Towards accelerometry based static posture identification

Human activity classification has wide-spread applications ranging from human computer interaction to disease progression studies. In this paper we propose a body posture model based on the Euler angles of the torso, arms and legs. The Euler angles are computed based on data streams originating from...

Full description

Saved in:
Bibliographic Details
Published in2011 IEEE Consumer Communications and Networking Conference (CCNC) pp. 29 - 33
Main Authors Min Xu, Goldfain, Albert, Chowdhury, Atanu Roy, DelloStritto, Jim
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.01.2011
Subjects
Acceleration
Accelerometers
Accuracy
Clustering algorithms
Humans
Leg
Torso
Online AccessGet full text
ISBN9781424487899
1424487897
ISSN2331-9852
DOI10.1109/CCNC.2011.5766477

Cover

More Information
Summary:Human activity classification has wide-spread applications ranging from human computer interaction to disease progression studies. In this paper we propose a body posture model based on the Euler angles of the torso, arms and legs. The Euler angles are computed based on data streams originating from a wireless Body Sensor Network (BSN) comprising of nine accelerometers. Thereafter they are used to reconstruct different body postures based on an unsupervised learning and clustering algorithm. We validate our algorithm by implementing a classification engine in Matlab, capable of classifying subtle changes in posture with 97% accuracy.
ISBN:9781424487899
1424487897
ISSN:2331-9852
DOI:10.1109/CCNC.2011.5766477