van der Heijden / Duin / de Ridder Classification, Parameter Estimation and State Estimation

An Engineering Approach Using MATLAB
1. Auflage 2005
ISBN: 978-0-470-09014-5
Verlag: John Wiley & Sons
Format: PDF
Kopierschutz: Adobe DRM (»Systemvoraussetzungen)

E-Book, Englisch, 440 Seiten, E-Book

Classification, Parameter Estimation and State Estimation isa practical guide for data analysts and designers of measurementsystems and postgraduates students that are interested in advancedmeasurement systems using MATLAB. 'Prtools' is a powerful MATLABtoolbox for pattern recognition and is written and owned by one ofthe co-authors, B. Duin of the Delft University of Technology.
After an introductory chapter, the book provides the theoreticalconstruction for classification, estimation and state estimation.The book also deals with the skills required to bring thetheoretical concepts to practical systems, and how to evaluatethese systems. Together with the many examples in the chapters, thebook is accompanied by a MATLAB toolbox for pattern recognition andclassification. The appendix provides the necessary documentationfor this toolbox as well as an overview of the most usefulfunctions from these toolboxes. With its integrated and unifiedapproach to classification, parameter estimation and stateestimation, this book is a suitable practical supplement inexisting university courses in pattern classification, optimalestimation and data analysis.
* Covers all contemporary main methods for classification andestimation.
* Integrated approach to classification, parameter estimation andstate estimation
* Highlights the practical deployment of theoretical issues.
* Provides a concise and practical approach supported by MATLABtoolbox.
* Offers exercises at the end of each chapter and numerous workedout examples.
* PRtools toolbox (MATLAB) and code of worked out examplesavailable from the internet
* Many examples showing implementations in MATLAB
* Enables students to practice their skills using a MATLABenvironment

Autoren/Hrsg.

van der Heijden, Ferdinand

Duin, Robert

de Ridder, Dick

Tax, David M. J.

Inhaltsverzeichnis

Preface.
Foreword.
1. Introduction.
2. Detection and Classification.
3. Parameter Estimation.
4. State Estimation.
5. Supervised Learning.
6. Feature Extraction and Selection.
7. Unsupervised Learning.
8. State Estimation in Practice.
9. Worked Out Examples.
Appendix A: Topics Selected from Functional Analysis.
Appendix B: Topics Selected from Linear Algebra and MatrixTheory.
Appendix C: Probability Theory.
Appendix D: Discrete-time Dynamic Systems.
Appendix E: Introduction to PRTools.
Appendix F: Used MATLAB Toolboxes.
Index.

Über Autor(innen)

F. van der Heijden, Laboratory for Measurement andInstrumentation, Faculty of Electrical Engineering, University ofTwente, P.O. Box 217, 7500AE Enschede, The Netherlands
His main research area is in Measurement and Instrumentation atan academic level and covers sensors and micro measurement systems,and image based measurement systems. He has written books, manybook chapters and journal articles.
R.P.W. Duin, Pattern Recognition Group, Delft Universityof Technology, Department of Imaging Sciences & TechnologyLorentzeg 1-2628 CD Delft, The Netherlands
His research includes: theory and applications of imageprocessing and pattern recognition, with a special interest insensors, measurements and measurement accuracy. He also studies thedevelopment and use of tools in this area. He has written 6 books(in English and Dutch) and many journal and conference papers andchapters in books. He is a member of Advanced School for Computingand Imaging (ASCI), Dutch Pattern Recognition Society (NVPHBV),International Association for Pattern Recognition (IAPR) and IAPRTechnical Committee TC1 (statistical pattern recognition).
D. de Ridder, Pattern Recognition Group, Delft Universityof Technology, Department of Imaging Sciences & TechnologyLorentzeg 1-2628 CD Delft, The Netherlands
He mainly works on methods for mapping high-dimensionalmeasurement sets to low-dimensional representations, suitable forsubsequent regression or classification. He works closely with RDuin and has co-written many papers with him.
D.M.J. Tax, Fraunhofer FIRST.IDA, Kekul´estr. 7,D-12489, Berlin, Germany
His main research interest is one-class classification. He wasthe author/co-author of many journal publications