Subspace

Reference:Slides of EE4C03, TUDHayes M H. Statistical digital signal processing and modelingContentSteepest Descent AlgorithmStability / ConvergenceConverge rateMean-square errorLMS AlgorithmConvergence in the meanConvergence in the mean-squareNormalize

ContentThe FIR Wiener FilterFilteringPredictionDeconvolutionNoise cancellationDiscrete Kalman FilterThe discrete form of the Wiener filtering problem, is to design a filter to recover a signal d(n)d (n)d(n) from noisy observationsx(n)=d(n)+v(n)x(n)=d(n

Reference:Slides of EE4C03, TUDHayes M H. Statistical digital signal processing and modelingContentNonparametric MethodsThe PeriodogramA filter bank interpretation of the periodogramPerformance of the periodogramThe Modified PeriodogramPerformance of th

Reference:Slides of EE4C03, TUDHayes M H. Statistical digital signal processing and modelingContentDevelopment of the RecursionThe Lattice FilterFIR lattice filterIIR lattice filterPropertiesThe Schur AlgorithmCholesky Factorization of a Toeplitz Matrix

ContentSignal modelsDetermine models: Least SquaresDetermine models: Pade ApproximationDetermine models: Prony’s MethodDM-Special case: All-pole modelingAll-pole modeling with finite dataAutocorrelation methodCovariance methodExamplesPole estimationChannel

Reference:Slides of EE4C03, TUDHayes M H. Statistical digital signal processing and modeling[M]. John Wiley & Sons, 2009.ContentRandom VariablesDefinitionsLinear Mean-Square EstimationRandom ProcessDefinitionStationarityAutocorrelation and autocovar