Authors:
Muawya Habib Sarnoub Eldaw
;
Mark Levene
and
George Roussos
Affiliation:
Birkbeck and University of London, United Kingdom
Keyword(s):
Presence Analytics, Density-based Clustering, Social-DBSCAN, WLAN Traces, Wireless Network Traces, Eduroam, Social Groups, Class Attendance, Human Presence, Learning Activity, Mobile Data, Mobile Users.
Abstract:
We demonstrate how social density-based clustering of WLAN traces can be utilised to detect granular social
groups of mobile users within a university campus. Furthermore, the ability to detect such social groups, which
can be linked to the learning activities taking place at target locations, provides an invaluable opportunity to
understand the presence and movement of people within such an environment. For example, the proposed
density-based clustering procedure, which we call Social-DBSCAN, has real potential to support human mobility
studies such as the optimisation of space usage strategies. It can automatically detect the academic term
period, the classes, and the attendance data. From a large Eduroam log of an academic site, we chose as a
proof concept, selected locations with known capacity for the evaluation of our proposed method, which we
successfully utilise to detect the regular learning activities at those locations, and to provide accurate estimates
about the attendanc
e levels over the academic term period.
(More)