Multimodal Data Enabled Motion Detection and Recognition in Exercise Social Networks

DOI

10.2991/meic-14.2014.322How to use a DOI?

Keywords

Multmodal data; social network; motion recognition; smart phone; sensor

Abstract

With the stress of working and living increasing day by day, a fairly large number of people have been in the state of sub-health. Therefore, in developed countries, health problems have become a social focus which cannot be ignored. In this paper, we utilize rich functions of smart phones, make them as social terminals providing daily convenient fitness services for the users. Users are connected by the exercise social network and can compete and treat their exercise points for coupons or games, etc. By processing multimodal data from three axis accelerator, gyroscope, direction sensor, together with pattern recognition, users can do body exercise through specified training motions such as raising dumbbells, deep crouch, sit-up, running recognized which will be identified and recorded for social usage. Our system leverages multimodal data processing to fit individuals so that we can get better accuracy no matter what the person’s habit is or what device he is using.

Copyright

© 2014, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Tingting Fu
AU  - Peng Gao
PY  - 2014/11
DA  - 2014/11
TI  - Multimodal Data Enabled Motion Detection and Recognition in Exercise Social Networks
BT  - Proceedings of the 2014 International Conference on Mechatronics, Electronic, Industrial and Control Engineering
PB  - Atlantis Press
SP  - 1429
EP  - 1433
SN  - 2352-5401
UR  - https://doi.org/10.2991/meic-14.2014.322
DO  - 10.2991/meic-14.2014.322
ID  - Fu2014/11
ER  -