Basic Definitions and The Spectral Estimation Problem

Lecture 1

Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R. Moses, Prentice Hall, 1997

Slide L1–1

Informal Definition of Spectral Estimation

Given: A finite record of a signal. Determine: The distribution of signal power over frequency.
signal t ω t=1, 2, ... ω ω+∆ω π spectral density

! = (angular) frequency in radians/(sampling interval) f = !=2 = frequency in cycles/(sampling interval)

Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R. Moses, Prentice Hall, 1997

Slide L1–2

Applications Temporal Spectral Analysis Vibration monitoring and fault detection Hidden periodicity finding Speech processing and audio devices Medical diagnosis Seismology and ground movement study Control systems design Radar, Sonar

Spatial Spectral Analysis Source location using sensor arrays
Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R. Moses, Prentice Hall, 1997 Slide L1–3

Moses.1 jy(t)j2 < 1 X Then: Y (! ) = 1 t=.Deterministic Signals fy(t)g1 .1 y(t)e. Prentice Hall. 1997 Slide L1–4 .i!t exists and is called the Discrete-Time Fourier Transform (DTFT) Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R.1 = t= If: discrete-time deterministic data sequence X 1 t=.

Prentice Hall. 1997 . Moses.Energy Spectral Density Parseval's Equality: jy(t)j2 = 21 .i!k (k) = 1 t=. k) Slide L1–5 Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R.1 y(t)y (t .1 X (k)e. S (!)d! t=.1 X Z 1 where 4 S (!) = jY (!)j2 = Energy Spectral Density We can write S (!) = where X 1 k=.

Moses. 1997 Slide L1–6 . Prentice Hall. Stoica and R.Random Signals Random Signal random signal probabilistic statements about future variations t current observation time Here: X 1 t=.1 n jy(t)j2 = 1 o But: E jy(t)j2 < 1 E f g = Expectation over the ensemble of realizations E jy(t)j2 n o = Average power in y (t) PSD = (Average) power spectral density Lecture notes to accompany Introduction to Spectral Analysis by P.

Prentice Hall.i!k (k) is the autocovariance sequence (ACS) r(k) = E fy(t)y (t . Stoica and R. (!)d! Z (!)d! = infinitesimal signal power in the band ! d! 2 Lecture notes to accompany Introduction to Spectral Analysis by P. (!)ei!k d! n o (Inverse DTFT) Interpretation: so r(0) = E jy(t)j2 = 21 . Moses.k) r(0) jr(k)j Z Note that r(k) = 21 . k)g r(k) = r (.First Definition of PSD (! ) = where r X 1 k=.1 r(k)e. 1997 Slide L1–7 .

t=1 y(t)e. Stoica and R. Moses.Second Definition of PSD 1 N y(t)e. Prentice Hall.i!t Lecture notes to accompany Introduction to Spectral Analysis by P. 1997 Slide L1–8 .i!t (!) = Nlim E N !1 t=1 X > : 8 > < 2 9 > = > Note that 1 jY (!)j2 (!) = Nlim E N N !1 YN (!) = X where N is the finite DTFT of fy(t)g.

1997 Slide L1–9 . Stoica and R.! ) P3: If y Lecture notes to accompany Introduction to Spectral Analysis by P.1=2 1=2] (!) 0 (t) is real. Thus.Properties of the PSD P1: (!) = (! + 2 ) for all !. P2: ] () f 2 . Moses. we can restrict attention to !2 . Prentice Hall. Then: (! ) = (.! ) Otherwise: (! ) 6= (.

Transfer of PSD Through Linear Systems System Function: where q . 1997 Slide L1–10 . 1) H (q ) y (t) 2 y (! ) = jH (! )j e( e(t) e (! ) Then !) y(t) = X 1 k=0 hk e(t .1 H (q) = X 1 k=0 hk q. Moses. Stoica and R.1y(t) = y(t . Prentice Hall.i!k H (! ) = X 1 y (!) = jH (!)j2 e(!) k=0 Lecture notes to accompany Introduction to Spectral Analysis by P. k) hk e.k = unit delay operator: q.

Parametric: – Assumes a parameterized functional form of the PSD Lecture notes to accompany Introduction to Spectral Analysis by P. ]g Find an estimate of Two Main Approaches : Nonparametric: – Derived from the PSD definitions. Moses. Stoica and R. Prentice Hall. 1997 Slide L1–11 .The Spectral Estimation Problem The Problem: From a sample fy(1) : : : y(N )g (!): f ^(!) ! 2 .

Periodogram and Correlogram Methods Lecture 2 Lecture notes to accompany Introduction to Spectral Analysis by P. Moses. 1997 Slide L2–1 . Prentice Hall. Stoica and R.

Moses. Prentice Hall. Lecture notes to accompany Introduction to Spectral Analysis by P.i!t N t=1 Natural estimator N 2 Used by Schuster ( 1900) to determine “hidden periodicities” (hence the name). 1997 Slide L2–2 .i!t (!) = Nlim E N !1 t=1 X > : 8 > < 2 9 > = > Given : Drop “ fy(t)gN t=1 lim ” and “E N !1 f g” to get X ^p(!) = 1 y(t)e. Stoica and R.Periodogram Recall 2nd definition of (! ): 1 N y(t)e.

1997 Slide L2–3 .i!k ^c(!) = k=. Moses.i!k (k)” by “^(k)”: r r ^(k)e.(N .1 N .1 X r(k)e. Stoica and R. Prentice Hall.Correlogram Recall 1st definition of (! ): (! ) = P X 1 Truncate the “ ” and replace “r k=.1) Lecture notes to accompany Introduction to Spectral Analysis by P.

k t=k+1 X Standard biased estimate: 1 N y(t)y (t . 1997 Slide L2–4 . k) k 0 ^ r(k) = N . Prentice Hall.Covariance Estimators (or Sample Covariances) Standard unbiased estimate: 1 N y(t)y (t . Stoica and R.k) k < 0 r Lecture notes to accompany Introduction to Spectral Analysis by P. Moses. k) k 0 r(k) = N ^ t=k+1 X For both estimators: r ^(k) = ^ (.

i!k ^p(!) = ^c(!) Consequence: Both p ! and ^( ) ^c(!) can be analyzed simultaneously.(N . Prentice Hall. 1997 .1 X = ^c(!) k=.1) r ^(k)e. N ^p(!) = 1 y(t)e. Slide L2–5 Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R.Relationship Between ^p (! ) and ^c(! ) If: the biased ACS estimator r Then: ^(k) is used in ^c(!).i!t N t=1 X 2 = N . Moses.

r(k) may be large for large jkj ^ Even if the errors r k r k Nj. ( )] Lecture notes to accompany Introduction to Spectral Analysis by P. Thus. Prentice Hall. ( )g ^ ( ) . Moses. ^p(!) and ^c(!) have poor performance. 1997 Slide L2–6 . p! f^( ) . even for large N .1 are small. jk =0 there are “so many” that when summed in ! . the PSD error is large. Stoica and R.Statistical Performance of ^p(! ) and ^c(! ) Summary: Both are asymptotically (for large N ) unbiased: E ^p(!) ! (!) as N ! 1 n o Both have “large” variance. Intuitive explanation: r(k) .

1 n o n o X ! X N . ( )WB (! . ) d Z Ideally: WB (!) = Dirac impulse (!). n o 0 k 1 .i!k k=. N k=. 1997 . window E ^p(!) = 21 . Stoica and R.1 X wB (k) = 8 < : = Thus.(N .1) N .1 jkj r(k)e.Bias Analysis of the Periodogram E ^p(!) = E ^c(!) = E f^(k)g e.1) 1 = wB (k)r(k)e. Moses. Slide L2–7 Lecture notes to accompany Introduction to Spectral Analysis by P. Prentice Hall. or triangular. 1 jkj N Bartlett.(N .i!k = 1. jNj jkj N .i!k r k=.

for N = 25 −10 −20 dB −30 −40 −50 −60 −3 −2 −1 0 1 ANGULAR FREQUENCY 2 3 Main lobe 3dB width For “small” N . Stoica and R. Moses. Slide L2–8 Lecture notes to accompany Introduction to Spectral Analysis by P. Prentice Hall. WB 1=N . 1997 . (!) may differ quite a bit from (!).Bartlett Window WB (! ) 1 sin(!N=2) 2 WB (!) = N sin(!=2) " # 0 WB (!)=WB (0).

Stoica and R. 1997 Slide L2–9 . ^ φ(ω)≅W (ω) B Sidelobe Level: leakage φ(ω)≅δ(ω) leakage ω ω Lecture notes to accompany Introduction to Spectral Analysis by P. Moses. φ(ω) smearing ω ω (!) separated in f by less than 1=N are not ^ φ(ω) <1/Ν Thus: Periodogram resolution limit = 1=N .Smearing and Leakage Main Lobe Width: smearing or smoothing Details in resolvable. Prentice Hall.

so ! is asymptotically unbiased. Stoica and R. WB ! !. 1997 Slide L2–10 . severe bias As N . Moses.Periodogram Bias Properties Summary of Periodogram Bias Properties: For “small” N . !1 ^( ) ( )! ( ) Lecture notes to accompany Introduction to Spectral Analysis by P. Prentice Hall.

Periodogram Variance As N !1 E ^p(!1) . (!1) ^p(!2) . Moses. Prentice Hall. 1997 Slide L2–11 . (!2) 2(!1) !1 = !2 = 0 !1 6= !2 nh ih ( io Inconsistent estimate Erratic behavior ^ φ(ω) ^ φ(ω) asymptotic mean = φ(ω) ω + 1 st. Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R. dev = φ(ω) too - Resolvability properties depend on both bias and variance.

Moses. 1 Direct computation of O N 2 flops ( ) .1 fY (k)gN=0 from fy(t)gN : t=1 k Lecture notes to accompany Introduction to Spectral Analysis by P.Discrete Fourier Transform (DFT) Finite DTFT: YN (!) = X N t=1 y(t)e. 1997 Slide L2–12 . Prentice Hall. N Let ! = N Then YN ( 2 k) is the Discrete Fourier Transform (DFT): N X Y (k) = N t=1 y(t)W tk k = 0 ::: N .i!t 2 k and W = e.i 2 . Stoica and R.

Radix–2 Fast Fourier Transform (FFT) N = 2m N=2 N Y (k) = y(t)W tk + y(t)W tk t=1 t=N=2+1 N=2 2 = y(t) + y(t + N=2)W Nk ]W tk t=1 Nk +1 for even k with W 2 = . Stoica and R. Moses. 1997 .i2 =N . ~ 4 = 0 2 4 : : : N . Prentice Hall.1 for odd k Assume: X X X Let N For k ~ ~ = N=2 and W = W 2 = e. 1 = 2p + 1: X t=1 ~ ~ y(t) + y(t + N )]W tp Y (2p + 1) = Each is a N ~ N ~ = N=2-point DFT computation. y(t + N )]W tgW tp Lecture notes to accompany Introduction to Spectral Analysis by P. 2 = 2p: Y (2p) = For k X ~ N = 1 3 5 : : : N . Slide L2–13 t=1 ~ ~ f y(t) .

FFT Computation Count Let ck Then = number of flops for N = 2k point FFT. 1997 Slide L2–14 . Prentice Hall.1 k2k ) ck = 2 ck = 1 N log2 N 2 Thus. Lecture notes to accompany Introduction to Spectral Analysis by P. Moses. Stoica and R. 2k + 2c ck = 2 k.

1 ! N k=0 ^ φ(ω) continuous curve Lecture notes to accompany Introduction to Spectral Analysis by P. Moses. N=8 ω 2 k N .Zero Padding Append the given data by zeros prior to computing DFT (or FFT): fy(1) : : : y(N ) 0 : : : 0g | N {z } Goals: Apply a radix-2 FFT (so N Finer sampling of = power of 2) ^(!): 2 k N .1 N k=0 sampled. 1997 Slide L2–15 . Stoica and R. Prentice Hall.

Prentice Hall.Improved Periodogram-Based Methods Lecture 3 Lecture notes to accompany Introduction to Spectral Analysis by P. 1997 Slide L3–1 . Stoica and R. Moses.

Prentice Hall.1 X k=. ^( ) jj ^BT (!) = M .1) w(k)^(k)e. with small weight applied to covariances r k with “large” k . Stoica and R.(M . Moses.Blackman-Tukey Method Basic Idea: Weighted correlogram. 1997 Slide L3–2 .i!k r fw(k)g = Lag Window w(k) 1 -M M k Lecture notes to accompany Introduction to Spectral Analysis by P.

Moses. 1997 .Blackman-Tukey Method. Z W (!) = = Conclusion: Effect: DTFT fw(k)g Spectral Window ^BT (!) = “locally” smoothed periodogram Variance decreases substantially Bias increases slightly By proper choice of M : MSE = var + bias2 ! 0 as N ! 1 Slide L3–3 Lecture notes to accompany Introduction to Spectral Analysis by P. )d 2 . con't ^BT (!) = 1 ^p( )W (! . Prentice Hall. Stoica and R.

1997 Slide L3–4 .1 X . Moses. W (!)d! = equiv bandwidth e= W (0) Ne e = 1 Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R.1) Ne = k=. w(k) is a psd sequence) ^BT (!) 0 (which is desirable) Then: Time-Bandwidth Product M . )d 2 . Prentice Hall.(M (0) w Z w (k ) = equiv time width 1 2 .Window Design Considerations Nonnegativeness: ^BT (!) = 1 ^p( ) W (! . 0 Z | {z } If W (!) 0 (.

e) is essentially ) Choose window shape to compromise between smearing (main lobe width) and leakage (sidelobe level). once M is given. ) Choose M as a tradeoff between variance and bias. bias decreases and variance increases. As M increases. Once M is given. Moses. Lecture notes to accompany Introduction to Spectral Analysis by P. The energy in the main lobe and in the sidelobes cannot be reduced simultaneously. con't e = 1=Ne = 0(1=M ) is the BT resolution threshold. Ne (and hence fixed.Window Design. Stoica and R. 1997 Slide L3–5 . Prentice Hall.

M 0 = 25 −10 −20 dB −30 −40 −50 −60 −3 −2 −1 0 1 ANGULAR FREQUENCY 2 3 Rectangular Window. Prentice Hall. 1997 Slide L3–6 .Window Examples Triangular Window. M 0 −10 = 25 −20 dB −30 −40 −50 −60 −3 −2 −1 0 1 ANGULAR FREQUENCY 2 3 Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R. Moses.

Bartlett Method Basic Idea:
1 Μ 2Μ ... Ν

^1(ω) ^2(ω) φ φ

... average

^L(ω) φ

^B(ω) φ
Mathematically:

yj (t) = y((j ; 1)M + t) t = 1 : : : M = the j th subsequence 4 (j = 1 : : : L = N=M ])

^j (!) = 1 yj (t)e;i!t M t=1
X

M

2

1 L ^ (!) ^B (!) = L j =1 j
X

Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R. Moses, Prentice Hall, 1997

Slide L3–7

Comparison of Bartlett and Blackman-Tukey Estimates

1 L ^B (!) = L j =1
X

8 > < > :

M ;1 X

=

'
Thus:

k=;(M ;1) M ;1 X k=;(M ;1)

k=;(M ;1) 8 M ;1 < 1 X L X
:

r ^j (k)e;i!k
9 =

9 > = >

L j =1

r ^j (k) e;i!k

r ^(k)e;i!k

^B (!) ' ^BT (!)
Since B ! implicitly uses method has

with a rectangular lag window wR k

()

^( )

fwR(k)g, the Bartlett

High resolution (little smearing) Large leakage and relatively large variance
Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R. Moses, Prentice Hall, 1997 Slide L3–8

Welch Method Similar to Bartlett method, but allow overlap of subsequences (gives more subsequences, and thus “better” averaging) use data window for each periodogram; gives mainlobe-sidelobe tradeoff capability

1

2 . . . subseq subseq #1 #2 subseq #S

N

Let S # of subsequences of length M . (Overlapping means S > N=M “better averaging”.)

=

])

Additional flexibility: The data in each subsequence are weighted by a temporal window Welch is approximately equal to non-rectangular lag window.

^BT (!) with a
Slide L3–9

Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R. Moses, Prentice Hall, 1997

k +J 1 ^D(!k ) = ^p (!j ) 2J + 1 j=k. Stoica and R.1 ! = N j =0 Idea: “Local averaging” of (2J + 1) samples in the j (2 + 1) frequency domain should reduce the variance by about J .J X Lecture notes to accompany Introduction to Spectral Analysis by P. Moses. 1997 Slide L3–10 .Daniell Method By a previous result. Prentice Hall. f ^p(!j )g are (nearly) uncorrelated random variables for 2 j N . for N 1.

Moses. Then. for N 1. 1997 Slide L3–11 . Stoica and R. Hence: ^D (! ) ' ^BT (! ) with a rectangular spectral Let Z window. con't As J increases: Bias increases (more smoothing) Variance decreases (more averaging) = 2J=N . ^D(!) ' 1 ^p(!)d! 2 . Lecture notes to accompany Introduction to Spectral Analysis by P.Daniell Method. Prentice Hall.

Lecture notes to accompany Introduction to Spectral Analysis by P. Prentice Hall. BT periodogram – Local smoothing/averaging of spectral window. ^BT (!) with a rectangular Slide L3–12 – Implemented by local averaging of periodogram values. Welch periodograms – Approximate interpretation: BT ! with a suitable lag window (rectangular for Bartlett. Moses. ^p(!) by a suitably selected ^(k) using a lag – Implemented by truncating and weighting r window in c ! ^( ) Bartlett. 1997 . Daniell Periodogram – Approximate interpretation: spectral window. Stoica and R. more general for Welch).Summary of Periodogram Methods Unwindowed periodogram – reasonable bias – unacceptable variance Modified periodograms – Attempt to reduce the variance at the expense of (slightly) increasing the bias. ^ () – Implemented by averaging subsample periodograms.

Prentice Hall. Moses.Parametric Methods for Rational Spectra Lecture 4 Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R. 1997 Slide L4–1 .

Basic Idea of Parametric Spectral Estimation Observed Data Assumed functional form of φ(ω.i!k (!) is a rational function in e. Stoica and R. provided m and n are chosen sufficiently large. P By Weierstrass theorem. ! can approximate arbitrarily well any continuous PSD. Moses.i! .θ) Estimate parameters in φ(ω. Note. however: choice of m and n is not simple some PSDs are not continuous Lecture notes to accompany Introduction to Spectral Analysis by P.θ) φ(ω) possibly revise assumption on φ(ω) Rational Spectra jkj m k e. Prentice Hall. 1997 Slide L4–2 ( ) .i!k (!) = P jkj n k e.θ) ^ θ Estimate PSD ^ ^ =φ(ω.

and ARMA Models By Spectral Factorization theorem.g.1 + + anz..m and. Prentice Hall. A(! ) = A(z )jz =ei! Signal Modeling Interpretation: e(t) e (! ) = 2 - B (q) A(q) white noise B (!) 2 2 A(!) ltered white noise y(t)y (! ) = ARMA: AR: MA: A(q)y(t) = B (q)e(t) A(q)y(t) = e(t) y(t) = B (q)e(t) Slide L4–3 Lecture notes to accompany Introduction to Spectral Analysis by P.AR. MA. Moses. 1997 . a rational factored as (!) can be B (!) 2 2 (!) = A(!) A(z) = 1 + a1z.n B (z) = 1 + b1z. e. Stoica and R.1 + + bmz.

k) and take E f g to give: X r (k ) + X 2 m bj hj . 1997 Slide L4–4 . Moses. j ) (b0 = 1) Multiply by y (t . Prentice Hall.k = j =0 = 0 for k > m B (q) = 1 h q.ARMA Covariance Structure ARMA signal model: y(t)+ X n i=1 n aiy(t .k (h = 1) where H (q ) = A(q ) 0 k k=0 X X i=1 air(k . Stoica and R. i) = m j =0 bj E fe(t . i) = X m j =0 bj e(t . j )y (t . k)g Lecture notes to accompany Introduction to Spectral Analysis by P.

an 0 3 7 7 7 5 2 6 6 6 4 Writing covariance equation in matrix form for k : : : n: =1 r(0) r(.1) : : : r(. . 1997 Slide L4–5 . Stoica and R.AR Signals: Yule-Walker Equations AR: m = 0. r(n) : : : r(0) 1 = 2 R 0 2 6 6 6 4 7 7 7 5 " # " 32 6 6 6 4 3 7 7 7 5 # These are the Yule–Walker (YW) Equations. 2 1 a1 = 0 . r (. Moses.n) . Prentice Hall. . r(1) r(0) . Lecture notes to accompany Introduction to Spectral Analysis by P. .1) . . . . .

. . r . Prentice Hall. Stoica and R. ^(. . r ^(n) : : : r(0) ^ ^n a 0 32 7 7 7 5 6 6 6 4 3 7 7 7 5 2 6 6 6 4 3 7 7 7 5 Then the PSD estimate is ^2 ^(!) = ^ 2 jA(!)j Lecture notes to accompany Introduction to Spectral Analysis by P.AR Spectral Estimation: YW Method Yule-Walker Method: Replace r 2 6 6 6 4 (k) by r(k) and solve for f^ig and ^2: ^ a r ^(0) ^(. Moses. 1997 Slide L4–6 . . . r ^(1) r(0) ^ ^.1 = 0 a .1) : : : ^(.1) .n) 1 r r ^2 . .

n) . .(Y Y ). n)]T . i) = y(t) + 'T (t) = a1 : : : an]T to minimize f( ) = X N This gives 2 y=6 4 y(n + 1) y(n + 2) y(N ) .1(Y y) where 3 7 5 2 6 t=n+1 je(t)j2 y(1) y(2) y(N . Stoica and R. .AR Spectral Estimation: LS Method Least Squares Method: e(t) = y(t) + X n 4 = y(t) + y(t) ^ where '(t) = y (t . 2) Lecture notes to accompany Introduction to Spectral Analysis by P. Moses. . . 1997 Slide L4–7 . 3 7 5 Y =4 y(n) y(n . . . 1) y(n + 1) y(n) . y(N . Find i=1 aiy(t . ^ = . 1) y(N . 1) : : : y (t . Prentice Hall.

{z .. . .n .. Moses. 32 7 7 7 5 } 6 6 6 4 1 n 3 7 7 7 5 2 6 6 6 4 ^ k = either r(k) or r(k). .Levinson–Durbin Algorithm Fast. Stoica and R. n . . 0 2 n 3 7 7 7 5 O(n3) flops = 1 : : : n: O(n4) flops Levinson–Durbin Algorithm: Exploits the Toeplitz form of Rn+1 to obtain the solutions for k : : : n in O n2 flops! =1 ( ) Lecture notes to accompany Introduction to Spectral Analysis by P.. order-recursive solution to YW equations 2 6 6 6 4 | 0 . Prentice Hall. 1997 Slide L4–8 . . .0 . Direct Solution: For one given value of n: For k Rn+1 1 0 = 0 ..1 1 .1 ..

Prentice Hall. . 2 4 Rn+1 n+1 r ~n n+1 r ~n 0 3 5 2 r ~n = 6 4 . where x = xn : : : x1]T ~ ~ ~ Nested structure 2 Rn+2 = Thus. n 3 7 5 1 Rn+2 4 1 n = 0 3 5 2 4 Rn+1 n+1 r ~n n+1 r ~n 0 32 54 1 n n = 0 0 n 3 5 2 4 2 3 5 where r n = n+1 + ~n n Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R.Levinson-Durbin Alg. 1997 Slide L4–9 . con't Relevant Properties of R: Rx = y $ Rx = y. Moses.

Moses. 1997 . Stoica and R. con't 2 Rn+2 4 82 < 4 +2 : 1 n n = 0 0 n 3 5 2 4 2 3 5 2 Rn+2 4 39 = 5 2 0 ~n = 0n 2 1 n 3 5 2 4 3 5 2 3 5 Combining these gives: Rn 0 1 n + kn ~n 0 1 3 5 2 4 = 4 n + kn n 2 0 n + kn 2 n = 4 n 2 +1 3 5 0 0 Thus. 2 kn = . Prentice Hall.Levinson-Durbin Alg. Lecture notes to accompany Introduction to Spectral Analysis by P. jknj2) 2 2 n " n # " ~n 1 # Computation count: k flops for the step k 2 ) n2 flops !k+1 2 to determine f k k gn=1 k Slide L4–10 This is O (n2) times faster than the direct solution. n = n ) n+1 = 0 + kn 2+1 = n + kn n = n(1 .

r(k) = 0 for jkj > m and 2 2 = m r(k)e. Prentice Hall. m) Thus.MA Signals MA: n =0 y(t) = B (q)e(t) = e(t) + b1e(t . 1) + + bme(t . Moses. Stoica and R.m X Lecture notes to accompany Introduction to Spectral Analysis by P.i!k (!) = jB(!)j k=. 1997 Slide L4–11 .

i!k k=. Moses. Prentice Hall. ^(!) is not guaranteed to be 0 =0 Both methods are special cases of ARMA methods described below. Lecture notes to accompany Introduction to Spectral Analysis by P. with AR model order n . Estimate fbkg and 2 and insert them in (!) = jB(!)j2 2 nonlinear estimation problem ^(!) is guaranteed to be 0 2. 1997 Slide L4–12 .m ^BT (!) with a rectangular lag window of 2m + 1.MA Spectrum Estimation Two main ways to Estimate (! ): 1. Insert sample covariances (! ) = This is length X m f^(k)g in: r r(k)e. Stoica and R.

Prentice Hall.i!k k (!) = 2 A(!) jA(!)j2 P where k = E f B(q)e(t)] B(q)e(t . k)] g = E f A(q)y(t)] A(q)y(t . k)] g = X n X n j =0 p=0 aj ap r(k + p . Moses. j ) Lecture notes to accompany Introduction to Spectral Analysis by P.m k e.ARMA Signals ARMA models can represent spectra with both peaks (AR part) and valleys (MA part). Stoica and R. 1997 Slide L4–13 . A(q)y(t) = B (q)e(t) B (!) 2 = m=.

m k e jA(!)j2 linear estimation problem (the Modified Yule-Walker method). Moses. ^(!) is not guaranteed to be 0 Lecture notes to accompany Introduction to Spectral Analysis by P. Estimate fai bj A(!) nonlinear estimation problem. can use an approximate linear two-stage least squares method ^(!) is guaranteed to be 0 2. 1997 Slide L4–14 . Prentice Hall. Stoica and R.ARMA Spectrum Estimation Two Methods: 2g in (!) = 2 B(!) 2 1. Estimate fai r(k)g in (!) = P m .i!k k=.

f kgK=1 by using AR k 1b) Estimate the noise sequence ^(t) = y(t) + ^1y(t .Two-Stage Least-Squares Method Assumption: The ARMA model is invertible: A e(t) = B(q) y(t) (q ) = y(t) + 1y(t . K ) ^2 = N 1 j^(t)j2 e N . 1997 Slide L4–15 . for some large K e(t) ' y(t) + 1y(t . K ) 1a) Estimate the coefficients modelling techniques. K t=K +1 X Lecture notes to accompany Introduction to Spectral Analysis by P. 1) + + K y(t . Moses. 2) + = AR(1) with j kj ! 0 as k ! 1 Step 1: Approximate. Stoica and R. 1) + 2y(t . 1) + e and its variance + ^K y(t . Prentice Hall.

Note that the ai and bj coefficients enter linearly in the above equation: y(t) .y(t . y(t . Moses. con't fe(t)g by ^(t) in the ARMA equation. e A(q)y(t) ' B (q)^(t) e and obtain estimates of fai bj g by applying least squares Step 2: Replace techniques. 1) : : : . n) e ^(t . Stoica and R. m)] e e = a1 : : : an b1 : : : bm]T Lecture notes to accompany Introduction to Spectral Analysis by P. 1) : : : ^(t . 1997 Slide L4–16 .Two-Stage Least-Squares Method. ^(t) ' . Prentice Hall.

fast Levinson-type algorithms exist for obtaining ai . least f^ g Note: For narrowband ARMA signals. 1997 Slide L4–17 . 5 . . the accuracy of ai is often better for M > n Lecture notes to accompany Introduction to Spectral Analysis by P. # 2 = r(m + M . . n + 1) r(m . . If M > n overdetermined squares solution for ai . 1) : : : r(m . .. r(m + M ) r(m + 1) r(m + 2) 3 7 If M n. . Prentice Hall. n + M ) . n + 2) . . Moses. i) = 0 k > m 3 7 5 " r(m) r(m + 1) . Stoica and R.Modified Yule-Walker Method ARMA Covariance Equation: r(k) + 2 6 4 X n In matrix form for k i=1 air(k . = f^ g Y W system of equations.. = m + 1 ::: m + M a1 an . r f^ g . .6 4 Replace fr(k)g by f^(k)g and solve for faig. : : : r(m . .

Summary of Parametric Methods for Rational Spectra Method AR: YW or LS low low-medium medium-high medium-high medium low-medium No No Yes Computational Burden low Accuracy medium Guarantee ^(! ) 0 ? Yes MA: BT ARMA: MYW ARMA: 2-Stage LS Use for Spectra with (narrow) peaks but no valley Broadband spectra possibly with valleys but no peaks Spectra with both peaks and (not too deep) valleys As above Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R. 1997 Slide L4–18 . Moses. Prentice Hall.

Prentice Hall. 1997 Slide L5–1 .Parametric Methods for Line Spectra — Part 1 Lecture 5 Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R. Moses.

Stoica and R. Prentice Hall. Moses. !1 !2 !3 - An “Ideal” line spectrum Lecture notes to accompany Introduction to Spectral Analysis by P. 1997 . Examples: communications radar.Line Spectra Many applications have signals with (near) sinusoidal components. sonar geophysical seismology ARMA model is a poor approximation Better approximation by Discrete/Line Spectrum Models 2 6(2 1) 2 6 (!) 6 (2 2) 2 6 (2 2) 3 ! Slide L5–2 .

Moses. 1997 . Stoica and R. Prentice Hall. ] (realistic and mathematically convenient) A3: e(t) = circular white noise with variance 2 E fe(t)e (s)g = 2 t s E fe(t)e(s)g = 0 (can be achieved by “slow” sampling) Slide L5–3 Lecture notes to accompany Introduction to Spectral Analysis by P. power f g f g y(t) = x(t) + e(t) t = 1 2 : : : n x(t) = k ei(!k t+ k ) k=1 xk (t) X | {z } Assumptions: A1: A2: k>0 !k 2 .Line Spectral Signal Model Signal Model: Sinusoidal components of frequencies !k and powers 2 . uniformly distributed on . superimposed in white noise of k 2. ] (prevents model ambiguities) f'k g = independent rv's.

for p 6= j =2 .i'j o e Z n 1 i' d' 2 = 0.Covariance Function and PSD Note that: E E n i'p e. 1997 . !p) + 2 p Slide L5–4 Lecture notes to accompany Introduction to Spectral Analysis by P. k)g = n=1 2ei!pk + 2 k 0 p p P and (! ) = 2 X n p=1 2 (! .i'j o = E nei'p o E ne. Prentice Hall. r(k) = E fy(t)y (t . Moses. for p = j e i'p e. e E xp(t)xj (t .i'j o = 1. Stoica and R. k) = 2 ei!pk p j p n o Hence.

Moses. Prentice Hall.Parameter Estimation Estimate either: f!k k 'k gn=1 k 2 (Signal Model) f!k 2gn=1 2 k k Once (PSD Model) ^ Major Estimation Problem: f!k g f!kg are determined: ^ X f ^2g can be obtained by a least squares method from k n 2ei!pk + residuals ^ ^ r(k) = p p=1 OR: Both k and 'k can be derived by a least squares method from f^ g f^ g X y(t) = with n k= k=1 k ei'k . 1997 Slide L5–5 . Stoica and R. ^ ei!k t + residuals k Lecture notes to accompany Introduction to Spectral Analysis by P.

Prentice Hall. B = eiN!1 eiN!n k 2 6 4 3 7 5 Lecture notes to accompany Introduction to Spectral Analysis by P. . 1997 Slide L5–6 .Nonlinear Least Squares (NLS) Method min' g f! Let: X N k k k t=1 | y(t) . . X n k=1 {z F (! ') k ei(!k t+'k ) 2 } = kei'k = 1 : : : n]T Y = y(1) : : : y(N )]T ei!1 ei!n . Stoica and R. Moses. .

Moses.1B Y !=^ ! and ! = arg max Y B (B B ).1B Y ] B B] . Y B(B B).1B Y This gives: ^ = (B B). Stoica and R. con't Then: F = (Y . B ) = kY .1B Y ] +Y Y .Nonlinear Least Squares (NLS) Method.1B Y ^ ! Lecture notes to accompany Introduction to Spectral Analysis by P. B k2 = . Prentice Hall. (B B). B ) (Y . (B B). 1997 Slide L5–7 .

Prentice Hall.NLS Properties Excellent Accuracy: 6 2 (for N var (^k ) = 3 2 ! N k Example: N = 300 SNRk = 2= 2 = 30 dB k q 1) Then var (^k ) 10. 1997 Slide L5–8 . Stoica and R.5. Moses. ! Difficult Implementation: The NLS cost function F is multimodal. it is difficult to avoid convergence to local minima. Lecture notes to accompany Introduction to Spectral Analysis by P.

Unwindowed Periodogram as an Approximate NLS Method

For a single (complex) sinusoid, the maximum of the unwindowed periodogram is the NLS frequency estimate: Assume: Then:

n=1
X

B B=N
N t=1

BY=

y(t)e;i!t = Y (!)

(finite DTFT)

1 Y B (B B );1B Y = N jY (!)j2 = ^p(!) = (Unwindowed Periodogram)
So, with no approximation,

! = arg max ^p(!) ^ !

Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R. Moses, Prentice Hall, 1997

Slide L5–9

Unwindowed Periodogram as an Approximate NLS Method, con't

Assume: Then:

n>1

f!kgn=1 ' the ^ k
provided that

locations of the peaks of p !

^( )

n

largest

inf j!k ; !pj > 2 =N
which is the periodogram resolution limit. If better resolution desired then use a High/Super Resolution method.

Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R. Moses, Prentice Hall, 1997

Slide L5–10

High-Order Yule-Walker Method Recall:

y(t) = x(t) + e(t) =

k ei(!k t+'k ) +e(t) | {z } k=1 xk (t)
X

n

“Degenerate” ARMA equation for y (t):
n

(1 ; ei!k q;1)xk (t) = k ei(!kt+'k) ; ei!k ei !k(t;1)+'k] = 0
o

Let

B (q) = 1 +

4 bk q;k = A(q)A(q) k=1 A(q) = (1 ; ei!1 q;1) (1 ; ei!n q;1) A(q) = arbitrary
X

L

Then B

(q)x(t) 0 ) B (q)y(t) = B (q)e(t)
Slide L5–11

Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R. Moses, Prentice Hall, 1997

Stoica and R. f!kgn=1. Prentice Hall. along with L .High-Order Yule-Walker Method. con't Estimation Procedure: Estimate f^igL=1 using an ARMA MYW technique b i ^( ) Roots of B q give “spurious” roots. 1997 Slide L5–12 . n ^ k Lecture notes to accompany Introduction to Spectral Analysis by P. Moses.

Lecture notes to accompany Introduction to Spectral Analysis by P. Prentice Hall. . r(L + M . i) = 0 k > L In matrix form for k 2 6 6 6 4 | = L + 1 ::: L + M 3 7 7 7 5 2 6 6 6 4 3 7 7 7 5 } : : : r(1) r(L + 1) : : : r(2) b = . Moses.High-Order and Overdetermined YW Equations ARMA covariance: r (k ) + X L i=1 bir(k . r(L + 2) . . . . Stoica and R. 1) : : : r(M ) r(L + M ) 4 4 = = {z } | {z r(L) r(L + 1) This is a high-order (if L > n) and overdetermined (if M > L) system of YW equations. . 1997 Slide L5–13 .

High-Order and Overdetermined YW Equations. Stoica and R. diagonal and nonsingular Thus.V . Lecture notes to accompany Introduction to Spectral Analysis by P. The Minimum-Norm solution is b = . 1997 Slide L5–14 . if the Minimum-Norm solution b is used. con't Fact: SVD of rank : ( )=n =U V U = (M n) with U U = In V = (n L) with V V = In = (n n). n) spurious zeros of B (q ) are located strictly inside the unit circle. (U V )b = .1U Important property: The additional (L . y = . Prentice Hall. Moses.

Prentice Hall. V be defined similarly to U . . Compute ^ = . Moses. Stoica and R. 1997 Slide L5–15 . f^ g When the SNR is low.HOYW Equations. SVD of .1U ^ ^ ^ b ^(q) that Then !k n=1 are found from the n zeroes of B k are closest to the unit circle.V ^ . this is the price paid for increased accuracy when L > n. V from the Let U . r . Lecture notes to accompany Introduction to Spectral Analysis by P. Practical Solution Let ^= ^ ^ ^ ^ but made from f^(k)g instead of fr(k)g. this approach may give spurious frequency estimates when L > n.

Moses. 1997 Slide L6–1 .Parametric Methods for Line Spectra — Part 2 Lecture 6 Lecture notes to accompany Introduction to Spectral Analysis by P. Prentice Hall. Stoica and R.

Prentice Hall.. 1) (for m 3 7 7 7 5 n) 2 46 y(t) = 6 ~ 6 4 y(t .The Covariance Matrix Equation Let: a(!) = 1 e. .1)! ]T A = a(!1) : : : a(!n)] (m n) rank Note: Define (A) = n y(t) y(t .. 0 2 n 3 7 5 Lecture notes to accompany Introduction to Spectral Analysis by P. Moses. Stoica and R. = Ax(t) + ~(t) ~ e where x(t) = x1(t) : : : xn(t)]T ~ ~(t) = e(t) : : : e(t .i! : : : e. 1997 Slide L6–2 . m + 1) . m + 1)]T e 4 R = E fy(t)~ (t)g = APA + 2I ~ y Then with 2 P = E fx(t)~ (t)g = ~ x 6 4 2 1 0 .i(m.

Moses. n)) Thus.n] (m (m .. Prentice Hall.. 1997 Slide L6–3 .Eigendecomposition of R and Its Properties R = APA + 2I (m > n) Let: 1 2 ::: m: eigenvalues of R fs1 : : : sng: orthonormal eigenvectors associated with f 1 : : : ng fg1 : : : gm. m 7 5 S G # Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R.ng: orthonormal eigenvectors associated with f n+1 : : : m g S = s1 : : : sn] (m n) G = g1 : : : gm. 2 R = S G] 6 4 1 3 " .

=0 A G=0 Slide L6–4 Lecture notes to accompany Introduction to Spectral Analysis by P. Therefore.Eigendecomposition of R and Its Properties.1) = AC S = A(PA S ( ) = rank(A) = n). since S G j j 6= 0 4 . Prentice Hall. Stoica and R.. = = nonsingular 0 n. 2 2 6 4 3 7 5 2 6 4 Note: RS = APA S + 2S = S 1 0 . . Moses. 0 n 3 7 5 with C (since rank S . 1997 ... 2 . con't As rank (APA ) = n: k > 2 k = 1 ::: n k = 2 k = n + 1 ::: m 0 1.

A G= G=0 a (!n) ) fa(!k )gn=1 ? R(G) k 2 6 4 3 7 5 Thus. Prentice Hall. 1997 Slide L6–5 . Moses. Stoica and R.MUSIC Method a (!1) . f!kgn=1 are the unique solutions of k a (!)GG a(!) = 0. Let: 1 N y(t)~ (t) ^ ~ y R = N t=m ^^ S G = S G made from the ^ eigenvectors of R X Lecture notes to accompany Introduction to Spectral Analysis by P. .

Stoica and R.1)]T Note: Both variants of MUSIC may produce spurious frequency estimates. Moses. Prentice Hall.1 : : : z.1)GG a(z) = 0 that are closest to the unit circle.Spectral and Root MUSIC Methods Spectral MUSIC Method: f!kgn=1 = the locations of the n highest peaks of the ^ k “pseudo-spectrum” function: 1 ^G a(!) ! 2 . 1997 Slide L6–6 . Lecture notes to accompany Introduction to Spectral Analysis by P. Here. a (!)G ^ Root MUSIC Method: ] f!kgn=1 = the angular positions of the n roots of: ^ k ^^ aT (z. a(z) = 1 z.(m.

1)^1 = 0 g no problem with spurious frequency estimates computationally simple (much) less accurate than MUSIC with m n+1 Lecture notes to accompany Introduction to Spectral Analysis by P.Pisarenko Method Pisarenko is a special case of MUSIC with m (the minimum possible value). Moses. Stoica and R. Prentice Hall. ) f!kgn=1 can be found from the roots of ^ k aT (z. 1997 Slide L6–7 . If: =n+1 m=n+1 Then: ^ g G = ^1.

but only one vector in G (as in Pisarenko). with first element equal ^ ^ to one. that has minimum Euclidean norm. Uses m n (as in MUSIC). g # Lecture notes to accompany Introduction to Spectral Analysis by P. Moses. Stoica and R. and reduce risk of false frequency estimates. Prentice Hall. 1997 Slide L6–8 .Min-Norm Method Goals: Reduce computational burden. R( ) Let " 1 = the vector in R(G).

Prentice Hall. Stoica and R.1) 1 ^ g " # that are closest to the unit circle.Min-Norm Method. Lecture notes to accompany Introduction to Spectral Analysis by P. con't Spectral Min-Norm f!gn=1 = ^k the locations of the n highest peaks in the “pseudo-spectrum” 2 1 = a (!) 1 ^ g " # Root Min-Norm f!gn=1 = ^k the angular positions of the n roots of the polynomial aT (z. Moses. 1997 Slide L6–9 .

k k2) ) ^ = .S(S S ). Moses.S =(1 . k k2) g Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R. Prentice Hall.1 gm " # " # Min-Norm Method: Determining g ^ Then: 1 2 R(G) ) S 1 = 0 ^ ^ ^ ^ g g ) S ^= . for N 1. k k2) = (S S ) ) (S S ). (S S ).Let S ^= S g1 .1 = =(1 . at least.1 exists iff = k k2 6= 1 (This holds.1 g + S S . g " # Min-Norm solution: As: ^ = . 1997 Slide L6–10 .) ^^ I=S S= Multiplying the above equation by gives: (1 .

Prentice Hall.1 0]S S2 = 0 Im. Then S2 = A2C = A1DC = S1 C .i!n S1 = Im.1]A Then A2 Also. Moses. D= 0 e.1DC {z } So has the same eigenvalues as D . Stoica and R.ESPRIT Method Let A1 = Im. determined as is uniquely = (S1S1). 1997 Slide L6–11 ..1S1S2 Lecture notes to accompany Introduction to Spectral Analysis by P.1]S 2 6 4 | 3 7 5 Recall S = AC with jC j 6= 0.1 0]A A2 = 0 Im.i!1 0 . where e.. let = A1D.

ESPRIT Implementation From the eigendecomposition of R. ^ ^ ^ ^ The frequency estimates are found by: where f^kgn=1 are the eigenvalues of k ^ = (S1S1). Stoica and R. arg(^k ) ^ k ESPRIT Advantages: computationally simple no extraneous frequency estimates (unlike in MUSIC or Min–Norm) accurate frequency estimates Lecture notes to accompany Introduction to Spectral Analysis by P. Prentice Hall. find S . Moses.1S1S2 ^^ ^^ f!kgn=1 = . then S1 and S2 . 1997 Slide L6–12 .

Prentice Hall. Stoica and R. Moses. 1997 .Summary of Frequency Estimation Methods Method Periodogram Nonlinear LS Yule-Walker Pisarenko MUSIC Min-Norm ESPRIT Computational Accuracy / Risk for False Burden Resolution Freq Estimates small medium-high medium very high very high very high medium high medium small low none high high medium medium high small medium very high none Recommendation: Use Periodogram for medium-resolution applications Use ESPRIT for high-resolution applications Slide L6–13 Lecture notes to accompany Introduction to Spectral Analysis by P.

Moses. 1997 Slide L7–1 . Stoica and R.Filter Bank Methods Lecture 7 Lecture notes to accompany Introduction to Spectral Analysis by P. Prentice Hall.

by assuming that ! is nearly constant over the bands f ( )g ( ) !. !+ ] N >1 1 2 is more general than 1.Basic Ideas Two main PSD estimation approaches: 1. Prentice Hall. 1997 Slide L7–2 . Moses. (!) by a 2. Lecture notes to accompany Introduction to Spectral Analysis by P. Parametric Approach: Parameterize finite-dimensional model. Stoica and R. ( =2 2 =1 N > 1 leads to the variability / resolution compromise associated with all nonparametric methods. but 2 requires to ensure that the number of estimated values = = ) is < N . Nonparametric Approach: Implicitly smooth ! !=.

jH ( )j2 ( )d = ' 21 !+ !. 1997 . Z 6 ~ (! ) @ -! (b) Z !c ^FB (!) ' 1 2 (a) . Slide L7–3 Lecture notes to accompany Introduction to Spectral Analysis by P. !c @Q Q -! .with varying ! Power Calculation Bandpass Filter c and xed bandwidth - Power in the band - Division by lter bandwidth ^(!c ) - 6 y y (! ) . are conflicting. Prentice Hall. Stoica and R. Moses. 2 ! + 2 ] Note that assumptions (a) and (b). c ( )d = (') (!) (a) consistent power calculation (b) Ideal passband filter with bandwidth (c) ( ) constant on 2 ! . as well as (b) and (c).Filter Bank Approach to Spectral Estimation H 6 (!) 1 !c -! Filtered Signal y (t) .

1997 .Filter Bank Interpretation of the Periodogram 1 N y(t)e.!) . 1 H (!) = hk e ! N ei(~. Moses.t) t=1 X X = N where ( X 1 k=0 hk y(N .i!k = 1 eiN (~. Stoica and R.i!t 2 ~ ^p(~) = ! 4 N t=1 2 N 1 ~ = N y(t)ei!(N . Prentice Hall.!) . 1 ~ hk = N otherwise 0 1 center frequency of H 3dB bandwidth of H (!) = ! ~ (!) ' 1=N Slide L7–4 Lecture notes to accompany Introduction to Spectral Analysis by P. 1 k=0 X 1 ei!k k = 0 : : : N . k) 2 ! .

^( ) Lecture notes to accompany Introduction to Spectral Analysis by P. 1997 Slide L7–5 .Filter Bank Interpretation of the Periodogram. Stoica and R. !). con't jH (!)j as a function of (~ . power calculation from only 1 sample of filter output. ! 0 −5 −10 −15 dB −20 −25 −30 −35 −40 −3 −2 −1 0 1 ANGULAR FREQUENCY 2 3 Conclusion: The periodogram p ! is a filter bank PSD estimator with bandpass filter as given above. Moses. for N = 50. Prentice Hall. and: narrow filter passband.

Stoica and R. This “multiwindow approach” is similar to the Daniell method. This approach leads to Bartlett and Welch methods. Both approaches compromise bias for variance. Split the available sample. 2. ~ provides several samples for power calculation. more data points for the power calculation stage. Use several bandpass filters on the whole sample. Each filter covers a small band centered on ! . Moses. and bandpass filter each subsample. 1997 Slide L7–6 . Lecture notes to accompany Introduction to Spectral Analysis by P.Possible Improvements to the Filter Bank Approach 1. Prentice Hall. and in fact are quite related to each other: splitting the data sample can be interpreted as a special form of windowing or filtering.

m) h y(t) ~ E jyF (t)j2 = h Rh R = E fy(t)~ (t)g ~ y {z } 7 5 {z } n o y(t) 3 H (! ) = where a X m (! ) = 1 k=0 e. = h0 h1 : : : hm] . Stoica and R. k) 2 6 4 | .i!k = h a(!) Lecture notes to accompany Introduction to Spectral Analysis by P. yF (t) = X m k=0 | hk y(t .Capon Method Idea: Data-dependent bandpass filter design. 1997 Slide L7–7 . Prentice Hall. y(t .im! ]T hk e.i! : : : e. Moses.

1997 Slide L7–8 .1 a (!)R a(!) with N 1 ^ y(t)~ (t) ~ y R = N .Capon Method.1a=a R.1a o The power at the filter output is: E jyF (t)j2 = h0Rh0 = 1=a (!)R. con't Capon Filter Design Problem: min(h Rh) h Solution: subject to h a(!) = 1 h0 = R.1a(!) which should be the power of y (t) in a passband centered on ! .m t=m+1 X Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R. n The Bandwidth 1 ' m+1 = (filter 1 length) Conclusion Estimate PSD as: +1 ^(!) = m^. Prentice Hall. Moses.

Stoica and R. but it splits the N -data point sample into (N m) subsequences of length m with maximum overlap. . Moses. Prentice Hall. bias decreases and variance increases. 1997 Slide L7–9 . Capon uses one bandpass filter only. Lecture notes to accompany Introduction to Spectral Analysis by P.Capon Properties m is the user parameter that controls the compromise between bias and variance: – as m increases.

Relation between Capon and Blackman-Tukey Methods Consider ^BT (!) with Bartlett window: m m + 1 .i!(t.s) = m+1 r t=0 s=0 ^ a (!)Ra(!) R = ^(i .i!k ^ k=. j )] ^ r = m+1 X X X Then we have ^ a (!)Ra(!) ^BT (!) = m+1 m+1 ^C (!) = ^ a (!)R.m m + 1 1 m m ^(t . Moses.1a(!) Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R. Prentice Hall. s)e. 1997 Slide L7–10 . jkj ^BT (!) = r(k)e.

^( ) ^( ) Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R. C ! generally has less statistical variability than the AR PSD estimator.Relation between Capon and AR Methods Let 2 ^k ^k (!) = ^ 2 jAk(!)j be the kth order AR PSD estimate of y (t). AR Then ^C (!) = 1 1 m 1= ^AR(!) m + 1 k=0 k X Consequences: Due to the average over k. Due to the low-order AR terms in the average. 1997 Slide L7–11 . Prentice Hall. C ! generally has worse resolution and bias properties than the AR method. Moses.

1997 Slide L8–1 . Prentice Hall.Spatial Methods — Part 1 Lecture 8 Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R. Moses.

@.. Sensor 2 Sensor m Problem: Detect and locate n radiating sources by using an array of m passive sensors. electromagnetic. communications. 1997 Slide L8–2 . . Sensor 1 @.@ .. Prentice Hall. @. underwater surveillance Basic Approach: Determine energy distribution over space (thus the name “spatial spectral analysis”) Lecture notes to accompany Introduction to Spectral Analysis by P. sonar. @. . seismology. seismometers Applications: Radar. Emitted energy: Acoustic. Stoica and R.. v Source n @. @. antennas. .R . mechanical Receiving sensors: Hydrophones. . Moses.The Spatial Spectral Estimation Problem Source 1 vSource 2 B B B B N B cccc ccc c c c c c v @ .@ . @.

Stoica and R. AOA).) Lecture notes to accompany Introduction to Spectral Analysis by P. (We do not treat the detection problem) The sensors are linear dynamic elements with known transfer characteristics and known locations (That is. Prentice Hall.Simplifying Assumptions Far-field sources in the same plane as the array of sensors Non-dispersive wave propagation Hence: The waves are planar and the only location parameter is direction of arrival (DOA) (or angle of arrival. 1997 Slide L8–3 . The number of sources n is known. Moses. the array is calibrated.

thermal noise in sensor electronics. Moses. at the “first” sensor) the delay between the reference point and the kth sensor the impulse response (weighting function) of sensor k “noise” at the kth sensor (e. Basic Problem: Estimate the time delays known but x t unknown. Then the output of sensor k is yk (t) = hk (t) x(t .) hk (t) = ek (t) = Note: t 2 R (continuous-time signals). k) + ek (t) ( = convolution operator).g...g. () f kg with hk(t) This is a time-delay estimation problem in the unknown input case. 1997 Slide L8–4 . etc.Array Model — Single Emitter Case x(t) = k= the signal waveform as measured at a reference point (e. Prentice Hall. background noise. Stoica and R. Lecture notes to accompany Introduction to Spectral Analysis by P.

Prentice Hall. k) ' (t) '(t . !c k ] hk (t) x(t . 1997 . k ) ' jHk (!c)j (t)cos !ct + '(t) . !c k + argfHk (!c)g] where Hk function (!) = Ffhk(t)g is the kth sensor's transfer Hence. Moses.Narrowband Assumption Assume: The emitted signals are narrowband with known carrier frequency !c . k ) ' (t) cos !ct + '(t) . Then: x(t) = (t) cos !ct + '(t)] where (t) '(t) vary “slowly enough” so that (t . the kth sensor output is yk (t) = jHk (!c)j (t) cos !ct + '(t) . !c k + arg Hk (!c)] + ek(t) Slide L8–5 Lecture notes to accompany Introduction to Spectral Analysis by P. k ) ' '(t) Time delay is now ' to a phase shift !c k : x(t . Stoica and R.

Prentice Hall.i! + ek (t) | s(t) {z } | Hk (!c) {z k c } c k yk (t) = s(t)Hk (!c) e.Complex Signal Representation The noise-free output has the form: z(t) = (t) cos !ct + (t)] = = (t) ei !ct+ (t)] + e.i!ct to obtain (t)ei (t) lowpass highpass Hence. Moses. by low-pass filtering and sampling the signal yk (t)=2 = yk(t)e. Lecture notes to accompany Introduction to Spectral Analysis by P.i!ct ~ = yk(t) cos(!ct) .i 2!ct+ (t)] g n o | {z } | {z } Lowpass filter 2z(t)e.i !ct+ (t)] 2 Demodulate z (t) (translate to baseband): 2z(t)e.!ct = (t)f ei (t) + e. iyk(t) sin(!ct) we get the complex representation: (for t 2 Z ) yk (t) = (t) ei'(t) jHk (!c)j ei arg H (! )] e. Stoica and R.i!c k + ek (t) where s(t) is the complex envelope of x(t). 1997 Slide L8–6 or .

Vector Representation for a Narrowband Source

Let

= m =
a( ) =
2 6 4

the emitter DOA the number of sensors
2 6 4

H1(!c) e;i!c
. .

1

3 7 5

Hm(!c) e;i!c m y1(t) e1(t) . . y(t) = e(t) = . . ym(t) em(t)
3 7 5 2 6 4

3 7 5

Then

y(t) = a( )s(t) + e(t)
NOTE: enters a via both For omnidirectional sensors the on .

()

f kg and fHk(!c)g. fHk(!c)g do not depend

Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R. Moses, Prentice Hall, 1997

Slide L8–7

Analog Processing Block Diagram

Analog processing for each receiving array element
SENSOR DEMODULATION

A/D CONVERSION

-

-

Internal Noise External Noise XXXXX ? XX ll z l - Cabling and , Filtering : ,, Incoming Transducer Signal x(t ; k )

Re yk (t)] Lowpass Re yk (t)] - !! ~ Filter A/D cos(!ct) 6 y k (t) Oscillator -sin(!ct) ? ~ - Im yk (t)] Lowpass Im yk (t)] - !! Filter A/D

-

Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R. Moses, Prentice Hall, 1997

Slide L8–8

Multiple Emitter Case Given n emitters with received signals: DOAs:

fsk(t)gn=1 k

k

Linear sensors

) y(t) = a( 1)s1(t) +

+ a( n)sn(t) + e(t)

Let

A = a( 1) : : : a( n)] (m n) s(t) = s1(t) : : : sn(t)]T (n 1)
Then, the array equation is:

y(t) = As(t) + e(t)
Use the planar wave assumption to find the dependence of k on .
Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R. Moses, Prentice Hall, 1997 Slide L8–9

Stoica and R. Moses. 1997 Slide L8–10 . 1) c Lecture notes to accompany Introduction to Spectral Analysis by P. Prentice Hall.Uniform Linear Arrays Source h JJ J J J J JJ J ^ J J JJ JJ+ JJ JJ 2 ] J d sin J ^ JJ J JJ 3 J J v 4 1 v ]? v d - v ppp m vSensor ULA Geometry Sensor #1 = time delay reference Time Delay for sensor k: where c = wave propagation speed d sin k = (k .

Spatial Frequency Let: sin 4 !s = !c d sin = 2 dc=f = 2 d sin c c = c=fc = signal wavelength a( ) = 1 e. Slide L8–11 d = spatial sampling period Lecture notes to accompany Introduction to Spectral Analysis by P. 1997 . Stoica and R. Moses.i!s : : : e. !s = spatial frequency The function !s 7! a( ) is one-to-one for j!sj $ dj sin j 1 d =2 As =2 d =2 is a spatial Shannon sampling theorem.i(m. Prentice Hall.1)!s ]T By direct analogy with the vector a(! ) made from uniform samples of a sinusoidal time series.

Spatial Methods — Part 2 Lecture 9 Lecture notes to accompany Introduction to Spectral Analysis by P. 1997 Slide L9–1 . Moses. Prentice Hall. Stoica and R.

1997 Slide L9–2 . Stoica and R. Lecture notes to accompany Introduction to Spectral Analysis by P. Prentice Hall.Spatial Filtering Spatial filtering useful for DOA discrimination (similar to frequency discrimination of time-series filtering) Nonparametric DOA estimation There is a strong analogy between temporal filtering and spatial filtering. Moses.

k) = h y(t) k=0 h = ho : : : hm. Moses. Lecture notes to accompany Introduction to Spectral Analysis by P.Analogy between Temporal and Spatial Filtering Temporal FIR Filter: yF (t) = hk u(t .i! : : : e. m + 1)]T If u m.1 X (t) = ei!t then yF (t) = h a(!)] u(t) | {z } filter transfer function a(!) = 1 e.i(m.1)! ]T We can select h to enhance or attenuate signals with different frequencies ! .1] y(t) = u(t) : : : u(t . 1997 Slide L9–3 . Stoica and R. Prentice Hall.

Analogy between Temporal and Spatial Filtering Spatial Filter: fyk(t)gm=1 = k the “spatial samples” obtained with a sensor array. Stoica and R. Lecture notes to accompany Introduction to Spectral Analysis by P. 1997 Slide L9–4 . Prentice Hall. Spatial FIR Filter output: yF (t) = X m k=1 hk yk (t) = h y(t) Narrowband Wavefront: The array's (noise-free) response to a narrowband ( sinusoidal) wavefront with complex envelope s t is: () y(t) = a( )s(t) a( ) = 1 e. Moses.i!c m ]T yF (t) = h a( )] s(t) | {z } The corresponding filter output is filter transfer function We can select h to enhance or attenuate signals coming from different DOAs.i!c 2 : : : e.

@ 0 B 1 C h @@ C B B e.B ..1 ? - 1 . 1997 Slide L9–5 . B . Prentice Hall.i! C @ h a(!)]u(t) R @ C . Cu(t) C B . ? qq 1 ! (Spatial sampling) (b) Spatial filter Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R. s qq h - ? 1 ? - m. Moses. B B @ . C C B C B C B C B C B A @ ..? B -P C B C B B B .1 q .Analogy between Temporal and Spatial Filtering u(t) = ei!t z 1 s q.i! m | e {z a( ) aa m! point ( ) qq ( ) 1 C C C C C Cs(t) C C C C C A } - ? @ ? @ @ h - 1 @ R @ - P h a( )]s(t) - hm.i! Be 2 B !! B B B B .i m. ! hm. | e {z } ? a(!) 1 ? 0 qq ( 1) 1 (Temporal sampling) (a) Temporal filter narrowband source with DOA= Z z Z Z Z ~ aa 1reference !! h 0 0 1 B aa 2.

where 0 j ( )j = ( ) = 25 0 30 −30 Th et a (d eg ) 60 −60 90 0 2 4 6 Magnitude 8 10 −90 Lecture notes to accompany Introduction to Spectral Analysis by P. con't Example: The response magnitude h a of a spatial filter (or beamformer) for a 10-element ULA. Stoica and R. h a 0 . Here. 1997 Slide L9–6 . Prentice Hall. Moses.Spatial Filtering.

Prentice Hall. Stoica and R. To locate an emitter in the field of view. Lecture notes to accompany Introduction to Spectral Analysis by P. by sweeping the filter through the DOA range of interest (“goniometer”). Moses. hence filtering out interferences located outside the filter's beam (but possibly having the same temporal characteristics as the signal).Spatial Filtering Uses Spatial Filters can be used To pass the signal of interest only. 1997 Slide L9–7 .

Basic Ideas Design a filter h ( ) such that for each – It passes undistorted the signal with DOA = – It attenuates all DOAs 6= Sweep the filter through the DOA range of interest. 1997 . n o n o The (dominant) peaks of h DOAs of the sources. Moses. and evaluate the powers of the filtered signals: E jyF (t)j2 = E jh ( )y(t)j2 = h ( )Rh( ) with R = E fy (t)y (t)g. Stoica and R. ( )Rh( ) give the Slide L9–8 Lecture notes to accompany Introduction to Spectral Analysis by P.Nonparametric Spatial Methods A Filter Bank Approach to DOA estimation. Prentice Hall.

Beamforming Method Assume the array output is spatially white: Then: R = E fy(t)y (t)g = I E jyF (t)j2 = h h n o Hence: In direct analogy with the temporally white assumption for filter bank methods. Moses. y t can be considered as impinging on the array from all DOAs. Stoica and R. () Filter Design: min (h h) h Solution: subject to h a( ) = 1 h = a( )=a ( )a( ) = a( )=m E jyF (t)j2 = a ( )Ra( )=m2 n o Lecture notes to accompany Introduction to Spectral Analysis by P. Prentice Hall. 1997 Slide L9–9 .

Prentice Hall. but Slide L9–10 Lecture notes to accompany Introduction to Spectral Analysis by P. 1997 . Resolution Threshold: inf j k . Stoica and R. 1 = 1. pj > = wavelength array length array beamwidth Inconsistency problem: Beamforming DOA estimates are consistent if n inconsistent if n > . ( )^ ( ) This is the direct spatial analog of the Blackman-Tukey periodogram. Moses.Implementation of Beamforming 1 N y(t)y (t) ^ R=N t=1 X The beamforming DOA estimates are: f^kg = the locations of the n largest peaks of a Ra .

They do not make assumptions on the covariance properties of the data (and hence do not depend on them). Both Beamforming and Capon are nonparametric approaches. Prentice Hall. Lecture notes to accompany Introduction to Spectral Analysis by P.1a( ): Performance: Slightly superior to Beamforming.1a( )=a ( )R.1a( ) E jyF (t)j2 = 1=a ( )R. 1997 Slide L9–11 .1a( ) n o Implementation: f^kg = the locations of the n largest peaks of ^ 1=a ( )R.Capon Method Filter design: min(h Rh) subject to h a( ) = 1 h Solution: h = R. Stoica and R. Moses.

MUSIC. almost without modification. Moses. Stoica and R. MIN-NORM and ESPRIT methods of frequency estimation can be used. 1997 Slide L9–12 .Parametric Methods Assumptions: The array is described by the equation: y(t) = As(t) + e(t) The noise is spatially white and has the same power in all sensors: E fe(t)e (t)g = 2I The signal covariance matrix P = E fs(t)s (t)g is nonsingular. YW. Then: R = E fy(t)y (t)g = APA + 2I Thus: The NLS. Prentice Hall. for DOA estimation. Lecture notes to accompany Introduction to Spectral Analysis by P.

1A ]Rg X f kg For N . this is precisely the form of the NLS method of frequency estimation. f ^k g = arg max trf A(A A).1A y(t) t = 1 : : : N s X Then 1 N k I . Stoica and R. As(t)k2 min(t)g N f k g fs t=1 X | Minimizing f over s gives f ( s) {z } ^(t) = (A A). Prentice Hall. A(A A). A(A A).1A ]Rg ^ Thus.1A ]y(t)k2 f ( ^) = N s t=1 1 N y (t) I . A(A A).Nonlinear Least Squares Method 1 N ky(t) . Moses. 1997 Slide L9–13 =1 . Lecture notes to accompany Introduction to Spectral Analysis by P.1A ]y(t) = N t=1 ^ = trf I .

Prentice Hall. Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R.Nonlinear Least Squares Method Properties of NLS: Performance: high Computational complexity: high Main drawback: need for multidimensional search. 1997 Slide L9–14 . Moses.

Yule-Walker Method e y(t) = y(t) = A s(t) + ~(t) ~ y(t) ~ e(t) A " # " # " # Assume: Then: E fe(t)~ (t)g = 0 e 4 E fy(t)~ (t)g = AP A ~ . Stoica and R.) = n. = U1 U2 ] 0 n n 0 V1 g n .n ~ ~ Properties: A V2 = 0 V1 2 R(A) Then: rank |{z} |{z} Lecture notes to accompany Introduction to Spectral Analysis by P. is .n 0 V2 g L n M . and the SVD of . Moses. 1997 Slide L9–15 .= y (M L) Also assume: M > n L > n ( ) m = M + L > 2n) rank ~ (A) = rank(A) = n " # " # (. Prentice Hall.

YW-MUSIC DOA Estimator f^kg = where the n largest peaks of 1=~ ( )V2V2 ~( ) a ^^a ~( ). Moses.=N y t=1 X Properties: Computational complexity: medium Performance: satisfactory if m 2n Main advantages: – weak assumption on e t – the subarray A need not be calibrated f ( )g Lecture notes to accompany Introduction to Spectral Analysis by P. (L 1). using 1 N y(t)~ (t) ^ . is the “array transfer vector” for y(t) a ~ at DOA ^ V2 is defined similarly to V2. 1997 Slide L9–16 . Stoica and R. Prentice Hall.

1997 Slide L9–17 . that is. Lecture notes to accompany Introduction to Spectral Analysis by P.MUSIC and Min-Norm Methods Both MUSIC and Min-Norm methods for frequency estimation apply with only minor modifications to the DOA estimation problem. Spectral forms of MUSIC and Min-Norm can be used for arbitrary arrays Root forms can be used only with ULAs MUSIC and Min-Norm break down if the source signals are coherent. Moses. if rank (P ) = rank(E fs(t)s (t)g) < n Modifications that apply in the coherent case exist. Prentice Hall. Stoica and R.

Lecture notes to accompany Introduction to Spectral Analysis by P. 1997 Slide L9–18 ( ) = d sin( )=c .ESPRIT Method Assumption: The array is made from two identical subarrays separated by a known displacement vector. where e. Moses..i!c ( 1) 0 . Stoica and R.. Prentice Hall. Let m = # sensors in each subarray A1 = Im 0]A (transfer matrix of subarray 1) A2 = 0 Im]A (transfer matrix of subarray 2) Then A2 = A1D.i!c ( n) ( ) = the time delay from subarray 1 to 2 6 4 3 7 5 subarray 2 for a signal with DOA = : where d is the subarray separation and is measured from the perpendicular to the subarray displacement vector. D= 0 e.

1 . Prentice Hall. so m m and . con't ESPRIT Scenario source θ known subarray 1 displac ement v ector subarray 2 Properties: Requires special array geometry Computationally efficient No risk of spurious DOA estimates Does not require array calibration Note: For a ULA. Moses.1]A Lecture notes to accompany Introduction to Spectral Analysis by P.1 0]A = . the two subarrays are often the first m and last m array elements.1 A1 = Im.ESPRIT Method. 1997 Slide L9–19 . Stoica and R.1 A2 = 0 Im.

Master your semester with Scribd & The New York Times

Special offer for students: Only $4.99/month.

Master your semester with Scribd & The New York Times

Cancel anytime.