Probabilistic Approaches to ECG Segmentation and Feature Extraction - Chapter 11

N. P. Hughes 

This page provides supplementary information and relevant links for Chapter 11 in Advanced Methods for ECG Analysis, which is co-edited by Francisco Azuaje and Patrick McSharry, and is published by Artech House. The main URL for this book can be found here, together with ordering information. Much of the software associated with this book can be found here.

 

Links:

• Pablo Laguna's list of publications 
• ecgpuwave - T-wave Analysis Software
• Netlab -- A free set of pattern recognition & neural network tools in Matlab by Ian Nabney. the associated book is simply wonderful. 
• ECGtools - A selection of ECG analysis tools in Matlab including a self-explaining QRS detector, filtering tools and HRV analysis algorithms.  

 

Contents:

11.1 Introduction 291

11.2 The Electrocardiogram

11.2.1 The ECG Waveform

11.2.2 ECG Interval Analysis

11.2.3 Manual ECG Interval Analysis

11.3 Automated ECG Interval Analysis

 

11.4 The Probabilistic Modeling Approach

 

11.5 Data Collection

 

11.6 Introduction to Hidden Markov modeling

11.6.1 Overview

11.6.2 Stochastic Processes and Markov Models

11.6.3 Hidden Markov Models

11.6.4 Inference in HMMs

11.6.5 Learning in HMMs

11.7 Hidden Markov Models for ECG Segmentation

11.7.1 Overview

11.7.2 ECG Signal Normalization

11.7.3 Types of Model Segmentations

11.7.4 Performance Evaluation

11.8 Wavelet Encoding of the ECG

11.8.1 Wavelet Transforms

11.8.2 HMMs with Wavelet Encoded ECG

11.9 Duration Modeling for Robust Segmentations

 

11.10 Conclusions

CHAPTER 12