The Community for Technology Leaders
2007 11th IEEE International Symposium on Wearable Computers (2007)
Boston, MA, USA
Oct. 11, 2007 to Oct. 13, 2007
ISBN: 978-1-4244-1452-9
pp: 1-4
Emmanuel Munguia Tapia , House_n, Massachusetts Institute of Technology, Cambridge, MA, USA, emunguia@mit.edu
Stephen S. Intille , House_n, Massachusetts Institute of Technology, Cambridge, MA, USA, intille@mit.edu
William Haskell , Stanford Medical School, Palo Alto, CA, USA
Kent Larson , House_n, Massachusetts Institute of Technology, Cambridge, MA, USA
Julie Wright , Boston Medical Center, Boston, MA USA
Abby King , Stanford Medical School, Palo Alto, CA, USA
Robert Friedman , Boston Medical Center, Boston, MA USA
ABSTRACT
In this paper, we present a real-time algorithm for automatic recognition of not only physical activities, but also, in some cases, their intensities, using five triaxial wireless accelerometers and a wireless heart rate monitor. The algorithm has been evaluated using datasets consisting of 30 physical gymnasium activities collected from a total of 21 people at two different labs. On these activities, we have obtained a recognition accuracy performance of 94.6% using subject-dependent training and 56.3% using subject-independent training. The addition of heart rate data improves subject-dependent recognition accuracy only by 1.2% and subject-independent recognition only by 2.1%. When recognizing activity type without differentiating intensity levels, we obtain a subject-independent performance of 80.6%. We discuss why heart rate data has such little discriminatory power.
INDEX TERMS
CITATION

K. Larson et al., "Real-Time Recognition of Physical Activities and Their Intensities Using Wireless Accelerometers and a Heart Rate Monitor," 2007 11th IEEE International Symposium on Wearable Computers(ISWC), Boston, MA, USA, 2007, pp. 1-4.
doi:10.1109/ISWC.2007.4373774
93 ms
(Ver 3.3 (11022016))