Giovanni Cuffaro

Federica Paganelli, Georgios Mylonas, Giovanni Cuffaro et al.

Raising awareness among young people, and especially students, on the relevance of behavior change for achieving energy savings is increasingly being considered as a key enabler towards long-term and cost-effective energy efficiency policies. However, the way to successfully apply educational interventions focused on such targets inside schools is still an open question. In this paper, we present our approach for enabling IoT-based energy savings and sustainability awareness lectures and promoting data-driven energy-saving behaviors focused on a high school audience. We present our experiences toward the successful application of sets of educational tools and software over a real-world Internet of Things (IoT) deployment. We discuss the use of gamification and competition as a very effective end-user engagement mechanism for school audiences. We also present the design of an IoT-based hands-on lab activity, integrated within a high school computer science curricula utilizing IoT devices and data produced inside the school building, along with the Node-RED platform. We describe the tools used, the organization of the educational activities and related goals. We report on the experience carried out in both directions in a high school in Italy and conclude by discussing the results in terms of achieved energy savings within an observation period.

Giovanni Cuffaro, Federico Becattini, Claudio Baecchi et al.

In this paper we present a simple yet effective approach to extend without supervision any object proposal from static images to videos. Unlike previous methods, these spatio-temporal proposals, to which we refer as tracks, are generated relying on little or no visual content by only exploiting bounding boxes spatial correlations through time. The tracks that we obtain are likely to represent objects and are a general-purpose tool to represent meaningful video content for a wide variety of tasks. For unannotated videos, tracks can be used to discover content without any supervision. As further contribution we also propose a novel and dataset-independent method to evaluate a generic object proposal based on the entropy of a classifier output response. We experiment on two competitive datasets, namely YouTube Objects and ILSVRC-2015 VID.