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
devices. Large-scale sensing systems may support a diverse set of applications, mostly related to urban
scenarios, from predicting traffic jams and modelling human activities, social interactions and mobility patterns, to community health tracking and city environmental monitoring.

Recent research efforts aim to make large-scale sensing a reality by leveraging the increasing sensing
capabilities found in personal devices such as cell phones. Architectural challenges include methods for
accurate sensing, context extraction, inference and sharing data, as well as protecting the privacy of involved
people. Placing people at the centre of the sensing system implies, first or all that owners of personal sensing
devices should keep the desirable level of user experience. Therefore, sensing systems should ensure that
owners of sensorial devices are agnostic of any sensing activity, to ensure the desirable adoption rate.
Opportunistic sensing ensures that the owner of sensorial devices remain agnostic of any sensorial activity:
the device is activated whenever its state matches the requirements of a sensing application, and the latter
does not have an impact on user experience. However, opportunistic sensing occurs without user intervention
and may be required to infer about complex activities. Hence, a major challenge is the correlation of contextual conditions and personal characteristics (e.g. age and lifestyle) encountered in large-scale mobile sensing systems, as well as the integration of multiple data representing the same real-world activity into a consistent, accurate, and useful representation.
Current approaches to opportunistic sensing focus on the usage of personal sensing devices, such as smart
phones, to infer about individual activities. However, the major impact of large-scale sensing systems is
expected to be in the inference about group, communities or swarm behaviour. For instance, the automatic
recognition of the density of human gathering and the direction of movement of is relevant for many

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.


CitySense considers three main use-cases which have been thoroughly described in Deliverable D1 - Use-cases and Problem Space. This section provides a summary of such use-cases.

Elderly Social Stimulation

Older people are particularly vulnerable to social isolation and loneliness owing to loss of friends and family, mobility or income. Social isolation and loneliness have a detrimental effect on health and wellbeing. The impact of loneliness and social isolation on an individual’s health and wellbeing has cost implications for health and social care services. It is necessary to help alleviating loneliness and improve the quality of life of older people, reducing dependence on more costly services.

Within this use-case the CitySense project aims to improve life experience among elderly people by focusing on group services and wider community engagement. To achieve such goal the proposed CitySense framework aims to support:

  • Detection of social isolation, aiming to to trigger alerts and actions.
  • Detection of common interests and behavior to stimulate social interaction.

Cooperative Mobility

Personal mobility is key to the success and prosperity of every country's economy. But the growing population and the increasing amount of traffic are mitigating human quality of life in urban areas. The answer to the problem of increasing passenger transportation lies with cooperative mobility systems: aims to create cooperation amongst drivers, passengers and pedestrian to create a stress free mobility experiment in urban scenarios.

In this use-case the CitySense project aims to understand how accurate measures about people daily habits correlated with open data about transportation will improve quality of life by reducing stress, based on:

  • Identification of the citizen's daily activities in a non-intrusive way.
  • Identification of roaming routines: mobility profiles of participants are annotated with contextual information, such as transportation modality and activity state.
  • Prediction of people's mobility and needs of transportation.

Small Trusted Citizen Communities

Within the context of trusted spheres, e.g. family or affiliation, there is a series of services that can be improved to assist the citizen daily routines. In this context, CitySense expects to explore the potential of small controlled, trusted spheres, to estimate potential applicability. This aspect is being addressed in cooperation with Senception Lda.