pmusic Psuedospectrum using MUSIC algorithm [S,w] = pmusic(x,p) [S,w] = pmusic(x,p,w) [S,w] = pmusic(x,p,nfft) [S,w] = pmusic(x,p,nfft,fs) [S,w] = pmusic(x,p,f,fs) [S,f] = pmusic(...,'corr') [S,f] = pmusic(x,p,nfft,fs,nwin,noverlap) [...] = pmusic(...,freqrange) [...,v,e] = pmusic(...) Parameters: x - int|double - vector|matrix Input signal. In case of a matrix, each row of x represents a seperate observation of the signal. If 'corr' flag is specified, then x is the correlation matrix. If w is not specified in the input, it is determined by the algorithm. If x is real valued, then range of w is [0, pi]. Otherwise, the range of w is [0, 2pi) p - int|double - scalar|vector p(1) is the dimension of the signal subspace p(2), if specified, represents a threshold that is multiplied by the smallest estimated eigenvalue of the signal's correlation matrix. w - int|double - vector w is the vector of normalized frequencies over which the pseuspectrogram is to be computed. nfft - int - scalar (Default = 256) Length of the fft used to compute pseudospectrum. The length of S (and hence w/f) depends on the type of values in x and nfft. If x is real, length of s is (nfft/2 + 1) {Range of w = [0, pi]} if nfft is even and (nfft+1)/2 {Range of w = [0, pi)} otherwise. If x is complex, length of s is nfft. fs - int|double - scalar (Default = 1) Sampling rate. Used to convert the normalized frequencies (w) to actual values (f) and vice-versa. nwin - int|double - scalar (int only)|vector (Default = 2*p(1)) If nwin is scalar, it is the length of the rectangular window. Otherwise, the vector input is considered as the window coefficients. Not used if 'corr' flag present. If x is a vector, windowing not done in nwin in scalar. If x is a matrix, noverlap - int - scalar (Default = nwin-1) number of points by which successive windows overlap. noverlap not used if x is a matrix freqrange - string The range of frequencies over which the pseudospetrogram is computed. Three possible values - 'onesided', 'twosided', 'centered' 'corr' flag Presence indicates that the primary input x is actually a correlation matrix Examples: TODO: | peig | periodogram | pmtm | prony | pwelch | rooteig | rootmusic Ayush Baid References [1] Petre Stoica and Randolph Moses, Introduction To Spectral Analysis, Prentice-Hall, 1997, pg. 15 [2] S. J. Orfanidis, Optimum Signal Processing. An Introduction. 2nd Ed., Macmillan, 1988.