I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
15
,
No
.
2
,
A
p
r
il
20
25
,
p
p
.
1
8
8
0
~
1
8
8
8
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
15
i
2
.
pp
1
8
8
0
-
1
8
8
8
1880
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Stress
de
tec
tion t
hro
ug
h weara
ble
sens
o
rs
:
a
co
nv
o
lutiona
l
neura
l
net
wo
rk
-
b
a
sed
a
ppro
a
ch usi
ng
heart rat
e and
step data
Rif
k
i Wij
a
y
a
,
G
a
m
ma
K
o
s
a
l
a
S
c
h
o
o
l
o
f
C
o
m
p
u
t
i
n
g
,
Te
l
k
o
m U
n
i
v
e
r
si
t
y
,
B
a
n
d
u
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
Ap
r
1
,
2
0
2
4
R
ev
is
ed
Oct
2
,
2
0
2
4
Acc
ep
ted
Oct
2
3
,
2
0
2
4
Wi
th
t
h
e
c
u
rre
n
t
tec
h
n
o
l
o
g
ica
l
a
d
v
a
n
c
e
m
e
n
ts,
p
a
rti
c
u
larl
y
in
se
n
sin
g
tec
h
n
o
l
o
g
ies
,
m
o
n
it
o
rin
g
v
a
rio
u
s
h
e
a
lt
h
a
sp
e
c
ts,
in
c
lu
d
in
g
h
e
a
rt
ra
te,
h
a
s
b
e
c
o
m
e
fe
a
sib
le.
Th
e
p
ro
b
lem
a
d
d
re
ss
e
d
in
th
is
stu
d
y
is
t
h
e
n
e
e
d
fo
r
e
ffe
c
ti
v
e
stre
ss
d
e
tec
ti
o
n
m
e
th
o
d
s
to
m
it
ig
a
te t
h
e
sig
n
if
ica
n
t
c
o
n
se
q
u
e
n
c
e
s o
f
h
ig
h
-
in
te
n
sity
o
r
l
o
n
g
-
term
stre
ss
,
wh
ic
h
imp
a
c
ts
sa
fe
ty
a
n
d
d
isru
p
ts
n
o
rm
a
l
ro
u
ti
n
e
s.
We
p
ro
p
o
se
a
stre
ss
d
e
tec
ti
o
n
sy
ste
m
d
e
v
e
l
o
p
e
d
b
a
s
e
d
o
n
t
h
e
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
(
CNN
)
m
e
th
o
d
to
a
d
d
re
ss
t
h
is.
Th
e
stu
d
y
in
v
o
lv
e
s
u
n
i
v
e
rsity
stu
d
e
n
ts
a
g
e
d
2
0
–
2
2
,
f
o
c
u
sin
g
o
n
m
e
n
tal
st
re
ss
.
Th
e
d
a
tas
e
t
e
n
c
o
m
p
a
ss
e
s
p
a
ra
m
e
ters
su
c
h
a
s
h
e
a
rt
ra
te,
f
o
o
tstep
s,
a
n
d
re
sti
n
g
h
e
a
rt
ra
t
e
re
c
o
rd
e
d
t
h
ro
u
g
h
a
sm
a
rtwa
tch
with
1
4
9
,
7
9
7
-
r
o
w
d
a
ta.
O
u
r
re
su
lt
s
in
d
ica
te
t
h
a
t
th
e
CNN
m
o
d
e
l
a
c
h
iev
e
s
a
n
8
4
.
5
%
a
c
c
u
ra
c
y
,
8
0
.
9
%
p
re
c
isio
n
,
7
9
.
8
%
re
c
a
ll
,
a
n
d
a
n
8
0
.
4
%
F
1
-
sc
o
re
,
c
o
n
firmi
n
g
it
s
e
ffica
c
y
in
stre
ss
c
las
sifica
ti
o
n
.
T
h
e
c
o
n
fu
si
o
n
m
a
tri
x
f
u
rth
e
r
v
a
li
d
a
tes
th
e
m
o
d
e
l
’
s
a
c
c
u
ra
c
y
,
p
a
rti
c
u
larly
f
o
r
c
las
se
s
1
a
n
d
2
.
T
h
is
re
se
a
rc
h
c
o
n
tri
b
u
tes
sig
n
if
ica
n
tl
y
t
o
t
h
e
d
e
v
e
lo
p
m
e
n
t
o
f
a
n
e
ffe
c
ti
v
e
a
n
d
p
ra
c
ti
c
a
l
stre
ss
d
e
tec
ti
o
n
m
e
th
o
d
,
h
o
ld
in
g
p
ro
m
ise
fo
r
e
n
h
a
n
c
i
n
g
we
ll
-
b
e
in
g
a
n
d
p
re
v
e
n
ti
n
g
stre
ss
-
re
late
d
h
e
a
lt
h
issu
e
s
.
K
ey
w
o
r
d
s
:
C
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
Hea
r
t r
ate
m
o
n
ito
r
i
n
g
Me
n
tal
s
tr
ess
Sm
ar
twatch
d
ata
an
aly
s
is
Stre
s
s
d
etec
tio
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
:
R
if
k
i Wi
jay
a
Sch
o
o
l o
f
C
o
m
p
u
tin
g
,
T
elk
o
m
Un
iv
er
is
ty
J
l.
T
elek
o
m
u
n
ik
asi No
.
1
,
B
an
d
u
n
g
,
4
0
2
5
7
,
I
n
d
o
n
esia
E
m
ail: r
if
k
iwijay
a@
telk
o
m
u
n
i
v
er
s
ity
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
Peo
p
le
g
en
er
ally
d
esire
co
n
tr
o
l
in
th
eir
liv
es,
b
u
t
as
th
ey
ag
e
,
th
ey
o
f
ten
ex
p
er
ien
ce
m
o
r
e
l
o
s
s
es
th
an
g
ain
s
[
1
]
.
W
ith
ad
v
an
ci
n
g
a
g
e,
in
d
iv
id
u
als
m
u
s
t
m
ak
e
s
tr
ateg
ic
ch
o
ices
ab
o
u
t
wh
er
e
to
in
v
est
th
eir
en
er
g
y
an
d
r
eso
u
r
ce
s
.
B
o
th
t
h
eo
r
eti
ca
l
an
d
e
m
p
ir
ical
wo
r
k
s
u
g
g
ests
th
at
s
o
cial
in
ter
ac
tio
n
s
ar
e
g
r
ea
tly
v
alu
ed
th
r
o
u
g
h
o
u
t
o
n
e
’
s
life
.
E
r
ic
’
s
r
esear
ch
s
h
o
ws
th
at
wh
ile
ad
u
l
ts
p
er
ce
iv
e
a
d
ec
r
ea
s
e
in
t
h
eir
co
n
tr
o
l
o
v
er
n
o
n
-
s
o
cial
s
tr
es
s
o
r
s
as
th
ey
ag
e,
th
is
r
ed
u
ctio
n
is
n
o
t
ev
id
en
t
in
th
e
co
n
tex
t
o
f
s
o
cial
s
tr
e
s
s
o
r
s
.
T
h
is
f
in
d
in
g
im
p
lies
th
at
s
o
cio
em
o
tio
n
al
as
p
ec
ts
r
em
ain
r
o
b
u
s
t,
m
ain
tain
i
n
g
th
eir
s
ig
n
if
ica
n
ce
in
th
e
liv
es o
f
o
ld
er
a
d
u
lts
.
Stre
s
s
co
n
s
titu
te
s
a
u
b
iq
u
ito
u
s
co
m
p
o
n
en
t
o
f
ev
er
y
d
ay
ex
i
s
ten
ce
,
en
co
u
n
ter
e
d
b
y
th
e
m
ajo
r
ity
o
f
in
d
iv
id
u
als
ac
r
o
s
s
d
iv
er
s
e
co
n
tex
ts
an
d
m
o
d
alities
.
No
n
et
h
eless
,
ex
p
o
s
u
r
e
to
h
ig
h
in
te
n
s
ity
o
r
p
r
o
lo
n
g
ed
s
tr
ess
ca
n
co
m
p
r
o
m
is
e
s
af
ety
an
d
p
er
tu
r
b
th
e
r
eg
u
lar
ity
o
f
d
aily
ac
tiv
ities
.
E
ar
l
y
id
e
n
tific
atio
n
o
f
m
en
ta
l
s
tr
ess
i
s
cr
u
cial
f
o
r
av
e
r
tin
g
a
p
leth
o
r
a
o
f
h
ea
lth
is
s
u
es th
at
s
tr
ess
m
ay
p
r
ec
ip
itate
[
2
]
.
I
t
is
cr
u
cial
to
d
etec
t
m
e
n
tal
s
tr
ess
ea
r
ly
,
as
it
ca
n
p
r
ev
e
n
t
th
e
em
er
g
en
ce
o
f
n
u
m
er
o
u
s
h
ea
lth
p
r
o
b
lem
s
r
elate
d
to
s
tr
ess
.
Str
ess
ca
n
p
r
im
ar
ily
b
e
ca
teg
o
r
iz
ed
in
to
ac
u
te
s
tr
ess
an
d
ch
r
o
n
i
c
s
tr
ess
.
T
h
e
r
elea
s
e
o
f
s
tr
ess
h
o
r
m
o
n
es
s
u
ch
as
co
r
tis
o
l
ca
n
lead
to
u
n
h
ea
lth
y
h
ab
its
s
u
ch
as
s
m
o
k
in
g
a
d
d
ictio
n
,
co
n
s
u
m
in
g
u
n
h
ea
lth
y
f
o
o
d
,
a
n
d
t
h
e
u
s
e
o
f
m
ed
icatio
n
th
at
p
o
ten
tially
i
n
cr
ea
s
es
h
ea
lth
r
is
k
s
,
in
clu
d
i
n
g
a
d
ec
lin
e
in
th
e
im
m
u
n
e
s
y
s
tem
,
in
cr
ea
s
ed
b
lo
o
d
p
r
ess
u
r
e,
b
r
ain
d
is
o
r
d
er
s
,
h
ea
r
t
attac
k
s
,
s
tr
o
k
es,
v
io
len
ce
,
s
u
icid
e,
an
d
e
v
en
an
elev
ated
r
is
k
o
f
ca
n
ce
r
[
2
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
S
tr
ess
d
etec
tio
n
th
r
o
u
g
h
w
ea
r
a
b
le
s
en
s
o
r
s
:
a
co
n
v
o
lu
tio
n
a
l
n
eu
r
a
l n
etw
o
r
k
-
b
a
s
ed
…
(
R
ifk
i Wija
ya
)
1881
Hea
r
t
r
ate
m
o
n
ito
r
in
g
was
in
v
esti
g
ated
u
s
in
g
th
e
h
ea
r
t
r
ate
v
ar
iab
ilit
y
(
HR
V)
tech
n
iq
u
e,
s
p
ec
if
ically
f
o
cu
s
in
g
o
n
m
en
tal
s
tr
ess
d
etec
tio
n
th
r
o
u
g
h
p
h
o
to
p
leth
y
s
m
o
g
r
ap
h
y
(
PP
G)
.
T
h
is
s
tu
d
y
e
m
p
lo
y
ed
th
e
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
(
SVM)
f
o
r
c
lass
if
icatio
n
,
d
r
awin
g
o
n
lo
w
f
r
eq
u
e
n
cy
(
L
F),
h
ig
h
f
r
eq
u
e
n
cy
(
HF)
,
an
d
th
e
L
F/HF
r
atio
m
etr
ics
f
r
o
m
HR
V
’
s
f
r
eq
u
en
cy
d
o
m
ai
n
an
al
y
s
is
.
L
F
m
etr
ics
wer
e
o
b
s
er
v
ed
to
escalate
u
n
d
e
r
co
n
d
itio
n
s
o
f
m
ild
/lo
w
s
tr
ess
.
I
n
co
n
tr
ast,
HF
m
etr
ics
in
cr
ea
s
ed
d
u
r
in
g
m
ild
/lo
w
an
d
m
o
d
er
ate
s
tr
ess
lev
els,
im
p
licatin
g
b
o
th
th
e
au
t
o
n
o
m
i
c
n
er
v
o
u
s
s
y
s
tem
(
ANS)
an
d
s
y
m
p
ath
etic
n
e
r
v
o
u
s
s
y
s
tem
(
SNS).
Ad
d
itio
n
ally
,
s
tr
ess
lev
els
an
d
th
e
L
F/HF
r
atio
p
r
o
g
r
ess
iv
ely
r
o
s
e
f
r
o
m
m
ild
to
s
ev
er
e
s
tr
ess
co
n
d
itio
n
s
.
An
aly
s
is
o
f
1
5
s
u
b
jects
lab
eled
3
ty
p
es
b
aselin
e,
am
u
s
em
en
t
a
n
d
s
tr
ess
r
ev
e
aled
d
etec
tio
n
ac
cu
r
ac
ies
o
f
7
5
.
2
1
%.
An
aly
s
is
o
f
s
am
e
d
ata
with
2
clas
s
(
s
tr
es
s
an
d
n
o
n
-
s
tr
ess
)
r
esu
ltin
g
ac
cu
r
ac
ies
o
f
8
8
.
5
6
%.
3
class
es
an
d
2
class
es
ar
e
u
s
in
g
h
y
b
r
id
co
n
v
o
l
u
tio
n
al
n
e
u
r
al
n
etwo
r
k
(
C
NN)
to
d
etec
t
s
tr
ess
[
3
]
.
T
h
ar
io
n
et
a
l.
[
4
]
d
is
cu
s
s
ed
th
e
an
aly
s
is
o
f
h
ea
r
t
r
ate
v
ar
ia
b
ilit
y
as
a
s
tr
ess
d
etec
tio
n
m
eth
o
d
.
T
h
is
r
esear
ch
ca
lcu
lated
h
ea
r
t
r
ate
v
ar
iab
ilit
y
u
s
in
g
b
o
t
h
tim
e
-
d
o
m
ain
an
d
f
r
e
q
u
en
c
y
-
d
o
m
ain
m
eth
o
d
s
.
T
h
e
r
esu
lts
s
h
o
wed
th
at
h
ea
r
t
r
ate
v
ar
ia
b
ilit
y
co
u
ld
s
er
v
e
as
a
g
o
o
d
i
n
d
icato
r
f
o
r
d
etec
tin
g
s
tr
ess
[
5
]
.
Sh
u
et
a
l.
[
6
]
in
v
esti
g
ated
th
e
u
s
e
o
f
h
ea
r
t
r
ate
v
ar
iab
ilit
y
as
an
in
d
icato
r
o
f
s
tr
ess
in
em
o
tio
n
r
ec
o
g
n
itio
n
.
T
h
e
s
tu
d
y
d
em
o
n
s
tr
ated
th
at
ch
an
g
es
in
h
ea
r
t
r
ate
co
u
ld
b
e
u
tili
ze
d
to
id
en
tify
em
o
tio
n
s
s
u
ch
as
n
eu
tr
al,
s
ad
an
d
h
ap
p
y
u
s
in
g
em
o
tio
n
al
s
tim
u
lu
s
f
r
o
m
v
id
eo
clip
s
.
Ov
er
two
d
ec
ad
es,
s
tr
ess
an
d
d
e
p
r
ess
io
n
h
a
v
e
b
ee
n
d
ete
cted
as
p
r
o
m
in
e
n
t
g
lo
b
al
p
u
b
lic
h
ea
lth
co
n
ce
r
n
[
7
]
.
I
t
is
a
m
en
tal
c
o
n
d
itio
n
th
at
ar
is
es
wh
en
an
in
d
iv
id
u
al
e
x
p
er
ie
n
ce
s
an
in
a
b
ilit
y
to
m
ee
t
t
h
ei
r
n
ee
d
s
o
r
ex
p
ec
tatio
n
s
,
r
esu
ltin
g
in
p
r
ess
u
r
e.
T
h
is
p
r
ess
u
r
e
ca
n
af
f
ec
t
b
o
th
m
en
tal
an
d
p
h
y
s
i
ca
l
h
ea
lth
,
as
well
as
in
d
iv
id
u
al
p
r
o
d
u
ctiv
ity
[
8
]
.
Mo
r
eo
v
er
,
s
tr
ess
r
ef
er
s
to
th
e
m
en
tal
im
b
alan
ce
f
ac
ed
b
y
a
n
in
d
iv
id
u
al
d
u
e
to
th
e
p
r
esen
ce
o
f
p
r
ess
u
r
e.
T
h
is
p
r
ess
u
r
e
ar
is
es
f
r
o
m
th
e
in
d
iv
id
u
al
’
s
in
ab
ilit
y
to
m
ee
t
th
eir
n
ee
d
s
o
r
ex
p
ec
tatio
n
s
,
wh
ich
ca
n
s
tem
f
r
o
m
b
o
th
i
n
ter
n
al
an
d
ex
ter
n
al
d
em
an
d
s
.
E
m
o
tio
n
al
r
ea
ct
io
n
will
co
n
s
is
t
o
f
d
en
ial
s
y
m
p
to
m
s
an
d
p
a
n
g
s
o
f
s
tr
o
n
g
em
o
ti
o
n
s
u
ch
as tr
a
u
m
atic
im
ag
es
[
9
]
.
A
c
c
o
r
d
i
n
g
t
o
h
e
a
l
t
h
p
s
y
c
h
o
l
o
g
y
r
e
s
e
a
r
c
h
,
t
h
r
e
e
f
a
c
t
o
r
s
c
a
n
t
r
ig
g
e
r
s
t
r
e
s
s
,
i
n
v
o
l
v
i
n
g
p
h
y
s
i
c
al
-
b
i
o
l
o
g
i
c
a
l
s
t
r
es
s
o
r
s
s
u
c
h
a
s
c
h
a
l
le
n
g
i
n
g
-
to
-
t
r
e
a
t
i
ll
n
e
s
s
e
s
o
r
p
h
y
s
i
c
al
d
i
s
a
b
i
li
t
ie
s
,
p
s
y
c
h
o
l
o
g
i
c
al
s
t
r
es
s
o
r
s
e
n
c
o
m
p
a
s
s
i
n
g
n
e
g
a
t
i
v
e
t
h
o
u
g
h
t
s
o
r
f
e
e
l
i
n
g
s
o
f
f
r
u
s
t
r
a
t
i
o
n
,
a
n
d
s
o
c
i
al
s
t
r
e
s
s
o
r
s
r
el
a
t
e
d
t
o
d
i
s
h
a
r
m
o
n
i
o
u
s
r
e
l
a
t
i
o
n
s
h
i
p
s
a
m
o
n
g
i
n
d
i
v
i
d
u
a
l
s
,
i
n
s
o
c
i
et
y
,
o
r
w
i
th
i
n
t
h
e
f
a
m
i
l
y
.
T
h
e
i
m
p
a
ct
s
o
f
s
t
r
e
s
s
o
n
h
e
a
l
t
h
i
n
c
l
u
d
e
s
t
r
es
s
h
o
r
m
o
n
e
r
e
l
e
as
e
,
i
n
c
r
e
a
s
e
d
h
e
a
r
t
r
a
t
e
,
a
n
d
r
e
s
p
i
r
a
t
o
r
y
r
a
t
e
[
1
0
]
.
S
t
r
e
s
s
c
a
n
al
s
o
l
e
a
d
t
o
s
y
m
p
t
o
m
s
s
u
c
h
a
s
h
e
a
d
a
c
h
e
s
a
n
d
d
i
f
f
ic
u
l
t
y
s
l
e
e
p
i
n
g
,
as
w
el
l
as
a
n
i
n
c
r
e
as
ed
r
i
s
k
o
f
h
e
a
l
t
h
d
is
o
r
d
e
r
s
s
u
c
h
a
s
h
y
p
e
r
t
e
n
s
i
o
n
a
n
d
d
i
g
e
s
t
i
v
e
p
r
o
b
l
e
m
s
[
1
1
]
.
Stre
s
s
is
a
co
m
p
lex
p
h
en
o
m
en
o
n
th
at
ca
n
af
f
ec
t
a
n
in
d
i
v
id
u
a
l
’
s
p
h
y
s
ical
an
d
m
e
n
tal
well
-
b
ein
g
[
1
2
]
.
I
n
m
an
y
ca
s
es,
ac
u
te
s
tr
ess
ca
n
tr
ig
g
er
th
e
“
f
ig
h
t
o
r
f
lig
h
t
”
r
esp
o
n
s
e,
wh
ich
is
u
s
ef
u
l
f
o
r
d
ea
lin
g
with
em
er
g
en
cy
s
itu
atio
n
s
.
Ho
we
v
er
,
wh
e
n
s
tr
ess
p
er
s
is
ts
in
to
ch
r
o
n
icity
,
t
h
e
b
o
d
y
ex
p
er
ien
ce
s
ex
ce
s
s
iv
e
p
r
ess
u
r
e,
n
eg
ativ
ely
im
p
ac
tin
g
th
e
h
ea
lth
s
y
s
tem
.
C
h
r
o
n
ic
s
tr
ess
ca
n
im
p
air
th
e
im
m
u
n
e
s
y
s
tem
,
in
cr
ea
s
e
th
e
r
is
k
o
f
h
ea
r
t
d
is
ea
s
e,
an
d
ev
en
ac
ce
ler
ate
th
e
ag
in
g
p
r
o
ce
s
s
.
Ad
d
itio
n
ally
,
s
tr
es
s
ca
n
a
f
f
ec
t
s
leep
q
u
ality
,
co
n
ce
n
tr
atio
n
,
an
d
d
aily
p
r
o
d
u
ctiv
ity
,
lead
in
g
to
m
en
tal
h
ea
lt
h
p
r
o
b
lem
s
s
u
ch
as a
n
x
iety
an
d
d
ep
r
ess
io
n
[
1
3
]
.
I
n
I
E
E
E
Acc
ess
,
T
ask
asap
lid
is
et
a
l.
[
1
4
]
h
as
r
ev
iewe
d
m
a
n
y
s
tr
ess
d
etec
tio
n
m
eth
o
d
s
,
o
n
e
o
f
wh
ich
u
s
es
h
ea
r
t
r
ate
o
n
a
Fit
b
it
wea
r
ab
le
s
en
s
o
r
.
Kh
o
o
et
a
l.
[
1
5
]
r
ev
iewe
d
all
m
u
ltimo
d
al
m
en
t
al
h
ea
lth
d
etec
tio
n
,
o
n
e
o
f
th
em
u
s
in
g
HR
V
an
d
Kh
o
o
et
a
l.
also
s
h
o
ws
th
at
m
o
d
ality
f
u
s
io
n
tech
n
iq
u
es
f
o
r
c
o
n
ca
ten
atin
g
f
ea
tu
r
e
r
ep
r
esen
tatio
n
s
as
a
s
in
g
le
in
p
u
t
to
lear
n
h
ig
h
-
lev
el
r
ep
r
esen
tatio
n
s
ca
n
b
e
u
s
ed
in
d
e
n
s
e
a
n
d
f
u
lly
co
n
n
ec
ted
lay
er
s
with
atten
tio
n
m
ec
h
an
i
s
m
s
lik
e
C
NN,
m
u
lti
-
h
ea
d
atten
tio
n
n
etwo
r
k
,
a
n
d
tr
a
n
s
f
o
r
m
er
.
C
h
alm
er
s
et
a
l.
[
1
6
]
u
s
in
g
a
wea
r
a
b
le
d
ev
ice
en
titl
ed
“
Stre
s
s
wa
tch
:
th
e
u
s
e
o
f
h
ea
r
t
r
ate
an
d
h
ea
r
t
r
ate
v
ar
iab
ilit
y
to
d
etec
t
s
tr
ess
:
a
p
ilo
t
s
tu
d
y
u
s
in
g
s
m
ar
t
watc
h
wea
r
a
b
les
,
”
h
as
s
i
m
ilar
r
esear
ch
with
a
d
if
f
e
r
e
n
t
v
ar
ia
b
le,
wh
ich
is
h
ea
r
t r
ate
v
ar
ia
b
ilit
y
(
HR
V)
an
d
r
esti
n
g
h
ea
r
t r
ate
(
R
HR
)
.
C
h
alm
er
s
et
a
l.
[
1
6
]
h
as sh
o
wn
th
at
HR
V
ca
n
n
o
t b
e
m
ea
s
u
r
ed
in
d
iv
id
u
ally
,
it
m
u
s
t
co
n
s
id
er
th
e
R
HR
b
aselin
e
wh
ile
an
x
iety
an
d
s
tr
ess
s
tate
to
e
n
s
u
r
e
ad
d
itiv
e
ac
u
te
s
tr
ess
.
Sim
et
a
l.
[
1
7
]
u
s
es
a
C
NN
to
d
etec
t
s
tr
ess
with
f
iv
e
class
es
(
n
o
r
esp
o
n
s
e,
n
o
t
s
tr
ess
ed
,
a
b
it
s
tr
ess
ed
,
m
o
d
er
ate,
a
lo
t,
an
d
ex
tr
em
ely
)
,
r
esu
ltin
g
in
7
9
.
2
5
%
Ad
aBo
o
s
t
ap
p
r
o
ac
h
ac
c
u
r
a
cy
Fo
n
tes
et
a
l.
[
1
8
]
u
s
ed
C
NN
to
im
p
r
o
v
e
HR
V
-
b
ased
ac
u
te
s
tr
ess
d
etec
tio
n
,
r
esu
ltin
g
in
a
9
5
.
8
3
% a
cc
u
r
ac
y
.
C
o
n
s
id
er
in
g
th
e
s
er
io
u
s
im
p
a
ct
o
f
s
tr
ess
o
n
h
u
m
an
h
ea
lth
,
th
e
au
th
o
r
co
n
d
u
cted
r
esear
ch
to
d
etec
t
m
ild
s
tr
ess
u
s
in
g
th
e
C
NN
m
e
th
o
d
.
T
h
is
ap
p
r
o
ac
h
aim
s
to
in
teg
r
ate
s
ev
er
al
r
elev
an
t
d
ata
la
y
er
s
,
s
u
ch
as
h
ea
r
t
r
ate,
f
o
o
ts
tep
,
an
d
r
esti
n
g
h
ea
r
t
r
ate,
as
p
r
im
ar
y
p
a
r
am
eter
s
i
n
th
e
s
tr
ess
d
etec
tio
n
p
r
o
ce
s
s
.
T
h
is
in
teg
r
atio
n
is
ex
p
ec
ted
t
o
p
r
o
v
id
e
a
m
o
r
e
h
o
lis
tic
u
n
d
er
s
tan
d
in
g
o
f
s
tr
ess
co
n
d
itio
n
s
an
d
ev
alu
ate
C
NN
’
s
p
er
f
o
r
m
an
ce
in
m
an
ag
in
g
a
n
d
an
aly
zi
n
g
h
ea
r
t
r
ate
d
ata.
T
h
e
r
esu
lts
o
f
th
is
s
tu
d
y
ar
e
an
ticip
ated
t
o
co
n
tr
ib
u
te
s
ig
n
if
ican
tly
to
d
ev
elo
p
in
g
m
o
r
e
e
f
f
ec
tiv
e
a
n
d
p
r
ac
tical
s
tr
ess
d
etec
tio
n
m
eth
o
d
s
.
Ou
r
r
esear
c
h
ca
n
b
e
im
p
lem
e
n
ted
in
wea
r
ab
le
h
ea
lth
m
o
n
ito
r
i
n
g
d
ev
ices
to
p
r
o
v
id
e
u
s
er
s
with
r
ea
l
-
tim
e
s
tr
ess
d
etec
tio
n
an
d
m
an
ag
em
en
t.
T
h
is
ca
n
b
e
p
ar
ticu
lar
ly
u
s
ef
u
l
in
wo
r
k
p
lace
welln
ess
p
r
o
g
r
am
s
,
wh
er
e
e
m
p
lo
y
e
r
s
ca
n
o
f
f
er
p
er
s
o
n
alize
d
s
tr
ess
m
an
ag
em
en
t
s
tr
ateg
ies
to
em
p
lo
y
ee
s
b
ased
o
n
th
eir
s
tr
ess
l
ev
els.
Ou
r
ap
p
r
o
ac
h
u
tili
ze
s
c
o
m
m
o
n
l
y
av
ailab
le
s
en
s
o
r
s
in
wea
r
ab
le
d
e
v
ices,
s
u
ch
as
h
ea
r
t
r
ate
m
o
n
ito
r
s
a
n
d
ac
ce
ler
o
m
eter
s
.
T
h
is
en
s
u
r
es
th
at
o
u
r
m
eth
o
d
ca
n
b
e
im
p
lem
e
n
ted
with
o
u
t sig
n
if
ican
t a
d
d
itio
n
al
co
s
ts
,
m
ak
in
g
it a
cc
ess
ib
le
to
a
wid
e
r
an
g
e
o
f
u
s
er
s
.
T
h
e
e
v
a
l
u
a
t
i
o
n
o
f
t
h
e
C
N
N
m
o
d
e
l
a
c
h
i
e
v
e
s
a
n
8
4
.
5
%
a
c
c
u
r
a
c
y
,
8
0
.
9
%
p
r
e
c
i
s
i
o
n
,
7
9
.
8
%
r
e
c
a
l
l
,
a
n
d
a
n
8
0
.
4
%
F
1
-
s
c
o
r
e
.
T
h
e
c
o
n
f
u
s
i
o
n
m
a
t
r
i
x
f
u
r
t
h
e
r
v
a
l
i
d
a
t
es
t
h
e
m
o
d
e
l
’
s
a
c
c
u
r
a
c
y
,
p
a
r
t
ic
u
l
a
r
l
y
f
o
r
c
l
a
s
s
e
s
1
(
s
t
r
e
s
s
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
25
:
1
8
8
0
-
1
8
8
8
1882
a
n
d
2
(
n
o
s
t
r
es
s
)
.
T
h
e
n
o
v
e
l
t
y
o
f
t
h
i
s
r
e
s
e
a
r
c
h
l
i
es
i
n
u
t
i
li
z
in
g
t
h
r
e
e
v
a
r
i
a
b
l
es
t
h
at
h
a
v
e
n
o
t
b
e
e
n
p
r
e
v
i
o
u
s
l
y
e
m
p
l
o
y
e
d
i
n
a
n
y
k
n
o
w
n
s
t
u
d
i
e
s
.
S
t
r
e
s
s
w
il
l
r
e
d
u
c
e
t
h
e
n
u
m
b
e
r
o
f
f
o
o
t
s
t
e
p
s
,
as
m
e
n
t
i
o
n
e
d
b
y
B
r
o
c
k
m
a
n
n
a
n
d
R
o
s
s
[
1
9
]
.
A
l
t
i
n
i
a
n
d
P
le
w
s
[
2
0
]
c
o
n
d
u
c
t
e
d
r
e
s
e
a
r
c
h
i
n
5
y
e
a
r
s
f
o
r
a
l
o
n
g
i
t
u
d
i
n
a
l
s
t
u
d
y
o
f
H
R
V
at
r
e
s
t
(
R
HR
)
a
n
d
s
t
r
e
s
s
.
T
h
es
e
r
e
s
u
lt
s
c
o
n
f
i
r
m
t
h
e
e
f
f
i
c
a
c
y
o
f
t
h
e
p
r
o
p
o
s
e
d
s
t
r
ess
d
e
t
e
ct
i
o
n
s
y
s
t
e
m
an
d
i
t
s
p
o
t
e
n
t
ia
l
t
o
c
o
n
t
r
i
b
u
t
e
s
i
g
n
i
f
i
c
a
n
t
l
y
t
o
t
h
e
d
e
v
e
l
o
p
m
e
n
t
o
f
m
o
r
e
e
f
f
e
c
t
i
v
e
an
d
p
r
a
c
t
i
c
a
l
s
t
r
es
s
d
et
e
c
t
i
o
n
m
et
h
o
d
s
.
2.
M
E
T
H
O
D
I
n
th
e
d
esig
n
p
h
ase
o
f
th
e
s
y
s
tem
co
n
s
tr
u
cted
in
th
is
r
esear
ch
,
a
s
y
s
tem
is
d
ev
elo
p
ed
to
a
n
aly
ze
th
e
im
p
lem
en
tatio
n
o
f
a
s
tr
ess
d
et
ec
tio
n
s
y
s
tem
u
s
in
g
th
e
C
NN
m
eth
o
d
.
T
h
is
p
h
ase
in
v
o
lv
es
c
r
ea
tin
g
a
s
tr
u
ctu
r
ed
p
lan
th
at
o
u
tlin
es
th
e
n
ec
ess
ar
y
s
tep
s
f
o
r
b
u
ild
in
g
an
d
ev
alu
atin
g
th
e
s
tr
ess
d
etec
tio
n
s
y
s
te
m
.
T
h
e
r
esear
ch
is
d
iv
id
ed
in
t
o
s
ev
er
al
s
tag
es
th
at
alig
n
with
th
e
b
lo
ck
d
iag
r
am
d
ep
icted
i
n
Fig
u
r
e
1
,
e
n
s
u
r
in
g
a
s
y
s
tem
atic
ap
p
r
o
ac
h
to
th
e
d
ev
elo
p
m
en
t
p
r
o
ce
s
s
.
Fig
u
r
e
1
.
Data
co
llectio
n
,
p
r
e
p
r
o
ce
s
s
in
g
,
C
NN
im
p
lem
en
tatio
n
,
an
d
ev
alu
atio
n
p
r
o
ce
s
s
es
2
.
1
.
Da
t
a
Co
llect
io
n
I
n
th
e
d
esig
n
o
f
t
h
is
s
y
s
tem
,
th
e
m
ain
f
o
cu
s
is
to
d
etec
t
h
ea
r
t
r
ate,
f
o
o
ts
tep
,
an
d
r
esti
n
g
h
ea
r
t
r
ate
as
k
ey
p
ar
a
m
eter
s
to
id
en
tif
y
th
e
lev
el
o
f
s
tr
ess
.
T
h
e
f
ir
s
t
p
r
o
c
ess
in
v
o
lv
es
d
ata
co
llectio
n
.
Data
co
llectio
n
was
co
n
d
u
cte
d
o
n
1
0
p
ar
ticip
an
ts
wh
o
ar
e
T
elk
o
m
Un
iv
e
r
s
ity
s
tu
d
en
ts
ag
ed
b
etwe
en
2
0
an
d
2
2
y
ea
r
s
,
with
th
e
id
en
tifie
d
ty
p
e
o
f
s
tr
ess
b
ein
g
m
en
tal
s
tr
ess
.
T
h
is
d
ata
in
clu
d
es
in
f
o
r
m
atio
n
o
n
h
ea
r
t
r
ate,
t
h
e
n
u
m
b
er
o
f
s
tep
s
(
f
o
o
ts
tep
s
)
,
an
d
r
esti
n
g
h
ea
r
t r
ate
m
ea
s
u
r
ed
u
s
in
g
t
h
e
Fit
b
it C
h
ar
g
e
3
s
m
ar
t w
atch
.
T
h
is
s
y
s
tem
,
b
u
ilt
o
n
s
m
ar
tw
atch
tech
n
o
lo
g
y
,
is
d
esig
n
ed
to
en
h
an
ce
o
u
r
u
n
d
e
r
s
tan
d
in
g
o
f
m
en
tal
s
tr
ess
b
y
f
o
cu
s
in
g
o
n
th
r
ee
k
ey
p
ar
am
eter
s
.
I
t
ca
p
tu
r
e
s
r
ea
l
-
tim
e
p
h
y
s
io
lo
g
ical
r
esp
o
n
s
es,
p
r
o
v
id
in
g
im
m
ed
iate
an
d
ac
cu
r
ate
d
ata
a
b
o
u
t
s
tr
ess
lev
els.
T
h
is
ap
p
r
o
a
ch
en
s
u
r
es
r
esear
ch
er
s
ca
n
a
n
aly
ze
m
en
tal
s
tr
ess
m
o
r
e
ef
f
ec
tiv
el
y
with
in
th
e
s
tu
d
ied
p
o
p
u
latio
n
,
lead
in
g
t
o
b
et
ter
in
s
ig
h
ts
an
d
p
o
ten
tial in
ter
v
en
tio
n
s
.
2
.
2
.
P
re
pro
ce
s
s
ing
T
h
e
p
r
ep
r
o
ce
s
s
in
g
s
tag
e
h
elp
s
en
s
u
r
e
th
at
th
e
d
ata
u
s
ed
to
tr
ain
th
e
m
o
d
el
is
clea
n
,
r
el
ev
an
t,
an
d
r
ea
d
y
f
o
r
u
s
e
in
th
e
tr
ain
in
g
an
d
test
in
g
p
r
o
ce
s
s
es
[
2
1
]
.
I
n
th
is
s
tag
e,
p
r
o
ce
s
s
es
s
u
ch
as
h
an
d
lin
g
m
is
s
in
g
v
alu
es,
lab
elin
g
d
ata,
co
n
v
er
t
in
g
d
ata
in
to
a
p
p
r
o
p
r
iate
f
o
r
m
ats,
d
ata
n
o
r
m
aliza
tio
n
,
an
d
s
p
litt
in
g
d
ata
i
n
to
tr
ain
in
g
an
d
test
in
g
d
ata
ar
e
ca
r
r
ied
o
u
t.
T
h
e
p
r
o
ce
s
s
es in
th
is
s
tag
e
ca
n
b
e
s
ee
n
in
Fig
u
r
e
2
.
Fig
u
r
e
2
.
T
h
e
p
r
e
p
r
o
ce
s
s
in
g
f
l
o
w
s
tar
ts
with
r
em
o
v
in
g
n
o
is
e
an
d
d
i
v
id
es th
e
d
ata
in
to
tr
ain
in
g
an
d
test
d
ata
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
S
tr
ess
d
etec
tio
n
th
r
o
u
g
h
w
ea
r
a
b
le
s
en
s
o
r
s
:
a
co
n
v
o
lu
tio
n
a
l
n
eu
r
a
l n
etw
o
r
k
-
b
a
s
ed
…
(
R
ifk
i Wija
ya
)
1883
2
.
3
.
Co
nv
o
lutio
na
l
neura
l net
wo
rk
C
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
(
C
NN
)
s
tan
d
s
o
u
t
as
a
s
p
ec
ia
lized
ar
ch
itectu
r
e
with
in
ar
tifi
cial
n
eu
r
al
n
etwo
r
k
s
,
m
etic
u
lo
u
s
ly
c
r
af
t
ed
f
o
r
p
r
o
ce
s
s
in
g
s
tr
u
ctu
r
ed
d
ata
[
2
2
]
.
C
o
m
p
r
is
in
g
d
is
tin
ct
lay
er
s
,
C
NN
p
o
s
s
ess
es
th
e
in
n
ate
ab
ilit
y
to
au
to
n
o
m
o
u
s
ly
a
n
d
h
ier
ar
c
h
ically
d
is
ce
r
n
f
ea
t
u
r
es
f
r
o
m
in
p
u
t
d
ata.
T
h
e
co
n
v
o
l
u
tio
n
al
L
a
y
er
,
with
its
co
n
v
o
lu
tio
n
o
p
er
atio
n
s
,
ex
c
els
in
ex
tr
ac
tin
g
in
tr
icate
f
ea
tu
r
es
b
y
s
ca
n
n
in
g
m
in
u
te
p
o
r
tio
n
s
o
f
th
e
in
p
u
t
u
s
in
g
f
ilter
s
o
r
k
er
n
els.
T
h
is
f
ac
ilit
ate
s
th
e
d
etec
tio
n
o
f
s
p
ec
if
ic
p
atter
n
s
,
en
ab
lin
g
th
e
m
o
d
el
to
ac
q
u
i
r
e
a
n
u
a
n
ce
d
u
n
d
e
r
s
tan
d
in
g
o
f
th
e
d
ata
’
s
h
ier
ar
c
h
ical
s
tr
u
ctu
r
es.
T
h
e
la
y
er
,
in
co
r
p
o
r
atin
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
,
co
n
tr
ib
u
tes
b
y
elim
in
a
tin
g
n
eg
ativ
e
v
al
u
es
in
th
e
c
o
n
v
o
lu
tio
n
r
esu
lts
,
r
ec
o
g
n
izin
g
in
tr
icate
p
atter
n
s
an
d
f
o
r
m
in
g
a
b
s
tr
ac
t
d
ata
r
ep
r
esen
tatio
n
s
.
T
h
e
p
o
o
lin
g
lay
er
s
tr
ateg
ically
r
e
d
u
ce
s
th
e
s
p
atial
d
im
e
n
s
io
n
s
o
f
t
h
e
co
n
v
o
l
u
tio
n
al
lay
e
r
o
u
tp
u
ts
,
m
itig
atin
g
co
m
p
u
tatio
n
al
co
m
p
lex
ity
a
n
d
p
r
ev
en
tin
g
o
v
er
f
itti
n
g
.
F
in
ally
,
th
e
f
u
lly
co
n
n
ec
ted
lay
er
am
alg
am
ates
in
f
o
r
m
atio
n
f
r
o
m
p
r
ec
ed
i
n
g
la
y
er
s
,
s
er
v
in
g
as
a
d
ec
is
iv
e
class
if
ier
f
o
r
task
s
lik
e
s
tr
es
s
clas
s
if
icatio
n
b
ased
o
n
h
ea
r
t
r
ate,
cu
lm
in
atin
g
in
a
c
o
m
p
r
eh
e
n
s
iv
e
an
d
s
o
p
h
is
ticated
d
ata
an
aly
s
is
.
T
h
e
m
ain
f
o
r
m
u
la
r
elate
d
to
th
e
co
n
v
o
l
u
tio
n
o
p
er
atio
n
i
n
a
C
NN
ca
n
b
e
s
ee
n
in
(
1
)
.
(
,
)
=
(
∗
)
(
,
)
=
∑
∑
(
,
)
∙
(
−
,
−
)
(
1
)
W
h
en
,
(
,
)
is
th
e
p
ix
el
at
p
o
s
itio
n
(
,
)
in
t
h
e
c
o
n
v
o
lu
tio
n
r
esu
lt m
atr
ix
.
(
,
)
is
th
e
p
ix
el
v
alu
e
at
p
o
s
itio
n
(
,
)
in
th
e
in
p
u
t
(
im
ag
e
o
r
d
ata
m
atr
i
x
)
.
(
−
,
−
)
is
th
e
v
al
u
e
o
f
th
e
f
ilter
(
k
er
n
el)
at
p
o
s
itio
n
(
−
,
−
)
.
∑
d
an
∑
ar
e
s
y
m
b
o
ls
f
o
r
s
u
m
m
in
g
u
p
all
th
e
p
ix
el
v
alu
es
in
th
e
co
n
v
o
l
u
tio
n
o
p
er
atio
n
.
T
h
e
eq
u
atio
n
(
1
)
d
escr
ib
es
th
e
co
n
v
o
lu
tio
n
p
r
o
ce
s
s
b
etwe
en
th
e
in
p
u
t
(
I
)
a
n
d
th
e
f
ilter
(
K
)
,
r
esu
ltin
g
in
th
e
co
n
v
o
l
u
tio
n
m
at
r
ix
S
.
Af
ter
war
d
,
th
is
co
n
v
o
lu
ti
o
n
r
esu
lt
ca
n
b
e
o
p
er
ated
with
an
ac
tiv
atio
n
f
u
n
ctio
n
,
s
u
ch
as
th
e
R
eL
U
f
u
n
ctio
n
,
a
n
d
u
n
d
er
g
o
la
y
er
s
o
f
p
o
o
lin
g
an
d
f
u
lly
c
o
n
n
ec
te
d
lay
e
r
s
to
g
en
e
r
ate
th
e
f
in
al
o
u
tp
u
t
[
2
3
]
.
2
.
4
.
E
v
a
lua
t
io
n
ph
a
s
e
E
v
alu
atin
g
C
NN
m
o
d
els
in
t
h
e
co
n
tex
t
o
f
a
s
p
ec
if
ic
task
ca
n
b
e
d
o
n
e
u
s
in
g
v
a
r
io
u
s
p
e
r
f
o
r
m
a
n
ce
m
etr
ics
[
2
3
]
.
T
h
ese
m
etr
ics
p
r
o
v
id
e
a
q
u
an
titativ
e
f
r
am
ewo
r
k
f
o
r
ass
ess
in
g
th
e
m
o
d
el’
s
ef
f
ec
tiv
en
ess
,
en
ab
lin
g
r
esear
ch
e
r
s
to
id
en
ti
f
y
s
tr
en
g
th
s
an
d
a
r
ea
s
f
o
r
im
p
r
o
v
em
e
n
t.
B
elo
w
is
a
b
r
ief
ex
p
lan
atio
n
o
f
s
o
m
e
co
m
m
o
n
l
y
u
s
ed
ev
alu
atio
n
m
etr
ics,
h
ig
h
lig
h
tin
g
t
h
eir
r
e
lev
an
ce
in
an
aly
zin
g
m
o
d
el
p
er
f
o
r
m
an
ce
with
in
d
if
f
er
en
t ta
s
k
s
.
2
.
4
.
1
.
Co
nfusi
o
n
m
a
t
rix
A
co
n
f
u
s
io
n
m
atr
ix
is
a
m
atr
ix
tab
le
u
s
ed
in
th
e
e
v
alu
atio
n
o
f
th
e
p
er
f
o
r
m
an
ce
o
f
a
cla
s
s
if
icatio
n
m
o
d
el.
T
h
e
c
o
n
f
u
s
io
n
m
atr
ix
p
r
o
v
id
es
a
co
m
p
r
e
h
en
s
iv
e
o
v
er
v
iew
o
f
h
o
w
well
a
class
i
f
icatio
n
m
o
d
el
ca
n
p
r
ed
ict
th
e
co
r
r
ec
t
tar
g
et
clas
s
es
an
d
an
aly
ze
s
th
e
ty
p
es
o
f
er
r
o
r
s
m
ad
e
b
y
t
h
e
m
o
d
el
[
2
4
]
.
T
h
e
m
atr
ix
is
co
m
p
o
s
ed
o
f
f
o
u
r
k
e
y
co
m
p
o
n
en
ts
:
tr
u
e
p
o
s
itiv
es
(
T
P),
wh
ich
r
ef
lect
co
r
r
ec
tly
p
r
ed
icted
p
o
s
itiv
e
in
s
tan
ce
s
;
tr
u
e
n
eg
ativ
es
(
T
N)
,
in
d
icatin
g
in
s
tan
ce
s
ac
cu
r
ately
i
d
en
tifi
ed
as
n
eg
ativ
e;
f
alse
p
o
s
itiv
es
(
FP
)
,
r
ep
r
esen
tin
g
ca
s
es
in
co
r
r
ec
tly
class
if
ied
a
s
p
o
s
itiv
e
d
esp
ite
b
elo
n
g
in
g
to
th
e
n
e
g
ativ
e
class
(
T
y
p
e
I
er
r
o
r
)
;
an
d
f
alse
n
eg
ativ
es
(
FN)
,
w
h
ich
d
en
o
te
p
o
s
itiv
e
in
s
tan
ce
s
m
is
class
if
ied
as
n
e
g
ativ
e
(
T
y
p
e
I
I
er
r
o
r
)
.
T
h
ese
ele
m
en
ts
p
r
o
v
id
e
a
d
etailed
b
r
ea
k
d
o
wn
o
f
th
e
m
o
d
el
’
s
class
if
icatio
n
p
er
f
o
r
m
an
ce
,
allo
win
g
f
o
r
a
t
h
o
r
o
u
g
h
a
n
aly
s
is
o
f
its
ac
cu
r
ac
y
an
d
th
e
t
y
p
es
o
f
e
r
r
o
r
s
it
m
ak
es
in
p
r
ed
ictin
g
ta
r
g
et
class
es
[
2
5
]
.
B
y
u
s
in
g
th
e
s
e
f
o
u
r
m
ain
ce
lls
,
th
e
co
n
f
u
s
io
n
m
atr
ix
ca
n
b
e
s
t
ated
in
T
ab
le
1
.
T
ab
le
1
.
T
a
b
le
ex
p
lain
in
g
th
e
co
n
f
u
s
io
n
m
atr
ix
A
c
t
u
a
l
v
a
l
u
e
P
o
si
t
i
v
e
N
e
g
a
t
i
v
e
P
r
e
d
i
c
t
i
v
e
v
a
l
u
e
P
o
si
t
i
v
e
Tr
u
e
p
o
si
t
i
v
e
(
TP)
F
a
l
se
n
e
g
a
t
i
v
e
(
TN
)
N
e
g
a
t
i
v
e
F
a
l
se
n
e
g
a
t
i
v
e
(FN)
Tr
u
e
n
e
g
a
t
i
v
e
(
TN
)
T
h
e
co
n
f
u
s
io
n
m
atr
ix
aid
s
in
ca
lcu
latin
g
v
a
r
io
u
s
class
if
icatio
n
e
v
alu
atio
n
m
etr
ics
s
u
ch
as
ac
cu
r
ac
y
,
r
ec
all,
p
r
ec
is
io
n
,
an
d
F1
-
s
co
r
e
[
2
6
]
.
B
y
u
tili
zin
g
th
e
v
alu
e
s
f
r
o
m
th
e
co
n
f
u
s
io
n
m
atr
ix
ce
lls
,
we
ca
n
b
etter
u
n
d
er
s
tan
d
t
h
e
class
if
icatio
n
m
o
d
el
’
s
p
er
f
o
r
m
an
ce
ac
r
o
s
s
d
if
f
er
en
t
asp
ec
ts
.
T
h
e
ac
cu
r
ac
y
,
r
ec
all,
p
r
ec
is
io
n
,
an
d
F1
-
s
co
r
e
ca
lc
u
latio
n
s
ca
n
b
e
o
b
s
er
v
e
d
in
(
2
)
to
(
5
).
=
(
+
)
(
+
+
+
)
(
2
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
25
:
1
8
8
0
-
1
8
8
8
1884
Acc
u
r
ac
y
m
ea
s
u
r
es
h
o
w
o
f
te
n
th
e
m
o
d
el
p
r
o
v
id
es
co
r
r
ec
t
p
r
ed
ictio
n
s
o
v
er
all.
I
t
is
ex
p
r
ess
ed
as
th
e
to
tal
co
r
r
ec
t p
r
e
d
ictio
n
s
(
tr
u
e
n
eg
at
iv
e
an
d
tr
u
e
p
o
s
itiv
e
)
r
atio
to
t
h
e
to
tal
n
u
m
b
er
o
f
s
am
p
les.
=
(
+
)
(
3
)
Pre
cisi
o
n
m
ea
s
u
r
es
h
o
w
p
r
ec
i
s
e
th
e
m
o
d
el
is
in
p
r
ed
ictin
g
th
e
p
o
s
itiv
e
class
.
I
t
is
ex
p
r
es
s
ed
as
th
e
r
atio
o
f
tr
u
e
p
o
s
itiv
e
to
th
e
to
tal
p
o
s
itiv
e
p
r
ed
ictio
n
s
(
f
alse
p
o
s
itiv
e
a
n
d
tr
u
e
p
o
s
itiv
e
).
=
(
+
)
(
4
)
R
ec
all
m
ea
s
u
r
es
th
e
m
o
d
el
’
s
ab
ilit
y
to
d
etec
t
all
in
s
tan
ce
s
o
f
th
e
ac
t
u
al
p
o
s
itiv
e
class
.
I
t
is
ex
p
r
ess
ed
as
th
e
r
atio
o
f
tr
u
e
p
o
s
itiv
e
to
t
h
e
to
t
al
in
s
tan
ce
s
o
f
th
e
p
o
s
itiv
e
cla
s
s
(
tr
u
e
p
o
s
itiv
e
an
d
f
alse
n
eg
ativ
e)
.
1
−
=
2
∗
+
(
5
)
T
h
e
F1
-
s
co
r
e
r
ep
r
esen
ts
th
e
h
ar
m
o
n
ic
m
ea
n
b
etwe
en
p
r
ec
is
io
n
an
d
r
ec
all
,
o
f
f
er
in
g
a
b
ala
n
ce
d
m
ea
s
u
r
e
th
at
en
co
m
p
ass
es b
o
th
.
F1
-
s
co
r
e
a
ch
iev
es a
h
ig
h
v
alu
e
if
a
n
d
o
n
l
y
if
b
o
t
h
p
r
ec
is
io
n
a
n
d
r
ec
all
h
av
e
h
ig
h
v
alu
es.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
I
m
plem
ent
a
t
io
n
prepro
ce
s
s
i
ng
T
h
e
o
u
tco
m
es
o
f
th
e
d
ata
p
r
e
p
r
o
ce
s
s
in
g
s
tag
e
ar
e
d
etailed
in
s
ec
tio
n
s
3
.
1
.
1
t
o
3
.
1
.
5
.
T
h
es
e
s
ec
tio
n
s
co
v
er
th
e
r
esu
lts
f
r
o
m
h
an
d
lin
g
m
is
s
in
g
v
alu
es,
im
p
lem
en
tin
g
d
ata
la
b
elin
g
,
c
o
n
v
e
r
tin
g
d
ata
f
o
r
m
ats,
n
o
r
m
alizin
g
d
ata,
an
d
s
p
litt
in
g
th
e
d
ata,
wh
ich
c
o
llectiv
ely
co
n
s
titu
te
th
e
p
r
e
p
r
o
ce
s
s
in
g
s
tep
s
f
o
r
th
is
r
esear
ch
.
E
ac
h
s
tep
is
cr
itic
al
to
e
n
s
u
r
in
g
th
e
d
ataset’
s
q
u
ality
an
d
s
u
itab
ilit
y
f
o
r
an
aly
s
is
,
u
ltima
tely
en
h
an
cin
g
th
e
r
eliab
ilit
y
a
n
d
a
cc
u
r
ac
y
o
f
th
e
r
esu
lts
p
r
esen
te
d
in
s
u
b
s
eq
u
e
n
t sectio
n
s
.
3
.
1
.
1
.
Resul
t
s
f
ro
m
o
v
er
co
m
i
ng
m
is
s
ing
v
a
lues
T
h
e
m
ain
o
b
jectiv
e
o
f
t
h
is
s
tag
e
is
to
clea
n
an
d
p
r
e
p
ar
e
th
e
d
ata
f
o
r
f
u
r
th
er
a
n
aly
s
is
o
r
m
o
d
elin
g
.
I
n
th
is
p
h
ase,
th
e
d
ataset
is
ev
a
lu
ated
u
s
in
g
th
e
(
)
.
(
)
f
u
n
ctio
n
to
id
en
tify
th
e
n
u
m
b
er
o
f
m
is
s
in
g
v
alu
es
in
ea
ch
c
o
lu
m
n
.
Su
b
s
e
q
u
en
tly
,
r
o
ws
co
n
tain
i
n
g
m
is
s
in
g
v
alu
es
ar
e
r
em
o
v
ed
u
s
in
g
th
e
d
r
o
p
a
f
u
n
ctio
n
,
an
d
th
e
m
o
d
if
ied
d
ataset
is
s
to
r
ed
b
ac
k
in
th
e
v
ar
iab
le
“
d
ata.
”
T
h
is
ac
tio
n
is
tak
e
n
to
clea
n
s
e
th
e
d
ataset
f
r
o
m
r
o
ws
with
m
is
s
in
g
v
alu
es.
A
f
ter
th
is
p
r
o
ce
s
s
,
an
o
th
er
ev
alu
atio
n
u
s
in
g
(
)
.
(
)
is
co
n
d
u
cted
to
en
s
u
r
e
th
at
th
e
d
ataset
u
s
ed
i
s
f
r
ee
f
r
o
m
m
is
s
in
g
v
alu
es.
Ultim
ately
,
th
is
p
iece
o
f
co
d
e
aim
s
to
h
an
d
le
a
n
d
elim
in
ate
m
is
s
in
g
v
alu
es
in
th
e
d
ataset
b
ef
o
r
e
p
r
o
ce
ed
in
g
t
o
th
e
an
aly
s
is
o
r
m
o
d
elin
g
s
tag
e.
T
h
e
o
u
tco
m
es
o
f
th
is
s
tag
e
ca
n
b
e
o
b
s
er
v
ed
in
F
ig
u
r
e
3
.
Fig
u
r
e
3
.
R
esu
lts
o
f
th
e
m
is
s
in
g
v
alu
e
r
e
m
o
v
al
s
tag
e
3
.
1
.
2
.
I
m
plem
ent
a
t
i
o
n
o
f
la
b
eling
da
t
a
T
h
is
p
r
o
ce
s
s
aim
s
to
p
r
o
v
i
d
e
lab
els
to
th
e
d
ata
b
ased
o
n
th
e
in
ter
v
iew
r
esu
lts
f
r
o
m
p
a
r
ticip
an
ts
,
ass
ig
n
in
g
th
e
lab
el
“
ya
”
(
y
e
s
)
f
o
r
f
ee
lin
g
s
tr
ess
an
d
“
tid
a
k
”
(
n
o
)
f
o
r
n
o
t
f
ee
lin
g
s
tr
ess
,
wh
ich
will
b
e
s
u
b
s
eq
u
en
tly
co
n
v
er
ted
t
o
“
ya
”
with
a
v
alu
e
o
f
1
an
d
“
tid
a
k
”
with
a
v
alu
e
o
f
0
.
T
h
e
o
u
tco
m
es
o
f
th
is
lab
elin
g
p
r
o
ce
s
s
ar
e
p
r
esen
ted
in
T
ab
le
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
S
tr
ess
d
etec
tio
n
th
r
o
u
g
h
w
ea
r
a
b
le
s
en
s
o
r
s
:
a
co
n
v
o
lu
tio
n
a
l
n
eu
r
a
l n
etw
o
r
k
-
b
a
s
ed
…
(
R
ifk
i Wija
ya
)
1885
T
ab
le
2
.
R
esu
lts
f
r
o
m
th
e
d
ata
lab
elin
g
ID
D
a
t
e
T
i
me
bpm
st
e
p
F
e
e
l
i
n
g
s
t
r
e
ss
I
D
0
0
1
2
0
2
3
-
09
-
2
3
0
0
:
0
0
:
0
2
99
0
No
I
D
0
0
1
2
0
2
3
-
09
-
2
3
0
0
:
0
0
:
0
7
98
0
No
I
D
0
0
1
2
0
2
3
-
09
-
2
3
1
4
:
4
7
:
1
2
1
0
4
10
Y
e
s
I
D
0
0
1
2
0
2
3
-
09
-
2
3
1
4
:
4
7
:
1
7
1
0
7
10
Y
e
s
3
.
1
.
3
.
Da
t
a
f
o
r
m
a
t
c
o
nv
er
s
io
n
I
n
th
is
s
tag
e,
ad
ju
s
tm
en
ts
to
t
h
e
d
ata
f
o
r
m
at
ar
e
m
a
d
e.
T
h
e
r
e
ar
e
a
s
er
ies
o
f
d
ata
ty
p
e
co
n
v
er
s
io
n
s
(
ca
s
tin
g
)
f
o
r
co
lu
m
n
s
in
th
e
d
ataset.
First
ly
,
th
e
co
lu
m
n
s
′
′
(
h
ea
r
t
r
ate
p
er
m
in
u
te)
,
′
′
(
n
u
m
b
er
o
f
s
tep
s
)
,
′
ℎ
′
(
f
atig
u
e
lab
el)
,
a
n
d
′
′
(
tim
e)
ar
e
co
n
v
e
r
ted
to
th
e
i
n
teg
er
d
ata
ty
p
e
u
s
in
g
th
e
′
′
(
in
t)
f
u
n
ctio
n
.
T
h
is
co
n
v
e
r
ts
th
e
v
alu
es
in
th
ese
co
lu
m
n
s
in
t
o
in
teg
er
s
,
f
ac
ilit
atin
g
f
u
r
th
er
p
r
o
ce
s
s
in
g
an
d
an
aly
s
is
.
T
h
e
c
o
d
e
f
o
r
th
e
f
o
r
m
at
ad
j
u
s
tm
en
t c
an
b
e
s
ee
n
in
Fig
u
r
e
4
.
Fig
u
r
e
4
.
C
o
d
e
f
o
r
t
h
e
d
ata
f
o
r
m
at
co
n
v
er
s
io
n
s
tag
e
3
.
1
.
4
.
No
rma
lized
da
t
a
I
n
th
is
s
tag
e,
d
ata
n
o
r
m
aliza
ti
o
n
is
p
er
f
o
r
m
ed
u
s
in
g
m
in
-
m
ax
s
ca
lin
g
.
No
r
m
aliza
tio
n
is
th
e
p
r
o
ce
s
s
o
f
tr
a
n
s
f
o
r
m
in
g
d
ata
s
o
t
h
at
i
ts
v
alu
es
f
all
with
in
a
s
p
ec
if
i
c
r
an
g
e
,
in
th
is
ca
s
e,
t
h
e
r
a
n
g
e
b
etwe
en
0
a
n
d
1
[
2
7
]
.
ℎ
_
=
(
ℎ
−
ℎ
_
)
/
(
ℎ
_
−
ℎ
_
)
,
ℎ
_
=
(
ℎ
−
ℎ
_
)
(
ℎ
_
−
ℎ
_
)
(
6
)
_
=
(
–
_
)
(
_
–
_
)
(
7
)
3
.
1
.
5
.
Sp
lit
da
t
a
In
th
is
s
tag
e,
th
e
d
ataset
is
d
iv
id
ed
in
to
two
m
ain
s
u
b
s
ets:
tr
ain
in
g
d
ata
(
tr
ain
)
a
n
d
test
in
g
d
ata
(
test
)
.
T
h
e
ch
o
s
en
p
r
o
p
o
r
tio
n
allo
c
ates
7
0
%
o
f
th
e
d
ata
to
tr
ai
n
in
g
th
e
m
o
d
el
(
_
an
d
_
)
an
d
th
e
r
em
ain
in
g
3
0
%
to
test
in
g
o
r
ev
alu
atin
g
th
e
m
o
d
el’
s
p
er
f
o
r
m
an
ce
(
_
an
d
_
)
.
T
h
is
s
p
lit
en
s
u
r
es
a
b
alan
ce
d
a
p
p
r
o
ac
h
,
allo
win
g
th
e
m
o
d
el
to
lear
n
ef
f
ec
tiv
el
y
wh
ile
p
r
o
v
id
in
g
s
u
f
f
icien
t
d
a
ta
f
o
r
a
n
u
n
b
iased
ev
alu
atio
n
o
f
its
p
r
ed
ictiv
e
ac
c
u
r
ac
y
an
d
g
e
n
er
aliza
tio
n
ca
p
a
b
ilit
ies.
3.
2
.
Resul
t
s
f
ro
m
t
he
CNN
m
o
del
T
h
e
r
esu
lts
o
f
th
e
C
NN
m
o
d
el
im
p
lem
en
tatio
n
ar
e
v
is
u
alize
d
u
s
in
g
a
g
r
ap
h
o
f
th
e
m
o
d
el
’
s
lo
s
s
,
co
n
s
is
tin
g
o
f
two
lin
es:
th
e
b
lu
e
lin
e
r
ep
r
esen
tin
g
th
e
tr
ai
n
in
g
lo
s
s
an
d
th
e
r
ed
lin
e
r
ep
r
ese
n
tin
g
th
e
v
alid
atio
n
lo
s
s
.
T
h
e
tr
ain
in
g
lo
s
s
is
th
e
er
r
o
r
v
alu
e
p
r
o
d
u
ce
d
b
y
th
e
m
o
d
el
wh
en
tr
ain
ed
with
th
e
tr
ain
in
g
d
ata.
T
h
e
tr
ain
in
g
lo
s
s
will
co
n
tin
u
e
t
o
d
ec
r
ea
s
e
as
th
e
tr
ain
in
g
i
ter
atio
n
s
p
r
o
g
r
ess
.
T
h
is
s
u
g
g
ests
th
e
m
o
d
el
is
im
p
r
o
v
in
g
its
ab
ilit
y
to
id
en
t
if
y
p
atter
n
s
with
in
th
e
tr
ain
in
g
d
ataset.
T
h
en
,
th
e
v
alid
atio
n
lo
s
s
i
s
th
e
er
r
o
r
v
alu
e
p
r
o
d
u
ce
d
b
y
th
e
m
o
d
el
wh
en
test
ed
with
v
alid
atio
n
d
ata.
T
h
e
v
alid
atio
n
lo
s
s
will
a
ls
o
d
ec
r
ea
s
e
as
th
e
tr
ain
in
g
iter
atio
n
s
p
r
o
g
r
ess
,
b
u
t
th
e
d
ec
r
ea
s
e
will
b
e
s
lo
w
er
th
an
th
e
tr
ain
i
n
g
l
o
s
s
.
T
h
is
in
d
icate
s
th
at
th
e
m
o
d
el
is
ap
p
r
o
ac
h
i
n
g
its
lim
it
in
r
ec
o
g
n
izin
g
p
atter
n
s
in
th
e
tr
ain
in
g
d
ata.
T
h
e
g
r
ap
h
f
o
r
t
h
e
m
o
d
el
lo
s
s
ca
n
b
e
s
ee
n
in
Fig
u
r
e
5
.
B
ased
o
n
th
e
g
r
ap
h
,
it
ca
n
b
e
co
n
clu
d
e
d
th
at
th
e
C
NN
m
o
d
el
h
as
s
u
cc
ess
f
u
lly
ac
h
iev
ed
g
o
o
d
ac
cu
r
ac
y
.
T
h
is
is
ev
id
en
t
f
r
o
m
th
e
s
ig
n
if
ican
t
d
ec
r
ea
s
e
in
b
o
th
tr
ain
in
g
lo
s
s
an
d
v
alid
atio
n
lo
s
s
as
th
e
tr
ain
in
g
iter
atio
n
s
p
r
o
g
r
ess
.
At
th
e
6
0
th
ep
o
ch
,
th
e
tr
ain
in
g
lo
s
s
an
d
v
alid
atio
n
lo
s
s
r
ea
ch
v
alu
es
o
f
0
.
1
2
an
d
0
.
1
4
,
r
esp
ec
tiv
ely
.
T
h
ese
lo
w
lo
s
s
v
alu
es
in
d
icate
th
at
th
e
C
NN
m
o
d
el
ca
n
r
ec
o
g
n
ize
p
atter
n
s
in
th
e
tr
ain
in
g
d
ata
with
h
ig
h
ac
cu
r
ac
y
.
B
ased
o
n
Fig
u
r
e
6
,
it
ca
n
b
e
co
n
clu
d
e
d
th
at
th
e
r
esu
lts
o
f
t
h
e
C
NN
im
p
lem
en
tatio
n
ar
e
q
u
ite
g
o
o
d
.
T
h
is
is
ev
id
en
t
f
r
o
m
t
h
e
tr
a
in
in
g
ac
cu
r
ac
y
an
d
v
alid
atio
n
ac
cu
r
ac
y
v
alu
es,
r
ea
c
h
in
g
8
5
%
an
d
8
2
.
5
%,
r
esp
ec
tiv
ely
.
T
r
ain
i
n
g
ac
c
u
r
a
cy
is
th
e
m
o
d
el
’
s
ac
cu
r
ac
y
wh
en
tr
ain
ed
with
tr
ain
in
g
d
ata
[
2
8
]
.
Valid
atio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
25
:
1
8
8
0
-
1
8
8
8
1886
ac
cu
r
ac
y
is
th
e
m
o
d
el
’
s
ac
cu
r
ac
y
wh
en
test
ed
with
v
alid
at
io
n
d
ata.
Hig
h
ac
cu
r
ac
y
v
al
u
es
in
d
icate
th
at
th
e
C
NN
m
o
d
el
is
ca
p
ab
le
o
f
r
ec
o
g
n
izin
g
p
atter
n
s
in
b
o
th
tr
ain
i
n
g
an
d
v
alid
atio
n
d
ata
ef
f
ec
tiv
ely
.
Fig
u
r
e
5
.
Mo
d
el
lo
s
s
g
r
ap
h
o
n
C
NN
Fig
u
r
e
6
.
Mo
d
el
ac
cu
r
ac
y
g
r
a
p
h
o
n
C
NN
3.
3
.
E
v
a
lua
t
io
n
T
h
e
m
o
d
el
e
v
alu
atio
n
s
tag
e
i
n
clu
d
es
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
F1
-
s
co
r
e,
an
d
co
n
f
u
s
i
o
n
m
atr
i
x
.
E
ac
h
o
f
th
ese
m
etr
ics
o
f
f
er
s
a
u
n
iq
u
e
p
er
s
p
ec
tiv
e
o
n
th
e
m
o
d
el’
s
p
er
f
o
r
m
an
ce
,
ass
ess
in
g
its
ab
ilit
y
to
p
r
e
d
ict
tar
g
et
v
alu
es
ac
c
u
r
ately
an
d
class
if
y
d
ata
ef
f
ec
tiv
ely
.
B
y
co
m
b
in
in
g
t
h
ese
m
etr
ics,
a
c
o
m
p
r
e
h
en
s
iv
e
u
n
d
er
s
tan
d
i
n
g
o
f
th
e
m
o
d
el
’
s
s
tr
en
g
th
s
an
d
wea
k
n
ess
es
is
ac
h
iev
ed
,
f
ac
ilit
atin
g
a
m
o
r
e
in
ter
p
r
etatio
n
o
f
its
p
r
ed
ictiv
e
an
d
g
en
e
r
aliza
tio
n
ca
p
ab
ilit
ies.
3.
3
.
1
.
Acc
ura
cy
,
re
c
a
ll,
prec
is
io
n,
a
nd
F
1
-
s
co
re
T
h
e
ac
cu
r
ac
y
r
esu
lt
i
n
d
icate
s
th
at
th
e
C
NN
m
o
d
el
ca
n
c
o
r
r
ec
tly
p
r
ed
ict
t
h
e
tar
g
et
f
o
r
8
4
.
5
%
o
f
th
e
to
tal
d
ata.
T
h
e
p
r
ec
is
io
n
v
alu
e
s
h
o
ws
th
at
th
e
C
NN
m
o
d
el
c
an
p
r
e
d
ict
th
e
ac
tu
al
ta
r
g
et
f
o
r
8
0
.
9
%
o
f
th
e
to
tal
ac
tu
al
tar
g
ets.
T
h
e
r
ec
all
v
al
u
e
in
d
icate
s
th
at
th
e
C
NN
m
o
d
el
ca
n
p
r
ed
ict
all
ac
t
u
al
tar
g
ets
f
o
r
7
9
.
8
%.
T
h
e
F1
-
s
co
r
e
v
alu
e
s
h
o
ws
th
at
th
e
C
NN
m
o
d
el
p
r
ed
icts
th
e
ta
r
g
et
well,
b
alan
cin
g
p
r
ec
is
io
n
an
d
r
ec
all,
with
a
s
co
r
e
o
f
8
0
.
4
%.
Fu
r
t
h
er
d
etail
s
ca
n
b
e
s
ee
n
in
Fig
u
r
e
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
S
tr
ess
d
etec
tio
n
th
r
o
u
g
h
w
ea
r
a
b
le
s
en
s
o
r
s
:
a
co
n
v
o
lu
tio
n
a
l
n
eu
r
a
l n
etw
o
r
k
-
b
a
s
ed
…
(
R
ifk
i Wija
ya
)
1887
3.
3
.
2
.
Co
nfusi
o
n
m
a
t
rix
B
ased
o
n
th
e
co
n
f
u
s
io
n
m
atr
ix
p
lo
t
f
r
o
m
C
NN,
it
ca
n
b
e
c
o
n
clu
d
e
d
th
at
t
h
e
C
NN
m
o
d
el
is
ca
p
ab
l
e
o
f
p
r
ed
ictin
g
class
es
with
g
o
o
d
ac
c
u
r
ac
y
.
T
h
is
is
e
v
id
en
t
f
r
o
m
th
e
h
ig
h
d
iag
o
n
al
v
alu
e
s
in
th
e
co
n
f
u
s
io
n
m
atr
ix
,
n
am
ely
2
3
,
7
0
8
f
o
r
class
1
an
d
1
4
,
2
7
4
f
o
r
class
2
.
T
h
e
d
iag
o
n
al
v
alu
es
i
n
th
e
co
n
f
u
s
io
n
m
atr
i
x
r
ep
r
esen
t
th
e
n
u
m
b
e
r
o
f
co
r
r
e
ctly
p
r
ed
icted
in
s
tan
ce
s
.
T
h
e
co
m
p
lete
C
o
n
f
u
s
io
n
Ma
tr
ix
r
e
s
u
lts
ca
n
b
e
s
ee
n
in
Fig
u
r
e
7
.
Fig
u
r
e
7
.
C
o
m
p
lete
c
o
n
f
u
s
io
n
m
atr
ix
an
d
e
v
alu
atio
n
r
esu
lt
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
aim
s
to
d
etec
t
s
tr
es
s
b
ased
o
n
h
ea
r
t
r
ate
u
s
in
g
th
e
C
NN
m
eth
o
d
.
T
h
e
ev
alu
atio
n
r
esu
lts
o
f
th
e
m
o
d
el
ac
h
iev
e
d
an
ac
cu
r
a
cy
o
f
8
4
.
5
%,
p
r
ec
is
io
n
o
f
8
0
.
9
%,
r
ec
all
o
f
7
9
.
8
%,
an
d
an
F1
-
s
co
r
e
o
f
8
0
.
4
%.
T
h
e
co
n
f
u
s
io
n
m
atr
ix
in
d
icate
s
th
at
th
e
m
o
d
el
ca
n
p
r
ed
ict
class
es
1
an
d
2
well,
wi
th
h
ig
h
d
iag
o
n
al
v
alu
es.
As
a
f
u
tu
r
e
r
esear
ch
d
ir
ec
tio
n
,
t
h
is
s
tu
d
y
co
u
ld
s
er
v
e
as
a
f
o
u
n
d
atio
n
f
o
r
f
u
r
th
e
r
ex
p
lo
r
ati
o
n
in
to
in
te
g
r
atin
g
ad
d
itio
n
al
f
ac
t
o
r
s
to
en
r
ich
h
e
ar
t
r
ate
d
ata
an
d
ad
d
in
g
m
o
r
e
s
u
b
jects
an
d
ty
p
es
o
f
s
tr
ess
.
T
h
is
co
u
ld
en
h
a
n
ce
th
e
ac
cu
r
ac
y
a
n
d
a
p
p
licab
ilit
y
o
f
th
e
m
o
d
el
in
m
o
r
e
c
o
m
p
lex
s
tr
ess
s
i
tu
atio
n
s
.
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
e
au
th
o
r
s
wo
u
ld
lik
e
to
ex
p
r
ess
th
eir
g
r
atitu
d
e
to
th
e
Sch
o
o
l
o
f
C
o
m
p
u
tin
g
,
Un
iv
er
s
ity
o
f
B
an
d
u
n
g
,
I
n
d
o
n
esia,
f
o
r
th
eir
f
in
an
cial
s
u
p
p
o
r
t
an
d
th
e
p
r
o
v
is
io
n
o
f
ess
en
tial
in
f
r
astru
ctu
r
e
th
at
m
ad
e
th
is
r
esear
ch
p
o
s
s
ib
le.
RE
F
E
R
E
NC
E
S
[
1
]
E.
S
.
C
e
r
i
n
o
e
t
a
l
.
,
“
P
r
e
ser
v
i
n
g
w
h
a
t
mat
t
e
r
s:
L
o
n
g
i
t
u
d
i
n
a
l
c
h
a
n
g
e
s i
n
c
o
n
t
r
o
l
o
v
e
r
i
n
t
e
r
p
e
r
so
n
a
l
st
r
e
ss a
n
d
n
o
n
i
n
t
e
r
p
e
r
so
n
a
l
st
r
e
ss
i
n
d
a
i
l
y
l
i
f
e
,
”
T
h
e
J
o
u
r
n
a
l
s
o
f
G
e
ro
n
t
o
l
o
g
y
,
S
e
r
i
e
s
B:
Psy
c
h
o
l
o
g
i
c
a
l
S
c
i
e
n
c
e
s
a
n
d
S
o
c
i
a
l
S
c
i
e
n
c
e
s
,
v
o
l
.
7
9
,
n
o
.
4
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
9
3
/
g
e
r
o
n
b
/
g
b
a
e
0
1
2
.
[
2
]
R
.
B
.
R
a
mt
e
k
e
a
n
d
V
.
R
.
T
h
o
o
l
,
“
H
e
a
r
t
r
a
t
e
v
a
r
i
a
b
i
l
i
t
y
-
b
a
s
e
d
me
n
t
a
l
st
r
e
s
s
d
e
t
e
c
t
i
o
n
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
i
n
A
p
p
l
i
e
d
I
n
f
o
rm
a
t
i
o
n
Pr
o
c
e
ssi
n
g
S
y
st
e
m
s
,
S
p
r
i
n
g
e
r
S
i
n
g
a
p
o
r
e
,
2
0
2
1
,
p
p
.
5
1
–
61
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
16
-
2
0
0
8
-
9
_
5
.
[
3
]
N
.
R
a
s
h
i
d
,
L.
C
h
e
n
,
M
.
D
a
u
t
t
a
,
A
.
Ji
me
n
e
z
,
P
.
Tse
n
g
,
a
n
d
M
.
A
.
A
l
F
a
r
u
q
u
e
,
“
F
e
a
t
u
r
e
a
u
g
m
e
n
t
e
d
h
y
b
r
i
d
C
N
N
f
o
r
st
r
e
ss
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
w
r
i
st
-
b
a
s
e
d
p
h
o
t
o
p
l
e
t
h
y
s
mo
g
r
a
p
h
y
se
n
s
o
r
,
”
i
n
2
0
2
1
4
3
r
d
A
n
n
u
a
l
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
f
t
h
e
I
EEE
En
g
i
n
e
e
ri
n
g
i
n
Me
d
i
c
i
n
e
& B
i
o
l
o
g
y
S
o
c
i
e
t
y
(
E
MB
C
)
,
N
o
v
.
2
0
2
1
,
p
p
.
2
3
7
4
–
2
3
7
7
,
d
o
i
:
1
0
.
1
1
0
9
/
E
M
B
C
4
6
1
6
4
.
2
0
2
1
.
9
6
3
0
5
7
6
.
[
4
]
E.
T
h
a
r
i
o
n
,
U
.
K
a
c
h
r
o
o
,
J
.
N
o
e
l
,
a
n
d
P
.
S
a
mu
e
l
,
“
C
a
r
d
i
a
c
a
u
t
o
n
o
m
i
c
a
c
t
i
v
i
t
y
,
p
e
r
so
n
a
l
i
t
y
t
r
a
i
t
s,
a
n
d
a
c
a
d
e
m
i
c
p
e
r
f
o
r
m
a
n
c
e
i
n
f
i
r
st
-
y
e
a
r
m
e
d
i
c
a
l
s
t
u
d
e
n
t
s:
a
g
e
n
d
e
r
-
s
p
e
c
i
f
i
c
r
e
l
a
t
i
o
n
,
”
C
u
re
u
s
,
N
o
v
.
2
0
2
3
,
d
o
i
:
1
0
.
7
7
5
9
/
c
u
r
e
u
s
.
4
9
0
8
7
.
[
5
]
K
.
M
.
D
a
l
me
i
d
a
a
n
d
G
.
L
.
M
a
sal
a
,
“
H
R
V
f
e
a
t
u
r
e
s
a
s
v
i
a
b
l
e
p
h
y
s
i
o
l
o
g
i
c
a
l
mar
k
e
r
s
f
o
r
st
r
e
ss
d
e
t
e
c
t
i
o
n
u
si
n
g
w
e
a
r
a
b
l
e
d
e
v
i
c
e
s
,
”
S
e
n
so
rs
,
v
o
l
.
2
1
,
n
o
.
8
,
A
p
r
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
s2
1
0
8
2
8
7
3
.
[
6
]
L.
S
h
u
e
t
a
l
.
,
“
W
e
a
r
a
b
l
e
e
mo
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
h
e
a
r
t
r
a
t
e
d
a
t
a
f
r
o
m
a
sm
a
r
t
b
r
a
c
e
l
e
t
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
0
,
n
o
.
3
,
J
a
n
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
0
0
3
0
7
1
8
.
[
7
]
G
.
Li
me
n
i
h
,
A
.
M
a
c
D
o
u
g
a
l
l
,
M
.
W
e
d
l
a
k
e
,
a
n
d
E.
N
o
u
v
e
t
,
“
D
e
p
r
e
ss
i
o
n
a
n
d
g
l
o
b
a
l
me
n
t
a
l
h
e
a
l
t
h
i
n
t
h
e
G
l
o
b
a
l
S
o
u
t
h
:
A
c
r
i
t
i
c
a
l
a
n
a
l
y
si
s
o
f
p
o
l
i
c
y
a
n
d
d
i
s
c
o
u
r
se,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
S
o
c
i
a
l
D
e
t
e
rm
i
n
a
n
t
s
o
f
H
e
a
l
t
h
a
n
d
H
e
a
l
t
h
S
e
rv
i
c
e
s
,
v
o
l
.
5
4
,
n
o
.
2
,
p
p
.
9
5
–
1
0
7
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
7
7
/
2
7
5
5
1
9
3
8
2
3
1
2
2
0
2
3
0
.
[
8
]
T.
C
a
ssi
d
y
,
S
t
r
e
ss,
c
o
g
n
i
t
i
o
n
a
n
d
h
e
a
l
t
h
:
Re
a
l
w
o
rl
d
e
x
a
m
p
l
e
s
a
n
d
p
r
a
c
t
i
c
a
l
a
p
p
l
i
c
a
t
i
o
n
s
.
R
o
u
t
l
e
d
g
e
,
2
0
2
2
,
d
o
i
:
1
0
.
4
3
2
4
/
9
7
8
1
0
0
3
0
9
8
7
3
7
.
[
9
]
M
.
J
.
H
o
r
o
w
i
t
z
,
T
re
a
t
m
e
n
t
o
f
st
r
e
ss r
e
sp
o
n
s
e
sy
n
d
ro
m
e
s
,
2
n
d
e
d
.
A
m
e
r
i
c
a
n
P
sy
c
h
i
a
t
r
i
c
A
ss
o
c
i
a
t
i
o
n
P
u
b
l
i
s
h
i
n
g
,
2
0
2
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
25
:
1
8
8
0
-
1
8
8
8
1888
[
1
0
]
R
.
T
i
w
a
r
i
,
R
.
K
u
m
a
r
,
S
.
M
a
l
i
k
,
T.
R
a
j
,
a
n
d
P
.
K
u
m
a
r
,
“
A
n
a
l
y
s
i
s
o
f
h
e
a
r
t
r
a
t
e
v
a
r
i
a
b
i
l
i
t
y
a
n
d
i
m
p
l
i
c
a
t
i
o
n
o
f
d
i
f
f
e
r
e
n
t
f
a
c
t
o
r
s
on
h
e
a
r
t
r
a
t
e
v
a
r
i
a
b
i
l
i
t
y
,
”
C
u
rre
n
t
C
a
r
d
i
o
l
o
g
y
Re
v
i
e
w
s
,
v
o
l
.
1
7
,
n
o
.
5
,
S
e
p
.
2
0
2
1
,
d
o
i
:
1
0
.
2
1
7
4
/
1
5
7
3
4
0
3
x
1
6
9
9
9
2
0
1
2
3
1
2
0
3
8
5
4
.
[
1
1
]
B
.
A
.
O
r
o
i
a
n
,
A
.
C
i
o
b
i
c
a
,
D
.
T
i
mo
f
t
e
,
C
.
S
t
e
f
a
n
e
sc
u
,
a
n
d
I
.
L.
S
e
r
b
a
n
,
“
N
e
w
me
t
a
b
o
l
i
c
,
d
i
g
e
st
i
v
e
,
a
n
d
o
x
i
d
a
t
i
v
e
s
t
r
e
ss
-
r
e
l
a
t
e
d
man
i
f
e
st
a
t
i
o
n
s
a
ss
o
c
i
a
t
e
d
w
i
t
h
p
o
s
t
t
r
a
u
ma
t
i
c
s
t
r
e
ss
d
i
s
o
r
d
e
r
,
”
O
x
i
d
a
t
i
v
e
Me
d
i
c
i
n
e
a
n
d
C
e
l
l
u
l
a
r
L
o
n
g
e
v
i
t
y
,
n
o
.
1
,
J
a
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
1
/
5
5
9
9
2
6
5
.
[
1
2
]
A
.
M
e
n
s
a
h
,
“
Jo
b
s
t
r
e
ss
a
n
d
me
n
t
a
l
w
e
l
l
-
b
e
i
n
g
a
m
o
n
g
w
o
r
k
i
n
g
me
n
a
n
d
w
o
me
n
i
n
E
u
r
o
p
e
:
T
h
e
me
d
i
a
t
i
n
g
r
o
l
e
o
f
s
o
c
i
a
l
su
p
p
o
r
t
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
n
v
i
ro
n
m
e
n
t
a
l
Re
s
e
a
r
c
h
a
n
d
P
u
b
l
i
c
H
e
a
l
t
h
,
v
o
l
.
1
8
,
n
o
.
5
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
i
j
e
r
p
h
1
8
0
5
2
4
9
4
.
[
1
3
]
B
.
T
h
i
e
l
m
a
n
n
,
R
.
S
.
S
c
h
i
e
r
h
o
l
z
,
a
n
d
I
.
B
ö
c
k
e
l
ma
n
n
,
“
S
u
b
j
e
c
t
i
v
e
a
n
d
o
b
j
e
c
t
i
v
e
c
o
n
se
q
u
e
n
c
e
s
o
f
s
t
r
e
ss
i
n
s
u
b
j
e
c
t
s
w
i
t
h
su
b
j
e
c
t
i
v
e
l
y
d
i
f
f
e
r
e
n
t
s
l
e
e
p
q
u
a
l
i
t
y
—
A
c
r
o
s
s
-
sec
t
i
o
n
a
l
st
u
d
y
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
n
v
i
ro
n
m
e
n
t
a
l
R
e
s
e
a
r
c
h
a
n
d
P
u
b
l
i
c
H
e
a
l
t
h
,
v
o
l
.
1
8
,
n
o
.
1
9
,
S
e
p
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
i
j
e
r
p
h
1
8
1
9
9
9
9
0
.
[
1
4
]
G
.
T
a
sk
a
sa
p
l
i
d
i
s,
D
.
A
.
F
o
t
i
a
d
i
s,
a
n
d
P
.
D
.
B
a
mi
d
i
s,
“
R
e
v
i
e
w
o
f
s
t
r
e
ss
d
e
t
e
c
t
i
o
n
met
h
o
d
s
u
si
n
g
w
e
a
r
a
b
l
e
s
e
n
so
r
s
,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
3
8
2
1
9
–
3
8
2
4
6
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
a
c
c
e
s
s.
2
0
2
4
.
3
3
7
3
0
1
0
.
[
1
5
]
L.
S
.
K
h
o
o
,
M
.
K
.
Li
m
,
C
.
Y
.
C
h
o
n
g
,
a
n
d
R
.
M
c
N
a
n
e
y
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
mu
l
t
i
mo
d
a
l
me
n
t
a
l
h
e
a
l
t
h
d
e
t
e
c
t
i
o
n
:
A
sy
s
t
e
mat
i
c
r
e
v
i
e
w
o
f
p
a
ssi
v
e
se
n
si
n
g
a
p
p
r
o
a
c
h
e
s
,
”
S
e
n
so
rs
,
v
o
l
.
2
4
,
n
o
.
2
,
Ja
n
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
s2
4
0
2
0
3
4
8
.
[
1
6
]
T.
C
h
a
l
mers
e
t
a
l
.
,
“
S
t
r
e
ss
w
a
t
c
h
:
T
h
e
u
se
o
f
h
e
a
r
t
r
a
t
e
a
n
d
h
e
a
r
t
r
a
t
e
v
a
r
i
a
b
i
l
i
t
y
t
o
d
e
t
e
c
t
st
r
e
ss:
A
p
i
l
o
t
s
t
u
d
y
u
si
n
g
sm
a
r
t
w
a
t
c
h
w
e
a
r
a
b
l
e
s
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
2
,
n
o
.
1
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
2
0
1
0
1
5
1
.
[
1
7
]
S.
-
H
.
S
i
m,
“
Ex
p
l
o
r
a
t
i
o
n
o
f
e
d
g
e
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
se
d
s
t
r
e
ss
d
e
t
e
c
t
i
o
n
u
si
n
g
w
e
a
r
a
b
l
e
d
e
v
i
c
e
s,
”
M
.
S
.
t
h
e
si
s,
A
r
i
z
o
n
a
S
t
a
t
e
U
n
i
v
e
r
si
t
y
,
2
0
2
2
.
[
1
8
]
L.
F
o
n
t
e
s
,
P
.
M
a
c
h
a
d
o
,
D
.
V
i
n
k
e
m
e
i
e
r
,
S
.
Y
a
h
a
y
a
,
J
.
J
.
B
i
r
d
,
a
n
d
I
.
K
.
I
h
i
a
n
l
e
,
“
En
h
a
n
c
i
n
g
st
r
e
ss
d
e
t
e
c
t
i
o
n
:
A
c
o
mp
r
e
h
e
n
s
i
v
e
a
p
p
r
o
a
c
h
t
h
r
o
u
g
h
r
P
P
G
a
n
a
l
y
s
i
s
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
4
,
n
o
.
4
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
s2
4
0
4
1
0
9
6
.
[
1
9
]
A
.
N
.
B
r
o
c
k
m
a
n
n
a
n
d
K
.
M
.
R
o
ss,
“
B
i
d
i
r
e
c
t
i
o
n
a
l
a
sso
c
i
a
t
i
o
n
b
e
t
w
e
e
n
st
r
e
ss
a
n
d
p
h
y
si
c
a
l
a
c
t
i
v
i
t
y
i
n
a
d
u
l
t
s
w
i
t
h
o
v
e
r
w
e
i
g
h
t
a
n
d
o
b
e
si
t
y
,
”
J
o
u
r
n
a
l
o
f
B
e
h
a
v
i
o
r
a
l
M
e
d
i
c
i
n
e
,
v
o
l
.
4
3
,
n
o
.
2
,
p
p
.
2
4
6
–
2
5
3
,
M
a
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
8
6
5
-
020
-
0
0
1
4
5
-
2.
[
2
0
]
M
.
A
l
t
i
n
i
a
n
d
D
.
P
l
e
w
s
,
“
W
h
a
t
i
s
b
e
h
i
n
d
c
h
a
n
g
e
s
i
n
r
e
s
t
i
n
g
h
e
a
r
t
r
a
t
e
a
n
d
h
e
a
r
t
r
a
t
e
v
a
r
i
a
b
i
l
i
t
y
?
A
l
a
r
g
e
-
sca
l
e
a
n
a
l
y
si
s
o
f
l
o
n
g
i
t
u
d
i
n
a
l
m
e
a
s
u
r
e
m
e
n
t
s a
c
q
u
i
r
e
d
i
n
f
r
e
e
-
l
i
v
i
n
g
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
1
,
n
o
.
2
3
,
N
o
v
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
1
2
3
7
9
3
2
.
[
2
1
]
Y
.
Z
h
a
n
g
,
M
.
S
a
f
d
a
r
,
J.
X
i
e
,
J
.
Li
,
M
.
S
a
g
e
,
a
n
d
Y
.
F
.
Zh
a
o
,
“
A
sy
s
t
e
m
a
t
i
c
r
e
v
i
e
w
o
n
d
a
t
a
o
f
a
d
d
i
t
i
v
e
m
a
n
u
f
a
c
t
u
r
i
n
g
f
o
r
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
l
i
c
a
t
i
o
n
s
:
t
h
e
d
a
t
a
q
u
a
l
i
t
y
,
t
y
p
e
,
p
r
e
p
r
o
c
e
ss
i
n
g
,
a
n
d
ma
n
a
g
e
men
t
,
”
J
o
u
r
n
a
l
o
f
I
n
t
e
l
l
i
g
e
n
t
M
a
n
u
f
a
c
t
u
r
i
n
g
,
v
o
l
.
3
4
,
n
o
.
8
,
p
p
.
3
3
0
5
–
3
3
4
0
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
8
4
5
-
0
2
2
-
0
2
0
1
7
-
9.
[
2
2
]
R
.
K
h
a
n
a
m,
M
.
H
u
ssa
i
n
,
R
.
H
i
l
l
,
a
n
d
P
.
A
l
l
e
n
,
“
A
c
o
mp
r
e
h
e
n
s
i
v
e
r
e
v
i
e
w
o
f
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
s
f
o
r
d
e
f
e
c
t
d
e
t
e
c
t
i
o
n
i
n
i
n
d
u
st
r
i
a
l
a
p
p
l
i
c
a
t
i
o
n
s
,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
9
4
2
5
0
–
9
4
2
9
5
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
a
c
c
e
s
s.
2
0
2
4
.
3
4
2
5
1
6
6
.
[
2
3
]
Y
.
W
a
n
g
,
Y
.
Li
,
Y
.
S
o
n
g
,
a
n
d
X
.
R
o
n
g
,
“
T
h
e
i
n
f
l
u
e
n
c
e
o
f
t
h
e
a
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
i
n
a
c
o
n
v
o
l
u
t
i
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
m
o
d
e
l
o
f
f
a
c
i
a
l
e
x
p
r
e
ss
i
o
n
r
e
c
o
g
n
i
t
i
o
n
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
0
,
n
o
.
5
,
M
a
r
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
0
0
5
1
8
9
7
.
[
2
4
]
D
.
K
r
st
i
n
i
ć
,
M
.
B
r
a
o
v
i
ć
,
L
.
Š
e
r
i
ć
,
a
n
d
D
.
B
o
ž
i
ć
-
Š
t
u
l
i
ć
,
“
M
u
l
t
i
-
l
a
b
e
l
c
l
a
ssi
f
i
e
r
p
e
r
f
o
r
ma
n
c
e
e
v
a
l
u
a
t
i
o
n
w
i
t
h
c
o
n
f
u
si
o
n
m
a
t
r
i
x
,
”
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
& In
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
J
u
n
.
2
0
2
0
,
p
p
.
1
–
14
,
d
o
i
:
1
0
.
5
1
2
1
/
c
si
t
.
2
0
2
0
.
1
0
0
8
0
1
.
[
2
5
]
M
.
H
e
y
d
a
r
i
a
n
,
T.
E.
D
o
y
l
e
,
a
n
d
R
.
S
a
ma
v
i
,
“
M
L
C
M
:
M
u
l
t
i
-
l
a
b
e
l
c
o
n
f
u
s
i
o
n
m
a
t
r
i
x
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
0
,
p
p
.
1
9
0
8
3
–
1
9
0
9
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
a
c
c
e
ss
.
2
0
2
2
.
3
1
5
1
0
4
8
.
[
2
6
]
J.
C
.
O
b
i
,
“
A
c
o
m
p
a
r
a
t
i
v
e
s
t
u
d
y
o
f
s
e
v
e
r
a
l
c
l
a
ssi
f
i
c
a
t
i
o
n
m
e
t
r
i
c
s
a
n
d
t
h
e
i
r
p
e
r
f
o
r
m
a
n
c
e
s
o
n
d
a
t
a
,
”
Wo
rl
d
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
d
En
g
i
n
e
e
ri
n
g
T
e
c
h
n
o
l
o
g
y
a
n
d
S
c
i
e
n
c
e
s
,
v
o
l
.
8
,
n
o
.
1
,
p
p
.
3
0
8
–
3
1
4
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
3
0
5
7
4
/
w
j
a
e
t
s
.
2
0
2
3
.
8
.
1
.
0
0
5
4
.
[
2
7
]
D
.
S
i
n
g
h
a
n
d
B
.
S
i
n
g
h
,
“
I
n
v
e
s
t
i
g
a
t
i
n
g
t
h
e
i
m
p
a
c
t
o
f
d
a
t
a
n
o
r
ma
l
i
z
a
t
i
o
n
o
n
c
l
a
ss
i
f
i
c
a
t
i
o
n
p
e
r
f
o
r
ma
n
c
e
,
”
A
p
p
l
i
e
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
9
7
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
so
c
.
2
0
1
9
.
1
0
5
5
2
4
.
[
2
8
]
B
.
M
i
r
z
a
s
o
l
e
i
m
a
n
,
J.
B
i
l
m
e
s,
a
n
d
J
.
Le
s
k
o
v
e
c
,
“
C
o
r
e
se
t
s
f
o
r
d
a
t
a
-
e
f
f
i
c
i
e
n
t
t
r
a
i
n
i
n
g
o
f
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
mo
d
e
l
s
,
”
i
n
3
7
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
Ma
c
h
i
n
e
L
e
a
r
n
i
n
g
,
I
C
ML
2
0
2
0
,
2
0
2
0
,
p
p
.
6
9
0
6
–
6
9
1
6
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Rifk
i
Wija
y
a
re
c
e
iv
e
d
th
e
b
a
c
h
e
lo
r
d
e
g
re
e
i
n
m
a
th
e
m
a
ti
c
s
,
a
m
a
ste
r
d
e
g
re
e
in
d
ig
it
a
l
m
e
d
ia
g
a
m
e
a
n
d
tec
h
n
o
lo
g
y
,
a
n
d
a
P
h
.
D.
in
e
lec
tri
c
a
l
e
n
g
in
e
e
rin
g
a
n
d
i
n
fo
rm
a
ti
c
s
fro
m
th
e
Ba
n
d
u
n
g
In
st
it
u
te
o
f
Tec
h
n
o
l
o
g
y
.
C
u
rre
n
tl
y
se
rv
in
g
a
s
a
lec
tu
r
e
r
a
n
d
re
se
a
rc
h
e
r
a
t
Telk
o
m
Un
iv
e
rsity
,
h
is
re
se
a
rc
h
a
n
d
d
e
v
e
lo
p
m
e
n
t
f
o
c
u
s
e
n
c
o
m
p
a
ss
e
s
a
re
a
s
su
c
h
a
s
d
a
ta
s
c
ien
c
e
,
a
rti
ficia
l
in
telli
g
e
n
c
e
,
b
i
o
m
e
d
ica
l
in
fo
rm
a
ti
c
s,
b
ig
d
a
ta,
a
n
d
Io
T
.
H
e
h
a
s
a
c
ti
v
e
ly
p
lay
e
d
a
r
o
le
in
t
h
e
a
c
a
d
e
m
ic
c
o
m
m
u
n
it
y
,
se
rv
in
g
a
s
a
sp
e
a
k
e
r
a
t
v
a
rio
u
s
c
o
n
fe
re
n
c
e
s
a
n
d
p
u
b
li
s
h
in
g
in
flu
e
n
ti
a
l
wo
rk
s
i
n
p
re
stig
io
u
s
jo
u
r
n
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s.
Wi
t
h
a
c
o
m
m
it
m
e
n
t
to
h
ig
h
e
r
e
d
u
c
a
ti
o
n
a
n
d
t
h
e
in
teg
ra
ti
o
n
o
f
th
e
o
ry
a
n
d
p
ra
c
ti
c
e
,
a
lo
n
g
wit
h
h
is
d
e
d
ica
ti
o
n
t
o
in
n
o
v
a
ti
v
e
tea
c
h
in
g
m
e
th
o
d
s,
h
e
b
r
in
g
s
v
a
lu
a
b
le
c
o
n
t
rib
u
ti
o
n
s
to
a
d
v
a
n
c
in
g
th
e
se
field
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
rif
k
iwij
a
y
a
@t
e
lk
o
m
u
n
iv
e
rsit
y
.
a
c
.
id
.
G
a
m
m
a
K
o
s
a
la
e
a
rn
e
d
h
is
b
a
c
h
e
l
o
r
d
e
g
re
e
(B
.
Sc
.
)
in
e
lec
tro
n
ics
a
n
d
in
stru
m
e
n
tati
o
n
fr
o
m
G
a
d
jah
M
a
d
a
Un
iv
e
rsity
,
m
a
ste
r’s
d
e
g
re
e
(M
.
Sc
.
)
in
a
rti
ficia
l
in
telli
g
e
n
c
e
fro
m
G
a
d
jah
M
a
d
a
Un
iv
e
rsity
,
a
n
d
D
o
c
to
ra
te
(P
h
.
D
.
)
in
ima
g
e
p
ro
c
e
ss
in
g
fr
o
m
G
a
d
jah
M
a
d
a
Un
i
v
e
rsity
.
Cu
rre
n
tl
y
,
h
e
tea
c
h
e
s
a
n
d
c
o
n
d
u
c
ts
re
se
a
rc
h
a
t
Telk
o
m
Un
i
v
e
rsity
,
fo
c
u
sin
g
o
n
th
e
field
s
o
f
c
o
m
p
u
ter
v
isio
n
,
m
a
c
h
in
e
lea
rn
in
g
,
a
rti
ficia
l
in
telli
g
e
n
c
e
.
As
a
n
a
c
ti
v
e
m
e
m
b
e
r
o
f
th
e
c
o
m
m
u
n
it
y
,
h
e
f
re
q
u
e
n
tl
y
sp
e
a
k
s
a
t
c
o
n
fe
re
n
c
e
s
a
n
d
p
u
b
li
sh
e
s
a
rt
icle
s
in
p
re
stig
i
o
u
s
j
o
u
r
n
a
ls,
d
ri
v
in
g
i
n
n
o
v
a
t
io
n
th
r
o
u
g
h
h
is
d
e
d
ica
ti
o
n
to
h
i
g
h
e
r
e
d
u
c
a
ti
o
n
a
n
d
c
u
tt
in
g
-
e
d
g
e
tea
c
h
in
g
m
e
th
o
d
s.
H
e
c
a
n
b
e
c
o
n
tac
ted
a
t
:
g
a
m
m
a
k
o
sa
la@
telk
o
m
u
n
iv
e
rsity
.
a
c
.
id
.
Evaluation Warning : The document was created with Spire.PDF for Python.