Home // eTELEMED 2014, The Sixth International Conference on eHealth, Telemedicine, and Social Medicine // View article

Wearable Recognition System for Sports Activities

Authors:
Ali Mehmood Khan
Michael Lawo

Keywords: Physical activities; accelerometer sensor; classifier

Abstract:
Physical activity is a major part of a user's context for wearable computing applications. The system should be able to acquire the user's physical activities by using body worn sensors. We want to develop a sports activities recognition system that is practical, reliable, and can be used for health-care related applications. We propose to use the axivity device which is a readymade, light weight, small and easy to use device for identifying basic physical training activities (i.e., using elliptical trainer, butterfly, bench-press and pull down ) and different swimming styles (i.e., dolphin, back-stroke, breast-stroke and free-style) using decision tree classifier, Averaged one-dependence estimators (AODE) and Neural networks. In this paper, we present an approach to build a system that exhibits this property and provides evidence based on data for 8 different activities collected from 20 different subjects. Our results indicate that the system has a good rate of accuracy.

Pages: 1 to 5

Copyright: Copyright (c) IARIA, 2014

Publication date: March 23, 2014

Published in: conference

ISSN: 2308-4359

ISBN: 978-1-61208-327-8

Location: Barcelona, Spain

Dates: from March 23, 2014 to March 27, 2014