Modern Earth Observation systems provide remote sensing data at different temporal and spatial resolutions. Among all the available spatial mission, today the Sentinel-2 program supplies high temporal (every five days) and high spatial resolution (HSR) (10 m) images that can be useful to monitor land cover dynamics. On the other hand, very HSR (VHSR) imagery is still essential to figure out land cover mapping characterized by fine spatial patterns. Understanding how to jointly leverage these complementary sources in an efficient way when dealing with land cover mapping is a current challenge in remote sensing. With the aim of providing land cover mapping through the fusion of multitemporal HSR and VHSR satellite images, we propose a suitable end-to-end deep learning framework, namely $M^3\text{Fusion}$ , which is able to simultaneously leverage the temporal knowledge contained in time series data as well as the fine spatial information available in VHSR images. Experiments carried out on the Reunion Island study area confirm the quality of our proposal considering both quantitative and qualitative aspects.

Clustering data described by categorical attributes is a challenging task in data mining applications. Unlike numerical attributes, it is difficult to define a distance between pairs of values of a categorical attribute, since the values are not ordered. In this article, we propose a framework to learn a context-based distance for categorical attributes. The key intuition of this work is that the distance between two values of a categorical attribute A _i can be determined by the way in which the values of the other attributes A _j are distributed in the dataset objects: if they are similarly distributed in the groups of objects in correspondence of the distinct values of A _i a low value of distance is obtained. We propose also a solution to the critical point of the choice of the attributes A _j . We validate our approach by embedding our distance learning framework in a hierarchical clustering algorithm. We applied it on various real world and synthetic datasets, both low and high-dimensional. Experimental results show that our method is competitive with respect to the state of the art of categorical data clustering approaches. We also show that our approach is scalable and has a low impact on the overall computational time of a clustering task.

In this paper, we address the problem of enhancing young people's awareness of the mechanisms involving privacy in online social networks by presenting an innovative approach based on gamification. In particular, we propose a web application that allows kids and teenagers to experience the typical dynamics of information spread through a realistic interactive simulation. Under the supervision of the teacher, the students are inserted in a small artificial social graph, and, through the different stages of game, they can post sentences with different levels of sensitivity, and "like" or share messages published by friends. At the end of game session, the application calculate multiple behavioral scores, that can be used by the teacher to raise the curiosity of the students and stimulate discussions. Moreover, a complete interactive report is generated to analyze every individual action of the terminated game sessions. Our educational tool has been employed within an extensive experimental study involving more than 450 kids and 22 teachers in seven Italian primary school institutes. The results show that our approach is stimulating and supports teachers in helping kids discover and recognize potential privacy risks in social network activities.

Satellite image time series (SITS) collected by modern Earth Observation (EO) systems represent a valuable source of information that supports several tasks related to the monitoring of the Earth surface dynamics over large areas. A main challenge is then to design methods able to leverage the complementarity between the temporal dynamics and the spatial patterns that characterize these data structures. Focusing on land cover classification (or mapping) tasks, the majority of approaches dealing with SITS data only considers the temporal dimension, while the integration of the spatial context is frequently neglected. In this work, we propose an attentive spatial temporal graph convolutional neural network that exploits both spatial and temporal dimensions in SITS. Despite the fact that this neural network model is well suited to deal with spatio-temporal information, this is the first work that considers it for the analysis of SITS data. Experiments are conducted on two study areas characterized by different land cover landscapes and real-world operational constraints (i.e., limited labeled data due to acquisition costs). The results show that our model consistently outperforms all the competing methods obtaining a performance gain, in terms of F-Measure, of at least 5 points with respect to the best competing approaches on both benchmarks.