I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
9
,
No
.
4
,
A
u
g
u
s
t
201
9
,
p
p
.
2
9
9
3
~3
0
0
1
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v9
i
4
.
p
p
2
9
9
3
-
3001
2993
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e
.
co
m/
jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
I
JE
C
E
A
m
ultilabel
c
la
ss
ificatio
n
a
ppro
a
c
h f
o
r
c
o
m
plex
h
u
m
a
n
a
ctivities using
a
c
o
m
bina
tion
of
e
m
ergi
ng
p
a
tt
erns
a
nd
f
u
zz
y
s
e
ts
Neha
l A
.
Sa
k
r
1
,
M
er
v
a
t
Abu
-
E
lK
heir
2
,
A.
At
w
a
n
3
,
H
.
H
.
So
li
m
a
n
4
1
,
3,
4
De
p
a
rtm
e
n
t
o
f
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
F
a
c
u
lt
y
o
f
Co
m
p
u
ter a
n
d
I
n
f
o
rm
a
ti
o
n
S
c
ien
c
e
s,
M
a
n
so
u
ra
Un
iv
e
rsit
y
,
Eg
y
p
t
2
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
,
F
a
c
u
lt
y
o
f
M
e
d
ia E
n
g
in
e
e
rin
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
T
h
e
G
e
r
m
a
n
Un
iv
e
rsit
y
in
Ca
iro
,
Eg
y
p
t
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
12
,
2
0
1
8
R
ev
i
s
ed
Mar
3
0
,
2
0
1
9
A
cc
ep
ted
A
p
r
3
,
2
0
1
9
In
o
u
r
d
a
il
y
li
v
e
s,
h
u
m
a
n
s
p
e
rf
o
r
m
d
iff
e
re
n
t
A
c
ti
v
it
ies
o
f
Da
il
y
L
iv
in
g
(A
D
L
),
su
c
h
a
s
c
o
o
k
in
g
,
a
n
d
stu
d
y
in
g
.
A
c
c
o
rd
in
g
to
t
h
e
n
a
t
u
re
o
f
h
u
m
a
n
s,
th
e
y
p
e
r
f
o
r
m
th
e
se
a
c
ti
v
it
ies
in
a
se
q
u
e
n
ti
a
l/
sim
p
le
o
r
a
n
o
v
e
rlap
p
in
g
/co
m
p
lex
sc
e
n
a
rio
.
M
a
n
y
re
s
e
a
rc
h
a
tt
e
m
p
ts
a
d
d
re
ss
e
d
sim
p
le
a
c
ti
v
it
y
re
c
o
g
n
it
io
n
,
b
u
t
c
o
m
p
lex
a
c
ti
v
it
y
re
c
o
g
n
it
io
n
is
stil
l
a
c
h
a
ll
e
n
g
in
g
issu
e
.
Re
c
o
g
n
it
io
n
o
f
c
o
m
p
lex
a
c
ti
v
it
ies
is
a
m
u
lt
il
a
b
e
l
c
las
sif
ic
a
ti
o
n
p
ro
b
lem
,
su
c
h
th
a
t
a
te
st
in
sta
n
c
e
is
a
ss
i
g
n
e
d
to
a
m
u
lt
ip
le
o
v
e
rlap
p
i
n
g
a
c
ti
v
it
ies
.
Ex
isti
n
g
d
a
ta
-
d
riv
e
n
tec
h
n
iq
u
e
s
f
o
r
c
o
m
p
lex
a
c
ti
v
it
y
r
e
c
o
g
n
it
io
n
c
a
n
re
c
o
g
n
ize
a
m
a
x
i
m
u
m
n
u
m
b
e
r
o
f
t
w
o
o
v
e
rlap
p
in
g
a
c
ti
v
it
ies
a
n
d
re
q
u
ire a
train
in
g
d
a
tas
e
t
o
f
c
o
m
p
le
x
(i.
e
.
m
u
lt
il
a
b
e
l)
a
c
ti
v
it
ies
.
In
th
is
p
a
p
e
r,
w
e
p
ro
p
o
se
a
m
u
lt
il
a
b
e
l
c
las
sif
ica
ti
o
n
a
p
p
r
o
a
c
h
f
o
r
c
o
m
p
lex
a
c
ti
v
it
y
r
e
c
o
g
n
it
io
n
u
sin
g
a
c
o
m
b
in
a
ti
o
n
o
f
Em
e
rg
in
g
P
a
tt
e
r
n
s
a
n
d
F
u
z
z
y
S
e
ts.
In
o
u
r
a
p
p
r
o
a
c
h
,
w
e
re
q
u
ire
a
train
in
g
d
a
tas
e
t
o
f
o
n
ly
si
m
p
le
(i.
e
.
sin
g
le
-
lab
e
l)
a
c
ti
v
it
ies
.
F
irst,
w
e
u
se
a
p
a
tt
e
rn
m
in
in
g
tec
h
n
iq
u
e
to
e
x
trac
t
d
isc
rim
in
a
ti
v
e
f
e
a
t
u
re
s
c
a
ll
e
d
S
tro
n
g
Ju
m
p
in
g
Em
e
rg
in
g
P
a
tt
e
rn
s
(S
JE
P
s)
th
a
t
e
x
c
lu
siv
e
ly
r
e
p
re
se
n
t
e
a
c
h
a
c
ti
v
it
y
.
T
h
e
n
,
o
u
r
sc
o
r
in
g
f
u
n
c
ti
o
n
tak
e
s
S
JEP
s
a
n
d
f
u
z
z
y
m
e
m
b
e
rsh
ip
v
a
lu
e
s
o
f
in
c
o
m
in
g
se
n
so
r
d
a
ta
a
n
d
o
u
t
p
u
ts
th
e
a
c
ti
v
it
y
lab
e
l(s)
.
W
e
v
a
li
d
a
te
o
u
r
a
p
p
ro
a
c
h
u
si
n
g
tw
o
d
if
fe
re
n
t
d
a
tas
e
t.
Ex
p
e
rim
e
n
tal
re
su
lt
s
d
e
m
o
n
stra
te
th
e
e
ff
icie
n
c
y
a
n
d
su
p
e
rio
ri
ty
o
f
o
u
r
a
p
p
r
o
a
c
h
a
g
a
in
st o
th
e
r
a
p
p
ro
a
c
h
e
s.
K
ey
w
o
r
d
s
:
C
o
m
p
le
x
a
ctiv
it
y
r
ec
o
g
n
itio
n
Fu
zz
y
s
et
s
Mu
ltil
ab
el
c
la
s
s
i
f
icatio
n
P
atter
n
m
i
n
in
g
P
er
v
asiv
e
c
o
m
p
u
ti
n
g
Co
p
y
rig
h
t
©
2
0
1
9
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Neh
al
A
.
Sa
k
r
,
Dep
ar
t
m
en
t I
n
f
o
r
m
atio
n
T
ec
h
n
o
lo
g
y
,
Facu
lt
y
o
f
C
o
m
p
u
ter
an
d
I
n
f
o
r
m
atio
n
Scien
ce
s
,
Ma
n
s
o
u
r
a
U
n
iv
er
s
it
y
,
6
0
E
lg
o
m
h
o
r
ia
s
t,
Ma
n
s
o
u
r
a
Un
i
v
er
s
it
y
,
Dak
a
h
lia,
E
g
y
p
t.
E
m
ail:
n
eh
al_
s
ak
r
@
m
an
s
.
ed
u
.
eg
1.
I
NT
RO
D
UCT
I
O
N
Hu
m
an
A
ct
iv
i
t
y
R
ec
o
g
n
itio
n
(
HA
R
)
is
a
f
ield
in
p
er
v
as
iv
e
co
m
p
u
tin
g
,
th
a
t
is
co
n
ce
r
n
ed
w
it
h
r
ec
o
g
n
izi
n
g
th
e
ac
tiv
ities
p
er
f
o
r
m
ed
b
y
a
p
er
s
o
n
u
s
in
g
d
ata
co
llect
ed
f
r
o
m
th
e
m
o
n
ito
r
i
n
g
d
e
v
ices.
I
n
th
e
b
eg
i
n
n
i
n
g
o
f
H
A
R
,
v
i
s
io
n
-
b
ased
HAR
u
s
ed
ca
m
er
as
to
m
o
n
ito
r
h
u
m
a
n
s
w
it
h
i
n
th
eir
s
u
r
r
o
u
n
d
i
n
g
en
v
ir
o
n
m
e
n
t
s
[
1
]
.
T
h
e
r
ap
id
d
ev
elo
p
m
en
t
s
o
f
t
h
e
m
o
n
it
o
r
in
g
d
ev
ice
s
f
r
o
m
ca
m
er
as
to
s
en
s
o
r
s
lead
to
t
h
e
r
elea
s
e
o
f
s
e
n
s
o
r
-
b
ased
HAR
[
2
]
.
I
n
s
e
n
s
o
r
-
b
ased
HAR,
h
u
m
a
n
s
w
ea
r
s
en
s
o
r
s
o
r
in
s
tall
th
e
m
i
n
th
e
s
u
r
r
o
u
n
d
in
g
e
n
v
ir
o
n
m
e
n
t
to
tr
ac
k
t
h
eir
m
o
v
e
m
e
n
t
s
,
a
n
d
en
v
ir
o
n
m
en
tal
co
n
d
itio
n
s
.
Sen
s
o
r
-
b
as
ed
H
AR
g
ain
s
a
lo
t
o
f
r
esear
c
h
i
n
ter
e
s
t
d
u
e
to
t
h
e
w
id
e
r
an
g
e
o
f
i
ts
ap
p
licatio
n
d
o
m
a
in
s
i
n
m
e
d
ical,
s
ec
u
r
it
y
,
an
d
m
ilit
ar
y
[
3
]
.
I
n
th
is
p
ap
er
,
w
e
ar
e
in
ter
e
s
te
d
in
s
e
n
s
o
r
-
b
ased
H
A
R
in
w
h
ich
h
u
m
a
n
ac
ti
v
it
y
i
s
co
m
p
r
is
ed
o
f
a
s
e
t
o
f
s
en
s
o
r
r
ea
d
in
g
s
o
cc
u
r
r
in
g
w
it
h
i
n
a
s
p
ec
if
ic
ti
m
e
i
n
ter
v
al.
E
ac
h
o
f
th
ese
r
ea
d
in
g
s
f
o
r
m
s
an
ac
tio
n
th
at
r
ep
r
esen
ts
an
a
to
m
ic
o
p
er
atio
n
s
u
ch
a
s
o
p
en
in
g
fr
id
g
e
.
W
it
h
in
a
s
p
ec
if
ic
ti
m
e
in
te
r
v
al,
a
p
er
s
o
n
ca
n
p
er
f
o
r
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
4
,
A
u
g
u
s
t 2
0
1
9
:
2
9
9
3
-
300
1
2994
m
u
ltip
le
ac
tiv
ities
s
eq
u
en
tiall
y
o
r
in
a
co
m
p
le
x
s
ce
n
ar
io
.
S
eq
u
en
tial
(
i.e
.
s
i
m
p
le)
ac
tiv
iti
es
ar
e
ex
ec
u
ted
o
n
e
af
ter
t
h
e
o
th
er
,
w
h
ile
co
m
p
l
ex
ac
ti
v
itie
s
m
a
y
b
e
e
x
ec
u
t
ed
in
a
co
n
c
u
r
r
en
t
o
r
a
n
i
n
ter
leav
ed
m
a
n
n
er
.
I
n
co
n
c
u
r
r
en
t
ac
t
i
v
itie
s
,
ac
tio
n
s
o
f
d
if
f
er
e
n
t
ac
ti
v
itie
s
ar
e
ex
ec
u
ted
s
i
m
u
ltan
o
u
s
l
y
.
I
n
in
ter
leav
ed
ac
tiv
ities
,
ac
tio
n
s
o
f
d
i
f
f
er
en
t
ac
ti
v
itie
s
ar
e
ex
ec
u
ted
i
n
ter
ch
a
n
g
ea
b
il
it
y
.
Fi
g
u
r
e
1
il
lu
s
tr
ates
d
if
f
er
e
n
t
t
y
p
es
o
f
ac
tiv
it
y
ex
ec
u
t
io
n
w
it
h
ex
a
m
p
le
s
.
Fig
u
r
e
1
.
Si
m
p
le,
in
ter
leav
ed
,
an
d
co
n
cu
r
r
en
t a
ct
iv
i
ties
w
it
h
ex
a
m
p
le
s
Ma
n
y
r
esear
ch
atte
m
p
ts
h
a
v
e
b
ee
n
i
n
tr
o
d
u
ce
d
f
o
r
s
i
m
p
le
ac
tiv
it
y
r
ec
o
g
n
it
io
n
,
b
u
t
lit
tle
wo
r
k
tar
g
et
s
co
m
p
le
x
ac
ti
v
it
y
r
ec
o
g
n
itio
n
an
d
s
till
s
a
ch
alle
n
g
in
g
is
s
u
e.
C
o
m
p
lex
ac
t
i
v
it
y
r
ec
o
g
n
iti
o
n
is
a
m
u
l
tilab
el
class
i
f
icatio
n
p
r
o
b
lem
,
an
d
a
test
in
s
tan
ce
is
a
s
s
i
g
n
ed
m
u
ltip
le
clas
s
lab
els.
Fo
r
in
s
ta
n
ce
,
w
h
e
n
u
s
er
i
s
d
r
in
kin
g
co
ffee
w
h
ile
w
a
tch
in
g
TV
,
th
e
r
ec
o
g
n
itio
n
m
o
d
el
s
h
o
u
ld
id
en
ti
f
y
th
e
s
e
t
w
o
ac
ti
v
ities
.
E
x
is
ti
n
g
d
ata
-
d
r
iv
en
ap
p
r
o
ac
h
es
f
o
r
co
m
p
le
x
H
AR
h
a
v
e
s
o
m
e
li
m
itat
io
n
s
.
First,
in
o
r
d
er
to
r
ec
o
g
n
ize
co
m
p
le
x
ac
ti
v
itie
s
,
th
e
y
r
eq
u
ir
e
a
tr
ain
i
n
g
d
atase
t o
f
co
m
p
lex
ac
ti
v
it
ies.
C
o
n
s
id
e
r
w
e
h
a
v
e
m
ac
ti
v
itie
s
,
an
d
t
h
e
n
w
e
h
a
v
e
m
(
m
-
1)
p
o
s
s
ib
le
co
m
b
i
n
atio
n
s
th
a
t
f
o
r
m
co
m
p
lex
o
n
es,
w
h
ic
h
is
d
i
f
f
icu
lt
to
o
b
tain
.
Seco
n
d
l
y
,
ex
is
t
in
g
ap
p
r
o
ac
h
es
f
o
r
co
m
p
le
x
H
AR
li
m
it
th
e
n
u
m
b
er
o
f
o
v
er
lap
p
in
g
ac
ti
v
itie
s
,
an
d
ca
n
n
o
t
r
ec
o
g
n
ize
m
o
r
e
th
an
t
w
o
o
v
er
lap
p
in
g
(
i.e
.
in
ter
leav
ed
o
r
co
n
cu
r
r
en
t)
ac
tiv
itie
s
.
I
n
t
h
is
p
ap
er
,
w
e
p
r
ese
n
t
a
n
o
v
el
m
u
ltil
a
b
el
cla
s
s
i
f
icatio
n
ap
p
r
o
a
ch
o
f
co
m
p
le
x
h
u
m
a
n
ac
tiv
itie
s
.
I
n
o
u
r
ap
p
r
o
ac
h
,
w
e
ca
n
r
ec
o
g
n
ize
m
u
lt
ilab
eled
(
i.e
.
co
m
p
lex
)
ac
ti
v
itie
s
f
r
o
m
s
i
n
g
le
-
l
ab
eled
(
i.e
.
s
i
m
p
le)
ac
tiv
itie
s
.
T
h
is
is
ac
h
iev
ed
b
y
m
a
k
i
n
g
a
co
m
b
in
a
tio
n
o
f
E
m
er
g
i
n
g
P
atter
n
s
a
n
d
F
u
zz
y
Sets
.
Fi
r
s
t,
w
e
u
s
e
a
tr
ain
i
n
g
d
ataset
o
f
s
i
m
p
le
ac
t
i
v
itie
s
a
n
d
ap
p
l
y
a
p
atter
n
m
i
n
in
g
tech
n
iq
u
e
to
e
x
tr
ac
t
d
is
c
r
i
m
i
n
ati
v
e
f
ea
t
u
r
es
th
at
ar
e
ex
cl
u
s
iv
el
y
p
r
ese
n
t
i
n
ea
c
h
ac
ti
v
it
y
ca
lled
Stro
n
g
J
u
m
p
i
n
g
E
m
er
g
i
n
g
P
atter
n
s
(
SJ
E
P
s
)
.
T
h
en
,
o
u
r
r
ec
o
g
n
itio
n
m
o
d
el
u
s
e
a
s
co
r
i
n
g
f
u
n
c
tio
n
to
id
en
t
if
y
ac
ti
v
it
y
lab
el(
s
)
u
s
in
g
t
h
e
e
x
tr
ac
ted
SJ
E
P
s
w
it
h
f
u
zz
y
m
e
m
b
er
s
h
ip
v
a
lu
e
s
o
f
i
n
co
m
i
n
g
s
en
s
o
r
ev
en
t
s
(
ac
tio
n
s
)
.
T
h
e
r
est
o
f
p
ap
er
is
o
r
g
a
n
ize
d
as
f
o
llo
w
s
.
I
n
S
ec
tio
n
2
,
we
r
ev
ie
w
th
e
p
r
ev
io
u
s
w
o
r
k
p
r
o
p
o
s
ed
f
o
r
co
m
p
le
x
H
AR
.
T
h
en
,
w
e
f
o
r
m
u
la
te
o
u
r
p
r
o
b
lem
a
n
d
in
t
r
o
d
u
ce
th
e
r
eq
u
ir
ed
p
r
elim
in
ar
ies
in
S
ec
t
io
n
3
.
Sectio
n
4
in
tr
o
d
u
ce
s
th
e
p
r
o
p
o
s
e
d
ap
p
r
o
ac
h
f
o
r
co
m
p
lex
H
AR
.
I
n
S
ec
tio
n
5
,
w
e
p
r
esen
t
o
u
r
em
p
ir
ical
r
esu
lts
.
Fin
all
y
,
w
e
co
n
cl
u
d
e
o
u
r
w
o
r
k
an
d
d
is
cu
s
s
o
u
r
p
lan
s
f
o
r
f
u
t
u
r
e
w
o
r
k
i
n
S
ec
tio
n
6
.
2.
RE
L
AT
E
D
WO
RK
T
h
e
ex
is
ti
n
g
ap
p
r
o
ac
h
es
f
o
r
HAR
ca
n
b
e
d
i
v
id
ed
in
to
t
wo
p
r
o
m
i
n
en
t
ap
p
r
o
ac
h
es
d
ata
-
d
r
iv
en
a
n
d
k
n
o
w
led
g
e
-
d
r
i
v
en
ap
p
r
o
ac
h
es
[
4
]
.
I
n
th
is
p
ap
er
,
w
e
ar
e
in
t
er
ested
in
d
ata
-
d
r
iv
en
ap
p
r
o
ac
h
es
th
a
t
r
eq
u
ir
e
a
p
r
ed
ef
in
ed
d
ataset
to
b
u
ild
th
e
class
i
f
icatio
n
m
o
d
el
u
s
i
n
g
m
a
ch
in
e
-
le
ar
n
i
n
g
tec
h
n
iq
u
es,
a
n
d
th
en
u
s
e
th
e
b
u
i
lt
m
o
d
el
to
id
en
ti
f
y
u
n
lab
eled
a
ctiv
itie
s
.
A
s
a
m
u
l
tilab
el
clas
s
if
icatio
n
p
r
o
b
le
m
,
th
e
p
r
o
b
le
m
o
f
co
m
p
le
x
H
AR
ca
n
b
e
h
a
n
d
led
w
it
h
t
h
r
ee
m
ai
n
ap
p
r
o
ac
h
es:
d
ata
tr
an
s
f
o
r
m
at
io
n
,
m
et
h
o
d
ad
ap
tatio
n
,
an
d
e
n
s
e
m
b
le
o
f
class
i
f
i
er
s
[
5
]
.
T
h
e
d
ata
tr
an
s
f
o
r
m
atio
n
ap
p
r
o
ac
h
co
n
v
er
ts
t
h
e
m
u
ltil
ab
el
class
i
f
icatio
n
p
r
o
b
lem
i
n
to
a
n
u
m
b
er
o
f
b
in
ar
y
cla
s
s
i
f
icatio
n
p
r
o
b
lem
s
(
e.
g
.
b
in
ar
y
r
elev
a
n
ce
,
clas
s
if
ier
c
h
ai
n
)
,
m
u
l
ticla
s
s
c
lass
if
icatio
n
p
r
o
b
lem
s
(
e.
g
.
lab
el
p
o
w
er
s
et)
,
o
r
u
s
e
en
s
e
m
b
le
m
et
h
o
d
s
.
Fo
r
e
x
a
m
p
le,
i
n
[
6
]
th
e
au
t
h
o
r
s
ap
p
lied
a
d
y
n
a
m
ic
s
eg
m
e
n
tatio
n
ap
p
r
o
ac
h
to
s
p
lit
co
m
p
le
x
ac
tiv
ities
i
n
to
m
u
lti
p
le
s
i
m
p
le
ac
tiv
ities
,
an
d
t
h
en
ap
p
ly
th
e
R
an
d
o
m
Fo
r
est tec
h
n
iq
u
e
w
it
h
a
v
o
ti
n
g
m
ec
h
a
n
i
s
m
to
id
en
tify
ac
ti
v
it
y
lab
els.
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:
2
0
8
8
-
8708
A
mu
ltil
a
b
el
cla
s
s
ifica
tio
n
a
p
p
r
o
a
ch
fo
r
co
mp
lex
h
u
ma
n
a
ctivities u
s
in
g
a
co
mb
in
a
tio
n
o
f
.
.
.
(
N
eh
a
l A
.
S
a
kr)
2995
On
t
h
e
o
th
er
h
an
d
,
m
et
h
o
d
ad
ap
tatio
n
ap
p
r
o
ac
h
ex
ten
d
s
th
e
tr
ad
itio
n
a
l
m
e
th
o
d
s
f
o
r
b
in
ar
y
class
i
f
icatio
n
to
s
u
p
p
o
r
t
m
u
lt
ilab
el
class
i
f
ica
tio
n
.
T
h
e
ex
is
tin
g
atte
m
p
ts
ar
e
p
r
o
b
ab
ilis
ti
c
g
r
ap
h
ical
m
o
d
els,
p
atter
n
m
i
n
i
n
g
-
b
ased
m
o
d
els,
o
r
ar
e
b
ased
o
n
tim
e
s
er
ie
s
class
i
f
icatio
n
.
I
n
[
7
,
8
]
th
e
au
th
o
r
s
e
x
te
n
d
th
e
tr
ad
itio
n
al
C
o
n
d
itio
n
a
l
R
an
d
o
m
Field
s
(
C
R
Fs
)
to
h
a
n
d
le
co
m
p
lex
ac
ti
v
itie
s
.
T
h
e
y
p
r
o
p
o
s
ed
a
Facto
r
ial
C
R
F
(
FC
R
F),
an
d
a
S
k
ip
c
h
ai
n
C
R
F
(
S
C
C
R
F)
r
esp
ec
ti
v
el
y
.
I
n
[
9
]
,
th
e
au
t
h
o
r
s
p
r
esen
ted
a
m
o
d
if
ied
H
id
d
e
n
Ma
r
k
o
v
Mo
d
el
(
HM
M)
to
d
ea
l
w
it
h
in
ter
leav
ed
ac
tiv
itie
s
ca
lled
I
n
ter
leav
ed
HM
M
(
I
HM
M)
.
A
ls
o
[
1
0
]
p
r
esen
ted
a
m
o
d
i
f
ied
Naï
v
e
B
a
y
es
(
NB
)
ca
lled
I
n
ter
v
al
T
em
p
o
r
al
B
a
y
esia
n
Net
w
o
r
k
(
I
T
B
N)
.
A
n
o
th
e
r
atte
m
p
t
p
r
esen
ted
a
p
atter
n
m
in
i
n
g
ap
p
r
o
ac
h
to
r
ec
o
g
n
ize
s
i
m
p
le,
in
ter
lea
v
ed
,
an
d
co
n
cu
r
r
en
t
ac
tiv
ities
[
1
1
]
,
an
d
ti
m
e
-
s
er
ie
s
b
ased
class
i
f
ic
atio
n
in
[
1
2
]
.
3.
P
RE
L
I
M
I
NARIE
S
B
ef
o
r
e
g
o
in
g
i
n
d
ep
th
to
th
e
p
r
o
p
o
s
ed
m
o
d
el,
w
e
f
o
r
m
u
late
th
e
ta
s
k
o
f
s
e
n
s
o
r
-
b
as
e
d
HA
R
a
s
f
o
llo
w
s
.
C
o
n
s
id
er
w
e
h
av
e
a
s
et
S
o
f
s
en
s
o
r
s
attac
h
ed
to
h
u
m
an
o
r
i
n
s
tal
led
in
t
h
e
en
v
ir
o
n
m
e
n
t.
U
s
i
n
g
t
h
ese
s
en
s
o
r
s
to
m
o
n
ito
r
h
u
m
a
n
b
e
h
av
io
r
,
w
e
o
b
tain
a
d
ata
s
et
=
{
1
,
2
,
…
.
}
th
at
co
n
s
is
ts
o
f
a
s
et
o
f
ac
ti
v
it
y
tr
ac
es
.
E
ac
h
tr
ac
e
is
as
a
s
eq
u
en
ce
o
f
tr
i
g
g
er
ed
s
en
s
o
r
s
(
i.e
.
ev
e
n
ts
)
,
w
h
er
ea
s
ea
c
h
ev
en
t
is
a
t
u
p
le
o
f
<
,
,
,
>
w
h
er
e,
ts
r
ep
r
esen
ts
ti
m
e
s
ta
m
p
,
sn
:
s
en
s
o
r
n
a
m
e,
sv
:
s
en
s
o
r
v
al
u
e,
l
:
th
e
ac
tiv
it
y
la
b
el
f
r
o
m
t
h
e
s
e
t
A
o
f
n
ac
ti
v
it
y
lab
els.
Ou
r
m
ai
n
g
o
al
is
to
b
u
i
ld
a
m
ap
p
in
g
f
u
n
ctio
n
(
MF)
th
a
t
ass
i
g
n
n
e
w
ac
t
iv
i
t
y
tr
ac
es
f
o
r
s
i
m
p
le
o
r
co
m
p
le
x
ac
tiv
itie
s
w
i
th
t
h
e
co
r
r
ec
t
lab
el(
s
)
.
B
elo
w
w
e
li
s
t
a
s
et
o
f
d
e
f
i
n
itio
n
r
eq
u
ir
ed
i
n
o
u
r
p
r
o
p
o
s
e
d
ap
p
r
o
ac
h
[
1
3
]
.
I
t
e
m
s
et
,
i
n
o
u
r
ta
s
k
a
n
ite
m
i
co
r
r
esp
o
n
d
s
to
a
p
air
o
f
s
en
s
o
r
n
a
m
e
an
d
v
al
u
e,
s
u
ch
th
a
t a
s
et
o
f
ite
m
s
f
o
r
m
s
a
n
ite
m
s
et
=
{
1
,
2
,
…
.
}
.
T
he
s
up
po
rt
,
f
o
r
an
ite
m
s
e
t
X
in
d
ataset
D
,
r
ef
er
r
ed
as s
(
,
)
=
(
,
)
(
)
⁄
.
T
he
G
ro
w
t
h
ra
t
e
,
f
o
r
an
ite
m
s
et
X
f
r
o
m
d
ataset
1
to
d
at
aset
2
r
ef
er
r
ed
as
(
,
1
,
2
)
i
s
co
m
p
u
ted
as:
(
,
1
,
2
)
=
{
0
(
,
1
)
=
0
,
(
,
2
)
=
0
∞
(
,
1
)
=
0
(
,
2
)
>
0
(
,
2
)
(
,
1
)
⁄
ℎ
E
m
er
g
ing
P
a
t
t
er
n
(
E
P
)
,
a
p
atter
n
X
i
s
E
P
,
(
)
=
{
:
(
,
2
)
>
,
(
,
1
,
2
)
≥
ρ
}
,
w
h
er
e
is
t
h
e
t
h
r
esh
o
ld
o
f
m
in
i
m
u
m
s
u
p
p
o
r
t,
an
d
ρ
th
e
t
h
r
e
s
h
o
ld
o
f
m
i
n
i
m
u
m
g
r
o
w
t
h
r
at
e.
W
ith
r
eg
ar
d
to
th
e
ta
s
k
o
f
H
AR
,
E
P
s
r
ep
r
esen
t
th
e
d
i
s
cr
i
m
in
at
iv
e
f
ea
t
u
r
e
s
b
et
w
ee
n
ac
tiv
it
y
clas
s
es.
T
h
er
ef
o
r
e,
E
P
s
m
ak
e
ab
s
o
lu
te
s
ep
ar
atio
n
.
I
n
ad
d
itio
n
,
th
e
n
u
m
b
er
o
f
t
h
e
ex
tr
ac
te
d
E
P
s
w
ill
b
e
ex
tr
e
m
e
l
y
h
ig
h
.
I
n
o
r
d
e
r
to
r
ed
u
ce
th
e
n
u
m
b
er
o
f
t
h
e
e
x
tr
ac
ted
E
P
s
,
w
e
in
tr
o
d
u
ce
t
h
e
Mi
n
E
P
s
.
M
ini
m
a
l
E
m
er
g
ing
P
a
t
t
er
n
(
M
inE
P
)
,
a
p
atter
n
X
is
Min
E
P
f
r
o
m
1
to
2
,
(
,
1
,
2
)
=
{
:
(
,
1
,
2
)
≥
ρ
,
∄
|
⊂
(
,
1
,
2
)
≥
ρ
}
.
J
u
m
pin
g
E
m
er
g
ing
P
a
t
t
er
n
(
J
E
P
)
,
a
p
atter
n
X
is
J
E
P
f
r
o
m
1
to
2
,
(
,
1
,
2
)
=
{
:
(
,
1
,
2
)
=
∞
}
.
Str
o
ng
J
u
m
p
ing
E
m
er
g
i
n
g
P
a
t
t
er
n
(
SJ
E
P
)
,
a
p
a
tter
n
X
is
SJ
E
P
f
r
o
m
1
to
2
,
(
,
1
,
2
)
=
{
:
(
,
1
,
2
)
=
∞
,
∄
⊂
:
(
,
1
,
2
)
=
∞
}
.
Ou
r
m
a
in
g
o
al
i
s
th
e
r
ec
o
g
n
itio
n
o
f
co
m
p
le
x
h
u
m
an
ac
tiv
ities
u
s
in
g
a
tr
ain
in
g
d
ata
s
et
o
f
s
i
m
p
le
ac
t
iv
i
ties
,
s
o
,
w
e
n
ee
d
d
is
cr
i
m
i
n
ati
v
e
f
ea
t
u
r
es
t
h
at
ar
e
ex
clu
s
iv
e
l
y
p
r
esen
t
in
ea
ch
ac
tiv
it
y
clas
s
.
T
h
is
is
ac
h
ie
v
e
d
w
it
h
th
e
s
p
ec
i
f
ic
t
y
p
e
o
f
E
P
s
ca
lled
SJ
E
P
s
th
a
t
co
m
b
in
e
t
h
e
d
is
cr
i
m
i
n
ati
v
e
ch
ar
ac
ter
is
tic
s
o
f
J
E
P
s
an
d
Min
E
P
s
.
A
d
etai
led
d
is
cu
s
s
io
n
ab
o
u
t d
i
f
f
er
e
n
t t
y
p
es o
f
E
P
s
w
i
th
e
x
a
m
p
le
w
i
ll b
e
f
o
u
n
d
in
[
1
4
]
.
4.
T
H
E
P
RO
P
O
SE
D
AP
P
RO
A
CH
I
n
th
i
s
p
ap
er
,
w
e
p
r
esen
t
a
n
o
v
el
ap
p
r
o
ac
h
f
o
r
th
e
r
ec
o
g
n
i
tio
n
o
f
s
i
m
p
le
a
n
d
co
m
p
lex
h
u
m
a
n
ac
tiv
itie
s
u
s
i
n
g
a
co
m
b
in
a
tio
n
o
f
E
m
er
g
in
g
P
atter
n
s
an
d
F
u
z
z
y
Set
s
.
T
h
is
is
ac
co
m
p
l
is
h
ed
in
t
w
o
m
ain
p
h
ase
s
tr
ain
i
n
g
a
n
d
tes
tin
g
a
s
s
h
o
w
n
in
F
ig
u
r
e
2
.
I
n
t
h
e
f
ir
s
t
p
h
ase,
w
e
u
s
e
a
tr
ain
in
g
d
atase
t
o
f
s
i
m
p
le
ac
ti
v
itie
s
an
d
p
r
o
d
u
ce
;
th
e
d
is
cr
i
m
i
n
ati
v
e
SJ
E
P
s
f
o
r
ea
ch
ac
tiv
it
y
c
lass
,
b
esid
es
s
e
n
s
o
r
/acti
v
it
y
co
r
r
elatio
n
m
a
tr
ix
.
T
h
en
,
in
t
h
e
s
ec
o
n
d
p
h
ase,
we
s
eg
m
e
n
t
t
h
e
i
n
co
m
i
n
g
s
e
n
s
o
r
d
ata,
an
d
th
e
n
ea
c
h
s
eg
m
e
n
t
i
s
as
s
ig
n
ed
w
it
h
th
e
co
r
r
esp
o
n
d
in
g
lab
el(
s
)
u
s
in
g
o
u
r
co
n
s
tr
u
cted
s
co
r
in
g
f
u
n
ctio
n
.
B
el
o
w
,
w
e
d
is
c
u
s
s
th
ese
t
w
o
p
h
a
s
es
in
d
etails.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
4
,
A
u
g
u
s
t 2
0
1
9
:
2
9
9
3
-
300
1
2996
Fig
u
r
e
2
.
T
h
e
p
r
o
p
o
s
ed
S
J
E
P
-
b
ased
ap
p
r
o
ac
h
f
o
r
s
i
m
p
le
a
n
d
co
m
p
le
x
ac
ti
v
ities
r
ec
o
g
n
it
io
n
4
.
1
.
T
he
t
ra
ini
ng
p
ha
s
e
T
h
e
m
ai
n
g
o
als o
f
th
i
s
p
h
ase
a
r
e
th
e
m
i
n
i
n
g
o
f
t
h
e
SJ
E
P
s
,
co
m
p
u
tat
io
n
o
f
t
h
e
d
is
cr
i
m
in
at
iv
e
s
co
r
e
o
f
SJ
E
P
s
,
an
d
co
m
p
u
tat
io
n
o
f
t
h
e
s
en
s
o
r
/acti
v
it
y
co
r
r
elat
io
n
m
a
tr
ix
r
eq
u
ir
ed
at
th
e
test
in
g
p
h
a
s
e.
4
.
1
.
1
.
M
ini
ng
t
he
s
t
ro
ng
j
um
pin
g
e
m
er
g
i
ng
pa
t
t
er
ns
Fro
m
t
h
e
c
h
ar
ac
ter
is
tic
s
o
f
S
J
E
P
s
in
tr
o
d
u
ce
d
b
ef
o
r
e,
th
e
y
m
ak
e
o
n
e
-
v
er
s
u
s
-
all
ab
s
o
l
u
te
s
ep
ar
atio
n
(
i.e
.
s
ep
ar
ate
o
n
e
ac
tiv
it
y
clas
s
f
r
o
m
t
h
e
r
e
m
ai
n
i
n
g
cla
s
s
e
s
)
.
Giv
en
a
p
r
e
-
p
r
o
ce
s
s
ed
d
atase
t
o
f
tr
ac
e
s
eq
u
en
ce
s
f
o
r
s
i
m
p
le
ac
ti
v
itie
s
(
i.e
.
r
ep
r
esen
ted
as
a
p
air
s
o
f
s
en
s
o
r
n
a
m
e
a
n
d
v
alu
e)
,
Al
g
o
r
ith
m
1
o
u
tp
u
ts
th
e
co
r
r
esp
o
n
d
in
g
SJ
E
P
s
.
A
l
g
o
r
i
t
h
m
1
.
M
i
n
i
n
g
o
f
S
t
ro
n
g
Ju
m
p
i
n
g
E
m
e
r
g
i
n
g
P
a
t
t
e
rn
s
In
p
ut
:
Pr
e
p
ro
c
e
s
s
e
d
d
a
t
a
s
e
t
o
f
o
b
s
e
rv
a
t
i
o
n
s
e
q
u
e
n
c
e
s
f
o
r
t
h
e
s
i
m
p
l
e
a
c
t
i
v
i
t
i
e
s
O
ut
p
ut
:
T
h
e
s
e
t
o
f
S
J
E
Ps
.
St
e
ps
:
1.
B
e
g
i
n
2.
F
o
r
e
a
c
h
a
c
t
i
v
i
t
y
c
l
a
s
s
,
=
1
,
…
,
3.
C
o
n
s
i
d
e
r
d
a
t
a
s
e
t
D
i
c
o
n
t
a
i
n
s
o
b
s
e
r
v
a
t
i
o
n
s
e
q
u
e
n
c
e
s
fr
o
m
c
l
a
ss
,
a
n
d
D
′
i
c
o
n
t
a
i
n
s
o
b
se
rv
a
t
i
o
n
s
e
q
u
e
n
c
e
s
fr
o
m
−
1
c
l
a
s
s
e
s
,
D
′
i
=
⋃
D
j
k
j
=
1
,
i
≠
j
4.
C
o
m
p
u
t
e
It
e
m
S
e
t
_
L
i
s
t
o
f
a
l
l
i
t
e
m
s
e
t
s
i
n
d
a
t
a
s
e
t
u
s
i
n
g
t
h
e
FP
-
g
r
o
w
t
h
a
l
g
o
r
i
t
h
m
[
1
5
]
5.
F
o
r
eac
h
c
a
n
d
i
d
a
t
e
i
t
e
m
s
e
t
i
n
It
e
mS
e
t
_
L
i
s
t
,
6.
C
o
m
p
u
t
e
(
,
D
i
)
7.
C
o
m
p
u
t
e
(
,
D
′
i
)
,
8.
C
o
m
p
u
t
e
(
,
,
D
′
i
)
9.
If
(
,
D
i
,
D
′
i
)
=
∞
10.
Ad
d
c
a
n
d
i
d
a
t
e
t
o
t
h
e
s
e
t
o
f
SJ
E
Ps
f
o
r
c
l
a
s
s
11.
E
n
d
I
f
12.
E
n
d
F
o
r
13.
E
n
d
F
o
r
14.
E
n
d
4
.
1
.
2
.
Co
m
pu
t
a
t
io
n o
f
co
rr
ela
t
i
o
n m
a
t
ri
x
T
h
e
o
th
er
f
ea
tu
r
e
co
m
p
u
ted
i
n
th
e
tr
ai
n
i
n
g
p
h
a
s
e
is
t
h
e
s
en
s
o
r
/activ
it
y
co
r
r
elatio
n
m
atr
i
x
.
F
o
r
ea
ch
s
en
s
o
r
s
f
r
o
m
t
h
e
s
et
o
f
s
en
s
o
r
s
=
{
1
,
2
,
…
}
u
s
ed
f
o
r
m
o
n
ito
r
in
g
ac
tiv
it
y
a
f
r
o
m
t
h
e
s
et
o
f
ac
ti
v
ities
=
{
1
,
2
,
…
}
,
w
e
co
m
p
u
te
a
co
r
r
elatio
n
m
a
tr
ix
th
at
m
ea
s
u
r
es
t
h
e
in
ter
d
ep
en
d
en
c
y
b
et
w
ee
n
ea
ch
s
en
s
o
r
an
d
ac
tiv
it
y
u
s
i
n
g
th
e
s
u
p
p
o
r
t
(
,
)
d
ef
in
ed
i
n
S
ec
tio
n
3
.
4
.
2
.
T
he
t
esting
ph
a
s
e
T
h
e
in
p
u
t
to
th
is
p
h
a
s
e
is
a
s
tr
ea
m
o
f
s
e
n
s
o
r
r
ea
d
in
g
s
f
o
r
th
e
p
er
f
o
r
m
ed
h
u
m
an
ac
t
iv
ities
to
b
e
r
ec
o
g
n
ized
.
I
n
o
r
d
er
to
id
en
tify
th
e
s
e
ac
tiv
i
ties
,
t
h
e
in
p
u
t
s
tr
ea
m
s
h
o
u
ld
b
e
s
eg
m
en
ted
b
ef
o
r
eh
an
d
.
R
eg
ar
d
in
g
tr
ac
e
s
eg
m
e
n
tatio
n
,
t
h
er
e
e
x
i
s
t
t
w
o
m
a
in
ap
p
r
o
ac
h
es,
f
ix
e
d
-
s
ize
s
e
g
m
e
n
ta
t
io
n
,
a
n
d
d
y
n
a
m
ic
s
e
g
m
e
n
tatio
n
.
I
n
th
i
s
p
ap
er
,
w
e
ar
e
in
ter
este
d
in
f
i
x
ed
-
s
ize
s
eg
m
e
n
tatio
n
t
h
at
u
s
es
a
f
ix
ed
-
len
g
t
h
s
lid
i
n
g
w
i
n
d
o
w
to
s
p
lit
t
h
e
g
iv
e
n
tr
ac
e
i
n
to
eq
u
al
-
s
ized
ti
m
e
s
e
g
m
e
n
ts
,
w
h
ic
h
ad
d
th
e
f
o
llo
w
i
n
g
ch
a
llen
g
e.
T
h
e
s
ize
u
s
ed
f
o
r
s
eg
m
e
n
tatio
n
is
co
n
s
id
er
ed
a
ch
alle
n
g
e,
b
ec
au
s
e
ac
ti
v
itie
s
o
cc
u
r
w
it
h
d
if
f
er
en
t
d
u
r
atio
n
s
.
As
a
r
es
u
lt,
ac
ti
v
it
y
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:
2
0
8
8
-
8708
A
mu
ltil
a
b
el
cla
s
s
ifica
tio
n
a
p
p
r
o
a
ch
fo
r
co
mp
lex
h
u
ma
n
a
ctivities u
s
in
g
a
co
mb
in
a
tio
n
o
f
.
.
.
(
N
eh
a
l A
.
S
a
kr)
2997
ca
n
b
e
d
is
tr
ib
u
ted
a
m
o
n
g
a
n
u
m
b
er
o
f
s
e
g
m
en
t
s
.
T
o
r
eso
lv
e
t
h
is
is
s
u
e,
w
h
ile
co
m
p
u
ti
n
g
s
co
r
e
at
s
p
ec
if
ic
s
eg
m
e
n
t,
w
e
ta
k
e
i
n
to
ac
co
u
n
t
t
h
e
s
co
r
e
i
n
p
r
ev
io
u
s
s
e
g
m
en
t
w
it
h
p
ar
a
m
eter
α
th
at
i
s
th
e
_
r
ef
er
(
2
)
.
Fo
r
th
e
task
o
f
ac
ti
v
it
y
r
ec
o
g
n
itio
n
,
w
it
h
i
n
a
s
p
ec
if
ic
test
s
eg
m
e
n
t
th
e
e
x
is
ti
n
g
ac
tiv
itie
s
ex
ec
u
ted
s
eq
u
en
tiall
y
o
r
in
p
ar
allel
m
a
y
b
e
f
u
ll
y
co
n
tai
n
ed
o
r
p
ar
tiall
y
co
n
tain
ed
.
Fro
m
t
h
is
p
er
s
p
ec
tiv
e,
w
e
m
a
k
e
u
s
e
o
f
f
u
zz
y
s
et
t
h
eo
r
y
; t
h
at
i
s
an
ac
tiv
it
y
e
x
is
t
s
w
it
h
a
s
p
ec
i
f
ic
d
eg
r
ee
o
f
m
e
m
b
er
s
h
ip
v
al
u
e.
Usi
n
g
a
co
m
b
i
n
atio
n
o
f
th
e
SJ
E
P
s
ex
tr
ac
ted
in
t
h
e
t
r
ain
in
g
p
h
a
s
e
a
n
d
th
e
f
u
zz
y
s
e
t
th
eo
r
y
,
w
e
p
r
o
p
o
s
e
a
SJ
E
P
-
b
ased
alg
o
r
ith
m
f
o
r
th
e
r
ec
o
g
n
itio
n
o
f
s
i
m
p
le
an
d
co
m
p
lex
h
u
m
a
n
ac
ti
v
it
ies
th
at
co
n
s
is
t
o
f
th
r
ee
m
ai
n
p
h
as
es
as
p
r
esen
ted
i
n
A
l
g
o
r
ith
m
2
.
First,
w
e
co
m
p
u
te
th
e
m
a
tch
i
n
g
-
s
co
r
e
th
at
id
en
tif
ie
s
th
e
ca
n
d
id
ate
ac
t
iv
itie
s
ex
i
s
ti
n
g
i
n
th
e
c
u
r
r
en
t
s
eg
m
e
n
t
r
ef
er
(
1
)
.
T
h
en
,
w
e
co
m
p
u
te
t
h
e
li
k
eli
h
o
o
d
s
co
r
e
(
l
ike_
s
co
r
e
)
f
o
r
ea
ch
ca
n
d
id
ate
ac
t
iv
i
t
y
u
s
i
n
g
a
s
co
r
i
n
g
f
u
n
ctio
n
r
ef
er
(
3
)
.
Fin
all
y
,
u
s
in
g
t
h
e
co
m
p
u
ted
l
ik
eli
h
o
o
d
s
an
d
a
p
r
ed
ef
in
ed
t
h
r
es
h
o
ld
,
w
e
m
ak
e
a
d
ec
is
io
n
o
n
t
h
e
w
i
n
n
i
n
g
ac
ti
v
itie
s
f
r
o
m
t
h
ese
ca
n
d
id
ates u
s
i
n
g
t
h
e
f
o
llo
w
in
g
r
u
l
e.
“
I
f
_
(
,
)
≥
×
(
_
)
T
h
en
o
u
tp
u
t
”,
w
h
er
e
r
ef
er
s
to
th
e
ca
n
d
id
ate
ac
tiv
it
y
,
cu
r
r
en
t tr
ac
e
s
eg
m
e
n
t
,
an
d
a
u
s
er
-
d
e
f
in
ed
t
h
r
es
h
o
ld
u
s
ed
f
o
r
tu
n
i
n
g
th
e
t
h
r
es
h
o
ld
.
A
l
g
o
r
i
t
h
m
2
.
T
h
e
Pr
o
p
o
s
e
d
R
e
c
o
g
n
i
t
i
o
n
A
l
g
o
r
i
t
h
m
.
In
p
ut
:
A
s
e
t
o
f
p
r
e
p
r
o
c
e
s
s
e
d
t
r
a
c
e
s
e
g
m
e
n
t
s
:
S
=
{
s
1
,
s
2
,
…
.
.
s
t
}
,
T
h
e
e
x
t
r
a
c
t
e
d
SJ
E
P
s,
c
o
r
r
e
l
a
t
i
o
n
m
a
t
r
i
x
O
ut
p
ut
:
W
i
n
n
i
n
g
A
c
t
i
v
i
t
y
l
a
b
e
l
(
s)
fo
r
e
a
c
h
s
e
g
m
e
n
t
:
St
e
ps
1.
Be
g
i
n
2.
F
o
r
e
a
c
h
se
g
m
e
n
t
∈
p
r
e
p
ro
c
e
ss
e
d
a
s
a
s
e
q
u
e
n
c
e
o
f
i
t
e
m
s
=
<
1
,
2
,
…
.
,
>
3.
F
o
r
e
a
c
h
SJ
E
P
i
n
t
h
e
s
e
t
s
S
J
E
P
s
4.
C
o
m
p
u
t
e
ℎ
_
(
,
)
5.
If
ℎ
_
>
0
6.
L
a
b
e
l
=
g
e
t
A
c
t
i
v
i
t
y
L
a
b
e
l
(
S
J
E
P
)
7.
Ad
d
L
a
b
e
l
t
o
8.
E
n
d
I
f
9.
E
n
d
F
o
r
10.
F
o
r
e
a
c
h
c
a
n
d
i
d
a
t
e
a
c
t
i
v
i
t
y
i
n
w
i
t
h
c
a
rd
i
n
a
l
i
t
y
11.
F
o
r
e
a
c
h
i
t
e
m
e
i
n
t
h
e
c
u
rr
e
n
t
s
e
g
m
e
n
t
w
i
t
h
c
a
rd
i
n
a
l
i
t
y
l
12.
C
o
m
p
u
t
e
_
ℎ
(
,
)
13.
E
n
d
F
o
r
14.
C
o
m
p
u
t
e
_
(
,
)
,
a
n
d
c
_
(
,
)
15.
E
n
d
F
o
r
16.
_
=
(
_
)
17.
F
o
r
e
a
c
h
a
c
t
i
v
i
t
y
i
n
18.
If
_
(
,
)
≥
×
_
19.
Ad
d
t
o
(
)
20.
E
n
d
I
f
21.
E
n
d
F
o
r
22.
E
n
d
F
o
r
23.
E
n
d
Def
ini
t
io
n
4
.
1
:
T
h
e
m
atc
h
i
n
g
s
co
r
e
(
m
atc
h
_
s
co
r
e)
o
f
th
e
s
et
1
of
SJ
E
P
s
w
it
h
th
e
s
et
2
o
f
s
en
s
o
r
ev
en
t
s
w
i
t
h
in
a
s
p
ec
if
ic
te
s
t is d
ef
in
ed
as
f
o
llo
w
s
ℎ
_
(
1
,
2
)
=
{
0
1
∩
2
=
∅
1
1
∩
2
=
2
|
1
∩
2
|
|
2
|
ℎ
(
1
)
_
(
,
)
=
×
_
(
,
−
1
)
+
(
1
−
)
×
_
(
,
)
(
2
)
_
(
,
)
=
∑
_
ℎ
(
,
)
=
1
(
3
)
_
ℎ
(
,
)
=
(
,
)
∑
(
,
)
=
1
,
∑
_
ℎ
(
,
)
=
1
=
1
(
4
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
4
,
A
u
g
u
s
t 2
0
1
9
:
2
9
9
3
-
300
1
2998
5.
E
XP
E
R
I
M
E
NT
A
L
RE
SUL
T
S AN
D
E
VA
L
UA
T
I
O
N
I
n
th
is
s
ec
tio
n
,
w
e
p
r
ese
n
t
t
h
e
ex
p
er
i
m
e
n
tal
e
v
al
u
atio
n
o
f
t
h
e
p
r
o
p
o
s
ed
a
p
p
r
o
ac
h
.
First,
w
e
in
tr
o
d
u
ce
th
e
d
atasets
u
s
ed
,
f
o
llo
w
ed
w
i
th
o
u
r
s
etti
n
g
s
f
o
r
th
e
ev
a
lu
at
i
o
n
,
an
d
th
en
w
e
p
r
esen
t
a
n
d
d
is
cu
s
s
o
u
r
o
b
tain
ed
r
esu
lt
s
.
R
eg
ar
d
in
g
th
e
d
ataset
s
u
s
ed
,
w
e
ev
a
lu
ate
o
u
r
ap
p
r
o
ac
h
u
s
i
n
g
t
w
o
d
ataset
s
w
i
th
d
if
f
er
en
t
m
o
n
ito
r
in
g
ap
p
r
o
ac
h
es;
C
A
S
AS
b
en
c
h
m
ar
k
in
g
d
ataset
[
1
6
]
,
an
d
d
ataset
o
f
s
i
m
p
le,
i
n
ter
lea
v
ed
an
d
co
m
p
le
x
ac
ti
v
itie
s
r
ef
er
ee
d
as
SIC
A
f
r
o
m
[
1
1
]
.
C
A
S
AS
d
atase
t
w
a
s
co
llected
f
r
o
m
a
s
m
ar
t
h
o
m
e
eq
u
ip
p
ed
w
it
h
d
if
f
er
en
t
t
y
p
es
o
f
en
v
ir
o
n
m
e
n
tal
s
en
s
o
r
s
(
e.
g
.
m
o
tio
n
,
d
o
o
r
,
te
m
p
er
atu
r
e)
,
i
n
w
h
ic
h
2
0
p
ar
ticip
an
ts
co
llec
ted
a
s
et
o
f
s
i
m
p
le
an
d
co
m
p
lex
o
b
s
er
v
at
io
n
s
eq
u
en
ce
s
f
o
r
ei
g
h
t
d
i
f
f
er
en
t
ADL
ac
ti
v
itie
s
p
r
esen
ted
i
n
T
ab
le
1
.
On
th
e
o
th
er
h
an
d
,
SI
C
A
co
n
ta
in
s
o
b
s
er
v
atio
n
s
eq
u
en
ce
s
o
f
s
i
m
p
le
a
n
d
co
m
p
lex
ex
ec
u
tio
n
o
f
2
6
d
if
f
er
e
n
t
ac
ti
v
it
ies
co
llected
b
y
f
o
u
r
v
o
l
u
n
teer
s
u
s
in
g
t
w
o
s
et
s
o
f
w
ea
r
ab
le
s
en
s
o
r
s
as lis
ted
in
T
ab
le
2
.
T
ab
le
1
.
A
ctiv
it
ies C
o
llected
i
n
C
AS
A
S d
ataset
[
1
6
]
N
o
.
A
c
t
i
v
i
t
y
1
T
a
k
e
M
e
d
i
c
i
n
e
2
W
a
t
c
h
D
V
D
3
W
a
t
e
r
P
l
a
n
t
s
4
A
n
s
w
e
r
p
h
o
n
e
5
W
r
i
t
e
B
i
r
t
h
d
a
y
C
a
r
d
6
P
r
e
p
a
r
e
M
e
a
l
7
C
l
e
a
n
8
S
e
l
e
c
t
a
n
o
u
t
f
i
t
T
ab
le
2
.
A
ctiv
it
ies co
llected
i
n
SIC
A
d
atase
t
[
1
1
]
N
o
.
A
c
t
i
v
i
t
y
N
o
.
A
c
t
i
v
i
t
y
N
o
.
A
c
t
i
v
i
t
y
1
mak
i
n
g
c
o
f
f
e
e
10
b
r
u
s
h
i
n
g
t
e
e
t
h
19
V
a
c
u
u
m
i
n
g
2
mak
i
n
g
t
e
a
11
w
a
sh
i
n
g
h
a
n
d
s
20
t
a
k
i
n
g
o
u
t
t
r
a
sh
3
mak
i
n
g
o
a
t
me
a
l
12
w
a
sh
i
n
g
f
a
c
e
21
u
si
n
g
p
h
o
n
e
4
f
r
y
i
n
g
e
g
g
s
13
w
a
sh
i
n
g
c
l
o
t
h
e
s
22
w
a
t
c
h
i
n
g
T
V
5
mak
i
n
g
a
d
r
i
n
k
14
i
r
o
n
i
n
g
23
w
a
t
c
h
i
n
g
D
V
D
6
a
p
p
l
y
i
n
g
mak
e
u
p
15
e
a
t
i
n
g
me
a
l
24
u
si
n
g
c
o
m
p
u
t
e
r
7
b
r
u
s
h
i
n
g
h
a
i
r
16
D
r
i
n
k
i
n
g
25
r
e
a
d
i
n
g
b
o
o
k
8
S
h
a
v
i
n
g
17
t
a
k
i
n
g
me
d
i
c
a
t
i
o
n
26
l
i
st
e
n
i
n
g
mu
si
c
9
T
o
i
l
e
t
i
n
g
18
c
l
e
a
n
i
n
g
a
d
i
n
i
n
g
t
a
b
l
e
T
o
ev
alu
ate
o
u
r
w
o
r
k
,
w
e
u
s
e
3
-
f
o
ld
cr
o
s
s
v
alid
atio
n
w
it
h
C
AS
A
S
an
d
1
0
-
f
o
ld
cr
o
s
s
v
alid
atio
n
w
it
h
SIC
A
d
ataset,
b
esid
es t
h
e
th
r
e
e
s
tan
d
ar
d
ev
alu
a
tio
n
m
etr
ics:
P
r
ec
is
io
n
,
R
ec
all,
an
d
F
-
Me
as
u
r
e.
=
(5
)
=
(6
)
−
=
2
.
.
+
(7
)
Usi
n
g
th
e
t
w
o
d
if
f
er
en
t
d
at
asets
,
an
d
f
i
x
ed
-
t
i
m
e
s
e
g
m
e
n
tatio
n
ap
p
r
o
ac
h
w
it
h
d
if
f
er
en
t
s
lid
i
n
g
w
i
n
d
o
w
s
m
o
v
in
g
ar
o
u
n
d
th
e
av
er
ag
e
w
i
n
d
o
w
le
n
g
th
(
)
,
w
e
p
er
f
o
r
m
t
w
o
ex
p
er
i
m
e
n
ts
.
I
n
ea
c
h
ex
p
er
i
m
e
n
t,
f
ir
s
t
w
e
co
m
p
ar
e
th
e
p
er
f
o
r
m
a
n
ce
o
f
o
u
r
ap
p
r
o
ac
h
f
o
r
s
i
m
p
le
ac
ti
v
it
y
r
ec
o
g
n
i
tio
n
w
i
th
t
h
r
ee
p
o
p
u
lar
class
if
ier
s
,
Su
p
p
o
r
t
v
ec
to
r
Ma
ch
in
e
(
SVM)
,
H
id
d
en
Ma
r
k
o
v
Mo
d
el
(
HM
M)
,
an
d
K
-
Nea
r
est
Neig
h
b
o
r
(
K
-
NN)
as
s
h
o
w
n
in
Fig
u
r
e
3
.
Fo
r
th
e
r
ec
o
g
n
itio
n
o
f
co
m
p
lex
ac
ti
v
itie
s
,
w
e
co
m
p
u
te
th
e
p
r
ec
is
io
n
,
R
ec
all,
a
n
d
F
-
m
ea
s
u
r
e
f
o
r
o
u
r
ap
p
r
o
ac
h
an
d
co
m
p
ar
e
it
ag
ain
s
t
m
et
h
o
d
s
i
n
[
6
]
an
d
[
1
1
]
as
d
ep
icted
in
Fig
u
r
e
4
a
n
d
Fi
g
u
r
e
5
r
esp
e
ctiv
el
y
,
w
h
er
e
t
h
e
X
-
a
x
is
r
ef
er
s
to
t
h
e
w
i
n
d
o
w
s
ize
an
d
t
h
e
Y
-
a
x
is
r
ef
er
s
to
th
e
e
v
alu
a
tio
n
m
etr
ic.
R
e
g
ar
d
in
g
t
h
e
p
ar
a
m
e
ter
s
α
,
,
w
e
r
ea
c
h
t
h
e
b
est
r
es
u
ts
w
it
h
,
α
=
0
.
3
,
λ
=
0
.
1
in
C
A
S
AS d
ataset,
an
d
=
0
.
3
,
=
0
.
8
in
SI
C
A
d
ataset.
Fro
m
th
e
r
es
u
lts
s
h
o
w
n
in
F
i
g
u
r
e
3
,
th
er
e
is
a
clo
s
e
co
m
p
etitio
n
b
et
w
ee
n
o
u
r
ap
p
r
o
ac
h
,
SVM
an
d
K
-
NN
ex
ce
p
t
HM
M
w
it
h
t
h
e
lo
w
e
s
t
v
al
u
e.
Ho
w
e
v
er
,
o
u
r
ap
p
r
o
ac
h
ac
h
ie
v
es
t
h
e
h
ig
h
e
s
t
p
er
f
o
r
m
a
n
ce
f
o
r
th
e
r
ec
o
g
n
itio
n
o
f
s
i
m
p
le
ac
ti
v
itie
s
i
n
b
o
th
d
atasets
.
R
e
g
ar
d
in
g
P
r
ec
is
io
n
,
R
ec
all,
a
n
d
F
-
Me
asu
r
e
f
o
r
co
m
p
le
x
ac
tiv
iti
e
s
,
t
h
e
r
es
u
lt
s
s
h
o
w
n
i
n
Fi
g
u
r
e
4
an
d
Fi
g
u
r
e
5
i
n
d
i
ca
te
th
e
s
u
p
er
io
r
it
y
o
f
o
u
r
ap
p
r
o
ac
h
ag
ai
n
s
t
th
e
o
th
er
s
i
n
[6
,
11]
at
lar
g
e
w
i
n
d
o
w
s
co
n
tain
in
g
m
u
ltip
le
o
v
er
lap
p
in
g
ac
ti
v
itie
s
.
I
n
Fi
g
u
r
e
4
,
u
s
i
n
g
C
A
S
AS
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:
2
0
8
8
-
8708
A
mu
ltil
a
b
el
cla
s
s
ifica
tio
n
a
p
p
r
o
a
ch
fo
r
co
mp
lex
h
u
ma
n
a
ctivities u
s
in
g
a
co
mb
in
a
tio
n
o
f
.
.
.
(
N
eh
a
l A
.
S
a
kr)
2999
d
ataset,
o
u
r
ap
p
r
o
ac
h
ac
h
iev
e
s
th
e
h
i
g
h
e
s
t
F
-
m
ea
s
u
r
e
r
ate
at
w
i
n
d
o
w
s
ize
1
.
5
×
L
av
g
w
h
ic
h
is
9
2
.
3
%
,
w
h
il
e
th
e
o
t
h
er
i
n
[
6
]
r
ea
ch
e
s
8
1
.
1
%
.
T
h
e
s
a
m
e
i
n
SIC
A
d
ataset,
w
e
r
ea
ch
9
2
%
f
o
r
F
-
Me
a
s
u
r
e,
th
at
is
al
m
o
s
t
1
0
%
m
o
r
e
t
h
a
n
th
e
o
t
h
er
in
[
1
1
]
.
(
a)
(
b
)
Fig
u
r
e
3
.
T
h
e
co
m
p
ar
is
o
n
R
e
s
u
lts
f
o
r
S
i
m
p
le
A
c
tiv
it
y
R
ec
o
g
n
i
tio
n
,
(
a)
C
AS
A
S Da
ta
s
et
,
(
b
)
SICA
Da
taset
(
a)
(
b
)
(
c)
Fig
u
r
e
4
.
C
o
m
p
ar
is
o
n
r
es
u
lt
s
o
f
o
u
r
SJ
E
P
-
b
ased
a
p
p
r
o
ac
h
an
d
[
6
]
u
s
in
g
C
AS
A
S d
ataset
(
a)
(
b
)
(
c)
Fig
u
r
e
5
.
C
o
m
p
ar
i
s
io
n
r
es
u
lt
s
o
f
o
u
r
SJ
E
P
-
b
ased
a
p
p
r
o
ac
h
an
d
[
1
1
]
u
s
in
g
SIC
A
d
ataset
50
55
60
65
70
75
80
85
90
95
100
96.6
96.15
93.16
72.07
A
ccur
acy
(%
)
Techni
que
s
S
JE
P
-
bas
e
d
S
V
M
K
-
NN
H
M
M
50
55
60
65
70
75
80
85
90
95
100
9
3
.2
4
91.34
90.05
70.08
A
ccur
acy
(%
)
Techni
que
s
S
JE
P
-
bas
e
d
S
V
M
K
-
NN
H
M
M
50
55
60
65
70
75
80
85
90
95
100
0.1
0.5
1
1.5
2
2.5
3
3.5
P
r
e
ci
s
i
on
(%
)
wi
ndow
s
i
z
e
(L
avg
)
M
al
az
i
[
6]
S
J
E
P
-
base
d
50
55
60
65
70
75
80
85
90
95
100
0.1
0.5
1
1.5
2
2.5
3
3
.5
R
e
cal
l
(%)
wi
ndow
s
i
z
e
(L
avg
)
M
al
az
i
[
6]
S
J
E
P
-
base
d
50
55
60
65
70
75
80
85
90
95
100
0.1
0.5
1
1.5
2
2.5
3
3.5
F
-
M
e
asur
e
(%
)
wi
ndow
s
i
z
e
(L
avg
)
M
al
az
i
[
6]
S
J
E
P
-
base
d
50
55
60
65
70
75
80
85
90
95
100
0.1
0.5
1
1.5
2
2.5
3
3
.5
P
r
e
ci
s
i
on
(%
)
wi
ndow
s
i
z
e
(L
avg
)
Lu
[
1
1]
S
J
E
P
-
ba
se
d
50
55
60
65
70
75
80
85
90
95
100
0.1
0.5
1
1.5
2
2.5
3
3.5
R
e
cal
l
(%)
wi
ndow
s
i
z
e
(L
avg
)
Lu
[
1
1]
S
J
E
P
-
ba
se
d
50
55
60
65
70
75
80
85
90
95
100
0.1
0.5
1
1.5
2
2.5
3
3.5
F
-
M
e
asur
e
(%
)
wi
ndow
s
i
z
e
(L
avg
)
Lu
[
1
1]
S
J
E
P
-
ba
se
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
4
,
A
u
g
u
s
t 2
0
1
9
:
2
9
9
3
-
300
1
3000
6.
CO
NCLU
SI
O
N
Th
e
m
ai
n
o
b
j
ec
tiv
e
o
f
th
is
p
ap
er
is
to
d
esig
n
a
u
n
i
f
ied
f
r
a
m
e
w
o
r
k
t
h
at
r
ec
o
g
n
ize
b
o
th
s
i
m
p
le
an
d
co
m
p
le
x
ac
ti
v
it
ies
e
f
f
icie
n
tl
y
an
d
o
v
er
co
m
e
t
h
e
f
o
llo
w
i
n
g
c
h
alle
n
g
e
s
:
t
h
e
r
eq
u
ir
e
m
e
n
t
o
f
a
tr
ain
i
n
g
d
ataset
o
f
co
m
p
le
x
ac
ti
v
itie
s
an
d
th
e
ab
i
lit
y
to
r
ec
o
g
n
ize
a
m
a
x
i
m
u
m
o
f
t
w
o
o
v
er
lap
p
in
g
ac
ti
v
itie
s
.
T
h
is
w
a
s
ac
h
ie
v
ed
u
s
i
n
g
a
co
m
b
i
n
atio
n
o
f
d
is
cr
i
m
i
n
ati
v
e
f
ea
tu
r
e
s
ca
lled
Stro
n
g
J
u
m
p
i
n
g
E
m
er
g
in
g
P
atter
n
s
a
n
d
F
u
zz
y
s
ets.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
co
n
s
is
t
s
o
f
t
w
o
m
a
in
p
h
ases
tr
ain
i
n
g
a
n
d
test
i
n
g
.
I
n
t
h
e
tr
ai
n
i
n
g
p
h
as
e,
w
e
e
x
tr
ac
t
SJ
E
P
s
th
e
r
ep
r
esen
t
ea
c
h
ac
ti
v
it
y
cl
ass
b
esid
es
a
n
o
th
er
d
is
cr
i
m
i
n
atin
g
f
ea
tu
r
e.
W
h
i
le
in
t
h
e
te
s
tin
g
p
h
a
s
e,
w
e
u
s
e
th
e
e
x
tr
ac
ted
SJ
E
P
s
an
d
f
ea
tu
r
e
as
i
n
p
u
t
s
to
a
s
co
r
i
n
g
f
u
n
c
ti
o
n
th
at
o
u
tp
u
ts
t
h
e
ac
t
iv
i
t
y
lab
els
f
o
r
th
e
e
x
is
t
in
g
ac
tiv
itie
s
.
Usi
n
g
t
w
o
d
atase
ts
w
i
th
d
if
f
er
e
n
t
m
o
n
ito
r
i
n
g
ap
p
r
o
ac
h
es
a
n
d
s
ize
f
o
r
th
e
ev
alu
a
tio
n
,
th
e
e
x
p
er
i
m
e
n
tal
r
e
s
u
l
ts
i
n
d
i
ca
te
th
e
ef
f
icie
n
c
y
a
n
d
s
u
p
er
io
r
it
y
o
f
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
a
g
ain
s
t
o
t
h
er
s
.
Ou
r
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
ass
u
m
ed
th
at
all
ac
ti
v
itie
s
ar
e
lin
ea
r
l
y
s
ep
ar
ated
an
d
it
is
d
esig
n
ed
f
o
r
s
in
g
le
r
esid
en
ts
.
T
h
er
ef
o
r
e,
in
th
e
f
u
tu
r
e,
o
u
r
p
lan
s
ar
e
to
ex
te
n
d
th
e
p
r
o
p
o
s
ed
m
o
d
el
to
d
ea
l
w
it
h
n
o
n
li
n
ea
r
s
ep
ar
ated
ac
tiv
ities
a
n
d
m
u
lti
-
r
esid
en
ts
.
RE
F
E
R
E
NC
E
S
[1
]
S
.
Zh
a
n
g
,
e
t
a
l
.
,
“
A
Re
v
ie
w
o
n
Hu
m
a
n
A
c
ti
v
it
y
Re
c
o
g
n
it
io
n
Us
in
g
V
is
io
n
-
Ba
se
d
M
e
th
o
d
,
”
J
o
u
r
n
a
l
o
f
He
a
l
th
c
a
re
En
g
i
n
e
e
rin
g
,
v
o
l.
2
0
1
7
,
2
0
1
7
.
[2
]
L
.
Ch
e
n
,
e
t
a
l
.
,
“
S
e
n
so
r
-
b
a
se
d
a
c
ti
v
it
y
re
c
o
g
n
it
io
n
,
”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
S
y
ste
ms
,
M
a
n
a
n
d
Cy
b
e
rn
e
ti
c
s
Pa
rt
C:
Ap
p
li
c
a
ti
o
n
s
a
n
d
Rev
iews
,
v
o
l
/i
ss
u
e
:
42
(
6
)
,
p
p
.
7
9
0
-
8
0
8
,
2
0
1
2
.
[3
]
S
.
Ra
n
a
sin
g
h
e
,
e
t
a
l
.
,
“
A
R
e
v
ie
w
o
n
A
p
p
li
c
a
ti
o
n
s o
f
A
c
ti
v
it
y
R
e
c
o
g
n
it
io
n
S
y
ste
m
s
w
it
h
Re
g
a
rd
to
P
e
rf
o
r
m
a
n
c
e
a
n
d
Ev
a
lu
a
ti
o
n
,
”
I
n
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Distri
b
u
te
d
S
e
n
so
r Ne
two
rk
s
,
v
o
l
/i
ss
u
e
:
12
(
8
)
,
p
p
.
1
-
2
1
,
2
0
1
6
.
[4
]
G
.
O
k
e
y
o
,
e
t
a
l
.
,
“
A
Kn
o
w
led
g
e
-
Driv
e
n
A
p
p
ro
a
c
h
to
C
o
m
p
o
site
Ac
ti
v
it
y
Re
c
o
g
n
it
io
n
i
n
S
m
a
rt
En
v
iro
n
m
e
n
ts
,
”
Ub
iq
u
it
o
u
s Co
m
p
u
ti
n
g
a
n
d
Amb
i
e
n
t
In
telli
g
e
n
c
e
6
th
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
,
UCAmI 2
0
1
2
,
p
p
.
3
2
2
-
3
2
9
,
2
0
1
2
.
[5
]
F
.
He
rre
ra
,
e
t
a
l
.
,
“
M
u
lt
il
a
b
e
l
Clas
sif
ic
a
ti
o
n
,”
S
p
rin
g
e
r In
ter
n
a
ti
o
n
a
l
P
u
b
li
s
h
in
g
S
wit
ze
rla
n
d
,
p
p
.
1
7
-
3
2
,
2
0
1
6
.
[6
]
H.
T
.
M
a
la
z
i
a
n
d
M
.
Da
v
a
ri,
“
Co
m
b
in
in
g
e
m
e
r
g
in
g
p
a
tt
e
rn
s
w
it
h
r
a
n
d
o
m
f
o
re
st
f
o
r
c
o
m
p
lex
a
c
ti
v
it
y
re
c
o
g
n
it
io
n
i
n
s
m
a
rt
h
o
m
e
s
,
”
Ap
p
li
e
d
In
telli
g
e
n
c
e
,
v
o
l
/i
ss
u
e
:
48
(
2
)
,
p
p
.
3
1
5
-
3
3
0
,
2
0
1
8
.
[7
]
T
.
W
u
,
e
t
a
l
.
,
“
Jo
in
t
re
c
o
g
n
it
i
o
n
o
f
m
u
lt
ip
le
c
o
n
c
u
rre
n
t
a
c
ti
v
it
ies
u
sin
g
f
a
c
t
o
rial
c
o
n
d
it
i
o
n
a
l
r
a
n
d
o
m
f
ield
s
,
”
Pro
c
2
2
n
d
Co
n
f
o
n
Art
if
icia
l
In
tel
li
g
e
n
c
e
(
AA
AI
-
2
0
0
7
)
,
p
p
.
8
2
-
8
7
,
2
0
0
7
.
[8
]
D.
H.
Hu
a
n
d
Q.
Ya
n
g
,
“
CIGA
R
:
Co
n
c
u
rre
n
t
a
n
d
In
terle
a
v
in
g
G
o
a
l
a
n
d
A
c
ti
v
it
y
Re
c
o
g
n
it
io
n
,
”
AA
AI
Co
n
fer
e
n
c
e
o
n
Art
if
icia
l
In
tell
ig
e
n
c
e
,
p
p
.
1
3
6
3
-
1
3
6
8
,
2
0
0
8
.
[9
]
J.
M
o
d
a
y
il
,
e
t
a
l
.
,
“
I
m
p
ro
v
in
g
t
h
e
re
c
o
g
n
it
io
n
o
f
in
terle
a
v
e
d
a
c
ti
v
it
ies
,
”
Pro
c
e
e
d
in
g
s
o
f
th
e
1
0
t
h
in
ter
n
a
ti
o
n
a
l
c
o
n
fer
e
n
c
e
o
n
U
b
iq
u
it
o
u
s c
o
mp
u
t
in
g
-
Ub
iC
o
mp
’
0
8
,
p
p
.
4
0
,
2
0
0
8
.
[1
0
]
Y.
Zh
a
n
g
,
e
t
a
l
.
,
“
M
o
d
e
li
n
g
tem
p
o
ra
l
i
n
tera
c
ti
o
n
s
w
it
h
in
terv
a
l
te
m
p
o
ra
l
b
a
y
e
si
a
n
n
e
tw
o
rk
s
f
o
r
c
o
m
p
lex
a
c
ti
v
it
y
re
c
o
g
n
it
io
n
,
”
IEE
E
T
ra
n
s
a
c
ti
o
n
s
o
n
Pa
tt
e
rn
An
a
lys
is
a
n
d
M
a
c
h
in
e
In
telli
g
e
n
c
e
,
v
o
l
/i
ss
u
e
:
35
(
10
)
,
p
p
.
2
4
6
8
-
2
4
8
3
,
2
0
1
3
.
[1
1
]
T
.
G
u
,
e
t
a
l
.
,
“
A
p
a
tt
e
rn
m
in
in
g
a
p
p
ro
a
c
h
to
se
n
so
r
-
b
a
se
d
h
u
m
a
n
a
c
ti
v
it
y
re
c
o
g
n
it
io
n
,
”
IEE
E
T
r
a
n
sa
c
ti
o
n
s
o
n
Kn
o
wled
g
e
a
n
d
D
a
ta
En
g
i
n
e
e
rin
g
,
v
o
l
/i
ss
u
e
:
23
(
9
)
,
p
p
.
1
3
5
9
-
1
3
7
2
,
2
0
1
1
.
[1
2
]
L
.
L
iu
,
e
t
a
l
.
,
“
Co
m
p
lex
a
c
ti
v
it
y
re
c
o
g
n
it
io
n
u
si
n
g
ti
m
e
se
rie
s
p
a
tt
e
rn
d
icti
o
n
a
ry
lea
rn
e
d
f
ro
m
u
b
iq
u
it
o
u
s
se
n
so
rs
,
”
In
fo
rm
a
t
io
n
S
c
ien
c
e
s
,
p
p
.
1
-
1
7
,
2
0
1
6
.
[1
3
]
A
.
M
.
G
.
V
ico
,
e
t
a
l
.
,
“
A
n
o
v
e
rv
ie
w
o
f
e
m
e
rg
in
g
p
a
tt
e
rn
m
i
n
in
g
i
n
su
p
e
rv
ise
d
d
e
sc
rip
ti
v
e
ru
le
d
isc
o
v
e
ry
:
tax
o
n
o
m
y
,
e
m
p
iri
c
a
l
stu
d
y
,
tren
d
s,
a
n
d
p
ro
sp
e
c
ts
,
”
W
il
e
y
In
ter
d
is
c
ip
li
n
a
ry
Rev
iews
:
Da
ta
M
in
in
g
a
n
d
Kn
o
wled
g
e
Disc
o
v
e
ry
,
v
o
l
/i
ss
u
e
:
8
(
1
)
,
p
p
.
1
-
2
2
,
2
0
1
8
.
[1
4
]
C.
O.
J.
G
.
Bo
rro
to
M
.
a
n
d
M
a
rtí
n
e
z
T
.
J.,
“
A
su
rv
e
y
o
f
e
m
e
r
g
in
g
p
a
tt
e
rn
s
f
o
r
su
p
e
rv
ise
d
c
las
sif
ic
a
t
io
n
,
”
Arti
fi
c
ia
l
In
telli
g
e
n
c
e
Rev
iew
,
v
o
l
/i
ss
u
e
:
42
(
4
)
,
p
p
.
7
0
5
-
7
2
1
,
2
0
1
4
.
[1
5
]
R.
K.
,
e
t
a
l
.,
“
A
n
F
P
-
G
ro
w
th
A
p
p
ro
a
c
h
to
M
in
i
n
g
A
ss
o
c
iatio
n
Ru
les
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
Co
mp
u
ter
S
c
ien
c
e
a
n
d
M
o
b
i
le Co
mp
u
ti
n
g
,
v
o
l
/i
ss
u
e
:
2
(
2
)
,
p
p
.
1
-
5
,
2
0
1
3
.
[1
6
]
G
.
S
in
g
la,
e
t
a
l
.
,
“
T
ra
c
k
in
g
A
c
ti
v
it
ies
in
C
o
m
p
lex
S
e
tt
in
g
s
Us
in
g
S
m
a
rt
En
v
iro
n
m
e
n
t
T
e
c
h
n
o
lo
g
ies
,”
In
ter
n
a
ti
o
n
a
l
jo
u
rn
a
l
o
f
b
io
sc
ien
c
e
s,
p
sy
c
h
ia
try
,
a
n
d
tec
h
n
o
l
o
g
y
(
IJ
B
S
PT
)
,
v
o
l
/i
s
su
e
:
1
(
1
)
,
p
p
.
2
5
-
3
5
,
2
0
0
9
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
N
e
h
a
l
A.
S
a
k
r
re
c
e
iv
e
d
h
e
r
B
.
S
c
.
in
C
o
m
p
u
ter
S
c
ien
c
e
s
f
ro
m
F
a
c
u
lt
y
o
f
Co
m
p
u
ter
a
n
d
In
f
o
rm
a
ti
o
n
S
c
ien
c
e
s,
M
a
n
s
o
u
ra
Un
iv
e
rsit
y
o
f
Eg
y
p
t
in
2
0
0
7
.
S
h
e
re
c
e
iv
e
d
h
e
r
M
.
S
c
.
d
e
g
re
e
in
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
f
ro
m
F
a
c
u
lt
y
o
f
Co
m
p
u
ter
a
n
d
In
f
o
rm
a
ti
o
n
S
c
ien
c
e
s,
M
a
n
so
u
r
a
Un
iv
e
rsit
y
o
f
E
g
y
p
t
in
2
0
1
3
.
S
h
e
is cu
rre
n
tl
y
a
P
h
D stu
d
e
n
t
a
n
d
tea
c
h
in
g
a
ss
istan
t
in
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
D
e
p
a
rt
m
e
n
t
a
t
F
a
c
u
lt
y
o
f
Co
m
p
u
ter
a
n
d
In
f
o
r
m
a
ti
o
n
S
c
ien
c
e
s,
M
a
n
s
o
u
ra
Un
iv
e
r
sit
y
.
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:
2
0
8
8
-
8708
A
mu
ltil
a
b
el
cla
s
s
ifica
tio
n
a
p
p
r
o
a
ch
fo
r
co
mp
lex
h
u
ma
n
a
ctivities u
s
in
g
a
co
mb
in
a
tio
n
o
f
.
.
.
(
N
eh
a
l A
.
S
a
kr)
3001
M
e
r
v
a
t
Abu
-
ElK
h
e
ir
r
e
c
e
iv
e
d
h
e
r
B.
S
c
.
d
e
g
re
e
in
In
f
o
rm
a
ti
o
n
S
y
ste
m
s
f
ro
m
M
a
n
so
u
ra
Un
iv
e
rsit
y
in
2
0
0
0
.
S
h
e
re
c
e
iv
e
d
h
e
r
M
.
S
c
.
d
e
g
re
e
in
In
f
o
rm
a
ti
o
n
S
y
ste
m
s
f
ro
m
A
in
S
h
a
m
s
Un
iv
e
rsit
y
in
2
0
0
7
.
T
h
ro
u
g
h
a
n
Eg
y
p
ti
a
n
-
f
u
n
d
e
d
j
o
in
t
sc
h
o
lars
h
i
p
,
sh
e
re
c
e
iv
e
d
h
e
r
P
h
D
d
e
g
re
e
f
ro
m
M
a
n
so
u
ra
Un
iv
e
rsity
w
it
h
c
o
ll
a
b
o
ra
ti
o
n
f
ro
m
Qu
e
e
n
’s
Un
iv
e
rsit
y
,
Ca
n
a
d
a
in
2
0
1
2
.
S
h
e
w
a
s
a
n
A
ss
ist
a
n
t
P
ro
f
e
ss
o
r
o
f
Co
m
p
u
ter
a
n
d
In
f
o
rm
a
ti
o
n
S
c
ie
n
c
e
s
a
t
M
a
n
so
u
ra
Un
iv
e
rsity
,
Eg
y
p
t.
S
h
e
h
a
s
se
r
v
e
d
a
s
a
w
o
r
k
sh
o
p
c
o
-
C
h
a
ir
f
o
r
th
e
IEE
E
W
ire
les
s
L
o
c
a
l
Ne
t
w
o
rk
s
a
n
d
th
e
IEE
E
Co
n
v
e
rg
e
n
t
Io
T
w
o
rk
sh
o
p
.
S
h
e
is
a
n
IE
EE
m
e
m
b
e
r
sin
c
e
2
0
1
4
.
S
h
e
is
c
u
rre
n
t
ly
a
n
A
s
so
c
iate
P
ro
f
e
ss
o
r
o
f
M
e
d
ia E
n
g
in
e
e
rin
g
a
n
d
T
e
c
h
n
o
l
o
g
y
a
t
T
h
e
G
e
r
m
a
n
Un
iv
e
rsit
y
in
Ca
iro
.
A
.
Atw
a
n
re
c
e
iv
e
d
h
is
B.
S
c
.
in
El
e
c
tro
n
ics
a
n
d
Co
m
m
u
n
ica
ti
o
n
f
ro
m
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
,
M
a
n
so
u
ra
Un
iv
e
rsity
,
Eg
y
p
t
in
1
9
8
8
.
He
re
c
e
i
v
e
d
h
is
M
.
S
c
.
d
e
g
re
e
in
El
e
c
tri
c
a
l
Co
m
m
u
n
ica
ti
o
n
f
ro
m
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
,
M
a
n
so
u
ra
Un
iv
e
rsity
,
Eg
y
p
t
in
1
9
9
8
.
He
re
c
e
i
v
e
d
h
is
P
h
D
d
e
g
re
e
in
C
o
m
m
u
n
ica
ti
o
n
s
f
ro
m
M
a
n
so
u
ra
Un
iv
e
rsit
y
in
2
0
0
4
.
He
w
a
s
a
V
ice
De
a
n
o
f
S
t
u
d
e
n
t
A
ff
a
irs,
F
a
c
u
lt
y
o
f
Co
m
p
u
ter
a
n
d
I
n
f
o
rm
a
ti
o
n
S
c
ien
c
e
s,
M
a
n
so
u
ra
Un
iv
e
rsity
.
He
is
c
u
rre
n
tl
y
a
v
isit
in
g
P
r
o
f
e
ss
o
r
a
t
F
a
c
u
lt
y
o
f
Co
m
p
u
ti
n
g
a
n
d
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
No
rth
e
rn
Bo
r
d
e
r
Un
iv
e
rsity
,
S
a
u
d
i
A
ra
b
ia.
H
.
H
.
S
o
li
m
a
n
re
c
e
iv
e
d
h
is B.
S
c
.
a
n
d
M
.
S
c
.
d
e
g
re
e
s in
1
9
8
3
a
n
d
1
9
8
7
re
sp
e
c
ti
v
e
ly
f
ro
m
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
,
M
a
n
so
u
ra
Un
iv
e
rsit
y
,
Eg
y
p
t.
T
h
ro
u
g
h
a
n
Eg
y
p
ti
a
n
-
f
u
n
d
e
d
j
o
in
t
sc
h
o
lars
h
ip
,
h
e
re
c
e
iv
e
d
h
is
P
h
D
d
e
g
re
e
f
ro
m
M
a
n
so
u
ra
Un
iv
e
rsit
y
w
it
h
c
o
ll
a
b
o
ra
ti
o
n
f
ro
m
a
Un
iv
e
rsit
y
in
G
e
r
m
a
n
in
1
9
9
3
.
He
is
c
u
rre
n
tl
y
th
e
De
a
n
o
f
F
a
c
u
lt
y
o
f
Co
m
p
u
ter
a
n
d
In
f
o
r
m
a
ti
o
n
S
c
ien
c
e
s,
M
a
n
so
u
ra
U
n
iv
e
rsity
.
Evaluation Warning : The document was created with Spire.PDF for Python.