book

Academic Press Library in Signal Processing

by Sergios Theodoridis, Rama Chellappa

August 2013

Intermediate to advanced

1012 pages

32h 55m

English

Academic Press

Read now

Unlock full access

Signal Processing at Your Fingertips!
Section 1Section 2
Acknowledgments3.01.1 A brief historical recount3.01.2 Content3.01.3 Contributions3.01.4 Suggested further readingReferences

Abstract3.02.1 Introduction3.02.2 Example: variable selection in regression3.02.3 Methods based on statistical inference paradigms3.02.4 Information and coding theory based methods3.02.5 Example: estimating number of signals in subspace methods3.02.6 ConclusionReferences
Abstract3.03.1 Introduction3.03.2 Linear signal transforms3.03.3 Quadratic time-frequency distributions
3.03.5 Processing of sparse signals in time-frequency3.03.6 Examples of time-frequency analysis applicationsReferences
Abstract3.04.1 Introduction3.04.2 Parameter estimation3.04.3 Computational methods3.04.4 State-space models and sequential inference3.04.5 ConclusionA Probability densities and integralsReferences
Abstract3.05.1 Introduction3.05.2 Distributed detection with independent observations3.05.3 Distributed detection with dependent observations3.05.4 ConclusionReferences
AbstractAcknowledgments3.06.1 Introduction3.06.2 Mathematical preliminaries3.06.3 Bayesian quickest change detection3.06.4 Minimax quickest change detection3.06.5 Relationship between the models3.06.6 Variants and generalizations of the quickest change detection problem3.06.7 Applications of quickest change detection3.06.8 Conclusions and future directionsReferences
AbstractAcknowledgment3.07.1 Introduction3.07.2 Theory—overview3.07.3 Estimation methods3.07.4 Motion models3.07.5 Maps and applications3.07.6 Mapping in practice3.07.7 ConclusionReferences
Abstract3.08.1 Introduction3.08.2 Parametric statistical models3.08.3 Maximum likelihood estimation and the CRB3.08.4 Mean-square error bound3.08.5 Perturbation methods for algorithm analysis3.08.6 Constrained Cramér-Rao bound and constrained MLE3.08.7 Multiplicative and non-Gaussian noise3.08.8 Asymptotic analysis and the central limit theorem3.08.9 Asymptotic analysis and parametric models3.08.10 Monte Carlo methods3.08.11 Confidence intervals3.08.12 ConclusionReferences
AbstractAcknowledgments3.09.1 Motivation3.09.2 Mean-square-error estimation3.09.3 Distributed optimization via diffusion strategies3.09.4 Adaptive diffusion strategies3.09.5 Performance of steepest-descent diffusion strategies3.09.6 Performance of adaptive diffusion strategies
3.09.8 Selecting the combination weights3.09.9 Diffusion with noisy information exchanges3.09.10 Extensions and further considerationsAppendicesReferences
3.10.1 Some history3.10.2 Summary of the included chapters3.10.3 OutlookReferences
Abstract3.11.1 Introduction3.11.2 Geometric data model3.11.3 Spatial filtering and beam patterns3.11.4 Beam forming and signal detection3.11.5 Direction-of-arrival estimation3.11.6 Non-coherent array applications3.11.7 Concluding remarksReferences
AbstractAcknowledgments3.12.1 Introduction3.12.2 Data and beamforming models3.12.3 Adaptive beamforming3.12.4 Robust adaptive beamformingReferences
Abstract3.13.1 Introduction3.13.2 Environment and channel modeling3.13.3 Broadband beamformer design in element space3.13.4 Broadband beamformer design using the wave equation3.13.5 Optimum and adaptive broadband beamforming3.13.6 ConclusionReferences
AbstractAcknowledgments3.14.1 Background3.14.2 Data model3.14.3 Beamforming methods3.14.4 Subspace methods3.14.5 Parametric methods3.14.6 Wideband DOA estimation3.14.7 Signal detection3.14.8 Special topics3.14.9 DiscussionReferences
AbstractAcknowledgment3.15.1 Introduction3.15.2 Data model3.15.3 Subspace estimation3.15.4 Subspace-based algorithms3.15.5 ConclusionsReferences
Abstract3.16.1 Introduction3.16.2 Models and basic assumption3.16.3 General statistical tools for performance analysis of DOA estimation3.16.4 Asymptotic distribution of estimated DOA3.16.5 Detection of number of sources3.16.6 Resolution of two closely spaced sourcesReferences
Abstract3.17.1 Introduction3.17.2 Nonstationary signals and time-frequency representations3.17.3 Spatial time-frequency distribution3.17.4 DOA estimation techniques3.17.5 Joint DOD/DOA estimation in MIMO radar systems3.17.6 ConclusionReferences
Abstract3.18.1 Introduction3.18.2 Problem formulation3.18.3 Triangulation3.18.4 Signal propagation models3.18.5 Source localization algorithms3.18.6 Target tracking algorithm3.18.7 ConclusionReferences
Abstract3.19.1 Introduction3.19.2 Ideal array signal models3.19.3 Examples of array nonidealities3.19.4 Array calibration3.19.5 Model-driven techniques3.19.6 Data-driven techniques3.19.7 Robust methods3.19.8 Array processing examples3.19.9 ConclusionReferences
Abstract3.20.1 Introduction and background3.20.2 Radar applications3.20.3 Radio astronomy3.20.4 Positioning and navigation
3.20.6 Biomedical3.20.7 Sonar3.20.8 Microphone arrays3.20.9 Chemical sensor arrays3.20.10 ConclusionReferences and Further Reading

Content preview from Academic Press Library in Signal Processing

3.09.7 Comparing the performance of cooperative strategies

Using the expressions just derived for the MSD of the network, we can compare the performance of various cooperative and non-cooperative strategies. Table 9.6 further ahead summarizes the results derived in this section and the conditions under which they hold.

Table 9.6

Comparison of the MSD Performance of Various Cooperative Strategies

3.09.7.1 Comparing ATC and CTA strategies

We first compare the performance of the adaptive ATC and CTA diffusion strategies (9.153) and (9.154) when they employ a doubly stochastic combination matrix . That is, let us consider the two scenarios: