T
E
L
KO
M
N
I
KA
T
e
lec
om
m
u
n
icat
ion
,
Com
p
u
t
i
n
g,
E
lec
t
r
on
ics
an
d
Cont
r
ol
Vol.
18
,
No.
1
,
F
e
br
ua
r
y
2020
,
pp.
317
~
331
I
S
S
N:
1693
-
6930,
a
c
c
r
e
dit
e
d
F
ir
s
t
G
r
a
de
by
Ke
me
nr
is
tekdikti
,
De
c
r
e
e
No:
21/E
/KP
T
/2018
DO
I
:
10.
12928/
T
E
L
KO
M
NI
KA
.
v18i1.
12434
317
Jou
r
n
al
h
omepage
:
ht
tp:
//
jour
nal.
uad
.
ac
.
id/
index
.
php/T
E
L
K
OM
N
I
K
A
S
m
ar
t
h
e
al
t
h
m
on
ito
r
in
g syst
e
m
u
si
n
g I
o
T
b
ase
d
s
m
ar
t
f
itn
e
ss mir
r
or
Am
gad
M
u
n
e
e
r
1
,
S
u
li
m
an
M
oh
am
e
d
F
a
t
i
2
,
S
ad
d
am
F
u
d
d
ah
3
1,
3
Sch
o
o
l
o
f
Mech
a
t
ro
n
i
c
s
E
n
g
i
n
eeri
n
g
,
A
s
i
a
Pac
i
fi
c
U
n
i
v
ers
i
t
y
o
f
T
ec
h
n
o
l
o
g
y
&
In
n
o
v
a
t
i
o
n
,
Mal
a
y
s
i
a
2
Co
l
l
eg
e
o
f
C
o
mp
u
t
er
an
d
In
f
o
rm
at
i
o
n
Sci
en
ce
s
,
Pri
n
c
e
Su
l
t
a
n
U
n
i
v
ers
i
t
y
,
Sau
d
i
A
ra
b
i
a
Ar
t
icle
I
n
f
o
AB
S
T
RA
CT
A
r
ti
c
le
h
is
tor
y
:
R
e
c
e
ived
J
a
n
25
,
2019
R
e
vis
e
d
Nov
2
5
,
20
19
Ac
c
e
pted
De
c
25
,
20
19
T
h
e
s
mar
t
fi
t
n
e
s
s
m
i
rro
r
p
ro
p
o
s
ed
i
n
t
h
i
s
re
s
earch
a
i
ms
t
o
p
r
o
v
i
d
e
t
h
e
u
s
er
s
w
i
t
h
a
p
l
a
t
fo
r
m
t
o
m
o
n
i
t
o
r
t
h
ei
r
h
ea
l
t
h
an
d
fi
t
n
e
s
s
s
t
a
t
u
s
o
n
a
d
a
i
l
y
b
a
s
i
s
.
T
h
e
s
y
s
t
em
emp
l
o
y
s
a
n
u
m
b
er
o
f
s
en
s
o
rs
t
o
mo
n
i
t
o
r
t
h
e
b
o
d
y
mas
s
i
n
d
ex
(BMI)
an
d
amo
u
n
t
o
f
b
o
d
y
fa
t
p
re
s
e
n
t
i
n
t
h
e
u
s
er’
s
b
o
d
y
.
A
w
e
i
g
h
t
s
ca
l
e
co
n
s
i
s
t
i
n
g
o
f
fo
u
r
l
o
a
d
s
en
s
o
rs
h
a
s
b
een
i
m
p
l
eme
n
t
e
d
t
o
o
b
t
ai
n
t
h
e
w
e
i
g
h
t
o
f
t
h
e
u
s
er
w
h
erea
s
an
u
l
t
ras
o
n
i
c
s
e
n
s
o
r
h
a
s
b
ee
n
u
s
ed
t
o
meas
u
re
t
h
e
h
ei
g
h
t
o
f
t
h
e
u
s
er.
In
ad
d
i
t
i
o
n
,
fo
u
r
el
ec
t
ro
d
e
p
l
a
t
es
h
av
e
b
ee
n
i
m
p
l
eme
n
t
e
d
o
n
t
h
e
fo
o
t
w
ei
g
h
t
s
cal
e
t
o
i
n
f
u
s
e
a
s
ma
l
l
am
o
u
n
t
o
f
el
ect
r
i
c
cu
r
ren
t
(1
m
A
)
fo
r
BI
A
(
b
i
o
el
ec
t
ri
ca
l
i
mp
e
d
an
ce
an
a
l
y
s
i
s
)
t
o
es
t
i
ma
t
e
t
h
e
a
mo
u
n
t
o
f
b
o
d
y
fat
p
ercen
t
ag
e,
l
ean
b
o
d
y
mas
s
an
d
t
o
t
al
b
o
d
y
w
at
er.
A
n
IR
t
emp
erat
u
re
s
e
n
s
o
r
h
as
b
een
i
m
p
l
eme
n
t
e
d
i
n
t
h
e
res
earc
h
t
o
meas
u
re
t
h
e
t
emp
erat
u
re
o
f
t
h
e
u
s
er’
s
b
o
d
y
fro
m
t
h
e
fo
reh
e
ad
.
T
es
t
s
co
n
d
u
c
t
ed
o
n
t
h
e
s
y
s
t
em
i
l
l
u
s
t
rat
e
t
h
a
t
i
t
i
s
a
b
l
e
t
o
accu
ra
t
el
y
co
m
p
u
t
e
t
h
e
b
o
d
y
mas
s
i
n
d
e
x
an
d
p
erfo
rm
a
b
i
o
el
ec
t
ri
ca
l
i
mp
e
d
an
ce
an
al
y
s
i
s
o
n
t
h
e
u
s
er.
T
h
e
s
y
s
t
e
m
i
s
ab
l
e
t
o
ac
h
i
e
v
e
a
9
2
.
5
%
a
n
d
9
3
.
7
%
accu
r
acy
i
n
d
et
erm
i
n
i
n
g
t
h
e
b
o
d
y
mas
s
i
n
d
e
x
an
d
b
o
d
y
fat
p
ercen
t
ag
e
re
s
p
ec
t
i
v
el
y
.
A
n
acc
u
racy
o
f
9
5
.
3
%
w
as
o
b
s
erv
e
d
i
n
t
h
e
d
e
t
ermi
n
at
i
o
n
o
f
t
h
e
b
o
d
y
t
emp
era
t
u
r
e.
K
e
y
w
o
r
d
s
:
B
ody
m
a
s
s
i
nde
x
I
nter
ne
t
of
t
hings
(
I
oT
)
P
e
r
s
ona
l
h
e
a
lt
hc
a
r
e
S
mar
t
f
it
ne
s
s
m
ir
r
or
S
mar
t
h
ome
Th
i
s
i
s
a
n
o
p
en
a
c
ces
s
a
r
t
i
c
l
e
u
n
d
e
r
th
e
CC
B
Y
-
SA
l
i
ce
n
s
e
.
C
or
r
e
s
pon
din
g
A
u
th
or
:
S
uli
man
M
oha
med
F
a
ti
,
C
oll
e
ge
of
C
omput
e
r
a
nd
I
nf
o
r
mation
S
c
ienc
e
s
,
P
r
ince
S
ult
a
n
Unive
r
s
it
y,
11586,
R
iyadh,
S
a
udi
Ar
a
bia
.
E
mail:
s
mf
a
ti
@ya
hoo.
c
om
1.
I
NT
RODU
C
T
I
ON
W
it
h
the
mas
s
ive
a
dva
nc
e
ment
in
I
T
f
ield
s
uc
h
a
s
I
nter
ne
t
of
thi
ngs
,
c
loud
c
omput
ing
,
a
nd
da
ta
a
na
lyt
ics
,
s
e
lf
he
a
lt
h
c
a
r
e
(
S
HC
)
is
ge
tt
ing
polp
ular
a
da
y
a
f
te
r
da
y.
S
e
lf
he
a
lt
h
c
a
r
e
(
S
HC
)
r
e
f
e
r
s
to
a
ll
the
a
c
ti
vit
ies
c
a
r
r
ied
out
by
the
indi
vdua
ls
to
mon
i
tor
their
he
a
lt
h
without
pr
of
e
s
s
ional
a
s
s
is
tanc
e
r
e
lyi
ng
on
a
dvice
s
a
nd
pa
s
t
e
xpe
r
ienc
e
s
[
1]
.
Now
a
dys
,
s
e
lf
he
a
lt
h
c
a
r
e
(
S
HC
)
be
c
a
me
r
e
c
e
ntl
y
a
gr
owing
in
dus
tr
y
a
ll
ove
r
the
wor
ld
[
2]
pa
r
ti
c
ular
ly
,
with
the
mas
s
ive
a
va
il
a
bil
it
y
of
s
mar
t
a
nd
we
r
a
ble
de
vice
s
.
S
HC
ga
ins
it
s
im
por
tanc
e
f
r
om
the
c
ons
ider
a
ble
r
e
duc
ti
on
in
c
os
t
s
that
may
be
incu
r
r
e
d
f
or
pa
ti
e
nts
a
nd
a
ls
o
f
o
r
c
a
r
e
giver
s
’
c
ompanie
s
[
3,
4]
.
No
e
xtr
a
c
ha
r
ge
s
r
e
late
d
to
h
os
pit
a
li
z
a
ti
on,
tr
a
ns
p
or
tation,
a
nd
f
a
c
il
it
ies
.
T
he
hos
pit
a
l
pr
ovidi
ng
HH
C
s
e
r
vice
s
will
r
e
s
ha
pe
the
r
e
gular
c
ons
ult
a
nt
with
high
qua
li
ty
o
f
s
a
ti
s
f
a
c
ti
on
c
a
r
e
f
or
pa
ti
e
nts
.
I
n
[
5
]
a
uthor
s
c
onc
lude
that
S
HC
s
e
r
vice
s
a
r
e
les
s
e
xpe
ns
ive
c
ompar
e
d
with
the
hos
pit
a
l
s
e
r
vice
s
.
P
r
ovidi
ng
medic
a
l
s
e
r
vice
a
t
home
a
nd
a
wa
y
f
r
o
m
t
r
a
dit
ional
he
a
lt
hc
a
r
e
f
a
c
il
i
ti
e
s
wa
s
e
na
bled
by
s
e
ve
r
a
l
e
na
bler
s
mainly
inf
or
mation
tec
hnology
(
I
T
)
[
6
,
7]
.
I
T
tec
hnologi
e
s
dis
r
upti
ng
he
a
lt
hc
a
r
e
f
ields
include
int
e
r
ne
t
of
thi
ngs
(
I
oT
)
[
8
-
12]
na
med
a
ls
o
int
e
r
ne
t
o
f
he
a
lt
h
thi
ngs
,
bod
y
a
r
e
a
ne
t
wo
r
k
[
1
3]
,
c
loud
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
1693
-
6930
T
E
L
KO
M
NI
KA
T
e
lec
omm
un
C
omput
E
l
C
ontr
o
l
,
Vol.
18
,
No
.
1
,
F
e
br
ua
r
y
2020
:
317
-
331
318
platf
or
ms
[
1
,
14]
,
big
da
ta
[
14
,
15]
a
nd
s
e
r
vice
r
o
boti
c
s
a
nd
dr
one
s
[
16,
17
]
.
A
va
r
iety
of
I
T
e
na
bl
e
d
HH
C
s
olut
ions
we
r
e
pr
opos
e
d
s
u
c
h
e
-
h
e
a
lt
h
[
5]
,
s
mar
t
he
a
lt
h
c
a
r
e
a
nd
s
mar
t
e
nvir
onments
li
ke
S
P
HE
R
E
a
nd
PL
AI
M
OS,
we
-
c
a
r
e
,
c
a
r
e
Ne
t
a
nd
B
E
S
I
[
8
,
9
,
12
,
1
6
-
19]
,
m
-
he
a
lt
h
[
10]
a
nd
tele
-
he
a
lt
h
[
14]
.
M
il
lennia
ls
in
today’
s
s
oc
iety
a
r
e
c
ons
tantly
dis
tr
a
c
ted
with
va
r
ious
is
s
ue
s
in
the
de
ve
lopi
ng
s
oc
iety
that
li
tt
le
or
no
a
tt
e
nti
on
is
dir
e
c
ted
towa
r
ds
maint
a
ini
ng
a
he
a
lt
hy
li
f
e
s
tyl
e
.
P
oo
r
l
if
e
s
tyl
e
s
c
ha
r
a
c
ter
ize
d
with
poor
e
a
ti
ng
ha
bit
s
,
f
it
ne
s
s
r
outi
ne
s
a
nd
r
e
s
t
ha
ve
made
mos
t
pe
ople
in
the
c
ur
r
e
nt
c
e
ntur
ies
pr
one
t
o
he
a
lt
h
r
is
ks
a
nd
is
s
ue
s
.
B
e
s
ides
,
the
wr
ong
ha
bit
s
may
c
a
us
e
a
s
igi
nif
a
c
nt
inc
r
e
a
s
e
in
c
hr
onic
dis
e
a
s
e
s
.
T
hu
s
,
h
e
a
lt
h
is
s
ue
s
r
e
late
d
to
poor
f
it
ne
s
s
ha
ve
be
c
ome
a
r
a
ging
pr
oblem
in
the
c
ur
r
e
nt
wor
ld
whe
r
e
by
a
v
a
r
iety
of
li
f
e
-
thr
e
a
te
ning
a
il
ments
a
nd
dis
e
a
s
e
s
a
r
e
be
ing
de
tec
ted
e
a
c
h
da
y.
M
o
s
t
of
the
he
a
lt
h
is
s
ue
s
e
xp
e
r
ienc
e
d
da
il
y
or
igi
na
te
mainly
f
r
om
poor
e
a
ti
ng
ha
bit
s
,
lac
k
of
e
xpos
ur
e
to
he
a
lt
h
a
nd
f
it
ne
s
s
e
xe
r
c
i
s
e
s
[
20
]
.
I
n
the
pa
s
t
a
lot
o
f
e
f
f
or
ts
ha
ve
be
e
n
made
to
e
ns
ur
e
that
thes
e
dis
e
a
s
e
s
a
r
e
c
ontr
o
ll
e
d
a
nd
t
r
e
a
ted
with
e
a
s
e
s
uc
h
a
s
c
onduc
ti
ng
f
r
e
que
nt
vis
it
s
to
the
doc
tor
a
nd
e
ns
ur
ing
that
pr
ope
r
f
e
e
ding
ha
bit
s
s
uc
h
a
s
s
tr
ict
diets
a
r
e
f
oll
owe
d.
B
ut
in
or
de
r
to
a
c
hieve
thi
s
e
a
r
ly
de
tec
ti
on
of
the
dis
e
a
s
e
s
is
r
e
quir
e
d
thr
ough
e
f
f
icie
nt
pe
r
iodi
c
moni
tor
ing
a
nd
c
oll
e
c
ti
on
o
f
he
a
lt
h/f
i
tnes
s
da
ta.
Ac
quis
it
ion
of
pe
r
iodi
c
r
e
a
l
ti
me
f
it
ne
s
s
a
nd
he
a
lt
h
da
t
a
is
a
c
ompl
e
x
tas
k
that
is
s
igni
f
ica
nt
in
o
r
de
r
to
identif
y
he
a
lt
h
is
s
ue
s
a
f
f
e
c
ti
ng
the
us
e
r
.
One
wa
y
of
e
ns
ur
ing
that
he
a
lt
h/f
it
ne
s
s
da
ta
of
the
us
e
r
is
a
c
c
e
s
s
e
d
is
by
int
e
gr
a
ti
ng
a
n
I
o
T
ba
s
e
d
s
mar
t
mi
r
r
o
r
tec
hnology
a
nd
wir
e
les
s
s
e
ns
or
s
in
moni
tor
ing
th
e
r
e
a
l
ti
me
he
a
lt
h/f
it
ne
s
s
s
tate
of
the
us
e
r
a
s
pr
opos
e
d
in
t
h
is
s
tudy.
T
his
s
tudy
highl
ight
s
the
de
ve
lopm
e
nt
of
a
s
mar
t
m
ir
r
o
r
that
is
c
onne
c
ted
to
s
mar
t
de
vice
s
f
o
r
the
pur
pos
e
s
of
of
f
e
r
ing
a
dva
nc
e
s
f
unc
ti
ona
li
ty
s
uc
h
a
s
moni
tor
ing
the
he
a
lt
h
of
it
s
us
e
r
s
.
T
he
pr
opos
e
d
s
mar
t
mi
r
r
or
will
he
lp
in
p
r
ovidi
ng
a
n
innov
a
ti
ve
uniq
ue
platf
or
m
f
or
us
e
r
s
to
mon
it
or
their
he
a
lt
h
f
i
tn
e
s
s
s
tatus
with
s
e
lf
-
a
da
pti
ng
f
e
a
tur
e
s
by
e
mpl
oying
wir
e
les
s
s
m
a
r
t
s
e
ns
or
s
a
nd
c
omput
e
r
vis
ion.
A
number
of
li
ter
a
tur
e
s
ha
s
be
e
n
r
e
vie
we
d
ba
s
e
d
on
the
de
ve
lop
ment
a
nd
a
ppli
c
a
ti
on
of
s
mar
t
mi
r
r
or
s
.
Va
r
ious
r
e
s
e
a
r
c
he
r
s
ha
ve
uti
li
z
e
d
s
e
ve
r
a
l
a
ppr
oa
c
he
s
to
de
ve
lop
s
ma
r
t
mi
r
r
or
s
ba
s
e
d
on
I
oT
us
ing
R
a
s
pbe
r
r
y
pi.
T
h
e
s
tudi
e
s
pr
opos
e
d
in
the
li
te
r
a
tur
e
r
e
view
e
d
ha
ve
include
d
s
ome
f
e
a
tur
e
s
s
uc
h
a
s
ti
me,
da
te
,
ne
ws
,
we
a
ther
upda
tes
a
nd
c
a
lenda
r
.
L
it
tl
e
or
n
o
e
f
f
or
t
ha
s
be
e
n
made
on
de
ve
lopm
e
nt
of
f
i
tnes
s
a
nd
he
a
lt
h
ba
s
e
d
s
ma
r
t
mi
r
r
or
e
xc
e
pt
f
or
two
s
tudi
e
s
whic
h
moni
tor
the
us
e
r
we
ight
only.
T
he
r
e
f
or
e
,
thi
s
s
tudy
will
f
oc
us
on
the
im
pleme
ntation
of
f
it
ne
s
s
f
e
a
tur
e
s
a
nd
he
a
lt
h
moni
tor
ing
a
s
we
ll
a
s
f
a
c
e
r
e
c
og
nit
ion
to
a
ll
ow
the
s
ys
tem
to
c
onti
nuous
ly
moni
tor
the
he
a
lt
h
of
a
pa
r
ti
c
ular
us
e
r
ove
r
t
im
e
.
T
hus
,
s
ome
of
the
r
e
s
e
a
r
c
h
que
s
ti
ons
that
will
be
c
ons
ider
e
d
in
the
de
ve
lopm
e
nt
of
the
pr
opos
e
d
f
it
ne
s
s
moni
tor
ing
s
ys
tem
include
:
−
W
ha
t
tr
a
it
s
will
be
us
e
d
to
mo
ni
tor
the
he
a
lt
h/f
it
ne
s
s
of
the
us
e
r
?
−
W
ha
t
s
e
ns
or
s
will
be
us
e
d
to
c
oll
e
c
t
r
e
a
l
ti
me
he
a
lt
h/f
it
ne
s
s
da
ta?
−
W
ha
t
type
a
nd
s
ize
of
mi
r
r
o
r
wil
l
be
us
e
d?
−
W
ha
t
I
o
T
tec
hnology
will
be
us
e
d
to
s
e
nd
a
nd
r
e
c
e
ive
he
a
lt
h/f
it
ne
s
s
da
ta?
−
W
ha
t
tec
hniques
will
be
us
e
d
to
i
de
nt
if
y
a
pa
r
ti
c
ul
a
r
us
e
r
?
−
W
ha
t
type
of
e
mbedde
d
ha
r
dwa
r
e
s
ys
tem
will
be
u
s
e
d
to
a
na
lyze
the
he
a
lt
h/f
it
ne
s
s
da
ta?
2.
RE
L
AT
E
D
WORKS
2.
1.
S
e
lf
h
e
alt
h
c
ar
e
s
ys
t
e
m
s
I
n
thi
s
s
e
c
ti
on
we
dis
c
us
s
the
wa
y
to
c
on
s
tr
uc
t
a
s
e
lf
-
diagnos
ti
c
s
ys
tem.
M
im
e
[
10
]
is
a
home
table
t
-
ba
s
e
d
movi
e
s
s
ys
tem
a
dde
d
to
a
ugmente
d
r
e
a
li
ty
s
ubs
ys
tem.
T
he
a
uthor
r
e
po
r
ted
the
us
e
r
e
x
pe
r
ienc
e
with
s
uc
h
s
e
tup
in
both
a
s
s
is
ted
a
nd
un
-
a
s
s
is
ted
us
ing
"
blood
t
e
s
ti
ng"
e
xpe
r
im
e
nts
.
He
de
s
c
r
ibed
the
us
e
r
e
xpe
r
ienc
e
s
in
us
ing
the
movi
e
s
to
guide
the
pa
ti
e
n
ts
.
Ata
ll
a
h
e
t
a
l
[
11
]
pr
opos
e
d
a
home
a
s
s
is
tant
s
ys
t
e
m
to
a
da
pt
to
ne
e
dy
older
pa
ti
e
nts
to
im
pr
ove
their
a
utonom
y
a
t
home,
a
nd
les
s
e
n
their
de
pe
nde
nc
e
o
n
other
pe
ople.
T
he
s
olut
ion
is
pr
oa
c
ti
ve
home
m
onit
or
ing
s
ys
tem
that
a
da
pts
to
us
e
r
ha
bit
s
.
T
he
y
us
e
d
c
las
s
if
ica
ti
on
a
nd
c
lus
ter
ing
a
lgor
it
hms
f
or
a
c
ti
vit
y
r
e
c
ognit
ion.
Author
s
in
[
12
]
de
s
c
r
ibed
a
c
loud
-
ba
s
e
d
s
mar
t
home
e
nvir
onment
f
o
r
home
he
a
lt
hc
a
r
e
.
T
he
y
u
s
e
d
I
oT
de
vice
s
to
c
oll
e
c
t
da
ta
thr
oug
h
home
we
a
r
a
ble
s
e
ns
or
s
a
nd
medic
a
l
c
ontextua
l
da
ta.
A
s
mar
t
home
ga
tew
a
y
wa
s
then
us
e
d
to
s
e
nd
thes
e
da
ta
to
a
pr
ivate
c
loud.
T
his
c
loud
wa
s
make
a
va
il
a
ble
to
r
e
mate
he
a
lt
hc
a
r
e
pr
ovider
s
.
I
n
[
13
]
Hos
s
a
in
e
t
a
l
pr
o
pos
e
d
a
s
mar
t
home
he
a
lt
h
c
a
r
e
s
ys
tem
f
or
e
lder
ly
pe
ople.
T
he
s
ys
tem
us
e
s
mul
ti
modal
s
pe
e
c
h,
a
nd
video
a
long
with
oth
e
r
I
o
T
's
s
e
ns
or
s
to
c
onti
nuous
ly
c
a
ptur
e
thes
e
da
t
a
s
tr
e
a
m
to
a
pr
ivate
c
loud
.
C
las
s
if
ica
ti
on
s
c
or
e
s
a
r
e
c
omput
e
d
in
the
c
loud
on
the
pa
ti
e
nt
c
ondit
ion
a
nd
c
on
ve
ye
d
to
the
c
a
r
e
give
r
s
.
Anothe
r
s
ys
tem
ba
s
e
d
on
c
loud
te
c
hnology
wa
s
dis
c
u
s
s
e
d
in
[
15]
.
C
loud
a
s
s
is
ted
b
ody
a
r
e
a
ne
twor
k
f
or
s
mar
t
home
he
a
lt
hc
a
r
e
us
e
d
by
home
pa
ti
e
nts
.
I
t
s
tor
e
s
,
pr
oc
e
s
s
,
a
nd
a
na
lys
e
da
ta
s
tr
e
a
ms
f
r
om
the
wir
e
les
s
s
m
a
r
t
home
I
o
T
de
vice
s
.
T
he
y
p
r
e
s
e
nted
a
c
l
oud
r
e
s
our
c
e
a
ll
oc
a
ti
on
s
tr
a
tegy
b
a
s
e
d
on
a
ge
nt
-
ba
s
e
d
modeling
a
nd
on
tol
ogy
to
s
uppor
t
d
iver
s
e
C
AB
AN
a
ppli
c
a
ti
ons
.
M
or
ove
r
,
a
n
e
mot
io
n
-
a
wa
r
e
c
onne
c
ted
he
a
lt
hc
a
r
e
s
ys
tem
[
18]
us
e
d
dif
f
e
r
e
nt
I
o
T
de
vice
s
to
c
oll
e
c
t
s
t
r
e
a
ms
o
f
da
ta
f
r
om
pa
ti
e
nt
in
a
s
mar
t
hom
e
he
a
lt
hc
a
r
e
f
a
c
il
it
y.
T
his
wa
s
f
e
d
int
o
a
n
e
mot
ion
de
tec
ti
on
a
lgor
it
hm
.
B
oth
s
pe
e
c
h
a
nd
im
a
ge
d
a
ta
we
r
e
us
e
d.
T
he
y
then
f
us
e
d
to
p
r
oduc
e
f
inal
s
c
or
e
s
of
th
e
e
mot
ion.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KO
M
NI
KA
T
e
lec
omm
un
C
omput
E
l
C
ontr
o
l
Smar
t
he
alt
h
monitor
ing
s
y
s
tem
us
i
ng
I
o
T
bas
e
d
s
mar
t
fi
tnes
s
mir
r
o
r
(
A
mgad
M
une
e
r
)
319
Ve
r
ís
s
im
o
e
t
a
l
[
14
]
p
r
e
s
e
nted
a
ub
iqui
tous
he
a
lt
hc
a
r
e
a
nd
a
c
ti
vit
y
moni
tor
ing
s
ys
tem
th
r
ough
r
e
c
ognizing
pa
ti
e
nt's
r
e
a
l
-
ti
me
a
c
ti
vit
ies
.
T
he
pr
o
pos
e
d
s
ys
tem
is
ba
s
e
d
on
s
pa
ti
otempor
a
l
mi
ning
t
e
c
hnique
to
buil
d
a
n
a
c
ti
vit
y
pr
e
diction
model.
A
mi
c
r
o
-
a
ggr
e
ga
ti
on
a
ppr
oa
c
h
wa
s
us
e
d
to
e
nha
nc
e
the
pr
ivac
y
o
f
the
c
oll
e
c
ted
a
ppr
oa
c
h
human
s
e
ns
e
d
da
ta.
A
s
ma
r
t
in
home
mon
it
or
ing
s
ys
tem
[
21
]
wa
s
im
pleme
nte
d
to
he
lp
e
lder
ly
a
nd
tr
a
c
k
thei
r
a
c
ti
ons
.
I
t
is
a
n
I
oT
s
e
ns
or
y
s
ys
tem
r
un
by
a
f
uz
z
y
c
ont
r
oll
e
r
.
T
he
s
e
t
o
f
f
uz
z
y
r
ules
a
r
e
wr
it
ten
by
s
pe
c
ialize
d
medic
a
l
s
t
a
f
f
.
T
he
r
ules
s
pe
c
if
y
a
f
us
ion
ba
s
e
d
a
r
c
hit
e
c
tur
e
.
A
s
im
il
a
r
s
ys
tem
wa
s
pr
e
s
e
nted
in
[
22
]
us
ing
a
c
onvolut
ional
ne
ur
a
l
ne
twor
k
model
f
or
pa
ti
e
nt
c
ons
ult
a
ti
on.
I
t
ha
s
high
dis
e
a
s
e
diagnos
is
pe
r
f
or
manc
e
.
I
t
e
na
bles
s
e
lf
-
c
he
c
king
of
the
us
e
r
's
he
a
lt
h
c
ondit
i
on
a
nd
f
low
up
with
him
on
a
r
e
gular
ba
s
i
s
.
C
e
r
tain
main
s
ympt
oms
,
pos
s
ibl
e
dis
e
a
s
e
s
c
a
n
be
pr
e
-
diagno
s
e
d.
O’
C
onnor
,
&
And
r
e
ws
[
16]
pr
e
s
e
nted
a
f
r
a
mew
o
r
k
to
a
s
s
e
s
s
the
qua
li
ty
of
onli
ne
he
a
lt
h
po
r
tals
in
As
ian
c
ountr
ies
a
ga
ins
t
HO
N
s
tanda
r
d.
T
he
ir
s
t
udy
c
ons
ider
e
d
J
a
pa
ne
s
e
,
Kor
e
a
n,
C
hines
e
,
a
nd
M
a
lay.
T
he
r
e
s
ult
s
howe
d
that
only
the
J
a
pa
ne
s
e
we
bs
it
e
s
ha
ve
highl
y
met
HO
N
s
tanda
r
ds
.
Author
s
in
[
17
]
pr
e
s
e
nted
a
n
e
nc
yc
lopae
dia
of
s
ympt
oms
/di
a
gn
os
is
in
C
hines
e
by
f
us
ing
medic
a
l
da
ta
e
xtr
a
c
t
e
d
f
r
o
m
mains
tr
e
a
m
C
hines
e
he
a
lt
hc
a
r
e
we
bs
it
e
s
.
S
a
did
Ha
s
a
n
e
t
a
l
[
18]
ha
s
pr
opos
e
d
a
kno
wle
dge
gr
a
p
h
c
li
nica
l
diagnos
is
a
lgor
it
hm
that
f
us
e
d
medic
a
l
knowle
dge
c
oll
e
c
ted
f
r
om
va
r
ious
s
our
c
e
s
.
T
he
s
ys
tem
wa
s
pr
ove
n
e
f
f
e
c
ti
ve
whe
n
c
ompar
e
d
to
the
s
tate
-
of
-
the
-
a
r
t
de
e
p
l
e
a
r
ning
c
li
nica
l
diagnos
is
s
ys
tems
.
T
he
is
s
ue
s
o
f
s
e
c
ur
it
y,
pr
ivac
y
of
medic
a
l
he
a
lt
hc
a
r
e
r
e
c
or
ds
we
r
e
a
ddr
e
s
s
e
d
in
[
16
-
19]
pa
r
ti
c
ull
a
r
y
in
wir
e
les
s
s
e
tup
s
.
M
a
r
ia
e
t
a
l
[
2
3]
us
e
d
k
-
media
n
s
c
lus
ter
ing
tec
hnique
with
s
ub
s
a
mpl
e
va
li
da
ti
on
to
f
latten
medic
a
l
r
e
c
or
ds
int
o
the
pa
ti
e
nt
leve
l.
Autho
r
s
in
[
17]
p
r
e
s
e
nted
a
c
las
s
if
ica
ti
on
method
to
c
las
s
if
y
medic
a
l
text
da
ta
f
ound
in
medic
a
l
r
e
c
or
ds
.
T
he
y
us
e
d
n
e
ur
a
l
ne
twor
k
a
lgor
it
hms
f
o
r
na
med
e
nti
ty
r
e
c
ognit
ion
in
C
hines
e
e
lec
tr
onic
medic
a
l
r
e
c
or
ds
.
I
n
[
19
]
a
ut
hor
s
ha
ve
i
de
nti
f
ies
c
li
nica
l
c
onc
e
pts
a
utom
a
ti
c
a
ll
y
f
r
om
medic
a
l
r
e
c
or
ds
us
ing
OC
R
a
nd
a
ppli
e
d
qua
nti
t
a
ti
ve
a
na
lys
is
.
Da
ta
we
r
e
c
oll
e
c
ted
f
r
om
medic
a
l
notes
,
lab
tes
t,
a
nd
othe
r
outs
ide
medic
a
l
r
e
c
or
ds
f
or
ve
r
i
f
ica
ti
on
a
nd
va
li
da
ti
on
pu
r
pos
e
s
.
2.
2.
I
n
t
e
r
n
e
t
of
h
e
alt
h
c
ar
e
t
h
in
gs
T
he
B
ody
a
r
e
a
ne
twor
k
in
[
2
4
]
is
the
f
r
ont
e
n
d
of
mobi
le
he
a
lt
hc
a
r
e
in
the
ne
w
pe
r
s
ona
li
z
e
d
he
a
lt
hc
a
r
e
tr
e
nd.
Va
r
it
y
of
body
s
e
ns
or
s
a
r
e
us
e
d
to
a
qui
r
e
s
ignals
f
r
om
the
pa
ti
e
nt
a
nd
tr
a
ns
f
e
r
them
to
his
/her
mobi
le
phone
f
or
c
oll
e
c
ti
ve
pr
oc
e
s
s
ing
of
da
ta.
S
e
ve
r
a
l
mobi
le
medic
a
l
a
pps
we
r
e
tes
t
a
nd
ve
r
if
ied.
T
he
wor
k
in
[
2
4
]
e
xa
mi
ne
s
a
number
o
f
F
DA
-
Appr
ove
d
mHe
a
lt
h
pr
oduc
ts
in
the
mar
ke
t
c
la
s
s
if
ied
in
to
s
e
ve
n
a
r
e
a
s
(
s
e
e
the
c
ha
r
t
a
bove
)
.
USA
,
C
hina,
T
a
iwa
n,
Aus
tr
a
li
a
,
C
a
na
da
,
Ne
w
Z
e
a
land,
a
nd
Ne
ther
l
a
nds
a
r
e
a
mong
the
lar
ge
s
t
pr
oduc
e
r
s
to
s
uc
h
pr
oduc
ts
.
2.
3.
M
ob
il
e
h
e
alt
h
c
ar
e
/m
e
d
ical
ap
p
s
M
e
dica
l
He
a
lt
h
pr
ogr
a
ms
s
uf
f
e
r
s
with
a
c
c
ur
a
c
y
of
their
a
lar
ms
,
B
e
n
Amor
a
nd
L
a
hya
ni
tr
ied
to
r
e
duc
e
d
f
a
ls
e
a
lar
ms
s
ignals
ge
ne
r
a
ted
by
medic
a
l
he
a
lt
h
pr
ogr
a
ms
a
nd
a
pps
with
us
ing
s
tatis
ti
c
a
l
methods
to
de
c
r
e
a
s
e
the
dim
e
ns
ions
of
a
lar
m
ge
ne
r
a
ti
ng
f
a
c
tor
s
while
s
im
ult
a
ne
ous
ly
p
r
e
s
e
r
ving
the
r
e
lev
a
nc
e
of
medic
a
l
he
a
lt
h
p
r
ogr
a
m
it
s
e
lf
.
T
he
y
incor
po
r
a
ted
incr
e
menta
l
p
r
incipa
l
c
omponent
a
na
lys
is
t
o
r
e
duc
e
the
dim
e
ns
ions
a
long
with
mul
ti
va
r
iate
a
nomaly
de
tec
ti
on
ba
s
e
d
up
on
s
qua
r
e
d
pr
e
diction
e
r
r
or
s
a
nd
a
nomalous
vit
a
l
s
ign
is
olation
f
o
r
c
ontr
ibut
ion
g
r
a
ph
[2
5
]
.
Sa
r
wa
r
e
t.
a
l
.
dis
c
ove
r
e
d
a
s
tr
ong
c
or
r
e
lation
be
twe
e
n
us
e
of
s
mar
t
phone
/devic
e
s
a
nd
da
ta
tr
a
ns
f
e
r
r
e
d
to
he
a
lt
h
c
a
r
e
p
r
ovider
s
th
r
ough
t
he
s
e
de
vice
s
.
M
He
a
lt
h
a
pps
a
r
e
dr
a
matica
ll
y
c
ha
nging
the
s
e
na
r
ios
of
c
li
nica
l
c
a
r
e
.
T
his
ne
w
s
e
tup
is
mu
c
h
lowe
r
in
c
os
t
a
nd
e
a
s
e
o
f
us
e
than
e
xis
ti
ng
s
e
tu
ps
[
2
6
]
.
S
odhr
o,
L
uo
a
nd
S
a
nga
iah
inves
ti
ga
ted
wa
ys
to
opti
mi
z
e
medic
a
l
da
ta
c
omm
unica
ti
on
tec
hniques
ove
r
5G
ne
twor
ks
.
T
his
is
ne
e
de
d
f
or
medic
a
l
da
ta
vis
ua
li
z
a
ti
on,
high
s
e
ns
ing
leve
ls
,
a
nd
be
tt
e
r
qua
li
ty
o
f
s
e
r
vice
.
W
indow
ba
s
e
d
r
a
te
c
ontr
ol
a
lgo
r
it
hm
is
s
ugge
s
ted
to
opti
mi
z
e
s
uc
h
tec
hniques
.
T
his
is
s
ometim
e
s
c
a
ll
e
d
e
dge
c
omput
ing
ba
s
e
d
he
a
lt
h
c
a
r
e
.
I
n
s
uc
h
s
e
tu
p,
ne
twor
k
pa
r
a
mete
r
s
us
e
d
we
r
e
'pe
a
k
-
to
-
mea
n',
s
tanda
r
d
de
viation,
de
lay,
a
nd
ji
tt
e
r
[
2
7
]
.
Onode
r
a
a
nd
S
e
ng
oku,
s
tudi
e
d
mar
ke
t
s
c
ope
of
mobi
le
h
e
a
lt
h
(
mHe
a
lt
h)
pr
ogr
a
ms
,
their
s
tudy
r
e
ve
a
ls
E
ur
ope
is
c
ur
r
e
ntl
y
l
e
a
ding
in
mHe
a
lt
h
ini
ti
a
ti
ve
s
a
nd
mar
ke
t
pa
r
ti
a
ll
y
be
c
a
us
e
of
he
a
vy
inves
tm
e
nt
a
nd
ini
ti
a
ti
ve
s
by
va
r
ious
g
ove
r
nment
a
ge
nc
ies
,
howe
ve
r
mar
ke
t
tr
e
nd
pr
e
d
i
c
t
s
tr
ong
gr
owth
s
ignals
f
r
om
As
ia
P
a
c
if
ic
r
e
gion
a
nd
L
a
ti
n
Ame
r
ica
a
s
we
ll
dur
ing
upc
o
mi
ng
ye
a
r
s
[
2
8
]
.
A
bus
ines
s
int
e
ll
igenc
e
a
s
s
e
s
s
ment
publi
s
he
d
by
B
I
S
r
e
s
e
a
r
c
h
viz.
"
Globa
l
mobi
le
medic
a
l
a
pps
mar
ke
t
-
a
na
lys
is
a
nd
f
or
e
c
a
s
t
,
2017
-
2025"
wor
ld
mobi
le
medic
a
l
a
pp
mar
ke
t
is
s
tea
dil
y
gr
owing
f
or
las
t
f
e
w
ye
a
r
s
a
nd
is
e
s
ti
mate
d
to
gr
ow
f
u
r
ther
with
p
e
r
s
is
tent,
c
ur
r
e
nt
s
oc
io
-
e
c
onomi
c
f
a
c
tor
s
in
ne
a
r
f
utu
r
e
.
E
s
ti
mate
d
va
lue
of
global
mobi
le
medic
a
l
a
pps
wa
s
1.
40
$
bil
li
on
du
r
ing
ye
a
r
2016
a
nd
is
pr
oje
c
ted
t
o
s
wung
by
11.
22
$
by
ye
a
r
s
2025.
Dr
iven
by
r
a
pidl
y
incr
e
a
s
ing
s
mar
tphone
mar
ke
t
a
nd
e
xpone
nti
a
l
pe
ne
tr
a
ti
on
of
mobi
le
phone
s
in
indi
vidual
li
ve
s
,
r
e
li
a
ble
a
nd
c
h
e
a
p
ne
twor
k
c
onne
c
ti
vit
y
with
a
dva
nc
e
4/5G
c
on
ne
c
ti
ons
,
inves
tm
e
nt
by
gove
r
nments
,
mHe
a
l
ths
ini
ti
a
t
ives
will
c
e
r
tainly
im
pr
ove
the
QoS
int
o
mobi
le
he
a
lt
h
c
a
r
e
s
e
gment
[
2
9
].
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
1693
-
6930
T
E
L
KO
M
NI
KA
T
e
lec
omm
un
C
omput
E
l
C
ontr
o
l
,
Vol.
18
,
No
.
1
,
F
e
br
ua
r
y
2020
:
317
-
331
320
2.
4.
S
m
ar
t
m
irr
or
in
S
HC
ap
p
li
c
at
ion
s
Now
a
da
ys
tec
hnology
ha
s
be
e
n
e
nha
n
c
e
d
to
make
human’
s
li
f
e
be
tt
e
r
a
nd
e
a
s
y.
T
he
r
e
a
r
e
many
tec
hnologi
e
s
uti
li
z
e
d
in
s
mar
t
mi
r
r
or
s
uc
h
a
s
de
e
p
lea
r
ning,
a
r
t
if
icia
l
int
e
ll
igenc
e
,
I
o
T
a
n
d
c
loud.
T
he
r
e
a
s
e
a
r
c
he
r
s
in
[
30
]
ha
ve
p
r
opos
e
d
a
s
mar
t
mi
r
r
or
f
or
phys
ica
ll
y
c
ha
ll
e
nge
d
pe
ople
ba
s
e
d
on
I
o
T
.
T
he
pr
opos
e
d
s
ys
tem
c
a
n
mana
ge
their
ti
me
a
nd
r
outi
ne
s
e
f
f
e
c
ti
ve
ly
a
nd
da
il
y
.
T
he
main
idea
of
t
h
e
wor
k
wa
s
to
de
s
ign
s
mar
t
m
ir
r
o
r
s
ys
tem
ba
s
e
d
R
a
s
pbe
r
r
y
P
i
a
long
wi
th
a
voice
r
e
c
ognit
ion
s
ys
tem
that
c
a
n
f
a
c
il
it
a
te
the
c
a
r
r
ying
out
of
s
mar
t
mi
r
r
o
r
.
L
a
s
tl
y,
the
pr
opos
e
d
s
ys
tem
im
pleme
nted
a
ll
kinds
of
r
e
a
l
tec
hnologi
e
s
that
c
a
n
he
lp
the
us
e
r
s
to
mana
ge
thei
r
ti
me.
Yus
r
i
e
t
a
l
,
[
31
]
pr
opos
e
d
a
s
mar
t
mi
r
r
or
f
o
r
s
m
a
r
t
li
f
e
r
e
s
e
a
r
c
he
r
c
omes
with
a
p
r
opos
e
d
s
ys
tem
c
a
ll
e
d
s
mar
t
mi
r
r
o
r
.
T
he
idea
be
hind
the
pr
opos
e
d
it
is
ba
s
e
d
on
I
o
T
a
nd
the
s
ys
tem
a
ll
ows
us
e
r
s
to
a
c
c
e
s
s
inf
or
mation
a
s
we
ll
a
s
c
ont
r
ol
the
hous
e
li
ghts
.
T
he
im
pleme
nted
met
hod
in
the
s
ys
tem
is
e
vo
lut
ionar
y
pr
otot
yping
whic
h
c
oll
e
c
ts
a
ll
r
e
quir
e
ments
a
nd
de
s
igns
the
s
ys
tem
in
a
f
a
s
t
wa
y.
T
he
tes
t
ing
ha
s
be
e
n
e
va
luate
d
with
the
ter
m
of
"
f
a
il
"
a
nd
"
s
uc
c
e
s
s
"
i
n
or
de
r
to
know
whe
ther
“
the
f
ield
ha
s
pe
r
f
or
me
d
we
ll
or
r
e
s
or
ted
int
o
f
a
il
ur
e
.
L
a
s
tl
y,
ther
e
a
r
e
s
ome
li
mi
tat
ion
in
[
31
]
s
uc
h
a
s
the
s
ys
tem
ne
e
d
s
im
pr
ove
ment
in
or
de
r
to
im
pleme
nt
a
ne
w
tec
hnol
ogy
on
s
mar
t
mi
r
r
o
r
a
nd
im
pleme
nted
other
f
unc
ti
ona
li
ty
that
ha
s
be
e
n
pr
opos
e
d
in
[
30
]
.
Anothe
r
wor
k
wa
s
pr
opos
e
d
by
[
32
]
whic
h
ha
s
dis
c
us
s
e
d
the
f
it
m
ir
r
o
r
,
a
s
mar
t
mi
r
r
o
r
f
or
h
e
a
lt
hc
a
r
e
li
ving.
T
he
idea
be
hind
thi
s
f
it
mi
r
r
o
r
is
to
a
f
f
e
c
t
t
he
f
e
e
li
ngs
o
f
the
us
e
r
in
a
pos
it
ive
wa
y
by
a
r
is
e
of
his
o
r
he
r
,
mood
mot
ivation
a
nd
f
e
e
li
ng
o
f
f
it
ne
s
s
.
Ac
c
or
ding
to
the
e
xpe
r
mi
ntal
r
e
s
ult
s
s
tate
d
that
f
it
m
ir
r
or
c
a
n
he
lp
pe
ople
to
ge
t
a
wa
ke
in
the
mor
ning
,
a
nd
r
a
i
s
e
their
mot
ivation
to
do
s
por
ts
.
B
e
s
ides
,
the
inv
e
s
ti
ga
ti
on
r
e
s
ult
s
s
tate
d
that
a
mong
43
us
e
r
s
839
va
li
d
s
e
ts
of
wor
kout
da
ta
we
r
e
r
e
tr
ieve
d.
Ne
ve
r
thele
s
s
,
due
to
tec
hnica
l
pr
oblems
the
da
ta
f
r
o
m
two
pa
r
ti
c
ip
a
nts
c
ould
not
be
us
e
d
f
or
a
ll
hypothes
e
s
.
M
or
e
ove
r
,
the
pa
r
ti
c
ipants
we
r
e
divi
de
d
int
o
th
r
e
e
un
li
ke
typ
e
s
of
a
thl
e
te,
whic
h
a
r
e
11
pa
r
ti
c
ipants
(
26
.
83%
)
ha
d
high,
24
mi
ddle
(
58
.
54%
)
a
nd
6
low
de
gr
e
e
s
(
14
.
63%
)
of
s
por
ts
mot
ivati
on.
R
e
a
s
e
r
a
c
he
r
s
in
[
33
]
ha
s
pr
e
s
e
nted
a
“
wiz
e
”
mi
r
r
or
,
“
a
plat
f
or
m
f
o
r
the
e
s
ti
mation
of
c
a
r
dio
-
meta
boli
c
r
is
k
f
r
om
s
e
ns
e
d
f
a
c
ial
da
ta
a
nd
the
de
li
ve
r
y
of
pe
r
s
ona
li
z
e
d
us
e
r
guidanc
e
towa
r
ds
li
f
e
s
tyl
e
c
ha
nge
”
.
T
he
pr
opos
e
d
“
wiz
e
”
mi
r
r
o
r
ha
s
a
n
a
dva
nc
e
d
s
e
ns
ing
f
e
a
tur
e
s
a
ge
nda
f
or
unr
e
mar
ka
bl
e
pur
c
ha
s
e
of
videos
,
i
mage
s
,
a
nd
3D
s
c
a
ns
of
ind
ivi
dua
ls
s
tanding
in
f
r
on
t
o
f
the
mi
r
r
o
r
.
T
he
“
w
ize
”
mi
r
r
o
r
invol
ve
a
mul
ti
s
pe
c
tr
a
l,
a
vis
ibl
e
c
a
mer
a
,
i
maging
s
ys
tem,
a
br
e
a
th
a
na
lys
is
s
tanda
r
d
de
vice
s
a
nd
3D
opti
c
a
l
s
e
ns
or
s
.
T
hus
,
the
mul
ti
s
pe
c
tr
a
l
im
a
ging
s
ys
tem
he
lps
to
a
na
lyze
the
mi
c
r
oc
i
r
c
ulation
a
nd
s
kin
ti
s
s
ue
.
F
or
e
mot
ional
a
na
lys
is
vis
ibl
e
c
a
mer
a
s
ha
s
be
e
n
ut
i
li
z
e
d,
in
or
de
r
to
de
dica
te
the
a
nxiety,
s
tr
e
s
s
a
nd
f
a
ti
gue
f
r
om
c
a
ptur
ing
video
s
e
que
nc
e
s
.
A
3D
s
c
a
n
i
mpl
e
mente
d
to
s
c
a
n
the
f
a
c
e
c
ha
nge
.
T
hus
,
ther
e
we
r
e
many
l
im
it
a
ti
ons
s
uc
h
a
s
the
a
c
c
ur
a
c
y
of
the
pr
opos
e
d
s
ys
tem
wa
s
low.
M
a
he
s
hw
a
r
i,
Ka
ur
&
Ana
nd
[
34
]
pr
opos
e
d
a
r
e
f
l
e
c
ti
ve
int
e
r
f
a
c
e
to
maximi
z
e
p
r
oduc
ti
vit
y
,
s
mar
t
mi
r
r
or
.
T
he
pr
opos
e
d
s
tudy
pr
e
s
e
nted
a
ne
w
de
s
ign
a
nd
de
ve
lopm
e
nt
of
a
s
mar
t
mi
r
r
or
that
s
igni
f
ies
a
n
e
lega
nt
int
e
r
f
a
c
e
f
or
s
lanting
inf
or
mation
f
or
mu
lt
ipl
e
pe
o
ple
in
a
home
e
nvir
onment
.
A
f
a
c
e
r
e
c
ognit
ion
a
ppr
oa
c
h
wa
s
uti
li
z
e
d
in
the
pr
opos
e
d
s
mar
t
mi
r
r
or
.
T
he
s
ys
tem
de
li
ve
r
s
a
we
bpa
ge
s
e
r
v
ice
s
in
or
de
r
to
a
c
c
e
s
s
inf
or
mation
f
e
e
ds
to
the
mi
r
r
or
.
T
he
s
ys
tem
de
ve
loped
include
d
a
R
a
s
pbe
r
r
y
pi
3
,
c
omput
e
r
a
nd
a
we
bc
a
m
f
or
f
a
c
e
de
tec
ti
on
wa
s
uti
li
z
e
d
a
s
we
ll
a
s
L
C
D
pa
n
e
l
in
or
de
r
to
s
how
the
int
e
r
f
a
c
e
.
T
he
r
e
f
or
e
,
the
main
ke
y
f
e
a
tur
e
s
a
nd
the
wo
r
king
p
r
inciple
of
the
pr
opos
e
d
s
ys
tem
a
s
f
oll
ow,
a
we
bc
a
m
us
e
d
be
hind
the
mi
r
r
or
f
a
c
ial
r
e
c
ognit
ion
to
r
e
c
ognize
the
pe
r
s
o
n
who
is
s
tanding
in
f
r
ont
of
the
s
mar
t
mi
r
r
o
r
.
T
he
o
pe
n
C
V
platf
or
m
us
e
d
f
or
mac
hine
vis
ion
pr
ogr
a
mi
ng.
L
a
s
tl
y,
the
main
li
mi
tation
o
f
the
pr
opos
e
d
s
ys
tem
s
ometim
e
s
the
mi
r
r
or
c
a
nnot
r
e
c
ognize
the
us
e
r
f
a
c
e
or
other
us
e
r
c
a
n
a
c
c
e
s
s
the
s
e
n
s
it
ive
da
ta
f
or
other
us
e
r
s
.
T
his
s
tudy
ne
e
ds
to
e
nha
nc
e
d
the
f
a
c
ial
r
e
c
ognit
ion
by
a
dd
a
high
s
e
c
ur
i
ty
.
Anothe
r
r
e
s
e
a
r
c
h
done
by
[
35
]
ha
s
pr
e
s
e
nted
a
n
int
e
r
a
c
ti
ve
s
mar
t
mi
r
r
or
ba
s
e
d
on
I
oT
platf
or
m
a
nd
R
a
s
pbe
r
r
y
pi
3.
T
he
p
r
opos
e
d
s
mar
t
mi
r
r
o
r
wa
s
de
s
igned
to
br
ing
tec
h
nology
s
e
a
ml
e
s
s
ly
int
o
pe
ople’
s
li
ve
s
to
mana
ge
their
ti
me
a
nd
da
il
y
r
outi
ne
s
.
T
his
s
ys
tem
us
e
d
f
or
us
e
r
pr
oduc
ti
vit
y
a
nd
e
f
f
e
c
ti
ve
ti
me
mana
ge
ment.
T
his
mi
r
r
or
wor
k
on
voice
r
e
c
ognit
ion
to
be
e
a
s
y
us
e
d
a
nd
it
a
c
c
e
pt
na
tur
a
l
langua
ge
.
B
a
s
e
d
on
the
c
onc
e
pt
o
f
I
oT
that
ha
s
be
e
n
im
pleme
nted
in
the
p
r
opos
e
d
s
ys
tem,
the
us
e
r
c
o
uld
c
omm
unica
te
with
the
e
nvi
r
onment
o
f
the
li
v
i
ng
-
r
oom
a
r
ound
him
e
a
s
il
y.
M
or
e
ove
r
,
in
the
de
ve
loped
GU
I
it
ha
s
be
e
n
de
s
ign
s
ome
icons
s
uc
h
a
s
holi
d
a
ys
,
ti
me
da
te,
we
a
ther
a
nd
ne
ws
.
How
e
ve
r
,
ther
e
we
r
e
s
o
me
li
mi
tations
in
the
p
r
opos
e
d
s
ys
tem,
f
or
e
xa
m
ple
whe
n
the
us
e
r
a
s
ks
the
s
mar
t
mi
r
r
or
a
bout
the
da
ta
ne
e
de
d
the
s
ys
tem
take
f
e
w
mi
nutes
to
r
e
s
pon
s
e
.
Als
o
the
s
ys
tem
r
e
quir
e
d
a
good
int
e
r
ne
t
c
onne
c
ti
on.
M
or
e
ove
r
,
the
a
uthor
s
in
[
3
5
]
pr
opos
e
d
a
n
int
e
r
a
c
ti
ve
s
mar
t
m
ir
r
o
r
with
va
r
ious
f
e
a
tur
e
s
to
make
s
ur
e
that
e
ve
r
y
mi
nute
of
the
us
e
r
is
uti
li
z
e
d
pr
ope
r
ly.
T
he
p
r
opos
e
d
s
mar
t
mi
r
r
or
a
ll
ows
us
e
r
s
to
us
e
a
home
objec
t
a
s
a
n
int
e
r
a
c
ti
ve
int
e
r
f
a
c
e
pr
ovidi
ng
c
us
to
mi
z
a
ble
s
e
r
vice
s
.
T
he
main
a
dva
ntage
o
f
thi
s
mi
r
r
or
is
to
tr
a
c
k
the
he
a
lt
h
of
the
us
e
r
whic
h
r
e
s
ult
s
in
a
he
a
lt
hy
li
f
e
.
T
he
de
ve
loped
mi
r
r
or
a
ble
to
dis
pl
a
y
the
r
e
a
l
ti
me
inf
or
mation
li
ke
the
we
a
ther
,
the
pa
r
t
icula
r
loca
ti
on
a
nd
da
y
today
s
c
he
dule
a
s
we
ll
a
s
the
ne
w
s
ha
ppe
ning
a
r
ound
th
e
wor
ld
.
B
e
s
ides
,
the
mos
t
im
por
tant
f
e
a
tur
e
in
the
pr
opos
e
d
mi
r
r
or
is
the
we
ight
tr
a
c
ke
r
that
c
a
n
tr
a
c
ke
d
the
us
e
r
we
ight
a
nd
make
s
ur
e
that
the
u
s
e
r
is
f
it
a
nd
dis
play
we
ight
of
the
us
e
r
in
the
da
i
ly
ba
s
is
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KO
M
NI
KA
T
e
lec
omm
un
C
omput
E
l
C
ontr
o
l
Smar
t
he
alt
h
monitor
ing
s
y
s
tem
us
i
ng
I
o
T
bas
e
d
s
mar
t
fi
tnes
s
mir
r
o
r
(
A
mgad
M
une
e
r
)
321
F
ur
ther
mor
e
,
the
s
ys
tem
c
a
n
a
ls
o
be
uti
li
z
e
d
th
e
window
bli
nds
a
nd
c
ontr
ol
li
ght
ing
in
the
r
oom
b
a
s
e
d
on
a
c
ontr
ol
of
s
ingl
e
po
int
.
Anothe
r
a
dva
ntage
of
thi
s
s
ys
tem
that
the
we
ight
a
nd
other
he
a
lt
h
c
ondit
ion
s
c
a
n
be
c
he
c
ke
d
li
ve
a
t
wha
teve
r
point
the
us
e
r
r
e
mains
on
a
he
a
p
c
e
ll
incor
po
r
a
ted
s
tool
.
T
his
will
ha
ve
the
c
a
pa
c
it
y
to
pr
opos
e
a
nd
pr
ope
l
the
us
e
r
to
de
c
r
e
a
s
e
we
ight
i
f
ne
e
de
d.
S
ir
ipala
e
t
a
l.
[
3
6
]
pr
opos
e
d
a
magi
c
s
mar
t
mi
r
r
o
r
to
moni
to
r
c
hil
dr
e
n
whi
le
their
pa
r
e
nts
a
t
wo
r
k.
T
he
s
mar
t
mi
r
r
or
de
ve
loped
ba
s
e
d
on
I
o
T
a
nd
it
i
mpl
e
mente
d
R
a
s
pbe
r
r
y
pi
.
T
his
mi
r
r
or
a
ls
o
im
ple
mente
d
a
s
mar
t
tec
hnology
whic
h
ha
s
the
a
bil
it
y
to
s
how
the
de
tails
to
the
us
e
r
us
ing
a
s
mar
t
pho
ne
with
a
ndr
oid
a
ppli
c
a
ti
on.
T
he
r
e
s
e
a
r
c
he
r
s
s
tate
d
that
the
pr
opos
e
d
s
mar
t
m
ir
r
o
r
is
ve
r
y
dif
f
e
r
e
nt
f
r
om
the
other
mi
r
r
or
that
ha
s
b
e
e
n
de
ve
loped
pr
e
vious
ly
with
f
e
w
f
e
a
tur
e
s
s
uc
h
a
s
ti
me,
da
te,
ne
ws
a
nd
we
a
ther
or
e
ve
n
the
w
e
ight
a
nd
other
he
a
lt
h
c
ondit
i
ons
.
T
he
R
a
s
pbe
r
r
y
magic
mi
r
r
or
is
mor
e
a
dva
nc
e
d
a
nd
int
e
r
a
c
ti
ve
whic
h
a
ll
ows
the
pa
r
e
nts
to
ke
e
p
tr
a
c
king
their
c
hil
dr
e
n
e
ve
n
thoug
h
they
a
r
e
in
the
wor
k,
they
c
a
n
ge
t
noti
f
ica
ti
o
n
to
their
s
mar
t
phone
us
ing
I
o
T
a
ppr
oa
c
h
that
ha
s
be
e
n
im
p
leme
nted
in
thi
s
s
tudy.
T
he
r
e
f
or
e
,
r
e
a
s
e
r
c
he
r
s
in
[
3
7
]
de
s
c
r
ibes
a
ne
w
d
e
s
ign
of
int
e
r
a
c
ti
ve
mi
r
r
or
.
T
he
de
ve
loped
s
mar
t
mi
r
r
or
identi
f
ies
the
us
e
r
a
c
c
or
ding
to
the
im
a
ge
pr
oc
e
s
s
ing
a
ppr
oa
c
h
a
nd
p
r
ovides
a
he
a
lt
h
pr
ogr
e
s
s
r
e
pr
e
s
e
ntation.
B
e
s
ides
,
the
he
a
lt
h
pa
r
a
mete
r
mea
s
ur
e
ment
a
nd
a
na
lys
is
he
lp
the
u
s
e
r
in
lea
ding
a
he
a
lt
hier
li
f
e
.
F
ur
the
r
mor
e
,
ther
e
s
e
ve
r
a
l
f
e
a
tur
e
s
ha
ve
be
e
n
e
xtr
a
c
ted
in
thi
s
s
ys
t
e
m
s
uc
h
a
s
e
mot
ion
r
e
c
ognit
ion,
mout
h
f
e
a
tu
r
e
e
xt
r
a
c
ti
on,
a
nd
he
a
lt
h
p
r
ogr
e
s
s
r
e
p
r
e
s
e
ntation
a
nd
m
ir
r
o
r
us
a
ge
ti
me.
I
t
ha
s
be
e
n
tas
ted
e
a
c
h
pa
r
t
in
o
r
de
r
to
a
na
lys
e
s
the
pe
r
f
or
manc
e
of
the
pr
opos
e
d
s
ys
tem.
How
e
ve
r
,
the
s
ys
tem
ha
s
be
e
n
tr
a
ined
with
42
im
a
ge
s
f
or
9
di
f
f
e
r
e
nt
pe
ople
a
nd
the
r
e
s
ult
o
f
the
s
ys
tem
wa
s
va
r
y
f
r
om
one
to
a
nother
whic
h
mea
ns
the
s
ys
tem
c
a
nnot
r
e
c
ognize
s
ome
us
e
r
a
nd
dis
play
a
s
a
ti
s
f
a
c
tor
y
r
e
s
ult
.
B
e
s
ides
that,
the
s
ys
tem
c
a
n
be
e
nha
nc
e
d
by
a
dd
s
ome
a
dva
nc
e
d
f
unc
ti
ona
li
ty
s
uc
h
a
s
s
pe
e
c
h
pr
oc
e
s
s
ing.
L
a
s
tl
y,
the
a
c
c
ur
a
c
y
of
the
e
mot
ion
r
e
c
ognit
ion
a
ppr
oa
c
h
ne
e
d
be
im
pr
ove
d
by
e
xtr
a
c
ti
ng
a
ddit
ional
f
e
a
tur
e
li
ke
e
ye
f
e
a
tur
e
.
I
n
s
umm
a
r
y,
s
mar
t
mi
r
r
or
s
c
omm
only
a
ll
ow
us
e
r
s
s
ome
c
us
tom
iza
ti
on
in
o
r
de
r
to
b
r
ing
a
pe
r
s
ona
li
z
e
d
s
e
r
vice
,
a
s
mar
t
mi
r
r
or
ne
e
ds
to
ide
nti
f
y
the
us
e
r
who
is
s
tanding
in
f
r
ont
o
f
it
.
T
hus
,
it
c
ould
a
c
c
e
s
s
a
nd
dis
play
the
us
e
r
’
s
pe
r
s
ona
l
i
n
f
or
mati
on
li
ke
his
o
r
he
r
s
c
he
dule
in
or
de
r
to
do
a
ppoi
ntm
e
nts
.
Automatic
a
ppr
oa
c
he
s
f
or
identif
ying
us
e
r
s
include
f
a
c
e
r
e
c
ognit
ion
[3
8
,
39
]
,
tag
-
ba
s
e
d
identif
ica
ti
on,
biom
e
tr
ic
da
ta,
a
nd
pe
r
s
ona
l
b
e
longi
ngs
s
uc
h
a
s
to
othbr
us
h
[
4
0
]
.
A
dif
f
e
r
e
nt
wor
k
[
4
1
]
pr
opos
e
d
the
im
p
leme
ntation
of
a
nth
r
opometr
y
a
nd
bioele
c
tr
ica
l
im
pe
da
nc
e
a
na
lys
is
a
s
int
e
r
c
ha
nge
a
ble
tec
hniques
f
or
a
s
s
e
s
s
ing
body
he
a
lt
h
of
s
por
ts
pe
r
s
ons
.
I
n
the
a
nth
r
o
pometr
y
a
na
lys
is
va
r
ious
ins
tr
uments
a
nd
e
quipm
e
nt
we
r
e
us
e
d
to
c
omput
e
body
de
ns
it
y
,
we
ight
a
nd
he
ight
whic
h
we
r
e
us
e
d
to
c
omput
e
body
f
a
t
pe
r
c
e
ntage
.
in
o
r
d
e
r
to
c
omput
e
bia,
a
f
oot
s
c
a
le
wa
s
us
e
d
c
ons
is
ti
n
g
of
two
e
lec
tr
ode
s
plac
e
d
pa
r
a
ll
e
l
to
e
a
c
h
oth
e
r
,
to
a
ll
ow
the
us
e
r
s
f
e
e
t
to
be
e
xpo
s
e
d
to
the
low
induction
c
ur
r
e
nt
f
or
im
pe
da
nc
e
a
na
lys
is
.
T
e
s
ti
ng
wa
s
c
onduc
ted
on
83
s
por
ts
a
thl
e
tes
whe
r
e
by
the
pe
r
c
e
ntage
of
body
f
a
t
wa
s
e
s
ti
mate
d
us
ing
B
I
A
a
nd
a
nthr
opometr
y
a
n
a
lys
is
.
T
he
int
e
r
na
l
c
ons
is
tenc
y
of
the
B
F
da
ta
wa
s
mea
s
ur
e
d
us
ing
P
e
a
r
s
on’
s
c
or
r
e
lation
.
R
e
s
ult
s
f
r
om
the
tes
ts
c
onduc
ted
il
lus
tr
a
te
that
a
be
tt
e
r
c
or
r
e
lation
c
o
e
f
f
icie
nt
wa
s
a
c
hieve
d
u
s
ing
bioele
c
tr
ica
l
im
pe
da
nc
e
a
na
lys
is
i.
e
.
14
.
78
±
9
.
29
whe
r
e
a
s
the
a
n
thr
opometr
y
a
na
lys
is
pr
oduc
e
d
a
c
or
r
e
lation
c
oe
f
f
icie
nt
o
f
13
.
08
±
5
.
T
he
de
s
ign
a
nd
a
na
lys
is
of
a
djus
table
c
ons
tant
c
ur
r
e
nt
s
our
c
e
with
mul
ti
f
r
e
que
nc
y
f
o
r
mea
s
ur
e
ment
of
bioele
c
tr
ica
l
im
pe
da
nc
e
ha
s
be
e
n
pr
opos
e
d
by
[
4
2
]
.
I
n
th
is
r
e
s
e
a
r
c
h
a
ha
nd
a
nd
f
oot
s
c
a
le
a
na
lyze
r
we
r
e
us
e
d
f
or
bioele
c
tr
ica
l
i
mpeda
nc
e
a
na
lys
is
whe
r
e
by
e
lec
tr
ode
s
us
e
d
f
or
mea
s
ur
e
ment
we
r
e
p
lac
e
d
a
s
the
f
r
ont
a
nd
r
e
a
r
s
oles
of
the
leg
whe
r
e
a
s
the
pa
lm
a
nd
thum
b
we
r
e
us
e
d
a
s
e
lec
tr
ode
c
ontac
t
s
f
or
the
ha
nds
.
A
s
im
il
a
r
wor
k
to
[
4
1
]
p
r
opo
s
e
d
by
[
4
3
]
in
or
de
r
to
us
e
o
f
bioele
c
tr
ica
l
i
mpeda
nc
e
a
na
lys
is
to
s
tudy
the
r
e
f
e
r
e
nc
e
va
lues
of
a
given
population
ba
s
e
d
o
n
thei
r
pha
s
e
a
ngle,
a
ge
a
nd
s
e
x.
B
I
A
wa
s
us
e
d
in
thi
s
s
tudy
to
c
omput
e
r
e
a
c
tanc
e
a
nd
r
e
s
is
tanc
e
whic
h
wa
s
then
us
e
d
a
s
a
pha
s
e
a
ngle
indi
c
a
tor
.
T
he
f
a
t
mas
s
wa
s
then
e
s
ti
mate
d
f
r
om
a
s
e
r
ies
of
pa
r
a
mete
r
s
c
ons
is
ti
ng
of
tot
a
l
body
wa
ter
,
we
ight
a
nd
hydr
o
d
e
ns
it
ometr
y
whic
h
we
r
e
then
im
pleme
nted
in
the
S
ir
i
e
qua
ti
on.
T
he
pha
s
e
a
ng
les
obtaine
d
f
r
om
the
e
qua
ti
on
we
r
e
then
c
ompa
r
e
d
ove
r
dif
f
e
r
e
nt
a
ge
s
,
s
e
xe
s
,
body
mas
s
index
(
B
M
I
)
.
F
in
dings
f
r
om
the
r
e
s
e
a
r
c
h
c
onduc
ted
by
[
4
1
]
s
howe
d
that
a
r
m
pos
tur
e
playe
d
a
s
i
gnif
ica
nt
r
ole
in
c
omput
ing
B
I
A
va
lues
.
B
e
nt
a
r
m
pos
tur
e
a
f
f
e
c
ted
the
f
low
o
f
th
e
c
ur
r
e
nt
whe
r
e
a
s
s
tr
e
tche
d
out
a
r
ms
pr
oduc
e
d
be
tt
e
r
r
e
s
ult
s
with
a
n
a
c
c
ur
a
c
y
o
f
92
.
4%
a
nd
mea
n
di
f
f
e
r
e
nc
e
of
±
0.
87%
.
I
n
a
ddit
ion,
the
s
ys
tem
wa
s
a
ble
to
wor
k
e
f
f
icie
ntl
y
be
t
we
e
n
f
r
e
que
nc
ies
of
50
a
nd
100
k
Hz
,
with
the
be
s
t
r
e
s
ult
s
obtaine
d
a
t
a
f
r
e
que
nc
y
of
85
k
Hz
.
T
he
r
e
s
e
a
r
c
he
r
s
howe
ve
r
r
e
c
omm
e
nde
d
that
f
ur
ther
r
e
s
e
a
r
c
h
s
hould
be
c
onduc
ted
to
s
tudy
the
im
pa
c
t
of
e
lec
tr
oly
te
wipe
s
on
the
e
f
f
e
c
ti
ve
ne
s
s
of
bioe
lec
tr
ica
l
im
pe
da
nc
e
a
na
lys
is
.
I
n
[
4
4
]
a
c
ompar
is
on
of
dif
f
e
r
e
nt
tec
hniques
us
e
d
to
mea
s
ur
e
body
c
ompos
it
ion
wa
s
c
onduc
ted.
I
n
thi
s
r
e
s
e
a
r
c
h,
two
tec
hniques
we
r
e
us
e
d
a
s
c
a
s
e
s
tudi
e
s
i.
e
.
bioele
c
tr
ica
l
im
pe
da
nc
e
a
na
lys
is
(
B
I
A)
a
nd
a
ir
dis
plac
e
ment
plethys
mogr
a
phy
(
AD
P
)
.
T
e
s
ti
ng
w
a
s
c
onduc
ted
on
41
pa
r
t
icipa
nts
on
two
di
f
f
e
r
e
nt
oc
c
a
s
ions
a
f
ter
a
n
ove
r
night
f
a
s
ti
ng
pe
r
iod
with
no
wa
ter
a
n
d
f
ood.
M
e
a
s
ur
e
m
e
nt
of
the
he
ight
,
we
ight
a
nd
pe
r
c
e
ntage
of
body
f
a
t
wa
s
then
c
a
r
r
ied
out
us
ing
the
two
a
pp
r
oa
c
he
s
i.
e
.
B
I
A
a
nd
AD
P
.
T
he
s
k
inf
o
ld
in
(
1
)
,
(
2
)
a
nd
(
3)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
1693
-
6930
T
E
L
KO
M
NI
KA
T
e
lec
omm
un
C
omput
E
l
C
ontr
o
l
,
Vol.
18
,
No
.
1
,
F
e
br
ua
r
y
2020
:
317
-
331
322
we
r
e
then
us
e
d
to
c
a
lcula
te
the
pe
r
c
e
ntage
o
f
B
F
(
body
f
a
t)
ba
s
e
d
on
the
va
lues
de
r
ived
f
r
om
the
two
a
ppr
o
a
c
he
s
i.
e
.
F
F
M
(
f
a
t
f
r
e
e
mas
s
(
Kg)
,
H
(
h
e
ight
(
c
m)
,
B
W
(
body
we
ight
(
Kg)
,
R
(
r
e
s
is
tanc
e
(
Ω
)
.
=
−
10
.
68
+
(
0
.
65
2
)
+
0
.
2
6
+
0
.
02
(
1)
=
−
(
2)
%
=
×
100%
(
3)
T
he
r
e
s
ult
s
obtaine
d
f
r
om
the
tes
ts
il
lus
tr
a
te
that
b
ot
h
s
ys
tems
ha
ve
a
high
c
or
r
e
lation
be
twe
e
n
them
whe
r
e
by
the
mea
n
dif
f
e
r
e
nc
e
obs
e
r
ve
d
f
r
om
B
I
A
a
nd
AD
P
wa
s
3.
1
%
a
nd
4
.
1%
r
e
s
pe
c
ti
ve
ly
whe
r
e
a
s
the
a
c
c
ur
a
c
y
wa
s
83.
2%
a
nd
78.
4%
f
o
r
B
I
A
a
nd
A
DP
r
e
s
pe
c
ti
ve
l
y.
T
he
tes
t
da
ta
f
r
om
th
is
r
e
s
e
a
r
c
h
i
ndica
ted
that
the
bioele
c
tr
ica
l
im
pe
da
nc
e
a
na
lys
is
(
B
I
A)
a
ppr
oa
c
h
wa
s
be
tt
e
r
than
the
a
ir
dis
pl
a
c
e
ment
plethys
mogr
a
phy
(
AD
P
)
.
I
n
[
4
5
]
a
bioele
c
tr
ica
l
im
pe
da
nc
e
a
na
lys
is
s
ys
tem
ha
s
be
e
n
pr
opos
e
d
to
e
va
l
ua
te
the
he
a
lt
h
of
poult
r
y
a
nd
e
ggs
.
B
I
A
wa
s
s
e
lec
ted
by
th
e
r
e
s
e
a
r
c
he
r
s
s
inc
e
it
pr
e
s
e
nts
a
pa
inl
e
s
s
a
nd
mor
e
a
c
c
ur
a
te
a
nd
non
-
invas
ive
a
ppr
oa
c
h
of
mea
s
ur
ing
poult
r
y
he
a
lt
h
a
t
di
f
f
e
r
e
nt
s
tage
s
of
their
li
f
e
c
yc
le.
Dur
in
g
tes
ti
ng
f
our
va
lues
we
r
e
mea
s
ur
e
d
us
ing
the
b
io
-
im
pe
da
nc
e
a
ppa
r
a
tus
i.
e
.
r
e
s
is
tanc
e
,
r
e
a
c
tanc
e
,
e
gg
we
ight
a
nd
pha
s
e
a
ngle.
T
he
pha
s
e
a
ngle
a
nd
im
pe
da
nc
e
va
lu
e
s
obtaine
d
f
r
om
the
bioele
c
tr
ica
l
im
pe
da
nc
e
a
na
lys
is
we
r
e
a
ls
o
us
e
d
to
dif
f
e
r
e
nti
a
te
the
s
e
x
of
the
poult
r
y
in
e
ggs
.
R
e
s
ult
s
obtaine
d
f
r
om
the
s
tudy
il
lus
tr
a
te
that
the
B
I
A
a
ppr
oa
c
h
is
a
ble
to
a
c
c
ur
a
tely
pr
e
dict
the
s
e
x
a
nd
he
a
lt
h
of
the
e
ggs
a
nd
poult
r
y
with
a
c
or
r
e
lation
va
lue
of
0.
739
a
t
p
≤
0.
05
.
T
o
c
onc
lude,
a
number
o
f
li
te
r
a
tur
e
s
ha
s
be
e
n
r
e
vi
e
we
d
ba
s
e
d
on
the
de
ve
lopm
e
nt
a
nd
a
ppli
c
a
ti
on
of
s
ma
r
t
mi
r
r
or
s
.
Va
r
ious
r
e
s
e
a
r
c
he
r
s
ha
ve
uti
li
z
e
d
s
e
ve
r
a
l
a
ppr
oa
c
he
s
to
de
ve
lop
s
mar
t
mi
r
r
or
s
ba
s
e
d
on
I
oT
us
ing
R
a
s
pbe
r
r
y
pi.
T
he
s
tudi
e
s
pr
opos
e
d
in
the
li
t
e
r
a
tur
e
r
e
view
e
d
ha
ve
include
d
s
ome
f
e
a
tur
e
s
s
uc
h
a
s
ti
me,
da
te,
ne
ws
,
we
a
ther
upda
tes
a
nd
c
a
lenda
r
.
L
it
tl
e
or
no
e
f
f
o
r
t
ha
s
be
e
n
made
on
de
ve
lopm
e
nt
of
a
f
it
ne
s
s
a
nd
he
a
lt
h
ba
s
e
d
s
mar
t
mi
r
r
or
e
xc
e
pt
f
or
two
s
tudi
e
s
whic
h
moni
tor
the
us
e
r
we
ight
only.
T
he
r
e
f
o
r
e
,
t
his
s
tudy
will
f
oc
us
on
the
im
pleme
ntation
of
f
it
ne
s
s
f
e
a
tur
e
s
a
nd
he
a
lt
h
moni
tor
ing
a
s
we
ll
a
s
f
a
c
e
r
e
c
ogn
it
ion
to
a
ll
ow
the
s
ys
tem
to
c
onti
nuous
ly
moni
tor
the
he
a
lt
h
of
a
pa
r
ti
c
ular
us
e
r
ove
r
ti
me.
3.
P
ROP
OS
E
D
S
HC
S
YST
E
M
S
T
he
p
r
opos
e
d
s
mar
t
he
a
lt
h/f
it
ne
s
s
mi
r
r
or
s
ys
tem
us
e
s
the
f
a
c
ial
r
e
c
ognit
ion
tec
hnique
to
a
c
c
e
s
s
the
his
tor
ica
l
he
a
lt
h
da
ta
ba
s
e
of
the
us
e
r
whe
r
e
a
s
a
ne
two
r
k
o
f
s
e
ns
or
is
us
e
d
to
o
btain
r
e
a
l
ti
me
he
a
lt
h
a
nd
f
it
ne
s
s
da
ta
f
r
om
the
us
e
r
a
s
s
hown
in
the
block
d
iagr
a
m
in
F
igu
r
e
1
.
A
he
a
lt
h
moni
tor
ing
is
then
p
e
r
f
or
med
ba
s
e
d
on
the
us
e
r
’
s
pr
e
vious
he
a
lt
h
his
tor
y
whe
r
e
by
the
diagnos
is
a
nd
the
s
e
n
s
or
da
ta
a
r
e
dis
pl
a
ye
d
on
the
s
mar
t
mi
r
r
or
.
F
igur
e
1.
He
a
lt
h/f
it
ne
s
s
moni
tor
ing
s
ys
tem
block
d
iagr
a
m
3.
1.
F
ac
e
r
e
c
ogn
it
ion
Ac
c
or
ding
to
Z
ha
ng
e
t
a
l
.
[
4
6
]
f
a
c
e
r
e
c
ognit
ion
r
e
f
e
r
s
to
the
pr
oc
e
s
s
of
mapping
the
f
a
c
e
o
f
a
g
iven
indi
vidual
to
their
identi
ty.
T
he
f
a
c
ial
r
e
c
ognit
ion
s
ys
tem
im
pleme
nted
in
thi
s
s
tudy
wa
s
us
e
d
f
o
r
pur
pos
e
s
of
identif
ying
the
us
e
r
.
I
de
nti
f
ica
ti
on
o
f
the
us
e
r
e
na
bles
the
s
ys
tem
to
c
ompar
e
the
c
ur
r
e
nt
he
a
lt
h
s
tatus
of
the
us
e
r
with
pr
e
vious
ly
obtaine
d
his
tor
ica
l
da
ta.
A
USB
we
b
c
a
m
wa
s
us
e
d
f
or
the
pur
pos
e
of
im
a
ge
a
c
quis
it
ion
whe
r
e
a
s
a
R
a
s
pbe
r
r
y
pi
3
f
it
ted
with
Ope
nC
V
wa
s
us
e
d
to
de
ve
lop
the
f
a
c
e
r
e
c
ogni
ti
on
a
lgor
it
hm.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KO
M
NI
KA
T
e
lec
omm
un
C
omput
E
l
C
ontr
o
l
Smar
t
he
alt
h
monitor
ing
s
y
s
tem
us
i
ng
I
o
T
bas
e
d
s
mar
t
fi
tnes
s
mir
r
o
r
(
A
mgad
M
une
e
r
)
323
Af
ter
the
pr
oc
e
s
s
of
a
c
quir
ing
the
us
e
r
’
s
i
mage
is
c
ompl
e
te,
f
e
a
tur
e
e
xtr
a
c
ti
on
is
c
a
r
r
ied
out
to
is
ol
a
te
ke
e
n
a
r
e
a
s
of
int
e
r
e
s
t
ba
s
e
d
on
his
/her
f
a
c
ial
f
e
a
tur
e
s
.
C
onve
r
s
ion
of
the
a
c
quir
e
d
im
a
ge
f
r
om
R
GB
to
g
r
a
y
s
c
a
le
wa
s
then
c
a
r
r
ied
out
in
or
de
r
to
a
ll
ow
the
e
dge
s
of
the
r
e
tr
ieve
d
im
a
ge
to
be
f
ound
thr
ough
the
pr
oc
e
s
s
of
e
dge
s
e
gmenta
ti
on
a
s
s
hown
in
F
igur
e
2.
E
igenve
c
tor
s
we
r
e
then
e
mpl
oye
d
f
or
r
e
c
ons
tr
uc
ti
ng
f
a
c
ial
f
e
a
tur
e
s
f
r
om
the
e
dge
map
be
f
or
e
f
a
c
e
loca
li
z
a
ti
on
w
a
s
done
.
F
a
c
e
loca
l
iza
ti
on
wa
s
done
in
thr
e
e
s
teps
a
s
e
xplaine
d
be
low:
−
Ha
a
r
-
f
e
a
tur
e
s
e
lec
ti
on
s
t
a
ge
,
whe
r
e
by
the
digi
tal
f
e
a
tur
e
s
e
xtr
a
c
ted
f
r
om
the
f
a
c
e
s
uc
h
a
s
e
ye
s
,
nos
e
a
nd
mout
h
a
r
e
s
e
t
a
pa
r
t
f
r
o
m
the
f
a
c
ial
im
a
ge
.
−
F
a
c
e
ve
c
tor
nor
maliza
ti
on
,
whe
r
e
by
the
f
a
c
e
ve
c
t
or
a
ve
r
a
ge
f
r
om
e
a
c
h
E
igen
va
lue
a
r
e
manipulate
d
to
lowe
r
dim
e
ns
ion
ve
c
tor
s
with
the
a
im
of
c
a
lcula
ti
n
g
the
ove
r
a
ll
di
mens
ions
of
the
digi
ti
z
e
d
f
a
c
ial
f
e
a
t
ur
e
s
obtaine
d
dur
ing
th
e
pr
e
vious
s
tage
i.
e
.
Ha
a
r
-
f
e
a
tur
e
s
e
lec
ti
on
s
tage
.
−
F
a
c
e
identif
ica
ti
on
s
tage
,
whe
r
e
by
the
e
xtr
a
c
ted
f
a
c
ial
dim
e
ns
ions
f
r
om
the
p
r
e
vious
s
tage
a
nd
the
E
igen
va
lues
a
r
e
us
e
d
f
or
pur
pos
e
s
of
c
ompar
ing
with
other
f
a
c
ial
im
a
ge
s
hos
ted
in
a
da
taba
s
e
.
I
n
thi
s
s
tage
,
c
a
s
c
a
ding
c
las
s
if
ier
s
a
r
e
e
mpl
oye
d
f
or
the
p
r
oc
e
s
s
of
c
las
s
if
ying
the
im
a
ge
s
s
e
lec
ted
.
F
igur
e
2.
I
mage
pr
oc
e
s
s
ing
f
lowc
ha
r
t
3.
2.
Healt
h
/f
it
n
e
s
s
m
on
it
or
in
g
T
he
he
a
lt
h
f
it
ne
s
s
s
ys
tem
im
pleme
nted
f
or
the
s
mar
t
f
it
ne
s
s
mi
r
r
o
r
r
e
li
e
s
on
inf
o
r
mation
obt
a
ined
f
r
om
a
ne
twor
k
of
wi
r
e
les
s
s
e
ns
or
s
a
s
s
hown
in
F
igur
e
3
.
T
he
I
R
tempe
r
a
tur
e
s
e
ns
or
wa
s
us
e
d
to
obtain
the
tempe
r
a
tur
e
o
f
the
identif
ied
us
e
r
,
whe
r
e
a
s
the
we
i
ghing
s
c
a
le
wa
s
us
e
d
f
or
B
I
A
(
bioele
c
tr
ica
l
im
pe
da
nc
e
a
na
lys
is
)
a
nd
B
M
I
a
na
lys
i
s
.
Onc
e
the
u
s
e
r
s
teps
on
to
the
we
igh
s
c
a
le,
a
c
a
mer
a
take
s
a
photo
of
the
u
s
e
r
to
be
pr
oc
e
s
s
e
d
f
or
identif
ica
ti
on
pur
pos
e
s
.
Onc
e
the
us
e
r
is
identi
f
ied,
his
/her
he
a
lt
h
da
ta
is
a
c
c
e
s
s
e
d
f
r
om
the
da
ta
ba
s
e
f
or
c
ompar
is
on
with
the
c
omput
e
d
B
I
A,
B
M
I
a
nd
body
tempe
r
a
tur
e
inf
or
mation.
I
f
t
he
r
e
s
ult
s
obtaine
d
a
r
e
s
uit
a
ble,
they
a
r
e
dis
playe
d
on
the
s
mar
t
mi
r
r
o
r
.
How
e
ve
r
,
if
the
r
e
s
ult
s
a
r
e
c
ons
ider
e
d
not
to
be
in
the
r
a
nge
s
e
t,
then
t
he
r
e
s
ult
s
a
r
e
dis
playe
d
with
r
e
c
omm
e
nda
ti
ons
to
a
ll
ow
the
us
e
r
to
a
djus
t
his
he
a
lt
h/f
it
ne
s
s
.
T
he
body
mas
s
index
o
f
the
us
e
r
w
a
s
c
a
lcula
ted
us
ing
(
4)
a
s
pr
opos
e
d
by
Kim
e
t
a
l.
[
4
7
]
a
nd
F
r
a
nk
[
4
8
].
=
ℎ
(
ℎ
)
2
(
4)
B
I
A
(
bioele
c
tr
ica
l
im
pe
da
nc
e
a
na
lys
is
)
wa
s
us
e
d
t
o
e
s
ti
mate
other
he
a
lt
h
pr
ope
r
ti
e
s
of
the
us
e
r
s
uc
h
a
s
body
f
a
t
pe
r
c
e
ntage
,
lea
n
body
mas
s
a
nd
tot
a
l
body
wa
ter
a
s
s
ho
wn
in
F
igur
e
4
.
Ac
c
or
ding
to
M
a
r
ia
e
t
a
l.
[
4
3
]
,
B
I
A
mea
s
ur
e
s
the
a
mount
of
oppos
it
ion
(
im
pe
da
nc
e
)
of
f
e
r
e
d
by
body
ti
s
s
ue
s
to
the
f
low
of
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
1693
-
6930
T
E
L
KO
M
NI
KA
T
e
lec
omm
un
C
omput
E
l
C
ontr
o
l
,
Vol.
18
,
No
.
1
,
F
e
br
ua
r
y
2020
:
317
-
331
324
a
s
mall
a
mount
of
Ac
c
ur
r
e
nt
i.
e
.
les
s
than
1
mA.
T
he
a
mount
of
im
pe
da
nc
e
mea
s
ur
e
d
va
r
ies
with
the
f
r
e
que
nc
y
of
the
c
ur
r
e
nt
a
ppli
e
d
i
.
e
.
50
kH
z
f
or
e
a
c
h
f
r
e
que
nc
y.
T
wo
bio
-
e
lec
tr
ic
e
lec
tr
od
e
s
we
r
e
ins
talled
a
t
the
ba
s
e
of
the
we
ighi
ng
s
c
a
le
f
or
pur
p
os
e
s
of
pe
r
f
or
mi
ng
B
I
A
(
bioele
c
tr
ica
l
im
pe
da
nc
e
a
na
lys
is
)
a
s
s
hown
in
F
igur
e
3
.
Ac
c
or
ding
to
I
nB
ody
[
49
]
,
t
o
pe
r
f
or
m
B
I
A,
the
body
wa
s
divi
de
d
int
o
3
main
s
e
c
ti
ons
i.
e
.
tr
unk
,
r
igh
t
leg
a
nd
lef
t
leg
a
s
s
hown
in
F
igur
e
4,
whe
r
e
by
the
im
pe
da
nc
e
(
Z
)
o
f
e
a
c
h
s
e
c
ti
on
wa
s
c
omput
e
d
a
s
s
hown
in
T
a
ble
1
,
F
igur
e
3.
He
a
lt
h
moni
tor
ing
T
a
ble
1.
I
mpeda
nc
e
of
va
r
ious
body
pa
r
ts
Z
(
Ω
)
(
T
r
unk)
(
R
ig
ht
L
e
g)
(
L
e
f
t
L
e
g)
1 kH
z
26.8
306.8
316.1
5 kH
z
25.7
303.0
314.1
50 kHz
23.0
282.3
289.8
250 kHz
20.4
263.3
272.7
500 kHz
19.1
258.1
267.8
1000 kHz
17.0
254.5
264.0
F
igur
e
4.
B
ioele
c
tr
ica
l
im
pe
da
nc
e
a
na
lys
is
3.
3.
F
at
f
r
e
e
m
as
s
(
F
F
M
)
,
f
r
e
e
m
as
s
(
F
M
)
an
d
b
od
y
f
at
(
B
F
)
c
alcul
at
ion
In
(
5)
,
(
6)
a
nd
(
7)
a
s
pr
opos
e
d
by
Kim
e
t
a
l.
[
4
7
]
a
nd
F
r
a
nk
[
4
8
]
a
nd
I
nB
ody
[
49
]
we
r
e
us
e
d
to
c
a
lcula
te
the
f
a
t
f
r
e
e
mas
s
(
F
F
M
)
,
f
r
e
e
mas
s
(
F
M
)
a
nd
body
f
a
t
(
B
F
)
f
or
the
us
e
r
s
r
e
s
pe
c
ti
ve
ly.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KO
M
NI
KA
T
e
lec
omm
un
C
omput
E
l
C
ontr
o
l
Smar
t
he
alt
h
monitor
ing
s
y
s
tem
us
i
ng
I
o
T
bas
e
d
s
mar
t
fi
tnes
s
mir
r
o
r
(
A
mgad
M
une
e
r
)
325
=
−
10
.
68
+
(
0
.
65
2
)
+
0
.
26
+
0
.
02
(
5)
=
−
(
6)
%
=
×
100%
(
7)
F
F
M
–
f
a
t
f
r
e
e
m
a
s
s
(
Kg)
,
H
–
h
e
igh
t
(
c
m
)
,
B
W
–
body
we
ight
(
Kg
)
,
R
–
r
e
s
is
tanc
e
(
Ω
)
&
B
F
–
body
f
a
t
3.
4.
E
lec
t
r
ical
c
on
s
t
r
u
c
t
ion
T
he
e
lec
tr
onic
c
omponents
us
e
d
f
o
r
the
de
ve
lop
ment
of
the
s
ys
tem
a
r
e
a
s
s
hown
in
the
e
lec
tr
ica
l
s
c
he
matic
in
F
igu
r
e
5
.
T
he
s
mar
t
m
ir
r
o
r
de
ve
lope
d
r
e
li
e
s
on
a
W
I
F
I
c
onne
c
ti
on
a
nd
ther
e
f
or
e
a
R
a
s
pbe
r
r
y
pi
3
on
-
boa
r
d
c
omput
e
r
wa
s
us
e
d
to
pr
ovide
int
e
r
n
e
t
c
onn
e
c
ti
on
a
nd
a
c
t
a
s
the
s
ol
e
mi
c
r
oc
ontr
oll
e
r
us
e
d
to
r
e
tr
ieve
a
nd
tr
a
ns
mi
t
da
ta
f
r
om
the
s
e
ns
or
s
a
nd
we
ight
s
c
a
le.
T
he
HX
711
modul
e
wa
s
im
p
leme
nted
in
the
s
ys
tem
to
a
mpl
if
y
the
s
ignal
of
the
load
c
e
ll
us
e
d
to
mea
s
ur
e
the
ove
r
a
ll
we
ight
of
the
us
e
r
.
T
h
e
a
na
l
og
s
ignal
pr
oduc
e
d
by
the
load
c
e
ll
wa
s
we
a
k
a
nd
ther
e
f
or
e
the
HX
711
modul
e
wa
s
im
pleme
nted
to
c
onve
r
t
the
we
a
k
s
ignal
int
o
bit
s
a
nd
bytes
f
or
e
a
s
y
int
e
r
p
r
e
tation
by
the
R
a
s
pbe
r
r
y
pi
m
icr
oc
ontr
oll
e
r
.
An
L
C
D
T
V
moni
tor
dis
play
with
HD
M
I
c
onne
c
ti
on
wa
s
us
e
d
to
d
is
play
us
e
r
’
s
pe
r
s
on
a
l
in
f
or
mation
s
uc
h
a
s
e
mails
,
we
a
ther
f
or
e
c
a
s
t,
Qur
a
n
quo
tes
,
upc
omi
ng
e
ve
nt
s
,
ne
ws
f
e
e
d
a
nd
he
a
lt
h
da
ta
p
r
oc
e
s
s
e
d
f
r
om
th
e
he
a
lt
h
moni
tor
ing
s
ys
tem.
T
he
double
-
s
ided
mi
r
r
or
pr
o
pos
e
d
in
the
be
ginni
ng
wa
s
de
e
med
quit
e
e
xpe
ns
ive
a
f
t
e
r
f
ur
ther
r
e
s
e
a
r
c
h
a
nd
a
na
lys
is
,
the
r
e
f
or
e
a
ti
nt
f
il
m
nor
mal
ly
us
e
d
f
or
c
a
r
a
nd
buil
ding
pr
ivac
y
wa
s
us
e
d
to
pr
ovide
a
two
-
wa
y
r
e
f
lec
ti
on
of
the
us
e
r
a
nd
r
e
leva
nt
f
it
ne
s
s
inf
or
mat
ion
f
r
om
the
L
C
D
s
c
r
e
e
n.
I
n
a
ddit
ion
,
a
DH
T
11
tempe
r
a
tur
e
s
e
ns
or
wa
s
us
e
d
t
o
r
e
a
d
a
nd
r
e
c
or
d
the
e
nv
ir
onment
tempe
r
a
tur
e
i.
e
.
tempe
r
a
tu
r
e
of
the
r
oom
,
to
e
na
ble
the
us
e
r
t
o
be
a
wa
r
e
of
the
r
oom
tempe
r
a
tur
e
a
nd
make
n
e
c
e
s
s
a
r
y
a
djus
tm
e
nts
to
the
HV
AC
s
ys
tem.
How
e
ve
r
,
a
n
I
R
tempe
r
a
tur
e
s
e
ns
or
wa
s
us
e
d
f
or
pur
pos
e
s
of
o
btaining
the
body
tempe
r
a
tur
e
of
the
u
s
e
r
.
An
inf
r
a
-
r
e
d
tempe
r
a
tur
e
s
e
ns
or
wa
s
us
e
d
in
c
ompar
is
on
to
other
tempe
r
a
tur
e
s
e
ns
or
s
s
ince
it
doe
s
not
r
e
qui
r
e
the
u
s
e
r
to
be
in
c
ontac
t
with
-
it
du
r
ing
ope
r
a
ti
on.
I
n
a
d
dit
ion,
I
R
tempe
r
a
tur
e
s
e
ns
or
s
a
r
e
known
to
be
mor
e
a
c
c
ur
a
t
e
,
pr
e
c
is
e
a
nd
we
a
r
f
r
e
e
s
ince
ther
e
is
no
phys
ica
l
c
ontac
t
with
the
us
e
r
.
T
he
tempe
r
a
tur
e
obtaine
d
f
r
om
the
body
would
then
be
c
ompar
e
d
with
pr
e
vious
ly
c
oll
e
c
ted
va
lues
in
or
de
r
to
obtain
a
c
onc
lus
ion
i.
e
.
if
te
mper
a
tur
e
is
nor
mal
or
a
bnor
mal
.
T
he
ha
r
dwa
r
e
s
ys
tem
de
ve
loped
f
or
th
e
s
mar
t
f
i
tnes
s
mi
r
r
or
c
ons
is
ts
of
a
B
luetooth
e
na
bled
we
ighi
ng
s
c
a
le
a
nd
a
s
mar
t
mi
r
r
or
.
T
he
we
ighi
ng
s
c
a
le
wa
s
made
f
r
om
3D
p
r
int
e
d
m
a
ter
ial
a
nd
mea
s
ur
e
s
30.
3
c
m
by
35
.
2
c
m
by
4.
8
c
m.
F
our
load
s
e
ns
or
s
loca
ted
a
t
the
f
our
c
or
ne
r
s
o
f
the
we
i
ghing
s
c
a
le
w
e
r
e
us
e
d
to
mea
s
ur
e
the
we
ight
o
f
th
e
us
e
r
a
s
s
hown
in
F
igur
e
6
.
F
igur
e
5.
E
lec
tr
ica
l
s
c
he
matic
F
igur
e
6.
W
e
ight
f
oot
s
c
a
le
F
ur
ther
mor
e
,
f
ou
r
s
tainles
s
s
tee
l
e
lec
tr
ode
plate
s
a
ls
o
loca
ted
a
t
the
f
our
c
or
ne
r
s
of
the
we
ight
s
c
a
le
a
bove
the
load
s
e
ns
or
s
w
e
r
e
us
e
d
f
or
B
I
A
(
bioele
c
tr
ica
l
im
pe
da
nc
e
a
na
lys
is
)
in
or
de
r
to
c
a
lcula
te
other
he
a
lt
h
pr
ope
r
ti
e
s
of
the
us
e
r
s
uc
h
a
s
body
f
a
t
pe
r
c
e
ntage
,
lea
n
body
mas
s
a
nd
to
tal
body
wa
ter
.
T
he
s
mar
t
mi
r
r
or
de
ve
loped
mea
s
ur
e
s
45.
2
c
m
by
115
c
m
by
6
.
7
c
m
a
nd
c
ons
is
ts
of
a
n
L
C
D
s
c
r
e
e
n
moun
ted
onto
a
woode
n
f
r
a
me
a
nd
c
ove
r
e
d
with
a
th
in
f
il
m
of
windo
w
ti
nt
to
p
r
oduc
e
the
e
f
f
e
c
t
of
a
double
-
s
ided
mi
r
r
o
r
.
T
he
c
ompl
e
te
s
ys
tem
ha
s
be
e
n
r
e
c
on
s
tr
uc
ted
a
n
d
tes
ted
f
or
the
pur
pos
e
of
pr
oving
i
ts
f
ub
c
ti
on
a
li
ty
a
nd
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
1693
-
6930
T
E
L
KO
M
NI
KA
T
e
lec
omm
un
C
omput
E
l
C
ontr
o
l
,
Vol.
18
,
No
.
1
,
F
e
br
ua
r
y
2020
:
317
-
331
326
pe
r
f
or
manc
e
.
F
igur
e
s
7,
8
a
nd
9
de
pict
the
r
unnin
g
s
ys
tem.
T
he
a
ndr
o
id
a
ppli
c
a
ti
on
de
ve
loped
us
in
g
a
ndr
oid
s
tudi
o
f
or
body
he
a
lt
h
a
nd
f
it
ne
s
s
t
r
a
c
king
is
a
s
s
hown
in
F
igu
r
e
10
a
nd
F
igur
e
11
whe
r
e
the
idnt
i
f
c
a
ti
on
of
the
us
e
r
,
body
we
ight
a
nd
f
a
t
s
hown
in
the
de
ve
lo
p
e
d
mobi
le
a
pp.
Als
o,
the
R
a
s
pbe
r
r
y
pi
GU
I
f
or
t
he
s
mar
t
f
it
ne
s
s
/hea
lt
h
moni
tor
ing
mi
r
r
or
is
a
s
s
hown
in
F
ig
ur
e
12.
F
igur
e
7.
F
oot
s
c
a
le
a
nd
s
mar
t
mi
r
r
or
F
igur
e
8
.
S
e
ns
or
a
nd
mi
r
r
or
c
ons
tr
uc
ti
on
F
igur
e
9
.
S
e
ns
or
a
nd
mi
r
r
or
c
ons
tr
uc
ti
on
F
igur
e
10
.
Andr
oid
Applica
ti
on
F
igur
e
11.
T
r
a
c
king
gr
a
ph
da
ta
ba
s
e
F
igur
e
12.
S
mar
t
mi
r
r
or
GU
I
Evaluation Warning : The document was created with Spire.PDF for Python.