Research Article
A Study on the Impact of Indoor Positioning Performance on Activity Recognition Applications
@INPROCEEDINGS{10.4108/eai.7-11-2017.2273779, author={Andreas Mathisen and S\`{u}ren S\`{u}rensen and Allan Stisen and Henrik Blunck and Kaj Gr\`{u}nb\c{c}k}, title={A Study on the Impact of Indoor Positioning Performance on Activity Recognition Applications}, proceedings={14th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services}, publisher={ACM}, proceedings_a={MOBIQUITOUS}, year={2018}, month={4}, keywords={human activity recognition indoor positioning empirical studies}, doi={10.4108/eai.7-11-2017.2273779} }- Andreas Mathisen
Søren Sørensen
Allan Stisen
Henrik Blunck
Kaj Grønbæk
Year: 2018
A Study on the Impact of Indoor Positioning Performance on Activity Recognition Applications
MOBIQUITOUS
ACM
DOI: 10.4108/eai.7-11-2017.2273779
Abstract
Due to substantial research in indoor positioning a vast amount of location technologies and algorithms are available to enable various applications. However, it is challenging knowing which positioning system is optimal, or sufficient, for a specific application - not only when considering development and maintenance costs, but also the potential impact of the positioning system’s performance on the respective application’s performance.
In this paper, we present an evaluation of how positioning performance affects two chosen real-world applications at a 160, 000m2 hospital building complex using an existing WiFi system as primary sensing infrastructure. While a multitude of positioning applications are run at the hospital, we focused on two applications within human activity recognition (HAR). HAR is an application area of positioning where the impacts are indirect and challenging to predict, therefore motivating this type of investigation yet underrepresented in the literature.
Our evaluation includes several WiFi based indoor positioning system variants and investigates the impact of their respective performances on the two HAR applications. Among others, our evaluation shows that positioning accuracy is not the only performance measure important to consider, and that it has a surprisingly small impact on the applications’ performance - suggesting that the increased costs for a higher-accuracy positioning system often do not yield the anticipated returns.