Xiang / Peng / Yang Blind Source Separation

Dependent Component Analysis
1. Auflage 2014
ISBN: 978-981-287-227-2
Verlag: Springer Nature Singapore
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 101 Seiten

Reihe: SpringerBriefs in Signal Processing

This book provides readers a complete and self-contained set of knowledge about dependent source separation, including the latest development in this field. The book gives an overview on blind source separation where three promising blind separation techniques that can tackle mutually correlated sources are presented. The book further focuses on the non-negativity based methods, the time-frequency analysis based methods, and the pre-coding based methods, respectively.

Yong Xiang received the B.E. and M.E. degrees from the University of Electronic Science and Technology of China, Chengdu, China, in 1983 and 1989, respectively. In 2003, he received the Ph.D. degree from The University of Melbourne, Melbourne, Australia. He was with the Southwest Institute of Electronic Equipment of China, Chengdu, from 1983 to 1986. In 1989, he joined the University of Electronic Science and Technology of China, where he was a Lecturer from 1989 to 1992 and an Associate Professor from 1992 to 1997. He was a Senior Communications Engineer with Bandspeed Inc., Melbourne, Australia, from 2000 to 2002. He is currently an Associate Professor with the School of Information Technology at Deakin University, Australia. His research interests include blind signal/system estimation, communication signal processing, information and network security, speech and image processing, and pattern recognition.Dezhong Peng received the B.S. degree in applied mathematics, the M.S. and Ph.D. degrees in computer software and theory from the University of Electronic Science and Technology of China, Chengdu, China, in 1998, 2001 and 2006, respectively. He was a Postdoctoral Research Fellow at the School of Engineering, Deakin University, Australia from 2007 to 2009. Currently, he is a Professor at the Machine Intelligence Laboratory, College of Computer Science, Sichuan University, Chengdu, China. His current research interests include blind signal processing and neural networks.Zuyuan Yang received the B.E. degree from Hunan University of Science and Technology, Xiangtan, China, and the Ph.D. degree from South China University of Technology, Guangzhou, China, in 2003 and 2010, respectively. He was a recipient of the Excellent Ph.D. Thesis Award of Guangdong Province in 2010. Dr Yang is currently a Researcher with the Faculty of Automation, Guangdong University of Technology, Guangzhou. His current research interests include blind source separation, compressed sensing, nonnegative matrix factorization, and image processing.

Autoren/Hrsg.

Xiang, Yong

Peng, Dezhong

Yang, Zuyuan

Inhaltsverzeichnis

1;Preface;7
2;Acknowledgments;8
3;Contents;9
4;1 Introduction;11
4.1;1.1 Background of Blind Source Separation;11
4.2;1.2 Statistics Based Methods for Blind Source Separation;15
4.2.1;1.2.1 Higher-Order Statistics Based Methods;15
4.2.2;1.2.2 Second-Order Statistics Based Methods;17
4.3;1.3 Blind Source Separation via Dependent Component Analysis;18
4.3.1;1.3.1 Scenarios of Mutually Correlated Sources;18
4.3.2;1.3.2 Dependent Component Analysis Based Methods;20
4.4;References;24
5;2 Dependent Component Analysis Exploiting Nonnegativity and/or Time-Domain Sparsity;28
5.1;2.1 Nonnegative Sparse Representation Based Methods;28
5.1.1;2.1.1 Sparsity Measures for Nonnegative Signals;29
5.1.2;2.1.2 Estimation of Mixing Matrix and Source Signals;32
5.1.3;2.1.3 Uniqueness Conditions;36
5.2;2.2 Convex Geometry Analysis Based Methods;37
5.2.1;2.2.1 Geometric Features;38
5.2.2;2.2.2 Estimation of Source Signals;40
5.2.3;2.2.3 Source Identifiability Analysis;43
5.3;2.3 Nonnegative Matrix Factorization Based Methods;45
5.3.1;2.3.1 Nonnegative Matrix Factorization Models;45
5.3.2;2.3.2 Estimation of Mixing Matrix and Source Signals;48
5.3.3;2.3.3 Algorithm Analysis;53
5.4;References;53
6;3 Dependent Component Analysis Using Time-Frequency Analysis;57
6.1;3.1 Fundamentals of TFA;57
6.2;3.2 TFA-Based Methods for Mixing Matrix Estimation;60
6.2.1;3.2.1 System Model and Existing Works;60
6.2.2;3.2.2 Mixing Matrix Estimation Under Relaxed TF Sparsity;61
6.2.3;3.2.3 Mixing Matrix Estimation Under Local TF Sparsity;63
6.3;3.3 TFA-Based Methods for Source Recovery;64
6.3.1;3.3.1 Source Recovery Under Strong TF Sparsity;64
6.3.2;3.3.2 Source Recovery Under Relaxed TF Sparsity;67
6.3.3;3.3.3 Recovery of Non-sparse Dependent Sources;73
6.4;References;78
7;4 Dependent Component Analysis Using Precoding;80
7.1;4.1 Concept of Precoding Based Dependent Component Analysis;80
7.2;4.2 Precoding Based Time-Domain Method;81
7.3;4.3 Precoding Based Z-Domain Methods;87
7.3.1;4.3.1 Using Second-Order Precoders;87
7.3.2;4.3.2 Using First-Order Precoders;92
7.4;References;97
8;5 Future Work;98
8.1;5.1 Future Work for DCA Exploiting Nonnegativity and/or Time-Domain Sparsity;98
8.2;5.2 Future Work for DCA Exploiting Time-Frequency Analysis (TFA);99
8.3;5.3 Future Work for DCA Exploiting Precoding;100
8.4;References;100