Home // ADAPTIVE 2019, The Eleventh International Conference on Adaptive and Self-Adaptive Systems and Applications // View article

Real-Time Activity Recognition Utilizing Dynamically On-Body Placed Smartphones

Authors:
Marc Kurz
Bernhard Hiesl
Erik Sonnleitner

Keywords: Activity recognition; Mobile sensing; Self-adaptation; Adaptive application; Adaptive real-time strategies

Abstract:
This work-in-progress paper presents a project that deals with real-time recognition of people's activities by utilizing commercial smartphones. One important and crucial aspect is that the phone can be placed on various on-body positions (with different orientation and rotation), thus the system has to adapt autonomously to the current phone-location. There are many possibilities to purse the smartphone - for example, facing downwards to your body, facing up away from your body, left or right pocket or even back pocket. The application has to adapt to these variations of the on-body positions to fulfill the activity recognition task in real-time. The activities that are considered in this paper are five common modes of locomotion: (i) standing, (ii) walking, (iii) running, (iv) stairs-up and (v) stairs-down. The paper presents the problem definition, reflects related work on this topic, showing the relevance of the project, and discusses the intended approach, expected results and already conducted work.

Pages: 84 to 87

Copyright: Copyright (c) IARIA, 2019

Publication date: May 5, 2019

Published in: conference

ISSN: 2308-4146

ISBN: 978-1-61208-706-1

Location: Venice, Italy

Dates: from May 5, 2019 to May 9, 2019