Practical guide for biomedical signals analysis using machine learning techniques : a MATLAB based approach
This volume presents how machine learning and biomedical signal processing methods can be used in biomedical signal analysis. Different machine learning applications in biomedical signal analysis, including those for electrocardiogram, electroencephalogram and electromyogram are described in a pract...
Saved in:
| Main Author: | |
|---|---|
| Format: | eBook Book |
| Language: | English |
| Published: |
London
Academic Press, an imprint of Elsevier
2019
Elsevier Science & Technology Academic Press |
| Edition: | 1 |
| Subjects: | |
| ISBN: | 9780128174449, 0128174447 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Table of Contents:
- Front Cover -- Practical Guide for Biomedical Signals Analysis Using Machine Learning Techniques: A MATLAB® Based Approach -- Copyright -- Dedication -- Contents -- Preface -- Acknowledgments -- Chapter 1: Introduction and Background -- 1.1. Electroencephalography -- 1.2. Electromyography -- 1.3. Electrocardiography -- 1.4. Phonocardiography -- 1.5. Photoplethysmography -- 1.6. Other Biomedical Signals -- 1.6.1. The Electroneurogram -- 1.6.2. The Electroretinogram -- 1.6.3. The Electrooculogram -- 1.6.4. The Electrogastrogram -- 1.6.5. The Carotid Pulse -- 1.6.6. The Vibromyogram -- 1.7. Machine Learning Methods -- References -- Chapter 2: Biomedical Signals -- 2.1. The Electroencephalogram -- 2.1.1. Introduction -- 2.1.2. The Nervous System -- 2.1.3. The Brain -- 2.1.4. Electroencephalography -- 2.1.5. Historical Perspective -- 2.1.6. EEG Recording Techniques -- 2.1.7. The EEG Measured on the Scalp -- 2.1.8. EEG Rhythms and Waveforms -- 2.1.9. Uses of EEG Signals in Epileptic Seizure Detection and Prediction -- 2.1.10. Uses of EEG Signals in Brain-Computer Interfacing -- 2.1.11. Uses of EEG Signals in Migraine Detection -- 2.1.12. Uses of EEG Signals in Source Localization -- 2.1.13. Uses of EEG Signals in Sleep -- 2.1.14. Uses of EEG Signal for Emotion Recognition -- 2.1.15. Freiburg EEG Database for Epileptic Seizure Prediction and Detection -- 2.2. The Electromyogram -- 2.2.1. Introduction -- 2.2.2. The Electromyograph and Instrumentation -- 2.2.3. EMG Electrodes -- 2.2.4. Signal Acquisition -- 2.2.5. Signal Amplification and Filtering -- 2.2.6. Signal Digitization -- 2.2.7. The Motor Unit Action Potential -- 2.2.8. Myoelectric Signal Recording -- 2.2.9. Neuromuscular Disorders -- 2.2.10. Uses of EMG Signals in Diagnosis of Neuromuscular Disorders -- 2.2.11. Uses of EMG Signals in Prosthesis Control
- 3.5.1. Short-Time Fourier Transform: The Spectrogram -- 3.5.2. Wigner-Ville Distribution -- 3.5.3. Choi-Williams Distribution -- 3.5.4. Analytic Signal -- 3.5.5. Wavelet Analysis -- 3.5.6. Continuous Wavelet Transform -- 3.5.7. Discrete Wavelet Transform -- 3.5.8. Stationary Wavelet Transform -- 3.5.9. Wavelet Packet Decomposition -- 3.5.10. Dual Tree Complex Wavelet Transform -- 3.5.11. Tunable Q-Factor Wavelet Transform -- 3.5.12. Flexible Analytic Wavelet Transform -- 3.5.13. Empirical Wavelet Transform -- 3.5.14. Empirical Mode Decomposition -- 3.5.15. Ensemble Empirical Mode Decomposition -- 3.5.16. Complete Ensemble Empirical Mode Decomposition -- References -- Chapter 4: Feature Extraction and Dimension Reduction -- 4.1. Introduction -- 4.2. Feature Extraction Methods -- 4.2.1. Examples for Feature Extraction -- 4.3. Dimension Reduction/Feature Selection Methods -- 4.3.1. Statistical Features -- 4.3.2. Examples With Statistical Features -- 4.3.3. Entropy -- 4.3.4. Kolmogorov Entropy -- 4.3.5. Approximate and Sample Entropy -- 4.3.6. Detrended Fluctuation Analysis -- 4.3.7. Principal Component Analysis -- 4.3.8. Independent Component Analysis -- 4.3.9. Linear Discriminant Analysis -- 4.4. Electrocardiogram Signal Preprocessing -- 4.4.1. QRS Detection Algorithms -- References -- Chapter 5: Biomedical Signal Classification Methods -- 5.1. Introduction -- 5.2. Performance Evaluation Metrics -- 5.3. Linear Discriminant Analysis -- 5.4. Naïve Bayes -- 5.5. k-Nearest Neighbor -- 5.6. Artificial Neural Networks -- 5.7. Support Vector Machines -- 5.8. Decision Tree (DT) -- 5.9. Deep Learning -- References -- Index -- Back Cover
- 2.2.12. Uses of EMG Signals in Rehabilitation Robotics -- 2.2.13. Other EMG Applications -- 2.3. The Electrocardiogram -- 2.3.1. Introduction -- 2.3.2. Electrocardiogram Signals -- 2.3.3. Physiology -- 2.3.4. The ECG Waveform -- 2.3.5. Heart Diseases -- 2.3.6. Uses of ECG Signals in Diagnosis of Heart Arrhythmia -- 2.3.7. Uses of ECG Signals in Congestive Heart Failure Detection -- 2.3.8. Uses of ECG Signals in Sleep Apnea Detection -- 2.3.9. Uses of ECG Signals in Fetal Analysis -- 2.4. Phonocardiogram -- 2.4.1. Heart Murmurs -- 2.4.2. First Heart Sound (S1) -- 2.4.2.1. Atrial Component -- 2.4.2.2. Mitral Component -- 2.4.2.3. Tricuspid Component -- 2.4.2.4. Aortic Component -- 2.4.3. Second Heart Sound (S2) -- 2.4.4. Third Heart Sound (S3) -- 2.4.5. Fourth Heart Sound (S4) -- 2.4.6. Uses of PCG Signals in Diagnosis of Heart Diseases -- 2.5. Photoplethysmography -- 2.6. Other Biomedical Signals -- 2.6.1. Electroneurogram -- 2.6.2. Electroretinogram -- 2.6.3. Electrooculogram -- 2.6.4. Electrogastrogram -- 2.6.5. Carotid Pulse -- 2.6.6. Vibromyogram -- 2.6.7. Vibroarthrogram -- References -- Further Reading -- Chapter 3: Biomedical Signal Processing Techniques -- 3.1. Introduction to Spectral Analysis -- 3.2. Power Spectral Density -- 3.2.1. Continuous-Time Fourier Series Analysis -- 3.2.2. Discrete-Time Fourier Series Analysis -- 3.2.3. Frequency Resolution -- 3.2.4. Windowing Techniques -- 3.2.5. Periodogram Power Spectral Density -- 3.2.6. Welch Power Spectral Density -- 3.3. Parametric Model-Based Methods -- 3.3.1. Autoregressive Model for Spectral Analysis -- 3.3.2. Yule-Walker AR Modeling -- 3.3.3. Covariance Method -- 3.3.4. Modified Covariance Method -- 3.3.5. Burg Method -- 3.4. Subspace-Based Methods for Spectral Analysis -- 3.4.1. MUSIC Modeling -- 3.4.2. Eigenvector Modeling -- 3.5. Time-Frequency Analysis