| Description |
1 online resource (viii, 99 pages) |
| Series |
Synthesis lectures on signal processing (Online) |
|
Synthesis lectures on signal processing (Online)
|
| Contents |
1. Introduction -- 1.1. Complete-data case -- 1.2. Missing-data case -- 1.3. Summary -- 2. APES for complete data spectral estimation -- 2.1. Introduction -- 2.2. Problem formulation -- 2.3. Forward-only APES estimator -- 2.4. Two-step filtering-based interpretation -- 2.5. Forward-backward averaging -- 2.6. Fast implementation -- 3. Gapped-data APES -- 3.1. Introduction -- 3.2. GAPES -- 3.3. Two-dimensional GAPES -- 3.4. Numerical examples -- 4. Maximum likelihood fitting interpretation of APES -- 4.1. Introduction -- 4.2. ML fitting based spectral estimator -- 4.3. Remarks on the ML fitting criterion -- 5. One-dimensional missing-data APES via expectation maximization -- 5.1. Introduction -- 5.2. EM for missing-data spectral estimation -- 5.3. MAPES-EM1 -- 5.4. MAPES-EM2 -- 5.5. Aspects of interest -- 5.6. MAPES compared with GAPES -- 5.7. Numerical examples -- 6. Two-dimensional MAPES via expectation maximization and cyclic maximization -- 6.1. Introduction -- 6.2. Two-dimensional ML-based APES -- 6.3. Two-dimensional MAPES via EM -- 6.4. Two-dimensional MAPES via CM -- 6.5. MAPES-EM versus MAPES-CM -- 6.6. Numerical examples -- 7. Conclusions and software -- 7.1. Concluding remarks -- 7.2. Online software -- References -- The authors |
| Summary |
Spectral estimation is important in many fields including astronomy, meteorology, seismology, communications, economics, speech analysis, medical imaging, radar, sonar, and underwater acoustics. Most existing spectral estimation algorithms are devised for uniformly sampled complete-data sequences. However, the spectral estimation for data sequences with missing samples is also important in many applications ranging from astronomical time series analysis to synthetic aperture radar imaging with angular diversity. For spectral estimation in the missing-data case, the challenge is how to extend the existing spectral estimation techniques to deal with these missing-data samples. Recently, nonparametric adaptive filtering based techniques have been developed successfully for various missing-data problems. Collectively, these algorithms provide a comprehensive toolset for the missing-data problem based exclusively on the nonparametric adaptive filter-bank approaches, which are robust and accurate, and can provide high resolution and low sidelobes. In this lecture, we present these algorithms for both one-dimensional and two-dimensional spectral estimation problems |
| Notes |
Title from PDF title page (viewed December 2, 2005) |
|
Series statement from caption on home page |
| Bibliography |
Includes bibliographical references (pages 91-96) |
| Subject |
Signal processing -- Statistical methods
|
|
Nonparametric statistics.
|
|
Missing observations (Statistics)
|
|
Adaptive signal processing.
|
|
Statistics, Nonparametric
|
|
COMPUTERS -- Information Theory.
|
|
TECHNOLOGY & ENGINEERING -- Signals & Signal Processing.
|
|
Adaptive signal processing
|
|
Missing observations (Statistics)
|
|
Nonparametric statistics
|
|
Signal processing -- Statistical methods
|
| Form |
Electronic book
|
| Author |
Li, Jian, 1965 April 17-
|
|
Stoica, Petre.
|
| ISBN |
1598290002 |
|
9781598290004 |
|
9781598290011 |
|
1598290010 |
|
9783031025259 |
|
3031025253 |
|
