A pinboard by
Luca Bedogni

Post Doc, University of Bologna


Leveraging on mobile devices as smartphones to infer actions, context and neighbors of human beings

Mobile devices are becoming part of everyone daily lifes. Thanks to them, human beings are able to access to a plethora of different applications, enhancing their daily life. Several of these applications rely on the so called context of the human being, which can be the location, the people in the same area or listening to the same music, or even playing the same game.

For instance, navigation applications are useless if they can't have access to the location of the user. Transportation mode detection techniques, a niche of context aware computing, allows you to track the activities you do in a day, training and counting calories and distances traveled. Popular applications such as Spotify also exploit this information, by providing suitable music depending on the running pace you are keeping.

Of course, knowing the context might also pose threats on the privacy and eventually security of the user. Following the previous example, knowing that someone is running, and knowing the location, might encourage burglars to enter her or his home, as it is currently empty. Hence, it is fundamental to understand which information and to whom.

In my research, I tackle both these challenges. At first, I study and develop new algorithms that infer part of the context of a human being. In particular, I have been active in the last year in activity recognition, which like transportation mode detection, infer the activity a human being is doing. This has application also in e-health applications, to understand whether a human being is correctly performing an activity such as climbing stairs, walking or running, typically after an injury or surgery.

Moreover, I also study the so called minimum set of needed information, that is, the amount of data the algorithms need in order to understand the context. In fact, a well designed algorithm is not only the one that correctly assess the action of the user, but also that which do not request data in excess to infer the action.


The role of social interaction on users motivation to exercise: A persuasive web framework to enhance the self-management of a healthy lifestyle

Abstract: The current research guidelines of the European community suggest the importance of the development of systems that help users manage their health themselves. The increasing amount of communication technologies and devices from which users can access information, and the possibility to interact through social media channels, play an important role in this scenario. Based on these considerations, in this paper we present an innovative persuasive web application, designed both to exploit social networking sites and to cooperate with a mobile application that already operates in the e-health and motivational domains. In particular, the innovative aspects introduced by the web application are the possibility to access also from a web browser some features previously available only through a mobile application and a more direct and user-friendly integration of social network sites. Indeed, thanks to an extensive interaction with the Facebook social network, users are allowed to share their experience with the application. This generates a strong social influence effect, which inspires and motivates other users to improve their exercising activity. Experimental results put in evidence that our web application, also thanks to social interactions, is favoring an enhancement of users’ motivation to a more active lifestyle. This is mainly due to its capability to have an impact on the other users thanks to the posts generated on the Facebook social network.

Pub.: 04 Sep '16, Pinned: 28 Jul '17