Open AccessDissertation
Kernel Methods for Nonlinear Identification, Equalization and Separation of Signals
Steven Van Vaerenbergh
- 03 Feb 2010
TL;DR: In this paper, the authors study the application of kernel methods in signal processing in this work, including the blind source separation, and the kernel recursive least-squares (KRLS) algorithm.
read more
Abstract: espanolEn la ultima decada, los metodos kernel (metodos nucleo) han demostrado ser tecnicas muy eficaces en la resolucion de problemas no lineales. Parte de su exito puede atribuirse a su solida base matematica dentro de los espacios de Hilbert generados por funciones kernel ("reproducing kernel Hilbert spaces", RKHS); y al hecho de que resultan en problemas convexos de optimizacion. Ademas, son aproximadores universales y la complejidad computacional que requieren es moderada. Gracias a estas caracteristicas, los metodos kernel constituyen una alternativa atractiva a las tecnicas tradicionales no lineales, como las series de Volterra, los polinomios y las redes neuronales. Los metodos kernel tambien presentan ciertos inconvenientes que deben ser abordados adecuadamente en las distintas aplicaciones, por ejemplo, las dificultades asociadas al manejo de grandes conjuntos de datos y los problemas de sobreajuste ocasionados al trabajar en espacios de dimensionalidad infinita. En este trabajo se desarrolla un conjunto de algoritmos basados en metodos kernel para resolver una serie de problemas no lineales, dentro del ambito del procesado de senal y las comunicaciones. En particular, se tratan problemas de identificacion e igualacion de sistemas no lineales, y problemas de separacion ciega de fuentes no lineal ("blind source separation", BSS). Esta tesis se divide en tres partes. La primera parte consiste en un estudio de la literatura sobre los metodos kernel. En la segunda parte, se proponen una serie de tecnicas nuevas basadas en regresion con kernels para resolver problemas de identificacion e igualacion de sistemas de Wiener y de Hammerstein, en casos supervisados y ciegos. Como contribucion adicional se estudia el campo del filtrado adaptativo mediante kernels y se proponen dos algoritmos recursivos de minimos cuadrados mediante kernels ("kernel recursive least-squares", KRLS). En la tercera parte se tratan problemas de decodificacion ciega en que las fuentes son dispersas, como es el caso en comunicaciones digitales. La dispersidad de las fuentes se refleja en que las muestras observadas se agrupan, lo cual ha permitido disenar tecnicas de decodificacion basadas en agrupamiento espectral. Las tecnicas propuestas se han aplicado al problema de la decodificacion ciega de canales MIMO rapidamente variantes en el tiempo, y a la separacion ciega de fuentes post no lineal. EnglishIn the last decade, kernel methods have become established techniques to perform nonlinear signal processing. Thanks to their foundation in the solid mathematical framework of reproducing kernel Hilbert spaces (RKHS), kernel methods yield convex optimization problems. In addition, they are universal nonlinear approximators and require only moderate computational complexity. These properties make them an attractive alternative to traditional nonlinear techniques such as Volterra series, polynomial filters and neural networks. This work aims to study the application of kernel methods to resolve nonlinear problems in signal processing and communications. Specifically, the problems treated in this thesis consist of the identification and equalization of nonlinear systems, both in supervised and blind scenarios, kernel adaptive filtering and nonlinear blind source separation. In a first contribution, a framework for identification and equalization of nonlinear Wiener and Hammerstein systems is designed, based on kernel canonical correlation analysis (KCCA). As a result of this study, various other related techniques are proposed, including two kernel recursive least squares (KRLS) algorithms with fixed memory size, and a KCCA-based blind equalization technique for Wiener systems that uses oversampling. The second part of this thesis treats two nonlinear blind decoding problems of sparse data, posed under conditions that do not permit the application of traditional clustering techniques. For these problems, which include the blind decoding of fast time-varying MIMO channels, a set of algorithms based on spectral clustering is designed. The effectiveness of the proposed techniques is demonstrated through various simulations.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Online Sequential Extreme Learning Machine With Kernels
TL;DR: This work proposes a straightforward extension of the well-known kernel recursive least-squares, belonging to the kernel adaptive filtering (KAF) family, to the ELM framework, and presents an algorithm for this task, which can result in a highly efficient algorithm, both in terms of obtained generalization error and training time.
158
Cost-sensitive transfer kernel canonical correlation analysis for heterogeneous defect prediction
Zhiqiang Li,Xiao-Yuan Jing,Xiao-Yuan Jing,Fei Wu,Xiaoke Zhu,Xiaoke Zhu,Baowen Xu,Shi Ying +7 more
- 01 Jun 2018
TL;DR: A new cost-sensitive transfer kernel canonical correlation analysis (CTKCCA) approach for HDP can not only make the data distributions of source and target projects much more similar in the nonlinear feature space, where the learned features have favorable separability, but also utilize the different misclassification costs for defective and defect-free classes to alleviate the class imbalance problem.
120
One-class support vector machines approach to anomaly detection
TL;DR: Two-class and one-class support vector machines (SVM) for detection of fraudulent credit card transactions are presented and the performance of binary classifiers using balanced and imbalanced datasets with one- class SVM classifiers are described and compared.
88
Heterogeneous defect prediction with two-stage ensemble learning
Zhiqiang Li,Zhiqiang Li,Xiao-Yuan Jing,Xiao-Yuan Jing,Xiaoke Zhu,Hongyu Zhang,Baowen Xu,Shi Ying +7 more
- 04 Jun 2019
TL;DR: A novel Two-Stage Ensemble Learning (TSEL) approach to HDP, which contains two stages: ensemble multi-kernel domain adaptation (EMDA) stage and ensemble data sampling (EDS) stage, which develops an Ensemble Multiple Kernel Correlation Alignment (EMKCA) predictor, which combines the advantage of multiple kernel learning and domain adaptation techniques.
61
References
•Book
The Nature of Statistical Learning Theory
Vladimir Vapnik
- 01 Jan 1995
TL;DR: Setting of the learning problem consistency of learning processes bounds on the rate of convergence ofLearning processes controlling the generalization ability of learning process constructing learning algorithms what is important in learning theory?
46K
•Book
Neural Networks: A Comprehensive Foundation
Simon Haykin
- 16 Jul 1998
TL;DR: Thorough, well-organized, and completely up to date, this book examines all the important aspects of this emerging technology, including the learning process, back-propagation learning, radial-basis function networks, self-organizing systems, modular networks, temporal processing and neurodynamics, and VLSI implementation of neural networks.
•Book
Digital Communications
John G. Proakis
- 01 Jan 1983
TL;DR: This month's guest columnist, Steve Bible, N7HPR, is completing a master’s degree in computer science at the Naval Postgraduate School in Monterey, California, and his research area closely follows his interest in amateur radio.
27.7K