COMPLEX-VALUED ADAPTIVE SIGNAL PROCESSING - Adaptive Signal Processing: Next Generation Solutions - page 30

Figure 1.5 (a) Scatter plot and the (b) covariance and pseudo-covariance function
plots for a sample wind data.

functions are the same. Hence, it has a non-zero pseudo-covariance function thus
quantitatively verifying its noncircular nature.
In Figures 1.5 and 1.6, we show examples of real-world signals where the
samples within each data set are normalized to zero mean and unit variance. The
scatter plot of a sample of wind data obtained from http: // mesonet.agron.iastate.
edu is shown in Figure 1.5 along with its covariance and pseudo-covariance
functions. The data are interpreted as complex by combining its strength as the
magnitude and direction as the phase information. As observed from the scatter
plot as well as its nonzero pseudo-covariance function, the signal is noncircular.
Two more samples are shown in Figure 1.6. The example in Figure 1.6 a shows

Figure 1.6 Scatter plots of (a) a circular (radar) data and (b) a noncircular

(fMRI) data.