Group affiliation detection in a challenging environment

Forskningsoutput: Kapitel i bok/rapport/Conference proceedingKonferenspaper i proceeding


Social interaction sensing and indoor positioning using are widely researched. However, many use cases only need to determine proximity, and not the exact location. In this paper, we describe two methods to determine which meeting each user is participating in using proximity data collected from a challenging real-world office.
We show that the RSSI threshold approach to detecting proximity is not feasible due to the optimal RSSI range being very small. Instead, we achieve an F-score of 82% with a simple method, k-nearest neighbor classification, using data from the whole population. This method does not need any historical data or training, calibration to an environment, nor find a specific RSSI threshold. Finally, we present result from a user study with a prototype meeting application that identifies meeting participants, and advice on consequences of the above result for UI design.


Enheter & grupper

Ämnesklassifikation (UKÄ) – OBLIGATORISK

  • Datavetenskap (datalogi)
Titel på värdpublikationThe 5th International Symposium on Emerging Information, Communication and Networks
FörlagElsevier Limited
StatusPublished - 2018
Peer review utfördJa

Relaterad forskningsoutput

Jonsson, H., 2018 jun 15, Lund: Computer Science, Lund University. 140 s.

Forskningsoutput: AvhandlingDoktorsavhandling (sammanläggning)

Visa alla (1)

Related projects

Johan Åkesson, Boris Magnusson, David Svensson Fors, Eva Magnusson, Görel Hedin, Krzysztof Kuchcinski, Per Andersson, Pierre Nugues, Sven Robertz, Torbjörn Ekman, Annabella Loconsole, Alma Orucevic-Alagic, Björn A Johnsson, Dietmar Pfahl, Elizabeth Bjarnason, Emma Söderberg, Giedré Sabaliauskaité, Håkan Jonsson, Jörn Janneck, Krzysztof Wnuk, Markus Borg, Mats Skoglund, Sardar Muhammad Sulaman, Sten Minör, Thomas Sandholm, Günter Alce, Mattias Wallergård, Chenxin Zhang, Sebastian Barney, Jan Kasper Martinsen, Håkan Grahn, Samireh Jalali, Anders Ardö, Emelie Engström, Richard Berntsson Svensson, Björn Regnell, Per Runeson, Claes Wohlin, Martin Höst & Jonas Wisbrant


Projekt: Forskning

Visa alla (1)