Time–Frequency Domain for Segmentation and Classification of Non-stationary Signals
The Stockwell Transform Applied on Bio-signals and Electric Signals
Publication Date: February 2014 Hardback 160 pp.
Non-stationary signals are generally found in nature and any information concerning such signals cannot easily be described or predicted. The extraction, analysis and classification of these signals are complicated by different types of noise. As any false results could possibly have dire consequences, the robustness of tools used for these purposes in certain fields is of course vital.
With this in mind, the authors of this book present here original methods and algorithms for extracting information from non-stationary signals such as heart sounds and power electric signals. The methods proposed focus on the time–frequency (TF) domain, most notably on the Stockwell transform for the feature extraction process and the identification of signatures.
The advanced signal processing tools and techniques presented in this book and the originality of the authors’ contributions will prove very useful for those involved in engineering and research in the field of signal processing, as well as for professionals in industry and healthcare.
1. The Need for Time–Frequency Analysis.
2. Time–Frequency Analysis: The S-Transform.
3. Segmentation and Classification of Heart Sounds Based on the S-Transform.
4. Adaline for the Detection of Electrical Events in Electrical Signals.
5. FPGA Implementation of the Adaline.
About the Authors
Ali Moukadem is a post-doctoral researcher at the MIPS laboratory at the University of Haute Alsace in France. His research interests include time-frequency analysis, multi-resolution analysis, non-stationary signals, and biomedical signals.
Djaffar Ould Abdeslam is Associate-Professor at the University of Haute Alsace in France. His research interests include advanced and intelligent methods for power quality improvement and monitoring, the control of Active Power Filters (APF) with ANNs and fuzzy logic and the hardware implementation of ANNs.
Alain Dieterlen is Professor at the MIPS laboratory at the University of Haute Alsace in France. His research interests include instrumentation, image and signal processing.