e
e
n
tr
y
h
as
a
s
eq
u
en
ce
o
f
l
en
g
th
"
n
",
it is
s
aid
th
at
th
e
L
STM
r
ea
d
s
it in
tim
e
s
tep
s
"n
".
T
h
e
d
ec
o
d
er
is
an
L
STM
w
ith
in
itial
s
tat
es in
itialized
to
th
e
f
in
al
s
tates
o
f
th
e
L
STM
e
n
co
d
er
,
i.e
.
,
th
e
c
o
n
tex
t
v
ec
to
r
o
f
th
e
f
in
al
en
c
o
d
er
ce
ll
is
en
ter
e
d
in
to
t
h
e
f
ir
s
t
ce
ll
o
f
th
e
d
ec
o
d
er
n
etwo
r
k
.
B
y
u
s
in
g
th
ese
in
itial
s
tates,
th
e
d
e
co
d
er
s
tar
ts
to
g
en
e
r
ate
th
e
o
u
tp
u
t
s
eq
u
en
ce
,
an
d
th
ese
r
esu
lts
ar
e
also
tak
en
in
to
ac
co
u
n
t
f
o
r
f
u
tu
r
e
o
u
tp
u
ts
.
A
p
ile
o
f
s
ev
er
al
L
STM
u
n
its
wh
er
e
p
r
ed
icts
an
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
23
,
No
.
2
,
Au
g
u
s
t 2
0
2
1
:
1
2
0
0
-
1
2
1
1
1206
o
u
tp
u
t
at
tim
e
s
tep
n
.
E
v
e
r
y
r
ec
u
r
r
in
g
u
n
it
ac
ce
p
ts
a
h
id
d
en
s
tate
f
r
o
m
th
e
p
r
e
v
io
u
s
u
n
it
a
n
d
g
e
n
er
ates
an
d
o
u
tp
u
ts
its
h
id
d
en
s
tate.
An
y
h
id
d
en
s
tate
ℎ
is
ca
lcu
lated
u
s
in
g
th
e
(
3
)
.
ℎ
=
(
(
ℎℎ
)
ℎ
−
1
)
(
3
)
An
d
th
e
o
u
tp
u
t
at
th
e
tim
e
s
tep
n
is
ca
lcu
lated
u
s
in
g
th
e
(
4
)
.
=
(
ℎ
)
(
4
)
T
h
e
o
u
tp
u
ts
ar
e
ca
lcu
lated
b
y
th
e
u
s
e
o
f
t
h
e
h
i
d
d
en
s
tate
at
th
e
cu
r
r
en
t
tim
e
s
tep
an
d
th
e
r
esp
ec
tiv
e
weig
h
t
W
(
S).
So
f
tm
ax
is
u
s
ed
to
cr
ea
te
a
p
r
o
b
a
b
ilit
y
v
ec
to
r
th
at
will
h
elp
to
d
eter
m
in
e
t
h
e
f
in
al
o
u
tp
u
t
(
f
o
r
ex
am
p
le,
it is
a
wo
r
d
in
a
q
u
esti
o
n
-
an
s
wer
p
r
o
b
lem
)
[
4
2
]
.
4.
RE
SU
L
T
S
AND
D
I
SCU
SS
I
O
N
T
h
e
f
ir
s
t
s
tep
is
th
e
co
llectio
n
o
f
d
ata
f
r
o
m
th
e
R
ed
d
it
web
s
ite,
th
e
aim
o
f
th
is
s
tep
is
to
p
r
o
v
id
e
th
e
Data
b
ase,
A
f
r
ac
tio
n
o
f
th
e
s
cr
ap
p
in
g
p
r
o
g
r
am
co
d
e
is
d
is
p
lay
ed
in
F
ig
u
r
e
6
.
T
h
is
p
ar
t
is
ess
en
tial
s
in
ce
a
d
atab
ase
th
at
m
ee
ts
th
e
r
e
q
u
i
r
em
en
ts
o
f
t
h
is
p
r
o
b
lem
is
n
o
t
av
ailab
le.
A
s
elec
tio
n
o
f
s
u
b
-
d
ir
ec
t
o
r
ies
(
s
u
b
-
R
ed
d
it)
h
as
b
ee
n
m
ad
e
,
to
h
a
v
e
o
n
ly
th
e
q
u
esti
o
n
s
an
d
a
n
s
wer
s
o
n
m
en
tal
d
is
o
r
d
er
s
.
T
h
e
s
elec
ted
s
u
b
-
R
ed
d
it
ar
e
an
x
iety
,
d
ep
r
ess
io
n
,
s
tr
ess
,
d
ep
r
ess
io
n
_
h
el
p
,
talk
-
th
e
r
ap
y
,
ask
ath
er
ap
is
t,
as sh
o
wn
in
th
e
Fig
u
r
e
6
,
Fig
u
r
e
6
.
C
o
llectin
g
Su
b
R
ed
d
its
f
r
o
m
th
e
R
ed
d
it we
b
s
ite
T
h
e
d
atab
ase
is
co
m
p
letely
n
ew,
it
is
p
r
ep
a
r
ed
esp
ec
iall
y
f
o
r
th
is
ch
atb
o
t
b
ec
a
u
s
e
it
in
c
lu
d
es
q
u
esti
o
n
s
an
d
an
s
wer
s
o
n
is
s
u
es
o
f
m
en
tal
h
ea
lth
s
u
ch
as
d
ep
r
ess
io
n
an
d
an
x
iety
,
wh
et
h
er
in
C
OVI
D
-
19
o
r
n
o
t,
as
well
as
th
er
a
p
is
t's
an
s
wer
s
th
at
ca
n
b
e
b
e
n
ef
icial.
Fig
u
r
e
7
s
h
o
ws
th
e
f
ir
s
t
5
n
e
g
ativ
e
an
d
p
o
s
itiv
e
q
u
esti
o
n
s
,
Fig
u
r
e
7
.
T
h
e
f
ir
s
t 5
p
o
s
itiv
e
a
n
d
n
eg
ativ
e
q
u
esti
o
n
s
Af
ter
th
e
ex
ec
u
tio
n
o
f
th
e
c
o
d
e
p
r
esen
ted
in
Fig
u
r
e
6
,
5
7
3
5
q
u
esti
o
n
s
wer
e
co
llected
,
o
f
wh
ich
4
0
.
5
4
%
wer
e
n
eg
ativ
es,
3
8
.
7
9
%
wer
e
n
eu
tr
al
an
d
2
0
.
6
6
%
wer
e
p
o
s
itiv
es.
T
h
is
is
p
r
esen
te
d
b
y
th
e
d
iag
r
a
m
in
Fig
u
r
e
8
.
I
n
th
is
s
ec
tio
n
,
t
h
e
v
er
if
icatio
n
o
f
th
e
f
r
eq
u
en
cies
o
f
o
cc
u
r
r
en
ce
is
n
ec
ess
ar
y
to
v
alid
ate
th
e
co
llected
d
atab
ase.
T
o
v
alid
at
e
it,
it
is
n
ec
es
s
ar
y
to
h
av
e
p
o
s
itiv
e
wo
r
d
s
.
B
ec
au
s
e
th
e
ch
at
b
o
t
h
as
a
d
ep
r
ess
ed
o
r
an
x
i
o
u
s
p
er
s
o
n
in
f
r
o
n
t
o
f
it,
it
m
u
s
t
r
ea
s
s
u
r
e
h
im
an
d
lead
a
s
er
io
u
s
co
n
v
er
s
atio
n
wit
h
h
im
.
th
e
p
ip
elin
e
s
tep
s
o
f
th
e
n
atu
r
al
lan
g
u
a
g
e
p
r
o
ce
s
s
in
g
wer
e
f
o
llo
wed
an
d
th
e
ca
lcu
latio
n
o
f
wo
r
d
s
ap
p
ea
r
an
ce
f
r
eq
u
e
n
cies
is
d
o
n
e.
T
a
b
le
1
s
h
o
ws
th
e
f
r
e
q
u
en
cy
o
f
ap
p
ea
r
an
ce
o
f
t
h
e
m
o
s
t
co
m
m
o
n
n
e
g
ati
v
e
a
n
d
p
o
s
itiv
e
wo
r
d
s
in
t
h
e
co
llected
q
u
esti
o
n
s
.
f
or
s
ub
m
i
s
s
i
o
n
i
n
r
edd
i
t
.
s
u
b
r
edd
i
t
(
'
a
nx
i
e
t
y+
depr
es
s
i
o
n
+
s
t
r
es
s
+
depr
es
s
i
o
n_
h
e
l
p
+
t
alkt
h
er
ap
y
+
as
kat
h
er
ap
i
s
t
+
C
or
o
n
a
vi
r
u
s
'
)
.
n
ew
(
l
i
m
i
t
=
No
n
e)
:
h
ea
d
l
i
nes
.
add(
s
ub
m
i
s
s
i
o
n
.
t
i
t
l
e
)
di
s
p
l
a
y
.
c
l
ea
r
_o
u
t
p
ut
(
)
pr
i
n
t
(
l
e
n
(
h
ea
d
l
i
nes
)
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
To
w
a
r
d
s
d
ev
elo
p
in
g
a
p
o
ck
et
t
h
era
p
is
t:
a
n
in
tellig
en
t
a
d
a
p
tive
p
s
yc
h
o
lo
g
ica
l su
p
p
o
r
t
…
(
I
n
tis
s
a
r
S
a
lh
i
)
1207
Fig
u
r
e
8
.
Qu
esti
o
n
d
is
tr
ib
u
tio
n
o
f
q
u
esti
o
n
s
co
llected
f
r
o
m
R
ed
d
it
T
ab
le
1
.
W
o
r
d
ap
p
ea
r
a
n
ce
f
r
e
q
u
en
cies
P
o
si
t
i
v
e
Ti
t
l
e
s
N
e
g
a
t
i
v
e
Ti
t
l
e
s
W
o
r
d
A
p
p
e
a
r
a
n
c
e
F
r
e
q
u
e
n
c
y
W
o
r
d
A
p
p
e
a
r
a
n
c
e
F
r
e
q
u
e
n
c
y
H
e
l
p
2
4
2
S
t
r
e
ss
2
3
2
Li
k
e
1
6
0
D
e
p
r
e
ss
i
o
n
1
9
8
Th
e
r
a
p
i
st
1
2
3
A
n
x
i
e
t
y
1
8
4
F
e
e
l
1
1
4
Th
e
r
a
p
i
st
1
6
6
N
e
e
d
82
F
e
e
l
1
5
3
Th
e
r
a
p
y
76
Li
f
e
98
P
l
e
a
s
e
68
G
e
t
95
A
n
x
i
e
t
y
64
Th
e
r
a
p
y
86
G
e
t
60
Li
k
e
86
A
n
y
o
n
e
51
S
t
r
e
sse
d
85
K
n
o
w
50
W
a
n
t
77
S
o
me
o
n
e
47
B
a
d
76
F
r
i
e
n
d
46
A
n
y
o
n
e
72
Li
f
e
45
F
e
e
l
i
n
g
69
Lo
v
e
44
K
n
o
w
66
G
o
o
d
42
D
e
p
r
e
ss
e
d
65
B
e
st
41
S
t
o
p
63
B
e
t
t
e
r
40
H
e
l
p
57
S
t
r
e
ss
39
El
se
56
O
n
e
36
P
e
o
p
l
e
55
Fig
u
r
es
9
an
d
1
0
s
h
o
w
th
e
f
r
e
q
u
en
cy
d
is
tr
ib
u
tio
n
s
o
f
th
e
m
o
s
t
co
m
m
o
n
l
y
u
s
ed
wo
r
d
s
in
t
h
e
p
o
s
itiv
e
an
d
n
eg
ativ
e
s
ets,
r
esp
ec
tiv
ely
.
T
h
e
f
r
e
q
u
en
c
y
o
f
ap
p
ea
r
an
ce
o
f
p
o
s
itiv
e
wo
r
d
s
is
m
o
r
e
im
p
o
r
tan
t
th
a
n
n
eg
ativ
e
wo
r
d
s
.
T
h
is
is
ex
t
r
em
ely
v
al
u
ab
le,
c
o
n
s
id
er
in
g
th
at
th
e
ch
atb
o
t
m
u
s
t
ca
r
r
y
o
n
a
p
o
s
itiv
e
co
n
v
er
s
atio
n
an
d
th
u
s
h
as
to
ex
p
r
ess
its
elf
in
a
way
th
at
m
ak
es
it
f
ee
l
co
m
f
o
r
tab
le
f
o
r
t
h
e
p
er
s
o
n
f
ac
in
g
it.
Af
ter
co
m
p
letin
g
t
h
e
s
tep
s
o
f
th
e
n
atu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
u
n
it,
we
m
o
v
ed
o
n
to
th
e
n
atu
r
al
lan
g
u
ag
e
co
m
p
r
eh
e
n
s
io
n
u
n
it
an
d
tr
ain
ed
o
u
r
d
ata
th
r
o
u
g
h
th
e
s
eq
u
e
n
ce
-
to
-
s
eq
u
e
n
ce
r
e
-
in
f
o
r
m
atio
n
m
o
d
el
b
u
ilt
u
s
in
g
th
e
T
en
s
o
r
Flo
w
f
r
am
ew
o
r
k
[
4
3
]
an
d
th
e
Ker
as
API
[
4
4
]
;
with
5
0
ep
o
c
h
s
.
Fig
u
r
es
1
1
,
1
2
an
d
1
3
s
h
o
w
th
e
r
esu
lts
o
f
th
e
tr
ain
in
g
o
f
o
u
r
m
o
d
el
ar
e
f
o
r
ep
o
ch
s
1
,
5
,
a
n
d
5
0
.
Fig
u
r
e
9
.
Fre
q
u
en
cy
d
is
tr
ib
u
ti
o
n
o
f
t
h
e
ap
p
ea
r
an
ce
o
f
p
o
s
itiv
e
wo
r
d
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
23
,
No
.
2
,
Au
g
u
s
t 2
0
2
1
:
1
2
0
0
-
1
2
1
1
1208
Fig
u
r
e
1
0
.
Fre
q
u
en
c
y
d
is
tr
ib
u
t
io
n
o
f
t
h
e
ap
p
ea
r
an
ce
o
f
n
e
g
ativ
e
wo
r
d
s
Fig
u
r
e
1
1
.
T
r
ain
in
g
in
ep
o
ch
1
Fig
u
r
e
1
2
.
T
r
ain
in
g
in
ep
o
ch
5
Fig
u
r
e
1
3
.
T
r
ain
in
g
in
ep
o
ch
5
0
T
h
e
m
o
d
el
h
as a
n
ac
cu
r
ac
y
o
f
9
5
%,
th
is
is
ca
lcu
lated
u
s
in
g
t
h
e
(5
)
,
=
1
−
(5
)
T
h
e
co
m
p
ar
is
o
n
b
etwe
en
th
e
p
r
ed
ictio
n
s
an
d
th
e
tar
g
ets
is
m
o
r
e
in
ter
esti
n
g
,
if
b
o
th
ar
e
t
h
e
s
am
e
it
m
ea
n
s
th
at
th
e
ch
atb
o
t
is
p
er
f
o
r
m
in
g
p
r
o
p
er
ly
.
T
h
is
ju
s
tifie
s
th
e
d
ec
is
io
n
to
d
is
p
lay
th
e
m
o
n
th
e
s
cr
ee
n
s
.
ch
atb
o
ts
th
at
tr
ea
t
s
p
ec
if
ic
m
en
tal
h
ea
lth
in
th
e
co
n
tex
t
o
f
a
p
a
n
d
em
ic
s
u
c
h
as
th
e
o
n
e
r
elate
d
to
C
OVI
D
-
19
.
T
h
e
o
th
e
r
s
ar
e
m
o
r
e
g
e
n
er
al.
T
h
e
ap
p
r
o
ac
h
t
r
ea
ts
em
o
tio
n
s
,
wh
ile
th
e
o
th
e
r
s
d
o
n
o
t.
Desp
ite
all
th
is
,
we
t
ested
s
o
m
e
s
y
s
tem
s
with
th
e
co
llected
d
ata
b
ase,
th
e
r
esu
lts
wer
e
d
if
f
er
e
n
t
b
u
t
n
o
t
v
er
y
f
a
r
f
r
o
m
o
u
r
s
.
t
h
is
ca
n
b
e
ex
p
lain
e
d
b
y
th
e
f
ac
t
th
at
th
ese
s
y
s
tem
s
ar
e
n
o
t
d
esig
n
ed
in
th
e
s
am
e
co
n
te
x
t
an
d
d
o
n
o
t
tak
e
em
o
tio
n
s
in
to
ac
co
u
n
t.
Af
te
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
To
w
a
r
d
s
d
ev
elo
p
in
g
a
p
o
ck
et
t
h
era
p
is
t:
a
n
in
tellig
en
t
a
d
a
p
tive
p
s
yc
h
o
lo
g
ica
l su
p
p
o
r
t
…
(
I
n
tis
s
a
r
S
a
lh
i
)
1209
tr
ain
in
g
o
u
r
m
o
d
el,
we
in
teg
r
ated
th
e
n
atu
r
al
lan
g
u
a
g
e
co
m
p
r
eh
en
s
io
n
u
n
it
in
to
a
th
er
a
p
is
t
ch
atb
o
t
th
at
we
h
av
e
im
p
lem
e
n
ted
.
Fig
u
r
e
1
4
s
h
o
ws
th
e
g
r
ap
h
ical
in
te
r
f
ac
e
o
f
th
e
th
e
r
ap
is
t
ch
atb
o
t.
W
e
wer
e
ab
le
to
b
u
ild
a
ch
atb
o
t
th
at
an
s
wer
s
o
u
r
in
itia
l
p
r
o
b
lem
,
it
ca
n
co
n
d
u
ct
a
d
ia
lo
g
u
e
with
a
p
e
r
s
o
n
in
a
f
lu
id
an
d
clea
r
way
.
T
h
e
ch
atb
o
t'
s
an
s
wer
i
s
in
th
e
f
o
r
m
o
f
te
x
t
an
d
v
o
ice.
T
h
is
ca
n
f
ac
ilit
ate
in
ter
ac
tio
n
with
th
e
ch
atb
o
t.
T
h
e
m
ain
co
n
ce
r
n
t
h
at
o
cc
u
r
s
is
th
at
h
e
d
o
es n
o
t r
esp
o
n
d
i
n
th
e
s
am
e
way
to
m
ess
ag
es h
e
h
as n
ev
e
r
s
ee
n
b
ef
o
r
e.
Fig
u
r
e
1
4
.
T
h
e
g
r
ap
h
ical
in
t
e
r
f
ac
e
o
f
th
e
th
er
ap
is
t c
h
atb
o
t
5.
C
O
NCLU
SI
O
N
I
n
th
is
p
ap
er
,
we
h
av
e
tr
ie
d
to
d
ev
elo
p
a
ch
atb
o
t
s
y
s
tem
b
ased
o
n
th
e
s
eq
u
en
tial
atten
tio
n
m
ec
h
an
is
m
b
ased
o
n
d
ee
p
r
e
cu
r
r
en
t
n
e
u
r
al
n
etwo
r
k
s
f
o
r
p
s
y
ch
o
lo
g
ical
q
u
e
r
ies,
to
h
elp
p
eo
p
le
af
f
ec
te
d
b
y
m
en
tal
h
ea
lth
d
is
o
r
d
er
s
,
esp
e
cially
,
s
tu
d
en
ts
in
C
OVI
D
-
19
p
an
d
e
m
ic
s
itu
atio
n
.
W
e
p
r
o
p
o
s
ed
an
ad
v
a
n
ce
d
ar
ch
itectu
r
e
o
f
an
ad
a
p
tiv
e
t
h
er
ap
eu
tic
ch
at
b
o
t
with
s
elf
-
lear
n
in
g
ab
ilit
ies.
T
h
is
was
d
esig
n
ed
with
th
e
p
r
in
cip
al
o
b
jectiv
e
t
o
f
ill
i
n
a
h
ea
lth
ca
r
e
g
ap
in
th
e
C
OVI
D
-
19
p
an
d
em
ic
s
itu
atio
n
a
n
d
to
p
r
o
v
id
e
a
f
le
x
ib
le
c
h
at
in
ter
f
ac
e
to
an
s
wer
q
u
esti
o
n
s
f
r
o
m
p
eo
p
le
wh
o
f
ee
l
o
v
er
wh
elm
ed
b
y
th
e
ev
e
n
ts
.
T
h
e
Seq
2
Seq
m
o
d
e
p
r
esen
ted
in
th
e
p
ap
e
r
was b
u
i
lt
u
s
in
g
th
e
T
en
s
o
r
Flo
w
f
r
am
e
wo
r
k
a
n
d
th
e
Ker
as
API
.
T
h
e
p
er
f
o
r
m
an
ce
o
f
th
e
m
o
d
el
was
lim
ited
d
u
e
to
th
e
lim
ited
tr
ain
in
g
;
h
o
we
v
er
,
th
e
p
ap
er
s
h
o
ws
th
e
u
s
e
o
f
a
d
at
ab
ased
ap
p
r
o
ac
h
in
th
e
co
n
s
tr
u
ctio
n
o
f
th
e
ch
at
b
o
t.
Sig
n
if
ican
t
r
esu
lts
ca
n
b
e
ac
h
iev
ed
b
o
th
b
y
u
s
in
g
h
ig
h
-
p
er
f
o
r
m
a
n
ce
co
m
p
u
tatio
n
al
to
o
ls
an
d
b
y
m
o
d
if
y
in
g
th
e
tr
ain
in
g
h
y
p
er
p
ar
am
eter
s
.
T
h
ese
will
b
e
ta
k
en
in
to
ac
co
u
n
t
in
f
u
tu
r
e
s
tu
d
ies.
th
is
in
clu
d
es
also
th
e
o
p
tim
izatio
n
o
f
t
h
e
ch
atb
o
t
u
tili
zin
g
th
e
m
o
s
t
r
ec
en
t
o
p
tim
izatio
n
m
eth
o
d
s
wh
ich
a
r
e
th
e
Gar
r
a
R
u
f
a
o
p
tim
izatio
n
,
th
e
C
W
O,
an
d
th
e
E
HO
o
p
tim
izatio
n
.
ACK
NO
WL
E
DG
E
M
E
NT
T
h
is
wo
r
k
is
s
u
p
p
o
r
ted
b
y
th
e
Un
iv
er
s
ity
Hass
an
I
I
o
f
C
asab
lan
ca
-
Mo
r
o
cc
o
an
d
T
h
e
Natio
n
a
l
Scien
tific
R
esear
ch
an
d
T
ec
h
n
o
lo
g
y
C
en
ter
(
C
NR
ST)
u
n
d
e
r
th
e
p
r
o
g
r
am
“su
p
p
o
r
t
p
r
o
g
r
a
m
f
o
r
s
cien
tific
an
d
tech
n
o
lo
g
ical
r
esear
ch
r
elate
d
to
C
OVI
D
-
19
”,
p
r
o
ject
"E
lab
o
r
atio
n
o
f
a
p
s
y
ch
o
lo
g
i
ca
l
an
d
p
ed
ag
o
g
ical
s
u
p
p
o
r
t
p
latf
o
r
m
".
RE
F
E
R
E
NC
E
S
[1
]
R.
Ro
d
ríg
u
e
z
-
Re
y
,
H.
G
a
rrid
o
-
He
rn
a
n
sa
iz,
a
n
d
S
.
Co
l
lad
o
,
“
P
sy
c
h
o
l
o
g
ica
l
Im
p
a
c
t
a
n
d
As
so
c
iate
d
F
a
c
to
rs
Du
ri
n
g
th
e
In
it
ial
S
tag
e
o
f
t
h
e
C
o
ro
n
a
v
ir
u
s
(COV
ID
-
1
9
)
P
a
n
d
e
m
ic
Am
o
n
g
t
h
e
G
e
n
e
ra
l
P
o
p
u
lati
o
n
in
S
p
a
i
n
,
”
Fro
n
ti
e
rs
i
n
Psy
c
h
o
lo
g
y
,
v
o
l.
11
,
p
.
1
5
4
0
,
2
0
2
0
,
d
o
i:
1
0
.
3
3
8
9
/fp
s
y
g
.
2
0
2
0
.
0
1
5
4
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.