(To see other currencies, click on price)
MORE ABOUT THIS BOOK
Main description:
This book is a practical guide to the field of biomedical signal processing and pattern recognition. The authors provide a self-contained volume that will address all the main issues – e.g., signal peculiarities, popular algorithms, key application examples, etc. – as well as provide an overview of common traps and mistakes and how to avoid them. The book makes extensive use of pseudo-code and code samples. It discusses available open source toolboxes as well. This book will the non-specilist up to speed with regard to relevant signal processing and pattern recognition. More importantly, it will enable the reader to either program the necessary algorithms or to modify existing open source libraries.
This book fills a gap in several new interdisciplinary areas, such as human-machine interaction, affective computing, and computer games, that have as a common task the processing and analysis of biomedical data. Yet, it is also a valuable tool for students at the intermediate and advanced levels in more traditional biomedical pattern recognition.
Feature:
A self contained text covering topics from basic biomedical signal characteristics to applications
Back cover:
This book is a practical guide to the field of biomedical signal processing and pattern recognition. The authors provide a self-contained volume that will address all the main issues – e.g., signal peculiarities, popular algorithms, key application examples, etc. – as well as provide an overview of common traps and mistakes and how to avoid them. The book makes extensive use of pseudo-code and code samples. It discusses available open source toolboxes as well. This book will the non-specilist up to speed with regard to relevant signal processing and pattern recognition. More importantly, it will enable the reader to either program the necessary algorithms or to modify existing open source libraries.
This book fills a gap in several new interdisciplinary areas, such as human-machine interaction, affective computing, and computer games, that have as a common task the processing and analysis of biomedical data. Yet, it is also a valuable tool for students at the intermediate and advanced levels in more traditional biomedical pattern recognition.
Contents:
PART I – THE BASICS
1. Introduction and book overview
2. Biomedical signal characteristics
2.1. Time series
2.2. Medical Images
3. Signal Preprocessing
3.1. Frequency domain filters
3.2. Spatial filters
3.3. Referencing
3.4. Image enhancement
3.5. Blind source separation (PCA, ICA, SVD)
4. Domain transformations and typical features
4.1. EEG
4.2. EMG
4.3. ECG
4.4. Medical Images
4.5. Other signals (GSR, nIRS, etc.)
PART II – ALGORITHMS
5. Overview
5.1. Discriminative vs. Generative
5.2. Supervised learning
5.3. Unsupervised learning
5.4. Reinforcement learning
5.5. Transduction
6. Bayesian approaches
7. K-nearest neighbour
8. Linear discriminant analysis
9. Support vector machines
10. Quadratic classifiers
11. Evolutionary Algorithms
12. Artificial neural networks
13. Hidden Markov models
14. Features Selection
14.1. Statistical class separation
14.2. Classifier dependent
15. Adaptive Algorithms
PART III – APPLICATIONS (short literature review + 1 fully worked example including online data and code)
16. EEG
17. EMG
18. ECG
19. Medical Images
APPENDICES (if needed)
mathematical proofs (?)
code samples (?)
PRODUCT DETAILS
Publisher: Springer (Springer Netherlands)
Publication date: August, 2016
Pages: 290
Availability: Not available (reason unspecified)
Subcategories: Biomedical Engineering
From the same series
