MUSIC and Eigenvector Analysis Methods

The pmusic and peig functions provide two related spectral analysis methods:

• pmusic provides the multiple signal classification (MUSIC) method developed by Schmidt.

• peig provides the eigenvector (EV) method developed by Johnson.

Both of these methods are frequency estimator techniques based on eigenanalysis of the autocorrelation matrix. This type of spectral analysis categorizes the information in a correlation or data matrix, assigning information to either a signal subspace or a noise subspace.

Eigenanalysis Overview

Consider a number of complex sinusoids embedded in white noise. You can write the autocorrelation matrix R for this system as the sum of the signal autocorrelation matrix (S) and the noise autocorrelation matrix (W): R = S + W. There is a close relationship between the eigenvectors of the signal autocorrelation matrix and the signal and noise subspaces. The eigenvectors v of S span the same signal subspace as the signal vectors. If the system contains M complex sinusoids and the order of the autocorrelation matrix is p, eigenvectors v_M+1 through v_p+1 span the noise subspace of the autocorrelation matrix.

Frequency Estimator Functions

To generate their frequency estimates, eigenanalysis methods calculate functions of the vectors in the signal and noise subspaces. Both the MUSIC and EV techniques choose a function that goes to infinity (denominator goes to zero) at one of the sinusoidal frequencies in the input signal. Using digital technology, the resulting estimate has sharp peaks at the frequencies of interest; this means that there might not be infinity values in the vectors.

The MUSIC estimate is given by the formula

$${\widehat{P}}_{\text{MUSIC}}(f)=\frac{1}{{\displaystyle \sum _{k=p+1}^M{\left|v_k^{H}e(f)\right|}^2}},$$

where the v_k are the eigenvectors of the noise subspace and e(f) is a vector of complex sinusoids:

$$e(f)={[\begin{array}{lllll}1\hfill & e^{j2\pi f}\hfill & e^{j4\pi f}\hfill & \dots \hfill & e^{j2(M-1)\pi f}\hfill \end{array}]}^T.$$

Here v represents the eigenvectors of the input signal's correlation matrix; v_k is the kth eigenvector. H is the conjugate transpose operator. The eigenvectors used in the sum correspond to the smallest eigenvalues and span the noise subspace (p is the size of the signal subspace).

The expression v_k^He(f) is equivalent to a Fourier transform (the vector e(f) consists of complex exponentials). This form is useful for numeric computation because the FFT can be computed for each v_k and then the squared magnitudes can be summed.

The EV method weights the summation by the eigenvalues of the correlation matrix:

$${\widehat{P}}_{\text{EV}}(f)=\frac{1}{{\displaystyle \sum _{k=p+1}^M\frac{1}{{\lambda }_k}{\left|v_k^{H}e(f)\right|}^2}}.$$

The pmusic and peig functions interpret their first input either as a signal matrix or as a correlation matrix (if the 'corr' input flag is set). In the former case, the singular value decomposition of the signal matrix is used to determine the signal and noise subspaces. In the latter case, the eigenvalue decomposition of the correlation matrix is used to determine the signal and noise subspaces.