A framework to detect and classify activity transitions in low-power applications

Jeffrey Boyd, Hari Sundaram

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

Abstract

Minimizing the number of computations a low-power device makes is important to achieve long battery life. In this paper we present a framework for a low-power device to minimize the number of calculations needed to detect and classify simple activities of daily living such as sitting, standing, walking, reaching, and eating. This technique uses wavelet analysis as part of the feature set extracted from accelerometer data. A log-likelihood ratio test and Hidden Markov Models (HMM) are used to detect transitions and classify different activities. A tradeoff is made between power and accuracy.

Original languageEnglish (US)
Title of host publicationProceedings - 2009 IEEE International Conference on Multimedia and Expo, ICME 2009
Pages1716-1719
Number of pages4
DOIs
StatePublished - 2009
Externally publishedYes
Event2009 IEEE International Conference on Multimedia and Expo, ICME 2009 - New York, NY, United States
Duration: Jun 28 2009Jul 3 2009

Publication series

NameProceedings - 2009 IEEE International Conference on Multimedia and Expo, ICME 2009

Other

Other2009 IEEE International Conference on Multimedia and Expo, ICME 2009
Country/TerritoryUnited States
CityNew York, NY
Period6/28/097/3/09

Keywords

  • Gesture recognition
  • HMM
  • Inertial sensors
  • Low power
  • Wavelet analysis

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Computer Networks and Communications
  • Hardware and Architecture
  • Software

Fingerprint

Dive into the research topics of 'A framework to detect and classify activity transitions in low-power applications'. Together they form a unique fingerprint.

Cite this