Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

6-2012

Abstract

Power consumption on mobile phones is a painful obstacle towards adoption of continuous sensing driven applications, e.g., continuously inferring individual’s locomotive activities (such as ‘sit’, ‘stand’ or ‘walk’) using the embedded accelerometer sensor. To reduce the energy overhead of such continuous activity sensing, we first investigate how the choice of accelerometer sampling frequency & classification features affects, separately for each activity, the “energy overhead” vs. “classification accuracy” tradeoff. We find that such tradeoff is activity specific. Based on this finding, we introduce an activity-sensitive strategy (dubbed “A3R” – Adaptive Accelerometer-based Activity Recognition) for continuous activity recognition, where the choice of both the accelerometer sampling frequency and the classification features is adapted in real-time, as an individual performs daily lifestyle-based activities. We evaluate the performance of A3R using longitudinal, multi-day observations of continuous activity traces. We also implement A3R for the android platform and carry out evaluation of energy savings. We show that our strategy can achieve an energy savings of 50% under ideal conditions. For a real test case with users running the application on their android phones, we achieve an energy savings of 20-25%.

Keywords

energy efficient learning, continuous activity recognition, NCCR-MICS, NCCR-MICS/ESDM

Discipline

Digital Communications and Networking | Software Engineering

Research Areas

Software and Cyber-Physical Systems

Publication

2012 16th International Symposium on Wearable Computers: Newcastle, June 18-22: Proceedings

First Page

17

Last Page

24

ISBN

9781467315838

Identifier

10.1109/ISWC.2012.23

Publisher

IEEE Computer Society

City or Country

Los Alamitos, CA

Copyright Owner and License

LARC

Additional URL

https://doi.org/10.1109/ISWC.2012.23

Download

Share

COinS