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.
36
,
No
.
1
,
Octo
b
er
20
24
,
p
p
.
3
0
2
~
3
1
7
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
36.
i
1
.
p
p
302
-
3
1
7
302
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
The po
ten
tial o
f
t
he int
e
rnet
of
thi
ng
s for huma
n ac
tivity
recog
nition in sm
a
rt
ho
me: ov
ervi
e
w,
cha
lleng
es
,
a
p
pro
a
ches
K
ha
dija
E
s
s
a
f
i,
L
a
ila
M
o
us
s
a
id
En
g
i
n
e
e
r
i
n
g
,
I
n
n
o
v
a
t
i
o
n
a
n
d
Emer
g
i
n
g
T
e
c
h
n
o
l
o
g
i
e
s (E
2
I
T)
,
En
g
i
n
e
e
r
i
n
g
R
e
se
a
r
c
h
L
a
b
o
r
a
t
o
r
y
(
L
R
I
)
,
EN
S
EM
,
H
a
ssan
I
I
U
n
i
v
e
r
si
t
y
,
C
a
sa
b
l
a
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
Feb
15
,
2
0
2
4
R
ev
is
ed
Ma
y
27
,
2
0
2
4
Acc
ep
ted
J
u
n
5
,
2
0
2
4
Hu
m
a
n
a
c
ti
v
it
y
re
c
o
g
n
it
io
n
(HA
R)
is
a
tec
h
n
o
lo
g
y
t
h
a
t
i
n
fe
rs
c
u
rre
n
t
u
se
r
a
c
ti
v
it
ies
b
y
u
si
n
g
t
h
e
a
v
a
il
a
b
le
se
n
so
ry
d
a
ta
n
e
two
r
k
.
Re
se
a
rc
h
o
n
a
c
ti
v
it
y
re
c
o
g
n
it
i
o
n
is
c
o
n
sid
e
re
d
e
x
trem
e
ly
imp
o
r
tan
t,
p
a
rti
c
u
larly
w
h
e
n
it
c
o
m
e
s
to
d
e
li
v
e
rin
g
se
n
si
ti
v
e
se
rv
ice
s
su
c
h
a
s
h
e
a
lt
h
c
a
re
se
rv
ice
s
a
n
d
li
v
e
trac
k
in
g
a
ss
istan
c
e
a
n
d
a
u
to
n
o
m
y
.
F
o
r
t
h
i
s
p
u
rp
o
se
,
m
a
n
y
re
se
a
rc
h
e
rs
h
a
v
e
p
ro
p
o
se
d
a
k
n
o
wle
d
g
e
-
d
ri
v
e
n
a
p
p
ro
a
c
h
o
r
d
a
ta
-
d
riv
e
n
re
a
so
n
i
n
g
f
o
r
id
e
n
ti
fica
ti
o
n
tec
h
n
iq
u
e
s.
Ho
we
v
e
r,
t
h
e
re
a
re
m
u
lt
ip
le
li
m
it
a
ti
o
n
s
a
ss
o
c
iate
d
with
t
h
e
se
a
p
p
ro
a
c
h
e
s
a
n
d
t
h
e
re
su
lt
i
n
g
m
o
d
e
ls
a
re
ty
p
ica
ll
y
n
o
t
c
o
m
p
lete
e
n
o
u
g
h
t
o
c
a
p
tu
re
a
ll
ty
p
e
s
o
f
h
u
m
a
n
a
c
ti
v
it
ies
.
Th
u
s,
re
c
e
n
t
wo
r
k
s
h
a
v
e
su
g
g
e
ste
d
c
o
m
b
in
i
n
g
th
e
se
tec
h
n
i
q
u
e
s
t
h
ro
u
g
h
a
h
y
b
ri
d
m
o
d
e
l.
T
h
is
p
a
p
e
r'
s
g
o
a
l
is
to
g
iv
e
a
b
rief
o
v
e
rv
iew
o
f
a
c
ti
v
it
y
re
c
o
g
n
it
i
o
n
imp
lem
e
n
tati
o
n
a
p
p
r
o
a
c
h
e
s
b
y
lo
o
k
in
g
a
t
v
a
ri
o
u
s
se
n
si
n
g
tec
h
n
o
lo
g
ies
u
se
d
t
o
g
a
t
h
e
r
d
a
ta
fro
m
in
tern
e
t
o
f
th
in
g
s
(I
o
T)
g
a
d
g
e
ts,
lo
o
k
i
n
g
a
t
p
re
p
ro
c
e
ss
in
g
a
n
d
fe
a
tu
re
e
x
trac
ti
o
n
a
p
p
ro
a
c
h
e
s,
a
n
d
th
e
n
c
o
m
p
a
rin
g
m
e
th
o
d
s
u
se
d
t
o
id
e
n
ti
fy
h
u
m
a
n
a
c
ti
v
it
ies
in
sm
a
rt
h
o
m
e
s,
a
n
d
h
i
g
h
li
g
h
ti
n
g
t
h
e
ir
stre
n
g
t
h
s
a
n
d
we
a
k
n
e
s
se
s
a
c
ro
ss
v
a
rio
u
s
fiel
d
s.
Nu
m
e
ro
u
s
p
e
r
ti
n
e
n
t
wo
r
k
s
we
re
lo
c
a
ted
,
a
n
d
th
e
i
r
a
c
c
o
m
p
li
sh
m
e
n
ts we
re
a
ss
e
ss
e
d
.
K
ey
w
o
r
d
s
:
Activ
ity
r
ec
o
g
n
itio
n
Data
-
d
r
iv
en
I
n
ter
n
et
o
f
th
in
g
s
Kn
o
wled
g
e
-
d
r
iv
en
Sm
ar
t h
o
m
e
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
:
Kh
ad
ija
E
s
s
af
i
E
n
g
in
ee
r
in
g
,
I
n
n
o
v
atio
n
an
d
E
m
er
g
in
g
T
ec
h
n
o
lo
g
ies (
E
2
I
T
)
,
E
n
g
in
ee
r
i
n
g
R
esear
ch
L
ab
o
r
a
to
r
y
(
L
R
I
)
E
NSEM
,
Hass
an
I
I
Un
iv
er
s
ity
C
asab
lan
ca
,
Mo
r
o
cc
o
E
m
ail: k
h
ad
ija.
ess
af
i.d
o
c2
1
@
en
s
em
.
ac
.
m
a
1.
I
NT
RO
D
UCT
I
O
N
No
wad
ay
s
,
a
s
m
ar
t
h
o
m
e
c
o
m
es
with
a
wid
e
r
a
n
g
e
o
f
s
en
s
o
r
s
an
d
ac
tu
ato
r
s
,
wh
ic
h
r
ef
e
r
s
to
au
to
m
atio
n
t
o
o
ls
th
at
ca
n
h
el
p
to
d
etec
t
an
d
m
ea
s
u
r
e
th
e
p
h
y
s
ical
ch
ar
ac
ter
is
tics
o
f
th
e
en
v
ir
o
n
m
en
t
ar
o
u
n
d
u
s
.
T
h
ey
ar
e
ca
p
ab
le
o
f
m
ea
s
u
r
in
g
lig
h
t
in
ten
s
ity
,
co
n
v
er
ti
n
g
h
ea
t
in
to
tem
p
er
atu
r
e,
d
ete
ctin
g
d
o
o
r
o
p
en
in
g
s
,
d
etec
tin
g
tem
p
er
at
u
r
e
an
d
h
u
m
id
ity
ch
an
g
es
in
th
e
r
o
o
m
s
,
as
well
as
o
p
er
atin
g
o
u
r
h
o
m
e
ap
p
lian
ce
s
an
d
h
ea
tin
g
s
y
s
tem
s
.
T
h
ese
d
ev
ic
es
ca
n
n
o
w
b
e
r
em
o
tely
co
n
tr
o
lled
an
d
co
n
n
ec
ted
to
a
n
in
c
r
ea
s
in
g
n
u
m
b
er
o
f
d
ev
ices.
T
h
er
ef
o
r
e,
a
s
m
ar
t
h
o
m
e
m
u
s
t
co
m
p
r
eh
en
d
a
n
d
r
ec
o
g
n
ize
h
u
m
an
b
e
h
av
io
u
r
to
o
f
f
er
al
l
o
f
th
ese
f
u
n
ctio
n
s
.
T
o
ac
h
iev
e
th
is
,
r
e
s
ea
r
ch
er
s
ar
e
wo
r
k
i
n
g
o
n
h
u
m
an
ac
tiv
ity
r
ec
o
g
n
itio
n
(
HAR)
m
eth
o
d
o
lo
g
ies,
in
v
o
lv
in
g
th
e
o
b
s
er
v
atio
n
an
d
ass
ess
m
en
t
o
f
th
e
ac
tio
n
s
p
er
f
o
r
m
ed
b
y
o
n
e
o
r
m
o
r
e
in
d
iv
i
d
u
als,
with
th
e
aim
o
f
id
en
tify
i
n
g
th
e
s
p
ec
if
ic
ac
t
iv
ities
b
ein
g
ca
r
r
ied
o
u
t.
T
wo
ca
teg
o
r
ies
[
1
]
s
en
s
o
r
-
b
ased
s
y
s
tem
s
an
d
v
id
eo
-
b
ased
s
y
s
tem
s
—
ca
n
b
e
u
s
ed
to
ca
teg
o
r
ize
th
e
n
u
m
er
o
u
s
HA
R
s
y
s
tem
s
[
2
]
as sh
o
wn
in
Fig
u
r
e
1
.
T
h
e
HAR
s
y
s
tem
m
ay
r
ec
o
g
n
ize
a
p
er
s
o
n
'
s
in
ten
tio
n
s
an
d
ac
tio
n
s
b
y
tr
ac
k
in
g
h
is
o
r
h
er
ac
tiv
ities
.
Sin
ce
s
en
s
o
r
s
an
d
ca
m
e
r
as
ar
e
n
o
w
r
ea
d
ily
av
ailab
le
an
d
f
air
ly
p
r
iced
,
it
is
o
n
e
o
f
th
e
m
o
s
t
p
o
p
u
lar
a
n
d
d
if
f
icu
lt st
u
d
y
to
p
ics r
ig
h
t n
o
w.
I
n
HAR,
th
e
ter
m
"d
ata
co
l
lectio
n
"
r
ef
er
s
to
th
e
g
ath
er
in
g
o
f
s
en
s
o
r
s
ig
n
als o
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:
2
5
0
2
-
4
7
52
Th
e
p
o
ten
tia
l
o
f th
e
in
tern
et
o
f th
in
g
s
fo
r
h
u
ma
n
a
ctivity
r
ec
o
g
n
itio
n
i
n
s
ma
r
t h
o
me
… (
K
h
a
d
ija
E
s
s
a
fi
)
303
v
id
eo
s
.
Data
s
ets
ar
e
o
f
ten
o
b
tain
ed
f
r
o
m
s
en
s
o
r
s
s
u
ch
th
e
elec
tr
o
m
y
o
g
r
ap
h
y
,
ac
ce
ler
o
m
eter
,
g
y
r
o
s
co
p
e,
m
ag
n
eto
m
eter
,
an
d
v
id
eo
o
r
s
till
p
ictu
r
es,
m
ak
in
g
th
em
a
f
u
n
d
am
e
n
tal
p
ar
t
an
d
t
h
e
f
o
u
n
d
atio
n
o
f
a
n
y
HAR
s
y
s
tem
.
Activ
ity
r
ec
o
g
n
itio
n
c
an
b
e
d
i
v
id
ed
in
t
o
two
g
r
o
u
p
s
:
s
en
s
o
r
-
b
ased
an
d
v
is
io
n
-
b
ased
.
Fig
u
r
e
1
.
HAR
ca
teg
o
r
ies
Vis
io
n
-
b
ased
HAR
is
th
e
u
s
e
o
f
co
m
p
u
ter
v
is
io
n
to
o
ls
,
s
u
ch
as
ca
m
er
as,
to
m
o
n
ito
r
ch
a
n
g
es
in
th
e
en
v
ir
o
n
m
en
t
a
n
d
h
u
m
a
n
ac
tiv
i
ty
.
I
t h
as
lately
b
ec
o
m
e
m
o
r
e
p
r
o
m
in
e
n
t
as
a
r
esu
lt
o
f
its
u
s
ag
e
ac
r
o
s
s
a
d
iv
er
s
e
r
an
g
e
o
f
p
r
ac
tical
ap
p
licatio
n
s
,
lik
e
en
s
u
r
in
g
s
ec
u
r
ity
an
d
co
n
d
u
ctin
g
s
u
r
v
eillan
ce
.
To
g
u
ar
an
tee
s
ec
u
r
ity
in
p
u
b
lic
lo
ca
tio
n
s
,
it
is
cr
u
cia
l
to
im
p
lem
e
n
t
HAR
f
o
r
cl
o
s
ed
-
cir
cu
it
telev
is
io
n
(
C
C
T
V)
s
y
s
tem
s
,
wh
ich
co
m
p
r
is
e
a
n
etwo
r
k
o
f
ca
m
er
a
s
with
a
ce
n
tr
al
r
ec
o
r
d
in
g
h
u
b
.
Vis
io
n
-
b
ased
HAR
r
esear
ch
ca
n
b
e
d
iv
i
d
ed
in
to
r
ed
g
r
ee
n
b
lu
e
(
R
GB
)
d
ata
[
3
]
a
n
d
r
e
d
g
r
ee
n
b
l
u
e
-
d
ep
th
(
R
GB
-
D
)
d
ata
[
4
]
d
ep
e
n
d
in
g
o
n
th
e
ty
p
e
o
f
d
ata
e
m
p
lo
y
ed
.
Vis
io
n
-
b
ased
HAR
f
r
am
ewo
r
k
s
u
tili
zin
g
R
GB
d
ata
o
f
ten
ex
h
ib
it
a
lo
wer
lev
el
o
f
ac
cu
r
ac
y
c
o
m
p
a
r
ed
to
th
o
s
e
u
tili
zin
g
R
GB
-
D
d
ata,
o
win
g
to
th
e
au
g
m
en
ted
in
f
o
r
m
atio
n
a
n
d
d
ep
th
ch
an
n
els
p
r
o
v
i
d
ed
b
y
m
u
lti
-
m
o
d
al
d
ata
[
3
]
.
Nev
e
r
th
ele
s
s
,
th
e
u
tili
za
tio
n
o
f
R
GB
d
ata
r
em
ain
s
p
r
ev
alen
t
in
cu
r
r
en
t
HAR
f
r
am
ewo
r
k
s
d
u
e
to
ch
allen
g
es
s
u
ch
as
th
e
co
m
p
lex
ities
o
f
s
etu
p
(
in
v
o
lv
in
g
in
tr
icate
co
n
f
ig
u
r
a
tio
n
s
f
o
r
v
ar
io
u
s
HAR
s
ce
n
ar
io
s
)
,
co
m
p
u
tatio
n
al
d
em
an
d
s
ar
is
in
g
f
r
o
m
v
ast
d
atasets
,
an
d
elev
ated
ex
p
en
s
es.
On
th
e
o
th
er
h
an
d
,
s
en
s
o
r
-
b
ased
HAR
ca
p
tu
r
es
d
aily
liv
in
g
ac
tiv
ities
f
r
o
m
s
en
s
o
r
s
[
5
]
,
a
n
d
in
v
o
lv
es
f
o
llo
win
g
a
p
er
s
o
n
'
s
ac
tiv
ities
u
s
in
g
a
n
etwo
r
k
o
f
co
n
n
ec
te
d
d
ev
ices.D
a
ta
f
r
o
m
th
e
s
en
s
o
r
s
is
g
en
er
ated
as
a
tim
e
s
er
ies
o
f
s
tate
ch
an
g
es
o
r
p
ar
am
eter
v
alu
es.
Nu
m
er
o
u
s
s
en
s
o
r
s
,
in
clu
d
in
g
ac
ce
ler
o
m
eter
s
,
m
ag
n
eto
m
eter
s
,
n
o
is
e
s
en
s
o
r
s
,
elec
t
r
o
m
y
o
g
r
a
p
h
y
,
g
y
r
o
s
co
p
es,
an
d
r
a
d
ar
,
ca
n
b
e
p
o
s
itio
n
ed
o
n
p
e
o
p
le,
o
n
th
in
g
s
,
o
r
i
n
th
e
e
n
v
ir
o
n
m
en
t
.
As
a
r
esu
lt,
th
er
e
a
r
e
th
r
ee
d
is
tin
ct
ca
teg
o
r
ies
in
to
wh
ic
h
th
e
s
en
s
o
r
-
b
ased
s
o
lu
tio
n
s
ca
n
b
e
s
u
b
d
iv
id
ed
:
wea
r
ab
le
[
6
]
,
s
en
s
o
r
o
n
o
b
ject
s
[
7
]
,
an
d
am
b
ien
t sen
s
o
r
[
8
].
−
W
ea
r
ab
le
s
en
s
o
r
:
wh
ich
is
f
r
eq
u
en
tly
u
s
ed
f
o
r
HAR
s
y
s
tem
s
,
ca
n
d
ir
ec
tly
r
ec
o
r
d
b
o
d
y
m
o
v
em
en
t.
Acc
eler
o
m
eter
,
m
a
g
n
eto
m
eter
,
an
d
g
y
r
o
s
co
p
e
a
r
e
th
r
ee
co
m
m
o
n
wea
r
a
b
le
s
en
s
o
r
s
th
at
ca
n
b
e
ea
s
ily
wo
r
n
b
y
p
eo
p
le
o
r
in
teg
r
ated
in
t
o
p
o
r
tab
le
d
ev
ices lik
e
s
m
ar
tp
h
o
n
es [
9
]
,
s
m
ar
t b
an
d
s
,
s
m
ar
t w
atch
es,
o
r
g
lass
es.
T
h
en
,
b
y
co
m
p
ar
in
g
th
e
s
ig
n
al
d
if
f
er
en
ce
s
b
ef
o
r
e
an
d
a
f
ter
a
n
ac
tiv
ity
,
h
u
m
an
ac
tiv
ity
ca
n
b
e
id
en
tifie
d
.
−
Sen
s
o
r
o
n
o
b
jects:
th
e
s
en
s
o
r
s
th
at
ar
e
af
f
ix
e
d
to
a
s
p
ec
if
ic
o
b
ject
to
tr
ac
k
ac
tiv
ity
ar
o
u
n
d
it
[
10
]
.
W
h
ile
o
b
ject
s
en
s
o
r
s
d
etec
t
th
e
m
o
v
em
en
t
o
f
a
s
p
ec
if
ic
o
b
ject
to
i
n
f
er
h
u
m
an
ac
tiv
ity
,
wea
r
ab
le
s
en
s
o
r
s
ass
es
s
h
u
m
an
b
e
h
av
io
u
r
s
d
ir
ec
tly
.
A
s
m
ar
t
d
r
in
k
in
g
c
u
p
,
f
o
r
in
s
tan
ce
,
m
ay
h
a
v
e
an
ac
ce
ler
o
m
eter
lin
k
ed
to
it
to
m
o
r
e
ef
f
ec
tiv
ely
m
o
n
ito
r
th
e
u
s
er
'
s
d
r
in
k
in
g
p
atter
n
s
an
d
al
er
t
th
em
wh
en
th
eir
d
aily
wate
r
co
n
s
u
m
p
tio
n
is
in
s
u
f
f
icien
t
[
1
1
]
.
A
n
o
th
er
in
s
tan
ce
o
f
HAR
u
tili
zin
g
s
m
ar
t
o
b
ject
s
en
s
o
r
s
is
th
e
u
s
ag
e
o
f
s
m
ar
t
d
o
o
r
b
ells
,
wh
ich
ty
p
ically
f
ea
t
u
r
e
a
ca
m
e
r
a
an
d
a
m
icr
o
p
h
o
n
e
an
d
h
elp
to
d
etec
t
th
e
p
r
esen
ce
o
f
a
p
er
s
o
n
at
a
d
o
o
r
an
d
t
o
c
o
llect
d
ata
ab
o
u
t
t
h
is
p
er
s
o
n
.
T
h
e
p
er
s
o
n
'
s
b
eh
av
io
u
r
,
s
u
ch
as
k
n
o
c
k
in
g
,
r
in
g
in
g
t
h
e
d
o
o
r
b
ell,
o
r
s
tan
d
in
g
o
n
th
e
d
o
o
r
way
,
ca
n
th
e
n
b
e
class
if
ied
u
s
in
g
th
is
d
ata
b
y
tr
ain
in
g
a
m
ac
h
in
e
lear
n
i
n
g
m
o
d
el
[
1
2
]
.
−
Am
b
ien
t
s
en
s
o
r
:
r
ad
a
r
,
p
r
ess
u
r
e
s
en
s
o
r
s
,
an
d
tem
p
er
atu
r
e
s
en
s
o
r
s
ar
e
s
o
m
e
o
f
th
e
am
b
ien
t
s
en
s
o
r
s
th
at
ar
e
g
en
er
ally
in
co
r
p
o
r
ate
d
in
to
a
u
s
er
'
s
s
m
ar
t
en
v
ir
o
n
m
en
t
an
d
ar
e
u
s
ed
to
co
llect
in
f
o
r
m
atio
n
o
n
h
o
w
p
eo
p
le
in
ter
ac
t
with
th
eir
s
u
r
r
o
u
n
d
in
g
s
.
W
h
ile
o
b
ject
s
en
s
o
r
s
tr
ac
k
o
b
ject
m
o
v
em
e
n
ts
,
am
b
ie
n
t
s
en
s
o
r
s
r
ec
o
r
d
th
e
ch
an
g
e
in
th
e
en
v
ir
o
n
m
en
t.
G
u
er
r
er
o
-
Ullo
a
et
a
l.
[
1
3
]
Au
t
h
o
r
s
p
r
o
p
o
s
e
a
s
y
s
tem
th
at
u
s
e
s
am
b
ien
t sen
s
o
r
s
to
co
llect
d
ata
o
n
th
e
en
v
ir
o
n
m
en
tal
co
n
d
itio
n
s
o
f
p
lan
ts
,
s
u
ch
as
tem
p
er
atu
r
e,
h
u
m
i
d
ity
,
an
d
lig
h
t.
T
h
is
d
ata
is
th
en
u
s
ed
to
co
n
tr
o
l
th
e
elem
en
ts
o
f
th
e
p
la
n
t
ca
r
e
s
y
s
tem
,
s
u
ch
as
wate
r
in
g
,
f
er
tili
za
tio
n
,
an
d
lig
h
tin
g
.
Am
b
ien
t
s
en
s
o
r
s
h
av
e
b
ee
n
u
tili
ze
d
in
s
ev
er
al
wo
r
k
s
o
f
liter
atu
r
e
to
id
en
tify
h
a
n
d
g
estu
r
es
an
d
d
aily
ac
tiv
ities
[
1
4
]
,
[
1
5
]
.
T
h
e
m
ajo
r
ity
o
f
th
e
w
o
r
k
was
ev
a
lu
ated
in
a
s
m
ar
t
h
o
m
e
s
ettin
g
.
Ad
d
itio
n
ally
,
th
e
ad
o
p
tio
n
o
f
ap
p
r
o
p
r
iate
e
n
v
ir
o
n
m
en
tal
s
en
s
o
r
s
m
u
s
t
b
e
ca
r
ef
u
lly
p
lan
n
e
d
d
ep
en
d
in
g
o
n
th
e
ac
tiv
ities
b
ec
au
s
e
th
ey
ar
e
h
ig
h
l
y
s
en
s
itiv
e
to
ch
a
n
g
es in
th
e
e
n
v
ir
o
n
m
en
t
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
36
,
No
.
1
,
Octo
b
er
20
24
:
302
-
3
1
7
304
−
Hy
b
r
id
s
en
s
o
r
:
f
o
r
th
e
p
u
r
p
o
s
e
o
f
im
p
r
o
v
in
g
HAR
m
o
d
el
r
o
b
u
s
tn
ess
an
d
ac
cu
r
ac
y
[
1
6
]
,
r
esear
ch
er
s
h
av
e
in
cr
ea
s
in
g
ly
u
tili
ze
d
h
y
b
r
i
d
s
en
s
o
r
s
[
1
7
]
,
wh
ich
s
ig
n
if
ies
H
AR
ap
p
licatio
n
s
th
at
co
m
b
in
e
v
ar
io
u
s
ty
p
es
o
f
s
en
s
o
r
s
,
lik
e
co
m
b
in
in
g
am
b
ien
t
an
d
o
b
ject
s
en
s
o
r
s
th
at
ca
n
r
ec
o
r
d
b
o
th
th
e
o
b
ject
m
o
v
em
en
ts
an
d
en
v
ir
o
n
m
en
t
s
tate.
T
h
ese
r
ec
e
n
t
wo
r
k
s
s
u
g
g
est
th
at
th
e
ad
o
p
tio
n
o
f
h
y
b
r
id
s
en
s
o
r
s
,
wh
ic
h
cr
ea
te
d
iv
er
s
e
d
atasets
f
r
o
m
n
u
m
er
o
u
s
s
o
u
r
ce
s
,
ca
n
s
ig
n
i
f
ican
tly
ad
v
an
ce
HAR
r
esear
ch
ef
f
o
r
ts
an
d
e
n
co
u
r
ag
e
ap
p
licatio
n
s
in
s
y
s
tem
s
lik
e
co
m
m
er
cial
s
m
ar
t h
o
m
es [
1
8
]
.
I
t
is
ev
id
en
t
to
r
ec
o
r
d
th
at
v
is
io
n
s
en
s
o
r
s
h
av
e
b
ee
n
wid
el
y
u
s
ed
im
m
ed
iately
[
19
]
.
Alth
o
u
g
h
p
r
iv
ac
y
co
n
ce
r
n
s
h
av
e
b
ee
n
ad
d
r
ess
ed
p
r
o
g
r
ess
iv
ely
,
r
esid
en
ts
ar
e
m
o
r
e
lik
ely
to
e
m
b
r
ac
e
am
b
ien
t
s
en
s
o
r
s
.
As
a
r
esu
lt,
th
e
n
o
n
-
v
is
io
n
en
v
ir
o
n
m
en
tal
s
en
s
o
r
s
h
av
e
em
er
g
ed
as
a
r
esear
ch
f
o
cu
s
[
2
0
]
an
d
th
ey
ar
e
m
o
r
e
co
m
m
o
n
l
y
ac
ce
p
ted
s
in
ce
th
ey
ar
e
r
eg
ar
d
e
d
as
less
o
b
tr
u
s
iv
e.
Sen
s
o
r
s
ar
e
th
e
b
ac
k
b
o
n
e
o
f
s
m
ar
t
h
o
m
e
tech
n
o
lo
g
y
,
p
r
o
v
i
d
in
g
v
ital
in
f
o
r
m
atio
n
an
d
ac
tin
g
as
th
e
e
y
es
an
d
ea
r
s
o
f
in
tellig
e
n
t
s
y
s
tem
s
d
esig
n
ed
to
id
en
tify
h
u
m
an
b
eh
a
v
io
r
.
T
h
e
two
m
ain
ap
p
r
o
ac
h
es
to
ac
tiv
ity
r
ec
o
g
n
itio
n
ar
e
p
o
wer
e
d
b
y
th
is
g
ath
er
ed
d
ata:
th
e
k
n
o
wled
g
e
-
d
r
iv
en
a
p
p
r
o
a
ch
,
wh
ich
u
s
es
h
u
m
an
e
x
p
er
t
is
e
an
d
p
r
e
-
estab
lis
h
ed
r
u
les
to
in
ter
p
r
et
s
en
s
o
r
d
ata,
an
d
t
h
e
d
ata
-
d
r
iv
en
a
p
p
r
o
ac
h
,
wh
ich
u
s
es a
lg
o
r
ith
m
s
t
o
d
etec
t p
atter
n
s
am
o
n
g
m
ass
iv
e
am
o
u
n
ts
o
f
d
ata.
Alth
o
u
g
h
s
ev
er
al
s
u
r
v
ey
s
h
av
e
b
ee
n
co
n
d
u
cted
u
tili
z
in
g
d
ata
-
d
r
iv
en
o
r
k
n
o
wled
g
e
-
d
r
i
v
en
m
eth
o
d
o
l
o
g
y
,
n
o
s
p
ec
if
ic
s
u
r
v
ey
h
as
b
ee
n
c
o
n
d
u
cted
th
at
o
f
f
er
s
a
clea
r
co
m
p
ar
is
o
n
o
f
th
e
s
e
two
ap
p
r
o
ac
h
es.
W
e
b
eliev
e
th
is
to
b
e
th
e
f
ir
s
t
ar
ticle
d
is
cu
s
s
in
g
th
e
m
o
s
t
r
ec
en
t
co
m
p
ar
is
o
n
b
etwe
en
k
n
o
wled
g
e
-
an
d
d
ata
-
d
r
iv
en
m
eth
o
d
s
f
o
r
id
e
n
tify
in
g
h
u
m
a
n
ac
tiv
ity
in
s
m
ar
t
h
o
m
es.
W
e
h
o
p
e
th
at
th
is
wo
r
k
will
h
elp
p
r
o
v
id
e
an
o
v
er
v
iew
o
f
th
e
last
s
tu
d
ies an
d
will su
g
g
est p
o
ten
tial d
ir
ec
ti
o
n
s
f
o
r
f
u
tu
r
e
r
esear
ch
.
T
h
i
s
is
h
o
w
t
h
e
r
e
s
t
o
f
t
h
e
p
ap
e
r
i
s
s
t
r
u
ct
u
r
e
d
.
I
n
s
e
c
t
i
o
n
2
,
w
e
d
e
s
c
r
i
b
e
t
h
e
p
o
t
e
n
t
ia
l
o
f
th
e
I
o
T
f
o
r
H
A
R
.
W
e
d
i
s
c
u
s
s
t
h
e
a
d
o
p
t
e
d
m
e
t
h
o
d
o
l
o
g
y
f
o
r
t
h
i
s
r
e
v
i
e
w
a
n
d
t
h
e
n
w
e
f
o
c
u
s
o
n
t
h
e
c
o
m
p
a
r
i
s
o
n
b
e
t
w
e
e
n
t
h
e
s
t
r
e
n
g
t
h
s
a
n
d
we
a
k
n
e
s
s
e
s
o
f
d
a
t
a
-
d
r
i
v
e
n
a
n
d
k
n
o
w
l
e
d
g
e
-
d
r
i
v
e
n
H
A
R
m
et
h
o
d
s
i
n
s
ec
t
i
o
n
s
3
a
n
d
4
r
e
s
p
e
c
t
i
v
e
l
y
.
A
d
d
i
t
i
o
n
a
l
l
y
,
w
e
p
r
e
s
e
n
t
m
a
n
y
c
h
a
l
l
e
n
g
es
t
o
i
d
e
n
t
i
f
y
i
n
g
h
u
m
a
n
a
c
t
i
v
it
y
i
n
s
m
a
r
t
h
o
m
es
.
A
d
is
c
u
s
s
i
o
n
a
n
d
i
n
s
i
g
h
ts
o
n
t
h
e
r
e
v
i
e
w'
s
f
i
n
d
i
n
g
s
a
r
e
p
r
e
s
e
n
t
e
d
i
n
s
e
c
t
i
o
n
5
.
Fin
a
l
l
y
,
s
e
ct
i
o
n
6
b
r
i
n
g
s
t
h
is
p
a
p
e
r
t
o
a
c
l
o
s
e
.
2.
T
H
E
I
N
T
E
RN
E
T
O
F
T
H
I
N
G
S F
O
R
H
AR
T
h
e
I
o
T
,
o
f
ten
allu
d
ed
to
as
I
o
T
,
en
c
o
m
p
ass
es
a
n
etwo
r
k
o
f
tan
g
ib
le,
r
ea
l
-
wo
r
ld
o
b
jects
in
ter
co
n
n
ec
ted
th
r
o
u
g
h
th
e
I
n
ter
n
et.
T
h
ese
o
b
jects
co
m
m
u
n
icate
with
ea
ch
o
th
er
b
y
ex
c
h
an
g
i
n
g
d
ata
co
llected
f
r
o
m
s
en
s
o
r
s
an
d
u
s
in
g
s
u
itab
le
co
m
m
u
n
icatio
n
p
r
o
to
co
ls
.
T
h
is
em
er
g
i
n
g
tech
n
o
lo
g
y
is
g
r
a
d
u
ally
b
ec
o
m
in
g
a
p
ar
t
o
f
o
u
r
d
aily
life
[
21
].
T
h
e
tech
n
o
lo
g
y
u
n
d
e
r
ly
in
g
I
o
T
n
etwo
r
k
in
g
is
elu
ci
d
ated
in
[
22
]
as
an
im
p
r
o
v
em
e
n
t
o
f
co
m
m
u
n
icati
o
n
p
r
o
to
co
ls
f
o
r
in
te
r
co
n
n
ec
ted
in
tellig
en
t
o
b
jects.
T
h
is
en
h
an
ce
m
en
t
in
v
o
lv
es
th
e
in
teg
r
atio
n
o
f
d
iv
er
s
e
s
en
s
o
r
s
an
d
ac
t
o
r
n
etwo
r
k
s
to
ac
h
iev
e
id
e
n
tific
atio
n
a
n
d
tr
ac
k
in
g
f
u
n
ctio
n
alities
.
Fu
r
th
er
m
o
r
e
,
Su
ltan
an
d
Ah
m
ed
[
23
]
d
ef
in
es
it
as
a
co
n
f
ig
u
r
atio
n
o
f
s
en
s
o
r
s
an
d
ac
tu
ato
r
s
em
b
ed
d
ed
with
in
p
h
y
s
ical
o
b
jects.
T
h
ese
co
m
p
o
n
en
ts
h
av
e
th
e
a
b
ilit
y
to
s
en
d
d
ata
ac
r
o
s
s
wir
ed
n
etwo
r
k
s
as we
ll a
s
wir
eles
s
ly
.
R
eg
ar
d
in
g
th
e
ac
q
u
is
itio
n
o
f
d
ata
f
o
r
r
em
o
te
m
o
n
ito
r
in
g
an
d
ac
tiv
ity
r
ec
o
g
n
itio
n
,
th
e
p
iv
o
tal
co
m
p
o
n
en
ts
in
cr
ea
tin
g
a
s
m
ar
t
h
o
m
e
ar
e
I
o
T
s
en
s
o
r
s
an
d
th
e
co
r
r
esp
o
n
d
i
n
g
s
en
s
in
g
tech
n
o
lo
g
ies.
T
h
e
in
teg
r
atio
n
o
f
th
ese
s
en
s
o
r
s
th
r
o
u
g
h
clo
u
d
-
b
ased
d
atab
ases
an
d
n
etwo
r
k
in
g
tec
h
n
o
l
o
g
ies
p
lay
s
a
cr
u
cial
r
o
le,
b
u
t
also
it
is
a
d
if
f
icu
lt
tech
n
ical
ch
allen
g
e
b
ec
au
s
e
it
aim
s
f
o
r
h
ig
h
p
r
ec
is
io
n
,
r
o
b
u
s
tn
e
s
s
,
an
d
lo
w
en
er
g
y
co
n
s
u
m
p
tio
n
.
Ho
wev
er
,
th
er
e
ar
e
m
an
y
p
r
o
m
is
in
g
tech
n
iq
u
es
to
m
ee
t
th
is
ch
allen
g
e
lik
e
th
e
ad
ap
tatio
n
o
f
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
,
t
h
e
u
s
e
o
f
a
r
tific
ial
n
eu
r
al
n
etwo
r
k
s
,
an
d
th
e
s
p
ec
ialized
eq
u
ip
m
en
t
[
2
4
]
.
2
.
1
.
I
o
T
la
y
er
-
ba
s
ed
persp
ec
t
iv
e
f
o
r
hu
ma
n a
ct
iv
it
y
re
co
g
nitio
n
Fo
r
th
e
p
u
r
p
o
s
es
o
f
d
ata
co
llectio
n
,
s
h
ar
in
g
,
an
d
an
a
ly
s
is
,
I
o
T
ap
p
licatio
n
s
en
a
b
le
d
ev
ice
co
n
n
ec
tiv
ity
an
d
in
ter
ac
tio
n
th
r
o
u
g
h
th
e
I
n
te
r
n
et.
T
h
e
g
e
n
er
ated
I
o
T
d
ata
ca
n
g
o
th
r
o
u
g
h
a
n
u
m
b
e
r
o
f
lear
n
in
g
p
h
ases
f
o
r
ac
tiv
ity
r
ec
o
g
n
itio
n
[
1
]
u
s
in
g
th
e
in
f
o
r
m
atio
n
o
b
tain
ed
f
r
o
m
d
if
f
er
en
t
I
o
T
s
en
s
o
r
s
,
as
illu
s
tr
ated
in
Fig
u
r
e
2
.
Fig
u
r
e
2
.
I
o
T
lay
e
r
-
b
ased
p
er
s
p
ec
tiv
e
f
o
r
HAR
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:
2
5
0
2
-
4
7
52
Th
e
p
o
ten
tia
l
o
f th
e
in
tern
et
o
f th
in
g
s
fo
r
h
u
ma
n
a
ctivity
r
ec
o
g
n
itio
n
i
n
s
ma
r
t h
o
me
… (
K
h
a
d
ija
E
s
s
a
fi
)
305
T
h
e
r
ec
en
t
liter
atu
r
e
o
n
in
tellig
en
t
s
y
s
tem
s
b
ased
o
n
th
e
r
ec
o
g
n
itio
n
o
f
h
u
m
an
ac
tiv
ity
test
if
ies
to
th
e
r
ap
id
ity
with
wh
ich
th
is
tech
n
o
lo
g
y
e
v
o
lv
es
an
d
its
tr
an
s
f
o
r
m
ativ
e
im
p
ac
t
in
v
ar
io
u
s
ap
p
licatio
n
s
[
2
5
]
.
I
t
o
p
e
n
s
u
p
ex
citin
g
p
r
o
s
p
ec
ts
f
o
r
im
p
r
o
v
i
n
g
o
u
r
q
u
ality
o
f
life
a
n
d
o
u
r
s
af
ety
th
r
o
u
g
h
a
d
ee
p
er
u
n
d
er
s
tan
d
in
g
o
f
h
u
m
an
ac
tiv
ities
.
T
h
e
s
tr
u
ctu
r
e
o
f
t
h
e
HAR
s
y
s
tem
co
n
s
is
ts
o
f
f
o
u
r
I
o
T
-
b
ased
lay
e
r
s
:
2
.
1
.
1
.
Sens
ing
la
y
er
T
h
e
s
en
s
in
g
lay
er
en
a
b
les
th
e
p
r
in
cip
al
s
en
s
in
g
an
d
co
llectin
g
g
o
als;
it
is
u
s
ed
to
id
en
tify
t
h
in
g
s
an
d
co
llect
d
ata
o
n
th
e
en
v
ir
o
n
m
en
t
an
d
its
o
cc
u
p
an
ts
b
y
d
ep
lo
y
in
g
v
a
r
io
u
s
s
en
s
in
g
d
ev
ic
es
u
s
in
g
a
r
an
g
e
o
f
ap
p
r
o
ac
h
es,
in
clu
d
in
g
im
p
lan
t
ed
,
wea
r
ab
le
,
o
n
-
ap
p
lian
ce
,
o
r
en
v
i
r
o
n
m
e
n
tal
s
en
s
o
r
s
,
a
n
d
,
tag
s
.
Fo
r
in
s
tan
ce
,
in
th
e
c
o
n
tex
t
o
f
h
ea
lth
ca
r
e,
t
h
e
s
en
s
in
g
lay
e
r
is
task
ed
with
k
ee
p
i
n
g
t
r
ac
k
o
f
t
h
e
u
s
er
s
'
p
h
y
s
ical,
m
en
tal,
a
n
d
em
o
tio
n
al
well
-
b
ein
g
.
T
h
e
p
r
o
ce
s
s
o
f
m
ea
s
u
r
in
g
ch
ar
a
cter
is
tics
r
elate
d
to
p
eo
p
le
an
d
th
eir
s
o
u
n
d
s
h
as
b
ee
n
m
ad
e
ea
s
ier
in
r
ec
en
t
y
ea
r
s
t
h
an
k
s
to
th
e
p
r
o
g
r
ess
in
s
m
all
an
d
lo
w
-
co
s
t
wea
r
ab
le
s
en
s
o
r
s
.
T
h
ese
in
clu
d
e
in
er
tial
s
en
s
o
r
s
(
s
u
ch
as
g
y
r
o
s
co
p
es,
ac
ce
ler
o
m
eter
s
,
an
d
b
ar
o
m
et
r
ic
p
r
ess
u
r
e
s
en
s
o
r
s
)
as
well
a
s
p
h
y
s
io
lo
g
ical
s
en
s
o
r
s
(
lik
e
s
k
i
n
tem
p
er
atu
r
e
s
en
s
o
r
s
,
s
p
ir
o
m
eter
s
,
an
d
b
lo
o
d
p
r
ess
u
r
e
cu
f
f
s
)
[
2
6
].
2
.
1
.
2
.
Net
wo
r
k
la
y
er
T
h
e
n
etwo
r
k
lay
er
tak
es
o
n
th
e
r
esp
o
n
s
ib
ilit
y
o
f
in
ter
co
n
n
ec
tin
g
all
d
ev
ices
with
in
th
e
s
en
s
o
r
y
lay
er
an
d
e
n
ab
lin
g
I
o
T
in
f
r
astru
ctu
r
es
to
c
o
llect,
s
to
r
e,
tr
an
s
m
it
,
d
is
tr
ib
u
te,
an
d
ag
g
r
eg
ate
c
u
s
to
m
ized
d
ata
f
o
r
ac
tiv
ity
d
etec
tio
n
.
T
h
is
lay
er
ty
p
ically
in
clu
d
es
a
wid
e
v
ar
iety
o
f
id
ea
s
an
d
m
eth
o
d
s
,
in
c
lu
d
in
g
to
p
o
lo
g
ies,
ar
ch
itectu
r
e,
s
ec
u
r
ity
,
p
r
iv
ac
y
,
an
d
tech
n
o
lo
g
ies
f
o
r
c
o
m
m
u
n
icatio
n
an
d
lo
ca
tio
n
.
As
a
r
e
s
u
lt,
it
p
er
m
its
th
e
ef
f
icien
t
an
d
s
ec
u
r
e
co
n
v
ey
a
n
ce
o
f
d
ata
to
th
e
ap
p
r
o
p
r
ia
te
d
ata
p
r
o
ce
s
s
in
g
u
n
its
.
Nu
m
er
o
u
s
s
h
o
r
t
-
r
an
g
e
co
m
m
u
n
icatio
n
p
r
o
to
co
ls
h
av
e
s
ee
n
wid
esp
r
ea
d
ad
o
p
tio
n
,
Z
ig
B
ee
is
an
ex
am
p
le.
2
.
1
.
3
.
Ana
ly
s
is
la
y
er
T
h
e
p
r
o
ce
s
s
in
g
lay
e
r
m
a
n
ag
e
s
v
alu
ab
le
k
n
o
wled
g
e
e
x
tr
ac
t
ed
f
r
o
m
th
e
s
en
s
o
r
d
ata
o
b
tai
n
ed
in
th
e
in
itial
lay
er
.
I
t
s
to
r
es
an
d
s
u
b
s
eq
u
en
tly
an
aly
s
es
th
e
s
ig
n
al
d
ata
r
ec
eiv
ed
f
r
o
m
th
e
n
etwo
r
k
lay
er
.
I
t
is
r
esp
o
n
s
ib
le
f
o
r
th
e
ag
g
r
e
g
ati
o
n
,
p
r
o
ce
s
s
in
g
,
a
n
d
a
n
aly
s
is
o
f
s
en
s
ed
in
f
o
r
m
atio
n
,
as
wel
l
as
th
e
s
u
b
s
eq
u
e
n
t
tr
an
s
f
o
r
m
atio
n
o
f
th
at
i
n
f
o
r
m
a
tio
n
in
to
m
ea
n
in
g
f
u
l k
n
o
wled
g
e.
Fo
u
r
k
e
y
d
ata
p
r
o
ce
s
s
in
g
s
t
ag
es
ar
e
in
v
o
lv
e
d
in
ac
tiv
ity
r
ec
o
g
n
itio
n
:
d
ata
p
r
e
-
p
r
o
ce
s
s
in
g
,
d
ata
s
eg
m
en
tatio
n
,
f
ea
tu
r
e
ex
tr
ac
ti
o
n
,
an
d
class
if
icatio
n
/clu
s
ter
in
g
:
−
Data
p
r
ep
r
o
ce
s
s
in
g
:
a
n
y
k
i
n
d
o
f
i
n
f
o
r
m
atio
n
g
at
h
er
ed
f
r
o
m
I
o
T
s
en
s
in
g
d
e
v
ices
m
u
s
t
g
o
th
r
o
u
g
h
p
r
ep
r
o
ce
s
s
in
g
to
f
ac
ilit
ate
th
e
lear
n
in
g
o
f
p
r
o
ce
s
s
in
g
alg
o
r
ith
m
s
f
r
o
m
r
elev
an
t
d
at
a,
en
ab
lin
g
th
e
r
ef
in
em
en
t
o
f
a
u
n
iv
er
s
al
m
o
d
el,
esp
ec
ially
in
th
e
co
n
tex
t
o
f
r
ec
o
g
n
izin
g
ac
tiv
ities
with
in
a
s
m
ar
t
h
o
m
e.
T
h
e
v
ar
io
u
s
I
o
T
s
en
s
in
g
d
a
tasets
th
at
h
av
e
b
ee
n
g
ath
e
r
ed
co
n
tain
n
o
is
y
d
ata
[
2
7
]
an
d
th
ey
ar
e
u
n
s
tr
u
ctu
r
ed
as
a
r
esu
lt
o
f
d
is
r
u
p
tio
n
s
a
n
d
v
ar
y
in
g
h
u
m
an
a
ctio
n
s
[
2
8
]
.
T
h
er
ef
o
r
e,
th
e
m
a
jo
r
task
s
o
f
th
e
p
r
ep
r
o
ce
s
s
in
g
s
tep
p
r
io
r
to
t
h
e
s
tar
t
o
f
f
ea
tu
r
e
e
x
tr
ac
tio
n
ar
e
th
e
elim
in
atio
n
o
f
n
o
is
e
[
2
8
]
,
co
n
v
er
s
io
n
a
n
d
n
o
r
m
aliza
tio
n
o
f
d
ata
[
2
9
]
,
la
b
ellin
g
[
3
0
]
,
a
n
d
[
3
1
]
f
o
r
tr
an
s
f
o
r
m
in
g
t
h
e
d
ataset
in
to
a
n
a
p
p
r
o
p
r
iate
f
o
r
m
.
So
b
r
ief
ly
d
ata
p
r
ep
r
o
ce
s
s
in
g
is
th
e
p
r
o
ce
s
s
o
f
o
r
g
an
izin
g
a
n
d
clea
n
in
g
r
aw
d
ata
s
o
th
at
it
is
f
it
f
o
r
u
s
e
in
s
u
b
s
eq
u
en
t p
r
o
ce
s
s
es in
im
p
r
o
v
in
g
ca
teg
o
r
izatio
n
ac
c
u
r
ac
y
.
−
Data
s
eg
m
en
tatio
n
:
is
a
co
m
m
o
n
a
p
p
r
o
ac
h
th
at
r
ef
er
s
to
o
n
e
o
f
th
e
cr
u
cial
asp
ec
ts
o
f
d
a
ta
p
r
o
ce
s
s
in
g
.
I
n
ac
tu
ality
,
n
o
p
r
o
ce
d
u
r
e
ca
n
d
ea
l
with
th
e
o
b
tain
ed
d
ata
in
a
s
in
g
le
s
tep
.
Data
m
u
s
t
th
er
e
f
o
r
e
b
e
d
iv
id
e
d
in
to
a
co
llectio
n
o
f
s
eg
m
en
ts
,
k
n
o
wn
as
win
d
o
ws,
d
u
r
in
g
th
e
s
eg
m
en
tatio
n
p
r
o
ce
s
s
.
Fo
llo
win
g
th
at,
ea
ch
s
eg
m
en
t
ca
n
b
e
e
x
am
in
ed
in
d
ep
en
d
en
tly
.
T
h
er
e
ar
e
two
s
eg
m
en
tatio
n
m
eth
o
d
s
d
escr
ib
ed
in
th
e
liter
atu
r
e:
s
tatic
an
d
d
y
n
am
ic
[
3
2
]
,
[
3
3
]
.
Static seg
m
en
tatio
n
,
o
n
th
e
o
n
e
h
an
d
,
d
en
o
tes a
p
r
ed
eter
m
in
ed
s
eg
m
en
t size
th
at
ca
n
n
o
t
b
e
alter
ed
.
Dif
f
er
en
t
s
eg
m
en
t
s
izes
will
b
e
em
p
lo
y
ed
t
o
ev
alu
ate
t
h
e
ap
p
licatio
n
.
T
h
e
b
est
-
p
er
f
o
r
m
in
g
s
ize
is
th
en
s
elec
ted
.
I
n
co
n
tr
ast,
d
y
n
a
m
ic
s
eg
m
en
tatio
n
en
ab
les
th
e
d
iv
is
io
n
o
f
th
e
d
ata
in
to
a
co
llectio
n
o
f
s
eg
m
e
n
ts
o
f
v
a
r
y
in
g
s
izes.
Du
r
in
g
th
e
a
p
p
licatio
n
p
r
o
ce
s
s
,
ea
ch
s
ize
is
d
y
n
am
ically
s
elec
ted
.
−
Featu
r
e
ex
tr
ac
tio
n
:
s
in
ce
s
en
s
o
r
d
ata
is
d
er
iv
ed
f
r
o
m
s
en
s
o
r
ev
en
ts
,
it
ca
n
n
o
t
b
e
p
r
o
ce
s
s
ed
d
ir
ec
tly
u
n
til
it
is
in
clu
d
ed
in
th
e
f
ea
tu
r
e
v
ec
t
o
r
in
s
o
m
e
way
.
T
h
e
f
ea
t
u
r
es
th
at
ca
n
b
e
u
s
ed
to
ex
p
r
ess
ac
tiv
ity
in
s
m
ar
t
h
o
m
es a
r
e
n
u
m
er
o
u
s
,
an
d
t
h
ese
q
u
alities
m
ay
ap
p
ea
r
in
f
ea
tu
r
es th
at
p
o
r
tr
ay
co
n
tin
u
o
u
s
o
r
d
is
cr
ete
v
alu
es,
f
ea
tu
r
es
th
at
d
ep
ict
tem
p
o
r
al
s
eq
u
en
ce
s
o
f
o
cc
u
r
r
e
n
ce
s
,
o
r
in
r
elatio
n
to
th
e
co
n
ten
t
o
f
ac
tiv
ities
[
3
4
]
.
"Fea
tu
r
e
ex
tr
ac
tio
n
"
is
a
cr
u
cial
s
tep
in
th
e
ac
tiv
ity
r
ec
o
g
n
iti
o
n
p
r
o
ce
s
s
b
ec
au
s
e
if
th
e
f
ea
tu
r
es a
r
e
r
eliab
le,
an
y
class
if
icatio
n
tech
n
iq
u
e
m
ay
b
e
c
h
o
s
en
with
ac
c
u
r
ac
y
.
T
h
e
al
g
o
r
ith
m
s
m
u
s
t
id
en
tify
a
r
an
g
e
o
f
ac
tiv
ities
at
th
e
m
o
m
en
t
th
ey
tak
e
p
lace
as
well
as
th
e
u
s
er
's
s
tate
d
u
r
in
g
th
at
tim
e
b
y
s
elec
tin
g
all
o
f
th
e
s
en
s
o
r
s
th
at
m
ak
e
u
p
t
h
e
cir
cu
m
s
tan
ce
.
−
Activ
ity
class
if
icatio
n
:
e
v
en
t
u
ally
class
if
ies
th
ese
f
ea
tu
r
e
s
in
to
v
a
r
io
u
s
b
asic
ac
tiv
ity
p
atter
n
s
.
I
t
is
p
o
s
s
ib
le
to
in
f
er
h
ig
h
-
lev
el
ev
er
y
d
a
y
ac
tiv
ities
lik
e
co
o
k
in
g
,
ea
tin
g
,
o
r
d
r
ess
in
g
wh
en
u
tili
ze
d
in
co
m
b
in
atio
n
with
u
s
er
co
n
tex
t
d
ata
(
s
u
ch
as
an
o
b
ject'
s
s
tate
o
r
th
e
u
s
er
'
s
lo
ca
tio
n
)
.
T
h
e
two
p
r
im
ar
y
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
36
,
No
.
1
,
Octo
b
er
20
24
:
302
-
3
1
7
306
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
s
o
f
class
if
icatio
n
an
d
cl
u
s
ter
in
g
ar
e
r
elate
d
r
esp
ec
tiv
ely
to
s
u
p
er
v
is
ed
a
n
d
u
n
s
u
p
er
v
is
ed
al
g
o
r
ith
m
s
.
A
r
ev
iew
o
f
v
ar
i
o
u
s
p
r
ep
r
o
ce
s
s
in
g
an
d
f
ea
tu
r
e
ex
tr
ac
tio
n
tec
h
n
iq
u
es
f
o
r
I
o
T
d
ata
f
r
o
m
s
m
ar
t
h
o
m
es
ca
n
b
e
f
o
u
n
d
in
[
35
]
.
A
n
u
m
b
er
o
f
class
if
icatio
n
alg
o
r
ith
m
s
th
at
ar
e
u
tili
ze
d
in
s
m
ar
t
h
o
m
es
to
id
en
tify
h
u
m
an
ac
tiv
ity
u
s
in
g
th
e
in
f
o
r
m
atio
n
g
ath
er
ed
b
y
th
e
s
en
s
o
r
s
h
av
e
also
b
ee
n
e
x
am
in
ed
.
T
im
e
lim
its
,
d
at
a
im
b
alan
ce
s
an
d
n
o
is
es,
an
d
co
m
p
u
tin
g
co
m
p
le
x
ity
.
ca
n
all
h
av
e
an
im
p
ac
t o
n
t
h
e
ab
ilit
y
o
f
s
en
s
o
r
s
to
id
e
n
tify
h
u
m
an
ac
tiv
ity
f
r
o
m
s
en
s
o
r
d
ata.
Acc
o
r
d
in
g
t
o
th
e
au
th
o
r
s
,
tim
e
-
b
ased
lab
elin
g
o
f
th
e
d
a
ta
g
ath
er
ed
b
y
I
o
T
s
en
s
o
r
s
f
o
r
th
e
p
u
r
p
o
s
e
o
f
id
e
n
tify
in
g
h
u
m
an
ac
tiv
ity
ca
n
h
elp
to
in
cr
ea
s
e
ac
cu
r
ac
y
an
d
l
o
wer
co
m
p
u
tatio
n
al
co
m
p
lex
ity
.
2
.
1
.
4
.
Appl
ica
t
io
n la
y
er
T
h
is
lay
er
g
iv
es
u
s
er
s
d
ir
ec
t
in
tellig
en
t
ac
ce
s
s
to
a
v
ar
iety
o
f
s
o
p
h
is
ticated
s
er
v
ices
th
a
t
im
p
r
o
v
e
th
eir
ev
er
y
d
ay
life
a
n
d
h
e
alth
m
an
ag
e
m
en
t.
W
ith
its
r
em
o
te
d
iag
n
o
s
is
f
ea
tu
r
es,
m
ed
ic
al
p
r
o
f
ess
io
n
als
ca
n
ev
alu
ate
p
atien
ts
f
r
o
m
a
d
is
tan
ce
.
Featu
r
es
f
o
r
b
eh
a
v
io
r
r
ec
o
g
n
itio
n
g
iv
e
th
e
s
y
s
tem
th
e
ab
ilit
y
to
t
r
ac
k
a
n
d
co
m
p
r
eh
e
n
d
u
s
er
r
o
u
tin
es
an
d
b
eh
a
v
io
r
s
.
I
t
p
r
o
v
id
es
s
u
r
v
e
illan
ce
o
f
e
v
er
y
d
a
y
ac
tiv
ities
f
o
r
s
en
io
r
citizen
s
,
g
u
ar
an
teein
g
th
eir
s
af
ety
an
d
well
-
b
ein
g
.
T
o
s
u
p
p
o
r
t
o
v
er
all
h
ea
lth
,
it
also
in
teg
r
ates
s
m
ar
t
b
io
lo
g
ical
s
en
s
in
g
,
s
m
ar
t
ass
is
tan
ce
,
an
d
s
elf
-
m
an
a
g
em
en
t
to
o
ls
,
m
e
asu
r
es
em
er
g
en
c
y
alar
m
s
,
an
d
m
o
n
ito
r
s
c
h
r
o
n
i
c
d
is
ea
s
es.
3.
M
E
T
H
O
D
3
.
1
.
Select
io
n pro
ce
s
s
T
h
e
s
co
p
in
g
r
e
v
iew
m
eth
o
d
'
s
th
r
ee
b
asic
s
tep
s
wer
e
u
s
ed
t
o
p
ick
a
lar
g
e
n
u
m
b
er
o
f
r
elev
an
t
p
ap
e
r
s
f
o
r
th
is
in
v
esti
g
atio
n
.
T
h
e
f
ir
s
t
s
tep
is
to
id
en
tify
k
ey
wo
r
d
s
an
d
s
ea
r
ch
f
o
r
r
elev
an
t
to
p
ics
u
s
in
g
ex
is
tin
g
d
atab
ases
.
W
e
wer
e
ab
le
to
co
m
p
ile
th
e
liter
atu
r
e
f
o
r
t
h
is
wo
r
k
u
s
in
g
d
atab
ases
s
u
ch
as Go
o
g
le
Sch
o
lar
,
I
E
E
E
an
d
MD
PI
b
y
em
p
lo
y
in
g
a
s
tr
ateg
y
b
ased
o
n
a
s
et
o
f
k
e
y
wo
r
d
s
.
T
h
e
s
ea
r
ch
s
tr
in
g
we
u
s
ed
f
o
r
th
is
p
u
r
p
o
s
e
was:
"h
u
m
an
ac
tiv
ity
r
ec
o
g
n
itio
n
"
an
d
(
"
d
ata
-
d
r
iv
e
n
"
o
r
"d
ata
-
b
ased
"
)
a
n
d
(
"k
n
o
wled
g
e
-
d
r
iv
e
n
"
o
r
"k
n
o
wled
g
e
-
b
ased
"
)
an
d
"sm
ar
t
h
o
m
e,
"
B
ec
au
s
e
o
f
th
e
cu
r
r
en
t
s
tu
d
y
en
d
ea
v
o
r
,
7
9
3
p
a
p
er
s
wer
e
s
u
cc
ess
f
u
lly
co
llected
d
u
r
in
g
th
e
f
ir
s
t p
h
ase
o
f
th
e
s
y
s
tem
atic
r
ev
iew
ap
p
r
o
ac
h
.
3
.
2
.
Scre
ening
pro
ce
s
s
T
h
er
e
ar
e
7
9
3
p
ap
er
s
in
th
e
in
itial
s
cr
ee
n
in
g
r
o
u
n
d
.
T
h
ese
p
u
b
licatio
n
s
wer
e
ev
alu
ated
in
th
e
s
ec
o
n
d
s
tep
u
s
in
g
in
cl
u
s
io
n
a
n
d
e
x
cl
u
s
io
n
cr
iter
ia
th
at
we
h
ad
estab
lis
h
ed
.
T
h
e
p
r
im
ar
y
in
clu
s
io
n
cr
iter
i
o
n
,
wh
ich
r
esu
lted
in
th
e
ex
clu
s
io
n
o
f
3
6
7
d
ata,
was
th
e
s
tu
d
y
'
s
f
iv
e
-
y
ea
r
p
e
r
io
d
f
r
o
m
2
0
2
0
to
2
0
2
4
.
Sin
ce
p
ee
r
-
r
ev
iewe
d
jo
u
r
n
al
p
ap
er
s
p
r
o
v
i
d
e
th
e
m
o
s
t
u
s
ef
u
l
in
f
o
r
m
atio
n
,
th
ey
s
atis
f
y
th
e
s
ec
o
n
d
co
n
d
itio
n
.
T
h
e
an
aly
s
is
d
id
n
o
t
in
clu
d
e
d
is
s
er
tatio
n
s
,
b
o
o
k
c
h
ap
ter
s
,
m
ee
tin
g
a
b
s
tr
ac
ts
,
co
n
f
er
en
ce
p
r
o
ce
e
d
in
g
s
,
o
r
b
o
o
k
ch
a
p
ter
s
.
Mo
r
eo
v
er
,
th
e
r
e
v
iew
co
n
tai
n
ed
o
n
ly
E
n
g
lis
h
-
lan
g
u
ag
e
p
ap
er
s
with
f
u
ll
-
tex
t
ac
ce
s
s
ib
i
lity
.
B
ased
o
n
th
e
s
p
ec
if
ic
cr
iter
ia
in
d
icate
d
in
T
ab
le
1
,
a
to
tal
o
f
2
6
9
p
u
b
lic
atio
n
s
wer
e
ex
clu
d
ed
.
So
,
f
o
r
th
e
elig
ib
ilit
y
lev
el,
th
e
th
ir
d
lev
el
,
a
to
tal
o
f
97
ar
t
icles
h
av
e
b
ee
n
p
r
e
p
ar
ed
.
At
t
h
is
s
tag
e,
ev
er
y
p
u
b
licatio
n
w
as
ch
ec
k
ed
t
o
m
ak
e
s
u
r
e
it
s
ati
s
f
ied
th
e
in
clu
s
io
n
r
eq
u
ir
em
e
n
ts
an
d
f
it
th
e
g
o
als
o
f
th
e
cu
r
r
e
n
t
s
tu
d
y
.
As
a
r
esu
lt,
32
p
ap
e
r
s
wer
e
d
is
q
u
alif
ied
b
ec
au
s
e
th
eir
titl
e
s
,
ab
s
tr
ac
ts
,
o
r
o
u
t
-
of
-
f
ield
in
f
o
r
m
atio
n
h
ad
n
o
th
in
g
t
o
d
o
with
th
e
p
u
r
p
o
s
e
o
f
th
e
s
tu
d
y
.
Fin
ally
,
65
item
s
r
e
m
ain
av
ailab
le
f
o
r
r
e
v
iew.
T
ab
le
1
.
T
h
e
s
elec
tio
n
cr
iter
io
n
is
s
ea
r
ch
in
g
C
r
i
t
e
r
i
o
n
Ex
c
l
u
si
o
n
I
n
c
l
u
s
i
o
n
Ti
me
l
i
n
e
Li
t
e
r
a
t
u
r
e
t
y
p
e
La
n
g
u
a
g
e
P
u
b
l
i
c
a
t
i
o
n
st
a
g
e
A
c
c
e
ss
i
b
i
l
i
t
y
P
e
e
r
r
e
v
i
e
w
i
n
g
<
2
0
2
0
N
o
n
-
j
o
u
r
n
a
l
a
r
t
i
c
l
e
N
o
n
–
En
g
l
i
s
h
I
n
p
r
e
ss
N
o
n
–
o
p
e
n
a
c
c
e
ss
No
2
0
2
0
-
2
0
2
4
Jo
u
r
n
a
l
a
r
t
i
c
l
e
En
g
l
i
sh
F
i
n
a
l
O
p
e
n
a
c
c
e
ss
Y
e
s
4.
H
UM
AN
AC
T
I
V
I
T
Y
RE
CO
G
NIT
I
O
N
AP
P
RO
ACH
E
S
4
.
1
.
T
he
cha
lleng
es in r
ec
o
g
nizin
g
hu
m
a
n a
ct
iv
it
y
in s
ma
rt
ho
m
es
I
n
s
m
ar
t
en
v
ir
o
n
m
en
ts
,
ac
c
u
r
ate
ac
tiv
ity
r
ec
o
g
n
itio
n
is
ess
en
tial
to
s
u
p
p
o
r
t
an
d
a
s
s
is
t
u
s
er
s
,
esp
ec
ially
th
e
eld
er
ly
an
d
th
o
s
e
with
co
g
n
itiv
e
d
is
ab
ilit
ies.
I
n
o
r
d
er
to
p
er
f
o
r
m
th
is
m
is
s
io
n
,
Sm
ar
t
h
o
m
es
ar
e
o
u
tf
itted
with
m
o
n
ito
r
in
g
to
o
ls
ca
p
ab
le
o
f
i
d
en
tify
in
g
ev
e
r
y
d
ay
r
o
u
tin
es,
a
ctiv
ities
,
b
eh
av
io
u
r
al
p
atter
n
s
,
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:
2
5
0
2
-
4
7
52
Th
e
p
o
ten
tia
l
o
f th
e
in
tern
et
o
f th
in
g
s
fo
r
h
u
ma
n
a
ctivity
r
ec
o
g
n
itio
n
i
n
s
ma
r
t h
o
me
… (
K
h
a
d
ija
E
s
s
a
fi
)
307
ab
n
o
r
m
al
b
e
h
av
io
u
r
[
36
]
an
d
ev
en
g
iv
in
g
in
d
iv
i
d
u
alize
d
s
er
v
ice.
T
h
ey
ca
n
also
b
e
u
s
ed
to
k
ee
p
an
ey
e
o
n
en
v
ir
o
n
m
en
tal
ch
an
g
es b
y
d
ep
lo
y
in
g
s
en
s
o
r
s
o
n
v
ar
i
o
u
s
item
s
an
d
p
lacin
g
t
h
em
in
v
ar
io
u
s
l
o
ca
tio
n
s
.
I
n
o
r
d
e
r
to
d
etec
t
th
e
Sp
atio
-
tem
p
o
r
al
s
tates
o
f
p
h
y
s
ical
o
r
en
v
ir
o
n
m
en
tal
cir
cu
m
s
tan
ce
s
,
a
s
m
ar
t
h
o
m
e
is
o
u
tf
itted
with
a
n
u
m
b
er
o
f
in
ex
p
en
s
iv
e,
n
o
n
-
in
tr
u
s
i
v
e
am
b
ien
t
s
en
s
o
r
s
.
Fig
u
r
e
3
illu
s
tr
ates
th
e
lay
o
u
t
o
f
a
s
m
ar
t
h
o
m
e
an
d
th
e
p
o
s
itio
n
s
o
f
s
en
s
o
r
s
u
s
ed
f
o
r
co
l
lectin
g
d
ata.
E
ac
h
s
en
s
o
r
,
f
o
r
ex
am
p
le,
p
ass
iv
e
in
f
r
ar
ed
(
PIR)
s
en
s
o
r
s
,
h
u
m
id
i
ty
an
d
tem
p
er
at
u
r
e
s
en
s
o
r
s
,
elec
tr
icity
u
s
ag
e
s
en
s
o
r
s
,
an
d
en
tr
y
way
s
en
s
o
r
s
f
o
r
d
o
o
r
s
,
am
o
n
g
o
th
er
s
,
is
u
s
ed
t
o
tr
ac
k
d
i
f
f
er
en
t
p
h
y
s
ical
ch
ar
ac
ter
is
tics
[
37
]
.
PIR
s
en
s
o
r
s
ar
e
f
r
eq
u
e
n
tly
u
s
ed
to
m
o
n
ito
r
te
n
an
t
m
o
v
em
e
n
t
as
an
in
d
icato
r
o
f
th
e
o
cc
u
p
an
cy
o
f
a
p
ar
ticu
lar
s
p
ac
e
in
th
e
h
o
m
e
.
T
h
ey
tr
ac
k
th
e
in
f
r
ar
ed
lig
h
t
th
at
o
b
jects
in
th
eir
f
ield
o
f
v
ie
w
em
it
an
d
m
ea
s
u
r
e
it.
As
a
r
esu
lt,
th
ey
ca
n
id
en
ti
f
y
a
r
esid
en
t'
s
m
o
v
em
e
n
t
wh
e
th
er
th
e
y
e
n
ter
o
r
ex
it
th
e
s
en
s
o
r
'
s
f
ield
o
f
v
iew.
W
h
ile
th
e
h
u
m
id
ity
,
tem
p
er
at
u
r
e,
a
n
d
elec
tr
icity
u
s
ag
e
s
en
s
o
r
s
ar
e
u
s
ed
to
m
o
n
ito
r
th
e
r
ec
o
r
d
ed
v
alu
es
f
o
r
th
ese
in
d
icato
r
s
,
th
e
d
o
o
r
e
n
tr
an
ce
s
en
s
o
r
s
ar
e
u
tili
ze
d
to
d
eter
m
in
e
i
f
th
e
d
o
o
r
is
o
p
e
n
o
r
clo
s
ed
.
T
h
ese
s
en
s
o
r
s
ar
e
th
e
m
o
s
t
f
r
eq
u
en
t
ly
em
p
lo
y
ed
f
o
r
ac
tiv
ity
d
ail
y
liv
in
g
m
o
n
ito
r
in
g
d
u
e
to
p
r
iv
ac
y
,
af
f
o
r
d
ab
ilit
y
,
an
d
eth
ical
is
s
u
es,
as th
ey
allo
w
p
eo
p
le
to
liv
e
r
eg
u
la
r
liv
es with
o
u
t f
ee
lin
g
c
o
n
s
tr
ain
ed
b
y
tech
n
o
lo
g
y
[
38
].
T
h
e
co
m
p
lex
n
atu
r
e
o
f
h
u
m
a
n
ac
tiv
ity
a
n
d
h
o
w
it
v
ar
ies
f
r
o
m
r
esid
en
t
to
r
esid
en
t
m
ak
es
HAR
in
s
m
ar
t h
o
m
es a
d
if
f
icu
lt su
b
ject
to
s
o
lv
e.
E
ac
h
in
h
ab
itan
t h
as a
u
n
iq
u
e
way
o
f
life
,
r
o
u
tin
e,
o
r
s
et
o
f
s
k
ills
.
T
h
e
en
o
r
m
o
u
s
v
ar
iety
o
f
d
aily
ac
ti
v
ities
,
in
clu
d
in
g
th
e
v
ar
iety
an
d
ad
ap
tab
ilit
y
o
f
th
e
way
u
s
ed
to
ca
r
r
y
th
e
m
o
u
t,
n
ec
ess
itate
a
m
eth
o
d
th
at
is
s
ca
lab
le
an
d
m
u
s
t
b
e
ad
a
p
tiv
e.
T
h
at’
s
wh
y
id
e
n
tify
in
g
h
u
m
a
n
ac
tio
n
s
u
s
in
g
d
ata
f
r
o
m
s
en
s
o
r
s
co
m
p
r
is
es so
m
e
ch
allen
g
es d
escr
ib
ed
:
−
Hete
r
o
g
en
eo
u
s
d
ata:
t
y
p
ically
,
ea
ch
s
o
r
t
o
f
s
en
s
o
r
is
u
ti
lized
to
p
r
o
v
id
e
a
ce
r
tain
ty
p
e
o
f
d
ata
(
i.e
h
u
m
id
ity
,
a
n
d
tem
p
e
r
atu
r
e
)
.
I
n
a
s
m
ar
t
en
v
ir
o
n
m
en
t,
a
v
ar
i
ety
o
f
s
en
s
o
r
s
ar
e
o
f
ten
p
r
o
d
u
ce
d
,
with
ea
ch
o
n
e
s
er
v
in
g
a
s
p
ec
if
ic
p
u
r
p
o
s
e
(
i.e
g
ettin
g
an
o
b
ject'
s
s
tatu
s
,
an
d
id
en
tify
i
n
g
u
s
er
lo
ca
tio
n
)
.
As a
r
esu
lt,
th
e
d
ata
p
r
o
v
id
ed
b
y
th
is
v
ast ar
r
a
y
o
f
s
en
s
o
r
s
is
h
eter
o
g
en
eo
u
s
.
−
Dy
n
am
ic
en
v
ir
o
n
m
en
t:
in
an
o
p
en
en
v
ir
o
n
m
e
n
t,
f
o
r
ex
a
m
p
le
as
s
h
o
wn
in
Fig
u
r
e
3
th
er
e
is
alwa
y
s
th
e
p
o
s
s
ib
ilit
y
o
f
ch
a
n
g
es,
esp
ec
ially
with
n
ew
s
en
s
o
r
s
wh
ic
h
ar
r
iv
e
o
r
wh
ich
d
is
ap
p
ea
r
.
So
,
it'
s
v
er
y
im
p
o
r
tan
t
t
o
ad
a
p
t
to
t
h
is
d
y
n
am
icity
to
av
o
i
d
h
a
v
in
g
a
s
o
lu
tio
n
th
at
o
n
ly
ap
p
lies
to
o
n
e
ty
p
e
o
f
ar
ch
itectu
r
e
o
r
en
v
ir
o
n
m
e
n
t.
−
I
m
p
er
f
ec
t
d
ata:
d
u
e
to
h
a
r
d
w
ar
e
lim
itatio
n
s
o
n
s
en
s
o
r
eq
u
i
p
m
en
t,
g
iv
e
n
d
ata
is
alwa
y
s
s
u
b
ject
to
s
o
m
e
d
eg
r
ee
o
f
er
r
o
r
.
A
d
d
itio
n
ally
,
s
en
s
o
r
m
alf
u
n
ctio
n
s
o
r
f
ailu
r
es
f
r
eq
u
e
n
tly
r
esu
lt
in
lo
wer
-
q
u
ality
s
en
s
o
r
d
ata.
As
a
r
esu
lt,
f
ix
in
g
s
en
s
o
r
wea
k
n
ess
es
m
ak
es
it
p
o
s
s
i
b
le
to
d
ec
r
ea
s
e
in
f
o
r
m
atio
n
m
is
in
ter
p
r
etatio
n
.
On
e
o
f
th
e
p
r
im
ar
y
r
esear
ch
q
u
esti
o
n
s
in
s
ce
n
ar
io
id
en
tific
atio
n
is
h
o
w
to
h
an
d
le
u
n
ce
r
tain
s
en
s
o
r
d
ata.
Un
ce
r
tain
ty
m
etr
ics
f
o
r
d
esc
r
ib
in
g
s
en
s
o
r
d
ata,
s
u
ch
as
in
co
m
p
leten
ess
,
co
r
r
ec
tn
ess
,
tim
elin
ess
,
an
d
d
ep
en
d
a
b
ilit
y
,
ar
e
in
tr
o
d
u
ce
d
b
y
s
p
ec
if
icatio
n
-
b
ased
tech
n
iq
u
es [
3
9
]
.
Fig
u
r
e
3
.
A
s
m
ar
t
h
o
m
e'
s
f
lo
o
r
p
lan
an
d
s
en
s
o
r
in
s
tallatio
n
l
o
ca
tio
n
s
em
p
lo
y
e
d
f
o
r
ac
tiv
ity
r
ec
o
g
n
itio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
36
,
No
.
1
,
Octo
b
er
20
24
:
302
-
3
1
7
308
−
Simu
ltan
eo
u
s
ac
tiv
ities
:
a
s
in
g
le
u
s
er
ca
n
n
atu
r
ally
en
g
ag
e
in
m
u
ltip
le
ac
tiv
ities
s
im
u
l
tan
eo
u
s
ly
[
4
0
]
.
Peo
p
le
ca
n
lis
ten
to
m
u
s
ic
wh
ile
d
o
in
g
o
th
e
r
th
in
g
s
,
s
u
c
h
as
s
h
o
p
p
in
g
o
r
r
u
n
n
in
g
.
I
t
is
n
o
t
r
eq
u
ir
ed
t
o
id
en
tify
wh
ich
ac
tio
n
b
eg
a
n
f
ir
s
t
in
th
is
in
s
tan
ce
b
ec
au
s
e
th
er
e
ar
e
co
n
c
u
r
r
en
t
ac
tiv
ities
wh
er
e
o
n
e
ac
tiv
ity
,
lik
e
r
u
n
n
in
g
,
b
e
g
in
s
wh
ile
th
e
o
th
er
h
as
alr
ea
d
y
b
eg
u
n
(
e.
g
.
,
lis
ten
in
g
to
m
u
s
ic)
.
I
t
r
e
q
u
ir
es
a
s
p
ec
ialized
ap
p
r
o
ac
h
to
id
e
n
tif
y
th
ese
n
o
n
-
s
eq
u
en
tial b
e
h
av
i
o
u
r
s
.
−
I
n
ter
leav
ed
ac
tiv
ities
:
i
n
th
e
r
ea
l
wo
r
ld
,
o
n
e
ac
tiv
ity
m
ay
b
e
in
ter
r
u
p
ted
b
y
a
n
o
th
er
[
4
1
]
.
Fo
r
in
s
tan
ce
,
an
em
p
lo
y
ee
is
wo
r
k
i
n
g
o
n
an
a
d
m
in
is
tr
ativ
e
f
ile
as
a
cu
r
r
en
t
a
ctiv
ity
,
an
d
th
e
n
h
e
r
ec
eiv
ed
a
p
h
o
n
e
ca
ll.
I
n
th
is
s
ce
n
ar
io
,
th
e
f
ir
s
t a
ctiv
ity
is
in
ter
r
u
p
ted
f
o
r
th
e
d
u
r
atio
n
o
f
th
e
s
ec
o
n
d
ac
tiv
ity
b
e
f
o
r
e
t
h
e
f
ir
s
t a
ctio
n
is
r
estar
ted
.
−
R
ec
o
g
n
izin
g
m
u
ltip
le
r
esid
en
ts
:
e
v
en
th
o
u
g
h
k
ee
p
in
g
t
r
ac
k
o
f
a
s
in
g
le
r
esid
en
t'
s
d
aily
ac
tiv
ities
is
a
ch
allen
g
in
g
task
,
m
an
ag
in
g
m
u
ltip
le
r
esid
en
ts
is
s
ig
n
if
ican
tly
m
o
r
e
d
if
f
icu
lt.
I
n
f
ac
t,
t
h
e
s
am
e
ac
tio
n
s
b
ec
o
m
e
m
o
r
e
c
o
m
p
licated
to
id
en
tify
wh
en
n
u
m
e
r
o
u
s
p
e
o
p
le
liv
in
g
o
r
wo
r
k
in
g
to
g
et
h
er
in
th
e
s
am
e
s
p
ac
e.
On
th
e
o
n
e
h
an
d
,
a
r
es
id
en
t
m
ay
in
ter
ac
t
with
o
th
er
s
in
a
g
r
o
u
p
t
o
ca
r
r
y
o
u
t
s
h
ar
e
d
task
s
.
I
n
th
is
in
s
tan
ce
,
ea
ch
r
esid
en
t
in
th
e
g
r
o
u
p
h
as
th
e
s
am
e
ac
tiv
ity
r
ef
lecte
d
b
y
th
e
s
en
s
o
r
s
'
ac
tiv
ati
o
n
.
On
th
e
o
th
er
h
an
d
,
ev
er
y
o
n
e
ca
n
ca
r
r
y
o
u
t
m
u
ltip
le
task
s
s
im
u
ltan
eo
u
s
ly
.
T
h
e
s
en
s
o
r
s
f
o
r
v
a
r
io
u
s
ac
tiv
ities
ar
e
s
im
u
ltan
eo
u
s
ly
ac
tiv
ated
as
a
r
esu
lt.
T
h
e
ac
tiv
ity
s
eq
u
e
n
ce
s
ar
e
c
r
ea
ted
b
y
m
er
g
in
g
an
d
c
o
m
b
in
in
g
th
ese
ac
tiv
atio
n
s
.
So
,
a
r
esid
en
t'
s
ac
tiv
ity
co
u
ld
co
n
s
titu
te
a
n
o
is
e
f
o
r
an
o
th
e
r
'
s
ac
tiv
ity
.
A
lth
o
u
g
h
v
ar
io
u
s
s
tatis
t
ical
m
ea
s
u
r
em
en
ts
ar
e
o
f
f
er
ed
in
th
is
f
ield
o
f
s
tu
d
y
,
it i
s
s
till
r
eg
ar
d
ed
as d
if
f
icu
lt [
4
2
]
.
−
Data
s
tr
ea
m
in
g
:
s
en
s
o
r
d
ata
i
s
p
r
o
v
id
e
d
as
a
tim
e
s
er
ies
o
r
s
en
s
o
r
d
ata
s
tr
ea
m
.
Hen
ce
,
t
h
is
d
ata
ca
n
b
e
im
m
ed
iately
ev
alu
ate
d
u
s
in
g
an
o
n
lin
e
tech
n
iq
u
e
o
r
s
to
r
ed
o
n
a
co
m
p
u
ter
f
o
r
f
u
r
th
er
o
f
f
l
in
e
p
r
o
ce
s
s
in
g
.
C
o
n
s
eq
u
en
tly
,
o
u
tco
m
es th
at
a
r
r
iv
e
af
ter
s
ig
n
i
f
ican
t d
elay
s
m
ig
h
t d
im
in
is
h
in
th
ei
r
ef
f
ec
tiv
e
n
ess
.
4
.
2
.
H
u
m
a
n
a
ct
i
v
it
y
re
c
o
g
nitio
n a
pp
ro
a
ches in sm
a
rt
ho
m
es
Fo
r
th
e
p
u
r
p
o
s
e
o
f
id
en
tify
i
n
g
h
u
m
an
ac
tiv
ities
with
in
th
e
s
m
ar
t
h
o
m
e,
t
h
er
e
ar
e
th
r
ee
m
ajo
r
ca
teg
o
r
ies
in
to
w
h
ich
th
e
m
eth
o
d
o
l
o
g
ies
id
en
tifie
d
in
th
e
liter
atu
r
e
ca
n
b
e
ca
te
g
o
r
ized
:
d
ata
-
d
r
i
v
en
ap
p
r
o
ac
h
es
(
DDA)
,
k
n
o
wled
g
e
-
d
r
iv
en
ap
p
r
o
ac
h
es
(
KDA)
,
an
d
h
y
b
r
id
ap
p
r
o
ac
h
es
(
HA)
.
KDA
m
ak
es
u
s
e
o
f
r
u
le
d
esig
n
an
d
ex
p
e
r
t
k
n
o
w
led
g
e.
T
h
is
m
ea
n
s
it
m
ak
es
u
s
e
o
f
lo
g
ical
r
ea
s
o
n
in
g
,
m
o
d
elin
g
,
an
d
p
r
io
r
k
n
o
wled
g
e
o
f
th
e
d
o
m
ain
.
D
DA
m
o
d
els
a
n
d
d
etec
ts
th
e
ac
tio
n
u
s
in
g
u
s
er
-
g
en
er
ate
d
d
ata.
I
t
is
b
ased
o
n
m
ac
h
in
e
lear
n
i
n
g
a
n
d
d
ata
m
i
n
in
g
tech
n
iq
u
es.
T
h
e
f
u
n
d
am
en
tal
p
r
o
b
lem
with
s
u
ch
m
eth
o
d
s
is
th
at
th
ey
ar
e
n
o
t
id
ea
l
f
o
r
h
an
d
lin
g
u
n
ce
r
tain
d
ata.
T
o
s
o
lv
e
th
ese
p
r
o
b
lem
s
,
h
y
b
r
id
tech
n
iq
u
es
th
at
co
m
b
in
e
th
e
ad
v
an
tag
es o
f
d
ata
-
d
r
iv
en
a
n
d
KDA
ar
e
s
u
itab
le
[
43
]
.
4
.
2
.
1
.
Da
t
a
-
ba
s
ed
a
pp
ro
a
ch
Data
-
d
r
iv
en
m
eth
o
d
s
e
m
p
lo
y
in
g
m
ac
h
i
n
e
lear
n
i
n
g
a
n
d
d
a
ta
m
in
in
g
ap
p
r
o
ac
h
es
d
e
v
elo
p
ac
tiv
ity
m
o
d
els
f
r
o
m
e
x
is
tin
g
d
atasets
[
44
]
.
T
h
ey
tr
ain
th
e
ac
tiv
ity
m
o
d
el,
w
h
ich
ca
p
tu
r
es
th
e
im
p
licit
g
en
er
al
r
u
les,
u
s
in
g
a
lar
g
e
am
o
u
n
t
o
f
la
b
eled
d
ata.
I
t
ca
n
b
e
u
s
ed
to
d
e
v
elo
p
m
o
r
e
ac
c
u
r
ate
an
d
e
f
f
ici
en
t
s
y
s
tem
s
lik
e
th
e
ex
am
p
le
o
f
clim
ate
co
n
tr
o
l
s
y
s
tem
s
in
s
m
ar
t
g
r
ee
n
h
o
u
s
es
[
4
5
]
.
T
h
is
wo
u
ld
o
p
tim
iz
e
cr
o
p
p
r
o
d
u
ctio
n
,
im
p
r
o
v
e
p
r
o
d
u
ct
q
u
ality
,
an
d
r
ed
u
ce
en
er
g
y
co
n
s
u
m
p
tio
n
.
Data
-
d
r
iv
en
m
eth
o
d
s
,
wh
ich
lar
g
ely
r
ely
o
n
p
r
o
b
a
b
ilis
tic
an
d
s
tatis
tical
r
e
aso
n
in
g
,
co
n
tain
b
o
t
h
s
u
p
er
v
is
ed
an
d
u
n
s
u
p
er
v
is
ed
lear
n
in
g
ap
p
r
o
ac
h
es
b
ased
o
n
m
ac
h
in
e
lea
r
n
in
g
a
n
d
d
ee
p
lear
n
in
g
tech
n
iq
u
es
as
s
h
o
wn
in
Fig
u
r
e
4
.
Actu
ally
,
t
h
e
d
at
a
-
d
r
iv
en
a
p
p
r
o
ac
h
was m
o
s
tly
u
s
ed
in
th
e
f
ir
s
t in
v
esti
g
atio
n
s
[
4
6]
:
−
Su
p
er
v
is
ed
lear
n
in
g
alg
o
r
ith
m
s
cr
ea
te
a
m
o
d
el
u
s
in
g
a
l
ab
elled
tr
ain
in
g
d
ataset
in
ac
co
r
d
an
ce
with
a
p
r
ed
ef
in
e
d
co
llectio
n
o
f
ch
ar
a
cter
is
tics
in
o
r
d
er
to
u
n
d
e
r
s
tan
d
th
e
d
e
p
en
d
e
n
cies
an
d
co
r
r
elatio
n
s
b
etwe
en
th
e
tar
g
eted
p
r
ed
ictio
n
o
u
tp
u
t
an
d
th
e
in
p
u
t
d
ata.
I
t
d
ev
el
o
p
s
r
u
les
th
at
d
eter
m
in
e
th
e
lik
elih
o
o
d
th
at
th
e
lab
el
will
o
cc
u
r
g
iv
en
th
e
in
p
u
t.
Fo
llo
win
g
tr
ain
in
g
,
th
e
alg
o
r
ith
m
ca
n
ca
teg
o
r
ize
f
r
esh
u
n
k
n
o
wn
d
ata
a
n
d
f
o
r
ec
ast
th
e
o
u
tp
u
t
v
alu
es
f
o
r
n
o
v
el
d
ata
u
s
in
g
co
r
r
elatio
n
s
ac
q
u
ir
ed
f
r
o
m
p
r
ev
io
u
s
d
atasets
,
ac
co
r
d
in
g
to
th
e
lear
n
ed
r
u
les.
T
h
e
m
o
r
e
ex
am
p
les
th
at
ar
e
p
r
o
v
id
ed
,
th
e
ea
s
ier
it
will
b
e
f
o
r
th
e
alg
o
r
ith
m
to
ad
a
p
t
an
d
h
an
d
le
d
if
f
e
r
en
t
in
p
u
ts
.
An
ex
am
p
le
o
f
a
r
ec
en
t
wo
r
k
b
ased
o
n
Su
p
er
v
is
ed
m
ac
h
i
n
e
lear
n
i
n
g
alg
o
r
ith
m
s
is
g
iv
en
in
[
4
7
]
.
−
Un
s
u
p
er
v
is
ed
lear
n
i
n
g
tech
n
iq
u
es
ex
tr
ac
t
in
s
ig
h
ts
d
ir
ec
tly
f
r
o
m
th
e
d
ata,
with
o
u
t
r
eq
u
ir
i
n
g
lab
els.
T
h
e
y
ar
e
th
e
f
am
ily
o
f
m
ac
h
in
e
le
ar
n
in
g
tech
n
iq
u
es
wh
er
e
th
e
d
ata
is
n
o
t
lab
elled
.
I
n
s
tead
o
f
d
ep
e
n
d
in
g
o
n
ex
is
tin
g
in
f
o
r
m
atio
n
f
r
o
m
th
e
class
,
th
ey
lo
o
k
f
o
r
an
d
d
e
d
u
ce
lo
g
ical
r
elatio
n
s
h
ip
s
b
etwe
en
th
e
d
ata.
T
h
ese
alg
o
r
ith
m
s
u
s
e
m
eth
o
d
s
to
an
aly
s
e
th
e
in
p
u
t
d
ataset
in
s
ea
r
ch
o
f
p
atter
n
s
,
r
u
les,
an
d
s
u
m
m
ar
ies
th
at
ass
is
t
u
s
er
s
in
b
etter
u
n
d
er
s
tan
d
in
g
th
e
d
ata
an
d
d
er
iv
in
g
in
s
ig
h
tf
u
l
co
n
clu
s
io
n
s
.
T
h
er
e
ar
e
n
u
m
er
o
u
s
u
n
s
u
p
er
v
is
ed
ap
p
r
o
ac
h
es;
s
o
m
e
clu
s
ter
co
m
p
ar
a
b
le
d
ata
u
s
in
g
d
is
tan
ce
cr
iter
ia,
wh
ile
o
th
er
s
tr
y
t
o
lear
n
th
ese
p
r
in
cip
les
o
n
th
eir
o
wn
.
Un
s
u
p
er
v
is
ed
lear
n
in
g
h
as
th
e
m
ain
b
en
ef
it o
f
allo
win
g
f
o
r
t
h
e
d
is
co
v
er
y
o
f
r
u
les
an
d
c
o
r
r
elatio
n
s
th
at
w
o
u
ld
o
t
h
er
wis
e
g
o
u
n
r
ec
o
g
n
i
ze
d
b
y
ex
p
e
r
ts
.
An
ex
am
p
le
o
f
u
n
s
u
p
er
v
is
ed
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
i
s
p
r
esen
ted
in
[
4
8
]
.
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:
2
5
0
2
-
4
7
52
Th
e
p
o
ten
tia
l
o
f th
e
in
tern
et
o
f th
in
g
s
fo
r
h
u
ma
n
a
ctivity
r
ec
o
g
n
itio
n
i
n
s
ma
r
t h
o
me
… (
K
h
a
d
ija
E
s
s
a
fi
)
309
Fig
u
r
e
4
.
Su
p
er
v
is
ed
an
d
u
n
s
u
p
er
v
is
ed
lear
n
in
g
m
eth
o
d
s
4
.
2
.
2
.
K
no
wledg
e
-
driv
en
a
pp
ro
a
ch
Kn
o
wled
g
e
-
d
r
iv
en
a
p
p
r
o
ac
h
r
elies
o
n
p
r
io
r
k
n
o
wled
g
e
ab
o
u
t
th
e
r
ea
l
wo
r
ld
,
wh
ich
s
h
o
ws
th
at
th
e
lis
t
o
f
o
b
jects
an
d
f
ea
tu
r
es
n
ee
d
ed
to
co
m
p
lete
a
task
is
co
n
s
is
ten
tly
v
er
y
s
im
ilar
.
I
t
in
c
o
r
p
o
r
ates
r
ea
s
o
n
in
g
en
g
in
es,
o
n
to
lo
g
ies,
a
n
d
l
o
g
ic
r
u
les
to
i
n
f
er
a
p
p
r
o
p
r
iate
ac
ti
o
n
s
f
r
o
m
th
e
in
p
u
t
o
f
th
e
c
u
r
r
en
t
s
en
s
o
r
s
.
E
v
e
n
if
th
e
ac
tiv
ity
is
ca
r
r
ied
o
u
t
in
v
ar
io
u
s
way
s
in
r
ea
l
-
wo
r
ld
s
ce
n
ar
io
s
,
th
e
v
a
r
iety
in
th
e
n
u
m
b
er
an
d
k
i
n
d
o
f
o
b
jects
in
v
o
lv
e
d
is
lim
ited
.
Fo
r
ex
am
p
le,
th
e
ac
tiv
ity
“to
ir
o
n
clo
th
es”
co
n
tain
s
ac
tio
n
s
i
n
v
o
lv
in
g
an
i
r
o
n
,
an
ir
o
n
in
g
b
o
ar
d
,
a
wate
r
s
p
r
ay
e
r
,
an
d
clo
th
es
.
Ho
wev
e
r
,
as
p
e
o
p
le
d
if
f
e
r
in
th
eir
life
s
ty
les,
ab
ilit
ies,
an
d
h
ab
its
th
ey
h
av
e
th
e
p
o
ten
tial to
ca
r
r
y
o
u
t a
n
ac
tiv
ity
in
a
v
ar
iety
o
f
way
s
.
T
h
e
ac
q
u
is
itio
n
o
f
th
e
n
ec
es
s
ar
y
co
n
tex
tu
al
k
n
o
wled
g
e
i
s
th
e
in
itial
s
tep
f
o
r
k
n
o
wle
d
g
e
-
d
r
i
v
en
s
y
s
tem
s
.
T
y
p
ically
,
th
is
i
s
a
cc
o
m
p
lis
h
ed
b
y
ap
p
ly
in
g
co
m
m
o
n
k
n
o
wled
g
e
en
g
in
ee
r
in
g
ap
p
r
o
ac
h
es
[
49
]
.
Dif
f
er
en
t
s
tr
ateg
ies
ca
n
b
e
d
is
tin
g
u
is
h
ed
d
ep
en
d
in
g
o
n
th
e
ty
p
e
o
f
k
n
o
wled
g
e
th
at
h
as
b
ee
n
lear
n
ed
.
C
h
en
et
a
l.
[
50
]
d
em
o
n
s
tr
ate
ab
o
u
t
ac
tiv
ity
r
ec
o
g
n
itio
n
,
s
e
v
er
al
r
esear
ch
er
s
em
p
lo
y
lo
g
i
c
-
b
ased
tech
n
iq
u
es,
wh
ile
o
th
er
s
ad
o
p
t
o
n
to
lo
g
y
-
b
ased
tech
n
iq
u
es.
T
h
ese
tec
h
n
iq
u
es
f
ac
ilit
ate
a
wid
ely
a
cc
ep
ted
an
d
clea
r
r
ep
r
esen
tatio
n
o
f
ac
tiv
ity
d
e
f
in
itio
n
s
,
wh
ich
r
em
ai
n
s
in
d
ep
en
d
en
t
o
f
alg
o
r
ith
m
ic
p
r
e
f
er
en
ce
s
,
f
o
s
ter
in
g
p
o
r
tab
ilit
y
,
r
e
u
s
ab
ilit
y
,
an
d
in
t
er
o
p
er
a
b
ilit
y
.
4
.
2
.
3
.
Co
m
pa
riso
n
T
h
e
f
o
llo
win
g
T
a
b
le
2
r
ev
ie
ws
r
ec
en
t
wo
r
k
s
o
n
s
m
ar
t
cities
b
ased
o
n
a
d
ata
-
d
r
iv
e
n
ap
p
r
o
ac
h
a
n
d
Kn
o
wled
g
e
an
d
r
esu
m
es
th
ei
r
ad
v
an
tag
es
an
d
d
is
ad
v
an
tag
e
s
ac
co
r
d
in
g
to
th
e
p
r
esen
ted
c
r
iter
ia
in
s
ec
tio
n
3
.
T
h
is
co
m
p
ar
is
o
n
h
ig
h
lig
h
ts
th
e
co
n
tin
u
o
u
s
d
eb
ate
in
th
e
s
cien
tific
co
m
m
u
n
ity
o
v
er
th
e
ap
p
r
o
p
r
iate
ap
p
r
o
ac
h
es
f
o
r
d
iv
e
r
s
e
ap
p
licatio
n
s
,
f
r
o
m
h
ea
lth
ca
r
e
to
s
m
ar
t
b
u
ild
in
g
m
a
n
ag
em
e
n
t.
I
t
is
esp
ec
ially
r
elev
an
t
in
s
ec
to
r
s
lik
e
ac
tiv
ity
r
ec
o
g
n
i
tio
n
in
s
m
ar
t h
o
m
es.
Data
-
d
r
iv
en
s
tr
ateg
ies,
wh
ich
ar
e
h
ig
h
ly
r
eg
ar
d
ed
f
o
r
th
eir
ac
cu
r
ac
y
an
d
ad
ap
ta
b
ilit
y
,
p
er
f
o
r
m
b
est
in
co
n
te
x
ts
with
lo
ts
o
f
d
ata.
T
h
ey
u
s
e
m
ac
h
in
e
lear
n
in
g
al
g
o
r
ith
m
s
to
ex
am
i
n
e
an
d
f
o
r
e
ca
s
t
d
ata
b
ased
o
n
p
atter
n
s
f
o
u
n
d
in
s
id
e.
H
o
wev
er
,
th
ey
h
av
e
s
o
m
e
s
ig
n
if
ican
t
d
is
ad
v
an
tag
es,
s
u
ch
as
th
eir
r
elian
ce
o
n
lar
g
e,
h
ig
h
-
q
u
ality
d
ata
an
d
th
e
p
o
s
s
ib
le
p
r
iv
ac
y
is
s
u
es
th
ey
b
r
in
g
.
Fu
r
th
er
m
o
r
e,
it
ca
n
b
e
ch
alle
n
g
in
g
to
u
n
d
er
s
tan
d
an
d
p
u
t
y
o
u
r
tr
u
s
t
in
ce
r
tain
d
ata
-
d
r
iv
en
m
o
d
els,
s
u
c
h
as
th
o
s
e
b
ased
o
n
d
ee
p
lear
n
in
g
,
d
u
e
t
o
th
ei
r
co
m
p
lex
ity
a
n
d
b
lac
k
-
b
o
x
n
at
u
r
e
in
cr
u
cial
ap
p
licatio
n
s
.
On
th
e
o
th
e
r
h
a
n
d
,
k
n
o
wled
g
e
-
d
r
iv
e
n
s
tr
ateg
ies
u
s
e
p
r
e
-
estab
lis
h
ed
r
u
les
an
d
ex
p
er
t
in
s
ig
h
ts
to
p
r
o
v
id
e
h
ig
h
in
ter
p
r
etab
ilit
y
a
n
d
q
u
ick
e
x
ec
u
tio
n
.
T
h
is
m
ak
es th
em
ex
tr
em
ely
u
s
ef
u
l in
s
itu
atio
n
s
wh
er
e
th
er
e
is
a
lack
o
f
d
ata
o
r
wh
e
n
j
u
d
g
m
e
n
ts
n
ee
d
t
o
b
e
ju
s
tifie
d
.
Ho
wev
er
,
th
eir
in
f
lex
ib
ilit
y
an
d
r
elian
ce
o
n
th
o
r
o
u
g
h
,
co
r
r
ec
t
d
o
m
ain
k
n
o
wled
g
e
m
ig
h
t
r
estrict
th
eir
f
l
ex
ib
ilit
y
an
d
m
ak
e
m
an
u
al
u
p
d
ates
n
ec
ess
ar
y
to
ad
ju
s
t to
n
ew
d
ata
o
r
en
v
ir
o
n
m
en
tal
ch
an
g
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
36
,
No
.
1
,
Octo
b
er
20
24
:
302
-
3
1
7
310
T
ab
le
2
.
Stre
n
g
th
s
an
d
wea
k
n
ess
es o
f
th
e
d
ata
-
d
r
iv
e
n
an
d
k
n
o
wled
g
e
-
d
r
iv
en
[
5
1
]
-
[
1
1
5
]
App
r
oac
h
t
yp
e
S
t
r
e
n
g
t
h
s
Re
f
e
r
e
n
c
e
s
We
ak
n
e
s
s
e
s
Re
f
e
r
e
n
c
e
s
Dat
a
-
d
r
iven
C
ompr
e
he
ns
ive
Da
ta
Ana
lys
is
:
F
a
c
il
it
a
tes
the
ga
ther
in
g
a
nd
e
xa
mi
na
ti
on
o
f
e
nor
mous
volu
mes
of
da
ta
to
ga
in
a
n
unde
r
s
tanding
of
c
omf
or
t,
e
ne
r
gy
e
f
f
icie
nc
y,
a
nd
s
pa
c
e
us
e
in
s
mar
t
buil
dings
.
Automate
d
F
e
a
tu
r
e
E
xt
r
a
c
ti
on
:
T
his
tec
hnique
r
e
duc
e
s
the
ne
e
d
f
or
manua
l
e
nginee
r
in
g
by
f
a
c
il
it
a
t
ing
a
utonom
ous
lea
r
n
ing
a
nd
r
e
pr
e
s
e
ntation.
I
t
is
pa
r
ti
c
ula
r
ly
us
e
f
ul
f
or
HA
R
.
Ac
c
ur
a
c
y
a
nd
R
obus
tnes
s
:
De
e
p
AI
models
tr
a
ined
on
mas
s
ive
da
tas
e
ts
im
pr
o
ve
the
a
c
c
ur
a
c
y
a
nd
r
obus
tnes
s
of
s
ys
tems
s
uc
h
a
s
wir
e
les
s
s
e
n
s
ing.
F
lexible
a
nd
Ada
ptable
S
ys
tems
:
F
a
c
il
it
a
tes
the
c
r
e
a
ti
on
of
f
le
xibl
e
a
nd
a
da
ptable
s
ys
tems
that
a
r
e
s
im
ple
to
r
e
tr
a
in
us
ing
f
r
e
s
h
da
ta.
Va
luable
I
ns
ight
s
int
o
Hu
man
Ac
ti
vit
ies
:
they
a
r
e
obtaine
d
by
us
ing
s
e
ns
or
da
ta,
whic
h
c
a
ptur
e
s
va
r
iation
be
twe
e
n
da
tas
e
ts
f
or
be
tt
e
r
a
c
ti
vit
y
tr
a
c
king
a
nd
de
c
is
ion
-
making.
P
r
ivac
y
in
C
oll
a
bo
r
a
ti
ve
L
e
a
r
ning
:
R
e
duc
e
s
pr
ivac
y
c
onc
e
r
ns
by
a
ggr
e
ga
ti
ng
man
y
models
withou
t
s
ha
r
ing
da
tas
e
ts
.
P
r
e
dicti
ve
P
e
r
f
o
r
manc
e
B
oos
t:
E
nha
nc
e
s
pr
e
dictive
pe
r
f
or
manc
e
f
or
a
va
r
iety
of
us
e
s
.
[
51]
,
[
54
]
,
[
60]
,
[
72
]
,
[
83]
,
[
102
]
,
[
111]
[
52]
,
[
53
]
,
[
63]
,
[
67]
,
[
75
]
,
[
76]
[
53]
,
[
61
]
,
[
86]
,
[
89]
,
[
99
]
,
[
105]
,
[
108]
[
53]
,
[
55
]
,
[
65]
,
[
66]
,
[
79
]
,
[
81]
,
[
84]
,
[
98
]
,
[
102]
,
[
103]
,
[
105
]
,
[
110]
,
[
113]
,
[
114
]
[
51]
,
[
54
]
,
[
57]
,
[
65]
,
[
69
]
,
[
70]
,
[
87]
,
[
91
]
,
[
96]
,
[
101]
,
[
106
]
[
56]
,
[
80
]
[
58]
,
[
81
]
,
[
91]
,
[
110]
,
[
113]
De
pe
nde
nc
e
on
Da
ta
Qua
li
ty:
T
he
qua
nti
ty
a
nd
qua
li
t
y
of
da
ta
ga
ther
e
d
ha
ve
a
s
igni
f
ica
nt
im
pa
c
t
on
pe
r
f
o
r
manc
e
.
P
r
ivac
y
C
onc
e
r
ns
:
G
a
the
r
ing
a
nd
e
xa
mi
ning
pe
r
s
ona
l
in
f
or
mation
gi
ve
s
r
is
e
to
pr
ivac
y
c
onc
e
r
ns
.
T
e
c
hnica
l
C
ompl
e
xit
y:
S
pe
c
ia
li
z
e
d
tool
s
a
nd
knowle
dge
a
r
e
ne
e
de
d
to
im
pleme
nt
a
nd
maintain
c
ompl
ica
ted
models
.
L
a
c
k
of
I
nter
pr
e
tabi
li
ty:
I
t
c
a
n
be
c
ha
ll
e
nging
to
int
e
r
pr
e
t
mo
de
ls
,
pa
r
ti
c
ular
ly
thos
e
ba
s
e
d
on
de
e
p
lea
r
ning.
R
e
quir
e
s
L
a
r
ge
Amou
nts
of
L
a
be
led
T
r
a
ini
ng
Da
ta:
Ac
quir
ing
a
s
igni
f
ica
nt
a
mount
of
labe
led
da
ta
c
a
n
be
e
xpe
ns
ive
a
nd
ti
me
-
c
ons
um
ing
C
omput
a
ti
o
na
l
I
ntens
it
y
:
T
he
tr
a
ini
ng
a
nd
inf
e
r
e
nc
e
of
de
e
p
AI
models
f
r
e
que
nt
ly
ne
e
d
s
ubs
tantial
c
omput
a
ti
o
na
l
r
e
s
our
c
e
s
,
whic
h
may
r
e
s
tr
ict
the
models
'
a
ppl
ica
bil
it
y.
C
ha
ll
e
nge
s
in
M
a
na
ging
He
ter
oge
ne
it
ies
a
mong
Us
e
r
s
a
nd
Ac
ti
vit
ies
:
M
a
na
ging
he
ter
oge
ne
it
ies
a
mong
us
e
r
s
a
nd
a
c
ti
vit
ies
may
pr
ovi
de
dif
f
icu
lt
ies
,
pa
r
ti
c
ular
ly
in
f
e
de
r
a
ted
lea
r
ning
e
nvir
on
ments
.
E
ne
r
gy
C
ons
u
mpt
ion
C
onc
e
r
ns
:
W
hil
e
c
hoos
ing
de
vice
s
with
f
e
we
r
da
tas
e
ts
may
r
e
s
ult
in
lowe
r
lea
r
ni
ng
a
c
c
ur
a
c
y,
s
e
lec
ti
ng
I
oT
de
vice
s
with
lar
ge
r
da
tas
e
ts
f
or
tr
a
i
ning
may
lea
d
to
higher
e
ne
r
gy
c
ons
umpt
ion
R
e
gulator
y
a
nd
E
t
hica
l
C
ha
ll
e
nge
s
:
T
he
a
ppli
c
a
ti
on
of
A
I
in
he
a
lt
hc
a
r
e
r
a
is
e
s
e
thi
c
a
l
que
s
ti
ons
a
nd
c
a
ll
s
f
or
r
e
gulato
r
y
s
upe
r
vis
ion
to
gua
r
a
ntee
pa
ti
e
n
t
s
a
f
e
ty.
[
51]
,
[
53
]
,
[
54]
,
[
63]
,
[
77]
,
[
84
]
,
[
85]
,
[
89]
,
[
91]
,
[
92
]
,
[
98]
,
[
104]
[
51]
,
[
56
]
,
[
73]
-
[
75
]
,
[
81]
-
[
83
]
,
[
91]
,
[
94
]
,
[
95]
,
[
98
]
,
[
102]
,
[
103
]
,
[
111]
,
[
112
]
[
51]
,
[
61
]
,
[
64]
,
[
73]
,
[
81]
,
[
83
]
,
[
87]
,
[
100]
,
[
109]
,
[
113
]
[
51]
,
[
52
]
,
[
87]
,
[
106]
[
52]
-
[
56
]
,
[
63]
,
[
65
]
,
[
81]
-
[
83
]
,
[
93]
,
[
94
]
,
[
100]
,
[
103
]
,
[
115]
[
53]
,
[
65
]
,
[
76]
,
[
105]
[
54]
,
[
64
]
,
[
86]
,
[
89]
[
56]
,
[
70
]
[
57]
,
[
102
]
Kn
owle
d
ge
-
d
r
iven
E
xpe
r
ti
s
e
Us
e
:
Util
ize
s
e
xpe
r
ti
s
e
to
inf
or
m
de
c
is
ions
a
nd
f
or
e
c
a
s
ts
by
f
us
ing
bus
ines
s
r
ules
with
e
xpe
r
t
knowle
dge
;
us
e
f
ul
in
a
r
e
a
s
with
li
mi
ted
da
ta.
I
nter
p
r
e
tabil
it
y:
M
ode
ls
a
r
e
f
r
e
que
nt
ly
mor
e
c
omp
r
e
he
ns
ibl
e
a
nd
tr
a
ns
pa
r
e
nt,
whic
h
pr
o
mot
e
s
us
e
r
a
dopti
on.
I
mm
e
dia
te
I
mpl
e
me
ntation
:
S
olut
i
ons
ba
s
e
d
on
pr
ior
knowle
dge
c
a
n
be
im
pleme
nted
im
med
iate
ly,
ne
ga
ti
ng
the
ne
e
d
f
or
pr
o
tr
a
c
ted
lea
r
ning
s
tage
s
.
R
e
duc
e
d
Da
ta
De
pe
nde
nc
y:
a
ble
to
ope
r
a
te
with
li
tt
le
or
no
labe
led
da
ta
by
us
ing
pr
e
-
e
s
tablis
he
d
models
a
nd
r
ules
S
uppo
r
t
f
or
De
c
is
ion
-
M
a
king:
Us
e
s
pr
of
e
s
s
ional
ins
igh
ts
to
make
mor
e
tr
us
twor
thy
a
nd
e
duc
a
ted
de
c
is
ions
;
e
s
pe
c
ially
us
e
f
ul
f
or
I
oT
a
nd
he
a
lt
hc
a
r
e
a
ppli
c
a
ti
ons
.
[
51]
-
[
54
]
,
[
59]
,
[
63
]
,
[
69]
,
[
72
]
-
[
75]
,
[
78]
,
[
80
]
,
[
84]
,
[
87]
,
[
90
]
-
[
92
]
,
[
95]
,
[
100
]
-
[
105
]
,
[
106]
,
[
107
]
,
[
109]
,
[
111]
,
[
115
]
[
52]
,
[
53
]
,
[
63]
,
[
75]
,
[
78
]
,
[
88]
,
[
103]
,
[
106
]
,
[
108]
,
[
109]
[
67]
,
[
104
]
,
[
114]
[
52]
,
[
53
]
,
[
54]
,
[
76]
,
[
78
]
,
[
89]
,
[
104]
[
51]
,
[
68
]
,
[
69]
,
[
73]
,
[
74
]
,
[
91]
,
[
95]
,
[
101
]
L
im
i
ted
Ada
ptabil
it
y
&
De
pe
nde
nc
y
on
E
xpe
r
t
Know
ledge
:
Ha
s
tr
ouble
a
djus
t
ing
to
nove
l
s
it
ua
ti
ons
or
una
nti
c
i
pa
ted
e
ve
nts
that
we
r
e
n'
t
c
ove
r
e
d
by
the
guidelines
a
t
f
ir
s
t.
I
t
is
highl
y
de
pe
nde
nt
on
the
a
va
il
a
bil
it
y
a
nd
c
ompr
e
he
ns
ivene
s
s
of
e
xpe
r
ts
Know
ledge
R
e
pr
e
s
e
ntation
Di
f
f
icu
lt
ies
:
I
t
c
a
n
be
dif
f
icult
to
a
pp
r
opr
iate
ly
c
a
ptur
e
a
nd
r
e
pr
e
s
e
nt
dyna
mi
c
,
c
ompl
ica
ted
know
ledge
.
T
im
e
-
c
ons
umi
n
g
R
ule
De
f
ini
ti
on:
M
a
nua
l
labor
is
ne
e
de
d
f
or
both
f
e
a
tur
e
e
nginee
r
ing
a
nd
r
u
le
de
f
ini
t
ion,
a
nd
e
s
s
e
nti
a
l
pa
tt
e
r
ns
may
be
ove
r
looked.
Ac
c
ur
a
c
y
De
pe
nde
nt
on
P
r
e
vi
ous
Know
ledge
&
on
Know
n
P
a
t
ter
ns
:
P
r
e
vious
know
ledge
,
whic
h
may
not
a
lwa
ys
be
c
ur
r
e
nt
or
e
a
s
il
y
a
c
c
e
s
s
ibl
e
,
de
ter
mi
ne
s
e
f
f
e
c
ti
ve
ne
s
s
.
Huma
n
L
a
be
li
n
g
R
e
quir
e
men
ts
:
T
he
pr
a
c
ti
c
a
l
im
ple
menta
ti
o
n
of
ne
w
s
e
ns
or
s
or
de
ploym
e
n
t
a
djus
tm
e
nts
is
li
mi
ted
due
to
the
ne
e
d
f
or
human
labe
li
ng
a
nd
r
e
mapping.
[
51]
-
[
53
]
,
[
59]
,
[
62
]
-
[
64]
,
[
72
]
-
[
74]
,
[
76
]
,
[
84]
,
[
87
]
,
[
92]
,
[
93]
,
[
95]
,
[
100
]
,
[
102]
,
[
103]
,
[
105
]
,
[
107]
,
[
109]
,
[
111
]
,
[
114
]
[
51]
,
[
63
]
,
[
71]
,
[
89]
,
[
91]
,
[
92
]
,
[
95]
,
[
101]
,
[
113]
[
52
]
,
[
54
]
,
[
59]
,
[
63]
,
[
100]
,
[
102
]
,
[
109]
,
[
115]
[
51]
-
[
53
]
,
[
59]
,
[
62
]
,
[
67]
,
[
72
]
,
[
80]
,
[
84]
,
[
90]
,
[
92
]
,
[
93]
,
[
100]
,
[
108]
[
52]
,
[
54
]
,
[
63]
,
[
115]
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:
2
5
0
2
-
4
7
52
Th
e
p
o
ten
tia
l
o
f th
e
in
tern
et
o
f th
in
g
s
fo
r
h
u
ma
n
a
ctivity
r
ec
o
g
n
itio
n
i
n
s
ma
r
t h
o
me
… (
K
h
a
d
ija
E
s
s
a
fi
)
311
4
.
2
.
4
.
H
y
brid a
pp
ro
a
ch
B
y
c
o
m
b
i
n
i
n
g
d
i
f
f
e
r
e
n
t
m
e
t
h
o
d
o
l
o
g
i
e
s
,
a
h
y
b
r
i
d
a
p
p
r
o
a
c
h
a
c
h
i
e
v
e
s
t
h
e
"
b
es
t
o
f
b
o
t
h
w
o
r
l
d
s
"
.
T
h
is
a
p
p
r
o
a
c
h
c
a
n
p
r
o
v
i
d
e
a
f
o
r
m
a
l
,
s
e
m
a
n
t
i
c
,
a
n
d
e
x
te
n
d
a
b
l
e
m
o
d
e
l
c
a
p
a
b
l
e
o
f
d
e
a
l
i
n
g
w
it
h
t
h
e
u
n
c
e
r
t
a
i
n
t
y
p
r
e
s
e
n
t
i
n
s
e
n
s
o
r
d
a
ta
a
n
d
r
e
a
s
o
n
i
n
g
r
u
l
e
s
[
116
].
R
e
c
o
g
n
i
zi
n
g
a
l
l
t
y
p
e
s
o
f
h
u
m
a
n
a
c
t
i
v
i
ti
es
i
n
h
o
m
e
s
e
tt
i
n
g
s
m
i
g
h
t
b
e
c
h
a
l
l
e
n
g
i
n
g
d
u
e
t
o
t
h
e
d
i
f
f
i
c
u
l
t
y
i
n
d
e
f
i
n
i
n
g
c
o
m
p
l
e
t
e
a
c
t
i
v
i
t
y
m
o
d
e
l
s
.
A
d
e
s
i
r
a
b
l
e
s
i
t
u
at
i
o
n
m
o
d
e
l
i
s
t
h
e
r
e
f
o
r
e
b
u
i
l
t
o
n
a
s
o
u
n
d
l
o
g
ic
a
l
f
r
a
m
ew
o
r
k
t
h
a
t
i
n
c
l
u
d
es
r
u
l
es
t
o
e
n
s
u
r
e
t
h
e
c
o
n
s
i
s
t
e
n
c
y
a
n
d
i
n
t
e
g
r
it
y
o
f
t
h
e
k
n
o
w
l
e
d
g
e
b
a
s
e
a
s
w
e
l
l
as
l
o
g
i
ca
l
p
r
i
m
i
t
i
v
es
t
h
a
t
p
o
s
s
es
s
t
h
e
n
e
ce
s
s
a
r
y
r
i
c
h
n
e
s
s
t
o
e
n
c
o
m
p
a
s
s
a
d
i
v
e
r
s
e
r
a
n
g
e
o
f
i
n
f
o
r
m
a
t
i
o
n
,
i
n
c
l
u
d
i
n
g
s
e
n
s
o
r
d
a
t
a
,
d
o
m
a
i
n
e
x
p
e
r
ti
s
e
,
d
i
s
t
i
lle
d
c
o
n
t
e
x
t
,
a
n
d
s
i
t
u
at
i
o
n
a
l
k
n
o
w
l
e
d
g
e
.
H
e
n
c
e
,
b
y
c
o
m
b
i
n
i
n
g
d
a
t
a
-
d
r
i
v
e
n
s
t
r
a
t
e
g
ie
s
w
i
t
h
k
n
o
w
l
e
d
g
e
-
d
r
i
v
e
n
m
o
d
e
l
s
,
t
h
i
s
c
h
a
ll
e
n
g
e
c
a
n
b
e
e
f
f
e
c
t
i
v
e
l
y
a
d
d
r
e
s
s
e
d
.
C
o
m
b
i
n
i
n
g
t
h
e
t
w
o
c
a
n
r
e
s
u
lt
i
n
a
c
t
i
v
i
t
y
m
o
d
e
ls
t
h
a
t
a
r
e
c
o
m
p
r
e
h
e
n
s
i
v
e
a
n
d
s
u
f
f
i
c
i
e
n
tl
y
e
n
o
u
g
h
t
o
i
n
c
l
u
d
e
a
l
l
v
a
r
i
e
t
i
es
o
f
h
u
m
a
n
a
ct
i
v
i
ti
es
.
A
d
d
i
t
i
o
n
a
l
l
y
,
t
h
e
s
e
m
o
d
e
ls
a
r
e
a
l
s
o
c
a
p
a
b
l
e
o
f
o
n
g
o
i
n
g
e
v
o
l
u
t
i
o
n
a
n
d
c
a
n
le
a
r
n
t
o
a
d
j
u
s
t
t
o
u
s
e
r
s
'
d
i
v
e
r
s
e
b
e
h
a
v
io
u
r
.
T
h
e
r
e
f
o
r
e
,
r
e
c
e
n
t
w
o
r
k
s
h
a
v
e
b
e
e
n
m
o
t
i
v
a
t
e
d
t
o
p
r
o
p
o
s
e
h
y
b
r
i
d
m
o
d
e
l
s
.
I
n
t
h
i
s
s
u
r
v
e
y
,
w
e
p
r
o
v
i
d
e
d
n
u
m
e
r
o
u
s
HA
f
o
r
HAR
w
h
i
c
h
c
o
n
t
i
n
u
e
t
o
b
e
g
o
o
d
c
h
o
i
c
e
s
f
o
r
p
r
o
c
e
s
s
i
n
g
a
n
d
a
s
s
e
s
s
i
n
g
s
e
n
s
o
r
d
a
t
a
wi
t
h
i
n
i
n
te
l
l
i
g
e
n
t
e
n
v
i
r
o
n
m
e
n
ts
,
i
n
f
l
u
e
n
ce
d
b
y
t
h
e
m
e
t
h
o
d
o
f
h
y
b
r
i
d
i
z
a
t
io
n
e
m
p
l
o
y
e
d
.
I
n
t
h
e
p
e
r
s
p
e
c
t
i
v
e
o
f
c
o
m
b
i
n
i
n
g
K
n
o
w
l
e
d
g
e
-
b
a
s
e
d
a
n
d
D
a
t
a
-
d
r
i
v
e
n
a
p
p
r
o
a
c
h
e
s
,
R
i
b
o
n
i
e
t
al
.
p
r
e
s
e
n
t
a
s
o
l
u
t
i
o
n
n
a
m
e
d
“
C
OS
AR
”
[
117
]
,
a
n
a
d
e
p
t
c
o
n
t
e
x
t
-
a
w
a
r
e
m
o
b
i
l
e
a
p
p
t
h
a
t
i
n
t
e
g
r
a
t
e
s
o
n
t
o
lo
g
i
e
s
w
i
t
h
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
.
T
h
e
m
a
ch
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
i
s
f
i
r
s
t
a
c
t
i
v
a
t
e
d
t
o
f
o
r
e
c
as
t
t
h
e
m
o
s
t
e
x
p
e
c
t
e
d
a
c
t
i
v
it
i
es
u
s
i
n
g
t
r
a
i
n
i
n
g
d
a
t
a
t
h
a
t
h
a
s
b
e
e
n
s
u
p
p
l
i
e
d
.
T
h
e
r
e
s
u
l
ts
a
r
e
t
h
e
n
r
e
f
i
n
e
d
u
s
i
n
g
a
n
o
n
t
o
l
o
g
ic
a
l
r
e
a
s
o
n
e
r
,
w
h
i
c
h
c
h
o
o
s
e
s
f
r
o
m
a
s
e
t
o
f
p
o
t
e
n
t
i
a
l
u
s
e
r
a
c
t
i
o
n
s
b
a
s
e
d
o
n
t
h
e
u
s
e
r
'
s
l
o
c
a
t
i
o
n
a
s
d
e
te
r
m
i
n
e
d
b
y
a
l
o
c
a
l
i
z
at
i
o
n
s
e
r
v
e
r
.
A
n
o
t
h
e
r
h
y
b
r
i
d
s
o
l
u
t
i
o
n
i
s
p
r
o
p
o
s
e
d
b
y
R
i
b
o
n
i
e
t
a
l
.
i
n
[
118
]
c
a
l
l
e
d
S
m
a
r
tF
AB
E
R
s
y
s
t
e
m
wh
i
c
h
i
s
a
n
e
x
t
e
n
s
i
o
n
a
n
d
a
m
e
l
i
o
r
a
t
i
o
n
o
f
F
AB
E
R
[
119
]
.
T
h
e
o
b
j
e
c
t
i
v
e
s
o
f
t
h
e
s
e
t
wo
f
r
a
m
e
w
o
r
k
s
a
r
e
s
i
m
i
la
r
.
T
h
e
s
y
s
te
m
d
e
l
i
v
e
r
s
t
h
e
i
n
f
e
r
r
e
d
e
v
e
n
t
s
a
n
d
a
c
ti
o
n
s
t
o
a
m
o
d
u
l
e
t
a
s
k
e
d
wi
t
h
c
r
e
a
ti
n
g
f
e
a
t
u
r
e
v
e
c
t
o
r
s
b
as
e
d
o
n
t
h
e
r
ec
e
i
v
e
d
e
v
e
n
t
s
r
at
h
e
r
t
h
a
n
t
h
e
M
L
N
c
l
a
s
s
i
f
ie
r
.
T
h
e
c
l
a
s
s
i
f
ic
a
t
i
o
n
o
f
a
c
t
i
v
i
ti
e
s
is
d
o
n
e
u
s
i
n
g
a
m
a
c
h
i
n
e
-
l
e
a
r
n
i
n
g
m
o
d
u
l
e
t
h
a
t
r
e
c
e
i
v
e
s
t
h
e
s
e
f
e
a
t
u
r
es
.
T
h
e
n
e
x
t
s
t
e
p
is
t
o
a
p
p
l
y
a
s
u
g
g
e
s
t
e
d
t
e
c
h
n
i
q
u
e
c
a
l
l
e
d
S
m
a
r
t
A
g
g
r
e
g
a
t
i
o
n
to
i
n
f
e
r
i
n
s
t
a
n
c
e
s
o
f
c
u
r
r
e
n
t
a
c
t
i
v
it
y
.
A
d
d
i
t
i
o
n
a
ll
y
,
R
i
b
o
n
i
e
t
a
l
.
[
120
]
c
r
e
a
t
e
a
n
e
x
t
r
e
m
e
l
y
c
o
m
p
r
e
h
e
n
s
i
v
e
o
n
t
o
l
o
g
i
c
m
o
d
e
l
u
s
e
d
t
h
e
web
o
n
t
o
l
o
g
i
c
l
a
n
g
u
a
g
e
(
OW
L
2
)
,
w
i
t
h
t
h
e
e
v
e
n
t
u
a
l
a
i
m
o
f
c
o
n
n
e
c
t
i
n
g
t
h
i
s
k
n
o
w
l
e
d
g
e
t
o
M
a
r
k
o
v
l
o
g
i
c
n
e
t
w
o
r
k
s
(
M
L
N
)
,
f
a
ci
l
it
a
t
i
n
g
th
e
a
p
p
l
i
c
a
t
i
o
n
o
f
p
r
o
b
a
b
i
l
i
s
t
i
c
r
e
a
s
o
n
i
n
g
.
T
h
e
s
y
s
t
e
m
'
s
g
e
n
e
r
al
i
t
y
is
c
o
m
p
r
o
m
i
s
e
d
b
y
t
h
e
i
r
m
e
t
h
o
d
'
s
r
e
q
u
i
r
e
m
e
n
t
f
o
r
e
x
t
r
e
m
e
l
y
p
r
e
c
i
s
e
a
c
ti
v
i
t
y
m
o
d
e
l
s
.
G
a
b
r
i
e
l
e
p
r
es
e
n
t
a
n
o
v
e
l
h
y
b
r
id
s
t
r
a
te
g
y
u
s
i
n
g
k
n
o
w
l
e
d
g
e
-
b
as
e
d
a
n
d
p
r
o
b
a
b
i
l
is
t
ic
r
e
as
o
n
i
n
g
,
h
e
u
s
e
d
u
n
s
u
p
e
r
v
i
s
e
d
f
e
e
d
b
a
c
k
t
o
c
l
ass
i
f
y
t
h
e
r
u
l
es
t
h
a
t
p
e
r
f
o
r
m
e
d
w
e
l
l
i
n
t
h
e
r
ea
l
-
w
o
r
l
d
d
a
ta
s
et
[
121
]
.
O
n
t
h
e
o
t
h
e
r
h
a
n
d
,
a
n
o
t
h
e
r
h
y
b
r
i
d
m
o
d
e
l
h
a
s
b
e
e
n
d
e
v
e
l
o
p
e
d
i
n
[
122
]
t
h
a
t
i
n
c
l
u
d
e
s
a
m
a
c
h
i
n
e
-
l
e
a
r
n
i
n
g
m
e
t
h
o
d
o
l
o
g
y
,
a
n
o
n
t
o
l
o
g
y
,
a
n
d
a
l
o
g
-
l
i
n
e
a
r
s
y
s
te
m
.
T
h
i
s
m
o
d
e
l
a
i
m
s
t
o
i
d
e
n
t
if
y
a
m
u
l
t
i
-
t
i
e
r
e
d
a
c
ti
v
i
t
y
s
t
r
u
c
tu
r
e
w
i
t
h
f
o
u
r
t
i
e
r
s
:
c
o
m
p
l
e
x
a
c
ti
v
i
t
y
(
L
e
v
e
l
1
)
,
s
im
p
l
e
a
c
ti
v
i
t
y
(
L
e
v
e
l
2
)
,
m
a
n
i
p
u
l
a
t
i
v
e
g
es
t
u
r
e
(
L
e
v
el
3
)
,
a
n
d
at
o
m
i
c
g
es
t
u
r
e
(
L
e
v
e
l
4
)
.
T
h
r
o
u
g
h
t
h
e
u
s
e
o
f
a
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
a
t
o
m
i
c
g
e
s
t
u
r
e
s
a
r
e
d
e
t
ec
t
e
d
.
A
d
d
it
i
o
n
a
l
l
y
,
m
a
n
i
p
u
l
a
ti
n
g
g
e
s
t
u
r
e
s
,
b
a
s
i
c
a
ct
i
v
it
i
es
,
a
n
d
co
m
p
l
i
c
a
t
e
d
ac
t
i
v
it
i
es
a
r
e
i
n
f
e
r
r
e
d
t
h
r
o
u
g
h
a
p
r
o
b
a
b
i
l
is
t
i
c
o
n
t
o
l
o
g
y
e
s
t
a
b
l
i
s
h
e
d
b
y
t
h
e
l
o
g
-
l
i
n
e
a
r
a
n
d
c
o
n
v
e
n
t
i
o
n
a
l
o
n
t
o
l
o
g
i
c
a
l
r
e
as
o
n
i
n
g
t
a
s
k
s
.
A
n
o
t
h
e
r
h
y
b
r
i
d
p
r
o
p
o
s
a
l
i
s
p
r
o
p
o
s
e
d
i
n
[
123
]
,
MLN
a
r
e
u
s
e
d
f
o
r
a
c
t
i
v
i
t
y
r
e
c
o
g
n
i
t
i
o
n
c
o
m
b
i
n
i
n
g
t
h
e
u
s
a
g
e
o
f
o
n
t
o
l
o
g
i
e
s
w
i
t
h
s
t
a
t
is
t
i
c
a
l
l
ea
r
n
i
n
g
m
e
t
h
o
d
s
(
M
L
N
)
.
T
h
e
s
u
g
g
e
s
t
e
d
s
y
s
t
e
m
m
a
k
e
s
u
s
e
o
f
t
h
e
m
o
d
e
l
-
t
h
e
o
r
e
t
i
c
s
e
m
a
n
ti
c
p
r
o
p
e
r
t
y
i
n
h
e
r
e
n
t
i
n
d
es
c
r
i
p
ti
o
n
l
o
g
i
c
t
o
t
r
an
s
f
o
r
m
t
h
e
a
ct
i
v
it
y
m
o
d
e
l
b
as
ed
o
n
o
n
t
o
l
o
g
y
i
n
t
o
c
o
r
r
e
s
p
o
n
d
i
n
g
f
i
r
s
t
-
o
r
d
e
r
r
u
l
e
s
.
T
h
i
s
p
r
o
c
e
d
u
r
e
e
n
t
a
i
l
s
c
r
e
a
t
i
n
g
MLN
,
w
h
e
r
e
l
e
a
r
n
e
r
s
g
r
a
s
p
w
e
i
g
h
t
e
d
f
i
r
s
t
-
o
r
d
e
r
r
u
l
e
s
,
e
n
a
b
l
i
n
g
p
r
o
b
a
b
i
li
s
ti
c
r
e
as
o
n
i
n
g
w
i
t
h
i
n
a
f
r
a
m
e
w
o
r
k
o
f
k
n
o
w
l
e
d
g
e
r
e
p
r
e
s
e
n
t
at
i
o
n
.
S
u
k
o
r
e
t
a
l
.
[
124
]
p
r
o
p
o
s
e
a
n
a
l
t
e
r
n
a
t
e
s
t
r
at
e
g
y
t
h
a
t
c
o
m
b
i
n
es
k
n
o
w
l
e
d
g
e
-
d
r
i
v
e
n
r
e
as
o
n
i
n
g
w
i
t
h
d
a
t
a
-
d
r
i
v
e
n
r
e
a
s
o
n
i
n
g
t
o
e
n
a
b
l
e
a
c
ti
v
i
t
y
m
o
d
e
ls
t
o
a
u
t
o
m
at
i
c
a
ll
y
e
v
o
l
v
e
a
n
d
a
d
a
p
t
i
n
r
es
p
o
n
s
e
to
u
s
e
r
s
p
e
c
i
f
i
c
i
ti
e
s
.
F
i
r
s
t
o
f
a
l
l
,
a
k
n
o
w
l
e
d
g
e
-
d
r
i
v
en
r
a
t
i
o
n
a
l
e
f
o
r
as
s
u
m
i
n
g
a
n
i
n
i
ti
a
l
a
ct
i
v
i
t
y
m
o
d
e
l
i
s
d
es
c
r
i
b
e
d
.
I
n
o
r
d
e
r
t
o
c
r
e
a
t
e
a
d
y
n
a
m
i
c
a
c
t
i
v
it
y
m
o
d
e
l
t
h
a
t
l
e
a
r
n
s
u
s
e
r
s
'
v
a
r
ie
d
a
c
t
i
o
n
s
,
t
h
e
m
o
d
e
l
i
s
t
h
e
n
t
r
a
i
n
e
d
u
s
i
n
g
d
a
t
a
-
d
r
i
v
e
n
m
e
t
h
o
d
o
l
o
g
i
e
s
.
I
n
t
h
e
s
a
m
e
p
er
s
p
e
c
t
i
v
e
,
a
n
d
i
n
o
r
d
e
r
t
o
o
v
e
r
c
o
m
e
t
h
e
i
s
s
u
es
w
it
h
a
c
t
i
v
i
t
y
m
o
d
e
l
i
n
g
,
C
h
e
n
e
t
a
l
.
[
125
]
p
r
o
p
o
s
e
a
n
o
n
t
o
l
o
g
y
-
b
a
s
e
d
h
y
b
r
i
d
s
t
r
at
e
g
y
t
h
a
t
c
o
m
b
i
n
e
s
d
a
ta
-
d
r
i
v
e
n
l
ea
r
n
i
n
g
c
a
p
a
b
i
l
i
ti
e
s
wi
t
h
a
k
n
o
w
l
e
d
g
e
-
d
r
i
v
e
n
a
p
p
r
o
a
c
h
.
T
o
g
e
n
e
r
a
t
e
i
n
d
i
v
i
d
u
al
a
ct
i
v
i
t
y
m
o
d
e
l
s
u
s
i
n
g
i
n
c
r
e
m
e
n
ta
l
l
e
a
r
n
i
n
g
,
g
e
n
e
r
i
c
a
c
ti
v
i
t
y
m
o
d
e
l
s
t
h
a
t
a
r
e
a
p
p
r
o
p
r
i
a
t
e
f
o
r
a
l
l
u
s
e
r
s
a
r
e
f
i
r
s
t
p
r
o
v
i
d
e
d
.
A
s
a
c
o
n
c
e
p
t
u
a
l
f
o
u
n
d
a
t
i
o
n
a
n
d
t
e
c
h
n
o
l
o
g
i
c
a
l
e
n
a
b
l
e
r
s
f
o
r
A
c
ti
v
i
t
y
D
ai
l
y
L
if
e
m
o
d
e
l
i
n
g
,
c
l
a
s
s
i
f
ic
a
t
i
o
n
,
a
n
d
l
e
a
r
n
i
n
g
,
t
h
e
a
p
p
r
o
a
c
h
m
a
k
e
s
u
s
e
o
f
s
e
m
a
n
t
i
c
t
e
c
h
n
o
l
o
g
i
e
s
.
O
n
t
h
e
o
t
h
e
r
h
a
n
d
,
A
z
k
u
n
e
e
t
a
l
.
p
r
o
p
o
s
e
i
n
[
49
]
a
n
o
v
e
l
a
c
t
i
v
i
t
y
r
e
c
o
g
n
i
ti
o
n
s
y
s
t
e
m
t
h
a
t
m
e
r
g
e
s
u
n
s
u
p
e
r
v
i
s
e
d
l
e
a
r
n
i
n
g
a
p
p
r
o
ac
h
e
s
w
it
h
a
c
t
i
v
it
y
m
o
d
e
l
s
b
a
s
e
d
o
n
k
n
o
w
l
e
d
g
e
.
T
h
e
m
o
s
t
f
r
e
q
u
e
n
t
a
c
t
i
o
n
s
e
q
u
e
n
c
e
s
ca
r
r
i
e
d
o
u
t
b
y
a
p
e
r
s
o
n
a
r
e
f
i
r
s
t
e
x
t
r
ac
t
e
d
u
s
i
n
g
a
d
o
m
a
i
n
-
s
p
e
c
i
f
i
c
d
at
a
m
i
n
i
n
g
m
e
t
h
o
d
p
r
e
v
i
o
u
s
l
y
c
r
e
a
t
e
d
b
y
C
o
o
k
e
t
a
l
.
i
n
[
126
]
.
T
o
d
e
t
e
r
m
i
n
e
w
h
i
c
h
a
c
t
i
v
i
t
i
es
a
r
e
b
e
i
n
g
c
a
r
r
i
e
d
o
u
t
i
n
a
p
a
r
t
i
c
u
l
a
r
a
c
t
i
o
n
s
e
q
u
e
n
c
e
,
t
h
e
w
r
i
t
e
r
s
s
e
c
o
n
d
l
y
i
n
c
o
r
p
o
r
a
t
e
a
k
n
o
w
l
e
d
g
e
-
b
a
s
ed
a
c
t
i
v
i
t
y
m
o
d
e
l
i
n
t
o
a
u
n
i
q
u
e
m
a
t
c
h
i
n
g
m
e
t
h
o
d
.
T
h
e
m
e
t
h
o
d
y
i
e
l
d
s
a
n
e
x
p
a
n
d
ab
l
e
a
c
t
i
v
it
y
r
e
c
o
g
n
i
t
i
o
n
s
y
s
t
e
m
.
M
o
r
e
r
e
c
e
n
t
l
y
,
i
n
2
0
2
0
,
A
y
a
r
i
e
t
a
l
.
[
127
]
s
h
o
w
e
d
b
e
t
t
e
r
p
e
r
f
o
r
m
a
n
c
e
t
h
a
n
b
a
s
e
l
i
n
e
m
o
d
e
l
s
b
y
p
u
t
t
i
n
g
o
u
t
a
h
y
b
r
i
d
m
o
d
e
l
t
h
a
t
c
o
m
b
i
n
e
s
p
o
s
s
i
b
i
l
is
ti
c
l
o
g
ic
wi
t
h
a
M
u
l
t
i
la
y
e
r
Pe
r
c
e
p
t
r
o
n
(
M
L
P
)
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
e
m
o
t
i
o
n
-
c
o
n
t
e
x
t
u
a
l
i
d
e
n
ti
f
i
c
at
io
n
i
n
c
o
g
n
i
t
i
v
e
a
i
d
s
e
r
v
ic
e
s
.
B
e
tt
i
n
i
e
t
a
l
.
[
68
]
,
b
y
c
o
m
b
i
n
i
n
g
s
e
m
i
-
s
u
p
e
r
v
is
e
d
Evaluation Warning : The document was created with Spire.PDF for Python.