Mobile phones have an unprecedented rate of penetration across the world. Such devices produce a large amount of data that have been used on different domains. In this work, we make use of mobile calls to monitor the presence of individuals region by region. Traditionally, this activity has been conducted by means of censuses and surveys. Nowadays, technologies open new possibilities to analyse the individual calling behaviour to determine the amount of residents, commuters and visitors moving in an area. To this end, in this paper we provide a clustering technique completely unsupervised able to cluster data by exploring an arbitrary similarity metric. We make use of such technique, and we define metric to analyse mobile calls and individual profiles. The approach provides better population estimation with respect to state of the art when results are compared with real census data and greatly improves the execution time of a previous work of some of the authors of this paper. The scalability and flexibility of the proposed framework enables novel scenarios for the characterization of people by means of data derived from mobile users, ranging from the nearly real-time estimation of presences to the definition of complex, uncommon user archetypes.

Scalable and flexible clustering solutions for mobile phone based population indicators

Lulli, Alessandro;Dazzi, Patrizio;Ricci, Laura Emilia Maria
2017-01-01

Abstract

Mobile phones have an unprecedented rate of penetration across the world. Such devices produce a large amount of data that have been used on different domains. In this work, we make use of mobile calls to monitor the presence of individuals region by region. Traditionally, this activity has been conducted by means of censuses and surveys. Nowadays, technologies open new possibilities to analyse the individual calling behaviour to determine the amount of residents, commuters and visitors moving in an area. To this end, in this paper we provide a clustering technique completely unsupervised able to cluster data by exploring an arbitrary similarity metric. We make use of such technique, and we define metric to analyse mobile calls and individual profiles. The approach provides better population estimation with respect to state of the art when results are compared with real census data and greatly improves the execution time of a previous work of some of the authors of this paper. The scalability and flexibility of the proposed framework enables novel scenarios for the characterization of people by means of data derived from mobile users, ranging from the nearly real-time estimation of presences to the definition of complex, uncommon user archetypes.
2017
Lulli, Alessandro; Gabrielli, Lorenzo; Dazzi, Patrizio; Dell’Amico, Matteo; Michiardi, Pietro; Nanni, Mirco; Ricci, Laura Emilia Maria
File in questo prodotto:
Non ci sono file associati a questo prodotto.

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/11568/892080
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 6
  • ???jsp.display-item.citation.isi??? ND
social impact