A distributed hidden markov model for fine-grained annotation in body sensor networks

Eric Guenterberg, Hassan Ghasemzadeh, Roozbeh Jafari

Research output: Chapter in Book/Report/Conference proceedingConference contribution

20 Scopus citations

Abstract

Human movement models often divide movements into parts. In walking the stride can be segmented into four different parts, and in golf and other sports, the swing is divided into section based on the primary direction of motion. When analyzing a movement, it is important to correctly locate the key events dividing portions. There exist methods for dividing certain actions using data from specific sensors. We introduce a generalized method for event annotation based on Hidden Markov Models. Genetic algorithms are used for feature selection and model parameterization. Further, collaborative techniques are explored. We validate this method on a walking dataset using inertial sensors placed on various locations on a human body. Our technique is computationally simple to allow it to run on resource constrained sensor nodes.

Original languageEnglish (US)
Title of host publicationProceedings - 2009 6th International Workshop on Wearable and Implantable Body Sensor Networks, BSN 2009
Pages339-344
Number of pages6
DOIs
StatePublished - 2009
Externally publishedYes
Event2009 6th International Workshop on Wearable and Implantable Body Sensor Networks, BSN 2009 - Berkeley, CA, United States
Duration: Jun 3 2009Jun 5 2009

Publication series

NameProceedings - 2009 6th International Workshop on Wearable and Implantable Body Sensor Networks, BSN 2009

Other

Other2009 6th International Workshop on Wearable and Implantable Body Sensor Networks, BSN 2009
Country/TerritoryUnited States
CityBerkeley, CA
Period6/3/096/5/09

Keywords

  • Body sensor networks
  • Distributed
  • Hidden markov models
  • Segmentation

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Hardware and Architecture
  • Biomedical Engineering
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'A distributed hidden markov model for fine-grained annotation in body sensor networks'. Together they form a unique fingerprint.

Cite this