News‎ > ‎

Pervasive people-centric sensing to infer about individual and collective behaviour

posted Jul 1, 2016, 7:45 AM by Paulo Mendes   [ updated Jan 26, 2017, 6:05 AM ]

Pervasive computing has been mostly used to build systems encompassing a small number of devices that interact with single users or small groups. As technology becomes truly pervasive, low-cost sensing systems may be built and easily deployed based on diverse sensing devices, such as mobile phones, which are carried by a large number of people, as well as embedded systems that can be integrated into self-propelled sensing

The CitySense project aims to develop a pervasive sensing system able to infer about individual behaviour (e.g. avoid social isolation, children protection), as well as collective behaviour (e.g. crowd control, detection of human swarms, urban sensing).

This project is a joint effort developed by COPELABS and Senception Lda.

In the context of promoting well-being several eHealth applications have been focused on tracking activities, such as sleep or specific fitness habits, with the purpose of promoting physical well-being with increasing success. Sensing technology can, however, be applied to improve social well-being, in addition to physical well-being. NSense has been developed within the CitySense project to capture and to infer social interaction patterns aiming to assist in the promotion of social well-being. Experiments carried out under realistic settings validate the NSense performance in terms of its capability to infer social interaction context based on our proposed computational utility functions. Traces obtained during the experiments are available via the CRAWDAD international trace repository.

Major References
  • Rute C. Sofia, Saeik Firdose, Luis Lopes, Waldir Moreira, Pallavali Reddy, and Paulo Mendes, "NSense:  A People-centric, non-intrusive Opportunistic Sensing Tool for Contextualizing Social Interaction" (short version under submission, June 2016).