DSP_MATLAB.zip

  • PUDN用户
    了解作者
  • matlab
    开发工具
  • 134KB
    文件大小
  • zip
    文件格式
  • 0
    收藏次数
  • 1 积分
    下载积分
  • 4
    下载次数
  • 2014-04-08 07:58
    上传日期
含有近120多个用MATLAB编写的信号处理程序
DSP_MATLAB.zip
  • DSP_MATLAB
  • 例15.3.2
  • plot_STFT_square.m
    1.4KB
  • wienerfilter.m
    724B
  • noisy_voice.wav
    62.5KB
  • wiener_speech.m
    1.1KB
  • cut_frame.m
    507B
  • add_overlap.m
    292B
  • exa150302.m
    466B
  • exa090300_2.m
    586B
  • exa141201_pmusic.m
    508B
  • exa141202.m
    865B
  • exa090300_1.m
    733B
  • exa160502.m
    837B
  • exa060701_1.m
    747B
  • exa100201.m
    696B
  • exa010101.m
    634B
  • exa120801_cohere.m
    1.1KB
  • exa100302_ab.m
    1.2KB
  • exa141201_pcov.m
    441B
  • exa030903.m
    957B
  • exa120800_cov.m
    389B
  • exa030702.m
    973B
  • exa050403.m
    1.4KB
  • exa011003_randn.m
    589B
  • exa080701_dct1.m
    642B
  • exa141201_peig.m
    564B
  • exa100301.m
    1.2KB
  • exa070500_3.m
    546B
  • exa011001_rand.m
    605B
  • exa050401_1.m
    609B
  • exa060702_1.m
    988B
  • exa040701_fft.m
    557B
  • exa070804_remezord_1.m
    602B
  • exa070500_2.m
    449B
  • exa011007_xcorr.m
    895B
  • fast_LOT.m
    1.5KB
  • exa031102_hilbert.m
    550B
  • exa10302_cd.m
    1.5KB
  • exa060701_2.m
    729B
  • exa011006_conv.m
    561B
  • exa10301.m
    1.1KB
  • exa160505.m
    946B
  • exa060701_3.m
    524B
  • exa141201_pmem.m
    445B
  • rounding.m
    568B
  • truncation.m
    575B
  • exa160506.m
    1.1KB
  • exa120802_tfe.m
    608B
  • exa130701_pwelch.m
    604B
  • exa080702_dct2.m
    1.2KB
  • exa080703_LOT_1D.m
    1.3KB
  • exa090803_deconv.m
    524B
  • exa050501.m
    1.2KB
  • exa060703_2.m
    611B
  • exa050802_grpdelay.m
    718B
  • exa090804_svd.m
    478B
  • exa150601.m
    893B
  • exa030201.m
    1.4KB
  • exa020805_residuez.m
    635B
  • exa100100.m
    486B
  • exa070803_remez_2.m
    600B
  • exa030101.m
    558B
  • exa020802_impz.m
    389B
  • exa050804_latcfilt.m
    745B
  • exa040702_czt.m
    765B
  • exa020802.m
    974B
  • exa141201_pmcov.m
    449B
  • test.mat
    2.2KB
  • exa120800_corrcoef.m
    390B
  • exa030202.m
    620B
  • exa050803_tf2latc.m
    643B
  • exa160301a.m
    1.1KB
  • exa020806.m
    626B
  • exa070801_fir1.m
    721B
  • exa030102.m
    567B
  • exa031101_conv.m
    718B
  • exa011002_rand.m
    540B
  • GIRL.BMP
    17.1KB
  • exa090802_modulate.m
    823B
  • exa020803_freqz.m
    560B
  • exa080701_dct1_test.m
    352B
  • exa070101.m
    819B
  • exa020801_filter.m
    500B
  • exa050101.m
    627B
  • exa100401.m
    880B
  • exa090801_in_de_re.m
    844B
  • exa020807.m
    593B
  • exa030701.m
    694B
  • exa160504.m
    751B
  • exa020502.m
    494B
  • exa011005_chirp.m
    534B
  • exa060703_1.m
    835B
  • exa060702_2.m
    593B
  • exa030203.m
    496B
  • fig160201.m
    274B
  • exa011004_sinc.m
    405B
  • exa020503.m
    992B
  • exa070802_fir2.m
    647B
  • exa141201_pburg.m
    444B
内容介绍
% exa160301b, 研究LMS算法的性能,求学习曲线。应用模型是系统辨识,见exa160501; clear all; N1=1000; N=100; M=15; b = fir1(M-1,0.5); % FIR system to be identified mu1 = 0.001; % LMS step size mu2 = 0.01; % LMS step size for k=1:N x = randn(1,N1); % Input to the filter noise = 0.1*randn(1,N1); % Observation noise signal d = filter(b,1,x)+noise; % Desired signal ha1 = adaptfilt.lms(M,mu1); [y1,e1] = filter(ha1,x,d); e21(k,:)=e1; ha2 = adaptfilt.lms(M,mu2); [y2,e2] = filter(ha2,x,d); e22(k,:)=e2; end E_mu1 = sum(e21.^2,1)./N; E_mu2 = sum(e22.^2,1)./N; figure(1) plot(E_mu1);grid; hold on; plot(E_mu2); hold on; xlabel('Number of interations') ylabel('Mean square error for mu1,mu2') N=10*N; for k=1:N x = randn(1,N1); % Input to the filter noise = 0.1*randn(1,N1); % Observation noise signal d = filter(b,1,x)+noise; % Desired signal ha1 = adaptfilt.lms(M,mu1); [y1,e1] = filter(ha1,x,d); e21(k,:)=e1; ha2 = adaptfilt.lms(M,mu2); [y2,e2] = filter(ha2,x,d); e22(k,:)=e2; end E_mu1 = sum(e21.^2,1)./N; E_mu2 = sum(e22.^2,1)./N; plot(E_mu1,'r');grid; hold on; plot(E_mu2,'r'); rd=xcorr(d,'biased'); rx=xcorr(x,'biased'); rxd=xcorr(d,x,'biased'); RX=toeplitz(rx(N1:(N1+(M-1)))); e_min=rd(N1)-rxd(N1:(N1+(M-1)))*inv(RX)*rxd(N1:(N1+(M-1)))'; e_min
评论
    相关推荐