Soft Computing

, Volume 17, Issue 2, pp 333–343

Human activity recognition based on a sensor weighting hierarchical classifier

  • Oresti Banos
  • Miguel Damas
  • Hector Pomares
  • Fernando Rojas
  • Blanca Delgado-Marquez
  • Olga Valenzuela
Focus

DOI: 10.1007/s00500-012-0896-3

Cite this article as:
Banos, O., Damas, M., Pomares, H. et al. Soft Comput (2013) 17: 333. doi:10.1007/s00500-012-0896-3

Abstract

The analysis of daily living human behavior has proven to be of key importance to prevent unhealthy habits. The diversity of activities and the individuals’ particular execution style determine that several sources of information are normally required. One of the main issues is to optimally combine them to guarantee performance, scalability and robustness. In this paper we present a fusion classification methodology which takes into account the potential of the individual decisions yielded at both activity and sensor classification levels. Particularly tested on a wearable sensors based system, the method reinforces the idea that some parts of the body (i.e., sensors) may be specially informative for the recognition of each particular activity, thus supporting the ranking of the decisions provided by each associated sensor decision entity. Our method systematically outperforms the results obtained by traditional multiclass models which otherwise may require a high-dimensional feature space to acquire a similar performance. The comparison with other activity-recognition fusion approaches also demonstrates our model scales significantly better for small sensor networks.

Keywords

Multisource fusion Hierarchical classification Weighted decision Binary classifiers Activity recognition Wearable sensors 

Copyright information

© Springer-Verlag 2012

Authors and Affiliations

  • Oresti Banos
    • 1
  • Miguel Damas
    • 1
  • Hector Pomares
    • 1
  • Fernando Rojas
    • 1
  • Blanca Delgado-Marquez
    • 2
  • Olga Valenzuela
    • 3
  1. 1.Department of Computer Architecture and Computer TechnologyCITIC-UGR, University of GranadaGranadaSpain
  2. 2.Department of International EconomicsUniversity of GranadaGranadaSpain
  3. 3.Department of Applied MathematicsUniversity of GranadaGranadaSpain