Browse by author
Lookup NU author(s): Nils Hammerla,
Dr Peter Andras,
Dr Thomas Ploetz
Full text for this publication is not currently held within this repository. Alternative links are provided below where available.
The majority of activity recognition systems in wearable computing rely on a set of statistical measures, such as means and moments, extracted from short frames of continuous sensor measurements to perform recognition. These features implicitly quantify the distribution of data observed in each frame. However, feature selection remains challenging and labour intensive, rendering a more generic method to quantify distributions in accelerometer data much desired. In this paper we present the ECDF representation, a novel approach to preserve characteristics of arbitrary distributions for feature extraction which is particularly suitable for embedded applications. In extensive experiments on 6 publicly available datasets we demonstrate that it outperforms common approaches to feature extraction across a wide variety of tasks.
Author(s): Hammerla N, Kirkham R, Andras P, Ploetz T
Publication type: Conference Proceedings (inc. Abstract)
Publication status: Published
Conference Name: International Symposium on Wearable Computers (ISWC)
Year of Conference: 2013
Print publication date: 08/09/2013
Publisher: Association for Computing Machinery
Library holdings: Search Newcastle University Library for this item