Optimal signal processing under uncertainty [E-Book] / author: Edward R. Dougherty
In the classical approach to optimal filtering, it is assumed that the stochastic model of the physical process is fully known. For instance, in Wiener filtering it is assumed that the power spectra are known with certainty. The implicit assumption is that the parameters of the model can be accurate...
Saved in:
Full text |
|
Personal Name(s): | Dougherty, Edward R., author |
Imprint: |
Bellingham, Washington :
SPIE,
2018
|
Physical Description: |
1 online resource (308 pages) |
Note: |
englisch |
ISBN: |
9781510619302 |
DOI: |
10.1117/3.2317891 |
Series Title: |
/* Depending on the record driver, $field may either be an array with
"name" and "number" keys or a flat string containing only the series
name. We should account for both cases to maximize compatibility. */?>
SPIE Press monograph ;
PM287 |
Subject (ZB): | |
Subject (LOC): |
- Preface
- Acknowledgments
- 1. Random functions: 1.1. Moments; 1.2. Calculus; 1.3. Three fundamental processes; 1.4. Stationarity; 1.5. Linear systems
- 2. Canonical expansions: 2.1. Fourier representation and projections; 2.2. Constructing canonical expansions; 2.3. Orthonormal coordinate functions; 2.4. Derivation from a covariance expansion; 2.5. Integral canonical expansions; 2.6. Expansions of WS stationary processes
- 3. Optimal filtering: 3.1. Optimal mean-square-error filters; 3.2. Optimal finite-observation linear filters; 3.3. Optimal linear filters for random vectors; 3.4. Recursive linear filters; 3.5. Optimal infinite-observation linear filters; 3.6. Optimal filtering via canonical expansions; 3.7. Optimal morphological bandpass filters; 3.8. General schema for optimal design
- 4. Optimal robust filtering: 4.1. Intrinsically Bayesian robust filters; 4.2. Optimal Bayesian filters; 4.3. Model-constrained Bayesian robust filters; 4.4. Robustness via integral canonical expansions; 4.5. Minimax robust filters; 4.6. IBR Kalman filtering; 4.7. IBR Kalman-Bucy filtering
- 5. Optimal experimental design: 5.1. Mean objective cost of uncertainty; 5.2. Experimental design for IBR linear filtering; 5.3. IBR Karhunen-Loève compression; 5.4. Markovian regulatory networks; 5.5. Complexity reduction; 5.6. Sequential experimental design; 5.7. Design with inexact measurements; 5.8. General MOCU-based experimental design
- 6. Optimal classification: 6.1. Bayes classifier; 6.2. Optimal Bayesian classifier; 6.3. Classification rules; 6.4. OBC in the discrete and Gaussian models; 6.5. Consistency; 6.6. Optimal sampling via experimental design; 6.7. Prior construction; 6.8. Epistemology
- 7. Optimal clustering: 7.1. Clustering; 7.2. Bayes clusterer; 7.3. Separable point processes; 7.4. Intrinsically Bayesian robust clusterer
- References
- Index