I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
15
,
No
.
5
,
Octo
b
er
20
25
,
p
p
.
4
6
2
0
~
4
6
2
9
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
15
i
5
.
pp
4
6
2
0
-
4
6
2
9
4620
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Lo
w comp
lex
i
ty h
uma
n f
a
ll de
tect
io
n using
body
loca
tion a
nd
po
sture geo
metry
P
ipa
t
Sa
k
a
rin
1
,
Su
cha
da
Sitj
o
ng
s
a
t
a
po
rn
2
1
El
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
G
r
a
d
u
a
t
e
P
r
o
g
r
a
m,
F
a
c
u
l
t
y
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
Te
c
h
n
o
l
o
g
y
,
M
a
h
a
n
a
k
o
r
n
U
n
i
v
e
r
si
t
y
o
f
Te
c
h
n
o
l
o
g
y
,
B
a
n
g
k
o
k
,
T
h
a
i
l
a
n
d
2
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
E
n
g
i
n
e
e
r
i
n
g
,
M
a
h
a
n
a
k
o
r
n
I
n
st
i
t
u
t
e
o
f
I
n
n
o
v
a
t
i
o
n
(
M
I
I
)
F
a
c
u
l
t
y
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
Te
c
h
n
o
l
o
g
y
,
M
a
h
a
n
a
k
o
r
n
U
n
i
v
e
r
s
i
t
y
o
f
T
e
c
h
n
o
l
o
g
y
,
B
a
n
g
k
o
k
,
T
h
a
i
l
a
n
d
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
5
,
2
0
2
5
R
ev
is
ed
J
u
n
1
9
,
2
0
2
5
Acc
ep
ted
J
u
l 1
2
,
2
0
2
5
Th
is
p
a
p
e
r
p
re
se
n
ts
t
h
e
h
u
m
a
n
f
a
ll
d
e
tec
ti
o
n
u
sin
g
b
o
d
y
lo
c
a
ti
o
n
(HFBL
)
a
n
d
p
o
st
u
re
g
e
o
m
e
try
.
T
h
e
m
a
in
c
o
n
tri
b
u
ti
o
n
o
f
t
h
e
p
ro
p
o
se
d
HF
BL
sy
ste
m
is
to
re
d
u
c
e
th
e
c
o
m
p
u
tatio
n
a
l
c
o
m
p
lex
it
y
o
f
fa
ll
d
e
tec
ti
o
n
sy
s
tem
wh
il
e
m
a
in
tain
in
g
a
c
c
u
ra
c
y
,
a
s
m
o
st
fa
ll
d
e
tec
ti
o
n
tec
h
n
i
q
u
e
s
re
ly
o
n
c
o
m
p
u
tati
o
n
a
ll
y
c
o
m
p
lex
a
lg
o
r
it
h
m
s
fro
m
m
a
c
h
in
e
lea
rn
in
g
o
r
d
e
e
p
lea
rn
in
g
.
Th
is
a
p
p
r
o
a
c
h
e
x
a
m
in
e
s
th
e
h
u
m
a
n
p
o
st
u
re
b
y
a
p
p
l
y
in
g
th
e
ima
g
e
se
g
m
e
n
tatio
n
a
n
d
ra
ti
o
b
y
p
o
stu
r
e
g
e
o
m
e
try
.
Th
e
n
,
th
e
d
istan
c
e
tr
a
n
sfo
rm
is
u
se
d
t
o
c
a
lcu
late
th
e
h
i
g
h
b
ri
g
h
t
n
e
ss
p
o
in
ts
o
n
t
h
e
h
u
m
a
n
b
o
d
y
.
Th
e
se
p
o
in
ts
a
re
th
e
m
a
x
imu
m
v
a
l
u
e
s
c
o
m
p
a
r
e
d
wit
h
t
h
e
e
d
g
e
v
a
lu
e
s.
Afte
rwa
rd
,
o
n
e
o
f
th
e
se
p
o
i
n
ts i
s se
lec
ted
a
s a
c
e
n
ter p
o
i
n
t.
A
li
n
e
is f
o
rm
e
d
b
y
t
h
is ce
n
ter p
o
in
t
a
li
g
n
e
d
h
o
rizo
n
tall
y
to
se
p
a
ra
te
th
e
u
p
p
e
r
a
re
a
a
n
d
lo
we
r
a
re
a
,
th
e
n
a
n
in
ters
e
c
ti
o
n
l
in
e
is
d
ra
wn
t
h
ro
u
g
h
th
is
c
e
n
ter
p
o
in
t
v
e
rti
c
a
ll
y
th
a
t
c
a
n
se
p
a
ra
te
th
e
fo
u
r
q
u
a
d
ra
n
ts
o
f
b
o
d
y
lo
c
a
ti
o
n
.
Wi
th
th
e
h
e
lp
o
f
p
o
st
u
re
g
e
o
m
e
try
,
t
h
e
a
n
g
les
a
re
e
m
p
lo
y
e
d
fo
r
p
re
d
icti
o
n
“
F
a
ll
”
o
r
“
No
tF
a
l
l”
a
c
ti
o
n
s
a
t
e
a
c
h
fra
m
e
o
f
v
id
e
o
se
q
u
e
n
c
e
.
Re
fe
rrin
g
to
th
e
d
y
n
a
m
ic
b
a
lan
c
e
,
t
h
e
ra
ti
o
b
e
twe
e
n
th
e
d
istan
c
e
v
e
c
to
rs fro
m
th
e
c
e
n
ter p
o
in
t
t
o
th
e
ri
g
h
t
a
n
d
left
leg
s is
c
a
lcu
late
d
to
c
o
n
f
irm
fa
ll
a
n
d
n
o
n
-
fa
ll
a
c
ti
v
it
ies
,
u
ti
li
z
in
g
t
h
e
P
y
th
a
g
o
re
a
n
tri
g
o
n
o
m
e
tri
c
i
d
e
n
ti
t
y
.
F
o
r
e
x
p
e
rime
n
ts,
2
,
5
4
2
ima
g
e
s
fro
m
th
e
UR
fa
ll
d
e
tec
ti
o
n
d
a
tas
e
t,
wit
h
d
ime
n
sio
n
s
o
f
6
4
0
×
4
8
0
×
3
we
re
p
re
p
a
re
d
th
r
o
u
g
h
ima
g
e
se
g
m
e
n
tatio
n
to
fin
d
t
h
e
h
u
m
a
n
b
o
d
y
sh
a
p
e
f
o
r
a
n
a
l
y
sis
u
sin
g
t
h
e
p
ro
p
o
se
d
HFBL
sy
ste
m
.
Re
su
lt
s
d
e
m
o
n
stra
te
th
a
t
th
e
lo
w
c
o
m
p
u
tati
o
n
a
l
HFBL
a
p
p
r
o
a
c
h
c
a
n
p
r
o
v
i
d
e
9
1
.
2
3
%
a
c
c
u
ra
c
y
,
t
h
e
p
re
c
isio
n
v
a
l
u
e
is
9
9
.
1
4
%
,
t
h
e
re
c
a
ll
v
a
lu
e
is 8
4
.
4
8
%
,
a
n
d
t
h
e
F
1
-
sc
o
re
v
a
lu
e
is
9
1
.
2
2
%
.
K
ey
w
o
r
d
s
:
B
o
d
y
lo
ca
tio
n
Dis
tan
ce
tr
an
s
f
o
r
m
E
u
clid
ea
n
d
is
tan
ce
Hu
m
an
f
all
d
etec
tio
n
Po
s
tu
r
e
g
eo
m
etr
y
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
:
Pip
at
Sak
ar
in
E
lectr
ical
E
n
g
in
ee
r
in
g
Gr
ad
u
a
te
Pro
g
r
am
,
Facu
lty
o
f
E
n
g
in
e
er
in
g
an
d
T
ec
h
n
o
lo
g
y
,
Ma
h
an
ak
o
r
n
Un
iv
e
r
s
ity
o
f
T
e
ch
n
o
lo
g
y
1
4
0
C
h
eu
m
-
Sam
p
h
an
R
o
ad
,
K
r
ath
u
m
R
ai,
No
n
g
ch
o
k
,
B
an
g
k
o
k
1
0
5
3
0
,
T
h
ailan
d
E
m
ail: p
ip
at.
s
k
r
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
an
n
u
al
p
o
p
u
latio
n
tr
en
d
h
as
also
led
to
an
in
cr
ea
s
in
g
n
u
m
b
er
o
f
eld
er
l
y
p
e
o
p
le
an
d
th
e
n
u
m
b
e
r
o
f
p
eo
p
le
ag
e
d
o
v
e
r
8
0
y
ea
r
s
i
s
p
r
o
jecte
d
to
r
ea
ch
2
5
6
m
illi
o
n
in
2
0
3
0
[
1
]
.
T
h
e
in
cr
ea
s
in
g
n
u
m
b
er
o
f
eld
er
l
y
p
eo
p
le
is
s
p
ec
if
ically
r
elate
d
t
o
th
e
d
ev
elo
p
m
e
n
t
o
f
ca
r
e
tech
n
o
lo
g
ies.
I
n
[
2
]
,
th
e
au
th
o
r
s
h
av
e
p
r
esen
ted
a
n
in
teg
r
ated
s
m
ar
t
ca
r
in
g
h
o
m
e
s
y
s
tem
b
ased
o
n
th
e
in
ter
n
et
o
f
th
in
g
s
(
I
o
T
)
tech
n
o
lo
g
y
.
A
s
s
tated
o
n
r
ed
u
cin
g
th
e
d
ata
ca
lcu
latio
n
,
th
e
p
r
o
p
o
s
ed
en
er
g
y
-
s
av
in
g
c
o
m
p
r
ess
io
n
m
eth
o
d
o
n
th
e
clo
u
d
p
latf
o
r
m
[
3
]
h
as
b
ee
n
in
tr
o
d
u
ce
d
to
d
ec
r
ea
s
e
th
e
laten
cy
o
f
d
ata
tr
a
n
s
m
is
s
io
n
o
n
t
h
e
wea
r
ab
le
m
ed
ical
s
en
s
o
r
s
i
n
em
b
e
d
d
ed
s
ig
n
al
p
r
o
ce
s
s
in
g
.
R
ec
en
tly
,
th
e
h
u
m
an
f
all
d
etec
tio
n
s
y
s
tem
(
HFDS)
is
a
k
ey
im
p
o
r
tan
t
tech
n
o
lo
g
y
f
o
r
ca
r
in
g
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Lo
w
co
mp
lexity
h
u
ma
n
fa
ll d
e
tectio
n
u
s
in
g
b
o
d
y
lo
c
a
tio
n
a
n
d
p
o
s
tu
r
e
g
eo
metry
(
P
ip
a
t S
a
k
a
r
in
)
4621
eld
er
ly
p
e
o
p
le
u
s
in
g
th
e
v
ar
io
u
s
m
o
v
em
e
n
ts
o
f
p
o
s
itio
n
d
etec
tio
n
.
Falls
b
y
a
g
in
g
p
eo
p
le
ar
e
th
e
lead
in
g
ca
u
s
e
o
f
s
ev
er
e
in
j
u
r
y
-
r
elate
d
d
ea
th
f
o
r
ag
i
n
g
p
e
o
p
le
[
4
]
s
u
ch
as
b
ac
k
war
d
f
all
o
n
s
lip
p
er
y
g
r
o
u
n
d
,
f
o
r
war
d
f
alls
b
y
tr
ip
p
in
g
,
s
id
ewa
y
s
,
an
d
s
tr
aig
h
t
-
d
o
w
n
f
alls
d
u
e
to
m
is
s
-
s
tep
p
in
g
an
d
f
ain
tin
g
,
r
esp
ec
tiv
ely
.
Sev
er
al
f
all
d
etec
tio
n
s
y
s
tem
s
h
av
e
b
ee
n
m
o
d
if
ied
b
y
u
s
in
g
v
ar
io
u
s
tec
h
n
o
lo
g
ies
class
if
ied
in
t
o
v
is
io
n
-
b
ased
a
p
p
r
o
ac
h
es
as
m
ac
h
in
e
lear
n
in
g
,
s
en
s
o
r
s
an
d
wea
r
ab
le
d
e
v
ices.
As
f
o
llo
wed
th
e
v
is
io
n
-
b
ased
s
y
s
tem
an
d
m
ac
h
in
e
lear
n
in
g
s
y
s
tem
,
Har
r
o
u
et
a
l.
[
5
]
h
av
e
d
em
o
n
s
tr
ated
th
e
HFDS
tech
n
iq
u
e
b
y
d
iv
id
in
g
f
i
v
e
p
ar
ts
o
f
im
ag
e
an
d
ca
lcu
latin
g
th
e
a
r
ea
r
atio
o
f
d
i
f
f
er
en
t
p
o
s
es.
I
n
[
6
]
,
a
m
u
lti
-
s
tag
e
co
n
v
o
lu
tio
n
n
eu
r
al
n
etwo
r
k
(
C
NN)
h
as
b
ee
n
d
ep
lo
y
e
d
with
th
e
in
v
er
ted
p
e
n
d
u
lu
m
m
o
d
el
f
o
r
f
all
p
r
ed
ict
io
n
.
B
ased
o
n
th
e
Op
e
n
p
o
s
e
s
k
eleto
n
,
L
in
et
a
l.
[
7
]
h
av
e
an
aly
ze
d
th
e
in
f
o
r
m
atio
n
o
n
th
e
ch
an
g
es
o
f
h
u
m
a
n
b
o
n
e
s
k
eleta
l
jo
in
ts
in
th
e
v
ar
io
u
s
m
o
v
em
e
n
ts
u
s
in
g
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
an
d
g
ated
r
ec
u
r
r
en
t
u
n
it
(
GR
U)
m
o
d
el.
I
n
[
8
]
,
a
t
wo
-
s
tag
e
HFDS
h
as
b
ee
n
ap
p
lied
b
y
co
m
p
ar
in
g
th
e
en
er
g
y
v
alu
e
an
d
3
-
s
tate
s
co
r
es
an
aly
ze
d
f
r
o
m
s
k
eleta
l
s
tr
u
ctu
r
e.
Fo
llo
win
g
th
e
m
ac
h
in
e
lear
n
in
g
s
y
s
tem
,
B
ed
d
iar
et
a
l.
[
4
]
m
o
d
if
ied
th
e
ir
ap
p
r
o
ac
h
b
y
u
s
in
g
th
e
an
g
le
b
etwe
en
th
e
ce
n
te
r
o
f
th
e
h
ea
d
an
d
h
ip
to
p
r
ed
i
ct
r
esu
lts
.
Fall
d
etec
tio
n
in
[
9
]
is
p
er
f
o
r
m
ed
u
s
in
g
h
u
m
a
n
s
k
eleto
n
an
d
t
h
e
m
ac
h
in
e
lear
n
in
g
s
y
s
tem
f
o
r
p
r
ed
ictio
n
.
I
n
s
tu
d
y
[
1
0
]
,
b
as
ed
o
n
th
e
f
ast
p
o
s
e
esti
m
atio
n
m
eth
o
d
,
th
e
tim
e
-
d
is
tr
ib
u
ted
co
n
v
o
lu
tio
n
al
L
ST
M
(
T
D
-
C
NN
-
L
STM
)
is
u
s
ed
to
p
r
ed
ict
th
e
r
esu
lts
.
Kesk
es
an
d
No
u
m
eir
[
1
1
]
h
as
s
u
b
s
tan
tiated
f
all
d
etec
tio
n
b
y
s
p
atial
tem
p
o
r
al
g
r
ap
h
co
n
v
o
lu
tio
n
al
n
etwo
r
k
s
(
ST
-
GC
N)
m
eth
o
d
.
I
n
[
1
2
]
,
th
e
r
esu
lts
o
f
th
e
m
ac
h
in
e
lear
n
in
g
s
y
s
tem
u
s
in
g
p
o
s
tu
r
es
f
r
o
m
h
u
m
an
s
ilh
o
u
ettes
ar
e
p
r
e
s
en
ted
.
I
n
[
1
3
]
,
th
e
s
k
eleto
n
in
f
o
r
m
atio
n
f
r
o
m
Op
en
p
o
s
e,
th
e
m
o
v
em
en
t
o
f
th
e
ce
n
ter
p
o
in
t
o
f
th
e
h
ip
jo
i
n
t,
th
e
an
g
le
b
etwe
e
n
b
o
d
y
ce
n
ter
lin
e,
g
r
o
u
n
d
a
n
d
t
h
e
r
atio
b
etwe
en
t
h
e
wid
th
an
d
h
eig
h
t
o
f
h
u
m
an
b
o
d
y
r
ec
ta
n
g
u
lar
ar
e
u
s
ed
f
o
r
p
r
ed
ictio
n
.
As
a
p
o
s
e
esti
m
atio
n
b
ased
[
1
4
]
,
th
e
in
f
o
r
m
atio
n
r
atio
b
etwe
en
d
ef
lectio
n
an
d
ac
ce
ler
atio
n
f
ea
tu
r
es
with
m
ac
h
in
e
lear
n
in
g
s
y
s
tem
to
p
r
ed
ict
th
e
r
esu
lts
.
I
n
[
1
5
]
,
th
e
in
f
o
r
m
atio
n
ab
o
u
t
p
o
s
itio
n
ch
a
n
g
e
b
etwe
en
p
o
in
t
o
f
h
ea
d
a
n
d
s
h
o
u
ld
er
e
x
tr
ac
ted
b
y
Po
s
eN
et
was
an
aly
ze
d
b
y
GR
U
m
o
d
el.
I
n
[
1
6
]
,
t
h
e
Op
en
PifPaf
m
o
d
el
ex
tr
ac
ts
th
e
h
u
m
an
p
o
s
e
esti
m
atio
n
in
f
o
r
m
atio
n
f
r
o
m
m
u
lti
-
ca
m
er
a
a
n
d
u
s
es
L
STM
f
o
r
id
en
tific
atio
n
.
I
n
t
h
i
s
p
a
p
e
r
,
we
p
r
o
p
o
s
e
a
h
u
m
a
n
f
a
l
l
d
et
e
c
ti
o
n
u
s
i
n
g
b
o
d
y
l
o
c
a
t
i
o
n
(
H
FB
L
)
.
T
h
e
p
u
r
p
o
s
e
o
f
t
h
is
s
y
s
te
m
i
s
t
o
r
e
d
u
c
e
t
h
e
h
i
g
h
c
o
m
p
u
t
a
t
i
o
n
a
l
c
o
m
p
l
e
x
it
y
o
f
t
e
n
f
o
u
n
d
i
n
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
a
p
p
l
i
e
d
t
o
f
a
ll
d
e
te
c
t
i
o
n
s
y
s
te
m
s
a
s
d
i
s
c
u
s
s
e
d
in
p
r
i
o
r
r
e
s
e
a
r
c
h
,
w
h
il
e
t
h
e
p
r
o
p
o
s
e
d
H
FB
L
s
t
i
ll
a
c
h
i
e
v
e
s
a
c
c
u
r
at
e
a
n
d
r
e
l
i
a
b
le
f
a
l
l
d
e
t
e
c
ti
o
n
.
T
h
e
p
r
o
p
o
s
e
d
H
F
B
L
s
y
s
t
e
m
w
i
ll
b
e
p
e
r
f
o
r
m
e
d
u
s
i
n
g
i
m
a
g
e
s
e
g
m
e
n
t
a
ti
o
n
[
1
7
]
a
n
d
d
i
s
t
a
n
c
e
t
o
o
r
g
a
n
i
z
e
t
h
e
h
u
m
a
n
b
o
d
y
p
o
s
t
u
r
e
f
o
r
f
a
l
l
p
r
e
d
i
c
t
i
o
n
.
T
h
e
n
,
t
h
e
d
i
s
t
a
n
c
e
t
r
a
n
s
f
o
r
m
[
1
8
]
is
u
s
e
d
t
o
f
i
n
d
a
c
e
n
t
e
r
p
o
i
n
t
.
A
n
i
n
t
e
r
s
e
ct
i
o
n
lin
e
s
ta
r
t
e
d
at
t
h
i
s
c
e
n
t
e
r
p
o
i
n
t
i
s
a
l
i
g
n
e
d
t
o
s
e
p
a
r
a
te
t
h
e
u
p
p
e
r
a
r
e
a
a
n
d
l
o
w
e
r
a
r
e
a
,
i
n
c
l
u
d
i
n
g
t
h
e
r
a
t
i
o
b
et
w
e
e
n
v
ec
t
o
r
s
f
r
o
m
t
h
e
c
e
n
te
r
p
o
i
n
t
t
o
r
i
g
h
t
a
n
d
l
e
f
t
le
g
s
,
t
o
c
o
n
f
i
r
m
f
a
l
l
a
n
d
n
o
n
-
f
a
l
l
s
i
t
u
a
t
i
o
n
s
.
D
u
e
t
o
t
h
e
l
o
w
c
o
m
p
le
x
i
t
y
d
e
s
i
g
n
,
t
h
e
p
r
o
p
o
s
e
d
HF
B
L
s
y
s
t
e
m
c
a
n
b
e
a
p
p
l
i
e
d
t
o
t
h
e
e
m
b
e
d
d
e
d
I
o
T
d
e
v
i
c
e
s
.
2.
P
RO
P
O
SE
D
H
UM
A
N
F
AL
L
DE
T
E
CT
I
O
N
USI
NG
H
UM
AN
B
O
D
Y
L
O
CA
T
I
O
N
T
h
e
h
u
m
an
f
all
d
etec
tio
n
u
s
in
g
b
o
d
y
lo
ca
tio
n
(
HFB
L
)
s
y
s
te
m
is
to
p
r
ed
ict
h
u
m
an
f
alls
b
y
th
e
h
u
m
a
n
b
o
d
y
p
o
s
itio
n
an
d
th
en
to
s
en
d
in
f
o
r
m
atio
n
f
o
r
ass
is
tan
ce
.
Pro
p
o
s
ed
HFB
L
s
y
s
tem
is
in
tr
o
d
u
ce
d
in
Fig
u
r
e
1
.
T
h
ese
im
ag
es
o
r
v
id
eo
s
eq
u
e
n
ce
s
f
r
o
m
i
n
ter
n
et
p
r
o
to
c
o
l
c
am
er
a
(
I
P
C
am
er
a)
a
r
e
s
en
t
t
o
m
ak
e
t
h
e
im
ag
e
s
eg
m
en
ts
f
o
r
f
in
d
in
g
th
e
h
u
m
a
n
b
o
d
y
s
h
ap
e.
T
h
e
d
is
tan
ce
tr
a
n
s
f
o
r
m
atio
n
is
u
s
ed
to
a
n
aly
ze
th
e
b
o
d
y
s
h
a
p
e
t
o
f
in
d
th
e
an
g
le
an
d
r
atio
f
r
o
m
th
e
ce
n
ter
a
n
d
r
ef
er
en
c
e
p
o
in
t
s
.
Fin
ally
,
th
e
an
g
le
an
d
r
atio
ar
e
u
s
ed
to
p
r
e
d
ict
f
all
o
r
n
o
n
-
f
all
ac
tiv
ities
.
Fig
u
r
e
1
.
Ov
e
r
v
iew
o
f
p
r
o
p
o
s
ed
HFB
L
s
y
s
tem
2
.
1
.
H
u
m
a
n seg
m
ent
a
nd
dis
t
a
nce
t
ra
ns
f
o
rm
I
m
ag
e
s
eg
m
en
tatio
n
is
a
tech
n
iq
u
e
f
o
r
class
if
y
in
g
o
b
ject
s
o
r
f
in
d
in
g
lo
ca
tio
n
s
u
s
in
g
p
ix
el
-
lev
el
an
aly
s
is
to
s
ep
ar
ate
o
b
jects
in
th
e
im
ag
es.
T
h
er
e
ar
e
s
ev
er
al
way
s
to
cla
s
s
if
y
o
b
jects
o
r
f
in
d
th
eir
lo
ca
tio
n
s
s
u
ch
as
f
in
d
in
g
ed
g
es,
s
ep
a
r
atin
g
co
lo
r
s
o
r
f
i
n
d
in
g
ch
ar
ac
te
r
is
tics
o
f
th
e
im
ag
e.
T
h
er
e
ar
e
s
ev
er
al
tech
n
iq
u
es
b
ased
o
n
C
NN.
U
-
n
et
is
o
n
e
o
f
s
ev
er
al
s
eg
m
en
tatio
n
tech
n
iq
u
es
u
s
in
g
en
co
d
er
-
d
ec
o
d
er
o
r
u
p
-
s
am
p
lin
g
an
d
d
o
wn
-
s
am
p
lin
g
in
ea
ch
lay
er
i
n
a
U
-
s
h
ap
e
[
1
9
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
6
2
0
-
4
6
2
9
4622
Fo
r
th
e
p
r
o
p
o
s
ed
HFB
L
m
o
d
e
l
s
y
s
tem
,
we
in
tr
o
d
u
ce
t
h
e
R
esNet
-
34
[
2
0
]
,
[
2
1
]
im
p
lem
e
n
t
ed
with
3
4
lay
er
s
.
T
h
e
p
r
e
-
tr
ain
ed
m
o
d
el
[
2
2
]
–
[
2
4
]
is
s
elec
ted
f
o
r
d
is
co
v
er
in
g
th
e
h
u
m
an
p
o
s
e
s
eg
m
en
tatio
n
f
o
r
en
co
d
in
g
/d
ec
o
d
i
n
g
o
r
u
p
/d
o
wn
s
am
p
lin
g
b
ased
o
n
U
-
Net.
A
f
r
am
e
o
f
v
id
eo
s
eq
u
e
n
ce
s
is
ch
an
g
ed
f
r
o
m
r
e
d
,
g
r
ee
n
,
an
d
b
lu
e
(
R
GB
)
to
g
r
ay
s
ca
le
f
o
r
r
ed
u
cin
g
th
e
r
eso
lu
tio
n
.
An
o
r
ig
in
al
R
GB
im
ag
e
is
s
h
o
wn
in
Fig
u
r
e
2
(
a)
.
R
esu
lt o
f
h
u
m
an
s
eg
m
en
t in
g
r
ay
s
ca
le
is
s
h
o
wn
in
Fig
u
r
e
2
(
b
)
.
Fo
llo
win
g
th
e
im
ag
e
p
r
o
ce
s
s
in
g
,
th
e
d
is
tan
ce
tr
a
n
s
f
o
r
m
a
tio
n
(
DT
)
tech
n
iq
u
e
is
a
wi
d
ely
u
s
ed
tech
n
iq
u
e
f
o
r
ca
lcu
latin
g
th
e
clo
s
est
d
is
tan
ce
b
etwe
en
th
e
o
b
jects
o
f
in
ter
est
an
d
d
is
in
ter
est
o
r
th
e
b
ac
k
g
r
o
u
n
d
.
R
esu
lts
ar
e
s
to
r
ed
in
ea
c
h
p
i
x
el,
wh
ich
is
c
alled
a
d
is
tan
ce
m
a
p
as
s
h
o
wn
in
Fig
u
r
e
2
(
c)
.
R
ef
er
r
in
g
to
[
2
4
]
–
[
2
6
]
,
we
d
et
er
m
in
e
th
at
an
im
ag
e
(
,
)
co
n
s
is
ts
o
f
o
b
jects
o
f
in
ter
est
(
)
an
d
o
b
j
ec
ts
o
f
non
-
in
ter
est
(
̃
)
,
wh
er
e
(
,
)
∈
{
,
̃
}
.
T
h
e
p
o
s
itio
n
o
f
th
e
p
i
x
el
{
,
}
o
f
th
e
o
b
jects
o
f
in
ter
est
(
)
is
d
e
f
in
ed
in
x
-
a
x
is
an
d
y
-
ax
is
,
r
esp
ec
tiv
ely
.
I
n
s
im
ilar
way
,
t
h
e
p
o
s
itio
n
o
f
p
i
x
el
{
,
}
o
f
o
b
ject
s
o
f
n
o
n
-
in
ter
est
(
̃
)
in
x
-
ax
is
an
d
y
-
ax
is
is
in
ten
d
ed
.
So
,
th
e
d
is
tan
ce
b
etwe
en
p
ix
els
o
f
(
)
an
d
(
̃
)
ca
n
b
e
o
b
tain
ed
f
r
o
m
th
e
E
u
clid
ea
n
d
is
tan
ce
(
,
)
as
(
1
)
.
(
,
)
=
√
{
(
−
)
2
+
(
−
)
2
}
(
1
)
Fu
r
th
er
m
o
r
e
,
we
r
ef
er
to
th
e
E
u
clid
ea
n
d
is
tan
ce
tr
an
s
f
o
r
m
atio
n
(
,
)
,
wh
ich
ca
n
b
e
d
ef
in
e
d
f
o
r
{
,
̃
}
by
(
2
)
.
(
,
)
=
{
0
;
(
,
)
∈
{
̃
}
{
(
,
)
;
(
,
)
∈
{
}
(
2
)
wh
er
e
{
(
,
)
}
is
u
n
d
er
co
n
d
itio
n
∀
(
0
,
0
)
∈
̃
a
n
d
(
0
,
0
)
ar
e
th
e
in
itial
v
alu
es
o
f
p
ix
els
o
f
{
,
̃
}
.
2
.
2
.
Ang
le
a
nd
ra
t
io
by
ca
lc
ulu
s
R
ef
er
r
in
g
to
(
2
)
,
th
e
r
esu
lts
f
r
o
m
th
e
E
u
clid
ea
n
d
is
tan
ce
tr
a
n
s
f
o
r
m
ca
n
i
d
en
tify
t
h
e
b
r
ig
h
t
est
p
o
in
t,
wh
ich
b
ec
o
m
es th
e
ce
n
ter
p
o
i
n
t
(
,
)
as d
ef
in
ed
b
y
(
3
)
.
(
,
)
=
{
(
,
)
}
(
3
)
Su
b
s
eq
u
en
tly
,
th
e
ed
g
e
v
alu
es
(
,
)
ca
n
b
e
co
m
p
u
ted
u
s
in
g
a
m
in
im
u
m
d
is
tan
ce
tr
an
s
f
o
r
m
.
(
,
)
=
{
(
,
)
}
(
4
)
wh
er
e
(
,
)
is
r
ef
er
r
in
g
(
2
)
.
As
s
h
o
wn
in
Fig
u
r
e
2
,
th
e
ce
n
ter
p
o
in
t
C
in
Fig
u
r
e
2
(
c)
is
u
s
ed
to
d
iv
id
e
th
e
im
ag
e
in
to
f
o
u
r
q
u
ad
r
an
ts
(
Q1
,
Q2
,
Q3
,
Q4
)
in
an
an
ti
-
clo
ck
wis
e
d
ir
ec
tio
n
,
as
d
em
o
n
s
tr
ated
in
Fig
u
r
e
2
(
d
)
,
wh
er
e
th
e
m
in
im
u
m
d
is
tan
ce
v
alu
es
f
r
o
m
(
3
)
1
(
1
,
1
)
,
2
(
2
,
2
)
,
3
(
3
,
3
)
,
an
d
4
(
4
,
4
)
ca
n
b
e
d
ef
in
ed
as
(
5
)
an
d
(
6
)
.
1
(
1
,
1
)
=
(
>
,
<
)
;
2
(
2
,
2
)
=
(
<
,
<
)
(
5
)
3
(
3
,
3
)
=
(
<
,
>
)
;
4
(
2
,
2
)
=
(
>
,
>
)
(
6
)
Fro
m
th
e
(
5
)
an
d
(
6
)
,
we
ca
n
f
in
d
th
e
p
o
in
t
(
,
)
,
(
,
)
,
(
,
)
an
d
(
ℎ
,
ℎ
)
in
Fig
u
r
e
2
(
d
)
th
at
ca
n
b
e
co
m
p
u
ted
b
y
(
7
)
a
n
d
(
8
)
.
(
,
)
=
{
(
,
2
)
}
;
(
,
)
=
{
(
,
1
)
}
(
7
)
(
,
)
=
{
(
,
4
)
}
;
(
ℎ
,
ℎ
)
=
{
(
,
3
)
}
(
8
)
wh
er
e
(
,
2
)
d
en
o
te
a
ce
n
ter
p
o
in
t
o
n
th
e
b
o
d
y
a
n
d
th
e
s
ec
o
n
d
q
u
a
d
r
an
ts
.
Fro
m
Fig
u
r
e
2
(
d
)
,
th
e
d
is
tan
ce
f
r
o
m
p
o
in
t C to
p
o
in
t A
,
p
o
in
t
B
,
p
o
in
t E
,
p
o
in
t H
an
d
p
o
i
n
t
G
th
at
ca
n
b
e
d
ef
in
ed
as
(
9
)
a
n
d
(
1
0
)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Lo
w
co
mp
lexity
h
u
ma
n
fa
ll d
e
tectio
n
u
s
in
g
b
o
d
y
lo
c
a
tio
n
a
n
d
p
o
s
tu
r
e
g
eo
metry
(
P
ip
a
t S
a
k
a
r
in
)
4623
⃑
⃑
⃑
⃑
⃑
=
(
,
)
;
⃑
⃑
⃑
⃑
⃑
=
(
,
)
;
⃑
⃑
⃑
⃑
⃑
=
(
,
)
(
9
)
⃑
⃑
⃑
⃑
⃑
=
(
,
)
;
⃑
⃑
⃑
⃑
⃑
=
(
,
)
(
1
0
)
(
a)
(
b
)
(
c)
(
d
)
Fig
u
r
e
2
.
I
m
ag
e
o
f
h
u
m
an
(
a)
o
r
ig
in
al
R
GB
,
(
b
)
s
eg
m
en
t,
(
c)
d
is
tan
ce
m
ap
an
d
ce
n
ter
p
o
in
t
,
an
d
(
d
)
4
q
u
ad
r
an
ts
Fo
llo
win
g
th
e
l
o
wer
r
i
g
h
t
s
id
e
o
f
Fig
u
r
e
3
(
a)
f
o
r
th
e
an
g
le
ca
lcu
lu
s
,
an
g
le
°
b
etwe
en
p
o
i
n
t
A,
p
o
in
t C,
an
d
p
o
in
t B ca
n
b
e
ca
lcu
lated
b
y
(
1
1
)
.
°
=
1
°
+
2
°
(
1
1
)
wh
er
e
th
e
an
g
le
1
°
an
d
2
°
is
d
eter
m
in
ed
b
y
Py
th
ag
o
r
ea
n
tr
i
g
o
n
o
m
etr
ic
id
en
tity
as
(
1
2
)
.
1
°
=
−
1
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
;
2
°
=
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
(
1
2
)
T
h
er
ef
o
r
e,
th
e
a
n
g
le
°
(
1
1
)
ca
n
b
e
d
eter
m
in
e
d
b
y
(
1
3
)
.
°
=
−
1
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
+
−
1
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
(
1
3
)
T
h
e
an
g
le
°
b
etwe
en
p
o
in
t H
,
p
o
in
t C an
d
p
o
in
t E
as p
r
esen
te
d
in
Fig
u
r
e
3
(
b
)
wh
ich
ca
n
ca
l
cu
lated
b
y
(
1
4
)
.
°
=
3
°
+
4
°
(
1
4
)
T
h
e
an
g
le
3
°
an
d
4
°
ca
n
co
m
p
u
ted
b
y
(
1
5
)
.
3
°
=
−
1
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
;
4
°
=
−
1
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
(
1
5
)
As (
1
4
)
,
th
e
a
n
g
le
°
ca
n
b
e
ca
lcu
lated
b
y
(
1
5
)
as
(
1
6
)
:
°
=
−
1
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
+
−
1
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
(
1
6
)
Acc
o
r
d
in
g
to
s
tan
d
in
g
b
alan
ce
,
th
e
d
y
n
am
ic
b
alan
ce
is
ab
ilit
y
to
m
ain
tain
b
alan
ce
wh
ile
m
o
v
in
g
th
e
b
o
d
y
.
T
h
er
ef
o
r
e,
th
e
r
atio
b
etwe
en
th
e
lef
t a
n
d
r
ig
h
t le
g
s
wh
ile
b
alan
cin
g
th
e
b
o
d
y
is
r
elate
d
b
y
R
1
an
d
R
2
.
1
=
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
;
2
=
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
⃑
(
1
7
)
wh
er
e
th
e
r
atio
R
1
b
etwe
en
⃑
⃑
⃑
⃑
⃑
an
d
⃑
⃑
⃑
⃑
⃑
is
r
ec
ip
r
o
ca
l to
th
e
r
atio
R
2
b
etwe
en
⃑
⃑
⃑
⃑
⃑
an
d
⃑
⃑
⃑
⃑
⃑
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
6
2
0
-
4
6
2
9
4624
(
a)
(
b
)
Fig
u
r
e
3
.
An
g
le
(
a)
°
an
d
(
b
)
°
2
.
2
.
“
F
a
ll”
a
nd
“
No
t
F
a
ll”
p
r
edict
io
n
I
n
th
is
s
ec
ti
o
n
,
we
in
tr
o
d
u
ce
t
h
e
co
n
s
t
r
a
in
ts
f
o
r
“Fa
ll”
an
d
“N
o
tF
all
”
p
r
e
d
i
cti
o
n
r
el
ate
d
t
o
b
o
d
y
lo
c
ati
o
n
a
n
d
p
o
s
t
u
r
e
g
e
o
m
et
r
y
.
T
h
e
p
r
e
d
ic
ti
o
n
“N
o
tFa
ll”
as
p
r
ese
n
t
ed
in
F
ig
u
r
e
4
(
a
)
s
h
o
ws
t
h
a
t
th
e
a
n
g
le
°
is
th
e
a
n
g
l
e
b
etw
ee
n
p
o
i
n
t
A
,
p
o
i
n
t
C
a
n
d
p
o
in
t
B
,
th
e
a
n
g
le
°
is
t
h
e
an
g
l
e
b
et
wee
n
p
o
i
n
t
H
,
p
o
i
n
t
C
a
n
d
p
o
i
n
t
E
.
T
h
e
an
g
l
es
°
a
n
d
°
ar
e
cl
o
s
e
t
o
0
°
,
t
h
e
p
r
o
p
o
s
ed
HFB
L
s
y
s
tem
wi
ll
p
r
e
d
i
ct
“N
o
tF
all
”
ac
t
iv
i
ty
.
As
Fig
u
r
e
4
(
b
)
,
th
e
p
r
ed
ictio
n
“Fall”
co
n
s
is
ts
o
f
°
an
d
°
,
th
at
ar
e
clo
s
e
to
180
°
,
th
e
p
r
o
p
o
s
ed
HFB
L
s
y
s
tem
will
p
r
ed
ict
th
at
h
u
m
an
“Fall”
ac
tiv
ity
.
T
h
e
r
elatio
n
s
h
ip
f
o
r
p
r
ed
ictin
g
wh
eth
er
a
p
er
s
o
n
will
f
all
o
r
n
o
t f
all
wh
ich
ca
n
b
e
d
ef
in
ed
as
(
1
8
)
.
(
)
=
{
“
”
,
°
=
180°
°
=
180°
“
”
,
°
=
0°
°
=
0°
(
1
8
)
wh
er
e
is
th
e
s
eq
u
en
ce
o
f
v
id
eo
d
ata
s
ets f
o
r
s
im
u
latio
n
.
Fig
u
r
e
s
4
(
a)
an
d
4
(
b
)
,
th
e
p
ar
am
eter
s
{
,
1
}
ar
e
th
r
esh
o
ld
f
o
r
f
allin
g
an
d
{
,
1
}
ar
e
th
r
esh
o
ld
f
o
r
n
o
t f
allin
g
.
T
h
en
,
we
ca
n
p
r
ed
ict
wh
eth
er
a
h
u
m
an
will f
all
an
d
n
o
t f
all
wh
ich
ca
n
b
e
d
eter
m
in
ed
b
y
(
1
9
)
.
(
)
=
{
“
”
,
°
=
180
°
−
°
=
180
°
−
1
,
ℎ
0
°
≤
{
,
1
}
≤
180
°
“
”
,
°
=
0
°
+
°
=
0
°
+
1
,
ℎ
0
°
≤
{
,
1
}
≤
180
°
(
1
9
)
wh
er
e
th
e
s
u
m
m
atio
n
o
f
,
,
1
ar
e
1
co
r
r
elate
d
with
th
is
co
n
d
itio
n
b
elo
w
+
=
1
+
1
=
180
°
(
2
0
)
(
a)
(
b
)
Fig
u
r
e
4
.
Pre
d
ictio
n
(
a)
“No
tFall” a
n
d
(
b
)
“Fall”
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Lo
w
co
mp
lexity
h
u
ma
n
fa
ll d
e
tectio
n
u
s
in
g
b
o
d
y
lo
c
a
tio
n
a
n
d
p
o
s
tu
r
e
g
eo
metry
(
P
ip
a
t S
a
k
a
r
in
)
4625
3.
SI
M
UL
A
T
I
O
N
R
E
S
UL
T
S
A
to
tal
o
f
2
6
-
v
id
eo
d
atasets
was
u
s
ed
f
o
r
th
e
s
im
u
latio
n
,
wi
th
ea
ch
v
id
eo
b
ein
g
2
m
in
u
tes
lo
n
g
an
d
h
av
in
g
a
r
eso
lu
tio
n
o
f
6
4
0
×
4
8
0
.
T
h
e
UR
f
all
d
etec
tio
n
d
at
asets
[
2
7
]
with
2
,
5
4
2
im
ag
es
an
d
th
e
s
ize
o
f
640
×
480
×
3
was
p
r
ep
ar
ed
th
r
o
u
g
h
im
ag
e
s
eg
m
en
tatio
n
to
f
in
d
th
e
h
u
m
a
n
b
o
d
y
s
h
ap
e
a
n
d
t
o
an
aly
ze
u
s
in
g
th
e
p
r
o
p
o
s
ed
HFB
L
s
y
s
tem
.
T
h
e
r
esu
lts
ar
e
s
h
o
wn
in
Fig
u
r
e
5
,
Fig
u
r
e
s
6
(
a
)
to
6
(
i)
,
an
d
T
a
b
les 1
to
5.
Fig
u
r
e
5
.
R
esu
lts
o
f
th
e
p
r
o
p
o
s
ed
HFB
L
m
o
d
el
f
o
r
h
u
m
an
f
all
p
r
ed
ictio
n
(
a)
(
b
)
(
c)
(
d
)
(
e)
(f)
(
g
)
(
h
)
(
i)
Fig
u
r
e
6
.
T
h
e
r
esu
lts
o
f
(
a
)
,
(
d
)
,
(
g
)
ex
p
ec
ted
v
alu
es o
f
f
alls
,
(
b
)
,
(
e
)
,
(
h
)
th
e
p
r
ed
icted
v
alu
es o
f
f
alls
b
y
th
e
p
r
o
p
o
s
ed
HFB
L
m
o
d
el,
an
d
(
c
)
,
(
f
)
,
(
i)
th
e
ac
tu
al
v
alu
es o
f
f
alls
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
6
2
0
-
4
6
2
9
4626
As s
h
o
wn
in
T
ab
le
1
,
th
e
e
x
p
e
r
im
en
tal
r
esu
lts
wer
e
o
b
tain
ed
b
y
m
o
d
if
y
in
g
th
e
v
alu
es o
f
an
d
1
o
f
th
e
p
r
o
p
o
s
ed
HFB
L
m
o
d
el
with
o
u
t
in
clu
d
in
g
th
e
v
alu
es
o
f
R
1
an
d
R
2
.
T
h
e
b
est
v
alu
es
in
th
is
tab
le
ar
e
=
60
°
an
d
1
=
60
°
,
with
an
ac
cu
r
ac
y
o
f
7
8
.
9
1
%,
a
p
r
ec
is
io
n
o
f
8
6
.
8
0
%,
a
r
ec
all
o
f
7
1
.
8
7
%,
an
d
F1
-
Sco
r
e
o
f
7
8
.
6
3
%
.
All th
e
r
esu
lts
ar
e
o
b
tain
ed
ar
e
lo
w
ac
cu
r
ate.
T
ab
le
2
is
th
e
r
esu
lt
o
f
th
e
e
x
p
er
im
en
t
b
y
a
d
ju
s
tin
g
t
h
e
v
al
u
e
o
f
an
d
1
o
f
th
e
p
r
o
p
o
s
ed
HFB
L
m
o
d
el
b
y
ta
k
in
g
in
t
o
co
n
s
id
er
atio
n
th
e
v
alu
e
o
f
R
1
=
1
.
5
a
n
d
R
2
=
0
.
7
.
T
h
e
b
est
v
alu
e
in
th
i
s
tab
le
is
=
60
°
an
d
1
=
30
°
with
th
e
v
alu
e
o
f
ac
cu
r
ac
y
o
f
9
1
.
1
5
%,
p
r
ec
is
io
n
o
f
9
9
.
0
6
%,
r
ec
all
o
f
8
4
.
3
7
%
an
d
F1
-
Sco
r
e
o
f
9
1
.
1
2
%.
T
h
e
r
esu
lts
h
av
e
h
ig
h
er
ac
cu
r
ac
y
th
an
b
ef
o
r
e
.
T
ab
le
3
p
r
esen
ts
th
e
r
esu
lts
o
f
th
e
ex
p
er
im
e
n
t
b
y
ad
j
u
s
tin
g
th
e
v
alu
e
o
f
an
d
1
o
f
th
e
p
r
o
p
o
s
ed
HFB
L
m
o
d
el
an
d
ad
ju
s
tin
g
th
e
v
alu
e
o
f
R
1
=
2
.
5
an
d
R
2
=
0
.
4
to
b
e
co
n
s
id
er
ed
as
well.
T
h
e
b
est
v
alu
e
in
th
is
tab
le
is
=
60
°
an
d
1
=
30
°
with
th
e
v
alu
e
ac
cu
r
ac
y
at
9
1
.
2
3
%,
th
e
v
alu
e
o
f
p
r
ec
is
io
n
at
9
9
.
1
4
%,
th
e
v
alu
e
o
f
r
ec
all
at
8
4
.
4
8
% a
n
d
th
e
v
alu
e
o
f
F1
-
Sco
r
e
at
9
1
.
2
2
%.
T
h
e
r
esu
lts
d
em
o
n
s
tr
ate
h
ig
h
e
r
a
cc
u
r
ac
y
.
As
s
h
o
wn
in
T
ab
le
4
,
th
e
ex
p
er
im
en
t'
s
r
esu
lt
s
wer
e
o
b
tain
ed
b
y
ad
j
u
s
tin
g
th
e
v
alu
es
o
f
an
d
1
o
f
th
e
p
r
o
p
o
s
ed
HFB
L
m
o
d
el
R
1
=
3
.
5
a
n
d
R
2
=
0
.
3
.
T
h
e
b
est
v
a
lu
es
in
th
is
tab
le
ar
e
=
60
°
an
d
1
=
30
°
with
th
e
v
alu
e
o
f
ac
cu
r
ac
y
at
9
1
.
2
3
%,
th
e
v
alu
e
o
f
p
r
ec
is
io
n
at
9
9
.
0
6
%,
th
e
v
alu
e
o
f
r
ec
all
at
8
4
.
5
1
% a
n
d
th
e
v
alu
e
o
f
F1
-
Sco
r
e
at
9
1
.
2
1
%.
T
h
e
r
e
s
u
lts
h
av
e
h
ig
h
er
ac
c
u
r
ac
y
.
T
h
e
p
r
o
p
o
s
ed
HFB
L
m
o
d
el
p
r
ed
icts
“Fall”
o
r
“No
tFall”
an
d
its
r
esu
lts
ar
e
p
r
esen
ted
i
n
Fig
u
r
e
5
u
s
in
g
a
d
ataset
o
f
2
6
v
id
eo
d
at
a
s
ets.
T
h
i
s
p
r
ed
ictio
n
is
b
ased
o
n
a
d
ataset
o
f
2
6
v
id
eo
clip
s
,
ea
ch
2
m
in
u
tes in
len
g
th
an
d
with
a
r
eso
lu
tio
n
o
f
6
4
0
×
4
8
0
.
T
h
e
p
r
ed
ictio
n
r
e
s
u
lt
(
‘
Pre
d
ict’
)
is
th
at
a
p
er
s
o
n
will
f
all
b
y
th
e
p
r
o
p
o
s
ed
HFB
L
m
o
d
el
co
m
p
ar
ed
with
th
e
ex
p
ec
tatio
n
o
f
f
all
an
d
th
e
ac
tu
al
f
all.
A
s
s
h
o
wn
in
T
ab
le
5
,
th
e
∆
−
is
th
e
d
if
f
er
en
ce
b
etwe
en
t
h
e
p
r
o
p
o
s
ed
HFB
L
m
o
d
el
an
d
f
all
ex
p
ec
tatio
n
.
T
h
e
av
er
ag
e
t
im
e
o
f
f
all
with
th
e
ex
p
ec
ted
v
al
u
e
h
as
an
a
v
er
ag
e
d
if
f
er
en
ce
∆
−
at
5
.
3
1
s
ec
o
n
d
s
.
T
h
e
∆
−
is
th
e
d
if
f
er
en
ce
b
etwe
en
th
e
p
r
o
p
o
s
ed
HFB
L
m
o
d
el
an
d
ac
t
u
al
f
al
l,
th
e
av
er
ag
e
tim
e
o
f
∆
−
is
3
1
.
3
1
s
ec
o
n
d
s
.
T
ab
le
1
.
E
x
p
er
im
en
tal
r
esu
lts
o
f
ad
ju
s
tin
g
an
d
1
v
alu
es o
f
th
e
p
r
o
p
o
s
ed
HFB
L
m
o
d
el
with
o
u
t R1
an
d
R
2
β
β1
°
°
A
c
c
u
r
a
c
y
(
%)
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
F1
-
S
c
o
r
e
(
%)
30°
30°
1
5
0
°
1
5
0
°
6
8
.
4
9
9
7
.
0
3
4
2
.
9
3
5
9
.
5
3
60°
60°
1
2
0
°
1
2
0
°
7
8
.
9
1
8
6
.
8
0
7
1
.
8
7
7
8
.
6
3
80°
80°
1
0
0
°
1
0
0
°
7
7
.
1
4
7
8
.
3
5
7
9
.
6
6
7
9
.
0
0
30°
60°
1
5
0
°
1
2
0
°
7
1
.
0
1
9
6
.
4
9
4
8
.
0
3
6
4
.
1
4
30°
80°
1
5
0
°
1
0
0
°
7
2
.
3
1
9
3
.
6
0
5
2
.
2
6
6
7
.
0
7
60°
30°
1
2
0
°
1
5
0
°
7
8
.
6
8
8
7
.
2
5
7
0
.
8
5
7
8
.
2
0
T
ab
le
2
.
E
x
p
er
im
en
tal
r
esu
lts
o
f
ad
ju
s
tin
g
,
1
,
R1
=
1
.
5
a
n
d
R
2
=
0
.
7
o
f
th
e
p
r
o
p
o
s
ed
HFB
L
m
o
d
el
R1
=
1
.
5
,
R
2
=
0
.
7
β
β1
°
°
A
c
c
u
r
a
c
y
(
%)
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
F1
-
S
c
o
r
e
(
%)
80°
30°
1
0
0
°
1
5
0
°
8
7
.
1
8
8
8
.
4
9
8
7
.
5
8
8
8
.
0
3
6
0
°
3
0
°
1
2
0
°
1
5
0
°
9
1
.
1
5
9
9
.
0
6
8
4
.
3
7
9
1
.
1
2
30°
30°
1
5
0
°
1
5
0
°
7
4
.
3
5
9
9
.
4
5
5
2
.
6
7
6
8
.
8
6
30°
80°
1
5
0
°
1
0
0
°
7
9
.
8
6
9
4
.
2
2
6
6
.
6
9
7
8
.
1
0
30°
60°
1
5
0
°
1
2
0
°
7
7
.
8
1
9
8
.
5
5
5
9
.
6
8
7
4
.
3
4
T
ab
le
3
.
E
x
p
er
im
en
tal
r
esu
lts
o
f
ad
ju
s
tin
g
,
1
,
R1
=
2
.
5
a
n
d
R
2
=
0
.
4
o
f
th
e
p
r
o
p
o
s
ed
HFB
L
m
o
d
el
R1
=
2
.
5
,
R
2
=
0
.
4
β
β1
°
°
A
c
c
u
r
a
c
y
(
%)
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
F1
-
S
c
o
r
e
(
%)
80°
30°
1
0
0
°
1
5
0
°
8
7
.
2
9
8
8
.
8
2
8
7
.
4
6
8
8
.
1
4
6
0
°
3
0
°
1
2
0
°
1
5
0
°
9
1
.
2
3
9
9
.
1
4
8
4
.
4
8
9
1
.
2
2
30°
30°
1
5
0
°
1
5
0
°
7
4
.
2
7
9
9
.
5
9
5
2
.
5
5
6
8
.
8
0
30°
80°
1
5
0
°
1
0
0
°
7
9
.
8
6
9
4
.
3
3
6
6
.
6
9
7
8
.
1
4
30°
60°
1
5
0
°
1
2
0
°
7
7
.
8
1
9
8
.
6
7
5
9
.
6
9
7
4
.
3
9
T
ab
le
4
.
E
x
p
er
im
en
tal
r
esu
lts
o
f
ad
ju
s
tin
g
,
1
,
R1
=
3
.
5
a
n
d
R
2
=
0
.
3
o
f
th
e
p
r
o
p
o
s
ed
HFB
L
m
o
d
el
R1
=
3
.
5
,
R
2
=
0
.
3
β
β1
°
°
A
c
c
u
r
a
c
y
(
%)
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
F1
-
S
c
o
r
e
(
%)
80°
30°
1
0
0
°
1
5
0
°
8
7
.
2
5
8
8
.
5
0
8
7
.
7
3
8
8
.
1
1
6
0
°
3
0
°
1
2
0
°
1
5
0
°
9
1
.
2
3
9
9
.
0
6
8
4
.
5
1
9
1
.
2
1
30°
30°
1
5
0
°
1
5
0
°
7
4
.
3
9
9
9
.
4
5
5
2
.
7
4
6
8
.
9
3
30°
80°
1
5
0
°
1
0
0
°
7
9
.
8
6
9
4
.
2
2
6
6
.
6
9
7
8
.
1
0
30°
60°
1
5
0
°
1
2
0
°
7
7
.
8
9
9
8
.
5
6
5
9
.
8
2
7
4
.
4
5
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Lo
w
co
mp
lexity
h
u
ma
n
fa
ll d
e
tectio
n
u
s
in
g
b
o
d
y
lo
c
a
tio
n
a
n
d
p
o
s
tu
r
e
g
eo
metry
(
P
ip
a
t S
a
k
a
r
in
)
4627
T
ab
le
5
.
T
h
e
d
if
f
e
r
en
ce
∆
−
b
etwe
en
th
e
p
r
e
d
ictio
n
o
f
th
e
p
r
o
p
o
s
ed
HFB
L
m
o
d
el
an
d
t
h
e
ex
p
ec
tatio
n
an
d
th
e
d
if
f
er
en
ce
∆
−
b
etwe
en
p
r
ed
ictio
n
o
f
t
h
e
p
r
o
p
o
s
ed
HFB
L
an
d
th
e
ac
t
u
al
f
all
N
o
.
o
f
se
q
u
e
n
c
e
o
f
v
i
d
e
o
Ex
p
e
c
t
a
t
i
o
n
(
sec
.
)
P
r
o
p
o
se
d
H
F
B
L
m
o
d
e
l
(
sec
.
)
F
a
l
l
(
sec
.
)
∆
−
(
sec
.
)
∆
−
(
sec
.
)
1
60
62
84
2
22
4
16
16
82
0
66
8
56
58
1
0
0
2
42
10
28
32
68
4
36
17
28
30
60
2
30
26
36
36
70
0
34
T
i
m
e
a
v
e
r
a
g
e
5
.
3
1
3
1
.
3
1
Fro
m
Fig
u
r
e
6
,
it
s
h
o
ws
th
e
e
x
p
ec
ted
v
al
u
e
in
Fig
u
r
e
6
(
a)
o
f
a
p
e
r
s
o
n
f
allin
g
at
5
4
s
ec
o
n
d
s
o
f
t
h
e
v
id
eo
,
an
d
th
e
p
r
e
d
icted
v
alu
e
o
f
th
e
p
er
s
o
n
f
allin
g
o
f
th
e
p
r
o
p
o
s
ed
HFB
L
m
o
d
el
in
Fig
u
r
e
6
(
b
)
at
6
0
s
ec
o
n
d
s
o
f
th
e
v
id
eo
an
d
th
e
ac
tu
al
p
e
r
s
o
n
f
allin
g
in
Fig
u
r
e
6
(
c)
at
8
4
s
ec
o
n
d
s
o
f
th
e
v
id
eo
.
T
h
e
ex
p
ec
ted
v
alu
e
o
f
a
p
er
s
o
n
f
allin
g
in
Fig
u
r
e
6
(
d
)
at
2
8
s
ec
o
n
d
s
o
f
th
e
v
id
eo
,
th
e
p
r
ed
icted
v
alu
e
o
f
a
p
e
r
s
o
n
f
allin
g
o
f
th
e
p
r
o
p
o
s
ed
HFB
L
m
o
d
el
in
Fig
u
r
e
6
(
e)
at
3
2
s
ec
o
n
d
s
o
f
th
e
v
id
eo
,
th
e
ac
tu
al
p
er
s
o
n
f
allin
g
in
Fig
u
r
e
6
(
f
)
at
6
8
s
ec
o
n
d
s
o
f
th
e
v
id
e
o
,
an
d
th
e
ex
p
ec
ted
v
alu
e
o
f
a
p
e
r
s
o
n
f
all
in
g
in
Fig
u
r
e
6
(
g
)
at
6
6
s
ec
o
n
d
s
o
f
th
e
v
id
e
o
.
T
h
e
p
r
ed
icted
v
alu
e
o
f
a
p
er
s
o
n
f
a
llin
g
o
f
th
e
p
r
o
p
o
s
ed
HFB
L
m
o
d
el
in
Fig
u
r
e
6
(
h
)
at
7
2
s
e
co
n
d
s
o
f
th
e
v
i
d
eo
,
an
d
th
e
ac
tu
al
p
er
s
o
n
f
allin
g
in
Fig
u
r
e
6
(
i)
at
8
6
s
ec
o
n
d
s
o
f
th
e
v
id
e
o
.
Ov
er
all,
it
s
h
o
w
s
th
at
th
e
p
r
ed
icted
v
alu
e
o
f
a
p
er
s
o
n
f
allin
g
o
f
th
e
p
r
o
p
o
s
ed
HFB
L
m
o
d
el
is
clo
s
ed
to
th
e
ex
p
ec
te
d
v
alu
e
o
f
a
p
er
s
o
n
f
allin
g
a
n
d
ca
n
b
e
p
r
ed
icted
b
e
f
o
r
e
t
h
e
ac
t
u
al
p
er
s
o
n
f
alls
.
4.
CO
NCLU
SI
O
N
W
e
p
r
o
p
o
s
e
a
l
o
w
co
m
p
u
tati
o
n
al
an
d
r
eliab
le
ac
c
u
r
ate
f
al
l
d
etec
tio
n
HFB
L
m
o
d
el
u
s
in
g
h
u
m
an
b
o
d
y
l
o
ca
tio
n
an
d
p
o
s
tu
r
e
g
e
o
m
etr
y
.
T
h
e
p
r
o
p
o
s
ed
HFB
L
m
o
d
el
ap
p
lied
th
e
im
ag
e
s
e
g
m
en
tatio
n
to
f
in
d
h
u
m
an
p
o
s
tu
r
e
an
d
d
is
tan
ce
tr
an
s
f
o
r
m
to
ca
lcu
late
th
e
r
e
f
er
en
ce
p
o
i
n
ts
an
d
an
g
les
f
o
r
f
all
an
d
n
o
n
-
f
al
l
p
r
ed
ictio
n
.
A
d
ataset
o
f
2
,
5
4
2
im
ag
es
with
th
e
s
ize
o
f
6
4
0
×
4
8
0
×
3
an
d
a
d
ataset
o
f
2
6
v
id
eo
s
with
ea
ch
v
id
eo
b
ein
g
2
m
in
u
tes
lo
n
g
a
n
d
h
av
i
n
g
a
r
eso
lu
tio
n
o
f
6
4
0
×
4
8
0
f
r
o
m
th
e
UR
f
all
d
etec
tio
n
d
ataset
ar
e
p
r
e
p
ar
ed
f
o
r
s
im
u
latio
n
.
B
y
m
o
d
if
y
in
g
o
n
l
y
an
d
o
f
th
e
p
r
o
p
o
s
ed
HFB
L
m
o
d
el,
th
e
ac
c
u
r
ac
y
v
alu
e
is
9
1
.
2
3
%,
th
e
p
r
ec
is
io
n
v
alu
e
is
9
9
.
1
4
%,
th
e
r
ec
all
v
alu
e
is
8
4
.
4
8
%,
an
d
th
e
F1
-
s
co
r
e
v
alu
e
is
9
1
.
2
2
%.
T
h
e
p
r
ed
ictio
n
o
f
f
aller
s
b
y
th
e
p
r
o
p
o
s
ed
HFB
L
m
o
d
el
ca
n
p
r
ed
ict
f
aller
s
clo
s
e
to
th
e
ex
p
ec
ted
f
aller
v
al
u
e
at
a
n
a
v
er
ag
e
o
f
5
.
3
1
s
ec
o
n
d
s
,
a
n
d
th
e
p
r
ed
icti
o
n
v
al
u
e
o
f
f
aller
s
b
y
th
e
p
r
o
p
o
s
ed
HFB
L
m
o
d
el
ca
n
p
r
ed
i
ct
f
aller
s
i
n
a
d
v
a
n
c
e
w
i
t
h
t
h
e
a
c
t
u
al
f
a
ll
e
r
v
a
l
u
e
a
t
an
a
v
e
r
a
g
e
o
f
3
1
.
3
1
s
e
c
o
n
d
s
.
F
u
t
u
r
e
w
o
r
k
o
n
t
h
e
p
r
o
p
o
s
e
d
m
o
d
e
l
m
a
y
i
n
c
o
r
p
o
r
a
t
e
a
d
a
p
t
i
v
e
,
t
r
a
c
k
i
n
g
,
a
n
d
t
i
m
e
-
b
a
s
e
d
f
u
n
c
t
i
o
n
s
w
it
h
h
i
g
h
a
c
c
u
r
a
c
y
.
T
h
e
s
e
i
m
p
r
o
v
e
m
en
t
s
a
i
m
t
o
r
e
d
u
c
e
m
i
s
p
r
e
d
i
c
ti
o
n
s
c
a
u
s
e
d
b
y
h
i
g
h
-
a
n
g
l
e
a
n
d
i
n
s
u
f
f
i
c
i
e
n
t
l
i
g
h
tin
g
,
i
m
p
r
o
v
e
a
c
c
u
r
a
c
y
f
o
r
a
c
t
i
v
i
t
i
es
s
u
c
h
a
s
l
y
i
n
g
d
o
w
n
o
r
k
n
e
e
l
i
n
g
,
a
n
d
e
n
a
b
l
e
m
u
l
t
i
-
p
e
r
s
o
n
p
r
e
d
i
c
ti
o
n
,
t
h
u
s
o
v
e
r
c
o
m
i
n
g
t
h
e
c
u
r
r
e
n
t
s
i
n
g
l
e
-
p
e
r
s
o
n
l
i
m
it
a
t
i
o
n
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
in
v
o
lv
ed
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Pip
at
Sak
ar
in
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Su
ch
ad
a
Sit
jo
n
g
s
atap
o
r
n
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
6
2
0
-
4
6
2
9
4628
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
i
n
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
o
p
en
ly
av
ailab
le
in
UR
f
all
d
etec
tio
n
d
atasets
a
t
h
ttp
:
//d
o
i.o
r
g
/
1
0
.
1
0
1
6
/j.c
mp
b
.
2
0
1
4
.
0
9
.
0
0
5
,
[
2
7
]
.
RE
F
E
R
E
NC
E
S
[
1
]
U
n
i
t
e
d
N
a
t
i
o
n
s
,
“
W
o
r
l
d
p
o
p
u
l
a
t
i
o
n
p
r
o
s
p
e
c
t
s
2
0
2
4
:
su
m
mary
o
f
r
e
s
u
l
t
s,
”
U
n
i
t
e
d
N
a
t
i
o
n
s
D
e
p
a
r
t
m
e
n
t
o
f
Ec
o
n
o
m
i
c
a
n
d
S
o
c
i
a
l
Af
f
a
i
rs
,
P
o
p
u
l
a
t
i
o
n
D
i
v
i
s
i
o
n
,
p
p
.
1
–
5
2
,
2
0
2
4
.
[
2
]
T.
H
.
Jo
,
J.
H
.
M
a
,
a
n
d
S
.
H
.
C
h
a
,
“
El
d
e
r
l
y
p
e
r
c
e
p
t
i
o
n
o
n
t
h
e
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
-
b
a
se
d
i
n
t
e
g
r
a
t
e
d
sm
a
r
t
-
h
o
m
e
s
y
st
e
m,”
S
e
n
s
o
rs
,
v
o
l
.
2
1
,
n
o
.
4
,
p
.
1
2
8
4
,
F
e
b
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
1
0
4
1
2
8
4
.
[
3
]
I
.
B
o
u
k
h
e
n
n
o
u
f
a
,
A
.
A
mi
r
a
,
F
.
B
e
n
s
a
a
l
i
,
a
n
d
S
.
S
.
Esf
a
h
a
n
i
,
“
A
n
o
v
e
l
g
a
t
e
w
a
y
-
b
a
se
d
s
o
l
u
t
i
o
n
f
o
r
r
e
m
o
t
e
e
l
d
e
r
l
y
m
o
n
i
t
o
r
i
n
g
,
”
J
o
u
rn
a
l
o
f
Bi
o
m
e
d
i
c
a
l
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
0
9
,
p
.
1
0
3
5
2
1
,
S
e
p
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
b
i
.
2
0
2
0
.
1
0
3
5
2
1
.
[
4
]
D
.
R
.
B
e
d
d
i
a
r
,
M
.
O
u
ssa
l
a
h
,
a
n
d
B
.
N
i
n
i
,
“
F
a
l
l
d
e
t
e
c
t
i
o
n
u
si
n
g
b
o
d
y
g
e
o
met
r
y
a
n
d
h
u
ma
n
p
o
se
e
st
i
ma
t
i
o
n
i
n
v
i
d
e
o
se
q
u
e
n
c
e
s,”
J
o
u
rn
a
l
o
f
Vi
s
u
a
l
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
I
m
a
g
e
R
e
p
r
e
se
n
t
a
t
i
o
n
,
v
o
l
.
8
2
,
p
.
1
0
3
4
0
7
,
Ja
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
v
c
i
r
.
2
0
2
1
.
1
0
3
4
0
7
.
[
5
]
F
.
H
a
r
r
o
u
,
N
.
Z
e
r
r
o
u
k
i
,
Y
.
S
u
n
,
a
n
d
A
.
H
o
u
a
c
i
n
e
,
“
A
n
i
n
t
e
g
r
a
t
e
d
v
i
si
o
n
-
b
a
s
e
d
a
p
p
r
o
a
c
h
f
o
r
e
f
f
i
c
i
e
n
t
h
u
m
a
n
f
a
l
l
d
e
t
e
c
t
i
o
n
i
n
a
h
o
m
e
e
n
v
i
r
o
n
me
n
t
,
”
I
E
EE
Ac
c
e
ss
,
v
o
l
.
7
,
p
p
.
1
1
4
9
6
6
–
1
1
4
9
7
4
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
3
6
3
2
0
.
[
6
]
J.
Zh
a
n
g
,
C
.
W
u
,
a
n
d
Y
.
W
a
n
g
,
“
H
u
man
f
a
l
l
d
e
t
e
c
t
i
o
n
b
a
se
d
o
n
b
o
d
y
p
o
s
t
u
r
e
sp
a
t
i
o
-
t
e
m
p
o
r
a
l
e
v
o
l
u
t
i
o
n
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
0
,
n
o
.
3
,
p
.
9
4
6
,
F
e
b
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
0
0
3
0
9
4
6
.
[
7
]
C.
-
B
.
Li
n
,
Z
.
D
o
n
g
,
W
.
-
K
.
K
u
a
n
,
a
n
d
Y
.
-
F
.
H
u
a
n
g
,
“
A
f
r
a
mew
o
r
k
f
o
r
f
a
l
l
d
e
t
e
c
t
i
o
n
b
a
s
e
d
o
n
O
p
e
n
P
o
se
S
k
e
l
e
t
o
n
a
n
d
LSTM
/
G
R
U
m
o
d
e
l
s,”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
1
,
n
o
.
1
,
p
.
3
2
9
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
1
0
1
0
3
2
9
.
[
8
]
K
.
H
a
n
,
Q
.
Y
a
n
g
,
a
n
d
Z.
H
u
a
n
g
,
“
A
t
w
o
-
st
a
g
e
f
a
l
l
r
e
c
o
g
n
i
t
i
o
n
a
l
g
o
r
i
t
h
m
b
a
se
d
o
n
h
u
m
a
n
p
o
s
t
u
r
e
f
e
a
t
u
r
e
s,
”
S
e
n
s
o
rs
(
S
w
i
t
zer
l
a
n
d
)
,
v
o
l
.
2
0
,
n
o
.
2
3
,
p
p
.
1
–
2
1
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
0
2
3
6
9
6
6
.
[
9
]
W
.
C
h
e
n
,
Z
.
J
i
a
n
g
,
H
.
G
u
o
,
a
n
d
X
.
N
i
,
“
F
a
l
l
d
e
t
e
c
t
i
o
n
b
a
se
d
o
n
k
e
y
p
o
i
n
t
s
o
f
h
u
m
a
n
-
S
k
e
l
e
t
o
n
u
si
n
g
O
p
e
n
P
o
se,
”
S
y
m
m
e
t
ry
,
v
o
l
.
1
2
,
n
o
.
5
,
p
.
7
4
4
,
M
a
y
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
s
y
m1
2
0
5
0
7
4
4
.
[
1
0
]
M
.
S
a
l
i
m
i
,
J.
J
.
M
.
M
a
c
h
a
d
o
,
a
n
d
J.
M
.
R
.
S
.
Ta
v
a
r
e
s,
“
U
si
n
g
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
s
f
o
r
h
u
m
a
n
f
a
l
l
d
e
t
e
c
t
i
o
n
b
a
se
d
o
n
p
o
s
e
e
st
i
mat
i
o
n
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
2
,
n
o
.
1
2
,
p
.
4
5
4
4
,
Ju
n
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
2
1
2
4
5
4
4
.
[
1
1
]
O
.
K
e
sk
e
s
a
n
d
R
.
N
o
u
me
i
r
,
“
V
i
si
o
n
-
b
a
se
d
f
a
l
l
d
e
t
e
c
t
i
o
n
u
s
i
n
g
S
T
-
G
C
N
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
9
,
p
p
.
2
8
2
2
4
–
2
8
2
3
6
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
0
5
8
2
1
9
.
[
1
2
]
A
.
I
a
z
z
i
,
M
.
R
z
i
z
a
,
a
n
d
R
.
O
u
l
a
d
H
a
j
Th
a
m
i
,
“
F
a
l
l
d
e
t
e
c
t
i
o
n
s
y
s
t
e
m
-
b
a
s
e
d
p
o
s
t
u
r
e
-
r
e
c
o
g
n
i
t
i
o
n
f
o
r
i
n
d
o
o
r
e
n
v
i
r
o
n
me
n
t
s
,
”
J
o
u
rn
a
l
o
f
I
m
a
g
i
n
g
,
v
o
l
.
7
,
n
o
.
3
,
p
.
4
2
,
F
e
b
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
j
i
m
a
g
i
n
g
7
0
3
0
0
4
2
.
[
1
3
]
H
.
R
a
mi
r
e
z
,
S
.
A
.
V
e
l
a
st
i
n
,
I
.
M
e
z
a
,
E.
F
a
b
r
e
g
a
s,
D
.
M
a
k
r
i
s,
a
n
d
G
.
F
a
r
i
a
s,
“
F
a
l
l
d
e
t
e
c
t
i
o
n
a
n
d
a
c
t
i
v
i
t
y
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
h
u
ma
n
sk
e
l
e
t
o
n
f
e
a
t
u
r
e
s,
”
I
E
EE
A
c
c
e
ss
,
v
o
l
.
9
,
p
p
.
3
3
5
3
2
–
3
3
5
4
2
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
0
6
1
6
2
6
.
[
1
4
]
Y.
-
H
.
Li
u
,
P
.
C
.
K
.
H
u
n
g
,
F
.
I
q
b
a
l
,
a
n
d
B
.
C
.
M
.
F
u
n
g
,
“
A
u
t
o
m
a
t
i
c
f
a
l
l
r
i
sk
d
e
t
e
c
t
i
o
n
b
a
s
e
d
o
n
i
m
b
a
l
a
n
c
e
d
d
a
t
a
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
9
,
p
p
.
1
6
3
5
9
4
–
1
6
3
6
1
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
1
3
3
2
9
7
.
[
1
5
]
Y.
-
K
.
K
a
n
g
,
H
.
-
Y
.
K
a
n
g
,
a
n
d
D
.
-
S
.
W
e
o
n
,
“
F
a
l
l
d
e
t
e
c
t
i
o
n
b
a
s
e
d
o
n
h
u
ma
n
S
k
e
l
e
t
o
n
k
e
y
p
o
i
n
t
s u
si
n
g
G
R
U
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
t
e
r
n
e
t
,
Br
o
a
d
c
a
st
i
n
g
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
,
v
o
l
.
1
2
,
p
p
.
8
3
–
9
2
,
2
0
2
0
,
d
o
i
:
1
0
.
7
2
3
6
/
I
J
I
B
C
.
2
0
2
0
.
1
2
.
4
.
8
3
.
[
1
6
]
M
.
T
a
u
f
e
e
q
u
e
,
S
.
K
o
i
t
a
,
N
.
S
p
i
c
h
e
r
,
a
n
d
T.
M
.
D
e
s
e
r
n
o
,
“
M
u
l
t
i
-
c
a
m
e
r
a
,
m
u
l
t
i
-
p
e
r
s
o
n
,
a
n
d
r
e
a
l
-
t
i
me
f
a
l
l
d
e
t
e
c
t
i
o
n
u
si
n
g
l
o
n
g
s
h
o
r
t
t
e
r
m
mem
o
r
y
,
”
i
n
M
e
d
i
c
a
l
I
m
a
g
i
n
g
2
0
2
1
:
I
m
a
g
i
n
g
I
n
f
o
rm
a
t
i
c
s
f
o
r
H
e
a
l
t
h
c
a
re
,
Re
se
a
r
c
h
,
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
F
e
b
.
2
0
2
1
,
p
.
8
,
d
o
i
:
1
0
.
1
1
1
7
/
1
2
.
2
5
8
0
7
0
0
.
[
1
7
]
S
.
M
i
n
a
e
e
,
Y
.
Y
.
B
o
y
k
o
v
,
F
.
P
o
r
i
k
l
i
,
A
.
J.
P
l
a
z
a
,
N
.
K
e
h
t
a
r
n
a
v
a
z
,
a
n
d
D
.
T
e
r
z
o
p
o
u
l
o
s
,
“
I
mag
e
se
g
m
e
n
t
a
t
i
o
n
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
:
a
su
r
v
e
y
,
”
I
EE
E
T
r
a
n
s
a
c
t
i
o
n
s
o
n
P
a
t
t
e
rn
An
a
l
y
si
s
a
n
d
Ma
c
h
i
n
e
I
n
t
e
l
l
i
g
e
n
c
e
,
p
p
.
1
–
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
TPA
M
I
.
2
0
2
1
.
3
0
5
9
9
6
8
.
[
1
8
]
T.
S
t
r
u
t
z
,
“
T
h
e
d
i
st
a
n
c
e
t
r
a
n
sf
o
r
m
a
n
d
i
t
s
c
o
mp
u
t
a
t
i
o
n
,
”
a
rX
i
v
:
2
1
0
6
.
0
3
5
0
3
,
2
0
2
3
.
[
1
9
]
N
.
S
i
d
d
i
q
u
e
,
S
.
P
a
h
e
d
i
n
g
,
C
.
P
.
El
k
i
n
,
a
n
d
V
.
D
e
v
a
b
h
a
k
t
u
n
i
,
“
U
-
n
e
t
a
n
d
i
t
s
v
a
r
i
a
n
t
s
f
o
r
me
d
i
c
a
l
i
ma
g
e
s
e
g
me
n
t
a
t
i
o
n
:
a
r
e
v
i
e
w
o
f
t
h
e
o
r
y
a
n
d
a
p
p
l
i
c
a
t
i
o
n
s,
”
I
EE
E
A
c
c
e
s
s
,
v
o
l
.
9
,
p
p
.
8
2
0
3
1
–
8
2
0
5
7
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
0
8
6
0
2
0
.
[
2
0
]
N
.
M
.
A
.
-
M
.
M
.
A
l
-
M
o
o
s
a
w
i
a
n
d
R
.
S
.
K
h
u
d
e
y
e
r
,
“
R
e
sN
e
t
-
3
4
/
D
R
:
a
r
e
si
d
u
a
l
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
t
h
e
d
i
a
g
n
o
s
i
s
o
f
d
i
a
b
e
t
i
c
r
e
t
i
n
o
p
a
t
h
y
,
”
I
n
f
o
rm
a
t
i
c
a
,
v
o
l
.
4
5
,
n
o
.
7
,
D
e
c
.
2
0
2
1
,
d
o
i
:
1
0
.
3
1
4
4
9
/
i
n
f
.
v
4
5
i
7
.
3
7
7
4
.
[
2
1
]
R
.
A
.
N
si
a
h
,
S
.
M
a
n
t
e
y
,
a
n
d
Y
.
Y
.
Zi
g
g
a
h
,
“
B
u
i
l
d
i
n
g
s
e
g
me
n
t
a
t
i
o
n
f
r
o
m
U
A
V
o
r
t
h
o
m
o
sa
i
c
s
u
si
n
g
U
N
e
t
-
r
e
sn
e
t
-
3
4
o
p
t
i
mi
s
e
d
w
i
t
h
g
r
e
y
w
o
l
f
o
p
t
i
m
i
sat
i
o
n
a
l
g
o
r
i
t
h
m,
”
S
m
a
r
t
C
o
n
s
t
r
u
c
t
i
o
n
a
n
d
S
u
st
a
i
n
a
b
l
e
C
i
t
i
e
s
,
v
o
l
.
1
,
n
o
.
1
,
p
.
2
1
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
4
2
6
8
-
023
-
0
0
0
1
9
-
x.
[
2
2
]
M
.
G
a
o
,
D
.
Q
i
,
H
.
M
u
,
a
n
d
J.
C
h
e
n
,
“
A
t
r
a
n
sf
e
r
r
e
si
d
u
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
b
a
sed
o
n
R
e
sN
e
t
-
3
4
f
o
r
d
e
t
e
c
t
i
o
n
o
f
w
o
o
d
k
n
o
t
d
e
f
e
c
t
s
,
”
Fo
res
t
s
,
v
o
l
.
1
2
,
n
o
.
2
,
p
.
2
1
2
,
F
e
b
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
f
1
2
0
2
0
2
1
2
.
[
2
3
]
R
.
M
N
a
n
d
C
.
B
S
,
“
P
r
o
st
a
t
e
g
l
a
n
d
s
e
g
me
n
t
a
t
i
o
n
u
s
i
n
g
sem
a
n
t
i
c
s
e
g
men
t
a
t
i
o
n
m
o
d
e
l
s
U
-
N
e
t
a
n
d
Li
n
k
N
e
t
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
E
n
g
i
n
e
e
r
i
n
g
T
r
e
n
d
s
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
7
0
,
n
o
.
1
2
,
p
p
.
2
5
2
–
2
7
1
,
D
e
c
.
2
0
2
2
,
d
o
i
:
1
0
.
1
4
4
4
5
/
2
2
3
1
5
3
8
1
/
I
JETT
-
V
7
0
I
1
2
P
2
2
4
.
[
2
4
]
M
.
A
l
a
b
d
u
l
h
a
f
i
t
h
e
t
a
l
.
,
“
A
u
t
o
m
a
t
e
d
w
o
u
n
d
c
a
r
e
b
y
e
m
p
l
o
y
i
n
g
a
r
e
l
i
a
b
l
e
U
-
N
e
t
a
r
c
h
i
t
e
c
t
u
r
e
c
o
m
b
i
n
e
d
w
i
t
h
R
e
sN
e
t
f
e
a
t
u
r
e
e
n
c
o
d
e
r
s f
o
r
m
o
n
i
t
o
r
i
n
g
c
h
r
o
n
i
c
w
o
u
n
d
s
,
”
Fro
n
t
i
e
rs i
n
Me
d
i
c
i
n
e
,
v
o
l
.
1
1
,
J
a
n
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
8
9
/
f
m
e
d
.
2
0
2
4
.
1
3
1
0
1
3
7
.
[
2
5
]
C.
-
S
.
H
u
,
A
.
L
a
w
so
n
,
Y
.
-
M
.
C
h
u
n
g
,
a
n
d
K
.
K
e
e
g
a
n
,
“
Tw
o
-
p
a
r
a
m
e
t
e
r
p
e
r
si
st
e
n
c
e
f
o
r
i
ma
g
e
s
v
i
a
d
i
s
t
a
n
c
e
t
r
a
n
sf
o
r
m,
”
i
n
2
0
2
1
I
EEE/
C
VF
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
Vi
s
i
o
n
W
o
r
k
sh
o
p
s
(
I
C
C
V
W)
,
O
c
t
.
2
0
2
1
,
p
p
.
4
1
5
9
–
4
1
6
7
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
V
W
5
4
1
2
0
.
2
0
2
1
.
0
0
4
6
4
.
[
2
6
]
X
.
Li
e
t
a
l
.
,
“
W
D
TI
S
e
g
:
o
n
e
-
st
a
g
e
i
n
t
e
r
a
c
t
i
v
e
s
e
g
m
e
n
t
a
t
i
o
n
f
o
r
b
r
e
a
s
t
u
l
t
r
a
so
u
n
d
i
m
a
g
e
u
si
n
g
w
e
i
g
h
t
e
d
d
i
s
t
a
n
c
e
t
r
a
n
sf
o
r
m
a
n
d
sh
a
p
e
-
a
w
a
r
e
c
o
m
p
o
u
n
d
l
o
ss
,
”
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
1
,
n
o
.
1
4
,
p
.
6
2
7
9
,
Ju
l
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
1
1
4
6
2
7
9
.
[
2
7
]
B
.
K
w
o
l
e
k
a
n
d
M
.
K
e
p
s
k
i
,
“
H
u
m
a
n
f
a
l
l
d
e
t
e
c
t
i
o
n
o
n
e
m
b
e
d
d
e
d
p
l
a
t
f
o
r
m
u
si
n
g
d
e
p
t
h
m
a
p
s
a
n
d
w
i
r
e
l
e
ss
a
c
c
e
l
e
r
o
met
e
r
,
”
C
o
m
p
u
t
e
r
M
e
t
h
o
d
s
a
n
d
Pr
o
g
r
a
m
s
i
n
Bi
o
m
e
d
i
c
i
n
e
,
v
o
l
.
1
1
7
,
n
o
.
3
,
p
p
.
4
8
9
–
5
0
1
,
D
e
c
.
2
0
1
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
m
p
b
.
2
0
1
4
.
0
9
.
0
0
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Lo
w
co
mp
lexity
h
u
ma
n
fa
ll d
e
tectio
n
u
s
in
g
b
o
d
y
lo
c
a
tio
n
a
n
d
p
o
s
tu
r
e
g
eo
metry
(
P
ip
a
t S
a
k
a
r
in
)
4629
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Pi
p
a
t
S
a
k
a
r
i
n
re
c
e
iv
e
d
t
h
e
B.
E
n
g
.
d
e
g
re
e
i
n
e
lec
tri
c
a
l
e
n
g
in
e
e
rin
g
fro
m
M
a
h
a
n
a
k
o
r
n
Un
i
v
e
rsity
o
f
Tec
h
n
o
l
o
g
y
,
T
h
a
il
a
n
d
i
n
1
9
9
9
a
n
d
M
.
En
g
.
d
e
g
re
e
in
e
lec
tri
c
a
l
e
n
g
in
e
e
rin
g
in
2
0
0
5
.
C
u
rre
n
tl
y
,
h
e
h
o
ld
s
a
P
h
.
D.
in
e
lec
tri
c
a
l
e
n
g
in
e
e
rin
g
(e
lec
tro
n
ic)
in
M
a
h
a
n
a
k
o
r
n
Un
i
v
e
rsity
o
f
Te
c
h
n
o
l
o
g
y
,
Th
a
il
a
n
d
.
His
re
se
a
rc
h
in
tere
sts
a
re
a
rti
ficia
l
in
telli
g
e
n
c
e
(AI),
m
a
c
h
in
e
lea
rn
i
n
g
,
a
n
d
e
m
b
e
d
d
e
d
sy
ste
m
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
p
ip
a
t.
s
k
r@g
m
a
il
.
c
o
m
.
S
u
c
h
a
d
a
S
itj
o
n
g
s
a
ta
p
o
r
n
re
c
e
iv
e
d
t
h
e
B.
E
n
g
.
d
e
g
re
e
(
first
-
c
las
s
h
o
n
o
u
rs)
a
n
d
D.E
n
g
.
d
e
g
re
e
in
e
lec
tro
n
ic
e
n
g
i
n
e
e
rin
g
fr
o
m
M
a
h
a
n
a
k
o
r
n
Un
iv
e
rsity
o
f
Tec
h
n
o
l
o
g
y
,
Ba
n
g
k
o
k
,
Th
a
il
a
n
d
i
n
2
0
0
2
a
n
d
2
0
0
9
.
S
h
e
h
a
s
wo
r
k
e
d
a
s
lec
tu
re
r
a
t
th
e
De
p
a
rtme
n
t
o
f
El
e
c
tro
n
ic
En
g
in
e
e
ri
n
g
,
M
a
h
a
n
a
k
o
r
n
Un
iv
e
rsit
y
o
f
Tec
h
n
o
l
o
g
y
sin
c
e
2
0
0
2
.
Cu
r
re
n
tl
y
,
sh
e
is
a
n
a
ss
o
c
iate
p
ro
fe
ss
o
r
in
e
lec
tro
n
ic
e
n
g
in
e
e
rin
g
,
th
e
a
ss
istan
t
p
re
si
d
e
n
t
fo
r
Re
se
a
rc
h
a
n
d
De
a
n
o
f
G
ra
d
u
a
te
Co
ll
e
g
e
i
n
M
a
h
a
n
a
k
o
r
n
Un
i
v
e
rsity
o
f
Tec
h
n
o
l
o
g
y
.
He
r
re
se
a
rc
h
in
tere
sts
a
re
m
a
th
e
m
a
ti
c
a
l
a
n
d
sta
ti
stica
l
m
o
d
e
ls
in
t
h
e
a
re
a
o
f
a
d
a
p
t
iv
e
sig
n
a
l
p
ro
c
e
s
sin
g
fo
r
c
o
m
m
u
n
ica
ti
o
n
s,
n
e
two
r
k
in
g
,
e
m
b
e
d
d
e
d
sy
ste
m
,
m
a
c
h
in
e
le
a
rn
in
g
,
ima
g
e
a
n
d
v
id
e
o
p
ro
c
e
ss
in
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ss
u
c
h
a
d
a
@m
u
t.
a
c
.
th
.
Evaluation Warning : The document was created with Spire.PDF for Python.