Classification of physical activities based on sparse representation

Shaopeng Liu; Robert X Gao; Dinesh John; John Staudenmayer; Patty S Freedson

doi:10.1109/EMBC.2012.6347410

Classification of physical activities based on sparse representation

Annu Int Conf IEEE Eng Med Biol Soc. 2012:2012:6200-3. doi: 10.1109/EMBC.2012.6347410.

Authors

Shaopeng Liu¹, Robert X Gao, Dinesh John, John Staudenmayer, Patty S Freedson

Affiliation

¹ Electromechanical Systems Laboratory, Department of Mechanical Engineering, University of Connecticut, Storrs, CT 06269, USA.

PMID: 23367345
DOI: 10.1109/EMBC.2012.6347410

Abstract

This paper presents a new classification method for physical activity assessment, based on sparse representation. This method bypasses the need for feature extraction and selection that is typically involved for activity classification, and classifies activities using raw sensor signals directly. Higher discriminative power than that from the conventional k-nearest neighbor algorithm has been demonstrated through experiments performed on 105 subjects.

MeSH terms

Algorithms
Humans
Motor Activity*