Energy and Accuracy Trade-Offs in Accelerometry-Based Activity Recognition
Energy and Accuracy Trade-Offs in Accelerometry-Based Activity Recognition
Driven by real-world applications such as fitness, wellbeing and healthcare, accelerometry-based activity recognition has been widely studied to provide context-awareness to future pervasive technologies. Accurate recognition and energy efficiency are key issues in enabling long-term and unobtrusive monitoring. While the majority of accelerometry-based activity recognition systems stream data to a central point for processing, some solutions process data locally on the sensor node to save energy. In this paper, we investigate the trade-offs between classification accuracy and energy efficiency by comparing on- and off-node schemes. An empirical energy model is presented and used to evaluate the energy efficiency of both systems, and a practical case study (monitoring the physical activities of office workers) is developed to evaluate the effect on classification accuracy. The results show a 40% energy saving can be obtained with a 13% reduction in classification accuracy, but this performance depends heavily on the wearer’s activity.
activity recognition, body sensor networks, classification accuracy, energy efficiency
978-1-4673-5775-3
Wang, Ning
12c074fb-be39-46a1-b3b1-670e6e57c16c
Merrett, Geoff V.
89b3a696-41de-44c3-89aa-b0aa29f54020
Maunder, Robert G.
76099323-7d58-4732-a98f-22a662ccba6c
Rogers, Alex
f9130bc6-da32-474e-9fab-6c6cb8077fdc
July 2013
Wang, Ning
12c074fb-be39-46a1-b3b1-670e6e57c16c
Merrett, Geoff V.
89b3a696-41de-44c3-89aa-b0aa29f54020
Maunder, Robert G.
76099323-7d58-4732-a98f-22a662ccba6c
Rogers, Alex
f9130bc6-da32-474e-9fab-6c6cb8077fdc
Wang, Ning, Merrett, Geoff V., Maunder, Robert G. and Rogers, Alex
(2013)
Energy and Accuracy Trade-Offs in Accelerometry-Based Activity Recognition.
2013 22nd International Conference on Computer Communications and Networks (ICCCN), Nassau, Bahamas.
30 Jul - 02 Aug 2013.
6 pp
.
(doi:10.1109/ICCCN.2013.6614133).
Record type:
Conference or Workshop Item
(Paper)
Abstract
Driven by real-world applications such as fitness, wellbeing and healthcare, accelerometry-based activity recognition has been widely studied to provide context-awareness to future pervasive technologies. Accurate recognition and energy efficiency are key issues in enabling long-term and unobtrusive monitoring. While the majority of accelerometry-based activity recognition systems stream data to a central point for processing, some solutions process data locally on the sensor node to save energy. In this paper, we investigate the trade-offs between classification accuracy and energy efficiency by comparing on- and off-node schemes. An empirical energy model is presented and used to evaluate the energy efficiency of both systems, and a practical case study (monitoring the physical activities of office workers) is developed to evaluate the effect on classification accuracy. The results show a 40% energy saving can be obtained with a 13% reduction in classification accuracy, but this performance depends heavily on the wearer’s activity.
Text
merrett.pdf
- Accepted Manuscript
More information
Accepted/In Press date: 29 April 2013
Published date: July 2013
Additional Information:
(c) IEEE 2013
Venue - Dates:
2013 22nd International Conference on Computer Communications and Networks (ICCCN), Nassau, Bahamas, 2013-07-30 - 2013-08-02
Keywords:
activity recognition, body sensor networks, classification accuracy, energy efficiency
Organisations:
Agents, Interactions & Complexity, Electronic & Software Systems, Southampton Wireless Group
Identifiers
Local EPrints ID: 352018
URI: http://eprints.soton.ac.uk/id/eprint/352018
ISBN: 978-1-4673-5775-3
PURE UUID: 1ebccca7-78a2-429d-92a0-d5078a5c4c88
Catalogue record
Date deposited: 29 Apr 2013 10:41
Last modified: 15 Mar 2024 03:30
Export record
Altmetrics
Contributors
Author:
Ning Wang
Author:
Geoff V. Merrett
Author:
Robert G. Maunder
Author:
Alex Rogers
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics