Extracting Significant Mobile Phone Interaction Patterns Based on Community Structures

Document Type

Article

Publication Date

3-1-2019

Abstract

Mobile phones have emerged as an essential part of people's lives. The data produced from them can be utilized to derive the spatio-temporal information of their users' whereabouts. We can obtain a rich data set of human activities, interactions, social relationships, and mobility. Hence, it has been possible to explore these information sources with applications ranging from disaster management to disease epidemiology. In this paper, we have focused on the use of call detail records to explore and interpret patterns embedded in interaction flows of people through their mobile phone calls. To do so, we consider the geographical context of subscribers/celltowers to discover structures of spatio-temporal interactions and communities' patterns in Macau. We have explored the inter and intra-polygon interaction flows. The results suggest that subscribers tend to communicate within a spatial-proximity community. In order to delineate relatively contiguous objects with similar attribute values, we have implemented an efficient hierarchical clustering approach. By identifying key objects and their close associates and exploring their communication patterns, we can detect shared interests and dominant interactions that influence societal patterns. Such insight is useful for resource optimization in network planning, content distribution, and urban planning.

Identifier

85059111401 (Scopus)

Publication Title

IEEE Transactions on Intelligent Transportation Systems

External Full Text Location

https://doi.org/10.1109/TITS.2018.2836800

ISSN

15249050

First Page

1031

Last Page

1041

Issue

3

Volume

20

Grant

119/2014/A3

Fund Ref

Fundo para o Desenvolvimento das Ciências e da Tecnologia

This document is currently not available here.

Share

COinS