Beitrag in einem Tagungsband
Distances for WiFi Based Topological Indoor Mapping
Details zur Publikation
Autor(inn)en: | Schäfermeier, B.; Hanika, T.; Stumme, G. |
Herausgeber: | ACM |
Verlagsort / Veröffentlichungsort: | New York |
Publikationsjahr: | 2018 |
Zeitschrift: | Tohoku Mathematical Journal |
Seitenbereich: | 308-3017 |
Buchtitel: | MobiQuitous '19: Proceedings of the 16th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services |
Abkürzung der Fachzeitschrift: | TMJ |
ISBN: | 978-1-4503-7283-1 |
ISSN: | 0040-8735 |
DOI-Link der Erstveröffentlichung: |
Zusammenfassung, Abstract
For localization and mapping of indoor environments through WiFi signals, locations are often represented as likelihoods of the received signal strength indicator. In this work we compare various measures of distance between such likelihoods in combination with different methods for estimation and representation. In particular, we show that among the considered distance measures the Earth Mover's Distance seems the most beneficial for the localization task. Combined with kernel density estimation we were able to retain the topological structure of rooms in a real-world office scenario.
For localization and mapping of indoor environments through WiFi signals, locations are often represented as likelihoods of the received signal strength indicator. In this work we compare various measures of distance between such likelihoods in combination with different methods for estimation and representation. In particular, we show that among the considered distance measures the Earth Mover's Distance seems the most beneficial for the localization task. Combined with kernel density estimation we were able to retain the topological structure of rooms in a real-world office scenario.
Schlagwörter
2018 equivalence kde localization myown navigation preprint publist wifi
