Real-Time Robust Heart Rate Estimation Based on Bayesian Framework and Grid Filters

Real-Time Robust Heart Rate Estimation Based on Bayesian Framework and Grid Filters

Radoslav Bortel (Czech Technical University in Prague, Czech Republic) and Pavel Sovka (Czech Technical University in Prague, Czech Republic)
Copyright: © 2012 |Pages: 24
DOI: 10.4018/978-1-4666-1803-9.ch005
OnDemand PDF Download:
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

In this chapter, the authors discuss derivation, implementation, and testing of a robust real-time algorithm for the estimation of heart rate (HR) from electrocardiograms recorded on subjects performing vigorous physical activity. They formulate the problem of HR estimation as a problem of inference in a Bayesian network, which utilizes prior information about the probability distribution of HR changes. From this formulation they derive an inference procedure, which can be implemented as a grid filter. The resulting algorithm can then follow even a rapidly changing HR, whilst withstanding a series of missed or false QRS detections. Also, the HR estimate is complete with confidence intervals to allow the identification of the moments, where the precision of HR estimation is lowered. Additionally, the computational complexity of this algorithm is acceptable for battery powered portable devices.
Chapter Preview
Top

Background

The signal processing chain for the HR estimation is shown in Figure 1. First, the electric potentials created by the heart are measured, amplified and digitized. After, an algorithm commonly termed as a QRS complex detector, or simply QRS detector, searches the ECG signal, and identifies all the recognizable QRS complexes. Last, the positions of the QRS complexes are used to estimate the HR of the measured subject.

Figure 1.

The signal processing chain used for the heart rate estimation

978-1-4666-1803-9.ch005.f01

Even though in this chapter we will concentrate chiefly on the last stage - the HR estimation - it is important to understand characteristics of data we are going to process. Therefore, in this section we will provide a brief overview of all the above-mentioned signal processing stages. Namely, we will comment on heart activity, ECG signal measurement, QRS complex detection, current state of the art of a robust HR estimation, and also on the Bayesian framework that we are going to use in the design our HR estimator.

Complete Chapter List

Search this Book:
Reset