A Particle Filter Framework for the Estimation of Heart Rate from ECG Signals Corrupted by Motion Artifacts
Viswam Nathan, Ilge Akkaya, Roozbeh Jafari

Citation
Viswam Nathan, Ilge Akkaya, Roozbeh Jafari. "A Particle Filter Framework for the Estimation of Heart Rate from ECG Signals Corrupted by Motion Artifacts". EMBC 2015, 25, August, 2015.

Abstract
In this work we describe a methodology to probabilistically estimate the locations of R-peaks in an electrocardiogram (ECG) stream using a particle filter. This is useful for heart rate estimation, which is an important metric for medical diagnostics. Some scenarios require constant monitoring in-home using a wearable device and this is an especially challenging task due to the likelihood of the ECG signals being disrupted by motion artifacts. In this work we show how, with appropriate models for the heart rate and the observations of R-peaks, the particle filter can effectively track the true R-peak locations amidst the motion artifacts. A particle filter based framework has several advantages due to its freedom from assumptions about the models for the signal and noise, as well as its ability to track multiple possible heart rates at the same time. Moreover the proposed framework is not exclusive to ECG signals and could easily be leveraged for tracking other physiological parameters given suitable models. We describe the implementation of the particle filter and validate it on real ECG data affected by motion artifacts from the MIT-BIH noise stress test database. The average error between the estimated heart rate and the true heart rate is around 5 beats per minute for signal streams contaminated with noisy segments with SNR as low as -6dB.

Electronic downloads

Internal. This publication has been marked by the author for TerraSwarm-only distribution, so electronic downloads are not available without logging in.

Citation formats

• HTML

  Viswam Nathan, Ilge Akkaya, Roozbeh Jafari. <a
  href="http://www.terraswarm.org/pubs/538.html"
  >A Particle Filter Framework for the Estimation of Heart
  Rate from ECG Signals Corrupted by Motion
  Artifacts</a>, EMBC 2015, 25, August, 2015.

• Plain text

  Viswam Nathan, Ilge Akkaya, Roozbeh Jafari. "A Particle
  Filter Framework for the Estimation of Heart Rate from ECG
  Signals Corrupted by Motion Artifacts". EMBC 2015, 25,
  August, 2015.

• BibTeX

  @inproceedings{NathanAkkayaJafari15_ParticleFilterFrameworkForEstimationOfHeartRateFromECG,
      author = {Viswam Nathan and Ilge Akkaya and Roozbeh Jafari},
      title = {A Particle Filter Framework for the Estimation of
                Heart Rate from ECG Signals Corrupted by Motion
                Artifacts},
      booktitle = {EMBC 2015},
      day = {25},
      month = {August},
      year = {2015},
      abstract = {In this work we describe a methodology to
                probabilistically estimate the locations of
                R-peaks in an electrocardiogram (ECG) stream using
                a particle filter. This is useful for heart rate
                estimation, which is an important metric for
                medical diagnostics. Some scenarios require
                constant monitoring in-home using a wearable
                device and this is an especially challenging task
                due to the likelihood of the ECG signals being
                disrupted by motion artifacts. In this work we
                show how, with appropriate models for the heart
                rate and the observations of R-peaks, the particle
                filter can effectively track the true R-peak
                locations amidst the motion artifacts. A particle
                filter based framework has several advantages due
                to its freedom from assumptions about the models
                for the signal and noise, as well as its ability
                to track multiple possible heart rates at the same
                time. Moreover the proposed framework is not
                exclusive to ECG signals and could easily be
                leveraged for tracking other physiological
                parameters given suitable models. We describe the
                implementation of the particle filter and validate
                it on real ECG data affected by motion artifacts
                from the MIT-BIH noise stress test database. The
                average error between the estimated heart rate and
                the true heart rate is around 5 beats per minute
                for signal streams contaminated with noisy
                segments with SNR as low as -6dB.},
      URL = {http://terraswarm.org/pubs/538.html}
  }
  

Posted by Barb Hoversten on 21 Apr 2015.
Groups: services