Power-accuracy tradeoffs in human activity transition detection

Jeffrey Boyd, Hari Sundaram, Aviral Shrivastava

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Wearable, mobile computing platforms are envisioned to be used in out-patient monitoring and care. These systems continuously perform signal filtering, transformations, and classification, which are quite compute intensive, and quickly drain the system energy. The design space of these human activity sensors is large and includes the choice of sampling frequency, feature detection algorithm, length of the window of transition detection etc., and all these choices fundamentally trade-off power/performance for accuracy of detection. In this work, we explore this design space, and make several interesting conclusions that can be used as rules of thumb for quick, yet power-efficient designs of such systems. For instance, we find that the x-axis of our signal, which was oriented to be parallel to the forearm, is the most important signal to be monitored, for our set of hand activities. Our experimental results show that by carefully choosing system design parameters, there is considerable (5X) scope of improving the performance/power of the system, for minimal (5%) loss in accuracy.

Original languageEnglish (US)
Title of host publicationDATE 10 - Design, Automation and Test in Europe
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages6
ISBN (Print)9783981080162
StatePublished - 2010
Externally publishedYes
EventDesign, Automation and Test in Europe Conference and Exhibition, DATE 2010 - Dresden, Germany
Duration: Mar 8 2010Mar 12 2010

Publication series

NameProceedings -Design, Automation and Test in Europe, DATE
ISSN (Print)1530-1591


OtherDesign, Automation and Test in Europe Conference and Exhibition, DATE 2010

ASJC Scopus subject areas

  • General Engineering


Dive into the research topics of 'Power-accuracy tradeoffs in human activity transition detection'. Together they form a unique fingerprint.

Cite this