close all,
clear all,
clc,
Xn=[];
Zn=[];
for n=1:1000
Xn(n) = randn();
if(n==1), Zn(n) = Xn(n); end
if(n>1),
Zn(n) = 0.95 * (Zn(n-1) + Xn(n));
end
end
subplot(2,2,1); plot(Xn); title('Zero Mean Gaussian Distributed
Random Noise')
subplot(2,2,2); plot(Zn); title('Zn = 0.95 * (Z(n-1) + xn)');
[Pxx,w] = pwelch(Xn);
subplot(2,2,3); plot(w,Pxx); title('Power Spectral Estimate for
Signal Xn');
[Pxx,w] = pwelch(Zn);
subplot(2,2,4); plot(w,Pxx); title('Power Spectral Estimate for
Signal Zn');
for ExpNo=1:100
Xn=[];
Zn=[];
for n=1:1000
Xn(n) = randn();
if(n==1), Zn(n) = Xn(n); end
if(n>1),
Zn(n) = (0.95 * Zn(n-1)) + Xn(n);
end
end
C_Xn = xcorr(Xn); %Auto-Correlation of Proces Xn
C_Zn = xcorr(Zn); %Auto-Correlation of Proces Zn
Covariance_Xn = cov(Xn);
Covariance_Zn = cov(Zn);
end
7. X(n) is a zero- discrete-time random process. following input-output relationship: zn) -0.95 mean, stationary, identically and independently, Gaussian distributed white The sample functions of...
5. A stationary random process X[n] is input to a discrete time LTI system with frequency response j“)-10 zero mean given as A(e nmay be expressed as where Wnlis a zero mea a-HS1 unit variancei.i.d. (independent identically distributed) Gaussian sequence and c, d are constants. Let Yl be the output random a)Determine the mean function for the output random sequence Yn in terms ofa, c and d b) Determine S7 (e), the power spectral density ofthe output random sequence Yn]...
Let Xn, -inf to +inf be a discrete-time zero-mean white noise process, i.e., μx[n] = 0, Rx[n] =δ[n]. The process is filtered using an LTI system with impulse response h[n] =αδ[n] + βδ[n−1]. Find α and β such that the output process Yn has autocorrelation function Ry[n] =δ[n+1] + 2δ[n] +δ[n−1]. 5) (3 points) Let Xn, -o0 K n oo, be a discrete-time zero-mean white noise process, i.e, ,1z[n]-(), Rx [n] S[n]. The process is filtered using an LTI system...