Statistical Machine Learning for Automatic Assessment of Physical Activity Intensity Using Multi-axial Accelerometry and Heart Rate

Garcia Garcia, Fernando and García Sáez, Gema and Chausa Fernández, Paloma and Martínez Sarriegui, Iñaki and Benito Peinado, Pedro José and Gómez Aguilera, Enrique J. and Hernando Pérez, María Elena (2011). Statistical Machine Learning for Automatic Assessment of Physical Activity Intensity Using Multi-axial Accelerometry and Heart Rate. In: "AIME'11 13th conference on Artificial intelligence in medicine", 02/07/2011 - 06/072011, Bled, Eslovenia. ISBN 978-3-642-22217-7.

Description

Title: Statistical Machine Learning for Automatic Assessment of Physical Activity Intensity Using Multi-axial Accelerometry and Heart Rate
Author/s:
  • Garcia Garcia, Fernando
  • García Sáez, Gema
  • Chausa Fernández, Paloma
  • Martínez Sarriegui, Iñaki
  • Benito Peinado, Pedro José
  • Gómez Aguilera, Enrique J.
  • Hernando Pérez, María Elena
Item Type: Presentation at Congress or Conference (Unspecified)
Event Title: AIME'11 13th conference on Artificial intelligence in medicine
Event Dates: 02/07/2011 - 06/072011
Event Location: Bled, Eslovenia
Title of Book: AIME'11 Proceedings of the 13th conference on Artificial intelligence in medicine
Date: 2011
ISBN: 978-3-642-22217-7
Subjects:
Faculty: E.T.S.I. Telecomunicación (UPM)
Department: Tecnología Fotónica [hasta 2014]
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (786kB) | Preview

Abstract

This work explores the automatic recognition of physical activity intensity patterns from multi-axial accelerometry and heart rate signals. Data collection was carried out in free-living conditions and in three controlled gymnasium circuits, for a total amount of 179.80 h of data divided into: sedentary situations (65.5%), light-to-moderate activity (17.6%) and vigorous exercise (16.9%). The proposed machine learning algorithms comprise the following steps: time-domain feature definition, standardization and PCA projection, unsupervised clustering (by k-means and GMM) and a HMM to account for long-term temporal trends. Performance was evaluated by 30 runs of a 10-fold cross-validation. Both k-means and GMM-based approaches yielded high overall accuracy (86.97% and 85.03%, respectively) and, given the imbalance of the dataset, meritorious F-measures (up to 77.88%) for non-sedentary cases. Classification errors tended to be concentrated around transients, what constrains their practical impact. Hence, we consider our proposal to be suitable for 24 h-based monitoring of physical activity in ambulatory scenarios and a first step towards intensity-specific energy expenditure estimators

More information

Item ID: 14157
DC Identifier: http://oa.upm.es/14157/
OAI Identifier: oai:oa.upm.es:14157
Official URL: http://www.aimedicine.info/aime11/
Deposited by: Memoria Investigacion
Deposited on: 19 Dec 2012 09:55
Last Modified: 21 Apr 2016 13:41
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM