The growing interest in concepts such as smart cities and smart mobility is giving more and more importance to place of interest (POI) information, which proves to be crucial in providing efficient and tailored location-based services (LBSs). Though plenty of solutions exist for recognizing indoor places, the literature lacks of approaches aimed at recognizing big outdoor places without the GPS employment. Even if GPS-based solutions assure great accuracy, they have a strong request in terms of energy necessary to achieve such result. As a consequence, if LBSs are thought on the move (e.g., mobile devices such as smartphones are used) energy consumption is a key constraint. This paper proposes a POI recognition algorithm called enhanced location recognition algorithm for automatic check-in applications (E-LRACI). It is an evolution of LRACI (Location Recognition Algorithm for automatic Check-In applications, originally reported in [I. Bisio, F. Lavagetto, M. Marchese, and A. Sciarrone, ''GPS/HPS-andwifi fingerprint-based location recognition for check-in applications over smartphones in cloud-based LBSS,'' IEEE Transactions on Multimedia, vol. 15, no. 4, pp. 858-869, Jun. 2013]) which aims at recognizing big outdoor places by only exploiting radio beacons emitted by WiFi access points. In terms of contributions, this paper first, proposes a novel fingerprint algorithm; second, solves the problem of big outdoor POI recognition without using GPS by leveraging the concept of spot; and third, compares the results obtained by E-LRACI and other reference works both in terms of recognition accuracy and computational complexity. The obtained numerical results, carried out on real data (acquired with Android-based smartphones), prove that E-LRACI provides the best results since it is able to guarantee the highest accuracy (95% versus, at most, 89%) at a lowest computational complexity with respect to the existing POI recognition algorithms.

Outdoor Places of Interest Recognition Using WiFi Fingerprints

Bisio I.;Garibotto C.;Lavagetto F.;Sciarrone A.
2019-01-01

Abstract

The growing interest in concepts such as smart cities and smart mobility is giving more and more importance to place of interest (POI) information, which proves to be crucial in providing efficient and tailored location-based services (LBSs). Though plenty of solutions exist for recognizing indoor places, the literature lacks of approaches aimed at recognizing big outdoor places without the GPS employment. Even if GPS-based solutions assure great accuracy, they have a strong request in terms of energy necessary to achieve such result. As a consequence, if LBSs are thought on the move (e.g., mobile devices such as smartphones are used) energy consumption is a key constraint. This paper proposes a POI recognition algorithm called enhanced location recognition algorithm for automatic check-in applications (E-LRACI). It is an evolution of LRACI (Location Recognition Algorithm for automatic Check-In applications, originally reported in [I. Bisio, F. Lavagetto, M. Marchese, and A. Sciarrone, ''GPS/HPS-andwifi fingerprint-based location recognition for check-in applications over smartphones in cloud-based LBSS,'' IEEE Transactions on Multimedia, vol. 15, no. 4, pp. 858-869, Jun. 2013]) which aims at recognizing big outdoor places by only exploiting radio beacons emitted by WiFi access points. In terms of contributions, this paper first, proposes a novel fingerprint algorithm; second, solves the problem of big outdoor POI recognition without using GPS by leveraging the concept of spot; and third, compares the results obtained by E-LRACI and other reference works both in terms of recognition accuracy and computational complexity. The obtained numerical results, carried out on real data (acquired with Android-based smartphones), prove that E-LRACI provides the best results since it is able to guarantee the highest accuracy (95% versus, at most, 89%) at a lowest computational complexity with respect to the existing POI recognition algorithms.
File in questo prodotto:
File Dimensione Formato  
08667655.pdf

accesso chiuso

Tipologia: Documento in versione editoriale
Dimensione 2.1 MB
Formato Adobe PDF
2.1 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11567/947551
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 18
  • ???jsp.display-item.citation.isi??? 15
social impact