We present a methodology to automatically identify users’ relevant places from cellular network data.1 In this work we used anonymized Call Detail Record (CDR) comprising information on where and when users access the cellular network. The key idea is to effectively cluster CDRs together and to weigh clusters to determine those associated to frequented places. The approach can identify users’ home and work locations as well as other places (e.g., associated to leisure and night life). We evaluated our approach threefold: (i) on the basis of groundtruth information coming from a fraction of users whose relevant places were known, (ii) by comparing the resulting number of inhabitants of a given city with the number of inhabitants as extracted by the national census. (iii) Via stability analysis to verify the consistency of the extracted results across multiple time periods. Results show the effectiveness of our approach with an average 90% precision and recall.

Automatic identification of relevant places from cellular network data / Mamei, Marco; Colonna, Massimo; Galassi, Marco. - In: PERVASIVE AND MOBILE COMPUTING. - ISSN 1574-1192. - STAMPA. - 31:(2016), pp. 147-158. [10.1016/j.pmcj.2016.01.009]

Automatic identification of relevant places from cellular network data

MAMEI, Marco;GALASSI, MARCO
2016

Abstract

We present a methodology to automatically identify users’ relevant places from cellular network data.1 In this work we used anonymized Call Detail Record (CDR) comprising information on where and when users access the cellular network. The key idea is to effectively cluster CDRs together and to weigh clusters to determine those associated to frequented places. The approach can identify users’ home and work locations as well as other places (e.g., associated to leisure and night life). We evaluated our approach threefold: (i) on the basis of groundtruth information coming from a fraction of users whose relevant places were known, (ii) by comparing the resulting number of inhabitants of a given city with the number of inhabitants as extracted by the national census. (iii) Via stability analysis to verify the consistency of the extracted results across multiple time periods. Results show the effectiveness of our approach with an average 90% precision and recall.
2016
31
147
158
Automatic identification of relevant places from cellular network data / Mamei, Marco; Colonna, Massimo; Galassi, Marco. - In: PERVASIVE AND MOBILE COMPUTING. - ISSN 1574-1192. - STAMPA. - 31:(2016), pp. 147-158. [10.1016/j.pmcj.2016.01.009]
Mamei, Marco; Colonna, Massimo; Galassi, Marco
File in questo prodotto:
File Dimensione Formato  
userPlacesPMC - R2.pdf

Open access

Tipologia: Versione dell'autore revisionata e accettata per la pubblicazione
Dimensione 1.07 MB
Formato Adobe PDF
1.07 MB Adobe PDF Visualizza/Apri
VQR_1-s2.0-S1574119216000213-main(2).pdf

Open access

Tipologia: Versione pubblicata dall'editore
Dimensione 1.28 MB
Formato Adobe PDF
1.28 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11380/1116624
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 15
  • ???jsp.display-item.citation.isi??? 12
social impact