小波去噪舉例

《小波去噪舉例》由會(huì)員上傳分享，免費(fèi)在線(xiàn)閱讀，更多相關(guān)內(nèi)容在行業(yè)資料-天天文庫(kù)。

1、[4]§4.6小波去噪舉例4.6.1MATLAB中用wnoise函數(shù)測(cè)試去噪算法sqrt_snr=3;init=231434;[x,xn]=wnoise(3,11,sqrt_snr,init);%WNOISEgeneratenoisywavelettestdata.%X=WNOISE(FUN,N)returnsvaluesofthetestfunctiongivenbyFUN,ona%2^Nsampleof[0,1].[X,XN]=WNOISE(FUN,N,SQRT_SNR)returnsthe%previousvectorXrescaledsuchtha

2、tstd(x)=SQRT_SNR.Thereturned%vectorXNcontainsthesametestvectorXcorruptedbyanadditiveGaussian%whitenoiseN(0,1).ThenXNhasasignal-to-noiseratioof(SQRT_SNR^2).%[X,XN]=WNOISE(FUN,N,SQRT_SNR,INIT)returnspreviousvectorsXand%XN,butthegeneratorseedissettoINIvalue.subplot(3,2,1),plot(x)titl

3、e('originaltestfunction')subplot(3,2,2),plot(xn)title('noisedfunction')%產(chǎn)生一個(gè)長(zhǎng)為2**11點(diǎn)，包含高斯白噪聲的正弦信號(hào)，噪聲的的標(biāo)準(zhǔn)偏差為3。lev=5;xd=wden(x,'heursure','s','one',lev,'sym8');%[XD,CXD,LXD]=WDEN(X,TPTR,SORH,SCAL,N,'wname')%returnsade-noisedversionXDofinputsignalXobtainedbythresholdingthe%waveletcoe

4、fficients.Additionaloutputarguments[CXD,LXD]arethewavelet%decompositionstructureofde-noisedsignalXD.（WDEN根據(jù)信號(hào)小波分解%結(jié)構(gòu)[C,L]對(duì)信號(hào)進(jìn)行去噪處理，返回處理信號(hào)XD，以及XD的小波分解%結(jié)構(gòu){CXD，LXD}）。%TPTR(containsthresholdselectionrule)='heursure',%'heursure'isanheuristicvariantofthefirstoption%（選擇基于Stein無(wú)偏估計(jì)理論的自適應(yīng)域

5、值的啟發(fā)式改進(jìn)）%SORH('s'or'h')isforsoftorhardthresholding（決定域值的使用方式）%SCAL(='onedefinesmultiplicativethresholdrescaling:'one'fornorescaling%（決定域值是否隨噪聲變化）'wname'='sym8'subplot(3,2,3),plot(xd)title('Onede-noisedfunction')%利用’sym8’小波對(duì)信號(hào)分解，在分解的第5層上，利用啟發(fā)式SURE域值選擇法對(duì)信號(hào)去噪。xd=wden(x,'heursure','s'

6、,'sln',lev,'sym8');%'sln'forrescalingusingasingleestimation%oflevelnoisebasedonfirstlevelcoefficients（根據(jù)第一層小波分解的噪聲方%差調(diào)整域值）subplot(3,2,4),plot(xd)title('Slnde-noisedfunction')%同上’sym8’小波對(duì)信號(hào)分解條件，但用軟SURE域值選擇算法對(duì)信號(hào)去噪。xd=wden(x,'sqtwolog','s','sln',lev,'sym8');%foruniversalthresholdsqrt

7、(2*log(.))（固定域值選擇算法去噪）.subplot(3,2,5),plot(xd)title('Sqtwologde-noisedfunction')%同上’sym8’小波對(duì)信號(hào)分解條件，但用固定域值選擇算法去噪。[c,l]=wavedec(x,lev,'sym8');%WAVEDECperformsamultilevel1-Dwaveletanalysisusingeitheraspecific%wavelet'wname'oraspecificsetofwaveletdecompositionfilters(see%WFILTERS).[C,

8、L]=WAVEDEC(X,N,'wname')returnsthe