Traditional Methods:
1. Modified Periodogram Method
2. Blackman-Tukey Method
3. The Fast Correlation Method
By:
Parametric
Non Parametric
AR, ARMA based
Periodogram &
Modified
Periodogram
Blackman
Tuckey
Subspace Based
(high-resolution)
Ex: MUSIC
and ESPRIT
Fast Correlation
Model fitting based
Ex: Least Squares
Modified Periodogram
1
1
Pper (e j ) | X N (e j ) |2
N
N
1
j
j 2 ,
Pper (e )
Px (e ) * WR (e )
2N
j
1
PM (e j )
NU
1
U
N
N 1
x ( n) w
(n)e jn
sin( N 2) j ( N 1) 2
WR (e )
e
sin( 2)
j
jn
x
(
n
)
w
(
n
)
e
n
2
1
w(n)
2N
n 0
W (e
) d
N=128,Rectangular
Window
jn
x
(
n
)
w
(
n
)
e
1
U
N
Bias:
N 1
w(n)
Variance:
n 0
E{PM (e j )}
Resolution:
1
j
j 2
Px (e ) W (e )
2NU
window dependent
Var {PM (e j )} Px2 (e j )
n 0 ,1,....., L 1
Overlap = L-D
....
6
PW (e j )
1
KLU
k 1 L 1
jn
x
(
n
iD
)
e
i 0 n 0
k 1
1
PW (e ) PM( i ) (e j )
L i 0
j
Bias
E{PB (e j )}
Resolution
1 L 1
2
U w(n)
L n 0
1
j
j 2
Px (e ) W (e )
2LU
Window dependent
Variance
9 L 2 j
j
Var {Pper (e )}
Px (e )
16 N
N 512
k 4
N 512 , L 128
8
Note: Bartlett & Welch are design to reduce the variance of the Periodogra
by averaging and modified it.
Periodogram is computed by taking the Fourier transform of a
consistent estimate of the auto correlation sequence.
For any finite data record of length N, the variance
r (k )of
x
will
rx ( N 1)
1
x( N 1) x(0)
N
at lag k n 1
rx (k )
PBT (e )
j
jk
r
(
k
)
w
(
k
)
e
x
k M
PBT (e j )
Bias
jk
r
(
k
)
w
(
k
)
e
x
k M
1
j
E{PBT (e )}
Px (e j ) W (e j )
2
Resolution
Window dependent
2
x
2
w
(k )
M
N 512 , M 128
Rectangular
N 512 , M 128
Hanning
N 512 , M 128
Bartlett
12
N 512 , M 128
Blackman
rx ( k )
1 1 *
F X (k ) X (k )
N
Thank You.