From the experience of the Trentino Open Living Data (TOLD) project, SKIL Lab, in collaboration with Politecnico di Milano, is developing CitySensing, a platform for the management of large events in urban areas based on social media and mobile network Big Data Streams. The platform, by the means of a dashboard, enable the monitoring of venues providing insights such as the estimation of presence, the socio-demographic distribution, the provenience, the arguments of interest, the sentiment, etc. The platform has been deployed in several settings in Italy, such as the Design Week event in Milan (see citysensing.fuorisalone.it) and will be the basis for future geo-referenced big data services for the public administration.
The Mobile Territorial Lab (MTL) project has been created by Telecom Italia SKIL Lab, in cooperation with Telefónica I+D, the Human Dynamics group at MIT Media Lab, the Institute for Data Driven Design (ID³) and Fondazione Bruno Kessler, and with contributions from Telecom Italia Future Center. The project aims at creating an experimental environment to push forward the research on human-behavior analysis and interaction studies of people while in mobility. MTL aims at exploiting smartphones’ sensing capabilities to unobtrusively and cost-effectively access to previously inaccessible sources of data related to daily social behavior (location, physical proximity of other devices; communication data (phone calls and SMS), movement patterns, and so on. The Mobile Territorial Lab (MTL) in Trentino is the first of a network of living labs and aims at fostering mobile phone related research activities with real people on a very responsive territory. This includes the involvement of a significant number of committed users with the goal of having a continuous and active user base to interact with and cutting down the experimentation setup costs. A continue and active user base equipped with smartphones, enabling users to access (from everywhere) online services and to collect personal or contextual information from the integrated sensors, represents a valuable and unique sample for investigating new paradigms of Personal (Big) Data management and novel Personal Data-driven services.
> Discover more on www.mobileterritoriallab.eu
Toward a new model for personal data management: from data protection to data control and exploitation
Ubiquitous sensing is nowadays reality and it has gone largely beyond the widespread adoption of smartphones among a large majority of the consumers. Ubiquitous computing, in fact, is rapidly broadening its boundaries, leveraging on continuously increasing sensing opportunities offered by modern, low-cost technologies (ranging from wearable/body sensors to smart homes, vehicles and other devices empowered with rich sensing capabilities). These leaded to the generation and collection of a previously unimaginable quantity and variety of Personal Data (PD), which have enriched everyone’s digital footprint and has become the core of digital services and mobile applications. Smartphones capabilities of collecting contextual information and of ensuring connection to the network while in mobility, moreover, has further pushed the success of social networks applications andthe digitalization of business/personal services, chich have resulted in a tremendous and continuous production of PD.
Quantify yourself – The objective of this PhD grant is investigating the needs,
In the last years wearable (sensors, such as wristbands, clocks, etc.) shown among the technologies which have experienced the higher increase of attention and expectations, both in terms of applicative domains and impact on user life. Moreover they witnessed a fast and significant growth under many perspective: in terms of production (variety of producers, sensors, features and associated algorithms), in terms of adoption and diffusion, in terms of quality and potentials improvements.
The project aims at studying analytical methods that enable the understanding of individual behavior and indicators emerging from personal and Big Data.
Anomaly detection is a critical step in order to get a better understanding of complex systems and gather insights about them. The topic becomes even more interesting and challenging when the anomaly has to be detected in real-time on data streams that have different provenance. The state of the art is rich of effective solutions applicable when data is homogenous and “at-rest”, but it lacks solutions for heterogeneous data “in-motion”.