High-Performance Indoor Localization with Full-Band GSM Fingerprints

Author

Denby, Bruce ; Oussar, Yacine ; Ahriz, Iness ; Dreyfus, Gérard

Author_Institution

Univ. Pierre et Marie Curie - Paris VI, Paris, France

fYear

2009

fDate

14-18 June 2009

Firstpage

1

Lastpage

5

Abstract

GSM trace mobile measurements are used to study indoor handset localization in an urban apartment setting. Nearest-neighbor, support vector machine (SVM), and Gaussian process classifiers are compared. A linear SVM is found to provide mean room-level classification efficiency near 100%, but only when the full set of GSM carriers is used. To our knowledge, this is the first study to use fingerprints containing all GSM carriers, and the first to suggest that GSM could be useful for very high-performance indoor localization.

Keywords

cellular radio; indoor radio; GSM trace mobile measurement; Gaussian process classifiers; full-band GSM fingerprint; high-performance indoor localization; indoor handset localization; mean room-level classification efficiency; support vector machine; urban apartment setting; Databases; Fingerprint recognition; GSM; Global Positioning System; Nuclear magnetic resonance; Position measurement; Support vector machine classification; Support vector machines; Telephone sets; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Communications Workshops, 2009. ICC Workshops 2009. IEEE International Conference on

Conference_Location

Dresden

Print_ISBN

978-1-4244-3437-4

Type

conf

DOI

10.1109/ICCW.2009.5207991

Filename

5207991