Blind Source Separation by Ganesh R. Naik & Wenwu Wang
Author:Ganesh R. Naik & Wenwu Wang
Language: eng
Format: epub
Publisher: Springer Berlin Heidelberg, Berlin, Heidelberg
Fig. 9.3DOA tracking for three targets. , . ‘’ actual track, ‘’ estimated track. a MAP, b -SVD-MCS, c -SVD, d Capon
Fig. 9.4DOA tracking for three targets. , . ‘’ actual track, ‘’ estimated track. a MAP, b -SVD-MCS, c -SVD, d Capon
Fig. 9.5Broadband DOA estimation results for three sources are located at and . , . a MAP, b -SVD, c Capon
Narrowband DOA tracking results are shown in Fig. 9.3. We consider three uncorrelated moving sources. The starting location of sources are and respectively. The average and . As can be seen in Fig. 9.3a MAP can track the sources almost accurately. There is a little error tracking the first source between time index and . -SVD-MCS can track sources until time index . The interesting observation is that once -SVD-MCS loses track of DOAs, it cannot back to the track again. As illustrated in Fig. 9.3b, after time index , -SVD-MCS cannot track second and third DOAs anymore. Instead, it generates some random walk around the track of first source. -SVD can track the first source only. Capon also tracks first source. However, it generates another fictitious path from to .
We consider another route in Fig. 9.4. The starting DOA locations are and , respectively. In this scenario the first source crosses the route of other two sources. It is difficult to keep track of sources when they cross each other. Figure 9.4a illustrates that MAP is able to keep tracking the sources. In some cases, the estimated route of some sources are displaced from the actual route, however, MAP algorithm can back to the actual route of sources immediately. As before, -SVD-MCS can track the sources until time index . The algorithm loses the track of sources when the first and second sources cross each other. -SVD and Capon failed tracking sources. Until time index , both algorithms track the first sources, however, they start tracking the second source after time index .
Fig. 9.6Separating a broadband DOA in presence of jamming signal. The jamming signal comes from and actual source is at .
Download
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.
Algorithms of the Intelligent Web by Haralambos Marmanis;Dmitry Babenko(8315)
Test-Driven Development with Java by Alan Mellor(6860)
Data Augmentation with Python by Duc Haba(6779)
Principles of Data Fabric by Sonia Mezzetta(6521)
Learn Blender Simulations the Right Way by Stephen Pearson(6424)
Microservices with Spring Boot 3 and Spring Cloud by Magnus Larsson(6289)
Hadoop in Practice by Alex Holmes(5967)
Jquery UI in Action : Master the concepts Of Jquery UI: A Step By Step Approach by ANMOL GOYAL(5817)
RPA Solution Architect's Handbook by Sachin Sahgal(5688)
Big Data Analysis with Python by Ivan Marin(5429)
The Infinite Retina by Robert Scoble Irena Cronin(5383)
Life 3.0: Being Human in the Age of Artificial Intelligence by Tegmark Max(5164)
Pretrain Vision and Large Language Models in Python by Emily Webber(4393)
Infrastructure as Code for Beginners by Russ McKendrick(4164)
Functional Programming in JavaScript by Mantyla Dan(4048)
The Age of Surveillance Capitalism by Shoshana Zuboff(3966)
WordPress Plugin Development Cookbook by Yannick Lefebvre(3876)
Embracing Microservices Design by Ovais Mehboob Ahmed Khan Nabil Siddiqui and Timothy Oleson(3676)
Applied Machine Learning for Healthcare and Life Sciences Using AWS by Ujjwal Ratan(3654)
