Login / Signup

Allumo: Preprocessing and Calibration Software for Wearable Accelerometers Used in Posture Tracking.

Alexis Fortin-CôtéJean-Sébastien RoyLaurent J BouyerPhilip JacksonAlexandre Campeau-Lecours
Published in: Sensors (Basel, Switzerland) (2019)
Inertial measurement units have recently shown great potential for the accurate measurement of joint angle movements in replacement of motion capture systems. In the race towards long duration tracking, inertial measurement units increasingly aim to ensure portability and long battery life, allowing improved ecological studies. Their main advantage over laboratory grade equipment is their usability in a wider range of environment for greater ecological value. For accurate and useful measurements, these types of sensors require a robust orientation estimation that remains accurate over long periods of time. To this end, we developed the Allumo software for the preprocessing and calibration of the orientation estimate of triaxial accelerometers. This software has an automatic orientation calibration procedure, an automatic erroneous orientation-estimate detection and useful visualization to help process long and short measurement periods. These automatic procedures are detailed in this paper, and two case studies are presented to showcase the usefulness of the software. The Allumo software is open-source and available online.
Keyphrases
  • high resolution
  • data analysis
  • deep learning
  • low cost
  • machine learning
  • human health
  • climate change
  • social media
  • minimally invasive
  • electronic health record
  • heart rate
  • neural network
  • mass spectrometry