Particle Filters for Robust Estimation from Physiological Sensors in the Swarm
Viswam Nathan

Citation
Viswam Nathan. "Particle Filters for Robust Estimation from Physiological Sensors in the Swarm". Tutorial, 12, May, 2016.

Abstract
With the increased adoption of wearable sensors, we expect personal physiological monitoring to be an important application of the future. Pervasive and continuous monitoring of vitals offers several advantages over traditional, sporadic clinical visits. However, wearable sensors are typically much noisier than their medical grade counterparts. This talk explains how the particle filter, a probabilistic state estimation technique, can be applied to this problem to robustly estimate underlying physiological parameters in noisy environments. This will include real experimental results on heart rate monitoring under the condition of motion artifacts. Furthermore, we will explore the possibility of using the particle filter to effectively fuse information from multiple simultaneous sensors.

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. <a
    href="http://www.terraswarm.org/pubs/765.html"
    ><i>Particle Filters for Robust Estimation from
    Physiological Sensors in the Swarm</i></a>,
    Tutorial,  12, May, 2016.
  • Plain text
    Viswam Nathan. "Particle Filters for Robust Estimation
    from Physiological Sensors in the Swarm". Tutorial, 
    12, May, 2016.
  • BibTeX
    @tutorial{Nathan16_ParticleFiltersForRobustEstimationFromPhysiologicalSensors,
        author = {Viswam Nathan},
        title = {Particle Filters for Robust Estimation from
                  Physiological Sensors in the Swarm},
        day = {12},
        month = {May},
        year = {2016},
        abstract = {With the increased adoption of wearable sensors,
                  we expect personal physiological monitoring to be
                  an important application of the future. Pervasive
                  and continuous monitoring of vitals offers several
                  advantages over traditional, sporadic clinical
                  visits. However, wearable sensors are typically
                  much noisier than their medical grade
                  counterparts. This talk explains how the particle
                  filter, a probabilistic state estimation
                  technique, can be applied to this problem to
                  robustly estimate underlying physiological
                  parameters in noisy environments. This will
                  include real experimental results on heart rate
                  monitoring under the condition of motion
                  artifacts. Furthermore, we will explore the
                  possibility of using the particle filter to
                  effectively fuse information from multiple
                  simultaneous sensors.},
        URL = {http://terraswarm.org/pubs/765.html}
    }
    

Posted by Elizabeth Coyne on 17 Mar 2016.
Groups: services

Notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright.