On preserving statistical characteristics of accelerometry data using their empirical cumulative distribution

Hammerla, Nils Y; Kirkham, Reuben; Andras, Peter; Ploetz, Thomas

Abstract

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 six publicly available datasets we demonstrate that it outperforms common approaches to feature extraction across a wide variety of tasks.

Citation

Hammerla, N. Y., Kirkham, R., Andras, P., & Ploetz, T. (2013, September). On preserving statistical characteristics of accelerometry data using their empirical cumulative distribution. Presented at UbiComp '13: The 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing, Zurich, Switzerland

• Presentation Conference Type: Conference Paper (published)
• Conference Name: UbiComp '13: The 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing
• Start Date: Sep 8, 2013
• End Date: Sep 12, 2013
• Publication Date: 2013-09
• Deposit Date: Nov 16, 2021
• Publisher: Association for Computing Machinery (ACM)
• Pages: 65-68
• Book Title: Proceedings of the 2013 international symposium on wearable computers
• ISBN: 978-1-4503-2127-3
• DOI: https://doi.org/10.1145/2493988.2494353
• Public URL: http://researchrepository.napier.ac.uk/Output/2809291