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

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

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

Random Signals Random Signal random signal probabilistic statements about future variations t current observation time Here: X 1 t=. Stoica and R. 1997 Slide L1–6 . Moses. Prentice Hall.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.

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

Prentice Hall.Second Definition of PSD 1 N y(t)e. Moses.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. t=1 y(t)e. Stoica and R. 1997 Slide L1–8 .i!t Lecture notes to accompany Introduction to Spectral Analysis by P.

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

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

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

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

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). Prentice Hall. 1997 Slide L2–2 .Periodogram Recall 2nd definition of (! ): 1 N y(t)e. Stoica and R.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. Moses.

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

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

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

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

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

Moses. (!) may differ quite a bit from (!). 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 . Slide L2–8 Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R. 1997 .Bartlett Window WB (! ) 1 sin(!N=2) 2 WB (!) = N sin(!=2) " # 0 WB (!)=WB (0). WB 1=N . Prentice Hall.

Smearing and Leakage Main Lobe Width: smearing or smoothing Details in resolvable. Prentice Hall. 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 . Moses. ^ 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. Stoica and R. 1997 Slide L2–9 .

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

(!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. (!1) ^p(!2) . Moses. Prentice Hall. 1997 Slide L2–11 . Stoica and R. Lecture notes to accompany Introduction to Spectral Analysis by P. dev = φ(ω) too - Resolvability properties depend on both bias and variance.Periodogram Variance As N !1 E ^p(!1) .

Moses. Prentice Hall.i 2 . 1997 Slide L2–12 . 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.i!t 2 k and W = e.Discrete Fourier Transform (DFT) Finite DTFT: YN (!) = X N t=1 y(t)e. Stoica and R. 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 .

1997 .1 for odd k Assume: X X X Let N For k ~ ~ = N=2 and W = W 2 = e. Stoica and R.i2 =N . Slide L2–13 t=1 ~ ~ f y(t) . Prentice Hall. Moses. y(t + N )]W tgW tp Lecture notes to accompany Introduction to Spectral Analysis by P.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 = . 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. 2 = 2p: Y (2p) = For k X ~ N = 1 3 5 : : : N . ~ 4 = 0 2 4 : : : N .

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

1997 Slide L2–15 .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 . Moses.1 N k=0 sampled. N=8 ω 2 k N . Stoica and R.1 ! N k=0 ^ φ(ω) continuous curve Lecture notes to accompany Introduction to Spectral Analysis by P. Prentice Hall.

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

with small weight applied to covariances r k with “large” k .(M .Blackman-Tukey Method Basic Idea: Weighted correlogram. Stoica and R. ^( ) jj ^BT (!) = M . Prentice Hall.1 X k=. Moses. 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.1) w(k)^(k)e.

Blackman-Tukey Method. con't ^BT (!) = 1 ^p( )W (! . 1997 . Prentice Hall. Stoica and R. Moses. )d 2 . 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.

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

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

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. Moses. Prentice Hall. M 0 = 25 −10 −20 dB −30 −40 −50 −60 −3 −2 −1 0 1 ANGULAR FREQUENCY 2 3 Rectangular Window. Stoica and R. 1997 Slide L3–6 .Window Examples Triangular Window.

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

Daniell Method By a previous result. k +J 1 ^D(!k ) = ^p (!j ) 2J + 1 j=k. 1997 Slide L3–10 . Stoica and R. for N 1. f ^p(!j )g are (nearly) uncorrelated random variables for 2 j N . Moses. Prentice Hall.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.

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

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

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

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

and ARMA Models By Spectral Factorization theorem. 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. e.1 + + bmz.g. Prentice Hall.AR.1 + + anz. MA. a rational factored as (!) can be B (!) 2 2 (!) = A(!) A(z) = 1 + a1z. Stoica and R.m and. Moses. 1997 ..n B (z) = 1 + b1z.

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

.AR Signals: Yule-Walker Equations AR: m = 0. 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 (. Stoica and R. .1) : : : r(. 1997 Slide L4–5 . . . Lecture notes to accompany Introduction to Spectral Analysis by P. Prentice Hall. 2 1 a1 = 0 . . . r(1) r(0) .n) . Moses. 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.

Moses. . . . Stoica and R. r ^(1) r(0) ^ ^.1) : : : ^(. 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. ^(. r .1 = 0 a . .n) 1 r r ^2 . 1997 Slide L4–6 . . . Prentice Hall.1) .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.1(Y y) where 3 7 5 2 6 t=n+1 je(t)j2 y(1) y(2) y(N . 1) : : : y (t . 1997 Slide L4–7 . 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 ) . 3 7 5 Y =4 y(n) y(n . n) . Find i=1 aiy(t . . 1) y(n + 1) y(n) . . . 1) y(N .AR Spectral Estimation: LS Method Least Squares Method: e(t) = y(t) + X n 4 = y(t) + y(t) ^ where '(t) = y (t . y(N . . n)]T . ^ = . . . Prentice Hall. Stoica and R.(Y Y ). 2) Lecture notes to accompany Introduction to Spectral Analysis by P.

n .. .1 1 . .. {z .1 .n .0 . Prentice Hall. . .Levinson–Durbin Algorithm Fast. . 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). 1997 Slide L4–8 .. 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 . Direct Solution: For one given value of n: For k Rn+1 1 0 = 0 . Moses.. .. Stoica and R.

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

2 kn = .Levinson-Durbin Alg. Stoica and R. 1997 . Prentice Hall. n = n ) n+1 = 0 + kn 2+1 = n + kn n = n(1 . Moses. 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. 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.

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

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

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

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

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

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

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

Prentice Hall.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. Moses. 1997 Slide L4–18 . Stoica and R.

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

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 . Prentice Hall. 1997 . Moses. Stoica and R. !1 !2 !3 - An “Ideal” line spectrum Lecture notes to accompany Introduction to Spectral Analysis by P. Examples: communications radar.Line Spectra Many applications have signals with (near) sinusoidal components.

Stoica and R.Line Spectral Signal Model Signal Model: Sinusoidal components of frequencies !k and powers 2 . ] (prevents model ambiguities) f'k g = independent rv's. ] (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. Moses. uniformly distributed on . 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 . 1997 . Prentice Hall. superimposed in white noise of k 2.

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

^ ei!k t + residuals k Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R.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 . Moses. Prentice Hall. 1997 Slide L5–5 .

. Stoica and R. . 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 . . B = eiN!1 eiN!n k 2 6 4 3 7 5 Lecture notes to accompany Introduction to Spectral Analysis by P. Moses. Prentice Hall.

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

Moses. Stoica and R. it is difficult to avoid convergence to local minima. ! Difficult Implementation: The NLS cost function F is multimodal.5.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 . Prentice Hall. 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

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

. 1997 Slide L5–13 . .High-Order and Overdetermined YW Equations ARMA covariance: r (k ) + X L i=1 bir(k . Prentice Hall. . 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 = . . r(L + 2) . Lecture notes to accompany Introduction to Spectral Analysis by P. Stoica and R. Moses. 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. r(L + M . .

1U Important property: The additional (L . Stoica and R.V . 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). diagonal and nonsingular Thus. if the Minimum-Norm solution b is used. Lecture notes to accompany Introduction to Spectral Analysis by P. y = . The Minimum-Norm solution is b = . Moses.High-Order and Overdetermined YW Equations. n) spurious zeros of B (q ) are located strictly inside the unit circle. 1997 Slide L5–14 . (U V )b = . Prentice Hall.

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

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

i(m. 1) (for m 3 7 7 7 5 n) 2 46 y(t) = 6 ~ 6 4 y(t .i! : : : e. . Moses. Stoica and R.The Covariance Matrix Equation Let: a(!) = 1 e.. Prentice Hall. 1997 Slide L6–2 .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. = Ax(t) + ~(t) ~ e where x(t) = x1(t) : : : xn(t)]T ~ ~(t) = e(t) : : : e(t . 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 .

. Stoica and R.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. Prentice Hall.n] (m (m . Moses. n)) Thus. 1997 Slide L6–3 . 2 R = S G] 6 4 1 3 " .ng: orthonormal eigenvectors associated with f n+1 : : : m g S = s1 : : : sn] (m n) G = g1 : : : gm.

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

.MUSIC Method a (!1) . Prentice Hall. 1997 Slide L6–5 . A G= G=0 a (!n) ) fa(!k )gn=1 ? R(G) k 2 6 4 3 7 5 Thus. Stoica and R. 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. f!kgn=1 are the unique solutions of k a (!)GG a(!) = 0. Moses.

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

Moses. 1997 Slide L6–7 .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. Stoica and R. ) f!kgn=1 can be found from the roots of ^ k aT (z.Pisarenko Method Pisarenko is a special case of MUSIC with m (the minimum possible value). If: =n+1 m=n+1 Then: ^ g G = ^1. Prentice Hall.

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

Stoica and R. Prentice Hall.1) 1 ^ g " # that are closest to the unit circle. Lecture notes to accompany Introduction to Spectral Analysis by P. 1997 Slide L6–9 . 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.Min-Norm Method. Moses.

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

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

1S1S2 ^^ ^^ f!kgn=1 = . 1997 Slide L6–12 . find S . 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.ESPRIT Implementation From the eigendecomposition of R. ^ ^ ^ ^ The frequency estimates are found by: where f^kgn=1 are the eigenvalues of k ^ = (S1S1). Moses. then S1 and S2 . Prentice Hall. Stoica and R.

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. Stoica and R. Moses. 1997 . Prentice Hall.

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

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

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

1 k=0 X 1 ei!k k = 0 : : : N . Prentice Hall. k) 2 ! . Stoica and R. Moses.i!k = 1 eiN (~.t) t=1 X X = N where ( X 1 k=0 hk y(N . 1997 .i!t 2 ~ ^p(~) = ! 4 N t=1 2 N 1 ~ = N y(t)ei!(N .!) . 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 H (!) = hk e ! N ei(~.Filter Bank Interpretation of the Periodogram 1 N y(t)e.!) .

Stoica and R. 1997 Slide L7–5 .Filter Bank Interpretation of the Periodogram. ^( ) Lecture notes to accompany Introduction to Spectral Analysis by P. Prentice Hall. for N = 50. power calculation from only 1 sample of filter output. !). Moses. and: narrow filter passband. con't jH (!)j as a function of (~ . ! 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.

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

= h0 h1 : : : hm] . Stoica and R. 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. 1997 Slide L7–7 .Capon Method Idea: Data-dependent bandpass filter design. Prentice Hall.im! ]T hk e. y(t . yF (t) = X m k=0 | hk y(t .i!k = h a(!) Lecture notes to accompany Introduction to Spectral Analysis by P. k) 2 6 4 | .i! : : : e. Moses.

1 a (!)R a(!) with N 1 ^ y(t)~ (t) ~ y R = N . Stoica and R. Prentice Hall. Moses.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.m t=m+1 X Lecture notes to accompany Introduction to Spectral Analysis by P. 1997 Slide L7–8 .Capon Method. n The Bandwidth 1 ' m+1 = (filter 1 length) Conclusion Estimate PSD as: +1 ^(!) = m^.1a(!) which should be the power of y (t) in a passband centered on ! .1a=a R.

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

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

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). ^( ) ^( ) Lecture notes to accompany Introduction to Spectral Analysis by P. Due to the low-order AR terms in the average. Moses. 1997 Slide L7–11 . C ! generally has worse resolution and bias properties than the AR method. AR Then ^C (!) = 1 1 m 1= ^AR(!) m + 1 k=0 k X Consequences: Due to the average over k. Prentice Hall.

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

. Sensor 2 Sensor m Problem: Detect and locate n radiating sources by using an array of m passive sensors. Stoica and R. seismology..R . seismometers Applications: Radar. .@ .The Spatial Spectral Estimation Problem Source 1 vSource 2 B B B B N B cccc ccc c c c c c v @ . @. Moses. 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. 1997 Slide L8–2 . @. communications. v Source n @. .@ . Sensor 1 @. mechanical Receiving sensors: Hydrophones. electromagnetic. Emitted energy: Acoustic. antennas. . sonar. Prentice Hall.. @. @. @..

1997 Slide L8–3 .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. (We do not treat the detection problem) The sensors are linear dynamic elements with known transfer characteristics and known locations (That is. Prentice Hall. AOA). Moses. The number of sources n is known. Stoica and R. the array is calibrated.) Lecture notes to accompany Introduction to Spectral Analysis by P.

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

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

Lecture notes to accompany Introduction to Spectral Analysis by P. Prentice Hall.i!ct ~ = yk(t) cos(!ct) .!ct = (t)f ei (t) + e. by low-pass filtering and sampling the signal yk (t)=2 = yk(t)e. Stoica and R.Complex Signal Representation The noise-free output has the form: z(t) = (t) cos !ct + (t)] = = (t) ei !ct+ (t)] + e.i! + ek (t) | s(t) {z } | Hk (!c) {z k c } c k yk (t) = s(t)Hk (!c) 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.i!ct to obtain (t)ei (t) lowpass highpass Hence.i 2!ct+ (t)] g n o | {z } | {z } Lowpass filter 2z(t)e. 1997 Slide L8–6 or .i !ct+ (t)] 2 Demodulate z (t) (translate to baseband): 2z(t)e. Moses.i!c k + ek (t) where s(t) is the complex envelope of x(t).

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

1997 Slide L8–10 . 1) c Lecture notes to accompany Introduction to Spectral Analysis by P. Prentice Hall. Stoica and R.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 . Moses.

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

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

Stoica and R. Moses. Lecture notes to accompany Introduction to Spectral Analysis by P.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. Prentice Hall. 1997 Slide L9–2 .

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

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. Stoica and R. 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.Analogy between Temporal and Spatial Filtering Spatial Filter: fyk(t)gm=1 = k the “spatial samples” obtained with a sensor array. 1997 Slide L9–4 . Lecture notes to accompany Introduction to Spectral Analysis by P. Moses. Prentice Hall.

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

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. h a 0 . 1997 Slide L9–6 .Spatial Filtering. Here. Moses. Stoica and R. Prentice Hall.

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

Moses. 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. 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. 1997 . n o n o The (dominant) peaks of h DOAs of the sources. 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.

y t can be considered as impinging on the array from all DOAs. () 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.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. 1997 Slide L9–9 . Stoica and R. Prentice Hall.

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

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

Then: R = E fy(t)y (t)g = APA + 2I Thus: The NLS.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. MUSIC. MIN-NORM and ESPRIT methods of frequency estimation can be used. Moses. almost without modification. 1997 Slide L9–12 . Lecture notes to accompany Introduction to Spectral Analysis by P. YW. Stoica and R. for DOA estimation. Prentice Hall.

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

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

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

(L 1). using 1 N y(t)~ (t) ^ . 1997 Slide L9–16 .=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.YW-MUSIC DOA Estimator f^kg = where the n largest peaks of 1=~ ( )V2V2 ~( ) a ^^a ~( ). is the “array transfer vector” for y(t) a ~ at DOA ^ V2 is defined similarly to V2. Prentice Hall. Stoica and R. Moses.

that is.MUSIC and Min-Norm Methods Both MUSIC and Min-Norm methods for frequency estimation apply with only minor modifications to the DOA estimation problem. if rank (P ) = rank(E fs(t)s (t)g) < n Modifications that apply in the coherent case exist. 1997 Slide L9–17 . Stoica and R. 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. Lecture notes to accompany Introduction to Spectral Analysis by P. Prentice Hall.

Prentice Hall.ESPRIT Method Assumption: The array is made from two identical subarrays separated by a known displacement vector.. Stoica and R. Lecture notes to accompany Introduction to Spectral Analysis by P.i!c ( 1) 0 . Moses. where e. D= 0 e. 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. 1997 Slide L9–18 ( ) = d sin( )=c .

1 . 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. 1997 Slide L9–19 .1 0]A = .1 A1 = Im. so m m and .1]A Lecture notes to accompany Introduction to Spectral Analysis by P.1 A2 = 0 Im. Moses. the two subarrays are often the first m and last m array elements. Stoica and R. Prentice Hall.ESPRIT Method.

Sign up to vote on this title
UsefulNot useful