Modified Random Forest algorithm for Wi-Fi Indoor Localization System

Rafał Górak , Marcin Luckner

Abstract

The paper presents a modification of Random Forest approach to the indoor localization problem. The localization solution is based on RSS (Received Signal Strength) from multiple sources of Wi–Fi signal. We analyze two localization models. The first one is built using a straightforward application of a random forest method. The second model is a combination of localization models built for each Access Point from the building’s network using similar technique (Random Forests) as for the first model. The modification proposed in the second model gives us a substantial accuracy improvement when compared to the first model. We test also the solution against a network malfunction when some Access Points are turned off as the malfunction immunity is another important feature of the presented localization solution.
Author Rafał Górak ZPG
Rafał Górak,,
- Department of Foundations Geometry
, Marcin Luckner ZSMPW
Marcin Luckner,,
- Department of Structural Methods for Knowledge Processing
Pages147-157
Publication size in sheets0.5
Book Nguyen Ngoc Thanh, Lazaros Iliadis, Manolopoulos Yannis, Trawiński Bogdan (eds.): Computational Collective Intelligence, Lecture Notes in Artificial Intelligence, vol. 9876, 2016, SPRINGER-VERLAG BERLIN, ISBN 978-3-319-45245-6, [978-3-319-45246-3]
Keywords in EnglishIndoor Localisation, Fingerprinting, Wi-Fi Localisation, Mobile Computing
Abstract in PolishW pracy zaproponowano odmienny model lokalizacji za pomocą lasów losowych. Dla każdego źródła sygnałów tworzony jest nowy klasyfikator, a decyzja o lokalizacji jest uśrednioną decyzją wszystkich klasyfikatorów. Klasyfikatory dla których nie odnotowano sygnału są wyłączone z głosowania. System poprawia wyniki klasyfikatora, zwłaszcza w przypadku gdy sieć uległa uszkodzeniu.
DOIDOI:10.1007/978-3-319-45246-3_14
URL http://link.springer.com/chapter/10.1007%2F978-3-319-45246-3_14
Languageen angielski
Score (nominal)15
ScoreMinisterial score = 15.0, 26-06-2017, BookChapterSeriesAndMatConf
Ministerial score (2013-2016) = 15.0, 26-06-2017, BookChapterSeriesAndMatConf
Citation count*0
Cite
Share Share

Get link to the record
msginfo.png


* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.
Back