Advanced

Frequency tracking of atrial fibrillation using hidden Markov models.

Sandberg, Frida LU ; Stridh, Martin LU and Sörnmo, Leif LU (2008) In IEEE Transactions on Biomedical Engineering 55(2). p.502-511
Abstract
A hidden Markov model (HMM) is employed to improve noise robustness when tracking the dominant frequency of atrial fibrillation (AF) in the electrocardiogram (ECG). Following QRST cancellation, a sequence of observed frequency states is obtained from the residual ECG, using the short-time Fourier transform. Based on the observed state sequence, the Viterbi algorithm retrieves the optimal state sequence by exploiting the state transition matrix, incorporating knowledge on AF characteristics, and the observation matrix, incorporating knowledge of the frequency estimation method and signal-to-noise ratio (SNR). The tracking method is evaluated with simulated AF signals to which noise, obtained from ECG recordings, has been added at different... (More)
A hidden Markov model (HMM) is employed to improve noise robustness when tracking the dominant frequency of atrial fibrillation (AF) in the electrocardiogram (ECG). Following QRST cancellation, a sequence of observed frequency states is obtained from the residual ECG, using the short-time Fourier transform. Based on the observed state sequence, the Viterbi algorithm retrieves the optimal state sequence by exploiting the state transition matrix, incorporating knowledge on AF characteristics, and the observation matrix, incorporating knowledge of the frequency estimation method and signal-to-noise ratio (SNR). The tracking method is evaluated with simulated AF signals to which noise, obtained from ECG recordings, has been added at different SNRs. The results show that the use of HMM improves performance considerably by reducing the rms error associated with frequency tracking: at 4-dB SNR, the rms error drops from 0.2 to 0.04 Hz. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
IEEE Transactions on Biomedical Engineering
volume
55
issue
2
pages
502 - 511
publisher
IEEE--Institute of Electrical and Electronics Engineers Inc.
external identifiers
  • pmid:18269985
  • wos:000252622200012
  • scopus:38349013346
ISSN
0018-9294
DOI
10.1109/TBME.2007.905488
language
English
LU publication?
yes
id
11b2c8f6-8466-405a-b275-cecd0605870a (old id 1042032)
date added to LUP
2008-03-14 10:11:43
date last changed
2017-07-23 04:22:08
@article{11b2c8f6-8466-405a-b275-cecd0605870a,
  abstract     = {A hidden Markov model (HMM) is employed to improve noise robustness when tracking the dominant frequency of atrial fibrillation (AF) in the electrocardiogram (ECG). Following QRST cancellation, a sequence of observed frequency states is obtained from the residual ECG, using the short-time Fourier transform. Based on the observed state sequence, the Viterbi algorithm retrieves the optimal state sequence by exploiting the state transition matrix, incorporating knowledge on AF characteristics, and the observation matrix, incorporating knowledge of the frequency estimation method and signal-to-noise ratio (SNR). The tracking method is evaluated with simulated AF signals to which noise, obtained from ECG recordings, has been added at different SNRs. The results show that the use of HMM improves performance considerably by reducing the rms error associated with frequency tracking: at 4-dB SNR, the rms error drops from 0.2 to 0.04 Hz.},
  author       = {Sandberg, Frida and Stridh, Martin and Sörnmo, Leif},
  issn         = {0018-9294},
  language     = {eng},
  number       = {2},
  pages        = {502--511},
  publisher    = {IEEE--Institute of Electrical and Electronics Engineers Inc.},
  series       = {IEEE Transactions on Biomedical Engineering},
  title        = {Frequency tracking of atrial fibrillation using hidden Markov models.},
  url          = {http://dx.doi.org/10.1109/TBME.2007.905488},
  volume       = {55},
  year         = {2008},
}