I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Ro
bo
t
ics a
nd
Aut
o
m
a
t
io
n
(
I
J
RA)
Vo
l.
1
5
,
No
.
1
,
Ma
r
ch
20
2
6
,
p
p
.
2
4
7
~
2
5
6
I
SS
N:
2722
-
2
5
8
6
,
DOI
:
1
0
.
1
1
5
9
1
/i
jr
a
.
v
1
5
i
1
.
pp
2
4
7
-
256
247
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
r
a
.
ia
esco
r
e.
co
m
An impro
v
ed blac
k
-
wing
ed
kite
alg
o
rithm optimiz
ed
ba
ck
-
pro
pa
g
a
tion neura
l net
wo
rk
for bic
eps curl
cla
ss
ifica
tion
Chun
qin
g
L
i
u
1
,
K
im
G
eo
k So
h
1
,
H
a
zizi
Abu Sa
a
d
2
,
H
a
o
h
a
o
M
a
3
1
F
a
c
u
l
t
y
o
f
Ed
u
c
a
t
i
o
n
a
l
S
t
u
d
i
e
s
,
U
n
i
v
e
r
si
t
i
P
u
t
r
a
M
a
l
a
y
s
i
a
,
S
e
r
d
a
n
g
,
M
a
l
a
y
si
a
2
F
a
c
u
l
t
y
o
f
M
e
d
i
c
i
n
e
a
n
d
H
e
a
l
t
h
S
c
i
e
n
c
e
s
,
U
n
i
v
e
r
s
i
t
i
P
u
t
r
a
M
a
l
a
y
s
i
a
,
S
e
r
d
a
n
g
,
M
a
l
a
y
si
a
3
F
a
c
u
l
t
y
o
f
En
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
s
i
t
i
P
u
t
r
a
M
a
l
a
y
si
a
,
S
e
r
d
a
n
g
,
M
a
l
a
y
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
y
7
,
2
0
2
5
R
ev
is
ed
Feb
9
,
2
0
2
6
Acc
ep
ted
Feb
2
1
,
2
0
2
6
Ac
c
u
ra
tely
id
e
n
ti
f
y
in
g
a
n
d
c
l
a
ss
ify
in
g
b
ice
p
s
c
u
rl
t
y
p
e
s
is
o
f
v
it
a
l
imp
o
rtan
c
e
fo
r
sp
o
rts
train
in
g
a
n
d
u
p
p
e
r
l
imb
j
o
in
t
re
h
a
b
i
li
tatio
n
t
ra
in
in
g
.
It
c
a
n
imp
ro
v
e
t
h
e
e
ffe
c
t
a
n
d
re
d
u
c
e
th
e
risk
o
f
in
ju
r
y
c
a
u
se
d
b
y
i
n
c
o
rre
c
t
train
in
g
.
I
n
t
h
is
stu
d
y
,
a
d
a
tas
e
t
o
f
b
ice
p
s
c
u
rl
train
i
n
g
wa
s
o
b
tain
e
d
b
y
m
e
a
su
rin
g
we
a
ra
b
le
se
n
so
rs.
Aft
e
r
d
a
ta
p
re
p
r
o
c
e
ss
in
g
,
3
4
0
sa
m
p
les
o
f
3
5
-
d
ime
n
sio
n
a
l
fe
a
tu
re
d
a
ta
we
re
o
b
tai
n
e
d
.
Th
e
c
las
sifica
ti
o
n
lab
e
ls
o
f
th
e
d
a
tas
e
t
we
re
m
a
rk
e
d
a
s
1
-
5
a
c
c
o
rd
in
g
t
o
t
h
e
fi
v
e
t
y
p
e
s
o
f
b
ice
p
s
c
u
rl.
T
h
is
stu
d
y
p
r
o
p
o
se
d
a
b
lac
k
-
win
g
e
d
k
it
e
a
lg
o
rit
h
m
(IBKA
)
th
a
t
u
se
s
th
e
g
o
o
d
p
o
i
n
t
se
t
(G
P
S
)
m
e
th
o
d
a
n
d
th
e
a
d
a
p
ti
v
e
sp
iral
se
a
rc
h
ru
le,
a
m
u
lt
i
-
stra
teg
y
.
IBKA
o
p
t
imiz
e
d
t
h
e
i
n
it
ial
we
ig
h
ts,
b
ias
e
s,
a
n
d
h
id
d
e
n
lay
e
r
n
u
m
b
e
rs
a
n
d
p
ro
v
id
e
d
th
e
m
t
o
th
e
b
a
c
k
-
p
r
o
p
a
g
a
ti
o
n
n
e
u
ra
l
n
e
two
rk
(BP
NN
)
t
o
e
sta
b
li
sh
th
e
IBKA
-
BP
NN
m
o
d
e
l
.
T
h
e
c
o
n
stru
c
ted
IBKA
-
BP
NN
m
o
d
e
l
imp
ro
v
e
d
th
e
c
las
sifica
ti
o
n
a
c
c
u
ra
c
y
o
f
th
e
train
in
g
se
t
fro
m
7
9
.
8
3
%
t
o
9
4
.
5
4
%
,
a
n
d
t
h
e
a
c
c
u
ra
c
y
o
f
th
e
tes
t
se
t
fro
m
6
9
.
6
1
%
to
8
8
.
3
3
%
.
Th
e
IBKA
-
BP
NN
m
o
d
e
l
pr
o
p
o
se
d
i
n
t
h
is stu
d
y
p
r
o
v
i
d
e
s a
re
li
a
b
le d
e
c
isio
n
-
m
a
k
i
n
g
b
a
sis fo
r
re
a
l
-
ti
m
e
c
o
a
c
h
in
g
,
a
th
lete
p
e
rfo
rm
a
n
c
e
a
n
a
ly
sis,
a
n
d
u
p
p
e
r
li
m
b
re
h
a
b
il
i
tati
o
n
.
F
u
tu
re
wo
rk
will
e
x
p
a
n
d
t
h
e
d
a
tas
e
t,
in
teg
ra
te
m
o
re
b
io
sig
n
a
ls,
a
n
d
e
x
p
l
o
re
li
g
h
twe
i
g
h
t
d
e
p
l
o
y
m
e
n
t
o
n
we
a
ra
b
le h
a
rd
wa
re
.
K
ey
w
o
r
d
s
:
B
icep
cu
r
l
B
lack
-
win
g
ed
k
ite
alg
o
r
ith
m
B
P n
eu
r
al
n
etwo
r
k
C
las
s
if
icatio
n
Go
o
d
p
o
in
t set
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
:
Kim
Geo
k
So
h
Facu
lty
o
f
E
d
u
ca
tio
n
al
Stu
d
ie
s
,
Un
iv
er
s
iti Pu
tr
a
Ma
lay
s
ia
Ser
d
an
g
,
Ma
lay
s
ia
E
m
ail: k
im
s
@
u
p
m
.
ed
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
No
wad
ay
s
,
p
eo
p
le
p
a
y
m
o
r
e
a
n
d
m
o
r
e
atten
tio
n
to
p
h
y
s
ical
h
ea
lth
an
d
s
tr
en
g
th
e
n
s
p
o
r
ts
tr
ain
in
g
[
1
]
.
Am
o
n
g
th
e
m
,
b
ice
p
s
cu
r
l
is
a
p
ar
ticu
lar
ly
c
o
m
m
o
n
tr
ain
in
g
m
o
v
em
en
t.
Fro
m
t
h
e
p
er
s
p
ec
t
iv
e
o
f
r
o
b
o
tics
,
th
is
s
p
o
r
ts
tr
ain
in
g
is
a
s
in
g
le
-
jo
i
n
t
elb
o
w
f
lex
io
n
ex
er
cise,
w
h
ich
ca
n
m
a
k
e
th
e
b
o
d
y
m
o
r
e
b
ea
u
tifu
l
an
d
ca
n
ex
er
cise
th
e
b
icep
s
,
b
r
ac
h
iali
s
,
an
d
b
r
ac
h
i
o
r
ad
ialis
[
2
]
,
[
3
]
.
B
icep
s
cu
r
l
is
clo
s
ely
r
ela
ted
to
p
r
o
f
ess
io
n
al
s
tr
en
g
th
tr
ain
in
g
an
d
d
aily
life
,
s
u
ch
as
weig
h
tliftin
g
an
d
ca
r
r
y
in
g
g
o
o
d
s
.
I
t
is
also
o
n
e
o
f
th
e
r
eg
u
lar
tr
ain
in
g
item
s
in
u
p
p
er
lim
b
r
eh
a
b
ilit
atio
n
tr
ain
in
g
.
I
t
is
v
er
y
im
p
o
r
tan
t
to
p
er
f
o
r
m
th
e
c
o
r
r
ec
t
b
icep
s
cu
r
l
ty
p
e
,
as
in
co
r
r
ec
t
p
o
s
tu
r
e
d
u
r
in
g
tr
ain
in
g
will
n
o
t
o
n
ly
f
ail
to
ac
h
iev
e
th
e
d
esire
d
tr
ain
in
g
ef
f
ec
t,
b
u
t
m
ay
ev
en
ca
u
s
e
elb
o
w
an
d
s
h
o
u
ld
er
in
ju
r
ies.
E
s
p
ec
ially
f
o
r
p
r
o
f
ess
io
n
al
ath
letes
an
d
u
p
p
er
lim
b
r
eh
a
b
ilit
atio
n
tr
ain
er
s
,
p
er
f
o
r
m
in
g
ac
cu
r
ate
b
icep
s
cu
r
ls
is
cr
u
cial
[
4
]
–
[
6
]
.
Du
r
in
g
p
r
o
f
es
s
io
n
al
s
p
o
r
ts
tr
ain
i
n
g
,
tr
ain
ee
s
ar
e
r
e
q
u
ir
e
d
to
ca
r
r
y
o
u
t
s
tan
d
ar
d
ized
tr
ain
i
n
g
ac
co
r
d
in
g
to
t
h
e
b
ice
p
s
cu
r
l
ty
p
e
ac
c
u
r
ately
[
7
]
.
I
n
r
e
ce
n
t
y
ea
r
s
,
with
th
e
im
p
r
o
v
em
en
t
o
f
s
en
s
o
r
m
ea
s
u
r
em
en
t
tech
n
o
l
o
g
y
an
d
co
m
p
u
ter
in
f
o
r
m
atio
n
tec
h
n
o
lo
g
y
[
8
]
,
[
9
]
,
m
an
y
s
ch
o
lar
s
h
av
e
in
teg
r
ated
co
m
p
u
tatio
n
al
tech
n
o
lo
g
y
s
p
o
r
ts
tr
ain
in
g
in
to
s
p
o
r
ts
tr
ain
in
g
an
d
ac
h
iev
e
d
m
an
y
r
esu
lt
s
[
1
0
]
.
B
icep
s
cu
r
l
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
2
5
8
6
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
1
5
,
No
.
1
,
Ma
r
ch
20
2
6
:
247
-
256
248
ty
p
e
r
ec
o
g
n
itio
n
is
a
s
u
p
er
v
is
ed
lear
n
i
n
g
class
if
icatio
n
p
r
e
d
ictio
n
p
r
o
b
lem
.
I
n
o
r
d
er
to
id
en
tify
t
h
e
ty
p
e
o
f
b
icep
s
cu
r
l,
wea
r
ab
le
s
en
s
o
r
d
ev
ices
ar
e
o
f
ten
u
s
ed
to
c
o
llec
t
tr
ain
in
g
p
r
o
ce
s
s
d
ata
[
1
1
]
.
M
o
s
t
r
esear
ch
er
s
u
s
e
ad
v
an
ce
d
W
ir
eless
s
E
MG
Sen
s
o
r
B
I
OM
-
L
E
2
an
d
g
o
n
i
o
m
et
er
B
I
OM
-
W
S1
5
0
to
d
etec
t
th
e
elec
tr
o
m
y
o
g
r
ap
h
y
o
f
th
e
b
ice
p
s
an
d
r
ea
l
-
tim
e
d
at
a
o
f
elb
o
w
j
o
in
t m
o
v
em
en
t
[
1
2
]
.
T
h
er
e
ar
e
m
an
y
m
et
h
o
d
s
to
a
ch
iev
e
th
e
m
u
lti
-
ca
teg
o
r
y
class
if
icatio
n
p
r
o
b
lem
o
f
b
ice
p
s
cu
r
l
ac
tio
n
r
ec
o
g
n
itio
n
.
T
r
a
d
itio
n
al
ca
lc
u
latio
n
s
in
clu
d
e
l
o
g
is
tic
r
eg
r
e
s
s
io
n
,
B
ay
esian
m
eth
o
d
,
d
ec
i
s
io
n
tr
ee
,
r
an
d
o
m
f
o
r
est,
an
d
K
-
n
ea
r
est n
eig
h
b
o
r
m
ac
h
in
e
lear
n
i
n
g
m
eth
o
d
[
1
3
]
.
T
h
e
m
ath
e
m
atica
l m
o
d
el
is
s
im
p
le
an
d
f
ast,
b
u
t
th
e
ac
cu
r
ac
y
is
n
o
t
h
ig
h
f
o
r
p
r
o
ce
s
s
in
g
m
u
lti
-
d
im
e
n
s
io
n
a
l
d
ata
a
n
d
n
o
n
lin
ea
r
p
r
o
b
le
m
s
.
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e,
r
a
d
ial
b
asis
f
u
n
ctio
n
,
an
d
o
th
er
n
eu
r
al
n
etwo
r
k
m
o
d
els
ar
e
in
cr
ea
s
in
g
ly
u
s
ed
in
r
eg
r
ess
io
n
a
n
d
class
if
icatio
n
ap
p
licatio
n
s
[
1
4
]
.
Hy
p
er
p
a
r
am
eter
tu
n
i
n
g
o
f
d
if
f
er
en
t a
lg
o
r
ith
m
s
ca
n
o
f
te
n
s
ee
k
b
etter
ac
cu
r
ac
y
.
b
ac
k
-
p
r
o
p
a
g
atio
n
n
eu
r
al
n
etwo
r
k
(
B
PNN)
h
as
o
u
ts
tan
d
in
g
ad
v
an
tag
es
in
r
ea
lizin
g
r
eg
r
ess
io
n
p
r
ed
ictio
n
an
d
an
aly
tical
p
r
ed
ictio
n
in
lin
ea
r
an
d
n
o
n
lin
ea
r
p
r
o
b
lem
s
th
r
o
u
g
h
a
s
tack
ed
f
u
lly
co
n
n
e
cted
s
tr
u
ctu
r
e
an
d
g
r
ad
ien
t d
escen
t tr
ai
n
in
g
[
1
5
]
.
I
n
r
ec
en
t
y
ea
r
s
,
s
war
m
in
t
ellig
en
ce
alg
o
r
ith
m
s
h
av
e
b
ee
n
in
cr
ea
s
in
g
ly
ap
p
lied
to
p
r
ac
tical
en
g
in
ee
r
in
g
p
r
o
b
lem
s
an
d
al
g
o
r
ith
m
o
p
tim
izatio
n
.
T
h
ese
h
eu
r
is
tic
alg
o
r
ith
m
s
ar
e
o
f
t
en
in
s
p
ir
ed
b
y
th
e
b
eh
av
io
r
s
o
f
an
im
als
an
d
p
lan
ts
in
n
atu
r
e
,
s
u
ch
as
s
ea
r
ch
in
g
,
ex
p
lo
r
in
g
,
ca
p
tu
r
in
g
,
p
lu
n
d
e
r
in
g
,
a
n
d
ev
o
lv
i
n
g
.
T
h
e
B
lack
-
win
g
ed
k
ite
alg
o
r
ith
m
(
B
KA)
[
1
6
]
is
in
s
p
ir
ed
b
y
an
d
s
im
u
lates
th
e
m
ig
r
atio
n
an
d
h
u
n
tin
g
b
eh
av
io
r
o
f
b
lack
-
win
g
ed
k
ite
s
.
I
t
h
as
f
ast
g
lo
b
al
e
x
p
lo
r
atio
n
an
d
l
o
ca
l
ex
p
l
o
itatio
n
ca
p
ab
ilit
ies
an
d
is
in
th
e
ex
p
lo
r
ato
r
y
s
tag
e
in
h
u
m
an
m
o
tio
n
tr
ain
in
g
ap
p
licatio
n
s
.
R
esear
ch
er
s
h
av
e
u
s
ed
m
an
y
s
war
m
in
tellig
en
ce
alg
o
r
ith
m
s
to
o
p
tim
ize
n
eu
r
al
n
etwo
r
k
p
ar
am
eter
s
f
o
r
b
etter
ac
cu
r
ac
y
.
Par
ticle
s
war
m
o
p
tim
izatio
n
,
g
r
ay
wo
lf
alg
o
r
ith
m
,
an
d
d
u
n
g
b
ee
tle
alg
o
r
ith
m
h
a
v
e
b
ee
n
u
s
ed
to
a
d
ju
s
t
n
eu
r
al
n
etwo
r
k
weig
h
ts
,
ar
ch
itectu
r
es,
an
d
lear
n
in
g
h
y
p
er
p
ar
am
eter
s
.
T
h
ese
alg
o
r
ith
m
s
ca
n
u
s
u
ally
a
v
o
id
lo
ca
l
m
i
n
im
a
ca
u
s
ed
b
y
g
r
ad
ie
n
t
d
escen
t
m
eth
o
d
s
.
T
h
is
s
tu
d
y
attem
p
ts
to
im
p
r
o
v
e
th
e
B
KA
alg
o
r
ith
m
an
d
th
en
t
u
n
e
t
h
e
B
PNN
f
r
am
ewo
r
k
to
p
r
e
d
ict
f
iv
e
b
icep
s
cu
r
l
p
o
s
tu
r
es.
T
h
e
co
n
tr
ib
u
tio
n
s
o
f
th
is
s
tu
d
y
a
r
e
s
u
m
m
ar
ized
as f
o
llo
ws
.
−
T
h
e
B
KA
alg
o
r
ith
m
is
im
p
r
o
v
ed
b
y
u
s
in
g
m
u
ltip
le
s
tr
ateg
ies,
s
u
ch
as
th
e
o
p
tim
al
p
o
in
t
s
et
an
d
th
e
ad
ap
tiv
e
t
-
s
p
ir
al
s
tr
ateg
y
,
t
o
a
ch
iev
e
b
etter
o
p
tim
izatio
n
co
m
p
u
tin
g
p
er
f
o
r
m
an
ce
.
−
T
h
e
im
p
r
o
v
ed
B
KA
(
I
B
KA)
alg
o
r
ith
m
was
u
s
ed
to
o
p
tim
ize
B
PNN,
an
d
th
e
I
B
KA
-
B
PNN
p
r
ed
ictio
n
m
o
d
el
is
p
r
o
p
o
s
ed
to
ac
h
iev
e
class
if
icatio
n
p
r
ed
ictio
n
o
f
f
iv
e
ty
p
es o
f
b
ice
p
s
cu
r
ls
.
T
h
e
co
n
ten
t
f
r
am
ewo
r
k
o
f
th
e
s
u
b
s
eq
u
en
t
p
a
p
er
is
as f
o
llo
ws:
s
ec
tio
n
2
d
etails
th
e
p
r
o
p
o
s
ed
m
eth
o
d
,
in
clu
d
in
g
th
e
d
ataset
s
o
u
r
ce
,
p
r
ep
r
o
ce
s
s
in
g
,
im
p
r
o
v
e
d
B
KA,
an
d
B
PNN
ar
ch
itectu
r
e.
S
ec
tio
n
3
p
r
esen
ts
th
e
p
er
f
o
r
m
an
ce
test
r
esu
lts
o
f
t
h
e
im
p
r
o
v
ed
B
KA
an
d
th
e
p
r
ed
ictio
n
r
esu
lts
o
f
th
e
estab
lis
h
ed
I
B
KA
-
B
PNN
m
o
d
el.
Sectio
n
4
s
u
m
m
ar
ize
s
th
e
f
in
d
in
g
s
o
f
th
e
I
B
KA
-
B
PNN
m
o
d
el
an
d
d
is
cu
s
s
es
th
e
d
ir
ec
tio
n
o
f
ex
ten
d
in
g
th
is
tech
n
o
lo
g
y
to
o
th
er
s
p
o
r
ts
tr
ain
in
g
s
ce
n
ar
io
s
.
2.
M
E
T
H
O
D
T
h
is
s
ec
tio
n
o
u
tlin
es
th
e
o
v
er
all
p
r
o
ce
s
s
o
f
th
e
I
B
KA
-
B
P
NN
m
o
d
el
f
o
r
b
icep
s
cu
r
l
cl
ass
if
icatio
n
p
r
o
p
o
s
ed
in
th
is
s
tu
d
y
.
First,
d
ata
co
llectio
n
an
d
d
ata
s
et
s
o
u
r
ce
s
f
o
r
b
icep
s
cu
r
l tr
ain
i
n
g
ar
e
in
tr
o
d
u
ce
d
.
T
h
e
n
,
th
e
m
u
lti
-
s
tr
ateg
y
im
p
r
o
v
em
e
n
t
s
tr
ateg
y
o
f
th
e
im
p
r
o
v
ed
I
B
KA
is
in
tr
o
d
u
ce
d
,
f
o
c
u
s
in
g
o
n
th
e
g
o
o
d
p
o
in
t
s
et
co
n
s
tr
u
ctio
n
an
d
a
d
ap
tiv
e
s
p
ir
al
s
ea
r
ch
s
tr
ateg
y
.
Fin
ally
,
t
h
e
B
PNN
ar
ch
itectu
r
e,
p
ar
am
eter
s
elec
tio
n
,
an
d
m
o
d
el
e
v
alu
atio
n
cr
iter
ia
ar
e
i
n
tr
o
d
u
ce
d
.
T
h
e
o
v
e
r
all
wo
r
k
f
l
o
w
d
iag
r
am
o
f
th
e
I
B
KA
-
B
P
NN
m
o
d
el
is
s
h
o
wn
in
Fig
u
r
e
1
.
2
.
1
.
M
ea
s
urem
ent
s
a
nd
da
t
a
s
et
s
T
h
e
ex
p
er
im
en
tal
d
ata
o
f
th
e
b
icep
s
cu
r
l
is
m
ea
s
u
r
ed
b
y
r
ef
er
r
in
g
to
th
e
wea
r
a
b
le
m
e
asu
r
em
en
t
m
eth
o
d
u
s
ed
in
cu
r
r
en
t
m
ain
s
tr
ea
m
r
esear
ch
.
T
h
e
d
ata
co
ll
ec
tio
n
s
am
p
les
s
elec
ted
h
ea
lt
h
y
ad
u
lt
v
o
l
u
n
teer
s
an
d
ath
letes,
an
d
r
e
p
ea
ted
cu
r
l
m
ea
s
u
r
em
en
ts
wer
e
p
er
f
o
r
m
ed
.
C
o
m
m
o
n
d
u
m
b
b
ell
s
in
g
le
-
ar
m
b
icep
s
cu
r
ls
ca
n
b
e
p
e
r
f
o
r
m
ed
in
f
iv
e
p
o
s
tu
r
es:
s
tan
d
ar
d
tech
n
i
q
u
e,
elb
o
w
-
f
lin
g
,
p
a
r
tial
-
u
p
,
p
ar
tial
-
d
o
wn
,
an
d
h
ip
-
s
win
g
.
T
h
e
f
iv
e
ty
p
es c
o
r
r
esp
o
n
d
t
o
t
h
e
f
iv
e
lab
els 1
–
5
o
f
th
e
class
v
ar
iab
le.
T
h
e
d
a
t
a
a
c
q
u
i
s
i
t
i
o
n
s
c
h
e
m
e
is
s
h
o
w
n
i
n
F
i
g
u
r
e
2
.
I
t
i
n
c
l
u
d
e
s
a
s
i
x
-
a
x
i
s
i
n
e
r
t
i
al
m
e
a
s
u
r
e
m
e
n
t
u
n
i
t
(
I
M
U
)
,
a
s
u
r
f
a
c
e
e
le
c
t
r
o
m
y
o
g
r
a
p
h
y
(
E
M
G
)
s
e
n
s
o
r
,
a
f
le
x
i
b
l
e
f
a
b
r
i
c
s
t
r
a
i
n
s
e
n
s
o
r
c
u
f
f
,
a
n
d
a
t
w
o
-
a
x
i
s
e
l
e
ct
r
o
n
i
c
g
o
n
i
o
m
e
t
e
r
.
A
l
l
d
a
t
a
c
a
n
b
e
t
r
a
n
s
f
e
r
r
e
d
t
o
a
c
o
m
p
u
t
e
r
v
i
a
a
U
SB
d
a
t
a
a
c
q
u
is
i
ti
o
n
(
D
A
Q
)
ca
r
d
f
o
r
s
t
o
r
a
g
e
.
T
h
e
s
i
x
-
a
x
is
i
n
e
r
ti
a
l
m
ea
s
u
r
e
m
e
n
t
u
n
i
t
(
I
M
U
)
is
u
s
e
d
t
o
ca
p
t
u
r
e
t
h
e
l
i
n
ea
r
a
n
d
a
n
g
u
l
a
r
m
o
v
em
e
n
t
o
f
t
h
e
f
o
r
e
a
r
m
d
u
r
i
n
g
e
a
c
h
c
u
r
l
.
T
h
e
s
u
r
f
a
c
e
e
l
e
c
t
r
o
m
y
o
g
r
a
p
h
y
(
E
M
G
)
s
e
n
s
o
r
is
u
s
e
d
t
o
r
e
c
o
r
d
m
u
s
cl
e
ac
t
i
v
a
t
i
o
n
p
at
t
e
r
n
s
t
o
d
i
s
t
i
n
g
u
is
h
b
e
t
we
e
n
c
o
r
r
e
c
t
p
o
s
t
u
r
e
a
n
d
m
o
m
e
n
t
u
m
-
as
s
is
t
e
d
m
o
v
e
m
e
n
t
.
T
h
e
t
w
o
-
a
x
is
e
l
ec
t
r
o
n
i
c
g
o
n
i
o
m
e
t
e
r
c
a
n
m
e
a
s
u
r
e
t
h
e
f
le
x
i
o
n
a
n
g
l
e
i
n
r
ea
l
t
i
m
e
a
n
d
c
a
n
ac
c
u
r
a
t
e
l
y
d
is
tin
g
u
i
s
h
b
e
t
w
e
e
n
li
f
t
i
n
g
a
n
d
l
o
we
r
i
n
g
.
T
h
e
co
llected
d
ataset
in
clu
d
es
th
e
E
u
ler
an
g
le
p
o
s
tu
r
e
o
f
th
e
wr
is
t,
f
o
r
ea
r
m
,
a
n
d
u
p
p
er
ar
m
m
ea
s
u
r
ed
b
y
I
MU
,
an
d
3
5
-
d
i
m
en
s
io
n
al
d
ata
s
u
c
h
as
lim
b
s
eg
m
en
t
r
o
tatio
n
s
p
ee
d
,
a
x
is
an
g
u
lar
v
elo
city
,
ax
is
ac
ce
ler
atio
n
,
an
d
ax
is
m
ag
n
eti
c
f
ield
m
ea
s
u
r
ed
b
y
E
MG
[
1
7
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
I
SS
N:
2722
-
2
5
8
6
A
n
imp
r
o
ve
d
b
la
ck
-
w
in
g
e
d
ki
te
a
lg
o
r
ith
m
o
p
timiz
ed
b
a
ck
-
p
r
o
p
a
g
a
tio
n
…
(
C
h
u
n
q
in
g
Liu
)
249
Fig
u
r
e
1
.
W
o
r
k
f
lo
w
d
iag
r
am
o
f
th
e
I
B
KA
-
B
PNN
m
o
d
el
Fig
u
r
e
2
.
Sch
em
atic
d
iag
r
am
o
f
d
ata
ac
q
u
is
itio
n
s
ch
em
e
T
h
e
d
ataset
o
b
tain
ed
f
r
o
m
th
e
p
r
elim
in
ar
y
co
llectio
n
was
p
r
ep
r
o
ce
s
s
ed
to
f
ac
ilit
ate
th
e
s
u
b
s
eq
u
en
t
p
r
ed
ictio
n
m
o
d
el
ca
lcu
latio
n
.
On
ly
th
e
d
ata
co
llected
d
u
r
in
g
th
e
s
tab
le
cu
r
l
tr
ain
in
g
p
r
o
ce
s
s
wa
s
r
etain
ed
;
all
ch
an
n
els
o
f
d
if
f
er
en
t
s
en
s
o
r
s
wer
e
tim
e
-
alig
n
ed
,
an
d
th
e
ef
f
ec
tiv
e
m
ea
s
u
r
em
en
t
d
ata
o
f
t
h
e
s
am
e
b
icep
s
c
u
r
l
tr
ain
in
g
was
co
n
v
er
ted
in
to
a
3
5
-
d
im
e
n
s
io
n
al
f
ea
tu
r
e
v
ec
t
o
r
.
T
h
e
d
ataset
was
lab
elled
1
t
o
5
ac
co
r
d
in
g
to
th
e
f
iv
e
ty
p
es
o
f
b
icep
s
cu
r
ls
.
Hig
h
-
f
r
eq
u
en
cy
elec
tr
o
n
ic
n
o
is
e
an
d
lo
w
-
f
r
eq
u
e
n
cy
d
r
if
t
d
ata
w
er
e
elim
in
ated
,
th
e
d
is
to
r
ted
f
r
ag
m
en
ts
co
llected
i
n
th
e
d
ata
wer
e
d
elete
d
,
an
d
t
h
e
5
ty
p
es
o
f
s
am
p
les
wer
e
b
alan
ce
d
,
r
esu
ltin
g
in
a
to
tal
o
f
3
4
0
r
o
ws an
d
3
5
co
l
u
m
n
s
o
f
d
ata.
2
.
2
.
I
m
pro
v
em
ent
o
f
bla
c
k
-
w
ing
ed
k
it
e
a
lg
o
rit
h
m
T
h
e
o
r
i
g
i
n
a
l
B
K
A
a
l
g
o
r
i
t
h
m
is
i
n
s
p
i
r
e
d
b
y
t
h
e
at
t
a
c
k
a
n
d
m
i
g
r
a
t
i
o
n
b
e
h
a
v
i
o
r
s
o
f
b
la
c
k
-
w
in
g
e
d
k
i
t
e
s
.
T
h
e
p
r
e
y
i
s
e
q
u
i
v
a
l
e
n
t
t
o
t
h
e
g
l
o
b
a
l
o
p
t
i
m
a
l
s
o
l
u
ti
o
n
o
f
t
h
e
a
l
g
o
r
i
t
h
m
.
T
h
e
a
t
t
a
c
k
b
e
h
a
v
i
o
r
a
l
l
o
w
s
t
h
e
a
l
g
o
r
it
h
m
t
o
f
i
n
d
t
h
e
o
p
t
i
m
al
s
o
l
u
t
i
o
n
w
ith
i
n
a
s
p
e
c
i
f
ie
d
r
a
n
g
e
,
a
n
d
t
h
e
m
i
g
r
a
t
i
o
n
b
e
h
a
v
i
o
r
a
l
l
o
ws
t
h
e
a
l
g
o
r
i
t
h
m
t
o
e
x
p
l
o
r
e
n
e
w
p
o
t
e
n
t
i
a
l
s
o
l
u
ti
o
n
a
r
e
a
s
i
n
a
l
a
r
g
e
r
r
a
n
g
e
t
o
a
v
o
i
d
b
e
i
n
g
t
r
a
p
p
e
d
i
n
t
h
e
l
o
c
a
l
o
p
t
i
m
a
l
s
o
l
u
ti
o
n
.
T
h
e
o
r
ig
in
al
B
KA
alg
o
r
ith
m
u
s
es
r
an
d
o
m
p
o
p
u
latio
n
p
o
s
itio
n
s
f
o
r
p
o
p
u
latio
n
in
itializatio
n
.
T
o
ad
d
r
ess
th
is
in
s
tab
ilit
y
,
th
i
s
s
t
u
d
y
p
r
o
p
o
s
es
th
e
g
o
o
d
p
o
in
t
s
et
(
GPS)
m
eth
o
d
[
1
8
]
to
im
p
r
o
v
e
th
e
s
tab
ilit
y
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
2
5
8
6
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
1
5
,
No
.
1
,
Ma
r
ch
20
2
6
:
247
-
256
250
p
o
p
u
latio
n
in
itializatio
n
.
Fo
r
p
r
o
b
lem
s
with
i
p
o
p
u
latio
n
s
an
d
j
d
im
en
s
io
n
s
,
th
e
m
eth
o
d
o
f
f
in
d
in
g
th
e
o
p
tim
al
p
o
in
t set is sh
o
wn
in
(
1
)
.
{
=
(
2
c
os
(
2
)
,
1
)
=
2
+
3
=
+
(
−
)
(
1
)
T
h
e
r
esu
lts
o
f
u
s
in
g
GPS
p
o
p
u
latio
n
in
itializatio
n
an
d
r
an
d
o
m
p
o
p
u
latio
n
i
n
itializatio
n
u
s
ed
in
th
e
o
r
i
g
in
al
B
KA
alg
o
r
ith
m
ar
e
co
m
p
ar
e
d
,
as
s
h
o
wn
in
Fig
u
r
e
3
.
I
t
ca
n
b
e
in
tu
itiv
ely
s
ee
n
th
at
GPS
p
o
p
u
latio
n
in
itializatio
n
is
m
o
r
e
u
n
if
o
r
m
an
d
s
tab
le
th
an
r
an
d
o
m
p
o
p
u
la
tio
n
in
itializatio
n
.
Fig
u
r
e
3
.
C
o
m
p
a
r
is
o
n
o
f
p
o
p
u
latio
n
in
itializatio
n
I
n
th
e
attac
k
b
eh
a
v
io
r
s
tag
e,
th
is
s
tu
d
y
p
r
o
p
o
s
es
an
a
d
ap
tiv
e
T
-
s
p
ir
al
s
tr
ateg
y
,
as
s
h
o
w
n
in
f
o
r
m
u
la
(
2
)
,
wh
ic
h
ca
n
e
n
h
an
ce
th
e
al
g
o
r
ith
m
'
s
lo
ca
l
ex
p
lo
itatio
n
a
b
ilit
y
to
f
in
d
th
e
o
p
tim
al
s
o
lu
t
io
n
[
1
9
]
.
I
t
ca
n
also
ex
p
an
d
th
e
n
eig
h
b
o
r
h
o
o
d
r
a
n
g
e
to
av
o
id
f
allin
g
in
to
th
e
lo
ca
l
o
p
tim
al
s
o
lu
tio
n
.
{
+
1
,
=
,
+
(
1
+
s
in
(
)
)
×
,
×
,
<
+
1
,
=
,
+
×
(
2
−
1
)
×
,
×
,
ℎ
=
×
×
=
×
s
in
(
)
=
×
cos
(
)
=
×
=
×
(
)
(
2
)
H
er
e,
,
,
+
1
,
r
ep
r
esen
t
th
e
p
o
s
itio
n
o
f
th
e
i
-
th
b
lac
k
-
win
g
e
d
k
i
te
in
th
e
j
-
d
im
en
s
io
n
al
t
-
th
a
n
d
(
t+1
)
-
t
h
iter
atio
n
s
tep
s
,
r
esp
ec
tiv
ely
.
r
is
a
r
an
d
o
m
n
u
m
b
e
r
b
etwe
en
0
an
d
1
.
t
is
th
e
cu
r
r
en
t
iter
atio
n
n
u
m
b
er
,
an
d
T
is
th
e
to
tal
n
u
m
b
er
o
f
iter
atio
n
s
s
et.
n
is
th
e
n
o
n
lin
ea
r
f
ac
to
r
.
m
is
a
r
an
d
o
m
v
alu
e
b
etwe
en
(
0
,
2
π)
.
U
is
a
co
n
s
tan
t
o
f
2
.
v
is
a
co
n
s
tan
t
o
f
5
.
tr
n
d
is
a
v
ar
iab
le
s
tep
l
en
g
th
g
en
e
r
ated
u
s
in
g
th
e
ch
a
r
ac
ter
is
tics
o
f
th
e
t
d
is
tr
ib
u
tio
n
.
T
o
v
e
r
if
y
th
e
s
u
p
er
io
r
ity
o
f
t
h
e
p
r
o
p
o
s
ed
I
B
KA
alg
o
r
ith
m
,
in
a
d
d
itio
n
to
th
e
b
en
c
h
m
ar
k
f
u
n
ctio
n
s
test
,
a
s
ev
en
-
d
im
en
s
io
n
al
en
g
i
n
ee
r
in
g
d
esig
n
task
ca
lcu
latio
n
co
m
p
ar
is
o
n
was
s
elec
ted
.
T
h
e
I
B
KA
alg
o
r
ith
m
was
co
m
p
ar
ed
with
th
e
o
r
ig
in
al
d
u
n
g
b
ee
tle
o
p
tim
izer
(
DB
O
)
[
2
0
]
,
Har
r
is
Haw
k
s
o
p
tim
izer
(
HHO
)
[
2
1
]
,
an
d
g
r
ey
wo
lf
o
p
tim
izer
(
GW
O
)
[
2
2
]
alg
o
r
ith
m
s
.
T
h
e
co
m
p
a
r
is
o
n
r
esu
lts
ar
e
s
h
o
wn
i
n
Fig
u
r
e
4
.
T
h
e
alg
o
r
ith
m
s
wer
e
r
u
n
3
0
t
im
es
in
d
ep
en
d
e
n
tly
,
with
a
p
o
p
u
latio
n
s
ize
o
f
3
0
an
d
5
0
0
iter
atio
n
s
.
T
h
e
co
n
v
er
g
en
ce
cu
r
v
e
s
h
o
w
n
in
Fig
u
r
e
4
(
a
)
a
n
d
th
e
b
o
x
p
lo
t
s
h
o
wn
in
Fig
u
r
e
4
(
b
)
in
t
u
itiv
ely
ex
p
r
ess
th
e
r
o
b
u
s
tn
ess
an
d
s
u
p
er
io
r
ity
o
f
t
h
e
B
KA
alg
o
r
ith
m
im
p
r
o
v
ed
b
y
g
o
o
d
p
o
in
t set in
itializatio
n
an
d
ad
ap
tiv
e
s
p
ir
al
s
ea
r
ch
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
I
SS
N:
2722
-
2
5
8
6
A
n
imp
r
o
ve
d
b
la
ck
-
w
in
g
e
d
ki
te
a
lg
o
r
ith
m
o
p
timiz
ed
b
a
ck
-
p
r
o
p
a
g
a
tio
n
…
(
C
h
u
n
q
in
g
Liu
)
251
(
a)
(
b
)
Fig
u
r
e
4
.
Per
f
o
r
m
an
c
e
co
m
p
ar
is
o
n
o
f
im
p
r
o
v
e
d
B
KA
alg
o
r
ith
m
: (
a)
c
o
n
v
er
g
en
ce
c
u
r
v
es f
o
r
a
7
-
d
i
m
en
s
io
n
al
en
g
in
ee
r
in
g
p
r
o
b
lem
a
n
d
(
b
)
c
o
m
p
ar
is
o
n
o
f
b
o
x
p
lo
ts
f
o
r
o
p
t
im
ized
ca
lcu
latio
n
s
2
.
3
.
B
a
c
k
-
pro
pa
g
a
t
io
n neura
l net
wo
rk
B
PNN
is
a
f
ee
d
f
o
r
war
d
ar
tifi
cial
n
eu
r
al
n
etwo
r
k
,
as
s
h
o
wn
in
Fig
u
r
e
5
,
wh
ich
co
n
s
is
ts
o
f
an
in
p
u
t
lay
er
,
m
u
ltip
le
h
id
d
e
n
lay
er
s
,
an
d
an
o
u
tp
u
t
lay
er
.
T
h
e
o
r
i
g
in
al
B
PNN
n
etwo
r
k
u
s
es
th
e
s
ig
m
o
id
n
o
n
lin
ea
r
ac
tiv
atio
n
f
u
n
cti
o
n
.
I
ts
lear
n
i
n
g
p
r
o
ce
s
s
u
s
es th
e
er
r
o
r
b
ac
k
-
p
r
o
p
a
g
atio
n
alg
o
r
ith
m
[
2
3
]
–
[
2
5
]
.
Fig
u
r
e
5
.
Diag
r
a
m
o
f
B
PNN
n
etwo
r
k
s
tr
u
ctu
r
e
T
h
e
n
eu
r
o
n
’
s
p
r
e
d
icted
o
u
tp
u
t
̂
is
co
m
p
u
ted
b
y
(
3
)
,
wh
er
e
w
ij
an
d
b
ij
a
r
e
th
e
s
y
n
ap
tic
we
ig
h
t
an
d
b
ias,
r
esp
ec
tiv
ely
.
T
h
e
n
etwo
r
k
’
s
o
v
er
all
lo
s
s
is
q
u
an
tifie
d
b
y
th
e
s
u
m
-
of
-
s
q
u
ar
e
d
er
r
o
r
s
in
(
4
)
,
wh
ich
co
m
p
ar
es
ea
c
h
p
r
ed
ictio
n
̂
with
its
g
r
o
u
n
d
-
tr
u
t
h
tar
g
et
y
j
.
T
o
m
in
im
ize
t
h
is
lo
s
s
,
th
e
weig
h
ts
ar
e
iter
ativ
ely
r
ef
in
ed
with
g
r
a
d
ien
t
d
escen
t,
as
s
h
o
wn
in
(
5
)
,
w
h
er
e
η
d
en
o
tes
th
e
lear
n
in
g
-
r
ate
co
e
f
f
icien
t
th
at
co
n
tr
o
ls
th
e
s
tep
s
ize
o
f
ea
ch
u
p
d
ate.
̂
=
(
∑
−
=
1
)
(
3
)
=
∑
(
̂
−
)
2
=
1
(
4
)
=
−
(
)
(
5
)
T
h
e
id
ea
o
f
I
B
KA
to
o
p
tim
ize
B
PNN
is
to
u
s
e
th
e
g
lo
b
al
o
p
tim
al
s
o
lu
tio
n
f
o
u
n
d
b
y
I
B
KA
as
th
e
p
ar
am
eter
s
o
f
B
PNN.
I
B
KA
r
eg
ar
d
s
ea
ch
p
o
p
u
latio
n
as
a
ca
n
d
id
ate
s
et
o
f
weig
h
ts
,
b
iases
,
an
d
th
e
n
u
m
b
er
o
f
h
id
d
en
lay
er
s
o
f
B
PNN.
T
h
e
weig
h
ts
,
b
iases
,
a
n
d
n
u
m
b
er
o
f
h
i
d
d
en
lay
er
s
r
an
d
o
m
l
y
g
e
n
er
ated
b
y
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
2
5
8
6
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
1
5
,
No
.
1
,
Ma
r
ch
20
2
6
:
247
-
256
252
o
r
ig
in
al
B
PNN
ar
e
u
s
ed
a
s
t
h
e
in
itial
s
ea
r
ch
s
tar
tin
g
p
o
i
n
t
o
f
th
e
p
o
p
u
latio
n
o
f
I
B
KA,
ev
alu
ated
o
n
th
e
tr
ain
in
g
s
et,
an
d
iter
ativ
el
y
u
p
d
ated
.
T
h
e
iter
ativ
e
ca
lcu
lat
io
n
is
s
to
p
p
ed
u
n
til
th
e
p
r
e
d
ictio
n
er
r
o
r
o
f
th
e
B
PNN
n
etwo
r
k
co
n
v
er
g
es
b
el
o
w
th
e
tar
g
et
th
r
esh
o
ld
.
T
h
e
f
i
n
al
B
PNN
m
o
d
el
will
b
e
u
s
ed
f
o
r
th
e
r
ec
o
g
n
itio
n
o
f
f
iv
e
t
y
p
es o
f
b
icep
s
cu
r
ls
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
s
ec
tio
n
o
u
tlin
es
th
e
ex
p
er
im
en
tal
s
ch
em
e,
in
clu
d
in
g
d
ata
p
ar
titi
o
n
in
g
,
ev
alu
atio
n
m
etr
ics,
an
d
co
m
p
u
tin
g
en
v
ir
o
n
m
en
t.
T
h
e
class
if
icat
io
n
p
r
ed
ictio
n
r
esu
lts
o
b
tain
ed
u
s
in
g
th
e
o
r
ig
in
al
B
PNN
ar
e
p
r
esen
ted
.
Su
b
s
eq
u
en
tly
,
th
e
p
r
o
p
o
s
ed
I
B
KA
-
B
PNN
m
o
d
el
is
u
s
ed
f
o
r
class
if
icatio
n
p
r
e
d
ictio
n
.
Fin
ally
,
t
h
e
p
r
ac
tical
s
ig
n
if
ican
ce
o
f
th
is
s
tu
d
y
f
o
r
b
ice
p
s
cu
r
l ty
p
e
r
ec
o
g
n
itio
n
is
d
is
cu
s
s
ed
.
3
.
1
.
O
ri
g
ina
l BPNN
p
re
dict
i
o
n
T
h
e
p
r
e
p
r
o
ce
s
s
ed
d
ata
s
et
co
n
tain
s
3
4
0
s
am
p
les,
ea
ch
with
3
5
in
p
u
t
f
ea
tu
r
es.
T
h
e
d
ataset
o
b
tain
e
d
af
ter
p
r
ep
r
o
ce
s
s
in
g
th
e
d
ata
m
ea
s
u
r
ed
in
th
e
b
icep
s
cu
r
l
ex
p
er
im
en
t
was
d
iv
id
ed
in
to
a
tr
ai
n
in
g
s
et
(
7
0
%)
an
d
a
test
s
et
(
3
0
%).
T
h
e
r
o
b
u
s
tn
ess
was
m
ea
s
u
r
ed
b
y
th
e
s
tan
d
ar
d
d
ev
iatio
n
o
f
t
h
e
av
er
a
g
e
a
cc
u
r
ac
y
o
f
th
e
test
s
et
o
v
er
te
n
r
u
n
s
.
T
h
e
lear
n
in
g
r
ate
was
s
et
to
0
.
0
1
,
an
d
th
e
n
u
m
b
er
o
f
h
id
d
e
n
lay
e
r
s
was
6
ac
c
o
r
d
in
g
to
th
e
em
p
ir
ical
f
o
r
m
u
la.
T
o
elim
in
ate
th
e
co
n
tin
g
en
c
y
ca
u
s
ed
b
y
r
a
n
d
o
m
in
itiali
za
tio
n
,
th
e
co
m
p
lete
e
x
p
er
i
m
en
t
was
r
ep
ea
ted
1
0
tim
es
u
n
d
e
r
d
if
f
e
r
en
t
r
an
d
o
m
in
itializatio
n
s
,
a
n
d
th
e
m
o
d
el'
s
r
o
b
u
s
tn
ess
was
m
ea
s
u
r
ed
b
y
th
e
s
tan
d
ar
d
d
e
v
iatio
n
o
f
t
h
e
av
e
r
ag
e
ac
cu
r
ac
y
o
f
th
e
test
s
et.
T
h
e
r
esu
lts
o
f
th
e
o
r
ig
in
al
B
PNN
m
o
d
el
f
o
r
b
icep
s
cu
r
l ty
p
e
class
if
icatio
n
p
r
e
d
ictio
n
ar
e
s
h
o
wn
in
Fig
u
r
e
6
.
Fig
u
r
e
6
(
a)
p
lo
ts
th
e
co
m
p
ar
is
o
n
cu
r
v
e
b
etwe
en
th
e
ac
tu
al
lab
el
an
d
th
e
p
r
ed
icted
la
b
el
o
n
th
e
tr
ain
in
g
s
et.
Af
ter
m
u
ltip
le
te
s
ts
,
th
e
av
er
a
g
e
ac
c
u
r
ac
y
o
f
t
h
e
tr
ain
in
g
s
et
is
7
9
.
8
3
%.
Fi
g
u
r
e
6
(
b
)
p
lo
ts
th
e
co
m
p
ar
is
o
n
cu
r
v
e
b
etwe
en
th
e
ac
tu
al
lab
el
an
d
th
e
p
r
ed
icted
lab
el
o
n
th
e
test
s
e
t.
T
h
e
av
er
ag
e
ac
cu
r
ac
y
o
f
th
e
test
s
et
is
6
9
.
6
1
%,
s
h
o
win
g
a
ce
r
tain
p
er
f
o
r
m
an
ce
f
l
u
ctu
atio
n
.
T
h
e
o
r
i
g
in
al
B
PNN
m
o
d
el
h
as
a
s
m
all
n
u
m
b
er
o
f
h
ig
h
-
o
r
d
e
r
ca
teg
o
r
y
m
is
ju
d
g
m
en
ts
,
wh
ich
is
r
elate
d
to
th
e
o
v
er
f
itti
n
g
o
f
th
e
m
o
d
el
an
d
th
e
in
itializatio
n
s
ettin
g
o
f
th
e
m
o
d
el
p
ar
a
m
eter
s
.
(
a)
(
b
)
Fig
u
r
e
6
.
T
h
e
o
r
i
g
in
al
B
PNN
class
if
icatio
n
r
esu
lts
: (
a)
r
esu
lt
s
o
f
tr
ain
in
g
s
et
class
if
icatio
n
an
d
(
b
)
r
esu
lts
o
f
test
s
et
cla
s
s
if
icatio
n
3
.
2
.
I
B
P
A
-
B
P
NN
p
re
dict
io
n
T
o
s
o
lv
e
t
h
e
p
r
o
b
lem
o
f
in
s
u
f
f
icien
t
g
en
er
aliza
tio
n
ab
ilit
y
an
d
lo
w
ac
c
u
r
ac
y
r
ate
o
f
th
e
o
r
i
g
in
al
B
PNN
o
n
th
e
b
icep
s
cu
r
l
d
ataset,
th
is
s
tu
d
y
attem
p
ts
to
u
s
e
th
e
im
p
r
o
v
ed
B
KA
alg
o
r
ith
m
to
g
lo
b
ally
o
p
tim
ize
th
e
weig
h
ts
,
b
iases
,
an
d
n
u
m
b
er
o
f
h
id
d
e
n
lay
e
r
s
o
f
B
PNN.
T
h
e
I
B
KA
alg
o
r
ith
m
co
m
b
in
es
th
e
im
p
r
o
v
e
d
s
tr
ateg
y
o
f
GPS p
o
p
u
latio
n
in
itializatio
n
an
d
ad
ap
t
iv
e
s
p
ir
al
s
ea
r
ch
to
ac
ce
ler
ate
co
n
v
er
g
en
ce
wh
ile
m
ain
tain
in
g
p
o
p
u
latio
n
d
iv
er
s
ity
.
T
h
e
p
o
p
u
latio
n
s
ize
o
f
I
B
KA
-
B
P
NN
is
3
0
,
th
e
m
ax
im
u
m
n
u
m
b
er
o
f
iter
atio
n
s
is
3
0
,
an
d
th
e
o
th
er
s
ettin
g
s
o
f
B
PNN
ar
e
co
n
s
i
s
ten
t w
ith
th
e
o
r
ig
in
al.
T
h
e
co
n
v
er
g
en
ce
cu
r
v
e
o
f
th
e
I
B
KA
-
B
P
NN
m
o
d
el
is
s
h
o
wn
in
Fig
u
r
e
7
.
I
B
KA
o
b
tain
ed
o
p
tim
ized
in
i
tial
weig
h
ts
an
d
b
ias
v
alu
es
o
f
B
PNN,
an
d
th
e
o
p
tim
al
n
u
m
b
er
o
f
h
id
d
en
la
y
er
s
is
1
0
.
I
B
KA
o
p
tim
izes
th
e
in
itial
weig
h
t,
th
r
esh
o
ld
,
an
d
h
id
d
en
lay
er
s
ize
o
f
B
PNN
g
lo
b
ally
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
I
SS
N:
2722
-
2
5
8
6
A
n
imp
r
o
ve
d
b
la
ck
-
w
in
g
e
d
ki
te
a
lg
o
r
ith
m
o
p
timiz
ed
b
a
ck
-
p
r
o
p
a
g
a
tio
n
…
(
C
h
u
n
q
in
g
Liu
)
253
s
ig
n
if
ican
tly
im
p
r
o
v
in
g
th
e
m
o
d
el'
s
ab
ilit
y
to
d
is
tin
g
u
is
h
f
iv
e
b
icep
s
cu
r
ls
.
Fig
u
r
e
8
s
h
o
ws
th
e
co
n
f
u
s
io
n
m
atr
ix
o
f
I
B
KA
-
B
PNN
o
n
th
e
tr
ain
in
g
s
et
an
d
test
s
e
t
to
v
er
if
y
th
e
class
if
icatio
n
p
er
f
o
r
m
an
ce
o
f
th
e
m
o
d
el.
Fig
u
r
es
8
(
a)
a
n
d
8
(
c)
s
h
o
w
t
h
e
class
if
icatio
n
r
esu
lts
in
th
e
tr
ain
in
g
p
h
ase.
T
h
e
r
ec
o
g
n
itio
n
r
ates
o
f
ca
teg
o
r
y
4
an
d
ca
teg
o
r
y
5
r
ea
ch
1
0
0
% a
n
d
9
7
.
9
%,
r
esp
ec
tiv
ely
,
an
d
th
e
o
v
er
all
tr
ain
in
g
ac
cu
r
ac
y
r
ea
c
h
es 9
4
.
5
4
%,
wh
ich
is
1
4
.
7
1
%
h
i
g
h
er
t
h
an
th
at
o
f
th
e
o
r
i
g
in
al
B
PNN.
Fig
u
r
es
8
(
b
)
a
n
d
8
(
d
)
s
h
o
w
th
e
class
if
icatio
n
p
r
e
d
ictio
n
r
esu
lts
o
f
th
e
test
s
et,
an
d
its
o
v
er
all
ac
cu
r
ac
y
is
im
p
r
o
v
e
d
to
8
8
.
3
3
% (
th
e
o
r
ig
in
al
B
PNN
is
6
9
.
6
1
%).
Fig
u
r
e
7
.
C
o
n
v
er
g
e
n
ce
cu
r
v
e
o
f
th
e
I
B
KA
-
B
PNN
m
o
d
el
(
a)
(
b
)
(
c)
(
d
)
Fig
u
r
e
8
.
T
h
e
I
B
KA
-
B
PNN
cl
ass
if
icatio
n
r
esu
lts
: (
a)
r
esu
lts
o
f
tr
ain
in
g
s
et
class
if
icatio
n
,
(
b
)
r
esu
lts
o
f
test
s
et
class
if
icatio
n
,
(
c)
co
n
f
u
s
io
n
m
atr
ix
f
o
r
t
r
ain
in
g
d
ata,
an
d
(
d
)
co
n
f
u
s
io
n
m
atr
ix
f
o
r
test
d
ata
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
2
5
8
6
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
1
5
,
No
.
1
,
Ma
r
ch
20
2
6
:
247
-
256
254
I
B
KA
-
B
P
NN
s
h
o
ws
a
co
m
p
r
eh
en
s
iv
e
an
d
s
ig
n
if
ican
t
p
er
f
o
r
m
an
ce
leap
co
m
p
ar
ed
to
th
e
o
r
ig
in
al
B
PNN
in
th
e
r
ec
o
g
n
itio
n
o
f
f
iv
e
ty
p
es
o
f
b
icep
s
cu
r
l
m
o
v
e
m
en
ts
.
B
ased
o
n
th
e
s
am
e
d
ata
p
ar
titi
o
n
in
g
an
d
ten
in
d
ep
en
d
en
t
ex
p
er
im
en
ts
,
th
e
av
er
ag
e
ac
c
u
r
ac
y
o
f
t
h
e
tr
ain
i
n
g
s
et
an
d
test
s
et
o
f
I
B
KA
-
B
PNN
in
cr
ea
s
ed
to
9
4
.
5
4
%
a
n
d
8
3
.
3
3
%,
r
esp
ec
ti
v
ely
,
wh
ich
is
1
4
.
7
1
an
d
1
3
.
7
2
p
er
ce
n
tag
e
p
o
in
ts
h
ig
h
er
t
h
an
th
e
7
9
.
8
3
%
an
d
6
9
.
6
1
%
o
f
th
e
o
r
ig
i
n
al
B
PNN
m
o
d
el.
I
n
ter
m
s
o
f
co
m
p
r
eh
en
s
iv
e
ac
cu
r
ac
y
,
r
o
b
u
s
tn
ess
,
an
d
o
th
er
m
u
lti
-
d
im
en
s
io
n
al
in
d
icato
r
s
,
I
B
KA
-
B
PNN
is
s
ig
n
if
ican
tly
b
etter
th
an
th
e
u
n
o
p
tim
ized
B
PNN,
wh
ich
p
r
o
v
es
th
e
ef
f
ec
tiv
en
ess
o
f
th
e
im
p
r
o
v
ed
B
KA
alg
o
r
ith
m
in
weig
h
t
an
d
n
etwo
r
k
s
tr
u
ctu
r
e
o
p
tim
izat
io
n
,
an
d
p
r
o
v
id
es
a
d
ata
an
aly
s
is
b
asis
f
o
r
s
u
b
s
eq
u
en
t c
lass
if
icatio
n
an
d
tr
ain
in
g
o
f
m
o
r
e
co
m
p
lex
m
o
tio
n
p
o
s
tu
r
es.
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
in
v
esti
g
ates
f
iv
e
co
m
m
o
n
b
ice
p
s
cu
r
l
class
if
ic
atio
n
m
eth
o
d
s
,
aim
in
g
to
m
a
x
im
ize
th
e
tr
ain
in
g
ef
f
ec
t
f
o
r
p
r
o
f
ess
io
n
al
s
p
o
r
ts
tr
ain
in
g
an
d
u
p
p
er
lim
b
r
eh
ab
ilit
atio
n
tr
ain
in
g
.
A
wea
r
ab
le
s
en
s
o
r
d
ataset
was
s
elec
ted
in
th
e
s
tu
d
y
,
wh
ich
co
n
tain
s
m
u
ltip
le
r
ep
etitio
n
s
o
f
th
e
s
tan
d
ar
d
tech
n
iq
u
e,
el
b
o
w
-
f
lin
g
,
p
ar
tial
-
u
p
,
p
ar
tial
-
d
o
w
n
,
an
d
h
ip
-
s
win
g
.
A
m
u
lti
-
s
tr
ateg
y
im
p
r
o
v
ed
I
B
KA
wa
s
p
r
o
p
o
s
ed
.
I
B
KA
also
s
u
r
p
ass
ed
th
e
m
o
s
t
ad
v
an
ce
d
o
p
tim
izer
s
,
s
u
ch
as
DB
O,
HHO,
an
d
GW
O,
in
an
in
d
e
p
e
n
d
en
t
s
ev
e
n
-
d
im
e
n
s
io
n
al
en
g
i
n
ee
r
in
g
b
en
c
h
m
ar
k
test
,
p
r
o
v
in
g
th
e
ef
f
ec
tiv
e
n
ess
o
f
its
im
p
r
o
v
ed
s
tr
ateg
y
.
I
B
KA
was
u
s
ed
to
o
p
tim
ize
th
e
w
eig
h
ts
,
b
iases
,
an
d
n
u
m
b
er
o
f
h
id
d
en
lay
er
s
o
f
th
e
B
PNN,
th
er
eb
y
estab
lis
h
i
n
g
th
e
I
B
KA
-
B
PNN
m
o
d
el.
T
h
e
I
B
KA
-
B
PN
N
m
o
d
el
im
p
r
o
v
e
d
th
e
ac
cu
r
ac
y
o
f
th
e
t
r
ain
in
g
s
et
f
r
o
m
7
9
.
8
3
%
to
9
4
.
5
4
%,
an
d
th
e
ac
c
u
r
ac
y
o
f
t
h
e
test
s
et
f
r
o
m
6
9
.
6
1
% to
8
8
.
3
3
%.
T
h
ese
f
in
d
in
g
s
in
d
icate
t
h
at
t
h
e
I
B
KA
-
B
PNN
m
o
d
el
p
r
o
v
i
d
es
d
ata
s
u
p
p
o
r
t
f
o
r
th
e
class
if
icatio
n
o
f
b
icep
s
cu
r
l
tr
ain
in
g
an
d
u
p
p
er
lim
b
r
eh
a
b
ilit
atio
n
tr
ain
in
g
p
atter
n
s
,
wh
ich
h
elp
s
im
p
r
o
v
e
th
e
s
af
ety
an
d
ef
f
ec
tiv
en
ess
o
f
s
p
o
r
ts
tr
ain
in
g
.
I
n
th
e
f
u
tu
r
e,
th
e
r
esear
ch
team
will
ex
p
an
d
th
e
d
ata
s
et
to
tar
g
et
a
wid
er
r
an
g
e
o
f
s
p
o
r
ts
tr
ain
in
g
d
i
g
itizatio
n
an
d
in
teg
r
ate
m
o
r
e
b
io
lo
g
ical
s
ig
n
als.
T
h
is
r
ese
ar
ch
team
ac
tiv
ely
ex
p
lo
r
es
th
e
d
e
p
lo
y
m
e
n
t
o
f
ar
tific
ial
in
tellig
en
ce
tech
n
o
l
o
g
y
an
d
d
ev
el
o
p
s
wea
r
ab
le
h
ar
d
war
e
d
e
v
ices
to
ass
is
t
in
th
e
s
p
o
r
ts
tr
ain
in
g
p
r
o
ce
s
s
,
p
r
o
v
i
d
e
ath
letes
with
i
n
tu
itiv
e
f
ee
d
b
ac
k
o
n
tr
ain
in
g
p
o
s
tu
r
e
d
ev
iatio
n
s
,
an
d
ac
ce
ler
ate
th
e
a
p
p
licatio
n
o
f
s
m
ar
t sen
s
o
r
-
b
ased
t
r
ain
in
g
s
y
s
tem
s
in
s
p
o
r
ts
s
cien
ce
an
d
r
eh
ab
ilit
atio
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
C
h
u
n
q
in
g
L
i
u
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Kim
Geo
k
So
h
✓
✓
✓
✓
✓
✓
✓
✓
✓
Haz
izi
Ab
u
Saad
✓
✓
✓
✓
✓
Hao
h
ao
Ma
✓
✓
✓
✓
✓
✓
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
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
i
n
g
s
o
f
th
is
s
tu
d
y
ar
e
a
v
ailab
le
f
r
o
m
th
e
c
o
r
r
esp
o
n
d
in
g
au
th
o
r
KG
upon
r
ea
s
o
n
ab
le
r
eq
u
est.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
I
SS
N:
2722
-
2
5
8
6
A
n
imp
r
o
ve
d
b
la
ck
-
w
in
g
e
d
ki
te
a
lg
o
r
ith
m
o
p
timiz
ed
b
a
ck
-
p
r
o
p
a
g
a
tio
n
…
(
C
h
u
n
q
in
g
Liu
)
255
RE
F
E
R
E
NC
E
S
[
1
]
X
.
Zh
e
n
g
,
S
.
A
.
E.
H
e
a
d
l
e
y
,
S
.
A
.
M
a
r
i
s,
a
n
d
D
.
M
.
S
m
i
t
h
,
“
A
c
u
t
e
c
a
r
d
i
o
v
a
s
c
u
l
a
r
r
e
sp
o
n
se
s
t
o
u
n
i
l
a
t
e
r
a
l
b
i
c
e
p
c
u
r
l
s
w
i
t
h
b
l
o
o
d
f
l
o
w
r
e
st
r
i
c
t
i
o
n
,
”
J
o
u
rn
a
l
o
f
E
x
e
rc
i
s
e
S
c
i
e
n
c
e
a
n
d
F
i
t
n
e
s
s
,
v
o
l
.
2
1
,
n
o
.
2
,
p
p
.
1
7
9
–
1
8
5
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
e
s
f
.
2
0
2
3
.
0
1
.
0
0
1
.
[
2
]
Z.
G
.
X
i
a
o
a
n
d
C
.
M
e
n
o
n
,
“
D
o
e
s
f
o
r
c
e
my
o
g
r
a
p
h
y
r
e
c
o
r
d
e
d
a
t
t
h
e
w
r
i
s
t
c
o
r
r
e
l
a
t
e
t
o
r
e
s
i
st
a
n
c
e
l
o
a
d
l
e
v
e
l
s
d
u
r
i
n
g
b
i
c
e
p
c
u
r
l
s?
,
”
J
o
u
rn
a
l
o
f
Bi
o
m
e
c
h
a
n
i
c
s
,
v
o
l
.
8
3
,
p
p
.
3
1
0
–
3
1
4
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
b
i
o
m
e
c
h
.
2
0
1
8
.
1
1
.
0
3
5
.
[
3
]
C
.
Y
.
C
h
o
u
e
t
a
l
.
,
“
V
a
l
i
d
a
t
i
o
n
o
f
mu
sc
l
e
u
l
t
r
a
so
u
n
d
s
p
e
c
k
l
e
t
r
a
c
k
i
n
g
a
n
d
t
h
e
e
f
f
e
c
t
o
f
n
o
r
d
i
c
h
a
m
s
t
r
i
n
g
e
x
e
r
c
i
s
e
o
n
b
i
c
e
p
s
f
e
mo
r
i
s
d
i
sp
l
a
c
e
m
e
n
t
,
”
U
l
t
ra
so
u
n
d
i
n
M
e
d
i
c
i
n
e
a
n
d
B
i
o
l
o
g
y
,
v
o
l
.
5
1
,
n
o
.
4
,
p
p
.
7
1
5
–
7
2
1
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
u
l
t
r
a
s
med
b
i
o
.
2
0
2
5
.
0
1
.
0
0
5
.
[
4
]
S
.
S
.
G
a
r
i
k
a
,
A
.
M
a
h
mo
o
d
,
R
.
M
i
t
t
a
l
,
a
n
d
V
.
K
.
D
i
g
g
e
,
“
A
n
a
t
o
m
i
c
a
l
d
i
s
t
a
l
b
i
c
e
p
s
t
e
n
d
o
n
r
e
c
o
n
s
t
r
u
c
t
i
o
n
w
i
t
h
a
sem
i
t
e
n
d
i
n
o
s
u
s
a
u
t
o
g
r
a
f
t
,
”
J
o
u
r
n
a
l
o
f
O
rt
h
o
p
a
e
d
i
c
R
e
p
o
r
t
s
,
v
o
l
.
3
,
n
o
.
4
,
p
.
1
0
0
3
4
5
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
o
r
e
p
.
2
0
2
4
.
1
0
0
3
4
5
.
[
5
]
B
.
H
o
c
h
r
e
i
t
e
r
e
t
a
l
.
,
“
D
i
s
t
a
l
b
i
c
e
p
s
t
e
n
d
o
n
r
e
p
a
i
r
u
si
n
g
a
d
o
u
b
l
e
i
n
t
r
a
c
o
r
t
i
c
a
l
b
u
t
t
o
n
a
n
a
t
o
m
i
c
f
o
o
t
p
r
i
n
t
r
e
p
a
i
r
t
e
c
h
n
i
q
u
e
,
”
J
o
u
rn
a
l
o
f
S
h
o
u
l
d
e
r
a
n
d
El
b
o
w
S
u
rg
e
ry
,
v
o
l
.
3
3
,
n
o
.
1
0
,
p
p
.
2
2
4
3
–
2
2
5
1
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
s
e
.
2
0
2
4
.
0
3
.
0
2
8
.
[
6
]
C
.
B
.
Tse
a
n
d
R
.
S
.
J.
E
l
l
i
o
t
t
,
“
A
c
u
t
e
c
o
m
p
a
r
t
me
n
t
s
y
n
d
r
o
me
o
f
t
h
e
a
n
t
e
r
i
o
r
c
o
mp
a
r
t
m
e
n
t
o
f
t
h
e
a
r
m
f
o
l
l
o
w
i
n
g
a
t
r
a
u
m
a
t
i
c
d
i
st
a
l
b
i
c
e
p
s
r
u
p
t
u
r
e
w
i
t
h
r
u
p
t
u
r
e
o
f
a
h
i
g
h
-
t
a
k
e
o
f
f
r
a
d
i
a
l
a
r
t
e
r
y
:
A
c
a
se
r
e
p
o
r
t
,
”
J
o
u
rn
a
l
o
f
O
rt
h
o
p
a
e
d
i
c
Re
p
o
rt
s
,
v
o
l
.
3
,
n
o
.
3
,
p
.
1
0
0
2
9
9
,
S
e
p
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
o
r
e
p
.
2
0
2
3
.
1
0
0
2
9
9
.
[
7
]
D
.
S
.
C
l
a
r
k
,
B
.
P
.
M
o
o
r
e
,
a
n
d
J.
S
.
S
o
mers
o
n
,
“
S
e
n
s
o
r
y
n
e
u
r
a
p
r
a
x
i
a
a
f
t
e
r
d
i
s
t
a
l
b
i
c
e
p
s
r
e
p
a
i
r
i
s
n
o
t
a
ss
o
c
i
a
t
e
d
w
i
t
h
p
a
t
i
e
n
t
-
r
e
p
o
r
t
e
d
o
u
t
c
o
m
e
s
o
r
sa
t
i
sf
a
c
t
i
o
n
:
a
r
e
t
r
o
s
p
e
c
t
i
v
e
c
o
h
o
r
t
s
t
u
d
y
,
”
J
o
u
rn
a
l
o
f
S
h
o
u
l
d
e
r
a
n
d
El
b
o
w
S
u
r
g
e
r
y
,
v
o
l
.
3
3
,
n
o
.
1
2
,
p
p
.
2
6
9
5
–
2
7
0
1
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
se.
2
0
2
4
.
0
5
.
0
5
9
.
[
8
]
A
.
W
.
M
c
D
e
v
i
t
t
,
J.
L.
Y
o
u
n
g
,
J
.
A
.
C
l
e
l
a
n
d
,
P
.
H
i
e
f
i
e
l
d
,
a
n
d
S
.
J
.
S
n
o
d
g
r
a
ss,
“
P
h
y
s
i
c
a
l
t
h
e
r
a
p
y
i
n
t
e
r
v
e
n
t
i
o
n
s
u
se
d
t
o
t
r
e
a
t
i
n
d
i
v
i
d
u
a
l
s
w
i
t
h
b
i
c
e
p
s
t
e
n
d
i
n
o
p
a
t
h
y
:
a
sc
o
p
i
n
g
r
e
v
i
e
w
,
”
Br
a
z
i
l
i
a
n
J
o
u
rn
a
l
o
f
Ph
y
si
c
a
l
T
h
e
r
a
p
y
,
v
o
l
.
2
8
,
n
o
.
1
,
p
.
1
0
0
5
8
6
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
j
p
t
.
2
0
2
3
.
1
0
0
5
8
6
.
[
9
]
C
.
P
i
t
s
i
l
o
s,
I
.
G
i
g
i
s
,
K
.
C
h
i
t
a
s,
P
.
P
a
p
a
d
o
p
o
u
l
o
s,
a
n
d
K
.
D
i
t
si
o
s,
“
S
y
st
e
m
a
t
i
c
r
e
v
i
e
w
o
f
d
i
st
a
l
b
i
c
e
p
s
t
e
n
d
o
n
r
u
p
t
u
r
e
i
n
a
t
h
l
e
t
e
s:
t
r
e
a
t
me
n
t
a
n
d
r
e
h
a
b
i
l
i
t
a
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
S
h
o
u
l
d
e
r
a
n
d
E
l
b
o
w
S
u
r
g
e
ry
,
v
o
l
.
3
1
,
n
o
.
8
,
p
p
.
1
7
6
3
–
1
7
7
2
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
s
e
.
2
0
2
2
.
0
2
.
0
2
7
.
[
1
0
]
T.
J
.
F
r
e
e
b
o
r
n
a
n
d
B
.
F
u
,
“
T
i
me
-
c
o
u
r
se
b
i
c
e
p
t
i
ss
u
e
b
i
o
-
i
m
p
e
d
a
n
c
e
c
h
a
n
g
e
s
t
h
r
o
u
g
h
o
u
t
a
f
a
t
i
g
u
i
n
g
e
x
e
r
c
i
s
e
p
r
o
t
o
c
o
l
,
”
M
e
d
i
c
a
l
En
g
i
n
e
e
ri
n
g
a
n
d
P
h
y
s
i
c
s
,
v
o
l
.
6
9
,
p
p
.
1
0
9
–
1
1
5
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
me
d
e
n
g
p
h
y
.
2
0
1
9
.
0
4
.
0
0
6
.
[
1
1
]
A
.
K
.
G
o
w
d
e
t
a
l
.
,
“
R
e
t
u
r
n
t
o
sp
o
r
t
a
n
d
w
e
i
g
h
t
l
i
f
t
i
n
g
a
n
a
l
y
si
s
f
o
l
l
o
w
i
n
g
d
i
s
t
a
l
b
i
c
e
p
s
t
e
n
d
o
n
r
e
p
a
i
r
,
”
J
o
u
r
n
a
l
o
f
S
h
o
u
l
d
e
r
a
n
d
El
b
o
w
S
u
r
g
e
r
y
,
v
o
l
.
3
0
,
n
o
.
9
,
p
p
.
2
0
9
7
–
2
1
0
4
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
se.
2
0
2
1
.
0
1
.
0
3
4
.
[
1
2
]
B
.
F
u
a
n
d
T.
J.
F
r
e
e
b
o
r
n
,
“
C
o
l
e
-
i
m
p
e
d
a
n
c
e
p
a
r
a
m
e
t
e
r
s
r
e
p
r
e
s
e
n
t
i
n
g
b
i
c
e
p
s
t
i
ssu
e
b
i
o
i
mp
e
d
a
n
c
e
i
n
h
e
a
l
t
h
y
a
d
u
l
t
s
a
n
d
t
h
e
i
r
a
l
t
e
r
a
t
i
o
n
s
f
o
l
l
o
w
i
n
g
e
c
c
e
n
t
r
i
c
e
x
e
r
c
i
se
,
”
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
Re
se
a
rc
h
,
v
o
l
.
2
5
,
p
p
.
2
8
5
–
2
9
3
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
a
r
e
.
2
0
2
0
.
0
5
.
0
1
6
.
[
1
3
]
P
.
B
.
Y
a
n
g
,
Y
.
J.
C
h
a
n
,
S
.
K
.
Y
a
z
d
i
,
a
n
d
J.
W
.
L
i
m,
“
O
p
t
i
mi
s
a
t
i
o
n
a
n
d
e
c
o
n
o
mi
c
a
n
a
l
y
si
s
o
f
i
n
d
u
s
t
r
i
a
l
-
sc
a
l
e
a
n
a
e
r
o
b
i
c
c
o
-
d
i
g
e
s
t
i
o
n
(
A
C
o
D
)
o
f
p
a
l
m o
i
l
mi
l
l
e
f
f
l
u
e
n
t
(
P
O
M
E)
a
n
d
d
e
c
a
n
t
e
r
c
a
k
e
(
D
C
)
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
s:
A
c
o
mp
a
r
a
t
i
v
e
st
u
d
y
o
f
G
r
a
d
i
e
n
t
B
o
o
s
t
i
n
g
M
a
c
h
i
n
e
s
(
G
B
M
)
,
K
-
n
e
a
r
e
st
n
e
i
g
h
b
o
u
r
s
(
K
N
N
)
,
a
n
d
r
a
n
d
o
m
f
o
r
e
st
(
R
F
)
,
”
J
o
u
r
n
a
l
o
f
Wa
t
e
r
Pro
c
e
ss
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
5
8
,
p
.
1
0
4
7
5
2
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
w
p
e
.
2
0
2
3
.
1
0
4
7
5
2
.
[
1
4
]
Z
.
S
u
n
,
G
.
W
a
n
g
,
P
.
Li
,
H
.
W
a
n
g
,
M
.
Zh
a
n
g
,
a
n
d
X
.
Li
a
n
g
,
“
A
n
i
mp
r
o
v
e
d
r
a
n
d
o
m
f
o
r
e
st
b
a
sed
o
n
t
h
e
c
l
a
ssi
f
i
c
a
t
i
o
n
a
c
c
u
r
a
c
y
a
n
d
c
o
r
r
e
l
a
t
i
o
n
m
e
a
su
r
e
m
e
n
t
o
f
d
e
c
i
si
o
n
t
r
e
e
s,
”
Ex
p
e
rt
S
y
st
e
m
s
w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
3
7
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
s
w
a
.
2
0
2
3
.
1
2
1
5
4
9
.
[
1
5
]
F
.
W
a
n
g
,
“
T
h
e
a
n
a
l
y
si
s
o
f
r
e
g
i
o
n
a
l
i
c
e
a
n
d
s
n
o
w
t
o
u
r
i
s
t
d
e
s
t
i
n
a
t
i
o
n
s
u
n
d
e
r
b
a
c
k
p
r
o
p
a
g
a
t
i
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
H
e
l
i
y
o
n
,
v
o
l
.
1
0
,
n
o
.
2
3
,
p
.
e
4
0
0
3
5
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
h
e
l
i
y
o
n
.
2
0
2
4
.
e
4
0
0
3
5
.
[
1
6
]
J.
W
a
n
g
,
W
.
C
.
W
a
n
g
,
X
.
X
.
H
u
,
L
.
Q
i
u
,
a
n
d
H
.
F
.
Z
a
n
g
,
“
B
l
a
c
k
-
w
i
n
g
e
d
k
i
t
e
a
l
g
o
r
i
t
h
m:
a
n
a
t
u
r
e
-
i
n
sp
i
r
e
d
m
e
t
a
-
h
e
u
r
i
s
t
i
c
f
o
r
so
l
v
i
n
g
b
e
n
c
h
m
a
r
k
f
u
n
c
t
i
o
n
s
a
n
d
e
n
g
i
n
e
e
r
i
n
g
p
r
o
b
l
e
ms
,
”
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
R
e
v
i
e
w
,
v
o
l
.
5
7
,
n
o
.
4
,
p
.
9
8
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
4
6
2
-
0
2
4
-
1
0
7
2
3
-
4.
[
1
7
]
C
.
W
a
n
g
,
X
.
W
a
n
g
,
Q
.
Li
,
a
n
d
X
.
T
a
o
,
“
R
e
c
o
g
n
i
z
i
n
g
a
n
d
p
r
e
d
i
c
t
i
n
g
mu
scu
l
a
r
f
a
t
i
g
u
e
o
f
b
i
c
e
p
s
b
r
a
c
h
i
i
i
n
m
o
t
i
o
n
w
i
t
h
n
o
v
e
l
f
a
b
r
i
c
st
r
a
i
n
se
n
so
r
s
b
a
s
e
d
o
n
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
Bi
o
m
e
d
i
c
a
l
S
i
g
n
a
l
Pro
c
e
ssi
n
g
a
n
d
C
o
n
t
r
o
l
,
v
o
l
.
9
6
,
p
.
1
0
6
6
4
7
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
s
p
c
.
2
0
2
4
.
1
0
6
6
4
7
.
[
1
8
]
M
.
H
a
o
h
a
o
e
t
a
l
.
,
“
I
mp
r
o
v
e
d
b
l
a
c
k
-
w
i
n
g
e
d
k
i
t
e
a
l
g
o
r
i
t
h
m a
n
d
f
i
n
i
t
e
e
l
e
me
n
t
a
n
a
l
y
si
s
f
o
r
r
o
b
o
t
p
a
r
a
l
l
e
l
g
r
i
p
p
e
r
d
e
si
g
n
,
”
A
d
v
a
n
c
e
s
i
n
Me
c
h
a
n
i
c
a
l
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
6
,
n
o
.
1
0
,
p
.
1
6
8
7
8
1
3
2
2
4
1
2
8
8
4
0
2
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
7
7
/
1
6
8
7
8
1
3
2
2
4
1
2
8
8
4
0
2
.
[
1
9
]
X
.
S
h
e
n
,
Y
.
W
u
,
L.
L
i
,
a
n
d
T
.
Zh
a
n
g
,
“
A
mo
d
i
f
i
e
d
a
d
a
p
t
i
v
e
b
e
l
u
g
a
w
h
a
l
e
o
p
t
i
m
i
z
a
t
i
o
n
b
a
se
d
o
n
s
p
i
r
a
l
se
a
r
c
h
a
n
d
e
l
i
t
i
s
t
s
t
r
a
t
e
g
y
f
o
r
s
h
o
r
t
-
t
e
r
m
h
y
d
r
o
t
h
e
r
ma
l
sc
h
e
d
u
l
i
n
g
,
”
El
e
c
t
ri
c
Po
w
e
r
S
y
s
t
e
m
s
R
e
se
a
rc
h
,
v
o
l
.
2
2
8
,
p
.
1
1
0
0
5
1
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
p
sr
.
2
0
2
3
.
1
1
0
0
5
1
.
[
2
0
]
H
.
M
a
e
t
a
l
.
,
“
R
o
b
o
t
m
a
n
i
p
u
l
a
t
o
r
m
i
n
i
m
u
m
j
e
r
k
t
r
a
j
e
c
t
o
r
y
p
l
a
n
n
i
n
g
b
a
se
d
o
n
t
h
e
i
mp
r
o
v
e
d
d
u
n
g
b
e
e
t
l
e
o
p
t
i
mi
z
e
r
a
l
g
o
r
i
t
h
m
,
”
J
o
u
rn
a
l
o
f
C
i
r
c
u
i
t
s,
S
y
s
t
e
m
s
a
n
d
C
o
m
p
u
t
e
rs
,
v
o
l
.
3
4
,
n
o
.
1
,
p
.
2
5
5
0
0
2
8
,
2
0
2
5
,
d
o
i
:
1
0
.
1
1
4
2
/
S
0
2
1
8
1
2
6
6
2
5
5
0
0
2
8
8
.
[
2
1
]
H
.
M
.
A
l
a
b
o
o
l
,
D
.
A
l
a
r
a
b
i
a
t
,
L
.
A
b
u
a
l
i
g
a
h
,
a
n
d
A
.
A
.
H
e
i
d
a
r
i
,
“
H
a
r
r
i
s
H
a
w
k
s
o
p
t
i
m
i
z
a
t
i
o
n
:
a
c
o
m
p
r
e
h
e
n
si
v
e
r
e
v
i
e
w
o
f
r
e
c
e
n
t
v
a
r
i
a
n
t
s
a
n
d
a
p
p
l
i
c
a
t
i
o
n
s,
”
N
e
u
ra
l
C
o
m
p
u
t
i
n
g
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
3
,
n
o
.
1
5
,
p
p
.
8
9
3
9
–
8
9
8
0
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
2
1
-
0
2
1
-
0
5
7
2
0
-
5.
[
2
2
]
S
.
N
.
M
a
k
h
a
d
me
h
e
t
a
l
.
,
“
R
e
c
e
n
t
a
d
v
a
n
c
e
s
i
n
g
r
e
y
w
o
l
f
o
p
t
i
mi
z
e
r
,
i
t
s
v
e
r
si
o
n
s
a
n
d
a
p
p
l
i
c
a
t
i
o
n
s
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
2
2
9
9
1
–
2
3
0
2
8
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
3
0
4
8
8
9
.
[
2
3
]
M
.
X
i
a
o
,
R
.
Lu
o
,
Y
.
C
h
e
n
,
a
n
d
X
.
G
e
,
“
P
r
e
d
i
c
t
i
o
n
m
o
d
e
l
o
f
a
s
p
h
a
l
t
p
a
v
e
men
t
f
u
n
c
t
i
o
n
a
l
a
n
d
st
r
u
c
t
u
r
a
l
p
e
r
f
o
r
man
c
e
u
si
n
g
P
S
O
-
B
P
N
N
a
l
g
o
r
i
t
h
m
,
”
C
o
n
s
t
ru
c
t
i
o
n
a
n
d
Bu
i
l
d
i
n
g
M
a
t
e
ri
a
l
s
,
v
o
l
.
4
0
7
,
p
.
1
3
3
5
3
4
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
n
b
u
i
l
d
m
a
t
.
2
0
2
3
.
1
3
3
5
3
4
.
[
2
4
]
Y
.
W
u
,
A
.
C
.
Y
.
Y
u
e
n
,
C
.
M
o
,
Q
.
C
h
e
n
,
a
n
d
X
.
H
u
a
n
g
,
“
A
n
a
d
v
a
n
c
e
d
B
P
N
N
/
R
V
EA
c
o
u
p
l
e
d
c
o
n
t
r
o
l
st
r
a
t
e
g
y
f
o
r
n
o
v
e
l
i
mm
e
r
se
d
l
i
q
u
i
d
c
o
o
l
i
n
g
b
a
t
t
e
r
y
t
h
e
r
m
a
l
m
a
n
a
g
e
me
n
t
s
y
st
e
m,
”
J
o
u
r
n
a
l
o
f
E
n
e
r
g
y
S
t
o
r
a
g
e
,
v
o
l
.
1
2
5
,
p
.
1
1
7
0
0
8
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
s
t
.
2
0
2
5
.
1
1
7
0
0
8
.
[
2
5
]
Y
.
Q
.
N
i
a
n
d
M
.
L
i
,
“
W
i
n
d
p
r
e
ss
u
r
e
d
a
t
a
r
e
c
o
n
st
r
u
c
t
i
o
n
u
si
n
g
n
e
u
r
a
l
n
e
t
w
o
r
k
t
e
c
h
n
i
q
u
e
s
:
A
c
o
m
p
a
r
i
s
o
n
b
e
t
w
e
e
n
B
P
N
N
a
n
d
G
R
N
N
,
”
M
e
a
su
r
e
m
e
n
t
:
J
o
u
r
n
a
l
o
f
t
h
e
I
n
t
e
rn
a
t
i
o
n
a
l
M
e
a
s
u
rem
e
n
t
C
o
n
f
e
d
e
r
a
t
i
o
n
,
v
o
l
.
8
8
,
p
p
.
4
6
8
–
4
7
6
,
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
me
a
su
r
e
me
n
t
.
2
0
1
6
.
0
4
.
0
4
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
7
2
2
-
2
5
8
6
I
AE
S
I
n
t
J
R
o
b
&
A
u
to
m
,
Vo
l
.
1
5
,
No
.
1
,
Ma
r
ch
20
2
6
:
247
-
256
256
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Chu
n
q
in
g
Li
u
re
c
e
iv
e
d
h
e
r
b
a
c
h
e
lo
r’s
d
e
g
re
e
i
n
p
h
y
sic
a
l
e
d
u
c
a
ti
o
n
fro
m
G
a
n
n
a
n
No
rm
a
l
Un
iv
e
rsity
i
n
2
0
1
8
a
n
d
h
e
r
m
a
ste
r’s
d
e
g
re
e
in
p
h
y
sic
a
l
e
d
u
c
a
ti
o
n
a
n
d
train
in
g
fro
m
F
u
ji
a
n
N
o
rm
a
l
Un
iv
e
rsit
y
i
n
2
0
2
1
.
S
h
e
is
c
u
rre
n
tl
y
p
u
rsu
in
g
a
P
h
.
D.
in
p
h
y
sic
a
l
e
d
u
c
a
ti
o
n
a
t
Un
iv
e
rsiti
P
u
tra
M
a
lay
sia
.
He
r
r
e
se
a
rc
h
in
tere
sts
in
c
lu
d
e
p
h
y
sic
a
l
e
d
u
c
a
ti
o
n
,
sp
o
rts
sc
ien
c
e
,
a
n
d
sp
o
rts
trai
n
in
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
c
h
u
n
q
in
g
0
2
0
3
@o
u
tl
o
o
k
.
c
o
m
.
K
im
G
e
o
k
S
o
h
is
a
n
As
so
c
i
a
te
P
ro
fe
ss
o
r
i
n
th
e
De
p
a
rtme
n
t
o
f
S
p
o
r
ts
S
t
u
d
ies
,
F
a
c
u
lt
y
o
f
E
d
u
c
a
ti
o
n
a
l
S
tu
d
ies
,
Un
i
v
e
rsiti
P
u
tra
M
a
lay
sia
.
S
h
e
h
o
ld
s
a
B.
S
c
.
in
p
h
y
sic
a
l
e
d
u
c
a
ti
o
n
(
1
9
9
6
)
a
n
d
a
n
M
.
S
.
in
sp
o
rts
sc
ien
c
e
(1
9
9
8
)
fro
m
Un
i
v
e
rsiti
P
u
tra
M
a
lay
sia
,
a
n
d
a
P
h
.
D.
i
n
e
x
e
rc
ise
sc
ien
c
e
a
n
d
h
e
a
lt
h
(2
0
0
4
)
fro
m
Un
iv
e
rsiti
M
a
lay
a
,
Ku
a
la
Lu
m
p
u
r.
He
r
a
re
a
o
f
sp
e
c
ializa
ti
o
n
is
p
h
y
sic
a
l
e
d
u
c
a
ti
o
n
a
n
d
s
p
o
rts
sc
ien
c
e
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
k
ims
@u
p
m
.
e
d
u
.
m
y
.
H
a
z
izi
Abu
S
a
a
d
is
a
n
As
so
c
iate
P
ro
fe
ss
o
r
o
f
C
o
m
m
u
n
it
y
Nu
tri
ti
o
n
i
n
t
h
e
De
p
a
rtme
n
t
o
f
Nu
tri
t
io
n
a
n
d
Die
tetics
,
F
a
c
u
lt
y
o
f
M
e
d
ici
n
e
a
n
d
He
a
lt
h
S
c
ien
c
e
s,
Un
iv
e
rsit
i
P
u
tra
M
a
lay
sia
.
F
r
o
m
2
0
1
3
to
2
0
2
0
,
h
e
se
rv
e
d
a
s
De
p
u
t
y
Dire
c
to
r
o
f
th
e
S
p
o
r
ts
Ac
a
d
e
m
y
a
t
Un
iv
e
rsiti
P
u
tra
M
a
lay
sia
.
He
is
a
m
e
m
b
e
r
a
n
d
e
x
p
e
rt
o
n
se
v
e
r
a
l
n
a
ti
o
n
a
l
c
o
m
m
it
tee
s
a
n
d
se
rv
e
s
a
s
a
re
se
a
r
c
h
c
o
n
su
lt
a
n
t
i
n
th
e
field
s
o
f
n
u
tri
ti
o
n
,
p
h
y
sic
a
l
a
c
ti
v
it
y
,
a
n
d
o
b
e
sity
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
h
a
z
izi@u
p
m
.
e
d
u
.
m
y
.
H
a
o
h
a
o
Ma
re
c
e
iv
e
d
h
is
b
a
c
h
e
lo
r’s
d
e
g
re
e
i
n
m
e
c
h
a
n
ica
l
d
e
sig
n
,
m
a
n
u
fa
c
tu
rin
g
,
a
n
d
a
u
to
m
a
ti
o
n
fro
m
No
rt
h
U
n
iv
e
rsity
o
f
C
h
i
n
a
in
2
0
1
1
a
n
d
h
is
m
a
ste
r’s d
e
g
re
e
in
m
e
c
h
a
n
ica
l
a
n
d
e
lec
tro
n
ic
e
n
g
in
e
e
rin
g
fr
o
m
Xid
ian
U
n
iv
e
rsit
y
,
C
h
i
n
a
,
i
n
2
0
1
4
.
He
is
c
u
rre
n
tl
y
p
u
rs
u
in
g
a
P
h
.
D.
in
e
n
g
in
e
e
rin
g
a
t
U
n
iv
e
rsit
i
P
u
tra
M
a
lay
sia
.
He
is
a
lso
a
L
e
c
tu
re
r
a
t
Ti
a
n
sh
u
i
No
rm
a
l
Un
iv
e
rsity
,
C
h
in
a
.
His
re
se
a
rc
h
i
n
tere
sts
in
c
lu
d
e
i
n
telli
g
e
n
t
o
p
ti
m
i
z
a
ti
o
n
a
l
g
o
rit
h
m
s,
r
o
b
o
t
ics
,
a
n
d
n
e
u
ra
l
n
e
two
r
k
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
m
a
h
a
o
1
0
0
1
@
o
u
t
lo
o
k
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.