Ecole d'ingénieur et centre de recherche en Sciences du numérique

Improving population estimation from mobile calls: a clustering approach

Dazzi, Patrizio; Dell'Amico, Matteo; Gabrielli, Lorenzo; Lulli, Alessandro; Michiardi, Pietro; Nanni, Mirco; Ricci, Laura

ISCC 2016, 21st IEEE Symposium on Computers and Communications, June 27-30, 2016, Messina, Italy

Statistical authorities promote and safeguard the production and publication of official statistics that serve the public good. One of their duties is 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 such as a continuous sensing of the presences by leveraging the data associated to mobile devices, e.g., the behaviour of users on doing calls. In this paper first we propose a specifically conceived similarity function able to capture similarity between individuals call behaviours. Second we make use of a clustering algorithm able to handle arbitrary metric leading to a good internal and external consistency of clusters. The approach provides better population estimation with respect to state of the art comparing with real census data. The scalability and flexibility that characterises the proposed framework enables novel scenarios for the characterization of people by means of data derived from mobile users, ranging from the nearly-realtime estimation of presences to the definition of complex, uncommon user archetypes.

Document Doi Bibtex

Titre:Improving population estimation from mobile calls: a clustering approach
Type:Conférence
Langue:English
Ville:Messina
Pays:ITALIE
Date:
Département:Data Science
Eurecom ref:4958
Copyright: © 2016 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Bibtex: @inproceedings{EURECOM+4958, doi = {http://dx.doi.org/10.1109/ISCC.2016.7543882}, year = {2016}, title = {{I}mproving population estimation from mobile calls: a clustering approach}, author = {{D}azzi, {P}atrizio and {D}ell'{A}mico, {M}atteo and {G}abrielli, {L}orenzo and {L}ulli, {A}lessandro and {M}ichiardi, {P}ietro and {N}anni, {M}irco and {R}icci, {L}aura}, booktitle = {{ISCC} 2016, 21st {IEEE} {S}ymposium on {C}omputers and {C}ommunications, {J}une 27-30, 2016, {M}essina, {I}taly}, address = {{M}essina, {ITALIE}}, month = {06}, url = {http://www.eurecom.fr/publication/4958} }
Voir aussi: