信號的相關矩陣或協方差矩陣在系統識別中扮演着重要角色。事實上，對於一個LTI隨機系統，其輸出序列的二階統計量完全可以確定該系統。
定義
互相關和協方差
對於均值為0的白噪聲序列，二者形式是一致的。
Matlab計算
matlab中的相關命令：
% 協方差矩陣
data_cov = cov((data));
%信號自相關
autocorr(data, 1023)
% 互相關系數
R = corrcoef(data);
% 互功率譜密度（互功率譜密度與信號的互相關函數具有傅里葉變換關系）
pxy = cpsd(x,y,window,noverlap,nfft)
% Cross-correlation 互相關or自相關
[a,b]=xcorr(x,'unbiased');
[a,b]=xcorr(x,y,'unbiased');
scaleopt — Normalization option
'none' (default) | 'biased' | 'unbiased' | 'coeff'
returns the cross-correlation of two discrete-time sequences, x and y.
Cross-correlation measures the similarity between x and shifted (lagged) copies of y as a function of the lag.
If x and y have different lengths, the function appends zeros at the end of the shorter vector so it has the same length, N, as the other.
autocorr和xcorr有什么不一樣的？
% 與xcorr類似的還有互協方差xcov
c = xcov(x,y)
c = xcov(x)
returns the cross-covariance of two discrete-time sequences, x and y.
Cross-covariance measures the similarity between x and shifted (lagged) copies of y as a function of the lag.
If x and y have different lengths, the function appends zeros at the end of the shorter vector so it has the same length as the other.
https://blog.csdn.net/jonathanlin2008/article/details/6566802
https://www.cnblogs.com/maxwell-maxwill/p/12146919.html
https://blog.csdn.net/scuthanman/article/details/5588138